diff options
| author | Tvrtko Ursulin | 2025-02-05 09:29:14 +0000 |
|---|---|---|
| committer | Tvrtko Ursulin | 2025-02-05 09:29:14 +0000 |
| commit | c771600c6af14749609b49565ffb4cac2959710d (patch) | |
| tree | e9be426f1b32598527127fd0fa1b265a7cc83044 /include/linux | |
| parent | 4a82ceb04ad4bbb9cc20925abccb70938313e555 (diff) | |
| parent | 2014c95afecee3e76ca4a56956a936e23283f05b (diff) | |
Merge drm/drm-next into drm-intel-gt-next
We need
4ba4f1afb6a9 ("perf: Generic hotplug support for a PMU with a scope")
in order to land a i915 PMU simplification and a fix. That landed in 6.12
and we are stuck at 6.9 so lets bump things forward.
Signed-off-by: Tvrtko Ursulin <tursulin@ursulin.net>
Diffstat (limited to 'include/linux')
922 files changed, 34310 insertions, 13916 deletions
diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 34829f2c517a..4e495b29c640 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -24,6 +24,7 @@ struct irq_domain_ops; #define _LINUX #endif #include <acpi/acpi.h> +#include <acpi/acpi_numa.h> #ifdef CONFIG_ACPI @@ -35,12 +36,11 @@ struct irq_domain_ops; #include <acpi/acpi_bus.h> #include <acpi/acpi_drivers.h> -#include <acpi/acpi_numa.h> #include <acpi/acpi_io.h> #include <asm/acpi.h> #ifdef CONFIG_ACPI_TABLE_LIB -#define EXPORT_SYMBOL_ACPI_LIB(x) EXPORT_SYMBOL_NS_GPL(x, ACPI) +#define EXPORT_SYMBOL_ACPI_LIB(x) EXPORT_SYMBOL_NS_GPL(x, "ACPI") #define __init_or_acpilib #define __initdata_or_acpilib #else @@ -107,6 +107,7 @@ enum acpi_irq_model_id { ACPI_IRQ_MODEL_PLATFORM, ACPI_IRQ_MODEL_GIC, ACPI_IRQ_MODEL_LPIC, + ACPI_IRQ_MODEL_RINTC, ACPI_IRQ_MODEL_COUNT }; @@ -237,14 +238,6 @@ acpi_table_parse_cedt(enum acpi_cedt_type id, int acpi_parse_mcfg (struct acpi_table_header *header); void acpi_table_print_madt_entry (struct acpi_subtable_header *madt); -static inline bool acpi_gicc_is_usable(struct acpi_madt_generic_interrupt *gicc) -{ - return gicc->flags & ACPI_MADT_ENABLED; -} - -/* the following numa functions are architecture-dependent */ -void acpi_numa_slit_init (struct acpi_table_slit *slit); - #if defined(CONFIG_X86) || defined(CONFIG_LOONGARCH) void acpi_numa_processor_affinity_init (struct acpi_srat_cpu_affinity *pa); #else @@ -267,7 +260,11 @@ static inline void acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa) { } #endif -int acpi_numa_memory_affinity_init (struct acpi_srat_mem_affinity *ma); +#ifdef CONFIG_RISCV +void acpi_numa_rintc_affinity_init(struct acpi_srat_rintc_affinity *pa); +#else +static inline void acpi_numa_rintc_affinity_init(struct acpi_srat_rintc_affinity *pa) { } +#endif #ifndef PHYS_CPUID_INVALID typedef u32 phys_cpuid_t; @@ -284,6 +281,9 @@ static inline bool invalid_phys_cpuid(phys_cpuid_t phys_id) return phys_id == PHYS_CPUID_INVALID; } + +int __init acpi_get_madt_revision(void); + /* Validate the processor object's proc_id */ bool acpi_duplicate_processor_id(int proc_id); /* Processor _CTS control */ @@ -309,6 +309,8 @@ int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, u32 acpi_id, int acpi_unmap_cpu(int cpu); #endif /* CONFIG_ACPI_HOTPLUG_CPU */ +acpi_handle acpi_get_processor_handle(int cpu); + #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC int acpi_get_ioapic_id(acpi_handle handle, u32 gsi_base, u64 *phys_addr); #endif @@ -361,6 +363,7 @@ void acpi_unregister_gsi (u32 gsi); struct pci_dev; +struct acpi_prt_entry *acpi_pci_irq_lookup(struct pci_dev *dev, int pin); int acpi_pci_irq_enable (struct pci_dev *dev); void acpi_penalize_isa_irq(int irq, int active); bool acpi_isa_irq_available(int irq); @@ -385,7 +388,7 @@ extern bool acpi_is_pnp_device(struct acpi_device *); #if defined(CONFIG_ACPI_WMI) || defined(CONFIG_ACPI_WMI_MODULE) -typedef void (*wmi_notify_handler) (u32 value, void *context); +typedef void (*wmi_notify_handler) (union acpi_object *data, void *context); int wmi_instance_count(const char *guid); @@ -400,7 +403,6 @@ extern acpi_status wmi_set_block(const char *guid, u8 instance, extern acpi_status wmi_install_notify_handler(const char *guid, wmi_notify_handler handler, void *data); extern acpi_status wmi_remove_notify_handler(const char *guid); -extern acpi_status wmi_get_event_data(u32 event, struct acpi_buffer *out); extern bool wmi_has_guid(const char *guid); extern char *wmi_get_acpi_device_uid(const char *guid); @@ -421,7 +423,7 @@ extern char *wmi_get_acpi_device_uid(const char *guid); extern char acpi_video_backlight_string[]; extern long acpi_is_video_device(acpi_handle handle); -extern int acpi_blacklisted(void); + extern void acpi_osi_setup(char *str); extern bool acpi_osi_is_win8(void); @@ -573,10 +575,15 @@ acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context); #define OSC_SB_CPCV2_SUPPORT 0x00000040 #define OSC_SB_PCLPI_SUPPORT 0x00000080 #define OSC_SB_OSLPI_SUPPORT 0x00000100 +#define OSC_SB_FAST_THERMAL_SAMPLING_SUPPORT 0x00000200 +#define OSC_SB_OVER_16_PSTATES_SUPPORT 0x00000400 +#define OSC_SB_GED_SUPPORT 0x00000800 #define OSC_SB_CPC_DIVERSE_HIGH_SUPPORT 0x00001000 -#define OSC_SB_GENERIC_INITIATOR_SUPPORT 0x00002000 +#define OSC_SB_IRQ_RESOURCE_SOURCE_SUPPORT 0x00002000 #define OSC_SB_CPC_FLEXIBLE_ADR_SPACE 0x00004000 +#define OSC_SB_GENERIC_INITIATOR_SUPPORT 0x00020000 #define OSC_SB_NATIVE_USB4_SUPPORT 0x00040000 +#define OSC_SB_BATTERY_CHARGE_LIMITING_SUPPORT 0x00080000 #define OSC_SB_PRM_SUPPORT 0x00200000 #define OSC_SB_FFH_OPR_SUPPORT 0x00400000 @@ -762,6 +769,7 @@ static inline u64 acpi_arch_get_root_pointer(void) } #endif +int acpi_get_local_u64_address(acpi_handle handle, u64 *addr); int acpi_get_local_address(acpi_handle handle, u32 *addr); const char *acpi_get_subsystem_id(acpi_handle handle); @@ -778,8 +786,6 @@ const char *acpi_get_subsystem_id(acpi_handle handle); #define acpi_dev_uid_match(adev, uid2) (adev && false) #define acpi_dev_hid_uid_match(adev, hid2, uid2) (adev && false) -#include <acpi/acpi_numa.h> - struct fwnode_handle; static inline bool acpi_dev_found(const char *hid) @@ -848,6 +854,11 @@ static inline struct fwnode_handle *acpi_fwnode_handle(struct acpi_device *adev) return NULL; } +static inline acpi_handle acpi_device_handle(struct acpi_device *adev) +{ + return NULL; +} + static inline bool has_acpi_companion(struct device *dev) { return false; @@ -1077,6 +1088,11 @@ static inline bool acpi_sleep_state_supported(u8 sleep_state) return false; } +static inline acpi_handle acpi_get_processor_handle(int cpu) +{ + return NULL; +} + #endif /* !CONFIG_ACPI */ extern void arch_post_acpi_subsys_init(void); @@ -1153,8 +1169,6 @@ int acpi_subsys_suspend_noirq(struct device *dev); int acpi_subsys_suspend(struct device *dev); int acpi_subsys_freeze(struct device *dev); int acpi_subsys_poweroff(struct device *dev); -void acpi_ec_mark_gpe_for_wake(void); -void acpi_ec_set_gpe_wake_mask(u8 action); int acpi_subsys_restore_early(struct device *dev); #else static inline int acpi_subsys_prepare(struct device *dev) { return 0; } @@ -1165,6 +1179,12 @@ static inline int acpi_subsys_suspend(struct device *dev) { return 0; } static inline int acpi_subsys_freeze(struct device *dev) { return 0; } static inline int acpi_subsys_poweroff(struct device *dev) { return 0; } static inline int acpi_subsys_restore_early(struct device *dev) { return 0; } +#endif + +#if defined(CONFIG_ACPI_EC) && defined(CONFIG_PM_SLEEP) +void acpi_ec_mark_gpe_for_wake(void); +void acpi_ec_set_gpe_wake_mask(u8 action); +#else static inline void acpi_ec_mark_gpe_for_wake(void) {} static inline void acpi_ec_set_gpe_wake_mask(u8 action) {} #endif @@ -1233,7 +1253,7 @@ bool acpi_gpio_get_irq_resource(struct acpi_resource *ares, struct acpi_resource_gpio **agpio); bool acpi_gpio_get_io_resource(struct acpi_resource *ares, struct acpi_resource_gpio **agpio); -int acpi_dev_gpio_irq_wake_get_by(struct acpi_device *adev, const char *name, int index, +int acpi_dev_gpio_irq_wake_get_by(struct acpi_device *adev, const char *con_id, int index, bool *wake_capable); #else static inline bool acpi_gpio_get_irq_resource(struct acpi_resource *ares, @@ -1246,7 +1266,7 @@ static inline bool acpi_gpio_get_io_resource(struct acpi_resource *ares, { return false; } -static inline int acpi_dev_gpio_irq_wake_get_by(struct acpi_device *adev, const char *name, +static inline int acpi_dev_gpio_irq_wake_get_by(struct acpi_device *adev, const char *con_id, int index, bool *wake_capable) { return -ENXIO; @@ -1259,10 +1279,10 @@ static inline int acpi_dev_gpio_irq_wake_get(struct acpi_device *adev, int index return acpi_dev_gpio_irq_wake_get_by(adev, NULL, index, wake_capable); } -static inline int acpi_dev_gpio_irq_get_by(struct acpi_device *adev, const char *name, +static inline int acpi_dev_gpio_irq_get_by(struct acpi_device *adev, const char *con_id, int index) { - return acpi_dev_gpio_irq_wake_get_by(adev, name, index, NULL); + return acpi_dev_gpio_irq_wake_get_by(adev, con_id, index, NULL); } static inline int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index) @@ -1333,6 +1353,8 @@ struct acpi_probe_entry { kernel_ulong_t driver_data; }; +void arch_sort_irqchip_probe(struct acpi_probe_entry *ap_head, int nr); + #define ACPI_DECLARE_PROBE_ENTRY(table, name, table_id, subtable, \ valid, data, fn) \ static const struct acpi_probe_entry __acpi_probe_##name \ @@ -1513,11 +1535,7 @@ static inline int find_acpi_cpu_topology_hetero_id(unsigned int cpu) } #endif -#ifdef CONFIG_ARM64 -void acpi_arm_init(void); -#else -static inline void acpi_arm_init(void) { } -#endif +void acpi_arch_init(void); #ifdef CONFIG_ACPI_PCC void acpi_init_pcc(void); diff --git a/include/linux/acpi_dma.h b/include/linux/acpi_dma.h index 72cedb916a9c..e748b2877602 100644 --- a/include/linux/acpi_dma.h +++ b/include/linux/acpi_dma.h @@ -11,10 +11,11 @@ #ifndef __LINUX_ACPI_DMA_H #define __LINUX_ACPI_DMA_H -#include <linux/list.h> -#include <linux/device.h> #include <linux/err.h> #include <linux/dmaengine.h> +#include <linux/types.h> + +struct device; /** * struct acpi_dma_spec - slave device DMA resources @@ -65,7 +66,6 @@ int devm_acpi_dma_controller_register(struct device *dev, struct dma_chan *(*acpi_dma_xlate) (struct acpi_dma_spec *, struct acpi_dma *), void *data); -void devm_acpi_dma_controller_free(struct device *dev); struct dma_chan *acpi_dma_request_slave_chan_by_index(struct device *dev, size_t index); @@ -94,9 +94,6 @@ static inline int devm_acpi_dma_controller_register(struct device *dev, { return -ENODEV; } -static inline void devm_acpi_dma_controller_free(struct device *dev) -{ -} static inline struct dma_chan *acpi_dma_request_slave_chan_by_index( struct device *dev, size_t index) diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h index 1cb65592c95d..d4ed5622cf2b 100644 --- a/include/linux/acpi_iort.h +++ b/include/linux/acpi_iort.h @@ -39,7 +39,7 @@ void iort_get_rmr_sids(struct fwnode_handle *iommu_fwnode, void iort_put_rmr_sids(struct fwnode_handle *iommu_fwnode, struct list_head *head); /* IOMMU interface */ -int iort_dma_get_ranges(struct device *dev, u64 *size); +int iort_dma_get_ranges(struct device *dev, u64 *limit); int iort_iommu_configure_id(struct device *dev, const u32 *id_in); void iort_iommu_get_resv_regions(struct device *dev, struct list_head *head); phys_addr_t acpi_iort_dma_get_max_cpu_address(void); @@ -55,7 +55,7 @@ void iort_get_rmr_sids(struct fwnode_handle *iommu_fwnode, struct list_head *hea static inline void iort_put_rmr_sids(struct fwnode_handle *iommu_fwnode, struct list_head *head) { } /* IOMMU interface */ -static inline int iort_dma_get_ranges(struct device *dev, u64 *size) +static inline int iort_dma_get_ranges(struct device *dev, u64 *limit) { return -ENODEV; } static inline int iort_iommu_configure_id(struct device *dev, const u32 *id_in) { return -ENODEV; } diff --git a/include/linux/acpi_pmtmr.h b/include/linux/acpi_pmtmr.h index 50d88bf1498d..0ded9220d379 100644 --- a/include/linux/acpi_pmtmr.h +++ b/include/linux/acpi_pmtmr.h @@ -26,6 +26,19 @@ static inline u32 acpi_pm_read_early(void) return acpi_pm_read_verified() & ACPI_PM_MASK; } +/** + * Register callback for suspend and resume event + * + * @cb Callback triggered on suspend and resume + * @data Data passed with the callback + */ +void acpi_pmtmr_register_suspend_resume_callback(void (*cb)(void *data, bool suspend), void *data); + +/** + * Remove registered callback for suspend and resume event + */ +void acpi_pmtmr_unregister_suspend_resume_callback(void); + #else static inline u32 acpi_pm_read_early(void) diff --git a/include/linux/adreno-smmu-priv.h b/include/linux/adreno-smmu-priv.h index c637e0997f6d..abec23c7744f 100644 --- a/include/linux/adreno-smmu-priv.h +++ b/include/linux/adreno-smmu-priv.h @@ -50,6 +50,11 @@ struct adreno_smmu_fault_info { * the GPU driver must call resume_translation() * @resume_translation: Resume translation after a fault * + * @set_prr_bit: [optional] Configure the GPU's Partially Resident + * Region (PRR) bit in the ACTLR register. + * @set_prr_addr: [optional] Configure the PRR_CFG_*ADDR register with + * the physical address of PRR page passed from GPU + * driver. * * The GPU driver (drm/msm) and adreno-smmu work together for controlling * the GPU's SMMU instance. This is by necessity, as the GPU is directly @@ -67,6 +72,8 @@ struct adreno_smmu_priv { void (*get_fault_info)(const void *cookie, struct adreno_smmu_fault_info *info); void (*set_stall)(const void *cookie, bool enabled); void (*resume_translation)(const void *cookie, bool terminate); + void (*set_prr_bit)(const void *cookie, bool set); + void (*set_prr_addr)(const void *cookie, phys_addr_t page_addr); }; #endif /* __ADRENO_SMMU_PRIV_H */ diff --git a/include/linux/aer.h b/include/linux/aer.h index 4b97f38f3fcf..947b63091902 100644 --- a/include/linux/aer.h +++ b/include/linux/aer.h @@ -16,10 +16,18 @@ #define AER_CORRECTABLE 2 #define DPC_FATAL 3 +/* + * AER and DPC capabilities TLP Logging register sizes (PCIe r6.2, sec 7.8.4 + * & 7.9.14). + */ +#define PCIE_STD_NUM_TLP_HEADERLOG 4 +#define PCIE_STD_MAX_TLP_PREFIXLOG 4 + struct pci_dev; struct pcie_tlp_log { - u32 dw[4]; + u32 dw[PCIE_STD_NUM_TLP_HEADERLOG]; + u32 prefix[PCIE_STD_MAX_TLP_PREFIXLOG]; }; struct aer_capability_regs { @@ -37,8 +45,6 @@ struct aer_capability_regs { u16 uncor_err_source; }; -int pcie_read_tlp_log(struct pci_dev *dev, int where, struct pcie_tlp_log *log); - #if defined(CONFIG_PCIEAER) int pci_aer_clear_nonfatal_status(struct pci_dev *dev); int pcie_aer_is_native(struct pci_dev *dev); diff --git a/include/linux/alarmtimer.h b/include/linux/alarmtimer.h index 05e758b8b894..3ffa5341dce2 100644 --- a/include/linux/alarmtimer.h +++ b/include/linux/alarmtimer.h @@ -20,12 +20,6 @@ enum alarmtimer_type { ALARM_BOOTTIME_FREEZER, }; -enum alarmtimer_restart { - ALARMTIMER_NORESTART, - ALARMTIMER_RESTART, -}; - - #define ALARMTIMER_STATE_INACTIVE 0x00 #define ALARMTIMER_STATE_ENQUEUED 0x01 @@ -42,14 +36,14 @@ enum alarmtimer_restart { struct alarm { struct timerqueue_node node; struct hrtimer timer; - enum alarmtimer_restart (*function)(struct alarm *, ktime_t now); + void (*function)(struct alarm *, ktime_t now); enum alarmtimer_type type; int state; void *data; }; void alarm_init(struct alarm *alarm, enum alarmtimer_type type, - enum alarmtimer_restart (*function)(struct alarm *, ktime_t)); + void (*function)(struct alarm *, ktime_t)); void alarm_start(struct alarm *alarm, ktime_t start); void alarm_start_relative(struct alarm *alarm, ktime_t start); void alarm_restart(struct alarm *alarm); diff --git a/include/linux/alcor_pci.h b/include/linux/alcor_pci.h index c4a0b23846d8..dcb1d37dabc2 100644 --- a/include/linux/alcor_pci.h +++ b/include/linux/alcor_pci.h @@ -11,6 +11,7 @@ #define ALCOR_SD_CARD 0 #define ALCOR_MS_CARD 1 +#define DRV_NAME_ALCOR_PCI "alcor_pci" #define DRV_NAME_ALCOR_PCI_SDMMC "alcor_sdmmc" #define DRV_NAME_ALCOR_PCI_MS "alcor_ms" diff --git a/include/linux/alloc_tag.h b/include/linux/alloc_tag.h new file mode 100644 index 000000000000..a946e0203e6d --- /dev/null +++ b/include/linux/alloc_tag.h @@ -0,0 +1,244 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * allocation tagging + */ +#ifndef _LINUX_ALLOC_TAG_H +#define _LINUX_ALLOC_TAG_H + +#include <linux/bug.h> +#include <linux/codetag.h> +#include <linux/container_of.h> +#include <linux/preempt.h> +#include <asm/percpu.h> +#include <linux/cpumask.h> +#include <linux/smp.h> +#include <linux/static_key.h> +#include <linux/irqflags.h> + +struct alloc_tag_counters { + u64 bytes; + u64 calls; +}; + +/* + * An instance of this structure is created in a special ELF section at every + * allocation callsite. At runtime, the special section is treated as + * an array of these. Embedded codetag utilizes codetag framework. + */ +struct alloc_tag { + struct codetag ct; + struct alloc_tag_counters __percpu *counters; +} __aligned(8); + +struct alloc_tag_kernel_section { + struct alloc_tag *first_tag; + unsigned long count; +}; + +struct alloc_tag_module_section { + union { + unsigned long start_addr; + struct alloc_tag *first_tag; + }; + unsigned long end_addr; + /* used size */ + unsigned long size; +}; + +#ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG + +#define CODETAG_EMPTY ((void *)1) + +static inline bool is_codetag_empty(union codetag_ref *ref) +{ + return ref->ct == CODETAG_EMPTY; +} + +static inline void set_codetag_empty(union codetag_ref *ref) +{ + if (ref) + ref->ct = CODETAG_EMPTY; +} + +#else /* CONFIG_MEM_ALLOC_PROFILING_DEBUG */ + +static inline bool is_codetag_empty(union codetag_ref *ref) { return false; } + +static inline void set_codetag_empty(union codetag_ref *ref) +{ + if (ref) + ref->ct = NULL; +} + +#endif /* CONFIG_MEM_ALLOC_PROFILING_DEBUG */ + +#ifdef CONFIG_MEM_ALLOC_PROFILING + +#define ALLOC_TAG_SECTION_NAME "alloc_tags" + +struct codetag_bytes { + struct codetag *ct; + s64 bytes; +}; + +size_t alloc_tag_top_users(struct codetag_bytes *tags, size_t count, bool can_sleep); + +static inline struct alloc_tag *ct_to_alloc_tag(struct codetag *ct) +{ + return container_of(ct, struct alloc_tag, ct); +} + +#ifdef ARCH_NEEDS_WEAK_PER_CPU +/* + * When percpu variables are required to be defined as weak, static percpu + * variables can't be used inside a function (see comments for DECLARE_PER_CPU_SECTION). + * Instead we will account all module allocations to a single counter. + */ +DECLARE_PER_CPU(struct alloc_tag_counters, _shared_alloc_tag); + +#define DEFINE_ALLOC_TAG(_alloc_tag) \ + static struct alloc_tag _alloc_tag __used __aligned(8) \ + __section(ALLOC_TAG_SECTION_NAME) = { \ + .ct = CODE_TAG_INIT, \ + .counters = &_shared_alloc_tag }; + +#else /* ARCH_NEEDS_WEAK_PER_CPU */ + +#define DEFINE_ALLOC_TAG(_alloc_tag) \ + static DEFINE_PER_CPU(struct alloc_tag_counters, _alloc_tag_cntr); \ + static struct alloc_tag _alloc_tag __used __aligned(8) \ + __section(ALLOC_TAG_SECTION_NAME) = { \ + .ct = CODE_TAG_INIT, \ + .counters = &_alloc_tag_cntr }; + +#endif /* ARCH_NEEDS_WEAK_PER_CPU */ + +DECLARE_STATIC_KEY_MAYBE(CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT, + mem_alloc_profiling_key); + +static inline bool mem_alloc_profiling_enabled(void) +{ + return static_branch_maybe(CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT, + &mem_alloc_profiling_key); +} + +static inline struct alloc_tag_counters alloc_tag_read(struct alloc_tag *tag) +{ + struct alloc_tag_counters v = { 0, 0 }; + struct alloc_tag_counters *counter; + int cpu; + + for_each_possible_cpu(cpu) { + counter = per_cpu_ptr(tag->counters, cpu); + v.bytes += counter->bytes; + v.calls += counter->calls; + } + + return v; +} + +#ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG +static inline void alloc_tag_add_check(union codetag_ref *ref, struct alloc_tag *tag) +{ + WARN_ONCE(ref && ref->ct && !is_codetag_empty(ref), + "alloc_tag was not cleared (got tag for %s:%u)\n", + ref->ct->filename, ref->ct->lineno); + + WARN_ONCE(!tag, "current->alloc_tag not set\n"); +} + +static inline void alloc_tag_sub_check(union codetag_ref *ref) +{ + WARN_ONCE(ref && !ref->ct, "alloc_tag was not set\n"); +} +#else +static inline void alloc_tag_add_check(union codetag_ref *ref, struct alloc_tag *tag) {} +static inline void alloc_tag_sub_check(union codetag_ref *ref) {} +#endif + +/* Caller should verify both ref and tag to be valid */ +static inline bool __alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag) +{ + alloc_tag_add_check(ref, tag); + if (!ref || !tag) + return false; + + ref->ct = &tag->ct; + return true; +} + +static inline bool alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag) +{ + if (unlikely(!__alloc_tag_ref_set(ref, tag))) + return false; + + /* + * We need in increment the call counter every time we have a new + * allocation or when we split a large allocation into smaller ones. + * Each new reference for every sub-allocation needs to increment call + * counter because when we free each part the counter will be decremented. + */ + this_cpu_inc(tag->counters->calls); + return true; +} + +static inline void alloc_tag_add(union codetag_ref *ref, struct alloc_tag *tag, size_t bytes) +{ + if (likely(alloc_tag_ref_set(ref, tag))) + this_cpu_add(tag->counters->bytes, bytes); +} + +static inline void alloc_tag_sub(union codetag_ref *ref, size_t bytes) +{ + struct alloc_tag *tag; + + alloc_tag_sub_check(ref); + if (!ref || !ref->ct) + return; + + if (is_codetag_empty(ref)) { + ref->ct = NULL; + return; + } + + tag = ct_to_alloc_tag(ref->ct); + + this_cpu_sub(tag->counters->bytes, bytes); + this_cpu_dec(tag->counters->calls); + + ref->ct = NULL; +} + +#define alloc_tag_record(p) ((p) = current->alloc_tag) + +#else /* CONFIG_MEM_ALLOC_PROFILING */ + +#define DEFINE_ALLOC_TAG(_alloc_tag) +static inline bool mem_alloc_profiling_enabled(void) { return false; } +static inline void alloc_tag_add(union codetag_ref *ref, struct alloc_tag *tag, + size_t bytes) {} +static inline void alloc_tag_sub(union codetag_ref *ref, size_t bytes) {} +#define alloc_tag_record(p) do {} while (0) + +#endif /* CONFIG_MEM_ALLOC_PROFILING */ + +#define alloc_hooks_tag(_tag, _do_alloc) \ +({ \ + typeof(_do_alloc) _res; \ + if (mem_alloc_profiling_enabled()) { \ + struct alloc_tag * __maybe_unused _old; \ + _old = alloc_tag_save(_tag); \ + _res = _do_alloc; \ + alloc_tag_restore(_tag, _old); \ + } else \ + _res = _do_alloc; \ + _res; \ +}) + +#define alloc_hooks(_do_alloc) \ +({ \ + DEFINE_ALLOC_TAG(_alloc_tag); \ + alloc_hooks_tag(&_alloc_tag, _do_alloc); \ +}) + +#endif /* _LINUX_ALLOC_TAG_H */ diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h index c60a6a14638c..9946276aff73 100644 --- a/include/linux/amba/bus.h +++ b/include/linux/amba/bus.h @@ -105,24 +105,36 @@ enum amba_vendor { AMBA_VENDOR_LSI = 0xb6, }; -extern struct bus_type amba_bustype; +extern const struct bus_type amba_bustype; #define to_amba_device(d) container_of_const(d, struct amba_device, dev) #define amba_get_drvdata(d) dev_get_drvdata(&d->dev) #define amba_set_drvdata(d,p) dev_set_drvdata(&d->dev, p) +/* + * use a macro to avoid include chaining to get THIS_MODULE + */ +#define amba_driver_register(drv) \ + __amba_driver_register(drv, THIS_MODULE) + #ifdef CONFIG_ARM_AMBA -int amba_driver_register(struct amba_driver *); +int __amba_driver_register(struct amba_driver *, struct module *); void amba_driver_unregister(struct amba_driver *); +bool dev_is_amba(const struct device *dev); #else -static inline int amba_driver_register(struct amba_driver *drv) +static inline int __amba_driver_register(struct amba_driver *drv, + struct module *owner) { return -EINVAL; } static inline void amba_driver_unregister(struct amba_driver *drv) { } +static inline bool dev_is_amba(const struct device *dev) +{ + return false; +} #endif struct amba_device *amba_device_alloc(const char *, resource_size_t, size_t); diff --git a/include/linux/amd-iommu.h b/include/linux/amd-iommu.h index 2b90c48a6a87..062fbd4c9b77 100644 --- a/include/linux/amd-iommu.h +++ b/include/linux/amd-iommu.h @@ -31,11 +31,11 @@ struct amd_iommu_pi_data { struct task_struct; struct pci_dev; -extern int amd_iommu_detect(void); +extern void amd_iommu_detect(void); #else /* CONFIG_AMD_IOMMU */ -static inline int amd_iommu_detect(void) { return -ENODEV; } +static inline void amd_iommu_detect(void) { } #endif /* CONFIG_AMD_IOMMU */ diff --git a/include/linux/amd-pmf-io.h b/include/linux/amd-pmf-io.h index b4f818205216..6fa510f419c0 100644 --- a/include/linux/amd-pmf-io.h +++ b/include/linux/amd-pmf-io.h @@ -18,10 +18,12 @@ * enum sfh_message_type - Query the SFH message type * @MT_HPD: Message ID to know the Human presence info from MP2 FW * @MT_ALS: Message ID to know the Ambient light info from MP2 FW + * @MT_SRA: Message ID to know the SRA data from MP2 FW */ enum sfh_message_type { MT_HPD, MT_ALS, + MT_SRA, }; /** @@ -40,10 +42,23 @@ enum sfh_hpd_info { * struct amd_sfh_info - get HPD sensor info from MP2 FW * @ambient_light: Populates the ambient light information * @user_present: Populates the user presence information + * @platform_type: Operating modes (clamshell, flat, tent, etc.) + * @laptop_placement: Device states (ontable, onlap, outbag) */ struct amd_sfh_info { u32 ambient_light; u8 user_present; + u32 platform_type; + u32 laptop_placement; +}; + +enum laptop_placement { + LP_UNKNOWN = 0, + ON_TABLE, + ON_LAP_MOTION, + IN_BAG, + OUT_OF_BAG, + LP_UNDEFINED, }; int amd_get_sfh_info(struct amd_sfh_info *sfh_info, enum sfh_message_type op); diff --git a/include/linux/amd-pstate.h b/include/linux/amd-pstate.h deleted file mode 100644 index d21838835abd..000000000000 --- a/include/linux/amd-pstate.h +++ /dev/null @@ -1,127 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * linux/include/linux/amd-pstate.h - * - * Copyright (C) 2022 Advanced Micro Devices, Inc. - * - * Author: Meng Li <li.meng@amd.com> - */ - -#ifndef _LINUX_AMD_PSTATE_H -#define _LINUX_AMD_PSTATE_H - -#include <linux/pm_qos.h> - -#define AMD_CPPC_EPP_PERFORMANCE 0x00 -#define AMD_CPPC_EPP_BALANCE_PERFORMANCE 0x80 -#define AMD_CPPC_EPP_BALANCE_POWERSAVE 0xBF -#define AMD_CPPC_EPP_POWERSAVE 0xFF - -/********************************************************************* - * AMD P-state INTERFACE * - *********************************************************************/ -/** - * struct amd_aperf_mperf - * @aperf: actual performance frequency clock count - * @mperf: maximum performance frequency clock count - * @tsc: time stamp counter - */ -struct amd_aperf_mperf { - u64 aperf; - u64 mperf; - u64 tsc; -}; - -/** - * struct amd_cpudata - private CPU data for AMD P-State - * @cpu: CPU number - * @req: constraint request to apply - * @cppc_req_cached: cached performance request hints - * @highest_perf: the maximum performance an individual processor may reach, - * assuming ideal conditions - * For platforms that do not support the preferred core feature, the - * highest_pef may be configured with 166 or 255, to avoid max frequency - * calculated wrongly. we take the fixed value as the highest_perf. - * @nominal_perf: the maximum sustained performance level of the processor, - * assuming ideal operating conditions - * @lowest_nonlinear_perf: the lowest performance level at which nonlinear power - * savings are achieved - * @lowest_perf: the absolute lowest performance level of the processor - * @prefcore_ranking: the preferred core ranking, the higher value indicates a higher - * priority. - * @max_freq: the frequency that mapped to highest_perf - * @min_freq: the frequency that mapped to lowest_perf - * @nominal_freq: the frequency that mapped to nominal_perf - * @lowest_nonlinear_freq: the frequency that mapped to lowest_nonlinear_perf - * @cur: Difference of Aperf/Mperf/tsc count between last and current sample - * @prev: Last Aperf/Mperf/tsc count value read from register - * @freq: current cpu frequency value - * @boost_supported: check whether the Processor or SBIOS supports boost mode - * @hw_prefcore: check whether HW supports preferred core featue. - * Only when hw_prefcore and early prefcore param are true, - * AMD P-State driver supports preferred core featue. - * @epp_policy: Last saved policy used to set energy-performance preference - * @epp_cached: Cached CPPC energy-performance preference value - * @policy: Cpufreq policy value - * @cppc_cap1_cached Cached MSR_AMD_CPPC_CAP1 register value - * - * The amd_cpudata is key private data for each CPU thread in AMD P-State, and - * represents all the attributes and goals that AMD P-State requests at runtime. - */ -struct amd_cpudata { - int cpu; - - struct freq_qos_request req[2]; - u64 cppc_req_cached; - - u32 highest_perf; - u32 nominal_perf; - u32 lowest_nonlinear_perf; - u32 lowest_perf; - u32 prefcore_ranking; - u32 min_limit_perf; - u32 max_limit_perf; - u32 min_limit_freq; - u32 max_limit_freq; - - u32 max_freq; - u32 min_freq; - u32 nominal_freq; - u32 lowest_nonlinear_freq; - - struct amd_aperf_mperf cur; - struct amd_aperf_mperf prev; - - u64 freq; - bool boost_supported; - bool hw_prefcore; - - /* EPP feature related attributes*/ - s16 epp_policy; - s16 epp_cached; - u32 policy; - u64 cppc_cap1_cached; - bool suspended; -}; - -/* - * enum amd_pstate_mode - driver working mode of amd pstate - */ -enum amd_pstate_mode { - AMD_PSTATE_UNDEFINED = 0, - AMD_PSTATE_DISABLE, - AMD_PSTATE_PASSIVE, - AMD_PSTATE_ACTIVE, - AMD_PSTATE_GUIDED, - AMD_PSTATE_MAX, -}; - -static const char * const amd_pstate_mode_string[] = { - [AMD_PSTATE_UNDEFINED] = "undefined", - [AMD_PSTATE_DISABLE] = "disable", - [AMD_PSTATE_PASSIVE] = "passive", - [AMD_PSTATE_ACTIVE] = "active", - [AMD_PSTATE_GUIDED] = "guided", - NULL, -}; -#endif /* _LINUX_AMD_PSTATE_H */ diff --git a/include/linux/anon_inodes.h b/include/linux/anon_inodes.h index 93a5f16d03f3..edef565c2a1a 100644 --- a/include/linux/anon_inodes.h +++ b/include/linux/anon_inodes.h @@ -9,12 +9,17 @@ #ifndef _LINUX_ANON_INODES_H #define _LINUX_ANON_INODES_H +#include <linux/types.h> + struct file_operations; struct inode; struct file *anon_inode_getfile(const char *name, const struct file_operations *fops, void *priv, int flags); +struct file *anon_inode_getfile_fmode(const char *name, + const struct file_operations *fops, + void *priv, int flags, fmode_t f_mode); struct file *anon_inode_create_getfile(const char *name, const struct file_operations *fops, void *priv, int flags, diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h index a63d61ca55af..2222e8b03ff4 100644 --- a/include/linux/arch_topology.h +++ b/include/linux/arch_topology.h @@ -11,10 +11,6 @@ void topology_normalize_cpu_scale(void); int topology_update_cpu_topology(void); -#ifdef CONFIG_ACPI_CPPC_LIB -void topology_init_cpu_capacity_cppc(void); -#endif - struct device_node; bool topology_parse_cpu_capacity(struct device_node *cpu_node, int cpu); @@ -49,6 +45,7 @@ enum scale_freq_source { SCALE_FREQ_SOURCE_CPUFREQ = 0, SCALE_FREQ_SOURCE_ARCH, SCALE_FREQ_SOURCE_CPPC, + SCALE_FREQ_SOURCE_VIRT, }; struct scale_freq_data { @@ -60,14 +57,14 @@ void topology_scale_freq_tick(void); void topology_set_scale_freq_source(struct scale_freq_data *data, const struct cpumask *cpus); void topology_clear_scale_freq_source(enum scale_freq_source source, const struct cpumask *cpus); -DECLARE_PER_CPU(unsigned long, thermal_pressure); +DECLARE_PER_CPU(unsigned long, hw_pressure); -static inline unsigned long topology_get_thermal_pressure(int cpu) +static inline unsigned long topology_get_hw_pressure(int cpu) { - return per_cpu(thermal_pressure, cpu); + return per_cpu(hw_pressure, cpu); } -void topology_update_thermal_pressure(const struct cpumask *cpus, +void topology_update_hw_pressure(const struct cpumask *cpus, unsigned long capped_freq); struct cpu_topology { diff --git a/include/linux/args.h b/include/linux/args.h index 8ff60a54eb7d..2e8e65d975c7 100644 --- a/include/linux/args.h +++ b/include/linux/args.h @@ -17,9 +17,9 @@ * that as _n. */ -/* This counts to 12. Any more, it will return 13th argument. */ -#define __COUNT_ARGS(_0, _1, _2, _3, _4, _5, _6, _7, _8, _9, _10, _11, _12, _n, X...) _n -#define COUNT_ARGS(X...) __COUNT_ARGS(, ##X, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0) +/* This counts to 15. Any more, it will return 16th argument. */ +#define __COUNT_ARGS(_0, _1, _2, _3, _4, _5, _6, _7, _8, _9, _10, _11, _12, _13, _14, _15, _n, X...) _n +#define COUNT_ARGS(X...) __COUNT_ARGS(, ##X, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0) /* Concatenate two parameters, but allow them to be expanded beforehand. */ #define __CONCAT(a, b) a ## b diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 083f85653716..67f6fdf2e7cd 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -115,6 +115,70 @@ /* KVM "vendor specific" services */ #define ARM_SMCCC_KVM_FUNC_FEATURES 0 #define ARM_SMCCC_KVM_FUNC_PTP 1 +/* Start of pKVM hypercall range */ +#define ARM_SMCCC_KVM_FUNC_HYP_MEMINFO 2 +#define ARM_SMCCC_KVM_FUNC_MEM_SHARE 3 +#define ARM_SMCCC_KVM_FUNC_MEM_UNSHARE 4 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_5 5 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_6 6 +#define ARM_SMCCC_KVM_FUNC_MMIO_GUARD 7 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_8 8 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_9 9 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_10 10 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_11 11 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_12 12 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_13 13 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_14 14 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_15 15 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_16 16 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_17 17 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_18 18 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_19 19 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_20 20 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_21 21 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_22 22 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_23 23 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_24 24 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_25 25 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_26 26 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_27 27 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_28 28 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_29 29 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_30 30 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_31 31 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_32 32 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_33 33 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_34 34 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_35 35 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_36 36 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_37 37 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_38 38 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_39 39 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_40 40 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_41 41 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_42 42 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_43 43 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_44 44 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_45 45 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_46 46 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_47 47 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_48 48 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_49 49 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_50 50 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_51 51 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_52 52 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_53 53 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_54 54 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_55 55 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_56 56 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_57 57 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_58 58 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_59 59 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_60 60 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_61 61 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_62 62 +#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_63 63 +/* End of pKVM hypercall range */ #define ARM_SMCCC_KVM_FUNC_FEATURES_2 127 #define ARM_SMCCC_KVM_NUM_FUNCS 128 @@ -137,6 +201,30 @@ ARM_SMCCC_OWNER_VENDOR_HYP, \ ARM_SMCCC_KVM_FUNC_PTP) +#define ARM_SMCCC_VENDOR_HYP_KVM_HYP_MEMINFO_FUNC_ID \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_64, \ + ARM_SMCCC_OWNER_VENDOR_HYP, \ + ARM_SMCCC_KVM_FUNC_HYP_MEMINFO) + +#define ARM_SMCCC_VENDOR_HYP_KVM_MEM_SHARE_FUNC_ID \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_64, \ + ARM_SMCCC_OWNER_VENDOR_HYP, \ + ARM_SMCCC_KVM_FUNC_MEM_SHARE) + +#define ARM_SMCCC_VENDOR_HYP_KVM_MEM_UNSHARE_FUNC_ID \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_64, \ + ARM_SMCCC_OWNER_VENDOR_HYP, \ + ARM_SMCCC_KVM_FUNC_MEM_UNSHARE) + +#define ARM_SMCCC_VENDOR_HYP_KVM_MMIO_GUARD_FUNC_ID \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_64, \ + ARM_SMCCC_OWNER_VENDOR_HYP, \ + ARM_SMCCC_KVM_FUNC_MMIO_GUARD) + /* ptp_kvm counter type ID */ #define KVM_PTP_VIRT_COUNTER 0 #define KVM_PTP_PHYS_COUNTER 1 @@ -227,8 +315,6 @@ u32 arm_smccc_get_version(void); void __init arm_smccc_version_init(u32 version, enum arm_smccc_conduit conduit); -extern u64 smccc_has_sve_hint; - /** * arm_smccc_get_soc_id_version() * @@ -327,15 +413,6 @@ struct arm_smccc_quirk { }; /** - * __arm_smccc_sve_check() - Set the SVE hint bit when doing SMC calls - * - * Sets the SMCCC hint bit to indicate if there is live state in the SVE - * registers, this modifies x0 in place and should never be called from C - * code. - */ -asmlinkage unsigned long __arm_smccc_sve_check(unsigned long x0); - -/** * __arm_smccc_smc() - make SMC calls * @a0-a7: arguments passed in registers 0 to 7 * @res: result values from registers 0 to 3 @@ -402,20 +479,6 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, #endif -/* nVHE hypervisor doesn't have a current thread so needs separate checks */ -#if defined(CONFIG_ARM64_SVE) && !defined(__KVM_NVHE_HYPERVISOR__) - -#define SMCCC_SVE_CHECK ALTERNATIVE("nop \n", "bl __arm_smccc_sve_check \n", \ - ARM64_SVE) -#define smccc_sve_clobbers "x16", "x30", "cc", - -#else - -#define SMCCC_SVE_CHECK -#define smccc_sve_clobbers - -#endif - #define __constraint_read_2 "r" (arg0) #define __constraint_read_3 __constraint_read_2, "r" (arg1) #define __constraint_read_4 __constraint_read_3, "r" (arg2) @@ -486,12 +549,11 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, register unsigned long r3 asm("r3"); \ CONCATENATE(__declare_arg_, \ COUNT_ARGS(__VA_ARGS__))(__VA_ARGS__); \ - asm volatile(SMCCC_SVE_CHECK \ - inst "\n" : \ + asm volatile(inst "\n" : \ "=r" (r0), "=r" (r1), "=r" (r2), "=r" (r3) \ : CONCATENATE(__constraint_read_, \ COUNT_ARGS(__VA_ARGS__)) \ - : smccc_sve_clobbers "memory"); \ + : "memory"); \ if (___res) \ *___res = (typeof(*___res)){r0, r1, r2, r3}; \ } while (0) @@ -540,7 +602,7 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, asm ("" : \ : CONCATENATE(__constraint_read_, \ COUNT_ARGS(__VA_ARGS__)) \ - : smccc_sve_clobbers "memory"); \ + : "memory"); \ if (___res) \ ___res->a0 = SMCCC_RET_NOT_SUPPORTED; \ } while (0) diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h index c906f666ff5d..74169dd0f659 100644 --- a/include/linux/arm_ffa.h +++ b/include/linux/arm_ffa.h @@ -73,6 +73,11 @@ #define FFA_FN64_MEM_PERM_GET FFA_SMC_64(0x88) #define FFA_MEM_PERM_SET FFA_SMC_32(0x89) #define FFA_FN64_MEM_PERM_SET FFA_SMC_64(0x89) +#define FFA_CONSOLE_LOG FFA_SMC_32(0x8A) +#define FFA_PARTITION_INFO_GET_REGS FFA_SMC_64(0x8B) +#define FFA_EL3_INTR_HANDLE FFA_SMC_32(0x8C) +#define FFA_MSG_SEND_DIRECT_REQ2 FFA_SMC_64(0x8D) +#define FFA_MSG_SEND_DIRECT_RESP2 FFA_SMC_64(0x8E) /* * For some calls it is necessary to use SMC64 to pass or return 64-bit values. @@ -126,6 +131,7 @@ /* FFA Bus/Device/Driver related */ struct ffa_device { u32 id; + u32 properties; int vm_id; bool mode_32bit; uuid_t uuid; @@ -148,7 +154,7 @@ struct ffa_driver { struct device_driver driver; }; -#define to_ffa_driver(d) container_of(d, struct ffa_driver, driver) +#define to_ffa_driver(d) container_of_const(d, struct ffa_driver, driver) static inline void ffa_dev_set_drvdata(struct ffa_device *fdev, void *data) { @@ -160,9 +166,12 @@ static inline void *ffa_dev_get_drvdata(struct ffa_device *fdev) return dev_get_drvdata(&fdev->dev); } +struct ffa_partition_info; + #if IS_REACHABLE(CONFIG_ARM_FFA_TRANSPORT) -struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id, - const struct ffa_ops *ops); +struct ffa_device * +ffa_device_register(const struct ffa_partition_info *part_info, + const struct ffa_ops *ops); void ffa_device_unregister(struct ffa_device *ffa_dev); int ffa_driver_register(struct ffa_driver *driver, struct module *owner, const char *mod_name); @@ -170,9 +179,9 @@ void ffa_driver_unregister(struct ffa_driver *driver); bool ffa_device_is_valid(struct ffa_device *ffa_dev); #else -static inline -struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id, - const struct ffa_ops *ops) +static inline struct ffa_device * +ffa_device_register(const struct ffa_partition_info *part_info, + const struct ffa_ops *ops) { return NULL; } @@ -211,6 +220,9 @@ bool ffa_device_is_valid(struct ffa_device *ffa_dev) { return false; } extern const struct bus_type ffa_bus_type; +/* The FF-A 1.0 partition structure lacks the uuid[4] */ +#define FFA_1_0_PARTITON_INFO_SZ (8) + /* FFA transport related */ struct ffa_partition_info { u16 id; @@ -221,12 +233,29 @@ struct ffa_partition_info { #define FFA_PARTITION_DIRECT_SEND BIT(1) /* partition can send and receive indirect messages. */ #define FFA_PARTITION_INDIRECT_MSG BIT(2) +/* partition can receive notifications */ +#define FFA_PARTITION_NOTIFICATION_RECV BIT(3) /* partition runs in the AArch64 execution state. */ #define FFA_PARTITION_AARCH64_EXEC BIT(8) u32 properties; u32 uuid[4]; }; +static inline +bool ffa_partition_check_property(struct ffa_device *dev, u32 property) +{ + return dev->properties & property; +} + +#define ffa_partition_supports_notify_recv(dev) \ + ffa_partition_check_property(dev, FFA_PARTITION_NOTIFICATION_RECV) + +#define ffa_partition_supports_indirect_msg(dev) \ + ffa_partition_check_property(dev, FFA_PARTITION_INDIRECT_MSG) + +#define ffa_partition_supports_direct_recv(dev) \ + ffa_partition_check_property(dev, FFA_PARTITION_DIRECT_RECV) + /* For use with FFA_MSG_SEND_DIRECT_{REQ,RESP} which pass data via registers */ struct ffa_send_direct_data { unsigned long data0; /* w3/x3 */ @@ -236,6 +265,19 @@ struct ffa_send_direct_data { unsigned long data4; /* w7/x7 */ }; +struct ffa_indirect_msg_hdr { + u32 flags; + u32 res0; + u32 offset; + u32 send_recv_id; + u32 size; +}; + +/* For use with FFA_MSG_SEND_DIRECT_{REQ,RESP}2 which pass data via registers */ +struct ffa_send_direct_data2 { + unsigned long data[14]; /* x4-x17 */ +}; + struct ffa_mem_region_addr_range { /* The base IPA of the constituent memory region, aligned to 4 kiB */ u64 address; @@ -396,6 +438,9 @@ struct ffa_msg_ops { void (*mode_32bit_set)(struct ffa_device *dev); int (*sync_send_receive)(struct ffa_device *dev, struct ffa_send_direct_data *data); + int (*indirect_send)(struct ffa_device *dev, void *buf, size_t sz); + int (*sync_send_receive2)(struct ffa_device *dev, const uuid_t *uuid, + struct ffa_send_direct_data2 *data); }; struct ffa_mem_ops { diff --git a/include/linux/asn1_decoder.h b/include/linux/asn1_decoder.h index 83f9c6e1e5e9..b41bce82a191 100644 --- a/include/linux/asn1_decoder.h +++ b/include/linux/asn1_decoder.h @@ -9,6 +9,7 @@ #define _LINUX_ASN1_DECODER_H #include <linux/asn1.h> +#include <linux/types.h> struct asn1_decoder; diff --git a/include/linux/asn1_encoder.h b/include/linux/asn1_encoder.h index 08cd0c2ad34f..d17484dffb74 100644 --- a/include/linux/asn1_encoder.h +++ b/include/linux/asn1_encoder.h @@ -6,7 +6,6 @@ #include <linux/types.h> #include <linux/asn1.h> #include <linux/asn1_ber_bytecode.h> -#include <linux/bug.h> #define asn1_oid_len(oid) (sizeof(oid)/sizeof(u32)) unsigned char * diff --git a/include/linux/ath9k_platform.h b/include/linux/ath9k_platform.h deleted file mode 100644 index 76860a461ed2..000000000000 --- a/include/linux/ath9k_platform.h +++ /dev/null @@ -1,51 +0,0 @@ -/* - * Copyright (c) 2008 Atheros Communications Inc. - * Copyright (c) 2009 Gabor Juhos <juhosg@openwrt.org> - * Copyright (c) 2009 Imre Kaloz <kaloz@openwrt.org> - * - * Permission to use, copy, modify, and/or distribute this software for any - * purpose with or without fee is hereby granted, provided that the above - * copyright notice and this permission notice appear in all copies. - * - * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES - * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF - * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR - * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES - * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN - * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF - * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. - */ - -#ifndef _LINUX_ATH9K_PLATFORM_H -#define _LINUX_ATH9K_PLATFORM_H - -#define ATH9K_PLAT_EEP_MAX_WORDS 2048 - -struct ath9k_platform_data { - const char *eeprom_name; - - u16 eeprom_data[ATH9K_PLAT_EEP_MAX_WORDS]; - u8 *macaddr; - - int led_pin; - u32 gpio_mask; - u32 gpio_val; - - u32 bt_active_pin; - u32 bt_priority_pin; - u32 wlan_active_pin; - - bool endian_check; - bool is_clk_25mhz; - bool tx_gain_buffalo; - bool disable_2ghz; - bool disable_5ghz; - bool led_active_high; - - int (*get_mac_revision)(void); - int (*external_reset)(void); - - bool use_eeprom; -}; - -#endif /* _LINUX_ATH9K_PLATFORM_H */ diff --git a/include/linux/atomic/atomic-arch-fallback.h b/include/linux/atomic/atomic-arch-fallback.h index 956bcba5dbf2..2f9d36b72bd8 100644 --- a/include/linux/atomic/atomic-arch-fallback.h +++ b/include/linux/atomic/atomic-arch-fallback.h @@ -2242,7 +2242,7 @@ raw_atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) /** * raw_atomic_sub_and_test() - atomic subtract and test if zero with full ordering - * @i: int value to add + * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with full ordering. @@ -4368,7 +4368,7 @@ raw_atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) /** * raw_atomic64_sub_and_test() - atomic subtract and test if zero with full ordering - * @i: s64 value to add + * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with full ordering. @@ -4690,4 +4690,4 @@ raw_atomic64_dec_if_positive(atomic64_t *v) } #endif /* _LINUX_ATOMIC_FALLBACK_H */ -// 14850c0b0db20c62fdc78ccd1d42b98b88d76331 +// b565db590afeeff0d7c9485ccbca5bb6e155749f diff --git a/include/linux/atomic/atomic-instrumented.h b/include/linux/atomic/atomic-instrumented.h index debd487fe971..9409a6ddf3e0 100644 --- a/include/linux/atomic/atomic-instrumented.h +++ b/include/linux/atomic/atomic-instrumented.h @@ -1349,7 +1349,7 @@ atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) /** * atomic_sub_and_test() - atomic subtract and test if zero with full ordering - * @i: int value to add + * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with full ordering. @@ -2927,7 +2927,7 @@ atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) /** * atomic64_sub_and_test() - atomic subtract and test if zero with full ordering - * @i: s64 value to add + * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with full ordering. @@ -4505,7 +4505,7 @@ atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new) /** * atomic_long_sub_and_test() - atomic subtract and test if zero with full ordering - * @i: long value to add + * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with full ordering. @@ -5050,4 +5050,4 @@ atomic_long_dec_if_positive(atomic_long_t *v) #endif /* _LINUX_ATOMIC_INSTRUMENTED_H */ -// ce5b65e0f1f8a276268b667194581d24bed219d4 +// 8829b337928e9508259079d32581775ececd415b diff --git a/include/linux/atomic/atomic-long.h b/include/linux/atomic/atomic-long.h index 3ef844b3ab8a..f86b29d90877 100644 --- a/include/linux/atomic/atomic-long.h +++ b/include/linux/atomic/atomic-long.h @@ -1535,7 +1535,7 @@ raw_atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new) /** * raw_atomic_long_sub_and_test() - atomic subtract and test if zero with full ordering - * @i: long value to add + * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with full ordering. @@ -1809,4 +1809,4 @@ raw_atomic_long_dec_if_positive(atomic_long_t *v) } #endif /* _LINUX_ATOMIC_LONG_H */ -// 1c4a26fc77f345342953770ebe3c4d08e7ce2f9a +// eadf183c3600b8b92b91839dd3be6bcc560c752d diff --git a/include/linux/attribute_container.h b/include/linux/attribute_container.h index e4004d1e6725..b3643de9931d 100644 --- a/include/linux/attribute_container.h +++ b/include/linux/attribute_container.h @@ -61,14 +61,8 @@ int attribute_container_device_trigger_safe(struct device *dev, int (*undo)(struct attribute_container *, struct device *, struct device *)); -void attribute_container_trigger(struct device *dev, - int (*fn)(struct attribute_container *, - struct device *)); int attribute_container_add_attrs(struct device *classdev); int attribute_container_add_class_device(struct device *classdev); -int attribute_container_add_class_device_adapter(struct attribute_container *cont, - struct device *dev, - struct device *classdev); void attribute_container_remove_attrs(struct device *classdev); void attribute_container_class_device_del(struct device *classdev); struct attribute_container *attribute_container_classdev_to_container(struct device *); diff --git a/include/linux/auxiliary_bus.h b/include/linux/auxiliary_bus.h index de21d9d24a95..65dd7f154374 100644 --- a/include/linux/auxiliary_bus.h +++ b/include/linux/auxiliary_bus.h @@ -58,6 +58,10 @@ * in * @name: Match name found by the auxiliary device driver, * @id: unique identitier if multiple devices of the same name are exported, + * @sysfs: embedded struct which hold all sysfs related fields, + * @sysfs.irqs: irqs xarray contains irq indices which are used by the device, + * @sysfs.lock: Synchronize irq sysfs creation, + * @sysfs.irq_dir_exists: whether "irqs" directory exists, * * An auxiliary_device represents a part of its parent device's functionality. * It is given a name that, combined with the registering drivers @@ -139,6 +143,11 @@ struct auxiliary_device { struct device dev; const char *name; u32 id; + struct { + struct xarray irqs; + struct mutex lock; /* Synchronize irq sysfs creation */ + bool irq_dir_exists; + } sysfs; }; /** @@ -203,7 +212,7 @@ static inline struct auxiliary_device *to_auxiliary_dev(struct device *dev) return container_of(dev, struct auxiliary_device, dev); } -static inline struct auxiliary_driver *to_auxiliary_drv(struct device_driver *drv) +static inline const struct auxiliary_driver *to_auxiliary_drv(const struct device_driver *drv) { return container_of(drv, struct auxiliary_driver, driver); } @@ -212,8 +221,24 @@ int auxiliary_device_init(struct auxiliary_device *auxdev); int __auxiliary_device_add(struct auxiliary_device *auxdev, const char *modname); #define auxiliary_device_add(auxdev) __auxiliary_device_add(auxdev, KBUILD_MODNAME) +#ifdef CONFIG_SYSFS +int auxiliary_device_sysfs_irq_add(struct auxiliary_device *auxdev, int irq); +void auxiliary_device_sysfs_irq_remove(struct auxiliary_device *auxdev, + int irq); +#else /* CONFIG_SYSFS */ +static inline int +auxiliary_device_sysfs_irq_add(struct auxiliary_device *auxdev, int irq) +{ + return 0; +} + +static inline void +auxiliary_device_sysfs_irq_remove(struct auxiliary_device *auxdev, int irq) {} +#endif + static inline void auxiliary_device_uninit(struct auxiliary_device *auxdev) { + mutex_destroy(&auxdev->sysfs.lock); put_device(&auxdev->dev); } @@ -244,8 +269,4 @@ void auxiliary_driver_unregister(struct auxiliary_driver *auxdrv); #define module_auxiliary_driver(__auxiliary_driver) \ module_driver(__auxiliary_driver, auxiliary_driver_register, auxiliary_driver_unregister) -struct auxiliary_device *auxiliary_find_device(struct device *start, - const void *data, - int (*match)(struct device *dev, const void *data)); - #endif /* _AUXILIARY_BUS_H_ */ diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index 8e177b67e82f..13a11f3c09b8 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -89,6 +89,9 @@ enum virtchnl_rx_hsplit { VIRTCHNL_RX_HSPLIT_SPLIT_SCTP = 8, }; +enum virtchnl_bw_limit_type { + VIRTCHNL_BW_SHAPER = 0, +}; /* END GENERIC DEFINES */ /* Opcodes for VF-PF communication. These are placed in the v_opcode field @@ -151,6 +154,11 @@ enum virtchnl_ops { VIRTCHNL_OP_DISABLE_VLAN_STRIPPING_V2 = 55, VIRTCHNL_OP_ENABLE_VLAN_INSERTION_V2 = 56, VIRTCHNL_OP_DISABLE_VLAN_INSERTION_V2 = 57, + /* opcode 57 - 65 are reserved */ + VIRTCHNL_OP_GET_QOS_CAPS = 66, + /* opcode 68 through 111 are reserved */ + VIRTCHNL_OP_CONFIG_QUEUE_BW = 112, + VIRTCHNL_OP_CONFIG_QUANTA = 113, VIRTCHNL_OP_MAX, }; @@ -247,6 +255,7 @@ VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vsi_resource); /* used to negotiate communicating link speeds in Mbps */ #define VIRTCHNL_VF_CAP_ADV_LINK_SPEED BIT(7) #define VIRTCHNL_VF_OFFLOAD_CRC BIT(10) +#define VIRTCHNL_VF_OFFLOAD_TC_U32 BIT(11) #define VIRTCHNL_VF_OFFLOAD_VLAN_V2 BIT(15) #define VIRTCHNL_VF_OFFLOAD_VLAN BIT(16) #define VIRTCHNL_VF_OFFLOAD_RX_POLLING BIT(17) @@ -260,6 +269,7 @@ VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vsi_resource); #define VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC BIT(26) #define VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF BIT(27) #define VIRTCHNL_VF_OFFLOAD_FDIR_PF BIT(28) +#define VIRTCHNL_VF_OFFLOAD_QOS BIT(29) #define VF_BASE_MODE_OFFLOADS (VIRTCHNL_VF_OFFLOAD_L2 | \ VIRTCHNL_VF_OFFLOAD_VLAN | \ @@ -1121,6 +1131,7 @@ enum virtchnl_vfr_states { }; #define VIRTCHNL_MAX_NUM_PROTO_HDRS 32 +#define VIRTCHNL_MAX_SIZE_RAW_PACKET 1024 #define PROTO_HDR_SHIFT 5 #define PROTO_HDR_FIELD_START(proto_hdr_type) ((proto_hdr_type) << PROTO_HDR_SHIFT) #define PROTO_HDR_FIELD_MASK ((1UL << PROTO_HDR_SHIFT) - 1) @@ -1266,13 +1277,22 @@ struct virtchnl_proto_hdrs { u8 pad[3]; /** * specify where protocol header start from. + * must be 0 when sending a raw packet request. * 0 - from the outer layer * 1 - from the first inner layer * 2 - from the second inner layer * .... **/ int count; /* the proto layers must < VIRTCHNL_MAX_NUM_PROTO_HDRS */ - struct virtchnl_proto_hdr proto_hdr[VIRTCHNL_MAX_NUM_PROTO_HDRS]; + union { + struct virtchnl_proto_hdr + proto_hdr[VIRTCHNL_MAX_NUM_PROTO_HDRS]; + struct { + u16 pkt_len; + u8 spec[VIRTCHNL_MAX_SIZE_RAW_PACKET]; + u8 mask[VIRTCHNL_MAX_SIZE_RAW_PACKET]; + } raw; + }; }; VIRTCHNL_CHECK_STRUCT_LEN(2312, virtchnl_proto_hdrs); @@ -1405,6 +1425,86 @@ struct virtchnl_fdir_del { VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_fdir_del); +struct virtchnl_shaper_bw { + /* Unit is Kbps */ + u32 committed; + u32 peak; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_shaper_bw); + +/* VIRTCHNL_OP_GET_QOS_CAPS + * VF sends this message to get its QoS Caps, such as + * TC number, Arbiter and Bandwidth. + */ +struct virtchnl_qos_cap_elem { + u8 tc_num; + u8 tc_prio; +#define VIRTCHNL_ABITER_STRICT 0 +#define VIRTCHNL_ABITER_ETS 2 + u8 arbiter; +#define VIRTCHNL_STRICT_WEIGHT 1 + u8 weight; + enum virtchnl_bw_limit_type type; + union { + struct virtchnl_shaper_bw shaper; + u8 pad2[32]; + }; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(40, virtchnl_qos_cap_elem); + +struct virtchnl_qos_cap_list { + u16 vsi_id; + u16 num_elem; + struct virtchnl_qos_cap_elem cap[]; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(4, virtchnl_qos_cap_list); +#define virtchnl_qos_cap_list_LEGACY_SIZEOF 44 + +/* VIRTCHNL_OP_CONFIG_QUEUE_BW */ +struct virtchnl_queue_bw { + u16 queue_id; + u8 tc; + u8 pad; + struct virtchnl_shaper_bw shaper; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_queue_bw); + +struct virtchnl_queues_bw_cfg { + u16 vsi_id; + u16 num_queues; + struct virtchnl_queue_bw cfg[]; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(4, virtchnl_queues_bw_cfg); +#define virtchnl_queues_bw_cfg_LEGACY_SIZEOF 16 + +enum virtchnl_queue_type { + VIRTCHNL_QUEUE_TYPE_TX = 0, + VIRTCHNL_QUEUE_TYPE_RX = 1, +}; + +/* structure to specify a chunk of contiguous queues */ +struct virtchnl_queue_chunk { + /* see enum virtchnl_queue_type */ + s32 type; + u16 start_queue_id; + u16 num_queues; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_queue_chunk); + +struct virtchnl_quanta_cfg { + u16 quanta_size; + u16 pad; + struct virtchnl_queue_chunk queue_select; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_quanta_cfg); + #define __vss_byone(p, member, count, old) \ (struct_size(p, member, count) + (old - 1 - struct_size(p, member, 0))) @@ -1427,6 +1527,8 @@ VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_fdir_del); __vss(virtchnl_vlan_filter_list_v2, __vss_byelem, p, m, c), \ __vss(virtchnl_tc_info, __vss_byelem, p, m, c), \ __vss(virtchnl_rdma_qvlist_info, __vss_byelem, p, m, c), \ + __vss(virtchnl_qos_cap_list, __vss_byelem, p, m, c), \ + __vss(virtchnl_queues_bw_cfg, __vss_byelem, p, m, c), \ __vss(virtchnl_rss_key, __vss_byone, p, m, c), \ __vss(virtchnl_rss_lut, __vss_byone, p, m, c)) @@ -1626,6 +1728,35 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode, case VIRTCHNL_OP_DISABLE_VLAN_INSERTION_V2: valid_len = sizeof(struct virtchnl_vlan_setting); break; + case VIRTCHNL_OP_GET_QOS_CAPS: + break; + case VIRTCHNL_OP_CONFIG_QUEUE_BW: + valid_len = virtchnl_queues_bw_cfg_LEGACY_SIZEOF; + if (msglen >= valid_len) { + struct virtchnl_queues_bw_cfg *q_bw = + (struct virtchnl_queues_bw_cfg *)msg; + + valid_len = virtchnl_struct_size(q_bw, cfg, + q_bw->num_queues); + if (q_bw->num_queues == 0) { + err_msg_format = true; + break; + } + } + break; + case VIRTCHNL_OP_CONFIG_QUANTA: + valid_len = sizeof(struct virtchnl_quanta_cfg); + if (msglen >= valid_len) { + struct virtchnl_quanta_cfg *q_quanta = + (struct virtchnl_quanta_cfg *)msg; + + if (q_quanta->quanta_size == 0 || + q_quanta->queue_select.num_queues == 0) { + err_msg_format = true; + break; + } + } + break; /* These are always errors coming from the VF. */ case VIRTCHNL_OP_EVENT: case VIRTCHNL_OP_UNKNOWN: diff --git a/include/linux/backing-file.h b/include/linux/backing-file.h index 3f1fe1774f1b..1476a6ed1bfd 100644 --- a/include/linux/backing-file.h +++ b/include/linux/backing-file.h @@ -14,27 +14,29 @@ struct backing_file_ctx { const struct cred *cred; - struct file *user_file; - void (*accessed)(struct file *); - void (*end_write)(struct file *); + void (*accessed)(struct file *file); + void (*end_write)(struct kiocb *iocb, ssize_t); }; struct file *backing_file_open(const struct path *user_path, int flags, const struct path *real_path, const struct cred *cred); +struct file *backing_tmpfile_open(const struct path *user_path, int flags, + const struct path *real_parentpath, + umode_t mode, const struct cred *cred); ssize_t backing_file_read_iter(struct file *file, struct iov_iter *iter, struct kiocb *iocb, int flags, struct backing_file_ctx *ctx); ssize_t backing_file_write_iter(struct file *file, struct iov_iter *iter, struct kiocb *iocb, int flags, struct backing_file_ctx *ctx); -ssize_t backing_file_splice_read(struct file *in, loff_t *ppos, +ssize_t backing_file_splice_read(struct file *in, struct kiocb *iocb, struct pipe_inode_info *pipe, size_t len, unsigned int flags, struct backing_file_ctx *ctx); ssize_t backing_file_splice_write(struct pipe_inode_info *pipe, - struct file *out, loff_t *ppos, size_t len, - unsigned int flags, + struct file *out, struct kiocb *iocb, + size_t len, unsigned int flags, struct backing_file_ctx *ctx); int backing_file_mmap(struct file *file, struct vm_area_struct *vma, struct backing_file_ctx *ctx); diff --git a/include/linux/backlight.h b/include/linux/backlight.h index 614653e07e3a..f5652e5a9060 100644 --- a/include/linux/backlight.h +++ b/include/linux/backlight.h @@ -13,6 +13,7 @@ #include <linux/fb.h> #include <linux/mutex.h> #include <linux/notifier.h> +#include <linux/types.h> /** * enum backlight_update_reason - what method was used to update backlight @@ -65,24 +66,6 @@ enum backlight_type { BACKLIGHT_TYPE_MAX, }; -/** - * enum backlight_notification - the type of notification - * - * The notifications that is used for notification sent to the receiver - * that registered notifications using backlight_register_notifier(). - */ -enum backlight_notification { - /** - * @BACKLIGHT_REGISTERED: The backlight device is registered. - */ - BACKLIGHT_REGISTERED, - - /** - * @BACKLIGHT_UNREGISTERED: The backlight revice is unregistered. - */ - BACKLIGHT_UNREGISTERED, -}; - /** enum backlight_scale - the type of scale used for brightness values * * The type of scale used for brightness values. @@ -110,7 +93,6 @@ enum backlight_scale { }; struct backlight_device; -struct fb_info; /** * struct backlight_ops - backlight operations @@ -160,18 +142,18 @@ struct backlight_ops { int (*get_brightness)(struct backlight_device *); /** - * @check_fb: Check the framebuffer device. + * @controls_device: Check against the display device * - * Check if given framebuffer device is the one bound to this backlight. - * This operation is optional and if not implemented it is assumed that the - * fbdev is always the one bound to the backlight. + * Check if the backlight controls the given display device. This + * operation is optional and if not implemented it is assumed that + * the display is always the one controlled by the backlight. * * RETURNS: * - * If info is NULL or the info matches the fbdev bound to the backlight return true. - * If info does not match the fbdev bound to the backlight return false. + * If display_dev is NULL or display_dev matches the device controlled by + * the backlight, return true. Otherwise return false. */ - int (*check_fb)(struct backlight_device *bd, struct fb_info *info); + bool (*controls_device)(struct backlight_device *bd, struct device *display_dev); }; /** @@ -209,33 +191,18 @@ struct backlight_properties { * attribute: /sys/class/backlight/<backlight>/bl_power * When the power property is updated update_status() is called. * - * The possible values are: (0: full on, 1 to 3: power saving - * modes; 4: full off), see FB_BLANK_XXX. + * The possible values are: (0: full on, 4: full off), see + * BACKLIGHT_POWER constants. * - * When the backlight device is enabled @power is set - * to FB_BLANK_UNBLANK. When the backlight device is disabled - * @power is set to FB_BLANK_POWERDOWN. + * When the backlight device is enabled, @power is set to + * BACKLIGHT_POWER_ON. When the backlight device is disabled, + * @power is set to BACKLIGHT_POWER_OFF. */ int power; - /** - * @fb_blank: The power state from the FBIOBLANK ioctl. - * - * When the FBIOBLANK ioctl is called @fb_blank is set to the - * blank parameter and the update_status() operation is called. - * - * When the backlight device is enabled @fb_blank is set - * to FB_BLANK_UNBLANK. When the backlight device is disabled - * @fb_blank is set to FB_BLANK_POWERDOWN. - * - * Backlight drivers should avoid using this property. It has been - * replaced by state & BL_CORE_FBLANK (although most drivers should - * use backlight_is_blank() as the preferred means to get the blank - * state). - * - * fb_blank is deprecated and will be removed. - */ - int fb_blank; +#define BACKLIGHT_POWER_ON (0) +#define BACKLIGHT_POWER_OFF (4) +#define BACKLIGHT_POWER_REDUCED (1) // deprecated; don't use in new code /** * @type: The type of backlight supported. @@ -365,8 +332,7 @@ static inline int backlight_enable(struct backlight_device *bd) if (!bd) return 0; - bd->props.power = FB_BLANK_UNBLANK; - bd->props.fb_blank = FB_BLANK_UNBLANK; + bd->props.power = BACKLIGHT_POWER_ON; bd->props.state &= ~BL_CORE_FBBLANK; return backlight_update_status(bd); @@ -381,8 +347,7 @@ static inline int backlight_disable(struct backlight_device *bd) if (!bd) return 0; - bd->props.power = FB_BLANK_POWERDOWN; - bd->props.fb_blank = FB_BLANK_POWERDOWN; + bd->props.power = BACKLIGHT_POWER_OFF; bd->props.state |= BL_CORE_FBBLANK; return backlight_update_status(bd); @@ -395,15 +360,13 @@ static inline int backlight_disable(struct backlight_device *bd) * Display is expected to be blank if any of these is true:: * * 1) if power in not UNBLANK - * 2) if fb_blank is not UNBLANK - * 3) if state indicate BLANK or SUSPENDED + * 2) if state indicate BLANK or SUSPENDED * * Returns true if display is expected to be blank, false otherwise. */ static inline bool backlight_is_blank(const struct backlight_device *bd) { - return bd->props.power != FB_BLANK_UNBLANK || - bd->props.fb_blank != FB_BLANK_UNBLANK || + return bd->props.power != BACKLIGHT_POWER_ON || bd->props.state & (BL_CORE_SUSPENDED | BL_CORE_FBBLANK); } @@ -440,8 +403,6 @@ void devm_backlight_device_unregister(struct device *dev, struct backlight_device *bd); void backlight_force_update(struct backlight_device *bd, enum backlight_update_reason reason); -int backlight_register_notifier(struct notifier_block *nb); -int backlight_unregister_notifier(struct notifier_block *nb); struct backlight_device *backlight_device_get_by_name(const char *name); struct backlight_device *backlight_device_get_by_type(enum backlight_type type); int backlight_device_set_brightness(struct backlight_device *bd, diff --git a/include/linux/bcma/bcma_driver_pci.h b/include/linux/bcma/bcma_driver_pci.h index 68da8dba5162..dba41b65ae0d 100644 --- a/include/linux/bcma/bcma_driver_pci.h +++ b/include/linux/bcma/bcma_driver_pci.h @@ -203,7 +203,7 @@ struct pci_dev; #define BCMA_CORE_PCI_MDIO_RXCTRL0 0x840 /* PCIE Root Capability Register bits (Host mode only) */ -#define BCMA_CORE_PCI_RC_CRS_VISIBILITY 0x0001 +#define BCMA_CORE_PCI_RC_RRS_VISIBILITY 0x0001 struct bcma_drv_pci; struct bcma_bus; diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 70f97f685bff..60d674af3080 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -19,13 +19,13 @@ struct linux_binprm { #ifdef CONFIG_MMU struct vm_area_struct *vma; unsigned long vma_pages; + unsigned long argmin; /* rlimit marker for copy_strings() */ #else # define MAX_ARG_PAGES 32 struct page *page[MAX_ARG_PAGES]; #endif struct mm_struct *mm; unsigned long p; /* current top of mem */ - unsigned long argmin; /* rlimit marker for copy_strings() */ unsigned int /* Should an execfd be passed to userspace? */ have_execfd:1, @@ -42,7 +42,14 @@ struct linux_binprm { * Set when errors can no longer be returned to the * original userspace. */ - point_of_no_return:1; + point_of_no_return:1, + /* Set when "comm" must come from the dentry. */ + comm_from_dentry:1, + /* + * Set by user space to check executability according to the + * caller's environment. + */ + is_check:1; struct file *executable; /* Executable to pass to the interpreter */ struct file *interpreter; struct file *file; diff --git a/include/linux/bio-integrity.h b/include/linux/bio-integrity.h new file mode 100644 index 000000000000..802f52e38efd --- /dev/null +++ b/include/linux/bio-integrity.h @@ -0,0 +1,163 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_BIO_INTEGRITY_H +#define _LINUX_BIO_INTEGRITY_H + +#include <linux/bio.h> + +enum bip_flags { + BIP_BLOCK_INTEGRITY = 1 << 0, /* block layer owns integrity data */ + BIP_MAPPED_INTEGRITY = 1 << 1, /* ref tag has been remapped */ + BIP_DISK_NOCHECK = 1 << 2, /* disable disk integrity checking */ + BIP_IP_CHECKSUM = 1 << 3, /* IP checksum */ + BIP_COPY_USER = 1 << 4, /* Kernel bounce buffer in use */ + BIP_CHECK_GUARD = 1 << 5, /* guard check */ + BIP_CHECK_REFTAG = 1 << 6, /* reftag check */ + BIP_CHECK_APPTAG = 1 << 7, /* apptag check */ +}; + +struct bio_integrity_payload { + struct bio *bip_bio; /* parent bio */ + + struct bvec_iter bip_iter; + + unsigned short bip_vcnt; /* # of integrity bio_vecs */ + unsigned short bip_max_vcnt; /* integrity bio_vec slots */ + unsigned short bip_flags; /* control flags */ + u16 app_tag; /* application tag value */ + + struct bvec_iter bio_iter; /* for rewinding parent bio */ + + struct work_struct bip_work; /* I/O completion */ + + struct bio_vec *bip_vec; + struct bio_vec bip_inline_vecs[];/* embedded bvec array */ +}; + +#define BIP_CLONE_FLAGS (BIP_MAPPED_INTEGRITY | BIP_IP_CHECKSUM | \ + BIP_CHECK_GUARD | BIP_CHECK_REFTAG | BIP_CHECK_APPTAG) + +#ifdef CONFIG_BLK_DEV_INTEGRITY + +#define bip_for_each_vec(bvl, bip, iter) \ + for_each_bvec(bvl, (bip)->bip_vec, iter, (bip)->bip_iter) + +#define bio_for_each_integrity_vec(_bvl, _bio, _iter) \ + for_each_bio(_bio) \ + bip_for_each_vec(_bvl, _bio->bi_integrity, _iter) + +static inline struct bio_integrity_payload *bio_integrity(struct bio *bio) +{ + if (bio->bi_opf & REQ_INTEGRITY) + return bio->bi_integrity; + + return NULL; +} + +static inline bool bio_integrity_flagged(struct bio *bio, enum bip_flags flag) +{ + struct bio_integrity_payload *bip = bio_integrity(bio); + + if (bip) + return bip->bip_flags & flag; + + return false; +} + +static inline sector_t bip_get_seed(struct bio_integrity_payload *bip) +{ + return bip->bip_iter.bi_sector; +} + +static inline void bip_set_seed(struct bio_integrity_payload *bip, + sector_t seed) +{ + bip->bip_iter.bi_sector = seed; +} + +struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio, gfp_t gfp, + unsigned int nr); +int bio_integrity_add_page(struct bio *bio, struct page *page, unsigned int len, + unsigned int offset); +int bio_integrity_map_user(struct bio *bio, struct iov_iter *iter); +int bio_integrity_map_iter(struct bio *bio, struct uio_meta *meta); +void bio_integrity_unmap_user(struct bio *bio); +bool bio_integrity_prep(struct bio *bio); +void bio_integrity_advance(struct bio *bio, unsigned int bytes_done); +void bio_integrity_trim(struct bio *bio); +int bio_integrity_clone(struct bio *bio, struct bio *bio_src, gfp_t gfp_mask); +int bioset_integrity_create(struct bio_set *bs, int pool_size); +void bioset_integrity_free(struct bio_set *bs); +void bio_integrity_init(void); + +#else /* CONFIG_BLK_DEV_INTEGRITY */ + +static inline struct bio_integrity_payload *bio_integrity(struct bio *bio) +{ + return NULL; +} + +static inline int bioset_integrity_create(struct bio_set *bs, int pool_size) +{ + return 0; +} + +static inline void bioset_integrity_free(struct bio_set *bs) +{ +} + +static inline int bio_integrity_map_user(struct bio *bio, struct iov_iter *iter) +{ + return -EINVAL; +} + +static inline int bio_integrity_map_iter(struct bio *bio, struct uio_meta *meta) +{ + return -EINVAL; +} + +static inline void bio_integrity_unmap_user(struct bio *bio) +{ +} + +static inline bool bio_integrity_prep(struct bio *bio) +{ + return true; +} + +static inline int bio_integrity_clone(struct bio *bio, struct bio *bio_src, + gfp_t gfp_mask) +{ + return 0; +} + +static inline void bio_integrity_advance(struct bio *bio, + unsigned int bytes_done) +{ +} + +static inline void bio_integrity_trim(struct bio *bio) +{ +} + +static inline void bio_integrity_init(void) +{ +} + +static inline bool bio_integrity_flagged(struct bio *bio, enum bip_flags flag) +{ + return false; +} + +static inline struct bio_integrity_payload * +bio_integrity_alloc(struct bio *bio, gfp_t gfp, unsigned int nr) +{ + return ERR_PTR(-EINVAL); +} + +static inline int bio_integrity_add_page(struct bio *bio, struct page *page, + unsigned int len, unsigned int offset) +{ + return 0; +} +#endif /* CONFIG_BLK_DEV_INTEGRITY */ +#endif /* _LINUX_BIO_INTEGRITY_H */ diff --git a/include/linux/bio.h b/include/linux/bio.h index 875d792bffff..4b79bf50f4f0 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -19,9 +19,6 @@ static inline unsigned int bio_max_segs(unsigned int nr_segs) return min(nr_segs, BIO_MAX_VECS); } -#define bio_prio(bio) (bio)->bi_ioprio -#define bio_set_prio(bio, prio) ((bio)->bi_ioprio = prio) - #define bio_iter_iovec(bio, iter) \ bvec_iter_bvec((bio)->bi_io_vec, (iter)) @@ -321,74 +318,11 @@ static inline void bio_next_folio(struct folio_iter *fi, struct bio *bio) #define bio_for_each_folio_all(fi, bio) \ for (bio_first_folio(&fi, bio, 0); fi.folio; bio_next_folio(&fi, bio)) -enum bip_flags { - BIP_BLOCK_INTEGRITY = 1 << 0, /* block layer owns integrity data */ - BIP_MAPPED_INTEGRITY = 1 << 1, /* ref tag has been remapped */ - BIP_CTRL_NOCHECK = 1 << 2, /* disable HBA integrity checking */ - BIP_DISK_NOCHECK = 1 << 3, /* disable disk integrity checking */ - BIP_IP_CHECKSUM = 1 << 4, /* IP checksum */ - BIP_INTEGRITY_USER = 1 << 5, /* Integrity payload is user address */ - BIP_COPY_USER = 1 << 6, /* Kernel bounce buffer in use */ -}; - -/* - * bio integrity payload - */ -struct bio_integrity_payload { - struct bio *bip_bio; /* parent bio */ - - struct bvec_iter bip_iter; - - unsigned short bip_vcnt; /* # of integrity bio_vecs */ - unsigned short bip_max_vcnt; /* integrity bio_vec slots */ - unsigned short bip_flags; /* control flags */ - - struct bvec_iter bio_iter; /* for rewinding parent bio */ - - struct work_struct bip_work; /* I/O completion */ - - struct bio_vec *bip_vec; - struct bio_vec bip_inline_vecs[];/* embedded bvec array */ -}; - -#if defined(CONFIG_BLK_DEV_INTEGRITY) - -static inline struct bio_integrity_payload *bio_integrity(struct bio *bio) -{ - if (bio->bi_opf & REQ_INTEGRITY) - return bio->bi_integrity; - - return NULL; -} - -static inline bool bio_integrity_flagged(struct bio *bio, enum bip_flags flag) -{ - struct bio_integrity_payload *bip = bio_integrity(bio); - - if (bip) - return bip->bip_flags & flag; - - return false; -} - -static inline sector_t bip_get_seed(struct bio_integrity_payload *bip) -{ - return bip->bip_iter.bi_sector; -} - -static inline void bip_set_seed(struct bio_integrity_payload *bip, - sector_t seed) -{ - bip->bip_iter.bi_sector = seed; -} - -#endif /* CONFIG_BLK_DEV_INTEGRITY */ - void bio_trim(struct bio *bio, sector_t offset, sector_t size); extern struct bio *bio_split(struct bio *bio, int sectors, gfp_t gfp, struct bio_set *bs); -struct bio *bio_split_rw(struct bio *bio, const struct queue_limits *lim, - unsigned *segs, struct bio_set *bs, unsigned max_bytes); +int bio_split_rw_at(struct bio *bio, const struct queue_limits *lim, + unsigned *segs, unsigned max_bytes); /** * bio_next_split - get next @sectors from a bio, splitting if necessary @@ -479,16 +413,12 @@ int __must_check bio_add_page(struct bio *bio, struct page *page, unsigned len, unsigned off); bool __must_check bio_add_folio(struct bio *bio, struct folio *folio, size_t len, size_t off); -extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *, - unsigned int, unsigned int); -int bio_add_zone_append_page(struct bio *bio, struct page *page, - unsigned int len, unsigned int offset); void __bio_add_page(struct bio *bio, struct page *page, unsigned int len, unsigned int off); void bio_add_folio_nofail(struct bio *bio, struct folio *folio, size_t len, size_t off); int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter); -void bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter); +void bio_iov_bvec_set(struct bio *bio, const struct iov_iter *iter); void __bio_release_pages(struct bio *bio, bool mark_dirty); extern void bio_set_pages_dirty(struct bio *bio); extern void bio_check_pages_dirty(struct bio *bio); @@ -615,6 +545,13 @@ static inline void bio_list_merge(struct bio_list *bl, struct bio_list *bl2) bl->tail = bl2->tail; } +static inline void bio_list_merge_init(struct bio_list *bl, + struct bio_list *bl2) +{ + bio_list_merge(bl, bl2); + bio_list_init(bl2); +} + static inline void bio_list_merge_head(struct bio_list *bl, struct bio_list *bl2) { @@ -714,95 +651,6 @@ static inline bool bioset_initialized(struct bio_set *bs) return bs->bio_slab != NULL; } -#if defined(CONFIG_BLK_DEV_INTEGRITY) - -#define bip_for_each_vec(bvl, bip, iter) \ - for_each_bvec(bvl, (bip)->bip_vec, iter, (bip)->bip_iter) - -#define bio_for_each_integrity_vec(_bvl, _bio, _iter) \ - for_each_bio(_bio) \ - bip_for_each_vec(_bvl, _bio->bi_integrity, _iter) - -int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t len, u32 seed); -extern struct bio_integrity_payload *bio_integrity_alloc(struct bio *, gfp_t, unsigned int); -extern int bio_integrity_add_page(struct bio *, struct page *, unsigned int, unsigned int); -extern bool bio_integrity_prep(struct bio *); -extern void bio_integrity_advance(struct bio *, unsigned int); -extern void bio_integrity_trim(struct bio *); -extern int bio_integrity_clone(struct bio *, struct bio *, gfp_t); -extern int bioset_integrity_create(struct bio_set *, int); -extern void bioset_integrity_free(struct bio_set *); -extern void bio_integrity_init(void); - -#else /* CONFIG_BLK_DEV_INTEGRITY */ - -static inline void *bio_integrity(struct bio *bio) -{ - return NULL; -} - -static inline int bioset_integrity_create(struct bio_set *bs, int pool_size) -{ - return 0; -} - -static inline void bioset_integrity_free (struct bio_set *bs) -{ - return; -} - -static inline bool bio_integrity_prep(struct bio *bio) -{ - return true; -} - -static inline int bio_integrity_clone(struct bio *bio, struct bio *bio_src, - gfp_t gfp_mask) -{ - return 0; -} - -static inline void bio_integrity_advance(struct bio *bio, - unsigned int bytes_done) -{ - return; -} - -static inline void bio_integrity_trim(struct bio *bio) -{ - return; -} - -static inline void bio_integrity_init(void) -{ - return; -} - -static inline bool bio_integrity_flagged(struct bio *bio, enum bip_flags flag) -{ - return false; -} - -static inline void *bio_integrity_alloc(struct bio * bio, gfp_t gfp, - unsigned int nr) -{ - return ERR_PTR(-EINVAL); -} - -static inline int bio_integrity_add_page(struct bio *bio, struct page *page, - unsigned int len, unsigned int offset) -{ - return 0; -} - -static inline int bio_integrity_map_user(struct bio *bio, void __user *ubuf, - ssize_t len, u32 seed) -{ - return -EINVAL; -} - -#endif /* CONFIG_BLK_DEV_INTEGRITY */ - /* * Mark a bio as polled. Note that for async polled IO, the caller must * expect -EWOULDBLOCK if we cannot allocate a request (or other resources). @@ -822,7 +670,28 @@ static inline void bio_clear_polled(struct bio *bio) bio->bi_opf &= ~REQ_POLLED; } +/** + * bio_is_zone_append - is this a zone append bio? + * @bio: bio to check + * + * Check if @bio is a zone append operation. Core block layer code and end_io + * handlers must use this instead of an open coded REQ_OP_ZONE_APPEND check + * because the block layer can rewrite REQ_OP_ZONE_APPEND to REQ_OP_WRITE if + * it is not natively supported. + */ +static inline bool bio_is_zone_append(struct bio *bio) +{ + if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED)) + return false; + return bio_op(bio) == REQ_OP_ZONE_APPEND || + bio_flagged(bio, BIO_EMULATES_ZONE_APPEND); +} + struct bio *blk_next_bio(struct bio *bio, struct block_device *bdev, unsigned int nr_pages, blk_opf_t opf, gfp_t gfp); +struct bio *bio_chain_and_submit(struct bio *prev, struct bio *new); + +struct bio *blk_alloc_discard_bio(struct block_device *bdev, + sector_t *sector, sector_t *nr_sects, gfp_t gfp_mask); #endif /* __LINUX_BIO_H */ diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index aa4096126553..2026953e2c4e 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -23,7 +23,7 @@ struct device; * * Function implementations generic to all architectures are in * lib/bitmap.c. Functions implementations that are architecture - * specific are in various include/asm-<arch>/bitops.h headers + * specific are in various arch/<arch>/include/asm/bitops.h headers * and other arch/<arch> specific files. * * See lib/bitmap.c for more details. @@ -83,6 +83,10 @@ struct device; * bitmap_to_arr64(buf, src, nbits) Copy nbits from buf to u64[] dst * bitmap_get_value8(map, start) Get 8bit value from map at start * bitmap_set_value8(map, value, start) Set 8bit value to map at start + * bitmap_read(map, start, nbits) Read an nbits-sized value from + * map at start + * bitmap_write(map, value, start, nbits) Write an nbits-sized value to + * map at start * * Note, bitmap_zero() and bitmap_fill() operate over the region of * unsigned longs, that is, bits behind bitmap till the unsigned long @@ -199,12 +203,12 @@ unsigned long bitmap_find_next_zero_area_off(unsigned long *map, * the bit offset of all zero areas this function finds is multiples of that * power of 2. A @align_mask of 0 means no alignment is required. */ -static inline unsigned long -bitmap_find_next_zero_area(unsigned long *map, - unsigned long size, - unsigned long start, - unsigned int nr, - unsigned long align_mask) +static __always_inline +unsigned long bitmap_find_next_zero_area(unsigned long *map, + unsigned long size, + unsigned long start, + unsigned int nr, + unsigned long align_mask) { return bitmap_find_next_zero_area_off(map, size, start, nr, align_mask, 0); @@ -222,9 +226,11 @@ void bitmap_fold(unsigned long *dst, const unsigned long *orig, #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1))) #define BITMAP_LAST_WORD_MASK(nbits) (~0UL >> (-(nbits) & (BITS_PER_LONG - 1))) -static inline void bitmap_zero(unsigned long *dst, unsigned int nbits) +#define bitmap_size(nbits) (ALIGN(nbits, BITS_PER_LONG) / BITS_PER_BYTE) + +static __always_inline void bitmap_zero(unsigned long *dst, unsigned int nbits) { - unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); + unsigned int len = bitmap_size(nbits); if (small_const_nbits(nbits)) *dst = 0; @@ -232,9 +238,9 @@ static inline void bitmap_zero(unsigned long *dst, unsigned int nbits) memset(dst, 0, len); } -static inline void bitmap_fill(unsigned long *dst, unsigned int nbits) +static __always_inline void bitmap_fill(unsigned long *dst, unsigned int nbits) { - unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); + unsigned int len = bitmap_size(nbits); if (small_const_nbits(nbits)) *dst = ~0UL; @@ -242,10 +248,10 @@ static inline void bitmap_fill(unsigned long *dst, unsigned int nbits) memset(dst, 0xff, len); } -static inline void bitmap_copy(unsigned long *dst, const unsigned long *src, - unsigned int nbits) +static __always_inline +void bitmap_copy(unsigned long *dst, const unsigned long *src, unsigned int nbits) { - unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); + unsigned int len = bitmap_size(nbits); if (small_const_nbits(nbits)) *dst = *src; @@ -256,14 +262,26 @@ static inline void bitmap_copy(unsigned long *dst, const unsigned long *src, /* * Copy bitmap and clear tail bits in last word. */ -static inline void bitmap_copy_clear_tail(unsigned long *dst, - const unsigned long *src, unsigned int nbits) +static __always_inline +void bitmap_copy_clear_tail(unsigned long *dst, const unsigned long *src, unsigned int nbits) { bitmap_copy(dst, src, nbits); if (nbits % BITS_PER_LONG) dst[nbits / BITS_PER_LONG] &= BITMAP_LAST_WORD_MASK(nbits); } +static inline void bitmap_copy_and_extend(unsigned long *to, + const unsigned long *from, + unsigned int count, unsigned int size) +{ + unsigned int copy = BITS_TO_LONGS(count); + + memcpy(to, from, copy * sizeof(long)); + if (count % BITS_PER_LONG) + to[copy - 1] &= BITMAP_LAST_WORD_MASK(count); + memset(to + copy, 0, bitmap_size(size) - copy * sizeof(long)); +} + /* * On 32-bit systems bitmaps are represented as u32 arrays internally. On LE64 * machines the order of hi and lo parts of numbers match the bitmap structure. @@ -300,16 +318,18 @@ void bitmap_to_arr64(u64 *buf, const unsigned long *bitmap, unsigned int nbits); bitmap_copy_clear_tail((unsigned long *)(buf), (const unsigned long *)(bitmap), (nbits)) #endif -static inline bool bitmap_and(unsigned long *dst, const unsigned long *src1, - const unsigned long *src2, unsigned int nbits) +static __always_inline +bool bitmap_and(unsigned long *dst, const unsigned long *src1, + const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return (*dst = *src1 & *src2 & BITMAP_LAST_WORD_MASK(nbits)) != 0; return __bitmap_and(dst, src1, src2, nbits); } -static inline void bitmap_or(unsigned long *dst, const unsigned long *src1, - const unsigned long *src2, unsigned int nbits) +static __always_inline +void bitmap_or(unsigned long *dst, const unsigned long *src1, + const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = *src1 | *src2; @@ -317,8 +337,9 @@ static inline void bitmap_or(unsigned long *dst, const unsigned long *src1, __bitmap_or(dst, src1, src2, nbits); } -static inline void bitmap_xor(unsigned long *dst, const unsigned long *src1, - const unsigned long *src2, unsigned int nbits) +static __always_inline +void bitmap_xor(unsigned long *dst, const unsigned long *src1, + const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = *src1 ^ *src2; @@ -326,16 +347,17 @@ static inline void bitmap_xor(unsigned long *dst, const unsigned long *src1, __bitmap_xor(dst, src1, src2, nbits); } -static inline bool bitmap_andnot(unsigned long *dst, const unsigned long *src1, - const unsigned long *src2, unsigned int nbits) +static __always_inline +bool bitmap_andnot(unsigned long *dst, const unsigned long *src1, + const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return (*dst = *src1 & ~(*src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0; return __bitmap_andnot(dst, src1, src2, nbits); } -static inline void bitmap_complement(unsigned long *dst, const unsigned long *src, - unsigned int nbits) +static __always_inline +void bitmap_complement(unsigned long *dst, const unsigned long *src, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = ~(*src); @@ -350,8 +372,8 @@ static inline void bitmap_complement(unsigned long *dst, const unsigned long *sr #endif #define BITMAP_MEM_MASK (BITMAP_MEM_ALIGNMENT - 1) -static inline bool bitmap_equal(const unsigned long *src1, - const unsigned long *src2, unsigned int nbits) +static __always_inline +bool bitmap_equal(const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return !((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits)); @@ -370,10 +392,9 @@ static inline bool bitmap_equal(const unsigned long *src1, * * Returns: True if (*@src1 | *@src2) == *@src3, false otherwise */ -static inline bool bitmap_or_equal(const unsigned long *src1, - const unsigned long *src2, - const unsigned long *src3, - unsigned int nbits) +static __always_inline +bool bitmap_or_equal(const unsigned long *src1, const unsigned long *src2, + const unsigned long *src3, unsigned int nbits) { if (!small_const_nbits(nbits)) return __bitmap_or_equal(src1, src2, src3, nbits); @@ -381,9 +402,8 @@ static inline bool bitmap_or_equal(const unsigned long *src1, return !(((*src1 | *src2) ^ *src3) & BITMAP_LAST_WORD_MASK(nbits)); } -static inline bool bitmap_intersects(const unsigned long *src1, - const unsigned long *src2, - unsigned int nbits) +static __always_inline +bool bitmap_intersects(const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return ((*src1 & *src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0; @@ -391,8 +411,8 @@ static inline bool bitmap_intersects(const unsigned long *src1, return __bitmap_intersects(src1, src2, nbits); } -static inline bool bitmap_subset(const unsigned long *src1, - const unsigned long *src2, unsigned int nbits) +static __always_inline +bool bitmap_subset(const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return ! ((*src1 & ~(*src2)) & BITMAP_LAST_WORD_MASK(nbits)); @@ -400,7 +420,8 @@ static inline bool bitmap_subset(const unsigned long *src1, return __bitmap_subset(src1, src2, nbits); } -static inline bool bitmap_empty(const unsigned long *src, unsigned nbits) +static __always_inline +bool bitmap_empty(const unsigned long *src, unsigned nbits) { if (small_const_nbits(nbits)) return ! (*src & BITMAP_LAST_WORD_MASK(nbits)); @@ -408,7 +429,8 @@ static inline bool bitmap_empty(const unsigned long *src, unsigned nbits) return find_first_bit(src, nbits) == nbits; } -static inline bool bitmap_full(const unsigned long *src, unsigned int nbits) +static __always_inline +bool bitmap_full(const unsigned long *src, unsigned int nbits) { if (small_const_nbits(nbits)) return ! (~(*src) & BITMAP_LAST_WORD_MASK(nbits)); @@ -442,8 +464,8 @@ unsigned long bitmap_weight_andnot(const unsigned long *src1, return __bitmap_weight_andnot(src1, src2, nbits); } -static __always_inline void bitmap_set(unsigned long *map, unsigned int start, - unsigned int nbits) +static __always_inline +void bitmap_set(unsigned long *map, unsigned int start, unsigned int nbits) { if (__builtin_constant_p(nbits) && nbits == 1) __set_bit(start, map); @@ -458,8 +480,8 @@ static __always_inline void bitmap_set(unsigned long *map, unsigned int start, __bitmap_set(map, start, nbits); } -static __always_inline void bitmap_clear(unsigned long *map, unsigned int start, - unsigned int nbits) +static __always_inline +void bitmap_clear(unsigned long *map, unsigned int start, unsigned int nbits) { if (__builtin_constant_p(nbits) && nbits == 1) __clear_bit(start, map); @@ -474,8 +496,9 @@ static __always_inline void bitmap_clear(unsigned long *map, unsigned int start, __bitmap_clear(map, start, nbits); } -static inline void bitmap_shift_right(unsigned long *dst, const unsigned long *src, - unsigned int shift, unsigned int nbits) +static __always_inline +void bitmap_shift_right(unsigned long *dst, const unsigned long *src, + unsigned int shift, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = (*src & BITMAP_LAST_WORD_MASK(nbits)) >> shift; @@ -483,8 +506,9 @@ static inline void bitmap_shift_right(unsigned long *dst, const unsigned long *s __bitmap_shift_right(dst, src, shift, nbits); } -static inline void bitmap_shift_left(unsigned long *dst, const unsigned long *src, - unsigned int shift, unsigned int nbits) +static __always_inline +void bitmap_shift_left(unsigned long *dst, const unsigned long *src, + unsigned int shift, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = (*src << shift) & BITMAP_LAST_WORD_MASK(nbits); @@ -492,11 +516,12 @@ static inline void bitmap_shift_left(unsigned long *dst, const unsigned long *sr __bitmap_shift_left(dst, src, shift, nbits); } -static inline void bitmap_replace(unsigned long *dst, - const unsigned long *old, - const unsigned long *new, - const unsigned long *mask, - unsigned int nbits) +static __always_inline +void bitmap_replace(unsigned long *dst, + const unsigned long *old, + const unsigned long *new, + const unsigned long *mask, + unsigned int nbits) { if (small_const_nbits(nbits)) *dst = (*old & ~(*mask)) | (*new & *mask); @@ -539,8 +564,9 @@ static inline void bitmap_replace(unsigned long *dst, * bitmap_gather() can be seen as the 'reverse' bitmap_scatter() operation. * See bitmap_scatter() for details related to this relationship. */ -static inline void bitmap_scatter(unsigned long *dst, const unsigned long *src, - const unsigned long *mask, unsigned int nbits) +static __always_inline +void bitmap_scatter(unsigned long *dst, const unsigned long *src, + const unsigned long *mask, unsigned int nbits) { unsigned int n = 0; unsigned int bit; @@ -593,8 +619,9 @@ static inline void bitmap_scatter(unsigned long *dst, const unsigned long *src, * bitmap_scatter(res, src, mask, n) and a call to * bitmap_scatter(res, result, mask, n) will lead to the same res value. */ -static inline void bitmap_gather(unsigned long *dst, const unsigned long *src, - const unsigned long *mask, unsigned int nbits) +static __always_inline +void bitmap_gather(unsigned long *dst, const unsigned long *src, + const unsigned long *mask, unsigned int nbits) { unsigned int n = 0; unsigned int bit; @@ -605,9 +632,9 @@ static inline void bitmap_gather(unsigned long *dst, const unsigned long *src, __assign_bit(n++, dst, test_bit(bit, src)); } -static inline void bitmap_next_set_region(unsigned long *bitmap, - unsigned int *rs, unsigned int *re, - unsigned int end) +static __always_inline +void bitmap_next_set_region(unsigned long *bitmap, unsigned int *rs, + unsigned int *re, unsigned int end) { *rs = find_next_bit(bitmap, end, *rs); *re = find_next_zero_bit(bitmap, end, *rs + 1); @@ -622,7 +649,8 @@ static inline void bitmap_next_set_region(unsigned long *bitmap, * This is the complement to __bitmap_find_free_region() and releases * the found region (by clearing it in the bitmap). */ -static inline void bitmap_release_region(unsigned long *bitmap, unsigned int pos, int order) +static __always_inline +void bitmap_release_region(unsigned long *bitmap, unsigned int pos, int order) { bitmap_clear(bitmap, pos, BIT(order)); } @@ -638,7 +666,8 @@ static inline void bitmap_release_region(unsigned long *bitmap, unsigned int pos * Returns: 0 on success, or %-EBUSY if specified region wasn't * free (not all bits were zero). */ -static inline int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order) +static __always_inline +int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order) { unsigned int len = BIT(order); @@ -662,7 +691,8 @@ static inline int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos * Returns: the bit offset in bitmap of the allocated region, * or -errno on failure. */ -static inline int bitmap_find_free_region(unsigned long *bitmap, unsigned int bits, int order) +static __always_inline +int bitmap_find_free_region(unsigned long *bitmap, unsigned int bits, int order) { unsigned int pos, end; /* scans bitmap by regions of size order */ @@ -716,44 +746,89 @@ static inline int bitmap_find_free_region(unsigned long *bitmap, unsigned int bi * That is ``(u32 *)(&val)[0]`` gets the upper 32 bits, * but we expect the lower 32-bits of u64. */ -static inline void bitmap_from_u64(unsigned long *dst, u64 mask) +static __always_inline void bitmap_from_u64(unsigned long *dst, u64 mask) { bitmap_from_arr64(dst, &mask, 64); } /** - * bitmap_get_value8 - get an 8-bit value within a memory region + * bitmap_read - read a value of n-bits from the memory region * @map: address to the bitmap memory region - * @start: bit offset of the 8-bit value; must be a multiple of 8 + * @start: bit offset of the n-bit value + * @nbits: size of value in bits, nonzero, up to BITS_PER_LONG * - * Returns the 8-bit value located at the @start bit offset within the @src - * memory region. + * Returns: value of @nbits bits located at the @start bit offset within the + * @map memory region. For @nbits = 0 and @nbits > BITS_PER_LONG the return + * value is undefined. */ -static inline unsigned long bitmap_get_value8(const unsigned long *map, - unsigned long start) +static __always_inline +unsigned long bitmap_read(const unsigned long *map, unsigned long start, unsigned long nbits) { - const size_t index = BIT_WORD(start); - const unsigned long offset = start % BITS_PER_LONG; + size_t index = BIT_WORD(start); + unsigned long offset = start % BITS_PER_LONG; + unsigned long space = BITS_PER_LONG - offset; + unsigned long value_low, value_high; - return (map[index] >> offset) & 0xFF; + if (unlikely(!nbits || nbits > BITS_PER_LONG)) + return 0; + + if (space >= nbits) + return (map[index] >> offset) & BITMAP_LAST_WORD_MASK(nbits); + + value_low = map[index] & BITMAP_FIRST_WORD_MASK(start); + value_high = map[index + 1] & BITMAP_LAST_WORD_MASK(start + nbits); + return (value_low >> offset) | (value_high << space); } /** - * bitmap_set_value8 - set an 8-bit value within a memory region + * bitmap_write - write n-bit value within a memory region * @map: address to the bitmap memory region - * @value: the 8-bit value; values wider than 8 bits may clobber bitmap - * @start: bit offset of the 8-bit value; must be a multiple of 8 + * @value: value to write, clamped to nbits + * @start: bit offset of the n-bit value + * @nbits: size of value in bits, nonzero, up to BITS_PER_LONG. + * + * bitmap_write() behaves as-if implemented as @nbits calls of __assign_bit(), + * i.e. bits beyond @nbits are ignored: + * + * for (bit = 0; bit < nbits; bit++) + * __assign_bit(start + bit, bitmap, val & BIT(bit)); + * + * For @nbits == 0 and @nbits > BITS_PER_LONG no writes are performed. */ -static inline void bitmap_set_value8(unsigned long *map, unsigned long value, - unsigned long start) +static __always_inline +void bitmap_write(unsigned long *map, unsigned long value, + unsigned long start, unsigned long nbits) { - const size_t index = BIT_WORD(start); - const unsigned long offset = start % BITS_PER_LONG; + size_t index; + unsigned long offset; + unsigned long space; + unsigned long mask; + bool fit; + + if (unlikely(!nbits || nbits > BITS_PER_LONG)) + return; + + mask = BITMAP_LAST_WORD_MASK(nbits); + value &= mask; + offset = start % BITS_PER_LONG; + space = BITS_PER_LONG - offset; + fit = space >= nbits; + index = BIT_WORD(start); - map[index] &= ~(0xFFUL << offset); + map[index] &= (fit ? (~(mask << offset)) : ~BITMAP_FIRST_WORD_MASK(start)); map[index] |= value << offset; + if (fit) + return; + + map[index + 1] &= BITMAP_FIRST_WORD_MASK(start + nbits); + map[index + 1] |= (value >> space); } +#define bitmap_get_value8(map, start) \ + bitmap_read(map, start, BITS_PER_BYTE) +#define bitmap_set_value8(map, value, start) \ + bitmap_write(map, value, start, BITS_PER_BYTE) + #endif /* __ASSEMBLY__ */ #endif /* __LINUX_BITMAP_H */ diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 2ba557e067fe..c1cb53cf2f0f 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -8,19 +8,14 @@ #include <uapi/linux/kernel.h> -/* Set bits in the first 'n' bytes when loaded from memory */ -#ifdef __LITTLE_ENDIAN -# define aligned_byte_mask(n) ((1UL << 8*(n))-1) -#else -# define aligned_byte_mask(n) (~0xffUL << (BITS_PER_LONG - 8 - 8*(n))) -#endif - #define BITS_PER_TYPE(type) (sizeof(type) * BITS_PER_BYTE) #define BITS_TO_LONGS(nr) __KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(long)) #define BITS_TO_U64(nr) __KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(u64)) #define BITS_TO_U32(nr) __KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(u32)) #define BITS_TO_BYTES(nr) __KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(char)) +#define BYTES_TO_BITS(nb) ((nb) * BITS_PER_BYTE) + extern unsigned int __sw_hweight8(unsigned int w); extern unsigned int __sw_hweight16(unsigned int w); extern unsigned int __sw_hweight32(unsigned int w); @@ -52,12 +47,17 @@ extern unsigned long __sw_hweight64(__u64 w); __builtin_constant_p(*(const unsigned long *)(addr))) ? \ const##op(nr, addr) : op(nr, addr)) +/* + * The following macros are non-atomic versions of their non-underscored + * counterparts. + */ #define __set_bit(nr, addr) bitop(___set_bit, nr, addr) #define __clear_bit(nr, addr) bitop(___clear_bit, nr, addr) #define __change_bit(nr, addr) bitop(___change_bit, nr, addr) #define __test_and_set_bit(nr, addr) bitop(___test_and_set_bit, nr, addr) #define __test_and_clear_bit(nr, addr) bitop(___test_and_clear_bit, nr, addr) #define __test_and_change_bit(nr, addr) bitop(___test_and_change_bit, nr, addr) + #define test_bit(nr, addr) bitop(_test_bit, nr, addr) #define test_bit_acquire(nr, addr) bitop(_test_bit_acquire, nr, addr) @@ -80,6 +80,7 @@ __check_bitop_pr(__test_and_set_bit); __check_bitop_pr(__test_and_clear_bit); __check_bitop_pr(__test_and_change_bit); __check_bitop_pr(test_bit); +__check_bitop_pr(test_bit_acquire); #undef __check_bitop_pr @@ -200,7 +201,7 @@ static __always_inline __s64 sign_extend64(__u64 value, int index) return (__s64)(value << shift) >> shift; } -static inline unsigned fls_long(unsigned long l) +static inline unsigned int fls_long(unsigned long l) { if (sizeof(l) == 4) return fls(l); @@ -229,6 +230,37 @@ static inline int get_count_order_long(unsigned long l) } /** + * parity8 - get the parity of an u8 value + * @value: the value to be examined + * + * Determine the parity of the u8 argument. + * + * Returns: + * 0 for even parity, 1 for odd parity + * + * Note: This function informs you about the current parity. Example to bail + * out when parity is odd: + * + * if (parity8(val) == 1) + * return -EBADMSG; + * + * If you need to calculate a parity bit, you need to draw the conclusion from + * this result yourself. Example to enforce odd parity, parity bit is bit 7: + * + * if (parity8(val) == 0) + * val ^= BIT(7); + */ +static inline int parity8(u8 val) +{ + /* + * One explanation of this algorithm: + * https://funloop.org/codex/problem/parity/README.html + */ + val ^= val >> 4; + return (0x6996 >> (val & 0xf)) & 1; +} + +/** * __ffs64 - find first set bit in a 64 bit word * @word: The 64 bit word * @@ -236,7 +268,7 @@ static inline int get_count_order_long(unsigned long l) * The result is not defined if no bits are set, so check that @word * is non-zero before calling this. */ -static inline unsigned long __ffs64(u64 word) +static inline unsigned int __ffs64(u64 word) { #if BITS_PER_LONG == 32 if (((u32)word) == 0UL) @@ -252,18 +284,12 @@ static inline unsigned long __ffs64(u64 word) * @word: The word to search * @n: Bit to find */ -static inline unsigned long fns(unsigned long word, unsigned int n) +static inline unsigned int fns(unsigned long word, unsigned int n) { - unsigned int bit; + while (word && n--) + word &= word - 1; - while (word) { - bit = __ffs(word); - if (n-- == 0) - return bit; - __clear_bit(bit, &word); - } - - return BITS_PER_LONG; + return word ? __ffs(word) : BITS_PER_LONG; } /** @@ -272,23 +298,11 @@ static inline unsigned long fns(unsigned long word, unsigned int n) * @addr: the address to start counting from * @value: the value to assign */ -static __always_inline void assign_bit(long nr, volatile unsigned long *addr, - bool value) -{ - if (value) - set_bit(nr, addr); - else - clear_bit(nr, addr); -} +#define assign_bit(nr, addr, value) \ + ((value) ? set_bit((nr), (addr)) : clear_bit((nr), (addr))) -static __always_inline void __assign_bit(long nr, volatile unsigned long *addr, - bool value) -{ - if (value) - __set_bit(nr, addr); - else - __clear_bit(nr, addr); -} +#define __assign_bit(nr, addr, value) \ + ((value) ? __set_bit((nr), (addr)) : __clear_bit((nr), (addr))) /** * __ptr_set_bit - Set bit in a pointer's value diff --git a/include/linux/bits.h b/include/linux/bits.h index 0eb24d21aac2..61a75d3f294b 100644 --- a/include/linux/bits.h +++ b/include/linux/bits.h @@ -20,9 +20,8 @@ */ #if !defined(__ASSEMBLY__) #include <linux/build_bug.h> -#define GENMASK_INPUT_CHECK(h, l) \ - (BUILD_BUG_ON_ZERO(__builtin_choose_expr( \ - __is_constexpr((l) > (h)), (l) > (h), 0))) +#include <linux/compiler.h> +#define GENMASK_INPUT_CHECK(h, l) BUILD_BUG_ON_ZERO(const_true((l) > (h))) #else /* * BUILD_BUG_ON_ZERO is not available in h files included from asm files, @@ -36,4 +35,19 @@ #define GENMASK_ULL(h, l) \ (GENMASK_INPUT_CHECK(h, l) + __GENMASK_ULL(h, l)) +#if !defined(__ASSEMBLY__) +/* + * Missing asm support + * + * __GENMASK_U128() depends on _BIT128() which would not work + * in the asm code, as it shifts an 'unsigned __init128' data + * type instead of direct representation of 128 bit constants + * such as long and unsigned long. The fundamental problem is + * that a 128 bit constant will get silently truncated by the + * gcc compiler. + */ +#define GENMASK_U128(h, l) \ + (GENMASK_INPUT_CHECK(h, l) + __GENMASK_U128(h, l)) +#endif + #endif /* __LINUX_BITS_H */ diff --git a/include/linux/blk-integrity.h b/include/linux/blk-integrity.h index e253e7bd0d17..c7eae0bfb013 100644 --- a/include/linux/blk-integrity.h +++ b/include/linux/blk-integrity.h @@ -3,55 +3,44 @@ #define _LINUX_BLK_INTEGRITY_H #include <linux/blk-mq.h> +#include <linux/bio-integrity.h> struct request; enum blk_integrity_flags { - BLK_INTEGRITY_VERIFY = 1 << 0, - BLK_INTEGRITY_GENERATE = 1 << 1, + BLK_INTEGRITY_NOVERIFY = 1 << 0, + BLK_INTEGRITY_NOGENERATE = 1 << 1, BLK_INTEGRITY_DEVICE_CAPABLE = 1 << 2, - BLK_INTEGRITY_IP_CHECKSUM = 1 << 3, + BLK_INTEGRITY_REF_TAG = 1 << 3, + BLK_INTEGRITY_STACKED = 1 << 4, }; -struct blk_integrity_iter { - void *prot_buf; - void *data_buf; - sector_t seed; - unsigned int data_size; - unsigned short interval; - unsigned char tuple_size; - unsigned char pi_offset; - const char *disk_name; -}; - -typedef blk_status_t (integrity_processing_fn) (struct blk_integrity_iter *); -typedef void (integrity_prepare_fn) (struct request *); -typedef void (integrity_complete_fn) (struct request *, unsigned int); - -struct blk_integrity_profile { - integrity_processing_fn *generate_fn; - integrity_processing_fn *verify_fn; - integrity_prepare_fn *prepare_fn; - integrity_complete_fn *complete_fn; - const char *name; -}; +const char *blk_integrity_profile_name(struct blk_integrity *bi); +bool queue_limits_stack_integrity(struct queue_limits *t, + struct queue_limits *b); +static inline bool queue_limits_stack_integrity_bdev(struct queue_limits *t, + struct block_device *bdev) +{ + return queue_limits_stack_integrity(t, &bdev->bd_disk->queue->limits); +} #ifdef CONFIG_BLK_DEV_INTEGRITY -void blk_integrity_register(struct gendisk *, struct blk_integrity *); -void blk_integrity_unregister(struct gendisk *); -int blk_integrity_compare(struct gendisk *, struct gendisk *); -int blk_rq_map_integrity_sg(struct request_queue *, struct bio *, - struct scatterlist *); +int blk_rq_map_integrity_sg(struct request *, struct scatterlist *); int blk_rq_count_integrity_sg(struct request_queue *, struct bio *); +int blk_rq_integrity_map_user(struct request *rq, void __user *ubuf, + ssize_t bytes); -static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk) +static inline bool +blk_integrity_queue_supports_integrity(struct request_queue *q) { - struct blk_integrity *bi = &disk->queue->integrity; + return q->limits.integrity.tuple_size; +} - if (!bi->profile) +static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk) +{ + if (!blk_integrity_queue_supports_integrity(disk->queue)) return NULL; - - return bi; + return &disk->queue->limits.integrity; } static inline struct blk_integrity * @@ -60,18 +49,6 @@ bdev_get_integrity(struct block_device *bdev) return blk_get_integrity(bdev->bd_disk); } -static inline bool -blk_integrity_queue_supports_integrity(struct request_queue *q) -{ - return q->integrity.profile; -} - -static inline void blk_queue_max_integrity_segments(struct request_queue *q, - unsigned int segs) -{ - q->limits.max_integrity_segments = segs; -} - static inline unsigned short queue_max_integrity_segments(const struct request_queue *q) { @@ -106,14 +83,13 @@ static inline bool blk_integrity_rq(struct request *rq) } /* - * Return the first bvec that contains integrity data. Only drivers that are - * limited to a single integrity segment should use this helper. + * Return the current bvec that contains the integrity data. bip_iter may be + * advanced to iterate over the integrity data. */ -static inline struct bio_vec *rq_integrity_vec(struct request *rq) +static inline struct bio_vec rq_integrity_vec(struct request *rq) { - if (WARN_ON_ONCE(queue_max_integrity_segments(rq->q) > 1)) - return NULL; - return rq->bio->bi_integrity->bip_vec; + return mp_bvec_iter_bvec(rq->bio->bi_integrity->bip_vec, + rq->bio->bi_integrity->bip_iter); } #else /* CONFIG_BLK_DEV_INTEGRITY */ static inline int blk_rq_count_integrity_sg(struct request_queue *q, @@ -121,12 +97,17 @@ static inline int blk_rq_count_integrity_sg(struct request_queue *q, { return 0; } -static inline int blk_rq_map_integrity_sg(struct request_queue *q, - struct bio *b, +static inline int blk_rq_map_integrity_sg(struct request *q, struct scatterlist *s) { return 0; } +static inline int blk_rq_integrity_map_user(struct request *rq, + void __user *ubuf, + ssize_t bytes) +{ + return -EINVAL; +} static inline struct blk_integrity *bdev_get_integrity(struct block_device *b) { return NULL; @@ -140,21 +121,6 @@ blk_integrity_queue_supports_integrity(struct request_queue *q) { return false; } -static inline int blk_integrity_compare(struct gendisk *a, struct gendisk *b) -{ - return 0; -} -static inline void blk_integrity_register(struct gendisk *d, - struct blk_integrity *b) -{ -} -static inline void blk_integrity_unregister(struct gendisk *d) -{ -} -static inline void blk_queue_max_integrity_segments(struct request_queue *q, - unsigned int segs) -{ -} static inline unsigned short queue_max_integrity_segments(const struct request_queue *q) { @@ -177,9 +143,11 @@ static inline int blk_integrity_rq(struct request *rq) return 0; } -static inline struct bio_vec *rq_integrity_vec(struct request *rq) +static inline struct bio_vec rq_integrity_vec(struct request *rq) { - return NULL; + /* the optimizer will remove all calls to this function */ + return (struct bio_vec){ }; } #endif /* CONFIG_BLK_DEV_INTEGRITY */ + #endif /* _LINUX_BLK_INTEGRITY_H */ diff --git a/include/linux/blk-mq-pci.h b/include/linux/blk-mq-pci.h deleted file mode 100644 index ca544e1d3508..000000000000 --- a/include/linux/blk-mq-pci.h +++ /dev/null @@ -1,11 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_BLK_MQ_PCI_H -#define _LINUX_BLK_MQ_PCI_H - -struct blk_mq_queue_map; -struct pci_dev; - -void blk_mq_pci_map_queues(struct blk_mq_queue_map *qmap, struct pci_dev *pdev, - int offset); - -#endif /* _LINUX_BLK_MQ_PCI_H */ diff --git a/include/linux/blk-mq-virtio.h b/include/linux/blk-mq-virtio.h deleted file mode 100644 index 13226e9b22dd..000000000000 --- a/include/linux/blk-mq-virtio.h +++ /dev/null @@ -1,11 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_BLK_MQ_VIRTIO_H -#define _LINUX_BLK_MQ_VIRTIO_H - -struct blk_mq_queue_map; -struct virtio_device; - -void blk_mq_virtio_map_queues(struct blk_mq_queue_map *qmap, - struct virtio_device *vdev, int first_vec); - -#endif /* _LINUX_BLK_MQ_VIRTIO_H */ diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index d3d8fd8e229b..9ebb53f031cd 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -27,38 +27,61 @@ typedef enum rq_end_io_ret (rq_end_io_fn)(struct request *, blk_status_t); * request flags */ typedef __u32 __bitwise req_flags_t; -/* drive already may have started this one */ -#define RQF_STARTED ((__force req_flags_t)(1 << 1)) -/* request for flush sequence */ -#define RQF_FLUSH_SEQ ((__force req_flags_t)(1 << 4)) -/* merge of different types, fail separately */ -#define RQF_MIXED_MERGE ((__force req_flags_t)(1 << 5)) -/* don't call prep for this one */ -#define RQF_DONTPREP ((__force req_flags_t)(1 << 7)) -/* use hctx->sched_tags */ -#define RQF_SCHED_TAGS ((__force req_flags_t)(1 << 8)) -/* use an I/O scheduler for this request */ -#define RQF_USE_SCHED ((__force req_flags_t)(1 << 9)) -/* vaguely specified driver internal error. Ignored by the block layer */ -#define RQF_FAILED ((__force req_flags_t)(1 << 10)) -/* don't warn about errors */ -#define RQF_QUIET ((__force req_flags_t)(1 << 11)) -/* account into disk and partition IO statistics */ -#define RQF_IO_STAT ((__force req_flags_t)(1 << 13)) -/* runtime pm request */ -#define RQF_PM ((__force req_flags_t)(1 << 15)) -/* on IO scheduler merge hash */ -#define RQF_HASHED ((__force req_flags_t)(1 << 16)) -/* track IO completion time */ -#define RQF_STATS ((__force req_flags_t)(1 << 17)) -/* Look at ->special_vec for the actual data payload instead of the - bio chain. */ -#define RQF_SPECIAL_PAYLOAD ((__force req_flags_t)(1 << 18)) -/* The per-zone write lock is held for this request */ -#define RQF_ZONE_WRITE_LOCKED ((__force req_flags_t)(1 << 19)) -/* ->timeout has been called, don't expire again */ -#define RQF_TIMED_OUT ((__force req_flags_t)(1 << 21)) -#define RQF_RESV ((__force req_flags_t)(1 << 23)) +/* Keep rqf_name[] in sync with the definitions below */ +enum { + /* drive already may have started this one */ + __RQF_STARTED, + /* request for flush sequence */ + __RQF_FLUSH_SEQ, + /* merge of different types, fail separately */ + __RQF_MIXED_MERGE, + /* don't call prep for this one */ + __RQF_DONTPREP, + /* use hctx->sched_tags */ + __RQF_SCHED_TAGS, + /* use an I/O scheduler for this request */ + __RQF_USE_SCHED, + /* vaguely specified driver internal error. Ignored by block layer */ + __RQF_FAILED, + /* don't warn about errors */ + __RQF_QUIET, + /* account into disk and partition IO statistics */ + __RQF_IO_STAT, + /* runtime pm request */ + __RQF_PM, + /* on IO scheduler merge hash */ + __RQF_HASHED, + /* track IO completion time */ + __RQF_STATS, + /* Look at ->special_vec for the actual data payload instead of the + bio chain. */ + __RQF_SPECIAL_PAYLOAD, + /* request completion needs to be signaled to zone write plugging. */ + __RQF_ZONE_WRITE_PLUGGING, + /* ->timeout has been called, don't expire again */ + __RQF_TIMED_OUT, + __RQF_RESV, + __RQF_BITS +}; + +#define RQF_STARTED ((__force req_flags_t)(1 << __RQF_STARTED)) +#define RQF_FLUSH_SEQ ((__force req_flags_t)(1 << __RQF_FLUSH_SEQ)) +#define RQF_MIXED_MERGE ((__force req_flags_t)(1 << __RQF_MIXED_MERGE)) +#define RQF_DONTPREP ((__force req_flags_t)(1 << __RQF_DONTPREP)) +#define RQF_SCHED_TAGS ((__force req_flags_t)(1 << __RQF_SCHED_TAGS)) +#define RQF_USE_SCHED ((__force req_flags_t)(1 << __RQF_USE_SCHED)) +#define RQF_FAILED ((__force req_flags_t)(1 << __RQF_FAILED)) +#define RQF_QUIET ((__force req_flags_t)(1 << __RQF_QUIET)) +#define RQF_IO_STAT ((__force req_flags_t)(1 << __RQF_IO_STAT)) +#define RQF_PM ((__force req_flags_t)(1 << __RQF_PM)) +#define RQF_HASHED ((__force req_flags_t)(1 << __RQF_HASHED)) +#define RQF_STATS ((__force req_flags_t)(1 << __RQF_STATS)) +#define RQF_SPECIAL_PAYLOAD \ + ((__force req_flags_t)(1 << __RQF_SPECIAL_PAYLOAD)) +#define RQF_ZONE_WRITE_PLUGGING \ + ((__force req_flags_t)(1 << __RQF_ZONE_WRITE_PLUGGING)) +#define RQF_TIMED_OUT ((__force req_flags_t)(1 << __RQF_TIMED_OUT)) +#define RQF_RESV ((__force req_flags_t)(1 << __RQF_RESV)) /* flags that prevent us from merging requests: */ #define RQF_NOMERGE_FLAGS \ @@ -126,19 +149,13 @@ struct request { * physical address coalescing is performed. */ unsigned short nr_phys_segments; - -#ifdef CONFIG_BLK_DEV_INTEGRITY unsigned short nr_integrity_segments; -#endif #ifdef CONFIG_BLK_INLINE_ENCRYPTION struct bio_crypt_ctx *crypt_ctx; struct blk_crypto_keyslot *crypt_keyslot; #endif - enum rw_hint write_hint; - unsigned short ioprio; - enum mq_rq_state state; atomic_t ref; @@ -202,7 +219,9 @@ static inline bool blk_rq_is_passthrough(struct request *rq) static inline unsigned short req_get_ioprio(struct request *req) { - return req->ioprio; + if (req->bio) + return req->bio->bi_ioprio; + return 0; } #define rq_data_dir(rq) (op_is_write(req_op(rq)) ? WRITE : READ) @@ -210,62 +229,61 @@ static inline unsigned short req_get_ioprio(struct request *req) #define rq_dma_dir(rq) \ (op_is_write(req_op(rq)) ? DMA_TO_DEVICE : DMA_FROM_DEVICE) -#define rq_list_add(listptr, rq) do { \ - (rq)->rq_next = *(listptr); \ - *(listptr) = rq; \ -} while (0) +static inline int rq_list_empty(const struct rq_list *rl) +{ + return rl->head == NULL; +} -#define rq_list_add_tail(lastpptr, rq) do { \ - (rq)->rq_next = NULL; \ - **(lastpptr) = rq; \ - *(lastpptr) = &rq->rq_next; \ -} while (0) +static inline void rq_list_init(struct rq_list *rl) +{ + rl->head = NULL; + rl->tail = NULL; +} -#define rq_list_pop(listptr) \ -({ \ - struct request *__req = NULL; \ - if ((listptr) && *(listptr)) { \ - __req = *(listptr); \ - *(listptr) = __req->rq_next; \ - } \ - __req; \ -}) +static inline void rq_list_add_tail(struct rq_list *rl, struct request *rq) +{ + rq->rq_next = NULL; + if (rl->tail) + rl->tail->rq_next = rq; + else + rl->head = rq; + rl->tail = rq; +} -#define rq_list_peek(listptr) \ -({ \ - struct request *__req = NULL; \ - if ((listptr) && *(listptr)) \ - __req = *(listptr); \ - __req; \ -}) +static inline void rq_list_add_head(struct rq_list *rl, struct request *rq) +{ + rq->rq_next = rl->head; + rl->head = rq; + if (!rl->tail) + rl->tail = rq; +} -#define rq_list_for_each(listptr, pos) \ - for (pos = rq_list_peek((listptr)); pos; pos = rq_list_next(pos)) +static inline struct request *rq_list_pop(struct rq_list *rl) +{ + struct request *rq = rl->head; -#define rq_list_for_each_safe(listptr, pos, nxt) \ - for (pos = rq_list_peek((listptr)), nxt = rq_list_next(pos); \ - pos; pos = nxt, nxt = pos ? rq_list_next(pos) : NULL) + if (rq) { + rl->head = rl->head->rq_next; + if (!rl->head) + rl->tail = NULL; + rq->rq_next = NULL; + } -#define rq_list_next(rq) (rq)->rq_next -#define rq_list_empty(list) ((list) == (struct request *) NULL) + return rq; +} -/** - * rq_list_move() - move a struct request from one list to another - * @src: The source list @rq is currently in - * @dst: The destination list that @rq will be appended to - * @rq: The request to move - * @prev: The request preceding @rq in @src (NULL if @rq is the head) - */ -static inline void rq_list_move(struct request **src, struct request **dst, - struct request *rq, struct request *prev) +static inline struct request *rq_list_peek(struct rq_list *rl) { - if (prev) - prev->rq_next = rq->rq_next; - else - *src = rq->rq_next; - rq_list_add(dst, rq); + return rl->head; } +#define rq_list_for_each(rl, pos) \ + for (pos = rq_list_peek((rl)); (pos); pos = pos->rq_next) + +#define rq_list_for_each_safe(rl, pos, nxt) \ + for (pos = rq_list_peek((rl)), nxt = pos->rq_next; \ + pos; pos = nxt, nxt = pos ? pos->rq_next : NULL) + /** * enum blk_eh_timer_return - How the timeout handler should proceed * @BLK_EH_DONE: The block driver completed the command or will complete it at @@ -278,9 +296,6 @@ enum blk_eh_timer_return { BLK_EH_RESET_TIMER, }; -#define BLK_TAG_ALLOC_FIFO 0 /* allocate starting from 0 */ -#define BLK_TAG_ALLOC_RR 1 /* allocate starting from last allocated tag */ - /** * struct blk_mq_hw_ctx - State for a hardware queue facing the hardware * block device @@ -553,7 +568,7 @@ struct blk_mq_ops { * empty the @rqlist completely, then the rest will be queued * individually by the block layer upon return. */ - void (*queue_rqs)(struct request **rqlist); + void (*queue_rqs)(struct rq_list *rqlist); /** * @get_budget: Reserve budget before queue request, once .queue_rq is @@ -644,8 +659,8 @@ struct blk_mq_ops { #endif }; +/* Keep hctx_flag_name[] in sync with the definitions below */ enum { - BLK_MQ_F_SHOULD_MERGE = 1 << 0, BLK_MQ_F_TAG_QUEUE_SHARED = 1 << 1, /* * Set when this device requires underlying blk-mq device for @@ -653,37 +668,35 @@ enum { */ BLK_MQ_F_STACKING = 1 << 2, BLK_MQ_F_TAG_HCTX_SHARED = 1 << 3, - BLK_MQ_F_BLOCKING = 1 << 5, - /* Do not allow an I/O scheduler to be configured. */ - BLK_MQ_F_NO_SCHED = 1 << 6, + BLK_MQ_F_BLOCKING = 1 << 4, + + /* + * Alloc tags on a round-robin base instead of the first available one. + */ + BLK_MQ_F_TAG_RR = 1 << 5, + /* * Select 'none' during queue registration in case of a single hwq * or shared hwqs instead of 'mq-deadline'. */ - BLK_MQ_F_NO_SCHED_BY_DEFAULT = 1 << 7, - BLK_MQ_F_ALLOC_POLICY_START_BIT = 8, - BLK_MQ_F_ALLOC_POLICY_BITS = 1, + BLK_MQ_F_NO_SCHED_BY_DEFAULT = 1 << 6, - BLK_MQ_S_STOPPED = 0, - BLK_MQ_S_TAG_ACTIVE = 1, - BLK_MQ_S_SCHED_RESTART = 2, - - /* hw queue is inactive after all its CPUs become offline */ - BLK_MQ_S_INACTIVE = 3, - - BLK_MQ_MAX_DEPTH = 10240, - - BLK_MQ_CPU_WORK_BATCH = 8, + BLK_MQ_F_MAX = 1 << 7, }; -#define BLK_MQ_FLAG_TO_ALLOC_POLICY(flags) \ - ((flags >> BLK_MQ_F_ALLOC_POLICY_START_BIT) & \ - ((1 << BLK_MQ_F_ALLOC_POLICY_BITS) - 1)) -#define BLK_ALLOC_POLICY_TO_MQ_FLAG(policy) \ - ((policy & ((1 << BLK_MQ_F_ALLOC_POLICY_BITS) - 1)) \ - << BLK_MQ_F_ALLOC_POLICY_START_BIT) +#define BLK_MQ_MAX_DEPTH (10240) #define BLK_MQ_NO_HCTX_IDX (-1U) +enum { + /* Keep hctx_state_name[] in sync with the definitions below */ + BLK_MQ_S_STOPPED, + BLK_MQ_S_TAG_ACTIVE, + BLK_MQ_S_SCHED_RESTART, + /* hw queue is inactive after all its CPUs become offline */ + BLK_MQ_S_INACTIVE, + BLK_MQ_S_MAX +}; + struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, struct queue_limits *lim, void *queuedata, struct lock_class_key *lkclass); @@ -831,12 +844,6 @@ void blk_mq_end_request_batch(struct io_comp_batch *ib); */ static inline bool blk_mq_need_time_stamp(struct request *rq) { - /* - * passthrough io doesn't use iostat accounting, cgroup stats - * and io scheduler functionalities. - */ - if (blk_rq_is_passthrough(rq)) - return false; return (rq->rq_flags & (RQF_IO_STAT | RQF_STATS | RQF_USE_SCHED)); } @@ -866,7 +873,7 @@ static inline bool blk_mq_add_to_batch(struct request *req, else if (iob->complete != complete) return false; iob->need_ts |= blk_mq_need_time_stamp(req); - rq_list_add(&iob->req_list, req); + rq_list_add_tail(&iob->req_list, req); return true; } @@ -893,14 +900,32 @@ void blk_mq_delay_run_hw_queues(struct request_queue *q, unsigned long msecs); void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset, busy_tag_iter_fn *fn, void *priv); void blk_mq_tagset_wait_completed_request(struct blk_mq_tag_set *tagset); -void blk_mq_freeze_queue(struct request_queue *q); -void blk_mq_unfreeze_queue(struct request_queue *q); +void blk_mq_freeze_queue_nomemsave(struct request_queue *q); +void blk_mq_unfreeze_queue_nomemrestore(struct request_queue *q); +static inline unsigned int __must_check +blk_mq_freeze_queue(struct request_queue *q) +{ + unsigned int memflags = memalloc_noio_save(); + + blk_mq_freeze_queue_nomemsave(q); + return memflags; +} +static inline void +blk_mq_unfreeze_queue(struct request_queue *q, unsigned int memflags) +{ + blk_mq_unfreeze_queue_nomemrestore(q); + memalloc_noio_restore(memflags); +} void blk_freeze_queue_start(struct request_queue *q); void blk_mq_freeze_queue_wait(struct request_queue *q); int blk_mq_freeze_queue_wait_timeout(struct request_queue *q, unsigned long timeout); +void blk_mq_unfreeze_queue_non_owner(struct request_queue *q); +void blk_freeze_queue_start_non_owner(struct request_queue *q); void blk_mq_map_queues(struct blk_mq_queue_map *qmap); +void blk_mq_map_hw_queues(struct blk_mq_queue_map *qmap, + struct device *dev, unsigned int offset); void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues); void blk_mq_quiesce_queue_nowait(struct request_queue *q); @@ -957,15 +982,6 @@ static inline void blk_mq_cleanup_rq(struct request *rq) rq->q->mq_ops->cleanup_rq(rq); } -static inline void blk_rq_bio_prep(struct request *rq, struct bio *bio, - unsigned int nr_segs) -{ - rq->nr_phys_segments = nr_segs; - rq->__data_len = bio->bi_iter.bi_size; - rq->bio = rq->biotail = bio; - rq->ioprio = bio_prio(bio); -} - void blk_mq_hctx_set_fq_lock_class(struct blk_mq_hw_ctx *hctx, struct lock_class_key *key); @@ -1150,85 +1166,4 @@ static inline int blk_rq_map_sg(struct request_queue *q, struct request *rq, } void blk_dump_rq_flags(struct request *, char *); -#ifdef CONFIG_BLK_DEV_ZONED -static inline unsigned int blk_rq_zone_no(struct request *rq) -{ - return disk_zone_no(rq->q->disk, blk_rq_pos(rq)); -} - -static inline unsigned int blk_rq_zone_is_seq(struct request *rq) -{ - return disk_zone_is_seq(rq->q->disk, blk_rq_pos(rq)); -} - -/** - * blk_rq_is_seq_zoned_write() - Check if @rq requires write serialization. - * @rq: Request to examine. - * - * Note: REQ_OP_ZONE_APPEND requests do not require serialization. - */ -static inline bool blk_rq_is_seq_zoned_write(struct request *rq) -{ - return op_needs_zoned_write_locking(req_op(rq)) && - blk_rq_zone_is_seq(rq); -} - -bool blk_req_needs_zone_write_lock(struct request *rq); -bool blk_req_zone_write_trylock(struct request *rq); -void __blk_req_zone_write_lock(struct request *rq); -void __blk_req_zone_write_unlock(struct request *rq); - -static inline void blk_req_zone_write_lock(struct request *rq) -{ - if (blk_req_needs_zone_write_lock(rq)) - __blk_req_zone_write_lock(rq); -} - -static inline void blk_req_zone_write_unlock(struct request *rq) -{ - if (rq->rq_flags & RQF_ZONE_WRITE_LOCKED) - __blk_req_zone_write_unlock(rq); -} - -static inline bool blk_req_zone_is_write_locked(struct request *rq) -{ - return rq->q->disk->seq_zones_wlock && - test_bit(blk_rq_zone_no(rq), rq->q->disk->seq_zones_wlock); -} - -static inline bool blk_req_can_dispatch_to_zone(struct request *rq) -{ - if (!blk_req_needs_zone_write_lock(rq)) - return true; - return !blk_req_zone_is_write_locked(rq); -} -#else /* CONFIG_BLK_DEV_ZONED */ -static inline bool blk_rq_is_seq_zoned_write(struct request *rq) -{ - return false; -} - -static inline bool blk_req_needs_zone_write_lock(struct request *rq) -{ - return false; -} - -static inline void blk_req_zone_write_lock(struct request *rq) -{ -} - -static inline void blk_req_zone_write_unlock(struct request *rq) -{ -} -static inline bool blk_req_zone_is_write_locked(struct request *rq) -{ - return false; -} - -static inline bool blk_req_can_dispatch_to_zone(struct request *rq) -{ - return true; -} -#endif /* CONFIG_BLK_DEV_ZONED */ - #endif /* BLK_MQ_H */ diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index cb1526ec44b5..dce7615c35e7 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -45,12 +45,17 @@ struct block_device { struct request_queue * bd_queue; struct disk_stats __percpu *bd_stats; unsigned long bd_stamp; - bool bd_read_only; /* read-only policy */ - u8 bd_partno; - bool bd_write_holder; - bool bd_has_submit_bio; + atomic_t __bd_flags; // partition number + flags +#define BD_PARTNO 255 // lower 8 bits; assign-once +#define BD_READ_ONLY (1u<<8) // read-only policy +#define BD_WRITE_HOLDER (1u<<9) +#define BD_HAS_SUBMIT_BIO (1u<<10) +#define BD_RO_WARNED (1u<<11) +#ifdef CONFIG_FAIL_MAKE_REQUEST +#define BD_MAKE_IT_FAIL (1u<<12) +#endif dev_t bd_dev; - struct inode *bd_inode; /* will die */ + struct address_space *bd_mapping; /* page cache */ atomic_t bd_openers; spinlock_t bd_size_lock; /* for bd_inode->i_size updates */ @@ -65,11 +70,10 @@ struct block_device { struct mutex bd_fsfreeze_mutex; /* serialize freeze/thaw */ struct partition_meta_info *bd_meta_info; -#ifdef CONFIG_FAIL_MAKE_REQUEST - bool bd_make_it_fail; -#endif - bool bd_ro_warned; int bd_writers; +#ifdef CONFIG_SECURITY + void *bd_security; +#endif /* * keep this out-of-line as it's both big and not needed in the fast * path @@ -88,15 +92,9 @@ struct block_device { /* * Block error status values. See block/blk-core:blk_errors for the details. - * Alpha cannot write a byte atomically, so we need to use 32-bit value. */ -#if defined(CONFIG_ALPHA) && !defined(__alpha_bwx__) -typedef u32 __bitwise blk_status_t; -typedef u32 blk_short_t; -#else typedef u8 __bitwise blk_status_t; typedef u16 blk_short_t; -#endif #define BLK_STS_OK 0 #define BLK_STS_NOTSUPP ((__force blk_status_t)1) #define BLK_STS_TIMEOUT ((__force blk_status_t)2) @@ -137,25 +135,13 @@ typedef u16 blk_short_t; #define BLK_STS_DEV_RESOURCE ((__force blk_status_t)13) /* - * BLK_STS_ZONE_RESOURCE is returned from the driver to the block layer if zone - * related resources are unavailable, but the driver can guarantee the queue - * will be rerun in the future once the resources become available again. - * - * This is different from BLK_STS_DEV_RESOURCE in that it explicitly references - * a zone specific resource and IO to a different zone on the same device could - * still be served. Examples of that are zones that are write-locked, but a read - * to the same zone could be served. - */ -#define BLK_STS_ZONE_RESOURCE ((__force blk_status_t)14) - -/* * BLK_STS_ZONE_OPEN_RESOURCE is returned from the driver in the completion * path if the device returns a status indicating that too many zone resources * are currently open. The same command should be successful if resubmitted * after the number of open zones decreases below the device's limits, which is * reported in the request_queue's max_open_zones. */ -#define BLK_STS_ZONE_OPEN_RESOURCE ((__force blk_status_t)15) +#define BLK_STS_ZONE_OPEN_RESOURCE ((__force blk_status_t)14) /* * BLK_STS_ZONE_ACTIVE_RESOURCE is returned from the driver in the completion @@ -164,20 +150,25 @@ typedef u16 blk_short_t; * after the number of active zones decreases below the device's limits, which * is reported in the request_queue's max_active_zones. */ -#define BLK_STS_ZONE_ACTIVE_RESOURCE ((__force blk_status_t)16) +#define BLK_STS_ZONE_ACTIVE_RESOURCE ((__force blk_status_t)15) /* * BLK_STS_OFFLINE is returned from the driver when the target device is offline * or is being taken offline. This could help differentiate the case where a * device is intentionally being shut down from a real I/O error. */ -#define BLK_STS_OFFLINE ((__force blk_status_t)17) +#define BLK_STS_OFFLINE ((__force blk_status_t)16) /* * BLK_STS_DURATION_LIMIT is returned from the driver when the target device * aborted the command because it exceeded one of its Command Duration Limits. */ -#define BLK_STS_DURATION_LIMIT ((__force blk_status_t)18) +#define BLK_STS_DURATION_LIMIT ((__force blk_status_t)17) + +/* + * Invalid size or alignment. + */ +#define BLK_STS_INVAL ((__force blk_status_t)19) /** * blk_path_error - returns true if error may be path related @@ -234,7 +225,12 @@ struct bio { struct bvec_iter bi_iter; - blk_qc_t bi_cookie; + union { + /* for polled bios: */ + blk_qc_t bi_cookie; + /* for plugged zoned writes only: */ + unsigned int __bi_nr_segments; + }; bio_end_io_t *bi_end_io; void *bi_private; #ifdef CONFIG_BLK_CGROUP @@ -255,11 +251,9 @@ struct bio { struct bio_crypt_ctx *bi_crypt_context; #endif - union { #if defined(CONFIG_BLK_DEV_INTEGRITY) - struct bio_integrity_payload *bi_integrity; /* data integrity */ + struct bio_integrity_payload *bi_integrity; /* data integrity */ #endif - }; unsigned short bi_vcnt; /* how many bio_vec's */ @@ -304,7 +298,8 @@ enum { BIO_QOS_THROTTLED, /* bio went through rq_qos throttle path */ BIO_QOS_MERGED, /* but went through rq_qos merge path */ BIO_REMAPPED, - BIO_ZONE_WRITE_LOCKED, /* Owns a zoned device zone write lock */ + BIO_ZONE_WRITE_PLUGGING, /* bio handled through zone write plugging */ + BIO_EMULATES_ZONE_APPEND, /* bio emulates a zone append operation */ BIO_FLAG_LAST }; @@ -360,6 +355,7 @@ enum req_op { REQ_OP_LAST = (__force blk_opf_t)36, }; +/* Keep cmd_flag_name[] in sync with the definitions below */ enum req_flag_bits { __REQ_FAILFAST_DEV = /* no driver retries of device errors */ REQ_OP_BITS, @@ -381,7 +377,7 @@ enum req_flag_bits { __REQ_SWAP, /* swap I/O */ __REQ_DRV, /* for driver use */ __REQ_FS_PRIVATE, /* for file system (submitter) use */ - + __REQ_ATOMIC, /* for atomic write operations */ /* * Command specific flags, keep last: */ @@ -413,6 +409,7 @@ enum req_flag_bits { #define REQ_SWAP (__force blk_opf_t)(1ULL << __REQ_SWAP) #define REQ_DRV (__force blk_opf_t)(1ULL << __REQ_DRV) #define REQ_FS_PRIVATE (__force blk_opf_t)(1ULL << __REQ_FS_PRIVATE) +#define REQ_ATOMIC (__force blk_opf_t)(1ULL << __REQ_ATOMIC) #define REQ_NOUNMAP (__force blk_opf_t)(1ULL << __REQ_NOUNMAP) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 69e7da33ca49..248416ecd01c 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -25,6 +25,7 @@ #include <linux/uuid.h> #include <linux/xarray.h> #include <linux/file.h> +#include <linux/lockdep.h> struct module; struct request_queue; @@ -105,9 +106,16 @@ enum { struct disk_events; struct badblocks; +enum blk_integrity_checksum { + BLK_INTEGRITY_CSUM_NONE = 0, + BLK_INTEGRITY_CSUM_IP = 1, + BLK_INTEGRITY_CSUM_CRC = 2, + BLK_INTEGRITY_CSUM_CRC64 = 3, +} __packed ; + struct blk_integrity { - const struct blk_integrity_profile *profile; unsigned char flags; + enum blk_integrity_checksum csum_type; unsigned char tuple_size; unsigned char pi_offset; unsigned char interval_exp; @@ -179,22 +187,20 @@ struct gendisk { #ifdef CONFIG_BLK_DEV_ZONED /* - * Zoned block device information for request dispatch control. - * nr_zones is the total number of zones of the device. This is always - * 0 for regular block devices. conv_zones_bitmap is a bitmap of nr_zones - * bits which indicates if a zone is conventional (bit set) or - * sequential (bit clear). seq_zones_wlock is a bitmap of nr_zones - * bits which indicates if a zone is write locked, that is, if a write - * request targeting the zone was dispatched. - * - * Reads of this information must be protected with blk_queue_enter() / - * blk_queue_exit(). Modifying this information is only allowed while - * no requests are being processed. See also blk_mq_freeze_queue() and - * blk_mq_unfreeze_queue(). + * Zoned block device information. Reads of this information must be + * protected with blk_queue_enter() / blk_queue_exit(). Modifying this + * information is only allowed while no requests are being processed. + * See also blk_mq_freeze_queue() and blk_mq_unfreeze_queue(). */ unsigned int nr_zones; - unsigned long *conv_zones_bitmap; - unsigned long *seq_zones_wlock; + unsigned int zone_capacity; + unsigned int last_zone_capacity; + unsigned long __rcu *conv_zones_bitmap; + unsigned int zone_wplugs_hash_bits; + spinlock_t zone_wplugs_lock; + struct mempool_s *zone_wplugs_pool; + struct hlist_head *zone_wplugs_hash; + struct workqueue_struct *zone_wplugs_wq; #endif /* CONFIG_BLK_DEV_ZONED */ #if IS_ENABLED(CONFIG_CDROM) @@ -213,11 +219,6 @@ struct gendisk { struct blk_independent_access_ranges *ia_ranges; }; -static inline bool disk_live(struct gendisk *disk) -{ - return !inode_unhashed(disk->part0->bd_inode); -} - /** * disk_openers - returns how many openers are there for a disk * @disk: disk to check @@ -233,6 +234,19 @@ static inline unsigned int disk_openers(struct gendisk *disk) return atomic_read(&disk->part0->bd_openers); } +/** + * disk_has_partscan - return %true if partition scanning is enabled on a disk + * @disk: disk to check + * + * Returns %true if partitions scanning is enabled for @disk, or %false if + * partition scanning is disabled either permanently or temporarily. + */ +static inline bool disk_has_partscan(struct gendisk *disk) +{ + return !(disk->flags & (GENHD_FL_NO_PART | GENHD_FL_HIDDEN)) && + !test_bit(GD_SUPPRESS_PART_SCAN, &disk->state); +} + /* * The gendisk is refcounted by the part0 block_device, and the bd_device * therein is also used for device model presentation in sysfs. @@ -253,6 +267,7 @@ static inline dev_t disk_devt(struct gendisk *disk) return MKDEV(disk->major, disk->first_minor); } +/* blk_validate_limits() validates bsize, so drivers don't usually need to */ static inline int blk_validate_block_size(unsigned long bsize) { if (bsize < 512 || bsize > PAGE_SIZE || !is_power_of_2(bsize)) @@ -267,17 +282,82 @@ static inline bool blk_op_is_passthrough(blk_opf_t op) return op == REQ_OP_DRV_IN || op == REQ_OP_DRV_OUT; } +/* flags set by the driver in queue_limits.features */ +typedef unsigned int __bitwise blk_features_t; + +/* supports a volatile write cache */ +#define BLK_FEAT_WRITE_CACHE ((__force blk_features_t)(1u << 0)) + +/* supports passing on the FUA bit */ +#define BLK_FEAT_FUA ((__force blk_features_t)(1u << 1)) + +/* rotational device (hard drive or floppy) */ +#define BLK_FEAT_ROTATIONAL ((__force blk_features_t)(1u << 2)) + +/* contributes to the random number pool */ +#define BLK_FEAT_ADD_RANDOM ((__force blk_features_t)(1u << 3)) + +/* do disk/partitions IO accounting */ +#define BLK_FEAT_IO_STAT ((__force blk_features_t)(1u << 4)) + +/* don't modify data until writeback is done */ +#define BLK_FEAT_STABLE_WRITES ((__force blk_features_t)(1u << 5)) + +/* always completes in submit context */ +#define BLK_FEAT_SYNCHRONOUS ((__force blk_features_t)(1u << 6)) + +/* supports REQ_NOWAIT */ +#define BLK_FEAT_NOWAIT ((__force blk_features_t)(1u << 7)) + +/* supports DAX */ +#define BLK_FEAT_DAX ((__force blk_features_t)(1u << 8)) + +/* supports I/O polling */ +#define BLK_FEAT_POLL ((__force blk_features_t)(1u << 9)) + +/* is a zoned device */ +#define BLK_FEAT_ZONED ((__force blk_features_t)(1u << 10)) + +/* supports PCI(e) p2p requests */ +#define BLK_FEAT_PCI_P2PDMA ((__force blk_features_t)(1u << 12)) + +/* skip this queue in blk_mq_(un)quiesce_tagset */ +#define BLK_FEAT_SKIP_TAGSET_QUIESCE ((__force blk_features_t)(1u << 13)) + +/* bounce all highmem pages */ +#define BLK_FEAT_BOUNCE_HIGH ((__force blk_features_t)(1u << 14)) + +/* undocumented magic for bcache */ +#define BLK_FEAT_RAID_PARTIAL_STRIPES_EXPENSIVE \ + ((__force blk_features_t)(1u << 15)) + +/* atomic writes enabled */ +#define BLK_FEAT_ATOMIC_WRITES \ + ((__force blk_features_t)(1u << 16)) + /* - * BLK_BOUNCE_NONE: never bounce (default) - * BLK_BOUNCE_HIGH: bounce all highmem pages + * Flags automatically inherited when stacking limits. */ -enum blk_bounce { - BLK_BOUNCE_NONE, - BLK_BOUNCE_HIGH, -}; +#define BLK_FEAT_INHERIT_MASK \ + (BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA | BLK_FEAT_ROTATIONAL | \ + BLK_FEAT_STABLE_WRITES | BLK_FEAT_ZONED | BLK_FEAT_BOUNCE_HIGH | \ + BLK_FEAT_RAID_PARTIAL_STRIPES_EXPENSIVE) + +/* internal flags in queue_limits.flags */ +typedef unsigned int __bitwise blk_flags_t; + +/* do not send FLUSH/FUA commands despite advertising a write cache */ +#define BLK_FLAG_WRITE_CACHE_DISABLED ((__force blk_flags_t)(1u << 0)) + +/* I/O topology is misaligned */ +#define BLK_FLAG_MISALIGNED ((__force blk_flags_t)(1u << 1)) + +/* passthrough command IO accounting */ +#define BLK_FLAG_IOSTATS_PASSTHROUGH ((__force blk_flags_t)(1u << 2)) struct queue_limits { - enum blk_bounce bounce; + blk_features_t features; + blk_flags_t flags; unsigned long seg_boundary_mask; unsigned long virt_boundary_mask; @@ -297,19 +377,26 @@ struct queue_limits { unsigned int max_user_discard_sectors; unsigned int max_secure_erase_sectors; unsigned int max_write_zeroes_sectors; + unsigned int max_hw_zone_append_sectors; unsigned int max_zone_append_sectors; unsigned int discard_granularity; unsigned int discard_alignment; unsigned int zone_write_granularity; + /* atomic write limits */ + unsigned int atomic_write_hw_max; + unsigned int atomic_write_max_sectors; + unsigned int atomic_write_hw_boundary; + unsigned int atomic_write_boundary_sectors; + unsigned int atomic_write_hw_unit_min; + unsigned int atomic_write_unit_min; + unsigned int atomic_write_hw_unit_max; + unsigned int atomic_write_unit_max; + unsigned short max_segments; unsigned short max_integrity_segments; unsigned short max_discard_segments; - unsigned char misaligned; - unsigned char discard_misaligned; - unsigned char raid_partial_stripes_expensive; - bool zoned; unsigned int max_open_zones; unsigned int max_active_zones; @@ -319,20 +406,20 @@ struct queue_limits { * due to possible offsets. */ unsigned int dma_alignment; + unsigned int dma_pad_mask; + + struct blk_integrity integrity; }; typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx, void *data); -void disk_set_zoned(struct gendisk *disk); - #define BLK_ALL_ZONES ((unsigned int)-1) int blkdev_report_zones(struct block_device *bdev, sector_t sector, unsigned int nr_zones, report_zones_cb cb, void *data); int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op, sector_t sectors, sector_t nr_sectors); -int blk_revalidate_disk_zones(struct gendisk *disk, - void (*update_driver_data)(struct gendisk *disk)); +int blk_revalidate_disk_zones(struct gendisk *disk); /* * Independent access ranges: struct blk_independent_access_range describes @@ -391,6 +478,11 @@ struct request_queue { struct xarray hctx_table; struct percpu_ref q_usage_counter; + struct lock_class_key io_lock_cls_key; + struct lockdep_map io_lockdep_map; + + struct lock_class_key q_lock_cls_key; + struct lockdep_map q_lockdep_map; struct request *last_merge; @@ -407,10 +499,6 @@ struct request_queue { struct queue_limits limits; -#ifdef CONFIG_BLK_DEV_INTEGRITY - struct blk_integrity integrity; -#endif /* CONFIG_BLK_DEV_INTEGRITY */ - #ifdef CONFIG_PM struct device *dev; enum rpm_status rpm_status; @@ -432,8 +520,6 @@ struct request_queue { */ int id; - unsigned int dma_pad_mask; - /* * queue settings */ @@ -449,8 +535,6 @@ struct request_queue { atomic_t nr_active_requests_shared_tags; - unsigned int required_elevator_features; - struct blk_mq_tags *sched_shared_tags; struct list_head icq_list; @@ -477,7 +561,6 @@ struct request_queue { struct list_head flush_list; struct mutex sysfs_lock; - struct mutex sysfs_dir_lock; struct mutex limits_lock; /* @@ -494,6 +577,16 @@ struct request_queue { struct throtl_data *td; #endif struct rcu_head rcu_head; +#ifdef CONFIG_LOCKDEP + struct task_struct *mq_freeze_owner; + int mq_freeze_owner_depth; + /* + * Records disk & queue state in current context, used in unfreeze + * queue + */ + bool mq_freeze_disk_dead; + bool mq_freeze_queue_dying; +#endif wait_queue_head_t mq_freeze_wq; /* * Protect concurrent access to q_usage_counter by @@ -511,65 +604,42 @@ struct request_queue { * Serializes all debugfs metadata operations using the above dentries. */ struct mutex debugfs_mutex; - - bool mq_sysfs_init_done; }; /* Keep blk_queue_flag_name[] in sync with the definitions below */ -#define QUEUE_FLAG_STOPPED 0 /* queue is stopped */ -#define QUEUE_FLAG_DYING 1 /* queue being torn down */ -#define QUEUE_FLAG_NOMERGES 3 /* disable merge attempts */ -#define QUEUE_FLAG_SAME_COMP 4 /* complete on same CPU-group */ -#define QUEUE_FLAG_FAIL_IO 5 /* fake timeout */ -#define QUEUE_FLAG_NONROT 6 /* non-rotational device (SSD) */ -#define QUEUE_FLAG_VIRT QUEUE_FLAG_NONROT /* paravirt device */ -#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_HW_WC 13 /* Write back caching supported */ -#define QUEUE_FLAG_INIT_DONE 14 /* queue is initialized */ -#define QUEUE_FLAG_STABLE_WRITES 15 /* don't modify blks until WB is done */ -#define QUEUE_FLAG_POLL 16 /* IO polling enabled if set */ -#define QUEUE_FLAG_WC 17 /* Write back caching */ -#define QUEUE_FLAG_FUA 18 /* device supports FUA writes */ -#define QUEUE_FLAG_DAX 19 /* device supports DAX */ -#define QUEUE_FLAG_STATS 20 /* track IO start and completion times */ -#define QUEUE_FLAG_REGISTERED 22 /* queue has been registered to a disk */ -#define QUEUE_FLAG_QUIESCED 24 /* queue has been quiesced */ -#define QUEUE_FLAG_PCI_P2PDMA 25 /* device supports PCI p2p requests */ -#define QUEUE_FLAG_ZONE_RESETALL 26 /* supports Zone Reset All */ -#define QUEUE_FLAG_RQ_ALLOC_TIME 27 /* record rq->alloc_time_ns */ -#define QUEUE_FLAG_HCTX_ACTIVE 28 /* at least one blk-mq hctx is active */ -#define QUEUE_FLAG_NOWAIT 29 /* device supports NOWAIT */ -#define QUEUE_FLAG_SQ_SCHED 30 /* single queue style io dispatch */ -#define QUEUE_FLAG_SKIP_TAGSET_QUIESCE 31 /* quiesce_tagset skip the queue*/ +enum { + QUEUE_FLAG_DYING, /* queue being torn down */ + QUEUE_FLAG_NOMERGES, /* disable merge attempts */ + QUEUE_FLAG_SAME_COMP, /* complete on same CPU-group */ + QUEUE_FLAG_FAIL_IO, /* fake timeout */ + QUEUE_FLAG_NOXMERGES, /* No extended merges */ + QUEUE_FLAG_SAME_FORCE, /* force complete on same CPU */ + QUEUE_FLAG_INIT_DONE, /* queue is initialized */ + QUEUE_FLAG_STATS, /* track IO start and completion times */ + QUEUE_FLAG_REGISTERED, /* queue has been registered to a disk */ + QUEUE_FLAG_QUIESCED, /* queue has been quiesced */ + QUEUE_FLAG_RQ_ALLOC_TIME, /* record rq->alloc_time_ns */ + QUEUE_FLAG_HCTX_ACTIVE, /* at least one blk-mq hctx is active */ + QUEUE_FLAG_SQ_SCHED, /* single queue style io dispatch */ + QUEUE_FLAG_MAX +}; -#define QUEUE_FLAG_MQ_DEFAULT ((1UL << QUEUE_FLAG_IO_STAT) | \ - (1UL << QUEUE_FLAG_SAME_COMP) | \ - (1UL << QUEUE_FLAG_NOWAIT)) +#define QUEUE_FLAG_MQ_DEFAULT (1UL << QUEUE_FLAG_SAME_COMP) void blk_queue_flag_set(unsigned int flag, struct request_queue *q); void blk_queue_flag_clear(unsigned int flag, struct request_queue *q); -bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); -#define blk_queue_stopped(q) test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags) #define blk_queue_dying(q) test_bit(QUEUE_FLAG_DYING, &(q)->queue_flags) #define blk_queue_init_done(q) test_bit(QUEUE_FLAG_INIT_DONE, &(q)->queue_flags) #define blk_queue_nomerges(q) test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags) #define blk_queue_noxmerges(q) \ test_bit(QUEUE_FLAG_NOXMERGES, &(q)->queue_flags) -#define blk_queue_nonrot(q) test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags) -#define blk_queue_stable_writes(q) \ - test_bit(QUEUE_FLAG_STABLE_WRITES, &(q)->queue_flags) -#define blk_queue_io_stat(q) test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags) -#define blk_queue_add_random(q) test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags) -#define blk_queue_zone_resetall(q) \ - test_bit(QUEUE_FLAG_ZONE_RESETALL, &(q)->queue_flags) -#define blk_queue_dax(q) test_bit(QUEUE_FLAG_DAX, &(q)->queue_flags) -#define blk_queue_pci_p2pdma(q) \ - test_bit(QUEUE_FLAG_PCI_P2PDMA, &(q)->queue_flags) +#define blk_queue_nonrot(q) (!((q)->limits.features & BLK_FEAT_ROTATIONAL)) +#define blk_queue_io_stat(q) ((q)->limits.features & BLK_FEAT_IO_STAT) +#define blk_queue_passthrough_stat(q) \ + ((q)->limits.flags & BLK_FLAG_IOSTATS_PASSTHROUGH) +#define blk_queue_dax(q) ((q)->limits.features & BLK_FEAT_DAX) +#define blk_queue_pci_p2pdma(q) ((q)->limits.features & BLK_FEAT_PCI_P2PDMA) #ifdef CONFIG_BLK_RQ_ALLOC_TIME #define blk_queue_rq_alloc_time(q) \ test_bit(QUEUE_FLAG_RQ_ALLOC_TIME, &(q)->queue_flags) @@ -585,7 +655,7 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); #define blk_queue_registered(q) test_bit(QUEUE_FLAG_REGISTERED, &(q)->queue_flags) #define blk_queue_sq_sched(q) test_bit(QUEUE_FLAG_SQ_SCHED, &(q)->queue_flags) #define blk_queue_skip_tagset_quiesce(q) \ - test_bit(QUEUE_FLAG_SKIP_TAGSET_QUIESCE, &(q)->queue_flags) + ((q)->limits.features & BLK_FEAT_SKIP_TAGSET_QUIESCE) extern void blk_set_pm_only(struct request_queue *q); extern void blk_clear_pm_only(struct request_queue *q); @@ -615,43 +685,37 @@ static inline enum rpm_status queue_rpm_status(struct request_queue *q) static inline bool blk_queue_is_zoned(struct request_queue *q) { - return IS_ENABLED(CONFIG_BLK_DEV_ZONED) && q->limits.zoned; + return IS_ENABLED(CONFIG_BLK_DEV_ZONED) && + (q->limits.features & BLK_FEAT_ZONED); } #ifdef CONFIG_BLK_DEV_ZONED -unsigned int bdev_nr_zones(struct block_device *bdev); - static inline unsigned int disk_nr_zones(struct gendisk *disk) { - return blk_queue_is_zoned(disk->queue) ? disk->nr_zones : 0; + return disk->nr_zones; } - -static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector) +bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs); +#else /* CONFIG_BLK_DEV_ZONED */ +static inline unsigned int disk_nr_zones(struct gendisk *disk) { - if (!blk_queue_is_zoned(disk->queue)) - return 0; - return sector >> ilog2(disk->queue->limits.chunk_sectors); + return 0; } - -static inline bool disk_zone_is_seq(struct gendisk *disk, sector_t sector) +static inline bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs) { - if (!blk_queue_is_zoned(disk->queue)) - return false; - if (!disk->conv_zones_bitmap) - return true; - return !test_bit(disk_zone_no(disk, sector), disk->conv_zones_bitmap); + return false; } +#endif /* CONFIG_BLK_DEV_ZONED */ -static inline void disk_set_max_open_zones(struct gendisk *disk, - unsigned int max_open_zones) +static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector) { - disk->queue->limits.max_open_zones = max_open_zones; + if (!blk_queue_is_zoned(disk->queue)) + return 0; + return sector >> ilog2(disk->queue->limits.chunk_sectors); } -static inline void disk_set_max_active_zones(struct gendisk *disk, - unsigned int max_active_zones) +static inline unsigned int bdev_nr_zones(struct block_device *bdev) { - disk->queue->limits.max_active_zones = max_active_zones; + return disk_nr_zones(bdev->bd_disk); } static inline unsigned int bdev_max_open_zones(struct block_device *bdev) @@ -664,35 +728,6 @@ static inline unsigned int bdev_max_active_zones(struct block_device *bdev) return bdev->bd_disk->queue->limits.max_active_zones; } -#else /* CONFIG_BLK_DEV_ZONED */ -static inline unsigned int bdev_nr_zones(struct block_device *bdev) -{ - return 0; -} - -static inline unsigned int disk_nr_zones(struct gendisk *disk) -{ - return 0; -} -static inline bool disk_zone_is_seq(struct gendisk *disk, sector_t sector) -{ - return false; -} -static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector) -{ - return 0; -} -static inline unsigned int bdev_max_open_zones(struct block_device *bdev) -{ - return 0; -} - -static inline unsigned int bdev_max_active_zones(struct block_device *bdev) -{ - return 0; -} -#endif /* CONFIG_BLK_DEV_ZONED */ - static inline unsigned int blk_queue_depth(struct request_queue *q) { if (q->queue_depth) @@ -711,6 +746,9 @@ static inline unsigned int blk_queue_depth(struct request_queue *q) #define for_each_bio(_bio) \ for (; _bio; _bio = _bio->bi_next) +int __must_check add_disk_fwnode(struct device *parent, struct gendisk *disk, + const struct attribute_group **groups, + struct fwnode_handle *fwnode); int __must_check device_add_disk(struct device *parent, struct gendisk *disk, const struct attribute_group **groups); static inline int __must_check add_disk(struct gendisk *disk) @@ -722,15 +760,35 @@ void invalidate_disk(struct gendisk *disk); void set_disk_ro(struct gendisk *disk, bool read_only); void disk_uevent(struct gendisk *disk, enum kobject_action action); -static inline int get_disk_ro(struct gendisk *disk) +static inline u8 bdev_partno(const struct block_device *bdev) { - return disk->part0->bd_read_only || + return atomic_read(&bdev->__bd_flags) & BD_PARTNO; +} + +static inline bool bdev_test_flag(const struct block_device *bdev, unsigned flag) +{ + return atomic_read(&bdev->__bd_flags) & flag; +} + +static inline void bdev_set_flag(struct block_device *bdev, unsigned flag) +{ + atomic_or(flag, &bdev->__bd_flags); +} + +static inline void bdev_clear_flag(struct block_device *bdev, unsigned flag) +{ + atomic_andnot(flag, &bdev->__bd_flags); +} + +static inline bool get_disk_ro(struct gendisk *disk) +{ + return bdev_test_flag(disk->part0, BD_READ_ONLY) || test_bit(GD_READ_ONLY, &disk->state); } -static inline int bdev_read_only(struct block_device *bdev) +static inline bool bdev_read_only(struct block_device *bdev) { - return bdev->bd_read_only || get_disk_ro(bdev->bd_disk); + return bdev_test_flag(bdev, BD_READ_ONLY) || get_disk_ro(bdev->bd_disk); } bool set_capacity_and_notify(struct gendisk *disk, sector_t size); @@ -855,20 +913,23 @@ static inline unsigned int bio_zone_no(struct bio *bio) return disk_zone_no(bio->bi_bdev->bd_disk, bio->bi_iter.bi_sector); } -static inline unsigned int bio_zone_is_seq(struct bio *bio) +static inline bool bio_straddles_zones(struct bio *bio) { - return disk_zone_is_seq(bio->bi_bdev->bd_disk, bio->bi_iter.bi_sector); + return bio_sectors(bio) && + bio_zone_no(bio) != + disk_zone_no(bio->bi_bdev->bd_disk, bio_end_sector(bio) - 1); } /* - * Return how much of the chunk is left to be used for I/O at a given offset. + * Return how much within the boundary is left to be used for I/O at a given + * offset. */ -static inline unsigned int blk_chunk_sectors_left(sector_t offset, - unsigned int chunk_sectors) +static inline unsigned int blk_boundary_sectors_left(sector_t offset, + unsigned int boundary_sectors) { - if (unlikely(!is_power_of_2(chunk_sectors))) - return chunk_sectors - sector_div(offset, chunk_sectors); - return chunk_sectors - (offset & (chunk_sectors - 1)); + if (unlikely(!is_power_of_2(boundary_sectors))) + return boundary_sectors - sector_div(offset, boundary_sectors); + return boundary_sectors - (offset & (boundary_sectors - 1)); } /** @@ -880,84 +941,82 @@ static inline unsigned int blk_chunk_sectors_left(sector_t offset, * the caller can modify. The caller must call queue_limits_commit_update() * to finish the update. * - * Context: process context. The caller must have frozen the queue or ensured - * that there is outstanding I/O by other means. + * Context: process context. */ static inline struct queue_limits queue_limits_start_update(struct request_queue *q) - __acquires(q->limits_lock) { mutex_lock(&q->limits_lock); return q->limits; } +int queue_limits_commit_update_frozen(struct request_queue *q, + struct queue_limits *lim); int queue_limits_commit_update(struct request_queue *q, struct queue_limits *lim); int queue_limits_set(struct request_queue *q, struct queue_limits *lim); +int blk_validate_limits(struct queue_limits *lim); + +/** + * queue_limits_cancel_update - cancel an atomic update of queue limits + * @q: queue to update + * + * This functions cancels an atomic update of the queue limits started by + * queue_limits_start_update() and should be used when an error occurs after + * starting update. + */ +static inline void queue_limits_cancel_update(struct request_queue *q) +{ + mutex_unlock(&q->limits_lock); +} + +/* + * These helpers are for drivers that have sloppy feature negotiation and might + * have to disable DISCARD, WRITE_ZEROES or SECURE_DISCARD from the I/O + * completion handler when the device returned an indicator that the respective + * feature is not actually supported. They are racy and the driver needs to + * cope with that. Try to avoid this scheme if you can. + */ +static inline void blk_queue_disable_discard(struct request_queue *q) +{ + q->limits.max_discard_sectors = 0; +} + +static inline void blk_queue_disable_secure_erase(struct request_queue *q) +{ + q->limits.max_secure_erase_sectors = 0; +} + +static inline void blk_queue_disable_write_zeroes(struct request_queue *q) +{ + q->limits.max_write_zeroes_sectors = 0; +} /* * Access functions for manipulating queue properties */ -void blk_queue_bounce_limit(struct request_queue *q, enum blk_bounce limit); -extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int); -extern void blk_queue_chunk_sectors(struct request_queue *, unsigned int); -extern void blk_queue_max_segments(struct request_queue *, unsigned short); -extern void blk_queue_max_discard_segments(struct request_queue *, - unsigned short); -void blk_queue_max_secure_erase_sectors(struct request_queue *q, - unsigned int max_sectors); -extern void blk_queue_max_segment_size(struct request_queue *, unsigned int); -extern void blk_queue_max_discard_sectors(struct request_queue *q, - unsigned int max_discard_sectors); -extern void blk_queue_max_write_zeroes_sectors(struct request_queue *q, - unsigned int max_write_same_sectors); -extern void blk_queue_logical_block_size(struct request_queue *, unsigned int); -extern void blk_queue_max_zone_append_sectors(struct request_queue *q, - unsigned int max_zone_append_sectors); -extern void blk_queue_physical_block_size(struct request_queue *, unsigned int); -void blk_queue_zone_write_granularity(struct request_queue *q, - unsigned int size); -extern void blk_queue_alignment_offset(struct request_queue *q, - unsigned int alignment); -void disk_update_readahead(struct gendisk *disk); -extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min); -extern void blk_queue_io_min(struct request_queue *q, unsigned int min); -extern void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt); -extern void blk_queue_io_opt(struct request_queue *q, unsigned int opt); extern void blk_set_queue_depth(struct request_queue *q, unsigned int depth); extern void blk_set_stacking_limits(struct queue_limits *lim); extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, sector_t offset); void queue_limits_stack_bdev(struct queue_limits *t, struct block_device *bdev, sector_t offset, const char *pfx); -extern void blk_queue_update_dma_pad(struct request_queue *, unsigned int); -extern void blk_queue_segment_boundary(struct request_queue *, unsigned long); -extern void blk_queue_virt_boundary(struct request_queue *, unsigned long); -extern void blk_queue_dma_alignment(struct request_queue *, int); -extern void blk_queue_update_dma_alignment(struct request_queue *, int); extern void blk_queue_rq_timeout(struct request_queue *, unsigned int); -extern void blk_queue_write_cache(struct request_queue *q, bool enabled, bool fua); struct blk_independent_access_ranges * disk_alloc_independent_access_ranges(struct gendisk *disk, int nr_ia_ranges); void disk_set_independent_access_ranges(struct gendisk *disk, struct blk_independent_access_ranges *iars); -/* - * Elevator features for blk_queue_required_elevator_features: - */ -/* Supports zoned block devices sequential write constraint */ -#define ELEVATOR_F_ZBD_SEQ_WRITE (1U << 0) - -extern void blk_queue_required_elevator_features(struct request_queue *q, - unsigned int features); -extern bool blk_queue_can_use_dma_map_merging(struct request_queue *q, - struct device *dev); - bool __must_check blk_get_queue(struct request_queue *); extern void blk_put_queue(struct request_queue *); void blk_mark_disk_dead(struct gendisk *disk); +struct rq_list { + struct request *head; + struct request *tail; +}; + #ifdef CONFIG_BLOCK /* * blk_plug permits building a queue of related requests by holding the I/O @@ -971,10 +1030,10 @@ void blk_mark_disk_dead(struct gendisk *disk); * blk_flush_plug() is called. */ struct blk_plug { - struct request *mq_list; /* blk-mq requests */ + struct rq_list mq_list; /* blk-mq requests */ /* if ios_left is > 1, we can batch tag/rq allocations */ - struct request *cached_rq; + struct rq_list cached_rqs; u64 cur_ktime; unsigned short nr_ios; @@ -1067,6 +1126,7 @@ int blkdev_issue_secure_erase(struct block_device *bdev, sector_t sector, #define BLKDEV_ZERO_NOUNMAP (1 << 0) /* do not free blocks */ #define BLKDEV_ZERO_NOFALLBACK (1 << 1) /* don't write explicit zeroes */ +#define BLKDEV_ZERO_KILLABLE (1 << 2) /* interruptible by fatal signals */ extern int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct bio **biop, @@ -1097,7 +1157,7 @@ static inline int sb_issue_zeroout(struct super_block *sb, sector_t block, static inline bool bdev_is_partition(struct block_device *bdev) { - return bdev->bd_partno; + return bdev_partno(bdev) != 0; } enum blk_default_limits { @@ -1116,6 +1176,11 @@ enum blk_default_limits { */ #define BLK_DEF_MAX_SECTORS_CAP 2560u +static inline struct queue_limits *bdev_limits(struct block_device *bdev) +{ + return &bdev_get_queue(bdev)->limits; +} + static inline unsigned long queue_segment_boundary(const struct request_queue *q) { return q->limits.seg_boundary_mask; @@ -1156,18 +1221,20 @@ static inline unsigned int queue_max_segment_size(const struct request_queue *q) return q->limits.max_segment_size; } -static inline unsigned int queue_max_zone_append_sectors(const struct request_queue *q) +static inline bool queue_emulates_zone_append(struct request_queue *q) { + return blk_queue_is_zoned(q) && !q->limits.max_hw_zone_append_sectors; +} - const struct queue_limits *l = &q->limits; - - return min(l->max_zone_append_sectors, l->max_sectors); +static inline bool bdev_emulates_zone_append(struct block_device *bdev) +{ + return queue_emulates_zone_append(bdev_get_queue(bdev)); } static inline unsigned int bdev_max_zone_append_sectors(struct block_device *bdev) { - return queue_max_zone_append_sectors(bdev_get_queue(bdev)); + return bdev_limits(bdev)->max_zone_append_sectors; } static inline unsigned int bdev_max_segments(struct block_device *bdev) @@ -1177,12 +1244,7 @@ static inline unsigned int bdev_max_segments(struct block_device *bdev) static inline unsigned queue_logical_block_size(const struct request_queue *q) { - int retval = 512; - - if (q && q->limits.logical_block_size) - retval = q->limits.logical_block_size; - - return retval; + return q->limits.logical_block_size; } static inline unsigned int bdev_logical_block_size(struct block_device *bdev) @@ -1205,7 +1267,7 @@ static inline unsigned int queue_io_min(const struct request_queue *q) return q->limits.io_min; } -static inline int bdev_io_min(struct block_device *bdev) +static inline unsigned int bdev_io_min(struct block_device *bdev) { return queue_io_min(bdev_get_queue(bdev)); } @@ -1215,7 +1277,7 @@ static inline unsigned int queue_io_opt(const struct request_queue *q) return q->limits.io_opt; } -static inline int bdev_io_opt(struct block_device *bdev) +static inline unsigned int bdev_io_opt(struct block_device *bdev) { return queue_io_opt(bdev_get_queue(bdev)); } @@ -1237,28 +1299,23 @@ unsigned int bdev_discard_alignment(struct block_device *bdev); static inline unsigned int bdev_max_discard_sectors(struct block_device *bdev) { - return bdev_get_queue(bdev)->limits.max_discard_sectors; + return bdev_limits(bdev)->max_discard_sectors; } static inline unsigned int bdev_discard_granularity(struct block_device *bdev) { - return bdev_get_queue(bdev)->limits.discard_granularity; + return bdev_limits(bdev)->discard_granularity; } static inline unsigned int bdev_max_secure_erase_sectors(struct block_device *bdev) { - return bdev_get_queue(bdev)->limits.max_secure_erase_sectors; + return bdev_limits(bdev)->max_secure_erase_sectors; } static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev) { - struct request_queue *q = bdev_get_queue(bdev); - - if (q) - return q->limits.max_write_zeroes_sectors; - - return 0; + return bdev_limits(bdev)->max_write_zeroes_sectors; } static inline bool bdev_nonrot(struct block_device *bdev) @@ -1268,29 +1325,38 @@ static inline bool bdev_nonrot(struct block_device *bdev) static inline bool bdev_synchronous(struct block_device *bdev) { - return test_bit(QUEUE_FLAG_SYNCHRONOUS, - &bdev_get_queue(bdev)->queue_flags); + return bdev->bd_disk->queue->limits.features & BLK_FEAT_SYNCHRONOUS; } static inline bool bdev_stable_writes(struct block_device *bdev) { - return test_bit(QUEUE_FLAG_STABLE_WRITES, - &bdev_get_queue(bdev)->queue_flags); + struct request_queue *q = bdev_get_queue(bdev); + + if (IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY) && + q->limits.integrity.csum_type != BLK_INTEGRITY_CSUM_NONE) + return true; + return q->limits.features & BLK_FEAT_STABLE_WRITES; +} + +static inline bool blk_queue_write_cache(struct request_queue *q) +{ + return (q->limits.features & BLK_FEAT_WRITE_CACHE) && + !(q->limits.flags & BLK_FLAG_WRITE_CACHE_DISABLED); } static inline bool bdev_write_cache(struct block_device *bdev) { - return test_bit(QUEUE_FLAG_WC, &bdev_get_queue(bdev)->queue_flags); + return blk_queue_write_cache(bdev_get_queue(bdev)); } static inline bool bdev_fua(struct block_device *bdev) { - return test_bit(QUEUE_FLAG_FUA, &bdev_get_queue(bdev)->queue_flags); + return bdev_limits(bdev)->features & BLK_FEAT_FUA; } static inline bool bdev_nowait(struct block_device *bdev) { - return test_bit(QUEUE_FLAG_NOWAIT, &bdev_get_queue(bdev)->queue_flags); + return bdev->bd_disk->queue->limits.features & BLK_FEAT_NOWAIT; } static inline bool bdev_is_zoned(struct block_device *bdev) @@ -1303,18 +1369,6 @@ static inline unsigned int bdev_zone_no(struct block_device *bdev, sector_t sec) return disk_zone_no(bdev->bd_disk, sec); } -/* Whether write serialization is required for @op on zoned devices. */ -static inline bool op_needs_zoned_write_locking(enum req_op op) -{ - return op == REQ_OP_WRITE || op == REQ_OP_WRITE_ZEROES; -} - -static inline bool bdev_op_is_zoned_write(struct block_device *bdev, - enum req_op op) -{ - return bdev_is_zoned(bdev) && op_needs_zoned_write_locking(op); -} - static inline sector_t bdev_zone_sectors(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); @@ -1330,15 +1384,75 @@ static inline sector_t bdev_offset_from_zone_start(struct block_device *bdev, return sector & (bdev_zone_sectors(bdev) - 1); } +static inline sector_t bio_offset_from_zone_start(struct bio *bio) +{ + return bdev_offset_from_zone_start(bio->bi_bdev, + bio->bi_iter.bi_sector); +} + static inline bool bdev_is_zone_start(struct block_device *bdev, sector_t sector) { return bdev_offset_from_zone_start(bdev, sector) == 0; } -static inline int queue_dma_alignment(const struct request_queue *q) +/** + * bdev_zone_is_seq - check if a sector belongs to a sequential write zone + * @bdev: block device to check + * @sector: sector number + * + * Check if @sector on @bdev is contained in a sequential write required zone. + */ +static inline bool bdev_zone_is_seq(struct block_device *bdev, sector_t sector) +{ + bool is_seq = false; + +#if IS_ENABLED(CONFIG_BLK_DEV_ZONED) + if (bdev_is_zoned(bdev)) { + struct gendisk *disk = bdev->bd_disk; + unsigned long *bitmap; + + rcu_read_lock(); + bitmap = rcu_dereference(disk->conv_zones_bitmap); + is_seq = !bitmap || + !test_bit(disk_zone_no(disk, sector), bitmap); + rcu_read_unlock(); + } +#endif + + return is_seq; +} + +int blk_zone_issue_zeroout(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp_mask); + +static inline unsigned int queue_dma_alignment(const struct request_queue *q) { - return q ? q->limits.dma_alignment : 511; + return q->limits.dma_alignment; +} + +static inline unsigned int +queue_atomic_write_unit_max_bytes(const struct request_queue *q) +{ + return q->limits.atomic_write_unit_max; +} + +static inline unsigned int +queue_atomic_write_unit_min_bytes(const struct request_queue *q) +{ + return q->limits.atomic_write_unit_min; +} + +static inline unsigned int +queue_atomic_write_boundary_bytes(const struct request_queue *q) +{ + return q->limits.atomic_write_boundary_sectors << SECTOR_SHIFT; +} + +static inline unsigned int +queue_atomic_write_max_bytes(const struct request_queue *q) +{ + return q->limits.atomic_write_max_sectors << SECTOR_SHIFT; } static inline unsigned int bdev_dma_alignment(struct block_device *bdev) @@ -1353,10 +1467,17 @@ static inline bool bdev_iter_is_aligned(struct block_device *bdev, bdev_logical_block_size(bdev) - 1); } -static inline int blk_rq_aligned(struct request_queue *q, unsigned long addr, +static inline unsigned int +blk_lim_dma_alignment_and_pad(struct queue_limits *lim) +{ + return lim->dma_alignment | lim->dma_pad_mask; +} + +static inline bool blk_rq_aligned(struct request_queue *q, unsigned long addr, unsigned int len) { - unsigned int alignment = queue_dma_alignment(q) | q->dma_pad_mask; + unsigned int alignment = blk_lim_dma_alignment_and_pad(&q->limits); + return !(addr & alignment) && !(len & alignment); } @@ -1366,11 +1487,6 @@ static inline unsigned int blksize_bits(unsigned int size) return order_base_2(size >> SECTOR_SHIFT) + SECTOR_SHIFT; } -static inline unsigned int block_size(struct block_device *bdev) -{ - return 1 << bdev->bd_inode->i_blkbits; -} - int kblockd_schedule_work(struct work_struct *work); int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay); @@ -1475,8 +1591,7 @@ static inline void bio_end_io_acct(struct bio *bio, unsigned long start_time) return bio_end_io_acct_remapped(bio, start_time, bio->bi_bdev); } -int bdev_read_only(struct block_device *bdev); -int set_blocksize(struct block_device *bdev, int size); +int set_blocksize(struct file *file, int size); int lookup_bdev(const char *pathname, dev_t *dev); @@ -1538,6 +1653,8 @@ void blkdev_put_no_open(struct block_device *bdev); struct block_device *I_BDEV(struct inode *inode); struct block_device *file_bdev(struct file *bdev_file); +bool disk_live(struct gendisk *disk); +unsigned int block_size(struct block_device *bdev); #ifdef CONFIG_BLOCK void invalidate_bdev(struct block_device *bdev); @@ -1545,7 +1662,7 @@ int sync_blockdev(struct block_device *bdev); int sync_blockdev_range(struct block_device *bdev, loff_t lstart, loff_t lend); int sync_blockdev_nowait(struct block_device *bdev); void sync_bdevs(bool wait); -void bdev_statx_dioalign(struct inode *inode, struct kstat *stat); +void bdev_statx(struct path *, struct kstat *, u32); void printk_all_partitions(void); int __init early_lookup_bdev(const char *pathname, dev_t *dev); #else @@ -1563,7 +1680,8 @@ static inline int sync_blockdev_nowait(struct block_device *bdev) static inline void sync_bdevs(bool wait) { } -static inline void bdev_statx_dioalign(struct inode *inode, struct kstat *stat) +static inline void bdev_statx(struct path *path, struct kstat *stat, + u32 request_mask) { } static inline void printk_all_partitions(void) @@ -1580,11 +1698,51 @@ int bdev_thaw(struct block_device *bdev); void bdev_fput(struct file *bdev_file); struct io_comp_batch { - struct request *req_list; + struct rq_list req_list; bool need_ts; void (*complete)(struct io_comp_batch *); }; +static inline bool blk_atomic_write_start_sect_aligned(sector_t sector, + struct queue_limits *limits) +{ + unsigned int alignment = max(limits->atomic_write_hw_unit_min, + limits->atomic_write_hw_boundary); + + return IS_ALIGNED(sector, alignment >> SECTOR_SHIFT); +} + +static inline bool bdev_can_atomic_write(struct block_device *bdev) +{ + struct request_queue *bd_queue = bdev->bd_queue; + struct queue_limits *limits = &bd_queue->limits; + + if (!limits->atomic_write_unit_min) + return false; + + if (bdev_is_partition(bdev)) + return blk_atomic_write_start_sect_aligned(bdev->bd_start_sect, + limits); + + return true; +} + +static inline unsigned int +bdev_atomic_write_unit_min_bytes(struct block_device *bdev) +{ + if (!bdev_can_atomic_write(bdev)) + return 0; + return queue_atomic_write_unit_min_bytes(bdev_get_queue(bdev)); +} + +static inline unsigned int +bdev_atomic_write_unit_max_bytes(struct block_device *bdev) +{ + if (!bdev_can_atomic_write(bdev)) + return 0; + return queue_atomic_write_unit_max_bytes(bdev_get_queue(bdev)); +} + #define DEFINE_IO_COMP_BATCH(name) struct io_comp_batch name = { } #endif /* _LINUX_BLKDEV_H */ diff --git a/include/linux/bootmem_info.h b/include/linux/bootmem_info.h index cffa38a73618..d8a8d245824a 100644 --- a/include/linux/bootmem_info.h +++ b/include/linux/bootmem_info.h @@ -6,11 +6,10 @@ #include <linux/kmemleak.h> /* - * Types for free bootmem stored in page->lru.next. These have to be in - * some random range in unsigned long space for debugging purposes. + * Types for free bootmem stored in the low bits of page->private. */ -enum { - MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE = 12, +enum bootmem_type { + MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE = 1, SECTION_INFO = MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE, MIX_SECTION_INFO, NODE_INFO, @@ -21,9 +20,19 @@ enum { void __init register_page_bootmem_info_node(struct pglist_data *pgdat); void get_page_bootmem(unsigned long info, struct page *page, - unsigned long type); + enum bootmem_type type); void put_page_bootmem(struct page *page); +static inline enum bootmem_type bootmem_type(const struct page *page) +{ + return (unsigned long)page->private & 0xf; +} + +static inline unsigned long bootmem_info(const struct page *page) +{ + return (unsigned long)page->private >> 4; +} + /* * Any memory allocated via the memblock allocator and not via the * buddy will be marked reserved already in the memmap. For those @@ -31,7 +40,7 @@ void put_page_bootmem(struct page *page); */ static inline void free_bootmem_page(struct page *page) { - unsigned long magic = page->index; + enum bootmem_type type = bootmem_type(page); /* * The reserve_bootmem_region sets the reserved flag on bootmem @@ -39,7 +48,7 @@ static inline void free_bootmem_page(struct page *page) */ VM_BUG_ON_PAGE(page_ref_count(page) != 2, page); - if (magic == SECTION_INFO || magic == MIX_SECTION_INFO) + if (type == SECTION_INFO || type == MIX_SECTION_INFO) put_page_bootmem(page); else VM_BUG_ON_PAGE(1, page); @@ -53,8 +62,18 @@ static inline void put_page_bootmem(struct page *page) { } +static inline enum bootmem_type bootmem_type(const struct page *page) +{ + return SECTION_INFO; +} + +static inline unsigned long bootmem_info(const struct page *page) +{ + return 0; +} + static inline void get_page_bootmem(unsigned long info, struct page *page, - unsigned long type) + enum bootmem_type type) { } diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index fb3c3e7181e6..7fc69083e745 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -138,7 +138,7 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, short access, enum cgroup_bpf_attach_type atype); int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, - struct ctl_table *table, int write, + const struct ctl_table *table, int write, char **buf, size_t *pcount, loff_t *ppos, enum cgroup_bpf_attach_type atype); @@ -209,7 +209,7 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk, int __ret = 0; \ if (cgroup_bpf_enabled(CGROUP_INET_EGRESS) && sk) { \ typeof(sk) __sk = sk_to_full_sk(sk); \ - if (sk_fullsock(__sk) && __sk == skb_to_full_sk(skb) && \ + if (__sk && __sk == skb_to_full_sk(skb) && \ cgroup_bpf_sock_enabled(__sk, CGROUP_INET_EGRESS)) \ __ret = __cgroup_bpf_run_filter_skb(__sk, skb, \ CGROUP_INET_EGRESS); \ @@ -390,14 +390,6 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk, __ret; \ }) -#define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) \ -({ \ - int __ret = 0; \ - if (cgroup_bpf_enabled(CGROUP_GETSOCKOPT)) \ - copy_from_sockptr(&__ret, optlen, sizeof(int)); \ - __ret; \ -}) - #define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, optlen, \ max_optlen, retval) \ ({ \ @@ -518,7 +510,6 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; }) #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(atype, major, minor, access) ({ 0; }) #define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,pos) ({ 0; }) -#define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, \ optlen, max_optlen, retval) ({ retval; }) #define BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sock, level, optname, optval, \ diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 890e152d553e..f3f50e29d639 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -184,8 +184,8 @@ struct bpf_map_ops { }; enum { - /* Support at most 10 fields in a BTF type */ - BTF_FIELDS_MAX = 10, + /* Support at most 11 fields in a BTF type */ + BTF_FIELDS_MAX = 11, }; enum btf_field_type { @@ -202,6 +202,8 @@ enum btf_field_type { BPF_GRAPH_NODE = BPF_RB_NODE | BPF_LIST_NODE, BPF_GRAPH_ROOT = BPF_RB_ROOT | BPF_LIST_HEAD, BPF_REFCOUNT = (1 << 9), + BPF_WORKQUEUE = (1 << 10), + BPF_UPTR = (1 << 11), }; typedef void (*btf_dtor_kfunc_t)(void *); @@ -238,6 +240,7 @@ struct btf_record { u32 field_mask; int spin_lock_off; int timer_off; + int wq_off; int refcount_off; struct btf_field fields[]; }; @@ -273,7 +276,7 @@ struct bpf_map { u32 btf_value_type_id; u32 btf_vmlinux_value_type_id; struct btf *btf; -#ifdef CONFIG_MEMCG_KMEM +#ifdef CONFIG_MEMCG struct obj_cgroup *objcg; #endif char name[BPF_OBJ_NAME_LEN]; @@ -292,6 +295,7 @@ struct bpf_map { * same prog type, JITed flag and xdp_has_frags flag. */ struct { + const struct btf_type *attach_func_proto; spinlock_t lock; enum bpf_prog_type type; bool jited; @@ -312,11 +316,15 @@ static inline const char *btf_field_type_name(enum btf_field_type type) return "bpf_spin_lock"; case BPF_TIMER: return "bpf_timer"; + case BPF_WORKQUEUE: + return "bpf_wq"; case BPF_KPTR_UNREF: case BPF_KPTR_REF: return "kptr"; case BPF_KPTR_PERCPU: return "percpu_kptr"; + case BPF_UPTR: + return "uptr"; case BPF_LIST_HEAD: return "bpf_list_head"; case BPF_LIST_NODE: @@ -340,9 +348,12 @@ static inline u32 btf_field_type_size(enum btf_field_type type) return sizeof(struct bpf_spin_lock); case BPF_TIMER: return sizeof(struct bpf_timer); + case BPF_WORKQUEUE: + return sizeof(struct bpf_wq); case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: + case BPF_UPTR: return sizeof(u64); case BPF_LIST_HEAD: return sizeof(struct bpf_list_head); @@ -367,9 +378,12 @@ static inline u32 btf_field_type_align(enum btf_field_type type) return __alignof__(struct bpf_spin_lock); case BPF_TIMER: return __alignof__(struct bpf_timer); + case BPF_WORKQUEUE: + return __alignof__(struct bpf_wq); case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: + case BPF_UPTR: return __alignof__(u64); case BPF_LIST_HEAD: return __alignof__(struct bpf_list_head); @@ -406,9 +420,11 @@ static inline void bpf_obj_init_field(const struct btf_field *field, void *addr) /* RB_ROOT_CACHED 0-inits, no need to do anything after memset */ case BPF_SPIN_LOCK: case BPF_TIMER: + case BPF_WORKQUEUE: case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: + case BPF_UPTR: break; default: WARN_ON_ONCE(1); @@ -497,6 +513,25 @@ static inline void copy_map_value_long(struct bpf_map *map, void *dst, void *src bpf_obj_memcpy(map->record, dst, src, map->value_size, true); } +static inline void bpf_obj_swap_uptrs(const struct btf_record *rec, void *dst, void *src) +{ + unsigned long *src_uptr, *dst_uptr; + const struct btf_field *field; + int i; + + if (!btf_record_has_field(rec, BPF_UPTR)) + return; + + for (i = 0, field = rec->fields; i < rec->cnt; i++, field++) { + if (field->type != BPF_UPTR) + continue; + + src_uptr = src + field->offset; + dst_uptr = dst + field->offset; + swap(*src_uptr, *dst_uptr); + } +} + static inline void bpf_obj_memzero(struct btf_record *rec, void *dst, u32 size) { u32 curr_off = 0; @@ -525,6 +560,7 @@ static inline void zero_map_value(struct bpf_map *map, void *dst) void copy_map_value_locked(struct bpf_map *map, void *dst, void *src, bool lock_src); void bpf_timer_cancel_and_free(void *timer); +void bpf_wq_cancel_and_free(void *timer); void bpf_list_head_free(const struct btf_field *field, void *list_head, struct bpf_spin_lock *spin_lock); void bpf_rb_root_free(const struct btf_field *field, void *rb_root, @@ -624,6 +660,7 @@ enum bpf_type_flag { */ PTR_UNTRUSTED = BIT(6 + BPF_BASE_TYPE_BITS), + /* MEM can be uninitialized. */ MEM_UNINIT = BIT(7 + BPF_BASE_TYPE_BITS), /* DYNPTR points to memory local to the bpf program. */ @@ -684,6 +721,18 @@ enum bpf_type_flag { /* DYNPTR points to xdp_buff */ DYNPTR_TYPE_XDP = BIT(16 + BPF_BASE_TYPE_BITS), + /* Memory must be aligned on some architectures, used in combination with + * MEM_FIXED_SIZE. + */ + MEM_ALIGNED = BIT(17 + BPF_BASE_TYPE_BITS), + + /* MEM is being written to, often combined with MEM_UNINIT. Non-presence + * of MEM_WRITE means that MEM is only being read. MEM_WRITE without the + * MEM_UNINIT means that memory needs to be initialized since it is also + * read. + */ + MEM_WRITE = BIT(18 + BPF_BASE_TYPE_BITS), + __BPF_TYPE_FLAG_MAX, __BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1, }; @@ -721,8 +770,6 @@ enum bpf_arg_type { ARG_ANYTHING, /* any (initialized) argument is ok */ ARG_PTR_TO_SPIN_LOCK, /* pointer to bpf_spin_lock */ ARG_PTR_TO_SOCK_COMMON, /* pointer to sock_common */ - ARG_PTR_TO_INT, /* pointer to int */ - ARG_PTR_TO_LONG, /* pointer to long */ ARG_PTR_TO_SOCKET, /* pointer to bpf_sock (fullsock) */ ARG_PTR_TO_BTF_ID, /* pointer to in-kernel struct */ ARG_PTR_TO_RINGBUF_MEM, /* pointer to dynamically reserved ringbuf memory */ @@ -733,7 +780,7 @@ enum bpf_arg_type { ARG_PTR_TO_STACK, /* pointer to stack */ ARG_PTR_TO_CONST_STR, /* pointer to a null terminated read-only string */ ARG_PTR_TO_TIMER, /* pointer to bpf_timer */ - ARG_PTR_TO_KPTR, /* pointer to referenced kptr */ + ARG_KPTR_XCHG_DEST, /* pointer to destination that kptrs are bpf_kptr_xchg'd into */ ARG_PTR_TO_DYNPTR, /* pointer to bpf_dynptr. See bpf_type_flag for dynptr type */ __BPF_ARG_TYPE_MAX, @@ -744,10 +791,10 @@ enum bpf_arg_type { ARG_PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_SOCKET, ARG_PTR_TO_STACK_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_STACK, ARG_PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_BTF_ID, - /* pointer to memory does not need to be initialized, helper function must fill - * all bytes or clear them in error case. + /* Pointer to memory does not need to be initialized, since helper function + * fills all bytes or clears them in error case. */ - ARG_PTR_TO_UNINIT_MEM = MEM_UNINIT | ARG_PTR_TO_MEM, + ARG_PTR_TO_UNINIT_MEM = MEM_UNINIT | MEM_WRITE | ARG_PTR_TO_MEM, /* Pointer to valid memory of size known at compile time. */ ARG_PTR_TO_FIXED_SIZE_MEM = MEM_FIXED_SIZE | ARG_PTR_TO_MEM, @@ -797,6 +844,12 @@ struct bpf_func_proto { bool gpl_only; bool pkt_access; bool might_sleep; + /* set to true if helper follows contract for llvm + * attribute bpf_fastcall: + * - void functions do not scratch r0 + * - functions taking N arguments scratch only registers r1-rN + */ + bool allow_fastcall; enum bpf_return_type ret_type; union { struct { @@ -879,10 +932,6 @@ enum bpf_reg_type { * additional context, assume the value is non-null. */ PTR_TO_BTF_ID, - /* PTR_TO_BTF_ID_OR_NULL points to a kernel struct that has not - * been checked for null. Used primarily to inform the verifier - * an explicit null check is required for this struct. - */ PTR_TO_MEM, /* reg points to valid memory region */ PTR_TO_ARENA, PTR_TO_BUF, /* reg points to a read/write buffer */ @@ -895,6 +944,10 @@ enum bpf_reg_type { PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | PTR_TO_SOCKET, PTR_TO_SOCK_COMMON_OR_NULL = PTR_MAYBE_NULL | PTR_TO_SOCK_COMMON, PTR_TO_TCP_SOCK_OR_NULL = PTR_MAYBE_NULL | PTR_TO_TCP_SOCK, + /* PTR_TO_BTF_ID_OR_NULL points to a kernel struct that has not + * been checked for null. Used primarily to inform the verifier + * an explicit null check is required for this struct. + */ PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | PTR_TO_BTF_ID, /* This must be the last entry. Its purpose is to ensure the enum is @@ -909,6 +962,7 @@ static_assert(__BPF_REG_TYPE_MAX <= BPF_BASE_TYPE_LIMIT); */ struct bpf_insn_access_aux { enum bpf_reg_type reg_type; + bool is_ldsx; union { int ctx_field_size; struct { @@ -917,6 +971,7 @@ struct bpf_insn_access_aux { }; }; struct bpf_verifier_log *log; /* for verbose logs */ + bool is_retval; /* is accessing function return value ? */ }; static inline void @@ -955,6 +1010,8 @@ struct bpf_verifier_ops { struct bpf_insn_access_aux *info); int (*gen_prologue)(struct bpf_insn *insn, bool direct_write, const struct bpf_prog *prog); + int (*gen_epilogue)(struct bpf_insn *insn, const struct bpf_prog *prog, + s16 ctx_stack_off); int (*gen_ld_abs)(const struct bpf_insn *orig, struct bpf_insn *insn_buf); u32 (*convert_ctx_access)(enum bpf_access_type type, @@ -1116,8 +1173,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i void *func_addr); void *arch_alloc_bpf_trampoline(unsigned int size); void arch_free_bpf_trampoline(void *image, unsigned int size); -void arch_protect_bpf_trampoline(void *image, unsigned int size); -void arch_unprotect_bpf_trampoline(void *image, unsigned int size); +int __must_check arch_protect_bpf_trampoline(void *image, unsigned int size); int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags, struct bpf_tramp_links *tlinks, void *func_addr); @@ -1266,10 +1322,15 @@ int bpf_dynptr_check_size(u32 size); u32 __bpf_dynptr_size(const struct bpf_dynptr_kern *ptr); const void *__bpf_dynptr_data(const struct bpf_dynptr_kern *ptr, u32 len); void *__bpf_dynptr_data_rw(const struct bpf_dynptr_kern *ptr, u32 len); +bool __bpf_dynptr_is_rdonly(const struct bpf_dynptr_kern *ptr); #ifdef CONFIG_BPF_JIT -int bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr); -int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr); +int bpf_trampoline_link_prog(struct bpf_tramp_link *link, + struct bpf_trampoline *tr, + struct bpf_prog *tgt_prog); +int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, + struct bpf_trampoline *tr, + struct bpf_prog *tgt_prog); struct bpf_trampoline *bpf_trampoline_get(u64 key, struct bpf_attach_target_info *tgt_info); void bpf_trampoline_put(struct bpf_trampoline *tr); @@ -1341,7 +1402,8 @@ int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_func void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from, struct bpf_prog *to); /* Called only from JIT-enabled code, so there's no need for stubs. */ -void bpf_image_ksym_add(void *data, unsigned int size, struct bpf_ksym *ksym); +void bpf_image_ksym_init(void *data, unsigned int size, struct bpf_ksym *ksym); +void bpf_image_ksym_add(struct bpf_ksym *ksym); void bpf_image_ksym_del(struct bpf_ksym *ksym); void bpf_ksym_add(struct bpf_ksym *ksym); void bpf_ksym_del(struct bpf_ksym *ksym); @@ -1350,12 +1412,14 @@ void bpf_jit_uncharge_modmem(u32 size); bool bpf_prog_has_trampoline(const struct bpf_prog *prog); #else static inline int bpf_trampoline_link_prog(struct bpf_tramp_link *link, - struct bpf_trampoline *tr) + struct bpf_trampoline *tr, + struct bpf_prog *tgt_prog) { return -ENOTSUPP; } static inline int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, - struct bpf_trampoline *tr) + struct bpf_trampoline *tr, + struct bpf_prog *tgt_prog) { return -ENOTSUPP; } @@ -1444,6 +1508,7 @@ struct bpf_prog_aux { u32 max_rdwr_access; struct btf *attach_btf; const struct bpf_ctx_arg_aux *ctx_arg_info; + void __percpu *priv_stack_ptr; struct mutex dst_mutex; /* protects dst_* pointers below, *after* prog becomes visible */ struct bpf_prog *dst_prog; struct bpf_trampoline *dst_trampoline; @@ -1459,7 +1524,14 @@ struct bpf_prog_aux { bool xdp_has_frags; bool exception_cb; bool exception_boundary; + bool is_extended; /* true if extended by freplace program */ + bool jits_use_priv_stack; + bool priv_stack_requested; + bool changes_pkt_data; + u64 prog_array_member_cnt; /* counts how many times as member of prog_array */ + struct mutex ext_mutex; /* mutex for is_extended and prog_array_member_cnt */ struct bpf_arena *arena; + void (*recursion_detected)(struct bpf_prog *prog); /* callback if recursion is detected */ /* BTF_KIND_FUNC_PROTO for valid attach_btf_id */ const struct btf_type *attach_func_proto; /* function name for valid attach_btf_id */ @@ -1574,6 +1646,11 @@ struct bpf_link { enum bpf_link_type type; const struct bpf_link_ops *ops; struct bpf_prog *prog; + /* whether BPF link itself has "sleepable" semantics, which can differ + * from underlying BPF program having a "sleepable" semantics, as BPF + * link's semantics is determined by target attach hook + */ + bool sleepable; /* rcu is used before freeing, work can be used to schedule that * RCU-based freeing before that, so they never overlap */ @@ -1590,8 +1667,10 @@ struct bpf_link_ops { */ void (*dealloc)(struct bpf_link *link); /* deallocate link resources callback, called after RCU grace period; - * if underlying BPF program is sleepable we go through tasks trace - * RCU GP and then "classic" RCU GP + * if either the underlying BPF program is sleepable or BPF link's + * target hook is sleepable, we'll go through tasks trace RCU GP and + * then "classic" RCU GP; this need for chaining tasks trace and + * classic RCU GPs is designated by setting bpf_link->sleepable flag */ void (*dealloc_deferred)(struct bpf_link *link); int (*detach)(struct bpf_link *link); @@ -1602,6 +1681,7 @@ struct bpf_link_ops { struct bpf_link_info *info); int (*update_map)(struct bpf_link *link, struct bpf_map *new_map, struct bpf_map *old_map); + __poll_t (*poll)(struct file *file, struct poll_table_struct *pts); }; struct bpf_tramp_link { @@ -1622,6 +1702,12 @@ struct bpf_tracing_link { struct bpf_prog *tgt_prog; }; +struct bpf_raw_tp_link { + struct bpf_link link; + struct bpf_raw_event_map *btp; + u64 cookie; +}; + struct bpf_link_primer { struct bpf_link *link; struct file *file; @@ -1714,9 +1800,9 @@ struct bpf_struct_ops { int (*init_member)(const struct btf_type *t, const struct btf_member *member, void *kdata, const void *udata); - int (*reg)(void *kdata); - void (*unreg)(void *kdata); - int (*update)(void *kdata, void *old_kdata); + int (*reg)(void *kdata, struct bpf_link *link); + void (*unreg)(void *kdata, struct bpf_link *link); + int (*update)(void *kdata, void *old_kdata, struct bpf_link *link); int (*validate)(void *kdata); void *cfi_stubs; struct module *owner; @@ -1778,6 +1864,7 @@ struct bpf_struct_ops_common_value { #define BPF_MODULE_OWNER ((void *)((0xeB9FUL << 2) + POISON_POINTER_DELTA)) bool bpf_struct_ops_get(const void *kdata); void bpf_struct_ops_put(const void *kdata); +int bpf_struct_ops_supported(const struct bpf_struct_ops *st_ops, u32 moff); int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, void *value); int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks, @@ -1834,6 +1921,10 @@ static inline void bpf_module_put(const void *data, struct module *owner) { module_put(owner); } +static inline int bpf_struct_ops_supported(const struct bpf_struct_ops *st_ops, u32 moff) +{ + return -ENOTSUPP; +} static inline int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, void *value) @@ -2103,26 +2194,25 @@ bpf_prog_run_array(const struct bpf_prog_array *array, * rcu-protected dynamically sized maps. */ static __always_inline u32 -bpf_prog_run_array_uprobe(const struct bpf_prog_array __rcu *array_rcu, +bpf_prog_run_array_uprobe(const struct bpf_prog_array *array, const void *ctx, bpf_prog_run_fn run_prog) { const struct bpf_prog_array_item *item; const struct bpf_prog *prog; - const struct bpf_prog_array *array; struct bpf_run_ctx *old_run_ctx; struct bpf_trace_run_ctx run_ctx; u32 ret = 1; might_fault(); + RCU_LOCKDEP_WARN(!rcu_read_lock_trace_held(), "no rcu lock held"); + + if (unlikely(!array)) + return ret; - rcu_read_lock_trace(); migrate_disable(); run_ctx.is_uprobe = true; - array = rcu_dereference_check(array_rcu, rcu_read_lock_trace_held()); - if (unlikely(!array)) - goto out; old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); item = &array->items[0]; while ((prog = READ_ONCE(item->prog))) { @@ -2137,9 +2227,7 @@ bpf_prog_run_array_uprobe(const struct bpf_prog_array __rcu *array_rcu, rcu_read_unlock(); } bpf_reset_run_ctx(old_run_ctx); -out: migrate_enable(); - rcu_read_unlock_trace(); return ret; } @@ -2204,12 +2292,39 @@ void bpf_map_free_record(struct bpf_map *map); struct btf_record *btf_record_dup(const struct btf_record *rec); bool btf_record_equal(const struct btf_record *rec_a, const struct btf_record *rec_b); void bpf_obj_free_timer(const struct btf_record *rec, void *obj); +void bpf_obj_free_workqueue(const struct btf_record *rec, void *obj); void bpf_obj_free_fields(const struct btf_record *rec, void *obj); void __bpf_obj_drop_impl(void *p, const struct btf_record *rec, bool percpu); struct bpf_map *bpf_map_get(u32 ufd); struct bpf_map *bpf_map_get_with_uref(u32 ufd); -struct bpf_map *__bpf_map_get(struct fd f); + +/* + * The __bpf_map_get() and __btf_get_by_fd() functions parse a file + * descriptor and return a corresponding map or btf object. + * Their names are double underscored to emphasize the fact that they + * do not increase refcnt. To also increase refcnt use corresponding + * bpf_map_get() and btf_get_by_fd() functions. + */ + +static inline struct bpf_map *__bpf_map_get(struct fd f) +{ + if (fd_empty(f)) + return ERR_PTR(-EBADF); + if (unlikely(fd_file(f)->f_op != &bpf_map_fops)) + return ERR_PTR(-EINVAL); + return fd_file(f)->private_data; +} + +static inline struct btf *__btf_get_by_fd(struct fd f) +{ + if (fd_empty(f)) + return ERR_PTR(-EBADF); + if (unlikely(fd_file(f)->f_op != &btf_fops)) + return ERR_PTR(-EINVAL); + return fd_file(f)->private_data; +} + void bpf_map_inc(struct bpf_map *map); void bpf_map_inc_with_uref(struct bpf_map *map); struct bpf_map *__bpf_map_inc_not_zero(struct bpf_map *map, bool uref); @@ -2235,7 +2350,7 @@ struct bpf_prog *bpf_prog_get_curr_or_next(u32 *id); int bpf_map_alloc_pages(const struct bpf_map *map, gfp_t gfp, int nid, unsigned long nr_pages, struct page **page_array); -#ifdef CONFIG_MEMCG_KMEM +#ifdef CONFIG_MEMCG void *bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags, int node); void *bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags); @@ -2244,31 +2359,18 @@ void *bpf_map_kvcalloc(struct bpf_map *map, size_t n, size_t size, void __percpu *bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, size_t align, gfp_t flags); #else -static inline void * -bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags, - int node) -{ - return kmalloc_node(size, flags, node); -} - -static inline void * -bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags) -{ - return kzalloc(size, flags); -} - -static inline void * -bpf_map_kvcalloc(struct bpf_map *map, size_t n, size_t size, gfp_t flags) -{ - return kvcalloc(n, size, flags); -} - -static inline void __percpu * -bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, size_t align, - gfp_t flags) -{ - return __alloc_percpu_gfp(size, align, flags); -} +/* + * These specialized allocators have to be macros for their allocations to be + * accounted separately (to have separate alloc_tag). + */ +#define bpf_map_kmalloc_node(_map, _size, _flags, _node) \ + kmalloc_node(_size, _flags, _node) +#define bpf_map_kzalloc(_map, _size, _flags) \ + kzalloc(_size, _flags) +#define bpf_map_kvcalloc(_map, _n, _size, _flags) \ + kvcalloc(_n, _size, _flags) +#define bpf_map_alloc_percpu(_map, _size, _align, _flags) \ + __alloc_percpu_gfp(_size, _align, _flags) #endif static inline int @@ -2329,10 +2431,14 @@ int bpf_prog_new_fd(struct bpf_prog *prog); void bpf_link_init(struct bpf_link *link, enum bpf_link_type type, const struct bpf_link_ops *ops, struct bpf_prog *prog); +void bpf_link_init_sleepable(struct bpf_link *link, enum bpf_link_type type, + const struct bpf_link_ops *ops, struct bpf_prog *prog, + bool sleepable); int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer); int bpf_link_settle(struct bpf_link_primer *primer); void bpf_link_cleanup(struct bpf_link_primer *primer); void bpf_link_inc(struct bpf_link *link); +struct bpf_link *bpf_link_inc_not_zero(struct bpf_link *link); void bpf_link_put(struct bpf_link *link); int bpf_link_new_fd(struct bpf_link *link); struct bpf_link *bpf_link_get_from_fd(u32 ufd); @@ -2492,7 +2598,7 @@ struct sk_buff; struct bpf_dtab_netdev; struct bpf_cpu_map_entry; -void __dev_flush(void); +void __dev_flush(struct list_head *flush_list); int dev_xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx); int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf, @@ -2500,12 +2606,12 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf, int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_map *map, bool exclude_ingress); int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, - struct bpf_prog *xdp_prog); + const struct bpf_prog *xdp_prog); int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, - struct bpf_prog *xdp_prog, struct bpf_map *map, - bool exclude_ingress); + const struct bpf_prog *xdp_prog, + struct bpf_map *map, bool exclude_ingress); -void __cpu_map_flush(void); +void __cpu_map_flush(struct list_head *flush_list); int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf, struct net_device *dev_rx); int cpu_map_generic_redirect(struct bpf_cpu_map_entry *rcpu, @@ -2642,8 +2748,6 @@ void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data, void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr); void bpf_dynptr_set_rdonly(struct bpf_dynptr_kern *ptr); -bool dev_check_flush(void); -bool cpu_map_check_flush(void); #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) { @@ -2685,6 +2789,12 @@ static inline void bpf_link_init(struct bpf_link *link, enum bpf_link_type type, { } +static inline void bpf_link_init_sleepable(struct bpf_link *link, enum bpf_link_type type, + const struct bpf_link_ops *ops, struct bpf_prog *prog, + bool sleepable) +{ +} + static inline int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer) { @@ -2704,6 +2814,11 @@ static inline void bpf_link_inc(struct bpf_link *link) { } +static inline struct bpf_link *bpf_link_inc_not_zero(struct bpf_link *link) +{ + return NULL; +} + static inline void bpf_link_put(struct bpf_link *link) { } @@ -2731,7 +2846,7 @@ static inline struct bpf_token *bpf_token_get_from_fd(u32 ufd) return ERR_PTR(-EOPNOTSUPP); } -static inline void __dev_flush(void) +static inline void __dev_flush(struct list_head *flush_list) { } @@ -2764,20 +2879,20 @@ struct sk_buff; static inline int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, - struct bpf_prog *xdp_prog) + const struct bpf_prog *xdp_prog) { return 0; } static inline int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, - struct bpf_prog *xdp_prog, struct bpf_map *map, - bool exclude_ingress) + const struct bpf_prog *xdp_prog, + struct bpf_map *map, bool exclude_ingress) { return 0; } -static inline void __cpu_map_flush(void) +static inline void __cpu_map_flush(struct list_head *flush_list) { } @@ -2926,8 +3041,7 @@ bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr) return ret; } -void __bpf_free_used_btfs(struct bpf_prog_aux *aux, - struct btf_mod_pair *used_btfs, u32 len); +void __bpf_free_used_btfs(struct btf_mod_pair *used_btfs, u32 len); static inline struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type) @@ -3005,6 +3119,7 @@ int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype); int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags); int sock_map_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr); +int sock_map_link_create(const union bpf_attr *attr, struct bpf_prog *prog); void sock_map_unhash(struct sock *sk); void sock_map_destroy(struct sock *sk); @@ -3103,6 +3218,11 @@ static inline int sock_map_bpf_prog_query(const union bpf_attr *attr, { return -EINVAL; } + +static inline int sock_map_link_create(const union bpf_attr *attr, struct bpf_prog *prog) +{ + return -EOPNOTSUPP; +} #endif /* CONFIG_BPF_SYSCALL */ #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ @@ -3170,7 +3290,9 @@ extern const struct bpf_func_proto bpf_get_current_uid_gid_proto; extern const struct bpf_func_proto bpf_get_current_comm_proto; extern const struct bpf_func_proto bpf_get_stackid_proto; extern const struct bpf_func_proto bpf_get_stack_proto; +extern const struct bpf_func_proto bpf_get_stack_sleepable_proto; extern const struct bpf_func_proto bpf_get_task_stack_proto; +extern const struct bpf_func_proto bpf_get_task_stack_sleepable_proto; extern const struct bpf_func_proto bpf_get_stackid_proto_pe; extern const struct bpf_func_proto bpf_get_stack_proto_pe; extern const struct bpf_func_proto bpf_sock_map_update_proto; @@ -3178,6 +3300,7 @@ extern const struct bpf_func_proto bpf_sock_hash_update_proto; extern const struct bpf_func_proto bpf_get_current_cgroup_id_proto; extern const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto; extern const struct bpf_func_proto bpf_get_cgroup_classid_curr_proto; +extern const struct bpf_func_proto bpf_current_task_under_cgroup_proto; extern const struct bpf_func_proto bpf_msg_redirect_hash_proto; extern const struct bpf_func_proto bpf_msg_redirect_map_proto; extern const struct bpf_func_proto bpf_sk_redirect_hash_proto; @@ -3252,8 +3375,8 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size); -int bpf_dynptr_from_skb_rdonly(struct sk_buff *skb, u64 flags, - struct bpf_dynptr_kern *ptr); +int bpf_dynptr_from_skb_rdonly(struct __sk_buff *skb, u64 flags, + struct bpf_dynptr *ptr); #else static inline bool bpf_sock_common_is_valid_access(int off, int size, enum bpf_access_type type, @@ -3275,8 +3398,8 @@ static inline u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, { return 0; } -static inline int bpf_dynptr_from_skb_rdonly(struct sk_buff *skb, u64 flags, - struct bpf_dynptr_kern *ptr) +static inline int bpf_dynptr_from_skb_rdonly(struct __sk_buff *skb, u64 flags, + struct bpf_dynptr *ptr) { return -EOPNOTSUPP; } diff --git a/include/linux/bpf_crypto.h b/include/linux/bpf_crypto.h new file mode 100644 index 000000000000..a41e71d4e2d9 --- /dev/null +++ b/include/linux/bpf_crypto.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ +#ifndef _BPF_CRYPTO_H +#define _BPF_CRYPTO_H + +struct bpf_crypto_type { + void *(*alloc_tfm)(const char *algo); + void (*free_tfm)(void *tfm); + int (*has_algo)(const char *algo); + int (*setkey)(void *tfm, const u8 *key, unsigned int keylen); + int (*setauthsize)(void *tfm, unsigned int authsize); + int (*encrypt)(void *tfm, const u8 *src, u8 *dst, unsigned int len, u8 *iv); + int (*decrypt)(void *tfm, const u8 *src, u8 *dst, unsigned int len, u8 *iv); + unsigned int (*ivsize)(void *tfm); + unsigned int (*statesize)(void *tfm); + u32 (*get_flags)(void *tfm); + struct module *owner; + char name[14]; +}; + +int bpf_crypto_register_type(const struct bpf_crypto_type *type); +int bpf_crypto_unregister_type(const struct bpf_crypto_type *type); + +#endif /* _BPF_CRYPTO_H */ diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h index dcddb0aef7d8..ab7244d8108f 100644 --- a/include/linux/bpf_local_storage.h +++ b/include/linux/bpf_local_storage.h @@ -77,7 +77,13 @@ struct bpf_local_storage_elem { struct hlist_node map_node; /* Linked to bpf_local_storage_map */ struct hlist_node snode; /* Linked to bpf_local_storage */ struct bpf_local_storage __rcu *local_storage; - struct rcu_head rcu; + union { + struct rcu_head rcu; + struct hlist_node free_node; /* used to postpone + * bpf_selem_free + * after raw_spin_unlock + */ + }; /* 8 bytes hole */ /* The data is stored in another cacheline to minimize * the number of cachelines access during a cache hit. @@ -181,7 +187,7 @@ void bpf_selem_link_map(struct bpf_local_storage_map *smap, struct bpf_local_storage_elem * bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, void *value, - bool charge_mem, gfp_t gfp_flags); + bool charge_mem, bool swap_uptrs, gfp_t gfp_flags); void bpf_selem_free(struct bpf_local_storage_elem *selem, struct bpf_local_storage_map *smap, @@ -195,7 +201,7 @@ bpf_local_storage_alloc(void *owner, struct bpf_local_storage_data * bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, - void *value, u64 map_flags, gfp_t gfp_flags); + void *value, u64 map_flags, bool swap_uptrs, gfp_t gfp_flags); u64 bpf_local_storage_map_mem_usage(const struct bpf_map *map); diff --git a/include/linux/bpf_lsm.h b/include/linux/bpf_lsm.h index 1de7ece5d36d..aefcd6564251 100644 --- a/include/linux/bpf_lsm.h +++ b/include/linux/bpf_lsm.h @@ -9,6 +9,7 @@ #include <linux/sched.h> #include <linux/bpf.h> +#include <linux/bpf_verifier.h> #include <linux/lsm_hooks.h> #ifdef CONFIG_BPF_LSM @@ -45,6 +46,8 @@ void bpf_inode_storage_free(struct inode *inode); void bpf_lsm_find_cgroup_shim(const struct bpf_prog *prog, bpf_func_t *bpf_func); +int bpf_lsm_get_retval_range(const struct bpf_prog *prog, + struct bpf_retval_range *range); #else /* !CONFIG_BPF_LSM */ static inline bool bpf_lsm_is_sleepable_hook(u32 btf_id) @@ -78,6 +81,11 @@ static inline void bpf_lsm_find_cgroup_shim(const struct bpf_prog *prog, { } +static inline int bpf_lsm_get_retval_range(const struct bpf_prog *prog, + struct bpf_retval_range *range) +{ + return -EOPNOTSUPP; +} #endif /* CONFIG_BPF_LSM */ #endif /* _LINUX_BPF_LSM_H */ diff --git a/include/linux/bpf_mem_alloc.h b/include/linux/bpf_mem_alloc.h index aaf004d94322..e45162ef59bb 100644 --- a/include/linux/bpf_mem_alloc.h +++ b/include/linux/bpf_mem_alloc.h @@ -33,6 +33,9 @@ int bpf_mem_alloc_percpu_init(struct bpf_mem_alloc *ma, struct obj_cgroup *objcg int bpf_mem_alloc_percpu_unit_init(struct bpf_mem_alloc *ma, int size); void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma); +/* Check the allocation size for kmalloc equivalent allocator */ +int bpf_mem_alloc_check_size(bool percpu, size_t size); + /* kmalloc/kfree equivalent: */ void *bpf_mem_alloc(struct bpf_mem_alloc *ma, size_t size); void bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr); diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 9f2a6b83b49e..fa78f49d4a9a 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -146,6 +146,7 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_XDP, xdp) BPF_LINK_TYPE(BPF_LINK_TYPE_NETFILTER, netfilter) BPF_LINK_TYPE(BPF_LINK_TYPE_TCX, tcx) BPF_LINK_TYPE(BPF_LINK_TYPE_NETKIT, netkit) +BPF_LINK_TYPE(BPF_LINK_TYPE_SOCKMAP, sockmap) #endif #ifdef CONFIG_PERF_EVENTS BPF_LINK_TYPE(BPF_LINK_TYPE_PERF_EVENT, perf) diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 7cb1b75eee38..32c23f2a3086 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -23,6 +23,8 @@ * (in the "-8,-16,...,-512" form) */ #define TMP_STR_BUF_LEN 320 +/* Patch buffer size */ +#define INSN_BUF_SIZE 32 /* Liveness marks, used for registers and spilled-regs (in stack slots). * Read marks propagate upwards until they find a write mark; they record that @@ -46,22 +48,6 @@ enum bpf_reg_liveness { REG_LIVE_DONE = 0x8, /* liveness won't be updating this register anymore */ }; -/* For every reg representing a map value or allocated object pointer, - * we consider the tuple of (ptr, id) for them to be unique in verifier - * context and conside them to not alias each other for the purposes of - * tracking lock state. - */ -struct bpf_active_lock { - /* This can either be reg->map_ptr or reg->btf. If ptr is NULL, - * there's no active lock held, and other fields have no - * meaning. If non-NULL, it indicates that a lock is held and - * id member has the reg->id of the register which can be >= 0. - */ - void *ptr; - /* This will be reg->id */ - u32 id; -}; - #define ITER_PREFIX "bpf_iter_" enum bpf_iter_state { @@ -73,7 +59,10 @@ enum bpf_iter_state { struct bpf_reg_state { /* Ordering of fields matters. See states_equal() */ enum bpf_reg_type type; - /* Fixed part of pointer offset, pointer types only */ + /* + * Fixed part of pointer offset, pointer types only. + * Or constant delta between "linked" scalars with the same ID. + */ s32 off; union { /* valid when type == PTR_TO_PACKET */ @@ -167,6 +156,13 @@ struct bpf_reg_state { * Similarly to dynptrs, we use ID to track "belonging" of a reference * to a specific instance of bpf_iter. */ + /* + * Upper bit of ID is used to remember relationship between "linked" + * registers. Example: + * r1 = r2; both will have r1->id == r2->id == N + * r1 += 10; r1->id == N | BPF_ADD_CONST and r1->off == 10 + */ +#define BPF_ADD_CONST (1U << 31) u32 id; /* PTR_TO_SOCKET and PTR_TO_TCP_SOCK could be a ptr returned * from a pointer-cast helper, bpf_sk_fullsock() and @@ -237,6 +233,7 @@ enum bpf_stack_slot_type { */ STACK_DYNPTR, STACK_ITER, + STACK_IRQ_FLAG, }; #define BPF_REG_SIZE 8 /* size of eBPF register in bytes */ @@ -254,6 +251,14 @@ struct bpf_stack_state { }; struct bpf_reference_state { + /* Each reference object has a type. Ensure REF_TYPE_PTR is zero to + * default to pointer reference on zero initialization of a state. + */ + enum ref_state_type { + REF_TYPE_PTR = 1, + REF_TYPE_IRQ = 2, + REF_TYPE_LOCK = 3, + } type; /* Track each reference created with a unique id, even if the same * instruction creates the reference multiple times (eg, via CALL). */ @@ -262,17 +267,10 @@ struct bpf_reference_state { * is used purely to inform the user of a reference leak. */ int insn_idx; - /* There can be a case like: - * main (frame 0) - * cb (frame 1) - * func (frame 3) - * cb (frame 4) - * Hence for frame 4, if callback_ref just stored boolean, it would be - * impossible to distinguish nested callback refs. Hence store the - * frameno and compare that to callback_ref in check_reference_leak when - * exiting a callback function. + /* Use to keep track of the source object of a lock, to ensure + * it matches on unlock. */ - int callback_ref; + void *ptr; }; struct bpf_retval_range { @@ -319,8 +317,6 @@ struct bpf_func_state { u32 callback_depth; /* The following fields should be last. See copy_func_state() */ - int acquired_refs; - struct bpf_reference_state *refs; /* The state of the stack. Each element of the array describes BPF_REG_SIZE * (i.e. 8) bytes worth of stack memory. * stack[0] represents bytes [*(r10-8)..*(r10-1)] @@ -337,7 +333,7 @@ struct bpf_func_state { #define MAX_CALL_FRAMES 8 -/* instruction history flags, used in bpf_jmp_history_entry.flags field */ +/* instruction history flags, used in bpf_insn_hist_entry.flags field */ enum { /* instruction references stack slot through PTR_TO_STACK register; * we also store stack's frame number in lower 3 bits (MAX_CALL_FRAMES is 8) @@ -355,12 +351,16 @@ enum { static_assert(INSN_F_FRAMENO_MASK + 1 >= MAX_CALL_FRAMES); static_assert(INSN_F_SPI_MASK + 1 >= MAX_BPF_STACK / 8); -struct bpf_jmp_history_entry { +struct bpf_insn_hist_entry { u32 idx; /* insn idx can't be bigger than 1 million */ u32 prev_idx : 22; /* special flags, e.g., whether insn is doing register stack spill/load */ u32 flags : 10; + /* additional registers that need precision tracking when this + * jump is backtracked, vector of six 10-bit records + */ + u64 linked_regs; }; /* Maximum number of register states that can exist at once */ @@ -369,6 +369,8 @@ struct bpf_verifier_state { /* call stack tracking */ struct bpf_func_state *frame[MAX_CALL_FRAMES]; struct bpf_verifier_state *parent; + /* Acquired reference states */ + struct bpf_reference_state *refs; /* * 'branches' field is the number of branches left to explore: * 0 - all possible paths from this state reached bpf_exit or @@ -418,14 +420,19 @@ struct bpf_verifier_state { u32 insn_idx; u32 curframe; - struct bpf_active_lock active_lock; - bool speculative; + u32 acquired_refs; + u32 active_locks; + u32 active_preempt_locks; + u32 active_irq_id; bool active_rcu_lock; + + bool speculative; /* If this state was ever pointed-to by other state's loop_entry field * this flag would be set to true. Used to avoid freeing such states * while they are still in use. */ bool used_as_loop_entry; + bool in_sleepable; /* first and last insn idx of this verifier state */ u32 first_insn_idx; @@ -440,13 +447,14 @@ struct bpf_verifier_state { * See get_loop_entry() for more information. */ struct bpf_verifier_state *loop_entry; - /* jmp history recorded from first to last. - * backtracking is using it to go from last to first. - * For most states jmp_history_cnt is [0-3]. + /* Sub-range of env->insn_hist[] corresponding to this state's + * instruction history. + * Backtracking is using it to go from last to first. + * For most states instruction history is short, 0-3 instructions. * For loops can go up to ~40. */ - struct bpf_jmp_history_entry *jmp_history; - u32 jmp_history_cnt; + u32 insn_hist_start; + u32 insn_hist_end; u32 dfs_depth; u32 callback_unroll_depth; u32 may_goto_depth; @@ -502,6 +510,13 @@ struct bpf_loop_inline_state { u32 callback_subprogno; /* valid when fit_for_inline is true */ }; +/* pointer and state for maps */ +struct bpf_map_ptr_state { + struct bpf_map *map_ptr; + bool poison; + bool unpriv; +}; + /* Possible states for alu_state member. */ #define BPF_ALU_SANITIZE_SRC (1U << 0) #define BPF_ALU_SANITIZE_DST (1U << 1) @@ -514,7 +529,7 @@ struct bpf_loop_inline_state { struct bpf_insn_aux_data { union { enum bpf_reg_type ptr_type; /* pointer type for load/store insns */ - unsigned long map_ptr_state; /* pointer/poison value for maps */ + struct bpf_map_ptr_state map_ptr_state; s32 call_imm; /* saved imm field of call insn */ u32 alu_limit; /* limit for add/sub register with pointer */ struct { @@ -553,6 +568,14 @@ struct bpf_insn_aux_data { bool is_iter_next; /* bpf_iter_<type>_next() kfunc call */ bool call_with_percpu_alloc_ptr; /* {this,per}_cpu_ptr() with prog percpu alloc */ u8 alu_state; /* used in combination with alu_limit */ + /* true if STX or LDX instruction is a part of a spill/fill + * pattern for a bpf_fastcall call. + */ + u8 fastcall_pattern:1; + /* for CALL instructions, a number of spill/fill pairs in the + * bpf_fastcall pattern. + */ + u8 fastcall_spills_num:3; /* below fields are initialized once */ unsigned int orig_idx; /* original instruction index */ @@ -616,12 +639,22 @@ struct bpf_subprog_arg_info { }; }; +enum priv_stack_mode { + PRIV_STACK_UNKNOWN, + NO_PRIV_STACK, + PRIV_STACK_ADAPTIVE, +}; + struct bpf_subprog_info { /* 'start' has to be the first field otherwise find_subprog() won't work */ u32 start; /* insn idx of function entry point */ u32 linfo_idx; /* The idx to the main_prog->aux->linfo */ u16 stack_depth; /* max. stack depth used by this function */ u16 stack_extra; + /* offsets in range [stack_depth .. fastcall_stack_off) + * are used for bpf_fastcall spills and fills. + */ + s16 fastcall_stack_off; bool has_tail_call: 1; bool tail_call_reachable: 1; bool has_ld_abs: 1; @@ -629,7 +662,11 @@ struct bpf_subprog_info { bool is_async_cb: 1; bool is_exception_cb: 1; bool args_cached: 1; + /* true if bpf_fastcall stack region is used by functions that can't be inlined */ + bool keep_fastcall_stack: 1; + bool changes_pkt_data: 1; + enum priv_stack_mode priv_stack_mode; u8 arg_cnt; struct bpf_subprog_arg_info args[MAX_BPF_FUNC_REG_ARGS]; }; @@ -708,7 +745,9 @@ struct bpf_verifier_env { int cur_stack; } cfg; struct backtrack_state bt; - struct bpf_jmp_history_entry *cur_hist_ent; + struct bpf_insn_hist_entry *insn_hist; + struct bpf_insn_hist_entry *cur_hist_ent; + u32 insn_hist_cap; u32 pass_cnt; /* number of times do_check() was called */ u32 subprog_cnt; /* number of instructions analyzed by the verifier */ @@ -737,10 +776,14 @@ struct bpf_verifier_env { /* Same as scratched_regs but for stack slots */ u64 scratched_stack_slots; u64 prev_log_pos, prev_insn_print_pos; + /* buffer used to temporary hold constants as scalar registers */ + struct bpf_reg_state fake_reg[2]; /* buffer used to generate temporary string representations, * e.g., in reg_type_str() to generate reg_type string */ char tmp_str_buf[TMP_STR_BUF_LEN]; + struct bpf_insn insn_buf[INSN_BUF_SIZE]; + struct bpf_insn epilogue_buf[INSN_BUF_SIZE]; }; static inline struct bpf_func_info_aux *subprog_aux(struct bpf_verifier_env *env, int subprog) @@ -835,8 +878,8 @@ static inline u32 type_flag(u32 type) /* only use after check_attach_btf_id() */ static inline enum bpf_prog_type resolve_prog_type(const struct bpf_prog *prog) { - return prog->type == BPF_PROG_TYPE_EXT ? - prog->aux->dst_prog->type : prog->type; + return (prog->type == BPF_PROG_TYPE_EXT && prog->aux->saved_dst_prog_type) ? + prog->aux->saved_dst_prog_type : prog->type; } static inline bool bpf_prog_check_recur(const struct bpf_prog *prog) @@ -845,6 +888,7 @@ static inline bool bpf_prog_check_recur(const struct bpf_prog *prog) case BPF_PROG_TYPE_TRACING: return prog->expected_attach_type != BPF_TRACE_ITER; case BPF_PROG_TYPE_STRUCT_OPS: + return prog->aux->jits_use_priv_stack; case BPF_PROG_TYPE_LSM: return false; default: @@ -884,6 +928,11 @@ static inline bool type_is_sk_pointer(enum bpf_reg_type type) type == PTR_TO_XDP_SOCK; } +static inline bool type_may_be_null(u32 type) +{ + return type & PTR_MAYBE_NULL; +} + static inline void mark_reg_scratched(struct bpf_verifier_env *env, u32 regno) { env->scratched_regs |= 1U << regno; @@ -936,8 +985,9 @@ const char *dynptr_type_str(enum bpf_dynptr_type type); const char *iter_type_str(const struct btf *btf, u32 btf_id); const char *iter_state_str(enum bpf_iter_state state); -void print_verifier_state(struct bpf_verifier_env *env, - const struct bpf_func_state *state, bool print_all); -void print_insn_state(struct bpf_verifier_env *env, const struct bpf_func_state *state); +void print_verifier_state(struct bpf_verifier_env *env, const struct bpf_verifier_state *vstate, + u32 frameno, bool print_all); +void print_insn_state(struct bpf_verifier_env *env, const struct bpf_verifier_state *vstate, + u32 frameno); #endif /* _LINUX_BPF_VERIFIER_H */ diff --git a/include/linux/bpfptr.h b/include/linux/bpfptr.h index 79b2f78eec1a..1af241525a17 100644 --- a/include/linux/bpfptr.h +++ b/include/linux/bpfptr.h @@ -65,9 +65,9 @@ static inline int copy_to_bpfptr_offset(bpfptr_t dst, size_t offset, return copy_to_sockptr_offset((sockptr_t) dst, offset, src, size); } -static inline void *kvmemdup_bpfptr(bpfptr_t src, size_t len) +static inline void *kvmemdup_bpfptr_noprof(bpfptr_t src, size_t len) { - void *p = kvmalloc(len, GFP_USER | __GFP_NOWARN); + void *p = kvmalloc_noprof(len, GFP_USER | __GFP_NOWARN); if (!p) return ERR_PTR(-ENOMEM); @@ -77,6 +77,7 @@ static inline void *kvmemdup_bpfptr(bpfptr_t src, size_t len) } return p; } +#define kvmemdup_bpfptr(...) alloc_hooks(kvmemdup_bpfptr_noprof(__VA_ARGS__)) static inline long strncpy_from_bpfptr(char *dst, bpfptr_t src, size_t count) { diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 1394ba302367..028b3e00378e 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -271,12 +271,100 @@ #define BCM5482_SSD_SGMII_SLAVE_EN 0x0002 /* Slave mode enable */ #define BCM5482_SSD_SGMII_SLAVE_AD 0x0001 /* Slave auto-detection */ +/* BroadR-Reach LRE Registers. */ +#define MII_BCM54XX_LRECR 0x00 /* LRE Control Register */ +#define MII_BCM54XX_LRESR 0x01 /* LRE Status Register */ +#define MII_BCM54XX_LREPHYSID1 0x02 /* LRE PHYS ID 1 */ +#define MII_BCM54XX_LREPHYSID2 0x03 /* LRE PHYS ID 2 */ +#define MII_BCM54XX_LREANAA 0x04 /* LDS Auto-Negotiation Advertised Ability */ +#define MII_BCM54XX_LREANAC 0x05 /* LDS Auto-Negotiation Advertised Control */ +#define MII_BCM54XX_LREANPT 0x06 /* LDS Ability Next Page Transmit */ +#define MII_BCM54XX_LRELPA 0x07 /* LDS Link Partner Ability */ +#define MII_BCM54XX_LRELPNPM 0x08 /* LDS Link Partner Next Page Message */ +#define MII_BCM54XX_LRELPNPC 0x09 /* LDS Link Partner Next Page Control */ +#define MII_BCM54XX_LRELDSE 0x0a /* LDS Expansion Register */ +#define MII_BCM54XX_LREES 0x0f /* LRE Extended Status */ + +/* LRE control register. */ +#define LRECR_RESET 0x8000 /* Reset to default state */ +#define LRECR_LOOPBACK 0x4000 /* Internal Loopback */ +#define LRECR_LDSRES 0x2000 /* Restart LDS Process */ +#define LRECR_LDSEN 0x1000 /* LDS Enable */ +#define LRECR_PDOWN 0x0800 /* Enable low power state */ +#define LRECR_ISOLATE 0x0400 /* Isolate data paths from MII */ +#define LRECR_SPEED100 0x0200 /* Select 100 Mbps */ +#define LRECR_SPEED10 0x0000 /* Select 10 Mbps */ +#define LRECR_4PAIRS 0x0020 /* Select 4 Pairs */ +#define LRECR_2PAIRS 0x0010 /* Select 2 Pairs */ +#define LRECR_1PAIR 0x0000 /* Select 1 Pair */ +#define LRECR_MASTER 0x0008 /* Force Master when LDS disabled */ +#define LRECR_SLAVE 0x0000 /* Force Slave when LDS disabled */ + +/* LRE status register. */ +#define LRESR_100_1PAIR 0x2000 /* Can do 100Mbps 1 Pair */ +#define LRESR_100_4PAIR 0x1000 /* Can do 100Mbps 4 Pairs */ +#define LRESR_100_2PAIR 0x0800 /* Can do 100Mbps 2 Pairs */ +#define LRESR_10_2PAIR 0x0400 /* Can do 10Mbps 2 Pairs */ +#define LRESR_10_1PAIR 0x0200 /* Can do 10Mbps 1 Pair */ +#define LRESR_ESTATEN 0x0100 /* Extended Status in R15 */ +#define LRESR_RESV 0x0080 /* Unused... */ +#define LRESR_MFPS 0x0040 /* Can suppress Management Frames Preamble */ +#define LRESR_LDSCOMPLETE 0x0020 /* LDS Auto-negotiation complete */ +#define LRESR_8023 0x0010 /* Has IEEE 802.3 Support */ +#define LRESR_LDSABILITY 0x0008 /* LDS auto-negotiation capable */ +#define LRESR_LSTATUS 0x0004 /* Link status */ +#define LRESR_JCD 0x0002 /* Jabber detected */ +#define LRESR_ERCAP 0x0001 /* Ext-reg capability */ + +/* LDS Auto-Negotiation Advertised Ability. */ +#define LREANAA_PAUSE_ASYM 0x8000 /* Can pause asymmetrically */ +#define LREANAA_PAUSE 0x4000 /* Can pause */ +#define LREANAA_100_1PAIR 0x0020 /* Can do 100Mbps 1 Pair */ +#define LREANAA_100_4PAIR 0x0010 /* Can do 100Mbps 4 Pair */ +#define LREANAA_100_2PAIR 0x0008 /* Can do 100Mbps 2 Pair */ +#define LREANAA_10_2PAIR 0x0004 /* Can do 10Mbps 2 Pair */ +#define LREANAA_10_1PAIR 0x0002 /* Can do 10Mbps 1 Pair */ + +#define LRE_ADVERTISE_FULL (LREANAA_100_1PAIR | LREANAA_100_4PAIR | \ + LREANAA_100_2PAIR | LREANAA_10_2PAIR | \ + LREANAA_10_1PAIR) + +#define LRE_ADVERTISE_ALL LRE_ADVERTISE_FULL + +/* LDS Link Partner Ability. */ +#define LRELPA_PAUSE_ASYM 0x8000 /* Supports asymmetric pause */ +#define LRELPA_PAUSE 0x4000 /* Supports pause capability */ +#define LRELPA_100_1PAIR 0x0020 /* 100Mbps 1 Pair capable */ +#define LRELPA_100_4PAIR 0x0010 /* 100Mbps 4 Pair capable */ +#define LRELPA_100_2PAIR 0x0008 /* 100Mbps 2 Pair capable */ +#define LRELPA_10_2PAIR 0x0004 /* 10Mbps 2 Pair capable */ +#define LRELPA_10_1PAIR 0x0002 /* 10Mbps 1 Pair capable */ + +/* LDS Expansion register. */ +#define LDSE_DOWNGRADE 0x8000 /* Can do LDS Speed Downgrade */ +#define LDSE_MASTER 0x4000 /* Master / Slave */ +#define LDSE_PAIRS_MASK 0x3000 /* Pair Count Mask */ +#define LDSE_PAIRS_SHIFT 12 +#define LDSE_4PAIRS (2 << LDSE_PAIRS_SHIFT) /* 4 Pairs Connection */ +#define LDSE_2PAIRS (1 << LDSE_PAIRS_SHIFT) /* 2 Pairs Connection */ +#define LDSE_1PAIR (0 << LDSE_PAIRS_SHIFT) /* 1 Pair Connection */ +#define LDSE_CABLEN_MASK 0x0FFF /* Cable Length Mask */ + /* BCM54810 Registers */ #define BCM54810_EXP_BROADREACH_LRE_MISC_CTL (MII_BCM54XX_EXP_SEL_ER + 0x90) #define BCM54810_EXP_BROADREACH_LRE_MISC_CTL_EN (1 << 0) #define BCM54810_SHD_CLK_CTL 0x3 #define BCM54810_SHD_CLK_CTL_GTXCLK_EN (1 << 9) +/* BCM54811 Registers */ +#define BCM54811_EXP_BROADREACH_LRE_OVERLAY_CTL (MII_BCM54XX_EXP_SEL_ER + 0x9A) +/* Access Control Override Enable */ +#define BCM54811_EXP_BROADREACH_LRE_OVERLAY_CTL_EN BIT(15) +/* Access Control Override Value */ +#define BCM54811_EXP_BROADREACH_LRE_OVERLAY_CTL_OVERRIDE_VAL BIT(14) +/* Access Control Value */ +#define BCM54811_EXP_BROADREACH_LRE_OVERLAY_CTL_VAL BIT(13) + /* BCM54612E Registers */ #define BCM54612E_EXP_SPARE0 (MII_BCM54XX_EXP_SEL_ETC + 0x34) #define BCM54612E_LED4_CLK125OUT_EN (1 << 1) diff --git a/include/linux/bsg-lib.h b/include/linux/bsg-lib.h index 9e97ced2896d..14fa93268630 100644 --- a/include/linux/bsg-lib.h +++ b/include/linux/bsg-lib.h @@ -65,7 +65,8 @@ struct bsg_job { void bsg_job_done(struct bsg_job *job, int result, unsigned int reply_payload_rcv_len); struct request_queue *bsg_setup_queue(struct device *dev, const char *name, - bsg_job_fn *job_fn, bsg_timeout_fn *timeout, int dd_job_size); + struct queue_limits *lim, bsg_job_fn *job_fn, + bsg_timeout_fn *timeout, int dd_job_size); void bsg_remove_queue(struct request_queue *q); void bsg_job_put(struct bsg_job *job); int __must_check bsg_job_get(struct bsg_job *job); diff --git a/include/linux/btf.h b/include/linux/btf.h index f9e56fd12a9f..2a08a2b55592 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -75,6 +75,7 @@ #define KF_ITER_NEXT (1 << 9) /* kfunc implements BPF iter next method */ #define KF_ITER_DESTROY (1 << 10) /* kfunc implements BPF iter destructor */ #define KF_RCU_PROTECTED (1 << 11) /* kfunc should be protected by rcu cs when they are invoked */ +#define KF_FASTCALL (1 << 12) /* kfunc supports bpf_fastcall protocol */ /* * Tag marking a kernel function as a kfunc. This is meant to minimize the @@ -82,7 +83,7 @@ * as to avoid issues such as the compiler inlining or eliding either a static * kfunc, or a global kfunc in an LTO build. */ -#define __bpf_kfunc __used noinline +#define __bpf_kfunc __used __retain noinline #define __bpf_kfunc_start_defs() \ __diag_push(); \ @@ -140,6 +141,7 @@ extern const struct file_operations btf_fops; const char *btf_get_name(const struct btf *btf); void btf_get(struct btf *btf); void btf_put(struct btf *btf); +const struct btf_header *btf_header(const struct btf *btf); int btf_new_fd(const union bpf_attr *attr, bpfptr_t uattr, u32 uattr_sz); struct btf *btf_get_by_fd(int fd); int btf_get_info_by_fd(const struct btf *btf, @@ -212,8 +214,10 @@ int btf_get_fd_by_id(u32 id); u32 btf_obj_id(const struct btf *btf); bool btf_is_kernel(const struct btf *btf); bool btf_is_module(const struct btf *btf); +bool btf_is_vmlinux(const struct btf *btf); struct module *btf_try_get_module(const struct btf *btf); u32 btf_nr_types(const struct btf *btf); +struct btf *btf_base_btf(const struct btf *btf); bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s, const struct btf_member *m, u32 expected_offset, u32 expected_size); @@ -339,11 +343,21 @@ static inline u8 btf_int_offset(const struct btf_type *t) return BTF_INT_OFFSET(*(u32 *)(t + 1)); } +static inline __u8 btf_int_bits(const struct btf_type *t) +{ + return BTF_INT_BITS(*(__u32 *)(t + 1)); +} + static inline bool btf_type_is_scalar(const struct btf_type *t) { return btf_type_is_int(t) || btf_type_is_enum(t); } +static inline bool btf_type_is_fwd(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_FWD; +} + static inline bool btf_type_is_typedef(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_TYPEDEF; @@ -478,6 +492,11 @@ static inline struct btf_param *btf_params(const struct btf_type *t) return (struct btf_param *)(t + 1); } +static inline struct btf_decl_tag *btf_decl_tag(const struct btf_type *t) +{ + return (struct btf_decl_tag *)(t + 1); +} + static inline int btf_id_cmp_func(const void *a, const void *b) { const int *pa = a, *pb = b; @@ -515,9 +534,38 @@ static inline const struct bpf_struct_ops_desc *bpf_struct_ops_find(struct btf * } #endif +enum btf_field_iter_kind { + BTF_FIELD_ITER_IDS, + BTF_FIELD_ITER_STRS, +}; + +struct btf_field_desc { + /* once-per-type offsets */ + int t_off_cnt, t_offs[2]; + /* member struct size, or zero, if no members */ + int m_sz; + /* repeated per-member offsets */ + int m_off_cnt, m_offs[1]; +}; + +struct btf_field_iter { + struct btf_field_desc desc; + void *p; + int m_idx; + int off_idx; + int vlen; +}; + #ifdef CONFIG_BPF_SYSCALL const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id); +void btf_set_base_btf(struct btf *btf, const struct btf *base_btf); +int btf_relocate(struct btf *btf, const struct btf *base_btf, __u32 **map_ids); +int btf_field_iter_init(struct btf_field_iter *it, struct btf_type *t, + enum btf_field_iter_kind iter_kind); +__u32 *btf_field_iter_next(struct btf_field_iter *it); + const char *btf_name_by_offset(const struct btf *btf, u32 offset); +const char *btf_str_by_offset(const struct btf *btf, u32 offset); struct btf *btf_parse_vmlinux(void); struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog); u32 *btf_kfunc_id_set_contains(const struct btf *btf, u32 kfunc_btf_id, @@ -531,18 +579,52 @@ s32 btf_find_dtor_kfunc(struct btf *btf, u32 btf_id); int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_cnt, struct module *owner); struct btf_struct_meta *btf_find_struct_meta(const struct btf *btf, u32 btf_id); +bool btf_is_projection_of(const char *pname, const char *tname); bool btf_is_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, const struct btf_type *t, enum bpf_prog_type prog_type, int arg); int get_kern_ctx_btf_id(struct bpf_verifier_log *log, enum bpf_prog_type prog_type); bool btf_types_are_same(const struct btf *btf1, u32 id1, const struct btf *btf2, u32 id2); +int btf_check_iter_arg(struct btf *btf, const struct btf_type *func, int arg_idx); + +static inline bool btf_type_is_struct_ptr(struct btf *btf, const struct btf_type *t) +{ + if (!btf_type_is_ptr(t)) + return false; + + t = btf_type_skip_modifiers(btf, t->type, NULL); + + return btf_type_is_struct(t); +} #else static inline const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id) { return NULL; } + +static inline void btf_set_base_btf(struct btf *btf, const struct btf *base_btf) +{ +} + +static inline int btf_relocate(void *log, struct btf *btf, const struct btf *base_btf, + __u32 **map_ids) +{ + return -EOPNOTSUPP; +} + +static inline int btf_field_iter_init(struct btf_field_iter *it, struct btf_type *t, + enum btf_field_iter_kind iter_kind) +{ + return -EOPNOTSUPP; +} + +static inline __u32 *btf_field_iter_next(struct btf_field_iter *it) +{ + return NULL; +} + static inline const char *btf_name_by_offset(const struct btf *btf, u32 offset) { @@ -589,16 +671,9 @@ static inline bool btf_types_are_same(const struct btf *btf1, u32 id1, { return false; } -#endif - -static inline bool btf_type_is_struct_ptr(struct btf *btf, const struct btf_type *t) +static inline int btf_check_iter_arg(struct btf *btf, const struct btf_type *func, int arg_idx) { - if (!btf_type_is_ptr(t)) - return false; - - t = btf_type_skip_modifiers(btf, t->type, NULL); - - return btf_type_is_struct(t); + return -EOPNOTSUPP; } - +#endif #endif diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index e24aabfe8ecc..139bdececdcf 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -3,6 +3,8 @@ #ifndef _LINUX_BTF_IDS_H #define _LINUX_BTF_IDS_H +#include <linux/types.h> /* for u32 */ + struct btf_id_set { u32 cnt; u32 ids[]; @@ -281,5 +283,6 @@ extern u32 btf_tracing_ids[]; extern u32 bpf_cgroup_btf_id[]; extern u32 bpf_local_storage_map_btf_id[]; extern u32 btf_bpf_map_id[]; +extern u32 bpf_kmem_cache_btf_id[]; #endif diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index d78454a4dd1f..932139c5d46f 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -53,7 +53,7 @@ typedef void (bh_end_io_t)(struct buffer_head *bh, int uptodate); * filesystem and block layers. Nowadays the basic I/O unit * is the bio, and buffer_heads are used for extracting block * mappings (via a get_block_t call), for tracking state within - * a page (via a page_mapping) and for wrapping bio submission + * a folio (via a folio_mapping) and for wrapping bio submission * for backward compatibility reasons (e.g. submit_bh). */ struct buffer_head { @@ -199,8 +199,7 @@ void folio_set_bh(struct buffer_head *bh, struct folio *folio, unsigned long offset); struct buffer_head *folio_alloc_buffers(struct folio *folio, unsigned long size, gfp_t gfp); -struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size, - bool retry); +struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size); struct buffer_head *create_empty_buffers(struct folio *folio, unsigned long blocksize, unsigned long b_state); void end_buffer_read_sync(struct buffer_head *bh, int uptodate); @@ -258,18 +257,18 @@ int __block_write_full_folio(struct inode *inode, struct folio *folio, int block_read_full_folio(struct folio *, get_block_t *); bool block_is_partially_uptodate(struct folio *, size_t from, size_t count); int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, get_block_t *get_block); -int __block_write_begin(struct page *page, loff_t pos, unsigned len, + struct folio **foliop, get_block_t *get_block); +int __block_write_begin(struct folio *folio, loff_t pos, unsigned len, get_block_t *get_block); int block_write_end(struct file *, struct address_space *, - loff_t, unsigned, unsigned, - struct page *, void *); + loff_t, unsigned len, unsigned copied, + struct folio *, void *); int generic_write_end(struct file *, struct address_space *, - loff_t, unsigned, unsigned, - struct page *, void *); + loff_t, unsigned len, unsigned copied, + struct folio *, void *); void folio_zero_new_buffers(struct folio *folio, size_t from, size_t to); int cont_write_begin(struct file *, struct address_space *, loff_t, - unsigned, struct page **, void **, + unsigned, struct folio **, void **, get_block_t *, loff_t *); int generic_cont_expand_simple(struct inode *inode, loff_t size); void block_commit_write(struct page *page, unsigned int from, unsigned int to); @@ -303,12 +302,38 @@ static inline void put_bh(struct buffer_head *bh) atomic_dec(&bh->b_count); } +/** + * brelse - Release a buffer. + * @bh: The buffer to release. + * + * Decrement a buffer_head's reference count. If @bh is NULL, this + * function is a no-op. + * + * If all buffers on a folio have zero reference count, are clean + * and unlocked, and if the folio is unlocked and not under writeback + * then try_to_free_buffers() may strip the buffers from the folio in + * preparation for freeing it (sometimes, rarely, buffers are removed + * from a folio but it ends up not being freed, and buffers may later + * be reattached). + * + * Context: Any context. + */ static inline void brelse(struct buffer_head *bh) { if (bh) __brelse(bh); } +/** + * bforget - Discard any dirty data in a buffer. + * @bh: The buffer to forget. + * + * Call this function instead of brelse() if the data written to a buffer + * no longer needs to be written back. It will clear the buffer's dirty + * flag so writeback of this buffer will be skipped. + * + * Context: Any context. + */ static inline void bforget(struct buffer_head *bh) { if (bh) @@ -338,7 +363,7 @@ static inline struct buffer_head *getblk_unmovable(struct block_device *bdev, { gfp_t gfp; - gfp = mapping_gfp_constraint(bdev->bd_inode->i_mapping, ~__GFP_FS); + gfp = mapping_gfp_constraint(bdev->bd_mapping, ~__GFP_FS); gfp |= __GFP_NOFAIL; return bdev_getblk(bdev, block, size, gfp); @@ -349,7 +374,7 @@ static inline struct buffer_head *__getblk(struct block_device *bdev, { gfp_t gfp; - gfp = mapping_gfp_constraint(bdev->bd_inode->i_mapping, ~__GFP_FS); + gfp = mapping_gfp_constraint(bdev->bd_mapping, ~__GFP_FS); gfp |= __GFP_MOVABLE | __GFP_NOFAIL; return bdev_getblk(bdev, block, size, gfp); @@ -437,17 +462,21 @@ static inline void bh_readahead_batch(int nr, struct buffer_head *bhs[], } /** - * __bread() - reads a specified block and returns the bh - * @bdev: the block_device to read from - * @block: number of block - * @size: size (in bytes) to read + * __bread() - Read a block. + * @bdev: The block device to read from. + * @block: Block number in units of block size. + * @size: The block size of this device in bytes. * - * Reads a specified block, and returns buffer head that contains it. - * The page cache is allocated from movable area so that it can be migrated. - * It returns NULL if the block was unreadable. + * Read a specified block, and return the buffer head that refers + * to it. The memory is allocated from the movable area so that it can + * be migrated. The returned buffer head has its refcount increased. + * The caller should call brelse() when it has finished with the buffer. + * + * Context: May sleep waiting for I/O. + * Return: NULL if the block was unreadable. */ -static inline struct buffer_head * -__bread(struct block_device *bdev, sector_t block, unsigned size) +static inline struct buffer_head *__bread(struct block_device *bdev, + sector_t block, unsigned size) { return __bread_gfp(bdev, block, size, __GFP_MOVABLE); } diff --git a/include/linux/bug.h b/include/linux/bug.h index 348acf2558f3..a9948a9f1093 100644 --- a/include/linux/bug.h +++ b/include/linux/bug.h @@ -73,15 +73,23 @@ static inline void generic_bug_clear_once(void) {} #endif /* CONFIG_GENERIC_BUG */ +#ifdef CONFIG_PRINTK +void mem_dump_obj(void *object); +#else +static inline void mem_dump_obj(void *object) {} +#endif + /* * Since detected data corruption should stop operation on the affected * structures. Return value must be checked and sanely acted on by caller. */ static inline __must_check bool check_data_corruption(bool v) { return v; } -#define CHECK_DATA_CORRUPTION(condition, fmt, ...) \ +#define CHECK_DATA_CORRUPTION(condition, addr, fmt, ...) \ check_data_corruption(({ \ bool corruption = unlikely(condition); \ if (corruption) { \ + if (addr) \ + mem_dump_obj(addr); \ if (IS_ENABLED(CONFIG_BUG_ON_DATA_CORRUPTION)) { \ pr_err(fmt, ##__VA_ARGS__); \ BUG(); \ diff --git a/include/linux/buildid.h b/include/linux/buildid.h index 20aa3c2d89f7..014a88c41073 100644 --- a/include/linux/buildid.h +++ b/include/linux/buildid.h @@ -7,8 +7,8 @@ #define BUILD_ID_SIZE_MAX 20 struct vm_area_struct; -int build_id_parse(struct vm_area_struct *vma, unsigned char *build_id, - __u32 *size); +int build_id_parse(struct vm_area_struct *vma, unsigned char *build_id, __u32 *size); +int build_id_parse_nofault(struct vm_area_struct *vma, unsigned char *build_id, __u32 *size); int build_id_parse_buf(const void *buf, unsigned char *build_id, u32 buf_size); #if IS_ENABLED(CONFIG_STACKTRACE_BUILD_ID) || IS_ENABLED(CONFIG_VMCORE_INFO) diff --git a/include/linux/bus/stm32_firewall_device.h b/include/linux/bus/stm32_firewall_device.h new file mode 100644 index 000000000000..5178b72bc920 --- /dev/null +++ b/include/linux/bus/stm32_firewall_device.h @@ -0,0 +1,142 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2023, STMicroelectronics - All Rights Reserved + */ + +#ifndef STM32_FIREWALL_DEVICE_H +#define STM32_FIREWALL_DEVICE_H + +#include <linux/of.h> +#include <linux/platform_device.h> +#include <linux/types.h> + +#define STM32_FIREWALL_MAX_EXTRA_ARGS 5 + +/* Opaque reference to stm32_firewall_controller */ +struct stm32_firewall_controller; + +/** + * struct stm32_firewall - Information on a device's firewall. Each device can have more than one + * firewall. + * + * @firewall_ctrl: Pointer referencing a firewall controller of the device. It is + * opaque so a device cannot manipulate the controller's ops or access + * the controller's data + * @extra_args: Extra arguments that are implementation dependent + * @entry: Name of the firewall entry + * @extra_args_size: Number of extra arguments + * @firewall_id: Firewall ID associated the device for this firewall controller + */ +struct stm32_firewall { + struct stm32_firewall_controller *firewall_ctrl; + u32 extra_args[STM32_FIREWALL_MAX_EXTRA_ARGS]; + const char *entry; + size_t extra_args_size; + u32 firewall_id; +}; + +#if IS_ENABLED(CONFIG_STM32_FIREWALL) +/** + * stm32_firewall_get_firewall - Get the firewall(s) associated to given device. + * The firewall controller reference is always the first argument + * of each of the access-controller property entries. + * The firewall ID is always the second argument of each of the + * access-controller property entries. + * If there's no argument linked to the phandle, then the firewall ID + * field is set to U32_MAX, which is an invalid ID. + * + * @np: Device node to parse + * @firewall: Array of firewall references + * @nb_firewall: Number of firewall references to get. Must be at least 1. + * + * Returns 0 on success, -ENODEV if there's no match with a firewall controller or appropriate errno + * code if error occurred. + */ +int stm32_firewall_get_firewall(struct device_node *np, struct stm32_firewall *firewall, + unsigned int nb_firewall); + +/** + * stm32_firewall_grant_access - Request firewall access rights and grant access. + * + * @firewall: Firewall reference containing the ID to check against its firewall + * controller + * + * Returns 0 if access is granted, -EACCES if access is denied, -ENODEV if firewall is null or + * appropriate errno code if error occurred + */ +int stm32_firewall_grant_access(struct stm32_firewall *firewall); + +/** + * stm32_firewall_release_access - Release access granted from a call to + * stm32_firewall_grant_access(). + * + * @firewall: Firewall reference containing the ID to check against its firewall + * controller + */ +void stm32_firewall_release_access(struct stm32_firewall *firewall); + +/** + * stm32_firewall_grant_access_by_id - Request firewall access rights of a given device + * based on a specific firewall ID + * + * Warnings: + * There is no way to ensure that the given ID will correspond to the firewall referenced in the + * device node if the ID did not come from stm32_firewall_get_firewall(). In that case, this + * function must be used with caution. + * This function should be used for subsystem resources that do not have the same firewall ID + * as their parent. + * U32_MAX is an invalid ID. + * + * @firewall: Firewall reference containing the firewall controller + * @subsystem_id: Firewall ID of the subsystem resource + * + * Returns 0 if access is granted, -EACCES if access is denied, -ENODEV if firewall is null or + * appropriate errno code if error occurred + */ +int stm32_firewall_grant_access_by_id(struct stm32_firewall *firewall, u32 subsystem_id); + +/** + * stm32_firewall_release_access_by_id - Release access granted from a call to + * stm32_firewall_grant_access_by_id(). + * + * Warnings: + * There is no way to ensure that the given ID will correspond to the firewall referenced in the + * device node if the ID did not come from stm32_firewall_get_firewall(). In that case, this + * function must be used with caution. + * This function should be used for subsystem resources that do not have the same firewall ID + * as their parent. + * U32_MAX is an invalid ID. + * + * @firewall: Firewall reference containing the firewall controller + * @subsystem_id: Firewall ID of the subsystem resource + */ +void stm32_firewall_release_access_by_id(struct stm32_firewall *firewall, u32 subsystem_id); + +#else /* CONFIG_STM32_FIREWALL */ + +int stm32_firewall_get_firewall(struct device_node *np, struct stm32_firewall *firewall, + unsigned int nb_firewall) +{ + return -ENODEV; +} + +int stm32_firewall_grant_access(struct stm32_firewall *firewall) +{ + return -ENODEV; +} + +void stm32_firewall_release_access(struct stm32_firewall *firewall) +{ +} + +int stm32_firewall_grant_access_by_id(struct stm32_firewall *firewall, u32 subsystem_id) +{ + return -ENODEV; +} + +void stm32_firewall_release_access_by_id(struct stm32_firewall *firewall, u32 subsystem_id) +{ +} + +#endif /* CONFIG_STM32_FIREWALL */ +#endif /* STM32_FIREWALL_DEVICE_H */ diff --git a/include/linux/bvec.h b/include/linux/bvec.h index bd1e361b351c..ba8f52d48b94 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -280,4 +280,13 @@ static inline void *bvec_virt(struct bio_vec *bvec) return page_address(bvec->bv_page) + bvec->bv_offset; } +/** + * bvec_phys - return the physical address for a bvec + * @bvec: bvec to return the physical address for + */ +static inline phys_addr_t bvec_phys(const struct bio_vec *bvec) +{ + return page_to_phys(bvec->bv_page) + bvec->bv_offset; +} + #endif /* __LINUX_BVEC_H */ diff --git a/include/linux/cache.h b/include/linux/cache.h index 0ecb17bb6883..ca2a05682a54 100644 --- a/include/linux/cache.h +++ b/include/linux/cache.h @@ -13,6 +13,32 @@ #define SMP_CACHE_BYTES L1_CACHE_BYTES #endif +/** + * SMP_CACHE_ALIGN - align a value to the L2 cacheline size + * @x: value to align + * + * On some architectures, L2 ("SMP") CL size is bigger than L1, and sometimes, + * this needs to be accounted. + * + * Return: aligned value. + */ +#ifndef SMP_CACHE_ALIGN +#define SMP_CACHE_ALIGN(x) ALIGN(x, SMP_CACHE_BYTES) +#endif + +/* + * ``__aligned_largest`` aligns a field to the value most optimal for the + * target architecture to perform memory operations. Get the actual value + * to be able to use it anywhere else. + */ +#ifndef __LARGEST_ALIGN +#define __LARGEST_ALIGN sizeof(struct { long x; } __aligned_largest) +#endif + +#ifndef LARGEST_ALIGN +#define LARGEST_ALIGN(x) ALIGN(x, __LARGEST_ALIGN) +#endif + /* * __read_mostly is used to keep rarely changing variables out of frequently * updated cachelines. Its use should be reserved for data that is used @@ -95,6 +121,39 @@ __u8 __cacheline_group_end__##GROUP[0] #endif +/** + * __cacheline_group_begin_aligned - declare an aligned group start + * @GROUP: name of the group + * @...: optional group alignment + * + * The following block inside a struct: + * + * __cacheline_group_begin_aligned(grp); + * field a; + * field b; + * __cacheline_group_end_aligned(grp); + * + * will always be aligned to either the specified alignment or + * ``SMP_CACHE_BYTES``. + */ +#define __cacheline_group_begin_aligned(GROUP, ...) \ + __cacheline_group_begin(GROUP) \ + __aligned((__VA_ARGS__ + 0) ? : SMP_CACHE_BYTES) + +/** + * __cacheline_group_end_aligned - declare an aligned group end + * @GROUP: name of the group + * @...: optional alignment (same as was in __cacheline_group_begin_aligned()) + * + * Note that the end marker is aligned to sizeof(long) to allow more precise + * size assertion. It also declares a padding at the end to avoid next field + * falling into this cacheline. + */ +#define __cacheline_group_end_aligned(GROUP, ...) \ + __cacheline_group_end(GROUP) __aligned(sizeof(long)); \ + struct { } __cacheline_group_pad__##GROUP \ + __aligned((__VA_ARGS__ + 0) ? : SMP_CACHE_BYTES) + #ifndef CACHELINE_ASSERT_GROUP_MEMBER #define CACHELINE_ASSERT_GROUP_MEMBER(TYPE, GROUP, MEMBER) \ BUILD_BUG_ON(!(offsetof(TYPE, MEMBER) >= \ diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h index 2cb15fe4fe12..c8f4f0a0b874 100644 --- a/include/linux/cacheinfo.h +++ b/include/linux/cacheinfo.h @@ -3,7 +3,8 @@ #define _LINUX_CACHEINFO_H #include <linux/bitops.h> -#include <linux/cpumask.h> +#include <linux/cpuhplock.h> +#include <linux/cpumask_types.h> #include <linux/smp.h> struct device_node; @@ -113,26 +114,40 @@ int acpi_get_cache_info(unsigned int cpu, const struct attribute_group *cache_get_priv_group(struct cacheinfo *this_leaf); /* - * Get the id of the cache associated with @cpu at level @level. + * Get the cacheinfo structure for the cache associated with @cpu at + * level @level. * cpuhp lock must be held. */ -static inline int get_cpu_cacheinfo_id(int cpu, int level) +static inline struct cacheinfo *get_cpu_cacheinfo_level(int cpu, int level) { struct cpu_cacheinfo *ci = get_cpu_cacheinfo(cpu); int i; + lockdep_assert_cpus_held(); + for (i = 0; i < ci->num_leaves; i++) { if (ci->info_list[i].level == level) { if (ci->info_list[i].attributes & CACHE_ID) - return ci->info_list[i].id; - return -1; + return &ci->info_list[i]; + return NULL; } } - return -1; + return NULL; } -#ifdef CONFIG_ARM64 +/* + * Get the id of the cache associated with @cpu at level @level. + * cpuhp lock must be held. + */ +static inline int get_cpu_cacheinfo_id(int cpu, int level) +{ + struct cacheinfo *ci = get_cpu_cacheinfo_level(cpu, level); + + return ci ? ci->id : -1; +} + +#if defined(CONFIG_ARM64) || defined(CONFIG_ARM) #define use_arch_cache_info() (true) #else #define use_arch_cache_info() (false) @@ -140,8 +155,14 @@ static inline int get_cpu_cacheinfo_id(int cpu, int level) #ifndef CONFIG_ARCH_HAS_CPU_CACHE_ALIASING #define cpu_dcache_is_aliasing() false +#define cpu_icache_is_aliasing() cpu_dcache_is_aliasing() #else #include <asm/cachetype.h> + +#ifndef cpu_icache_is_aliasing +#define cpu_icache_is_aliasing() cpu_dcache_is_aliasing() +#endif + #endif #endif /* _LINUX_CACHEINFO_H */ diff --git a/include/linux/call_once.h b/include/linux/call_once.h new file mode 100644 index 000000000000..6261aa0b3fb0 --- /dev/null +++ b/include/linux/call_once.h @@ -0,0 +1,45 @@ +#ifndef _LINUX_CALL_ONCE_H +#define _LINUX_CALL_ONCE_H + +#include <linux/types.h> +#include <linux/mutex.h> + +#define ONCE_NOT_STARTED 0 +#define ONCE_RUNNING 1 +#define ONCE_COMPLETED 2 + +struct once { + atomic_t state; + struct mutex lock; +}; + +static inline void __once_init(struct once *once, const char *name, + struct lock_class_key *key) +{ + atomic_set(&once->state, ONCE_NOT_STARTED); + __mutex_init(&once->lock, name, key); +} + +#define once_init(once) \ +do { \ + static struct lock_class_key __key; \ + __once_init((once), #once, &__key); \ +} while (0) + +static inline void call_once(struct once *once, void (*cb)(struct once *)) +{ + /* Pairs with atomic_set_release() below. */ + if (atomic_read_acquire(&once->state) == ONCE_COMPLETED) + return; + + guard(mutex)(&once->lock); + WARN_ON(atomic_read(&once->state) == ONCE_RUNNING); + if (atomic_read(&once->state) != ONCE_NOT_STARTED) + return; + + atomic_set(&once->state, ONCE_RUNNING); + cb(once); + atomic_set_release(&once->state, ONCE_COMPLETED); +} + +#endif /* _LINUX_CALL_ONCE_H */ diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 1b92aed49363..23492213ea35 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -186,7 +186,7 @@ void close_candev(struct net_device *dev); int can_change_mtu(struct net_device *dev, int new_mtu); int can_eth_ioctl_hwts(struct net_device *netdev, struct ifreq *ifr, int cmd); int can_ethtool_op_get_ts_info_hwts(struct net_device *dev, - struct ethtool_ts_info *info); + struct kernel_ethtool_ts_info *info); int register_candev(struct net_device *dev); void unregister_candev(struct net_device *dev); diff --git a/include/linux/cc_platform.h b/include/linux/cc_platform.h index 60693a145894..0bf7d33a1048 100644 --- a/include/linux/cc_platform.h +++ b/include/linux/cc_platform.h @@ -82,14 +82,12 @@ enum cc_attr { CC_ATTR_GUEST_SEV_SNP, /** - * @CC_ATTR_HOTPLUG_DISABLED: Hotplug is not supported or disabled. + * @CC_ATTR_GUEST_SNP_SECURE_TSC: SNP Secure TSC is active. * - * The platform/OS is running as a guest/virtual machine does not - * support CPU hotplug feature. - * - * Examples include TDX Guest. + * The platform/OS is running as a guest/virtual machine and actively + * using AMD SEV-SNP Secure TSC feature. */ - CC_ATTR_HOTPLUG_DISABLED, + CC_ATTR_GUEST_SNP_SECURE_TSC, /** * @CC_ATTR_HOST_SEV_SNP: AMD SNP enabled on the host. diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h index 98c6fd0b39b6..fdfb61ccf55a 100644 --- a/include/linux/cdrom.h +++ b/include/linux/cdrom.h @@ -77,7 +77,7 @@ struct cdrom_device_ops { unsigned int clearing, int slot); int (*tray_move) (struct cdrom_device_info *, int); int (*lock_door) (struct cdrom_device_info *, int); - int (*select_speed) (struct cdrom_device_info *, int); + int (*select_speed) (struct cdrom_device_info *, unsigned long); int (*get_last_session) (struct cdrom_device_info *, struct cdrom_multisession *); int (*get_mcn) (struct cdrom_device_info *, diff --git a/include/linux/cdx/cdx_bus.h b/include/linux/cdx/cdx_bus.h index b57118aaa679..79bb80e56790 100644 --- a/include/linux/cdx/cdx_bus.h +++ b/include/linux/cdx/cdx_bus.h @@ -211,7 +211,7 @@ struct cdx_driver { }; #define to_cdx_driver(_drv) \ - container_of(_drv, struct cdx_driver, driver) + container_of_const(_drv, struct cdx_driver, driver) /* Macro to avoid include chaining to get THIS_MODULE */ #define cdx_driver_register(drv) \ diff --git a/include/linux/ceph/ceph_debug.h b/include/linux/ceph/ceph_debug.h index 11a92a946016..5f904591fa5f 100644 --- a/include/linux/ceph/ceph_debug.h +++ b/include/linux/ceph/ceph_debug.h @@ -27,17 +27,13 @@ ##__VA_ARGS__) # else /* faux printk call just to see any compiler warnings. */ -# define dout(fmt, ...) do { \ - if (0) \ - printk(KERN_DEBUG fmt, ##__VA_ARGS__); \ - } while (0) -# define doutc(client, fmt, ...) do { \ - if (0) \ - printk(KERN_DEBUG "[%pU %llu] " fmt, \ - &client->fsid, \ - client->monc.auth->global_id, \ - ##__VA_ARGS__); \ - } while (0) +# define dout(fmt, ...) \ + no_printk(KERN_DEBUG fmt, ##__VA_ARGS__) +# define doutc(client, fmt, ...) \ + no_printk(KERN_DEBUG "[%pU %llu] " fmt, \ + &client->fsid, \ + client->monc.auth->global_id, \ + ##__VA_ARGS__) # endif #else diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index ee1d0e5f9789..c7f2c63b3bc3 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -504,20 +504,6 @@ struct ceph_mds_request_head_legacy { #define CEPH_MDS_REQUEST_HEAD_VERSION 3 -struct ceph_mds_request_head_old { - __le16 version; /* struct version */ - __le64 oldest_client_tid; - __le32 mdsmap_epoch; /* on client */ - __le32 flags; /* CEPH_MDS_FLAG_* */ - __u8 num_retry, num_fwd; /* count retry, fwd attempts */ - __le16 num_releases; /* # include cap/lease release records */ - __le32 op; /* mds op code */ - __le32 caller_uid, caller_gid; - __le64 ino; /* use this ino for openc, mkdir, mknod, - etc. (if replaying) */ - union ceph_mds_request_args_ext args; -} __attribute__ ((packed)); - struct ceph_mds_request_head { __le16 version; /* struct version */ __le64 oldest_client_tid; @@ -808,7 +794,7 @@ struct ceph_mds_caps { struct ceph_mds_cap_peer { __le64 cap_id; - __le32 seq; + __le32 issue_seq; __le32 mseq; __le32 mds; __u8 flags; @@ -822,7 +808,7 @@ struct ceph_mds_cap_release { struct ceph_mds_cap_item { __le64 ino; __le64 cap_id; - __le32 migrate_seq, seq; + __le32 migrate_seq, issue_seq; } __attribute__ ((packed)); #define CEPH_MDS_LEASE_REVOKE 1 /* mds -> client */ diff --git a/include/linux/ceph/decode.h b/include/linux/ceph/decode.h index 04f3ace5787b..8fc1aed64113 100644 --- a/include/linux/ceph/decode.h +++ b/include/linux/ceph/decode.h @@ -6,7 +6,7 @@ #include <linux/bug.h> #include <linux/slab.h> #include <linux/time.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/ceph/types.h> diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 4497d0a6772c..733e7f93db66 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -4,7 +4,7 @@ #include <linux/ceph/ceph_debug.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/backing-dev.h> #include <linux/completion.h> #include <linux/exportfs.h> @@ -317,12 +317,6 @@ extern void ceph_release_page_vector(struct page **pages, int num_pages); extern void ceph_put_page_vector(struct page **pages, int num_pages, bool dirty); extern struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags); -extern int ceph_copy_user_to_page_vector(struct page **pages, - const void __user *data, - loff_t off, size_t len); -extern void ceph_copy_to_page_vector(struct page **pages, - const void *data, - loff_t off, size_t len); extern void ceph_copy_from_page_vector(struct page **pages, void *data, loff_t off, size_t len); diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index f66f6aac74f6..d55b30057a45 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -449,8 +449,6 @@ extern int ceph_osdc_init(struct ceph_osd_client *osdc, extern void ceph_osdc_stop(struct ceph_osd_client *osdc); extern void ceph_osdc_reopen_osds(struct ceph_osd_client *osdc); -extern void ceph_osdc_handle_reply(struct ceph_osd_client *osdc, - struct ceph_msg *msg); extern void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg); void ceph_osdc_update_epoch_barrier(struct ceph_osd_client *osdc, u32 eb); @@ -628,8 +626,6 @@ int ceph_osdc_notify(struct ceph_osd_client *osdc, u32 timeout, struct page ***preply_pages, size_t *preply_len); -int ceph_osdc_watch_check(struct ceph_osd_client *osdc, - struct ceph_osd_linger_request *lreq); int ceph_osdc_list_watchers(struct ceph_osd_client *osdc, struct ceph_object_id *oid, struct ceph_object_locator *oloc, diff --git a/include/linux/ceph/pagelist.h b/include/linux/ceph/pagelist.h index 5dead8486fd8..879bec0863aa 100644 --- a/include/linux/ceph/pagelist.h +++ b/include/linux/ceph/pagelist.h @@ -17,12 +17,6 @@ struct ceph_pagelist { refcount_t refcnt; }; -struct ceph_pagelist_cursor { - struct ceph_pagelist *pl; /* pagelist, for error checking */ - struct list_head *page_lru; /* page in list */ - size_t room; /* room remaining to reset to */ -}; - struct ceph_pagelist *ceph_pagelist_alloc(gfp_t gfp_flags); extern void ceph_pagelist_release(struct ceph_pagelist *pl); @@ -33,12 +27,6 @@ extern int ceph_pagelist_reserve(struct ceph_pagelist *pl, size_t space); extern int ceph_pagelist_free_reserve(struct ceph_pagelist *pl); -extern void ceph_pagelist_set_cursor(struct ceph_pagelist *pl, - struct ceph_pagelist_cursor *c); - -extern int ceph_pagelist_truncate(struct ceph_pagelist *pl, - struct ceph_pagelist_cursor *c); - static inline int ceph_pagelist_encode_64(struct ceph_pagelist *pl, u64 v) { __le64 ev = cpu_to_le64(v); diff --git a/include/linux/cfag12864b.h b/include/linux/cfag12864b.h index 6617d9c68d86..83e6613d12ae 100644 --- a/include/linux/cfag12864b.h +++ b/include/linux/cfag12864b.h @@ -28,13 +28,6 @@ extern unsigned char * cfag12864b_buffer; /* - * Get the refresh rate of the LCD - * - * Returns the refresh rate (hertz). - */ -extern unsigned int cfag12864b_getrate(void); - -/* * Enable refreshing * * Returns 0 if successful (anyone was using it), @@ -50,16 +43,6 @@ extern unsigned char cfag12864b_enable(void); extern void cfag12864b_disable(void); /* - * Is enabled refreshing? (is anyone using the module?) - * - * Returns 0 if refreshing is not enabled (anyone is using it), - * or != 0 if refreshing is enabled (someone is using it). - * - * Useful for buffer read-only modules. - */ -extern unsigned char cfag12864b_isenabled(void); - -/* * Is the module inited? */ extern unsigned char cfag12864b_isinited(void); diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index ea48c861cd36..1b20d2d8ef7c 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -119,7 +119,12 @@ enum { /* * Enable hugetlb accounting for the memory controller. */ - CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING = (1 << 19), + CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING = (1 << 19), + + /* + * Enable legacy local pids.events. + */ + CGRP_ROOT_PIDS_LOCAL_EVENTS = (1 << 20), }; /* cftype->flags */ @@ -167,7 +172,11 @@ struct cgroup_subsys_state { /* reference count - access via css_[try]get() and css_put() */ struct percpu_ref refcnt; - /* siblings list anchored at the parent's ->children */ + /* + * siblings list anchored at the parent's ->children + * + * linkage is protected by cgroup_mutex or RCU + */ struct list_head sibling; struct list_head children; @@ -205,6 +214,14 @@ struct cgroup_subsys_state { * fields of the containing structure. */ struct cgroup_subsys_state *parent; + + /* + * Keep track of total numbers of visible descendant CSSes. + * The total number of dying CSSes is tracked in + * css->cgroup->nr_dying_subsys[ssid]. + * Protected by cgroup_mutex. + */ + int nr_descendants; }; /* @@ -310,6 +327,7 @@ struct cgroup_base_stat { #ifdef CONFIG_SCHED_CORE u64 forceidle_sum; #endif + u64 ntime; }; /* @@ -380,7 +398,7 @@ struct cgroup_freezer_state { bool freeze; /* Should the cgroup actually be frozen? */ - int e_freeze; + bool e_freeze; /* Fields below are protected by css_set_lock */ @@ -465,6 +483,12 @@ struct cgroup { /* Private pointers for each registered subsystem */ struct cgroup_subsys_state __rcu *subsys[CGROUP_SUBSYS_COUNT]; + /* + * Keep track of total number of dying CSSes at and below this cgroup. + * Protected by cgroup_mutex. + */ + int nr_dying_subsys[CGROUP_SUBSYS_COUNT]; + struct cgroup_root *root; /* @@ -534,9 +558,6 @@ struct cgroup { /* used to store eBPF programs */ struct cgroup_bpf bpf; - /* If there is block congestion on this cgroup. */ - atomic_t congestion_count; - /* Used to store internal freezer state */ struct cgroup_freezer_state freezer; @@ -676,9 +697,7 @@ struct cftype { __poll_t (*poll)(struct kernfs_open_file *of, struct poll_table_struct *pt); -#ifdef CONFIG_DEBUG_LOCK_ALLOC struct lock_class_key lockdep_key; -#endif }; /* @@ -775,6 +794,11 @@ struct cgroup_subsys { extern struct percpu_rw_semaphore cgroup_threadgroup_rwsem; +struct cgroup_of_peak { + unsigned long value; + struct list_head list; +}; + /** * cgroup_threadgroup_change_begin - threadgroup exclusion for cgroups * @tsk: target task diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 34aaf0e87def..f8ef47f8a634 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -10,8 +10,8 @@ */ #include <linux/sched.h> -#include <linux/cpumask.h> #include <linux/nodemask.h> +#include <linux/list.h> #include <linux/rculist.h> #include <linux/cgroupstats.h> #include <linux/fs.h> @@ -29,8 +29,6 @@ struct kernel_clone_args; -#ifdef CONFIG_CGROUPS - /* * All weight knobs on the default hierarchy should use the following min, * default and max values. The default value is the logarithmic center of @@ -40,6 +38,8 @@ struct kernel_clone_args; #define CGROUP_WEIGHT_DFL 100 #define CGROUP_WEIGHT_MAX 10000 +#ifdef CONFIG_CGROUPS + enum { CSS_TASK_ITER_PROCS = (1U << 0), /* walk only threadgroup leaders */ CSS_TASK_ITER_THREADED = (1U << 1), /* walk all threaded css_sets in the domain */ @@ -690,7 +690,7 @@ static inline void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen) void cgroup_rstat_updated(struct cgroup *cgrp, int cpu); void cgroup_rstat_flush(struct cgroup *cgrp); void cgroup_rstat_flush_hold(struct cgroup *cgrp); -void cgroup_rstat_flush_release(void); +void cgroup_rstat_flush_release(struct cgroup *cgrp); /* * Basic resource stats. @@ -855,4 +855,6 @@ static inline void cgroup_bpf_put(struct cgroup *cgrp) {} struct cgroup *task_get_cgroup1(struct task_struct *tsk, int hierarchy_id); +struct cgroup_of_peak *of_peak(struct kernfs_open_file *of); + #endif /* _LINUX_CGROUP_H */ diff --git a/include/linux/cgroup_dmem.h b/include/linux/cgroup_dmem.h new file mode 100644 index 000000000000..dd4869f1d736 --- /dev/null +++ b/include/linux/cgroup_dmem.h @@ -0,0 +1,66 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2023-2024 Intel Corporation + */ + +#ifndef _CGROUP_DMEM_H +#define _CGROUP_DMEM_H + +#include <linux/types.h> +#include <linux/llist.h> + +struct dmem_cgroup_pool_state; + +/* Opaque definition of a cgroup region, used internally */ +struct dmem_cgroup_region; + +#if IS_ENABLED(CONFIG_CGROUP_DMEM) +struct dmem_cgroup_region *dmem_cgroup_register_region(u64 size, const char *name_fmt, ...) __printf(2,3); +void dmem_cgroup_unregister_region(struct dmem_cgroup_region *region); +int dmem_cgroup_try_charge(struct dmem_cgroup_region *region, u64 size, + struct dmem_cgroup_pool_state **ret_pool, + struct dmem_cgroup_pool_state **ret_limit_pool); +void dmem_cgroup_uncharge(struct dmem_cgroup_pool_state *pool, u64 size); +bool dmem_cgroup_state_evict_valuable(struct dmem_cgroup_pool_state *limit_pool, + struct dmem_cgroup_pool_state *test_pool, + bool ignore_low, bool *ret_hit_low); + +void dmem_cgroup_pool_state_put(struct dmem_cgroup_pool_state *pool); +#else +static inline __printf(2,3) struct dmem_cgroup_region * +dmem_cgroup_register_region(u64 size, const char *name_fmt, ...) +{ + return NULL; +} + +static inline void dmem_cgroup_unregister_region(struct dmem_cgroup_region *region) +{ } + +static inline int dmem_cgroup_try_charge(struct dmem_cgroup_region *region, u64 size, + struct dmem_cgroup_pool_state **ret_pool, + struct dmem_cgroup_pool_state **ret_limit_pool) +{ + *ret_pool = NULL; + + if (ret_limit_pool) + *ret_limit_pool = NULL; + + return 0; +} + +static inline void dmem_cgroup_uncharge(struct dmem_cgroup_pool_state *pool, u64 size) +{ } + +static inline +bool dmem_cgroup_state_evict_valuable(struct dmem_cgroup_pool_state *limit_pool, + struct dmem_cgroup_pool_state *test_pool, + bool ignore_low, bool *ret_hit_low) +{ + return true; +} + +static inline void dmem_cgroup_pool_state_put(struct dmem_cgroup_pool_state *pool) +{ } + +#endif +#endif /* _CGROUP_DMEM_H */ diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h index 445235487230..3fd0bcbf3080 100644 --- a/include/linux/cgroup_subsys.h +++ b/include/linux/cgroup_subsys.h @@ -65,6 +65,10 @@ SUBSYS(rdma) SUBSYS(misc) #endif +#if IS_ENABLED(CONFIG_CGROUP_DMEM) +SUBSYS(dmem) +#endif + /* * The following subsystems are not supported on the default hierarchy. */ diff --git a/include/linux/cleanup.h b/include/linux/cleanup.h index c2d09bc4f976..ec00e3f7af2b 100644 --- a/include/linux/cleanup.h +++ b/include/linux/cleanup.h @@ -1,9 +1,145 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __LINUX_GUARDS_H -#define __LINUX_GUARDS_H +#ifndef _LINUX_CLEANUP_H +#define _LINUX_CLEANUP_H #include <linux/compiler.h> +/** + * DOC: scope-based cleanup helpers + * + * The "goto error" pattern is notorious for introducing subtle resource + * leaks. It is tedious and error prone to add new resource acquisition + * constraints into code paths that already have several unwind + * conditions. The "cleanup" helpers enable the compiler to help with + * this tedium and can aid in maintaining LIFO (last in first out) + * unwind ordering to avoid unintentional leaks. + * + * As drivers make up the majority of the kernel code base, here is an + * example of using these helpers to clean up PCI drivers. The target of + * the cleanups are occasions where a goto is used to unwind a device + * reference (pci_dev_put()), or unlock the device (pci_dev_unlock()) + * before returning. + * + * The DEFINE_FREE() macro can arrange for PCI device references to be + * dropped when the associated variable goes out of scope:: + * + * DEFINE_FREE(pci_dev_put, struct pci_dev *, if (_T) pci_dev_put(_T)) + * ... + * struct pci_dev *dev __free(pci_dev_put) = + * pci_get_slot(parent, PCI_DEVFN(0, 0)); + * + * The above will automatically call pci_dev_put() if @dev is non-NULL + * when @dev goes out of scope (automatic variable scope). If a function + * wants to invoke pci_dev_put() on error, but return @dev (i.e. without + * freeing it) on success, it can do:: + * + * return no_free_ptr(dev); + * + * ...or:: + * + * return_ptr(dev); + * + * The DEFINE_GUARD() macro can arrange for the PCI device lock to be + * dropped when the scope where guard() is invoked ends:: + * + * DEFINE_GUARD(pci_dev, struct pci_dev *, pci_dev_lock(_T), pci_dev_unlock(_T)) + * ... + * guard(pci_dev)(dev); + * + * The lifetime of the lock obtained by the guard() helper follows the + * scope of automatic variable declaration. Take the following example:: + * + * func(...) + * { + * if (...) { + * ... + * guard(pci_dev)(dev); // pci_dev_lock() invoked here + * ... + * } // <- implied pci_dev_unlock() triggered here + * } + * + * Observe the lock is held for the remainder of the "if ()" block not + * the remainder of "func()". + * + * Now, when a function uses both __free() and guard(), or multiple + * instances of __free(), the LIFO order of variable definition order + * matters. GCC documentation says: + * + * "When multiple variables in the same scope have cleanup attributes, + * at exit from the scope their associated cleanup functions are run in + * reverse order of definition (last defined, first cleanup)." + * + * When the unwind order matters it requires that variables be defined + * mid-function scope rather than at the top of the file. Take the + * following example and notice the bug highlighted by "!!":: + * + * LIST_HEAD(list); + * DEFINE_MUTEX(lock); + * + * struct object { + * struct list_head node; + * }; + * + * static struct object *alloc_add(void) + * { + * struct object *obj; + * + * lockdep_assert_held(&lock); + * obj = kzalloc(sizeof(*obj), GFP_KERNEL); + * if (obj) { + * LIST_HEAD_INIT(&obj->node); + * list_add(obj->node, &list): + * } + * return obj; + * } + * + * static void remove_free(struct object *obj) + * { + * lockdep_assert_held(&lock); + * list_del(&obj->node); + * kfree(obj); + * } + * + * DEFINE_FREE(remove_free, struct object *, if (_T) remove_free(_T)) + * static int init(void) + * { + * struct object *obj __free(remove_free) = NULL; + * int err; + * + * guard(mutex)(&lock); + * obj = alloc_add(); + * + * if (!obj) + * return -ENOMEM; + * + * err = other_init(obj); + * if (err) + * return err; // remove_free() called without the lock!! + * + * no_free_ptr(obj); + * return 0; + * } + * + * That bug is fixed by changing init() to call guard() and define + + * initialize @obj in this order:: + * + * guard(mutex)(&lock); + * struct object *obj __free(remove_free) = alloc_add(); + * + * Given that the "__free(...) = NULL" pattern for variables defined at + * the top of the function poses this potential interdependency problem + * the recommendation is to always define and assign variables in one + * statement and not group variable definitions at the top of the + * function when __free() is used. + * + * Lastly, given that the benefit of cleanup helpers is removal of + * "goto", and that the "goto" statement can jump between scopes, the + * expectation is that usage of "goto" and cleanup helpers is never + * mixed in the same function. I.e. for a given routine, convert all + * resources that need a "goto" cleanup to scope-based cleanup, or + * convert none of them. + */ + /* * DEFINE_FREE(name, type, free): * simple helper macro that defines the required wrapper for a __free() @@ -63,17 +199,20 @@ #define __free(_name) __cleanup(__free_##_name) -#define __get_and_null_ptr(p) \ - ({ __auto_type __ptr = &(p); \ - __auto_type __val = *__ptr; \ - *__ptr = NULL; __val; }) +#define __get_and_null(p, nullvalue) \ + ({ \ + __auto_type __ptr = &(p); \ + __auto_type __val = *__ptr; \ + *__ptr = nullvalue; \ + __val; \ + }) static inline __must_check const volatile void * __must_check_fn(const volatile void *val) { return val; } #define no_free_ptr(p) \ - ((typeof(p)) __must_check_fn(__get_and_null_ptr(p))) + ((typeof(p)) __must_check_fn(__get_and_null(p, NULL))) #define return_ptr(p) return no_free_ptr(p) @@ -95,7 +234,7 @@ const volatile void * __must_check_fn(const volatile void *val) * DEFINE_CLASS(fdget, struct fd, fdput(_T), fdget(fd), int fd) * * CLASS(fdget, f)(fd); - * if (!f.file) + * if (fd_empty(f)) * return -EBADF; * * // use 'f' without concern @@ -146,14 +285,20 @@ static inline class_##_name##_t class_##_name##ext##_constructor(_init_args) \ * similar to scoped_guard(), except it does fail when the lock * acquire fails. * + * Only for conditional locks. */ +#define __DEFINE_CLASS_IS_CONDITIONAL(_name, _is_cond) \ +static __maybe_unused const bool class_##_name##_is_conditional = _is_cond + #define DEFINE_GUARD(_name, _type, _lock, _unlock) \ + __DEFINE_CLASS_IS_CONDITIONAL(_name, false); \ DEFINE_CLASS(_name, _type, if (_T) { _unlock; }, ({ _lock; _T; }), _type _T); \ static inline void * class_##_name##_lock_ptr(class_##_name##_t *_T) \ - { return *_T; } + { return (void *)(__force unsigned long)*_T; } #define DEFINE_GUARD_COND(_name, _ext, _condlock) \ + __DEFINE_CLASS_IS_CONDITIONAL(_name##_ext, true); \ EXTEND_CLASS(_name, _ext, \ ({ void *_t = _T; if (_T && !(_condlock)) _t = NULL; _t; }), \ class_##_name##_t _T) \ @@ -164,16 +309,40 @@ static inline class_##_name##_t class_##_name##ext##_constructor(_init_args) \ CLASS(_name, __UNIQUE_ID(guard)) #define __guard_ptr(_name) class_##_name##_lock_ptr +#define __is_cond_ptr(_name) class_##_name##_is_conditional + +/* + * Helper macro for scoped_guard(). + * + * Note that the "!__is_cond_ptr(_name)" part of the condition ensures that + * compiler would be sure that for the unconditional locks the body of the + * loop (caller-provided code glued to the else clause) could not be skipped. + * It is needed because the other part - "__guard_ptr(_name)(&scope)" - is too + * hard to deduce (even if could be proven true for unconditional locks). + */ +#define __scoped_guard(_name, _label, args...) \ + for (CLASS(_name, scope)(args); \ + __guard_ptr(_name)(&scope) || !__is_cond_ptr(_name); \ + ({ goto _label; })) \ + if (0) { \ +_label: \ + break; \ + } else + +#define scoped_guard(_name, args...) \ + __scoped_guard(_name, __UNIQUE_ID(label), args) -#define scoped_guard(_name, args...) \ - for (CLASS(_name, scope)(args), \ - *done = NULL; __guard_ptr(_name)(&scope) && !done; done = (void *)1) +#define __scoped_cond_guard(_name, _fail, _label, args...) \ + for (CLASS(_name, scope)(args); true; ({ goto _label; })) \ + if (!__guard_ptr(_name)(&scope)) { \ + BUILD_BUG_ON(!__is_cond_ptr(_name)); \ + _fail; \ +_label: \ + break; \ + } else -#define scoped_cond_guard(_name, _fail, args...) \ - for (CLASS(_name, scope)(args), \ - *done = NULL; !done; done = (void *)1) \ - if (!__guard_ptr(_name)(&scope)) _fail; \ - else +#define scoped_cond_guard(_name, _fail, args...) \ + __scoped_cond_guard(_name, _fail, __UNIQUE_ID(label), args) /* * Additional helper macros for generating lock guards with types, either for @@ -208,7 +377,7 @@ static inline void class_##_name##_destructor(class_##_name##_t *_T) \ \ static inline void *class_##_name##_lock_ptr(class_##_name##_t *_T) \ { \ - return _T->lock; \ + return (void *)(__force unsigned long)_T->lock; \ } @@ -230,14 +399,17 @@ static inline class_##_name##_t class_##_name##_constructor(void) \ } #define DEFINE_LOCK_GUARD_1(_name, _type, _lock, _unlock, ...) \ +__DEFINE_CLASS_IS_CONDITIONAL(_name, false); \ __DEFINE_UNLOCK_GUARD(_name, _type, _unlock, __VA_ARGS__) \ __DEFINE_LOCK_GUARD_1(_name, _type, _lock) #define DEFINE_LOCK_GUARD_0(_name, _lock, _unlock, ...) \ +__DEFINE_CLASS_IS_CONDITIONAL(_name, false); \ __DEFINE_UNLOCK_GUARD(_name, void, _unlock, __VA_ARGS__) \ __DEFINE_LOCK_GUARD_0(_name, _lock) #define DEFINE_LOCK_GUARD_1_COND(_name, _ext, _condlock) \ + __DEFINE_CLASS_IS_CONDITIONAL(_name##_ext, true); \ EXTEND_CLASS(_name, _ext, \ ({ class_##_name##_t _t = { .lock = l }, *_T = &_t;\ if (_T->lock && !(_condlock)) _T->lock = NULL; \ @@ -247,4 +419,4 @@ __DEFINE_LOCK_GUARD_0(_name, _lock) { return class_##_name##_lock_ptr(_T); } -#endif /* __LINUX_GUARDS_H */ +#endif /* _LINUX_CLEANUP_H */ diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 4a537260f655..2e6e603b7493 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -394,6 +394,20 @@ struct clk *clk_register_fixed_rate(struct device *dev, const char *name, __clk_hw_register_fixed_rate((dev), NULL, (name), (parent_name), NULL, \ NULL, (flags), (fixed_rate), 0, 0, true) /** + * devm_clk_hw_register_fixed_rate_parent_data - register fixed-rate clock with + * the clock framework + * @dev: device that is registering this clock + * @name: name of this clock + * @parent_data: parent clk data + * @flags: framework-specific flags + * @fixed_rate: non-adjustable clock rate + */ +#define devm_clk_hw_register_fixed_rate_parent_data(dev, name, parent_data, flags, \ + fixed_rate) \ + __clk_hw_register_fixed_rate((dev), NULL, (name), NULL, NULL, \ + (parent_data), (flags), (fixed_rate), 0, \ + 0, true) +/** * clk_hw_register_fixed_rate_parent_hw - register fixed-rate clock with * the clock framework * @dev: device that is registering this clock @@ -609,6 +623,24 @@ struct clk *clk_register_gate(struct device *dev, const char *name, NULL, (flags), (reg), (bit_idx), \ (clk_gate_flags), (lock)) /** + * devm_clk_hw_register_gate_parent_hw - register a gate clock with the clock + * framework + * @dev: device that is registering this clock + * @name: name of this clock + * @parent_hw: pointer to parent clk + * @flags: framework-specific flags for this clock + * @reg: register address to control gating of this clock + * @bit_idx: which bit in the register controls gating of this clock + * @clk_gate_flags: gate-specific flags for this clock + * @lock: shared register lock for this clock + */ +#define devm_clk_hw_register_gate_parent_hw(dev, name, parent_hw, flags, \ + reg, bit_idx, clk_gate_flags, \ + lock) \ + __devm_clk_hw_register_gate((dev), NULL, (name), NULL, (parent_hw), \ + NULL, (flags), (reg), (bit_idx), \ + (clk_gate_flags), (lock)) +/** * devm_clk_hw_register_gate_parent_data - register a gate clock with the * clock framework * @dev: device that is registering this clock @@ -675,13 +707,15 @@ struct clk_div_table { * CLK_DIVIDER_BIG_ENDIAN - By default little endian register accesses are used * for the divider register. Setting this flag makes the register accesses * big endian. + * CLK_DIVIDER_EVEN_INTEGERS - clock divisor is 2, 4, 6, 8, 10, etc. + * Formula is 2 * (value read from hardware + 1). */ struct clk_divider { struct clk_hw hw; void __iomem *reg; u8 shift; u8 width; - u8 flags; + u16 flags; const struct clk_div_table *table; spinlock_t *lock; }; @@ -697,6 +731,7 @@ struct clk_divider { #define CLK_DIVIDER_READ_ONLY BIT(5) #define CLK_DIVIDER_MAX_AT_ZERO BIT(6) #define CLK_DIVIDER_BIG_ENDIAN BIT(7) +#define CLK_DIVIDER_EVEN_INTEGERS BIT(8) extern const struct clk_ops clk_divider_ops; extern const struct clk_ops clk_divider_ro_ops; @@ -726,19 +761,21 @@ struct clk_hw *__clk_hw_register_divider(struct device *dev, struct device_node *np, const char *name, const char *parent_name, const struct clk_hw *parent_hw, const struct clk_parent_data *parent_data, unsigned long flags, - void __iomem *reg, u8 shift, u8 width, u8 clk_divider_flags, + void __iomem *reg, u8 shift, u8 width, + unsigned long clk_divider_flags, const struct clk_div_table *table, spinlock_t *lock); struct clk_hw *__devm_clk_hw_register_divider(struct device *dev, struct device_node *np, const char *name, const char *parent_name, const struct clk_hw *parent_hw, const struct clk_parent_data *parent_data, unsigned long flags, - void __iomem *reg, u8 shift, u8 width, u8 clk_divider_flags, + void __iomem *reg, u8 shift, u8 width, + unsigned long clk_divider_flags, const struct clk_div_table *table, spinlock_t *lock); struct clk *clk_register_divider_table(struct device *dev, const char *name, const char *parent_name, unsigned long flags, void __iomem *reg, u8 shift, u8 width, - u8 clk_divider_flags, const struct clk_div_table *table, - spinlock_t *lock); + unsigned long clk_divider_flags, + const struct clk_div_table *table, spinlock_t *lock); /** * clk_register_divider - register a divider clock with the clock framework * @dev: device registering this clock @@ -1123,6 +1160,9 @@ struct clk_hw *clk_hw_register_fixed_factor_with_accuracy_fwname(struct device * struct device_node *np, const char *name, const char *fw_name, unsigned long flags, unsigned int mult, unsigned int div, unsigned long acc); +struct clk_hw *clk_hw_register_fixed_factor_index(struct device *dev, + const char *name, unsigned int index, unsigned long flags, + unsigned int mult, unsigned int div); void clk_hw_unregister_fixed_factor(struct clk_hw *hw); struct clk_hw *devm_clk_hw_register_fixed_factor(struct device *dev, const char *name, const char *parent_name, unsigned long flags, @@ -1346,7 +1386,6 @@ unsigned long clk_hw_get_flags(const struct clk_hw *hw); (clk_hw_get_flags((hw)) & CLK_SET_RATE_PARENT) bool clk_hw_is_prepared(const struct clk_hw *hw); -bool clk_hw_rate_is_protected(const struct clk_hw *hw); bool clk_hw_is_enabled(const struct clk_hw *hw); bool __clk_is_enabled(struct clk *clk); struct clk *__clk_lookup(const char *name); diff --git a/include/linux/clk.h b/include/linux/clk.h index 0fa56d672532..b607482ca77e 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -496,11 +496,13 @@ int __must_check devm_clk_bulk_get_all(struct device *dev, struct clk_bulk_data **clks); /** - * devm_clk_bulk_get_all_enable - Get and enable all clocks of the consumer (managed) + * devm_clk_bulk_get_all_enabled - Get and enable all clocks of the consumer (managed) * @dev: device for clock "consumer" * @clks: pointer to the clk_bulk_data table of consumer * - * Returns success (0) or negative errno. + * Returns a positive value for the number of clocks obtained while the + * clock references are stored in the clk_bulk_data table in @clks field. + * Returns 0 if there're none and a negative value if something failed. * * This helper function allows drivers to get all clocks of the * consumer and enables them in one operation with management. @@ -508,8 +510,8 @@ int __must_check devm_clk_bulk_get_all(struct device *dev, * is unbound. */ -int __must_check devm_clk_bulk_get_all_enable(struct device *dev, - struct clk_bulk_data **clks); +int __must_check devm_clk_bulk_get_all_enabled(struct device *dev, + struct clk_bulk_data **clks); /** * devm_clk_get - lookup and obtain a managed reference to a clock producer. @@ -641,6 +643,32 @@ struct clk *devm_clk_get_optional_prepared(struct device *dev, const char *id); struct clk *devm_clk_get_optional_enabled(struct device *dev, const char *id); /** + * devm_clk_get_optional_enabled_with_rate - devm_clk_get_optional() + + * clk_set_rate() + + * clk_prepare_enable() + * @dev: device for clock "consumer" + * @id: clock consumer ID + * @rate: new clock rate + * + * Context: May sleep. + * + * Return: a struct clk corresponding to the clock producer, or + * valid IS_ERR() condition containing errno. The implementation + * uses @dev and @id to determine the clock consumer, and thereby + * the clock producer. If no such clk is found, it returns NULL + * which serves as a dummy clk. That's the only difference compared + * to devm_clk_get_enabled(). + * + * The returned clk (if valid) is prepared and enabled and rate was set. + * + * The clock will automatically be disabled, unprepared and freed + * when the device is unbound from the bus. + */ +struct clk *devm_clk_get_optional_enabled_with_rate(struct device *dev, + const char *id, + unsigned long rate); + +/** * devm_get_clk_from_child - lookup and obtain a managed reference to a * clock producer from child node. * @dev: device for clock "consumer" @@ -982,6 +1010,13 @@ static inline struct clk *devm_clk_get_optional_enabled(struct device *dev, return NULL; } +static inline struct clk * +devm_clk_get_optional_enabled_with_rate(struct device *dev, const char *id, + unsigned long rate) +{ + return NULL; +} + static inline int __must_check devm_clk_bulk_get(struct device *dev, int num_clks, struct clk_bulk_data *clks) { @@ -1001,7 +1036,7 @@ static inline int __must_check devm_clk_bulk_get_all(struct device *dev, return 0; } -static inline int __must_check devm_clk_bulk_get_all_enable(struct device *dev, +static inline int __must_check devm_clk_bulk_get_all_enabled(struct device *dev, struct clk_bulk_data **clks) { return 0; diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index 9aac31d856f3..b0df28ddd394 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -12,7 +12,7 @@ #ifdef CONFIG_GENERIC_CLOCKEVENTS # include <linux/clocksource.h> -# include <linux/cpumask.h> +# include <linux/cpumask_types.h> # include <linux/ktime.h> # include <linux/notifier.h> diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 0ad8b550bb4b..65b7c41471c3 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -21,6 +21,7 @@ #include <asm/div64.h> #include <asm/io.h> +struct clocksource_base; struct clocksource; struct module; @@ -48,8 +49,10 @@ struct module; * @archdata: Optional arch-specific data * @max_cycles: Maximum safe cycle value which won't overflow on * multiplication + * @max_raw_delta: Maximum safe delta value for negative motion detection * @name: Pointer to clocksource name * @list: List head for registration (internal) + * @freq_khz: Clocksource frequency in khz. * @rating: Rating value for selection (higher is better) * To avoid rating inflation the following * list should give you a guide as to how @@ -70,6 +73,8 @@ struct module; * validate the clocksource from which the snapshot was * taken. * @flags: Flags describing special properties + * @base: Hardware abstraction for clock on which a clocksource + * is based * @enable: Optional function to enable the clocksource * @disable: Optional function to disable the clocksource * @suspend: Optional suspend function for the clocksource @@ -105,12 +110,15 @@ struct clocksource { struct arch_clocksource_data archdata; #endif u64 max_cycles; + u64 max_raw_delta; const char *name; struct list_head list; + u32 freq_khz; int rating; enum clocksource_ids id; enum vdso_clock_mode vdso_clock_mode; unsigned long flags; + struct clocksource_base *base; int (*enable)(struct clocksource *cs); void (*disable)(struct clocksource *cs); @@ -209,7 +217,6 @@ static inline s64 clocksource_cyc2ns(u64 cycles, u32 mult, u32 shift) extern int clocksource_unregister(struct clocksource*); extern void clocksource_touch_watchdog(void); -extern void clocksource_change_rating(struct clocksource *cs, int rating); extern void clocksource_suspend(void); extern void clocksource_resume(void); extern struct clocksource * __init clocksource_default_clock(void); @@ -306,4 +313,25 @@ static inline unsigned int clocksource_get_max_watchdog_retry(void) void clocksource_verify_percpu(struct clocksource *cs); +/** + * struct clocksource_base - hardware abstraction for clock on which a clocksource + * is based + * @id: Defaults to CSID_GENERIC. The id value is used for conversion + * functions which require that the current clocksource is based + * on a clocksource_base with a particular ID in certain snapshot + * functions to allow callers to validate the clocksource from + * which the snapshot was taken. + * @freq_khz: Nominal frequency of the base clock in kHz + * @offset: Offset between the base clock and the clocksource + * @numerator: Numerator of the clock ratio between base clock and the clocksource + * @denominator: Denominator of the clock ratio between base clock and the clocksource + */ +struct clocksource_base { + enum clocksource_ids id; + u32 freq_khz; + u64 offset; + u32 numerator; + u32 denominator; +}; + #endif /* _LINUX_CLOCKSOURCE_H */ diff --git a/include/linux/clocksource_ids.h b/include/linux/clocksource_ids.h index a4fa3436940c..c4ef4ae2eded 100644 --- a/include/linux/clocksource_ids.h +++ b/include/linux/clocksource_ids.h @@ -6,9 +6,11 @@ enum clocksource_ids { CSID_GENERIC = 0, CSID_ARM_ARCH_COUNTER, + CSID_S390_TOD, CSID_X86_TSC_EARLY, CSID_X86_TSC, CSID_X86_KVM_CLK, + CSID_X86_ART, CSID_MAX, }; diff --git a/include/linux/closure.h b/include/linux/closure.h index c554c6a08768..880fe85e35e9 100644 --- a/include/linux/closure.h +++ b/include/linux/closure.h @@ -159,6 +159,7 @@ struct closure { #ifdef CONFIG_DEBUG_CLOSURES #define CLOSURE_MAGIC_DEAD 0xc054dead #define CLOSURE_MAGIC_ALIVE 0xc054a11e +#define CLOSURE_MAGIC_STACK 0xc05451cc unsigned int magic; struct list_head all; @@ -194,6 +195,18 @@ static inline void closure_sync(struct closure *cl) __closure_sync(cl); } +int __closure_sync_timeout(struct closure *cl, unsigned long timeout); + +static inline int closure_sync_timeout(struct closure *cl, unsigned long timeout) +{ +#ifdef CONFIG_DEBUG_CLOSURES + BUG_ON(closure_nr_remaining(cl) != 1 && !cl->closure_get_happened); +#endif + return cl->closure_get_happened + ? __closure_sync_timeout(cl, timeout) + : 0; +} + #ifdef CONFIG_DEBUG_CLOSURES void closure_debug_create(struct closure *cl); @@ -273,6 +286,21 @@ static inline void closure_get(struct closure *cl) } /** + * closure_get_not_zero + */ +static inline bool closure_get_not_zero(struct closure *cl) +{ + unsigned old = atomic_read(&cl->remaining); + do { + if (!(old & CLOSURE_REMAINING_MASK)) + return false; + + } while (!atomic_try_cmpxchg_acquire(&cl->remaining, &old, old + 1)); + + return true; +} + +/** * closure_init - Initialize a closure, setting the refcount to 1 * @cl: closure to initialize * @parent: parent of the new closure. cl will take a refcount on it for its @@ -296,6 +324,18 @@ static inline void closure_init_stack(struct closure *cl) { memset(cl, 0, sizeof(struct closure)); atomic_set(&cl->remaining, CLOSURE_REMAINING_INITIALIZER); +#ifdef CONFIG_DEBUG_CLOSURES + cl->magic = CLOSURE_MAGIC_STACK; +#endif +} + +static inline void closure_init_stack_release(struct closure *cl) +{ + memset(cl, 0, sizeof(struct closure)); + atomic_set_release(&cl->remaining, CLOSURE_REMAINING_INITIALIZER); +#ifdef CONFIG_DEBUG_CLOSURES + cl->magic = CLOSURE_MAGIC_STACK; +#endif } /** @@ -343,6 +383,8 @@ do { \ */ #define closure_return(_cl) continue_at((_cl), NULL, NULL) +void closure_return_sync(struct closure *cl); + /** * continue_at_nobarrier - jump to another function without barrier * @@ -412,4 +454,39 @@ do { \ __closure_wait_event(waitlist, _cond); \ } while (0) +#define __closure_wait_event_timeout(waitlist, _cond, _until) \ +({ \ + struct closure cl; \ + long _t; \ + \ + closure_init_stack(&cl); \ + \ + while (1) { \ + closure_wait(waitlist, &cl); \ + if (_cond) { \ + _t = max_t(long, 1L, _until - jiffies); \ + break; \ + } \ + _t = max_t(long, 0L, _until - jiffies); \ + if (!_t) \ + break; \ + closure_sync_timeout(&cl, _t); \ + } \ + closure_wake_up(waitlist); \ + closure_sync(&cl); \ + _t; \ +}) + +/* + * Returns 0 if timeout expired, remaining time in jiffies (at least 1) if + * condition became true + */ +#define closure_wait_event_timeout(waitlist, _cond, _timeout) \ +({ \ + unsigned long _until = jiffies + _timeout; \ + (_cond) \ + ? max_t(long, 1L, _until - jiffies) \ + : __closure_wait_event_timeout(waitlist, _cond, _until);\ +}) + #endif /* _LINUX_CLOSURE_H */ diff --git a/include/linux/cma.h b/include/linux/cma.h index 9db877506ea8..d15b64f51336 100644 --- a/include/linux/cma.h +++ b/include/linux/cma.h @@ -52,4 +52,20 @@ extern bool cma_release(struct cma *cma, const struct page *pages, unsigned long extern int cma_for_each_area(int (*it)(struct cma *cma, void *data), void *data); extern void cma_reserve_pages_on_error(struct cma *cma); + +#ifdef CONFIG_CMA +struct folio *cma_alloc_folio(struct cma *cma, int order, gfp_t gfp); +bool cma_free_folio(struct cma *cma, const struct folio *folio); +#else +static inline struct folio *cma_alloc_folio(struct cma *cma, int order, gfp_t gfp) +{ + return NULL; +} + +static inline bool cma_free_folio(struct cma *cma, const struct folio *folio) +{ + return false; +} +#endif + #endif diff --git a/include/linux/cmpxchg-emu.h b/include/linux/cmpxchg-emu.h new file mode 100644 index 000000000000..998deec67740 --- /dev/null +++ b/include/linux/cmpxchg-emu.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Emulated 1-byte and 2-byte cmpxchg operations for architectures + * lacking direct support for these sizes. These are implemented in terms + * of 4-byte cmpxchg operations. + * + * Copyright (C) 2024 Paul E. McKenney. + */ + +#ifndef __LINUX_CMPXCHG_EMU_H +#define __LINUX_CMPXCHG_EMU_H + +uintptr_t cmpxchg_emu_u8(volatile u8 *p, uintptr_t old, uintptr_t new); + +#endif /* __LINUX_CMPXCHG_EMU_H */ diff --git a/include/linux/codetag.h b/include/linux/codetag.h new file mode 100644 index 000000000000..d14dbd26b370 --- /dev/null +++ b/include/linux/codetag.h @@ -0,0 +1,111 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * code tagging framework + */ +#ifndef _LINUX_CODETAG_H +#define _LINUX_CODETAG_H + +#include <linux/types.h> + +struct codetag_iterator; +struct codetag_type; +struct codetag_module; +struct seq_buf; +struct module; + +#define CODETAG_SECTION_START_PREFIX "__start_" +#define CODETAG_SECTION_STOP_PREFIX "__stop_" + +/* + * An instance of this structure is created in a special ELF section at every + * code location being tagged. At runtime, the special section is treated as + * an array of these. + */ +struct codetag { + unsigned int flags; /* used in later patches */ + unsigned int lineno; + const char *modname; + const char *function; + const char *filename; +} __aligned(8); + +union codetag_ref { + struct codetag *ct; +}; + +struct codetag_type_desc { + const char *section; + size_t tag_size; + void (*module_load)(struct codetag_type *cttype, + struct codetag_module *cmod); + void (*module_unload)(struct codetag_type *cttype, + struct codetag_module *cmod); +#ifdef CONFIG_MODULES + void (*module_replaced)(struct module *mod, struct module *new_mod); + bool (*needs_section_mem)(struct module *mod, unsigned long size); + void *(*alloc_section_mem)(struct module *mod, unsigned long size, + unsigned int prepend, unsigned long align); + void (*free_section_mem)(struct module *mod, bool used); +#endif +}; + +struct codetag_iterator { + struct codetag_type *cttype; + struct codetag_module *cmod; + unsigned long mod_id; + struct codetag *ct; +}; + +#ifdef MODULE +#define CT_MODULE_NAME KBUILD_MODNAME +#else +#define CT_MODULE_NAME NULL +#endif + +#define CODE_TAG_INIT { \ + .modname = CT_MODULE_NAME, \ + .function = __func__, \ + .filename = __FILE__, \ + .lineno = __LINE__, \ + .flags = 0, \ +} + +void codetag_lock_module_list(struct codetag_type *cttype, bool lock); +bool codetag_trylock_module_list(struct codetag_type *cttype); +struct codetag_iterator codetag_get_ct_iter(struct codetag_type *cttype); +struct codetag *codetag_next_ct(struct codetag_iterator *iter); + +void codetag_to_text(struct seq_buf *out, struct codetag *ct); + +struct codetag_type * +codetag_register_type(const struct codetag_type_desc *desc); + +#if defined(CONFIG_CODE_TAGGING) && defined(CONFIG_MODULES) + +bool codetag_needs_module_section(struct module *mod, const char *name, + unsigned long size); +void *codetag_alloc_module_section(struct module *mod, const char *name, + unsigned long size, unsigned int prepend, + unsigned long align); +void codetag_free_module_sections(struct module *mod); +void codetag_module_replaced(struct module *mod, struct module *new_mod); +void codetag_load_module(struct module *mod); +void codetag_unload_module(struct module *mod); + +#else /* defined(CONFIG_CODE_TAGGING) && defined(CONFIG_MODULES) */ + +static inline bool +codetag_needs_module_section(struct module *mod, const char *name, + unsigned long size) { return false; } +static inline void * +codetag_alloc_module_section(struct module *mod, const char *name, + unsigned long size, unsigned int prepend, + unsigned long align) { return NULL; } +static inline void codetag_free_module_sections(struct module *mod) {} +static inline void codetag_module_replaced(struct module *mod, struct module *new_mod) {} +static inline void codetag_load_module(struct module *mod) {} +static inline void codetag_unload_module(struct module *mod) {} + +#endif /* defined(CONFIG_CODE_TAGGING) && defined(CONFIG_MODULES) */ + +#endif /* _LINUX_CODETAG_H */ diff --git a/include/linux/compat.h b/include/linux/compat.h index 233f61ec8afc..56cebaff0c91 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -608,7 +608,7 @@ asmlinkage long compat_sys_fstatfs(unsigned int fd, asmlinkage long compat_sys_fstatfs64(unsigned int fd, compat_size_t sz, struct compat_statfs64 __user *buf); asmlinkage long compat_sys_truncate(const char __user *, compat_off_t); -asmlinkage long compat_sys_ftruncate(unsigned int, compat_ulong_t); +asmlinkage long compat_sys_ftruncate(unsigned int, compat_off_t); /* No generic prototype for truncate64, ftruncate64, fallocate */ asmlinkage long compat_sys_openat(int dfd, const char __user *filename, int flags, umode_t mode); diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index 49feac0162a5..2e7c2c282f3a 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_COMPILER_TYPES_H -#error "Please don't include <linux/compiler-clang.h> directly, include <linux/compiler.h> instead." +#error "Please do not include <linux/compiler-clang.h> directly, include <linux/compiler.h> instead." #endif /* Compiler specific definitions for Clang compiler */ @@ -118,3 +118,13 @@ #define __diag_ignore_all(option, comment) \ __diag_clang(13, ignore, option) + +/* + * clang has horrible behavior with "g" or "rm" constraints for asm + * inputs, turning them into something worse than "m". Avoid using + * constraints with multiple possible uses (but "ir" seems to be ok): + * + * https://github.com/llvm/llvm-project/issues/20571 + */ +#define ASM_INPUT_G "ir" +#define ASM_INPUT_RM "r" diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index aff92b1d284f..c9b58188ec61 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_COMPILER_TYPES_H -#error "Please don't include <linux/compiler-gcc.h> directly, include <linux/compiler.h> instead." +#error "Please do not include <linux/compiler-gcc.h> directly, include <linux/compiler.h> instead." #endif /* @@ -52,38 +52,6 @@ */ #define barrier_before_unreachable() asm volatile("") -/* - * Mark a position in code as unreachable. This can be used to - * suppress control flow warnings after asm blocks that transfer - * control elsewhere. - */ -#define unreachable() \ - do { \ - annotate_unreachable(); \ - barrier_before_unreachable(); \ - __builtin_unreachable(); \ - } while (0) - -/* - * GCC 'asm goto' with outputs miscompiles certain code sequences: - * - * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=113921 - * - * Work around it via the same compiler barrier quirk that we used - * to use for the old 'asm goto' workaround. - * - * Also, always mark such 'asm goto' statements as volatile: all - * asm goto statements are supposed to be volatile as per the - * documentation, but some versions of gcc didn't actually do - * that for asms with outputs: - * - * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=98619 - */ -#ifdef CONFIG_GCC_ASM_GOTO_OUTPUT_WORKAROUND -#define asm_goto_output(x...) \ - do { asm volatile goto(x); asm (""); } while (0) -#endif - #if defined(CONFIG_ARCH_USE_BUILTIN_BSWAP) #define __HAVE_BUILTIN_BSWAP32__ #define __HAVE_BUILTIN_BSWAP64__ @@ -100,7 +68,11 @@ #define __noscs __attribute__((__no_sanitize__("shadow-call-stack"))) #endif +#ifdef __SANITIZE_HWADDRESS__ +#define __no_sanitize_address __attribute__((__no_sanitize__("hwaddress"))) +#else #define __no_sanitize_address __attribute__((__no_sanitize_address__)) +#endif #if defined(__SANITIZE_THREAD__) #define __no_sanitize_thread __attribute__((__no_sanitize_thread__)) diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 8c252e073bd8..b087de2f3e94 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -109,44 +109,21 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, /* Unreachable code */ #ifdef CONFIG_OBJTOOL -/* - * These macros help objtool understand GCC code flow for unreachable code. - * The __COUNTER__ based labels are a hack to make each instance of the macros - * unique, to convince GCC not to merge duplicate inline asm statements. - */ -#define __stringify_label(n) #n - -#define __annotate_reachable(c) ({ \ - asm volatile(__stringify_label(c) ":\n\t" \ - ".pushsection .discard.reachable\n\t" \ - ".long " __stringify_label(c) "b - .\n\t" \ - ".popsection\n\t"); \ -}) -#define annotate_reachable() __annotate_reachable(__COUNTER__) - -#define __annotate_unreachable(c) ({ \ - asm volatile(__stringify_label(c) ":\n\t" \ - ".pushsection .discard.unreachable\n\t" \ - ".long " __stringify_label(c) "b - .\n\t" \ - ".popsection\n\t" : : "i" (c)); \ -}) -#define annotate_unreachable() __annotate_unreachable(__COUNTER__) - /* Annotate a C jump table to allow objtool to follow the code flow */ -#define __annotate_jump_table __section(".rodata..c_jump_table") - +#define __annotate_jump_table __section(".rodata..c_jump_table,\"a\",@progbits #") #else /* !CONFIG_OBJTOOL */ -#define annotate_reachable() -#define annotate_unreachable() #define __annotate_jump_table #endif /* CONFIG_OBJTOOL */ -#ifndef unreachable -# define unreachable() do { \ - annotate_unreachable(); \ +/* + * Mark a position in code as unreachable. This can be used to + * suppress control flow warnings after asm blocks that transfer + * control elsewhere. + */ +#define unreachable() do { \ + barrier_before_unreachable(); \ __builtin_unreachable(); \ } while (0) -#endif /* * KENTRY - kernel entry point @@ -194,47 +171,78 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, * This data_race() macro is useful for situations in which data races * should be forgiven. One example is diagnostic code that accesses * shared variables but is not a part of the core synchronization design. + * For example, if accesses to a given variable are protected by a lock, + * except for diagnostic code, then the accesses under the lock should + * be plain C-language accesses and those in the diagnostic code should + * use data_race(). This way, KCSAN will complain if buggy lockless + * accesses to that variable are introduced, even if the buggy accesses + * are protected by READ_ONCE() or WRITE_ONCE(). * * This macro *does not* affect normal code generation, but is a hint - * to tooling that data races here are to be ignored. + * to tooling that data races here are to be ignored. If the access must + * be atomic *and* KCSAN should ignore the access, use both data_race() + * and READ_ONCE(), for example, data_race(READ_ONCE(x)). */ #define data_race(expr) \ ({ \ - __unqual_scalar_typeof(({ expr; })) __v = ({ \ - __kcsan_disable_current(); \ - expr; \ - }); \ + __kcsan_disable_current(); \ + __auto_type __v = (expr); \ __kcsan_enable_current(); \ __v; \ }) #endif /* __KERNEL__ */ +/** + * offset_to_ptr - convert a relative memory offset to an absolute pointer + * @off: the address of the 32-bit offset value + */ +static inline void *offset_to_ptr(const int *off) +{ + return (void *)((unsigned long)off + *off); +} + +#endif /* __ASSEMBLY__ */ + +#ifdef CONFIG_64BIT +#define ARCH_SEL(a,b) a +#else +#define ARCH_SEL(a,b) b +#endif + /* * Force the compiler to emit 'sym' as a symbol, so that we can reference * it from inline assembler. Necessary in case 'sym' could be inlined * otherwise, or eliminated entirely due to lack of references that are * visible to the compiler. */ -#define ___ADDRESSABLE(sym, __attrs) \ - static void * __used __attrs \ +#define ___ADDRESSABLE(sym, __attrs) \ + static void * __used __attrs \ __UNIQUE_ID(__PASTE(__addressable_,sym)) = (void *)(uintptr_t)&sym; + #define __ADDRESSABLE(sym) \ ___ADDRESSABLE(sym, __section(".discard.addressable")) -/** - * offset_to_ptr - convert a relative memory offset to an absolute pointer - * @off: the address of the 32-bit offset value - */ -static inline void *offset_to_ptr(const int *off) -{ - return (void *)((unsigned long)off + *off); -} +#define __ADDRESSABLE_ASM(sym) \ + .pushsection .discard.addressable,"aw"; \ + .align ARCH_SEL(8,4); \ + ARCH_SEL(.quad, .long) __stringify(sym); \ + .popsection; -#endif /* __ASSEMBLY__ */ +#define __ADDRESSABLE_ASM_STR(sym) __stringify(__ADDRESSABLE_ASM(sym)) + +#ifdef __CHECKER__ +#define __BUILD_BUG_ON_ZERO_MSG(e, msg) (0) +#else /* __CHECKER__ */ +#define __BUILD_BUG_ON_ZERO_MSG(e, msg) ((int)sizeof(struct {_Static_assert(!(e), msg);})) +#endif /* __CHECKER__ */ /* &a[0] degrades to a pointer: a different type from an array */ -#define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) +#define __must_be_array(a) __BUILD_BUG_ON_ZERO_MSG(__same_type((a), &(a)[0]), "must be array") + +/* Require C Strings (i.e. NUL-terminated) lack the "nonstring" attribute. */ +#define __must_be_cstr(p) \ + __BUILD_BUG_ON_ZERO_MSG(__annotated(p, nonstring), "must be cstr (NUL-terminated)") /* * This returns a constant expression while determining if an argument is @@ -291,6 +299,37 @@ static inline void *offset_to_ptr(const int *off) #define is_unsigned_type(type) (!is_signed_type(type)) /* + * Useful shorthand for "is this condition known at compile-time?" + * + * Note that the condition may involve non-constant values, + * but the compiler may know enough about the details of the + * values to determine that the condition is statically true. + */ +#define statically_true(x) (__builtin_constant_p(x) && (x)) + +/* + * Similar to statically_true() but produces a constant expression + * + * To be used in conjunction with macros, such as BUILD_BUG_ON_ZERO(), + * which require their input to be a constant expression and for which + * statically_true() would otherwise fail. + * + * This is a trade-off: const_true() requires all its operands to be + * compile time constants. Else, it would always returns false even on + * the most trivial cases like: + * + * true || non_const_var + * + * On the opposite, statically_true() is able to fold more complex + * tautologies and will return true on expressions such as: + * + * !(non_const_var * 8 % 4) + * + * For the general case, statically_true() is better. + */ +#define const_true(x) __builtin_choose_expr(__is_constexpr(x), x, false) + +/* * This is needed in functions which generate the stack canary, see * arch/x86/kernel/smpboot.c::start_secondary() for an example. */ diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index 8bdf6e0918c1..c16d4199bf92 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -95,19 +95,6 @@ #endif /* - * Optional: only supported since gcc >= 15 - * Optional: only supported since clang >= 18 - * - * gcc: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=108896 - * clang: https://github.com/llvm/llvm-project/pull/76348 - */ -#if __has_attribute(__counted_by__) -# define __counted_by(member) __attribute__((__counted_by__(member))) -#else -# define __counted_by(member) -#endif - -/* * Optional: not supported by gcc * Optional: only supported since clang >= 14.0 * @@ -362,6 +349,19 @@ #define __used __attribute__((__used__)) /* + * The __used attribute guarantees that the attributed variable will be + * always emitted by a compiler. It doesn't prevent the compiler from + * throwing 'unused' warnings when it can't detect how the variable is + * actually used. It's a compiler implementation details either emit + * the warning in that case or not. + * + * The combination of both 'used' and 'unused' attributes ensures that + * the variable would be emitted, and will not trigger 'unused' warnings. + * The attribute is applicable for functions, static and global variables. + */ +#define __always_used __used __maybe_unused + +/* * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-warn_005funused_005fresult-function-attribute * clang: https://clang.llvm.org/docs/AttributeReference.html#nodiscard-warn-unused-result */ diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 2abaa3a825a9..981cc3d7e3aa 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -143,6 +143,29 @@ static inline void __chk_io_ptr(const volatile void __iomem *ptr) { } # define __preserve_most #endif +/* + * Annotating a function/variable with __retain tells the compiler to place + * the object in its own section and set the flag SHF_GNU_RETAIN. This flag + * instructs the linker to retain the object during garbage-cleanup or LTO + * phases. + * + * Note that the __used macro is also used to prevent functions or data + * being optimized out, but operates at the compiler/IR-level and may still + * allow unintended removal of objects during linking. + * + * Optional: only supported since gcc >= 11, clang >= 13 + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-retain-function-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#retain + */ +#if __has_attribute(__retain__) && \ + (defined(CONFIG_LD_DEAD_CODE_DATA_ELIMINATION) || \ + defined(CONFIG_LTO_CLANG)) +# define __retain __attribute__((__retain__)) +#else +# define __retain +#endif + /* Compiler specific macros. */ #ifdef __clang__ #include <linux/compiler-clang.h> @@ -243,6 +266,12 @@ struct ftrace_likely_data { #define noinline_for_stack noinline /* + * Use noinline_for_tracing for functions that should not be inlined. + * For tracing reasons. + */ +#define noinline_for_tracing noinline + +/* * Sanitizer helper attributes: Because using __always_inline and * __no_sanitize_* conflict, provide helper attributes that will either expand * to __no_sanitize_* in compilation units where instrumentation is enabled @@ -273,15 +302,63 @@ struct ftrace_likely_data { * disable all instrumentation. See Kconfig.kcsan where this is mandatory. */ # define __no_kcsan __no_sanitize_thread __disable_sanitizer_instrumentation +/* + * Type qualifier to mark variables where all data-racy accesses should be + * ignored by KCSAN. Note, the implementation simply marks these variables as + * volatile, since KCSAN will treat such accesses as "marked". + */ +# define __data_racy volatile # define __no_sanitize_or_inline __no_kcsan notrace __maybe_unused #else # define __no_kcsan +# define __data_racy +#endif + +#ifdef __SANITIZE_MEMORY__ +/* + * Similarly to KASAN and KCSAN, KMSAN loses function attributes of inlined + * functions, therefore disabling KMSAN checks also requires disabling inlining. + * + * __no_sanitize_or_inline effectively prevents KMSAN from reporting errors + * within the function and marks all its outputs as initialized. + */ +# define __no_sanitize_or_inline __no_kmsan_checks notrace __maybe_unused #endif #ifndef __no_sanitize_or_inline #define __no_sanitize_or_inline __always_inline #endif +/* + * Optional: only supported since gcc >= 15 + * Optional: only supported since clang >= 18 + * + * gcc: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=108896 + * clang: https://github.com/llvm/llvm-project/pull/76348 + * + * __bdos on clang < 19.1.2 can erroneously return 0: + * https://github.com/llvm/llvm-project/pull/110497 + * + * __bdos on clang < 19.1.3 can be off by 4: + * https://github.com/llvm/llvm-project/pull/112636 + */ +#ifdef CONFIG_CC_HAS_COUNTED_BY +# define __counted_by(member) __attribute__((__counted_by__(member))) +#else +# define __counted_by(member) +#endif + +/* + * Apply __counted_by() when the Endianness matches to increase test coverage. + */ +#ifdef __LITTLE_ENDIAN +#define __counted_by_le(member) __counted_by(member) +#define __counted_by_be(member) +#else +#define __counted_by_le(member) +#define __counted_by_be(member) __counted_by(member) +#endif + /* Do not trap wrapping arithmetic within an annotated function. */ #ifdef CONFIG_UBSAN_SIGNED_WRAP # define __signed_wrap __attribute__((no_sanitize("signed-integer-overflow"))) @@ -369,6 +446,13 @@ struct ftrace_likely_data { #define __member_size(p) __builtin_object_size(p, 1) #endif +/* Determine if an attribute has been applied to a variable. */ +#if __has_builtin(__builtin_has_attribute) +#define __annotated(var, attr) __builtin_has_attribute(var, attr) +#else +#define __annotated(var, attr) (false) +#endif + /* * Some versions of gcc do not mark 'asm goto' volatile: * @@ -380,6 +464,15 @@ struct ftrace_likely_data { #define asm_goto_output(x...) asm volatile goto(x) #endif +/* + * Clang has trouble with constraints with multiple + * alternative behaviors (mainly "g" and "rm"). + */ +#ifndef ASM_INPUT_G + #define ASM_INPUT_G "g" + #define ASM_INPUT_RM "rm" +#endif + #ifdef CONFIG_CC_HAS_ASM_INLINE #define asm_inline asm __inline #else diff --git a/include/linux/configfs.h b/include/linux/configfs.h index 2606711adb18..c771e9d0d0b9 100644 --- a/include/linux/configfs.h +++ b/include/linux/configfs.h @@ -216,6 +216,9 @@ struct configfs_group_operations { struct config_group *(*make_group)(struct config_group *group, const char *name); void (*disconnect_notify)(struct config_group *group, struct config_item *item); void (*drop_item)(struct config_group *group, struct config_item *item); + bool (*is_visible)(struct config_item *item, struct configfs_attribute *attr, int n); + bool (*is_bin_visible)(struct config_item *item, struct configfs_bin_attribute *attr, + int n); }; struct configfs_subsystem { diff --git a/include/linux/console.h b/include/linux/console.h index 31a8f5b85f5d..eba367bf605d 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -16,7 +16,9 @@ #include <linux/atomic.h> #include <linux/bits.h> +#include <linux/irq_work.h> #include <linux/rculist.h> +#include <linux/rcuwait.h> #include <linux/types.h> #include <linux/vesa.h> @@ -303,7 +305,7 @@ struct nbcon_write_context { /** * struct console - The console descriptor structure * @name: The name of the console driver - * @write: Write callback to output messages (Optional) + * @write: Legacy 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) @@ -320,10 +322,14 @@ struct nbcon_write_context { * @data: Driver private data * @node: hlist node for the console list * - * @write_atomic: Write callback for atomic context * @nbcon_state: State for nbcon consoles * @nbcon_seq: Sequence number of the next record for nbcon to print + * @nbcon_device_ctxt: Context available for non-printing operations + * @nbcon_prev_seq: Seq num the previous nbcon owner was assigned to print * @pbufs: Pointer to nbcon private buffer + * @kthread: Printer kthread for this console + * @rcuwait: RCU-safe wait object for @kthread waking + * @irq_work: Defer @kthread waking to IRQ work context */ struct console { char name[16]; @@ -345,11 +351,121 @@ struct console { struct hlist_node node; /* nbcon console specific members */ - bool (*write_atomic)(struct console *con, - struct nbcon_write_context *wctxt); + + /** + * @write_atomic: + * + * NBCON callback to write out text in any context. (Optional) + * + * This callback is called with the console already acquired. However, + * a higher priority context is allowed to take it over by default. + * + * The callback must call nbcon_enter_unsafe() and nbcon_exit_unsafe() + * around any code where the takeover is not safe, for example, when + * manipulating the serial port registers. + * + * nbcon_enter_unsafe() will fail if the context has lost the console + * ownership in the meantime. In this case, the callback is no longer + * allowed to go forward. It must back out immediately and carefully. + * The buffer content is also no longer trusted since it no longer + * belongs to the context. + * + * The callback should allow the takeover whenever it is safe. It + * increases the chance to see messages when the system is in trouble. + * If the driver must reacquire ownership in order to finalize or + * revert hardware changes, nbcon_reacquire_nobuf() can be used. + * However, on reacquire the buffer content is no longer available. A + * reacquire cannot be used to resume printing. + * + * The callback can be called from any context (including NMI). + * Therefore it must avoid usage of any locking and instead rely + * on the console ownership for synchronization. + */ + void (*write_atomic)(struct console *con, struct nbcon_write_context *wctxt); + + /** + * @write_thread: + * + * NBCON callback to write out text in task context. + * + * This callback must be called only in task context with both + * device_lock() and the nbcon console acquired with + * NBCON_PRIO_NORMAL. + * + * The same rules for console ownership verification and unsafe + * sections handling applies as with write_atomic(). + * + * The console ownership handling is necessary for synchronization + * against write_atomic() which is synchronized only via the context. + * + * The device_lock() provides the primary serialization for operations + * on the device. It might be as relaxed (mutex)[*] or as tight + * (disabled preemption and interrupts) as needed. It allows + * the kthread to operate in the least restrictive mode[**]. + * + * [*] Standalone nbcon_context_try_acquire() is not safe with + * the preemption enabled, see nbcon_owner_matches(). But it + * can be safe when always called in the preemptive context + * under the device_lock(). + * + * [**] The device_lock() makes sure that nbcon_context_try_acquire() + * would never need to spin which is important especially with + * PREEMPT_RT. + */ + void (*write_thread)(struct console *con, struct nbcon_write_context *wctxt); + + /** + * @device_lock: + * + * NBCON callback to begin synchronization with driver code. + * + * Console drivers typically must deal with access to the hardware + * via user input/output (such as an interactive login shell) and + * output of kernel messages via printk() calls. This callback is + * called by the printk-subsystem whenever it needs to synchronize + * with hardware access by the driver. It should be implemented to + * use whatever synchronization mechanism the driver is using for + * itself (for example, the port lock for uart serial consoles). + * + * The callback is always called from task context. It may use any + * synchronization method required by the driver. + * + * IMPORTANT: The callback MUST disable migration. The console driver + * may be using a synchronization mechanism that already takes + * care of this (such as spinlocks). Otherwise this function must + * explicitly call migrate_disable(). + * + * The flags argument is provided as a convenience to the driver. It + * will be passed again to device_unlock(). It can be ignored if the + * driver does not need it. + */ + void (*device_lock)(struct console *con, unsigned long *flags); + + /** + * @device_unlock: + * + * NBCON callback to finish synchronization with driver code. + * + * It is the counterpart to device_lock(). + * + * This callback is always called from task context. It must + * appropriately re-enable migration (depending on how device_lock() + * disabled migration). + * + * The flags argument is the value of the same variable that was + * passed to device_lock(). + */ + void (*device_unlock)(struct console *con, unsigned long flags); + atomic_t __private nbcon_state; atomic_long_t __private nbcon_seq; + struct nbcon_context __private nbcon_device_ctxt; + atomic_long_t __private nbcon_prev_seq; + struct printk_buffers *pbufs; + struct task_struct *kthread; + struct rcuwait rcuwait; + struct irq_work irq_work; }; #ifdef CONFIG_LOCKDEP @@ -378,28 +494,34 @@ extern void console_list_unlock(void) __releases(console_mutex); extern struct hlist_head console_list; /** - * console_srcu_read_flags - Locklessly read the console flags + * console_srcu_read_flags - Locklessly read flags of a possibly registered + * console * @con: struct console pointer of console to read flags from * - * This function provides the necessary READ_ONCE() and data_race() - * notation for locklessly reading the console flags. The READ_ONCE() - * in this function matches the WRITE_ONCE() when @flags are modified - * for registered consoles with console_srcu_write_flags(). + * Locklessly reading @con->flags provides a consistent read value because + * there is at most one CPU modifying @con->flags and that CPU is using only + * read-modify-write operations to do so. + * + * Requires console_srcu_read_lock to be held, which implies that @con might + * be a registered console. The purpose of holding console_srcu_read_lock is + * to guarantee that the console state is valid (CON_SUSPENDED/CON_ENABLED) + * and that no exit/cleanup routines will run if the console is currently + * undergoing unregistration. * - * Only use this function to read console flags when locklessly - * iterating the console list via srcu. + * If the caller is holding the console_list_lock or it is _certain_ that + * @con is not and will not become registered, the caller may read + * @con->flags directly instead. * * Context: Any context. + * Return: The current value of the @con->flags field. */ static inline short console_srcu_read_flags(const struct console *con) { WARN_ON_ONCE(!console_srcu_read_lock_is_held()); /* - * Locklessly reading console->flags provides a consistent - * read value because there is at most one CPU modifying - * console->flags and that CPU is using only read-modify-write - * operations to do so. + * The READ_ONCE() matches the WRITE_ONCE() when @flags are modified + * for registered consoles with console_srcu_write_flags(). */ return data_race(READ_ONCE(con->flags)); } @@ -477,13 +599,19 @@ static inline bool console_is_registered(const struct console *con) hlist_for_each_entry(con, &console_list, node) #ifdef CONFIG_PRINTK +extern void nbcon_cpu_emergency_enter(void); +extern void nbcon_cpu_emergency_exit(void); extern bool nbcon_can_proceed(struct nbcon_write_context *wctxt); extern bool nbcon_enter_unsafe(struct nbcon_write_context *wctxt); extern bool nbcon_exit_unsafe(struct nbcon_write_context *wctxt); +extern void nbcon_reacquire_nobuf(struct nbcon_write_context *wctxt); #else +static inline void nbcon_cpu_emergency_enter(void) { } +static inline void nbcon_cpu_emergency_exit(void) { } static inline bool nbcon_can_proceed(struct nbcon_write_context *wctxt) { return false; } static inline bool nbcon_enter_unsafe(struct nbcon_write_context *wctxt) { return false; } static inline bool nbcon_exit_unsafe(struct nbcon_write_context *wctxt) { return false; } +static inline void nbcon_reacquire_nobuf(struct nbcon_write_context *wctxt) { } #endif extern int console_set_on_cmdline; diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index 6e76b9dba00e..af9fe87a0922 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -26,26 +26,26 @@ extern void user_exit_callable(void); static inline void user_enter(void) { if (context_tracking_enabled()) - ct_user_enter(CONTEXT_USER); + ct_user_enter(CT_STATE_USER); } static inline void user_exit(void) { if (context_tracking_enabled()) - ct_user_exit(CONTEXT_USER); + ct_user_exit(CT_STATE_USER); } /* Called with interrupts disabled. */ static __always_inline void user_enter_irqoff(void) { if (context_tracking_enabled()) - __ct_user_enter(CONTEXT_USER); + __ct_user_enter(CT_STATE_USER); } static __always_inline void user_exit_irqoff(void) { if (context_tracking_enabled()) - __ct_user_exit(CONTEXT_USER); + __ct_user_exit(CT_STATE_USER); } static inline enum ctx_state exception_enter(void) @@ -57,7 +57,7 @@ static inline enum ctx_state exception_enter(void) return 0; prev_ctx = __ct_state(); - if (prev_ctx != CONTEXT_KERNEL) + if (prev_ctx != CT_STATE_KERNEL) ct_user_exit(prev_ctx); return prev_ctx; @@ -67,7 +67,7 @@ static inline void exception_exit(enum ctx_state prev_ctx) { if (!IS_ENABLED(CONFIG_HAVE_CONTEXT_TRACKING_USER_OFFSTACK) && context_tracking_enabled()) { - if (prev_ctx != CONTEXT_KERNEL) + if (prev_ctx != CT_STATE_KERNEL) ct_user_enter(prev_ctx); } } @@ -75,15 +75,17 @@ static inline void exception_exit(enum ctx_state prev_ctx) static __always_inline bool context_tracking_guest_enter(void) { if (context_tracking_enabled()) - __ct_user_enter(CONTEXT_GUEST); + __ct_user_enter(CT_STATE_GUEST); return context_tracking_enabled_this_cpu(); } -static __always_inline void context_tracking_guest_exit(void) +static __always_inline bool context_tracking_guest_exit(void) { if (context_tracking_enabled()) - __ct_user_exit(CONTEXT_GUEST); + __ct_user_exit(CT_STATE_GUEST); + + return context_tracking_enabled_this_cpu(); } #define CT_WARN_ON(cond) WARN_ON(context_tracking_enabled() && (cond)) @@ -98,7 +100,7 @@ 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 __always_inline void context_tracking_guest_exit(void) { } +static __always_inline bool context_tracking_guest_exit(void) { return false; } #define CT_WARN_ON(cond) do { } while (0) #endif /* !CONFIG_CONTEXT_TRACKING_USER */ @@ -113,13 +115,17 @@ extern void ct_idle_enter(void); extern void ct_idle_exit(void); /* - * Is the current CPU in an extended quiescent state? + * Is RCU watching the current CPU (IOW, it is not in an extended quiescent state)? + * + * Note that this returns the actual boolean data (watching / not watching), + * whereas ct_rcu_watching() returns the RCU_WATCHING subvariable of + * context_tracking.state. * * No ordering, as we are sampling CPU-local information. */ -static __always_inline bool rcu_dynticks_curr_cpu_in_eqs(void) +static __always_inline bool rcu_is_watching_curr_cpu(void) { - return !(raw_atomic_read(this_cpu_ptr(&context_tracking.state)) & RCU_DYNTICKS_IDX); + return raw_atomic_read(this_cpu_ptr(&context_tracking.state)) & CT_RCU_WATCHING; } /* @@ -140,9 +146,9 @@ static __always_inline bool warn_rcu_enter(void) * lots of the actual reporting also relies on RCU. */ preempt_disable_notrace(); - if (rcu_dynticks_curr_cpu_in_eqs()) { + if (!rcu_is_watching_curr_cpu()) { ret = true; - ct_state_inc(RCU_DYNTICKS_IDX); + ct_state_inc(CT_RCU_WATCHING); } return ret; @@ -151,7 +157,7 @@ static __always_inline bool warn_rcu_enter(void) static __always_inline void warn_rcu_exit(bool rcu) { if (rcu) - ct_state_inc(RCU_DYNTICKS_IDX); + ct_state_inc(CT_RCU_WATCHING); preempt_enable_notrace(); } diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h index bbff5f7f8803..7b8433d5a8ef 100644 --- a/include/linux/context_tracking_state.h +++ b/include/linux/context_tracking_state.h @@ -7,22 +7,22 @@ #include <linux/context_tracking_irq.h> /* Offset to allow distinguishing irq vs. task-based idle entry/exit. */ -#define DYNTICK_IRQ_NONIDLE ((LONG_MAX / 2) + 1) +#define CT_NESTING_IRQ_NONIDLE ((LONG_MAX / 2) + 1) enum ctx_state { - CONTEXT_DISABLED = -1, /* returned by ct_state() if unknown */ - CONTEXT_KERNEL = 0, - CONTEXT_IDLE = 1, - CONTEXT_USER = 2, - CONTEXT_GUEST = 3, - CONTEXT_MAX = 4, + CT_STATE_DISABLED = -1, /* returned by ct_state() if unknown */ + CT_STATE_KERNEL = 0, + CT_STATE_IDLE = 1, + CT_STATE_USER = 2, + CT_STATE_GUEST = 3, + CT_STATE_MAX = 4, }; -/* Even value for idle, else odd. */ -#define RCU_DYNTICKS_IDX CONTEXT_MAX +/* Odd value for watching, else even. */ +#define CT_RCU_WATCHING CT_STATE_MAX -#define CT_STATE_MASK (CONTEXT_MAX - 1) -#define CT_DYNTICKS_MASK (~CT_STATE_MASK) +#define CT_STATE_MASK (CT_STATE_MAX - 1) +#define CT_RCU_WATCHING_MASK (~CT_STATE_MASK) struct context_tracking { #ifdef CONFIG_CONTEXT_TRACKING_USER @@ -39,8 +39,8 @@ struct context_tracking { atomic_t state; #endif #ifdef CONFIG_CONTEXT_TRACKING_IDLE - long dynticks_nesting; /* Track process nesting level. */ - long dynticks_nmi_nesting; /* Track irq/NMI nesting level. */ + long nesting; /* Track process nesting level. */ + long nmi_nesting; /* Track irq/NMI nesting level. */ #endif }; @@ -56,47 +56,47 @@ static __always_inline int __ct_state(void) #endif #ifdef CONFIG_CONTEXT_TRACKING_IDLE -static __always_inline int ct_dynticks(void) +static __always_inline int ct_rcu_watching(void) { - return atomic_read(this_cpu_ptr(&context_tracking.state)) & CT_DYNTICKS_MASK; + return atomic_read(this_cpu_ptr(&context_tracking.state)) & CT_RCU_WATCHING_MASK; } -static __always_inline int ct_dynticks_cpu(int cpu) +static __always_inline int ct_rcu_watching_cpu(int cpu) { struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu); - return atomic_read(&ct->state) & CT_DYNTICKS_MASK; + return atomic_read(&ct->state) & CT_RCU_WATCHING_MASK; } -static __always_inline int ct_dynticks_cpu_acquire(int cpu) +static __always_inline int ct_rcu_watching_cpu_acquire(int cpu) { struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu); - return atomic_read_acquire(&ct->state) & CT_DYNTICKS_MASK; + return atomic_read_acquire(&ct->state) & CT_RCU_WATCHING_MASK; } -static __always_inline long ct_dynticks_nesting(void) +static __always_inline long ct_nesting(void) { - return __this_cpu_read(context_tracking.dynticks_nesting); + return __this_cpu_read(context_tracking.nesting); } -static __always_inline long ct_dynticks_nesting_cpu(int cpu) +static __always_inline long ct_nesting_cpu(int cpu) { struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu); - return ct->dynticks_nesting; + return ct->nesting; } -static __always_inline long ct_dynticks_nmi_nesting(void) +static __always_inline long ct_nmi_nesting(void) { - return __this_cpu_read(context_tracking.dynticks_nmi_nesting); + return __this_cpu_read(context_tracking.nmi_nesting); } -static __always_inline long ct_dynticks_nmi_nesting_cpu(int cpu) +static __always_inline long ct_nmi_nesting_cpu(int cpu) { struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu); - return ct->dynticks_nmi_nesting; + return ct->nmi_nesting; } #endif /* #ifdef CONFIG_CONTEXT_TRACKING_IDLE */ @@ -113,7 +113,7 @@ static __always_inline bool context_tracking_enabled_cpu(int cpu) return context_tracking_enabled() && per_cpu(context_tracking.active, cpu); } -static inline bool context_tracking_enabled_this_cpu(void) +static __always_inline bool context_tracking_enabled_this_cpu(void) { return context_tracking_enabled() && __this_cpu_read(context_tracking.active); } @@ -123,14 +123,14 @@ static inline bool context_tracking_enabled_this_cpu(void) * * Returns the current cpu's context tracking state if context tracking * is enabled. If context tracking is disabled, returns - * CONTEXT_DISABLED. This should be used primarily for debugging. + * CT_STATE_DISABLED. This should be used primarily for debugging. */ static __always_inline int ct_state(void) { int ret; if (!context_tracking_enabled()) - return CONTEXT_DISABLED; + return CT_STATE_DISABLED; preempt_disable(); ret = __ct_state(); diff --git a/include/linux/coredump.h b/include/linux/coredump.h index d3eba4360150..77e6e195d1d6 100644 --- a/include/linux/coredump.h +++ b/include/linux/coredump.h @@ -30,6 +30,8 @@ struct coredump_params { struct core_vma_metadata *vma_meta; }; +extern unsigned int core_file_note_size_limit; + /* * These are the only things you should do on a core-file: use only these * functions to write out all the necessary info. @@ -41,8 +43,30 @@ extern int dump_align(struct coredump_params *cprm, int align); int dump_user_range(struct coredump_params *cprm, unsigned long start, unsigned long len); extern void do_coredump(const kernel_siginfo_t *siginfo); + +/* + * Logging for the coredump code, ratelimited. + * The TGID and comm fields are added to the message. + */ + +#define __COREDUMP_PRINTK(Level, Format, ...) \ + do { \ + char comm[TASK_COMM_LEN]; \ + /* This will always be NUL terminated. */ \ + memcpy(comm, current->comm, sizeof(comm)); \ + printk_ratelimited(Level "coredump: %d(%*pE): " Format "\n", \ + task_tgid_vnr(current), (int)strlen(comm), comm, ##__VA_ARGS__); \ + } while (0) \ + +#define coredump_report(fmt, ...) __COREDUMP_PRINTK(KERN_INFO, fmt, ##__VA_ARGS__) +#define coredump_report_failure(fmt, ...) __COREDUMP_PRINTK(KERN_WARNING, fmt, ##__VA_ARGS__) + #else static inline void do_coredump(const kernel_siginfo_t *siginfo) {} + +#define coredump_report(...) +#define coredump_report_failure(...) + #endif #if defined(CONFIG_COREDUMP) && defined(CONFIG_SYSCTL) diff --git a/include/linux/coresight-pmu.h b/include/linux/coresight-pmu.h index 51ac441a37c3..89b0ac0014b0 100644 --- a/include/linux/coresight-pmu.h +++ b/include/linux/coresight-pmu.h @@ -49,12 +49,21 @@ * 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 + * [39:08] - Sink ID - as reported in /sys/bus/event_source/devices/cs_etm/sinks/ + * Added in minor version 1. + * [55:40] - Unused (SBZ) + * [59:56] - Minor Version - previously existing fields are compatible with + * all minor versions. + * [63:60] - Major Version - previously existing fields mean different things + * in new major versions. */ #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_SINK_ID_MASK GENMASK_ULL(39, 8) -#define CS_AUX_HW_ID_CURR_VERSION 0 +#define CS_AUX_HW_ID_MINOR_VERSION_MASK GENMASK_ULL(59, 56) +#define CS_AUX_HW_ID_MAJOR_VERSION_MASK GENMASK_ULL(63, 60) + +#define CS_AUX_HW_ID_MAJOR_VERSION 0 +#define CS_AUX_HW_ID_MINOR_VERSION 1 #endif diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 5f288d475490..17276965ff1d 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -12,6 +12,7 @@ #include <linux/io.h> #include <linux/perf_event.h> #include <linux/sched.h> +#include <linux/platform_device.h> /* Peripheral id registers (0xFD0-0xFEC) */ #define CORESIGHT_PERIPHIDR4 0xfd0 @@ -171,6 +172,9 @@ struct coresight_desc { * @dest_dev: a @coresight_device representation of the component connected to @src_port. NULL until the device is created * @link: Representation of the connection as a sysfs link. + * @filter_src_fwnode: filter source component's fwnode handle. + * @filter_src_dev: a @coresight_device representation of the component that + needs to be filtered. * * The full connection structure looks like this, where in_conns store * references to same connection as the source device's out_conns. @@ -199,8 +203,10 @@ struct coresight_connection { struct coresight_device *dest_dev; struct coresight_sysfs_link *link; struct coresight_device *src_dev; - atomic_t src_refcnt; - atomic_t dest_refcnt; + struct fwnode_handle *filter_src_fwnode; + struct coresight_device *filter_src_dev; + int src_refcnt; + int dest_refcnt; }; /** @@ -217,6 +223,24 @@ struct coresight_sysfs_link { const char *target_name; }; +/* architecturally we have 128 IDs some of which are reserved */ +#define CORESIGHT_TRACE_IDS_MAX 128 + +/** + * 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. + * @perf_cs_etm_session_active: Number of Perf sessions using this ID map. + */ +struct coresight_trace_id_map { + DECLARE_BITMAP(used_ids, CORESIGHT_TRACE_IDS_MAX); + atomic_t __percpu *cpu_map; + atomic_t perf_cs_etm_session_active; + spinlock_t lock; +}; + /** * struct coresight_device - representation of a device as used by the framework * @pdata: Platform data with device connections associated to this device. @@ -270,6 +294,7 @@ struct coresight_device { bool sysfs_sink_activated; struct dev_ext_attribute *ea; struct coresight_device *def_sink; + struct coresight_trace_id_map perf_sink_id_map; /* sysfs links between components */ int nr_links; bool has_conns_grp; @@ -364,7 +389,7 @@ struct coresight_ops_link { struct coresight_ops_source { int (*cpu_id)(struct coresight_device *csdev); int (*enable)(struct coresight_device *csdev, struct perf_event *event, - enum cs_mode mode); + enum cs_mode mode, struct coresight_trace_id_map *id_map); void (*disable)(struct coresight_device *csdev, struct perf_event *event); }; @@ -568,9 +593,14 @@ static inline void csdev_access_write64(struct csdev_access *csa, u64 val, u32 o } #endif /* CONFIG_64BIT */ +static inline bool coresight_is_device_source(struct coresight_device *csdev) +{ + return csdev && (csdev->type == CORESIGHT_DEV_TYPE_SOURCE); +} + static inline bool coresight_is_percpu_source(struct coresight_device *csdev) { - return csdev && (csdev->type == CORESIGHT_DEV_TYPE_SOURCE) && + return csdev && coresight_is_device_source(csdev) && (csdev->subtype.source_subtype == CORESIGHT_DEV_SUBTYPE_SOURCE_PROC); } @@ -642,6 +672,7 @@ void coresight_relaxed_write64(struct coresight_device *csdev, void coresight_write64(struct coresight_device *csdev, u64 val, u32 offset); extern int coresight_get_cpu(struct device *dev); +extern int coresight_get_static_trace_id(struct device *dev, u32 *id); struct coresight_platform_data *coresight_get_platform_data(struct device *dev); struct coresight_connection * @@ -658,4 +689,9 @@ coresight_find_output_type(struct coresight_platform_data *pdata, enum coresight_dev_type type, union coresight_dev_subtype subtype); +int coresight_init_driver(const char *drv, struct amba_driver *amba_drv, + struct platform_driver *pdev_drv); + +void coresight_remove_driver(struct amba_driver *amba_drv, + struct platform_driver *pdev_drv); #endif /* _LINUX_COREISGHT_H */ diff --git a/include/linux/counter.h b/include/linux/counter.h index 702e9108bbb4..426b7d58a438 100644 --- a/include/linux/counter.h +++ b/include/linux/counter.h @@ -6,14 +6,15 @@ #ifndef _COUNTER_H_ #define _COUNTER_H_ +#include <linux/array_size.h> #include <linux/cdev.h> #include <linux/device.h> -#include <linux/kernel.h> #include <linux/kfifo.h> #include <linux/mutex.h> #include <linux/spinlock_types.h> #include <linux/types.h> #include <linux/wait.h> + #include <uapi/linux/counter.h> struct counter_device; @@ -359,7 +360,6 @@ struct counter_ops { * @num_counts: number of Counts specified in @counts * @ext: optional array of Counter device extensions * @num_ext: number of Counter device extensions specified in @ext - * @priv: optional private data supplied by driver * @dev: internal device structure * @chrdev: internal character device structure * @events_list: list of current watching Counter events @@ -602,6 +602,9 @@ struct counter_array { #define COUNTER_COMP_FLOOR(_read, _write) \ COUNTER_COMP_COUNT_U64("floor", _read, _write) +#define COUNTER_COMP_FREQUENCY(_read) \ + COUNTER_COMP_SIGNAL_U64("frequency", _read, NULL) + #define COUNTER_COMP_POLARITY(_read, _write, _available) \ { \ .type = COUNTER_COMP_SIGNAL_POLARITY, \ diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 861c3bfc5f17..6a0a8f1c7c90 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -16,8 +16,8 @@ #include <linux/node.h> #include <linux/compiler.h> -#include <linux/cpumask.h> #include <linux/cpuhotplug.h> +#include <linux/cpuhplock.h> #include <linux/cpu_smt.h> struct device; @@ -77,6 +77,7 @@ extern ssize_t cpu_show_gds(struct device *dev, struct device_attribute *attr, char *buf); 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 __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, @@ -132,38 +133,6 @@ static inline int add_cpu(unsigned int cpu) { return 0;} #endif /* CONFIG_SMP */ extern const struct bus_type cpu_subsys; -extern int lockdep_is_cpus_held(void); - -#ifdef CONFIG_HOTPLUG_CPU -extern void cpus_write_lock(void); -extern void cpus_write_unlock(void); -extern void cpus_read_lock(void); -extern void cpus_read_unlock(void); -extern int cpus_read_trylock(void); -extern void lockdep_assert_cpus_held(void); -extern void cpu_hotplug_disable(void); -extern void cpu_hotplug_enable(void); -void clear_tasks_mm_cpumask(int cpu); -int remove_cpu(unsigned int cpu); -int cpu_device_down(struct device *dev); -extern void smp_shutdown_nonboot_cpus(unsigned int primary_cpu); - -#else /* CONFIG_HOTPLUG_CPU */ - -static inline void cpus_write_lock(void) { } -static inline void cpus_write_unlock(void) { } -static inline void cpus_read_lock(void) { } -static inline void cpus_read_unlock(void) { } -static inline int cpus_read_trylock(void) { return true; } -static inline void lockdep_assert_cpus_held(void) { } -static inline void cpu_hotplug_disable(void) { } -static inline void cpu_hotplug_enable(void) { } -static inline int remove_cpu(unsigned int cpu) { return -EPERM; } -static inline void smp_shutdown_nonboot_cpus(unsigned int primary_cpu) { } -#endif /* !CONFIG_HOTPLUG_CPU */ - -DEFINE_LOCK_GUARD_0(cpus_read_lock, cpus_read_lock(), cpus_read_unlock()) - #ifdef CONFIG_PM_SLEEP_SMP extern int freeze_secondary_cpus(int primary); extern void thaw_secondary_cpus(void); diff --git a/include/linux/cpu_cooling.h b/include/linux/cpu_cooling.h index a3bdc8a98f2c..2c774fb3c091 100644 --- a/include/linux/cpu_cooling.h +++ b/include/linux/cpu_cooling.h @@ -15,7 +15,6 @@ #include <linux/of.h> #include <linux/thermal.h> -#include <linux/cpumask.h> struct cpufreq_policy; diff --git a/include/linux/cpu_rmap.h b/include/linux/cpu_rmap.h index cae324d10965..20b5729903d7 100644 --- a/include/linux/cpu_rmap.h +++ b/include/linux/cpu_rmap.h @@ -7,7 +7,7 @@ * Copyright 2011 Solarflare Communications Inc. */ -#include <linux/cpumask.h> +#include <linux/cpumask_types.h> #include <linux/gfp.h> #include <linux/slab.h> #include <linux/kref.h> diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 9956afb9acc2..7fe0981a7e46 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -241,6 +241,12 @@ struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy); void cpufreq_enable_fast_switch(struct cpufreq_policy *policy); void cpufreq_disable_fast_switch(struct cpufreq_policy *policy); bool has_target_index(void); + +DECLARE_PER_CPU(unsigned long, cpufreq_pressure); +static inline unsigned long cpufreq_get_pressure(int cpu) +{ + return READ_ONCE(per_cpu(cpufreq_pressure, cpu)); +} #else static inline unsigned int cpufreq_get(unsigned int cpu) { @@ -264,6 +270,10 @@ static inline bool cpufreq_supports_freq_invariance(void) } static inline void disable_cpufreq(void) { } static inline void cpufreq_update_limits(unsigned int cpu) { } +static inline unsigned long cpufreq_get_pressure(int cpu) +{ + return 0; +} #endif #ifdef CONFIG_CPU_FREQ_STAT @@ -386,7 +396,7 @@ struct cpufreq_driver { int (*online)(struct cpufreq_policy *policy); int (*offline)(struct cpufreq_policy *policy); - int (*exit)(struct cpufreq_policy *policy); + void (*exit)(struct cpufreq_policy *policy); int (*suspend)(struct cpufreq_policy *policy); int (*resume)(struct cpufreq_policy *policy); @@ -567,12 +577,6 @@ static inline unsigned long cpufreq_scale(unsigned long old, u_int div, #define CPUFREQ_POLICY_POWERSAVE (1) #define CPUFREQ_POLICY_PERFORMANCE (2) -/* - * The polling frequency depends on the capability of the processor. Default - * polling frequency is 1000 times the transition latency of the processor. - */ -#define LATENCY_MULTIPLIER (1000) - struct cpufreq_governor { char name[CPUFREQ_NAME_LEN]; int (*init)(struct cpufreq_policy *policy); @@ -775,7 +779,7 @@ ssize_t cpufreq_show_cpus(const struct cpumask *mask, char *buf); #ifdef CONFIG_CPU_FREQ int cpufreq_boost_trigger_state(int state); -int cpufreq_boost_enabled(void); +bool cpufreq_boost_enabled(void); int cpufreq_enable_boost_support(void); bool policy_has_boost_freq(struct cpufreq_policy *policy); @@ -1103,10 +1107,9 @@ static inline int parse_perf_domain(int cpu, const char *list_name, const char *cell_name, struct of_phandle_args *args) { - struct device_node *cpu_np; int ret; - cpu_np = of_cpu_device_node_get(cpu); + struct device_node *cpu_np __free(device_node) = of_cpu_device_node_get(cpu); if (!cpu_np) return -ENODEV; @@ -1114,9 +1117,6 @@ static inline int parse_perf_domain(int cpu, const char *list_name, args); if (ret < 0) return ret; - - of_node_put(cpu_np); - return 0; } @@ -1154,9 +1154,9 @@ static inline int cpufreq_boost_trigger_state(int state) { return 0; } -static inline int cpufreq_boost_enabled(void) +static inline bool cpufreq_boost_enabled(void) { - return 0; + return false; } static inline int cpufreq_enable_boost_support(void) diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 35e78ddb2b37..6cc5e484547c 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -27,7 +27,7 @@ * startup callbacks sequentially from CPUHP_OFFLINE + 1 to CPUHP_ONLINE * during a CPU online operation. During a CPU offline operation the * installed teardown callbacks are invoked in the reverse order from - * CPU_ONLINE - 1 down to CPUHP_OFFLINE. + * CPUHP_ONLINE - 1 down to CPUHP_OFFLINE. * * The state space has three sections: PREPARE, STARTING and ONLINE. * @@ -100,7 +100,6 @@ enum cpuhp_state { CPUHP_WORKQUEUE_PREP, CPUHP_POWER_NUMA_PREPARE, CPUHP_HRTIMERS_PREPARE, - CPUHP_PROFILE_PREPARE, CPUHP_X2APIC_PREPARE, CPUHP_SMPCFD_PREPARE, CPUHP_RELAY_PREPARE, @@ -122,6 +121,7 @@ enum cpuhp_state { CPUHP_KVM_PPC_BOOK3S_PREPARE, CPUHP_ZCOMP_PREPARE, CPUHP_TIMERS_PREPARE, + CPUHP_TMIGR_PREPARE, CPUHP_MIPS_SOC_PREPARE, CPUHP_BP_PREPARE_DYN, CPUHP_BP_PREPARE_DYN_END = CPUHP_BP_PREPARE_DYN + 20, @@ -144,13 +144,16 @@ enum cpuhp_state { CPUHP_AP_IRQ_ARMADA_XP_STARTING, CPUHP_AP_IRQ_BCM2836_STARTING, CPUHP_AP_IRQ_MIPS_GIC_STARTING, - CPUHP_AP_IRQ_LOONGARCH_STARTING, + CPUHP_AP_IRQ_EIOINTC_STARTING, + CPUHP_AP_IRQ_AVECINTC_STARTING, CPUHP_AP_IRQ_SIFIVE_PLIC_STARTING, + CPUHP_AP_IRQ_THEAD_ACLINT_SSWI_STARTING, + CPUHP_AP_IRQ_RISCV_IMSIC_STARTING, + CPUHP_AP_IRQ_RISCV_SBI_IPI_STARTING, CPUHP_AP_ARM_MVEBU_COHERENCY, CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING, CPUHP_AP_PERF_X86_STARTING, CPUHP_AP_PERF_X86_AMD_IBS_STARTING, - CPUHP_AP_PERF_X86_CSTATE_STARTING, CPUHP_AP_PERF_XTENSA_STARTING, CPUHP_AP_ARM_VFP_STARTING, CPUHP_AP_ARM64_DEBUG_MONITORS_STARTING, @@ -170,6 +173,7 @@ enum cpuhp_state { CPUHP_AP_ARMADA_TIMER_STARTING, CPUHP_AP_MIPS_GIC_TIMER_STARTING, CPUHP_AP_ARC_TIMER_STARTING, + CPUHP_AP_REALTEK_TIMER_STARTING, CPUHP_AP_RISCV_TIMER_STARTING, CPUHP_AP_CLINT_TIMER_STARTING, CPUHP_AP_CSKY_TIMER_STARTING, @@ -205,8 +209,6 @@ enum cpuhp_state { CPUHP_AP_PERF_X86_UNCORE_ONLINE, CPUHP_AP_PERF_X86_AMD_UNCORE_ONLINE, CPUHP_AP_PERF_X86_AMD_POWER_ONLINE, - CPUHP_AP_PERF_X86_RAPL_ONLINE, - CPUHP_AP_PERF_X86_CSTATE_ONLINE, CPUHP_AP_PERF_S390_CF_ONLINE, CPUHP_AP_PERF_S390_SF_ONLINE, CPUHP_AP_PERF_ARM_CCI_ONLINE, @@ -225,6 +227,7 @@ enum cpuhp_state { CPUHP_AP_PERF_ARM_APM_XGENE_ONLINE, CPUHP_AP_PERF_ARM_CAVIUM_TX2_UNCORE_ONLINE, CPUHP_AP_PERF_ARM_MARVELL_CN10K_DDR_ONLINE, + CPUHP_AP_PERF_ARM_MRVL_PEM_ONLINE, CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE, CPUHP_AP_PERF_POWERPC_CORE_IMC_ONLINE, CPUHP_AP_PERF_POWERPC_THREAD_IMC_ONLINE, @@ -237,6 +240,7 @@ enum cpuhp_state { CPUHP_AP_WORKQUEUE_ONLINE, CPUHP_AP_RANDOM_ONLINE, CPUHP_AP_RCUTREE_ONLINE, + CPUHP_AP_KTHREADS_ONLINE, CPUHP_AP_BASE_CACHEINFO_ONLINE, CPUHP_AP_ONLINE_DYN, CPUHP_AP_ONLINE_DYN_END = CPUHP_AP_ONLINE_DYN + 40, diff --git a/include/linux/cpuhplock.h b/include/linux/cpuhplock.h new file mode 100644 index 000000000000..f7aa20f62b87 --- /dev/null +++ b/include/linux/cpuhplock.h @@ -0,0 +1,49 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * include/linux/cpuhplock.h - CPU hotplug locking + * + * Locking functions for CPU hotplug. + */ +#ifndef _LINUX_CPUHPLOCK_H_ +#define _LINUX_CPUHPLOCK_H_ + +#include <linux/cleanup.h> +#include <linux/errno.h> + +struct device; + +extern int lockdep_is_cpus_held(void); + +#ifdef CONFIG_HOTPLUG_CPU +void cpus_write_lock(void); +void cpus_write_unlock(void); +void cpus_read_lock(void); +void cpus_read_unlock(void); +int cpus_read_trylock(void); +void lockdep_assert_cpus_held(void); +void cpu_hotplug_disable_offlining(void); +void cpu_hotplug_disable(void); +void cpu_hotplug_enable(void); +void clear_tasks_mm_cpumask(int cpu); +int remove_cpu(unsigned int cpu); +int cpu_device_down(struct device *dev); +void smp_shutdown_nonboot_cpus(unsigned int primary_cpu); + +#else /* CONFIG_HOTPLUG_CPU */ + +static inline void cpus_write_lock(void) { } +static inline void cpus_write_unlock(void) { } +static inline void cpus_read_lock(void) { } +static inline void cpus_read_unlock(void) { } +static inline int cpus_read_trylock(void) { return true; } +static inline void lockdep_assert_cpus_held(void) { } +static inline void cpu_hotplug_disable_offlining(void) { } +static inline void cpu_hotplug_disable(void) { } +static inline void cpu_hotplug_enable(void) { } +static inline int remove_cpu(unsigned int cpu) { return -EPERM; } +static inline void smp_shutdown_nonboot_cpus(unsigned int primary_cpu) { } +#endif /* !CONFIG_HOTPLUG_CPU */ + +DEFINE_LOCK_GUARD_0(cpus_read_lock, cpus_read_lock(), cpus_read_unlock()) + +#endif /* _LINUX_CPUHPLOCK_H_ */ diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 3183aeb7f5b4..a9ee4fe55dcf 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -61,7 +61,7 @@ struct cpuidle_state { struct cpuidle_driver *drv, int index); - int (*enter_dead) (struct cpuidle_device *dev, int index); + void (*enter_dead) (struct cpuidle_device *dev, int index); /* * CPUs execute ->enter_s2idle with the local tick or entire timekeeping diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 1c29947db848..36a890d0dd57 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -9,25 +9,13 @@ */ #include <linux/cleanup.h> #include <linux/kernel.h> -#include <linux/threads.h> #include <linux/bitmap.h> +#include <linux/cpumask_types.h> #include <linux/atomic.h> #include <linux/bug.h> #include <linux/gfp_types.h> #include <linux/numa.h> -/* Don't assign or return these: may not be this big! */ -typedef struct cpumask { DECLARE_BITMAP(bits, NR_CPUS); } cpumask_t; - -/** - * cpumask_bits - get the bits in a cpumask - * @maskp: the struct cpumask * - * - * You should only assume nr_cpu_ids bits of this mask are valid. This is - * a macro so it's const-correct. - */ -#define cpumask_bits(maskp) ((maskp)->bits) - /** * cpumask_pr_args - printf args to output a cpumask * @maskp: cpumask to be printed @@ -42,7 +30,7 @@ typedef struct cpumask { DECLARE_BITMAP(bits, NR_CPUS); } cpumask_t; extern unsigned int nr_cpu_ids; #endif -static inline void set_nr_cpu_ids(unsigned int nr) +static __always_inline void set_nr_cpu_ids(unsigned int nr) { #if (NR_CPUS == 1) || defined(CONFIG_FORCE_NR_CPUS) WARN_ON(nr != nr_cpu_ids); @@ -93,6 +81,7 @@ static inline void set_nr_cpu_ids(unsigned int nr) * * cpu_possible_mask- has bit 'cpu' set iff cpu is populatable * cpu_present_mask - has bit 'cpu' set iff cpu is populated + * cpu_enabled_mask - has bit 'cpu' set iff cpu can be brought online * cpu_online_mask - has bit 'cpu' set iff cpu available to scheduler * cpu_active_mask - has bit 'cpu' set iff cpu available to migration * @@ -125,11 +114,13 @@ static inline void set_nr_cpu_ids(unsigned int nr) extern struct cpumask __cpu_possible_mask; extern struct cpumask __cpu_online_mask; +extern struct cpumask __cpu_enabled_mask; extern struct cpumask __cpu_present_mask; extern struct cpumask __cpu_active_mask; extern struct cpumask __cpu_dying_mask; #define cpu_possible_mask ((const struct cpumask *)&__cpu_possible_mask) #define cpu_online_mask ((const struct cpumask *)&__cpu_online_mask) +#define cpu_enabled_mask ((const struct cpumask *)&__cpu_enabled_mask) #define cpu_present_mask ((const struct cpumask *)&__cpu_present_mask) #define cpu_active_mask ((const struct cpumask *)&__cpu_active_mask) #define cpu_dying_mask ((const struct cpumask *)&__cpu_dying_mask) @@ -158,7 +149,7 @@ static __always_inline unsigned int cpumask_check(unsigned int cpu) * * Return: >= nr_cpu_ids if no cpus set. */ -static inline unsigned int cpumask_first(const struct cpumask *srcp) +static __always_inline unsigned int cpumask_first(const struct cpumask *srcp) { return find_first_bit(cpumask_bits(srcp), small_cpumask_bits); } @@ -169,7 +160,7 @@ static inline unsigned int cpumask_first(const struct cpumask *srcp) * * Return: >= nr_cpu_ids if all cpus are set. */ -static inline unsigned int cpumask_first_zero(const struct cpumask *srcp) +static __always_inline unsigned int cpumask_first_zero(const struct cpumask *srcp) { return find_first_zero_bit(cpumask_bits(srcp), small_cpumask_bits); } @@ -181,19 +172,36 @@ static inline unsigned int cpumask_first_zero(const struct cpumask *srcp) * * Return: >= nr_cpu_ids if no cpus set in both. See also cpumask_next_and(). */ -static inline +static __always_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), small_cpumask_bits); } /** + * cpumask_first_and_and - return the first cpu from *srcp1 & *srcp2 & *srcp3 + * @srcp1: the first input + * @srcp2: the second input + * @srcp3: the third input + * + * Return: >= nr_cpu_ids if no cpus set in all. + */ +static __always_inline +unsigned int cpumask_first_and_and(const struct cpumask *srcp1, + const struct cpumask *srcp2, + const struct cpumask *srcp3) +{ + return find_first_and_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), + cpumask_bits(srcp3), small_cpumask_bits); +} + +/** * cpumask_last - get the last CPU in a cpumask * @srcp: - the cpumask pointer * * Return: >= nr_cpumask_bits if no CPUs set. */ -static inline unsigned int cpumask_last(const struct cpumask *srcp) +static __always_inline unsigned int cpumask_last(const struct cpumask *srcp) { return find_last_bit(cpumask_bits(srcp), small_cpumask_bits); } @@ -205,7 +213,7 @@ static inline unsigned int cpumask_last(const struct cpumask *srcp) * * Return: >= nr_cpu_ids if no further cpus set. */ -static inline +static __always_inline unsigned int cpumask_next(int n, const struct cpumask *srcp) { /* -1 is a legal arg here. */ @@ -221,7 +229,8 @@ unsigned int cpumask_next(int n, const struct cpumask *srcp) * * Return: >= nr_cpu_ids if no further cpus unset. */ -static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp) +static __always_inline +unsigned int cpumask_next_zero(int n, const struct cpumask *srcp) { /* -1 is a legal arg here. */ if (n != -1) @@ -231,18 +240,21 @@ static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp) #if NR_CPUS == 1 /* Uniprocessor: there is only one valid CPU */ -static inline unsigned int cpumask_local_spread(unsigned int i, int node) +static __always_inline +unsigned int cpumask_local_spread(unsigned int i, int node) { return 0; } -static inline unsigned int cpumask_any_and_distribute(const struct cpumask *src1p, - const struct cpumask *src2p) +static __always_inline +unsigned int cpumask_any_and_distribute(const struct cpumask *src1p, + const struct cpumask *src2p) { return cpumask_first_and(src1p, src2p); } -static inline unsigned int cpumask_any_distribute(const struct cpumask *srcp) +static __always_inline +unsigned int cpumask_any_distribute(const struct cpumask *srcp) { return cpumask_first(srcp); } @@ -261,9 +273,9 @@ unsigned int cpumask_any_distribute(const struct cpumask *srcp); * * Return: >= nr_cpu_ids if no further cpus set in both. */ -static inline +static __always_inline unsigned int cpumask_next_and(int n, const struct cpumask *src1p, - const struct cpumask *src2p) + const struct cpumask *src2p) { /* -1 is a legal arg here. */ if (n != -1) @@ -283,7 +295,7 @@ unsigned int cpumask_next_and(int n, const struct cpumask *src1p, for_each_set_bit(cpu, cpumask_bits(mask), small_cpumask_bits) #if NR_CPUS == 1 -static inline +static __always_inline unsigned int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap) { cpumask_check(start); @@ -369,14 +381,24 @@ unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int sta 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. + * for_each_cpu_from - iterate over CPUs present in @mask, from @cpu to the end of @mask. + * @cpu: the (optionally unsigned) integer iterator + * @mask: the cpumask pointer + * + * After the loop, cpu is >= nr_cpu_ids. + */ +#define for_each_cpu_from(cpu, mask) \ + for_each_set_bit_from(cpu, cpumask_bits(mask), small_cpumask_bits) + +/** + * cpumask_any_but - return an arbitrary cpu in a cpumask, but not this one. * @mask: the cpumask to search * @cpu: the cpu to ignore. * * Often used to find any cpu but smp_processor_id() in a mask. * Return: >= nr_cpu_ids if no cpus set. */ -static inline +static __always_inline unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu) { unsigned int i; @@ -389,13 +411,37 @@ unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu) } /** + * cpumask_any_and_but - pick an arbitrary cpu from *mask1 & *mask2, but not this one. + * @mask1: the first input cpumask + * @mask2: the second input cpumask + * @cpu: the cpu to ignore + * + * Returns >= nr_cpu_ids if no cpus set. + */ +static __always_inline +unsigned int cpumask_any_and_but(const struct cpumask *mask1, + const struct cpumask *mask2, + unsigned int cpu) +{ + unsigned int i; + + cpumask_check(cpu); + i = cpumask_first_and(mask1, mask2); + if (i != cpu) + return i; + + return cpumask_next_and(cpu, mask1, mask2); +} + +/** * cpumask_nth - get the Nth cpu in a cpumask * @srcp: the cpumask pointer * @cpu: the Nth cpu to find, starting from 0 * * Return: >= nr_cpu_ids if such cpu doesn't exist. */ -static inline unsigned int cpumask_nth(unsigned int cpu, const struct cpumask *srcp) +static __always_inline +unsigned int cpumask_nth(unsigned int cpu, const struct cpumask *srcp) { return find_nth_bit(cpumask_bits(srcp), small_cpumask_bits, cpumask_check(cpu)); } @@ -408,7 +454,7 @@ static inline unsigned int cpumask_nth(unsigned int cpu, const struct cpumask *s * * Return: >= nr_cpu_ids if such cpu doesn't exist. */ -static inline +static __always_inline unsigned int cpumask_nth_and(unsigned int cpu, const struct cpumask *srcp1, const struct cpumask *srcp2) { @@ -424,7 +470,7 @@ unsigned int cpumask_nth_and(unsigned int cpu, const struct cpumask *srcp1, * * Return: >= nr_cpu_ids if such cpu doesn't exist. */ -static inline +static __always_inline unsigned int cpumask_nth_andnot(unsigned int cpu, const struct cpumask *srcp1, const struct cpumask *srcp2) { @@ -467,12 +513,14 @@ unsigned int cpumask_nth_and_andnot(unsigned int cpu, const struct cpumask *srcp * @cpu: cpu number (< nr_cpu_ids) * @dstp: the cpumask pointer */ -static __always_inline void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) +static __always_inline +void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) { set_bit(cpumask_check(cpu), cpumask_bits(dstp)); } -static __always_inline void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) +static __always_inline +void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) { __set_bit(cpumask_check(cpu), cpumask_bits(dstp)); } @@ -494,13 +542,30 @@ static __always_inline void __cpumask_clear_cpu(int cpu, struct cpumask *dstp) } /** + * cpumask_assign_cpu - assign a cpu in a cpumask + * @cpu: cpu number (< nr_cpu_ids) + * @dstp: the cpumask pointer + * @bool: the value to assign + */ +static __always_inline void cpumask_assign_cpu(int cpu, struct cpumask *dstp, bool value) +{ + assign_bit(cpumask_check(cpu), cpumask_bits(dstp), value); +} + +static __always_inline void __cpumask_assign_cpu(int cpu, struct cpumask *dstp, bool value) +{ + __assign_bit(cpumask_check(cpu), cpumask_bits(dstp), value); +} + +/** * cpumask_test_cpu - test for a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @cpumask: the cpumask pointer * * Return: true if @cpu is set in @cpumask, else returns false */ -static __always_inline bool cpumask_test_cpu(int cpu, const struct cpumask *cpumask) +static __always_inline +bool cpumask_test_cpu(int cpu, const struct cpumask *cpumask) { return test_bit(cpumask_check(cpu), cpumask_bits((cpumask))); } @@ -514,7 +579,8 @@ static __always_inline bool cpumask_test_cpu(int cpu, const struct cpumask *cpum * * Return: true if @cpu is set in old bitmap of @cpumask, else returns false */ -static __always_inline bool cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask) +static __always_inline +bool cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask) { return test_and_set_bit(cpumask_check(cpu), cpumask_bits(cpumask)); } @@ -528,7 +594,8 @@ static __always_inline bool cpumask_test_and_set_cpu(int cpu, struct cpumask *cp * * Return: true if @cpu is set in old bitmap of @cpumask, else returns false */ -static __always_inline bool cpumask_test_and_clear_cpu(int cpu, struct cpumask *cpumask) +static __always_inline +bool cpumask_test_and_clear_cpu(int cpu, struct cpumask *cpumask) { return test_and_clear_bit(cpumask_check(cpu), cpumask_bits(cpumask)); } @@ -537,7 +604,7 @@ 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 */ -static inline void cpumask_setall(struct cpumask *dstp) +static __always_inline void cpumask_setall(struct cpumask *dstp) { if (small_const_nbits(small_cpumask_bits)) { cpumask_bits(dstp)[0] = BITMAP_LAST_WORD_MASK(nr_cpumask_bits); @@ -550,7 +617,7 @@ static inline void cpumask_setall(struct cpumask *dstp) * cpumask_clear - clear all cpus (< nr_cpu_ids) in a cpumask * @dstp: the cpumask pointer */ -static inline void cpumask_clear(struct cpumask *dstp) +static __always_inline void cpumask_clear(struct cpumask *dstp) { bitmap_zero(cpumask_bits(dstp), large_cpumask_bits); } @@ -563,9 +630,9 @@ static inline void cpumask_clear(struct cpumask *dstp) * * Return: false if *@dstp is empty, else returns true */ -static inline bool cpumask_and(struct cpumask *dstp, - const struct cpumask *src1p, - const struct cpumask *src2p) +static __always_inline +bool cpumask_and(struct cpumask *dstp, const struct cpumask *src1p, + const struct cpumask *src2p) { return bitmap_and(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); @@ -577,8 +644,9 @@ static inline bool cpumask_and(struct cpumask *dstp, * @src1p: the first input * @src2p: the second input */ -static inline void cpumask_or(struct cpumask *dstp, const struct cpumask *src1p, - const struct cpumask *src2p) +static __always_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), small_cpumask_bits); @@ -590,9 +658,9 @@ static inline void cpumask_or(struct cpumask *dstp, const struct cpumask *src1p, * @src1p: the first input * @src2p: the second input */ -static inline void cpumask_xor(struct cpumask *dstp, - const struct cpumask *src1p, - const struct cpumask *src2p) +static __always_inline +void cpumask_xor(struct cpumask *dstp, const struct cpumask *src1p, + const struct cpumask *src2p) { bitmap_xor(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); @@ -606,9 +674,9 @@ static inline void cpumask_xor(struct cpumask *dstp, * * Return: false if *@dstp is empty, else returns true */ -static inline bool cpumask_andnot(struct cpumask *dstp, - const struct cpumask *src1p, - const struct cpumask *src2p) +static __always_inline +bool cpumask_andnot(struct cpumask *dstp, const struct cpumask *src1p, + const struct cpumask *src2p) { return bitmap_andnot(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); @@ -621,8 +689,8 @@ static inline bool cpumask_andnot(struct cpumask *dstp, * * Return: true if the cpumasks are equal, false if not */ -static inline bool cpumask_equal(const struct cpumask *src1p, - const struct cpumask *src2p) +static __always_inline +bool cpumask_equal(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_equal(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); @@ -637,9 +705,9 @@ static inline bool cpumask_equal(const struct cpumask *src1p, * Return: true if first cpumask ORed with second cpumask == third cpumask, * otherwise false */ -static inline bool cpumask_or_equal(const struct cpumask *src1p, - const struct cpumask *src2p, - const struct cpumask *src3p) +static __always_inline +bool cpumask_or_equal(const struct cpumask *src1p, const struct cpumask *src2p, + const struct cpumask *src3p) { return bitmap_or_equal(cpumask_bits(src1p), cpumask_bits(src2p), cpumask_bits(src3p), small_cpumask_bits); @@ -653,8 +721,8 @@ static inline bool cpumask_or_equal(const struct cpumask *src1p, * Return: true if first cpumask ANDed with second cpumask is non-empty, * otherwise false */ -static inline bool cpumask_intersects(const struct cpumask *src1p, - const struct cpumask *src2p) +static __always_inline +bool cpumask_intersects(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_intersects(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); @@ -667,8 +735,8 @@ static inline bool cpumask_intersects(const struct cpumask *src1p, * * Return: true if *@src1p is a subset of *@src2p, else returns false */ -static inline bool cpumask_subset(const struct cpumask *src1p, - const struct cpumask *src2p) +static __always_inline +bool cpumask_subset(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_subset(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); @@ -680,7 +748,7 @@ static inline bool cpumask_subset(const struct cpumask *src1p, * * Return: true if srcp is empty (has no bits set), else false */ -static inline bool cpumask_empty(const struct cpumask *srcp) +static __always_inline bool cpumask_empty(const struct cpumask *srcp) { return bitmap_empty(cpumask_bits(srcp), small_cpumask_bits); } @@ -691,7 +759,7 @@ static inline bool cpumask_empty(const struct cpumask *srcp) * * Return: true if srcp is full (has all bits set), else false */ -static inline bool cpumask_full(const struct cpumask *srcp) +static __always_inline bool cpumask_full(const struct cpumask *srcp) { return bitmap_full(cpumask_bits(srcp), nr_cpumask_bits); } @@ -702,7 +770,7 @@ static inline bool cpumask_full(const struct cpumask *srcp) * * Return: count of bits set in *srcp */ -static inline unsigned int cpumask_weight(const struct cpumask *srcp) +static __always_inline unsigned int cpumask_weight(const struct cpumask *srcp) { return bitmap_weight(cpumask_bits(srcp), small_cpumask_bits); } @@ -714,8 +782,8 @@ static inline unsigned int cpumask_weight(const struct cpumask *srcp) * * Return: count of bits set in both *srcp1 and *srcp2 */ -static inline unsigned int cpumask_weight_and(const struct cpumask *srcp1, - const struct cpumask *srcp2) +static __always_inline +unsigned int cpumask_weight_and(const struct cpumask *srcp1, const struct cpumask *srcp2) { return bitmap_weight_and(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits); } @@ -727,8 +795,9 @@ static inline unsigned int cpumask_weight_and(const struct cpumask *srcp1, * * Return: count of bits set in both *srcp1 and *srcp2 */ -static inline unsigned int cpumask_weight_andnot(const struct cpumask *srcp1, - const struct cpumask *srcp2) +static __always_inline +unsigned int cpumask_weight_andnot(const struct cpumask *srcp1, + const struct cpumask *srcp2) { return bitmap_weight_andnot(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits); } @@ -739,8 +808,8 @@ static inline unsigned int cpumask_weight_andnot(const struct cpumask *srcp1, * @srcp: the input to shift * @n: the number of bits to shift by */ -static inline void cpumask_shift_right(struct cpumask *dstp, - const struct cpumask *srcp, int n) +static __always_inline +void cpumask_shift_right(struct cpumask *dstp, const struct cpumask *srcp, int n) { bitmap_shift_right(cpumask_bits(dstp), cpumask_bits(srcp), n, small_cpumask_bits); @@ -752,8 +821,8 @@ static inline void cpumask_shift_right(struct cpumask *dstp, * @srcp: the input to shift * @n: the number of bits to shift by */ -static inline void cpumask_shift_left(struct cpumask *dstp, - const struct cpumask *srcp, int n) +static __always_inline +void cpumask_shift_left(struct cpumask *dstp, const struct cpumask *srcp, int n) { bitmap_shift_left(cpumask_bits(dstp), cpumask_bits(srcp), n, nr_cpumask_bits); @@ -764,14 +833,14 @@ static inline void cpumask_shift_left(struct cpumask *dstp, * @dstp: the result * @srcp: the input cpumask */ -static inline void cpumask_copy(struct cpumask *dstp, - const struct cpumask *srcp) +static __always_inline +void cpumask_copy(struct cpumask *dstp, const struct cpumask *srcp) { bitmap_copy(cpumask_bits(dstp), cpumask_bits(srcp), large_cpumask_bits); } /** - * cpumask_any - pick a "random" cpu from *srcp + * cpumask_any - pick an arbitrary cpu from *srcp * @srcp: the input cpumask * * Return: >= nr_cpu_ids if no cpus set. @@ -779,7 +848,7 @@ static inline void cpumask_copy(struct cpumask *dstp, #define cpumask_any(srcp) cpumask_first(srcp) /** - * cpumask_any_and - pick a "random" cpu from *mask1 & *mask2 + * cpumask_any_and - pick an arbitrary cpu from *mask1 & *mask2 * @mask1: the first input cpumask * @mask2: the second input cpumask * @@ -801,8 +870,8 @@ static inline void cpumask_copy(struct cpumask *dstp, * * Return: -errno, or 0 for success. */ -static inline int cpumask_parse_user(const char __user *buf, int len, - struct cpumask *dstp) +static __always_inline +int cpumask_parse_user(const char __user *buf, int len, struct cpumask *dstp) { return bitmap_parse_user(buf, len, cpumask_bits(dstp), nr_cpumask_bits); } @@ -815,8 +884,8 @@ static inline int cpumask_parse_user(const char __user *buf, int len, * * Return: -errno, or 0 for success. */ -static inline int cpumask_parselist_user(const char __user *buf, int len, - struct cpumask *dstp) +static __always_inline +int cpumask_parselist_user(const char __user *buf, int len, struct cpumask *dstp) { return bitmap_parselist_user(buf, len, cpumask_bits(dstp), nr_cpumask_bits); @@ -829,7 +898,7 @@ static inline int cpumask_parselist_user(const char __user *buf, int len, * * Return: -errno, or 0 for success. */ -static inline int cpumask_parse(const char *buf, struct cpumask *dstp) +static __always_inline int cpumask_parse(const char *buf, struct cpumask *dstp) { return bitmap_parse(buf, UINT_MAX, cpumask_bits(dstp), nr_cpumask_bits); } @@ -841,7 +910,7 @@ static inline int cpumask_parse(const char *buf, struct cpumask *dstp) * * Return: -errno, or 0 for success. */ -static inline int cpulist_parse(const char *buf, struct cpumask *dstp) +static __always_inline int cpulist_parse(const char *buf, struct cpumask *dstp) { return bitmap_parselist(buf, cpumask_bits(dstp), nr_cpumask_bits); } @@ -851,60 +920,19 @@ static inline int cpulist_parse(const char *buf, struct cpumask *dstp) * * Return: size to allocate for a &struct cpumask in bytes */ -static inline unsigned int cpumask_size(void) +static __always_inline unsigned int cpumask_size(void) { - return BITS_TO_LONGS(large_cpumask_bits) * sizeof(long); + return bitmap_size(large_cpumask_bits); } -/* - * cpumask_var_t: struct cpumask for stack usage. - * - * Oh, the wicked games we play! In order to make kernel coding a - * little more difficult, we typedef cpumask_var_t to an array or a - * pointer: doing &mask on an array is a noop, so it still works. - * - * i.e. - * cpumask_var_t tmpmask; - * if (!alloc_cpumask_var(&tmpmask, GFP_KERNEL)) - * return -ENOMEM; - * - * ... use 'tmpmask' like a normal struct cpumask * ... - * - * free_cpumask_var(tmpmask); - * - * - * However, one notable exception is there. alloc_cpumask_var() allocates - * only nr_cpumask_bits bits (in the other hand, real cpumask_t always has - * NR_CPUS bits). Therefore you don't have to dereference cpumask_var_t. - * - * cpumask_var_t tmpmask; - * if (!alloc_cpumask_var(&tmpmask, GFP_KERNEL)) - * return -ENOMEM; - * - * var = *tmpmask; - * - * This code makes NR_CPUS length memcopy and brings to a memory corruption. - * cpumask_copy() provide safe copy functionality. - * - * Note that there is another evil here: If you define a cpumask_var_t - * as a percpu variable then the way to obtain the address of the cpumask - * structure differently influences what this_cpu_* operation needs to be - * used. Please use this_cpu_cpumask_var_t in those cases. The direct use - * of this_cpu_ptr() or this_cpu_read() will lead to failures when the - * other type of cpumask_var_t implementation is configured. - * - * Please also note that __cpumask_var_read_mostly can be used to declare - * a cpumask_var_t variable itself (not its content) as read mostly. - */ #ifdef CONFIG_CPUMASK_OFFSTACK -typedef struct cpumask *cpumask_var_t; #define this_cpu_cpumask_var_ptr(x) this_cpu_read(x) #define __cpumask_var_read_mostly __read_mostly bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node); -static inline +static __always_inline bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { return alloc_cpumask_var_node(mask, flags | __GFP_ZERO, node); @@ -922,13 +950,13 @@ bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) * * Return: %true if allocation succeeded, %false if not */ -static inline +static __always_inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return alloc_cpumask_var_node(mask, flags, NUMA_NO_NODE); } -static inline +static __always_inline bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return alloc_cpumask_var(mask, flags | __GFP_ZERO); @@ -938,54 +966,53 @@ void alloc_bootmem_cpumask_var(cpumask_var_t *mask); void free_cpumask_var(cpumask_var_t mask); void free_bootmem_cpumask_var(cpumask_var_t mask); -static inline bool cpumask_available(cpumask_var_t mask) +static __always_inline bool cpumask_available(cpumask_var_t mask) { return mask != NULL; } #else -typedef struct cpumask cpumask_var_t[1]; #define this_cpu_cpumask_var_ptr(x) this_cpu_ptr(x) #define __cpumask_var_read_mostly -static inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) +static __always_inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return true; } -static inline bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, +static __always_inline bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { return true; } -static inline bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) +static __always_inline bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { cpumask_clear(*mask); return true; } -static inline bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, +static __always_inline bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { cpumask_clear(*mask); return true; } -static inline void alloc_bootmem_cpumask_var(cpumask_var_t *mask) +static __always_inline void alloc_bootmem_cpumask_var(cpumask_var_t *mask) { } -static inline void free_cpumask_var(cpumask_var_t mask) +static __always_inline void free_cpumask_var(cpumask_var_t mask) { } -static inline void free_bootmem_cpumask_var(cpumask_var_t mask) +static __always_inline void free_bootmem_cpumask_var(cpumask_var_t mask) { } -static inline bool cpumask_available(cpumask_var_t mask) +static __always_inline bool cpumask_available(cpumask_var_t mask) { return true; } @@ -1009,57 +1036,25 @@ extern const DECLARE_BITMAP(cpu_all_bits, NR_CPUS); #else #define for_each_possible_cpu(cpu) for_each_cpu((cpu), cpu_possible_mask) #define for_each_online_cpu(cpu) for_each_cpu((cpu), cpu_online_mask) +#define for_each_enabled_cpu(cpu) for_each_cpu((cpu), cpu_enabled_mask) #define for_each_present_cpu(cpu) for_each_cpu((cpu), cpu_present_mask) #endif /* Wrappers for arch boot code to manipulate normally-constant masks */ void init_cpu_present(const struct cpumask *src); void init_cpu_possible(const struct cpumask *src); -void init_cpu_online(const struct cpumask *src); -static inline void reset_cpu_possible_mask(void) -{ - bitmap_zero(cpumask_bits(&__cpu_possible_mask), NR_CPUS); -} +#define assign_cpu(cpu, mask, val) \ + assign_bit(cpumask_check(cpu), cpumask_bits(mask), (val)) -static inline void -set_cpu_possible(unsigned int cpu, bool possible) -{ - if (possible) - cpumask_set_cpu(cpu, &__cpu_possible_mask); - else - cpumask_clear_cpu(cpu, &__cpu_possible_mask); -} - -static inline void -set_cpu_present(unsigned int cpu, bool present) -{ - if (present) - cpumask_set_cpu(cpu, &__cpu_present_mask); - else - cpumask_clear_cpu(cpu, &__cpu_present_mask); -} +#define set_cpu_possible(cpu, possible) assign_cpu((cpu), &__cpu_possible_mask, (possible)) +#define set_cpu_enabled(cpu, enabled) assign_cpu((cpu), &__cpu_enabled_mask, (enabled)) +#define set_cpu_present(cpu, present) assign_cpu((cpu), &__cpu_present_mask, (present)) +#define set_cpu_active(cpu, active) assign_cpu((cpu), &__cpu_active_mask, (active)) +#define set_cpu_dying(cpu, dying) assign_cpu((cpu), &__cpu_dying_mask, (dying)) void set_cpu_online(unsigned int cpu, bool online); -static inline void -set_cpu_active(unsigned int cpu, bool active) -{ - if (active) - cpumask_set_cpu(cpu, &__cpu_active_mask); - else - cpumask_clear_cpu(cpu, &__cpu_active_mask); -} - -static inline void -set_cpu_dying(unsigned int cpu, bool dying) -{ - if (dying) - cpumask_set_cpu(cpu, &__cpu_dying_mask); - else - cpumask_clear_cpu(cpu, &__cpu_dying_mask); -} - /** * to_cpumask - convert a NR_CPUS bitmap to a struct cpumask * * @bitmap: the bitmap @@ -1074,7 +1069,7 @@ set_cpu_dying(unsigned int cpu, bool dying) ((struct cpumask *)(1 ? (bitmap) \ : (void *)sizeof(__check_is_bitmap(bitmap)))) -static inline int __check_is_bitmap(const unsigned long *bitmap) +static __always_inline int __check_is_bitmap(const unsigned long *bitmap) { return 1; } @@ -1089,7 +1084,7 @@ static inline int __check_is_bitmap(const unsigned long *bitmap) extern const unsigned long cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)]; -static inline const struct cpumask *get_cpu_mask(unsigned int cpu) +static __always_inline const struct cpumask *get_cpu_mask(unsigned int cpu) { const unsigned long *p = cpu_bit_bitmap[1 + cpu % BITS_PER_LONG]; p -= cpu / BITS_PER_LONG; @@ -1112,30 +1107,36 @@ static __always_inline unsigned int num_online_cpus(void) return raw_atomic_read(&__num_online_cpus); } #define num_possible_cpus() cpumask_weight(cpu_possible_mask) +#define num_enabled_cpus() cpumask_weight(cpu_enabled_mask) #define num_present_cpus() cpumask_weight(cpu_present_mask) #define num_active_cpus() cpumask_weight(cpu_active_mask) -static inline bool cpu_online(unsigned int cpu) +static __always_inline bool cpu_online(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_online_mask); } -static inline bool cpu_possible(unsigned int cpu) +static __always_inline bool cpu_enabled(unsigned int cpu) +{ + return cpumask_test_cpu(cpu, cpu_enabled_mask); +} + +static __always_inline bool cpu_possible(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_possible_mask); } -static inline bool cpu_present(unsigned int cpu) +static __always_inline bool cpu_present(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_present_mask); } -static inline bool cpu_active(unsigned int cpu) +static __always_inline bool cpu_active(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_active_mask); } -static inline bool cpu_dying(unsigned int cpu) +static __always_inline bool cpu_dying(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_dying_mask); } @@ -1144,30 +1145,36 @@ static inline bool cpu_dying(unsigned int cpu) #define num_online_cpus() 1U #define num_possible_cpus() 1U +#define num_enabled_cpus() 1U #define num_present_cpus() 1U #define num_active_cpus() 1U -static inline bool cpu_online(unsigned int cpu) +static __always_inline bool cpu_online(unsigned int cpu) { return cpu == 0; } -static inline bool cpu_possible(unsigned int cpu) +static __always_inline bool cpu_possible(unsigned int cpu) { return cpu == 0; } -static inline bool cpu_present(unsigned int cpu) +static __always_inline bool cpu_enabled(unsigned int cpu) { return cpu == 0; } -static inline bool cpu_active(unsigned int cpu) +static __always_inline bool cpu_present(unsigned int cpu) { return cpu == 0; } -static inline bool cpu_dying(unsigned int cpu) +static __always_inline bool cpu_active(unsigned int cpu) +{ + return cpu == 0; +} + +static __always_inline bool cpu_dying(unsigned int cpu) { return false; } @@ -1201,7 +1208,7 @@ static inline bool cpu_dying(unsigned int cpu) * Return: the length of the (null-terminated) @buf string, zero if * nothing is copied. */ -static inline ssize_t +static __always_inline ssize_t cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask) { return bitmap_print_to_pagebuf(list, buf, cpumask_bits(mask), @@ -1224,9 +1231,9 @@ cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask) * Return: the length of how many bytes have been copied, excluding * terminating '\0'. */ -static inline ssize_t -cpumap_print_bitmask_to_buf(char *buf, const struct cpumask *mask, - loff_t off, size_t count) +static __always_inline +ssize_t cpumap_print_bitmask_to_buf(char *buf, const struct cpumask *mask, + loff_t off, size_t count) { return bitmap_print_bitmask_to_buf(buf, cpumask_bits(mask), nr_cpu_ids, off, count) - 1; @@ -1246,9 +1253,9 @@ cpumap_print_bitmask_to_buf(char *buf, const struct cpumask *mask, * Return: the length of how many bytes have been copied, excluding * terminating '\0'. */ -static inline ssize_t -cpumap_print_list_to_buf(char *buf, const struct cpumask *mask, - loff_t off, size_t count) +static __always_inline +ssize_t cpumap_print_list_to_buf(char *buf, const struct cpumask *mask, + loff_t off, size_t count) { return bitmap_print_list_to_buf(buf, cpumask_bits(mask), nr_cpu_ids, off, count) - 1; diff --git a/include/linux/cpumask_types.h b/include/linux/cpumask_types.h new file mode 100644 index 000000000000..461ed1b6bcdb --- /dev/null +++ b/include/linux/cpumask_types.h @@ -0,0 +1,66 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_CPUMASK_TYPES_H +#define __LINUX_CPUMASK_TYPES_H + +#include <linux/bitops.h> +#include <linux/threads.h> + +/* Don't assign or return these: may not be this big! */ +typedef struct cpumask { DECLARE_BITMAP(bits, NR_CPUS); } cpumask_t; + +/** + * cpumask_bits - get the bits in a cpumask + * @maskp: the struct cpumask * + * + * You should only assume nr_cpu_ids bits of this mask are valid. This is + * a macro so it's const-correct. + */ +#define cpumask_bits(maskp) ((maskp)->bits) + +/* + * cpumask_var_t: struct cpumask for stack usage. + * + * Oh, the wicked games we play! In order to make kernel coding a + * little more difficult, we typedef cpumask_var_t to an array or a + * pointer: doing &mask on an array is a noop, so it still works. + * + * i.e. + * cpumask_var_t tmpmask; + * if (!alloc_cpumask_var(&tmpmask, GFP_KERNEL)) + * return -ENOMEM; + * + * ... use 'tmpmask' like a normal struct cpumask * ... + * + * free_cpumask_var(tmpmask); + * + * + * However, one notable exception is there. alloc_cpumask_var() allocates + * only nr_cpumask_bits bits (in the other hand, real cpumask_t always has + * NR_CPUS bits). Therefore you don't have to dereference cpumask_var_t. + * + * cpumask_var_t tmpmask; + * if (!alloc_cpumask_var(&tmpmask, GFP_KERNEL)) + * return -ENOMEM; + * + * var = *tmpmask; + * + * This code makes NR_CPUS length memcopy and brings to a memory corruption. + * cpumask_copy() provide safe copy functionality. + * + * Note that there is another evil here: If you define a cpumask_var_t + * as a percpu variable then the way to obtain the address of the cpumask + * structure differently influences what this_cpu_* operation needs to be + * used. Please use this_cpu_cpumask_var_t in those cases. The direct use + * of this_cpu_ptr() or this_cpu_read() will lead to failures when the + * other type of cpumask_var_t implementation is configured. + * + * Please also note that __cpumask_var_read_mostly can be used to declare + * a cpumask_var_t variable itself (not its content) as read mostly. + */ +#ifdef CONFIG_CPUMASK_OFFSTACK +typedef struct cpumask *cpumask_var_t; +#else +typedef struct cpumask cpumask_var_t[1]; +#endif /* CONFIG_CPUMASK_OFFSTACK */ + +#endif /* __LINUX_CPUMASK_TYPES_H */ diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 0ce6ff0d9c9a..835e7b793f6a 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -70,7 +70,6 @@ extern int cpuset_init(void); extern void cpuset_init_smp(void); extern void cpuset_force_rebuild(void); extern void cpuset_update_active_cpus(void); -extern void cpuset_wait_for_hotplug(void); extern void inc_dl_tasks_cs(struct task_struct *task); extern void dec_dl_tasks_cs(struct task_struct *task); extern void cpuset_lock(void); @@ -100,6 +99,7 @@ static inline bool cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) extern int cpuset_mems_allowed_intersects(const struct task_struct *tsk1, const struct task_struct *tsk2); +#ifdef CONFIG_CPUSETS_V1 #define cpuset_memory_pressure_bump() \ do { \ if (cpuset_memory_pressure_enabled) \ @@ -107,6 +107,9 @@ extern int cpuset_mems_allowed_intersects(const struct task_struct *tsk1, } while (0) extern int cpuset_memory_pressure_enabled; extern void __cpuset_memory_pressure_bump(void); +#else +static inline void cpuset_memory_pressure_bump(void) { } +#endif extern void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task); @@ -114,7 +117,6 @@ extern int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *tsk); extern int cpuset_mem_spread_node(void); -extern int cpuset_slab_spread_node(void); static inline int cpuset_do_page_mem_spread(void) { @@ -185,8 +187,6 @@ static inline void cpuset_update_active_cpus(void) partition_sched_domains(1, NULL, NULL); } -static inline void cpuset_wait_for_hotplug(void) { } - static inline void inc_dl_tasks_cs(struct task_struct *task) { } static inline void dec_dl_tasks_cs(struct task_struct *task) { } static inline void cpuset_lock(void) { } @@ -249,11 +249,6 @@ static inline int cpuset_mem_spread_node(void) return 0; } -static inline int cpuset_slab_spread_node(void) -{ - return 0; -} - static inline int cpuset_do_page_mem_spread(void) { return 0; diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h index d33352c2e386..44305336314e 100644 --- a/include/linux/crash_core.h +++ b/include/linux/crash_core.h @@ -37,17 +37,16 @@ static inline void arch_kexec_unprotect_crashkres(void) { } #ifndef arch_crash_handle_hotplug_event -static inline void arch_crash_handle_hotplug_event(struct kimage *image) { } +static inline void arch_crash_handle_hotplug_event(struct kimage *image, void *arg) { } #endif -int crash_check_update_elfcorehdr(void); +int crash_check_hotplug_support(void); -#ifndef crash_hotplug_cpu_support -static inline int crash_hotplug_cpu_support(void) { return 0; } -#endif - -#ifndef crash_hotplug_memory_support -static inline int crash_hotplug_memory_support(void) { return 0; } +#ifndef arch_crash_hotplug_support +static inline int arch_crash_hotplug_support(struct kimage *image, unsigned long kexec_flags) +{ + return 0; +} #endif #ifndef crash_get_elfcorehdr_size diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index acc55626afdc..2f2555e6407c 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -20,6 +20,8 @@ extern int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size); extern void elfcorehdr_free(unsigned long long addr); extern ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos); extern ssize_t elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos); +void elfcorehdr_fill_device_ram_ptload_elf64(Elf64_Phdr *phdr, + unsigned long long paddr, unsigned long long size); extern int remap_oldmem_pfn_range(struct vm_area_struct *vma, unsigned long from, unsigned long pfn, unsigned long size, pgprot_t prot); @@ -99,6 +101,12 @@ static inline void vmcore_unusable(void) * indicated in the vmcore instead. For example, a ballooned page * contains no data and reading from such a page will cause high * load in the hypervisor. + * @get_device_ram: query RAM ranges that can only be detected by device + * drivers, such as the virtio-mem driver, so they can be included in + * the crash dump on architectures that allocate the elfcore hdr in the dump + * ("2nd") kernel. Indicated RAM ranges may contain holes to reduce the + * total number of ranges; such holes can be detected using the pfn_is_ram + * callback just like for other RAM. * @next: List head to manage registered callbacks internally; initialized by * register_vmcore_cb(). * @@ -109,11 +117,44 @@ static inline void vmcore_unusable(void) */ struct vmcore_cb { bool (*pfn_is_ram)(struct vmcore_cb *cb, unsigned long pfn); + int (*get_device_ram)(struct vmcore_cb *cb, struct list_head *list); struct list_head next; }; extern void register_vmcore_cb(struct vmcore_cb *cb); extern void unregister_vmcore_cb(struct vmcore_cb *cb); +struct vmcore_range { + struct list_head list; + unsigned long long paddr; + unsigned long long size; + loff_t offset; +}; + +/* Allocate a vmcore range and add it to the list. */ +static inline int vmcore_alloc_add_range(struct list_head *list, + unsigned long long paddr, unsigned long long size) +{ + struct vmcore_range *m = kzalloc(sizeof(*m), GFP_KERNEL); + + if (!m) + return -ENOMEM; + m->paddr = paddr; + m->size = size; + list_add_tail(&m->list, list); + return 0; +} + +/* Free a list of vmcore ranges. */ +static inline void vmcore_free_ranges(struct list_head *list) +{ + struct vmcore_range *m, *tmp; + + list_for_each_entry_safe(m, tmp, list, list) { + list_del(&m->list); + kfree(m); + } +} + #else /* !CONFIG_CRASH_DUMP */ static inline bool is_kdump_kernel(void) { return false; } #endif /* CONFIG_CRASH_DUMP */ diff --git a/include/linux/crc-t10dif.h b/include/linux/crc-t10dif.h index 6bb0c0bf357b..16787c1cee21 100644 --- a/include/linux/crc-t10dif.h +++ b/include/linux/crc-t10dif.h @@ -6,11 +6,29 @@ #define CRC_T10DIF_DIGEST_SIZE 2 #define CRC_T10DIF_BLOCK_SIZE 1 -#define CRC_T10DIF_STRING "crct10dif" -extern __u16 crc_t10dif_generic(__u16 crc, const unsigned char *buffer, - size_t len); -extern __u16 crc_t10dif(unsigned char const *, size_t); -extern __u16 crc_t10dif_update(__u16 crc, unsigned char const *, size_t); +u16 crc_t10dif_arch(u16 crc, const u8 *p, size_t len); +u16 crc_t10dif_generic(u16 crc, const u8 *p, size_t len); + +static inline u16 crc_t10dif_update(u16 crc, const u8 *p, size_t len) +{ + if (IS_ENABLED(CONFIG_CRC_T10DIF_ARCH)) + return crc_t10dif_arch(crc, p, len); + return crc_t10dif_generic(crc, p, len); +} + +static inline u16 crc_t10dif(const u8 *p, size_t len) +{ + return crc_t10dif_update(0, p, len); +} + +#if IS_ENABLED(CONFIG_CRC_T10DIF_ARCH) +bool crc_t10dif_is_optimized(void); +#else +static inline bool crc_t10dif_is_optimized(void) +{ + return false; +} +#endif #endif diff --git a/include/linux/crc32.h b/include/linux/crc32.h index 9e8a032c1788..e9bd40056687 100644 --- a/include/linux/crc32.h +++ b/include/linux/crc32.h @@ -8,8 +8,49 @@ #include <linux/types.h> #include <linux/bitrev.h> -u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len); -u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len); +u32 __pure crc32_le_arch(u32 crc, const u8 *p, size_t len); +u32 __pure crc32_le_base(u32 crc, const u8 *p, size_t len); +u32 __pure crc32_be_arch(u32 crc, const u8 *p, size_t len); +u32 __pure crc32_be_base(u32 crc, const u8 *p, size_t len); +u32 __pure crc32c_le_arch(u32 crc, const u8 *p, size_t len); +u32 __pure crc32c_le_base(u32 crc, const u8 *p, size_t len); + +static inline u32 __pure crc32_le(u32 crc, const u8 *p, size_t len) +{ + if (IS_ENABLED(CONFIG_CRC32_ARCH)) + return crc32_le_arch(crc, p, len); + return crc32_le_base(crc, p, len); +} + +static inline u32 __pure crc32_be(u32 crc, const u8 *p, size_t len) +{ + if (IS_ENABLED(CONFIG_CRC32_ARCH)) + return crc32_be_arch(crc, p, len); + return crc32_be_base(crc, p, len); +} + +/* TODO: leading underscores should be dropped once callers have been updated */ +static inline u32 __pure __crc32c_le(u32 crc, const u8 *p, size_t len) +{ + if (IS_ENABLED(CONFIG_CRC32_ARCH)) + return crc32c_le_arch(crc, p, len); + return crc32c_le_base(crc, p, len); +} + +/* + * crc32_optimizations() returns flags that indicate which CRC32 library + * functions are using architecture-specific optimizations. Unlike + * IS_ENABLED(CONFIG_CRC32_ARCH) it takes into account the different CRC32 + * variants and also whether any needed CPU features are available at runtime. + */ +#define CRC32_LE_OPTIMIZATION BIT(0) /* crc32_le() is optimized */ +#define CRC32_BE_OPTIMIZATION BIT(1) /* crc32_be() is optimized */ +#define CRC32C_OPTIMIZATION BIT(2) /* __crc32c_le() is optimized */ +#if IS_ENABLED(CONFIG_CRC32_ARCH) +u32 crc32_optimizations(void); +#else +static inline u32 crc32_optimizations(void) { return 0; } +#endif /** * crc32_le_combine - Combine two crc32 check values into one. For two @@ -36,8 +77,6 @@ static inline u32 crc32_le_combine(u32 crc1, u32 crc2, size_t len2) return crc32_le_shift(crc1, len2) ^ crc2; } -u32 __pure __crc32c_le(u32 crc, unsigned char const *p, size_t len); - /** * __crc32c_le_combine - Combine two crc32c check values into one. For two * sequences of bytes, seq1 and seq2 with lengths len1 diff --git a/include/linux/crc32c.h b/include/linux/crc32c.h index 357ae4611a45..47eb78003c26 100644 --- a/include/linux/crc32c.h +++ b/include/linux/crc32c.h @@ -2,9 +2,12 @@ #ifndef _LINUX_CRC32C_H #define _LINUX_CRC32C_H -#include <linux/types.h> +#include <linux/crc32.h> -extern u32 crc32c(u32 crc, const void *address, unsigned int length); +static inline u32 crc32c(u32 crc, const void *address, unsigned int length) +{ + return __crc32c_le(crc, address, length); +} /* This macro exists for backwards-compatibility. */ #define crc32c_le crc32c diff --git a/include/linux/cred.h b/include/linux/cred.h index 2976f534a7a3..0c3c4b16b469 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -155,8 +155,6 @@ extern struct cred *prepare_creds(void); extern struct cred *prepare_exec_creds(void); extern int commit_creds(struct cred *); extern void abort_creds(struct cred *); -extern const struct cred *override_creds(const struct cred *); -extern void revert_creds(const struct cred *); extern struct cred *prepare_kernel_cred(struct task_struct *); extern int set_security_override(struct cred *, u32); extern int set_security_override_from_ctx(struct cred *, const char *); @@ -172,30 +170,20 @@ static inline bool cap_ambient_invariant_ok(const struct cred *cred) cred->cap_inheritable)); } -/** - * get_new_cred_many - Get references on a new set of credentials - * @cred: The new credentials to reference - * @nr: Number of references to acquire - * - * Get references on the specified set of new credentials. The caller must - * release all acquired references. - */ -static inline struct cred *get_new_cred_many(struct cred *cred, int nr) +static inline const struct cred *override_creds(const struct cred *override_cred) { - atomic_long_add(nr, &cred->usage); - return cred; + const struct cred *old = current->cred; + + rcu_assign_pointer(current->cred, override_cred); + return old; } -/** - * get_new_cred - Get a reference on a new set of credentials - * @cred: The new credentials to reference - * - * Get a reference on the specified set of new credentials. The caller must - * release the reference. - */ -static inline struct cred *get_new_cred(struct cred *cred) +static inline const struct cred *revert_creds(const struct cred *revert_cred) { - return get_new_cred_many(cred, 1); + const struct cred *override_cred = current->cred; + + rcu_assign_pointer(current->cred, revert_cred); + return override_cred; } /** @@ -218,7 +206,8 @@ static inline const struct cred *get_cred_many(const struct cred *cred, int nr) if (!cred) return cred; nonconst_cred->non_rcu = 0; - return get_new_cred_many(nonconst_cred, nr); + atomic_long_add(nr, &nonconst_cred->usage); + return cred; } /* diff --git a/include/linux/cxl-event.h b/include/linux/cxl-event.h deleted file mode 100644 index 03fa6d50d46f..000000000000 --- a/include/linux/cxl-event.h +++ /dev/null @@ -1,143 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 2023 Intel Corporation. */ -#ifndef _LINUX_CXL_EVENT_H -#define _LINUX_CXL_EVENT_H - -/* - * Common Event Record Format - * CXL rev 3.0 section 8.2.9.2.1; Table 8-42 - */ -struct cxl_event_record_hdr { - u8 length; - u8 flags[3]; - __le16 handle; - __le16 related_handle; - __le64 timestamp; - u8 maint_op_class; - u8 reserved[15]; -} __packed; - -#define CXL_EVENT_RECORD_DATA_LENGTH 0x50 -struct cxl_event_generic { - struct cxl_event_record_hdr hdr; - u8 data[CXL_EVENT_RECORD_DATA_LENGTH]; -} __packed; - -/* - * General Media Event Record - * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43 - */ -#define CXL_EVENT_GEN_MED_COMP_ID_SIZE 0x10 -struct cxl_event_gen_media { - struct cxl_event_record_hdr hdr; - __le64 phys_addr; - u8 descriptor; - u8 type; - u8 transaction_type; - u8 validity_flags[2]; - u8 channel; - u8 rank; - u8 device[3]; - u8 component_id[CXL_EVENT_GEN_MED_COMP_ID_SIZE]; - u8 reserved[46]; -} __packed; - -/* - * DRAM Event Record - DER - * CXL rev 3.0 section 8.2.9.2.1.2; Table 3-44 - */ -#define CXL_EVENT_DER_CORRECTION_MASK_SIZE 0x20 -struct cxl_event_dram { - struct cxl_event_record_hdr hdr; - __le64 phys_addr; - u8 descriptor; - u8 type; - u8 transaction_type; - u8 validity_flags[2]; - u8 channel; - u8 rank; - u8 nibble_mask[3]; - u8 bank_group; - u8 bank; - u8 row[3]; - u8 column[2]; - u8 correction_mask[CXL_EVENT_DER_CORRECTION_MASK_SIZE]; - u8 reserved[0x17]; -} __packed; - -/* - * Get Health Info Record - * CXL rev 3.0 section 8.2.9.8.3.1; Table 8-100 - */ -struct cxl_get_health_info { - u8 health_status; - u8 media_status; - u8 add_status; - u8 life_used; - u8 device_temp[2]; - u8 dirty_shutdown_cnt[4]; - u8 cor_vol_err_cnt[4]; - u8 cor_per_err_cnt[4]; -} __packed; - -/* - * Memory Module Event Record - * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45 - */ -struct cxl_event_mem_module { - struct cxl_event_record_hdr hdr; - u8 event_type; - struct cxl_get_health_info info; - u8 reserved[0x3d]; -} __packed; - -union cxl_event { - struct cxl_event_generic generic; - struct cxl_event_gen_media gen_media; - struct cxl_event_dram dram; - struct cxl_event_mem_module mem_module; -} __packed; - -/* - * Common Event Record Format; in event logs - * CXL rev 3.0 section 8.2.9.2.1; Table 8-42 - */ -struct cxl_event_record_raw { - uuid_t id; - union cxl_event event; -} __packed; - -enum cxl_event_type { - CXL_CPER_EVENT_GENERIC, - CXL_CPER_EVENT_GEN_MEDIA, - CXL_CPER_EVENT_DRAM, - CXL_CPER_EVENT_MEM_MODULE, -}; - -#define CPER_CXL_DEVICE_ID_VALID BIT(0) -#define CPER_CXL_DEVICE_SN_VALID BIT(1) -#define CPER_CXL_COMP_EVENT_LOG_VALID BIT(2) -struct cxl_cper_event_rec { - struct { - u32 length; - u64 validation_bits; - struct cper_cxl_event_devid { - u16 vendor_id; - u16 device_id; - u8 func_num; - u8 device_num; - u8 bus_num; - u16 segment_num; - u16 slot_num; /* bits 2:0 reserved */ - u8 reserved; - } __packed device_id; - struct cper_cxl_event_sn { - u32 lower_dw; - u32 upper_dw; - } __packed dev_serial_num; - } __packed hdr; - - union cxl_event event; -} __packed; - -#endif /* _LINUX_CXL_EVENT_H */ diff --git a/include/linux/damon.h b/include/linux/damon.h index 886d07294f4e..af525252b853 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -105,6 +105,8 @@ struct damon_target { * @DAMOS_NOHUGEPAGE: Call ``madvise()`` for the region with MADV_NOHUGEPAGE. * @DAMOS_LRU_PRIO: Prioritize the region on its LRU lists. * @DAMOS_LRU_DEPRIO: Deprioritize the region on its LRU lists. + * @DAMOS_MIGRATE_HOT: Migrate the regions prioritizing warmer regions. + * @DAMOS_MIGRATE_COLD: Migrate the regions prioritizing colder regions. * @DAMOS_STAT: Do nothing but count the stat. * @NR_DAMOS_ACTIONS: Total number of DAMOS actions * @@ -122,6 +124,8 @@ enum damos_action { DAMOS_NOHUGEPAGE, DAMOS_LRU_PRIO, DAMOS_LRU_DEPRIO, + DAMOS_MIGRATE_HOT, + DAMOS_MIGRATE_COLD, DAMOS_STAT, /* Do nothing but only record the stat */ NR_DAMOS_ACTIONS, }; @@ -189,11 +193,16 @@ struct damos_quota_goal { * size quota is set, DAMON tries to apply the action only up to &sz bytes * within &reset_interval. * - * Internally, the time quota is transformed to a size quota using estimated - * throughput of the scheme's action. DAMON then compares it against &sz and - * uses smaller one as the effective quota. + * To convince the different types of quotas and goals, DAMON internally + * converts those into one single size quota called "effective quota". DAMON + * internally uses it as the only one real quota. The conversion is made as + * follows. * - * If @goals is not empt, DAMON calculates yet another size quota based on the + * The time quota is transformed to a size quota using estimated throughput of + * the scheme's action. DAMON then compares it against &sz and uses smaller + * one as the effective quota. + * + * If @goals is not empty, DAMON calculates yet another size quota based on the * goals using its internal feedback loop algorithm, for every @reset_interval. * Then, if the new size quota is smaller than the effective quota, it uses the * new size quota as the effective quota. @@ -229,7 +238,6 @@ struct damos_quota { unsigned long charge_addr_from; /* For prioritization */ - unsigned long histogram[DAMOS_MAX_SCORE + 1]; unsigned int min_score; /* For feedback loop */ @@ -283,13 +291,33 @@ struct damos_watermarks { * @sz_tried: Total size of regions that the scheme is tried to be applied. * @nr_applied: Total number of regions that the scheme is applied. * @sz_applied: Total size of regions that the scheme is applied. + * @sz_ops_filter_passed: + * Total bytes that passed ops layer-handled DAMOS filters. * @qt_exceeds: Total number of times the quota of the scheme has exceeded. + * + * "Tried an action to a region" in this context means the DAMOS core logic + * determined the region as eligible to apply the action. The access pattern + * (&struct damos_access_pattern), quotas (&struct damos_quota), watermarks + * (&struct damos_watermarks) and filters (&struct damos_filter) that handled + * on core logic can affect this. The core logic asks the operation set + * (&struct damon_operations) to apply the action to the region. + * + * "Applied an action to a region" in this context means the operation set + * (&struct damon_operations) successfully applied the action to the region, at + * least to a part of the region. The filters (&struct damos_filter) that + * handled on operation set layer and type of the action and pages of the + * region can affect this. For example, if a filter is set to exclude + * anonymous pages and the region has only anonymous pages, the region will be + * failed at applying the action. If the action is &DAMOS_PAGEOUT and all + * pages of the region are already paged out, the region will be failed at + * applying the action. */ struct damos_stat { unsigned long nr_tried; unsigned long sz_tried; unsigned long nr_applied; unsigned long sz_applied; + unsigned long sz_ops_filter_passed; unsigned long qt_exceeds; }; @@ -297,6 +325,7 @@ struct damos_stat { * 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. + * @DAMOS_FILTER_TYPE_YOUNG: Recently accessed pages. * @DAMOS_FILTER_TYPE_ADDR: Address range. * @DAMOS_FILTER_TYPE_TARGET: Data Access Monitoring target. * @NR_DAMOS_FILTER_TYPES: Number of filter types. @@ -315,6 +344,7 @@ struct damos_stat { enum damos_filter_type { DAMOS_FILTER_TYPE_ANON, DAMOS_FILTER_TYPE_MEMCG, + DAMOS_FILTER_TYPE_YOUNG, DAMOS_FILTER_TYPE_ADDR, DAMOS_FILTER_TYPE_TARGET, NR_DAMOS_FILTER_TYPES, @@ -322,8 +352,9 @@ enum damos_filter_type { /** * struct damos_filter - DAMOS action target memory filter. - * @type: Type of the page. - * @matching: If the matching page should filtered out or in. + * @type: Type of the target memory. + * @matching: Whether this is for @type-matching memory. + * @allow: Whether to include or exclude the @matching memory. * @memcg_id: Memcg id of the question if @type is DAMOS_FILTER_MEMCG. * @addr_range: Address range if @type is DAMOS_FILTER_TYPE_ADDR. * @target_idx: Index of the &struct damon_target of @@ -332,13 +363,15 @@ enum damos_filter_type { * @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. - * Support of each filter type depends on the running &struct damon_operations - * and the type. Refer to &enum damos_filter_type for more detai. + * byte of the region matches to this given condition and avoid applying the + * action if so. Support of each filter type depends on the running &struct + * damon_operations and the type. Refer to &enum damos_filter_type for more + * details. */ struct damos_filter { enum damos_filter_type type; bool matching; + bool allow; union { unsigned short memcg_id; struct damon_addr_range addr_range; @@ -347,6 +380,31 @@ struct damos_filter { struct list_head list; }; +struct damon_ctx; +struct damos; + +/** + * struct damos_walk_control - Control damos_walk(). + * + * @walk_fn: Function to be called back for each region. + * @data: Data that will be passed to walk functions. + * + * Control damos_walk(), which requests specific kdamond to invoke the given + * function to each region that eligible to apply actions of the kdamond's + * schemes. Refer to damos_walk() for more details. + */ +struct damos_walk_control { + void (*walk_fn)(void *data, struct damon_ctx *ctx, + struct damon_target *t, struct damon_region *r, + struct damos *s, unsigned long sz_filter_passed); + void *data; +/* private: internal use only */ + /* informs if the kdamond finished handling of the walk request */ + struct completion completion; + /* informs if the walk is canceled. */ + bool canceled; +}; + /** * struct damos_access_pattern - Target access pattern of the given scheme. * @min_sz_region: Minimum size of target regions. @@ -372,6 +430,7 @@ struct damos_access_pattern { * @apply_interval_us: The time between applying the @action. * @quota: Control the aggressiveness of this scheme. * @wmarks: Watermarks for automated (in)activation of this scheme. + * @target_nid: Destination node if @action is "migrate_{hot,cold}". * @filters: Additional set of &struct damos_filter for &action. * @stat: Statistics of this scheme. * @list: List head for siblings. @@ -387,6 +446,10 @@ struct damos_access_pattern { * monitoring context are inactive, DAMON stops monitoring either, and just * repeatedly checks the watermarks. * + * @target_nid is used to set the migration target node for migrate_hot or + * migrate_cold actions, which means it's only meaningful when @action is either + * "migrate_hot" or "migrate_cold". + * * Before applying the &action to a memory region, &struct damon_operations * implementation could check pages of the region and skip &action to respect * &filters @@ -405,9 +468,14 @@ struct damos { * @action */ unsigned long next_apply_sis; + /* informs if ongoing DAMOS walk for this scheme is finished */ + bool walk_completed; /* public: */ struct damos_quota quota; struct damos_watermarks wmarks; + union { + int target_nid; + }; struct list_head filters; struct damos_stat stat; struct list_head list; @@ -429,8 +497,6 @@ enum damon_ops_id { NR_DAMON_OPS, }; -struct damon_ctx; - /** * struct damon_operations - Monitoring operations for given use cases. * @@ -474,7 +540,8 @@ struct damon_ctx; * @apply_scheme is called from @kdamond when a region for user provided * DAMON-based operation scheme is found. It should apply the scheme's action * to the region and return bytes of the region that the action is successfully - * applied. + * applied. It should also report how many bytes of the region has passed + * filters (&struct damos_filter) that handled by itself. * @target_valid should check whether the target is still valid for the * monitoring. * @cleanup is called from @kdamond just before its termination. @@ -491,7 +558,7 @@ struct damon_operations { struct damos *scheme); unsigned long (*apply_scheme)(struct damon_ctx *context, struct damon_target *t, struct damon_region *r, - struct damos *scheme); + struct damos *scheme, unsigned long *sz_filter_passed); bool (*target_valid)(struct damon_target *t); void (*cleanup)(struct damon_ctx *context); }; @@ -539,6 +606,27 @@ struct damon_callback { void (*before_terminate)(struct damon_ctx *context); }; +/* + * struct damon_call_control - Control damon_call(). + * + * @fn: Function to be called back. + * @data: Data that will be passed to @fn. + * @return_code: Return code from @fn invocation. + * + * Control damon_call(), which requests specific kdamond to invoke a given + * function. Refer to damon_call() for more details. + */ +struct damon_call_control { + int (*fn)(void *data); + void *data; + int return_code; +/* private: internal use only */ + /* informs if the kdamond finished handling of the request */ + struct completion completion; + /* informs if the kdamond canceled @fn infocation */ + bool canceled; +}; + /** * struct damon_attrs - Monitoring attributes for accuracy/overhead control. * @@ -616,6 +704,14 @@ struct damon_ctx { unsigned long next_ops_update_sis; /* for waiting until the execution of the kdamond_fn is started */ struct completion kdamond_started; + /* for scheme quotas prioritization */ + unsigned long *regions_score_histogram; + + struct damon_call_control *call_control; + struct mutex call_control_lock; + + struct damos_walk_control *walk_control; + struct mutex walk_control_lock; /* public: */ struct task_struct *kdamond; @@ -710,7 +806,7 @@ void damon_update_region_access_rate(struct damon_region *r, bool accessed, struct damon_attrs *attrs); struct damos_filter *damos_new_filter(enum damos_filter_type type, - bool matching); + bool matching, bool allow); void damos_add_filter(struct damos *s, struct damos_filter *f); void damos_destroy_filter(struct damos_filter *f); @@ -724,9 +820,11 @@ struct damos *damon_new_scheme(struct damos_access_pattern *pattern, enum damos_action action, unsigned long apply_interval_us, struct damos_quota *quota, - struct damos_watermarks *wmarks); + struct damos_watermarks *wmarks, + int target_nid); void damon_add_scheme(struct damon_ctx *ctx, struct damos *s); void damon_destroy_scheme(struct damos *s); +int damos_commit_quota_goals(struct damos_quota *dst, struct damos_quota *src); struct damon_target *damon_new_target(void); void damon_add_target(struct damon_ctx *ctx, struct damon_target *t); @@ -740,6 +838,7 @@ void damon_destroy_ctx(struct damon_ctx *ctx); int damon_set_attrs(struct damon_ctx *ctx, struct damon_attrs *attrs); void damon_set_schemes(struct damon_ctx *ctx, struct damos **schemes, ssize_t nr_schemes); +int damon_commit_ctx(struct damon_ctx *old_ctx, struct damon_ctx *new_ctx); int damon_nr_running_ctxs(void); bool damon_is_registered_ops(enum damon_ops_id id); int damon_register_ops(struct damon_operations *ops); @@ -761,6 +860,9 @@ static inline unsigned int damon_max_nr_accesses(const struct damon_attrs *attrs int damon_start(struct damon_ctx **ctxs, int nr_ctxs, bool exclusive); int damon_stop(struct damon_ctx **ctxs, int nr_ctxs); +int damon_call(struct damon_ctx *ctx, struct damon_call_control *control); +int damos_walk(struct damon_ctx *ctx, struct damos_walk_control *control); + int damon_set_region_biggest_system_ram_default(struct damon_target *t, unsigned long *start, unsigned long *end); diff --git a/include/linux/dax.h b/include/linux/dax.h index 9d3e3327af4c..df41a0017b31 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -27,12 +27,6 @@ struct dax_operations { */ long (*direct_access)(struct dax_device *, pgoff_t, long, enum dax_access_mode, void **, pfn_t *); - /* - * Validate whether this device is usable as an fsdax backing - * device. - */ - bool (*dax_supported)(struct dax_device *, struct block_device *, int, - sector_t, sector_t); /* zero_page_range: required operation. Zero page range */ int (*zero_page_range)(struct dax_device *, pgoff_t, size_t); /* diff --git a/include/linux/dcache.h b/include/linux/dcache.h index bf53e3894aae..4afb60365675 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -57,6 +57,7 @@ struct qstr { }; #define QSTR_INIT(n,l) { { { .len = l } }, .name = n } +#define QSTR(n) (struct qstr)QSTR_INIT(n, strlen(n)) extern const struct qstr empty_name; extern const struct qstr slash_name; @@ -68,16 +69,24 @@ extern const struct qstr dotdot_name; * large memory footprint increase). */ #ifdef CONFIG_64BIT -# define DNAME_INLINE_LEN 40 /* 192 bytes */ +# define DNAME_INLINE_WORDS 5 /* 192 bytes */ #else # ifdef CONFIG_SMP -# define DNAME_INLINE_LEN 40 /* 128 bytes */ +# define DNAME_INLINE_WORDS 9 /* 128 bytes */ # else -# define DNAME_INLINE_LEN 44 /* 128 bytes */ +# define DNAME_INLINE_WORDS 11 /* 128 bytes */ # endif #endif +#define DNAME_INLINE_LEN (DNAME_INLINE_WORDS*sizeof(unsigned long)) + +union shortname_store { + unsigned char string[DNAME_INLINE_LEN]; + unsigned long words[DNAME_INLINE_WORDS]; +}; + #define d_lock d_lockref.lock +#define d_iname d_shortname.string struct dentry { /* RCU lookup touched fields */ @@ -88,14 +97,19 @@ struct dentry { struct qstr d_name; struct inode *d_inode; /* Where the name belongs to - NULL is * negative */ - unsigned char d_iname[DNAME_INLINE_LEN]; /* small names */ + union shortname_store d_shortname; + /* --- cacheline 1 boundary (64 bytes) was 32 bytes ago --- */ /* Ref lookup also touches following */ - struct lockref d_lockref; /* per-dentry lock and refcount */ const struct dentry_operations *d_op; struct super_block *d_sb; /* The root of the dentry tree */ unsigned long d_time; /* used by d_revalidate */ void *d_fsdata; /* fs-specific data */ + /* --- cacheline 2 boundary (128 bytes) --- */ + struct lockref d_lockref; /* per-dentry lock and refcount + * keep separate from RCU lookup area if + * possible! + */ union { struct list_head d_lru; /* LRU list */ @@ -131,7 +145,8 @@ enum d_real_type { }; struct dentry_operations { - int (*d_revalidate)(struct dentry *, unsigned int); + int (*d_revalidate)(struct inode *, const struct qstr *, + struct dentry *, unsigned int); int (*d_weak_revalidate)(struct dentry *, unsigned int); int (*d_hash)(const struct dentry *, struct qstr *); int (*d_compare)(const struct dentry *, @@ -145,6 +160,8 @@ struct dentry_operations { struct vfsmount *(*d_automount)(struct path *); int (*d_manage)(const struct path *, bool); struct dentry *(*d_real)(struct dentry *, enum d_real_type type); + bool (*d_unalias_trylock)(const struct dentry *); + void (*d_unalias_unlock)(const struct dentry *); } ____cacheline_aligned; /* @@ -278,6 +295,8 @@ static inline unsigned d_count(const struct dentry *dentry) return dentry->d_lockref.count; } +ino_t d_parent_ino(struct dentry *dentry); + /* * helper function for dentry_operations.d_dname() members */ @@ -582,7 +601,7 @@ static inline struct inode *d_real_inode(const struct dentry *dentry) struct name_snapshot { struct qstr name; - unsigned char inline_name[DNAME_INLINE_LEN]; + union shortname_store inline_name; }; void take_dentry_name_snapshot(struct name_snapshot *, struct dentry *); void release_dentry_name_snapshot(struct name_snapshot *); diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index c9c65b132c0f..fa2568b4380d 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -57,7 +57,6 @@ static const struct file_operations __fops = { \ .release = simple_attr_release, \ .read = debugfs_attr_read, \ .write = (__is_signed) ? debugfs_attr_write_signed : debugfs_attr_write, \ - .llseek = no_llseek, \ } #define DEFINE_DEBUGFS_ATTRIBUTE(__fops, __get, __set, __fmt) \ @@ -68,13 +67,77 @@ static const struct file_operations __fops = { \ typedef struct vfsmount *(*debugfs_automount_t)(struct dentry *, void *); +struct debugfs_short_fops { + ssize_t (*read)(struct file *, char __user *, size_t, loff_t *); + ssize_t (*write)(struct file *, const char __user *, size_t, loff_t *); + loff_t (*llseek) (struct file *, loff_t, int); +}; + #if defined(CONFIG_DEBUG_FS) struct dentry *debugfs_lookup(const char *name, struct dentry *parent); -struct dentry *debugfs_create_file(const char *name, umode_t mode, - struct dentry *parent, void *data, - const struct file_operations *fops); +struct dentry *debugfs_create_file_full(const char *name, umode_t mode, + struct dentry *parent, void *data, + const void *aux, + const struct file_operations *fops); +struct dentry *debugfs_create_file_short(const char *name, umode_t mode, + struct dentry *parent, void *data, + const void *aux, + const struct debugfs_short_fops *fops); + +/** + * debugfs_create_file - create a file in the debugfs filesystem + * @name: a pointer to a string containing the name of the file to create. + * @mode: the permission that the file should have. + * @parent: a pointer to the parent dentry for this file. This should be a + * directory dentry if set. If this parameter is NULL, then the + * file will be created in the root of the debugfs filesystem. + * @data: a pointer to something that the caller will want to get to later + * on. The inode.i_private pointer will point to this value on + * the open() call. + * @fops: a pointer to a struct file_operations or struct debugfs_short_fops that + * should be used for this file. + * + * This is the basic "create a file" function for debugfs. It allows for a + * wide range of flexibility in creating a file, or a directory (if you want + * to create a directory, the debugfs_create_dir() function is + * recommended to be used instead.) + * + * This function will return a pointer to a dentry if it succeeds. This + * pointer must be passed to the debugfs_remove() function when the file is + * to be removed (no automatic cleanup happens if your module is unloaded, + * you are responsible here.) If an error occurs, ERR_PTR(-ERROR) will be + * returned. + * + * If debugfs is not enabled in the kernel, the value -%ENODEV will be + * returned. + * + * If fops points to a struct debugfs_short_fops, then simple_open() will be + * used for the open, and only read/write/llseek are supported and are proxied, + * so no module reference or release are needed. + * + * NOTE: it's expected that most callers should _ignore_ the errors returned + * by this function. Other debugfs functions handle the fact that the "dentry" + * passed to them could be an error and they don't crash in that case. + * Drivers should generally work fine even if debugfs fails to init anyway. + */ +#define debugfs_create_file(name, mode, parent, data, fops) \ + _Generic(fops, \ + const struct file_operations *: debugfs_create_file_full, \ + const struct debugfs_short_fops *: debugfs_create_file_short, \ + struct file_operations *: debugfs_create_file_full, \ + struct debugfs_short_fops *: debugfs_create_file_short) \ + (name, mode, parent, data, NULL, fops) + +#define debugfs_create_file_aux(name, mode, parent, data, aux, fops) \ + _Generic(fops, \ + const struct file_operations *: debugfs_create_file_full, \ + const struct debugfs_short_fops *: debugfs_create_file_short, \ + struct file_operations *: debugfs_create_file_full, \ + struct debugfs_short_fops *: debugfs_create_file_short) \ + (name, mode, parent, data, aux, fops) + struct dentry *debugfs_create_file_unsafe(const char *name, umode_t mode, struct dentry *parent, void *data, const struct file_operations *fops); @@ -100,6 +163,7 @@ void debugfs_remove(struct dentry *dentry); void debugfs_lookup_and_remove(const char *name, struct dentry *parent); const struct file_operations *debugfs_real_fops(const struct file *filp); +const void *debugfs_get_aux(const struct file *file); int debugfs_file_get(struct dentry *dentry); void debugfs_file_put(struct dentry *dentry); @@ -111,8 +175,7 @@ ssize_t debugfs_attr_write(struct file *file, const char __user *buf, ssize_t debugfs_attr_write_signed(struct file *file, const char __user *buf, size_t len, loff_t *ppos); -struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry, - struct dentry *new_dir, const char *new_name); +int debugfs_change_name(struct dentry *dentry, const char *fmt, ...) __printf(2, 3); void debugfs_create_u8(const char *name, umode_t mode, struct dentry *parent, u8 *value); @@ -206,9 +269,17 @@ static inline struct dentry *debugfs_lookup(const char *name, return ERR_PTR(-ENODEV); } +static inline struct dentry *debugfs_create_file_aux(const char *name, + umode_t mode, struct dentry *parent, + void *data, void *aux, + const void *fops) +{ + return ERR_PTR(-ENODEV); +} + static inline struct dentry *debugfs_create_file(const char *name, umode_t mode, struct dentry *parent, void *data, - const struct file_operations *fops) + const void *fops) { return ERR_PTR(-ENODEV); } @@ -259,6 +330,7 @@ static inline void debugfs_lookup_and_remove(const char *name, { } const struct file_operations *debugfs_real_fops(const struct file *filp); +void *debugfs_get_aux(const struct file *file); static inline int debugfs_file_get(struct dentry *dentry) { @@ -288,10 +360,10 @@ static inline ssize_t debugfs_attr_write_signed(struct file *file, return -ENODEV; } -static inline struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry, - struct dentry *new_dir, char *new_name) +static inline int __printf(2, 3) debugfs_change_name(struct dentry *dentry, + const char *fmt, ...) { - return ERR_PTR(-ENODEV); + return -ENODEV; } static inline void debugfs_create_u8(const char *name, umode_t mode, @@ -399,6 +471,11 @@ static inline ssize_t debugfs_read_file_str(struct file *file, #endif +#define debugfs_create_file_aux_num(name, mode, parent, data, n, fops) \ + debugfs_create_file_aux(name, mode, parent, data, \ + (void *)(unsigned long)n, fops) +#define debugfs_get_aux_num(f) (unsigned long)debugfs_get_aux(f) + /** * debugfs_create_xul - create a debugfs file that is used to read and write an * unsigned long value, formatted in hexadecimal diff --git a/include/linux/debugobjects.h b/include/linux/debugobjects.h index 32444686b6ff..8b95545e7924 100644 --- a/include/linux/debugobjects.h +++ b/include/linux/debugobjects.h @@ -23,13 +23,17 @@ struct debug_obj_descr; * @state: tracked object state * @astate: current active state * @object: pointer to the real object + * @batch_last: pointer to the last hlist node in a batch * @descr: pointer to an object type specific debug description structure */ struct debug_obj { - struct hlist_node node; - enum debug_obj_state state; - unsigned int astate; - void *object; + struct hlist_node node; + enum debug_obj_state state; + unsigned int astate; + union { + void *object; + struct hlist_node *batch_last; + }; const struct debug_obj_descr *descr; }; diff --git a/include/linux/decompress/unxz.h b/include/linux/decompress/unxz.h index f764e2a7201e..3dd2658a9dab 100644 --- a/include/linux/decompress/unxz.h +++ b/include/linux/decompress/unxz.h @@ -1,10 +1,9 @@ +/* SPDX-License-Identifier: 0BSD */ + /* * Wrapper for decompressing XZ-compressed kernel, initramfs, and initrd * * Author: Lasse Collin <lasse.collin@tukaani.org> - * - * This file has been put into the public domain. - * You can do whatever you want with this file. */ #ifndef DECOMPRESS_UNXZ_H diff --git a/include/linux/delay.h b/include/linux/delay.h index ff9cda975e30..89866bab100d 100644 --- a/include/linux/delay.h +++ b/include/linux/delay.h @@ -6,21 +6,12 @@ * Copyright (C) 1993 Linus Torvalds * * Delay routines, using a pre-computed "loops_per_jiffy" value. - * - * Please note that ndelay(), udelay() and mdelay() may return early for - * several reasons: - * 1. computed loops_per_jiffy too low (due to the time taken to - * execute the timer interrupt.) - * 2. cache behaviour affecting the time it takes to execute the - * loop function. - * 3. CPU clock rate changes. - * - * Please see this thread: - * https://lists.openwall.net/linux-kernel/2011/01/09/56 + * Sleep routines using timer list timers or hrtimers. */ #include <linux/math.h> #include <linux/sched.h> +#include <linux/jiffies.h> extern unsigned long loops_per_jiffy; @@ -35,12 +26,21 @@ extern unsigned long loops_per_jiffy; * The 2nd mdelay() definition ensures GCC will optimize away the * while loop for the common cases where n <= MAX_UDELAY_MS -- Paul G. */ - #ifndef MAX_UDELAY_MS #define MAX_UDELAY_MS 5 #endif #ifndef mdelay +/** + * mdelay - Inserting a delay based on milliseconds with busy waiting + * @n: requested delay in milliseconds + * + * See udelay() for basic information about mdelay() and it's variants. + * + * Please double check, whether mdelay() is the right way to go or whether a + * refactoring of the code is the better variant to be able to use msleep() + * instead. + */ #define mdelay(n) (\ (__builtin_constant_p(n) && (n)<=MAX_UDELAY_MS) ? udelay((n)*1000) : \ ({unsigned long __ms=(n); while (__ms--) udelay(1000);})) @@ -63,30 +63,75 @@ unsigned long msleep_interruptible(unsigned int msecs); void usleep_range_state(unsigned long min, unsigned long max, unsigned int state); +/** + * usleep_range - Sleep for an approximate time + * @min: Minimum time in microseconds to sleep + * @max: Maximum time in microseconds to sleep + * + * For basic information please refere to usleep_range_state(). + * + * The task will be in the state TASK_UNINTERRUPTIBLE during the sleep. + */ static inline void usleep_range(unsigned long min, unsigned long max) { usleep_range_state(min, max, TASK_UNINTERRUPTIBLE); } -static inline void usleep_idle_range(unsigned long min, unsigned long max) +/** + * usleep_range_idle - Sleep for an approximate time with idle time accounting + * @min: Minimum time in microseconds to sleep + * @max: Maximum time in microseconds to sleep + * + * For basic information please refere to usleep_range_state(). + * + * The sleeping task has the state TASK_IDLE during the sleep to prevent + * contribution to the load avarage. + */ +static inline void usleep_range_idle(unsigned long min, unsigned long max) { usleep_range_state(min, max, TASK_IDLE); } +/** + * ssleep - wrapper for seconds around msleep + * @seconds: Requested sleep duration in seconds + * + * Please refere to msleep() for detailed information. + */ static inline void ssleep(unsigned int seconds) { msleep(seconds * 1000); } -/* see Documentation/timers/timers-howto.rst for the thresholds */ +static const unsigned int max_slack_shift = 2; +#define USLEEP_RANGE_UPPER_BOUND ((TICK_NSEC << max_slack_shift) / NSEC_PER_USEC) + +/** + * fsleep - flexible sleep which autoselects the best mechanism + * @usecs: requested sleep duration in microseconds + * + * flseep() selects the best mechanism that will provide maximum 25% slack + * to the requested sleep duration. Therefore it uses: + * + * * udelay() loop for sleep durations <= 10 microseconds to avoid hrtimer + * overhead for really short sleep durations. + * * usleep_range() for sleep durations which would lead with the usage of + * msleep() to a slack larger than 25%. This depends on the granularity of + * jiffies. + * * msleep() for all other sleep durations. + * + * Note: When %CONFIG_HIGH_RES_TIMERS is not set, all sleeps are processed with + * the granularity of jiffies and the slack might exceed 25% especially for + * short sleep durations. + */ static inline void fsleep(unsigned long usecs) { if (usecs <= 10) udelay(usecs); - else if (usecs <= 20000) - usleep_range(usecs, 2 * usecs); + else if (usecs < USLEEP_RANGE_UPPER_BOUND) + usleep_range(usecs, usecs + (usecs >> max_slack_shift)); else - msleep(DIV_ROUND_UP(usecs, 1000)); + msleep(DIV_ROUND_UP(usecs, USEC_PER_MSEC)); } #endif /* defined(_LINUX_DELAY_H) */ diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index 6639f48dac36..800dcc360db2 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -29,25 +29,39 @@ struct task_delay_info { * XXX_delay contains the accumulated delay time in nanoseconds. */ u64 blkio_start; + u64 blkio_delay_max; + u64 blkio_delay_min; u64 blkio_delay; /* wait for sync block io completion */ u64 swapin_start; + u64 swapin_delay_max; + u64 swapin_delay_min; u64 swapin_delay; /* wait for swapin */ u32 blkio_count; /* total count of the number of sync block */ /* io operations performed */ u32 swapin_count; /* total count of swapin */ u64 freepages_start; + u64 freepages_delay_max; + u64 freepages_delay_min; u64 freepages_delay; /* wait for memory reclaim */ u64 thrashing_start; + u64 thrashing_delay_max; + u64 thrashing_delay_min; u64 thrashing_delay; /* wait for thrashing page */ u64 compact_start; + u64 compact_delay_max; + u64 compact_delay_min; u64 compact_delay; /* wait for memory compact */ u64 wpcopy_start; + u64 wpcopy_delay_max; + u64 wpcopy_delay_min; u64 wpcopy_delay; /* wait for write-protect copy */ + u64 irq_delay_max; + u64 irq_delay_min; u64 irq_delay; /* wait for IRQ/SOFTIRQ */ u32 freepages_count; /* total count of memory reclaim */ diff --git a/include/linux/dev_printk.h b/include/linux/dev_printk.h index 6bfe70decc9f..eb2094e43050 100644 --- a/include/linux/dev_printk.h +++ b/include/linux/dev_printk.h @@ -130,6 +130,16 @@ void _dev_info(const struct device *dev, const char *fmt, ...) }) /* + * Dummy dev_printk for disabled debugging statements to use whilst maintaining + * gcc's format checking. + */ +#define dev_no_printk(level, dev, fmt, ...) \ + ({ \ + if (0) \ + _dev_printk(level, dev, fmt, ##__VA_ARGS__); \ + }) + +/* * #defines for all the dev_<level> macros to prefix with whatever * possible use of #define dev_fmt(fmt) ... */ @@ -158,10 +168,7 @@ void _dev_info(const struct device *dev, const char *fmt, ...) dev_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__) #else #define dev_dbg(dev, fmt, ...) \ -({ \ - if (0) \ - dev_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__); \ -}) + dev_no_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__) #endif #ifdef CONFIG_PRINTK @@ -247,20 +254,14 @@ do { \ } while (0) #else #define dev_dbg_ratelimited(dev, fmt, ...) \ -do { \ - if (0) \ - dev_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__); \ -} while (0) + dev_no_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__) #endif #ifdef VERBOSE_DEBUG #define dev_vdbg dev_dbg #else #define dev_vdbg(dev, fmt, ...) \ -({ \ - if (0) \ - dev_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__); \ -}) + dev_no_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__) #endif /* @@ -275,5 +276,14 @@ do { \ dev_driver_string(dev), dev_name(dev), ## arg) __printf(3, 4) int dev_err_probe(const struct device *dev, int err, const char *fmt, ...); +__printf(3, 4) int dev_warn_probe(const struct device *dev, int err, const char *fmt, ...); + +/* Simple helper for dev_err_probe() when ERR_PTR() is to be returned. */ +#define dev_err_ptr_probe(dev, ___err, fmt, ...) \ + ERR_PTR(dev_err_probe(dev, ___err, fmt, ##__VA_ARGS__)) + +/* Simple helper for dev_err_probe() when ERR_CAST() is to be returned. */ +#define dev_err_cast_probe(dev, ___err_ptr, fmt, ...) \ + ERR_PTR(dev_err_probe(dev, PTR_ERR(___err_ptr), fmt, ##__VA_ARGS__)) #endif /* _DEVICE_PRINTK_H_ */ diff --git a/include/linux/devcoredump.h b/include/linux/devcoredump.h index c8f7eb6cc191..377892604ff4 100644 --- a/include/linux/devcoredump.h +++ b/include/linux/devcoredump.h @@ -12,6 +12,9 @@ #include <linux/scatterlist.h> #include <linux/slab.h> +/* if data isn't read by userspace after 5 minutes then delete it */ +#define DEVCD_TIMEOUT (HZ * 60 * 5) + /* * _devcd_free_sgtable - free all the memory of the given scatterlist table * (i.e. both pages and scatterlist instances) @@ -50,16 +53,17 @@ static inline void _devcd_free_sgtable(struct scatterlist *table) kfree(delete_iter); } - #ifdef CONFIG_DEV_COREDUMP void dev_coredumpv(struct device *dev, void *data, size_t datalen, gfp_t gfp); -void dev_coredumpm(struct device *dev, struct module *owner, - void *data, size_t datalen, gfp_t gfp, - ssize_t (*read)(char *buffer, loff_t offset, size_t count, - void *data, size_t datalen), - void (*free)(void *data)); +void dev_coredumpm_timeout(struct device *dev, struct module *owner, + void *data, size_t datalen, gfp_t gfp, + ssize_t (*read)(char *buffer, loff_t offset, + size_t count, void *data, + size_t datalen), + void (*free)(void *data), + unsigned long timeout); void dev_coredumpsg(struct device *dev, struct scatterlist *table, size_t datalen, gfp_t gfp); @@ -73,11 +77,13 @@ static inline void dev_coredumpv(struct device *dev, void *data, } static inline void -dev_coredumpm(struct device *dev, struct module *owner, - void *data, size_t datalen, gfp_t gfp, - ssize_t (*read)(char *buffer, loff_t offset, size_t count, - void *data, size_t datalen), - void (*free)(void *data)) +dev_coredumpm_timeout(struct device *dev, struct module *owner, + void *data, size_t datalen, gfp_t gfp, + ssize_t (*read)(char *buffer, loff_t offset, + size_t count, void *data, + size_t datalen), + void (*free)(void *data), + unsigned long timeout) { free(data); } @@ -92,4 +98,29 @@ static inline void dev_coredump_put(struct device *dev) } #endif /* CONFIG_DEV_COREDUMP */ +/** + * dev_coredumpm - create device coredump with read/free methods + * @dev: the struct device for the crashed device + * @owner: the module that contains the read/free functions, use %THIS_MODULE + * @data: data cookie for the @read/@free functions + * @datalen: length of the data + * @gfp: allocation flags + * @read: function to read from the given buffer + * @free: function to free the given buffer + * + * Creates a new device coredump for the given device. If a previous one hasn't + * been read yet, the new coredump is discarded. The data lifetime is determined + * by the device coredump framework and when it is no longer needed the @free + * function will be called to free the data. + */ +static inline void dev_coredumpm(struct device *dev, struct module *owner, + void *data, size_t datalen, gfp_t gfp, + ssize_t (*read)(char *buffer, loff_t offset, size_t count, + void *data, size_t datalen), + void (*free)(void *data)) +{ + dev_coredumpm_timeout(dev, owner, data, datalen, gfp, read, free, + DEVCD_TIMEOUT); +} + #endif /* __DEVCOREDUMP_H */ diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 82b2195efaca..bcc6d7b69470 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -180,6 +180,11 @@ int dm_get_device(struct dm_target *ti, const char *path, blk_mode_t mode, void dm_put_device(struct dm_target *ti, struct dm_dev *d); /* + * Helper function for getting devices + */ +int dm_devt_from_path(const char *path, dev_t *dev_p); + +/* * Information about a target type */ @@ -294,6 +299,9 @@ struct target_type { #define dm_target_supports_mixed_zoned_model(type) (false) #endif +#define DM_TARGET_ATOMIC_WRITES 0x00000400 +#define dm_target_supports_atomic_writes(type) ((type)->features & DM_TARGET_ATOMIC_WRITES) + struct dm_target { struct dm_table *table; struct target_type *type; @@ -358,22 +366,17 @@ struct dm_target { bool discards_supported:1; /* - * Set if this target requires that discards be split on - * 'max_discard_sectors' boundaries. - */ - bool max_discard_granularity:1; - - /* - * Set if this target requires that secure_erases be split on - * 'max_secure_erase_sectors' boundaries. + * Automatically set by dm-core if this target supports + * REQ_OP_ZONE_RESET_ALL. Otherwise, this operation will be emulated + * using REQ_OP_ZONE_RESET. Target drivers must not set this manually. */ - bool max_secure_erase_granularity:1; + bool zone_reset_all_supported:1; /* - * Set if this target requires that write_zeroes be split on - * 'max_write_zeroes_sectors' boundaries. + * Set if this target requires that discards be split on + * 'max_discard_sectors' boundaries. */ - bool max_write_zeroes_granularity:1; + bool max_discard_granularity:1; /* * Set if we need to limit the number of in-flight bios when swapping. @@ -397,6 +400,27 @@ struct dm_target { * bio_set_dev(). NOTE: ideally a target should _not_ need this. */ bool needs_bio_set_dev:1; + + /* + * Set if the target supports flush optimization. If all the targets in + * a table have flush_bypasses_map set, the dm core will not send + * flushes to the targets via a ->map method. It will iterate over + * dm_table->devices and send flushes to the devices directly. This + * optimization reduces the number of flushes being sent when multiple + * targets in a table use the same underlying device. + * + * This optimization may be enabled on targets that just pass the + * flushes to the underlying devices without performing any other + * actions on the flush request. Currently, dm-linear and dm-stripe + * support it. + */ + bool flush_bypasses_map:1; + + /* + * Set if the target calls bio_integrity_alloc on bios received + * in the map method. + */ + bool mempool_needs_integrity:1; }; void *dm_per_bio_data(struct bio *bio, size_t data_size); @@ -503,7 +527,6 @@ 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 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); #ifdef CONFIG_BLK_DEV_ZONED struct dm_report_zones_args { diff --git a/include/linux/device.h b/include/linux/device.h index b9f5464f44ed..80a5b3268986 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -132,6 +132,8 @@ ssize_t device_show_bool(struct device *dev, struct device_attribute *attr, char *buf); ssize_t device_store_bool(struct device *dev, struct device_attribute *attr, const char *buf, size_t count); +ssize_t device_show_string(struct device *dev, struct device_attribute *attr, + char *buf); /** * DEVICE_ATTR - Define a device attribute. @@ -251,6 +253,19 @@ ssize_t device_store_bool(struct device *dev, struct device_attribute *attr, struct dev_ext_attribute dev_attr_##_name = \ { __ATTR(_name, _mode, device_show_bool, device_store_bool), &(_var) } +/** + * DEVICE_STRING_ATTR_RO - Define a device attribute backed by a r/o string. + * @_name: Attribute name. + * @_mode: File mode. + * @_var: Identifier of string. + * + * Like DEVICE_ULONG_ATTR(), but @_var is a string. Because the length of the + * string allocation is unknown, the attribute must be read-only. + */ +#define DEVICE_STRING_ATTR_RO(_name, _mode, _var) \ + struct dev_ext_attribute dev_attr_##_name = \ + { __ATTR(_name, (_mode) & ~0222, device_show_string, NULL), (_var) } + #define DEVICE_ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store) \ struct device_attribute dev_attr_##_name = \ __ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store) @@ -384,7 +399,23 @@ void __iomem *devm_of_iomap(struct device *dev, #endif /* allows to add/remove a custom action to devres stack */ -void devm_remove_action(struct device *dev, void (*action)(void *), void *data); +int devm_remove_action_nowarn(struct device *dev, void (*action)(void *), void *data); + +/** + * devm_remove_action() - removes previously added custom action + * @dev: Device that owns the action + * @action: Function implementing the action + * @data: Pointer to data passed to @action implementation + * + * Removes instance of @action previously added by devm_add_action(). + * Both action and data should match one of the existing entries. + */ +static inline +void devm_remove_action(struct device *dev, void (*action)(void *), void *data) +{ + WARN_ON(devm_remove_action_nowarn(dev, action, data)); +} + void devm_release_action(struct device *dev, void (*action)(void *), void *data); int __devm_add_action(struct device *dev, void (*action)(void *), void *data, const char *name); @@ -691,6 +722,9 @@ struct device_physical_location { * and optionall (if the coherent mask is large enough) also * for dma allocations. This flag is managed by the dma ops * instance from ->dma_supported. + * @dma_skip_sync: DMA sync operations can be skipped for coherent buffers. + * @dma_iommu: Device is using default IOMMU implementation for DMA and + * doesn't rely on dma_ops structure. * * At the lowest level, every device in a Linux system is represented by an * instance of struct device. The device structure contains the information @@ -732,7 +766,7 @@ struct device { struct dev_pin_info *pins; #endif struct dev_msi_info msi; -#ifdef CONFIG_DMA_OPS +#ifdef CONFIG_ARCH_HAS_DMA_OPS const struct dma_map_ops *dma_ops; #endif u64 *dma_mask; /* dma mask (if dma'able device) */ @@ -803,6 +837,12 @@ struct device { #ifdef CONFIG_DMA_OPS_BYPASS bool dma_ops_bypass : 1; #endif +#ifdef CONFIG_DMA_NEED_SYNC + bool dma_skip_sync:1; +#endif +#ifdef CONFIG_IOMMU_DMA + bool dma_iommu:1; +#endif }; /** @@ -1012,13 +1052,6 @@ static inline void device_lock_assert(struct device *dev) lockdep_assert_held(&dev->mutex); } -static inline struct device_node *dev_of_node(struct device *dev) -{ - if (!IS_ENABLED(CONFIG_OF) || !dev) - return NULL; - return dev->of_node; -} - static inline bool dev_has_sync_state(struct device *dev) { if (!dev) @@ -1057,15 +1090,44 @@ void device_del(struct device *dev); DEFINE_FREE(device_del, struct device *, if (_T) device_del(_T)) -int device_for_each_child(struct device *dev, void *data, - int (*fn)(struct device *dev, void *data)); -int device_for_each_child_reverse(struct device *dev, void *data, - int (*fn)(struct device *dev, void *data)); -struct device *device_find_child(struct device *dev, void *data, - int (*match)(struct device *dev, void *data)); -struct device *device_find_child_by_name(struct device *parent, - const char *name); -struct device *device_find_any_child(struct device *parent); +int device_for_each_child(struct device *parent, void *data, + device_iter_t fn); +int device_for_each_child_reverse(struct device *parent, void *data, + device_iter_t fn); +int device_for_each_child_reverse_from(struct device *parent, + struct device *from, void *data, + device_iter_t fn); +struct device *device_find_child(struct device *parent, const void *data, + device_match_t match); +/** + * device_find_child_by_name - device iterator for locating a child device. + * @parent: parent struct device + * @name: name of the child device + * + * This is similar to the device_find_child() function above, but it + * returns a reference to a device that has the name @name. + * + * NOTE: you will need to drop the reference with put_device() after use. + */ +static inline struct device *device_find_child_by_name(struct device *parent, + const char *name) +{ + return device_find_child(parent, name, device_match_name); +} + +/** + * device_find_any_child - device iterator for locating a child device, if any. + * @parent: parent struct device + * + * This is similar to the device_find_child() function above, but it + * returns a reference to a child device, if any. + * + * NOTE: you will need to drop the reference with put_device() after use. + */ +static inline struct device *device_find_any_child(struct device *parent) +{ + return device_find_child(parent, NULL, device_match_any); +} int device_rename(struct device *dev, const char *new_name); int device_move(struct device *dev, struct device *new_parent, @@ -1125,10 +1187,18 @@ void unlock_device_hotplug(void); int lock_device_hotplug_sysfs(void); int device_offline(struct device *dev); int device_online(struct device *dev); + void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode); void set_secondary_fwnode(struct device *dev, struct fwnode_handle *fwnode); -void device_set_of_node_from_dev(struct device *dev, const struct device *dev2); void device_set_node(struct device *dev, struct fwnode_handle *fwnode); +void device_set_of_node_from_dev(struct device *dev, const struct device *dev2); + +static inline struct device_node *dev_of_node(struct device *dev) +{ + if (!IS_ENABLED(CONFIG_OF) || !dev) + return NULL; + return dev->of_node; +} static inline int dev_num_vf(struct device *dev) { @@ -1157,12 +1227,12 @@ static inline void *dev_get_platdata(const struct device *dev) * Manual binding of a device to driver. See drivers/base/bus.c * for information on use. */ -int __must_check device_driver_attach(struct device_driver *drv, +int __must_check device_driver_attach(const struct device_driver *drv, struct device *dev); int __must_check device_bind_driver(struct device *dev); void device_release_driver(struct device *dev); int __must_check device_attach(struct device *dev); -int __must_check driver_attach(struct device_driver *drv); +int __must_check driver_attach(const struct device_driver *drv); void device_initial_probe(struct device *dev); int __must_check device_reprobe(struct device *dev); @@ -1201,23 +1271,10 @@ static inline void device_remove_group(struct device *dev, return device_remove_groups(dev, groups); } -int __must_check devm_device_add_groups(struct device *dev, - const struct attribute_group **groups); int __must_check devm_device_add_group(struct device *dev, const struct attribute_group *grp); /* - * Platform "fixup" functions - allow the platform to have their say - * about devices and actions that the general device layer doesn't - * know about. - */ -/* Notify platform of device discovery */ -extern int (*platform_notify)(struct device *dev); - -extern int (*platform_notify_remove)(struct device *dev); - - -/* * get_device - atomically increment the reference count for the device. * */ diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index 5ef4ec1c36c3..f5a56efd2bd6 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -48,6 +48,7 @@ struct fwnode_handle; * will never get called until they do. * @remove: Called when a device removed from this bus. * @shutdown: Called at shut-down time to quiesce the device. + * @irq_get_affinity: Get IRQ affinity mask for the device on this bus. * * @online: Called to put the device back online (after offlining it). * @offline: Called to put the device offline for hot-removal. May fail. @@ -81,12 +82,14 @@ struct bus_type { const struct attribute_group **dev_groups; const struct attribute_group **drv_groups; - int (*match)(struct device *dev, struct device_driver *drv); + int (*match)(struct device *dev, const struct device_driver *drv); 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); void (*shutdown)(struct device *dev); + const struct cpumask *(*irq_get_affinity)(struct device *dev, + unsigned int irq_vec); int (*online)(struct device *dev); int (*offline)(struct device *dev); @@ -126,8 +129,12 @@ 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); +/* Matching function type for drivers/base APIs to find a specific device */ +typedef int (*device_match_t)(struct device *dev, const void *data); + /* Generic device matching functions that all busses can use to match with */ int device_match_name(struct device *dev, const void *name); +int device_match_type(struct device *dev, const void *type); int device_match_of_node(struct device *dev, const void *np); int device_match_fwnode(struct device *dev, const void *fwnode); int device_match_devt(struct device *dev, const void *pdevt); @@ -135,12 +142,14 @@ int device_match_acpi_dev(struct device *dev, const void *adev); int device_match_acpi_handle(struct device *dev, const void *handle); int device_match_any(struct device *dev, const void *unused); +/* Device iterating function type for various driver core for_each APIs */ +typedef int (*device_iter_t)(struct device *dev, void *data); + /* iterator helpers for buses */ -int bus_for_each_dev(const struct bus_type *bus, struct device *start, void *data, - int (*fn)(struct device *dev, void *data)); +int bus_for_each_dev(const struct bus_type *bus, struct device *start, + void *data, device_iter_t fn); struct device *bus_find_device(const struct bus_type *bus, struct device *start, - const void *data, - int (*match)(struct device *dev, const void *data)); + const void *data, device_match_t match); /** * bus_find_device_by_name - device iterator for locating a particular device * of a specific name. diff --git a/include/linux/device/class.h b/include/linux/device/class.h index c576b49c55c2..45ee3a634999 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -82,20 +82,18 @@ bool class_is_registered(const struct class *class); struct class_compat; struct class_compat *class_compat_register(const char *name); void class_compat_unregister(struct class_compat *cls); -int class_compat_create_link(struct class_compat *cls, struct device *dev, - struct device *device_link); -void class_compat_remove_link(struct class_compat *cls, struct device *dev, - struct device *device_link); +int class_compat_create_link(struct class_compat *cls, struct device *dev); +void class_compat_remove_link(struct class_compat *cls, struct device *dev); void class_dev_iter_init(struct class_dev_iter *iter, const struct class *class, const struct device *start, const struct device_type *type); struct device *class_dev_iter_next(struct class_dev_iter *iter); void class_dev_iter_exit(struct class_dev_iter *iter); -int class_for_each_device(const struct class *class, const struct device *start, void *data, - int (*fn)(struct device *dev, void *data)); +int class_for_each_device(const struct class *class, const struct device *start, + void *data, device_iter_t fn); struct device *class_find_device(const struct class *class, const struct device *start, - const void *data, int (*match)(struct device *, const void *)); + const void *data, device_match_t match); /** * class_find_device_by_name - device iterator for locating a particular device diff --git a/include/linux/device/driver.h b/include/linux/device/driver.h index 7738f458995f..cd8e0f0a634b 100644 --- a/include/linux/device/driver.h +++ b/include/linux/device/driver.h @@ -146,18 +146,18 @@ struct driver_attribute { #define DRIVER_ATTR_WO(_name) \ struct driver_attribute driver_attr_##_name = __ATTR_WO(_name) -int __must_check driver_create_file(struct device_driver *driver, +int __must_check driver_create_file(const struct device_driver *driver, const struct driver_attribute *attr); -void driver_remove_file(struct device_driver *driver, +void driver_remove_file(const struct device_driver *driver, const struct driver_attribute *attr); int driver_set_override(struct device *dev, const char **override, const char *s, size_t len); int __must_check driver_for_each_device(struct device_driver *drv, struct device *start, - void *data, int (*fn)(struct device *dev, void *)); -struct device *driver_find_device(struct device_driver *drv, + void *data, device_iter_t fn); +struct device *driver_find_device(const struct device_driver *drv, struct device *start, const void *data, - int (*match)(struct device *dev, const void *data)); + device_match_t match); /** * driver_find_device_by_name - device iterator for locating a particular device @@ -165,7 +165,7 @@ struct device *driver_find_device(struct device_driver *drv, * @drv: the driver we're iterating * @name: name of the device to match */ -static inline struct device *driver_find_device_by_name(struct device_driver *drv, +static inline struct device *driver_find_device_by_name(const struct device_driver *drv, const char *name) { return driver_find_device(drv, NULL, name, device_match_name); @@ -178,7 +178,7 @@ static inline struct device *driver_find_device_by_name(struct device_driver *dr * @np: of_node pointer to match. */ static inline struct device * -driver_find_device_by_of_node(struct device_driver *drv, +driver_find_device_by_of_node(const struct device_driver *drv, const struct device_node *np) { return driver_find_device(drv, NULL, np, device_match_of_node); @@ -203,13 +203,13 @@ driver_find_device_by_fwnode(struct device_driver *drv, * @drv: the driver we're iterating * @devt: devt pointer to match. */ -static inline struct device *driver_find_device_by_devt(struct device_driver *drv, +static inline struct device *driver_find_device_by_devt(const struct device_driver *drv, dev_t devt) { return driver_find_device(drv, NULL, &devt, device_match_devt); } -static inline struct device *driver_find_next_device(struct device_driver *drv, +static inline struct device *driver_find_next_device(const struct device_driver *drv, struct device *start) { return driver_find_device(drv, start, NULL, device_match_any); @@ -223,14 +223,14 @@ static inline struct device *driver_find_next_device(struct device_driver *drv, * @adev: ACPI_COMPANION device to match. */ static inline struct device * -driver_find_device_by_acpi_dev(struct device_driver *drv, +driver_find_device_by_acpi_dev(const struct device_driver *drv, const struct acpi_device *adev) { return driver_find_device(drv, NULL, adev, device_match_acpi_dev); } #else static inline struct device * -driver_find_device_by_acpi_dev(struct device_driver *drv, const void *adev) +driver_find_device_by_acpi_dev(const struct device_driver *drv, const void *adev) { return NULL; } diff --git a/include/linux/devm-helpers.h b/include/linux/devm-helpers.h index 74891802200d..708ca9131402 100644 --- a/include/linux/devm-helpers.h +++ b/include/linux/devm-helpers.h @@ -41,7 +41,7 @@ static inline void devm_delayed_work_drop(void *res) * detached. A few drivers need delayed work which must be cancelled before * driver is detached to avoid accessing removed resources. * devm_delayed_work_autocancel() can be used to omit the explicit - * cancelleation when driver is detached. + * cancellation when driver is detached. */ static inline int devm_delayed_work_autocancel(struct device *dev, struct delayed_work *w, @@ -66,7 +66,7 @@ static inline void devm_work_drop(void *res) * A few drivers need to queue work which must be cancelled before driver * is detached to avoid accessing removed resources. * devm_work_autocancel() can be used to omit the explicit - * cancelleation when driver is detached. + * cancellation when driver is detached. */ static inline int devm_work_autocancel(struct device *dev, struct work_struct *w, diff --git a/include/linux/dfl.h b/include/linux/dfl.h index 0a7a00a0ee7f..1f02db0c1897 100644 --- a/include/linux/dfl.h +++ b/include/linux/dfl.h @@ -71,7 +71,7 @@ struct dfl_driver { }; #define to_dfl_dev(d) container_of(d, struct dfl_device, dev) -#define to_dfl_drv(d) container_of(d, struct dfl_driver, drv) +#define to_dfl_drv(d) container_of_const(d, struct dfl_driver, drv) /* * use a macro to avoid include chaining to get THIS_MODULE. diff --git a/include/linux/dim.h b/include/linux/dim.h index f343bc9aa2ec..06543fd40fcc 100644 --- a/include/linux/dim.h +++ b/include/linux/dim.h @@ -10,6 +10,15 @@ #include <linux/types.h> #include <linux/workqueue.h> +struct net_device; + +/* Number of DIM profiles and period mode. */ +#define NET_DIM_PARAMS_NUM_PROFILES 5 +#define NET_DIM_DEFAULT_RX_CQ_PKTS_FROM_EQE 256 +#define NET_DIM_DEFAULT_TX_CQ_PKTS_FROM_EQE 128 +#define NET_DIM_DEF_PROFILE_CQE 1 +#define NET_DIM_DEF_PROFILE_EQE 1 + /* * Number of events between DIM iterations. * Causes a moderation of the algorithm run. @@ -38,12 +47,45 @@ * @pkts: CQ packet counter suggestion (by DIM) * @comps: Completion counter * @cq_period_mode: CQ period count mode (from CQE/EQE) + * @rcu: for asynchronous kfree_rcu */ struct dim_cq_moder { u16 usec; u16 pkts; u16 comps; u8 cq_period_mode; + struct rcu_head rcu; +}; + +#define DIM_PROFILE_RX BIT(0) /* support rx profile modification */ +#define DIM_PROFILE_TX BIT(1) /* support tx profile modification */ + +#define DIM_COALESCE_USEC BIT(0) /* support usec field modification */ +#define DIM_COALESCE_PKTS BIT(1) /* support pkts field modification */ +#define DIM_COALESCE_COMPS BIT(2) /* support comps field modification */ + +/** + * struct dim_irq_moder - Structure for irq moderation information. + * Used to collect irq moderation related information. + * + * @profile_flags: DIM_PROFILE_* + * @coal_flags: DIM_COALESCE_* for Rx and Tx + * @dim_rx_mode: Rx DIM period count mode: CQE or EQE + * @dim_tx_mode: Tx DIM period count mode: CQE or EQE + * @rx_profile: DIM profile list for Rx + * @tx_profile: DIM profile list for Tx + * @rx_dim_work: Rx DIM worker scheduled by net_dim() + * @tx_dim_work: Tx DIM worker scheduled by net_dim() + */ +struct dim_irq_moder { + u8 profile_flags; + u8 coal_flags; + u8 dim_rx_mode; + u8 dim_tx_mode; + struct dim_cq_moder __rcu *rx_profile; + struct dim_cq_moder __rcu *tx_profile; + void (*rx_dim_work)(struct work_struct *work); + void (*tx_dim_work)(struct work_struct *work); }; /** @@ -192,6 +234,77 @@ enum dim_step_result { }; /** + * net_dim_init_irq_moder - collect information to initialize irq moderation + * @dev: target network device + * @profile_flags: Rx or Tx profile modification capability + * @coal_flags: irq moderation params flags + * @rx_mode: CQ period mode for Rx + * @tx_mode: CQ period mode for Tx + * @rx_dim_work: Rx worker called after dim decision + * @tx_dim_work: Tx worker called after dim decision + * + * Return: 0 on success or a negative error code. + */ +int net_dim_init_irq_moder(struct net_device *dev, u8 profile_flags, + u8 coal_flags, u8 rx_mode, u8 tx_mode, + void (*rx_dim_work)(struct work_struct *work), + void (*tx_dim_work)(struct work_struct *work)); + +/** + * net_dim_free_irq_moder - free fields for irq moderation + * @dev: target network device + */ +void net_dim_free_irq_moder(struct net_device *dev); + +/** + * net_dim_setting - initialize DIM's cq mode and schedule worker + * @dev: target network device + * @dim: DIM context + * @is_tx: true indicates the tx direction, false indicates the rx direction + */ +void net_dim_setting(struct net_device *dev, struct dim *dim, bool is_tx); + +/** + * net_dim_work_cancel - synchronously cancel dim's worker + * @dim: DIM context + */ +void net_dim_work_cancel(struct dim *dim); + +/** + * net_dim_get_rx_irq_moder - get DIM rx results based on profile_ix + * @dev: target network device + * @dim: DIM context + * + * Return: DIM irq moderation + */ +struct dim_cq_moder +net_dim_get_rx_irq_moder(struct net_device *dev, struct dim *dim); + +/** + * net_dim_get_tx_irq_moder - get DIM tx results based on profile_ix + * @dev: target network device + * @dim: DIM context + * + * Return: DIM irq moderation + */ +struct dim_cq_moder +net_dim_get_tx_irq_moder(struct net_device *dev, struct dim *dim); + +/** + * net_dim_set_rx_mode - set DIM rx cq mode + * @dev: target network device + * @rx_mode: target rx cq mode + */ +void net_dim_set_rx_mode(struct net_device *dev, u8 rx_mode); + +/** + * net_dim_set_tx_mode - set DIM tx cq mode + * @dev: target network device + * @tx_mode: target tx cq mode + */ +void net_dim_set_tx_mode(struct net_device *dev, u8 tx_mode); + +/** * dim_on_top - check if current state is a good place to stop (top location) * @dim: DIM context * @@ -238,7 +351,8 @@ void dim_park_tired(struct dim *dim); * Takes into consideration counter wrap-around. * Returned boolean indicates whether curr_stats are reliable. */ -bool dim_calc_stats(struct dim_sample *start, struct dim_sample *end, +bool dim_calc_stats(const struct dim_sample *start, + const struct dim_sample *end, struct dim_stats *curr_stats); /** @@ -311,7 +425,7 @@ struct dim_cq_moder net_dim_get_def_tx_moderation(u8 cq_period_mode); * This is the main logic of the algorithm, where data is processed in order * to decide on next required action. */ -void net_dim(struct dim *dim, struct dim_sample end_sample); +void net_dim(struct dim *dim, const struct dim_sample *end_sample); /* RDMA DIM */ diff --git a/include/linux/dio.h b/include/linux/dio.h index 2b5923909f96..464331c4c4a7 100644 --- a/include/linux/dio.h +++ b/include/linux/dio.h @@ -93,7 +93,7 @@ struct dio_driver { struct device_driver driver; }; -#define to_dio_driver(drv) container_of(drv, struct dio_driver, driver) +#define to_dio_driver(drv) container_of_const(drv, struct dio_driver, driver) /* DIO/DIO-II boards all have the following 8bit registers. * These are offsets from the base of the device. diff --git a/include/linux/dlm.h b/include/linux/dlm.h index c58c4f790c04..bacda9898f2b 100644 --- a/include/linux/dlm.h +++ b/include/linux/dlm.h @@ -35,6 +35,9 @@ struct dlm_lockspace_ops { int num_slots, int our_slot, uint32_t generation); }; +/* only relevant for kernel lockspaces, will be removed in future */ +#define DLM_LSFL_SOFTIRQ __DLM_LSFL_RESERVED0 + /* * dlm_new_lockspace * @@ -55,6 +58,11 @@ struct dlm_lockspace_ops { * used to select the directory node. Must be the same on all nodes. * DLM_LSFL_NEWEXCL * dlm_new_lockspace() should return -EEXIST if the lockspace exists. + * DLM_LSFL_SOFTIRQ + * dlm request callbacks (ast, bast) are softirq safe. Flag should be + * preferred by users. Will be default in some future. If set the + * strongest context for ast, bast callback is softirq as it avoids + * an additional context switch. * * lvblen: length of lvb in bytes. Must be multiple of 8. * dlm_new_lockspace() returns an error if this does not match @@ -121,7 +129,14 @@ int dlm_release_lockspace(dlm_lockspace_t *lockspace, int force); * call. * * AST routines should not block (at least not for long), but may make - * any locking calls they please. + * any locking calls they please. If DLM_LSFL_SOFTIRQ for kernel + * users of dlm_new_lockspace() is passed the ast and bast callbacks + * can be processed in softirq context. Also some of the callback + * contexts are in the same context as the DLM lock request API, users + * must not hold locks while calling dlm lock request API and trying + * to acquire this lock in the callback again, this will end in a + * lock recursion. For newer implementation the DLM_LSFL_SOFTIRQ + * should be used. */ int dlm_lock(dlm_lockspace_t *lockspace, diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index 3eb3589ff43e..d7e30d4f7503 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -12,7 +12,7 @@ #include <linux/mem_encrypt.h> #include <linux/swiotlb.h> -extern unsigned int zone_dma_bits; +extern u64 zone_dma_limit; /* * Record the mapping of CPU physical to DMA addresses for a given region. @@ -54,6 +54,24 @@ static inline phys_addr_t translate_dma_to_phys(struct device *dev, return (phys_addr_t)-1; } +static inline dma_addr_t dma_range_map_min(const struct bus_dma_region *map) +{ + dma_addr_t ret = (dma_addr_t)U64_MAX; + + for (; map->size; map++) + ret = min(ret, map->dma_start); + return ret; +} + +static inline dma_addr_t dma_range_map_max(const struct bus_dma_region *map) +{ + dma_addr_t ret = 0; + + for (; map->size; map++) + ret = max(ret, map->dma_start + map->size - 1); + return ret; +} + #ifdef CONFIG_ARCH_HAS_PHYS_TO_DMA #include <asm/dma-direct.h> #ifndef phys_to_dma_unencrypted diff --git a/include/linux/dma-fence-array.h b/include/linux/dma-fence-array.h index ec7f25def392..079b3dec0a16 100644 --- a/include/linux/dma-fence-array.h +++ b/include/linux/dma-fence-array.h @@ -33,6 +33,7 @@ struct dma_fence_array_cb { * @num_pending: fences in the array still pending * @fences: array of the fences * @work: internal irq_work function + * @callbacks: array of callback helpers */ struct dma_fence_array { struct dma_fence base; @@ -43,6 +44,8 @@ struct dma_fence_array { struct dma_fence **fences; struct irq_work work; + + struct dma_fence_array_cb callbacks[] __counted_by(num_fences); }; /** @@ -76,6 +79,12 @@ to_dma_fence_array(struct dma_fence *fence) for (index = 0, fence = dma_fence_array_first(head); fence; \ ++(index), fence = dma_fence_array_next(head, index)) +struct dma_fence_array *dma_fence_array_alloc(int num_fences); +void dma_fence_array_init(struct dma_fence_array *array, + int num_fences, struct dma_fence **fences, + u64 context, unsigned seqno, + bool signal_on_any); + struct dma_fence_array *dma_fence_array_create(int num_fences, struct dma_fence **fences, u64 context, unsigned seqno, diff --git a/include/linux/dma-fence-chain.h b/include/linux/dma-fence-chain.h index 4bdf0b96da28..68c3c1e41014 100644 --- a/include/linux/dma-fence-chain.h +++ b/include/linux/dma-fence-chain.h @@ -85,11 +85,13 @@ dma_fence_chain_contained(struct dma_fence *fence) * dma_fence_chain_alloc * * Returns a new struct dma_fence_chain object or NULL on failure. + * + * This specialized allocator has to be a macro for its allocations to be + * accounted separately (to have a separate alloc_tag). The typecast is + * intentional to enforce typesafety. */ -static inline struct dma_fence_chain *dma_fence_chain_alloc(void) -{ - return kmalloc(sizeof(struct dma_fence_chain), GFP_KERNEL); -}; +#define dma_fence_chain_alloc() \ + ((struct dma_fence_chain *)kmalloc(sizeof(struct dma_fence_chain), GFP_KERNEL)) /** * dma_fence_chain_free diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index c3f9bb6602ba..e7ad819962e3 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -574,6 +574,12 @@ int dma_fence_get_status(struct dma_fence *fence); * rather than success. This must be set before signaling (so that the value * is visible before any waiters on the signal callback are woken). This * helper exists to help catching erroneous setting of #dma_fence.error. + * + * Examples of error codes which drivers should use: + * + * * %-ENODATA This operation produced no data, no other operation affected. + * * %-ECANCELED All operations from the same context have been canceled. + * * %-ETIME Operation caused a timeout and potentially device reset. */ static inline void dma_fence_set_error(struct dma_fence *fence, int error) @@ -682,11 +688,4 @@ static inline bool dma_fence_is_container(struct dma_fence *fence) return dma_fence_is_array(fence) || dma_fence_is_chain(fence); } -#define DMA_FENCE_WARN(f, fmt, args...) \ - do { \ - struct dma_fence *__ff = (f); \ - pr_warn("f %llu#%llu: " fmt, __ff->context, __ff->seqno,\ - ##args); \ - } while (0) - #endif /* __LINUX_DMA_FENCE_H */ diff --git a/include/linux/dma-heap.h b/include/linux/dma-heap.h index 0c05561cad6e..27d15f60950a 100644 --- a/include/linux/dma-heap.h +++ b/include/linux/dma-heap.h @@ -9,22 +9,21 @@ #ifndef _DMA_HEAPS_H #define _DMA_HEAPS_H -#include <linux/cdev.h> #include <linux/types.h> struct dma_heap; /** * struct dma_heap_ops - ops to operate on a given heap - * @allocate: allocate dmabuf and return struct dma_buf ptr + * @allocate: allocate dmabuf and return struct dma_buf ptr * * allocate returns dmabuf on success, ERR_PTR(-errno) on error. */ struct dma_heap_ops { struct dma_buf *(*allocate)(struct dma_heap *heap, unsigned long len, - unsigned long fd_flags, - unsigned long heap_flags); + u32 fd_flags, + u64 heap_flags); }; /** @@ -41,28 +40,10 @@ struct dma_heap_export_info { void *priv; }; -/** - * dma_heap_get_drvdata() - get per-heap driver data - * @heap: DMA-Heap to retrieve private data for - * - * Returns: - * The per-heap data for the heap. - */ void *dma_heap_get_drvdata(struct dma_heap *heap); -/** - * dma_heap_get_name() - get heap name - * @heap: DMA-Heap to retrieve private data for - * - * Returns: - * The char* for the heap name. - */ const char *dma_heap_get_name(struct dma_heap *heap); -/** - * dma_heap_add - adds a heap to dmabuf heaps - * @exp_info: information needed to register this heap - */ struct dma_heap *dma_heap_add(const struct dma_heap_export_info *exp_info); #endif /* _DMA_HEAPS_H */ diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h index 4abc60f04209..e172522cd936 100644 --- a/include/linux/dma-map-ops.h +++ b/include/linux/dma-map-ops.h @@ -13,32 +13,17 @@ struct cma; struct iommu_ops; -/* - * Values for struct dma_map_ops.flags: - * - * DMA_F_PCI_P2PDMA_SUPPORTED: Indicates the dma_map_ops implementation can - * handle PCI P2PDMA pages in the map_sg/unmap_sg operation. - */ -#define DMA_F_PCI_P2PDMA_SUPPORTED (1 << 0) - struct dma_map_ops { - unsigned int flags; - void *(*alloc)(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs); void (*free)(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle, unsigned long attrs); - struct page *(*alloc_pages)(struct device *dev, size_t size, + struct page *(*alloc_pages_op)(struct device *dev, size_t size, dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp); void (*free_pages)(struct device *dev, size_t size, struct page *vaddr, dma_addr_t dma_handle, enum dma_data_direction dir); - struct sg_table *(*alloc_noncontiguous)(struct device *dev, size_t size, - enum dma_data_direction dir, gfp_t gfp, - unsigned long attrs); - void (*free_noncontiguous)(struct device *dev, size_t size, - struct sg_table *sgt, enum dma_data_direction dir); int (*mmap)(struct device *, struct vm_area_struct *, void *, dma_addr_t, size_t, unsigned long attrs); @@ -85,7 +70,7 @@ struct dma_map_ops { unsigned long (*get_merge_boundary)(struct device *dev); }; -#ifdef CONFIG_DMA_OPS +#ifdef CONFIG_ARCH_HAS_DMA_OPS #include <asm/dma-mapping.h> static inline const struct dma_map_ops *get_dma_ops(struct device *dev) @@ -100,7 +85,7 @@ static inline void set_dma_ops(struct device *dev, { dev->dma_ops = dma_ops; } -#else /* CONFIG_DMA_OPS */ +#else /* CONFIG_ARCH_HAS_DMA_OPS */ static inline const struct dma_map_ops *get_dma_ops(struct device *dev) { return NULL; @@ -109,7 +94,7 @@ static inline void set_dma_ops(struct device *dev, const struct dma_map_ops *dma_ops) { } -#endif /* CONFIG_DMA_OPS */ +#endif /* CONFIG_ARCH_HAS_DMA_OPS */ #ifdef CONFIG_DMA_CMA extern struct cma *dma_contiguous_default_area; @@ -216,20 +201,6 @@ static inline int dma_mmap_from_global_coherent(struct vm_area_struct *vma, } #endif /* CONFIG_DMA_GLOBAL_POOL */ -/* - * This is the actual return value from the ->alloc_noncontiguous method. - * The users of the DMA API should only care about the sg_table, but to make - * the DMA-API internal vmaping and freeing easier we stash away the page - * array as well (except for the fallback case). This can go away any time, - * e.g. when a vmap-variant that takes a scatterlist comes along. - */ -struct dma_sgt_handle { - struct sg_table sgt; - struct page **pages; -}; -#define sgt_handle(sgt) \ - container_of((sgt), struct dma_sgt_handle, sgt) - int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs); @@ -271,7 +242,16 @@ static inline bool dev_is_dma_coherent(struct device *dev) { return true; } -#endif /* CONFIG_ARCH_HAS_DMA_COHERENCE_H */ +#endif + +static inline void dma_reset_need_sync(struct device *dev) +{ +#ifdef CONFIG_DMA_NEED_SYNC + /* Reset it only once so that the function can be called on hotpath */ + if (unlikely(dev->dma_skip_sync)) + dev->dma_skip_sync = false; +#endif +} /* * Check whether potential kmalloc() buffers are safe for non-coherent DMA. @@ -426,11 +406,9 @@ bool arch_dma_unmap_sg_direct(struct device *dev, struct scatterlist *sg, #endif #ifdef CONFIG_ARCH_HAS_SETUP_DMA_OPS -void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, - bool coherent); +void arch_setup_dma_ops(struct device *dev, bool coherent); #else -static inline void arch_setup_dma_ops(struct device *dev, u64 dma_base, - u64 size, bool coherent) +static inline void arch_setup_dma_ops(struct device *dev, bool coherent) { } #endif /* CONFIG_ARCH_HAS_SETUP_DMA_OPS */ diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 4a658de44ee9..b79925b1c433 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -2,15 +2,11 @@ #ifndef _LINUX_DMA_MAPPING_H #define _LINUX_DMA_MAPPING_H -#include <linux/cache.h> -#include <linux/sizes.h> -#include <linux/string.h> #include <linux/device.h> #include <linux/err.h> #include <linux/dma-direction.h> #include <linux/scatterlist.h> #include <linux/bug.h> -#include <linux/mem_encrypt.h> /** * List of possible attributes associated with a DMA mapping. The semantics @@ -117,14 +113,6 @@ dma_addr_t dma_map_resource(struct device *dev, phys_addr_t phys_addr, size_t size, enum dma_data_direction dir, unsigned long attrs); void dma_unmap_resource(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir, unsigned long attrs); -void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size, - enum dma_data_direction dir); -void dma_sync_single_for_device(struct device *dev, dma_addr_t addr, - size_t size, enum dma_data_direction dir); -void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, - int nelems, enum dma_data_direction dir); -void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, - int nelems, enum dma_data_direction dir); void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag, unsigned long attrs); void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr, @@ -147,7 +135,6 @@ u64 dma_get_required_mask(struct device *dev); bool dma_addressing_limited(struct device *dev); size_t dma_max_mapping_size(struct device *dev); size_t dma_opt_mapping_size(struct device *dev); -bool dma_need_sync(struct device *dev, dma_addr_t dma_addr); unsigned long dma_get_merge_boundary(struct device *dev); struct sg_table *dma_alloc_noncontiguous(struct device *dev, size_t size, enum dma_data_direction dir, gfp_t gfp, unsigned long attrs); @@ -195,22 +182,6 @@ static inline void dma_unmap_resource(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir, unsigned long attrs) { } -static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, - size_t size, enum dma_data_direction dir) -{ -} -static inline void dma_sync_single_for_device(struct device *dev, - dma_addr_t addr, size_t size, enum dma_data_direction dir) -{ -} -static inline void dma_sync_sg_for_cpu(struct device *dev, - struct scatterlist *sg, int nelems, enum dma_data_direction dir) -{ -} -static inline void dma_sync_sg_for_device(struct device *dev, - struct scatterlist *sg, int nelems, enum dma_data_direction dir) -{ -} static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { return -ENOMEM; @@ -277,10 +248,6 @@ static inline size_t dma_opt_mapping_size(struct device *dev) { return 0; } -static inline bool dma_need_sync(struct device *dev, dma_addr_t dma_addr) -{ - return false; -} static inline unsigned long dma_get_merge_boundary(struct device *dev) { return 0; @@ -310,6 +277,82 @@ static inline int dma_mmap_noncontiguous(struct device *dev, } #endif /* CONFIG_HAS_DMA */ +#if defined(CONFIG_HAS_DMA) && defined(CONFIG_DMA_NEED_SYNC) +void __dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size, + enum dma_data_direction dir); +void __dma_sync_single_for_device(struct device *dev, dma_addr_t addr, + size_t size, enum dma_data_direction dir); +void __dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, + int nelems, enum dma_data_direction dir); +void __dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, + int nelems, enum dma_data_direction dir); +bool __dma_need_sync(struct device *dev, dma_addr_t dma_addr); + +static inline bool dma_dev_need_sync(const struct device *dev) +{ + /* Always call DMA sync operations when debugging is enabled */ + return !dev->dma_skip_sync || IS_ENABLED(CONFIG_DMA_API_DEBUG); +} + +static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, + size_t size, enum dma_data_direction dir) +{ + if (dma_dev_need_sync(dev)) + __dma_sync_single_for_cpu(dev, addr, size, dir); +} + +static inline void dma_sync_single_for_device(struct device *dev, + dma_addr_t addr, size_t size, enum dma_data_direction dir) +{ + if (dma_dev_need_sync(dev)) + __dma_sync_single_for_device(dev, addr, size, dir); +} + +static inline void dma_sync_sg_for_cpu(struct device *dev, + struct scatterlist *sg, int nelems, enum dma_data_direction dir) +{ + if (dma_dev_need_sync(dev)) + __dma_sync_sg_for_cpu(dev, sg, nelems, dir); +} + +static inline void dma_sync_sg_for_device(struct device *dev, + struct scatterlist *sg, int nelems, enum dma_data_direction dir) +{ + if (dma_dev_need_sync(dev)) + __dma_sync_sg_for_device(dev, sg, nelems, dir); +} + +static inline bool dma_need_sync(struct device *dev, dma_addr_t dma_addr) +{ + return dma_dev_need_sync(dev) ? __dma_need_sync(dev, dma_addr) : false; +} +#else /* !CONFIG_HAS_DMA || !CONFIG_DMA_NEED_SYNC */ +static inline bool dma_dev_need_sync(const struct device *dev) +{ + return false; +} +static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, + size_t size, enum dma_data_direction dir) +{ +} +static inline void dma_sync_single_for_device(struct device *dev, + dma_addr_t addr, size_t size, enum dma_data_direction dir) +{ +} +static inline void dma_sync_sg_for_cpu(struct device *dev, + struct scatterlist *sg, int nelems, enum dma_data_direction dir) +{ +} +static inline void dma_sync_sg_for_device(struct device *dev, + struct scatterlist *sg, int nelems, enum dma_data_direction dir) +{ +} +static inline bool dma_need_sync(struct device *dev, dma_addr_t dma_addr) +{ + return false; +} +#endif /* !CONFIG_HAS_DMA || !CONFIG_DMA_NEED_SYNC */ + struct page *dma_alloc_pages(struct device *dev, size_t size, dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp); void dma_free_pages(struct device *dev, size_t size, struct page *page, @@ -477,13 +520,11 @@ static inline unsigned int dma_get_max_seg_size(struct device *dev) return SZ_64K; } -static inline int dma_set_max_seg_size(struct device *dev, unsigned int size) +static inline void dma_set_max_seg_size(struct device *dev, unsigned int size) { - if (dev->dma_parms) { - dev->dma_parms->max_segment_size = size; - return 0; - } - return -EIO; + if (WARN_ON_ONCE(!dev->dma_parms)) + return; + dev->dma_parms->max_segment_size = size; } static inline unsigned long dma_get_seg_boundary(struct device *dev) @@ -512,13 +553,11 @@ static inline unsigned long dma_get_seg_boundary_nr_pages(struct device *dev, return (dma_get_seg_boundary(dev) >> page_shift) + 1; } -static inline int dma_set_seg_boundary(struct device *dev, unsigned long mask) +static inline void dma_set_seg_boundary(struct device *dev, unsigned long mask) { - if (dev->dma_parms) { - dev->dma_parms->segment_boundary_mask = mask; - return 0; - } - return -EIO; + if (WARN_ON_ONCE(!dev->dma_parms)) + return; + dev->dma_parms->segment_boundary_mask = mask; } static inline unsigned int dma_get_min_align_mask(struct device *dev) @@ -528,13 +567,12 @@ static inline unsigned int dma_get_min_align_mask(struct device *dev) return 0; } -static inline int dma_set_min_align_mask(struct device *dev, +static inline void dma_set_min_align_mask(struct device *dev, unsigned int min_align_mask) { if (WARN_ON_ONCE(!dev->dma_parms)) - return -EIO; + return; dev->dma_parms->min_align_mask = min_align_mask; - return 0; } #ifndef dma_get_cache_alignment diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index 8d0e34dad446..c5ab6fd9ebe8 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -105,10 +105,10 @@ enum dma_resv_usage { * This should be used by submissions which don't want to participate in * any implicit synchronization. * - * The most common case are preemption fences, page table updates, TLB - * flushes as well as explicit synced user submissions. + * The most common cases are preemption fences, page table updates, TLB + * flushes as well as explicitly synced user submissions. * - * Explicit synced user user submissions can be promoted to + * Explicitly synced user submissions can be promoted to * DMA_RESV_USAGE_READ or DMA_RESV_USAGE_WRITE as needed using * dma_buf_import_sync_file() when implicit synchronization should * become necessary after initial adding of the fence. diff --git a/include/linux/dma/imx-dma.h b/include/linux/dma/imx-dma.h index cfec5f946e23..76a8de9ae151 100644 --- a/include/linux/dma/imx-dma.h +++ b/include/linux/dma/imx-dma.h @@ -41,6 +41,7 @@ enum sdma_peripheral_type { IMX_DMATYPE_SAI, /* SAI */ IMX_DMATYPE_MULTI_SAI, /* MULTI FIFOs For Audio */ IMX_DMATYPE_HDMI, /* HDMI Audio */ + IMX_DMATYPE_I2C, /* I2C */ }; enum imx_dma_prio { diff --git a/include/linux/dma/ipu-dma.h b/include/linux/dma/ipu-dma.h deleted file mode 100644 index 6969391580d2..000000000000 --- a/include/linux/dma/ipu-dma.h +++ /dev/null @@ -1,174 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2008 - * Guennadi Liakhovetski, DENX Software Engineering, <lg@denx.de> - * - * Copyright (C) 2005-2007 Freescale Semiconductor, Inc. - */ - -#ifndef __LINUX_DMA_IPU_DMA_H -#define __LINUX_DMA_IPU_DMA_H - -#include <linux/types.h> -#include <linux/dmaengine.h> - -/* IPU DMA Controller channel definitions. */ -enum ipu_channel { - IDMAC_IC_0 = 0, /* IC (encoding task) to memory */ - IDMAC_IC_1 = 1, /* IC (viewfinder task) to memory */ - IDMAC_ADC_0 = 1, - IDMAC_IC_2 = 2, - IDMAC_ADC_1 = 2, - IDMAC_IC_3 = 3, - IDMAC_IC_4 = 4, - IDMAC_IC_5 = 5, - IDMAC_IC_6 = 6, - IDMAC_IC_7 = 7, /* IC (sensor data) to memory */ - IDMAC_IC_8 = 8, - IDMAC_IC_9 = 9, - IDMAC_IC_10 = 10, - IDMAC_IC_11 = 11, - IDMAC_IC_12 = 12, - IDMAC_IC_13 = 13, - IDMAC_SDC_0 = 14, /* Background synchronous display data */ - IDMAC_SDC_1 = 15, /* Foreground data (overlay) */ - IDMAC_SDC_2 = 16, - IDMAC_SDC_3 = 17, - IDMAC_ADC_2 = 18, - IDMAC_ADC_3 = 19, - IDMAC_ADC_4 = 20, - IDMAC_ADC_5 = 21, - IDMAC_ADC_6 = 22, - IDMAC_ADC_7 = 23, - IDMAC_PF_0 = 24, - IDMAC_PF_1 = 25, - IDMAC_PF_2 = 26, - IDMAC_PF_3 = 27, - IDMAC_PF_4 = 28, - IDMAC_PF_5 = 29, - IDMAC_PF_6 = 30, - IDMAC_PF_7 = 31, -}; - -/* Order significant! */ -enum ipu_channel_status { - IPU_CHANNEL_FREE, - IPU_CHANNEL_INITIALIZED, - IPU_CHANNEL_READY, - IPU_CHANNEL_ENABLED, -}; - -#define IPU_CHANNELS_NUM 32 - -enum pixel_fmt { - /* 1 byte */ - IPU_PIX_FMT_GENERIC, - IPU_PIX_FMT_RGB332, - IPU_PIX_FMT_YUV420P, - IPU_PIX_FMT_YUV422P, - IPU_PIX_FMT_YUV420P2, - IPU_PIX_FMT_YVU422P, - /* 2 bytes */ - IPU_PIX_FMT_RGB565, - IPU_PIX_FMT_RGB666, - IPU_PIX_FMT_BGR666, - IPU_PIX_FMT_YUYV, - IPU_PIX_FMT_UYVY, - /* 3 bytes */ - IPU_PIX_FMT_RGB24, - IPU_PIX_FMT_BGR24, - /* 4 bytes */ - IPU_PIX_FMT_GENERIC_32, - IPU_PIX_FMT_RGB32, - IPU_PIX_FMT_BGR32, - IPU_PIX_FMT_ABGR32, - IPU_PIX_FMT_BGRA32, - IPU_PIX_FMT_RGBA32, -}; - -enum ipu_color_space { - IPU_COLORSPACE_RGB, - IPU_COLORSPACE_YCBCR, - IPU_COLORSPACE_YUV -}; - -/* - * Enumeration of IPU rotation modes - */ -enum ipu_rotate_mode { - /* Note the enum values correspond to BAM value */ - IPU_ROTATE_NONE = 0, - IPU_ROTATE_VERT_FLIP = 1, - IPU_ROTATE_HORIZ_FLIP = 2, - IPU_ROTATE_180 = 3, - IPU_ROTATE_90_RIGHT = 4, - IPU_ROTATE_90_RIGHT_VFLIP = 5, - IPU_ROTATE_90_RIGHT_HFLIP = 6, - IPU_ROTATE_90_LEFT = 7, -}; - -/* - * Enumeration of DI ports for ADC. - */ -enum display_port { - DISP0, - DISP1, - DISP2, - DISP3 -}; - -struct idmac_video_param { - unsigned short in_width; - unsigned short in_height; - uint32_t in_pixel_fmt; - unsigned short out_width; - unsigned short out_height; - uint32_t out_pixel_fmt; - unsigned short out_stride; - bool graphics_combine_en; - bool global_alpha_en; - bool key_color_en; - enum display_port disp; - unsigned short out_left; - unsigned short out_top; -}; - -/* - * Union of initialization parameters for a logical channel. So far only video - * parameters are used. - */ -union ipu_channel_param { - struct idmac_video_param video; -}; - -struct idmac_tx_desc { - struct dma_async_tx_descriptor txd; - struct scatterlist *sg; /* scatterlist for this */ - unsigned int sg_len; /* tx-descriptor. */ - struct list_head list; -}; - -struct idmac_channel { - struct dma_chan dma_chan; - dma_cookie_t completed; /* last completed cookie */ - union ipu_channel_param params; - enum ipu_channel link; /* input channel, linked to the output */ - enum ipu_channel_status status; - void *client; /* Only one client per channel */ - unsigned int n_tx_desc; - struct idmac_tx_desc *desc; /* allocated tx-descriptors */ - struct scatterlist *sg[2]; /* scatterlist elements in buffer-0 and -1 */ - struct list_head free_list; /* free tx-descriptors */ - struct list_head queue; /* queued tx-descriptors */ - spinlock_t lock; /* protects sg[0,1], queue */ - struct mutex chan_mutex; /* protects status, cookie, free_list */ - bool sec_chan_en; - int active_buffer; - unsigned int eof_irq; - char eof_name[16]; /* EOF IRQ name for request_irq() */ -}; - -#define to_tx_desc(tx) container_of(tx, struct idmac_tx_desc, txd) -#define to_idmac_chan(c) container_of(c, struct idmac_channel, dma_chan) - -#endif /* __LINUX_DMA_IPU_DMA_H */ diff --git a/include/linux/dma/k3-udma-glue.h b/include/linux/dma/k3-udma-glue.h index 1e491c5dcac2..2dea217629d0 100644 --- a/include/linux/dma/k3-udma-glue.h +++ b/include/linux/dma/k3-udma-glue.h @@ -136,8 +136,6 @@ u32 k3_udma_glue_rx_flow_get_fdq_id(struct k3_udma_glue_rx_channel *rx_chn, u32 k3_udma_glue_rx_get_flow_id_base(struct k3_udma_glue_rx_channel *rx_chn); int k3_udma_glue_rx_get_irq(struct k3_udma_glue_rx_channel *rx_chn, u32 flow_num); -void k3_udma_glue_rx_put_irq(struct k3_udma_glue_rx_channel *rx_chn, - u32 flow_num); void k3_udma_glue_reset_rx_chn(struct k3_udma_glue_rx_channel *rx_chn, u32 flow_num, void *data, void (*cleanup)(void *data, dma_addr_t desc_dma), diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 752dbde4cec1..346251bf1026 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -84,7 +84,7 @@ enum dma_transfer_direction { DMA_TRANS_NONE, }; -/** +/* * Interleaved Transfer Request * ---------------------------- * A chunk is collection of contiguous bytes to be transferred. @@ -161,6 +161,16 @@ struct dma_interleaved_template { }; /** + * struct dma_vec - DMA vector + * @addr: Bus address of the start of the vector + * @len: Length in bytes of the DMA vector + */ +struct dma_vec { + dma_addr_t addr; + size_t len; +}; + +/** * enum dma_ctrl_flags - DMA flags to augment operation preparation, * control completion, and communicate status. * @DMA_PREP_INTERRUPT - trigger an interrupt (callback) upon completion of @@ -213,7 +223,7 @@ enum sum_check_bits { }; /** - * enum pq_check_flags - result of async_{xor,pq}_zero_sum operations + * enum sum_check_flags - result of async_{xor,pq}_zero_sum operations * @SUM_CHECK_P_RESULT - 1 if xor zero sum error, 0 otherwise * @SUM_CHECK_Q_RESULT - 1 if reed-solomon zero sum error, 0 otherwise */ @@ -276,7 +286,7 @@ typedef struct { DECLARE_BITMAP(bits, DMA_TX_TYPE_END); } dma_cap_mask_t; * pointer to the engine's metadata area * 4. Read out the metadata from the pointer * - * Note: the two mode is not compatible and clients must use one mode for a + * Warning: the two modes are not compatible and clients must use one mode for a * descriptor. */ enum dma_desc_metadata_mode { @@ -584,9 +594,13 @@ struct dma_descriptor_metadata_ops { * @phys: physical address of the descriptor * @chan: target channel for this operation * @tx_submit: accept the descriptor, assign ordered cookie and mark the + * @desc_free: driver's callback function to free a resusable descriptor + * after completion * descriptor pending. To be pushed on .issue_pending() call * @callback: routine to call after this operation is complete + * @callback_result: error result from a DMA transaction * @callback_param: general parameter to pass to the callback routine + * @unmap: hook for generic DMA unmap data * @desc_metadata_mode: core managed metadata mode to protect mixed use of * DESC_METADATA_CLIENT or DESC_METADATA_ENGINE. Otherwise * DESC_METADATA_NONE @@ -817,6 +831,9 @@ struct dma_filter { * @device_prep_dma_memset: prepares a memset operation * @device_prep_dma_memset_sg: prepares a memset operation over a scatter list * @device_prep_dma_interrupt: prepares an end of chain interrupt operation + * @device_prep_peripheral_dma_vec: prepares a scatter-gather DMA transfer, + * where the address and size of each segment is located in one entry of + * the dma_vec array. * @device_prep_slave_sg: prepares a slave dma operation * @device_prep_dma_cyclic: prepare a cyclic dma operation suitable for audio. * The function takes a buffer of size buf_len. The callback function will @@ -910,6 +927,10 @@ struct dma_device { struct dma_async_tx_descriptor *(*device_prep_dma_interrupt)( struct dma_chan *chan, unsigned long flags); + struct dma_async_tx_descriptor *(*device_prep_peripheral_dma_vec)( + struct dma_chan *chan, const struct dma_vec *vecs, + size_t nents, enum dma_transfer_direction direction, + unsigned long flags); struct dma_async_tx_descriptor *(*device_prep_slave_sg)( struct dma_chan *chan, struct scatterlist *sgl, unsigned int sg_len, enum dma_transfer_direction direction, @@ -973,6 +994,25 @@ static inline struct dma_async_tx_descriptor *dmaengine_prep_slave_single( dir, flags, NULL); } +/** + * dmaengine_prep_peripheral_dma_vec() - Prepare a DMA scatter-gather descriptor + * @chan: The channel to be used for this descriptor + * @vecs: The array of DMA vectors that should be transferred + * @nents: The number of DMA vectors in the array + * @dir: Specifies the direction of the data transfer + * @flags: DMA engine flags + */ +static inline struct dma_async_tx_descriptor *dmaengine_prep_peripheral_dma_vec( + struct dma_chan *chan, const struct dma_vec *vecs, size_t nents, + enum dma_transfer_direction dir, unsigned long flags) +{ + if (!chan || !chan->device || !chan->device->device_prep_peripheral_dma_vec) + return NULL; + + return chan->device->device_prep_peripheral_dma_vec(chan, vecs, nents, + dir, flags); +} + static inline struct dma_async_tx_descriptor *dmaengine_prep_slave_sg( struct dma_chan *chan, struct scatterlist *sgl, unsigned int sg_len, enum dma_transfer_direction dir, unsigned long flags) @@ -1575,7 +1615,8 @@ int dma_async_device_register(struct dma_device *device); int dmaenginem_async_device_register(struct dma_device *device); void dma_async_device_unregister(struct dma_device *device); int dma_async_device_channel_register(struct dma_device *device, - struct dma_chan *chan); + struct dma_chan *chan, + const char *name); void dma_async_device_channel_unregister(struct dma_device *device, struct dma_chan *chan); void dma_run_dependencies(struct dma_async_tx_descriptor *tx); diff --git a/include/linux/dmar.h b/include/linux/dmar.h index e34b601b71fd..692b2b445761 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -117,7 +117,7 @@ extern int dmar_remove_dev_scope(struct dmar_pci_notify_info *info, int count); /* Intel IOMMU detection */ void detect_intel_iommu(void); -extern int enable_drhd_fault_handling(void); +extern int enable_drhd_fault_handling(unsigned int cpu); extern int dmar_device_add(acpi_handle handle); extern int dmar_device_remove(acpi_handle handle); @@ -292,7 +292,6 @@ static inline void dmar_copy_shared_irte(struct irte *dst, struct irte *src) struct irq_data; extern void dmar_msi_unmask(struct irq_data *data); extern void dmar_msi_mask(struct irq_data *data); -extern void dmar_msi_read(int irq, struct msi_msg *msg); extern void dmar_msi_write(int irq, struct msi_msg *msg); extern int dmar_set_interrupt(struct intel_iommu *iommu); extern irqreturn_t dmar_fault(int irq, void *dev_id); diff --git a/include/linux/dpll.h b/include/linux/dpll.h index d275736230b3..5e4f9ab1cf75 100644 --- a/include/linux/dpll.h +++ b/include/linux/dpll.h @@ -15,6 +15,7 @@ struct dpll_device; struct dpll_pin; +struct dpll_pin_esync; struct dpll_device_ops { int (*mode_get)(const struct dpll_device *dpll, void *dpll_priv, @@ -25,6 +26,10 @@ struct dpll_device_ops { struct netlink_ext_ack *extack); int (*temp_get)(const struct dpll_device *dpll, void *dpll_priv, s32 *temp, struct netlink_ext_ack *extack); + int (*clock_quality_level_get)(const struct dpll_device *dpll, + void *dpll_priv, + unsigned long *qls, + struct netlink_ext_ack *extack); }; struct dpll_pin_ops { @@ -83,6 +88,13 @@ struct dpll_pin_ops { int (*ffo_get)(const struct dpll_pin *pin, void *pin_priv, const struct dpll_device *dpll, void *dpll_priv, s64 *ffo, struct netlink_ext_ack *extack); + int (*esync_set)(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + u64 freq, struct netlink_ext_ack *extack); + int (*esync_get)(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + struct dpll_pin_esync *esync, + struct netlink_ext_ack *extack); }; struct dpll_pin_frequency { @@ -111,6 +123,13 @@ struct dpll_pin_phase_adjust_range { s32 max; }; +struct dpll_pin_esync { + u64 freq; + const struct dpll_pin_frequency *range; + u8 range_num; + u8 pulse; +}; + struct dpll_pin_properties { const char *board_label; const char *panel_label; diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index f3664ee12170..d13aabdeb4b2 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -8,12 +8,18 @@ #include <net/dsa.h> #include <linux/types.h> +/* VBID is limited to three bits only and zero is reserved. + * Only 7 bridges can be enumerated. + */ +#define DSA_TAG_8021Q_MAX_NUM_BRIDGES 7 + int dsa_tag_8021q_register(struct dsa_switch *ds, __be16 proto); void dsa_tag_8021q_unregister(struct dsa_switch *ds); int dsa_tag_8021q_bridge_join(struct dsa_switch *ds, int port, - struct dsa_bridge bridge); + struct dsa_bridge bridge, bool *tx_fwd_offload, + struct netlink_ext_ack *extack); void dsa_tag_8021q_bridge_leave(struct dsa_switch *ds, int port, struct dsa_bridge bridge); diff --git a/include/linux/dsa/lan9303.h b/include/linux/dsa/lan9303.h index b4f22112ba75..3ce7cbcc37a3 100644 --- a/include/linux/dsa/lan9303.h +++ b/include/linux/dsa/lan9303.h @@ -5,8 +5,8 @@ struct lan9303; struct lan9303_phy_ops { /* PHY 1 and 2 access*/ - int (*phy_read)(struct lan9303 *chip, int port, int regnum); - int (*phy_write)(struct lan9303 *chip, int port, + int (*phy_read)(struct lan9303 *chip, int addr, int regnum); + int (*phy_write)(struct lan9303 *chip, int addr, int regnum, u16 val); }; diff --git a/include/linux/dsa/ocelot.h b/include/linux/dsa/ocelot.h index dca2969015d8..620a3260fc08 100644 --- a/include/linux/dsa/ocelot.h +++ b/include/linux/dsa/ocelot.h @@ -5,6 +5,8 @@ #ifndef _NET_DSA_TAG_OCELOT_H #define _NET_DSA_TAG_OCELOT_H +#include <linux/if_bridge.h> +#include <linux/if_vlan.h> #include <linux/kthread.h> #include <linux/packing.h> #include <linux/skbuff.h> @@ -13,6 +15,7 @@ struct ocelot_skb_cb { struct sk_buff *clone; unsigned int ptp_class; /* valid only for clones */ + unsigned long ptp_tx_time; /* valid only for clones */ u32 tstamp_lo; u8 ptp_cmd; u8 ts_id; @@ -273,4 +276,49 @@ static inline u32 ocelot_ptp_rew_op(struct sk_buff *skb) return rew_op; } +/** + * ocelot_xmit_get_vlan_info: Determine VLAN_TCI and TAG_TYPE for injected frame + * @skb: Pointer to socket buffer + * @br: Pointer to bridge device that the port is under, if any + * @vlan_tci: + * @tag_type: + * + * If the port is under a VLAN-aware bridge, remove the VLAN header from the + * payload and move it into the DSA tag, which will make the switch classify + * the packet to the bridge VLAN. Otherwise, leave the classified VLAN at zero, + * which is the pvid of standalone ports (OCELOT_STANDALONE_PVID), although not + * of VLAN-unaware bridge ports (that would be ocelot_vlan_unaware_pvid()). + * Anyway, VID 0 is fine because it is stripped on egress for these port modes, + * and source address learning is not performed for packets injected from the + * CPU anyway, so it doesn't matter that the VID is "wrong". + */ +static inline void ocelot_xmit_get_vlan_info(struct sk_buff *skb, + struct net_device *br, + u64 *vlan_tci, u64 *tag_type) +{ + struct vlan_ethhdr *hdr; + u16 proto, tci; + + if (!br || !br_vlan_enabled(br)) { + *vlan_tci = 0; + *tag_type = IFH_TAG_TYPE_C; + return; + } + + hdr = (struct vlan_ethhdr *)skb_mac_header(skb); + br_vlan_get_proto(br, &proto); + + if (ntohs(hdr->h_vlan_proto) == proto) { + vlan_remove_tag(skb, &tci); + *vlan_tci = tci; + } else { + rcu_read_lock(); + br_vlan_get_pvid_rcu(br, &tci); + rcu_read_unlock(); + *vlan_tci = tci; + } + + *tag_type = (proto != ETH_P_8021Q) ? IFH_TAG_TYPE_S : IFH_TAG_TYPE_C; +} + #endif diff --git a/include/linux/dw_apb_timer.h b/include/linux/dw_apb_timer.h index 82ebf9223948..f8811c46b89e 100644 --- a/include/linux/dw_apb_timer.h +++ b/include/linux/dw_apb_timer.h @@ -34,9 +34,6 @@ struct dw_apb_clocksource { }; void dw_apb_clockevent_register(struct dw_apb_clock_event_device *dw_ced); -void dw_apb_clockevent_pause(struct dw_apb_clock_event_device *dw_ced); -void dw_apb_clockevent_resume(struct dw_apb_clock_event_device *dw_ced); -void dw_apb_clockevent_stop(struct dw_apb_clock_event_device *dw_ced); struct dw_apb_clock_event_device * dw_apb_clockevent_init(int cpu, const char *name, unsigned rating, diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h index 4fcbf4d4fd0a..ff44ec346162 100644 --- a/include/linux/dynamic_debug.h +++ b/include/linux/dynamic_debug.h @@ -305,9 +305,9 @@ void __dynamic_ibdev_dbg(struct _ddebug *descriptor, #define DYNAMIC_DEBUG_BRANCH(descriptor) false #define dynamic_pr_debug(fmt, ...) \ - do { if (0) printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); } while (0) + no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #define dynamic_dev_dbg(dev, fmt, ...) \ - do { if (0) dev_printk(KERN_DEBUG, dev, fmt, ##__VA_ARGS__); } while (0) + dev_no_printk(KERN_DEBUG, dev, fmt, ##__VA_ARGS__) #define dynamic_hex_dump(prefix_str, prefix_type, rowsize, \ groupsize, buf, len, ascii) \ do { if (0) \ diff --git a/include/linux/dynamic_queue_limits.h b/include/linux/dynamic_queue_limits.h index 5693a4be0d9a..808b1a5102e7 100644 --- a/include/linux/dynamic_queue_limits.h +++ b/include/linux/dynamic_queue_limits.h @@ -50,6 +50,9 @@ struct dql { unsigned int adj_limit; /* limit + num_completed */ unsigned int last_obj_cnt; /* Count at last queuing */ + /* Stall threshold (in jiffies), defined by user */ + unsigned short stall_thrs; + unsigned long history_head; /* top 58 bits of jiffies */ /* stall entries, a bit per entry */ unsigned long history[DQL_HIST_LEN]; @@ -71,8 +74,6 @@ struct dql { unsigned int min_limit; /* Minimum limit */ unsigned int slack_hold_time; /* Time to measure slack */ - /* Stall threshold (in jiffies), defined by user */ - unsigned short stall_thrs; /* Longest stall detected, reported to user */ unsigned short stall_max; unsigned long last_reap; /* Last reap (in jiffies) */ @@ -83,27 +84,11 @@ struct dql { #define DQL_MAX_OBJECT (UINT_MAX / 16) #define DQL_MAX_LIMIT ((UINT_MAX / 2) - DQL_MAX_OBJECT) -/* - * Record number of objects queued. Assumes that caller has already checked - * availability in the queue with dql_avail. - */ -static inline void dql_queued(struct dql *dql, unsigned int count) +/* Populate the bitmap to be processed later in dql_check_stall() */ +static inline void dql_queue_stall(struct dql *dql) { unsigned long map, now, now_hi, i; - BUG_ON(count > DQL_MAX_OBJECT); - - dql->last_obj_cnt = count; - - /* We want to force a write first, so that cpu do not attempt - * to get cache line containing last_obj_cnt, num_queued, adj_limit - * in Shared state, but directly does a Request For Ownership - * It is only a hint, we use barrier() only. - */ - barrier(); - - dql->num_queued += count; - now = jiffies; now_hi = now / BITS_PER_LONG; @@ -133,6 +118,31 @@ static inline void dql_queued(struct dql *dql, unsigned int count) WRITE_ONCE(DQL_HIST_ENT(dql, now_hi), map | BIT_MASK(now)); } +/* + * Record number of objects queued. Assumes that caller has already checked + * availability in the queue with dql_avail. + */ +static inline void dql_queued(struct dql *dql, unsigned int count) +{ + if (WARN_ON_ONCE(count > DQL_MAX_OBJECT)) + return; + + WRITE_ONCE(dql->last_obj_cnt, count); + + /* We want to force a write first, so that cpu do not attempt + * to get cache line containing last_obj_cnt, num_queued, adj_limit + * in Shared state, but directly does a Request For Ownership + * It is only a hint, we use barrier() only. + */ + barrier(); + + dql->num_queued += count; + + /* Only populate stall information if the threshold is set */ + if (READ_ONCE(dql->stall_thrs)) + dql_queue_stall(dql); +} + /* Returns how many objects can be queued, < 0 indicates over limit. */ static inline int dql_avail(const struct dql *dql) { diff --git a/include/linux/eeprom_93cx6.h b/include/linux/eeprom_93cx6.h index c860c72a921d..3a485cc0e0fa 100644 --- a/include/linux/eeprom_93cx6.h +++ b/include/linux/eeprom_93cx6.h @@ -11,6 +11,8 @@ Supported chipsets: 93c46, 93c56 and 93c66. */ +#include <linux/bits.h> + /* * EEPROM operation defines. */ @@ -34,6 +36,7 @@ * @register_write(struct eeprom_93cx6 *eeprom): handler to * write to the eeprom register by using all reg_* fields. * @width: eeprom width, should be one of the PCI_EEPROM_WIDTH_* defines + * @quirks: eeprom or controller quirks * @drive_data: Set if we're driving the data line. * @reg_data_in: register field to indicate data input * @reg_data_out: register field to indicate data output @@ -50,6 +53,9 @@ struct eeprom_93cx6 { void (*register_write)(struct eeprom_93cx6 *eeprom); int width; + unsigned int quirks; +/* Some EEPROMs require an extra clock cycle before reading */ +#define PCI_EEPROM_QUIRK_EXTRA_READ_CYCLE BIT(0) char drive_data; char reg_data_in; @@ -71,3 +77,8 @@ extern void eeprom_93cx6_wren(struct eeprom_93cx6 *eeprom, bool enable); extern void eeprom_93cx6_write(struct eeprom_93cx6 *eeprom, u8 addr, u16 data); + +static inline bool has_quirk_extra_read_cycle(struct eeprom_93cx6 *eeprom) +{ + return eeprom->quirks & PCI_EEPROM_QUIRK_EXTRA_READ_CYCLE; +} diff --git a/include/linux/eeprom_93xx46.h b/include/linux/eeprom_93xx46.h deleted file mode 100644 index 34c2175e6a1e..000000000000 --- a/include/linux/eeprom_93xx46.h +++ /dev/null @@ -1,32 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Module: eeprom_93xx46 - * platform description for 93xx46 EEPROMs. - */ -#include <linux/gpio/consumer.h> - -struct eeprom_93xx46_platform_data { - unsigned char flags; -#define EE_ADDR8 0x01 /* 8 bit addr. cfg */ -#define EE_ADDR16 0x02 /* 16 bit addr. cfg */ -#define EE_READONLY 0x08 /* forbid writing */ -#define EE_SIZE1K 0x10 /* 1 kb of data, that is a 93xx46 */ -#define EE_SIZE2K 0x20 /* 2 kb of data, that is a 93xx56 */ -#define EE_SIZE4K 0x40 /* 4 kb of data, that is a 93xx66 */ - - unsigned int quirks; -/* Single word read transfers only; no sequential read. */ -#define EEPROM_93XX46_QUIRK_SINGLE_WORD_READ (1 << 0) -/* Instructions such as EWEN are (addrlen + 2) in length. */ -#define EEPROM_93XX46_QUIRK_INSTRUCTION_LENGTH (1 << 1) -/* Add extra cycle after address during a read */ -#define EEPROM_93XX46_QUIRK_EXTRA_READ_CYCLE BIT(2) - - /* - * optional hooks to control additional logic - * before and after spi transfer. - */ - void (*prepare)(void *); - void (*finish)(void *); - struct gpio_desc *select; -}; diff --git a/include/linux/efi.h b/include/linux/efi.h index d59b0947fba0..053c57e61869 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -74,10 +74,10 @@ typedef void *efi_handle_t; */ typedef guid_t efi_guid_t __aligned(__alignof__(u32)); -#define EFI_GUID(a, b, c, d...) (efi_guid_t){ { \ +#define EFI_GUID(a, b, c, d...) ((efi_guid_t){ { \ (a) & 0xff, ((a) >> 8) & 0xff, ((a) >> 16) & 0xff, ((a) >> 24) & 0xff, \ (b) & 0xff, ((b) >> 8) & 0xff, \ - (c) & 0xff, ((c) >> 8) & 0xff, d } } + (c) & 0xff, ((c) >> 8) & 0xff, d } }) /* * Generic EFI table header @@ -363,7 +363,6 @@ void efi_native_runtime_setup(void); #define ACPI_20_TABLE_GUID EFI_GUID(0x8868e871, 0xe4f1, 0x11d3, 0xbc, 0x22, 0x00, 0x80, 0xc7, 0x3c, 0x88, 0x81) #define SMBIOS_TABLE_GUID EFI_GUID(0xeb9d2d31, 0x2d88, 0x11d3, 0x9a, 0x16, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d) #define SMBIOS3_TABLE_GUID EFI_GUID(0xf2fd1544, 0x9794, 0x4a2c, 0x99, 0x2e, 0xe5, 0xbb, 0xcf, 0x20, 0xe3, 0x94) -#define UGA_IO_PROTOCOL_GUID EFI_GUID(0x61a4d49e, 0x6f68, 0x4f1b, 0xb9, 0x22, 0xa8, 0x6e, 0xed, 0x0b, 0x07, 0xa2) #define EFI_GLOBAL_VARIABLE_GUID EFI_GUID(0x8be4df61, 0x93ca, 0x11d2, 0xaa, 0x0d, 0x00, 0xe0, 0x98, 0x03, 0x2b, 0x8c) #define UV_SYSTEM_TABLE_GUID EFI_GUID(0x3b13a7d4, 0x633e, 0x11dd, 0x93, 0xec, 0xda, 0x25, 0x56, 0xd8, 0x95, 0x93) #define LINUX_EFI_CRASH_GUID EFI_GUID(0xcfc8fc79, 0xbe2e, 0x4ddc, 0x97, 0xf0, 0x9f, 0x98, 0xbf, 0xe2, 0x98, 0xa0) @@ -373,18 +372,17 @@ void efi_native_runtime_setup(void); #define EFI_DEVICE_PATH_TO_TEXT_PROTOCOL_GUID EFI_GUID(0x8b843e20, 0x8132, 0x4852, 0x90, 0xcc, 0x55, 0x1a, 0x4e, 0x4a, 0x7f, 0x1c) #define EFI_DEVICE_PATH_FROM_TEXT_PROTOCOL_GUID EFI_GUID(0x05c99a21, 0xc70f, 0x4ad2, 0x8a, 0x5f, 0x35, 0xdf, 0x33, 0x43, 0xf5, 0x1e) #define EFI_GRAPHICS_OUTPUT_PROTOCOL_GUID EFI_GUID(0x9042a9de, 0x23dc, 0x4a38, 0x96, 0xfb, 0x7a, 0xde, 0xd0, 0x80, 0x51, 0x6a) -#define EFI_UGA_PROTOCOL_GUID EFI_GUID(0x982c298b, 0xf4fa, 0x41cb, 0xb8, 0x38, 0x77, 0xaa, 0x68, 0x8f, 0xb8, 0x39) #define EFI_PCI_IO_PROTOCOL_GUID EFI_GUID(0x4cf5b200, 0x68b8, 0x4ca5, 0x9e, 0xec, 0xb2, 0x3e, 0x3f, 0x50, 0x02, 0x9a) #define EFI_FILE_INFO_ID EFI_GUID(0x09576e92, 0x6d3f, 0x11d2, 0x8e, 0x39, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b) #define EFI_SYSTEM_RESOURCE_TABLE_GUID EFI_GUID(0xb122a263, 0x3661, 0x4f68, 0x99, 0x29, 0x78, 0xf8, 0xb0, 0xd6, 0x21, 0x80) #define EFI_FILE_SYSTEM_GUID EFI_GUID(0x964e5b22, 0x6459, 0x11d2, 0x8e, 0x39, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b) #define DEVICE_TREE_GUID EFI_GUID(0xb1b621d5, 0xf19c, 0x41a5, 0x83, 0x0b, 0xd9, 0x15, 0x2c, 0x69, 0xaa, 0xe0) -#define EFI_PROPERTIES_TABLE_GUID EFI_GUID(0x880aaca3, 0x4adc, 0x4a04, 0x90, 0x79, 0xb7, 0x47, 0x34, 0x08, 0x25, 0xe5) #define EFI_RNG_PROTOCOL_GUID EFI_GUID(0x3152bca5, 0xeade, 0x433d, 0x86, 0x2e, 0xc0, 0x1c, 0xdc, 0x29, 0x1f, 0x44) #define EFI_RNG_ALGORITHM_RAW EFI_GUID(0xe43176d7, 0xb6e8, 0x4827, 0xb7, 0x84, 0x7f, 0xfd, 0xc4, 0xb6, 0x85, 0x61) #define EFI_MEMORY_ATTRIBUTES_TABLE_GUID EFI_GUID(0xdcfa911d, 0x26eb, 0x469f, 0xa2, 0x20, 0x38, 0xb7, 0xdc, 0x46, 0x12, 0x20) #define EFI_CONSOLE_OUT_DEVICE_GUID EFI_GUID(0xd3b36f2c, 0xd551, 0x11d4, 0x9a, 0x46, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d) #define APPLE_PROPERTIES_PROTOCOL_GUID EFI_GUID(0x91bd12fe, 0xf6c3, 0x44fb, 0xa5, 0xb7, 0x51, 0x22, 0xab, 0x30, 0x3a, 0xe0) +#define APPLE_SET_OS_PROTOCOL_GUID EFI_GUID(0xc5c5da95, 0x7d5c, 0x45e6, 0xb2, 0xf1, 0x3f, 0xd5, 0x2b, 0xb1, 0x00, 0x77) #define EFI_TCG2_PROTOCOL_GUID EFI_GUID(0x607f766c, 0x7455, 0x42be, 0x93, 0x0b, 0xe4, 0xd7, 0x6d, 0xb2, 0x72, 0x0f) #define EFI_TCG2_FINAL_EVENTS_TABLE_GUID EFI_GUID(0x1e2ed096, 0x30e2, 0x4254, 0xbd, 0x89, 0x86, 0x3b, 0xbe, 0xf8, 0x23, 0x25) #define EFI_LOAD_FILE_PROTOCOL_GUID EFI_GUID(0x56ec3091, 0x954c, 0x11d2, 0x8e, 0x3f, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b) @@ -580,15 +578,6 @@ struct efi_mem_range { }; typedef struct { - u32 version; - u32 length; - u64 memory_protection_attribute; -} efi_properties_table_t; - -#define EFI_PROPERTIES_TABLE_VERSION 0x00010000 -#define EFI_PROPERTIES_RUNTIME_MEMORY_PROTECTION_NON_EXECUTABLE_PE_DATA 0x1 - -typedef struct { u16 version; u16 length; u32 runtime_services_supported; @@ -607,7 +596,11 @@ typedef struct { u32 num_entries; u32 desc_size; u32 flags; - efi_memory_desc_t entry[0]; + /* + * There are @num_entries following, each of size @desc_size bytes, + * including an efi_memory_desc_t header. See efi_memdesc_ptr(). + */ + efi_memory_desc_t entry[]; } efi_memory_attributes_table_t; typedef struct { @@ -759,8 +752,6 @@ 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, - struct resource *data_resource, struct resource *bss_resource); extern u64 efi_get_fdt_params(struct efi_memory_map_data *data); extern struct kobject *efi_kobj; @@ -783,7 +774,7 @@ extern int efi_memattr_apply_permissions(struct mm_struct *mm, efi_memattr_perm_setter fn); /* - * efi_early_memdesc_ptr - get the n-th EFI memmap descriptor + * efi_memdesc_ptr - get the n-th EFI memmap descriptor * @map: the start of efi memmap * @desc_size: the size of space for each EFI memmap descriptor * @n: the index of efi memmap descriptor @@ -801,7 +792,7 @@ extern int efi_memattr_apply_permissions(struct mm_struct *mm, * during bootup since for_each_efi_memory_desc_xxx() is available after the * kernel initializes the EFI subsystem to set up struct efi_memory_map. */ -#define efi_early_memdesc_ptr(map, desc_size, n) \ +#define efi_memdesc_ptr(map, desc_size, n) \ (efi_memory_desc_t *)((void *)(map) + ((n) * (desc_size))) /* Iterate through an efi_memory_map */ @@ -868,10 +859,9 @@ static inline int efi_range_is_wc(unsigned long start, unsigned long len) #define EFI_PARAVIRT 6 /* Access is via a paravirt interface */ #define EFI_ARCH_1 7 /* First arch-specific bit */ #define EFI_DBG 8 /* Print additional debug info at runtime */ -#define EFI_NX_PE_DATA 9 /* Can runtime data regions be mapped non-executable? */ -#define EFI_MEM_ATTR 10 /* Did firmware publish an EFI_MEMORY_ATTRIBUTES table? */ -#define EFI_MEM_NO_SOFT_RESERVE 11 /* Is the kernel configured to ignore soft reservations? */ -#define EFI_PRESERVE_BS_REGIONS 12 /* Are EFI boot-services memory segments available? */ +#define EFI_MEM_ATTR 9 /* Did firmware publish an EFI_MEMORY_ATTRIBUTES table? */ +#define EFI_MEM_NO_SOFT_RESERVE 10 /* Is the kernel configured to ignore soft reservations? */ +#define EFI_PRESERVE_BS_REGIONS 11 /* Are EFI boot-services memory segments available? */ #ifdef CONFIG_EFI /* @@ -1072,12 +1062,11 @@ static inline u64 efivar_reserved_space(void) { return 0; } #endif /* - * The maximum size of VariableName + Data = 1024 - * Therefore, it's reasonable to save that much - * space in each part of the structure, - * and we use a page for reading/writing. + * There is no actual upper limit specified for the variable name size. + * + * This limit exists only for practical purposes, since name conversions + * are bounds-checked and name data is occasionally stored in-line. */ - #define EFI_VAR_NAME_LEN 1024 int efivars_register(struct efivars *efivars, @@ -1295,8 +1284,6 @@ struct linux_efi_memreserve { void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size); -char *efi_systab_show_arch(char *str); - /* * The LINUX_EFI_MOK_VARIABLE_TABLE_GUID config table can be provided * to the kernel by an EFI boot loader. The table contains a packed diff --git a/include/linux/einj-cxl.h b/include/linux/einj-cxl.h deleted file mode 100644 index 624ff6ff41f9..000000000000 --- a/include/linux/einj-cxl.h +++ /dev/null @@ -1,44 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * CXL protocol Error INJection support. - * - * Copyright (c) 2023 Advanced Micro Devices, Inc. - * All Rights Reserved. - * - * Author: Ben Cheatham <benjamin.cheatham@amd.com> - */ -#ifndef EINJ_CXL_H -#define EINJ_CXL_H - -#include <linux/errno.h> -#include <linux/types.h> - -struct pci_dev; -struct seq_file; - -#if IS_ENABLED(CONFIG_ACPI_APEI_EINJ_CXL) -int einj_cxl_available_error_type_show(struct seq_file *m, void *v); -int einj_cxl_inject_error(struct pci_dev *dport_dev, u64 type); -int einj_cxl_inject_rch_error(u64 rcrb, u64 type); -bool einj_cxl_is_initialized(void); -#else /* !IS_ENABLED(CONFIG_ACPI_APEI_EINJ_CXL) */ -static inline int einj_cxl_available_error_type_show(struct seq_file *m, - void *v) -{ - return -ENXIO; -} - -static inline int einj_cxl_inject_error(struct pci_dev *dport_dev, u64 type) -{ - return -ENXIO; -} - -static inline int einj_cxl_inject_rch_error(u64 rcrb, u64 type) -{ - return -ENXIO; -} - -static inline bool einj_cxl_is_initialized(void) { return false; } -#endif /* CONFIG_ACPI_APEI_EINJ_CXL */ - -#endif /* EINJ_CXL_H */ diff --git a/include/linux/eisa.h b/include/linux/eisa.h index b012e30afebd..f98200cae637 100644 --- a/include/linux/eisa.h +++ b/include/linux/eisa.h @@ -60,7 +60,7 @@ struct eisa_driver { struct device_driver driver; }; -#define to_eisa_driver(drv) container_of(drv,struct eisa_driver, driver) +#define to_eisa_driver(drv) container_of_const(drv,struct eisa_driver, driver) /* These external functions are only available when EISA support is enabled. */ #ifdef CONFIG_EISA diff --git a/include/linux/elf.h b/include/linux/elf.h index c9a46c4e183b..5c402788da19 100644 --- a/include/linux/elf.h +++ b/include/linux/elf.h @@ -65,7 +65,7 @@ extern Elf64_Dyn _DYNAMIC []; struct file; struct coredump_params; -#ifndef ARCH_HAVE_EXTRA_ELF_NOTES +#ifndef CONFIG_ARCH_HAVE_EXTRA_ELF_NOTES static inline int elf_coredump_extra_notes_size(void) { return 0; } static inline int elf_coredump_extra_notes_write(struct coredump_params *cprm) { return 0; } #else diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 70cd7258cd29..78318d49276d 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -55,6 +55,8 @@ struct em_perf_table { * struct em_perf_domain - Performance domain * @em_table: Pointer to the runtime modifiable em_perf_table * @nr_perf_states: Number of performance states + * @min_perf_state: Minimum allowed Performance State index + * @max_perf_state: Maximum allowed Performance State index * @flags: See "em_perf_domain flags" * @cpus: Cpumask covering the CPUs of the domain. It's here * for performance reasons to avoid potential cache @@ -70,6 +72,8 @@ struct em_perf_table { struct em_perf_domain { struct em_perf_table __rcu *em_table; int nr_perf_states; + int min_perf_state; + int max_perf_state; unsigned long flags; unsigned long cpus[]; }; @@ -172,13 +176,16 @@ struct em_perf_table __rcu *em_table_alloc(struct em_perf_domain *pd); void em_table_free(struct em_perf_table __rcu *table); int em_dev_compute_costs(struct device *dev, struct em_perf_state *table, int nr_states); +int em_dev_update_chip_binning(struct device *dev); +int em_update_performance_limits(struct em_perf_domain *pd, + unsigned long freq_min_khz, unsigned long freq_max_khz); +void em_rebuild_sched_domains(void); /** * em_pd_get_efficient_state() - Get an efficient performance state from the EM * @table: List of performance states, in ascending order - * @nr_perf_states: Number of performance states + * @pd: performance domain for which this must be done * @max_util: Max utilization to map with the EM - * @pd_flags: Performance Domain flags * * It is called from the scheduler code quite frequently and as a consequence * doesn't implement any check. @@ -187,13 +194,16 @@ int em_dev_compute_costs(struct device *dev, struct em_perf_state *table, * requirement. */ static inline int -em_pd_get_efficient_state(struct em_perf_state *table, int nr_perf_states, - unsigned long max_util, unsigned long pd_flags) +em_pd_get_efficient_state(struct em_perf_state *table, + struct em_perf_domain *pd, unsigned long max_util) { + unsigned long pd_flags = pd->flags; + int min_ps = pd->min_perf_state; + int max_ps = pd->max_perf_state; struct em_perf_state *ps; int i; - for (i = 0; i < nr_perf_states; i++) { + for (i = min_ps; i <= max_ps; i++) { ps = &table[i]; if (ps->performance >= max_util) { if (pd_flags & EM_PERF_DOMAIN_SKIP_INEFFICIENCIES && @@ -203,7 +213,7 @@ em_pd_get_efficient_state(struct em_perf_state *table, int nr_perf_states, } } - return nr_perf_states - 1; + return max_ps; } /** @@ -252,8 +262,7 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd, * requested performance. */ em_table = rcu_dereference(pd->em_table); - i = em_pd_get_efficient_state(em_table->state, pd->nr_perf_states, - max_util, pd->flags); + i = em_pd_get_efficient_state(em_table->state, pd, max_util); ps = &em_table->state[i]; /* @@ -386,6 +395,17 @@ int em_dev_compute_costs(struct device *dev, struct em_perf_state *table, { return -EINVAL; } +static inline int em_dev_update_chip_binning(struct device *dev) +{ + return -EINVAL; +} +static inline +int em_update_performance_limits(struct em_perf_domain *pd, + unsigned long freq_min_khz, unsigned long freq_max_khz) +{ + return -EINVAL; +} +static inline void em_rebuild_sched_domains(void) {} #endif #endif diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h index b0fb775a600d..fc61d0205c97 100644 --- a/include/linux/entry-common.h +++ b/include/linux/entry-common.h @@ -64,7 +64,8 @@ #define EXIT_TO_USER_MODE_WORK \ (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE | \ - _TIF_NEED_RESCHED | _TIF_PATCH_PENDING | _TIF_NOTIFY_SIGNAL | \ + _TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY | \ + _TIF_PATCH_PENDING | _TIF_NOTIFY_SIGNAL | \ ARCH_EXIT_TO_USER_MODE_WORK) /** @@ -108,7 +109,7 @@ 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() != CT_STATE_USER); user_exit_irqoff(); instrumentation_begin(); diff --git a/include/linux/entry-kvm.h b/include/linux/entry-kvm.h index 6813171afccb..16149f6625e4 100644 --- a/include/linux/entry-kvm.h +++ b/include/linux/entry-kvm.h @@ -17,8 +17,9 @@ #endif #define XFER_TO_GUEST_MODE_WORK \ - (_TIF_NEED_RESCHED | _TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL | \ - _TIF_NOTIFY_RESUME | ARCH_XFER_TO_GUEST_MODE_WORK) + (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY | _TIF_SIGPENDING | \ + _TIF_NOTIFY_SIGNAL | _TIF_NOTIFY_RESUME | \ + ARCH_XFER_TO_GUEST_MODE_WORK) struct kvm_vcpu; diff --git a/include/linux/err.h b/include/linux/err.h index b5d9bb2a2349..a4dacd745fcf 100644 --- a/include/linux/err.h +++ b/include/linux/err.h @@ -41,6 +41,9 @@ static inline void * __must_check ERR_PTR(long error) return (void *) error; } +/* Return the pointer in the percpu address space. */ +#define ERR_PTR_PCPU(error) ((void __percpu *)(unsigned long)ERR_PTR(error)) + /** * PTR_ERR - Extract the error code from an error pointer. * @ptr: An error pointer. @@ -51,6 +54,9 @@ static inline long __must_check PTR_ERR(__force const void *ptr) return (long) ptr; } +/* Read an error pointer from the percpu address space. */ +#define PTR_ERR_PCPU(ptr) (PTR_ERR((const void *)(__force const unsigned long)(ptr))) + /** * IS_ERR - Detect an error pointer. * @ptr: The pointer to check. @@ -61,6 +67,9 @@ static inline bool __must_check IS_ERR(__force const void *ptr) return IS_ERR_VALUE((unsigned long)ptr); } +/* Read an error pointer from the percpu address space. */ +#define IS_ERR_PCPU(ptr) (IS_ERR((const void *)(__force const unsigned long)(ptr))) + /** * IS_ERR_OR_NULL - Detect an error pointer or a null pointer. * @ptr: The pointer to check. diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 297231854ada..9a1eacf35d37 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -21,7 +21,7 @@ #include <linux/netdevice.h> #include <linux/random.h> #include <linux/crc32.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <asm/bitsperlong.h> #ifdef __KERNEL__ @@ -71,11 +71,17 @@ static const u8 eth_reserved_addr_base[ETH_ALEN] __aligned(2) = { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x00 }; #define eth_stp_addr eth_reserved_addr_base +static const u8 eth_ipv4_mcast_addr_base[ETH_ALEN] __aligned(2) = +{ 0x01, 0x00, 0x5e, 0x00, 0x00, 0x00 }; + +static const u8 eth_ipv6_mcast_addr_base[ETH_ALEN] __aligned(2) = +{ 0x33, 0x33, 0x00, 0x00, 0x00, 0x00 }; + /** * is_link_local_ether_addr - Determine if given Ethernet address is link-local * @addr: Pointer to a six-byte array containing the Ethernet address * - * Return true if address is link local reserved addr (01:80:c2:00:00:0X) per + * Return: true if address is link local reserved addr (01:80:c2:00:00:0X) per * IEEE 802.1Q 8.6.3 Frame filtering. * * Please note: addr must be aligned to u16. @@ -98,7 +104,7 @@ static inline bool is_link_local_ether_addr(const u8 *addr) * is_zero_ether_addr - Determine if give Ethernet address is all zeros. * @addr: Pointer to a six-byte array containing the Ethernet address * - * Return true if the address is all zeroes. + * Return: true if the address is all zeroes. * * Please note: addr must be aligned to u16. */ @@ -117,7 +123,7 @@ static inline bool is_zero_ether_addr(const u8 *addr) * is_multicast_ether_addr - Determine if the Ethernet address is a multicast. * @addr: Pointer to a six-byte array containing the Ethernet address * - * Return true if the address is a multicast address. + * Return: true if the address is a multicast address. * By definition the broadcast address is also a multicast address. */ static inline bool is_multicast_ether_addr(const u8 *addr) @@ -151,7 +157,7 @@ static inline bool is_multicast_ether_addr_64bits(const u8 *addr) * is_local_ether_addr - Determine if the Ethernet address is locally-assigned one (IEEE 802). * @addr: Pointer to a six-byte array containing the Ethernet address * - * Return true if the address is a local address. + * Return: true if the address is a local address. */ static inline bool is_local_ether_addr(const u8 *addr) { @@ -162,7 +168,7 @@ static inline bool is_local_ether_addr(const u8 *addr) * is_broadcast_ether_addr - Determine if the Ethernet address is broadcast * @addr: Pointer to a six-byte array containing the Ethernet address * - * Return true if the address is the broadcast address. + * Return: true if the address is the broadcast address. * * Please note: addr must be aligned to u16. */ @@ -177,7 +183,7 @@ static inline bool is_broadcast_ether_addr(const u8 *addr) * is_unicast_ether_addr - Determine if the Ethernet address is unicast * @addr: Pointer to a six-byte array containing the Ethernet address * - * Return true if the address is a unicast address. + * Return: true if the address is a unicast address. */ static inline bool is_unicast_ether_addr(const u8 *addr) { @@ -191,7 +197,7 @@ static inline bool is_unicast_ether_addr(const u8 *addr) * Check that the Ethernet address (MAC) is not 00:00:00:00:00:00, is not * a multicast address, and is not FF:FF:FF:FF:FF:FF. * - * Return true if the address is valid. + * Return: true if the address is valid. * * Please note: addr must be aligned to u16. */ @@ -208,7 +214,7 @@ static inline bool is_valid_ether_addr(const u8 *addr) * * Check that the value from the Ethertype/length field is a valid Ethertype. * - * Return true if the valid is an 802.3 supported Ethertype. + * Return: true if the valid is an 802.3 supported Ethertype. */ static inline bool eth_proto_is_802_3(__be16 proto) { @@ -430,18 +436,16 @@ static inline bool ether_addr_equal_masked(const u8 *addr1, const u8 *addr2, static inline bool ether_addr_is_ipv4_mcast(const u8 *addr) { - u8 base[ETH_ALEN] = { 0x01, 0x00, 0x5e, 0x00, 0x00, 0x00 }; u8 mask[ETH_ALEN] = { 0xff, 0xff, 0xff, 0x80, 0x00, 0x00 }; - return ether_addr_equal_masked(addr, base, mask); + return ether_addr_equal_masked(addr, eth_ipv4_mcast_addr_base, mask); } static inline bool ether_addr_is_ipv6_mcast(const u8 *addr) { - u8 base[ETH_ALEN] = { 0x33, 0x33, 0x00, 0x00, 0x00, 0x00 }; u8 mask[ETH_ALEN] = { 0xff, 0xff, 0x00, 0x00, 0x00, 0x00 }; - return ether_addr_equal_masked(addr, base, mask); + return ether_addr_equal_masked(addr, eth_ipv6_mcast_addr_base, mask); } static inline bool ether_addr_is_ip_mcast(const u8 *addr) @@ -454,7 +458,7 @@ static inline bool ether_addr_is_ip_mcast(const u8 *addr) * ether_addr_to_u64 - Convert an Ethernet address into a u64 value. * @addr: Pointer to a six-byte array containing the Ethernet address * - * Return a u64 value of the address + * Return: a u64 value of the address */ static inline u64 ether_addr_to_u64(const u8 *addr) { @@ -632,8 +636,16 @@ static inline void eth_skb_pkt_type(struct sk_buff *skb, } } +static inline struct ethhdr *eth_skb_pull_mac(struct sk_buff *skb) +{ + struct ethhdr *eth = (struct ethhdr *)skb->data; + + skb_pull_inline(skb, ETH_HLEN); + return eth; +} + /** - * eth_skb_pad - Pad buffer to mininum number of octets for Ethernet frame + * eth_skb_pad - Pad buffer to minimum number of octets for Ethernet frame * @skb: Buffer to pad * * An Ethernet frame should have a minimum size of 60 bytes. This function diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 9901e563f706..870994cc3ef7 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -18,6 +18,7 @@ #include <linux/if_ether.h> #include <linux/netlink.h> #include <uapi/linux/ethtool.h> +#include <uapi/linux/net_tstamp.h> struct compat_ethtool_rx_flow_spec { u32 flow_type; @@ -77,6 +78,9 @@ enum { * @cqe_size: Size of TX/RX completion queue event * @tx_push_buf_len: Size of TX push buffer * @tx_push_buf_max_len: Maximum allowed size of TX push buffer + * @hds_thresh: Packet size threshold for header data split (HDS) + * @hds_thresh_max: Maximum supported setting for @hds_threshold + * */ struct kernel_ethtool_ringparam { u32 rx_buf_len; @@ -86,6 +90,8 @@ struct kernel_ethtool_ringparam { u32 cqe_size; u32 tx_push_buf_len; u32 tx_push_buf_max_len; + u32 hds_thresh; + u32 hds_thresh_max; }; /** @@ -96,6 +102,7 @@ struct kernel_ethtool_ringparam { * @ETHTOOL_RING_USE_RX_PUSH: capture for setting rx_push * @ETHTOOL_RING_USE_TX_PUSH_BUF_LEN: capture for setting tx_push_buf_len * @ETHTOOL_RING_USE_TCP_DATA_SPLIT: capture for setting tcp_data_split + * @ETHTOOL_RING_USE_HDS_THRS: capture for setting header-data-split-thresh */ enum ethtool_supported_ring_param { ETHTOOL_RING_USE_RX_BUF_LEN = BIT(0), @@ -104,6 +111,7 @@ enum ethtool_supported_ring_param { ETHTOOL_RING_USE_RX_PUSH = BIT(3), ETHTOOL_RING_USE_TX_PUSH_BUF_LEN = BIT(4), ETHTOOL_RING_USE_TCP_DATA_SPLIT = BIT(5), + ETHTOOL_RING_USE_HDS_THRS = BIT(6), }; #define __ETH_RSS_HASH_BIT(bit) ((u32)1 << (bit)) @@ -159,6 +167,49 @@ static inline u32 ethtool_rxfh_indir_default(u32 index, u32 n_rx_rings) return index % n_rx_rings; } +/** + * struct ethtool_rxfh_context - a custom RSS context configuration + * @indir_size: Number of u32 entries in indirection table + * @key_size: Size of hash key, in bytes + * @priv_size: Size of driver private data, in bytes + * @hfunc: RSS hash function identifier. One of the %ETH_RSS_HASH_* + * @input_xfrm: Defines how the input data is transformed. Valid values are one + * of %RXH_XFRM_*. + * @indir_configured: indir has been specified (at create time or subsequently) + * @key_configured: hkey has been specified (at create time or subsequently) + */ +struct ethtool_rxfh_context { + u32 indir_size; + u32 key_size; + u16 priv_size; + u8 hfunc; + u8 input_xfrm; + u8 indir_configured:1; + u8 key_configured:1; + /* private: driver private data, indirection table, and hash key are + * stored sequentially in @data area. Use below helpers to access. + */ + u32 key_off; + u8 data[] __aligned(sizeof(void *)); +}; + +static inline void *ethtool_rxfh_context_priv(struct ethtool_rxfh_context *ctx) +{ + return ctx->data; +} + +static inline u32 *ethtool_rxfh_context_indir(struct ethtool_rxfh_context *ctx) +{ + return (u32 *)(ctx->data + ALIGN(ctx->priv_size, sizeof(u32))); +} + +static inline u8 *ethtool_rxfh_context_key(struct ethtool_rxfh_context *ctx) +{ + return &ctx->data[ctx->key_off]; +} + +void ethtool_rxfh_context_lost(struct net_device *dev, u32 context_id); + /* declare a link mode bitmap */ #define __ETHTOOL_DECLARE_LINK_MODE_MASK(name) \ DECLARE_BITMAP(name, __ETHTOOL_LINK_MODE_MASK_NBITS) @@ -213,7 +264,7 @@ struct ethtool_link_ksettings { * @mode : one of the ETHTOOL_LINK_MODE_*_BIT * (not atomic, no bound checking) * - * Returns true/false. + * Returns: true/false. */ #define ethtool_link_ksettings_test_link_mode(ptr, name, mode) \ test_bit(ETHTOOL_LINK_MODE_ ## mode ## _BIT, (ptr)->link_modes.name) @@ -284,7 +335,9 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, #define ETHTOOL_COALESCE_TX_AGGR_MAX_BYTES BIT(24) #define ETHTOOL_COALESCE_TX_AGGR_MAX_FRAMES BIT(25) #define ETHTOOL_COALESCE_TX_AGGR_TIME_USECS BIT(26) -#define ETHTOOL_COALESCE_ALL_PARAMS GENMASK(26, 0) +#define ETHTOOL_COALESCE_RX_PROFILE BIT(27) +#define ETHTOOL_COALESCE_TX_PROFILE BIT(28) +#define ETHTOOL_COALESCE_ALL_PARAMS GENMASK(28, 0) #define ETHTOOL_COALESCE_USECS \ (ETHTOOL_COALESCE_RX_USECS | ETHTOOL_COALESCE_TX_USECS) @@ -366,6 +419,29 @@ struct ethtool_eth_phy_stats { ); }; +/** + * struct ethtool_phy_stats - PHY-level statistics counters + * @rx_packets: Total successfully received frames + * @rx_bytes: Total successfully received bytes + * @rx_errors: Total received frames with errors (e.g., CRC errors) + * @tx_packets: Total successfully transmitted frames + * @tx_bytes: Total successfully transmitted bytes + * @tx_errors: Total transmitted frames with errors + * + * This structure provides a standardized interface for reporting + * PHY-level statistics counters. It is designed to expose statistics + * commonly provided by PHYs but not explicitly defined in the IEEE + * 802.3 standard. + */ +struct ethtool_phy_stats { + u64 rx_packets; + u64 rx_bytes; + u64 rx_errors; + u64 tx_packets; + u64 tx_bytes; + u64 tx_errors; +}; + /* Basic IEEE 802.3 MAC Ctrl statistics (30.3.3.*), not otherwise exposed * via a more targeted API. */ @@ -480,21 +556,47 @@ struct ethtool_rmon_stats { ); }; +/** + * struct ethtool_ts_stats - HW timestamping statistics + * @pkts: Number of packets successfully timestamped by the hardware. + * @onestep_pkts_unconfirmed: Number of PTP packets with one-step TX + * timestamping that were sent, but for which the + * device offers no confirmation whether they made + * it onto the wire and the timestamp was inserted + * in the originTimestamp or correctionField, or + * not. + * @lost: Number of hardware timestamping requests where the timestamping + * information from the hardware never arrived for submission with + * the skb. + * @err: Number of arbitrary timestamp generation error events that the + * hardware encountered, exclusive of @lost statistics. Cases such + * as resource exhaustion, unavailability, firmware errors, and + * detected illogical timestamp values not submitted with the skb + * are inclusive to this counter. + */ +struct ethtool_ts_stats { + struct_group(tx_stats, + u64 pkts; + u64 onestep_pkts_unconfirmed; + u64 lost; + u64 err; + ); +}; + #define ETH_MODULE_EEPROM_PAGE_LEN 128 #define ETH_MODULE_MAX_I2C_ADDRESS 0x7f /** - * struct ethtool_module_eeprom - EEPROM dump from specified page - * @offset: Offset within the specified EEPROM page to begin read, in bytes. - * @length: Number of bytes to read. - * @page: Page number to read from. - * @bank: Page bank number to read from, if applicable by EEPROM spec. + * struct ethtool_module_eeprom - plug-in module EEPROM read / write parameters + * @offset: When @offset is 0-127, it is used as an address to the Lower Memory + * (@page must be 0). Otherwise, it is used as an address to the + * Upper Memory. + * @length: Number of bytes to read / write. + * @page: Page number. + * @bank: Bank number, if supported by EEPROM spec. * @i2c_address: I2C address of a page. Value less than 0x7f expected. Most * EEPROMs use 0x50 or 0x51. * @data: Pointer to buffer with EEPROM data of @length size. - * - * This can be used to manage pages during EEPROM dump in ethtool and pass - * required information to the driver. */ struct ethtool_module_eeprom { u32 offset; @@ -642,15 +744,51 @@ struct ethtool_rxfh_param { }; /** + * struct kernel_ethtool_ts_info - kernel copy of struct ethtool_ts_info + * @cmd: command number = %ETHTOOL_GET_TS_INFO + * @so_timestamping: bit mask of the sum of the supported SO_TIMESTAMPING flags + * @phc_index: device index of the associated PHC, or -1 if there is none + * @phc_qualifier: qualifier of the associated PHC + * @tx_types: bit mask of the supported hwtstamp_tx_types enumeration values + * @rx_filters: bit mask of the supported hwtstamp_rx_filters enumeration values + */ +struct kernel_ethtool_ts_info { + u32 cmd; + u32 so_timestamping; + int phc_index; + enum hwtstamp_provider_qualifier phc_qualifier; + enum hwtstamp_tx_types tx_types; + enum hwtstamp_rx_filters rx_filters; +}; + +/** * struct ethtool_ops - optional netdev operations * @cap_link_lanes_supported: indicates if the driver supports lanes * parameter. * @cap_rss_ctx_supported: indicates if the driver supports RSS - * contexts. + * contexts via legacy API, drivers implementing @create_rxfh_context + * do not have to set this bit. * @cap_rss_sym_xor_supported: indicates if the driver supports symmetric-xor * RSS. + * @rxfh_per_ctx_key: device supports setting different RSS key for each + * additional context. Netlink API should report hfunc, key, and input_xfrm + * for every context, not just context 0. + * @cap_rss_rxnfc_adds: device supports nonzero ring_cookie in filters with + * %FLOW_RSS flag; the queue ID from the filter is added to the value from + * the indirection table to determine the delivery queue. + * @rxfh_indir_space: max size of RSS indirection tables, if indirection table + * size as returned by @get_rxfh_indir_size may change during lifetime + * of the device. Leave as 0 if the table size is constant. + * @rxfh_key_space: same as @rxfh_indir_space, but for the key. + * @rxfh_priv_size: size of the driver private data area the core should + * allocate for an RSS context (in &struct ethtool_rxfh_context). + * @rxfh_max_num_contexts: maximum (exclusive) supported RSS context ID. + * If this is zero then the core may choose any (nonzero) ID, otherwise + * the core will only use IDs strictly less than this value, as the + * @rss_context argument to @create_rxfh_context and friends. * @supported_coalesce_params: supported types of interrupt coalescing. * @supported_ring_params: supported ring params. + * @supported_hwtstamp_qualifiers: bitfield of supported hwtstamp qualifier. * @get_drvinfo: Report driver/device information. Modern drivers no * longer have to implement this callback. Most fields are * correctly filled in by the core using system information, or @@ -745,6 +883,32 @@ struct ethtool_rxfh_param { * will remain unchanged. * Returns a negative error code or zero. An error code must be returned * if at least one unsupported change was requested. + * @create_rxfh_context: Create a new RSS context with the specified RX flow + * hash indirection table, hash key, and hash function. + * The &struct ethtool_rxfh_context for this context is passed in @ctx; + * note that the indir table, hkey and hfunc are not yet populated as + * of this call. The driver does not need to update these; the core + * will do so if this op succeeds. + * However, if @rxfh.indir is set to %NULL, the driver must update the + * indir table in @ctx with the (default or inherited) table actually in + * use; similarly, if @rxfh.key is %NULL, @rxfh.hfunc is + * %ETH_RSS_HASH_NO_CHANGE, or @rxfh.input_xfrm is %RXH_XFRM_NO_CHANGE, + * the driver should update the corresponding information in @ctx. + * If the driver provides this method, it must also provide + * @modify_rxfh_context and @remove_rxfh_context. + * Returns a negative error code or zero. + * @modify_rxfh_context: Reconfigure the specified RSS context. Allows setting + * the contents of the RX flow hash indirection table, hash key, and/or + * hash function associated with the given context. + * Parameters which are set to %NULL or zero will remain unchanged. + * The &struct ethtool_rxfh_context for this context is passed in @ctx; + * note that it will still contain the *old* settings. The driver does + * not need to update these; the core will do so if this op succeeds. + * Returns a negative error code or zero. An error code must be returned + * if at least one unsupported change was requested. + * @remove_rxfh_context: Remove the specified RSS context. + * The &struct ethtool_rxfh_context for this context is passed in @ctx. + * Returns a negative error code or zero. * @get_channels: Get number of channels. * @set_channels: Set number of channels. Returns a negative error code or * zero. @@ -755,7 +919,10 @@ struct ethtool_rxfh_param { * @get_ts_info: Get the time stamping and PTP hardware clock capabilities. * It may be called with RCU, or rtnl or reference on the device. * Drivers supporting transmit time stamps in software should set this to - * ethtool_op_get_ts_info(). + * ethtool_op_get_ts_info(). Drivers must not zero statistics which they + * don't report. The stats structure is initialized to ETHTOOL_STAT_NOT_SET + * indicating driver does not report statistics. + * @get_ts_stats: Query the device hardware timestamping statistics. * @get_module_info: Get the size and type of the eeprom contained within * a plug-in module. * @get_module_eeprom: Get the eeprom information from the plug-in module @@ -799,6 +966,8 @@ struct ethtool_rxfh_param { * @get_module_eeprom_by_page: Get a region of plug-in module EEPROM data from * specified page. Returns a negative error code or the amount of bytes * read. + * @set_module_eeprom_by_page: Write to a region of plug-in module EEPROM, + * from kernel space only. Returns a negative error code or zero. * @get_eth_phy_stats: Query some of the IEEE 802.3 PHY statistics. * @get_eth_mac_stats: Query some of the IEEE 802.3 MAC statistics. * @get_eth_ctrl_stats: Query some of the IEEE 802.3 MAC Ctrl statistics. @@ -829,8 +998,15 @@ struct ethtool_ops { u32 cap_link_lanes_supported:1; u32 cap_rss_ctx_supported:1; u32 cap_rss_sym_xor_supported:1; + u32 rxfh_per_ctx_key:1; + u32 cap_rss_rxnfc_adds:1; + u32 rxfh_indir_space; + u16 rxfh_key_space; + u16 rxfh_priv_size; + u32 rxfh_max_num_contexts; u32 supported_coalesce_params; u32 supported_ring_params; + u32 supported_hwtstamp_qualifiers; void (*get_drvinfo)(struct net_device *, struct ethtool_drvinfo *); int (*get_regs_len)(struct net_device *); void (*get_regs)(struct net_device *, struct ethtool_regs *, void *); @@ -891,13 +1067,27 @@ struct ethtool_ops { int (*get_rxfh)(struct net_device *, struct ethtool_rxfh_param *); int (*set_rxfh)(struct net_device *, struct ethtool_rxfh_param *, struct netlink_ext_ack *extack); + int (*create_rxfh_context)(struct net_device *, + struct ethtool_rxfh_context *ctx, + const struct ethtool_rxfh_param *rxfh, + struct netlink_ext_ack *extack); + int (*modify_rxfh_context)(struct net_device *, + struct ethtool_rxfh_context *ctx, + const struct ethtool_rxfh_param *rxfh, + struct netlink_ext_ack *extack); + int (*remove_rxfh_context)(struct net_device *, + struct ethtool_rxfh_context *ctx, + u32 rss_context, + struct netlink_ext_ack *extack); void (*get_channels)(struct net_device *, struct ethtool_channels *); int (*set_channels)(struct net_device *, struct ethtool_channels *); int (*get_dump_flag)(struct net_device *, struct ethtool_dump *); int (*get_dump_data)(struct net_device *, struct ethtool_dump *, void *); int (*set_dump)(struct net_device *, struct ethtool_dump *); - int (*get_ts_info)(struct net_device *, struct ethtool_ts_info *); + int (*get_ts_info)(struct net_device *, struct kernel_ethtool_ts_info *); + void (*get_ts_stats)(struct net_device *dev, + struct ethtool_ts_stats *ts_stats); int (*get_module_info)(struct net_device *, struct ethtool_modinfo *); int (*get_module_eeprom)(struct net_device *, @@ -931,6 +1121,9 @@ struct ethtool_ops { int (*get_module_eeprom_by_page)(struct net_device *dev, const struct ethtool_module_eeprom *page, struct netlink_ext_ack *extack); + int (*set_module_eeprom_by_page)(struct net_device *dev, + const struct ethtool_module_eeprom *page, + struct netlink_ext_ack *extack); void (*get_eth_phy_stats)(struct net_device *dev, struct ethtool_eth_phy_stats *phy_stats); void (*get_eth_mac_stats)(struct net_device *dev, @@ -973,6 +1166,21 @@ int ethtool_virtdev_set_link_ksettings(struct net_device *dev, const struct ethtool_link_ksettings *cmd, u32 *dev_speed, u8 *dev_duplex); +/** + * struct ethtool_netdev_state - per-netdevice state for ethtool features + * @rss_ctx: XArray of custom RSS contexts + * @rss_lock: Protects entries in @rss_ctx. May be taken from + * within RTNL. + * @wol_enabled: Wake-on-LAN is enabled + * @module_fw_flash_in_progress: Module firmware flashing is in progress. + */ +struct ethtool_netdev_state { + struct xarray rss_ctx; + struct mutex rss_lock; + unsigned wol_enabled:1; + unsigned module_fw_flash_in_progress:1; +}; + struct phy_device; struct phy_tdr_config; struct phy_plca_cfg; @@ -1032,13 +1240,14 @@ ethtool_params_from_link_mode(struct ethtool_link_ksettings *link_ksettings, * @dev: pointer to net_device structure * @vclock_index: pointer to pointer of vclock index * - * Return number of phc vclocks + * Return: number of phc vclocks */ int ethtool_get_phc_vclocks(struct net_device *dev, int **vclock_index); /* Some generic methods drivers may use in their ethtool_ops */ u32 ethtool_op_get_link(struct net_device *dev); -int ethtool_op_get_ts_info(struct net_device *dev, struct ethtool_ts_info *eti); +int ethtool_op_get_ts_info(struct net_device *dev, + struct kernel_ethtool_ts_info *eti); /** * ethtool_mm_frag_size_add_to_min - Translate (standard) additional fragment @@ -1085,9 +1294,10 @@ static inline int ethtool_mm_frag_size_min_to_add(u32 val_min, u32 *val_add, * ethtool_get_ts_info_by_layer - Obtains time stamping capabilities from the MAC or PHY layer. * @dev: pointer to net_device structure * @info: buffer to hold the result - * Returns zero on success, non-zero otherwise. + * Returns: zero on success, non-zero otherwise. */ -int ethtool_get_ts_info_by_layer(struct net_device *dev, struct ethtool_ts_info *info); +int ethtool_get_ts_info_by_layer(struct net_device *dev, + struct kernel_ethtool_ts_info *info); /** * ethtool_sprintf - Write formatted string to ethtool string data diff --git a/include/linux/ethtool_netlink.h b/include/linux/ethtool_netlink.h index fae0dfb9a9c8..aba91335273a 100644 --- a/include/linux/ethtool_netlink.h +++ b/include/linux/ethtool_netlink.h @@ -23,8 +23,10 @@ struct phy_device; int ethnl_cable_test_alloc(struct phy_device *phydev, u8 cmd); void ethnl_cable_test_free(struct phy_device *phydev); void ethnl_cable_test_finished(struct phy_device *phydev); -int ethnl_cable_test_result(struct phy_device *phydev, u8 pair, u8 result); -int ethnl_cable_test_fault_length(struct phy_device *phydev, u8 pair, u32 cm); +int ethnl_cable_test_result_with_src(struct phy_device *phydev, u8 pair, + u8 result, u32 src); +int ethnl_cable_test_fault_length_with_src(struct phy_device *phydev, u8 pair, + u32 cm, u32 src); int ethnl_cable_test_amplitude(struct phy_device *phydev, u8 pair, s16 mV); int ethnl_cable_test_pulse(struct phy_device *phydev, u16 mV); int ethnl_cable_test_step(struct phy_device *phydev, u32 first, u32 last, @@ -54,14 +56,14 @@ static inline void ethnl_cable_test_free(struct phy_device *phydev) static inline void ethnl_cable_test_finished(struct phy_device *phydev) { } -static inline int ethnl_cable_test_result(struct phy_device *phydev, u8 pair, - u8 result) +static inline int ethnl_cable_test_result_with_src(struct phy_device *phydev, + u8 pair, u8 result, u32 src) { return -EOPNOTSUPP; } -static inline int ethnl_cable_test_fault_length(struct phy_device *phydev, - u8 pair, u32 cm) +static inline int ethnl_cable_test_fault_length_with_src(struct phy_device *phydev, + u8 pair, u32 cm, u32 src) { return -EOPNOTSUPP; } @@ -119,4 +121,19 @@ static inline bool ethtool_dev_mm_supported(struct net_device *dev) } #endif /* IS_ENABLED(CONFIG_ETHTOOL_NETLINK) */ + +static inline int ethnl_cable_test_result(struct phy_device *phydev, u8 pair, + u8 result) +{ + return ethnl_cable_test_result_with_src(phydev, pair, result, + ETHTOOL_A_CABLE_INF_SRC_TDR); +} + +static inline int ethnl_cable_test_fault_length(struct phy_device *phydev, + u8 pair, u32 cm) +{ + return ethnl_cable_test_fault_length_with_src(phydev, pair, cm, + ETHTOOL_A_CABLE_INF_SRC_TDR); +} + #endif /* _LINUX_ETHTOOL_NETLINK_H_ */ diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h index 3337745d81bd..0c0d00fcd131 100644 --- a/include/linux/eventpoll.h +++ b/include/linux/eventpoll.h @@ -42,7 +42,7 @@ static inline void eventpoll_release(struct file *file) * because the file in on the way to be removed and nobody ( but * eventpoll ) has still a reference to this file. */ - if (likely(!file->f_ep)) + if (likely(!READ_ONCE(file->f_ep))) return; /* diff --git a/include/linux/evm.h b/include/linux/evm.h index d48d6da32315..ddece4a6b25d 100644 --- a/include/linux/evm.h +++ b/include/linux/evm.h @@ -26,6 +26,8 @@ extern int evm_protected_xattr_if_enabled(const char *req_xattr_name); extern int evm_read_protected_xattrs(struct dentry *dentry, u8 *buffer, int buffer_size, char type, bool canonical_fmt); +extern bool evm_metadata_changed(struct inode *inode, + struct inode *metadata_inode); #ifdef CONFIG_FS_POSIX_ACL extern int posix_xattr_acl(const char *xattrname); #else @@ -76,5 +78,11 @@ static inline int evm_read_protected_xattrs(struct dentry *dentry, u8 *buffer, return -EOPNOTSUPP; } +static inline bool evm_metadata_changed(struct inode *inode, + struct inode *metadata_inode) +{ + return false; +} + #endif /* CONFIG_EVM */ #endif /* LINUX_EVM_H */ diff --git a/include/linux/execmem.h b/include/linux/execmem.h new file mode 100644 index 000000000000..64130ae19690 --- /dev/null +++ b/include/linux/execmem.h @@ -0,0 +1,181 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_EXECMEM_ALLOC_H +#define _LINUX_EXECMEM_ALLOC_H + +#include <linux/types.h> +#include <linux/moduleloader.h> + +#if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \ + !defined(CONFIG_KASAN_VMALLOC) +#include <linux/kasan.h> +#define MODULE_ALIGN (PAGE_SIZE << KASAN_SHADOW_SCALE_SHIFT) +#else +#define MODULE_ALIGN PAGE_SIZE +#endif + +/** + * enum execmem_type - types of executable memory ranges + * + * There are several subsystems that allocate executable memory. + * Architectures define different restrictions on placement, + * permissions, alignment and other parameters for memory that can be used + * by these subsystems. + * Types in this enum identify subsystems that allocate executable memory + * and let architectures define parameters for ranges suitable for + * allocations by each subsystem. + * + * @EXECMEM_DEFAULT: default parameters that would be used for types that + * are not explicitly defined. + * @EXECMEM_MODULE_TEXT: parameters for module text sections + * @EXECMEM_KPROBES: parameters for kprobes + * @EXECMEM_FTRACE: parameters for ftrace + * @EXECMEM_BPF: parameters for BPF + * @EXECMEM_MODULE_DATA: parameters for module data sections + * @EXECMEM_TYPE_MAX: + */ +enum execmem_type { + EXECMEM_DEFAULT, + EXECMEM_MODULE_TEXT = EXECMEM_DEFAULT, + EXECMEM_KPROBES, + EXECMEM_FTRACE, + EXECMEM_BPF, + EXECMEM_MODULE_DATA, + EXECMEM_TYPE_MAX, +}; + +/** + * enum execmem_range_flags - options for executable memory allocations + * @EXECMEM_KASAN_SHADOW: allocate kasan shadow + * @EXECMEM_ROX_CACHE: allocations should use ROX cache of huge pages + */ +enum execmem_range_flags { + EXECMEM_KASAN_SHADOW = (1 << 0), + EXECMEM_ROX_CACHE = (1 << 1), +}; + +#ifdef CONFIG_ARCH_HAS_EXECMEM_ROX +/** + * execmem_fill_trapping_insns - set memory to contain instructions that + * will trap + * @ptr: pointer to memory to fill + * @size: size of the range to fill + * @writable: is the memory poited by @ptr is writable or ROX + * + * A hook for architecures to fill execmem ranges with invalid instructions. + * Architectures that use EXECMEM_ROX_CACHE must implement this. + */ +void execmem_fill_trapping_insns(void *ptr, size_t size, bool writable); +#endif + +/** + * struct execmem_range - definition of an address space suitable for code and + * related data allocations + * @start: address space start + * @end: address space end (inclusive) + * @fallback_start: start of the secondary address space range for fallback + * allocations on architectures that require it + * @fallback_end: start of the secondary address space (inclusive) + * @pgprot: permissions for memory in this address space + * @alignment: alignment required for text allocations + * @flags: options for memory allocations for this range + */ +struct execmem_range { + unsigned long start; + unsigned long end; + unsigned long fallback_start; + unsigned long fallback_end; + pgprot_t pgprot; + unsigned int alignment; + enum execmem_range_flags flags; +}; + +/** + * struct execmem_info - architecture parameters for code allocations + * @ranges: array of parameter sets defining architecture specific + * parameters for executable memory allocations. The ranges that are not + * explicitly initialized by an architecture use parameters defined for + * @EXECMEM_DEFAULT. + */ +struct execmem_info { + struct execmem_range ranges[EXECMEM_TYPE_MAX]; +}; + +/** + * execmem_arch_setup - define parameters for allocations of executable memory + * + * A hook for architectures to define parameters for allocations of + * executable memory. These parameters should be filled into the + * @execmem_info structure. + * + * For architectures that do not implement this method a default set of + * parameters will be used + * + * Return: a structure defining architecture parameters and restrictions + * for allocations of executable memory + */ +struct execmem_info *execmem_arch_setup(void); + +/** + * execmem_alloc - allocate executable memory + * @type: type of the allocation + * @size: how many bytes of memory are required + * + * Allocates memory that will contain executable code, either generated or + * loaded from kernel modules. + * + * Allocates memory that will contain data coupled with executable code, + * like data sections in kernel modules. + * + * The memory will have protections defined by architecture for executable + * region of the @type. + * + * Return: a pointer to the allocated memory or %NULL + */ +void *execmem_alloc(enum execmem_type type, size_t size); + +/** + * execmem_free - free executable memory + * @ptr: pointer to the memory that should be freed + */ +void execmem_free(void *ptr); + +#ifdef CONFIG_MMU +/** + * execmem_vmap - create virtual mapping for EXECMEM_MODULE_DATA memory + * @size: size of the virtual mapping in bytes + * + * Maps virtually contiguous area in the range suitable for EXECMEM_MODULE_DATA. + * + * Return: the area descriptor on success or %NULL on failure. + */ +struct vm_struct *execmem_vmap(size_t size); +#endif + +/** + * execmem_update_copy - copy an update to executable memory + * @dst: destination address to update + * @src: source address containing the data + * @size: how many bytes of memory shold be copied + * + * Copy @size bytes from @src to @dst using text poking if the memory at + * @dst is read-only. + * + * Return: a pointer to @dst or NULL on error + */ +void *execmem_update_copy(void *dst, const void *src, size_t size); + +/** + * execmem_is_rox - check if execmem is read-only + * @type - the execmem type to check + * + * Return: %true if the @type is read-only, %false if it's writable + */ +bool execmem_is_rox(enum execmem_type type); + +#if defined(CONFIG_EXECMEM) && !defined(CONFIG_ARCH_WANTS_EXECMEM_LATE) +void execmem_init(void); +#else +static inline void execmem_init(void) {} +#endif + +#endif /* _LINUX_EXECMEM_ALLOC_H */ diff --git a/include/linux/export.h b/include/linux/export.h index 0bbd02fd351d..a8c23d945634 100644 --- a/include/linux/export.h +++ b/include/linux/export.h @@ -52,22 +52,37 @@ #else +#ifdef CONFIG_GENDWARFKSYMS +/* + * With CONFIG_GENDWARFKSYMS, ensure the compiler emits debugging + * information for all exported symbols, including those defined in + * different TUs, by adding a __gendwarfksyms_ptr_<symbol> pointer + * that's discarded during the final link. + */ +#define __GENDWARFKSYMS_EXPORT(sym) \ + static typeof(sym) *__gendwarfksyms_ptr_##sym __used \ + __section(".discard.gendwarfksyms") = &sym; +#else +#define __GENDWARFKSYMS_EXPORT(sym) +#endif + #define __EXPORT_SYMBOL(sym, license, ns) \ extern typeof(sym) sym; \ __ADDRESSABLE(sym) \ + __GENDWARFKSYMS_EXPORT(sym) \ asm(__stringify(___EXPORT_SYMBOL(sym, license, ns))) #endif #ifdef DEFAULT_SYMBOL_NAMESPACE -#define _EXPORT_SYMBOL(sym, license) __EXPORT_SYMBOL(sym, license, __stringify(DEFAULT_SYMBOL_NAMESPACE)) +#define _EXPORT_SYMBOL(sym, license) __EXPORT_SYMBOL(sym, license, DEFAULT_SYMBOL_NAMESPACE) #else #define _EXPORT_SYMBOL(sym, license) __EXPORT_SYMBOL(sym, license, "") #endif #define EXPORT_SYMBOL(sym) _EXPORT_SYMBOL(sym, "") #define EXPORT_SYMBOL_GPL(sym) _EXPORT_SYMBOL(sym, "GPL") -#define EXPORT_SYMBOL_NS(sym, ns) __EXPORT_SYMBOL(sym, "", __stringify(ns)) -#define EXPORT_SYMBOL_NS_GPL(sym, ns) __EXPORT_SYMBOL(sym, "GPL", __stringify(ns)) +#define EXPORT_SYMBOL_NS(sym, ns) __EXPORT_SYMBOL(sym, "", ns) +#define EXPORT_SYMBOL_NS_GPL(sym, ns) __EXPORT_SYMBOL(sym, "GPL", ns) #endif /* _LINUX_EXPORT_H */ diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h index bb37ad5cc954..a087606ace19 100644 --- a/include/linux/exportfs.h +++ b/include/linux/exportfs.h @@ -3,6 +3,7 @@ #define LINUX_EXPORTFS_H 1 #include <linux/types.h> +#include <linux/path.h> struct dentry; struct iattr; @@ -156,8 +157,33 @@ struct fid { }; }; +enum handle_to_path_flags { + HANDLE_CHECK_PERMS = (1 << 0), + HANDLE_CHECK_SUBTREE = (1 << 1), +}; + +struct handle_to_path_ctx { + struct path root; + enum handle_to_path_flags flags; + unsigned int fh_flags; +}; + #define EXPORT_FH_CONNECTABLE 0x1 /* Encode file handle with parent */ #define EXPORT_FH_FID 0x2 /* File handle may be non-decodeable */ +#define EXPORT_FH_DIR_ONLY 0x4 /* Only decode file handle for a directory */ + +/* + * Filesystems use only lower 8 bits of file_handle type for fid_type. + * name_to_handle_at() uses upper 16 bits of type as user flags to be + * interpreted by open_by_handle_at(). + */ +#define FILEID_USER_FLAGS_MASK 0xffff0000 +#define FILEID_USER_FLAGS(type) ((type) & FILEID_USER_FLAGS_MASK) + +/* Flags supported in encoded handle_type that is exported to user */ +#define FILEID_IS_CONNECTABLE 0x10000 +#define FILEID_IS_DIR 0x20000 +#define FILEID_VALID_USER_FLAGS (FILEID_IS_CONNECTABLE | FILEID_IS_DIR) /** * struct export_operations - for nfsd to communicate with file systems @@ -211,6 +237,12 @@ struct fid { * is also a directory. In the event that it cannot be found, or storage * space cannot be allocated, a %ERR_PTR should be returned. * + * permission: + * Allow filesystems to specify a custom permission function. + * + * open: + * Allow filesystems to specify a custom open function. + * * commit_metadata: * @commit_metadata should commit metadata changes to stable storage. * @@ -237,6 +269,8 @@ struct export_operations { bool write, u32 *device_generation); int (*commit_blocks)(struct inode *inode, struct iomap *iomaps, int nr_iomaps, struct iattr *iattr); + int (*permission)(struct handle_to_path_ctx *ctx, unsigned int oflags); + struct file * (*open)(struct path *path, unsigned int oflags); #define EXPORT_OP_NOWCC (0x1) /* don't collect v3 wcc data */ #define EXPORT_OP_NOSUBTREECHK (0x2) /* no subtree checking */ #define EXPORT_OP_CLOSE_BEFORE_UNLINK (0x4) /* close files before unlink */ @@ -249,19 +283,6 @@ struct export_operations { unsigned long flags; }; -/** - * exportfs_lock_op_is_async() - export op supports async lock operation - * @export_ops: the nfs export operations to check - * - * Returns true if the nfs export_operations structure has - * EXPORT_OP_ASYNC_LOCK in their flags set - */ -static inline bool -exportfs_lock_op_is_async(const struct export_operations *export_ops) -{ - return export_ops->flags & EXPORT_OP_ASYNC_LOCK; -} - extern int exportfs_encode_inode_fh(struct inode *inode, struct fid *fid, int *max_len, struct inode *parent, int flags); @@ -305,6 +326,7 @@ static inline int exportfs_encode_fid(struct inode *inode, struct fid *fid, extern struct dentry *exportfs_decode_fh_raw(struct vfsmount *mnt, struct fid *fid, int fh_len, int fileid_type, + unsigned int flags, int (*acceptable)(void *, struct dentry *), void *context); extern struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid, diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index a357287eac1e..c24f8bc01045 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -19,15 +19,16 @@ #define F2FS_BLKSIZE_BITS PAGE_SHIFT /* bits for F2FS_BLKSIZE */ #define F2FS_MAX_EXTENSION 64 /* # of extension entries */ #define F2FS_EXTENSION_LEN 8 /* max size of extension */ -#define F2FS_BLK_ALIGN(x) (((x) + F2FS_BLKSIZE - 1) >> F2FS_BLKSIZE_BITS) #define NULL_ADDR ((block_t)0) /* used as block_t addresses */ #define NEW_ADDR ((block_t)-1) /* used as block_t addresses */ #define COMPRESS_ADDR ((block_t)-2) /* used as compressed data flag */ -#define F2FS_BYTES_TO_BLK(bytes) ((bytes) >> F2FS_BLKSIZE_BITS) -#define F2FS_BLK_TO_BYTES(blk) ((blk) << F2FS_BLKSIZE_BITS) +#define F2FS_BLKSIZE_MASK (F2FS_BLKSIZE - 1) +#define F2FS_BYTES_TO_BLK(bytes) ((unsigned long long)(bytes) >> F2FS_BLKSIZE_BITS) +#define F2FS_BLK_TO_BYTES(blk) ((unsigned long long)(blk) << F2FS_BLKSIZE_BITS) #define F2FS_BLK_END_BYTES(blk) (F2FS_BLK_TO_BYTES(blk + 1) - 1) +#define F2FS_BLK_ALIGN(x) (F2FS_BYTES_TO_BLK((x) + F2FS_BLKSIZE - 1)) /* 0, 1(node nid), 2(meta nid) are reserved node id */ #define F2FS_RESERVED_NODE_NUM 3 @@ -259,15 +260,14 @@ struct node_footer { #define CUR_ADDRS_PER_INODE(inode) (DEF_ADDRS_PER_INODE - \ get_extra_isize(inode)) #define DEF_NIDS_PER_INODE 5 /* Node IDs in an Inode */ -#define ADDRS_PER_INODE(inode) addrs_per_inode(inode) +#define ADDRS_PER_INODE(inode) addrs_per_page(inode, true) /* Address Pointers in a Direct Block */ #define DEF_ADDRS_PER_BLOCK ((F2FS_BLKSIZE - sizeof(struct node_footer)) / sizeof(__le32)) -#define ADDRS_PER_BLOCK(inode) addrs_per_block(inode) +#define ADDRS_PER_BLOCK(inode) addrs_per_page(inode, false) /* Node IDs in an Indirect Block */ #define NIDS_PER_BLOCK ((F2FS_BLKSIZE - sizeof(struct node_footer)) / sizeof(__le32)) -#define ADDRS_PER_PAGE(page, inode) \ - (IS_INODE(page) ? ADDRS_PER_INODE(inode) : ADDRS_PER_BLOCK(inode)) +#define ADDRS_PER_PAGE(page, inode) (addrs_per_page(inode, IS_INODE(page))) #define NODE_DIR1_BLOCK (DEF_ADDRS_PER_INODE + 1) #define NODE_DIR2_BLOCK (DEF_ADDRS_PER_INODE + 2) @@ -279,7 +279,7 @@ struct node_footer { #define F2FS_INLINE_DATA 0x02 /* file inline data flag */ #define F2FS_INLINE_DENTRY 0x04 /* file inline dentry flag */ #define F2FS_DATA_EXIST 0x08 /* file inline data exist flag */ -#define F2FS_INLINE_DOTS 0x10 /* file having implicit dot dentries */ +#define F2FS_INLINE_DOTS 0x10 /* file having implicit dot dentries (obsolete) */ #define F2FS_EXTRA_ATTR 0x20 /* file having extra attribute */ #define F2FS_PIN_FILE 0x40 /* file should not be gced */ #define F2FS_COMPRESS_RELEASED 0x80 /* file released compressed blocks */ @@ -394,7 +394,8 @@ struct f2fs_nat_block { /* * F2FS uses 4 bytes to represent block address. As a result, supported size of - * disk is 16 TB and it equals to 16 * 1024 * 1024 / 2 segments. + * disk is 16 TB for a 4K page size and 64 TB for a 16K page size and it equals + * to 16 * 1024 * 1024 / 2 segments. */ #define F2FS_MAX_SEGMENT ((16 * 1024 * 1024) / 2) @@ -424,8 +425,10 @@ struct f2fs_sit_block { /* * For segment summary * - * One summary block contains exactly 512 summary entries, which represents - * exactly one segment by default. Not allow to change the basic units. + * One summary block with 4KB size contains exactly 512 summary entries, which + * represents exactly one segment with 2MB size. + * Similarly, in the case of block with 16KB size, it represents one segment with 8MB size. + * Not allow to change the basic units. * * NOTE: For initializing fields, you must use set_summary * @@ -556,6 +559,7 @@ typedef __le32 f2fs_hash_t; /* * space utilization of regular dentry and inline dentry (w/o extra reservation) + * when block size is 4KB. * regular dentry inline dentry (def) inline dentry (min) * bitmap 1 * 27 = 27 1 * 23 = 23 1 * 1 = 1 * reserved 1 * 3 = 3 1 * 7 = 7 1 * 1 = 1 diff --git a/include/linux/falloc.h b/include/linux/falloc.h index f3f0b97b1675..3f49f3df6af5 100644 --- a/include/linux/falloc.h +++ b/include/linux/falloc.h @@ -25,12 +25,18 @@ struct space_resv { #define FS_IOC_UNRESVSP64 _IOW('X', 43, struct space_resv) #define FS_IOC_ZERO_RANGE _IOW('X', 57, struct space_resv) -#define FALLOC_FL_SUPPORTED_MASK (FALLOC_FL_KEEP_SIZE | \ - FALLOC_FL_PUNCH_HOLE | \ - FALLOC_FL_COLLAPSE_RANGE | \ - FALLOC_FL_ZERO_RANGE | \ - FALLOC_FL_INSERT_RANGE | \ - FALLOC_FL_UNSHARE_RANGE) +/* + * Mask of all supported fallocate modes. Only one can be set at a time. + * + * In addition to the mode bit, the mode argument can also encode flags. + * FALLOC_FL_KEEP_SIZE is the only supported flag so far. + */ +#define FALLOC_FL_MODE_MASK (FALLOC_FL_ALLOCATE_RANGE | \ + FALLOC_FL_PUNCH_HOLE | \ + FALLOC_FL_COLLAPSE_RANGE | \ + FALLOC_FL_ZERO_RANGE | \ + FALLOC_FL_INSERT_RANGE | \ + FALLOC_FL_UNSHARE_RANGE) /* on ia32 l_start is on a 32-bit boundary */ #if defined(CONFIG_X86_64) diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 4f1c4f603118..78f660ebc318 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -36,6 +36,7 @@ #define FANOTIFY_ADMIN_INIT_FLAGS (FANOTIFY_PERM_CLASSES | \ FAN_REPORT_TID | \ FAN_REPORT_PIDFD | \ + FAN_REPORT_FD_ERROR | \ FAN_UNLIMITED_QUEUE | \ FAN_UNLIMITED_MARKS) @@ -88,6 +89,16 @@ #define FANOTIFY_DIRENT_EVENTS (FAN_MOVE | FAN_CREATE | FAN_DELETE | \ FAN_RENAME) +/* Content events can be used to inspect file content */ +#define FANOTIFY_CONTENT_PERM_EVENTS (FAN_OPEN_PERM | FAN_OPEN_EXEC_PERM | \ + FAN_ACCESS_PERM) +/* Pre-content events can be used to fill file content */ +#define FANOTIFY_PRE_CONTENT_EVENTS (FAN_PRE_ACCESS) + +/* Events that require a permission response from user */ +#define FANOTIFY_PERM_EVENTS (FANOTIFY_CONTENT_PERM_EVENTS | \ + FANOTIFY_PRE_CONTENT_EVENTS) + /* Events that can be reported with event->fd */ #define FANOTIFY_FD_EVENTS (FANOTIFY_PATH_EVENTS | FANOTIFY_PERM_EVENTS) @@ -103,10 +114,6 @@ FANOTIFY_INODE_EVENTS | \ FANOTIFY_ERROR_EVENTS) -/* Events that require a permission response from user */ -#define FANOTIFY_PERM_EVENTS (FAN_OPEN_PERM | FAN_ACCESS_PERM | \ - FAN_OPEN_EXEC_PERM) - /* Extra flags that may be reported with event or control handling of events */ #define FANOTIFY_EVENT_FLAGS (FAN_EVENT_ON_CHILD | FAN_ONDIR) @@ -125,7 +132,9 @@ /* These masks check for invalid bits in permission responses. */ #define FANOTIFY_RESPONSE_ACCESS (FAN_ALLOW | FAN_DENY) #define FANOTIFY_RESPONSE_FLAGS (FAN_AUDIT | FAN_INFO) -#define FANOTIFY_RESPONSE_VALID_MASK (FANOTIFY_RESPONSE_ACCESS | FANOTIFY_RESPONSE_FLAGS) +#define FANOTIFY_RESPONSE_VALID_MASK \ + (FANOTIFY_RESPONSE_ACCESS | FANOTIFY_RESPONSE_FLAGS | \ + (FAN_ERRNO_MASK << FAN_ERRNO_SHIFT)) /* Do not use these old uapi constants internally */ #undef FAN_ALL_CLASS_BITS diff --git a/include/linux/fault-inject.h b/include/linux/fault-inject.h index 6d5edef09d45..8c829d28dcf3 100644 --- a/include/linux/fault-inject.h +++ b/include/linux/fault-inject.h @@ -2,13 +2,17 @@ #ifndef _LINUX_FAULT_INJECT_H #define _LINUX_FAULT_INJECT_H +#include <linux/err.h> +#include <linux/types.h> + +struct dentry; +struct kmem_cache; + #ifdef CONFIG_FAULT_INJECTION -#include <linux/types.h> -#include <linux/debugfs.h> +#include <linux/atomic.h> #include <linux/configfs.h> #include <linux/ratelimit.h> -#include <linux/atomic.h> /* * For explanation of the elements of this struct, see @@ -51,6 +55,28 @@ int setup_fault_attr(struct fault_attr *attr, char *str); bool should_fail_ex(struct fault_attr *attr, ssize_t size, int flags); bool should_fail(struct fault_attr *attr, ssize_t size); +#else /* CONFIG_FAULT_INJECTION */ + +struct fault_attr { +}; + +#define DECLARE_FAULT_ATTR(name) struct fault_attr name = {} + +static inline int setup_fault_attr(struct fault_attr *attr, char *str) +{ + return 0; /* Note: 0 means error for __setup() handlers! */ +} +static inline bool should_fail_ex(struct fault_attr *attr, ssize_t size, int flags) +{ + return false; +} +static inline bool should_fail(struct fault_attr *attr, ssize_t size) +{ + return false; +} + +#endif /* CONFIG_FAULT_INJECTION */ + #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS struct dentry *fault_create_debugfs_attr(const char *name, @@ -87,26 +113,19 @@ static inline void fault_config_init(struct fault_config *config, #endif /* CONFIG_FAULT_INJECTION_CONFIGFS */ -#endif /* CONFIG_FAULT_INJECTION */ - -struct kmem_cache; - -bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order); - #ifdef CONFIG_FAIL_PAGE_ALLOC -bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order); +bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order); #else -static inline bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) +static inline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) { return false; } #endif /* CONFIG_FAIL_PAGE_ALLOC */ -int should_failslab(struct kmem_cache *s, gfp_t gfpflags); #ifdef CONFIG_FAILSLAB -extern bool __should_failslab(struct kmem_cache *s, gfp_t gfpflags); +int should_failslab(struct kmem_cache *s, gfp_t gfpflags); #else -static inline bool __should_failslab(struct kmem_cache *s, gfp_t gfpflags) +static inline int should_failslab(struct kmem_cache *s, gfp_t gfpflags) { return false; } diff --git a/include/linux/fb.h b/include/linux/fb.h index 811e47f9d1c3..5ba187e08cf7 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -12,7 +12,7 @@ #include <linux/types.h> #include <linux/workqueue.h> -#include <asm/fb.h> +#include <asm/video.h> struct backlight_device; struct device; @@ -21,6 +21,7 @@ struct fb_info; struct file; struct i2c_adapter; struct inode; +struct lcd_device; struct module; struct notifier_block; struct page; @@ -225,6 +226,7 @@ struct fb_deferred_io { struct mutex lock; /* mutex that protects the pageref list */ struct list_head pagereflist; /* list of pagerefs for touched pages */ /* callback */ + struct page *(*get_page)(struct fb_info *info, unsigned long offset); void (*deferred_io)(struct fb_info *info, struct list_head *pagelist); }; #endif @@ -479,6 +481,13 @@ struct fb_info { struct mutex bl_curve_mutex; u8 bl_curve[FB_BACKLIGHT_LEVELS]; #endif + + /* + * Assigned LCD device; set before framebuffer + * registration, remove after unregister + */ + struct lcd_device *lcd_dev; + #ifdef CONFIG_FB_DEFERRED_IO struct delayed_work deferred_work; unsigned long npagerefs; @@ -509,6 +518,7 @@ struct fb_info { void *par; bool skip_vt_switch; /* no VT switch on suspend/resume required */ + bool skip_panic; /* Do not write to the fb after a panic */ }; /* This will go away @@ -600,6 +610,7 @@ extern ssize_t fb_sys_write(struct fb_info *info, const char __user *buf, /* fbmem.c */ extern int register_framebuffer(struct fb_info *fb_info); extern void unregister_framebuffer(struct fb_info *fb_info); +extern int devm_register_framebuffer(struct device *dev, struct fb_info *fb_info); extern char* fb_get_buffer_offset(struct fb_info *info, struct fb_pixmap *buf, u32 size); extern void fb_pad_unaligned_buffer(u8 *dst, u32 d_pitch, u8 *src, u32 idx, u32 height, u32 shift_high, u32 shift_low, u32 mod); @@ -742,6 +753,20 @@ extern struct fb_info *framebuffer_alloc(size_t size, struct device *dev); extern void framebuffer_release(struct fb_info *info); extern void fb_bl_default_curve(struct fb_info *fb_info, u8 off, u8 min, u8 max); +#if IS_ENABLED(CONFIG_FB_BACKLIGHT) +struct backlight_device *fb_bl_device(struct fb_info *info); +#else +static inline struct backlight_device *fb_bl_device(struct fb_info *info) +{ + return NULL; +} +#endif + +static inline struct lcd_device *fb_lcd_device(struct fb_info *info) +{ + return info->lcd_dev; +} + /* fbmon.c */ #define FB_MAXTIMINGS 0 #define FB_VSYNCTIMINGS 1 diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h index 78c8326d74ae..c45306a9f007 100644 --- a/include/linux/fdtable.h +++ b/include/linux/fdtable.h @@ -22,7 +22,6 @@ * as this is the granularity returned by copy_fdset(). */ #define NR_OPEN_DEFAULT BITS_PER_LONG -#define NR_OPEN_MAX ~0U struct fdtable { unsigned int max_fds; @@ -33,16 +32,6 @@ struct fdtable { struct rcu_head rcu; }; -static inline bool close_on_exec(unsigned int fd, const struct fdtable *fdt) -{ - return test_bit(fd, fdt->close_on_exec); -} - -static inline bool fd_is_open(unsigned int fd, const struct fdtable *fdt) -{ - return test_bit(fd, fdt->open_fds); -} - /* * Open file table structure */ @@ -103,25 +92,26 @@ static inline struct file *files_lookup_fd_locked(struct files_struct *files, un return files_lookup_fd_raw(files, fd); } -struct file *lookup_fdget_rcu(unsigned int fd); -struct file *task_lookup_fdget_rcu(struct task_struct *task, unsigned int fd); -struct file *task_lookup_next_fdget_rcu(struct task_struct *task, unsigned int *fd); +static inline bool close_on_exec(unsigned int fd, const struct files_struct *files) +{ + return test_bit(fd, files_fdtable(files)->close_on_exec); +} struct task_struct; void put_files_struct(struct files_struct *fs); int unshare_files(void); -struct files_struct *dup_fd(struct files_struct *, unsigned, int *) __latent_entropy; +struct fd_range { + unsigned int from, to; +}; +struct files_struct *dup_fd(struct files_struct *, struct fd_range *) __latent_entropy; void do_close_on_exec(struct files_struct *); int iterate_fd(struct files_struct *, unsigned, int (*)(const void *, struct file *, unsigned), const void *); extern int close_fd(unsigned int fd); -extern int __close_range(unsigned int fd, unsigned int max_fd, unsigned int flags); extern struct file *file_close_fd(unsigned int fd); -extern int unshare_fd(unsigned long unshare_flags, unsigned int max_fds, - struct files_struct **new_fdp); extern struct kmem_cache *files_cachep; diff --git a/include/linux/fiemap.h b/include/linux/fiemap.h index c50882f19235..966092ffa89a 100644 --- a/include/linux/fiemap.h +++ b/include/linux/fiemap.h @@ -5,12 +5,18 @@ #include <uapi/linux/fiemap.h> #include <linux/fs.h> +/** + * struct fiemap_extent_info - fiemap request to a filesystem + * @fi_flags: Flags as passed from user + * @fi_extents_mapped: Number of mapped extents + * @fi_extents_max: Size of fiemap_extent array + * @fi_extents_start: Start of fiemap_extent array + */ struct fiemap_extent_info { - unsigned int fi_flags; /* Flags as passed from user */ - unsigned int fi_extents_mapped; /* Number of mapped extents */ - unsigned int fi_extents_max; /* Size of fiemap_extent array */ - struct fiemap_extent __user *fi_extents_start; /* Start of - fiemap_extent array */ + unsigned int fi_flags; + unsigned int fi_extents_mapped; + unsigned int fi_extents_max; + struct fiemap_extent __user *fi_extents_start; }; int fiemap_prep(struct inode *inode, struct fiemap_extent_info *fieinfo, diff --git a/include/linux/file.h b/include/linux/file.h index 169692cb1906..302f11355b10 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -11,6 +11,7 @@ #include <linux/posix_types.h> #include <linux/errno.h> #include <linux/cleanup.h> +#include <linux/err.h> struct file; @@ -29,61 +30,59 @@ extern struct file *alloc_file_pseudo_noaccount(struct inode *, struct vfsmount extern struct file *alloc_file_clone(struct file *, int flags, const struct file_operations *); -static inline void fput_light(struct file *file, int fput_needed) -{ - if (fput_needed) - fput(file); -} - +/* either a reference to struct file + flags + * (cloned vs. borrowed, pos locked), with + * flags stored in lower bits of value, + * or empty (represented by 0). + */ struct fd { - struct file *file; - unsigned int flags; + unsigned long word; }; #define FDPUT_FPUT 1 #define FDPUT_POS_UNLOCK 2 -static inline void fdput(struct fd fd) +#define fd_file(f) ((struct file *)((f).word & ~(FDPUT_FPUT|FDPUT_POS_UNLOCK))) +static inline bool fd_empty(struct fd f) { - if (fd.flags & FDPUT_FPUT) - fput(fd.file); + return unlikely(!f.word); } -extern struct file *fget(unsigned int fd); -extern struct file *fget_raw(unsigned int fd); -extern struct file *fget_task(struct task_struct *task, unsigned int fd); -extern unsigned long __fdget(unsigned int fd); -extern unsigned long __fdget_raw(unsigned int fd); -extern unsigned long __fdget_pos(unsigned int fd); -extern void __f_unlock_pos(struct file *); - -static inline struct fd __to_fd(unsigned long v) +#define EMPTY_FD (struct fd){0} +static inline struct fd BORROWED_FD(struct file *f) { - return (struct fd){(struct file *)(v & ~3),v & 3}; + return (struct fd){(unsigned long)f}; } - -static inline struct fd fdget(unsigned int fd) +static inline struct fd CLONED_FD(struct file *f) { - return __to_fd(__fdget(fd)); + return (struct fd){(unsigned long)f | FDPUT_FPUT}; } -static inline struct fd fdget_raw(unsigned int fd) +static inline void fdput(struct fd fd) { - return __to_fd(__fdget_raw(fd)); + if (fd.word & FDPUT_FPUT) + fput(fd_file(fd)); } -static inline struct fd fdget_pos(int fd) -{ - return __to_fd(__fdget_pos(fd)); -} +extern struct file *fget(unsigned int fd); +extern struct file *fget_raw(unsigned int fd); +extern struct file *fget_task(struct task_struct *task, unsigned int fd); +extern struct file *fget_task_next(struct task_struct *task, unsigned int *fd); +extern void __f_unlock_pos(struct file *); + +struct fd fdget(unsigned int fd); +struct fd fdget_raw(unsigned int fd); +struct fd fdget_pos(unsigned int fd); static inline void fdput_pos(struct fd f) { - if (f.flags & FDPUT_POS_UNLOCK) - __f_unlock_pos(f.file); + if (f.word & FDPUT_POS_UNLOCK) + __f_unlock_pos(fd_file(f)); fdput(f); } DEFINE_CLASS(fd, struct fd, fdput(_T), fdget(fd), int fd) +DEFINE_CLASS(fd_raw, struct fd, fdput(_T), fdget_raw(fd), int fd) +DEFINE_CLASS(fd_pos, struct fd, fdput_pos(_T), fdget_pos(fd), int fd) extern int f_dupfd(unsigned int from, struct file *file, unsigned flags); extern int replace_fd(unsigned fd, struct file *file, unsigned flags); @@ -95,6 +94,27 @@ extern void put_unused_fd(unsigned int fd); DEFINE_CLASS(get_unused_fd, int, if (_T >= 0) put_unused_fd(_T), get_unused_fd_flags(flags), unsigned flags) +DEFINE_FREE(fput, struct file *, if (!IS_ERR_OR_NULL(_T)) fput(_T)) + +/* + * take_fd() will take care to set @fd to -EBADF ensuring that + * CLASS(get_unused_fd) won't call put_unused_fd(). This makes it + * easier to rely on CLASS(get_unused_fd): + * + * struct file *f; + * + * CLASS(get_unused_fd, fd)(O_CLOEXEC); + * if (fd < 0) + * return fd; + * + * f = dentry_open(&path, O_RDONLY, current_cred()); + * if (IS_ERR(f)) + * return PTR_ERR(f); + * + * fd_install(fd, f); + * return take_fd(fd); + */ +#define take_fd(fd) __get_and_null(fd, -EBADF) extern void fd_install(unsigned int fd, struct file *file); diff --git a/include/linux/file_ref.h b/include/linux/file_ref.h new file mode 100644 index 000000000000..9b3a8d9b17ab --- /dev/null +++ b/include/linux/file_ref.h @@ -0,0 +1,177 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _LINUX_FILE_REF_H +#define _LINUX_FILE_REF_H + +#include <linux/atomic.h> +#include <linux/preempt.h> +#include <linux/types.h> + +/* + * file_ref is a reference count implementation specifically for use by + * files. It takes inspiration from rcuref but differs in key aspects + * such as support for SLAB_TYPESAFE_BY_RCU type caches. + * + * FILE_REF_ONEREF FILE_REF_MAXREF + * 0x0000000000000000UL 0x7FFFFFFFFFFFFFFFUL + * <-------------------valid -------------------> + * + * FILE_REF_SATURATED + * 0x8000000000000000UL 0xA000000000000000UL 0xBFFFFFFFFFFFFFFFUL + * <-----------------------saturation zone----------------------> + * + * FILE_REF_RELEASED FILE_REF_DEAD + * 0xC000000000000000UL 0xE000000000000000UL + * <-------------------dead zone-------------------> + * + * FILE_REF_NOREF + * 0xFFFFFFFFFFFFFFFFUL + */ + +#ifdef CONFIG_64BIT +#define FILE_REF_ONEREF 0x0000000000000000UL +#define FILE_REF_MAXREF 0x7FFFFFFFFFFFFFFFUL +#define FILE_REF_SATURATED 0xA000000000000000UL +#define FILE_REF_RELEASED 0xC000000000000000UL +#define FILE_REF_DEAD 0xE000000000000000UL +#define FILE_REF_NOREF 0xFFFFFFFFFFFFFFFFUL +#else +#define FILE_REF_ONEREF 0x00000000U +#define FILE_REF_MAXREF 0x7FFFFFFFU +#define FILE_REF_SATURATED 0xA0000000U +#define FILE_REF_RELEASED 0xC0000000U +#define FILE_REF_DEAD 0xE0000000U +#define FILE_REF_NOREF 0xFFFFFFFFU +#endif + +typedef struct { +#ifdef CONFIG_64BIT + atomic64_t refcnt; +#else + atomic_t refcnt; +#endif +} file_ref_t; + +/** + * file_ref_init - Initialize a file reference count + * @ref: Pointer to the reference count + * @cnt: The initial reference count typically '1' + */ +static inline void file_ref_init(file_ref_t *ref, unsigned long cnt) +{ + atomic_long_set(&ref->refcnt, cnt - 1); +} + +bool __file_ref_put(file_ref_t *ref, unsigned long cnt); + +/** + * file_ref_get - Acquire one reference on a file + * @ref: Pointer to the reference count + * + * Similar to atomic_inc_not_zero() but saturates at FILE_REF_MAXREF. + * + * Provides full memory ordering. + * + * Return: False if the attempt to acquire a reference failed. This happens + * when the last reference has been put already. True if a reference + * was successfully acquired + */ +static __always_inline __must_check bool file_ref_get(file_ref_t *ref) +{ + /* + * Unconditionally increase the reference count with full + * ordering. The saturation and dead zones provide enough + * tolerance for this. + * + * If this indicates negative the file in question the fail can + * be freed and immediately reused due to SLAB_TYPSAFE_BY_RCU. + * Hence, unconditionally altering the file reference count to + * e.g., reset the file reference count back to the middle of + * the deadzone risk end up marking someone else's file as dead + * behind their back. + * + * It would be possible to do a careful: + * + * cnt = atomic_long_inc_return(); + * if (likely(cnt >= 0)) + * return true; + * + * and then something like: + * + * if (cnt >= FILE_REF_RELEASE) + * atomic_long_try_cmpxchg(&ref->refcnt, &cnt, FILE_REF_DEAD), + * + * to set the value back to the middle of the deadzone. But it's + * practically impossible to go from FILE_REF_DEAD to + * FILE_REF_ONEREF. It would need 2305843009213693952/2^61 + * file_ref_get()s to resurrect such a dead file. + */ + return !atomic_long_add_negative(1, &ref->refcnt); +} + +/** + * file_ref_inc - Acquire one reference on a file + * @ref: Pointer to the reference count + * + * Acquire an additional reference on a file. Warns if the caller didn't + * already hold a reference. + */ +static __always_inline void file_ref_inc(file_ref_t *ref) +{ + long prior = atomic_long_fetch_inc_relaxed(&ref->refcnt); + WARN_ONCE(prior < 0, "file_ref_inc() on a released file reference"); +} + +/** + * file_ref_put -- Release a file reference + * @ref: Pointer to the reference count + * + * Provides release memory ordering, such that prior loads and stores + * are done before, and provides an acquire ordering on success such + * that free() must come after. + * + * Return: True if this was the last reference with no future references + * possible. This signals the caller that it can safely release + * the object which is protected by the reference counter. + * False if there are still active references or the put() raced + * with a concurrent get()/put() pair. Caller is not allowed to + * release the protected object. + */ +static __always_inline __must_check bool file_ref_put(file_ref_t *ref) +{ + long cnt; + + /* + * While files are SLAB_TYPESAFE_BY_RCU and thus file_ref_put() + * calls don't risk UAFs when a file is recyclyed, it is still + * vulnerable to UAFs caused by freeing the whole slab page once + * it becomes unused. Prevent file_ref_put() from being + * preempted protects against this. + */ + guard(preempt)(); + /* + * Unconditionally decrease the reference count. The saturation + * and dead zones provide enough tolerance for this. If this + * fails then we need to handle the last reference drop and + * cases inside the saturation and dead zones. + */ + cnt = atomic_long_dec_return(&ref->refcnt); + if (cnt >= 0) + return false; + return __file_ref_put(ref, cnt); +} + +/** + * file_ref_read - Read the number of file references + * @ref: Pointer to the reference count + * + * Return: The number of held references (0 ... N) + */ +static inline unsigned long file_ref_read(file_ref_t *ref) +{ + unsigned long c = atomic_long_read(&ref->refcnt); + + /* Return 0 if within the DEAD zone. */ + return c >= FILE_REF_RELEASED ? 0 : c + 1; +} + +#endif diff --git a/include/linux/filelock.h b/include/linux/filelock.h index daee999d05f3..c412ded9171e 100644 --- a/include/linux/filelock.h +++ b/include/linux/filelock.h @@ -180,6 +180,11 @@ static inline void locks_wake_up(struct file_lock *fl) wake_up(&fl->c.flc_wait); } +static inline bool locks_can_async_lock(const struct file_operations *fops) +{ + return !fops->lock || fops->fop_flags & FOP_ASYNC_LOCK; +} + /* fs/locks.c */ void locks_free_lock_context(struct inode *inode); void locks_free_lock(struct file_lock *fl); @@ -420,28 +425,38 @@ static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl) #ifdef CONFIG_FILE_LOCKING static inline int break_lease(struct inode *inode, unsigned int mode) { + struct file_lock_context *flctx; + /* * Since this check is lockless, we must ensure that any refcounts * taken are done before checking i_flctx->flc_lease. Otherwise, we * could end up racing with tasks trying to set a new lease on this * file. */ + flctx = READ_ONCE(inode->i_flctx); + if (!flctx) + return 0; smp_mb(); - if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) + if (!list_empty_careful(&flctx->flc_lease)) return __break_lease(inode, mode, FL_LEASE); return 0; } static inline int break_deleg(struct inode *inode, unsigned int mode) { + struct file_lock_context *flctx; + /* * Since this check is lockless, we must ensure that any refcounts * taken are done before checking i_flctx->flc_lease. Otherwise, we * could end up racing with tasks trying to set a new lease on this * file. */ + flctx = READ_ONCE(inode->i_flctx); + if (!flctx) + return 0; smp_mb(); - if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) + if (!list_empty_careful(&flctx->flc_lease)) return __break_lease(inode, mode, FL_DELEG); return 0; } diff --git a/include/linux/filter.h b/include/linux/filter.h index c99bc3df2d28..a3ea46281595 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -75,6 +75,9 @@ struct ctl_table_header; /* unused opcode to mark special load instruction. Same as BPF_MSH */ #define BPF_PROBE_MEM32 0xa0 +/* unused opcode to mark special atomic instruction */ +#define BPF_PROBE_ATOMIC 0xe0 + /* unused opcode to mark call to interpreter with arguments */ #define BPF_CALL_ARGS 0xe0 @@ -178,6 +181,25 @@ struct ctl_table_header; .off = 0, \ .imm = 0 }) +/* Special (internal-only) form of mov, used to resolve per-CPU addrs: + * dst_reg = src_reg + <percpu_base_off> + * BPF_ADDR_PERCPU is used as a special insn->off value. + */ +#define BPF_ADDR_PERCPU (-1) + +#define BPF_MOV64_PERCPU_REG(DST, SRC) \ + ((struct bpf_insn) { \ + .code = BPF_ALU64 | BPF_MOV | BPF_X, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = BPF_ADDR_PERCPU, \ + .imm = 0 }) + +static inline bool insn_is_mov_percpu_addr(const struct bpf_insn *insn) +{ + return insn->code == (BPF_ALU64 | BPF_MOV | BPF_X) && insn->off == BPF_ADDR_PERCPU; +} + /* Short form of mov, dst_reg = imm32 */ #define BPF_MOV64_IMM(DST, IMM) \ @@ -228,6 +250,16 @@ static inline bool insn_is_zext(const struct bpf_insn *insn) return insn->code == (BPF_ALU | BPF_MOV | BPF_X) && insn->imm == 1; } +/* addr_space_cast from as(0) to as(1) is for converting bpf arena pointers + * to pointers in user vma. + */ +static inline bool insn_is_cast_user(const struct bpf_insn *insn) +{ + return insn->code == (BPF_ALU64 | BPF_MOV | BPF_X) && + insn->off == BPF_ADDR_SPACE_CAST && + insn->imm == 1U << 16; +} + /* BPF_LD_IMM64 macro encodes single 'load 64-bit immediate' insn */ #define BPF_LD_IMM64(DST, IMM) \ BPF_LD_IMM64_RAW(DST, 0, IMM) @@ -405,6 +437,16 @@ static inline bool insn_is_zext(const struct bpf_insn *insn) .off = OFF, \ .imm = 0 }) +/* Unconditional jumps, gotol pc + imm32 */ + +#define BPF_JMP32_A(IMM) \ + ((struct bpf_insn) { \ + .code = BPF_JMP32 | BPF_JA, \ + .dst_reg = 0, \ + .src_reg = 0, \ + .off = 0, \ + .imm = IMM }) + /* Relative call */ #define BPF_CALL_REL(TGT) \ @@ -644,14 +686,16 @@ static __always_inline u32 __bpf_prog_run(const struct bpf_prog *prog, cant_migrate(); if (static_branch_unlikely(&bpf_stats_enabled_key)) { struct bpf_prog_stats *stats; - u64 start = sched_clock(); + u64 duration, start = sched_clock(); unsigned long flags; ret = dfunc(ctx, prog->insnsi, prog->bpf_func); + + duration = sched_clock() - start; stats = this_cpu_ptr(prog->stats); flags = u64_stats_update_begin_irqsave(&stats->syncp); u64_stats_inc(&stats->cnt); - u64_stats_add(&stats->nsecs, sched_clock() - start); + u64_stats_add(&stats->nsecs, duration); u64_stats_update_end_irqrestore(&stats->syncp, flags); } else { ret = dfunc(ctx, prog->insnsi, prog->bpf_func); @@ -699,21 +743,128 @@ struct bpf_nh_params { }; }; +/* flags for bpf_redirect_info kern_flags */ +#define BPF_RI_F_RF_NO_DIRECT BIT(0) /* no napi_direct on return_frame */ +#define BPF_RI_F_RI_INIT BIT(1) +#define BPF_RI_F_CPU_MAP_INIT BIT(2) +#define BPF_RI_F_DEV_MAP_INIT BIT(3) +#define BPF_RI_F_XSK_MAP_INIT BIT(4) + struct bpf_redirect_info { u64 tgt_index; void *tgt_value; struct bpf_map *map; u32 flags; - u32 kern_flags; u32 map_id; enum bpf_map_type map_type; struct bpf_nh_params nh; + u32 kern_flags; }; -DECLARE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info); +struct bpf_net_context { + struct bpf_redirect_info ri; + struct list_head cpu_map_flush_list; + struct list_head dev_map_flush_list; + struct list_head xskmap_map_flush_list; +}; -/* flags for bpf_redirect_info kern_flags */ -#define BPF_RI_F_RF_NO_DIRECT BIT(0) /* no napi_direct on return_frame */ +static inline struct bpf_net_context *bpf_net_ctx_set(struct bpf_net_context *bpf_net_ctx) +{ + struct task_struct *tsk = current; + + if (tsk->bpf_net_context != NULL) + return NULL; + bpf_net_ctx->ri.kern_flags = 0; + + tsk->bpf_net_context = bpf_net_ctx; + return bpf_net_ctx; +} + +static inline void bpf_net_ctx_clear(struct bpf_net_context *bpf_net_ctx) +{ + if (bpf_net_ctx) + current->bpf_net_context = NULL; +} + +static inline struct bpf_net_context *bpf_net_ctx_get(void) +{ + return current->bpf_net_context; +} + +static inline struct bpf_redirect_info *bpf_net_ctx_get_ri(void) +{ + struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get(); + + if (!(bpf_net_ctx->ri.kern_flags & BPF_RI_F_RI_INIT)) { + memset(&bpf_net_ctx->ri, 0, offsetof(struct bpf_net_context, ri.nh)); + bpf_net_ctx->ri.kern_flags |= BPF_RI_F_RI_INIT; + } + + return &bpf_net_ctx->ri; +} + +static inline struct list_head *bpf_net_ctx_get_cpu_map_flush_list(void) +{ + struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get(); + + if (!(bpf_net_ctx->ri.kern_flags & BPF_RI_F_CPU_MAP_INIT)) { + INIT_LIST_HEAD(&bpf_net_ctx->cpu_map_flush_list); + bpf_net_ctx->ri.kern_flags |= BPF_RI_F_CPU_MAP_INIT; + } + + return &bpf_net_ctx->cpu_map_flush_list; +} + +static inline struct list_head *bpf_net_ctx_get_dev_flush_list(void) +{ + struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get(); + + if (!(bpf_net_ctx->ri.kern_flags & BPF_RI_F_DEV_MAP_INIT)) { + INIT_LIST_HEAD(&bpf_net_ctx->dev_map_flush_list); + bpf_net_ctx->ri.kern_flags |= BPF_RI_F_DEV_MAP_INIT; + } + + return &bpf_net_ctx->dev_map_flush_list; +} + +static inline struct list_head *bpf_net_ctx_get_xskmap_flush_list(void) +{ + struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get(); + + if (!(bpf_net_ctx->ri.kern_flags & BPF_RI_F_XSK_MAP_INIT)) { + INIT_LIST_HEAD(&bpf_net_ctx->xskmap_map_flush_list); + bpf_net_ctx->ri.kern_flags |= BPF_RI_F_XSK_MAP_INIT; + } + + return &bpf_net_ctx->xskmap_map_flush_list; +} + +static inline void bpf_net_ctx_get_all_used_flush_lists(struct list_head **lh_map, + struct list_head **lh_dev, + struct list_head **lh_xsk) +{ + struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get(); + u32 kern_flags = bpf_net_ctx->ri.kern_flags; + struct list_head *lh; + + *lh_map = *lh_dev = *lh_xsk = NULL; + + if (!IS_ENABLED(CONFIG_BPF_SYSCALL)) + return; + + lh = &bpf_net_ctx->dev_map_flush_list; + if (kern_flags & BPF_RI_F_DEV_MAP_INIT && !list_empty(lh)) + *lh_dev = lh; + + lh = &bpf_net_ctx->cpu_map_flush_list; + if (kern_flags & BPF_RI_F_CPU_MAP_INIT && !list_empty(lh)) + *lh_map = lh; + + lh = &bpf_net_ctx->xskmap_map_flush_list; + if (IS_ENABLED(CONFIG_XDP_SOCKETS) && + kern_flags & BPF_RI_F_XSK_MAP_INIT && !list_empty(lh)) + *lh_xsk = lh; +} /* Compute the linear packet data range [data, data_end) which * will be accessed by various program types (cls_bpf, act_bpf, @@ -887,20 +1038,22 @@ bpf_ctx_narrow_access_offset(u32 off, u32 size, u32 size_default) #define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0])) -static inline void bpf_prog_lock_ro(struct bpf_prog *fp) +static inline int __must_check bpf_prog_lock_ro(struct bpf_prog *fp) { #ifndef CONFIG_BPF_JIT_ALWAYS_ON if (!fp->jited) { set_vm_flush_reset_perms(fp); - set_memory_ro((unsigned long)fp, fp->pages); + return set_memory_ro((unsigned long)fp, fp->pages); } #endif + return 0; } -static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) +static inline int __must_check +bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) { set_vm_flush_reset_perms(hdr); - set_memory_rox((unsigned long)hdr, hdr->size >> PAGE_SHIFT); + return set_memory_rox((unsigned long)hdr, hdr->size >> PAGE_SHIFT); } int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap); @@ -957,14 +1110,19 @@ u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog); void bpf_jit_compile(struct bpf_prog *prog); bool bpf_jit_needs_zext(void); +bool bpf_jit_inlines_helper_call(s32 imm); bool bpf_jit_supports_subprog_tailcalls(void); +bool bpf_jit_supports_percpu_insn(void); bool bpf_jit_supports_kfunc_call(void); bool bpf_jit_supports_far_kfunc_call(void); bool bpf_jit_supports_exceptions(void); bool bpf_jit_supports_ptr_xchg(void); bool bpf_jit_supports_arena(void); +bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena); +bool bpf_jit_supports_private_stack(void); +u64 bpf_arch_uaddress_limit(void); void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie); -bool bpf_helper_changes_pkt_data(void *func); +bool bpf_helper_changes_pkt_data(enum bpf_func_id func_id); static inline bool bpf_dump_raw_ok(const struct cred *cred) { @@ -978,25 +1136,23 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len); int bpf_remove_insns(struct bpf_prog *prog, u32 off, u32 cnt); -void bpf_clear_redirect_map(struct bpf_map *map); - static inline bool xdp_return_frame_no_direct(void) { - struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); return ri->kern_flags & BPF_RI_F_RF_NO_DIRECT; } static inline void xdp_set_return_frame_no_direct(void) { - struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); ri->kern_flags |= BPF_RI_F_RF_NO_DIRECT; } static inline void xdp_clear_return_frame_no_direct(void) { - struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); ri->kern_flags &= ~BPF_RI_F_RF_NO_DIRECT; } @@ -1023,17 +1179,18 @@ static inline int xdp_ok_fwd_dev(const struct net_device *fwd, * This does not appear to be a real limitation for existing software. */ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, - struct xdp_buff *xdp, struct bpf_prog *prog); + struct xdp_buff *xdp, const struct bpf_prog *prog); int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, - struct bpf_prog *prog); + const struct bpf_prog *prog); int xdp_do_redirect_frame(struct net_device *dev, struct xdp_buff *xdp, struct xdp_frame *xdpf, - struct bpf_prog *prog); + const struct bpf_prog *prog); void xdp_do_flush(void); -void bpf_warn_invalid_xdp_action(struct net_device *dev, struct bpf_prog *prog, u32 act); +void bpf_warn_invalid_xdp_action(const struct net_device *dev, + const struct bpf_prog *prog, u32 act); #ifdef CONFIG_INET struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, @@ -1089,8 +1246,7 @@ bpf_jit_binary_pack_alloc(unsigned int proglen, u8 **ro_image, struct bpf_binary_header **rw_hdr, u8 **rw_image, bpf_jit_fill_hole_t bpf_fill_ill_insns); -int bpf_jit_binary_pack_finalize(struct bpf_prog *prog, - struct bpf_binary_header *ro_header, +int bpf_jit_binary_pack_finalize(struct bpf_binary_header *ro_header, struct bpf_binary_header *rw_header); void bpf_jit_binary_pack_free(struct bpf_binary_header *ro_header, struct bpf_binary_header *rw_header); @@ -1168,18 +1324,18 @@ static inline bool bpf_jit_kallsyms_enabled(void) return false; } -const char *__bpf_address_lookup(unsigned long addr, unsigned long *size, +int __bpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char *sym); bool is_bpf_text_address(unsigned long addr); int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym); struct bpf_prog *bpf_prog_ksym_find(unsigned long addr); -static inline const char * +static inline int bpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char **modname, char *sym) { - const char *ret = __bpf_address_lookup(addr, size, off, sym); + int ret = __bpf_address_lookup(addr, size, off, sym); if (ret && modname) *modname = NULL; @@ -1223,11 +1379,11 @@ static inline bool bpf_jit_kallsyms_enabled(void) return false; } -static inline const char * +static inline int __bpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char *sym) { - return NULL; + return 0; } static inline bool is_bpf_text_address(unsigned long addr) @@ -1246,11 +1402,11 @@ static inline struct bpf_prog *bpf_prog_ksym_find(unsigned long addr) return NULL; } -static inline const char * +static inline int bpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char **modname, char *sym) { - return NULL; + return 0; } static inline void bpf_prog_kallsyms_add(struct bpf_prog *fp) @@ -1366,7 +1522,7 @@ struct bpf_sock_ops_kern { struct bpf_sysctl_kern { struct ctl_table_header *head; - struct ctl_table *table; + const struct ctl_table *table; void *cur_val; size_t cur_len; void *new_val; @@ -1472,7 +1628,7 @@ extern struct static_key_false bpf_sk_lookup_enabled; _all_pass || _selected_sk ? SK_PASS : SK_DROP; \ }) -static inline bool bpf_sk_lookup_run_v4(struct net *net, int protocol, +static inline bool bpf_sk_lookup_run_v4(const struct net *net, int protocol, const __be32 saddr, const __be16 sport, const __be32 daddr, const u16 dport, const int ifindex, struct sock **psk) @@ -1509,7 +1665,7 @@ static inline bool bpf_sk_lookup_run_v4(struct net *net, int protocol, } #if IS_ENABLED(CONFIG_IPV6) -static inline bool bpf_sk_lookup_run_v6(struct net *net, int protocol, +static inline bool bpf_sk_lookup_run_v6(const struct net *net, int protocol, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, @@ -1552,7 +1708,7 @@ static __always_inline long __bpf_xdp_redirect_map(struct bpf_map *map, u64 inde u64 flags, const u64 flag_mask, void *lookup_elem(struct bpf_map *map, u32 key)) { - struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); const u64 action_mask = XDP_ABORTED | XDP_DROP | XDP_PASS | XDP_TX; /* Lower bits of the flags are used as return code on lookup failure */ diff --git a/include/linux/find.h b/include/linux/find.h index c69598e383c1..68685714bc18 100644 --- a/include/linux/find.h +++ b/include/linux/find.h @@ -29,6 +29,8 @@ unsigned long __find_nth_and_andnot_bit(const unsigned long *addr1, const unsign unsigned long n); extern unsigned long _find_first_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size); +unsigned long _find_first_and_and_bit(const unsigned long *addr1, const unsigned long *addr2, + const unsigned long *addr3, unsigned long size); extern unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size); extern unsigned long _find_last_bit(const unsigned long *addr, unsigned long size); @@ -50,7 +52,7 @@ unsigned long _find_next_bit_le(const unsigned long *addr, unsigned * Returns the bit number for the next set bit * If no bits are set, returns @size. */ -static inline +static __always_inline unsigned long find_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { @@ -79,7 +81,7 @@ unsigned long find_next_bit(const unsigned long *addr, unsigned long size, * Returns the bit number for the next set bit * If no bits are set, returns @size. */ -static inline +static __always_inline unsigned long find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) @@ -110,7 +112,7 @@ unsigned long find_next_and_bit(const unsigned long *addr1, * Returns the bit number for the next set bit * If no bits are set, returns @size. */ -static inline +static __always_inline unsigned long find_next_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) @@ -140,7 +142,7 @@ unsigned long find_next_andnot_bit(const unsigned long *addr1, * Returns the bit number for the next set bit * If no bits are set, returns @size. */ -static inline +static __always_inline unsigned long find_next_or_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) @@ -169,7 +171,7 @@ unsigned long find_next_or_bit(const unsigned long *addr1, * Returns the bit number of the next zero bit * If no bits are zero, returns @size. */ -static inline +static __always_inline unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { @@ -196,7 +198,7 @@ unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, * Returns the bit number of the first set bit. * If no bits are set, returns @size. */ -static inline +static __always_inline unsigned long find_first_bit(const unsigned long *addr, unsigned long size) { if (small_const_nbits(size)) { @@ -220,9 +222,9 @@ unsigned long find_first_bit(const unsigned long *addr, unsigned long size) * idx = find_first_bit(addr, size); * * Returns the bit number of the N'th set bit. - * If no such, returns @size. + * If no such, returns >= @size. */ -static inline +static __always_inline unsigned long find_nth_bit(const unsigned long *addr, unsigned long size, unsigned long n) { if (n >= size) @@ -247,7 +249,7 @@ unsigned long find_nth_bit(const unsigned long *addr, unsigned long size, unsign * Returns the bit number of the N'th set bit. * If no such, returns @size. */ -static inline +static __always_inline unsigned long find_nth_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long n) { @@ -274,7 +276,7 @@ unsigned long find_nth_and_bit(const unsigned long *addr1, const unsigned long * * Returns the bit number of the N'th set bit. * If no such, returns @size. */ -static inline +static __always_inline unsigned long find_nth_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long n) { @@ -330,7 +332,7 @@ unsigned long find_nth_and_andnot_bit(const unsigned long *addr1, * Returns the bit number for the next set bit * If no bits are set, returns @size. */ -static inline +static __always_inline unsigned long find_first_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size) @@ -345,6 +347,31 @@ unsigned long find_first_and_bit(const unsigned long *addr1, } #endif +/** + * find_first_and_and_bit - find the first set bit in 3 memory regions + * @addr1: The first address to base the search on + * @addr2: The second address to base the search on + * @addr3: The third address to base the search on + * @size: The bitmap size in bits + * + * Returns the bit number for the first set bit + * If no bits are set, returns @size. + */ +static __always_inline +unsigned long find_first_and_and_bit(const unsigned long *addr1, + const unsigned long *addr2, + const unsigned long *addr3, + unsigned long size) +{ + if (small_const_nbits(size)) { + unsigned long val = *addr1 & *addr2 & *addr3 & GENMASK(size - 1, 0); + + return val ? __ffs(val) : size; + } + + return _find_first_and_and_bit(addr1, addr2, addr3, size); +} + #ifndef find_first_zero_bit /** * find_first_zero_bit - find the first cleared bit in a memory region @@ -354,7 +381,7 @@ unsigned long find_first_and_bit(const unsigned long *addr1, * Returns the bit number of the first cleared bit. * If no bits are zero, returns @size. */ -static inline +static __always_inline unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size) { if (small_const_nbits(size)) { @@ -375,7 +402,7 @@ unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size) * * Returns the bit number of the last set bit, or size. */ -static inline +static __always_inline unsigned long find_last_bit(const unsigned long *addr, unsigned long size) { if (small_const_nbits(size)) { @@ -398,7 +425,7 @@ unsigned long find_last_bit(const unsigned long *addr, unsigned long size) * Returns the bit number for the next set bit, or first set bit up to @offset * If no bits are set, returns @size. */ -static inline +static __always_inline unsigned long find_next_and_bit_wrap(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) @@ -421,7 +448,7 @@ unsigned long find_next_and_bit_wrap(const unsigned long *addr1, * Returns the bit number for the next set bit, or first set bit up to @offset * If no bits are set, returns @size. */ -static inline +static __always_inline unsigned long find_next_bit_wrap(const unsigned long *addr, unsigned long size, unsigned long offset) { @@ -438,7 +465,7 @@ unsigned long find_next_bit_wrap(const unsigned long *addr, * Helper for for_each_set_bit_wrap(). Make sure you're doing right thing * before using it alone. */ -static inline +static __always_inline unsigned long __for_each_wrap(const unsigned long *bitmap, unsigned long size, unsigned long start, unsigned long n) { @@ -479,20 +506,20 @@ extern unsigned long find_next_clump8(unsigned long *clump, #if defined(__LITTLE_ENDIAN) -static inline unsigned long find_next_zero_bit_le(const void *addr, - unsigned long size, unsigned long offset) +static __always_inline +unsigned long find_next_zero_bit_le(const void *addr, unsigned long size, unsigned long offset) { return find_next_zero_bit(addr, size, offset); } -static inline unsigned long find_next_bit_le(const void *addr, - unsigned long size, unsigned long offset) +static __always_inline +unsigned long find_next_bit_le(const void *addr, unsigned long size, unsigned long offset) { return find_next_bit(addr, size, offset); } -static inline unsigned long find_first_zero_bit_le(const void *addr, - unsigned long size) +static __always_inline +unsigned long find_first_zero_bit_le(const void *addr, unsigned long size) { return find_first_zero_bit(addr, size); } @@ -500,7 +527,7 @@ static inline unsigned long find_first_zero_bit_le(const void *addr, #elif defined(__BIG_ENDIAN) #ifndef find_next_zero_bit_le -static inline +static __always_inline unsigned long find_next_zero_bit_le(const void *addr, unsigned long size, unsigned long offset) { @@ -519,7 +546,7 @@ unsigned long find_next_zero_bit_le(const void *addr, unsigned #endif #ifndef find_first_zero_bit_le -static inline +static __always_inline unsigned long find_first_zero_bit_le(const void *addr, unsigned long size) { if (small_const_nbits(size)) { @@ -533,7 +560,7 @@ unsigned long find_first_zero_bit_le(const void *addr, unsigned long size) #endif #ifndef find_next_bit_le -static inline +static __always_inline unsigned long find_next_bit_le(const void *addr, unsigned long size, unsigned long offset) { diff --git a/include/linux/firewire.h b/include/linux/firewire.h index dd9f2d765e68..b632eec3ab52 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -134,6 +134,8 @@ struct fw_card { __be32 topology_map[(CSR_TOPOLOGY_MAP_END - CSR_TOPOLOGY_MAP) / 4]; __be32 maint_utility_register; + + struct workqueue_struct *isoc_wq; }; static inline struct fw_card *fw_card_get(struct fw_card *card) @@ -462,7 +464,7 @@ struct fw_iso_packet { /* rx: Sync bit, wait for matching sy */ u32 tag:2; /* tx: Tag in packet header */ u32 sy:4; /* tx: Sy in packet header */ - u32 header_length:8; /* Length of immediate header */ + u32 header_length:8; /* Size of immediate header */ u32 header[]; /* tx: Top of 1394 isoch. data_block */ }; @@ -509,6 +511,7 @@ union fw_iso_callback { struct fw_iso_context { struct fw_card *card; + struct work_struct work; int type; int channel; int speed; @@ -528,6 +531,25 @@ int fw_iso_context_queue(struct fw_iso_context *ctx, unsigned long payload); void fw_iso_context_queue_flush(struct fw_iso_context *ctx); int fw_iso_context_flush_completions(struct fw_iso_context *ctx); + +/** + * fw_iso_context_schedule_flush_completions() - schedule work item to process isochronous context. + * @ctx: the isochronous context + * + * Schedule a work item on workqueue to process the isochronous context. The registered callback + * function is called by the worker when a queued packet buffer with the interrupt flag is + * completed, either after transmission in the IT context or after being filled in the IR context. + * The callback function is also called when the header buffer in the context becomes full, If it + * is required to process the context in the current context, fw_iso_context_flush_completions() is + * available instead. + * + * Context: Any context. + */ +static inline void fw_iso_context_schedule_flush_completions(struct fw_iso_context *ctx) +{ + queue_work(ctx->card->isoc_wq, &ctx->work); +} + int fw_iso_context_start(struct fw_iso_context *ctx, int cycle, int sync, int tags); int fw_iso_context_stop(struct fw_iso_context *ctx); diff --git a/include/linux/firmware.h b/include/linux/firmware.h index f026f8926d79..aae1b85ffc10 100644 --- a/include/linux/firmware.h +++ b/include/linux/firmware.h @@ -98,6 +98,10 @@ static inline bool firmware_request_builtin(struct firmware *fw, #if IS_REACHABLE(CONFIG_FW_LOADER) int request_firmware(const struct firmware **fw, const char *name, struct device *device); +int firmware_request_nowait_nowarn( + struct module *module, const char *name, + struct device *device, gfp_t gfp, void *context, + void (*cont)(const struct firmware *fw, void *context)); int firmware_request_nowarn(const struct firmware **fw, const char *name, struct device *device); int firmware_request_platform(const struct firmware **fw, const char *name, @@ -123,6 +127,14 @@ static inline int request_firmware(const struct firmware **fw, return -EINVAL; } +static inline int firmware_request_nowait_nowarn( + struct module *module, const char *name, + struct device *device, gfp_t gfp, void *context, + void (*cont)(const struct firmware *fw, void *context)) +{ + return -EINVAL; +} + static inline int firmware_request_nowarn(const struct firmware **fw, const char *name, struct device *device) diff --git a/include/linux/firmware/cirrus/cs_dsp.h b/include/linux/firmware/cirrus/cs_dsp.h index 23384a54d575..7cae703b3137 100644 --- a/include/linux/firmware/cirrus/cs_dsp.h +++ b/include/linux/firmware/cirrus/cs_dsp.h @@ -42,6 +42,16 @@ #define CS_DSP_ACKED_CTL_MIN_VALUE 0 #define CS_DSP_ACKED_CTL_MAX_VALUE 0xFFFFFF +/* + * Write sequence operation codes + */ +#define CS_DSP_WSEQ_FULL 0x00 +#define CS_DSP_WSEQ_ADDR8 0x02 +#define CS_DSP_WSEQ_L16 0x04 +#define CS_DSP_WSEQ_H16 0x05 +#define CS_DSP_WSEQ_UNLOCK 0xFD +#define CS_DSP_WSEQ_END 0xFF + /** * struct cs_dsp_region - Describes a logical memory region in DSP address space * @type: Memory region type @@ -167,7 +177,7 @@ struct cs_dsp { const struct cs_dsp_region *mem; int num_mems; - int fw_ver; + int wmfw_ver; bool booted; bool running; @@ -213,13 +223,13 @@ int cs_dsp_adsp2_init(struct cs_dsp *dsp); int cs_dsp_halo_init(struct cs_dsp *dsp); int cs_dsp_adsp1_power_up(struct cs_dsp *dsp, - const struct firmware *wmfw_firmware, char *wmfw_filename, - const struct firmware *coeff_firmware, char *coeff_filename, + const struct firmware *wmfw_firmware, const char *wmfw_filename, + const struct firmware *coeff_firmware, const char *coeff_filename, const char *fw_name); void cs_dsp_adsp1_power_down(struct cs_dsp *dsp); int cs_dsp_power_up(struct cs_dsp *dsp, - const struct firmware *wmfw_firmware, char *wmfw_filename, - const struct firmware *coeff_firmware, char *coeff_filename, + const struct firmware *wmfw_firmware, const char *wmfw_filename, + const struct firmware *coeff_firmware, const char *coeff_filename, const char *fw_name); void cs_dsp_power_down(struct cs_dsp *dsp); int cs_dsp_run(struct cs_dsp *dsp); @@ -238,8 +248,12 @@ void cs_dsp_cleanup_debugfs(struct cs_dsp *dsp); int cs_dsp_coeff_write_acked_control(struct cs_dsp_coeff_ctl *ctl, unsigned int event_id); int cs_dsp_coeff_write_ctrl(struct cs_dsp_coeff_ctl *ctl, unsigned int off, const void *buf, size_t len); +int cs_dsp_coeff_lock_and_write_ctrl(struct cs_dsp_coeff_ctl *ctl, unsigned int off, + const void *buf, size_t len); int cs_dsp_coeff_read_ctrl(struct cs_dsp_coeff_ctl *ctl, unsigned int off, void *buf, size_t len); +int cs_dsp_coeff_lock_and_read_ctrl(struct cs_dsp_coeff_ctl *ctl, unsigned int off, + void *buf, size_t len); struct cs_dsp_coeff_ctl *cs_dsp_get_ctl(struct cs_dsp *dsp, const char *name, int type, unsigned int alg); @@ -255,6 +269,23 @@ struct cs_dsp_alg_region *cs_dsp_find_alg_region(struct cs_dsp *dsp, const char *cs_dsp_mem_region_name(unsigned int type); /** + * struct cs_dsp_wseq - Describes a write sequence + * @ctl: Write sequence cs_dsp control + * @ops: Operations contained within + */ +struct cs_dsp_wseq { + struct cs_dsp_coeff_ctl *ctl; + struct list_head ops; +}; + +int cs_dsp_wseq_init(struct cs_dsp *dsp, struct cs_dsp_wseq *wseqs, unsigned int num_wseqs); +int cs_dsp_wseq_write(struct cs_dsp *dsp, struct cs_dsp_wseq *wseq, u32 addr, u32 data, + u8 op_code, bool update); +int cs_dsp_wseq_multi_write(struct cs_dsp *dsp, struct cs_dsp_wseq *wseq, + const struct reg_sequence *reg_seq, int num_regs, + u8 op_code, bool update); + +/** * struct cs_dsp_chunk - Describes a buffer holding data formatted for the DSP * @data: Pointer to underlying buffer memory * @max: Pointer to end of the buffer memory diff --git a/include/linux/firmware/cirrus/cs_dsp_test_utils.h b/include/linux/firmware/cirrus/cs_dsp_test_utils.h new file mode 100644 index 000000000000..4f87a908ab4f --- /dev/null +++ b/include/linux/firmware/cirrus/cs_dsp_test_utils.h @@ -0,0 +1,160 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Support utilities for cs_dsp testing. + * + * Copyright (C) 2024 Cirrus Logic, Inc. and + * Cirrus Logic International Semiconductor Ltd. + */ + +#include <linux/regmap.h> +#include <linux/firmware/cirrus/wmfw.h> + +struct kunit; +struct cs_dsp_test; +struct cs_dsp_test_local; + +/** + * struct cs_dsp_test - base class for test utilities + * + * @test: Pointer to struct kunit instance. + * @dsp: Pointer to struct cs_dsp instance. + * @local: Private data for each test suite. + */ +struct cs_dsp_test { + struct kunit *test; + struct cs_dsp *dsp; + + struct cs_dsp_test_local *local; + + /* Following members are private */ + bool saw_bus_write; +}; + +/** + * struct cs_dsp_mock_alg_def - Info for creating a mock algorithm entry. + * + * @id Algorithm ID. + * @ver; Algorithm version. + * @xm_base_words XM base address in DSP words. + * @xm_size_words XM size in DSP words. + * @ym_base_words YM base address in DSP words. + * @ym_size_words YM size in DSP words. + * @zm_base_words ZM base address in DSP words. + * @zm_size_words ZM size in DSP words. + */ +struct cs_dsp_mock_alg_def { + unsigned int id; + unsigned int ver; + unsigned int xm_base_words; + unsigned int xm_size_words; + unsigned int ym_base_words; + unsigned int ym_size_words; + unsigned int zm_base_words; + unsigned int zm_size_words; +}; + +struct cs_dsp_mock_coeff_def { + const char *shortname; + const char *fullname; + const char *description; + u16 type; + u16 flags; + u16 mem_type; + unsigned int offset_dsp_words; + unsigned int length_bytes; +}; + +/** + * struct cs_dsp_mock_xm_header - XM header builder + * + * @test_priv: Pointer to the struct cs_dsp_test. + * @blob_data: Pointer to the created blob data. + * @blob_size_bytes: Size of the data at blob_data. + */ +struct cs_dsp_mock_xm_header { + struct cs_dsp_test *test_priv; + void *blob_data; + size_t blob_size_bytes; +}; + +struct cs_dsp_mock_wmfw_builder; +struct cs_dsp_mock_bin_builder; + +extern const unsigned int cs_dsp_mock_adsp2_32bit_sysbase; +extern const unsigned int cs_dsp_mock_adsp2_16bit_sysbase; +extern const unsigned int cs_dsp_mock_halo_core_base; +extern const unsigned int cs_dsp_mock_halo_sysinfo_base; + +extern const struct cs_dsp_region cs_dsp_mock_halo_dsp1_regions[]; +extern const unsigned int cs_dsp_mock_halo_dsp1_region_sizes[]; +extern const struct cs_dsp_region cs_dsp_mock_adsp2_32bit_dsp1_regions[]; +extern const unsigned int cs_dsp_mock_adsp2_32bit_dsp1_region_sizes[]; +extern const struct cs_dsp_region cs_dsp_mock_adsp2_16bit_dsp1_regions[]; +extern const unsigned int cs_dsp_mock_adsp2_16bit_dsp1_region_sizes[]; +int cs_dsp_mock_count_regions(const unsigned int *region_sizes); +unsigned int cs_dsp_mock_size_of_region(const struct cs_dsp *dsp, int mem_type); +unsigned int cs_dsp_mock_base_addr_for_mem(struct cs_dsp_test *priv, int mem_type); +unsigned int cs_dsp_mock_reg_addr_inc_per_unpacked_word(struct cs_dsp_test *priv); +unsigned int cs_dsp_mock_reg_block_length_bytes(struct cs_dsp_test *priv, int mem_type); +unsigned int cs_dsp_mock_reg_block_length_registers(struct cs_dsp_test *priv, int mem_type); +unsigned int cs_dsp_mock_reg_block_length_dsp_words(struct cs_dsp_test *priv, int mem_type); +bool cs_dsp_mock_has_zm(struct cs_dsp_test *priv); +int cs_dsp_mock_packed_to_unpacked_mem_type(int packed_mem_type); +unsigned int cs_dsp_mock_num_dsp_words_to_num_packed_regs(unsigned int num_dsp_words); +unsigned int cs_dsp_mock_xm_header_get_alg_base_in_words(struct cs_dsp_test *priv, + unsigned int alg_id, + int mem_type); +unsigned int cs_dsp_mock_xm_header_get_fw_version_from_regmap(struct cs_dsp_test *priv); +unsigned int cs_dsp_mock_xm_header_get_fw_version(struct cs_dsp_mock_xm_header *header); +void cs_dsp_mock_xm_header_drop_from_regmap_cache(struct cs_dsp_test *priv); +int cs_dsp_mock_xm_header_write_to_regmap(struct cs_dsp_mock_xm_header *header); +struct cs_dsp_mock_xm_header *cs_dsp_create_mock_xm_header(struct cs_dsp_test *priv, + const struct cs_dsp_mock_alg_def *algs, + size_t num_algs); + +int cs_dsp_mock_regmap_init(struct cs_dsp_test *priv); +void cs_dsp_mock_regmap_drop_range(struct cs_dsp_test *priv, + unsigned int first_reg, unsigned int last_reg); +void cs_dsp_mock_regmap_drop_regs(struct cs_dsp_test *priv, + unsigned int first_reg, size_t num_regs); +void cs_dsp_mock_regmap_drop_bytes(struct cs_dsp_test *priv, + unsigned int first_reg, size_t num_bytes); +void cs_dsp_mock_regmap_drop_system_regs(struct cs_dsp_test *priv); +bool cs_dsp_mock_regmap_is_dirty(struct cs_dsp_test *priv, bool drop_system_regs); + +struct cs_dsp_mock_bin_builder *cs_dsp_mock_bin_init(struct cs_dsp_test *priv, + int format_version, + unsigned int fw_version); +void cs_dsp_mock_bin_add_raw_block(struct cs_dsp_mock_bin_builder *builder, + unsigned int alg_id, unsigned int alg_ver, + int type, unsigned int offset, + const void *payload_data, size_t payload_len_bytes); +void cs_dsp_mock_bin_add_info(struct cs_dsp_mock_bin_builder *builder, + const char *info); +void cs_dsp_mock_bin_add_name(struct cs_dsp_mock_bin_builder *builder, + const char *name); +void cs_dsp_mock_bin_add_patch(struct cs_dsp_mock_bin_builder *builder, + unsigned int alg_id, unsigned int alg_ver, + int mem_region, unsigned int reg_addr_offset, + const void *payload_data, size_t payload_len_bytes); +struct firmware *cs_dsp_mock_bin_get_firmware(struct cs_dsp_mock_bin_builder *builder); + +struct cs_dsp_mock_wmfw_builder *cs_dsp_mock_wmfw_init(struct cs_dsp_test *priv, + int format_version); +void cs_dsp_mock_wmfw_add_raw_block(struct cs_dsp_mock_wmfw_builder *builder, + int mem_region, unsigned int mem_offset_dsp_words, + const void *payload_data, size_t payload_len_bytes); +void cs_dsp_mock_wmfw_add_info(struct cs_dsp_mock_wmfw_builder *builder, + const char *info); +void cs_dsp_mock_wmfw_add_data_block(struct cs_dsp_mock_wmfw_builder *builder, + int mem_region, unsigned int mem_offset_dsp_words, + const void *payload_data, size_t payload_len_bytes); +void cs_dsp_mock_wmfw_start_alg_info_block(struct cs_dsp_mock_wmfw_builder *builder, + unsigned int alg_id, + const char *name, + const char *description); +void cs_dsp_mock_wmfw_add_coeff_desc(struct cs_dsp_mock_wmfw_builder *builder, + const struct cs_dsp_mock_coeff_def *def); +void cs_dsp_mock_wmfw_end_alg_info_block(struct cs_dsp_mock_wmfw_builder *builder); +struct firmware *cs_dsp_mock_wmfw_get_firmware(struct cs_dsp_mock_wmfw_builder *builder); +int cs_dsp_mock_wmfw_format_version(struct cs_dsp_mock_wmfw_builder *builder); diff --git a/include/linux/firmware/imx/sm.h b/include/linux/firmware/imx/sm.h new file mode 100644 index 000000000000..9b85a3f028d1 --- /dev/null +++ b/include/linux/firmware/imx/sm.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Copyright 2024 NXP + */ + +#ifndef _SCMI_IMX_H +#define _SCMI_IMX_H + +#include <linux/bitfield.h> +#include <linux/errno.h> +#include <linux/types.h> + +#define SCMI_IMX_CTRL_PDM_CLK_SEL 0 /* AON PDM clock sel */ +#define SCMI_IMX_CTRL_MQS1_SETTINGS 1 /* AON MQS settings */ +#define SCMI_IMX_CTRL_SAI1_MCLK 2 /* AON SAI1 MCLK */ +#define SCMI_IMX_CTRL_SAI3_MCLK 3 /* WAKE SAI3 MCLK */ +#define SCMI_IMX_CTRL_SAI4_MCLK 4 /* WAKE SAI4 MCLK */ +#define SCMI_IMX_CTRL_SAI5_MCLK 5 /* WAKE SAI5 MCLK */ + +int scmi_imx_misc_ctrl_get(u32 id, u32 *num, u32 *val); +int scmi_imx_misc_ctrl_set(u32 id, u32 val); + +#endif diff --git a/include/linux/firmware/mediatek/mtk-adsp-ipc.h b/include/linux/firmware/mediatek/mtk-adsp-ipc.h index 5b1d16fa3f56..6e86799a7dc4 100644 --- a/include/linux/firmware/mediatek/mtk-adsp-ipc.h +++ b/include/linux/firmware/mediatek/mtk-adsp-ipc.h @@ -40,7 +40,7 @@ struct mtk_adsp_chan { struct mtk_adsp_ipc { struct mtk_adsp_chan chans[MTK_ADSP_MBOX_NUM]; struct device *dev; - struct mtk_adsp_ipc_ops *ops; + const struct mtk_adsp_ipc_ops *ops; void *private_data; }; diff --git a/include/linux/firmware/qcom/qcom_qseecom.h b/include/linux/firmware/qcom/qcom_qseecom.h index 366243ee9609..3387897bf368 100644 --- a/include/linux/firmware/qcom/qcom_qseecom.h +++ b/include/linux/firmware/qcom/qcom_qseecom.h @@ -26,56 +26,11 @@ struct qseecom_client { }; /** - * qseecom_scm_dev() - Get the SCM device associated with the QSEECOM client. - * @client: The QSEECOM client device. - * - * Returns the SCM device under which the provided QSEECOM client device - * operates. This function is intended to be used for DMA allocations. - */ -static inline struct device *qseecom_scm_dev(struct qseecom_client *client) -{ - return client->aux_dev.dev.parent->parent; -} - -/** - * qseecom_dma_alloc() - Allocate DMA memory for a QSEECOM client. - * @client: The QSEECOM client to allocate the memory for. - * @size: The number of bytes to allocate. - * @dma_handle: Pointer to where the DMA address should be stored. - * @gfp: Allocation flags. - * - * Wrapper function for dma_alloc_coherent(), allocating DMA memory usable for - * TZ/QSEECOM communication. Refer to dma_alloc_coherent() for details. - */ -static inline void *qseecom_dma_alloc(struct qseecom_client *client, size_t size, - dma_addr_t *dma_handle, gfp_t gfp) -{ - return dma_alloc_coherent(qseecom_scm_dev(client), size, dma_handle, gfp); -} - -/** - * dma_free_coherent() - Free QSEECOM DMA memory. - * @client: The QSEECOM client for which the memory has been allocated. - * @size: The number of bytes allocated. - * @cpu_addr: Virtual memory address to free. - * @dma_handle: DMA memory address to free. - * - * Wrapper function for dma_free_coherent(), freeing memory previously - * allocated with qseecom_dma_alloc(). Refer to dma_free_coherent() for - * details. - */ -static inline void qseecom_dma_free(struct qseecom_client *client, size_t size, - void *cpu_addr, dma_addr_t dma_handle) -{ - return dma_free_coherent(qseecom_scm_dev(client), size, cpu_addr, dma_handle); -} - -/** * qcom_qseecom_app_send() - Send to and receive data from a given QSEE app. * @client: The QSEECOM client associated with the target app. - * @req: DMA address of the request buffer sent to the app. + * @req: Request buffer sent to the app (must be TZ memory). * @req_size: Size of the request buffer. - * @rsp: DMA address of the response buffer, written to by the app. + * @rsp: Response buffer, written to by the app (must be TZ memory). * @rsp_size: Size of the response buffer. * * Sends a request to the QSEE app associated with the given client and read @@ -90,8 +45,8 @@ static inline void qseecom_dma_free(struct qseecom_client *client, size_t size, * Return: Zero on success, nonzero on failure. */ static inline int qcom_qseecom_app_send(struct qseecom_client *client, - dma_addr_t req, size_t req_size, - dma_addr_t rsp, size_t rsp_size) + void *req, size_t req_size, + void *rsp, size_t rsp_size) { return qcom_scm_qseecom_app_send(client->app_id, req, req_size, rsp, rsp_size); } diff --git a/include/linux/firmware/qcom/qcom_scm.h b/include/linux/firmware/qcom/qcom_scm.h index aaa19f93ac43..983e1591bbba 100644 --- a/include/linux/firmware/qcom/qcom_scm.h +++ b/include/linux/firmware/qcom/qcom_scm.h @@ -85,6 +85,8 @@ int qcom_scm_io_writel(phys_addr_t addr, unsigned int val); bool qcom_scm_restore_sec_cfg_available(void); int qcom_scm_restore_sec_cfg(u32 device_id, u32 spare); +int qcom_scm_set_gpu_smmu_aperture(unsigned int context_bank); +bool qcom_scm_set_gpu_smmu_aperture_is_available(void); int qcom_scm_iommu_secure_ptbl_size(u32 spare, size_t *size); int qcom_scm_iommu_secure_ptbl_init(u64 addr, u32 size, u32 spare); int qcom_scm_iommu_set_cp_pool_size(u32 spare, u32 size); @@ -103,6 +105,14 @@ bool qcom_scm_ice_available(void); int qcom_scm_ice_invalidate_key(u32 index); int qcom_scm_ice_set_key(u32 index, const u8 *key, u32 key_size, enum qcom_scm_ice_cipher cipher, u32 data_unit_size); +bool qcom_scm_has_wrapped_key_support(void); +int qcom_scm_derive_sw_secret(const u8 *eph_key, size_t eph_key_size, + u8 *sw_secret, size_t sw_secret_size); +int qcom_scm_generate_ice_key(u8 *lt_key, size_t lt_key_size); +int qcom_scm_prepare_ice_key(const u8 *lt_key, size_t lt_key_size, + u8 *eph_key, size_t eph_key_size); +int qcom_scm_import_ice_key(const u8 *raw_key, size_t raw_key_size, + u8 *lt_key, size_t lt_key_size); bool qcom_scm_hdcp_available(void); int qcom_scm_hdcp_req(struct qcom_scm_hdcp_req *req, u32 req_cnt, u32 *resp); @@ -115,11 +125,40 @@ int qcom_scm_lmh_dcvsh(u32 payload_fn, u32 payload_reg, u32 payload_val, int qcom_scm_lmh_profile_change(u32 profile_id); bool qcom_scm_lmh_dcvsh_available(void); +/* + * Request TZ to program set of access controlled registers necessary + * irrespective of any features + */ +#define QCOM_SCM_GPU_ALWAYS_EN_REQ BIT(0) +/* + * Request TZ to program BCL id to access controlled register when BCL is + * enabled + */ +#define QCOM_SCM_GPU_BCL_EN_REQ BIT(1) +/* + * Request TZ to program set of access controlled register for CLX feature + * when enabled + */ +#define QCOM_SCM_GPU_CLX_EN_REQ BIT(2) +/* + * Request TZ to program tsense ids to access controlled registers for reading + * gpu temperature sensors + */ +#define QCOM_SCM_GPU_TSENSE_EN_REQ BIT(3) + +int qcom_scm_gpu_init_regs(u32 gpu_req); + +int qcom_scm_shm_bridge_enable(void); +int qcom_scm_shm_bridge_create(struct device *dev, u64 pfn_and_ns_perm_flags, + u64 ipfn_and_s_perm_flags, u64 size_and_flags, + u64 ns_vmids, u64 *handle); +int qcom_scm_shm_bridge_delete(struct device *dev, u64 handle); + #ifdef CONFIG_QCOM_QSEECOM int qcom_scm_qseecom_app_get_id(const char *app_name, u32 *app_id); -int qcom_scm_qseecom_app_send(u32 app_id, dma_addr_t req, size_t req_size, - dma_addr_t rsp, size_t rsp_size); +int qcom_scm_qseecom_app_send(u32 app_id, void *req, size_t req_size, + void *rsp, size_t rsp_size); #else /* CONFIG_QCOM_QSEECOM */ @@ -129,8 +168,8 @@ static inline int qcom_scm_qseecom_app_get_id(const char *app_name, u32 *app_id) } static inline int qcom_scm_qseecom_app_send(u32 app_id, - dma_addr_t req, size_t req_size, - dma_addr_t rsp, size_t rsp_size) + void *req, size_t req_size, + void *rsp, size_t rsp_size) { return -EINVAL; } diff --git a/include/linux/firmware/qcom/qcom_tzmem.h b/include/linux/firmware/qcom/qcom_tzmem.h new file mode 100644 index 000000000000..b83b63a0c049 --- /dev/null +++ b/include/linux/firmware/qcom/qcom_tzmem.h @@ -0,0 +1,56 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2023-2024 Linaro Ltd. + */ + +#ifndef __QCOM_TZMEM_H +#define __QCOM_TZMEM_H + +#include <linux/cleanup.h> +#include <linux/gfp.h> +#include <linux/types.h> + +struct device; +struct qcom_tzmem_pool; + +/** + * enum qcom_tzmem_policy - Policy for pool growth. + */ +enum qcom_tzmem_policy { + /**< Static pool, never grow above initial size. */ + QCOM_TZMEM_POLICY_STATIC = 1, + /**< When out of memory, add increment * current size of memory. */ + QCOM_TZMEM_POLICY_MULTIPLIER, + /**< When out of memory add as much as is needed until max_size. */ + QCOM_TZMEM_POLICY_ON_DEMAND, +}; + +/** + * struct qcom_tzmem_pool_config - TZ memory pool configuration. + * @initial_size: Number of bytes to allocate for the pool during its creation. + * @policy: Pool size growth policy. + * @increment: Used with policies that allow pool growth. + * @max_size: Size above which the pool will never grow. + */ +struct qcom_tzmem_pool_config { + size_t initial_size; + enum qcom_tzmem_policy policy; + size_t increment; + size_t max_size; +}; + +struct qcom_tzmem_pool * +qcom_tzmem_pool_new(const struct qcom_tzmem_pool_config *config); +void qcom_tzmem_pool_free(struct qcom_tzmem_pool *pool); +struct qcom_tzmem_pool * +devm_qcom_tzmem_pool_new(struct device *dev, + const struct qcom_tzmem_pool_config *config); + +void *qcom_tzmem_alloc(struct qcom_tzmem_pool *pool, size_t size, gfp_t gfp); +void qcom_tzmem_free(void *ptr); + +DEFINE_FREE(qcom_tzmem, void *, if (_T) qcom_tzmem_free(_T)) + +phys_addr_t qcom_tzmem_to_phys(void *ptr); + +#endif /* __QCOM_TZMEM */ diff --git a/include/linux/firmware/xlnx-event-manager.h b/include/linux/firmware/xlnx-event-manager.h index 82e8254b0f80..645dd34155e6 100644 --- a/include/linux/firmware/xlnx-event-manager.h +++ b/include/linux/firmware/xlnx-event-manager.h @@ -1,4 +1,9 @@ /* SPDX-License-Identifier: GPL-2.0 */ +/* + * Xilinx Event Management Driver + * + * Copyright (C) 2024, Advanced Micro Devices, Inc. + */ #ifndef _FIRMWARE_XLNX_EVENT_MANAGER_H_ #define _FIRMWARE_XLNX_EVENT_MANAGER_H_ @@ -7,6 +12,11 @@ #define CB_MAX_PAYLOAD_SIZE (4U) /*In payload maximum 32bytes */ +#define EVENT_SUBSYSTEM_RESTART (4U) + +#define PM_DEV_ACPU_0_0 (0x1810c0afU) +#define PM_DEV_ACPU_0 (0x1810c003U) + /************************** Exported Function *****************************/ typedef void (*event_cb_func_t)(const u32 *payload, void *data); diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 1a069a56c961..6d4dbc196b93 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -3,7 +3,7 @@ * Xilinx Zynq MPSoC Firmware layer * * Copyright (C) 2014-2021 Xilinx - * Copyright (C) 2022 - 2023, Advanced Micro Devices, Inc. + * Copyright (C) 2022 - 2024, Advanced Micro Devices, Inc. * * Michal Simek <michal.simek@amd.com> * Davorin Mista <davorin.mista@aggios.com> @@ -32,6 +32,19 @@ /* SMC SIP service Call Function Identifier Prefix */ #define PM_SIP_SVC 0xC2000000 +/* SMC function ID to get SiP SVC version */ +#define GET_SIP_SVC_VERSION (0x8200ff03U) + +/* SiP Service Calls version numbers */ +#define SIP_SVC_VERSION_MAJOR (0U) +#define SIP_SVC_VERSION_MINOR (2U) + +#define SIP_SVC_PASSTHROUGH_VERSION ((SIP_SVC_VERSION_MAJOR << 16) | \ + SIP_SVC_VERSION_MINOR) + +/* Fixed ID for FW specific APIs */ +#define PASS_THROUGH_FW_CMD_ID GENMASK(11, 0) + /* PM API versions */ #define PM_API_VERSION_1 1 #define PM_API_VERSION_2 2 @@ -51,6 +64,10 @@ #define API_ID_MASK GENMASK(7, 0) #define MODULE_ID_MASK GENMASK(11, 8) +#define PLM_MODULE_ID_MASK GENMASK(15, 8) + +/* Firmware feature check version mask */ +#define FIRMWARE_VERSION_MASK 0xFFFFU /* ATF only commands */ #define TF_A_PM_REGISTER_SGI 0xa04 @@ -59,7 +76,13 @@ #define GET_CALLBACK_DATA 0xa01 /* Number of 32bits values in payload */ -#define PAYLOAD_ARG_CNT 4U +#define PAYLOAD_ARG_CNT 7U + +/* Number of 64bits arguments for SMC call */ +#define SMC_ARG_CNT_64 8U + +/* Number of 32bits arguments for SMC call */ +#define SMC_ARG_CNT_32 13U /* Number of arguments for a callback */ #define CB_ARG_CNT 4 @@ -127,6 +150,7 @@ enum pm_module_id { PM_MODULE_ID = 0x0, + XPM_MODULE_ID = 0x2, XSEM_MODULE_ID = 0x3, TF_A_MODULE_ID = 0xa, }; @@ -215,9 +239,13 @@ enum pm_ioctl_id { /* Runtime feature configuration */ IOCTL_SET_FEATURE_CONFIG = 26, IOCTL_GET_FEATURE_CONFIG = 27, + /* IOCTL for Secure Read/Write Interface */ + IOCTL_READ_REG = 28, /* Dynamic SD/GEM configuration */ IOCTL_SET_SD_CONFIG = 30, IOCTL_SET_GEM_CONFIG = 31, + /* IOCTL to get default/current QoS */ + IOCTL_GET_QOS = 34, }; enum pm_query_id { @@ -235,6 +263,7 @@ enum pm_query_id { PM_QID_PINCTRL_GET_PIN_GROUPS = 11, PM_QID_CLOCK_GET_NUM_CLOCKS = 12, PM_QID_CLOCK_GET_MAX_DIVISOR = 13, + PM_QID_PINCTRL_GET_ATTRIBUTES = 15, }; enum rpu_oper_mode { @@ -530,6 +559,7 @@ struct zynqmp_pm_query_data { }; int zynqmp_pm_invoke_fn(u32 pm_api_id, u32 *ret_payload, u32 num_args, ...); +int zynqmp_pm_invoke_fw_fn(u32 pm_api_id, u32 *ret_payload, u32 num_args, ...); #if IS_REACHABLE(CONFIG_ZYNQMP_FIRMWARE) int zynqmp_pm_get_api_version(u32 *version); @@ -550,9 +580,9 @@ int zynqmp_pm_get_pll_frac_data(u32 clk_id, u32 *data); int zynqmp_pm_set_sd_tapdelay(u32 node_id, u32 type, u32 value); int zynqmp_pm_sd_dll_reset(u32 node_id, u32 type); int zynqmp_pm_ospi_mux_select(u32 dev_id, u32 select); -int zynqmp_pm_reset_assert(const enum zynqmp_pm_reset reset, +int zynqmp_pm_reset_assert(const u32 reset, const enum zynqmp_pm_reset_action assert_flag); -int zynqmp_pm_reset_get_status(const enum zynqmp_pm_reset reset, u32 *status); +int zynqmp_pm_reset_get_status(const u32 reset, u32 *status); unsigned int zynqmp_pm_bootmode_read(u32 *ps_mode); int zynqmp_pm_bootmode_write(u32 ps_mode); int zynqmp_pm_init_finalize(void); @@ -695,14 +725,13 @@ static inline int zynqmp_pm_ospi_mux_select(u32 dev_id, u32 select) return -ENODEV; } -static inline int zynqmp_pm_reset_assert(const enum zynqmp_pm_reset reset, +static inline int zynqmp_pm_reset_assert(const u32 reset, const enum zynqmp_pm_reset_action assert_flag) { return -ENODEV; } -static inline int zynqmp_pm_reset_get_status(const enum zynqmp_pm_reset reset, - u32 *status) +static inline int zynqmp_pm_reset_get_status(const u32 reset, u32 *status) { return -ENODEV; } diff --git a/include/linux/folio_queue.h b/include/linux/folio_queue.h new file mode 100644 index 000000000000..4d3f8074c137 --- /dev/null +++ b/include/linux/folio_queue.h @@ -0,0 +1,330 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* Queue of folios definitions + * + * Copyright (C) 2024 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * See: + * + * Documentation/core-api/folio_queue.rst + * + * for a description of the API. + */ + +#ifndef _LINUX_FOLIO_QUEUE_H +#define _LINUX_FOLIO_QUEUE_H + +#include <linux/pagevec.h> + +/* + * Segment in a queue of running buffers. Each segment can hold a number of + * folios and a portion of the queue can be referenced with the ITER_FOLIOQ + * iterator. The possibility exists of inserting non-folio elements into the + * queue (such as gaps). + * + * Explicit prev and next pointers are used instead of a list_head to make it + * easier to add segments to tail and remove them from the head without the + * need for a lock. + */ +struct folio_queue { + struct folio_batch vec; /* Folios in the queue segment */ + u8 orders[PAGEVEC_SIZE]; /* Order of each folio */ + struct folio_queue *next; /* Next queue segment or NULL */ + struct folio_queue *prev; /* Previous queue segment of NULL */ + unsigned long marks; /* 1-bit mark per folio */ + unsigned long marks2; /* Second 1-bit mark per folio */ + unsigned long marks3; /* Third 1-bit mark per folio */ +#if PAGEVEC_SIZE > BITS_PER_LONG +#error marks is not big enough +#endif + unsigned int rreq_id; + unsigned int debug_id; +}; + +/** + * folioq_init - Initialise a folio queue segment + * @folioq: The segment to initialise + * @rreq_id: The request identifier to use in tracelines. + * + * Initialise a folio queue segment and set an identifier to be used in traces. + * + * Note that the folio pointers are left uninitialised. + */ +static inline void folioq_init(struct folio_queue *folioq, unsigned int rreq_id) +{ + folio_batch_init(&folioq->vec); + folioq->next = NULL; + folioq->prev = NULL; + folioq->marks = 0; + folioq->marks2 = 0; + folioq->marks3 = 0; + folioq->rreq_id = rreq_id; + folioq->debug_id = 0; +} + +/** + * folioq_nr_slots: Query the capacity of a folio queue segment + * @folioq: The segment to query + * + * Query the number of folios that a particular folio queue segment might hold. + * [!] NOTE: This must not be assumed to be the same for every segment! + */ +static inline unsigned int folioq_nr_slots(const struct folio_queue *folioq) +{ + return PAGEVEC_SIZE; +} + +/** + * folioq_count: Query the occupancy of a folio queue segment + * @folioq: The segment to query + * + * Query the number of folios that have been added to a folio queue segment. + * Note that this is not decreased as folios are removed from a segment. + */ +static inline unsigned int folioq_count(struct folio_queue *folioq) +{ + return folio_batch_count(&folioq->vec); +} + +/** + * folioq_full: Query if a folio queue segment is full + * @folioq: The segment to query + * + * Query if a folio queue segment is fully occupied. Note that this does not + * change if folios are removed from a segment. + */ +static inline bool folioq_full(struct folio_queue *folioq) +{ + //return !folio_batch_space(&folioq->vec); + return folioq_count(folioq) >= folioq_nr_slots(folioq); +} + +/** + * folioq_is_marked: Check first folio mark in a folio queue segment + * @folioq: The segment to query + * @slot: The slot number of the folio to query + * + * Determine if the first mark is set for the folio in the specified slot in a + * folio queue segment. + */ +static inline bool folioq_is_marked(const struct folio_queue *folioq, unsigned int slot) +{ + return test_bit(slot, &folioq->marks); +} + +/** + * folioq_mark: Set the first mark on a folio in a folio queue segment + * @folioq: The segment to modify + * @slot: The slot number of the folio to modify + * + * Set the first mark for the folio in the specified slot in a folio queue + * segment. + */ +static inline void folioq_mark(struct folio_queue *folioq, unsigned int slot) +{ + set_bit(slot, &folioq->marks); +} + +/** + * folioq_unmark: Clear the first mark on a folio in a folio queue segment + * @folioq: The segment to modify + * @slot: The slot number of the folio to modify + * + * Clear the first mark for the folio in the specified slot in a folio queue + * segment. + */ +static inline void folioq_unmark(struct folio_queue *folioq, unsigned int slot) +{ + clear_bit(slot, &folioq->marks); +} + +/** + * folioq_is_marked2: Check second folio mark in a folio queue segment + * @folioq: The segment to query + * @slot: The slot number of the folio to query + * + * Determine if the second mark is set for the folio in the specified slot in a + * folio queue segment. + */ +static inline bool folioq_is_marked2(const struct folio_queue *folioq, unsigned int slot) +{ + return test_bit(slot, &folioq->marks2); +} + +/** + * folioq_mark2: Set the second mark on a folio in a folio queue segment + * @folioq: The segment to modify + * @slot: The slot number of the folio to modify + * + * Set the second mark for the folio in the specified slot in a folio queue + * segment. + */ +static inline void folioq_mark2(struct folio_queue *folioq, unsigned int slot) +{ + set_bit(slot, &folioq->marks2); +} + +/** + * folioq_unmark2: Clear the second mark on a folio in a folio queue segment + * @folioq: The segment to modify + * @slot: The slot number of the folio to modify + * + * Clear the second mark for the folio in the specified slot in a folio queue + * segment. + */ +static inline void folioq_unmark2(struct folio_queue *folioq, unsigned int slot) +{ + clear_bit(slot, &folioq->marks2); +} + +/** + * folioq_is_marked3: Check third folio mark in a folio queue segment + * @folioq: The segment to query + * @slot: The slot number of the folio to query + * + * Determine if the third mark is set for the folio in the specified slot in a + * folio queue segment. + */ +static inline bool folioq_is_marked3(const struct folio_queue *folioq, unsigned int slot) +{ + return test_bit(slot, &folioq->marks3); +} + +/** + * folioq_mark3: Set the third mark on a folio in a folio queue segment + * @folioq: The segment to modify + * @slot: The slot number of the folio to modify + * + * Set the third mark for the folio in the specified slot in a folio queue + * segment. + */ +static inline void folioq_mark3(struct folio_queue *folioq, unsigned int slot) +{ + set_bit(slot, &folioq->marks3); +} + +/** + * folioq_unmark3: Clear the third mark on a folio in a folio queue segment + * @folioq: The segment to modify + * @slot: The slot number of the folio to modify + * + * Clear the third mark for the folio in the specified slot in a folio queue + * segment. + */ +static inline void folioq_unmark3(struct folio_queue *folioq, unsigned int slot) +{ + clear_bit(slot, &folioq->marks3); +} + +static inline unsigned int __folio_order(struct folio *folio) +{ + if (!folio_test_large(folio)) + return 0; + return folio->_flags_1 & 0xff; +} + +/** + * folioq_append: Add a folio to a folio queue segment + * @folioq: The segment to add to + * @folio: The folio to add + * + * Add a folio to the tail of the sequence in a folio queue segment, increasing + * the occupancy count and returning the slot number for the folio just added. + * The folio size is extracted and stored in the queue and the marks are left + * unmodified. + * + * Note that it's left up to the caller to check that the segment capacity will + * not be exceeded and to extend the queue. + */ +static inline unsigned int folioq_append(struct folio_queue *folioq, struct folio *folio) +{ + unsigned int slot = folioq->vec.nr++; + + folioq->vec.folios[slot] = folio; + folioq->orders[slot] = __folio_order(folio); + return slot; +} + +/** + * folioq_append_mark: Add a folio to a folio queue segment + * @folioq: The segment to add to + * @folio: The folio to add + * + * Add a folio to the tail of the sequence in a folio queue segment, increasing + * the occupancy count and returning the slot number for the folio just added. + * The folio size is extracted and stored in the queue, the first mark is set + * and and the second and third marks are left unmodified. + * + * Note that it's left up to the caller to check that the segment capacity will + * not be exceeded and to extend the queue. + */ +static inline unsigned int folioq_append_mark(struct folio_queue *folioq, struct folio *folio) +{ + unsigned int slot = folioq->vec.nr++; + + folioq->vec.folios[slot] = folio; + folioq->orders[slot] = __folio_order(folio); + folioq_mark(folioq, slot); + return slot; +} + +/** + * folioq_folio: Get a folio from a folio queue segment + * @folioq: The segment to access + * @slot: The folio slot to access + * + * Retrieve the folio in the specified slot from a folio queue segment. Note + * that no bounds check is made and if the slot hasn't been added into yet, the + * pointer will be undefined. If the slot has been cleared, NULL will be + * returned. + */ +static inline struct folio *folioq_folio(const struct folio_queue *folioq, unsigned int slot) +{ + return folioq->vec.folios[slot]; +} + +/** + * folioq_folio_order: Get the order of a folio from a folio queue segment + * @folioq: The segment to access + * @slot: The folio slot to access + * + * Retrieve the order of the folio in the specified slot from a folio queue + * segment. Note that no bounds check is made and if the slot hasn't been + * added into yet, the order returned will be 0. + */ +static inline unsigned int folioq_folio_order(const struct folio_queue *folioq, unsigned int slot) +{ + return folioq->orders[slot]; +} + +/** + * folioq_folio_size: Get the size of a folio from a folio queue segment + * @folioq: The segment to access + * @slot: The folio slot to access + * + * Retrieve the size of the folio in the specified slot from a folio queue + * segment. Note that no bounds check is made and if the slot hasn't been + * added into yet, the size returned will be PAGE_SIZE. + */ +static inline size_t folioq_folio_size(const struct folio_queue *folioq, unsigned int slot) +{ + return PAGE_SIZE << folioq_folio_order(folioq, slot); +} + +/** + * folioq_clear: Clear a folio from a folio queue segment + * @folioq: The segment to clear + * @slot: The folio slot to clear + * + * Clear a folio from a sequence in a folio queue segment and clear its marks. + * The occupancy count is left unchanged. + */ +static inline void folioq_clear(struct folio_queue *folioq, unsigned int slot) +{ + folioq->vec.folios[slot] = NULL; + folioq_unmark(folioq, slot); + folioq_unmark2(folioq, slot); + folioq_unmark3(folioq, slot); +} + +#endif /* _LINUX_FOLIO_QUEUE_H */ diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index 6aeebe0a6777..e4ce1cae03bf 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -15,10 +15,14 @@ #define FORTIFY_REASON(func, write) (FIELD_PREP(BIT(0), write) | \ FIELD_PREP(GENMASK(7, 1), func)) +/* Overridden by KUnit tests. */ #ifndef fortify_panic # define fortify_panic(func, write, avail, size, retfail) \ __fortify_panic(FORTIFY_REASON(func, write), avail, size) #endif +#ifndef fortify_warn_once +# define fortify_warn_once(x...) WARN_ONCE(x) +#endif #define FORTIFY_READ 0 #define FORTIFY_WRITE 1 @@ -71,17 +75,30 @@ void __write_overflow_field(size_t avail, size_t wanted) __compiletime_warning(" __ret; \ }) -#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) +#if defined(__SANITIZE_ADDRESS__) + +#if !defined(CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX) && !defined(CONFIG_GENERIC_ENTRY) +extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(memset); +extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(memmove); +extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(memcpy); +#elif defined(CONFIG_KASAN_GENERIC) +extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(__asan_memset); +extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(__asan_memmove); +extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(__asan_memcpy); +#else /* CONFIG_KASAN_SW_TAGS */ +extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(__hwasan_memset); +extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(__hwasan_memmove); +extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(__hwasan_memcpy); +#endif + extern void *__underlying_memchr(const void *p, int c, __kernel_size_t size) __RENAME(memchr); extern int __underlying_memcmp(const void *p, const void *q, __kernel_size_t size) __RENAME(memcmp); -extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(memcpy); -extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(memmove); -extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(memset); extern char *__underlying_strcat(char *p, const char *q) __RENAME(strcat); extern char *__underlying_strcpy(char *p, const char *q) __RENAME(strcpy); extern __kernel_size_t __underlying_strlen(const char *p) __RENAME(strlen); extern char *__underlying_strncat(char *p, const char *q, __kernel_size_t count) __RENAME(strncat); extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) __RENAME(strncpy); + #else #if defined(__SANITIZE_MEMORY__) @@ -106,6 +123,7 @@ extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) #define __underlying_strlen __builtin_strlen #define __underlying_strncat __builtin_strncat #define __underlying_strncpy __builtin_strncpy + #endif /** @@ -583,11 +601,7 @@ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size, /* * Warn when writing beyond destination field size. * - * We must ignore p_size_field == 0 for existing 0-element - * fake flexible arrays, until they are all converted to - * proper flexible arrays. - * - * The implementation of __builtin_*object_size() behaves + * Note the implementation of __builtin_*object_size() behaves * like sizeof() when not directly referencing a flexible * array member, which means there will be many bounds checks * that will appear at run-time, without a way for them to be @@ -595,13 +609,19 @@ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size, * is specifically the flexible array member). * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=101832 */ - if (p_size_field != 0 && p_size_field != SIZE_MAX && + if (p_size_field != SIZE_MAX && p_size != p_size_field && p_size_field < size) return true; return false; } +/* + * To work around what seems to be an optimizer bug, the macro arguments + * need to have const copies or the values end up changed by the time they + * reach fortify_warn_once(). See commit 6f7630b1b5bc ("fortify: Capture + * __bos() results in const temp vars") for more details. + */ #define __fortify_memcpy_chk(p, q, size, p_size, q_size, \ p_size_field, q_size_field, op) ({ \ const size_t __fortify_size = (size_t)(size); \ @@ -609,14 +629,20 @@ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size, const size_t __q_size = (q_size); \ const size_t __p_size_field = (p_size_field); \ const size_t __q_size_field = (q_size_field); \ - WARN_ONCE(fortify_memcpy_chk(__fortify_size, __p_size, \ + /* Keep a mutable version of the size for the final copy. */ \ + size_t __copy_size = __fortify_size; \ + fortify_warn_once(fortify_memcpy_chk(__fortify_size, __p_size, \ __q_size, __p_size_field, \ __q_size_field, FORTIFY_FUNC_ ##op), \ #op ": detected field-spanning write (size %zu) of single %s (size %zu)\n", \ __fortify_size, \ "field \"" #p "\" at " FILE_LINE, \ __p_size_field); \ - __underlying_##op(p, q, __fortify_size); \ + /* Hide only the run-time size from value range tracking to */ \ + /* silence compile-time false positive bounds warnings. */ \ + if (!__builtin_constant_p(__copy_size)) \ + OPTIMIZER_HIDE_VAR(__copy_size); \ + __underlying_##op(p, q, __copy_size); \ }) /* @@ -725,18 +751,20 @@ __FORTIFY_INLINE void *memchr_inv(const void * const POS0 p, int c, size_t size) return __real_memchr_inv(p, c, size); } -extern void *__real_kmemdup(const void *src, size_t len, gfp_t gfp) __RENAME(kmemdup) +extern void *__real_kmemdup(const void *src, size_t len, gfp_t gfp) __RENAME(kmemdup_noprof) __realloc_size(2); -__FORTIFY_INLINE void *kmemdup(const void * const POS0 p, size_t size, gfp_t gfp) +__FORTIFY_INLINE void *kmemdup_noprof(const void * const POS0 p, size_t size, gfp_t gfp) { const size_t p_size = __struct_size(p); if (__compiletime_lessthan(p_size, size)) __read_overflow(); if (p_size < size) - fortify_panic(FORTIFY_FUNC_kmemdup, FORTIFY_READ, p_size, size, NULL); + fortify_panic(FORTIFY_FUNC_kmemdup, FORTIFY_READ, p_size, size, + __real_kmemdup(p, 0, gfp)); return __real_kmemdup(p, size, gfp); } +#define kmemdup(...) alloc_hooks(kmemdup_noprof(__VA_ARGS__)) /** * strcpy - Copy a string into another string buffer diff --git a/include/linux/fpga/fpga-bridge.h b/include/linux/fpga/fpga-bridge.h index 223da48a6d18..94c4edd047e5 100644 --- a/include/linux/fpga/fpga-bridge.h +++ b/include/linux/fpga/fpga-bridge.h @@ -45,6 +45,7 @@ struct fpga_bridge_info { * @dev: FPGA bridge device * @mutex: enforces exclusive reference to bridge * @br_ops: pointer to struct of FPGA bridge ops + * @br_ops_owner: module containing the br_ops * @info: fpga image specific information * @node: FPGA bridge list node * @priv: low level driver private date @@ -54,6 +55,7 @@ struct fpga_bridge { struct device dev; struct mutex mutex; /* for exclusive reference to bridge */ const struct fpga_bridge_ops *br_ops; + struct module *br_ops_owner; struct fpga_image_info *info; struct list_head node; void *priv; @@ -79,10 +81,12 @@ int of_fpga_bridge_get_to_list(struct device_node *np, struct fpga_image_info *info, struct list_head *bridge_list); +#define fpga_bridge_register(parent, name, br_ops, priv) \ + __fpga_bridge_register(parent, name, br_ops, priv, THIS_MODULE) struct fpga_bridge * -fpga_bridge_register(struct device *parent, const char *name, - const struct fpga_bridge_ops *br_ops, - void *priv); +__fpga_bridge_register(struct device *parent, const char *name, + const struct fpga_bridge_ops *br_ops, void *priv, + struct module *owner); void fpga_bridge_unregister(struct fpga_bridge *br); #endif /* _LINUX_FPGA_BRIDGE_H */ diff --git a/include/linux/fpga/fpga-mgr.h b/include/linux/fpga/fpga-mgr.h index 54f63459efd6..0d4fe068f3d8 100644 --- a/include/linux/fpga/fpga-mgr.h +++ b/include/linux/fpga/fpga-mgr.h @@ -201,6 +201,7 @@ struct fpga_manager_ops { * @state: state of fpga manager * @compat_id: FPGA manager id for compatibility check. * @mops: pointer to struct of fpga manager ops + * @mops_owner: module containing the mops * @priv: low level driver private date */ struct fpga_manager { @@ -210,6 +211,7 @@ struct fpga_manager { enum fpga_mgr_states state; struct fpga_compat_id *compat_id; const struct fpga_manager_ops *mops; + struct module *mops_owner; void *priv; }; @@ -230,18 +232,30 @@ struct fpga_manager *fpga_mgr_get(struct device *dev); void fpga_mgr_put(struct fpga_manager *mgr); +#define fpga_mgr_register_full(parent, info) \ + __fpga_mgr_register_full(parent, info, THIS_MODULE) struct fpga_manager * -fpga_mgr_register_full(struct device *parent, const struct fpga_manager_info *info); +__fpga_mgr_register_full(struct device *parent, const struct fpga_manager_info *info, + struct module *owner); +#define fpga_mgr_register(parent, name, mops, priv) \ + __fpga_mgr_register(parent, name, mops, priv, THIS_MODULE) struct fpga_manager * -fpga_mgr_register(struct device *parent, const char *name, - const struct fpga_manager_ops *mops, void *priv); +__fpga_mgr_register(struct device *parent, const char *name, + const struct fpga_manager_ops *mops, void *priv, struct module *owner); + void fpga_mgr_unregister(struct fpga_manager *mgr); +#define devm_fpga_mgr_register_full(parent, info) \ + __devm_fpga_mgr_register_full(parent, info, THIS_MODULE) struct fpga_manager * -devm_fpga_mgr_register_full(struct device *parent, const struct fpga_manager_info *info); +__devm_fpga_mgr_register_full(struct device *parent, const struct fpga_manager_info *info, + struct module *owner); +#define devm_fpga_mgr_register(parent, name, mops, priv) \ + __devm_fpga_mgr_register(parent, name, mops, priv, THIS_MODULE) struct fpga_manager * -devm_fpga_mgr_register(struct device *parent, const char *name, - const struct fpga_manager_ops *mops, void *priv); +__devm_fpga_mgr_register(struct device *parent, const char *name, + const struct fpga_manager_ops *mops, void *priv, + struct module *owner); #endif /*_LINUX_FPGA_MGR_H */ diff --git a/include/linux/fpga/fpga-region.h b/include/linux/fpga/fpga-region.h index 9d4d32909340..5fbc05fe70a6 100644 --- a/include/linux/fpga/fpga-region.h +++ b/include/linux/fpga/fpga-region.h @@ -36,6 +36,7 @@ struct fpga_region_info { * @mgr: FPGA manager * @info: FPGA image info * @compat_id: FPGA region id for compatibility check. + * @ops_owner: module containing the get_bridges function * @priv: private data * @get_bridges: optional function to get bridges to a list */ @@ -46,6 +47,7 @@ struct fpga_region { struct fpga_manager *mgr; struct fpga_image_info *info; struct fpga_compat_id *compat_id; + struct module *ops_owner; void *priv; int (*get_bridges)(struct fpga_region *region); }; @@ -58,12 +60,17 @@ fpga_region_class_find(struct device *start, const void *data, int fpga_region_program_fpga(struct fpga_region *region); +#define fpga_region_register_full(parent, info) \ + __fpga_region_register_full(parent, info, THIS_MODULE) struct fpga_region * -fpga_region_register_full(struct device *parent, const struct fpga_region_info *info); +__fpga_region_register_full(struct device *parent, const struct fpga_region_info *info, + struct module *owner); +#define fpga_region_register(parent, mgr, get_bridges) \ + __fpga_region_register(parent, mgr, get_bridges, THIS_MODULE) struct fpga_region * -fpga_region_register(struct device *parent, struct fpga_manager *mgr, - int (*get_bridges)(struct fpga_region *)); +__fpga_region_register(struct device *parent, struct fpga_manager *mgr, + int (*get_bridges)(struct fpga_region *), struct module *owner); void fpga_region_unregister(struct fpga_region *region); #endif /* _FPGA_REGION_H */ diff --git a/include/linux/fprobe.h b/include/linux/fprobe.h index 3e03758151f4..702099f08929 100644 --- a/include/linux/fprobe.h +++ b/include/linux/fprobe.h @@ -5,41 +5,68 @@ #include <linux/compiler.h> #include <linux/ftrace.h> -#include <linux/rethook.h> +#include <linux/rcupdate.h> +#include <linux/refcount.h> +#include <linux/slab.h> + +struct fprobe; +typedef int (*fprobe_entry_cb)(struct fprobe *fp, unsigned long entry_ip, + unsigned long ret_ip, struct ftrace_regs *regs, + void *entry_data); + +typedef void (*fprobe_exit_cb)(struct fprobe *fp, unsigned long entry_ip, + unsigned long ret_ip, struct ftrace_regs *regs, + void *entry_data); + +/** + * struct fprobe_hlist_node - address based hash list node for fprobe. + * + * @hlist: The hlist node for address search hash table. + * @addr: One of the probing address of @fp. + * @fp: The fprobe which owns this. + */ +struct fprobe_hlist_node { + struct hlist_node hlist; + unsigned long addr; + struct fprobe *fp; +}; + +/** + * struct fprobe_hlist - hash list nodes for fprobe. + * + * @hlist: The hlist node for existence checking hash table. + * @rcu: rcu_head for RCU deferred release. + * @fp: The fprobe which owns this fprobe_hlist. + * @size: The size of @array. + * @array: The fprobe_hlist_node for each address to probe. + */ +struct fprobe_hlist { + struct hlist_node hlist; + struct rcu_head rcu; + struct fprobe *fp; + int size; + struct fprobe_hlist_node array[] __counted_by(size); +}; /** * struct fprobe - ftrace based probe. - * @ops: The ftrace_ops. + * * @nmissed: The counter for missing events. * @flags: The status flag. - * @rethook: The rethook data structure. (internal data) * @entry_data_size: The private data storage size. - * @nr_maxactive: The max number of active functions. * @entry_handler: The callback function for function entry. * @exit_handler: The callback function for function exit. + * @hlist_array: The fprobe_hlist for fprobe search from IP hash table. */ struct fprobe { -#ifdef CONFIG_FUNCTION_TRACER - /* - * If CONFIG_FUNCTION_TRACER is not set, CONFIG_FPROBE is disabled too. - * But user of fprobe may keep embedding the struct fprobe on their own - * code. To avoid build error, this will keep the fprobe data structure - * defined here, but remove ftrace_ops data structure. - */ - struct ftrace_ops ops; -#endif unsigned long nmissed; unsigned int flags; - struct rethook *rethook; size_t entry_data_size; - int nr_maxactive; - int (*entry_handler)(struct fprobe *fp, unsigned long entry_ip, - unsigned long ret_ip, struct pt_regs *regs, - void *entry_data); - void (*exit_handler)(struct fprobe *fp, unsigned long entry_ip, - unsigned long ret_ip, struct pt_regs *regs, - void *entry_data); + fprobe_entry_cb entry_handler; + fprobe_exit_cb exit_handler; + + struct fprobe_hlist *hlist_array; }; /* This fprobe is soft-disabled. */ @@ -115,4 +142,9 @@ static inline void enable_fprobe(struct fprobe *fp) fp->flags &= ~FPROBE_FL_DISABLED; } +/* The entry data size is 4 bits (=16) * sizeof(long) in maximum */ +#define FPROBE_DATA_SIZE_BITS 4 +#define MAX_FPROBE_DATA_SIZE_WORD ((1L << FPROBE_DATA_SIZE_BITS) - 1) +#define MAX_FPROBE_DATA_SIZE (MAX_FPROBE_DATA_SIZE_WORD * sizeof(long)) + #endif diff --git a/include/linux/fpu.h b/include/linux/fpu.h new file mode 100644 index 000000000000..2fb63e22913b --- /dev/null +++ b/include/linux/fpu.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _LINUX_FPU_H +#define _LINUX_FPU_H + +#ifdef _LINUX_FPU_COMPILATION_UNIT +#error FP code must be compiled separately. See Documentation/core-api/floating-point.rst. +#endif + +#include <asm/fpu.h> + +#endif diff --git a/include/linux/fs.h b/include/linux/fs.h index 8dfd53b52744..be3ad155ec9f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -45,6 +45,8 @@ #include <linux/slab.h> #include <linux/maple_tree.h> #include <linux/rw_hint.h> +#include <linux/file_ref.h> +#include <linux/unicode.h> #include <asm/byteorder.h> #include <uapi/linux/fs.h> @@ -73,6 +75,8 @@ struct fscrypt_inode_info; struct fscrypt_operations; struct fsverity_info; struct fsverity_operations; +struct fsnotify_mark_connector; +struct fsnotify_sb_info; struct fs_context; struct fs_parameter_spec; struct fileattr; @@ -110,23 +114,28 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, */ /* file is open for reading */ -#define FMODE_READ ((__force fmode_t)0x1) +#define FMODE_READ ((__force fmode_t)(1 << 0)) /* file is open for writing */ -#define FMODE_WRITE ((__force fmode_t)0x2) +#define FMODE_WRITE ((__force fmode_t)(1 << 1)) /* file is seekable */ -#define FMODE_LSEEK ((__force fmode_t)0x4) +#define FMODE_LSEEK ((__force fmode_t)(1 << 2)) /* file can be accessed using pread */ -#define FMODE_PREAD ((__force fmode_t)0x8) +#define FMODE_PREAD ((__force fmode_t)(1 << 3)) /* file can be accessed using pwrite */ -#define FMODE_PWRITE ((__force fmode_t)0x10) +#define FMODE_PWRITE ((__force fmode_t)(1 << 4)) /* File is opened for execution with sys_execve / sys_uselib */ -#define FMODE_EXEC ((__force fmode_t)0x20) +#define FMODE_EXEC ((__force fmode_t)(1 << 5)) /* File writes are restricted (block device specific) */ -#define FMODE_WRITE_RESTRICTED ((__force fmode_t)0x40) +#define FMODE_WRITE_RESTRICTED ((__force fmode_t)(1 << 6)) +/* File supports atomic writes */ +#define FMODE_CAN_ATOMIC_WRITE ((__force fmode_t)(1 << 7)) + +/* FMODE_* bit 8 */ + /* 32bit hashes as llseek() offset (for directories) */ -#define FMODE_32BITHASH ((__force fmode_t)0x200) +#define FMODE_32BITHASH ((__force fmode_t)(1 << 9)) /* 64bit hashes as llseek() offset (for directories) */ -#define FMODE_64BITHASH ((__force fmode_t)0x400) +#define FMODE_64BITHASH ((__force fmode_t)(1 << 10)) /* * Don't update ctime and mtime. @@ -134,60 +143,85 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, * Currently a special hack for the XFS open_by_handle ioctl, but we'll * hopefully graduate it to a proper O_CMTIME flag supported by open(2) soon. */ -#define FMODE_NOCMTIME ((__force fmode_t)0x800) +#define FMODE_NOCMTIME ((__force fmode_t)(1 << 11)) /* Expect random access pattern */ -#define FMODE_RANDOM ((__force fmode_t)0x1000) +#define FMODE_RANDOM ((__force fmode_t)(1 << 12)) -/* File is huge (eg. /dev/mem): treat loff_t as unsigned */ -#define FMODE_UNSIGNED_OFFSET ((__force fmode_t)0x2000) +/* FMODE_* bit 13 */ /* File is opened with O_PATH; almost nothing can be done with it */ -#define FMODE_PATH ((__force fmode_t)0x4000) +#define FMODE_PATH ((__force fmode_t)(1 << 14)) /* File needs atomic accesses to f_pos */ -#define FMODE_ATOMIC_POS ((__force fmode_t)0x8000) +#define FMODE_ATOMIC_POS ((__force fmode_t)(1 << 15)) /* Write access to underlying fs */ -#define FMODE_WRITER ((__force fmode_t)0x10000) +#define FMODE_WRITER ((__force fmode_t)(1 << 16)) /* Has read method(s) */ -#define FMODE_CAN_READ ((__force fmode_t)0x20000) +#define FMODE_CAN_READ ((__force fmode_t)(1 << 17)) /* Has write method(s) */ -#define FMODE_CAN_WRITE ((__force fmode_t)0x40000) +#define FMODE_CAN_WRITE ((__force fmode_t)(1 << 18)) -#define FMODE_OPENED ((__force fmode_t)0x80000) -#define FMODE_CREATED ((__force fmode_t)0x100000) +#define FMODE_OPENED ((__force fmode_t)(1 << 19)) +#define FMODE_CREATED ((__force fmode_t)(1 << 20)) /* File is stream-like */ -#define FMODE_STREAM ((__force fmode_t)0x200000) +#define FMODE_STREAM ((__force fmode_t)(1 << 21)) /* File supports DIRECT IO */ -#define FMODE_CAN_ODIRECT ((__force fmode_t)0x400000) +#define FMODE_CAN_ODIRECT ((__force fmode_t)(1 << 22)) -#define FMODE_NOREUSE ((__force fmode_t)0x800000) - -/* File supports non-exclusive O_DIRECT writes from multiple threads */ -#define FMODE_DIO_PARALLEL_WRITE ((__force fmode_t)0x1000000) +#define FMODE_NOREUSE ((__force fmode_t)(1 << 23)) /* File is embedded in backing_file object */ -#define FMODE_BACKING ((__force fmode_t)0x2000000) +#define FMODE_BACKING ((__force fmode_t)(1 << 24)) + +/* + * Together with FMODE_NONOTIFY_PERM defines which fsnotify events shouldn't be + * generated (see below) + */ +#define FMODE_NONOTIFY ((__force fmode_t)(1 << 25)) -/* File was opened by fanotify and shouldn't generate fanotify events */ -#define FMODE_NONOTIFY ((__force fmode_t)0x4000000) +/* + * Together with FMODE_NONOTIFY defines which fsnotify events shouldn't be + * generated (see below) + */ +#define FMODE_NONOTIFY_PERM ((__force fmode_t)(1 << 26)) /* File is capable of returning -EAGAIN if I/O will block */ -#define FMODE_NOWAIT ((__force fmode_t)0x8000000) +#define FMODE_NOWAIT ((__force fmode_t)(1 << 27)) /* File represents mount that needs unmounting */ -#define FMODE_NEED_UNMOUNT ((__force fmode_t)0x10000000) +#define FMODE_NEED_UNMOUNT ((__force fmode_t)(1 << 28)) /* File does not contribute to nr_files count */ -#define FMODE_NOACCOUNT ((__force fmode_t)0x20000000) +#define FMODE_NOACCOUNT ((__force fmode_t)(1 << 29)) + +/* + * The two FMODE_NONOTIFY* define which fsnotify events should not be generated + * for a file. These are the possible values of (f->f_mode & + * FMODE_FSNOTIFY_MASK) and their meaning: + * + * FMODE_NONOTIFY - suppress all (incl. non-permission) events. + * FMODE_NONOTIFY_PERM - suppress permission (incl. pre-content) events. + * FMODE_NONOTIFY | FMODE_NONOTIFY_PERM - suppress only pre-content events. + */ +#define FMODE_FSNOTIFY_MASK \ + (FMODE_NONOTIFY | FMODE_NONOTIFY_PERM) -/* File supports async buffered reads */ -#define FMODE_BUF_RASYNC ((__force fmode_t)0x40000000) +#define FMODE_FSNOTIFY_NONE(mode) \ + ((mode & FMODE_FSNOTIFY_MASK) == FMODE_NONOTIFY) +#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS +#define FMODE_FSNOTIFY_PERM(mode) \ + ((mode & FMODE_FSNOTIFY_MASK) == 0 || \ + (mode & FMODE_FSNOTIFY_MASK) == (FMODE_NONOTIFY | FMODE_NONOTIFY_PERM)) +#define FMODE_FSNOTIFY_HSM(mode) \ + ((mode & FMODE_FSNOTIFY_MASK) == 0) +#else +#define FMODE_FSNOTIFY_PERM(mode) 0 +#define FMODE_FSNOTIFY_HSM(mode) 0 +#endif -/* File supports async nowait buffered writes */ -#define FMODE_BUF_WASYNC ((__force fmode_t)0x80000000) /* * Attribute flags. These should be or-ed together to figure out what @@ -210,6 +244,7 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define ATTR_OPEN (1 << 15) /* Truncating from open(O_TRUNC) */ #define ATTR_TIMES_SET (1 << 16) #define ATTR_TOUCH (1 << 17) +#define ATTR_DELEG (1 << 18) /* Delegated attrs. Don't break write delegations */ /* * Whiteout is represented by a char device. The following constants define the @@ -319,6 +354,8 @@ struct readahead_control; #define IOCB_SYNC (__force int) RWF_SYNC #define IOCB_NOWAIT (__force int) RWF_NOWAIT #define IOCB_APPEND (__force int) RWF_APPEND +#define IOCB_ATOMIC (__force int) RWF_ATOMIC +#define IOCB_DONTCACHE (__force int) RWF_DONTCACHE /* non-RWF related bits - start at 16 */ #define IOCB_EVENTFD (1 << 16) @@ -345,6 +382,7 @@ struct readahead_control; #define IOCB_DIO_CALLER_COMP (1 << 22) /* kiocb is a read or write operation submitted by fs/aio.c. */ #define IOCB_AIO_RW (1 << 23) +#define IOCB_HAS_METADATA (1 << 24) /* for use in trace events */ #define TRACE_IOCB_STRINGS \ @@ -353,6 +391,8 @@ struct readahead_control; { IOCB_SYNC, "SYNC" }, \ { IOCB_NOWAIT, "NOWAIT" }, \ { IOCB_APPEND, "APPEND" }, \ + { IOCB_ATOMIC, "ATOMIC" }, \ + { IOCB_DONTCACHE, "DONTCACHE" }, \ { IOCB_EVENTFD, "EVENTFD"}, \ { IOCB_DIRECT, "DIRECT" }, \ { IOCB_WRITE, "WRITE" }, \ @@ -406,10 +446,10 @@ struct address_space_operations { int (*write_begin)(struct file *, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata); + struct folio **foliop, void **fsdata); int (*write_end)(struct file *, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata); + struct folio *folio, void *fsdata); /* Unfortunately this kludge is needed for FIBMAP. Don't use it */ sector_t (*bmap)(struct address_space *, sector_t); @@ -621,8 +661,8 @@ is_uncached_acl(struct posix_acl *acl) #define IOP_NOFOLLOW 0x0004 #define IOP_XATTR 0x0008 #define IOP_DEFAULT_READLINK 0x0010 - -struct fsnotify_mark_connector; +#define IOP_MGTIME 0x0020 +#define IOP_CACHED_LINK 0x0040 /* * Keep mostly read-only and often accessed (especially for @@ -664,9 +704,13 @@ struct inode { }; dev_t i_rdev; loff_t i_size; - struct timespec64 __i_atime; - struct timespec64 __i_mtime; - struct timespec64 __i_ctime; /* use inode_*_ctime accessors! */ + time64_t i_atime_sec; + time64_t i_mtime_sec; + time64_t i_ctime_sec; + u32 i_atime_nsec; + u32 i_mtime_nsec; + u32 i_ctime_nsec; + u32 i_generation; spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */ unsigned short i_bytes; u8 i_blkbits; @@ -678,7 +722,8 @@ struct inode { #endif /* Misc */ - unsigned long i_state; + u32 i_state; + /* 32-bit hole */ struct rw_semaphore i_rwsem; unsigned long dirtied_when; /* jiffies of first dirtying */ @@ -715,7 +760,10 @@ struct inode { }; struct file_lock_context *i_flctx; struct address_space i_data; - struct list_head i_devices; + union { + struct list_head i_devices; + int i_linklen; + }; union { struct pipe_inode_info *i_pipe; struct cdev *i_cdev; @@ -723,10 +771,10 @@ struct inode { unsigned i_dir_seq; }; - __u32 i_generation; #ifdef CONFIG_FSNOTIFY __u32 i_fsnotify_mask; /* all events this inode cares about */ + /* 32-bit hole reserved for expanding i_fsnotify_mask */ struct fsnotify_mark_connector __rcu *i_fsnotify_marks; #endif @@ -741,6 +789,28 @@ struct inode { void *i_private; /* fs or device private pointer */ } __randomize_layout; +static inline void inode_set_cached_link(struct inode *inode, char *link, int linklen) +{ + inode->i_link = link; + inode->i_linklen = linklen; + inode->i_opflags |= IOP_CACHED_LINK; +} + +/* + * Get bit address from inode->i_state to use with wait_var_event() + * infrastructre. + */ +#define inode_state_wait_address(inode, bit) ((char *)&(inode)->i_state + (bit)) + +struct wait_queue_head *inode_bit_waitqueue(struct wait_bit_queue_entry *wqe, + struct inode *inode, u32 bit); + +static inline void inode_wake_up_bit(struct inode *inode, u32 bit) +{ + /* Caller is responsible for correct memory barriers. */ + wake_up_var(inode_state_wait_address(inode, bit)); +} + struct timespec64 timestamp_truncate(struct timespec64 t, struct inode *inode); static inline unsigned int i_blocksize(const struct inode *node) @@ -943,6 +1013,7 @@ static inline unsigned imajor(const struct inode *inode) } struct fown_struct { + struct file *file; /* backpointer for security modules */ rwlock_t lock; /* protects pid, uid, euid fields */ struct pid *pid; /* pid or -pgrp where SIGIO should be sent */ enum pid_type pid_type; /* Kind of process group SIGIO should be sent to */ @@ -982,52 +1053,69 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index) index < ra->start + ra->size); } -/* - * f_{lock,count,pos_lock} members can be highly contended and share - * the same cacheline. f_{lock,mode} are very frequently used together - * and so share the same cacheline as well. The read-mostly - * f_{path,inode,op} are kept on a separate cacheline. +/** + * struct file - Represents a file + * @f_ref: reference count + * @f_lock: Protects f_ep, f_flags. Must not be taken from IRQ context. + * @f_mode: FMODE_* flags often used in hotpaths + * @f_op: file operations + * @f_mapping: Contents of a cacheable, mappable object. + * @private_data: filesystem or driver specific data + * @f_inode: cached inode + * @f_flags: file flags + * @f_iocb_flags: iocb flags + * @f_cred: stashed credentials of creator/opener + * @f_path: path of the file + * @f_pos_lock: lock protecting file position + * @f_pipe: specific to pipes + * @f_pos: file position + * @f_security: LSM security context of this file + * @f_owner: file owner + * @f_wb_err: writeback error + * @f_sb_err: per sb writeback errors + * @f_ep: link of all epoll hooks for this file + * @f_task_work: task work entry point + * @f_llist: work queue entrypoint + * @f_ra: file's readahead state + * @f_freeptr: Pointer used by SLAB_TYPESAFE_BY_RCU file cache (don't touch.) */ struct file { + file_ref_t f_ref; + spinlock_t f_lock; + fmode_t f_mode; + const struct file_operations *f_op; + struct address_space *f_mapping; + void *private_data; + struct inode *f_inode; + unsigned int f_flags; + unsigned int f_iocb_flags; + const struct cred *f_cred; + /* --- cacheline 1 boundary (64 bytes) --- */ + struct path f_path; union { - /* fput() uses task work when closing and freeing file (default). */ - struct callback_head f_task_work; - /* fput() must use workqueue (most kernel threads). */ - struct llist_node f_llist; - unsigned int f_iocb_flags; + /* regular files (with FMODE_ATOMIC_POS) and directories */ + struct mutex f_pos_lock; + /* pipes */ + u64 f_pipe; }; - - /* - * Protects f_ep, f_flags. - * Must not be taken from IRQ context. - */ - spinlock_t f_lock; - fmode_t f_mode; - atomic_long_t f_count; - struct mutex f_pos_lock; - loff_t f_pos; - unsigned int f_flags; - struct fown_struct f_owner; - const struct cred *f_cred; - struct file_ra_state f_ra; - struct path f_path; - struct inode *f_inode; /* cached value */ - const struct file_operations *f_op; - - u64 f_version; + loff_t f_pos; #ifdef CONFIG_SECURITY - void *f_security; + void *f_security; #endif - /* needed for tty driver, and maybe others */ - void *private_data; - + /* --- cacheline 2 boundary (128 bytes) --- */ + struct fown_struct *f_owner; + errseq_t f_wb_err; + errseq_t f_sb_err; #ifdef CONFIG_EPOLL - /* Used by fs/eventpoll.c to link all the hooks to this file */ - struct hlist_head *f_ep; -#endif /* #ifdef CONFIG_EPOLL */ - struct address_space *f_mapping; - errseq_t f_wb_err; - errseq_t f_sb_err; /* for syncfs */ + struct hlist_head *f_ep; +#endif + union { + struct callback_head f_task_work; + struct llist_node f_llist; + struct file_ra_state f_ra; + freeptr_t f_freeptr; + }; + /* --- cacheline 3 boundary (192 bytes) --- */ } __randomize_layout __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */ @@ -1035,19 +1123,19 @@ struct file_handle { __u32 handle_bytes; int handle_type; /* file identifier */ - unsigned char f_handle[]; + unsigned char f_handle[] __counted_by(handle_bytes); }; static inline struct file *get_file(struct file *f) { - atomic_long_inc(&f->f_count); + file_ref_inc(&f->f_ref); return f; } struct file *get_file_rcu(struct file __rcu **f); struct file *get_file_active(struct file **f); -#define file_count(x) atomic_long_read(&(x)->f_count) +#define file_count(f) file_ref_read(&(f)->f_ref) #define MAX_NON_LFS ((1UL<<31) - 1) @@ -1071,6 +1159,12 @@ struct file_lease; #define OFFT_OFFSET_MAX type_max(off_t) #endif +int file_f_owner_allocate(struct file *file); +static inline struct fown_struct *file_f_owner(const struct file *file) +{ + return READ_ONCE(file->f_owner); +} + extern void send_sigio(struct fown_struct *fown, int fd, int band); static inline struct inode *file_inode(const struct file *f) @@ -1119,7 +1213,7 @@ extern void __f_setown(struct file *filp, struct pid *, enum pid_type, int force extern int f_setown(struct file *filp, int who, int force); extern void f_delown(struct file *filp); extern pid_t f_getown(struct file *filp); -extern int send_sigurg(struct fown_struct *fown); +extern int send_sigurg(struct file *file); /* * sb->s_flags. Note that these mirror the equivalent MS_* flags where @@ -1177,13 +1271,15 @@ extern int send_sigurg(struct fown_struct *fown); #define SB_I_USERNS_VISIBLE 0x00000010 /* fstype already mounted */ #define SB_I_IMA_UNVERIFIABLE_SIGNATURE 0x00000020 #define SB_I_UNTRUSTED_MOUNTER 0x00000040 -#define SB_I_EVM_UNSUPPORTED 0x00000080 +#define SB_I_EVM_HMAC_UNSUPPORTED 0x00000080 #define SB_I_SKIP_SYNC 0x00000100 /* Skip superblock at global sync */ #define SB_I_PERSB_BDI 0x00000200 /* has a per-sb bdi */ #define SB_I_TS_EXPIRY_WARNED 0x00000400 /* warned about timestamp range expiry */ #define SB_I_RETIRED 0x00000800 /* superblock shouldn't be reused */ #define SB_I_NOUMASK 0x00001000 /* VFS does not apply umask */ +#define SB_I_NOIDMAP 0x00002000 /* No idmapped mounts on this superblock */ +#define SB_I_ALLOW_HSM 0x00004000 /* Allow HSM events on this superblock */ /* Possible states of 'frozen' field */ enum { @@ -1251,7 +1347,7 @@ struct super_block { /* * Keep s_fs_info, s_time_gran, s_fsnotify_mask, and - * s_fsnotify_marks together for cache efficiency. They are frequently + * s_fsnotify_info together for cache efficiency. They are frequently * accessed and rarely modified. */ void *s_fs_info; /* Filesystem private info */ @@ -1262,8 +1358,8 @@ struct super_block { time64_t s_time_min; time64_t s_time_max; #ifdef CONFIG_FSNOTIFY - __u32 s_fsnotify_mask; - struct fsnotify_mark_connector __rcu *s_fsnotify_marks; + u32 s_fsnotify_mask; + struct fsnotify_sb_info *s_fsnotify_info; #endif /* @@ -1304,12 +1400,6 @@ struct super_block { /* Number of inodes with nlink == 0 but still referenced */ atomic_long_t s_remove_count; - /* - * Number of inode/mount/sb objects that are being watched, note that - * inodes objects are currently double-accounted. - */ - atomic_long_t s_fsnotify_connectors; - /* Read-only state of the superblock is being changed */ int s_readonly_remount; @@ -1544,26 +1634,32 @@ static inline bool fsuidgid_has_mapping(struct super_block *sb, struct timespec64 current_time(struct inode *inode); struct timespec64 inode_set_ctime_current(struct inode *inode); +struct timespec64 inode_set_ctime_deleg(struct inode *inode, + struct timespec64 update); static inline time64_t inode_get_atime_sec(const struct inode *inode) { - return inode->__i_atime.tv_sec; + return inode->i_atime_sec; } static inline long inode_get_atime_nsec(const struct inode *inode) { - return inode->__i_atime.tv_nsec; + return inode->i_atime_nsec; } static inline struct timespec64 inode_get_atime(const struct inode *inode) { - return inode->__i_atime; + struct timespec64 ts = { .tv_sec = inode_get_atime_sec(inode), + .tv_nsec = inode_get_atime_nsec(inode) }; + + return ts; } static inline struct timespec64 inode_set_atime_to_ts(struct inode *inode, struct timespec64 ts) { - inode->__i_atime = ts; + inode->i_atime_sec = ts.tv_sec; + inode->i_atime_nsec = ts.tv_nsec; return ts; } @@ -1572,28 +1668,32 @@ static inline struct timespec64 inode_set_atime(struct inode *inode, { struct timespec64 ts = { .tv_sec = sec, .tv_nsec = nsec }; + return inode_set_atime_to_ts(inode, ts); } static inline time64_t inode_get_mtime_sec(const struct inode *inode) { - return inode->__i_mtime.tv_sec; + return inode->i_mtime_sec; } static inline long inode_get_mtime_nsec(const struct inode *inode) { - return inode->__i_mtime.tv_nsec; + return inode->i_mtime_nsec; } static inline struct timespec64 inode_get_mtime(const struct inode *inode) { - return inode->__i_mtime; + struct timespec64 ts = { .tv_sec = inode_get_mtime_sec(inode), + .tv_nsec = inode_get_mtime_nsec(inode) }; + return ts; } static inline struct timespec64 inode_set_mtime_to_ts(struct inode *inode, struct timespec64 ts) { - inode->__i_mtime = ts; + inode->i_mtime_sec = ts.tv_sec; + inode->i_mtime_nsec = ts.tv_nsec; return ts; } @@ -1605,28 +1705,37 @@ static inline struct timespec64 inode_set_mtime(struct inode *inode, return inode_set_mtime_to_ts(inode, ts); } +/* + * Multigrain timestamps + * + * Conditionally use fine-grained ctime and mtime timestamps when there + * are users actively observing them via getattr. The primary use-case + * for this is NFS clients that use the ctime to distinguish between + * different states of the file, and that are often fooled by multiple + * operations that occur in the same coarse-grained timer tick. + */ +#define I_CTIME_QUERIED ((u32)BIT(31)) + static inline time64_t inode_get_ctime_sec(const struct inode *inode) { - return inode->__i_ctime.tv_sec; + return inode->i_ctime_sec; } static inline long inode_get_ctime_nsec(const struct inode *inode) { - return inode->__i_ctime.tv_nsec; + return inode->i_ctime_nsec & ~I_CTIME_QUERIED; } static inline struct timespec64 inode_get_ctime(const struct inode *inode) { - return inode->__i_ctime; -} + struct timespec64 ts = { .tv_sec = inode_get_ctime_sec(inode), + .tv_nsec = inode_get_ctime_nsec(inode) }; -static inline struct timespec64 inode_set_ctime_to_ts(struct inode *inode, - struct timespec64 ts) -{ - inode->__i_ctime = ts; return ts; } +struct timespec64 inode_set_ctime_to_ts(struct inode *inode, struct timespec64 ts); + /** * inode_set_ctime - set the ctime in the inode * @inode: inode in which to set the ctime @@ -1672,7 +1781,7 @@ static inline bool __sb_start_write_trylock(struct super_block *sb, int level) #define __sb_writers_acquired(sb, lev) \ percpu_rwsem_acquire(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_) #define __sb_writers_release(sb, lev) \ - percpu_rwsem_release(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_) + percpu_rwsem_release(&(sb)->s_writers.rw_sem[(lev)-1], _THIS_IP_) /** * __sb_write_started - check if sb freeze level is held @@ -1908,7 +2017,7 @@ struct file *kernel_tmpfile_open(struct mnt_idmap *idmap, umode_t mode, int open_flag, const struct cred *cred); struct file *kernel_file_open(const struct path *path, int flags, - struct inode *inode, const struct cred *cred); + const struct cred *cred); int vfs_mkobj(struct dentry *, umode_t, int (*f)(struct dentry *, umode_t, void *), @@ -1935,6 +2044,8 @@ void inode_init_owner(struct mnt_idmap *idmap, struct inode *inode, extern bool may_open_dev(const struct path *path); umode_t mode_strip_sgid(struct mnt_idmap *idmap, const struct inode *dir, umode_t mode); +bool in_group_or_capable(struct mnt_idmap *idmap, + const struct inode *inode, vfsgid_t vfsgid); /* * This is the "filldir" function type, used by readdir() to let @@ -2003,8 +2114,11 @@ struct iov_iter; struct io_uring_cmd; struct offset_ctx; +typedef unsigned int __bitwise fop_flags_t; + struct file_operations { struct module *owner; + fop_flags_t fop_flags; loff_t (*llseek) (struct file *, loff_t, int); ssize_t (*read) (struct file *, char __user *, size_t, loff_t *); ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *); @@ -2017,7 +2131,6 @@ struct file_operations { long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long); long (*compat_ioctl) (struct file *, unsigned int, unsigned long); int (*mmap) (struct file *, struct vm_area_struct *); - unsigned long mmap_supported_flags; int (*open) (struct inode *, struct file *); int (*flush) (struct file *, fl_owner_t id); int (*release) (struct inode *, struct file *); @@ -2048,6 +2161,23 @@ struct file_operations { unsigned int poll_flags); } __randomize_layout; +/* Supports async buffered reads */ +#define FOP_BUFFER_RASYNC ((__force fop_flags_t)(1 << 0)) +/* Supports async buffered writes */ +#define FOP_BUFFER_WASYNC ((__force fop_flags_t)(1 << 1)) +/* Supports synchronous page faults for mappings */ +#define FOP_MMAP_SYNC ((__force fop_flags_t)(1 << 2)) +/* Supports non-exclusive O_DIRECT writes from multiple threads */ +#define FOP_DIO_PARALLEL_WRITE ((__force fop_flags_t)(1 << 3)) +/* Contains huge pages */ +#define FOP_HUGE_PAGES ((__force fop_flags_t)(1 << 4)) +/* Treat loff_t as unsigned (e.g., /dev/mem) */ +#define FOP_UNSIGNED_OFFSET ((__force fop_flags_t)(1 << 5)) +/* Supports asynchronous lock callbacks */ +#define FOP_ASYNC_LOCK ((__force fop_flags_t)(1 << 6)) +/* File system supports uncached read/write buffered IO */ +#define FOP_DONTCACHE ((__force fop_flags_t)(1 << 7)) + /* Wrap a directory iterator that needs exclusive inode access */ int wrap_directory_iterator(struct file *, struct dir_context *, int (*) (struct file *, struct dir_context *)); @@ -2098,18 +2228,6 @@ struct inode_operations { struct offset_ctx *(*get_offset_ctx)(struct inode *inode); } ____cacheline_aligned; -static inline ssize_t call_read_iter(struct file *file, struct kiocb *kio, - struct iov_iter *iter) -{ - return file->f_op->read_iter(kio, iter); -} - -static inline ssize_t call_write_iter(struct file *file, struct kiocb *kio, - struct iov_iter *iter) -{ - return file->f_op->write_iter(kio, iter); -} - static inline int call_mmap(struct file *file, struct vm_area_struct *vma) { return file->f_op->mmap(file, vma); @@ -2119,6 +2237,7 @@ extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); +int remap_verify_area(struct file *file, loff_t pos, loff_t len, bool write); int __generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *len, unsigned int remap_flags, @@ -2253,7 +2372,13 @@ static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags #define IS_DEADDIR(inode) ((inode)->i_flags & S_DEAD) #define IS_NOCMTIME(inode) ((inode)->i_flags & S_NOCMTIME) + +#ifdef CONFIG_SWAP #define IS_SWAPFILE(inode) ((inode)->i_flags & S_SWAPFILE) +#else +#define IS_SWAPFILE(inode) ((void)(inode), 0U) +#endif + #define IS_PRIVATE(inode) ((inode)->i_flags & S_PRIVATE) #define IS_IMA(inode) ((inode)->i_flags & S_IMA) #define IS_AUTOMOUNT(inode) ((inode)->i_flags & S_AUTOMOUNT) @@ -2351,8 +2476,6 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, * * I_REFERENCED Marks the inode as recently references on the LRU list. * - * I_DIO_WAKEUP Never set. Only used as a key for wait_on_bit(). - * * I_WB_SWITCH Cgroup bdi_writeback switching in progress. Used to * synchronize competing switching instances and to tell * wb stat updates to grab the i_pages lock. See @@ -2371,29 +2494,36 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, * * I_PINNING_FSCACHE_WB Inode is pinning an fscache object for writeback. * + * I_LRU_ISOLATING Inode is pinned being isolated from LRU without holding + * i_count. + * * Q: What is the difference between I_WILL_FREE and I_FREEING? + * + * __I_{SYNC,NEW,LRU_ISOLATING} are used to derive unique addresses to wait + * upon. There's one free address left. */ -#define I_DIRTY_SYNC (1 << 0) -#define I_DIRTY_DATASYNC (1 << 1) -#define I_DIRTY_PAGES (1 << 2) -#define __I_NEW 3 +#define __I_NEW 0 #define I_NEW (1 << __I_NEW) -#define I_WILL_FREE (1 << 4) -#define I_FREEING (1 << 5) -#define I_CLEAR (1 << 6) -#define __I_SYNC 7 +#define __I_SYNC 1 #define I_SYNC (1 << __I_SYNC) -#define I_REFERENCED (1 << 8) -#define __I_DIO_WAKEUP 9 -#define I_DIO_WAKEUP (1 << __I_DIO_WAKEUP) +#define __I_LRU_ISOLATING 2 +#define I_LRU_ISOLATING (1 << __I_LRU_ISOLATING) + +#define I_DIRTY_SYNC (1 << 3) +#define I_DIRTY_DATASYNC (1 << 4) +#define I_DIRTY_PAGES (1 << 5) +#define I_WILL_FREE (1 << 6) +#define I_FREEING (1 << 7) +#define I_CLEAR (1 << 8) +#define I_REFERENCED (1 << 9) #define I_LINKABLE (1 << 10) #define I_DIRTY_TIME (1 << 11) -#define I_WB_SWITCH (1 << 13) -#define I_OVL_INUSE (1 << 14) -#define I_CREATING (1 << 15) -#define I_DONTCACHE (1 << 16) -#define I_SYNC_QUEUED (1 << 17) -#define I_PINNING_NETFS_WB (1 << 18) +#define I_WB_SWITCH (1 << 12) +#define I_OVL_INUSE (1 << 13) +#define I_CREATING (1 << 14) +#define I_DONTCACHE (1 << 15) +#define I_SYNC_QUEUED (1 << 16) +#define I_PINNING_NETFS_WB (1 << 17) #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES) @@ -2473,6 +2603,7 @@ struct file_system_type { #define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */ #define FS_DISALLOW_NOTIFY_PERM 16 /* Disable fanotify permission events */ #define FS_ALLOW_IDMAP 32 /* FS has been updated to handle vfs idmappings. */ +#define FS_MGTIME 64 /* FS uses multigrain timestamps */ #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ int (*init_fs_context)(struct fs_context *); const struct fs_parameter_spec *parameters; @@ -2496,6 +2627,17 @@ struct file_system_type { #define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME) +/** + * is_mgtime: is this inode using multigrain timestamps + * @inode: inode to test for multigrain timestamps + * + * Return true if the inode uses multigrain timestamps, false otherwise. + */ +static inline bool is_mgtime(const struct inode *inode) +{ + return inode->i_opflags & IOP_MGTIME; +} + extern struct dentry *mount_bdev(struct file_system_type *fs_type, int flags, const char *dev_name, void *data, int (*fill_super)(struct super_block *, void *, int)); @@ -2527,10 +2669,17 @@ struct super_block *sget(struct file_system_type *type, struct super_block *sget_dev(struct fs_context *fc, dev_t dev); /* Alas, no aliases. Too much hassle with bringing module.h everywhere */ -#define fops_get(fops) \ - (((fops) && try_module_get((fops)->owner) ? (fops) : NULL)) -#define fops_put(fops) \ - do { if (fops) module_put((fops)->owner); } while(0) +#define fops_get(fops) ({ \ + const struct file_operations *_fops = (fops); \ + (((_fops) && try_module_get((_fops)->owner) ? (_fops) : NULL)); \ +}) + +#define fops_put(fops) ({ \ + const struct file_operations *_fops = (fops); \ + if (_fops) \ + module_put((_fops)->owner); \ +}) + /* * This one is to be used *ONLY* from ->open() instances. * fops must be non-NULL, pinned down *and* module dependencies @@ -2652,6 +2801,8 @@ static inline struct file *file_open_root_mnt(struct vfsmount *mnt, } struct file *dentry_open(const struct path *path, int flags, const struct cred *creds); +struct file *dentry_open_nonotify(const struct path *path, int flags, + const struct cred *cred); struct file *dentry_create(const struct path *path, int flags, umode_t mode, const struct cred *cred); struct path *backing_file_user_path(struct file *f); @@ -2686,10 +2837,20 @@ static inline struct file *file_clone_open(struct file *file) } extern int filp_close(struct file *, fl_owner_t id); -extern struct filename *getname_flags(const char __user *, int, int *); +extern struct filename *getname_flags(const char __user *, int); extern struct filename *getname_uflags(const char __user *, int); extern struct filename *getname(const char __user *); extern struct filename *getname_kernel(const char *); +extern struct filename *__getname_maybe_null(const char __user *); +static inline struct filename *getname_maybe_null(const char __user *name, int flags) +{ + if (!(flags & AT_EMPTY_PATH)) + return getname(name); + + if (!name) + return NULL; + return __getname_maybe_null(name); +} extern void putname(struct filename *name); extern int finish_open(struct file *file, struct dentry *dentry, @@ -2765,6 +2926,8 @@ extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart, extern int __must_check file_check_and_advance_wb_err(struct file *file); extern int __must_check file_write_and_wait_range(struct file *file, loff_t start, loff_t end); +int filemap_fdatawrite_range_kick(struct address_space *mapping, loff_t start, + loff_t end); static inline int file_write_and_wait(struct file *file) { @@ -2797,6 +2960,11 @@ static inline ssize_t generic_write_sync(struct kiocb *iocb, ssize_t count) (iocb->ki_flags & IOCB_SYNC) ? 0 : 1); if (ret) return ret; + } else if (iocb->ki_flags & IOCB_DONTCACHE) { + struct address_space *mapping = iocb->ki_filp->f_mapping; + + filemap_fdatawrite_range_kick(mapping, iocb->ki_pos, + iocb->ki_pos + count); } return count; @@ -2950,6 +3118,28 @@ static inline void allow_write_access(struct file *file) if (file) atomic_inc(&file_inode(file)->i_writecount); } + +/* + * Do not prevent write to executable file when watched by pre-content events. + * + * Note that FMODE_FSNOTIFY_HSM mode is set depending on pre-content watches at + * the time of file open and remains constant for entire lifetime of the file, + * so if pre-content watches are added post execution or removed before the end + * of the execution, it will not cause i_writecount reference leak. + */ +static inline int exe_file_deny_write_access(struct file *exe_file) +{ + if (unlikely(FMODE_FSNOTIFY_HSM(exe_file->f_mode))) + return 0; + return deny_write_access(exe_file); +} +static inline void exe_file_allow_write_access(struct file *exe_file) +{ + if (unlikely(!exe_file || FMODE_FSNOTIFY_HSM(exe_file->f_mode))) + return; + allow_write_access(exe_file); +} + static inline bool inode_is_open_for_write(const struct inode *inode) { return atomic_read(&inode->i_writecount) > 0; @@ -3006,7 +3196,12 @@ extern loff_t default_llseek(struct file *file, loff_t offset, int whence); extern loff_t vfs_llseek(struct file *file, loff_t offset, int whence); -extern int inode_init_always(struct super_block *, struct inode *); +extern int inode_init_always_gfp(struct super_block *, struct inode *, gfp_t); +static inline int inode_init_always(struct super_block *sb, struct inode *inode) +{ + return inode_init_always_gfp(sb, inode, GFP_NOFS); +} + extern void inode_init_once(struct inode *); extern void address_space_init_once(struct address_space *mapping); extern struct inode * igrab(struct inode *); @@ -3030,7 +3225,12 @@ extern struct inode *inode_insert5(struct inode *inode, unsigned long hashval, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *data); -extern struct inode * iget5_locked(struct super_block *, unsigned long, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *); +struct inode *iget5_locked(struct super_block *, unsigned long, + int (*test)(struct inode *, void *), + int (*set)(struct inode *, void *), void *); +struct inode *iget5_locked_rcu(struct super_block *, unsigned long, + int (*test)(struct inode *, void *), + int (*set)(struct inode *, void *), void *); extern struct inode * iget_locked(struct super_block *, unsigned long); extern struct inode *find_inode_nowait(struct super_block *, unsigned long, @@ -3068,7 +3268,14 @@ static inline bool is_zero_ino(ino_t ino) return (u32)ino == 0; } -extern void __iget(struct inode * inode); +/* + * inode->i_lock must be held + */ +static inline void __iget(struct inode *inode) +{ + atomic_inc(&inode->i_count); +} + extern void iget_failed(struct inode *); extern void clear_inode(struct inode *); extern void __destroy_inode(struct inode *); @@ -3085,11 +3292,7 @@ int setattr_should_drop_sgid(struct mnt_idmap *idmap, * This must be used for allocating filesystems specific inodes to set * up the inode reclaim context correctly. */ -static inline void * -alloc_inode_sb(struct super_block *sb, struct kmem_cache *cache, gfp_t gfp) -{ - return kmem_cache_alloc_lru(cache, &sb->s_inode_lru, gfp); -} +#define alloc_inode_sb(_sb, _cache, _gfp) kmem_cache_alloc_lru(_cache, &_sb->s_inode_lru, _gfp) extern void __insert_inode_hash(struct inode *, unsigned long hashval); static inline void insert_inode_hash(struct inode *inode) @@ -3150,11 +3353,12 @@ extern ssize_t iter_file_splice_write(struct pipe_inode_info *, extern void file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping); extern loff_t noop_llseek(struct file *file, loff_t offset, int whence); -#define no_llseek NULL extern loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize); extern loff_t generic_file_llseek(struct file *file, loff_t offset, int whence); extern loff_t generic_file_llseek_size(struct file *file, loff_t offset, int whence, loff_t maxsize, loff_t eof); +loff_t generic_llseek_cookie(struct file *file, loff_t offset, int whence, + u64 *cookie); extern loff_t fixed_size_llseek(struct file *file, loff_t offset, int whence, loff_t size); extern loff_t no_seek_end_llseek_size(struct file *, loff_t, int, loff_t); @@ -3192,7 +3396,9 @@ static inline ssize_t blockdev_direct_IO(struct kiocb *iocb, } #endif +bool inode_dio_finished(const struct inode *inode); void inode_dio_wait(struct inode *inode); +void inode_dio_wait_interruptible(struct inode *inode); /** * inode_dio_begin - signal start of a direct I/O requests @@ -3216,7 +3422,7 @@ static inline void inode_dio_begin(struct inode *inode) static inline void inode_dio_end(struct inode *inode) { if (atomic_dec_and_test(&inode->i_dio_count)) - wake_up_bit(&inode->i_state, __I_DIO_WAKEUP); + wake_up_var(&inode->i_dio_count); } extern void inode_set_flags(struct inode *inode, unsigned int flags, @@ -3226,7 +3432,7 @@ extern const struct file_operations generic_ro_fops; #define special_file(m) (S_ISCHR(m)||S_ISBLK(m)||S_ISFIFO(m)||S_ISSOCK(m)) -extern int readlink_copy(char __user *, int, const char *); +extern int readlink_copy(char __user *, int, const char *, int); extern int page_readlink(struct dentry *, char __user *, int); extern const char *page_get_link(struct dentry *, struct inode *, struct delayed_call *); @@ -3234,8 +3440,12 @@ extern void page_put_link(void *); extern int page_symlink(struct inode *inode, const char *symname, int len); extern const struct inode_operations page_symlink_inode_operations; extern void kfree_link(void *); +void fill_mg_cmtime(struct kstat *stat, u32 request_mask, struct inode *inode); void generic_fillattr(struct mnt_idmap *, u32, struct inode *, struct kstat *); void generic_fill_statx_attr(struct inode *inode, struct kstat *stat); +void generic_fill_statx_atomic_writes(struct kstat *stat, + unsigned int unit_min, + unsigned int unit_max); extern int vfs_getattr_nosec(const struct path *, struct kstat *, u32, unsigned int); extern int vfs_getattr(const struct path *, struct kstat *, u32, unsigned int); void __inode_add_bytes(struct inode *inode, loff_t bytes); @@ -3306,7 +3516,7 @@ extern ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter); extern int simple_empty(struct dentry *); extern int simple_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata); + struct folio **foliop, void **fsdata); extern const struct address_space_operations ram_aops; extern int always_delete_dentry(const struct dentry *); extern struct inode *alloc_anon_inode(struct super_block *); @@ -3339,7 +3549,8 @@ struct offset_ctx { void simple_offset_init(struct offset_ctx *octx); int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry); void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry); -int simple_offset_empty(struct dentry *dentry); +int simple_offset_rename(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry); int simple_offset_rename_exchange(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, @@ -3354,6 +3565,58 @@ extern int generic_file_fsync(struct file *, loff_t, loff_t, int); extern int generic_check_addressable(unsigned, u64); extern void generic_set_sb_d_ops(struct super_block *sb); +extern int generic_ci_match(const struct inode *parent, + const struct qstr *name, + const struct qstr *folded_name, + const u8 *de_name, u32 de_name_len); + +#if IS_ENABLED(CONFIG_UNICODE) +int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str); +int generic_ci_d_compare(const struct dentry *dentry, unsigned int len, + const char *str, const struct qstr *name); + +/** + * generic_ci_validate_strict_name - Check if a given name is suitable + * for a directory + * + * This functions checks if the proposed filename is valid for the + * parent directory. That means that only valid UTF-8 filenames will be + * accepted for casefold directories from filesystems created with the + * strict encoding flag. That also means that any name will be + * accepted for directories that doesn't have casefold enabled, or + * aren't being strict with the encoding. + * + * @dir: inode of the directory where the new file will be created + * @name: name of the new file + * + * Return: + * * True: if the filename is suitable for this directory. It can be + * true if a given name is not suitable for a strict encoding + * directory, but the directory being used isn't strict + * * False if the filename isn't suitable for this directory. This only + * happens when a directory is casefolded and the filesystem is strict + * about its encoding. + */ +static inline bool generic_ci_validate_strict_name(struct inode *dir, struct qstr *name) +{ + if (!IS_CASEFOLDED(dir) || !sb_has_strict_encoding(dir->i_sb)) + return true; + + /* + * A casefold dir must have a encoding set, unless the filesystem + * is corrupted + */ + if (WARN_ON_ONCE(!dir->i_sb->s_encoding)) + return true; + + return !utf8_validate(dir->i_sb->s_encoding, name); +} +#else +static inline bool generic_ci_validate_strict_name(struct inode *dir, struct qstr *name) +{ + return true; +} +#endif static inline bool sb_has_encoding(const struct super_block *sb) { @@ -3406,7 +3669,8 @@ static inline int iocb_flags(struct file *file) return res; } -static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags) +static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags, + int rw_type) { int kiocb_flags = 0; @@ -3423,7 +3687,20 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags) if (flags & RWF_NOWAIT) { if (!(ki->ki_filp->f_mode & FMODE_NOWAIT)) return -EOPNOTSUPP; - kiocb_flags |= IOCB_NOIO; + } + if (flags & RWF_ATOMIC) { + if (rw_type != WRITE) + return -EOPNOTSUPP; + if (!(ki->ki_filp->f_mode & FMODE_CAN_ATOMIC_WRITE)) + return -EOPNOTSUPP; + } + if (flags & RWF_DONTCACHE) { + /* file system must support it */ + if (!(ki->ki_filp->f_op->fop_flags & FOP_DONTCACHE)) + return -EOPNOTSUPP; + /* DAX mappings not supported */ + if (IS_DAX(ki->ki_filp->f_mapping->host)) + return -EOPNOTSUPP; } kiocb_flags |= (__force int) (flags & RWF_SUPPORTED); if (flags & RWF_SYNC) @@ -3439,20 +3716,6 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags) return 0; } -static inline ino_t parent_ino(struct dentry *dentry) -{ - ino_t res; - - /* - * Don't strictly need d_lock here? If the parent ino could change - * then surely we'd have a deeper race in the caller? - */ - spin_lock(&dentry->d_lock); - res = dentry->d_parent->d_inode->i_ino; - spin_unlock(&dentry->d_lock); - return res; -} - /* Transaction based IO helpers */ /* @@ -3532,11 +3795,9 @@ struct ctl_table; int __init list_bdev_fs_names(char *buf, size_t size); #define __FMODE_EXEC ((__force int) FMODE_EXEC) -#define __FMODE_NONOTIFY ((__force int) FMODE_NONOTIFY) #define ACC_MODE(x) ("\004\002\006\006"[(x)&O_ACCMODE]) -#define OPEN_FMODE(flag) ((__force fmode_t)(((flag + 1) & O_ACCMODE) | \ - (flag & __FMODE_NONOTIFY))) +#define OPEN_FMODE(flag) ((__force fmode_t)((flag + 1) & O_ACCMODE)) static inline bool is_sxid(umode_t mode) { @@ -3577,7 +3838,7 @@ static inline bool dir_emit_dot(struct file *file, struct dir_context *ctx) static inline bool dir_emit_dotdot(struct file *file, struct dir_context *ctx) { return ctx->actor(ctx, "..", 2, ctx->pos, - parent_ino(file->f_path.dentry), DT_DIR); + d_parent_ino(file->f_path.dentry), DT_DIR); } static inline bool dir_emit_dots(struct file *file, struct dir_context *ctx) { @@ -3616,4 +3877,23 @@ extern int vfs_fadvise(struct file *file, loff_t offset, loff_t len, extern int generic_fadvise(struct file *file, loff_t offset, loff_t len, int advice); +static inline bool vfs_empty_path(int dfd, const char __user *path) +{ + char c; + + if (dfd < 0) + return false; + + /* We now allow NULL to be used for empty path. */ + if (!path) + return true; + + if (unlikely(get_user(c, path))) + return false; + + return !c; +} + +int generic_atomic_write_valid(struct kiocb *iocb, struct iov_iter *iter); + #endif /* _LINUX_FS_H */ diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index c13e99cbbf81..4b4bfef6f053 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -160,6 +160,12 @@ extern int get_tree_keyed(struct fs_context *fc, int setup_bdev_super(struct super_block *sb, int sb_flags, struct fs_context *fc); + +#define GET_TREE_BDEV_QUIET_LOOKUP 0x0001 +int get_tree_bdev_flags(struct fs_context *fc, + int (*fill_super)(struct super_block *sb, + struct fs_context *fc), unsigned int flags); + extern int get_tree_bdev(struct fs_context *fc, int (*fill_super)(struct super_block *sb, struct fs_context *fc)); diff --git a/include/linux/fs_parser.h b/include/linux/fs_parser.h index 01542c4b87a2..53e566efd5fd 100644 --- a/include/linux/fs_parser.h +++ b/include/linux/fs_parser.h @@ -28,7 +28,8 @@ typedef int fs_param_type(struct p_log *, */ fs_param_type fs_param_is_bool, fs_param_is_u32, fs_param_is_s32, fs_param_is_u64, fs_param_is_enum, fs_param_is_string, fs_param_is_blob, fs_param_is_blockdev, - fs_param_is_path, fs_param_is_fd; + fs_param_is_path, fs_param_is_fd, fs_param_is_uid, fs_param_is_gid, + fs_param_is_file_or_string; /* * Specification of the type of value a parameter wants. @@ -57,6 +58,8 @@ struct fs_parse_result { int int_32; /* For spec_s32/spec_enum */ unsigned int uint_32; /* For spec_u32{,_octal,_hex}/spec_enum */ u64 uint_64; /* For spec_u64 */ + kuid_t uid; + kgid_t gid; }; }; @@ -81,6 +84,8 @@ extern int fs_lookup_param(struct fs_context *fc, extern int lookup_constant(const struct constant_table tbl[], const char *name, int not_found); +extern const struct constant_table bool_names[]; + #ifdef CONFIG_VALIDATE_FS_PARSER extern bool validate_constant_table(const struct constant_table *tbl, size_t tbl_size, int low, int high, int special); @@ -131,5 +136,13 @@ static inline bool fs_validate_description(const char *name, #define fsparam_bdev(NAME, OPT) __fsparam(fs_param_is_blockdev, NAME, OPT, 0, NULL) #define fsparam_path(NAME, OPT) __fsparam(fs_param_is_path, NAME, OPT, 0, NULL) #define fsparam_fd(NAME, OPT) __fsparam(fs_param_is_fd, NAME, OPT, 0, NULL) +#define fsparam_file_or_string(NAME, OPT) \ + __fsparam(fs_param_is_file_or_string, NAME, OPT, 0, NULL) +#define fsparam_uid(NAME, OPT) __fsparam(fs_param_is_uid, NAME, OPT, 0, NULL) +#define fsparam_gid(NAME, OPT) __fsparam(fs_param_is_gid, NAME, OPT, 0, NULL) + +/* String parameter that allows empty argument */ +#define fsparam_string_empty(NAME, OPT) \ + __fsparam(fs_param_is_string, NAME, OPT, fs_param_can_be_empty, NULL) #endif /* _LINUX_FS_PARSER_H */ diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index bdf7f3eddf0a..4c91a019972b 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -19,6 +19,7 @@ enum fscache_cache_trace; enum fscache_cookie_trace; enum fscache_access_trace; +enum fscache_volume_trace; enum fscache_cache_state { FSCACHE_CACHE_IS_NOT_PRESENT, /* No cache is present for this name */ @@ -97,6 +98,11 @@ extern void fscache_withdraw_cookie(struct fscache_cookie *cookie); extern void fscache_io_error(struct fscache_cache *cache); +extern struct fscache_volume * +fscache_try_get_volume(struct fscache_volume *volume, + enum fscache_volume_trace where); +extern void fscache_put_volume(struct fscache_volume *volume, + enum fscache_volume_trace where); extern void fscache_end_volume_access(struct fscache_volume *volume, struct fscache_cookie *cookie, enum fscache_access_trace why); diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 6e8562cbcc43..9de27643607f 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -172,9 +172,12 @@ extern void __fscache_invalidate(struct fscache_cookie *, const void *, loff_t, extern int __fscache_begin_read_operation(struct netfs_cache_resources *, struct fscache_cookie *); extern int __fscache_begin_write_operation(struct netfs_cache_resources *, struct fscache_cookie *); -extern void __fscache_write_to_cache(struct fscache_cookie *, struct address_space *, - loff_t, size_t, loff_t, netfs_io_terminated_t, void *, - bool); +void __fscache_write_to_cache(struct fscache_cookie *cookie, + struct address_space *mapping, + loff_t start, size_t len, loff_t i_size, + netfs_io_terminated_t term_func, + void *term_func_priv, + bool using_pgpriv2, bool cond); extern void __fscache_clear_page_bits(struct address_space *, loff_t, size_t); /** @@ -597,7 +600,8 @@ static inline void fscache_clear_page_bits(struct address_space *mapping, * @i_size: The new size of the inode * @term_func: The function to call upon completion * @term_func_priv: The private data for @term_func - * @caching: If PG_fscache has been set + * @using_pgpriv2: If we're using PG_private_2 to mark in-progress write + * @caching: If we actually want to do the caching * * Helper function for a netfs to write dirty data from an inode into the cache * object that's backing it. @@ -608,19 +612,21 @@ static inline void fscache_clear_page_bits(struct address_space *mapping, * marked with PG_fscache. * * If given, @term_func will be called upon completion and supplied with - * @term_func_priv. Note that the PG_fscache flags will have been cleared by - * this point, so the netfs must retain its own pin on the mapping. + * @term_func_priv. Note that if @using_pgpriv2 is set, the PG_private_2 flags + * will have been cleared by this point, so the netfs must retain its own pin + * on the mapping. */ static inline void fscache_write_to_cache(struct fscache_cookie *cookie, struct address_space *mapping, loff_t start, size_t len, loff_t i_size, netfs_io_terminated_t term_func, void *term_func_priv, - bool caching) + bool using_pgpriv2, bool caching) { if (caching) __fscache_write_to_cache(cookie, mapping, start, len, i_size, - term_func, term_func_priv, caching); + term_func, term_func_priv, + using_pgpriv2, caching); else if (term_func) term_func(term_func_priv, -ENOBUFS, false); diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index 772f822dc6b8..18855cb44b1c 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -192,7 +192,8 @@ struct fscrypt_operations { unsigned int *num_devs); }; -int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags); +int fscrypt_d_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags); static inline struct fscrypt_inode_info * fscrypt_get_inode_info(const struct inode *inode) @@ -711,8 +712,8 @@ static inline u64 fscrypt_fname_siphash(const struct inode *dir, return 0; } -static inline int fscrypt_d_revalidate(struct dentry *dentry, - unsigned int flags) +static inline int fscrypt_d_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { return 1; } diff --git a/include/linux/fsi.h b/include/linux/fsi.h index 3df8c54868df..8c5eef808788 100644 --- a/include/linux/fsi.h +++ b/include/linux/fsi.h @@ -44,7 +44,7 @@ struct fsi_driver { }; #define to_fsi_dev(devp) container_of(devp, struct fsi_device, dev) -#define to_fsi_drv(drvp) container_of(drvp, struct fsi_driver, drv) +#define to_fsi_drv(drvp) container_of_const(drvp, struct fsi_driver, drv) extern int fsi_driver_register(struct fsi_driver *fsi_drv); extern void fsi_driver_unregister(struct fsi_driver *fsi_drv); diff --git a/include/linux/fsl/enetc_mdio.h b/include/linux/fsl/enetc_mdio.h index df25fffdc0ae..623ccfcbf39c 100644 --- a/include/linux/fsl/enetc_mdio.h +++ b/include/linux/fsl/enetc_mdio.h @@ -59,7 +59,8 @@ static inline int enetc_mdio_read_c45(struct mii_bus *bus, int phy_id, static inline int enetc_mdio_write_c45(struct mii_bus *bus, int phy_id, int devad, int regnum, u16 value) { return -EINVAL; } -struct enetc_hw *enetc_hw_alloc(struct device *dev, void __iomem *port_regs) +static inline struct enetc_hw *enetc_hw_alloc(struct device *dev, + void __iomem *port_regs) { return ERR_PTR(-EINVAL); } #endif diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h index a1b3de87a3d1..99f30c7d6208 100644 --- a/include/linux/fsl/mc.h +++ b/include/linux/fsl/mc.h @@ -56,7 +56,7 @@ struct fsl_mc_driver { }; #define to_fsl_mc_driver(_drv) \ - container_of(_drv, struct fsl_mc_driver, driver) + container_of_const(_drv, struct fsl_mc_driver, driver) /** * enum fsl_mc_pool_type - Types of allocatable MC bus resources @@ -436,23 +436,23 @@ void fsl_mc_free_irqs(struct fsl_mc_device *mc_dev); struct fsl_mc_device *fsl_mc_get_endpoint(struct fsl_mc_device *mc_dev, u16 if_id); -extern struct bus_type fsl_mc_bus_type; +extern const struct bus_type fsl_mc_bus_type; -extern struct device_type fsl_mc_bus_dprc_type; -extern struct device_type fsl_mc_bus_dpni_type; -extern struct device_type fsl_mc_bus_dpio_type; -extern struct device_type fsl_mc_bus_dpsw_type; -extern struct device_type fsl_mc_bus_dpbp_type; -extern struct device_type fsl_mc_bus_dpcon_type; -extern struct device_type fsl_mc_bus_dpmcp_type; -extern struct device_type fsl_mc_bus_dpmac_type; -extern struct device_type fsl_mc_bus_dprtc_type; -extern struct device_type fsl_mc_bus_dpseci_type; -extern struct device_type fsl_mc_bus_dpdmux_type; -extern struct device_type fsl_mc_bus_dpdcei_type; -extern struct device_type fsl_mc_bus_dpaiop_type; -extern struct device_type fsl_mc_bus_dpci_type; -extern struct device_type fsl_mc_bus_dpdmai_type; +extern const struct device_type fsl_mc_bus_dprc_type; +extern const struct device_type fsl_mc_bus_dpni_type; +extern const struct device_type fsl_mc_bus_dpio_type; +extern const struct device_type fsl_mc_bus_dpsw_type; +extern const struct device_type fsl_mc_bus_dpbp_type; +extern const struct device_type fsl_mc_bus_dpcon_type; +extern const struct device_type fsl_mc_bus_dpmcp_type; +extern const struct device_type fsl_mc_bus_dpmac_type; +extern const struct device_type fsl_mc_bus_dprtc_type; +extern const struct device_type fsl_mc_bus_dpseci_type; +extern const struct device_type fsl_mc_bus_dpdmux_type; +extern const struct device_type fsl_mc_bus_dpdcei_type; +extern const struct device_type fsl_mc_bus_dpaiop_type; +extern const struct device_type fsl_mc_bus_dpci_type; +extern const struct device_type fsl_mc_bus_dpdmai_type; static inline bool is_fsl_mc_bus_dprc(const struct fsl_mc_device *mc_dev) { diff --git a/include/linux/fsl/netc_global.h b/include/linux/fsl/netc_global.h new file mode 100644 index 000000000000..fdecca8c90f0 --- /dev/null +++ b/include/linux/fsl/netc_global.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */ +/* Copyright 2024 NXP + */ +#ifndef __NETC_GLOBAL_H +#define __NETC_GLOBAL_H + +#include <linux/io.h> + +static inline u32 netc_read(void __iomem *reg) +{ + return ioread32(reg); +} + +static inline void netc_write(void __iomem *reg, u32 val) +{ + iowrite32(val, reg); +} + +#endif diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 1a9de119a0f7..1a9ef8f6784d 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -17,10 +17,23 @@ #include <linux/slab.h> #include <linux/bug.h> +/* Are there any inode/mount/sb objects watched with priority prio or above? */ +static inline bool fsnotify_sb_has_priority_watchers(struct super_block *sb, + int prio) +{ + struct fsnotify_sb_info *sbinfo = fsnotify_sb_info(sb); + + /* Were any marks ever added to any object on this sb? */ + if (!sbinfo) + return false; + + return atomic_long_read(&sbinfo->watched_objects[prio]); +} + /* Are there any inode/mount/sb objects that are being watched at all? */ static inline bool fsnotify_sb_has_watchers(struct super_block *sb) { - return atomic_long_read(&sb->s_fsnotify_connectors); + return fsnotify_sb_has_priority_watchers(sb, 0); } /* @@ -95,26 +108,35 @@ static inline void fsnotify_dentry(struct dentry *dentry, __u32 mask) fsnotify_parent(dentry, mask, dentry, FSNOTIFY_EVENT_DENTRY); } -static inline int fsnotify_file(struct file *file, __u32 mask) +static inline int fsnotify_path(const struct path *path, __u32 mask) { - const struct path *path; + return fsnotify_parent(path->dentry, mask, path, FSNOTIFY_EVENT_PATH); +} - if (file->f_mode & FMODE_NONOTIFY) +static inline int fsnotify_file(struct file *file, __u32 mask) +{ + /* + * FMODE_NONOTIFY are fds generated by fanotify itself which should not + * generate new events. We also don't want to generate events for + * FMODE_PATH fds (involves open & close events) as they are just + * handle creation / destruction events and not "real" file events. + */ + if (FMODE_FSNOTIFY_NONE(file->f_mode)) return 0; - path = &file->f_path; - return fsnotify_parent(path->dentry, mask, path, FSNOTIFY_EVENT_PATH); + return fsnotify_path(&file->f_path, mask); } #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS + +void file_set_fsnotify_mode(struct file *file); + /* * fsnotify_file_area_perm - permission hook before access to file range */ static inline int fsnotify_file_area_perm(struct file *file, int perm_mask, const loff_t *ppos, size_t count) { - __u32 fsnotify_mask = FS_ACCESS_PERM; - /* * filesystem may be modified in the context of permission events * (e.g. by HSM filling a file on access), so sb freeze protection @@ -122,14 +144,49 @@ static inline int fsnotify_file_area_perm(struct file *file, int perm_mask, */ lockdep_assert_once(file_write_not_started(file)); + if (!(perm_mask & (MAY_READ | MAY_WRITE | MAY_ACCESS))) + return 0; + + if (likely(!FMODE_FSNOTIFY_PERM(file->f_mode))) + return 0; + + /* + * read()/write() and other types of access generate pre-content events. + */ + if (unlikely(FMODE_FSNOTIFY_HSM(file->f_mode))) { + int ret = fsnotify_pre_content(&file->f_path, ppos, count); + + if (ret) + return ret; + } + if (!(perm_mask & MAY_READ)) return 0; - return fsnotify_file(file, fsnotify_mask); + /* + * read() also generates the legacy FS_ACCESS_PERM event, so content + * scanners can inspect the content filled by pre-content event. + */ + return fsnotify_path(&file->f_path, FS_ACCESS_PERM); } /* - * fsnotify_file_perm - permission hook before file access + * fsnotify_truncate_perm - permission hook before file truncate + */ +static inline int fsnotify_truncate_perm(const struct path *path, loff_t length) +{ + struct inode *inode = d_inode(path->dentry); + + if (!(inode->i_sb->s_iflags & SB_I_ALLOW_HSM) || + !fsnotify_sb_has_priority_watchers(inode->i_sb, + FSNOTIFY_PRIO_PRE_CONTENT)) + return 0; + + return fsnotify_pre_content(path, &length, 0); +} + +/* + * fsnotify_file_perm - permission hook before file access (unknown range) */ static inline int fsnotify_file_perm(struct file *file, int perm_mask) { @@ -143,22 +200,34 @@ static inline int fsnotify_open_perm(struct file *file) { int ret; + if (likely(!FMODE_FSNOTIFY_PERM(file->f_mode))) + return 0; + if (file->f_flags & __FMODE_EXEC) { - ret = fsnotify_file(file, FS_OPEN_EXEC_PERM); + ret = fsnotify_path(&file->f_path, FS_OPEN_EXEC_PERM); if (ret) return ret; } - return fsnotify_file(file, FS_OPEN_PERM); + return fsnotify_path(&file->f_path, FS_OPEN_PERM); } #else +static inline void file_set_fsnotify_mode(struct file *file) +{ +} + static inline int fsnotify_file_area_perm(struct file *file, int perm_mask, const loff_t *ppos, size_t count) { return 0; } +static inline int fsnotify_truncate_perm(const struct path *path, loff_t length) +{ + return 0; +} + static inline int fsnotify_file_perm(struct file *file, int perm_mask) { return 0; diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 8f40c349b228..0d24a21a8e60 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -55,6 +55,9 @@ #define FS_OPEN_PERM 0x00010000 /* open event in an permission hook */ #define FS_ACCESS_PERM 0x00020000 /* access event in a permissions hook */ #define FS_OPEN_EXEC_PERM 0x00040000 /* open/exec event in a permission hook */ +/* #define FS_DIR_MODIFY 0x00080000 */ /* Deprecated (reserved) */ + +#define FS_PRE_ACCESS 0x00100000 /* Pre-content access hook */ /* * Set on inode mark that cares about things that happen to its children. @@ -77,8 +80,14 @@ */ #define ALL_FSNOTIFY_DIRENT_EVENTS (FS_CREATE | FS_DELETE | FS_MOVE | FS_RENAME) -#define ALL_FSNOTIFY_PERM_EVENTS (FS_OPEN_PERM | FS_ACCESS_PERM | \ - FS_OPEN_EXEC_PERM) +/* Content events can be used to inspect file content */ +#define FSNOTIFY_CONTENT_PERM_EVENTS (FS_OPEN_PERM | FS_OPEN_EXEC_PERM | \ + FS_ACCESS_PERM) +/* Pre-content events can be used to fill file content */ +#define FSNOTIFY_PRE_CONTENT_EVENTS (FS_PRE_ACCESS) + +#define ALL_FSNOTIFY_PERM_EVENTS (FSNOTIFY_CONTENT_PERM_EVENTS | \ + FSNOTIFY_PRE_CONTENT_EVENTS) /* * This is a list of all events that may get sent to a parent that is watching @@ -177,6 +186,17 @@ struct fsnotify_event { }; /* + * fsnotify group priorities. + * Events are sent in order from highest priority to lowest priority. + */ +enum fsnotify_group_prio { + FSNOTIFY_PRIO_NORMAL = 0, /* normal notifiers, no permissions */ + FSNOTIFY_PRIO_CONTENT, /* fanotify permission events */ + FSNOTIFY_PRIO_PRE_CONTENT, /* fanotify pre-content events */ + __FSNOTIFY_PRIO_NUM +}; + +/* * A group is a "thing" that wants to receive notification about filesystem * events. The mask holds the subset of event types this group cares about. * refcnt on a group is up to the implementor and at any moment if it goes 0 @@ -201,19 +221,11 @@ struct fsnotify_group { wait_queue_head_t notification_waitq; /* read() on the notification file blocks on this waitq */ unsigned int q_len; /* events on the queue */ unsigned int max_events; /* maximum events allowed on the list */ - /* - * Valid fsnotify group priorities. Events are send in order from highest - * priority to lowest priority. We default to the lowest priority. - */ - #define FS_PRIO_0 0 /* normal notifiers, no permissions */ - #define FS_PRIO_1 1 /* fanotify content based access control */ - #define FS_PRIO_2 2 /* fanotify pre-content access */ - unsigned int priority; + enum fsnotify_group_prio priority; /* priority for sending events */ bool shutdown; /* group is being shut down, don't queue more events */ #define FSNOTIFY_GROUP_USER 0x01 /* user allocated group */ #define FSNOTIFY_GROUP_DUPS 0x02 /* allow multiple marks per object */ -#define FSNOTIFY_GROUP_NOFS 0x04 /* group lock is not direct reclaim safe */ int flags; unsigned int owner_flags; /* stored flags of mark_mutex owner */ @@ -264,27 +276,25 @@ struct fsnotify_group { static inline void fsnotify_group_lock(struct fsnotify_group *group) { mutex_lock(&group->mark_mutex); - if (group->flags & FSNOTIFY_GROUP_NOFS) - group->owner_flags = memalloc_nofs_save(); + group->owner_flags = memalloc_nofs_save(); } static inline void fsnotify_group_unlock(struct fsnotify_group *group) { - if (group->flags & FSNOTIFY_GROUP_NOFS) - memalloc_nofs_restore(group->owner_flags); + memalloc_nofs_restore(group->owner_flags); mutex_unlock(&group->mark_mutex); } static inline void fsnotify_group_assert_locked(struct fsnotify_group *group) { WARN_ON_ONCE(!mutex_is_locked(&group->mark_mutex)); - if (group->flags & FSNOTIFY_GROUP_NOFS) - WARN_ON_ONCE(!(current->flags & PF_MEMALLOC_NOFS)); + WARN_ON_ONCE(!(current->flags & PF_MEMALLOC_NOFS)); } /* When calling fsnotify tell it if the data is a path or inode */ enum fsnotify_data_type { FSNOTIFY_EVENT_NONE, + FSNOTIFY_EVENT_FILE_RANGE, FSNOTIFY_EVENT_PATH, FSNOTIFY_EVENT_INODE, FSNOTIFY_EVENT_DENTRY, @@ -297,6 +307,17 @@ struct fs_error_report { struct super_block *sb; }; +struct file_range { + const struct path *path; + loff_t pos; + size_t count; +}; + +static inline const struct path *file_range_path(const struct file_range *range) +{ + return range->path; +} + static inline struct inode *fsnotify_data_inode(const void *data, int data_type) { switch (data_type) { @@ -306,6 +327,8 @@ static inline struct inode *fsnotify_data_inode(const void *data, int data_type) return d_inode(data); case FSNOTIFY_EVENT_PATH: return d_inode(((const struct path *)data)->dentry); + case FSNOTIFY_EVENT_FILE_RANGE: + return d_inode(file_range_path(data)->dentry); case FSNOTIFY_EVENT_ERROR: return ((struct fs_error_report *)data)->inode; default: @@ -321,6 +344,8 @@ static inline struct dentry *fsnotify_data_dentry(const void *data, int data_typ return (struct dentry *)data; case FSNOTIFY_EVENT_PATH: return ((const struct path *)data)->dentry; + case FSNOTIFY_EVENT_FILE_RANGE: + return file_range_path(data)->dentry; default: return NULL; } @@ -332,6 +357,8 @@ static inline const struct path *fsnotify_data_path(const void *data, switch (data_type) { case FSNOTIFY_EVENT_PATH: return data; + case FSNOTIFY_EVENT_FILE_RANGE: + return file_range_path(data); default: return NULL; } @@ -347,6 +374,8 @@ static inline struct super_block *fsnotify_data_sb(const void *data, return ((struct dentry *)data)->d_sb; case FSNOTIFY_EVENT_PATH: return ((const struct path *)data)->dentry->d_sb; + case FSNOTIFY_EVENT_FILE_RANGE: + return file_range_path(data)->dentry->d_sb; case FSNOTIFY_EVENT_ERROR: return ((struct fs_error_report *) data)->sb; default: @@ -366,6 +395,18 @@ static inline struct fs_error_report *fsnotify_data_error_report( } } +static inline const struct file_range *fsnotify_data_file_range( + const void *data, + int data_type) +{ + switch (data_type) { + case FSNOTIFY_EVENT_FILE_RANGE: + return (struct file_range *)data; + default: + return NULL; + } +} + /* * Index to merged marks iterator array that correlates to a type of watch. * The type of watched object can be deduced from the iterator type, but not @@ -457,13 +498,6 @@ FSNOTIFY_ITER_FUNCS(sb, SB) type++) /* - * fsnotify_connp_t is what we embed in objects which connector can be attached - * to. fsnotify_connp_t * is how we refer from connector back to object. - */ -struct fsnotify_mark_connector; -typedef struct fsnotify_mark_connector __rcu *fsnotify_connp_t; - -/* * Inode/vfsmount/sb point to this structure which tracks all marks attached to * the inode/vfsmount/sb. The reference to inode/vfsmount/sb is held by this * structure. We destroy this structure when there are no more marks attached @@ -471,12 +505,14 @@ typedef struct fsnotify_mark_connector __rcu *fsnotify_connp_t; */ struct fsnotify_mark_connector { spinlock_t lock; - unsigned short type; /* Type of object [lock] */ + unsigned char type; /* Type of object [lock] */ + unsigned char prio; /* Highest priority group */ +#define FSNOTIFY_CONN_FLAG_IS_WATCHED 0x01 #define FSNOTIFY_CONN_FLAG_HAS_IREF 0x02 unsigned short flags; /* flags [lock] */ union { /* Object pointer [lock] */ - fsnotify_connp_t *obj; + void *obj; /* Used listing heads to free after srcu period expires */ struct fsnotify_mark_connector *destroy_next; }; @@ -484,6 +520,37 @@ struct fsnotify_mark_connector { }; /* + * Container for per-sb fsnotify state (sb marks and more). + * Attached lazily on first marked object on the sb and freed when killing sb. + */ +struct fsnotify_sb_info { + struct fsnotify_mark_connector __rcu *sb_marks; + /* + * Number of inode/mount/sb objects that are being watched in this sb. + * Note that inodes objects are currently double-accounted. + * + * The value in watched_objects[prio] is the number of objects that are + * watched by groups of priority >= prio, so watched_objects[0] is the + * total number of watched objects in this sb. + */ + atomic_long_t watched_objects[__FSNOTIFY_PRIO_NUM]; +}; + +static inline struct fsnotify_sb_info *fsnotify_sb_info(struct super_block *sb) +{ +#ifdef CONFIG_FSNOTIFY + return READ_ONCE(sb->s_fsnotify_info); +#else + return NULL; +#endif +} + +static inline atomic_long_t *fsnotify_sb_watched_objects(struct super_block *sb) +{ + return &fsnotify_sb_info(sb)->watched_objects[0]; +} + +/* * A mark is simply an object attached to an in core inode which allows an * fsnotify listener to indicate they are either no longer interested in events * of a type matching mask or only interested in those events. @@ -546,6 +613,7 @@ extern int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data extern void __fsnotify_inode_delete(struct inode *inode); extern void __fsnotify_vfsmount_delete(struct vfsmount *mnt); extern void fsnotify_sb_delete(struct super_block *sb); +extern void fsnotify_sb_free(struct super_block *sb); extern u32 fsnotify_get_cookie(void); static inline __u32 fsnotify_parent_needed_mask(__u32 mask) @@ -563,12 +631,14 @@ static inline __u32 fsnotify_parent_needed_mask(__u32 mask) static inline int fsnotify_inode_watches_children(struct inode *inode) { + __u32 parent_mask = READ_ONCE(inode->i_fsnotify_mask); + /* FS_EVENT_ON_CHILD is set if the inode may care */ - if (!(inode->i_fsnotify_mask & FS_EVENT_ON_CHILD)) + if (!(parent_mask & FS_EVENT_ON_CHILD)) return 0; /* this inode might care about child events, does it care about the * specific set of events that can happen on a child? */ - return inode->i_fsnotify_mask & FS_EVENTS_POSS_ON_CHILD; + return parent_mask & FS_EVENTS_POSS_ON_CHILD; } /* @@ -582,7 +652,7 @@ static inline void fsnotify_update_flags(struct dentry *dentry) /* * Serialisation of setting PARENT_WATCHED on the dentries is provided * by d_lock. If inotify_inode_watched changes after we have taken - * d_lock, the following __fsnotify_update_child_dentry_flags call will + * d_lock, the following fsnotify_set_children_dentry_flags call will * find our entry, so it will spin until we complete here, and update * us with the new state. */ @@ -758,30 +828,35 @@ extern void fsnotify_recalc_mask(struct fsnotify_mark_connector *conn); extern void fsnotify_init_mark(struct fsnotify_mark *mark, struct fsnotify_group *group); /* Find mark belonging to given group in the list of marks */ -extern struct fsnotify_mark *fsnotify_find_mark(fsnotify_connp_t *connp, - struct fsnotify_group *group); +struct fsnotify_mark *fsnotify_find_mark(void *obj, unsigned int obj_type, + struct fsnotify_group *group); /* attach the mark to the object */ -extern int fsnotify_add_mark(struct fsnotify_mark *mark, - fsnotify_connp_t *connp, unsigned int obj_type, - int add_flags); -extern int fsnotify_add_mark_locked(struct fsnotify_mark *mark, - fsnotify_connp_t *connp, - unsigned int obj_type, int add_flags); +int fsnotify_add_mark(struct fsnotify_mark *mark, void *obj, + unsigned int obj_type, int add_flags); +int fsnotify_add_mark_locked(struct fsnotify_mark *mark, void *obj, + unsigned int obj_type, int add_flags); /* attach the mark to the inode */ static inline int fsnotify_add_inode_mark(struct fsnotify_mark *mark, struct inode *inode, int add_flags) { - return fsnotify_add_mark(mark, &inode->i_fsnotify_marks, - FSNOTIFY_OBJ_TYPE_INODE, add_flags); + return fsnotify_add_mark(mark, inode, FSNOTIFY_OBJ_TYPE_INODE, + add_flags); } static inline int fsnotify_add_inode_mark_locked(struct fsnotify_mark *mark, struct inode *inode, int add_flags) { - return fsnotify_add_mark_locked(mark, &inode->i_fsnotify_marks, - FSNOTIFY_OBJ_TYPE_INODE, add_flags); + return fsnotify_add_mark_locked(mark, inode, FSNOTIFY_OBJ_TYPE_INODE, + add_flags); +} + +static inline struct fsnotify_mark *fsnotify_find_inode_mark( + struct inode *inode, + struct fsnotify_group *group) +{ + return fsnotify_find_mark(inode, FSNOTIFY_OBJ_TYPE_INODE, group); } /* given a group and a mark, flag mark to be freed when all references are dropped */ @@ -820,9 +895,17 @@ static inline void fsnotify_init_event(struct fsnotify_event *event) { INIT_LIST_HEAD(&event->list); } +int fsnotify_pre_content(const struct path *path, const loff_t *ppos, + size_t count); #else +static inline int fsnotify_pre_content(const struct path *path, + const loff_t *ppos, size_t count) +{ + return 0; +} + static inline int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *name, struct inode *inode, u32 cookie) @@ -845,6 +928,9 @@ static inline void __fsnotify_vfsmount_delete(struct vfsmount *mnt) static inline void fsnotify_sb_delete(struct super_block *sb) {} +static inline void fsnotify_sb_free(struct super_block *sb) +{} + static inline void fsnotify_update_flags(struct dentry *dentry) {} diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 54d53f345d14..fbabc3d848b3 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -43,9 +43,8 @@ struct dyn_ftrace; char *arch_ftrace_match_adjust(char *str, const char *search); -#ifdef CONFIG_HAVE_FUNCTION_GRAPH_RETVAL -struct fgraph_ret_regs; -unsigned long ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs); +#ifdef CONFIG_HAVE_FUNCTION_GRAPH_FREGS +unsigned long ftrace_return_to_handler(struct ftrace_regs *fregs); #else unsigned long ftrace_return_to_handler(unsigned long frame_pointer); #endif @@ -83,19 +82,18 @@ static inline void early_trace_init(void) { } struct module; struct ftrace_hash; -struct ftrace_direct_func; #if defined(CONFIG_FUNCTION_TRACER) && defined(CONFIG_MODULES) && \ defined(CONFIG_DYNAMIC_FTRACE) -const char * +int ftrace_mod_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char **modname, char *sym); #else -static inline const char * +static inline int ftrace_mod_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char **modname, char *sym) { - return NULL; + return 0; } #endif @@ -114,14 +112,61 @@ static inline int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *val #ifdef CONFIG_FUNCTION_TRACER -extern int ftrace_enabled; +#include <linux/ftrace_regs.h> -#ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS +extern int ftrace_enabled; +/** + * ftrace_regs - ftrace partial/optimal register set + * + * ftrace_regs represents a group of registers which is used at the + * function entry and exit. There are three types of registers. + * + * - Registers for passing the parameters to callee, including the stack + * pointer. (e.g. rcx, rdx, rdi, rsi, r8, r9 and rsp on x86_64) + * - Registers for passing the return values to caller. + * (e.g. rax and rdx on x86_64) + * - Registers for hooking the function call and return including the + * frame pointer (the frame pointer is architecture/config dependent) + * (e.g. rip, rbp and rsp for x86_64) + * + * Also, architecture dependent fields can be used for internal process. + * (e.g. orig_ax on x86_64) + * + * Basically, ftrace_regs stores the registers related to the context. + * On function entry, registers for function parameters and hooking the + * function call are stored, and on function exit, registers for function + * return value and frame pointers are stored. + * + * And also, it dpends on the context that which registers are restored + * from the ftrace_regs. + * On the function entry, those registers will be restored except for + * the stack pointer, so that user can change the function parameters + * and instruction pointer (e.g. live patching.) + * On the function exit, only registers which is used for return values + * are restored. + * + * NOTE: user *must not* access regs directly, only do it via APIs, because + * the member can be changed according to the architecture. + * This is why the structure is empty here, so that nothing accesses + * the ftrace_regs directly. + */ struct ftrace_regs { - struct pt_regs regs; + /* Nothing to see here, use the accessor functions! */ }; -#define arch_ftrace_get_regs(fregs) (&(fregs)->regs) + +#define ftrace_regs_size() sizeof(struct __arch_ftrace_regs) + +#ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS +/* + * Architectures that define HAVE_DYNAMIC_FTRACE_WITH_ARGS must define their own + * arch_ftrace_get_regs() where it only returns pt_regs *if* it is fully + * populated. It should return NULL otherwise. + */ +static inline struct pt_regs *arch_ftrace_get_regs(struct ftrace_regs *fregs) +{ + return &arch_ftrace_regs(fregs)->regs; +} /* * ftrace_regs_set_instruction_pointer() is to be defined by the architecture @@ -131,6 +176,12 @@ struct ftrace_regs { #define ftrace_regs_set_instruction_pointer(fregs, ip) do { } while (0) #endif /* CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */ +#ifdef CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS + +static_assert(sizeof(struct pt_regs) == ftrace_regs_size()); + +#endif /* CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS */ + static __always_inline struct pt_regs *ftrace_get_regs(struct ftrace_regs *fregs) { if (!fregs) @@ -139,6 +190,54 @@ static __always_inline struct pt_regs *ftrace_get_regs(struct ftrace_regs *fregs return arch_ftrace_get_regs(fregs); } +#if !defined(CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS) || \ + defined(CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS) + +static __always_inline struct pt_regs * +ftrace_partial_regs(struct ftrace_regs *fregs, struct pt_regs *regs) +{ + /* + * If CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS=y, ftrace_regs memory + * layout is including pt_regs. So always returns that address. + * Since arch_ftrace_get_regs() will check some members and may return + * NULL, we can not use it. + */ + return &arch_ftrace_regs(fregs)->regs; +} + +#endif /* !CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS || CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS */ + +#ifdef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS + +/* + * Please define arch dependent pt_regs which compatible to the + * perf_arch_fetch_caller_regs() but based on ftrace_regs. + * This requires + * - user_mode(_regs) returns false (always kernel mode). + * - able to use the _regs for stack trace. + */ +#ifndef arch_ftrace_fill_perf_regs +/* As same as perf_arch_fetch_caller_regs(), do nothing by default */ +#define arch_ftrace_fill_perf_regs(fregs, _regs) do {} while (0) +#endif + +static __always_inline struct pt_regs * +ftrace_fill_perf_regs(struct ftrace_regs *fregs, struct pt_regs *regs) +{ + arch_ftrace_fill_perf_regs(fregs, regs); + return regs; +} + +#else /* !CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */ + +static __always_inline struct pt_regs * +ftrace_fill_perf_regs(struct ftrace_regs *fregs, struct pt_regs *regs) +{ + return &arch_ftrace_regs(fregs)->regs; +} + +#endif + /* * When true, the ftrace_regs_{get,set}_*() functions may be used on fregs. * Note: this can be true even when ftrace_get_regs() cannot provide a pt_regs. @@ -151,22 +250,22 @@ static __always_inline bool ftrace_regs_has_args(struct ftrace_regs *fregs) return ftrace_get_regs(fregs) != NULL; } -#ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS -#define ftrace_regs_get_instruction_pointer(fregs) \ - instruction_pointer(ftrace_get_regs(fregs)) -#define ftrace_regs_get_argument(fregs, n) \ - regs_get_kernel_argument(ftrace_get_regs(fregs), n) -#define ftrace_regs_get_stack_pointer(fregs) \ - kernel_stack_pointer(ftrace_get_regs(fregs)) -#define ftrace_regs_return_value(fregs) \ - regs_return_value(ftrace_get_regs(fregs)) -#define ftrace_regs_set_return_value(fregs, ret) \ - regs_set_return_value(ftrace_get_regs(fregs), ret) -#define ftrace_override_function_with_return(fregs) \ - override_function_with_return(ftrace_get_regs(fregs)) -#define ftrace_regs_query_register_offset(name) \ - regs_query_register_offset(name) -#endif +#ifdef CONFIG_HAVE_REGS_AND_STACK_ACCESS_API +static __always_inline unsigned long +ftrace_regs_get_kernel_stack_nth(struct ftrace_regs *fregs, unsigned int nth) +{ + unsigned long *stackp; + + stackp = (unsigned long *)ftrace_regs_get_stack_pointer(fregs); + if (((unsigned long)(stackp + nth) & ~(THREAD_SIZE - 1)) == + ((unsigned long)stackp & ~(THREAD_SIZE - 1))) + return *(stackp + nth); + + return 0; +} +#else /* !CONFIG_HAVE_REGS_AND_STACK_ACCESS_API */ +#define ftrace_regs_get_kernel_stack_nth(fregs, nth) (0L) +#endif /* CONFIG_HAVE_REGS_AND_STACK_ACCESS_API */ typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct ftrace_regs *fregs); @@ -228,6 +327,7 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops); * ftrace_enabled. * DIRECT - Used by the direct ftrace_ops helper for direct functions * (internal ftrace only, should not be used by others) + * SUBOP - Is controlled by another op in field managed. */ enum { FTRACE_OPS_FL_ENABLED = BIT(0), @@ -248,6 +348,7 @@ enum { FTRACE_OPS_FL_TRACE_ARRAY = BIT(15), FTRACE_OPS_FL_PERMANENT = BIT(16), FTRACE_OPS_FL_DIRECT = BIT(17), + FTRACE_OPS_FL_SUBOP = BIT(18), }; #ifndef CONFIG_DYNAMIC_FTRACE_WITH_ARGS @@ -335,7 +436,9 @@ struct ftrace_ops { unsigned long trampoline; unsigned long trampoline_size; struct list_head list; + struct list_head subop_list; ftrace_ops_func_t ops_func; + struct ftrace_ops *managed; #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS unsigned long direct_call; #endif @@ -414,7 +517,6 @@ struct ftrace_func_entry { }; #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS -extern int ftrace_direct_func_count; unsigned long ftrace_find_rec_direct(unsigned long ip); int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr); int unregister_ftrace_direct(struct ftrace_ops *ops, unsigned long addr, @@ -426,7 +528,6 @@ void ftrace_stub_direct_tramp(void); #else struct ftrace_ops; -# define ftrace_direct_func_count 0 static inline unsigned long ftrace_find_rec_direct(unsigned long ip) { return 0; @@ -470,7 +571,7 @@ static inline void arch_ftrace_set_direct_caller(struct ftrace_regs *fregs, extern int stack_tracer_enabled; -int stack_trace_sysctl(struct ctl_table *table, int write, void *buffer, +int stack_trace_sysctl(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); /* DO NOT MODIFY THIS VARIABLE DIRECTLY! */ @@ -512,6 +613,28 @@ static inline void stack_tracer_disable(void) { } static inline void stack_tracer_enable(void) { } #endif +enum { + FTRACE_UPDATE_CALLS = (1 << 0), + FTRACE_DISABLE_CALLS = (1 << 1), + FTRACE_UPDATE_TRACE_FUNC = (1 << 2), + FTRACE_START_FUNC_RET = (1 << 3), + FTRACE_STOP_FUNC_RET = (1 << 4), + FTRACE_MAY_SLEEP = (1 << 5), +}; + +/* Arches can override ftrace_get_symaddr() to convert fentry_ip to symaddr. */ +#ifndef ftrace_get_symaddr +/** + * ftrace_get_symaddr - return the symbol address from fentry_ip + * @fentry_ip: the address of ftrace location + * + * Get the symbol address from @fentry_ip (fast path). If there is no fast + * search path, this returns 0. + * User may need to use kallsyms API to find the symbol address. + */ +#define ftrace_get_symaddr(fentry_ip) (0) +#endif + #ifdef CONFIG_DYNAMIC_FTRACE void ftrace_arch_code_modify_prepare(void); @@ -606,15 +729,6 @@ void ftrace_set_global_notrace(unsigned char *buf, int len, int reset); void ftrace_free_filter(struct ftrace_ops *ops); void ftrace_ops_set_global_filter(struct ftrace_ops *ops); -enum { - FTRACE_UPDATE_CALLS = (1 << 0), - FTRACE_DISABLE_CALLS = (1 << 1), - FTRACE_UPDATE_TRACE_FUNC = (1 << 2), - FTRACE_START_FUNC_RET = (1 << 3), - FTRACE_STOP_FUNC_RET = (1 << 4), - FTRACE_MAY_SLEEP = (1 << 5), -}; - /* * The FTRACE_UPDATE_* enum is used to pass information back * from the ftrace_update_record() and ftrace_test_record() @@ -822,7 +936,8 @@ static inline int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) extern int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr); #if defined(CONFIG_DYNAMIC_FTRACE_WITH_REGS) || \ - defined(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS) + defined(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS) || \ + defined(CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS) /** * ftrace_modify_call - convert from one addr to another (no nop) * @rec: the call site record (e.g. mcount/fentry) @@ -1013,6 +1128,17 @@ struct ftrace_graph_ent { } __packed; /* + * Structure that defines an entry function trace with retaddr. + * It's already packed but the attribute "packed" is needed + * to remove extra padding at the end. + */ +struct fgraph_retaddr_ent { + unsigned long func; /* Current function */ + int depth; + unsigned long retaddr; /* Return address */ +} __packed; + +/* * Structure that defines a return function trace. * It's already packed but the attribute "packed" is needed * to remove extra padding at the end. @@ -1025,23 +1151,38 @@ struct ftrace_graph_ret { int depth; /* Number of functions that overran the depth limit for current task */ unsigned int overrun; - unsigned long long calltime; - unsigned long long rettime; } __packed; +struct fgraph_ops; + /* Type of the callback handlers for tracing function graph*/ -typedef void (*trace_func_graph_ret_t)(struct ftrace_graph_ret *); /* return */ -typedef int (*trace_func_graph_ent_t)(struct ftrace_graph_ent *); /* entry */ +typedef void (*trace_func_graph_ret_t)(struct ftrace_graph_ret *, + struct fgraph_ops *, + struct ftrace_regs *); /* return */ +typedef int (*trace_func_graph_ent_t)(struct ftrace_graph_ent *, + struct fgraph_ops *, + struct ftrace_regs *); /* entry */ -extern int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace); +extern int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace, + struct fgraph_ops *gops, + struct ftrace_regs *fregs); +bool ftrace_pids_enabled(struct ftrace_ops *ops); #ifdef CONFIG_FUNCTION_GRAPH_TRACER struct fgraph_ops { trace_func_graph_ent_t entryfunc; trace_func_graph_ret_t retfunc; + struct ftrace_ops ops; /* for the hash lists */ + void *private; + trace_func_graph_ent_t saved_func; + int idx; }; +void *fgraph_reserve_data(int idx, int size_bytes); +void *fgraph_retrieve_data(int idx, int *size_bytes); +void *fgraph_retrieve_parent_data(int idx, int *size_bytes, int depth); + /* * Stack of return addresses for functions * of a thread. @@ -1050,16 +1191,10 @@ struct fgraph_ops { struct ftrace_ret_stack { unsigned long ret; unsigned long func; - unsigned long long calltime; -#ifdef CONFIG_FUNCTION_PROFILER - unsigned long long subtime; -#endif #ifdef HAVE_FUNCTION_GRAPH_FP_TEST unsigned long fp; #endif -#ifdef HAVE_FUNCTION_GRAPH_RET_ADDR_PTR unsigned long *retp; -#endif }; /* @@ -1070,14 +1205,23 @@ struct ftrace_ret_stack { extern void return_to_handler(void); extern int -function_graph_enter(unsigned long ret, unsigned long func, - unsigned long frame_pointer, unsigned long *retp); +function_graph_enter_regs(unsigned long ret, unsigned long func, + unsigned long frame_pointer, unsigned long *retp, + struct ftrace_regs *fregs); + +static inline int function_graph_enter(unsigned long ret, unsigned long func, + unsigned long fp, unsigned long *retp) +{ + return function_graph_enter_regs(ret, func, fp, retp, NULL); +} struct ftrace_ret_stack * -ftrace_graph_get_ret_stack(struct task_struct *task, int idx); +ftrace_graph_get_ret_stack(struct task_struct *task, int skip); +unsigned long ftrace_graph_top_ret_addr(struct task_struct *task); unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx, unsigned long ret, unsigned long *retp); +unsigned long *fgraph_get_task_var(struct fgraph_ops *gops); /* * Sometimes we don't want to trace a function with the function @@ -1116,6 +1260,9 @@ extern void ftrace_graph_init_task(struct task_struct *t); extern void ftrace_graph_exit_task(struct task_struct *t); extern void ftrace_graph_init_idle_task(struct task_struct *t, int cpu); +/* Used by assembly, but to quiet sparse warnings */ +extern struct ftrace_ops *function_trace_op; + static inline void pause_graph_tracing(void) { atomic_inc(¤t->tracing_graph_pause); @@ -1159,7 +1306,7 @@ extern int tracepoint_printk; extern void disable_trace_on_warning(void); extern int __disable_trace_on_warning; -int tracepoint_printk_sysctl(struct ctl_table *table, int write, +int tracepoint_printk_sysctl(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); #else /* CONFIG_TRACING */ diff --git a/include/linux/ftrace_regs.h b/include/linux/ftrace_regs.h new file mode 100644 index 000000000000..bbc1873ca6b8 --- /dev/null +++ b/include/linux/ftrace_regs.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_FTRACE_REGS_H +#define _LINUX_FTRACE_REGS_H + +/* + * For archs that just copy pt_regs in ftrace regs, it can use this default. + * If an architecture does not use pt_regs, it must define all the below + * accessor functions. + */ +#ifndef HAVE_ARCH_FTRACE_REGS +struct __arch_ftrace_regs { + struct pt_regs regs; +}; + +#define arch_ftrace_regs(fregs) ((struct __arch_ftrace_regs *)(fregs)) + +struct ftrace_regs; + +#define ftrace_regs_get_instruction_pointer(fregs) \ + instruction_pointer(&arch_ftrace_regs(fregs)->regs) +#define ftrace_regs_get_argument(fregs, n) \ + regs_get_kernel_argument(&arch_ftrace_regs(fregs)->regs, n) +#define ftrace_regs_get_stack_pointer(fregs) \ + kernel_stack_pointer(&arch_ftrace_regs(fregs)->regs) +#define ftrace_regs_get_return_value(fregs) \ + regs_return_value(&arch_ftrace_regs(fregs)->regs) +#define ftrace_regs_set_return_value(fregs, ret) \ + regs_set_return_value(&arch_ftrace_regs(fregs)->regs, ret) +#define ftrace_override_function_with_return(fregs) \ + override_function_with_return(&arch_ftrace_regs(fregs)->regs) +#define ftrace_regs_query_register_offset(name) \ + regs_query_register_offset(name) +#define ftrace_regs_get_frame_pointer(fregs) \ + frame_pointer(&arch_ftrace_regs(fregs)->regs) + +#endif /* HAVE_ARCH_FTRACE_REGS */ + +#endif /* _LINUX_FTRACE_REGS_H */ diff --git a/include/linux/fw_table.h b/include/linux/fw_table.h index 3ff4c277296f..9bd605b87c4c 100644 --- a/include/linux/fw_table.h +++ b/include/linux/fw_table.h @@ -54,7 +54,7 @@ int cdat_table_parse(enum acpi_cdat_type type, #define EXPORT_SYMBOL_FWTBL_LIB(x) EXPORT_SYMBOL_ACPI_LIB(x) #define __init_or_fwtbl_lib __init_or_acpilib #else -#define EXPORT_SYMBOL_FWTBL_LIB(x) EXPORT_SYMBOL_NS_GPL(x, CXL) +#define EXPORT_SYMBOL_FWTBL_LIB(x) EXPORT_SYMBOL_NS_GPL(x, "CXL") #define __init_or_fwtbl_lib #endif diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index 0d79070c5a70..0731994b9d7c 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -112,6 +112,7 @@ struct fwnode_reference_args { * @device_is_available: Return true if the device is available. * @device_get_match_data: Return the device driver match data. * @property_present: Return true if a property is present. + * @property_read_bool: Return a boolean property value. * @property_read_int_array: Read an array of integer properties. Return zero on * success, a negative error code otherwise. * @property_read_string_array: Read an array of string properties. Return zero @@ -141,6 +142,8 @@ struct fwnode_operations { (*device_get_dma_attr)(const struct fwnode_handle *fwnode); bool (*property_present)(const struct fwnode_handle *fwnode, const char *propname); + bool (*property_read_bool)(const struct fwnode_handle *fwnode, + const char *propname); int (*property_read_int_array)(const struct fwnode_handle *fwnode, const char *propname, unsigned int elem_size, void *val, diff --git a/include/linux/gameport.h b/include/linux/gameport.h index 07e370113b2b..86d62fdafd7a 100644 --- a/include/linux/gameport.h +++ b/include/linux/gameport.h @@ -58,7 +58,7 @@ struct gameport_driver { bool ignore; }; -#define to_gameport_driver(d) container_of(d, struct gameport_driver, driver) +#define to_gameport_driver(d) container_of_const(d, struct gameport_driver, driver) int gameport_open(struct gameport *gameport, struct gameport_driver *drv, int mode); void gameport_close(struct gameport *gameport); diff --git a/include/linux/generic-radix-tree.h b/include/linux/generic-radix-tree.h index f3512fddf3d7..5b51c3d582d6 100644 --- a/include/linux/generic-radix-tree.h +++ b/include/linux/generic-radix-tree.h @@ -41,6 +41,7 @@ #include <linux/limits.h> #include <linux/log2.h> #include <linux/math.h> +#include <linux/slab.h> #include <linux/types.h> struct genradix_root; @@ -48,10 +49,63 @@ struct genradix_root; #define GENRADIX_NODE_SHIFT 9 #define GENRADIX_NODE_SIZE (1U << GENRADIX_NODE_SHIFT) +#define GENRADIX_ARY (GENRADIX_NODE_SIZE / sizeof(struct genradix_node *)) +#define GENRADIX_ARY_SHIFT ilog2(GENRADIX_ARY) + +/* depth that's needed for a genradix that can address up to ULONG_MAX: */ +#define GENRADIX_MAX_DEPTH \ + DIV_ROUND_UP(BITS_PER_LONG - GENRADIX_NODE_SHIFT, GENRADIX_ARY_SHIFT) + +#define GENRADIX_DEPTH_MASK \ + ((unsigned long) (roundup_pow_of_two(GENRADIX_MAX_DEPTH + 1) - 1)) + +static inline int genradix_depth_shift(unsigned depth) +{ + return GENRADIX_NODE_SHIFT + GENRADIX_ARY_SHIFT * depth; +} + +/* + * Returns size (of data, in bytes) that a tree of a given depth holds: + */ +static inline size_t genradix_depth_size(unsigned depth) +{ + return 1UL << genradix_depth_shift(depth); +} + +static inline unsigned genradix_root_to_depth(struct genradix_root *r) +{ + return (unsigned long) r & GENRADIX_DEPTH_MASK; +} + +static inline struct genradix_node *genradix_root_to_node(struct genradix_root *r) +{ + return (void *) ((unsigned long) r & ~GENRADIX_DEPTH_MASK); +} + struct __genradix { struct genradix_root *root; }; +struct genradix_node { + union { + /* Interior node: */ + struct genradix_node *children[GENRADIX_ARY]; + + /* Leaf: */ + u8 data[GENRADIX_NODE_SIZE]; + }; +}; + +static inline struct genradix_node *genradix_alloc_node(gfp_t gfp_mask) +{ + return kzalloc(GENRADIX_NODE_SIZE, gfp_mask); +} + +static inline void genradix_free_node(struct genradix_node *node) +{ + kfree(node); +} + /* * NOTE: currently, sizeof(_type) must not be larger than GENRADIX_NODE_SIZE: */ @@ -128,6 +182,30 @@ static inline size_t __idx_to_offset(size_t idx, size_t obj_size) #define __genradix_idx_to_offset(_radix, _idx) \ __idx_to_offset(_idx, __genradix_obj_size(_radix)) +static inline void *__genradix_ptr_inlined(struct __genradix *radix, size_t offset) +{ + struct genradix_root *r = READ_ONCE(radix->root); + struct genradix_node *n = genradix_root_to_node(r); + unsigned level = genradix_root_to_depth(r); + unsigned shift = genradix_depth_shift(level); + + if (unlikely(ilog2(offset) >= genradix_depth_shift(level))) + return NULL; + + while (n && shift > GENRADIX_NODE_SHIFT) { + shift -= GENRADIX_ARY_SHIFT; + n = n->children[offset >> shift]; + offset &= (1UL << shift) - 1; + } + + return n ? &n->data[offset] : NULL; +} + +#define genradix_ptr_inlined(_radix, _idx) \ + (__genradix_cast(_radix) \ + __genradix_ptr_inlined(&(_radix)->tree, \ + __genradix_idx_to_offset(_radix, _idx))) + void *__genradix_ptr(struct __genradix *, size_t); /** @@ -142,7 +220,24 @@ void *__genradix_ptr(struct __genradix *, size_t); __genradix_ptr(&(_radix)->tree, \ __genradix_idx_to_offset(_radix, _idx))) -void *__genradix_ptr_alloc(struct __genradix *, size_t, gfp_t); +void *__genradix_ptr_alloc(struct __genradix *, size_t, + struct genradix_node **, gfp_t); + +#define genradix_ptr_alloc_inlined(_radix, _idx, _gfp) \ + (__genradix_cast(_radix) \ + (__genradix_ptr_inlined(&(_radix)->tree, \ + __genradix_idx_to_offset(_radix, _idx)) ?: \ + __genradix_ptr_alloc(&(_radix)->tree, \ + __genradix_idx_to_offset(_radix, _idx), \ + NULL, _gfp))) + +#define genradix_ptr_alloc_preallocated_inlined(_radix, _idx, _new_node, _gfp)\ + (__genradix_cast(_radix) \ + (__genradix_ptr_inlined(&(_radix)->tree, \ + __genradix_idx_to_offset(_radix, _idx)) ?: \ + __genradix_ptr_alloc(&(_radix)->tree, \ + __genradix_idx_to_offset(_radix, _idx), \ + _new_node, _gfp))) /** * genradix_ptr_alloc - get a pointer to a genradix entry, allocating it @@ -157,7 +252,13 @@ void *__genradix_ptr_alloc(struct __genradix *, size_t, gfp_t); (__genradix_cast(_radix) \ __genradix_ptr_alloc(&(_radix)->tree, \ __genradix_idx_to_offset(_radix, _idx), \ - _gfp)) + NULL, _gfp)) + +#define genradix_ptr_alloc_preallocated(_radix, _idx, _new_node, _gfp)\ + (__genradix_cast(_radix) \ + __genradix_ptr_alloc(&(_radix)->tree, \ + __genradix_idx_to_offset(_radix, _idx), \ + _new_node, _gfp)) struct genradix_iter { size_t offset; diff --git a/include/linux/genetlink.h b/include/linux/genetlink.h deleted file mode 100644 index c285968e437a..000000000000 --- a/include/linux/genetlink.h +++ /dev/null @@ -1,19 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __LINUX_GENERIC_NETLINK_H -#define __LINUX_GENERIC_NETLINK_H - -#include <uapi/linux/genetlink.h> - - -/* All generic netlink requests are serialized by a global lock. */ -extern void genl_lock(void); -extern void genl_unlock(void); - -/* for synchronisation between af_netlink and genetlink */ -extern atomic_t genl_sk_destructing_cnt; -extern wait_queue_head_t genl_sk_destructing_waitq; - -#define MODULE_ALIAS_GENL_FAMILY(family)\ - MODULE_ALIAS_NET_PF_PROTO_NAME(PF_NETLINK, NETLINK_GENERIC, "-family-" family) - -#endif /* __LINUX_GENERIC_NETLINK_H */ diff --git a/include/linux/genl_magic_struct.h b/include/linux/genl_magic_struct.h index a419d93789ff..621b87a87d74 100644 --- a/include/linux/genl_magic_struct.h +++ b/include/linux/genl_magic_struct.h @@ -15,8 +15,8 @@ #endif #include <linux/args.h> -#include <linux/genetlink.h> #include <linux/types.h> +#include <net/genetlink.h> extern int CONCATENATE(GENL_MAGIC_FAMILY, _genl_register)(void); extern void CONCATENATE(GENL_MAGIC_FAMILY, _genl_unregister)(void); diff --git a/include/linux/gfp.h b/include/linux/gfp.h index c775ea3c6015..6bb1a5a7a4ae 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -6,6 +6,8 @@ #include <linux/mmzone.h> #include <linux/topology.h> +#include <linux/alloc_tag.h> +#include <linux/sched.h> struct vm_area_struct; struct mempolicy; @@ -155,6 +157,31 @@ static inline int gfp_zonelist(gfp_t flags) } /* + * gfp flag masking for nested internal allocations. + * + * For code that needs to do allocations inside the public allocation API (e.g. + * memory allocation tracking code) the allocations need to obey the caller + * allocation context constrains to prevent allocation context mismatches (e.g. + * GFP_KERNEL allocations in GFP_NOFS contexts) from potential deadlock + * situations. + * + * It is also assumed that these nested allocations are for internal kernel + * object storage purposes only and are not going to be used for DMA, etc. Hence + * we strip out all the zone information and leave just the context information + * intact. + * + * Further, internal allocations must fail before the higher level allocation + * can fail, so we must make them fail faster and fail silently. We also don't + * want them to deplete emergency reserves. Hence nested allocations must be + * prepared for these allocations to fail. + */ +static inline gfp_t gfp_nested_mask(gfp_t flags) +{ + return ((flags & (GFP_KERNEL | GFP_ATOMIC | __GFP_NOLOCKDEP)) | + (__GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN)); +} + +/* * We get the zone list from the current node and the gfp_mask. * This zone list contains a maximum of MAX_NUMNODES*MAX_NR_ZONES zones. * There are two zonelists per node, one for all zones with memory and @@ -175,42 +202,42 @@ static inline void arch_free_page(struct page *page, int order) { } static inline void arch_alloc_page(struct page *page, int order) { } #endif -struct page *__alloc_pages(gfp_t gfp, unsigned int order, int preferred_nid, +struct page *__alloc_pages_noprof(gfp_t gfp, unsigned int order, int preferred_nid, nodemask_t *nodemask); -struct folio *__folio_alloc(gfp_t gfp, unsigned int order, int preferred_nid, +#define __alloc_pages(...) alloc_hooks(__alloc_pages_noprof(__VA_ARGS__)) + +struct folio *__folio_alloc_noprof(gfp_t gfp, unsigned int order, int preferred_nid, nodemask_t *nodemask); +#define __folio_alloc(...) alloc_hooks(__folio_alloc_noprof(__VA_ARGS__)) -unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, +unsigned long alloc_pages_bulk_noprof(gfp_t gfp, int preferred_nid, nodemask_t *nodemask, int nr_pages, - struct list_head *page_list, struct page **page_array); +#define __alloc_pages_bulk(...) alloc_hooks(alloc_pages_bulk_noprof(__VA_ARGS__)) -unsigned long alloc_pages_bulk_array_mempolicy(gfp_t gfp, +unsigned long alloc_pages_bulk_mempolicy_noprof(gfp_t gfp, unsigned long nr_pages, struct page **page_array); +#define alloc_pages_bulk_mempolicy(...) \ + alloc_hooks(alloc_pages_bulk_mempolicy_noprof(__VA_ARGS__)) /* Bulk allocate order-0 pages */ -static inline unsigned long -alloc_pages_bulk_list(gfp_t gfp, unsigned long nr_pages, struct list_head *list) -{ - return __alloc_pages_bulk(gfp, numa_mem_id(), NULL, nr_pages, list, NULL); -} +#define alloc_pages_bulk(_gfp, _nr_pages, _page_array) \ + __alloc_pages_bulk(_gfp, numa_mem_id(), NULL, _nr_pages, _page_array) static inline unsigned long -alloc_pages_bulk_array(gfp_t gfp, unsigned long nr_pages, struct page **page_array) -{ - return __alloc_pages_bulk(gfp, numa_mem_id(), NULL, nr_pages, NULL, page_array); -} - -static inline unsigned long -alloc_pages_bulk_array_node(gfp_t gfp, int nid, unsigned long nr_pages, struct page **page_array) +alloc_pages_bulk_node_noprof(gfp_t gfp, int nid, unsigned long nr_pages, + struct page **page_array) { if (nid == NUMA_NO_NODE) nid = numa_mem_id(); - return __alloc_pages_bulk(gfp, nid, NULL, nr_pages, NULL, page_array); + return alloc_pages_bulk_noprof(gfp, nid, NULL, nr_pages, page_array); } +#define alloc_pages_bulk_node(...) \ + alloc_hooks(alloc_pages_bulk_node_noprof(__VA_ARGS__)) + static inline void warn_if_node_offline(int this_node, gfp_t gfp_mask) { gfp_t warn_gfp = gfp_mask & (__GFP_THISNODE|__GFP_NOWARN); @@ -230,107 +257,107 @@ static inline void warn_if_node_offline(int this_node, gfp_t gfp_mask) * online. For more general interface, see alloc_pages_node(). */ static inline struct page * -__alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order) +__alloc_pages_node_noprof(int nid, gfp_t gfp_mask, unsigned int order) { VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES); warn_if_node_offline(nid, gfp_mask); - return __alloc_pages(gfp_mask, order, nid, NULL); + return __alloc_pages_noprof(gfp_mask, order, nid, NULL); } +#define __alloc_pages_node(...) alloc_hooks(__alloc_pages_node_noprof(__VA_ARGS__)) + static inline -struct folio *__folio_alloc_node(gfp_t gfp, unsigned int order, int nid) +struct folio *__folio_alloc_node_noprof(gfp_t gfp, unsigned int order, int nid) { VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES); warn_if_node_offline(nid, gfp); - return __folio_alloc(gfp, order, nid, NULL); + return __folio_alloc_noprof(gfp, order, nid, NULL); } +#define __folio_alloc_node(...) alloc_hooks(__folio_alloc_node_noprof(__VA_ARGS__)) + /* * Allocate pages, preferring the node given as nid. When nid == NUMA_NO_NODE, * prefer the current CPU's closest node. Otherwise node must be valid and * online. */ -static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask, - unsigned int order) +static inline struct page *alloc_pages_node_noprof(int nid, gfp_t gfp_mask, + unsigned int order) { if (nid == NUMA_NO_NODE) nid = numa_mem_id(); - return __alloc_pages_node(nid, gfp_mask, order); + return __alloc_pages_node_noprof(nid, gfp_mask, order); } +#define alloc_pages_node(...) alloc_hooks(alloc_pages_node_noprof(__VA_ARGS__)) + #ifdef CONFIG_NUMA -struct page *alloc_pages(gfp_t gfp, unsigned int order); -struct page *alloc_pages_mpol(gfp_t gfp, unsigned int order, +struct page *alloc_pages_noprof(gfp_t gfp, unsigned int order); +struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order); +struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order, struct mempolicy *mpol, pgoff_t ilx, int nid); -struct folio *folio_alloc(gfp_t gfp, unsigned int order); -struct folio *vma_alloc_folio(gfp_t gfp, int order, struct vm_area_struct *vma, - unsigned long addr, bool hugepage); +struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order, struct vm_area_struct *vma, + unsigned long addr); #else -static inline struct page *alloc_pages(gfp_t gfp_mask, unsigned int order) +static inline struct page *alloc_pages_noprof(gfp_t gfp_mask, unsigned int order) { - return alloc_pages_node(numa_node_id(), gfp_mask, order); + return alloc_pages_node_noprof(numa_node_id(), gfp_mask, order); } -static inline struct page *alloc_pages_mpol(gfp_t gfp, unsigned int order, - struct mempolicy *mpol, pgoff_t ilx, int nid) +static inline struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order) { - return alloc_pages(gfp, order); + return __folio_alloc_node_noprof(gfp, order, numa_node_id()); } -static inline struct folio *folio_alloc(gfp_t gfp, unsigned int order) +static inline struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order, + struct mempolicy *mpol, pgoff_t ilx, int nid) { - return __folio_alloc_node(gfp, order, numa_node_id()); + return folio_alloc_noprof(gfp, order); } -#define vma_alloc_folio(gfp, order, vma, addr, hugepage) \ - folio_alloc(gfp, order) +#define vma_alloc_folio_noprof(gfp, order, vma, addr) \ + folio_alloc_noprof(gfp, order) #endif + +#define alloc_pages(...) alloc_hooks(alloc_pages_noprof(__VA_ARGS__)) +#define folio_alloc(...) alloc_hooks(folio_alloc_noprof(__VA_ARGS__)) +#define folio_alloc_mpol(...) alloc_hooks(folio_alloc_mpol_noprof(__VA_ARGS__)) +#define vma_alloc_folio(...) alloc_hooks(vma_alloc_folio_noprof(__VA_ARGS__)) + #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) -static inline struct page *alloc_page_vma(gfp_t gfp, + +static inline struct page *alloc_page_vma_noprof(gfp_t gfp, struct vm_area_struct *vma, unsigned long addr) { - struct folio *folio = vma_alloc_folio(gfp, 0, vma, addr, false); + struct folio *folio = vma_alloc_folio_noprof(gfp, 0, vma, addr); return &folio->page; } +#define alloc_page_vma(...) alloc_hooks(alloc_page_vma_noprof(__VA_ARGS__)) -extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order); -extern unsigned long get_zeroed_page(gfp_t gfp_mask); +extern unsigned long get_free_pages_noprof(gfp_t gfp_mask, unsigned int order); +#define __get_free_pages(...) alloc_hooks(get_free_pages_noprof(__VA_ARGS__)) -void *alloc_pages_exact(size_t size, gfp_t gfp_mask) __alloc_size(1); -void free_pages_exact(void *virt, size_t size); -__meminit void *alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask) __alloc_size(2); - -#define __get_free_page(gfp_mask) \ - __get_free_pages((gfp_mask), 0) +extern unsigned long get_zeroed_page_noprof(gfp_t gfp_mask); +#define get_zeroed_page(...) alloc_hooks(get_zeroed_page_noprof(__VA_ARGS__)) -#define __get_dma_pages(gfp_mask, order) \ - __get_free_pages((gfp_mask) | GFP_DMA, (order)) +void *alloc_pages_exact_noprof(size_t size, gfp_t gfp_mask) __alloc_size(1); +#define alloc_pages_exact(...) alloc_hooks(alloc_pages_exact_noprof(__VA_ARGS__)) -extern void __free_pages(struct page *page, unsigned int order); -extern void free_pages(unsigned long addr, unsigned int order); +void free_pages_exact(void *virt, size_t size); -struct page_frag_cache; -void page_frag_cache_drain(struct page_frag_cache *nc); -extern void __page_frag_cache_drain(struct page *page, unsigned int count); -void *__page_frag_alloc_align(struct page_frag_cache *nc, unsigned int fragsz, - gfp_t gfp_mask, unsigned int align_mask); +__meminit void *alloc_pages_exact_nid_noprof(int nid, size_t size, gfp_t gfp_mask) __alloc_size(2); +#define alloc_pages_exact_nid(...) \ + alloc_hooks(alloc_pages_exact_nid_noprof(__VA_ARGS__)) -static inline void *page_frag_alloc_align(struct page_frag_cache *nc, - unsigned int fragsz, gfp_t gfp_mask, - unsigned int align) -{ - WARN_ON_ONCE(!is_power_of_2(align)); - return __page_frag_alloc_align(nc, fragsz, gfp_mask, -align); -} +#define __get_free_page(gfp_mask) \ + __get_free_pages((gfp_mask), 0) -static inline void *page_frag_alloc(struct page_frag_cache *nc, - unsigned int fragsz, gfp_t gfp_mask) -{ - return __page_frag_alloc_align(nc, fragsz, gfp_mask, ~0u); -} +#define __get_dma_pages(gfp_mask, order) \ + __get_free_pages((gfp_mask) | GFP_DMA, (order)) -extern void page_frag_free(void *addr); +extern void __free_pages(struct page *page, unsigned int order); +extern void free_pages(unsigned long addr, unsigned int order); #define __free_page(page) __free_pages((page), 0) #define free_page(addr) free_pages((addr), 0) @@ -374,11 +401,38 @@ extern gfp_t vma_thp_gfp_mask(struct vm_area_struct *vma); #ifdef CONFIG_CONTIG_ALLOC /* The below functions must be run on a range from a single zone. */ -extern int alloc_contig_range(unsigned long start, unsigned long end, +extern int alloc_contig_range_noprof(unsigned long start, unsigned long end, unsigned migratetype, gfp_t gfp_mask); -extern struct page *alloc_contig_pages(unsigned long nr_pages, gfp_t gfp_mask, - int nid, nodemask_t *nodemask); +#define alloc_contig_range(...) alloc_hooks(alloc_contig_range_noprof(__VA_ARGS__)) + +extern struct page *alloc_contig_pages_noprof(unsigned long nr_pages, gfp_t gfp_mask, + int nid, nodemask_t *nodemask); +#define alloc_contig_pages(...) alloc_hooks(alloc_contig_pages_noprof(__VA_ARGS__)) + #endif void free_contig_range(unsigned long pfn, unsigned long nr_pages); +#ifdef CONFIG_CONTIG_ALLOC +static inline struct folio *folio_alloc_gigantic_noprof(int order, gfp_t gfp, + int nid, nodemask_t *node) +{ + struct page *page; + + if (WARN_ON(!order || !(gfp & __GFP_COMP))) + return NULL; + + page = alloc_contig_pages_noprof(1 << order, gfp, nid, node); + + return page ? page_folio(page) : NULL; +} +#else +static inline struct folio *folio_alloc_gigantic_noprof(int order, gfp_t gfp, + int nid, nodemask_t *node) +{ + return NULL; +} +#endif +/* This should be paired with folio_put() rather than free_contig_range(). */ +#define folio_alloc_gigantic(...) alloc_hooks(folio_alloc_gigantic_noprof(__VA_ARGS__)) + #endif /* __LINUX_GFP_H */ diff --git a/include/linux/gfp_types.h b/include/linux/gfp_types.h index 13becafe41df..65db9349f905 100644 --- a/include/linux/gfp_types.h +++ b/include/linux/gfp_types.h @@ -55,6 +55,9 @@ enum { #ifdef CONFIG_LOCKDEP ___GFP_NOLOCKDEP_BIT, #endif +#ifdef CONFIG_SLAB_OBJ_EXT + ___GFP_NO_OBJ_EXT_BIT, +#endif ___GFP_LAST_BIT }; @@ -95,6 +98,11 @@ enum { #else #define ___GFP_NOLOCKDEP 0 #endif +#ifdef CONFIG_SLAB_OBJ_EXT +#define ___GFP_NO_OBJ_EXT BIT(___GFP_NO_OBJ_EXT_BIT) +#else +#define ___GFP_NO_OBJ_EXT 0 +#endif /* * Physical address zone modifiers (see linux/mmzone.h - low four bits) @@ -135,12 +143,15 @@ enum { * node with no fallbacks or placement policy enforcements. * * %__GFP_ACCOUNT causes the allocation to be accounted to kmemcg. + * + * %__GFP_NO_OBJ_EXT causes slab allocation to have no object extension. */ #define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE) #define __GFP_WRITE ((__force gfp_t)___GFP_WRITE) #define __GFP_HARDWALL ((__force gfp_t)___GFP_HARDWALL) #define __GFP_THISNODE ((__force gfp_t)___GFP_THISNODE) #define __GFP_ACCOUNT ((__force gfp_t)___GFP_ACCOUNT) +#define __GFP_NO_OBJ_EXT ((__force gfp_t)___GFP_NO_OBJ_EXT) /** * DOC: Watermark modifiers @@ -204,7 +215,8 @@ enum { * the caller still has to check for failures) while costly requests try to be * not disruptive and back off even without invoking the OOM killer. * The following three modifiers might be used to override some of these - * implicit rules. + * implicit rules. Please note that all of them must be used along with + * %__GFP_DIRECT_RECLAIM flag. * * %__GFP_NORETRY: The VM implementation will try only very lightweight * memory direct reclaim to get some memory under memory pressure (thus @@ -235,11 +247,14 @@ enum { * cannot handle allocation failures. The allocation could block * indefinitely but will never return with failure. Testing for * failure is pointless. + * It _must_ be blockable and used together with __GFP_DIRECT_RECLAIM. + * It should _never_ be used in non-sleepable contexts. * New users should be evaluated carefully (and the flag should be * used only when there is no reasonable failure policy) but it is * definitely preferable to use the flag rather than opencode endless * loop around allocator. - * Using this flag for costly allocations is _highly_ discouraged. + * Allocating pages from the buddy with __GFP_NOFAIL and order > 1 is + * not supported. Please consider using kvmalloc() instead. */ #define __GFP_IO ((__force gfp_t)___GFP_IO) #define __GFP_FS ((__force gfp_t)___GFP_FS) diff --git a/include/linux/gpio.h b/include/linux/gpio.h index 7ecc25c543ce..6270150f4e29 100644 --- a/include/linux/gpio.h +++ b/include/linux/gpio.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* - * <linux/gpio.h> + * NOTE: This header *must not* be included. * * This is the LEGACY GPIO bulk include file, including legacy APIs. It is * used for GPIO drivers still referencing the global GPIO numberspace, @@ -16,21 +16,10 @@ struct device; -/* see Documentation/driver-api/gpio/legacy.rst */ - /* make these flag values available regardless of GPIO kconfig options */ -#define GPIOF_DIR_OUT (0 << 0) -#define GPIOF_DIR_IN (1 << 0) - -#define GPIOF_INIT_LOW (0 << 1) -#define GPIOF_INIT_HIGH (1 << 1) - -#define GPIOF_IN (GPIOF_DIR_IN) -#define GPIOF_OUT_INIT_LOW (GPIOF_DIR_OUT | GPIOF_INIT_LOW) -#define GPIOF_OUT_INIT_HIGH (GPIOF_DIR_OUT | GPIOF_INIT_HIGH) - -/* Gpio pin is active-low */ -#define GPIOF_ACTIVE_LOW (1 << 2) +#define GPIOF_IN ((1 << 0)) +#define GPIOF_OUT_INIT_LOW ((0 << 0) | (0 << 1)) +#define GPIOF_OUT_INIT_HIGH ((0 << 0) | (1 << 1)) /** * struct gpio - a structure describing a GPIO with configuration @@ -74,6 +63,12 @@ static inline bool gpio_is_valid(int number) * Until they are all fixed, leave 0-512 space for them. */ #define GPIO_DYNAMIC_BASE 512 +/* + * Define the maximum of the possible GPIO in the global numberspace. + * While the GPIO base and numbers are positive, we limit it with signed + * maximum as a lot of code is using negative values for special cases. + */ +#define GPIO_DYNAMIC_MAX INT_MAX /* Always use the library code for GPIO management calls, * or when sleeping may be involved. @@ -114,10 +109,6 @@ static inline int gpio_to_irq(unsigned gpio) } int gpio_request_one(unsigned gpio, unsigned long flags, const char *label); -int gpio_request_array(const struct gpio *array, size_t num); -void gpio_free_array(const struct gpio *array, size_t num); - -/* CONFIG_GPIOLIB: bindings for managed devices that want to request gpios */ int devm_gpio_request(struct device *dev, unsigned gpio, const char *label); int devm_gpio_request_one(struct device *dev, unsigned gpio, @@ -146,11 +137,6 @@ static inline int gpio_request_one(unsigned gpio, return -ENOSYS; } -static inline int gpio_request_array(const struct gpio *array, size_t num) -{ - return -ENOSYS; -} - static inline void gpio_free(unsigned gpio) { might_sleep(); @@ -159,14 +145,6 @@ static inline void gpio_free(unsigned gpio) WARN_ON(1); } -static inline void gpio_free_array(const struct gpio *array, size_t num) -{ - might_sleep(); - - /* GPIO can never have been requested */ - WARN_ON(1); -} - static inline int gpio_direction_input(unsigned gpio) { return -ENOSYS; diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index f8617eaf08ba..2dd7cb9cc270 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -376,9 +376,7 @@ struct gpio_irq_chip { * @names: if set, must be an array of strings to use as alternative * names for the GPIOs in this chip. Any entry in the array * may be NULL if there is no alias for the GPIO, however the - * array must be @ngpio entries long. A name can include a single printk - * format specifier for an unsigned int. It is substituted by the actual - * number of the gpio. + * array must be @ngpio entries long. * @can_sleep: flag must be set iff get()/set() methods sleep, as they * must while accessing GPIO expander chips over I2C or SPI. This * implies that if the chip supports IRQs, these IRQs need to be threaded @@ -634,10 +632,6 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, devm_gpiochip_add_data_with_key(dev, gc, data, NULL, NULL) #endif /* CONFIG_LOCKDEP */ -static inline int gpiochip_add(struct gpio_chip *gc) -{ - return gpiochip_add_data(gc, NULL); -} void gpiochip_remove(struct gpio_chip *gc); int devm_gpiochip_add_data_with_key(struct device *dev, struct gpio_chip *gc, void *data, struct lock_class_key *lock_key, @@ -793,7 +787,6 @@ struct gpio_desc *gpiochip_request_own_desc(struct gpio_chip *gc, enum gpiod_flags dflags); void gpiochip_free_own_desc(struct gpio_desc *desc); -struct gpio_desc *gpiochip_get_desc(struct gpio_chip *gc, unsigned int hwnum); struct gpio_desc * gpio_device_get_desc(struct gpio_device *gdev, unsigned int hwnum); diff --git a/include/linux/gpio/property.h b/include/linux/gpio/property.h index 1a14e239221f..0d2209308002 100644 --- a/include/linux/gpio/property.h +++ b/include/linux/gpio/property.h @@ -4,7 +4,11 @@ #include <linux/property.h> +struct software_node; + #define PROPERTY_ENTRY_GPIO(_name_, _chip_node_, _idx_, _flags_) \ PROPERTY_ENTRY_REF(_name_, _chip_node_, _idx_, _flags_) +extern const struct software_node swnode_gpio_undefined; + #endif /* __LINUX_GPIO_PROPERTY_H */ diff --git a/include/linux/greybus.h b/include/linux/greybus.h index 634c9511cf78..4d58e27ceaf6 100644 --- a/include/linux/greybus.h +++ b/include/linux/greybus.h @@ -64,7 +64,7 @@ struct greybus_driver { struct device_driver driver; }; -#define to_greybus_driver(d) container_of(d, struct greybus_driver, driver) +#define to_greybus_driver(d) container_of_const(d, struct greybus_driver, driver) static inline void greybus_set_drvdata(struct gb_bundle *bundle, void *data) { diff --git a/include/linux/habanalabs/cpucp_if.h b/include/linux/habanalabs/cpucp_if.h index f316c8d0f3fc..7ed3fdd55dda 100644 --- a/include/linux/habanalabs/cpucp_if.h +++ b/include/linux/habanalabs/cpucp_if.h @@ -42,6 +42,12 @@ enum eq_event_id { EQ_EVENT_PWR_BRK_ENTRY, EQ_EVENT_PWR_BRK_EXIT, EQ_EVENT_HEARTBEAT, + EQ_EVENT_CPLD_RESET_REASON, + EQ_EVENT_CPLD_SHUTDOWN, + EQ_EVENT_POWER_EVT_START, + EQ_EVENT_POWER_EVT_END, + EQ_EVENT_THERMAL_EVT_START, + EQ_EVENT_THERMAL_EVT_END, }; /* @@ -391,6 +397,9 @@ struct hl_eq_entry { #define EQ_CTL_READY_SHIFT 31 #define EQ_CTL_READY_MASK 0x80000000 +#define EQ_CTL_EVENT_MODE_SHIFT 28 +#define EQ_CTL_EVENT_MODE_MASK 0x70000000 + #define EQ_CTL_EVENT_TYPE_SHIFT 16 #define EQ_CTL_EVENT_TYPE_MASK 0x0FFF0000 @@ -853,9 +862,6 @@ struct cpucp_packet { * result cannot be used to hold general purpose data. */ __le32 status_mask; - - /* random, used once number, for security packets */ - __le32 nonce; }; union { @@ -864,6 +870,9 @@ struct cpucp_packet { /* For Generic packet sub index */ __le32 pkt_subidx; + + /* random, used once number, for security packets */ + __le32 nonce; }; }; @@ -1140,6 +1149,7 @@ struct cpucp_security_info { * (0 = fully functional, 1 = lower-half is not functional, * 2 = upper-half is not functional) * @sec_info: security information + * @cpld_timestamp: CPLD programmed F/W timestamp. * @pll_map: Bit map of supported PLLs for current ASIC version. * @mme_binning_mask: MME binning mask, * bits [0:6] <==> dcore0 mme fma @@ -1165,7 +1175,7 @@ struct cpucp_security_info { struct cpucp_info { struct cpucp_sensor sensors[CPUCP_MAX_SENSORS]; __u8 kernel_version[VERSION_MAX_LEN]; - __le32 reserved; + __le32 reserved1; __le32 card_type; __le32 card_location; __le32 cpld_version; @@ -1187,7 +1197,7 @@ struct cpucp_info { __u8 substrate_version; __u8 eq_health_check_supported; struct cpucp_security_info sec_info; - __le32 fw_hbm_region_size; + __le32 cpld_timestamp; __u8 pll_map[PLL_MAP_LEN]; __le64 mme_binning_mask; __u8 fw_os_version[VERSION_MAX_LEN]; diff --git a/include/linux/habanalabs/hl_boot_if.h b/include/linux/habanalabs/hl_boot_if.h index 93366d5621fd..d2a9fc96424b 100644 --- a/include/linux/habanalabs/hl_boot_if.h +++ b/include/linux/habanalabs/hl_boot_if.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 * - * Copyright 2018-2020 HabanaLabs, Ltd. + * Copyright 2018-2023 HabanaLabs, Ltd. * All Rights Reserved. * */ @@ -49,7 +49,6 @@ enum cpu_boot_err { #define CPU_BOOT_ERR_FATAL_MASK \ ((1 << CPU_BOOT_ERR_DRAM_INIT_FAIL) | \ (1 << CPU_BOOT_ERR_PLL_FAIL) | \ - (1 << CPU_BOOT_ERR_DEVICE_UNUSABLE_FAIL) | \ (1 << CPU_BOOT_ERR_BINNING_FAIL) | \ (1 << CPU_BOOT_ERR_DRAM_SKIPPED) | \ (1 << CPU_BOOT_ERR_ENG_ARC_MEM_SCRUB_FAIL) | \ @@ -194,6 +193,8 @@ enum cpu_boot_dev_sts { CPU_BOOT_DEV_STS_FW_NIC_STAT_EXT_EN = 24, CPU_BOOT_DEV_STS_IS_IDLE_CHECK_EN = 25, CPU_BOOT_DEV_STS_MAP_HWMON_EN = 26, + CPU_BOOT_DEV_STS_NIC_MEM_CLEAR_EN = 27, + CPU_BOOT_DEV_STS_MMU_PGTBL_DRAM_EN = 28, CPU_BOOT_DEV_STS_ENABLED = 31, CPU_BOOT_DEV_STS_SCND_EN = 63, CPU_BOOT_DEV_STS_LAST = 64 /* we have 2 registers of 32 bits */ @@ -331,6 +332,17 @@ enum cpu_boot_dev_sts { * HWMON enum mapping to cpucp enums. * Initialized in: linux * + * CPU_BOOT_DEV_STS0_NIC_MEM_CLEAR_EN + * If set, means f/w supports nic hbm memory clear and + * tmr,txs hbm memory init. + * Initialized in: zephyr-mgmt + * + * CPU_BOOT_DEV_STS_MMU_PGTBL_DRAM_EN + * MMU page tables are located in DRAM. + * F/W initializes security settings for MMU + * page tables to reside in DRAM. + * Initialized in: zephyr-mgmt + * * CPU_BOOT_DEV_STS0_ENABLED Device status register enabled. * This is a main indication that the * running FW populates the device status @@ -367,6 +379,8 @@ enum cpu_boot_dev_sts { #define CPU_BOOT_DEV_STS0_FW_NIC_STAT_EXT_EN (1 << CPU_BOOT_DEV_STS_FW_NIC_STAT_EXT_EN) #define CPU_BOOT_DEV_STS0_IS_IDLE_CHECK_EN (1 << CPU_BOOT_DEV_STS_IS_IDLE_CHECK_EN) #define CPU_BOOT_DEV_STS0_MAP_HWMON_EN (1 << CPU_BOOT_DEV_STS_MAP_HWMON_EN) +#define CPU_BOOT_DEV_STS0_NIC_MEM_CLEAR_EN (1 << CPU_BOOT_DEV_STS_NIC_MEM_CLEAR_EN) +#define CPU_BOOT_DEV_STS0_MMU_PGTBL_DRAM_EN (1 << CPU_BOOT_DEV_STS_MMU_PGTBL_DRAM_EN) #define CPU_BOOT_DEV_STS0_ENABLED (1 << CPU_BOOT_DEV_STS_ENABLED) #define CPU_BOOT_DEV_STS1_ENABLED (1 << CPU_BOOT_DEV_STS_ENABLED) @@ -450,11 +464,11 @@ struct cpu_dyn_regs { __le32 gic_dma_core_irq_ctrl; __le32 gic_host_halt_irq; __le32 gic_host_ints_irq; - __le32 gic_host_soft_rst_irq; + __le32 reserved0; __le32 gic_rot_qm_irq_ctrl; - __le32 cpu_rst_status; + __le32 reserved1; __le32 eng_arc_irq_ctrl; - __le32 reserved1[20]; /* reserve for future use */ + __le32 reserved2[20]; /* reserve for future use */ }; /* TODO: remove the desc magic after the code is updated to use message */ @@ -551,8 +565,9 @@ enum lkd_fw_ascii_msg_lvls { LKD_FW_ASCII_MSG_DBG = 3, }; -#define LKD_FW_ASCII_MSG_MAX_LEN 128 -#define LKD_FW_ASCII_MSG_MAX 4 /* consider ABI when changing */ +#define LKD_FW_ASCII_MSG_MAX_LEN 128 +#define LKD_FW_ASCII_MSG_MAX 4 /* consider ABI when changing */ +#define LKD_FW_ASCII_MSG_MIN_DESC_VERSION 3 struct lkd_fw_ascii_msg { __u8 valid; diff --git a/include/linux/hdmi.h b/include/linux/hdmi.h index 3bb87bf6bc65..96bda41d9148 100644 --- a/include/linux/hdmi.h +++ b/include/linux/hdmi.h @@ -59,6 +59,15 @@ enum hdmi_infoframe_type { #define HDMI_DRM_INFOFRAME_SIZE 26 #define HDMI_VENDOR_INFOFRAME_SIZE 4 +/* + * HDMI 1.3a table 5-14 states that the largest InfoFrame_length is 27, + * not including the packet header or checksum byte. We include the + * checksum byte in HDMI_INFOFRAME_HEADER_SIZE, so this should allow + * HDMI_INFOFRAME_SIZE(MAX) to be the largest buffer we could ever need + * for any HDMI infoframe. + */ +#define HDMI_MAX_INFOFRAME_SIZE 27 + #define HDMI_INFOFRAME_SIZE(type) \ (HDMI_INFOFRAME_HEADER_SIZE + HDMI_ ## type ## _INFOFRAME_SIZE) @@ -436,7 +445,6 @@ ssize_t hdmi_infoframe_pack(union hdmi_infoframe *frame, void *buffer, size_t size); ssize_t hdmi_infoframe_pack_only(const union hdmi_infoframe *frame, void *buffer, size_t size); -int hdmi_infoframe_check(union hdmi_infoframe *frame); int hdmi_infoframe_unpack(union hdmi_infoframe *frame, const void *buffer, size_t size); void hdmi_infoframe_log(const char *level, struct device *dev, diff --git a/include/linux/hid-over-i2c.h b/include/linux/hid-over-i2c.h new file mode 100644 index 000000000000..3b1a0208a6b8 --- /dev/null +++ b/include/linux/hid-over-i2c.h @@ -0,0 +1,117 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright 2024 Intel Corporation */ + +#include <linux/bits.h> + +#ifndef _HID_OVER_I2C_H_ +#define _HID_OVER_I2C_H_ + +#define HIDI2C_REG_LEN sizeof(__le16) + +/* Input report type definition in HIDI2C protocol */ +enum hidi2c_report_type { + HIDI2C_RESERVED = 0, + HIDI2C_INPUT, + HIDI2C_OUTPUT, + HIDI2C_FEATURE, +}; + +/* Power state type definition in HIDI2C protocol */ +enum hidi2c_power_state { + HIDI2C_ON, + HIDI2C_SLEEP, +}; + +/* Opcode type definition in HIDI2C protocol */ +enum hidi2c_opcode { + HIDI2C_RESET = 1, + HIDI2C_GET_REPORT, + HIDI2C_SET_REPORT, + HIDI2C_GET_IDLE, + HIDI2C_SET_IDLE, + HIDI2C_GET_PROTOCOL, + HIDI2C_SET_PROTOCOL, + HIDI2C_SET_POWER, +}; + +/** + * struct hidi2c_report_packet - Report packet definition in HIDI2C protocol + * @len: data field length + * @data: HIDI2C report packet data + */ +struct hidi2c_report_packet { + __le16 len; + u8 data[]; +} __packed; + +#define HIDI2C_LENGTH_LEN sizeof(__le16) + +#define HIDI2C_PACKET_LEN(data_len) ((data_len) + HIDI2C_LENGTH_LEN) +#define HIDI2C_DATA_LEN(pkt_len) ((pkt_len) - HIDI2C_LENGTH_LEN) + +#define HIDI2C_CMD_MAX_RI 0x0F + +/** + * HIDI2C command data packet - Command packet definition in HIDI2C protocol + * @report_id: [0:3] report id (<15) for features or output reports + * @report_type: [4:5] indicate report type, reference to hidi2c_report_type + * @reserved0: [6:7] reserved bits + * @opcode: [8:11] command operation code, reference to hidi2c_opcode + * @reserved1: [12:15] reserved bits + * @report_id_optional: [23:16] appended 3rd byte. + * If the report_id in the low byte is set to the + * sentinel value (HIDI2C_CMD_MAX_RI), then this + * optional third byte represents the report id (>=15) + * Otherwise, not this 3rd byte. + */ + +#define HIDI2C_CMD_LEN sizeof(__le16) +#define HIDI2C_CMD_LEN_OPT (sizeof(__le16) + 1) +#define HIDI2C_CMD_REPORT_ID GENMASK(3, 0) +#define HIDI2C_CMD_REPORT_TYPE GENMASK(5, 4) +#define HIDI2C_CMD_OPCODE GENMASK(11, 8) +#define HIDI2C_CMD_OPCODE GENMASK(11, 8) +#define HIDI2C_CMD_3RD_BYTE GENMASK(23, 16) + +#define HIDI2C_HID_DESC_BCDVERSION 0x100 + +/** + * struct hidi2c_dev_descriptor - HIDI2C device descriptor definition + * @dev_desc_len: The length of the complete device descriptor, fixed to 0x1E (30). + * @bcd_ver: The version number of the HIDI2C protocol supported. + * In binary coded decimal (BCD) format. + * @report_desc_len: The length of the report descriptor + * @report_desc_reg: The register address to retrieve report descriptor + * @input_reg: the register address to retrieve input report + * @max_input_len: The length of the largest possible HID input (or feature) report + * @output_reg: the register address to send output report + * @max_output_len: The length of the largest output (or feature) report + * @cmd_reg: the register address to send command + * @data_reg: the register address to send command data + * @vendor_id: Device manufacturers vendor ID + * @product_id: Device unique model/product ID + * @version_id: Device’s unique version + * @reserved0: Reserved and should be 0 + * @reserved1: Reserved and should be 0 + */ +struct hidi2c_dev_descriptor { + __le16 dev_desc_len; + __le16 bcd_ver; + __le16 report_desc_len; + __le16 report_desc_reg; + __le16 input_reg; + __le16 max_input_len; + __le16 output_reg; + __le16 max_output_len; + __le16 cmd_reg; + __le16 data_reg; + __le16 vendor_id; + __le16 product_id; + __le16 version_id; + __le16 reserved0; + __le16 reserved1; +} __packed; + +#define HIDI2C_DEV_DESC_LEN sizeof(struct hidi2c_dev_descriptor) + +#endif /* _HID_OVER_I2C_H_ */ diff --git a/include/linux/hid-over-spi.h b/include/linux/hid-over-spi.h new file mode 100644 index 000000000000..da5a14b5e89b --- /dev/null +++ b/include/linux/hid-over-spi.h @@ -0,0 +1,155 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright 2024 Intel Corporation */ + +#ifndef _HID_OVER_SPI_H_ +#define _HID_OVER_SPI_H_ + +#include <linux/bits.h> +#include <linux/types.h> + +/* Input report type definition in HIDSPI protocol */ +enum input_report_type { + INVALID_INPUT_REPORT_TYPE_0 = 0, + DATA = 1, + INVALID_TYPE_2 = 2, + RESET_RESPONSE = 3, + COMMAND_RESPONSE = 4, + GET_FEATURE_RESPONSE = 5, + INVALID_TYPE_6 = 6, + DEVICE_DESCRIPTOR_RESPONSE = 7, + REPORT_DESCRIPTOR_RESPONSE = 8, + SET_FEATURE_RESPONSE = 9, + OUTPUT_REPORT_RESPONSE = 10, + GET_INPUT_REPORT_RESPONSE = 11, + INVALID_INPUT_REPORT_TYPE = 0xF, +}; + +/* Output report type definition in HIDSPI protocol */ +enum output_report_type { + INVALID_OUTPUT_REPORT_TYPE_0 = 0, + DEVICE_DESCRIPTOR = 1, + REPORT_DESCRIPTOR = 2, + SET_FEATURE = 3, + GET_FEATURE = 4, + OUTPUT_REPORT = 5, + GET_INPUT_REPORT = 6, + COMMAND_CONTENT = 7, +}; + +/* Set power command ID for output report */ +#define HIDSPI_SET_POWER_CMD_ID 1 + +/* Power state definition in HIDSPI protocol */ +enum hidspi_power_state { + HIDSPI_ON = 1, + HIDSPI_SLEEP = 2, + HIDSPI_OFF = 3, +}; + +/** + * Input report header definition in HIDSPI protocol + * Report header size is 32bits, it includes: + * protocol_ver: [0:3] Current supported HIDSPI protocol version, must be 0x3 + * reserved0: [4:7] Reserved bits + * input_report_len: [8:21] Input report length in number bytes divided by 4 + * last_frag_flag: [22]Indicate if this packet is last fragment. + * 1 - indicates last fragment + * 0 - indicates additional fragments + * reserved1: [23] Reserved bits + * @sync_const: [24:31] Used to validate input report header, must be 0x5A + */ +#define HIDSPI_INPUT_HEADER_SIZE sizeof(u32) +#define HIDSPI_INPUT_HEADER_VER GENMASK(3, 0) +#define HIDSPI_INPUT_HEADER_REPORT_LEN GENMASK(21, 8) +#define HIDSPI_INPUT_HEADER_LAST_FLAG BIT(22) +#define HIDSPI_INPUT_HEADER_SYNC GENMASK(31, 24) + +/** + * struct input_report_body_header - Input report body header definition in HIDSPI protocol + * @input_report_type: indicate input report type, reference to enum input_report_type + * @content_len: this input report body packet length + * @content_id: indicate this input report's report id + */ +struct input_report_body_header { + u8 input_report_type; + __le16 content_len; + u8 content_id; +} __packed; + +#define HIDSPI_INPUT_BODY_HEADER_SIZE sizeof(struct input_report_body_header) + +/** + * struct input_report_body - Input report body definition in HIDSPI protocol + * @body_hdr: input report body header + * @content: input report body content + */ +struct input_report_body { + struct input_report_body_header body_hdr; + u8 content[]; +} __packed; + +#define HIDSPI_INPUT_BODY_SIZE(content_len) ((content_len) + HIDSPI_INPUT_BODY_HEADER_SIZE) + +/** + * struct output_report_header - Output report header definition in HIDSPI protocol + * @report_type: output report type, reference to enum output_report_type + * @content_len: length of content + * @content_id: 0x00 - descriptors + * report id - Set/Feature feature or Input/Output Reports + * command opcode - for commands + */ +struct output_report_header { + u8 report_type; + __le16 content_len; + u8 content_id; +} __packed; + +#define HIDSPI_OUTPUT_REPORT_HEADER_SIZE sizeof(struct output_report_header) + +/** + * struct output_report - Output report definition in HIDSPI protocol + * @output_hdr: output report header + * @content: output report content + */ +struct output_report { + struct output_report_header output_hdr; + u8 content[]; +} __packed; + +#define HIDSPI_OUTPUT_REPORT_SIZE(content_len) ((content_len) + HIDSPI_OUTPUT_REPORT_HEADER_SIZE) + +/** + * struct hidspi_dev_descriptor - HIDSPI device descriptor definition + * @dev_desc_len: The length of the complete device descriptor, fixed to 0x18 (24). + * @bcd_ver: The version number of the HIDSPI protocol supported. + * In binary coded decimal (BCD) format. Must be fixed to 0x0300. + * @rep_desc_len: The length of the report descriptor + * @max_input_len: The length of the largest possible HID input (or feature) report + * @max_output_len: The length of the largest output (or feature) report + * @max_frag_len: The length of the largest fragment, where a fragment represents + * the body of an input report. + * @vendor_id: Device manufacturers vendor ID + * @product_id: Device unique model/product ID + * @version_id: Device’s unique version + * @flags: Specify flags for the device’s operation + * @reserved: Reserved and should be 0 + */ +struct hidspi_dev_descriptor { + __le16 dev_desc_len; + __le16 bcd_ver; + __le16 rep_desc_len; + __le16 max_input_len; + __le16 max_output_len; + __le16 max_frag_len; + __le16 vendor_id; + __le16 product_id; + __le16 version_id; + __le16 flags; + __le32 reserved; +}; + +#define HIDSPI_DEVICE_DESCRIPTOR_SIZE sizeof(struct hidspi_dev_descriptor) +#define HIDSPI_INPUT_DEVICE_DESCRIPTOR_SIZE \ + (HIDSPI_INPUT_BODY_HEADER_SIZE + HIDSPI_DEVICE_DESCRIPTOR_SIZE) + +#endif /* _HID_OVER_SPI_H_ */ diff --git a/include/linux/hid-sensor-ids.h b/include/linux/hid-sensor-ids.h index 6730ee900ee1..8a03d9696b1c 100644 --- a/include/linux/hid-sensor-ids.h +++ b/include/linux/hid-sensor-ids.h @@ -30,6 +30,8 @@ #define HID_USAGE_SENSOR_PROX 0x200011 #define HID_USAGE_SENSOR_DATA_PRESENCE 0x2004b0 #define HID_USAGE_SENSOR_HUMAN_PRESENCE 0x2004b1 +#define HID_USAGE_SENSOR_HUMAN_PROXIMITY 0x2004b2 +#define HID_USAGE_SENSOR_HUMAN_ATTENTION 0x2004bd /* Pressure (200031) */ #define HID_USAGE_SENSOR_PRESSURE 0x200031 diff --git a/include/linux/hid.h b/include/linux/hid.h index b12cb1c8e682..cdc0dc13c87f 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -46,7 +46,7 @@ struct hid_item { __s16 s16; __u32 u32; __s32 s32; - __u8 *longdata; + const __u8 *longdata; } data; }; @@ -218,6 +218,7 @@ struct hid_item { #define HID_GD_DOWN 0x00010091 #define HID_GD_RIGHT 0x00010092 #define HID_GD_LEFT 0x00010093 +#define HID_GD_DO_NOT_DISTURB 0x0001009b /* Microsoft Win8 Wireless Radio Controls CA usage codes */ #define HID_GD_RFKILL_BTN 0x000100c6 #define HID_GD_RFKILL_LED 0x000100c7 @@ -359,6 +360,7 @@ struct hid_item { * | @HID_QUIRK_NO_OUTPUT_REPORTS_ON_INTR_EP: * | @HID_QUIRK_HAVE_SPECIAL_DRIVER: * | @HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE: + * | @HID_QUIRK_IGNORE_SPECIAL_DRIVER * | @HID_QUIRK_FULLSPEED_INTERVAL: * | @HID_QUIRK_NO_INIT_REPORTS: * | @HID_QUIRK_NO_IGNORE: @@ -384,6 +386,7 @@ struct hid_item { #define HID_QUIRK_HAVE_SPECIAL_DRIVER BIT(19) #define HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE BIT(20) #define HID_QUIRK_NOINVERT BIT(21) +#define HID_QUIRK_IGNORE_SPECIAL_DRIVER BIT(22) #define HID_QUIRK_FULLSPEED_INTERVAL BIT(28) #define HID_QUIRK_NO_INIT_REPORTS BIT(29) #define HID_QUIRK_NO_IGNORE BIT(30) @@ -474,9 +477,9 @@ struct hid_usage { __s8 wheel_factor; /* 120/resolution_multiplier */ __u16 code; /* input driver code */ __u8 type; /* input driver type */ - __s8 hat_min; /* hat switch fun */ - __s8 hat_max; /* ditto */ - __s8 hat_dir; /* ditto */ + __s16 hat_min; /* hat switch fun */ + __s16 hat_max; /* ditto */ + __s16 hat_dir; /* ditto */ __s16 wheel_accumulated; /* hi-res wheel */ }; @@ -599,15 +602,17 @@ enum hid_battery_status { struct hid_driver; struct hid_ll_driver; -struct hid_device { /* device report descriptor */ - __u8 *dev_rdesc; - unsigned dev_rsize; - __u8 *rdesc; - unsigned rsize; +struct hid_device { + const __u8 *dev_rdesc; /* device report descriptor */ + const __u8 *bpf_rdesc; /* bpf modified report descriptor, if any */ + const __u8 *rdesc; /* currently used report descriptor */ + unsigned int dev_rsize; + unsigned int bpf_rsize; + unsigned int rsize; + unsigned int collection_size; /* Number of allocated hid_collections */ struct hid_collection *collection; /* List of HID collections */ - unsigned collection_size; /* Number of allocated hid_collections */ - unsigned maxcollection; /* Number of parsed collections */ - unsigned maxapplication; /* Number of applications */ + unsigned int maxcollection; /* Number of parsed collections */ + unsigned int maxapplication; /* Number of applications */ __u16 bus; /* BUS ID */ __u16 group; /* Report group */ __u32 vendor; /* Vendor ID */ @@ -822,7 +827,7 @@ struct hid_driver { struct hid_usage *usage, __s32 value); void (*report)(struct hid_device *hdev, struct hid_report *report); - __u8 *(*report_fixup)(struct hid_device *hdev, __u8 *buf, + const __u8 *(*report_fixup)(struct hid_device *hdev, __u8 *buf, unsigned int *size); int (*input_mapping)(struct hid_device *hdev, @@ -940,6 +945,8 @@ extern void hidinput_report_event(struct hid_device *hid, struct hid_report *rep extern int hidinput_connect(struct hid_device *hid, unsigned int force); extern void hidinput_disconnect(struct hid_device *); +struct hid_field *hid_find_field(struct hid_device *hdev, unsigned int report_type, + unsigned int application, unsigned int usage); int hid_set_field(struct hid_field *, unsigned, __s32); int hid_input_report(struct hid_device *hid, enum hid_report_type type, u8 *data, u32 size, int interrupt); @@ -953,7 +960,7 @@ struct hid_device *hid_allocate_device(void); struct hid_report *hid_register_report(struct hid_device *device, enum hid_report_type type, unsigned int id, unsigned int application); -int hid_parse_report(struct hid_device *hid, __u8 *start, unsigned size); +int hid_parse_report(struct hid_device *hid, const __u8 *start, unsigned size); struct hid_report *hid_validate_values(struct hid_device *hid, enum hid_report_type type, unsigned int id, unsigned int field_index, @@ -972,7 +979,6 @@ const struct hid_device_id *hid_match_device(struct hid_device *hdev, struct hid_driver *hdrv); bool hid_compare_device_paths(struct hid_device *hdev_a, struct hid_device *hdev_b, char separator); -s32 hid_snto32(__u32 value, unsigned n); __u32 hid_field_extract(const struct hid_device *hid, __u8 *report, unsigned offset, unsigned n); @@ -1125,6 +1131,13 @@ int __must_check hid_hw_open(struct hid_device *hdev); void hid_hw_close(struct hid_device *hdev); void hid_hw_request(struct hid_device *hdev, struct hid_report *report, enum hid_class_request reqtype); +int __hid_hw_raw_request(struct hid_device *hdev, + unsigned char reportnum, __u8 *buf, + size_t len, enum hid_report_type rtype, + enum hid_class_request reqtype, + __u64 source, bool from_bpf); +int __hid_hw_output_report(struct hid_device *hdev, __u8 *buf, size_t len, __u64 source, + bool from_bpf); int hid_hw_raw_request(struct hid_device *hdev, unsigned char reportnum, __u8 *buf, size_t len, enum hid_report_type rtype, diff --git a/include/linux/hid_bpf.h b/include/linux/hid_bpf.h index 7118ac28d468..a2e47dbcf82c 100644 --- a/include/linux/hid_bpf.h +++ b/include/linux/hid_bpf.h @@ -4,7 +4,8 @@ #define __HID_BPF_H #include <linux/bpf.h> -#include <linux/spinlock.h> +#include <linux/mutex.h> +#include <linux/srcu.h> #include <uapi/linux/hid.h> struct hid_device; @@ -20,15 +21,9 @@ struct hid_device; * struct hid_bpf_ctx - User accessible data for all HID programs * * ``data`` is not directly accessible from the context. We need to issue - * a call to ``hid_bpf_get_data()`` in order to get a pointer to that field. + * a call to hid_bpf_get_data() in order to get a pointer to that field. * - * All of these fields are currently read-only. - * - * @index: program index in the jump table. No special meaning (a smaller index - * doesn't mean the program will be executed before another program with - * a bigger index). - * @hid: the ``struct hid_device`` representing the device itself - * @report_type: used for ``hid_bpf_device_event()`` + * @hid: the &struct hid_device representing the device itself * @allocated_size: Allocated size of data. * * This is how much memory is available and can be requested @@ -45,73 +40,147 @@ struct hid_device; * ``size`` must always be less or equal than ``allocated_size`` (it is enforced * once all BPF programs have been run). * @retval: Return value of the previous program. + * + * ``hid`` and ``allocated_size`` are read-only, ``size`` and ``retval`` are read-write. */ struct hid_bpf_ctx { - __u32 index; - const struct hid_device *hid; + struct hid_device *hid; __u32 allocated_size; - enum hid_report_type report_type; union { __s32 retval; __s32 size; }; }; -/** - * enum hid_bpf_attach_flags - flags used when attaching a HIF-BPF program - * - * @HID_BPF_FLAG_NONE: no specific flag is used, the kernel choses where to - * insert the program - * @HID_BPF_FLAG_INSERT_HEAD: insert the given program before any other program - * currently attached to the device. This doesn't - * guarantee that this program will always be first - * @HID_BPF_FLAG_MAX: sentinel value, not to be used by the callers - */ -enum hid_bpf_attach_flags { - HID_BPF_FLAG_NONE = 0, - HID_BPF_FLAG_INSERT_HEAD = _BITUL(0), - HID_BPF_FLAG_MAX, -}; - -/* Following functions are tracepoints that BPF programs can attach to */ -int hid_bpf_device_event(struct hid_bpf_ctx *ctx); -int hid_bpf_rdesc_fixup(struct hid_bpf_ctx *ctx); - /* * Below is HID internal */ -/* internal function to call eBPF programs, not to be used by anybody */ -int __hid_bpf_tail_call(struct hid_bpf_ctx *ctx); - #define HID_BPF_MAX_PROGS_PER_DEV 64 #define HID_BPF_FLAG_MASK (((HID_BPF_FLAG_MAX - 1) << 1) - 1) -/* types of HID programs to attach to */ -enum hid_bpf_prog_type { - HID_BPF_PROG_TYPE_UNDEF = -1, - HID_BPF_PROG_TYPE_DEVICE_EVENT, /* an event is emitted from the device */ - HID_BPF_PROG_TYPE_RDESC_FIXUP, - HID_BPF_PROG_TYPE_MAX, -}; struct hid_report_enum; -struct hid_bpf_ops { +struct hid_ops { struct hid_report *(*hid_get_report)(struct hid_report_enum *report_enum, const u8 *data); int (*hid_hw_raw_request)(struct hid_device *hdev, unsigned char reportnum, __u8 *buf, size_t len, enum hid_report_type rtype, - enum hid_class_request reqtype); + enum hid_class_request reqtype, + u64 source, bool from_bpf); + int (*hid_hw_output_report)(struct hid_device *hdev, __u8 *buf, size_t len, + u64 source, bool from_bpf); + int (*hid_input_report)(struct hid_device *hid, enum hid_report_type type, + u8 *data, u32 size, int interrupt, u64 source, bool from_bpf, + bool lock_already_taken); struct module *owner; const struct bus_type *bus_type; }; -extern struct hid_bpf_ops *hid_bpf_ops; +extern const struct hid_ops *hid_ops; + +/** + * struct hid_bpf_ops - A BPF struct_ops of callbacks allowing to attach HID-BPF + * programs to a HID device + * @hid_id: the HID uniq ID to attach to. This is writeable before ``load()``, and + * cannot be changed after + * @flags: flags used while attaching the struct_ops to the device. Currently only + * available value is %0 or ``BPF_F_BEFORE``. + * Writeable only before ``load()`` + */ +struct hid_bpf_ops { + /* hid_id needs to stay first so we can easily change it + * from userspace. + */ + int hid_id; + u32 flags; + + /* private: do not show up in the docs */ + struct list_head list; + + /* public: rest should show up in the docs */ + + /** + * @hid_device_event: called whenever an event is coming in from the device + * + * It has the following arguments: + * + * ``ctx``: The HID-BPF context as &struct hid_bpf_ctx + * + * Return: %0 on success and keep processing; a positive + * value to change the incoming size buffer; a negative + * error code to interrupt the processing of this event + * + * Context: Interrupt context. + */ + int (*hid_device_event)(struct hid_bpf_ctx *ctx, enum hid_report_type report_type, + u64 source); + + /** + * @hid_rdesc_fixup: called when the probe function parses the report descriptor + * of the HID device + * + * It has the following arguments: + * + * ``ctx``: The HID-BPF context as &struct hid_bpf_ctx + * + * Return: %0 on success and keep processing; a positive + * value to change the incoming size buffer; a negative + * error code to interrupt the processing of this device + */ + int (*hid_rdesc_fixup)(struct hid_bpf_ctx *ctx); + + /** + * @hid_hw_request: called whenever a hid_hw_raw_request() call is emitted + * on the HID device + * + * It has the following arguments: + * + * ``ctx``: The HID-BPF context as &struct hid_bpf_ctx + * + * ``reportnum``: the report number, as in hid_hw_raw_request() + * + * ``rtype``: the report type (``HID_INPUT_REPORT``, ``HID_FEATURE_REPORT``, + * ``HID_OUTPUT_REPORT``) + * + * ``reqtype``: the request + * + * ``source``: a u64 referring to a uniq but identifiable source. If %0, the + * kernel itself emitted that call. For hidraw, ``source`` is set + * to the associated ``struct file *``. + * + * Return: %0 to keep processing the request by hid-core; any other value + * stops hid-core from processing that event. A positive value should be + * returned with the number of bytes returned in the incoming buffer; a + * negative error code interrupts the processing of this call. + */ + int (*hid_hw_request)(struct hid_bpf_ctx *ctx, unsigned char reportnum, + enum hid_report_type rtype, enum hid_class_request reqtype, + u64 source); -struct hid_bpf_prog_list { - u16 prog_idx[HID_BPF_MAX_PROGS_PER_DEV]; - u8 prog_cnt; + /** + * @hid_hw_output_report: called whenever a hid_hw_output_report() call is emitted + * on the HID device + * + * It has the following arguments: + * + * ``ctx``: The HID-BPF context as &struct hid_bpf_ctx + * + * ``source``: a u64 referring to a uniq but identifiable source. If %0, the + * kernel itself emitted that call. For hidraw, ``source`` is set + * to the associated ``struct file *``. + * + * Return: %0 to keep processing the request by hid-core; any other value + * stops hid-core from processing that event. A positive value should be + * returned with the number of bytes written to the device; a negative error + * code interrupts the processing of this call. + */ + int (*hid_hw_output_report)(struct hid_bpf_ctx *ctx, u64 source); + + + /* private: do not show up in the docs */ + struct hid_device *hdev; }; /* stored in each device */ @@ -121,38 +190,46 @@ struct hid_bpf { * to this HID device */ u32 allocated_data; - - struct hid_bpf_prog_list __rcu *progs[HID_BPF_PROG_TYPE_MAX]; /* attached BPF progs */ bool destroyed; /* prevents the assignment of any progs */ - spinlock_t progs_lock; /* protects RCU update of progs */ -}; - -/* specific HID-BPF link when a program is attached to a device */ -struct hid_bpf_link { - struct bpf_link link; - int hid_table_index; + struct hid_bpf_ops *rdesc_ops; + struct list_head prog_list; + struct mutex prog_list_lock; /* protects prog_list update */ + struct srcu_struct srcu; /* protects prog_list read-only access */ }; #ifdef CONFIG_HID_BPF u8 *dispatch_hid_bpf_device_event(struct hid_device *hid, enum hid_report_type type, u8 *data, - u32 *size, int interrupt); + u32 *size, int interrupt, u64 source, bool from_bpf); +int dispatch_hid_bpf_raw_requests(struct hid_device *hdev, + unsigned char reportnum, __u8 *buf, + u32 size, enum hid_report_type rtype, + enum hid_class_request reqtype, + u64 source, bool from_bpf); +int dispatch_hid_bpf_output_report(struct hid_device *hdev, __u8 *buf, u32 size, + u64 source, bool from_bpf); int hid_bpf_connect_device(struct hid_device *hdev); void hid_bpf_disconnect_device(struct hid_device *hdev); void hid_bpf_destroy_device(struct hid_device *hid); -void hid_bpf_device_init(struct hid_device *hid); -u8 *call_hid_bpf_rdesc_fixup(struct hid_device *hdev, u8 *rdesc, unsigned int *size); +int hid_bpf_device_init(struct hid_device *hid); +const u8 *call_hid_bpf_rdesc_fixup(struct hid_device *hdev, const u8 *rdesc, unsigned int *size); #else /* CONFIG_HID_BPF */ static inline u8 *dispatch_hid_bpf_device_event(struct hid_device *hid, enum hid_report_type type, - u8 *data, u32 *size, int interrupt) { return data; } + u8 *data, u32 *size, int interrupt, + u64 source, bool from_bpf) { return data; } +static inline int dispatch_hid_bpf_raw_requests(struct hid_device *hdev, + unsigned char reportnum, u8 *buf, + u32 size, enum hid_report_type rtype, + enum hid_class_request reqtype, + u64 source, bool from_bpf) { return 0; } +static inline int dispatch_hid_bpf_output_report(struct hid_device *hdev, __u8 *buf, u32 size, + u64 source, bool from_bpf) { return 0; } static inline int hid_bpf_connect_device(struct hid_device *hdev) { return 0; } static inline void hid_bpf_disconnect_device(struct hid_device *hdev) {} static inline void hid_bpf_destroy_device(struct hid_device *hid) {} -static inline void hid_bpf_device_init(struct hid_device *hid) {} -static inline u8 *call_hid_bpf_rdesc_fixup(struct hid_device *hdev, u8 *rdesc, unsigned int *size) -{ - return kmemdup(rdesc, *size, GFP_KERNEL); -} +static inline int hid_bpf_device_init(struct hid_device *hid) { return 0; } +static inline const u8 *call_hid_bpf_rdesc_fixup(struct hid_device *hdev, const u8 *rdesc, + unsigned int *size) { return rdesc; } #endif /* CONFIG_HID_BPF */ diff --git a/include/linux/hidraw.h b/include/linux/hidraw.h index cd67f4ca5599..18fd30a288de 100644 --- a/include/linux/hidraw.h +++ b/include/linux/hidraw.h @@ -32,6 +32,7 @@ struct hidraw_list { struct hidraw *hidraw; struct list_head node; struct mutex read_mutex; + bool revoked; }; #ifdef CONFIG_HIDRAW diff --git a/include/linux/highmem-internal.h b/include/linux/highmem-internal.h index a3028e400a9c..dd100e849f5e 100644 --- a/include/linux/highmem-internal.h +++ b/include/linux/highmem-internal.h @@ -131,22 +131,17 @@ static inline void __kunmap_atomic(const void *addr) preempt_enable(); } -unsigned int __nr_free_highpages(void); -extern atomic_long_t _totalhigh_pages; +unsigned long __nr_free_highpages(void); +unsigned long __totalhigh_pages(void); -static inline unsigned int nr_free_highpages(void) +static inline unsigned long nr_free_highpages(void) { return __nr_free_highpages(); } static inline unsigned long totalhigh_pages(void) { - return (unsigned long)atomic_long_read(&_totalhigh_pages); -} - -static inline void totalhigh_pages_add(long count) -{ - atomic_long_add(count, &_totalhigh_pages); + return __totalhigh_pages(); } static inline bool is_kmap_addr(const void *x) @@ -239,8 +234,8 @@ static inline void __kunmap_atomic(const void *addr) preempt_enable(); } -static inline unsigned int nr_free_highpages(void) { return 0; } -static inline unsigned long totalhigh_pages(void) { return 0UL; } +static inline unsigned long nr_free_highpages(void) { return 0; } +static inline unsigned long totalhigh_pages(void) { return 0; } static inline bool is_kmap_addr(const void *x) { diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 00341b56d291..5c6bea81a90e 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -179,7 +179,7 @@ static inline void *kmap_local_folio(struct folio *folio, size_t offset); static inline void *kmap_atomic(struct page *page); /* Highmem related interfaces for management code */ -static inline unsigned int nr_free_highpages(void); +static inline unsigned long nr_free_highpages(void); static inline unsigned long totalhigh_pages(void); #ifndef ARCH_HAS_FLUSH_ANON_PAGE @@ -226,8 +226,8 @@ struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma, { struct folio *folio; - folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, vaddr, false); - if (folio) + folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, vaddr); + if (folio && user_alloc_needs_zeroing()) clear_user_highpage(&folio->page, vaddr); return folio; @@ -352,6 +352,9 @@ static inline int copy_mc_user_highpage(struct page *to, struct page *from, kunmap_local(vto); kunmap_local(vfrom); + if (ret) + memory_failure_queue(page_to_pfn(from), 0); + return ret; } @@ -368,6 +371,9 @@ static inline int copy_mc_highpage(struct page *to, struct page *from) kunmap_local(vto); kunmap_local(vfrom); + if (ret) + memory_failure_queue(page_to_pfn(from), 0); + return ret; } #else diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h index 9d7754ad5e9b..99fcf65d575f 100644 --- a/include/linux/hisi_acc_qm.h +++ b/include/linux/hisi_acc_qm.h @@ -97,6 +97,8 @@ /* page number for queue file region */ #define QM_DOORBELL_PAGE_NR 1 +#define QM_DEV_ALG_MAX_LEN 256 + /* uacce mode of the driver */ #define UACCE_MODE_NOUACCE 0 /* don't use uacce */ #define UACCE_MODE_SVA 1 /* use uacce sva mode */ @@ -122,6 +124,7 @@ enum qm_hw_ver { QM_HW_V1 = 0x20, QM_HW_V2 = 0x21, QM_HW_V3 = 0x30, + QM_HW_V4 = 0x50, }; enum qm_fun_type { @@ -156,6 +159,7 @@ enum qm_cap_bits { QM_SUPPORT_MB_COMMAND, QM_SUPPORT_SVA_PREFETCH, QM_SUPPORT_RPM, + QM_SUPPORT_DAE, }; struct qm_dev_alg { @@ -229,6 +233,12 @@ struct hisi_qm_status { struct hisi_qm; +enum acc_err_result { + ACC_ERR_NONE, + ACC_ERR_NEED_RESET, + ACC_ERR_RECOVERED, +}; + struct hisi_qm_err_info { char *acpi_rst; u32 msi_wr_port; @@ -257,9 +267,11 @@ struct hisi_qm_err_ini { void (*close_axi_master_ooo)(struct hisi_qm *qm); void (*open_sva_prefetch)(struct hisi_qm *qm); void (*close_sva_prefetch)(struct hisi_qm *qm); - void (*log_dev_hw_err)(struct hisi_qm *qm, u32 err_sts); void (*show_last_dfx_regs)(struct hisi_qm *qm); void (*err_info_init)(struct hisi_qm *qm); + enum acc_err_result (*get_err_result)(struct hisi_qm *qm); + bool (*dev_is_abnormal)(struct hisi_qm *qm); + int (*set_priv_status)(struct hisi_qm *qm); }; struct hisi_qm_cap_info { @@ -274,13 +286,25 @@ struct hisi_qm_cap_info { u32 v3_val; }; +struct hisi_qm_cap_query_info { + u32 type; + const char *name; + u32 offset; + u32 v1_val; + u32 v2_val; + u32 v3_val; +}; + struct hisi_qm_cap_record { u32 type; + const char *name; u32 cap_val; }; struct hisi_qm_cap_tables { + u32 qm_cap_size; struct hisi_qm_cap_record *qm_cap_table; + u32 dev_cap_size; struct hisi_qm_cap_record *dev_cap_table; }; @@ -374,6 +398,8 @@ struct hisi_qm { struct mutex mailbox_lock; + struct mutex ifc_lock; + const struct hisi_qm_hw_ops *ops; struct qm_debug debug; @@ -436,37 +462,6 @@ struct hisi_qp { struct uacce_queue *uacce_q; }; -static inline int q_num_set(const char *val, const struct kernel_param *kp, - unsigned int device) -{ - struct pci_dev *pdev; - u32 n, q_num; - int ret; - - if (!val) - return -EINVAL; - - pdev = pci_get_device(PCI_VENDOR_ID_HUAWEI, device, NULL); - if (!pdev) { - q_num = min_t(u32, QM_QNUM_V1, QM_QNUM_V2); - pr_info("No device found currently, suppose queue number is %u\n", - q_num); - } else { - if (pdev->revision == QM_HW_V1) - q_num = QM_QNUM_V1; - else - q_num = QM_QNUM_V2; - - pci_dev_put(pdev); - } - - ret = kstrtou32(val, 10, &n); - if (ret || n < QM_MIN_QNUM || n > q_num) - return -EINVAL; - - return param_set_int(val, kp); -} - static inline int vfs_num_set(const char *val, const struct kernel_param *kp) { u32 n; @@ -526,6 +521,8 @@ static inline void hisi_qm_del_list(struct hisi_qm *qm, struct hisi_qm_list *qm_ mutex_unlock(&qm_list->lock); } +int hisi_qm_q_num_set(const char *val, const struct kernel_param *kp, + unsigned int device); int hisi_qm_init(struct hisi_qm *qm); void hisi_qm_uninit(struct hisi_qm *qm); int hisi_qm_start(struct hisi_qm *qm); @@ -583,6 +580,9 @@ void hisi_qm_regs_dump(struct seq_file *s, struct debugfs_regset32 *regset); u32 hisi_qm_get_hw_info(struct hisi_qm *qm, const struct hisi_qm_cap_info *info_table, u32 index, bool is_read); +u32 hisi_qm_get_cap_value(struct hisi_qm *qm, + const struct hisi_qm_cap_query_info *info_table, + u32 index, bool is_read); int hisi_qm_set_algs(struct hisi_qm *qm, u64 alg_msk, const struct qm_dev_alg *dev_algs, u32 dev_algs_size); diff --git a/include/linux/host1x.h b/include/linux/host1x.h index 9c8119ed13a4..9fa9c30a34e6 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -14,12 +14,17 @@ enum host1x_class { HOST1X_CLASS_HOST1X = 0x1, + HOST1X_CLASS_NVJPG1 = 0x7, + HOST1X_CLASS_NVENC = 0x21, + HOST1X_CLASS_NVENC1 = 0x22, HOST1X_CLASS_GR2D = 0x51, HOST1X_CLASS_GR2D_SB = 0x52, HOST1X_CLASS_VIC = 0x5D, HOST1X_CLASS_GR3D = 0x60, + HOST1X_CLASS_NVJPG = 0xC0, HOST1X_CLASS_NVDEC = 0xF0, HOST1X_CLASS_NVDEC1 = 0xF5, + HOST1X_CLASS_OFA = 0xF8, }; struct host1x; @@ -466,6 +471,7 @@ struct host1x_memory_context { refcount_t ref; struct pid *owner; + struct device_dma_parameters dma_parms; struct device dev; u64 dma_mask; u32 stream_id; diff --git a/include/linux/host1x_context_bus.h b/include/linux/host1x_context_bus.h index 72462737a6db..c928cb432680 100644 --- a/include/linux/host1x_context_bus.h +++ b/include/linux/host1x_context_bus.h @@ -9,7 +9,7 @@ #include <linux/device.h> #ifdef CONFIG_TEGRA_HOST1X_CONTEXT_BUS -extern struct bus_type host1x_context_device_bus_type; +extern const struct bus_type host1x_context_device_bus_type; #endif #endif diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index aa1e65ccb615..f7bfdcf0dda3 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -228,32 +228,17 @@ static inline void hrtimer_cancel_wait_running(struct hrtimer *timer) /* Initialize timers: */ extern void hrtimer_init(struct hrtimer *timer, clockid_t which_clock, enum hrtimer_mode mode); -extern void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, clockid_t clock_id, - enum hrtimer_mode mode); +extern void hrtimer_setup(struct hrtimer *timer, enum hrtimer_restart (*function)(struct hrtimer *), + clockid_t clock_id, enum hrtimer_mode mode); +extern void hrtimer_setup_on_stack(struct hrtimer *timer, + enum hrtimer_restart (*function)(struct hrtimer *), + clockid_t clock_id, enum hrtimer_mode mode); +extern void hrtimer_setup_sleeper_on_stack(struct hrtimer_sleeper *sl, clockid_t clock_id, + enum hrtimer_mode mode); #ifdef CONFIG_DEBUG_OBJECTS_TIMERS -extern void hrtimer_init_on_stack(struct hrtimer *timer, clockid_t which_clock, - enum hrtimer_mode mode); -extern void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl, - clockid_t clock_id, - enum hrtimer_mode mode); - extern void destroy_hrtimer_on_stack(struct hrtimer *timer); #else -static inline void hrtimer_init_on_stack(struct hrtimer *timer, - clockid_t which_clock, - enum hrtimer_mode mode) -{ - hrtimer_init(timer, which_clock, mode); -} - -static inline void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl, - clockid_t clock_id, - enum hrtimer_mode mode) -{ - hrtimer_init_sleeper(sl, clock_id, mode); -} - static inline void destroy_hrtimer_on_stack(struct hrtimer *timer) { } #endif @@ -337,6 +322,28 @@ static inline int hrtimer_callback_running(struct hrtimer *timer) return timer->base->running == timer; } +/** + * hrtimer_update_function - Update the timer's callback function + * @timer: Timer to update + * @function: New callback function + * + * Only safe to call if the timer is not enqueued. Can be called in the callback function if the + * timer is not enqueued at the same time (see the comments above HRTIMER_STATE_ENQUEUED). + */ +static inline void hrtimer_update_function(struct hrtimer *timer, + enum hrtimer_restart (*function)(struct hrtimer *)) +{ + guard(raw_spinlock_irqsave)(&timer->base->cpu_base->lock); + + if (WARN_ON_ONCE(hrtimer_is_queued(timer))) + return; + + if (WARN_ON_ONCE(!function)) + return; + + timer->function = function; +} + /* Forward a hrtimer so it expires after now: */ extern u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval); @@ -379,6 +386,7 @@ extern void __init hrtimers_init(void); extern void sysrq_timer_list_show(void); int hrtimers_prepare_cpu(unsigned int cpu); +int hrtimers_cpu_starting(unsigned int cpu); #ifdef CONFIG_HOTPLUG_CPU int hrtimers_cpu_dying(unsigned int cpu); #else diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index de0c89105076..93e509b6c00e 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -2,10 +2,10 @@ #ifndef _LINUX_HUGE_MM_H #define _LINUX_HUGE_MM_H -#include <linux/sched/coredump.h> #include <linux/mm_types.h> #include <linux/fs.h> /* only for vma_is_dax() */ +#include <linux/kobject.h> vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf); int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, @@ -63,9 +63,7 @@ ssize_t single_hugepage_flag_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf, enum transparent_hugepage_flag flag); extern struct kobj_attribute shmem_enabled_attr; - -#define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT) -#define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER) +extern struct kobj_attribute thpsize_shmem_enabled_attr; /* * Mask of all large folio orders supported for anonymous THP; all orders up to @@ -75,26 +73,100 @@ extern struct kobj_attribute shmem_enabled_attr; #define THP_ORDERS_ALL_ANON ((BIT(PMD_ORDER + 1) - 1) & ~(BIT(0) | BIT(1))) /* - * Mask of all large folio orders supported for file THP. + * Mask of all large folio orders supported for file THP. Folios in a DAX + * file is never split and the MAX_PAGECACHE_ORDER limit does not apply to + * it. Same to PFNMAPs where there's neither page* nor pagecache. */ -#define THP_ORDERS_ALL_FILE (BIT(PMD_ORDER) | BIT(PUD_ORDER)) +#define THP_ORDERS_ALL_SPECIAL \ + (BIT(PMD_ORDER) | BIT(PUD_ORDER)) +#define THP_ORDERS_ALL_FILE_DEFAULT \ + ((BIT(MAX_PAGECACHE_ORDER + 1) - 1) & ~BIT(0)) /* * Mask of all large folio orders supported for THP. */ -#define THP_ORDERS_ALL (THP_ORDERS_ALL_ANON | THP_ORDERS_ALL_FILE) +#define THP_ORDERS_ALL \ + (THP_ORDERS_ALL_ANON | THP_ORDERS_ALL_SPECIAL | THP_ORDERS_ALL_FILE_DEFAULT) -#define thp_vma_allowable_order(vma, vm_flags, smaps, in_pf, enforce_sysfs, order) \ - (!!thp_vma_allowable_orders(vma, vm_flags, smaps, in_pf, enforce_sysfs, BIT(order))) +#define TVA_SMAPS (1 << 0) /* Will be used for procfs */ +#define TVA_IN_PF (1 << 1) /* Page fault handler */ +#define TVA_ENFORCE_SYSFS (1 << 2) /* Obey sysfs configuration */ -#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#define thp_vma_allowable_order(vma, vm_flags, tva_flags, order) \ + (!!thp_vma_allowable_orders(vma, vm_flags, tva_flags, BIT(order))) + +#define split_folio(f) split_folio_to_list(f, NULL) + +#ifdef CONFIG_PGTABLE_HAS_HUGE_LEAVES #define HPAGE_PMD_SHIFT PMD_SHIFT -#define HPAGE_PMD_SIZE ((1UL) << HPAGE_PMD_SHIFT) +#define HPAGE_PUD_SHIFT PUD_SHIFT +#else +#define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; }) +#define HPAGE_PUD_SHIFT ({ BUILD_BUG(); 0; }) +#endif + +#define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT) +#define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER) #define HPAGE_PMD_MASK (~(HPAGE_PMD_SIZE - 1)) +#define HPAGE_PMD_SIZE ((1UL) << HPAGE_PMD_SHIFT) -#define HPAGE_PUD_SHIFT PUD_SHIFT -#define HPAGE_PUD_SIZE ((1UL) << HPAGE_PUD_SHIFT) +#define HPAGE_PUD_ORDER (HPAGE_PUD_SHIFT-PAGE_SHIFT) +#define HPAGE_PUD_NR (1<<HPAGE_PUD_ORDER) #define HPAGE_PUD_MASK (~(HPAGE_PUD_SIZE - 1)) +#define HPAGE_PUD_SIZE ((1UL) << HPAGE_PUD_SHIFT) + +enum mthp_stat_item { + MTHP_STAT_ANON_FAULT_ALLOC, + MTHP_STAT_ANON_FAULT_FALLBACK, + MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE, + MTHP_STAT_ZSWPOUT, + MTHP_STAT_SWPIN, + MTHP_STAT_SWPIN_FALLBACK, + MTHP_STAT_SWPIN_FALLBACK_CHARGE, + MTHP_STAT_SWPOUT, + MTHP_STAT_SWPOUT_FALLBACK, + MTHP_STAT_SHMEM_ALLOC, + MTHP_STAT_SHMEM_FALLBACK, + MTHP_STAT_SHMEM_FALLBACK_CHARGE, + MTHP_STAT_SPLIT, + MTHP_STAT_SPLIT_FAILED, + MTHP_STAT_SPLIT_DEFERRED, + MTHP_STAT_NR_ANON, + MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, + __MTHP_STAT_COUNT +}; + +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && defined(CONFIG_SYSFS) +struct mthp_stat { + unsigned long stats[ilog2(MAX_PTRS_PER_PTE) + 1][__MTHP_STAT_COUNT]; +}; + +DECLARE_PER_CPU(struct mthp_stat, mthp_stats); + +static inline void mod_mthp_stat(int order, enum mthp_stat_item item, int delta) +{ + if (order <= 0 || order > PMD_ORDER) + return; + + this_cpu_add(mthp_stats.stats[order][item], delta); +} + +static inline void count_mthp_stat(int order, enum mthp_stat_item item) +{ + mod_mthp_stat(order, item, 1); +} + +#else +static inline void mod_mthp_stat(int order, enum mthp_stat_item item, int delta) +{ +} + +static inline void count_mthp_stat(int order, enum mthp_stat_item item) +{ +} +#endif + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE extern unsigned long transparent_hugepage_flags; extern unsigned long huge_anon_orders_always; @@ -114,18 +186,6 @@ static inline bool hugepage_global_always(void) (1<<TRANSPARENT_HUGEPAGE_FLAG); } -static inline bool hugepage_flags_enabled(void) -{ - /* - * We cover both the anon and the file-backed case here; we must return - * true if globally enabled, even when all anon sizes are set to never. - * So we don't need to look at huge_anon_orders_inherit. - */ - return hugepage_global_enabled() || - huge_anon_orders_always || - huge_anon_orders_madvise; -} - static inline int highest_order(unsigned long orders) { return fls_long(orders) - 1; @@ -196,31 +256,16 @@ static inline unsigned long thp_vma_suitable_orders(struct vm_area_struct *vma, return orders; } -static inline bool file_thp_enabled(struct vm_area_struct *vma) -{ - struct inode *inode; - - if (!vma->vm_file) - return false; - - inode = vma->vm_file->f_inode; - - return (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS)) && - !inode_is_open_for_write(inode) && S_ISREG(inode->i_mode); -} - unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma, - unsigned long vm_flags, bool smaps, - bool in_pf, bool enforce_sysfs, + unsigned long vm_flags, + unsigned long tva_flags, unsigned long orders); /** * thp_vma_allowable_orders - determine hugepage orders that are allowed for vma * @vma: the vm area to check * @vm_flags: use these vm_flags instead of vma->vm_flags - * @smaps: whether answer will be used for smaps file - * @in_pf: whether answer will be used by page fault handler - * @enforce_sysfs: whether sysfs config should be taken into account + * @tva_flags: Which TVA flags to honour * @orders: bitfield of all orders to consider * * Calculates the intersection of the requested hugepage orders and the allowed @@ -233,12 +278,12 @@ unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma, */ static inline unsigned long thp_vma_allowable_orders(struct vm_area_struct *vma, - unsigned long vm_flags, bool smaps, - bool in_pf, bool enforce_sysfs, + unsigned long vm_flags, + unsigned long tva_flags, unsigned long orders) { /* Optimization to check if required orders are enabled early. */ - if (enforce_sysfs && vma_is_anonymous(vma)) { + if ((tva_flags & TVA_ENFORCE_SYSFS) && vma_is_anonymous(vma)) { unsigned long mask = READ_ONCE(huge_anon_orders_always); if (vm_flags & VM_HUGEPAGE) @@ -252,26 +297,68 @@ unsigned long thp_vma_allowable_orders(struct vm_area_struct *vma, return 0; } - return __thp_vma_allowable_orders(vma, vm_flags, smaps, in_pf, - enforce_sysfs, orders); + return __thp_vma_allowable_orders(vma, vm_flags, tva_flags, orders); } +struct thpsize { + struct kobject kobj; + struct list_head node; + int order; +}; + +#define to_thpsize(kobj) container_of(kobj, struct thpsize, kobj) + #define transparent_hugepage_use_zero_page() \ (transparent_hugepage_flags & \ (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG)) +static inline bool vma_thp_disabled(struct vm_area_struct *vma, + unsigned long vm_flags) +{ + /* + * Explicitly disabled through madvise or prctl, or some + * architectures may disable THP for some mappings, for + * example, s390 kvm. + */ + return (vm_flags & VM_NOHUGEPAGE) || + test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags); +} + +static inline bool thp_disabled_by_hw(void) +{ + /* If the hardware/firmware marked hugepage support disabled. */ + return transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_UNSUPPORTED); +} + unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); +unsigned long thp_get_unmapped_area_vmflags(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, unsigned long flags, + vm_flags_t vm_flags); -void folio_prep_large_rmappable(struct folio *folio); -bool can_split_folio(struct folio *folio, int *pextra_pins); +bool can_split_folio(struct folio *folio, int caller_pins, int *pextra_pins); int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, unsigned int new_order); +int min_order_for_split(struct folio *folio); +int split_folio_to_list(struct folio *folio, struct list_head *list); static inline int split_huge_page(struct page *page) { - return split_huge_page_to_list_to_order(page, NULL, 0); + struct folio *folio = page_folio(page); + int ret = min_order_for_split(folio); + + if (ret < 0) + return ret; + + /* + * split_huge_page() locks the page before splitting and + * expects the same page that has been split to be locked when + * returned. split_folio(page_folio(page)) cannot be used here + * because it converts the page to folio and passes the head + * page to be split. + */ + return split_huge_page_to_list_to_order(page, NULL, ret); } -void deferred_split_folio(struct folio *folio); +void deferred_split_folio(struct folio *folio, bool partially_mapped); void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long address, bool freeze, struct folio *folio); @@ -292,6 +379,17 @@ void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud, unsigned long address); +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD +int change_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma, + pud_t *pudp, unsigned long addr, pgprot_t newprot, + unsigned long cp_flags); +#else +static inline int +change_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma, + pud_t *pudp, unsigned long addr, pgprot_t newprot, + unsigned long cp_flags) { return 0; } +#endif + #define split_huge_pud(__vma, __pud, __address) \ do { \ pud_t *____pud = (__pud); \ @@ -344,17 +442,15 @@ static inline bool folio_test_pmd_mappable(struct folio *folio) struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, int flags, struct dev_pagemap **pgmap); -struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, - pud_t *pud, int flags, struct dev_pagemap **pgmap); vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf); -extern struct page *huge_zero_page; +extern struct folio *huge_zero_folio; extern unsigned long huge_zero_pfn; -static inline bool is_huge_zero_page(struct page *page) +static inline bool is_huge_zero_folio(const struct folio *folio) { - return READ_ONCE(huge_zero_page) == page; + return READ_ONCE(huge_zero_folio) == folio; } static inline bool is_huge_zero_pmd(pmd_t pmd) @@ -362,13 +458,8 @@ static inline bool is_huge_zero_pmd(pmd_t pmd) return pmd_present(pmd) && READ_ONCE(huge_zero_pfn) == pmd_pfn(pmd); } -static inline bool is_huge_zero_pud(pud_t pud) -{ - return false; -} - -struct page *mm_get_huge_zero_page(struct mm_struct *mm); -void mm_put_huge_zero_page(struct mm_struct *mm); +struct folio *mm_get_huge_zero_folio(struct mm_struct *mm); +void mm_put_huge_zero_folio(struct mm_struct *mm); #define mk_huge_pmd(page, prot) pmd_mkhuge(mk_pmd(page, prot)) @@ -377,14 +468,12 @@ static inline bool thp_migration_supported(void) return IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION); } -#else /* CONFIG_TRANSPARENT_HUGEPAGE */ -#define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; }) -#define HPAGE_PMD_MASK ({ BUILD_BUG(); 0; }) -#define HPAGE_PMD_SIZE ({ BUILD_BUG(); 0; }) +void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address, + pmd_t *pmd, bool freeze, struct folio *folio); +bool unmap_huge_pmd_locked(struct vm_area_struct *vma, unsigned long addr, + pmd_t *pmdp, struct folio *folio); -#define HPAGE_PUD_SHIFT ({ BUILD_BUG(); 0; }) -#define HPAGE_PUD_MASK ({ BUILD_BUG(); 0; }) -#define HPAGE_PUD_SIZE ({ BUILD_BUG(); 0; }) +#else /* CONFIG_TRANSPARENT_HUGEPAGE */ static inline bool folio_test_pmd_mappable(struct folio *folio) { @@ -404,21 +493,27 @@ static inline unsigned long thp_vma_suitable_orders(struct vm_area_struct *vma, } static inline unsigned long thp_vma_allowable_orders(struct vm_area_struct *vma, - unsigned long vm_flags, bool smaps, - bool in_pf, bool enforce_sysfs, + unsigned long vm_flags, + unsigned long tva_flags, unsigned long orders) { return 0; } -static inline void folio_prep_large_rmappable(struct folio *folio) {} - #define transparent_hugepage_flags 0UL #define thp_get_unmapped_area NULL +static inline unsigned long +thp_get_unmapped_area_vmflags(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags, vm_flags_t vm_flags) +{ + return 0; +} + static inline bool -can_split_folio(struct folio *folio, int *pextra_pins) +can_split_folio(struct folio *folio, int caller_pins, int *pextra_pins) { return false; } @@ -432,7 +527,13 @@ static inline int split_huge_page(struct page *page) { return 0; } -static inline void deferred_split_folio(struct folio *folio) {} + +static inline int split_folio_to_list(struct folio *folio, struct list_head *list) +{ + return 0; +} + +static inline void deferred_split_folio(struct folio *folio, bool partially_mapped) {} #define split_huge_pmd(__vma, __pmd, __address) \ do { } while (0) @@ -440,6 +541,16 @@ static inline void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long address, bool freeze, struct folio *folio) {} static inline void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, bool freeze, struct folio *folio) {} +static inline void split_huge_pmd_locked(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmd, + bool freeze, struct folio *folio) {} + +static inline bool unmap_huge_pmd_locked(struct vm_area_struct *vma, + unsigned long addr, pmd_t *pmdp, + struct folio *folio) +{ + return false; +} #define split_huge_pud(__vma, __pmd, __address) \ do { } while (0) @@ -483,7 +594,7 @@ static inline vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf) return 0; } -static inline bool is_huge_zero_page(struct page *page) +static inline bool is_huge_zero_folio(const struct folio *folio) { return false; } @@ -493,12 +604,7 @@ static inline bool is_huge_zero_pmd(pmd_t pmd) return false; } -static inline bool is_huge_zero_pud(pud_t pud) -{ - return false; -} - -static inline void mm_put_huge_zero_page(struct mm_struct *mm) +static inline void mm_put_huge_zero_folio(struct mm_struct *mm) { return; } @@ -509,15 +615,32 @@ static inline struct page *follow_devmap_pmd(struct vm_area_struct *vma, return NULL; } -static inline struct page *follow_devmap_pud(struct vm_area_struct *vma, - unsigned long addr, pud_t *pud, int flags, struct dev_pagemap **pgmap) +static inline bool thp_migration_supported(void) { - return NULL; + return false; } -static inline bool thp_migration_supported(void) +static inline int highest_order(unsigned long orders) { - return false; + return 0; +} + +static inline int next_order(unsigned long *orders, int prev) +{ + return 0; +} + +static inline void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud, + unsigned long address) +{ +} + +static inline int change_huge_pud(struct mmu_gather *tlb, + struct vm_area_struct *vma, pud_t *pudp, + unsigned long addr, pgprot_t newprot, + unsigned long cp_flags) +{ + return 0; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ @@ -532,19 +655,4 @@ static inline int split_folio_to_order(struct folio *folio, int new_order) return split_folio_to_list_to_order(folio, NULL, new_order); } -#define split_folio_to_list(f, l) split_folio_to_list_to_order(f, l, 0) -#define split_folio(f) split_folio_to_order(f, 0) - -/* - * archs that select ARCH_WANTS_THP_SWAP but don't support THP_SWP due to - * limitations in the implementation like arm64 MTE can override this to - * false - */ -#ifndef arch_thp_swp_supported -static inline bool arch_thp_swp_supported(void) -{ - return true; -} -#endif - #endif /* _LINUX_HUGE_MM_H */ diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 77b30a8c6076..ec8c0ccc8f95 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -20,12 +20,6 @@ struct user_struct; struct mmu_gather; struct node; -#ifndef CONFIG_ARCH_HAS_HUGEPD -typedef struct { unsigned long pd; } hugepd_t; -#define is_hugepd(hugepd) (0) -#define __hugepd(x) ((hugepd_t) { (x) }) -#endif - void free_huge_folio(struct folio *folio); #ifdef CONFIG_HUGETLB_PAGE @@ -133,9 +127,6 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, unsigned long len); int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *, struct vm_area_struct *); -struct page *hugetlb_follow_page_mask(struct vm_area_struct *vma, - unsigned long address, unsigned int flags, - unsigned int *page_mask); void unmap_hugepage_range(struct vm_area_struct *, unsigned long, unsigned long, struct page *, zap_flags_t); @@ -162,11 +153,11 @@ 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); -bool isolate_hugetlb(struct folio *folio, struct list_head *list); +bool folio_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 folio_putback_active_hugetlb(struct folio *folio); +void folio_putback_hugetlb(struct folio *folio); void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int reason); void hugetlb_fix_reserve_counts(struct inode *inode); extern struct mutex *hugetlb_fault_mutex_table; @@ -174,8 +165,11 @@ u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx); pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pud_t *pud); +bool hugetlbfs_pagecache_present(struct hstate *h, + struct vm_area_struct *vma, + unsigned long address); -struct address_space *hugetlb_page_mapping_lock_write(struct page *hpage); +struct address_space *hugetlb_folio_mapping_lock_write(struct folio *folio); extern int sysctl_hugetlb_shm_group; extern struct list_head huge_boot_pages[MAX_NUMNODES]; @@ -272,13 +266,9 @@ void hugetlb_vma_unlock_write(struct vm_area_struct *vma); int hugetlb_vma_trylock_write(struct vm_area_struct *vma); void hugetlb_vma_assert_locked(struct vm_area_struct *vma); void hugetlb_vma_lock_release(struct kref *kref); - -int pmd_huge(pmd_t pmd); -int pud_huge(pud_t pud); long hugetlb_change_protection(struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot, unsigned long cp_flags); - bool is_hugetlb_entry_migration(pte_t pte); bool is_hugetlb_entry_hwpoisoned(pte_t pte); void hugetlb_unshare_all_pmds(struct vm_area_struct *vma); @@ -298,8 +288,8 @@ static inline unsigned long hugetlb_total_pages(void) return 0; } -static inline struct address_space *hugetlb_page_mapping_lock_write( - struct page *hpage) +static inline struct address_space *hugetlb_folio_mapping_lock_write( + struct folio *folio) { return NULL; } @@ -329,13 +319,6 @@ static inline void hugetlb_zap_end( { } -static inline struct page *hugetlb_follow_page_mask( - struct vm_area_struct *vma, unsigned long address, unsigned int flags, - unsigned int *page_mask) -{ - BUILD_BUG(); /* should never be compiled in if !CONFIG_HUGETLB_PAGE*/ -} - static inline int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *dst_vma, @@ -399,16 +382,6 @@ static inline void hugetlb_vma_assert_locked(struct vm_area_struct *vma) { } -static inline int pmd_huge(pmd_t pmd) -{ - return 0; -} - -static inline int pud_huge(pud_t pud) -{ - return 0; -} - static inline int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr, unsigned long len) { @@ -441,7 +414,7 @@ static inline pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, return NULL; } -static inline bool isolate_hugetlb(struct folio *folio, struct list_head *list) +static inline bool folio_isolate_hugetlb(struct folio *folio, struct list_head *list) { return false; } @@ -457,7 +430,7 @@ static inline int get_huge_page_for_hwpoison(unsigned long pfn, int flags, return 0; } -static inline void folio_putback_active_hugetlb(struct folio *folio) +static inline void folio_putback_hugetlb(struct folio *folio) { } @@ -493,16 +466,6 @@ static inline vm_fault_t hugetlb_fault(struct mm_struct *mm, static inline void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) { } #endif /* !CONFIG_HUGETLB_PAGE */ -/* - * hugepages at page global directory. If arch support - * hugepages at pgd level, they need to define this. - */ -#ifndef pgd_huge -#define pgd_huge(x) 0 -#endif -#ifndef p4d_huge -#define p4d_huge(x) 0 -#endif #ifndef pgd_write static inline int pgd_write(pgd_t pgd) @@ -554,17 +517,13 @@ static inline struct hugetlbfs_inode_info *HUGETLBFS_I(struct inode *inode) return container_of(inode, struct hugetlbfs_inode_info, vfs_inode); } -extern const struct file_operations hugetlbfs_file_operations; extern const struct vm_operations_struct hugetlb_vm_ops; struct file *hugetlb_file_setup(const char *name, size_t size, vm_flags_t acct, int creat_flags, int page_size_log); -static inline bool is_file_hugepages(struct file *file) +static inline bool is_file_hugepages(const struct file *file) { - if (file->f_op == &hugetlbfs_file_operations) - return true; - - return is_file_shm_hugepages(file); + return file->f_op->fop_flags & FOP_HUGE_PAGES; } static inline struct hstate *hstate_inode(struct inode *i) @@ -587,16 +546,10 @@ static inline struct hstate *hstate_inode(struct inode *i) } #endif /* !CONFIG_HUGETLBFS */ -#ifdef HAVE_ARCH_HUGETLB_UNMAPPED_AREA -unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, - unsigned long len, unsigned long pgoff, - unsigned long flags); -#endif /* HAVE_ARCH_HUGETLB_UNMAPPED_AREA */ - unsigned long -generic_hugetlb_get_unmapped_area(struct file *file, unsigned long addr, - unsigned long len, unsigned long pgoff, - unsigned long flags); +hugetlb_get_unmapped_area(struct file *file, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags); /* * huegtlb page specific state flags. These flags are located in page.private @@ -648,47 +601,35 @@ static __always_inline \ bool folio_test_hugetlb_##flname(struct folio *folio) \ { void *private = &folio->private; \ return test_bit(HPG_##flname, private); \ - } \ -static inline int HPage##uname(struct page *page) \ - { return test_bit(HPG_##flname, &(page->private)); } + } #define SETHPAGEFLAG(uname, flname) \ static __always_inline \ void folio_set_hugetlb_##flname(struct folio *folio) \ { void *private = &folio->private; \ set_bit(HPG_##flname, private); \ - } \ -static inline void SetHPage##uname(struct page *page) \ - { set_bit(HPG_##flname, &(page->private)); } + } #define CLEARHPAGEFLAG(uname, flname) \ static __always_inline \ void folio_clear_hugetlb_##flname(struct folio *folio) \ { void *private = &folio->private; \ clear_bit(HPG_##flname, private); \ - } \ -static inline void ClearHPage##uname(struct page *page) \ - { clear_bit(HPG_##flname, &(page->private)); } + } #else #define TESTHPAGEFLAG(uname, flname) \ static inline bool \ folio_test_hugetlb_##flname(struct folio *folio) \ - { return 0; } \ -static inline int HPage##uname(struct page *page) \ { return 0; } #define SETHPAGEFLAG(uname, flname) \ static inline void \ folio_set_hugetlb_##flname(struct folio *folio) \ - { } \ -static inline void SetHPage##uname(struct page *page) \ { } #define CLEARHPAGEFLAG(uname, flname) \ static inline void \ folio_clear_hugetlb_##flname(struct folio *folio) \ - { } \ -static inline void ClearHPage##uname(struct page *page) \ { } #endif @@ -713,6 +654,7 @@ HPAGEFLAG(RawHwpUnreliable, raw_hwp_unreliable) /* Defines one hugetlb page size */ struct hstate { struct mutex resize_lock; + struct lock_class_key resize_key; int next_nid_to_alloc; int next_nid_to_free; unsigned int order; @@ -730,11 +672,6 @@ struct hstate { unsigned int nr_huge_pages_node[MAX_NUMNODES]; unsigned int free_huge_pages_node[MAX_NUMNODES]; unsigned int surplus_huge_pages_node[MAX_NUMNODES]; -#ifdef CONFIG_CGROUP_HUGETLB - /* cgroup control files */ - struct cftype cgroup_files_dfl[8]; - struct cftype cgroup_files_legacy[10]; -#endif char name[HSTATE_NAME_LEN]; }; @@ -744,10 +681,15 @@ struct huge_bootmem_page { }; int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list); +int replace_free_hugepage_folios(unsigned long start_pfn, unsigned long end_pfn); struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, - unsigned long addr, int avoid_reserve); + unsigned long addr, bool cow_from_owner); struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, - nodemask_t *nmask, gfp_t gfp_mask); + nodemask_t *nmask, gfp_t gfp_mask, + bool allow_alloc_fallback); +struct folio *alloc_hugetlb_folio_reserve(struct hstate *h, int preferred_nid, + nodemask_t *nmask, gfp_t gfp_mask); + 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, @@ -859,9 +801,9 @@ static inline int is_hugepage_only_range(struct mm_struct *mm, #define is_hugepage_only_range is_hugepage_only_range #endif -#ifndef arch_clear_hugepage_flags -static inline void arch_clear_hugepage_flags(struct page *page) { } -#define arch_clear_hugepage_flags arch_clear_hugepage_flags +#ifndef arch_clear_hugetlb_flags +static inline void arch_clear_hugetlb_flags(struct folio *folio) { } +#define arch_clear_hugetlb_flags arch_clear_hugetlb_flags #endif #ifndef arch_make_huge_pte @@ -888,8 +830,8 @@ static inline int hstate_index(struct hstate *h) return h - hstates; } -extern int dissolve_free_huge_page(struct page *page); -extern int dissolve_free_huge_pages(unsigned long start_pfn, +int dissolve_free_hugetlb_folio(struct folio *folio); +int dissolve_free_hugetlb_folios(unsigned long start_pfn, unsigned long end_pfn); #ifdef CONFIG_MEMORY_FAILURE @@ -952,10 +894,11 @@ static inline bool hugepage_movable_supported(struct hstate *h) /* Movability of hugepages depends on migration support. */ static inline gfp_t htlb_alloc_mask(struct hstate *h) { - if (hugepage_movable_supported(h)) - return GFP_HIGHUSER_MOVABLE; - else - return GFP_HIGHUSER; + gfp_t gfp = __GFP_COMP | __GFP_NOWARN; + + gfp |= hugepage_movable_supported(h) ? GFP_HIGHUSER_MOVABLE : GFP_HIGHUSER; + + return gfp; } static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask) @@ -970,13 +913,64 @@ static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask) return modified_mask; } +static inline bool htlb_allow_alloc_fallback(int reason) +{ + bool allowed_fallback = false; + + /* + * Note: the memory offline, memory failure and migration syscalls will + * be allowed to fallback to other nodes due to lack of a better chioce, + * that might break the per-node hugetlb pool. While other cases will + * set the __GFP_THISNODE to avoid breaking the per-node hugetlb pool. + */ + switch (reason) { + case MR_MEMORY_HOTPLUG: + case MR_MEMORY_FAILURE: + case MR_SYSCALL: + case MR_MEMPOLICY_MBIND: + allowed_fallback = true; + break; + default: + break; + } + + return allowed_fallback; +} + static inline spinlock_t *huge_pte_lockptr(struct hstate *h, struct mm_struct *mm, pte_t *pte) { - if (huge_page_size(h) == PMD_SIZE) + const unsigned long size = huge_page_size(h); + + VM_WARN_ON(size == PAGE_SIZE); + + /* + * hugetlb must use the exact same PT locks as core-mm page table + * walkers would. When modifying a PTE table, hugetlb must take the + * PTE PT lock, when modifying a PMD table, hugetlb must take the PMD + * PT lock etc. + * + * The expectation is that any hugetlb folio smaller than a PMD is + * always mapped into a single PTE table and that any hugetlb folio + * smaller than a PUD (but at least as big as a PMD) is always mapped + * into a single PMD table. + * + * If that does not hold for an architecture, then that architecture + * must disable split PT locks such that all *_lockptr() functions + * will give us the same result: the per-MM PT lock. + * + * Note that with e.g., CONFIG_PGTABLE_LEVELS=2 where + * PGDIR_SIZE==P4D_SIZE==PUD_SIZE==PMD_SIZE, we'd use pud_lockptr() + * and core-mm would use pmd_lockptr(). However, in such configurations + * split PMD locks are disabled -- they don't make sense on a single + * PGDIR page table -- and the end result is the same. + */ + if (size >= PUD_SIZE) + return pud_lockptr(mm, (pud_t *) pte); + else if (size >= PMD_SIZE || IS_ENABLED(CONFIG_HIGHPTE)) return pmd_lockptr(mm, (pmd_t *) pte); - VM_BUG_ON(huge_page_size(h) == PAGE_SIZE); - return &mm->page_table_lock; + /* pte_alloc_huge() only applies with !CONFIG_HIGHPTE */ + return ptep_lockptr(mm, pte); } #ifndef hugepages_supported @@ -1036,9 +1030,19 @@ void hugetlb_unregister_node(struct node *node); */ bool is_raw_hwpoison_page_in_hugepage(struct page *page); +static inline unsigned long huge_page_mask_align(struct file *file) +{ + return PAGE_MASK & ~huge_page_mask(hstate_file(file)); +} + #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; +static inline unsigned long huge_page_mask_align(struct file *file) +{ + return 0; +} + static inline struct hugepage_subpool *hugetlb_folio_subpool(struct folio *folio) { return NULL; @@ -1056,16 +1060,30 @@ static inline int isolate_or_dissolve_huge_page(struct page *page, return -ENOMEM; } +static inline int replace_free_hugepage_folios(unsigned long start_pfn, + unsigned long end_pfn) +{ + return 0; +} + static inline struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, unsigned long addr, - int avoid_reserve) + bool cow_from_owner) +{ + return NULL; +} + +static inline struct folio * +alloc_hugetlb_folio_reserve(struct hstate *h, int preferred_nid, + nodemask_t *nmask, gfp_t gfp_mask) { return NULL; } static inline struct folio * alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, - nodemask_t *nmask, gfp_t gfp_mask) + nodemask_t *nmask, gfp_t gfp_mask, + bool allow_alloc_fallback) { return NULL; } @@ -1150,12 +1168,12 @@ static inline int hstate_index(struct hstate *h) return 0; } -static inline int dissolve_free_huge_page(struct page *page) +static inline int dissolve_free_hugetlb_folio(struct folio *folio) { return 0; } -static inline int dissolve_free_huge_pages(unsigned long start_pfn, +static inline int dissolve_free_hugetlb_folios(unsigned long start_pfn, unsigned long end_pfn) { return 0; @@ -1181,6 +1199,11 @@ static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask) return 0; } +static inline bool htlb_allow_alloc_fallback(int reason) +{ + return false; +} + static inline spinlock_t *huge_pte_lockptr(struct hstate *h, struct mm_struct *mm, pte_t *pte) { @@ -1221,6 +1244,12 @@ static inline void hugetlb_register_node(struct node *node) static inline void hugetlb_unregister_node(struct node *node) { } + +static inline bool hugetlbfs_pagecache_present( + struct hstate *h, struct vm_area_struct *vma, unsigned long address) +{ + return false; +} #endif /* CONFIG_HUGETLB_PAGE */ static inline spinlock_t *huge_pte_lock(struct hstate *h, @@ -1241,7 +1270,7 @@ static inline __init void hugetlb_cma_reserve(int order) } #endif -#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE +#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING static inline bool hugetlb_pmd_shared(pte_t *pte) { return page_count(virt_to_page(pte)) > 1; @@ -1277,8 +1306,7 @@ bool __vma_private_lock(struct vm_area_struct *vma); 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) +#if defined(CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING) && defined(CONFIG_LOCKDEP) struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; /* diff --git a/include/linux/hw_random.h b/include/linux/hw_random.h index 136e9842120e..b424555753b1 100644 --- a/include/linux/hw_random.h +++ b/include/linux/hw_random.h @@ -13,9 +13,8 @@ #define LINUX_HWRANDOM_H_ #include <linux/completion.h> -#include <linux/types.h> -#include <linux/list.h> #include <linux/kref.h> +#include <linux/types.h> /** * struct hwrng - Hardware Random Number Generator driver diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h index edf96f249eb5..3a63dff62d03 100644 --- a/include/linux/hwmon.h +++ b/include/linux/hwmon.h @@ -45,6 +45,7 @@ enum hwmon_chip_attributes { hwmon_chip_power_samples, hwmon_chip_temp_samples, hwmon_chip_beep_enable, + hwmon_chip_pec, }; #define HWMON_C_TEMP_RESET_HISTORY BIT(hwmon_chip_temp_reset_history) @@ -60,6 +61,7 @@ enum hwmon_chip_attributes { #define HWMON_C_POWER_SAMPLES BIT(hwmon_chip_power_samples) #define HWMON_C_TEMP_SAMPLES BIT(hwmon_chip_temp_samples) #define HWMON_C_BEEP_ENABLE BIT(hwmon_chip_beep_enable) +#define HWMON_C_PEC BIT(hwmon_chip_pec) enum hwmon_temp_attributes { hwmon_temp_enable, @@ -366,7 +368,9 @@ enum hwmon_intrusion_attributes { /** * struct hwmon_ops - hwmon device operations - * @is_visible: Callback to return attribute visibility. Mandatory. + * @visible: Static visibility. If non-zero, 'is_visible' is ignored. + * @is_visible: Callback to return attribute visibility. Mandatory unless + * 'visible' is non-zero. * Parameters are: * @const void *drvdata: * Pointer to driver-private data structure passed @@ -410,6 +414,7 @@ enum hwmon_intrusion_attributes { * The function returns 0 on success or a negative error number. */ struct hwmon_ops { + umode_t visible; umode_t (*is_visible)(const void *drvdata, enum hwmon_sensor_types type, u32 attr, int channel); int (*read)(struct device *dev, enum hwmon_sensor_types type, @@ -479,7 +484,6 @@ devm_hwmon_device_register_with_info(struct device *dev, const struct attribute_group **extra_groups); void hwmon_device_unregister(struct device *dev); -void devm_hwmon_device_unregister(struct device *dev); int hwmon_notify_event(struct device *dev, enum hwmon_sensor_types type, u32 attr, int channel); diff --git a/include/linux/hwspinlock.h b/include/linux/hwspinlock.h index bfe7c1f1ac6d..f0231dbc4777 100644 --- a/include/linux/hwspinlock.h +++ b/include/linux/hwspinlock.h @@ -68,6 +68,7 @@ int __hwspin_lock_timeout(struct hwspinlock *, unsigned int, int, int __hwspin_trylock(struct hwspinlock *, int, unsigned long *); void __hwspin_unlock(struct hwspinlock *, int, unsigned long *); int of_hwspin_lock_get_id_byname(struct device_node *np, const char *name); +int hwspin_lock_bust(struct hwspinlock *hwlock, unsigned int id); int devm_hwspin_lock_free(struct device *dev, struct hwspinlock *hwlock); struct hwspinlock *devm_hwspin_lock_request(struct device *dev); struct hwspinlock *devm_hwspin_lock_request_specific(struct device *dev, @@ -127,6 +128,11 @@ void __hwspin_unlock(struct hwspinlock *hwlock, int mode, unsigned long *flags) { } +static inline int hwspin_lock_bust(struct hwspinlock *hwlock, unsigned int id) +{ + return 0; +} + static inline int of_hwspin_lock_get_id(struct device_node *np, int index) { return 0; diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 96ceb4095425..4179add2864b 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -24,7 +24,7 @@ #include <linux/mod_devicetable.h> #include <linux/interrupt.h> #include <linux/reciprocal_div.h> -#include <asm/hyperv-tlfs.h> +#include <hyperv/hvhdk.h> #define MAX_PAGE_BUFFER_COUNT 32 #define MAX_MULTIPAGE_BUFFER_COUNT 32 /* 128K */ @@ -768,15 +768,6 @@ struct vmbus_close_msg { struct vmbus_channel_close_channel msg; }; -/* Define connection identifier type. */ -union hv_connection_id { - u32 asu32; - struct { - u32 id:24; - u32 reserved:8; - } u; -}; - enum vmbus_device_type { HV_IDE = 0, HV_SCSI, @@ -820,6 +811,8 @@ struct vmbus_requestor { #define VMBUS_RQST_RESET (U64_MAX - 3) struct vmbus_device { + /* preferred ring buffer size in KB, 0 means no preferred size for this device */ + size_t pref_ring_size; u16 dev_type; guid_t guid; bool perf_device; @@ -1328,11 +1321,7 @@ struct hv_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) -{ - return container_of(d, struct hv_driver, driver); -} +#define drv_to_hv_drv(d) container_of_const(d, struct hv_driver, driver) static inline void hv_set_drvdata(struct hv_device *dev, void *data) { @@ -1561,6 +1550,7 @@ struct hv_util_service { void *channel; void (*util_cb)(void *); int (*util_init)(struct hv_util_service *); + int (*util_init_transport)(void); void (*util_deinit)(void); int (*util_pre_suspend)(void); int (*util_pre_resume)(void); diff --git a/include/linux/i2c-mux.h b/include/linux/i2c-mux.h index 98ef73b7c8fd..1784ac7afb11 100644 --- a/include/linux/i2c-mux.h +++ b/include/linux/i2c-mux.h @@ -56,8 +56,7 @@ struct i2c_adapter *i2c_root_adapter(struct device *dev); * callback functions to perform hardware-specific mux control. */ int i2c_mux_add_adapter(struct i2c_mux_core *muxc, - u32 force_nr, u32 chan_id, - unsigned int class); + u32 force_nr, u32 chan_id); void i2c_mux_del_adapters(struct i2c_mux_core *muxc); diff --git a/include/linux/i2c-of-prober.h b/include/linux/i2c-of-prober.h new file mode 100644 index 000000000000..bb6d47f50ee5 --- /dev/null +++ b/include/linux/i2c-of-prober.h @@ -0,0 +1,140 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Definitions for the Linux I2C OF component prober + * + * Copyright (C) 2024 Google LLC + */ + +#ifndef _LINUX_I2C_OF_PROBER_H +#define _LINUX_I2C_OF_PROBER_H + +#include <linux/kconfig.h> +#include <linux/types.h> + +struct device; +struct device_node; + +/** + * struct i2c_of_probe_ops - I2C OF component prober callbacks + * + * A set of callbacks to be used by i2c_of_probe_component(). + * + * All callbacks are optional. Callbacks are called only once per run, and are + * used in the order they are defined in this structure. + * + * All callbacks that have return values shall return %0 on success, + * or a negative error number on failure. + * + * The @dev parameter passed to the callbacks is the same as @dev passed to + * i2c_of_probe_component(). It should only be used for dev_printk() calls + * and nothing else, especially not managed device resource (devres) APIs. + */ +struct i2c_of_probe_ops { + /** + * @enable: Retrieve and enable resources so that the components respond to probes. + * + * It is OK for this callback to return -EPROBE_DEFER since the intended use includes + * retrieving resources and enables them. Resources should be reverted to their initial + * state and released before returning if this fails. + */ + int (*enable)(struct device *dev, struct device_node *bus_node, void *data); + + /** + * @cleanup_early: Release exclusive resources prior to calling probe() on a + * detected component. + * + * Only called if a matching component is actually found. If none are found, + * resources that would have been released in this callback should be released in + * @free_resourcs_late instead. + */ + void (*cleanup_early)(struct device *dev, void *data); + + /** + * @cleanup: Opposite of @enable to balance refcounts and free resources after probing. + * + * Should check if resources were already freed by @cleanup_early. + */ + void (*cleanup)(struct device *dev, void *data); +}; + +/** + * struct i2c_of_probe_cfg - I2C OF component prober configuration + * @ops: Callbacks for the prober to use. + * @type: A string to match the device node name prefix to probe for. + */ +struct i2c_of_probe_cfg { + const struct i2c_of_probe_ops *ops; + const char *type; +}; + +#if IS_ENABLED(CONFIG_OF_DYNAMIC) + +int i2c_of_probe_component(struct device *dev, const struct i2c_of_probe_cfg *cfg, void *ctx); + +/** + * DOC: I2C OF component prober simple helpers + * + * Components such as trackpads are commonly connected to a devices baseboard + * with a 6-pin ribbon cable. That gives at most one voltage supply and one + * GPIO (commonly a "enable" or "reset" line) besides the I2C bus, interrupt + * pin, and common ground. Touchscreens, while integrated into the display + * panel's connection, typically have the same set of connections. + * + * A simple set of helpers are provided here for use with the I2C OF component + * prober. This implementation targets such components, allowing for at most + * one regulator supply. + * + * The following helpers are provided: + * * i2c_of_probe_simple_enable() + * * i2c_of_probe_simple_cleanup_early() + * * i2c_of_probe_simple_cleanup() + */ + +/** + * struct i2c_of_probe_simple_opts - Options for simple I2C component prober callbacks + * @res_node_compatible: Compatible string of device node to retrieve resources from. + * @supply_name: Name of regulator supply. + * @gpio_name: Name of GPIO. NULL if no GPIO line is used. Empty string ("") if GPIO + * line is unnamed. + * @post_power_on_delay_ms: Delay after regulators are powered on. Passed to msleep(). + * @post_gpio_config_delay_ms: Delay after GPIO is configured. Passed to msleep(). + * @gpio_assert_to_enable: %true if GPIO should be asserted, i.e. set to logical high, + * to enable the component. + * + * This describes power sequences common for the class of components supported by the + * simple component prober: + * * @gpio_name is configured to the non-active setting according to @gpio_assert_to_enable. + * * @supply_name regulator supply is enabled. + * * Wait for @post_power_on_delay_ms to pass. + * * @gpio_name is configured to the active setting according to @gpio_assert_to_enable. + * * Wait for @post_gpio_config_delay_ms to pass. + */ +struct i2c_of_probe_simple_opts { + const char *res_node_compatible; + const char *supply_name; + const char *gpio_name; + unsigned int post_power_on_delay_ms; + unsigned int post_gpio_config_delay_ms; + bool gpio_assert_to_enable; +}; + +struct gpio_desc; +struct regulator; + +struct i2c_of_probe_simple_ctx { + /* public: provided by user before helpers are used. */ + const struct i2c_of_probe_simple_opts *opts; + /* private: internal fields for helpers. */ + struct regulator *supply; + struct gpio_desc *gpiod; +}; + +int i2c_of_probe_simple_enable(struct device *dev, struct device_node *bus_node, void *data); +void i2c_of_probe_simple_cleanup_early(struct device *dev, void *data); +void i2c_of_probe_simple_cleanup(struct device *dev, void *data); + +extern struct i2c_of_probe_ops i2c_of_probe_simple_ops; + +#endif /* IS_ENABLED(CONFIG_OF_DYNAMIC) */ + +#endif /* _LINUX_I2C_OF_PROBER_H */ diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 5e6cd43a6dbd..c31fd1dba3bd 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -30,7 +30,6 @@ extern const struct device_type i2c_client_type; /* --- General options ------------------------------------------------ */ struct i2c_msg; -struct i2c_algorithm; struct i2c_adapter; struct i2c_client; struct i2c_driver; @@ -245,7 +244,6 @@ enum i2c_driver_flags { * @id_table: List of I2C devices supported by this driver * @detect: Callback for device detection * @address_list: The I2C addresses to probe (for detect) - * @clients: List of detected clients we created (for i2c-core use only) * @flags: A bitmask of flags defined in &enum i2c_driver_flags * * The driver.owner field should be set to the module owner of this driver. @@ -300,11 +298,10 @@ struct i2c_driver { /* Device detection callback for automatic device creation */ int (*detect)(struct i2c_client *client, struct i2c_board_info *info); const unsigned short *address_list; - struct list_head clients; u32 flags; }; -#define to_i2c_driver(d) container_of(d, struct i2c_driver, driver) +#define to_i2c_driver(d) container_of_const(d, struct i2c_driver, driver) /** * struct i2c_client - represent an I2C slave device @@ -316,12 +313,12 @@ struct i2c_driver { * @dev: Driver model device node for the slave. * @init_irq: IRQ that was set at initialization * @irq: indicates the IRQ generated by this device (if any) - * @detected: member of an i2c_driver.clients list or i2c-core's - * userspace_devices list * @slave_cb: Callback when I2C slave mode of an adapter is used. The adapter * calls it to pass on slave events to the slave driver. * @devres_group_id: id of the devres group that will be created for resources * acquired when probing this device. + * @debugfs: pointer to the debugfs subdirectory which the I2C core created + * for this client. * * An i2c_client identifies a single device (i.e. chip) connected to an * i2c bus. The behaviour exposed to Linux is defined by the driver @@ -335,6 +332,8 @@ struct i2c_client { #define I2C_CLIENT_SLAVE 0x20 /* we are the slave */ #define I2C_CLIENT_HOST_NOTIFY 0x40 /* We want to use I2C host notify */ #define I2C_CLIENT_WAKE 0x80 /* for board_info; true iff can wake */ +#define I2C_CLIENT_AUTO 0x100 /* client was auto-detected */ +#define I2C_CLIENT_USER 0x200 /* client was userspace-created */ #define I2C_CLIENT_SCCB 0x9000 /* Use Omnivision SCCB protocol */ /* Must match I2C_M_STOP|IGNORE_NAK */ @@ -346,11 +345,11 @@ struct i2c_client { struct device dev; /* the device structure */ int init_irq; /* irq set at initialization */ int irq; /* irq issued by device */ - struct list_head detected; #if IS_ENABLED(CONFIG_I2C_SLAVE) i2c_slave_cb_t slave_cb; /* callback for slave mode */ #endif void *devres_group_id; /* ID of probe devres group */ + struct dentry *debugfs; /* per-client debugfs dir */ }; #define to_i2c_client(d) container_of(d, struct i2c_client, dev) @@ -512,46 +511,54 @@ i2c_register_board_info(int busnum, struct i2c_board_info const *info, #endif /* I2C_BOARDINFO */ /** - * struct i2c_algorithm - represent I2C transfer method - * @master_xfer: Issue a set of i2c transactions to the given I2C adapter - * defined by the msgs array, with num messages available to transfer via - * the adapter specified by adap. - * @master_xfer_atomic: same as @master_xfer. Yet, only using atomic context - * so e.g. PMICs can be accessed very late before shutdown. Optional. - * @smbus_xfer: Issue smbus transactions to the given I2C adapter. If this + * struct i2c_algorithm - represent I2C transfer methods + * @xfer: Transfer a given number of messages defined by the msgs array via + * the specified adapter. + * @xfer_atomic: Same as @xfer. Yet, only using atomic context so e.g. PMICs + * can be accessed very late before shutdown. Optional. + * @smbus_xfer: Issue SMBus transactions to the given I2C adapter. If this * is not present, then the bus layer will try and convert the SMBus calls * into I2C transfers instead. - * @smbus_xfer_atomic: same as @smbus_xfer. Yet, only using atomic context + * @smbus_xfer_atomic: Same as @smbus_xfer. Yet, only using atomic context * so e.g. PMICs can be accessed very late before shutdown. Optional. * @functionality: Return the flags that this algorithm/adapter pair supports * from the ``I2C_FUNC_*`` flags. - * @reg_slave: Register given client to I2C slave mode of this adapter - * @unreg_slave: Unregister given client from I2C slave mode of this adapter + * @reg_target: Register given client to local target mode of this adapter + * @unreg_target: Unregister given client from local target mode of this adapter + * + * @master_xfer: deprecated, use @xfer + * @master_xfer_atomic: deprecated, use @xfer_atomic + * @reg_slave: deprecated, use @reg_target + * @unreg_slave: deprecated, use @unreg_target * - * The following structs are for those who like to implement new bus drivers: * i2c_algorithm is the interface to a class of hardware solutions which can * be addressed using the same bus algorithms - i.e. bit-banging or the PCF8584 * to name two of the most common. * - * The return codes from the ``master_xfer{_atomic}`` fields should indicate the + * The return codes from the ``xfer{_atomic}`` fields should indicate the * type of error code that occurred during the transfer, as documented in the * Kernel Documentation file Documentation/i2c/fault-codes.rst. Otherwise, the * number of messages executed should be returned. */ struct i2c_algorithm { /* - * If an adapter algorithm can't do I2C-level access, set master_xfer + * If an adapter algorithm can't do I2C-level access, set xfer * to NULL. If an adapter algorithm can do SMBus access, set * smbus_xfer. If set to NULL, the SMBus protocol is simulated * using common I2C messages. - * - * master_xfer should return the number of messages successfully - * processed, or a negative value on error */ - int (*master_xfer)(struct i2c_adapter *adap, struct i2c_msg *msgs, - int num); - int (*master_xfer_atomic)(struct i2c_adapter *adap, + union { + int (*xfer)(struct i2c_adapter *adap, struct i2c_msg *msgs, + int num); + int (*master_xfer)(struct i2c_adapter *adap, struct i2c_msg *msgs, + int num); + }; + union { + int (*xfer_atomic)(struct i2c_adapter *adap, struct i2c_msg *msgs, int num); + int (*master_xfer_atomic)(struct i2c_adapter *adap, + struct i2c_msg *msgs, int num); + }; int (*smbus_xfer)(struct i2c_adapter *adap, u16 addr, unsigned short flags, char read_write, u8 command, int size, union i2c_smbus_data *data); @@ -563,8 +570,14 @@ struct i2c_algorithm { u32 (*functionality)(struct i2c_adapter *adap); #if IS_ENABLED(CONFIG_I2C_SLAVE) - int (*reg_slave)(struct i2c_client *client); - int (*unreg_slave)(struct i2c_client *client); + union { + int (*reg_target)(struct i2c_client *client); + int (*reg_slave)(struct i2c_client *client); + }; + union { + int (*unreg_target)(struct i2c_client *client); + int (*unreg_slave)(struct i2c_client *client); + }; #endif }; @@ -738,9 +751,6 @@ struct i2c_adapter { char name[48]; struct completion dev_released; - struct mutex userspace_clients_lock; - struct list_head userspace_clients; - struct i2c_bus_recovery_info *bus_recovery_info; const struct i2c_adapter_quirks *quirks; @@ -748,6 +758,9 @@ struct i2c_adapter { struct regulator *bus_regulator; struct dentry *debugfs; + + /* 7bit address space */ + DECLARE_BITMAP(addrs_in_instantiation, 1 << 7); }; #define to_i2c_adapter(d) container_of(d, struct i2c_adapter, dev) @@ -852,7 +865,6 @@ static inline void i2c_mark_adapter_resumed(struct i2c_adapter *adap) /* i2c adapter classes (bitmask) */ #define I2C_CLASS_HWMON (1<<0) /* lm_sensors, ... */ -#define I2C_CLASS_SPD (1<<7) /* Memory modules */ /* Warn users that the adapter doesn't support classes anymore */ #define I2C_CLASS_DEPRECATED (1<<8) @@ -961,8 +973,6 @@ int i2c_handle_smbus_host_notify(struct i2c_adapter *adap, unsigned short addr); #define builtin_i2c_driver(__i2c_driver) \ builtin_driver(__i2c_driver, i2c_add_driver) -#endif /* I2C */ - /* must call put_device() when done with returned i2c_client device */ struct i2c_client *i2c_find_device_by_fwnode(struct fwnode_handle *fwnode); @@ -972,6 +982,28 @@ struct i2c_adapter *i2c_find_adapter_by_fwnode(struct fwnode_handle *fwnode); /* must call i2c_put_adapter() when done with returned i2c_adapter device */ struct i2c_adapter *i2c_get_adapter_by_fwnode(struct fwnode_handle *fwnode); +#else /* I2C */ + +static inline struct i2c_client * +i2c_find_device_by_fwnode(struct fwnode_handle *fwnode) +{ + return NULL; +} + +static inline struct i2c_adapter * +i2c_find_adapter_by_fwnode(struct fwnode_handle *fwnode) +{ + return NULL; +} + +static inline struct i2c_adapter * +i2c_get_adapter_by_fwnode(struct fwnode_handle *fwnode) +{ + return NULL; +} + +#endif /* !I2C */ + #if IS_ENABLED(CONFIG_OF) /* must call put_device() when done with returned i2c_client device */ static inline struct i2c_client *of_find_i2c_device_by_node(struct device_node *node) @@ -1034,7 +1066,7 @@ static inline int of_i2c_get_board_info(struct device *dev, struct acpi_resource; struct acpi_resource_i2c_serialbus; -#if IS_ENABLED(CONFIG_ACPI) +#if IS_REACHABLE(CONFIG_ACPI) && IS_REACHABLE(CONFIG_I2C) bool i2c_acpi_get_i2c_resource(struct acpi_resource *ares, struct acpi_resource_i2c_serialbus **i2c); int i2c_acpi_client_count(struct acpi_device *adev); diff --git a/include/linux/i3c/device.h b/include/linux/i3c/device.h index e119f11948ef..b674f64d0822 100644 --- a/include/linux/i3c/device.h +++ b/include/linux/i3c/device.h @@ -183,10 +183,7 @@ struct i3c_driver { const struct i3c_device_id *id_table; }; -static inline struct i3c_driver *drv_to_i3cdrv(struct device_driver *drv) -{ - return container_of(drv, struct i3c_driver, driver); -} +#define drv_to_i3cdrv(__drv) container_of_const(__drv, struct i3c_driver, driver) struct device *i3cdev_to_dev(struct i3c_device *i3cdev); @@ -286,7 +283,7 @@ static inline void i3c_i2c_driver_unregister(struct i3c_driver *i3cdrv, * module_i3c_i2c_driver() - Register a module providing an I3C and an I2C * driver * @__i3cdrv: the I3C driver to register - * @__i2cdrv: the I3C driver to register + * @__i2cdrv: the I2C driver to register * * Provide generic init/exit functions that simply register/unregister an I3C * and an I2C driver. diff --git a/include/linux/i3c/master.h b/include/linux/i3c/master.h index 0ca27dd86956..12d532b012c5 100644 --- a/include/linux/i3c/master.h +++ b/include/linux/i3c/master.h @@ -33,6 +33,7 @@ enum { struct i3c_master_controller; struct i3c_bus; struct i3c_device; +extern const struct bus_type i3c_bus_type; /** * struct i3c_i2c_dev_desc - Common part of the I3C/I2C device descriptor @@ -277,13 +278,29 @@ enum i3c_bus_mode { }; /** + * enum i3c_open_drain_speed - I3C open-drain speed + * @I3C_OPEN_DRAIN_SLOW_SPEED: Slow open-drain speed for sending the first + * broadcast address. The first broadcast address at this speed + * will be visible to all devices on the I3C bus. I3C devices + * working in I2C mode will turn off their spike filter when + * switching into I3C mode. + * @I3C_OPEN_DRAIN_NORMAL_SPEED: Normal open-drain speed in I3C bus mode. + */ +enum i3c_open_drain_speed { + I3C_OPEN_DRAIN_SLOW_SPEED, + I3C_OPEN_DRAIN_NORMAL_SPEED, +}; + +/** * enum i3c_addr_slot_status - I3C address slot status * @I3C_ADDR_SLOT_FREE: address is free * @I3C_ADDR_SLOT_RSVD: address is reserved * @I3C_ADDR_SLOT_I2C_DEV: address is assigned to an I2C device * @I3C_ADDR_SLOT_I3C_DEV: address is assigned to an I3C device * @I3C_ADDR_SLOT_STATUS_MASK: address slot mask - * + * @I3C_ADDR_SLOT_EXT_STATUS_MASK: address slot mask with extended information + * @I3C_ADDR_SLOT_EXT_DESIRED: the bitmask represents addresses that are preferred by some devices, + * such as the "assigned-address" property in a device tree source. * On an I3C bus, addresses are assigned dynamically, and we need to know which * addresses are free to use and which ones are already assigned. * @@ -296,8 +313,12 @@ enum i3c_addr_slot_status { I3C_ADDR_SLOT_I2C_DEV, I3C_ADDR_SLOT_I3C_DEV, I3C_ADDR_SLOT_STATUS_MASK = 3, + I3C_ADDR_SLOT_EXT_STATUS_MASK = 7, + I3C_ADDR_SLOT_EXT_DESIRED = BIT(2), }; +#define I3C_ADDR_SLOT_STATUS_BITS 4 + /** * struct i3c_bus - I3C bus object * @cur_master: I3C master currently driving the bus. Since I3C is multi-master @@ -339,7 +360,7 @@ enum i3c_addr_slot_status { struct i3c_bus { struct i3c_dev_desc *cur_master; int id; - unsigned long addrslots[((I2C_MAX_ADDR + 1) * 2) / BITS_PER_LONG]; + unsigned long addrslots[((I2C_MAX_ADDR + 1) * I3C_ADDR_SLOT_STATUS_BITS) / BITS_PER_LONG]; enum i3c_bus_mode mode; struct { unsigned long i3c; @@ -435,6 +456,7 @@ struct i3c_bus { * NULL. * @enable_hotjoin: enable hot join event detect. * @disable_hotjoin: disable hot join event detect. + * @set_speed: adjust I3C open drain mode timing. */ struct i3c_master_controller_ops { int (*bus_init)(struct i3c_master_controller *master); @@ -463,6 +485,7 @@ struct i3c_master_controller_ops { struct i3c_ibi_slot *slot); int (*enable_hotjoin)(struct i3c_master_controller *master); int (*disable_hotjoin)(struct i3c_master_controller *master); + int (*set_speed)(struct i3c_master_controller *master, enum i3c_open_drain_speed speed); }; /** diff --git a/include/linux/i8042.h b/include/linux/i8042.h index 95b07f8b77fe..00037c13abc8 100644 --- a/include/linux/i8042.h +++ b/include/linux/i8042.h @@ -54,15 +54,29 @@ struct serio; +/** + * typedef i8042_filter_t - i8042 filter callback + * @data: Data received by the i8042 controller + * @str: Status register of the i8042 controller + * @serio: Serio of the i8042 controller + * @context: Context pointer associated with this callback + * + * This represents a i8042 filter callback which can be used with i8042_install_filter() + * and i8042_remove_filter() to filter the i8042 input for platform-specific key codes. + * + * Context: Interrupt context. + * Returns: true if the data should be filtered out, false if otherwise. + */ +typedef bool (*i8042_filter_t)(unsigned char data, unsigned char str, struct serio *serio, + void *context); + #if defined(CONFIG_SERIO_I8042) || defined(CONFIG_SERIO_I8042_MODULE) void i8042_lock_chip(void); void i8042_unlock_chip(void); int i8042_command(unsigned char *param, int command); -int i8042_install_filter(bool (*filter)(unsigned char data, unsigned char str, - struct serio *serio)); -int i8042_remove_filter(bool (*filter)(unsigned char data, unsigned char str, - struct serio *serio)); +int i8042_install_filter(i8042_filter_t filter, void *context); +int i8042_remove_filter(i8042_filter_t filter); #else @@ -79,14 +93,12 @@ static inline int i8042_command(unsigned char *param, int command) return -ENODEV; } -static inline int i8042_install_filter(bool (*filter)(unsigned char data, unsigned char str, - struct serio *serio)) +static inline int i8042_install_filter(i8042_filter_t filter, void *context) { return -ENODEV; } -static inline int i8042_remove_filter(bool (*filter)(unsigned char data, unsigned char str, - struct serio *serio)) +static inline int i8042_remove_filter(i8042_filter_t filter) { return -ENODEV; } diff --git a/include/linux/i8253.h b/include/linux/i8253.h index 8336b2f6f834..56c280eb2d4f 100644 --- a/include/linux/i8253.h +++ b/include/linux/i8253.h @@ -21,9 +21,9 @@ #define PIT_LATCH ((PIT_TICK_RATE + HZ/2) / HZ) extern raw_spinlock_t i8253_lock; -extern bool i8253_clear_counter_on_shutdown; extern struct clock_event_device i8253_clockevent; extern void clockevent_i8253_init(bool oneshot); +extern void clockevent_i8253_disable(void); extern void setup_pit_timer(void); diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 3385a2cc5b09..16741e542e81 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -20,7 +20,7 @@ #include <linux/etherdevice.h> #include <linux/bitfield.h> #include <asm/byteorder.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* * DS bit usage @@ -373,6 +373,7 @@ struct ieee80211_trigger { /** * ieee80211_has_tods - check if IEEE80211_FCTL_TODS is set * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame has to-DS set */ static inline bool ieee80211_has_tods(__le16 fc) { @@ -382,6 +383,7 @@ static inline bool ieee80211_has_tods(__le16 fc) /** * ieee80211_has_fromds - check if IEEE80211_FCTL_FROMDS is set * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame has from-DS set */ static inline bool ieee80211_has_fromds(__le16 fc) { @@ -391,6 +393,7 @@ static inline bool ieee80211_has_fromds(__le16 fc) /** * ieee80211_has_a4 - check if IEEE80211_FCTL_TODS and IEEE80211_FCTL_FROMDS are set * @fc: frame control bytes in little-endian byteorder + * Return: whether or not it's a 4-address frame (from-DS and to-DS set) */ static inline bool ieee80211_has_a4(__le16 fc) { @@ -401,6 +404,7 @@ static inline bool ieee80211_has_a4(__le16 fc) /** * ieee80211_has_morefrags - check if IEEE80211_FCTL_MOREFRAGS is set * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame has more fragments (more frags bit set) */ static inline bool ieee80211_has_morefrags(__le16 fc) { @@ -410,6 +414,7 @@ static inline bool ieee80211_has_morefrags(__le16 fc) /** * ieee80211_has_retry - check if IEEE80211_FCTL_RETRY is set * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the retry flag is set */ static inline bool ieee80211_has_retry(__le16 fc) { @@ -419,6 +424,7 @@ static inline bool ieee80211_has_retry(__le16 fc) /** * ieee80211_has_pm - check if IEEE80211_FCTL_PM is set * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the power management flag is set */ static inline bool ieee80211_has_pm(__le16 fc) { @@ -428,6 +434,7 @@ static inline bool ieee80211_has_pm(__le16 fc) /** * ieee80211_has_moredata - check if IEEE80211_FCTL_MOREDATA is set * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the more data flag is set */ static inline bool ieee80211_has_moredata(__le16 fc) { @@ -437,6 +444,7 @@ static inline bool ieee80211_has_moredata(__le16 fc) /** * ieee80211_has_protected - check if IEEE80211_FCTL_PROTECTED is set * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the protected flag is set */ static inline bool ieee80211_has_protected(__le16 fc) { @@ -446,6 +454,7 @@ static inline bool ieee80211_has_protected(__le16 fc) /** * ieee80211_has_order - check if IEEE80211_FCTL_ORDER is set * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the order flag is set */ static inline bool ieee80211_has_order(__le16 fc) { @@ -455,6 +464,7 @@ static inline bool ieee80211_has_order(__le16 fc) /** * ieee80211_is_mgmt - check if type is IEEE80211_FTYPE_MGMT * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame type is management */ static inline bool ieee80211_is_mgmt(__le16 fc) { @@ -465,6 +475,7 @@ static inline bool ieee80211_is_mgmt(__le16 fc) /** * ieee80211_is_ctl - check if type is IEEE80211_FTYPE_CTL * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame type is control */ static inline bool ieee80211_is_ctl(__le16 fc) { @@ -475,6 +486,7 @@ static inline bool ieee80211_is_ctl(__le16 fc) /** * ieee80211_is_data - check if type is IEEE80211_FTYPE_DATA * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is a data frame */ static inline bool ieee80211_is_data(__le16 fc) { @@ -485,6 +497,7 @@ static inline bool ieee80211_is_data(__le16 fc) /** * ieee80211_is_ext - check if type is IEEE80211_FTYPE_EXT * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame type is extended */ static inline bool ieee80211_is_ext(__le16 fc) { @@ -496,6 +509,7 @@ static inline bool ieee80211_is_ext(__le16 fc) /** * ieee80211_is_data_qos - check if type is IEEE80211_FTYPE_DATA and IEEE80211_STYPE_QOS_DATA is set * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is a QoS data frame */ static inline bool ieee80211_is_data_qos(__le16 fc) { @@ -510,6 +524,8 @@ static inline bool ieee80211_is_data_qos(__le16 fc) /** * ieee80211_is_data_present - check if type is IEEE80211_FTYPE_DATA and has data * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is a QoS data frame that has data + * (i.e. is not null data) */ static inline bool ieee80211_is_data_present(__le16 fc) { @@ -524,6 +540,7 @@ static inline bool ieee80211_is_data_present(__le16 fc) /** * ieee80211_is_assoc_req - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ASSOC_REQ * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is an association request */ static inline bool ieee80211_is_assoc_req(__le16 fc) { @@ -534,6 +551,7 @@ static inline bool ieee80211_is_assoc_req(__le16 fc) /** * ieee80211_is_assoc_resp - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ASSOC_RESP * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is an association response */ static inline bool ieee80211_is_assoc_resp(__le16 fc) { @@ -544,6 +562,7 @@ static inline bool ieee80211_is_assoc_resp(__le16 fc) /** * ieee80211_is_reassoc_req - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_REASSOC_REQ * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is a reassociation request */ static inline bool ieee80211_is_reassoc_req(__le16 fc) { @@ -554,6 +573,7 @@ static inline bool ieee80211_is_reassoc_req(__le16 fc) /** * ieee80211_is_reassoc_resp - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_REASSOC_RESP * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is a reassociation response */ static inline bool ieee80211_is_reassoc_resp(__le16 fc) { @@ -564,6 +584,7 @@ static inline bool ieee80211_is_reassoc_resp(__le16 fc) /** * ieee80211_is_probe_req - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_PROBE_REQ * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is a probe request */ static inline bool ieee80211_is_probe_req(__le16 fc) { @@ -574,6 +595,7 @@ static inline bool ieee80211_is_probe_req(__le16 fc) /** * ieee80211_is_probe_resp - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_PROBE_RESP * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is a probe response */ static inline bool ieee80211_is_probe_resp(__le16 fc) { @@ -584,6 +606,7 @@ static inline bool ieee80211_is_probe_resp(__le16 fc) /** * ieee80211_is_beacon - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_BEACON * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is a (regular, not S1G) beacon */ static inline bool ieee80211_is_beacon(__le16 fc) { @@ -595,6 +618,7 @@ static inline bool ieee80211_is_beacon(__le16 fc) * ieee80211_is_s1g_beacon - check if IEEE80211_FTYPE_EXT && * IEEE80211_STYPE_S1G_BEACON * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is an S1G beacon */ static inline bool ieee80211_is_s1g_beacon(__le16 fc) { @@ -604,30 +628,21 @@ static inline bool ieee80211_is_s1g_beacon(__le16 fc) } /** - * ieee80211_next_tbtt_present - check if IEEE80211_FTYPE_EXT && - * IEEE80211_STYPE_S1G_BEACON && IEEE80211_S1G_BCN_NEXT_TBTT - * @fc: frame control bytes in little-endian byteorder - */ -static inline bool ieee80211_next_tbtt_present(__le16 fc) -{ - return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == - cpu_to_le16(IEEE80211_FTYPE_EXT | IEEE80211_STYPE_S1G_BEACON) && - fc & cpu_to_le16(IEEE80211_S1G_BCN_NEXT_TBTT); -} - -/** - * ieee80211_is_s1g_short_beacon - check if next tbtt present bit is set. Only - * true for S1G beacons when they're short. + * ieee80211_is_s1g_short_beacon - check if frame is an S1G short beacon * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is an S1G short beacon, + * i.e. it is an S1G beacon with 'next TBTT' flag set */ static inline bool ieee80211_is_s1g_short_beacon(__le16 fc) { - return ieee80211_is_s1g_beacon(fc) && ieee80211_next_tbtt_present(fc); + return ieee80211_is_s1g_beacon(fc) && + (fc & cpu_to_le16(IEEE80211_S1G_BCN_NEXT_TBTT)); } /** * ieee80211_is_atim - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ATIM * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is an ATIM frame */ static inline bool ieee80211_is_atim(__le16 fc) { @@ -638,6 +653,7 @@ static inline bool ieee80211_is_atim(__le16 fc) /** * ieee80211_is_disassoc - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_DISASSOC * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is a disassociation frame */ static inline bool ieee80211_is_disassoc(__le16 fc) { @@ -648,6 +664,7 @@ static inline bool ieee80211_is_disassoc(__le16 fc) /** * ieee80211_is_auth - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_AUTH * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is an authentication frame */ static inline bool ieee80211_is_auth(__le16 fc) { @@ -658,6 +675,7 @@ static inline bool ieee80211_is_auth(__le16 fc) /** * ieee80211_is_deauth - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_DEAUTH * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is a deauthentication frame */ static inline bool ieee80211_is_deauth(__le16 fc) { @@ -668,6 +686,7 @@ static inline bool ieee80211_is_deauth(__le16 fc) /** * ieee80211_is_action - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ACTION * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is an action frame */ static inline bool ieee80211_is_action(__le16 fc) { @@ -678,6 +697,7 @@ static inline bool ieee80211_is_action(__le16 fc) /** * ieee80211_is_back_req - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_BACK_REQ * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is a block-ACK request frame */ static inline bool ieee80211_is_back_req(__le16 fc) { @@ -688,6 +708,7 @@ static inline bool ieee80211_is_back_req(__le16 fc) /** * ieee80211_is_back - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_BACK * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is a block-ACK frame */ static inline bool ieee80211_is_back(__le16 fc) { @@ -698,6 +719,7 @@ static inline bool ieee80211_is_back(__le16 fc) /** * ieee80211_is_pspoll - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_PSPOLL * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is a PS-poll frame */ static inline bool ieee80211_is_pspoll(__le16 fc) { @@ -708,6 +730,7 @@ static inline bool ieee80211_is_pspoll(__le16 fc) /** * ieee80211_is_rts - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_RTS * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is an RTS frame */ static inline bool ieee80211_is_rts(__le16 fc) { @@ -718,6 +741,7 @@ static inline bool ieee80211_is_rts(__le16 fc) /** * ieee80211_is_cts - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_CTS * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is a CTS frame */ static inline bool ieee80211_is_cts(__le16 fc) { @@ -728,6 +752,7 @@ static inline bool ieee80211_is_cts(__le16 fc) /** * ieee80211_is_ack - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_ACK * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is an ACK frame */ static inline bool ieee80211_is_ack(__le16 fc) { @@ -738,6 +763,7 @@ static inline bool ieee80211_is_ack(__le16 fc) /** * ieee80211_is_cfend - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_CFEND * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is a CF-end frame */ static inline bool ieee80211_is_cfend(__le16 fc) { @@ -748,6 +774,7 @@ static inline bool ieee80211_is_cfend(__le16 fc) /** * ieee80211_is_cfendack - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_CFENDACK * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is a CF-end-ack frame */ static inline bool ieee80211_is_cfendack(__le16 fc) { @@ -758,6 +785,7 @@ static inline bool ieee80211_is_cfendack(__le16 fc) /** * ieee80211_is_nullfunc - check if frame is a regular (non-QoS) nullfunc frame * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is a nullfunc frame */ static inline bool ieee80211_is_nullfunc(__le16 fc) { @@ -768,6 +796,7 @@ static inline bool ieee80211_is_nullfunc(__le16 fc) /** * ieee80211_is_qos_nullfunc - check if frame is a QoS nullfunc frame * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is a QoS nullfunc frame */ static inline bool ieee80211_is_qos_nullfunc(__le16 fc) { @@ -778,6 +807,7 @@ static inline bool ieee80211_is_qos_nullfunc(__le16 fc) /** * ieee80211_is_trigger - check if frame is trigger frame * @fc: frame control field in little-endian byteorder + * Return: whether or not the frame is a trigger frame */ static inline bool ieee80211_is_trigger(__le16 fc) { @@ -788,6 +818,7 @@ static inline bool ieee80211_is_trigger(__le16 fc) /** * ieee80211_is_any_nullfunc - check if frame is regular or QoS nullfunc frame * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is a nullfunc or QoS nullfunc frame */ static inline bool ieee80211_is_any_nullfunc(__le16 fc) { @@ -797,6 +828,8 @@ static inline bool ieee80211_is_any_nullfunc(__le16 fc) /** * ieee80211_is_first_frag - check if IEEE80211_SCTL_FRAG is not set * @seq_ctrl: frame sequence control bytes in little-endian byteorder + * Return: whether or not the frame is the first fragment (also true if + * it's not fragmented at all) */ static inline bool ieee80211_is_first_frag(__le16 seq_ctrl) { @@ -806,6 +839,7 @@ static inline bool ieee80211_is_first_frag(__le16 seq_ctrl) /** * ieee80211_is_frag - check if a frame is a fragment * @hdr: 802.11 header of the frame + * Return: whether or not the frame is a fragment */ static inline bool ieee80211_is_frag(struct ieee80211_hdr *hdr) { @@ -1101,7 +1135,7 @@ enum ieee80211_vht_opmode_bits { }; /** - * enum ieee80211_s1g_chanwidth + * enum ieee80211_s1g_chanwidth - S1G channel widths * These are defined in IEEE802.11-2016ah Table 10-20 * as BSS Channel Width * @@ -1287,6 +1321,24 @@ struct ieee80211_ttlm_elem { u8 optional[]; } __packed; +/** + * struct ieee80211_bss_load_elem - BSS Load elemen + * + * Defined in section 9.4.2.26 in IEEE 802.11-REVme D4.1 + * + * @sta_count: total number of STAs currently associated with the AP. + * @channel_util: Percentage of time that the access point sensed the channel + * was busy. This value is in range [0, 255], the highest value means + * 100% busy. + * @avail_admission_capa: remaining amount of medium time used for admission + * control. + */ +struct ieee80211_bss_load_elem { + __le16 sta_count; + u8 channel_util; + __le16 avail_admission_capa; +} __packed; + struct ieee80211_mgmt { __le16 frame_control; __le16 duration; @@ -1393,6 +1445,8 @@ struct ieee80211_mgmt { __le16 status; __le16 capab; __le16 timeout; + /* followed by BA Extension */ + u8 variable[]; } __packed addba_resp; struct{ u8 action_code; @@ -1478,6 +1532,17 @@ struct ieee80211_mgmt { struct { u8 action_code; } __packed ttlm_tear_down; + struct { + u8 action_code; + u8 dialog_token; + u8 variable[]; + } __packed ml_reconf_req; + struct { + u8 action_code; + u8 dialog_token; + u8 count; + u8 variable[]; + } __packed ml_reconf_resp; } u; } __packed action; DECLARE_FLEX_ARRAY(u8, body); /* Generic frame body */ @@ -1488,11 +1553,13 @@ struct ieee80211_mgmt { #define BSS_MEMBERSHIP_SELECTOR_HT_PHY 127 #define BSS_MEMBERSHIP_SELECTOR_VHT_PHY 126 #define BSS_MEMBERSHIP_SELECTOR_GLK 125 -#define BSS_MEMBERSHIP_SELECTOR_EPS 124 +#define BSS_MEMBERSHIP_SELECTOR_EPD 124 #define BSS_MEMBERSHIP_SELECTOR_SAE_H2E 123 #define BSS_MEMBERSHIP_SELECTOR_HE_PHY 122 #define BSS_MEMBERSHIP_SELECTOR_EHT_PHY 121 +#define BSS_MEMBERSHIP_SELECTOR_MIN BSS_MEMBERSHIP_SELECTOR_EHT_PHY + /* mgmt header + 1 byte category code */ #define IEEE80211_MIN_ACTION_SIZE offsetof(struct ieee80211_mgmt, u.action.u) @@ -2341,6 +2408,8 @@ struct ieee80211_eht_operation_info { * @max_vht_nss: current maximum NSS as advertised by the STA in * operating mode notification, can be 0 in which case the * capability data will be used to derive this (from MCS support) + * Return: The maximum NSS that can be used for the given bandwidth/MCS + * combination * * Due to the VHT Extended NSS Bandwidth Support, the maximum NSS can * vary for a given BW/MCS. This function parses the data. @@ -2352,44 +2421,6 @@ int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, int mcs, bool ext_nss_bw_capable, unsigned int max_vht_nss); -/** - * enum ieee80211_ap_reg_power - regulatory power for a Access Point - * - * @IEEE80211_REG_UNSET_AP: Access Point has no regulatory power mode - * @IEEE80211_REG_LPI_AP: Indoor Access Point - * @IEEE80211_REG_SP_AP: Standard power Access Point - * @IEEE80211_REG_VLP_AP: Very low power Access Point - * @IEEE80211_REG_AP_POWER_AFTER_LAST: internal - * @IEEE80211_REG_AP_POWER_MAX: maximum value - */ -enum ieee80211_ap_reg_power { - IEEE80211_REG_UNSET_AP, - IEEE80211_REG_LPI_AP, - IEEE80211_REG_SP_AP, - IEEE80211_REG_VLP_AP, - IEEE80211_REG_AP_POWER_AFTER_LAST, - IEEE80211_REG_AP_POWER_MAX = - IEEE80211_REG_AP_POWER_AFTER_LAST - 1, -}; - -/** - * enum ieee80211_client_reg_power - regulatory power for a client - * - * @IEEE80211_REG_UNSET_CLIENT: Client has no regulatory power mode - * @IEEE80211_REG_DEFAULT_CLIENT: Default Client - * @IEEE80211_REG_SUBORDINATE_CLIENT: Subordinate Client - * @IEEE80211_REG_CLIENT_POWER_AFTER_LAST: internal - * @IEEE80211_REG_CLIENT_POWER_MAX: maximum value - */ -enum ieee80211_client_reg_power { - IEEE80211_REG_UNSET_CLIENT, - IEEE80211_REG_DEFAULT_CLIENT, - IEEE80211_REG_SUBORDINATE_CLIENT, - IEEE80211_REG_CLIENT_POWER_AFTER_LAST, - IEEE80211_REG_CLIENT_POWER_MAX = - IEEE80211_REG_CLIENT_POWER_AFTER_LAST - 1, -}; - /* 802.11ax HE MAC capabilities */ #define IEEE80211_HE_MAC_CAP0_HTC_HE 0x01 #define IEEE80211_HE_MAC_CAP0_TWT_REQ 0x02 @@ -2742,9 +2773,11 @@ static inline bool ieee80211_he_capa_size_ok(const u8 *data, u8 len) #define IEEE80211_HE_OPERATION_PARTIAL_BSS_COLOR 0x40000000 #define IEEE80211_HE_OPERATION_BSS_COLOR_DISABLED 0x80000000 -#define IEEE80211_6GHZ_CTRL_REG_LPI_AP 0 -#define IEEE80211_6GHZ_CTRL_REG_SP_AP 1 -#define IEEE80211_6GHZ_CTRL_REG_VLP_AP 2 +#define IEEE80211_6GHZ_CTRL_REG_LPI_AP 0 +#define IEEE80211_6GHZ_CTRL_REG_SP_AP 1 +#define IEEE80211_6GHZ_CTRL_REG_VLP_AP 2 +#define IEEE80211_6GHZ_CTRL_REG_INDOOR_LPI_AP 3 +#define IEEE80211_6GHZ_CTRL_REG_INDOOR_SP_AP 4 /** * struct ieee80211_he_6ghz_oper - HE 6 GHz operation Information field @@ -2769,22 +2802,6 @@ struct ieee80211_he_6ghz_oper { u8 minrate; } __packed; -/* - * In "9.4.2.161 Transmit Power Envelope element" of "IEEE Std 802.11ax-2021", - * it show four types in "Table 9-275a-Maximum Transmit Power Interpretation - * subfield encoding", and two category for each type in "Table E-12-Regulatory - * Info subfield encoding in the United States". - * So it it totally max 8 Transmit Power Envelope element. - */ -#define IEEE80211_TPE_MAX_IE_COUNT 8 -/* - * In "Table 9-277—Meaning of Maximum Transmit Power Count subfield" - * of "IEEE Std 802.11ax™‐2021", the max power level is 8. - */ -#define IEEE80211_MAX_NUM_PWR_LEVEL 8 - -#define IEEE80211_TPE_MAX_POWER_COUNT 8 - /* transmit power interpretation type of transmit power envelope element */ enum ieee80211_tx_power_intrpt_type { IEEE80211_TPE_LOCAL_EIRP, @@ -2793,24 +2810,107 @@ enum ieee80211_tx_power_intrpt_type { IEEE80211_TPE_REG_CLIENT_EIRP_PSD, }; +/* category type of transmit power envelope element */ +enum ieee80211_tx_power_category_6ghz { + IEEE80211_TPE_CAT_6GHZ_DEFAULT = 0, + IEEE80211_TPE_CAT_6GHZ_SUBORDINATE = 1, +}; + +/* + * For IEEE80211_TPE_LOCAL_EIRP / IEEE80211_TPE_REG_CLIENT_EIRP, + * setting to 63.5 dBm means no constraint. + */ +#define IEEE80211_TPE_MAX_TX_PWR_NO_CONSTRAINT 127 + +/* + * For IEEE80211_TPE_LOCAL_EIRP_PSD / IEEE80211_TPE_REG_CLIENT_EIRP_PSD, + * setting to 127 indicates no PSD limit for the 20 MHz channel. + */ +#define IEEE80211_TPE_PSD_NO_LIMIT 127 + /** * struct ieee80211_tx_pwr_env - Transmit Power Envelope - * @tx_power_info: Transmit Power Information field - * @tx_power: Maximum Transmit Power field + * @info: Transmit Power Information field + * @variable: Maximum Transmit Power field * * This structure represents the payload of the "Transmit Power * Envelope element" as described in IEEE Std 802.11ax-2021 section * 9.4.2.161 */ struct ieee80211_tx_pwr_env { - u8 tx_power_info; - s8 tx_power[IEEE80211_TPE_MAX_POWER_COUNT]; + u8 info; + u8 variable[]; } __packed; #define IEEE80211_TX_PWR_ENV_INFO_COUNT 0x7 #define IEEE80211_TX_PWR_ENV_INFO_INTERPRET 0x38 #define IEEE80211_TX_PWR_ENV_INFO_CATEGORY 0xC0 +#define IEEE80211_TX_PWR_ENV_EXT_COUNT 0xF + +static inline bool ieee80211_valid_tpe_element(const u8 *data, u8 len) +{ + const struct ieee80211_tx_pwr_env *env = (const void *)data; + u8 count, interpret, category; + u8 needed = sizeof(*env); + u8 N; /* also called N in the spec */ + + if (len < needed) + return false; + + count = u8_get_bits(env->info, IEEE80211_TX_PWR_ENV_INFO_COUNT); + interpret = u8_get_bits(env->info, IEEE80211_TX_PWR_ENV_INFO_INTERPRET); + category = u8_get_bits(env->info, IEEE80211_TX_PWR_ENV_INFO_CATEGORY); + + switch (category) { + case IEEE80211_TPE_CAT_6GHZ_DEFAULT: + case IEEE80211_TPE_CAT_6GHZ_SUBORDINATE: + break; + default: + return false; + } + + switch (interpret) { + case IEEE80211_TPE_LOCAL_EIRP: + case IEEE80211_TPE_REG_CLIENT_EIRP: + if (count > 3) + return false; + + /* count == 0 encodes 1 value for 20 MHz, etc. */ + needed += count + 1; + + if (len < needed) + return false; + + /* there can be extension fields not accounted for in 'count' */ + + return true; + case IEEE80211_TPE_LOCAL_EIRP_PSD: + case IEEE80211_TPE_REG_CLIENT_EIRP_PSD: + if (count > 4) + return false; + + N = count ? 1 << (count - 1) : 1; + needed += N; + + if (len < needed) + return false; + + if (len > needed) { + u8 K = u8_get_bits(env->variable[N], + IEEE80211_TX_PWR_ENV_EXT_COUNT); + + needed += 1 + K; + if (len < needed) + return false; + } + + return true; + } + + return false; +} + /* * ieee80211_he_oper_size - calculate 802.11ax HE Operations IE size * @he_oper_ie: byte data of the He Operations IE, stating from the byte @@ -3796,6 +3896,16 @@ enum ieee80211_protected_eht_actioncode { WLAN_PROTECTED_EHT_ACTION_TTLM_REQ = 0, WLAN_PROTECTED_EHT_ACTION_TTLM_RES = 1, WLAN_PROTECTED_EHT_ACTION_TTLM_TEARDOWN = 2, + WLAN_PROTECTED_EHT_ACTION_EPCS_ENABLE_REQ = 3, + WLAN_PROTECTED_EHT_ACTION_EPCS_ENABLE_RESP = 4, + WLAN_PROTECTED_EHT_ACTION_EPCS_ENABLE_TEARDOWN = 5, + WLAN_PROTECTED_EHT_ACTION_EML_OP_MODE_NOTIF = 6, + WLAN_PROTECTED_EHT_ACTION_LINK_RECOMMEND = 7, + WLAN_PROTECTED_EHT_ACTION_ML_OP_UPDATE_REQ = 8, + WLAN_PROTECTED_EHT_ACTION_ML_OP_UPDATE_RESP = 9, + WLAN_PROTECTED_EHT_ACTION_LINK_RECONFIG_NOTIF = 10, + WLAN_PROTECTED_EHT_ACTION_LINK_RECONFIG_REQ = 11, + WLAN_PROTECTED_EHT_ACTION_LINK_RECONFIG_RESP = 12, }; /* Security key length */ @@ -4125,7 +4235,7 @@ enum ieee80211_idle_options { }; /** - * struct ieee80211_bss_max_idle_period_ie + * struct ieee80211_bss_max_idle_period_ie - BSS max idle period element struct * * This structure refers to "BSS Max idle period element" * @@ -4160,7 +4270,7 @@ enum ieee80211_sa_query_action { }; /** - * struct ieee80211_bssid_index + * struct ieee80211_bssid_index - multiple BSSID index element structure * * This structure refers to "Multiple BSSID-index element" * @@ -4175,7 +4285,8 @@ struct ieee80211_bssid_index { }; /** - * struct ieee80211_multiple_bssid_configuration + * struct ieee80211_multiple_bssid_configuration - multiple BSSID configuration + * element structure * * This structure refers to "Multiple BSSID Configuration element" * @@ -4306,6 +4417,7 @@ struct ieee80211_he_6ghz_capa { /** * ieee80211_get_qos_ctl - get pointer to qos control bytes * @hdr: the frame + * Return: a pointer to the QoS control field in the frame header * * The qos ctrl bytes come after the frame_control, duration, seq_num * and 3 or 4 addresses of length ETH_ALEN. Checks frame_control to choose @@ -4328,6 +4440,7 @@ static inline u8 *ieee80211_get_qos_ctl(struct ieee80211_hdr *hdr) /** * ieee80211_get_tid - get qos TID * @hdr: the frame + * Return: the TID from the QoS control field */ static inline u8 ieee80211_get_tid(struct ieee80211_hdr *hdr) { @@ -4339,6 +4452,7 @@ static inline u8 ieee80211_get_tid(struct ieee80211_hdr *hdr) /** * ieee80211_get_SA - get pointer to SA * @hdr: the frame + * Return: a pointer to the source address (SA) * * Given an 802.11 frame, this function returns the offset * to the source address (SA). It does not verify that the @@ -4358,6 +4472,7 @@ static inline u8 *ieee80211_get_SA(struct ieee80211_hdr *hdr) /** * ieee80211_get_DA - get pointer to DA * @hdr: the frame + * Return: a pointer to the destination address (DA) * * Given an 802.11 frame, this function returns the offset * to the destination address (DA). It does not verify that @@ -4376,6 +4491,7 @@ static inline u8 *ieee80211_get_DA(struct ieee80211_hdr *hdr) /** * ieee80211_is_bufferable_mmpdu - check if frame is bufferable MMPDU * @skb: the skb to check, starting with the 802.11 header + * Return: whether or not the MMPDU is bufferable */ static inline bool ieee80211_is_bufferable_mmpdu(struct sk_buff *skb) { @@ -4414,6 +4530,7 @@ static inline bool ieee80211_is_bufferable_mmpdu(struct sk_buff *skb) /** * _ieee80211_is_robust_mgmt_frame - check if frame is a robust management frame * @hdr: the frame (buffer must include at least the first octet of payload) + * Return: whether or not the frame is a robust management frame */ static inline bool _ieee80211_is_robust_mgmt_frame(struct ieee80211_hdr *hdr) { @@ -4450,6 +4567,7 @@ static inline bool _ieee80211_is_robust_mgmt_frame(struct ieee80211_hdr *hdr) /** * ieee80211_is_robust_mgmt_frame - check if skb contains a robust mgmt frame * @skb: the skb containing the frame, length will be checked + * Return: whether or not the frame is a robust management frame */ static inline bool ieee80211_is_robust_mgmt_frame(struct sk_buff *skb) { @@ -4462,6 +4580,7 @@ static inline bool ieee80211_is_robust_mgmt_frame(struct sk_buff *skb) * ieee80211_is_public_action - check if frame is a public action frame * @hdr: the frame * @len: length of the frame + * Return: whether or not the frame is a public action frame */ static inline bool ieee80211_is_public_action(struct ieee80211_hdr *hdr, size_t len) @@ -4507,8 +4626,9 @@ ieee80211_is_protected_dual_of_public_action(struct sk_buff *skb) /** * _ieee80211_is_group_privacy_action - check if frame is a group addressed - * privacy action frame + * privacy action frame * @hdr: the frame + * Return: whether or not the frame is a group addressed privacy action frame */ static inline bool _ieee80211_is_group_privacy_action(struct ieee80211_hdr *hdr) { @@ -4524,8 +4644,9 @@ static inline bool _ieee80211_is_group_privacy_action(struct ieee80211_hdr *hdr) /** * ieee80211_is_group_privacy_action - check if frame is a group addressed - * privacy action frame + * privacy action frame * @skb: the skb containing the frame, length will be checked + * Return: whether or not the frame is a group addressed privacy action frame */ static inline bool ieee80211_is_group_privacy_action(struct sk_buff *skb) { @@ -4537,6 +4658,7 @@ static inline bool ieee80211_is_group_privacy_action(struct sk_buff *skb) /** * ieee80211_tu_to_usec - convert time units (TU) to microseconds * @tu: the TUs + * Return: the time value converted to microseconds */ static inline unsigned long ieee80211_tu_to_usec(unsigned long tu) { @@ -4548,6 +4670,7 @@ static inline unsigned long ieee80211_tu_to_usec(unsigned long tu) * @tim: the TIM IE * @tim_len: length of the TIM IE * @aid: the AID to look for + * Return: whether or not traffic is indicated in the TIM for the given AID */ static inline bool ieee80211_check_tim(const struct ieee80211_tim_ie *tim, u8 tim_len, u16 aid) @@ -4574,8 +4697,10 @@ static inline bool ieee80211_check_tim(const struct ieee80211_tim_ie *tim, } /** - * ieee80211_get_tdls_action - get tdls packet action (or -1, if not tdls packet) + * ieee80211_get_tdls_action - get TDLS action code * @skb: the skb containing the frame, length will not be checked + * Return: the TDLS action code, or -1 if it's not an encapsulated TDLS action + * frame * * This function assumes the frame is a data frame, and that the network header * is in the correct place. @@ -4615,6 +4740,7 @@ static inline int ieee80211_get_tdls_action(struct sk_buff *skb) /** * ieee80211_action_contains_tpc - checks if the frame contains TPC element * @skb: the skb containing the frame, length will be checked + * Return: %true if the frame contains a TPC element, %false otherwise * * This function checks if it's either TPC report action frame or Link * Measurement report action frame as defined in IEEE Std. 802.11-2012 8.5.2.5 @@ -4659,6 +4785,11 @@ static inline bool ieee80211_action_contains_tpc(struct sk_buff *skb) return true; } +/** + * ieee80211_is_timing_measurement - check if frame is timing measurement response + * @skb: the SKB to check + * Return: whether or not the frame is a valid timing measurement response + */ static inline bool ieee80211_is_timing_measurement(struct sk_buff *skb) { struct ieee80211_mgmt *mgmt = (void *)skb->data; @@ -4678,6 +4809,11 @@ static inline bool ieee80211_is_timing_measurement(struct sk_buff *skb) return false; } +/** + * ieee80211_is_ftm - check if frame is FTM response + * @skb: the SKB to check + * Return: whether or not the frame is a valid FTM response action frame + */ static inline bool ieee80211_is_ftm(struct sk_buff *skb) { struct ieee80211_mgmt *mgmt = (void *)skb->data; @@ -4732,6 +4868,7 @@ struct element { * @element: element pointer after for_each_element() or friends * @data: same data pointer as passed to for_each_element() or friends * @datalen: same data length as passed to for_each_element() or friends + * Return: %true if all elements were iterated, %false otherwise; see notes * * This function returns %true if all the data was parsed or considered * while walking the elements. Only use this if your for_each_element() @@ -4847,6 +4984,7 @@ struct ieee80211_multi_link_elem { #define IEEE80211_MLC_BASIC_PRES_EML_CAPA 0x0080 #define IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP 0x0100 #define IEEE80211_MLC_BASIC_PRES_MLD_ID 0x0200 +#define IEEE80211_MLC_BASIC_PRES_EXT_MLD_CAPA_OP 0x0400 #define IEEE80211_MED_SYNC_DELAY_DURATION 0x00ff #define IEEE80211_MED_SYNC_DELAY_SYNC_OFDM_ED_THRESH 0x0f00 @@ -4904,6 +5042,8 @@ struct ieee80211_multi_link_elem { #define IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_SUPP_DIFF 3 #define IEEE80211_MLD_CAP_OP_FREQ_SEP_TYPE_IND 0x0f80 #define IEEE80211_MLD_CAP_OP_AAR_SUPPORT 0x1000 +#define IEEE80211_MLD_CAP_OP_LINK_RECONF_SUPPORT 0x2000 +#define IEEE80211_MLD_CAP_OP_ALIGNED_TWT_SUPPORT 0x4000 struct ieee80211_mle_basic_common_info { u8 len; @@ -4919,6 +5059,9 @@ struct ieee80211_mle_preq_common_info { } __packed; #define IEEE80211_MLC_RECONF_PRES_MLD_MAC_ADDR 0x0010 +#define IEEE80211_MLC_RECONF_PRES_EML_CAPA 0x0020 +#define IEEE80211_MLC_RECONF_PRES_MLD_CAPA_OP 0x0040 +#define IEEE80211_MLC_RECONF_PRES_EXT_MLD_CAPA_OP 0x0080 /* no fixed fields in RECONF */ @@ -4935,43 +5078,39 @@ struct ieee80211_mle_tdls_common_info { * ieee80211_mle_common_size - check multi-link element common size * @data: multi-link element, must already be checked for size using * ieee80211_mle_size_ok() + * Return: the size of the multi-link element's "common" subfield */ static inline u8 ieee80211_mle_common_size(const u8 *data) { const struct ieee80211_multi_link_elem *mle = (const void *)data; u16 control = le16_to_cpu(mle->control); - u8 common = 0; switch (u16_get_bits(control, IEEE80211_ML_CONTROL_TYPE)) { case IEEE80211_ML_CONTROL_TYPE_BASIC: case IEEE80211_ML_CONTROL_TYPE_PREQ: case IEEE80211_ML_CONTROL_TYPE_TDLS: case IEEE80211_ML_CONTROL_TYPE_RECONF: + case IEEE80211_ML_CONTROL_TYPE_PRIO_ACCESS: /* * The length is the first octet pointed by mle->variable so no * need to add anything */ break; - case IEEE80211_ML_CONTROL_TYPE_PRIO_ACCESS: - if (control & IEEE80211_MLC_PRIO_ACCESS_PRES_AP_MLD_MAC_ADDR) - common += ETH_ALEN; - return common; default: WARN_ON(1); return 0; } - return sizeof(*mle) + common + mle->variable[0]; + return sizeof(*mle) + mle->variable[0]; } /** * ieee80211_mle_get_link_id - returns the link ID * @data: the basic multi link element + * Return: the link ID, or -1 if not present * * The element is assumed to be of the correct type (BASIC) and big enough, * this must be checked using ieee80211_mle_type_ok(). - * - * If the BSS link ID can't be found, -1 will be returned */ static inline int ieee80211_mle_get_link_id(const u8 *data) { @@ -4991,12 +5130,10 @@ static inline int ieee80211_mle_get_link_id(const u8 *data) /** * ieee80211_mle_get_bss_param_ch_cnt - returns the BSS parameter change count * @data: pointer to the basic multi link element + * Return: the BSS Parameter Change Count field value, or -1 if not present * * The element is assumed to be of the correct type (BASIC) and big enough, * this must be checked using ieee80211_mle_type_ok(). - * - * If the BSS parameter change count value can't be found (the presence bit - * for it is clear), -1 will be returned. */ static inline int ieee80211_mle_get_bss_param_ch_cnt(const u8 *data) @@ -5019,13 +5156,13 @@ ieee80211_mle_get_bss_param_ch_cnt(const u8 *data) /** * ieee80211_mle_get_eml_med_sync_delay - returns the medium sync delay - * @data: pointer to the multi link EHT IE + * @data: pointer to the multi-link element + * Return: the medium synchronization delay field value from the multi-link + * element, or the default value (%IEEE80211_MED_SYNC_DELAY_DEFAULT) + * if not present * * The element is assumed to be of the correct type (BASIC) and big enough, * this must be checked using ieee80211_mle_type_ok(). - * - * If the medium synchronization is not present, then the default value is - * returned. */ static inline u16 ieee80211_mle_get_eml_med_sync_delay(const u8 *data) { @@ -5049,12 +5186,12 @@ static inline u16 ieee80211_mle_get_eml_med_sync_delay(const u8 *data) /** * ieee80211_mle_get_eml_cap - returns the EML capability - * @data: pointer to the multi link EHT IE + * @data: pointer to the multi-link element + * Return: the EML capability field value from the multi-link element, + * or 0 if not present * * The element is assumed to be of the correct type (BASIC) and big enough, * this must be checked using ieee80211_mle_type_ok(). - * - * If the EML capability is not present, 0 will be returned. */ static inline u16 ieee80211_mle_get_eml_cap(const u8 *data) { @@ -5080,13 +5217,12 @@ static inline u16 ieee80211_mle_get_eml_cap(const u8 *data) /** * ieee80211_mle_get_mld_capa_op - returns the MLD capabilities and operations. - * @data: pointer to the multi link EHT IE + * @data: pointer to the multi-link element + * Return: the MLD capabilities and operations field value from the multi-link + * element, or 0 if not present * * The element is assumed to be of the correct type (BASIC) and big enough, * this must be checked using ieee80211_mle_type_ok(). - * - * If the MLD capabilities and operations field is not present, 0 will be - * returned. */ static inline u16 ieee80211_mle_get_mld_capa_op(const u8 *data) { @@ -5116,13 +5252,53 @@ static inline u16 ieee80211_mle_get_mld_capa_op(const u8 *data) } /** - * ieee80211_mle_get_mld_id - returns the MLD ID - * @data: pointer to the multi link element + * ieee80211_mle_get_ext_mld_capa_op - returns the extended MLD capabilities + * and operations. + * @data: pointer to the multi-link element + * Return: the extended MLD capabilities and operations field value from + * the multi-link element, or 0 if not present * * The element is assumed to be of the correct type (BASIC) and big enough, * this must be checked using ieee80211_mle_type_ok(). + */ +static inline u16 ieee80211_mle_get_ext_mld_capa_op(const u8 *data) +{ + const struct ieee80211_multi_link_elem *mle = (const void *)data; + u16 control = le16_to_cpu(mle->control); + const u8 *common = mle->variable; + + /* + * common points now at the beginning of + * ieee80211_mle_basic_common_info + */ + common += sizeof(struct ieee80211_mle_basic_common_info); + + if (!(control & IEEE80211_MLC_BASIC_PRES_EXT_MLD_CAPA_OP)) + return 0; + + if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID) + common += 1; + if (control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT) + common += 1; + if (control & IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY) + common += 2; + if (control & IEEE80211_MLC_BASIC_PRES_EML_CAPA) + common += 2; + if (control & IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP) + common += 2; + if (control & IEEE80211_MLC_BASIC_PRES_MLD_ID) + common += 1; + + return get_unaligned_le16(common); +} + +/** + * ieee80211_mle_get_mld_id - returns the MLD ID + * @data: pointer to the multi-link element + * Return: The MLD ID in the given multi-link element, or 0 if not present * - * If the MLD ID is not present, 0 will be returned. + * The element is assumed to be of the correct type (BASIC) and big enough, + * this must be checked using ieee80211_mle_type_ok(). */ static inline u8 ieee80211_mle_get_mld_id(const u8 *data) { @@ -5157,6 +5333,7 @@ static inline u8 ieee80211_mle_get_mld_id(const u8 *data) * ieee80211_mle_size_ok - validate multi-link element size * @data: pointer to the element data * @len: length of the containing element + * Return: whether or not the multi-link element size is OK */ static inline bool ieee80211_mle_size_ok(const u8 *data, size_t len) { @@ -5166,7 +5343,7 @@ static inline bool ieee80211_mle_size_ok(const u8 *data, size_t len) bool check_common_len = false; u16 control; - if (len < fixed) + if (!data || len < fixed) return false; control = le16_to_cpu(mle->control); @@ -5187,6 +5364,8 @@ static inline bool ieee80211_mle_size_ok(const u8 *data, size_t len) common += 2; if (control & IEEE80211_MLC_BASIC_PRES_MLD_ID) common += 1; + if (control & IEEE80211_MLC_BASIC_PRES_EXT_MLD_CAPA_OP) + common += 2; break; case IEEE80211_ML_CONTROL_TYPE_PREQ: common += sizeof(struct ieee80211_mle_preq_common_info); @@ -5197,14 +5376,19 @@ static inline bool ieee80211_mle_size_ok(const u8 *data, size_t len) case IEEE80211_ML_CONTROL_TYPE_RECONF: if (control & IEEE80211_MLC_RECONF_PRES_MLD_MAC_ADDR) common += ETH_ALEN; + if (control & IEEE80211_MLC_RECONF_PRES_EML_CAPA) + common += 2; + if (control & IEEE80211_MLC_RECONF_PRES_MLD_CAPA_OP) + common += 2; + if (control & IEEE80211_MLC_RECONF_PRES_EXT_MLD_CAPA_OP) + common += 2; break; case IEEE80211_ML_CONTROL_TYPE_TDLS: common += sizeof(struct ieee80211_mle_tdls_common_info); check_common_len = true; break; case IEEE80211_ML_CONTROL_TYPE_PRIO_ACCESS: - if (control & IEEE80211_MLC_PRIO_ACCESS_PRES_AP_MLD_MAC_ADDR) - common += ETH_ALEN; + common = ETH_ALEN + 1; break; default: /* we don't know this type */ @@ -5226,6 +5410,7 @@ static inline bool ieee80211_mle_size_ok(const u8 *data, size_t len) * @data: pointer to the element data * @type: expected type of the element * @len: length of the containing element + * Return: whether or not the multi-link element type matches and size is OK */ static inline bool ieee80211_mle_type_ok(const u8 *data, u8 type, size_t len) { @@ -5269,6 +5454,7 @@ struct ieee80211_mle_per_sta_profile { * profile size * @data: pointer to the sub element data * @len: length of the containing sub element + * Return: %true if the STA profile is large enough, %false otherwise */ static inline bool ieee80211_mle_basic_sta_prof_size_ok(const u8 *data, size_t len) @@ -5302,7 +5488,7 @@ static inline bool ieee80211_mle_basic_sta_prof_size_ok(const u8 *data, info_len += 1; return prof->sta_info_len >= info_len && - fixed + prof->sta_info_len <= len; + fixed + prof->sta_info_len - 1 <= len; } /** @@ -5345,14 +5531,20 @@ ieee80211_mle_basic_sta_prof_bss_param_ch_cnt(const struct ieee80211_mle_per_sta #define IEEE80211_MLE_STA_RECONF_CONTROL_COMPLETE_PROFILE 0x0010 #define IEEE80211_MLE_STA_RECONF_CONTROL_STA_MAC_ADDR_PRESENT 0x0020 #define IEEE80211_MLE_STA_RECONF_CONTROL_AP_REM_TIMER_PRESENT 0x0040 -#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_UPDATE_TYPE 0x0780 -#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_PARAMS_PRESENT 0x0800 +#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE 0x0780 +#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE_AP_REM 0 +#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE_OP_PARAM_UPDATE 1 +#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE_ADD_LINK 2 +#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE_DEL_LINK 3 +#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE_NSTR_STATUS 4 +#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_PARAMS_PRESENT 0x0800 /** * ieee80211_mle_reconf_sta_prof_size_ok - validate reconfiguration multi-link * element sta profile size. * @data: pointer to the sub element data * @len: length of the containing sub element + * Return: %true if the STA profile is large enough, %false otherwise */ static inline bool ieee80211_mle_reconf_sta_prof_size_ok(const u8 *data, size_t len) diff --git a/include/linux/if_hsr.h b/include/linux/if_hsr.h index 0404f5bf4f30..d7941fd88032 100644 --- a/include/linux/if_hsr.h +++ b/include/linux/if_hsr.h @@ -13,6 +13,15 @@ enum hsr_version { PRP_V1, }; +enum hsr_port_type { + HSR_PT_NONE = 0, /* Must be 0, used by framereg */ + HSR_PT_SLAVE_A, + HSR_PT_SLAVE_B, + HSR_PT_INTERLINK, + HSR_PT_MASTER, + HSR_PT_PORTS, /* This must be the last item in the enum */ +}; + /* HSR Tag. * As defined in IEC-62439-3:2010, the HSR tag is really { ethertype = 0x88FB, * path, LSDU_size, sequence Nr }. But we let eth_header() create { h_dest, @@ -32,6 +41,8 @@ struct hsr_tag { #if IS_ENABLED(CONFIG_HSR) extern bool is_hsr_master(struct net_device *dev); extern int hsr_get_version(struct net_device *dev, enum hsr_version *ver); +struct net_device *hsr_get_port_ndev(struct net_device *ndev, + enum hsr_port_type pt); #else static inline bool is_hsr_master(struct net_device *dev) { @@ -42,6 +53,12 @@ static inline int hsr_get_version(struct net_device *dev, { return -EINVAL; } + +static inline struct net_device *hsr_get_port_ndev(struct net_device *ndev, + enum hsr_port_type pt) +{ + return ERR_PTR(-EINVAL); +} #endif /* CONFIG_HSR */ #endif /*_LINUX_IF_HSR_H_*/ diff --git a/include/linux/if_ltalk.h b/include/linux/if_ltalk.h deleted file mode 100644 index 4cc1c0b77870..000000000000 --- a/include/linux/if_ltalk.h +++ /dev/null @@ -1,8 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __LINUX_LTALK_H -#define __LINUX_LTALK_H - -#include <uapi/linux/if_ltalk.h> - -extern struct net_device *alloc_ltalkdev(int sizeof_priv); -#endif diff --git a/include/linux/if_rmnet.h b/include/linux/if_rmnet.h index 839d1e48b85e..c44bf6e80ecb 100644 --- a/include/linux/if_rmnet.h +++ b/include/linux/if_rmnet.h @@ -42,7 +42,7 @@ struct rmnet_map_ul_csum_header { /* csum_info field: * OFFSET: where (offset in bytes) to insert computed checksum - * UDP: 1 = UDP checksum (zero checkum means no checksum) + * UDP: 1 = UDP checksum (zero checksum means no checksum) * ENABLED: 1 = checksum computation requested */ #define MAP_CSUM_UL_OFFSET_MASK GENMASK(13, 0) diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index c1645c86eed9..38456b42cdb5 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -176,6 +176,7 @@ struct netpoll; * @real_dev_addr: address of underlying netdevice * @dent: proc dir entry * @vlan_pcpu_stats: ptr to percpu rx stats + * @netpoll: netpoll instance "propagated" down to @real_dev */ struct vlan_dev_priv { unsigned int nr_ingress_mappings; @@ -310,7 +311,7 @@ static inline bool vlan_uses_dev(const struct net_device *dev) * eth_type_vlan - check for valid vlan ether type. * @ethertype: ether type to check * - * Returns true if the ether type is a vlan ether type. + * Returns: true if the ether type is a vlan ether type. */ static inline bool eth_type_vlan(__be16 ethertype) { @@ -341,9 +342,9 @@ static inline bool vlan_hw_offload_capable(netdev_features_t features, * @mac_len: MAC header length including outer vlan headers * * Inserts the VLAN tag into @skb as part of the payload at offset mac_len - * Returns error if skb_cow_head fails. - * * Does not change skb->protocol so this function can be used during receive. + * + * Returns: error if skb_cow_head fails. */ static inline int __vlan_insert_inner_tag(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci, @@ -390,9 +391,9 @@ static inline int __vlan_insert_inner_tag(struct sk_buff *skb, * @vlan_tci: VLAN TCI to insert * * Inserts the VLAN tag into @skb as part of the payload - * Returns error if skb_cow_head fails. - * * Does not change skb->protocol so this function can be used during receive. + * + * Returns: error if skb_cow_head fails. */ static inline int __vlan_insert_tag(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) @@ -414,6 +415,8 @@ static inline int __vlan_insert_tag(struct sk_buff *skb, * doesn't have to worry about freeing the original skb. * * Does not change skb->protocol so this function can be used during receive. + * + * Return: modified @skb on success, NULL on error (@skb is freed). */ static inline struct sk_buff *vlan_insert_inner_tag(struct sk_buff *skb, __be16 vlan_proto, @@ -443,6 +446,8 @@ static inline struct sk_buff *vlan_insert_inner_tag(struct sk_buff *skb, * doesn't have to worry about freeing the original skb. * * Does not change skb->protocol so this function can be used during receive. + * + * Return: modified @skb on success, NULL on error (@skb is freed). */ static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) @@ -461,6 +466,8 @@ static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb, * * Following the skb_unshare() example, in case of error, the calling function * doesn't have to worry about freeing the original skb. + * + * Return: modified @skb on success, NULL on error (@skb is freed). */ static inline struct sk_buff *vlan_insert_tag_set_proto(struct sk_buff *skb, __be16 vlan_proto, @@ -533,7 +540,7 @@ static inline void __vlan_hwaccel_put_tag(struct sk_buff *skb, * @skb: skbuff to query * @vlan_tci: buffer to store value * - * Returns error if the skb is not of VLAN type + * Returns: error if the skb is not of VLAN type */ static inline int __vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci) { @@ -551,7 +558,7 @@ static inline int __vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci) * @skb: skbuff to query * @vlan_tci: buffer to store value * - * Returns error if @skb->vlan_tci is not set correctly + * Returns: error if @skb->vlan_tci is not set correctly */ static inline int __vlan_hwaccel_get_tag(const struct sk_buff *skb, u16 *vlan_tci) @@ -570,7 +577,7 @@ static inline int __vlan_hwaccel_get_tag(const struct sk_buff *skb, * @skb: skbuff to query * @vlan_tci: buffer to store value * - * Returns error if the skb is not VLAN tagged + * Returns: error if the skb is not VLAN tagged */ static inline int vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci) { @@ -582,16 +589,19 @@ static inline int vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci) } /** - * vlan_get_protocol - get protocol EtherType. + * __vlan_get_protocol_offset() - get protocol EtherType. * @skb: skbuff to query * @type: first vlan protocol + * @mac_offset: MAC offset * @depth: buffer to store length of eth and vlan tags in bytes * - * Returns the EtherType of the packet, regardless of whether it is + * Returns: the EtherType of the packet, regardless of whether it is * vlan encapsulated (normal or hardware accelerated) or not. */ -static inline __be16 __vlan_get_protocol(const struct sk_buff *skb, __be16 type, - int *depth) +static inline __be16 __vlan_get_protocol_offset(const struct sk_buff *skb, + __be16 type, + int mac_offset, + int *depth) { unsigned int vlan_depth = skb->mac_len, parse_depth = VLAN_MAX_DEPTH; @@ -610,7 +620,8 @@ static inline __be16 __vlan_get_protocol(const struct sk_buff *skb, __be16 type, do { struct vlan_hdr vhdr, *vh; - vh = skb_header_pointer(skb, vlan_depth, sizeof(vhdr), &vhdr); + vh = skb_header_pointer(skb, mac_offset + vlan_depth, + sizeof(vhdr), &vhdr); if (unlikely(!vh || !--parse_depth)) return 0; @@ -625,11 +636,17 @@ static inline __be16 __vlan_get_protocol(const struct sk_buff *skb, __be16 type, return type; } +static inline __be16 __vlan_get_protocol(const struct sk_buff *skb, __be16 type, + int *depth) +{ + return __vlan_get_protocol_offset(skb, type, 0, depth); +} + /** * vlan_get_protocol - get protocol EtherType. * @skb: skbuff to query * - * Returns the EtherType of the packet, regardless of whether it is + * Returns: the EtherType of the packet, regardless of whether it is * vlan encapsulated (normal or hardware accelerated) or not. */ static inline __be16 vlan_get_protocol(const struct sk_buff *skb) @@ -710,7 +727,7 @@ static inline void vlan_set_encap_proto(struct sk_buff *skb, * Expects the skb to contain a VLAN tag in the payload, and to have skb->data * pointing at the MAC header. * - * Returns a new pointer to skb->data, or NULL on failure to pull. + * Returns: a new pointer to skb->data, or NULL on failure to pull. */ static inline void *vlan_remove_tag(struct sk_buff *skb, u16 *vlan_tci) { @@ -727,7 +744,7 @@ static inline void *vlan_remove_tag(struct sk_buff *skb, u16 *vlan_tci) * skb_vlan_tagged - check if skb is vlan tagged. * @skb: skbuff to query * - * Returns true if the skb is tagged, regardless of whether it is hardware + * Returns: true if the skb is tagged, regardless of whether it is hardware * accelerated or not. */ static inline bool skb_vlan_tagged(const struct sk_buff *skb) @@ -743,7 +760,7 @@ static inline bool skb_vlan_tagged(const struct sk_buff *skb) * skb_vlan_tagged_multi - check if skb is vlan tagged with multiple headers. * @skb: skbuff to query * - * Returns true if the skb is tagged with multiple vlan headers, regardless + * Returns: true if the skb is tagged with multiple vlan headers, regardless * of whether it is hardware accelerated or not. */ static inline bool skb_vlan_tagged_multi(struct sk_buff *skb) @@ -774,7 +791,7 @@ static inline bool skb_vlan_tagged_multi(struct sk_buff *skb) * @skb: skbuff to query * @features: features to be checked * - * Returns features without unsafe ones if the skb has multiple tags. + * Returns: features without unsafe ones if the skb has multiple tags. */ static inline netdev_features_t vlan_features_check(struct sk_buff *skb, netdev_features_t features) @@ -798,9 +815,11 @@ static inline netdev_features_t vlan_features_check(struct sk_buff *skb, * @h1: Pointer to vlan header * @h2: Pointer to vlan header * - * Compare two vlan headers, returns 0 if equal. + * Compare two vlan headers. * * Please note that alignment of h1 & h2 are only guaranteed to be 16 bits. + * + * Return: 0 if equal, arbitrary non-zero value if not equal. */ static inline unsigned long compare_vlan_header(const struct vlan_hdr *h1, const struct vlan_hdr *h2) diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 5171231f70a8..073b30a9b850 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -87,6 +87,8 @@ struct ip_mc_list { char loaded; unsigned char gsquery; /* check source marks? */ unsigned char crcount; + unsigned long mca_cstamp; + unsigned long mca_tstamp; struct rcu_head rcu; }; diff --git a/include/linux/iio/adc/ad_sigma_delta.h b/include/linux/iio/adc/ad_sigma_delta.h index 719cf9cc6e1a..417073c52380 100644 --- a/include/linux/iio/adc/ad_sigma_delta.h +++ b/include/linux/iio/adc/ad_sigma_delta.h @@ -29,6 +29,7 @@ struct ad_sd_calib_data { struct ad_sigma_delta; struct device; +struct gpio_desc; struct iio_dev; /** @@ -37,6 +38,10 @@ struct iio_dev; * @append_status: Will be called to enable status append at the end of the sample, may be NULL. * @set_mode: Will be called to select the current mode, may be NULL. * @disable_all: Will be called to disable all channels, may be NULL. + * @disable_one: Will be called to disable a single channel after + * ad_sigma_delta_single_conversion(), may be NULL. + * Usage of this callback expects iio_chan_spec.address to contain + * the value required for the driver to identify the channel. * @postprocess_sample: Is called for each sampled data word, can be used to * modify or drop the sample data, it, may be NULL. * @has_registers: true if the device has writable and readable registers, false @@ -48,12 +53,15 @@ struct iio_dev; * be used. * @irq_flags: flags for the interrupt used by the triggered buffer * @num_slots: Number of sequencer slots + * @irq_line: IRQ for reading conversions. If 0, spi->irq will be used + * @num_resetclks: Number of SPI clk cycles with MOSI=1 to reset the chip. */ struct ad_sigma_delta_info { int (*set_channel)(struct ad_sigma_delta *, unsigned int channel); int (*append_status)(struct ad_sigma_delta *, bool append); int (*set_mode)(struct ad_sigma_delta *, enum ad_sigma_delta_mode mode); int (*disable_all)(struct ad_sigma_delta *); + int (*disable_one)(struct ad_sigma_delta *, unsigned int chan); int (*postprocess_sample)(struct ad_sigma_delta *, unsigned int raw_sample); bool has_registers; unsigned int addr_shift; @@ -62,6 +70,8 @@ struct ad_sigma_delta_info { unsigned int data_reg; unsigned long irq_flags; unsigned int num_slots; + int irq_line; + unsigned int num_resetclks; }; /** @@ -78,6 +88,7 @@ struct ad_sigma_delta { /* private: */ struct completion completion; + spinlock_t irq_lock; /* protects .irq_dis and irq en/disable state */ bool irq_dis; bool bus_locked; @@ -89,6 +100,8 @@ struct ad_sigma_delta { unsigned int active_slots; unsigned int current_slot; unsigned int num_slots; + struct gpio_desc *rdy_gpiod; + int irq_line; bool status_appended; /* map slots to channels in order to know what to expect from devices */ unsigned int *slots; @@ -137,6 +150,15 @@ static inline int ad_sigma_delta_disable_all(struct ad_sigma_delta *sd) return 0; } +static inline int ad_sigma_delta_disable_one(struct ad_sigma_delta *sd, + unsigned int chan) +{ + if (sd->info->disable_one) + return sd->info->disable_one(sd, chan); + + return 0; +} + static inline int ad_sigma_delta_set_mode(struct ad_sigma_delta *sd, unsigned int mode) { @@ -161,8 +183,7 @@ int ad_sd_write_reg(struct ad_sigma_delta *sigma_delta, unsigned int reg, int ad_sd_read_reg(struct ad_sigma_delta *sigma_delta, unsigned int reg, unsigned int size, unsigned int *val); -int ad_sd_reset(struct ad_sigma_delta *sigma_delta, - unsigned int reset_length); +int ad_sd_reset(struct ad_sigma_delta *sigma_delta); int ad_sigma_delta_single_conversion(struct iio_dev *indio_dev, const struct iio_chan_spec *chan, int *val); diff --git a/include/linux/iio/backend.h b/include/linux/iio/backend.h index a6d79381866e..10be00f3b120 100644 --- a/include/linux/iio/backend.h +++ b/include/linux/iio/backend.h @@ -3,7 +3,9 @@ #define _IIO_BACKEND_H_ #include <linux/types.h> +#include <linux/iio/iio.h> +struct iio_chan_spec; struct fwnode_handle; struct iio_backend; struct device; @@ -12,15 +14,39 @@ struct iio_dev; enum iio_backend_data_type { IIO_BACKEND_TWOS_COMPLEMENT, IIO_BACKEND_OFFSET_BINARY, + IIO_BACKEND_DATA_UNSIGNED, IIO_BACKEND_DATA_TYPE_MAX }; +enum iio_backend_data_source { + IIO_BACKEND_INTERNAL_CONTINUOUS_WAVE, + IIO_BACKEND_EXTERNAL, + IIO_BACKEND_INTERNAL_RAMP_16BIT, + IIO_BACKEND_DATA_SOURCE_MAX +}; + +#define iio_backend_debugfs_ptr(ptr) PTR_IF(IS_ENABLED(CONFIG_DEBUG_FS), ptr) + +/** + * IIO_BACKEND_EX_INFO - Helper for an IIO extended channel attribute + * @_name: Attribute name + * @_shared: Whether the attribute is shared between all channels + * @_what: Data private to the driver + */ +#define IIO_BACKEND_EX_INFO(_name, _shared, _what) { \ + .name = (_name), \ + .shared = (_shared), \ + .read = iio_backend_ext_info_get, \ + .write = iio_backend_ext_info_set, \ + .private = (_what), \ +} + /** * struct iio_backend_data_fmt - Backend data format - * @type: Data type. - * @sign_extend: Bool to tell if the data is sign extended. - * @enable: Enable/Disable the data format module. If disabled, - * not formatting will happen. + * @type: Data type. + * @sign_extend: Bool to tell if the data is sign extended. + * @enable: Enable/Disable the data format module. If disabled, + * not formatting will happen. */ struct iio_backend_data_fmt { enum iio_backend_data_type type; @@ -28,15 +54,48 @@ struct iio_backend_data_fmt { bool enable; }; +/* vendor specific from 32 */ +enum iio_backend_test_pattern { + IIO_BACKEND_NO_TEST_PATTERN, + /* modified prbs9 */ + IIO_BACKEND_ADI_PRBS_9A = 32, + /* modified prbs23 */ + IIO_BACKEND_ADI_PRBS_23A, + IIO_BACKEND_TEST_PATTERN_MAX +}; + +enum iio_backend_sample_trigger { + IIO_BACKEND_SAMPLE_TRIGGER_EDGE_FALLING, + IIO_BACKEND_SAMPLE_TRIGGER_EDGE_RISING, + IIO_BACKEND_SAMPLE_TRIGGER_MAX +}; + /** * struct iio_backend_ops - operations structure for an iio_backend - * @enable: Enable backend. - * @disable: Disable backend. - * @chan_enable: Enable one channel. - * @chan_disable: Disable one channel. - * @data_format_set: Configure the data format for a specific channel. - * @request_buffer: Request an IIO buffer. - * @free_buffer: Free an IIO buffer. + * @enable: Enable backend. + * @disable: Disable backend. + * @chan_enable: Enable one channel. + * @chan_disable: Disable one channel. + * @data_format_set: Configure the data format for a specific channel. + * @data_source_set: Configure the data source for a specific channel. + * @set_sample_rate: Configure the sampling rate for a specific channel. + * @test_pattern_set: Configure a test pattern. + * @chan_status: Get the channel status. + * @iodelay_set: Set digital I/O delay. + * @data_sample_trigger: Control when to sample data. + * @request_buffer: Request an IIO buffer. + * @free_buffer: Free an IIO buffer. + * @extend_chan_spec: Extend an IIO channel. + * @ext_info_set: Extended info setter. + * @ext_info_get: Extended info getter. + * @read_raw: Read a channel attribute from a backend device + * @debugfs_print_chan_status: Print channel status into a buffer. + * @debugfs_reg_access: Read or write register value of backend. + * @ddr_enable: Enable interface DDR (Double Data Rate) mode. + * @ddr_disable: Disable interface DDR (Double Data Rate) mode. + * @data_stream_enable: Enable data stream. + * @data_stream_disable: Disable data stream. + * @data_transfer_addr: Set data address. **/ struct iio_backend_ops { int (*enable)(struct iio_backend *back); @@ -45,28 +104,123 @@ struct iio_backend_ops { int (*chan_disable)(struct iio_backend *back, unsigned int chan); int (*data_format_set)(struct iio_backend *back, unsigned int chan, const struct iio_backend_data_fmt *data); + int (*data_source_set)(struct iio_backend *back, unsigned int chan, + enum iio_backend_data_source data); + int (*set_sample_rate)(struct iio_backend *back, unsigned int chan, + u64 sample_rate_hz); + int (*test_pattern_set)(struct iio_backend *back, + unsigned int chan, + enum iio_backend_test_pattern pattern); + int (*chan_status)(struct iio_backend *back, unsigned int chan, + bool *error); + int (*iodelay_set)(struct iio_backend *back, unsigned int chan, + unsigned int taps); + int (*data_sample_trigger)(struct iio_backend *back, + enum iio_backend_sample_trigger trigger); struct iio_buffer *(*request_buffer)(struct iio_backend *back, struct iio_dev *indio_dev); void (*free_buffer)(struct iio_backend *back, struct iio_buffer *buffer); + int (*extend_chan_spec)(struct iio_backend *back, + struct iio_chan_spec *chan); + int (*ext_info_set)(struct iio_backend *back, uintptr_t private, + const struct iio_chan_spec *chan, + const char *buf, size_t len); + int (*ext_info_get)(struct iio_backend *back, uintptr_t private, + const struct iio_chan_spec *chan, char *buf); + int (*read_raw)(struct iio_backend *back, + struct iio_chan_spec const *chan, int *val, int *val2, + long mask); + int (*debugfs_print_chan_status)(struct iio_backend *back, + unsigned int chan, char *buf, + size_t len); + int (*debugfs_reg_access)(struct iio_backend *back, unsigned int reg, + unsigned int writeval, unsigned int *readval); + int (*ddr_enable)(struct iio_backend *back); + int (*ddr_disable)(struct iio_backend *back); + int (*data_stream_enable)(struct iio_backend *back); + int (*data_stream_disable)(struct iio_backend *back); + int (*data_transfer_addr)(struct iio_backend *back, u32 address); +}; + +/** + * struct iio_backend_info - info structure for an iio_backend + * @name: Backend name. + * @ops: Backend operations. + */ +struct iio_backend_info { + const char *name; + const struct iio_backend_ops *ops; }; int iio_backend_chan_enable(struct iio_backend *back, unsigned int chan); int iio_backend_chan_disable(struct iio_backend *back, unsigned int chan); int devm_iio_backend_enable(struct device *dev, struct iio_backend *back); +int iio_backend_enable(struct iio_backend *back); +void iio_backend_disable(struct iio_backend *back); int iio_backend_data_format_set(struct iio_backend *back, unsigned int chan, const struct iio_backend_data_fmt *data); +int iio_backend_data_source_set(struct iio_backend *back, unsigned int chan, + enum iio_backend_data_source data); +int iio_backend_set_sampling_freq(struct iio_backend *back, unsigned int chan, + u64 sample_rate_hz); +int iio_backend_test_pattern_set(struct iio_backend *back, + unsigned int chan, + enum iio_backend_test_pattern pattern); +int iio_backend_chan_status(struct iio_backend *back, unsigned int chan, + bool *error); +int iio_backend_iodelay_set(struct iio_backend *back, unsigned int lane, + unsigned int taps); +int iio_backend_data_sample_trigger(struct iio_backend *back, + enum iio_backend_sample_trigger trigger); int devm_iio_backend_request_buffer(struct device *dev, struct iio_backend *back, struct iio_dev *indio_dev); - +int iio_backend_ddr_enable(struct iio_backend *back); +int iio_backend_ddr_disable(struct iio_backend *back); +int iio_backend_data_stream_enable(struct iio_backend *back); +int iio_backend_data_stream_disable(struct iio_backend *back); +int iio_backend_data_transfer_addr(struct iio_backend *back, u32 address); +ssize_t iio_backend_ext_info_set(struct iio_dev *indio_dev, uintptr_t private, + const struct iio_chan_spec *chan, + const char *buf, size_t len); +ssize_t iio_backend_ext_info_get(struct iio_dev *indio_dev, uintptr_t private, + const struct iio_chan_spec *chan, char *buf); +int iio_backend_read_raw(struct iio_backend *back, + struct iio_chan_spec const *chan, int *val, int *val2, + long mask); +int iio_backend_extend_chan_spec(struct iio_backend *back, + struct iio_chan_spec *chan); void *iio_backend_get_priv(const struct iio_backend *conv); struct iio_backend *devm_iio_backend_get(struct device *dev, const char *name); +struct iio_backend *devm_iio_backend_fwnode_get(struct device *dev, + const char *name, + struct fwnode_handle *fwnode); struct iio_backend * __devm_iio_backend_get_from_fwnode_lookup(struct device *dev, struct fwnode_handle *fwnode); int devm_iio_backend_register(struct device *dev, - const struct iio_backend_ops *ops, void *priv); + const struct iio_backend_info *info, void *priv); + +static inline int iio_backend_read_scale(struct iio_backend *back, + struct iio_chan_spec const *chan, + int *val, int *val2) +{ + return iio_backend_read_raw(back, chan, val, val2, IIO_CHAN_INFO_SCALE); +} + +static inline int iio_backend_read_offset(struct iio_backend *back, + struct iio_chan_spec const *chan, + int *val, int *val2) +{ + return iio_backend_read_raw(back, chan, val, val2, + IIO_CHAN_INFO_OFFSET); +} +ssize_t iio_backend_debugfs_print_chan_status(struct iio_backend *back, + unsigned int chan, char *buf, + size_t len); +void iio_backend_debugfs_add(struct iio_backend *back, + struct iio_dev *indio_dev); #endif diff --git a/include/linux/iio/buffer-dma.h b/include/linux/iio/buffer-dma.h index 18d3702fa95d..5eb66a399002 100644 --- a/include/linux/iio/buffer-dma.h +++ b/include/linux/iio/buffer-dma.h @@ -7,6 +7,7 @@ #ifndef __INDUSTRIALIO_DMA_BUFFER_H__ #define __INDUSTRIALIO_DMA_BUFFER_H__ +#include <linux/atomic.h> #include <linux/list.h> #include <linux/kref.h> #include <linux/spinlock.h> @@ -16,6 +17,9 @@ struct iio_dma_buffer_queue; struct iio_dma_buffer_ops; struct device; +struct dma_buf_attachment; +struct dma_fence; +struct sg_table; /** * enum iio_block_state - State of a struct iio_dma_buffer_block @@ -41,6 +45,10 @@ enum iio_block_state { * @queue: Parent DMA buffer queue * @kref: kref used to manage the lifetime of block * @state: Current state of the block + * @cyclic: True if this is a cyclic buffer + * @fileio: True if this buffer is used for fileio mode + * @sg_table: DMA table for the transfer when transferring a DMABUF + * @fence: DMA fence to be signaled when a DMABUF transfer is complete */ struct iio_dma_buffer_block { /* May only be accessed by the owner of the block */ @@ -63,6 +71,12 @@ struct iio_dma_buffer_block { * queue->list_lock if the block is not owned by the core. */ enum iio_block_state state; + + bool cyclic; + bool fileio; + + struct sg_table *sg_table; + struct dma_fence *fence; }; /** @@ -72,6 +86,7 @@ struct iio_dma_buffer_block { * @pos: Read offset in the active block * @block_size: Size of each block * @next_dequeue: index of next block that will be dequeued + * @enabled: Whether the buffer is operating in fileio mode */ struct iio_dma_buffer_queue_fileio { struct iio_dma_buffer_block *blocks[2]; @@ -80,6 +95,7 @@ struct iio_dma_buffer_queue_fileio { size_t block_size; unsigned int next_dequeue; + bool enabled; }; /** @@ -95,6 +111,7 @@ struct iio_dma_buffer_queue_fileio { * the DMA controller * @incoming: List of buffers on the incoming queue * @active: Whether the buffer is currently active + * @num_dmabufs: Total number of DMABUFs attached to this queue * @fileio: FileIO state */ struct iio_dma_buffer_queue { @@ -107,6 +124,7 @@ struct iio_dma_buffer_queue { struct list_head incoming; bool active; + atomic_t num_dmabufs; struct iio_dma_buffer_queue_fileio fileio; }; @@ -132,7 +150,9 @@ int iio_dma_buffer_disable(struct iio_buffer *buffer, struct iio_dev *indio_dev); int iio_dma_buffer_read(struct iio_buffer *buffer, size_t n, char __user *user_buffer); -size_t iio_dma_buffer_data_available(struct iio_buffer *buffer); +int iio_dma_buffer_write(struct iio_buffer *buffer, size_t n, + const char __user *user_buffer); +size_t iio_dma_buffer_usage(struct iio_buffer *buffer); int iio_dma_buffer_set_bytes_per_datum(struct iio_buffer *buffer, size_t bpd); int iio_dma_buffer_set_length(struct iio_buffer *buffer, unsigned int length); int iio_dma_buffer_request_update(struct iio_buffer *buffer); @@ -142,4 +162,17 @@ int iio_dma_buffer_init(struct iio_dma_buffer_queue *queue, void iio_dma_buffer_exit(struct iio_dma_buffer_queue *queue); void iio_dma_buffer_release(struct iio_dma_buffer_queue *queue); +struct iio_dma_buffer_block * +iio_dma_buffer_attach_dmabuf(struct iio_buffer *buffer, + struct dma_buf_attachment *attach); +void iio_dma_buffer_detach_dmabuf(struct iio_buffer *buffer, + struct iio_dma_buffer_block *block); +int iio_dma_buffer_enqueue_dmabuf(struct iio_buffer *buffer, + struct iio_dma_buffer_block *block, + struct dma_fence *fence, + struct sg_table *sgt, + size_t size, bool cyclic); +void iio_dma_buffer_lock_queue(struct iio_buffer *buffer); +void iio_dma_buffer_unlock_queue(struct iio_buffer *buffer); + #endif diff --git a/include/linux/iio/buffer-dmaengine.h b/include/linux/iio/buffer-dmaengine.h index cbb8ba957fad..81d9a19aeb91 100644 --- a/include/linux/iio/buffer-dmaengine.h +++ b/include/linux/iio/buffer-dmaengine.h @@ -7,14 +7,28 @@ #ifndef __IIO_DMAENGINE_H__ #define __IIO_DMAENGINE_H__ +#include <linux/iio/buffer.h> + struct iio_dev; struct device; -struct iio_buffer *iio_dmaengine_buffer_alloc(struct device *dev, - const char *channel); void iio_dmaengine_buffer_free(struct iio_buffer *buffer); -int devm_iio_dmaengine_buffer_setup(struct device *dev, - struct iio_dev *indio_dev, - const char *channel); +struct iio_buffer *iio_dmaengine_buffer_setup_ext(struct device *dev, + struct iio_dev *indio_dev, + const char *channel, + enum iio_buffer_direction dir); + +#define iio_dmaengine_buffer_setup(dev, indio_dev, channel) \ + iio_dmaengine_buffer_setup_ext(dev, indio_dev, channel, \ + IIO_BUFFER_DIRECTION_IN) + +int devm_iio_dmaengine_buffer_setup_ext(struct device *dev, + struct iio_dev *indio_dev, + const char *channel, + enum iio_buffer_direction dir); + +#define devm_iio_dmaengine_buffer_setup(dev, indio_dev, channel) \ + devm_iio_dmaengine_buffer_setup_ext(dev, indio_dev, channel, \ + IIO_BUFFER_DIRECTION_IN) #endif diff --git a/include/linux/iio/buffer.h b/include/linux/iio/buffer.h index 418b1307d3f2..3b8d618bb3df 100644 --- a/include/linux/iio/buffer.h +++ b/include/linux/iio/buffer.h @@ -37,7 +37,7 @@ int iio_pop_from_buffer(struct iio_buffer *buffer, void *data); static inline int iio_push_to_buffers_with_timestamp(struct iio_dev *indio_dev, void *data, int64_t timestamp) { - if (indio_dev->scan_timestamp) { + if (ACCESS_PRIVATE(indio_dev, scan_timestamp)) { size_t ts_offset = indio_dev->scan_bytes / sizeof(int64_t) - 1; ((int64_t *)data)[ts_offset] = timestamp; } diff --git a/include/linux/iio/buffer_impl.h b/include/linux/iio/buffer_impl.h index 89c3fd7c29ca..e72552e026f3 100644 --- a/include/linux/iio/buffer_impl.h +++ b/include/linux/iio/buffer_impl.h @@ -9,8 +9,12 @@ #include <uapi/linux/iio/buffer.h> #include <linux/iio/buffer.h> +struct dma_buf_attachment; +struct dma_fence; struct iio_dev; +struct iio_dma_buffer_block; struct iio_buffer; +struct sg_table; /** * INDIO_BUFFER_FLAG_FIXED_WATERMARK - Watermark level of the buffer can not be @@ -39,6 +43,16 @@ struct iio_buffer; * device stops sampling. Calles are balanced with @enable. * @release: called when the last reference to the buffer is dropped, * should free all resources allocated by the buffer. + * @attach_dmabuf: called from userspace via ioctl to attach one external + * DMABUF. + * @detach_dmabuf: called from userspace via ioctl to detach one previously + * attached DMABUF. + * @enqueue_dmabuf: called from userspace via ioctl to queue this DMABUF + * object to this buffer. Requires a valid DMABUF fd, that + * was previouly attached to this buffer. + * @lock_queue: called when the core needs to lock the buffer queue; + * it is used when enqueueing DMABUF objects. + * @unlock_queue: used to unlock a previously locked buffer queue * @modes: Supported operating modes by this buffer type * @flags: A bitmask combination of INDIO_BUFFER_FLAG_* * @@ -68,6 +82,17 @@ struct iio_buffer_access_funcs { void (*release)(struct iio_buffer *buffer); + struct iio_dma_buffer_block * (*attach_dmabuf)(struct iio_buffer *buffer, + struct dma_buf_attachment *attach); + void (*detach_dmabuf)(struct iio_buffer *buffer, + struct iio_dma_buffer_block *block); + int (*enqueue_dmabuf)(struct iio_buffer *buffer, + struct iio_dma_buffer_block *block, + struct dma_fence *fence, struct sg_table *sgt, + size_t size, bool cyclic); + void (*lock_queue)(struct iio_buffer *buffer); + void (*unlock_queue)(struct iio_buffer *buffer); + unsigned int modes; unsigned int flags; }; @@ -136,6 +161,12 @@ struct iio_buffer { /* @ref: Reference count of the buffer. */ struct kref ref; + + /* @dmabufs: List of DMABUF attachments */ + struct list_head dmabufs; /* P: dmabufs_mutex */ + + /* @dmabufs_mutex: Protects dmabufs */ + struct mutex dmabufs_mutex; }; /** @@ -159,6 +190,8 @@ void iio_buffer_init(struct iio_buffer *buffer); struct iio_buffer *iio_buffer_get(struct iio_buffer *buffer); void iio_buffer_put(struct iio_buffer *buffer); +void iio_buffer_signal_dmabuf_done(struct dma_fence *fence, int ret); + #else /* CONFIG_IIO_BUFFER */ static inline void iio_buffer_get(struct iio_buffer *buffer) {} diff --git a/include/linux/iio/common/inv_sensors_timestamp.h b/include/linux/iio/common/inv_sensors_timestamp.h index a47d304d1ba7..8d506f1e9df2 100644 --- a/include/linux/iio/common/inv_sensors_timestamp.h +++ b/include/linux/iio/common/inv_sensors_timestamp.h @@ -71,8 +71,7 @@ int inv_sensors_timestamp_update_odr(struct inv_sensors_timestamp *ts, uint32_t period, bool fifo); void inv_sensors_timestamp_interrupt(struct inv_sensors_timestamp *ts, - uint32_t fifo_period, size_t fifo_nb, - size_t sensor_nb, int64_t timestamp); + size_t sample_nb, int64_t timestamp); static inline int64_t inv_sensors_timestamp_pop(struct inv_sensors_timestamp *ts) { diff --git a/include/linux/iio/consumer.h b/include/linux/iio/consumer.h index e9910b41d48e..6a4479616479 100644 --- a/include/linux/iio/consumer.h +++ b/include/linux/iio/consumer.h @@ -418,7 +418,7 @@ unsigned int iio_get_channel_ext_info_count(struct iio_channel *chan); * @chan: The channel being queried. * @attr: The ext_info attribute to read. * @buf: Where to store the attribute value. Assumed to hold - * at least PAGE_SIZE bytes. + * at least PAGE_SIZE bytes and to be aligned at PAGE_SIZE. * * Returns the number of bytes written to buf (perhaps w/o zero termination; * it need not even be a string), or an error code. @@ -441,4 +441,14 @@ ssize_t iio_read_channel_ext_info(struct iio_channel *chan, ssize_t iio_write_channel_ext_info(struct iio_channel *chan, const char *attr, const char *buf, size_t len); +/** + * iio_read_channel_label() - read label for a given channel + * @chan: The channel being queried. + * @buf: Where to store the attribute value. Assumed to hold + * at least PAGE_SIZE bytes and to be aligned at PAGE_SIZE. + * + * Returns the number of bytes written to buf, or an error code. + */ +ssize_t iio_read_channel_label(struct iio_channel *chan, char *buf); + #endif diff --git a/include/linux/iio/driver.h b/include/linux/iio/driver.h index 7a157ed218f6..7f8b55551ed0 100644 --- a/include/linux/iio/driver.h +++ b/include/linux/iio/driver.h @@ -18,7 +18,7 @@ struct iio_map; * @map: array of mappings specifying association of channel with client */ int iio_map_array_register(struct iio_dev *indio_dev, - struct iio_map *map); + const struct iio_map *map); /** * iio_map_array_unregister() - tell the core to remove consumer mappings for @@ -38,6 +38,7 @@ int iio_map_array_unregister(struct iio_dev *indio_dev); * handle de-registration of the IIO map object when the device's refcount goes to * zero. */ -int devm_iio_map_array_register(struct device *dev, struct iio_dev *indio_dev, struct iio_map *maps); +int devm_iio_map_array_register(struct device *dev, struct iio_dev *indio_dev, + const struct iio_map *maps); #endif diff --git a/include/linux/iio/events.h b/include/linux/iio/events.h index a4558c45a548..72062a0c7c87 100644 --- a/include/linux/iio/events.h +++ b/include/linux/iio/events.h @@ -10,7 +10,7 @@ #include <uapi/linux/iio/events.h> /** - * IIO_EVENT_CODE() - create event identifier + * _IIO_EVENT_CODE() - create event identifier * @chan_type: Type of the channel. Should be one of enum iio_chan_type. * @diff: Whether the event is for an differential channel or not. * @modifier: Modifier for the channel. Should be one of enum iio_modifier. @@ -19,10 +19,13 @@ * @chan: Channel number for non-differential channels. * @chan1: First channel number for differential channels. * @chan2: Second channel number for differential channels. + * + * Drivers should use the specialized macros below instead of using this one + * directly. */ -#define IIO_EVENT_CODE(chan_type, diff, modifier, direction, \ - type, chan, chan1, chan2) \ +#define _IIO_EVENT_CODE(chan_type, diff, modifier, direction, \ + type, chan, chan1, chan2) \ (((u64)type << 56) | ((u64)diff << 55) | \ ((u64)direction << 48) | ((u64)modifier << 40) | \ ((u64)chan_type << 32) | (((u16)chan2) << 16) | ((u16)chan1) | \ @@ -30,7 +33,8 @@ /** - * IIO_MOD_EVENT_CODE() - create event identifier for modified channels + * IIO_MOD_EVENT_CODE() - create event identifier for modified (non + * differential) channels * @chan_type: Type of the channel. Should be one of enum iio_chan_type. * @number: Channel number. * @modifier: Modifier for the channel. Should be one of enum iio_modifier. @@ -40,10 +44,11 @@ #define IIO_MOD_EVENT_CODE(chan_type, number, modifier, \ type, direction) \ - IIO_EVENT_CODE(chan_type, 0, modifier, direction, type, number, 0, 0) + _IIO_EVENT_CODE(chan_type, 0, modifier, direction, type, number, 0, 0) /** - * IIO_UNMOD_EVENT_CODE() - create event identifier for unmodified channels + * IIO_UNMOD_EVENT_CODE() - create event identifier for unmodified (non + * differential) channels * @chan_type: Type of the channel. Should be one of enum iio_chan_type. * @number: Channel number. * @type: Type of the event. Should be one of enum iio_event_type. @@ -51,6 +56,18 @@ */ #define IIO_UNMOD_EVENT_CODE(chan_type, number, type, direction) \ - IIO_EVENT_CODE(chan_type, 0, 0, direction, type, number, 0, 0) + _IIO_EVENT_CODE(chan_type, 0, 0, direction, type, number, 0, 0) + +/** + * IIO_DIFF_EVENT_CODE() - create event identifier for differential channels + * @chan_type: Type of the channel. Should be one of enum iio_chan_type. + * @chan1: First channel number for differential channels. + * @chan2: Second channel number for differential channels. + * @type: Type of the event. Should be one of enum iio_event_type. + * @direction: Direction of the event. One of enum iio_event_direction. + */ + +#define IIO_DIFF_EVENT_CODE(chan_type, chan1, chan2, type, direction) \ + _IIO_EVENT_CODE(chan_type, 1, 0, direction, type, 0, chan1, chan2) #endif diff --git a/include/linux/iio/iio-gts-helper.h b/include/linux/iio/iio-gts-helper.h index 9cb6c80dea71..e5de7a124bad 100644 --- a/include/linux/iio/iio-gts-helper.h +++ b/include/linux/iio/iio-gts-helper.h @@ -188,6 +188,9 @@ int iio_gts_total_gain_to_scale(struct iio_gts *gts, int total_gain, int iio_gts_find_gain_sel_for_scale_using_time(struct iio_gts *gts, int time_sel, int scale_int, int scale_nano, int *gain_sel); +int iio_gts_find_gain_time_sel_for_scale(struct iio_gts *gts, int scale_int, + int scale_nano, int *gain_sel, + int *time_sel); int iio_gts_get_scale(struct iio_gts *gts, int gain, int time, int *scale_int, int *scale_nano); int iio_gts_find_new_gain_sel_by_old_gain_time(struct iio_gts *gts, @@ -196,6 +199,9 @@ int iio_gts_find_new_gain_sel_by_old_gain_time(struct iio_gts *gts, int iio_gts_find_new_gain_by_old_gain_time(struct iio_gts *gts, int old_gain, int old_time, int new_time, int *new_gain); +int iio_gts_find_new_gain_by_gain_time_min(struct iio_gts *gts, int old_gain, + int old_time, int new_time, + int *new_gain, bool *in_range); int iio_gts_avail_times(struct iio_gts *gts, const int **vals, int *type, int *length); int iio_gts_all_avail_scales(struct iio_gts *gts, const int **vals, int *type, diff --git a/include/linux/iio/iio-opaque.h b/include/linux/iio/iio-opaque.h index 5aec3945555b..4247497f3f8b 100644 --- a/include/linux/iio/iio-opaque.h +++ b/include/linux/iio/iio-opaque.h @@ -28,7 +28,7 @@ * @groupcounter: index of next attribute group * @legacy_scan_el_group: attribute group for legacy scan elements attribute group * @legacy_buffer_group: attribute group for legacy buffer attributes group - * @bounce_buffer: for devices that call iio_push_to_buffers_with_timestamp_unaligned() + * @bounce_buffer: for devices that call iio_push_to_buffers_with_ts_unaligned() * @bounce_buffer_size: size of currently allocate bounce buffer * @scan_index_timestamp: cache of the index to the timestamp * @clock_id: timestamping clock posix identifier @@ -70,7 +70,7 @@ struct iio_dev_opaque { #if defined(CONFIG_DEBUG_FS) struct dentry *debugfs_dentry; - unsigned cached_reg_addr; + unsigned int cached_reg_addr; char read_buf[20]; unsigned int read_buf_len; #endif diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index e370a7bb3300..56161e02f002 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -174,6 +174,27 @@ struct iio_event_spec { }; /** + * struct iio_scan_type - specification for channel data format in buffer + * @sign: 's' or 'u' to specify signed or unsigned + * @realbits: Number of valid bits of data + * @storagebits: Realbits + padding + * @shift: Shift right by this before masking out realbits. + * @repeat: Number of times real/storage bits repeats. When the + * repeat element is more than 1, then the type element in + * sysfs will show a repeat value. Otherwise, the number + * of repetitions is omitted. + * @endianness: little or big endian + */ +struct iio_scan_type { + char sign; + u8 realbits; + u8 storagebits; + u8 shift; + u8 repeat; + enum iio_endian endianness; +}; + +/** * struct iio_chan_spec - specification of a single channel * @type: What type of measurement is the channel making. * @channel: What number do we wish to assign the channel. @@ -183,18 +204,13 @@ struct iio_event_spec { * @address: Driver specific identifier. * @scan_index: Monotonic index to give ordering in scans when read * from a buffer. - * @scan_type: struct describing the scan type - * @scan_type.sign: 's' or 'u' to specify signed or unsigned - * @scan_type.realbits: Number of valid bits of data - * @scan_type.storagebits: Realbits + padding - * @scan_type.shift: Shift right by this before masking out - * realbits. - * @scan_type.repeat: Number of times real/storage bits repeats. - * When the repeat element is more than 1, then - * the type element in sysfs will show a repeat - * value. Otherwise, the number of repetitions - * is omitted. - * @scan_type.endianness: little or big endian + * @scan_type: struct describing the scan type - mutually exclusive + * with ext_scan_type. + * @ext_scan_type: Used in rare cases where there is more than one scan + * format for a channel. When this is used, the flag + * has_ext_scan_type must be set and the driver must + * implement get_current_scan_type in struct iio_info. + * @num_ext_scan_type: Number of elements in ext_scan_type. * @info_mask_separate: What information is to be exported that is specific to * this channel. * @info_mask_separate_available: What availability information is to be @@ -238,6 +254,7 @@ struct iio_event_spec { * attributes but not for event codes. * @output: Channel is output. * @differential: Channel is differential. + * @has_ext_scan_type: True if ext_scan_type is used instead of scan_type. */ struct iio_chan_spec { enum iio_chan_type type; @@ -245,14 +262,13 @@ struct iio_chan_spec { int channel2; unsigned long address; int scan_index; - struct { - char sign; - u8 realbits; - u8 storagebits; - u8 shift; - u8 repeat; - enum iio_endian endianness; - } scan_type; + union { + struct iio_scan_type scan_type; + struct { + const struct iio_scan_type *ext_scan_type; + unsigned int num_ext_scan_type; + }; + }; long info_mask_separate; long info_mask_separate_available; long info_mask_shared_by_type; @@ -266,10 +282,11 @@ struct iio_chan_spec { const struct iio_chan_spec_ext_info *ext_info; const char *extend_name; const char *datasheet_name; - unsigned modified:1; - unsigned indexed:1; - unsigned output:1; - unsigned differential:1; + unsigned int modified:1; + unsigned int indexed:1; + unsigned int output:1; + unsigned int differential:1; + unsigned int has_ext_scan_type:1; }; @@ -432,6 +449,9 @@ struct iio_trigger; /* forward declaration */ * for better event identification. * @validate_trigger: function to validate the trigger when the * current trigger gets changed. + * @get_current_scan_type: must be implemented by drivers that use ext_scan_type + * in the channel spec to return the index of the currently + * active ext_scan type for a channel. * @update_scan_mode: function to configure device and scan buffer when * channels have changed * @debugfs_reg_access: function to read or write register value of device @@ -494,7 +514,7 @@ struct iio_info { const struct iio_chan_spec *chan, enum iio_event_type type, enum iio_event_direction dir, - int state); + bool state); int (*read_event_value)(struct iio_dev *indio_dev, const struct iio_chan_spec *chan, @@ -516,16 +536,18 @@ struct iio_info { int (*validate_trigger)(struct iio_dev *indio_dev, struct iio_trigger *trig); + int (*get_current_scan_type)(const struct iio_dev *indio_dev, + const struct iio_chan_spec *chan); int (*update_scan_mode)(struct iio_dev *indio_dev, const unsigned long *scan_mask); int (*debugfs_reg_access)(struct iio_dev *indio_dev, - unsigned reg, unsigned writeval, - unsigned *readval); + unsigned int reg, unsigned int writeval, + unsigned int *readval); int (*fwnode_xlate)(struct iio_dev *indio_dev, const struct fwnode_reference_args *iiospec); - int (*hwfifo_set_watermark)(struct iio_dev *indio_dev, unsigned val); + int (*hwfifo_set_watermark)(struct iio_dev *indio_dev, unsigned int val); int (*hwfifo_flush_to_buffer)(struct iio_dev *indio_dev, - unsigned count); + unsigned int count); }; /** @@ -587,9 +609,9 @@ struct iio_dev { int scan_bytes; const unsigned long *available_scan_masks; - unsigned masklength; + unsigned int __private masklength; const unsigned long *active_scan_mask; - bool scan_timestamp; + bool __private scan_timestamp; struct iio_trigger *trig; struct iio_poll_func *pollfunc; struct iio_poll_func *pollfunc_event; @@ -602,7 +624,7 @@ struct iio_dev { const struct iio_info *info; const struct iio_buffer_setup_ops *setup_ops; - void *priv; + void *__private priv; }; int iio_device_id(struct iio_dev *indio_dev); @@ -763,7 +785,7 @@ struct iio_dev *iio_device_alloc(struct device *parent, int sizeof_priv); /* The information at the returned address is guaranteed to be cacheline aligned */ static inline void *iio_priv(const struct iio_dev *indio_dev) { - return indio_dev->priv; + return ACCESS_PRIVATE(indio_dev, priv); } void iio_device_free(struct iio_dev *indio_dev); @@ -788,6 +810,98 @@ static inline struct dentry *iio_get_debugfs_dentry(struct iio_dev *indio_dev) } #endif +/** + * iio_device_suspend_triggering() - suspend trigger attached to an iio_dev + * @indio_dev: iio_dev associated with the device that will have triggers suspended + * + * Return 0 if successful, negative otherwise + **/ +int iio_device_suspend_triggering(struct iio_dev *indio_dev); + +/** + * iio_device_resume_triggering() - resume trigger attached to an iio_dev + * that was previously suspended with iio_device_suspend_triggering() + * @indio_dev: iio_dev associated with the device that will have triggers resumed + * + * Return 0 if successful, negative otherwise + **/ +int iio_device_resume_triggering(struct iio_dev *indio_dev); + +#ifdef CONFIG_ACPI +bool iio_read_acpi_mount_matrix(struct device *dev, + struct iio_mount_matrix *orientation, + char *acpi_method); +const char *iio_get_acpi_device_name_and_data(struct device *dev, const void **data); +#else +static inline bool iio_read_acpi_mount_matrix(struct device *dev, + struct iio_mount_matrix *orientation, + char *acpi_method) +{ + return false; +} +static inline const char * +iio_get_acpi_device_name_and_data(struct device *dev, const void **data) +{ + return NULL; +} +#endif +static inline const char *iio_get_acpi_device_name(struct device *dev) +{ + return iio_get_acpi_device_name_and_data(dev, NULL); +} + +/** + * iio_get_current_scan_type - Get the current scan type for a channel + * @indio_dev: the IIO device to get the scan type for + * @chan: the channel to get the scan type for + * + * Most devices only have one scan type per channel and can just access it + * directly without calling this function. Core IIO code and drivers that + * implement ext_scan_type in the channel spec should use this function to + * get the current scan type for a channel. + * + * Returns: the current scan type for the channel or error. + */ +static inline const struct iio_scan_type +*iio_get_current_scan_type(const struct iio_dev *indio_dev, + const struct iio_chan_spec *chan) +{ + int ret; + + if (chan->has_ext_scan_type) { + ret = indio_dev->info->get_current_scan_type(indio_dev, chan); + if (ret < 0) + return ERR_PTR(ret); + + if (ret >= chan->num_ext_scan_type) + return ERR_PTR(-EINVAL); + + return &chan->ext_scan_type[ret]; + } + + return &chan->scan_type; +} + +/** + * iio_get_masklength - Get length of the channels mask + * @indio_dev: the IIO device to get the masklength for + */ +static inline unsigned int iio_get_masklength(const struct iio_dev *indio_dev) +{ + return ACCESS_PRIVATE(indio_dev, masklength); +} + +int iio_active_scan_mask_index(struct iio_dev *indio_dev); + +/** + * iio_for_each_active_channel - Iterated over active channels + * @indio_dev: the IIO device + * @chan: Holds the index of the enabled channel + */ +#define iio_for_each_active_channel(indio_dev, chan) \ + for_each_set_bit((chan), (indio_dev)->active_scan_mask, \ + iio_get_masklength(indio_dev)) + ssize_t iio_format_value(char *buf, unsigned int type, int size, int *vals); int iio_str_to_fixpoint(const char *str, int fract_mult, int *integer, diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h index 8898966bc0f0..4bb98d9731de 100644 --- a/include/linux/iio/imu/adis.h +++ b/include/linux/iio/imu/adis.h @@ -9,6 +9,7 @@ #ifndef __IIO_ADIS_H__ #define __IIO_ADIS_H__ +#include <linux/cleanup.h> #include <linux/spi/spi.h> #include <linux/interrupt.h> #include <linux/iio/iio.h> @@ -21,6 +22,7 @@ #define ADIS_REG_PAGE_ID 0x00 struct adis; +struct iio_dev_attr; /** * struct adis_timeouts - ADIS chip variant timeouts @@ -84,6 +86,7 @@ struct adis_data { bool unmasked_drdy; bool has_paging; + bool has_fifo; unsigned int burst_reg_cmd; unsigned int burst_len; @@ -96,7 +99,6 @@ struct adis_data { * @spi: Reference to SPI device which owns this ADIS IIO device * @trig: IIO trigger object data * @data: ADIS chip variant specific data - * @burst: ADIS burst transfer information * @burst_extra_len: Burst extra length. Should only be used by devices that can * dynamically change their burst mode length. * @state_lock: Lock used by the device to protect state @@ -148,13 +150,8 @@ int __adis_reset(struct adis *adis); */ static inline int adis_reset(struct adis *adis) { - int ret; - - mutex_lock(&adis->state_lock); - ret = __adis_reset(adis); - mutex_unlock(&adis->state_lock); - - return ret; + guard(mutex)(&adis->state_lock); + return __adis_reset(adis); } int __adis_write_reg(struct adis *adis, unsigned int reg, @@ -246,13 +243,8 @@ static inline int __adis_read_reg_32(struct adis *adis, unsigned int reg, static inline int adis_write_reg(struct adis *adis, unsigned int reg, unsigned int val, unsigned int size) { - int ret; - - mutex_lock(&adis->state_lock); - ret = __adis_write_reg(adis, reg, val, size); - mutex_unlock(&adis->state_lock); - - return ret; + guard(mutex)(&adis->state_lock); + return __adis_write_reg(adis, reg, val, size); } /** @@ -265,13 +257,8 @@ static inline int adis_write_reg(struct adis *adis, unsigned int reg, static int adis_read_reg(struct adis *adis, unsigned int reg, unsigned int *val, unsigned int size) { - int ret; - - mutex_lock(&adis->state_lock); - ret = __adis_read_reg(adis, reg, val, size); - mutex_unlock(&adis->state_lock); - - return ret; + guard(mutex)(&adis->state_lock); + return __adis_read_reg(adis, reg, val, size); } /** @@ -363,12 +350,8 @@ int __adis_update_bits_base(struct adis *adis, unsigned int reg, const u32 mask, static inline int adis_update_bits_base(struct adis *adis, unsigned int reg, const u32 mask, const u32 val, u8 size) { - int ret; - - mutex_lock(&adis->state_lock); - ret = __adis_update_bits_base(adis, reg, mask, val, size); - mutex_unlock(&adis->state_lock); - return ret; + guard(mutex)(&adis->state_lock); + return __adis_update_bits_base(adis, reg, mask, val, size); } /** @@ -409,35 +392,19 @@ int __adis_enable_irq(struct adis *adis, bool enable); static inline int adis_enable_irq(struct adis *adis, bool enable) { - int ret; - - mutex_lock(&adis->state_lock); - ret = __adis_enable_irq(adis, enable); - mutex_unlock(&adis->state_lock); - - return ret; + guard(mutex)(&adis->state_lock); + return __adis_enable_irq(adis, enable); } static inline int adis_check_status(struct adis *adis) { - int ret; - - mutex_lock(&adis->state_lock); - ret = __adis_check_status(adis); - mutex_unlock(&adis->state_lock); - - return ret; -} - -static inline void adis_dev_lock(struct adis *adis) -{ - mutex_lock(&adis->state_lock); + guard(mutex)(&adis->state_lock); + return __adis_check_status(adis); } -static inline void adis_dev_unlock(struct adis *adis) -{ - mutex_unlock(&adis->state_lock); -} +#define adis_dev_auto_lock(adis) guard(mutex)(&(adis)->state_lock) +#define adis_dev_auto_scoped_lock(adis) \ + scoped_guard(mutex, &(adis)->state_lock) int adis_single_conversion(struct iio_dev *indio_dev, const struct iio_chan_spec *chan, @@ -515,11 +482,19 @@ int adis_single_conversion(struct iio_dev *indio_dev, #define ADIS_ROT_CHAN(mod, addr, si, info_sep, info_all, bits) \ ADIS_MOD_CHAN(IIO_ROT, mod, addr, si, info_sep, info_all, bits) +#define devm_adis_setup_buffer_and_trigger(adis, indio_dev, trigger_handler) \ + devm_adis_setup_buffer_and_trigger_with_attrs((adis), (indio_dev), \ + (trigger_handler), NULL, \ + NULL) + #ifdef CONFIG_IIO_ADIS_LIB_BUFFER int -devm_adis_setup_buffer_and_trigger(struct adis *adis, struct iio_dev *indio_dev, - irq_handler_t trigger_handler); +devm_adis_setup_buffer_and_trigger_with_attrs(struct adis *adis, + struct iio_dev *indio_dev, + irq_handler_t trigger_handler, + const struct iio_buffer_setup_ops *ops, + const struct iio_dev_attr **buffer_attrs); int devm_adis_probe_trigger(struct adis *adis, struct iio_dev *indio_dev); @@ -529,8 +504,11 @@ int adis_update_scan_mode(struct iio_dev *indio_dev, #else /* CONFIG_IIO_BUFFER */ static inline int -devm_adis_setup_buffer_and_trigger(struct adis *adis, struct iio_dev *indio_dev, - irq_handler_t trigger_handler) +devm_adis_setup_buffer_and_trigger_with_attrs(struct adis *adis, + struct iio_dev *indio_dev, + irq_handler_t trigger_handler, + const struct iio_buffer_setup_ops *ops, + const struct iio_dev_attr **buffer_attrs) { return 0; } diff --git a/include/linux/iio/timer/stm32-timer-trigger.h b/include/linux/iio/timer/stm32-timer-trigger.h index 37572e4dc73a..1ee237b56183 100644 --- a/include/linux/iio/timer/stm32-timer-trigger.h +++ b/include/linux/iio/timer/stm32-timer-trigger.h @@ -72,6 +72,12 @@ #define TIM17_OC1 "tim17_oc1" +#define TIM20_OC1 "tim20_oc1" +#define TIM20_OC2 "tim20_oc2" +#define TIM20_OC3 "tim20_oc3" +#define TIM20_TRGO "tim20_trgo" +#define TIM20_TRGO2 "tim20_trgo2" + #if IS_REACHABLE(CONFIG_IIO_STM32_TIMER_TRIGGER) bool is_stm32_timer_trigger(struct iio_trigger *trig); #else diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index cb5280e6cc21..5730ba6b1cfa 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -141,7 +141,7 @@ static inline void ipv4_devconf_setall(struct in_device *in_dev) ARP_EVICT_NOCARRIER) struct in_ifaddr { - struct hlist_node hash; + struct hlist_node addr_lst; struct in_ifaddr __rcu *ifa_next; struct in_device *ifa_dev; struct rcu_head rcu_head; @@ -226,6 +226,10 @@ static __inline__ bool bad_mask(__be32 mask, __be32 addr) for (ifa = rtnl_dereference((in_dev)->ifa_list); ifa; \ ifa = rtnl_dereference(ifa->ifa_next)) +#define in_dev_for_each_ifa_rtnl_net(net, ifa, in_dev) \ + for (ifa = rtnl_net_dereference(net, (in_dev)->ifa_list); ifa; \ + ifa = rtnl_net_dereference(net, ifa->ifa_next)) + #define in_dev_for_each_ifa_rcu(ifa, in_dev) \ for (ifa = rcu_dereference((in_dev)->ifa_list); ifa; \ ifa = rcu_dereference(ifa->ifa_next)) @@ -252,6 +256,11 @@ static inline struct in_device *__in_dev_get_rtnl(const struct net_device *dev) return rtnl_dereference(dev->ip_ptr); } +static inline struct in_device *__in_dev_get_rtnl_net(const struct net_device *dev) +{ + return rtnl_net_dereference(dev_net(dev), dev->ip_ptr); +} + /* called with rcu_read_lock or rtnl held */ static inline bool ip_ignore_linkdown(const struct net_device *dev) { diff --git a/include/linux/init.h b/include/linux/init.h index 58cef4c2e59a..ee1309473bc6 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -84,11 +84,15 @@ #define __exit __section(".exit.text") __exitused __cold notrace -/* Used for MEMORY_HOTPLUG */ -#define __meminit __section(".meminit.text") __cold notrace \ - __latent_entropy -#define __meminitdata __section(".meminit.data") -#define __meminitconst __section(".meminit.rodata") +#ifdef CONFIG_MEMORY_HOTPLUG +#define __meminit +#define __meminitdata +#define __meminitconst +#else +#define __meminit __init +#define __meminitdata __initdata +#define __meminitconst __initconst +#endif /* For assembly routines */ #define __HEAD .section ".head.text","ax" @@ -99,10 +103,6 @@ #define __INITRODATA .section ".init.rodata","a",%progbits #define __FINITDATA .previous -#define __MEMINIT .section ".meminit.text", "ax" -#define __MEMINITDATA .section ".meminit.data", "aw" -#define __MEMINITRODATA .section ".meminit.rodata", "a" - /* silence warnings when references are OK */ #define __REF .section ".ref.text", "ax" #define __REFDATA .section ".ref.data", "aw" diff --git a/include/linux/input.h b/include/linux/input.h index c22ac465254b..7d7cb0593a63 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -275,7 +275,8 @@ struct input_handle; * it may not sleep * @events: event sequence handler. This method is being called by * input core with interrupts disabled and dev->event_lock - * spinlock held and so it may not sleep + * spinlock held and so it may not sleep. The method must return + * number of events passed to it. * @filter: similar to @event; separates normal event handlers from * "filters". * @match: called after comparing device's id with handler's id_table @@ -285,6 +286,10 @@ struct input_handle; * @start: starts handler for given handle. This function is called by * input core right after connect() method and also when a process * that "grabbed" a device releases it + * @passive_observer: set to %true by drivers only interested in observing + * data stream from devices if there are other users present. Such + * drivers will not result in starting underlying hardware device + * when input_open_device() is called for their handles * @legacy_minors: set to %true by drivers using legacy minor ranges * @minor: beginning of range of 32 legacy minors for devices this driver * can provide @@ -312,14 +317,15 @@ struct input_handler { void *private; void (*event)(struct input_handle *handle, unsigned int type, unsigned int code, int value); - void (*events)(struct input_handle *handle, - const struct input_value *vals, unsigned int count); + unsigned int (*events)(struct input_handle *handle, + struct input_value *vals, unsigned int count); bool (*filter)(struct input_handle *handle, unsigned int type, unsigned int code, int value); bool (*match)(struct input_handler *handler, struct input_dev *dev); int (*connect)(struct input_handler *handler, struct input_dev *dev, const struct input_device_id *id); void (*disconnect)(struct input_handle *handle); void (*start)(struct input_handle *handle); + bool passive_observer; bool legacy_minors; int minor; const char *name; @@ -338,12 +344,16 @@ struct input_handler { * @name: name given to the handle by handler that created it * @dev: input device the handle is attached to * @handler: handler that works with the device through this handle + * @handle_events: event sequence handler. It is set up by the input core + * according to event handling method specified in the @handler. See + * input_handle_setup_event_handler(). + * This method is being called by the input core with interrupts disabled + * and dev->event_lock spinlock held and so it may not sleep. * @d_node: used to put the handle on device's list of attached handles * @h_node: used to put the handle on handler's list of handles from which * it gets events */ struct input_handle { - void *private; int open; @@ -352,6 +362,10 @@ struct input_handle { struct input_dev *dev; struct input_handler *handler; + unsigned int (*handle_events)(struct input_handle *handle, + struct input_value *vals, + unsigned int count); + struct list_head d_node; struct list_head h_node; }; diff --git a/include/linux/input/matrix_keypad.h b/include/linux/input/matrix_keypad.h index b8d8d69eba29..90867f44ab4d 100644 --- a/include/linux/input/matrix_keypad.h +++ b/include/linux/input/matrix_keypad.h @@ -34,52 +34,6 @@ struct matrix_keymap_data { unsigned int keymap_size; }; -/** - * struct matrix_keypad_platform_data - platform-dependent keypad data - * @keymap_data: pointer to &matrix_keymap_data - * @row_gpios: pointer to array of gpio numbers representing rows - * @col_gpios: pointer to array of gpio numbers reporesenting colums - * @num_row_gpios: actual number of row gpios used by device - * @num_col_gpios: actual number of col gpios used by device - * @col_scan_delay_us: delay, measured in microseconds, that is - * needed before we can keypad after activating column gpio - * @debounce_ms: debounce interval in milliseconds - * @clustered_irq: may be specified if interrupts of all row/column GPIOs - * are bundled to one single irq - * @clustered_irq_flags: flags that are needed for the clustered irq - * @active_low: gpio polarity - * @wakeup: controls whether the device should be set up as wakeup - * source - * @no_autorepeat: disable key autorepeat - * @drive_inactive_cols: drive inactive columns during scan, rather than - * making them inputs. - * - * This structure represents platform-specific data that use used by - * matrix_keypad driver to perform proper initialization. - */ -struct matrix_keypad_platform_data { - const struct matrix_keymap_data *keymap_data; - - const unsigned int *row_gpios; - const unsigned int *col_gpios; - - unsigned int num_row_gpios; - unsigned int num_col_gpios; - - unsigned int col_scan_delay_us; - - /* key debounce interval in milli-second */ - unsigned int debounce_ms; - - unsigned int clustered_irq; - unsigned int clustered_irq_flags; - - bool active_low; - bool wakeup; - bool no_autorepeat; - bool drive_inactive_cols; -}; - int matrix_keypad_build_keymap(const struct matrix_keymap_data *keymap_data, const char *keymap_name, unsigned int rows, unsigned int cols, @@ -88,6 +42,4 @@ int matrix_keypad_build_keymap(const struct matrix_keymap_data *keymap_data, int matrix_keypad_parse_properties(struct device *dev, unsigned int *rows, unsigned int *cols); -#define matrix_keypad_parse_of_params matrix_keypad_parse_properties - #endif /* _MATRIX_KEYPAD_H */ diff --git a/include/linux/instrumentation.h b/include/linux/instrumentation.h index bc7babe91b2e..bf675a8aef8a 100644 --- a/include/linux/instrumentation.h +++ b/include/linux/instrumentation.h @@ -4,14 +4,14 @@ #ifdef CONFIG_NOINSTR_VALIDATION +#include <linux/objtool.h> #include <linux/stringify.h> /* Begin/end of an instrumentation safe region */ #define __instrumentation_begin(c) ({ \ asm volatile(__stringify(c) ": nop\n\t" \ - ".pushsection .discard.instr_begin\n\t" \ - ".long " __stringify(c) "b - .\n\t" \ - ".popsection\n\t" : : "i" (c)); \ + ANNOTATE_INSTR_BEGIN(__ASM_BREF(c)) \ + : : "i" (c)); \ }) #define instrumentation_begin() __instrumentation_begin(__COUNTER__) @@ -48,9 +48,8 @@ */ #define __instrumentation_end(c) ({ \ asm volatile(__stringify(c) ": nop\n\t" \ - ".pushsection .discard.instr_end\n\t" \ - ".long " __stringify(c) "b - .\n\t" \ - ".popsection\n\t" : : "i" (c)); \ + ANNOTATE_INSTR_END(__ASM_BREF(c)) \ + : : "i" (c)); \ }) #define instrumentation_end() __instrumentation_end(__COUNTER__) #else /* !CONFIG_NOINSTR_VALIDATION */ diff --git a/include/linux/instrumented.h b/include/linux/instrumented.h index 1b608e00290a..711a1f0d1a73 100644 --- a/include/linux/instrumented.h +++ b/include/linux/instrumented.h @@ -148,6 +148,41 @@ instrument_copy_from_user_after(const void *to, const void __user *from, } /** + * instrument_memcpy_before - add instrumentation before non-instrumented memcpy + * @to: destination address + * @from: source address + * @n: number of bytes to copy + * + * Instrument memory accesses that happen in custom memcpy implementations. The + * instrumentation should be inserted before the memcpy call. + */ +static __always_inline void instrument_memcpy_before(void *to, const void *from, + unsigned long n) +{ + kasan_check_write(to, n); + kasan_check_read(from, n); + kcsan_check_write(to, n); + kcsan_check_read(from, n); +} + +/** + * instrument_memcpy_after - add instrumentation after non-instrumented memcpy + * @to: destination address + * @from: source address + * @n: number of bytes to copy + * @left: number of bytes not copied (if known) + * + * Instrument memory accesses that happen in custom memcpy implementations. The + * instrumentation should be inserted after the memcpy call. + */ +static __always_inline void instrument_memcpy_after(void *to, const void *from, + unsigned long n, + unsigned long left) +{ + kmsan_memmove(to, from, n - left); +} + +/** * instrument_get_user() - add instrumentation to get_user()-like macros * @to: destination variable, may not be address-taken * diff --git a/include/linux/integrity.h b/include/linux/integrity.h index 459b79683783..f5842372359b 100644 --- a/include/linux/integrity.h +++ b/include/linux/integrity.h @@ -8,6 +8,7 @@ #define _LINUX_INTEGRITY_H #include <linux/fs.h> +#include <linux/iversion.h> enum integrity_status { INTEGRITY_PASS = 0, @@ -28,4 +29,37 @@ static inline void integrity_load_keys(void) } #endif /* CONFIG_INTEGRITY */ +/* An inode's attributes for detection of changes */ +struct integrity_inode_attributes { + u64 version; /* track inode changes */ + unsigned long ino; + dev_t dev; +}; + +/* + * On stacked filesystems the i_version alone is not enough to detect file data + * or metadata change. Additional metadata is required. + */ +static inline void +integrity_inode_attrs_store(struct integrity_inode_attributes *attrs, + u64 i_version, const struct inode *inode) +{ + attrs->version = i_version; + attrs->dev = inode->i_sb->s_dev; + attrs->ino = inode->i_ino; +} + +/* + * On stacked filesystems detect whether the inode or its content has changed. + */ +static inline bool +integrity_inode_attrs_changed(const struct integrity_inode_attributes *attrs, + const struct inode *inode) +{ + return (inode->i_sb->s_dev != attrs->dev || + inode->i_ino != attrs->ino || + !inode_eq_iversion(inode, attrs->version)); +} + + #endif /* _LINUX_INTEGRITY_H */ diff --git a/include/linux/intel-ish-client-if.h b/include/linux/intel-ish-client-if.h index 771622650247..dfbf7d9d7bb5 100644 --- a/include/linux/intel-ish-client-if.h +++ b/include/linux/intel-ish-client-if.h @@ -100,7 +100,6 @@ void ishtp_cl_destroy_connection(struct ishtp_cl *cl, bool reset); int ishtp_cl_send(struct ishtp_cl *cl, uint8_t *buf, size_t length); int ishtp_cl_flush_queues(struct ishtp_cl *cl); int ishtp_cl_io_rb_recycle(struct ishtp_cl_rb *rb); -bool ishtp_cl_tx_empty(struct ishtp_cl *cl); struct ishtp_cl_rb *ishtp_cl_rx_get_rb(struct ishtp_cl *cl); void *ishtp_get_client_data(struct ishtp_cl *cl); void ishtp_set_client_data(struct ishtp_cl *cl, void *data); diff --git a/include/linux/intel_rapl.h b/include/linux/intel_rapl.h index f3196f82fd8a..c0397423d3a8 100644 --- a/include/linux/intel_rapl.h +++ b/include/linux/intel_rapl.h @@ -158,6 +158,26 @@ struct rapl_if_priv { void *rpi; }; +#ifdef CONFIG_PERF_EVENTS +/** + * struct rapl_package_pmu_data: Per package data for PMU support + * @scale: Scale of 2^-32 Joules for each energy counter increase. + * @lock: Lock to protect n_active and active_list. + * @n_active: Number of active events. + * @active_list: List of active events. + * @timer_interval: Maximum timer expiration time before counter overflow. + * @hrtimer: Periodically update the counter to prevent overflow. + */ +struct rapl_package_pmu_data { + u64 scale[RAPL_DOMAIN_MAX]; + raw_spinlock_t lock; + int n_active; + struct list_head active_list; + ktime_t timer_interval; + struct hrtimer hrtimer; +}; +#endif + /* maximum rapl package domain name: package-%d-die-%d */ #define PACKAGE_DOMAIN_NAME_LENGTH 30 @@ -176,6 +196,10 @@ struct rapl_package { struct cpumask cpumask; char name[PACKAGE_DOMAIN_NAME_LENGTH]; struct rapl_if_priv *priv; +#ifdef CONFIG_PERF_EVENTS + bool has_pmu; + struct rapl_package_pmu_data pmu_data; +#endif }; struct rapl_package *rapl_find_package_domain_cpuslocked(int id, struct rapl_if_priv *priv, @@ -188,4 +212,12 @@ struct rapl_package *rapl_find_package_domain(int id, struct rapl_if_priv *priv, struct rapl_package *rapl_add_package(int id, struct rapl_if_priv *priv, bool id_is_cpu); void rapl_remove_package(struct rapl_package *rp); +#ifdef CONFIG_PERF_EVENTS +int rapl_package_add_pmu(struct rapl_package *rp); +void rapl_package_remove_pmu(struct rapl_package *rp); +#else +static inline int rapl_package_add_pmu(struct rapl_package *rp) { return 0; } +static inline void rapl_package_remove_pmu(struct rapl_package *rp) { } +#endif + #endif /* __INTEL_RAPL_H__ */ diff --git a/include/linux/intel_tcc.h b/include/linux/intel_tcc.h index 8ff8eabb4a98..fa788817acfc 100644 --- a/include/linux/intel_tcc.h +++ b/include/linux/intel_tcc.h @@ -14,5 +14,6 @@ int intel_tcc_get_tjmax(int cpu); int intel_tcc_get_offset(int cpu); int intel_tcc_set_offset(int cpu, int offset); int intel_tcc_get_temp(int cpu, int *temp, bool pkg); +u32 intel_tcc_get_offset_mask(void); #endif /* __INTEL_TCC_H__ */ diff --git a/include/linux/intel_tpmi.h b/include/linux/intel_tpmi.h index a3529b962be6..ff480b47ae64 100644 --- a/include/linux/intel_tpmi.h +++ b/include/linux/intel_tpmi.h @@ -21,22 +21,29 @@ enum intel_tpmi_id { TPMI_ID_PEM = 1, /* Power and Perf excursion Monitor */ TPMI_ID_UNCORE = 2, /* Uncore Frequency Scaling */ TPMI_ID_SST = 5, /* Speed Select Technology */ + TPMI_ID_PLR = 0xc, /* Performance Limit Reasons */ TPMI_CONTROL_ID = 0x80, /* Special ID for getting feature status */ TPMI_INFO_ID = 0x81, /* Special ID for PCI BDF and Package ID information */ }; /** * struct intel_tpmi_plat_info - Platform information for a TPMI device instance - * @package_id: CPU Package id - * @bus_number: PCI bus number - * @device_number: PCI device number + * @cdie_mask: Mask of all compute dies in the partition + * @package_id: CPU Package id + * @partition: Package partition id when multiple VSEC PCI devices per package + * @segment: PCI segment ID + * @bus_number: PCI bus number + * @device_number: PCI device number * @function_number: PCI function number * * Structure to store platform data for a TPMI device instance. This * struct is used to return data via tpmi_get_platform_data(). */ struct intel_tpmi_plat_info { + u16 cdie_mask; u8 package_id; + u8 partition; + u8 segment; u8 bus_number; u8 device_number; u8 function_number; @@ -47,4 +54,5 @@ struct resource *tpmi_get_resource_at_index(struct auxiliary_device *auxdev, int int tpmi_get_resource_count(struct auxiliary_device *auxdev); int tpmi_get_feature_status(struct auxiliary_device *auxdev, int feature_id, bool *read_blocked, bool *write_blocked); +struct dentry *tpmi_get_debugfs_dir(struct auxiliary_device *auxdev); #endif diff --git a/include/linux/intel_vsec.h b/include/linux/intel_vsec.h new file mode 100644 index 000000000000..b94beab64610 --- /dev/null +++ b/include/linux/intel_vsec.h @@ -0,0 +1,150 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _INTEL_VSEC_H +#define _INTEL_VSEC_H + +#include <linux/auxiliary_bus.h> +#include <linux/bits.h> + +#define VSEC_CAP_TELEMETRY BIT(0) +#define VSEC_CAP_WATCHER BIT(1) +#define VSEC_CAP_CRASHLOG BIT(2) +#define VSEC_CAP_SDSI BIT(3) +#define VSEC_CAP_TPMI BIT(4) + +/* Intel DVSEC offsets */ +#define INTEL_DVSEC_ENTRIES 0xA +#define INTEL_DVSEC_SIZE 0xB +#define INTEL_DVSEC_TABLE 0xC +#define INTEL_DVSEC_TABLE_BAR(x) ((x) & GENMASK(2, 0)) +#define INTEL_DVSEC_TABLE_OFFSET(x) ((x) & GENMASK(31, 3)) +#define TABLE_OFFSET_SHIFT 3 + +struct pci_dev; +struct resource; + +enum intel_vsec_id { + VSEC_ID_TELEMETRY = 2, + VSEC_ID_WATCHER = 3, + VSEC_ID_CRASHLOG = 4, + VSEC_ID_SDSI = 65, + VSEC_ID_TPMI = 66, +}; + +/** + * struct intel_vsec_header - Common fields of Intel VSEC and DVSEC registers. + * @rev: Revision ID of the VSEC/DVSEC register space + * @length: Length of the VSEC/DVSEC register space + * @id: ID of the feature + * @num_entries: Number of instances of the feature + * @entry_size: Size of the discovery table for each feature + * @tbir: BAR containing the discovery tables + * @offset: BAR offset of start of the first discovery table + */ +struct intel_vsec_header { + u8 rev; + u16 length; + u16 id; + u8 num_entries; + u8 entry_size; + u8 tbir; + u32 offset; +}; + +enum intel_vsec_quirks { + /* Watcher feature not supported */ + VSEC_QUIRK_NO_WATCHER = BIT(0), + + /* Crashlog feature not supported */ + VSEC_QUIRK_NO_CRASHLOG = BIT(1), + + /* Use shift instead of mask to read discovery table offset */ + VSEC_QUIRK_TABLE_SHIFT = BIT(2), + + /* DVSEC not present (provided in driver data) */ + VSEC_QUIRK_NO_DVSEC = BIT(3), + + /* Platforms requiring quirk in the auxiliary driver */ + VSEC_QUIRK_EARLY_HW = BIT(4), +}; + +/** + * struct pmt_callbacks - Callback infrastructure for PMT devices + * ->read_telem() when specified, called by client driver to access PMT data (instead + * of direct copy). + * @pdev: PCI device reference for the callback's use + * @guid: ID of data to acccss + * @data: buffer for the data to be copied + * @off: offset into the requested buffer + * @count: size of buffer + */ +struct pmt_callbacks { + int (*read_telem)(struct pci_dev *pdev, u32 guid, u64 *data, loff_t off, u32 count); +}; + +/** + * struct intel_vsec_platform_info - Platform specific data + * @parent: parent device in the auxbus chain + * @headers: list of headers to define the PMT client devices to create + * @priv_data: private data, usable by parent devices, currently a callback + * @caps: bitmask of PMT capabilities for the given headers + * @quirks: bitmask of VSEC device quirks + * @base_addr: allow a base address to be specified (rather than derived) + */ +struct intel_vsec_platform_info { + struct device *parent; + struct intel_vsec_header **headers; + void *priv_data; + unsigned long caps; + unsigned long quirks; + u64 base_addr; +}; + +/** + * struct intel_sec_device - Auxbus specific device information + * @auxdev: auxbus device struct for auxbus access + * @pcidev: pci device associated with the device + * @resource: any resources shared by the parent + * @ida: id reference + * @num_resources: number of resources + * @id: xarray id + * @priv_data: any private data needed + * @quirks: specified quirks + * @base_addr: base address of entries (if specified) + */ +struct intel_vsec_device { + struct auxiliary_device auxdev; + struct pci_dev *pcidev; + struct resource *resource; + struct ida *ida; + int num_resources; + int id; /* xa */ + void *priv_data; + size_t priv_data_size; + unsigned long quirks; + u64 base_addr; +}; + +int intel_vsec_add_aux(struct pci_dev *pdev, struct device *parent, + struct intel_vsec_device *intel_vsec_dev, + const char *name); + +static inline struct intel_vsec_device *dev_to_ivdev(struct device *dev) +{ + return container_of(dev, struct intel_vsec_device, auxdev.dev); +} + +static inline struct intel_vsec_device *auxdev_to_ivdev(struct auxiliary_device *auxdev) +{ + return container_of(auxdev, struct intel_vsec_device, auxdev); +} + +#if IS_ENABLED(CONFIG_INTEL_VSEC) +void intel_vsec_register(struct pci_dev *pdev, + struct intel_vsec_platform_info *info); +#else +static inline void intel_vsec_register(struct pci_dev *pdev, + struct intel_vsec_platform_info *info) +{ +} +#endif +#endif diff --git a/include/linux/interconnect-clk.h b/include/linux/interconnect-clk.h index 0cd80112bea5..9bcee3e9c56c 100644 --- a/include/linux/interconnect-clk.h +++ b/include/linux/interconnect-clk.h @@ -11,12 +11,16 @@ struct device; struct icc_clk_data { struct clk *clk; const char *name; + unsigned int master_id; + unsigned int slave_id; }; struct icc_provider *icc_clk_register(struct device *dev, unsigned int first_id, unsigned int num_clocks, const struct icc_clk_data *data); +int devm_icc_clk_register(struct device *dev, unsigned int first_id, + unsigned int num_clocks, const struct icc_clk_data *data); void icc_clk_unregister(struct icc_provider *provider); #endif diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 5c9bdd3ffccc..8cd9327e4e78 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -5,13 +5,14 @@ #include <linux/kernel.h> #include <linux/bitops.h> -#include <linux/cpumask.h> +#include <linux/cleanup.h> #include <linux/irqreturn.h> #include <linux/irqnr.h> #include <linux/hardirq.h> #include <linux/irqflags.h> #include <linux/hrtimer.h> #include <linux/kref.h> +#include <linux/cpumask_types.h> #include <linux/workqueue.h> #include <linux/jump_label.h> @@ -168,7 +169,7 @@ static inline int __must_check request_irq(unsigned int irq, irq_handler_t handler, unsigned long flags, const char *name, void *dev) { - return request_threaded_irq(irq, handler, NULL, flags, name, dev); + return request_threaded_irq(irq, handler, NULL, flags | IRQF_COND_ONESHOT, name, dev); } extern int __must_check @@ -235,6 +236,9 @@ extern void enable_percpu_irq(unsigned int irq, unsigned int type); extern bool irq_percpu_is_enabled(unsigned int irq); extern void irq_wake_thread(unsigned int irq, void *dev_id); +DEFINE_LOCK_GUARD_1(disable_irq, int, + disable_irq(*_T->lock), enable_irq(*_T->lock)) + extern void disable_nmi_nosync(unsigned int irq); extern void disable_percpu_nmi(unsigned int irq); extern void enable_nmi(unsigned int irq); @@ -272,7 +276,7 @@ struct irq_affinity_notify { #define IRQ_AFFINITY_MAX_SETS 4 /** - * struct irq_affinity - Description for automatic irq affinity assignements + * struct irq_affinity - Description for automatic irq affinity assignments * @pre_vectors: Don't apply affinity to @pre_vectors at beginning of * the MSI(-X) vector space * @post_vectors: Don't apply affinity to @post_vectors at end of @@ -590,7 +594,7 @@ extern const char * const softirq_to_name[NR_SOFTIRQS]; struct softirq_action { - void (*action)(struct softirq_action *); + void (*action)(void); }; asmlinkage void do_softirq(void); @@ -605,13 +609,60 @@ static inline void do_softirq_post_smp_call_flush(unsigned int unused) } #endif -extern void open_softirq(int nr, void (*action)(struct softirq_action *)); +extern void open_softirq(int nr, void (*action)(void)); extern void softirq_init(void); extern void __raise_softirq_irqoff(unsigned int nr); extern void raise_softirq_irqoff(unsigned int nr); extern void raise_softirq(unsigned int nr); +/* + * With forced-threaded interrupts enabled a raised softirq is deferred to + * ksoftirqd unless it can be handled within the threaded interrupt. This + * affects timer_list timers and hrtimers which are explicitly marked with + * HRTIMER_MODE_SOFT. + * With PREEMPT_RT enabled more hrtimers are moved to softirq for processing + * which includes all timers which are not explicitly marked HRTIMER_MODE_HARD. + * Userspace controlled timers (like the clock_nanosleep() interface) is divided + * into two categories: Tasks with elevated scheduling policy including + * SCHED_{FIFO|RR|DL} and the remaining scheduling policy. The tasks with the + * elevated scheduling policy are woken up directly from the HARDIRQ while all + * other wake ups are delayed to softirq and so to ksoftirqd. + * + * The ksoftirqd runs at SCHED_OTHER policy at which it should remain since it + * handles the softirq in an overloaded situation (not handled everything + * within its last run). + * If the timers are handled at SCHED_OTHER priority then they competes with all + * other SCHED_OTHER tasks for CPU resources are possibly delayed. + * Moving timers softirqs to a low priority SCHED_FIFO thread instead ensures + * that timer are performed before scheduling any SCHED_OTHER thread. + */ +DECLARE_PER_CPU(struct task_struct *, ktimerd); +DECLARE_PER_CPU(unsigned long, pending_timer_softirq); +void raise_ktimers_thread(unsigned int nr); + +static inline unsigned int local_timers_pending_force_th(void) +{ + return __this_cpu_read(pending_timer_softirq); +} + +static inline void raise_timer_softirq(unsigned int nr) +{ + lockdep_assert_in_irq(); + if (force_irqthreads()) + raise_ktimers_thread(nr); + else + __raise_softirq_irqoff(nr); +} + +static inline unsigned int local_timers_pending(void) +{ + if (force_irqthreads()) + return local_timers_pending_force_th(); + else + return local_softirq_pending(); +} + DECLARE_PER_CPU(struct task_struct *, ksoftirqd); static inline struct task_struct *this_cpu_ksoftirqd(void) diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index 86cf1f7ae389..bba2a51c87d2 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -85,6 +85,9 @@ struct io_pgtable_cfg { * * IO_PGTABLE_QUIRK_ARM_OUTER_WBWA: Override the outer-cacheability * attributes set in the TCR for a non-coherent page-table walker. + * + * IO_PGTABLE_QUIRK_ARM_HD: Enables dirty tracking in stage 1 pagetable. + * IO_PGTABLE_QUIRK_ARM_S2FWB: Use the FWB format for the MemAttrs bits */ #define IO_PGTABLE_QUIRK_ARM_NS BIT(0) #define IO_PGTABLE_QUIRK_NO_PERMS BIT(1) @@ -92,6 +95,8 @@ struct io_pgtable_cfg { #define IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT BIT(4) #define IO_PGTABLE_QUIRK_ARM_TTBR1 BIT(5) #define IO_PGTABLE_QUIRK_ARM_OUTER_WBWA BIT(6) + #define IO_PGTABLE_QUIRK_ARM_HD BIT(7) + #define IO_PGTABLE_QUIRK_ARM_S2FWB BIT(8) unsigned long quirks; unsigned long pgsize_bitmap; unsigned int ias; @@ -168,15 +173,29 @@ struct io_pgtable_cfg { u64 ttbr[4]; u32 n_ttbrs; } apple_dart_cfg; + + struct { + int nid; + } amd; }; }; /** + * struct arm_lpae_io_pgtable_walk_data - information from a pgtable walk + * + * @ptes: The recorded PTE values from the walk + */ +struct arm_lpae_io_pgtable_walk_data { + u64 ptes[4]; +}; + +/** * struct io_pgtable_ops - Page table manipulation API for IOMMU drivers. * * @map_pages: Map a physically contiguous range of pages of the same size. * @unmap_pages: Unmap a range of virtually contiguous pages of the same size. * @iova_to_phys: Translate iova to physical address. + * @pgtable_walk: (optional) Perform a page table walk for a given iova. * * These functions map directly onto the iommu_ops member functions with * the same names. @@ -190,6 +209,7 @@ struct io_pgtable_ops { struct iommu_iotlb_gather *gather); phys_addr_t (*iova_to_phys)(struct io_pgtable_ops *ops, unsigned long iova); + int (*pgtable_walk)(struct io_pgtable_ops *ops, unsigned long iova, void *wd); int (*read_and_clear_dirty)(struct io_pgtable_ops *ops, unsigned long iova, size_t size, unsigned long flags, diff --git a/include/linux/io.h b/include/linux/io.h index 235ba7d80a8f..59ec5eea696c 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -6,6 +6,7 @@ #ifndef _LINUX_IO_H #define _LINUX_IO_H +#include <linux/sizes.h> #include <linux/types.h> #include <linux/init.h> #include <linux/bug.h> @@ -16,9 +17,15 @@ struct device; struct resource; -__visible void __iowrite32_copy(void __iomem *to, const void *from, size_t count); +#ifndef __iowrite32_copy +void __iowrite32_copy(void __iomem *to, const void *from, size_t count); +#endif + void __ioread32_copy(void *to, const void __iomem *from, size_t count); + +#ifndef __iowrite64_copy void __iowrite64_copy(void __iomem *to, const void *from, size_t count); +#endif #ifdef CONFIG_MMU int ioremap_page_range(unsigned long addr, unsigned long end, diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 68ed6697fece..85fe4e6b275c 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -11,15 +11,12 @@ void __io_uring_cancel(bool cancel_all); void __io_uring_free(struct task_struct *tsk); void io_uring_unreg_ringfd(void); const char *io_uring_get_opcode(u8 opcode); -int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags); bool io_is_uring_fops(struct file *file); static inline void io_uring_files_cancel(void) { - if (current->io_uring) { - io_uring_unreg_ringfd(); + if (current->io_uring) __io_uring_cancel(false); - } } static inline void io_uring_task_cancel(void) { @@ -45,11 +42,6 @@ static inline const char *io_uring_get_opcode(u8 opcode) { return ""; } -static inline int io_uring_cmd_sock(struct io_uring_cmd *cmd, - unsigned int issue_flags) -{ - return -EOPNOTSUPP; -} static inline bool io_is_uring_fops(struct file *file) { return false; diff --git a/include/linux/io_uring/cmd.h b/include/linux/io_uring/cmd.h index e453a997c060..abd0c8bd950b 100644 --- a/include/linux/io_uring/cmd.h +++ b/include/linux/io_uring/cmd.h @@ -18,23 +18,53 @@ struct io_uring_cmd { u8 pdu[32]; /* available inline for free use */ }; +struct io_uring_cmd_data { + void *op_data; + struct io_uring_sqe sqes[2]; +}; + static inline const void *io_uring_sqe_cmd(const struct io_uring_sqe *sqe) { return sqe->cmd; } +static inline void io_uring_cmd_private_sz_check(size_t cmd_sz) +{ + BUILD_BUG_ON(cmd_sz > sizeof_field(struct io_uring_cmd, pdu)); +} +#define io_uring_cmd_to_pdu(cmd, pdu_type) ( \ + io_uring_cmd_private_sz_check(sizeof(pdu_type)), \ + ((pdu_type *)&(cmd)->pdu) \ +) + #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, + +/* + * Completes the request, i.e. posts an io_uring CQE and deallocates @ioucmd + * and the corresponding io_uring request. + * + * Note: the caller should never hard code @issue_flags and is only allowed + * to pass the mask provided by the core io_uring code. + */ +void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, u64 res2, unsigned issue_flags); + void __io_uring_cmd_do_in_task(struct io_uring_cmd *ioucmd, void (*task_work_cb)(struct io_uring_cmd *, unsigned), unsigned flags); +/* + * Note: the caller should never hard code @issue_flags and only use the + * mask provided by the core io_uring code. + */ void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd, unsigned int issue_flags); +/* Execute the request from a blocking context */ +void io_uring_cmd_issue_blocking(struct io_uring_cmd *ioucmd); + #else static inline int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw, struct iov_iter *iter, void *ioucmd) @@ -42,7 +72,7 @@ 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, unsigned issue_flags) + u64 ret2, unsigned issue_flags) { } static inline void __io_uring_cmd_do_in_task(struct io_uring_cmd *ioucmd, @@ -54,8 +84,22 @@ static inline void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd, unsigned int issue_flags) { } +static inline void io_uring_cmd_issue_blocking(struct io_uring_cmd *ioucmd) +{ +} #endif +/* + * Polled completions must ensure they are coming from a poll queue, and + * hence are completed inside the usual poll handling loops. + */ +static inline void io_uring_cmd_iopoll_done(struct io_uring_cmd *ioucmd, + ssize_t ret, ssize_t res2) +{ + lockdep_assert(in_task()); + io_uring_cmd_done(ioucmd, ret, res2, 0); +} + /* users must follow the IOU_F_TWQ_LAZY_WAKE semantics */ static inline void io_uring_cmd_do_in_task_lazy(struct io_uring_cmd *ioucmd, void (*task_work_cb)(struct io_uring_cmd *, unsigned)) @@ -71,7 +115,12 @@ static inline void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd, static inline struct task_struct *io_uring_cmd_get_task(struct io_uring_cmd *cmd) { - return cmd_to_io_kiocb(cmd)->task; + return cmd_to_io_kiocb(cmd)->tctx->task; +} + +static inline struct io_uring_cmd_data *io_uring_cmd_get_async_data(struct io_uring_cmd *cmd) +{ + return cmd_to_io_kiocb(cmd)->async_data; } #endif /* _LINUX_IO_URING_CMD_H */ diff --git a/include/linux/io_uring/net.h b/include/linux/io_uring/net.h new file mode 100644 index 000000000000..b58f39fed4d5 --- /dev/null +++ b/include/linux/io_uring/net.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _LINUX_IO_URING_NET_H +#define _LINUX_IO_URING_NET_H + +struct io_uring_cmd; + +#if defined(CONFIG_IO_URING) +int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags); + +#else +static inline int io_uring_cmd_sock(struct io_uring_cmd *cmd, + unsigned int issue_flags) +{ + return -EOPNOTSUPP; +} +#endif + +#endif diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index ac333ea81d31..3def525a1da3 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -37,6 +37,7 @@ enum io_uring_cmd_flags { /* set when uring wants to cancel a previously issued command */ IO_URING_F_CANCEL = (1 << 11), IO_URING_F_COMPAT = (1 << 12), + IO_URING_F_TASK_DEAD = (1 << 13), }; struct io_wq_work_node { @@ -50,24 +51,23 @@ struct io_wq_work_list { struct io_wq_work { struct io_wq_work_node list; - unsigned flags; + atomic_t flags; /* place it here instead of io_kiocb as it fills padding and saves 4B */ int cancel_seq; }; -struct io_fixed_file { - /* file * with additional FFS_* flags */ - unsigned long file_ptr; +struct io_rsrc_data { + unsigned int nr; + struct io_rsrc_node **nodes; }; struct io_file_table { - struct io_fixed_file *files; + struct io_rsrc_data data; unsigned long *bitmap; unsigned int alloc_hint; }; struct io_hash_bucket { - spinlock_t lock; struct hlist_head list; } ____cacheline_aligned_in_smp; @@ -76,6 +76,13 @@ struct io_hash_table { unsigned hash_bits; }; +struct io_mapped_region { + struct page **pages; + void *ptr; + unsigned nr_pages; + unsigned flags; +}; + /* * Arbitrary limit, can be raised if need be */ @@ -85,6 +92,7 @@ struct io_uring_task { /* submission side */ int cached_refs; const struct io_ring_ctx *last; + struct task_struct *task; struct io_wq *io_wq; struct file *registered_rings[IO_RINGFD_REG_MAX]; @@ -205,24 +213,17 @@ struct io_submit_state { bool plug_started; bool need_plug; + bool cq_flush; unsigned short submit_nr; - unsigned int cqes_count; struct blk_plug plug; }; -struct io_ev_fd { - struct eventfd_ctx *cq_ev_fd; - unsigned int eventfd_async: 1; - struct rcu_head rcu; - atomic_t refs; - atomic_t ops; -}; - struct io_alloc_cache { - struct io_wq_work_node list; + void **entries; unsigned int nr_cached; unsigned int max_cached; - size_t elem_size; + unsigned int elem_size; + unsigned int init_clear; }; struct io_ring_ctx { @@ -247,6 +248,9 @@ struct io_ring_ctx { struct io_rings *rings; struct percpu_ref refs; + clockid_t clockid; + enum tk_offsets clock_offset; + enum task_work_notify_mode notify_method; unsigned sq_thread_idle; } ____cacheline_aligned_in_smp; @@ -275,7 +279,6 @@ struct io_ring_ctx { * Fixed resources fast path, should be accessed only under * uring_lock, and updated through io_uring_register(2) */ - struct io_rsrc_node *rsrc_node; atomic_t cancel_seq; /* @@ -288,23 +291,33 @@ struct io_ring_ctx { struct io_wq_work_list iopoll_list; struct io_file_table file_table; - struct io_mapped_ubuf **user_bufs; - unsigned nr_user_files; - unsigned nr_user_bufs; + struct io_rsrc_data buf_table; struct io_submit_state submit_state; + /* + * Modifications are protected by ->uring_lock and ->mmap_lock. + * The flags, buf_pages and buf_nr_pages fields should be stable + * once published. + */ struct xarray io_bl_xa; - struct io_hash_table cancel_table_locked; + struct io_hash_table cancel_table; struct io_alloc_cache apoll_cache; struct io_alloc_cache netmsg_cache; + struct io_alloc_cache rw_cache; + struct io_alloc_cache uring_cache; /* * Any cancelable uring_cmd is added to this list in * ->uring_cmd() by io_uring_cmd_insert_cancelable() */ struct hlist_head cancelable_uring_cmd; + /* + * For Hybrid IOPOLL, runtime in hybrid polling, without + * scheduling time + */ + u64 hybrid_poll_time; } ____cacheline_aligned_in_smp; struct { @@ -319,6 +332,9 @@ struct io_ring_ctx { unsigned cq_entries; struct io_ev_fd __rcu *io_ev_fd; unsigned cq_extra; + + void *cq_wait_arg; + size_t cq_wait_size; } ____cacheline_aligned_in_smp; /* @@ -327,6 +343,7 @@ struct io_ring_ctx { */ struct { struct llist_head work_llist; + struct llist_head retry_llist; unsigned long check_cq; atomic_t cq_wait_nr; atomic_t cq_timeouts; @@ -335,23 +352,16 @@ struct io_ring_ctx { /* timeouts */ struct { - spinlock_t timeout_lock; + raw_spinlock_t timeout_lock; struct list_head timeout_list; struct list_head ltimeout_list; unsigned cq_last_tm_flush; } ____cacheline_aligned_in_smp; - struct io_uring_cqe completion_cqes[16]; - spinlock_t completion_lock; - /* IRQ completion list, under ->completion_lock */ - unsigned int locked_free_nr; - struct io_wq_work_list locked_free_list; - struct list_head io_buffers_comp; struct list_head cq_overflow_list; - struct io_hash_table cancel_table; struct hlist_head waitid_list; @@ -371,24 +381,10 @@ struct io_ring_ctx { struct list_head io_buffers_cache; - /* deferred free list, protected by ->uring_lock */ - struct hlist_head io_buf_list; - /* Keep this last, we don't need it for the fast path */ struct wait_queue_head poll_wq; struct io_restriction restrictions; - /* slow path rsrc auxilary data, used by update/register */ - struct io_mapped_ubuf *dummy_ubuf; - struct io_rsrc_data *file_data; - struct io_rsrc_data *buf_data; - - /* protected by ->uring_lock */ - struct list_head rsrc_ref_list; - struct io_alloc_cache rsrc_node_cache; - struct wait_queue_head rsrc_quiesce_wq; - unsigned rsrc_quiesce; - u32 pers_next; struct xarray personalities; @@ -412,14 +408,17 @@ struct io_ring_ctx { struct callback_head poll_wq_task_work; struct list_head defer_list; + struct io_alloc_cache msg_cache; + spinlock_t msg_lock; + #ifdef CONFIG_NET_RX_BUSY_POLL struct list_head napi_list; /* track busy poll napi_id */ spinlock_t napi_lock; /* napi_list lock */ /* napi busy poll default timeout */ - unsigned int napi_busy_poll_to; + ktime_t napi_busy_poll_dt; bool napi_prefer_busy_poll; - bool napi_enabled; + u8 napi_track_mode; DECLARE_HASHTABLE(napi_ht, 4); #endif @@ -428,18 +427,19 @@ struct io_ring_ctx { unsigned evfd_last_cq_tail; /* - * If IORING_SETUP_NO_MMAP is used, then the below holds - * the gup'ed pages for the two rings, and the sqes. + * Protection for resize vs mmap races - both the mmap and resize + * side will need to grab this lock, to prevent either side from + * being run concurrently with the other. */ - unsigned short n_ring_pages; - unsigned short n_sqe_pages; - struct page **ring_pages; - struct page **sqe_pages; + struct mutex mmap_lock; + + struct io_mapped_region sq_region; + struct io_mapped_region ring_region; + /* used for optimised request parameter and wait argument passing */ + struct io_mapped_region param_region; }; struct io_tw_state { - /* ->uring_lock is taken, callbacks can use io_tw_lock to lock it */ - bool locked; }; enum { @@ -459,6 +459,7 @@ enum { REQ_F_LINK_TIMEOUT_BIT, REQ_F_NEED_CLEANUP_BIT, REQ_F_POLLED_BIT, + REQ_F_HYBRID_IOPOLL_STATE_BIT, REQ_F_BUFFER_SELECTED_BIT, REQ_F_BUFFER_RING_BIT, REQ_F_REISSUE_BIT, @@ -471,15 +472,16 @@ enum { REQ_F_DOUBLE_POLL_BIT, REQ_F_APOLL_MULTISHOT_BIT, REQ_F_CLEAR_POLLIN_BIT, - REQ_F_HASH_LOCKED_BIT, /* keep async read/write and isreg together and in order */ REQ_F_SUPPORT_NOWAIT_BIT, REQ_F_ISREG_BIT, REQ_F_POLL_NO_LAZY_BIT, - REQ_F_CANCEL_SEQ_BIT, REQ_F_CAN_POLL_BIT, REQ_F_BL_EMPTY_BIT, REQ_F_BL_NO_RECYCLE_BIT, + REQ_F_BUFFERS_COMMIT_BIT, + REQ_F_BUF_NODE_BIT, + REQ_F_HAS_METADATA_BIT, /* not a real bit, just to check we're not overflowing the space */ __REQ_F_LAST_BIT, @@ -518,6 +520,8 @@ enum { REQ_F_NEED_CLEANUP = IO_REQ_FLAG(REQ_F_NEED_CLEANUP_BIT), /* already went through poll handler */ REQ_F_POLLED = IO_REQ_FLAG(REQ_F_POLLED_BIT), + /* every req only blocks once in hybrid poll */ + REQ_F_IOPOLL_STATE = IO_REQ_FLAG(REQ_F_HYBRID_IOPOLL_STATE_BIT), /* buffer already selected */ REQ_F_BUFFER_SELECTED = IO_REQ_FLAG(REQ_F_BUFFER_SELECTED_BIT), /* buffer selected from ring, needs commit */ @@ -546,18 +550,20 @@ enum { REQ_F_APOLL_MULTISHOT = IO_REQ_FLAG(REQ_F_APOLL_MULTISHOT_BIT), /* recvmsg special flag, clear EPOLLIN */ REQ_F_CLEAR_POLLIN = IO_REQ_FLAG(REQ_F_CLEAR_POLLIN_BIT), - /* hashed into ->cancel_hash_locked, protected by ->uring_lock */ - REQ_F_HASH_LOCKED = IO_REQ_FLAG(REQ_F_HASH_LOCKED_BIT), /* don't use lazy poll wake for this request */ REQ_F_POLL_NO_LAZY = IO_REQ_FLAG(REQ_F_POLL_NO_LAZY_BIT), - /* cancel sequence is set and valid */ - REQ_F_CANCEL_SEQ = IO_REQ_FLAG(REQ_F_CANCEL_SEQ_BIT), /* file is pollable */ REQ_F_CAN_POLL = IO_REQ_FLAG(REQ_F_CAN_POLL_BIT), /* buffer list was empty after selection of buffer */ REQ_F_BL_EMPTY = IO_REQ_FLAG(REQ_F_BL_EMPTY_BIT), /* don't recycle provided buffers for this request */ REQ_F_BL_NO_RECYCLE = IO_REQ_FLAG(REQ_F_BL_NO_RECYCLE_BIT), + /* buffer ring head needs incrementing on put */ + REQ_F_BUFFERS_COMMIT = IO_REQ_FLAG(REQ_F_BUFFERS_COMMIT_BIT), + /* buf node is valid */ + REQ_F_BUF_NODE = IO_REQ_FLAG(REQ_F_BUF_NODE_BIT), + /* request has read/write metadata assigned */ + REQ_F_HAS_METADATA = IO_REQ_FLAG(REQ_F_HAS_METADATA_BIT), }; typedef void (*io_req_tw_func_t)(struct io_kiocb *req, struct io_tw_state *ts); @@ -627,12 +633,9 @@ struct io_kiocb { struct io_cqe cqe; struct io_ring_ctx *ctx; - struct task_struct *task; + struct io_uring_task *tctx; union { - /* store used ubuf, so we can prevent reloading */ - struct io_mapped_ubuf *imu; - /* stores selected buf, valid IFF REQ_F_BUFFER_SELECTED is set */ struct io_buffer *kbuf; @@ -641,6 +644,8 @@ struct io_kiocb { * REQ_F_BUFFER_RING is set. */ struct io_buffer_list *buf_list; + + struct io_rsrc_node *buf_node; }; union { @@ -650,18 +655,26 @@ struct io_kiocb { __poll_t apoll_events; }; - struct io_rsrc_node *rsrc_node; + struct io_rsrc_node *file_node; atomic_t refs; - atomic_t poll_refs; + bool cancel_seq_set; struct io_task_work io_task_work; - /* for polled requests, i.e. IORING_OP_POLL_ADD and async armed poll */ - struct hlist_node hash_node; + union { + /* + * for polled requests, i.e. IORING_OP_POLL_ADD and async armed + * poll + */ + struct hlist_node hash_node; + /* For IOPOLL setup queues, with hybrid polling */ + u64 iopoll_start; + }; /* internal polling, see IORING_FEAT_FAST_POLL */ struct async_poll *apoll; /* opcode allocated if it needs to store data for async defer */ void *async_data; /* linked requests, IFF REQ_F_HARDLINK or REQ_F_LINK are set */ + atomic_t poll_refs; struct io_kiocb *link; /* custom credentials, valid IFF REQ_F_CREDS is set */ const struct cred *creds; @@ -678,4 +691,9 @@ struct io_overflow_cqe { struct io_uring_cqe cqe; }; +static inline bool io_ctx_cqe32(struct io_ring_ctx *ctx) +{ + return ctx->flags & IORING_SETUP_CQE32; +} + #endif diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 6fc1c858013d..75bf54e76f3b 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -53,6 +53,9 @@ struct vm_fault; * * IOMAP_F_XATTR indicates that the iomap is for an extended attribute extent * rather than a file data extent. + * + * IOMAP_F_BOUNDARY indicates that I/O and I/O completions for this iomap must + * never be merged with the mapping before it. */ #define IOMAP_F_NEW (1U << 0) #define IOMAP_F_DIRTY (1U << 1) @@ -64,6 +67,7 @@ struct vm_fault; #define IOMAP_F_BUFFER_HEAD 0 #endif /* CONFIG_BUFFER_HEAD */ #define IOMAP_F_XATTR (1U << 5) +#define IOMAP_F_BOUNDARY (1U << 6) /* * Flags set by the core iomap code during operations: @@ -178,6 +182,7 @@ struct iomap_folio_ops { #else #define IOMAP_DAX 0 #endif /* CONFIG_FS_DAX */ +#define IOMAP_ATOMIC (1 << 9) struct iomap_ops { /* @@ -256,12 +261,41 @@ static inline const struct iomap *iomap_iter_srcmap(const struct iomap_iter *i) return &i->iomap; } -ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from, - const struct iomap_ops *ops); -int iomap_file_buffered_write_punch_delalloc(struct inode *inode, - struct iomap *iomap, loff_t pos, loff_t length, ssize_t written, - int (*punch)(struct inode *inode, loff_t pos, loff_t length)); +/* + * Return the file offset for the first unchanged block after a short write. + * + * If nothing was written, round @pos down to point at the first block in + * the range, else round up to include the partially written block. + */ +static inline loff_t iomap_last_written_block(struct inode *inode, loff_t pos, + ssize_t written) +{ + if (unlikely(!written)) + return round_down(pos, i_blocksize(inode)); + return round_up(pos + written, i_blocksize(inode)); +} + +/* + * Check if the range needs to be unshared for a FALLOC_FL_UNSHARE_RANGE + * operation. + * + * Don't bother with blocks that are not shared to start with; or mappings that + * cannot be shared, such as inline data, delalloc reservations, holes or + * unwritten extents. + * + * Note that we use srcmap directly instead of iomap_iter_srcmap as unsharing + * requires providing a separate source map, and the presence of one is a good + * indicator that unsharing is needed, unlike IOMAP_F_SHARED which can be set + * for any data that goes into the COW fork for XFS. + */ +static inline bool iomap_want_unshare_iter(const struct iomap_iter *iter) +{ + return (iter->iomap.flags & IOMAP_F_SHARED) && + iter->srcmap.type == IOMAP_MAPPED; +} +ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from, + const struct iomap_ops *ops, void *private); 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); @@ -277,6 +311,13 @@ int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, const struct iomap_ops *ops); vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops); + +typedef void (*iomap_punch_t)(struct inode *inode, loff_t offset, loff_t length, + struct iomap *iomap); +void iomap_write_delalloc_release(struct inode *inode, loff_t start_byte, + loff_t end_byte, unsigned flags, struct iomap *iomap, + iomap_punch_t punch); + int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len, const struct iomap_ops *ops); loff_t iomap_seek_hole(struct inode *inode, loff_t offset, @@ -294,7 +335,7 @@ struct iomap_ioend { u16 io_type; u16 io_flags; /* IOMAP_F_* */ struct inode *io_inode; /* file being written to */ - size_t io_size; /* size of the extent */ + size_t io_size; /* size of data within eof */ loff_t io_offset; /* offset in the file */ sector_t io_sector; /* start sector of ioend */ struct bio io_bio; /* MUST BE LAST! */ diff --git a/include/linux/iommu-dma.h b/include/linux/iommu-dma.h new file mode 100644 index 000000000000..508beaa44c39 --- /dev/null +++ b/include/linux/iommu-dma.h @@ -0,0 +1,69 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved + * + * DMA operations that map physical memory through IOMMU. + */ +#ifndef _LINUX_IOMMU_DMA_H +#define _LINUX_IOMMU_DMA_H + +#include <linux/dma-direction.h> + +#ifdef CONFIG_IOMMU_DMA +static inline bool use_dma_iommu(struct device *dev) +{ + return dev->dma_iommu; +} +#else +static inline bool use_dma_iommu(struct device *dev) +{ + return false; +} +#endif /* CONFIG_IOMMU_DMA */ + +dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, enum dma_data_direction dir, + unsigned long attrs); +void iommu_dma_unmap_page(struct device *dev, dma_addr_t dma_handle, + size_t size, enum dma_data_direction dir, unsigned long attrs); +int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, + enum dma_data_direction dir, unsigned long attrs); +void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, + enum dma_data_direction dir, unsigned long attrs); +void *iommu_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, + gfp_t gfp, unsigned long attrs); +int iommu_dma_mmap(struct device *dev, struct vm_area_struct *vma, + void *cpu_addr, dma_addr_t dma_addr, size_t size, + unsigned long attrs); +int iommu_dma_get_sgtable(struct device *dev, struct sg_table *sgt, + void *cpu_addr, dma_addr_t dma_addr, size_t size, + unsigned long attrs); +unsigned long iommu_dma_get_merge_boundary(struct device *dev); +size_t iommu_dma_opt_mapping_size(void); +size_t iommu_dma_max_mapping_size(struct device *dev); +void iommu_dma_free(struct device *dev, size_t size, void *cpu_addr, + dma_addr_t handle, unsigned long attrs); +dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys, + size_t size, enum dma_data_direction dir, unsigned long attrs); +void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle, + size_t size, enum dma_data_direction dir, unsigned long attrs); +struct sg_table *iommu_dma_alloc_noncontiguous(struct device *dev, size_t size, + enum dma_data_direction dir, gfp_t gfp, unsigned long attrs); +void iommu_dma_free_noncontiguous(struct device *dev, size_t size, + struct sg_table *sgt, enum dma_data_direction dir); +void *iommu_dma_vmap_noncontiguous(struct device *dev, size_t size, + struct sg_table *sgt); +#define iommu_dma_vunmap_noncontiguous(dev, vaddr) \ + vunmap(vaddr); +int iommu_dma_mmap_noncontiguous(struct device *dev, struct vm_area_struct *vma, + size_t size, struct sg_table *sgt); +void iommu_dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, + size_t size, enum dma_data_direction dir); +void iommu_dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle, + size_t size, enum dma_data_direction dir); +void iommu_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sgl, + int nelems, enum dma_data_direction dir); +void iommu_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sgl, + int nelems, enum dma_data_direction dir); + +#endif /* _LINUX_IOMMU_DMA_H */ diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 2e925b5eba53..38c65e92ecd0 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -42,6 +42,8 @@ struct notifier_block; struct iommu_sva; struct iommu_dma_cookie; struct iommu_fault_param; +struct iommufd_ctx; +struct iommufd_viommu; #define IOMMU_FAULT_PERM_READ (1 << 0) /* read */ #define IOMMU_FAULT_PERM_WRITE (1 << 1) /* write */ @@ -69,8 +71,7 @@ enum iommu_fault_type { struct iommu_fault_page_request { #define IOMMU_FAULT_PAGE_REQUEST_PASID_VALID (1 << 0) #define IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE (1 << 1) -#define IOMMU_FAULT_PAGE_REQUEST_PRIV_DATA (1 << 2) -#define IOMMU_FAULT_PAGE_RESPONSE_NEEDS_PASID (1 << 3) +#define IOMMU_FAULT_PAGE_RESPONSE_NEEDS_PASID (1 << 2) u32 flags; u32 pasid; u32 grpid; @@ -125,12 +126,16 @@ struct iopf_fault { struct iopf_group { struct iopf_fault last_fault; struct list_head faults; + size_t fault_count; /* list node for iommu_fault_param::faults */ struct list_head pending_node; struct work_struct work; - struct iommu_domain *domain; + struct iommu_attach_handle *attach_handle; /* The device's fault data parameter. */ struct iommu_fault_param *fault_param; + /* Used by handler provider to hook the group on its own lists. */ + struct list_head node; + u32 cookie; }; /** @@ -318,6 +323,9 @@ enum iommu_dev_features { #define IOMMU_PASID_INVALID (-1U) typedef unsigned int ioasid_t; +/* Read but do not clear any dirty bits */ +#define IOMMU_DIRTY_NO_CLEAR (1 << 0) + #ifdef CONFIG_IOMMU_API /** @@ -354,9 +362,6 @@ struct iommu_dirty_bitmap { struct iommu_iotlb_gather *gather; }; -/* Read but do not clear any dirty bits */ -#define IOMMU_DIRTY_NO_CLEAR (1 << 0) - /** * struct iommu_dirty_ops - domain specific dirty tracking operations * @set_dirty_tracking: Enable or Disable dirty tracking on the iommu domain @@ -488,7 +493,9 @@ static inline int __iommu_copy_struct_from_user_array( * @index: Index to the location in the array to copy user data from * @min_last: The last member of the data structure @kdst points in the * initial version. - * Return 0 for success, otherwise -error. + * + * Copy a single entry from a user array. Return 0 for success, otherwise + * -error. */ #define iommu_copy_struct_from_user_array(kdst, user_array, data_type, index, \ min_last) \ @@ -497,6 +504,50 @@ static inline int __iommu_copy_struct_from_user_array( offsetofend(typeof(*(kdst)), min_last)) /** + * iommu_copy_struct_from_full_user_array - Copy iommu driver specific user + * space data from an iommu_user_data_array + * @kdst: Pointer to an iommu driver specific user data that is defined in + * include/uapi/linux/iommufd.h + * @kdst_entry_size: sizeof(*kdst) + * @user_array: Pointer to a struct iommu_user_data_array for a user space + * array + * @data_type: The data type of the @kdst. Must match with @user_array->type + * + * Copy the entire user array. kdst must have room for kdst_entry_size * + * user_array->entry_num bytes. Return 0 for success, otherwise -error. + */ +static inline int +iommu_copy_struct_from_full_user_array(void *kdst, size_t kdst_entry_size, + struct iommu_user_data_array *user_array, + unsigned int data_type) +{ + unsigned int i; + int ret; + + if (user_array->type != data_type) + return -EINVAL; + if (!user_array->entry_num) + return -EINVAL; + if (likely(user_array->entry_len == kdst_entry_size)) { + if (copy_from_user(kdst, user_array->uptr, + user_array->entry_num * + user_array->entry_len)) + return -EFAULT; + } + + /* Copy item by item */ + for (i = 0; i != user_array->entry_num; i++) { + ret = copy_struct_from_user( + kdst + kdst_entry_size * i, kdst_entry_size, + user_array->uptr + user_array->entry_len * i, + user_array->entry_len); + if (ret) + return ret; + } + return 0; +} + +/** * struct iommu_ops - iommu ops and capabilities * @capable: check capability * @hw_info: report iommu hardware information. The data buffer returned by this @@ -506,18 +557,19 @@ static inline int __iommu_copy_struct_from_user_array( * @domain_alloc: allocate and return an iommu domain if success. Otherwise * NULL is returned. The domain is not fully initialized until * the caller iommu_domain_alloc() returns. - * @domain_alloc_user: Allocate an iommu domain corresponding to the input - * parameters as defined in include/uapi/linux/iommufd.h. - * Unlike @domain_alloc, it is called only by IOMMUFD and - * must fully initialize the new domain before return. - * Upon success, if the @user_data is valid and the @parent - * points to a kernel-managed domain, the new domain must be - * IOMMU_DOMAIN_NESTED type; otherwise, the @parent must be - * NULL while the @user_data can be optionally provided, the - * new domain must support __IOMMU_DOMAIN_PAGING. - * Upon failure, ERR_PTR must be returned. + * @domain_alloc_paging_flags: Allocate an iommu domain corresponding to the + * input parameters as defined in + * include/uapi/linux/iommufd.h. The @user_data can be + * optionally provided, the new domain must support + * __IOMMU_DOMAIN_PAGING. Upon failure, ERR_PTR must be + * returned. * @domain_alloc_paging: Allocate an iommu_domain that can be used for - * UNMANAGED, DMA, and DMA_FQ domain types. + * UNMANAGED, DMA, and DMA_FQ domain types. This is the + * same as invoking domain_alloc_paging_flags() with + * @flags=0, @user_data=NULL. A driver should implement + * only one of the two ops. + * @domain_alloc_sva: Allocate an iommu_domain for Shared Virtual Addressing. + * @domain_alloc_nested: Allocate an iommu_domain for nested translation. * @probe_device: Add device to iommu driver handling * @release_device: Remove device from iommu driver handling * @probe_finalize: Do final setup work after the device is added to an IOMMU @@ -535,9 +587,14 @@ static inline int __iommu_copy_struct_from_user_array( * - IOMMU_DOMAIN_DMA: must use a dma domain * - 0: use the default setting * @default_domain_ops: the default ops for domains - * @remove_dev_pasid: Remove any translation configurations of a specific - * pasid, so that any DMA transactions with this pasid - * will be blocked by the hardware. + * @viommu_alloc: Allocate an iommufd_viommu on a physical IOMMU instance behind + * the @dev, as the set of virtualization resources shared/passed + * to user space IOMMU instance. And associate it with a nesting + * @parent_domain. The @viommu_type must be defined in the header + * include/uapi/linux/iommufd.h + * It is required to call iommufd_viommu_alloc() helper for + * a bundled allocation of the core and the driver structures, + * using the given @ictx pointer. * @pgsize_bitmap: bitmap of all possible supported page sizes * @owner: Driver module providing these ops * @identity_domain: An always available, always attachable identity @@ -547,6 +604,10 @@ static inline int __iommu_copy_struct_from_user_array( * @default_domain: If not NULL this will always be set as the default domain. * This should be an IDENTITY/BLOCKED/PLATFORM domain. * Do not use in new drivers. + * @user_pasid_table: IOMMU driver supports user-managed PASID table. There is + * no user domain for each PASID and the I/O page faults are + * forwarded through the user domain attached to the device + * RID. */ struct iommu_ops { bool (*capable)(struct device *dev, enum iommu_cap); @@ -554,10 +615,15 @@ struct iommu_ops { /* Domain allocation and freeing by the iommu driver */ struct iommu_domain *(*domain_alloc)(unsigned iommu_domain_type); - struct iommu_domain *(*domain_alloc_user)( - struct device *dev, u32 flags, struct iommu_domain *parent, + struct iommu_domain *(*domain_alloc_paging_flags)( + struct device *dev, u32 flags, const struct iommu_user_data *user_data); struct iommu_domain *(*domain_alloc_paging)(struct device *dev); + struct iommu_domain *(*domain_alloc_sva)(struct device *dev, + struct mm_struct *mm); + struct iommu_domain *(*domain_alloc_nested)( + struct device *dev, struct iommu_domain *parent, u32 flags, + const struct iommu_user_data *user_data); struct iommu_device *(*probe_device)(struct device *dev); void (*release_device)(struct device *dev); @@ -578,7 +644,10 @@ struct iommu_ops { struct iommu_page_response *msg); int (*def_domain_type)(struct device *dev); - void (*remove_dev_pasid)(struct device *dev, ioasid_t pasid); + + struct iommufd_viommu *(*viommu_alloc)( + struct device *dev, struct iommu_domain *parent_domain, + struct iommufd_ctx *ictx, unsigned int viommu_type); const struct iommu_domain_ops *default_domain_ops; unsigned long pgsize_bitmap; @@ -587,6 +656,7 @@ struct iommu_ops { struct iommu_domain *blocked_domain; struct iommu_domain *release_domain; struct iommu_domain *default_domain; + u8 user_pasid_table:1; }; /** @@ -604,7 +674,8 @@ struct iommu_ops { * * EBUSY - device is attached to a domain and cannot be changed * * ENODEV - device specific errors, not able to be attached * * <others> - treated as ENODEV by the caller. Use is discouraged - * @set_dev_pasid: set an iommu domain to a pasid of device + * @set_dev_pasid: set or replace an iommu domain to a pasid of device. The pasid of + * the device should be left in the old config in error case. * @map_pages: map a physically contiguous set of pages of the same size to * an iommu domain. * @unmap_pages: unmap a number of pages of the same size from an iommu domain @@ -623,14 +694,13 @@ struct iommu_ops { * @enforce_cache_coherency: Prevent any kind of DMA from bypassing IOMMU_CACHE, * including no-snoop TLPs on PCIe or other platform * specific mechanisms. - * @enable_nesting: Enable nesting * @set_pgtable_quirks: Set io page table quirks (IO_PGTABLE_QUIRK_*) * @free: Release the domain after use. */ struct iommu_domain_ops { int (*attach_dev)(struct iommu_domain *domain, struct device *dev); int (*set_dev_pasid)(struct iommu_domain *domain, struct device *dev, - ioasid_t pasid); + ioasid_t pasid, struct iommu_domain *old); int (*map_pages)(struct iommu_domain *domain, unsigned long iova, phys_addr_t paddr, size_t pgsize, size_t pgcount, @@ -651,7 +721,6 @@ struct iommu_domain_ops { dma_addr_t iova); bool (*enforce_cache_coherency)(struct iommu_domain *domain); - int (*enable_nesting)(struct iommu_domain *domain); int (*set_pgtable_quirks)(struct iommu_domain *domain, unsigned long quirks); @@ -772,18 +841,18 @@ static inline void iommu_iotlb_gather_init(struct iommu_iotlb_gather *gather) }; } -extern int bus_iommu_probe(const struct bus_type *bus); -extern bool iommu_present(const 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(const struct bus_type *bus); +struct iommu_domain *iommu_paging_domain_alloc_flags(struct device *dev, unsigned int flags); +static inline struct iommu_domain *iommu_paging_domain_alloc(struct device *dev) +{ + return iommu_paging_domain_alloc_flags(dev, 0); +} extern void iommu_domain_free(struct iommu_domain *domain); extern int iommu_attach_device(struct iommu_domain *domain, struct device *dev); extern void iommu_detach_device(struct iommu_domain *domain, struct device *dev); -extern int iommu_sva_unbind_gpasid(struct iommu_domain *domain, - struct device *dev, ioasid_t pasid); 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, @@ -833,7 +902,6 @@ extern void iommu_group_put(struct iommu_group *group); extern int iommu_group_id(struct iommu_group *group); extern struct iommu_domain *iommu_group_default_domain(struct iommu_group *); -int iommu_enable_nesting(struct iommu_domain *domain); int iommu_set_pgtable_quirks(struct iommu_domain *domain, unsigned long quirks); @@ -965,7 +1033,6 @@ extern struct iommu_group *generic_single_device_group(struct device *dev); /** * struct iommu_fwspec - per-device IOMMU instance data - * @ops: ops for this device's IOMMU * @iommu_fwnode: firmware handle for this device's IOMMU * @flags: IOMMU_FWSPEC_* flags * @num_ids: number of associated device IDs @@ -976,7 +1043,6 @@ extern struct iommu_group *generic_single_device_group(struct device *dev); * consumers. */ struct iommu_fwspec { - const struct iommu_ops *ops; struct fwnode_handle *iommu_fwnode; u32 flags; unsigned int num_ids; @@ -985,28 +1051,36 @@ struct iommu_fwspec { /* ATS is supported */ #define IOMMU_FWSPEC_PCI_RC_ATS (1 << 0) +/* CANWBS is supported */ +#define IOMMU_FWSPEC_PCI_RC_CANWBS (1 << 1) + +/* + * An iommu attach handle represents a relationship between an iommu domain + * and a PASID or RID of a device. It is allocated and managed by the component + * that manages the domain and is stored in the iommu group during the time the + * domain is attached. + */ +struct iommu_attach_handle { + struct iommu_domain *domain; +}; /** * struct iommu_sva - handle to a device-mm bond */ struct iommu_sva { + struct iommu_attach_handle handle; struct device *dev; - struct iommu_domain *domain; - struct list_head handle_item; refcount_t users; }; struct iommu_mm_data { u32 pasid; struct list_head sva_domains; - struct list_head sva_handles; }; -int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode, - const struct iommu_ops *ops); +int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode); void iommu_fwspec_free(struct device *dev); int iommu_fwspec_add_ids(struct device *dev, const u32 *ids, int num_ids); -const struct iommu_ops *iommu_ops_from_fwnode(const struct fwnode_handle *fwnode); static inline struct iommu_fwspec *dev_iommu_fwspec_get(struct device *dev) { @@ -1049,12 +1123,10 @@ int iommu_device_claim_dma_owner(struct device *dev, void *owner); void iommu_device_release_dma_owner(struct device *dev); int iommu_attach_device_pasid(struct iommu_domain *domain, - struct device *dev, ioasid_t pasid); + struct device *dev, ioasid_t pasid, + struct iommu_attach_handle *handle); void iommu_detach_device_pasid(struct iommu_domain *domain, struct device *dev, ioasid_t pasid); -struct iommu_domain * -iommu_get_domain_for_dev_pasid(struct device *dev, ioasid_t pasid, - unsigned int type); ioasid_t iommu_alloc_global_pasid(struct device *dev); void iommu_free_global_pasid(ioasid_t pasid); #else /* CONFIG_IOMMU_API */ @@ -1068,19 +1140,20 @@ struct iommu_iotlb_gather {}; struct iommu_dirty_bitmap {}; struct iommu_dirty_ops {}; -static inline bool iommu_present(const struct bus_type *bus) +static inline bool device_iommu_capable(struct device *dev, enum iommu_cap cap) { return false; } -static inline bool device_iommu_capable(struct device *dev, enum iommu_cap cap) +static inline struct iommu_domain *iommu_paging_domain_alloc_flags(struct device *dev, + unsigned int flags) { - return false; + return ERR_PTR(-ENODEV); } -static inline struct iommu_domain *iommu_domain_alloc(const struct bus_type *bus) +static inline struct iommu_domain *iommu_paging_domain_alloc(struct device *dev) { - return NULL; + return ERR_PTR(-ENODEV); } static inline void iommu_domain_free(struct iommu_domain *domain) @@ -1312,8 +1385,7 @@ static inline void iommu_device_unlink(struct device *dev, struct device *link) } static inline int iommu_fwspec_init(struct device *dev, - struct fwnode_handle *iommu_fwnode, - const struct iommu_ops *ops) + struct fwnode_handle *iommu_fwnode) { return -ENODEV; } @@ -1328,12 +1400,6 @@ static inline int iommu_fwspec_add_ids(struct device *dev, u32 *ids, return -ENODEV; } -static inline -const struct iommu_ops *iommu_ops_from_fwnode(const struct fwnode_handle *fwnode) -{ - return NULL; -} - static inline int iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features feat) { @@ -1385,7 +1451,8 @@ static inline int iommu_device_claim_dma_owner(struct device *dev, void *owner) } static inline int iommu_attach_device_pasid(struct iommu_domain *domain, - struct device *dev, ioasid_t pasid) + struct device *dev, ioasid_t pasid, + struct iommu_attach_handle *handle) { return -ENODEV; } @@ -1395,13 +1462,6 @@ static inline void iommu_detach_device_pasid(struct iommu_domain *domain, { } -static inline struct iommu_domain * -iommu_get_domain_for_dev_pasid(struct device *dev, ioasid_t pasid, - unsigned int type) -{ - return NULL; -} - static inline ioasid_t iommu_alloc_global_pasid(struct device *dev) { return IOMMU_PASID_INVALID; @@ -1445,9 +1505,6 @@ static inline void iommu_debugfs_setup(void) {} #ifdef CONFIG_IOMMU_DMA #include <linux/msi.h> -/* Setup call for arch DMA mapping code */ -void iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 dma_limit); - int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base); int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr); @@ -1458,10 +1515,6 @@ void iommu_dma_compose_msi_msg(struct msi_desc *desc, struct msi_msg *msg); struct msi_desc; struct msi_msg; -static inline void iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 dma_limit) -{ -} - static inline int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base) { return -ENODEV; @@ -1531,13 +1584,11 @@ struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm); void iommu_sva_unbind_device(struct iommu_sva *handle); u32 iommu_sva_get_pasid(struct iommu_sva *handle); -struct iommu_domain *iommu_sva_domain_alloc(struct device *dev, - struct mm_struct *mm); #else static inline struct iommu_sva * iommu_sva_bind_device(struct device *dev, struct mm_struct *mm) { - return NULL; + return ERR_PTR(-ENODEV); } static inline void iommu_sva_unbind_device(struct iommu_sva *handle) @@ -1557,12 +1608,6 @@ static inline u32 mm_get_enqcmd_pasid(struct mm_struct *mm) } static inline void mm_pasid_drop(struct mm_struct *mm) {} - -static inline struct iommu_domain * -iommu_sva_domain_alloc(struct device *dev, struct mm_struct *mm) -{ - return NULL; -} #endif /* CONFIG_IOMMU_SVA */ #ifdef CONFIG_IOMMU_IOPF @@ -1573,7 +1618,7 @@ struct iopf_queue *iopf_queue_alloc(const char *name); void iopf_queue_free(struct iopf_queue *queue); int iopf_queue_discard_partial(struct iopf_queue *queue); void iopf_free_group(struct iopf_group *group); -void iommu_report_device_fault(struct device *dev, struct iopf_fault *evt); +int iommu_report_device_fault(struct device *dev, struct iopf_fault *evt); void iopf_group_response(struct iopf_group *group, enum iommu_page_response_code status); #else @@ -1611,9 +1656,10 @@ static inline void iopf_free_group(struct iopf_group *group) { } -static inline void +static inline int iommu_report_device_fault(struct device *dev, struct iopf_fault *evt) { + return -ENODEV; } static inline void iopf_group_response(struct iopf_group *group, diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h index ffc3a949f837..11110c749200 100644 --- a/include/linux/iommufd.h +++ b/include/linux/iommufd.h @@ -6,17 +6,47 @@ #ifndef __LINUX_IOMMUFD_H #define __LINUX_IOMMUFD_H -#include <linux/types.h> -#include <linux/errno.h> #include <linux/err.h> +#include <linux/errno.h> +#include <linux/refcount.h> +#include <linux/types.h> +#include <linux/xarray.h> struct device; -struct iommufd_device; -struct page; -struct iommufd_ctx; -struct iommufd_access; struct file; struct iommu_group; +struct iommu_user_data; +struct iommu_user_data_array; +struct iommufd_access; +struct iommufd_ctx; +struct iommufd_device; +struct iommufd_viommu_ops; +struct page; + +enum iommufd_object_type { + IOMMUFD_OBJ_NONE, + IOMMUFD_OBJ_ANY = IOMMUFD_OBJ_NONE, + IOMMUFD_OBJ_DEVICE, + IOMMUFD_OBJ_HWPT_PAGING, + IOMMUFD_OBJ_HWPT_NESTED, + IOMMUFD_OBJ_IOAS, + IOMMUFD_OBJ_ACCESS, + IOMMUFD_OBJ_FAULT, + IOMMUFD_OBJ_VIOMMU, + IOMMUFD_OBJ_VDEVICE, +#ifdef CONFIG_IOMMUFD_TEST + IOMMUFD_OBJ_SELFTEST, +#endif + IOMMUFD_OBJ_MAX, +}; + +/* Base struct for all objects with a userspace ID handle. */ +struct iommufd_object { + refcount_t shortterm_users; + refcount_t users; + enum iommufd_object_type type; + unsigned int id; +}; struct iommufd_device *iommufd_device_bind(struct iommufd_ctx *ictx, struct device *dev, u32 *id); @@ -54,6 +84,45 @@ void iommufd_access_detach(struct iommufd_access *access); void iommufd_ctx_get(struct iommufd_ctx *ictx); +struct iommufd_viommu { + struct iommufd_object obj; + struct iommufd_ctx *ictx; + struct iommu_device *iommu_dev; + struct iommufd_hwpt_paging *hwpt; + + const struct iommufd_viommu_ops *ops; + + struct xarray vdevs; + + unsigned int type; +}; + +/** + * struct iommufd_viommu_ops - vIOMMU specific operations + * @destroy: Clean up all driver-specific parts of an iommufd_viommu. The memory + * of the vIOMMU will be free-ed by iommufd core after calling this op + * @alloc_domain_nested: Allocate a IOMMU_DOMAIN_NESTED on a vIOMMU that holds a + * nesting parent domain (IOMMU_DOMAIN_PAGING). @user_data + * must be defined in include/uapi/linux/iommufd.h. + * It must fully initialize the new iommu_domain before + * returning. Upon failure, ERR_PTR must be returned. + * @cache_invalidate: Flush hardware cache used by a vIOMMU. It can be used for + * any IOMMU hardware specific cache: TLB and device cache. + * The @array passes in the cache invalidation requests, in + * form of a driver data structure. A driver must update the + * array->entry_num to report the number of handled requests. + * The data structure of the array entry must be defined in + * include/uapi/linux/iommufd.h + */ +struct iommufd_viommu_ops { + void (*destroy)(struct iommufd_viommu *viommu); + struct iommu_domain *(*alloc_domain_nested)( + struct iommufd_viommu *viommu, u32 flags, + const struct iommu_user_data *user_data); + int (*cache_invalidate)(struct iommufd_viommu *viommu, + struct iommu_user_data_array *array); +}; + #if IS_ENABLED(CONFIG_IOMMUFD) struct iommufd_ctx *iommufd_ctx_from_file(struct file *file); struct iommufd_ctx *iommufd_ctx_from_fd(int fd); @@ -111,4 +180,43 @@ static inline int iommufd_vfio_compat_set_no_iommu(struct iommufd_ctx *ictx) return -EOPNOTSUPP; } #endif /* CONFIG_IOMMUFD */ + +#if IS_ENABLED(CONFIG_IOMMUFD_DRIVER_CORE) +struct iommufd_object *_iommufd_object_alloc(struct iommufd_ctx *ictx, + size_t size, + enum iommufd_object_type type); +struct device *iommufd_viommu_find_dev(struct iommufd_viommu *viommu, + unsigned long vdev_id); +#else /* !CONFIG_IOMMUFD_DRIVER_CORE */ +static inline struct iommufd_object * +_iommufd_object_alloc(struct iommufd_ctx *ictx, size_t size, + enum iommufd_object_type type) +{ + return ERR_PTR(-EOPNOTSUPP); +} + +static inline struct device * +iommufd_viommu_find_dev(struct iommufd_viommu *viommu, unsigned long vdev_id) +{ + return NULL; +} +#endif /* CONFIG_IOMMUFD_DRIVER_CORE */ + +/* + * Helpers for IOMMU driver to allocate driver structures that will be freed by + * the iommufd core. The free op will be called prior to freeing the memory. + */ +#define iommufd_viommu_alloc(ictx, drv_struct, member, viommu_ops) \ + ({ \ + drv_struct *ret; \ + \ + static_assert(__same_type(struct iommufd_viommu, \ + ((drv_struct *)NULL)->member)); \ + static_assert(offsetof(drv_struct, member.obj) == 0); \ + ret = (drv_struct *)_iommufd_object_alloc( \ + ictx, sizeof(drv_struct), IOMMUFD_OBJ_VIOMMU); \ + if (!IS_ERR(ret)) \ + ret->member.ops = viommu_ops; \ + ret; \ + }) #endif diff --git a/include/linux/iopoll.h b/include/linux/iopoll.h index 19a7b00baff4..91324c331a4b 100644 --- a/include/linux/iopoll.h +++ b/include/linux/iopoll.h @@ -19,19 +19,19 @@ * @op: accessor function (takes @args as its arguments) * @val: Variable to read the value into * @cond: Break condition (usually involving @val) - * @sleep_us: Maximum time to sleep between reads in us (0 - * tight-loops). Should be less than ~20ms since usleep_range - * is used (see Documentation/timers/timers-howto.rst). + * @sleep_us: Maximum time to sleep between reads in us (0 tight-loops). Please + * read usleep_range() function description for details and + * limitations. * @timeout_us: Timeout in us, 0 means never timeout * @sleep_before_read: if it is true, sleep @sleep_us before read. * @args: arguments for @op poll * - * Returns 0 on success and -ETIMEDOUT upon a timeout. In either - * case, the last read value at @args is stored in @val. Must not - * be called from atomic context if sleep_us or timeout_us are used. - * * When available, you'll probably want to use one of the specialized * macros defined below rather than this macro directly. + * + * Returns: 0 on success and -ETIMEDOUT upon a timeout. In either + * case, the last read value at @args is stored in @val. Must not + * be called from atomic context if sleep_us or timeout_us are used. */ #define read_poll_timeout(op, val, cond, sleep_us, timeout_us, \ sleep_before_read, args...) \ @@ -64,22 +64,22 @@ * @op: accessor function (takes @args as its arguments) * @val: Variable to read the value into * @cond: Break condition (usually involving @val) - * @delay_us: Time to udelay between reads in us (0 tight-loops). Should - * be less than ~10us since udelay is used (see - * Documentation/timers/timers-howto.rst). + * @delay_us: Time to udelay between reads in us (0 tight-loops). Please + * read udelay() function description for details and + * limitations. * @timeout_us: Timeout in us, 0 means never timeout * @delay_before_read: if it is true, delay @delay_us before read. * @args: arguments for @op poll * - * Returns 0 on success and -ETIMEDOUT upon a timeout. In either - * case, the last read value at @args is stored in @val. - * * This macro does not rely on timekeeping. Hence it is safe to call even when * timekeeping is suspended, at the expense of an underestimation of wall clock * time, which is rather minimal with a non-zero delay_us. * * When available, you'll probably want to use one of the specialized * macros defined below rather than this macro directly. + * + * Returns: 0 on success and -ETIMEDOUT upon a timeout. In either + * case, the last read value at @args is stored in @val. */ #define read_poll_timeout_atomic(op, val, cond, delay_us, timeout_us, \ delay_before_read, args...) \ @@ -119,17 +119,17 @@ * @addr: Address to poll * @val: Variable to read the value into * @cond: Break condition (usually involving @val) - * @sleep_us: Maximum time to sleep between reads in us (0 - * tight-loops). Should be less than ~20ms since usleep_range - * is used (see Documentation/timers/timers-howto.rst). + * @sleep_us: Maximum time to sleep between reads in us (0 tight-loops). Please + * read usleep_range() function description for details and + * limitations. * @timeout_us: Timeout in us, 0 means never timeout * - * Returns 0 on success and -ETIMEDOUT upon a timeout. In either - * case, the last read value at @addr is stored in @val. Must not - * be called from atomic context if sleep_us or timeout_us are used. - * * When available, you'll probably want to use one of the specialized * macros defined below rather than this macro directly. + * + * Returns: 0 on success and -ETIMEDOUT upon a timeout. In either + * case, the last read value at @addr is stored in @val. Must not + * be called from atomic context if sleep_us or timeout_us are used. */ #define readx_poll_timeout(op, addr, val, cond, sleep_us, timeout_us) \ read_poll_timeout(op, val, cond, sleep_us, timeout_us, false, addr) @@ -140,16 +140,16 @@ * @addr: Address to poll * @val: Variable to read the value into * @cond: Break condition (usually involving @val) - * @delay_us: Time to udelay between reads in us (0 tight-loops). Should - * be less than ~10us since udelay is used (see - * Documentation/timers/timers-howto.rst). + * @delay_us: Time to udelay between reads in us (0 tight-loops). Please + * read udelay() function description for details and + * limitations. * @timeout_us: Timeout in us, 0 means never timeout * - * Returns 0 on success and -ETIMEDOUT upon a timeout. In either - * case, the last read value at @addr is stored in @val. - * * When available, you'll probably want to use one of the specialized * macros defined below rather than this macro directly. + * + * Returns: 0 on success and -ETIMEDOUT upon a timeout. In either + * case, the last read value at @addr is stored in @val. */ #define readx_poll_timeout_atomic(op, addr, val, cond, delay_us, timeout_us) \ read_poll_timeout_atomic(op, val, cond, delay_us, timeout_us, false, addr) diff --git a/include/linux/ioport.h b/include/linux/ioport.h index db7fe25f3370..5385349f0b8a 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -188,6 +188,42 @@ enum { #define DEFINE_RES_DMA(_dma) \ DEFINE_RES_DMA_NAMED((_dma), NULL) +/** + * typedef resource_alignf - Resource alignment callback + * @data: Private data used by the callback + * @res: Resource candidate range (an empty resource space) + * @size: The minimum size of the empty space + * @align: Alignment from the constraints + * + * Callback allows calculating resource placement and alignment beyond min, + * max, and align fields in the struct resource_constraint. + * + * Return: Start address for the resource. + */ +typedef resource_size_t (*resource_alignf)(void *data, + const struct resource *res, + resource_size_t size, + resource_size_t align); + +/** + * struct resource_constraint - constraints to be met while searching empty + * resource space + * @min: The minimum address for the memory range + * @max: The maximum address for the memory range + * @align: Alignment for the start address of the empty space + * @alignf: Additional alignment constraints callback + * @alignf_data: Data provided for @alignf callback + * + * Contains the range and alignment constraints that have to be met during + * find_resource_space(). @alignf can be NULL indicating no alignment beyond + * @align is necessary. + */ +struct resource_constraint { + resource_size_t min, max, align; + resource_alignf alignf; + void *alignf_data; +}; + /* PC/ISA/whatever - the normal PC address spaces: IO and memory */ extern struct resource ioport_resource; extern struct resource iomem_resource; @@ -207,15 +243,44 @@ extern void arch_remove_reservations(struct resource *avail); extern int allocate_resource(struct resource *root, struct resource *new, resource_size_t size, resource_size_t min, resource_size_t max, resource_size_t align, - resource_size_t (*alignf)(void *, - const struct resource *, - resource_size_t, - resource_size_t), + resource_alignf alignf, void *alignf_data); struct resource *lookup_resource(struct resource *root, resource_size_t start); int adjust_resource(struct resource *res, resource_size_t start, resource_size_t size); resource_size_t resource_alignment(struct resource *res); + +/** + * resource_set_size - Calculate resource end address from size and start + * @res: Resource descriptor + * @size: Size of the resource + * + * Calculate the end address for @res based on @size. + * + * Note: The start address of @res must be set when calling this function. + * Prefer resource_set_range() if setting both the start address and @size. + */ +static inline void resource_set_size(struct resource *res, resource_size_t size) +{ + res->end = res->start + size - 1; +} + +/** + * resource_set_range - Set resource start and end addresses + * @res: Resource descriptor + * @start: Start address for the resource + * @size: Size of the resource + * + * Set @res start address and calculate the end address based on @size. + */ +static inline void resource_set_range(struct resource *res, + resource_size_t start, + resource_size_t size) +{ + res->start = start; + resource_set_size(res, size); +} + static inline resource_size_t resource_size(const struct resource *res) { return res->end - res->start + 1; @@ -264,6 +329,9 @@ static inline bool resource_union(const struct resource *r1, const struct resour return true; } +int find_resource_space(struct resource *root, struct resource *new, + resource_size_t size, struct resource_constraint *constraint); + /* Convenience shorthand with allocation */ #define request_region(start,n,name) __request_region(&ioport_resource, (start), (n), (name), 0) #define request_muxed_region(start,n,name) __request_region(&ioport_resource, (start), (n), (name), IORESOURCE_MUXED) diff --git a/include/linux/ioprio.h b/include/linux/ioprio.h index db1249cd9692..b25377b6ea98 100644 --- a/include/linux/ioprio.h +++ b/include/linux/ioprio.h @@ -40,7 +40,7 @@ static inline int task_nice_ioclass(struct task_struct *task) { if (task->policy == SCHED_IDLE) return IOPRIO_CLASS_IDLE; - else if (task_is_realtime(task)) + else if (rt_or_dl_task_policy(task)) return IOPRIO_CLASS_RT; else return IOPRIO_CLASS_BE; diff --git a/include/linux/ioremap.h b/include/linux/ioremap.h index f0e99fc7dd8b..2bd1661fe9ad 100644 --- a/include/linux/ioremap.h +++ b/include/linux/ioremap.h @@ -4,6 +4,7 @@ #include <linux/kasan.h> #include <asm/pgtable.h> +#include <asm/vmalloc.h> #if defined(CONFIG_HAS_IOMEM) || defined(CONFIG_GENERIC_IOREMAP) /* diff --git a/include/linux/iov_iter.h b/include/linux/iov_iter.h index 270454a6703d..c4aa58032faf 100644 --- a/include/linux/iov_iter.h +++ b/include/linux/iov_iter.h @@ -10,6 +10,7 @@ #include <linux/uio.h> #include <linux/bvec.h> +#include <linux/folio_queue.h> typedef size_t (*iov_step_f)(void *iter_base, size_t progress, size_t len, void *priv, void *priv2); @@ -141,6 +142,60 @@ size_t iterate_bvec(struct iov_iter *iter, size_t len, void *priv, void *priv2, } /* + * Handle ITER_FOLIOQ. + */ +static __always_inline +size_t iterate_folioq(struct iov_iter *iter, size_t len, void *priv, void *priv2, + iov_step_f step) +{ + const struct folio_queue *folioq = iter->folioq; + unsigned int slot = iter->folioq_slot; + size_t progress = 0, skip = iter->iov_offset; + + if (slot == folioq_nr_slots(folioq)) { + /* The iterator may have been extended. */ + folioq = folioq->next; + slot = 0; + } + + do { + struct folio *folio = folioq_folio(folioq, slot); + size_t part, remain, consumed; + size_t fsize; + void *base; + + if (!folio) + break; + + fsize = folioq_folio_size(folioq, slot); + base = kmap_local_folio(folio, skip); + part = umin(len, PAGE_SIZE - skip % PAGE_SIZE); + remain = step(base, progress, part, priv, priv2); + kunmap_local(base); + consumed = part - remain; + len -= consumed; + progress += consumed; + skip += consumed; + if (skip >= fsize) { + skip = 0; + slot++; + if (slot == folioq_nr_slots(folioq) && folioq->next) { + folioq = folioq->next; + slot = 0; + } + } + if (remain) + break; + } while (len); + + iter->folioq_slot = slot; + iter->folioq = folioq; + iter->iov_offset = skip; + iter->count -= progress; + return progress; +} + +/* * Handle ITER_XARRAY. */ static __always_inline @@ -249,6 +304,8 @@ size_t iterate_and_advance2(struct iov_iter *iter, size_t len, void *priv, return iterate_bvec(iter, len, priv, priv2, step); if (iov_iter_is_kvec(iter)) return iterate_kvec(iter, len, priv, priv2, step); + if (iov_iter_is_folioq(iter)) + return iterate_folioq(iter, len, priv, priv2, step); if (iov_iter_is_xarray(iter)) return iterate_xarray(iter, len, priv, priv2, step); return iterate_discard(iter, len, priv, priv2, step); @@ -271,4 +328,51 @@ size_t iterate_and_advance(struct iov_iter *iter, size_t len, void *priv, return iterate_and_advance2(iter, len, priv, NULL, ustep, step); } +/** + * iterate_and_advance_kernel - Iterate over a kernel-internal iterator + * @iter: The iterator to iterate over. + * @len: The amount to iterate over. + * @priv: Data for the step functions. + * @priv2: More data for the step functions. + * @step: Function for other iterators; given kernel addresses. + * + * Iterate over the next part of an iterator, up to the specified length. The + * buffer is presented in segments, which for kernel iteration are broken up by + * physical pages and mapped, with the mapped address being presented. + * + * [!] Note This will only handle BVEC, KVEC, FOLIOQ, XARRAY and DISCARD-type + * iterators; it will not handle UBUF or IOVEC-type iterators. + * + * A step functions, @step, must be provided, one for handling mapped kernel + * addresses and the other is given user addresses which have the potential to + * fault since no pinning is performed. + * + * The step functions are passed the address and length of the segment, @priv, + * @priv2 and the amount of data so far iterated over (which can, for example, + * be added to @priv to point to the right part of a second buffer). The step + * functions should return the amount of the segment they didn't process (ie. 0 + * indicates complete processsing). + * + * This function returns the amount of data processed (ie. 0 means nothing was + * processed and the value of @len means processes to completion). + */ +static __always_inline +size_t iterate_and_advance_kernel(struct iov_iter *iter, size_t len, void *priv, + void *priv2, iov_step_f step) +{ + if (unlikely(iter->count < len)) + len = iter->count; + if (unlikely(!len)) + return 0; + if (iov_iter_is_bvec(iter)) + return iterate_bvec(iter, len, priv, priv2, step); + if (iov_iter_is_kvec(iter)) + return iterate_kvec(iter, len, priv, priv2, step); + if (iov_iter_is_folioq(iter)) + return iterate_folioq(iter, len, priv, priv2, step); + if (iov_iter_is_xarray(iter)) + return iterate_xarray(iter, len, priv, priv2, step); + return iterate_discard(iter, len, priv, priv2, step); +} + #endif /* _LINUX_IOV_ITER_H */ diff --git a/include/linux/iova.h b/include/linux/iova.h index 83c00fac2acb..d2c4fd923efa 100644 --- a/include/linux/iova.h +++ b/include/linux/iova.h @@ -65,6 +65,11 @@ static inline size_t iova_align(struct iova_domain *iovad, size_t size) return ALIGN(size, iovad->granule); } +static inline size_t iova_align_down(struct iova_domain *iovad, size_t size) +{ + return ALIGN_DOWN(size, iovad->granule); +} + static inline dma_addr_t iova_dma_addr(struct iova_domain *iovad, struct iova *iova) { return (dma_addr_t)iova->pfn_lo << iova_shift(iovad); diff --git a/include/linux/ipmi.h b/include/linux/ipmi.h index a1c9c0d48ebf..2f74dd90c271 100644 --- a/include/linux/ipmi.h +++ b/include/linux/ipmi.h @@ -126,7 +126,7 @@ int ipmi_create_user(unsigned int if_num, * the users before you destroy the callback structures, it should be * safe, too. */ -int ipmi_destroy_user(struct ipmi_user *user); +void ipmi_destroy_user(struct ipmi_user *user); /* Get the IPMI version of the BMC we are talking to. */ int ipmi_get_version(struct ipmi_user *user, diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 383a0ea2ab91..a6e2aadbb91b 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -89,6 +89,7 @@ struct ipv6_devconf { __u8 ioam6_enabled; __u8 ndisc_evict_nocarrier; __u8 ra_honor_pio_life; + __u8 ra_honor_pio_pflag; struct ctl_table_header *sysctl_header; }; diff --git a/include/linux/irq.h b/include/linux/irq.h index 97baa937ab5b..8daa17f0107a 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -64,7 +64,6 @@ enum irqchip_irq_state; * IRQ_NOAUTOEN - Interrupt is not automatically enabled in * request/setup_irq() * IRQ_NO_BALANCING - Interrupt cannot be balanced (affinity set) - * IRQ_MOVE_PCNTXT - Interrupt can be migrated from process context * IRQ_NESTED_THREAD - Interrupt nests into another thread * IRQ_PER_CPU_DEVID - Dev_id is a per-cpu variable * IRQ_IS_POLLED - Always polled by another interrupt. Exclude @@ -93,7 +92,6 @@ enum { IRQ_NOREQUEST = (1 << 11), IRQ_NOAUTOEN = (1 << 12), IRQ_NO_BALANCING = (1 << 13), - IRQ_MOVE_PCNTXT = (1 << 14), IRQ_NESTED_THREAD = (1 << 15), IRQ_NOTHREAD = (1 << 16), IRQ_PER_CPU_DEVID = (1 << 17), @@ -105,7 +103,7 @@ enum { #define IRQF_MODIFY_MASK \ (IRQ_TYPE_SENSE_MASK | IRQ_NOPROBE | IRQ_NOREQUEST | \ - IRQ_NOAUTOEN | IRQ_MOVE_PCNTXT | IRQ_LEVEL | IRQ_NO_BALANCING | \ + IRQ_NOAUTOEN | IRQ_LEVEL | IRQ_NO_BALANCING | \ IRQ_PER_CPU | IRQ_NESTED_THREAD | IRQ_NOTHREAD | IRQ_PER_CPU_DEVID | \ IRQ_IS_POLLED | IRQ_DISABLE_UNLAZY | IRQ_HIDDEN) @@ -115,7 +113,7 @@ enum { * Return value for chip->irq_set_affinity() * * IRQ_SET_MASK_OK - OK, core updates irq_common_data.affinity - * IRQ_SET_MASK_NOCPY - OK, chip did update irq_common_data.affinity + * IRQ_SET_MASK_NOCOPY - OK, chip did update irq_common_data.affinity * IRQ_SET_MASK_OK_DONE - Same as IRQ_SET_MASK_OK for core. Special code to * support stacked irqchips, which indicates skipping * all descendant irqchips. @@ -201,8 +199,6 @@ struct irq_data { * IRQD_LEVEL - Interrupt is level triggered * IRQD_WAKEUP_STATE - Interrupt is configured for wakeup * from suspend - * IRQD_MOVE_PCNTXT - Interrupt can be moved in process - * context * IRQD_IRQ_DISABLED - Disabled state of the interrupt * IRQD_IRQ_MASKED - Masked state of the interrupt * IRQD_IRQ_INPROGRESS - In progress state of the interrupt @@ -233,7 +229,6 @@ enum { IRQD_AFFINITY_SET = BIT(12), IRQD_LEVEL = BIT(13), IRQD_WAKEUP_STATE = BIT(14), - IRQD_MOVE_PCNTXT = BIT(15), IRQD_IRQ_DISABLED = BIT(16), IRQD_IRQ_MASKED = BIT(17), IRQD_IRQ_INPROGRESS = BIT(18), @@ -338,11 +333,6 @@ static inline bool irqd_is_wakeup_set(struct irq_data *d) return __irqd_to_state(d) & IRQD_WAKEUP_STATE; } -static inline bool irqd_can_move_in_process_context(struct irq_data *d) -{ - return __irqd_to_state(d) & IRQD_MOVE_PCNTXT; -} - static inline bool irqd_irq_disabled(struct irq_data *d) { return __irqd_to_state(d) & IRQD_IRQ_DISABLED; @@ -567,6 +557,7 @@ struct irq_chip { * in the suspend path if they are in disabled state * IRQCHIP_AFFINITY_PRE_STARTUP: Default affinity update before startup * IRQCHIP_IMMUTABLE: Don't ever change anything in this chip + * IRQCHIP_MOVE_DEFERRED: Move the interrupt in actual interrupt context */ enum { IRQCHIP_SET_TYPE_MASKED = (1 << 0), @@ -581,6 +572,7 @@ enum { IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND = (1 << 9), IRQCHIP_AFFINITY_PRE_STARTUP = (1 << 10), IRQCHIP_IMMUTABLE = (1 << 11), + IRQCHIP_MOVE_DEFERRED = (1 << 12), }; #include <linux/irqdesc.h> @@ -694,6 +686,9 @@ extern int irq_chip_request_resources_parent(struct irq_data *data); extern void irq_chip_release_resources_parent(struct irq_data *data); #endif +/* Disable or mask interrupts during a kernel kexec */ +extern void machine_kexec_mask_interrupts(void); + /* Handling of unhandled and spurious interrupts: */ extern void note_interrupt(struct irq_desc *desc, irqreturn_t action_ret); @@ -991,7 +986,6 @@ void irq_init_desc(unsigned int irq); * @ack: Ack register offset to reg_base * @eoi: Eoi register offset to reg_base * @type: Type configuration register offset to reg_base - * @polarity: Polarity configuration register offset to reg_base */ struct irq_chip_regs { unsigned long enable; @@ -1000,7 +994,6 @@ struct irq_chip_regs { unsigned long ack; unsigned long eoi; unsigned long type; - unsigned long polarity; }; /** @@ -1040,8 +1033,6 @@ struct irq_chip_type { * @irq_base: Interrupt base nr for this chip * @irq_cnt: Number of interrupts handled by this chip * @mask_cache: Cached mask register shared between all chip types - * @type_cache: Cached type register - * @polarity_cache: Cached polarity register * @wake_enabled: Interrupt can wakeup from suspend * @wake_active: Interrupt is marked as an wakeup from suspend source * @num_ct: Number of available irq_chip_type instances (usually 1) @@ -1068,8 +1059,6 @@ struct irq_chip_generic { unsigned int irq_base; unsigned int irq_cnt; u32 mask_cache; - u32 type_cache; - u32 polarity_cache; u32 wake_enabled; u32 wake_active; unsigned int num_ct; @@ -1106,6 +1095,7 @@ enum irq_gc_flags { * @irq_flags_to_set: IRQ* flags to set on irq setup * @irq_flags_to_clear: IRQ* flags to clear on irq setup * @gc_flags: Generic chip specific setup flags + * @exit: Function called on each chip when they are destroyed. * @gc: Array of pointers to generic interrupt chips */ struct irq_domain_chip_generic { @@ -1114,9 +1104,37 @@ struct irq_domain_chip_generic { unsigned int irq_flags_to_clear; unsigned int irq_flags_to_set; enum irq_gc_flags gc_flags; + void (*exit)(struct irq_chip_generic *gc); struct irq_chip_generic *gc[]; }; +/** + * struct irq_domain_chip_generic_info - Generic chip information structure + * @name: Name of the generic interrupt chip + * @handler: Interrupt handler used by the generic interrupt chip + * @irqs_per_chip: Number of interrupts each chip handles (max 32) + * @num_ct: Number of irq_chip_type instances associated with each + * chip + * @irq_flags_to_clear: IRQ_* bits to clear in the mapping function + * @irq_flags_to_set: IRQ_* bits to set in the mapping function + * @gc_flags: Generic chip specific setup flags + * @init: Function called on each chip when they are created. + * Allow to do some additional chip initialisation. + * @exit: Function called on each chip when they are destroyed. + * Allow to do some chip cleanup operation. + */ +struct irq_domain_chip_generic_info { + const char *name; + irq_flow_handler_t handler; + unsigned int irqs_per_chip; + unsigned int num_ct; + unsigned int irq_flags_to_clear; + unsigned int irq_flags_to_set; + enum irq_gc_flags gc_flags; + int (*init)(struct irq_chip_generic *gc); + void (*exit)(struct irq_chip_generic *gc); +}; + /* Generic chip callback functions */ void irq_gc_noop(struct irq_data *d); void irq_gc_mask_disable_reg(struct irq_data *d); @@ -1153,6 +1171,20 @@ int devm_irq_setup_generic_chip(struct device *dev, struct irq_chip_generic *gc, struct irq_chip_generic *irq_get_domain_generic_chip(struct irq_domain *d, unsigned int hw_irq); +#ifdef CONFIG_GENERIC_IRQ_CHIP +int irq_domain_alloc_generic_chips(struct irq_domain *d, + const struct irq_domain_chip_generic_info *info); +void irq_domain_remove_generic_chips(struct irq_domain *d); +#else +static inline int +irq_domain_alloc_generic_chips(struct irq_domain *d, + const struct irq_domain_chip_generic_info *info) +{ + return -EINVAL; +} +static inline void irq_domain_remove_generic_chips(struct irq_domain *d) { } +#endif /* CONFIG_GENERIC_IRQ_CHIP */ + int __irq_alloc_domain_generic_chips(struct irq_domain *d, int irqs_per_chip, int num_ct, const char *name, irq_flow_handler_t handler, diff --git a/include/linux/irq_sim.h b/include/linux/irq_sim.h index ab831e5ae748..89b4d8ff274b 100644 --- a/include/linux/irq_sim.h +++ b/include/linux/irq_sim.h @@ -16,11 +16,28 @@ * requested like normal irqs and enqueued from process context. */ +struct irq_sim_ops { + int (*irq_sim_irq_requested)(struct irq_domain *domain, + irq_hw_number_t hwirq, void *data); + void (*irq_sim_irq_released)(struct irq_domain *domain, + irq_hw_number_t hwirq, void *data); +}; + struct irq_domain *irq_domain_create_sim(struct fwnode_handle *fwnode, unsigned int num_irqs); struct irq_domain *devm_irq_domain_create_sim(struct device *dev, struct fwnode_handle *fwnode, unsigned int num_irqs); +struct irq_domain *irq_domain_create_sim_full(struct fwnode_handle *fwnode, + unsigned int num_irqs, + const struct irq_sim_ops *ops, + void *data); +struct irq_domain * +devm_irq_domain_create_sim_full(struct device *dev, + struct fwnode_handle *fwnode, + unsigned int num_irqs, + const struct irq_sim_ops *ops, + void *data); void irq_domain_remove_sim(struct irq_domain *domain); #endif /* _LINUX_IRQ_SIM_H */ diff --git a/include/linux/irqchip/arm-gic-common.h b/include/linux/irqchip/arm-gic-common.h index 1177f3a1aed5..fc0246cc05ac 100644 --- a/include/linux/irqchip/arm-gic-common.h +++ b/include/linux/irqchip/arm-gic-common.h @@ -10,10 +10,6 @@ #include <linux/irqchip/arm-vgic-info.h> #define GICD_INT_DEF_PRI 0xa0 -#define GICD_INT_DEF_PRI_X4 ((GICD_INT_DEF_PRI << 24) |\ - (GICD_INT_DEF_PRI << 16) |\ - (GICD_INT_DEF_PRI << 8) |\ - GICD_INT_DEF_PRI) struct irq_domain; struct fwnode_handle; diff --git a/include/linux/irqchip/arm-gic-v3-prio.h b/include/linux/irqchip/arm-gic-v3-prio.h new file mode 100644 index 000000000000..44157c9abb78 --- /dev/null +++ b/include/linux/irqchip/arm-gic-v3-prio.h @@ -0,0 +1,52 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __LINUX_IRQCHIP_ARM_GIC_V3_PRIO_H +#define __LINUX_IRQCHIP_ARM_GIC_V3_PRIO_H + +/* + * GIC priorities from the view of the PMR/RPR. + * + * These values are chosen to be valid in either the absolute priority space or + * the NS view of the priority space. The value programmed into the distributor + * and ITS will be chosen at boot time such that these values appear in the + * PMR/RPR. + * + * GICV3_PRIO_UNMASKED is the PMR view of the priority to use to permit both + * IRQs and pseudo-NMIs. + * + * GICV3_PRIO_IRQ is the PMR view of the priority of regular interrupts. This + * can be written to the PMR to mask regular IRQs. + * + * GICV3_PRIO_NMI is the PMR view of the priority of pseudo-NMIs. This can be + * written to the PMR to mask pseudo-NMIs. + * + * On arm64 some code sections either automatically switch back to PSR.I or + * explicitly require to not use priority masking. If bit GICV3_PRIO_PSR_I_SET + * is included in the priority mask, it indicates that PSR.I should be set and + * interrupt disabling temporarily does not rely on IRQ priorities. + */ +#define GICV3_PRIO_UNMASKED 0xe0 +#define GICV3_PRIO_IRQ 0xc0 +#define GICV3_PRIO_NMI 0x80 + +#define GICV3_PRIO_PSR_I_SET (1 << 4) + +#ifndef __ASSEMBLER__ + +#define __gicv3_prio_to_ns(p) (0xff & ((p) << 1)) +#define __gicv3_ns_to_prio(ns) (0x80 | ((ns) >> 1)) + +#define __gicv3_prio_valid_ns(p) \ + (__gicv3_ns_to_prio(__gicv3_prio_to_ns(p)) == (p)) + +static_assert(__gicv3_prio_valid_ns(GICV3_PRIO_NMI)); +static_assert(__gicv3_prio_valid_ns(GICV3_PRIO_IRQ)); + +static_assert(GICV3_PRIO_NMI < GICV3_PRIO_IRQ); +static_assert(GICV3_PRIO_IRQ < GICV3_PRIO_UNMASKED); + +static_assert(GICV3_PRIO_IRQ < (GICV3_PRIO_IRQ | GICV3_PRIO_PSR_I_SET)); + +#endif /* __ASSEMBLER */ + +#endif /* __LINUX_IRQCHIP_ARM_GIC_V3_PRIO_H */ diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 728691365464..70c0948f978e 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -638,7 +638,7 @@ struct fwnode_handle; int __init its_lpi_memreserve_init(void); int its_cpu_init(void); int its_init(struct fwnode_handle *handle, struct rdists *rdists, - struct irq_domain *domain); + struct irq_domain *domain, u8 irq_prio); int mbi_init(struct fwnode_handle *fwnode, struct irq_domain *parent); static inline bool gic_enable_sre(void) diff --git a/include/linux/irqchip/arm-gic-v4.h b/include/linux/irqchip/arm-gic-v4.h index 2c63375bbd43..7f1f11a5e4e4 100644 --- a/include/linux/irqchip/arm-gic-v4.h +++ b/include/linux/irqchip/arm-gic-v4.h @@ -25,6 +25,14 @@ struct its_vm { irq_hw_number_t db_lpi_base; unsigned long *db_bitmap; int nr_db_lpis; + /* + * Ensures mutual exclusion between updates to vlpi_count[] + * and map/unmap when using the ITSList mechanism. + * + * The lock order for any sequence involving the ITSList is + * vmapp_lock -> vpe_lock ->vmovp_lock. + */ + raw_spinlock_t vmapp_lock; u32 vlpi_count[GICv4_ITS_LIST_MAX]; }; @@ -58,10 +66,12 @@ struct its_vpe { bool enabled; bool group; } sgi_config[16]; - atomic_t vmapp_count; }; }; + /* Track the VPE being mapped */ + atomic_t vmapp_count; + /* * Ensures mutual exclusion between affinity setting of the * vPE and vLPI operations using vpe->col_idx. diff --git a/include/linux/irqchip/irq-partition-percpu.h b/include/linux/irqchip/irq-partition-percpu.h index 2f6ae7551748..b35ee22c278f 100644 --- a/include/linux/irqchip/irq-partition-percpu.h +++ b/include/linux/irqchip/irq-partition-percpu.h @@ -8,7 +8,7 @@ #define __LINUX_IRQCHIP_IRQ_PARTITION_PERCPU_H #include <linux/fwnode.h> -#include <linux/cpumask.h> +#include <linux/cpumask_types.h> #include <linux/irqdomain.h> struct partition_affinity { diff --git a/include/linux/irqchip/riscv-aplic.h b/include/linux/irqchip/riscv-aplic.h new file mode 100644 index 000000000000..ec8f7df50583 --- /dev/null +++ b/include/linux/irqchip/riscv-aplic.h @@ -0,0 +1,145 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2021 Western Digital Corporation or its affiliates. + * Copyright (C) 2022 Ventana Micro Systems Inc. + */ +#ifndef __LINUX_IRQCHIP_RISCV_APLIC_H +#define __LINUX_IRQCHIP_RISCV_APLIC_H + +#include <linux/bitops.h> + +#define APLIC_MAX_IDC BIT(14) +#define APLIC_MAX_SOURCE 1024 + +#define APLIC_DOMAINCFG 0x0000 +#define APLIC_DOMAINCFG_RDONLY 0x80000000 +#define APLIC_DOMAINCFG_IE BIT(8) +#define APLIC_DOMAINCFG_DM BIT(2) +#define APLIC_DOMAINCFG_BE BIT(0) + +#define APLIC_SOURCECFG_BASE 0x0004 +#define APLIC_SOURCECFG_D BIT(10) +#define APLIC_SOURCECFG_CHILDIDX_MASK 0x000003ff +#define APLIC_SOURCECFG_SM_MASK 0x00000007 +#define APLIC_SOURCECFG_SM_INACTIVE 0x0 +#define APLIC_SOURCECFG_SM_DETACH 0x1 +#define APLIC_SOURCECFG_SM_EDGE_RISE 0x4 +#define APLIC_SOURCECFG_SM_EDGE_FALL 0x5 +#define APLIC_SOURCECFG_SM_LEVEL_HIGH 0x6 +#define APLIC_SOURCECFG_SM_LEVEL_LOW 0x7 + +#define APLIC_MMSICFGADDR 0x1bc0 +#define APLIC_MMSICFGADDRH 0x1bc4 +#define APLIC_SMSICFGADDR 0x1bc8 +#define APLIC_SMSICFGADDRH 0x1bcc + +#ifdef CONFIG_RISCV_M_MODE +#define APLIC_xMSICFGADDR APLIC_MMSICFGADDR +#define APLIC_xMSICFGADDRH APLIC_MMSICFGADDRH +#else +#define APLIC_xMSICFGADDR APLIC_SMSICFGADDR +#define APLIC_xMSICFGADDRH APLIC_SMSICFGADDRH +#endif + +#define APLIC_xMSICFGADDRH_L BIT(31) +#define APLIC_xMSICFGADDRH_HHXS_MASK 0x1f +#define APLIC_xMSICFGADDRH_HHXS_SHIFT 24 +#define APLIC_xMSICFGADDRH_HHXS (APLIC_xMSICFGADDRH_HHXS_MASK << \ + APLIC_xMSICFGADDRH_HHXS_SHIFT) +#define APLIC_xMSICFGADDRH_LHXS_MASK 0x7 +#define APLIC_xMSICFGADDRH_LHXS_SHIFT 20 +#define APLIC_xMSICFGADDRH_LHXS (APLIC_xMSICFGADDRH_LHXS_MASK << \ + APLIC_xMSICFGADDRH_LHXS_SHIFT) +#define APLIC_xMSICFGADDRH_HHXW_MASK 0x7 +#define APLIC_xMSICFGADDRH_HHXW_SHIFT 16 +#define APLIC_xMSICFGADDRH_HHXW (APLIC_xMSICFGADDRH_HHXW_MASK << \ + APLIC_xMSICFGADDRH_HHXW_SHIFT) +#define APLIC_xMSICFGADDRH_LHXW_MASK 0xf +#define APLIC_xMSICFGADDRH_LHXW_SHIFT 12 +#define APLIC_xMSICFGADDRH_LHXW (APLIC_xMSICFGADDRH_LHXW_MASK << \ + APLIC_xMSICFGADDRH_LHXW_SHIFT) +#define APLIC_xMSICFGADDRH_BAPPN_MASK 0xfff +#define APLIC_xMSICFGADDRH_BAPPN_SHIFT 0 +#define APLIC_xMSICFGADDRH_BAPPN (APLIC_xMSICFGADDRH_BAPPN_MASK << \ + APLIC_xMSICFGADDRH_BAPPN_SHIFT) + +#define APLIC_xMSICFGADDR_PPN_SHIFT 12 + +#define APLIC_xMSICFGADDR_PPN_HART(__lhxs) \ + (BIT(__lhxs) - 1) + +#define APLIC_xMSICFGADDR_PPN_LHX_MASK(__lhxw) \ + (BIT(__lhxw) - 1) +#define APLIC_xMSICFGADDR_PPN_LHX_SHIFT(__lhxs) \ + ((__lhxs)) +#define APLIC_xMSICFGADDR_PPN_LHX(__lhxw, __lhxs) \ + (APLIC_xMSICFGADDR_PPN_LHX_MASK(__lhxw) << \ + APLIC_xMSICFGADDR_PPN_LHX_SHIFT(__lhxs)) + +#define APLIC_xMSICFGADDR_PPN_HHX_MASK(__hhxw) \ + (BIT(__hhxw) - 1) +#define APLIC_xMSICFGADDR_PPN_HHX_SHIFT(__hhxs) \ + ((__hhxs) + APLIC_xMSICFGADDR_PPN_SHIFT) +#define APLIC_xMSICFGADDR_PPN_HHX(__hhxw, __hhxs) \ + (APLIC_xMSICFGADDR_PPN_HHX_MASK(__hhxw) << \ + APLIC_xMSICFGADDR_PPN_HHX_SHIFT(__hhxs)) + +#define APLIC_IRQBITS_PER_REG 32 + +#define APLIC_SETIP_BASE 0x1c00 +#define APLIC_SETIPNUM 0x1cdc + +#define APLIC_CLRIP_BASE 0x1d00 +#define APLIC_CLRIPNUM 0x1ddc + +#define APLIC_SETIE_BASE 0x1e00 +#define APLIC_SETIENUM 0x1edc + +#define APLIC_CLRIE_BASE 0x1f00 +#define APLIC_CLRIENUM 0x1fdc + +#define APLIC_SETIPNUM_LE 0x2000 +#define APLIC_SETIPNUM_BE 0x2004 + +#define APLIC_GENMSI 0x3000 + +#define APLIC_TARGET_BASE 0x3004 +#define APLIC_TARGET_HART_IDX_SHIFT 18 +#define APLIC_TARGET_HART_IDX_MASK 0x3fff +#define APLIC_TARGET_HART_IDX (APLIC_TARGET_HART_IDX_MASK << \ + APLIC_TARGET_HART_IDX_SHIFT) +#define APLIC_TARGET_GUEST_IDX_SHIFT 12 +#define APLIC_TARGET_GUEST_IDX_MASK 0x3f +#define APLIC_TARGET_GUEST_IDX (APLIC_TARGET_GUEST_IDX_MASK << \ + APLIC_TARGET_GUEST_IDX_SHIFT) +#define APLIC_TARGET_IPRIO_SHIFT 0 +#define APLIC_TARGET_IPRIO_MASK 0xff +#define APLIC_TARGET_IPRIO (APLIC_TARGET_IPRIO_MASK << \ + APLIC_TARGET_IPRIO_SHIFT) +#define APLIC_TARGET_EIID_SHIFT 0 +#define APLIC_TARGET_EIID_MASK 0x7ff +#define APLIC_TARGET_EIID (APLIC_TARGET_EIID_MASK << \ + APLIC_TARGET_EIID_SHIFT) + +#define APLIC_IDC_BASE 0x4000 +#define APLIC_IDC_SIZE 32 + +#define APLIC_IDC_IDELIVERY 0x00 + +#define APLIC_IDC_IFORCE 0x04 + +#define APLIC_IDC_ITHRESHOLD 0x08 + +#define APLIC_IDC_TOPI 0x18 +#define APLIC_IDC_TOPI_ID_SHIFT 16 +#define APLIC_IDC_TOPI_ID_MASK 0x3ff +#define APLIC_IDC_TOPI_ID (APLIC_IDC_TOPI_ID_MASK << \ + APLIC_IDC_TOPI_ID_SHIFT) +#define APLIC_IDC_TOPI_PRIO_SHIFT 0 +#define APLIC_IDC_TOPI_PRIO_MASK 0xff +#define APLIC_IDC_TOPI_PRIO (APLIC_IDC_TOPI_PRIO_MASK << \ + APLIC_IDC_TOPI_PRIO_SHIFT) + +#define APLIC_IDC_CLAIMI 0x1c + +#endif diff --git a/include/linux/irqchip/riscv-imsic.h b/include/linux/irqchip/riscv-imsic.h new file mode 100644 index 000000000000..7494952c5518 --- /dev/null +++ b/include/linux/irqchip/riscv-imsic.h @@ -0,0 +1,96 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2021 Western Digital Corporation or its affiliates. + * Copyright (C) 2022 Ventana Micro Systems Inc. + */ +#ifndef __LINUX_IRQCHIP_RISCV_IMSIC_H +#define __LINUX_IRQCHIP_RISCV_IMSIC_H + +#include <linux/types.h> +#include <linux/bitops.h> +#include <linux/device.h> +#include <linux/fwnode.h> +#include <asm/csr.h> + +#define IMSIC_MMIO_PAGE_SHIFT 12 +#define IMSIC_MMIO_PAGE_SZ BIT(IMSIC_MMIO_PAGE_SHIFT) +#define IMSIC_MMIO_PAGE_LE 0x00 +#define IMSIC_MMIO_PAGE_BE 0x04 + +#define IMSIC_MIN_ID 63 +#define IMSIC_MAX_ID 2048 + +#define IMSIC_EIDELIVERY 0x70 + +#define IMSIC_EITHRESHOLD 0x72 + +#define IMSIC_EIP0 0x80 +#define IMSIC_EIP63 0xbf +#define IMSIC_EIPx_BITS 32 + +#define IMSIC_EIE0 0xc0 +#define IMSIC_EIE63 0xff +#define IMSIC_EIEx_BITS 32 + +#define IMSIC_FIRST IMSIC_EIDELIVERY +#define IMSIC_LAST IMSIC_EIE63 + +#define IMSIC_MMIO_SETIPNUM_LE 0x00 +#define IMSIC_MMIO_SETIPNUM_BE 0x04 + +struct imsic_local_config { + phys_addr_t msi_pa; + void __iomem *msi_va; +}; + +struct imsic_global_config { + /* + * MSI Target Address Scheme + * + * XLEN-1 12 0 + * | | | + * ------------------------------------------------------------- + * |xxxxxx|Group Index|xxxxxxxxxxx|HART Index|Guest Index| 0 | + * ------------------------------------------------------------- + */ + + /* Bits representing Guest index, HART index, and Group index */ + u32 guest_index_bits; + u32 hart_index_bits; + u32 group_index_bits; + u32 group_index_shift; + + /* Global base address matching all target MSI addresses */ + phys_addr_t base_addr; + + /* Number of interrupt identities */ + u32 nr_ids; + + /* Number of guest interrupt identities */ + u32 nr_guest_ids; + + /* Per-CPU IMSIC addresses */ + struct imsic_local_config __percpu *local; +}; + +#ifdef CONFIG_RISCV_IMSIC + +const struct imsic_global_config *imsic_get_global_config(void); + +#else + +static inline const struct imsic_global_config *imsic_get_global_config(void) +{ + return NULL; +} + +#endif + +#ifdef CONFIG_ACPI +int imsic_platform_acpi_probe(struct fwnode_handle *fwnode); +struct fwnode_handle *imsic_acpi_get_fwnode(struct device *dev); +#else +static inline struct fwnode_handle *imsic_acpi_get_fwnode(struct device *dev) { return NULL; } +#endif + +#endif diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index d9451d456a73..fd091c35d572 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -18,6 +18,18 @@ struct irq_domain; struct pt_regs; /** + * struct irqstat - interrupt statistics + * @cnt: real-time interrupt count + * @ref: snapshot of interrupt count + */ +struct irqstat { + unsigned int cnt; +#ifdef CONFIG_GENERIC_IRQ_STAT_SNAPSHOT + unsigned int ref; +#endif +}; + +/** * struct irq_desc - interrupt descriptor * @irq_common_data: per irq and chip data passed down to chip functions * @kstat_irqs: irq stats per cpu @@ -55,7 +67,7 @@ struct pt_regs; struct irq_desc { struct irq_common_data irq_common_data; struct irq_data irq_data; - unsigned int __percpu *kstat_irqs; + struct irqstat __percpu *kstat_irqs; irq_flow_handler_t handle_irq; struct irqaction *action; /* IRQ action list */ unsigned int status_use_accessors; @@ -119,7 +131,7 @@ extern struct irq_desc irq_desc[NR_IRQS]; static inline unsigned int irq_desc_kstat_cpu(struct irq_desc *desc, unsigned int cpu) { - return desc->kstat_irqs ? *per_cpu_ptr(desc->kstat_irqs, cpu) : 0; + return desc->kstat_irqs ? per_cpu(desc->kstat_irqs->cnt, cpu) : 0; } static inline struct irq_desc *irq_data_to_desc(struct irq_data *data) diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 21ecf582a0fe..e432b6a12a32 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -74,11 +74,24 @@ void of_phandle_args_to_fwspec(struct device_node *np, const u32 *args, * struct irq_domain_ops - Methods for irq_domain objects * @match: Match an interrupt controller device node to a host, returns * 1 on a match + * @select: Match an interrupt controller fw specification. It is more generic + * than @match as it receives a complete struct irq_fwspec. Therefore, + * @select is preferred if provided. Returns 1 on a match. * @map: Create or update a mapping between a virtual irq number and a hw * irq number. This is called only once for a given mapping. * @unmap: Dispose of such a mapping * @xlate: Given a device tree node and interrupt specifier, decode * the hardware irq number and linux irq type value. + * @alloc: Allocate @nr_irqs interrupts starting from @virq. + * @free: Free @nr_irqs interrupts starting from @virq. + * @activate: Activate one interrupt in HW (@irqd). If @reserve is set, only + * reserve the vector. If unset, assign the vector (called from + * request_irq()). + * @deactivate: Disarm one interrupt (@irqd). + * @translate: Given @fwspec, decode the hardware irq number (@out_hwirq) and + * linux irq type value (@out_type). This is a generalised @xlate + * (over struct irq_fwspec) and is preferred if provided. + * @debug_show: For domains to show specific data for an interrupt in debugfs. * * Functions below are provided by the driver and called whenever a new mapping * is created or an old mapping is disposed. The driver can then proceed to @@ -131,6 +144,9 @@ struct irq_domain_chip_generic; * Optional elements: * @fwnode: Pointer to firmware node associated with the irq_domain. Pretty easy * to swap it for the of_node via the irq_domain_get_of_node accessor + * @bus_token: @fwnode's device_node might be used for several irq domains. But + * in connection with @bus_token, the pair shall be unique in a + * system. * @gc: Pointer to a list of generic chips. There is a helper function for * setting up one or more generic chips for interrupt controllers * drivers using the generic chip library which uses this pointer. @@ -141,9 +157,12 @@ struct irq_domain_chip_generic; * purposes related to the irq domain. * @parent: Pointer to parent irq_domain to support hierarchy irq_domains * @msi_parent_ops: Pointer to MSI parent domain methods for per device domain init + * @exit: Function called when the domain is destroyed * * Revmap data, used internally by the irq domain code: - * @revmap_size: Size of the linear map table @revmap[] + * @hwirq_max: Top limit for the HW irq number. Especially to avoid + * conflicts/failures with reserved HW irqs. Can be ~0. + * @revmap_size: Size of the linear map table @revmap * @revmap_tree: Radix map tree for hwirqs that don't fit in the linear map * @revmap: Linear table of irq_data pointers */ @@ -169,6 +188,7 @@ struct irq_domain { #ifdef CONFIG_GENERIC_MSI_IRQ const struct msi_parent_ops *msi_parent_ops; #endif + void (*exit)(struct irq_domain *d); /* reverse map data. The linear map gets appended to the irq_domain */ irq_hw_number_t hwirq_max; @@ -182,7 +202,7 @@ enum { /* Irq domain is hierarchical */ IRQ_DOMAIN_FLAG_HIERARCHY = (1 << 0), - /* Irq domain name was allocated in __irq_domain_add() */ + /* Irq domain name was allocated internally */ IRQ_DOMAIN_NAME_ALLOCATED = (1 << 1), /* Irq domain is an IPI domain with virq per cpu */ @@ -208,6 +228,9 @@ enum { /* Irq domain is a MSI device domain */ IRQ_DOMAIN_FLAG_MSI_DEVICE = (1 << 9), + /* Irq domain must destroy generic chips when removed */ + IRQ_DOMAIN_FLAG_DESTROY_GC = (1 << 10), + /* * Flags starting from IRQ_DOMAIN_FLAG_NONCORE are reserved * for implementation specific purposes and ignored by the @@ -257,10 +280,59 @@ static inline struct fwnode_handle *irq_domain_alloc_fwnode(phys_addr_t *pa) } void irq_domain_free_fwnode(struct fwnode_handle *fwnode); -struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, unsigned int size, - irq_hw_number_t hwirq_max, int direct_max, - const struct irq_domain_ops *ops, - void *host_data); + +struct irq_domain_chip_generic_info; + +/** + * struct irq_domain_info - Domain information structure + * @fwnode: firmware node for the interrupt controller + * @domain_flags: Additional flags to add to the domain flags + * @size: Size of linear map; 0 for radix mapping only + * @hwirq_max: Maximum number of interrupts supported by controller + * @direct_max: Maximum value of direct maps; + * Use ~0 for no limit; 0 for no direct mapping + * @hwirq_base: The first hardware interrupt number (legacy domains only) + * @virq_base: The first Linux interrupt number for legacy domains to + * immediately associate the interrupts after domain creation + * @bus_token: Domain bus token + * @name_suffix: Optional name suffix to avoid collisions when multiple + * domains are added using same fwnode + * @ops: Domain operation callbacks + * @host_data: Controller private data pointer + * @dgc_info: Geneneric chip information structure pointer used to + * create generic chips for the domain if not NULL. + * @init: Function called when the domain is created. + * Allow to do some additional domain initialisation. + * @exit: Function called when the domain is destroyed. + * Allow to do some additional cleanup operation. + */ +struct irq_domain_info { + struct fwnode_handle *fwnode; + unsigned int domain_flags; + unsigned int size; + irq_hw_number_t hwirq_max; + int direct_max; + unsigned int hwirq_base; + unsigned int virq_base; + enum irq_domain_bus_token bus_token; + const char *name_suffix; + const struct irq_domain_ops *ops; + void *host_data; +#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY + /** + * @parent: Pointer to the parent irq domain used in a hierarchy domain + */ + struct irq_domain *parent; +#endif + struct irq_domain_chip_generic_info *dgc_info; + int (*init)(struct irq_domain *d); + void (*exit)(struct irq_domain *d); +}; + +struct irq_domain *irq_domain_instantiate(const struct irq_domain_info *info); +struct irq_domain *devm_irq_domain_instantiate(struct device *dev, + const struct irq_domain_info *info); + struct irq_domain *irq_domain_create_simple(struct fwnode_handle *fwnode, unsigned int size, unsigned int first_irq, @@ -293,7 +365,7 @@ static inline struct fwnode_handle *of_node_to_fwnode(struct device_node *node) extern const struct fwnode_operations irqchip_fwnode_ops; -static inline bool is_fwnode_irqchip(struct fwnode_handle *fwnode) +static inline bool is_fwnode_irqchip(const struct fwnode_handle *fwnode) { return fwnode && fwnode->ops == &irqchip_fwnode_ops; } @@ -350,7 +422,17 @@ static inline struct irq_domain *irq_domain_add_linear(struct device_node *of_no const struct irq_domain_ops *ops, void *host_data) { - return __irq_domain_add(of_node_to_fwnode(of_node), size, size, 0, ops, host_data); + struct irq_domain_info info = { + .fwnode = of_node_to_fwnode(of_node), + .size = size, + .hwirq_max = size, + .ops = ops, + .host_data = host_data, + }; + struct irq_domain *d; + + d = irq_domain_instantiate(&info); + return IS_ERR(d) ? NULL : d; } #ifdef CONFIG_IRQ_DOMAIN_NOMAP @@ -359,7 +441,17 @@ static inline struct irq_domain *irq_domain_add_nomap(struct device_node *of_nod const struct irq_domain_ops *ops, void *host_data) { - return __irq_domain_add(of_node_to_fwnode(of_node), 0, max_irq, max_irq, ops, host_data); + struct irq_domain_info info = { + .fwnode = of_node_to_fwnode(of_node), + .hwirq_max = max_irq, + .direct_max = max_irq, + .ops = ops, + .host_data = host_data, + }; + struct irq_domain *d; + + d = irq_domain_instantiate(&info); + return IS_ERR(d) ? NULL : d; } extern unsigned int irq_create_direct_mapping(struct irq_domain *host); @@ -369,7 +461,16 @@ static inline struct irq_domain *irq_domain_add_tree(struct device_node *of_node const struct irq_domain_ops *ops, void *host_data) { - return __irq_domain_add(of_node_to_fwnode(of_node), 0, ~0, 0, ops, host_data); + struct irq_domain_info info = { + .fwnode = of_node_to_fwnode(of_node), + .hwirq_max = ~0U, + .ops = ops, + .host_data = host_data, + }; + struct irq_domain *d; + + d = irq_domain_instantiate(&info); + return IS_ERR(d) ? NULL : d; } static inline struct irq_domain *irq_domain_create_linear(struct fwnode_handle *fwnode, @@ -377,14 +478,33 @@ static inline struct irq_domain *irq_domain_create_linear(struct fwnode_handle * const struct irq_domain_ops *ops, void *host_data) { - return __irq_domain_add(fwnode, size, size, 0, ops, host_data); + struct irq_domain_info info = { + .fwnode = fwnode, + .size = size, + .hwirq_max = size, + .ops = ops, + .host_data = host_data, + }; + struct irq_domain *d; + + d = irq_domain_instantiate(&info); + return IS_ERR(d) ? NULL : d; } static inline struct irq_domain *irq_domain_create_tree(struct fwnode_handle *fwnode, const struct irq_domain_ops *ops, void *host_data) { - return __irq_domain_add(fwnode, 0, ~0, 0, ops, host_data); + struct irq_domain_info info = { + .fwnode = fwnode, + .hwirq_max = ~0, + .ops = ops, + .host_data = host_data, + }; + struct irq_domain *d; + + d = irq_domain_instantiate(&info); + return IS_ERR(d) ? NULL : d; } extern void irq_domain_remove(struct irq_domain *host); diff --git a/include/linux/irqdomain_defs.h b/include/linux/irqdomain_defs.h index 5c1fe6f1fcde..36653e2ee1c9 100644 --- a/include/linux/irqdomain_defs.h +++ b/include/linux/irqdomain_defs.h @@ -25,7 +25,6 @@ enum irq_domain_bus_token { DOMAIN_BUS_PCI_DEVICE_MSIX, DOMAIN_BUS_DMAR, DOMAIN_BUS_AMDVI, - DOMAIN_BUS_PCI_DEVICE_IMS, DOMAIN_BUS_DEVICE_MSI, DOMAIN_BUS_WIRED_TO_MSI, }; diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 3f003d5fde53..57b074e0cfbb 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -18,6 +18,8 @@ #include <asm/irqflags.h> #include <asm/percpu.h> +struct task_struct; + /* Currently lockdep_softirqs_on/off is used only by lockdep */ #ifdef CONFIG_PROVE_LOCKING extern void lockdep_softirqs_on(unsigned long ip); @@ -25,12 +27,16 @@ extern void lockdep_hardirqs_on_prepare(void); extern void lockdep_hardirqs_on(unsigned long ip); extern void lockdep_hardirqs_off(unsigned long ip); + extern void lockdep_cleanup_dead_cpu(unsigned int cpu, + struct task_struct *idle); #else static inline void lockdep_softirqs_on(unsigned long ip) { } static inline void lockdep_softirqs_off(unsigned long ip) { } static inline void lockdep_hardirqs_on_prepare(void) { } static inline void lockdep_hardirqs_on(unsigned long ip) { } static inline void lockdep_hardirqs_off(unsigned long ip) { } + static inline void lockdep_cleanup_dead_cpu(unsigned int cpu, + struct task_struct *idle) {} #endif #ifdef CONFIG_TRACE_IRQFLAGS diff --git a/include/linux/irqnr.h b/include/linux/irqnr.h index 3496baa0b07f..e97206c721a0 100644 --- a/include/linux/irqnr.h +++ b/include/linux/irqnr.h @@ -5,30 +5,36 @@ #include <uapi/linux/irqnr.h> -extern int nr_irqs; +unsigned int irq_get_nr_irqs(void) __pure; +unsigned int irq_set_nr_irqs(unsigned int nr); extern struct irq_desc *irq_to_desc(unsigned int irq); unsigned int irq_get_next_irq(unsigned int offset); -# define for_each_irq_desc(irq, desc) \ - for (irq = 0, desc = irq_to_desc(irq); irq < nr_irqs; \ - irq++, desc = irq_to_desc(irq)) \ - if (!desc) \ - ; \ - else - +#define for_each_irq_desc(irq, desc) \ + for (unsigned int __nr_irqs__ = irq_get_nr_irqs(); __nr_irqs__; \ + __nr_irqs__ = 0) \ + for (irq = 0, desc = irq_to_desc(irq); irq < __nr_irqs__; \ + irq++, desc = irq_to_desc(irq)) \ + if (!desc) \ + ; \ + else # define for_each_irq_desc_reverse(irq, desc) \ - for (irq = nr_irqs - 1, desc = irq_to_desc(irq); irq >= 0; \ - irq--, desc = irq_to_desc(irq)) \ + for (irq = irq_get_nr_irqs() - 1, desc = irq_to_desc(irq); \ + irq >= 0; irq--, desc = irq_to_desc(irq)) \ if (!desc) \ ; \ else -# define for_each_active_irq(irq) \ - for (irq = irq_get_next_irq(0); irq < nr_irqs; \ - irq = irq_get_next_irq(irq + 1)) +#define for_each_active_irq(irq) \ + for (unsigned int __nr_irqs__ = irq_get_nr_irqs(); __nr_irqs__; \ + __nr_irqs__ = 0) \ + for (irq = irq_get_next_irq(0); irq < __nr_irqs__; \ + irq = irq_get_next_irq(irq + 1)) -#define for_each_irq_nr(irq) \ - for (irq = 0; irq < nr_irqs; irq++) +#define for_each_irq_nr(irq) \ + for (unsigned int __nr_irqs__ = irq_get_nr_irqs(); __nr_irqs__; \ + __nr_irqs__ = 0) \ + for (irq = 0; irq < __nr_irqs__; irq++) #endif diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 971f3e826e15..561025b4f3d9 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -28,7 +28,7 @@ #include <linux/slab.h> #include <linux/bit_spinlock.h> #include <linux/blkdev.h> -#include <crypto/hash.h> +#include <linux/crc32c.h> #endif #define journal_oom_retry 1 @@ -1086,6 +1086,13 @@ struct journal_s int j_revoke_records_per_block; /** + * @j_transaction_overhead_buffers: + * + * Number of blocks each transaction needs for its own bookkeeping + */ + int j_transaction_overhead_buffers; + + /** * @j_commit_interval: * * What is the maximum transaction lifetime before we begin a commit? @@ -1235,13 +1242,6 @@ struct journal_s void *j_private; /** - * @j_chksum_driver: - * - * Reference to checksum algorithm driver via cryptoapi. - */ - struct crypto_shash *j_chksum_driver; - - /** * @j_csum_seed: * * Precomputed journal UUID checksum for seeding other checksums. @@ -1434,7 +1434,9 @@ void jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block); extern void jbd2_journal_commit_transaction(journal_t *); /* Checkpoint list management */ -void __jbd2_journal_clean_checkpoint_list(journal_t *journal, bool destroy); +enum jbd2_shrink_type {JBD2_SHRINK_DESTROY, JBD2_SHRINK_BUSY_STOP, JBD2_SHRINK_BUSY_SKIP}; + +void __jbd2_journal_clean_checkpoint_list(journal_t *journal, enum jbd2_shrink_type type); unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal, unsigned long *nr_to_scan); int __jbd2_journal_remove_checkpoint(struct journal_head *); int jbd2_journal_try_remove_checkpoint(struct journal_head *jh); @@ -1586,10 +1588,13 @@ void jbd2_journal_put_journal_head(struct journal_head *jh); */ extern struct kmem_cache *jbd2_handle_cache; -static inline handle_t *jbd2_alloc_handle(gfp_t gfp_flags) -{ - return kmem_cache_zalloc(jbd2_handle_cache, gfp_flags); -} +/* + * This specialized allocator has to be a macro for its allocations to be + * accounted separately (to have a separate alloc_tag). The typecast is + * intentional to enforce typesafety. + */ +#define jbd2_alloc_handle(_gfp_flags) \ + ((handle_t *)kmem_cache_zalloc(jbd2_handle_cache, _gfp_flags)) static inline void jbd2_free_handle(handle_t *handle) { @@ -1602,10 +1607,13 @@ static inline void jbd2_free_handle(handle_t *handle) */ extern struct kmem_cache *jbd2_inode_cache; -static inline struct jbd2_inode *jbd2_alloc_inode(gfp_t gfp_flags) -{ - return kmem_cache_alloc(jbd2_inode_cache, gfp_flags); -} +/* + * This specialized allocator has to be a macro for its allocations to be + * accounted separately (to have a separate alloc_tag). The typecast is + * intentional to enforce typesafety. + */ +#define jbd2_alloc_inode(_gfp_flags) \ + ((struct jbd2_inode *)kmem_cache_alloc(jbd2_inode_cache, _gfp_flags)) static inline void jbd2_free_inode(struct jbd2_inode *jinode) { @@ -1660,12 +1668,7 @@ int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out); int jbd2_submit_inode_data(journal_t *journal, struct jbd2_inode *jinode); int jbd2_wait_inode_data(journal_t *journal, struct jbd2_inode *jinode); int jbd2_fc_wait_bufs(journal_t *journal, int num_blks); -int jbd2_fc_release_bufs(journal_t *journal); - -static inline int jbd2_journal_get_max_txn_bufs(journal_t *journal) -{ - return (journal->j_total_len - journal->j_fc_wbufsize) / 4; -} +void jbd2_fc_release_bufs(journal_t *journal); /* * is_journal_abort @@ -1696,7 +1699,7 @@ static inline void jbd2_journal_abort_handle(handle_t *handle) static inline void jbd2_init_fs_dev_write_error(journal_t *journal) { - struct address_space *mapping = journal->j_fs_dev->bd_inode->i_mapping; + struct address_space *mapping = journal->j_fs_dev->bd_mapping; /* * Save the original wb_err value of client fs's bdev mapping which @@ -1707,7 +1710,7 @@ static inline void jbd2_init_fs_dev_write_error(journal_t *journal) static inline int jbd2_check_fs_dev_write_error(journal_t *journal) { - struct address_space *mapping = journal->j_fs_dev->bd_inode->i_mapping; + struct address_space *mapping = journal->j_fs_dev->bd_mapping; return errseq_check(&mapping->wb_err, READ_ONCE(journal->j_fs_dev_wb_err)); @@ -1740,10 +1743,7 @@ static inline bool jbd2_journal_has_csum_v2or3_feature(journal_t *j) static inline int jbd2_journal_has_csum_v2or3(journal_t *journal) { - WARN_ON_ONCE(jbd2_journal_has_csum_v2or3_feature(journal) && - journal->j_chksum_driver == NULL); - - return journal->j_chksum_driver != NULL; + return jbd2_journal_has_csum_v2or3_feature(journal); } static inline int jbd2_journal_get_num_fc_blks(journal_superblock_t *jsb) @@ -1780,28 +1780,10 @@ static inline unsigned long jbd2_log_space_left(journal_t *journal) #define BJ_Reserved 4 /* Buffer is reserved for access by journal */ #define BJ_Types 5 -/* JBD uses a CRC32 checksum */ -#define JBD_MAX_CHECKSUM_SIZE 4 - static inline u32 jbd2_chksum(journal_t *journal, u32 crc, const void *address, unsigned int length) { - struct { - struct shash_desc shash; - char ctx[JBD_MAX_CHECKSUM_SIZE]; - } desc; - int err; - - BUG_ON(crypto_shash_descsize(journal->j_chksum_driver) > - JBD_MAX_CHECKSUM_SIZE); - - desc.shash.tfm = journal->j_chksum_driver; - *(u32 *)desc.ctx = crc; - - err = crypto_shash_update(&desc.shash, address, length); - BUG_ON(err); - - return *(u32 *)desc.ctx; + return crc32c(crc, address, length); } /* Return most recent uncommitted transaction */ diff --git a/include/linux/jhash.h b/include/linux/jhash.h index ab7f8c152b89..fa26a2dd3b52 100644 --- a/include/linux/jhash.h +++ b/include/linux/jhash.h @@ -31,7 +31,7 @@ /* Mask the hash value, i.e (value & jhash_mask(n)) instead of (value % n) */ #define jhash_mask(n) (jhash_size(n)-1) -/* __jhash_mix -- mix 3 32-bit values reversibly. */ +/* __jhash_mix - mix 3 32-bit values reversibly. */ #define __jhash_mix(a, b, c) \ { \ a -= c; a ^= rol32(c, 4); c += b; \ @@ -60,7 +60,7 @@ /* jhash - hash an arbitrary key * @k: sequence of bytes as key * @length: the length of the key - * @initval: the previous hash, or an arbitray value + * @initval: the previous hash, or an arbitrary value * * The generic version, hashes an arbitrary sequence of bytes. * No alignment or length assumptions are made about the input key. @@ -110,7 +110,7 @@ static inline u32 jhash(const void *key, u32 length, u32 initval) /* jhash2 - hash an array of u32's * @k: the key which must be an array of u32's * @length: the number of u32's in the key - * @initval: the previous hash, or an arbitray value + * @initval: the previous hash, or an arbitrary value * * Returns the hash value of the key. */ diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index d9f1435a5a13..ed945f42e064 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -418,7 +418,7 @@ extern unsigned long preset_lpj; #define NSEC_CONVERSION ((unsigned long)((((u64)1 << NSEC_JIFFIE_SC) +\ TICK_NSEC -1) / (u64)TICK_NSEC)) /* - * The maximum jiffie value is (MAX_INT >> 1). Here we translate that + * The maximum jiffy value is (MAX_INT >> 1). Here we translate that * into seconds. The 64-bit case will overflow if we are not careful, * so use the messy SH_DIV macro to do it. Still all constants. */ @@ -502,7 +502,7 @@ static inline unsigned long _msecs_to_jiffies(const unsigned int m) * - all other values are converted to jiffies by either multiplying * the input value by a factor or dividing it with a factor and * handling any 32-bit overflows. - * for the details see __msecs_to_jiffies() + * for the details see _msecs_to_jiffies() * * msecs_to_jiffies() checks for the passed in value being a constant * via __builtin_constant_p() allowing gcc to eliminate most of the @@ -526,6 +526,19 @@ static __always_inline unsigned long msecs_to_jiffies(const unsigned int m) } } +/** + * secs_to_jiffies: - convert seconds to jiffies + * @_secs: time in seconds + * + * Conversion is done by simple multiplication with HZ + * + * secs_to_jiffies() is defined as a macro rather than a static inline + * function so it can be used in static initializers. + * + * Return: jiffies value + */ +#define secs_to_jiffies(_secs) ((_secs) * HZ) + extern unsigned long __usecs_to_jiffies(const unsigned int u); #if !(USEC_PER_SEC % HZ) static inline unsigned long _usecs_to_jiffies(const unsigned int u) diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index f0a949b7c973..fdb79dd1ebd8 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -75,6 +75,7 @@ #include <linux/types.h> #include <linux/compiler.h> +#include <linux/cleanup.h> extern bool static_key_initialized; @@ -216,6 +217,7 @@ extern struct jump_entry __start___jump_table[]; extern struct jump_entry __stop___jump_table[]; extern void jump_label_init(void); +extern void jump_label_init_ro(void); extern void jump_label_lock(void); extern void jump_label_unlock(void); extern void arch_jump_label_transform(struct jump_entry *entry, @@ -265,6 +267,8 @@ static __always_inline void jump_label_init(void) static_key_initialized = true; } +static __always_inline void jump_label_init_ro(void) { } + static __always_inline bool static_key_false(struct static_key *key) { if (unlikely_notrace(static_key_count(key) > 0)) @@ -344,6 +348,8 @@ static inline void static_key_disable(struct static_key *key) #endif /* CONFIG_JUMP_LABEL */ +DEFINE_LOCK_GUARD_0(jump_label_lock, jump_label_lock(), jump_label_unlock()) + #define STATIC_KEY_INIT STATIC_KEY_INIT_FALSE #define jump_label_enabled static_key_enabled diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h index c3f075e8f60c..1c6a6c1704d8 100644 --- a/include/linux/kallsyms.h +++ b/include/linux/kallsyms.h @@ -57,10 +57,10 @@ static inline void *dereference_symbol_descriptor(void *ptr) preempt_disable(); mod = __module_address((unsigned long)ptr); - preempt_enable(); if (mod) ptr = dereference_module_function_descriptor(mod, ptr); + preempt_enable(); #endif return ptr; } diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 70d6a8f6e25d..890011071f2b 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -29,6 +29,9 @@ typedef unsigned int __bitwise kasan_vmalloc_flags_t; #define KASAN_VMALLOC_VM_ALLOC ((__force kasan_vmalloc_flags_t)0x02u) #define KASAN_VMALLOC_PROT_NORMAL ((__force kasan_vmalloc_flags_t)0x04u) +#define KASAN_VMALLOC_PAGE_RANGE 0x1 /* Apply exsiting page range */ +#define KASAN_VMALLOC_TLB_FLUSH 0x2 /* TLB flush */ + #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) #include <linux/pgtable.h> @@ -150,7 +153,7 @@ static __always_inline void kasan_unpoison_new_object(struct kmem_cache *cache, void __kasan_poison_new_object(struct kmem_cache *cache, void *object); /** - * kasan_unpoison_new_object - Repoison a new slab object. + * kasan_poison_new_object - Repoison a new slab object. * @cache: Cache the object belong to. * @object: Pointer to the object. * @@ -175,13 +178,59 @@ static __always_inline void * __must_check kasan_init_slab_obj( return (void *)object; } -bool __kasan_slab_free(struct kmem_cache *s, void *object, - unsigned long ip, bool init); +bool __kasan_slab_pre_free(struct kmem_cache *s, void *object, + unsigned long ip); +/** + * kasan_slab_pre_free - Check whether freeing a slab object is safe. + * @object: Object to be freed. + * + * This function checks whether freeing the given object is safe. It may + * check for double-free and invalid-free bugs and report them. + * + * This function is intended only for use by the slab allocator. + * + * @Return true if freeing the object is unsafe; false otherwise. + */ +static __always_inline bool kasan_slab_pre_free(struct kmem_cache *s, + void *object) +{ + if (kasan_enabled()) + return __kasan_slab_pre_free(s, object, _RET_IP_); + return false; +} + +bool __kasan_slab_free(struct kmem_cache *s, void *object, bool init, + bool still_accessible); +/** + * kasan_slab_free - Poison, initialize, and quarantine a slab object. + * @object: Object to be freed. + * @init: Whether to initialize the object. + * @still_accessible: Whether the object contents are still accessible. + * + * This function informs that a slab object has been freed and is not + * supposed to be accessed anymore, except when @still_accessible is set + * (indicating that the object is in a SLAB_TYPESAFE_BY_RCU cache and an RCU + * grace period might not have passed yet). + * + * For KASAN modes that have integrated memory initialization + * (kasan_has_integrated_init() == true), this function also initializes + * the object's memory. For other modes, the @init argument is ignored. + * + * This function might also take ownership of the object to quarantine it. + * When this happens, KASAN will defer freeing the object to a later + * stage and handle it internally until then. The return value indicates + * whether KASAN took ownership of the object. + * + * This function is intended only for use by the slab allocator. + * + * @Return true if KASAN took ownership of the object; false otherwise. + */ static __always_inline bool kasan_slab_free(struct kmem_cache *s, - void *object, bool init) + void *object, bool init, + bool still_accessible) { if (kasan_enabled()) - return __kasan_slab_free(s, object, _RET_IP_, init); + return __kasan_slab_free(s, object, init, still_accessible); return false; } @@ -371,7 +420,14 @@ static inline void *kasan_init_slab_obj(struct kmem_cache *cache, { return (void *)object; } -static inline bool kasan_slab_free(struct kmem_cache *s, void *object, bool init) + +static inline bool kasan_slab_pre_free(struct kmem_cache *s, void *object) +{ + return false; +} + +static inline bool kasan_slab_free(struct kmem_cache *s, void *object, + bool init, bool still_accessible) { return false; } @@ -435,7 +491,6 @@ void kasan_cache_create(struct kmem_cache *cache, unsigned int *size, void kasan_cache_shrink(struct kmem_cache *cache); void kasan_cache_shutdown(struct kmem_cache *cache); void kasan_record_aux_stack(void *ptr); -void kasan_record_aux_stack_noalloc(void *ptr); #else /* CONFIG_KASAN_GENERIC */ @@ -453,7 +508,6 @@ static inline void kasan_cache_create(struct kmem_cache *cache, static inline void kasan_cache_shrink(struct kmem_cache *cache) {} static inline void kasan_cache_shutdown(struct kmem_cache *cache) {} static inline void kasan_record_aux_stack(void *ptr) {} -static inline void kasan_record_aux_stack_noalloc(void *ptr) {} #endif /* CONFIG_KASAN_GENERIC */ @@ -511,7 +565,8 @@ void kasan_populate_early_vm_area_shadow(void *start, unsigned long size); int kasan_populate_vmalloc(unsigned long addr, unsigned long size); void kasan_release_vmalloc(unsigned long start, unsigned long end, unsigned long free_region_start, - unsigned long free_region_end); + unsigned long free_region_end, + unsigned long flags); #else /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */ @@ -526,7 +581,8 @@ static inline int kasan_populate_vmalloc(unsigned long start, static inline void kasan_release_vmalloc(unsigned long start, unsigned long end, unsigned long free_region_start, - unsigned long free_region_end) { } + unsigned long free_region_end, + unsigned long flags) { } #endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */ @@ -561,7 +617,8 @@ static inline int kasan_populate_vmalloc(unsigned long start, static inline void kasan_release_vmalloc(unsigned long start, unsigned long end, unsigned long free_region_start, - unsigned long free_region_end) { } + unsigned long free_region_end, + unsigned long flags) { } static inline void *kasan_unpoison_vmalloc(const void *start, unsigned long size, diff --git a/include/linux/kcore.h b/include/linux/kcore.h index 86c0f1d18998..9a2fa013c91d 100644 --- a/include/linux/kcore.h +++ b/include/linux/kcore.h @@ -20,19 +20,6 @@ struct kcore_list { int type; }; -struct vmcore { - struct list_head list; - unsigned long long paddr; - unsigned long long size; - loff_t offset; -}; - -struct vmcoredd_node { - struct list_head list; /* List of dumps */ - void *buf; /* Buffer containing device's dump */ - unsigned int size; /* Size of the buffer */ -}; - #ifdef CONFIG_PROC_KCORE void __init kclist_add(struct kcore_list *, void *, size_t, int type); diff --git a/include/linux/kcov.h b/include/linux/kcov.h index b851ba415e03..75a2fb8b16c3 100644 --- a/include/linux/kcov.h +++ b/include/linux/kcov.h @@ -21,6 +21,8 @@ enum kcov_mode { KCOV_MODE_TRACE_PC = 2, /* Collecting comparison operands mode. */ KCOV_MODE_TRACE_CMP = 3, + /* The process owns a KCOV remote reference. */ + KCOV_MODE_REMOTE = 4, }; #define KCOV_IN_CTXSW (1 << 30) @@ -55,21 +57,47 @@ static inline void kcov_remote_start_usb(u64 id) /* * The softirq flavor of kcov_remote_*() functions is introduced as a temporary - * work around for kcov's lack of nested remote coverage sections support in - * task context. Adding support for nested sections is tracked in: - * https://bugzilla.kernel.org/show_bug.cgi?id=210337 + * workaround for KCOV's lack of nested remote coverage sections support. + * + * Adding support is tracked in https://bugzilla.kernel.org/show_bug.cgi?id=210337. + * + * kcov_remote_start_usb_softirq(): + * + * 1. Only collects coverage when called in the softirq context. This allows + * avoiding nested remote coverage collection sections in the task context. + * For example, USB/IP calls usb_hcd_giveback_urb() in the task context + * within an existing remote coverage collection section. Thus, KCOV should + * not attempt to start collecting coverage within the coverage collection + * section in __usb_hcd_giveback_urb() in this case. + * + * 2. Disables interrupts for the duration of the coverage collection section. + * This allows avoiding nested remote coverage collection sections in the + * softirq context (a softirq might occur during the execution of a work in + * the BH workqueue, which runs with in_serving_softirq() > 0). + * For example, usb_giveback_urb_bh() runs in the BH workqueue with + * interrupts enabled, so __usb_hcd_giveback_urb() might be interrupted in + * the middle of its remote coverage collection section, and the interrupt + * handler might invoke __usb_hcd_giveback_urb() again. */ -static inline void kcov_remote_start_usb_softirq(u64 id) +static inline unsigned long kcov_remote_start_usb_softirq(u64 id) { - if (in_serving_softirq()) + unsigned long flags = 0; + + if (in_serving_softirq()) { + local_irq_save(flags); kcov_remote_start_usb(id); + } + + return flags; } -static inline void kcov_remote_stop_softirq(void) +static inline void kcov_remote_stop_softirq(unsigned long flags) { - if (in_serving_softirq()) + if (in_serving_softirq()) { kcov_remote_stop(); + local_irq_restore(flags); + } } #ifdef CONFIG_64BIT @@ -103,8 +131,11 @@ static inline u64 kcov_common_handle(void) } static inline void kcov_remote_start_common(u64 id) {} static inline void kcov_remote_start_usb(u64 id) {} -static inline void kcov_remote_start_usb_softirq(u64 id) {} -static inline void kcov_remote_stop_softirq(void) {} +static inline unsigned long kcov_remote_start_usb_softirq(u64 id) +{ + return 0; +} +static inline void kcov_remote_stop_softirq(unsigned long flags) {} #endif /* CONFIG_KCOV */ #endif /* _LINUX_KCOV_H */ diff --git a/include/linux/kdb.h b/include/linux/kdb.h index f6c2ddb16b95..905a2e2f45f6 100644 --- a/include/linux/kdb.h +++ b/include/linux/kdb.h @@ -140,9 +140,6 @@ extern const char *kdb_diemsg; extern unsigned int kdb_flags; /* Global flags, see kdb_state for per cpu state */ -extern void kdb_save_flags(void); -extern void kdb_restore_flags(void); - #define KDB_FLAG(flag) (kdb_flags & KDB_FLAG_##flag) #define KDB_FLAG_SET(flag) ((void)(kdb_flags |= KDB_FLAG_##flag)) #define KDB_FLAG_CLEAR(flag) ((void)(kdb_flags &= ~KDB_FLAG_##flag)) diff --git a/include/linux/kernel-page-flags.h b/include/linux/kernel-page-flags.h index 859f4b0c1b2b..196778a087c4 100644 --- a/include/linux/kernel-page-flags.h +++ b/include/linux/kernel-page-flags.h @@ -10,12 +10,11 @@ */ #define KPF_RESERVED 32 #define KPF_MLOCKED 33 -#define KPF_MAPPEDTODISK 34 +#define KPF_OWNER_2 34 #define KPF_PRIVATE 35 #define KPF_PRIVATE_2 36 #define KPF_OWNER_PRIVATE 37 #define KPF_ARCH 38 -#define KPF_UNCACHED 39 #define KPF_SOFTDIRTY 40 #define KPF_ARCH_2 41 #define KPF_ARCH_3 42 diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h index 9935f7ecbfb9..b97ce2df376f 100644 --- a/include/linux/kernel_stat.h +++ b/include/linux/kernel_stat.h @@ -5,7 +5,6 @@ #include <linux/smp.h> #include <linux/threads.h> #include <linux/percpu.h> -#include <linux/cpumask.h> #include <linux/interrupt.h> #include <linux/sched.h> #include <linux/vtime.h> @@ -79,6 +78,14 @@ static inline unsigned int kstat_cpu_softirqs_sum(int cpu) return sum; } +#ifdef CONFIG_GENERIC_IRQ_STAT_SNAPSHOT +extern void kstat_snapshot_irqs(void); +extern unsigned int kstat_get_irq_since_snapshot(unsigned int irq); +#else +static inline void kstat_snapshot_irqs(void) { } +static inline unsigned int kstat_get_irq_since_snapshot(unsigned int irq) { return 0; } +#endif + /* * Number of interrupts per specific IRQ source, since bootup */ diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 060835bb82d5..f0e9f8eda7a3 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -319,8 +319,10 @@ struct kimage { /* If set, we are using file mode kexec syscall */ unsigned int file_mode:1; #ifdef CONFIG_CRASH_HOTPLUG - /* If set, allow changes to elfcorehdr of kexec_load'd image */ - unsigned int update_elfcorehdr:1; + /* If set, it is safe to update kexec segments that are + * excluded from SHA calculation. + */ + unsigned int hotplug_support:1; #endif #ifdef ARCH_HAS_KIMAGE_ARCH @@ -391,9 +393,10 @@ bool kexec_load_permitted(int kexec_image_type); /* List of defined/legal kexec flags */ #ifndef CONFIG_KEXEC_JUMP -#define KEXEC_FLAGS (KEXEC_ON_CRASH | KEXEC_UPDATE_ELFCOREHDR) +#define KEXEC_FLAGS (KEXEC_ON_CRASH | KEXEC_UPDATE_ELFCOREHDR | KEXEC_CRASH_HOTPLUG_SUPPORT) #else -#define KEXEC_FLAGS (KEXEC_ON_CRASH | KEXEC_PRESERVE_CONTEXT | KEXEC_UPDATE_ELFCOREHDR) +#define KEXEC_FLAGS (KEXEC_ON_CRASH | KEXEC_PRESERVE_CONTEXT | KEXEC_UPDATE_ELFCOREHDR | \ + KEXEC_CRASH_HOTPLUG_SUPPORT) #endif /* List of defined/legal kexec file flags */ @@ -461,10 +464,8 @@ static inline void arch_kexec_pre_free_pages(void *vaddr, unsigned int pages) { extern bool kexec_file_dbg_print; -#define kexec_dprintk(fmt, ...) \ - printk("%s" fmt, \ - kexec_file_dbg_print ? KERN_INFO : KERN_DEBUG, \ - ##__VA_ARGS__) +#define kexec_dprintk(fmt, arg...) \ + do { if (kexec_file_dbg_print) pr_info(fmt, ##arg); } while (0) #else /* !CONFIG_KEXEC_CORE */ struct pt_regs; diff --git a/include/linux/key.h b/include/linux/key.h index 943a432da3ae..074dca3222b9 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -436,9 +436,6 @@ extern key_ref_t keyring_search(key_ref_t keyring, const char *description, bool recurse); -extern int keyring_add_key(struct key *keyring, - struct key *key); - extern int keyring_restrict(key_ref_t keyring, const char *type, const char *restriction); diff --git a/include/linux/kfence.h b/include/linux/kfence.h index 88100cc9caba..0ad1ddbb8b99 100644 --- a/include/linux/kfence.h +++ b/include/linux/kfence.h @@ -124,7 +124,7 @@ static __always_inline void *kfence_alloc(struct kmem_cache *s, size_t size, gfp if (!static_branch_likely(&kfence_allocation_key)) return NULL; #endif - if (likely(atomic_read(&kfence_allocation_gate))) + if (likely(atomic_read(&kfence_allocation_gate) > 0)) return NULL; return __kfence_alloc(s, size, flags); } diff --git a/include/linux/kfifo.h b/include/linux/kfifo.h index 0b35a41440ff..fd743d4c4b4b 100644 --- a/include/linux/kfifo.h +++ b/include/linux/kfifo.h @@ -36,10 +36,15 @@ * to lock the reader. */ -#include <linux/kernel.h> +#include <linux/array_size.h> #include <linux/spinlock.h> #include <linux/stddef.h> -#include <linux/scatterlist.h> +#include <linux/types.h> + +#include <asm/barrier.h> +#include <asm/errno.h> + +struct scatterlist; struct __kfifo { unsigned int in; @@ -304,19 +309,25 @@ __kfifo_uint_must_check_helper( \ ) /** - * kfifo_skip - skip output data + * kfifo_skip_count - skip output data * @fifo: address of the fifo to be used + * @count: count of data to skip */ -#define kfifo_skip(fifo) \ -(void)({ \ +#define kfifo_skip_count(fifo, count) do { \ typeof((fifo) + 1) __tmp = (fifo); \ const size_t __recsize = sizeof(*__tmp->rectype); \ struct __kfifo *__kfifo = &__tmp->kfifo; \ if (__recsize) \ __kfifo_skip_r(__kfifo, __recsize); \ else \ - __kfifo->out++; \ -}) + __kfifo->out += (count); \ +} while(0) + +/** + * kfifo_skip - skip output data + * @fifo: address of the fifo to be used + */ +#define kfifo_skip(fifo) kfifo_skip_count(fifo, 1) /** * kfifo_peek_len - gets the size of the next fifo record @@ -578,7 +589,7 @@ __kfifo_uint_must_check_helper( \ * @buf: pointer to the storage buffer * @n: max. number of elements to get * - * This macro get some data from the fifo and return the numbers of elements + * This macro gets some data from the fifo and returns the numbers of elements * copied. * * Note that with only one concurrent reader and one concurrent @@ -605,7 +616,7 @@ __kfifo_uint_must_check_helper( \ * @n: max. number of elements to get * @lock: pointer to the spinlock to use for locking * - * This macro get the data from the fifo and return the numbers of elements + * This macro gets the data from the fifo and returns the numbers of elements * copied. */ #define kfifo_out_spinlocked(fifo, buf, n, lock) \ @@ -703,11 +714,12 @@ __kfifo_int_must_check_helper( \ ) /** - * kfifo_dma_in_prepare - setup a scatterlist for DMA input + * kfifo_dma_in_prepare_mapped - setup a scatterlist for DMA input * @fifo: address of the fifo to be used * @sgl: pointer to the scatterlist array * @nents: number of entries in the scatterlist array * @len: number of elements to transfer + * @dma: mapped dma address to fill into @sgl * * This macro fills a scatterlist for DMA input. * It returns the number entries in the scatterlist array. @@ -715,7 +727,7 @@ __kfifo_int_must_check_helper( \ * Note that with only one concurrent reader and one concurrent * writer, you don't need extra locking to use these macros. */ -#define kfifo_dma_in_prepare(fifo, sgl, nents, len) \ +#define kfifo_dma_in_prepare_mapped(fifo, sgl, nents, len, dma) \ ({ \ typeof((fifo) + 1) __tmp = (fifo); \ struct scatterlist *__sgl = (sgl); \ @@ -724,16 +736,20 @@ __kfifo_int_must_check_helper( \ const size_t __recsize = sizeof(*__tmp->rectype); \ struct __kfifo *__kfifo = &__tmp->kfifo; \ (__recsize) ? \ - __kfifo_dma_in_prepare_r(__kfifo, __sgl, __nents, __len, __recsize) : \ - __kfifo_dma_in_prepare(__kfifo, __sgl, __nents, __len); \ + __kfifo_dma_in_prepare_r(__kfifo, __sgl, __nents, __len, __recsize, \ + dma) : \ + __kfifo_dma_in_prepare(__kfifo, __sgl, __nents, __len, dma); \ }) +#define kfifo_dma_in_prepare(fifo, sgl, nents, len) \ + kfifo_dma_in_prepare_mapped(fifo, sgl, nents, len, DMA_MAPPING_ERROR) + /** * kfifo_dma_in_finish - finish a DMA IN operation * @fifo: address of the fifo to be used * @len: number of bytes to received * - * This macro finish a DMA IN operation. The in counter will be updated by + * This macro finishes a DMA IN operation. The in counter will be updated by * the len parameter. No error checking will be done. * * Note that with only one concurrent reader and one concurrent @@ -752,11 +768,12 @@ __kfifo_int_must_check_helper( \ }) /** - * kfifo_dma_out_prepare - setup a scatterlist for DMA output + * kfifo_dma_out_prepare_mapped - setup a scatterlist for DMA output * @fifo: address of the fifo to be used * @sgl: pointer to the scatterlist array * @nents: number of entries in the scatterlist array * @len: number of elements to transfer + * @dma: mapped dma address to fill into @sgl * * This macro fills a scatterlist for DMA output which at most @len bytes * to transfer. @@ -766,7 +783,7 @@ __kfifo_int_must_check_helper( \ * Note that with only one concurrent reader and one concurrent * writer, you don't need extra locking to use these macros. */ -#define kfifo_dma_out_prepare(fifo, sgl, nents, len) \ +#define kfifo_dma_out_prepare_mapped(fifo, sgl, nents, len, dma) \ ({ \ typeof((fifo) + 1) __tmp = (fifo); \ struct scatterlist *__sgl = (sgl); \ @@ -775,32 +792,29 @@ __kfifo_int_must_check_helper( \ const size_t __recsize = sizeof(*__tmp->rectype); \ struct __kfifo *__kfifo = &__tmp->kfifo; \ (__recsize) ? \ - __kfifo_dma_out_prepare_r(__kfifo, __sgl, __nents, __len, __recsize) : \ - __kfifo_dma_out_prepare(__kfifo, __sgl, __nents, __len); \ + __kfifo_dma_out_prepare_r(__kfifo, __sgl, __nents, __len, __recsize, \ + dma) : \ + __kfifo_dma_out_prepare(__kfifo, __sgl, __nents, __len, dma); \ }) +#define kfifo_dma_out_prepare(fifo, sgl, nents, len) \ + kfifo_dma_out_prepare_mapped(fifo, sgl, nents, len, DMA_MAPPING_ERROR) + /** * kfifo_dma_out_finish - finish a DMA OUT operation * @fifo: address of the fifo to be used * @len: number of bytes transferred * - * This macro finish a DMA OUT operation. The out counter will be updated by + * This macro finishes a DMA OUT operation. The out counter will be updated by * the len parameter. No error checking will be done. * * Note that with only one concurrent reader and one concurrent * writer, you don't need extra locking to use these macros. */ -#define kfifo_dma_out_finish(fifo, len) \ -(void)({ \ - typeof((fifo) + 1) __tmp = (fifo); \ - unsigned int __len = (len); \ - const size_t __recsize = sizeof(*__tmp->rectype); \ - struct __kfifo *__kfifo = &__tmp->kfifo; \ - if (__recsize) \ - __kfifo_dma_out_finish_r(__kfifo, __recsize); \ - else \ - __kfifo->out += __len / sizeof(*__tmp->type); \ -}) +#define kfifo_dma_out_finish(fifo, len) do { \ + typeof((fifo) + 1) ___tmp = (fifo); \ + kfifo_skip_count(___tmp, (len) / sizeof(*___tmp->type)); \ +} while (0) /** * kfifo_out_peek - gets some data from the fifo @@ -808,7 +822,7 @@ __kfifo_int_must_check_helper( \ * @buf: pointer to the storage buffer * @n: max. number of elements to get * - * This macro get the data from the fifo and return the numbers of elements + * This macro gets the data from the fifo and returns the numbers of elements * copied. The data is not removed from the fifo. * * Note that with only one concurrent reader and one concurrent @@ -828,6 +842,63 @@ __kfifo_uint_must_check_helper( \ }) \ ) +/** + * kfifo_out_linear - gets a tail of/offset to available data + * @fifo: address of the fifo to be used + * @tail: pointer to an unsigned int to store the value of tail + * @n: max. number of elements to point at + * + * This macro obtains the offset (tail) to the available data in the fifo + * buffer and returns the + * numbers of elements available. It returns the available count till the end + * of data or till the end of the buffer. So that it can be used for linear + * data processing (like memcpy() of (@fifo->data + @tail) with count + * returned). + * + * Note that with only one concurrent reader and one concurrent + * writer, you don't need extra locking to use these macro. + */ +#define kfifo_out_linear(fifo, tail, n) \ +__kfifo_uint_must_check_helper( \ +({ \ + typeof((fifo) + 1) __tmp = (fifo); \ + unsigned int *__tail = (tail); \ + unsigned long __n = (n); \ + const size_t __recsize = sizeof(*__tmp->rectype); \ + struct __kfifo *__kfifo = &__tmp->kfifo; \ + (__recsize) ? \ + __kfifo_out_linear_r(__kfifo, __tail, __n, __recsize) : \ + __kfifo_out_linear(__kfifo, __tail, __n); \ +}) \ +) + +/** + * kfifo_out_linear_ptr - gets a pointer to the available data + * @fifo: address of the fifo to be used + * @ptr: pointer to data to store the pointer to tail + * @n: max. number of elements to point at + * + * Similarly to kfifo_out_linear(), this macro obtains the pointer to the + * available data in the fifo buffer and returns the numbers of elements + * available. It returns the available count till the end of available data or + * till the end of the buffer. So that it can be used for linear data + * processing (like memcpy() of @ptr with count returned). + * + * Note that with only one concurrent reader and one concurrent + * writer, you don't need extra locking to use these macro. + */ +#define kfifo_out_linear_ptr(fifo, ptr, n) \ +__kfifo_uint_must_check_helper( \ +({ \ + typeof((fifo) + 1) ___tmp = (fifo); \ + unsigned int ___tail; \ + unsigned int ___n = kfifo_out_linear(___tmp, &___tail, (n)); \ + *(ptr) = ___tmp->kfifo.data + ___tail * kfifo_esize(___tmp); \ + ___n; \ +}) \ +) + + extern int __kfifo_alloc(struct __kfifo *fifo, unsigned int size, size_t esize, gfp_t gfp_mask); @@ -849,14 +920,17 @@ extern int __kfifo_to_user(struct __kfifo *fifo, void __user *to, unsigned long len, unsigned int *copied); extern unsigned int __kfifo_dma_in_prepare(struct __kfifo *fifo, - struct scatterlist *sgl, int nents, unsigned int len); + struct scatterlist *sgl, int nents, unsigned int len, dma_addr_t dma); extern unsigned int __kfifo_dma_out_prepare(struct __kfifo *fifo, - struct scatterlist *sgl, int nents, unsigned int len); + struct scatterlist *sgl, int nents, unsigned int len, dma_addr_t dma); extern unsigned int __kfifo_out_peek(struct __kfifo *fifo, void *buf, unsigned int len); +extern unsigned int __kfifo_out_linear(struct __kfifo *fifo, + unsigned int *tail, unsigned int n); + extern unsigned int __kfifo_in_r(struct __kfifo *fifo, const void *buf, unsigned int len, size_t recsize); @@ -871,15 +945,15 @@ extern int __kfifo_to_user_r(struct __kfifo *fifo, void __user *to, unsigned long len, unsigned int *copied, size_t recsize); extern unsigned int __kfifo_dma_in_prepare_r(struct __kfifo *fifo, - struct scatterlist *sgl, int nents, unsigned int len, size_t recsize); + struct scatterlist *sgl, int nents, unsigned int len, size_t recsize, + dma_addr_t dma); extern void __kfifo_dma_in_finish_r(struct __kfifo *fifo, unsigned int len, size_t recsize); extern unsigned int __kfifo_dma_out_prepare_r(struct __kfifo *fifo, - struct scatterlist *sgl, int nents, unsigned int len, size_t recsize); - -extern void __kfifo_dma_out_finish_r(struct __kfifo *fifo, size_t recsize); + struct scatterlist *sgl, int nents, unsigned int len, size_t recsize, + dma_addr_t dma); extern unsigned int __kfifo_len_r(struct __kfifo *fifo, size_t recsize); @@ -888,6 +962,9 @@ extern void __kfifo_skip_r(struct __kfifo *fifo, size_t recsize); extern unsigned int __kfifo_out_peek_r(struct __kfifo *fifo, void *buf, unsigned int len, size_t recsize); +extern unsigned int __kfifo_out_linear_r(struct __kfifo *fifo, + unsigned int *tail, unsigned int n, size_t recsize); + extern unsigned int __kfifo_max_r(unsigned int len, size_t recsize); #endif diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h index 76e891ee9e37..51ef131e66b7 100644 --- a/include/linux/kgdb.h +++ b/include/linux/kgdb.h @@ -309,11 +309,9 @@ extern unsigned long kgdb_arch_pc(int exception, struct pt_regs *regs); #ifdef CONFIG_SERIAL_KGDB_NMI extern int kgdb_register_nmi_console(void); extern int kgdb_unregister_nmi_console(void); -extern bool kgdb_nmi_poll_knock(void); #else static inline int kgdb_register_nmi_console(void) { return 0; } static inline int kgdb_unregister_nmi_console(void) { return 0; } -static inline bool kgdb_nmi_poll_knock(void) { return true; } #endif extern int kgdb_register_io_module(struct kgdb_io *local_kgdb_io_ops); diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h index f68865e19b0b..1f46046080f5 100644 --- a/include/linux/khugepaged.h +++ b/include/linux/khugepaged.h @@ -2,8 +2,7 @@ #ifndef _LINUX_KHUGEPAGED_H #define _LINUX_KHUGEPAGED_H -#include <linux/sched/coredump.h> /* MMF_VM_HUGEPAGE */ - +extern unsigned int khugepaged_max_ptes_none __read_mostly; #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern struct attribute_group khugepaged_attr_group; diff --git a/include/linux/kmemleak.h b/include/linux/kmemleak.h index 6a3cd1bf4680..93a73c076d16 100644 --- a/include/linux/kmemleak.h +++ b/include/linux/kmemleak.h @@ -26,6 +26,7 @@ extern void kmemleak_free_part(const void *ptr, size_t size) __ref; extern void kmemleak_free_percpu(const void __percpu *ptr) __ref; extern void kmemleak_update_trace(const void *ptr) __ref; extern void kmemleak_not_leak(const void *ptr) __ref; +extern void kmemleak_transient_leak(const void *ptr) __ref; extern void kmemleak_ignore(const void *ptr) __ref; extern void kmemleak_scan_area(const void *ptr, size_t size, gfp_t gfp) __ref; extern void kmemleak_no_scan(const void *ptr) __ref; @@ -93,6 +94,9 @@ static inline void kmemleak_update_trace(const void *ptr) static inline void kmemleak_not_leak(const void *ptr) { } +static inline void kmemleak_transient_leak(const void *ptr) +{ +} static inline void kmemleak_ignore(const void *ptr) { } diff --git a/include/linux/kmsan-checks.h b/include/linux/kmsan-checks.h index c4cae333deec..e1082dc40abc 100644 --- a/include/linux/kmsan-checks.h +++ b/include/linux/kmsan-checks.h @@ -61,6 +61,17 @@ void kmsan_check_memory(const void *address, size_t size); void kmsan_copy_to_user(void __user *to, const void *from, size_t to_copy, size_t left); +/** + * kmsan_memmove() - Notify KMSAN about a data copy within kernel. + * @to: destination address in the kernel. + * @from: source address in the kernel. + * @size: number of bytes to copy. + * + * Invoked after non-instrumented version (e.g. implemented using assembly + * code) of memmove()/memcpy() is called, in order to copy KMSAN's metadata. + */ +void kmsan_memmove(void *to, const void *from, size_t to_copy); + #else static inline void kmsan_poison_memory(const void *address, size_t size, @@ -78,6 +89,10 @@ static inline void kmsan_copy_to_user(void __user *to, const void *from, { } +static inline void kmsan_memmove(void *to, const void *from, size_t to_copy) +{ +} + #endif #endif /* _LINUX_KMSAN_CHECKS_H */ diff --git a/include/linux/kmsan.h b/include/linux/kmsan.h index e0c23a32cdf0..2b1432cc16d5 100644 --- a/include/linux/kmsan.h +++ b/include/linux/kmsan.h @@ -230,6 +230,67 @@ void kmsan_handle_urb(const struct urb *urb, bool is_out); */ void kmsan_unpoison_entry_regs(const struct pt_regs *regs); +/** + * kmsan_get_metadata() - Return a pointer to KMSAN shadow or origins. + * @addr: kernel address. + * @is_origin: whether to return origins or shadow. + * + * Return NULL if metadata cannot be found. + */ +void *kmsan_get_metadata(void *addr, bool is_origin); + +/** + * kmsan_enable_current(): Enable KMSAN for the current task. + * + * Each kmsan_enable_current() current call must be preceded by a + * kmsan_disable_current() call. These call pairs may be nested. + */ +void kmsan_enable_current(void); + +/** + * kmsan_disable_current(): Disable KMSAN for the current task. + * + * Each kmsan_disable_current() current call must be followed by a + * kmsan_enable_current() call. These call pairs may be nested. + */ +void kmsan_disable_current(void); + +/** + * memset_no_sanitize_memory(): Fill memory without KMSAN instrumentation. + * @s: address of kernel memory to fill. + * @c: constant byte to fill the memory with. + * @n: number of bytes to fill. + * + * This is like memset(), but without KMSAN instrumentation. + */ +static inline void *memset_no_sanitize_memory(void *s, int c, size_t n) +{ + return __memset(s, c, n); +} + +extern bool kmsan_enabled; +extern int panic_on_kmsan; + +/* + * KMSAN performs a lot of consistency checks that are currently enabled by + * default. BUG_ON is normally discouraged in the kernel, unless used for + * debugging, but KMSAN itself is a debugging tool, so it makes little sense to + * recover if something goes wrong. + */ +#define KMSAN_WARN_ON(cond) \ + ({ \ + const bool __cond = WARN_ON(cond); \ + if (unlikely(__cond)) { \ + WRITE_ONCE(kmsan_enabled, false); \ + if (panic_on_kmsan) { \ + /* Can't call panic() here because */ \ + /* of uaccess checks. */ \ + BUG(); \ + } \ + } \ + __cond; \ + }) + #else static inline void kmsan_init_shadow(void) @@ -329,6 +390,21 @@ static inline void kmsan_unpoison_entry_regs(const struct pt_regs *regs) { } +static inline void kmsan_enable_current(void) +{ +} + +static inline void kmsan_disable_current(void) +{ +} + +static inline void *memset_no_sanitize_memory(void *s, int c, size_t n) +{ + return memset(s, c, n); +} + +#define KMSAN_WARN_ON WARN_ON + #endif #endif /* _LINUX_KMSAN_H */ diff --git a/include/linux/kmsan_types.h b/include/linux/kmsan_types.h index 929287981afe..dfc59918b3c0 100644 --- a/include/linux/kmsan_types.h +++ b/include/linux/kmsan_types.h @@ -31,7 +31,7 @@ struct kmsan_context_state { struct kmsan_ctx { struct kmsan_context_state cstate; int kmsan_in_runtime; - bool allow_reporting; + unsigned int depth; }; #endif /* _LINUX_KMSAN_TYPES_H */ diff --git a/include/linux/kmsg_dump.h b/include/linux/kmsg_dump.h index 906521c2329c..6055fc969877 100644 --- a/include/linux/kmsg_dump.h +++ b/include/linux/kmsg_dump.h @@ -40,6 +40,17 @@ struct kmsg_dump_iter { }; /** + * struct kmsg_dump_detail - kernel crash detail + * @reason: reason for the crash, see kmsg_dump_reason. + * @description: optional short string, to provide additional information. + */ + +struct kmsg_dump_detail { + enum kmsg_dump_reason reason; + const char *description; +}; + +/** * struct kmsg_dumper - kernel crash message dumper structure * @list: Entry in the dumper list (private) * @dump: Call into dumping code which will retrieve the data with @@ -49,13 +60,13 @@ struct kmsg_dump_iter { */ struct kmsg_dumper { struct list_head list; - void (*dump)(struct kmsg_dumper *dumper, enum kmsg_dump_reason reason); + void (*dump)(struct kmsg_dumper *dumper, struct kmsg_dump_detail *detail); enum kmsg_dump_reason max_reason; bool registered; }; #ifdef CONFIG_PRINTK -void kmsg_dump(enum kmsg_dump_reason reason); +void kmsg_dump_desc(enum kmsg_dump_reason reason, const char *desc); bool kmsg_dump_get_line(struct kmsg_dump_iter *iter, bool syslog, char *line, size_t size, size_t *len); @@ -71,7 +82,7 @@ int kmsg_dump_unregister(struct kmsg_dumper *dumper); const char *kmsg_dump_reason_str(enum kmsg_dump_reason reason); #else -static inline void kmsg_dump(enum kmsg_dump_reason reason) +static inline void kmsg_dump_desc(enum kmsg_dump_reason reason, const char *desc) { } @@ -107,4 +118,9 @@ static inline const char *kmsg_dump_reason_str(enum kmsg_dump_reason reason) } #endif +static inline void kmsg_dump(enum kmsg_dump_reason reason) +{ + kmsg_dump_desc(reason, NULL); +} + #endif /* _LINUX_KMSG_DUMP_H */ diff --git a/include/linux/kobject_ns.h b/include/linux/kobject_ns.h index be707748e7ce..150fe2ae1b6b 100644 --- a/include/linux/kobject_ns.h +++ b/include/linux/kobject_ns.h @@ -52,8 +52,6 @@ const struct kobj_ns_type_operations *kobj_ns_ops(const struct kobject *kobj); bool kobj_ns_current_may_mount(enum kobj_ns_type type); void *kobj_ns_grab_current(enum kobj_ns_type type); -const void *kobj_ns_netlink(enum kobj_ns_type type, struct sock *sk); -const void *kobj_ns_initial(enum kobj_ns_type type); void kobj_ns_drop(enum kobj_ns_type type, void *ns); #endif /* _LINUX_KOBJECT_NS_H */ diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 0ff44d6633e3..8c4f3bb24429 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -269,15 +269,6 @@ extern unsigned long __stop_kprobe_blacklist[]; extern struct kretprobe_blackpoint kretprobe_blacklist[]; -#ifdef CONFIG_KPROBES_SANITY_TEST -extern int init_test_probes(void); -#else /* !CONFIG_KPROBES_SANITY_TEST */ -static inline int init_test_probes(void) -{ - return 0; -} -#endif /* CONFIG_KPROBES_SANITY_TEST */ - extern int arch_prepare_kprobe(struct kprobe *p); extern void arch_arm_kprobe(struct kprobe *p); extern void arch_disarm_kprobe(struct kprobe *p); @@ -378,11 +369,15 @@ static inline void wait_for_kprobe_optimizer(void) { } extern void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *ops, struct ftrace_regs *fregs); extern int arch_prepare_kprobe_ftrace(struct kprobe *p); +/* Set when ftrace has been killed: kprobes on ftrace must be disabled for safety */ +extern bool kprobe_ftrace_disabled __read_mostly; +extern void kprobe_ftrace_kill(void); #else static inline int arch_prepare_kprobe_ftrace(struct kprobe *p) { return -EINVAL; } +static inline void kprobe_ftrace_kill(void) {} #endif /* CONFIG_KPROBES_ON_FTRACE */ /* Get the kprobe at this addr (if any) - called with preemption disabled */ @@ -495,6 +490,9 @@ static inline void kprobe_flush_task(struct task_struct *tk) static inline void kprobe_free_init_mem(void) { } +static inline void kprobe_ftrace_kill(void) +{ +} static inline int disable_kprobe(struct kprobe *kp) { return -EOPNOTSUPP; diff --git a/include/linux/kref.h b/include/linux/kref.h index d32e21a2538c..88e82ab1367c 100644 --- a/include/linux/kref.h +++ b/include/linux/kref.h @@ -46,18 +46,18 @@ static inline void kref_get(struct kref *kref) } /** - * kref_put - decrement refcount for object. - * @kref: object. - * @release: pointer to the function that will clean up the object when the + * kref_put - Decrement refcount for object + * @kref: Object + * @release: Pointer to the function that will clean up the object when the * last reference to the object is released. - * This pointer is required, and it is not acceptable to pass kfree - * in as this function. * - * Decrement the refcount, and if 0, call release(). - * Return 1 if the object was removed, otherwise return 0. Beware, if this - * function returns 0, you still can not count on the kref from remaining in - * memory. Only use the return value if you want to see if the kref is now - * gone, not present. + * Decrement the refcount, and if 0, call @release. The caller may not + * pass NULL or kfree() as the release function. + * + * Return: 1 if this call removed the object, otherwise return 0. Beware, + * if this function returns 0, another caller may have removed the object + * by the time this function returns. The return value is only certain + * if you want to see if the object is definitely released. */ static inline int kref_put(struct kref *kref, void (*release)(struct kref *kref)) { @@ -68,17 +68,37 @@ static inline int kref_put(struct kref *kref, void (*release)(struct kref *kref) return 0; } +/** + * kref_put_mutex - Decrement refcount for object + * @kref: Object + * @release: Pointer to the function that will clean up the object when the + * last reference to the object is released. + * @mutex: Mutex which protects the release function. + * + * This variant of kref_lock() calls the @release function with the @mutex + * held. The @release function will release the mutex. + */ static inline int kref_put_mutex(struct kref *kref, void (*release)(struct kref *kref), - struct mutex *lock) + struct mutex *mutex) { - if (refcount_dec_and_mutex_lock(&kref->refcount, lock)) { + if (refcount_dec_and_mutex_lock(&kref->refcount, mutex)) { release(kref); return 1; } return 0; } +/** + * kref_put_lock - Decrement refcount for object + * @kref: Object + * @release: Pointer to the function that will clean up the object when the + * last reference to the object is released. + * @lock: Spinlock which protects the release function. + * + * This variant of kref_lock() calls the @release function with the @lock + * held. The @release function will release the lock. + */ static inline int kref_put_lock(struct kref *kref, void (*release)(struct kref *kref), spinlock_t *lock) @@ -94,8 +114,6 @@ static inline int kref_put_lock(struct kref *kref, * kref_get_unless_zero - Increment refcount for object unless it is zero. * @kref: object. * - * Return non-zero if the increment succeeded. Otherwise return 0. - * * This function is intended to simplify locking around refcounting for * objects that can be looked up from a lookup structure, and which are * removed from that lookup structure in the object destructor. @@ -105,6 +123,8 @@ static inline int kref_put_lock(struct kref *kref, * With a lookup followed by a kref_get_unless_zero *with return value check* * locking in the kref_put path can be deferred to the actual removal from * the lookup structure and RCU lookups become trivial. + * + * Return: non-zero if the increment succeeded. Otherwise return 0. */ static inline int __must_check kref_get_unless_zero(struct kref *kref) { diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 401348e9f92b..d73095b5cd96 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -13,7 +13,6 @@ #include <linux/pagemap.h> #include <linux/rmap.h> #include <linux/sched.h> -#include <linux/sched/coredump.h> #ifdef CONFIG_KSM int ksm_madvise(struct vm_area_struct *vma, unsigned long start, @@ -33,28 +32,38 @@ void __ksm_exit(struct mm_struct *mm); */ #define is_ksm_zero_pte(pte) (is_zero_pfn(pte_pfn(pte)) && pte_dirty(pte)) -extern unsigned long ksm_zero_pages; +extern atomic_long_t ksm_zero_pages; + +static inline void ksm_map_zero_page(struct mm_struct *mm) +{ + atomic_long_inc(&ksm_zero_pages); + atomic_long_inc(&mm->ksm_zero_pages); +} static inline void ksm_might_unmap_zero_page(struct mm_struct *mm, pte_t pte) { if (is_ksm_zero_pte(pte)) { - ksm_zero_pages--; - mm->ksm_zero_pages--; + atomic_long_dec(&ksm_zero_pages); + atomic_long_dec(&mm->ksm_zero_pages); } } -static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) +static inline long mm_ksm_zero_pages(struct mm_struct *mm) { - int ret; + return atomic_long_read(&mm->ksm_zero_pages); +} - if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags)) { - ret = __ksm_enter(mm); - if (ret) - return ret; - } +static inline void ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) +{ + /* Adding mm to ksm is best effort on fork. */ + if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags)) + __ksm_enter(mm); +} - if (test_bit(MMF_VM_MERGE_ANY, &oldmm->flags)) - set_bit(MMF_VM_MERGE_ANY, &mm->flags); +static inline int ksm_execve(struct mm_struct *mm) +{ + if (test_bit(MMF_VM_MERGE_ANY, &mm->flags)) + return __ksm_enter(mm); return 0; } @@ -81,15 +90,10 @@ struct folio *ksm_might_need_to_copy(struct folio *folio, void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc); void folio_migrate_ksm(struct folio *newfolio, struct folio *folio); - -#ifdef CONFIG_MEMORY_FAILURE -void collect_procs_ksm(struct page *page, struct list_head *to_kill, - int force_early); -#endif - -#ifdef CONFIG_PROC_FS +void collect_procs_ksm(const struct folio *folio, const struct page *page, + struct list_head *to_kill, int force_early); long ksm_process_profit(struct mm_struct *); -#endif /* CONFIG_PROC_FS */ +bool ksm_process_mergeable(struct mm_struct *mm); #else /* !CONFIG_KSM */ @@ -102,7 +106,11 @@ static inline int ksm_disable(struct mm_struct *mm) return 0; } -static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) +static inline void ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) +{ +} + +static inline int ksm_execve(struct mm_struct *mm) { return 0; } @@ -115,12 +123,11 @@ static inline void ksm_might_unmap_zero_page(struct mm_struct *mm, pte_t pte) { } -#ifdef CONFIG_MEMORY_FAILURE -static inline void collect_procs_ksm(struct page *page, - struct list_head *to_kill, int force_early) +static inline void collect_procs_ksm(const struct folio *folio, + const struct page *page, struct list_head *to_kill, + int force_early) { } -#endif #ifdef CONFIG_MMU static inline int ksm_madvise(struct vm_area_struct *vma, unsigned long start, diff --git a/include/linux/kthread.h b/include/linux/kthread.h index b11f53c1ba2e..8d27403888ce 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -85,6 +85,7 @@ kthread_run_on_cpu(int (*threadfn)(void *data), void *data, void free_kthread_struct(struct task_struct *k); void kthread_bind(struct task_struct *k, unsigned int cpu); void kthread_bind_mask(struct task_struct *k, const struct cpumask *mask); +int kthread_affine_preferred(struct task_struct *p, const struct cpumask *mask); int kthread_stop(struct task_struct *k); int kthread_stop_put(struct task_struct *k); bool kthread_should_stop(void); @@ -186,13 +187,58 @@ extern void __kthread_init_worker(struct kthread_worker *worker, int kthread_worker_fn(void *worker_ptr); -__printf(2, 3) -struct kthread_worker * -kthread_create_worker(unsigned int flags, const char namefmt[], ...); +__printf(3, 4) +struct kthread_worker *kthread_create_worker_on_node(unsigned int flags, + int node, + const char namefmt[], ...); + +#define kthread_create_worker(flags, namefmt, ...) \ + kthread_create_worker_on_node(flags, NUMA_NO_NODE, namefmt, ## __VA_ARGS__); + +/** + * kthread_run_worker - create and wake a kthread worker. + * @flags: flags modifying the default behavior of the worker + * @namefmt: printf-style name for the thread. + * + * Description: Convenient wrapper for kthread_create_worker() followed by + * wake_up_process(). Returns the kthread_worker or ERR_PTR(-ENOMEM). + */ +#define kthread_run_worker(flags, namefmt, ...) \ +({ \ + struct kthread_worker *__kw \ + = kthread_create_worker(flags, namefmt, ## __VA_ARGS__); \ + if (!IS_ERR(__kw)) \ + wake_up_process(__kw->task); \ + __kw; \ +}) -__printf(3, 4) struct kthread_worker * +struct kthread_worker * kthread_create_worker_on_cpu(int cpu, unsigned int flags, - const char namefmt[], ...); + const char namefmt[]); + +/** + * kthread_run_worker_on_cpu - create and wake a cpu bound kthread worker. + * @cpu: CPU number + * @flags: flags modifying the default behavior of the worker + * @namefmt: printf-style name for the thread. Format is restricted + * to "name.*%u". Code fills in cpu number. + * + * Description: Convenient wrapper for kthread_create_worker_on_cpu() + * followed by wake_up_process(). Returns the kthread_worker or + * ERR_PTR(-ENOMEM). + */ +static inline struct kthread_worker * +kthread_run_worker_on_cpu(int cpu, unsigned int flags, + const char namefmt[]) +{ + struct kthread_worker *kw; + + kw = kthread_create_worker_on_cpu(cpu, flags, namefmt); + if (!IS_ERR(kw)) + wake_up_process(kw->task); + + return kw; +} bool kthread_queue_work(struct kthread_worker *worker, struct kthread_work *work); diff --git a/include/linux/ktime.h b/include/linux/ktime.h index 3a4e723eae0f..383ed9985802 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -222,6 +222,11 @@ static inline ktime_t ns_to_ktime(u64 ns) return ns; } +static inline ktime_t us_to_ktime(u64 us) +{ + return us * NSEC_PER_USEC; +} + static inline ktime_t ms_to_ktime(u64 ms) { return ms * NSEC_PER_MSEC; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 48f31dcd318a..3cb9a32a6330 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -97,6 +97,7 @@ #define KVM_PFN_ERR_HWPOISON (KVM_PFN_ERR_MASK + 1) #define KVM_PFN_ERR_RO_FAULT (KVM_PFN_ERR_MASK + 2) #define KVM_PFN_ERR_SIGPENDING (KVM_PFN_ERR_MASK + 3) +#define KVM_PFN_ERR_NEEDS_IO (KVM_PFN_ERR_MASK + 4) /* * error pfns indicate that the gfn is in slot but faild to @@ -153,13 +154,6 @@ static inline bool kvm_is_error_gpa(gpa_t gpa) return gpa == INVALID_GPA; } -#define KVM_ERR_PTR_BAD_PAGE (ERR_PTR(-ENOENT)) - -static inline bool is_error_page(struct page *page) -{ - return IS_ERR(page); -} - #define KVM_REQUEST_MASK GENMASK(7,0) #define KVM_REQUEST_NO_WAKEUP BIT(8) #define KVM_REQUEST_WAIT BIT(9) @@ -193,8 +187,6 @@ static inline bool is_error_page(struct page *page) bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, unsigned long *vcpu_bitmap); bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req); -bool kvm_make_all_cpus_request_except(struct kvm *kvm, unsigned int req, - struct kvm_vcpu *except); #define KVM_USERSPACE_IRQ_SOURCE_ID 0 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID 1 @@ -221,6 +213,7 @@ enum kvm_bus { KVM_PIO_BUS, KVM_VIRTIO_CCW_NOTIFY_BUS, KVM_FAST_MMIO_BUS, + KVM_IOCSR_BUS, KVM_NR_BUSES }; @@ -259,21 +252,25 @@ int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu); #ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER union kvm_mmu_notifier_arg { - pte_t pte; unsigned long attributes; }; +enum kvm_gfn_range_filter { + KVM_FILTER_SHARED = BIT(0), + KVM_FILTER_PRIVATE = BIT(1), +}; + struct kvm_gfn_range { struct kvm_memory_slot *slot; gfn_t start; gfn_t end; union kvm_mmu_notifier_arg arg; + enum kvm_gfn_range_filter attr_filter; bool may_block; }; bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range); bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range); bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range); -bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range); #endif enum { @@ -283,21 +280,19 @@ enum { READING_SHADOW_PAGE_TABLES, }; -#define KVM_UNMAPPED_PAGE ((void *) 0x500 + POISON_POINTER_DELTA) - struct kvm_host_map { /* * Only valid if the 'pfn' is managed by the host kernel (i.e. There is * a 'struct page' for it. When using mem= kernel parameter some memory * can be used as guest memory but they are not managed by host * kernel). - * If 'pfn' is not managed by the host kernel, this field is - * initialized to KVM_UNMAPPED_PAGE. */ + struct page *pinned_page; struct page *page; void *hva; kvm_pfn_t pfn; kvm_pfn_t gfn; + bool writable; }; /* @@ -346,7 +341,8 @@ struct kvm_vcpu { #ifndef __KVM_HAVE_ARCH_WQP struct rcuwait wait; #endif - struct pid __rcu *pid; + struct pid *pid; + rwlock_t pid_lock; int sigset_active; sigset_t sigset; unsigned int halt_poll_ns; @@ -382,8 +378,10 @@ struct kvm_vcpu { bool dy_eligible; } spin_loop; #endif + bool wants_to_run; bool preempted; bool ready; + bool scheduled_out; struct kvm_vcpu_arch arch; struct kvm_vcpu_stat stat; char stats_id[KVM_STATS_NAME_SIZE]; @@ -487,7 +485,15 @@ static __always_inline void guest_state_enter_irqoff(void) */ static __always_inline void guest_context_exit_irqoff(void) { - context_tracking_guest_exit(); + /* + * Guest mode is treated as a quiescent state, see + * guest_context_enter_irqoff() for more details. + */ + if (!context_tracking_guest_exit()) { + instrumentation_begin(); + rcu_virt_note_context_switch(); + instrumentation_end(); + } } /* @@ -596,7 +602,12 @@ struct kvm_memory_slot { #ifdef CONFIG_KVM_PRIVATE_MEM struct { - struct file __rcu *file; + /* + * Writes protected by kvm->slots_lock. Acquiring a + * reference via kvm_gmem_get_file() is protected by + * either kvm->slots_lock or kvm->srcu. + */ + struct file *file; pgoff_t pgoff; } gmem; #endif @@ -717,6 +728,13 @@ static inline bool kvm_arch_has_private_mem(struct kvm *kvm) } #endif +#ifndef kvm_arch_has_readonly_mem +static inline bool kvm_arch_has_readonly_mem(struct kvm *kvm) +{ + return IS_ENABLED(CONFIG_HAVE_KVM_READONLY_MEM); +} +#endif + struct kvm_memslots { u64 generation; atomic_long_t last_used_slot; @@ -956,6 +974,15 @@ static inline struct kvm_io_bus *kvm_get_bus(struct kvm *kvm, enum kvm_bus idx) static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i) { int num_vcpus = atomic_read(&kvm->online_vcpus); + + /* + * Explicitly verify the target vCPU is online, as the anti-speculation + * logic only limits the CPU's ability to speculate, e.g. given a "bad" + * index, clamping the index to 0 would return vCPU0, not NULL. + */ + if (i >= num_vcpus) + return NULL; + i = array_index_nospec(i, num_vcpus); /* Pairs with smp_wmb() in kvm_vm_ioctl_create_vcpu. */ @@ -963,9 +990,10 @@ static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i) return xa_load(&kvm->vcpu_array, i); } -#define kvm_for_each_vcpu(idx, vcpup, kvm) \ - xa_for_each_range(&kvm->vcpu_array, idx, vcpup, 0, \ - (atomic_read(&kvm->online_vcpus) - 1)) +#define kvm_for_each_vcpu(idx, vcpup, kvm) \ + if (atomic_read(&kvm->online_vcpus)) \ + xa_for_each_range(&kvm->vcpu_array, idx, vcpup, 0, \ + (atomic_read(&kvm->online_vcpus) - 1)) static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id) { @@ -1163,6 +1191,10 @@ static inline bool kvm_memslot_iter_is_valid(struct kvm_memslot_iter *iter, gfn_ kvm_memslot_iter_is_valid(iter, end); \ kvm_memslot_iter_next(iter)) +struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn); +struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu); +struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn); + /* * KVM_SET_USER_MEMORY_REGION ioctl allows the following operations: * - create a new memory slot @@ -1172,7 +1204,7 @@ static inline bool kvm_memslot_iter_is_valid(struct kvm_memslot_iter *iter, gfn_ * -- just change its flags * * Since flags can be changed by some of these operations, the following - * differentiation is the best we can do for __kvm_set_memory_region(): + * differentiation is the best we can do for kvm_set_memory_region(): */ enum kvm_mr_change { KVM_MR_CREATE, @@ -1181,10 +1213,8 @@ enum kvm_mr_change { KVM_MR_FLAGS_ONLY, }; -int kvm_set_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region2 *mem); -int __kvm_set_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region2 *mem); +int kvm_set_internal_memslot(struct kvm *kvm, + const struct kvm_userspace_memory_region2 *mem); void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot); void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen); int kvm_arch_prepare_memory_region(struct kvm *kvm, @@ -1201,33 +1231,70 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm); void kvm_arch_flush_shadow_memslot(struct kvm *kvm, struct kvm_memory_slot *slot); -int gfn_to_page_many_atomic(struct kvm_memory_slot *slot, gfn_t gfn, - struct page **pages, int nr_pages); +int kvm_prefetch_pages(struct kvm_memory_slot *slot, gfn_t gfn, + struct page **pages, int nr_pages); + +struct page *__gfn_to_page(struct kvm *kvm, gfn_t gfn, bool write); +static inline struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn) +{ + return __gfn_to_page(kvm, gfn, true); +} -struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn); unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn); unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable); unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn); unsigned long gfn_to_hva_memslot_prot(struct kvm_memory_slot *slot, gfn_t gfn, bool *writable); + +static inline void kvm_release_page_unused(struct page *page) +{ + if (!page) + return; + + put_page(page); +} + void kvm_release_page_clean(struct page *page); void kvm_release_page_dirty(struct page *page); -kvm_pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn); -kvm_pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault, - bool *writable); -kvm_pfn_t gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn); -kvm_pfn_t gfn_to_pfn_memslot_atomic(const struct kvm_memory_slot *slot, gfn_t gfn); -kvm_pfn_t __gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn, - bool atomic, bool interruptible, bool *async, - bool write_fault, bool *writable, hva_t *hva); +static inline void kvm_release_faultin_page(struct kvm *kvm, struct page *page, + bool unused, bool dirty) +{ + lockdep_assert_once(lockdep_is_held(&kvm->mmu_lock) || unused); -void kvm_release_pfn_clean(kvm_pfn_t pfn); -void kvm_release_pfn_dirty(kvm_pfn_t pfn); -void kvm_set_pfn_dirty(kvm_pfn_t pfn); -void kvm_set_pfn_accessed(kvm_pfn_t pfn); + if (!page) + return; + + /* + * If the page that KVM got from the *primary MMU* is writable, and KVM + * installed or reused a SPTE, mark the page/folio dirty. Note, this + * may mark a folio dirty even if KVM created a read-only SPTE, e.g. if + * the GFN is write-protected. Folios can't be safely marked dirty + * outside of mmu_lock as doing so could race with writeback on the + * folio. As a result, KVM can't mark folios dirty in the fast page + * fault handler, and so KVM must (somewhat) speculatively mark the + * folio dirty if KVM could locklessly make the SPTE writable. + */ + if (unused) + kvm_release_page_unused(page); + else if (dirty) + kvm_release_page_dirty(page); + else + kvm_release_page_clean(page); +} + +kvm_pfn_t __kvm_faultin_pfn(const struct kvm_memory_slot *slot, gfn_t gfn, + unsigned int foll, bool *writable, + struct page **refcounted_page); + +static inline kvm_pfn_t kvm_faultin_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, + bool write, bool *writable, + struct page **refcounted_page) +{ + return __kvm_faultin_pfn(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn, + write ? FOLL_WRITE : 0, writable, refcounted_page); +} -void kvm_release_pfn(kvm_pfn_t pfn, bool dirty); int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, int len); int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len); @@ -1291,19 +1358,28 @@ int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc, }) int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len); -struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn); bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn); bool kvm_vcpu_is_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn); unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn); void mark_page_dirty_in_slot(struct kvm *kvm, const struct kvm_memory_slot *memslot, gfn_t gfn); void mark_page_dirty(struct kvm *kvm, gfn_t gfn); -struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu); -struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn); -kvm_pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn); -kvm_pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn); -int kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map); -void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty); +int __kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map, + bool writable); +void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map); + +static inline int kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, + struct kvm_host_map *map) +{ + return __kvm_vcpu_map(vcpu, gpa, map, true); +} + +static inline int kvm_vcpu_map_readonly(struct kvm_vcpu *vcpu, gpa_t gpa, + struct kvm_host_map *map) +{ + return __kvm_vcpu_map(vcpu, gpa, map, false); +} + unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn); unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *writable); int kvm_vcpu_read_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, void *data, int offset, @@ -1498,8 +1574,6 @@ 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); -void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu); - void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu); void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu); int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id); @@ -1518,8 +1592,22 @@ 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); +/* + * kvm_arch_{enable,disable}_virtualization() are called on one CPU, under + * kvm_usage_lock, immediately after/before 0=>1 and 1=>0 transitions of + * kvm_usage_count, i.e. at the beginning of the generic hardware enabling + * sequence, and at the end of the generic hardware disabling sequence. + */ +void kvm_arch_enable_virtualization(void); +void kvm_arch_disable_virtualization(void); +/* + * kvm_arch_{enable,disable}_virtualization_cpu() are called on "every" CPU to + * do the actual twiddling of hardware bits. The hooks are called on all + * online CPUs when KVM enables/disabled virtualization, and on a single CPU + * when that CPU is onlined/offlined (including for Resume/Suspend). + */ +int kvm_arch_enable_virtualization_cpu(void); +void kvm_arch_disable_virtualization_cpu(void); #endif int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu); bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu); @@ -1663,9 +1751,6 @@ void kvm_arch_sync_events(struct kvm *kvm); int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu); -struct page *kvm_pfn_to_refcounted_page(kvm_pfn_t pfn); -bool kvm_is_zone_device_page(struct page *page); - struct kvm_irq_ack_notifier { struct hlist_node link; unsigned gsi; @@ -1959,8 +2044,6 @@ struct _kvm_stats_desc { HALT_POLL_HIST_COUNT), \ STATS_DESC_IBOOLEAN(VCPU_GENERIC, blocking) -extern struct dentry *kvm_debugfs_dir; - ssize_t kvm_stats_read(char *id, const struct kvm_stats_header *header, const struct _kvm_stats_desc *desc, void *stats, size_t size_stats, @@ -2100,6 +2183,7 @@ int kvm_set_irq_routing(struct kvm *kvm, const struct kvm_irq_routing_entry *entries, unsigned nr, unsigned flags); +int kvm_init_irq_routing(struct kvm *kvm); int kvm_set_routing_entry(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, const struct kvm_irq_routing_entry *ue); @@ -2109,6 +2193,11 @@ void kvm_free_irq_routing(struct kvm *kvm); static inline void kvm_free_irq_routing(struct kvm *kvm) {} +static inline int kvm_init_irq_routing(struct kvm *kvm) +{ + return 0; +} + #endif int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi); @@ -2355,12 +2444,6 @@ static inline int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu) } #endif /* CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE */ -typedef int (*kvm_vm_thread_fn_t)(struct kvm *kvm, uintptr_t data); - -int kvm_vm_create_worker_thread(struct kvm *kvm, kvm_vm_thread_fn_t thread_fn, - uintptr_t data, const char *name, - struct task_struct **thread_ptr); - #ifdef CONFIG_KVM_XFER_TO_GUEST_WORK static inline void kvm_handle_signal_exit(struct kvm_vcpu *vcpu) { @@ -2414,7 +2497,7 @@ static inline unsigned long kvm_get_memory_attributes(struct kvm *kvm, gfn_t gfn } bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end, - unsigned long attrs); + unsigned long mask, unsigned long attrs); bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm, struct kvm_gfn_range *range); bool kvm_arch_post_set_memory_attributes(struct kvm *kvm, @@ -2434,15 +2517,59 @@ static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn) #ifdef CONFIG_KVM_PRIVATE_MEM int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot, - gfn_t gfn, kvm_pfn_t *pfn, int *max_order); + gfn_t gfn, kvm_pfn_t *pfn, struct page **page, + int *max_order); #else static inline int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn, - kvm_pfn_t *pfn, int *max_order) + kvm_pfn_t *pfn, struct page **page, + int *max_order) { KVM_BUG_ON(1, kvm); return -EIO; } #endif /* CONFIG_KVM_PRIVATE_MEM */ +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE +int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_order); +#endif + +#ifdef CONFIG_KVM_GENERIC_PRIVATE_MEM +/** + * kvm_gmem_populate() - Populate/prepare a GPA range with guest data + * + * @kvm: KVM instance + * @gfn: starting GFN to be populated + * @src: userspace-provided buffer containing data to copy into GFN range + * (passed to @post_populate, and incremented on each iteration + * if not NULL) + * @npages: number of pages to copy from userspace-buffer + * @post_populate: callback to issue for each gmem page that backs the GPA + * range + * @opaque: opaque data to pass to @post_populate callback + * + * This is primarily intended for cases where a gmem-backed GPA range needs + * to be initialized with userspace-provided data prior to being mapped into + * the guest as a private page. This should be called with the slots->lock + * held so that caller-enforced invariants regarding the expected memory + * attributes of the GPA range do not race with KVM_SET_MEMORY_ATTRIBUTES. + * + * Returns the number of pages that were populated. + */ +typedef int (*kvm_gmem_populate_cb)(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, + void __user *src, int order, void *opaque); + +long kvm_gmem_populate(struct kvm *kvm, gfn_t gfn, void __user *src, long npages, + kvm_gmem_populate_cb post_populate, void *opaque); +#endif + +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE +void kvm_arch_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end); +#endif + +#ifdef CONFIG_KVM_GENERIC_PRE_FAULT_MEMORY +long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu, + struct kvm_pre_fault_memory *range); +#endif + #endif diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index d93f6522b2c3..827ecc0b7e10 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -86,6 +86,7 @@ struct gfn_to_pfn_cache { struct kvm_mmu_memory_cache { gfp_t gfp_zero; gfp_t gfp_custom; + u64 init_value; struct kmem_cache *kmem_cache; int capacity; int nobjs; diff --git a/include/linux/lcd.h b/include/linux/lcd.h index 238fb1dfed98..c3ccdff4519a 100644 --- a/include/linux/lcd.h +++ b/include/linux/lcd.h @@ -12,7 +12,11 @@ #include <linux/device.h> #include <linux/mutex.h> #include <linux/notifier.h> -#include <linux/fb.h> + +#define LCD_POWER_ON (0) +#define LCD_POWER_REDUCED (1) // deprecated; don't use in new code +#define LCD_POWER_REDUCED_VSYNC_SUSPEND (2) // deprecated; don't use in new code +#define LCD_POWER_OFF (4) /* Notes on locking: * @@ -30,7 +34,6 @@ */ struct lcd_device; -struct fb_info; struct lcd_properties { /* The maximum value for contrast (read-only) */ @@ -47,11 +50,23 @@ struct lcd_ops { int (*get_contrast)(struct lcd_device *); /* Set LCD panel contrast */ int (*set_contrast)(struct lcd_device *, int contrast); - /* Set LCD panel mode (resolutions ...) */ - int (*set_mode)(struct lcd_device *, struct fb_videomode *); - /* Check if given framebuffer device is the one LCD is bound to; - return 0 if not, !=0 if it is. If NULL, lcd always matches the fb. */ - int (*check_fb)(struct lcd_device *, struct fb_info *); + + /* + * Set LCD panel mode (resolutions ...) + */ + int (*set_mode)(struct lcd_device *lcd, u32 xres, u32 yres); + + /* + * Check if the LCD controls the given display device. This + * operation is optional and if not implemented it is assumed that + * the display is always the one controlled by the LCD. + * + * RETURNS: + * + * If display_dev is NULL or display_dev matches the device controlled by + * the LCD, return true. Otherwise return false. + */ + bool (*controls_device)(struct lcd_device *lcd, struct device *display_device); }; struct lcd_device { @@ -61,7 +76,7 @@ struct lcd_device { points to something in the body of that driver, it is also invalid. */ struct mutex ops_lock; /* If this is NULL, the backing module is unloaded */ - struct lcd_ops *ops; + const struct lcd_ops *ops; /* Serialise access to set_power method */ struct mutex update_lock; /* The framebuffer notifier block */ @@ -102,10 +117,10 @@ static inline void lcd_set_power(struct lcd_device *ld, int power) } extern struct lcd_device *lcd_device_register(const char *name, - struct device *parent, void *devdata, struct lcd_ops *ops); + struct device *parent, void *devdata, const struct lcd_ops *ops); extern struct lcd_device *devm_lcd_device_register(struct device *dev, const char *name, struct device *parent, - void *devdata, struct lcd_ops *ops); + void *devdata, const struct lcd_ops *ops); extern void lcd_device_unregister(struct lcd_device *ld); extern void devm_lcd_device_unregister(struct device *dev, struct lcd_device *ld); diff --git a/include/linux/leds.h b/include/linux/leds.h index db6b114bb3d9..98f9719c924c 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -107,6 +107,8 @@ struct led_classdev { #define LED_BRIGHT_HW_CHANGED BIT(21) #define LED_RETAIN_AT_SHUTDOWN BIT(22) #define LED_INIT_DEFAULT_TRIGGER BIT(23) +#define LED_REJECT_NAME_CONFLICT BIT(24) +#define LED_MULTI_COLOR BIT(25) /* set_brightness_work / blink_timer flags, atomic, private. */ unsigned long work_flags; @@ -169,6 +171,7 @@ struct led_classdev { int new_blink_brightness; void (*flash_resume)(struct led_classdev *led_cdev); + struct workqueue_struct *wq; /* LED workqueue */ struct work_struct set_brightness_work; int delayed_set_value; unsigned long delayed_delay_on; @@ -236,7 +239,7 @@ struct led_classdev { struct kernfs_node *brightness_hw_changed_kn; #endif - /* Ensures consistent access to the LED Flash Class device */ + /* Ensures consistent access to the LED class device */ struct mutex led_access; }; @@ -374,6 +377,25 @@ void led_set_brightness(struct led_classdev *led_cdev, unsigned int brightness); int led_set_brightness_sync(struct led_classdev *led_cdev, unsigned int value); /** + * led_mc_set_brightness - set mc LED color intensity values and brightness + * @led_cdev: the LED to set + * @intensity_value: array of per color intensity values to set + * @num_colors: amount of entries in intensity_value array + * @brightness: the brightness to set the LED to + * + * Set a multi-color LED's per color intensity values and brightness. + * If necessary, this cancels the software blink timer. This function is + * guaranteed not to sleep. + * + * Calling this function on a non multi-color led_classdev or with the wrong + * num_colors value is an error. In this case an error will be logged once + * and the call will do nothing. + */ +void led_mc_set_brightness(struct led_classdev *led_cdev, + unsigned int *intensity_value, unsigned int num_colors, + unsigned int brightness); + +/** * led_update_brightness - update LED brightness * @led_cdev: the LED to query * @@ -428,6 +450,16 @@ int led_compose_name(struct device *dev, struct led_init_data *init_data, char *led_classdev_name); /** + * led_get_color_name - get string representation of color ID + * @color_id: The LED_COLOR_ID_* constant + * + * Get the string name of a LED_COLOR_ID_* constant. + * + * Returns: A string constant or NULL on an invalid ID. + */ +const char *led_get_color_name(u8 color_id); + +/** * led_sysfs_is_disabled - check if LED sysfs interface is disabled * @led_cdev: the LED to query * @@ -455,6 +487,9 @@ struct led_trigger { int (*activate)(struct led_classdev *led_cdev); void (*deactivate)(struct led_classdev *led_cdev); + /* Brightness set by led_trigger_event */ + enum led_brightness brightness; + /* LED-private triggers have this set */ struct led_hw_trigger_type *trigger_type; @@ -487,6 +522,9 @@ void led_trigger_register_simple(const char *name, struct led_trigger **trigger); void led_trigger_unregister_simple(struct led_trigger *trigger); void led_trigger_event(struct led_trigger *trigger, enum led_brightness event); +void led_mc_trigger_event(struct led_trigger *trig, + unsigned int *intensity_value, unsigned int num_colors, + enum led_brightness brightness); void led_trigger_blink(struct led_trigger *trigger, unsigned long delay_on, unsigned long delay_off); void led_trigger_blink_oneshot(struct led_trigger *trigger, @@ -508,6 +546,12 @@ static inline void *led_get_trigger_data(struct led_classdev *led_cdev) return led_cdev->trigger_data; } +static inline enum led_brightness +led_trigger_get_brightness(const struct led_trigger *trigger) +{ + return trigger ? trigger->brightness : LED_OFF; +} + #define module_led_trigger(__led_trigger) \ module_driver(__led_trigger, led_trigger_register, \ led_trigger_unregister) @@ -523,6 +567,9 @@ static inline void led_trigger_register_simple(const char *name, static inline void led_trigger_unregister_simple(struct led_trigger *trigger) {} static inline void led_trigger_event(struct led_trigger *trigger, enum led_brightness event) {} +static inline void led_mc_trigger_event(struct led_trigger *trig, + unsigned int *intensity_value, unsigned int num_colors, + enum led_brightness brightness) {} static inline void led_trigger_blink(struct led_trigger *trigger, unsigned long delay_on, unsigned long delay_off) {} @@ -544,6 +591,12 @@ static inline void *led_get_trigger_data(struct led_classdev *led_cdev) return NULL; } +static inline enum led_brightness +led_trigger_get_brightness(const struct led_trigger *trigger) +{ + return LED_OFF; +} + #endif /* CONFIG_LEDS_TRIGGERS */ /* Trigger specific enum */ @@ -559,6 +612,8 @@ enum led_trigger_netdev_modes { TRIGGER_NETDEV_FULL_DUPLEX, TRIGGER_NETDEV_TX, TRIGGER_NETDEV_RX, + TRIGGER_NETDEV_TX_ERR, + TRIGGER_NETDEV_RX_ERR, /* Keep last */ __TRIGGER_NETDEV_MAX, @@ -690,18 +745,4 @@ enum led_audio { NUM_AUDIO_LEDS }; -#if IS_ENABLED(CONFIG_LEDS_TRIGGER_AUDIO) -enum led_brightness ledtrig_audio_get(enum led_audio type); -void ledtrig_audio_set(enum led_audio type, enum led_brightness state); -#else -static inline enum led_brightness ledtrig_audio_get(enum led_audio type) -{ - return LED_OFF; -} -static inline void ledtrig_audio_set(enum led_audio type, - enum led_brightness state) -{ -} -#endif - #endif /* __LINUX_LEDS_H_INCLUDED */ diff --git a/include/linux/libata.h b/include/linux/libata.h index 324d792e7c78..c1c57f814b98 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -55,6 +55,46 @@ /* defines only for the constants which don't work well as enums */ #define ATA_TAG_POISON 0xfafbfcfdU +/* + * Quirk flags bits. + * ata_device->quirks is an unsigned int, so __ATA_QUIRK_MAX must not exceed 32. + */ +enum ata_quirks { + __ATA_QUIRK_DIAGNOSTIC, /* Failed boot diag */ + __ATA_QUIRK_NODMA, /* DMA problems */ + __ATA_QUIRK_NONCQ, /* Don't use NCQ */ + __ATA_QUIRK_MAX_SEC_128, /* Limit max sects to 128 */ + __ATA_QUIRK_BROKEN_HPA, /* Broken HPA */ + __ATA_QUIRK_DISABLE, /* Disable it */ + __ATA_QUIRK_HPA_SIZE, /* Native size off by one */ + __ATA_QUIRK_IVB, /* cbl det validity bit bugs */ + __ATA_QUIRK_STUCK_ERR, /* Stuck ERR on next PACKET */ + __ATA_QUIRK_BRIDGE_OK, /* No bridge limits */ + __ATA_QUIRK_ATAPI_MOD16_DMA, /* Use ATAPI DMA for commands that */ + /* are not a multiple of 16 bytes */ + __ATA_QUIRK_FIRMWARE_WARN, /* Firmware update warning */ + __ATA_QUIRK_1_5_GBPS, /* Force 1.5 Gbps */ + __ATA_QUIRK_NOSETXFER, /* Skip SETXFER, SATA only */ + __ATA_QUIRK_BROKEN_FPDMA_AA, /* Skip AA */ + __ATA_QUIRK_DUMP_ID, /* Dump IDENTIFY data */ + __ATA_QUIRK_MAX_SEC_LBA48, /* Set max sects to 65535 */ + __ATA_QUIRK_ATAPI_DMADIR, /* Device requires dmadir */ + __ATA_QUIRK_NO_NCQ_TRIM, /* Do not use queued TRIM */ + __ATA_QUIRK_NOLPM, /* Do not use LPM */ + __ATA_QUIRK_WD_BROKEN_LPM, /* Some WDs have broken LPM */ + __ATA_QUIRK_ZERO_AFTER_TRIM, /* Guarantees zero after trim */ + __ATA_QUIRK_NO_DMA_LOG, /* Do not use DMA for log read */ + __ATA_QUIRK_NOTRIM, /* Do not use TRIM */ + __ATA_QUIRK_MAX_SEC_1024, /* Limit max sects to 1024 */ + __ATA_QUIRK_MAX_TRIM_128M, /* Limit max trim size to 128M */ + __ATA_QUIRK_NO_NCQ_ON_ATI, /* Disable NCQ on ATI chipset */ + __ATA_QUIRK_NO_ID_DEV_LOG, /* Identify device log missing */ + __ATA_QUIRK_NO_LOG_DIR, /* Do not read log directory */ + __ATA_QUIRK_NO_FUA, /* Do not use FUA */ + + __ATA_QUIRK_MAX, +}; + enum { /* various global constants */ LIBATA_MAX_PRD = ATA_MAX_PRD / 2, @@ -230,9 +270,7 @@ enum { /* bits 24:31 of host->flags are reserved for LLD specific flags */ - /* various lengths of time */ - ATA_TMOUT_BOOT = 30000, /* heuristic */ - ATA_TMOUT_BOOT_QUICK = 7000, /* heuristic */ + /* Various lengths of time */ ATA_TMOUT_INTERNAL_QUICK = 5000, ATA_TMOUT_MAX_PARK = 30000, @@ -338,6 +376,7 @@ enum { ATA_EHI_PRINTINFO = (1 << 18), /* print configuration info */ ATA_EHI_SETMODE = (1 << 19), /* configure transfer mode */ ATA_EHI_POST_SETMODE = (1 << 20), /* revalidating after setmode */ + ATA_EHI_DID_PRINT_QUIRKS = (1 << 21), /* already printed quirks info */ ATA_EHI_DID_RESET = ATA_EHI_DID_SOFTRESET | ATA_EHI_DID_HARDRESET, @@ -362,43 +401,42 @@ enum { */ ATA_EH_CMD_TIMEOUT_TABLE_SIZE = 8, - /* Horkage types. May be set by libata or controller on drives - (some horkage may be drive/controller pair dependent */ - - ATA_HORKAGE_DIAGNOSTIC = (1 << 0), /* Failed boot diag */ - ATA_HORKAGE_NODMA = (1 << 1), /* DMA problems */ - ATA_HORKAGE_NONCQ = (1 << 2), /* Don't use NCQ */ - ATA_HORKAGE_MAX_SEC_128 = (1 << 3), /* Limit max sects to 128 */ - ATA_HORKAGE_BROKEN_HPA = (1 << 4), /* Broken HPA */ - ATA_HORKAGE_DISABLE = (1 << 5), /* Disable it */ - ATA_HORKAGE_HPA_SIZE = (1 << 6), /* native size off by one */ - ATA_HORKAGE_IVB = (1 << 8), /* cbl det validity bit bugs */ - ATA_HORKAGE_STUCK_ERR = (1 << 9), /* stuck ERR on next PACKET */ - ATA_HORKAGE_BRIDGE_OK = (1 << 10), /* no bridge limits */ - ATA_HORKAGE_ATAPI_MOD16_DMA = (1 << 11), /* use ATAPI DMA for commands - not multiple of 16 bytes */ - ATA_HORKAGE_FIRMWARE_WARN = (1 << 12), /* firmware update warning */ - ATA_HORKAGE_1_5_GBPS = (1 << 13), /* force 1.5 Gbps */ - ATA_HORKAGE_NOSETXFER = (1 << 14), /* skip SETXFER, SATA only */ - ATA_HORKAGE_BROKEN_FPDMA_AA = (1 << 15), /* skip AA */ - ATA_HORKAGE_DUMP_ID = (1 << 16), /* dump IDENTIFY data */ - ATA_HORKAGE_MAX_SEC_LBA48 = (1 << 17), /* Set max sects to 65535 */ - ATA_HORKAGE_ATAPI_DMADIR = (1 << 18), /* device requires dmadir */ - ATA_HORKAGE_NO_NCQ_TRIM = (1 << 19), /* don't use queued TRIM */ - ATA_HORKAGE_NOLPM = (1 << 20), /* don't use LPM */ - ATA_HORKAGE_WD_BROKEN_LPM = (1 << 21), /* some WDs have broken LPM */ - ATA_HORKAGE_ZERO_AFTER_TRIM = (1 << 22),/* guarantees zero after trim */ - ATA_HORKAGE_NO_DMA_LOG = (1 << 23), /* don't use DMA for log read */ - ATA_HORKAGE_NOTRIM = (1 << 24), /* don't use TRIM */ - ATA_HORKAGE_MAX_SEC_1024 = (1 << 25), /* Limit max sects to 1024 */ - ATA_HORKAGE_MAX_TRIM_128M = (1 << 26), /* Limit max trim size to 128M */ - 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 */ + /* + * Quirk flags: may be set by libata or controller drivers on drives. + * Some quirks may be drive/controller pair dependent. + */ + ATA_QUIRK_DIAGNOSTIC = (1U << __ATA_QUIRK_DIAGNOSTIC), + ATA_QUIRK_NODMA = (1U << __ATA_QUIRK_NODMA), + ATA_QUIRK_NONCQ = (1U << __ATA_QUIRK_NONCQ), + ATA_QUIRK_MAX_SEC_128 = (1U << __ATA_QUIRK_MAX_SEC_128), + ATA_QUIRK_BROKEN_HPA = (1U << __ATA_QUIRK_BROKEN_HPA), + ATA_QUIRK_DISABLE = (1U << __ATA_QUIRK_DISABLE), + ATA_QUIRK_HPA_SIZE = (1U << __ATA_QUIRK_HPA_SIZE), + ATA_QUIRK_IVB = (1U << __ATA_QUIRK_IVB), + ATA_QUIRK_STUCK_ERR = (1U << __ATA_QUIRK_STUCK_ERR), + ATA_QUIRK_BRIDGE_OK = (1U << __ATA_QUIRK_BRIDGE_OK), + ATA_QUIRK_ATAPI_MOD16_DMA = (1U << __ATA_QUIRK_ATAPI_MOD16_DMA), + ATA_QUIRK_FIRMWARE_WARN = (1U << __ATA_QUIRK_FIRMWARE_WARN), + ATA_QUIRK_1_5_GBPS = (1U << __ATA_QUIRK_1_5_GBPS), + ATA_QUIRK_NOSETXFER = (1U << __ATA_QUIRK_NOSETXFER), + ATA_QUIRK_BROKEN_FPDMA_AA = (1U << __ATA_QUIRK_BROKEN_FPDMA_AA), + ATA_QUIRK_DUMP_ID = (1U << __ATA_QUIRK_DUMP_ID), + ATA_QUIRK_MAX_SEC_LBA48 = (1U << __ATA_QUIRK_MAX_SEC_LBA48), + ATA_QUIRK_ATAPI_DMADIR = (1U << __ATA_QUIRK_ATAPI_DMADIR), + ATA_QUIRK_NO_NCQ_TRIM = (1U << __ATA_QUIRK_NO_NCQ_TRIM), + ATA_QUIRK_NOLPM = (1U << __ATA_QUIRK_NOLPM), + ATA_QUIRK_WD_BROKEN_LPM = (1U << __ATA_QUIRK_WD_BROKEN_LPM), + ATA_QUIRK_ZERO_AFTER_TRIM = (1U << __ATA_QUIRK_ZERO_AFTER_TRIM), + ATA_QUIRK_NO_DMA_LOG = (1U << __ATA_QUIRK_NO_DMA_LOG), + ATA_QUIRK_NOTRIM = (1U << __ATA_QUIRK_NOTRIM), + ATA_QUIRK_MAX_SEC_1024 = (1U << __ATA_QUIRK_MAX_SEC_1024), + ATA_QUIRK_MAX_TRIM_128M = (1U << __ATA_QUIRK_MAX_TRIM_128M), + ATA_QUIRK_NO_NCQ_ON_ATI = (1U << __ATA_QUIRK_NO_NCQ_ON_ATI), + ATA_QUIRK_NO_ID_DEV_LOG = (1U << __ATA_QUIRK_NO_ID_DEV_LOG), + ATA_QUIRK_NO_LOG_DIR = (1U << __ATA_QUIRK_NO_LOG_DIR), + ATA_QUIRK_NO_FUA = (1U << __ATA_QUIRK_NO_FUA), - /* DMA mask for user DMA control: User visible values; DO NOT - renumber */ + /* User visible DMA mask for DMA control. DO NOT renumber. */ ATA_DMA_MASK_ATA = (1 << 0), /* DMA on ATA Disk */ ATA_DMA_MASK_ATAPI = (1 << 1), /* DMA on ATAPI */ ATA_DMA_MASK_CFA = (1 << 2), /* DMA on CF Card */ @@ -660,10 +698,25 @@ struct ata_cpr_log { struct ata_cpr cpr[] __counted_by(nr_cpr); }; +struct ata_cdl { + /* + * Buffer to cache the CDL log page 18h (command duration descriptors) + * for SCSI-ATA translation. + */ + u8 desc_log_buf[ATA_LOG_CDL_SIZE]; + + /* + * Buffer to handle reading the sense data for successful NCQ Commands + * log page for commands using a CDL with one of the limits policy set + * to 0xD (successful completion with sense data available bit set). + */ + u8 ncq_sense_log_buf[ATA_LOG_SENSE_NCQ_SIZE]; +}; + struct ata_device { struct ata_link *link; unsigned int devno; /* 0 or 1 */ - unsigned int horkage; /* List of broken features */ + unsigned int quirks; /* List of broken features */ unsigned long flags; /* ATA_DFLAG_xxx */ struct scsi_device *sdev; /* attached SCSI device */ void *private_data; @@ -722,13 +775,16 @@ struct ata_device { /* Concurrent positioning ranges */ struct ata_cpr_log *cpr_log; - /* Command Duration Limits log support */ - u8 cdl[ATA_LOG_CDL_SIZE]; + /* Command Duration Limits support */ + struct ata_cdl *cdl; /* error history */ int spdn_cnt; /* ering is CLEAR_END, read comment above CLEAR_END */ struct ata_ering ering; + + /* For EH */ + u8 sector_buf[ATA_SECT_SIZE] ____cacheline_aligned; }; /* Fields between ATA_DEVICE_CLEAR_BEGIN and ATA_DEVICE_CLEAR_END are @@ -814,7 +870,6 @@ struct ata_port { /* Flags that change dynamically, protected by ap->lock */ unsigned int pflags; /* ATA_PFLAG_xxx */ unsigned int print_id; /* user visible unique port ID */ - unsigned int local_port_no; /* host local port num */ unsigned int port_no; /* 0 based port no. inside the host */ #ifdef CONFIG_ATA_SFF @@ -875,9 +930,6 @@ struct ata_port { #ifdef CONFIG_ATA_ACPI struct ata_acpi_gtm __acpi_init_gtm; /* use ata_acpi_init_gtm() */ #endif - /* owned by EH */ - u8 *ncq_sense_buf; - u8 sector_buf[ATA_SECT_SIZE] ____cacheline_aligned; }; /* The following initializer overrides a method to NULL whether one of @@ -1065,11 +1117,9 @@ static inline bool ata_port_is_frozen(const struct ata_port *ap) extern int ata_std_prereset(struct ata_link *link, unsigned long deadline); extern int ata_wait_after_reset(struct ata_link *link, unsigned long deadline, int (*check_ready)(struct ata_link *link)); -extern int sata_std_hardreset(struct ata_link *link, unsigned int *class, - unsigned long deadline); extern void ata_std_postreset(struct ata_link *link, unsigned int *classes); -extern struct ata_host *ata_host_alloc(struct device *dev, int max_ports); +extern struct ata_host *ata_host_alloc(struct device *dev, int n_ports); extern struct ata_host *ata_host_alloc_pinfo(struct device *dev, const struct ata_port_info * const * ppi, int n_ports); extern void ata_host_get(struct ata_host *host); @@ -1082,7 +1132,6 @@ extern int ata_host_activate(struct ata_host *host, int irq, const struct scsi_host_template *sht); extern void ata_host_detach(struct ata_host *host); extern void ata_host_init(struct ata_host *, struct device *, struct ata_port_operations *); -extern int ata_scsi_detect(struct scsi_host_template *sht); extern int ata_scsi_ioctl(struct scsi_device *dev, unsigned int cmd, void __user *arg); #ifdef CONFIG_COMPAT @@ -1131,7 +1180,6 @@ extern int ata_xfer_mode2shift(u8 xfer_mode); extern const char *ata_mode_string(unsigned int xfer_mask); extern unsigned int ata_id_xfermask(const u16 *id); extern int ata_std_qc_defer(struct ata_queued_cmd *qc); -extern enum ata_completion_errors ata_noop_qc_prep(struct ata_queued_cmd *qc); extern void ata_sg_init(struct ata_queued_cmd *qc, struct scatterlist *sg, unsigned int n_elem); extern unsigned int ata_dev_classify(const struct ata_taskfile *tf); @@ -1151,13 +1199,19 @@ extern int ata_std_bios_param(struct scsi_device *sdev, struct block_device *bdev, sector_t capacity, int geom[]); extern void ata_scsi_unlock_native_capacity(struct scsi_device *sdev); -extern int ata_scsi_slave_alloc(struct scsi_device *sdev); -extern int ata_scsi_slave_config(struct scsi_device *sdev); -extern void ata_scsi_slave_destroy(struct scsi_device *sdev); +extern int ata_scsi_sdev_init(struct scsi_device *sdev); +int ata_scsi_sdev_configure(struct scsi_device *sdev, struct queue_limits *lim); +extern void ata_scsi_sdev_destroy(struct scsi_device *sdev); extern int ata_scsi_change_queue_depth(struct scsi_device *sdev, int queue_depth); extern int ata_change_queue_depth(struct ata_port *ap, struct scsi_device *sdev, int queue_depth); +extern int ata_ncq_prio_supported(struct ata_port *ap, struct scsi_device *sdev, + bool *supported); +extern int ata_ncq_prio_enabled(struct ata_port *ap, struct scsi_device *sdev, + bool *enabled); +extern int ata_ncq_prio_enable(struct ata_port *ap, struct scsi_device *sdev, + bool enable); extern struct ata_device *ata_dev_pair(struct ata_device *adev); extern int ata_do_set_mode(struct ata_link *link, struct ata_device **r_failed_dev); extern void ata_scsi_port_error_handler(struct Scsi_Host *host, struct ata_port *ap); @@ -1185,12 +1239,13 @@ extern int sata_scr_read(struct ata_link *link, int reg, u32 *val); extern int sata_scr_write(struct ata_link *link, int reg, u32 val); extern int sata_scr_write_flush(struct ata_link *link, int reg, u32 val); extern int sata_set_spd(struct ata_link *link); +int sata_std_hardreset(struct ata_link *link, unsigned int *class, + unsigned long deadline); extern int sata_link_hardreset(struct ata_link *link, const unsigned int *timing, unsigned long deadline, bool *online, int (*check_ready)(struct ata_link *)); extern int sata_link_resume(struct ata_link *link, const unsigned int *params, unsigned long deadline); -extern int ata_eh_read_sense_success_ncq_log(struct ata_link *link); extern void ata_eh_analyze_ncq_error(struct ata_link *link); #else static inline const unsigned int * @@ -1212,6 +1267,11 @@ static inline int sata_scr_write_flush(struct ata_link *link, int reg, u32 val) return -EOPNOTSUPP; } static inline int sata_set_spd(struct ata_link *link) { return -EOPNOTSUPP; } +static inline int sata_std_hardreset(struct ata_link *link, unsigned int *class, + unsigned long deadline) +{ + return -EOPNOTSUPP; +} static inline int sata_link_hardreset(struct ata_link *link, const unsigned int *timing, unsigned long deadline, @@ -1228,10 +1288,6 @@ static inline int sata_link_resume(struct ata_link *link, { return -EOPNOTSUPP; } -static inline int ata_eh_read_sense_success_ncq_log(struct ata_link *link) -{ - return -EOPNOTSUPP; -} static inline void ata_eh_analyze_ncq_error(struct ata_link *link) { } #endif extern int sata_link_debounce(struct ata_link *link, @@ -1239,12 +1295,13 @@ extern int sata_link_debounce(struct ata_link *link, extern int sata_link_scr_lpm(struct ata_link *link, enum ata_lpm_policy policy, bool spm_wakeup); extern int ata_slave_link_init(struct ata_port *ap); -extern struct ata_port *ata_sas_port_alloc(struct ata_host *, - struct ata_port_info *, struct Scsi_Host *); extern void ata_port_probe(struct ata_port *ap); -extern int ata_sas_tport_add(struct device *parent, struct ata_port *ap); -extern void ata_sas_tport_delete(struct ata_port *ap); -extern int ata_sas_slave_configure(struct scsi_device *, struct ata_port *); +extern struct ata_port *ata_port_alloc(struct ata_host *host); +extern void ata_port_free(struct ata_port *ap); +extern int ata_tport_add(struct device *parent, struct ata_port *ap); +extern void ata_tport_delete(struct ata_port *ap); +int ata_sas_sdev_configure(struct scsi_device *sdev, struct queue_limits *lim, + struct ata_port *ap); extern int ata_sas_queuecmd(struct scsi_cmnd *cmd, struct ata_port *ap); extern void ata_tf_to_fis(const struct ata_taskfile *tf, u8 pmp, int is_cmd, u8 *fis); @@ -1400,8 +1457,8 @@ extern const struct attribute_group *ata_common_sdev_groups[]; .this_id = ATA_SHT_THIS_ID, \ .emulated = ATA_SHT_EMULATED, \ .proc_name = drv_name, \ - .slave_alloc = ata_scsi_slave_alloc, \ - .slave_destroy = ata_scsi_slave_destroy, \ + .sdev_init = ata_scsi_sdev_init, \ + .sdev_destroy = ata_scsi_sdev_destroy, \ .bios_param = ata_std_bios_param, \ .unlock_native_capacity = ata_scsi_unlock_native_capacity,\ .max_sectors = ATA_MAX_SECTORS_LBA48 @@ -1409,14 +1466,14 @@ extern const struct attribute_group *ata_common_sdev_groups[]; #define ATA_SUBBASE_SHT(drv_name) \ __ATA_BASE_SHT(drv_name), \ .can_queue = ATA_DEF_QUEUE, \ - .tag_alloc_policy = BLK_TAG_ALLOC_RR, \ - .slave_configure = ata_scsi_slave_config + .tag_alloc_policy_rr = true, \ + .sdev_configure = ata_scsi_sdev_configure #define ATA_SUBBASE_SHT_QD(drv_name, drv_qd) \ __ATA_BASE_SHT(drv_name), \ .can_queue = drv_qd, \ - .tag_alloc_policy = BLK_TAG_ALLOC_RR, \ - .slave_configure = ata_scsi_slave_config + .tag_alloc_policy_rr = true, \ + .sdev_configure = ata_scsi_sdev_configure #define ATA_BASE_SHT(drv_name) \ ATA_SUBBASE_SHT(drv_name), \ @@ -1961,7 +2018,6 @@ extern unsigned int ata_sff_data_xfer(struct ata_queued_cmd *qc, extern unsigned int ata_sff_data_xfer32(struct ata_queued_cmd *qc, unsigned char *buf, unsigned int buflen, int rw); extern void ata_sff_irq_on(struct ata_port *ap); -extern void ata_sff_irq_clear(struct ata_port *ap); extern int ata_sff_hsm_move(struct ata_port *ap, struct ata_queued_cmd *qc, u8 status, int in_wq); extern void ata_sff_queue_work(struct work_struct *work); diff --git a/include/linux/libgcc.h b/include/linux/libgcc.h index fc388da6a027..0d68f9d6a6a7 100644 --- a/include/linux/libgcc.h +++ b/include/linux/libgcc.h @@ -34,4 +34,8 @@ long long notrace __lshrdi3(long long u, word_type b); long long notrace __muldi3(long long u, long long v); word_type notrace __ucmpdi2(unsigned long long a, unsigned long long b); +#ifdef CONFIG_HAVE_ARCH_LIBGCC_H +#include <asm/libgcc.h> +#endif + #endif /* __ASM_LIBGCC_H */ diff --git a/include/linux/linkmode.h b/include/linux/linkmode.h index 287f590ed56b..3b9de09871f6 100644 --- a/include/linux/linkmode.h +++ b/include/linux/linkmode.h @@ -37,35 +37,17 @@ static inline bool linkmode_empty(const unsigned long *src) return bitmap_empty(src, __ETHTOOL_LINK_MODE_MASK_NBITS); } -static inline int linkmode_andnot(unsigned long *dst, const unsigned long *src1, - const unsigned long *src2) +static inline bool linkmode_andnot(unsigned long *dst, + const unsigned long *src1, + const unsigned long *src2) { return bitmap_andnot(dst, src1, src2, __ETHTOOL_LINK_MODE_MASK_NBITS); } -static inline void linkmode_set_bit(int nr, volatile unsigned long *addr) -{ - __set_bit(nr, addr); -} - -static inline void linkmode_clear_bit(int nr, volatile unsigned long *addr) -{ - __clear_bit(nr, addr); -} - -static inline void linkmode_mod_bit(int nr, volatile unsigned long *addr, - int set) -{ - if (set) - linkmode_set_bit(nr, addr); - else - linkmode_clear_bit(nr, addr); -} - -static inline int linkmode_test_bit(int nr, const volatile unsigned long *addr) -{ - return test_bit(nr, addr); -} +#define linkmode_test_bit test_bit +#define linkmode_set_bit __set_bit +#define linkmode_clear_bit __clear_bit +#define linkmode_mod_bit __assign_bit static inline void linkmode_set_bit_array(const int *array, int array_size, unsigned long *addr) diff --git a/include/linux/linux_logo.h b/include/linux/linux_logo.h index d4d5b93efe84..e37699b7e839 100644 --- a/include/linux/linux_logo.h +++ b/include/linux/linux_logo.h @@ -10,9 +10,6 @@ * Copyright (C) 2001 Greg Banks <gnb@alphalink.com.au> * Copyright (C) 2001 Jan-Benedict Glaw <jbglaw@lug-owl.de> * Copyright (C) 2003 Geert Uytterhoeven <geert@linux-m68k.org> - * - * Serial_console ascii image can be any size, - * but should contain %s to display the version */ #include <linux/init.h> diff --git a/include/linux/list.h b/include/linux/list.h index 5f4b0a39cf46..29a375889fb8 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -687,14 +687,6 @@ static inline void list_splice_tail_init(struct list_head *list, for (pos = (head)->next; !list_is_head(pos, (head)); pos = pos->next) /** - * list_for_each_reverse - iterate backwards over a list - * @pos: the &struct list_head to use as a loop cursor. - * @head: the head for your list. - */ -#define list_for_each_reverse(pos, head) \ - for (pos = (head)->prev; pos != (head); pos = pos->prev) - -/** * list_for_each_rcu - Iterate over a list in an RCU-safe fashion * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index 792b67ceb631..fe739d35a864 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -32,6 +32,8 @@ struct list_lru_one { struct list_head list; /* may become negative during memcg reparenting */ long nr_items; + /* protects all fields above */ + spinlock_t lock; }; struct list_lru_memcg { @@ -41,31 +43,41 @@ struct list_lru_memcg { }; struct list_lru_node { - /* protects all lists on the node, including per cgroup */ - spinlock_t lock; /* global list, used for the root cgroup in cgroup aware lrus */ struct list_lru_one lru; - long nr_items; + atomic_long_t nr_items; } ____cacheline_aligned_in_smp; struct list_lru { struct list_lru_node *node; -#ifdef CONFIG_MEMCG_KMEM +#ifdef CONFIG_MEMCG struct list_head list; int shrinker_id; bool memcg_aware; struct xarray xa; #endif +#ifdef CONFIG_LOCKDEP + struct lock_class_key *key; +#endif }; void list_lru_destroy(struct list_lru *lru); int __list_lru_init(struct list_lru *lru, bool memcg_aware, - struct lock_class_key *key, struct shrinker *shrinker); + struct shrinker *shrinker); #define list_lru_init(lru) \ - __list_lru_init((lru), false, NULL, NULL) + __list_lru_init((lru), false, NULL) #define list_lru_init_memcg(lru, shrinker) \ - __list_lru_init((lru), true, NULL, shrinker) + __list_lru_init((lru), true, shrinker) + +static inline int list_lru_init_memcg_key(struct list_lru *lru, struct shrinker *shrinker, + struct lock_class_key *key) +{ +#ifdef CONFIG_LOCKDEP + lru->key = key; +#endif + return list_lru_init_memcg(lru, shrinker); +} int memcg_list_lru_alloc(struct mem_cgroup *memcg, struct list_lru *lru, gfp_t gfp); @@ -79,13 +91,24 @@ void memcg_reparent_list_lrus(struct mem_cgroup *memcg, struct mem_cgroup *paren * @memcg: the cgroup of the sublist to add the item to. * * If the element is already part of a list, this function returns doing - * nothing. Therefore the caller does not need to keep state about whether or - * not the element already belongs in the list and is allowed to lazy update - * it. Note however that this is valid for *a* list, not *this* list. If - * the caller organize itself in a way that elements can be in more than - * one type of list, it is up to the caller to fully remove the item from - * the previous list (with list_lru_del() for instance) before moving it - * to @lru. + * nothing. This means that it is not necessary to keep state about whether or + * not the element already belongs in the list. That said, this logic only + * works if the item is in *this* list. If the item might be in some other + * list, then you cannot rely on this check and you must remove it from the + * other list before trying to insert it. + * + * The lru list consists of many sublists internally; the @nid and @memcg + * parameters are used to determine which sublist to insert the item into. + * It's important to use the right value of @nid and @memcg when deleting the + * item, since it might otherwise get deleted from the wrong sublist. + * + * This also applies when attempting to insert the item multiple times - if + * the item is currently in one sublist and you call list_lru_add() again, you + * must pass the right @nid and @memcg parameters so that the same sublist is + * used. + * + * You must ensure that the memcg is not freed during this call (e.g., with + * rcu or by taking a css refcnt). * * Return: true if the list was updated, false otherwise */ @@ -101,7 +124,7 @@ bool list_lru_add(struct list_lru *lru, struct list_head *item, int nid, * memcg of the sublist is determined by @item list_head. This assumption is * valid for slab objects LRU such as dentries, inodes, etc. * - * Return value: true if the list was updated, false otherwise + * Return: true if the list was updated, false otherwise */ bool list_lru_add_obj(struct list_lru *lru, struct list_head *item); @@ -113,8 +136,19 @@ bool list_lru_add_obj(struct list_lru *lru, struct list_head *item); * @memcg: the cgroup of the sublist to delete the item from. * * This function works analogously as list_lru_add() in terms of list - * manipulation. The comments about an element already pertaining to - * a list are also valid for list_lru_del(). + * manipulation. + * + * The comments in list_lru_add() about an element already being in a list are + * also valid for list_lru_del(), that is, you can delete an item that has + * already been removed or never been added. However, if the item is in a + * list, it must be in *this* list, and you must pass the right value of @nid + * and @memcg so that the right sublist is used. + * + * You must ensure that the memcg is not freed during this call (e.g., with + * rcu or by taking a css refcnt). When a memcg is deleted, list_lru entries + * are automatically moved to the parent memcg. This is done in a race-free + * way, so during deletion of an memcg both the old and new memcg will resolve + * to the same sublist internally. * * Return: true if the list was updated, false otherwise */ @@ -130,7 +164,7 @@ bool list_lru_del(struct list_lru *lru, struct list_head *item, int nid, * memcg of the sublist is determined by @item list_head. This assumption is * valid for slab objects LRU such as dentries, inodes, etc. * - * Return value: true if the list was updated, false otherwise. + * Return: true if the list was updated, false otherwise. */ bool list_lru_del_obj(struct list_lru *lru, struct list_head *item); @@ -172,7 +206,7 @@ void list_lru_isolate_move(struct list_lru_one *list, struct list_head *item, struct list_head *head); typedef enum lru_status (*list_lru_walk_cb)(struct list_head *item, - struct list_lru_one *list, spinlock_t *lock, void *cb_arg); + struct list_lru_one *list, void *cb_arg); /** * list_lru_walk_one: walk a @lru, isolating and disposing freeable items. diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h index 9b9b38e89563..51a258c24ff5 100644 --- a/include/linux/livepatch.h +++ b/include/linux/livepatch.h @@ -18,9 +18,9 @@ #if IS_ENABLED(CONFIG_LIVEPATCH) /* task patch states */ -#define KLP_UNDEFINED -1 -#define KLP_UNPATCHED 0 -#define KLP_PATCHED 1 +#define KLP_TRANSITION_IDLE -1 +#define KLP_TRANSITION_UNPATCHED 0 +#define KLP_TRANSITION_PATCHED 1 /** * struct klp_func - function structure for live patching diff --git a/include/linux/local_lock.h b/include/linux/local_lock.h index e55010fa7329..091dc0b6bdfb 100644 --- a/include/linux/local_lock.h +++ b/include/linux/local_lock.h @@ -51,4 +51,25 @@ #define local_unlock_irqrestore(lock, flags) \ __local_unlock_irqrestore(lock, flags) +DEFINE_GUARD(local_lock, local_lock_t __percpu*, + local_lock(_T), + local_unlock(_T)) +DEFINE_GUARD(local_lock_irq, local_lock_t __percpu*, + local_lock_irq(_T), + local_unlock_irq(_T)) +DEFINE_LOCK_GUARD_1(local_lock_irqsave, local_lock_t __percpu, + local_lock_irqsave(_T->lock, _T->flags), + local_unlock_irqrestore(_T->lock, _T->flags), + unsigned long flags) + +#define local_lock_nested_bh(_lock) \ + __local_lock_nested_bh(_lock) + +#define local_unlock_nested_bh(_lock) \ + __local_unlock_nested_bh(_lock) + +DEFINE_GUARD(local_lock_nested_bh, local_lock_t __percpu*, + local_lock_nested_bh(_T), + local_unlock_nested_bh(_T)) + #endif diff --git a/include/linux/local_lock_internal.h b/include/linux/local_lock_internal.h index 975e33b793a7..8dd71fbbb6d2 100644 --- a/include/linux/local_lock_internal.h +++ b/include/linux/local_lock_internal.h @@ -62,6 +62,17 @@ do { \ local_lock_debug_init(lock); \ } while (0) +#define __spinlock_nested_bh_init(lock) \ +do { \ + static struct lock_class_key __key; \ + \ + debug_check_no_locks_freed((void *)lock, sizeof(*lock));\ + lockdep_init_map_type(&(lock)->dep_map, #lock, &__key, \ + 0, LD_WAIT_CONFIG, LD_WAIT_INV, \ + LD_LOCK_NORMAL); \ + local_lock_debug_init(lock); \ +} while (0) + #define __local_lock(lock) \ do { \ preempt_disable(); \ @@ -98,6 +109,15 @@ do { \ local_irq_restore(flags); \ } while (0) +#define __local_lock_nested_bh(lock) \ + do { \ + lockdep_assert_in_softirq(); \ + local_lock_acquire(this_cpu_ptr(lock)); \ + } while (0) + +#define __local_unlock_nested_bh(lock) \ + local_lock_release(this_cpu_ptr(lock)) + #else /* !CONFIG_PREEMPT_RT */ /* @@ -138,4 +158,15 @@ typedef spinlock_t local_lock_t; #define __local_unlock_irqrestore(lock, flags) __local_unlock(lock) +#define __local_lock_nested_bh(lock) \ +do { \ + lockdep_assert_in_softirq_func(); \ + spin_lock(this_cpu_ptr(lock)); \ +} while (0) + +#define __local_unlock_nested_bh(lock) \ +do { \ + spin_unlock(this_cpu_ptr((lock))); \ +} while (0) + #endif /* CONFIG_PREEMPT_RT */ diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index 1b95fe31051f..c8f0f9458f2c 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -200,7 +200,7 @@ extern const struct svc_procedure nlmsvc_procedures[24]; extern const struct svc_procedure nlmsvc_procedures4[24]; #endif extern int nlmsvc_grace_period; -extern unsigned long nlmsvc_timeout; +extern unsigned long nlm_timeout; extern bool nsm_use_hostnames; extern u32 nsm_local_state; @@ -278,9 +278,9 @@ __be32 nlmsvc_lock(struct svc_rqst *, struct nlm_file *, struct nlm_host *, struct nlm_lock *, int, struct nlm_cookie *, int); __be32 nlmsvc_unlock(struct net *net, struct nlm_file *, struct nlm_lock *); -__be32 nlmsvc_testlock(struct svc_rqst *, struct nlm_file *, - struct nlm_host *, struct nlm_lock *, - struct nlm_lock *, struct nlm_cookie *); +__be32 nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file, + struct nlm_host *host, struct nlm_lock *lock, + struct nlm_lock *conflock); __be32 nlmsvc_cancel_blocked(struct net *net, struct nlm_file *, struct nlm_lock *); void nlmsvc_retry_blocked(struct svc_rqst *rqstp); void nlmsvc_traverse_blocks(struct nlm_host *, struct nlm_file *, diff --git a/include/linux/lockd/xdr.h b/include/linux/lockd/xdr.h index 80cca9426761..17d53165d9f2 100644 --- a/include/linux/lockd/xdr.h +++ b/include/linux/lockd/xdr.h @@ -73,8 +73,6 @@ struct nlm_args { u32 fsm_mode; }; -typedef struct nlm_args nlm_args; - /* * Generic lockd result */ diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 08b0d1d9d78b..67964dc4db95 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -173,14 +173,32 @@ static inline void lockdep_init_map(struct lockdep_map *lock, const char *name, (lock)->dep_map.lock_type) #define lockdep_set_subclass(lock, sub) \ - lockdep_init_map_type(&(lock)->dep_map, #lock, (lock)->dep_map.key, sub,\ + lockdep_init_map_type(&(lock)->dep_map, (lock)->dep_map.name, (lock)->dep_map.key, sub,\ (lock)->dep_map.wait_type_inner, \ (lock)->dep_map.wait_type_outer, \ (lock)->dep_map.lock_type) +/** + * lockdep_set_novalidate_class: disable checking of lock ordering on a given + * lock + * @lock: Lock to mark + * + * Lockdep will still record that this lock has been taken, and print held + * instances when dumping locks + */ #define lockdep_set_novalidate_class(lock) \ lockdep_set_class_and_name(lock, &__lockdep_no_validate__, #lock) +/** + * lockdep_set_notrack_class: disable lockdep tracking of a given lock entirely + * @lock: Lock to mark + * + * Bigger hammer than lockdep_set_novalidate_class: so far just for bcachefs, + * which takes more locks than lockdep is able to track (48). + */ +#define lockdep_set_notrack_class(lock) \ + lockdep_set_class_and_name(lock, &__lockdep_no_track__, #lock) + /* * Compare locking classes */ @@ -338,6 +356,7 @@ static inline void lockdep_set_selftest_task(struct task_struct *task) #define lockdep_set_subclass(lock, sub) do { } while (0) #define lockdep_set_novalidate_class(lock) do { } while (0) +#define lockdep_set_notrack_class(lock) do { } while (0) /* * We don't define lockdep_match_class() and lockdep_match_key() for !LOCKDEP @@ -600,6 +619,8 @@ do { \ (!in_softirq() || in_irq() || in_nmi())); \ } while (0) +extern void lockdep_assert_in_softirq_func(void); + #else # define might_lock(lock) do { } while (0) # define might_lock_read(lock) do { } while (0) @@ -613,6 +634,7 @@ do { \ # define lockdep_assert_preemption_enabled() do { } while (0) # define lockdep_assert_preemption_disabled() do { } while (0) # define lockdep_assert_in_softirq() do { } while (0) +# define lockdep_assert_in_softirq_func() do { } while (0) #endif #ifdef CONFIG_PROVE_RAW_LOCK_NESTING diff --git a/include/linux/lockdep_types.h b/include/linux/lockdep_types.h index 70d30d40ea4a..9f361d3ab9d9 100644 --- a/include/linux/lockdep_types.h +++ b/include/linux/lockdep_types.h @@ -80,6 +80,7 @@ struct lock_class_key { }; extern struct lock_class_key __lockdep_no_validate__; +extern struct lock_class_key __lockdep_no_track__; struct lock_trace; diff --git a/include/linux/lockref.h b/include/linux/lockref.h index c3a1f78bc884..c39f119659ba 100644 --- a/include/linux/lockref.h +++ b/include/linux/lockref.h @@ -34,14 +34,24 @@ struct lockref { }; }; -extern void lockref_get(struct lockref *); -extern int lockref_put_return(struct lockref *); -extern int lockref_get_not_zero(struct lockref *); -extern int lockref_put_not_zero(struct lockref *); -extern int lockref_put_or_lock(struct lockref *); +/** + * lockref_init - Initialize a lockref + * @lockref: pointer to lockref structure + * @count: initial count + */ +static inline void lockref_init(struct lockref *lockref, unsigned int count) +{ + spin_lock_init(&lockref->lock); + lockref->count = count; +} + +void lockref_get(struct lockref *lockref); +int lockref_put_return(struct lockref *lockref); +bool lockref_get_not_zero(struct lockref *lockref); +bool lockref_put_or_lock(struct lockref *lockref); -extern void lockref_mark_dead(struct lockref *); -extern int lockref_get_not_dead(struct lockref *); +void lockref_mark_dead(struct lockref *lockref); +bool lockref_get_not_dead(struct lockref *lockref); /* Must be called under spinlock for reliable results */ static inline bool __lockref_is_dead(const struct lockref *l) diff --git a/include/linux/logic_pio.h b/include/linux/logic_pio.h index babf4e3c28ba..8f1a9408302f 100644 --- a/include/linux/logic_pio.h +++ b/include/linux/logic_pio.h @@ -17,7 +17,7 @@ enum { struct logic_pio_hwaddr { struct list_head list; - struct fwnode_handle *fwnode; + const struct fwnode_handle *fwnode; resource_size_t hw_start; resource_size_t io_start; resource_size_t size; /* range size populated */ @@ -110,8 +110,8 @@ void logic_outsl(unsigned long addr, const void *buffer, unsigned int count); #endif /* CONFIG_INDIRECT_PIO */ #define MMIO_UPPER_LIMIT (IO_SPACE_LIMIT - PIO_INDIRECT_SIZE) -struct logic_pio_hwaddr *find_io_range_by_fwnode(struct fwnode_handle *fwnode); -unsigned long logic_pio_trans_hwaddr(struct fwnode_handle *fwnode, +struct logic_pio_hwaddr *find_io_range_by_fwnode(const struct fwnode_handle *fwnode); +unsigned long logic_pio_trans_hwaddr(const struct fwnode_handle *fwnode, resource_size_t hw_addr, resource_size_t size); int logic_pio_register_range(struct logic_pio_hwaddr *newrange); void logic_pio_unregister_range(struct logic_pio_hwaddr *range); diff --git a/include/linux/lru_cache.h b/include/linux/lru_cache.h index c9afcdd9324c..ff82ef85a084 100644 --- a/include/linux/lru_cache.h +++ b/include/linux/lru_cache.h @@ -119,7 +119,7 @@ write intent log information, three of which are mentioned here. */ /* this defines an element in a tracked set - * .colision is for hash table lookup. + * .collision is for hash table lookup. * When we process a new IO request, we know its sector, thus can deduce the * region number (label) easily. To do the label -> object lookup without a * full list walk, we use a simple hash table. @@ -145,7 +145,7 @@ write intent log information, three of which are mentioned here. * But it avoids high order page allocations in kmalloc. */ struct lc_element { - struct hlist_node colision; + struct hlist_node collision; struct list_head list; /* LRU list or free list */ unsigned refcnt; /* back "pointer" into lc_cache->element[index], diff --git a/include/linux/lsm/apparmor.h b/include/linux/lsm/apparmor.h new file mode 100644 index 000000000000..612cbfacb072 --- /dev/null +++ b/include/linux/lsm/apparmor.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Linux Security Module interface to other subsystems. + * AppArmor presents single pointer to an aa_label structure. + */ +#ifndef __LINUX_LSM_APPARMOR_H +#define __LINUX_LSM_APPARMOR_H + +struct aa_label; + +struct lsm_prop_apparmor { +#ifdef CONFIG_SECURITY_APPARMOR + struct aa_label *label; +#endif +}; + +#endif /* ! __LINUX_LSM_APPARMOR_H */ diff --git a/include/linux/lsm/bpf.h b/include/linux/lsm/bpf.h new file mode 100644 index 000000000000..8106e206fcef --- /dev/null +++ b/include/linux/lsm/bpf.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Linux Security Module interface to other subsystems. + * BPF may present a single u32 value. + */ +#ifndef __LINUX_LSM_BPF_H +#define __LINUX_LSM_BPF_H +#include <linux/types.h> + +struct lsm_prop_bpf { +#ifdef CONFIG_BPF_LSM + u32 secid; +#endif +}; + +#endif /* ! __LINUX_LSM_BPF_H */ diff --git a/include/linux/lsm/selinux.h b/include/linux/lsm/selinux.h new file mode 100644 index 000000000000..9455a6b5b910 --- /dev/null +++ b/include/linux/lsm/selinux.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Linux Security Module interface to other subsystems. + * SELinux presents a single u32 value which is known as a secid. + */ +#ifndef __LINUX_LSM_SELINUX_H +#define __LINUX_LSM_SELINUX_H +#include <linux/types.h> + +struct lsm_prop_selinux { +#ifdef CONFIG_SECURITY_SELINUX + u32 secid; +#endif +}; + +#endif /* ! __LINUX_LSM_SELINUX_H */ diff --git a/include/linux/lsm/smack.h b/include/linux/lsm/smack.h new file mode 100644 index 000000000000..ff730dd7a734 --- /dev/null +++ b/include/linux/lsm/smack.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Linux Security Module interface to other subsystems. + * Smack presents a pointer into the global Smack label list. + */ +#ifndef __LINUX_LSM_SMACK_H +#define __LINUX_LSM_SMACK_H + +struct smack_known; + +struct lsm_prop_smack { +#ifdef CONFIG_SECURITY_SMACK + struct smack_known *skp; +#endif +}; + +#endif /* ! __LINUX_LSM_SMACK_H */ diff --git a/include/linux/lsm_audit.h b/include/linux/lsm_audit.h index 97a8b21eb033..e13d2f947b51 100644 --- a/include/linux/lsm_audit.h +++ b/include/linux/lsm_audit.h @@ -77,6 +77,7 @@ struct common_audit_data { #define LSM_AUDIT_DATA_LOCKDOWN 15 #define LSM_AUDIT_DATA_NOTIFICATION 16 #define LSM_AUDIT_DATA_ANONINODE 17 +#define LSM_AUDIT_DATA_NLMSGTYPE 18 union { struct path path; struct dentry *dentry; @@ -98,6 +99,7 @@ struct common_audit_data { struct lsm_ibendport_audit *ibendport; int reason; const char *anonclass; + u16 nlmsg_type; } u; /* this union contains LSM specific data */ union { @@ -116,14 +118,28 @@ struct common_audit_data { #define v4info fam.v4 #define v6info fam.v6 +#ifdef CONFIG_AUDIT + int ipv4_skb_to_auditdata(struct sk_buff *skb, struct common_audit_data *ad, u8 *proto); +#if IS_ENABLED(CONFIG_IPV6) int ipv6_skb_to_auditdata(struct sk_buff *skb, struct common_audit_data *ad, u8 *proto); +#endif /* IS_ENABLED(CONFIG_IPV6) */ void common_lsm_audit(struct common_audit_data *a, void (*pre_audit)(struct audit_buffer *, void *), void (*post_audit)(struct audit_buffer *, void *)); +#else /* CONFIG_AUDIT */ + +static inline void common_lsm_audit(struct common_audit_data *a, + void (*pre_audit)(struct audit_buffer *, void *), + void (*post_audit)(struct audit_buffer *, void *)) +{ +} + +#endif /* CONFIG_AUDIT */ + #endif diff --git a/include/linux/lsm_count.h b/include/linux/lsm_count.h new file mode 100644 index 000000000000..16eb49761b25 --- /dev/null +++ b/include/linux/lsm_count.h @@ -0,0 +1,135 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * Copyright (C) 2023 Google LLC. + */ + +#ifndef __LINUX_LSM_COUNT_H +#define __LINUX_LSM_COUNT_H + +#include <linux/args.h> + +#ifdef CONFIG_SECURITY + +/* + * Macros to count the number of LSMs enabled in the kernel at compile time. + */ + +/* + * Capabilities is enabled when CONFIG_SECURITY is enabled. + */ +#if IS_ENABLED(CONFIG_SECURITY) +#define CAPABILITIES_ENABLED 1, +#else +#define CAPABILITIES_ENABLED +#endif + +#if IS_ENABLED(CONFIG_SECURITY_SELINUX) +#define SELINUX_ENABLED 1, +#else +#define SELINUX_ENABLED +#endif + +#if IS_ENABLED(CONFIG_SECURITY_SMACK) +#define SMACK_ENABLED 1, +#else +#define SMACK_ENABLED +#endif + +#if IS_ENABLED(CONFIG_SECURITY_APPARMOR) +#define APPARMOR_ENABLED 1, +#else +#define APPARMOR_ENABLED +#endif + +#if IS_ENABLED(CONFIG_SECURITY_TOMOYO) +#define TOMOYO_ENABLED 1, +#else +#define TOMOYO_ENABLED +#endif + +#if IS_ENABLED(CONFIG_SECURITY_YAMA) +#define YAMA_ENABLED 1, +#else +#define YAMA_ENABLED +#endif + +#if IS_ENABLED(CONFIG_SECURITY_LOADPIN) +#define LOADPIN_ENABLED 1, +#else +#define LOADPIN_ENABLED +#endif + +#if IS_ENABLED(CONFIG_SECURITY_LOCKDOWN_LSM) +#define LOCKDOWN_ENABLED 1, +#else +#define LOCKDOWN_ENABLED +#endif + +#if IS_ENABLED(CONFIG_SECURITY_SAFESETID) +#define SAFESETID_ENABLED 1, +#else +#define SAFESETID_ENABLED +#endif + +#if IS_ENABLED(CONFIG_BPF_LSM) +#define BPF_LSM_ENABLED 1, +#else +#define BPF_LSM_ENABLED +#endif + +#if IS_ENABLED(CONFIG_SECURITY_LANDLOCK) +#define LANDLOCK_ENABLED 1, +#else +#define LANDLOCK_ENABLED +#endif + +#if IS_ENABLED(CONFIG_IMA) +#define IMA_ENABLED 1, +#else +#define IMA_ENABLED +#endif + +#if IS_ENABLED(CONFIG_EVM) +#define EVM_ENABLED 1, +#else +#define EVM_ENABLED +#endif + +#if IS_ENABLED(CONFIG_SECURITY_IPE) +#define IPE_ENABLED 1, +#else +#define IPE_ENABLED +#endif + +/* + * There is a trailing comma that we need to be accounted for. This is done by + * using a skipped argument in __COUNT_LSMS + */ +#define __COUNT_LSMS(skipped_arg, args...) COUNT_ARGS(args...) +#define COUNT_LSMS(args...) __COUNT_LSMS(args) + +#define MAX_LSM_COUNT \ + COUNT_LSMS( \ + CAPABILITIES_ENABLED \ + SELINUX_ENABLED \ + SMACK_ENABLED \ + APPARMOR_ENABLED \ + TOMOYO_ENABLED \ + YAMA_ENABLED \ + LOADPIN_ENABLED \ + LOCKDOWN_ENABLED \ + SAFESETID_ENABLED \ + BPF_LSM_ENABLED \ + LANDLOCK_ENABLED \ + IMA_ENABLED \ + EVM_ENABLED \ + IPE_ENABLED) + +#else + +#define MAX_LSM_COUNT 0 + +#endif /* CONFIG_SECURITY */ + +#endif /* __LINUX_LSM_COUNT_H */ diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 334e00efbde4..e2f1ce37c41e 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -48,7 +48,7 @@ LSM_HOOK(int, 0, quota_on, struct dentry *dentry) LSM_HOOK(int, 0, syslog, int type) LSM_HOOK(int, 0, settime, const struct timespec64 *ts, const struct timezone *tz) -LSM_HOOK(int, 1, vm_enough_memory, struct mm_struct *mm, long pages) +LSM_HOOK(int, 0, vm_enough_memory, struct mm_struct *mm, long pages) LSM_HOOK(int, 0, bprm_creds_for_exec, struct linux_binprm *bprm) LSM_HOOK(int, 0, bprm_creds_from_file, struct linux_binprm *bprm, const struct file *file) LSM_HOOK(int, 0, bprm_check_security, struct linux_binprm *bprm) @@ -83,7 +83,7 @@ LSM_HOOK(int, 0, move_mount, const struct path *from_path, const struct path *to_path) LSM_HOOK(int, -EOPNOTSUPP, dentry_init_security, struct dentry *dentry, int mode, const struct qstr *name, const char **xattr_name, - void **ctx, u32 *ctxlen) + struct lsm_context *cp) LSM_HOOK(int, 0, dentry_create_files_as, struct dentry *dentry, int mode, struct qstr *name, const struct cred *old, struct cred *new) @@ -114,6 +114,7 @@ LSM_HOOK(int, 0, path_notify, const struct path *path, u64 mask, unsigned int obj_type) LSM_HOOK(int, 0, inode_alloc_security, struct inode *inode) LSM_HOOK(void, LSM_RET_VOID, inode_free_security, struct inode *inode) +LSM_HOOK(void, LSM_RET_VOID, inode_free_security_rcu, void *inode_security) LSM_HOOK(int, -EOPNOTSUPP, inode_init_security, struct inode *inode, struct inode *dir, const struct qstr *qstr, struct xattr *xattrs, int *xattr_count) @@ -144,6 +145,7 @@ LSM_HOOK(int, 0, inode_setattr, struct mnt_idmap *idmap, struct dentry *dentry, LSM_HOOK(void, LSM_RET_VOID, inode_post_setattr, struct mnt_idmap *idmap, struct dentry *dentry, int ia_valid) LSM_HOOK(int, 0, inode_getattr, const struct path *path) +LSM_HOOK(int, 0, inode_xattr_skipcap, const char *name) LSM_HOOK(int, 0, inode_setxattr, struct mnt_idmap *idmap, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) @@ -174,9 +176,13 @@ LSM_HOOK(int, -EOPNOTSUPP, inode_setsecurity, struct inode *inode, const char *name, const void *value, size_t size, int flags) LSM_HOOK(int, 0, inode_listsecurity, struct inode *inode, char *buffer, size_t buffer_size) -LSM_HOOK(void, LSM_RET_VOID, inode_getsecid, struct inode *inode, u32 *secid) +LSM_HOOK(void, LSM_RET_VOID, inode_getlsmprop, struct inode *inode, + struct lsm_prop *prop) LSM_HOOK(int, 0, inode_copy_up, struct dentry *src, struct cred **new) -LSM_HOOK(int, -EOPNOTSUPP, inode_copy_up_xattr, const char *name) +LSM_HOOK(int, -EOPNOTSUPP, inode_copy_up_xattr, struct dentry *src, + const char *name) +LSM_HOOK(int, 0, inode_setintegrity, const struct inode *inode, + enum lsm_integrity_type type, const void *value, size_t size) LSM_HOOK(int, 0, kernfs_init_security, struct kernfs_node *kn_dir, struct kernfs_node *kn) LSM_HOOK(int, 0, file_permission, struct file *file, int mask) @@ -212,6 +218,8 @@ LSM_HOOK(int, 0, cred_prepare, struct cred *new, const struct cred *old, LSM_HOOK(void, LSM_RET_VOID, cred_transfer, struct cred *new, const struct cred *old) LSM_HOOK(void, LSM_RET_VOID, cred_getsecid, const struct cred *c, u32 *secid) +LSM_HOOK(void, LSM_RET_VOID, cred_getlsmprop, const struct cred *c, + struct lsm_prop *prop) LSM_HOOK(int, 0, kernel_act_as, struct cred *new, u32 secid) LSM_HOOK(int, 0, kernel_create_files_as, struct cred *new, struct inode *inode) LSM_HOOK(int, 0, kernel_module_request, char *kmod_name) @@ -230,9 +238,9 @@ LSM_HOOK(int, 0, task_fix_setgroups, struct cred *new, const struct cred * old) LSM_HOOK(int, 0, task_setpgid, struct task_struct *p, pid_t pgid) LSM_HOOK(int, 0, task_getpgid, struct task_struct *p) LSM_HOOK(int, 0, task_getsid, struct task_struct *p) -LSM_HOOK(void, LSM_RET_VOID, current_getsecid_subj, u32 *secid) -LSM_HOOK(void, LSM_RET_VOID, task_getsecid_obj, - struct task_struct *p, u32 *secid) +LSM_HOOK(void, LSM_RET_VOID, current_getlsmprop_subj, struct lsm_prop *prop) +LSM_HOOK(void, LSM_RET_VOID, task_getlsmprop_obj, + struct task_struct *p, struct lsm_prop *prop) LSM_HOOK(int, 0, task_setnice, struct task_struct *p, int nice) LSM_HOOK(int, 0, task_setioprio, struct task_struct *p, int ioprio) LSM_HOOK(int, 0, task_getioprio, struct task_struct *p) @@ -251,8 +259,8 @@ LSM_HOOK(void, LSM_RET_VOID, task_to_inode, struct task_struct *p, struct inode *inode) LSM_HOOK(int, 0, userns_create, const struct cred *cred) LSM_HOOK(int, 0, ipc_permission, struct kern_ipc_perm *ipcp, short flag) -LSM_HOOK(void, LSM_RET_VOID, ipc_getsecid, struct kern_ipc_perm *ipcp, - u32 *secid) +LSM_HOOK(void, LSM_RET_VOID, ipc_getlsmprop, struct kern_ipc_perm *ipcp, + struct lsm_prop *prop) LSM_HOOK(int, 0, msg_msg_alloc_security, struct msg_msg *msg) LSM_HOOK(void, LSM_RET_VOID, msg_msg_free_security, struct msg_msg *msg) LSM_HOOK(int, 0, msg_queue_alloc_security, struct kern_ipc_perm *perm) @@ -287,15 +295,16 @@ LSM_HOOK(int, -EINVAL, getprocattr, struct task_struct *p, const char *name, char **value) LSM_HOOK(int, -EINVAL, setprocattr, const char *name, void *value, size_t size) LSM_HOOK(int, 0, ismaclabel, const char *name) -LSM_HOOK(int, -EOPNOTSUPP, secid_to_secctx, u32 secid, char **secdata, - u32 *seclen) +LSM_HOOK(int, -EOPNOTSUPP, secid_to_secctx, u32 secid, struct lsm_context *cp) +LSM_HOOK(int, -EOPNOTSUPP, lsmprop_to_secctx, struct lsm_prop *prop, + struct lsm_context *cp) LSM_HOOK(int, 0, secctx_to_secid, const char *secdata, u32 seclen, u32 *secid) -LSM_HOOK(void, LSM_RET_VOID, release_secctx, char *secdata, u32 seclen) +LSM_HOOK(void, LSM_RET_VOID, release_secctx, struct lsm_context *cp) LSM_HOOK(void, LSM_RET_VOID, inode_invalidate_secctx, struct inode *inode) LSM_HOOK(int, 0, inode_notifysecctx, struct inode *inode, void *ctx, u32 ctxlen) LSM_HOOK(int, 0, inode_setsecctx, struct dentry *dentry, void *ctx, u32 ctxlen) -LSM_HOOK(int, -EOPNOTSUPP, inode_getsecctx, struct inode *inode, void **ctx, - u32 *ctxlen) +LSM_HOOK(int, -EOPNOTSUPP, inode_getsecctx, struct inode *inode, + struct lsm_context *cp) #if defined(CONFIG_SECURITY) && defined(CONFIG_WATCH_QUEUE) LSM_HOOK(int, 0, post_notification, const struct cred *w_cred, @@ -351,8 +360,7 @@ LSM_HOOK(void, LSM_RET_VOID, secmark_refcount_inc, void) LSM_HOOK(void, LSM_RET_VOID, secmark_refcount_dec, void) LSM_HOOK(void, LSM_RET_VOID, req_classify_flow, const struct request_sock *req, struct flowi_common *flic) -LSM_HOOK(int, 0, tun_dev_alloc_security, void **security) -LSM_HOOK(void, LSM_RET_VOID, tun_dev_free_security, void *security) +LSM_HOOK(int, 0, tun_dev_alloc_security, void *security) LSM_HOOK(int, 0, tun_dev_create, void) LSM_HOOK(int, 0, tun_dev_attach_queue, void *security) LSM_HOOK(int, 0, tun_dev_attach, struct sock *sk, void *security) @@ -372,8 +380,7 @@ LSM_HOOK(int, 0, mptcp_add_subflow, struct sock *sk, struct sock *ssk) LSM_HOOK(int, 0, ib_pkey_access, void *sec, u64 subnet_prefix, u16 pkey) LSM_HOOK(int, 0, ib_endport_manage_subnet, void *sec, const char *dev_name, u8 port_num) -LSM_HOOK(int, 0, ib_alloc_security, void **sec) -LSM_HOOK(void, LSM_RET_VOID, ib_free_security, void *sec) +LSM_HOOK(int, 0, ib_alloc_security, void *sec) #endif /* CONFIG_SECURITY_INFINIBAND */ #ifdef CONFIG_SECURITY_NETWORK_XFRM @@ -401,7 +408,6 @@ LSM_HOOK(int, 0, xfrm_decode_session, struct sk_buff *skb, u32 *secid, #ifdef CONFIG_KEYS LSM_HOOK(int, 0, key_alloc, struct key *key, const struct cred *cred, unsigned long flags) -LSM_HOOK(void, LSM_RET_VOID, key_free, struct key *key) LSM_HOOK(int, 0, key_permission, key_ref_t key_ref, const struct cred *cred, enum key_need_perm need_perm) LSM_HOOK(int, 0, key_getsecurity, struct key *key, char **buffer) @@ -412,9 +418,10 @@ LSM_HOOK(void, LSM_RET_VOID, key_post_create_or_update, struct key *keyring, #ifdef CONFIG_AUDIT LSM_HOOK(int, 0, audit_rule_init, u32 field, u32 op, char *rulestr, - void **lsmrule) + void **lsmrule, gfp_t gfp) LSM_HOOK(int, 0, audit_rule_known, struct audit_krule *krule) -LSM_HOOK(int, 0, audit_rule_match, u32 secid, u32 field, u32 op, void *lsmrule) +LSM_HOOK(int, 0, audit_rule_match, struct lsm_prop *prop, u32 field, u32 op, + void *lsmrule) LSM_HOOK(void, LSM_RET_VOID, audit_rule_free, void *lsmrule) #endif /* CONFIG_AUDIT */ @@ -429,7 +436,7 @@ LSM_HOOK(int, 0, bpf_prog_load, struct bpf_prog *prog, union bpf_attr *attr, struct bpf_token *token) LSM_HOOK(void, LSM_RET_VOID, bpf_prog_free, struct bpf_prog *prog) LSM_HOOK(int, 0, bpf_token_create, struct bpf_token *token, union bpf_attr *attr, - struct path *path) + const struct path *path) LSM_HOOK(void, LSM_RET_VOID, bpf_token_free, struct bpf_token *token) LSM_HOOK(int, 0, bpf_token_cmd, const struct bpf_token *token, enum bpf_cmd cmd) LSM_HOOK(int, 0, bpf_token_capable, const struct bpf_token *token, int cap) @@ -440,7 +447,6 @@ LSM_HOOK(int, 0, locked_down, enum lockdown_reason what) #ifdef CONFIG_PERF_EVENTS LSM_HOOK(int, 0, perf_event_open, struct perf_event_attr *attr, int type) LSM_HOOK(int, 0, perf_event_alloc, struct perf_event *event) -LSM_HOOK(void, LSM_RET_VOID, perf_event_free, struct perf_event *event) LSM_HOOK(int, 0, perf_event_read, struct perf_event *event) LSM_HOOK(int, 0, perf_event_write, struct perf_event *event) #endif /* CONFIG_PERF_EVENTS */ @@ -450,3 +456,10 @@ LSM_HOOK(int, 0, uring_override_creds, const struct cred *new) LSM_HOOK(int, 0, uring_sqpoll, void) LSM_HOOK(int, 0, uring_cmd, struct io_uring_cmd *ioucmd) #endif /* CONFIG_IO_URING */ + +LSM_HOOK(void, LSM_RET_VOID, initramfs_populated, void) + +LSM_HOOK(int, 0, bdev_alloc_security, struct block_device *bdev) +LSM_HOOK(void, LSM_RET_VOID, bdev_free_security, struct block_device *bdev) +LSM_HOOK(int, 0, bdev_setintegrity, struct block_device *bdev, + enum lsm_integrity_type type, const void *value, size_t size) diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index a2ade0ffe9e7..090d1d3e19fe 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -30,19 +30,47 @@ #include <linux/init.h> #include <linux/rculist.h> #include <linux/xattr.h> +#include <linux/static_call.h> +#include <linux/unroll.h> +#include <linux/jump_label.h> +#include <linux/lsm_count.h> union security_list_options { #define LSM_HOOK(RET, DEFAULT, NAME, ...) RET (*NAME)(__VA_ARGS__); #include "lsm_hook_defs.h" #undef LSM_HOOK + void *lsm_func_addr; }; -struct security_hook_heads { - #define LSM_HOOK(RET, DEFAULT, NAME, ...) struct hlist_head NAME; - #include "lsm_hook_defs.h" - #undef LSM_HOOK +/* + * @key: static call key as defined by STATIC_CALL_KEY + * @trampoline: static call trampoline as defined by STATIC_CALL_TRAMP + * @hl: The security_hook_list as initialized by the owning LSM. + * @active: Enabled when the static call has an LSM hook associated. + */ +struct lsm_static_call { + struct static_call_key *key; + void *trampoline; + struct security_hook_list *hl; + /* this needs to be true or false based on what the key defaults to */ + struct static_key_false *active; } __randomize_layout; +/* + * Table of the static calls for each LSM hook. + * Once the LSMs are initialized, their callbacks will be copied to these + * tables such that the calls are filled backwards (from last to first). + * This way, we can jump directly to the first used static call, and execute + * all of them after. This essentially makes the entry point + * dynamic to adapt the number of static calls to the number of callbacks. + */ +struct lsm_static_calls_table { + #define LSM_HOOK(RET, DEFAULT, NAME, ...) \ + struct lsm_static_call NAME[MAX_LSM_COUNT]; + #include <linux/lsm_hook_defs.h> + #undef LSM_HOOK +} __packed __randomize_layout; + /** * struct lsm_id - Identify a Linux Security Module. * @lsm: name of the LSM, must be approved by the LSM maintainers @@ -51,53 +79,45 @@ struct security_hook_heads { * Contains the information that identifies the LSM. */ struct lsm_id { - const char *name; - u64 id; + const char *name; + u64 id; }; /* * Security module hook list structure. * For use with generic list macros for common operations. + * + * struct security_hook_list - Contents of a cacheable, mappable object. + * @scalls: The beginning of the array of static calls assigned to this hook. + * @hook: The callback for the hook. + * @lsm: The name of the lsm that owns this hook. */ struct security_hook_list { - struct hlist_node list; - struct hlist_head *head; - union security_list_options hook; - const struct lsm_id *lsmid; + struct lsm_static_call *scalls; + union security_list_options hook; + const struct lsm_id *lsmid; } __randomize_layout; /* * Security blob size or offset data. */ struct lsm_blob_sizes { - int lbs_cred; - int lbs_file; - int lbs_inode; - int lbs_superblock; - int lbs_ipc; - int lbs_msg_msg; - int lbs_task; - int lbs_xattr_count; /* number of xattr slots in new_xattrs array */ + int lbs_cred; + int lbs_file; + int lbs_ib; + int lbs_inode; + int lbs_sock; + int lbs_superblock; + int lbs_ipc; + int lbs_key; + int lbs_msg_msg; + int lbs_perf_event; + int lbs_task; + int lbs_xattr_count; /* number of xattr slots in new_xattrs array */ + int lbs_tun_dev; + int lbs_bdev; }; -/** - * lsm_get_xattr_slot - Return the next available slot and increment the index - * @xattrs: array storing LSM-provided xattrs - * @xattr_count: number of already stored xattrs (updated) - * - * Retrieve the first available slot in the @xattrs array to fill with an xattr, - * and increment @xattr_count. - * - * Return: The slot to fill in @xattrs if non-NULL, NULL otherwise. - */ -static inline struct xattr *lsm_get_xattr_slot(struct xattr *xattrs, - int *xattr_count) -{ - if (unlikely(!xattrs)) - return NULL; - return &xattrs[(*xattr_count)++]; -} - /* * LSM_RET_VOID is used as the default value in LSM_HOOK definitions for void * LSM hooks (in include/linux/lsm_hook_defs.h). @@ -110,11 +130,11 @@ static inline struct xattr *lsm_get_xattr_slot(struct xattr *xattrs, * care of the common case and reduces the amount of * text involved. */ -#define LSM_HOOK_INIT(HEAD, HOOK) \ - { .head = &security_hook_heads.HEAD, .hook = { .HEAD = HOOK } } - -extern struct security_hook_heads security_hook_heads; -extern char *lsm_names; +#define LSM_HOOK_INIT(NAME, HOOK) \ + { \ + .scalls = static_calls_table.NAME, \ + .hook = { .NAME = HOOK } \ + } extern void security_add_hooks(struct security_hook_list *hooks, int count, const struct lsm_id *lsmid); @@ -137,9 +157,6 @@ struct lsm_info { struct lsm_blob_sizes *blobs; /* Optional: for blob sharing. */ }; -extern struct lsm_info __start_lsm_info[], __end_lsm_info[]; -extern struct lsm_info __start_early_lsm_info[], __end_early_lsm_info[]; - #define DEFINE_LSM(lsm) \ static struct lsm_info __lsm_##lsm \ __used __section(".lsm_info.init") \ @@ -150,6 +167,28 @@ extern struct lsm_info __start_early_lsm_info[], __end_early_lsm_info[]; __used __section(".early_lsm_info.init") \ __aligned(sizeof(unsigned long)) -extern int lsm_inode_alloc(struct inode *inode); +/* DO NOT tamper with these variables outside of the LSM framework */ +extern char *lsm_names; +extern struct lsm_static_calls_table static_calls_table __ro_after_init; +extern struct lsm_info __start_lsm_info[], __end_lsm_info[]; +extern struct lsm_info __start_early_lsm_info[], __end_early_lsm_info[]; + +/** + * lsm_get_xattr_slot - Return the next available slot and increment the index + * @xattrs: array storing LSM-provided xattrs + * @xattr_count: number of already stored xattrs (updated) + * + * Retrieve the first available slot in the @xattrs array to fill with an xattr, + * and increment @xattr_count. + * + * Return: The slot to fill in @xattrs if non-NULL, NULL otherwise. + */ +static inline struct xattr *lsm_get_xattr_slot(struct xattr *xattrs, + int *xattr_count) +{ + if (unlikely(!xattrs)) + return NULL; + return &xattrs[(*xattr_count)++]; +} #endif /* ! __LINUX_LSM_HOOKS_H */ diff --git a/include/linux/lz4.h b/include/linux/lz4.h index b16e15b9587a..ad6042a718b5 100644 --- a/include/linux/lz4.h +++ b/include/linux/lz4.h @@ -645,4 +645,10 @@ int LZ4_decompress_safe_usingDict(const char *source, char *dest, int LZ4_decompress_fast_usingDict(const char *source, char *dest, int originalSize, const char *dictStart, int dictSize); +#define LZ4_DECOMPRESS_INPLACE_MARGIN(compressedSize) (((compressedSize) >> 8) + 32) + +#ifndef LZ4_DISTANCE_MAX /* history window size; can be user-defined at compile time */ +#define LZ4_DISTANCE_MAX 65535 /* set to maximum value by default */ +#endif + #endif diff --git a/include/linux/mailbox/exynos-message.h b/include/linux/mailbox/exynos-message.h new file mode 100644 index 000000000000..5a9ed5ce2046 --- /dev/null +++ b/include/linux/mailbox/exynos-message.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Exynos mailbox message. + * + * Copyright 2024 Linaro Ltd. + */ + +#ifndef _LINUX_EXYNOS_MESSAGE_H_ +#define _LINUX_EXYNOS_MESSAGE_H_ + +#define EXYNOS_MBOX_CHAN_TYPE_DOORBELL 0 +#define EXYNOS_MBOX_CHAN_TYPE_DATA 1 + +struct exynos_mbox_msg { + unsigned int chan_id; + unsigned int chan_type; +}; + +#endif /* _LINUX_EXYNOS_MESSAGE_H_ */ diff --git a/include/linux/mailbox/mchp-ipc.h b/include/linux/mailbox/mchp-ipc.h new file mode 100644 index 000000000000..f084ac9e291b --- /dev/null +++ b/include/linux/mailbox/mchp-ipc.h @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + *Copyright (c) 2024 Microchip Technology Inc. All rights reserved. + */ + +#ifndef _LINUX_MCHP_IPC_H_ +#define _LINUX_MCHP_IPC_H_ + +#include <linux/mailbox_controller.h> +#include <linux/types.h> + +struct mchp_ipc_msg { + u32 *buf; + u16 size; +}; + +struct mchp_ipc_sbi_chan { + void *buf_base_tx; + void *buf_base_rx; + void *msg_buf_tx; + void *msg_buf_rx; + phys_addr_t buf_base_tx_addr; + phys_addr_t buf_base_rx_addr; + phys_addr_t msg_buf_tx_addr; + phys_addr_t msg_buf_rx_addr; + int chan_aggregated_irq; + int mp_irq; + int mc_irq; + u32 id; + u32 max_msg_size; +}; + +#endif /* _LINUX_MCHP_IPC_H_ */ diff --git a/include/linux/maple.h b/include/linux/maple.h index 9aae44efcfd4..3be4e567473c 100644 --- a/include/linux/maple.h +++ b/include/linux/maple.h @@ -97,7 +97,7 @@ int maple_add_packet(struct maple_device *mdev, u32 function, void maple_clear_dev(struct maple_device *mdev); #define to_maple_dev(n) container_of(n, struct maple_device, dev) -#define to_maple_driver(n) container_of(n, struct maple_driver, drv) +#define to_maple_driver(n) container_of_const(n, struct maple_driver, drv) #define maple_get_drvdata(d) dev_get_drvdata(&(d)->dev) #define maple_set_drvdata(d,p) dev_set_drvdata(&(d)->dev, (p)) diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h index a53ad4dabd7e..cbbcd18d4186 100644 --- a/include/linux/maple_tree.h +++ b/include/linux/maple_tree.h @@ -52,9 +52,9 @@ * bit in the node type. This is possible by using bit 1 to indicate if bit 2 * is part of the type or the slot. * - * Once the type is decided, the decision of an allocation range type or a range - * type is done by examining the immutable tree flag for the MAPLE_ALLOC_RANGE - * flag. + * Once the type is decided, the decision of an allocation range type or a + * range type is done by examining the immutable tree flag for the + * MT_FLAGS_ALLOC_RANGE flag. * * Node types: * 0x??1 = Root @@ -148,6 +148,18 @@ enum maple_type { maple_arange_64, }; +enum store_type { + wr_invalid, + wr_new_root, + wr_store_root, + wr_exact_fit, + wr_spanning_store, + wr_split_store, + wr_rebalance, + wr_append, + wr_node_store, + wr_slot_store, +}; /** * DOC: Maple tree flags @@ -212,7 +224,7 @@ typedef struct { /* nothing */ } lockdep_map_p; * (set at tree creation time) and dynamic information set under the spinlock. * * Another use of flags are to indicate global states of the tree. This is the - * case with the MAPLE_USE_RCU flag, which indicates the tree is currently in + * case with the MT_FLAGS_USE_RCU flag, which indicates the tree is currently in * RCU mode. This mode was added to allow the tree to reuse nodes instead of * re-allocating and RCU freeing nodes when there is a single user. */ @@ -436,6 +448,7 @@ struct ma_state { unsigned char offset; unsigned char mas_flags; unsigned char end; /* The end of the node */ + enum store_type store_type; /* The type of store needed for this operation */ }; struct ma_wr_state { @@ -477,6 +490,7 @@ struct ma_wr_state { .max = ULONG_MAX, \ .alloc = NULL, \ .mas_flags = 0, \ + .store_type = wr_invalid, \ } #define MA_WR_STATE(name, ma_state, wr_entry) \ @@ -578,6 +592,20 @@ static __always_inline void mas_reset(struct ma_state *mas) #define mas_for_each(__mas, __entry, __max) \ while (((__entry) = mas_find((__mas), (__max))) != NULL) +/** + * mas_for_each_rev() - Iterate over a range of the maple tree in reverse order. + * @__mas: Maple Tree operation state (maple_state) + * @__entry: Entry retrieved from the tree + * @__min: minimum index to retrieve from the tree + * + * When returned, mas->index and mas->last will hold the entire range for the + * entry. + * + * Note: may return the zero entry. + */ +#define mas_for_each_rev(__mas, __entry, __min) \ + while (((__entry) = mas_find_rev((__mas), (__min))) != NULL) + #ifdef CONFIG_DEBUG_MAPLE_TREE enum mt_dump_format { mt_dump_dec, diff --git a/include/linux/marvell_phy.h b/include/linux/marvell_phy.h index 693eba9869e4..b1fbe4118414 100644 --- a/include/linux/marvell_phy.h +++ b/include/linux/marvell_phy.h @@ -7,6 +7,7 @@ /* Known PHY IDs */ #define MARVELL_PHY_ID_88E1101 0x01410c60 +#define MARVELL_PHY_ID_88E3082 0x01410c80 #define MARVELL_PHY_ID_88E1112 0x01410c90 #define MARVELL_PHY_ID_88E1111 0x01410cc0 #define MARVELL_PHY_ID_88E1118 0x01410e10 @@ -31,6 +32,8 @@ /* Marvel 88E1111 in Finisar SFP module with modified PHY ID */ #define MARVELL_PHY_ID_88E1111_FINISAR 0x01ff0cc0 +/* ID from 88E6020, assumed to be the same for the whole 6250 family */ +#define MARVELL_PHY_ID_88E6250_FAMILY 0x01410db0 /* These Ethernet switch families contain embedded PHYs, but they do * not have a model ID. So the switch driver traps reads to the ID2 * register and returns the switch family ID diff --git a/include/linux/math.h b/include/linux/math.h index dd4152711de7..f5f18dc3616b 100644 --- a/include/linux/math.h +++ b/include/linux/math.h @@ -112,6 +112,8 @@ struct type##_fract { \ __##type numerator; \ __##type denominator; \ }; +__STRUCT_FRACT(s8) +__STRUCT_FRACT(u8) __STRUCT_FRACT(s16) __STRUCT_FRACT(u16) __STRUCT_FRACT(s32) diff --git a/include/linux/math64.h b/include/linux/math64.h index bf74478926d4..6aaccc1626ab 100644 --- a/include/linux/math64.h +++ b/include/linux/math64.h @@ -4,8 +4,8 @@ #include <linux/types.h> #include <linux/math.h> -#include <vdso/math64.h> #include <asm/div64.h> +#include <vdso/math64.h> #if BITS_PER_LONG == 64 @@ -179,16 +179,12 @@ static __always_inline u64 mul_u64_u64_shr(u64 a, u64 mul, unsigned int shift) #ifndef mul_u64_u32_shr static __always_inline u64 mul_u64_u32_shr(u64 a, u32 mul, unsigned int shift) { - u32 ah, al; + u32 ah = a >> 32, al = a; u64 ret; - al = a; - ah = a >> 32; - ret = mul_u32_u32(al, mul) >> shift; if (ah) ret += mul_u32_u32(ah, mul) << (32 - shift); - return ret; } #endif /* mul_u64_u32_shr */ @@ -302,6 +298,19 @@ u64 mul_u64_u64_div_u64(u64 a, u64 mul, u64 div); ({ u64 _tmp = (d); div64_u64((ll) + _tmp - 1, _tmp); }) /** + * DIV_U64_ROUND_UP - unsigned 64bit divide with 32bit divisor rounded up + * @ll: unsigned 64bit dividend + * @d: unsigned 32bit divisor + * + * Divide unsigned 64bit dividend by unsigned 32bit divisor + * and round up. + * + * Return: dividend / divisor rounded up + */ +#define DIV_U64_ROUND_UP(ll, d) \ + ({ u32 _tmp = (d); div_u64((ll) + _tmp - 1, _tmp); }) + +/** * DIV64_U64_ROUND_CLOSEST - unsigned 64bit divide with 64bit divisor rounded to nearest integer * @dividend: unsigned 64bit dividend * @divisor: unsigned 64bit divisor @@ -346,4 +355,19 @@ u64 mul_u64_u64_div_u64(u64 a, u64 mul, u64 div); div_s64((__x - (__d / 2)), __d); \ } \ ) + +/** + * roundup_u64 - Round up a 64bit value to the next specified 32bit multiple + * @x: the value to up + * @y: 32bit multiple to round up to + * + * Rounds @x to the next multiple of @y. For 32bit @x values, see roundup and + * the faster round_up() for powers of 2. + * + * Return: rounded up value. + */ +static inline u64 roundup_u64(u64 x, u32 y) +{ + return DIV_U64_ROUND_UP(x, y) * y; +} #endif /* _LINUX_MATH64_H */ diff --git a/include/linux/mcb.h b/include/linux/mcb.h index 0b971b24a804..4ab2691f51a6 100644 --- a/include/linux/mcb.h +++ b/include/linux/mcb.h @@ -94,10 +94,7 @@ struct mcb_driver { void (*shutdown)(struct mcb_device *mdev); }; -static inline struct mcb_driver *to_mcb_driver(struct device_driver *drv) -{ - return container_of(drv, struct mcb_driver, driver); -} +#define to_mcb_driver(__drv) container_of_const(__drv, struct mcb_driver, driver) static inline void *mcb_get_drvdata(struct mcb_device *dev) { diff --git a/include/linux/mdio.h b/include/linux/mdio.h index 68f8d2e970d4..3c3deac57894 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -31,7 +31,7 @@ struct mdio_device { struct mii_bus *bus; char modalias[MDIO_NAME_SIZE]; - int (*bus_match)(struct device *dev, struct device_driver *drv); + int (*bus_match)(struct device *dev, const struct device_driver *drv); void (*device_free)(struct mdio_device *mdiodev); void (*device_remove)(struct mdio_device *mdiodev); @@ -57,11 +57,8 @@ struct mdio_driver_common { }; #define MDIO_DEVICE_FLAG_PHY 1 -static inline struct mdio_driver_common * -to_mdio_common_driver(const struct device_driver *driver) -{ - return container_of(driver, struct mdio_driver_common, driver); -} +#define to_mdio_common_driver(__drv_c) container_of_const(__drv_c, struct mdio_driver_common, \ + driver) /* struct mdio_driver: Generic MDIO driver */ struct mdio_driver { @@ -80,12 +77,8 @@ struct mdio_driver { void (*shutdown)(struct mdio_device *mdiodev); }; -static inline struct mdio_driver * -to_mdio_driver(const struct device_driver *driver) -{ - return container_of(to_mdio_common_driver(driver), struct mdio_driver, - mdiodrv); -} +#define to_mdio_driver(__drv_m) container_of_const(to_mdio_common_driver(__drv_m), \ + struct mdio_driver, mdiodrv) /* device driver data */ static inline void mdiodev_set_drvdata(struct mdio_device *mdio, void *data) @@ -105,7 +98,7 @@ void mdio_device_remove(struct mdio_device *mdiodev); void mdio_device_reset(struct mdio_device *mdiodev, int value); int mdio_driver_register(struct mdio_driver *drv); void mdio_driver_unregister(struct mdio_driver *drv); -int mdio_device_bus_match(struct device *dev, struct device_driver *drv); +int mdio_device_bus_match(struct device *dev, const struct device_driver *drv); static inline void mdio_device_get(struct mdio_device *mdiodev) { @@ -172,31 +165,12 @@ extern int mdio_set_flag(const struct mdio_if_info *mdio, bool sense); extern int mdio45_links_ok(const struct mdio_if_info *mdio, u32 mmds); extern int mdio45_nway_restart(const struct mdio_if_info *mdio); -extern void mdio45_ethtool_gset_npage(const struct mdio_if_info *mdio, - struct ethtool_cmd *ecmd, - u32 npage_adv, u32 npage_lpa); extern void mdio45_ethtool_ksettings_get_npage(const struct mdio_if_info *mdio, struct ethtool_link_ksettings *cmd, u32 npage_adv, u32 npage_lpa); /** - * mdio45_ethtool_gset - get settings for ETHTOOL_GSET - * @mdio: MDIO interface - * @ecmd: Ethtool request structure - * - * Since the CSRs for auto-negotiation using next pages are not fully - * standardised, this function does not attempt to decode them. Use - * mdio45_ethtool_gset_npage() to specify advertisement bits from next - * pages. - */ -static inline void mdio45_ethtool_gset(const struct mdio_if_info *mdio, - struct ethtool_cmd *ecmd) -{ - mdio45_ethtool_gset_npage(mdio, ecmd, 0, 0); -} - -/** * mdio45_ethtool_ksettings_get - get settings for ETHTOOL_GLINKSETTINGS * @mdio: MDIO interface * @cmd: Ethtool request structure diff --git a/include/linux/memblock.h b/include/linux/memblock.h index e2082240586d..e79eb6ac516f 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -299,25 +299,6 @@ void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, void __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone, unsigned long *out_spfn, unsigned long *out_epfn); -/** - * for_each_free_mem_pfn_range_in_zone - iterate through zone specific free - * memblock areas - * @i: u64 used as loop variable - * @zone: zone in which all of the memory blocks reside - * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL - * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL - * - * Walks over free (memory && !reserved) areas of memblock in a specific - * zone. Available once memblock and an empty zone is initialized. The main - * assumption is that the zone start, end, and pgdat have been associated. - * This way we can use the zone to determine NUMA node, and if a given part - * of the memblock is valid for the zone. - */ -#define for_each_free_mem_pfn_range_in_zone(i, zone, p_start, p_end) \ - for (i = 0, \ - __next_mem_pfn_range_in_zone(&i, zone, p_start, p_end); \ - i != U64_MAX; \ - __next_mem_pfn_range_in_zone(&i, zone, p_start, p_end)) /** * for_each_free_mem_pfn_range_in_zone_from - iterate through zone specific @@ -335,8 +316,6 @@ void __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone, for (; i != U64_MAX; \ __next_mem_pfn_range_in_zone(&i, zone, p_start, p_end)) -int __init deferred_page_init_max_threads(const struct cpumask *node_cpumask); - #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ /** @@ -399,6 +378,10 @@ static inline int memblock_get_region_node(const struct memblock_region *r) /* Flags for memblock allocation APIs */ #define MEMBLOCK_ALLOC_ANYWHERE (~(phys_addr_t)0) #define MEMBLOCK_ALLOC_ACCESSIBLE 0 +/* + * MEMBLOCK_ALLOC_NOLEAKTRACE avoids kmemleak tracing. It implies + * MEMBLOCK_ALLOC_ACCESSIBLE + */ #define MEMBLOCK_ALLOC_NOLEAKTRACE 1 /* We are using top down, so it is safe to use 0 here */ @@ -438,6 +421,12 @@ static __always_inline void *memblock_alloc(phys_addr_t size, phys_addr_t align) MEMBLOCK_ALLOC_ACCESSIBLE, NUMA_NO_NODE); } +void *__memblock_alloc_or_panic(phys_addr_t size, phys_addr_t align, + const char *func); + +#define memblock_alloc_or_panic(size, align) \ + __memblock_alloc_or_panic(size, align, __func__) + static inline void *memblock_alloc_raw(phys_addr_t size, phys_addr_t align) { @@ -488,6 +477,7 @@ static inline __init_memblock bool memblock_bottom_up(void) phys_addr_t memblock_phys_mem_size(void); phys_addr_t memblock_reserved_size(void); +unsigned long memblock_estimated_nr_free_pages(void); phys_addr_t memblock_start_of_DRAM(void); phys_addr_t memblock_end_of_DRAM(void); void memblock_enforce_memory_limit(phys_addr_t memory_limit); @@ -565,7 +555,7 @@ static inline unsigned long memblock_region_reserved_end_pfn(const struct memblo } /** - * for_each_mem_region - itereate over memory regions + * for_each_mem_region - iterate over memory regions * @region: loop variable */ #define for_each_mem_region(region) \ diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 394fd0a887ae..6e74b8254d9b 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -57,7 +57,7 @@ enum memcg_memory_event { struct mem_cgroup_reclaim_cookie { pg_data_t *pgdat; - unsigned int generation; + int generation; }; #ifdef CONFIG_MEMCG @@ -69,67 +69,50 @@ struct mem_cgroup_id { refcount_t ref; }; -/* - * Per memcg event counter is incremented at every pagein/pageout. With THP, - * it will be incremented by the number of pages. This counter is used - * to trigger some periodic events. This is straightforward and better - * than using jiffies etc. to handle periodic memcg event. - */ -enum mem_cgroup_events_target { - MEM_CGROUP_TARGET_THRESH, - MEM_CGROUP_TARGET_SOFTLIMIT, - MEM_CGROUP_NTARGETS, -}; - struct memcg_vmstats_percpu; +struct memcg1_events_percpu; struct memcg_vmstats; +struct lruvec_stats_percpu; +struct lruvec_stats; struct mem_cgroup_reclaim_iter { struct mem_cgroup *position; /* scan generation, increased every round-trip */ - unsigned int generation; -}; - -struct lruvec_stats_percpu { - /* Local (CPU and cgroup) state */ - long state[NR_VM_NODE_STAT_ITEMS]; - - /* Delta calculation for lockless upward propagation */ - long state_prev[NR_VM_NODE_STAT_ITEMS]; -}; - -struct lruvec_stats { - /* Aggregated (CPU and subtree) state */ - long state[NR_VM_NODE_STAT_ITEMS]; - - /* Non-hierarchical (CPU aggregated) state */ - long state_local[NR_VM_NODE_STAT_ITEMS]; - - /* Pending child counts during tree propagation */ - long state_pending[NR_VM_NODE_STAT_ITEMS]; + atomic_t generation; }; /* * per-node information in memory controller. */ struct mem_cgroup_per_node { - struct lruvec lruvec; + /* Keep the read-only fields at the start */ + struct mem_cgroup *memcg; /* Back pointer, we cannot */ + /* use container_of */ struct lruvec_stats_percpu __percpu *lruvec_stats_percpu; - struct lruvec_stats lruvec_stats; - - unsigned long lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS]; - - struct mem_cgroup_reclaim_iter iter; - + struct lruvec_stats *lruvec_stats; struct shrinker_info __rcu *shrinker_info; +#ifdef CONFIG_MEMCG_V1 + /* + * Memcg-v1 only stuff in middle as buffer between read mostly fields + * and update often fields to avoid false sharing. If v1 stuff is + * not present, an explicit padding is needed. + */ + struct rb_node tree_node; /* RB tree node */ unsigned long usage_in_excess;/* Set to the value by which */ /* the soft limit is exceeded*/ bool on_tree; - struct mem_cgroup *memcg; /* Back pointer, we cannot */ - /* use container_of */ +#else + CACHELINE_PADDING(_pad1_); +#endif + + /* Fields which get updated often at the end. */ + struct lruvec lruvec; + CACHELINE_PADDING(_pad2_); + unsigned long lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS]; + struct mem_cgroup_reclaim_iter iter; }; struct mem_cgroup_threshold { @@ -211,14 +194,15 @@ struct mem_cgroup { struct page_counter memsw; /* v1 only */ }; - /* Legacy consumer-oriented counters */ - struct page_counter kmem; /* v1 only */ - struct page_counter tcpmem; /* v1 only */ + /* registered local peak watchers */ + struct list_head memory_peaks; + struct list_head swap_peaks; + spinlock_t peaks_lock; /* Range enforcement for interrupt charges */ struct work_struct high_work; -#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP) +#ifdef CONFIG_ZSWAP unsigned long zswap_max; /* @@ -228,8 +212,6 @@ struct mem_cgroup { bool zswap_writeback; #endif - unsigned long soft_limit; - /* vmpressure notifications */ struct vmpressure vmpressure; @@ -238,13 +220,7 @@ struct mem_cgroup { */ bool oom_group; - /* protected by memcg_oom_lock */ - bool oom_lock; - int under_oom; - - int swappiness; - /* OOM-Killer disable */ - int oom_kill_disable; + int swappiness; /* memory.events and memory.events.local */ struct cgroup_file events_file; @@ -253,29 +229,6 @@ struct mem_cgroup { /* handle for "memory.swap.events" */ struct cgroup_file swap_events_file; - /* protect arrays of thresholds */ - struct mutex thresholds_lock; - - /* thresholds for memory usage. RCU-protected */ - struct mem_cgroup_thresholds thresholds; - - /* thresholds for mem+swap usage. RCU-protected */ - struct mem_cgroup_thresholds memsw_thresholds; - - /* For oom notifier event fd */ - struct list_head oom_notify; - - /* - * Should we move charges of a task when a task is moved into this - * mem_cgroup ? And what type of charges should we move ? - */ - unsigned long move_charge_at_immigrate; - /* taken only while moving_account > 0 */ - spinlock_t move_lock; - unsigned long move_lock_flags; - - CACHELINE_PADDING(_pad1_); - /* memory.stat */ struct memcg_vmstats *vmstats; @@ -290,11 +243,6 @@ struct mem_cgroup { */ unsigned long socket_pressure; - /* Legacy tcp memory accounting */ - bool tcpmem_active; - int tcpmem_pressure; - -#ifdef CONFIG_MEMCG_KMEM int kmemcg_id; /* * memcg->objcg is wiped out as a part of the objcg repaprenting @@ -305,15 +253,6 @@ struct mem_cgroup { struct obj_cgroup *orig_objcg; /* list of inherited objcgs, protected by objcg_lock */ struct list_head objcg_list; -#endif - - CACHELINE_PADDING(_pad2_); - - /* - * set > 0 if pages under this cgroup are moving to other cgroup. - */ - atomic_t moving_account; - struct task_struct *move_lock_task; struct memcg_vmstats_percpu __percpu *vmstats_percpu; @@ -323,10 +262,6 @@ struct mem_cgroup { struct memcg_cgwb_frn cgwb_frn[MEMCG_CGWB_FRN_CNT]; #endif - /* List of events which userspace want to receive */ - struct list_head event_list; - spinlock_t event_list_lock; - #ifdef CONFIG_TRANSPARENT_HUGEPAGE struct deferred_split deferred_split_queue; #endif @@ -336,6 +271,43 @@ struct mem_cgroup { struct lru_gen_mm_list mm_list; #endif +#ifdef CONFIG_MEMCG_V1 + /* Legacy consumer-oriented counters */ + struct page_counter kmem; /* v1 only */ + struct page_counter tcpmem; /* v1 only */ + + struct memcg1_events_percpu __percpu *events_percpu; + + unsigned long soft_limit; + + /* protected by memcg_oom_lock */ + bool oom_lock; + int under_oom; + + /* OOM-Killer disable */ + int oom_kill_disable; + + /* protect arrays of thresholds */ + struct mutex thresholds_lock; + + /* thresholds for memory usage. RCU-protected */ + struct mem_cgroup_thresholds thresholds; + + /* thresholds for mem+swap usage. RCU-protected */ + struct mem_cgroup_thresholds memsw_thresholds; + + /* For oom notifier event fd */ + struct list_head oom_notify; + + /* Legacy tcp memory accounting */ + bool tcpmem_active; + int tcpmem_pressure; + + /* List of events which userspace want to receive */ + struct list_head event_list; + spinlock_t event_list_lock; +#endif /* CONFIG_MEMCG_V1 */ + struct mem_cgroup_per_node *nodeinfo[]; }; @@ -349,15 +321,32 @@ struct mem_cgroup { extern struct mem_cgroup *root_mem_cgroup; enum page_memcg_data_flags { - /* page->memcg_data is a pointer to an objcgs vector */ - MEMCG_DATA_OBJCGS = (1UL << 0), + /* page->memcg_data is a pointer to an slabobj_ext vector */ + MEMCG_DATA_OBJEXTS = (1UL << 0), /* page has been accounted as a non-slab kernel page */ MEMCG_DATA_KMEM = (1UL << 1), /* the next bit after the last actual flag */ __NR_MEMCG_DATA_FLAGS = (1UL << 2), }; -#define MEMCG_DATA_FLAGS_MASK (__NR_MEMCG_DATA_FLAGS - 1) +#define __FIRST_OBJEXT_FLAG __NR_MEMCG_DATA_FLAGS + +#else /* CONFIG_MEMCG */ + +#define __FIRST_OBJEXT_FLAG (1UL << 0) + +#endif /* CONFIG_MEMCG */ + +enum objext_flags { + /* slabobj_ext vector failed to allocate */ + OBJEXTS_ALLOC_FAIL = __FIRST_OBJEXT_FLAG, + /* the next bit after the last actual flag */ + __NR_OBJEXTS_FLAGS = (__FIRST_OBJEXT_FLAG << 1), +}; + +#define OBJEXTS_FLAGS_MASK (__NR_OBJEXTS_FLAGS - 1) + +#ifdef CONFIG_MEMCG static inline bool folio_memcg_kmem(struct folio *folio); @@ -365,11 +354,11 @@ static inline bool folio_memcg_kmem(struct folio *folio); * After the initialization objcg->memcg is always pointing at * a valid memcg, but can be atomically swapped to the parent memcg. * - * The caller must ensure that the returned memcg won't be released: - * e.g. acquire the rcu_read_lock or css_set_lock. + * The caller must ensure that the returned memcg won't be released. */ static inline struct mem_cgroup *obj_cgroup_memcg(struct obj_cgroup *objcg) { + lockdep_assert_once(rcu_read_lock_held() || lockdep_is_held(&cgroup_mutex)); return READ_ONCE(objcg->memcg); } @@ -388,10 +377,10 @@ static inline struct mem_cgroup *__folio_memcg(struct folio *folio) unsigned long memcg_data = folio->memcg_data; VM_BUG_ON_FOLIO(folio_test_slab(folio), folio); - VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_OBJCGS, folio); + VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_OBJEXTS, folio); VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_KMEM, folio); - return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); + return (struct mem_cgroup *)(memcg_data & ~OBJEXTS_FLAGS_MASK); } /* @@ -409,10 +398,10 @@ static inline struct obj_cgroup *__folio_objcg(struct folio *folio) unsigned long memcg_data = folio->memcg_data; VM_BUG_ON_FOLIO(folio_test_slab(folio), folio); - VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_OBJCGS, folio); + VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_OBJEXTS, folio); VM_BUG_ON_FOLIO(!(memcg_data & MEMCG_DATA_KMEM), folio); - return (struct obj_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); + return (struct obj_cgroup *)(memcg_data & ~OBJEXTS_FLAGS_MASK); } /* @@ -429,9 +418,7 @@ static inline struct obj_cgroup *__folio_objcg(struct folio *folio) * * - the folio lock * - LRU isolation - * - folio_memcg_lock() * - exclusive reference - * - mem_cgroup_trylock_pages() * * For a kmem folio a caller should hold an rcu read lock to protect memcg * associated with a kmem folio from being released. @@ -443,37 +430,17 @@ static inline struct mem_cgroup *folio_memcg(struct folio *folio) return __folio_memcg(folio); } -static inline struct mem_cgroup *page_memcg(struct page *page) -{ - return folio_memcg(page_folio(page)); -} - -/** - * folio_memcg_rcu - Locklessly get the memory cgroup associated with a folio. +/* + * folio_memcg_charged - If a folio is charged to a memory cgroup. * @folio: Pointer to the folio. * - * This function assumes that the folio is known to have a - * proper memory cgroup pointer. It's not safe to call this function - * against some type of folios, e.g. slab folios or ex-slab folios. - * - * Return: A pointer to the memory cgroup associated with the folio, - * or NULL. + * Returns true if folio is charged to a memory cgroup, otherwise returns false. */ -static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio) +static inline bool folio_memcg_charged(struct folio *folio) { - unsigned long memcg_data = READ_ONCE(folio->memcg_data); - - VM_BUG_ON_FOLIO(folio_test_slab(folio), folio); - WARN_ON_ONCE(!rcu_read_lock_held()); - - if (memcg_data & MEMCG_DATA_KMEM) { - struct obj_cgroup *objcg; - - objcg = (void *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); - return obj_cgroup_memcg(objcg); - } - - return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); + if (folio_memcg_kmem(folio)) + return __folio_objcg(folio) != NULL; + return __folio_memcg(folio) != NULL; } /* @@ -491,9 +458,7 @@ static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio) * * - the folio lock * - LRU isolation - * - lock_folio_memcg() * - exclusive reference - * - mem_cgroup_trylock_pages() * * For a kmem folio a caller should hold an rcu read lock to protect memcg * associated with a kmem folio from being released. @@ -506,17 +471,17 @@ static inline struct mem_cgroup *folio_memcg_check(struct folio *folio) */ unsigned long memcg_data = READ_ONCE(folio->memcg_data); - if (memcg_data & MEMCG_DATA_OBJCGS) + if (memcg_data & MEMCG_DATA_OBJEXTS) return NULL; if (memcg_data & MEMCG_DATA_KMEM) { struct obj_cgroup *objcg; - objcg = (void *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); + objcg = (void *)(memcg_data & ~OBJEXTS_FLAGS_MASK); return obj_cgroup_memcg(objcg); } - return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); + return (struct mem_cgroup *)(memcg_data & ~OBJEXTS_FLAGS_MASK); } static inline struct mem_cgroup *page_memcg_check(struct page *page) @@ -540,7 +505,6 @@ retry: return memcg; } -#ifdef CONFIG_MEMCG_KMEM /* * folio_memcg_kmem - Check if the folio has the memcg_kmem flag set. * @folio: Pointer to the folio. @@ -552,19 +516,10 @@ retry: static inline bool folio_memcg_kmem(struct folio *folio) { VM_BUG_ON_PGFLAGS(PageTail(&folio->page), &folio->page); - VM_BUG_ON_FOLIO(folio->memcg_data & MEMCG_DATA_OBJCGS, folio); + VM_BUG_ON_FOLIO(folio->memcg_data & MEMCG_DATA_OBJEXTS, folio); return folio->memcg_data & MEMCG_DATA_KMEM; } - -#else -static inline bool folio_memcg_kmem(struct folio *folio) -{ - return false; -} - -#endif - static inline bool PageMemcgKmem(struct page *page) { return folio_memcg_kmem(page_folio(page)); @@ -665,8 +620,6 @@ static inline bool mem_cgroup_below_min(struct mem_cgroup *target, page_counter_read(&memcg->memory); } -void mem_cgroup_commit_charge(struct folio *folio, struct mem_cgroup *memcg); - int __mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, gfp_t gfp); /** @@ -691,12 +644,12 @@ static inline int mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, return __mem_cgroup_charge(folio, mm, gfp); } -int mem_cgroup_hugetlb_try_charge(struct mem_cgroup *memcg, gfp_t gfp, - long nr_pages); +int mem_cgroup_charge_hugetlb(struct folio* folio, gfp_t gfp); int mem_cgroup_swapin_charge_folio(struct folio *folio, struct mm_struct *mm, gfp_t gfp, swp_entry_t entry); -void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry); + +void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry, unsigned int nr_pages); void __mem_cgroup_uncharge(struct folio *folio); @@ -721,7 +674,6 @@ static inline void mem_cgroup_uncharge_folios(struct folio_batch *folios) __mem_cgroup_uncharge_folios(folios); } -void mem_cgroup_cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages); void mem_cgroup_replace_folio(struct folio *old, struct folio *new); void mem_cgroup_migrate(struct folio *old, struct folio *new); @@ -781,6 +733,8 @@ struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm); struct mem_cgroup *get_mem_cgroup_from_current(void); +struct mem_cgroup *get_mem_cgroup_from_folio(struct folio *folio); + struct lruvec *folio_lruvec_lock(struct folio *folio); struct lruvec *folio_lruvec_lock_irq(struct folio *folio); struct lruvec *folio_lruvec_lock_irqsave(struct folio *folio, @@ -818,7 +772,8 @@ static inline void obj_cgroup_get_many(struct obj_cgroup *objcg, static inline void obj_cgroup_put(struct obj_cgroup *objcg) { - percpu_ref_put(&objcg->refcnt); + if (objcg) + percpu_ref_put(&objcg->refcnt); } static inline bool mem_cgroup_tryget(struct mem_cgroup *memcg) @@ -948,53 +903,16 @@ void mem_cgroup_print_oom_context(struct mem_cgroup *memcg, void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg); -static inline void mem_cgroup_enter_user_fault(void) -{ - WARN_ON(current->in_user_fault); - current->in_user_fault = 1; -} - -static inline void mem_cgroup_exit_user_fault(void) -{ - WARN_ON(!current->in_user_fault); - current->in_user_fault = 0; -} - -static inline bool task_in_memcg_oom(struct task_struct *p) -{ - return p->memcg_in_oom; -} - -bool mem_cgroup_oom_synchronize(bool wait); struct mem_cgroup *mem_cgroup_get_oom_group(struct task_struct *victim, struct mem_cgroup *oom_domain); void mem_cgroup_print_oom_group(struct mem_cgroup *memcg); -void folio_memcg_lock(struct folio *folio); -void folio_memcg_unlock(struct folio *folio); - -void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val); - -/* try to stablize folio_memcg() for all the pages in a memcg */ -static inline bool mem_cgroup_trylock_pages(struct mem_cgroup *memcg) -{ - rcu_read_lock(); - - if (mem_cgroup_disabled() || !atomic_read(&memcg->moving_account)) - return true; - - rcu_read_unlock(); - return false; -} - -static inline void mem_cgroup_unlock_pages(void) -{ - rcu_read_unlock(); -} +void __mod_memcg_state(struct mem_cgroup *memcg, enum memcg_stat_item idx, + int val); /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void mod_memcg_state(struct mem_cgroup *memcg, - int idx, int val) + enum memcg_stat_item idx, int val) { unsigned long flags; @@ -1004,7 +922,7 @@ static inline void mod_memcg_state(struct mem_cgroup *memcg, } static inline void mod_memcg_page_state(struct page *page, - int idx, int val) + enum memcg_stat_item idx, int val) { struct mem_cgroup *memcg; @@ -1012,55 +930,20 @@ static inline void mod_memcg_page_state(struct page *page, return; rcu_read_lock(); - memcg = page_memcg(page); + memcg = folio_memcg(page_folio(page)); if (memcg) mod_memcg_state(memcg, idx, val); rcu_read_unlock(); } unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx); - -static inline unsigned long lruvec_page_state(struct lruvec *lruvec, - enum node_stat_item idx) -{ - struct mem_cgroup_per_node *pn; - long x; - - if (mem_cgroup_disabled()) - return node_page_state(lruvec_pgdat(lruvec), idx); - - pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec); - x = READ_ONCE(pn->lruvec_stats.state[idx]); -#ifdef CONFIG_SMP - if (x < 0) - x = 0; -#endif - return x; -} - -static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, - enum node_stat_item idx) -{ - struct mem_cgroup_per_node *pn; - long x = 0; - - if (mem_cgroup_disabled()) - return node_page_state(lruvec_pgdat(lruvec), idx); - - pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec); - x = READ_ONCE(pn->lruvec_stats.state_local[idx]); -#ifdef CONFIG_SMP - if (x < 0) - x = 0; -#endif - return x; -} +unsigned long lruvec_page_state(struct lruvec *lruvec, enum node_stat_item idx); +unsigned long lruvec_page_state_local(struct lruvec *lruvec, + enum node_stat_item idx); void mem_cgroup_flush_stats(struct mem_cgroup *memcg); void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg); -void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, - int val); void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val); static inline void mod_lruvec_kmem_state(void *p, enum node_stat_item idx, @@ -1073,16 +956,6 @@ static inline void mod_lruvec_kmem_state(void *p, enum node_stat_item idx, local_irq_restore(flags); } -static inline void mod_memcg_lruvec_state(struct lruvec *lruvec, - enum node_stat_item idx, int val) -{ - unsigned long flags; - - local_irq_save(flags); - __mod_memcg_lruvec_state(lruvec, idx, val); - local_irq_restore(flags); -} - void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, unsigned long count); @@ -1106,8 +979,8 @@ static inline void count_memcg_folio_events(struct folio *folio, count_memcg_events(memcg, idx, nr); } -static inline void count_memcg_event_mm(struct mm_struct *mm, - enum vm_event_item idx) +static inline void count_memcg_events_mm(struct mm_struct *mm, + enum vm_event_item idx, unsigned long count) { struct mem_cgroup *memcg; @@ -1117,10 +990,16 @@ static inline void count_memcg_event_mm(struct mm_struct *mm, rcu_read_lock(); memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); if (likely(memcg)) - count_memcg_events(memcg, idx, 1); + count_memcg_events(memcg, idx, count); rcu_read_unlock(); } +static inline void count_memcg_event_mm(struct mm_struct *mm, + enum vm_event_item idx) +{ + count_memcg_events_mm(mm, idx, 1); +} + static inline void memcg_memory_event(struct mem_cgroup *memcg, enum memcg_memory_event event) { @@ -1163,9 +1042,22 @@ static inline void memcg_memory_event_mm(struct mm_struct *mm, void split_page_memcg(struct page *head, int old_order, int new_order); -unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, - gfp_t gfp_mask, - unsigned long *total_scanned); +static inline u64 cgroup_id_from_mm(struct mm_struct *mm) +{ + struct mem_cgroup *memcg; + u64 id; + + if (mem_cgroup_disabled()) + return 0; + + rcu_read_lock(); + memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); + if (!memcg) + memcg = root_mem_cgroup; + id = cgroup_id(memcg->css.cgroup); + rcu_read_unlock(); + return id; +} #else /* CONFIG_MEMCG */ @@ -1176,15 +1068,9 @@ static inline struct mem_cgroup *folio_memcg(struct folio *folio) return NULL; } -static inline struct mem_cgroup *page_memcg(struct page *page) +static inline bool folio_memcg_charged(struct folio *folio) { - return NULL; -} - -static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio) -{ - WARN_ON_ONCE(!rcu_read_lock_held()); - return NULL; + return false; } static inline struct mem_cgroup *folio_memcg_check(struct folio *folio) @@ -1262,21 +1148,15 @@ static inline bool mem_cgroup_below_min(struct mem_cgroup *target, return false; } -static inline void mem_cgroup_commit_charge(struct folio *folio, - struct mem_cgroup *memcg) -{ -} - static inline int mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, gfp_t gfp) { return 0; } -static inline int mem_cgroup_hugetlb_try_charge(struct mem_cgroup *memcg, - gfp_t gfp, long nr_pages) +static inline int mem_cgroup_charge_hugetlb(struct folio* folio, gfp_t gfp) { - return 0; + return 0; } static inline int mem_cgroup_swapin_charge_folio(struct folio *folio, @@ -1285,7 +1165,7 @@ static inline int mem_cgroup_swapin_charge_folio(struct folio *folio, return 0; } -static inline void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry) +static inline void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry, unsigned int nr) { } @@ -1297,11 +1177,6 @@ static inline void mem_cgroup_uncharge_folios(struct folio_batch *folios) { } -static inline void mem_cgroup_cancel_charge(struct mem_cgroup *memcg, - unsigned int nr_pages) -{ -} - static inline void mem_cgroup_replace_folio(struct folio *old, struct folio *new) { @@ -1349,12 +1224,21 @@ static inline struct mem_cgroup *get_mem_cgroup_from_current(void) return NULL; } +static inline struct mem_cgroup *get_mem_cgroup_from_folio(struct folio *folio) +{ + return NULL; +} + static inline struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css) { return NULL; } +static inline void obj_cgroup_get(struct obj_cgroup *objcg) +{ +} + static inline void obj_cgroup_put(struct obj_cgroup *objcg) { } @@ -1482,48 +1366,10 @@ mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg) { } -static inline void folio_memcg_lock(struct folio *folio) -{ -} - -static inline void folio_memcg_unlock(struct folio *folio) -{ -} - -static inline bool mem_cgroup_trylock_pages(struct mem_cgroup *memcg) -{ - /* to match folio_memcg_rcu() */ - rcu_read_lock(); - return true; -} - -static inline void mem_cgroup_unlock_pages(void) -{ - rcu_read_unlock(); -} - static inline void mem_cgroup_handle_over_high(gfp_t gfp_mask) { } -static inline void mem_cgroup_enter_user_fault(void) -{ -} - -static inline void mem_cgroup_exit_user_fault(void) -{ -} - -static inline bool task_in_memcg_oom(struct task_struct *p) -{ - return false; -} - -static inline bool mem_cgroup_oom_synchronize(bool wait) -{ - return false; -} - static inline struct mem_cgroup *mem_cgroup_get_oom_group( struct task_struct *victim, struct mem_cgroup *oom_domain) { @@ -1535,19 +1381,19 @@ static inline void mem_cgroup_print_oom_group(struct mem_cgroup *memcg) } static inline void __mod_memcg_state(struct mem_cgroup *memcg, - int idx, + enum memcg_stat_item idx, int nr) { } static inline void mod_memcg_state(struct mem_cgroup *memcg, - int idx, + enum memcg_stat_item idx, int nr) { } static inline void mod_memcg_page_state(struct page *page, - int idx, int val) + enum memcg_stat_item idx, int val) { } @@ -1576,11 +1422,6 @@ static inline void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg) { } -static inline void __mod_memcg_lruvec_state(struct lruvec *lruvec, - enum node_stat_item idx, int val) -{ -} - static inline void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val) { @@ -1614,6 +1455,11 @@ static inline void count_memcg_folio_events(struct folio *folio, { } +static inline void count_memcg_events_mm(struct mm_struct *mm, + enum vm_event_item idx, unsigned long count) +{ +} + static inline void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx) { @@ -1623,15 +1469,25 @@ static inline void split_page_memcg(struct page *head, int old_order, int new_or { } -static inline -unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, - gfp_t gfp_mask, - unsigned long *total_scanned) +static inline u64 cgroup_id_from_mm(struct mm_struct *mm) { return 0; } #endif /* CONFIG_MEMCG */ +/* + * Extended information for slab objects stored as an array in page->memcg_data + * if MEMCG_DATA_OBJEXTS is set. + */ +struct slabobj_ext { +#ifdef CONFIG_MEMCG + struct obj_cgroup *objcg; +#endif +#ifdef CONFIG_MEM_ALLOC_PROFILING + union codetag_ref ref; +#endif +} __aligned(8); + static inline void __inc_lruvec_kmem_state(void *p, enum node_stat_item idx) { __mod_lruvec_kmem_state(p, idx, 1); @@ -1671,7 +1527,7 @@ static inline void unlock_page_lruvec_irqrestore(struct lruvec *lruvec, spin_unlock_irqrestore(&lruvec->lru_lock, flags); } -/* Test requires a stable page->memcg binding, see page_memcg() */ +/* Test requires a stable folio->memcg binding, see folio_memcg() */ static inline bool folio_matches_lruvec(struct folio *folio, struct lruvec *lruvec) { @@ -1769,8 +1625,10 @@ void mem_cgroup_sk_alloc(struct sock *sk); void mem_cgroup_sk_free(struct sock *sk); static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) { +#ifdef CONFIG_MEMCG_V1 if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) return !!memcg->tcpmem_pressure; +#endif /* CONFIG_MEMCG_V1 */ do { if (time_before(jiffies, READ_ONCE(memcg->socket_pressure))) return true; @@ -1797,7 +1655,7 @@ static inline void set_shrinker_bit(struct mem_cgroup *memcg, } #endif -#ifdef CONFIG_MEMCG_KMEM +#ifdef CONFIG_MEMCG bool mem_cgroup_kmem_disabled(void); int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order); void __memcg_kmem_uncharge_page(struct page *page, int order); @@ -1862,11 +1720,11 @@ static inline int memcg_kmem_id(struct mem_cgroup *memcg) return memcg ? memcg->kmemcg_id : -1; } -struct mem_cgroup *mem_cgroup_from_obj(void *p); struct mem_cgroup *mem_cgroup_from_slab_obj(void *p); -static inline void count_objcg_event(struct obj_cgroup *objcg, - enum vm_event_item idx) +static inline void count_objcg_events(struct obj_cgroup *objcg, + enum vm_event_item idx, + unsigned long count) { struct mem_cgroup *memcg; @@ -1875,7 +1733,7 @@ static inline void count_objcg_event(struct obj_cgroup *objcg, rcu_read_lock(); memcg = obj_cgroup_memcg(objcg); - count_memcg_events(memcg, idx, 1); + count_memcg_events(memcg, idx, count); rcu_read_unlock(); } @@ -1925,24 +1783,20 @@ static inline int memcg_kmem_id(struct mem_cgroup *memcg) return -1; } -static inline struct mem_cgroup *mem_cgroup_from_obj(void *p) -{ - return NULL; -} - static inline struct mem_cgroup *mem_cgroup_from_slab_obj(void *p) { return NULL; } -static inline void count_objcg_event(struct obj_cgroup *objcg, - enum vm_event_item idx) +static inline void count_objcg_events(struct obj_cgroup *objcg, + enum vm_event_item idx, + unsigned long count) { } -#endif /* CONFIG_MEMCG_KMEM */ +#endif /* CONFIG_MEMCG */ -#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP) +#if defined(CONFIG_MEMCG) && defined(CONFIG_ZSWAP) bool obj_cgroup_may_zswap(struct obj_cgroup *objcg); void obj_cgroup_charge_zswap(struct obj_cgroup *objcg, size_t size); void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, size_t size); @@ -1967,4 +1821,60 @@ static inline bool mem_cgroup_zswap_writeback_enabled(struct mem_cgroup *memcg) } #endif + +/* Cgroup v1-related declarations */ + +#ifdef CONFIG_MEMCG_V1 +unsigned long memcg1_soft_limit_reclaim(pg_data_t *pgdat, int order, + gfp_t gfp_mask, + unsigned long *total_scanned); + +bool mem_cgroup_oom_synchronize(bool wait); + +static inline bool task_in_memcg_oom(struct task_struct *p) +{ + return p->memcg_in_oom; +} + +static inline void mem_cgroup_enter_user_fault(void) +{ + WARN_ON(current->in_user_fault); + current->in_user_fault = 1; +} + +static inline void mem_cgroup_exit_user_fault(void) +{ + WARN_ON(!current->in_user_fault); + current->in_user_fault = 0; +} + +#else /* CONFIG_MEMCG_V1 */ +static inline +unsigned long memcg1_soft_limit_reclaim(pg_data_t *pgdat, int order, + gfp_t gfp_mask, + unsigned long *total_scanned) +{ + return 0; +} + +static inline bool task_in_memcg_oom(struct task_struct *p) +{ + return false; +} + +static inline bool mem_cgroup_oom_synchronize(bool wait) +{ + return false; +} + +static inline void mem_cgroup_enter_user_fault(void) +{ +} + +static inline void mem_cgroup_exit_user_fault(void) +{ +} + +#endif /* CONFIG_MEMCG_V1 */ + #endif /* _LINUX_MEMCONTROL_H */ diff --git a/include/linux/memfd.h b/include/linux/memfd.h index e7abf6fa4c52..246daadbfde8 100644 --- a/include/linux/memfd.h +++ b/include/linux/memfd.h @@ -6,11 +6,29 @@ #ifdef CONFIG_MEMFD_CREATE extern long memfd_fcntl(struct file *file, unsigned int cmd, unsigned int arg); +struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx); +/* + * Check for any existing seals on mmap, return an error if access is denied due + * to sealing, or 0 otherwise. + * + * We also update VMA flags if appropriate by manipulating the VMA flags pointed + * to by vm_flags_ptr. + */ +int memfd_check_seals_mmap(struct file *file, unsigned long *vm_flags_ptr); #else static inline long memfd_fcntl(struct file *f, unsigned int c, unsigned int a) { return -EINVAL; } +static inline struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx) +{ + return ERR_PTR(-EINVAL); +} +static inline int memfd_check_seals_mmap(struct file *file, + unsigned long *vm_flags_ptr) +{ + return 0; +} #endif #endif /* __LINUX_MEMFD_H */ diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h index 69e781900082..0dc0cf2863e2 100644 --- a/include/linux/memory-tiers.h +++ b/include/linux/memory-tiers.h @@ -38,6 +38,7 @@ struct access_coordinate; #ifdef CONFIG_NUMA extern bool numa_demotion_enabled; extern struct memory_dev_type *default_dram_type; +extern nodemask_t default_dram_nodes; struct memory_dev_type *alloc_memory_type(int adistance); void put_memory_type(struct memory_dev_type *memtype); void init_node_memory_type(int node, struct memory_dev_type *default_type); @@ -48,6 +49,9 @@ int mt_calc_adistance(int node, int *adist); int mt_set_default_dram_perf(int nid, struct access_coordinate *perf, const char *source); int mt_perf_to_adistance(struct access_coordinate *perf, int *adist); +struct memory_dev_type *mt_find_alloc_memory_type(int adist, + struct list_head *memory_types); +void mt_put_memory_types(struct list_head *memory_types); #ifdef CONFIG_MIGRATION int next_demotion_node(int node); void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets); @@ -73,6 +77,7 @@ static inline bool node_is_toptier(int node) #define numa_demotion_enabled false #define default_dram_type NULL +#define default_dram_nodes NODE_MASK_NONE /* * CONFIG_NUMA implementation returns non NULL error. */ @@ -136,5 +141,15 @@ static inline int mt_perf_to_adistance(struct access_coordinate *perf, int *adis { return -EIO; } + +static inline struct memory_dev_type *mt_find_alloc_memory_type(int adist, + struct list_head *memory_types) +{ + return NULL; +} + +static inline void mt_put_memory_types(struct list_head *memory_types) +{ +} #endif /* CONFIG_NUMA */ #endif /* _LINUX_MEMORY_TIERS_H */ diff --git a/include/linux/memory/ti-aemif.h b/include/linux/memory/ti-aemif.h new file mode 100644 index 000000000000..da94a9d985e7 --- /dev/null +++ b/include/linux/memory/ti-aemif.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __MEMORY_TI_AEMIF_H +#define __MEMORY_TI_AEMIF_H + +/** + * struct aemif_cs_timings: structure to hold CS timing configuration + * values are expressed in number of clock cycles - 1 + * @ta: minimum turn around time + * @rhold: read hold width + * @rstrobe: read strobe width + * @rsetup: read setup width + * @whold: write hold width + * @wstrobe: write strobe width + * @wsetup: write setup width + */ +struct aemif_cs_timings { + u32 ta; + u32 rhold; + u32 rstrobe; + u32 rsetup; + u32 whold; + u32 wstrobe; + u32 wsetup; +}; + +struct aemif_device; + +int aemif_set_cs_timings(struct aemif_device *aemif, u8 cs, struct aemif_cs_timings *timings); +int aemif_check_cs_timings(struct aemif_cs_timings *timings); + +#endif // __MEMORY_TI_AEMIF_H diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 7a9ff464608d..eaac5ae8c05c 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -16,54 +16,6 @@ struct resource; struct vmem_altmap; struct dev_pagemap; -#ifdef CONFIG_HAVE_ARCH_NODEDATA_EXTENSION -/* - * For supporting node-hotadd, we have to allocate a new pgdat. - * - * If an arch has generic style NODE_DATA(), - * node_data[nid] = kzalloc() works well. But it depends on the architecture. - * - * In general, generic_alloc_nodedata() is used. - * - */ -extern pg_data_t *arch_alloc_nodedata(int nid); -extern void arch_refresh_nodedata(int nid, pg_data_t *pgdat); - -#else /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */ - -#define arch_alloc_nodedata(nid) generic_alloc_nodedata(nid) - -#ifdef CONFIG_NUMA -/* - * XXX: node aware allocation can't work well to get new node's memory at this time. - * Because, pgdat for the new node is not allocated/initialized yet itself. - * To use new node's memory, more consideration will be necessary. - */ -#define generic_alloc_nodedata(nid) \ -({ \ - memblock_alloc(sizeof(*pgdat), SMP_CACHE_BYTES); \ -}) - -extern pg_data_t *node_data[]; -static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat) -{ - node_data[nid] = pgdat; -} - -#else /* !CONFIG_NUMA */ - -/* never called */ -static inline pg_data_t *generic_alloc_nodedata(int nid) -{ - BUG(); - return NULL; -} -static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat) -{ -} -#endif /* CONFIG_NUMA */ -#endif /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */ - #ifdef CONFIG_MEMORY_HOTPLUG struct page *pfn_to_online_page(unsigned long pfn); @@ -175,8 +127,8 @@ extern int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages, extern void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long nr_pages); extern int online_pages(unsigned long pfn, unsigned long nr_pages, struct zone *zone, struct memory_group *group); -extern void __offline_isolated_pages(unsigned long start_pfn, - unsigned long end_pfn); +extern unsigned long __offline_isolated_pages(unsigned long start_pfn, + unsigned long end_pfn); typedef void (*online_page_callback_t)(struct page *page, unsigned int order); @@ -192,8 +144,6 @@ extern u64 max_mem_size; extern int mhp_online_type_from_str(const char *str); -/* Default online_type (MMOP_*) when new memory blocks are added. */ -extern int mhp_default_online_type; /* If movable_node boot option specified */ extern bool movable_node_enabled; static inline bool movable_node_is_enabled(void) @@ -351,6 +301,9 @@ static inline void __remove_memory(u64 start, u64 size) {} #endif /* CONFIG_MEMORY_HOTREMOVE */ #ifdef CONFIG_MEMORY_HOTPLUG +/* Default online_type (MMOP_*) when new memory blocks are added. */ +extern int mhp_get_default_online_type(void); +extern void mhp_set_default_online_type(int online_type); extern void __ref free_area_init_core_hotplug(struct pglist_data *pgdat); extern int __add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags); extern int add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags); diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 931b118336f4..ce9885e0178a 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -47,7 +47,7 @@ struct mempolicy { atomic_t refcnt; unsigned short mode; /* See MPOL_* above */ unsigned short flags; /* See set_mempolicy() MPOL_F_* above */ - nodemask_t nodes; /* interleave/bind/perfer */ + nodemask_t nodes; /* interleave/bind/preferred/etc */ int home_node; /* Home node to use for MPOL_BIND and MPOL_PREFERRED_MANY */ union { @@ -167,7 +167,8 @@ extern void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol); /* Check if a vma is migratable */ extern bool vma_migratable(struct vm_area_struct *vma); -int mpol_misplaced(struct folio *, struct vm_area_struct *, unsigned long); +int mpol_misplaced(struct folio *folio, struct vm_fault *vmf, + unsigned long addr); extern void mpol_put_task_policy(struct task_struct *); static inline bool mpol_is_preferred_many(struct mempolicy *pol) @@ -282,7 +283,7 @@ static inline int mpol_parse_str(char *str, struct mempolicy **mpol) #endif static inline int mpol_misplaced(struct folio *folio, - struct vm_area_struct *vma, + struct vm_fault *vmf, unsigned long address) { return -1; /* no node preference */ diff --git a/include/linux/mempool.h b/include/linux/mempool.h index 16c5cc807ff6..7b151441341b 100644 --- a/include/linux/mempool.h +++ b/include/linux/mempool.h @@ -5,6 +5,8 @@ #ifndef _LINUX_MEMPOOL_H #define _LINUX_MEMPOOL_H +#include <linux/sched.h> +#include <linux/alloc_tag.h> #include <linux/wait.h> #include <linux/compiler.h> @@ -39,18 +41,32 @@ void mempool_exit(mempool_t *pool); int mempool_init_node(mempool_t *pool, int min_nr, mempool_alloc_t *alloc_fn, mempool_free_t *free_fn, void *pool_data, gfp_t gfp_mask, int node_id); -int mempool_init(mempool_t *pool, int min_nr, mempool_alloc_t *alloc_fn, + +int mempool_init_noprof(mempool_t *pool, int min_nr, mempool_alloc_t *alloc_fn, mempool_free_t *free_fn, void *pool_data); +#define mempool_init(...) \ + alloc_hooks(mempool_init_noprof(__VA_ARGS__)) extern mempool_t *mempool_create(int min_nr, mempool_alloc_t *alloc_fn, mempool_free_t *free_fn, void *pool_data); -extern mempool_t *mempool_create_node(int min_nr, mempool_alloc_t *alloc_fn, + +extern mempool_t *mempool_create_node_noprof(int min_nr, mempool_alloc_t *alloc_fn, mempool_free_t *free_fn, void *pool_data, gfp_t gfp_mask, int nid); +#define mempool_create_node(...) \ + alloc_hooks(mempool_create_node_noprof(__VA_ARGS__)) + +#define mempool_create(_min_nr, _alloc_fn, _free_fn, _pool_data) \ + mempool_create_node(_min_nr, _alloc_fn, _free_fn, _pool_data, \ + GFP_KERNEL, NUMA_NO_NODE) extern int mempool_resize(mempool_t *pool, int new_min_nr); extern void mempool_destroy(mempool_t *pool); -extern void *mempool_alloc(mempool_t *pool, gfp_t gfp_mask) __malloc; + +extern void *mempool_alloc_noprof(mempool_t *pool, gfp_t gfp_mask) __malloc; +#define mempool_alloc(...) \ + alloc_hooks(mempool_alloc_noprof(__VA_ARGS__)) + extern void *mempool_alloc_preallocated(mempool_t *pool) __malloc; extern void mempool_free(void *element, mempool_t *pool); @@ -62,19 +78,10 @@ extern void mempool_free(void *element, mempool_t *pool); void *mempool_alloc_slab(gfp_t gfp_mask, void *pool_data); void mempool_free_slab(void *element, void *pool_data); -static inline int -mempool_init_slab_pool(mempool_t *pool, int min_nr, struct kmem_cache *kc) -{ - return mempool_init(pool, min_nr, mempool_alloc_slab, - mempool_free_slab, (void *) kc); -} - -static inline mempool_t * -mempool_create_slab_pool(int min_nr, struct kmem_cache *kc) -{ - return mempool_create(min_nr, mempool_alloc_slab, mempool_free_slab, - (void *) kc); -} +#define mempool_init_slab_pool(_pool, _min_nr, _kc) \ + mempool_init(_pool, (_min_nr), mempool_alloc_slab, mempool_free_slab, (void *)(_kc)) +#define mempool_create_slab_pool(_min_nr, _kc) \ + mempool_create((_min_nr), mempool_alloc_slab, mempool_free_slab, (void *)(_kc)) /* * a mempool_alloc_t and a mempool_free_t to kmalloc and kfree the @@ -83,17 +90,12 @@ mempool_create_slab_pool(int min_nr, struct kmem_cache *kc) void *mempool_kmalloc(gfp_t gfp_mask, void *pool_data); void mempool_kfree(void *element, void *pool_data); -static inline int mempool_init_kmalloc_pool(mempool_t *pool, int min_nr, size_t size) -{ - return mempool_init(pool, min_nr, mempool_kmalloc, - mempool_kfree, (void *) size); -} - -static inline mempool_t *mempool_create_kmalloc_pool(int min_nr, size_t size) -{ - return mempool_create(min_nr, mempool_kmalloc, mempool_kfree, - (void *) size); -} +#define mempool_init_kmalloc_pool(_pool, _min_nr, _size) \ + mempool_init(_pool, (_min_nr), mempool_kmalloc, mempool_kfree, \ + (void *)(unsigned long)(_size)) +#define mempool_create_kmalloc_pool(_min_nr, _size) \ + mempool_create((_min_nr), mempool_kmalloc, mempool_kfree, \ + (void *)(unsigned long)(_size)) void *mempool_kvmalloc(gfp_t gfp_mask, void *pool_data); void mempool_kvfree(void *element, void *pool_data); @@ -115,16 +117,11 @@ static inline mempool_t *mempool_create_kvmalloc_pool(int min_nr, size_t size) void *mempool_alloc_pages(gfp_t gfp_mask, void *pool_data); void mempool_free_pages(void *element, void *pool_data); -static inline int mempool_init_page_pool(mempool_t *pool, int min_nr, int order) -{ - return mempool_init(pool, min_nr, mempool_alloc_pages, - mempool_free_pages, (void *)(long)order); -} - -static inline mempool_t *mempool_create_page_pool(int min_nr, int order) -{ - return mempool_create(min_nr, mempool_alloc_pages, mempool_free_pages, - (void *)(long)order); -} +#define mempool_init_page_pool(_pool, _min_nr, _order) \ + mempool_init(_pool, (_min_nr), mempool_alloc_pages, \ + mempool_free_pages, (void *)(long)(_order)) +#define mempool_create_page_pool(_min_nr, _order) \ + mempool_create((_min_nr), mempool_alloc_pages, \ + mempool_free_pages, (void *)(long)(_order)) #endif /* _LINUX_MEMPOOL_H */ diff --git a/include/linux/memstick.h b/include/linux/memstick.h index ebf73d4ee969..107bdcbedf79 100644 --- a/include/linux/memstick.h +++ b/include/linux/memstick.h @@ -293,7 +293,7 @@ struct memstick_host { }; struct memstick_driver { - struct memstick_device_id *id_table; + const struct memstick_device_id *id_table; int (*probe)(struct memstick_dev *card); void (*remove)(struct memstick_dev *card); int (*suspend)(struct memstick_dev *card, diff --git a/include/linux/mfd/88pm80x.h b/include/linux/mfd/88pm80x.h index def5df6e74bf..551ef1c367d6 100644 --- a/include/linux/mfd/88pm80x.h +++ b/include/linux/mfd/88pm80x.h @@ -294,7 +294,7 @@ struct pm80x_chip { struct i2c_client *client; struct i2c_client *companion; struct regmap *regmap; - struct regmap_irq_chip *regmap_irq_chip; + const struct regmap_irq_chip *regmap_irq_chip; struct regmap_irq_chip_data *irq_data; int type; int irq; diff --git a/include/linux/mfd/88pm886.h b/include/linux/mfd/88pm886.h new file mode 100644 index 000000000000..85eca44f39ab --- /dev/null +++ b/include/linux/mfd/88pm886.h @@ -0,0 +1,78 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef __MFD_88PM886_H +#define __MFD_88PM886_H + +#include <linux/i2c.h> +#include <linux/regmap.h> + +#define PM886_A1_CHIP_ID 0xa1 + +#define PM886_IRQ_ONKEY 0 + +#define PM886_PAGE_OFFSET_REGULATORS 1 + +#define PM886_REG_ID 0x00 + +#define PM886_REG_STATUS1 0x01 +#define PM886_ONKEY_STS1 BIT(0) + +#define PM886_REG_INT_STATUS1 0x05 + +#define PM886_REG_INT_ENA_1 0x0a +#define PM886_INT_ENA1_ONKEY BIT(0) + +#define PM886_REG_MISC_CONFIG1 0x14 +#define PM886_SW_PDOWN BIT(5) + +#define PM886_REG_MISC_CONFIG2 0x15 +#define PM886_INT_INV BIT(0) +#define PM886_INT_CLEAR BIT(1) +#define PM886_INT_RC 0x00 +#define PM886_INT_WC BIT(1) +#define PM886_INT_MASK_MODE BIT(2) + +#define PM886_REG_RTC_CNT1 0xd1 +#define PM886_REG_RTC_CNT2 0xd2 +#define PM886_REG_RTC_CNT3 0xd3 +#define PM886_REG_RTC_CNT4 0xd4 +#define PM886_REG_RTC_SPARE1 0xea +#define PM886_REG_RTC_SPARE2 0xeb +#define PM886_REG_RTC_SPARE3 0xec +#define PM886_REG_RTC_SPARE4 0xed +#define PM886_REG_RTC_SPARE5 0xee +#define PM886_REG_RTC_SPARE6 0xef + +#define PM886_REG_BUCK_EN 0x08 +#define PM886_REG_LDO_EN1 0x09 +#define PM886_REG_LDO_EN2 0x0a +#define PM886_REG_LDO1_VOUT 0x20 +#define PM886_REG_LDO2_VOUT 0x26 +#define PM886_REG_LDO3_VOUT 0x2c +#define PM886_REG_LDO4_VOUT 0x32 +#define PM886_REG_LDO5_VOUT 0x38 +#define PM886_REG_LDO6_VOUT 0x3e +#define PM886_REG_LDO7_VOUT 0x44 +#define PM886_REG_LDO8_VOUT 0x4a +#define PM886_REG_LDO9_VOUT 0x50 +#define PM886_REG_LDO10_VOUT 0x56 +#define PM886_REG_LDO11_VOUT 0x5c +#define PM886_REG_LDO12_VOUT 0x62 +#define PM886_REG_LDO13_VOUT 0x68 +#define PM886_REG_LDO14_VOUT 0x6e +#define PM886_REG_LDO15_VOUT 0x74 +#define PM886_REG_LDO16_VOUT 0x7a +#define PM886_REG_BUCK1_VOUT 0xa5 +#define PM886_REG_BUCK2_VOUT 0xb3 +#define PM886_REG_BUCK3_VOUT 0xc1 +#define PM886_REG_BUCK4_VOUT 0xcf +#define PM886_REG_BUCK5_VOUT 0xdd + +#define PM886_LDO_VSEL_MASK 0x0f +#define PM886_BUCK_VSEL_MASK 0x7f + +struct pm886_chip { + struct i2c_client *client; + unsigned int chip_id; + struct regmap *regmap; +}; +#endif /* __MFD_88PM886_H */ diff --git a/include/linux/mfd/adp5585.h b/include/linux/mfd/adp5585.h new file mode 100644 index 000000000000..016033cd68e4 --- /dev/null +++ b/include/linux/mfd/adp5585.h @@ -0,0 +1,126 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Analog Devices ADP5585 I/O expander, PWM controller and keypad controller + * + * Copyright 2022 NXP + * Copyright 2024 Ideas on Board Oy + */ + +#ifndef __MFD_ADP5585_H_ +#define __MFD_ADP5585_H_ + +#include <linux/bits.h> + +#define ADP5585_ID 0x00 +#define ADP5585_MAN_ID_VALUE 0x20 +#define ADP5585_MAN_ID_MASK GENMASK(7, 4) +#define ADP5585_INT_STATUS 0x01 +#define ADP5585_STATUS 0x02 +#define ADP5585_FIFO_1 0x03 +#define ADP5585_FIFO_2 0x04 +#define ADP5585_FIFO_3 0x05 +#define ADP5585_FIFO_4 0x06 +#define ADP5585_FIFO_5 0x07 +#define ADP5585_FIFO_6 0x08 +#define ADP5585_FIFO_7 0x09 +#define ADP5585_FIFO_8 0x0a +#define ADP5585_FIFO_9 0x0b +#define ADP5585_FIFO_10 0x0c +#define ADP5585_FIFO_11 0x0d +#define ADP5585_FIFO_12 0x0e +#define ADP5585_FIFO_13 0x0f +#define ADP5585_FIFO_14 0x10 +#define ADP5585_FIFO_15 0x11 +#define ADP5585_FIFO_16 0x12 +#define ADP5585_GPI_INT_STAT_A 0x13 +#define ADP5585_GPI_INT_STAT_B 0x14 +#define ADP5585_GPI_STATUS_A 0x15 +#define ADP5585_GPI_STATUS_B 0x16 +#define ADP5585_RPULL_CONFIG_A 0x17 +#define ADP5585_RPULL_CONFIG_B 0x18 +#define ADP5585_RPULL_CONFIG_C 0x19 +#define ADP5585_RPULL_CONFIG_D 0x1a +#define ADP5585_Rx_PULL_CFG_PU_300K 0 +#define ADP5585_Rx_PULL_CFG_PD_300K 1 +#define ADP5585_Rx_PULL_CFG_PU_100K 2 +#define ADP5585_Rx_PULL_CFG_DISABLE 3 +#define ADP5585_Rx_PULL_CFG_MASK 3 +#define ADP5585_GPI_INT_LEVEL_A 0x1b +#define ADP5585_GPI_INT_LEVEL_B 0x1c +#define ADP5585_GPI_EVENT_EN_A 0x1d +#define ADP5585_GPI_EVENT_EN_B 0x1e +#define ADP5585_GPI_INTERRUPT_EN_A 0x1f +#define ADP5585_GPI_INTERRUPT_EN_B 0x20 +#define ADP5585_DEBOUNCE_DIS_A 0x21 +#define ADP5585_DEBOUNCE_DIS_B 0x22 +#define ADP5585_GPO_DATA_OUT_A 0x23 +#define ADP5585_GPO_DATA_OUT_B 0x24 +#define ADP5585_GPO_OUT_MODE_A 0x25 +#define ADP5585_GPO_OUT_MODE_B 0x26 +#define ADP5585_GPIO_DIRECTION_A 0x27 +#define ADP5585_GPIO_DIRECTION_B 0x28 +#define ADP5585_RESET1_EVENT_A 0x29 +#define ADP5585_RESET1_EVENT_B 0x2a +#define ADP5585_RESET1_EVENT_C 0x2b +#define ADP5585_RESET2_EVENT_A 0x2c +#define ADP5585_RESET2_EVENT_B 0x2d +#define ADP5585_RESET_CFG 0x2e +#define ADP5585_PWM_OFFT_LOW 0x2f +#define ADP5585_PWM_OFFT_HIGH 0x30 +#define ADP5585_PWM_ONT_LOW 0x31 +#define ADP5585_PWM_ONT_HIGH 0x32 +#define ADP5585_PWM_CFG 0x33 +#define ADP5585_PWM_IN_AND BIT(2) +#define ADP5585_PWM_MODE BIT(1) +#define ADP5585_PWM_EN BIT(0) +#define ADP5585_LOGIC_CFG 0x34 +#define ADP5585_LOGIC_FF_CFG 0x35 +#define ADP5585_LOGIC_INT_EVENT_EN 0x36 +#define ADP5585_POLL_PTIME_CFG 0x37 +#define ADP5585_PIN_CONFIG_A 0x38 +#define ADP5585_PIN_CONFIG_B 0x39 +#define ADP5585_PIN_CONFIG_C 0x3a +#define ADP5585_PULL_SELECT BIT(7) +#define ADP5585_C4_EXTEND_CFG_GPIO11 (0U << 6) +#define ADP5585_C4_EXTEND_CFG_RESET2 (1U << 6) +#define ADP5585_C4_EXTEND_CFG_MASK GENMASK(6, 6) +#define ADP5585_R4_EXTEND_CFG_GPIO5 (0U << 5) +#define ADP5585_R4_EXTEND_CFG_RESET1 (1U << 5) +#define ADP5585_R4_EXTEND_CFG_MASK GENMASK(5, 5) +#define ADP5585_R3_EXTEND_CFG_GPIO4 (0U << 2) +#define ADP5585_R3_EXTEND_CFG_LC (1U << 2) +#define ADP5585_R3_EXTEND_CFG_PWM_OUT (2U << 2) +#define ADP5585_R3_EXTEND_CFG_MASK GENMASK(3, 2) +#define ADP5585_R0_EXTEND_CFG_GPIO1 (0U << 0) +#define ADP5585_R0_EXTEND_CFG_LY (1U << 0) +#define ADP5585_R0_EXTEND_CFG_MASK GENMASK(0, 0) +#define ADP5585_GENERAL_CFG 0x3b +#define ADP5585_OSC_EN BIT(7) +#define ADP5585_OSC_FREQ_50KHZ (0U << 5) +#define ADP5585_OSC_FREQ_100KHZ (1U << 5) +#define ADP5585_OSC_FREQ_200KHZ (2U << 5) +#define ADP5585_OSC_FREQ_500KHZ (3U << 5) +#define ADP5585_OSC_FREQ_MASK GENMASK(6, 5) +#define ADP5585_INT_CFG BIT(1) +#define ADP5585_RST_CFG BIT(0) +#define ADP5585_INT_EN 0x3c + +#define ADP5585_MAX_REG ADP5585_INT_EN + +/* + * Bank 0 covers pins "GPIO 1/R0" to "GPIO 6/R5", numbered 0 to 5 by the + * driver, and bank 1 covers pins "GPIO 7/C0" to "GPIO 11/C4", numbered 6 to + * 10. Some variants of the ADP5585 don't support "GPIO 6/R5". As the driver + * uses identical GPIO numbering for all variants to avoid confusion, GPIO 5 is + * marked as reserved in the device tree for variants that don't support it. + */ +#define ADP5585_BANK(n) ((n) >= 6 ? 1 : 0) +#define ADP5585_BIT(n) ((n) >= 6 ? BIT((n) - 6) : BIT(n)) + +struct regmap; + +struct adp5585_dev { + struct regmap *regmap; +}; + +#endif diff --git a/include/linux/mfd/atmel-hlcdc.h b/include/linux/mfd/atmel-hlcdc.h index a186119a49b5..80d675a03b39 100644 --- a/include/linux/mfd/atmel-hlcdc.h +++ b/include/linux/mfd/atmel-hlcdc.h @@ -22,6 +22,8 @@ #define ATMEL_HLCDC_DITHER BIT(6) #define ATMEL_HLCDC_DISPDLY BIT(7) #define ATMEL_HLCDC_MODE_MASK GENMASK(9, 8) +#define ATMEL_XLCDC_MODE_MASK GENMASK(10, 8) +#define ATMEL_XLCDC_DPI BIT(11) #define ATMEL_HLCDC_PP BIT(10) #define ATMEL_HLCDC_VSPSU BIT(12) #define ATMEL_HLCDC_VSPHO BIT(13) @@ -34,6 +36,12 @@ #define ATMEL_HLCDC_IDR 0x30 #define ATMEL_HLCDC_IMR 0x34 #define ATMEL_HLCDC_ISR 0x38 +#define ATMEL_XLCDC_ATTRE 0x3c + +#define ATMEL_XLCDC_BASE_UPDATE BIT(0) +#define ATMEL_XLCDC_OVR1_UPDATE BIT(1) +#define ATMEL_XLCDC_OVR3_UPDATE BIT(2) +#define ATMEL_XLCDC_HEO_UPDATE BIT(3) #define ATMEL_HLCDC_CLKPOL BIT(0) #define ATMEL_HLCDC_CLKSEL BIT(2) @@ -48,6 +56,8 @@ #define ATMEL_HLCDC_DISP BIT(2) #define ATMEL_HLCDC_PWM BIT(3) #define ATMEL_HLCDC_SIP BIT(4) +#define ATMEL_XLCDC_SD BIT(5) +#define ATMEL_XLCDC_CM BIT(6) #define ATMEL_HLCDC_SOF BIT(0) #define ATMEL_HLCDC_SYNCDIS BIT(1) diff --git a/include/linux/mfd/axp20x.h b/include/linux/mfd/axp20x.h index f1755163dd9f..c3df0e615fbf 100644 --- a/include/linux/mfd/axp20x.h +++ b/include/linux/mfd/axp20x.h @@ -19,6 +19,8 @@ enum axp20x_variants { AXP223_ID, AXP288_ID, AXP313A_ID, + AXP323_ID, + AXP717_ID, AXP803_ID, AXP806_ID, AXP809_ID, @@ -104,14 +106,73 @@ enum axp20x_variants { #define AXP313A_ON_INDICATE 0x00 #define AXP313A_OUTPUT_CONTROL 0x10 -#define AXP313A_DCDC1_CONRTOL 0x13 -#define AXP313A_DCDC2_CONRTOL 0x14 -#define AXP313A_DCDC3_CONRTOL 0x15 -#define AXP313A_ALDO1_CONRTOL 0x16 -#define AXP313A_DLDO1_CONRTOL 0x17 +#define AXP313A_DCDC1_CONTROL 0x13 +#define AXP313A_DCDC2_CONTROL 0x14 +#define AXP313A_DCDC3_CONTROL 0x15 +#define AXP313A_ALDO1_CONTROL 0x16 +#define AXP313A_DLDO1_CONTROL 0x17 #define AXP313A_SHUTDOWN_CTRL 0x1a #define AXP313A_IRQ_EN 0x20 #define AXP313A_IRQ_STATE 0x21 +#define AXP323_DCDC_MODE_CTRL2 0x22 + +#define AXP717_ON_INDICATE 0x00 +#define AXP717_PMU_STATUS_2 0x01 +#define AXP717_BC_DETECT 0x05 +#define AXP717_PMU_FAULT 0x08 +#define AXP717_MODULE_EN_CONTROL_1 0x0b +#define AXP717_MIN_SYS_V_CONTROL 0x15 +#define AXP717_INPUT_VOL_LIMIT_CTRL 0x16 +#define AXP717_INPUT_CUR_LIMIT_CTRL 0x17 +#define AXP717_MODULE_EN_CONTROL_2 0x19 +#define AXP717_BOOST_CONTROL 0x1e +#define AXP717_VSYS_V_POWEROFF 0x24 +#define AXP717_IRQ0_EN 0x40 +#define AXP717_IRQ1_EN 0x41 +#define AXP717_IRQ2_EN 0x42 +#define AXP717_IRQ3_EN 0x43 +#define AXP717_IRQ4_EN 0x44 +#define AXP717_IRQ0_STATE 0x48 +#define AXP717_IRQ1_STATE 0x49 +#define AXP717_IRQ2_STATE 0x4a +#define AXP717_IRQ3_STATE 0x4b +#define AXP717_IRQ4_STATE 0x4c +#define AXP717_ICC_CHG_SET 0x62 +#define AXP717_ITERM_CHG_SET 0x63 +#define AXP717_CV_CHG_SET 0x64 +#define AXP717_DCDC_OUTPUT_CONTROL 0x80 +#define AXP717_DCDC1_CONTROL 0x83 +#define AXP717_DCDC2_CONTROL 0x84 +#define AXP717_DCDC3_CONTROL 0x85 +#define AXP717_DCDC4_CONTROL 0x86 +#define AXP717_LDO0_OUTPUT_CONTROL 0x90 +#define AXP717_LDO1_OUTPUT_CONTROL 0x91 +#define AXP717_ALDO1_CONTROL 0x93 +#define AXP717_ALDO2_CONTROL 0x94 +#define AXP717_ALDO3_CONTROL 0x95 +#define AXP717_ALDO4_CONTROL 0x96 +#define AXP717_BLDO1_CONTROL 0x97 +#define AXP717_BLDO2_CONTROL 0x98 +#define AXP717_BLDO3_CONTROL 0x99 +#define AXP717_BLDO4_CONTROL 0x9a +#define AXP717_CLDO1_CONTROL 0x9b +#define AXP717_CLDO2_CONTROL 0x9c +#define AXP717_CLDO3_CONTROL 0x9d +#define AXP717_CLDO4_CONTROL 0x9e +#define AXP717_CPUSLDO_CONTROL 0x9f +#define AXP717_BATT_PERCENT_DATA 0xa4 +#define AXP717_ADC_CH_EN_CONTROL 0xc0 +#define AXP717_BATT_V_H 0xc4 +#define AXP717_BATT_V_L 0xc5 +#define AXP717_VBUS_V_H 0xc6 +#define AXP717_VBUS_V_L 0xc7 +#define AXP717_VSYS_V_H 0xc8 +#define AXP717_VSYS_V_L 0xc9 +#define AXP717_BATT_CHRG_I_H 0xca +#define AXP717_BATT_CHRG_I_L 0xcb +#define AXP717_ADC_DATA_SEL 0xcd +#define AXP717_ADC_DATA_H 0xce +#define AXP717_ADC_DATA_L 0xcf #define AXP806_STARTUP_SRC 0x00 #define AXP806_CHIP_ID 0x03 @@ -434,6 +495,28 @@ enum { }; enum { + AXP717_DCDC1 = 0, + AXP717_DCDC2, + AXP717_DCDC3, + AXP717_DCDC4, + AXP717_ALDO1, + AXP717_ALDO2, + AXP717_ALDO3, + AXP717_ALDO4, + AXP717_BLDO1, + AXP717_BLDO2, + AXP717_BLDO3, + AXP717_BLDO4, + AXP717_CLDO1, + AXP717_CLDO2, + AXP717_CLDO3, + AXP717_CLDO4, + AXP717_CPUSLDO, + AXP717_BOOST, + AXP717_REG_ID_MAX, +}; + +enum { AXP806_DCDCA = 0, AXP806_DCDCB, AXP806_DCDCC, @@ -732,6 +815,40 @@ enum axp313a_irqs { AXP313A_IRQ_PEK_RIS_EDGE, }; +enum axp717_irqs { + AXP717_IRQ_VBUS_FAULT, + AXP717_IRQ_VBUS_OVER_V, + AXP717_IRQ_BOOST_OVER_V, + AXP717_IRQ_GAUGE_NEW_SOC = 4, + AXP717_IRQ_SOC_DROP_LVL1 = 6, + AXP717_IRQ_SOC_DROP_LVL2, + AXP717_IRQ_PEK_RIS_EDGE, + AXP717_IRQ_PEK_FAL_EDGE, + AXP717_IRQ_PEK_LONG, + AXP717_IRQ_PEK_SHORT, + AXP717_IRQ_BATT_REMOVAL, + AXP717_IRQ_BATT_PLUGIN, + AXP717_IRQ_VBUS_REMOVAL, + AXP717_IRQ_VBUS_PLUGIN, + AXP717_IRQ_BATT_OVER_V, + AXP717_IRQ_CHARG_TIMER, + AXP717_IRQ_DIE_TEMP_HIGH, + AXP717_IRQ_CHARG, + AXP717_IRQ_CHARG_DONE, + AXP717_IRQ_BATT_OVER_CURR, + AXP717_IRQ_LDO_OVER_CURR, + AXP717_IRQ_WDOG_EXPIRE, + AXP717_IRQ_BATT_ACT_TEMP_LOW, + AXP717_IRQ_BATT_ACT_TEMP_HIGH, + AXP717_IRQ_BATT_CHG_TEMP_LOW, + AXP717_IRQ_BATT_CHG_TEMP_HIGH, + AXP717_IRQ_BATT_QUIT_TEMP_HIGH, + AXP717_IRQ_BC_USB_CHNG = 30, + AXP717_IRQ_BC_USB_DONE, + AXP717_IRQ_TYPEC_PLUGIN = 37, + AXP717_IRQ_TYPEC_REMOVE, +}; + enum axp803_irqs { AXP803_IRQ_ACIN_OVER_V = 1, AXP803_IRQ_ACIN_PLUGIN, @@ -844,7 +961,7 @@ struct axp20x_dev { unsigned long irq_flags; struct regmap *regmap; struct regmap_irq_chip_data *regmap_irqc; - long variant; + enum axp20x_variants variant; int nr_cells; const struct mfd_cell *cells; const struct regmap_config *regmap_cfg; diff --git a/include/linux/mfd/cgbc.h b/include/linux/mfd/cgbc.h new file mode 100644 index 000000000000..badbec4c7033 --- /dev/null +++ b/include/linux/mfd/cgbc.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Congatec Board Controller driver definitions + * + * Copyright (C) 2024 Bootlin + * Author: Thomas Richard <thomas.richard@bootlin.com> + */ + +#ifndef _LINUX_MFD_CGBC_H_ + +/** + * struct cgbc_version - Board Controller device version structure + * @feature: Board Controller feature number + * @major: Board Controller major revision + * @minor: Board Controller minor revision + */ +struct cgbc_version { + unsigned char feature; + unsigned char major; + unsigned char minor; +}; + +/** + * struct cgbc_device_data - Internal representation of the Board Controller device + * @io_session: Pointer to the session IO memory + * @io_cmd: Pointer to the command IO memory + * @session: Session id returned by the Board Controller + * @dev: Pointer to kernel device structure + * @cgbc_version: Board Controller version structure + * @mutex: Board Controller mutex + */ +struct cgbc_device_data { + void __iomem *io_session; + void __iomem *io_cmd; + u8 session; + struct device *dev; + struct cgbc_version version; + struct mutex lock; +}; + +int cgbc_command(struct cgbc_device_data *cgbc, void *cmd, unsigned int cmd_size, + void *data, unsigned int data_size, u8 *status); + +#endif /*_LINUX_MFD_CGBC_H_*/ diff --git a/include/linux/mfd/core.h b/include/linux/mfd/core.h index e8bcad641d8c..faeea7abd688 100644 --- a/include/linux/mfd/core.h +++ b/include/linux/mfd/core.h @@ -72,7 +72,7 @@ struct mfd_cell { int (*resume)(struct platform_device *dev); /* platform data passed to the sub devices drivers */ - void *platform_data; + const void *platform_data; size_t pdata_size; /* Matches ACPI */ diff --git a/include/linux/mfd/cs40l50.h b/include/linux/mfd/cs40l50.h new file mode 100644 index 000000000000..e5dc49860944 --- /dev/null +++ b/include/linux/mfd/cs40l50.h @@ -0,0 +1,137 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * CS40L50 Advanced Haptic Driver with waveform memory, + * integrated DSP, and closed-loop algorithms + * + * Copyright 2024 Cirrus Logic, Inc. + * + * Author: James Ogletree <james.ogletree@cirrus.com> + */ + +#ifndef __MFD_CS40L50_H__ +#define __MFD_CS40L50_H__ + +#include <linux/firmware/cirrus/cs_dsp.h> +#include <linux/gpio/consumer.h> +#include <linux/pm.h> +#include <linux/regmap.h> + +/* Power Supply Configuration */ +#define CS40L50_BLOCK_ENABLES2 0x201C +#define CS40L50_ERR_RLS 0x2034 +#define CS40L50_BST_LPMODE_SEL 0x3810 +#define CS40L50_DCM_LOW_POWER 0x1 +#define CS40L50_OVERTEMP_WARN 0x4000010 + +/* Interrupts */ +#define CS40L50_IRQ1_INT_1 0xE010 +#define CS40L50_IRQ1_BASE CS40L50_IRQ1_INT_1 +#define CS40L50_IRQ1_INT_2 0xE014 +#define CS40L50_IRQ1_INT_8 0xE02C +#define CS40L50_IRQ1_INT_9 0xE030 +#define CS40L50_IRQ1_INT_10 0xE034 +#define CS40L50_IRQ1_INT_18 0xE054 +#define CS40L50_IRQ1_MASK_1 0xE090 +#define CS40L50_IRQ1_MASK_2 0xE094 +#define CS40L50_IRQ1_MASK_20 0xE0DC +#define CS40L50_IRQ1_INT_1_OFFSET (CS40L50_IRQ1_INT_1 - CS40L50_IRQ1_BASE) +#define CS40L50_IRQ1_INT_2_OFFSET (CS40L50_IRQ1_INT_2 - CS40L50_IRQ1_BASE) +#define CS40L50_IRQ1_INT_8_OFFSET (CS40L50_IRQ1_INT_8 - CS40L50_IRQ1_BASE) +#define CS40L50_IRQ1_INT_9_OFFSET (CS40L50_IRQ1_INT_9 - CS40L50_IRQ1_BASE) +#define CS40L50_IRQ1_INT_10_OFFSET (CS40L50_IRQ1_INT_10 - CS40L50_IRQ1_BASE) +#define CS40L50_IRQ1_INT_18_OFFSET (CS40L50_IRQ1_INT_18 - CS40L50_IRQ1_BASE) +#define CS40L50_IRQ_MASK_2_OVERRIDE 0xFFDF7FFF +#define CS40L50_IRQ_MASK_20_OVERRIDE 0x15C01000 +#define CS40L50_AMP_SHORT_MASK BIT(31) +#define CS40L50_DSP_QUEUE_MASK BIT(21) +#define CS40L50_TEMP_ERR_MASK BIT(31) +#define CS40L50_BST_UVP_MASK BIT(6) +#define CS40L50_BST_SHORT_MASK BIT(7) +#define CS40L50_BST_ILIMIT_MASK BIT(18) +#define CS40L50_UVLO_VDDBATT_MASK BIT(16) +#define CS40L50_GLOBAL_ERROR_MASK BIT(15) + +enum cs40l50_irq_list { + CS40L50_DSP_QUEUE_IRQ, + CS40L50_GLOBAL_ERROR_IRQ, + CS40L50_UVLO_VDDBATT_IRQ, + CS40L50_BST_ILIMIT_IRQ, + CS40L50_BST_SHORT_IRQ, + CS40L50_BST_UVP_IRQ, + CS40L50_TEMP_ERR_IRQ, + CS40L50_AMP_SHORT_IRQ, +}; + +/* DSP */ +#define CS40L50_XMEM_PACKED_0 0x2000000 +#define CS40L50_XMEM_UNPACKED24_0 0x2800000 +#define CS40L50_SYS_INFO_ID 0x25E0000 +#define CS40L50_DSP_QUEUE_WT 0x28042C8 +#define CS40L50_DSP_QUEUE_RD 0x28042CC +#define CS40L50_NUM_WAVES 0x2805C18 +#define CS40L50_CORE_BASE 0x2B80000 +#define CS40L50_YMEM_PACKED_0 0x2C00000 +#define CS40L50_YMEM_UNPACKED24_0 0x3400000 +#define CS40L50_PMEM_0 0x3800000 +#define CS40L50_DSP_POLL_US 1000 +#define CS40L50_DSP_TIMEOUT_COUNT 100 +#define CS40L50_RESET_PULSE_US 2200 +#define CS40L50_CP_READY_US 3100 +#define CS40L50_AUTOSUSPEND_MS 2000 +#define CS40L50_PM_ALGO 0x9F206 +#define CS40L50_GLOBAL_ERR_RLS_SET BIT(11) +#define CS40L50_GLOBAL_ERR_RLS_CLEAR 0 + +enum cs40l50_wseqs { + CS40L50_PWR_ON, + CS40L50_STANDBY, + CS40L50_ACTIVE, + CS40L50_NUM_WSEQS, +}; + +/* DSP Queue */ +#define CS40L50_DSP_QUEUE_BASE 0x11004 +#define CS40L50_DSP_QUEUE_END 0x1101C +#define CS40L50_DSP_QUEUE 0x11020 +#define CS40L50_PREVENT_HIBER 0x2000003 +#define CS40L50_ALLOW_HIBER 0x2000004 +#define CS40L50_SHUTDOWN 0x2000005 +#define CS40L50_SYSTEM_RESET 0x2000007 +#define CS40L50_START_I2S 0x3000002 +#define CS40L50_OWT_PUSH 0x3000008 +#define CS40L50_STOP_PLAYBACK 0x5000000 +#define CS40L50_OWT_DELETE 0xD000000 + +/* Firmware files */ +#define CS40L50_FW "cs40l50.wmfw" +#define CS40L50_WT "cs40l50.bin" + +/* Device */ +#define CS40L50_DEVID 0x0 +#define CS40L50_REVID 0x4 +#define CS40L50_DEVID_A 0x40A50 +#define CS40L50_REVID_B0 0xB0 + +struct cs40l50 { + struct device *dev; + struct regmap *regmap; + struct mutex lock; + struct cs_dsp dsp; + struct gpio_desc *reset_gpio; + struct regmap_irq_chip_data *irq_data; + const struct firmware *fw; + const struct firmware *bin; + struct cs_dsp_wseq wseqs[CS40L50_NUM_WSEQS]; + int irq; + u32 devid; + u32 revid; +}; + +int cs40l50_dsp_write(struct device *dev, struct regmap *regmap, u32 val); +int cs40l50_probe(struct cs40l50 *cs40l50); +int cs40l50_remove(struct cs40l50 *cs40l50); + +extern const struct regmap_config cs40l50_regmap; +extern const struct dev_pm_ops cs40l50_pm_ops; + +#endif /* __MFD_CS40L50_H__ */ diff --git a/include/linux/mfd/da9052/da9052.h b/include/linux/mfd/da9052/da9052.h index 76feb3a7066d..9cb2fc2938ce 100644 --- a/include/linux/mfd/da9052/da9052.h +++ b/include/linux/mfd/da9052/da9052.h @@ -93,6 +93,8 @@ struct da9052 { int chip_irq; + int fault_log; + /* SOC I/O transfer related fixes for DA9052/53 */ int (*fix_io) (struct da9052 *da9052, unsigned char reg); }; diff --git a/include/linux/mfd/da9063/core.h b/include/linux/mfd/da9063/core.h index 8db52324f416..eae82f421414 100644 --- a/include/linux/mfd/da9063/core.h +++ b/include/linux/mfd/da9063/core.h @@ -78,6 +78,7 @@ struct da9063 { enum da9063_type type; unsigned char variant_code; unsigned int flags; + bool use_sw_pm; /* Control interface */ struct regmap *regmap; diff --git a/include/linux/mfd/ds1wm.h b/include/linux/mfd/ds1wm.h deleted file mode 100644 index 43dfca1c9702..000000000000 --- a/include/linux/mfd/ds1wm.h +++ /dev/null @@ -1,29 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* MFD cell driver data for the DS1WM driver - * - * to be defined in the MFD device that is - * using this driver for one of his sub devices - */ - -struct ds1wm_driver_data { - int active_high; - int clock_rate; - /* in milliseconds, the amount of time to - * sleep following a reset pulse. Zero - * should work if your bus devices recover - * time respects the 1-wire spec since the - * ds1wm implements the precise timings of - * a reset pulse/presence detect sequence. - */ - unsigned int reset_recover_delay; - - /* Say 1 here for big endian Hardware - * (only relevant with bus-shift > 0 - */ - bool is_hw_big_endian; - - /* left shift of register number to get register address offsett. - * Only 0,1,2 allowed for 8,16 or 32 bit bus width respectively - */ - unsigned int bus_shift; -}; diff --git a/include/linux/mfd/idt8a340_reg.h b/include/linux/mfd/idt8a340_reg.h index 0c706085c205..53a222605526 100644 --- a/include/linux/mfd/idt8a340_reg.h +++ b/include/linux/mfd/idt8a340_reg.h @@ -61,7 +61,7 @@ #define HW_Q8_CTRL_SPARE (0xa7d4) #define HW_Q11_CTRL_SPARE (0xa7ec) -/** +/* * Select FOD5 as sync_trigger for Q8 divider. * Transition from logic zero to one * sets trigger to sync Q8 divider. @@ -70,7 +70,7 @@ */ #define Q9_TO_Q8_SYNC_TRIG BIT(1) -/** +/* * Enable FOD5 as driver for clock and sync for Q8 divider. * Enable fanout buffer for FOD5. * @@ -78,7 +78,7 @@ */ #define Q9_TO_Q8_FANOUT_AND_CLOCK_SYNC_ENABLE_MASK (BIT(0) | BIT(2)) -/** +/* * Select FOD6 as sync_trigger for Q11 divider. * Transition from logic zero to one * sets trigger to sync Q11 divider. @@ -87,7 +87,7 @@ */ #define Q10_TO_Q11_SYNC_TRIG BIT(1) -/** +/* * Enable FOD6 as driver for clock and sync for Q11 divider. * Enable fanout buffer for FOD6. * diff --git a/include/linux/mfd/intel-m10-bmc.h b/include/linux/mfd/intel-m10-bmc.h index ee66c9751003..988f1cd90032 100644 --- a/include/linux/mfd/intel-m10-bmc.h +++ b/include/linux/mfd/intel-m10-bmc.h @@ -205,6 +205,7 @@ struct m10bmc_csr_map { unsigned int pr_reh_addr; unsigned int pr_magic; unsigned int rsu_update_counter; + unsigned int staging_size; }; /** diff --git a/include/linux/mfd/lm3533.h b/include/linux/mfd/lm3533.h index 77092f6363ad..69059a7a2ce5 100644 --- a/include/linux/mfd/lm3533.h +++ b/include/linux/mfd/lm3533.h @@ -16,6 +16,7 @@ DEVICE_ATTR(_name, S_IRUGO | S_IWUSR , show_##_name, store_##_name) struct device; +struct gpio_desc; struct regmap; struct lm3533 { @@ -23,7 +24,7 @@ struct lm3533 { struct regmap *regmap; - int gpio_hwen; + struct gpio_desc *hwen; int irq; unsigned have_als:1; @@ -69,8 +70,6 @@ enum lm3533_boost_ovp { }; struct lm3533_platform_data { - int gpio_hwen; - enum lm3533_boost_ovp boost_ovp; enum lm3533_boost_freq boost_freq; diff --git a/include/linux/mfd/lp8788.h b/include/linux/mfd/lp8788.h index 51b47966a04d..fd17bec2a33e 100644 --- a/include/linux/mfd/lp8788.h +++ b/include/linux/mfd/lp8788.h @@ -11,7 +11,6 @@ #define __MFD_LP8788_H__ #include <linux/irqdomain.h> -#include <linux/pwm.h> #include <linux/regmap.h> #define LP8788_DEV_BUCK "lp8788-buck" @@ -87,12 +86,6 @@ enum lp8788_charger_event { CHARGER_DETECTED, }; -enum lp8788_bl_ctrl_mode { - LP8788_BL_REGISTER_ONLY, - LP8788_BL_COMB_PWM_BASED, /* PWM + I2C, changed by PWM input */ - LP8788_BL_COMB_REGISTER_BASED, /* PWM + I2C, changed by I2C */ -}; - enum lp8788_bl_dim_mode { LP8788_DIM_EXPONENTIAL, LP8788_DIM_LINEAR, @@ -202,31 +195,6 @@ struct lp8788_charger_platform_data { }; /* - * struct lp8788_backlight_platform_data - * @name : backlight driver name. (default: "lcd-backlight") - * @initial_brightness : initial value of backlight brightness - * @bl_mode : brightness control by pwm or lp8788 register - * @dim_mode : dimming mode selection - * @full_scale : full scale current setting - * @rise_time : brightness ramp up step time - * @fall_time : brightness ramp down step time - * @pwm_pol : pwm polarity setting when bl_mode is pwm based - * @period_ns : platform specific pwm period value. unit is nano. - Only valid when bl_mode is LP8788_BL_COMB_PWM_BASED - */ -struct lp8788_backlight_platform_data { - char *name; - int initial_brightness; - enum lp8788_bl_ctrl_mode bl_mode; - enum lp8788_bl_dim_mode dim_mode; - enum lp8788_bl_full_scale_current full_scale; - enum lp8788_bl_ramp_step rise_time; - enum lp8788_bl_ramp_step fall_time; - enum pwm_polarity pwm_pol; - unsigned int period_ns; -}; - -/* * struct lp8788_led_platform_data * @name : led driver name. (default: "keyboard-backlight") * @scale : current scale @@ -267,7 +235,6 @@ struct lp8788_vib_platform_data { * @buck2_dvs : configurations for buck2 dvs * @chg_pdata : platform data for charger driver * @alarm_sel : rtc alarm selection (1 or 2) - * @bl_pdata : configurable data for backlight driver * @led_pdata : configurable data for led driver * @vib_pdata : configurable data for vibrator driver * @adc_pdata : iio map data for adc driver @@ -289,9 +256,6 @@ struct lp8788_platform_data { /* rtc alarm */ enum lp8788_alarm_sel alarm_sel; - /* backlight */ - struct lp8788_backlight_platform_data *bl_pdata; - /* current sinks */ struct lp8788_led_platform_data *led_pdata; struct lp8788_vib_platform_data *vib_pdata; diff --git a/include/linux/mfd/max5970.h b/include/linux/mfd/max5970.h index 762a7d40c843..fc50e89edfaa 100644 --- a/include/linux/mfd/max5970.h +++ b/include/linux/mfd/max5970.h @@ -16,18 +16,6 @@ #define MAX5978_NUM_SWITCHES 1 #define MAX5970_NUM_LEDS 4 -struct max5970_data { - int num_switches; - u32 irng[MAX5970_NUM_SWITCHES]; - u32 mon_rng[MAX5970_NUM_SWITCHES]; - u32 shunt_micro_ohms[MAX5970_NUM_SWITCHES]; -}; - -enum max5970_chip_type { - TYPE_MAX5978 = 1, - TYPE_MAX5970, -}; - #define MAX5970_REG_CURRENT_L(ch) (0x01 + (ch) * 4) #define MAX5970_REG_CURRENT_H(ch) (0x00 + (ch) * 4) #define MAX5970_REG_VOLTAGE_L(ch) (0x03 + (ch) * 4) diff --git a/include/linux/mfd/max77693-private.h b/include/linux/mfd/max77693-private.h index 54444ff2a5de..c324d548619e 100644 --- a/include/linux/mfd/max77693-private.h +++ b/include/linux/mfd/max77693-private.h @@ -217,6 +217,10 @@ enum max77693_charger_battery_state { #define CHG_CNFG_01_CHGRSTRT_MASK (0x3 << CHG_CNFG_01_CHGRSTRT_SHIFT) #define CHG_CNFG_01_PQEN_MAKS BIT(CHG_CNFG_01_PQEN_SHIFT) +/* MAX77693_CHG_REG_CHG_CNFG_02 register */ +#define CHG_CNFG_02_CC_SHIFT 0 +#define CHG_CNFG_02_CC_MASK 0x3F + /* MAX77693_CHG_REG_CHG_CNFG_03 register */ #define CHG_CNFG_03_TOITH_SHIFT 0 #define CHG_CNFG_03_TOTIME_SHIFT 3 @@ -244,6 +248,7 @@ enum max77693_charger_battery_state { #define CHG_CNFG_12_VCHGINREG_MASK (0x3 << CHG_CNFG_12_VCHGINREG_SHIFT) /* MAX77693 CHG_CNFG_09 Register */ +#define CHG_CNFG_09_CHGIN_ILIM_SHIFT 0 #define CHG_CNFG_09_CHGIN_ILIM_MASK 0x7F /* MAX77693 CHG_CTRL Register */ @@ -414,17 +419,6 @@ enum max77693_haptic_reg { #define MAX77693_CONFIG2_MEN 6 #define MAX77693_CONFIG2_HTYP 5 -enum max77693_irq_source { - LED_INT = 0, - TOPSYS_INT, - CHG_INT, - MUIC_INT1, - MUIC_INT2, - MUIC_INT3, - - MAX77693_IRQ_GROUP_NR, -}; - #define SRC_IRQ_CHARGER BIT(0) #define SRC_IRQ_TOP BIT(1) #define SRC_IRQ_FLASH BIT(2) diff --git a/include/linux/mfd/mt6328/core.h b/include/linux/mfd/mt6328/core.h new file mode 100644 index 000000000000..9a08aed72b9f --- /dev/null +++ b/include/linux/mfd/mt6328/core.h @@ -0,0 +1,53 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2015 MediaTek Inc. + * Copyright (c) 2022 Yassine Oudjana <y.oudjana@protonmail.com> + */ + +#ifndef __MFD_MT6328_CORE_H__ +#define __MFD_MT6328_CORE_H__ + +enum mt6328_irq_status_numbers { + MT6328_IRQ_STATUS_PWRKEY = 0, + MT6328_IRQ_STATUS_HOMEKEY, + MT6328_IRQ_STATUS_PWRKEY_R, + MT6328_IRQ_STATUS_HOMEKEY_R, + MT6328_IRQ_STATUS_THR_H, + MT6328_IRQ_STATUS_THR_L, + MT6328_IRQ_STATUS_BAT_H, + MT6328_IRQ_STATUS_BAT_L, + MT6328_IRQ_STATUS_RTC, + MT6328_IRQ_STATUS_AUDIO, + MT6328_IRQ_STATUS_ACCDET, + MT6328_IRQ_STATUS_ACCDET_EINT, + MT6328_IRQ_STATUS_ACCDET_NEGV, + MT6328_IRQ_STATUS_NI_LBAT_INT, + MT6328_IRQ_STATUS_VPROC_OC = 16, + MT6328_IRQ_STATUS_VSYS_OC, + MT6328_IRQ_STATUS_VLTE_OC, + MT6328_IRQ_STATUS_VCORE_OC, + MT6328_IRQ_STATUS_VPA_OC, + MT6328_IRQ_STATUS_LDO_OC, + MT6328_IRQ_STATUS_BAT2_H, + MT6328_IRQ_STATUS_BAT2_L, + MT6328_IRQ_STATUS_VISMPS0_H, + MT6328_IRQ_STATUS_VISMPS0_L, + MT6328_IRQ_STATUS_AUXADC_IMP, + MT6328_IRQ_STATUS_OV = 32, + MT6328_IRQ_STATUS_BVALID_DET, + MT6328_IRQ_STATUS_VBATON_HV, + MT6328_IRQ_STATUS_VBATON_UNDET, + MT6328_IRQ_STATUS_WATCHDOG, + MT6328_IRQ_STATUS_PCHR_CM_VDEC, + MT6328_IRQ_STATUS_CHRDET, + MT6328_IRQ_STATUS_PCHR_CM_VINC, + MT6328_IRQ_STATUS_FG_BAT_H, + MT6328_IRQ_STATUS_FG_BAT_L, + MT6328_IRQ_STATUS_FG_CUR_H, + MT6328_IRQ_STATUS_FG_CUR_L, + MT6328_IRQ_STATUS_FG_ZCV, + MT6328_IRQ_STATUS_SPKL_D, + MT6328_IRQ_STATUS_SPKL_AB, +}; + +#endif /* __MFD_MT6323_CORE_H__ */ diff --git a/include/linux/mfd/mt6328/registers.h b/include/linux/mfd/mt6328/registers.h new file mode 100644 index 000000000000..8199aaea27b9 --- /dev/null +++ b/include/linux/mfd/mt6328/registers.h @@ -0,0 +1,822 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2022 Yassine Oudjana <y.oudjana@protonmail.com> + */ + +#ifndef __MFD_MT6328_REGISTERS_H__ +#define __MFD_MT6328_REGISTERS_H__ + +/* PMIC Registers */ +#define MT6328_STRUP_CON0 0x0000 +#define MT6328_STRUP_CON2 0x0002 +#define MT6328_STRUP_CON3 0x0004 +#define MT6328_STRUP_CON4 0x0006 +#define MT6328_STRUP_CON5 0x0008 +#define MT6328_STRUP_CON6 0x000a +#define MT6328_STRUP_CON7 0x000c +#define MT6328_STRUP_CON8 0x000e +#define MT6328_STRUP_CON9 0x0010 +#define MT6328_STRUP_CON10 0x0012 +#define MT6328_STRUP_CON11 0x0014 +#define MT6328_STRUP_CON12 0x0016 +#define MT6328_STRUP_CON13 0x0018 +#define MT6328_STRUP_CON14 0x001a +#define MT6328_STRUP_CON15 0x001c +#define MT6328_STRUP_CON16 0x001e +#define MT6328_STRUP_CON17 0x0020 +#define MT6328_STRUP_CON18 0x0022 +#define MT6328_STRUP_CON19 0x0024 +#define MT6328_STRUP_CON20 0x0026 +#define MT6328_STRUP_CON21 0x0028 +#define MT6328_STRUP_CON22 0x002a +#define MT6328_STRUP_CON23 0x002c +#define MT6328_STRUP_CON24 0x002e +#define MT6328_STRUP_CON25 0x0030 +#define MT6328_STRUP_CON26 0x0032 +#define MT6328_STRUP_CON27 0x0034 +#define MT6328_STRUP_CON28 0x0036 +#define MT6328_STRUP_CON29 0x0038 +#define MT6328_STRUP_CON30 0x003a +#define MT6328_STRUP_CON31 0x003c +#define MT6328_STRUP_CON32 0x003e +#define MT6328_STRUP_ANA_CON0 0x0040 +#define MT6328_HWCID 0x0200 +#define MT6328_SWCID 0x0202 +#define MT6328_TOP_CON 0x0204 +#define MT6328_TEST_OUT 0x0206 +#define MT6328_TEST_CON0 0x0208 +#define MT6328_TEST_CON1 0x020a +#define MT6328_TESTMODE_SW 0x020c +#define MT6328_EN_STATUS0 0x020e +#define MT6328_EN_STATUS1 0x0210 +#define MT6328_EN_STATUS2 0x0212 +#define MT6328_OCSTATUS0 0x0214 +#define MT6328_OCSTATUS1 0x0216 +#define MT6328_OCSTATUS2 0x0218 +#define MT6328_PGDEBSTATUS 0x021a +#define MT6328_PGSTATUS 0x021c +#define MT6328_THERMALSTATUS 0x021e +#define MT6328_TOPSTATUS 0x0220 +#define MT6328_TDSEL_CON 0x0222 +#define MT6328_RDSEL_CON 0x0224 +#define MT6328_SMT_CON0 0x0226 +#define MT6328_SMT_CON1 0x0228 +#define MT6328_SMT_CON2 0x022a +#define MT6328_DRV_CON0 0x022c +#define MT6328_DRV_CON1 0x022e +#define MT6328_DRV_CON2 0x0230 +#define MT6328_DRV_CON3 0x0232 +#define MT6328_TOP_STATUS 0x0234 +#define MT6328_TOP_STATUS_SET 0x0236 +#define MT6328_TOP_STATUS_CLR 0x0238 +#define MT6328_RGS_ANA_MON 0x023a +#define MT6328_TOP_CKPDN_CON0 0x023c +#define MT6328_TOP_CKPDN_CON0_SET 0x023e +#define MT6328_TOP_CKPDN_CON0_CLR 0x0240 +#define MT6328_TOP_CKPDN_CON1 0x0242 +#define MT6328_TOP_CKPDN_CON1_SET 0x0244 +#define MT6328_TOP_CKPDN_CON1_CLR 0x0246 +#define MT6328_TOP_CKPDN_CON2 0x0248 +#define MT6328_TOP_CKPDN_CON2_SET 0x024a +#define MT6328_TOP_CKPDN_CON2_CLR 0x024c +#define MT6328_TOP_CKPDN_CON3 0x024e +#define MT6328_TOP_CKPDN_CON3_SET 0x0250 +#define MT6328_TOP_CKPDN_CON3_CLR 0x0252 +#define MT6328_TOP_CKPDN_CON4 0x0254 +#define MT6328_TOP_CKPDN_CON4_SET 0x0256 +#define MT6328_TOP_CKPDN_CON4_CLR 0x0258 +#define MT6328_TOP_CKSEL_CON0 0x025a +#define MT6328_TOP_CKSEL_CON0_SET 0x025c +#define MT6328_TOP_CKSEL_CON0_CLR 0x025e +#define MT6328_TOP_CKSEL_CON1 0x0260 +#define MT6328_TOP_CKSEL_CON1_SET 0x0262 +#define MT6328_TOP_CKSEL_CON1_CLR 0x0264 +#define MT6328_TOP_CKSEL_CON2 0x0266 +#define MT6328_TOP_CKSEL_CON2_SET 0x0268 +#define MT6328_TOP_CKSEL_CON2_CLR 0x026a +#define MT6328_TOP_CKDIVSEL_CON0 0x026c +#define MT6328_TOP_CKDIVSEL_CON0_SET 0x026e +#define MT6328_TOP_CKDIVSEL_CON0_CLR 0x0270 +#define MT6328_TOP_CKDIVSEL_CON1 0x0272 +#define MT6328_TOP_CKDIVSEL_CON1_SET 0x0274 +#define MT6328_TOP_CKDIVSEL_CON1_CLR 0x0276 +#define MT6328_TOP_CKHWEN_CON0 0x0278 +#define MT6328_TOP_CKHWEN_CON0_SET 0x027a +#define MT6328_TOP_CKHWEN_CON0_CLR 0x027c +#define MT6328_TOP_CKHWEN_CON1 0x027e +#define MT6328_TOP_CKHWEN_CON1_SET 0x0280 +#define MT6328_TOP_CKHWEN_CON1_CLR 0x0282 +#define MT6328_TOP_CKTST_CON0 0x0284 +#define MT6328_TOP_CKTST_CON1 0x0286 +#define MT6328_TOP_CKTST_CON2 0x0288 +#define MT6328_TOP_CLKSQ 0x028a +#define MT6328_TOP_CLKSQ_SET 0x028c +#define MT6328_TOP_CLKSQ_CLR 0x028e +#define MT6328_TOP_CLKSQ_RTC 0x0290 +#define MT6328_TOP_CLKSQ_RTC_SET 0x0292 +#define MT6328_TOP_CLKSQ_RTC_CLR 0x0294 +#define MT6328_TOP_CLK_TRIM 0x0296 +#define MT6328_TOP_RST_CON0 0x0298 +#define MT6328_TOP_RST_CON0_SET 0x029a +#define MT6328_TOP_RST_CON0_CLR 0x029c +#define MT6328_TOP_RST_CON1 0x029e +#define MT6328_TOP_RST_MISC 0x02a0 +#define MT6328_TOP_RST_MISC_SET 0x02a2 +#define MT6328_TOP_RST_MISC_CLR 0x02a4 +#define MT6328_TOP_RST_STATUS 0x02a6 +#define MT6328_TOP_RST_STATUS_SET 0x02a8 +#define MT6328_TOP_RST_STATUS_CLR 0x02aa +#define MT6328_INT_CON0 0x02ac +#define MT6328_INT_CON0_SET 0x02ae +#define MT6328_INT_CON0_CLR 0x02b0 +#define MT6328_INT_CON1 0x02b2 +#define MT6328_INT_CON1_SET 0x02b4 +#define MT6328_INT_CON1_CLR 0x02b6 +#define MT6328_INT_CON2 0x02b8 +#define MT6328_INT_CON2_SET 0x02ba +#define MT6328_INT_CON2_CLR 0x02bc +#define MT6328_INT_MISC_CON 0x02be +#define MT6328_INT_MISC_CON_SET 0x02c0 +#define MT6328_INT_MISC_CON_CLR 0x02c2 +#define MT6328_INT_STATUS0 0x02c4 +#define MT6328_INT_STATUS1 0x02c6 +#define MT6328_INT_STATUS2 0x02c8 +#define MT6328_OC_GEAR_0 0x02ca +#define MT6328_FQMTR_CON0 0x02cc +#define MT6328_FQMTR_CON1 0x02ce +#define MT6328_FQMTR_CON2 0x02d0 +#define MT6328_RG_SPI_CON 0x02d2 +#define MT6328_DEW_DIO_EN 0x02d4 +#define MT6328_DEW_READ_TEST 0x02d6 +#define MT6328_DEW_WRITE_TEST 0x02d8 +#define MT6328_DEW_CRC_SWRST 0x02da +#define MT6328_DEW_CRC_EN 0x02dc +#define MT6328_DEW_CRC_VAL 0x02de +#define MT6328_DEW_DBG_MON_SEL 0x02e0 +#define MT6328_DEW_CIPHER_KEY_SEL 0x02e2 +#define MT6328_DEW_CIPHER_IV_SEL 0x02e4 +#define MT6328_DEW_CIPHER_EN 0x02e6 +#define MT6328_DEW_CIPHER_RDY 0x02e8 +#define MT6328_DEW_CIPHER_MODE 0x02ea +#define MT6328_DEW_CIPHER_SWRST 0x02ec +#define MT6328_DEW_RDDMY_NO 0x02ee +#define MT6328_INT_TYPE_CON0 0x02f0 +#define MT6328_INT_TYPE_CON0_SET 0x02f2 +#define MT6328_INT_TYPE_CON0_CLR 0x02f4 +#define MT6328_INT_TYPE_CON1 0x02f6 +#define MT6328_INT_TYPE_CON1_SET 0x02f8 +#define MT6328_INT_TYPE_CON1_CLR 0x02fa +#define MT6328_INT_TYPE_CON2 0x02fc +#define MT6328_INT_TYPE_CON2_SET 0x02fe +#define MT6328_INT_TYPE_CON2_CLR 0x0300 +#define MT6328_INT_STA 0x0302 +#define MT6328_BUCK_ALL_CON0 0x0400 +#define MT6328_BUCK_ALL_CON1 0x0402 +#define MT6328_BUCK_ALL_CON2 0x0404 +#define MT6328_BUCK_ALL_CON3 0x0406 +#define MT6328_BUCK_ALL_CON4 0x0408 +#define MT6328_BUCK_ALL_CON5 0x040a +#define MT6328_BUCK_ALL_CON6 0x040c +#define MT6328_BUCK_ALL_CON9 0x040e +#define MT6328_BUCK_ALL_CON12 0x0410 +#define MT6328_BUCK_ALL_CON13 0x0412 +#define MT6328_BUCK_ALL_CON14 0x0414 +#define MT6328_BUCK_ALL_CON16 0x0416 +#define MT6328_BUCK_ALL_CON18 0x0418 +#define MT6328_BUCK_ALL_CON19 0x041a +#define MT6328_BUCK_ALL_CON20 0x041c +#define MT6328_BUCK_ALL_CON21 0x041e +#define MT6328_BUCK_ALL_CON22 0x0420 +#define MT6328_BUCK_ALL_CON23 0x0422 +#define MT6328_BUCK_ALL_CON24 0x0424 +#define MT6328_BUCK_ALL_CON25 0x0426 +#define MT6328_BUCK_ALL_CON26 0x0428 +#define MT6328_BUCK_ALL_CON27 0x042a +#define MT6328_BUCK_ALL_CON28 0x042c +#define MT6328_SMPS_TOP_ANA_CON0 0x042e +#define MT6328_SMPS_TOP_ANA_CON1 0x0430 +#define MT6328_SMPS_TOP_ANA_CON2 0x0432 +#define MT6328_SMPS_TOP_ANA_CON3 0x0434 +#define MT6328_SMPS_TOP_ANA_CON4 0x0436 +#define MT6328_SMPS_TOP_ANA_CON5 0x0438 +#define MT6328_SMPS_TOP_ANA_CON6 0x043a +#define MT6328_SMPS_TOP_ANA_CON7 0x043c +#define MT6328_SMPS_TOP_ANA_CON8 0x043e +#define MT6328_VCORE_ANA_CON0 0x0440 +#define MT6328_VCORE_ANA_CON1 0x0442 +#define MT6328_VCORE_ANA_CON2 0x0444 +#define MT6328_VCORE_ANA_CON3 0x0446 +#define MT6328_VCORE_ANA_CON4 0x0448 +#define MT6328_VSYS22_ANA_CON0 0x044a +#define MT6328_VSYS22_ANA_CON1 0x044c +#define MT6328_VSYS22_ANA_CON2 0x044e +#define MT6328_VSYS22_ANA_CON3 0x0450 +#define MT6328_VSYS22_ANA_CON4 0x0452 +#define MT6328_VPROC_ANA_CON0 0x0454 +#define MT6328_VPROC_ANA_CON1 0x0456 +#define MT6328_VPROC_ANA_CON2 0x0458 +#define MT6328_VPROC_ANA_CON3 0x045a +#define MT6328_VPROC_ANA_CON4 0x045c +#define MT6328_OSC32_ANA_CON0 0x045e +#define MT6328_OSC32_ANA_CON1 0x0460 +#define MT6328_VPA_ANA_CON0 0x0462 +#define MT6328_VPA_ANA_CON1 0x0464 +#define MT6328_VPA_ANA_CON2 0x0466 +#define MT6328_VPA_ANA_CON3 0x0468 +#define MT6328_VLTE_ANA_CON0 0x046a +#define MT6328_VLTE_ANA_CON1 0x046c +#define MT6328_VLTE_ANA_CON2 0x046e +#define MT6328_VLTE_ANA_CON3 0x0470 +#define MT6328_VLTE_ANA_CON4 0x0472 +#define MT6328_VPROC_CON0 0x0474 +#define MT6328_VPROC_CON1 0x0476 +#define MT6328_VPROC_CON2 0x0478 +#define MT6328_VPROC_CON3 0x047a +#define MT6328_VPROC_CON4 0x047c +#define MT6328_VPROC_CON5 0x047e +#define MT6328_VPROC_CON6 0x0480 +#define MT6328_VPROC_CON7 0x0482 +#define MT6328_VPROC_CON8 0x0484 +#define MT6328_VPROC_CON9 0x0486 +#define MT6328_VPROC_CON10 0x0488 +#define MT6328_VPROC_CON11 0x048a +#define MT6328_VPROC_CON12 0x048c +#define MT6328_VPROC_CON13 0x048e +#define MT6328_VPROC_CON14 0x0490 +#define MT6328_VPROC_CON15 0x0492 +#define MT6328_VPROC_CON16 0x0494 +#define MT6328_VPROC_CON17 0x0496 +#define MT6328_VPROC_CON18 0x0498 +#define MT6328_VPROC_CON19 0x049a +#define MT6328_VSRAM_CON0 0x049c +#define MT6328_VSRAM_CON1 0x049e +#define MT6328_VSRAM_CON2 0x04a0 +#define MT6328_VSRAM_CON3 0x04a2 +#define MT6328_VSRAM_CON4 0x04a4 +#define MT6328_VSRAM_CON5 0x04a6 +#define MT6328_VSRAM_CON6 0x04a8 +#define MT6328_VSRAM_CON7 0x04aa +#define MT6328_VSRAM_CON8 0x04ac +#define MT6328_VSRAM_CON9 0x04ae +#define MT6328_VSRAM_CON10 0x04b0 +#define MT6328_VSRAM_CON11 0x04b2 +#define MT6328_VSRAM_CON12 0x04b4 +#define MT6328_VSRAM_CON13 0x04b6 +#define MT6328_VSRAM_CON14 0x04b8 +#define MT6328_VSRAM_CON15 0x04ba +#define MT6328_VSRAM_CON16 0x04bc +#define MT6328_VSRAM_CON17 0x04be +#define MT6328_VSRAM_CON18 0x04c0 +#define MT6328_VSRAM_CON19 0x04c2 +#define MT6328_VLTE_CON0 0x04c4 +#define MT6328_VLTE_CON1 0x04c6 +#define MT6328_VLTE_CON2 0x04c8 +#define MT6328_VLTE_CON3 0x04ca +#define MT6328_VLTE_CON4 0x04cc +#define MT6328_VLTE_CON5 0x04ce +#define MT6328_VLTE_CON6 0x04d0 +#define MT6328_VLTE_CON7 0x04d2 +#define MT6328_VLTE_CON8 0x04d4 +#define MT6328_VLTE_CON9 0x04d6 +#define MT6328_VLTE_CON10 0x04d8 +#define MT6328_VLTE_CON11 0x04da +#define MT6328_VLTE_CON12 0x04dc +#define MT6328_VLTE_CON13 0x04de +#define MT6328_VLTE_CON14 0x04e0 +#define MT6328_VLTE_CON15 0x04e2 +#define MT6328_VLTE_CON16 0x04e4 +#define MT6328_VLTE_CON17 0x04e6 +#define MT6328_VLTE_CON18 0x04e8 +#define MT6328_VLTE_CON19 0x04ea +#define MT6328_VCORE1_CON0 0x0600 +#define MT6328_VCORE1_CON1 0x0602 +#define MT6328_VCORE1_CON2 0x0604 +#define MT6328_VCORE1_CON3 0x0606 +#define MT6328_VCORE1_CON4 0x0608 +#define MT6328_VCORE1_CON5 0x060a +#define MT6328_VCORE1_CON6 0x060c +#define MT6328_VCORE1_CON7 0x060e +#define MT6328_VCORE1_CON8 0x0610 +#define MT6328_VCORE1_CON9 0x0612 +#define MT6328_VCORE1_CON10 0x0614 +#define MT6328_VCORE1_CON11 0x0616 +#define MT6328_VCORE1_CON12 0x0618 +#define MT6328_VCORE1_CON13 0x061a +#define MT6328_VCORE1_CON14 0x061c +#define MT6328_VCORE1_CON15 0x061e +#define MT6328_VCORE1_CON16 0x0620 +#define MT6328_VCORE1_CON17 0x0622 +#define MT6328_VCORE1_CON18 0x0624 +#define MT6328_VCORE1_CON19 0x0626 +#define MT6328_VSYS22_CON0 0x0628 +#define MT6328_VSYS22_CON1 0x062a +#define MT6328_VSYS22_CON2 0x062c +#define MT6328_VSYS22_CON3 0x062e +#define MT6328_VSYS22_CON4 0x0630 +#define MT6328_VSYS22_CON5 0x0632 +#define MT6328_VSYS22_CON6 0x0634 +#define MT6328_VSYS22_CON7 0x0636 +#define MT6328_VSYS22_CON8 0x0638 +#define MT6328_VSYS22_CON9 0x063a +#define MT6328_VSYS22_CON10 0x063c +#define MT6328_VSYS22_CON11 0x063e +#define MT6328_VSYS22_CON12 0x0640 +#define MT6328_VSYS22_CON13 0x0642 +#define MT6328_VSYS22_CON14 0x0644 +#define MT6328_VSYS22_CON15 0x0646 +#define MT6328_VSYS22_CON16 0x0648 +#define MT6328_VSYS22_CON17 0x064a +#define MT6328_VSYS22_CON18 0x064c +#define MT6328_VSYS22_CON19 0x064e +#define MT6328_VPA_CON0 0x0650 +#define MT6328_VPA_CON1 0x0652 +#define MT6328_VPA_CON2 0x0654 +#define MT6328_VPA_CON3 0x0656 +#define MT6328_VPA_CON4 0x0658 +#define MT6328_VPA_CON5 0x065a +#define MT6328_VPA_CON6 0x065c +#define MT6328_VPA_CON7 0x065e +#define MT6328_VPA_CON8 0x0660 +#define MT6328_VPA_CON9 0x0662 +#define MT6328_VPA_CON10 0x0664 +#define MT6328_VPA_CON11 0x0666 +#define MT6328_VPA_CON12 0x0668 +#define MT6328_VPA_CON13 0x066a +#define MT6328_VPA_CON14 0x066c +#define MT6328_VPA_CON15 0x066e +#define MT6328_VPA_CON16 0x0670 +#define MT6328_VPA_CON17 0x0672 +#define MT6328_VPA_CON18 0x0674 +#define MT6328_VPA_CON19 0x0676 +#define MT6328_VPA_CON20 0x0678 +#define MT6328_VPA_CON21 0x067a +#define MT6328_VPA_CON22 0x067c +#define MT6328_VPA_CON23 0x067e +#define MT6328_VPA_CON24 0x0680 +#define MT6328_BUCK_K_CON0 0x0682 +#define MT6328_BUCK_K_CON1 0x0684 +#define MT6328_BUCK_K_CON2 0x0686 +#define MT6328_BUCK_K_CON3 0x0688 +#define MT6328_ZCD_CON0 0x0800 +#define MT6328_ZCD_CON1 0x0802 +#define MT6328_ZCD_CON2 0x0804 +#define MT6328_ZCD_CON3 0x0806 +#define MT6328_ZCD_CON4 0x0808 +#define MT6328_ZCD_CON5 0x080a +#define MT6328_ISINK0_CON0 0x080c +#define MT6328_ISINK0_CON1 0x080e +#define MT6328_ISINK0_CON2 0x0810 +#define MT6328_ISINK0_CON3 0x0812 +#define MT6328_ISINK1_CON0 0x0814 +#define MT6328_ISINK1_CON1 0x0816 +#define MT6328_ISINK1_CON2 0x0818 +#define MT6328_ISINK1_CON3 0x081a +#define MT6328_ISINK2_CON1 0x081c +#define MT6328_ISINK3_CON1 0x081e +#define MT6328_ISINK_ANA0 0x0820 +#define MT6328_ISINK_ANA1 0x0822 +#define MT6328_ISINK_PHASE_DLY 0x0824 +#define MT6328_ISINK_SFSTR 0x0826 +#define MT6328_ISINK_EN_CTRL 0x0828 +#define MT6328_ISINK_MODE_CTRL 0x082a +#define MT6328_VTCXO_0_CON0 0x0a00 +#define MT6328_VTCXO_1_CON0 0x0a02 +#define MT6328_VAUD28_CON0 0x0a04 +#define MT6328_VAUX18_CON0 0x0a06 +#define MT6328_VRF18_0_CON0 0x0a08 +#define MT6328_VRF18_0_CON1 0x0a0a +#define MT6328_VCAMA_CON0 0x0a0c +#define MT6328_VCN28_CON0 0x0a0e +#define MT6328_VCN33_CON0 0x0a10 +#define MT6328_VCN33_CON1 0x0a12 +#define MT6328_VCN33_CON2 0x0a14 +#define MT6328_VRF18_1_CON0 0x0a16 +#define MT6328_VRF18_1_CON1 0x0a18 +#define MT6328_VUSB33_CON0 0x0a1a +#define MT6328_VMCH_CON0 0x0a1c +#define MT6328_VMCH_CON1 0x0a1e +#define MT6328_VMC_CON0 0x0a20 +#define MT6328_VMC_CON1 0x0a22 +#define MT6328_VEMC_3V3_CON0 0x0a24 +#define MT6328_VEMC_3V3_CON1 0x0a26 +#define MT6328_VIO28_CON0 0x0a28 +#define MT6328_VCAMAF_CON0 0x0a2a +#define MT6328_VGP1_CON0 0x0a2c +#define MT6328_VGP1_CON1 0x0a2e +#define MT6328_VEFUSE_CON0 0x0a30 +#define MT6328_VSIM1_CON0 0x0a32 +#define MT6328_VSIM2_CON0 0x0a34 +#define MT6328_VIO18_CON0 0x0a36 +#define MT6328_VIBR_CON0 0x0a38 +#define MT6328_VCN18_CON0 0x0a3a +#define MT6328_VCAM_CON0 0x0a3c +#define MT6328_VCAMIO_CON0 0x0a3e +#define MT6328_LDO_VSRAM_CON0 0x0a40 +#define MT6328_LDO_VSRAM_CON1 0x0a42 +#define MT6328_VTREF_CON0 0x0a44 +#define MT6328_VM_CON0 0x0a46 +#define MT6328_VM_CON1 0x0a48 +#define MT6328_VRTC_CON0 0x0a4a +#define MT6328_LDO_OCFB0 0x0a4c +#define MT6328_ALDO_ANA_CON0 0x0a4e +#define MT6328_ADLDO_ANA_CON1 0x0a50 +#define MT6328_ADLDO_ANA_CON2 0x0a52 +#define MT6328_ADLDO_ANA_CON3 0x0a54 +#define MT6328_ADLDO_ANA_CON4 0x0a56 +#define MT6328_ADLDO_ANA_CON5 0x0a58 +#define MT6328_ADLDO_ANA_CON6 0x0a5a +#define MT6328_ADLDO_ANA_CON7 0x0a5c +#define MT6328_ADLDO_ANA_CON8 0x0a5e +#define MT6328_ADLDO_ANA_CON9 0x0a60 +#define MT6328_ADLDO_ANA_CON10 0x0a62 +#define MT6328_ADLDO_ANA_CON11 0x0a64 +#define MT6328_ADLDO_ANA_CON12 0x0a66 +#define MT6328_ADLDO_ANA_CON13 0x0a68 +#define MT6328_DLDO_ANA_CON0 0x0a6a +#define MT6328_DLDO_ANA_CON1 0x0a6c +#define MT6328_DLDO_ANA_CON2 0x0a6e +#define MT6328_DLDO_ANA_CON3 0x0a70 +#define MT6328_DLDO_ANA_CON4 0x0a72 +#define MT6328_DLDO_ANA_CON5 0x0a74 +#define MT6328_SLDO_ANA_CON0 0x0a76 +#define MT6328_SLDO_ANA_CON1 0x0a78 +#define MT6328_SLDO_ANA_CON2 0x0a7a +#define MT6328_SLDO_ANA_CON3 0x0a7c +#define MT6328_SLDO_ANA_CON4 0x0a7e +#define MT6328_SLDO_ANA_CON5 0x0a80 +#define MT6328_SLDO_ANA_CON6 0x0a82 +#define MT6328_SLDO_ANA_CON7 0x0a84 +#define MT6328_SLDO_ANA_CON8 0x0a86 +#define MT6328_SLDO_ANA_CON9 0x0a88 +#define MT6328_SLDO_ANA_CON10 0x0a8a +#define MT6328_LDO_RSV_CON0 0x0a8c +#define MT6328_LDO_RSV_CON1 0x0a8e +#define MT6328_SPK_CON0 0x0a90 +#define MT6328_SPK_CON1 0x0a92 +#define MT6328_SPK_CON2 0x0a94 +#define MT6328_SPK_CON3 0x0a96 +#define MT6328_SPK_CON4 0x0a98 +#define MT6328_SPK_CON5 0x0a9a +#define MT6328_SPK_CON6 0x0a9c +#define MT6328_SPK_CON7 0x0a9e +#define MT6328_SPK_CON8 0x0aa0 +#define MT6328_SPK_CON9 0x0aa2 +#define MT6328_SPK_CON10 0x0aa4 +#define MT6328_SPK_CON11 0x0aa6 +#define MT6328_SPK_CON12 0x0aa8 +#define MT6328_SPK_CON13 0x0aaa +#define MT6328_SPK_CON14 0x0aac +#define MT6328_SPK_CON15 0x0aae +#define MT6328_SPK_CON16 0x0ab0 +#define MT6328_SPK_ANA_CON0 0x0ab2 +#define MT6328_SPK_ANA_CON1 0x0ab4 +#define MT6328_SPK_ANA_CON3 0x0ab6 +#define MT6328_OTP_CON0 0x0c00 +#define MT6328_OTP_CON1 0x0c02 +#define MT6328_OTP_CON2 0x0c04 +#define MT6328_OTP_CON3 0x0c06 +#define MT6328_OTP_CON4 0x0c08 +#define MT6328_OTP_CON5 0x0c0a +#define MT6328_OTP_CON6 0x0c0c +#define MT6328_OTP_CON7 0x0c0e +#define MT6328_OTP_CON8 0x0c10 +#define MT6328_OTP_CON9 0x0c12 +#define MT6328_OTP_CON10 0x0c14 +#define MT6328_OTP_CON11 0x0c16 +#define MT6328_OTP_CON12 0x0c18 +#define MT6328_OTP_CON13 0x0c1a +#define MT6328_OTP_CON14 0x0c1c +#define MT6328_OTP_DOUT_0_15 0x0c1e +#define MT6328_OTP_DOUT_16_31 0x0c20 +#define MT6328_OTP_DOUT_32_47 0x0c22 +#define MT6328_OTP_DOUT_48_63 0x0c24 +#define MT6328_OTP_DOUT_64_79 0x0c26 +#define MT6328_OTP_DOUT_80_95 0x0c28 +#define MT6328_OTP_DOUT_96_111 0x0c2a +#define MT6328_OTP_DOUT_112_127 0x0c2c +#define MT6328_OTP_DOUT_128_143 0x0c2e +#define MT6328_OTP_DOUT_144_159 0x0c30 +#define MT6328_OTP_DOUT_160_175 0x0c32 +#define MT6328_OTP_DOUT_176_191 0x0c34 +#define MT6328_OTP_DOUT_192_207 0x0c36 +#define MT6328_OTP_DOUT_208_223 0x0c38 +#define MT6328_OTP_DOUT_224_239 0x0c3a +#define MT6328_OTP_DOUT_240_255 0x0c3c +#define MT6328_OTP_DOUT_256_271 0x0c3e +#define MT6328_OTP_DOUT_272_287 0x0c40 +#define MT6328_OTP_DOUT_288_303 0x0c42 +#define MT6328_OTP_DOUT_304_319 0x0c44 +#define MT6328_OTP_DOUT_320_335 0x0c46 +#define MT6328_OTP_DOUT_336_351 0x0c48 +#define MT6328_OTP_DOUT_352_367 0x0c4a +#define MT6328_OTP_DOUT_368_383 0x0c4c +#define MT6328_OTP_DOUT_384_399 0x0c4e +#define MT6328_OTP_DOUT_400_415 0x0c50 +#define MT6328_OTP_DOUT_416_431 0x0c52 +#define MT6328_OTP_DOUT_432_447 0x0c54 +#define MT6328_OTP_DOUT_448_463 0x0c56 +#define MT6328_OTP_DOUT_464_479 0x0c58 +#define MT6328_OTP_DOUT_480_495 0x0c5a +#define MT6328_OTP_DOUT_496_511 0x0c5c +#define MT6328_OTP_VAL_0_15 0x0c5e +#define MT6328_OTP_VAL_16_31 0x0c60 +#define MT6328_OTP_VAL_32_47 0x0c62 +#define MT6328_OTP_VAL_48_63 0x0c64 +#define MT6328_OTP_VAL_64_79 0x0c66 +#define MT6328_OTP_VAL_80_95 0x0c68 +#define MT6328_OTP_VAL_96_111 0x0c6a +#define MT6328_OTP_VAL_112_127 0x0c6c +#define MT6328_OTP_VAL_128_143 0x0c6e +#define MT6328_OTP_VAL_144_159 0x0c70 +#define MT6328_OTP_VAL_160_175 0x0c72 +#define MT6328_OTP_VAL_176_191 0x0c74 +#define MT6328_OTP_VAL_192_207 0x0c76 +#define MT6328_OTP_VAL_208_223 0x0c78 +#define MT6328_OTP_VAL_224_239 0x0c7a +#define MT6328_OTP_VAL_240_255 0x0c7c +#define MT6328_OTP_VAL_256_271 0x0c7e +#define MT6328_OTP_VAL_272_287 0x0c80 +#define MT6328_OTP_VAL_288_303 0x0c82 +#define MT6328_OTP_VAL_304_319 0x0c84 +#define MT6328_OTP_VAL_320_335 0x0c86 +#define MT6328_OTP_VAL_336_351 0x0c88 +#define MT6328_OTP_VAL_352_367 0x0c8a +#define MT6328_OTP_VAL_368_383 0x0c8c +#define MT6328_OTP_VAL_384_399 0x0c8e +#define MT6328_OTP_VAL_400_415 0x0c90 +#define MT6328_OTP_VAL_416_431 0x0c92 +#define MT6328_OTP_VAL_432_447 0x0c94 +#define MT6328_OTP_VAL_448_463 0x0c96 +#define MT6328_OTP_VAL_464_479 0x0c98 +#define MT6328_OTP_VAL_480_495 0x0c9a +#define MT6328_OTP_VAL_496_511 0x0c9c +#define MT6328_RTC_MIX_CON0 0x0c9e +#define MT6328_RTC_MIX_CON1 0x0ca0 +#define MT6328_RTC_MIX_CON2 0x0ca2 +#define MT6328_FGADC_CON0 0x0ca4 +#define MT6328_FGADC_CON1 0x0ca6 +#define MT6328_FGADC_CON2 0x0ca8 +#define MT6328_FGADC_CON3 0x0caa +#define MT6328_FGADC_CON4 0x0cac +#define MT6328_FGADC_CON5 0x0cae +#define MT6328_FGADC_CON6 0x0cb0 +#define MT6328_FGADC_CON7 0x0cb2 +#define MT6328_FGADC_CON8 0x0cb4 +#define MT6328_FGADC_CON9 0x0cb6 +#define MT6328_FGADC_CON10 0x0cb8 +#define MT6328_FGADC_CON11 0x0cba +#define MT6328_FGADC_CON12 0x0cbc +#define MT6328_FGADC_CON13 0x0cbe +#define MT6328_FGADC_CON14 0x0cc0 +#define MT6328_FGADC_CON15 0x0cc2 +#define MT6328_FGADC_CON16 0x0cc4 +#define MT6328_FGADC_CON17 0x0cc6 +#define MT6328_FGADC_CON18 0x0cc8 +#define MT6328_FGADC_CON19 0x0cca +#define MT6328_FGADC_CON20 0x0ccc +#define MT6328_FGADC_CON21 0x0cce +#define MT6328_FGADC_CON22 0x0cd0 +#define MT6328_FGADC_CON23 0x0cd2 +#define MT6328_FGADC_CON24 0x0cd4 +#define MT6328_FGADC_CON25 0x0cd6 +#define MT6328_FGADC_CON26 0x0cd8 +#define MT6328_FGADC_CON27 0x0cda +#define MT6328_AUDDEC_ANA_CON0 0x0cdc +#define MT6328_AUDDEC_ANA_CON1 0x0cde +#define MT6328_AUDDEC_ANA_CON2 0x0ce0 +#define MT6328_AUDDEC_ANA_CON3 0x0ce2 +#define MT6328_AUDDEC_ANA_CON4 0x0ce4 +#define MT6328_AUDDEC_ANA_CON5 0x0ce6 +#define MT6328_AUDDEC_ANA_CON6 0x0ce8 +#define MT6328_AUDDEC_ANA_CON7 0x0cea +#define MT6328_AUDDEC_ANA_CON8 0x0cec +#define MT6328_AUDENC_ANA_CON0 0x0cee +#define MT6328_AUDENC_ANA_CON1 0x0cf0 +#define MT6328_AUDENC_ANA_CON2 0x0cf2 +#define MT6328_AUDENC_ANA_CON3 0x0cf4 +#define MT6328_AUDENC_ANA_CON4 0x0cf6 +#define MT6328_AUDENC_ANA_CON5 0x0cf8 +#define MT6328_AUDENC_ANA_CON6 0x0cfa +#define MT6328_AUDENC_ANA_CON7 0x0cfc +#define MT6328_AUDENC_ANA_CON8 0x0cfe +#define MT6328_AUDENC_ANA_CON9 0x0d00 +#define MT6328_AUDENC_ANA_CON10 0x0d02 +#define MT6328_AUDNCP_CLKDIV_CON0 0x0d04 +#define MT6328_AUDNCP_CLKDIV_CON1 0x0d06 +#define MT6328_AUDNCP_CLKDIV_CON2 0x0d08 +#define MT6328_AUDNCP_CLKDIV_CON3 0x0d0a +#define MT6328_AUDNCP_CLKDIV_CON4 0x0d0c +#define MT6328_AUXADC_ADC0 0x0e00 +#define MT6328_AUXADC_ADC1 0x0e02 +#define MT6328_AUXADC_ADC2 0x0e04 +#define MT6328_AUXADC_ADC3 0x0e06 +#define MT6328_AUXADC_ADC4 0x0e08 +#define MT6328_AUXADC_ADC5 0x0e0a +#define MT6328_AUXADC_ADC6 0x0e0c +#define MT6328_AUXADC_ADC7 0x0e0e +#define MT6328_AUXADC_ADC8 0x0e10 +#define MT6328_AUXADC_ADC9 0x0e12 +#define MT6328_AUXADC_ADC10 0x0e14 +#define MT6328_AUXADC_ADC11 0x0e16 +#define MT6328_AUXADC_ADC12 0x0e18 +#define MT6328_AUXADC_ADC13 0x0e1a +#define MT6328_AUXADC_ADC14 0x0e1c +#define MT6328_AUXADC_ADC15 0x0e1e +#define MT6328_AUXADC_ADC16 0x0e20 +#define MT6328_AUXADC_ADC17 0x0e22 +#define MT6328_AUXADC_ADC18 0x0e24 +#define MT6328_AUXADC_ADC19 0x0e26 +#define MT6328_AUXADC_ADC20 0x0e28 +#define MT6328_AUXADC_ADC21 0x0e2a +#define MT6328_AUXADC_ADC22 0x0e2c +#define MT6328_AUXADC_ADC23 0x0e2e +#define MT6328_AUXADC_ADC24 0x0e30 +#define MT6328_AUXADC_ADC25 0x0e32 +#define MT6328_AUXADC_ADC26 0x0e34 +#define MT6328_AUXADC_ADC27 0x0e36 +#define MT6328_AUXADC_ADC28 0x0e38 +#define MT6328_AUXADC_ADC29 0x0e3a +#define MT6328_AUXADC_ADC30 0x0e3c +#define MT6328_AUXADC_ADC31 0x0e3e +#define MT6328_AUXADC_ADC32 0x0e40 +#define MT6328_AUXADC_ADC33 0x0e42 +#define MT6328_AUXADC_BUF0 0x0e44 +#define MT6328_AUXADC_BUF1 0x0e46 +#define MT6328_AUXADC_BUF2 0x0e48 +#define MT6328_AUXADC_BUF3 0x0e4a +#define MT6328_AUXADC_BUF4 0x0e4c +#define MT6328_AUXADC_BUF5 0x0e4e +#define MT6328_AUXADC_BUF6 0x0e50 +#define MT6328_AUXADC_BUF7 0x0e52 +#define MT6328_AUXADC_BUF8 0x0e54 +#define MT6328_AUXADC_BUF9 0x0e56 +#define MT6328_AUXADC_BUF10 0x0e58 +#define MT6328_AUXADC_BUF11 0x0e5a +#define MT6328_AUXADC_BUF12 0x0e5c +#define MT6328_AUXADC_BUF13 0x0e5e +#define MT6328_AUXADC_BUF14 0x0e60 +#define MT6328_AUXADC_BUF15 0x0e62 +#define MT6328_AUXADC_BUF16 0x0e64 +#define MT6328_AUXADC_BUF17 0x0e66 +#define MT6328_AUXADC_BUF18 0x0e68 +#define MT6328_AUXADC_BUF19 0x0e6a +#define MT6328_AUXADC_BUF20 0x0e6c +#define MT6328_AUXADC_BUF21 0x0e6e +#define MT6328_AUXADC_BUF22 0x0e70 +#define MT6328_AUXADC_BUF23 0x0e72 +#define MT6328_AUXADC_BUF24 0x0e74 +#define MT6328_AUXADC_BUF25 0x0e76 +#define MT6328_AUXADC_BUF26 0x0e78 +#define MT6328_AUXADC_BUF27 0x0e7a +#define MT6328_AUXADC_BUF28 0x0e7c +#define MT6328_AUXADC_BUF29 0x0e7e +#define MT6328_AUXADC_BUF30 0x0e80 +#define MT6328_AUXADC_BUF31 0x0e82 +#define MT6328_AUXADC_STA0 0x0e84 +#define MT6328_AUXADC_STA1 0x0e86 +#define MT6328_AUXADC_RQST0 0x0e88 +#define MT6328_AUXADC_RQST0_SET 0x0e8a +#define MT6328_AUXADC_RQST0_CLR 0x0e8c +#define MT6328_AUXADC_RQST1 0x0e8e +#define MT6328_AUXADC_RQST1_SET 0x0e90 +#define MT6328_AUXADC_RQST1_CLR 0x0e92 +#define MT6328_AUXADC_CON0 0x0e94 +#define MT6328_AUXADC_CON0_SET 0x0e96 +#define MT6328_AUXADC_CON0_CLR 0x0e98 +#define MT6328_AUXADC_CON1 0x0e9a +#define MT6328_AUXADC_CON2 0x0e9c +#define MT6328_AUXADC_CON3 0x0e9e +#define MT6328_AUXADC_CON4 0x0ea0 +#define MT6328_AUXADC_CON5 0x0ea2 +#define MT6328_AUXADC_CON6 0x0ea4 +#define MT6328_AUXADC_CON7 0x0ea6 +#define MT6328_AUXADC_CON8 0x0ea8 +#define MT6328_AUXADC_CON9 0x0eaa +#define MT6328_AUXADC_CON10 0x0eac +#define MT6328_AUXADC_CON11 0x0eae +#define MT6328_AUXADC_CON12 0x0eb0 +#define MT6328_AUXADC_CON13 0x0eb2 +#define MT6328_AUXADC_CON14 0x0eb4 +#define MT6328_AUXADC_CON15 0x0eb6 +#define MT6328_AUXADC_CON16 0x0eb8 +#define MT6328_AUXADC_AUTORPT0 0x0eba +#define MT6328_AUXADC_LBAT0 0x0ebc +#define MT6328_AUXADC_LBAT1 0x0ebe +#define MT6328_AUXADC_LBAT2 0x0ec0 +#define MT6328_AUXADC_LBAT3 0x0ec2 +#define MT6328_AUXADC_LBAT4 0x0ec4 +#define MT6328_AUXADC_LBAT5 0x0ec6 +#define MT6328_AUXADC_LBAT6 0x0ec8 +#define MT6328_AUXADC_ACCDET 0x0eca +#define MT6328_AUXADC_THR0 0x0ecc +#define MT6328_AUXADC_THR1 0x0ece +#define MT6328_AUXADC_THR2 0x0ed0 +#define MT6328_AUXADC_THR3 0x0ed2 +#define MT6328_AUXADC_THR4 0x0ed4 +#define MT6328_AUXADC_THR5 0x0ed6 +#define MT6328_AUXADC_THR6 0x0ed8 +#define MT6328_AUXADC_EFUSE0 0x0eda +#define MT6328_AUXADC_EFUSE1 0x0edc +#define MT6328_AUXADC_EFUSE2 0x0ede +#define MT6328_AUXADC_EFUSE3 0x0ee0 +#define MT6328_AUXADC_EFUSE4 0x0ee2 +#define MT6328_AUXADC_EFUSE5 0x0ee4 +#define MT6328_AUXADC_DBG0 0x0ee6 +#define MT6328_AUXADC_IMP0 0x0ee8 +#define MT6328_AUXADC_IMP1 0x0eea +#define MT6328_AUXADC_VISMPS0_1 0x0eec +#define MT6328_AUXADC_VISMPS0_2 0x0eee +#define MT6328_AUXADC_VISMPS0_3 0x0ef0 +#define MT6328_AUXADC_VISMPS0_4 0x0ef2 +#define MT6328_AUXADC_VISMPS0_5 0x0ef4 +#define MT6328_AUXADC_VISMPS0_6 0x0ef6 +#define MT6328_AUXADC_VISMPS0_7 0x0ef8 +#define MT6328_AUXADC_LBAT2_1 0x0efa +#define MT6328_AUXADC_LBAT2_2 0x0efc +#define MT6328_AUXADC_LBAT2_3 0x0efe +#define MT6328_AUXADC_LBAT2_4 0x0f00 +#define MT6328_AUXADC_LBAT2_5 0x0f02 +#define MT6328_AUXADC_LBAT2_6 0x0f04 +#define MT6328_AUXADC_LBAT2_7 0x0f06 +#define MT6328_AUXADC_MDBG_0 0x0f08 +#define MT6328_AUXADC_MDBG_1 0x0f0a +#define MT6328_AUXADC_MDBG_2 0x0f0c +#define MT6328_AUXADC_MDRT_0 0x0f0e +#define MT6328_AUXADC_MDRT_1 0x0f10 +#define MT6328_AUXADC_MDRT_2 0x0f12 +#define MT6328_ACCDET_CON0 0x0f14 +#define MT6328_ACCDET_CON1 0x0f16 +#define MT6328_ACCDET_CON2 0x0f18 +#define MT6328_ACCDET_CON3 0x0f1a +#define MT6328_ACCDET_CON4 0x0f1c +#define MT6328_ACCDET_CON5 0x0f1e +#define MT6328_ACCDET_CON6 0x0f20 +#define MT6328_ACCDET_CON7 0x0f22 +#define MT6328_ACCDET_CON8 0x0f24 +#define MT6328_ACCDET_CON9 0x0f26 +#define MT6328_ACCDET_CON10 0x0f28 +#define MT6328_ACCDET_CON11 0x0f2a +#define MT6328_ACCDET_CON12 0x0f2c +#define MT6328_ACCDET_CON13 0x0f2e +#define MT6328_ACCDET_CON14 0x0f30 +#define MT6328_ACCDET_CON15 0x0f32 +#define MT6328_ACCDET_CON16 0x0f34 +#define MT6328_ACCDET_CON17 0x0f36 +#define MT6328_ACCDET_CON18 0x0f38 +#define MT6328_ACCDET_CON19 0x0f3a +#define MT6328_ACCDET_CON20 0x0f3c +#define MT6328_ACCDET_CON21 0x0f3e +#define MT6328_ACCDET_CON22 0x0f40 +#define MT6328_ACCDET_CON23 0x0f42 +#define MT6328_ACCDET_CON24 0x0f44 +#define MT6328_ACCDET_CON25 0x0f46 +#define MT6328_CHR_CON0 0x0f48 +#define MT6328_CHR_CON1 0x0f4a +#define MT6328_CHR_CON2 0x0f4c +#define MT6328_CHR_CON3 0x0f4e +#define MT6328_CHR_CON4 0x0f50 +#define MT6328_CHR_CON5 0x0f52 +#define MT6328_CHR_CON6 0x0f54 +#define MT6328_CHR_CON7 0x0f56 +#define MT6328_CHR_CON8 0x0f58 +#define MT6328_CHR_CON9 0x0f5a +#define MT6328_CHR_CON10 0x0f5c +#define MT6328_CHR_CON11 0x0f5e +#define MT6328_CHR_CON12 0x0f60 +#define MT6328_CHR_CON13 0x0f62 +#define MT6328_CHR_CON14 0x0f64 +#define MT6328_CHR_CON15 0x0f66 +#define MT6328_CHR_CON16 0x0f68 +#define MT6328_CHR_CON17 0x0f6a +#define MT6328_CHR_CON18 0x0f6c +#define MT6328_CHR_CON19 0x0f6e +#define MT6328_CHR_CON20 0x0f70 +#define MT6328_CHR_CON21 0x0f72 +#define MT6328_CHR_CON22 0x0f74 +#define MT6328_CHR_CON23 0x0f76 +#define MT6328_CHR_CON24 0x0f78 +#define MT6328_CHR_CON25 0x0f7a +#define MT6328_CHR_CON26 0x0f7c +#define MT6328_CHR_CON27 0x0f7e +#define MT6328_CHR_CON28 0x0f80 +#define MT6328_CHR_CON29 0x0f82 +#define MT6328_CHR_CON30 0x0f84 +#define MT6328_CHR_CON31 0x0f86 +#define MT6328_CHR_CON32 0x0f88 +#define MT6328_CHR_CON33 0x0f8a +#define MT6328_CHR_CON34 0x0f8c +#define MT6328_CHR_CON35 0x0f8e +#define MT6328_CHR_CON36 0x0f90 +#define MT6328_CHR_CON37 0x0f92 +#define MT6328_CHR_CON38 0x0f94 +#define MT6328_CHR_CON39 0x0f96 +#define MT6328_CHR_CON40 0x0f98 +#define MT6328_CHR_CON41 0x0f9a +#define MT6328_CHR_CON42 0x0f9c +#define MT6328_BATON_CON0 0x0f9e +#define MT6328_CHR_CON43 0x0fa0 +#define MT6328_EOSC_CALI_CON0 0x0faa +#define MT6328_EOSC_CALI_CON1 0x0fac +#define MT6328_VRTC_PWM_CON0 0x0fae + +#endif /* __MFD_MT6328_REGISTERS_H__ */ diff --git a/include/linux/mfd/mt6397/core.h b/include/linux/mfd/mt6397/core.h index 627487e26287..b774c3a4bb62 100644 --- a/include/linux/mfd/mt6397/core.h +++ b/include/linux/mfd/mt6397/core.h @@ -12,6 +12,7 @@ enum chip_id { MT6323_CHIP_ID = 0x23, + MT6328_CHIP_ID = 0x30, MT6331_CHIP_ID = 0x20, MT6332_CHIP_ID = 0x20, MT6357_CHIP_ID = 0x57, @@ -65,11 +66,11 @@ struct mt6397_chip { int irq; struct irq_domain *irq_domain; struct mutex irqlock; - u16 wake_mask[2]; - u16 irq_masks_cur[2]; - u16 irq_masks_cache[2]; - u16 int_con[2]; - u16 int_status[2]; + u16 wake_mask[3]; + u16 irq_masks_cur[3]; + u16 irq_masks_cache[3]; + u16 int_con[3]; + u16 int_status[3]; u16 chip_id; void *irq_data; }; diff --git a/include/linux/mfd/palmas.h b/include/linux/mfd/palmas.h index eda1ffd99c1a..dabcc0dea802 100644 --- a/include/linux/mfd/palmas.h +++ b/include/linux/mfd/palmas.h @@ -98,8 +98,8 @@ struct palmas_sleep_requestor_info { }; struct palmas_regs_info { - char *name; - char *sname; + const char *name; + const char *sname; u8 vsel_addr; u8 ctrl_addr; u8 tstep_addr; diff --git a/include/linux/mfd/qnap-mcu.h b/include/linux/mfd/qnap-mcu.h new file mode 100644 index 000000000000..8d48c212fd44 --- /dev/null +++ b/include/linux/mfd/qnap-mcu.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Core definitions for QNAP MCU MFD driver. + * Copyright (C) 2024 Heiko Stuebner <heiko@sntech.de> + */ + +#ifndef _LINUX_QNAP_MCU_H_ +#define _LINUX_QNAP_MCU_H_ + +struct qnap_mcu; + +struct qnap_mcu_variant { + u32 baud_rate; + int num_drives; + int fan_pwm_min; + int fan_pwm_max; + bool usb_led; +}; + +int qnap_mcu_exec(struct qnap_mcu *mcu, + const u8 *cmd_data, size_t cmd_data_size, + u8 *reply_data, size_t reply_data_size); +int qnap_mcu_exec_with_ack(struct qnap_mcu *mcu, + const u8 *cmd_data, size_t cmd_data_size); + +#endif /* _LINUX_QNAP_MCU_H_ */ diff --git a/include/linux/mfd/rk808.h b/include/linux/mfd/rk808.h index 78e167a92483..69cbea78b430 100644 --- a/include/linux/mfd/rk808.h +++ b/include/linux/mfd/rk808.h @@ -113,6 +113,148 @@ enum rk808_reg { #define RK808_INT_STS_MSK_REG2 0x4f #define RK808_IO_POL_REG 0x50 +/* RK816 */ +enum rk816_reg { + RK816_ID_DCDC1, + RK816_ID_DCDC2, + RK816_ID_DCDC3, + RK816_ID_DCDC4, + RK816_ID_LDO1, + RK816_ID_LDO2, + RK816_ID_LDO3, + RK816_ID_LDO4, + RK816_ID_LDO5, + RK816_ID_LDO6, + RK816_ID_BOOST, + RK816_ID_OTG_SW, +}; + +enum rk816_irqs { + /* INT_STS_REG1 */ + RK816_IRQ_PWRON_FALL, + RK816_IRQ_PWRON_RISE, + + /* INT_STS_REG2 */ + RK816_IRQ_VB_LOW, + RK816_IRQ_PWRON, + RK816_IRQ_PWRON_LP, + RK816_IRQ_HOTDIE, + RK816_IRQ_RTC_ALARM, + RK816_IRQ_RTC_PERIOD, + RK816_IRQ_USB_OV, + + /* INT_STS_REG3 */ + RK816_IRQ_PLUG_IN, + RK816_IRQ_PLUG_OUT, + RK816_IRQ_CHG_OK, + RK816_IRQ_CHG_TE, + RK816_IRQ_CHG_TS, + RK816_IRQ_CHG_CVTLIM, + RK816_IRQ_DISCHG_ILIM, +}; + +/* power channel registers */ +#define RK816_DCDC_EN_REG1 0x23 + +#define RK816_DCDC_EN_REG2 0x24 +#define RK816_BOOST_EN BIT(1) +#define RK816_OTG_EN BIT(2) +#define RK816_BOOST_EN_MSK BIT(5) +#define RK816_OTG_EN_MSK BIT(6) +#define RK816_BUCK_DVS_CONFIRM BIT(7) + +#define RK816_LDO_EN_REG1 0x27 + +#define RK816_LDO_EN_REG2 0x28 + +/* interrupt registers and irq definitions */ +#define RK816_INT_STS_REG1 0x49 +#define RK816_INT_STS_MSK_REG1 0x4a +#define RK816_INT_STS_PWRON_FALL BIT(5) +#define RK816_INT_STS_PWRON_RISE BIT(6) + +#define RK816_INT_STS_REG2 0x4c +#define RK816_INT_STS_MSK_REG2 0x4d +#define RK816_INT_STS_VB_LOW BIT(1) +#define RK816_INT_STS_PWRON BIT(2) +#define RK816_INT_STS_PWRON_LP BIT(3) +#define RK816_INT_STS_HOTDIE BIT(4) +#define RK816_INT_STS_RTC_ALARM BIT(5) +#define RK816_INT_STS_RTC_PERIOD BIT(6) +#define RK816_INT_STS_USB_OV BIT(7) + +#define RK816_INT_STS_REG3 0x4e +#define RK816_INT_STS_MSK_REG3 0x4f +#define RK816_INT_STS_PLUG_IN BIT(0) +#define RK816_INT_STS_PLUG_OUT BIT(1) +#define RK816_INT_STS_CHG_OK BIT(2) +#define RK816_INT_STS_CHG_TE BIT(3) +#define RK816_INT_STS_CHG_TS BIT(4) +#define RK816_INT_STS_CHG_CVTLIM BIT(6) +#define RK816_INT_STS_DISCHG_ILIM BIT(7) + +#define RK816_IRQ_STS_OFFSET(x) ((x) - RK816_INT_STS_REG1) +#define RK816_IRQ_MSK_OFFSET(x) ((x) - RK816_INT_STS_MSK_REG1) + +/* charger, boost and OTG registers */ +#define RK816_OTG_BUCK_LDO_CONFIG_REG 0x2a +#define RK816_CHRG_CONFIG_REG 0x2b +#define RK816_BOOST_ON_VESL_REG 0x54 +#define RK816_BOOST_SLP_VSEL_REG 0x55 +#define RK816_CHRG_BOOST_CONFIG_REG 0x9a +#define RK816_SUP_STS_REG 0xa0 +#define RK816_USB_CTRL_REG 0xa1 +#define RK816_CHRG_CTRL(x) (0xa3 + (x)) +#define RK816_BAT_CTRL_REG 0xa6 +#define RK816_BAT_HTS_TS_REG 0xa8 +#define RK816_BAT_LTS_TS_REG 0xa9 + +/* adc and fuel gauge registers */ +#define RK816_TS_CTRL_REG 0xac +#define RK816_ADC_CTRL_REG 0xad +#define RK816_GGCON_REG 0xb0 +#define RK816_GGSTS_REG 0xb1 +#define RK816_ZERO_CUR_ADC_REGH 0xb2 +#define RK816_ZERO_CUR_ADC_REGL 0xb3 +#define RK816_GASCNT_CAL_REG(x) (0xb7 - (x)) +#define RK816_GASCNT_REG(x) (0xbb - (x)) +#define RK816_BAT_CUR_AVG_REGH 0xbc +#define RK816_BAT_CUR_AVG_REGL 0xbd +#define RK816_TS_ADC_REGH 0xbe +#define RK816_TS_ADC_REGL 0xbf +#define RK816_USB_ADC_REGH 0xc0 +#define RK816_USB_ADC_REGL 0xc1 +#define RK816_BAT_OCV_REGH 0xc2 +#define RK816_BAT_OCV_REGL 0xc3 +#define RK816_BAT_VOL_REGH 0xc4 +#define RK816_BAT_VOL_REGL 0xc5 +#define RK816_RELAX_ENTRY_THRES_REGH 0xc6 +#define RK816_RELAX_ENTRY_THRES_REGL 0xc7 +#define RK816_RELAX_EXIT_THRES_REGH 0xc8 +#define RK816_RELAX_EXIT_THRES_REGL 0xc9 +#define RK816_RELAX_VOL1_REGH 0xca +#define RK816_RELAX_VOL1_REGL 0xcb +#define RK816_RELAX_VOL2_REGH 0xcc +#define RK816_RELAX_VOL2_REGL 0xcd +#define RK816_RELAX_CUR1_REGH 0xce +#define RK816_RELAX_CUR1_REGL 0xcf +#define RK816_RELAX_CUR2_REGH 0xd0 +#define RK816_RELAX_CUR2_REGL 0xd1 +#define RK816_CAL_OFFSET_REGH 0xd2 +#define RK816_CAL_OFFSET_REGL 0xd3 +#define RK816_NON_ACT_TIMER_CNT_REG 0xd4 +#define RK816_VCALIB0_REGH 0xd5 +#define RK816_VCALIB0_REGL 0xd6 +#define RK816_VCALIB1_REGH 0xd7 +#define RK816_VCALIB1_REGL 0xd8 +#define RK816_FCC_GASCNT_REG(x) (0xdc - (x)) +#define RK816_IOFFSET_REGH 0xdd +#define RK816_IOFFSET_REGL 0xde +#define RK816_SLEEP_CON_SAMP_CUR_REG 0xdf + +/* general purpose data registers 0xe0 ~ 0xf2 */ +#define RK816_DATA_REG(x) (0xe0 + (x)) + /* RK818 */ #define RK818_DCDC1 0 #define RK818_LDO1 4 @@ -791,6 +933,7 @@ enum rk806_dvs_mode { #define VOUT_LO_INT BIT(0) #define CLK32KOUT2_EN BIT(0) +#define TEMP105C 0x08 #define TEMP115C 0x0c #define TEMP_HOTDIE_MSK 0x0c #define SLP_SD_MSK (0x3 << 2) @@ -1191,6 +1334,7 @@ enum { RK806_ID = 0x8060, RK808_ID = 0x0000, RK809_ID = 0x8090, + RK816_ID = 0x8160, RK817_ID = 0x8170, RK818_ID = 0x8180, }; diff --git a/include/linux/mfd/rohm-bd71828.h b/include/linux/mfd/rohm-bd71828.h index 3b5f3a7db4bd..ce786c96404a 100644 --- a/include/linux/mfd/rohm-bd71828.h +++ b/include/linux/mfd/rohm-bd71828.h @@ -4,6 +4,7 @@ #ifndef __LINUX_MFD_BD71828_H__ #define __LINUX_MFD_BD71828_H__ +#include <linux/bits.h> #include <linux/mfd/rohm-generic.h> #include <linux/mfd/rohm-shared.h> @@ -41,7 +42,8 @@ enum { #define BD71828_REG_PS_CTRL_2 0x05 #define BD71828_REG_PS_CTRL_3 0x06 -//#define BD71828_REG_SWRESET 0x06 +#define BD71828_MASK_STATE_HBNT BIT(1) + #define BD71828_MASK_RUN_LVL_CTRL 0x30 /* Regulator control masks */ @@ -133,7 +135,6 @@ enum { #define BD71828_REG_LDO5_VOLT 0x43 #define BD71828_REG_LDO5_VOLT_OPT 0x42 #define BD71828_REG_LDO6_EN 0x44 -//#define BD71828_REG_LDO6_VOLT 0x4 #define BD71828_REG_LDO7_EN 0x45 #define BD71828_REG_LDO7_VOLT 0x46 diff --git a/include/linux/mfd/rohm-bd96801.h b/include/linux/mfd/rohm-bd96801.h new file mode 100644 index 000000000000..e2d9e10b6364 --- /dev/null +++ b/include/linux/mfd/rohm-bd96801.h @@ -0,0 +1,215 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* Copyright (C) 2024 ROHM Semiconductors */ + +#ifndef __MFD_BD96801_H__ +#define __MFD_BD96801_H__ + +#define BD96801_REG_SSCG_CTRL 0x09 +#define BD96801_REG_SHD_INTB 0x20 +#define BD96801_LDO5_VOL_LVL_REG 0x2c +#define BD96801_LDO6_VOL_LVL_REG 0x2d +#define BD96801_LDO7_VOL_LVL_REG 0x2e +#define BD96801_REG_BUCK_OVP 0x30 +#define BD96801_REG_BUCK_OVD 0x35 +#define BD96801_REG_LDO_OVP 0x31 +#define BD96801_REG_LDO_OVD 0x36 +#define BD96801_REG_BOOT_OVERTIME 0x3a +#define BD96801_REG_WD_TMO 0x40 +#define BD96801_REG_WD_CONF 0x41 +#define BD96801_REG_WD_FEED 0x42 +#define BD96801_REG_WD_FAILCOUNT 0x43 +#define BD96801_REG_WD_ASK 0x46 +#define BD96801_REG_WD_STATUS 0x4a +#define BD96801_REG_PMIC_STATE 0x4f +#define BD96801_REG_EXT_STATE 0x50 + +#define BD96801_STATE_STBY 0x09 + +#define BD96801_LOCK_REG 0x04 +#define BD96801_UNLOCK 0x9d +#define BD96801_LOCK 0x00 + +/* IRQ register area */ +#define BD96801_REG_INT_MAIN 0x51 + +/* + * The BD96801 has two physical IRQ lines, INTB and ERRB. + * + * The 'main status register' is located at 0x51. + * The ERRB status registers are located at 0x52 ... 0x5B + * INTB status registers are at range 0x5c ... 0x63 + */ +#define BD96801_REG_INT_SYS_ERRB1 0x52 +#define BD96801_REG_INT_SYS_INTB 0x5c +#define BD96801_REG_INT_LDO7_INTB 0x63 + +/* MASK registers */ +#define BD96801_REG_MASK_SYS_INTB 0x73 +#define BD96801_REG_MASK_SYS_ERRB 0x69 + +#define BD96801_MAX_REGISTER 0x7a + +#define BD96801_OTP_ERR_MASK BIT(0) +#define BD96801_DBIST_ERR_MASK BIT(1) +#define BD96801_EEP_ERR_MASK BIT(2) +#define BD96801_ABIST_ERR_MASK BIT(3) +#define BD96801_PRSTB_ERR_MASK BIT(4) +#define BD96801_DRMOS1_ERR_MASK BIT(5) +#define BD96801_DRMOS2_ERR_MASK BIT(6) +#define BD96801_SLAVE_ERR_MASK BIT(7) +#define BD96801_VREF_ERR_MASK BIT(0) +#define BD96801_TSD_ERR_MASK BIT(1) +#define BD96801_UVLO_ERR_MASK BIT(2) +#define BD96801_OVLO_ERR_MASK BIT(3) +#define BD96801_OSC_ERR_MASK BIT(4) +#define BD96801_PON_ERR_MASK BIT(5) +#define BD96801_POFF_ERR_MASK BIT(6) +#define BD96801_CMD_SHDN_ERR_MASK BIT(7) +#define BD96801_INT_PRSTB_WDT_ERR_MASK BIT(0) +#define BD96801_INT_CHIP_IF_ERR_MASK BIT(3) +#define BD96801_INT_SHDN_ERR_MASK BIT(7) +#define BD96801_OUT_PVIN_ERR_MASK BIT(0) +#define BD96801_OUT_OVP_ERR_MASK BIT(1) +#define BD96801_OUT_UVP_ERR_MASK BIT(2) +#define BD96801_OUT_SHDN_ERR_MASK BIT(7) + +/* ERRB IRQs */ +enum { + /* Reg 0x52, 0x53, 0x54 - ERRB system IRQs */ + BD96801_OTP_ERR_STAT, + BD96801_DBIST_ERR_STAT, + BD96801_EEP_ERR_STAT, + BD96801_ABIST_ERR_STAT, + BD96801_PRSTB_ERR_STAT, + BD96801_DRMOS1_ERR_STAT, + BD96801_DRMOS2_ERR_STAT, + BD96801_SLAVE_ERR_STAT, + BD96801_VREF_ERR_STAT, + BD96801_TSD_ERR_STAT, + BD96801_UVLO_ERR_STAT, + BD96801_OVLO_ERR_STAT, + BD96801_OSC_ERR_STAT, + BD96801_PON_ERR_STAT, + BD96801_POFF_ERR_STAT, + BD96801_CMD_SHDN_ERR_STAT, + BD96801_INT_PRSTB_WDT_ERR, + BD96801_INT_CHIP_IF_ERR, + BD96801_INT_SHDN_ERR_STAT, + + /* Reg 0x55 BUCK1 ERR IRQs */ + BD96801_BUCK1_PVIN_ERR_STAT, + BD96801_BUCK1_OVP_ERR_STAT, + BD96801_BUCK1_UVP_ERR_STAT, + BD96801_BUCK1_SHDN_ERR_STAT, + + /* Reg 0x56 BUCK2 ERR IRQs */ + BD96801_BUCK2_PVIN_ERR_STAT, + BD96801_BUCK2_OVP_ERR_STAT, + BD96801_BUCK2_UVP_ERR_STAT, + BD96801_BUCK2_SHDN_ERR_STAT, + + /* Reg 0x57 BUCK3 ERR IRQs */ + BD96801_BUCK3_PVIN_ERR_STAT, + BD96801_BUCK3_OVP_ERR_STAT, + BD96801_BUCK3_UVP_ERR_STAT, + BD96801_BUCK3_SHDN_ERR_STAT, + + /* Reg 0x58 BUCK4 ERR IRQs */ + BD96801_BUCK4_PVIN_ERR_STAT, + BD96801_BUCK4_OVP_ERR_STAT, + BD96801_BUCK4_UVP_ERR_STAT, + BD96801_BUCK4_SHDN_ERR_STAT, + + /* Reg 0x59 LDO5 ERR IRQs */ + BD96801_LDO5_PVIN_ERR_STAT, + BD96801_LDO5_OVP_ERR_STAT, + BD96801_LDO5_UVP_ERR_STAT, + BD96801_LDO5_SHDN_ERR_STAT, + + /* Reg 0x5a LDO6 ERR IRQs */ + BD96801_LDO6_PVIN_ERR_STAT, + BD96801_LDO6_OVP_ERR_STAT, + BD96801_LDO6_UVP_ERR_STAT, + BD96801_LDO6_SHDN_ERR_STAT, + + /* Reg 0x5b LDO7 ERR IRQs */ + BD96801_LDO7_PVIN_ERR_STAT, + BD96801_LDO7_OVP_ERR_STAT, + BD96801_LDO7_UVP_ERR_STAT, + BD96801_LDO7_SHDN_ERR_STAT, +}; + +/* INTB IRQs */ +enum { + /* Reg 0x5c (System INTB) */ + BD96801_TW_STAT, + BD96801_WDT_ERR_STAT, + BD96801_I2C_ERR_STAT, + BD96801_CHIP_IF_ERR_STAT, + + /* Reg 0x5d (BUCK1 INTB) */ + BD96801_BUCK1_OCPH_STAT, + BD96801_BUCK1_OCPL_STAT, + BD96801_BUCK1_OCPN_STAT, + BD96801_BUCK1_OVD_STAT, + BD96801_BUCK1_UVD_STAT, + BD96801_BUCK1_TW_CH_STAT, + + /* Reg 0x5e (BUCK2 INTB) */ + BD96801_BUCK2_OCPH_STAT, + BD96801_BUCK2_OCPL_STAT, + BD96801_BUCK2_OCPN_STAT, + BD96801_BUCK2_OVD_STAT, + BD96801_BUCK2_UVD_STAT, + BD96801_BUCK2_TW_CH_STAT, + + /* Reg 0x5f (BUCK3 INTB)*/ + BD96801_BUCK3_OCPH_STAT, + BD96801_BUCK3_OCPL_STAT, + BD96801_BUCK3_OCPN_STAT, + BD96801_BUCK3_OVD_STAT, + BD96801_BUCK3_UVD_STAT, + BD96801_BUCK3_TW_CH_STAT, + + /* Reg 0x60 (BUCK4 INTB)*/ + BD96801_BUCK4_OCPH_STAT, + BD96801_BUCK4_OCPL_STAT, + BD96801_BUCK4_OCPN_STAT, + BD96801_BUCK4_OVD_STAT, + BD96801_BUCK4_UVD_STAT, + BD96801_BUCK4_TW_CH_STAT, + + /* Reg 0x61 (LDO5 INTB) */ + BD96801_LDO5_OCPH_STAT, /* bit [0] */ + BD96801_LDO5_OVD_STAT, /* bit [3] */ + BD96801_LDO5_UVD_STAT, /* bit [4] */ + + /* Reg 0x62 (LDO6 INTB) */ + BD96801_LDO6_OCPH_STAT, /* bit [0] */ + BD96801_LDO6_OVD_STAT, /* bit [3] */ + BD96801_LDO6_UVD_STAT, /* bit [4] */ + + /* Reg 0x63 (LDO7 INTB) */ + BD96801_LDO7_OCPH_STAT, /* bit [0] */ + BD96801_LDO7_OVD_STAT, /* bit [3] */ + BD96801_LDO7_UVD_STAT, /* bit [4] */ +}; + +/* IRQ MASKs */ +#define BD96801_TW_STAT_MASK BIT(0) +#define BD96801_WDT_ERR_STAT_MASK BIT(1) +#define BD96801_I2C_ERR_STAT_MASK BIT(2) +#define BD96801_CHIP_IF_ERR_STAT_MASK BIT(3) + +#define BD96801_BUCK_OCPH_STAT_MASK BIT(0) +#define BD96801_BUCK_OCPL_STAT_MASK BIT(1) +#define BD96801_BUCK_OCPN_STAT_MASK BIT(2) +#define BD96801_BUCK_OVD_STAT_MASK BIT(3) +#define BD96801_BUCK_UVD_STAT_MASK BIT(4) +#define BD96801_BUCK_TW_CH_STAT_MASK BIT(5) + +#define BD96801_LDO_OCPH_STAT_MASK BIT(0) +#define BD96801_LDO_OVD_STAT_MASK BIT(3) +#define BD96801_LDO_UVD_STAT_MASK BIT(4) + +#endif diff --git a/include/linux/mfd/rohm-generic.h b/include/linux/mfd/rohm-generic.h index 4eeb22876bad..e7d4e6afe388 100644 --- a/include/linux/mfd/rohm-generic.h +++ b/include/linux/mfd/rohm-generic.h @@ -16,6 +16,7 @@ enum rohm_chip_type { ROHM_CHIP_TYPE_BD71828, ROHM_CHIP_TYPE_BD71837, ROHM_CHIP_TYPE_BD71847, + ROHM_CHIP_TYPE_BD96801, ROHM_CHIP_TYPE_AMOUNT }; diff --git a/include/linux/mfd/samsung/core.h b/include/linux/mfd/samsung/core.h index a212b9f72bc9..750274d41fc0 100644 --- a/include/linux/mfd/samsung/core.h +++ b/include/linux/mfd/samsung/core.h @@ -37,6 +37,7 @@ struct gpio_desc; enum sec_device_type { S5M8767X, + S2DOS05, S2MPA01, S2MPS11X, S2MPS13X, diff --git a/include/linux/mfd/stm32-timers.h b/include/linux/mfd/stm32-timers.h index ca35af30745f..f09ba598c97a 100644 --- a/include/linux/mfd/stm32-timers.h +++ b/include/linux/mfd/stm32-timers.h @@ -12,84 +12,106 @@ #include <linux/dma-mapping.h> #include <linux/regmap.h> -#define TIM_CR1 0x00 /* Control Register 1 */ -#define TIM_CR2 0x04 /* Control Register 2 */ -#define TIM_SMCR 0x08 /* Slave mode control reg */ -#define TIM_DIER 0x0C /* DMA/interrupt register */ -#define TIM_SR 0x10 /* Status register */ -#define TIM_EGR 0x14 /* Event Generation Reg */ -#define TIM_CCMR1 0x18 /* Capt/Comp 1 Mode Reg */ -#define TIM_CCMR2 0x1C /* Capt/Comp 2 Mode Reg */ -#define TIM_CCER 0x20 /* Capt/Comp Enable Reg */ -#define TIM_CNT 0x24 /* Counter */ -#define TIM_PSC 0x28 /* Prescaler */ -#define TIM_ARR 0x2c /* Auto-Reload Register */ -#define TIM_CCR1 0x34 /* Capt/Comp Register 1 */ -#define TIM_CCR2 0x38 /* Capt/Comp Register 2 */ -#define TIM_CCR3 0x3C /* Capt/Comp Register 3 */ -#define TIM_CCR4 0x40 /* Capt/Comp Register 4 */ -#define TIM_BDTR 0x44 /* Break and Dead-Time Reg */ -#define TIM_DCR 0x48 /* DMA control register */ -#define TIM_DMAR 0x4C /* DMA register for transfer */ -#define TIM_TISEL 0x68 /* Input Selection */ +#define TIM_CR1 0x00 /* Control Register 1 */ +#define TIM_CR2 0x04 /* Control Register 2 */ +#define TIM_SMCR 0x08 /* Slave mode control reg */ +#define TIM_DIER 0x0C /* DMA/interrupt register */ +#define TIM_SR 0x10 /* Status register */ +#define TIM_EGR 0x14 /* Event Generation Reg */ +#define TIM_CCMR1 0x18 /* Capt/Comp 1 Mode Reg */ +#define TIM_CCMR2 0x1C /* Capt/Comp 2 Mode Reg */ +#define TIM_CCER 0x20 /* Capt/Comp Enable Reg */ +#define TIM_CNT 0x24 /* Counter */ +#define TIM_PSC 0x28 /* Prescaler */ +#define TIM_ARR 0x2c /* Auto-Reload Register */ +#define TIM_CCRx(x) (0x34 + 4 * ((x) - 1)) /* Capt/Comp Register x (x ∈ {1, .. 4}) */ +#define TIM_CCR1 TIM_CCRx(1) /* Capt/Comp Register 1 */ +#define TIM_CCR2 TIM_CCRx(2) /* Capt/Comp Register 2 */ +#define TIM_CCR3 TIM_CCRx(3) /* Capt/Comp Register 3 */ +#define TIM_CCR4 TIM_CCRx(4) /* Capt/Comp Register 4 */ +#define TIM_BDTR 0x44 /* Break and Dead-Time Reg */ +#define TIM_DCR 0x48 /* DMA control register */ +#define TIM_DMAR 0x4C /* DMA register for transfer */ +#define TIM_TISEL 0x68 /* Input Selection */ -#define TIM_CR1_CEN BIT(0) /* Counter Enable */ -#define TIM_CR1_DIR BIT(4) /* Counter Direction */ -#define TIM_CR1_ARPE BIT(7) /* Auto-reload Preload Ena */ -#define TIM_CR2_MMS (BIT(4) | BIT(5) | BIT(6)) /* Master mode selection */ -#define TIM_CR2_MMS2 GENMASK(23, 20) /* Master mode selection 2 */ -#define TIM_SMCR_SMS (BIT(0) | BIT(1) | BIT(2)) /* Slave mode selection */ -#define TIM_SMCR_TS (BIT(4) | BIT(5) | BIT(6)) /* Trigger selection */ -#define TIM_DIER_UIE BIT(0) /* Update interrupt */ -#define TIM_DIER_UDE BIT(8) /* Update DMA request Enable */ -#define TIM_DIER_CC1DE BIT(9) /* CC1 DMA request Enable */ -#define TIM_DIER_CC2DE BIT(10) /* CC2 DMA request Enable */ -#define TIM_DIER_CC3DE BIT(11) /* CC3 DMA request Enable */ -#define TIM_DIER_CC4DE BIT(12) /* CC4 DMA request Enable */ -#define TIM_DIER_COMDE BIT(13) /* COM DMA request Enable */ -#define TIM_DIER_TDE BIT(14) /* Trigger DMA request Enable */ -#define TIM_SR_UIF BIT(0) /* Update interrupt flag */ -#define TIM_EGR_UG BIT(0) /* Update Generation */ -#define TIM_CCMR_PE BIT(3) /* Channel Preload Enable */ -#define TIM_CCMR_M1 (BIT(6) | BIT(5)) /* Channel PWM Mode 1 */ -#define TIM_CCMR_CC1S (BIT(0) | BIT(1)) /* Capture/compare 1 sel */ -#define TIM_CCMR_IC1PSC GENMASK(3, 2) /* Input capture 1 prescaler */ -#define TIM_CCMR_CC2S (BIT(8) | BIT(9)) /* Capture/compare 2 sel */ -#define TIM_CCMR_IC2PSC GENMASK(11, 10) /* Input capture 2 prescaler */ -#define TIM_CCMR_CC1S_TI1 BIT(0) /* IC1/IC3 selects TI1/TI3 */ -#define TIM_CCMR_CC1S_TI2 BIT(1) /* IC1/IC3 selects TI2/TI4 */ -#define TIM_CCMR_CC2S_TI2 BIT(8) /* IC2/IC4 selects TI2/TI4 */ -#define TIM_CCMR_CC2S_TI1 BIT(9) /* IC2/IC4 selects TI1/TI3 */ -#define TIM_CCER_CC1E BIT(0) /* Capt/Comp 1 out Ena */ -#define TIM_CCER_CC1P BIT(1) /* Capt/Comp 1 Polarity */ -#define TIM_CCER_CC1NE BIT(2) /* Capt/Comp 1N out Ena */ -#define TIM_CCER_CC1NP BIT(3) /* Capt/Comp 1N Polarity */ -#define TIM_CCER_CC2E BIT(4) /* Capt/Comp 2 out Ena */ -#define TIM_CCER_CC2P BIT(5) /* Capt/Comp 2 Polarity */ -#define TIM_CCER_CC3E BIT(8) /* Capt/Comp 3 out Ena */ -#define TIM_CCER_CC3P BIT(9) /* Capt/Comp 3 Polarity */ -#define TIM_CCER_CC4E BIT(12) /* Capt/Comp 4 out Ena */ -#define TIM_CCER_CC4P BIT(13) /* Capt/Comp 4 Polarity */ -#define TIM_CCER_CCXE (BIT(0) | BIT(4) | BIT(8) | BIT(12)) -#define TIM_BDTR_BKE(x) BIT(12 + (x) * 12) /* Break input enable */ -#define TIM_BDTR_BKP(x) BIT(13 + (x) * 12) /* Break input polarity */ -#define TIM_BDTR_AOE BIT(14) /* Automatic Output Enable */ -#define TIM_BDTR_MOE BIT(15) /* Main Output Enable */ -#define TIM_BDTR_BKF(x) (0xf << (16 + (x) * 4)) -#define TIM_DCR_DBA GENMASK(4, 0) /* DMA base addr */ -#define TIM_DCR_DBL GENMASK(12, 8) /* DMA burst len */ +#define TIM_CR1_CEN BIT(0) /* Counter Enable */ +#define TIM_CR1_DIR BIT(4) /* Counter Direction */ +#define TIM_CR1_ARPE BIT(7) /* Auto-reload Preload Ena */ +#define TIM_CR2_MMS (BIT(4) | BIT(5) | BIT(6)) /* Master mode selection */ +#define TIM_CR2_MMS2 GENMASK(23, 20) /* Master mode selection 2 */ +#define TIM_SMCR_SMS (BIT(0) | BIT(1) | BIT(2)) /* Slave mode selection */ +#define TIM_SMCR_TS (BIT(4) | BIT(5) | BIT(6)) /* Trigger selection */ +#define TIM_DIER_UIE BIT(0) /* Update interrupt */ +#define TIM_DIER_CCxIE(x) BIT(1 + ((x) - 1)) /* CCx Interrupt Enable (x ∈ {1, .. 4}) */ +#define TIM_DIER_CC1IE TIM_DIER_CCxIE(1) /* CC1 Interrupt Enable */ +#define TIM_DIER_CC2IE TIM_DIER_CCxIE(2) /* CC2 Interrupt Enable */ +#define TIM_DIER_CC3IE TIM_DIER_CCxIE(3) /* CC3 Interrupt Enable */ +#define TIM_DIER_CC4IE TIM_DIER_CCxIE(4) /* CC4 Interrupt Enable */ +#define TIM_DIER_UDE BIT(8) /* Update DMA request Enable */ +#define TIM_DIER_CCxDE(x) BIT(9 + ((x) - 1)) /* CCx DMA request Enable (x ∈ {1, .. 4}) */ +#define TIM_DIER_CC1DE TIM_DIER_CCxDE(1) /* CC1 DMA request Enable */ +#define TIM_DIER_CC2DE TIM_DIER_CCxDE(2) /* CC2 DMA request Enable */ +#define TIM_DIER_CC3DE TIM_DIER_CCxDE(3) /* CC3 DMA request Enable */ +#define TIM_DIER_CC4DE TIM_DIER_CCxDE(4) /* CC4 DMA request Enable */ +#define TIM_DIER_COMDE BIT(13) /* COM DMA request Enable */ +#define TIM_DIER_TDE BIT(14) /* Trigger DMA request Enable */ +#define TIM_SR_UIF BIT(0) /* Update interrupt flag */ +#define TIM_SR_CC_IF(x) BIT((x) + 1) /* CC1, CC2, CC3, CC4 interrupt flag */ +#define TIM_EGR_UG BIT(0) /* Update Generation */ +#define TIM_CCMR_PE BIT(3) /* Channel Preload Enable */ +#define TIM_CCMR_M1 (BIT(6) | BIT(5)) /* Channel PWM Mode 1 */ +#define TIM_CCMR_CC1S (BIT(0) | BIT(1)) /* Capture/compare 1 sel */ +#define TIM_CCMR_IC1PSC GENMASK(3, 2) /* Input capture 1 prescaler */ +#define TIM_CCMR_CC2S (BIT(8) | BIT(9)) /* Capture/compare 2 sel */ +#define TIM_CCMR_IC2PSC GENMASK(11, 10) /* Input capture 2 prescaler */ +#define TIM_CCMR_CC1S_TI1 BIT(0) /* IC1/IC3 selects TI1/TI3 */ +#define TIM_CCMR_CC1S_TI2 BIT(1) /* IC1/IC3 selects TI2/TI4 */ +#define TIM_CCMR_CC2S_TI2 BIT(8) /* IC2/IC4 selects TI2/TI4 */ +#define TIM_CCMR_CC2S_TI1 BIT(9) /* IC2/IC4 selects TI1/TI3 */ +#define TIM_CCMR_CC3S (BIT(0) | BIT(1)) /* Capture/compare 3 sel */ +#define TIM_CCMR_CC4S (BIT(8) | BIT(9)) /* Capture/compare 4 sel */ +#define TIM_CCMR_CC3S_TI3 BIT(0) /* IC3 selects TI3 */ +#define TIM_CCMR_CC4S_TI4 BIT(8) /* IC4 selects TI4 */ +#define TIM_CCER_CCxE(x) BIT(0 + 4 * ((x) - 1)) /* Capt/Comp x out Ena (x ∈ {1, .. 4}) */ +#define TIM_CCER_CCxP(x) BIT(1 + 4 * ((x) - 1)) /* Capt/Comp x Polarity (x ∈ {1, .. 4}) */ +#define TIM_CCER_CCxNE(x) BIT(2 + 4 * ((x) - 1)) /* Capt/Comp xN out Ena (x ∈ {1, .. 4}) */ +#define TIM_CCER_CCxNP(x) BIT(3 + 4 * ((x) - 1)) /* Capt/Comp xN Polarity (x ∈ {1, .. 4}) */ +#define TIM_CCER_CC1E TIM_CCER_CCxE(1) /* Capt/Comp 1 out Ena */ +#define TIM_CCER_CC1P TIM_CCER_CCxP(1) /* Capt/Comp 1 Polarity */ +#define TIM_CCER_CC1NE TIM_CCER_CCxNE(1) /* Capt/Comp 1N out Ena */ +#define TIM_CCER_CC1NP TIM_CCER_CCxNP(1) /* Capt/Comp 1N Polarity */ +#define TIM_CCER_CC2E TIM_CCER_CCxE(2) /* Capt/Comp 2 out Ena */ +#define TIM_CCER_CC2P TIM_CCER_CCxP(2) /* Capt/Comp 2 Polarity */ +#define TIM_CCER_CC2NE TIM_CCER_CCxNE(2) /* Capt/Comp 2N out Ena */ +#define TIM_CCER_CC2NP TIM_CCER_CCxNP(2) /* Capt/Comp 2N Polarity */ +#define TIM_CCER_CC3E TIM_CCER_CCxE(3) /* Capt/Comp 3 out Ena */ +#define TIM_CCER_CC3P TIM_CCER_CCxP(3) /* Capt/Comp 3 Polarity */ +#define TIM_CCER_CC3NE TIM_CCER_CCxNE(3) /* Capt/Comp 3N out Ena */ +#define TIM_CCER_CC3NP TIM_CCER_CCxNP(3) /* Capt/Comp 3N Polarity */ +#define TIM_CCER_CC4E TIM_CCER_CCxE(4) /* Capt/Comp 4 out Ena */ +#define TIM_CCER_CC4P TIM_CCER_CCxP(4) /* Capt/Comp 4 Polarity */ +#define TIM_CCER_CC4NE TIM_CCER_CCxNE(4) /* Capt/Comp 4N out Ena */ +#define TIM_CCER_CC4NP TIM_CCER_CCxNP(4) /* Capt/Comp 4N Polarity */ +#define TIM_CCER_CCXE (BIT(0) | BIT(4) | BIT(8) | BIT(12)) +#define TIM_BDTR_BKE(x) BIT(12 + (x) * 12) /* Break input enable */ +#define TIM_BDTR_BKP(x) BIT(13 + (x) * 12) /* Break input polarity */ +#define TIM_BDTR_AOE BIT(14) /* Automatic Output Enable */ +#define TIM_BDTR_MOE BIT(15) /* Main Output Enable */ +#define TIM_BDTR_BKF(x) (0xf << (16 + (x) * 4)) +#define TIM_DCR_DBA GENMASK(4, 0) /* DMA base addr */ +#define TIM_DCR_DBL GENMASK(12, 8) /* DMA burst len */ -#define MAX_TIM_PSC 0xFFFF -#define MAX_TIM_ICPSC 0x3 -#define TIM_CR2_MMS_SHIFT 4 -#define TIM_CR2_MMS2_SHIFT 20 +#define MAX_TIM_PSC 0xFFFF +#define MAX_TIM_ICPSC 0x3 +#define TIM_CR2_MMS_SHIFT 4 +#define TIM_CR2_MMS2_SHIFT 20 #define TIM_SMCR_SMS_SLAVE_MODE_DISABLED 0 /* counts on internal clock when CEN=1 */ #define TIM_SMCR_SMS_ENCODER_MODE_1 1 /* counts TI1FP1 edges, depending on TI2FP2 level */ #define TIM_SMCR_SMS_ENCODER_MODE_2 2 /* counts TI2FP2 edges, depending on TI1FP1 level */ #define TIM_SMCR_SMS_ENCODER_MODE_3 3 /* counts on both TI1FP1 and TI2FP2 edges */ -#define TIM_SMCR_TS_SHIFT 4 -#define TIM_BDTR_BKF_MASK 0xF -#define TIM_BDTR_BKF_SHIFT(x) (16 + (x) * 4) +#define TIM_SMCR_TS_SHIFT 4 +#define TIM_BDTR_BKF_MASK 0xF +#define TIM_BDTR_BKF_SHIFT(x) (16 + (x) * 4) enum stm32_timers_dmas { STM32_TIMERS_DMA_CH1, diff --git a/include/linux/mfd/syscon.h b/include/linux/mfd/syscon.h index c315903f6dab..aad9c6b50463 100644 --- a/include/linux/mfd/syscon.h +++ b/include/linux/mfd/syscon.h @@ -28,6 +28,8 @@ struct regmap *syscon_regmap_lookup_by_phandle_args(struct device_node *np, unsigned int *out_args); struct regmap *syscon_regmap_lookup_by_phandle_optional(struct device_node *np, const char *property); +int of_syscon_register_regmap(struct device_node *np, + struct regmap *regmap); #else static inline struct regmap *device_node_to_regmap(struct device_node *np) { @@ -67,6 +69,12 @@ static inline struct regmap *syscon_regmap_lookup_by_phandle_optional( return NULL; } +static inline int of_syscon_register_regmap(struct device_node *np, + struct regmap *regmap) +{ + return -EOPNOTSUPP; +} + #endif #endif /* __LINUX_MFD_SYSCON_H__ */ diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h deleted file mode 100644 index eace8ea6cda0..000000000000 --- a/include/linux/mfd/tmio.h +++ /dev/null @@ -1,133 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef MFD_TMIO_H -#define MFD_TMIO_H - -#include <linux/device.h> -#include <linux/fb.h> -#include <linux/io.h> -#include <linux/jiffies.h> -#include <linux/mmc/card.h> -#include <linux/platform_device.h> -#include <linux/pm_runtime.h> - -#define tmio_ioread8(addr) readb(addr) -#define tmio_ioread16(addr) readw(addr) -#define tmio_ioread16_rep(r, b, l) readsw(r, b, l) -#define tmio_ioread32(addr) \ - (((u32)readw((addr))) | (((u32)readw((addr) + 2)) << 16)) - -#define tmio_iowrite8(val, addr) writeb((val), (addr)) -#define tmio_iowrite16(val, addr) writew((val), (addr)) -#define tmio_iowrite16_rep(r, b, l) writesw(r, b, l) -#define tmio_iowrite32(val, addr) \ - do { \ - writew((val), (addr)); \ - writew((val) >> 16, (addr) + 2); \ - } while (0) - -#define sd_config_write8(base, shift, reg, val) \ - tmio_iowrite8((val), (base) + ((reg) << (shift))) -#define sd_config_write16(base, shift, reg, val) \ - tmio_iowrite16((val), (base) + ((reg) << (shift))) -#define sd_config_write32(base, shift, reg, val) \ - do { \ - tmio_iowrite16((val), (base) + ((reg) << (shift))); \ - tmio_iowrite16((val) >> 16, (base) + ((reg + 2) << (shift))); \ - } while (0) - -/* tmio MMC platform flags */ -/* - * Some controllers can support a 2-byte block size when the bus width - * is configured in 4-bit mode. - */ -#define TMIO_MMC_BLKSZ_2BYTES BIT(1) -/* - * Some controllers can support SDIO IRQ signalling. - */ -#define TMIO_MMC_SDIO_IRQ BIT(2) - -/* Some features are only available or tested on R-Car Gen2 or later */ -#define TMIO_MMC_MIN_RCAR2 BIT(3) - -/* - * Some controllers require waiting for the SD bus to become - * idle before writing to some registers. - */ -#define TMIO_MMC_HAS_IDLE_WAIT BIT(4) - -/* - * Use the busy timeout feature. Probably all TMIO versions support it. Yet, - * we don't have documentation for old variants, so we enable only known good - * variants with this flag. Can be removed once all variants are known good. - */ -#define TMIO_MMC_USE_BUSY_TIMEOUT BIT(5) - -/* - * Some controllers have CMD12 automatically - * issue/non-issue register - */ -#define TMIO_MMC_HAVE_CMD12_CTRL BIT(7) - -/* Controller has some SDIO status bits which must be 1 */ -#define TMIO_MMC_SDIO_STATUS_SETBITS BIT(8) - -/* - * Some controllers have a 32-bit wide data port register - */ -#define TMIO_MMC_32BIT_DATA_PORT BIT(9) - -/* - * Some controllers allows to set SDx actual clock - */ -#define TMIO_MMC_CLK_ACTUAL BIT(10) - -/* Some controllers have a CBSY bit */ -#define TMIO_MMC_HAVE_CBSY BIT(11) - -struct dma_chan; - -/* - * data for the MMC controller - */ -struct tmio_mmc_data { - void *chan_priv_tx; - void *chan_priv_rx; - unsigned int hclk; - unsigned long capabilities; - unsigned long capabilities2; - unsigned long flags; - u32 ocr_mask; /* available voltages */ - dma_addr_t dma_rx_offset; - unsigned int max_blk_count; - unsigned short max_segs; - void (*set_pwr)(struct platform_device *host, int state); - void (*set_clk_div)(struct platform_device *host, int state); -}; - -/* - * data for the NAND controller - */ -struct tmio_nand_data { - struct nand_bbt_descr *badblock_pattern; - struct mtd_partition *partition; - unsigned int num_partitions; - const char *const *part_parsers; -}; - -#define FBIO_TMIO_ACC_WRITE 0x7C639300 -#define FBIO_TMIO_ACC_SYNC 0x7C639301 - -struct tmio_fb_data { - int (*lcd_set_power)(struct platform_device *fb_dev, - bool on); - int (*lcd_mode)(struct platform_device *fb_dev, - const struct fb_videomode *mode); - int num_modes; - struct fb_videomode *modes; - - /* in mm: size of screen */ - int height; - int width; -}; - -#endif diff --git a/include/linux/mfd/tps65219.h b/include/linux/mfd/tps65219.h index e6826e34e2a6..546bceec7173 100644 --- a/include/linux/mfd/tps65219.h +++ b/include/linux/mfd/tps65219.h @@ -10,14 +10,9 @@ #include <linux/bitops.h> #include <linux/notifier.h> +#include <linux/regmap.h> #include <linux/regulator/driver.h> -struct regmap; -struct regmap_irq_chip_data; - -#define TPS65219_1V35 1350000 -#define TPS65219_1V8 1800000 - /* TPS chip id list */ #define TPS65219 0xF0 diff --git a/include/linux/mfd/tps65912.h b/include/linux/mfd/tps65912.h index 860ec0a16c96..e5373c302722 100644 --- a/include/linux/mfd/tps65912.h +++ b/include/linux/mfd/tps65912.h @@ -314,6 +314,5 @@ struct tps65912 { extern const struct regmap_config tps65912_regmap_config; int tps65912_device_init(struct tps65912 *tps); -void tps65912_device_exit(struct tps65912 *tps); #endif /* __LINUX_MFD_TPS65912_H */ diff --git a/include/linux/mfd/tps6594.h b/include/linux/mfd/tps6594.h index 3f7c5e23cd4c..16543fd4d83e 100644 --- a/include/linux/mfd/tps6594.h +++ b/include/linux/mfd/tps6594.h @@ -18,12 +18,13 @@ enum pmic_id { TPS6594, TPS6593, LP8764, + TPS65224, }; /* Macro to get page index from register address */ #define TPS6594_REG_TO_PAGE(reg) ((reg) >> 8) -/* Registers for page 0 of TPS6594 */ +/* Registers for page 0 */ #define TPS6594_REG_DEV_REV 0x01 #define TPS6594_REG_NVM_CODE_1 0x02 @@ -56,9 +57,6 @@ enum pmic_id { #define TPS6594_REG_GPIOX_OUT(gpio_inst) (TPS6594_REG_GPIO_OUT_1 + (gpio_inst) / 8) #define TPS6594_REG_GPIOX_IN(gpio_inst) (TPS6594_REG_GPIO_IN_1 + (gpio_inst) / 8) -#define TPS6594_REG_GPIO_IN_1 0x3f -#define TPS6594_REG_GPIO_IN_2 0x40 - #define TPS6594_REG_RAIL_SEL_1 0x41 #define TPS6594_REG_RAIL_SEL_2 0x42 #define TPS6594_REG_RAIL_SEL_3 0x43 @@ -70,13 +68,15 @@ enum pmic_id { #define TPS6594_REG_FSM_TRIG_MASK_3 0x48 #define TPS6594_REG_MASK_BUCK1_2 0x49 +#define TPS65224_REG_MASK_BUCKS 0x49 #define TPS6594_REG_MASK_BUCK3_4 0x4a #define TPS6594_REG_MASK_BUCK5 0x4b #define TPS6594_REG_MASK_LDO1_2 0x4c +#define TPS65224_REG_MASK_LDOS 0x4c #define TPS6594_REG_MASK_LDO3_4 0x4d #define TPS6594_REG_MASK_VMON 0x4e -#define TPS6594_REG_MASK_GPIO1_8_FALL 0x4f -#define TPS6594_REG_MASK_GPIO1_8_RISE 0x50 +#define TPS6594_REG_MASK_GPIO_FALL 0x4f +#define TPS6594_REG_MASK_GPIO_RISE 0x50 #define TPS6594_REG_MASK_GPIO9_11 0x51 #define TPS6594_REG_MASK_STARTUP 0x52 #define TPS6594_REG_MASK_MISC 0x53 @@ -174,6 +174,10 @@ enum pmic_id { #define TPS6594_REG_REGISTER_LOCK 0xa1 +#define TPS65224_REG_SRAM_ACCESS_1 0xa2 +#define TPS65224_REG_SRAM_ACCESS_2 0xa3 +#define TPS65224_REG_SRAM_ADDR_CTRL 0xa4 +#define TPS65224_REG_RECOV_CNT_PFSM_INCR 0xa5 #define TPS6594_REG_MANUFACTURING_VER 0xa6 #define TPS6594_REG_CUSTOMER_NVM_ID_REG 0xa7 @@ -182,6 +186,9 @@ enum pmic_id { #define TPS6594_REG_SOFT_REBOOT_REG 0xab +#define TPS65224_REG_ADC_CTRL 0xac +#define TPS65224_REG_ADC_RESULT_REG_1 0xad +#define TPS65224_REG_ADC_RESULT_REG_2 0xae #define TPS6594_REG_RTC_SECONDS 0xb5 #define TPS6594_REG_RTC_MINUTES 0xb6 #define TPS6594_REG_RTC_HOURS 0xb7 @@ -199,6 +206,7 @@ enum pmic_id { #define TPS6594_REG_RTC_CTRL_1 0xc2 #define TPS6594_REG_RTC_CTRL_2 0xc3 +#define TPS65224_REG_STARTUP_CTRL 0xc3 #define TPS6594_REG_RTC_STATUS 0xc4 #define TPS6594_REG_RTC_INTERRUPTS 0xc5 #define TPS6594_REG_RTC_COMP_LSB 0xc6 @@ -214,13 +222,17 @@ enum pmic_id { #define TPS6594_REG_PFSM_DELAY_REG_2 0xce #define TPS6594_REG_PFSM_DELAY_REG_3 0xcf #define TPS6594_REG_PFSM_DELAY_REG_4 0xd0 +#define TPS65224_REG_ADC_GAIN_COMP_REG 0xd0 +#define TPS65224_REG_CRC_CALC_CONTROL 0xef +#define TPS65224_REG_REGMAP_USER_CRC_LOW 0xf0 +#define TPS65224_REG_REGMAP_USER_CRC_HIGH 0xf1 -/* Registers for page 1 of TPS6594 */ +/* Registers for page 1 */ #define TPS6594_REG_SERIAL_IF_CONFIG 0x11a #define TPS6594_REG_I2C1_ID 0x122 #define TPS6594_REG_I2C2_ID 0x123 -/* Registers for page 4 of TPS6594 */ +/* Registers for page 4 */ #define TPS6594_REG_WD_ANSWER_REG 0x401 #define TPS6594_REG_WD_QUESTION_ANSW_CNT 0x402 #define TPS6594_REG_WD_WIN1_CFG 0x403 @@ -241,16 +253,26 @@ enum pmic_id { #define TPS6594_BIT_BUCK_PLDN BIT(5) #define TPS6594_BIT_BUCK_RV_SEL BIT(7) -/* BUCKX_CONF register field definition */ +/* TPS6594 BUCKX_CONF register field definition */ #define TPS6594_MASK_BUCK_SLEW_RATE GENMASK(2, 0) #define TPS6594_MASK_BUCK_ILIM GENMASK(5, 3) -/* BUCKX_PG_WINDOW register field definition */ +/* TPS65224 BUCKX_CONF register field definition */ +#define TPS65224_MASK_BUCK_SLEW_RATE GENMASK(1, 0) + +/* TPS6594 BUCKX_PG_WINDOW register field definition */ #define TPS6594_MASK_BUCK_OV_THR GENMASK(2, 0) #define TPS6594_MASK_BUCK_UV_THR GENMASK(5, 3) -/* BUCKX VSET */ -#define TPS6594_MASK_BUCKS_VSET GENMASK(7, 0) +/* TPS65224 BUCKX_PG_WINDOW register field definition */ +#define TPS65224_MASK_BUCK_VMON_THR GENMASK(1, 0) + +/* TPS6594 BUCKX_VOUT register field definition */ +#define TPS6594_MASK_BUCKS_VSET GENMASK(7, 0) + +/* TPS65224 BUCKX_VOUT register field definition */ +#define TPS65224_MASK_BUCK1_VSET GENMASK(7, 0) +#define TPS65224_MASK_BUCKS_VSET GENMASK(6, 0) /* LDOX_CTRL register field definition */ #define TPS6594_BIT_LDO_EN BIT(0) @@ -258,6 +280,7 @@ enum pmic_id { #define TPS6594_BIT_LDO_VMON_EN BIT(4) #define TPS6594_MASK_LDO_PLDN GENMASK(6, 5) #define TPS6594_BIT_LDO_RV_SEL BIT(7) +#define TPS65224_BIT_LDO_DISCHARGE_EN BIT(5) /* LDORTC_CTRL register field definition */ #define TPS6594_BIT_LDORTC_DIS BIT(0) @@ -271,6 +294,9 @@ enum pmic_id { #define TPS6594_MASK_LDO_OV_THR GENMASK(2, 0) #define TPS6594_MASK_LDO_UV_THR GENMASK(5, 3) +/* LDOX_PG_WINDOW register field definition */ +#define TPS65224_MASK_LDO_VMON_THR GENMASK(1, 0) + /* VCCA_VMON_CTRL register field definition */ #define TPS6594_BIT_VMON_EN BIT(0) #define TPS6594_BIT_VMON1_EN BIT(1) @@ -278,10 +304,12 @@ enum pmic_id { #define TPS6594_BIT_VMON2_EN BIT(3) #define TPS6594_BIT_VMON2_RV_SEL BIT(4) #define TPS6594_BIT_VMON_DEGLITCH_SEL BIT(5) +#define TPS65224_BIT_VMON_DEGLITCH_SEL GENMASK(7, 5) /* VCCA_PG_WINDOW register field definition */ #define TPS6594_MASK_VCCA_OV_THR GENMASK(2, 0) #define TPS6594_MASK_VCCA_UV_THR GENMASK(5, 3) +#define TPS65224_MASK_VCCA_VMON_THR GENMASK(1, 0) #define TPS6594_BIT_VCCA_PG_SET BIT(6) /* VMONX_PG_WINDOW register field definition */ @@ -289,6 +317,9 @@ enum pmic_id { #define TPS6594_MASK_VMONX_UV_THR GENMASK(5, 3) #define TPS6594_BIT_VMONX_RANGE BIT(6) +/* VMONX_PG_WINDOW register field definition */ +#define TPS65224_MASK_VMONX_THR GENMASK(1, 0) + /* GPIOX_CONF register field definition */ #define TPS6594_BIT_GPIO_DIR BIT(0) #define TPS6594_BIT_GPIO_OD BIT(1) @@ -296,6 +327,8 @@ enum pmic_id { #define TPS6594_BIT_GPIO_PU_PD_EN BIT(3) #define TPS6594_BIT_GPIO_DEGLITCH_EN BIT(4) #define TPS6594_MASK_GPIO_SEL GENMASK(7, 5) +#define TPS65224_MASK_GPIO_SEL GENMASK(6, 5) +#define TPS65224_MASK_GPIO_SEL_GPIO6 GENMASK(7, 5) /* NPWRON_CONF register field definition */ #define TPS6594_BIT_NRSTOUT_OD BIT(0) @@ -305,6 +338,12 @@ enum pmic_id { #define TPS6594_BIT_ENABLE_POL BIT(5) #define TPS6594_MASK_NPWRON_SEL GENMASK(7, 6) +/* POWER_ON_CONFIG register field definition */ +#define TPS65224_BIT_NINT_ENDRV_PU_SEL BIT(0) +#define TPS65224_BIT_NINT_ENDRV_SEL BIT(1) +#define TPS65224_BIT_EN_PB_DEGL BIT(5) +#define TPS65224_MASK_EN_PB_VSENSE_CONFIG GENMASK(7, 6) + /* GPIO_OUT_X register field definition */ #define TPS6594_BIT_GPIOX_OUT(gpio_inst) BIT((gpio_inst) % 8) @@ -312,6 +351,12 @@ enum pmic_id { #define TPS6594_BIT_GPIOX_IN(gpio_inst) BIT((gpio_inst) % 8) #define TPS6594_BIT_NPWRON_IN BIT(3) +/* GPIO_OUT_X register field definition */ +#define TPS65224_BIT_GPIOX_OUT(gpio_inst) BIT((gpio_inst)) + +/* GPIO_IN_X register field definition */ +#define TPS65224_BIT_GPIOX_IN(gpio_inst) BIT((gpio_inst)) + /* RAIL_SEL_1 register field definition */ #define TPS6594_MASK_BUCK1_GRP_SEL GENMASK(1, 0) #define TPS6594_MASK_BUCK2_GRP_SEL GENMASK(3, 2) @@ -343,6 +388,9 @@ enum pmic_id { #define TPS6594_BIT_GPIOX_FSM_MASK(gpio_inst) BIT(((gpio_inst) << 1) % 8) #define TPS6594_BIT_GPIOX_FSM_MASK_POL(gpio_inst) BIT(((gpio_inst) << 1) % 8 + 1) +#define TPS65224_BIT_GPIOX_FSM_MASK(gpio_inst) BIT(((gpio_inst) << 1) % 6) +#define TPS65224_BIT_GPIOX_FSM_MASK_POL(gpio_inst) BIT(((gpio_inst) << 1) % 6 + 1) + /* MASK_BUCKX register field definition */ #define TPS6594_BIT_BUCKX_OV_MASK(buck_inst) BIT(((buck_inst) << 2) % 8) #define TPS6594_BIT_BUCKX_UV_MASK(buck_inst) BIT(((buck_inst) << 2) % 8 + 1) @@ -361,22 +409,46 @@ enum pmic_id { #define TPS6594_BIT_VMON2_OV_MASK BIT(5) #define TPS6594_BIT_VMON2_UV_MASK BIT(6) +/* MASK_BUCK Register field definition */ +#define TPS65224_BIT_BUCK1_UVOV_MASK BIT(0) +#define TPS65224_BIT_BUCK2_UVOV_MASK BIT(1) +#define TPS65224_BIT_BUCK3_UVOV_MASK BIT(2) +#define TPS65224_BIT_BUCK4_UVOV_MASK BIT(4) + +/* MASK_LDO_VMON register field definition */ +#define TPS65224_BIT_LDO1_UVOV_MASK BIT(0) +#define TPS65224_BIT_LDO2_UVOV_MASK BIT(1) +#define TPS65224_BIT_LDO3_UVOV_MASK BIT(2) +#define TPS65224_BIT_VCCA_UVOV_MASK BIT(4) +#define TPS65224_BIT_VMON1_UVOV_MASK BIT(5) +#define TPS65224_BIT_VMON2_UVOV_MASK BIT(6) + /* MASK_GPIOX register field definition */ #define TPS6594_BIT_GPIOX_FALL_MASK(gpio_inst) BIT((gpio_inst) < 8 ? \ (gpio_inst) : (gpio_inst) % 8) #define TPS6594_BIT_GPIOX_RISE_MASK(gpio_inst) BIT((gpio_inst) < 8 ? \ (gpio_inst) : (gpio_inst) % 8 + 3) +/* MASK_GPIOX register field definition */ +#define TPS65224_BIT_GPIOX_FALL_MASK(gpio_inst) BIT((gpio_inst)) +#define TPS65224_BIT_GPIOX_RISE_MASK(gpio_inst) BIT((gpio_inst)) /* MASK_STARTUP register field definition */ #define TPS6594_BIT_NPWRON_START_MASK BIT(0) #define TPS6594_BIT_ENABLE_MASK BIT(1) #define TPS6594_BIT_FSD_MASK BIT(4) #define TPS6594_BIT_SOFT_REBOOT_MASK BIT(5) +#define TPS65224_BIT_VSENSE_MASK BIT(0) +#define TPS65224_BIT_PB_SHORT_MASK BIT(2) /* MASK_MISC register field definition */ #define TPS6594_BIT_BIST_PASS_MASK BIT(0) #define TPS6594_BIT_EXT_CLK_MASK BIT(1) +#define TPS65224_BIT_REG_UNLOCK_MASK BIT(2) #define TPS6594_BIT_TWARN_MASK BIT(3) +#define TPS65224_BIT_PB_LONG_MASK BIT(4) +#define TPS65224_BIT_PB_FALL_MASK BIT(5) +#define TPS65224_BIT_PB_RISE_MASK BIT(6) +#define TPS65224_BIT_ADC_CONV_READY_MASK BIT(7) /* MASK_MODERATE_ERR register field definition */ #define TPS6594_BIT_BIST_FAIL_MASK BIT(1) @@ -391,6 +463,8 @@ enum pmic_id { #define TPS6594_BIT_ORD_SHUTDOWN_MASK BIT(1) #define TPS6594_BIT_MCU_PWR_ERR_MASK BIT(2) #define TPS6594_BIT_SOC_PWR_ERR_MASK BIT(3) +#define TPS65224_BIT_COMM_ERR_MASK BIT(4) +#define TPS65224_BIT_I2C2_ERR_MASK BIT(5) /* MASK_COMM_ERR register field definition */ #define TPS6594_BIT_COMM_FRM_ERR_MASK BIT(0) @@ -426,6 +500,12 @@ enum pmic_id { #define TPS6594_BIT_BUCK3_4_INT BIT(1) #define TPS6594_BIT_BUCK5_INT BIT(2) +/* INT_BUCK register field definition */ +#define TPS65224_BIT_BUCK1_UVOV_INT BIT(0) +#define TPS65224_BIT_BUCK2_UVOV_INT BIT(1) +#define TPS65224_BIT_BUCK3_UVOV_INT BIT(2) +#define TPS65224_BIT_BUCK4_UVOV_INT BIT(3) + /* INT_BUCKX register field definition */ #define TPS6594_BIT_BUCKX_OV_INT(buck_inst) BIT(((buck_inst) << 2) % 8) #define TPS6594_BIT_BUCKX_UV_INT(buck_inst) BIT(((buck_inst) << 2) % 8 + 1) @@ -437,6 +517,14 @@ enum pmic_id { #define TPS6594_BIT_LDO3_4_INT BIT(1) #define TPS6594_BIT_VCCA_INT BIT(4) +/* INT_LDO_VMON register field definition */ +#define TPS65224_BIT_LDO1_UVOV_INT BIT(0) +#define TPS65224_BIT_LDO2_UVOV_INT BIT(1) +#define TPS65224_BIT_LDO3_UVOV_INT BIT(2) +#define TPS65224_BIT_VCCA_UVOV_INT BIT(4) +#define TPS65224_BIT_VMON1_UVOV_INT BIT(5) +#define TPS65224_BIT_VMON2_UVOV_INT BIT(6) + /* INT_LDOX register field definition */ #define TPS6594_BIT_LDOX_OV_INT(ldo_inst) BIT(((ldo_inst) << 2) % 8) #define TPS6594_BIT_LDOX_UV_INT(ldo_inst) BIT(((ldo_inst) << 2) % 8 + 1) @@ -462,17 +550,32 @@ enum pmic_id { /* INT_GPIOX register field definition */ #define TPS6594_BIT_GPIOX_INT(gpio_inst) BIT(gpio_inst) +/* INT_GPIO register field definition */ +#define TPS65224_BIT_GPIO1_INT BIT(0) +#define TPS65224_BIT_GPIO2_INT BIT(1) +#define TPS65224_BIT_GPIO3_INT BIT(2) +#define TPS65224_BIT_GPIO4_INT BIT(3) +#define TPS65224_BIT_GPIO5_INT BIT(4) +#define TPS65224_BIT_GPIO6_INT BIT(5) + /* INT_STARTUP register field definition */ #define TPS6594_BIT_NPWRON_START_INT BIT(0) +#define TPS65224_BIT_VSENSE_INT BIT(0) #define TPS6594_BIT_ENABLE_INT BIT(1) #define TPS6594_BIT_RTC_INT BIT(2) +#define TPS65224_BIT_PB_SHORT_INT BIT(2) #define TPS6594_BIT_FSD_INT BIT(4) #define TPS6594_BIT_SOFT_REBOOT_INT BIT(5) /* INT_MISC register field definition */ #define TPS6594_BIT_BIST_PASS_INT BIT(0) #define TPS6594_BIT_EXT_CLK_INT BIT(1) +#define TPS65224_BIT_REG_UNLOCK_INT BIT(2) #define TPS6594_BIT_TWARN_INT BIT(3) +#define TPS65224_BIT_PB_LONG_INT BIT(4) +#define TPS65224_BIT_PB_FALL_INT BIT(5) +#define TPS65224_BIT_PB_RISE_INT BIT(6) +#define TPS65224_BIT_ADC_CONV_READY_INT BIT(7) /* INT_MODERATE_ERR register field definition */ #define TPS6594_BIT_TSD_ORD_INT BIT(0) @@ -488,6 +591,7 @@ enum pmic_id { #define TPS6594_BIT_TSD_IMM_INT BIT(0) #define TPS6594_BIT_VCCA_OVP_INT BIT(1) #define TPS6594_BIT_PFSM_ERR_INT BIT(2) +#define TPS65224_BIT_BG_XMON_INT BIT(3) /* INT_FSM_ERR register field definition */ #define TPS6594_BIT_IMM_SHUTDOWN_INT BIT(0) @@ -496,6 +600,7 @@ enum pmic_id { #define TPS6594_BIT_SOC_PWR_ERR_INT BIT(3) #define TPS6594_BIT_COMM_ERR_INT BIT(4) #define TPS6594_BIT_READBACK_ERR_INT BIT(5) +#define TPS65224_BIT_I2C2_ERR_INT BIT(5) #define TPS6594_BIT_ESM_INT BIT(6) #define TPS6594_BIT_WD_INT BIT(7) @@ -536,8 +641,18 @@ enum pmic_id { #define TPS6594_BIT_VMON2_OV_STAT BIT(5) #define TPS6594_BIT_VMON2_UV_STAT BIT(6) +/* STAT_LDO_VMON register field definition */ +#define TPS65224_BIT_LDO1_UVOV_STAT BIT(0) +#define TPS65224_BIT_LDO2_UVOV_STAT BIT(1) +#define TPS65224_BIT_LDO3_UVOV_STAT BIT(2) +#define TPS65224_BIT_VCCA_UVOV_STAT BIT(4) +#define TPS65224_BIT_VMON1_UVOV_STAT BIT(5) +#define TPS65224_BIT_VMON2_UVOV_STAT BIT(6) + /* STAT_STARTUP register field definition */ +#define TPS65224_BIT_VSENSE_STAT BIT(0) #define TPS6594_BIT_ENABLE_STAT BIT(1) +#define TPS65224_BIT_PB_LEVEL_STAT BIT(2) /* STAT_MISC register field definition */ #define TPS6594_BIT_EXT_CLK_STAT BIT(1) @@ -549,6 +664,7 @@ enum pmic_id { /* STAT_SEVERE_ERR register field definition */ #define TPS6594_BIT_TSD_IMM_STAT BIT(0) #define TPS6594_BIT_VCCA_OVP_STAT BIT(1) +#define TPS65224_BIT_BG_XMON_STAT BIT(3) /* STAT_READBACK_ERR register field definition */ #define TPS6594_BIT_EN_DRV_READBACK_STAT BIT(0) @@ -597,6 +713,8 @@ enum pmic_id { #define TPS6594_BIT_BB_CHARGER_EN BIT(0) #define TPS6594_BIT_BB_ICHR BIT(1) #define TPS6594_MASK_BB_VEOC GENMASK(3, 2) +#define TPS65224_BIT_I2C1_SPI_CRC_EN BIT(4) +#define TPS65224_BIT_I2C2_CRC_EN BIT(5) #define TPS6594_BB_EOC_RDY BIT(7) /* ENABLE_DRV_REG register field definition */ @@ -617,6 +735,7 @@ enum pmic_id { #define TPS6594_BIT_NRSTOUT_SOC_IN BIT(2) #define TPS6594_BIT_FORCE_EN_DRV_LOW BIT(3) #define TPS6594_BIT_SPMI_LPM_EN BIT(4) +#define TPS65224_BIT_TSD_DISABLE BIT(5) /* RECOV_CNT_REG_1 register field definition */ #define TPS6594_MASK_RECOV_CNT GENMASK(3, 0) @@ -671,15 +790,27 @@ enum pmic_id { /* ESM_SOC_START_REG register field definition */ #define TPS6594_BIT_ESM_SOC_START BIT(0) +/* ESM_MCU_START_REG register field definition */ +#define TPS65224_BIT_ESM_MCU_START BIT(0) + /* ESM_SOC_MODE_CFG register field definition */ #define TPS6594_MASK_ESM_SOC_ERR_CNT_TH GENMASK(3, 0) #define TPS6594_BIT_ESM_SOC_ENDRV BIT(5) #define TPS6594_BIT_ESM_SOC_EN BIT(6) #define TPS6594_BIT_ESM_SOC_MODE BIT(7) +/* ESM_MCU_MODE_CFG register field definition */ +#define TPS65224_MASK_ESM_MCU_ERR_CNT_TH GENMASK(3, 0) +#define TPS65224_BIT_ESM_MCU_ENDRV BIT(5) +#define TPS65224_BIT_ESM_MCU_EN BIT(6) +#define TPS65224_BIT_ESM_MCU_MODE BIT(7) + /* ESM_SOC_ERR_CNT_REG register field definition */ #define TPS6594_MASK_ESM_SOC_ERR_CNT GENMASK(4, 0) +/* ESM_MCU_ERR_CNT_REG register field definition */ +#define TPS6594_MASK_ESM_MCU_ERR_CNT GENMASK(4, 0) + /* REGISTER_LOCK register field definition */ #define TPS6594_BIT_REGISTER_LOCK_STATUS BIT(0) @@ -687,6 +818,29 @@ enum pmic_id { #define TPS6594_MASK_VMON1_SLEW_RATE GENMASK(2, 0) #define TPS6594_MASK_VMON2_SLEW_RATE GENMASK(5, 3) +/* SRAM_ACCESS_1 Register field definition */ +#define TPS65224_MASk_SRAM_UNLOCK_SEQ GENMASK(7, 0) + +/* SRAM_ACCESS_2 Register field definition */ +#define TPS65224_BIT_SRAM_WRITE_MODE BIT(0) +#define TPS65224_BIT_OTP_PROG_USER BIT(1) +#define TPS65224_BIT_OTP_PROG_PFSM BIT(2) +#define TPS65224_BIT_OTP_PROG_STATUS BIT(3) +#define TPS65224_BIT_SRAM_UNLOCKED BIT(6) +#define TPS65224_USER_PROG_ALLOWED BIT(7) + +/* SRAM_ADDR_CTRL Register field definition */ +#define TPS65224_MASk_SRAM_SEL GENMASK(1, 0) + +/* RECOV_CNT_PFSM_INCR Register field definition */ +#define TPS65224_BIT_INCREMENT_RECOV_CNT BIT(0) + +/* MANUFACTURING_VER Register field definition */ +#define TPS65224_MASK_SILICON_REV GENMASK(7, 0) + +/* CUSTOMER_NVM_ID_REG Register field definition */ +#define TPS65224_MASK_CUSTOMER_NVM_ID GENMASK(7, 0) + /* SOFT_REBOOT_REG register field definition */ #define TPS6594_BIT_SOFT_REBOOT BIT(0) @@ -755,14 +909,83 @@ enum pmic_id { #define TPS6594_BIT_I2C2_CRC_EN BIT(2) #define TPS6594_MASK_T_CRC GENMASK(7, 3) +/* ADC_CTRL Register field definition */ +#define TPS65224_BIT_ADC_START BIT(0) +#define TPS65224_BIT_ADC_CONT_CONV BIT(1) +#define TPS65224_BIT_ADC_THERMAL_SEL BIT(2) +#define TPS65224_BIT_ADC_RDIV_EN BIT(3) +#define TPS65224_BIT_ADC_STATUS BIT(7) + +/* ADC_RESULT_REG_1 Register field definition */ +#define TPS65224_MASK_ADC_RESULT_11_4 GENMASK(7, 0) + +/* ADC_RESULT_REG_2 Register field definition */ +#define TPS65224_MASK_ADC_RESULT_3_0 GENMASK(7, 4) + +/* STARTUP_CTRL Register field definition */ +#define TPS65224_MASK_STARTUP_DEST GENMASK(6, 5) +#define TPS65224_BIT_FIRST_STARTUP_DONE BIT(7) + +/* SCRATCH_PAD_REG_1 Register field definition */ +#define TPS6594_MASK_SCRATCH_PAD_1 GENMASK(7, 0) + +/* SCRATCH_PAD_REG_2 Register field definition */ +#define TPS6594_MASK_SCRATCH_PAD_2 GENMASK(7, 0) + +/* SCRATCH_PAD_REG_3 Register field definition */ +#define TPS6594_MASK_SCRATCH_PAD_3 GENMASK(7, 0) + +/* SCRATCH_PAD_REG_4 Register field definition */ +#define TPS6594_MASK_SCRATCH_PAD_4 GENMASK(7, 0) + +/* PFSM_DELAY_REG_1 Register field definition */ +#define TPS6594_MASK_PFSM_DELAY1 GENMASK(7, 0) + +/* PFSM_DELAY_REG_2 Register field definition */ +#define TPS6594_MASK_PFSM_DELAY2 GENMASK(7, 0) + +/* PFSM_DELAY_REG_3 Register field definition */ +#define TPS6594_MASK_PFSM_DELAY3 GENMASK(7, 0) + +/* PFSM_DELAY_REG_4 Register field definition */ +#define TPS6594_MASK_PFSM_DELAY4 GENMASK(7, 0) + +/* CRC_CALC_CONTROL Register field definition */ +#define TPS65224_BIT_RUN_CRC_BIST BIT(0) +#define TPS65224_BIT_RUN_CRC_UPDATE BIT(1) + +/* ADC_GAIN_COMP_REG Register field definition */ +#define TPS65224_MASK_ADC_GAIN_COMP GENMASK(7, 0) + +/* REGMAP_USER_CRC_LOW Register field definition */ +#define TPS65224_MASK_REGMAP_USER_CRC16_LOW GENMASK(7, 0) + +/* REGMAP_USER_CRC_HIGH Register field definition */ +#define TPS65224_MASK_REGMAP_USER_CRC16_HIGH GENMASK(7, 0) + +/* WD_ANSWER_REG Register field definition */ +#define TPS6594_MASK_WD_ANSWER GENMASK(7, 0) + /* WD_QUESTION_ANSW_CNT register field definition */ #define TPS6594_MASK_WD_QUESTION GENMASK(3, 0) #define TPS6594_MASK_WD_ANSW_CNT GENMASK(5, 4) +#define TPS65224_BIT_INT_TOP_STATUS BIT(7) + +/* WD WIN1_CFG register field definition */ +#define TPS6594_MASK_WD_WIN1_CFG GENMASK(6, 0) + +/* WD WIN2_CFG register field definition */ +#define TPS6594_MASK_WD_WIN2_CFG GENMASK(6, 0) + +/* WD LongWin register field definition */ +#define TPS6594_MASK_WD_LONGWIN_CFG GENMASK(7, 0) /* WD_MODE_REG register field definition */ #define TPS6594_BIT_WD_RETURN_LONGWIN BIT(0) #define TPS6594_BIT_WD_MODE_SELECT BIT(1) #define TPS6594_BIT_WD_PWRHOLD BIT(2) +#define TPS65224_BIT_WD_ENDRV_SEL BIT(6) +#define TPS65224_BIT_WD_CNT_SEL BIT(7) /* WD_QA_CFG register field definition */ #define TPS6594_MASK_WD_QUESTION_SEED GENMASK(3, 0) @@ -993,6 +1216,106 @@ enum tps6594_irqs { #define TPS6594_IRQ_NAME_ALARM "alarm" #define TPS6594_IRQ_NAME_POWERUP "powerup" +/* IRQs */ +enum tps65224_irqs { + /* INT_BUCK register */ + TPS65224_IRQ_BUCK1_UVOV, + TPS65224_IRQ_BUCK2_UVOV, + TPS65224_IRQ_BUCK3_UVOV, + TPS65224_IRQ_BUCK4_UVOV, + /* INT_LDO_VMON register */ + TPS65224_IRQ_LDO1_UVOV, + TPS65224_IRQ_LDO2_UVOV, + TPS65224_IRQ_LDO3_UVOV, + TPS65224_IRQ_VCCA_UVOV, + TPS65224_IRQ_VMON1_UVOV, + TPS65224_IRQ_VMON2_UVOV, + /* INT_GPIO register */ + TPS65224_IRQ_GPIO1, + TPS65224_IRQ_GPIO2, + TPS65224_IRQ_GPIO3, + TPS65224_IRQ_GPIO4, + TPS65224_IRQ_GPIO5, + TPS65224_IRQ_GPIO6, + /* INT_STARTUP register */ + TPS65224_IRQ_VSENSE, + TPS65224_IRQ_ENABLE, + TPS65224_IRQ_PB_SHORT, + TPS65224_IRQ_FSD, + TPS65224_IRQ_SOFT_REBOOT, + /* INT_MISC register */ + TPS65224_IRQ_BIST_PASS, + TPS65224_IRQ_EXT_CLK, + TPS65224_IRQ_REG_UNLOCK, + TPS65224_IRQ_TWARN, + TPS65224_IRQ_PB_LONG, + TPS65224_IRQ_PB_FALL, + TPS65224_IRQ_PB_RISE, + TPS65224_IRQ_ADC_CONV_READY, + /* INT_MODERATE_ERR register */ + TPS65224_IRQ_TSD_ORD, + TPS65224_IRQ_BIST_FAIL, + TPS65224_IRQ_REG_CRC_ERR, + TPS65224_IRQ_RECOV_CNT, + /* INT_SEVERE_ERR register */ + TPS65224_IRQ_TSD_IMM, + TPS65224_IRQ_VCCA_OVP, + TPS65224_IRQ_PFSM_ERR, + TPS65224_IRQ_BG_XMON, + /* INT_FSM_ERR register */ + TPS65224_IRQ_IMM_SHUTDOWN, + TPS65224_IRQ_ORD_SHUTDOWN, + TPS65224_IRQ_MCU_PWR_ERR, + TPS65224_IRQ_SOC_PWR_ERR, + TPS65224_IRQ_COMM_ERR, + TPS65224_IRQ_I2C2_ERR, +}; + +#define TPS65224_IRQ_NAME_BUCK1_UVOV "buck1_uvov" +#define TPS65224_IRQ_NAME_BUCK2_UVOV "buck2_uvov" +#define TPS65224_IRQ_NAME_BUCK3_UVOV "buck3_uvov" +#define TPS65224_IRQ_NAME_BUCK4_UVOV "buck4_uvov" +#define TPS65224_IRQ_NAME_LDO1_UVOV "ldo1_uvov" +#define TPS65224_IRQ_NAME_LDO2_UVOV "ldo2_uvov" +#define TPS65224_IRQ_NAME_LDO3_UVOV "ldo3_uvov" +#define TPS65224_IRQ_NAME_VCCA_UVOV "vcca_uvov" +#define TPS65224_IRQ_NAME_VMON1_UVOV "vmon1_uvov" +#define TPS65224_IRQ_NAME_VMON2_UVOV "vmon2_uvov" +#define TPS65224_IRQ_NAME_GPIO1 "gpio1" +#define TPS65224_IRQ_NAME_GPIO2 "gpio2" +#define TPS65224_IRQ_NAME_GPIO3 "gpio3" +#define TPS65224_IRQ_NAME_GPIO4 "gpio4" +#define TPS65224_IRQ_NAME_GPIO5 "gpio5" +#define TPS65224_IRQ_NAME_GPIO6 "gpio6" +#define TPS65224_IRQ_NAME_VSENSE "vsense" +#define TPS65224_IRQ_NAME_ENABLE "enable" +#define TPS65224_IRQ_NAME_PB_SHORT "pb_short" +#define TPS65224_IRQ_NAME_FSD "fsd" +#define TPS65224_IRQ_NAME_SOFT_REBOOT "soft_reboot" +#define TPS65224_IRQ_NAME_BIST_PASS "bist_pass" +#define TPS65224_IRQ_NAME_EXT_CLK "ext_clk" +#define TPS65224_IRQ_NAME_REG_UNLOCK "reg_unlock" +#define TPS65224_IRQ_NAME_TWARN "twarn" +#define TPS65224_IRQ_NAME_PB_LONG "pb_long" +#define TPS65224_IRQ_NAME_PB_FALL "pb_fall" +#define TPS65224_IRQ_NAME_PB_RISE "pb_rise" +#define TPS65224_IRQ_NAME_ADC_CONV_READY "adc_conv_ready" +#define TPS65224_IRQ_NAME_TSD_ORD "tsd_ord" +#define TPS65224_IRQ_NAME_BIST_FAIL "bist_fail" +#define TPS65224_IRQ_NAME_REG_CRC_ERR "reg_crc_err" +#define TPS65224_IRQ_NAME_RECOV_CNT "recov_cnt" +#define TPS65224_IRQ_NAME_TSD_IMM "tsd_imm" +#define TPS65224_IRQ_NAME_VCCA_OVP "vcca_ovp" +#define TPS65224_IRQ_NAME_PFSM_ERR "pfsm_err" +#define TPS65224_IRQ_NAME_BG_XMON "bg_xmon" +#define TPS65224_IRQ_NAME_IMM_SHUTDOWN "imm_shutdown" +#define TPS65224_IRQ_NAME_ORD_SHUTDOWN "ord_shutdown" +#define TPS65224_IRQ_NAME_MCU_PWR_ERR "mcu_pwr_err" +#define TPS65224_IRQ_NAME_SOC_PWR_ERR "soc_pwr_err" +#define TPS65224_IRQ_NAME_COMM_ERR "comm_err" +#define TPS65224_IRQ_NAME_I2C2_ERR "i2c2_err" +#define TPS65224_IRQ_NAME_POWERUP "powerup" + /** * struct tps6594 - device private data structure * @@ -1014,7 +1337,9 @@ struct tps6594 { struct regmap_irq_chip_data *irq_data; }; -bool tps6594_is_volatile_reg(struct device *dev, unsigned int reg); +extern const struct regmap_access_table tps6594_volatile_table; +extern const struct regmap_access_table tps65224_volatile_table; + int tps6594_device_init(struct tps6594 *tps, bool enable_crc); #endif /* __LINUX_MFD_TPS6594_H */ diff --git a/include/linux/mfd/upboard-fpga.h b/include/linux/mfd/upboard-fpga.h new file mode 100644 index 000000000000..12231e40f5da --- /dev/null +++ b/include/linux/mfd/upboard-fpga.h @@ -0,0 +1,55 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * UP Board CPLD/FPGA driver + * + * Copyright (c) AAEON. All rights reserved. + * Copyright (C) 2024 Bootlin + * + * Author: Gary Wang <garywang@aaeon.com.tw> + * Author: Thomas Richard <thomas.richard@bootlin.com> + * + */ + +#ifndef __LINUX_MFD_UPBOARD_FPGA_H +#define __LINUX_MFD_UPBOARD_FPGA_H + +#define UPBOARD_REGISTER_SIZE 16 + +enum upboard_fpgareg { + UPBOARD_REG_PLATFORM_ID = 0x10, + UPBOARD_REG_FIRMWARE_ID = 0x11, + UPBOARD_REG_FUNC_EN0 = 0x20, + UPBOARD_REG_FUNC_EN1 = 0x21, + UPBOARD_REG_GPIO_EN0 = 0x30, + UPBOARD_REG_GPIO_EN1 = 0x31, + UPBOARD_REG_GPIO_EN2 = 0x32, + UPBOARD_REG_GPIO_DIR0 = 0x40, + UPBOARD_REG_GPIO_DIR1 = 0x41, + UPBOARD_REG_GPIO_DIR2 = 0x42, + UPBOARD_REG_MAX, +}; + +enum upboard_fpga_type { + UPBOARD_UP_FPGA, + UPBOARD_UP2_FPGA, +}; + +struct upboard_fpga_data { + enum upboard_fpga_type type; + const struct regmap_config *regmap_config; +}; + +struct upboard_fpga { + struct device *dev; + struct regmap *regmap; + struct gpio_desc *enable_gpio; + struct gpio_desc *reset_gpio; + struct gpio_desc *clear_gpio; + struct gpio_desc *strobe_gpio; + struct gpio_desc *datain_gpio; + struct gpio_desc *dataout_gpio; + unsigned int firmware_version; + const struct upboard_fpga_data *fpga_data; +}; + +#endif /* __LINUX_MFD_UPBOARD_FPGA_H */ diff --git a/include/linux/mhi.h b/include/linux/mhi.h index 77b8c0a26674..059dc94d20bb 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -290,6 +290,7 @@ struct mhi_controller_config { /** * struct mhi_controller - Master MHI controller structure + * @name: Device name of the MHI controller * @cntrl_dev: Pointer to the struct device of physical bus acting as the MHI * controller (required) * @mhi_dev: MHI device instance for the controller @@ -353,6 +354,7 @@ struct mhi_controller_config { * @read_reg: Read a MHI register via the physical link (required) * @write_reg: Write a MHI register via the physical link (required) * @reset: Controller specific reset function (optional) + * @edl_trigger: CB function to trigger EDL mode (optional) * @buffer_len: Bounce buffer length * @index: Index of the MHI controller instance * @bounce_buf: Use of bounce buffer @@ -366,6 +368,7 @@ struct mhi_controller_config { * they can be populated depending on the usecase. */ struct mhi_controller { + const char *name; struct device *cntrl_dev; struct mhi_device *mhi_dev; struct dentry *debugfs_dentry; @@ -435,6 +438,7 @@ struct mhi_controller { void (*write_reg)(struct mhi_controller *mhi_cntrl, void __iomem *addr, u32 val); void (*reset)(struct mhi_controller *mhi_cntrl); + int (*edl_trigger)(struct mhi_controller *mhi_cntrl); size_t buffer_len; int index; @@ -524,7 +528,7 @@ struct mhi_driver { struct device_driver driver; }; -#define to_mhi_driver(drv) container_of(drv, struct mhi_driver, driver) +#define to_mhi_driver(drv) container_of_const(drv, struct mhi_driver, driver) #define to_mhi_device(dev) container_of(dev, struct mhi_device, dev) /** @@ -630,13 +634,29 @@ int mhi_async_power_up(struct mhi_controller *mhi_cntrl); int mhi_sync_power_up(struct mhi_controller *mhi_cntrl); /** - * mhi_power_down - Start MHI power down sequence + * mhi_power_down - Power down the MHI device and also destroy the + * 'struct device' for the channels associated with it. + * See also mhi_power_down_keep_dev() which is a variant + * of this API that keeps the 'struct device' for channels + * (useful during suspend/hibernation). * @mhi_cntrl: MHI controller * @graceful: Link is still accessible, so do a graceful shutdown process */ void mhi_power_down(struct mhi_controller *mhi_cntrl, bool graceful); /** + * mhi_power_down_keep_dev - Power down the MHI device but keep the 'struct + * device' for the channels associated with it. + * This is a variant of 'mhi_power_down()' and + * useful in scenarios such as suspend/hibernation + * where destroying of the 'struct device' is not + * needed. + * @mhi_cntrl: MHI controller + * @graceful: Link is still accessible, so do a graceful shutdown process + */ +void mhi_power_down_keep_dev(struct mhi_controller *mhi_cntrl, bool graceful); + +/** * mhi_unprepare_after_power_down - Free any allocated memory after power down * @mhi_cntrl: MHI controller */ @@ -798,4 +818,13 @@ int mhi_queue_skb(struct mhi_device *mhi_dev, enum dma_data_direction dir, */ bool mhi_queue_is_full(struct mhi_device *mhi_dev, enum dma_data_direction dir); +/** + * mhi_get_channel_doorbell_offset - Get the channel doorbell offset + * @mhi_cntrl: MHI controller + * @chdb_offset: Read channel doorbell offset + * + * Return: 0 if the read succeeds, a negative error code otherwise + */ +int mhi_get_channel_doorbell_offset(struct mhi_controller *mhi_cntrl, u32 *chdb_offset); + #endif /* _MHI_H_ */ diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h index 11bf3212f782..7b40fc8cbe77 100644 --- a/include/linux/mhi_ep.h +++ b/include/linux/mhi_ep.h @@ -221,7 +221,7 @@ struct mhi_ep_driver { }; #define to_mhi_ep_device(dev) container_of(dev, struct mhi_ep_device, dev) -#define to_mhi_ep_driver(drv) container_of(drv, struct mhi_ep_driver, driver) +#define to_mhi_ep_driver(drv) container_of_const(drv, struct mhi_ep_driver, driver) /* * module_mhi_ep_driver() - Helper macro for drivers that don't do diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 2ce13e8a309b..29919faea2f1 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -63,8 +63,6 @@ extern const char *migrate_reason_names[MR_TYPES]; #ifdef CONFIG_MIGRATION 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); int migrate_pages(struct list_head *l, new_folio_t new, free_folio_t free, @@ -72,13 +70,13 @@ int migrate_pages(struct list_head *l, new_folio_t new, free_folio_t free, unsigned int *ret_succeeded); struct folio *alloc_migration_target(struct folio *src, unsigned long private); bool isolate_movable_page(struct page *page, isolate_mode_t mode); +bool isolate_folio_to_list(struct folio *folio, struct list_head *list); int migrate_huge_page_move_mapping(struct address_space *mapping, struct folio *dst, struct folio *src); void migration_entry_wait_on_locked(swp_entry_t entry, spinlock_t *ptl) __releases(ptl); void folio_migrate_flags(struct folio *newfolio, struct folio *folio); -void folio_migrate_copy(struct folio *newfolio, struct folio *folio); int folio_migrate_mapping(struct address_space *mapping, struct folio *newfolio, struct folio *folio, int extra_count); @@ -94,6 +92,8 @@ static inline struct folio *alloc_migration_target(struct folio *src, { return NULL; } static inline bool isolate_movable_page(struct page *page, isolate_mode_t mode) { return false; } +static inline bool isolate_folio_to_list(struct folio *folio, struct list_head *list) + { return false; } static inline int migrate_huge_page_move_mapping(struct address_space *mapping, struct folio *dst, struct folio *src) @@ -142,11 +142,16 @@ const struct movable_operations *page_movable_ops(struct page *page) } #ifdef CONFIG_NUMA_BALANCING -int migrate_misplaced_folio(struct folio *folio, struct vm_area_struct *vma, - int node); +int migrate_misplaced_folio_prepare(struct folio *folio, + struct vm_area_struct *vma, int node); +int migrate_misplaced_folio(struct folio *folio, int node); #else -static inline int migrate_misplaced_folio(struct folio *folio, - struct vm_area_struct *vma, int node) +static inline int migrate_misplaced_folio_prepare(struct folio *folio, + struct vm_area_struct *vma, int node) +{ + return -EAGAIN; /* can't migrate now */ +} +static inline int migrate_misplaced_folio(struct folio *folio, int node) { return -EAGAIN; /* can't migrate now */ } diff --git a/include/linux/migrate_mode.h b/include/linux/migrate_mode.h index f37cc03f9369..265c4328b36a 100644 --- a/include/linux/migrate_mode.h +++ b/include/linux/migrate_mode.h @@ -7,16 +7,11 @@ * on most operations but not ->writepage as the potential stall time * is too significant * MIGRATE_SYNC will block when migrating pages - * MIGRATE_SYNC_NO_COPY will block when migrating pages but will not copy pages - * with the CPU. Instead, page copy happens outside the migratepage() - * callback and is likely using a DMA engine. See migrate_vma() and HMM - * (mm/hmm.c) for users of this mode. */ enum migrate_mode { MIGRATE_ASYNC, MIGRATE_SYNC_LIGHT, MIGRATE_SYNC, - MIGRATE_SYNC_NO_COPY, }; enum migrate_reason { @@ -29,6 +24,7 @@ enum migrate_reason { MR_CONTIG_RANGE, MR_LONGTERM_PIN, MR_DEMOTION, + MR_DAMON, MR_TYPES }; diff --git a/include/linux/mii.h b/include/linux/mii.h index d5a959ce4877..b8f26d4513c3 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -140,7 +140,7 @@ static inline u32 ethtool_adv_to_mii_adv_t(u32 ethadv) * settings to phy autonegotiation advertisements for the * MII_ADVERTISE register. */ -static inline u32 linkmode_adv_to_mii_adv_t(unsigned long *advertising) +static inline u32 linkmode_adv_to_mii_adv_t(const unsigned long *advertising) { u32 result = 0; @@ -215,7 +215,8 @@ static inline u32 ethtool_adv_to_mii_ctrl1000_t(u32 ethadv) * settings to phy autonegotiation advertisements for the * MII_CTRL1000 register when in 1000T mode. */ -static inline u32 linkmode_adv_to_mii_ctrl1000_t(unsigned long *advertising) +static inline u32 +linkmode_adv_to_mii_ctrl1000_t(const unsigned long *advertising) { u32 result = 0; @@ -453,7 +454,7 @@ static inline void mii_ctrl1000_mod_linkmode_adv_t(unsigned long *advertising, * A small helper function that translates linkmode advertising to LVL * pause capabilities. */ -static inline u32 linkmode_adv_to_lcl_adv_t(unsigned long *advertising) +static inline u32 linkmode_adv_to_lcl_adv_t(const unsigned long *advertising) { u32 lcl_adv = 0; diff --git a/include/linux/mii_timestamper.h b/include/linux/mii_timestamper.h index 26b04f73f214..995db62570f9 100644 --- a/include/linux/mii_timestamper.h +++ b/include/linux/mii_timestamper.h @@ -59,7 +59,7 @@ struct mii_timestamper { struct phy_device *phydev); int (*ts_info)(struct mii_timestamper *mii_ts, - struct ethtool_ts_info *ts_info); + struct kernel_ethtool_ts_info *ts_info); struct device *device; }; diff --git a/include/linux/min_heap.h b/include/linux/min_heap.h index d52daf45861b..1160bed6579e 100644 --- a/include/linux/min_heap.h +++ b/include/linux/min_heap.h @@ -6,131 +6,472 @@ #include <linux/string.h> #include <linux/types.h> +/* + * The Min Heap API provides utilities for managing min-heaps, a binary tree + * structure where each node's value is less than or equal to its children's + * values, ensuring the smallest element is at the root. + * + * Users should avoid directly calling functions prefixed with __min_heap_*(). + * Instead, use the provided macro wrappers. + * + * For further details and examples, refer to Documentation/core-api/min_heap.rst. + */ + /** - * struct min_heap - Data structure to hold a min-heap. - * @data: Start of array holding the heap elements. + * Data structure to hold a min-heap. * @nr: Number of elements currently in the heap. * @size: Maximum number of elements that can be held in current storage. + * @data: Pointer to the start of array holding the heap elements. + * @preallocated: Start of the static preallocated array holding the heap elements. */ -struct min_heap { - void *data; - int nr; - int size; -}; +#define MIN_HEAP_PREALLOCATED(_type, _name, _nr) \ +struct _name { \ + size_t nr; \ + size_t size; \ + _type *data; \ + _type preallocated[_nr]; \ +} + +#define DEFINE_MIN_HEAP(_type, _name) MIN_HEAP_PREALLOCATED(_type, _name, 0) + +typedef DEFINE_MIN_HEAP(char, min_heap_char) min_heap_char; + +#define __minheap_cast(_heap) (typeof((_heap)->data[0]) *) +#define __minheap_obj_size(_heap) sizeof((_heap)->data[0]) /** * struct min_heap_callbacks - Data/functions to customise the min_heap. - * @elem_size: The nr of each element in bytes. * @less: Partial order function for this heap. * @swp: Swap elements function. */ struct min_heap_callbacks { - int elem_size; - bool (*less)(const void *lhs, const void *rhs); - void (*swp)(void *lhs, void *rhs); + bool (*less)(const void *lhs, const void *rhs, void *args); + void (*swp)(void *lhs, void *rhs, void *args); }; +/** + * is_aligned - is this pointer & size okay for word-wide copying? + * @base: pointer to data + * @size: size of each element + * @align: required alignment (typically 4 or 8) + * + * Returns true if elements can be copied using word loads and stores. + * The size must be a multiple of the alignment, and the base address must + * be if we do not have CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS. + * + * For some reason, gcc doesn't know to optimize "if (a & mask || b & mask)" + * to "if ((a | b) & mask)", so we do that by hand. + */ +__attribute_const__ __always_inline +static bool is_aligned(const void *base, size_t size, unsigned char align) +{ + unsigned char lsbits = (unsigned char)size; + + (void)base; +#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS + lsbits |= (unsigned char)(uintptr_t)base; +#endif + return (lsbits & (align - 1)) == 0; +} + +/** + * swap_words_32 - swap two elements in 32-bit chunks + * @a: pointer to the first element to swap + * @b: pointer to the second element to swap + * @n: element size (must be a multiple of 4) + * + * Exchange the two objects in memory. This exploits base+index addressing, + * which basically all CPUs have, to minimize loop overhead computations. + * + * For some reason, on x86 gcc 7.3.0 adds a redundant test of n at the + * bottom of the loop, even though the zero flag is still valid from the + * subtract (since the intervening mov instructions don't alter the flags). + * Gcc 8.1.0 doesn't have that problem. + */ +static __always_inline +void swap_words_32(void *a, void *b, size_t n) +{ + do { + u32 t = *(u32 *)(a + (n -= 4)); + *(u32 *)(a + n) = *(u32 *)(b + n); + *(u32 *)(b + n) = t; + } while (n); +} + +/** + * swap_words_64 - swap two elements in 64-bit chunks + * @a: pointer to the first element to swap + * @b: pointer to the second element to swap + * @n: element size (must be a multiple of 8) + * + * Exchange the two objects in memory. This exploits base+index + * addressing, which basically all CPUs have, to minimize loop overhead + * computations. + * + * We'd like to use 64-bit loads if possible. If they're not, emulating + * one requires base+index+4 addressing which x86 has but most other + * processors do not. If CONFIG_64BIT, we definitely have 64-bit loads, + * but it's possible to have 64-bit loads without 64-bit pointers (e.g. + * x32 ABI). Are there any cases the kernel needs to worry about? + */ +static __always_inline +void swap_words_64(void *a, void *b, size_t n) +{ + do { +#ifdef CONFIG_64BIT + u64 t = *(u64 *)(a + (n -= 8)); + *(u64 *)(a + n) = *(u64 *)(b + n); + *(u64 *)(b + n) = t; +#else + /* Use two 32-bit transfers to avoid base+index+4 addressing */ + u32 t = *(u32 *)(a + (n -= 4)); + *(u32 *)(a + n) = *(u32 *)(b + n); + *(u32 *)(b + n) = t; + + t = *(u32 *)(a + (n -= 4)); + *(u32 *)(a + n) = *(u32 *)(b + n); + *(u32 *)(b + n) = t; +#endif + } while (n); +} + +/** + * swap_bytes - swap two elements a byte at a time + * @a: pointer to the first element to swap + * @b: pointer to the second element to swap + * @n: element size + * + * This is the fallback if alignment doesn't allow using larger chunks. + */ +static __always_inline +void swap_bytes(void *a, void *b, size_t n) +{ + do { + char t = ((char *)a)[--n]; + ((char *)a)[n] = ((char *)b)[n]; + ((char *)b)[n] = t; + } while (n); +} + +/* + * The values are arbitrary as long as they can't be confused with + * a pointer, but small integers make for the smallest compare + * instructions. + */ +#define SWAP_WORDS_64 ((void (*)(void *, void *, void *))0) +#define SWAP_WORDS_32 ((void (*)(void *, void *, void *))1) +#define SWAP_BYTES ((void (*)(void *, void *, void *))2) + +/* + * Selects the appropriate swap function based on the element size. + */ +static __always_inline +void *select_swap_func(const void *base, size_t size) +{ + if (is_aligned(base, size, 8)) + return SWAP_WORDS_64; + else if (is_aligned(base, size, 4)) + return SWAP_WORDS_32; + else + return SWAP_BYTES; +} + +static __always_inline +void do_swap(void *a, void *b, size_t size, void (*swap_func)(void *lhs, void *rhs, void *args), + void *priv) +{ + if (swap_func == SWAP_WORDS_64) + swap_words_64(a, b, size); + else if (swap_func == SWAP_WORDS_32) + swap_words_32(a, b, size); + else if (swap_func == SWAP_BYTES) + swap_bytes(a, b, size); + else + swap_func(a, b, priv); +} + +/** + * parent - given the offset of the child, find the offset of the parent. + * @i: the offset of the heap element whose parent is sought. Non-zero. + * @lsbit: a precomputed 1-bit mask, equal to "size & -size" + * @size: size of each element + * + * In terms of array indexes, the parent of element j = @i/@size is simply + * (j-1)/2. But when working in byte offsets, we can't use implicit + * truncation of integer divides. + * + * Fortunately, we only need one bit of the quotient, not the full divide. + * @size has a least significant bit. That bit will be clear if @i is + * an even multiple of @size, and set if it's an odd multiple. + * + * Logically, we're doing "if (i & lsbit) i -= size;", but since the + * branch is unpredictable, it's done with a bit of clever branch-free + * code instead. + */ +__attribute_const__ __always_inline +static size_t parent(size_t i, unsigned int lsbit, size_t size) +{ + i -= size; + i -= size & -(i & lsbit); + return i / 2; +} + +/* Initialize a min-heap. */ +static __always_inline +void __min_heap_init_inline(min_heap_char *heap, void *data, int size) +{ + heap->nr = 0; + heap->size = size; + if (data) + heap->data = data; + else + heap->data = heap->preallocated; +} + +#define min_heap_init_inline(_heap, _data, _size) \ + __min_heap_init_inline(container_of(&(_heap)->nr, min_heap_char, nr), _data, _size) + +/* Get the minimum element from the heap. */ +static __always_inline +void *__min_heap_peek_inline(struct min_heap_char *heap) +{ + return heap->nr ? heap->data : NULL; +} + +#define min_heap_peek_inline(_heap) \ + (__minheap_cast(_heap) \ + __min_heap_peek_inline(container_of(&(_heap)->nr, min_heap_char, nr))) + +/* Check if the heap is full. */ +static __always_inline +bool __min_heap_full_inline(min_heap_char *heap) +{ + return heap->nr == heap->size; +} + +#define min_heap_full_inline(_heap) \ + __min_heap_full_inline(container_of(&(_heap)->nr, min_heap_char, nr)) + /* Sift the element at pos down the heap. */ static __always_inline -void min_heapify(struct min_heap *heap, int pos, - const struct min_heap_callbacks *func) +void __min_heap_sift_down_inline(min_heap_char *heap, int pos, size_t elem_size, + const struct min_heap_callbacks *func, void *args) { - void *left, *right; + const unsigned long lsbit = elem_size & -elem_size; void *data = heap->data; - void *root = data + pos * func->elem_size; - int i = pos, j; + void (*swp)(void *lhs, void *rhs, void *args) = func->swp; + /* pre-scale counters for performance */ + size_t a = pos * elem_size; + size_t b, c, d; + size_t n = heap->nr * elem_size; + + if (!swp) + swp = select_swap_func(data, elem_size); /* Find the sift-down path all the way to the leaves. */ - for (;;) { - if (i * 2 + 2 >= heap->nr) - break; - left = data + (i * 2 + 1) * func->elem_size; - right = data + (i * 2 + 2) * func->elem_size; - i = func->less(left, right) ? i * 2 + 1 : i * 2 + 2; - } + for (b = a; c = 2 * b + elem_size, (d = c + elem_size) < n;) + b = func->less(data + c, data + d, args) ? c : d; /* Special case for the last leaf with no sibling. */ - if (i * 2 + 2 == heap->nr) - i = i * 2 + 1; + if (d == n) + b = c; /* Backtrack to the correct location. */ - while (i != pos && func->less(root, data + i * func->elem_size)) - i = (i - 1) / 2; + while (b != a && func->less(data + a, data + b, args)) + b = parent(b, lsbit, elem_size); /* Shift the element into its correct place. */ - j = i; - while (i != pos) { - i = (i - 1) / 2; - func->swp(data + i * func->elem_size, data + j * func->elem_size); + c = b; + while (b != a) { + b = parent(b, lsbit, elem_size); + do_swap(data + b, data + c, elem_size, swp, args); } } +#define min_heap_sift_down_inline(_heap, _pos, _func, _args) \ + __min_heap_sift_down_inline(container_of(&(_heap)->nr, min_heap_char, nr), _pos, \ + __minheap_obj_size(_heap), _func, _args) + +/* Sift up ith element from the heap, O(log2(nr)). */ +static __always_inline +void __min_heap_sift_up_inline(min_heap_char *heap, size_t elem_size, size_t idx, + const struct min_heap_callbacks *func, void *args) +{ + const unsigned long lsbit = elem_size & -elem_size; + void *data = heap->data; + void (*swp)(void *lhs, void *rhs, void *args) = func->swp; + /* pre-scale counters for performance */ + size_t a = idx * elem_size, b; + + if (!swp) + swp = select_swap_func(data, elem_size); + + while (a) { + b = parent(a, lsbit, elem_size); + if (func->less(data + b, data + a, args)) + break; + do_swap(data + a, data + b, elem_size, swp, args); + a = b; + } +} + +#define min_heap_sift_up_inline(_heap, _idx, _func, _args) \ + __min_heap_sift_up_inline(container_of(&(_heap)->nr, min_heap_char, nr), \ + __minheap_obj_size(_heap), _idx, _func, _args) + /* Floyd's approach to heapification that is O(nr). */ static __always_inline -void min_heapify_all(struct min_heap *heap, - const struct min_heap_callbacks *func) +void __min_heapify_all_inline(min_heap_char *heap, size_t elem_size, + const struct min_heap_callbacks *func, void *args) { int i; for (i = heap->nr / 2 - 1; i >= 0; i--) - min_heapify(heap, i, func); + __min_heap_sift_down_inline(heap, i, elem_size, func, args); } +#define min_heapify_all_inline(_heap, _func, _args) \ + __min_heapify_all_inline(container_of(&(_heap)->nr, min_heap_char, nr), \ + __minheap_obj_size(_heap), _func, _args) + /* Remove minimum element from the heap, O(log2(nr)). */ static __always_inline -void min_heap_pop(struct min_heap *heap, - const struct min_heap_callbacks *func) +bool __min_heap_pop_inline(min_heap_char *heap, size_t elem_size, + const struct min_heap_callbacks *func, void *args) { void *data = heap->data; if (WARN_ONCE(heap->nr <= 0, "Popping an empty heap")) - return; + return false; /* Place last element at the root (position 0) and then sift down. */ heap->nr--; - memcpy(data, data + (heap->nr * func->elem_size), func->elem_size); - min_heapify(heap, 0, func); + memcpy(data, data + (heap->nr * elem_size), elem_size); + __min_heap_sift_down_inline(heap, 0, elem_size, func, args); + + return true; } +#define min_heap_pop_inline(_heap, _func, _args) \ + __min_heap_pop_inline(container_of(&(_heap)->nr, min_heap_char, nr), \ + __minheap_obj_size(_heap), _func, _args) + /* * Remove the minimum element and then push the given element. The * implementation performs 1 sift (O(log2(nr))) and is therefore more * efficient than a pop followed by a push that does 2. */ static __always_inline -void min_heap_pop_push(struct min_heap *heap, - const void *element, - const struct min_heap_callbacks *func) +void __min_heap_pop_push_inline(min_heap_char *heap, const void *element, size_t elem_size, + const struct min_heap_callbacks *func, void *args) { - memcpy(heap->data, element, func->elem_size); - min_heapify(heap, 0, func); + memcpy(heap->data, element, elem_size); + __min_heap_sift_down_inline(heap, 0, elem_size, func, args); } +#define min_heap_pop_push_inline(_heap, _element, _func, _args) \ + __min_heap_pop_push_inline(container_of(&(_heap)->nr, min_heap_char, nr), _element, \ + __minheap_obj_size(_heap), _func, _args) + /* Push an element on to the heap, O(log2(nr)). */ static __always_inline -void min_heap_push(struct min_heap *heap, const void *element, - const struct min_heap_callbacks *func) +bool __min_heap_push_inline(min_heap_char *heap, const void *element, size_t elem_size, + const struct min_heap_callbacks *func, void *args) { void *data = heap->data; - void *child, *parent; int pos; if (WARN_ONCE(heap->nr >= heap->size, "Pushing on a full heap")) - return; + return false; /* Place at the end of data. */ pos = heap->nr; - memcpy(data + (pos * func->elem_size), element, func->elem_size); + memcpy(data + (pos * elem_size), element, elem_size); heap->nr++; /* Sift child at pos up. */ - for (; pos > 0; pos = (pos - 1) / 2) { - child = data + (pos * func->elem_size); - parent = data + ((pos - 1) / 2) * func->elem_size; - if (func->less(parent, child)) - break; - func->swp(parent, child); - } + __min_heap_sift_up_inline(heap, elem_size, pos, func, args); + + return true; } +#define min_heap_push_inline(_heap, _element, _func, _args) \ + __min_heap_push_inline(container_of(&(_heap)->nr, min_heap_char, nr), _element, \ + __minheap_obj_size(_heap), _func, _args) + +/* Remove ith element from the heap, O(log2(nr)). */ +static __always_inline +bool __min_heap_del_inline(min_heap_char *heap, size_t elem_size, size_t idx, + const struct min_heap_callbacks *func, void *args) +{ + void *data = heap->data; + void (*swp)(void *lhs, void *rhs, void *args) = func->swp; + + if (WARN_ONCE(heap->nr <= 0, "Popping an empty heap")) + return false; + + if (!swp) + swp = select_swap_func(data, elem_size); + + /* Place last element at the root (position 0) and then sift down. */ + heap->nr--; + if (idx == heap->nr) + return true; + do_swap(data + (idx * elem_size), data + (heap->nr * elem_size), elem_size, swp, args); + __min_heap_sift_up_inline(heap, elem_size, idx, func, args); + __min_heap_sift_down_inline(heap, idx, elem_size, func, args); + + return true; +} + +#define min_heap_del_inline(_heap, _idx, _func, _args) \ + __min_heap_del_inline(container_of(&(_heap)->nr, min_heap_char, nr), \ + __minheap_obj_size(_heap), _idx, _func, _args) + +void __min_heap_init(min_heap_char *heap, void *data, int size); +void *__min_heap_peek(struct min_heap_char *heap); +bool __min_heap_full(min_heap_char *heap); +void __min_heap_sift_down(min_heap_char *heap, int pos, size_t elem_size, + const struct min_heap_callbacks *func, void *args); +void __min_heap_sift_up(min_heap_char *heap, size_t elem_size, size_t idx, + const struct min_heap_callbacks *func, void *args); +void __min_heapify_all(min_heap_char *heap, size_t elem_size, + const struct min_heap_callbacks *func, void *args); +bool __min_heap_pop(min_heap_char *heap, size_t elem_size, + const struct min_heap_callbacks *func, void *args); +void __min_heap_pop_push(min_heap_char *heap, const void *element, size_t elem_size, + const struct min_heap_callbacks *func, void *args); +bool __min_heap_push(min_heap_char *heap, const void *element, size_t elem_size, + const struct min_heap_callbacks *func, void *args); +bool __min_heap_del(min_heap_char *heap, size_t elem_size, size_t idx, + const struct min_heap_callbacks *func, void *args); + +#define min_heap_init(_heap, _data, _size) \ + __min_heap_init(container_of(&(_heap)->nr, min_heap_char, nr), _data, _size) +#define min_heap_peek(_heap) \ + (__minheap_cast(_heap) __min_heap_peek(container_of(&(_heap)->nr, min_heap_char, nr))) +#define min_heap_full(_heap) \ + __min_heap_full(container_of(&(_heap)->nr, min_heap_char, nr)) +#define min_heap_sift_down(_heap, _pos, _func, _args) \ + __min_heap_sift_down(container_of(&(_heap)->nr, min_heap_char, nr), _pos, \ + __minheap_obj_size(_heap), _func, _args) +#define min_heap_sift_up(_heap, _idx, _func, _args) \ + __min_heap_sift_up(container_of(&(_heap)->nr, min_heap_char, nr), \ + __minheap_obj_size(_heap), _idx, _func, _args) +#define min_heapify_all(_heap, _func, _args) \ + __min_heapify_all(container_of(&(_heap)->nr, min_heap_char, nr), \ + __minheap_obj_size(_heap), _func, _args) +#define min_heap_pop(_heap, _func, _args) \ + __min_heap_pop(container_of(&(_heap)->nr, min_heap_char, nr), \ + __minheap_obj_size(_heap), _func, _args) +#define min_heap_pop_push(_heap, _element, _func, _args) \ + __min_heap_pop_push(container_of(&(_heap)->nr, min_heap_char, nr), _element, \ + __minheap_obj_size(_heap), _func, _args) +#define min_heap_push(_heap, _element, _func, _args) \ + __min_heap_push(container_of(&(_heap)->nr, min_heap_char, nr), _element, \ + __minheap_obj_size(_heap), _func, _args) +#define min_heap_del(_heap, _idx, _func, _args) \ + __min_heap_del(container_of(&(_heap)->nr, min_heap_char, nr), \ + __minheap_obj_size(_heap), _idx, _func, _args) + #endif /* _LINUX_MIN_HEAP_H */ diff --git a/include/linux/minmax.h b/include/linux/minmax.h index 2ec559284a9f..eaaf5c008e4d 100644 --- a/include/linux/minmax.h +++ b/include/linux/minmax.h @@ -8,13 +8,10 @@ #include <linux/types.h> /* - * min()/max()/clamp() macros must accomplish three things: + * min()/max()/clamp() macros must accomplish several things: * * - Avoid multiple evaluations of the arguments (so side-effects like * "x++" happen only once) when non-constant. - * - Retain result as a constant expressions when called with only - * constant expressions (to avoid tripping VLA warnings in stack - * allocation usage). * - Perform signed v unsigned type-checking (to generate compile * errors instead of nasty runtime surprises). * - Unsigned char/short are always promoted to signed int and can be @@ -26,56 +23,79 @@ #define __typecheck(x, y) \ (!!(sizeof((typeof(x) *)1 == (typeof(y) *)1))) -/* is_signed_type() isn't a constexpr for pointer types */ -#define __is_signed(x) \ - __builtin_choose_expr(__is_constexpr(is_signed_type(typeof(x))), \ - is_signed_type(typeof(x)), 0) +/* + * __sign_use for integer expressions: + * bit #0 set if ok for unsigned comparisons + * bit #1 set if ok for signed comparisons + * + * In particular, statically non-negative signed integer expressions + * are ok for both. + * + * NOTE! Unsigned types smaller than 'int' are implicitly converted to 'int' + * in expressions, and are accepted for signed conversions for now. + * This is debatable. + * + * Note that 'x' is the original expression, and 'ux' is the unique variable + * that contains the value. + * + * We use 'ux' for pure type checking, and 'x' for when we need to look at the + * value (but without evaluating it for side effects! + * Careful to only ever evaluate it with sizeof() or __builtin_constant_p() etc). + * + * Pointers end up being checked by the normal C type rules at the actual + * comparison, and these expressions only need to be careful to not cause + * warnings for pointer use. + */ +#define __sign_use(ux) (is_signed_type(typeof(ux)) ? \ + (2 + __is_nonneg(ux)) : (1 + 2 * (sizeof(ux) < 4))) + +/* + * Check whether a signed value is always non-negative. + * + * A cast is needed to avoid any warnings from values that aren't signed + * integer types (in which case the result doesn't matter). + * + * On 64-bit any integer or pointer type can safely be cast to 'long long'. + * But on 32-bit we need to avoid warnings about casting pointers to integers + * of different sizes without truncating 64-bit values so 'long' or 'long long' + * must be used depending on the size of the value. + * + * This does not work for 128-bit signed integers since the cast would truncate + * them, but we do not use s128 types in the kernel (we do use 'u128', + * but they are handled by the !is_signed_type() case). + */ +#if __SIZEOF_POINTER__ == __SIZEOF_LONG_LONG__ +#define __is_nonneg(ux) statically_true((long long)(ux) >= 0) +#else +#define __is_nonneg(ux) statically_true( \ + (typeof(__builtin_choose_expr(sizeof(ux) > 4, 1LL, 1L)))(ux) >= 0) +#endif -/* True for a non-negative signed int constant */ -#define __is_noneg_int(x) \ - (__builtin_choose_expr(__is_constexpr(x) && __is_signed(x), x, -1) >= 0) +#define __types_ok(ux, uy) \ + (__sign_use(ux) & __sign_use(uy)) -#define __types_ok(x, y) \ - (__is_signed(x) == __is_signed(y) || \ - __is_signed((x) + 0) == __is_signed((y) + 0) || \ - __is_noneg_int(x) || __is_noneg_int(y)) +#define __types_ok3(ux, uy, uz) \ + (__sign_use(ux) & __sign_use(uy) & __sign_use(uz)) #define __cmp_op_min < #define __cmp_op_max > #define __cmp(op, x, y) ((x) __cmp_op_##op (y) ? (x) : (y)) -#define __cmp_once(op, x, y, unique_x, unique_y) ({ \ - typeof(x) unique_x = (x); \ - typeof(y) unique_y = (y); \ - static_assert(__types_ok(x, y), \ - #op "(" #x ", " #y ") signedness error, fix types or consider u" #op "() before " #op "_t()"); \ - __cmp(op, unique_x, unique_y); }) - -#define __careful_cmp(op, x, y) \ - __builtin_choose_expr(__is_constexpr((x) - (y)), \ - __cmp(op, x, y), \ - __cmp_once(op, x, y, __UNIQUE_ID(__x), __UNIQUE_ID(__y))) +#define __cmp_once_unique(op, type, x, y, ux, uy) \ + ({ type ux = (x); type uy = (y); __cmp(op, ux, uy); }) -#define __clamp(val, lo, hi) \ - ((val) >= (hi) ? (hi) : ((val) <= (lo) ? (lo) : (val))) +#define __cmp_once(op, type, x, y) \ + __cmp_once_unique(op, type, x, y, __UNIQUE_ID(x_), __UNIQUE_ID(y_)) -#define __clamp_once(val, lo, hi, unique_val, unique_lo, unique_hi) ({ \ - typeof(val) unique_val = (val); \ - typeof(lo) unique_lo = (lo); \ - typeof(hi) unique_hi = (hi); \ - static_assert(__builtin_choose_expr(__is_constexpr((lo) > (hi)), \ - (lo) <= (hi), true), \ - "clamp() low limit " #lo " greater than high limit " #hi); \ - static_assert(__types_ok(val, lo), "clamp() 'lo' signedness error"); \ - static_assert(__types_ok(val, hi), "clamp() 'hi' signedness error"); \ - __clamp(unique_val, unique_lo, unique_hi); }) +#define __careful_cmp_once(op, x, y, ux, uy) ({ \ + __auto_type ux = (x); __auto_type uy = (y); \ + BUILD_BUG_ON_MSG(!__types_ok(ux, uy), \ + #op"("#x", "#y") signedness error"); \ + __cmp(op, ux, uy); }) -#define __careful_clamp(val, lo, hi) ({ \ - __builtin_choose_expr(__is_constexpr((val) - (lo) + (hi)), \ - __clamp(val, lo, hi), \ - __clamp_once(val, lo, hi, __UNIQUE_ID(__val), \ - __UNIQUE_ID(__lo), __UNIQUE_ID(__hi))); }) +#define __careful_cmp(op, x, y) \ + __careful_cmp_once(op, x, y, __UNIQUE_ID(x_), __UNIQUE_ID(y_)) /** * min - return minimum of two values of the same or compatible types @@ -108,13 +128,20 @@ #define umax(x, y) \ __careful_cmp(max, (x) + 0u + 0ul + 0ull, (y) + 0u + 0ul + 0ull) +#define __careful_op3(op, x, y, z, ux, uy, uz) ({ \ + __auto_type ux = (x); __auto_type uy = (y);__auto_type uz = (z);\ + BUILD_BUG_ON_MSG(!__types_ok3(ux, uy, uz), \ + #op"3("#x", "#y", "#z") signedness error"); \ + __cmp(op, ux, __cmp(op, uy, uz)); }) + /** * min3 - return minimum of three values * @x: first value * @y: second value * @z: third value */ -#define min3(x, y, z) min((typeof(x))min(x, y), z) +#define min3(x, y, z) \ + __careful_op3(min, x, y, z, __UNIQUE_ID(x_), __UNIQUE_ID(y_), __UNIQUE_ID(z_)) /** * max3 - return maximum of three values @@ -122,7 +149,24 @@ * @y: second value * @z: third value */ -#define max3(x, y, z) max((typeof(x))max(x, y), z) +#define max3(x, y, z) \ + __careful_op3(max, x, y, z, __UNIQUE_ID(x_), __UNIQUE_ID(y_), __UNIQUE_ID(z_)) + +/** + * min_t - return minimum of two values, using the specified type + * @type: data type to use + * @x: first value + * @y: second value + */ +#define min_t(type, x, y) __cmp_once(min, type, x, y) + +/** + * max_t - return maximum of two values, using the specified type + * @type: data type to use + * @x: first value + * @y: second value + */ +#define max_t(type, x, y) __cmp_once(max, type, x, y) /** * min_not_zero - return the minimum that is _not_ zero, unless both are zero @@ -134,39 +178,57 @@ typeof(y) __y = (y); \ __x == 0 ? __y : ((__y == 0) ? __x : min(__x, __y)); }) +#define __clamp(val, lo, hi) \ + ((val) >= (hi) ? (hi) : ((val) <= (lo) ? (lo) : (val))) + +#define __clamp_once(type, val, lo, hi, uval, ulo, uhi) ({ \ + type uval = (val); \ + type ulo = (lo); \ + type uhi = (hi); \ + BUILD_BUG_ON_MSG(statically_true(ulo > uhi), \ + "clamp() low limit " #lo " greater than high limit " #hi); \ + BUILD_BUG_ON_MSG(!__types_ok3(uval, ulo, uhi), \ + "clamp("#val", "#lo", "#hi") signedness error"); \ + __clamp(uval, ulo, uhi); }) + +#define __careful_clamp(type, val, lo, hi) \ + __clamp_once(type, val, lo, hi, __UNIQUE_ID(v_), __UNIQUE_ID(l_), __UNIQUE_ID(h_)) + /** - * clamp - return a value clamped to a given range with strict typechecking + * clamp - return a value clamped to a given range with typechecking * @val: current value * @lo: lowest allowable value * @hi: highest allowable value * - * This macro does strict typechecking of @lo/@hi to make sure they are of the - * same type as @val. See the unnecessary pointer comparisons. - */ -#define clamp(val, lo, hi) __careful_clamp(val, lo, hi) - -/* - * ..and if you can't take the strict - * types, you can specify one yourself. - * - * Or not use min/max/clamp at all, of course. + * This macro checks @val/@lo/@hi to make sure they have compatible + * signedness. */ +#define clamp(val, lo, hi) __careful_clamp(__auto_type, val, lo, hi) /** - * min_t - return minimum of two values, using the specified type - * @type: data type to use - * @x: first value - * @y: second value + * clamp_t - return a value clamped to a given range using a given type + * @type: the type of variable to use + * @val: current value + * @lo: minimum allowable value + * @hi: maximum allowable value + * + * This macro does no typechecking and uses temporary variables of type + * @type to make all the comparisons. */ -#define min_t(type, x, y) __careful_cmp(min, (type)(x), (type)(y)) +#define clamp_t(type, val, lo, hi) __careful_clamp(type, val, lo, hi) /** - * max_t - return maximum of two values, using the specified type - * @type: data type to use - * @x: first value - * @y: second value + * clamp_val - return a value clamped to a given range using val's type + * @val: current value + * @lo: minimum allowable value + * @hi: maximum allowable value + * + * This macro does no typechecking and uses temporary variables of whatever + * type the input argument @val is. This is useful when @val is an unsigned + * type and @lo and @hi are literals that will otherwise be assigned a signed + * integer type. */ -#define max_t(type, x, y) __careful_cmp(max, (type)(x), (type)(y)) +#define clamp_val(val, lo, hi) __careful_clamp(typeof(val), val, lo, hi) /* * Do not check the array parameter using __must_be_array(). @@ -211,31 +273,6 @@ */ #define max_array(array, len) __minmax_array(max, array, len) -/** - * clamp_t - return a value clamped to a given range using a given type - * @type: the type of variable to use - * @val: current value - * @lo: minimum allowable value - * @hi: maximum allowable value - * - * This macro does no typechecking and uses temporary variables of type - * @type to make all the comparisons. - */ -#define clamp_t(type, val, lo, hi) __careful_clamp((type)(val), (type)(lo), (type)(hi)) - -/** - * clamp_val - return a value clamped to a given range using val's type - * @val: current value - * @lo: minimum allowable value - * @hi: maximum allowable value - * - * This macro does no typechecking and uses temporary variables of whatever - * type the input argument @val is. This is useful when @val is an unsigned - * type and @lo and @hi are literals that will otherwise be assigned a signed - * integer type. - */ -#define clamp_val(val, lo, hi) clamp_t(typeof(val), val, lo, hi) - static inline bool in_range64(u64 val, u64 start, u64 len) { return (val - start) < len; @@ -270,4 +307,13 @@ static inline bool in_range32(u32 val, u32 start, u32 len) #define swap(a, b) \ do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0) +/* + * Use these carefully: no type checking, and uses the arguments + * multiple times. Use for obvious constants only. + */ +#define MIN(a, b) __cmp(min, a, b) +#define MAX(a, b) __cmp(max, a, b) +#define MIN_T(type, a, b) __cmp(min, (type)(a), (type)(b)) +#define MAX_T(type, a, b) __cmp(max, (type)(a), (type)(b)) + #endif /* _LINUX_MINMAX_H */ diff --git a/include/linux/misc/keba.h b/include/linux/misc/keba.h new file mode 100644 index 000000000000..a81d6fa70851 --- /dev/null +++ b/include/linux/misc/keba.h @@ -0,0 +1,72 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2024, KEBA Industrial Automation Gmbh */ + +#ifndef _LINUX_MISC_KEBA_H +#define _LINUX_MISC_KEBA_H + +#include <linux/auxiliary_bus.h> + +struct i2c_board_info; +struct spi_board_info; + +/** + * struct keba_i2c_auxdev - KEBA I2C auxiliary device + * @auxdev: auxiliary device object + * @io: address range of I2C controller IO memory + * @info_size: number of I2C devices to be probed + * @info: I2C devices to be probed + */ +struct keba_i2c_auxdev { + struct auxiliary_device auxdev; + struct resource io; + int info_size; + struct i2c_board_info *info; +}; + +/** + * struct keba_spi_auxdev - KEBA SPI auxiliary device + * @auxdev: auxiliary device object + * @io: address range of SPI controller IO memory + * @info_size: number of SPI devices to be probed + * @info: SPI devices to be probed + */ +struct keba_spi_auxdev { + struct auxiliary_device auxdev; + struct resource io; + int info_size; + struct spi_board_info *info; +}; + +/** + * struct keba_fan_auxdev - KEBA fan auxiliary device + * @auxdev: auxiliary device object + * @io: address range of fan controller IO memory + */ +struct keba_fan_auxdev { + struct auxiliary_device auxdev; + struct resource io; +}; + +/** + * struct keba_batt_auxdev - KEBA battery auxiliary device + * @auxdev: auxiliary device object + * @io: address range of battery controller IO memory + */ +struct keba_batt_auxdev { + struct auxiliary_device auxdev; + struct resource io; +}; + +/** + * struct keba_uart_auxdev - KEBA UART auxiliary device + * @auxdev: auxiliary device object + * @io: address range of UART controller IO memory + * @irq: number of UART controller interrupt + */ +struct keba_uart_auxdev { + struct auxiliary_device auxdev; + struct resource io; + unsigned int irq; +}; + +#endif /* _LINUX_MISC_KEBA_H */ diff --git a/include/linux/misc_cgroup.h b/include/linux/misc_cgroup.h index e799b1f8d05b..49eef10c8e59 100644 --- a/include/linux/misc_cgroup.h +++ b/include/linux/misc_cgroup.h @@ -9,15 +9,16 @@ #define _MISC_CGROUP_H_ /** - * Types of misc cgroup entries supported by the host. + * enum misc_res_type - Types of misc cgroup entries supported by the host. */ enum misc_res_type { #ifdef CONFIG_KVM_AMD_SEV - /* AMD SEV ASIDs resource */ + /** @MISC_CG_RES_SEV: AMD SEV ASIDs resource */ MISC_CG_RES_SEV, - /* AMD SEV-ES ASIDs resource */ + /** @MISC_CG_RES_SEV_ES: AMD SEV-ES ASIDs resource */ MISC_CG_RES_SEV_ES, #endif + /** @MISC_CG_RES_TYPES: count of enum misc_res_type constants */ MISC_CG_RES_TYPES }; @@ -30,13 +31,16 @@ struct misc_cg; /** * struct misc_res: Per cgroup per misc type resource * @max: Maximum limit on the resource. + * @watermark: Historical maximum usage of the resource. * @usage: Current usage of the resource. * @events: Number of times, the resource limit exceeded. */ struct misc_res { u64 max; + atomic64_t watermark; atomic64_t usage; atomic64_t events; + atomic64_t events_local; }; /** @@ -50,6 +54,8 @@ struct misc_cg { /* misc.events */ struct cgroup_file events_file; + /* misc.events.local */ + struct cgroup_file events_local_file; struct misc_res res[MISC_CG_RES_TYPES]; }; diff --git a/include/linux/miscdevice.h b/include/linux/miscdevice.h index c0fea6ca5076..69e110c2b86a 100644 --- a/include/linux/miscdevice.h +++ b/include/linux/miscdevice.h @@ -76,7 +76,7 @@ struct device; struct attribute_group; -struct miscdevice { +struct miscdevice { int minor; const char *name; const struct file_operations *fops; diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h index cb15308b5cb0..991526039ccb 100644 --- a/include/linux/mlx5/cq.h +++ b/include/linux/mlx5/cq.h @@ -95,9 +95,10 @@ enum { }; enum { - MLX5_CQ_MODIFY_PERIOD = 1 << 0, - MLX5_CQ_MODIFY_COUNT = 1 << 1, - MLX5_CQ_MODIFY_OVERRUN = 1 << 2, + MLX5_CQ_MODIFY_PERIOD = BIT(0), + MLX5_CQ_MODIFY_COUNT = BIT(1), + MLX5_CQ_MODIFY_OVERRUN = BIT(2), + MLX5_CQ_MODIFY_PERIOD_MODE = BIT(4), }; enum { diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 01275c6e8468..0c48b20f818a 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -68,7 +68,7 @@ #define MLX5_UN_SZ_BYTES(typ) (sizeof(union mlx5_ifc_##typ##_bits) / 8) #define MLX5_UN_SZ_DW(typ) (sizeof(union mlx5_ifc_##typ##_bits) / 32) #define MLX5_BYTE_OFF(typ, fld) (__mlx5_bit_off(typ, fld) / 8) -#define MLX5_ADDR_OF(typ, p, fld) ((void *)((uint8_t *)(p) + MLX5_BYTE_OFF(typ, fld))) +#define MLX5_ADDR_OF(typ, p, fld) ((void *)((u8 *)(p) + MLX5_BYTE_OFF(typ, fld))) /* insert a value to a struct */ #define MLX5_SET(typ, p, fld, v) do { \ @@ -211,6 +211,7 @@ enum { enum { MLX5_PFAULT_SUBTYPE_WQE = 0, MLX5_PFAULT_SUBTYPE_RDMA = 1, + MLX5_PFAULT_SUBTYPE_MEMORY = 2, }; enum wqe_page_fault_type { @@ -294,6 +295,7 @@ enum { #define MLX5_UMR_FLEX_ALIGNMENT 0x40 #define MLX5_UMR_MTT_NUM_ENTRIES_ALIGNMENT (MLX5_UMR_FLEX_ALIGNMENT / sizeof(struct mlx5_mtt)) #define MLX5_UMR_KLM_NUM_ENTRIES_ALIGNMENT (MLX5_UMR_FLEX_ALIGNMENT / sizeof(struct mlx5_klm)) +#define MLX5_UMR_KSM_NUM_ENTRIES_ALIGNMENT (MLX5_UMR_FLEX_ALIGNMENT / sizeof(struct mlx5_ksm)) #define MLX5_USER_INDEX_LEN (MLX5_FLD_SZ_BYTES(qpc, user_index) * 8) @@ -369,6 +371,7 @@ enum mlx5_driver_event { MLX5_DRIVER_EVENT_SF_PEER_DEVLINK, MLX5_DRIVER_EVENT_AFFILIATION_DONE, MLX5_DRIVER_EVENT_AFFILIATION_REMOVED, + MLX5_DRIVER_EVENT_ACTIVE_BACKUP_LAG_CHANGE_LOWERSTATE, }; enum { @@ -645,10 +648,11 @@ struct mlx5_eqe_page_req { __be32 rsvd1[5]; }; +#define MEMORY_SCHEME_PAGE_FAULT_GRANULARITY 4096 struct mlx5_eqe_page_fault { - __be32 bytes_committed; union { struct { + __be32 bytes_committed; u16 reserved1; __be16 wqe_index; u16 reserved2; @@ -658,6 +662,7 @@ struct mlx5_eqe_page_fault { __be32 pftype_wq; } __packed wqe; struct { + __be32 bytes_committed; __be32 r_key; u16 reserved1; __be16 packet_length; @@ -665,6 +670,23 @@ struct mlx5_eqe_page_fault { __be64 rdma_va; __be32 pftype_token; } __packed rdma; + struct { + u8 flags; + u8 reserved1; + __be16 post_demand_fault_pages; + __be16 pre_demand_fault_pages; + __be16 token47_32; + __be32 token31_0; + /* + * FW changed from specifying the fault size in byte + * count to 4k pages granularity. The size specified + * in pages uses bits 31:12, to keep backward + * compatibility. + */ + __be32 demand_fault_pages; + __be32 mkey; + __be64 va; + } __packed memory; } __packed; } __packed; @@ -1223,6 +1245,7 @@ enum mlx5_cap_type { MLX5_CAP_DEV_EVENT = 0x14, MLX5_CAP_IPSEC, MLX5_CAP_CRYPTO = 0x1a, + MLX5_CAP_SHAMPO = 0x1d, MLX5_CAP_MACSEC = 0x1f, MLX5_CAP_GENERAL_2 = 0x20, MLX5_CAP_PORT_SELECTION = 0x25, @@ -1242,7 +1265,8 @@ enum mlx5_pcam_feature_groups { enum mlx5_mcam_reg_groups { MLX5_MCAM_REGS_FIRST_128 = 0x0, MLX5_MCAM_REGS_0x9100_0x917F = 0x2, - MLX5_MCAM_REGS_NUM = 0x3, + MLX5_MCAM_REGS_0x9180_0x91FF = 0x3, + MLX5_MCAM_REGS_NUM = 0x4, }; enum mlx5_mcam_feature_groups { @@ -1336,6 +1360,9 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_ESW_FT_FIELD_SUPPORT_2(mdev, cap) \ MLX5_CAP_ESW_FLOWTABLE(mdev, ft_field_support_2_esw_fdb.cap) +#define MLX5_CAP_NIC_RX_FT_FIELD_SUPPORT_2(mdev, cap) \ + MLX5_CAP_FLOWTABLE(mdev, ft_field_support_2_nic_receive.cap) + #define MLX5_CAP_ESW(mdev, cap) \ MLX5_GET(e_switch_cap, \ mdev->caps.hca[MLX5_CAP_ESWITCH]->cur, cap) @@ -1359,9 +1386,20 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_FLOWTABLE_PORT_SELECTION(mdev, cap) \ MLX5_CAP_PORT_SELECTION(mdev, flow_table_properties_port_selection.cap) +#define MLX5_CAP_PORT_SELECTION_FT_FIELD_SUPPORT_2(mdev, cap) \ + MLX5_CAP_PORT_SELECTION(mdev, ft_field_support_2_port_selection.cap) + #define MLX5_CAP_ODP(mdev, cap)\ MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->cur, cap) +#define MLX5_CAP_ODP_SCHEME(mdev, cap) \ + (MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->cur, \ + mem_page_fault) ? \ + MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->cur, \ + memory_page_fault_scheme_cap.cap) : \ + MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->cur, \ + transport_page_fault_scheme_cap.cap)) + #define MLX5_CAP_ODP_MAX(mdev, cap)\ MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->max, cap) @@ -1385,6 +1423,10 @@ enum mlx5_qcam_feature_groups { MLX5_GET(mcam_reg, (mdev)->caps.mcam[MLX5_MCAM_REGS_0x9100_0x917F], \ mng_access_reg_cap_mask.access_regs2.reg) +#define MLX5_CAP_MCAM_REG3(mdev, reg) \ + MLX5_GET(mcam_reg, (mdev)->caps.mcam[MLX5_MCAM_REGS_0x9180_0x91FF], \ + mng_access_reg_cap_mask.access_regs3.reg) + #define MLX5_CAP_MCAM_FEATURE(mdev, fld) \ MLX5_GET(mcam_reg, (mdev)->caps.mcam, mng_feature_cap_mask.enhanced_features.fld) @@ -1429,6 +1471,9 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_MACSEC(mdev, cap)\ MLX5_GET(macsec_cap, (mdev)->caps.hca[MLX5_CAP_MACSEC]->cur, cap) +#define MLX5_CAP_SHAMPO(mdev, cap) \ + MLX5_GET(shampo_cap, mdev->caps.hca[MLX5_CAP_SHAMPO]->cur, cap) + enum { MLX5_CMD_STAT_OK = 0x0, MLX5_CMD_STAT_INT_ERR = 0x1, @@ -1437,6 +1482,7 @@ enum { MLX5_CMD_STAT_BAD_SYS_STATE_ERR = 0x4, MLX5_CMD_STAT_BAD_RES_ERR = 0x5, MLX5_CMD_STAT_RES_BUSY = 0x6, + MLX5_CMD_STAT_NOT_READY = 0x7, MLX5_CMD_STAT_LIM_ERR = 0x8, MLX5_CMD_STAT_BAD_RES_STATE_ERR = 0x9, MLX5_CMD_STAT_IX_ERR = 0xa, @@ -1460,6 +1506,7 @@ enum { MLX5_PER_TRAFFIC_CLASS_CONGESTION_GROUP = 0x13, MLX5_PHYSICAL_LAYER_STATISTICAL_GROUP = 0x16, MLX5_INFINIBAND_PORT_COUNTERS_GROUP = 0x20, + MLX5_INFINIBAND_EXTENDED_PORT_COUNTERS_GROUP = 0x21, }; enum { diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index bf9324a31ae9..af86097641b0 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -45,7 +45,6 @@ #include <linux/workqueue.h> #include <linux/mempool.h> #include <linux/interrupt.h> -#include <linux/idr.h> #include <linux/notifier.h> #include <linux/refcount.h> #include <linux/auxiliary_bus.h> @@ -85,7 +84,7 @@ enum mlx5_sqp_t { }; enum { - MLX5_MAX_PORTS = 4, + MLX5_MAX_PORTS = 8, }; enum { @@ -159,9 +158,14 @@ enum { MLX5_REG_MSECQ = 0x9155, MLX5_REG_MSEES = 0x9156, MLX5_REG_MIRC = 0x9162, + MLX5_REG_MTPTM = 0x9180, + MLX5_REG_MTCTR = 0x9181, + MLX5_REG_MRTCQ = 0x9182, MLX5_REG_SBCAM = 0xB01F, MLX5_REG_RESOURCE_DUMP = 0xC000, + MLX5_REG_NIC_CAP = 0xC00D, MLX5_REG_DTOR = 0xC00E, + MLX5_REG_VHCA_ICM_CTRL = 0xC010, }; enum mlx5_qpts_trust_state { @@ -472,36 +476,6 @@ struct mlx5_core_sriov { u16 max_ec_vfs; }; -struct mlx5_fc_pool { - struct mlx5_core_dev *dev; - struct mutex pool_lock; /* protects pool lists */ - struct list_head fully_used; - struct list_head partially_used; - struct list_head unused; - int available_fcs; - int used_fcs; - int threshold; -}; - -struct mlx5_fc_stats { - spinlock_t counters_idr_lock; /* protects counters_idr */ - struct idr counters_idr; - struct list_head counters; - struct llist_head addlist; - struct llist_head dellist; - - struct workqueue_struct *wq; - struct delayed_work work; - unsigned long next_query; - unsigned long sampling_interval; /* jiffies */ - u32 *bulk_query_out; - int bulk_query_len; - size_t num_counters; - bool bulk_query_alloc_failed; - unsigned long next_bulk_query_alloc; - struct mlx5_fc_pool fc_pool; -}; - struct mlx5_events; struct mlx5_mpfs; struct mlx5_eswitch; @@ -553,6 +527,7 @@ enum { * creation/deletion on drivers rescan. Unset during device attach. */ MLX5_PRIV_FLAGS_DETACH = 1 << 2, + MLX5_PRIV_FLAGS_SWITCH_LEGACY = 1 << 3, }; struct mlx5_adev { @@ -628,7 +603,7 @@ struct mlx5_priv { struct mlx5_devcom_comp_dev *hca_devcom_comp; struct mlx5_fw_reset *fw_reset; struct mlx5_core_roce roce; - struct mlx5_fc_stats fc_stats; + struct mlx5_fc_stats *fc_stats; struct mlx5_rl_table rl_table; struct mlx5_ft_pool *ft_pool; @@ -643,6 +618,7 @@ struct mlx5_priv { struct mlx5_sf_hw_table *sf_hw_table; struct mlx5_sf_table *sf_table; #endif + struct blocking_notifier_head lag_nh; }; enum mlx5_device_state { @@ -718,7 +694,6 @@ struct mlx5_timer { struct timecounter tc; u32 nominal_c_mult; unsigned long overflow_period; - struct delayed_work overflow_work; }; struct mlx5_clock { @@ -766,6 +741,12 @@ struct mlx5_hca_cap { u32 max[MLX5_UN_SZ_DW(hca_cap_union)]; }; +enum mlx5_wc_state { + MLX5_WC_STATE_UNINITIALIZED, + MLX5_WC_STATE_UNSUPPORTED, + MLX5_WC_STATE_SUPPORTED, +}; + struct mlx5_core_dev { struct device *device; enum mlx5_coredev_type coredev_type; @@ -824,6 +805,9 @@ struct mlx5_core_dev { #endif u64 num_ipsec_offloads; struct mlx5_sd *sd; + enum mlx5_wc_state wc_state; + /* sync write combining state */ + struct mutex wc_state_lock; }; struct mlx5_db { @@ -862,6 +846,7 @@ struct mlx5_cmd_work_ent { void *context; int idx; struct completion handling; + struct completion slotted; struct completion done; struct mlx5_cmd *cmd; struct work_struct work; @@ -907,6 +892,7 @@ struct mlx5_hca_vport_context { u16 qkey_violation_counter; u16 pkey_violation_counter; bool grh_required; + u8 num_plane; }; #define STRUCT_FIELD(header, field) \ @@ -1170,7 +1156,6 @@ bool mlx5_lag_mode_is_hash(struct mlx5_core_dev *dev); bool mlx5_lag_is_master(struct mlx5_core_dev *dev); bool mlx5_lag_is_shared_fdb(struct mlx5_core_dev *dev); bool mlx5_lag_is_mpesw(struct mlx5_core_dev *dev); -struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev); u8 mlx5_lag_get_slave_port(struct mlx5_core_dev *dev, struct net_device *slave); int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev, @@ -1220,6 +1205,12 @@ static inline bool mlx5_core_is_vf(const struct mlx5_core_dev *dev) return dev->coredev_type == MLX5_COREDEV_VF; } +static inline bool mlx5_core_same_coredev_type(const struct mlx5_core_dev *dev1, + const struct mlx5_core_dev *dev2) +{ + return dev1->coredev_type == dev2->coredev_type; +} + static inline bool mlx5_core_is_ecpf(const struct mlx5_core_dev *dev) { return dev->caps.embedded_cpu; @@ -1375,10 +1366,5 @@ enum { MLX5_OCTWORD = 16, }; -struct msi_map mlx5_msix_alloc(struct mlx5_core_dev *dev, - irqreturn_t (*handler)(int, void *), - const struct irq_affinity_desc *affdesc, - const char *name); -void mlx5_msix_free(struct mlx5_core_dev *dev, struct msi_map map); - +bool mlx5_wc_support_get(struct mlx5_core_dev *mdev); #endif /* MLX5_DRIVER_H */ diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 3fb428ce7d1c..2a69d9d71276 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -163,7 +163,7 @@ struct mlx5_flow_destination { u32 tir_num; u32 ft_num; struct mlx5_flow_table *ft; - u32 counter_id; + struct mlx5_fc *counter; struct { u16 num; u16 vhca_id; @@ -298,10 +298,9 @@ int mlx5_modify_rule_destination(struct mlx5_flow_handle *handler, struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging); -/* As mlx5_fc_create() but doesn't queue stats refresh thread. */ -struct mlx5_fc *mlx5_fc_create_ex(struct mlx5_core_dev *dev, bool aging); - void mlx5_fc_destroy(struct mlx5_core_dev *dev, struct mlx5_fc *counter); +struct mlx5_fc *mlx5_fc_local_create(u32 counter_id, u32 offset, u32 bulk_size); +void mlx5_fc_local_destroy(struct mlx5_fc *counter); u64 mlx5_fc_query_lastuse(struct mlx5_fc *counter); void mlx5_fc_query_cached(struct mlx5_fc *counter, u64 *bytes, u64 *packets, u64 *lastuse); @@ -342,4 +341,7 @@ void mlx5_packet_reformat_dealloc(struct mlx5_core_dev *dev, struct mlx5_pkt_reformat *reformat); u32 mlx5_flow_table_id(struct mlx5_flow_table *ft); + +struct mlx5_flow_root_namespace * +mlx5_get_root_namespace(struct mlx5_core_dev *dev, enum mlx5_flow_namespace_type ns_type); #endif diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index c940b329a475..4f3716e124c9 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -80,23 +80,15 @@ enum { enum { MLX5_OBJ_TYPE_SW_ICM = 0x0008, - MLX5_OBJ_TYPE_HEADER_MODIFY_ARGUMENT = 0x23, -}; - -enum { - MLX5_GENERAL_OBJ_TYPES_CAP_SW_ICM = (1ULL << MLX5_OBJ_TYPE_SW_ICM), - MLX5_GENERAL_OBJ_TYPES_CAP_GENEVE_TLV_OPT = (1ULL << 11), - MLX5_GENERAL_OBJ_TYPES_CAP_VIRTIO_NET_Q = (1ULL << 13), - MLX5_GENERAL_OBJ_TYPES_CAP_HEADER_MODIFY_ARGUMENT = - (1ULL << MLX5_OBJ_TYPE_HEADER_MODIFY_ARGUMENT), - MLX5_GENERAL_OBJ_TYPES_CAP_MACSEC_OFFLOAD = (1ULL << 39), -}; - -enum { MLX5_OBJ_TYPE_GENEVE_TLV_OPT = 0x000b, MLX5_OBJ_TYPE_VIRTIO_NET_Q = 0x000d, MLX5_OBJ_TYPE_VIRTIO_Q_COUNTERS = 0x001c, MLX5_OBJ_TYPE_MATCH_DEFINER = 0x0018, + MLX5_OBJ_TYPE_HEADER_MODIFY_ARGUMENT = 0x23, + MLX5_OBJ_TYPE_STC = 0x0040, + MLX5_OBJ_TYPE_RTC = 0x0041, + MLX5_OBJ_TYPE_STE = 0x0042, + MLX5_OBJ_TYPE_MODIFY_HDR_PATTERN = 0x0043, MLX5_OBJ_TYPE_PAGE_TRACK = 0x46, MLX5_OBJ_TYPE_MKEY = 0xff01, MLX5_OBJ_TYPE_QP = 0xff02, @@ -112,6 +104,16 @@ enum { MLX5_OBJ_TYPE_RQT = 0xff0e, MLX5_OBJ_TYPE_FLOW_COUNTER = 0xff0f, MLX5_OBJ_TYPE_CQ = 0xff10, + MLX5_OBJ_TYPE_FT_ALIAS = 0xff15, +}; + +enum { + MLX5_GENERAL_OBJ_TYPES_CAP_SW_ICM = (1ULL << MLX5_OBJ_TYPE_SW_ICM), + MLX5_GENERAL_OBJ_TYPES_CAP_GENEVE_TLV_OPT = (1ULL << 11), + MLX5_GENERAL_OBJ_TYPES_CAP_VIRTIO_NET_Q = (1ULL << 13), + MLX5_GENERAL_OBJ_TYPES_CAP_HEADER_MODIFY_ARGUMENT = + (1ULL << MLX5_OBJ_TYPE_HEADER_MODIFY_ARGUMENT), + MLX5_GENERAL_OBJ_TYPES_CAP_MACSEC_OFFLOAD = (1ULL << 39), }; enum { @@ -313,6 +315,8 @@ enum { MLX5_CMD_OP_MODIFY_VHCA_STATE = 0xb0e, MLX5_CMD_OP_SYNC_CRYPTO = 0xb12, MLX5_CMD_OP_ALLOW_OTHER_VHCA_ACCESS = 0xb16, + MLX5_CMD_OP_GENERATE_WQE = 0xb17, + MLX5_CMD_OPCODE_QUERY_VUID = 0xb22, MLX5_CMD_OP_MAX }; @@ -416,7 +420,10 @@ struct mlx5_ifc_flow_table_fields_supported_bits { /* Table 2170 - Flow Table Fields Supported 2 Format */ struct mlx5_ifc_flow_table_fields_supported_2_bits { - u8 reserved_at_0[0xe]; + u8 reserved_at_0[0x2]; + u8 inner_l4_type[0x1]; + u8 outer_l4_type[0x1]; + u8 reserved_at_4[0xa]; u8 bth_opcode[0x1]; u8 reserved_at_f[0x1]; u8 tunnel_header_0_1[0x1]; @@ -482,7 +489,13 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 reserved_at_66[0x2]; u8 reformat_add_macsec[0x1]; u8 reformat_remove_macsec[0x1]; - u8 reserved_at_6a[0xe]; + u8 reparse[0x1]; + u8 reserved_at_6b[0x1]; + u8 cross_vhca_object[0x1]; + u8 reformat_l2_to_l3_audp_tunnel[0x1]; + u8 reformat_l3_audp_tunnel_to_l2[0x1]; + u8 ignore_flow_level_rtc_valid[0x1]; + u8 reserved_at_70[0x8]; u8 log_max_ft_num[0x8]; u8 reserved_at_80[0x10]; @@ -519,12 +532,26 @@ struct mlx5_ifc_ipv6_layout_bits { u8 ipv6[16][0x8]; }; +struct mlx5_ifc_ipv6_simple_layout_bits { + u8 ipv6_127_96[0x20]; + u8 ipv6_95_64[0x20]; + u8 ipv6_63_32[0x20]; + u8 ipv6_31_0[0x20]; +}; + union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits { + struct mlx5_ifc_ipv6_simple_layout_bits ipv6_simple_layout; struct mlx5_ifc_ipv6_layout_bits ipv6_layout; struct mlx5_ifc_ipv4_layout_bits ipv4_layout; u8 reserved_at_0[0x80]; }; +enum { + MLX5_PACKET_L4_TYPE_NONE, + MLX5_PACKET_L4_TYPE_TCP, + MLX5_PACKET_L4_TYPE_UDP, +}; + struct mlx5_ifc_fte_match_set_lyr_2_4_bits { u8 smac_47_16[0x20]; @@ -550,7 +577,8 @@ struct mlx5_ifc_fte_match_set_lyr_2_4_bits { u8 tcp_sport[0x10]; u8 tcp_dport[0x10]; - u8 reserved_at_c0[0x10]; + u8 l4_type[0x2]; + u8 reserved_at_c2[0xe]; u8 ipv4_ihl[0x4]; u8 reserved_at_c4[0x4]; @@ -783,7 +811,7 @@ struct mlx5_ifc_ads_bits { u8 reserved_at_2[0xe]; u8 pkey_index[0x10]; - u8 reserved_at_20[0x8]; + u8 plane_index[0x8]; u8 grh[0x1]; u8 mlid[0x7]; u8 rlid[0x10]; @@ -846,7 +874,11 @@ struct mlx5_ifc_flow_table_nic_cap_bits { struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_transmit_sniffer; - u8 reserved_at_e00[0x700]; + u8 reserved_at_e00[0x600]; + + struct mlx5_ifc_flow_table_fields_supported_2_bits ft_field_support_2_nic_receive; + + u8 reserved_at_1480[0x80]; struct mlx5_ifc_flow_table_fields_supported_2_bits ft_field_support_2_nic_receive_rdma; @@ -876,7 +908,9 @@ struct mlx5_ifc_port_selection_cap_bits { struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_port_selection; - u8 reserved_at_400[0x7c00]; + struct mlx5_ifc_flow_table_fields_supported_2_bits ft_field_support_2_port_selection; + + u8 reserved_at_480[0x7b80]; }; enum { @@ -895,7 +929,9 @@ struct mlx5_ifc_flow_table_eswitch_cap_bits { u8 reserved_at_8[0x5]; u8 fdb_uplink_hairpin[0x1]; u8 fdb_multi_path_any_table_limit_regc[0x1]; - u8 reserved_at_f[0x3]; + u8 reserved_at_f[0x1]; + u8 fdb_dynamic_tunnel[0x1]; + u8 reserved_at_11[0x1]; u8 fdb_multi_path_any_table[0x1]; u8 reserved_at_13[0x2]; u8 fdb_modify_header_fwd_to_table[0x1]; @@ -934,6 +970,73 @@ struct mlx5_ifc_flow_table_eswitch_cap_bits { u8 reserved_at_1900[0x6700]; }; +struct mlx5_ifc_wqe_based_flow_table_cap_bits { + u8 reserved_at_0[0x3]; + u8 log_max_num_ste[0x5]; + u8 reserved_at_8[0x3]; + u8 log_max_num_stc[0x5]; + u8 reserved_at_10[0x3]; + u8 log_max_num_rtc[0x5]; + u8 reserved_at_18[0x3]; + u8 log_max_num_header_modify_pattern[0x5]; + + u8 rtc_hash_split_table[0x1]; + u8 rtc_linear_lookup_table[0x1]; + u8 reserved_at_22[0x1]; + u8 stc_alloc_log_granularity[0x5]; + u8 reserved_at_28[0x3]; + u8 stc_alloc_log_max[0x5]; + u8 reserved_at_30[0x3]; + u8 ste_alloc_log_granularity[0x5]; + u8 reserved_at_38[0x3]; + u8 ste_alloc_log_max[0x5]; + + u8 reserved_at_40[0xb]; + u8 rtc_reparse_mode[0x5]; + u8 reserved_at_50[0x3]; + u8 rtc_index_mode[0x5]; + u8 reserved_at_58[0x3]; + u8 rtc_log_depth_max[0x5]; + + u8 reserved_at_60[0x10]; + u8 ste_format[0x10]; + + u8 stc_action_type[0x80]; + + u8 header_insert_type[0x10]; + u8 header_remove_type[0x10]; + + u8 trivial_match_definer[0x20]; + + u8 reserved_at_140[0x1b]; + u8 rtc_max_num_hash_definer_gen_wqe[0x5]; + + u8 reserved_at_160[0x18]; + u8 access_index_mode[0x8]; + + u8 reserved_at_180[0x10]; + u8 ste_format_gen_wqe[0x10]; + + u8 linear_match_definer_reg_c3[0x20]; + + u8 fdb_jump_to_tir_stc[0x1]; + u8 reserved_at_1c1[0x1f]; +}; + +struct mlx5_ifc_esw_cap_bits { + u8 reserved_at_0[0x1d]; + u8 merged_eswitch[0x1]; + u8 reserved_at_1e[0x2]; + + u8 reserved_at_20[0x40]; + + u8 esw_manager_vport_number_valid[0x1]; + u8 reserved_at_61[0xf]; + u8 esw_manager_vport_number[0x10]; + + u8 reserved_at_80[0x780]; +}; + enum { MLX5_COUNTER_SOURCE_ESWITCH = 0x0, MLX5_COUNTER_FLOW_ESWITCH = 0x1, @@ -992,7 +1095,9 @@ struct mlx5_ifc_qos_cap_bits { u8 log_esw_max_sched_depth[0x4]; u8 reserved_at_10[0x10]; - u8 reserved_at_20[0xb]; + u8 reserved_at_20[0x9]; + u8 esw_cross_esw_sched[0x1]; + u8 reserved_at_2a[0x1]; u8 log_max_qos_nic_queue_group[0x5]; u8 reserved_at_30[0x10]; @@ -1000,7 +1105,8 @@ struct mlx5_ifc_qos_cap_bits { u8 packet_pacing_min_rate[0x20]; - u8 reserved_at_80[0x10]; + u8 reserved_at_80[0xb]; + u8 log_esw_max_rate_limit[0x5]; u8 packet_pacing_rate_table_size[0x10]; u8 esw_element_type[0x10]; @@ -1011,7 +1117,8 @@ struct mlx5_ifc_qos_cap_bits { u8 max_tsar_bw_share[0x20]; - u8 reserved_at_100[0x20]; + u8 nic_element_type[0x10]; + u8 nic_tsar_type[0x10]; u8 reserved_at_120[0x3]; u8 log_meter_aso_granularity[0x5]; @@ -1077,7 +1184,8 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits { u8 tunnel_stateless_ip_over_ip_tx[0x1]; u8 reserved_at_2e[0x2]; u8 max_vxlan_udp_ports[0x8]; - u8 reserved_at_38[0x6]; + u8 swp_csum_l4_partial[0x1]; + u8 reserved_at_39[0x5]; u8 max_geneve_opt_len[0x1]; u8 tunnel_stateless_geneve_rx[0x1]; @@ -1308,11 +1416,13 @@ struct mlx5_ifc_atomic_caps_bits { u8 reserved_at_e0[0x720]; }; -struct mlx5_ifc_odp_cap_bits { +struct mlx5_ifc_odp_scheme_cap_bits { u8 reserved_at_0[0x40]; u8 sig[0x1]; - u8 reserved_at_41[0x1f]; + u8 reserved_at_41[0x4]; + u8 page_prefetch[0x1]; + u8 reserved_at_46[0x1a]; u8 reserved_at_60[0x20]; @@ -1326,7 +1436,20 @@ struct mlx5_ifc_odp_cap_bits { struct mlx5_ifc_odp_per_transport_service_cap_bits dc_odp_caps; - u8 reserved_at_120[0x6E0]; + u8 reserved_at_120[0xe0]; +}; + +struct mlx5_ifc_odp_cap_bits { + struct mlx5_ifc_odp_scheme_cap_bits transport_page_fault_scheme_cap; + + struct mlx5_ifc_odp_scheme_cap_bits memory_page_fault_scheme_cap; + + u8 reserved_at_400[0x200]; + + u8 mem_page_fault[0x1]; + u8 reserved_at_601[0x1f]; + + u8 reserved_at_620[0x1e0]; }; struct mlx5_ifc_tls_cap_bits { @@ -1426,9 +1549,13 @@ enum { }; enum { + MLX5_FLEX_IPV4_OVER_VXLAN_ENABLED = 1 << 0, + MLX5_FLEX_IPV6_OVER_VXLAN_ENABLED = 1 << 1, + MLX5_FLEX_IPV6_OVER_IP_ENABLED = 1 << 2, MLX5_FLEX_PARSER_GENEVE_ENABLED = 1 << 3, MLX5_FLEX_PARSER_MPLS_OVER_GRE_ENABLED = 1 << 4, MLX5_FLEX_PARSER_MPLS_OVER_UDP_ENABLED = 1 << 5, + MLX5_FLEX_P_BIT_VXLAN_GPE_ENABLED = 1 << 6, MLX5_FLEX_PARSER_VXLAN_GPE_ENABLED = 1 << 7, MLX5_FLEX_PARSER_ICMP_V4_ENABLED = 1 << 8, MLX5_FLEX_PARSER_ICMP_V6_ENABLED = 1 << 9, @@ -1466,10 +1593,14 @@ enum { MLX5_STEERING_FORMAT_CONNECTX_5 = 0, MLX5_STEERING_FORMAT_CONNECTX_6DX = 1, MLX5_STEERING_FORMAT_CONNECTX_7 = 2, + MLX5_STEERING_FORMAT_CONNECTX_8 = 3, }; struct mlx5_ifc_cmd_hca_cap_bits { - u8 reserved_at_0[0x10]; + u8 reserved_at_0[0x6]; + u8 page_request_disable[0x1]; + u8 abs_native_port_num[0x1]; + u8 reserved_at_8[0x8]; u8 shared_object_to_user_object_allowed[0x1]; u8 reserved_at_13[0xe]; u8 vhca_resource_manager[0x1]; @@ -1508,8 +1639,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 ts_cqe_to_dest_cqn[0x1]; u8 reserved_at_b3[0x6]; u8 go_back_n[0x1]; - u8 shampo[0x1]; - u8 reserved_at_bb[0x5]; + u8 reserved_at_ba[0x6]; u8 max_sgl_for_optimized_performance[0x8]; u8 log_max_cq_sz[0x8]; @@ -1632,7 +1762,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 pci_sync_for_fw_update_event[0x1]; u8 reserved_at_1f2[0x6]; u8 init2_lag_tx_port_affinity[0x1]; - u8 reserved_at_1fa[0x3]; + u8 reserved_at_1fa[0x2]; + u8 wqe_based_flow_table_update_cap[0x1]; u8 cqe_version[0x4]; u8 compact_address_vector[0x1]; @@ -1668,7 +1799,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 cq_oi[0x1]; u8 cq_resize[0x1]; u8 cq_moderation[0x1]; - u8 reserved_at_223[0x3]; + u8 cq_period_mode_modify[0x1]; + u8 reserved_at_224[0x2]; u8 cq_eq_remap[0x1]; u8 pg[0x1]; u8 block_lb_mc[0x1]; @@ -1698,7 +1830,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 regexp_params[0x1]; u8 uar_sz[0x6]; u8 port_selection_cap[0x1]; - u8 reserved_at_251[0x1]; + u8 nic_cap_reg[0x1]; u8 umem_uid_0[0x1]; u8 reserved_at_253[0x5]; u8 log_pg_sz[0x8]; @@ -1725,7 +1857,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_280[0x10]; u8 max_wqe_sz_sq[0x10]; - u8 reserved_at_2a0[0x10]; + u8 reserved_at_2a0[0xb]; + u8 shampo[0x1]; + u8 reserved_at_2ac[0x4]; u8 max_wqe_sz_rq[0x10]; u8 max_flow_counter_31_16[0x10]; @@ -1743,7 +1877,12 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_328[0x2]; u8 relaxed_ordering_read[0x1]; u8 log_max_pd[0x5]; - u8 reserved_at_330[0x6]; + u8 dp_ordering_ooo_all_ud[0x1]; + u8 dp_ordering_ooo_all_uc[0x1]; + u8 dp_ordering_ooo_all_xrc[0x1]; + u8 dp_ordering_ooo_all_dc[0x1]; + u8 dp_ordering_ooo_all_rc[0x1]; + u8 pcie_reset_using_hotreset_method[0x1]; u8 pci_sync_for_fw_update_with_driver_unload[0x1]; u8 vnic_env_cnt_steering_fail[0x1]; u8 vport_counter_local_loopback[0x1]; @@ -1864,7 +2003,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_5a0[0x10]; u8 enhanced_cqe_compression[0x1]; - u8 reserved_at_5b1[0x2]; + u8 reserved_at_5b1[0x1]; + u8 crossing_vhca_mkey[0x1]; u8 log_max_dek[0x5]; u8 reserved_at_5b8[0x4]; u8 mini_cqe_resp_stride_index[0x1]; @@ -1933,12 +2073,14 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 dynamic_msix_table_size[0xc]; u8 reserved_at_740[0xc]; u8 min_dynamic_vf_msix_table_size[0x4]; - u8 reserved_at_750[0x4]; + u8 reserved_at_750[0x2]; + u8 data_direct[0x1]; + u8 reserved_at_753[0x1]; u8 max_dynamic_vf_msix_table_size[0xc]; u8 reserved_at_760[0x3]; u8 log_max_num_header_modify_argument[0x5]; - u8 reserved_at_768[0x4]; + u8 log_header_modify_argument_granularity_offset[0x4]; u8 log_header_modify_argument_granularity[0x4]; u8 reserved_at_770[0x3]; u8 log_header_modify_argument_max_alloc[0x5]; @@ -1961,7 +2103,13 @@ struct mlx5_ifc_cmd_hca_cap_2_bits { u8 reserved_at_0[0x80]; u8 migratable[0x1]; - u8 reserved_at_81[0x1f]; + u8 reserved_at_81[0x7]; + u8 dp_ordering_force[0x1]; + u8 reserved_at_89[0x9]; + u8 query_vuid[0x1]; + u8 reserved_at_93[0x5]; + u8 umr_log_entity_size_5[0x1]; + u8 reserved_at_99[0x7]; u8 max_reformat_insert_size[0x8]; u8 max_reformat_insert_offset[0x8]; @@ -1971,9 +2119,14 @@ struct mlx5_ifc_cmd_hca_cap_2_bits { u8 reserved_at_c0[0x8]; u8 migration_multi_load[0x1]; u8 migration_tracking_state[0x1]; - u8 reserved_at_ca[0x6]; + u8 multiplane_qp_ud[0x1]; + u8 reserved_at_cb[0x5]; u8 migration_in_chunks[0x1]; - u8 reserved_at_d1[0xf]; + u8 reserved_at_d1[0x1]; + u8 sf_eq_usage[0x1]; + u8 reserved_at_d3[0x5]; + u8 multiplane[0x1]; + u8 reserved_at_d9[0x7]; u8 cross_vhca_object_to_object_supported[0x20]; @@ -1982,7 +2135,8 @@ struct mlx5_ifc_cmd_hca_cap_2_bits { u8 reserved_at_140[0x60]; u8 flow_table_type_2_type[0x8]; - u8 reserved_at_1a8[0x3]; + u8 reserved_at_1a8[0x2]; + u8 format_select_dw_8_6_ext[0x1]; u8 log_min_mkey_entity_size[0x5]; u8 reserved_at_1b0[0x10]; @@ -1997,14 +2151,42 @@ struct mlx5_ifc_cmd_hca_cap_2_bits { u8 ts_cqe_metadata_size2wqe_counter[0x5]; u8 reserved_at_250[0x10]; - u8 reserved_at_260[0x120]; - u8 reserved_at_380[0x10]; + u8 reserved_at_260[0x20]; + + u8 format_select_dw_gtpu_dw_0[0x8]; + u8 format_select_dw_gtpu_dw_1[0x8]; + u8 format_select_dw_gtpu_dw_2[0x8]; + u8 format_select_dw_gtpu_first_ext_dw_0[0x8]; + + u8 generate_wqe_type[0x20]; + + u8 reserved_at_2c0[0xc0]; + + u8 reserved_at_380[0xb]; + u8 min_mkey_log_entity_size_fixed_buffer[0x5]; u8 ec_vf_vport_base[0x10]; - u8 reserved_at_3a0[0x10]; + u8 reserved_at_3a0[0xa]; + u8 max_mkey_log_entity_size_mtt[0x6]; u8 max_rqt_vhca_id[0x10]; - u8 reserved_at_3c0[0x440]; + u8 reserved_at_3c0[0x20]; + + u8 reserved_at_3e0[0x10]; + u8 pcc_ifa2[0x1]; + u8 reserved_at_3f1[0xf]; + + u8 reserved_at_400[0x1]; + u8 min_mkey_log_entity_size_fixed_buffer_valid[0x1]; + u8 reserved_at_402[0xe]; + u8 return_reg_id[0x10]; + + u8 reserved_at_420[0x1c]; + u8 flow_table_hash_type[0x4]; + + u8 reserved_at_440[0x8]; + u8 max_num_eqs_24b[0x18]; + u8 reserved_at_460[0x3a0]; }; enum mlx5_ifc_flow_destination_type { @@ -2047,7 +2229,7 @@ struct mlx5_ifc_extended_dest_format_bits { u8 reserved_at_60[0x20]; }; -union mlx5_ifc_dest_format_struct_flow_counter_list_auto_bits { +union mlx5_ifc_dest_format_flow_counter_list_auto_bits { struct mlx5_ifc_extended_dest_format_bits extended_dest_format; struct mlx5_ifc_flow_counter_list_bits flow_counter_list; }; @@ -2139,12 +2321,17 @@ struct mlx5_ifc_wq_bits { u8 reserved_at_139[0x4]; u8 log_wqe_stride_size[0x3]; - u8 reserved_at_140[0x80]; + u8 dbr_umem_id[0x20]; + u8 wq_umem_id[0x20]; + + u8 wq_umem_offset[0x40]; u8 headers_mkey[0x20]; u8 shampo_enable[0x1]; - u8 reserved_at_1e1[0x4]; + u8 reserved_at_1e1[0x1]; + u8 shampo_mode[0x2]; + u8 reserved_at_1e4[0x1]; u8 log_reservation_size[0x3]; u8 reserved_at_1e8[0x5]; u8 log_max_num_of_packets_per_reservation[0x3]; @@ -2625,6 +2812,46 @@ struct mlx5_ifc_ib_port_cntrs_grp_data_layout_bits { u8 port_xmit_wait[0x20]; }; +struct mlx5_ifc_ib_ext_port_cntrs_grp_data_layout_bits { + u8 reserved_at_0[0x300]; + + u8 port_xmit_data_high[0x20]; + + u8 port_xmit_data_low[0x20]; + + u8 port_rcv_data_high[0x20]; + + u8 port_rcv_data_low[0x20]; + + u8 port_xmit_pkts_high[0x20]; + + u8 port_xmit_pkts_low[0x20]; + + u8 port_rcv_pkts_high[0x20]; + + u8 port_rcv_pkts_low[0x20]; + + u8 reserved_at_400[0x80]; + + u8 port_unicast_xmit_pkts_high[0x20]; + + u8 port_unicast_xmit_pkts_low[0x20]; + + u8 port_multicast_xmit_pkts_high[0x20]; + + u8 port_multicast_xmit_pkts_low[0x20]; + + u8 port_unicast_rcv_pkts_high[0x20]; + + u8 port_unicast_rcv_pkts_low[0x20]; + + u8 port_multicast_rcv_pkts_high[0x20]; + + u8 port_multicast_rcv_pkts_low[0x20]; + + u8 reserved_at_580[0x240]; +}; + struct mlx5_ifc_eth_per_tc_prio_grp_data_layout_bits { u8 transmit_queue_high[0x20]; @@ -3102,6 +3329,14 @@ struct mlx5_ifc_dropped_packet_logged_bits { u8 reserved_at_0[0xe0]; }; +struct mlx5_ifc_nic_cap_reg_bits { + u8 reserved_at_0[0x1a]; + u8 vhca_icm_ctrl[0x1]; + u8 reserved_at_1b[0x5]; + + u8 reserved_at_20[0x60]; +}; + struct mlx5_ifc_default_timeout_bits { u8 to_multiplier[0x3]; u8 reserved_at_3[0x9]; @@ -3138,6 +3373,18 @@ struct mlx5_ifc_dtor_reg_bits { u8 reserved_at_1c0[0x20]; }; +struct mlx5_ifc_vhca_icm_ctrl_reg_bits { + u8 vhca_id_valid[0x1]; + u8 reserved_at_1[0xf]; + u8 vhca_id[0x10]; + + u8 reserved_at_20[0xa0]; + + u8 cur_alloc_icm[0x20]; + + u8 reserved_at_e0[0x120]; +}; + enum { MLX5_CQ_ERROR_SYNDROME_CQ_OVERRUN = 0x1, MLX5_CQ_ERROR_SYNDROME_CQ_ACCESS_VIOLATION_ERROR = 0x2, @@ -3312,7 +3559,8 @@ struct mlx5_ifc_qpc_bits { u8 latency_sensitive[0x1]; u8 reserved_at_24[0x1]; u8 drain_sigerr[0x1]; - u8 reserved_at_26[0x2]; + u8 reserved_at_26[0x1]; + u8 dp_ordering_force[0x1]; u8 pd[0x18]; u8 mtu[0x3]; @@ -3385,7 +3633,8 @@ struct mlx5_ifc_qpc_bits { u8 rae[0x1]; u8 reserved_at_493[0x1]; u8 page_offset[0x6]; - u8 reserved_at_49a[0x3]; + u8 reserved_at_49a[0x2]; + u8 dp_ordering_1[0x1]; u8 cd_slave_receive[0x1]; u8 cd_slave_send[0x1]; u8 cd_master[0x1]; @@ -3474,6 +3723,22 @@ struct mlx5_ifc_crypto_cap_bits { u8 reserved_at_80[0x780]; }; +struct mlx5_ifc_shampo_cap_bits { + u8 reserved_at_0[0x3]; + u8 shampo_log_max_reservation_size[0x5]; + u8 reserved_at_8[0x3]; + u8 shampo_log_min_reservation_size[0x5]; + u8 shampo_min_mss_size[0x10]; + + u8 shampo_header_split[0x1]; + u8 shampo_header_split_data_merge[0x1]; + u8 reserved_at_22[0x1]; + u8 shampo_log_max_headers_entry_size[0x5]; + u8 reserved_at_28[0x18]; + + u8 reserved_at_40[0x7c0]; +}; + union mlx5_ifc_hca_cap_union_bits { struct mlx5_ifc_cmd_hca_cap_bits cmd_hca_cap; struct mlx5_ifc_cmd_hca_cap_2_bits cmd_hca_cap_2; @@ -3483,6 +3748,8 @@ union mlx5_ifc_hca_cap_union_bits { struct mlx5_ifc_per_protocol_networking_offload_caps_bits per_protocol_networking_offload_caps; struct mlx5_ifc_flow_table_nic_cap_bits flow_table_nic_cap; struct mlx5_ifc_flow_table_eswitch_cap_bits flow_table_eswitch_cap; + struct mlx5_ifc_wqe_based_flow_table_cap_bits wqe_based_flow_table_cap; + struct mlx5_ifc_esw_cap_bits esw_cap; struct mlx5_ifc_e_switch_cap_bits e_switch_cap; struct mlx5_ifc_port_selection_cap_bits port_selection_cap; struct mlx5_ifc_qos_cap_bits qos_cap; @@ -3599,7 +3866,7 @@ struct mlx5_ifc_flow_context_bits { u8 reserved_at_1300[0x500]; - union mlx5_ifc_dest_format_struct_flow_counter_list_auto_bits destination[]; + union mlx5_ifc_dest_format_flow_counter_list_auto_bits destination[]; }; enum { @@ -3840,7 +4107,8 @@ struct mlx5_ifc_sqc_bits { u8 reg_umr[0x1]; u8 allow_swp[0x1]; u8 hairpin[0x1]; - u8 reserved_at_f[0xb]; + u8 non_wire[0x1]; + u8 reserved_at_10[0xa]; u8 ts_format[0x2]; u8 reserved_at_1c[0x4]; @@ -3880,20 +4148,65 @@ enum { SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT_TC = 0x2, SCHEDULING_CONTEXT_ELEMENT_TYPE_PARA_VPORT_TC = 0x3, SCHEDULING_CONTEXT_ELEMENT_TYPE_QUEUE_GROUP = 0x4, + SCHEDULING_CONTEXT_ELEMENT_TYPE_RATE_LIMIT = 0x5, }; enum { - ELEMENT_TYPE_CAP_MASK_TASR = 1 << 0, + ELEMENT_TYPE_CAP_MASK_TSAR = 1 << 0, ELEMENT_TYPE_CAP_MASK_VPORT = 1 << 1, ELEMENT_TYPE_CAP_MASK_VPORT_TC = 1 << 2, ELEMENT_TYPE_CAP_MASK_PARA_VPORT_TC = 1 << 3, + ELEMENT_TYPE_CAP_MASK_QUEUE_GROUP = 1 << 4, + ELEMENT_TYPE_CAP_MASK_RATE_LIMIT = 1 << 5, +}; + +enum { + TSAR_ELEMENT_TSAR_TYPE_DWRR = 0x0, + TSAR_ELEMENT_TSAR_TYPE_ROUND_ROBIN = 0x1, + TSAR_ELEMENT_TSAR_TYPE_ETS = 0x2, + TSAR_ELEMENT_TSAR_TYPE_TC_ARB = 0x3, +}; + +enum { + TSAR_TYPE_CAP_MASK_DWRR = 1 << 0, + TSAR_TYPE_CAP_MASK_ROUND_ROBIN = 1 << 1, + TSAR_TYPE_CAP_MASK_ETS = 1 << 2, + TSAR_TYPE_CAP_MASK_TC_ARB = 1 << 3, +}; + +struct mlx5_ifc_tsar_element_bits { + u8 traffic_class[0x4]; + u8 reserved_at_4[0x4]; + u8 tsar_type[0x8]; + u8 reserved_at_10[0x10]; +}; + +struct mlx5_ifc_vport_element_bits { + u8 reserved_at_0[0x4]; + u8 eswitch_owner_vhca_id_valid[0x1]; + u8 eswitch_owner_vhca_id[0xb]; + u8 vport_number[0x10]; +}; + +struct mlx5_ifc_vport_tc_element_bits { + u8 traffic_class[0x4]; + u8 eswitch_owner_vhca_id_valid[0x1]; + u8 eswitch_owner_vhca_id[0xb]; + u8 vport_number[0x10]; +}; + +union mlx5_ifc_element_attributes_bits { + struct mlx5_ifc_tsar_element_bits tsar; + struct mlx5_ifc_vport_element_bits vport; + struct mlx5_ifc_vport_tc_element_bits vport_tc; + u8 reserved_at_0[0x20]; }; struct mlx5_ifc_scheduling_context_bits { u8 element_type[0x8]; u8 reserved_at_8[0x18]; - u8 element_attributes[0x20]; + union mlx5_ifc_element_attributes_bits element_attributes; u8 parent_element_id[0x20]; @@ -3903,7 +4216,9 @@ struct mlx5_ifc_scheduling_context_bits { u8 max_average_bw[0x20]; - u8 reserved_at_e0[0x120]; + u8 max_bw_obj_id[0x20]; + + u8 reserved_at_100[0x100]; }; struct mlx5_ifc_rqtc_bits { @@ -4075,6 +4390,7 @@ enum { MLX5_MKC_ACCESS_MODE_KSM = 0x3, MLX5_MKC_ACCESS_MODE_SW_ICM = 0x4, MLX5_MKC_ACCESS_MODE_MEMIC = 0x5, + MLX5_MKC_ACCESS_MODE_CROSSING = 0x6, }; struct mlx5_ifc_mkc_bits { @@ -4117,14 +4433,16 @@ struct mlx5_ifc_mkc_bits { u8 bsf_octword_size[0x20]; - u8 reserved_at_120[0x80]; + u8 reserved_at_120[0x60]; + + u8 crossing_target_vhca_id[0x10]; + u8 reserved_at_190[0x10]; u8 translations_octword_size[0x20]; u8 reserved_at_1c0[0x19]; u8 relaxed_ordering_read[0x1]; - u8 reserved_at_1d9[0x1]; - u8 log_page_size[0x5]; + u8 log_page_size[0x6]; u8 reserved_at_1e0[0x20]; }; @@ -4147,7 +4465,8 @@ struct mlx5_ifc_hca_vport_context_bits { u8 has_smi[0x1]; u8 has_raw[0x1]; u8 grh_required[0x1]; - u8 reserved_at_104[0xc]; + u8 reserved_at_104[0x4]; + u8 num_port_plane[0x8]; u8 port_physical_state[0x4]; u8 vport_state_policy[0x4]; u8 port_state[0x4]; @@ -4287,7 +4606,8 @@ struct mlx5_ifc_dctc_bits { u8 state[0x4]; u8 reserved_at_8[0x18]; - u8 reserved_at_20[0x8]; + u8 reserved_at_20[0x7]; + u8 dp_ordering_force[0x1]; u8 user_index[0x18]; u8 reserved_at_40[0x8]; @@ -4302,7 +4622,9 @@ struct mlx5_ifc_dctc_bits { u8 latency_sensitive[0x1]; u8 rlky[0x1]; u8 free_ar[0x1]; - u8 reserved_at_73[0xd]; + u8 reserved_at_73[0x1]; + u8 dp_ordering_1[0x1]; + u8 reserved_at_75[0xb]; u8 reserved_at_80[0x8]; u8 cs_res[0x8]; @@ -4361,10 +4683,10 @@ enum { MLX5_CQC_ST_FIRED = 0xa, }; -enum { +enum mlx5_cq_period_mode { MLX5_CQ_PERIOD_MODE_START_FROM_EQE = 0x0, MLX5_CQ_PERIOD_MODE_START_FROM_CQE = 0x1, - MLX5_CQ_PERIOD_NUM_MODES + MLX5_CQ_PERIOD_NUM_MODES, }; struct mlx5_ifc_cqc_bits { @@ -4516,6 +4838,7 @@ union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits { struct mlx5_ifc_eth_per_tc_prio_grp_data_layout_bits eth_per_tc_prio_grp_data_layout; struct mlx5_ifc_eth_per_tc_congest_prio_grp_data_layout_bits eth_per_tc_congest_prio_grp_data_layout; struct mlx5_ifc_ib_port_cntrs_grp_data_layout_bits ib_port_cntrs_grp_data_layout; + struct mlx5_ifc_ib_ext_port_cntrs_grp_data_layout_bits ib_ext_port_cntrs_grp_data_layout; struct mlx5_ifc_phys_layer_cntrs_bits phys_layer_cntrs; struct mlx5_ifc_phys_layer_statistical_cntrs_bits phys_layer_statistical_cntrs; u8 reserved_at_0[0x7c0]; @@ -4577,29 +4900,6 @@ struct mlx5_ifc_register_loopback_control_bits { u8 reserved_at_20[0x60]; }; -struct mlx5_ifc_vport_tc_element_bits { - u8 traffic_class[0x4]; - u8 reserved_at_4[0xc]; - u8 vport_number[0x10]; -}; - -struct mlx5_ifc_vport_element_bits { - u8 reserved_at_0[0x10]; - u8 vport_number[0x10]; -}; - -enum { - TSAR_ELEMENT_TSAR_TYPE_DWRR = 0x0, - TSAR_ELEMENT_TSAR_TYPE_ROUND_ROBIN = 0x1, - TSAR_ELEMENT_TSAR_TYPE_ETS = 0x2, -}; - -struct mlx5_ifc_tsar_element_bits { - u8 reserved_at_0[0x8]; - u8 tsar_type[0x8]; - u8 reserved_at_10[0x10]; -}; - enum { MLX5_TEARDOWN_HCA_OUT_FORCE_STATE_SUCCESS = 0x0, MLX5_TEARDOWN_HCA_OUT_FORCE_STATE_FAIL = 0x1, @@ -4880,6 +5180,16 @@ struct mlx5_ifc_set_fte_in_bits { struct mlx5_ifc_flow_context_bits flow_context; }; +struct mlx5_ifc_dest_format_bits { + u8 destination_type[0x8]; + u8 destination_id[0x18]; + + u8 destination_eswitch_owner_vhca_id_valid[0x1]; + u8 packet_reformat[0x1]; + u8 reserved_at_22[0xe]; + u8 destination_eswitch_owner_vhca_id[0x10]; +}; + struct mlx5_ifc_rts2rts_qp_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; @@ -5043,6 +5353,36 @@ struct mlx5_ifc_query_vport_state_out_bits { u8 state[0x4]; }; +struct mlx5_ifc_array1024_auto_bits { + u8 array1024_auto[32][0x20]; +}; + +struct mlx5_ifc_query_vuid_in_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + + u8 reserved_at_20[0x40]; + + u8 query_vfs_vuid[0x1]; + u8 data_direct[0x1]; + u8 reserved_at_62[0xe]; + u8 vhca_id[0x10]; +}; + +struct mlx5_ifc_query_vuid_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x1a0]; + + u8 reserved_at_1e0[0x10]; + u8 num_of_entries[0x10]; + + struct mlx5_ifc_array1024_auto_bits vuid[]; +}; + enum { MLX5_VPORT_STATE_OP_MOD_VNIC_VPORT = 0x0, MLX5_VPORT_STATE_OP_MOD_ESW_VPORT = 0x1, @@ -5604,7 +5944,11 @@ struct mlx5_ifc_query_q_counter_out_bits { u8 local_ack_timeout_err[0x20]; - u8 reserved_at_320[0xa0]; + u8 reserved_at_320[0x60]; + + u8 req_rnr_retries_exceeded[0x20]; + + u8 reserved_at_3a0[0x20]; u8 resp_local_length_error[0x20]; @@ -6035,6 +6379,20 @@ struct mlx5_ifc_modify_other_hca_cap_in_bits { struct mlx5_ifc_other_hca_cap_bits other_capability; }; +struct mlx5_ifc_sw_owner_icm_root_params_bits { + u8 sw_owner_icm_root_1[0x40]; + + u8 sw_owner_icm_root_0[0x40]; +}; + +struct mlx5_ifc_rtc_params_bits { + u8 rtc_id_0[0x20]; + + u8 rtc_id_1[0x20]; + + u8 reserved_at_40[0x40]; +}; + struct mlx5_ifc_flow_table_context_bits { u8 reformat_en[0x1]; u8 decap_en[0x1]; @@ -6042,7 +6400,8 @@ struct mlx5_ifc_flow_table_context_bits { u8 termination_table[0x1]; u8 table_miss_action[0x4]; u8 level[0x8]; - u8 reserved_at_10[0x8]; + u8 rtc_valid[0x1]; + u8 reserved_at_11[0x7]; u8 log_size[0x8]; u8 reserved_at_20[0x8]; @@ -6053,10 +6412,10 @@ struct mlx5_ifc_flow_table_context_bits { u8 reserved_at_60[0x60]; - u8 sw_owner_icm_root_1[0x40]; - - u8 sw_owner_icm_root_0[0x40]; - + union { + struct mlx5_ifc_sw_owner_icm_root_params_bits sws; + struct mlx5_ifc_rtc_params_bits hws; + }; }; struct mlx5_ifc_query_flow_table_out_bits { @@ -6704,6 +7063,7 @@ struct mlx5_ifc_alloc_packet_reformat_context_out_bits { enum { MLX5_REFORMAT_CONTEXT_ANCHOR_MAC_START = 0x1, + MLX5_REFORMAT_CONTEXT_ANCHOR_VLAN_START = 0x2, MLX5_REFORMAT_CONTEXT_ANCHOR_IP_START = 0x7, MLX5_REFORMAT_CONTEXT_ANCHOR_TCP_UDP_START = 0x9, }; @@ -7132,6 +7492,30 @@ struct mlx5_ifc_qp_2err_in_bits { u8 reserved_at_60[0x20]; }; +struct mlx5_ifc_trans_page_fault_info_bits { + u8 error[0x1]; + u8 reserved_at_1[0x4]; + u8 page_fault_type[0x3]; + u8 wq_number[0x18]; + + u8 reserved_at_20[0x8]; + u8 fault_token[0x18]; +}; + +struct mlx5_ifc_mem_page_fault_info_bits { + u8 error[0x1]; + u8 reserved_at_1[0xf]; + u8 fault_token_47_32[0x10]; + + u8 fault_token_31_0[0x20]; +}; + +union mlx5_ifc_page_fault_resume_in_page_fault_info_auto_bits { + struct mlx5_ifc_trans_page_fault_info_bits trans_page_fault_info; + struct mlx5_ifc_mem_page_fault_info_bits mem_page_fault_info; + u8 reserved_at_0[0x40]; +}; + struct mlx5_ifc_page_fault_resume_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; @@ -7148,13 +7532,8 @@ struct mlx5_ifc_page_fault_resume_in_bits { u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 error[0x1]; - u8 reserved_at_41[0x4]; - u8 page_fault_type[0x3]; - u8 wq_number[0x18]; - - u8 reserved_at_60[0x8]; - u8 token[0x18]; + union mlx5_ifc_page_fault_resume_in_page_fault_info_auto_bits + page_fault_info; }; struct mlx5_ifc_nop_out_bits { @@ -7663,7 +8042,7 @@ struct mlx5_ifc_mad_ifc_in_bits { u8 op_mod[0x10]; u8 remote_lid[0x10]; - u8 reserved_at_50[0x8]; + u8 plane_index[0x8]; u8 port[0x8]; u8 reserved_at_60[0x20]; @@ -8838,7 +9217,9 @@ struct mlx5_ifc_create_qp_in_bits { struct mlx5_ifc_qpc_bits qpc; - u8 reserved_at_800[0x60]; + u8 wq_umem_offset[0x40]; + + u8 wq_umem_id[0x20]; u8 wq_umem_valid[0x1]; u8 reserved_at_861[0x1f]; @@ -8904,7 +9285,8 @@ struct mlx5_ifc_create_mkey_in_bits { u8 pg_access[0x1]; u8 mkey_umem_valid[0x1]; - u8 reserved_at_62[0x1e]; + u8 data_direct[0x1]; + u8 reserved_at_63[0x1d]; struct mlx5_ifc_mkc_bits memory_key_mkey_entry; @@ -9592,7 +9974,9 @@ struct mlx5_ifc_ptys_reg_bits { u8 an_disable_cap[0x1]; u8 reserved_at_3[0x5]; u8 local_port[0x8]; - u8 reserved_at_10[0xd]; + u8 reserved_at_10[0x8]; + u8 plane_ind[0x4]; + u8 reserved_at_1c[0x1]; u8 proto_mask[0x3]; u8 an_status[0x4]; @@ -9793,7 +10177,35 @@ struct mlx5_ifc_pplm_reg_bits { u8 fec_override_admin_100g_2x[0x10]; u8 fec_override_admin_50g_1x[0x10]; - u8 reserved_at_140[0x140]; + u8 fec_override_cap_800g_8x[0x10]; + u8 fec_override_cap_400g_4x[0x10]; + + u8 fec_override_cap_200g_2x[0x10]; + u8 fec_override_cap_100g_1x[0x10]; + + u8 reserved_at_180[0xa0]; + + u8 fec_override_admin_800g_8x[0x10]; + u8 fec_override_admin_400g_4x[0x10]; + + u8 fec_override_admin_200g_2x[0x10]; + u8 fec_override_admin_100g_1x[0x10]; + + u8 reserved_at_260[0x60]; + + u8 fec_override_cap_1600g_8x[0x10]; + u8 fec_override_cap_800g_4x[0x10]; + + u8 fec_override_cap_400g_2x[0x10]; + u8 fec_override_cap_200g_1x[0x10]; + + u8 fec_override_admin_1600g_8x[0x10]; + u8 fec_override_admin_800g_4x[0x10]; + + u8 fec_override_admin_400g_2x[0x10]; + u8 fec_override_admin_200g_1x[0x10]; + + u8 reserved_at_340[0x80]; }; struct mlx5_ifc_ppcnt_reg_bits { @@ -9804,8 +10216,10 @@ struct mlx5_ifc_ppcnt_reg_bits { u8 grp[0x6]; u8 clr[0x1]; - u8 reserved_at_21[0x1c]; - u8 prio_tc[0x3]; + u8 reserved_at_21[0x13]; + u8 plane_ind[0x4]; + u8 reserved_at_38[0x3]; + u8 prio_tc[0x5]; union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits counter_set; }; @@ -10165,7 +10579,11 @@ struct mlx5_ifc_mtutc_reg_bits { }; struct mlx5_ifc_pcam_enhanced_features_bits { - u8 reserved_at_0[0x68]; + u8 reserved_at_0[0x1d]; + u8 fec_200G_per_lane_in_pplm[0x1]; + u8 reserved_at_1e[0x2a]; + u8 fec_100G_per_lane_in_pplm[0x1]; + u8 reserved_at_49[0x1f]; u8 fec_50G_per_lane_in_pplm[0x1]; u8 reserved_at_69[0x4]; u8 rx_icrc_encapsulated_counter[0x1]; @@ -10267,9 +10685,9 @@ struct mlx5_ifc_mcam_access_reg_bits { u8 mfrl[0x1]; u8 regs_39_to_32[0x8]; - u8 regs_31_to_10[0x16]; + u8 regs_31_to_11[0x15]; u8 mtmp[0x1]; - u8 regs_8_to_0[0x9]; + u8 regs_9_to_0[0xa]; }; struct mlx5_ifc_mcam_access_reg_bits1 { @@ -10296,6 +10714,19 @@ struct mlx5_ifc_mcam_access_reg_bits2 { u8 regs_31_to_0[0x20]; }; +struct mlx5_ifc_mcam_access_reg_bits3 { + u8 regs_127_to_96[0x20]; + + u8 regs_95_to_64[0x20]; + + u8 regs_63_to_32[0x20]; + + u8 regs_31_to_3[0x1d]; + u8 mrtcq[0x1]; + u8 mtctr[0x1]; + u8 mtptm[0x1]; +}; + struct mlx5_ifc_mcam_reg_bits { u8 reserved_at_0[0x8]; u8 feature_group[0x8]; @@ -10308,6 +10739,7 @@ struct mlx5_ifc_mcam_reg_bits { struct mlx5_ifc_mcam_access_reg_bits access_regs; struct mlx5_ifc_mcam_access_reg_bits1 access_regs1; struct mlx5_ifc_mcam_access_reg_bits2 access_regs2; + struct mlx5_ifc_mcam_access_reg_bits3 access_regs3; u8 reserved_at_0[0x80]; } mng_access_reg_cap_mask; @@ -10930,6 +11362,11 @@ struct mlx5_ifc_mcda_reg_bits { }; enum { + MLX5_MFRL_REG_PCI_RESET_METHOD_LINK_TOGGLE = 0, + MLX5_MFRL_REG_PCI_RESET_METHOD_HOT_RESET = 1, +}; + +enum { MLX5_MFRL_REG_RESET_STATE_IDLE = 0, MLX5_MFRL_REG_RESET_STATE_IN_NEGOTIATION = 1, MLX5_MFRL_REG_RESET_STATE_RESET_IN_PROGRESS = 2, @@ -10956,7 +11393,8 @@ struct mlx5_ifc_mfrl_reg_bits { u8 pci_sync_for_fw_update_start[0x1]; u8 pci_sync_for_fw_update_resp[0x2]; u8 rst_type_sel[0x3]; - u8 reserved_at_28[0x4]; + u8 pci_reset_req_method[0x3]; + u8 reserved_at_2b[0x1]; u8 reset_state[0x4]; u8 reset_type[0x8]; u8 reset_level[0x8]; @@ -11061,6 +11499,34 @@ struct mlx5_ifc_mtmp_reg_bits { u8 sensor_name_lo[0x20]; }; +struct mlx5_ifc_mtptm_reg_bits { + u8 reserved_at_0[0x10]; + u8 psta[0x1]; + u8 reserved_at_11[0xf]; + + u8 reserved_at_20[0x60]; +}; + +enum { + MLX5_MTCTR_REQUEST_NOP = 0x0, + MLX5_MTCTR_REQUEST_PTM_ROOT_CLOCK = 0x1, + MLX5_MTCTR_REQUEST_FREE_RUNNING_COUNTER = 0x2, + MLX5_MTCTR_REQUEST_REAL_TIME_CLOCK = 0x3, +}; + +struct mlx5_ifc_mtctr_reg_bits { + u8 first_clock_timestamp_request[0x8]; + u8 second_clock_timestamp_request[0x8]; + u8 reserved_at_10[0x10]; + + u8 first_clock_valid[0x1]; + u8 second_clock_valid[0x1]; + u8 reserved_at_22[0x1e]; + + u8 first_clock_timestamp[0x40]; + u8 second_clock_timestamp[0x40]; +}; + union mlx5_ifc_ports_control_registers_document_bits { struct mlx5_ifc_bufferx_reg_bits bufferx_reg; struct mlx5_ifc_eth_2819_cntrs_grp_data_layout_bits eth_2819_cntrs_grp_data_layout; @@ -11125,6 +11591,8 @@ union mlx5_ifc_ports_control_registers_document_bits { struct mlx5_ifc_mrtc_reg_bits mrtc_reg; struct mlx5_ifc_mtcap_reg_bits mtcap_reg; struct mlx5_ifc_mtmp_reg_bits mtmp_reg; + struct mlx5_ifc_mtptm_reg_bits mtptm_reg; + struct mlx5_ifc_mtctr_reg_bits mtctr_reg; u8 reserved_at_0[0x60e0]; }; @@ -12745,4 +13213,12 @@ struct mlx5_ifc_msees_reg_bits { u8 reserved_at_80[0x180]; }; +struct mlx5_ifc_mrtcq_reg_bits { + u8 reserved_at_0[0x40]; + + u8 rt_clock_identity[0x40]; + + u8 reserved_at_80[0x180]; +}; + #endif /* MLX5_IFC_H */ diff --git a/include/linux/mlx5/mlx5_ifc_vdpa.h b/include/linux/mlx5/mlx5_ifc_vdpa.h index 40371c916cf9..58dfa2ee7c83 100644 --- a/include/linux/mlx5/mlx5_ifc_vdpa.h +++ b/include/linux/mlx5/mlx5_ifc_vdpa.h @@ -148,7 +148,9 @@ enum { MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_ADDRS = (u64)1 << 6, MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_AVAIL_IDX = (u64)1 << 7, MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_USED_IDX = (u64)1 << 8, + MLX5_VIRTQ_MODIFY_MASK_QUEUE_VIRTIO_VERSION = (u64)1 << 10, MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_MKEY = (u64)1 << 11, + MLX5_VIRTQ_MODIFY_MASK_QUEUE_FEATURES = (u64)1 << 12, MLX5_VIRTQ_MODIFY_MASK_DESC_GROUP_MKEY = (u64)1 << 14, }; diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index 26092c78a985..e68d42b8ce65 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -155,10 +155,11 @@ struct mlx5_port_eth_proto { int mlx5_set_port_caps(struct mlx5_core_dev *dev, u8 port_num, u32 caps); int mlx5_query_port_ptys(struct mlx5_core_dev *dev, u32 *ptys, - int ptys_size, int proto_mask, u8 local_port); + int ptys_size, int proto_mask, + u8 local_port, u8 plane_index); int mlx5_query_ib_port_oper(struct mlx5_core_dev *dev, u16 *link_width_oper, - u16 *proto_oper, u8 local_port); + u16 *proto_oper, u8 local_port, u8 plane_index); void mlx5_toggle_port_link(struct mlx5_core_dev *dev); int mlx5_set_port_admin_status(struct mlx5_core_dev *dev, enum mlx5_port_status status); diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index f0e55bf3ec8b..fc7eeff99a8a 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -149,6 +149,7 @@ enum { MLX5_WQE_CTRL_CQ_UPDATE = 2 << 2, MLX5_WQE_CTRL_CQ_UPDATE_AND_EQE = 3 << 2, MLX5_WQE_CTRL_SOLICITED = 1 << 1, + MLX5_WQE_CTRL_INITIATOR_SMALL_FENCE = 1 << 5, }; enum { @@ -576,9 +577,12 @@ static inline const char *mlx5_qp_state_str(int state) static inline int mlx5_get_qp_default_ts(struct mlx5_core_dev *dev) { - return !MLX5_CAP_ROCE(dev, qp_ts_format) ? - MLX5_TIMESTAMP_FORMAT_FREE_RUNNING : - MLX5_TIMESTAMP_FORMAT_DEFAULT; + u8 supported_ts_cap = mlx5_get_roce_state(dev) ? + MLX5_CAP_ROCE(dev, qp_ts_format) : + MLX5_CAP_GEN(dev, sq_ts_format); + + return supported_ts_cap ? MLX5_TIMESTAMP_FORMAT_DEFAULT : + MLX5_TIMESTAMP_FORMAT_FREE_RUNNING; } #endif /* MLX5_QP_H */ diff --git a/include/linux/mm.h b/include/linux/mm.h index b6bdaa18b9e9..7b1068ddcbb7 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -5,6 +5,7 @@ #include <linux/errno.h> #include <linux/mmdebug.h> #include <linux/gfp.h> +#include <linux/pgalloc_tag.h> #include <linux/bug.h> #include <linux/list.h> #include <linux/mmzone.h> @@ -30,6 +31,7 @@ #include <linux/kasan.h> #include <linux/memremap.h> #include <linux/slab.h> +#include <linux/cacheinfo.h> struct mempolicy; struct anon_vma; @@ -96,6 +98,14 @@ extern const int mmap_rnd_compat_bits_max; extern int mmap_rnd_compat_bits __read_mostly; #endif +#ifndef DIRECT_MAP_PHYSMEM_END +# ifdef MAX_PHYSMEM_BITS +# define DIRECT_MAP_PHYSMEM_END ((1ULL << MAX_PHYSMEM_BITS) - 1) +# else +# define DIRECT_MAP_PHYSMEM_END (((phys_addr_t)-1)&~(1ULL<<63)) +# endif +#endif + #include <asm/page.h> #include <asm/processor.h> @@ -203,11 +213,11 @@ extern int sysctl_overcommit_memory; extern int sysctl_overcommit_ratio; extern unsigned long sysctl_overcommit_kbytes; -int overcommit_ratio_handler(struct ctl_table *, int, void *, size_t *, +int overcommit_ratio_handler(const struct ctl_table *, int, void *, size_t *, loff_t *); -int overcommit_kbytes_handler(struct ctl_table *, int, void *, size_t *, +int overcommit_kbytes_handler(const struct ctl_table *, int, void *, size_t *, loff_t *); -int overcommit_policy_handler(struct ctl_table *, int, void *, size_t *, +int overcommit_policy_handler(const struct ctl_table *, int, void *, size_t *, loff_t *); #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) @@ -320,21 +330,27 @@ extern unsigned int kobjsize(const void *objp); #define VM_HIGH_ARCH_BIT_3 35 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_BIT_4 36 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_BIT_5 37 /* bit only usable on 64-bit architectures */ +#define VM_HIGH_ARCH_BIT_6 38 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_0 BIT(VM_HIGH_ARCH_BIT_0) #define VM_HIGH_ARCH_1 BIT(VM_HIGH_ARCH_BIT_1) #define VM_HIGH_ARCH_2 BIT(VM_HIGH_ARCH_BIT_2) #define VM_HIGH_ARCH_3 BIT(VM_HIGH_ARCH_BIT_3) #define VM_HIGH_ARCH_4 BIT(VM_HIGH_ARCH_BIT_4) #define VM_HIGH_ARCH_5 BIT(VM_HIGH_ARCH_BIT_5) +#define VM_HIGH_ARCH_6 BIT(VM_HIGH_ARCH_BIT_6) #endif /* CONFIG_ARCH_USES_HIGH_VMA_FLAGS */ #ifdef CONFIG_ARCH_HAS_PKEYS -# define VM_PKEY_SHIFT VM_HIGH_ARCH_BIT_0 -# define VM_PKEY_BIT0 VM_HIGH_ARCH_0 /* A protection key is a 4-bit value */ -# define VM_PKEY_BIT1 VM_HIGH_ARCH_1 /* on x86 and 5-bit value on ppc64 */ -# define VM_PKEY_BIT2 VM_HIGH_ARCH_2 -# define VM_PKEY_BIT3 VM_HIGH_ARCH_3 -#ifdef CONFIG_PPC +# define VM_PKEY_SHIFT VM_HIGH_ARCH_BIT_0 +# define VM_PKEY_BIT0 VM_HIGH_ARCH_0 +# define VM_PKEY_BIT1 VM_HIGH_ARCH_1 +# define VM_PKEY_BIT2 VM_HIGH_ARCH_2 +#if CONFIG_ARCH_PKEY_BITS > 3 +# define VM_PKEY_BIT3 VM_HIGH_ARCH_3 +#else +# define VM_PKEY_BIT3 0 +#endif +#if CONFIG_ARCH_PKEY_BITS > 4 # define VM_PKEY_BIT4 VM_HIGH_ARCH_4 #else # define VM_PKEY_BIT4 0 @@ -352,13 +368,23 @@ extern unsigned int kobjsize(const void *objp); * for more details on the guard size. */ # define VM_SHADOW_STACK VM_HIGH_ARCH_5 -#else +#endif + +#if defined(CONFIG_ARM64_GCS) +/* + * arm64's Guarded Control Stack implements similar functionality and + * has similar constraints to shadow stacks. + */ +# define VM_SHADOW_STACK VM_HIGH_ARCH_6 +#endif + +#ifndef VM_SHADOW_STACK # define VM_SHADOW_STACK VM_NONE #endif #if defined(CONFIG_X86) # define VM_PAT VM_ARCH_1 /* PAT reserves whole VMA at once (x86) */ -#elif defined(CONFIG_PPC) +#elif defined(CONFIG_PPC64) # define VM_SAO VM_ARCH_1 /* Strong Access Ordering (powerpc) */ #elif defined(CONFIG_PARISC) # define VM_GROWSUP VM_ARCH_1 @@ -373,8 +399,8 @@ extern unsigned int kobjsize(const void *objp); #endif #if defined(CONFIG_ARM64_MTE) -# define VM_MTE VM_HIGH_ARCH_0 /* Use Tagged memory for access control */ -# define VM_MTE_ALLOWED VM_HIGH_ARCH_1 /* Tagged memory permitted */ +# define VM_MTE VM_HIGH_ARCH_4 /* Use Tagged memory for access control */ +# define VM_MTE_ALLOWED VM_HIGH_ARCH_5 /* Tagged memory permitted */ #else # define VM_MTE VM_NONE # define VM_MTE_ALLOWED VM_NONE @@ -405,6 +431,20 @@ extern unsigned int kobjsize(const void *objp); #define VM_ALLOW_ANY_UNCACHED VM_NONE #endif +#ifdef CONFIG_64BIT +#define VM_DROPPABLE_BIT 40 +#define VM_DROPPABLE BIT(VM_DROPPABLE_BIT) +#elif defined(CONFIG_PPC32) +#define VM_DROPPABLE VM_ARCH_1 +#else +#define VM_DROPPABLE VM_NONE +#endif + +#ifdef CONFIG_64BIT +/* VM is sealed, in vm_flags */ +#define VM_SEALED _BITUL(63) +#endif + /* Bits set in the VMA until the stack is in its final location */ #define VM_STACK_INCOMPLETE_SETUP (VM_RAND_READ | VM_SEQ_READ | VM_STACK_EARLY) @@ -671,7 +711,7 @@ static inline bool vma_start_read(struct vm_area_struct *vma) * we don't rely on for anything - the mm_lock_seq read against which we * need ordering is below. */ - if (READ_ONCE(vma->vm_lock_seq) == READ_ONCE(vma->vm_mm->mm_lock_seq)) + if (READ_ONCE(vma->vm_lock_seq) == READ_ONCE(vma->vm_mm->mm_lock_seq.sequence)) return false; if (unlikely(down_read_trylock(&vma->vm_lock->lock) == 0)) @@ -688,7 +728,7 @@ static inline bool vma_start_read(struct vm_area_struct *vma) * after it has been unlocked. * This pairs with RELEASE semantics in vma_end_write_all(). */ - if (unlikely(vma->vm_lock_seq == smp_load_acquire(&vma->vm_mm->mm_lock_seq))) { + if (unlikely(vma->vm_lock_seq == raw_read_seqcount(&vma->vm_mm->mm_lock_seq))) { up_read(&vma->vm_lock->lock); return false; } @@ -703,7 +743,7 @@ static inline void vma_end_read(struct vm_area_struct *vma) } /* WARNING! Can only be used if mmap_lock is expected to be write-locked */ -static bool __is_vma_write_locked(struct vm_area_struct *vma, int *mm_lock_seq) +static bool __is_vma_write_locked(struct vm_area_struct *vma, unsigned int *mm_lock_seq) { mmap_assert_write_locked(vma->vm_mm); @@ -711,7 +751,7 @@ static bool __is_vma_write_locked(struct vm_area_struct *vma, int *mm_lock_seq) * current task is holding mmap_write_lock, both vma->vm_lock_seq and * mm->mm_lock_seq can't be concurrently modified. */ - *mm_lock_seq = vma->vm_mm->mm_lock_seq; + *mm_lock_seq = vma->vm_mm->mm_lock_seq.sequence; return (vma->vm_lock_seq == *mm_lock_seq); } @@ -722,7 +762,7 @@ static bool __is_vma_write_locked(struct vm_area_struct *vma, int *mm_lock_seq) */ static inline void vma_start_write(struct vm_area_struct *vma) { - int mm_lock_seq; + unsigned int mm_lock_seq; if (__is_vma_write_locked(vma, &mm_lock_seq)) return; @@ -740,7 +780,7 @@ static inline void vma_start_write(struct vm_area_struct *vma) static inline void vma_assert_write_locked(struct vm_area_struct *vma) { - int mm_lock_seq; + unsigned int mm_lock_seq; VM_BUG_ON_VMA(!__is_vma_write_locked(vma, &mm_lock_seq), vma); } @@ -992,27 +1032,6 @@ static inline struct vm_area_struct *vma_prev(struct vma_iterator *vmi) return mas_prev(&vmi->mas, 0); } -static inline -struct vm_area_struct *vma_iter_prev_range(struct vma_iterator *vmi) -{ - return mas_prev_range(&vmi->mas, 0); -} - -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); -} - static inline int vma_iter_clear_gfp(struct vma_iterator *vmi, unsigned long start, unsigned long end, gfp_t gfp) { @@ -1104,7 +1123,7 @@ static inline unsigned int compound_order(struct page *page) * * Return: The order of the folio. */ -static inline unsigned int folio_order(struct folio *folio) +static inline unsigned int folio_order(const struct folio *folio) { if (!folio_test_large(folio)) return 0; @@ -1196,77 +1215,51 @@ static inline int is_vmalloc_or_module_addr(const void *x) /* * How many times the entire folio is mapped as a single unit (eg by a * PMD or PUD entry). This is probably not what you want, except for - * debugging purposes - it does not include PTE-mapped sub-pages; look - * at folio_mapcount() or page_mapcount() instead. + * debugging purposes or implementation of other core folio_*() primitives. */ -static inline int folio_entire_mapcount(struct folio *folio) +static inline int folio_entire_mapcount(const struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_large(folio), folio); return atomic_read(&folio->_entire_mapcount) + 1; } -/* - * The atomic page->_mapcount, starts from -1: so that transitions - * both from it and to it can be tracked, using atomic_inc_and_test - * and atomic_add_negative(-1). - */ -static inline void page_mapcount_reset(struct page *page) +static inline int folio_large_mapcount(const struct folio *folio) { - atomic_set(&(page)->_mapcount, -1); + VM_WARN_ON_FOLIO(!folio_test_large(folio), folio); + return atomic_read(&folio->_large_mapcount) + 1; } /** - * page_mapcount() - Number of times this precise page is mapped. - * @page: The page. + * folio_mapcount() - Number of mappings of this folio. + * @folio: The folio. * - * 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. + * The folio mapcount corresponds to the number of present user page table + * entries that reference any part of a folio. Each such present user page + * table entry must be paired with exactly on folio reference. * - * Will report 0 for pages which cannot be mapped into userspace, eg - * slab, page tables and similar. - */ -static inline int page_mapcount(struct page *page) -{ - int mapcount = atomic_read(&page->_mapcount) + 1; - - /* Handle page_has_type() pages */ - if (mapcount < 0) - mapcount = 0; - if (unlikely(PageCompound(page))) - mapcount += folio_entire_mapcount(page_folio(page)); - - return mapcount; -} - -int folio_total_mapcount(struct folio *folio); - -/** - * folio_mapcount() - Calculate the number of mappings of this folio. - * @folio: The folio. + * For ordindary folios, each user page table entry (PTE/PMD/PUD/...) counts + * exactly once. * - * A large folio tracks both how many times the entire folio is mapped, - * and how many times each individual page in the folio is mapped. - * This function calculates the total number of times the folio is - * mapped. + * For hugetlb folios, each abstracted "hugetlb" user page table entry that + * references the entire folio counts exactly once, even when such special + * page table entries are comprised of multiple ordinary page table entries. + * + * Will report 0 for pages which cannot be mapped into userspace, such as + * slab, page tables and similar. * * Return: The number of times this folio is mapped. */ -static inline int folio_mapcount(struct folio *folio) +static inline int folio_mapcount(const struct folio *folio) { - if (likely(!folio_test_large(folio))) - return atomic_read(&folio->_mapcount) + 1; - return folio_total_mapcount(folio); -} + int mapcount; -static inline bool folio_large_is_mapped(struct folio *folio) -{ - /* - * 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->_entire_mapcount) >= 0; + if (likely(!folio_test_large(folio))) { + mapcount = atomic_read(&folio->_mapcount) + 1; + if (page_mapcount_is_type(mapcount)) + mapcount = 0; + return mapcount; + } + return folio_large_mapcount(folio); } /** @@ -1275,11 +1268,9 @@ static inline bool folio_large_is_mapped(struct folio *folio) * * Return: True if any page in this folio is referenced by user page tables. */ -static inline bool folio_mapped(struct folio *folio) +static inline bool folio_mapped(const struct folio *folio) { - if (likely(!folio_test_large(folio))) - return atomic_read(&folio->_mapcount) >= 0; - return folio_large_is_mapped(folio); + return folio_mapcount(folio) >= 1; } /* @@ -1287,11 +1278,9 @@ static inline bool folio_mapped(struct folio *folio) * For compound page it returns true if any sub-page of compound page is mapped, * even if this particular sub-page is not itself mapped by any PTE or PMD. */ -static inline bool page_mapped(struct page *page) +static inline bool page_mapped(const struct page *page) { - if (likely(!PageCompound(page))) - return atomic_read(&page->_mapcount) >= 0; - return folio_large_is_mapped(page_folio(page)); + return folio_mapped(page_folio(page)); } static inline struct page *virt_to_head_page(const void *x) @@ -1310,15 +1299,12 @@ static inline struct folio *virt_to_folio(const void *x) void __folio_put(struct folio *folio); -void put_pages_list(struct list_head *pages); - void split_page(struct page *page, unsigned int order); void folio_copy(struct folio *dst, struct folio *src); +int folio_mc_copy(struct folio *dst, struct folio *src); unsigned long nr_free_buffer_pages(void); -void destroy_large_folio(struct folio *folio); - /* Returns the number of bytes in this potentially compound page. */ static inline unsigned long page_size(struct page *page) { @@ -1436,27 +1422,22 @@ vm_fault_t finish_fault(struct vm_fault *vmf); #if defined(CONFIG_ZONE_DEVICE) && defined(CONFIG_FS_DAX) DECLARE_STATIC_KEY_FALSE(devmap_managed_key); -bool __put_devmap_managed_page_refs(struct page *page, int refs); -static inline bool put_devmap_managed_page_refs(struct page *page, int refs) +bool __put_devmap_managed_folio_refs(struct folio *folio, int refs); +static inline bool put_devmap_managed_folio_refs(struct folio *folio, int refs) { if (!static_branch_unlikely(&devmap_managed_key)) return false; - if (!is_zone_device_page(page)) + if (!folio_is_zone_device(folio)) return false; - return __put_devmap_managed_page_refs(page, refs); + return __put_devmap_managed_folio_refs(folio, refs); } #else /* CONFIG_ZONE_DEVICE && CONFIG_FS_DAX */ -static inline bool put_devmap_managed_page_refs(struct page *page, int refs) +static inline bool put_devmap_managed_folio_refs(struct folio *folio, int refs) { return false; } #endif /* CONFIG_ZONE_DEVICE && CONFIG_FS_DAX */ -static inline bool put_devmap_managed_page(struct page *page) -{ - return put_devmap_managed_page_refs(page, 1); -} - /* 127: arbitrary random number, small enough to assemble well */ #define folio_ref_zero_or_close_to_overflow(folio) \ ((unsigned int) folio_ref_count(folio) + 127u <= 127u) @@ -1575,7 +1556,7 @@ static inline void put_page(struct page *page) * For some devmap managed pages we need to catch refcount transition * from 2 to 1: */ - if (put_devmap_managed_page(&folio->page)) + if (put_devmap_managed_folio_refs(folio, 1)) return; folio_put(folio); } @@ -1607,17 +1588,20 @@ static inline void put_page(struct page *page) * issue. * * Locking: the lockless algorithm described in folio_try_get_rcu() - * provides safe operation for get_user_pages(), page_mkclean() and + * provides safe operation for get_user_pages(), folio_mkclean() and * other calls that race to set up page table entries. */ #define GUP_PIN_COUNTING_BIAS (1U << 10) void unpin_user_page(struct page *page); +void unpin_folio(struct folio *folio); void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages, bool make_dirty); void unpin_user_page_range_dirty_lock(struct page *page, unsigned long npages, bool make_dirty); void unpin_user_pages(struct page **pages, unsigned long npages); +void unpin_user_folio(struct folio *folio, unsigned long npages); +void unpin_folios(struct folio **folios, unsigned long nfolios); static inline bool is_cow_mapping(vm_flags_t flags) { @@ -1765,6 +1749,8 @@ static inline void vma_set_access_pid_bit(struct vm_area_struct *vma) __set_bit(pid_bit, &vma->numab_state->pids_active[1]); } } + +bool folio_use_access_time(struct folio *folio); #else /* !CONFIG_NUMA_BALANCING */ static inline int folio_xchg_last_cpupid(struct folio *folio, int cpupid) { @@ -1818,6 +1804,10 @@ static inline bool cpupid_match_pid(struct task_struct *task, int cpupid) static inline void vma_set_access_pid_bit(struct vm_area_struct *vma) { } +static inline bool folio_use_access_time(struct folio *folio) +{ + return false; +} #endif /* CONFIG_NUMA_BALANCING */ #if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS) @@ -1916,7 +1906,7 @@ static inline unsigned long page_to_section(const struct page *page) * * Return: The Page Frame Number of the first page in the folio. */ -static inline unsigned long folio_pfn(struct folio *folio) +static inline unsigned long folio_pfn(const struct folio *folio) { return page_to_pfn(&folio->page); } @@ -1948,8 +1938,8 @@ static inline struct folio *pfn_folio(unsigned long pfn) * * For more information, please see Documentation/core-api/pin_user_pages.rst. * - * Return: True, if it is likely that the page has been "dma-pinned". - * False, if the page is definitely not dma-pinned. + * Return: True, if it is likely that the folio has been "dma-pinned". + * False, if the folio is definitely not dma-pinned. */ static inline bool folio_maybe_dma_pinned(struct folio *folio) { @@ -1968,11 +1958,6 @@ static inline bool folio_maybe_dma_pinned(struct folio *folio) GUP_PIN_COUNTING_BIAS; } -static inline bool page_maybe_dma_pinned(struct page *page) -{ - return folio_maybe_dma_pinned(page_folio(page)); -} - /* * This should most likely only be called during fork() to see whether we * should break the cow immediately for an anon page on the src mm. @@ -2069,7 +2054,7 @@ static inline void set_page_links(struct page *page, enum zone_type zone, * * Return: A positive power of two. */ -static inline long folio_nr_pages(struct folio *folio) +static inline long folio_nr_pages(const struct folio *folio) { if (!folio_test_large(folio)) return 1; @@ -2145,7 +2130,7 @@ static inline struct folio *folio_next(struct folio *folio) * it from being split. It is not necessary for the folio to be locked. * Return: The base-2 logarithm of the size of this folio. */ -static inline unsigned int folio_shift(struct folio *folio) +static inline unsigned int folio_shift(const struct folio *folio) { return PAGE_SHIFT + folio_order(folio); } @@ -2158,49 +2143,78 @@ static inline unsigned int folio_shift(struct folio *folio) * it from being split. It is not necessary for the folio to be locked. * Return: The number of bytes in this folio. */ -static inline size_t folio_size(struct folio *folio) +static inline size_t folio_size(const struct folio *folio) { return PAGE_SIZE << folio_order(folio); } /** - * folio_estimated_sharers - Estimate the number of sharers of a folio. + * folio_likely_mapped_shared - Estimate if the folio is mapped into the page + * tables of more than one MM * @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(). + * This function checks if the folio is currently mapped into more than one + * MM ("mapped shared"), or if the folio is only mapped into a single MM + * ("mapped exclusively"). + * + * For KSM folios, this function also returns "mapped shared" when a folio is + * mapped multiple times into the same MM, because the individual page mappings + * are independent. + * + * As precise information is not easily available for all folios, this function + * estimates the number of MMs ("sharers") that are currently mapping a folio + * using the number of times the first page of the folio is currently mapped + * into page tables. * - * Return: The estimated number of processes sharing a folio. + * For small anonymous folios and anonymous hugetlb folios, the return + * value will be exactly correct: non-KSM folios can only be mapped at most once + * into an MM, and they cannot be partially mapped. KSM folios are + * considered shared even if mapped multiple times into the same MM. + * + * For other folios, the result can be fuzzy: + * #. For partially-mappable large folios (THP), the return value can wrongly + * indicate "mapped exclusively" (false negative) when the folio is + * only partially mapped into at least one MM. + * #. For pagecache folios (including hugetlb), the return value can wrongly + * indicate "mapped shared" (false positive) when two VMAs in the same MM + * cover the same file range. + * + * Further, this function only considers current page table mappings that + * are tracked using the folio mapcount(s). + * + * This function does not consider: + * #. If the folio might get mapped in the (near) future (e.g., swapcache, + * pagecache, temporary unmapping for migration). + * #. If the folio is mapped differently (VM_PFNMAP). + * #. If hugetlb page table sharing applies. Callers might want to check + * hugetlb_pmd_shared(). + * + * Return: Whether the folio is estimated to be mapped into more than one MM. */ -static inline int folio_estimated_sharers(struct folio *folio) +static inline bool folio_likely_mapped_shared(struct folio *folio) { - return page_mapcount(folio_page(folio, 0)); -} + int mapcount = folio_mapcount(folio); -#ifndef HAVE_ARCH_MAKE_PAGE_ACCESSIBLE -static inline int arch_make_page_accessible(struct page *page) -{ - return 0; + /* Only partially-mappable folios require more care. */ + if (!folio_test_large(folio) || unlikely(folio_test_hugetlb(folio))) + return mapcount > 1; + + /* A single mapping implies "mapped exclusively". */ + if (mapcount <= 1) + return false; + + /* If any page is mapped more than once we treat it "mapped shared". */ + if (folio_entire_mapcount(folio) || mapcount > folio_nr_pages(folio)) + return true; + + /* Let's guess based on the first subpage. */ + return atomic_read(&folio->_mapcount) > 0; } -#endif #ifndef HAVE_ARCH_MAKE_FOLIO_ACCESSIBLE static inline int arch_make_folio_accessible(struct folio *folio) { - int ret; - long i, nr = folio_nr_pages(folio); - - for (i = 0; i < nr; i++) { - ret = arch_make_page_accessible(folio_page(folio, i)); - if (ret) - break; - } - - return ret; + return 0; } #endif @@ -2247,19 +2261,6 @@ static inline void *folio_address(const struct folio *folio) return page_address(&folio->page); } -extern pgoff_t __page_file_index(struct page *page); - -/* - * Return the pagecache index of the passed page. Regular pagecache pages - * use ->index whereas swapcache pages use swp_offset(->private) - */ -static inline pgoff_t page_index(struct page *page) -{ - if (unlikely(PageSwapCache(page))) - return __page_file_index(page); - return page->index; -} - /* * Return true only if the page has been allocated with * ALLOC_NO_WATERMARKS and the low watermark was not @@ -2319,6 +2320,7 @@ extern void pagefault_out_of_memory(void); struct zap_details { struct folio *single_folio; /* Locked folio to be unmapped */ bool even_cows; /* Zap COWed private pages too? */ + bool reclaim_pt; /* Need reclaim page tables? */ zap_flags_t zap_flags; /* Extra flags for zapping */ }; @@ -2393,15 +2395,40 @@ void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling); int copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma); -int follow_pte(struct mm_struct *mm, unsigned long address, - pte_t **ptepp, spinlock_t **ptlp); -int follow_pfn(struct vm_area_struct *vma, unsigned long address, - unsigned long *pfn); -int follow_phys(struct vm_area_struct *vma, unsigned long address, - unsigned int flags, unsigned long *prot, resource_size_t *phys); int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, void *buf, int len, int write); +struct follow_pfnmap_args { + /** + * Inputs: + * @vma: Pointer to @vm_area_struct struct + * @address: the virtual address to walk + */ + struct vm_area_struct *vma; + unsigned long address; + /** + * Internals: + * + * The caller shouldn't touch any of these. + */ + spinlock_t *lock; + pte_t *ptep; + /** + * Outputs: + * + * @pfn: the PFN of the address + * @pgprot: the pgprot_t of the mapping + * @writable: whether the mapping is writable + * @special: whether the mapping is a special mapping (real PFN maps) + */ + unsigned long pfn; + pgprot_t pgprot; + bool writable; + bool special; +}; +int follow_pfnmap_start(struct follow_pfnmap_args *args); +void follow_pfnmap_end(struct follow_pfnmap_args *args); + extern void truncate_pagecache(struct inode *inode, loff_t new); extern void truncate_setsize(struct inode *inode, loff_t newsize); void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to); @@ -2506,6 +2533,10 @@ long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags); long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags); +long memfd_pin_folios(struct file *memfd, loff_t start, loff_t end, + struct folio **folios, unsigned int max_folios, + pgoff_t *offset); +int folio_add_pins(struct folio *folio, unsigned int pins); int get_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); @@ -2521,16 +2552,12 @@ struct kvec; struct page *get_dump_page(unsigned long addr); bool folio_mark_dirty(struct folio *folio); +bool folio_mark_dirty_lock(struct folio *folio); bool set_page_dirty(struct page *page); int set_page_dirty_lock(struct page *page); int get_cmdline(struct task_struct *task, char *buffer, int buflen); -extern unsigned long move_page_tables(struct vm_area_struct *vma, - unsigned long old_addr, struct vm_area_struct *new_vma, - unsigned long new_addr, unsigned long len, - bool need_rmap_locks, bool for_stack); - /* * Flags used by change_protection(). For now we make it a bitmap so * that we can pass in multiple flags just like parameters. However @@ -2551,21 +2578,6 @@ extern unsigned long move_page_tables(struct vm_area_struct *vma, #define MM_CP_UFFD_WP_ALL (MM_CP_UFFD_WP | \ MM_CP_UFFD_WP_RESOLVE) -bool vma_needs_dirty_tracking(struct vm_area_struct *vma); -int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot); -static inline bool vma_wants_manual_pte_write_upgrade(struct vm_area_struct *vma) -{ - /* - * We want to check manually if we can change individual PTEs writable - * if we can't do that automatically for all PTEs in a mapping. For - * private mappings, that's always the case when we have write - * permissions as we properly have to handle COW. - */ - if (vma->vm_flags & VM_SHARED) - return vma_wants_writenotify(vma, vma->vm_page_prot); - return !!(vma->vm_flags & VM_WRITE); - -} bool can_change_pte_writable(struct vm_area_struct *vma, unsigned long addr, pte_t pte); extern long change_protection(struct mmu_gather *tlb, @@ -2689,6 +2701,30 @@ static inline pte_t pte_mkspecial(pte_t pte) } #endif +#ifndef CONFIG_ARCH_SUPPORTS_PMD_PFNMAP +static inline bool pmd_special(pmd_t pmd) +{ + return false; +} + +static inline pmd_t pmd_mkspecial(pmd_t pmd) +{ + return pmd; +} +#endif /* CONFIG_ARCH_SUPPORTS_PMD_PFNMAP */ + +#ifndef CONFIG_ARCH_SUPPORTS_PUD_PFNMAP +static inline bool pud_special(pud_t pud) +{ + return false; +} + +static inline pud_t pud_mkspecial(pud_t pud) +{ + return pud; +} +#endif /* CONFIG_ARCH_SUPPORTS_PUD_PFNMAP */ + #ifndef CONFIG_ARCH_HAS_PTE_DEVMAP static inline int pte_devmap(pte_t pte) { @@ -2859,12 +2895,13 @@ static inline bool pagetable_is_reserved(struct ptdesc *pt) * * Return: The ptdesc describing the allocated page tables. */ -static inline struct ptdesc *pagetable_alloc(gfp_t gfp, unsigned int order) +static inline struct ptdesc *pagetable_alloc_noprof(gfp_t gfp, unsigned int order) { - struct page *page = alloc_pages(gfp | __GFP_COMP, order); + struct page *page = alloc_pages_noprof(gfp | __GFP_COMP, order); return page_ptdesc(page); } +#define pagetable_alloc(...) alloc_hooks(pagetable_alloc_noprof(__VA_ARGS__)) /** * pagetable_free - Free pagetables @@ -2880,7 +2917,7 @@ static inline void pagetable_free(struct ptdesc *pt) __free_pages(page, compound_order(page)); } -#if USE_SPLIT_PTE_PTLOCKS +#if defined(CONFIG_SPLIT_PTE_PTLOCKS) #if ALLOC_SPLIT_PTLOCKS void __init ptlock_cache_init(void); bool ptlock_alloc(struct ptdesc *ptdesc); @@ -2915,6 +2952,13 @@ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd) return ptlock_ptr(page_ptdesc(pmd_page(*pmd))); } +static inline spinlock_t *ptep_lockptr(struct mm_struct *mm, pte_t *pte) +{ + BUILD_BUG_ON(IS_ENABLED(CONFIG_HIGHPTE)); + BUILD_BUG_ON(MAX_PTRS_PER_PTE * sizeof(pte_t) > PAGE_SIZE); + return ptlock_ptr(virt_to_ptdesc(pte)); +} + static inline bool ptlock_init(struct ptdesc *ptdesc) { /* @@ -2931,7 +2975,7 @@ static inline bool ptlock_init(struct ptdesc *ptdesc) return true; } -#else /* !USE_SPLIT_PTE_PTLOCKS */ +#else /* !defined(CONFIG_SPLIT_PTE_PTLOCKS) */ /* * We use mm->page_table_lock to guard all pagetable pages of the mm. */ @@ -2939,23 +2983,24 @@ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd) { return &mm->page_table_lock; } +static inline spinlock_t *ptep_lockptr(struct mm_struct *mm, pte_t *pte) +{ + return &mm->page_table_lock; +} static inline void ptlock_cache_init(void) {} static inline bool ptlock_init(struct ptdesc *ptdesc) { return true; } static inline void ptlock_free(struct ptdesc *ptdesc) {} -#endif /* USE_SPLIT_PTE_PTLOCKS */ +#endif /* defined(CONFIG_SPLIT_PTE_PTLOCKS) */ -static inline bool pagetable_pte_ctor(struct ptdesc *ptdesc) +static inline void __pagetable_ctor(struct ptdesc *ptdesc) { struct folio *folio = ptdesc_folio(ptdesc); - if (!ptlock_init(ptdesc)) - return false; __folio_set_pgtable(folio); lruvec_stat_add_folio(folio, NR_PAGETABLE); - return true; } -static inline void pagetable_pte_dtor(struct ptdesc *ptdesc) +static inline void pagetable_dtor(struct ptdesc *ptdesc) { struct folio *folio = ptdesc_folio(ptdesc); @@ -2964,7 +3009,29 @@ static inline void pagetable_pte_dtor(struct ptdesc *ptdesc) lruvec_stat_sub_folio(folio, NR_PAGETABLE); } -pte_t *__pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp); +static inline void pagetable_dtor_free(struct ptdesc *ptdesc) +{ + pagetable_dtor(ptdesc); + pagetable_free(ptdesc); +} + +static inline bool pagetable_pte_ctor(struct ptdesc *ptdesc) +{ + if (!ptlock_init(ptdesc)) + return false; + __pagetable_ctor(ptdesc); + return true; +} + +pte_t *___pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp); +static inline pte_t *__pte_offset_map(pmd_t *pmd, unsigned long addr, + pmd_t *pmdvalp) +{ + pte_t *pte; + + __cond_lock(RCU, pte = ___pte_offset_map(pmd, addr, pmdvalp)); + return pte; +} static inline pte_t *pte_offset_map(pmd_t *pmd, unsigned long addr) { return __pte_offset_map(pmd, addr, NULL); @@ -2977,12 +3044,16 @@ static inline pte_t *pte_offset_map_lock(struct mm_struct *mm, pmd_t *pmd, { pte_t *pte; - __cond_lock(*ptlp, pte = __pte_offset_map_lock(mm, pmd, addr, ptlp)); + __cond_lock(RCU, __cond_lock(*ptlp, + pte = __pte_offset_map_lock(mm, pmd, addr, ptlp))); return pte; } -pte_t *pte_offset_map_nolock(struct mm_struct *mm, pmd_t *pmd, - unsigned long addr, spinlock_t **ptlp); +pte_t *pte_offset_map_ro_nolock(struct mm_struct *mm, pmd_t *pmd, + unsigned long addr, spinlock_t **ptlp); +pte_t *pte_offset_map_rw_nolock(struct mm_struct *mm, pmd_t *pmd, + unsigned long addr, pmd_t *pmdvalp, + spinlock_t **ptlp); #define pte_unmap_unlock(pte, ptl) do { \ spin_unlock(ptl); \ @@ -3002,7 +3073,7 @@ pte_t *pte_offset_map_nolock(struct mm_struct *mm, pmd_t *pmd, ((unlikely(pmd_none(*(pmd))) && __pte_alloc_kernel(pmd))? \ NULL: pte_offset_kernel(pmd, address)) -#if USE_SPLIT_PMD_PTLOCKS +#if defined(CONFIG_SPLIT_PMD_PTLOCKS) static inline struct page *pmd_pgtable_page(pmd_t *pmd) { @@ -3028,14 +3099,6 @@ static inline bool pmd_ptlock_init(struct ptdesc *ptdesc) return ptlock_init(ptdesc); } -static inline void pmd_ptlock_free(struct ptdesc *ptdesc) -{ -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - VM_BUG_ON_PAGE(ptdesc->pmd_huge_pte, ptdesc_page(ptdesc)); -#endif - ptlock_free(ptdesc); -} - #define pmd_huge_pte(mm, pmd) (pmd_ptdesc(pmd)->pmd_huge_pte) #else @@ -3046,7 +3109,6 @@ static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd) } static inline bool pmd_ptlock_init(struct ptdesc *ptdesc) { return true; } -static inline void pmd_ptlock_free(struct ptdesc *ptdesc) {} #define pmd_huge_pte(mm, pmd) ((mm)->pmd_huge_pte) @@ -3061,24 +3123,13 @@ static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd) static inline bool pagetable_pmd_ctor(struct ptdesc *ptdesc) { - struct folio *folio = ptdesc_folio(ptdesc); - if (!pmd_ptlock_init(ptdesc)) return false; - __folio_set_pgtable(folio); - lruvec_stat_add_folio(folio, NR_PAGETABLE); + ptdesc_pmd_pts_init(ptdesc); + __pagetable_ctor(ptdesc); return true; } -static inline void pagetable_pmd_dtor(struct ptdesc *ptdesc) -{ - struct folio *folio = ptdesc_folio(ptdesc); - - pmd_ptlock_free(ptdesc); - __folio_clear_pgtable(folio); - lruvec_stat_sub_folio(folio, NR_PAGETABLE); -} - /* * No scalability reason to split PUD locks yet, but follow the same pattern * as the PMD locks to make it easier if we decide to. The VM should not be @@ -3100,18 +3151,17 @@ static inline spinlock_t *pud_lock(struct mm_struct *mm, pud_t *pud) static inline void pagetable_pud_ctor(struct ptdesc *ptdesc) { - struct folio *folio = ptdesc_folio(ptdesc); - - __folio_set_pgtable(folio); - lruvec_stat_add_folio(folio, NR_PAGETABLE); + __pagetable_ctor(ptdesc); } -static inline void pagetable_pud_dtor(struct ptdesc *ptdesc) +static inline void pagetable_p4d_ctor(struct ptdesc *ptdesc) { - struct folio *folio = ptdesc_folio(ptdesc); + __pagetable_ctor(ptdesc); +} - __folio_clear_pgtable(folio); - lruvec_stat_sub_folio(folio, NR_PAGETABLE); +static inline void pagetable_pgd_ctor(struct ptdesc *ptdesc) +{ + __pagetable_ctor(ptdesc); } extern void __init pagecache_init(void); @@ -3132,13 +3182,7 @@ extern void reserve_bootmem_region(phys_addr_t start, phys_addr_t end, int nid); /* Free the reserved page into the buddy system, so it gets managed. */ -static inline void free_reserved_page(struct page *page) -{ - ClearPageReserved(page); - init_page_count(page); - __free_page(page); - adjust_managed_page_count(page, 1); -} +void free_reserved_page(struct page *page); #define free_highmem_page(page) free_reserved_page(page) static inline void mark_page_reserved(struct page *page) @@ -3195,8 +3239,6 @@ static inline unsigned long get_num_physpages(void) */ void free_area_init(unsigned long *max_zone_pfn); unsigned long node_map_pfn_alignment(void); -unsigned long __absent_pages_in_range(int nid, unsigned long start_pfn, - unsigned long end_pfn); extern unsigned long absent_pages_in_range(unsigned long start_pfn, unsigned long end_pfn); extern void get_pfn_range_for_nid(unsigned int nid, @@ -3212,7 +3254,6 @@ static inline int early_pfn_to_nid(unsigned long pfn) extern int __meminit early_pfn_to_nid(unsigned long pfn); #endif -extern void set_dma_reserve(unsigned long new_dma_reserve); extern void mem_init(void); extern void __init mmap_init(void); @@ -3224,9 +3265,6 @@ static inline void show_mem(void) extern long si_mem_available(void); extern void si_meminfo(struct sysinfo * val); extern void si_meminfo_node(struct sysinfo *val, int nid); -#ifdef __HAVE_ARCH_RESERVED_KERNEL_PAGES -extern unsigned long arch_reserved_kernel_pages(void); -#endif extern __printf(3, 4) void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...); @@ -3273,78 +3311,11 @@ 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_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 anon_vma *find_mergeable_anon_vma(struct vm_area_struct *); 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 **, - unsigned long addr, unsigned long len, pgoff_t pgoff, - bool *need_rmap_locks); extern void exit_mmap(struct mm_struct *); -struct vm_area_struct *vma_modify(struct vma_iterator *vmi, - struct vm_area_struct *prev, - struct vm_area_struct *vma, - unsigned long start, unsigned long end, - unsigned long vm_flags, - struct mempolicy *policy, - struct vm_userfaultfd_ctx uffd_ctx, - struct anon_vma_name *anon_name); - -/* We are about to modify the VMA's flags. */ -static inline struct vm_area_struct -*vma_modify_flags(struct vma_iterator *vmi, - struct vm_area_struct *prev, - struct vm_area_struct *vma, - unsigned long start, unsigned long end, - unsigned long new_flags) -{ - return vma_modify(vmi, prev, vma, start, end, new_flags, - vma_policy(vma), vma->vm_userfaultfd_ctx, - anon_vma_name(vma)); -} - -/* We are about to modify the VMA's flags and/or anon_name. */ -static inline struct vm_area_struct -*vma_modify_flags_name(struct vma_iterator *vmi, - struct vm_area_struct *prev, - struct vm_area_struct *vma, - unsigned long start, - unsigned long end, - unsigned long new_flags, - struct anon_vma_name *new_name) -{ - return vma_modify(vmi, prev, vma, start, end, new_flags, - vma_policy(vma), vma->vm_userfaultfd_ctx, new_name); -} - -/* We are about to modify the VMA's memory policy. */ -static inline struct vm_area_struct -*vma_modify_policy(struct vma_iterator *vmi, - struct vm_area_struct *prev, - struct vm_area_struct *vma, - unsigned long start, unsigned long end, - struct mempolicy *new_pol) -{ - return vma_modify(vmi, prev, vma, start, end, vma->vm_flags, - new_pol, vma->vm_userfaultfd_ctx, anon_vma_name(vma)); -} - -/* We are about to modify the VMA's flags and/or uffd context. */ -static inline struct vm_area_struct -*vma_modify_flags_uffd(struct vma_iterator *vmi, - struct vm_area_struct *prev, - struct vm_area_struct *vma, - unsigned long start, unsigned long end, - unsigned long new_flags, - struct vm_userfaultfd_ctx new_ctx) -{ - return vma_modify(vmi, prev, vma, start, end, new_flags, - vma_policy(vma), new_ctx, anon_vma_name(vma)); -} +int relocate_vma_down(struct vm_area_struct *vma, unsigned long shift); +bool mmap_read_lock_maybe_expand(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long addr, bool write); static inline int check_data_rlimit(unsigned long rlim, unsigned long new, @@ -3377,19 +3348,21 @@ extern struct vm_area_struct *_install_special_mapping(struct mm_struct *mm, unsigned long addr, unsigned long len, unsigned long flags, const struct vm_special_mapping *spec); -/* This is an obsolete alternative to _install_special_mapping. */ -extern int install_special_mapping(struct mm_struct *mm, - unsigned long addr, unsigned long len, - unsigned long flags, struct page **pages); unsigned long randomize_stack_top(unsigned long stack_top); unsigned long randomize_page(unsigned long start, unsigned long range); -extern unsigned long get_unmapped_area(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); +unsigned long +__get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, + unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags); + +static inline unsigned long +get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, + unsigned long pgoff, unsigned long flags) +{ + return __get_unmapped_area(file, addr, len, pgoff, flags, 0); +} -extern unsigned long mmap_region(struct file *file, unsigned long addr, - unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, - struct list_head *uf); extern unsigned long do_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, vm_flags_t vm_flags, unsigned long pgoff, unsigned long *populate, @@ -3397,14 +3370,14 @@ extern unsigned long do_mmap(struct file *file, unsigned long addr, extern int do_vmi_munmap(struct vma_iterator *vmi, struct mm_struct *mm, unsigned long start, size_t len, struct list_head *uf, bool unlock); +int 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 unlock); extern int do_munmap(struct mm_struct *, unsigned long, size_t, struct list_head *uf); 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 unlock); extern int __mm_populate(unsigned long addr, unsigned long len, int ignore_errors); static inline void mm_populate(unsigned long addr, unsigned long len) @@ -3431,6 +3404,7 @@ struct vm_unmapped_area_info { unsigned long high_limit; unsigned long align_mask; unsigned long align_offset; + unsigned long start_gap; }; extern unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info); @@ -3446,15 +3420,13 @@ extern vm_fault_t filemap_fault(struct vm_fault *vmf); extern vm_fault_t filemap_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff); extern vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf); +extern vm_fault_t filemap_fsnotify_fault(struct vm_fault *vmf); extern unsigned long stack_guard_gap; /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */ int expand_stack_locked(struct vm_area_struct *vma, unsigned long address); struct vm_area_struct *expand_stack(struct mm_struct * mm, unsigned long addr); -/* CONFIG_STACK_GROWSUP still needs to grow downwards at some places */ -int expand_downwards(struct vm_area_struct *vma, unsigned long address); - /* Look up the first VMA which satisfies addr < vm_end, NULL if none. */ extern struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long addr); extern struct vm_area_struct * find_vma_prev(struct mm_struct * mm, unsigned long addr, @@ -3631,9 +3603,6 @@ static inline vm_fault_t vmf_fs_error(int err) return VM_FAULT_SIGBUS; } -struct page *follow_page(struct vm_area_struct *vma, unsigned long address, - unsigned int foll_flags); - static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags) { if (vm_fault & VM_FAULT_OOM) @@ -3787,24 +3756,22 @@ static inline bool page_is_guard(struct page *page) return PageGuard(page); } -bool __set_page_guard(struct zone *zone, struct page *page, unsigned int order, - int migratetype); +bool __set_page_guard(struct zone *zone, struct page *page, unsigned int order); static inline bool set_page_guard(struct zone *zone, struct page *page, - unsigned int order, int migratetype) + unsigned int order) { if (!debug_guardpage_enabled()) return false; - return __set_page_guard(zone, page, order, migratetype); + return __set_page_guard(zone, page, order); } -void __clear_page_guard(struct zone *zone, struct page *page, unsigned int order, - int migratetype); +void __clear_page_guard(struct zone *zone, struct page *page, unsigned int order); static inline void clear_page_guard(struct zone *zone, struct page *page, - unsigned int order, int migratetype) + unsigned int order) { if (!debug_guardpage_enabled()) return; - __clear_page_guard(zone, page, order, migratetype); + __clear_page_guard(zone, page, order); } #else /* CONFIG_DEBUG_PAGEALLOC */ @@ -3814,9 +3781,9 @@ static inline unsigned int debug_guardpage_minorder(void) { return 0; } static inline bool debug_guardpage_enabled(void) { return false; } static inline bool page_is_guard(struct page *page) { return false; } static inline bool set_page_guard(struct zone *zone, struct page *page, - unsigned int order, int migratetype) { return false; } + unsigned int order) { return false; } static inline void clear_page_guard(struct zone *zone, struct page *page, - unsigned int order, int migratetype) {} + unsigned int order) {} #endif /* CONFIG_DEBUG_PAGEALLOC */ #ifdef __HAVE_ARCH_GATE_AREA @@ -3839,7 +3806,7 @@ extern bool process_shares_mm(struct task_struct *p, struct mm_struct *mm); #ifdef CONFIG_SYSCTL extern int sysctl_drop_caches; -int drop_caches_sysctl_handler(struct ctl_table *, int, void *, size_t *, +int drop_caches_sysctl_handler(const struct ctl_table *, int, void *, size_t *, loff_t *); #endif @@ -3864,8 +3831,6 @@ void *sparse_buffer_alloc(unsigned long size); struct page * __populate_section_memmap(unsigned long pfn, unsigned long nr_pages, int nid, struct vmem_altmap *altmap, struct dev_pagemap *pgmap); -void pmd_init(void *addr); -void pud_init(void *addr); pgd_t *vmemmap_pgd_populate(unsigned long addr, int node); p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node); pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node); @@ -3971,7 +3936,6 @@ int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index, extern int memory_failure(unsigned long pfn, int flags); extern void memory_failure_queue_kick(int cpu); extern int unpoison_memory(unsigned long pfn); -extern void shake_page(struct page *p); extern atomic_long_t num_poisoned_pages __read_mostly; extern int soft_offline_page(unsigned long pfn, int flags); #ifdef CONFIG_MEMORY_FAILURE @@ -3984,7 +3948,6 @@ extern int __get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared); void num_poisoned_pages_inc(unsigned long pfn); void num_poisoned_pages_sub(unsigned long pfn, long i); -struct task_struct *task_early_kill(struct task_struct *tsk, int force_early); #else static inline void memory_failure_queue(unsigned long pfn, int flags) { @@ -4005,12 +3968,6 @@ static inline void num_poisoned_pages_sub(unsigned long pfn, long i) } #endif -#if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_KSM) -void add_to_kill_ksm(struct task_struct *tsk, struct page *p, - struct vm_area_struct *vma, struct list_head *to_kill, - unsigned long ksm_addr); -#endif - #if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG) extern void memblk_nr_poison_inc(unsigned long pfn); extern void memblk_nr_poison_sub(unsigned long pfn, long i); @@ -4051,10 +4008,10 @@ enum mf_result { enum mf_action_page_type { MF_MSG_KERNEL, MF_MSG_KERNEL_HIGH_ORDER, - MF_MSG_SLAB, MF_MSG_DIFFERENT_COMPOUND, MF_MSG_HUGE, MF_MSG_FREE_HUGE, + MF_MSG_GET_HWPOISON, MF_MSG_UNMAP_FAILED, MF_MSG_DIRTY_SWAPCACHE, MF_MSG_CLEAN_SWAPCACHE, @@ -4068,13 +4025,12 @@ enum mf_action_page_type { MF_MSG_BUDDY, MF_MSG_DAX, MF_MSG_UNSPLIT_THP, + MF_MSG_ALREADY_POISONED, MF_MSG_UNKNOWN, }; #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS) -extern void clear_huge_page(struct page *page, - unsigned long addr_hint, - unsigned int pages_per_huge_page); +void folio_zero_user(struct folio *folio, unsigned long addr_hint); int copy_user_large_folio(struct folio *dst, struct folio *src, unsigned long addr_hint, struct vm_area_struct *vma); @@ -4127,45 +4083,6 @@ unsigned long wp_shared_mapping_range(struct address_space *mapping, extern int sysctl_nr_trim_pages; -#ifdef CONFIG_PRINTK -void mem_dump_obj(void *object); -#else -static inline void mem_dump_obj(void *object) {} -#endif - -/** - * seal_check_write - Check for F_SEAL_WRITE or F_SEAL_FUTURE_WRITE flags and - * handle them. - * @seals: the seals to check - * @vma: the vma to operate on - * - * Check whether F_SEAL_WRITE or F_SEAL_FUTURE_WRITE are set; if so, do proper - * check/handling on the vma flags. Return 0 if check pass, or <0 for errors. - */ -static inline int seal_check_write(int seals, struct vm_area_struct *vma) -{ - if (seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) { - /* - * New PROT_WRITE and MAP_SHARED mmaps are not allowed when - * write seals are active. - */ - if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE)) - return -EPERM; - - /* - * Since an F_SEAL_[FUTURE_]WRITE sealed memfd can be mapped as - * MAP_SHARED and read-only, take care to not allow mprotect to - * revert protections on such mappings. Do this only for shared - * mappings. For private mappings, don't need to mask - * VM_MAYWRITE as we still want them to be COW-writable. - */ - if (vma->vm_flags & VM_SHARED) - vm_flags_clear(vma, VM_MAYWRITE); - } - - return 0; -} - #ifdef CONFIG_ANON_VMA_NAME int madvise_set_anon_name(struct mm_struct *mm, unsigned long start, unsigned long len_in, @@ -4180,18 +4097,18 @@ madvise_set_anon_name(struct mm_struct *mm, unsigned long start, #ifdef CONFIG_UNACCEPTED_MEMORY -bool range_contains_unaccepted_memory(phys_addr_t start, phys_addr_t end); -void accept_memory(phys_addr_t start, phys_addr_t end); +bool range_contains_unaccepted_memory(phys_addr_t start, unsigned long size); +void accept_memory(phys_addr_t start, unsigned long size); #else static inline bool range_contains_unaccepted_memory(phys_addr_t start, - phys_addr_t end) + unsigned long size) { return false; } -static inline void accept_memory(phys_addr_t start, phys_addr_t end) +static inline void accept_memory(phys_addr_t start, unsigned long size) { } @@ -4199,9 +4116,43 @@ static inline void accept_memory(phys_addr_t start, phys_addr_t end) static inline bool pfn_is_unaccepted_memory(unsigned long pfn) { - phys_addr_t paddr = pfn << PAGE_SHIFT; + return range_contains_unaccepted_memory(pfn << PAGE_SHIFT, PAGE_SIZE); +} + +void vma_pgtable_walk_begin(struct vm_area_struct *vma); +void vma_pgtable_walk_end(struct vm_area_struct *vma); + +int reserve_mem_find_by_name(const char *name, phys_addr_t *start, phys_addr_t *size); + +#ifdef CONFIG_64BIT +int do_mseal(unsigned long start, size_t len_in, unsigned long flags); +#else +static inline int do_mseal(unsigned long start, size_t len_in, unsigned long flags) +{ + /* noop on 32 bit */ + return 0; +} +#endif - return range_contains_unaccepted_memory(paddr, paddr + PAGE_SIZE); +/* + * user_alloc_needs_zeroing checks if a user folio from page allocator needs to + * be zeroed or not. + */ +static inline bool user_alloc_needs_zeroing(void) +{ + /* + * for user folios, arch with cache aliasing requires cache flush and + * arc changes folio->flags to make icache coherent with dcache, so + * always return false to make caller use + * clear_user_page()/clear_user_highpage(). + */ + return cpu_dcache_is_aliasing() || cpu_icache_is_aliasing() || + !static_branch_maybe(CONFIG_INIT_ON_ALLOC_DEFAULT_ON, + &init_on_alloc); } +int arch_get_shadow_stack_status(struct task_struct *t, unsigned long __user *status); +int arch_set_shadow_stack_status(struct task_struct *t, unsigned long status); +int arch_lock_shadow_stack_status(struct task_struct *t, unsigned long status); + #endif /* _LINUX_MM_H */ diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index f4fe593c1400..f9157a0c42a5 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -133,26 +133,25 @@ static inline int lru_hist_from_seq(unsigned long seq) return seq % NR_HIST_GENS; } -static inline int lru_tier_from_refs(int refs) +static inline int lru_tier_from_refs(int refs, bool workingset) { VM_WARN_ON_ONCE(refs > BIT(LRU_REFS_WIDTH)); - /* see the comment in folio_lru_refs() */ - return order_base_2(refs + 1); + /* see the comment on MAX_NR_TIERS */ + return workingset ? MAX_NR_TIERS - 1 : order_base_2(refs); } static inline int folio_lru_refs(struct folio *folio) { unsigned long flags = READ_ONCE(folio->flags); - bool workingset = flags & BIT(PG_workingset); + if (!(flags & BIT(PG_referenced))) + return 0; /* - * Return the number of accesses beyond PG_referenced, i.e., N-1 if the - * total number of accesses is N>1, since N=0,1 both map to the first - * tier. lru_tier_from_refs() will account for this off-by-one. Also see - * the comment on MAX_NR_TIERS. + * Return the total number of accesses including PG_referenced. Also see + * the comment on LRU_REFS_FLAGS. */ - return ((flags & LRU_REFS_MASK) >> LRU_REFS_PGOFF) + workingset; + return ((flags & LRU_REFS_MASK) >> LRU_REFS_PGOFF) + 1; } static inline int folio_lru_gen(struct folio *folio) @@ -218,6 +217,39 @@ static inline void lru_gen_update_size(struct lruvec *lruvec, struct folio *foli VM_WARN_ON_ONCE(lru_gen_is_active(lruvec, old_gen) && !lru_gen_is_active(lruvec, new_gen)); } +static inline unsigned long lru_gen_folio_seq(struct lruvec *lruvec, struct folio *folio, + bool reclaiming) +{ + int gen; + int type = folio_is_file_lru(folio); + struct lru_gen_folio *lrugen = &lruvec->lrugen; + + /* + * +-----------------------------------+-----------------------------------+ + * | Accessed through page tables and | Accessed through file descriptors | + * | promoted by folio_update_gen() | and protected by folio_inc_gen() | + * +-----------------------------------+-----------------------------------+ + * | PG_active (set while isolated) | | + * +-----------------+-----------------+-----------------+-----------------+ + * | PG_workingset | PG_referenced | PG_workingset | LRU_REFS_FLAGS | + * +-----------------------------------+-----------------------------------+ + * |<---------- MIN_NR_GENS ---------->| | + * |<---------------------------- MAX_NR_GENS ---------------------------->| + */ + if (folio_test_active(folio)) + gen = MIN_NR_GENS - folio_test_workingset(folio); + else if (reclaiming) + gen = MAX_NR_GENS; + else if ((!folio_is_file_lru(folio) && !folio_test_swapcache(folio)) || + (folio_test_reclaim(folio) && + (folio_test_dirty(folio) || folio_test_writeback(folio)))) + gen = MIN_NR_GENS; + else + gen = MAX_NR_GENS - folio_test_workingset(folio); + + return max(READ_ONCE(lrugen->max_seq) - gen + 1, READ_ONCE(lrugen->min_seq[type])); +} + static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { unsigned long seq; @@ -231,29 +263,8 @@ static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, if (folio_test_unevictable(folio) || !lrugen->enabled) return false; - /* - * There are four common cases for this page: - * 1. If it's hot, i.e., freshly faulted in, add it to the youngest - * generation, and it's protected over the rest below. - * 2. If it can't be evicted immediately, i.e., a dirty page pending - * writeback, add it to the second youngest generation. - * 3. If it should be evicted first, e.g., cold and clean from - * folio_rotate_reclaimable(), add it to the oldest generation. - * 4. Everything else falls between 2 & 3 above and is added to the - * second oldest generation if it's considered inactive, or the - * oldest generation otherwise. See lru_gen_is_active(). - */ - if (folio_test_active(folio)) - seq = lrugen->max_seq; - else if ((type == LRU_GEN_ANON && !folio_test_swapcache(folio)) || - (folio_test_reclaim(folio) && - (folio_test_dirty(folio) || folio_test_writeback(folio)))) - seq = lrugen->max_seq - 1; - else if (reclaiming || lrugen->min_seq[type] + MIN_NR_GENS >= lrugen->max_seq) - seq = lrugen->min_seq[type]; - else - seq = lrugen->min_seq[type] + 1; + seq = lru_gen_folio_seq(lruvec, folio, reclaiming); gen = lru_gen_from_seq(seq); flags = (gen + 1UL) << LRU_GEN_PGOFF; /* see the comment on MIN_NR_GENS about PG_active */ @@ -291,6 +302,12 @@ static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio, return true; } +static inline void folio_migrate_refs(struct folio *new, struct folio *old) +{ + unsigned long refs = READ_ONCE(old->flags) & LRU_REFS_MASK; + + set_mask_bits(&new->flags, LRU_REFS_MASK, refs); +} #else /* !CONFIG_LRU_GEN */ static inline bool lru_gen_enabled(void) @@ -313,6 +330,10 @@ static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio, return false; } +static inline void folio_migrate_refs(struct folio *new, struct folio *old) +{ + +} #endif /* CONFIG_LRU_GEN */ static __always_inline @@ -521,7 +542,7 @@ static inline pte_marker copy_pte_marker( { pte_marker srcm = pte_marker_get(entry); /* Always copy error entries. */ - pte_marker dstm = srcm & PTE_MARKER_POISONED; + pte_marker dstm = srcm & (PTE_MARKER_POISONED | PTE_MARKER_GUARD); /* Only copy PTE markers if UFFD register matches. */ if ((srcm & PTE_MARKER_UFFD_WP) && userfaultfd_wp(dst_vma)) @@ -541,9 +562,9 @@ static inline pte_marker copy_pte_marker( * Must be called with pgtable lock held so that no thread will see the none * pte, and if they see it, they'll fault and serialize at the pgtable lock. * - * This function is a no-op if PTE_MARKER_UFFD_WP is not enabled. + * Returns true if an uffd-wp pte was installed, false otherwise. */ -static inline void +static inline bool pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr, pte_t *pte, pte_t pteval) { @@ -560,7 +581,7 @@ pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr, * with a swap pte. There's no way of leaking the bit. */ if (vma_is_anonymous(vma) || !userfaultfd_wp(vma)) - return; + return false; /* A uffd-wp wr-protected normal pte */ if (unlikely(pte_present(pteval) && pte_uffd_wp(pteval))) @@ -573,10 +594,13 @@ pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr, if (unlikely(pte_swp_uffd_wp_any(pteval))) arm_uffd_pte = true; - if (unlikely(arm_uffd_pte)) + if (unlikely(arm_uffd_pte)) { set_pte_at(vma->vm_mm, addr, pte, make_pte_marker(PTE_MARKER_UFFD_WP)); + return true; + } #endif + return false; } static inline bool vma_has_recency(struct vm_area_struct *vma) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 5240bd7bca33..6b27db7f9496 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -46,9 +46,7 @@ struct mem_cgroup; * which is guaranteed to be aligned. If you use the same storage as * page->mapping, you must restore it to NULL before freeing the page. * - * If your page will not be mapped to userspace, you can also use the four - * bytes in the mapcount union, but you must call page_mapcount_reset() - * before freeing it. + * The mapcount field must not be used for own purposes. * * If you want to use the refcount field, it must be used in such a way * that other CPUs temporarily incrementing and then decrementing the @@ -111,7 +109,7 @@ struct page { /** * @private: Mapping-private opaque data. * Usually used for buffer_heads if PagePrivate. - * Used for swp_entry_t if PageSwapCache. + * Used for swp_entry_t if swapcache flag set. * Indicates order in the buddy system if PageBuddy. */ unsigned long private; @@ -152,18 +150,31 @@ struct page { union { /* This union is 4 bytes in size. */ /* - * If the page can be mapped to userspace, encodes the number - * of times this page is referenced by a page table. + * For head pages of typed folios, the value stored here + * allows for determining what this page is used for. The + * tail pages of typed folios will not store a type + * (page_type == _mapcount == -1). + * + * See page-flags.h for a list of page types which are currently + * stored here. + * + * Owners of typed folios may reuse the lower 16 bit of the + * head page page_type field after setting the page type, + * but must reset these 16 bit to -1 before clearing the + * page type. */ - atomic_t _mapcount; + unsigned int page_type; /* - * If the page is neither PageSlab nor mappable to userspace, - * the value stored here may help determine what this page - * is used for. See page-flags.h for a list of page types - * which are currently stored here. + * For pages that are part of non-typed folios for which mappings + * are tracked via the RMAP, encodes the number of times this page + * is directly referenced by a page table. + * + * Note that the mapcount is always initialized to -1, so that + * transitions both from it and to it can be tracked, using + * atomic_inc_and_test() and atomic_add_negative(-1). */ - unsigned int page_type; + atomic_t _mapcount; }; /* Usage count. *DO NOT USE DIRECTLY*. See page_ref.h */ @@ -171,6 +182,8 @@ struct page { #ifdef CONFIG_MEMCG unsigned long memcg_data; +#elif defined(CONFIG_SLAB_OBJ_EXT) + unsigned long _unused_slab_obj_exts; #endif /* @@ -289,7 +302,8 @@ typedef struct { * @virtual: Virtual address in the kernel direct map. * @_last_cpupid: IDs of last CPU and last process that accessed the folio. * @_entire_mapcount: Do not use directly, call folio_entire_mapcount(). - * @_nr_pages_mapped: Do not use directly, call folio_mapcount(). + * @_large_mapcount: Do not use directly, call folio_mapcount(). + * @_nr_pages_mapped: Do not use outside of rmap and debug code. * @_pincount: Do not use directly, call folio_maybe_dma_pinned(). * @_folio_nr_pages: Do not use directly, call folio_nr_pages(). * @_hugetlb_subpool: Do not use directly, use accessor in hugetlb.h. @@ -297,6 +311,7 @@ typedef struct { * @_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. + * @_unused_slab_obj_exts: Placeholder to match obj_exts in struct slab. * * 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 @@ -333,6 +348,8 @@ struct folio { atomic_t _refcount; #ifdef CONFIG_MEMCG unsigned long memcg_data; +#elif defined(CONFIG_SLAB_OBJ_EXT) + unsigned long _unused_slab_obj_exts; #endif #if defined(WANT_PAGE_VIRTUAL) void *virtual; @@ -348,8 +365,8 @@ struct folio { struct { unsigned long _flags_1; unsigned long _head_1; - unsigned long _folio_avail; /* public: */ + atomic_t _large_mapcount; atomic_t _entire_mapcount; atomic_t _nr_pages_mapped; atomic_t _pincount; @@ -421,13 +438,16 @@ FOLIO_MATCH(compound_head, _head_2a); * struct ptdesc - Memory descriptor for page tables. * @__page_flags: Same as page flags. Powerpc only. * @pt_rcu_head: For freeing page table pages. - * @pt_list: List of used page tables. Used for s390 and x86. + * @pt_list: List of used page tables. Used for s390 gmap shadow pages + * (which are not linked into the user page tables) and x86 + * pgds. * @_pt_pad_1: Padding that aliases with page's compound head. * @pmd_huge_pte: Protected by ptdesc->ptl, used for THPs. * @__page_mapping: Aliases with page->mapping. Unused for page tables. * @pt_index: Used for s390 gmap. * @pt_mm: Used for x86 pgds. * @pt_frag_refcount: For fragmented page table tracking. Powerpc only. + * @pt_share_count: Used for HugeTLB PMD page table share count. * @_pt_pad_2: Padding to ensure proper alignment. * @ptl: Lock for the page table. * @__page_type: Same as page->page_type. Unused for page tables. @@ -454,6 +474,9 @@ struct ptdesc { pgoff_t pt_index; struct mm_struct *pt_mm; atomic_t pt_frag_refcount; +#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING + atomic_t pt_share_count; +#endif }; union { @@ -499,14 +522,37 @@ static_assert(sizeof(struct ptdesc) <= sizeof(struct page)); const struct page *: (const struct ptdesc *)(p), \ struct page *: (struct ptdesc *)(p))) +#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING +static inline void ptdesc_pmd_pts_init(struct ptdesc *ptdesc) +{ + atomic_set(&ptdesc->pt_share_count, 0); +} + +static inline void ptdesc_pmd_pts_inc(struct ptdesc *ptdesc) +{ + atomic_inc(&ptdesc->pt_share_count); +} + +static inline void ptdesc_pmd_pts_dec(struct ptdesc *ptdesc) +{ + atomic_dec(&ptdesc->pt_share_count); +} + +static inline int ptdesc_pmd_pts_count(struct ptdesc *ptdesc) +{ + return atomic_read(&ptdesc->pt_share_count); +} +#else +static inline void ptdesc_pmd_pts_init(struct ptdesc *ptdesc) +{ +} +#endif + /* * Used for sizing the vmemmap region on some architectures */ #define STRUCT_PAGE_MAX_SHIFT (order_base_2(sizeof(struct page))) -#define PAGE_FRAG_CACHE_MAX_SIZE __ALIGN_MASK(32768, ~PAGE_MASK) -#define PAGE_FRAG_CACHE_MAX_ORDER get_order(PAGE_FRAG_CACHE_MAX_SIZE) - /* * page_private can be used on tail pages. However, PagePrivate is only * checked by the VM on the head page. So page_private on the tail pages @@ -525,21 +571,6 @@ static inline void *folio_get_private(struct folio *folio) return folio->private; } -struct page_frag_cache { - void * va; -#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) - __u16 offset; - __u16 size; -#else - __u32 offset; -#endif - /* we maintain a pagecount bias, so that we dont dirty cache line - * containing page->_refcount every time we allocate a fragment. - */ - unsigned int pagecnt_bias; - bool pfmemalloc; -}; - typedef unsigned long vm_flags_t; /* @@ -643,6 +674,9 @@ struct vma_numab_state { * per VM-area/task. A VM area is any part of the process virtual memory * space that has a special rule for the page-fault handlers (ie a shared * library, the executable area etc). + * + * Only explicitly marked struct members may be accessed by RCU readers before + * getting a stable reference. */ struct vm_area_struct { /* The first cache line has the info for VMA tree walking. */ @@ -658,7 +692,11 @@ struct vm_area_struct { #endif }; - struct mm_struct *vm_mm; /* The address space we belong to. */ + /* + * The address space we belong to. + * Unstable RCU readers are allowed to read this. + */ + struct mm_struct *vm_mm; pgprot_t vm_page_prot; /* Access permissions of this VMA. */ /* @@ -672,6 +710,12 @@ struct vm_area_struct { #ifdef CONFIG_PER_VMA_LOCK /* + * Flag to indicate areas detached from the mm->mm_mt tree. + * Unstable RCU readers are allowed to read this. + */ + bool detached; + + /* * Can only be written (using WRITE_ONCE()) while holding both: * - mmap_lock (in write mode) * - vm_lock->lock (in write mode) @@ -685,11 +729,9 @@ struct vm_area_struct { * counter reuse can only lead to occasional unnecessary use of the * slowpath. */ - int vm_lock_seq; + unsigned int vm_lock_seq; + /* Unstable RCU readers are allowed to read this. */ struct vma_lock *vm_lock; - - /* Flag to indicate areas detached from the mm->mm_mt tree */ - bool detached; #endif /* @@ -754,6 +796,7 @@ struct vm_area_struct { struct mm_cid { u64 time; int cid; + int recent_cid; }; #endif @@ -777,11 +820,7 @@ struct mm_struct { } ____cacheline_aligned_in_smp; struct maple_tree mm_mt; -#ifdef CONFIG_MMU - unsigned long (*get_unmapped_area) (struct file *filp, - unsigned long addr, unsigned long len, - unsigned long pgoff, unsigned long flags); -#endif + unsigned long mmap_base; /* base of mmap area */ unsigned long mmap_legacy_base; /* base of mmap area in bottom-up allocations */ #ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES @@ -828,6 +867,27 @@ struct mm_struct { * When the next mm_cid scan is due (in jiffies). */ unsigned long mm_cid_next_scan; + /** + * @nr_cpus_allowed: Number of CPUs allowed for mm. + * + * Number of CPUs allowed in the union of all mm's + * threads allowed CPUs. + */ + unsigned int nr_cpus_allowed; + /** + * @max_nr_cid: Maximum number of concurrency IDs allocated. + * + * Track the highest number of concurrency IDs allocated for the + * mm. + */ + atomic_t max_nr_cid; + /** + * @cpus_allowed_lock: Lock protecting mm cpus_allowed. + * + * Provide mutual exclusion for mm cpus_allowed and + * mm nr_cpus_allowed updates. + */ + raw_spinlock_t cpus_allowed_lock; #endif #ifdef CONFIG_MMU atomic_long_t pgtables_bytes; /* size of all page tables */ @@ -863,6 +923,9 @@ struct mm_struct { * Roughly speaking, incrementing the sequence number is * equivalent to releasing locks on VMAs; reading the sequence * number can be part of taking a read lock on a VMA. + * Incremented every time mmap_lock is write-locked/unlocked. + * Initialized to 0, therefore odd values indicate mmap_lock + * is write-locked and even values that it's released. * * Can be modified under write mmap_lock using RELEASE * semantics. @@ -871,7 +934,7 @@ struct mm_struct { * Can be read with ACQUIRE semantics if not holding write * mmap_lock. */ - int mm_lock_seq; + seqcount_t mm_lock_seq; #endif @@ -934,7 +997,7 @@ struct mm_struct { #ifdef CONFIG_MMU_NOTIFIER struct mmu_notifier_subscriptions *notifier_subscriptions; #endif -#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !defined(CONFIG_SPLIT_PMD_PTLOCKS) pgtable_t pmd_huge_pte; /* protected by page_table_lock */ #endif #ifdef CONFIG_NUMA_BALANCING @@ -988,7 +1051,7 @@ struct mm_struct { * Represent how many empty pages are merged with kernel zero * pages when enabling KSM use_zero_pages. */ - unsigned long ksm_zero_pages; + atomic_long_t ksm_zero_pages; #endif /* CONFIG_KSM */ #ifdef CONFIG_LRU_GEN_WALKS_MMU struct { @@ -1146,18 +1209,30 @@ static inline int mm_cid_clear_lazy_put(int cid) return cid & ~MM_CID_LAZY_PUT; } +/* + * mm_cpus_allowed: Union of all mm's threads allowed CPUs. + */ +static inline cpumask_t *mm_cpus_allowed(struct mm_struct *mm) +{ + unsigned long bitmap = (unsigned long)mm; + + bitmap += offsetof(struct mm_struct, cpu_bitmap); + /* Skip cpu_bitmap */ + bitmap += cpumask_size(); + return (struct cpumask *)bitmap; +} + /* Accessor for struct mm_struct's cidmask. */ static inline cpumask_t *mm_cidmask(struct mm_struct *mm) { - unsigned long cid_bitmap = (unsigned long)mm; + unsigned long cid_bitmap = (unsigned long)mm_cpus_allowed(mm); - cid_bitmap += offsetof(struct mm_struct, cpu_bitmap); - /* Skip cpu_bitmap */ + /* Skip mm_cpus_allowed */ cid_bitmap += cpumask_size(); return (struct cpumask *)cid_bitmap; } -static inline void mm_init_cid(struct mm_struct *mm) +static inline void mm_init_cid(struct mm_struct *mm, struct task_struct *p) { int i; @@ -1165,19 +1240,25 @@ static inline void mm_init_cid(struct mm_struct *mm) struct mm_cid *pcpu_cid = per_cpu_ptr(mm->pcpu_cid, i); pcpu_cid->cid = MM_CID_UNSET; + pcpu_cid->recent_cid = MM_CID_UNSET; pcpu_cid->time = 0; } + mm->nr_cpus_allowed = p->nr_cpus_allowed; + atomic_set(&mm->max_nr_cid, 0); + raw_spin_lock_init(&mm->cpus_allowed_lock); + cpumask_copy(mm_cpus_allowed(mm), &p->cpus_mask); cpumask_clear(mm_cidmask(mm)); } -static inline int mm_alloc_cid(struct mm_struct *mm) +static inline int mm_alloc_cid_noprof(struct mm_struct *mm, struct task_struct *p) { - mm->pcpu_cid = alloc_percpu(struct mm_cid); + mm->pcpu_cid = alloc_percpu_noprof(struct mm_cid); if (!mm->pcpu_cid) return -ENOMEM; - mm_init_cid(mm); + mm_init_cid(mm, p); return 0; } +#define mm_alloc_cid(...) alloc_hooks(mm_alloc_cid_noprof(__VA_ARGS__)) static inline void mm_destroy_cid(struct mm_struct *mm) { @@ -1187,16 +1268,31 @@ static inline void mm_destroy_cid(struct mm_struct *mm) static inline unsigned int mm_cid_size(void) { - return cpumask_size(); + return 2 * cpumask_size(); /* mm_cpus_allowed(), mm_cidmask(). */ +} + +static inline void mm_set_cpus_allowed(struct mm_struct *mm, const struct cpumask *cpumask) +{ + struct cpumask *mm_allowed = mm_cpus_allowed(mm); + + if (!mm) + return; + /* The mm_cpus_allowed is the union of each thread allowed CPUs masks. */ + raw_spin_lock(&mm->cpus_allowed_lock); + cpumask_or(mm_allowed, mm_allowed, cpumask); + WRITE_ONCE(mm->nr_cpus_allowed, cpumask_weight(mm_allowed)); + raw_spin_unlock(&mm->cpus_allowed_lock); } #else /* CONFIG_SCHED_MM_CID */ -static inline void mm_init_cid(struct mm_struct *mm) { } -static inline int mm_alloc_cid(struct mm_struct *mm) { return 0; } +static inline void mm_init_cid(struct mm_struct *mm, struct task_struct *p) { } +static inline int mm_alloc_cid(struct mm_struct *mm, struct task_struct *p) { return 0; } static inline void mm_destroy_cid(struct mm_struct *mm) { } + static inline unsigned int mm_cid_size(void) { return 0; } +static inline void mm_set_cpus_allowed(struct mm_struct *mm, const struct cpumask *cpumask) { } #endif /* CONFIG_SCHED_MM_CID */ struct mmu_gather; @@ -1299,6 +1395,9 @@ struct vm_special_mapping { int (*mremap)(const struct vm_special_mapping *sm, struct vm_area_struct *new_vma); + + void (*close)(const struct vm_special_mapping *sm, + struct vm_area_struct *vma); }; enum tlb_flush_reason { @@ -1307,6 +1406,7 @@ enum tlb_flush_reason { TLB_LOCAL_SHOOTDOWN, TLB_LOCAL_MM_SHOOTDOWN, TLB_REMOTE_SEND_IPI, + TLB_REMOTE_WRONG_CPU, NR_TLB_FLUSH_REASONS, }; @@ -1370,6 +1470,15 @@ enum fault_flag { typedef unsigned int __bitwise zap_flags_t; +/* Flags for clear_young_dirty_ptes(). */ +typedef int __bitwise cydp_t; + +/* Clear the access bit */ +#define CYDP_CLEAR_YOUNG ((__force cydp_t)BIT(0)) + +/* Clear the dirty bit */ +#define CYDP_CLEAR_DIRTY ((__force cydp_t)BIT(1)) + /* * FOLL_PIN and FOLL_LONGTERM may be used in various combinations with each * other. Here is what they mean, and how to use them: @@ -1462,4 +1571,88 @@ enum { /* See also internal only FOLL flags in mm/internal.h */ }; +/* mm flags */ + +/* + * The first two bits represent core dump modes for set-user-ID, + * the modes are SUID_DUMP_* defined in linux/sched/coredump.h + */ +#define MMF_DUMPABLE_BITS 2 +#define MMF_DUMPABLE_MASK ((1 << MMF_DUMPABLE_BITS) - 1) +/* coredump filter bits */ +#define MMF_DUMP_ANON_PRIVATE 2 +#define MMF_DUMP_ANON_SHARED 3 +#define MMF_DUMP_MAPPED_PRIVATE 4 +#define MMF_DUMP_MAPPED_SHARED 5 +#define MMF_DUMP_ELF_HEADERS 6 +#define MMF_DUMP_HUGETLB_PRIVATE 7 +#define MMF_DUMP_HUGETLB_SHARED 8 +#define MMF_DUMP_DAX_PRIVATE 9 +#define MMF_DUMP_DAX_SHARED 10 + +#define MMF_DUMP_FILTER_SHIFT MMF_DUMPABLE_BITS +#define MMF_DUMP_FILTER_BITS 9 +#define MMF_DUMP_FILTER_MASK \ + (((1 << MMF_DUMP_FILTER_BITS) - 1) << MMF_DUMP_FILTER_SHIFT) +#define MMF_DUMP_FILTER_DEFAULT \ + ((1 << MMF_DUMP_ANON_PRIVATE) | (1 << MMF_DUMP_ANON_SHARED) |\ + (1 << MMF_DUMP_HUGETLB_PRIVATE) | MMF_DUMP_MASK_DEFAULT_ELF) + +#ifdef CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS +# define MMF_DUMP_MASK_DEFAULT_ELF (1 << MMF_DUMP_ELF_HEADERS) +#else +# define MMF_DUMP_MASK_DEFAULT_ELF 0 +#endif + /* leave room for more dump flags */ +#define MMF_VM_MERGEABLE 16 /* KSM may merge identical pages */ +#define MMF_VM_HUGEPAGE 17 /* set when mm is available for khugepaged */ + +/* + * This one-shot flag is dropped due to necessity of changing exe once again + * on NFS restore + */ +//#define MMF_EXE_FILE_CHANGED 18 /* see prctl_set_mm_exe_file() */ + +#define MMF_HAS_UPROBES 19 /* has uprobes */ +#define MMF_RECALC_UPROBES 20 /* MMF_HAS_UPROBES can be wrong */ +#define MMF_OOM_SKIP 21 /* mm is of no interest for the OOM killer */ +#define MMF_UNSTABLE 22 /* mm is unstable for copy_from_user */ +#define MMF_HUGE_ZERO_PAGE 23 /* mm has ever used the global huge zero page */ +#define MMF_DISABLE_THP 24 /* disable THP for all VMAs */ +#define MMF_DISABLE_THP_MASK (1 << MMF_DISABLE_THP) +#define MMF_OOM_REAP_QUEUED 25 /* mm was queued for oom_reaper */ +#define MMF_MULTIPROCESS 26 /* mm is shared between processes */ +/* + * MMF_HAS_PINNED: Whether this mm has pinned any pages. This can be either + * replaced in the future by mm.pinned_vm when it becomes stable, or grow into + * a counter on its own. We're aggresive on this bit for now: even if the + * pinned pages were unpinned later on, we'll still keep this bit set for the + * 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_HAS_MDWE_NO_INHERIT 29 + +#define MMF_VM_MERGE_ANY 30 +#define MMF_VM_MERGE_ANY_MASK (1 << MMF_VM_MERGE_ANY) + +#define MMF_TOPDOWN 31 /* mm searches top down by default */ +#define MMF_TOPDOWN_MASK (1 << MMF_TOPDOWN) + +#define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\ + MMF_DISABLE_THP_MASK | MMF_HAS_MDWE_MASK |\ + MMF_VM_MERGE_ANY_MASK | MMF_TOPDOWN_MASK) + +static inline unsigned long mmf_init_flags(unsigned long flags) +{ + if (flags & (1UL << MMF_HAS_MDWE_NO_INHERIT)) + flags &= ~((1UL << MMF_HAS_MDWE) | + (1UL << MMF_HAS_MDWE_NO_INHERIT)); + return flags & MMF_INIT_MASK; +} + #endif /* _LINUX_MM_TYPES_H */ diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h index a2f6179b672b..a82aa80c0ba4 100644 --- a/include/linux/mm_types_task.h +++ b/include/linux/mm_types_task.h @@ -8,6 +8,7 @@ * (These are defined separately to decouple sched.h from mm_types.h as much as possible.) */ +#include <linux/align.h> #include <linux/types.h> #include <asm/page.h> @@ -16,9 +17,6 @@ #include <asm/tlbbatch.h> #endif -#define USE_SPLIT_PTE_PTLOCKS (NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS) -#define USE_SPLIT_PMD_PTLOCKS (USE_SPLIT_PTE_PTLOCKS && \ - IS_ENABLED(CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK)) #define ALLOC_SPLIT_PTLOCKS (SPINLOCK_SIZE > BITS_PER_LONG/8) /* @@ -46,6 +44,26 @@ struct page_frag { #endif }; +#define PAGE_FRAG_CACHE_MAX_SIZE __ALIGN_MASK(32768, ~PAGE_MASK) +#define PAGE_FRAG_CACHE_MAX_ORDER get_order(PAGE_FRAG_CACHE_MAX_SIZE) +struct page_frag_cache { + /* encoded_page consists of the virtual address, pfmemalloc bit and + * order of a page. + */ + unsigned long encoded_page; + + /* we maintain a pagecount bias, so that we dont dirty cache line + * containing page->_refcount every time we allocate a fragment. + */ +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) && (BITS_PER_LONG <= 32) + __u16 offset; + __u16 pagecnt_bias; +#else + __u32 offset; + __u32 pagecnt_bias; +#endif +}; + /* Track pages that require TLB flushes */ struct tlbflush_unmap_batch { #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH diff --git a/include/linux/mman.h b/include/linux/mman.h index bcb201ab7a41..a842783ffa62 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -2,6 +2,7 @@ #ifndef _LINUX_MMAN_H #define _LINUX_MMAN_H +#include <linux/fs.h> #include <linux/mm.h> #include <linux/percpu_counter.h> @@ -94,7 +95,7 @@ static inline void vm_unacct_memory(long pages) #endif #ifndef arch_calc_vm_flag_bits -#define arch_calc_vm_flag_bits(flags) 0 +#define arch_calc_vm_flag_bits(file, flags) 0 #endif #ifndef arch_validate_prot @@ -151,13 +152,13 @@ calc_vm_prot_bits(unsigned long prot, unsigned long pkey) * Combine the mmap "flags" argument into "vm_flags" used internally. */ static inline unsigned long -calc_vm_flag_bits(unsigned long flags) +calc_vm_flag_bits(struct file *file, unsigned long flags) { return _calc_vm_trans(flags, MAP_GROWSDOWN, VM_GROWSDOWN ) | _calc_vm_trans(flags, MAP_LOCKED, VM_LOCKED ) | _calc_vm_trans(flags, MAP_SYNC, VM_SYNC ) | _calc_vm_trans(flags, MAP_STACK, VM_NOHUGEPAGE) | - arch_calc_vm_flag_bits(flags); + arch_calc_vm_flag_bits(file, flags); } unsigned long vm_commit_limit(void); @@ -188,16 +189,31 @@ static inline bool arch_memory_deny_write_exec_supported(void) * * d) mmap(PROT_READ | PROT_EXEC) * mmap(PROT_READ | PROT_EXEC | PROT_BTI) + * + * This is only applicable if the user has set the Memory-Deny-Write-Execute + * (MDWE) protection mask for the current process. + * + * @old specifies the VMA flags the VMA originally possessed, and @new the ones + * we propose to set. + * + * Return: false if proposed change is OK, true if not ok and should be denied. */ -static inline bool map_deny_write_exec(struct vm_area_struct *vma, unsigned long vm_flags) +static inline bool map_deny_write_exec(unsigned long old, unsigned long new) { + /* If MDWE is disabled, we have nothing to deny. */ if (!test_bit(MMF_HAS_MDWE, ¤t->mm->flags)) return false; - if ((vm_flags & VM_EXEC) && (vm_flags & VM_WRITE)) + /* If the new VMA is not executable, we have nothing to deny. */ + if (!(new & VM_EXEC)) + return false; + + /* Under MDWE we do not accept newly writably executable VMAs... */ + if (new & VM_WRITE) return true; - if (!(vma->vm_flags & VM_EXEC) && (vm_flags & VM_EXEC)) + /* ...nor previously non-executable VMAs becoming executable. */ + if (!(old & VM_EXEC)) return true; return false; diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index 8d38dcb6d044..45a21faa3ff6 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -60,52 +60,79 @@ static inline void __mmap_lock_trace_released(struct mm_struct *mm, bool write) #endif /* CONFIG_TRACING */ -static inline void mmap_assert_locked(struct mm_struct *mm) +static inline void mmap_assert_locked(const struct mm_struct *mm) { - lockdep_assert_held(&mm->mmap_lock); - VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm); + rwsem_assert_held(&mm->mmap_lock); } -static inline void mmap_assert_write_locked(struct mm_struct *mm) +static inline void mmap_assert_write_locked(const struct mm_struct *mm) { - lockdep_assert_held_write(&mm->mmap_lock); - VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm); + rwsem_assert_held_write(&mm->mmap_lock); } #ifdef CONFIG_PER_VMA_LOCK -/* - * Drop all currently-held per-VMA locks. - * This is called from the mmap_lock implementation directly before releasing - * a write-locked mmap_lock (or downgrading it to read-locked). - * This should normally NOT be called manually from other places. - * If you want to call this manually anyway, keep in mind that this will release - * *all* VMA write locks, including ones from further up the stack. - */ -static inline void vma_end_write_all(struct mm_struct *mm) + +static inline void mm_lock_seqcount_init(struct mm_struct *mm) +{ + seqcount_init(&mm->mm_lock_seq); +} + +static inline void mm_lock_seqcount_begin(struct mm_struct *mm) +{ + do_raw_write_seqcount_begin(&mm->mm_lock_seq); +} + +static inline void mm_lock_seqcount_end(struct mm_struct *mm) +{ + ASSERT_EXCLUSIVE_WRITER(mm->mm_lock_seq); + do_raw_write_seqcount_end(&mm->mm_lock_seq); +} + +static inline bool mmap_lock_speculate_try_begin(struct mm_struct *mm, unsigned int *seq) { - mmap_assert_write_locked(mm); /* - * Nobody can concurrently modify mm->mm_lock_seq due to exclusive - * mmap_lock being held. - * We need RELEASE semantics here to ensure that preceding stores into - * the VMA take effect before we unlock it with this store. - * Pairs with ACQUIRE semantics in vma_start_read(). + * Since mmap_lock is a sleeping lock, and waiting for it to become + * unlocked is more or less equivalent with taking it ourselves, don't + * bother with the speculative path if mmap_lock is already write-locked + * and take the slow path, which takes the lock. */ - smp_store_release(&mm->mm_lock_seq, mm->mm_lock_seq + 1); + return raw_seqcount_try_begin(&mm->mm_lock_seq, *seq); +} + +static inline bool mmap_lock_speculate_retry(struct mm_struct *mm, unsigned int seq) +{ + return read_seqcount_retry(&mm->mm_lock_seq, seq); } -#else -static inline void vma_end_write_all(struct mm_struct *mm) {} -#endif + +#else /* CONFIG_PER_VMA_LOCK */ + +static inline void mm_lock_seqcount_init(struct mm_struct *mm) {} +static inline void mm_lock_seqcount_begin(struct mm_struct *mm) {} +static inline void mm_lock_seqcount_end(struct mm_struct *mm) {} + +static inline bool mmap_lock_speculate_try_begin(struct mm_struct *mm, unsigned int *seq) +{ + return false; +} + +static inline bool mmap_lock_speculate_retry(struct mm_struct *mm, unsigned int seq) +{ + return true; +} + +#endif /* CONFIG_PER_VMA_LOCK */ static inline void mmap_init_lock(struct mm_struct *mm) { init_rwsem(&mm->mmap_lock); + mm_lock_seqcount_init(mm); } static inline void mmap_write_lock(struct mm_struct *mm) { __mmap_lock_trace_start_locking(mm, true); down_write(&mm->mmap_lock); + mm_lock_seqcount_begin(mm); __mmap_lock_trace_acquire_returned(mm, true, true); } @@ -113,6 +140,7 @@ static inline void mmap_write_lock_nested(struct mm_struct *mm, int subclass) { __mmap_lock_trace_start_locking(mm, true); down_write_nested(&mm->mmap_lock, subclass); + mm_lock_seqcount_begin(mm); __mmap_lock_trace_acquire_returned(mm, true, true); } @@ -122,10 +150,26 @@ static inline int mmap_write_lock_killable(struct mm_struct *mm) __mmap_lock_trace_start_locking(mm, true); ret = down_write_killable(&mm->mmap_lock); + if (!ret) + mm_lock_seqcount_begin(mm); __mmap_lock_trace_acquire_returned(mm, true, ret == 0); return ret; } +/* + * Drop all currently-held per-VMA locks. + * This is called from the mmap_lock implementation directly before releasing + * a write-locked mmap_lock (or downgrading it to read-locked). + * This should normally NOT be called manually from other places. + * If you want to call this manually anyway, keep in mind that this will release + * *all* VMA write locks, including ones from further up the stack. + */ +static inline void vma_end_write_all(struct mm_struct *mm) +{ + mmap_assert_write_locked(mm); + mm_lock_seqcount_end(mm); +} + static inline void mmap_write_unlock(struct mm_struct *mm) { __mmap_lock_trace_released(mm, true); diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index f34407cc2788..526fce581657 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -35,7 +35,7 @@ struct mmc_csd { unsigned int wp_grp_size; unsigned int read_blkbits; unsigned int write_blkbits; - unsigned int capacity; + sector_t capacity; unsigned int read_partial:1, read_misalign:1, write_partial:1, @@ -188,6 +188,12 @@ struct sd_switch_caps { #define SD_MAX_CURRENT_400 (1 << SD_SET_CURRENT_LIMIT_400) #define SD_MAX_CURRENT_600 (1 << SD_SET_CURRENT_LIMIT_600) #define SD_MAX_CURRENT_800 (1 << SD_SET_CURRENT_LIMIT_800) + +#define SD4_SET_POWER_LIMIT_0_72W 0 +#define SD4_SET_POWER_LIMIT_1_44W 1 +#define SD4_SET_POWER_LIMIT_2_16W 2 +#define SD4_SET_POWER_LIMIT_2_88W 3 +#define SD4_SET_POWER_LIMIT_1_80W 4 }; struct sd_ext_reg { @@ -209,6 +215,34 @@ struct sd_ext_reg { #define SD_EXT_PERF_CMD_QUEUE (1<<4) }; +struct sd_uhs2_config { + u32 node_id; + + u32 n_fcu; + u32 maxblk_len; + u8 n_lanes; + u8 dadr_len; + u8 app_type; + u8 phy_minor_rev; + u8 phy_major_rev; + u8 can_hibernate; + u8 n_lss_sync; + u8 n_lss_dir; + u8 link_minor_rev; + u8 link_major_rev; + u8 dev_type; + u8 n_data_gap; + + u32 n_fcu_set; + u32 maxblk_len_set; + u8 n_lanes_set; + u8 speed_range_set; + u8 n_lss_sync_set; + u8 n_lss_dir_set; + u8 n_data_gap_set; + u8 max_retry_set; +}; + struct sdio_cccr { unsigned int sdio_vsn; unsigned int sd_vsn; @@ -294,6 +328,7 @@ struct mmc_card { #define MMC_QUIRK_BROKEN_SD_DISCARD (1<<14) /* Disable broken SD discard support */ #define MMC_QUIRK_BROKEN_SD_CACHE (1<<15) /* Disable broken SD cache support */ #define MMC_QUIRK_BROKEN_CACHE_FLUSH (1<<16) /* Don't flush cache until the write has occurred */ +#define MMC_QUIRK_BROKEN_SD_POWEROFF_NOTIFY (1<<17) /* Disable broken SD poweroff notify support */ bool written_flag; /* Indicates eMMC has been written since power on */ bool reenable_cmdq; /* Re-enable Command Queue */ @@ -319,6 +354,8 @@ struct mmc_card { struct sd_ext_reg ext_power; /* SD extension reg for PM */ struct sd_ext_reg ext_perf; /* SD extension reg for PERF */ + struct sd_uhs2_config uhs2_config; /* SD UHS-II config */ + unsigned int sdio_funcs; /* number of SDIO functions */ atomic_t sdio_funcs_probed; /* number of probed SDIO funcs */ struct sdio_cccr cccr; /* common card info */ diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h index 2c7928a50907..01e0f591a20b 100644 --- a/include/linux/mmc/core.h +++ b/include/linux/mmc/core.h @@ -11,16 +11,18 @@ struct mmc_data; struct mmc_request; -enum mmc_blk_status { - MMC_BLK_SUCCESS = 0, - MMC_BLK_PARTIAL, - MMC_BLK_CMD_ERR, - MMC_BLK_RETRY, - MMC_BLK_ABORT, - MMC_BLK_DATA_ERR, - MMC_BLK_ECC_ERR, - MMC_BLK_NOMEDIUM, - MMC_BLK_NEW_REQUEST, +#define UHS2_MAX_PAYLOAD_LEN 2 +#define UHS2_MAX_RESP_LEN 20 + +struct uhs2_command { + u16 header; + u16 arg; + __be32 payload[UHS2_MAX_PAYLOAD_LEN]; + u8 payload_len; + u8 packet_len; + u8 tmode_half_duplex; + u8 uhs2_resp[UHS2_MAX_RESP_LEN]; /* UHS2 native cmd resp */ + u8 uhs2_resp_len; /* UHS2 native cmd resp len */ }; struct mmc_command { @@ -55,6 +57,7 @@ struct mmc_command { #define MMC_RSP_NONE (0) #define MMC_RSP_R1 (MMC_RSP_PRESENT|MMC_RSP_CRC|MMC_RSP_OPCODE) #define MMC_RSP_R1B (MMC_RSP_PRESENT|MMC_RSP_CRC|MMC_RSP_OPCODE|MMC_RSP_BUSY) +#define MMC_RSP_R1B_NO_CRC (MMC_RSP_PRESENT|MMC_RSP_OPCODE|MMC_RSP_BUSY) #define MMC_RSP_R2 (MMC_RSP_PRESENT|MMC_RSP_136|MMC_RSP_CRC) #define MMC_RSP_R3 (MMC_RSP_PRESENT) #define MMC_RSP_R4 (MMC_RSP_PRESENT) @@ -62,9 +65,6 @@ struct mmc_command { #define MMC_RSP_R6 (MMC_RSP_PRESENT|MMC_RSP_CRC|MMC_RSP_OPCODE) #define MMC_RSP_R7 (MMC_RSP_PRESENT|MMC_RSP_CRC|MMC_RSP_OPCODE) -/* Can be used by core to poll after switch to MMC HS mode */ -#define MMC_RSP_R1_NO_CRC (MMC_RSP_PRESENT|MMC_RSP_OPCODE) - #define mmc_resp_type(cmd) ((cmd)->flags & (MMC_RSP_PRESENT|MMC_RSP_136|MMC_RSP_CRC|MMC_RSP_BUSY|MMC_RSP_OPCODE)) /* @@ -108,6 +108,12 @@ struct mmc_command { unsigned int busy_timeout; /* busy detect timeout in ms */ struct mmc_data *data; /* data segment associated with cmd */ struct mmc_request *mrq; /* associated request */ + + struct uhs2_command *uhs2_cmd; /* UHS2 command */ + + /* for SDUC */ + bool has_ext_addr; + u8 ext_addr; }; struct mmc_data { @@ -166,6 +172,7 @@ struct mmc_request { const struct bio_crypt_ctx *crypto_ctx; int crypto_key_slot; #endif + struct uhs2_command uhs2_cmd; }; struct mmc_card; diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 5894bf912f7b..68f09a955a90 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -10,12 +10,14 @@ #include <linux/sched.h> #include <linux/device.h> #include <linux/fault-inject.h> +#include <linux/debugfs.h> #include <linux/mmc/core.h> #include <linux/mmc/card.h> #include <linux/mmc/pm.h> #include <linux/dma-direction.h> #include <linux/blk-crypto-profile.h> +#include <linux/mmc/sd_uhs2.h> struct mmc_ios { unsigned int clock; /* clock rate */ @@ -63,6 +65,10 @@ struct mmc_ios { #define MMC_TIMING_MMC_HS400 10 #define MMC_TIMING_SD_EXP 11 #define MMC_TIMING_SD_EXP_1_2V 12 +#define MMC_TIMING_UHS2_SPEED_A 13 +#define MMC_TIMING_UHS2_SPEED_A_HD 14 +#define MMC_TIMING_UHS2_SPEED_B 15 +#define MMC_TIMING_UHS2_SPEED_B_HD 16 unsigned char signal_voltage; /* signalling voltage (1.8V or 3.3V) */ @@ -70,6 +76,9 @@ struct mmc_ios { #define MMC_SIGNAL_VOLTAGE_180 1 #define MMC_SIGNAL_VOLTAGE_120 2 + unsigned char vqmmc2_voltage; +#define MMC_VQMMC2_VOLTAGE_180 0 + unsigned char drv_type; /* driver type (A, B, C, D) */ #define MMC_SET_DRIVER_TYPE_B 0 @@ -91,6 +100,43 @@ struct mmc_clk_phase_map { struct mmc_clk_phase phase[MMC_NUM_CLK_PHASES]; }; +struct sd_uhs2_caps { + u32 dap; + u32 gap; + u32 group_desc; + u32 maxblk_len; + u32 n_fcu; + u8 n_lanes; + u8 addr64; + u8 card_type; + u8 phy_rev; + u8 speed_range; + u8 n_lss_sync; + u8 n_lss_dir; + u8 link_rev; + u8 host_type; + u8 n_data_gap; + + u32 maxblk_len_set; + u32 n_fcu_set; + u8 n_lanes_set; + u8 n_lss_sync_set; + u8 n_lss_dir_set; + u8 n_data_gap_set; + u8 max_retry_set; +}; + +enum sd_uhs2_operation { + UHS2_PHY_INIT = 0, + UHS2_SET_CONFIG, + UHS2_ENABLE_INT, + UHS2_DISABLE_INT, + UHS2_ENABLE_CLK, + UHS2_DISABLE_CLK, + UHS2_CHECK_DORMANT, + UHS2_SET_IOS, +}; + struct mmc_host; enum mmc_err_stat { @@ -218,6 +264,14 @@ struct mmc_host_ops { /* Initialize an SD express card, mandatory for MMC_CAP2_SD_EXP. */ int (*init_sd_express)(struct mmc_host *host, struct mmc_ios *ios); + + /* + * The uhs2_control callback is used to execute SD UHS-II specific + * operations. It's mandatory to implement for hosts that supports the + * SD UHS-II interface (MMC_CAP2_SD_UHS2). Expected return values are a + * negative errno in case of a failure or zero for success. + */ + int (*uhs2_control)(struct mmc_host *host, enum sd_uhs2_operation op); }; struct mmc_cqe_ops { @@ -264,16 +318,6 @@ struct mmc_cqe_ops { void (*cqe_recovery_finish)(struct mmc_host *host); }; -struct mmc_async_req { - /* active mmc request */ - struct mmc_request *mrq; - /* - * Check error status of completed mmc request. - * Returns 0 if success otherwise non zero. - */ - enum mmc_blk_status (*err_check)(struct mmc_card *, struct mmc_async_req *); -}; - /** * struct mmc_slot - MMC slot functions * @@ -291,26 +335,13 @@ struct mmc_slot { void *handler_priv; }; -/** - * mmc_context_info - synchronization details for mmc context - * @is_done_rcv wake up reason was done request - * @is_new_req wake up reason was new request - * @is_waiting_last_req mmc context waiting for single running request - * @wait wait queue - */ -struct mmc_context_info { - bool is_done_rcv; - bool is_new_req; - bool is_waiting_last_req; - wait_queue_head_t wait; -}; - struct regulator; struct mmc_pwrseq; struct mmc_supply { struct regulator *vmmc; /* Card power supply */ struct regulator *vqmmc; /* Optional Vccq supply */ + struct regulator *vqmmc2; /* Optional supply for phy */ }; struct mmc_ctx { @@ -402,6 +433,7 @@ struct mmc_host { MMC_CAP2_HS200_1_2V_SDR) #define MMC_CAP2_SD_EXP (1 << 7) /* SD express via PCIe */ #define MMC_CAP2_SD_EXP_1_2V (1 << 8) /* SD express 1.2V */ +#define MMC_CAP2_SD_UHS2 (1 << 9) /* SD UHS-II support */ #define MMC_CAP2_CD_ACTIVE_HIGH (1 << 10) /* Card-detect signal active high */ #define MMC_CAP2_RO_ACTIVE_HIGH (1 << 11) /* Write-protect signal active high */ #define MMC_CAP2_NO_PRESCAN_POWERUP (1 << 14) /* Don't power up before scan */ @@ -428,13 +460,17 @@ struct mmc_host { #endif #define MMC_CAP2_ALT_GPT_TEGRA (1 << 28) /* Host with eMMC that has GPT entry at a non-standard location */ + bool uhs2_sd_tran; /* UHS-II flag for SD_TRAN state */ + bool uhs2_app_cmd; /* UHS-II flag for APP command */ + struct sd_uhs2_caps uhs2_caps; /* Host UHS-II capabilities */ + int fixed_drv_type; /* fixed driver type for non-removable media */ mmc_pm_flag_t pm_caps; /* supported pm features */ /* host specific block data */ - unsigned int max_seg_size; /* see blk_queue_max_segment_size */ - unsigned short max_segs; /* see blk_queue_max_segments */ + unsigned int max_seg_size; /* lim->max_segment_size */ + unsigned short max_segs; /* lim->max_segments */ unsigned short unused; unsigned int max_req_size; /* maximum number of bytes in one req */ unsigned int max_blk_size; /* maximum size of one mmc block */ @@ -554,6 +590,14 @@ static inline struct mmc_host *mmc_from_priv(void *priv) return container_of(priv, struct mmc_host, private); } +#ifdef CONFIG_MMC_CRYPTO +static inline struct mmc_host * +mmc_from_crypto_profile(struct blk_crypto_profile *profile) +{ + return container_of(profile, struct mmc_host, crypto_profile); +} +#endif + #define mmc_host_is_spi(host) ((host)->caps & MMC_CAP_SPI) #define mmc_dev(x) ((x)->parent) @@ -590,6 +634,7 @@ int mmc_regulator_set_ocr(struct mmc_host *mmc, struct regulator *supply, unsigned short vdd_bit); int mmc_regulator_set_vqmmc(struct mmc_host *mmc, struct mmc_ios *ios); +int mmc_regulator_set_vqmmc2(struct mmc_host *mmc, struct mmc_ios *ios); #else static inline int mmc_regulator_set_ocr(struct mmc_host *mmc, struct regulator *supply, @@ -603,6 +648,12 @@ static inline int mmc_regulator_set_vqmmc(struct mmc_host *mmc, { return -EINVAL; } + +static inline int mmc_regulator_set_vqmmc2(struct mmc_host *mmc, + struct mmc_ios *ios) +{ + return -EINVAL; +} #endif int mmc_regulator_get_supply(struct mmc_host *mmc); @@ -638,6 +689,14 @@ static inline int mmc_card_uhs(struct mmc_card *card) card->host->ios.timing <= MMC_TIMING_UHS_DDR50; } +static inline bool mmc_card_uhs2(struct mmc_host *host) +{ + return host->ios.timing == MMC_TIMING_UHS2_SPEED_A || + host->ios.timing == MMC_TIMING_UHS2_SPEED_A_HD || + host->ios.timing == MMC_TIMING_UHS2_SPEED_B || + host->ios.timing == MMC_TIMING_UHS2_SPEED_B_HD; +} + void mmc_retune_timer_stop(struct mmc_host *host); static inline void mmc_retune_needed(struct mmc_host *host) @@ -672,7 +731,14 @@ static inline void mmc_debugfs_err_stats_inc(struct mmc_host *host, host->err_stats[stat] += 1; } -int mmc_sd_switch(struct mmc_card *card, int mode, int group, u8 value, u8 *resp); +static inline int mmc_card_uhs2_hd_mode(struct mmc_host *host) +{ + return host->ios.timing == MMC_TIMING_UHS2_SPEED_A_HD || + host->ios.timing == MMC_TIMING_UHS2_SPEED_B_HD; +} + +int mmc_sd_switch(struct mmc_card *card, bool mode, int group, + u8 value, u8 *resp); int mmc_send_status(struct mmc_card *card, u32 *status); int mmc_send_tuning(struct mmc_host *host, u32 opcode, int *cmd_error); int mmc_send_abort_tuning(struct mmc_host *host, u32 opcode); diff --git a/include/linux/mmc/sd.h b/include/linux/mmc/sd.h index 6727576a8755..af5fc70e09a2 100644 --- a/include/linux/mmc/sd.h +++ b/include/linux/mmc/sd.h @@ -15,6 +15,9 @@ #define SD_SEND_IF_COND 8 /* bcr [11:0] See below R7 */ #define SD_SWITCH_VOLTAGE 11 /* ac R1 */ +/* Class 2 */ +#define SD_ADDR_EXT 22 /* ac [5:0] R1 */ + /* class 10 */ #define SD_SWITCH 6 /* adtc [31:0] See below R1 */ @@ -36,6 +39,7 @@ /* OCR bit definitions */ #define SD_OCR_S18R (1 << 24) /* 1.8V switching request */ #define SD_ROCR_S18A SD_OCR_S18R /* 1.8V switching accepted by card */ +#define SD_OCR_2T (1 << 27) /* HO2T/CO2T - SDUC support */ #define SD_OCR_XPC (1 << 28) /* SDXC power control */ #define SD_OCR_CCS (1 << 30) /* Card Capacity Status */ diff --git a/include/linux/mmc/sd_uhs2.h b/include/linux/mmc/sd_uhs2.h new file mode 100644 index 000000000000..7abe9bd870c7 --- /dev/null +++ b/include/linux/mmc/sd_uhs2.h @@ -0,0 +1,240 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Header file for UHS-II packets, Host Controller registers and I/O + * accessors. + * + * Copyright (C) 2014 Intel Corp, All Rights Reserved. + */ +#ifndef LINUX_MMC_UHS2_H +#define LINUX_MMC_UHS2_H + +/* LINK Layer definition */ +/* + * UHS2 Header: + * Refer to UHS-II Addendum Version 1.02 Figure 5-2, the format of CCMD Header is described below: + * bit [3:0] : DID(Destination ID = Node ID of UHS2 card) + * bit [6:4] : TYP(Packet Type) + * 000b: CCMD(Control command packet) + * 001b: DCMD(Data command packet) + * 010b: RES(Response packet) + * 011b: DATA(Data payload packet) + * 111b: MSG(Message packet) + * Others: Reserved + * bit [7] : NP(Native Packet) + * bit [10:8] : TID(Transaction ID) + * bit [11] : Reserved + * bit [15:12]: SID(Source ID 0: Node ID of Host) + * + * Broadcast CCMD issued by Host is represented as DID=SID=0. + */ +/* + * UHS2 Argument: + * Refer to UHS-II Addendum Version 1.02 Figure 6-5, the format of CCMD Argument is described below: + * bit [3:0] : MSB of IOADR + * bit [5:4] : PLEN(Payload Length) + * 00b: 0 byte + * 01b: 4 bytes + * 10b: 8 bytes + * 11b: 16 bytes + * bit [6] : Reserved + * bit [7] : R/W(Read/Write) + * 0: Control read command + * 1: Control write command + * bit [15:8] : LSB of IOADR + * + * I/O Address specifies the address of register in UHS-II I/O space accessed by CCMD. + * The unit of I/O Address is 4 Bytes. It is transmitted in MSB first, LSB last. + */ +#define UHS2_NATIVE_PACKET_POS 7 +#define UHS2_NATIVE_PACKET (1 << UHS2_NATIVE_PACKET_POS) + +#define UHS2_PACKET_TYPE_POS 4 +#define UHS2_PACKET_TYPE_CCMD (0 << UHS2_PACKET_TYPE_POS) +#define UHS2_PACKET_TYPE_DCMD (1 << UHS2_PACKET_TYPE_POS) +#define UHS2_PACKET_TYPE_RES (2 << UHS2_PACKET_TYPE_POS) +#define UHS2_PACKET_TYPE_DATA (3 << UHS2_PACKET_TYPE_POS) +#define UHS2_PACKET_TYPE_MSG (7 << UHS2_PACKET_TYPE_POS) + +#define UHS2_DEST_ID_MASK 0x0F +#define UHS2_DEST_ID 0x1 + +#define UHS2_SRC_ID_POS 12 +#define UHS2_SRC_ID_MASK 0xF000 + +#define UHS2_TRANS_ID_POS 8 +#define UHS2_TRANS_ID_MASK 0x0700 + +/* UHS2 MSG */ +#define UHS2_MSG_CTG_POS 5 +#define UHS2_MSG_CTG_LMSG 0x00 +#define UHS2_MSG_CTG_INT 0x60 +#define UHS2_MSG_CTG_AMSG 0x80 + +#define UHS2_MSG_CTG_FCREQ 0x00 +#define UHS2_MSG_CTG_FCRDY 0x01 +#define UHS2_MSG_CTG_STAT 0x02 + +#define UHS2_MSG_CODE_POS 8 +#define UHS2_MSG_CODE_FC_UNRECOVER_ERR 0x8 +#define UHS2_MSG_CODE_STAT_UNRECOVER_ERR 0x8 +#define UHS2_MSG_CODE_STAT_RECOVER_ERR 0x1 + +/* TRANS Layer definition */ + +/* Native packets*/ +#define UHS2_NATIVE_CMD_RW_POS 7 +#define UHS2_NATIVE_CMD_WRITE (1 << UHS2_NATIVE_CMD_RW_POS) +#define UHS2_NATIVE_CMD_READ (0 << UHS2_NATIVE_CMD_RW_POS) + +#define UHS2_NATIVE_CMD_PLEN_POS 4 +#define UHS2_NATIVE_CMD_PLEN_4B (1 << UHS2_NATIVE_CMD_PLEN_POS) +#define UHS2_NATIVE_CMD_PLEN_8B (2 << UHS2_NATIVE_CMD_PLEN_POS) +#define UHS2_NATIVE_CMD_PLEN_16B (3 << UHS2_NATIVE_CMD_PLEN_POS) + +#define UHS2_NATIVE_CCMD_GET_MIOADR_MASK 0xF00 +#define UHS2_NATIVE_CCMD_MIOADR_MASK 0x0F + +#define UHS2_NATIVE_CCMD_LIOADR_POS 8 +#define UHS2_NATIVE_CCMD_GET_LIOADR_MASK 0x0FF + +#define UHS2_CCMD_DEV_INIT_COMPLETE_FLAG BIT(11) +#define UHS2_DEV_INIT_PAYLOAD_LEN 1 +#define UHS2_DEV_INIT_RESP_LEN 6 +#define UHS2_DEV_ENUM_PAYLOAD_LEN 1 +#define UHS2_DEV_ENUM_RESP_LEN 8 +#define UHS2_CFG_WRITE_PAYLOAD_LEN 2 +#define UHS2_CFG_WRITE_PHY_SET_RESP_LEN 4 +#define UHS2_CFG_WRITE_GENERIC_SET_RESP_LEN 5 +#define UHS2_GO_DORMANT_PAYLOAD_LEN 1 + +/* + * UHS2 Argument: + * Refer to UHS-II Addendum Version 1.02 Figure 6-8, the format of DCMD Argument is described below: + * bit [3:0] : Reserved + * bit [6:3] : TMODE(Transfer Mode) + * bit 3: DAM(Data Access Mode) + * bit 4: TLUM(TLEN Unit Mode) + * bit 5: LM(Length Mode) + * bit 6: DM(Duplex Mode) + * bit [7] : R/W(Read/Write) + * 0: Control read command + * 1: Control write command + * bit [15:8] : Reserved + * + * I/O Address specifies the address of register in UHS-II I/O space accessed by CCMD. + * The unit of I/O Address is 4 Bytes. It is transmitted in MSB first, LSB last. + */ +#define UHS2_DCMD_DM_POS 6 +#define UHS2_DCMD_2L_HD_MODE (1 << UHS2_DCMD_DM_POS) +#define UHS2_DCMD_LM_POS 5 +#define UHS2_DCMD_LM_TLEN_EXIST (1 << UHS2_DCMD_LM_POS) +#define UHS2_DCMD_TLUM_POS 4 +#define UHS2_DCMD_TLUM_BYTE_MODE (1 << UHS2_DCMD_TLUM_POS) +#define UHS2_NATIVE_DCMD_DAM_POS 3 +#define UHS2_NATIVE_DCMD_DAM_IO (1 << UHS2_NATIVE_DCMD_DAM_POS) + +#define UHS2_RES_NACK_POS 7 +#define UHS2_RES_NACK_MASK (0x1 << UHS2_RES_NACK_POS) + +#define UHS2_RES_ECODE_POS 4 +#define UHS2_RES_ECODE_MASK 0x7 +#define UHS2_RES_ECODE_COND 1 +#define UHS2_RES_ECODE_ARG 2 +#define UHS2_RES_ECODE_GEN 3 + +/* IOADR of device registers */ +#define UHS2_IOADR_GENERIC_CAPS 0x00 +#define UHS2_IOADR_PHY_CAPS 0x02 +#define UHS2_IOADR_LINK_CAPS 0x04 +#define UHS2_IOADR_RSV_CAPS 0x06 +#define UHS2_IOADR_GENERIC_SETTINGS 0x08 +#define UHS2_IOADR_PHY_SETTINGS 0x0A +#define UHS2_IOADR_LINK_SETTINGS 0x0C +#define UHS2_IOADR_PRESET 0x40 + +/* SD application packets */ +#define UHS2_SD_CMD_INDEX_POS 8 + +#define UHS2_SD_CMD_APP_POS 14 +#define UHS2_SD_CMD_APP (1 << UHS2_SD_CMD_APP_POS) + +/* UHS-II Device Registers */ +#define UHS2_DEV_CONFIG_REG 0x000 + +/* General Caps and Settings registers */ +#define UHS2_DEV_CONFIG_GEN_CAPS (UHS2_DEV_CONFIG_REG + 0x000) +#define UHS2_DEV_CONFIG_N_LANES_POS 8 +#define UHS2_DEV_CONFIG_N_LANES_MASK 0x3F +#define UHS2_DEV_CONFIG_2L_HD_FD 0x1 +#define UHS2_DEV_CONFIG_2D1U_FD 0x2 +#define UHS2_DEV_CONFIG_1D2U_FD 0x4 +#define UHS2_DEV_CONFIG_2D2U_FD 0x8 +#define UHS2_DEV_CONFIG_DADR_POS 14 +#define UHS2_DEV_CONFIG_DADR_MASK 0x1 +#define UHS2_DEV_CONFIG_APP_POS 16 +#define UHS2_DEV_CONFIG_APP_MASK 0xFF +#define UHS2_DEV_CONFIG_APP_SD_MEM 0x1 + +#define UHS2_DEV_CONFIG_GEN_SET (UHS2_DEV_CONFIG_REG + 0x008) +#define UHS2_DEV_CONFIG_GEN_SET_N_LANES_POS 8 +#define UHS2_DEV_CONFIG_GEN_SET_2L_FD_HD 0x0 +#define UHS2_DEV_CONFIG_GEN_SET_2D1U_FD 0x2 +#define UHS2_DEV_CONFIG_GEN_SET_1D2U_FD 0x3 +#define UHS2_DEV_CONFIG_GEN_SET_2D2U_FD 0x4 +#define UHS2_DEV_CONFIG_GEN_SET_CFG_COMPLETE BIT(31) + +/* PHY Caps and Settings registers */ +#define UHS2_DEV_CONFIG_PHY_CAPS (UHS2_DEV_CONFIG_REG + 0x002) +#define UHS2_DEV_CONFIG_PHY_MINOR_MASK 0xF +#define UHS2_DEV_CONFIG_PHY_MAJOR_POS 4 +#define UHS2_DEV_CONFIG_PHY_MAJOR_MASK 0x3 +#define UHS2_DEV_CONFIG_CAN_HIBER_POS 15 +#define UHS2_DEV_CONFIG_CAN_HIBER_MASK 0x1 +#define UHS2_DEV_CONFIG_PHY_CAPS1 (UHS2_DEV_CONFIG_REG + 0x003) +#define UHS2_DEV_CONFIG_N_LSS_SYN_MASK 0xF +#define UHS2_DEV_CONFIG_N_LSS_DIR_POS 4 +#define UHS2_DEV_CONFIG_N_LSS_DIR_MASK 0xF + +#define UHS2_DEV_CONFIG_PHY_SET (UHS2_DEV_CONFIG_REG + 0x00A) +#define UHS2_DEV_CONFIG_PHY_SET_SPEED_POS 6 +#define UHS2_DEV_CONFIG_PHY_SET_SPEED_A 0x0 +#define UHS2_DEV_CONFIG_PHY_SET_SPEED_B 0x1 + +/* LINK-TRAN Caps and Settings registers */ +#define UHS2_DEV_CONFIG_LINK_TRAN_CAPS (UHS2_DEV_CONFIG_REG + 0x004) +#define UHS2_DEV_CONFIG_LT_MINOR_MASK 0xF +#define UHS2_DEV_CONFIG_LT_MAJOR_POS 4 +#define UHS2_DEV_CONFIG_LT_MAJOR_MASK 0x3 +#define UHS2_DEV_CONFIG_N_FCU_POS 8 +#define UHS2_DEV_CONFIG_N_FCU_MASK 0xFF +#define UHS2_DEV_CONFIG_DEV_TYPE_POS 16 +#define UHS2_DEV_CONFIG_DEV_TYPE_MASK 0x7 +#define UHS2_DEV_CONFIG_MAX_BLK_LEN_POS 20 +#define UHS2_DEV_CONFIG_MAX_BLK_LEN_MASK 0xFFF +#define UHS2_DEV_CONFIG_LINK_TRAN_CAPS1 (UHS2_DEV_CONFIG_REG + 0x005) +#define UHS2_DEV_CONFIG_N_DATA_GAP_MASK 0xFF + +#define UHS2_DEV_CONFIG_LINK_TRAN_SET (UHS2_DEV_CONFIG_REG + 0x00C) +#define UHS2_DEV_CONFIG_LT_SET_MAX_BLK_LEN 0x200 +#define UHS2_DEV_CONFIG_LT_SET_MAX_RETRY_POS 16 + +/* Preset register */ +#define UHS2_DEV_CONFIG_PRESET (UHS2_DEV_CONFIG_REG + 0x040) + +#define UHS2_DEV_INT_REG 0x100 + +#define UHS2_DEV_STATUS_REG 0x180 + +#define UHS2_DEV_CMD_REG 0x200 +#define UHS2_DEV_CMD_FULL_RESET (UHS2_DEV_CMD_REG + 0x000) +#define UHS2_DEV_CMD_GO_DORMANT_STATE (UHS2_DEV_CMD_REG + 0x001) +#define UHS2_DEV_CMD_DORMANT_HIBER BIT(7) +#define UHS2_DEV_CMD_DEVICE_INIT (UHS2_DEV_CMD_REG + 0x002) +#define UHS2_DEV_INIT_COMPLETE_FLAG BIT(11) +#define UHS2_DEV_CMD_ENUMERATE (UHS2_DEV_CMD_REG + 0x003) +#define UHS2_DEV_CMD_TRANS_ABORT (UHS2_DEV_CMD_REG + 0x004) + +#define UHS2_RCLK_MAX 52000000 +#define UHS2_RCLK_MIN 26000000 + +#endif /* LINUX_MMC_UHS2_H */ diff --git a/include/linux/mmc/sdio_func.h b/include/linux/mmc/sdio_func.h index 478855b8e406..fed1f5f4a8d3 100644 --- a/include/linux/mmc/sdio_func.h +++ b/include/linux/mmc/sdio_func.h @@ -106,7 +106,10 @@ struct sdio_driver { .class = (dev_class), \ .vendor = SDIO_ANY_ID, .device = SDIO_ANY_ID -extern int sdio_register_driver(struct sdio_driver *); +/* use a macro to avoid include chaining to get THIS_MODULE */ +#define sdio_register_driver(drv) \ + __sdio_register_driver(drv, THIS_MODULE) +extern int __sdio_register_driver(struct sdio_driver *, struct module *); extern void sdio_unregister_driver(struct sdio_driver *); /** diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index 7fada7a714fe..7cddfdac2f57 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -124,6 +124,7 @@ #define SDIO_DEVICE_ID_REALTEK_RTW8723DS_2ANT 0xd723 #define SDIO_DEVICE_ID_REALTEK_RTW8723DS_1ANT 0xd724 #define SDIO_DEVICE_ID_REALTEK_RTW8821DS 0xd821 +#define SDIO_DEVICE_ID_REALTEK_RTW8723CS 0xb703 #define SDIO_VENDOR_ID_SIANO 0x039a #define SDIO_DEVICE_ID_SIANO_NOVA_B0 0x0201 diff --git a/include/linux/mmc/slot-gpio.h b/include/linux/mmc/slot-gpio.h index 5d3d15e97868..274a2767ea49 100644 --- a/include/linux/mmc/slot-gpio.h +++ b/include/linux/mmc/slot-gpio.h @@ -8,8 +8,8 @@ #ifndef MMC_SLOT_GPIO_H #define MMC_SLOT_GPIO_H +#include <linux/interrupt.h> #include <linux/types.h> -#include <linux/irqreturn.h> struct mmc_host; @@ -21,8 +21,8 @@ int mmc_gpiod_request_cd(struct mmc_host *host, const char *con_id, unsigned int debounce); int mmc_gpiod_request_ro(struct mmc_host *host, const char *con_id, unsigned int idx, unsigned int debounce); -void mmc_gpio_set_cd_isr(struct mmc_host *host, - irqreturn_t (*isr)(int irq, void *dev_id)); +int mmc_gpiod_set_cd_config(struct mmc_host *host, unsigned long config); +void mmc_gpio_set_cd_isr(struct mmc_host *host, irq_handler_t isr); int mmc_gpio_set_cd_wake(struct mmc_host *host, bool on); void mmc_gpiod_request_cd_irq(struct mmc_host *host); bool mmc_can_gpio_cd(struct mmc_host *host); diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h index 39a7714605a7..a0a3894900ed 100644 --- a/include/linux/mmdebug.h +++ b/include/linux/mmdebug.h @@ -9,10 +9,12 @@ struct page; struct vm_area_struct; struct mm_struct; struct vma_iterator; +struct vma_merge_struct; void dump_page(const struct page *page, const char *reason); void dump_vma(const struct vm_area_struct *vma); void dump_mm(const struct mm_struct *mm); +void dump_vmg(const struct vma_merge_struct *vmg, const char *reason); void vma_iter_dump_tree(const struct vma_iterator *vmi); #ifdef CONFIG_DEBUG_VM @@ -46,7 +48,7 @@ void vma_iter_dump_tree(const struct vma_iterator *vmi); } \ } while (0) #define VM_WARN_ON_ONCE_PAGE(cond, page) ({ \ - static bool __section(".data.once") __warned; \ + static bool __section(".data..once") __warned; \ int __ret_warn_once = !!(cond); \ \ if (unlikely(__ret_warn_once && !__warned)) { \ @@ -66,7 +68,7 @@ void vma_iter_dump_tree(const struct vma_iterator *vmi); unlikely(__ret_warn); \ }) #define VM_WARN_ON_ONCE_FOLIO(cond, folio) ({ \ - static bool __section(".data.once") __warned; \ + static bool __section(".data..once") __warned; \ int __ret_warn_once = !!(cond); \ \ if (unlikely(__ret_warn_once && !__warned)) { \ @@ -77,7 +79,7 @@ void vma_iter_dump_tree(const struct vma_iterator *vmi); unlikely(__ret_warn_once); \ }) #define VM_WARN_ON_ONCE_MM(cond, mm) ({ \ - static bool __section(".data.once") __warned; \ + static bool __section(".data..once") __warned; \ int __ret_warn_once = !!(cond); \ \ if (unlikely(__ret_warn_once && !__warned)) { \ @@ -87,6 +89,15 @@ void vma_iter_dump_tree(const struct vma_iterator *vmi); } \ unlikely(__ret_warn_once); \ }) +#define VM_WARN_ON_VMG(cond, vmg) ({ \ + int __ret_warn = !!(cond); \ + \ + if (unlikely(__ret_warn)) { \ + dump_vmg(vmg, "VM_WARN_ON_VMG(" __stringify(cond)")"); \ + WARN_ON(1); \ + } \ + unlikely(__ret_warn); \ +}) #define VM_WARN_ON(cond) (void)WARN_ON(cond) #define VM_WARN_ON_ONCE(cond) (void)WARN_ON_ONCE(cond) @@ -104,9 +115,10 @@ void vma_iter_dump_tree(const struct vma_iterator *vmi); #define VM_WARN_ON_FOLIO(cond, folio) BUILD_BUG_ON_INVALID(cond) #define VM_WARN_ON_ONCE_FOLIO(cond, folio) BUILD_BUG_ON_INVALID(cond) #define VM_WARN_ON_ONCE_MM(cond, mm) BUILD_BUG_ON_INVALID(cond) +#define VM_WARN_ON_VMG(cond, vmg) BUILD_BUG_ON_INVALID(cond) #define VM_WARN_ONCE(cond, format...) BUILD_BUG_ON_INVALID(cond) #define VM_WARN(cond, format...) BUILD_BUG_ON_INVALID(cond) -#endif +#endif /* CONFIG_DEBUG_VM */ #ifdef CONFIG_DEBUG_VM_IRQSOFF #define VM_WARN_ON_IRQS_ENABLED() WARN_ON_ONCE(!irqs_disabled()) diff --git a/include/linux/mmu_context.h b/include/linux/mmu_context.h index bbaec80c78c5..ac01dc4eb2ce 100644 --- a/include/linux/mmu_context.h +++ b/include/linux/mmu_context.h @@ -24,6 +24,7 @@ static inline void leave_mm(void) { } #ifndef task_cpu_possible_mask # define task_cpu_possible_mask(p) cpu_possible_mask # define task_cpu_possible(cpu, p) true +# define task_cpu_fallback_mask(p) housekeeping_cpumask(HK_TYPE_TICK) #else # define task_cpu_possible(cpu, p) cpumask_test_cpu((cpu), task_cpu_possible_mask(p)) #endif diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index f349e08a9dfe..e2dd57ca368b 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -123,15 +123,6 @@ struct mmu_notifier_ops { unsigned long address); /* - * change_pte is called in cases that pte mapping to page is changed: - * for example, when ksm remaps pte to point to a new shared page. - */ - void (*change_pte)(struct mmu_notifier *subscription, - struct mm_struct *mm, - unsigned long address, - pte_t pte); - - /* * invalidate_range_start() and invalidate_range_end() must be * paired and are called only when the mmap_lock and/or the * locks protecting the reverse maps are held. If the subsystem @@ -392,8 +383,6 @@ extern int __mmu_notifier_clear_young(struct mm_struct *mm, unsigned long end); extern int __mmu_notifier_test_young(struct mm_struct *mm, unsigned long address); -extern void __mmu_notifier_change_pte(struct mm_struct *mm, - unsigned long address, pte_t pte); extern int __mmu_notifier_invalidate_range_start(struct mmu_notifier_range *r); extern void __mmu_notifier_invalidate_range_end(struct mmu_notifier_range *r); extern void __mmu_notifier_arch_invalidate_secondary_tlbs(struct mm_struct *mm, @@ -439,13 +428,6 @@ static inline int mmu_notifier_test_young(struct mm_struct *mm, return 0; } -static inline void mmu_notifier_change_pte(struct mm_struct *mm, - unsigned long address, pte_t pte) -{ - if (mm_has_notifiers(mm)) - __mmu_notifier_change_pte(mm, address, pte); -} - static inline void mmu_notifier_invalidate_range_start(struct mmu_notifier_range *range) { @@ -581,26 +563,6 @@ static inline void mmu_notifier_range_init_owner( __young; \ }) -/* - * set_pte_at_notify() sets the pte _after_ running the notifier. - * This is safe to start by updating the secondary MMUs, because the primary MMU - * pte invalidate must have already happened with a ptep_clear_flush() before - * set_pte_at_notify() has been invoked. Updating the secondary MMUs first is - * required when we change both the protection of the mapping from read-only to - * read-write and the pfn (like during copy on write page faults). Otherwise the - * old page would remain mapped readonly in the secondary MMUs after the new - * page is already writable by some CPU through the primary MMU. - */ -#define set_pte_at_notify(__mm, __address, __ptep, __pte) \ -({ \ - struct mm_struct *___mm = __mm; \ - unsigned long ___address = __address; \ - pte_t ___pte = __pte; \ - \ - mmu_notifier_change_pte(___mm, ___address, ___pte); \ - set_pte_at(___mm, ___address, __ptep, ___pte); \ -}) - #else /* CONFIG_MMU_NOTIFIER */ struct mmu_notifier_range { @@ -644,15 +606,17 @@ static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm, return 0; } -static inline int mmu_notifier_test_young(struct mm_struct *mm, - unsigned long address) +static inline int mmu_notifier_clear_young(struct mm_struct *mm, + unsigned long start, + unsigned long end) { return 0; } -static inline void mmu_notifier_change_pte(struct mm_struct *mm, - unsigned long address, pte_t pte) +static inline int mmu_notifier_test_young(struct mm_struct *mm, + unsigned long address) { + return 0; } static inline void @@ -693,7 +657,6 @@ static inline void mmu_notifier_subscriptions_destroy(struct mm_struct *mm) #define ptep_clear_flush_notify ptep_clear_flush #define pmdp_huge_clear_flush_notify pmdp_huge_clear_flush #define pudp_huge_clear_flush_notify pudp_huge_clear_flush -#define set_pte_at_notify set_pte_at static inline void mmu_notifier_synchronize(void) { diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index c11b7cde81ef..9540b41894da 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -205,7 +205,10 @@ enum node_stat_item { NR_KERNEL_SCS_KB, /* measured in KiB */ #endif NR_PAGETABLE, /* used for pagetables */ - NR_SECONDARY_PAGETABLE, /* secondary pagetables, e.g. KVM pagetables */ + NR_SECONDARY_PAGETABLE, /* secondary pagetables, KVM & IOMMU */ +#ifdef CONFIG_IOMMU_SUPPORT + NR_IOMMU_PAGES, /* # of pages allocated by IOMMU */ +#endif #ifdef CONFIG_SWAP NR_SWAPCACHE, #endif @@ -217,6 +220,9 @@ enum node_stat_item { PGDEMOTE_KSWAPD, PGDEMOTE_DIRECT, PGDEMOTE_KHUGEPAGED, +#ifdef CONFIG_HUGETLB_PAGE + NR_HUGETLB, +#endif NR_VM_NODE_STAT_ITEMS }; @@ -326,66 +332,88 @@ enum lruvec_flags { #endif /* !__GENERATING_BOUNDS_H */ /* - * Evictable pages are divided into multiple generations. The youngest and the + * Evictable folios are divided into multiple generations. The youngest and the * oldest generation numbers, max_seq and min_seq, are monotonically increasing. * 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->folios[]. Otherwise it stores 0. + * a folio 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 - * eviction. The first check takes care of the accessed bit set on the initial - * fault; the second check makes sure this page hasn't been used since then. - * This process, AKA second chance, requires a minimum of two generations, - * hence MIN_NR_GENS. And to maintain ABI compatibility with the active/inactive - * LRU, e.g., /proc/vmstat, these two generations are considered active; the - * rest of generations, if they exist, are considered inactive. See - * lru_gen_is_active(). + * After a folio is faulted in, the aging needs to check the accessed bit at + * least twice before handing this folio over to the eviction. The first check + * clears the accessed bit from the initial fault; the second check makes sure + * this folio hasn't been used since then. This process, AKA second chance, + * requires a minimum of two generations, hence MIN_NR_GENS. And to maintain ABI + * compatibility with the active/inactive LRU, e.g., /proc/vmstat, these two + * generations are considered active; the 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->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(). + * PG_active is always cleared while a folio is on one of lrugen->folios[] so + * that the sliding window needs not to worry about it. And it's set again when + * a folio considered active is isolated for non-reclaiming purposes, e.g., + * migration. See lru_gen_add_folio() and lru_gen_del_folio(). * * MAX_NR_GENS is set to 4 so that the multi-gen LRU can support twice the * number of categories of the active/inactive LRU when keeping track of * accesses through page tables. This requires order_base_2(MAX_NR_GENS+1) bits - * in folio->flags. + * in folio->flags, masked by LRU_GEN_MASK. */ #define MIN_NR_GENS 2U #define MAX_NR_GENS 4U /* - * Each generation is divided into multiple tiers. A page accessed N times - * through file descriptors is in tier order_base_2(N). A page in the first tier - * (N=0,1) is marked by PG_referenced unless it was faulted in through page - * tables or read ahead. A page in any other tier (N>1) is marked by - * PG_referenced and PG_workingset. This implies a minimum of two tiers is - * supported without using additional bits in folio->flags. + * Each generation is divided into multiple tiers. A folio accessed N times + * through file descriptors is in tier order_base_2(N). A folio in the first + * tier (N=0,1) is marked by PG_referenced unless it was faulted in through page + * tables or read ahead. A folio in the last tier (MAX_NR_TIERS-1) is marked by + * PG_workingset. A folio in any other tier (1<N<5) between the first and last + * is marked by additional bits of LRU_REFS_WIDTH in folio->flags. * * 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 in the buffered access path. In the eviction path, - * comparisons of refaulted/(evicted+protected) from the first tier and the - * rest infer whether pages accessed multiple times through file descriptors - * are statistically hot and thus worth protecting. + * comparisons of refaulted/(evicted+protected) from the first tier and the rest + * infer whether folios accessed multiple times through file descriptors are + * statistically hot and thus worth protecting. * * MAX_NR_TIERS is set to 4 so that the multi-gen LRU can support twice the * number of categories of the active/inactive LRU when keeping track of * accesses through file descriptors. This uses MAX_NR_TIERS-2 spare bits in - * folio->flags. + * folio->flags, masked by LRU_REFS_MASK. */ #define MAX_NR_TIERS 4U #ifndef __GENERATING_BOUNDS_H -struct lruvec; -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) +/* + * For folios accessed multiple times through file descriptors, + * lru_gen_inc_refs() sets additional bits of LRU_REFS_WIDTH in folio->flags + * after PG_referenced, then PG_workingset after LRU_REFS_WIDTH. After all its + * bits are set, i.e., LRU_REFS_FLAGS|BIT(PG_workingset), a folio is lazily + * promoted into the second oldest generation in the eviction path. And when + * folio_inc_gen() does that, it clears LRU_REFS_FLAGS so that + * lru_gen_inc_refs() can start over. Note that for this case, LRU_REFS_MASK is + * only valid when PG_referenced is set. + * + * For folios accessed multiple times through page tables, folio_update_gen() + * from a page table walk or lru_gen_set_refs() from a rmap walk sets + * PG_referenced after the accessed bit is cleared for the first time. + * Thereafter, those two paths set PG_workingset and promote folios to the + * youngest generation. Like folio_inc_gen(), folio_update_gen() also clears + * PG_referenced. Note that for this case, LRU_REFS_MASK is not used. + * + * For both cases above, after PG_workingset is set on a folio, it remains until + * this folio is either reclaimed, or "deactivated" by lru_gen_clear_refs(). It + * can be set again if lru_gen_test_recent() returns true upon a refault. + */ +#define LRU_REFS_FLAGS (LRU_REFS_MASK | BIT(PG_referenced)) + +struct lruvec; +struct page_vma_mapped_walk; + #ifdef CONFIG_LRU_GEN enum { @@ -413,12 +441,11 @@ enum { /* * The youngest generation number is stored in max_seq for both anon and file * types as they are aged on an equal footing. The oldest generation numbers are - * stored in min_seq[] separately for anon and file types as clean file pages - * can be evicted regardless of swap constraints. - * - * Normally anon and file min_seq are in sync. But if swapping is constrained, - * e.g., out of swap space, file min_seq is allowed to advance and leave anon - * min_seq behind. + * stored in min_seq[] separately for anon and file types so that they can be + * incremented independently. Ideally min_seq[] are kept in sync when both anon + * and file types are evictable. However, to adapt to situations like extreme + * swappiness, they are allowed to be out of sync by at most + * MAX_NR_GENS-MIN_NR_GENS-1. * * The number of pages in each generation is eventually consistent and therefore * can be transiently negative when reset_batch_size() is pending. @@ -438,8 +465,8 @@ struct lru_gen_folio { unsigned long avg_refaulted[ANON_AND_FILE][MAX_NR_TIERS]; /* the exponential moving average of evicted+protected */ unsigned long avg_total[ANON_AND_FILE][MAX_NR_TIERS]; - /* the first tier doesn't need protection, hence the minus one */ - unsigned long protected[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS - 1]; + /* can only be modified under the LRU lock */ + unsigned long protected[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS]; /* can be modified without holding the LRU lock */ atomic_long_t evicted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS]; atomic_long_t refaulted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS]; @@ -455,9 +482,7 @@ struct lru_gen_folio { enum { MM_LEAF_TOTAL, /* total leaf entries */ - MM_LEAF_OLD, /* old leaf entries */ MM_LEAF_YOUNG, /* young leaf entries */ - MM_NONLEAF_TOTAL, /* total non-leaf entries */ MM_NONLEAF_FOUND, /* non-leaf entries found in Bloom filters */ MM_NONLEAF_ADDED, /* non-leaf entries added to Bloom filters */ NR_MM_STATS @@ -492,7 +517,7 @@ struct lru_gen_mm_walk { int mm_stats[NR_MM_STATS]; /* total batched items */ int batched; - bool can_swap; + int swappiness; bool force_scan; }; @@ -554,7 +579,7 @@ struct lru_gen_memcg { void lru_gen_init_pgdat(struct pglist_data *pgdat); void lru_gen_init_lruvec(struct lruvec *lruvec); -void lru_gen_look_around(struct page_vma_mapped_walk *pvmw); +bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw); void lru_gen_init_memcg(struct mem_cgroup *memcg); void lru_gen_exit_memcg(struct mem_cgroup *memcg); @@ -573,8 +598,9 @@ static inline void lru_gen_init_lruvec(struct lruvec *lruvec) { } -static inline void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) +static inline bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw) { + return false; } static inline void lru_gen_init_memcg(struct mem_cgroup *memcg) @@ -651,24 +677,18 @@ enum zone_watermarks { }; /* - * One per migratetype for each PAGE_ALLOC_COSTLY_ORDER. One additional list - * for THP which will usually be GFP_MOVABLE. Even if it is another type, - * it should not contribute to serious fragmentation causing THP allocation - * failures. + * One per migratetype for each PAGE_ALLOC_COSTLY_ORDER. Two additional lists + * are added for THP. One PCP list is used by GPF_MOVABLE, and the other PCP list + * is used by GFP_UNMOVABLE and GFP_RECLAIMABLE. */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE -#define NR_PCP_THP 1 +#define NR_PCP_THP 2 #else #define NR_PCP_THP 0 #endif #define NR_LOWORDER_PCP_LISTS (MIGRATE_PCPTYPES * (PAGE_ALLOC_COSTLY_ORDER + 1)) #define NR_PCP_LISTS (NR_LOWORDER_PCP_LISTS + NR_PCP_THP) -#define min_wmark_pages(z) (z->_watermark[WMARK_MIN] + z->watermark_boost) -#define low_wmark_pages(z) (z->_watermark[WMARK_LOW] + z->watermark_boost) -#define high_wmark_pages(z) (z->_watermark[WMARK_HIGH] + z->watermark_boost) -#define wmark_pages(z, i) (z->_watermark[i] + z->watermark_boost) - /* * Flags used in pcp->flags field. * @@ -827,6 +847,7 @@ struct zone { unsigned long watermark_boost; unsigned long nr_reserved_highatomic; + unsigned long nr_free_highatomic; /* * We don't know if the memory that we're going to allocate will be @@ -1014,6 +1035,32 @@ enum zone_flags { ZONE_BELOW_HIGH, /* zone is below high watermark. */ }; +static inline unsigned long wmark_pages(const struct zone *z, + enum zone_watermarks w) +{ + return z->_watermark[w] + z->watermark_boost; +} + +static inline unsigned long min_wmark_pages(const struct zone *z) +{ + return wmark_pages(z, WMARK_MIN); +} + +static inline unsigned long low_wmark_pages(const struct zone *z) +{ + return wmark_pages(z, WMARK_LOW); +} + +static inline unsigned long high_wmark_pages(const struct zone *z) +{ + return wmark_pages(z, WMARK_HIGH); +} + +static inline unsigned long promo_wmark_pages(const struct zone *z) +{ + return wmark_pages(z, WMARK_PROMO); +} + static inline unsigned long zone_managed_pages(struct zone *zone) { return (unsigned long)atomic_long_read(&zone->managed_pages); @@ -1686,7 +1733,7 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, zone = zonelist_zone(z)) #define for_next_zone_zonelist_nodemask(zone, z, highidx, nodemask) \ - for (zone = z->zone; \ + for (zone = zonelist_zone(z); \ zone; \ z = next_zones_zonelist(++z, highidx, nodemask), \ zone = zonelist_zone(z)) @@ -1722,7 +1769,7 @@ static inline bool movable_only_nodes(nodemask_t *nodes) nid = first_node(*nodes); zonelist = &NODE_DATA(nid)->node_zonelists[ZONELIST_FALLBACK]; z = first_zones_zonelist(zonelist, ZONE_NORMAL, nodes); - return (!z->zone) ? true : false; + return (!zonelist_zone(z)) ? true : false; } @@ -1977,8 +2024,9 @@ static inline int subsection_map_index(unsigned long pfn) static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) { int idx = subsection_map_index(pfn); + struct mem_section_usage *usage = READ_ONCE(ms->usage); - return test_bit(idx, READ_ONCE(ms->usage)->subsection_map); + return usage ? test_bit(idx, usage->subsection_map) : 0; } #else static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) diff --git a/include/linux/mnt_idmapping.h b/include/linux/mnt_idmapping.h index cd4d5c8781f5..b1b219bc3422 100644 --- a/include/linux/mnt_idmapping.h +++ b/include/linux/mnt_idmapping.h @@ -9,6 +9,7 @@ struct mnt_idmap; struct user_namespace; extern struct mnt_idmap nop_mnt_idmap; +extern struct mnt_idmap invalid_mnt_idmap; extern struct user_namespace init_user_ns; typedef struct { diff --git a/include/linux/mnt_namespace.h b/include/linux/mnt_namespace.h index 8f882f5881e8..70b366b64816 100644 --- a/include/linux/mnt_namespace.h +++ b/include/linux/mnt_namespace.h @@ -3,6 +3,9 @@ #define _NAMESPACE_H_ #ifdef __KERNEL__ +#include <linux/cleanup.h> +#include <linux/err.h> + struct mnt_namespace; struct fs_struct; struct user_namespace; @@ -11,6 +14,7 @@ struct ns_common; extern struct mnt_namespace *copy_mnt_ns(unsigned long, struct mnt_namespace *, struct user_namespace *, struct fs_struct *); extern void put_mnt_ns(struct mnt_namespace *ns); +DEFINE_FREE(put_mnt_ns, struct mnt_namespace *, if (!IS_ERR_OR_NULL(_T)) put_mnt_ns(_T)) extern struct ns_common *from_mnt_ns(struct mnt_namespace *); extern const struct file_operations proc_mounts_operations; diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 7a9a07ea451b..d67614f7b7f1 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -690,6 +690,8 @@ struct x86_cpu_id { __u16 model; __u16 steppings; __u16 feature; /* bit index */ + /* Solely for kernel-internal use: DO NOT EXPORT to userspace! */ + __u16 flags; kernel_ulong_t driver_data; }; @@ -698,6 +700,8 @@ struct x86_cpu_id { #define X86_FAMILY_ANY 0 #define X86_MODEL_ANY 0 #define X86_STEPPING_ANY 0 +#define X86_STEP_MIN 0 +#define X86_STEP_MAX 0xf #define X86_FEATURE_ANY 0 /* Same as FPU, you can't test for that */ /* diff --git a/include/linux/module.h b/include/linux/module.h index 1153b0d99a80..23792d5d7b74 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -52,9 +52,9 @@ struct module_kobject { struct module_attribute { struct attribute attr; - ssize_t (*show)(struct module_attribute *, struct module_kobject *, + ssize_t (*show)(const struct module_attribute *, struct module_kobject *, char *); - ssize_t (*store)(struct module_attribute *, struct module_kobject *, + ssize_t (*store)(const struct module_attribute *, struct module_kobject *, const char *, size_t count); void (*setup)(struct module *, const char *); int (*test)(struct module *); @@ -67,10 +67,10 @@ struct module_version_attribute { const char *version; }; -extern ssize_t __modver_version_show(struct module_attribute *, +extern ssize_t __modver_version_show(const struct module_attribute *, struct module_kobject *, char *); -extern struct module_attribute module_uevent; +extern const struct module_attribute module_uevent; /* These are either module local, or the kernel's dummy ones. */ extern int init_module(void); @@ -174,6 +174,12 @@ extern void cleanup_module(void); #define MODULE_SOFTDEP(_softdep) MODULE_INFO(softdep, _softdep) /* + * Weak module dependencies. See man modprobe.d for details. + * Example: MODULE_WEAKDEP("module-foo") + */ +#define MODULE_WEAKDEP(_weakdep) MODULE_INFO(weakdep, _weakdep) + +/* * MODULE_FILE is used for generating modules.builtin * So, make it no-op when this is being built as a module */ @@ -241,7 +247,7 @@ extern void cleanup_module(void); #ifdef MODULE /* Creates an alias so file2alias.c can find device table. */ #define MODULE_DEVICE_TABLE(type, name) \ -extern typeof(name) __mod_##type##__##name##_device_table \ +extern typeof(name) __mod_device_table__##type##__##name \ __attribute__ ((unused, alias(__stringify(name)))) #else /* !MODULE */ #define MODULE_DEVICE_TABLE(type, name) @@ -269,7 +275,7 @@ extern typeof(name) __mod_##type##__##name##_device_table \ #else #define MODULE_VERSION(_version) \ MODULE_INFO(version, _version); \ - static struct module_version_attribute __modver_attr \ + static const struct module_version_attribute __modver_attr \ __used __section("__modver") \ __aligned(__alignof__(struct module_version_attribute)) \ = { \ @@ -290,7 +296,7 @@ extern typeof(name) __mod_##type##__##name##_device_table \ * files require multiple MODULE_FIRMWARE() specifiers */ #define MODULE_FIRMWARE(_firmware) MODULE_INFO(firmware, _firmware) -#define MODULE_IMPORT_NS(ns) MODULE_INFO(import_ns, __stringify(ns)) +#define MODULE_IMPORT_NS(ns) MODULE_INFO(import_ns, ns) struct notifier_block; @@ -361,6 +367,8 @@ enum mod_mem_type { struct module_memory { void *base; + void *rw_copy; + bool is_rox; unsigned int size; #ifdef CONFIG_MODULES_TREE_LOOKUP @@ -422,7 +430,7 @@ struct module { /* Exported symbols */ const struct kernel_symbol *syms; - const s32 *crcs; + const u32 *crcs; unsigned int num_syms; #ifdef CONFIG_ARCH_USES_CFI_TRAPS @@ -440,7 +448,7 @@ struct module { /* GPL-only exported symbols. */ unsigned int num_gpl_syms; const struct kernel_symbol *gpl_syms; - const s32 *gpl_crcs; + const u32 *gpl_crcs; bool using_gplonly_symbols; #ifdef CONFIG_MODULE_SIG @@ -509,7 +517,9 @@ struct module { #endif #ifdef CONFIG_DEBUG_INFO_BTF_MODULES unsigned int btf_data_size; + unsigned int btf_base_data_size; void *btf_data; + void *btf_base_data; #endif #ifdef CONFIG_JUMP_LABEL struct jump_entry *jump_entries; @@ -605,6 +615,11 @@ static inline bool module_is_live(struct module *mod) return mod->state != MODULE_STATE_GOING; } +static inline bool module_is_coming(struct module *mod) +{ + return mod->state == MODULE_STATE_COMING; +} + struct module *__module_text_address(unsigned long addr); struct module *__module_address(unsigned long addr); bool is_module_address(unsigned long addr); @@ -754,6 +769,16 @@ static inline bool is_livepatch_module(struct module *mod) void set_module_sig_enforced(void); +void *__module_writable_address(struct module *mod, void *loc); + +static inline void *module_writable_address(struct module *mod, void *loc) +{ + if (!IS_ENABLED(CONFIG_ARCH_HAS_EXECMEM_ROX) || !mod || + mod->state != MODULE_STATE_UNFORMED) + return loc; + return __module_writable_address(mod, loc); +} + #else /* !CONFIG_MODULES... */ static inline struct module *__module_address(unsigned long addr) @@ -857,6 +882,15 @@ void *dereference_module_function_descriptor(struct module *mod, void *ptr) return ptr; } +static inline bool module_is_coming(struct module *mod) +{ + return false; +} + +static inline void *module_writable_address(struct module *mod, void *loc) +{ + return loc; +} #endif /* CONFIG_MODULES */ #ifdef CONFIG_SYSFS @@ -922,11 +956,11 @@ int module_kallsyms_on_each_symbol(const char *modname, * least KSYM_NAME_LEN long: a pointer to namebuf is returned if * found, otherwise NULL. */ -const char *module_address_lookup(unsigned long addr, - unsigned long *symbolsize, - unsigned long *offset, - char **modname, const unsigned char **modbuildid, - char *namebuf); +int module_address_lookup(unsigned long addr, + unsigned long *symbolsize, + unsigned long *offset, + char **modname, const unsigned char **modbuildid, + char *namebuf); int lookup_module_symbol_name(unsigned long addr, char *symname); int lookup_module_symbol_attrs(unsigned long addr, unsigned long *size, @@ -955,14 +989,14 @@ static inline int module_kallsyms_on_each_symbol(const char *modname, } /* For kallsyms to ask for address resolution. NULL means not found. */ -static inline const char *module_address_lookup(unsigned long addr, +static inline int module_address_lookup(unsigned long addr, unsigned long *symbolsize, unsigned long *offset, char **modname, const unsigned char **modbuildid, char *namebuf) { - return NULL; + return 0; } static inline int lookup_module_symbol_name(unsigned long addr, char *symname) diff --git a/include/linux/moduleloader.h b/include/linux/moduleloader.h index 89b1e0ed9811..1f5507ba5a12 100644 --- a/include/linux/moduleloader.h +++ b/include/linux/moduleloader.h @@ -25,13 +25,6 @@ int module_frob_arch_sections(Elf_Ehdr *hdr, /* Additional bytes needed by arch in front of individual sections */ unsigned int arch_mod_section_prepend(struct module *mod, unsigned int section); -/* Allocator used for allocating struct module, core sections and init - sections. Returns NULL on failure. */ -void *module_alloc(unsigned long size); - -/* Free memory returned from module_alloc. */ -void module_memfree(void *module_region); - /* Determines if the section name is an init section (that is only used during * module loading). */ @@ -115,6 +108,10 @@ int module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *mod); +int module_post_finalize(const Elf_Ehdr *hdr, + const Elf_Shdr *sechdrs, + struct module *mod); + #ifdef CONFIG_MODULES void flush_module_init_free_work(void); #else @@ -129,12 +126,4 @@ void module_arch_cleanup(struct module *mod); /* Any cleanup before freeing mod->module_init */ void module_arch_freeing_init(struct module *mod); -#if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \ - !defined(CONFIG_KASAN_VMALLOC) -#include <linux/kasan.h> -#define MODULE_ALIGN (PAGE_SIZE << KASAN_SHADOW_SCALE_SHIFT) -#else -#define MODULE_ALIGN PAGE_SIZE -#endif - #endif diff --git a/include/linux/mount.h b/include/linux/mount.h index c34c18b4e8f3..dcc17ce8a959 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -50,7 +50,7 @@ struct path; #define MNT_ATIME_MASK (MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME ) #define MNT_INTERNAL_FLAGS (MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL | \ - MNT_DOOMED | MNT_SYNC_UMOUNT | MNT_MARKED | MNT_ONRB) + MNT_DOOMED | MNT_SYNC_UMOUNT | MNT_MARKED) #define MNT_INTERNAL 0x4000 @@ -64,7 +64,6 @@ struct path; #define MNT_SYNC_UMOUNT 0x2000000 #define MNT_MARKED 0x4000000 #define MNT_UMOUNT 0x8000000 -#define MNT_ONRB 0x10000000 struct vfsmount { struct dentry *mnt_root; /* root of the mounted tree */ @@ -76,7 +75,7 @@ struct vfsmount { static inline struct mnt_idmap *mnt_idmap(const struct vfsmount *mnt) { /* Pairs with smp_store_release() in do_idmap_mount(). */ - return smp_load_acquire(&mnt->mnt_idmap); + return READ_ONCE(mnt->mnt_idmap); } extern int mnt_want_write(struct vfsmount *mnt); @@ -114,7 +113,7 @@ extern struct vfsmount *kern_mount(struct file_system_type *); extern void kern_unmount(struct vfsmount *mnt); extern int may_umount_tree(struct vfsmount *); extern int may_umount(struct vfsmount *); -extern long do_mount(const char *, const char __user *, +int do_mount(const char *, const char __user *, const char *, unsigned long, void *); extern struct vfsmount *collect_mounts(const struct path *); extern void drop_collected_mounts(struct vfsmount *); diff --git a/include/linux/moxtet.h b/include/linux/moxtet.h index ac577699edfd..dfa4800306ee 100644 --- a/include/linux/moxtet.h +++ b/include/linux/moxtet.h @@ -61,13 +61,8 @@ struct moxtet_driver { struct device_driver driver; }; -static inline struct moxtet_driver * -to_moxtet_driver(struct device_driver *drv) -{ - if (!drv) - return NULL; - return container_of(drv, struct moxtet_driver, driver); -} +#define to_moxtet_driver(__drv) \ + ( __drv ? container_of_const(__drv, struct moxtet_driver, driver) : NULL ) extern int __moxtet_register_driver(struct module *owner, struct moxtet_driver *mdrv); diff --git a/include/linux/mpi.h b/include/linux/mpi.h index eb0d1c1db208..47be46f36435 100644 --- a/include/linux/mpi.h +++ b/include/linux/mpi.h @@ -40,79 +40,26 @@ struct gcry_mpi { typedef struct gcry_mpi *MPI; #define mpi_get_nlimbs(a) ((a)->nlimbs) -#define mpi_has_sign(a) ((a)->sign) /*-- mpiutil.c --*/ MPI mpi_alloc(unsigned nlimbs); -void mpi_clear(MPI a); void mpi_free(MPI a); int mpi_resize(MPI a, unsigned nlimbs); -static inline MPI mpi_new(unsigned int nbits) -{ - return mpi_alloc((nbits + BITS_PER_MPI_LIMB - 1) / BITS_PER_MPI_LIMB); -} - MPI mpi_copy(MPI a); -MPI mpi_alloc_like(MPI a); -void mpi_snatch(MPI w, MPI u); -MPI mpi_set(MPI w, MPI u); -MPI mpi_set_ui(MPI w, unsigned long u); -MPI mpi_alloc_set_ui(unsigned long u); -void mpi_swap_cond(MPI a, MPI b, unsigned long swap); - -/* Constants used to return constant MPIs. See mpi_init if you - * want to add more constants. - */ -#define MPI_NUMBER_OF_CONSTANTS 6 -enum gcry_mpi_constants { - MPI_C_ZERO, - MPI_C_ONE, - MPI_C_TWO, - MPI_C_THREE, - MPI_C_FOUR, - MPI_C_EIGHT -}; - -MPI mpi_const(enum gcry_mpi_constants no); /*-- mpicoder.c --*/ - -/* Different formats of external big integer representation. */ -enum gcry_mpi_format { - GCRYMPI_FMT_NONE = 0, - GCRYMPI_FMT_STD = 1, /* Twos complement stored without length. */ - GCRYMPI_FMT_PGP = 2, /* As used by OpenPGP (unsigned only). */ - GCRYMPI_FMT_SSH = 3, /* As used by SSH (like STD but with length). */ - GCRYMPI_FMT_HEX = 4, /* Hex format. */ - GCRYMPI_FMT_USG = 5, /* Like STD but unsigned. */ - GCRYMPI_FMT_OPAQUE = 8 /* Opaque format (some functions only). */ -}; - MPI mpi_read_raw_data(const void *xbuffer, size_t nbytes); MPI mpi_read_from_buffer(const void *buffer, unsigned *ret_nread); -int mpi_fromstr(MPI val, const char *str); -MPI mpi_scanval(const char *string); MPI mpi_read_raw_from_sgl(struct scatterlist *sgl, unsigned int len); void *mpi_get_buffer(MPI a, unsigned *nbytes, int *sign); int mpi_read_buffer(MPI a, uint8_t *buf, unsigned buf_len, unsigned *nbytes, int *sign); int mpi_write_to_sgl(MPI a, struct scatterlist *sg, unsigned nbytes, int *sign); -int mpi_print(enum gcry_mpi_format format, unsigned char *buffer, - size_t buflen, size_t *nwritten, MPI a); /*-- mpi-mod.c --*/ -void mpi_mod(MPI rem, MPI dividend, MPI divisor); - -/* Context used with Barrett reduction. */ -struct barrett_ctx_s; -typedef struct barrett_ctx_s *mpi_barrett_t; - -mpi_barrett_t mpi_barrett_init(MPI m, int copy); -void mpi_barrett_free(mpi_barrett_t ctx); -void mpi_mod_barrett(MPI r, MPI x, mpi_barrett_t ctx); -void mpi_mul_barrett(MPI w, MPI u, MPI v, mpi_barrett_t ctx); +int mpi_mod(MPI rem, MPI dividend, MPI divisor); /*-- mpi-pow.c --*/ int mpi_powm(MPI res, MPI base, MPI exp, MPI mod); @@ -120,7 +67,6 @@ int mpi_powm(MPI res, MPI base, MPI exp, MPI mod); /*-- mpi-cmp.c --*/ int mpi_cmp_ui(MPI u, ulong v); int mpi_cmp(MPI u, MPI v); -int mpi_cmpabs(MPI u, MPI v); /*-- mpi-sub-ui.c --*/ int mpi_sub_ui(MPI w, MPI u, unsigned long vval); @@ -129,138 +75,22 @@ int mpi_sub_ui(MPI w, MPI u, unsigned long vval); void mpi_normalize(MPI a); unsigned mpi_get_nbits(MPI a); int mpi_test_bit(MPI a, unsigned int n); -void mpi_set_bit(MPI a, unsigned int n); -void mpi_set_highbit(MPI a, unsigned int n); -void mpi_clear_highbit(MPI a, unsigned int n); -void mpi_clear_bit(MPI a, unsigned int n); -void mpi_rshift_limbs(MPI a, unsigned int count); -void mpi_rshift(MPI x, MPI a, unsigned int n); -void mpi_lshift_limbs(MPI a, unsigned int count); -void mpi_lshift(MPI x, MPI a, unsigned int n); +int mpi_set_bit(MPI a, unsigned int n); +int mpi_rshift(MPI x, MPI a, unsigned int n); /*-- mpi-add.c --*/ -void mpi_add_ui(MPI w, MPI u, unsigned long v); -void mpi_add(MPI w, MPI u, MPI v); -void mpi_sub(MPI w, MPI u, MPI v); -void mpi_addm(MPI w, MPI u, MPI v, MPI m); -void mpi_subm(MPI w, MPI u, MPI v, MPI m); +int mpi_add(MPI w, MPI u, MPI v); +int mpi_sub(MPI w, MPI u, MPI v); +int mpi_addm(MPI w, MPI u, MPI v, MPI m); +int mpi_subm(MPI w, MPI u, MPI v, MPI m); /*-- mpi-mul.c --*/ -void mpi_mul(MPI w, MPI u, MPI v); -void mpi_mulm(MPI w, MPI u, MPI v, MPI m); +int mpi_mul(MPI w, MPI u, MPI v); +int mpi_mulm(MPI w, MPI u, MPI v, MPI m); /*-- mpi-div.c --*/ -void mpi_tdiv_r(MPI rem, MPI num, MPI den); -void mpi_fdiv_r(MPI rem, MPI dividend, MPI divisor); -void mpi_fdiv_q(MPI quot, MPI dividend, MPI divisor); - -/*-- mpi-inv.c --*/ -int mpi_invm(MPI x, MPI a, MPI n); - -/*-- ec.c --*/ - -/* Object to represent a point in projective coordinates */ -struct gcry_mpi_point { - MPI x; - MPI y; - MPI z; -}; - -typedef struct gcry_mpi_point *MPI_POINT; - -/* Models describing an elliptic curve */ -enum gcry_mpi_ec_models { - /* The Short Weierstrass equation is - * y^2 = x^3 + ax + b - */ - MPI_EC_WEIERSTRASS = 0, - /* The Montgomery equation is - * by^2 = x^3 + ax^2 + x - */ - MPI_EC_MONTGOMERY, - /* The Twisted Edwards equation is - * ax^2 + y^2 = 1 + bx^2y^2 - * Note that we use 'b' instead of the commonly used 'd'. - */ - MPI_EC_EDWARDS -}; - -/* Dialects used with elliptic curves */ -enum ecc_dialects { - ECC_DIALECT_STANDARD = 0, - ECC_DIALECT_ED25519, - ECC_DIALECT_SAFECURVE -}; - -/* This context is used with all our EC functions. */ -struct mpi_ec_ctx { - enum gcry_mpi_ec_models model; /* The model describing this curve. */ - enum ecc_dialects dialect; /* The ECC dialect used with the curve. */ - int flags; /* Public key flags (not always used). */ - unsigned int nbits; /* Number of bits. */ - - /* Domain parameters. Note that they may not all be set and if set - * the MPIs may be flagged as constant. - */ - MPI p; /* Prime specifying the field GF(p). */ - MPI a; /* First coefficient of the Weierstrass equation. */ - MPI b; /* Second coefficient of the Weierstrass equation. */ - MPI_POINT G; /* Base point (generator). */ - MPI n; /* Order of G. */ - unsigned int h; /* Cofactor. */ - - /* The actual key. May not be set. */ - MPI_POINT Q; /* Public key. */ - MPI d; /* Private key. */ - - const char *name; /* Name of the curve. */ - - /* This structure is private to mpi/ec.c! */ - struct { - struct { - unsigned int a_is_pminus3:1; - unsigned int two_inv_p:1; - } valid; /* Flags to help setting the helper vars below. */ - - int a_is_pminus3; /* True if A = P - 3. */ - - MPI two_inv_p; - - mpi_barrett_t p_barrett; - - /* Scratch variables. */ - MPI scratch[11]; - - /* Helper for fast reduction. */ - /* int nist_nbits; /\* If this is a NIST curve, the # of bits. *\/ */ - /* MPI s[10]; */ - /* MPI c; */ - } t; - - /* Curve specific computation routines for the field. */ - void (*addm)(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx); - void (*subm)(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ec); - void (*mulm)(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx); - void (*pow2)(MPI w, const MPI b, struct mpi_ec_ctx *ctx); - void (*mul2)(MPI w, MPI u, struct mpi_ec_ctx *ctx); -}; - -void mpi_ec_init(struct mpi_ec_ctx *ctx, enum gcry_mpi_ec_models model, - enum ecc_dialects dialect, - int flags, MPI p, MPI a, MPI b); -void mpi_ec_deinit(struct mpi_ec_ctx *ctx); -MPI_POINT mpi_point_new(unsigned int nbits); -void mpi_point_release(MPI_POINT p); -void mpi_point_init(MPI_POINT p); -void mpi_point_free_parts(MPI_POINT p); -int mpi_ec_get_affine(MPI x, MPI y, MPI_POINT point, struct mpi_ec_ctx *ctx); -void mpi_ec_add_points(MPI_POINT result, - MPI_POINT p1, MPI_POINT p2, - struct mpi_ec_ctx *ctx); -void mpi_ec_mul_point(MPI_POINT result, - MPI scalar, MPI_POINT point, - struct mpi_ec_ctx *ctx); -int mpi_ec_curve_point(MPI_POINT point, struct mpi_ec_ctx *ctx); +int mpi_tdiv_r(MPI rem, MPI num, MPI den); +int mpi_fdiv_r(MPI rem, MPI dividend, MPI divisor); /* inline functions */ diff --git a/include/linux/mroute_base.h b/include/linux/mroute_base.h index 9dd4bf157255..58a2401e4b55 100644 --- a/include/linux/mroute_base.h +++ b/include/linux/mroute_base.h @@ -146,9 +146,9 @@ struct mr_mfc { unsigned long last_assert; int minvif; int maxvif; - unsigned long bytes; - unsigned long pkt; - unsigned long wrong_if; + atomic_long_t bytes; + atomic_long_t pkt; + atomic_long_t wrong_if; unsigned long lastuse; unsigned char ttls[MAXVIFS]; refcount_t refcount; diff --git a/include/linux/msi.h b/include/linux/msi.h index 26d07e23052e..b10093c4d00e 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -19,13 +19,9 @@ */ #include <linux/irqdomain_defs.h> -#include <linux/cpumask.h> +#include <linux/cpumask_types.h> #include <linux/msi_api.h> -#include <linux/xarray.h> -#include <linux/mutex.h> -#include <linux/list.h> #include <linux/irq.h> -#include <linux/bits.h> #include <asm/msi.h> @@ -81,7 +77,6 @@ extern int pci_msi_ignore_mask; /* Helper functions */ struct msi_desc; struct pci_dev; -struct platform_msi_priv_data; struct device_attribute; struct irq_domain; struct irq_affinity_desc; @@ -228,22 +223,6 @@ struct msi_dev_domain { struct irq_domain *domain; }; -/** - * msi_device_data - MSI per device data - * @properties: MSI properties which are interesting to drivers - * @platform_data: Platform-MSI specific data - * @mutex: Mutex protecting the MSI descriptor store - * @__domains: Internal data for per device MSI domains - * @__iter_idx: Index to search the next entry for iterators - */ -struct msi_device_data { - unsigned long properties; - struct platform_msi_priv_data *platform_data; - struct mutex mutex; - struct msi_dev_domain __domains[MSI_MAX_DEVICE_IRQDOMAINS]; - unsigned long __iter_idx; -}; - int msi_setup_device_data(struct device *dev); void msi_lock_descs(struct device *dev); @@ -556,6 +535,8 @@ enum { MSI_FLAG_USE_DEV_FWNODE = (1 << 7), /* Set parent->dev into domain->pm_dev on device domain creation */ MSI_FLAG_PARENT_PM_DEV = (1 << 8), + /* Support for parent mask/unmask */ + MSI_FLAG_PCI_MSI_MASK_PARENT = (1 << 9), /* Mask for the generic functionality */ MSI_GENERIC_FLAGS_MASK = GENMASK(15, 0), @@ -573,8 +554,8 @@ enum { MSI_FLAG_MSIX_CONTIGUOUS = (1 << 19), /* PCI/MSI-X vectors can be dynamically allocated/freed post MSI-X enable */ MSI_FLAG_PCI_MSIX_ALLOC_DYN = (1 << 20), - /* Support for PCI/IMS */ - MSI_FLAG_PCI_IMS = (1 << 21), + /* PCI MSIs cannot be steered separately to CPU cores */ + MSI_FLAG_NO_AFFINITY = (1 << 21), }; /** @@ -641,41 +622,18 @@ void msi_domain_free_irqs_all(struct device *dev, unsigned int domid); struct msi_domain_info *msi_get_domain_info(struct irq_domain *domain); -struct irq_domain *platform_msi_create_irq_domain(struct fwnode_handle *fwnode, - struct msi_domain_info *info, - struct irq_domain *parent); - -/* When an MSI domain is used as an intermediate domain */ -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, - bool is_tree, - irq_write_msi_msg_t write_msi_msg, - const struct irq_domain_ops *ops, - void *host_data); - -#define platform_msi_create_device_domain(dev, nvec, write, ops, data) \ - __platform_msi_create_device_domain(dev, nvec, false, write, ops, data) -#define platform_msi_create_device_tree_domain(dev, nvec, write, ops, data) \ - __platform_msi_create_device_domain(dev, nvec, true, write, ops, data) - -int platform_msi_device_domain_alloc(struct irq_domain *domain, unsigned int virq, - unsigned int nr_irqs); -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); /* Per device platform MSI */ int platform_device_msi_init_and_alloc_irqs(struct device *dev, unsigned int nvec, irq_write_msi_msg_t write_msi_msg); void platform_device_msi_free_irqs_all(struct device *dev); bool msi_device_has_isolated_msi(struct device *dev); + +static inline int msi_domain_alloc_irqs(struct device *dev, unsigned int domid, int nirqs) +{ + return msi_domain_alloc_irqs_range(dev, domid, 0, nirqs - 1); +} + #else /* CONFIG_GENERIC_MSI_IRQ */ static inline bool msi_device_has_isolated_msi(struct device *dev) { diff --git a/include/linux/msi_api.h b/include/linux/msi_api.h index 391087ad99b1..5ae72d1912c4 100644 --- a/include/linux/msi_api.h +++ b/include/linux/msi_api.h @@ -15,7 +15,6 @@ struct device; */ enum msi_domain_ids { MSI_DEFAULT_DOMAIN, - MSI_SECONDARY_DOMAIN, MSI_MAX_DEVICE_IRQDOMAINS, }; diff --git a/include/linux/mtd/cfi.h b/include/linux/mtd/cfi.h index 947410faf9e2..35ca19ae21ae 100644 --- a/include/linux/mtd/cfi.h +++ b/include/linux/mtd/cfi.h @@ -308,32 +308,32 @@ static inline uint8_t cfi_read_query(struct map_info *map, uint32_t addr) { map_word val = map_read(map, addr); - if (map_bankwidth_is_1(map)) { + if (map_bankwidth_is_1(map)) return val.x[0]; - } else if (map_bankwidth_is_2(map)) { + if (map_bankwidth_is_2(map)) return cfi16_to_cpu(map, val.x[0]); - } else { - /* No point in a 64-bit byteswap since that would just be - swapping the responses from different chips, and we are - only interested in one chip (a representative sample) */ - return cfi32_to_cpu(map, val.x[0]); - } + /* + * No point in a 64-bit byteswap since that would just be + * swapping the responses from different chips, and we are + * only interested in one chip (a representative sample) + */ + return cfi32_to_cpu(map, val.x[0]); } static inline uint16_t cfi_read_query16(struct map_info *map, uint32_t addr) { map_word val = map_read(map, addr); - if (map_bankwidth_is_1(map)) { + if (map_bankwidth_is_1(map)) return val.x[0] & 0xff; - } else if (map_bankwidth_is_2(map)) { + if (map_bankwidth_is_2(map)) return cfi16_to_cpu(map, val.x[0]); - } else { - /* No point in a 64-bit byteswap since that would just be - swapping the responses from different chips, and we are - only interested in one chip (a representative sample) */ - return cfi32_to_cpu(map, val.x[0]); - } + /* + * No point in a 64-bit byteswap since that would just be + * swapping the responses from different chips, and we are + * only interested in one chip (a representative sample) + */ + return cfi32_to_cpu(map, val.x[0]); } void cfi_udelay(int us); diff --git a/include/linux/mtd/map.h b/include/linux/mtd/map.h index b4fa92a6e44b..1b56796f6cb3 100644 --- a/include/linux/mtd/map.h +++ b/include/linux/mtd/map.h @@ -15,7 +15,7 @@ #include <linux/kernel.h> #include <linux/io.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <asm/barrier.h> #ifdef CONFIG_MTD_MAP_BANK_WIDTH_1 diff --git a/include/linux/mtd/nand-ecc-mxic.h b/include/linux/mtd/nand-ecc-mxic.h index b125926e458c..0da4b2999576 100644 --- a/include/linux/mtd/nand-ecc-mxic.h +++ b/include/linux/mtd/nand-ecc-mxic.h @@ -16,7 +16,7 @@ struct mxic_ecc_engine; #if IS_ENABLED(CONFIG_MTD_NAND_ECC_MXIC) && IS_REACHABLE(CONFIG_MTD_NAND_CORE) -struct nand_ecc_engine_ops *mxic_ecc_get_pipelined_ops(void); +const struct nand_ecc_engine_ops *mxic_ecc_get_pipelined_ops(void); struct nand_ecc_engine *mxic_ecc_get_pipelined_engine(struct platform_device *spi_pdev); void mxic_ecc_put_pipelined_engine(struct nand_ecc_engine *eng); int mxic_ecc_process_data_pipelined(struct nand_ecc_engine *eng, @@ -24,7 +24,7 @@ int mxic_ecc_process_data_pipelined(struct nand_ecc_engine *eng, #else /* !CONFIG_MTD_NAND_ECC_MXIC */ -static inline struct nand_ecc_engine_ops *mxic_ecc_get_pipelined_ops(void) +static inline const struct nand_ecc_engine_ops *mxic_ecc_get_pipelined_ops(void) { return NULL; } diff --git a/include/linux/mtd/nand-qpic-common.h b/include/linux/mtd/nand-qpic-common.h new file mode 100644 index 000000000000..4d9b736ff8b7 --- /dev/null +++ b/include/linux/mtd/nand-qpic-common.h @@ -0,0 +1,478 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * QCOM QPIC common APIs header file + * + * Copyright (c) 2023 Qualcomm Inc. + * Authors: Md sadre Alam <quic_mdalam@quicinc.com> + * + */ +#ifndef __MTD_NAND_QPIC_COMMON_H__ +#define __MTD_NAND_QPIC_COMMON_H__ + +/* NANDc reg offsets */ +#define NAND_FLASH_CMD 0x00 +#define NAND_ADDR0 0x04 +#define NAND_ADDR1 0x08 +#define NAND_FLASH_CHIP_SELECT 0x0c +#define NAND_EXEC_CMD 0x10 +#define NAND_FLASH_STATUS 0x14 +#define NAND_BUFFER_STATUS 0x18 +#define NAND_DEV0_CFG0 0x20 +#define NAND_DEV0_CFG1 0x24 +#define NAND_DEV0_ECC_CFG 0x28 +#define NAND_AUTO_STATUS_EN 0x2c +#define NAND_DEV1_CFG0 0x30 +#define NAND_DEV1_CFG1 0x34 +#define NAND_READ_ID 0x40 +#define NAND_READ_STATUS 0x44 +#define NAND_DEV_CMD0 0xa0 +#define NAND_DEV_CMD1 0xa4 +#define NAND_DEV_CMD2 0xa8 +#define NAND_DEV_CMD_VLD 0xac +#define SFLASHC_BURST_CFG 0xe0 +#define NAND_ERASED_CW_DETECT_CFG 0xe8 +#define NAND_ERASED_CW_DETECT_STATUS 0xec +#define NAND_EBI2_ECC_BUF_CFG 0xf0 +#define FLASH_BUF_ACC 0x100 + +#define NAND_CTRL 0xf00 +#define NAND_VERSION 0xf08 +#define NAND_READ_LOCATION_0 0xf20 +#define NAND_READ_LOCATION_1 0xf24 +#define NAND_READ_LOCATION_2 0xf28 +#define NAND_READ_LOCATION_3 0xf2c +#define NAND_READ_LOCATION_LAST_CW_0 0xf40 +#define NAND_READ_LOCATION_LAST_CW_1 0xf44 +#define NAND_READ_LOCATION_LAST_CW_2 0xf48 +#define NAND_READ_LOCATION_LAST_CW_3 0xf4c + +/* dummy register offsets, used by qcom_write_reg_dma */ +#define NAND_DEV_CMD1_RESTORE 0xdead +#define NAND_DEV_CMD_VLD_RESTORE 0xbeef + +/* NAND_FLASH_CMD bits */ +#define PAGE_ACC BIT(4) +#define LAST_PAGE BIT(5) + +/* NAND_FLASH_CHIP_SELECT bits */ +#define NAND_DEV_SEL 0 +#define DM_EN BIT(2) + +/* NAND_FLASH_STATUS bits */ +#define FS_OP_ERR BIT(4) +#define FS_READY_BSY_N BIT(5) +#define FS_MPU_ERR BIT(8) +#define FS_DEVICE_STS_ERR BIT(16) +#define FS_DEVICE_WP BIT(23) + +/* NAND_BUFFER_STATUS bits */ +#define BS_UNCORRECTABLE_BIT BIT(8) +#define BS_CORRECTABLE_ERR_MSK 0x1f + +/* NAND_DEVn_CFG0 bits */ +#define DISABLE_STATUS_AFTER_WRITE BIT(4) +#define CW_PER_PAGE 6 +#define CW_PER_PAGE_MASK GENMASK(8, 6) +#define UD_SIZE_BYTES 9 +#define UD_SIZE_BYTES_MASK GENMASK(18, 9) +#define ECC_PARITY_SIZE_BYTES_RS GENMASK(22, 19) +#define SPARE_SIZE_BYTES 23 +#define SPARE_SIZE_BYTES_MASK GENMASK(26, 23) +#define NUM_ADDR_CYCLES 27 +#define NUM_ADDR_CYCLES_MASK GENMASK(29, 27) +#define STATUS_BFR_READ BIT(30) +#define SET_RD_MODE_AFTER_STATUS BIT(31) + +/* NAND_DEVn_CFG0 bits */ +#define DEV0_CFG1_ECC_DISABLE BIT(0) +#define WIDE_FLASH BIT(1) +#define NAND_RECOVERY_CYCLES 2 +#define NAND_RECOVERY_CYCLES_MASK GENMASK(4, 2) +#define CS_ACTIVE_BSY BIT(5) +#define BAD_BLOCK_BYTE_NUM 6 +#define BAD_BLOCK_BYTE_NUM_MASK GENMASK(15, 6) +#define BAD_BLOCK_IN_SPARE_AREA BIT(16) +#define WR_RD_BSY_GAP 17 +#define WR_RD_BSY_GAP_MASK GENMASK(22, 17) +#define ENABLE_BCH_ECC BIT(27) + +/* NAND_DEV0_ECC_CFG bits */ +#define ECC_CFG_ECC_DISABLE BIT(0) +#define ECC_SW_RESET BIT(1) +#define ECC_MODE 4 +#define ECC_MODE_MASK GENMASK(5, 4) +#define ECC_PARITY_SIZE_BYTES_BCH 8 +#define ECC_PARITY_SIZE_BYTES_BCH_MASK GENMASK(12, 8) +#define ECC_NUM_DATA_BYTES 16 +#define ECC_NUM_DATA_BYTES_MASK GENMASK(25, 16) +#define ECC_FORCE_CLK_OPEN BIT(30) + +/* NAND_DEV_CMD1 bits */ +#define READ_ADDR 0 + +/* NAND_DEV_CMD_VLD bits */ +#define READ_START_VLD BIT(0) +#define READ_STOP_VLD BIT(1) +#define WRITE_START_VLD BIT(2) +#define ERASE_START_VLD BIT(3) +#define SEQ_READ_START_VLD BIT(4) + +/* NAND_EBI2_ECC_BUF_CFG bits */ +#define NUM_STEPS 0 + +/* NAND_ERASED_CW_DETECT_CFG bits */ +#define ERASED_CW_ECC_MASK 1 +#define AUTO_DETECT_RES 0 +#define MASK_ECC BIT(ERASED_CW_ECC_MASK) +#define RESET_ERASED_DET BIT(AUTO_DETECT_RES) +#define ACTIVE_ERASED_DET (0 << AUTO_DETECT_RES) +#define CLR_ERASED_PAGE_DET (RESET_ERASED_DET | MASK_ECC) +#define SET_ERASED_PAGE_DET (ACTIVE_ERASED_DET | MASK_ECC) + +/* NAND_ERASED_CW_DETECT_STATUS bits */ +#define PAGE_ALL_ERASED BIT(7) +#define CODEWORD_ALL_ERASED BIT(6) +#define PAGE_ERASED BIT(5) +#define CODEWORD_ERASED BIT(4) +#define ERASED_PAGE (PAGE_ALL_ERASED | PAGE_ERASED) +#define ERASED_CW (CODEWORD_ALL_ERASED | CODEWORD_ERASED) + +/* NAND_READ_LOCATION_n bits */ +#define READ_LOCATION_OFFSET 0 +#define READ_LOCATION_SIZE 16 +#define READ_LOCATION_LAST 31 + +/* Version Mask */ +#define NAND_VERSION_MAJOR_MASK 0xf0000000 +#define NAND_VERSION_MAJOR_SHIFT 28 +#define NAND_VERSION_MINOR_MASK 0x0fff0000 +#define NAND_VERSION_MINOR_SHIFT 16 + +/* NAND OP_CMDs */ +#define OP_PAGE_READ 0x2 +#define OP_PAGE_READ_WITH_ECC 0x3 +#define OP_PAGE_READ_WITH_ECC_SPARE 0x4 +#define OP_PAGE_READ_ONFI_READ 0x5 +#define OP_PROGRAM_PAGE 0x6 +#define OP_PAGE_PROGRAM_WITH_ECC 0x7 +#define OP_PROGRAM_PAGE_SPARE 0x9 +#define OP_BLOCK_ERASE 0xa +#define OP_CHECK_STATUS 0xc +#define OP_FETCH_ID 0xb +#define OP_RESET_DEVICE 0xd + +/* Default Value for NAND_DEV_CMD_VLD */ +#define NAND_DEV_CMD_VLD_VAL (READ_START_VLD | WRITE_START_VLD | \ + ERASE_START_VLD | SEQ_READ_START_VLD) + +/* NAND_CTRL bits */ +#define BAM_MODE_EN BIT(0) + +/* + * the NAND controller performs reads/writes with ECC in 516 byte chunks. + * the driver calls the chunks 'step' or 'codeword' interchangeably + */ +#define NANDC_STEP_SIZE 512 + +/* + * the largest page size we support is 8K, this will have 16 steps/codewords + * of 512 bytes each + */ +#define MAX_NUM_STEPS (SZ_8K / NANDC_STEP_SIZE) + +/* we read at most 3 registers per codeword scan */ +#define MAX_REG_RD (3 * MAX_NUM_STEPS) + +/* ECC modes supported by the controller */ +#define ECC_NONE BIT(0) +#define ECC_RS_4BIT BIT(1) +#define ECC_BCH_4BIT BIT(2) +#define ECC_BCH_8BIT BIT(3) + +/* + * Returns the actual register address for all NAND_DEV_ registers + * (i.e. NAND_DEV_CMD0, NAND_DEV_CMD1, NAND_DEV_CMD2 and NAND_DEV_CMD_VLD) + */ +#define dev_cmd_reg_addr(nandc, reg) ((nandc)->props->dev_cmd_reg_start + (reg)) + +/* Returns the NAND register physical address */ +#define nandc_reg_phys(chip, offset) ((chip)->base_phys + (offset)) + +/* Returns the dma address for reg read buffer */ +#define reg_buf_dma_addr(chip, vaddr) \ + ((chip)->reg_read_dma + \ + ((u8 *)(vaddr) - (u8 *)(chip)->reg_read_buf)) + +#define QPIC_PER_CW_CMD_ELEMENTS 32 +#define QPIC_PER_CW_CMD_SGL 32 +#define QPIC_PER_CW_DATA_SGL 8 + +#define QPIC_NAND_COMPLETION_TIMEOUT msecs_to_jiffies(2000) + +/* + * Flags used in DMA descriptor preparation helper functions + * (i.e. qcom_read_reg_dma/qcom_write_reg_dma/qcom_read_data_dma/qcom_write_data_dma) + */ +/* Don't set the EOT in current tx BAM sgl */ +#define NAND_BAM_NO_EOT BIT(0) +/* Set the NWD flag in current BAM sgl */ +#define NAND_BAM_NWD BIT(1) +/* Finish writing in the current BAM sgl and start writing in another BAM sgl */ +#define NAND_BAM_NEXT_SGL BIT(2) +/* + * Erased codeword status is being used two times in single transfer so this + * flag will determine the current value of erased codeword status register + */ +#define NAND_ERASED_CW_SET BIT(4) + +#define MAX_ADDRESS_CYCLE 5 + +/* + * This data type corresponds to the BAM transaction which will be used for all + * NAND transfers. + * @bam_ce - the array of BAM command elements + * @cmd_sgl - sgl for NAND BAM command pipe + * @data_sgl - sgl for NAND BAM consumer/producer pipe + * @last_data_desc - last DMA desc in data channel (tx/rx). + * @last_cmd_desc - last DMA desc in command channel. + * @txn_done - completion for NAND transfer. + * @bam_ce_pos - the index in bam_ce which is available for next sgl + * @bam_ce_start - the index in bam_ce which marks the start position ce + * for current sgl. It will be used for size calculation + * for current sgl + * @cmd_sgl_pos - current index in command sgl. + * @cmd_sgl_start - start index in command sgl. + * @tx_sgl_pos - current index in data sgl for tx. + * @tx_sgl_start - start index in data sgl for tx. + * @rx_sgl_pos - current index in data sgl for rx. + * @rx_sgl_start - start index in data sgl for rx. + */ +struct bam_transaction { + struct bam_cmd_element *bam_ce; + struct scatterlist *cmd_sgl; + struct scatterlist *data_sgl; + struct dma_async_tx_descriptor *last_data_desc; + struct dma_async_tx_descriptor *last_cmd_desc; + struct completion txn_done; + struct_group(bam_positions, + u32 bam_ce_pos; + u32 bam_ce_start; + u32 cmd_sgl_pos; + u32 cmd_sgl_start; + u32 tx_sgl_pos; + u32 tx_sgl_start; + u32 rx_sgl_pos; + u32 rx_sgl_start; + + ); +}; + +/* + * This data type corresponds to the nand dma descriptor + * @dma_desc - low level DMA engine descriptor + * @list - list for desc_info + * + * @adm_sgl - sgl which will be used for single sgl dma descriptor. Only used by + * ADM + * @bam_sgl - sgl which will be used for dma descriptor. Only used by BAM + * @sgl_cnt - number of SGL in bam_sgl. Only used by BAM + * @dir - DMA transfer direction + */ +struct desc_info { + struct dma_async_tx_descriptor *dma_desc; + struct list_head node; + + union { + struct scatterlist adm_sgl; + struct { + struct scatterlist *bam_sgl; + int sgl_cnt; + }; + }; + enum dma_data_direction dir; +}; + +/* + * holds the current register values that we want to write. acts as a contiguous + * chunk of memory which we use to write the controller registers through DMA. + */ +struct nandc_regs { + __le32 cmd; + __le32 addr0; + __le32 addr1; + __le32 chip_sel; + __le32 exec; + + __le32 cfg0; + __le32 cfg1; + __le32 ecc_bch_cfg; + + __le32 clrflashstatus; + __le32 clrreadstatus; + + __le32 cmd1; + __le32 vld; + + __le32 orig_cmd1; + __le32 orig_vld; + + __le32 ecc_buf_cfg; + __le32 read_location0; + __le32 read_location1; + __le32 read_location2; + __le32 read_location3; + __le32 read_location_last0; + __le32 read_location_last1; + __le32 read_location_last2; + __le32 read_location_last3; + + __le32 erased_cw_detect_cfg_clr; + __le32 erased_cw_detect_cfg_set; +}; + +/* + * NAND controller data struct + * + * @dev: parent device + * + * @base: MMIO base + * + * @core_clk: controller clock + * @aon_clk: another controller clock + * + * @regs: a contiguous chunk of memory for DMA register + * writes. contains the register values to be + * written to controller + * + * @props: properties of current NAND controller, + * initialized via DT match data + * + * @controller: base controller structure + * @host_list: list containing all the chips attached to the + * controller + * + * @chan: dma channel + * @cmd_crci: ADM DMA CRCI for command flow control + * @data_crci: ADM DMA CRCI for data flow control + * + * @desc_list: DMA descriptor list (list of desc_infos) + * + * @data_buffer: our local DMA buffer for page read/writes, + * used when we can't use the buffer provided + * by upper layers directly + * @reg_read_buf: local buffer for reading back registers via DMA + * + * @base_phys: physical base address of controller registers + * @base_dma: dma base address of controller registers + * @reg_read_dma: contains dma address for register read buffer + * + * @buf_size/count/start: markers for chip->legacy.read_buf/write_buf + * functions + * @max_cwperpage: maximum QPIC codewords required. calculated + * from all connected NAND devices pagesize + * + * @reg_read_pos: marker for data read in reg_read_buf + * + * @cmd1/vld: some fixed controller register values + * + * @exec_opwrite: flag to select correct number of code word + * while reading status + */ +struct qcom_nand_controller { + struct device *dev; + + void __iomem *base; + + struct clk *core_clk; + struct clk *aon_clk; + + struct nandc_regs *regs; + struct bam_transaction *bam_txn; + + const struct qcom_nandc_props *props; + + struct nand_controller *controller; + struct list_head host_list; + + union { + /* will be used only by QPIC for BAM DMA */ + struct { + struct dma_chan *tx_chan; + struct dma_chan *rx_chan; + struct dma_chan *cmd_chan; + }; + + /* will be used only by EBI2 for ADM DMA */ + struct { + struct dma_chan *chan; + unsigned int cmd_crci; + unsigned int data_crci; + }; + }; + + struct list_head desc_list; + + u8 *data_buffer; + __le32 *reg_read_buf; + + phys_addr_t base_phys; + dma_addr_t base_dma; + dma_addr_t reg_read_dma; + + int buf_size; + int buf_count; + int buf_start; + unsigned int max_cwperpage; + + int reg_read_pos; + + u32 cmd1, vld; + bool exec_opwrite; +}; + +/* + * This data type corresponds to the NAND controller properties which varies + * among different NAND controllers. + * @ecc_modes - ecc mode for NAND + * @dev_cmd_reg_start - NAND_DEV_CMD_* registers starting offset + * @supports_bam - whether NAND controller is using BAM + * @nandc_part_of_qpic - whether NAND controller is part of qpic IP + * @qpic_version2 - flag to indicate QPIC IP version 2 + * @use_codeword_fixup - whether NAND has different layout for boot partitions + */ +struct qcom_nandc_props { + u32 ecc_modes; + u32 dev_cmd_reg_start; + bool supports_bam; + bool nandc_part_of_qpic; + bool qpic_version2; + bool use_codeword_fixup; +}; + +void qcom_free_bam_transaction(struct qcom_nand_controller *nandc); +struct bam_transaction *qcom_alloc_bam_transaction(struct qcom_nand_controller *nandc); +void qcom_clear_bam_transaction(struct qcom_nand_controller *nandc); +void qcom_qpic_bam_dma_done(void *data); +void qcom_nandc_dev_to_mem(struct qcom_nand_controller *nandc, bool is_cpu); +int qcom_prepare_bam_async_desc(struct qcom_nand_controller *nandc, + struct dma_chan *chan, unsigned long flags); +int qcom_prep_bam_dma_desc_cmd(struct qcom_nand_controller *nandc, bool read, + int reg_off, const void *vaddr, int size, unsigned int flags); +int qcom_prep_bam_dma_desc_data(struct qcom_nand_controller *nandc, bool read, + const void *vaddr, int size, unsigned int flags); +int qcom_prep_adm_dma_desc(struct qcom_nand_controller *nandc, bool read, int reg_off, + const void *vaddr, int size, bool flow_control); +int qcom_read_reg_dma(struct qcom_nand_controller *nandc, int first, int num_regs, + unsigned int flags); +int qcom_write_reg_dma(struct qcom_nand_controller *nandc, __le32 *vaddr, int first, + int num_regs, unsigned int flags); +int qcom_read_data_dma(struct qcom_nand_controller *nandc, int reg_off, const u8 *vaddr, + int size, unsigned int flags); +int qcom_write_data_dma(struct qcom_nand_controller *nandc, int reg_off, const u8 *vaddr, + int size, unsigned int flags); +int qcom_submit_descs(struct qcom_nand_controller *nandc); +void qcom_clear_read_regs(struct qcom_nand_controller *nandc); +void qcom_nandc_unalloc(struct qcom_nand_controller *nandc); +int qcom_nandc_alloc(struct qcom_nand_controller *nandc); +#endif + diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index b2996dc987ff..0e2f228e8b4a 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -103,6 +103,8 @@ enum nand_page_io_req_type { * @ooblen: the number of OOB bytes to read from/write to this page * @oobbuf: buffer to store OOB data in or get OOB data from * @mode: one of the %MTD_OPS_XXX mode + * @continuous: no need to start over the operation at the end of each page, the + * NAND device will automatically prepare the next one * * This object is used to pass per-page I/O requests to NAND sub-layers. This * way all useful information are already formatted in a useful way and @@ -125,6 +127,7 @@ struct nand_page_io_req { void *in; } oobbuf; int mode; + bool continuous; }; const struct mtd_ooblayout_ops *nand_get_small_page_ooblayout(void); @@ -290,7 +293,7 @@ enum nand_ecc_engine_integration { struct nand_ecc_engine { struct device *dev; struct list_head node; - struct nand_ecc_engine_ops *ops; + const struct nand_ecc_engine_ops *ops; enum nand_ecc_engine_integration integration; void *priv; }; @@ -906,19 +909,19 @@ static inline void nanddev_pos_next_page(struct nand_device *nand, } /** - * nand_io_iter_init - Initialize a NAND I/O iterator + * nand_io_page_iter_init - Initialize a NAND I/O iterator * @nand: NAND device * @offs: absolute offset * @req: MTD request * @iter: NAND I/O iterator * * Initializes a NAND iterator based on the information passed by the MTD - * layer. + * layer for page jumps. */ -static inline void nanddev_io_iter_init(struct nand_device *nand, - enum nand_page_io_req_type reqtype, - loff_t offs, struct mtd_oob_ops *req, - struct nand_io_iter *iter) +static inline void nanddev_io_page_iter_init(struct nand_device *nand, + enum nand_page_io_req_type reqtype, + loff_t offs, struct mtd_oob_ops *req, + struct nand_io_iter *iter) { struct mtd_info *mtd = nanddev_to_mtd(nand); @@ -937,6 +940,43 @@ static inline void nanddev_io_iter_init(struct nand_device *nand, iter->req.ooblen = min_t(unsigned int, iter->oobbytes_per_page - iter->req.ooboffs, iter->oobleft); + iter->req.continuous = false; +} + +/** + * nand_io_block_iter_init - Initialize a NAND I/O iterator + * @nand: NAND device + * @offs: absolute offset + * @req: MTD request + * @iter: NAND I/O iterator + * + * Initializes a NAND iterator based on the information passed by the MTD + * layer for block jumps (no OOB) + * + * In practice only reads may leverage this iterator. + */ +static inline void nanddev_io_block_iter_init(struct nand_device *nand, + enum nand_page_io_req_type reqtype, + loff_t offs, struct mtd_oob_ops *req, + struct nand_io_iter *iter) +{ + unsigned int offs_in_eb; + + iter->req.type = reqtype; + iter->req.mode = req->mode; + iter->req.dataoffs = nanddev_offs_to_pos(nand, offs, &iter->req.pos); + iter->req.ooboffs = 0; + iter->oobbytes_per_page = 0; + iter->dataleft = req->len; + iter->oobleft = 0; + iter->req.databuf.in = req->datbuf; + offs_in_eb = (nand->memorg.pagesize * iter->req.pos.page) + iter->req.dataoffs; + iter->req.datalen = min_t(unsigned int, + nanddev_eraseblock_size(nand) - offs_in_eb, + iter->dataleft); + iter->req.oobbuf.in = NULL; + iter->req.ooblen = 0; + iter->req.continuous = true; } /** @@ -963,6 +1003,25 @@ static inline void nanddev_io_iter_next_page(struct nand_device *nand, } /** + * nand_io_iter_next_block - Move to the next block + * @nand: NAND device + * @iter: NAND I/O iterator + * + * Updates the @iter to point to the next block. + * No OOB handling available. + */ +static inline void nanddev_io_iter_next_block(struct nand_device *nand, + struct nand_io_iter *iter) +{ + nanddev_pos_next_eraseblock(nand, &iter->req.pos); + iter->dataleft -= iter->req.datalen; + iter->req.databuf.in += iter->req.datalen; + iter->req.dataoffs = 0; + iter->req.datalen = min_t(unsigned int, nanddev_eraseblock_size(nand), + iter->dataleft); +} + +/** * nand_io_iter_end - Should end iteration or not * @nand: NAND device * @iter: NAND I/O iterator @@ -990,13 +1049,28 @@ static inline bool nanddev_io_iter_end(struct nand_device *nand, * @req: MTD I/O request * @iter: NAND I/O iterator * - * Should be used for iterate over pages that are contained in an MTD request. + * Should be used for iterating over pages that are contained in an MTD request. */ #define nanddev_io_for_each_page(nand, type, start, req, iter) \ - for (nanddev_io_iter_init(nand, type, start, req, iter); \ + for (nanddev_io_page_iter_init(nand, type, start, req, iter); \ !nanddev_io_iter_end(nand, iter); \ nanddev_io_iter_next_page(nand, iter)) +/** + * nand_io_for_each_block - Iterate over all NAND pages contained in an MTD I/O + * request, one block at a time + * @nand: NAND device + * @start: start address to read/write from + * @req: MTD I/O request + * @iter: NAND I/O iterator + * + * Should be used for iterating over blocks that are contained in an MTD request. + */ +#define nanddev_io_for_each_block(nand, type, start, req, iter) \ + for (nanddev_io_block_iter_init(nand, type, start, req, iter); \ + !nanddev_io_iter_end(nand, iter); \ + nanddev_io_iter_next_block(nand, iter)) + bool nanddev_isbad(struct nand_device *nand, const struct nand_pos *pos); bool nanddev_isreserved(struct nand_device *nand, const struct nand_pos *pos); int nanddev_markbad(struct nand_device *nand, const struct nand_pos *pos); diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h index 5c19ead60499..0da8a1c7740e 100644 --- a/include/linux/mtd/spinand.h +++ b/include/linux/mtd/spinand.h @@ -62,18 +62,38 @@ SPI_MEM_OP_NO_DUMMY, \ SPI_MEM_OP_NO_DATA) -#define SPINAND_PAGE_READ_FROM_CACHE_OP(fast, addr, ndummy, buf, len) \ - SPI_MEM_OP(SPI_MEM_OP_CMD(fast ? 0x0b : 0x03, 1), \ +#define SPINAND_PAGE_READ_FROM_CACHE_OP(addr, ndummy, buf, len, ...) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0x03, 1), \ SPI_MEM_OP_ADDR(2, addr, 1), \ SPI_MEM_OP_DUMMY(ndummy, 1), \ + SPI_MEM_OP_DATA_IN(len, buf, 1), \ + __VA_OPT__(SPI_MEM_OP_MAX_FREQ(__VA_ARGS__))) + +#define SPINAND_PAGE_READ_FROM_CACHE_FAST_OP(addr, ndummy, buf, len) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0x0b, 1), \ + SPI_MEM_OP_ADDR(2, addr, 1), \ + SPI_MEM_OP_DUMMY(ndummy, 1), \ + SPI_MEM_OP_DATA_IN(len, buf, 1)) + +#define SPINAND_PAGE_READ_FROM_CACHE_OP_3A(addr, ndummy, buf, len) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0x03, 1), \ + SPI_MEM_OP_ADDR(3, addr, 1), \ + SPI_MEM_OP_DUMMY(ndummy, 1), \ SPI_MEM_OP_DATA_IN(len, buf, 1)) -#define SPINAND_PAGE_READ_FROM_CACHE_OP_3A(fast, addr, ndummy, buf, len) \ - SPI_MEM_OP(SPI_MEM_OP_CMD(fast ? 0x0b : 0x03, 1), \ +#define SPINAND_PAGE_READ_FROM_CACHE_FAST_OP_3A(addr, ndummy, buf, len) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0x0b, 1), \ SPI_MEM_OP_ADDR(3, addr, 1), \ SPI_MEM_OP_DUMMY(ndummy, 1), \ SPI_MEM_OP_DATA_IN(len, buf, 1)) +#define SPINAND_PAGE_READ_FROM_CACHE_DTR_OP(addr, ndummy, buf, len, freq) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0x0d, 1), \ + SPI_MEM_DTR_OP_ADDR(2, addr, 1), \ + SPI_MEM_DTR_OP_DUMMY(ndummy, 1), \ + SPI_MEM_DTR_OP_DATA_IN(len, buf, 1), \ + SPI_MEM_OP_MAX_FREQ(freq)) + #define SPINAND_PAGE_READ_FROM_CACHE_X2_OP(addr, ndummy, buf, len) \ SPI_MEM_OP(SPI_MEM_OP_CMD(0x3b, 1), \ SPI_MEM_OP_ADDR(2, addr, 1), \ @@ -86,6 +106,13 @@ SPI_MEM_OP_DUMMY(ndummy, 1), \ SPI_MEM_OP_DATA_IN(len, buf, 2)) +#define SPINAND_PAGE_READ_FROM_CACHE_X2_DTR_OP(addr, ndummy, buf, len, freq) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0x3d, 1), \ + SPI_MEM_DTR_OP_ADDR(2, addr, 1), \ + SPI_MEM_DTR_OP_DUMMY(ndummy, 1), \ + SPI_MEM_DTR_OP_DATA_IN(len, buf, 2), \ + SPI_MEM_OP_MAX_FREQ(freq)) + #define SPINAND_PAGE_READ_FROM_CACHE_X4_OP(addr, ndummy, buf, len) \ SPI_MEM_OP(SPI_MEM_OP_CMD(0x6b, 1), \ SPI_MEM_OP_ADDR(2, addr, 1), \ @@ -98,6 +125,13 @@ SPI_MEM_OP_DUMMY(ndummy, 1), \ SPI_MEM_OP_DATA_IN(len, buf, 4)) +#define SPINAND_PAGE_READ_FROM_CACHE_X4_DTR_OP(addr, ndummy, buf, len, freq) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0x6d, 1), \ + SPI_MEM_DTR_OP_ADDR(2, addr, 1), \ + SPI_MEM_DTR_OP_DUMMY(ndummy, 1), \ + SPI_MEM_DTR_OP_DATA_IN(len, buf, 4), \ + SPI_MEM_OP_MAX_FREQ(freq)) + #define SPINAND_PAGE_READ_FROM_CACHE_DUALIO_OP(addr, ndummy, buf, len) \ SPI_MEM_OP(SPI_MEM_OP_CMD(0xbb, 1), \ SPI_MEM_OP_ADDR(2, addr, 2), \ @@ -110,6 +144,13 @@ SPI_MEM_OP_DUMMY(ndummy, 2), \ SPI_MEM_OP_DATA_IN(len, buf, 2)) +#define SPINAND_PAGE_READ_FROM_CACHE_DUALIO_DTR_OP(addr, ndummy, buf, len, freq) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0xbd, 1), \ + SPI_MEM_DTR_OP_ADDR(2, addr, 2), \ + SPI_MEM_DTR_OP_DUMMY(ndummy, 2), \ + SPI_MEM_DTR_OP_DATA_IN(len, buf, 2), \ + SPI_MEM_OP_MAX_FREQ(freq)) + #define SPINAND_PAGE_READ_FROM_CACHE_QUADIO_OP(addr, ndummy, buf, len) \ SPI_MEM_OP(SPI_MEM_OP_CMD(0xeb, 1), \ SPI_MEM_OP_ADDR(2, addr, 4), \ @@ -122,6 +163,13 @@ SPI_MEM_OP_DUMMY(ndummy, 4), \ SPI_MEM_OP_DATA_IN(len, buf, 4)) +#define SPINAND_PAGE_READ_FROM_CACHE_QUADIO_DTR_OP(addr, ndummy, buf, len, freq) \ + SPI_MEM_OP(SPI_MEM_OP_CMD(0xed, 1), \ + SPI_MEM_DTR_OP_ADDR(2, addr, 4), \ + SPI_MEM_DTR_OP_DUMMY(ndummy, 4), \ + SPI_MEM_DTR_OP_DATA_IN(len, buf, 4), \ + SPI_MEM_OP_MAX_FREQ(freq)) + #define SPINAND_PROG_EXEC_OP(addr) \ SPI_MEM_OP(SPI_MEM_OP_CMD(0x10, 1), \ SPI_MEM_OP_ADDR(3, addr, 1), \ @@ -268,6 +316,7 @@ extern const struct spinand_manufacturer gigadevice_spinand_manufacturer; extern const struct spinand_manufacturer macronix_spinand_manufacturer; extern const struct spinand_manufacturer micron_spinand_manufacturer; extern const struct spinand_manufacturer paragon_spinand_manufacturer; +extern const struct spinand_manufacturer skyhigh_spinand_manufacturer; extern const struct spinand_manufacturer toshiba_spinand_manufacturer; extern const struct spinand_manufacturer winbond_spinand_manufacturer; extern const struct spinand_manufacturer xtx_spinand_manufacturer; @@ -312,6 +361,9 @@ struct spinand_ecc_info { #define SPINAND_HAS_QE_BIT BIT(0) #define SPINAND_HAS_CR_FEAT_BIT BIT(1) +#define SPINAND_HAS_PROG_PLANE_SELECT_BIT BIT(2) +#define SPINAND_HAS_READ_PLANE_SELECT_BIT BIT(3) +#define SPINAND_NO_RAW_ACCESS BIT(4) /** * struct spinand_ondie_ecc_conf - private SPI-NAND on-die ECC engine structure @@ -336,6 +388,7 @@ struct spinand_ondie_ecc_conf { * @op_variants.update_cache: variants of the update-cache operation * @select_target: function used to select a target/die. Required only for * multi-die chips + * @set_cont_read: enable/disable continuous cached reads * * Each SPI NAND manufacturer driver should have a spinand_info table * describing all the chips supported by the driver. @@ -354,6 +407,8 @@ struct spinand_info { } op_variants; int (*select_target)(struct spinand_device *spinand, unsigned int target); + int (*set_cont_read)(struct spinand_device *spinand, + bool enable); }; #define SPINAND_ID(__method, ...) \ @@ -379,6 +434,9 @@ struct spinand_info { #define SPINAND_SELECT_TARGET(__func) \ .select_target = __func, +#define SPINAND_CONT_READ(__set_cont_read) \ + .set_cont_read = __set_cont_read, + #define SPINAND_INFO(__model, __id, __memorg, __eccreq, __op_variants, \ __flags, ...) \ { \ @@ -422,6 +480,12 @@ struct spinand_dirmap { * passed in spi_mem_op be DMA-able, so we can't based the bufs on * the stack * @manufacturer: SPI NAND manufacturer information + * @cont_read_possible: Field filled by the core once the whole system + * configuration is known to tell whether continuous reads are + * suitable to use or not in general with this chip/configuration. + * A per-transfer check must of course be done to ensure it is + * actually relevant to enable this feature. + * @set_cont_read: Enable/disable the continuous read feature * @priv: manufacturer private data */ struct spinand_device { @@ -451,6 +515,10 @@ struct spinand_device { u8 *scratchbuf; const struct spinand_manufacturer *manufacturer; void *priv; + + bool cont_read_possible; + int (*set_cont_read)(struct spinand_device *spinand, + bool enable); }; /** @@ -517,6 +585,7 @@ int spinand_match_and_init(struct spinand_device *spinand, enum spinand_readid_method rdid_method); int spinand_upd_cfg(struct spinand_device *spinand, u8 mask, u8 val); +int spinand_write_reg_op(struct spinand_device *spinand, u8 reg, u8 val); int spinand_select_target(struct spinand_device *spinand, unsigned int target); #endif /* __LINUX_MTD_SPINAND_H */ diff --git a/include/linux/mutex.h b/include/linux/mutex.h index 67edc4ca2bee..2bf91b57591b 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -22,6 +22,8 @@ #include <linux/cleanup.h> #include <linux/mutex_types.h> +struct device; + #ifdef CONFIG_DEBUG_LOCK_ALLOC # define __DEP_MAP_MUTEX_INITIALIZER(lockname) \ , .dep_map = { \ @@ -47,7 +49,6 @@ static inline void mutex_destroy(struct mutex *lock) {} #endif -#ifndef CONFIG_PREEMPT_RT /** * mutex_init - initialize the mutex * @mutex: the mutex to be initialized @@ -63,6 +64,18 @@ do { \ __mutex_init((mutex), #mutex, &__key); \ } while (0) +/** + * mutex_init_with_key - initialize a mutex with a given lockdep key + * @mutex: the mutex to be initialized + * @key: the lockdep key to be associated with the mutex + * + * Initialize the mutex to the unlocked state. + * + * It is not allowed to initialize an already locked mutex. + */ +#define mutex_init_with_key(mutex, key) __mutex_init((mutex), #mutex, (key)) + +#ifndef CONFIG_PREEMPT_RT #define __MUTEX_INITIALIZER(lockname) \ { .owner = ATOMIC_LONG_INIT(0) \ , .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(lockname.wait_lock) \ @@ -109,14 +122,33 @@ do { \ __mutex_rt_init((mutex), name, key); \ } while (0) -#define mutex_init(mutex) \ -do { \ - static struct lock_class_key __key; \ - \ - __mutex_init((mutex), #mutex, &__key); \ -} while (0) #endif /* CONFIG_PREEMPT_RT */ +#ifdef CONFIG_DEBUG_MUTEXES + +int __devm_mutex_init(struct device *dev, struct mutex *lock); + +#else + +static inline int __devm_mutex_init(struct device *dev, struct mutex *lock) +{ + /* + * When CONFIG_DEBUG_MUTEXES is off mutex_destroy() is just a nop so + * no really need to register it in the devm subsystem. + */ + return 0; +} + +#endif + +#define devm_mutex_init(dev, mutex) \ +({ \ + typeof(mutex) mutex_ = (mutex); \ + \ + mutex_init(mutex_); \ + __devm_mutex_init(dev, mutex_); \ +}) + /* * See kernel/locking/mutex.c for detailed documentation of these APIs. * Also see Documentation/locking/mutex-design.rst. diff --git a/include/linux/mv643xx.h b/include/linux/mv643xx.h deleted file mode 100644 index 000b126acfb6..000000000000 --- a/include/linux/mv643xx.h +++ /dev/null @@ -1,921 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * mv643xx.h - MV-643XX Internal registers definition file. - * - * Copyright 2002 Momentum Computer, Inc. - * Author: Matthew Dharm <mdharm@momenco.com> - * Copyright 2002 GALILEO TECHNOLOGY, LTD. - */ -#ifndef __ASM_MV643XX_H -#define __ASM_MV643XX_H - -#include <asm/types.h> -#include <linux/mv643xx_eth.h> -#include <linux/mv643xx_i2c.h> - -/****************************************/ -/* Processor Address Space */ -/****************************************/ - -/* DDR SDRAM BAR and size registers */ - -#define MV64340_CS_0_BASE_ADDR 0x008 -#define MV64340_CS_0_SIZE 0x010 -#define MV64340_CS_1_BASE_ADDR 0x208 -#define MV64340_CS_1_SIZE 0x210 -#define MV64340_CS_2_BASE_ADDR 0x018 -#define MV64340_CS_2_SIZE 0x020 -#define MV64340_CS_3_BASE_ADDR 0x218 -#define MV64340_CS_3_SIZE 0x220 - -/* Devices BAR and size registers */ - -#define MV64340_DEV_CS0_BASE_ADDR 0x028 -#define MV64340_DEV_CS0_SIZE 0x030 -#define MV64340_DEV_CS1_BASE_ADDR 0x228 -#define MV64340_DEV_CS1_SIZE 0x230 -#define MV64340_DEV_CS2_BASE_ADDR 0x248 -#define MV64340_DEV_CS2_SIZE 0x250 -#define MV64340_DEV_CS3_BASE_ADDR 0x038 -#define MV64340_DEV_CS3_SIZE 0x040 -#define MV64340_BOOTCS_BASE_ADDR 0x238 -#define MV64340_BOOTCS_SIZE 0x240 - -/* PCI 0 BAR and size registers */ - -#define MV64340_PCI_0_IO_BASE_ADDR 0x048 -#define MV64340_PCI_0_IO_SIZE 0x050 -#define MV64340_PCI_0_MEMORY0_BASE_ADDR 0x058 -#define MV64340_PCI_0_MEMORY0_SIZE 0x060 -#define MV64340_PCI_0_MEMORY1_BASE_ADDR 0x080 -#define MV64340_PCI_0_MEMORY1_SIZE 0x088 -#define MV64340_PCI_0_MEMORY2_BASE_ADDR 0x258 -#define MV64340_PCI_0_MEMORY2_SIZE 0x260 -#define MV64340_PCI_0_MEMORY3_BASE_ADDR 0x280 -#define MV64340_PCI_0_MEMORY3_SIZE 0x288 - -/* PCI 1 BAR and size registers */ -#define MV64340_PCI_1_IO_BASE_ADDR 0x090 -#define MV64340_PCI_1_IO_SIZE 0x098 -#define MV64340_PCI_1_MEMORY0_BASE_ADDR 0x0a0 -#define MV64340_PCI_1_MEMORY0_SIZE 0x0a8 -#define MV64340_PCI_1_MEMORY1_BASE_ADDR 0x0b0 -#define MV64340_PCI_1_MEMORY1_SIZE 0x0b8 -#define MV64340_PCI_1_MEMORY2_BASE_ADDR 0x2a0 -#define MV64340_PCI_1_MEMORY2_SIZE 0x2a8 -#define MV64340_PCI_1_MEMORY3_BASE_ADDR 0x2b0 -#define MV64340_PCI_1_MEMORY3_SIZE 0x2b8 - -/* SRAM base address */ -#define MV64340_INTEGRATED_SRAM_BASE_ADDR 0x268 - -/* internal registers space base address */ -#define MV64340_INTERNAL_SPACE_BASE_ADDR 0x068 - -/* Enables the CS , DEV_CS , PCI 0 and PCI 1 - windows above */ -#define MV64340_BASE_ADDR_ENABLE 0x278 - -/****************************************/ -/* PCI remap registers */ -/****************************************/ - /* PCI 0 */ -#define MV64340_PCI_0_IO_ADDR_REMAP 0x0f0 -#define MV64340_PCI_0_MEMORY0_LOW_ADDR_REMAP 0x0f8 -#define MV64340_PCI_0_MEMORY0_HIGH_ADDR_REMAP 0x320 -#define MV64340_PCI_0_MEMORY1_LOW_ADDR_REMAP 0x100 -#define MV64340_PCI_0_MEMORY1_HIGH_ADDR_REMAP 0x328 -#define MV64340_PCI_0_MEMORY2_LOW_ADDR_REMAP 0x2f8 -#define MV64340_PCI_0_MEMORY2_HIGH_ADDR_REMAP 0x330 -#define MV64340_PCI_0_MEMORY3_LOW_ADDR_REMAP 0x300 -#define MV64340_PCI_0_MEMORY3_HIGH_ADDR_REMAP 0x338 - /* PCI 1 */ -#define MV64340_PCI_1_IO_ADDR_REMAP 0x108 -#define MV64340_PCI_1_MEMORY0_LOW_ADDR_REMAP 0x110 -#define MV64340_PCI_1_MEMORY0_HIGH_ADDR_REMAP 0x340 -#define MV64340_PCI_1_MEMORY1_LOW_ADDR_REMAP 0x118 -#define MV64340_PCI_1_MEMORY1_HIGH_ADDR_REMAP 0x348 -#define MV64340_PCI_1_MEMORY2_LOW_ADDR_REMAP 0x310 -#define MV64340_PCI_1_MEMORY2_HIGH_ADDR_REMAP 0x350 -#define MV64340_PCI_1_MEMORY3_LOW_ADDR_REMAP 0x318 -#define MV64340_PCI_1_MEMORY3_HIGH_ADDR_REMAP 0x358 - -#define MV64340_CPU_PCI_0_HEADERS_RETARGET_CONTROL 0x3b0 -#define MV64340_CPU_PCI_0_HEADERS_RETARGET_BASE 0x3b8 -#define MV64340_CPU_PCI_1_HEADERS_RETARGET_CONTROL 0x3c0 -#define MV64340_CPU_PCI_1_HEADERS_RETARGET_BASE 0x3c8 -#define MV64340_CPU_GE_HEADERS_RETARGET_CONTROL 0x3d0 -#define MV64340_CPU_GE_HEADERS_RETARGET_BASE 0x3d8 -#define MV64340_CPU_IDMA_HEADERS_RETARGET_CONTROL 0x3e0 -#define MV64340_CPU_IDMA_HEADERS_RETARGET_BASE 0x3e8 - -/****************************************/ -/* CPU Control Registers */ -/****************************************/ - -#define MV64340_CPU_CONFIG 0x000 -#define MV64340_CPU_MODE 0x120 -#define MV64340_CPU_MASTER_CONTROL 0x160 -#define MV64340_CPU_CROSS_BAR_CONTROL_LOW 0x150 -#define MV64340_CPU_CROSS_BAR_CONTROL_HIGH 0x158 -#define MV64340_CPU_CROSS_BAR_TIMEOUT 0x168 - -/****************************************/ -/* SMP RegisterS */ -/****************************************/ - -#define MV64340_SMP_WHO_AM_I 0x200 -#define MV64340_SMP_CPU0_DOORBELL 0x214 -#define MV64340_SMP_CPU0_DOORBELL_CLEAR 0x21C -#define MV64340_SMP_CPU1_DOORBELL 0x224 -#define MV64340_SMP_CPU1_DOORBELL_CLEAR 0x22C -#define MV64340_SMP_CPU0_DOORBELL_MASK 0x234 -#define MV64340_SMP_CPU1_DOORBELL_MASK 0x23C -#define MV64340_SMP_SEMAPHOR0 0x244 -#define MV64340_SMP_SEMAPHOR1 0x24c -#define MV64340_SMP_SEMAPHOR2 0x254 -#define MV64340_SMP_SEMAPHOR3 0x25c -#define MV64340_SMP_SEMAPHOR4 0x264 -#define MV64340_SMP_SEMAPHOR5 0x26c -#define MV64340_SMP_SEMAPHOR6 0x274 -#define MV64340_SMP_SEMAPHOR7 0x27c - -/****************************************/ -/* CPU Sync Barrier Register */ -/****************************************/ - -#define MV64340_CPU_0_SYNC_BARRIER_TRIGGER 0x0c0 -#define MV64340_CPU_0_SYNC_BARRIER_VIRTUAL 0x0c8 -#define MV64340_CPU_1_SYNC_BARRIER_TRIGGER 0x0d0 -#define MV64340_CPU_1_SYNC_BARRIER_VIRTUAL 0x0d8 - -/****************************************/ -/* CPU Access Protect */ -/****************************************/ - -#define MV64340_CPU_PROTECT_WINDOW_0_BASE_ADDR 0x180 -#define MV64340_CPU_PROTECT_WINDOW_0_SIZE 0x188 -#define MV64340_CPU_PROTECT_WINDOW_1_BASE_ADDR 0x190 -#define MV64340_CPU_PROTECT_WINDOW_1_SIZE 0x198 -#define MV64340_CPU_PROTECT_WINDOW_2_BASE_ADDR 0x1a0 -#define MV64340_CPU_PROTECT_WINDOW_2_SIZE 0x1a8 -#define MV64340_CPU_PROTECT_WINDOW_3_BASE_ADDR 0x1b0 -#define MV64340_CPU_PROTECT_WINDOW_3_SIZE 0x1b8 - - -/****************************************/ -/* CPU Error Report */ -/****************************************/ - -#define MV64340_CPU_ERROR_ADDR_LOW 0x070 -#define MV64340_CPU_ERROR_ADDR_HIGH 0x078 -#define MV64340_CPU_ERROR_DATA_LOW 0x128 -#define MV64340_CPU_ERROR_DATA_HIGH 0x130 -#define MV64340_CPU_ERROR_PARITY 0x138 -#define MV64340_CPU_ERROR_CAUSE 0x140 -#define MV64340_CPU_ERROR_MASK 0x148 - -/****************************************/ -/* CPU Interface Debug Registers */ -/****************************************/ - -#define MV64340_PUNIT_SLAVE_DEBUG_LOW 0x360 -#define MV64340_PUNIT_SLAVE_DEBUG_HIGH 0x368 -#define MV64340_PUNIT_MASTER_DEBUG_LOW 0x370 -#define MV64340_PUNIT_MASTER_DEBUG_HIGH 0x378 -#define MV64340_PUNIT_MMASK 0x3e4 - -/****************************************/ -/* Integrated SRAM Registers */ -/****************************************/ - -#define MV64340_SRAM_CONFIG 0x380 -#define MV64340_SRAM_TEST_MODE 0X3F4 -#define MV64340_SRAM_ERROR_CAUSE 0x388 -#define MV64340_SRAM_ERROR_ADDR 0x390 -#define MV64340_SRAM_ERROR_ADDR_HIGH 0X3F8 -#define MV64340_SRAM_ERROR_DATA_LOW 0x398 -#define MV64340_SRAM_ERROR_DATA_HIGH 0x3a0 -#define MV64340_SRAM_ERROR_DATA_PARITY 0x3a8 - -/****************************************/ -/* SDRAM Configuration */ -/****************************************/ - -#define MV64340_SDRAM_CONFIG 0x1400 -#define MV64340_D_UNIT_CONTROL_LOW 0x1404 -#define MV64340_D_UNIT_CONTROL_HIGH 0x1424 -#define MV64340_SDRAM_TIMING_CONTROL_LOW 0x1408 -#define MV64340_SDRAM_TIMING_CONTROL_HIGH 0x140c -#define MV64340_SDRAM_ADDR_CONTROL 0x1410 -#define MV64340_SDRAM_OPEN_PAGES_CONTROL 0x1414 -#define MV64340_SDRAM_OPERATION 0x1418 -#define MV64340_SDRAM_MODE 0x141c -#define MV64340_EXTENDED_DRAM_MODE 0x1420 -#define MV64340_SDRAM_CROSS_BAR_CONTROL_LOW 0x1430 -#define MV64340_SDRAM_CROSS_BAR_CONTROL_HIGH 0x1434 -#define MV64340_SDRAM_CROSS_BAR_TIMEOUT 0x1438 -#define MV64340_SDRAM_ADDR_CTRL_PADS_CALIBRATION 0x14c0 -#define MV64340_SDRAM_DATA_PADS_CALIBRATION 0x14c4 - -/****************************************/ -/* SDRAM Error Report */ -/****************************************/ - -#define MV64340_SDRAM_ERROR_DATA_LOW 0x1444 -#define MV64340_SDRAM_ERROR_DATA_HIGH 0x1440 -#define MV64340_SDRAM_ERROR_ADDR 0x1450 -#define MV64340_SDRAM_RECEIVED_ECC 0x1448 -#define MV64340_SDRAM_CALCULATED_ECC 0x144c -#define MV64340_SDRAM_ECC_CONTROL 0x1454 -#define MV64340_SDRAM_ECC_ERROR_COUNTER 0x1458 - -/******************************************/ -/* Controlled Delay Line (CDL) Registers */ -/******************************************/ - -#define MV64340_DFCDL_CONFIG0 0x1480 -#define MV64340_DFCDL_CONFIG1 0x1484 -#define MV64340_DLL_WRITE 0x1488 -#define MV64340_DLL_READ 0x148c -#define MV64340_SRAM_ADDR 0x1490 -#define MV64340_SRAM_DATA0 0x1494 -#define MV64340_SRAM_DATA1 0x1498 -#define MV64340_SRAM_DATA2 0x149c -#define MV64340_DFCL_PROBE 0x14a0 - -/******************************************/ -/* Debug Registers */ -/******************************************/ - -#define MV64340_DUNIT_DEBUG_LOW 0x1460 -#define MV64340_DUNIT_DEBUG_HIGH 0x1464 -#define MV64340_DUNIT_MMASK 0X1b40 - -/****************************************/ -/* Device Parameters */ -/****************************************/ - -#define MV64340_DEVICE_BANK0_PARAMETERS 0x45c -#define MV64340_DEVICE_BANK1_PARAMETERS 0x460 -#define MV64340_DEVICE_BANK2_PARAMETERS 0x464 -#define MV64340_DEVICE_BANK3_PARAMETERS 0x468 -#define MV64340_DEVICE_BOOT_BANK_PARAMETERS 0x46c -#define MV64340_DEVICE_INTERFACE_CONTROL 0x4c0 -#define MV64340_DEVICE_INTERFACE_CROSS_BAR_CONTROL_LOW 0x4c8 -#define MV64340_DEVICE_INTERFACE_CROSS_BAR_CONTROL_HIGH 0x4cc -#define MV64340_DEVICE_INTERFACE_CROSS_BAR_TIMEOUT 0x4c4 - -/****************************************/ -/* Device interrupt registers */ -/****************************************/ - -#define MV64340_DEVICE_INTERRUPT_CAUSE 0x4d0 -#define MV64340_DEVICE_INTERRUPT_MASK 0x4d4 -#define MV64340_DEVICE_ERROR_ADDR 0x4d8 -#define MV64340_DEVICE_ERROR_DATA 0x4dc -#define MV64340_DEVICE_ERROR_PARITY 0x4e0 - -/****************************************/ -/* Device debug registers */ -/****************************************/ - -#define MV64340_DEVICE_DEBUG_LOW 0x4e4 -#define MV64340_DEVICE_DEBUG_HIGH 0x4e8 -#define MV64340_RUNIT_MMASK 0x4f0 - -/****************************************/ -/* PCI Slave Address Decoding registers */ -/****************************************/ - -#define MV64340_PCI_0_CS_0_BANK_SIZE 0xc08 -#define MV64340_PCI_1_CS_0_BANK_SIZE 0xc88 -#define MV64340_PCI_0_CS_1_BANK_SIZE 0xd08 -#define MV64340_PCI_1_CS_1_BANK_SIZE 0xd88 -#define MV64340_PCI_0_CS_2_BANK_SIZE 0xc0c -#define MV64340_PCI_1_CS_2_BANK_SIZE 0xc8c -#define MV64340_PCI_0_CS_3_BANK_SIZE 0xd0c -#define MV64340_PCI_1_CS_3_BANK_SIZE 0xd8c -#define MV64340_PCI_0_DEVCS_0_BANK_SIZE 0xc10 -#define MV64340_PCI_1_DEVCS_0_BANK_SIZE 0xc90 -#define MV64340_PCI_0_DEVCS_1_BANK_SIZE 0xd10 -#define MV64340_PCI_1_DEVCS_1_BANK_SIZE 0xd90 -#define MV64340_PCI_0_DEVCS_2_BANK_SIZE 0xd18 -#define MV64340_PCI_1_DEVCS_2_BANK_SIZE 0xd98 -#define MV64340_PCI_0_DEVCS_3_BANK_SIZE 0xc14 -#define MV64340_PCI_1_DEVCS_3_BANK_SIZE 0xc94 -#define MV64340_PCI_0_DEVCS_BOOT_BANK_SIZE 0xd14 -#define MV64340_PCI_1_DEVCS_BOOT_BANK_SIZE 0xd94 -#define MV64340_PCI_0_P2P_MEM0_BAR_SIZE 0xd1c -#define MV64340_PCI_1_P2P_MEM0_BAR_SIZE 0xd9c -#define MV64340_PCI_0_P2P_MEM1_BAR_SIZE 0xd20 -#define MV64340_PCI_1_P2P_MEM1_BAR_SIZE 0xda0 -#define MV64340_PCI_0_P2P_I_O_BAR_SIZE 0xd24 -#define MV64340_PCI_1_P2P_I_O_BAR_SIZE 0xda4 -#define MV64340_PCI_0_CPU_BAR_SIZE 0xd28 -#define MV64340_PCI_1_CPU_BAR_SIZE 0xda8 -#define MV64340_PCI_0_INTERNAL_SRAM_BAR_SIZE 0xe00 -#define MV64340_PCI_1_INTERNAL_SRAM_BAR_SIZE 0xe80 -#define MV64340_PCI_0_EXPANSION_ROM_BAR_SIZE 0xd2c -#define MV64340_PCI_1_EXPANSION_ROM_BAR_SIZE 0xd9c -#define MV64340_PCI_0_BASE_ADDR_REG_ENABLE 0xc3c -#define MV64340_PCI_1_BASE_ADDR_REG_ENABLE 0xcbc -#define MV64340_PCI_0_CS_0_BASE_ADDR_REMAP 0xc48 -#define MV64340_PCI_1_CS_0_BASE_ADDR_REMAP 0xcc8 -#define MV64340_PCI_0_CS_1_BASE_ADDR_REMAP 0xd48 -#define MV64340_PCI_1_CS_1_BASE_ADDR_REMAP 0xdc8 -#define MV64340_PCI_0_CS_2_BASE_ADDR_REMAP 0xc4c -#define MV64340_PCI_1_CS_2_BASE_ADDR_REMAP 0xccc -#define MV64340_PCI_0_CS_3_BASE_ADDR_REMAP 0xd4c -#define MV64340_PCI_1_CS_3_BASE_ADDR_REMAP 0xdcc -#define MV64340_PCI_0_CS_0_BASE_HIGH_ADDR_REMAP 0xF04 -#define MV64340_PCI_1_CS_0_BASE_HIGH_ADDR_REMAP 0xF84 -#define MV64340_PCI_0_CS_1_BASE_HIGH_ADDR_REMAP 0xF08 -#define MV64340_PCI_1_CS_1_BASE_HIGH_ADDR_REMAP 0xF88 -#define MV64340_PCI_0_CS_2_BASE_HIGH_ADDR_REMAP 0xF0C -#define MV64340_PCI_1_CS_2_BASE_HIGH_ADDR_REMAP 0xF8C -#define MV64340_PCI_0_CS_3_BASE_HIGH_ADDR_REMAP 0xF10 -#define MV64340_PCI_1_CS_3_BASE_HIGH_ADDR_REMAP 0xF90 -#define MV64340_PCI_0_DEVCS_0_BASE_ADDR_REMAP 0xc50 -#define MV64340_PCI_1_DEVCS_0_BASE_ADDR_REMAP 0xcd0 -#define MV64340_PCI_0_DEVCS_1_BASE_ADDR_REMAP 0xd50 -#define MV64340_PCI_1_DEVCS_1_BASE_ADDR_REMAP 0xdd0 -#define MV64340_PCI_0_DEVCS_2_BASE_ADDR_REMAP 0xd58 -#define MV64340_PCI_1_DEVCS_2_BASE_ADDR_REMAP 0xdd8 -#define MV64340_PCI_0_DEVCS_3_BASE_ADDR_REMAP 0xc54 -#define MV64340_PCI_1_DEVCS_3_BASE_ADDR_REMAP 0xcd4 -#define MV64340_PCI_0_DEVCS_BOOTCS_BASE_ADDR_REMAP 0xd54 -#define MV64340_PCI_1_DEVCS_BOOTCS_BASE_ADDR_REMAP 0xdd4 -#define MV64340_PCI_0_P2P_MEM0_BASE_ADDR_REMAP_LOW 0xd5c -#define MV64340_PCI_1_P2P_MEM0_BASE_ADDR_REMAP_LOW 0xddc -#define MV64340_PCI_0_P2P_MEM0_BASE_ADDR_REMAP_HIGH 0xd60 -#define MV64340_PCI_1_P2P_MEM0_BASE_ADDR_REMAP_HIGH 0xde0 -#define MV64340_PCI_0_P2P_MEM1_BASE_ADDR_REMAP_LOW 0xd64 -#define MV64340_PCI_1_P2P_MEM1_BASE_ADDR_REMAP_LOW 0xde4 -#define MV64340_PCI_0_P2P_MEM1_BASE_ADDR_REMAP_HIGH 0xd68 -#define MV64340_PCI_1_P2P_MEM1_BASE_ADDR_REMAP_HIGH 0xde8 -#define MV64340_PCI_0_P2P_I_O_BASE_ADDR_REMAP 0xd6c -#define MV64340_PCI_1_P2P_I_O_BASE_ADDR_REMAP 0xdec -#define MV64340_PCI_0_CPU_BASE_ADDR_REMAP_LOW 0xd70 -#define MV64340_PCI_1_CPU_BASE_ADDR_REMAP_LOW 0xdf0 -#define MV64340_PCI_0_CPU_BASE_ADDR_REMAP_HIGH 0xd74 -#define MV64340_PCI_1_CPU_BASE_ADDR_REMAP_HIGH 0xdf4 -#define MV64340_PCI_0_INTEGRATED_SRAM_BASE_ADDR_REMAP 0xf00 -#define MV64340_PCI_1_INTEGRATED_SRAM_BASE_ADDR_REMAP 0xf80 -#define MV64340_PCI_0_EXPANSION_ROM_BASE_ADDR_REMAP 0xf38 -#define MV64340_PCI_1_EXPANSION_ROM_BASE_ADDR_REMAP 0xfb8 -#define MV64340_PCI_0_ADDR_DECODE_CONTROL 0xd3c -#define MV64340_PCI_1_ADDR_DECODE_CONTROL 0xdbc -#define MV64340_PCI_0_HEADERS_RETARGET_CONTROL 0xF40 -#define MV64340_PCI_1_HEADERS_RETARGET_CONTROL 0xFc0 -#define MV64340_PCI_0_HEADERS_RETARGET_BASE 0xF44 -#define MV64340_PCI_1_HEADERS_RETARGET_BASE 0xFc4 -#define MV64340_PCI_0_HEADERS_RETARGET_HIGH 0xF48 -#define MV64340_PCI_1_HEADERS_RETARGET_HIGH 0xFc8 - -/***********************************/ -/* PCI Control Register Map */ -/***********************************/ - -#define MV64340_PCI_0_DLL_STATUS_AND_COMMAND 0x1d20 -#define MV64340_PCI_1_DLL_STATUS_AND_COMMAND 0x1da0 -#define MV64340_PCI_0_MPP_PADS_DRIVE_CONTROL 0x1d1C -#define MV64340_PCI_1_MPP_PADS_DRIVE_CONTROL 0x1d9C -#define MV64340_PCI_0_COMMAND 0xc00 -#define MV64340_PCI_1_COMMAND 0xc80 -#define MV64340_PCI_0_MODE 0xd00 -#define MV64340_PCI_1_MODE 0xd80 -#define MV64340_PCI_0_RETRY 0xc04 -#define MV64340_PCI_1_RETRY 0xc84 -#define MV64340_PCI_0_READ_BUFFER_DISCARD_TIMER 0xd04 -#define MV64340_PCI_1_READ_BUFFER_DISCARD_TIMER 0xd84 -#define MV64340_PCI_0_MSI_TRIGGER_TIMER 0xc38 -#define MV64340_PCI_1_MSI_TRIGGER_TIMER 0xcb8 -#define MV64340_PCI_0_ARBITER_CONTROL 0x1d00 -#define MV64340_PCI_1_ARBITER_CONTROL 0x1d80 -#define MV64340_PCI_0_CROSS_BAR_CONTROL_LOW 0x1d08 -#define MV64340_PCI_1_CROSS_BAR_CONTROL_LOW 0x1d88 -#define MV64340_PCI_0_CROSS_BAR_CONTROL_HIGH 0x1d0c -#define MV64340_PCI_1_CROSS_BAR_CONTROL_HIGH 0x1d8c -#define MV64340_PCI_0_CROSS_BAR_TIMEOUT 0x1d04 -#define MV64340_PCI_1_CROSS_BAR_TIMEOUT 0x1d84 -#define MV64340_PCI_0_SYNC_BARRIER_TRIGGER_REG 0x1D18 -#define MV64340_PCI_1_SYNC_BARRIER_TRIGGER_REG 0x1D98 -#define MV64340_PCI_0_SYNC_BARRIER_VIRTUAL_REG 0x1d10 -#define MV64340_PCI_1_SYNC_BARRIER_VIRTUAL_REG 0x1d90 -#define MV64340_PCI_0_P2P_CONFIG 0x1d14 -#define MV64340_PCI_1_P2P_CONFIG 0x1d94 - -#define MV64340_PCI_0_ACCESS_CONTROL_BASE_0_LOW 0x1e00 -#define MV64340_PCI_0_ACCESS_CONTROL_BASE_0_HIGH 0x1e04 -#define MV64340_PCI_0_ACCESS_CONTROL_SIZE_0 0x1e08 -#define MV64340_PCI_0_ACCESS_CONTROL_BASE_1_LOW 0x1e10 -#define MV64340_PCI_0_ACCESS_CONTROL_BASE_1_HIGH 0x1e14 -#define MV64340_PCI_0_ACCESS_CONTROL_SIZE_1 0x1e18 -#define MV64340_PCI_0_ACCESS_CONTROL_BASE_2_LOW 0x1e20 -#define MV64340_PCI_0_ACCESS_CONTROL_BASE_2_HIGH 0x1e24 -#define MV64340_PCI_0_ACCESS_CONTROL_SIZE_2 0x1e28 -#define MV64340_PCI_0_ACCESS_CONTROL_BASE_3_LOW 0x1e30 -#define MV64340_PCI_0_ACCESS_CONTROL_BASE_3_HIGH 0x1e34 -#define MV64340_PCI_0_ACCESS_CONTROL_SIZE_3 0x1e38 -#define MV64340_PCI_0_ACCESS_CONTROL_BASE_4_LOW 0x1e40 -#define MV64340_PCI_0_ACCESS_CONTROL_BASE_4_HIGH 0x1e44 -#define MV64340_PCI_0_ACCESS_CONTROL_SIZE_4 0x1e48 -#define MV64340_PCI_0_ACCESS_CONTROL_BASE_5_LOW 0x1e50 -#define MV64340_PCI_0_ACCESS_CONTROL_BASE_5_HIGH 0x1e54 -#define MV64340_PCI_0_ACCESS_CONTROL_SIZE_5 0x1e58 - -#define MV64340_PCI_1_ACCESS_CONTROL_BASE_0_LOW 0x1e80 -#define MV64340_PCI_1_ACCESS_CONTROL_BASE_0_HIGH 0x1e84 -#define MV64340_PCI_1_ACCESS_CONTROL_SIZE_0 0x1e88 -#define MV64340_PCI_1_ACCESS_CONTROL_BASE_1_LOW 0x1e90 -#define MV64340_PCI_1_ACCESS_CONTROL_BASE_1_HIGH 0x1e94 -#define MV64340_PCI_1_ACCESS_CONTROL_SIZE_1 0x1e98 -#define MV64340_PCI_1_ACCESS_CONTROL_BASE_2_LOW 0x1ea0 -#define MV64340_PCI_1_ACCESS_CONTROL_BASE_2_HIGH 0x1ea4 -#define MV64340_PCI_1_ACCESS_CONTROL_SIZE_2 0x1ea8 -#define MV64340_PCI_1_ACCESS_CONTROL_BASE_3_LOW 0x1eb0 -#define MV64340_PCI_1_ACCESS_CONTROL_BASE_3_HIGH 0x1eb4 -#define MV64340_PCI_1_ACCESS_CONTROL_SIZE_3 0x1eb8 -#define MV64340_PCI_1_ACCESS_CONTROL_BASE_4_LOW 0x1ec0 -#define MV64340_PCI_1_ACCESS_CONTROL_BASE_4_HIGH 0x1ec4 -#define MV64340_PCI_1_ACCESS_CONTROL_SIZE_4 0x1ec8 -#define MV64340_PCI_1_ACCESS_CONTROL_BASE_5_LOW 0x1ed0 -#define MV64340_PCI_1_ACCESS_CONTROL_BASE_5_HIGH 0x1ed4 -#define MV64340_PCI_1_ACCESS_CONTROL_SIZE_5 0x1ed8 - -/****************************************/ -/* PCI Configuration Access Registers */ -/****************************************/ - -#define MV64340_PCI_0_CONFIG_ADDR 0xcf8 -#define MV64340_PCI_0_CONFIG_DATA_VIRTUAL_REG 0xcfc -#define MV64340_PCI_1_CONFIG_ADDR 0xc78 -#define MV64340_PCI_1_CONFIG_DATA_VIRTUAL_REG 0xc7c -#define MV64340_PCI_0_INTERRUPT_ACKNOWLEDGE_VIRTUAL_REG 0xc34 -#define MV64340_PCI_1_INTERRUPT_ACKNOWLEDGE_VIRTUAL_REG 0xcb4 - -/****************************************/ -/* PCI Error Report Registers */ -/****************************************/ - -#define MV64340_PCI_0_SERR_MASK 0xc28 -#define MV64340_PCI_1_SERR_MASK 0xca8 -#define MV64340_PCI_0_ERROR_ADDR_LOW 0x1d40 -#define MV64340_PCI_1_ERROR_ADDR_LOW 0x1dc0 -#define MV64340_PCI_0_ERROR_ADDR_HIGH 0x1d44 -#define MV64340_PCI_1_ERROR_ADDR_HIGH 0x1dc4 -#define MV64340_PCI_0_ERROR_ATTRIBUTE 0x1d48 -#define MV64340_PCI_1_ERROR_ATTRIBUTE 0x1dc8 -#define MV64340_PCI_0_ERROR_COMMAND 0x1d50 -#define MV64340_PCI_1_ERROR_COMMAND 0x1dd0 -#define MV64340_PCI_0_ERROR_CAUSE 0x1d58 -#define MV64340_PCI_1_ERROR_CAUSE 0x1dd8 -#define MV64340_PCI_0_ERROR_MASK 0x1d5c -#define MV64340_PCI_1_ERROR_MASK 0x1ddc - -/****************************************/ -/* PCI Debug Registers */ -/****************************************/ - -#define MV64340_PCI_0_MMASK 0X1D24 -#define MV64340_PCI_1_MMASK 0X1DA4 - -/*********************************************/ -/* PCI Configuration, Function 0, Registers */ -/*********************************************/ - -#define MV64340_PCI_DEVICE_AND_VENDOR_ID 0x000 -#define MV64340_PCI_STATUS_AND_COMMAND 0x004 -#define MV64340_PCI_CLASS_CODE_AND_REVISION_ID 0x008 -#define MV64340_PCI_BIST_HEADER_TYPE_LATENCY_TIMER_CACHE_LINE 0x00C - -#define MV64340_PCI_SCS_0_BASE_ADDR_LOW 0x010 -#define MV64340_PCI_SCS_0_BASE_ADDR_HIGH 0x014 -#define MV64340_PCI_SCS_1_BASE_ADDR_LOW 0x018 -#define MV64340_PCI_SCS_1_BASE_ADDR_HIGH 0x01C -#define MV64340_PCI_INTERNAL_REG_MEM_MAPPED_BASE_ADDR_LOW 0x020 -#define MV64340_PCI_INTERNAL_REG_MEM_MAPPED_BASE_ADDR_HIGH 0x024 -#define MV64340_PCI_SUBSYSTEM_ID_AND_SUBSYSTEM_VENDOR_ID 0x02c -#define MV64340_PCI_EXPANSION_ROM_BASE_ADDR_REG 0x030 -#define MV64340_PCI_CAPABILTY_LIST_POINTER 0x034 -#define MV64340_PCI_INTERRUPT_PIN_AND_LINE 0x03C - /* capability list */ -#define MV64340_PCI_POWER_MANAGEMENT_CAPABILITY 0x040 -#define MV64340_PCI_POWER_MANAGEMENT_STATUS_AND_CONTROL 0x044 -#define MV64340_PCI_VPD_ADDR 0x048 -#define MV64340_PCI_VPD_DATA 0x04c -#define MV64340_PCI_MSI_MESSAGE_CONTROL 0x050 -#define MV64340_PCI_MSI_MESSAGE_ADDR 0x054 -#define MV64340_PCI_MSI_MESSAGE_UPPER_ADDR 0x058 -#define MV64340_PCI_MSI_MESSAGE_DATA 0x05c -#define MV64340_PCI_X_COMMAND 0x060 -#define MV64340_PCI_X_STATUS 0x064 -#define MV64340_PCI_COMPACT_PCI_HOT_SWAP 0x068 - -/***********************************************/ -/* PCI Configuration, Function 1, Registers */ -/***********************************************/ - -#define MV64340_PCI_SCS_2_BASE_ADDR_LOW 0x110 -#define MV64340_PCI_SCS_2_BASE_ADDR_HIGH 0x114 -#define MV64340_PCI_SCS_3_BASE_ADDR_LOW 0x118 -#define MV64340_PCI_SCS_3_BASE_ADDR_HIGH 0x11c -#define MV64340_PCI_INTERNAL_SRAM_BASE_ADDR_LOW 0x120 -#define MV64340_PCI_INTERNAL_SRAM_BASE_ADDR_HIGH 0x124 - -/***********************************************/ -/* PCI Configuration, Function 2, Registers */ -/***********************************************/ - -#define MV64340_PCI_DEVCS_0_BASE_ADDR_LOW 0x210 -#define MV64340_PCI_DEVCS_0_BASE_ADDR_HIGH 0x214 -#define MV64340_PCI_DEVCS_1_BASE_ADDR_LOW 0x218 -#define MV64340_PCI_DEVCS_1_BASE_ADDR_HIGH 0x21c -#define MV64340_PCI_DEVCS_2_BASE_ADDR_LOW 0x220 -#define MV64340_PCI_DEVCS_2_BASE_ADDR_HIGH 0x224 - -/***********************************************/ -/* PCI Configuration, Function 3, Registers */ -/***********************************************/ - -#define MV64340_PCI_DEVCS_3_BASE_ADDR_LOW 0x310 -#define MV64340_PCI_DEVCS_3_BASE_ADDR_HIGH 0x314 -#define MV64340_PCI_BOOT_CS_BASE_ADDR_LOW 0x318 -#define MV64340_PCI_BOOT_CS_BASE_ADDR_HIGH 0x31c -#define MV64340_PCI_CPU_BASE_ADDR_LOW 0x220 -#define MV64340_PCI_CPU_BASE_ADDR_HIGH 0x224 - -/***********************************************/ -/* PCI Configuration, Function 4, Registers */ -/***********************************************/ - -#define MV64340_PCI_P2P_MEM0_BASE_ADDR_LOW 0x410 -#define MV64340_PCI_P2P_MEM0_BASE_ADDR_HIGH 0x414 -#define MV64340_PCI_P2P_MEM1_BASE_ADDR_LOW 0x418 -#define MV64340_PCI_P2P_MEM1_BASE_ADDR_HIGH 0x41c -#define MV64340_PCI_P2P_I_O_BASE_ADDR 0x420 -#define MV64340_PCI_INTERNAL_REGS_I_O_MAPPED_BASE_ADDR 0x424 - -/****************************************/ -/* Messaging Unit Registers (I20) */ -/****************************************/ - -#define MV64340_I2O_INBOUND_MESSAGE_REG0_PCI_0_SIDE 0x010 -#define MV64340_I2O_INBOUND_MESSAGE_REG1_PCI_0_SIDE 0x014 -#define MV64340_I2O_OUTBOUND_MESSAGE_REG0_PCI_0_SIDE 0x018 -#define MV64340_I2O_OUTBOUND_MESSAGE_REG1_PCI_0_SIDE 0x01C -#define MV64340_I2O_INBOUND_DOORBELL_REG_PCI_0_SIDE 0x020 -#define MV64340_I2O_INBOUND_INTERRUPT_CAUSE_REG_PCI_0_SIDE 0x024 -#define MV64340_I2O_INBOUND_INTERRUPT_MASK_REG_PCI_0_SIDE 0x028 -#define MV64340_I2O_OUTBOUND_DOORBELL_REG_PCI_0_SIDE 0x02C -#define MV64340_I2O_OUTBOUND_INTERRUPT_CAUSE_REG_PCI_0_SIDE 0x030 -#define MV64340_I2O_OUTBOUND_INTERRUPT_MASK_REG_PCI_0_SIDE 0x034 -#define MV64340_I2O_INBOUND_QUEUE_PORT_VIRTUAL_REG_PCI_0_SIDE 0x040 -#define MV64340_I2O_OUTBOUND_QUEUE_PORT_VIRTUAL_REG_PCI_0_SIDE 0x044 -#define MV64340_I2O_QUEUE_CONTROL_REG_PCI_0_SIDE 0x050 -#define MV64340_I2O_QUEUE_BASE_ADDR_REG_PCI_0_SIDE 0x054 -#define MV64340_I2O_INBOUND_FREE_HEAD_POINTER_REG_PCI_0_SIDE 0x060 -#define MV64340_I2O_INBOUND_FREE_TAIL_POINTER_REG_PCI_0_SIDE 0x064 -#define MV64340_I2O_INBOUND_POST_HEAD_POINTER_REG_PCI_0_SIDE 0x068 -#define MV64340_I2O_INBOUND_POST_TAIL_POINTER_REG_PCI_0_SIDE 0x06C -#define MV64340_I2O_OUTBOUND_FREE_HEAD_POINTER_REG_PCI_0_SIDE 0x070 -#define MV64340_I2O_OUTBOUND_FREE_TAIL_POINTER_REG_PCI_0_SIDE 0x074 -#define MV64340_I2O_OUTBOUND_POST_HEAD_POINTER_REG_PCI_0_SIDE 0x0F8 -#define MV64340_I2O_OUTBOUND_POST_TAIL_POINTER_REG_PCI_0_SIDE 0x0FC - -#define MV64340_I2O_INBOUND_MESSAGE_REG0_PCI_1_SIDE 0x090 -#define MV64340_I2O_INBOUND_MESSAGE_REG1_PCI_1_SIDE 0x094 -#define MV64340_I2O_OUTBOUND_MESSAGE_REG0_PCI_1_SIDE 0x098 -#define MV64340_I2O_OUTBOUND_MESSAGE_REG1_PCI_1_SIDE 0x09C -#define MV64340_I2O_INBOUND_DOORBELL_REG_PCI_1_SIDE 0x0A0 -#define MV64340_I2O_INBOUND_INTERRUPT_CAUSE_REG_PCI_1_SIDE 0x0A4 -#define MV64340_I2O_INBOUND_INTERRUPT_MASK_REG_PCI_1_SIDE 0x0A8 -#define MV64340_I2O_OUTBOUND_DOORBELL_REG_PCI_1_SIDE 0x0AC -#define MV64340_I2O_OUTBOUND_INTERRUPT_CAUSE_REG_PCI_1_SIDE 0x0B0 -#define MV64340_I2O_OUTBOUND_INTERRUPT_MASK_REG_PCI_1_SIDE 0x0B4 -#define MV64340_I2O_INBOUND_QUEUE_PORT_VIRTUAL_REG_PCI_1_SIDE 0x0C0 -#define MV64340_I2O_OUTBOUND_QUEUE_PORT_VIRTUAL_REG_PCI_1_SIDE 0x0C4 -#define MV64340_I2O_QUEUE_CONTROL_REG_PCI_1_SIDE 0x0D0 -#define MV64340_I2O_QUEUE_BASE_ADDR_REG_PCI_1_SIDE 0x0D4 -#define MV64340_I2O_INBOUND_FREE_HEAD_POINTER_REG_PCI_1_SIDE 0x0E0 -#define MV64340_I2O_INBOUND_FREE_TAIL_POINTER_REG_PCI_1_SIDE 0x0E4 -#define MV64340_I2O_INBOUND_POST_HEAD_POINTER_REG_PCI_1_SIDE 0x0E8 -#define MV64340_I2O_INBOUND_POST_TAIL_POINTER_REG_PCI_1_SIDE 0x0EC -#define MV64340_I2O_OUTBOUND_FREE_HEAD_POINTER_REG_PCI_1_SIDE 0x0F0 -#define MV64340_I2O_OUTBOUND_FREE_TAIL_POINTER_REG_PCI_1_SIDE 0x0F4 -#define MV64340_I2O_OUTBOUND_POST_HEAD_POINTER_REG_PCI_1_SIDE 0x078 -#define MV64340_I2O_OUTBOUND_POST_TAIL_POINTER_REG_PCI_1_SIDE 0x07C - -#define MV64340_I2O_INBOUND_MESSAGE_REG0_CPU0_SIDE 0x1C10 -#define MV64340_I2O_INBOUND_MESSAGE_REG1_CPU0_SIDE 0x1C14 -#define MV64340_I2O_OUTBOUND_MESSAGE_REG0_CPU0_SIDE 0x1C18 -#define MV64340_I2O_OUTBOUND_MESSAGE_REG1_CPU0_SIDE 0x1C1C -#define MV64340_I2O_INBOUND_DOORBELL_REG_CPU0_SIDE 0x1C20 -#define MV64340_I2O_INBOUND_INTERRUPT_CAUSE_REG_CPU0_SIDE 0x1C24 -#define MV64340_I2O_INBOUND_INTERRUPT_MASK_REG_CPU0_SIDE 0x1C28 -#define MV64340_I2O_OUTBOUND_DOORBELL_REG_CPU0_SIDE 0x1C2C -#define MV64340_I2O_OUTBOUND_INTERRUPT_CAUSE_REG_CPU0_SIDE 0x1C30 -#define MV64340_I2O_OUTBOUND_INTERRUPT_MASK_REG_CPU0_SIDE 0x1C34 -#define MV64340_I2O_INBOUND_QUEUE_PORT_VIRTUAL_REG_CPU0_SIDE 0x1C40 -#define MV64340_I2O_OUTBOUND_QUEUE_PORT_VIRTUAL_REG_CPU0_SIDE 0x1C44 -#define MV64340_I2O_QUEUE_CONTROL_REG_CPU0_SIDE 0x1C50 -#define MV64340_I2O_QUEUE_BASE_ADDR_REG_CPU0_SIDE 0x1C54 -#define MV64340_I2O_INBOUND_FREE_HEAD_POINTER_REG_CPU0_SIDE 0x1C60 -#define MV64340_I2O_INBOUND_FREE_TAIL_POINTER_REG_CPU0_SIDE 0x1C64 -#define MV64340_I2O_INBOUND_POST_HEAD_POINTER_REG_CPU0_SIDE 0x1C68 -#define MV64340_I2O_INBOUND_POST_TAIL_POINTER_REG_CPU0_SIDE 0x1C6C -#define MV64340_I2O_OUTBOUND_FREE_HEAD_POINTER_REG_CPU0_SIDE 0x1C70 -#define MV64340_I2O_OUTBOUND_FREE_TAIL_POINTER_REG_CPU0_SIDE 0x1C74 -#define MV64340_I2O_OUTBOUND_POST_HEAD_POINTER_REG_CPU0_SIDE 0x1CF8 -#define MV64340_I2O_OUTBOUND_POST_TAIL_POINTER_REG_CPU0_SIDE 0x1CFC -#define MV64340_I2O_INBOUND_MESSAGE_REG0_CPU1_SIDE 0x1C90 -#define MV64340_I2O_INBOUND_MESSAGE_REG1_CPU1_SIDE 0x1C94 -#define MV64340_I2O_OUTBOUND_MESSAGE_REG0_CPU1_SIDE 0x1C98 -#define MV64340_I2O_OUTBOUND_MESSAGE_REG1_CPU1_SIDE 0x1C9C -#define MV64340_I2O_INBOUND_DOORBELL_REG_CPU1_SIDE 0x1CA0 -#define MV64340_I2O_INBOUND_INTERRUPT_CAUSE_REG_CPU1_SIDE 0x1CA4 -#define MV64340_I2O_INBOUND_INTERRUPT_MASK_REG_CPU1_SIDE 0x1CA8 -#define MV64340_I2O_OUTBOUND_DOORBELL_REG_CPU1_SIDE 0x1CAC -#define MV64340_I2O_OUTBOUND_INTERRUPT_CAUSE_REG_CPU1_SIDE 0x1CB0 -#define MV64340_I2O_OUTBOUND_INTERRUPT_MASK_REG_CPU1_SIDE 0x1CB4 -#define MV64340_I2O_INBOUND_QUEUE_PORT_VIRTUAL_REG_CPU1_SIDE 0x1CC0 -#define MV64340_I2O_OUTBOUND_QUEUE_PORT_VIRTUAL_REG_CPU1_SIDE 0x1CC4 -#define MV64340_I2O_QUEUE_CONTROL_REG_CPU1_SIDE 0x1CD0 -#define MV64340_I2O_QUEUE_BASE_ADDR_REG_CPU1_SIDE 0x1CD4 -#define MV64340_I2O_INBOUND_FREE_HEAD_POINTER_REG_CPU1_SIDE 0x1CE0 -#define MV64340_I2O_INBOUND_FREE_TAIL_POINTER_REG_CPU1_SIDE 0x1CE4 -#define MV64340_I2O_INBOUND_POST_HEAD_POINTER_REG_CPU1_SIDE 0x1CE8 -#define MV64340_I2O_INBOUND_POST_TAIL_POINTER_REG_CPU1_SIDE 0x1CEC -#define MV64340_I2O_OUTBOUND_FREE_HEAD_POINTER_REG_CPU1_SIDE 0x1CF0 -#define MV64340_I2O_OUTBOUND_FREE_TAIL_POINTER_REG_CPU1_SIDE 0x1CF4 -#define MV64340_I2O_OUTBOUND_POST_HEAD_POINTER_REG_CPU1_SIDE 0x1C78 -#define MV64340_I2O_OUTBOUND_POST_TAIL_POINTER_REG_CPU1_SIDE 0x1C7C - -/****************************************/ -/* Ethernet Unit Registers */ -/****************************************/ - -/*******************************************/ -/* CUNIT Registers */ -/*******************************************/ - - /* Address Decoding Register Map */ - -#define MV64340_CUNIT_BASE_ADDR_REG0 0xf200 -#define MV64340_CUNIT_BASE_ADDR_REG1 0xf208 -#define MV64340_CUNIT_BASE_ADDR_REG2 0xf210 -#define MV64340_CUNIT_BASE_ADDR_REG3 0xf218 -#define MV64340_CUNIT_SIZE0 0xf204 -#define MV64340_CUNIT_SIZE1 0xf20c -#define MV64340_CUNIT_SIZE2 0xf214 -#define MV64340_CUNIT_SIZE3 0xf21c -#define MV64340_CUNIT_HIGH_ADDR_REMAP_REG0 0xf240 -#define MV64340_CUNIT_HIGH_ADDR_REMAP_REG1 0xf244 -#define MV64340_CUNIT_BASE_ADDR_ENABLE_REG 0xf250 -#define MV64340_MPSC0_ACCESS_PROTECTION_REG 0xf254 -#define MV64340_MPSC1_ACCESS_PROTECTION_REG 0xf258 -#define MV64340_CUNIT_INTERNAL_SPACE_BASE_ADDR_REG 0xf25C - - /* Error Report Registers */ - -#define MV64340_CUNIT_INTERRUPT_CAUSE_REG 0xf310 -#define MV64340_CUNIT_INTERRUPT_MASK_REG 0xf314 -#define MV64340_CUNIT_ERROR_ADDR 0xf318 - - /* Cunit Control Registers */ - -#define MV64340_CUNIT_ARBITER_CONTROL_REG 0xf300 -#define MV64340_CUNIT_CONFIG_REG 0xb40c -#define MV64340_CUNIT_CRROSBAR_TIMEOUT_REG 0xf304 - - /* Cunit Debug Registers */ - -#define MV64340_CUNIT_DEBUG_LOW 0xf340 -#define MV64340_CUNIT_DEBUG_HIGH 0xf344 -#define MV64340_CUNIT_MMASK 0xf380 - - /* MPSCs Clocks Routing Registers */ - -#define MV64340_MPSC_ROUTING_REG 0xb400 -#define MV64340_MPSC_RX_CLOCK_ROUTING_REG 0xb404 -#define MV64340_MPSC_TX_CLOCK_ROUTING_REG 0xb408 - - /* MPSCs Interrupts Registers */ - -#define MV64340_MPSC_CAUSE_REG(port) (0xb804 + (port<<3)) -#define MV64340_MPSC_MASK_REG(port) (0xb884 + (port<<3)) - -#define MV64340_MPSC_MAIN_CONFIG_LOW(port) (0x8000 + (port<<12)) -#define MV64340_MPSC_MAIN_CONFIG_HIGH(port) (0x8004 + (port<<12)) -#define MV64340_MPSC_PROTOCOL_CONFIG(port) (0x8008 + (port<<12)) -#define MV64340_MPSC_CHANNEL_REG1(port) (0x800c + (port<<12)) -#define MV64340_MPSC_CHANNEL_REG2(port) (0x8010 + (port<<12)) -#define MV64340_MPSC_CHANNEL_REG3(port) (0x8014 + (port<<12)) -#define MV64340_MPSC_CHANNEL_REG4(port) (0x8018 + (port<<12)) -#define MV64340_MPSC_CHANNEL_REG5(port) (0x801c + (port<<12)) -#define MV64340_MPSC_CHANNEL_REG6(port) (0x8020 + (port<<12)) -#define MV64340_MPSC_CHANNEL_REG7(port) (0x8024 + (port<<12)) -#define MV64340_MPSC_CHANNEL_REG8(port) (0x8028 + (port<<12)) -#define MV64340_MPSC_CHANNEL_REG9(port) (0x802c + (port<<12)) -#define MV64340_MPSC_CHANNEL_REG10(port) (0x8030 + (port<<12)) - - /* MPSC0 Registers */ - - -/***************************************/ -/* SDMA Registers */ -/***************************************/ - -#define MV64340_SDMA_CONFIG_REG(channel) (0x4000 + (channel<<13)) -#define MV64340_SDMA_COMMAND_REG(channel) (0x4008 + (channel<<13)) -#define MV64340_SDMA_CURRENT_RX_DESCRIPTOR_POINTER(channel) (0x4810 + (channel<<13)) -#define MV64340_SDMA_CURRENT_TX_DESCRIPTOR_POINTER(channel) (0x4c10 + (channel<<13)) -#define MV64340_SDMA_FIRST_TX_DESCRIPTOR_POINTER(channel) (0x4c14 + (channel<<13)) - -#define MV64340_SDMA_CAUSE_REG 0xb800 -#define MV64340_SDMA_MASK_REG 0xb880 - -/* BRG Interrupts */ - -#define MV64340_BRG_CONFIG_REG(brg) (0xb200 + (brg<<3)) -#define MV64340_BRG_BAUDE_TUNING_REG(brg) (0xb208 + (brg<<3)) -#define MV64340_BRG_CAUSE_REG 0xb834 -#define MV64340_BRG_MASK_REG 0xb8b4 - -/****************************************/ -/* DMA Channel Control */ -/****************************************/ - -#define MV64340_DMA_CHANNEL0_CONTROL 0x840 -#define MV64340_DMA_CHANNEL0_CONTROL_HIGH 0x880 -#define MV64340_DMA_CHANNEL1_CONTROL 0x844 -#define MV64340_DMA_CHANNEL1_CONTROL_HIGH 0x884 -#define MV64340_DMA_CHANNEL2_CONTROL 0x848 -#define MV64340_DMA_CHANNEL2_CONTROL_HIGH 0x888 -#define MV64340_DMA_CHANNEL3_CONTROL 0x84C -#define MV64340_DMA_CHANNEL3_CONTROL_HIGH 0x88C - - -/****************************************/ -/* IDMA Registers */ -/****************************************/ - -#define MV64340_DMA_CHANNEL0_BYTE_COUNT 0x800 -#define MV64340_DMA_CHANNEL1_BYTE_COUNT 0x804 -#define MV64340_DMA_CHANNEL2_BYTE_COUNT 0x808 -#define MV64340_DMA_CHANNEL3_BYTE_COUNT 0x80C -#define MV64340_DMA_CHANNEL0_SOURCE_ADDR 0x810 -#define MV64340_DMA_CHANNEL1_SOURCE_ADDR 0x814 -#define MV64340_DMA_CHANNEL2_SOURCE_ADDR 0x818 -#define MV64340_DMA_CHANNEL3_SOURCE_ADDR 0x81c -#define MV64340_DMA_CHANNEL0_DESTINATION_ADDR 0x820 -#define MV64340_DMA_CHANNEL1_DESTINATION_ADDR 0x824 -#define MV64340_DMA_CHANNEL2_DESTINATION_ADDR 0x828 -#define MV64340_DMA_CHANNEL3_DESTINATION_ADDR 0x82C -#define MV64340_DMA_CHANNEL0_NEXT_DESCRIPTOR_POINTER 0x830 -#define MV64340_DMA_CHANNEL1_NEXT_DESCRIPTOR_POINTER 0x834 -#define MV64340_DMA_CHANNEL2_NEXT_DESCRIPTOR_POINTER 0x838 -#define MV64340_DMA_CHANNEL3_NEXT_DESCRIPTOR_POINTER 0x83C -#define MV64340_DMA_CHANNEL0_CURRENT_DESCRIPTOR_POINTER 0x870 -#define MV64340_DMA_CHANNEL1_CURRENT_DESCRIPTOR_POINTER 0x874 -#define MV64340_DMA_CHANNEL2_CURRENT_DESCRIPTOR_POINTER 0x878 -#define MV64340_DMA_CHANNEL3_CURRENT_DESCRIPTOR_POINTER 0x87C - - /* IDMA Address Decoding Base Address Registers */ - -#define MV64340_DMA_BASE_ADDR_REG0 0xa00 -#define MV64340_DMA_BASE_ADDR_REG1 0xa08 -#define MV64340_DMA_BASE_ADDR_REG2 0xa10 -#define MV64340_DMA_BASE_ADDR_REG3 0xa18 -#define MV64340_DMA_BASE_ADDR_REG4 0xa20 -#define MV64340_DMA_BASE_ADDR_REG5 0xa28 -#define MV64340_DMA_BASE_ADDR_REG6 0xa30 -#define MV64340_DMA_BASE_ADDR_REG7 0xa38 - - /* IDMA Address Decoding Size Address Register */ - -#define MV64340_DMA_SIZE_REG0 0xa04 -#define MV64340_DMA_SIZE_REG1 0xa0c -#define MV64340_DMA_SIZE_REG2 0xa14 -#define MV64340_DMA_SIZE_REG3 0xa1c -#define MV64340_DMA_SIZE_REG4 0xa24 -#define MV64340_DMA_SIZE_REG5 0xa2c -#define MV64340_DMA_SIZE_REG6 0xa34 -#define MV64340_DMA_SIZE_REG7 0xa3C - - /* IDMA Address Decoding High Address Remap and Access - Protection Registers */ - -#define MV64340_DMA_HIGH_ADDR_REMAP_REG0 0xa60 -#define MV64340_DMA_HIGH_ADDR_REMAP_REG1 0xa64 -#define MV64340_DMA_HIGH_ADDR_REMAP_REG2 0xa68 -#define MV64340_DMA_HIGH_ADDR_REMAP_REG3 0xa6C -#define MV64340_DMA_BASE_ADDR_ENABLE_REG 0xa80 -#define MV64340_DMA_CHANNEL0_ACCESS_PROTECTION_REG 0xa70 -#define MV64340_DMA_CHANNEL1_ACCESS_PROTECTION_REG 0xa74 -#define MV64340_DMA_CHANNEL2_ACCESS_PROTECTION_REG 0xa78 -#define MV64340_DMA_CHANNEL3_ACCESS_PROTECTION_REG 0xa7c -#define MV64340_DMA_ARBITER_CONTROL 0x860 -#define MV64340_DMA_CROSS_BAR_TIMEOUT 0x8d0 - - /* IDMA Headers Retarget Registers */ - -#define MV64340_DMA_HEADERS_RETARGET_CONTROL 0xa84 -#define MV64340_DMA_HEADERS_RETARGET_BASE 0xa88 - - /* IDMA Interrupt Register */ - -#define MV64340_DMA_INTERRUPT_CAUSE_REG 0x8c0 -#define MV64340_DMA_INTERRUPT_CAUSE_MASK 0x8c4 -#define MV64340_DMA_ERROR_ADDR 0x8c8 -#define MV64340_DMA_ERROR_SELECT 0x8cc - - /* IDMA Debug Register ( for internal use ) */ - -#define MV64340_DMA_DEBUG_LOW 0x8e0 -#define MV64340_DMA_DEBUG_HIGH 0x8e4 -#define MV64340_DMA_SPARE 0xA8C - -/****************************************/ -/* Timer_Counter */ -/****************************************/ - -#define MV64340_TIMER_COUNTER0 0x850 -#define MV64340_TIMER_COUNTER1 0x854 -#define MV64340_TIMER_COUNTER2 0x858 -#define MV64340_TIMER_COUNTER3 0x85C -#define MV64340_TIMER_COUNTER_0_3_CONTROL 0x864 -#define MV64340_TIMER_COUNTER_0_3_INTERRUPT_CAUSE 0x868 -#define MV64340_TIMER_COUNTER_0_3_INTERRUPT_MASK 0x86c - -/****************************************/ -/* Watchdog registers */ -/****************************************/ - -#define MV64340_WATCHDOG_CONFIG_REG 0xb410 -#define MV64340_WATCHDOG_VALUE_REG 0xb414 - -/****************************************/ -/* I2C Registers */ -/****************************************/ - -#define MV64XXX_I2C_OFFSET 0xc000 -#define MV64XXX_I2C_REG_BLOCK_SIZE 0x0020 - -/****************************************/ -/* GPP Interface Registers */ -/****************************************/ - -#define MV64340_GPP_IO_CONTROL 0xf100 -#define MV64340_GPP_LEVEL_CONTROL 0xf110 -#define MV64340_GPP_VALUE 0xf104 -#define MV64340_GPP_INTERRUPT_CAUSE 0xf108 -#define MV64340_GPP_INTERRUPT_MASK0 0xf10c -#define MV64340_GPP_INTERRUPT_MASK1 0xf114 -#define MV64340_GPP_VALUE_SET 0xf118 -#define MV64340_GPP_VALUE_CLEAR 0xf11c - -/****************************************/ -/* Interrupt Controller Registers */ -/****************************************/ - -/****************************************/ -/* Interrupts */ -/****************************************/ - -#define MV64340_MAIN_INTERRUPT_CAUSE_LOW 0x004 -#define MV64340_MAIN_INTERRUPT_CAUSE_HIGH 0x00c -#define MV64340_CPU_INTERRUPT0_MASK_LOW 0x014 -#define MV64340_CPU_INTERRUPT0_MASK_HIGH 0x01c -#define MV64340_CPU_INTERRUPT0_SELECT_CAUSE 0x024 -#define MV64340_CPU_INTERRUPT1_MASK_LOW 0x034 -#define MV64340_CPU_INTERRUPT1_MASK_HIGH 0x03c -#define MV64340_CPU_INTERRUPT1_SELECT_CAUSE 0x044 -#define MV64340_INTERRUPT0_MASK_0_LOW 0x054 -#define MV64340_INTERRUPT0_MASK_0_HIGH 0x05c -#define MV64340_INTERRUPT0_SELECT_CAUSE 0x064 -#define MV64340_INTERRUPT1_MASK_0_LOW 0x074 -#define MV64340_INTERRUPT1_MASK_0_HIGH 0x07c -#define MV64340_INTERRUPT1_SELECT_CAUSE 0x084 - -/****************************************/ -/* MPP Interface Registers */ -/****************************************/ - -#define MV64340_MPP_CONTROL0 0xf000 -#define MV64340_MPP_CONTROL1 0xf004 -#define MV64340_MPP_CONTROL2 0xf008 -#define MV64340_MPP_CONTROL3 0xf00c - -/****************************************/ -/* Serial Initialization registers */ -/****************************************/ - -#define MV64340_SERIAL_INIT_LAST_DATA 0xf324 -#define MV64340_SERIAL_INIT_CONTROL 0xf328 -#define MV64340_SERIAL_INIT_STATUS 0xf32c - -extern void mv64340_irq_init(unsigned int base); - -#endif /* __ASM_MV643XX_H */ diff --git a/include/linux/namei.h b/include/linux/namei.h index 74e0cc14ebf8..8ec8fed3bce8 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -44,18 +44,13 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT}; #define LOOKUP_BENEATH 0x080000 /* No escaping from starting point. */ #define LOOKUP_IN_ROOT 0x100000 /* Treat dirfd as fs root. */ #define LOOKUP_CACHED 0x200000 /* Only do cached lookup */ +#define LOOKUP_LINKAT_EMPTY 0x400000 /* Linkat request with empty path. */ /* LOOKUP_* flags which do scope-related checks based on the dirfd. */ #define LOOKUP_IS_SCOPED (LOOKUP_BENEATH | LOOKUP_IN_ROOT) extern int path_pts(struct path *path); -extern int user_path_at_empty(int, const char __user *, unsigned, struct path *, int *empty); - -static inline int user_path_at(int dfd, const char __user *name, unsigned flags, - struct path *path) -{ - return user_path_at_empty(dfd, name, flags, path, NULL); -} +extern int user_path_at(int, const char __user *, unsigned, struct path *); struct dentry *lookup_one_qstr_excl(const struct qstr *name, struct dentry *base, diff --git a/include/linux/nd.h b/include/linux/nd.h index b9771ba1ef87..fa099e295f78 100644 --- a/include/linux/nd.h +++ b/include/linux/nd.h @@ -84,11 +84,7 @@ struct nd_device_driver { void (*notify)(struct device *dev, enum nvdimm_event event); }; -static inline struct nd_device_driver *to_nd_device_driver( - struct device_driver *drv) -{ - return container_of(drv, struct nd_device_driver, drv); -}; +#define to_nd_device_driver(__drv) container_of_const(__drv, struct nd_device_driver, drv) /** * struct nd_namespace_common - core infrastructure of a namespace diff --git a/include/linux/net.h b/include/linux/net.h index 15df6d5f27a7..0ff950eecc6b 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -153,6 +153,7 @@ struct sockaddr; struct msghdr; struct module; struct sk_buff; +struct proto_accept_arg; typedef int (*sk_read_actor_t)(read_descriptor_t *, struct sk_buff *, unsigned int, size_t); typedef int (*skb_read_actor_t)(struct sock *, struct sk_buff *); @@ -171,7 +172,8 @@ struct proto_ops { int (*socketpair)(struct socket *sock1, struct socket *sock2); int (*accept) (struct socket *sock, - struct socket *newsock, int flags, bool kern); + struct socket *newsock, + struct proto_accept_arg *arg); int (*getname) (struct socket *sock, struct sockaddr *addr, int peer); @@ -320,10 +322,27 @@ static inline bool sendpage_ok(struct page *page) return !PageSlab(page) && page_count(page) >= 1; } +/* + * Check sendpage_ok on contiguous pages. + */ +static inline bool sendpages_ok(struct page *page, size_t len, size_t offset) +{ + struct page *p = page + (offset >> PAGE_SHIFT); + size_t count = 0; + + while (count < len) { + if (!sendpage_ok(p)) + return false; + + p++; + count += PAGE_SIZE; + } + + return true; +} + int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t len); -int kernel_sendmsg_locked(struct sock *sk, struct msghdr *msg, - struct kvec *vec, size_t num, size_t len); int kernel_recvmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t len, int flags); diff --git a/include/linux/net/intel/libie/rx.h b/include/linux/net/intel/libie/rx.h new file mode 100644 index 000000000000..8e97775f1d66 --- /dev/null +++ b/include/linux/net/intel/libie/rx.h @@ -0,0 +1,50 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (C) 2024 Intel Corporation */ + +#ifndef __LIBIE_RX_H +#define __LIBIE_RX_H + +#include <net/libeth/rx.h> + +/* Rx buffer management */ + +/* The largest size for a single descriptor as per HW */ +#define LIBIE_MAX_RX_BUF_LEN 9728U +/* "True" HW-writeable space: minimum from SW and HW values */ +#define LIBIE_RX_BUF_LEN(hr) min_t(u32, LIBETH_RX_PAGE_LEN(hr), \ + LIBIE_MAX_RX_BUF_LEN) + +/* The maximum frame size as per HW (S/G) */ +#define __LIBIE_MAX_RX_FRM_LEN 16382U +/* ATST, HW can chain up to 5 Rx descriptors */ +#define LIBIE_MAX_RX_FRM_LEN(hr) \ + min_t(u32, __LIBIE_MAX_RX_FRM_LEN, LIBIE_RX_BUF_LEN(hr) * 5) +/* Maximum frame size minus LL overhead */ +#define LIBIE_MAX_MTU \ + (LIBIE_MAX_RX_FRM_LEN(LIBETH_MAX_HEADROOM) - LIBETH_RX_LL_LEN) + +/* O(1) converting i40e/ice/iavf's 8/10-bit hardware packet type to a parsed + * bitfield struct. + */ + +#define LIBIE_RX_PT_NUM 154 + +extern const struct libeth_rx_pt libie_rx_pt_lut[LIBIE_RX_PT_NUM]; + +/** + * libie_rx_pt_parse - convert HW packet type to software bitfield structure + * @pt: 10-bit hardware packet type value from the descriptor + * + * ```libie_rx_pt_lut``` must be accessed only using this wrapper. + * + * Return: parsed bitfield struct corresponding to the provided ptype. + */ +static inline struct libeth_rx_pt libie_rx_pt_parse(u32 pt) +{ + if (unlikely(pt >= LIBIE_RX_PT_NUM)) + pt = 0; + + return libie_rx_pt_lut[pt]; +} + +#endif /* __LIBIE_RX_H */ diff --git a/include/linux/net_tstamp.h b/include/linux/net_tstamp.h index eb01c37e71e0..ff0758e88ea1 100644 --- a/include/linux/net_tstamp.h +++ b/include/linux/net_tstamp.h @@ -5,12 +5,48 @@ #include <uapi/linux/net_tstamp.h> +#define SOF_TIMESTAMPING_SOFTWARE_MASK (SOF_TIMESTAMPING_RX_SOFTWARE | \ + SOF_TIMESTAMPING_TX_SOFTWARE | \ + SOF_TIMESTAMPING_SOFTWARE) + +#define SOF_TIMESTAMPING_HARDWARE_MASK (SOF_TIMESTAMPING_RX_HARDWARE | \ + SOF_TIMESTAMPING_TX_HARDWARE | \ + SOF_TIMESTAMPING_RAW_HARDWARE) + enum hwtstamp_source { + HWTSTAMP_SOURCE_UNSPEC, HWTSTAMP_SOURCE_NETDEV, HWTSTAMP_SOURCE_PHYLIB, }; /** + * struct hwtstamp_provider_desc - hwtstamp provider description + * + * @index: index of the hwtstamp provider. + * @qualifier: hwtstamp provider qualifier. + */ +struct hwtstamp_provider_desc { + int index; + enum hwtstamp_provider_qualifier qualifier; +}; + +/** + * struct hwtstamp_provider - hwtstamp provider object + * + * @rcu_head: RCU callback used to free the struct. + * @source: source of the hwtstamp provider. + * @phydev: pointer of the phydev source in case a PTP coming from phylib + * @desc: hwtstamp provider description. + */ + +struct hwtstamp_provider { + struct rcu_head rcu_head; + enum hwtstamp_source source; + struct phy_device *phydev; + struct hwtstamp_provider_desc desc; +}; + +/** * struct kernel_hwtstamp_config - Kernel copy of struct hwtstamp_config * * @flags: see struct hwtstamp_config @@ -22,6 +58,7 @@ enum hwtstamp_source { * copied the ioctl request back to user space * @source: indication whether timestamps should come from the netdev or from * an attached phylib PHY + * @qualifier: qualifier of the hwtstamp provider * * Prefer using this structure for in-kernel processing of hardware * timestamping configuration, over the inextensible struct hwtstamp_config @@ -34,6 +71,7 @@ struct kernel_hwtstamp_config { struct ifreq *ifr; bool copied_to_user; enum hwtstamp_source source; + enum hwtstamp_provider_qualifier qualifier; }; static inline void hwtstamp_config_to_kernel(struct kernel_hwtstamp_config *kernel_cfg, diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 7c2d77d75a88..11be70a7929f 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -24,9 +24,8 @@ enum { NETIF_F_HW_VLAN_CTAG_FILTER_BIT,/* Receive filtering on VLAN CTAGs */ NETIF_F_VLAN_CHALLENGED_BIT, /* Device cannot handle VLAN packets */ NETIF_F_GSO_BIT, /* Enable software GSO. */ - NETIF_F_LLTX_BIT, /* LockLess TX - deprecated. Please */ - /* do not use LLTX in new drivers */ - NETIF_F_NETNS_LOCAL_BIT, /* Does not change network namespaces */ + __UNUSED_NETIF_F_12, + __UNUSED_NETIF_F_13, NETIF_F_GRO_BIT, /* Generic receive offload */ NETIF_F_LRO_BIT, /* large receive offload */ @@ -59,7 +58,7 @@ enum { NETIF_F_FCOE_CRC_BIT, /* FCoE CRC32 */ NETIF_F_SCTP_CRC_BIT, /* SCTP checksum offload */ - NETIF_F_FCOE_MTU_BIT, /* Supports max FCoE MTU, 2158 bytes*/ + __UNUSED_NETIF_F_37, NETIF_F_NTUPLE_BIT, /* N-tuple filters supported */ NETIF_F_RXHASH_BIT, /* Receive hashing offload */ NETIF_F_RXCSUM_BIT, /* Receive checksumming offload */ @@ -106,7 +105,6 @@ enum { #define __NETIF_F(name) __NETIF_F_BIT(NETIF_F_##name##_BIT) #define NETIF_F_FCOE_CRC __NETIF_F(FCOE_CRC) -#define NETIF_F_FCOE_MTU __NETIF_F(FCOE_MTU) #define NETIF_F_FRAGLIST __NETIF_F(FRAGLIST) #define NETIF_F_FSO __NETIF_F(FSO) #define NETIF_F_GRO __NETIF_F(GRO) @@ -120,10 +118,8 @@ enum { #define NETIF_F_HW_VLAN_CTAG_TX __NETIF_F(HW_VLAN_CTAG_TX) #define NETIF_F_IP_CSUM __NETIF_F(IP_CSUM) #define NETIF_F_IPV6_CSUM __NETIF_F(IPV6_CSUM) -#define NETIF_F_LLTX __NETIF_F(LLTX) #define NETIF_F_LOOPBACK __NETIF_F(LOOPBACK) #define NETIF_F_LRO __NETIF_F(LRO) -#define NETIF_F_NETNS_LOCAL __NETIF_F(NETNS_LOCAL) #define NETIF_F_NOCACHE_COPY __NETIF_F(NOCACHE_COPY) #define NETIF_F_NTUPLE __NETIF_F(NTUPLE) #define NETIF_F_RXCSUM __NETIF_F(RXCSUM) @@ -192,8 +188,7 @@ static inline int find_next_netdev_feature(u64 feature, unsigned long start) /* Features valid for ethtool to change */ /* = all defined minus driver/device-class-related */ -#define NETIF_F_NEVER_CHANGE (NETIF_F_VLAN_CHALLENGED | \ - NETIF_F_LLTX | NETIF_F_NETNS_LOCAL) +#define NETIF_F_NEVER_CHANGE NETIF_F_VLAN_CHALLENGED /* remember that ((t)1 << t_BITS) is undefined in C99 */ #define NETIF_F_ETHTOOL_BITS ((__NETIF_F_BIT(NETDEV_FEATURE_COUNT - 1) | \ @@ -214,9 +209,6 @@ static inline int find_next_netdev_feature(u64 feature, unsigned long start) #define NETIF_F_ALL_TSO (NETIF_F_TSO | NETIF_F_TSO6 | \ NETIF_F_TSO_ECN | NETIF_F_TSO_MANGLEID) -#define NETIF_F_ALL_FCOE (NETIF_F_FCOE_CRC | NETIF_F_FCOE_MTU | \ - NETIF_F_FSO) - /* List of features with software fallbacks. */ #define NETIF_F_GSO_SOFTWARE (NETIF_F_ALL_TSO | NETIF_F_GSO_SCTP | \ NETIF_F_GSO_UDP_L4 | NETIF_F_GSO_FRAGLIST) @@ -261,4 +253,11 @@ static inline int find_next_netdev_feature(u64 feature, unsigned long start) NETIF_F_GSO_UDP_TUNNEL | \ NETIF_F_GSO_UDP_TUNNEL_CSUM) +static inline netdev_features_t netdev_base_features(netdev_features_t features) +{ + features &= ~NETIF_F_ONE_FOR_ALL; + features |= NETIF_F_ALL_FOR_ALL; + return features; +} + #endif /* _LINUX_NETDEV_FEATURES_H */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index cb37817d6382..2a59034a5fa2 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -40,9 +40,9 @@ #include <net/dcbnl.h> #endif #include <net/netprio_cgroup.h> - #include <linux/netdev_features.h> #include <linux/neighbour.h> +#include <linux/netdevice_xmit.h> #include <uapi/linux/netdevice.h> #include <uapi/linux/if_bonding.h> #include <uapi/linux/pkt_cls.h> @@ -52,6 +52,7 @@ #include <net/net_trackers.h> #include <net/net_debug.h> #include <net/dropreason-core.h> +#include <net/neighbour_tables.h> struct netpoll_info; struct device; @@ -59,9 +60,10 @@ struct ethtool_ops; struct kernel_hwtstamp_config; struct phy_device; struct dsa_port; -struct ip_tunnel_parm; +struct ip_tunnel_parm_kern; struct macsec_context; struct macsec_ops; +struct netdev_config; struct netdev_name_node; struct sd_flow_limit; struct sfp_bus; @@ -79,6 +81,9 @@ struct xdp_buff; struct xdp_frame; struct xdp_metadata_ops; struct xdp_md; +struct ethtool_netdev_state; +struct phy_link_topology; +struct hwtstamp_provider; typedef u32 xdp_features_t; @@ -341,6 +346,16 @@ struct gro_list { #define GRO_HASH_BUCKETS 8 /* + * Structure for per-NAPI config + */ +struct napi_config { + u64 gro_flush_timeout; + u64 irq_suspend_timeout; + u32 defer_hard_irqs; + unsigned int napi_id; +}; + +/* * Structure for NAPI scheduling similar to tasklet but with weighting */ struct napi_struct { @@ -354,7 +369,7 @@ struct napi_struct { unsigned long state; int weight; - int defer_hard_irqs_count; + u32 defer_hard_irqs_count; unsigned long gro_bitmask; int (*poll)(struct napi_struct *, int); #ifdef CONFIG_NETPOLL @@ -368,13 +383,19 @@ struct napi_struct { struct sk_buff *skb; struct list_head rx_list; /* Pending GRO_NORMAL skbs */ int rx_count; /* length of rx_list */ - unsigned int napi_id; + unsigned int napi_id; /* protected by netdev_lock */ struct hrtimer timer; + /* all fields past this point are write-protected by netdev_lock */ struct task_struct *thread; + unsigned long gro_flush_timeout; + unsigned long irq_suspend_timeout; + u32 defer_hard_irqs; /* control-path-only fields follow */ struct list_head dev_list; struct hlist_node napi_hash_node; int irq; + int index; + struct napi_config *config; }; enum { @@ -491,7 +512,7 @@ static inline bool napi_prefer_busy_poll(struct napi_struct *n) * is scheduled for example in the context of delayed timer * that can be skipped if a NAPI is already scheduled. * - * Return True if NAPI is scheduled, False otherwise. + * Return: True if NAPI is scheduled, False otherwise. */ static inline bool napi_is_scheduled(struct napi_struct *n) { @@ -506,7 +527,7 @@ bool napi_schedule_prep(struct napi_struct *n); * * Schedule NAPI poll routine to be called if it is not already * running. - * Return true if we schedule a NAPI or false if not. + * Return: true if we schedule a NAPI or false if not. * Refer to napi_schedule_prep() for additional reason on why * a NAPI might not be scheduled. */ @@ -540,7 +561,7 @@ static inline void napi_schedule_irqoff(struct napi_struct *n) * Mark NAPI processing as complete. Should only be called if poll budget * has not been completely consumed. * Prefer over napi_complete(). - * Return false if device should avoid rearming interrupts. + * Return: false if device should avoid rearming interrupts. */ bool napi_complete_done(struct napi_struct *n, int work_done); @@ -551,16 +572,11 @@ static inline bool napi_complete(struct napi_struct *n) int dev_set_threaded(struct net_device *dev, bool threaded); -/** - * napi_disable - prevent NAPI from scheduling - * @n: NAPI context - * - * Stop NAPI from being scheduled on this context. - * Waits till any outstanding processing completes. - */ void napi_disable(struct napi_struct *n); +void napi_disable_locked(struct napi_struct *n); void napi_enable(struct napi_struct *n); +void napi_enable_locked(struct napi_struct *n); /** * napi_synchronize - wait until NAPI is not running @@ -643,9 +659,6 @@ struct netdev_queue { #ifdef CONFIG_SYSFS struct kobject kobj; #endif -#if defined(CONFIG_XPS) && defined(CONFIG_NUMA) - int numa_node; -#endif unsigned long tx_maxrate; /* * Number of TX timeouts for this queue @@ -658,13 +671,13 @@ struct netdev_queue { #ifdef CONFIG_XDP_SOCKETS struct xsk_buff_pool *pool; #endif - /* NAPI instance for the queue - * Readers and writers must hold RTNL - */ - struct napi_struct *napi; + /* * write-mostly part */ +#ifdef CONFIG_BQL + struct dql dql; +#endif spinlock_t _xmit_lock ____cacheline_aligned_in_smp; int xmit_lock_owner; /* @@ -674,8 +687,16 @@ struct netdev_queue { unsigned long state; -#ifdef CONFIG_BQL - struct dql dql; +/* + * slow- / control-path part + */ + /* NAPI instance for the queue + * Readers and writers must hold RTNL + */ + struct napi_struct *napi; + +#if defined(CONFIG_XPS) && defined(CONFIG_NUMA) + int numa_node; #endif } ____cacheline_aligned_in_smp; @@ -1064,8 +1085,8 @@ struct netdev_net_notifier { * * int (*ndo_do_ioctl)(struct net_device *dev, struct ifreq *ifr, int cmd); * Old-style ioctl entry point. This is used internally by the - * appletalk and ieee802154 subsystems but is no longer called by - * the device ioctl handler. + * ieee802154 subsystem but is no longer called by the device + * ioctl handler. * * int (*ndo_siocbond)(struct net_device *dev, struct ifreq *ifr, int cmd); * Used by the bonding driver for its device specific ioctls: @@ -1225,12 +1246,17 @@ struct netdev_net_notifier { * int (*ndo_fdb_add)(struct ndmsg *ndm, struct nlattr *tb[], * struct net_device *dev, * const unsigned char *addr, u16 vid, u16 flags, - * struct netlink_ext_ack *extack); + * bool *notified, struct netlink_ext_ack *extack); * Adds an FDB entry to dev for addr. + * Callee shall set *notified to true if it sent any appropriate + * notification(s). Otherwise core will send a generic one. * int (*ndo_fdb_del)(struct ndmsg *ndm, struct nlattr *tb[], * struct net_device *dev, - * const unsigned char *addr, u16 vid) - * Deletes the FDB entry from dev coresponding to addr. + * const unsigned char *addr, u16 vid + * bool *notified, struct netlink_ext_ack *extack); + * Deletes the FDB entry from dev corresponding to addr. + * Callee shall set *notified to true if it sent any appropriate + * notification(s). Otherwise core will send a generic one. * int (*ndo_fdb_del_bulk)(struct nlmsghdr *nlh, struct net_device *dev, * struct netlink_ext_ack *extack); * int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb, @@ -1327,7 +1353,7 @@ struct netdev_net_notifier { * queue id bound to an AF_XDP socket. The flags field specifies if * only RX, only Tx, or both should be woken up using the flags * XDP_WAKEUP_RX and XDP_WAKEUP_TX. - * int (*ndo_tunnel_ctl)(struct net_device *dev, struct ip_tunnel_parm *p, + * int (*ndo_tunnel_ctl)(struct net_device *dev, struct ip_tunnel_parm_kern *p, * int cmd); * Add, change, delete or get information on an IPv4 tunnel. * struct net_device *(*ndo_get_peer_dev)(struct net_device *dev); @@ -1405,8 +1431,7 @@ struct net_device_ops { __be16 proto, u16 vid); #ifdef CONFIG_NET_POLL_CONTROLLER void (*ndo_poll_controller)(struct net_device *dev); - int (*ndo_netpoll_setup)(struct net_device *dev, - struct netpoll_info *info); + int (*ndo_netpoll_setup)(struct net_device *dev); void (*ndo_netpoll_cleanup)(struct net_device *dev); #endif int (*ndo_set_vf_mac)(struct net_device *dev, @@ -1503,12 +1528,15 @@ struct net_device_ops { const unsigned char *addr, u16 vid, u16 flags, + bool *notified, struct netlink_ext_ack *extack); int (*ndo_fdb_del)(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, - u16 vid, struct netlink_ext_ack *extack); + u16 vid, + bool *notified, + struct netlink_ext_ack *extack); int (*ndo_fdb_del_bulk)(struct nlmsghdr *nlh, struct net_device *dev, struct netlink_ext_ack *extack); @@ -1583,7 +1611,8 @@ struct net_device_ops { int (*ndo_xsk_wakeup)(struct net_device *dev, u32 queue_id, u32 flags); int (*ndo_tunnel_ctl)(struct net_device *dev, - struct ip_tunnel_parm *p, int cmd); + struct ip_tunnel_parm_kern *p, + int cmd); struct net_device * (*ndo_get_peer_dev)(struct net_device *dev); int (*ndo_fill_forward_path)(struct net_device_path_ctx *ctx, struct net_device_path *path); @@ -1595,6 +1624,14 @@ struct net_device_ops { int (*ndo_hwtstamp_set)(struct net_device *dev, struct kernel_hwtstamp_config *kernel_config, struct netlink_ext_ack *extack); + +#if IS_ENABLED(CONFIG_NET_SHAPER) + /** + * @net_shaper_ops: Device shaping offload operations + * see include/net/net_shapers.h + */ + const struct net_shaper_ops *net_shaper_ops; +#endif }; /** @@ -1605,7 +1642,8 @@ struct net_device_ops { * userspace; this means that the order of these flags can change * during any kernel release. * - * You should have a pretty good reason to be extending these flags. + * You should add bitfield booleans after either net_device::priv_flags + * (hotpath) or ::threaded (slowpath) instead of extending these flags. * * @IFF_802_1Q_VLAN: 802.1Q VLAN device * @IFF_EBRIDGE: Ethernet bridging device @@ -1644,10 +1682,6 @@ struct net_device_ops { * @IFF_NO_ADDRCONF: prevent ipv6 addrconf * @IFF_TX_SKB_NO_LINEAR: device/driver is capable of xmitting frames with * skb_headlen(skb) == 0 (data starts from frag0) - * @IFF_CHANGE_PROTO_DOWN: device supports setting carrier via IFLA_PROTO_DOWN - * @IFF_SEE_ALL_HWTSTAMP_REQUESTS: device wants to see calls to - * ndo_hwtstamp_set() for all timestamp requests regardless of source, - * even if those aren't HWTSTAMP_SOURCE_NETDEV. */ enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, @@ -1682,42 +1716,8 @@ enum netdev_priv_flags { IFF_L3MDEV_RX_HANDLER = 1<<29, IFF_NO_ADDRCONF = BIT_ULL(30), IFF_TX_SKB_NO_LINEAR = BIT_ULL(31), - IFF_CHANGE_PROTO_DOWN = BIT_ULL(32), - IFF_SEE_ALL_HWTSTAMP_REQUESTS = BIT_ULL(33), }; -#define IFF_802_1Q_VLAN IFF_802_1Q_VLAN -#define IFF_EBRIDGE IFF_EBRIDGE -#define IFF_BONDING IFF_BONDING -#define IFF_ISATAP IFF_ISATAP -#define IFF_WAN_HDLC IFF_WAN_HDLC -#define IFF_XMIT_DST_RELEASE IFF_XMIT_DST_RELEASE -#define IFF_DONT_BRIDGE IFF_DONT_BRIDGE -#define IFF_DISABLE_NETPOLL IFF_DISABLE_NETPOLL -#define IFF_MACVLAN_PORT IFF_MACVLAN_PORT -#define IFF_BRIDGE_PORT IFF_BRIDGE_PORT -#define IFF_OVS_DATAPATH IFF_OVS_DATAPATH -#define IFF_TX_SKB_SHARING IFF_TX_SKB_SHARING -#define IFF_UNICAST_FLT IFF_UNICAST_FLT -#define IFF_TEAM_PORT IFF_TEAM_PORT -#define IFF_SUPP_NOFCS IFF_SUPP_NOFCS -#define IFF_LIVE_ADDR_CHANGE IFF_LIVE_ADDR_CHANGE -#define IFF_MACVLAN IFF_MACVLAN -#define IFF_XMIT_DST_RELEASE_PERM IFF_XMIT_DST_RELEASE_PERM -#define IFF_L3MDEV_MASTER IFF_L3MDEV_MASTER -#define IFF_NO_QUEUE IFF_NO_QUEUE -#define IFF_OPENVSWITCH IFF_OPENVSWITCH -#define IFF_L3MDEV_SLAVE IFF_L3MDEV_SLAVE -#define IFF_TEAM IFF_TEAM -#define IFF_RXFH_CONFIGURED IFF_RXFH_CONFIGURED -#define IFF_PHONY_HEADROOM IFF_PHONY_HEADROOM -#define IFF_MACSEC IFF_MACSEC -#define IFF_NO_RX_HANDLER IFF_NO_RX_HANDLER -#define IFF_FAILOVER IFF_FAILOVER -#define IFF_FAILOVER_SLAVE IFF_FAILOVER_SLAVE -#define IFF_L3MDEV_RX_HANDLER IFF_L3MDEV_RX_HANDLER -#define IFF_TX_SKB_NO_LINEAR IFF_TX_SKB_NO_LINEAR - /* Specifies the type of the struct net_device::ml_priv pointer */ enum netdev_ml_priv_type { ML_PRIV_NONE, @@ -1747,6 +1747,12 @@ enum netdev_reg_state { * data with strictly "high-level" data, and it has to know about * almost every data structure used in the INET module. * + * @priv_flags: flags invisible to userspace defined as bits, see + * enum netdev_priv_flags for the definitions + * @lltx: device supports lockless Tx. Deprecated for real HW + * drivers. Mainly used by logical interfaces, such as + * bonding and tunnels + * * @name: This is the first field of the "visible" part of this structure * (i.e. as seen by users in the "Space.c" file). It is the name * of the interface. @@ -1796,7 +1802,6 @@ enum netdev_reg_state { * @wireless_handlers: List of functions to handle Wireless Extensions, * instead of ioctl, * see <net/iw_handler.h> for details. - * @wireless_data: Instance data managed by the core of wireless extensions * * @netdev_ops: Includes several pointers to callbacks, * if one wants to override the ndo_*() functions @@ -1813,10 +1818,9 @@ enum netdev_reg_state { * * @flags: Interface flags (a la BSD) * @xdp_features: XDP capability supported by the device - * @priv_flags: Like 'flags' but invisible to userspace, - * see if.h for the definitions * @gflags: Global flags ( kept as legacy ) - * @padded: How much padding added by alloc_netdev() + * @priv_len: Size of the ->priv flexible array + * @priv: Flexible array containing private data * @operstate: RFC2863 operstate * @link_mode: Mapping policy to operstate * @if_port: Selectable AUI, TP, ... @@ -1882,9 +1886,6 @@ enum netdev_reg_state { * allocated at register_netdev() time * @real_num_rx_queues: Number of RX queues currently active in device * @xdp_prog: XDP sockets filter program pointer - * @gro_flush_timeout: timeout for GRO layer in NAPI - * @napi_defer_hard_irqs: If not zero, provides a counter that would - * allow to avoid NIC hard IRQ, on busy queues. * * @rx_handler: handler for received packets * @rx_handler_data: XXX: need comments on this one @@ -1956,6 +1957,7 @@ enum netdev_reg_state { * @sysfs_rx_queue_group: Space for optional per-rx queue attributes * @rtnl_link_ops: Rtnl_link_ops * @stat_ops: Optional ops for queue-aware statistics + * @queue_mgmt_ops: Optional ops for queue management * * @gso_max_size: Maximum size of generic segmentation offload * @tso_max_size: Device (as in HW) limit on the max TSO request size @@ -1973,6 +1975,7 @@ enum netdev_reg_state { * @fcoe_ddp_xid: Max exchange id for FCoE LRO by ddp * * @priomap: XXX: need comments on this one + * @link_topo: Physical link topology tracking attached PHYs * @phydev: Physical device may attach itself * for hardware timestamping * @sfp_bus: attached &struct sfp_bus structure. @@ -1983,10 +1986,16 @@ enum netdev_reg_state { * switch driver and used to set the phys state of the * switch port. * - * @wol_enabled: Wake-on-LAN is enabled - * * @threaded: napi threaded mode is enabled * + * @see_all_hwtstamp_requests: device wants to see calls to + * ndo_hwtstamp_set() for all timestamp requests + * regardless of source, even if those aren't + * HWTSTAMP_SOURCE_NETDEV + * @change_proto_down: device supports setting carrier via IFLA_PROTO_DOWN + * @netns_local: interface can't change network namespaces + * @fcoe_mtu: device supports maximum FCoE MTU, 2158 bytes + * * @net_notifier_list: List of per-net netdev notifier block * that follow this device when it is moved * to another network namespace. @@ -1996,6 +2005,7 @@ enum netdev_reg_state { * @udp_tunnel_nic_info: static structure describing the UDP tunnel * offload capabilities of the device * @udp_tunnel_nic: UDP tunnel offload state + * @ethtool: ethtool related state * @xdp_state: stores info on attached XDP BPF programs * * @nested_level: Used as a parameter of spin_lock_nested() of @@ -2024,6 +2034,17 @@ enum netdev_reg_state { * @dpll_pin: Pointer to the SyncE source pin of a DPLL subsystem, * where the clock is recovered. * + * @max_pacing_offload_horizon: max EDT offload horizon in nsec. + * @napi_config: An array of napi_config structures containing per-NAPI + * settings. + * @gro_flush_timeout: timeout for GRO layer in NAPI + * @napi_defer_hard_irqs: If not zero, provides a counter that would + * allow to avoid NIC hard IRQ, on busy queues. + * + * @neighbours: List heads pointing to this device's neighbours' + * dev_list, one per address-family. + * @hwprov: Tracks which PTP performs hardware packet time stamping. + * * FIXME: cleanup struct net_device such that network protocol info * moves out. */ @@ -2036,7 +2057,10 @@ struct net_device { /* TX read-mostly hotpath */ __cacheline_group_begin(net_device_read_tx); - unsigned long long priv_flags; + struct_group(priv_flags_fast, + unsigned long priv_flags:32; + unsigned long lltx:1; + ); const struct net_device_ops *netdev_ops; const struct header_ops *header_ops; struct netdev_queue *_tx; @@ -2086,8 +2110,6 @@ struct net_device { int ifindex; unsigned int real_num_rx_queues; struct netdev_rx_queue *_rx; - unsigned long gro_flush_timeout; - int napi_defer_hard_irqs; unsigned int gro_max_size; unsigned int gro_ipv4_max_size; rx_handler_func_t __rcu *rx_handler; @@ -2162,7 +2184,6 @@ struct net_device { #ifdef CONFIG_WIRELESS_EXT const struct iw_handler_def *wireless_handlers; - struct iw_public_data *wireless_data; #endif const struct ethtool_ops *ethtool_ops; #ifdef CONFIG_NET_L3_MASTER_DEV @@ -2196,10 +2217,10 @@ struct net_device { unsigned short neigh_priv_len; unsigned short dev_id; unsigned short dev_port; - unsigned short padded; + int irq; + u32 priv_len; spinlock_t addr_list_lock; - int irq; struct netdev_hw_addr_list uc; struct netdev_hw_addr_list mc; @@ -2221,6 +2242,9 @@ struct net_device { /* Protocol-specific pointers */ struct in_device __rcu *ip_ptr; + /** @fib_nh_head: nexthops associated with this netdev */ + struct hlist_head fib_nh_head; + #if IS_ENABLED(CONFIG_VLAN_8021Q) struct vlan_info __rcu *vlan_info; #endif @@ -2234,7 +2258,7 @@ struct net_device { void *atalk_ptr; #endif #if IS_ENABLED(CONFIG_AX25) - void *ax25_ptr; + struct ax25_dev __rcu *ax25_ptr; #endif #if IS_ENABLED(CONFIG_CFG80211) struct wireless_dev *ieee80211_ptr; @@ -2338,6 +2362,8 @@ struct net_device { const struct netdev_stat_ops *stat_ops; + const struct netdev_queue_mgmt_ops *queue_mgmt_ops; + /* for setting kernel sock attribute on TCP connection setup */ #define GSO_MAX_SEGS 65535u #define GSO_LEGACY_MAX_SIZE 65536u @@ -2363,12 +2389,18 @@ struct net_device { #if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) struct netprio_map __rcu *priomap; #endif + struct phy_link_topology *link_topo; struct phy_device *phydev; struct sfp_bus *sfp_bus; struct lock_class_key *qdisc_tx_busylock; bool proto_down; - unsigned wol_enabled:1; - unsigned threaded:1; + bool threaded; + + /* priv_flags_slow, ungrouped to save space */ + unsigned long see_all_hwtstamp_requests:1; + unsigned long change_proto_down:1; + unsigned long netns_local:1; + unsigned long fcoe_mtu:1; struct list_head net_notifier_list; @@ -2379,6 +2411,16 @@ struct net_device { const struct udp_tunnel_nic_info *udp_tunnel_nic_info; struct udp_tunnel_nic *udp_tunnel_nic; + /** @cfg: net_device queue-related configuration */ + struct netdev_config *cfg; + /** + * @cfg_pending: same as @cfg but when device is being actively + * reconfigured includes any changes to the configuration + * requested by the user, but which may or may not be rejected. + */ + struct netdev_config *cfg_pending; + struct ethtool_netdev_state *ethtool; + /* protected by rtnl_lock */ struct bpf_xdp_entity xdp_state[__MAX_XDP_MODE]; @@ -2397,7 +2439,55 @@ struct net_device { /** @page_pools: page pools created for this netdevice */ struct hlist_head page_pools; #endif -}; + + /** @irq_moder: dim parameters used if IS_ENABLED(CONFIG_DIMLIB). */ + struct dim_irq_moder *irq_moder; + + u64 max_pacing_offload_horizon; + struct napi_config *napi_config; + unsigned long gro_flush_timeout; + u32 napi_defer_hard_irqs; + + /** + * @up: copy of @state's IFF_UP, but safe to read with just @lock. + * May report false negatives while the device is being opened + * or closed (@lock does not protect .ndo_open, or .ndo_close). + */ + bool up; + + /** + * @lock: netdev-scope lock, protects a small selection of fields. + * Should always be taken using netdev_lock() / netdev_unlock() helpers. + * Drivers are free to use it for other protection. + * + * Protects: + * @gro_flush_timeout, @napi_defer_hard_irqs, @napi_list, + * @net_shaper_hierarchy, @reg_state, @threaded + * + * Partially protects (writers must hold both @lock and rtnl_lock): + * @up + * + * Also protects some fields in struct napi_struct. + * + * Ordering: take after rtnl_lock. + */ + struct mutex lock; + +#if IS_ENABLED(CONFIG_NET_SHAPER) + /** + * @net_shaper_hierarchy: data tracking the current shaper status + * see include/net/net_shapers.h + */ + struct net_shaper_hierarchy *net_shaper_hierarchy; +#endif + + struct hlist_head neighbours[NEIGH_NR_TABLES]; + + struct hwtstamp_provider __rcu *hwprov; + + u8 priv[] ____cacheline_aligned + __counted_by(priv_len); +} ____cacheline_aligned; #define to_net_dev(d) container_of(d, struct net_device, dev) /* @@ -2587,7 +2677,7 @@ void dev_net_set(struct net_device *dev, struct net *net) */ static inline void *netdev_priv(const struct net_device *dev) { - return (char *)dev + ALIGN(sizeof(struct net_device), NETDEV_ALIGN); + return (void *)dev->priv; } /* Set the sysfs physical device reference for the network logical device @@ -2605,18 +2695,58 @@ void netif_queue_set_napi(struct net_device *dev, unsigned int queue_index, enum netdev_queue_type type, struct napi_struct *napi); -static inline void netif_napi_set_irq(struct napi_struct *napi, int irq) +static inline void netdev_lock(struct net_device *dev) +{ + mutex_lock(&dev->lock); +} + +static inline void netdev_unlock(struct net_device *dev) +{ + mutex_unlock(&dev->lock); +} + +static inline void netdev_assert_locked(struct net_device *dev) +{ + lockdep_assert_held(&dev->lock); +} + +static inline void netdev_assert_locked_or_invisible(struct net_device *dev) +{ + if (dev->reg_state == NETREG_REGISTERED || + dev->reg_state == NETREG_UNREGISTERING) + netdev_assert_locked(dev); +} + +static inline void netif_napi_set_irq_locked(struct napi_struct *napi, int irq) { napi->irq = irq; } +static inline void netif_napi_set_irq(struct napi_struct *napi, int irq) +{ + netdev_lock(napi->dev); + netif_napi_set_irq_locked(napi, irq); + netdev_unlock(napi->dev); +} + /* Default NAPI poll() weight * Device drivers are strongly advised to not use bigger value */ #define NAPI_POLL_WEIGHT 64 -void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi, - int (*poll)(struct napi_struct *, int), int weight); +void netif_napi_add_weight_locked(struct net_device *dev, + struct napi_struct *napi, + int (*poll)(struct napi_struct *, int), + int weight); + +static inline void +netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi, + int (*poll)(struct napi_struct *, int), int weight) +{ + netdev_lock(dev); + netif_napi_add_weight_locked(dev, napi, poll, weight); + netdev_unlock(dev); +} /** * netif_napi_add() - initialize a NAPI context @@ -2635,6 +2765,13 @@ netif_napi_add(struct net_device *dev, struct napi_struct *napi, } static inline void +netif_napi_add_locked(struct net_device *dev, struct napi_struct *napi, + int (*poll)(struct napi_struct *, int)) +{ + netif_napi_add_weight_locked(dev, napi, poll, NAPI_POLL_WEIGHT); +} + +static inline void netif_napi_add_tx_weight(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), @@ -2644,6 +2781,31 @@ netif_napi_add_tx_weight(struct net_device *dev, netif_napi_add_weight(dev, napi, poll, weight); } +static inline void +netif_napi_add_config_locked(struct net_device *dev, struct napi_struct *napi, + int (*poll)(struct napi_struct *, int), int index) +{ + napi->index = index; + napi->config = &dev->napi_config[index]; + netif_napi_add_weight_locked(dev, napi, poll, NAPI_POLL_WEIGHT); +} + +/** + * netif_napi_add_config - initialize a NAPI context with persistent config + * @dev: network device + * @napi: NAPI context + * @poll: polling function + * @index: the NAPI index + */ +static inline void +netif_napi_add_config(struct net_device *dev, struct napi_struct *napi, + int (*poll)(struct napi_struct *, int), int index) +{ + netdev_lock(dev); + netif_napi_add_config_locked(dev, napi, poll, index); + netdev_unlock(dev); +} + /** * netif_napi_add_tx() - initialize a NAPI context to be used for Tx only * @dev: network device @@ -2661,6 +2823,8 @@ static inline void netif_napi_add_tx(struct net_device *dev, netif_napi_add_tx_weight(dev, napi, poll, NAPI_POLL_WEIGHT); } +void __netif_napi_del_locked(struct napi_struct *napi); + /** * __netif_napi_del - remove a NAPI context * @napi: NAPI context @@ -2669,7 +2833,18 @@ static inline void netif_napi_add_tx(struct net_device *dev, * containing @napi. Drivers might want to call this helper to combine * all the needed RCU grace periods into a single one. */ -void __netif_napi_del(struct napi_struct *napi); +static inline void __netif_napi_del(struct napi_struct *napi) +{ + netdev_lock(napi->dev); + __netif_napi_del_locked(napi); + netdev_unlock(napi->dev); +} + +static inline void netif_napi_del_locked(struct napi_struct *napi) +{ + __netif_napi_del_locked(napi); + synchronize_net(); +} /** * netif_napi_del - remove a NAPI context @@ -2727,12 +2902,12 @@ struct pcpu_sw_netstats { } __aligned(4 * sizeof(u64)); struct pcpu_dstats { - u64 rx_packets; - u64 rx_bytes; - u64 rx_drops; - u64 tx_packets; - u64 tx_bytes; - u64 tx_drops; + u64_stats_t rx_packets; + u64_stats_t rx_bytes; + u64_stats_t rx_drops; + u64_stats_t tx_packets; + u64_stats_t tx_bytes; + u64_stats_t tx_drops; struct u64_stats_sync syncp; } __aligned(8 * sizeof(u64)); @@ -2776,6 +2951,46 @@ static inline void dev_lstats_add(struct net_device *dev, unsigned int len) u64_stats_update_end(&lstats->syncp); } +static inline void dev_dstats_rx_add(struct net_device *dev, + unsigned int len) +{ + struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats); + + u64_stats_update_begin(&dstats->syncp); + u64_stats_inc(&dstats->rx_packets); + u64_stats_add(&dstats->rx_bytes, len); + u64_stats_update_end(&dstats->syncp); +} + +static inline void dev_dstats_rx_dropped(struct net_device *dev) +{ + struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats); + + u64_stats_update_begin(&dstats->syncp); + u64_stats_inc(&dstats->rx_drops); + u64_stats_update_end(&dstats->syncp); +} + +static inline void dev_dstats_tx_add(struct net_device *dev, + unsigned int len) +{ + struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats); + + u64_stats_update_begin(&dstats->syncp); + u64_stats_inc(&dstats->tx_packets); + u64_stats_add(&dstats->tx_bytes, len); + u64_stats_update_end(&dstats->syncp); +} + +static inline void dev_dstats_tx_dropped(struct net_device *dev) +{ + struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats); + + u64_stats_update_begin(&dstats->syncp); + u64_stats_inc(&dstats->tx_drops); + u64_stats_update_end(&dstats->syncp); +} + #define __netdev_alloc_pcpu_stats(type, gfp) \ ({ \ typeof(type) __percpu *pcpu_stats = alloc_percpu_gfp(type, gfp);\ @@ -3017,7 +3232,8 @@ int call_netdevice_notifiers_info(unsigned long val, #define net_device_entry(lh) list_entry(lh, struct net_device, dev_list) #define for_each_netdev_dump(net, d, ifindex) \ - xa_for_each_start(&(net)->dev_by_index, (ifindex), (d), (ifindex)) + for (; (d = xa_find(&(net)->dev_by_index, &ifindex, \ + ULONG_MAX, XA_PRESENT)); ifindex++) static inline struct net_device *next_net_device(struct net_device *dev) { @@ -3080,8 +3296,6 @@ void dev_disable_lro(struct net_device *dev); int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb); u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev); -u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev); int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev); int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id); @@ -3117,8 +3331,6 @@ static inline void unregister_netdevice(struct net_device *dev) int netdev_refcnt_read(const struct net_device *dev); void free_netdev(struct net_device *dev); -void netdev_freemem(struct net_device *dev); -void init_dummy_netdev(struct net_device *dev); struct net_device *netdev_get_xmit_slave(struct net_device *dev, struct sk_buff *skb, @@ -3132,7 +3344,7 @@ struct net_device *netdev_get_by_index(struct net *net, int ifindex, struct net_device *netdev_get_by_name(struct net *net, const char *name, netdevice_tracker *tracker, gfp_t gfp); struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex); -struct net_device *dev_get_by_napi_id(unsigned int napi_id); +void netdev_copy_name(struct net_device *dev, char *name); static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, @@ -3195,6 +3407,7 @@ static inline bool dev_has_header(const struct net_device *dev) struct softnet_data { struct list_head poll_list; struct sk_buff_head process_queue; + local_lock_t process_queue_bh_lock; /* stats */ unsigned int processed; @@ -3203,6 +3416,7 @@ struct softnet_data { struct softnet_data *rps_ipi_list; #endif + unsigned int received_rps; bool in_net_rx_action; bool in_napi_threaded_poll; @@ -3216,13 +3430,7 @@ struct softnet_data { struct sk_buff_head xfrm_backlog; #endif /* written and read only by owning cpu: */ - struct { - u16 recursion; - u8 more; -#ifdef CONFIG_NET_EGRESS - u8 skip_txqueue; -#endif - } xmit; + struct netdev_xmit xmit; #ifdef CONFIG_RPS /* input_queue_head should be written by cpu owning this struct, * and only read by other cpus. Worth using a cache line. @@ -3235,11 +3443,11 @@ struct softnet_data { unsigned int cpu; unsigned int input_queue_tail; #endif - unsigned int received_rps; - unsigned int dropped; struct sk_buff_head input_pkt_queue; struct napi_struct backlog; + atomic_t dropped ____cacheline_aligned_in_smp; + /* Another possibly contended cache line */ spinlock_t defer_lock ____cacheline_aligned_in_smp; int defer_count; @@ -3248,44 +3456,21 @@ struct softnet_data { call_single_data_t defer_csd; }; -static inline void input_queue_head_incr(struct softnet_data *sd) -{ -#ifdef CONFIG_RPS - sd->input_queue_head++; -#endif -} - -static inline void input_queue_tail_incr_save(struct softnet_data *sd, - unsigned int *qtail) -{ -#ifdef CONFIG_RPS - *qtail = ++sd->input_queue_tail; -#endif -} - DECLARE_PER_CPU_ALIGNED(struct softnet_data, softnet_data); +DECLARE_PER_CPU(struct page_pool *, system_page_pool); +#ifndef CONFIG_PREEMPT_RT static inline int dev_recursion_level(void) { return this_cpu_read(softnet_data.xmit.recursion); } - -#define XMIT_RECURSION_LIMIT 8 -static inline bool dev_xmit_recursion(void) -{ - return unlikely(__this_cpu_read(softnet_data.xmit.recursion) > - XMIT_RECURSION_LIMIT); -} - -static inline void dev_xmit_recursion_inc(void) +#else +static inline int dev_recursion_level(void) { - __this_cpu_inc(softnet_data.xmit.recursion); + return current->net_xmit.recursion; } -static inline void dev_xmit_recursion_dec(void) -{ - __this_cpu_dec(softnet_data.xmit.recursion); -} +#endif void __netif_schedule(struct Qdisc *q); void netif_schedule_queue(struct netdev_queue *txq); @@ -3350,6 +3535,12 @@ static inline void netif_tx_wake_all_queues(struct net_device *dev) static __always_inline void netif_tx_stop_queue(struct netdev_queue *dev_queue) { + /* Paired with READ_ONCE() from dev_watchdog() */ + WRITE_ONCE(dev_queue->trans_start, jiffies); + + /* This barrier is paired with smp_mb() from dev_watchdog() */ + smp_mb__before_atomic(); + /* Must be an atomic op see netif_txq_try_stop() */ set_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state); } @@ -3476,6 +3667,12 @@ static inline void netdev_tx_sent_queue(struct netdev_queue *dev_queue, if (likely(dql_avail(&dev_queue->dql) >= 0)) return; + /* Paired with READ_ONCE() from dev_watchdog() */ + WRITE_ONCE(dev_queue->trans_start, jiffies); + + /* This barrier is paired with smp_mb() from dev_watchdog() */ + smp_mb__before_atomic(); + set_bit(__QUEUE_STATE_STACK_XOFF, &dev_queue->state); /* @@ -3483,7 +3680,7 @@ static inline void netdev_tx_sent_queue(struct netdev_queue *dev_queue, * because in netdev_tx_completed_queue we update the dql_completed * before checking the XOFF flag. */ - smp_mb(); + smp_mb__after_atomic(); /* check again in case another CPU has just made room avail */ if (unlikely(dql_avail(&dev_queue->dql) >= 0)) @@ -3553,7 +3750,7 @@ static inline void netdev_tx_completed_queue(struct netdev_queue *dev_queue, dql_completed(&dev_queue->dql, bytes); /* - * Without the memory barrier there is a small possiblity that + * Without the memory barrier there is a small possibility that * netdev_tx_sent_queue will miss the update and cause the queue to * be stopped forever */ @@ -3592,6 +3789,17 @@ static inline void netdev_tx_reset_queue(struct netdev_queue *q) } /** + * netdev_tx_reset_subqueue - reset the BQL stats and state of a netdev queue + * @dev: network device + * @qid: stack index of the queue to reset + */ +static inline void netdev_tx_reset_subqueue(const struct net_device *dev, + u32 qid) +{ + netdev_tx_reset_queue(netdev_get_tx_queue(dev, qid)); +} + +/** * netdev_reset_queue - reset the packets and bytes count of a network device * @dev_queue: network device * @@ -3600,7 +3808,7 @@ static inline void netdev_tx_reset_queue(struct netdev_queue *q) */ static inline void netdev_reset_queue(struct net_device *dev_queue) { - netdev_tx_reset_queue(netdev_get_tx_queue(dev_queue, 0)); + netdev_tx_reset_subqueue(dev_queue, 0); } /** @@ -3738,7 +3946,7 @@ static inline bool netif_attr_test_mask(unsigned long j, * @online_mask: bitmask for CPUs/Rx queues that are online * @nr_bits: number of bits in the bitmask * - * Returns true if a CPU/Rx queue is online. + * Returns: true if a CPU/Rx queue is online. */ static inline bool netif_attr_test_online(unsigned long j, const unsigned long *online_mask, @@ -3758,7 +3966,8 @@ static inline bool netif_attr_test_online(unsigned long j, * @srcp: the cpumask/Rx queue mask pointer * @nr_bits: number of bits in the bitmask * - * Returns >= nr_bits if no further CPUs/Rx queues set. + * Returns: next (after n) CPU/Rx queue index in the mask; + * >= nr_bits if no further CPUs/Rx queues set. */ static inline unsigned int netif_attrmask_next(int n, const unsigned long *srcp, unsigned int nr_bits) @@ -3780,7 +3989,8 @@ static inline unsigned int netif_attrmask_next(int n, const unsigned long *srcp, * @src2p: the second CPUs/Rx queues mask pointer * @nr_bits: number of bits in the bitmask * - * Returns >= nr_bits if no further CPUs/Rx queues set in both. + * Returns: next (after n) CPU/Rx queue index set in both masks; + * >= nr_bits if no further CPUs/Rx queues set in both. */ static inline int netif_attrmask_next_and(int n, const unsigned long *src1p, const unsigned long *src2p, @@ -3886,9 +4096,9 @@ static inline void dev_consume_skb_any(struct sk_buff *skb) } u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp, - struct bpf_prog *xdp_prog); -void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog); -int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff **pskb); + const struct bpf_prog *xdp_prog); +void generic_xdp_tx(struct sk_buff *skb, const struct bpf_prog *xdp_prog); +int do_xdp_generic(const struct bpf_prog *xdp_prog, struct sk_buff **pskb); int netif_rx(struct sk_buff *skb); int __netif_rx(struct sk_buff *skb); @@ -3929,9 +4139,6 @@ int generic_hwtstamp_get_lower(struct net_device *dev, int generic_hwtstamp_set_lower(struct net_device *dev, struct kernel_hwtstamp_config *kernel_cfg, struct netlink_ext_ack *extack); -int dev_set_hwtstamp_phylib(struct net_device *dev, - struct kernel_hwtstamp_config *cfg, - struct netlink_ext_ack *extack); int dev_ethtool(struct net *net, struct ifreq *ifr, void __user *userdata); unsigned int dev_get_flags(const struct net_device *); int __dev_change_flags(struct net_device *dev, unsigned int flags, @@ -3967,8 +4174,12 @@ struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); u8 dev_xdp_prog_count(struct net_device *dev); +int dev_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf); +u8 dev_xdp_sb_prog_count(struct net_device *dev); u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode); +u32 dev_get_min_mp_channel_count(const struct net_device *dev); + int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb); int dev_forward_skb(struct net_device *dev, struct sk_buff *skb); int dev_forward_skb_nomtu(struct net_device *dev, struct sk_buff *skb); @@ -4127,6 +4338,8 @@ static inline void dev_put(struct net_device *dev) netdev_put(dev, NULL); } +DEFINE_FREE(dev_put, struct net_device *, if (_T) dev_put(_T)) + static inline void netdev_ref_replace(struct net_device *odev, struct net_device *ndev, netdevice_tracker *tracker, @@ -4174,7 +4387,7 @@ static inline bool netif_carrier_ok(const struct net_device *dev) unsigned long dev_trans_start(struct net_device *dev); -void __netdev_watchdog_up(struct net_device *dev); +void netdev_watchdog_up(struct net_device *dev); void netif_carrier_on(struct net_device *dev); void netif_carrier_off(struct net_device *dev); @@ -4464,7 +4677,7 @@ static inline void netif_tx_unlock_bh(struct net_device *dev) } #define HARD_TX_LOCK(dev, txq, cpu) { \ - if ((dev->features & NETIF_F_LLTX) == 0) { \ + if (!(dev)->lltx) { \ __netif_tx_lock(txq, cpu); \ } else { \ __netif_tx_acquire(txq); \ @@ -4472,12 +4685,12 @@ static inline void netif_tx_unlock_bh(struct net_device *dev) } #define HARD_TX_TRYLOCK(dev, txq) \ - (((dev->features & NETIF_F_LLTX) == 0) ? \ + (!(dev)->lltx ? \ __netif_tx_trylock(txq) : \ __netif_tx_acquire(txq)) #define HARD_TX_UNLOCK(dev, txq) { \ - if ((dev->features & NETIF_F_LLTX) == 0) { \ + if (!(dev)->lltx) { \ __netif_tx_unlock(txq); \ } else { \ __netif_tx_release(txq); \ @@ -4545,6 +4758,9 @@ static inline void netif_addr_unlock_bh(struct net_device *dev) void ether_setup(struct net_device *dev); +/* Allocate dummy net_device */ +struct net_device *alloc_netdev_dummy(int sizeof_priv); + /* Support for loadable net-drivers */ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, unsigned char name_assign_type, @@ -4565,6 +4781,9 @@ int devm_register_netdev(struct device *dev, struct net_device *ndev); /* General hardware address lists handling functions */ int __hw_addr_sync(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr_list *from_list, int addr_len); +int __hw_addr_sync_multiple(struct netdev_hw_addr_list *to_list, + struct netdev_hw_addr_list *from_list, + int addr_len); void __hw_addr_unsync(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr_list *from_list, int addr_len); int __hw_addr_sync_dev(struct netdev_hw_addr_list *list, @@ -4619,7 +4838,7 @@ void dev_uc_flush(struct net_device *dev); void dev_uc_init(struct net_device *dev); /** - * __dev_uc_sync - Synchonize device's unicast list + * __dev_uc_sync - Synchronize device's unicast list * @dev: device to sync * @sync: function to call if address should be added * @unsync: function to call if address should be removed @@ -4663,7 +4882,7 @@ void dev_mc_flush(struct net_device *dev); void dev_mc_init(struct net_device *dev); /** - * __dev_mc_sync - Synchonize device's multicast list + * __dev_mc_sync - Synchronize device's multicast list * @dev: device to sync * @sync: function to call if address should be added * @unsync: function to call if address should be removed @@ -4895,18 +5114,35 @@ static inline ktime_t netdev_get_tstamp(struct net_device *dev, return hwtstamps->hwtstamp; } -static inline netdev_tx_t __netdev_start_xmit(const struct net_device_ops *ops, - struct sk_buff *skb, struct net_device *dev, - bool more) +#ifndef CONFIG_PREEMPT_RT +static inline void netdev_xmit_set_more(bool more) { __this_cpu_write(softnet_data.xmit.more, more); - return ops->ndo_start_xmit(skb, dev); } static inline bool netdev_xmit_more(void) { return __this_cpu_read(softnet_data.xmit.more); } +#else +static inline void netdev_xmit_set_more(bool more) +{ + current->net_xmit.more = more; +} + +static inline bool netdev_xmit_more(void) +{ + return current->net_xmit.more; +} +#endif + +static inline netdev_tx_t __netdev_start_xmit(const struct net_device_ops *ops, + struct sk_buff *skb, struct net_device *dev, + bool more) +{ + netdev_xmit_set_more(more); + return ops->ndo_start_xmit(skb, dev); +} static inline netdev_tx_t netdev_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, bool more) @@ -5021,6 +5257,24 @@ void netif_set_tso_max_segs(struct net_device *dev, unsigned int segs); void netif_inherit_tso_max(struct net_device *to, const struct net_device *from); +static inline unsigned int +netif_get_gro_max_size(const struct net_device *dev, const struct sk_buff *skb) +{ + /* pairs with WRITE_ONCE() in netif_set_gro(_ipv4)_max_size() */ + return skb->protocol == htons(ETH_P_IPV6) ? + READ_ONCE(dev->gro_max_size) : + READ_ONCE(dev->gro_ipv4_max_size); +} + +static inline unsigned int +netif_get_gso_max_size(const struct net_device *dev, const struct sk_buff *skb) +{ + /* pairs with WRITE_ONCE() in netif_set_gso(_ipv4)_max_size() */ + return skb->protocol == htons(ETH_P_IPV6) ? + READ_ONCE(dev->gso_max_size) : + READ_ONCE(dev->gso_ipv4_max_size); +} + static inline bool netif_is_macsec(const struct net_device *dev) { return dev->priv_flags & IFF_MACSEC; diff --git a/include/linux/netdevice_xmit.h b/include/linux/netdevice_xmit.h new file mode 100644 index 000000000000..38325e070296 --- /dev/null +++ b/include/linux/netdevice_xmit.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _LINUX_NETDEVICE_XMIT_H +#define _LINUX_NETDEVICE_XMIT_H + +struct netdev_xmit { + u16 recursion; + u8 more; +#ifdef CONFIG_NET_EGRESS + u8 skip_txqueue; +#endif +}; + +#endif diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 2683b2b77612..2b8aac2c70ad 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -376,15 +376,11 @@ int nf_route(struct net *net, struct dst_entry **dst, struct flowi *fl, struct nf_conn; enum nf_nat_manip_type; struct nlattr; -enum ip_conntrack_dir; struct nf_nat_hook { int (*parse_nat_setup)(struct nf_conn *ct, enum nf_nat_manip_type manip, const struct nlattr *attr); void (*decode_session)(struct sk_buff *skb, struct flowi *fl); - unsigned int (*manip_pkt)(struct sk_buff *skb, struct nf_conn *ct, - enum nf_nat_manip_type mtype, - enum ip_conntrack_dir dir); void (*remove_nat_bysrc)(struct nf_conn *ct); }; diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 5897f3dbaf7c..f39f688d7285 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -357,7 +357,7 @@ extern struct static_key xt_tee_enabled; * Begin packet processing : all readers must wait the end * 1) Must be called with preemption disabled * 2) softirqs must be disabled too (or we should use this_cpu_add()) - * Returns : + * Returns: * 1 if no recursion on this cpu * 0 if recursion detected */ diff --git a/include/linux/netfilter_netdev.h b/include/linux/netfilter_netdev.h index 8676316547cc..3175073a66ba 100644 --- a/include/linux/netfilter_netdev.h +++ b/include/linux/netfilter_netdev.h @@ -66,7 +66,6 @@ static inline bool nf_hook_egress_active(void) * @rc: result code which shall be returned by __dev_queue_xmit() on failure * @dev: netdev whose egress hooks shall be applied to @skb * - * Returns @skb on success or %NULL if the packet was consumed or filtered. * Caller must hold rcu_read_lock. * * On ingress, packets are classified first by tc, then by netfilter. @@ -81,6 +80,8 @@ static inline bool nf_hook_egress_active(void) * called recursively by tunnel drivers such as vxlan, the flag is reverted to * false after sch_handle_egress(). This ensures that netfilter is applied * both on the overlay and underlying network. + * + * Returns: @skb on success or %NULL if the packet was consumed or filtered. */ static inline struct sk_buff *nf_hook_egress(struct sk_buff *skb, int *rc, struct net_device *dev) diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 100cbb261269..071d05d81d38 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -18,102 +18,30 @@ #include <linux/fs.h> #include <linux/pagemap.h> #include <linux/uio.h> +#include <linux/rolling_buffer.h> enum netfs_sreq_ref_trace; - -/* - * Overload PG_private_2 to give us PG_fscache - this is used to indicate that - * a page is currently backed by a local disk cache - */ -#define folio_test_fscache(folio) folio_test_private_2(folio) -#define PageFsCache(page) PagePrivate2((page)) -#define SetPageFsCache(page) SetPagePrivate2((page)) -#define ClearPageFsCache(page) ClearPagePrivate2((page)) -#define TestSetPageFsCache(page) TestSetPagePrivate2((page)) -#define TestClearPageFsCache(page) TestClearPagePrivate2((page)) +typedef struct mempool_s mempool_t; +struct folio_queue; /** - * folio_start_fscache - Start an fscache write on a folio. + * folio_start_private_2 - Start an fscache write on a folio. [DEPRECATED] * @folio: The folio. * * Call this function before writing a folio to a local cache. Starting a * second write before the first one finishes is not allowed. + * + * Note that this should no longer be used. */ -static inline void folio_start_fscache(struct folio *folio) +static inline void folio_start_private_2(struct folio *folio) { VM_BUG_ON_FOLIO(folio_test_private_2(folio), folio); folio_get(folio); folio_set_private_2(folio); } -/** - * folio_end_fscache - End an fscache write on a folio. - * @folio: The folio. - * - * Call this function after the folio has been written to the local cache. - * This will wake any sleepers waiting on this folio. - */ -static inline void folio_end_fscache(struct folio *folio) -{ - folio_end_private_2(folio); -} - -/** - * folio_wait_fscache - Wait for an fscache write on this folio to end. - * @folio: The folio. - * - * If this folio is currently being written to a local cache, wait for - * the write to finish. Another write may start after this one finishes, - * unless the caller holds the folio lock. - */ -static inline void folio_wait_fscache(struct folio *folio) -{ - folio_wait_private_2(folio); -} - -/** - * folio_wait_fscache_killable - Wait for an fscache write on this folio to end. - * @folio: The folio. - * - * If this folio is currently being written to a local cache, wait - * for the write to finish or for a fatal signal to be received. - * Another write may start after this one finishes, unless the caller - * holds the folio lock. - * - * Return: - * - 0 if successful. - * - -EINTR if a fatal signal was encountered. - */ -static inline int folio_wait_fscache_killable(struct folio *folio) -{ - return folio_wait_private_2_killable(folio); -} - -static inline void set_page_fscache(struct page *page) -{ - folio_start_fscache(page_folio(page)); -} - -static inline void end_page_fscache(struct page *page) -{ - folio_end_private_2(page_folio(page)); -} - -static inline void wait_on_page_fscache(struct page *page) -{ - folio_wait_private_2(page_folio(page)); -} - -static inline int wait_on_page_fscache_killable(struct page *page) -{ - return folio_wait_private_2_killable(page_folio(page)); -} - -/* Marks used on xarray-based buffers */ -#define NETFS_BUF_PUT_MARK XA_MARK_0 /* - Page needs putting */ -#define NETFS_BUF_PAGECACHE_MARK XA_MARK_1 /* - Page needs wb/dirty flag wrangling */ - enum netfs_io_source { + NETFS_SOURCE_UNKNOWN, NETFS_FILL_WITH_ZEROES, NETFS_DOWNLOAD_FROM_SERVER, NETFS_READ_FROM_CACHE, @@ -135,14 +63,17 @@ struct netfs_inode { #if IS_ENABLED(CONFIG_FSCACHE) struct fscache_cookie *cache; #endif + struct mutex wb_lock; /* Writeback serialisation */ loff_t remote_i_size; /* Size of the remote file */ loff_t zero_point; /* Size after which we assume there's no data * on the server */ + atomic_t io_count; /* Number of outstanding reqs */ unsigned long flags; #define NETFS_ICTX_ODIRECT 0 /* The file has DIO in progress */ #define NETFS_ICTX_UNBUFFERED 1 /* I/O should not use the pagecache */ #define NETFS_ICTX_WRITETHROUGH 2 /* Write-through caching */ -#define NETFS_ICTX_NO_WRITE_STREAMING 3 /* Don't engage in write-streaming */ +#define NETFS_ICTX_MODIFIED_ATTR 3 /* Indicate change in mtime/ctime */ +#define NETFS_ICTX_SINGLE_NO_UPLOAD 4 /* Monolithic payload, cache but no upload */ }; /* @@ -165,16 +96,25 @@ struct netfs_folio { unsigned int dirty_len; /* Write-streaming dirty data length */ }; #define NETFS_FOLIO_INFO 0x1UL /* OR'd with folio->private. */ +#define NETFS_FOLIO_COPY_TO_CACHE ((struct netfs_group *)0x356UL) /* Write to the cache only */ -static inline struct netfs_folio *netfs_folio_info(struct folio *folio) +static inline bool netfs_is_folio_info(const void *priv) { - void *priv = folio_get_private(folio); + return (unsigned long)priv & NETFS_FOLIO_INFO; +} - if ((unsigned long)priv & NETFS_FOLIO_INFO) +static inline struct netfs_folio *__netfs_folio_info(const void *priv) +{ + if (netfs_is_folio_info(priv)) return (struct netfs_folio *)((unsigned long)priv & ~NETFS_FOLIO_INFO); return NULL; } +static inline struct netfs_folio *netfs_folio_info(struct folio *folio) +{ + return __netfs_folio_info(folio_get_private(folio)); +} + static inline struct netfs_group *netfs_folio_group(struct folio *folio) { struct netfs_folio *finfo; @@ -187,6 +127,35 @@ static inline struct netfs_group *netfs_folio_group(struct folio *folio) } /* + * Stream of I/O subrequests going to a particular destination, such as the + * server or the local cache. This is mainly intended for writing where we may + * have to write to multiple destinations concurrently. + */ +struct netfs_io_stream { + /* Submission tracking */ + struct netfs_io_subrequest *construct; /* Op being constructed */ + size_t sreq_max_len; /* Maximum size of a subrequest */ + unsigned int sreq_max_segs; /* 0 or max number of segments in an iterator */ + unsigned int submit_off; /* Folio offset we're submitting from */ + unsigned int submit_len; /* Amount of data left to submit */ + unsigned int submit_extendable_to; /* Amount I/O can be rounded up to */ + void (*prepare_write)(struct netfs_io_subrequest *subreq); + void (*issue_write)(struct netfs_io_subrequest *subreq); + /* Collection tracking */ + struct list_head subrequests; /* Contributory I/O operations */ + struct netfs_io_subrequest *front; /* Op being collected */ + unsigned long long collected_to; /* Position we've collected results to */ + size_t transferred; /* The amount transferred from this stream */ + enum netfs_io_source source; /* Where to read from/write to */ + unsigned short error; /* Aggregate error for the stream */ + unsigned char stream_nr; /* Index of stream in parent table */ + bool avail; /* T if stream is available */ + bool active; /* T if stream is active */ + bool need_retry; /* T if this stream needs retrying */ + bool failed; /* T if this stream failed */ +}; + +/* * Resources required to do operations on a cache. */ struct netfs_cache_resources { @@ -209,33 +178,42 @@ struct netfs_io_subrequest { struct work_struct work; struct list_head rreq_link; /* Link in rreq->subrequests */ struct iov_iter io_iter; /* Iterator for this subrequest */ - loff_t start; /* Where to start the I/O */ + unsigned long long start; /* Where to start the I/O */ size_t len; /* Size of the I/O */ size_t transferred; /* Amount of data transferred */ refcount_t ref; short error; /* 0 or error that occurred */ unsigned short debug_index; /* Index in list (for debugging output) */ - unsigned int max_nr_segs; /* 0 or max number of segments in an iterator */ + unsigned int nr_segs; /* Number of segs in io_iter */ + u8 retry_count; /* The number of retries (0 on initial pass) */ enum netfs_io_source source; /* Where to read from/write to */ + unsigned char stream_nr; /* I/O stream this belongs to */ unsigned long flags; #define NETFS_SREQ_COPY_TO_CACHE 0 /* Set if should copy the data to the cache */ #define NETFS_SREQ_CLEAR_TAIL 1 /* Set if the rest of the read should be cleared */ -#define NETFS_SREQ_SHORT_IO 2 /* Set if the I/O was short */ #define NETFS_SREQ_SEEK_DATA_READ 3 /* Set if ->read() should SEEK_DATA first */ -#define NETFS_SREQ_NO_PROGRESS 4 /* Set if we didn't manage to read any data */ +#define NETFS_SREQ_MADE_PROGRESS 4 /* Set if we transferred at least some data */ #define NETFS_SREQ_ONDEMAND 5 /* Set if it's from on-demand read mode */ +#define NETFS_SREQ_BOUNDARY 6 /* Set if ends on hard boundary (eg. ceph object) */ +#define NETFS_SREQ_HIT_EOF 7 /* Set if short due to EOF */ +#define NETFS_SREQ_IN_PROGRESS 8 /* Unlocked when the subrequest completes */ +#define NETFS_SREQ_NEED_RETRY 9 /* Set if the filesystem requests a retry */ +#define NETFS_SREQ_FAILED 10 /* Set if the subreq failed unretryably */ }; enum netfs_io_origin { NETFS_READAHEAD, /* This read was triggered by readahead */ NETFS_READPAGE, /* This read is a synchronous read */ + NETFS_READ_GAPS, /* This read is a synchronous read to fill gaps */ + NETFS_READ_SINGLE, /* This read should be treated as a single object */ NETFS_READ_FOR_WRITE, /* This read is to prepare a write */ + NETFS_DIO_READ, /* This is a direct I/O read */ NETFS_WRITEBACK, /* This write was triggered by writepages */ + NETFS_WRITEBACK_SINGLE, /* This monolithic write was triggered by writepages */ NETFS_WRITETHROUGH, /* This write was made by netfs_perform_write() */ - NETFS_LAUNDER_WRITE, /* This is triggered by ->launder_folio() */ NETFS_UNBUFFERED_WRITE, /* This is an unbuffered write */ - NETFS_DIO_READ, /* This is a direct I/O read */ NETFS_DIO_WRITE, /* This is a direct I/O write */ + NETFS_PGPRIV2_COPY_TO_CACHE, /* [DEPRECATED] This is writing read data to the cache */ nr__netfs_io_origin } __mode(byte); @@ -252,41 +230,57 @@ struct netfs_io_request { struct address_space *mapping; /* The mapping being accessed */ struct kiocb *iocb; /* AIO completion vector */ struct netfs_cache_resources cache_resources; + struct netfs_io_request *copy_to_cache; /* Request to write just-read data to the cache */ + struct readahead_control *ractl; /* Readahead descriptor */ struct list_head proc_link; /* Link in netfs_iorequests */ - struct list_head subrequests; /* Contributory I/O operations */ - struct iov_iter iter; /* Unencrypted-side iterator */ - struct iov_iter io_iter; /* I/O (Encrypted-side) iterator */ + struct netfs_io_stream io_streams[2]; /* Streams of parallel I/O operations */ +#define NR_IO_STREAMS 2 //wreq->nr_io_streams + struct netfs_group *group; /* Writeback group being written back */ + struct rolling_buffer buffer; /* Unencrypted buffer */ +#define NETFS_ROLLBUF_PUT_MARK ROLLBUF_MARK_1 +#define NETFS_ROLLBUF_PAGECACHE_MARK ROLLBUF_MARK_2 + wait_queue_head_t waitq; /* Processor waiter */ void *netfs_priv; /* Private data for the netfs */ + void *netfs_priv2; /* Private data for the netfs */ struct bio_vec *direct_bv; /* DIO buffer list (when handling iovec-iter) */ unsigned int direct_bv_count; /* Number of elements in direct_bv[] */ unsigned int debug_id; unsigned int rsize; /* Maximum read size (0 for none) */ unsigned int wsize; /* Maximum write size (0 for none) */ - unsigned int subreq_counter; /* Next subreq->debug_index */ - atomic_t nr_outstanding; /* Number of ops in progress */ - atomic_t nr_copy_ops; /* Number of copy-to-cache ops in progress */ - size_t submitted; /* Amount submitted for I/O so far */ - size_t len; /* Length of the request */ - size_t upper_len; /* Length can be extended to here */ + atomic_t subreq_counter; /* Next subreq->debug_index */ + unsigned int nr_group_rel; /* Number of refs to release on ->group */ + spinlock_t lock; /* Lock for queuing subreqs */ + unsigned long long submitted; /* Amount submitted for I/O so far */ + unsigned long long len; /* Length of the request */ size_t transferred; /* Amount to be indicated as transferred */ - short error; /* 0 or error that occurred */ + long error; /* 0 or error that occurred */ enum netfs_io_origin origin; /* Origin of the request */ bool direct_bv_unpin; /* T if direct_bv[] must be unpinned */ - loff_t i_size; /* Size of the file */ - loff_t start; /* Start position */ + unsigned long long i_size; /* Size of the file */ + unsigned long long start; /* Start position */ + atomic64_t issued_to; /* Write issuer folio cursor */ + unsigned long long collected_to; /* Point we've collected to */ + unsigned long long cleaned_to; /* Position we've cleaned folios to */ + unsigned long long abandon_to; /* Position to abandon folios to */ pgoff_t no_unlock_folio; /* Don't unlock this folio after read */ + unsigned char front_folio_order; /* Order (size) of front folio */ refcount_t ref; unsigned long flags; -#define NETFS_RREQ_INCOMPLETE_IO 0 /* Some ioreqs terminated short or with error */ -#define NETFS_RREQ_COPY_TO_CACHE 1 /* Need to write to the cache */ +#define NETFS_RREQ_OFFLOAD_COLLECTION 0 /* Offload collection to workqueue */ #define NETFS_RREQ_NO_UNLOCK_FOLIO 2 /* Don't unlock no_unlock_folio on completion */ #define NETFS_RREQ_DONT_UNLOCK_FOLIOS 3 /* Don't unlock the folios on completion */ #define NETFS_RREQ_FAILED 4 /* The request failed */ #define NETFS_RREQ_IN_PROGRESS 5 /* Unlocked when the request completes */ -#define NETFS_RREQ_WRITE_TO_CACHE 7 /* Need to write to the cache */ +#define NETFS_RREQ_FOLIO_COPY_TO_CACHE 6 /* Copy current folio to cache from read */ #define NETFS_RREQ_UPLOAD_TO_SERVER 8 /* Need to write to the server */ #define NETFS_RREQ_NONBLOCK 9 /* Don't block if possible (O_NONBLOCK) */ #define NETFS_RREQ_BLOCKED 10 /* We blocked */ +#define NETFS_RREQ_PAUSE 11 /* Pause subrequest generation */ +#define NETFS_RREQ_USE_IO_ITER 12 /* Use ->io_iter rather than ->i_pages */ +#define NETFS_RREQ_ALL_QUEUED 13 /* All subreqs are now queued */ +#define NETFS_RREQ_NEED_RETRY 14 /* Need to try retrying */ +#define NETFS_RREQ_USE_PGPRIV2 31 /* [DEPRECATED] Use PG_private_2 to mark + * write to cache on read */ const struct netfs_request_ops *netfs_ops; void (*cleanup)(struct netfs_io_request *req); }; @@ -295,15 +289,15 @@ struct netfs_io_request { * Operations the network filesystem can/must provide to the helpers. */ struct netfs_request_ops { - unsigned int io_request_size; /* Alloc size for netfs_io_request struct */ - unsigned int io_subrequest_size; /* Alloc size for netfs_io_subrequest struct */ + mempool_t *request_pool; + mempool_t *subrequest_pool; int (*init_request)(struct netfs_io_request *rreq, struct file *file); void (*free_request)(struct netfs_io_request *rreq); void (*free_subrequest)(struct netfs_io_subrequest *rreq); /* Read request handling */ void (*expand_readahead)(struct netfs_io_request *rreq); - bool (*clamp_length)(struct netfs_io_subrequest *subreq); + int (*prepare_read)(struct netfs_io_subrequest *subreq); void (*issue_read)(struct netfs_io_subrequest *subreq); bool (*is_still_valid)(struct netfs_io_request *rreq); int (*check_write_begin)(struct file *file, loff_t pos, unsigned len, @@ -312,10 +306,13 @@ struct netfs_request_ops { /* Modification handling */ void (*update_i_size)(struct inode *inode, loff_t i_size); + void (*post_modify)(struct inode *inode); /* Write request handling */ - void (*create_write_requests)(struct netfs_io_request *wreq, - loff_t start, size_t len); + void (*begin_writeback)(struct netfs_io_request *wreq); + void (*prepare_write)(struct netfs_io_subrequest *subreq); + void (*issue_write)(struct netfs_io_subrequest *subreq); + void (*retry_request)(struct netfs_io_request *wreq, struct netfs_io_stream *stream); void (*invalidate_cache)(struct netfs_io_request *wreq); }; @@ -350,15 +347,27 @@ struct netfs_cache_ops { netfs_io_terminated_t term_func, void *term_func_priv); + /* Write data to the cache from a netfs subrequest. */ + void (*issue_write)(struct netfs_io_subrequest *subreq); + /* Expand readahead request */ void (*expand_readahead)(struct netfs_cache_resources *cres, - loff_t *_start, size_t *_len, loff_t i_size); + unsigned long long *_start, + unsigned long long *_len, + unsigned long long i_size); /* Prepare a read operation, shortening it to a cached/uncached * boundary as appropriate. */ enum netfs_io_source (*prepare_read)(struct netfs_io_subrequest *subreq, - loff_t i_size); + unsigned long long i_size); + + /* Prepare a write subrequest, working out if we're allowed to do it + * and finding out the maximum amount of data to gather before + * attempting to submit. If we're not permitted to do it, the + * subrequest should be marked failed. + */ + void (*prepare_write_subreq)(struct netfs_io_subrequest *subreq); /* Prepare a write operation, working out what part of the write we can * actually do. @@ -384,6 +393,7 @@ struct netfs_cache_ops { }; /* High-level read API. */ +ssize_t netfs_unbuffered_read_iter_locked(struct kiocb *iocb, struct iov_iter *iter); ssize_t netfs_unbuffered_read_iter(struct kiocb *iocb, struct iov_iter *iter); ssize_t netfs_buffered_read_iter(struct kiocb *iocb, struct iov_iter *iter); ssize_t netfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter); @@ -394,8 +404,17 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, ssize_t netfs_buffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *from, struct netfs_group *netfs_group); ssize_t netfs_unbuffered_write_iter(struct kiocb *iocb, struct iov_iter *from); +ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *iter, + struct netfs_group *netfs_group); ssize_t netfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from); +/* Single, monolithic object read/write API. */ +void netfs_single_mark_inode_dirty(struct inode *inode); +ssize_t netfs_read_single(struct inode *inode, struct file *file, struct iov_iter *iter); +int netfs_writeback_single(struct address_space *mapping, + struct writeback_control *wbc, + struct iov_iter *iter); + /* Address operations API */ struct readahead_control; void netfs_readahead(struct readahead_control *); @@ -410,13 +429,13 @@ int netfs_unpin_writeback(struct inode *inode, struct writeback_control *wbc); void netfs_clear_inode_writeback(struct inode *inode, const void *aux); void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length); bool netfs_release_folio(struct folio *folio, gfp_t gfp); -int netfs_launder_folio(struct folio *folio); /* VMA operations API. */ vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_group); /* (Sub)request management API. */ -void netfs_subreq_terminated(struct netfs_io_subrequest *, ssize_t, bool); +void netfs_read_subreq_progress(struct netfs_io_subrequest *subreq); +void netfs_read_subreq_terminated(struct netfs_io_subrequest *subreq); void netfs_get_subrequest(struct netfs_io_subrequest *subreq, enum netfs_sreq_ref_trace what); void netfs_put_subrequest(struct netfs_io_subrequest *subreq, @@ -426,9 +445,7 @@ ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len, iov_iter_extraction_t extraction_flags); size_t netfs_limit_iter(const struct iov_iter *iter, size_t start_offset, size_t max_size, size_t max_segs); -struct netfs_io_subrequest *netfs_create_write_request( - struct netfs_io_request *wreq, enum netfs_io_source dest, - loff_t start, size_t len, work_func_t worker); +void netfs_prepare_write_failed(struct netfs_io_subrequest *subreq); void netfs_write_subrequest_terminated(void *_op, ssize_t transferred_or_error, bool was_async); void netfs_queue_write_request(struct netfs_io_subrequest *subreq); @@ -440,6 +457,18 @@ void netfs_end_io_write(struct inode *inode); int netfs_start_io_direct(struct inode *inode); void netfs_end_io_direct(struct inode *inode); +/* Miscellaneous APIs. */ +struct folio_queue *netfs_folioq_alloc(unsigned int rreq_id, gfp_t gfp, + unsigned int trace /*enum netfs_folioq_trace*/); +void netfs_folioq_free(struct folio_queue *folioq, + unsigned int trace /*enum netfs_trace_folioq*/); + +/* Buffer wrangling helpers API. */ +int netfs_alloc_folioq_buffer(struct address_space *mapping, + struct folio_queue **_buffer, + size_t *_cur_size, ssize_t size, gfp_t gfp); +void netfs_free_folioq_buffer(struct folio_queue *fq); + /** * netfs_inode - Get the netfs inode context from the inode * @inode: The inode to query @@ -469,9 +498,11 @@ static inline void netfs_inode_init(struct netfs_inode *ctx, ctx->remote_i_size = i_size_read(&ctx->inode); ctx->zero_point = LLONG_MAX; ctx->flags = 0; + atomic_set(&ctx->io_count, 0); #if IS_ENABLED(CONFIG_FSCACHE) ctx->cache = NULL; #endif + mutex_init(&ctx->wb_lock); /* ->releasepage() drives zero_point */ if (use_zero_point) { ctx->zero_point = ctx->remote_i_size; @@ -511,4 +542,20 @@ static inline struct fscache_cookie *netfs_i_cookie(struct netfs_inode *ctx) #endif } +/** + * netfs_wait_for_outstanding_io - Wait for outstanding I/O to complete + * @inode: The netfs inode to wait on + * + * Wait for outstanding I/O requests of any type to complete. This is intended + * to be called from inode eviction routines. This makes sure that any + * resources held by those requests are cleaned up before we let the inode get + * cleaned up. + */ +static inline void netfs_wait_for_outstanding_io(struct inode *inode) +{ + struct netfs_inode *ictx = netfs_inode(inode); + + wait_var_event(&ictx->io_count, atomic_read(&ictx->io_count) == 0); +} + #endif /* _LINUX_NETFS_H */ diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 5df7340d4dab..c3ae84a77e16 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -34,6 +34,7 @@ struct netlink_skb_parms { #define NETLINK_CB(skb) (*(struct netlink_skb_parms*)&((skb)->cb)) #define NETLINK_CREDS(skb) (&NETLINK_CB((skb)).creds) +#define NETLINK_CTX_SIZE 48 void netlink_table_grab(void); @@ -47,7 +48,6 @@ struct netlink_kernel_cfg { unsigned int groups; unsigned int flags; void (*input)(struct sk_buff *skb); - struct mutex *cb_mutex; int (*bind)(struct net *net, int group); void (*unbind)(struct net *net, int group); void (*release) (struct sock *sk, unsigned long *groups); @@ -240,7 +240,7 @@ int netlink_register_notifier(struct notifier_block *nb); int netlink_unregister_notifier(struct notifier_block *nb); /* finegrained unicast helpers: */ -struct sock *netlink_getsockbyfilp(struct file *filp); +struct sock *netlink_getsockbyfd(int fd); int netlink_attachskb(struct sock *sk, struct sk_buff *skb, long *timeo, struct sock *ssk); void netlink_detachskb(struct sock *sk, struct sk_buff *skb); @@ -294,7 +294,7 @@ struct netlink_callback { int flags; bool strict_check; union { - u8 ctx[48]; + u8 ctx[NETLINK_CTX_SIZE]; /* args is deprecated. Cast a struct over ctx instead * for proper type safety. @@ -303,7 +303,7 @@ struct netlink_callback { }; }; -#define NL_ASSERT_DUMP_CTX_FITS(type_name) \ +#define NL_ASSERT_CTX_FITS(type_name) \ BUILD_BUG_ON(sizeof(type_name) > \ sizeof_field(struct netlink_callback, ctx)) diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index bd19c4b91e31..f91e50a76efd 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -32,6 +32,7 @@ struct netpoll { bool ipv6; u16 local_port, remote_port; u8 remote_mac[ETH_ALEN]; + struct sk_buff_head skb_pool; }; struct netpoll_info { @@ -56,7 +57,7 @@ static inline void netpoll_poll_disable(struct net_device *dev) { return; } static inline void netpoll_poll_enable(struct net_device *dev) { return; } #endif -void netpoll_send_udp(struct netpoll *np, const char *msg, int len); +int netpoll_send_udp(struct netpoll *np, const char *msg, int len); void netpoll_print_options(struct netpoll *np); int netpoll_parse_options(struct netpoll *np, char *opt); int __netpoll_setup(struct netpoll *np, struct net_device *ndev); @@ -64,6 +65,7 @@ int netpoll_setup(struct netpoll *np); void __netpoll_cleanup(struct netpoll *np); void __netpoll_free(struct netpoll *np); void netpoll_cleanup(struct netpoll *np); +void do_netpoll_cleanup(struct netpoll *np); netdev_tx_t netpoll_send_skb(struct netpoll *np, struct sk_buff *skb); #ifdef CONFIG_NETPOLL @@ -71,7 +73,7 @@ static inline void *netpoll_poll_lock(struct napi_struct *napi) { struct net_device *dev = napi->dev; - if (dev && dev->npinfo) { + if (dev && rcu_access_pointer(dev->npinfo)) { int owner = smp_processor_id(); while (cmpxchg(&napi->poll_owner, -1, owner) != -1) diff --git a/include/linux/nfs.h b/include/linux/nfs.h index ceb70a926b95..9ad727ddfedb 100644 --- a/include/linux/nfs.h +++ b/include/linux/nfs.h @@ -8,11 +8,20 @@ #ifndef _LINUX_NFS_H #define _LINUX_NFS_H +#include <linux/cred.h> +#include <linux/sunrpc/auth.h> #include <linux/sunrpc/msg_prot.h> #include <linux/string.h> #include <linux/crc32.h> #include <uapi/linux/nfs.h> +/* The LOCALIO program is entirely private to Linux and is + * NOT part of the uapi. + */ +#define NFS_LOCALIO_PROGRAM 400122 +#define LOCALIOPROC_NULL 0 +#define LOCALIOPROC_UUID_IS_LOCAL 1 + /* * This is the kernel NFS client file handle representation */ diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index ef8d2d618d5b..71fbebfa43c7 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -17,6 +17,7 @@ #include <linux/uidgid.h> #include <uapi/linux/nfs4.h> #include <linux/sunrpc/msg_prot.h> +#include <linux/sunrpc/xdrgen/nfs4_1.h> enum nfs4_acl_whotype { NFS4_ACL_WHO_NAMED = 0, @@ -281,15 +282,18 @@ enum nfsstat4 { /* nfs42 */ NFS4ERR_PARTNER_NOTSUPP = 10088, NFS4ERR_PARTNER_NO_AUTH = 10089, - NFS4ERR_UNION_NOTSUPP = 10090, - NFS4ERR_OFFLOAD_DENIED = 10091, - NFS4ERR_WRONG_LFS = 10092, - NFS4ERR_BADLABEL = 10093, - NFS4ERR_OFFLOAD_NO_REQS = 10094, + NFS4ERR_UNION_NOTSUPP = 10090, + NFS4ERR_OFFLOAD_DENIED = 10091, + NFS4ERR_WRONG_LFS = 10092, + NFS4ERR_BADLABEL = 10093, + NFS4ERR_OFFLOAD_NO_REQS = 10094, /* xattr (RFC8276) */ - NFS4ERR_NOXATTR = 10095, - NFS4ERR_XATTR2BIG = 10096, + NFS4ERR_NOXATTR = 10095, + NFS4ERR_XATTR2BIG = 10096, + + /* can be used for internal errors */ + NFS4ERR_FIRST_FREE }; /* error codes for internal client use */ @@ -362,11 +366,13 @@ enum limit_by4 { NFS4_LIMIT_BLOCKS = 2 }; -enum open_delegation_type4 { +enum nfs4_open_delegation_type4 { NFS4_OPEN_DELEGATE_NONE = 0, NFS4_OPEN_DELEGATE_READ = 1, NFS4_OPEN_DELEGATE_WRITE = 2, NFS4_OPEN_DELEGATE_NONE_EXT = 3, /* 4.1 */ + NFS4_OPEN_DELEGATE_READ_ATTRS_DELEG = 4, + NFS4_OPEN_DELEGATE_WRITE_ATTRS_DELEG = 5, }; enum why_no_delegation4 { /* new to v4.1 */ @@ -586,6 +592,9 @@ enum { #define FATTR4_WORD2_SECURITY_LABEL BIT(FATTR4_SEC_LABEL - 64) #define FATTR4_WORD2_MODE_UMASK BIT(FATTR4_MODE_UMASK - 64) #define FATTR4_WORD2_XATTR_SUPPORT BIT(FATTR4_XATTR_SUPPORT - 64) +#define FATTR4_WORD2_TIME_DELEG_ACCESS BIT(FATTR4_TIME_DELEG_ACCESS - 64) +#define FATTR4_WORD2_TIME_DELEG_MODIFY BIT(FATTR4_TIME_DELEG_MODIFY - 64) +#define FATTR4_WORD2_OPEN_ARGUMENTS BIT(FATTR4_OPEN_ARGUMENTS - 64) /* MDS threshold bitmap bits */ #define THRESHOLD_RD (1UL << 0) @@ -701,6 +710,12 @@ enum state_protect_how4 { SP4_SSV = 2 }; +/* GET_DIR_DELEGATION non-fatal status codes */ +enum gddrnf4_status { + GDD4_OK = 0, + GDD4_UNAVAIL = 1 +}; + enum pnfs_layouttype { LAYOUT_NFSV4_1_FILES = 1, LAYOUT_OSD2_OBJECTS = 2, diff --git a/include/linux/nfs_common.h b/include/linux/nfs_common.h new file mode 100644 index 000000000000..a541c3a02887 --- /dev/null +++ b/include/linux/nfs_common.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * This file contains constants and methods used by both NFS client and server. + */ +#ifndef _LINUX_NFS_COMMON_H +#define _LINUX_NFS_COMMON_H + +#include <linux/errno.h> +#include <uapi/linux/nfs.h> + +/* Mapping from NFS error code to "errno" error code. */ + +int nfs_stat_to_errno(enum nfs_stat status); +int nfs4_stat_to_errno(int stat); + +__u32 nfs_localio_errno_to_nfs4_stat(int errno); + +#endif /* _LINUX_NFS_COMMON_H */ diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index d59116ac8209..67ae2c3f41d2 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -77,6 +77,23 @@ struct nfs_lock_context { struct rcu_head rcu_head; }; +struct nfs_file_localio { + struct nfsd_file __rcu *ro_file; + struct nfsd_file __rcu *rw_file; + struct list_head list; + void __rcu *nfs_uuid; /* opaque pointer to 'nfs_uuid_t' */ +}; + +static inline void nfs_localio_file_init(struct nfs_file_localio *nfl) +{ +#if IS_ENABLED(CONFIG_NFS_LOCALIO) + nfl->ro_file = NULL; + nfl->rw_file = NULL; + INIT_LIST_HEAD(&nfl->list); + nfl->nfs_uuid = NULL; +#endif +} + struct nfs4_state; struct nfs_open_context { struct nfs_lock_context lock_context; @@ -87,15 +104,16 @@ struct nfs_open_context { struct nfs4_state *state; fmode_t mode; + int error; unsigned long flags; #define NFS_CONTEXT_BAD (2) #define NFS_CONTEXT_UNLOCK (3) #define NFS_CONTEXT_FILE_OPEN (4) - int error; - struct list_head list; struct nfs4_threshold *mdsthreshold; + struct list_head list; struct rcu_head rcu_head; + struct nfs_file_localio nfl; }; struct nfs_open_dir_context { @@ -561,6 +579,9 @@ extern int nfs_may_open(struct inode *inode, const struct cred *cred, int openfl extern void nfs_access_zap_cache(struct inode *inode); extern int nfs_access_get_cached(struct inode *inode, const struct cred *cred, u32 *mask, bool may_block); +extern int nfs_atomic_open_v23(struct inode *dir, struct dentry *dentry, + struct file *file, unsigned int open_flags, + umode_t mode); /* * linux/fs/nfs/symlink.c diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 92de074e63b9..f00bfcee7120 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -8,6 +8,7 @@ #include <linux/wait.h> #include <linux/nfs_xdr.h> #include <linux/sunrpc/xprt.h> +#include <linux/nfslocalio.h> #include <linux/atomic.h> #include <linux/refcount.h> @@ -125,6 +126,13 @@ struct nfs_client { struct net *cl_net; struct list_head pending_cb_stateids; struct rcu_head rcu; + +#if IS_ENABLED(CONFIG_NFS_LOCALIO) + struct timespec64 cl_nfssvc_boot; + seqlock_t cl_boot_lock; + nfs_uuid_t cl_uuid; + struct work_struct cl_local_probe_work; +#endif /* CONFIG_NFS_LOCALIO */ }; /* @@ -140,6 +148,7 @@ struct nfs_server { struct rpc_clnt * client_acl; /* ACL RPC client handle */ struct nlm_host *nlm_host; /* NLM client handle */ struct nfs_iostats __percpu *io_stats; /* I/O statistics */ + wait_queue_head_t write_congestion_wait; /* wait until write congestion eases */ atomic_long_t writeback; /* number of writeback pages */ unsigned int write_congested;/* flag set when writeback gets too high */ unsigned int flags; /* various flags */ @@ -157,6 +166,7 @@ struct nfs_server { #define NFS_MOUNT_WRITE_WAIT 0x02000000 #define NFS_MOUNT_TRUNK_DISCOVERY 0x04000000 #define NFS_MOUNT_SHUTDOWN 0x08000000 +#define NFS_MOUNT_NO_ALIGNWRITE 0x10000000 unsigned int fattr_valid; /* Valid attributes */ unsigned int caps; /* server capabilities */ @@ -233,12 +243,12 @@ struct nfs_server { /* the following fields are protected by nfs_client->cl_lock */ struct rb_root state_owners; #endif - struct ida openowner_id; - struct ida lockowner_id; + atomic64_t owner_ctr; struct list_head state_owners_lru; struct list_head layouts; struct list_head delegations; struct list_head ss_copies; + struct list_head ss_src_copies; unsigned long delegation_gen; unsigned long mig_gen; @@ -278,6 +288,9 @@ struct nfs_server { #define NFS_CAP_LGOPEN (1U << 5) #define NFS_CAP_CASE_INSENSITIVE (1U << 6) #define NFS_CAP_CASE_PRESERVING (1U << 7) +#define NFS_CAP_REBOOT_LAYOUTRETURN (1U << 8) +#define NFS_CAP_OPEN_XOR (1U << 12) +#define NFS_CAP_DELEGTIME (1U << 13) #define NFS_CAP_POSIX_LOCK (1U << 14) #define NFS_CAP_UIDGID_NOMAP (1U << 15) #define NFS_CAP_STATEID_NFSV41 (1U << 16) diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 1c315f854ea8..169b4ae30ff4 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -152,11 +152,8 @@ extern void nfs_pageio_cond_complete(struct nfs_pageio_descriptor *, pgoff_t); extern size_t nfs_generic_pg_test(struct nfs_pageio_descriptor *desc, struct nfs_page *prev, struct nfs_page *req); -extern int nfs_wait_on_request(struct nfs_page *); extern void nfs_unlock_request(struct nfs_page *req); extern void nfs_unlock_and_release_request(struct nfs_page *); -extern struct nfs_page *nfs_page_group_lock_head(struct nfs_page *req); -extern int nfs_page_group_lock_subrequests(struct nfs_page *head); extern void nfs_join_page_group(struct nfs_page *head, struct nfs_commit_info *cinfo, struct inode *inode); @@ -208,8 +205,8 @@ 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; + return req->wb_page->mapping->host; + return folio->mapping->host; } /** diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index d09b9773b20c..9155a6ffc370 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -446,7 +446,23 @@ struct nfs42_clone_res { struct stateowner_id { __u64 create_time; - __u32 uniquifier; + __u64 uniquifier; +}; + +struct nfs4_open_delegation { + __u32 open_delegation_type; + union { + struct { + fmode_t type; + __u32 do_recall; + nfs4_stateid stateid; + unsigned long pagemod_limit; + }; + struct { + __u32 why_no_delegation; + __u32 will_notify; + }; + }; }; /* @@ -468,7 +484,7 @@ struct nfs_openargs { nfs4_verifier verifier; /* EXCLUSIVE */ }; nfs4_stateid delegation; /* CLAIM_DELEGATE_CUR */ - fmode_t delegation_type; /* CLAIM_PREVIOUS */ + __u32 delegation_type; /* CLAIM_PREVIOUS */ } u; const struct qstr * name; const struct nfs_server *server; /* Needed for ID mapping */ @@ -490,13 +506,10 @@ struct nfs_openres { struct nfs_fattr * f_attr; struct nfs_seqid * seqid; const struct nfs_server *server; - fmode_t delegation_type; - nfs4_stateid delegation; - unsigned long pagemod_limit; - __u32 do_recall; __u32 attrset[NFS4_BITMAP_SIZE]; struct nfs4_string *owner; struct nfs4_string *group_owner; + struct nfs4_open_delegation delegation; __u32 access_request; __u32 access_supported; __u32 access_result; @@ -609,6 +622,13 @@ struct nfs_release_lockowner_res { struct nfs4_sequence_res seq_res; }; +struct nfs4_delegattr { + struct timespec64 atime; + struct timespec64 mtime; + bool atime_set; + bool mtime_set; +}; + struct nfs4_delegreturnargs { struct nfs4_sequence_args seq_args; const struct nfs_fh *fhandle; @@ -616,6 +636,7 @@ struct nfs4_delegreturnargs { const u32 *bitmask; u32 bitmask_store[NFS_BITMASK_SZ]; struct nfs4_layoutreturn_args *lr_args; + struct nfs4_delegattr *sattr_args; }; struct nfs4_delegreturnres { @@ -624,6 +645,8 @@ struct nfs4_delegreturnres { struct nfs_server *server; struct nfs4_layoutreturn_res *lr_res; int lr_ret; + bool sattr_res; + int sattr_ret; }; /* @@ -1190,6 +1213,14 @@ struct nfs4_statfs_res { struct nfs_fsstat *fsstat; }; +struct nfs4_open_caps { + u32 oa_share_access[1]; + u32 oa_share_deny[1]; + u32 oa_share_access_want[1]; + u32 oa_open_claim[1]; + u32 oa_createmode[1]; +}; + struct nfs4_server_caps_arg { struct nfs4_sequence_args seq_args; struct nfs_fh *fhandle; @@ -1206,6 +1237,7 @@ struct nfs4_server_caps_res { u32 fh_expire_type; u32 case_insensitive; u32 case_preserving; + struct nfs4_open_caps open_caps; }; #define NFS4_PATHNAME_MAXCOMPONENTS 512 @@ -1283,11 +1315,6 @@ struct nfs4_fsid_present_res { #endif /* CONFIG_NFS_V4 */ -struct nfstime4 { - u64 seconds; - u32 nseconds; -}; - #ifdef CONFIG_NFS_V4_1 struct pnfs_commit_bucket { @@ -1304,7 +1331,7 @@ struct pnfs_commit_array { struct rcu_head rcu; refcount_t refcount; unsigned int nbuckets; - struct pnfs_commit_bucket buckets[]; + struct pnfs_commit_bucket buckets[] __counted_by(nbuckets); }; struct pnfs_ds_commit_info { @@ -1406,7 +1433,7 @@ struct nfs41_secinfo_no_name_args { struct nfs41_test_stateid_args { struct nfs4_sequence_args seq_args; - nfs4_stateid *stateid; + nfs4_stateid stateid; }; struct nfs41_test_stateid_res { @@ -1605,6 +1632,7 @@ enum { NFS_IOHDR_RESEND_PNFS, NFS_IOHDR_RESEND_MDS, NFS_IOHDR_UNSTABLE_WRITES, + NFS_IOHDR_ODIRECT, }; struct nfs_io_completion; @@ -1753,7 +1781,7 @@ struct nfs_rpc_ops { struct nfs_fattr *, struct inode *); int (*setattr) (struct dentry *, struct nfs_fattr *, struct iattr *); - int (*lookup) (struct inode *, struct dentry *, + int (*lookup) (struct inode *, struct dentry *, const struct qstr *, struct nfs_fh *, struct nfs_fattr *); int (*lookupp) (struct inode *, struct nfs_fh *, struct nfs_fattr *); @@ -1807,7 +1835,8 @@ struct nfs_rpc_ops { int open_flags, struct iattr *iattr, int *); - int (*have_delegation)(struct inode *, fmode_t); + int (*have_delegation)(struct inode *, fmode_t, int); + int (*return_delegation)(struct inode *); struct nfs_client *(*alloc_client) (const struct nfs_client_initdata *); struct nfs_client *(*init_client) (struct nfs_client *, const struct nfs_client_initdata *); @@ -1821,6 +1850,24 @@ struct nfs_rpc_ops { }; /* + * Helper functions used by NFS client and/or server + */ +static inline void encode_opaque_fixed(struct xdr_stream *xdr, + const void *buf, size_t len) +{ + WARN_ON_ONCE(xdr_stream_encode_opaque_fixed(xdr, buf, len) < 0); +} + +static inline int decode_opaque_fixed(struct xdr_stream *xdr, + void *buf, size_t len) +{ + ssize_t ret = xdr_stream_decode_opaque_fixed(xdr, buf, len); + if (unlikely(ret < 0)) + return -EIO; + return 0; +} + +/* * Function vectors etc. for the NFS client */ extern const struct nfs_rpc_ops nfs_v2_clientops; @@ -1833,4 +1880,4 @@ extern const struct rpc_version nfs_version4; extern const struct rpc_version nfsacl_version3; extern const struct rpc_program nfsacl_program; -#endif +#endif /* _LINUX_NFS_XDR_H */ diff --git a/include/linux/nfslocalio.h b/include/linux/nfslocalio.h new file mode 100644 index 000000000000..9aa8a43843d7 --- /dev/null +++ b/include/linux/nfslocalio.h @@ -0,0 +1,122 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2024 Mike Snitzer <snitzer@hammerspace.com> + * Copyright (C) 2024 NeilBrown <neilb@suse.de> + */ +#ifndef __LINUX_NFSLOCALIO_H +#define __LINUX_NFSLOCALIO_H + +#if IS_ENABLED(CONFIG_NFS_LOCALIO) + +#include <linux/module.h> +#include <linux/list.h> +#include <linux/uuid.h> +#include <linux/sunrpc/clnt.h> +#include <linux/sunrpc/svcauth.h> +#include <linux/nfs.h> +#include <net/net_namespace.h> + +struct nfs_client; +struct nfs_file_localio; + +/* + * Useful to allow a client to negotiate if localio + * possible with its server. + * + * See Documentation/filesystems/nfs/localio.rst for more detail. + */ +typedef struct { + uuid_t uuid; + unsigned nfs3_localio_probe_count; + /* this struct is over a cacheline, avoid bouncing */ + spinlock_t ____cacheline_aligned lock; + struct list_head list; + spinlock_t *list_lock; /* nn->local_clients_lock */ + struct net __rcu *net; /* nfsd's network namespace */ + struct auth_domain *dom; /* auth_domain for localio */ + /* Local files to close when net is shut down or exports change */ + struct list_head files; +} nfs_uuid_t; + +void nfs_uuid_init(nfs_uuid_t *); +bool nfs_uuid_begin(nfs_uuid_t *); +void nfs_uuid_end(nfs_uuid_t *); +void nfs_uuid_is_local(const uuid_t *, struct list_head *, spinlock_t *, + struct net *, struct auth_domain *, struct module *); + +void nfs_localio_enable_client(struct nfs_client *clp); +void nfs_localio_disable_client(struct nfs_client *clp); +void nfs_localio_invalidate_clients(struct list_head *nn_local_clients, + spinlock_t *nn_local_clients_lock); + +/* localio needs to map filehandle -> struct nfsd_file */ +extern struct nfsd_file * +nfsd_open_local_fh(struct net *, struct auth_domain *, struct rpc_clnt *, + const struct cred *, const struct nfs_fh *, + const fmode_t) __must_hold(rcu); +void nfs_close_local_fh(struct nfs_file_localio *); + +struct nfsd_localio_operations { + bool (*nfsd_net_try_get)(struct net *); + void (*nfsd_net_put)(struct net *); + struct nfsd_file *(*nfsd_open_local_fh)(struct net *, + struct auth_domain *, + struct rpc_clnt *, + const struct cred *, + const struct nfs_fh *, + const fmode_t); + struct net *(*nfsd_file_put_local)(struct nfsd_file *); + struct nfsd_file *(*nfsd_file_get)(struct nfsd_file *); + void (*nfsd_file_put)(struct nfsd_file *); + struct file *(*nfsd_file_file)(struct nfsd_file *); +} ____cacheline_aligned; + +extern void nfsd_localio_ops_init(void); +extern const struct nfsd_localio_operations *nfs_to; + +struct nfsd_file *nfs_open_local_fh(nfs_uuid_t *, + struct rpc_clnt *, const struct cred *, + const struct nfs_fh *, struct nfs_file_localio *, + const fmode_t); + +static inline void nfs_to_nfsd_net_put(struct net *net) +{ + /* + * Once reference to net (and associated nfsd_serv) is dropped, NFSD + * could be unloaded, so ensure safe return from nfsd_net_put() by + * always taking RCU. + */ + rcu_read_lock(); + nfs_to->nfsd_net_put(net); + rcu_read_unlock(); +} + +static inline void nfs_to_nfsd_file_put_local(struct nfsd_file *localio) +{ + /* + * Must not hold RCU otherwise nfsd_file_put() can easily trigger: + * "Voluntary context switch within RCU read-side critical section!" + * by scheduling deep in underlying filesystem (e.g. XFS). + */ + struct net *net = nfs_to->nfsd_file_put_local(localio); + + nfs_to_nfsd_net_put(net); +} + +#else /* CONFIG_NFS_LOCALIO */ + +struct nfs_file_localio; +static inline void nfs_close_local_fh(struct nfs_file_localio *nfl) +{ +} +static inline void nfsd_localio_ops_init(void) +{ +} +struct nfs_client; +static inline void nfs_localio_disable_client(struct nfs_client *clp) +{ +} + +#endif /* CONFIG_NFS_LOCALIO */ + +#endif /* __LINUX_NFSLOCALIO_H */ diff --git a/include/linux/nmi.h b/include/linux/nmi.h index f53438eae815..a8dfb38c9bb6 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -105,10 +105,12 @@ void watchdog_hardlockup_check(unsigned int cpu, struct pt_regs *regs); extern void hardlockup_detector_perf_stop(void); extern void hardlockup_detector_perf_restart(void); extern void hardlockup_detector_perf_cleanup(void); +extern void hardlockup_config_perf_event(const char *str); #else static inline void hardlockup_detector_perf_stop(void) { } static inline void hardlockup_detector_perf_restart(void) { } static inline void hardlockup_detector_perf_cleanup(void) { } +static inline void hardlockup_config_perf_event(const char *str) { } #endif void watchdog_hardlockup_stop(void); diff --git a/include/linux/node.h b/include/linux/node.h index dfc004e4bee7..9a881c2208b3 100644 --- a/include/linux/node.h +++ b/include/linux/node.h @@ -16,7 +16,6 @@ #define _LINUX_NODE_H_ #include <linux/device.h> -#include <linux/cpumask.h> #include <linux/list.h> /** diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index b61438313a73..9fd7a0ce9c1a 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -107,11 +107,11 @@ extern nodemask_t _unused_nodemask_arg_; */ #define nodemask_pr_args(maskp) __nodemask_pr_numnodes(maskp), \ __nodemask_pr_bits(maskp) -static inline unsigned int __nodemask_pr_numnodes(const nodemask_t *m) +static __always_inline unsigned int __nodemask_pr_numnodes(const nodemask_t *m) { return m ? MAX_NUMNODES : 0; } -static inline const unsigned long *__nodemask_pr_bits(const nodemask_t *m) +static __always_inline const unsigned long *__nodemask_pr_bits(const nodemask_t *m) { return m ? m->bits : NULL; } @@ -132,19 +132,19 @@ static __always_inline void __node_set(int node, volatile nodemask_t *dstp) } #define node_clear(node, dst) __node_clear((node), &(dst)) -static inline void __node_clear(int node, volatile nodemask_t *dstp) +static __always_inline void __node_clear(int node, volatile nodemask_t *dstp) { clear_bit(node, dstp->bits); } #define nodes_setall(dst) __nodes_setall(&(dst), MAX_NUMNODES) -static inline void __nodes_setall(nodemask_t *dstp, unsigned int nbits) +static __always_inline void __nodes_setall(nodemask_t *dstp, unsigned int nbits) { bitmap_fill(dstp->bits, nbits); } #define nodes_clear(dst) __nodes_clear(&(dst), MAX_NUMNODES) -static inline void __nodes_clear(nodemask_t *dstp, unsigned int nbits) +static __always_inline void __nodes_clear(nodemask_t *dstp, unsigned int nbits) { bitmap_zero(dstp->bits, nbits); } @@ -154,14 +154,14 @@ static inline void __nodes_clear(nodemask_t *dstp, unsigned int nbits) #define node_test_and_set(node, nodemask) \ __node_test_and_set((node), &(nodemask)) -static inline bool __node_test_and_set(int node, nodemask_t *addr) +static __always_inline bool __node_test_and_set(int node, nodemask_t *addr) { return test_and_set_bit(node, addr->bits); } #define nodes_and(dst, src1, src2) \ __nodes_and(&(dst), &(src1), &(src2), MAX_NUMNODES) -static inline void __nodes_and(nodemask_t *dstp, const nodemask_t *src1p, +static __always_inline void __nodes_and(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_and(dstp->bits, src1p->bits, src2p->bits, nbits); @@ -169,7 +169,7 @@ static inline void __nodes_and(nodemask_t *dstp, const nodemask_t *src1p, #define nodes_or(dst, src1, src2) \ __nodes_or(&(dst), &(src1), &(src2), MAX_NUMNODES) -static inline void __nodes_or(nodemask_t *dstp, const nodemask_t *src1p, +static __always_inline void __nodes_or(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_or(dstp->bits, src1p->bits, src2p->bits, nbits); @@ -177,7 +177,7 @@ static inline void __nodes_or(nodemask_t *dstp, const nodemask_t *src1p, #define nodes_xor(dst, src1, src2) \ __nodes_xor(&(dst), &(src1), &(src2), MAX_NUMNODES) -static inline void __nodes_xor(nodemask_t *dstp, const nodemask_t *src1p, +static __always_inline void __nodes_xor(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_xor(dstp->bits, src1p->bits, src2p->bits, nbits); @@ -185,7 +185,7 @@ static inline void __nodes_xor(nodemask_t *dstp, const nodemask_t *src1p, #define nodes_andnot(dst, src1, src2) \ __nodes_andnot(&(dst), &(src1), &(src2), MAX_NUMNODES) -static inline void __nodes_andnot(nodemask_t *dstp, const nodemask_t *src1p, +static __always_inline void __nodes_andnot(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_andnot(dstp->bits, src1p->bits, src2p->bits, nbits); @@ -193,7 +193,7 @@ static inline void __nodes_andnot(nodemask_t *dstp, const nodemask_t *src1p, #define nodes_complement(dst, src) \ __nodes_complement(&(dst), &(src), MAX_NUMNODES) -static inline void __nodes_complement(nodemask_t *dstp, +static __always_inline void __nodes_complement(nodemask_t *dstp, const nodemask_t *srcp, unsigned int nbits) { bitmap_complement(dstp->bits, srcp->bits, nbits); @@ -201,7 +201,7 @@ static inline void __nodes_complement(nodemask_t *dstp, #define nodes_equal(src1, src2) \ __nodes_equal(&(src1), &(src2), MAX_NUMNODES) -static inline bool __nodes_equal(const nodemask_t *src1p, +static __always_inline bool __nodes_equal(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_equal(src1p->bits, src2p->bits, nbits); @@ -209,7 +209,7 @@ static inline bool __nodes_equal(const nodemask_t *src1p, #define nodes_intersects(src1, src2) \ __nodes_intersects(&(src1), &(src2), MAX_NUMNODES) -static inline bool __nodes_intersects(const nodemask_t *src1p, +static __always_inline bool __nodes_intersects(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_intersects(src1p->bits, src2p->bits, nbits); @@ -217,33 +217,33 @@ static inline bool __nodes_intersects(const nodemask_t *src1p, #define nodes_subset(src1, src2) \ __nodes_subset(&(src1), &(src2), MAX_NUMNODES) -static inline bool __nodes_subset(const nodemask_t *src1p, +static __always_inline bool __nodes_subset(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_subset(src1p->bits, src2p->bits, nbits); } #define nodes_empty(src) __nodes_empty(&(src), MAX_NUMNODES) -static inline bool __nodes_empty(const nodemask_t *srcp, unsigned int nbits) +static __always_inline bool __nodes_empty(const nodemask_t *srcp, unsigned int nbits) { return bitmap_empty(srcp->bits, nbits); } #define nodes_full(nodemask) __nodes_full(&(nodemask), MAX_NUMNODES) -static inline bool __nodes_full(const nodemask_t *srcp, unsigned int nbits) +static __always_inline bool __nodes_full(const nodemask_t *srcp, unsigned int nbits) { return bitmap_full(srcp->bits, nbits); } #define nodes_weight(nodemask) __nodes_weight(&(nodemask), MAX_NUMNODES) -static inline int __nodes_weight(const nodemask_t *srcp, unsigned int nbits) +static __always_inline int __nodes_weight(const nodemask_t *srcp, unsigned int nbits) { return bitmap_weight(srcp->bits, nbits); } #define nodes_shift_right(dst, src, n) \ __nodes_shift_right(&(dst), &(src), (n), MAX_NUMNODES) -static inline void __nodes_shift_right(nodemask_t *dstp, +static __always_inline void __nodes_shift_right(nodemask_t *dstp, const nodemask_t *srcp, int n, int nbits) { bitmap_shift_right(dstp->bits, srcp->bits, n, nbits); @@ -251,7 +251,7 @@ static inline void __nodes_shift_right(nodemask_t *dstp, #define nodes_shift_left(dst, src, n) \ __nodes_shift_left(&(dst), &(src), (n), MAX_NUMNODES) -static inline void __nodes_shift_left(nodemask_t *dstp, +static __always_inline void __nodes_shift_left(nodemask_t *dstp, const nodemask_t *srcp, int n, int nbits) { bitmap_shift_left(dstp->bits, srcp->bits, n, nbits); @@ -261,13 +261,13 @@ static inline void __nodes_shift_left(nodemask_t *dstp, > MAX_NUMNODES, then the silly min_ts could be dropped. */ #define first_node(src) __first_node(&(src)) -static inline unsigned int __first_node(const nodemask_t *srcp) +static __always_inline unsigned int __first_node(const nodemask_t *srcp) { return min_t(unsigned int, MAX_NUMNODES, find_first_bit(srcp->bits, MAX_NUMNODES)); } #define next_node(n, src) __next_node((n), &(src)) -static inline unsigned int __next_node(int n, const nodemask_t *srcp) +static __always_inline unsigned int __next_node(int n, const nodemask_t *srcp) { return min_t(unsigned int, MAX_NUMNODES, find_next_bit(srcp->bits, MAX_NUMNODES, n+1)); } @@ -277,7 +277,7 @@ static inline unsigned int __next_node(int n, const nodemask_t *srcp) * the first node in src if needed. Returns MAX_NUMNODES if src is empty. */ #define next_node_in(n, src) __next_node_in((n), &(src)) -static inline unsigned int __next_node_in(int node, const nodemask_t *srcp) +static __always_inline unsigned int __next_node_in(int node, const nodemask_t *srcp) { unsigned int ret = __next_node(node, srcp); @@ -286,7 +286,7 @@ static inline unsigned int __next_node_in(int node, const nodemask_t *srcp) return ret; } -static inline void init_nodemask_of_node(nodemask_t *mask, int node) +static __always_inline void init_nodemask_of_node(nodemask_t *mask, int node) { nodes_clear(*mask); node_set(node, *mask); @@ -304,7 +304,7 @@ static inline void init_nodemask_of_node(nodemask_t *mask, int node) }) #define first_unset_node(mask) __first_unset_node(&(mask)) -static inline unsigned int __first_unset_node(const nodemask_t *maskp) +static __always_inline unsigned int __first_unset_node(const nodemask_t *maskp) { return min_t(unsigned int, MAX_NUMNODES, find_first_zero_bit(maskp->bits, MAX_NUMNODES)); @@ -338,21 +338,21 @@ static inline unsigned int __first_unset_node(const nodemask_t *maskp) #define nodemask_parse_user(ubuf, ulen, dst) \ __nodemask_parse_user((ubuf), (ulen), &(dst), MAX_NUMNODES) -static inline int __nodemask_parse_user(const char __user *buf, int len, +static __always_inline int __nodemask_parse_user(const char __user *buf, int len, nodemask_t *dstp, int nbits) { return bitmap_parse_user(buf, len, dstp->bits, nbits); } #define nodelist_parse(buf, dst) __nodelist_parse((buf), &(dst), MAX_NUMNODES) -static inline int __nodelist_parse(const char *buf, nodemask_t *dstp, int nbits) +static __always_inline int __nodelist_parse(const char *buf, nodemask_t *dstp, int nbits) { return bitmap_parselist(buf, dstp->bits, nbits); } #define node_remap(oldbit, old, new) \ __node_remap((oldbit), &(old), &(new), MAX_NUMNODES) -static inline int __node_remap(int oldbit, +static __always_inline int __node_remap(int oldbit, const nodemask_t *oldp, const nodemask_t *newp, int nbits) { return bitmap_bitremap(oldbit, oldp->bits, newp->bits, nbits); @@ -360,7 +360,7 @@ static inline int __node_remap(int oldbit, #define nodes_remap(dst, src, old, new) \ __nodes_remap(&(dst), &(src), &(old), &(new), MAX_NUMNODES) -static inline void __nodes_remap(nodemask_t *dstp, const nodemask_t *srcp, +static __always_inline void __nodes_remap(nodemask_t *dstp, const nodemask_t *srcp, const nodemask_t *oldp, const nodemask_t *newp, int nbits) { bitmap_remap(dstp->bits, srcp->bits, oldp->bits, newp->bits, nbits); @@ -368,7 +368,7 @@ static inline void __nodes_remap(nodemask_t *dstp, const nodemask_t *srcp, #define nodes_onto(dst, orig, relmap) \ __nodes_onto(&(dst), &(orig), &(relmap), MAX_NUMNODES) -static inline void __nodes_onto(nodemask_t *dstp, const nodemask_t *origp, +static __always_inline void __nodes_onto(nodemask_t *dstp, const nodemask_t *origp, const nodemask_t *relmapp, int nbits) { bitmap_onto(dstp->bits, origp->bits, relmapp->bits, nbits); @@ -376,7 +376,7 @@ static inline void __nodes_onto(nodemask_t *dstp, const nodemask_t *origp, #define nodes_fold(dst, orig, sz) \ __nodes_fold(&(dst), &(orig), sz, MAX_NUMNODES) -static inline void __nodes_fold(nodemask_t *dstp, const nodemask_t *origp, +static __always_inline void __nodes_fold(nodemask_t *dstp, const nodemask_t *origp, int sz, int nbits) { bitmap_fold(dstp->bits, origp->bits, sz, nbits); @@ -418,22 +418,22 @@ enum node_states { extern nodemask_t node_states[NR_NODE_STATES]; #if MAX_NUMNODES > 1 -static inline int node_state(int node, enum node_states state) +static __always_inline int node_state(int node, enum node_states state) { return node_isset(node, node_states[state]); } -static inline void node_set_state(int node, enum node_states state) +static __always_inline void node_set_state(int node, enum node_states state) { __node_set(node, &node_states[state]); } -static inline void node_clear_state(int node, enum node_states state) +static __always_inline void node_clear_state(int node, enum node_states state) { __node_clear(node, &node_states[state]); } -static inline int num_node_state(enum node_states state) +static __always_inline int num_node_state(enum node_states state) { return nodes_weight(node_states[state]); } @@ -443,11 +443,11 @@ static inline int num_node_state(enum node_states state) #define first_online_node first_node(node_states[N_ONLINE]) #define first_memory_node first_node(node_states[N_MEMORY]) -static inline unsigned int next_online_node(int nid) +static __always_inline unsigned int next_online_node(int nid) { return next_node(nid, node_states[N_ONLINE]); } -static inline unsigned int next_memory_node(int nid) +static __always_inline unsigned int next_memory_node(int nid) { return next_node(nid, node_states[N_MEMORY]); } @@ -455,13 +455,13 @@ static inline unsigned int next_memory_node(int nid) extern unsigned int nr_node_ids; extern unsigned int nr_online_nodes; -static inline void node_set_online(int nid) +static __always_inline void node_set_online(int nid) { node_set_state(nid, N_ONLINE); nr_online_nodes = num_node_state(N_ONLINE); } -static inline void node_set_offline(int nid) +static __always_inline void node_set_offline(int nid) { node_clear_state(nid, N_ONLINE); nr_online_nodes = num_node_state(N_ONLINE); @@ -469,20 +469,20 @@ static inline void node_set_offline(int nid) #else -static inline int node_state(int node, enum node_states state) +static __always_inline int node_state(int node, enum node_states state) { return node == 0; } -static inline void node_set_state(int node, enum node_states state) +static __always_inline void node_set_state(int node, enum node_states state) { } -static inline void node_clear_state(int node, enum node_states state) +static __always_inline void node_clear_state(int node, enum node_states state) { } -static inline int num_node_state(enum node_states state) +static __always_inline int num_node_state(enum node_states state) { return 1; } @@ -502,7 +502,7 @@ static inline int num_node_state(enum node_states state) #endif -static inline int node_random(const nodemask_t *maskp) +static __always_inline int node_random(const nodemask_t *maskp) { #if defined(CONFIG_NUMA) && (MAX_NUMNODES > 1) int w, bit; diff --git a/include/linux/notifier.h b/include/linux/notifier.h index 45702bdcbceb..b42e64734968 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -237,7 +237,5 @@ static inline int notifier_to_errno(int ret) #define KBD_KEYSYM 0x0004 /* Keyboard keysym */ #define KBD_POST_KEYSYM 0x0005 /* Called after keyboard keysym interpretation */ -extern struct blocking_notifier_head reboot_notifier_list; - #endif /* __KERNEL__ */ #endif /* _LINUX_NOTIFIER_H */ diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h index 5601d14e2886..dab6a1734a22 100644 --- a/include/linux/nsproxy.h +++ b/include/linux/nsproxy.h @@ -42,6 +42,17 @@ struct nsproxy { }; extern struct nsproxy init_nsproxy; +#define to_ns_common(__ns) \ + _Generic((__ns), \ + struct cgroup_namespace *: &(__ns->ns), \ + struct ipc_namespace *: &(__ns->ns), \ + struct net *: &(__ns->ns), \ + struct pid_namespace *: &(__ns->ns), \ + struct mnt_namespace *: &(__ns->ns), \ + struct time_namespace *: &(__ns->ns), \ + struct user_namespace *: &(__ns->ns), \ + struct uts_namespace *: &(__ns->ns)) + /* * A structure to encompass all bits needed to install * a partial or complete new set of namespaces. @@ -112,4 +123,6 @@ static inline void get_nsproxy(struct nsproxy *ns) refcount_inc(&ns->count); } +DEFINE_FREE(put_nsproxy, struct nsproxy *, if (_T) put_nsproxy(_T)) + #endif diff --git a/include/linux/numa.h b/include/linux/numa.h index 915033a75731..3567e40329eb 100644 --- a/include/linux/numa.h +++ b/include/linux/numa.h @@ -15,6 +15,11 @@ #define NUMA_NO_NODE (-1) #define NUMA_NO_MEMBLK (-1) +static inline bool numa_valid_node(int nid) +{ + return nid >= 0 && nid < MAX_NUMNODES; +} + /* optionally keep NUMA memory info available post init */ #ifdef CONFIG_NUMA_KEEP_MEMINFO #define __initdata_or_meminfo @@ -25,6 +30,12 @@ #ifdef CONFIG_NUMA #include <asm/sparsemem.h> +extern struct pglist_data *node_data[]; +#define NODE_DATA(nid) (node_data[nid]) + +void __init alloc_node_data(int nid); +void __init alloc_offline_node_data(int nid); + /* Generic implementation available */ int numa_nearest_node(int node, unsigned int state); @@ -36,12 +47,7 @@ int memory_add_physaddr_to_nid(u64 start); int phys_to_target_node(u64 start); #endif -#ifndef numa_fill_memblks -static inline int __init numa_fill_memblks(u64 start, u64 end) -{ - return NUMA_NO_MEMBLK; -} -#endif +int numa_fill_memblks(u64 start, u64 end); #else /* !CONFIG_NUMA */ static inline int numa_nearest_node(int node, unsigned int state) @@ -57,6 +63,8 @@ static inline int phys_to_target_node(u64 start) { return 0; } + +static inline void alloc_offline_node_data(int nid) {} #endif #define numa_map_to_online_node(node) numa_nearest_node(node, N_ONLINE) diff --git a/include/linux/numa_memblks.h b/include/linux/numa_memblks.h new file mode 100644 index 000000000000..dd85613cdd86 --- /dev/null +++ b/include/linux/numa_memblks.h @@ -0,0 +1,61 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __NUMA_MEMBLKS_H +#define __NUMA_MEMBLKS_H + +#ifdef CONFIG_NUMA_MEMBLKS +#include <linux/types.h> + +#define NR_NODE_MEMBLKS (MAX_NUMNODES * 2) + +void __init numa_set_distance(int from, int to, int distance); +void __init numa_reset_distance(void); + +struct numa_memblk { + u64 start; + u64 end; + int nid; +}; + +struct numa_meminfo { + int nr_blks; + struct numa_memblk blk[NR_NODE_MEMBLKS]; +}; + +int __init numa_add_memblk(int nodeid, u64 start, u64 end); +void __init numa_remove_memblk_from(int idx, struct numa_meminfo *mi); + +int __init numa_cleanup_meminfo(struct numa_meminfo *mi); + +int __init numa_memblks_init(int (*init_func)(void), + bool memblock_force_top_down); + +extern int numa_distance_cnt; + +#ifdef CONFIG_NUMA_EMU +extern int emu_nid_to_phys[MAX_NUMNODES]; +int numa_emu_cmdline(char *str); +void __init numa_emu_update_cpu_to_node(int *emu_nid_to_phys, + unsigned int nr_emu_nids); +u64 __init numa_emu_dma_end(void); +void __init numa_emulation(struct numa_meminfo *numa_meminfo, + int numa_dist_cnt); +#else +static inline void numa_emulation(struct numa_meminfo *numa_meminfo, + int numa_dist_cnt) +{ } +static inline int numa_emu_cmdline(char *str) +{ + return -EINVAL; +} +#endif /* CONFIG_NUMA_EMU */ + +#ifdef CONFIG_NUMA_KEEP_MEMINFO +extern int phys_to_target_node(u64 start); +#define phys_to_target_node phys_to_target_node +extern int memory_add_physaddr_to_nid(u64 start); +#define memory_add_physaddr_to_nid memory_add_physaddr_to_nid +#endif /* CONFIG_NUMA_KEEP_MEMINFO */ + +#endif /* CONFIG_NUMA_MEMBLKS */ + +#endif /* __NUMA_MEMBLKS_H */ diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h index 4109f1bd6128..9f6acadfe0c8 100644 --- a/include/linux/nvme-fc-driver.h +++ b/include/linux/nvme-fc-driver.h @@ -620,7 +620,7 @@ enum { * * Structure used between LLDD and nvmet-fc layer to represent the exchange * context for a FC-NVME FCP I/O operation (e.g. a nvme sqe, the sqe-related - * memory transfers, and its assocated cqe transfer). + * memory transfers, and its associated cqe transfer). * * The structure is allocated by the LLDD whenever a FCP CMD IU is received * from the FC link. The address of the structure is passed to the nvmet-fc @@ -920,6 +920,9 @@ struct nvmet_fc_target_port { * further references to hosthandle. * Entrypoint is Mandatory if the lldd calls nvmet_fc_invalidate_host(). * + * @host_traddr: called by the transport to retrieve the node name and + * port name of the host port address. + * * @max_hw_queues: indicates the maximum number of hw queues the LLDD * supports for cpu affinitization. * Value is Mandatory. Must be at least 1. @@ -975,6 +978,7 @@ struct nvmet_fc_target_template { void (*ls_abort)(struct nvmet_fc_target_port *targetport, void *hosthandle, struct nvmefc_ls_req *lsreq); void (*host_release)(void *hosthandle); + int (*host_traddr)(void *hosthandle, u64 *wwnn, u64 *wwpn); u32 max_hw_queues; u16 max_sgl_segments; diff --git a/include/linux/nvme-keyring.h b/include/linux/nvme-keyring.h index e10333d78dbb..19d2b256180f 100644 --- a/include/linux/nvme-keyring.h +++ b/include/linux/nvme-keyring.h @@ -12,7 +12,7 @@ key_serial_t nvme_tls_psk_default(struct key *keyring, const char *hostnqn, const char *subnqn); key_serial_t nvme_keyring_id(void); - +struct key *nvme_tls_key_lookup(key_serial_t key_id); #else static inline key_serial_t nvme_tls_psk_default(struct key *keyring, @@ -24,5 +24,9 @@ static inline key_serial_t nvme_keyring_id(void) { return 0; } +static inline struct key *nvme_tls_key_lookup(key_serial_t key_id) +{ + return ERR_PTR(-ENOTSUPP); +} #endif /* !CONFIG_NVME_KEYRING */ #endif /* _NVME_KEYRING_H */ diff --git a/include/linux/nvme-rdma.h b/include/linux/nvme-rdma.h index eb2f04d636c8..97c5f00b9aa3 100644 --- a/include/linux/nvme-rdma.h +++ b/include/linux/nvme-rdma.h @@ -25,6 +25,7 @@ enum nvme_rdma_cm_status { NVME_RDMA_CM_NO_RSC = 0x06, NVME_RDMA_CM_INVALID_IRD = 0x07, NVME_RDMA_CM_INVALID_ORD = 0x08, + NVME_RDMA_CM_INVALID_CNTLID = 0x09, }; static inline const char *nvme_rdma_cm_msg(enum nvme_rdma_cm_status status) @@ -46,6 +47,8 @@ static inline const char *nvme_rdma_cm_msg(enum nvme_rdma_cm_status status) return "invalid IRD"; case NVME_RDMA_CM_INVALID_ORD: return "Invalid ORD"; + case NVME_RDMA_CM_INVALID_CNTLID: + return "invalid controller ID"; default: return "unrecognized reason"; } @@ -64,7 +67,8 @@ struct nvme_rdma_cm_req { __le16 qid; __le16 hrqsize; __le16 hsqsize; - u8 rsvd[24]; + __le16 cntlid; + u8 rsvd[22]; }; /** diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 425573202295..fe3b60818fdc 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -25,6 +25,9 @@ #define NVME_NSID_ALL 0xffffffff +/* Special NSSR value, 'NVMe' */ +#define NVME_SUBSYS_RESET 0x4E564D65 + enum nvme_subsys_type { /* Referral to another discovery type target subsystem */ NVME_NQN_DISC = 1, @@ -61,6 +64,7 @@ enum { /* Transport Type codes for Discovery Log Page entry TRTYPE field */ enum { + NVMF_TRTYPE_PCI = 0, /* PCI */ NVMF_TRTYPE_RDMA = 1, /* RDMA */ NVMF_TRTYPE_FC = 2, /* Fibre Channel */ NVMF_TRTYPE_TCP = 3, /* TCP/IP */ @@ -85,10 +89,11 @@ enum { enum { NVMF_RDMA_QPTYPE_CONNECTED = 1, /* Reliable Connected */ NVMF_RDMA_QPTYPE_DATAGRAM = 2, /* Reliable Datagram */ + NVMF_RDMA_QPTYPE_INVALID = 0xff, }; -/* RDMA QP Service Type codes for Discovery Log Page entry TSAS - * RDMA_QPTYPE field +/* RDMA Provider Type codes for Discovery Log Page entry TSAS + * RDMA_PRTYPE field */ enum { NVMF_RDMA_PRTYPE_NOT_SPECIFIED = 1, /* No Provider Specified */ @@ -110,6 +115,7 @@ enum { NVMF_TCP_SECTYPE_NONE = 0, /* No Security */ NVMF_TCP_SECTYPE_TLS12 = 1, /* TLSv1.2, NVMe-oF 1.1 and NVMe-TCP 3.6.1.1 */ NVMF_TCP_SECTYPE_TLS13 = 2, /* TLSv1.3, NVMe-oF 1.1 and NVMe-TCP 3.6.1.1 */ + NVMF_TCP_SECTYPE_INVALID = 0xff, }; #define NVME_AQ_DEPTH 32 @@ -270,6 +276,7 @@ enum nvme_ctrl_attr { NVME_CTRL_ATTR_HID_128_BIT = (1 << 0), NVME_CTRL_ATTR_TBKAS = (1 << 6), NVME_CTRL_ATTR_ELBAS = (1 << 15), + NVME_CTRL_ATTR_RHII = (1 << 18), }; struct nvme_id_ctrl { @@ -322,7 +329,8 @@ struct nvme_id_ctrl { __le32 sanicap; __le32 hmminds; __le16 hmmaxd; - __u8 rsvd338[4]; + __le16 nvmsetidmax; + __le16 endgidmax; __u8 anatt; __u8 anacap; __le32 anagrpmax; @@ -383,6 +391,11 @@ enum { NVME_CTRL_CTRATT_PREDICTABLE_LAT = 1 << 5, NVME_CTRL_CTRATT_NAMESPACE_GRANULARITY = 1 << 7, NVME_CTRL_CTRATT_UUID_LIST = 1 << 9, + NVME_CTRL_SGLS_BYTE_ALIGNED = 1, + NVME_CTRL_SGLS_DWORD_ALIGNED = 2, + NVME_CTRL_SGLS_KSDBDS = 1 << 2, + NVME_CTRL_SGLS_MSDS = 1 << 19, + NVME_CTRL_SGLS_SAOS = 1 << 20, }; struct nvme_lbaf { @@ -480,6 +493,9 @@ enum { NVME_ID_NS_NVM_STS_MASK = 0x7f, NVME_ID_NS_NVM_GUARD_SHIFT = 7, NVME_ID_NS_NVM_GUARD_MASK = 0x3, + NVME_ID_NS_NVM_QPIF_SHIFT = 9, + NVME_ID_NS_NVM_QPIF_MASK = 0xf, + NVME_ID_NS_NVM_QPIFS = 1 << 3, }; static inline __u8 nvme_elbaf_sts(__u32 elbaf) @@ -492,6 +508,11 @@ static inline __u8 nvme_elbaf_guard_type(__u32 elbaf) return (elbaf >> NVME_ID_NS_NVM_GUARD_SHIFT) & NVME_ID_NS_NVM_GUARD_MASK; } +static inline __u8 nvme_elbaf_qualified_guard_type(__u32 elbaf) +{ + return (elbaf >> NVME_ID_NS_NVM_QPIF_SHIFT) & NVME_ID_NS_NVM_QPIF_MASK; +} + struct nvme_id_ctrl_nvm { __u8 vsl; __u8 wzsl; @@ -509,6 +530,7 @@ enum { NVME_ID_CNS_NS_DESC_LIST = 0x03, NVME_ID_CNS_CS_NS = 0x05, NVME_ID_CNS_CS_CTRL = 0x06, + NVME_ID_CNS_NS_ACTIVE_LIST_CS = 0x07, NVME_ID_CNS_NS_CS_INDEP = 0x08, NVME_ID_CNS_NS_PRESENT_LIST = 0x10, NVME_ID_CNS_NS_PRESENT = 0x11, @@ -517,6 +539,7 @@ enum { NVME_ID_CNS_SCNDRY_CTRL_LIST = 0x15, NVME_ID_CNS_NS_GRANULARITY = 0x16, NVME_ID_CNS_UUID_LIST = 0x17, + NVME_ID_CNS_ENDGRP_LIST = 0x19, }; enum { @@ -547,6 +570,8 @@ enum { NVME_NS_FLBAS_LBA_SHIFT = 1, NVME_NS_FLBAS_META_EXT = 0x10, NVME_NS_NMIC_SHARED = 1 << 0, + NVME_NS_ROTATIONAL = 1 << 4, + NVME_NS_VWC_NOT_PRESENT = 1 << 5, NVME_LBAF_RP_BEST = 0, NVME_LBAF_RP_BETTER = 1, NVME_LBAF_RP_GOOD = 2, @@ -571,6 +596,7 @@ enum { NVME_NVM_NS_16B_GUARD = 0, NVME_NVM_NS_32B_GUARD = 1, NVME_NVM_NS_64B_GUARD = 2, + NVME_NVM_NS_QTYPE_GUARD = 3, }; static inline __u8 nvme_lbaf_index(__u8 flbas) @@ -603,6 +629,40 @@ enum { NVME_NIDT_CSI = 0x04, }; +struct nvme_endurance_group_log { + __u8 egcw; + __u8 egfeat; + __u8 rsvd2; + __u8 avsp; + __u8 avspt; + __u8 pused; + __le16 did; + __u8 rsvd8[24]; + __u8 ee[16]; + __u8 dur[16]; + __u8 duw[16]; + __u8 muw[16]; + __u8 hrc[16]; + __u8 hwc[16]; + __u8 mdie[16]; + __u8 neile[16]; + __u8 tegcap[16]; + __u8 uegcap[16]; + __u8 rsvd192[320]; +}; + +struct nvme_rotational_media_log { + __le16 endgid; + __le16 numa; + __le16 nrs; + __u8 rsvd6[2]; + __le32 spinc; + __le32 fspinc; + __le32 ldc; + __le32 fldc; + __u8 rsvd24[488]; +}; + struct nvme_smart_log { __u8 critical_warning; __u8 temperature[2]; @@ -973,8 +1033,8 @@ struct nvme_rw_command { __le16 control; __le32 dsmgmt; __le32 reftag; - __le16 apptag; - __le16 appmask; + __le16 lbat; + __le16 lbatm; }; enum { @@ -1043,8 +1103,8 @@ struct nvme_write_zeroes_cmd { __le16 control; __le32 dsmgmt; __le32 reftag; - __le16 apptag; - __le16 appmask; + __le16 lbat; + __le16 lbatm; }; enum nvme_zone_mgmt_action { @@ -1230,6 +1290,7 @@ enum { NVME_FEAT_WRITE_PROTECT = 0x84, NVME_FEAT_VENDOR_START = 0xC0, NVME_FEAT_VENDOR_END = 0xFF, + NVME_LOG_SUPPORTED = 0x00, NVME_LOG_ERROR = 0x01, NVME_LOG_SMART = 0x02, NVME_LOG_FW_SLOT = 0x03, @@ -1240,6 +1301,8 @@ enum { NVME_LOG_TELEMETRY_CTRL = 0x08, NVME_LOG_ENDURANCE_GROUP = 0x09, NVME_LOG_ANA = 0x0c, + NVME_LOG_FEATURES = 0x12, + NVME_LOG_RMI = 0x16, NVME_LOG_DISC = 0x70, NVME_LOG_RESERVATION = 0x80, NVME_FWACT_REPL = (0 << 3), @@ -1247,6 +1310,24 @@ enum { NVME_FWACT_ACTV = (2 << 3), }; +struct nvme_supported_log { + __le32 lids[256]; +}; + +enum { + NVME_LIDS_LSUPP = 1 << 0, +}; + +struct nvme_supported_features_log { + __le32 fis[256]; +}; + +enum { + NVME_FIS_FSUPP = 1 << 0, + NVME_FIS_NSCPE = 1 << 20, + NVME_FIS_CSCPE = 1 << 21, +}; + /* NVMe Namespace Write Protect State */ enum { NVME_NS_NO_WRITE_PROTECT = 0, @@ -1267,7 +1348,8 @@ struct nvme_identify { __u8 cns; __u8 rsvd3; __le16 ctrlid; - __u8 rsvd11[3]; + __le16 cnssid; + __u8 rsvd11; __u8 csi; __u32 rsvd12[4]; }; @@ -1375,7 +1457,7 @@ struct nvme_get_log_page_command { __u8 lsp; /* upper 4 bits reserved */ __le16 numdl; __le16 numdu; - __u16 rsvd11; + __le16 lsi; union { struct { __le32 lpol; @@ -1816,6 +1898,46 @@ static inline bool nvme_is_fabrics(const struct nvme_command *cmd) return cmd->common.opcode == nvme_fabrics_command; } +#ifdef CONFIG_NVME_VERBOSE_ERRORS +const char *nvme_get_error_status_str(u16 status); +const char *nvme_get_opcode_str(u8 opcode); +const char *nvme_get_admin_opcode_str(u8 opcode); +const char *nvme_get_fabrics_opcode_str(u8 opcode); +#else /* CONFIG_NVME_VERBOSE_ERRORS */ +static inline const char *nvme_get_error_status_str(u16 status) +{ + return "I/O Error"; +} +static inline const char *nvme_get_opcode_str(u8 opcode) +{ + return "I/O Cmd"; +} +static inline const char *nvme_get_admin_opcode_str(u8 opcode) +{ + return "Admin Cmd"; +} + +static inline const char *nvme_get_fabrics_opcode_str(u8 opcode) +{ + return "Fabrics Cmd"; +} +#endif /* CONFIG_NVME_VERBOSE_ERRORS */ + +static inline const char *nvme_opcode_str(int qid, u8 opcode) +{ + return qid ? nvme_get_opcode_str(opcode) : + nvme_get_admin_opcode_str(opcode); +} + +static inline const char *nvme_fabrics_opcode_str( + int qid, const struct nvme_command *cmd) +{ + if (nvme_is_fabrics(cmd)) + return nvme_get_fabrics_opcode_str(cmd->fabrics.fctype); + + return nvme_opcode_str(qid, cmd->common.opcode); +} + struct nvme_error_slot { __le64 error_count; __le16 sqid; @@ -1846,6 +1968,7 @@ enum { /* * Generic Command Status: */ + NVME_SCT_GENERIC = 0x0, NVME_SC_SUCCESS = 0x0, NVME_SC_INVALID_OPCODE = 0x1, NVME_SC_INVALID_FIELD = 0x2, @@ -1893,6 +2016,7 @@ enum { /* * Command Specific Status: */ + NVME_SCT_COMMAND_SPECIFIC = 0x100, NVME_SC_CQ_INVALID = 0x100, NVME_SC_QID_INVALID = 0x101, NVME_SC_QUEUE_SIZE = 0x102, @@ -1966,6 +2090,7 @@ enum { /* * Media and Data Integrity Errors: */ + NVME_SCT_MEDIA_ERROR = 0x200, NVME_SC_WRITE_FAULT = 0x280, NVME_SC_READ_ERROR = 0x281, NVME_SC_GUARD_CHECK = 0x282, @@ -1978,6 +2103,7 @@ enum { /* * Path-related Errors: */ + NVME_SCT_PATH = 0x300, NVME_SC_INTERNAL_PATH_ERROR = 0x300, NVME_SC_ANA_PERSISTENT_LOSS = 0x301, NVME_SC_ANA_INACCESSIBLE = 0x302, @@ -1986,11 +2112,17 @@ enum { NVME_SC_HOST_PATH_ERROR = 0x370, NVME_SC_HOST_ABORTED_CMD = 0x371, - NVME_SC_CRD = 0x1800, - NVME_SC_MORE = 0x2000, - NVME_SC_DNR = 0x4000, + NVME_SC_MASK = 0x00ff, /* Status Code */ + NVME_SCT_MASK = 0x0700, /* Status Code Type */ + NVME_SCT_SC_MASK = NVME_SCT_MASK | NVME_SC_MASK, + + NVME_STATUS_CRD = 0x1800, /* Command Retry Delayed */ + NVME_STATUS_MORE = 0x2000, + NVME_STATUS_DNR = 0x4000, /* Do Not Retry */ }; +#define NVME_SCT(status) ((status) >> 8 & 7) + struct nvme_completion { /* * Used by Admin and Fabrics commands to return data: @@ -2013,4 +2145,81 @@ struct nvme_completion { #define NVME_MINOR(ver) (((ver) >> 8) & 0xff) #define NVME_TERTIARY(ver) ((ver) & 0xff) +enum { + NVME_AEN_RESV_LOG_PAGE_AVALIABLE = 0x00, +}; + +enum { + NVME_PR_LOG_EMPTY_LOG_PAGE = 0x00, + NVME_PR_LOG_REGISTRATION_PREEMPTED = 0x01, + NVME_PR_LOG_RESERVATION_RELEASED = 0x02, + NVME_PR_LOG_RESERVATOIN_PREEMPTED = 0x03, +}; + +enum { + NVME_PR_NOTIFY_BIT_REG_PREEMPTED = 1, + NVME_PR_NOTIFY_BIT_RESV_RELEASED = 2, + NVME_PR_NOTIFY_BIT_RESV_PREEMPTED = 3, +}; + +struct nvme_pr_log { + __le64 count; + __u8 type; + __u8 nr_pages; + __u8 rsvd1[2]; + __le32 nsid; + __u8 rsvd2[48]; +}; + +struct nvmet_pr_register_data { + __le64 crkey; + __le64 nrkey; +}; + +struct nvmet_pr_acquire_data { + __le64 crkey; + __le64 prkey; +}; + +struct nvmet_pr_release_data { + __le64 crkey; +}; + +enum nvme_pr_capabilities { + NVME_PR_SUPPORT_PTPL = 1, + NVME_PR_SUPPORT_WRITE_EXCLUSIVE = 1 << 1, + NVME_PR_SUPPORT_EXCLUSIVE_ACCESS = 1 << 2, + NVME_PR_SUPPORT_WRITE_EXCLUSIVE_REG_ONLY = 1 << 3, + NVME_PR_SUPPORT_EXCLUSIVE_ACCESS_REG_ONLY = 1 << 4, + NVME_PR_SUPPORT_WRITE_EXCLUSIVE_ALL_REGS = 1 << 5, + NVME_PR_SUPPORT_EXCLUSIVE_ACCESS_ALL_REGS = 1 << 6, + NVME_PR_SUPPORT_IEKEY_VER_1_3_DEF = 1 << 7, +}; + +enum nvme_pr_register_action { + NVME_PR_REGISTER_ACT_REG = 0, + NVME_PR_REGISTER_ACT_UNREG = 1, + NVME_PR_REGISTER_ACT_REPLACE = 1 << 1, +}; + +enum nvme_pr_acquire_action { + NVME_PR_ACQUIRE_ACT_ACQUIRE = 0, + NVME_PR_ACQUIRE_ACT_PREEMPT = 1, + NVME_PR_ACQUIRE_ACT_PREEMPT_AND_ABORT = 1 << 1, +}; + +enum nvme_pr_release_action { + NVME_PR_RELEASE_ACT_RELEASE = 0, + NVME_PR_RELEASE_ACT_CLEAR = 1, +}; + +enum nvme_pr_change_ptpl { + NVME_PR_CPTPL_NO_CHANGE = 0, + NVME_PR_CPTPL_RESV = 1 << 30, + NVME_PR_CPTPL_CLEARED = 2 << 30, + NVME_PR_CPTPL_PERSIST = 3 << 30, +}; + +#define NVME_PR_IGNORE_KEY (1 << 3) + #endif /* _LINUX_NVME_H */ diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index f0ba0e03218f..515676ebe598 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -92,8 +92,8 @@ struct nvmem_cell_info { * @read_only: Device is read-only. * @root_only: Device is accessibly to root only. * @of_node: If given, this will be used instead of the parent's of_node. - * @reg_read: Callback to read data. - * @reg_write: Callback to write data. + * @reg_read: Callback to read data; return zero if successful. + * @reg_write: Callback to write data; return zero if successful. * @size: Device size. * @word_size: Minimum read/write access granularity. * @stride: Minimum read/write access stride. @@ -199,7 +199,10 @@ int nvmem_add_one_cell(struct nvmem_device *nvmem, int nvmem_layout_register(struct nvmem_layout *layout); void nvmem_layout_unregister(struct nvmem_layout *layout); -int nvmem_layout_driver_register(struct nvmem_layout_driver *drv); +#define nvmem_layout_driver_register(drv) \ + __nvmem_layout_driver_register(drv, THIS_MODULE) +int __nvmem_layout_driver_register(struct nvmem_layout_driver *drv, + struct module *owner); void nvmem_layout_driver_unregister(struct nvmem_layout_driver *drv); #define module_nvmem_layout_driver(__nvmem_layout_driver) \ module_driver(__nvmem_layout_driver, nvmem_layout_driver_register, \ diff --git a/include/linux/oa_tc6.h b/include/linux/oa_tc6.h new file mode 100644 index 000000000000..15f58e3c56c7 --- /dev/null +++ b/include/linux/oa_tc6.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * OPEN Alliance 10BASE‑T1x MAC‑PHY Serial Interface framework + * + * Link: https://opensig.org/download/document/OPEN_Alliance_10BASET1x_MAC-PHY_Serial_Interface_V1.1.pdf + * + * Author: Parthiban Veerasooran <parthiban.veerasooran@microchip.com> + */ + +#include <linux/etherdevice.h> +#include <linux/spi/spi.h> + +struct oa_tc6; + +struct oa_tc6 *oa_tc6_init(struct spi_device *spi, struct net_device *netdev); +void oa_tc6_exit(struct oa_tc6 *tc6); +int oa_tc6_write_register(struct oa_tc6 *tc6, u32 address, u32 value); +int oa_tc6_write_registers(struct oa_tc6 *tc6, u32 address, u32 value[], + u8 length); +int oa_tc6_read_register(struct oa_tc6 *tc6, u32 address, u32 *value); +int oa_tc6_read_registers(struct oa_tc6 *tc6, u32 address, u32 value[], + u8 length); +netdev_tx_t oa_tc6_start_xmit(struct oa_tc6 *tc6, struct sk_buff *skb); +int oa_tc6_zero_align_receive_frame_enable(struct oa_tc6 *tc6); diff --git a/include/linux/objagg.h b/include/linux/objagg.h index 78021777df46..6df5b887dc54 100644 --- a/include/linux/objagg.h +++ b/include/linux/objagg.h @@ -8,7 +8,6 @@ struct objagg_ops { size_t obj_size; bool (*delta_check)(void *priv, const void *parent_obj, const void *obj); - int (*hints_obj_cmp)(const void *obj1, const void *obj2); void * (*delta_create)(void *priv, void *parent_obj, void *obj); void (*delta_destroy)(void *priv, void *delta_priv); void * (*root_create)(void *priv, void *obj, unsigned int root_id); diff --git a/include/linux/objpool.h b/include/linux/objpool.h index 15aff4a17f0c..cb1758eaa2d3 100644 --- a/include/linux/objpool.h +++ b/include/linux/objpool.h @@ -5,6 +5,10 @@ #include <linux/types.h> #include <linux/refcount.h> +#include <linux/atomic.h> +#include <linux/cpumask.h> +#include <linux/irqflags.h> +#include <linux/smp.h> /* * objpool: ring-array based lockless MPMC queue @@ -69,7 +73,7 @@ typedef int (*objpool_fini_cb)(struct objpool_head *head, void *context); * struct objpool_head - object pooling metadata * @obj_size: object size, aligned to sizeof(void *) * @nr_objs: total objs (to be pre-allocated with objpool) - * @nr_cpus: local copy of nr_cpu_ids + * @nr_possible_cpus: cached value of num_possible_cpus() * @capacity: max objs can be managed by one objpool_slot * @gfp: gfp flags for kmalloc & vmalloc * @ref: refcount of objpool @@ -81,7 +85,7 @@ typedef int (*objpool_fini_cb)(struct objpool_head *head, void *context); struct objpool_head { int obj_size; int nr_objs; - int nr_cpus; + int nr_possible_cpus; int capacity; gfp_t gfp; refcount_t ref; @@ -118,13 +122,94 @@ int objpool_init(struct objpool_head *pool, int nr_objs, int object_size, gfp_t gfp, void *context, objpool_init_obj_cb objinit, objpool_fini_cb release); +/* try to retrieve object from slot */ +static inline void *__objpool_try_get_slot(struct objpool_head *pool, int cpu) +{ + struct objpool_slot *slot = pool->cpu_slots[cpu]; + /* load head snapshot, other cpus may change it */ + uint32_t head = smp_load_acquire(&slot->head); + + while (head != READ_ONCE(slot->last)) { + void *obj; + + /* + * data visibility of 'last' and 'head' could be out of + * order since memory updating of 'last' and 'head' are + * performed in push() and pop() independently + * + * before any retrieving attempts, pop() must guarantee + * 'last' is behind 'head', that is to say, there must + * be available objects in slot, which could be ensured + * by condition 'last != head && last - head <= nr_objs' + * that is equivalent to 'last - head - 1 < nr_objs' as + * 'last' and 'head' are both unsigned int32 + */ + if (READ_ONCE(slot->last) - head - 1 >= pool->nr_objs) { + head = READ_ONCE(slot->head); + continue; + } + + /* obj must be retrieved before moving forward head */ + obj = READ_ONCE(slot->entries[head & slot->mask]); + + /* move head forward to mark it's consumption */ + if (try_cmpxchg_release(&slot->head, &head, head + 1)) + return obj; + } + + return NULL; +} + /** * objpool_pop() - allocate an object from objpool * @pool: object pool * * return value: object ptr or NULL if failed */ -void *objpool_pop(struct objpool_head *pool); +static inline void *objpool_pop(struct objpool_head *pool) +{ + void *obj = NULL; + unsigned long flags; + int i, cpu; + + /* disable local irq to avoid preemption & interruption */ + raw_local_irq_save(flags); + + cpu = raw_smp_processor_id(); + for (i = 0; i < pool->nr_possible_cpus; i++) { + obj = __objpool_try_get_slot(pool, cpu); + if (obj) + break; + cpu = cpumask_next_wrap(cpu, cpu_possible_mask, -1, 1); + } + raw_local_irq_restore(flags); + + return obj; +} + +/* adding object to slot, abort if the slot was already full */ +static inline int +__objpool_try_add_slot(void *obj, struct objpool_head *pool, int cpu) +{ + struct objpool_slot *slot = pool->cpu_slots[cpu]; + uint32_t head, tail; + + /* loading tail and head as a local snapshot, tail first */ + tail = READ_ONCE(slot->tail); + + do { + head = READ_ONCE(slot->head); + /* fault caught: something must be wrong */ + WARN_ON_ONCE(tail - head > pool->nr_objs); + } while (!try_cmpxchg_acquire(&slot->tail, &tail, tail + 1)); + + /* now the tail position is reserved for the given obj */ + WRITE_ONCE(slot->entries[tail & slot->mask], obj); + /* update sequence to make this obj available for pop() */ + smp_store_release(&slot->last, tail + 1); + + return 0; +} /** * objpool_push() - reclaim the object and return back to objpool @@ -134,7 +219,19 @@ void *objpool_pop(struct objpool_head *pool); * return: 0 or error code (it fails only when user tries to push * the same object multiple times or wrong "objects" into objpool) */ -int objpool_push(void *obj, struct objpool_head *pool); +static inline int objpool_push(void *obj, struct objpool_head *pool) +{ + unsigned long flags; + int rc; + + /* disable local irq to avoid preemption & interruption */ + raw_local_irq_save(flags); + rc = __objpool_try_add_slot(obj, pool, raw_smp_processor_id()); + raw_local_irq_restore(flags); + + return rc; +} + /** * objpool_drop() - discard the object and deref objpool diff --git a/include/linux/objtool.h b/include/linux/objtool.h index b3b8d3dab52d..c722a921165b 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -45,29 +45,25 @@ #define STACK_FRAME_NON_STANDARD_FP(func) #endif -#define ANNOTATE_NOENDBR \ - "986: \n\t" \ - ".pushsection .discard.noendbr\n\t" \ - ".long 986b\n\t" \ - ".popsection\n\t" - #define ASM_REACHABLE \ "998:\n\t" \ ".pushsection .discard.reachable\n\t" \ ".long 998b\n\t" \ ".popsection\n\t" -#else /* __ASSEMBLY__ */ +#define __ASM_BREF(label) label ## b -/* - * This macro indicates that the following intra-function call is valid. - * Any non-annotated intra-function call will cause objtool to issue a warning. - */ -#define ANNOTATE_INTRA_FUNCTION_CALL \ - 999: \ - .pushsection .discard.intra_function_calls; \ - .long 999b; \ - .popsection; +#define __ASM_ANNOTATE(label, type) \ + ".pushsection .discard.annotate_insn,\"M\",@progbits,8\n\t" \ + ".long " __stringify(label) " - .\n\t" \ + ".long " __stringify(type) "\n\t" \ + ".popsection\n\t" + +#define ASM_ANNOTATE(type) \ + "911:\n\t" \ + __ASM_ANNOTATE(911b, type) + +#else /* __ASSEMBLY__ */ /* * In asm, there are two kinds of code: normal C-type callable functions and @@ -115,34 +111,11 @@ #endif .endm -.macro ANNOTATE_NOENDBR +.macro ANNOTATE type:req .Lhere_\@: - .pushsection .discard.noendbr - .long .Lhere_\@ - .popsection -.endm - -/* - * Use objtool to validate the entry requirement that all code paths do - * VALIDATE_UNRET_END before RET. - * - * NOTE: The macro must be used at the beginning of a global symbol, otherwise - * it will be ignored. - */ -.macro VALIDATE_UNRET_BEGIN -#if defined(CONFIG_NOINSTR_VALIDATION) && \ - (defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO)) -.Lhere_\@: - .pushsection .discard.validate_unret + .pushsection .discard.annotate_insn,"M",@progbits,8 .long .Lhere_\@ - . - .popsection -#endif -.endm - -.macro REACHABLE -.Lhere_\@: - .pushsection .discard.reachable - .long .Lhere_\@ + .long \type .popsection .endm @@ -155,20 +128,77 @@ #define UNWIND_HINT(type, sp_reg, sp_offset, signal) "\n\t" #define STACK_FRAME_NON_STANDARD(func) #define STACK_FRAME_NON_STANDARD_FP(func) -#define ANNOTATE_NOENDBR -#define ASM_REACHABLE +#define __ASM_ANNOTATE(label, type) +#define ASM_ANNOTATE(type) #else -#define ANNOTATE_INTRA_FUNCTION_CALL .macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 signal=0 .endm .macro STACK_FRAME_NON_STANDARD func:req .endm -.macro ANNOTATE_NOENDBR -.endm -.macro REACHABLE +.macro ANNOTATE type:req .endm #endif #endif /* CONFIG_OBJTOOL */ +#ifndef __ASSEMBLY__ +/* + * Annotate away the various 'relocation to !ENDBR` complaints; knowing that + * these relocations will never be used for indirect calls. + */ +#define ANNOTATE_NOENDBR ASM_ANNOTATE(ANNOTYPE_NOENDBR) +/* + * This should be used immediately before an indirect jump/call. It tells + * objtool the subsequent indirect jump/call is vouched safe for retpoline + * builds. + */ +#define ANNOTATE_RETPOLINE_SAFE ASM_ANNOTATE(ANNOTYPE_RETPOLINE_SAFE) +/* + * See linux/instrumentation.h + */ +#define ANNOTATE_INSTR_BEGIN(label) __ASM_ANNOTATE(label, ANNOTYPE_INSTR_BEGIN) +#define ANNOTATE_INSTR_END(label) __ASM_ANNOTATE(label, ANNOTYPE_INSTR_END) +/* + * objtool annotation to ignore the alternatives and only consider the original + * instruction(s). + */ +#define ANNOTATE_IGNORE_ALTERNATIVE ASM_ANNOTATE(ANNOTYPE_IGNORE_ALTS) +/* + * This macro indicates that the following intra-function call is valid. + * Any non-annotated intra-function call will cause objtool to issue a warning. + */ +#define ANNOTATE_INTRA_FUNCTION_CALL ASM_ANNOTATE(ANNOTYPE_INTRA_FUNCTION_CALL) +/* + * Use objtool to validate the entry requirement that all code paths do + * VALIDATE_UNRET_END before RET. + * + * NOTE: The macro must be used at the beginning of a global symbol, otherwise + * it will be ignored. + */ +#define ANNOTATE_UNRET_BEGIN ASM_ANNOTATE(ANNOTYPE_UNRET_BEGIN) +/* + * This should be used to refer to an instruction that is considered + * terminating, like a noreturn CALL or UD2 when we know they are not -- eg + * WARN using UD2. + */ +#define ANNOTATE_REACHABLE(label) __ASM_ANNOTATE(label, ANNOTYPE_REACHABLE) + +#else +#define ANNOTATE_NOENDBR ANNOTATE type=ANNOTYPE_NOENDBR +#define ANNOTATE_RETPOLINE_SAFE ANNOTATE type=ANNOTYPE_RETPOLINE_SAFE +/* ANNOTATE_INSTR_BEGIN ANNOTATE type=ANNOTYPE_INSTR_BEGIN */ +/* ANNOTATE_INSTR_END ANNOTATE type=ANNOTYPE_INSTR_END */ +#define ANNOTATE_IGNORE_ALTERNATIVE ANNOTATE type=ANNOTYPE_IGNORE_ALTS +#define ANNOTATE_INTRA_FUNCTION_CALL ANNOTATE type=ANNOTYPE_INTRA_FUNCTION_CALL +#define ANNOTATE_UNRET_BEGIN ANNOTATE type=ANNOTYPE_UNRET_BEGIN +#define ANNOTATE_REACHABLE ANNOTATE type=ANNOTYPE_REACHABLE +#endif + +#if defined(CONFIG_NOINSTR_VALIDATION) && \ + (defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO)) +#define VALIDATE_UNRET_BEGIN ANNOTATE_UNRET_BEGIN +#else +#define VALIDATE_UNRET_BEGIN +#endif + #endif /* _LINUX_OBJTOOL_H */ diff --git a/include/linux/objtool_types.h b/include/linux/objtool_types.h index 453a4f4ef39d..df5d9fa84dba 100644 --- a/include/linux/objtool_types.h +++ b/include/linux/objtool_types.h @@ -54,4 +54,16 @@ struct unwind_hint { #define UNWIND_HINT_TYPE_SAVE 6 #define UNWIND_HINT_TYPE_RESTORE 7 +/* + * Annotate types + */ +#define ANNOTYPE_NOENDBR 1 +#define ANNOTYPE_RETPOLINE_SAFE 2 +#define ANNOTYPE_INSTR_BEGIN 3 +#define ANNOTYPE_INSTR_END 4 +#define ANNOTYPE_UNRET_BEGIN 5 +#define ANNOTYPE_IGNORE_ALTS 6 +#define ANNOTYPE_INTRA_FUNCTION_CALL 7 +#define ANNOTYPE_REACHABLE 8 + #endif /* _LINUX_OBJTOOL_TYPES_H */ diff --git a/include/linux/of.h b/include/linux/of.h index a0bedd038a05..eaf0e2a2b75c 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -289,6 +289,9 @@ extern struct device_node *of_get_parent(const struct device_node *node); extern struct device_node *of_get_next_parent(struct device_node *node); extern struct device_node *of_get_next_child(const struct device_node *node, struct device_node *prev); +extern struct device_node *of_get_next_child_with_prefix(const struct device_node *node, + struct device_node *prev, + const char *prefix); extern struct device_node *of_get_next_available_child( const struct device_node *node, struct device_node *prev); extern struct device_node *of_get_next_reserved_child( @@ -308,6 +311,7 @@ extern struct device_node *of_find_node_with_property( extern struct property *of_find_property(const struct device_node *np, const char *name, int *lenp); +extern bool of_property_read_bool(const struct device_node *np, const char *propname); extern int of_property_count_elems_of_size(const struct device_node *np, const char *propname, int elem_size); extern int of_property_read_u32_index(const struct device_node *np, @@ -357,7 +361,7 @@ extern struct device_node *of_get_cpu_node(int cpu, unsigned int *thread); extern struct device_node *of_cpu_device_node_get(int cpu); extern int of_cpu_node_to_id(struct device_node *np); extern struct device_node *of_get_next_cpu_node(struct device_node *prev); -extern struct device_node *of_get_cpu_state_node(struct device_node *cpu_node, +extern struct device_node *of_get_cpu_state_node(const struct device_node *cpu_node, int index); extern u64 of_get_cpu_hwid(struct device_node *cpun, unsigned int thread); @@ -394,8 +398,7 @@ extern int of_phandle_iterator_args(struct of_phandle_iterator *it, uint32_t *args, int size); -extern void of_alias_scan(void * (*dt_alloc)(u64 size, u64 align)); -extern int of_alias_get_id(struct device_node *np, const char *stem); +extern int of_alias_get_id(const struct device_node *np, const char *stem); extern int of_alias_get_highest_id(const char *stem); bool of_machine_compatible_match(const char *const *compats); @@ -430,14 +433,12 @@ extern int of_detach_node(struct device_node *); #define of_match_ptr(_ptr) (_ptr) /* - * struct property *prop; - * const __be32 *p; * u32 u; * - * of_property_for_each_u32(np, "propname", prop, p, u) + * of_property_for_each_u32(np, "propname", u) * printk("U32 value: %x\n", u); */ -const __be32 *of_prop_next_u32(struct property *prop, const __be32 *cur, +const __be32 *of_prop_next_u32(const struct property *prop, const __be32 *cur, u32 *pu); /* * struct property *prop; @@ -446,11 +447,11 @@ const __be32 *of_prop_next_u32(struct property *prop, const __be32 *cur, * of_property_for_each_string(np, "propname", prop, s) * printk("String value: %s\n", s); */ -const char *of_prop_next_string(struct property *prop, const char *cur); +const char *of_prop_next_string(const struct property *prop, const char *cur); -bool of_console_check(struct device_node *dn, char *name, int index); +bool of_console_check(const struct device_node *dn, char *name, int index); -int of_map_id(struct device_node *np, u32 id, +int of_map_id(const struct device_node *np, u32 id, const char *map_name, const char *map_mask_name, struct device_node **target, u32 *id_out); @@ -614,6 +615,12 @@ static inline struct device_node *of_find_compatible_node( return NULL; } +static inline bool of_property_read_bool(const struct device_node *np, + const char *propname) +{ + return false; +} + static inline int of_property_count_elems_of_size(const struct device_node *np, const char *propname, int elem_size) { @@ -828,13 +835,13 @@ static inline bool of_console_check(const struct device_node *dn, const char *na return false; } -static inline const __be32 *of_prop_next_u32(struct property *prop, +static inline const __be32 *of_prop_next_u32(const struct property *prop, const __be32 *cur, u32 *pu) { return NULL; } -static inline const char *of_prop_next_string(struct property *prop, +static inline const char *of_prop_next_string(const struct property *prop, const char *cur) { return NULL; @@ -873,7 +880,7 @@ static inline void of_property_clear_flag(struct property *p, unsigned long flag { } -static inline int of_map_id(struct device_node *np, u32 id, +static inline int of_map_id(const struct device_node *np, u32 id, const char *map_name, const char *map_mask_name, struct device_node **target, u32 *id_out) { @@ -901,7 +908,7 @@ static inline const void *of_device_get_match_data(const struct device *dev) #define of_node_cmp(s1, s2) strcasecmp((s1), (s2)) #endif -static inline int of_prop_val_eq(struct property *p1, struct property *p2) +static inline int of_prop_val_eq(const struct property *p1, const struct property *p2) { return p1->length == p2->length && !memcmp(p1->value, p2->value, (size_t)p1->length); @@ -1242,24 +1249,6 @@ static inline int of_property_read_string_index(const struct device_node *np, } /** - * of_property_read_bool - Find a property - * @np: device node from which the property value is to be read. - * @propname: name of the property to be searched. - * - * 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. - */ -static inline bool of_property_read_bool(const struct device_node *np, - const char *propname) -{ - struct property *prop = of_find_property(np, propname, NULL); - - 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. @@ -1270,7 +1259,9 @@ static inline bool of_property_read_bool(const struct device_node *np, */ static inline bool of_property_present(const struct device_node *np, const char *propname) { - return of_property_read_bool(np, propname); + struct property *prop = of_find_property(np, propname, NULL); + + return prop ? true : false; } /** @@ -1431,11 +1422,12 @@ static inline int of_property_read_s32(const struct device_node *np, err == 0; \ err = of_phandle_iterator_next(it)) -#define of_property_for_each_u32(np, propname, prop, p, u) \ - for (prop = of_find_property(np, propname, NULL), \ - p = of_prop_next_u32(prop, NULL, &u); \ - p; \ - p = of_prop_next_u32(prop, p, &u)) +#define of_property_for_each_u32(np, propname, u) \ + for (struct {const struct property *prop; const __be32 *item; } _it = \ + {of_find_property(np, propname, NULL), \ + of_prop_next_u32(_it.prop, NULL, &u)}; \ + _it.item; \ + _it.item = of_prop_next_u32(_it.prop, _it.item, &u)) #define of_property_for_each_string(np, propname, prop, s) \ for (prop = of_find_property(np, propname, NULL), \ @@ -1469,6 +1461,12 @@ static inline int of_property_read_s32(const struct device_node *np, child != NULL; \ child = of_get_next_child(parent, child)) +#define for_each_child_of_node_with_prefix(parent, child, prefix) \ + for (struct device_node *child __free(device_node) = \ + of_get_next_child_with_prefix(parent, NULL, prefix); \ + child != NULL; \ + child = of_get_next_child_with_prefix(parent, child, prefix)) + #define for_each_available_child_of_node(parent, child) \ for (child = of_get_next_available_child(parent, NULL); child != NULL; \ child = of_get_next_available_child(parent, child)) @@ -1639,7 +1637,7 @@ int of_changeset_add_prop_string(struct of_changeset *ocs, int of_changeset_add_prop_string_array(struct of_changeset *ocs, struct device_node *np, const char *prop_name, - const char **str_array, size_t sz); + const char * const *str_array, size_t sz); int of_changeset_add_prop_u32_array(struct of_changeset *ocs, struct device_node *np, const char *prop_name, @@ -1652,6 +1650,13 @@ static inline int of_changeset_add_prop_u32(struct of_changeset *ocs, return of_changeset_add_prop_u32_array(ocs, np, prop_name, &val, 1); } +int of_changeset_update_prop_string(struct of_changeset *ocs, + struct device_node *np, + const char *prop_name, const char *str); + +int of_changeset_add_prop_bool(struct of_changeset *ocs, struct device_node *np, + const char *prop_name); + #else /* CONFIG_OF_DYNAMIC */ static inline int of_reconfig_notifier_register(struct notifier_block *nb) { @@ -1732,7 +1737,7 @@ struct of_overlay_notify_data { #ifdef CONFIG_OF_OVERLAY int of_overlay_fdt_apply(const void *overlay_fdt, u32 overlay_fdt_size, - int *ovcs_id, struct device_node *target_base); + int *ovcs_id, const struct device_node *target_base); int of_overlay_remove(int *ovcs_id); int of_overlay_remove_all(void); @@ -1742,7 +1747,7 @@ int of_overlay_notifier_unregister(struct notifier_block *nb); #else static inline int of_overlay_fdt_apply(const void *overlay_fdt, u32 overlay_fdt_size, - int *ovcs_id, struct device_node *target_base) + int *ovcs_id, const struct device_node *target_base) { return -ENOTSUPP; } diff --git a/include/linux/of_address.h b/include/linux/of_address.h index 26a19daf0d09..0cff90365391 100644 --- a/include/linux/of_address.h +++ b/include/linux/of_address.h @@ -10,7 +10,7 @@ struct of_bus; struct of_pci_range_parser { struct device_node *node; - struct of_bus *bus; + const struct of_bus *bus; const __be32 *range; const __be32 *end; int na; @@ -26,6 +26,7 @@ struct of_pci_range { u64 bus_addr; }; u64 cpu_addr; + u64 parent_bus_addr; u64 size; u32 flags; }; @@ -83,8 +84,8 @@ extern struct of_pci_range *of_pci_range_parser_one( struct of_pci_range *range); extern int of_pci_address_to_resource(struct device_node *dev, int bar, struct resource *r); -extern int of_pci_range_to_resource(struct of_pci_range *range, - struct device_node *np, +extern int of_pci_range_to_resource(const struct of_pci_range *range, + const struct device_node *np, struct resource *res); extern int of_range_to_resource(struct device_node *np, int index, struct resource *res); diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index d69ad5bb1eb1..b8d6c0c20876 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -31,6 +31,7 @@ extern void *of_fdt_unflatten_tree(const unsigned long *blob, extern int __initdata dt_root_addr_cells; extern int __initdata dt_root_size_cells; extern void *initial_boot_params; +extern phys_addr_t initial_boot_params_pa; extern char __dtb_start[]; extern char __dtb_end[]; @@ -70,8 +71,8 @@ extern u64 dt_mem_next_cell(int s, const __be32 **cellp); /* Early flat tree scan hooks */ extern int early_init_dt_scan_root(void); -extern bool early_init_dt_scan(void *params); -extern bool early_init_dt_verify(void *params); +extern bool early_init_dt_scan(void *dt_virt, phys_addr_t dt_phys); +extern bool early_init_dt_verify(void *dt_virt, phys_addr_t dt_phys); extern void early_init_dt_scan_nodes(void); extern const char *of_flat_dt_get_machine_name(void); diff --git a/include/linux/of_graph.h b/include/linux/of_graph.h index a4bea62bfa29..a692d9d979a6 100644 --- a/include/linux/of_graph.h +++ b/include/linux/of_graph.h @@ -11,6 +11,7 @@ #ifndef __LINUX_OF_GRAPH_H #define __LINUX_OF_GRAPH_H +#include <linux/cleanup.h> #include <linux/types.h> #include <linux/errno.h> @@ -37,14 +38,43 @@ struct of_endpoint { for (child = of_graph_get_next_endpoint(parent, NULL); child != NULL; \ child = of_graph_get_next_endpoint(parent, child)) +/** + * for_each_of_graph_port - iterate over every port in a device or ports node + * @parent: parent device or ports node containing port + * @child: loop variable pointing to the current port node + * + * When breaking out of the loop, and continue to use the @child, you need to + * use return_ptr(@child) or no_free_ptr(@child) not to call __free() for it. + */ +#define for_each_of_graph_port(parent, child) \ + for (struct device_node *child __free(device_node) = of_graph_get_next_port(parent, NULL);\ + child != NULL; child = of_graph_get_next_port(parent, child)) + +/** + * for_each_of_graph_port_endpoint - iterate over every endpoint in a port node + * @parent: parent port node + * @child: loop variable pointing to the current endpoint node + * + * When breaking out of the loop, and continue to use the @child, you need to + * use return_ptr(@child) or no_free_ptr(@child) not to call __free() for it. + */ +#define for_each_of_graph_port_endpoint(parent, child) \ + for (struct device_node *child __free(device_node) = of_graph_get_next_port_endpoint(parent, NULL);\ + child != NULL; child = of_graph_get_next_port_endpoint(parent, child)) + #ifdef CONFIG_OF bool of_graph_is_present(const struct device_node *node); int of_graph_parse_endpoint(const struct device_node *node, struct of_endpoint *endpoint); unsigned int of_graph_get_endpoint_count(const struct device_node *np); +unsigned int of_graph_get_port_count(struct device_node *np); struct device_node *of_graph_get_port_by_id(struct device_node *node, u32 id); struct device_node *of_graph_get_next_endpoint(const struct device_node *parent, struct device_node *previous); +struct device_node *of_graph_get_next_port(const struct device_node *parent, + struct device_node *port); +struct device_node *of_graph_get_next_port_endpoint(const struct device_node *port, + struct device_node *prev); struct device_node *of_graph_get_endpoint_by_regs( const struct device_node *parent, int port_reg, int reg); struct device_node *of_graph_get_remote_endpoint( @@ -73,6 +103,11 @@ static inline unsigned int of_graph_get_endpoint_count(const struct device_node return 0; } +static inline unsigned int of_graph_get_port_count(struct device_node *np) +{ + return 0; +} + static inline struct device_node *of_graph_get_port_by_id( struct device_node *node, u32 id) { @@ -86,6 +121,20 @@ static inline struct device_node *of_graph_get_next_endpoint( return NULL; } +static inline struct device_node *of_graph_get_next_port( + const struct device_node *parent, + struct device_node *previous) +{ + return NULL; +} + +static inline struct device_node *of_graph_get_next_port_endpoint( + const struct device_node *parent, + struct device_node *previous) +{ + return NULL; +} + static inline struct device_node *of_graph_get_endpoint_by_regs( const struct device_node *parent, int port_reg, int reg) { diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h index d6d3eae2f145..6337ad4e5fe8 100644 --- a/include/linux/of_irq.h +++ b/include/linux/of_irq.h @@ -48,12 +48,12 @@ extern int of_irq_to_resource_table(struct device_node *dev, struct resource *res, int nr_irqs); extern struct device_node *of_irq_find_parent(struct device_node *child); extern struct irq_domain *of_msi_get_domain(struct device *dev, - struct device_node *np, + const struct device_node *np, enum irq_domain_bus_token token); extern struct irq_domain *of_msi_map_get_device_domain(struct device *dev, u32 id, u32 bus_token); -extern void of_msi_configure(struct device *dev, struct device_node *np); +extern void of_msi_configure(struct device *dev, const struct device_node *np); u32 of_msi_map_id(struct device *dev, struct device_node *msi_np, u32 id_in); #else static inline void of_irq_init(const struct of_device_id *matches) diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h index a2ff1ad48f7f..17471ef8e092 100644 --- a/include/linux/of_platform.h +++ b/include/linux/of_platform.h @@ -47,8 +47,6 @@ struct of_dev_auxdata { { .compatible = _compat, .phys_addr = _phys, .name = _name, \ .platform_data = _pdata } -extern const struct of_device_id of_default_bus_match_table[]; - /* Platform drivers register/unregister */ extern struct platform_device *of_device_alloc(struct device_node *np, const char *bus_id, diff --git a/include/linux/of_reserved_mem.h b/include/linux/of_reserved_mem.h index 4de2a24cadc9..e338282da652 100644 --- a/include/linux/of_reserved_mem.h +++ b/include/linux/of_reserved_mem.h @@ -11,7 +11,6 @@ struct reserved_mem_ops; struct reserved_mem { const char *name; unsigned long fdt_node; - unsigned long phandle; const struct reserved_mem_ops *ops; phys_addr_t base; phys_addr_t size; diff --git a/include/linux/oid_registry.h b/include/linux/oid_registry.h index 51421fdbb0ba..6f9242259edc 100644 --- a/include/linux/oid_registry.h +++ b/include/linux/oid_registry.h @@ -69,6 +69,7 @@ enum OID { OID_certAuthInfoAccess, /* 1.3.6.1.5.5.7.1.1 */ OID_sha1, /* 1.3.14.3.2.26 */ OID_id_ansip384r1, /* 1.3.132.0.34 */ + OID_id_ansip521r1, /* 1.3.132.0.35 */ OID_sha256, /* 2.16.840.1.101.3.4.2.1 */ OID_sha384, /* 2.16.840.1.101.3.4.2.2 */ OID_sha512, /* 2.16.840.1.101.3.4.2.3 */ diff --git a/include/linux/omap-gpmc.h b/include/linux/omap-gpmc.h index 082841908fe7..263b915df1fb 100644 --- a/include/linux/omap-gpmc.h +++ b/include/linux/omap-gpmc.h @@ -66,10 +66,6 @@ extern int gpmc_calc_timings(struct gpmc_timings *gpmc_t, struct device_node; -extern int gpmc_get_client_irq(unsigned irq_config); - -extern unsigned int gpmc_ticks_to_ns(unsigned int ticks); - extern void gpmc_cs_write_reg(int cs, int idx, u32 val); extern int gpmc_calc_divider(unsigned int sync_clk); extern int gpmc_cs_set_timings(int cs, const struct gpmc_timings *t, @@ -84,13 +80,3 @@ extern void gpmc_read_settings_dt(struct device_node *np, struct gpmc_timings; struct omap_nand_platform_data; struct omap_onenand_platform_data; - -#if IS_ENABLED(CONFIG_MTD_ONENAND_OMAP2) -extern int gpmc_onenand_init(struct omap_onenand_platform_data *d); -#else -#define board_onenand_data NULL -static inline int gpmc_onenand_init(struct omap_onenand_platform_data *d) -{ - return 0; -} -#endif diff --git a/include/linux/omap-mailbox.h b/include/linux/omap-mailbox.h index 8aa984ec1f38..3cc5c4ed7f5a 100644 --- a/include/linux/omap-mailbox.h +++ b/include/linux/omap-mailbox.h @@ -10,17 +10,4 @@ typedef uintptr_t mbox_msg_t; #define omap_mbox_message(data) (u32)(mbox_msg_t)(data) -typedef int __bitwise omap_mbox_irq_t; -#define IRQ_TX ((__force omap_mbox_irq_t) 1) -#define IRQ_RX ((__force omap_mbox_irq_t) 2) - -struct mbox_chan; -struct mbox_client; - -struct mbox_chan *omap_mbox_request_channel(struct mbox_client *cl, - const char *chan_name); - -void omap_mbox_enable_irq(struct mbox_chan *chan, omap_mbox_irq_t irq); -void omap_mbox_disable_irq(struct mbox_chan *chan, omap_mbox_irq_t irq); - #endif /* OMAP_MAILBOX_H */ diff --git a/include/linux/once.h b/include/linux/once.h index bc714d414448..30346fcdc799 100644 --- a/include/linux/once.h +++ b/include/linux/once.h @@ -46,7 +46,7 @@ void __do_once_sleepable_done(bool *done, struct static_key_true *once_key, #define DO_ONCE(func, ...) \ ({ \ bool ___ret = false; \ - static bool __section(".data.once") ___done = false; \ + static bool __section(".data..once") ___done = false; \ static DEFINE_STATIC_KEY_TRUE(___once_key); \ if (static_branch_unlikely(&___once_key)) { \ unsigned long ___flags; \ @@ -64,7 +64,7 @@ void __do_once_sleepable_done(bool *done, struct static_key_true *once_key, #define DO_ONCE_SLEEPABLE(func, ...) \ ({ \ bool ___ret = false; \ - static bool __section(".data.once") ___done = false; \ + static bool __section(".data..once") ___done = false; \ static DEFINE_STATIC_KEY_TRUE(___once_key); \ if (static_branch_unlikely(&___once_key)) { \ ___ret = __do_once_sleepable_start(&___done); \ diff --git a/include/linux/once_lite.h b/include/linux/once_lite.h index b7bce4983638..27de7bc32a06 100644 --- a/include/linux/once_lite.h +++ b/include/linux/once_lite.h @@ -12,7 +12,7 @@ #define __ONCE_LITE_IF(condition) \ ({ \ - static bool __section(".data.once") __already_done; \ + static bool __section(".data..once") __already_done; \ bool __ret_cond = !!(condition); \ bool __ret_once = false; \ \ diff --git a/include/linux/oom.h b/include/linux/oom.h index 7d0c9c48a0c5..1e0fc6931ce9 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -7,7 +7,6 @@ #include <linux/types.h> #include <linux/nodemask.h> #include <uapi/linux/oom.h> -#include <linux/sched/coredump.h> /* MMF_* */ #include <linux/mm.h> /* VM_FAULT* */ struct zonelist; diff --git a/include/linux/packing.h b/include/linux/packing.h index 8d6571feb95d..0589d70bbe04 100644 --- a/include/linux/packing.h +++ b/include/linux/packing.h @@ -8,6 +8,83 @@ #include <linux/types.h> #include <linux/bitops.h> +#define GEN_PACKED_FIELD_STRUCT(__type) \ + struct packed_field_ ## __type { \ + __type startbit; \ + __type endbit; \ + __type offset; \ + __type size; \ + } + +/* struct packed_field_u8. Use with bit offsets < 256, buffers < 32B and + * unpacked structures < 256B. + */ +GEN_PACKED_FIELD_STRUCT(u8); + +/* struct packed_field_u16. Use with bit offsets < 65536, buffers < 8KB and + * unpacked structures < 64KB. + */ +GEN_PACKED_FIELD_STRUCT(u16); + +#define PACKED_FIELD(start, end, struct_name, struct_field) \ +{ \ + (start), \ + (end), \ + offsetof(struct_name, struct_field), \ + sizeof_field(struct_name, struct_field), \ +} + +#define CHECK_PACKED_FIELD_OVERLAP(fields, index1, index2) ({ \ + typeof(&(fields)[0]) __f = (fields); \ + typeof(__f[0]) _f1 = __f[index1]; typeof(__f[0]) _f2 = __f[index2]; \ + const bool _ascending = __f[0].startbit < __f[1].startbit; \ + BUILD_BUG_ON_MSG(_ascending && _f1.startbit >= _f2.startbit, \ + __stringify(fields) " field " __stringify(index2) \ + " breaks ascending order"); \ + BUILD_BUG_ON_MSG(!_ascending && _f1.startbit <= _f2.startbit, \ + __stringify(fields) " field " __stringify(index2) \ + " breaks descending order"); \ + BUILD_BUG_ON_MSG(max(_f1.endbit, _f2.endbit) <= \ + min(_f1.startbit, _f2.startbit), \ + __stringify(fields) " field " __stringify(index2) \ + " overlaps with previous field"); \ +}) + +#define CHECK_PACKED_FIELD(fields, index) ({ \ + typeof(&(fields)[0]) _f = (fields); \ + typeof(_f[0]) __f = _f[index]; \ + BUILD_BUG_ON_MSG(__f.startbit < __f.endbit, \ + __stringify(fields) " field " __stringify(index) \ + " start bit must not be smaller than end bit"); \ + BUILD_BUG_ON_MSG(__f.size != 1 && __f.size != 2 && \ + __f.size != 4 && __f.size != 8, \ + __stringify(fields) " field " __stringify(index) \ + " has unsupported unpacked storage size"); \ + BUILD_BUG_ON_MSG(__f.startbit - __f.endbit >= BITS_PER_BYTE * __f.size, \ + __stringify(fields) " field " __stringify(index) \ + " exceeds unpacked storage size"); \ + __builtin_choose_expr(index != 0, \ + CHECK_PACKED_FIELD_OVERLAP(fields, index - 1, index), \ + 1); \ +}) + +/* Note that the packed fields may be either in ascending or descending order. + * Thus, we must check that both the first and last field wit within the + * packed buffer size. + */ +#define CHECK_PACKED_FIELDS_SIZE(fields, pbuflen) ({ \ + typeof(&(fields)[0]) _f = (fields); \ + typeof(pbuflen) _len = (pbuflen); \ + const size_t num_fields = ARRAY_SIZE(fields); \ + BUILD_BUG_ON_MSG(!__builtin_constant_p(_len), \ + __stringify(fields) " pbuflen " __stringify(pbuflen) \ + " must be a compile time constant"); \ + BUILD_BUG_ON_MSG(_f[0].startbit >= BITS_PER_BYTE * _len, \ + __stringify(fields) " first field exceeds packed buffer size"); \ + BUILD_BUG_ON_MSG(_f[num_fields - 1].startbit >= BITS_PER_BYTE * _len, \ + __stringify(fields) " last field exceeds packed buffer size"); \ +}) + #define QUIRK_MSB_ON_THE_RIGHT BIT(0) #define QUIRK_LITTLE_ENDIAN BIT(1) #define QUIRK_LSW32_IS_FIRST BIT(2) @@ -17,33 +94,361 @@ enum packing_op { UNPACK, }; -/** - * packing - Convert numbers (currently u64) between a packed and an unpacked - * format. Unpacked means laid out in memory in the CPU's native - * understanding of integers, while packed means anything else that - * requires translation. - * - * @pbuf: Pointer to a buffer holding the packed value. - * @uval: Pointer to an u64 holding the unpacked value. - * @startbit: The index (in logical notation, compensated for quirks) where - * the packed value starts within pbuf. Must be larger than, or - * equal to, endbit. - * @endbit: The index (in logical notation, compensated for quirks) where - * the packed value ends within pbuf. Must be smaller than, or equal - * to, startbit. - * @op: If PACK, then uval will be treated as const pointer and copied (packed) - * into pbuf, between startbit and endbit. - * If UNPACK, then pbuf will be treated as const pointer and the logical - * value between startbit and endbit will be copied (unpacked) to uval. - * @quirks: A bit mask of QUIRK_LITTLE_ENDIAN, QUIRK_LSW32_IS_FIRST and - * QUIRK_MSB_ON_THE_RIGHT. - * - * Return: 0 on success, EINVAL or ERANGE if called incorrectly. Assuming - * correct usage, return code may be discarded. - * If op is PACK, pbuf is modified. - * If op is UNPACK, uval is modified. - */ int packing(void *pbuf, u64 *uval, int startbit, int endbit, size_t pbuflen, enum packing_op op, u8 quirks); +int pack(void *pbuf, u64 uval, size_t startbit, size_t endbit, size_t pbuflen, + u8 quirks); + +int unpack(const void *pbuf, u64 *uval, size_t startbit, size_t endbit, + size_t pbuflen, u8 quirks); + +void pack_fields_u8(void *pbuf, size_t pbuflen, const void *ustruct, + const struct packed_field_u8 *fields, size_t num_fields, + u8 quirks); + +void pack_fields_u16(void *pbuf, size_t pbuflen, const void *ustruct, + const struct packed_field_u16 *fields, size_t num_fields, + u8 quirks); + +void unpack_fields_u8(const void *pbuf, size_t pbuflen, void *ustruct, + const struct packed_field_u8 *fields, size_t num_fields, + u8 quirks); + +void unpack_fields_u16(const void *pbuf, size_t pbuflen, void *ustruct, + const struct packed_field_u16 *fields, size_t num_fields, + u8 quirks); + +/* Do not hand-edit the following packed field check macros! + * + * They are generated using scripts/gen_packed_field_checks.c, which may be + * built via "make scripts_gen_packed_field_checks". If larger macro sizes are + * needed in the future, please use this program to re-generate the macros and + * insert them here. + */ + +#define CHECK_PACKED_FIELDS_1(fields) \ + CHECK_PACKED_FIELD(fields, 0) + +#define CHECK_PACKED_FIELDS_2(fields) do { \ + CHECK_PACKED_FIELDS_1(fields); \ + CHECK_PACKED_FIELD(fields, 1); \ +} while (0) + +#define CHECK_PACKED_FIELDS_3(fields) do { \ + CHECK_PACKED_FIELDS_2(fields); \ + CHECK_PACKED_FIELD(fields, 2); \ +} while (0) + +#define CHECK_PACKED_FIELDS_4(fields) do { \ + CHECK_PACKED_FIELDS_3(fields); \ + CHECK_PACKED_FIELD(fields, 3); \ +} while (0) + +#define CHECK_PACKED_FIELDS_5(fields) do { \ + CHECK_PACKED_FIELDS_4(fields); \ + CHECK_PACKED_FIELD(fields, 4); \ +} while (0) + +#define CHECK_PACKED_FIELDS_6(fields) do { \ + CHECK_PACKED_FIELDS_5(fields); \ + CHECK_PACKED_FIELD(fields, 5); \ +} while (0) + +#define CHECK_PACKED_FIELDS_7(fields) do { \ + CHECK_PACKED_FIELDS_6(fields); \ + CHECK_PACKED_FIELD(fields, 6); \ +} while (0) + +#define CHECK_PACKED_FIELDS_8(fields) do { \ + CHECK_PACKED_FIELDS_7(fields); \ + CHECK_PACKED_FIELD(fields, 7); \ +} while (0) + +#define CHECK_PACKED_FIELDS_9(fields) do { \ + CHECK_PACKED_FIELDS_8(fields); \ + CHECK_PACKED_FIELD(fields, 8); \ +} while (0) + +#define CHECK_PACKED_FIELDS_10(fields) do { \ + CHECK_PACKED_FIELDS_9(fields); \ + CHECK_PACKED_FIELD(fields, 9); \ +} while (0) + +#define CHECK_PACKED_FIELDS_11(fields) do { \ + CHECK_PACKED_FIELDS_10(fields); \ + CHECK_PACKED_FIELD(fields, 10); \ +} while (0) + +#define CHECK_PACKED_FIELDS_12(fields) do { \ + CHECK_PACKED_FIELDS_11(fields); \ + CHECK_PACKED_FIELD(fields, 11); \ +} while (0) + +#define CHECK_PACKED_FIELDS_13(fields) do { \ + CHECK_PACKED_FIELDS_12(fields); \ + CHECK_PACKED_FIELD(fields, 12); \ +} while (0) + +#define CHECK_PACKED_FIELDS_14(fields) do { \ + CHECK_PACKED_FIELDS_13(fields); \ + CHECK_PACKED_FIELD(fields, 13); \ +} while (0) + +#define CHECK_PACKED_FIELDS_15(fields) do { \ + CHECK_PACKED_FIELDS_14(fields); \ + CHECK_PACKED_FIELD(fields, 14); \ +} while (0) + +#define CHECK_PACKED_FIELDS_16(fields) do { \ + CHECK_PACKED_FIELDS_15(fields); \ + CHECK_PACKED_FIELD(fields, 15); \ +} while (0) + +#define CHECK_PACKED_FIELDS_17(fields) do { \ + CHECK_PACKED_FIELDS_16(fields); \ + CHECK_PACKED_FIELD(fields, 16); \ +} while (0) + +#define CHECK_PACKED_FIELDS_18(fields) do { \ + CHECK_PACKED_FIELDS_17(fields); \ + CHECK_PACKED_FIELD(fields, 17); \ +} while (0) + +#define CHECK_PACKED_FIELDS_19(fields) do { \ + CHECK_PACKED_FIELDS_18(fields); \ + CHECK_PACKED_FIELD(fields, 18); \ +} while (0) + +#define CHECK_PACKED_FIELDS_20(fields) do { \ + CHECK_PACKED_FIELDS_19(fields); \ + CHECK_PACKED_FIELD(fields, 19); \ +} while (0) + +#define CHECK_PACKED_FIELDS_21(fields) do { \ + CHECK_PACKED_FIELDS_20(fields); \ + CHECK_PACKED_FIELD(fields, 20); \ +} while (0) + +#define CHECK_PACKED_FIELDS_22(fields) do { \ + CHECK_PACKED_FIELDS_21(fields); \ + CHECK_PACKED_FIELD(fields, 21); \ +} while (0) + +#define CHECK_PACKED_FIELDS_23(fields) do { \ + CHECK_PACKED_FIELDS_22(fields); \ + CHECK_PACKED_FIELD(fields, 22); \ +} while (0) + +#define CHECK_PACKED_FIELDS_24(fields) do { \ + CHECK_PACKED_FIELDS_23(fields); \ + CHECK_PACKED_FIELD(fields, 23); \ +} while (0) + +#define CHECK_PACKED_FIELDS_25(fields) do { \ + CHECK_PACKED_FIELDS_24(fields); \ + CHECK_PACKED_FIELD(fields, 24); \ +} while (0) + +#define CHECK_PACKED_FIELDS_26(fields) do { \ + CHECK_PACKED_FIELDS_25(fields); \ + CHECK_PACKED_FIELD(fields, 25); \ +} while (0) + +#define CHECK_PACKED_FIELDS_27(fields) do { \ + CHECK_PACKED_FIELDS_26(fields); \ + CHECK_PACKED_FIELD(fields, 26); \ +} while (0) + +#define CHECK_PACKED_FIELDS_28(fields) do { \ + CHECK_PACKED_FIELDS_27(fields); \ + CHECK_PACKED_FIELD(fields, 27); \ +} while (0) + +#define CHECK_PACKED_FIELDS_29(fields) do { \ + CHECK_PACKED_FIELDS_28(fields); \ + CHECK_PACKED_FIELD(fields, 28); \ +} while (0) + +#define CHECK_PACKED_FIELDS_30(fields) do { \ + CHECK_PACKED_FIELDS_29(fields); \ + CHECK_PACKED_FIELD(fields, 29); \ +} while (0) + +#define CHECK_PACKED_FIELDS_31(fields) do { \ + CHECK_PACKED_FIELDS_30(fields); \ + CHECK_PACKED_FIELD(fields, 30); \ +} while (0) + +#define CHECK_PACKED_FIELDS_32(fields) do { \ + CHECK_PACKED_FIELDS_31(fields); \ + CHECK_PACKED_FIELD(fields, 31); \ +} while (0) + +#define CHECK_PACKED_FIELDS_33(fields) do { \ + CHECK_PACKED_FIELDS_32(fields); \ + CHECK_PACKED_FIELD(fields, 32); \ +} while (0) + +#define CHECK_PACKED_FIELDS_34(fields) do { \ + CHECK_PACKED_FIELDS_33(fields); \ + CHECK_PACKED_FIELD(fields, 33); \ +} while (0) + +#define CHECK_PACKED_FIELDS_35(fields) do { \ + CHECK_PACKED_FIELDS_34(fields); \ + CHECK_PACKED_FIELD(fields, 34); \ +} while (0) + +#define CHECK_PACKED_FIELDS_36(fields) do { \ + CHECK_PACKED_FIELDS_35(fields); \ + CHECK_PACKED_FIELD(fields, 35); \ +} while (0) + +#define CHECK_PACKED_FIELDS_37(fields) do { \ + CHECK_PACKED_FIELDS_36(fields); \ + CHECK_PACKED_FIELD(fields, 36); \ +} while (0) + +#define CHECK_PACKED_FIELDS_38(fields) do { \ + CHECK_PACKED_FIELDS_37(fields); \ + CHECK_PACKED_FIELD(fields, 37); \ +} while (0) + +#define CHECK_PACKED_FIELDS_39(fields) do { \ + CHECK_PACKED_FIELDS_38(fields); \ + CHECK_PACKED_FIELD(fields, 38); \ +} while (0) + +#define CHECK_PACKED_FIELDS_40(fields) do { \ + CHECK_PACKED_FIELDS_39(fields); \ + CHECK_PACKED_FIELD(fields, 39); \ +} while (0) + +#define CHECK_PACKED_FIELDS_41(fields) do { \ + CHECK_PACKED_FIELDS_40(fields); \ + CHECK_PACKED_FIELD(fields, 40); \ +} while (0) + +#define CHECK_PACKED_FIELDS_42(fields) do { \ + CHECK_PACKED_FIELDS_41(fields); \ + CHECK_PACKED_FIELD(fields, 41); \ +} while (0) + +#define CHECK_PACKED_FIELDS_43(fields) do { \ + CHECK_PACKED_FIELDS_42(fields); \ + CHECK_PACKED_FIELD(fields, 42); \ +} while (0) + +#define CHECK_PACKED_FIELDS_44(fields) do { \ + CHECK_PACKED_FIELDS_43(fields); \ + CHECK_PACKED_FIELD(fields, 43); \ +} while (0) + +#define CHECK_PACKED_FIELDS_45(fields) do { \ + CHECK_PACKED_FIELDS_44(fields); \ + CHECK_PACKED_FIELD(fields, 44); \ +} while (0) + +#define CHECK_PACKED_FIELDS_46(fields) do { \ + CHECK_PACKED_FIELDS_45(fields); \ + CHECK_PACKED_FIELD(fields, 45); \ +} while (0) + +#define CHECK_PACKED_FIELDS_47(fields) do { \ + CHECK_PACKED_FIELDS_46(fields); \ + CHECK_PACKED_FIELD(fields, 46); \ +} while (0) + +#define CHECK_PACKED_FIELDS_48(fields) do { \ + CHECK_PACKED_FIELDS_47(fields); \ + CHECK_PACKED_FIELD(fields, 47); \ +} while (0) + +#define CHECK_PACKED_FIELDS_49(fields) do { \ + CHECK_PACKED_FIELDS_48(fields); \ + CHECK_PACKED_FIELD(fields, 48); \ +} while (0) + +#define CHECK_PACKED_FIELDS_50(fields) do { \ + CHECK_PACKED_FIELDS_49(fields); \ + CHECK_PACKED_FIELD(fields, 49); \ +} while (0) + +#define CHECK_PACKED_FIELDS(fields) \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 1, ({ CHECK_PACKED_FIELDS_1(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 2, ({ CHECK_PACKED_FIELDS_2(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 3, ({ CHECK_PACKED_FIELDS_3(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 4, ({ CHECK_PACKED_FIELDS_4(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 5, ({ CHECK_PACKED_FIELDS_5(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 6, ({ CHECK_PACKED_FIELDS_6(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 7, ({ CHECK_PACKED_FIELDS_7(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 8, ({ CHECK_PACKED_FIELDS_8(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 9, ({ CHECK_PACKED_FIELDS_9(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 10, ({ CHECK_PACKED_FIELDS_10(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 11, ({ CHECK_PACKED_FIELDS_11(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 12, ({ CHECK_PACKED_FIELDS_12(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 13, ({ CHECK_PACKED_FIELDS_13(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 14, ({ CHECK_PACKED_FIELDS_14(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 15, ({ CHECK_PACKED_FIELDS_15(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 16, ({ CHECK_PACKED_FIELDS_16(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 17, ({ CHECK_PACKED_FIELDS_17(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 18, ({ CHECK_PACKED_FIELDS_18(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 19, ({ CHECK_PACKED_FIELDS_19(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 20, ({ CHECK_PACKED_FIELDS_20(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 21, ({ CHECK_PACKED_FIELDS_21(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 22, ({ CHECK_PACKED_FIELDS_22(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 23, ({ CHECK_PACKED_FIELDS_23(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 24, ({ CHECK_PACKED_FIELDS_24(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 25, ({ CHECK_PACKED_FIELDS_25(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 26, ({ CHECK_PACKED_FIELDS_26(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 27, ({ CHECK_PACKED_FIELDS_27(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 28, ({ CHECK_PACKED_FIELDS_28(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 29, ({ CHECK_PACKED_FIELDS_29(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 30, ({ CHECK_PACKED_FIELDS_30(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 31, ({ CHECK_PACKED_FIELDS_31(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 32, ({ CHECK_PACKED_FIELDS_32(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 33, ({ CHECK_PACKED_FIELDS_33(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 34, ({ CHECK_PACKED_FIELDS_34(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 35, ({ CHECK_PACKED_FIELDS_35(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 36, ({ CHECK_PACKED_FIELDS_36(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 37, ({ CHECK_PACKED_FIELDS_37(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 38, ({ CHECK_PACKED_FIELDS_38(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 39, ({ CHECK_PACKED_FIELDS_39(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 40, ({ CHECK_PACKED_FIELDS_40(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 41, ({ CHECK_PACKED_FIELDS_41(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 42, ({ CHECK_PACKED_FIELDS_42(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 43, ({ CHECK_PACKED_FIELDS_43(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 44, ({ CHECK_PACKED_FIELDS_44(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 45, ({ CHECK_PACKED_FIELDS_45(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 46, ({ CHECK_PACKED_FIELDS_46(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 47, ({ CHECK_PACKED_FIELDS_47(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 48, ({ CHECK_PACKED_FIELDS_48(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 49, ({ CHECK_PACKED_FIELDS_49(fields); }), \ + __builtin_choose_expr(ARRAY_SIZE(fields) == 50, ({ CHECK_PACKED_FIELDS_50(fields); }), \ + ({ BUILD_BUG_ON_MSG(1, "CHECK_PACKED_FIELDS() must be regenerated to support array sizes larger than 50."); }) \ +)))))))))))))))))))))))))))))))))))))))))))))))))) + +/* End of generated content */ + +#define pack_fields(pbuf, pbuflen, ustruct, fields, quirks) \ + ({ \ + CHECK_PACKED_FIELDS(fields); \ + CHECK_PACKED_FIELDS_SIZE((fields), (pbuflen)); \ + _Generic((fields), \ + const struct packed_field_u8 * : pack_fields_u8, \ + const struct packed_field_u16 * : pack_fields_u16 \ + )((pbuf), (pbuflen), (ustruct), (fields), ARRAY_SIZE(fields), (quirks)); \ + }) + +#define unpack_fields(pbuf, pbuflen, ustruct, fields, quirks) \ + ({ \ + CHECK_PACKED_FIELDS(fields); \ + CHECK_PACKED_FIELDS_SIZE((fields), (pbuflen)); \ + _Generic((fields), \ + const struct packed_field_u8 * : unpack_fields_u8, \ + const struct packed_field_u16 * : unpack_fields_u16 \ + )((pbuf), (pbuflen), (ustruct), (fields), ARRAY_SIZE(fields), (quirks)); \ + }) + #endif diff --git a/include/linux/page-flags-layout.h b/include/linux/page-flags-layout.h index 7d79818dc065..4f5c9e979bb9 100644 --- a/include/linux/page-flags-layout.h +++ b/include/linux/page-flags-layout.h @@ -111,5 +111,12 @@ ZONES_WIDTH - LRU_GEN_WIDTH - SECTIONS_WIDTH - \ NODES_WIDTH - KASAN_TAG_WIDTH - LAST_CPUPID_WIDTH) +#define NR_NON_PAGEFLAG_BITS (SECTIONS_WIDTH + NODES_WIDTH + ZONES_WIDTH + \ + LAST_CPUPID_SHIFT + KASAN_TAG_WIDTH + \ + LRU_GEN_WIDTH + LRU_REFS_WIDTH) + +#define NR_UNUSED_PAGEFLAG_BITS (BITS_PER_LONG - \ + (NR_NON_PAGEFLAG_BITS + NR_PAGEFLAGS)) + #endif #endif /* _LINUX_PAGE_FLAGS_LAYOUT */ diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 4bf1c25fd1dc..36d283552f80 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -30,16 +30,11 @@ * - Pages falling into physical memory gaps - not IORESOURCE_SYSRAM. Trying * to read/write these pages might end badly. Don't touch! * - The zero page(s) - * - Pages not added to the page allocator when onlining a section because - * they were excluded via the online_page_callback() or because they are - * PG_hwpoison. * - Pages allocated in the context of kexec/kdump (loaded kernel image, * control pages, vmcoreinfo) * - MMIO/DMA pages. Some architectures don't allow to ioremap pages that are * not marked PG_reserved (as they might be in use by somebody else who does * not respect the caching strategy). - * - Pages part of an offline section (struct pages of offline sections should - * not be trusted as they will be initialized when first onlined). * - MCA pages on ia64 * - Pages holding CPU notes for POWER Firmware Assisted Dump * - Device memory (e.g. PMEM, DAX, HMM) @@ -71,8 +66,6 @@ * PG_referenced, PG_reclaim are used for page reclaim for anonymous and * file-backed pagecache (see mm/vmscan.c). * - * PG_error is set to indicate that an I/O error occurred on this page. - * * PG_arch_1 is an architecture specific page state bit. The generic code * guarantees that this bit is cleared for a page when it first is entered into * the page cache. @@ -108,23 +101,19 @@ enum pageflags { PG_waiters, /* Page has waiters, check its waitqueue. Must be bit #7 and in the same byte as "PG_locked" */ PG_active, PG_workingset, - PG_error, - PG_slab, - PG_owner_priv_1, /* Owner use. If pagecache, fs may use*/ + PG_owner_priv_1, /* Owner use. If pagecache, fs may use */ + PG_owner_2, /* Owner use. If pagecache, fs may use */ PG_arch_1, PG_reserved, PG_private, /* If pagecache, has fs-private data */ PG_private_2, /* If pagecache, has fs aux data */ - PG_mappedtodisk, /* Has blocks allocated on-disk */ PG_reclaim, /* To be reclaimed asap */ PG_swapbacked, /* Page is backed by RAM/swap */ PG_unevictable, /* Page is "unevictable" */ + PG_dropbehind, /* drop pages on IO completion */ #ifdef CONFIG_MMU PG_mlocked, /* Page is vma mlocked */ #endif -#ifdef CONFIG_ARCH_USES_PG_UNCACHED - PG_uncached, /* Page has been mapped as uncached */ -#endif #ifdef CONFIG_MEMORY_FAILURE PG_hwpoison, /* hardware poisoned page. Don't touch */ #endif @@ -132,14 +121,21 @@ enum pageflags { PG_young, PG_idle, #endif -#ifdef CONFIG_ARCH_USES_PG_ARCH_X +#ifdef CONFIG_ARCH_USES_PG_ARCH_2 PG_arch_2, +#endif +#ifdef CONFIG_ARCH_USES_PG_ARCH_3 PG_arch_3, #endif __NR_PAGEFLAGS, PG_readahead = PG_reclaim, + /* Anonymous memory (and shmem) */ + PG_swapcache = PG_owner_priv_1, /* Swap page: swp_entry_t in private */ + /* Some filesystems */ + PG_checked = PG_owner_priv_1, + /* * Depending on the way an anonymous folio can be mapped into a page * table (e.g., single PMD/PUD/CONT of the head page vs. PTE-mapped @@ -147,13 +143,13 @@ enum pageflags { * tail pages of an anonymous folio. For now, we only expect it to be * set on tail pages for PTE-mapped THP. */ - PG_anon_exclusive = PG_mappedtodisk, - - /* Filesystems */ - PG_checked = PG_owner_priv_1, + PG_anon_exclusive = PG_owner_2, - /* SwapBacked */ - PG_swapcache = PG_owner_priv_1, /* Swap page: swp_entry_t in private */ + /* + * Set if all buffer heads in the folio are mapped. + * Filesystems which do not use BHs can use it for their own purpose. + */ + PG_mappedtodisk = PG_owner_2, /* Two page bits are conscripted by FS-Cache to maintain local caching * state. These bits are set on pages belonging to the netfs's inodes @@ -189,8 +185,9 @@ enum pageflags { */ /* At least one page in this folio has the hwpoison flag set */ - PG_has_hwpoisoned = PG_error, + PG_has_hwpoisoned = PG_active, PG_large_rmappable = PG_workingset, /* anon or file-backed */ + PG_partially_mapped = PG_reclaim, /* was identified to be partially mapped */ }; #define PAGEFLAGS_MASK ((1UL << NR_PAGEFLAGS) - 1) @@ -241,7 +238,7 @@ static __always_inline int page_is_fake_head(const struct page *page) return page_fixed_fake_head(page) != page; } -static inline unsigned long _compound_head(const struct page *page) +static __always_inline unsigned long _compound_head(const struct page *page) { unsigned long head = READ_ONCE(page->compound_head); @@ -310,7 +307,7 @@ static const unsigned long *const_folio_flags(const struct folio *folio, { const struct page *page = &folio->page; - VM_BUG_ON_PGFLAGS(PageTail(page), page); + VM_BUG_ON_PGFLAGS(page->compound_head & 1, page); VM_BUG_ON_PGFLAGS(n > 0 && !test_bit(PG_head, &page->flags), page); return &page[n].flags; } @@ -319,7 +316,7 @@ static unsigned long *folio_flags(struct folio *folio, unsigned n) { struct page *page = &folio->page; - VM_BUG_ON_PGFLAGS(PageTail(page), page); + VM_BUG_ON_PGFLAGS(page->compound_head & 1, page); VM_BUG_ON_PGFLAGS(n > 0 && !test_bit(PG_head, &page->flags), page); return &page[n].flags; } @@ -512,19 +509,18 @@ static inline int TestClearPage##uname(struct page *page) { return 0; } __PAGEFLAG(Locked, locked, PF_NO_TAIL) FOLIO_FLAG(waiters, FOLIO_HEAD_PAGE) -PAGEFLAG(Error, error, PF_NO_TAIL) TESTCLEARFLAG(Error, error, PF_NO_TAIL) -PAGEFLAG(Referenced, referenced, PF_HEAD) - TESTCLEARFLAG(Referenced, referenced, PF_HEAD) - __SETPAGEFLAG(Referenced, referenced, PF_HEAD) +FOLIO_FLAG(referenced, FOLIO_HEAD_PAGE) + FOLIO_TEST_CLEAR_FLAG(referenced, FOLIO_HEAD_PAGE) + __FOLIO_SET_FLAG(referenced, FOLIO_HEAD_PAGE) PAGEFLAG(Dirty, dirty, PF_HEAD) TESTSCFLAG(Dirty, dirty, PF_HEAD) __CLEARPAGEFLAG(Dirty, dirty, PF_HEAD) PAGEFLAG(LRU, lru, PF_HEAD) __CLEARPAGEFLAG(LRU, lru, PF_HEAD) TESTCLEARFLAG(LRU, lru, PF_HEAD) -PAGEFLAG(Active, active, PF_HEAD) __CLEARPAGEFLAG(Active, active, PF_HEAD) - TESTCLEARFLAG(Active, active, PF_HEAD) +FOLIO_FLAG(active, FOLIO_HEAD_PAGE) + __FOLIO_CLEAR_FLAG(active, FOLIO_HEAD_PAGE) + FOLIO_TEST_CLEAR_FLAG(active, FOLIO_HEAD_PAGE) PAGEFLAG(Workingset, workingset, PF_HEAD) TESTCLEARFLAG(Workingset, workingset, PF_HEAD) -__PAGEFLAG(Slab, slab, PF_NO_TAIL) PAGEFLAG(Checked, checked, PF_NO_COMPOUND) /* Used by some filesystems */ /* Xen */ @@ -538,9 +534,9 @@ PAGEFLAG(XenRemapped, xen_remapped, PF_NO_COMPOUND) PAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) __CLEARPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) __SETPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) -PAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) - __CLEARPAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) - __SETPAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) +FOLIO_FLAG(swapbacked, FOLIO_HEAD_PAGE) + __FOLIO_CLEAR_FLAG(swapbacked, FOLIO_HEAD_PAGE) + __FOLIO_SET_FLAG(swapbacked, FOLIO_HEAD_PAGE) /* * Private page markings that may be used by the filesystem that owns the page @@ -548,9 +544,10 @@ PAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) * - PG_private and PG_private_2 cause release_folio() and co to be invoked */ PAGEFLAG(Private, private, PF_ANY) -PAGEFLAG(Private2, private_2, PF_ANY) TESTSCFLAG(Private2, private_2, PF_ANY) -PAGEFLAG(OwnerPriv1, owner_priv_1, PF_ANY) - TESTCLEARFLAG(OwnerPriv1, owner_priv_1, PF_ANY) +FOLIO_FLAG(private_2, FOLIO_HEAD_PAGE) + +/* owner_2 can be set on tail pages for anon memory */ +FOLIO_FLAG(owner_2, FOLIO_HEAD_PAGE) /* * Only test-and-set exist for PG_writeback. The unconditional operators are @@ -558,13 +555,17 @@ PAGEFLAG(OwnerPriv1, owner_priv_1, PF_ANY) */ TESTPAGEFLAG(Writeback, writeback, PF_NO_TAIL) TESTSCFLAG(Writeback, writeback, PF_NO_TAIL) -PAGEFLAG(MappedToDisk, mappedtodisk, PF_NO_TAIL) +FOLIO_FLAG(mappedtodisk, FOLIO_HEAD_PAGE) /* PG_readahead is only used for reads; PG_reclaim is only for writes */ PAGEFLAG(Reclaim, reclaim, PF_NO_TAIL) TESTCLEARFLAG(Reclaim, reclaim, PF_NO_TAIL) -PAGEFLAG(Readahead, readahead, PF_NO_COMPOUND) - TESTCLEARFLAG(Readahead, readahead, PF_NO_COMPOUND) +FOLIO_FLAG(readahead, FOLIO_HEAD_PAGE) + FOLIO_TEST_CLEAR_FLAG(readahead, FOLIO_HEAD_PAGE) + +FOLIO_FLAG(dropbehind, FOLIO_HEAD_PAGE) + FOLIO_TEST_CLEAR_FLAG(dropbehind, FOLIO_HEAD_PAGE) + __FOLIO_SET_FLAG(dropbehind, FOLIO_HEAD_PAGE) #ifdef CONFIG_HIGHMEM /* @@ -584,56 +585,50 @@ static __always_inline bool folio_test_swapcache(const struct folio *folio) test_bit(PG_swapcache, const_folio_flags(folio, 0)); } -static __always_inline bool PageSwapCache(const struct page *page) -{ - return folio_test_swapcache(page_folio(page)); -} - -SETPAGEFLAG(SwapCache, swapcache, PF_NO_TAIL) -CLEARPAGEFLAG(SwapCache, swapcache, PF_NO_TAIL) +FOLIO_SET_FLAG(swapcache, FOLIO_HEAD_PAGE) +FOLIO_CLEAR_FLAG(swapcache, FOLIO_HEAD_PAGE) #else -PAGEFLAG_FALSE(SwapCache, swapcache) +FOLIO_FLAG_FALSE(swapcache) #endif -PAGEFLAG(Unevictable, unevictable, PF_HEAD) - __CLEARPAGEFLAG(Unevictable, unevictable, PF_HEAD) - TESTCLEARFLAG(Unevictable, unevictable, PF_HEAD) +FOLIO_FLAG(unevictable, FOLIO_HEAD_PAGE) + __FOLIO_CLEAR_FLAG(unevictable, FOLIO_HEAD_PAGE) + FOLIO_TEST_CLEAR_FLAG(unevictable, FOLIO_HEAD_PAGE) #ifdef CONFIG_MMU -PAGEFLAG(Mlocked, mlocked, PF_NO_TAIL) - __CLEARPAGEFLAG(Mlocked, mlocked, PF_NO_TAIL) - TESTSCFLAG(Mlocked, mlocked, PF_NO_TAIL) -#else -PAGEFLAG_FALSE(Mlocked, mlocked) __CLEARPAGEFLAG_NOOP(Mlocked, mlocked) - TESTSCFLAG_FALSE(Mlocked, mlocked) -#endif - -#ifdef CONFIG_ARCH_USES_PG_UNCACHED -PAGEFLAG(Uncached, uncached, PF_NO_COMPOUND) +FOLIO_FLAG(mlocked, FOLIO_HEAD_PAGE) + __FOLIO_CLEAR_FLAG(mlocked, FOLIO_HEAD_PAGE) + FOLIO_TEST_CLEAR_FLAG(mlocked, FOLIO_HEAD_PAGE) + FOLIO_TEST_SET_FLAG(mlocked, FOLIO_HEAD_PAGE) #else -PAGEFLAG_FALSE(Uncached, uncached) +FOLIO_FLAG_FALSE(mlocked) + __FOLIO_CLEAR_FLAG_NOOP(mlocked) + FOLIO_TEST_CLEAR_FLAG_FALSE(mlocked) + FOLIO_TEST_SET_FLAG_FALSE(mlocked) #endif #ifdef CONFIG_MEMORY_FAILURE PAGEFLAG(HWPoison, hwpoison, PF_ANY) TESTSCFLAG(HWPoison, hwpoison, PF_ANY) #define __PG_HWPOISON (1UL << PG_hwpoison) -#define MAGIC_HWPOISON 0x48575053U /* HWPS */ -extern void SetPageHWPoisonTakenOff(struct page *page); -extern void ClearPageHWPoisonTakenOff(struct page *page); -extern bool take_page_off_buddy(struct page *page); -extern bool put_page_back_buddy(struct page *page); #else PAGEFLAG_FALSE(HWPoison, hwpoison) #define __PG_HWPOISON 0 #endif -#if defined(CONFIG_PAGE_IDLE_FLAG) && defined(CONFIG_64BIT) +#ifdef CONFIG_PAGE_IDLE_FLAG +#ifdef CONFIG_64BIT FOLIO_TEST_FLAG(young, FOLIO_HEAD_PAGE) FOLIO_SET_FLAG(young, FOLIO_HEAD_PAGE) FOLIO_TEST_CLEAR_FLAG(young, FOLIO_HEAD_PAGE) FOLIO_FLAG(idle, FOLIO_HEAD_PAGE) #endif +/* See page_idle.h for !64BIT workaround */ +#else /* !CONFIG_PAGE_IDLE_FLAG */ +FOLIO_FLAG_FALSE(young) +FOLIO_TEST_CLEAR_FLAG_FALSE(young) +FOLIO_FLAG_FALSE(idle) +#endif /* * PageReported() is used to track reported free pages within the Buddy @@ -650,27 +645,28 @@ PAGEFLAG_FALSE(VmemmapSelfHosted, vmemmap_self_hosted) #endif /* - * On an anonymous page mapped into a user virtual memory area, - * page->mapping points to its anon_vma, not to a struct address_space; + * On an anonymous folio mapped into a user virtual memory area, + * folio->mapping points to its anon_vma, not to a struct address_space; * with the PAGE_MAPPING_ANON bit set to distinguish it. See rmap.h. * * On an anonymous page in a VM_MERGEABLE area, if CONFIG_KSM is enabled, * the PAGE_MAPPING_MOVABLE bit may be set along with the PAGE_MAPPING_ANON - * bit; and then page->mapping points, not to an anon_vma, but to a private + * bit; and then folio->mapping points, not to an anon_vma, but to a private * structure which KSM associates with that merged page. See ksm.h. * * PAGE_MAPPING_KSM without PAGE_MAPPING_ANON is used for non-lru movable - * page and then page->mapping points to a struct movable_operations. + * page and then folio->mapping points to a struct movable_operations. * - * Please note that, confusingly, "page_mapping" refers to the inode - * address_space which maps the page from disk; whereas "page_mapped" - * refers to user virtual address space into which the page is mapped. + * Please note that, confusingly, "folio_mapping" refers to the inode + * address_space which maps the folio from disk; whereas "folio_mapped" + * refers to user virtual address space into which the folio is mapped. * * For slab pages, since slab reuses the bits in struct page to store its - * internal states, the page->mapping does not exist as such, nor do these - * flags below. So in order to avoid testing non-existent bits, please - * make sure that PageSlab(page) actually evaluates to false before calling - * the following functions (e.g., PageAnon). See mm/slab.h. + * internal states, the folio->mapping does not exist as such, nor do + * these flags below. So in order to avoid testing non-existent bits, + * please make sure that folio_test_slab(folio) actually evaluates to + * false before calling the following functions (e.g., folio_test_anon). + * See mm/slab.h. */ #define PAGE_MAPPING_ANON 0x1 #define PAGE_MAPPING_MOVABLE 0x2 @@ -688,7 +684,7 @@ static __always_inline bool folio_mapping_flags(const struct folio *folio) return ((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS) != 0; } -static __always_inline int PageMappingFlags(const struct page *page) +static __always_inline bool PageMappingFlags(const struct page *page) { return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) != 0; } @@ -698,6 +694,13 @@ static __always_inline bool folio_test_anon(const struct folio *folio) return ((unsigned long)folio->mapping & PAGE_MAPPING_ANON) != 0; } +static __always_inline bool PageAnonNotKsm(const struct page *page) +{ + unsigned long flags = (unsigned long)page_folio(page)->mapping; + + return (flags & PAGE_MAPPING_FLAGS) == PAGE_MAPPING_ANON; +} + static __always_inline bool PageAnon(const struct page *page) { return folio_test_anon(page_folio(page)); @@ -709,7 +712,7 @@ static __always_inline bool __folio_test_movable(const struct folio *folio) PAGE_MAPPING_MOVABLE; } -static __always_inline int __PageMovable(const struct page *page) +static __always_inline bool __PageMovable(const struct page *page) { return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) == PAGE_MAPPING_MOVABLE; @@ -727,16 +730,11 @@ static __always_inline bool folio_test_ksm(const struct folio *folio) return ((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS) == PAGE_MAPPING_KSM; } - -static __always_inline bool PageKsm(const struct page *page) -{ - return folio_test_ksm(page_folio(page)); -} #else -TESTPAGEFLAG_FALSE(Ksm, ksm) +FOLIO_TEST_FLAG_FALSE(ksm) #endif -u64 stable_page_flags(struct page *page); +u64 stable_page_flags(const struct page *page); /** * folio_xor_flags_has_waiters - Change some folio flags. @@ -784,7 +782,7 @@ static inline bool folio_test_uptodate(const struct folio *folio) return ret; } -static inline int PageUptodate(const struct page *page) +static inline bool PageUptodate(const struct page *page) { return folio_test_uptodate(page_folio(page)); } @@ -868,9 +866,11 @@ static inline void ClearPageCompound(struct page *page) BUG_ON(!PageHead(page)); ClearPageHead(page); } -PAGEFLAG(LargeRmappable, large_rmappable, PF_SECOND) +FOLIO_FLAG(large_rmappable, FOLIO_SECOND_PAGE) +FOLIO_FLAG(partially_mapped, FOLIO_SECOND_PAGE) #else -TESTPAGEFLAG_FALSE(LargeRmappable, large_rmappable) +FOLIO_FLAG_FALSE(large_rmappable) +FOLIO_FLAG_FALSE(partially_mapped) #endif #define PG_head_mask ((1UL << PG_head)) @@ -899,21 +899,9 @@ static inline int PageTransCompound(const struct page *page) { return PageCompound(page); } - -/* - * PageTransTail returns true for both transparent huge pages - * and hugetlbfs pages, so it should only be called when it's known - * that hugetlbfs pages aren't involved. - */ -static inline int PageTransTail(const struct page *page) -{ - return PageTail(page); -} #else TESTPAGEFLAG_FALSE(TransHuge, transhuge) TESTPAGEFLAG_FALSE(TransCompound, transcompound) -TESTPAGEFLAG_FALSE(TransCompoundMap, transcompoundmap) -TESTPAGEFLAG_FALSE(TransTail, transtail) #endif #if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_TRANSPARENT_HUGEPAGE) @@ -923,77 +911,88 @@ TESTPAGEFLAG_FALSE(TransTail, transtail) * * This flag is set by hwpoison handler. Cleared by THP split or free page. */ -PAGEFLAG(HasHWPoisoned, has_hwpoisoned, PF_SECOND) - TESTSCFLAG(HasHWPoisoned, has_hwpoisoned, PF_SECOND) +FOLIO_FLAG(has_hwpoisoned, FOLIO_SECOND_PAGE) #else -PAGEFLAG_FALSE(HasHWPoisoned, has_hwpoisoned) - TESTSCFLAG_FALSE(HasHWPoisoned, has_hwpoisoned) +FOLIO_FLAG_FALSE(has_hwpoisoned) #endif /* - * For pages that are never mapped to userspace (and aren't PageSlab), - * page_type may be used. Because it is initialised to -1, we invert the - * sense of the bit, so __SetPageFoo *clears* the bit used for PageFoo, and - * __ClearPageFoo *sets* the bit used for PageFoo. We reserve a few high and - * low bits so that an underflow or overflow of _mapcount won't be - * mistaken for a page type value. + * For pages that do not use mapcount, page_type may be used. + * The low 24 bits of pagetype may be used for your own purposes, as long + * as you are careful to not affect the top 8 bits. The low bits of + * pagetype will be overwritten when you clear the page_type from the page. */ +enum pagetype { + /* 0x00-0x7f are positive numbers, ie mapcount */ + /* Reserve 0x80-0xef for mapcount overflow. */ + PGTY_buddy = 0xf0, + PGTY_offline = 0xf1, + PGTY_table = 0xf2, + PGTY_guard = 0xf3, + PGTY_hugetlb = 0xf4, + PGTY_slab = 0xf5, + PGTY_zsmalloc = 0xf6, + PGTY_unaccepted = 0xf7, -#define PAGE_TYPE_BASE 0xf0000000 -/* Reserve 0x0000007f to catch underflows of _mapcount */ -#define PAGE_MAPCOUNT_RESERVE -128 -#define PG_buddy 0x00000080 -#define PG_offline 0x00000100 -#define PG_table 0x00000200 -#define PG_guard 0x00000400 -#define PG_hugetlb 0x00000800 + PGTY_mapcount_underflow = 0xff +}; -#define PageType(page, flag) \ - ((page->page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE) -#define folio_test_type(folio, flag) \ - ((folio->page.page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE) +static inline bool page_type_has_type(int page_type) +{ + return page_type < (PGTY_mapcount_underflow << 24); +} -static inline int page_type_has_type(unsigned int page_type) +/* This takes a mapcount which is one more than page->_mapcount */ +static inline bool page_mapcount_is_type(unsigned int mapcount) { - return (int)page_type < PAGE_MAPCOUNT_RESERVE; + return page_type_has_type(mapcount - 1); } -static inline int page_has_type(const struct page *page) +static inline bool page_has_type(const struct page *page) { - return page_type_has_type(page->page_type); + return page_mapcount_is_type(data_race(page->page_type)); } #define FOLIO_TYPE_OPS(lname, fname) \ -static __always_inline bool folio_test_##fname(const struct folio *folio)\ +static __always_inline bool folio_test_##fname(const struct folio *folio) \ { \ - return folio_test_type(folio, PG_##lname); \ + return data_race(folio->page.page_type >> 24) == PGTY_##lname; \ } \ static __always_inline void __folio_set_##fname(struct folio *folio) \ { \ - VM_BUG_ON_FOLIO(!folio_test_type(folio, 0), folio); \ - folio->page.page_type &= ~PG_##lname; \ + if (folio_test_##fname(folio)) \ + return; \ + VM_BUG_ON_FOLIO(data_race(folio->page.page_type) != UINT_MAX, \ + folio); \ + folio->page.page_type = (unsigned int)PGTY_##lname << 24; \ } \ static __always_inline void __folio_clear_##fname(struct folio *folio) \ { \ + if (folio->page.page_type == UINT_MAX) \ + return; \ VM_BUG_ON_FOLIO(!folio_test_##fname(folio), folio); \ - folio->page.page_type |= PG_##lname; \ + folio->page.page_type = UINT_MAX; \ } #define PAGE_TYPE_OPS(uname, lname, fname) \ FOLIO_TYPE_OPS(lname, fname) \ static __always_inline int Page##uname(const struct page *page) \ { \ - return PageType(page, PG_##lname); \ + return data_race(page->page_type >> 24) == PGTY_##lname; \ } \ static __always_inline void __SetPage##uname(struct page *page) \ { \ - VM_BUG_ON_PAGE(!PageType(page, 0), page); \ - page->page_type &= ~PG_##lname; \ + if (Page##uname(page)) \ + return; \ + VM_BUG_ON_PAGE(data_race(page->page_type) != UINT_MAX, page); \ + page->page_type = (unsigned int)PGTY_##lname << 24; \ } \ static __always_inline void __ClearPage##uname(struct page *page) \ { \ + if (page->page_type == UINT_MAX) \ + return; \ VM_BUG_ON_PAGE(!Page##uname(page), page); \ - page->page_type |= PG_##lname; \ + page->page_type = UINT_MAX; \ } /* @@ -1009,15 +1008,22 @@ PAGE_TYPE_OPS(Buddy, buddy, buddy) * The content of these pages is effectively stale. Such pages should not * be touched (read/write/dump/save) except by their owner. * + * When a memory block gets onlined, all pages are initialized with a + * refcount of 1 and PageOffline(). generic_online_page() will + * take care of clearing PageOffline(). + * * If a driver wants to allow to offline unmovable PageOffline() pages without * putting them back to the buddy, it can do so via the memory notifier by * decrementing the reference count in MEM_GOING_OFFLINE and incrementing the * reference count in MEM_CANCEL_OFFLINE. When offlining, the PageOffline() - * pages (now with a reference count of zero) are treated like free pages, - * allowing the containing memory block to get offlined. A driver that + * pages (now with a reference count of zero) are treated like free (unmanaged) + * pages, allowing the containing memory block to get offlined. A driver that * relies on this feature is aware that re-onlining the memory block will - * require to re-set the pages PageOffline() and not giving them to the - * buddy via online_page_callback_t. + * require not giving them to the buddy via generic_online_page(). + * + * Memory offlining code will not adjust the managed page count for any + * PageOffline() pages, treating them like they were never exposed to the + * buddy using generic_online_page(). * * There are drivers that mark a page PageOffline() and expect there won't be * any further access to page content. PFN walkers that read content of random @@ -1041,12 +1047,35 @@ PAGE_TYPE_OPS(Table, table, pgtable) */ PAGE_TYPE_OPS(Guard, guard, guard) +FOLIO_TYPE_OPS(slab, slab) + +/** + * PageSlab - Determine if the page belongs to the slab allocator + * @page: The page to test. + * + * Context: Any context. + * Return: True for slab pages, false for any other kind of page. + */ +static inline bool PageSlab(const struct page *page) +{ + return folio_test_slab(page_folio(page)); +} + #ifdef CONFIG_HUGETLB_PAGE FOLIO_TYPE_OPS(hugetlb, hugetlb) #else FOLIO_TEST_FLAG_FALSE(hugetlb) #endif +PAGE_TYPE_OPS(Zsmalloc, zsmalloc, zsmalloc) + +/* + * Mark pages that has to be accepted before touched for the first time. + * + * Serialized with zone lock. + */ +PAGE_TYPE_OPS(Unaccepted, unaccepted, unaccepted) + /** * PageHuge - Determine if the page belongs to hugetlbfs * @page: The page to test. @@ -1065,34 +1094,42 @@ static inline bool PageHuge(const struct page *page) * best effort only and inherently racy: there is no way to synchronize with * failing hardware. */ -static inline bool is_page_hwpoison(struct page *page) +static inline bool is_page_hwpoison(const struct page *page) { + const struct folio *folio; + if (PageHWPoison(page)) return true; - return PageHuge(page) && PageHWPoison(compound_head(page)); + folio = page_folio(page); + return folio_test_hugetlb(folio) && PageHWPoison(&folio->page); } -extern bool is_free_buddy_page(struct page *page); +bool is_free_buddy_page(const struct page *page); PAGEFLAG(Isolated, isolated, PF_ANY); static __always_inline int PageAnonExclusive(const struct page *page) { VM_BUG_ON_PGFLAGS(!PageAnon(page), page); - VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); + /* + * HugeTLB stores this information on the head page; THP keeps it per + * page + */ + if (PageHuge(page)) + page = compound_head(page); return test_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); } static __always_inline void SetPageAnonExclusive(struct page *page) { - VM_BUG_ON_PGFLAGS(!PageAnon(page) || PageKsm(page), page); + VM_BUG_ON_PGFLAGS(!PageAnonNotKsm(page), page); VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); set_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); } static __always_inline void ClearPageAnonExclusive(struct page *page) { - VM_BUG_ON_PGFLAGS(!PageAnon(page) || PageKsm(page), page); + VM_BUG_ON_PGFLAGS(!PageAnonNotKsm(page), page); VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); clear_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); } @@ -1118,7 +1155,7 @@ static __always_inline void __ClearPageAnonExclusive(struct page *page) (1UL << PG_lru | 1UL << PG_locked | \ 1UL << PG_private | 1UL << PG_private_2 | \ 1UL << PG_writeback | 1UL << PG_reserved | \ - 1UL << PG_slab | 1UL << PG_active | \ + 1UL << PG_active | \ 1UL << PG_unevictable | __PG_MLOCKED | LRU_GEN_MASK) /* @@ -1138,25 +1175,20 @@ static __always_inline void __ClearPageAnonExclusive(struct page *page) */ #define PAGE_FLAGS_SECOND \ (0xffUL /* order */ | 1UL << PG_has_hwpoisoned | \ - 1UL << PG_large_rmappable) + 1UL << PG_large_rmappable | 1UL << PG_partially_mapped) #define PAGE_FLAGS_PRIVATE \ (1UL << PG_private | 1UL << PG_private_2) /** - * page_has_private - Determine if page has private stuff - * @page: The page to be checked + * folio_has_private - Determine if folio has private stuff + * @folio: The folio to be checked * - * Determine if a page has private stuff, indicating that release routines + * Determine if a folio has private stuff, indicating that release routines * should be invoked upon it. */ -static inline int page_has_private(const struct page *page) -{ - return !!(page->flags & PAGE_FLAGS_PRIVATE); -} - -static inline bool folio_has_private(const struct folio *folio) +static inline int folio_has_private(const struct folio *folio) { - return page_has_private(&folio->page); + return !!(folio->flags & PAGE_FLAGS_PRIVATE); } #undef PF_ANY diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h index 4ac34392823a..898bb788243b 100644 --- a/include/linux/page-isolation.h +++ b/include/linux/page-isolation.h @@ -3,10 +3,6 @@ #define __LINUX_PAGEISOLATION_H #ifdef CONFIG_MEMORY_ISOLATION -static inline bool has_isolate_pageblock(struct zone *zone) -{ - return zone->nr_isolate_pageblock; -} static inline bool is_migrate_isolate_page(struct page *page) { return get_pageblock_migratetype(page) == MIGRATE_ISOLATE; @@ -16,10 +12,6 @@ static inline bool is_migrate_isolate(int migratetype) return migratetype == MIGRATE_ISOLATE; } #else -static inline bool has_isolate_pageblock(struct zone *zone) -{ - return false; -} static inline bool is_migrate_isolate_page(struct page *page) { return false; @@ -34,11 +26,12 @@ static inline bool is_migrate_isolate(int migratetype) #define REPORT_FAILURE 0x2 void set_pageblock_migratetype(struct page *page, int migratetype); -int move_freepages_block(struct zone *zone, struct page *page, - int migratetype, int *num_movable); + +bool move_freepages_block_isolate(struct zone *zone, struct page *page, + int migratetype); int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, - int migratetype, int flags, gfp_t gfp_flags); + int migratetype, int flags); void undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, int migratetype); diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h index 8cd858d912c4..46406f3fe34d 100644 --- a/include/linux/page_counter.h +++ b/include/linux/page_counter.h @@ -26,11 +26,14 @@ struct page_counter { atomic_long_t children_low_usage; unsigned long watermark; + /* Latest cg2 reset watermark */ + unsigned long local_watermark; unsigned long failcnt; /* Keep all the read most fields in a separete cacheline. */ CACHELINE_PADDING(_pad2_); + bool protection_support; unsigned long min; unsigned long low; unsigned long high; @@ -44,12 +47,17 @@ struct page_counter { #define PAGE_COUNTER_MAX (LONG_MAX / PAGE_SIZE) #endif +/* + * Protection is supported only for the first counter (with id 0). + */ static inline void page_counter_init(struct page_counter *counter, - struct page_counter *parent) + struct page_counter *parent, + bool protection_support) { - atomic_long_set(&counter->usage, 0); + counter->usage = (atomic_long_t)ATOMIC_LONG_INIT(0); counter->max = PAGE_COUNTER_MAX; counter->parent = parent; + counter->protection_support = protection_support; } static inline unsigned long page_counter_read(struct page_counter *counter) @@ -78,7 +86,24 @@ int page_counter_memparse(const char *buf, const char *max, static inline void page_counter_reset_watermark(struct page_counter *counter) { - counter->watermark = page_counter_read(counter); + unsigned long usage = page_counter_read(counter); + + /* + * Update local_watermark first, so it's always <= watermark + * (modulo CPU/compiler re-ordering) + */ + counter->local_watermark = usage; + counter->watermark = usage; } +#if IS_ENABLED(CONFIG_MEMCG) || IS_ENABLED(CONFIG_CGROUP_DMEM) +void page_counter_calculate_protection(struct page_counter *root, + struct page_counter *counter, + bool recursive_protection); +#else +static inline void page_counter_calculate_protection(struct page_counter *root, + struct page_counter *counter, + bool recursive_protection) {} +#endif + #endif /* _LINUX_PAGE_COUNTER_H */ diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h index be98564191e6..e4b48a0dda24 100644 --- a/include/linux/page_ext.h +++ b/include/linux/page_ext.h @@ -4,7 +4,6 @@ #include <linux/types.h> #include <linux/stacktrace.h> -#include <linux/stackdepot.h> struct pglist_data; @@ -78,7 +77,7 @@ static inline void page_ext_init(void) } #endif -extern struct page_ext *page_ext_get(struct page *page); +extern struct page_ext *page_ext_get(const struct page *page); extern void page_ext_put(struct page_ext *page_ext); static inline void *page_ext_data(struct page_ext *page_ext, @@ -118,7 +117,7 @@ static inline void page_ext_init_flatmem(void) { } -static inline struct page_ext *page_ext_get(struct page *page) +static inline struct page_ext *page_ext_get(const struct page *page) { return NULL; } diff --git a/include/linux/page_frag_cache.h b/include/linux/page_frag_cache.h new file mode 100644 index 000000000000..41a91df82631 --- /dev/null +++ b/include/linux/page_frag_cache.h @@ -0,0 +1,61 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _LINUX_PAGE_FRAG_CACHE_H +#define _LINUX_PAGE_FRAG_CACHE_H + +#include <linux/bits.h> +#include <linux/log2.h> +#include <linux/mm_types_task.h> +#include <linux/types.h> + +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) +/* Use a full byte here to enable assembler optimization as the shift + * operation is usually expecting a byte. + */ +#define PAGE_FRAG_CACHE_ORDER_MASK GENMASK(7, 0) +#else +/* Compiler should be able to figure out we don't read things as any value + * ANDed with 0 is 0. + */ +#define PAGE_FRAG_CACHE_ORDER_MASK 0 +#endif + +#define PAGE_FRAG_CACHE_PFMEMALLOC_BIT (PAGE_FRAG_CACHE_ORDER_MASK + 1) + +static inline bool encoded_page_decode_pfmemalloc(unsigned long encoded_page) +{ + return !!(encoded_page & PAGE_FRAG_CACHE_PFMEMALLOC_BIT); +} + +static inline void page_frag_cache_init(struct page_frag_cache *nc) +{ + nc->encoded_page = 0; +} + +static inline bool page_frag_cache_is_pfmemalloc(struct page_frag_cache *nc) +{ + return encoded_page_decode_pfmemalloc(nc->encoded_page); +} + +void page_frag_cache_drain(struct page_frag_cache *nc); +void __page_frag_cache_drain(struct page *page, unsigned int count); +void *__page_frag_alloc_align(struct page_frag_cache *nc, unsigned int fragsz, + gfp_t gfp_mask, unsigned int align_mask); + +static inline void *page_frag_alloc_align(struct page_frag_cache *nc, + unsigned int fragsz, gfp_t gfp_mask, + unsigned int align) +{ + WARN_ON_ONCE(!is_power_of_2(align)); + return __page_frag_alloc_align(nc, fragsz, gfp_mask, -align); +} + +static inline void *page_frag_alloc(struct page_frag_cache *nc, + unsigned int fragsz, gfp_t gfp_mask) +{ + return __page_frag_alloc_align(nc, fragsz, gfp_mask, ~0u); +} + +void page_frag_free(void *addr); + +#endif diff --git a/include/linux/page_idle.h b/include/linux/page_idle.h index d8f344840643..89ca0d5dc1e7 100644 --- a/include/linux/page_idle.h +++ b/include/linux/page_idle.h @@ -6,14 +6,12 @@ #include <linux/page-flags.h> #include <linux/page_ext.h> -#ifdef CONFIG_PAGE_IDLE_FLAG - -#ifndef CONFIG_64BIT +#if defined(CONFIG_PAGE_IDLE_FLAG) && !defined(CONFIG_64BIT) /* * If there is not enough space to store Idle and Young bits in page flags, use * page ext flags instead. */ -static inline bool folio_test_young(struct folio *folio) +static inline bool folio_test_young(const struct folio *folio) { struct page_ext *page_ext = page_ext_get(&folio->page); bool page_young; @@ -52,7 +50,7 @@ static inline bool folio_test_clear_young(struct folio *folio) return page_young; } -static inline bool folio_test_idle(struct folio *folio) +static inline bool folio_test_idle(const struct folio *folio) { struct page_ext *page_ext = page_ext_get(&folio->page); bool page_idle; @@ -60,7 +58,7 @@ static inline bool folio_test_idle(struct folio *folio) if (unlikely(!page_ext)) return false; - page_idle = test_bit(PAGE_EXT_IDLE, &page_ext->flags); + page_idle = test_bit(PAGE_EXT_IDLE, &page_ext->flags); page_ext_put(page_ext); return page_idle; @@ -87,61 +85,5 @@ static inline void folio_clear_idle(struct folio *folio) clear_bit(PAGE_EXT_IDLE, &page_ext->flags); page_ext_put(page_ext); } -#endif /* !CONFIG_64BIT */ - -#else /* !CONFIG_PAGE_IDLE_FLAG */ - -static inline bool folio_test_young(struct folio *folio) -{ - return false; -} - -static inline void folio_set_young(struct folio *folio) -{ -} - -static inline bool folio_test_clear_young(struct folio *folio) -{ - return false; -} - -static inline bool folio_test_idle(struct folio *folio) -{ - return false; -} - -static inline void folio_set_idle(struct folio *folio) -{ -} - -static inline void folio_clear_idle(struct folio *folio) -{ -} - -#endif /* CONFIG_PAGE_IDLE_FLAG */ - -static inline bool page_is_young(struct page *page) -{ - return folio_test_young(page_folio(page)); -} - -static inline void set_page_young(struct page *page) -{ - folio_set_young(page_folio(page)); -} - -static inline bool test_and_clear_page_young(struct page *page) -{ - return folio_test_clear_young(page_folio(page)); -} - -static inline bool page_is_idle(struct page *page) -{ - return folio_test_idle(page_folio(page)); -} - -static inline void set_page_idle(struct page *page) -{ - folio_set_idle(page_folio(page)); -} +#endif /* CONFIG_PAGE_IDLE_FLAG && !64BIT */ #endif /* _LINUX_MM_PAGE_IDLE_H */ diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h index d7c2d33baa7f..8c236c651d1d 100644 --- a/include/linux/page_ref.h +++ b/include/linux/page_ref.h @@ -139,20 +139,15 @@ static inline void folio_ref_sub(struct folio *folio, int nr) page_ref_sub(&folio->page, nr); } -static inline int page_ref_sub_return(struct page *page, int nr) +static inline int folio_ref_sub_return(struct folio *folio, int nr) { - int ret = atomic_sub_return(nr, &page->_refcount); + int ret = atomic_sub_return(nr, &folio->_refcount); if (page_ref_tracepoint_active(page_ref_mod_and_return)) - __page_ref_mod_and_return(page, -nr, ret); + __page_ref_mod_and_return(&folio->page, -nr, ret); return ret; } -static inline int folio_ref_sub_return(struct folio *folio, int nr) -{ - return page_ref_sub_return(&folio->page, nr); -} - static inline void page_ref_inc(struct page *page) { atomic_inc(&page->_refcount); @@ -235,7 +230,13 @@ static inline int folio_ref_dec_return(struct folio *folio) static inline bool page_ref_add_unless(struct page *page, int nr, int u) { - bool ret = atomic_add_unless(&page->_refcount, nr, u); + bool ret = false; + + rcu_read_lock(); + /* avoid writing to the vmemmap area being remapped */ + if (!page_is_fake_head(page) && page_ref_count(page) != u) + ret = atomic_add_unless(&page->_refcount, nr, u); + rcu_read_unlock(); if (page_ref_tracepoint_active(page_ref_mod_unless)) __page_ref_mod_unless(page, nr, ret); @@ -263,54 +264,9 @@ static inline bool folio_try_get(struct folio *folio) return folio_ref_add_unless(folio, 1, 0); } -static inline bool folio_ref_try_add_rcu(struct folio *folio, int count) -{ -#ifdef CONFIG_TINY_RCU - /* - * The caller guarantees the folio will not be freed from interrupt - * context, so (on !SMP) we only need preemption to be disabled - * and TINY_RCU does that for us. - */ -# ifdef CONFIG_PREEMPT_COUNT - VM_BUG_ON(!in_atomic() && !irqs_disabled()); -# endif - VM_BUG_ON_FOLIO(folio_ref_count(folio) == 0, folio); - folio_ref_add(folio, count); -#else - if (unlikely(!folio_ref_add_unless(folio, count, 0))) { - /* Either the folio has been freed, or will be freed. */ - return false; - } -#endif - return true; -} - -/** - * folio_try_get_rcu - Attempt to increase the refcount on a folio. - * @folio: The folio. - * - * This is a version of folio_try_get() optimised for non-SMP kernels. - * If you are still holding the rcu_read_lock() after looking up the - * page and know that the page cannot have its refcount decreased to - * zero in interrupt context, you can use this instead of folio_try_get(). - * - * Example users include get_user_pages_fast() (as pages are not unmapped - * from interrupt context) and the page cache lookups (as pages are not - * truncated from interrupt context). We also know that pages are not - * frozen in interrupt context for the purposes of splitting or migration. - * - * You can also use this function if you're holding a lock that prevents - * pages being frozen & removed; eg the i_pages lock for the page cache - * or the mmap_lock or page table lock for page tables. In this case, - * it will always succeed, and you could have used a plain folio_get(), - * but it's sometimes more convenient to have a common function called - * from both locked and RCU-protected contexts. - * - * Return: True if the reference count was successfully incremented. - */ -static inline bool folio_try_get_rcu(struct folio *folio) +static inline bool folio_ref_try_add(struct folio *folio, int count) { - return folio_ref_try_add_rcu(folio, 1); + return folio_ref_add_unless(folio, count, 0); } static inline int page_ref_freeze(struct page *page, int count) diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h index 3f2409b968ec..fc6b9c87cb0a 100644 --- a/include/linux/pageblock-flags.h +++ b/include/linux/pageblock-flags.h @@ -28,7 +28,7 @@ enum pageblock_bits { NR_PAGEBLOCK_BITS }; -#ifdef CONFIG_HUGETLB_PAGE +#if defined(CONFIG_HUGETLB_PAGE) #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE @@ -41,11 +41,15 @@ extern unsigned int pageblock_order; * Huge pages are a constant size, but don't exceed the maximum allocation * granularity. */ -#define pageblock_order min_t(unsigned int, HUGETLB_PAGE_ORDER, MAX_PAGE_ORDER) +#define pageblock_order MIN_T(unsigned int, HUGETLB_PAGE_ORDER, MAX_PAGE_ORDER) #endif /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */ -#else /* CONFIG_HUGETLB_PAGE */ +#elif defined(CONFIG_TRANSPARENT_HUGEPAGE) + +#define pageblock_order MIN_T(unsigned int, HPAGE_PMD_ORDER, MAX_PAGE_ORDER) + +#else /* CONFIG_TRANSPARENT_HUGEPAGE */ /* If huge pages are not used, group by MAX_ORDER_NR_PAGES */ #define pageblock_order MAX_PAGE_ORDER diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 2df35e65557d..47bfc6b1b632 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -32,6 +32,8 @@ int invalidate_inode_pages2_range(struct address_space *mapping, pgoff_t start, pgoff_t end); int kiocb_invalidate_pages(struct kiocb *iocb, size_t count); void kiocb_invalidate_post_direct_write(struct kiocb *iocb, size_t count); +int filemap_invalidate_pages(struct address_space *mapping, + loff_t pos, loff_t end, bool nowait); int write_inode_now(struct inode *, int sync); int filemap_fdatawrite(struct address_space *); @@ -40,6 +42,8 @@ int filemap_fdatawait_keep_errors(struct address_space *mapping); int filemap_fdatawait_range(struct address_space *, loff_t lstart, loff_t lend); int filemap_fdatawait_range_keep_errors(struct address_space *mapping, loff_t start_byte, loff_t end_byte); +int filemap_invalidate_inode(struct inode *inode, bool flush, + loff_t start, loff_t end); static inline int filemap_fdatawait(struct address_space *mapping) { @@ -202,13 +206,21 @@ enum mapping_flags { AS_EXITING = 4, /* final truncate in progress */ /* writeback related tags are not used */ AS_NO_WRITEBACK_TAGS = 5, - AS_LARGE_FOLIO_SUPPORT = 6, - AS_RELEASE_ALWAYS, /* Call ->release_folio(), even if no private data */ - AS_STABLE_WRITES, /* must wait for writeback before modifying + AS_RELEASE_ALWAYS = 6, /* Call ->release_folio(), even if no private data */ + AS_STABLE_WRITES = 7, /* must wait for writeback before modifying folio contents */ - AS_UNMOVABLE, /* The mapping cannot be moved, ever */ + AS_INACCESSIBLE = 8, /* Do not attempt direct R/W access to the mapping */ + /* Bits 16-25 are used for FOLIO_ORDER */ + AS_FOLIO_ORDER_BITS = 5, + AS_FOLIO_ORDER_MIN = 16, + AS_FOLIO_ORDER_MAX = AS_FOLIO_ORDER_MIN + AS_FOLIO_ORDER_BITS, }; +#define AS_FOLIO_ORDER_BITS_MASK ((1u << AS_FOLIO_ORDER_BITS) - 1) +#define AS_FOLIO_ORDER_MIN_MASK (AS_FOLIO_ORDER_BITS_MASK << AS_FOLIO_ORDER_MIN) +#define AS_FOLIO_ORDER_MAX_MASK (AS_FOLIO_ORDER_BITS_MASK << AS_FOLIO_ORDER_MAX) +#define AS_FOLIO_ORDER_MASK (AS_FOLIO_ORDER_MIN_MASK | AS_FOLIO_ORDER_MAX_MASK) + /** * mapping_set_error - record a writeback error in the address_space * @mapping: the mapping in which an error should be set @@ -307,20 +319,20 @@ static inline void mapping_clear_stable_writes(struct address_space *mapping) clear_bit(AS_STABLE_WRITES, &mapping->flags); } -static inline void mapping_set_unmovable(struct address_space *mapping) +static inline void mapping_set_inaccessible(struct address_space *mapping) { /* - * It's expected unmovable mappings are also unevictable. Compaction + * It's expected inaccessible mappings are also unevictable. Compaction * migrate scanner (isolate_migratepages_block()) relies on this to * reduce page locking. */ set_bit(AS_UNEVICTABLE, &mapping->flags); - set_bit(AS_UNMOVABLE, &mapping->flags); + set_bit(AS_INACCESSIBLE, &mapping->flags); } -static inline bool mapping_unmovable(struct address_space *mapping) +static inline bool mapping_inaccessible(struct address_space *mapping) { - return test_bit(AS_UNMOVABLE, &mapping->flags); + return test_bit(AS_INACCESSIBLE, &mapping->flags); } static inline gfp_t mapping_gfp_mask(struct address_space * mapping) @@ -344,9 +356,84 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) m->gfp_mask = mask; } +/* + * There are some parts of the kernel which assume that PMD entries + * are exactly HPAGE_PMD_ORDER. Those should be fixed, but until then, + * limit the maximum allocation order to PMD size. I'm not aware of any + * assumptions about maximum order if THP are disabled, but 8 seems like + * a good order (that's 1MB if you're using 4kB pages) + */ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#define PREFERRED_MAX_PAGECACHE_ORDER HPAGE_PMD_ORDER +#else +#define PREFERRED_MAX_PAGECACHE_ORDER 8 +#endif + +/* + * xas_split_alloc() does not support arbitrary orders. This implies no + * 512MB THP on ARM64 with 64KB base page size. + */ +#define MAX_XAS_ORDER (XA_CHUNK_SHIFT * 2 - 1) +#define MAX_PAGECACHE_ORDER min(MAX_XAS_ORDER, PREFERRED_MAX_PAGECACHE_ORDER) + +/* + * mapping_max_folio_size_supported() - Check the max folio size supported + * + * The filesystem should call this function at mount time if there is a + * requirement on the folio mapping size in the page cache. + */ +static inline size_t mapping_max_folio_size_supported(void) +{ + if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) + return 1U << (PAGE_SHIFT + MAX_PAGECACHE_ORDER); + return PAGE_SIZE; +} + +/* + * mapping_set_folio_order_range() - Set the orders supported by a file. + * @mapping: The address space of the file. + * @min: Minimum folio order (between 0-MAX_PAGECACHE_ORDER inclusive). + * @max: Maximum folio order (between @min-MAX_PAGECACHE_ORDER inclusive). + * + * The filesystem should call this function in its inode constructor to + * indicate which base size (min) and maximum size (max) of folio the VFS + * can use to cache the contents of the file. This should only be used + * if the filesystem needs special handling of folio sizes (ie there is + * something the core cannot know). + * Do not tune it based on, eg, i_size. + * + * Context: This should not be called while the inode is active as it + * is non-atomic. + */ +static inline void mapping_set_folio_order_range(struct address_space *mapping, + unsigned int min, + unsigned int max) +{ + if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) + return; + + if (min > MAX_PAGECACHE_ORDER) + min = MAX_PAGECACHE_ORDER; + + if (max > MAX_PAGECACHE_ORDER) + max = MAX_PAGECACHE_ORDER; + + if (max < min) + max = min; + + mapping->flags = (mapping->flags & ~AS_FOLIO_ORDER_MASK) | + (min << AS_FOLIO_ORDER_MIN) | (max << AS_FOLIO_ORDER_MAX); +} + +static inline void mapping_set_folio_min_order(struct address_space *mapping, + unsigned int min) +{ + mapping_set_folio_order_range(mapping, min, MAX_PAGECACHE_ORDER); +} + /** * mapping_set_large_folios() - Indicate the file supports large folios. - * @mapping: The file. + * @mapping: The address space of the file. * * The filesystem should call this function in its inode constructor to * indicate that the VFS can use large folios to cache the contents of @@ -357,7 +444,44 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) */ static inline void mapping_set_large_folios(struct address_space *mapping) { - __set_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags); + mapping_set_folio_order_range(mapping, 0, MAX_PAGECACHE_ORDER); +} + +static inline unsigned int +mapping_max_folio_order(const struct address_space *mapping) +{ + if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) + return 0; + return (mapping->flags & AS_FOLIO_ORDER_MAX_MASK) >> AS_FOLIO_ORDER_MAX; +} + +static inline unsigned int +mapping_min_folio_order(const struct address_space *mapping) +{ + if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) + return 0; + return (mapping->flags & AS_FOLIO_ORDER_MIN_MASK) >> AS_FOLIO_ORDER_MIN; +} + +static inline unsigned long +mapping_min_folio_nrpages(struct address_space *mapping) +{ + return 1UL << mapping_min_folio_order(mapping); +} + +/** + * mapping_align_index() - Align index for this mapping. + * @mapping: The address_space. + * @index: The page index. + * + * The index of a folio must be naturally aligned. If you are adding a + * new folio to the page cache and need to know what index to give it, + * call this function. + */ +static inline pgoff_t mapping_align_index(struct address_space *mapping, + pgoff_t index) +{ + return round_down(index, mapping_min_folio_nrpages(mapping)); } /* @@ -366,8 +490,17 @@ static inline void mapping_set_large_folios(struct address_space *mapping) */ static inline bool mapping_large_folio_support(struct address_space *mapping) { - return IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && - test_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags); + /* AS_FOLIO_ORDER is only reasonable for pagecache folios */ + VM_WARN_ONCE((unsigned long)mapping & PAGE_MAPPING_ANON, + "Anonymous mapping always supports large folio"); + + return mapping_max_folio_order(mapping) > 0; +} + +/* Return the maximum folio size for this pagecache mapping, in bytes. */ +static inline size_t mapping_max_folio_size(const struct address_space *mapping) +{ + return PAGE_SIZE << mapping_max_folio_order(mapping); } static inline int filemap_nr_thps(struct address_space *mapping) @@ -399,7 +532,6 @@ static inline void filemap_nr_thps_dec(struct address_space *mapping) #endif } -struct address_space *page_mapping(struct page *); struct address_space *folio_mapping(struct folio *); struct address_space *swapcache_mapping(struct folio *); @@ -528,38 +660,23 @@ static inline void *detach_page_private(struct page *page) return folio_detach_private(page_folio(page)); } -/* - * There are some parts of the kernel which assume that PMD entries - * are exactly HPAGE_PMD_ORDER. Those should be fixed, but until then, - * limit the maximum allocation order to PMD size. I'm not aware of any - * assumptions about maximum order if THP are disabled, but 8 seems like - * a good order (that's 1MB if you're using 4kB pages) - */ -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -#define MAX_PAGECACHE_ORDER HPAGE_PMD_ORDER -#else -#define MAX_PAGECACHE_ORDER 8 -#endif - #ifdef CONFIG_NUMA -struct folio *filemap_alloc_folio(gfp_t gfp, unsigned int order); +struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order); #else -static inline struct folio *filemap_alloc_folio(gfp_t gfp, unsigned int order) +static inline struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order) { - return folio_alloc(gfp, order); + return folio_alloc_noprof(gfp, order); } #endif +#define filemap_alloc_folio(...) \ + alloc_hooks(filemap_alloc_folio_noprof(__VA_ARGS__)) + static inline struct page *__page_cache_alloc(gfp_t gfp) { return &filemap_alloc_folio(gfp, 0)->page; } -static inline struct page *page_cache_alloc(struct address_space *x) -{ - return __page_cache_alloc(mapping_gfp_mask(x)); -} - static inline gfp_t readahead_gfp_mask(struct address_space *x) { return mapping_gfp_mask(x) | __GFP_NORETRY | __GFP_NOWARN; @@ -593,6 +710,7 @@ pgoff_t page_cache_prev_miss(struct address_space *mapping, * * %FGP_NOFS - __GFP_FS will get cleared in gfp. * * %FGP_NOWAIT - Don't block on the folio lock. * * %FGP_STABLE - Wait for the folio to be stable (finished writeback) + * * %FGP_DONTCACHE - Uncached buffered IO * * %FGP_WRITEBEGIN - The flags to use in a filesystem write_begin() * implementation. */ @@ -606,10 +724,21 @@ typedef unsigned int __bitwise fgf_t; #define FGP_NOWAIT ((__force fgf_t)0x00000020) #define FGP_FOR_MMAP ((__force fgf_t)0x00000040) #define FGP_STABLE ((__force fgf_t)0x00000080) +#define FGP_DONTCACHE ((__force fgf_t)0x00000100) #define FGF_GET_ORDER(fgf) (((__force unsigned)fgf) >> 26) /* top 6 bits */ #define FGP_WRITEBEGIN (FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE) +static inline unsigned int filemap_get_order(size_t size) +{ + unsigned int shift = ilog2(size); + + if (shift <= PAGE_SHIFT) + return 0; + + return shift - PAGE_SHIFT; +} + /** * fgf_set_order - Encode a length in the fgf_t flags. * @size: The suggested size of the folio to create. @@ -623,11 +752,11 @@ typedef unsigned int __bitwise fgf_t; */ static inline fgf_t fgf_set_order(size_t size) { - unsigned int shift = ilog2(size); + unsigned int order = filemap_get_order(size); - if (shift <= PAGE_SHIFT) + if (!order) return 0; - return (__force fgf_t)((shift - PAGE_SHIFT) << 26); + return (__force fgf_t)(order << 26); } void *filemap_get_entry(struct address_space *mapping, pgoff_t index); @@ -780,7 +909,7 @@ static inline struct page *grab_cache_page_nowait(struct address_space *mapping, mapping_gfp_mask(mapping)); } -#define swapcache_index(folio) __page_file_index(&(folio)->page) +extern pgoff_t __folio_swap_cache_index(struct folio *folio); /** * folio_index - File index of a folio. @@ -795,9 +924,9 @@ static inline struct page *grab_cache_page_nowait(struct address_space *mapping, */ static inline pgoff_t folio_index(struct folio *folio) { - if (unlikely(folio_test_swapcache(folio))) - return swapcache_index(folio); - return folio->index; + if (unlikely(folio_test_swapcache(folio))) + return __folio_swap_cache_index(folio); + return folio->index; } /** @@ -894,22 +1023,25 @@ static inline struct folio *read_mapping_folio(struct address_space *mapping, return read_cache_folio(mapping, index, NULL, file); } -/* - * Get the offset in PAGE_SIZE (even for hugetlb pages). +/** + * page_pgoff - Calculate the logical page offset of this page. + * @folio: The folio containing this page. + * @page: The page which we need the offset of. + * + * For file pages, this is the offset from the beginning of the file + * in units of PAGE_SIZE. For anonymous pages, this is the offset from + * the beginning of the anon_vma in units of PAGE_SIZE. This will + * return nonsense for KSM pages. + * + * Context: Caller must have a reference on the folio or otherwise + * prevent it from being split or freed. + * + * Return: The offset in units of PAGE_SIZE. */ -static inline pgoff_t page_to_pgoff(struct page *page) +static inline pgoff_t page_pgoff(const struct folio *folio, + const struct page *page) { - struct page *head; - - if (likely(!PageTransTail(page))) - return page->index; - - head = compound_head(page); - /* - * We don't initialize ->index for tail pages: calculate based on - * head page - */ - return head->index + page - head; + return folio->index + folio_page_idx(folio, page); } /* @@ -920,11 +1052,6 @@ static inline loff_t page_offset(struct page *page) return ((loff_t)page->index) << PAGE_SHIFT; } -static inline loff_t page_file_offset(struct page *page) -{ - return ((loff_t)page_index(page)) << PAGE_SHIFT; -} - /** * folio_pos - Returns the byte position of this folio in its file. * @folio: The folio. @@ -934,18 +1061,6 @@ static inline loff_t folio_pos(struct folio *folio) return page_offset(&folio->page); } -/** - * folio_file_pos - Returns the byte position of this folio in its file. - * @folio: The folio. - * - * This differs from folio_pos() for folios which belong to a swap file. - * NFS is the only filesystem today which needs to use folio_file_pos(). - */ -static inline loff_t folio_file_pos(struct folio *folio) -{ - return page_file_offset(&folio->page); -} - /* * Get the offset in PAGE_SIZE (even for hugetlb folios). */ @@ -1014,7 +1129,7 @@ static inline bool folio_trylock(struct folio *folio) /* * Return true if the page was successfully locked */ -static inline int trylock_page(struct page *page) +static inline bool trylock_page(struct page *page) { return folio_trylock(page_folio(page)); } @@ -1144,11 +1259,6 @@ void folio_end_writeback(struct folio *folio); void wait_for_stable_page(struct page *page); void folio_wait_stable(struct folio *folio); void __folio_mark_dirty(struct folio *folio, struct address_space *, int warn); -static inline void __set_page_dirty(struct page *page, - struct address_space *mapping, int warn) -{ - __folio_mark_dirty(page_folio(page), mapping, warn); -} void folio_account_cleaned(struct folio *folio, struct bdi_writeback *wb); void __folio_cancel_dirty(struct folio *folio); static inline void folio_cancel_dirty(struct folio *folio) @@ -1160,7 +1270,6 @@ static inline void folio_cancel_dirty(struct folio *folio) bool folio_clear_dirty_for_io(struct folio *folio); bool clear_page_dirty_for_io(struct page *page); void folio_invalidate(struct folio *folio, size_t offset, size_t length); -int __set_page_dirty_nobuffers(struct page *page); bool noop_dirty_folio(struct address_space *mapping, struct folio *folio); #ifdef CONFIG_MIGRATION @@ -1174,11 +1283,6 @@ void folio_wait_private_2(struct folio *folio); int folio_wait_private_2_killable(struct folio *folio); /* - * Add an arbitrary waiter to a page's wait queue - */ -void folio_add_wait_queue(struct folio *folio, wait_queue_entry_t *waiter); - -/* * Fault in userspace address range. */ size_t fault_in_writeable(char __user *uaddr, size_t size); @@ -1256,6 +1360,7 @@ struct readahead_control { pgoff_t _index; unsigned int _nr_pages; unsigned int _batch_count; + bool dropbehind; bool _workingset; unsigned long _pflags; }; @@ -1305,8 +1410,7 @@ void page_cache_sync_readahead(struct address_space *mapping, * @mapping: address_space which holds the pagecache and I/O vectors * @ra: file_ra_state which holds the readahead state * @file: Used by the filesystem for authentication. - * @folio: The folio at @index which triggered the readahead call. - * @index: Index of first page to be read. + * @folio: The folio which triggered the readahead call. * @req_count: Total number of pages being read by the caller. * * page_cache_async_readahead() should be called when a page is used which @@ -1317,9 +1421,9 @@ void page_cache_sync_readahead(struct address_space *mapping, static inline void page_cache_async_readahead(struct address_space *mapping, struct file_ra_state *ra, struct file *file, - struct folio *folio, pgoff_t index, unsigned long req_count) + struct folio *folio, unsigned long req_count) { - DEFINE_READAHEAD(ractl, file, ra, mapping, index); + DEFINE_READAHEAD(ractl, file, ra, mapping, folio->index); page_cache_async_ra(&ractl, folio, req_count); } @@ -1542,10 +1646,4 @@ unsigned int i_blocks_per_folio(struct inode *inode, struct folio *folio) { return folio_size(folio) >> inode->i_blkbits; } - -static inline -unsigned int i_blocks_per_page(struct inode *inode, struct page *page) -{ - return i_blocks_per_folio(inode, page_folio(page)); -} #endif /* _LINUX_PAGEMAP_H */ diff --git a/include/linux/pagewalk.h b/include/linux/pagewalk.h index 27cd1e59ccf7..9700a29f8afb 100644 --- a/include/linux/pagewalk.h +++ b/include/linux/pagewalk.h @@ -25,12 +25,15 @@ enum page_walk_lock { * this handler is required to be able to handle * pmd_trans_huge() pmds. They may simply choose to * split_huge_page() instead of handling it explicitly. - * @pte_entry: if set, called for each PTE (lowest-level) entry, - * including empty ones + * @pte_entry: if set, called for each PTE (lowest-level) entry + * including empty ones, except if @install_pte is set. + * If @install_pte is set, @pte_entry is called only for + * existing PTEs. * @pte_hole: if set, called for each hole at all levels, * 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. + * are skipped. If @install_pte is specified, this will + * not trigger for any populated ranges. * @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 @@ -51,6 +54,13 @@ enum page_walk_lock { * @pre_vma: if set, called before starting walk on a non-null vma. * @post_vma: if set, called after a walk on a non-null vma, provided * that @pre_vma and the vma walk succeeded. + * @install_pte: if set, missing page table entries are installed and + * thus all levels are always walked in the specified + * range. This callback is then invoked at the PTE level + * (having split any THP pages prior), providing the PTE to + * install. If allocations fail, the walk is aborted. This + * operation is only available for userland memory. Not + * usable for hugetlb ranges. * * p?d_entry callbacks are called even if those levels are folded on a * particular architecture/configuration. @@ -76,6 +86,8 @@ struct mm_walk_ops { int (*pre_vma)(unsigned long start, unsigned long end, struct mm_walk *walk); void (*post_vma)(struct mm_walk *walk); + int (*install_pte)(unsigned long addr, unsigned long next, + pte_t *ptep, struct mm_walk *walk); enum page_walk_lock walk_lock; }; @@ -130,4 +142,62 @@ int walk_page_mapping(struct address_space *mapping, pgoff_t first_index, pgoff_t nr, const struct mm_walk_ops *ops, void *private); +typedef int __bitwise folio_walk_flags_t; + +/* + * Walk migration entries as well. Careful: a large folio might get split + * concurrently. + */ +#define FW_MIGRATION ((__force folio_walk_flags_t)BIT(0)) + +/* Walk shared zeropages (small + huge) as well. */ +#define FW_ZEROPAGE ((__force folio_walk_flags_t)BIT(1)) + +enum folio_walk_level { + FW_LEVEL_PTE, + FW_LEVEL_PMD, + FW_LEVEL_PUD, +}; + +/** + * struct folio_walk - folio_walk_start() / folio_walk_end() data + * @page: exact folio page referenced (if applicable) + * @level: page table level identifying the entry type + * @pte: pointer to the page table entry (FW_LEVEL_PTE). + * @pmd: pointer to the page table entry (FW_LEVEL_PMD). + * @pud: pointer to the page table entry (FW_LEVEL_PUD). + * @ptl: pointer to the page table lock. + * + * (see folio_walk_start() documentation for more details) + */ +struct folio_walk { + /* public */ + struct page *page; + enum folio_walk_level level; + union { + pte_t *ptep; + pud_t *pudp; + pmd_t *pmdp; + }; + union { + pte_t pte; + pud_t pud; + pmd_t pmd; + }; + /* private */ + struct vm_area_struct *vma; + spinlock_t *ptl; +}; + +struct folio *folio_walk_start(struct folio_walk *fw, + struct vm_area_struct *vma, unsigned long addr, + folio_walk_flags_t flags); + +#define folio_walk_end(__fw, __vma) do { \ + spin_unlock((__fw)->ptl); \ + if (likely((__fw)->level == FW_LEVEL_PTE)) \ + pte_unmap((__fw)->ptep); \ + vma_pgtable_walk_end(__vma); \ +} while (0) + #endif /* _LINUX_PAGEWALK_H */ diff --git a/include/linux/panic.h b/include/linux/panic.h index 6717b15e798c..54d90b6c5f47 100644 --- a/include/linux/panic.h +++ b/include/linux/panic.h @@ -16,6 +16,7 @@ extern void oops_enter(void); extern void oops_exit(void); extern bool oops_may_print(void); +extern bool panic_triggering_all_cpu_backtrace; extern int panic_timeout; extern unsigned long panic_print; extern int panic_on_oops; @@ -77,9 +78,10 @@ static inline void set_arch_panic_timeout(int timeout, int arch_default_timeout) #define TAINT_FLAGS_MAX ((1UL << TAINT_FLAGS_COUNT) - 1) struct taint_flag { - char c_true; /* character printed when tainted */ - char c_false; /* character printed when not tainted */ - bool module; /* also show as a per-module taint flag */ + char c_true; /* character printed when tainted */ + char c_false; /* character printed when not tainted */ + bool module; /* also show as a per-module taint flag */ + const char *desc; /* verbose description of the set taint flag */ }; extern const struct taint_flag taint_flags[TAINT_FLAGS_COUNT]; @@ -90,6 +92,7 @@ enum lockdep_ok { }; extern const char *print_tainted(void); +extern const char *print_tainted_verbose(void); extern void add_taint(unsigned flag, enum lockdep_ok); extern int test_taint(unsigned flag); extern unsigned long get_taint(void); diff --git a/include/linux/papr_scm.h b/include/linux/papr_scm.h new file mode 100644 index 000000000000..eb36453813db --- /dev/null +++ b/include/linux/papr_scm.h @@ -0,0 +1,49 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef __LINUX_PAPR_SCM_H +#define __LINUX_PAPR_SCM_H + +/* DIMM health bitmap indicators */ +/* SCM device is unable to persist memory contents */ +#define PAPR_PMEM_UNARMED (1ULL << (63 - 0)) +/* SCM device failed to persist memory contents */ +#define PAPR_PMEM_SHUTDOWN_DIRTY (1ULL << (63 - 1)) +/* SCM device contents are persisted from previous IPL */ +#define PAPR_PMEM_SHUTDOWN_CLEAN (1ULL << (63 - 2)) +/* SCM device contents are not persisted from previous IPL */ +#define PAPR_PMEM_EMPTY (1ULL << (63 - 3)) +/* SCM device memory life remaining is critically low */ +#define PAPR_PMEM_HEALTH_CRITICAL (1ULL << (63 - 4)) +/* SCM device will be garded off next IPL due to failure */ +#define PAPR_PMEM_HEALTH_FATAL (1ULL << (63 - 5)) +/* SCM contents cannot persist due to current platform health status */ +#define PAPR_PMEM_HEALTH_UNHEALTHY (1ULL << (63 - 6)) +/* SCM device is unable to persist memory contents in certain conditions */ +#define PAPR_PMEM_HEALTH_NON_CRITICAL (1ULL << (63 - 7)) +/* SCM device is encrypted */ +#define PAPR_PMEM_ENCRYPTED (1ULL << (63 - 8)) +/* SCM device has been scrubbed and locked */ +#define PAPR_PMEM_SCRUBBED_AND_LOCKED (1ULL << (63 - 9)) + +#define PAPR_PMEM_SAVE_FAILED (1ULL << (63 - 10)) + +/* Bits status indicators for health bitmap indicating unarmed dimm */ +#define PAPR_PMEM_UNARMED_MASK (PAPR_PMEM_UNARMED | \ + PAPR_PMEM_HEALTH_UNHEALTHY) + +/* Bits status indicators for health bitmap indicating unflushed dimm */ +#define PAPR_PMEM_BAD_SHUTDOWN_MASK (PAPR_PMEM_SHUTDOWN_DIRTY) + +/* Bits status indicators for health bitmap indicating unrestored dimm */ +#define PAPR_PMEM_BAD_RESTORE_MASK (PAPR_PMEM_EMPTY) + +/* Bit status indicators for smart event notification */ +#define PAPR_PMEM_SMART_EVENT_MASK (PAPR_PMEM_HEALTH_CRITICAL | \ + PAPR_PMEM_HEALTH_FATAL | \ + PAPR_PMEM_HEALTH_UNHEALTHY) + +#define PAPR_PMEM_SAVE_MASK (PAPR_PMEM_SAVE_FAILED) + +#define PAPR_SCM_PERF_STATS_EYECATCHER __stringify(SCMSTATS) +#define PAPR_SCM_PERF_STATS_VERSION 0x1 + +#endif /* __LINUX_PAPR_SCM_H */ diff --git a/include/linux/parport.h b/include/linux/parport.h index fff39bc30629..464c2ad28039 100644 --- a/include/linux/parport.h +++ b/include/linux/parport.h @@ -252,13 +252,10 @@ struct parport { struct parport_driver { const char *name; - void (*attach) (struct parport *); void (*detach) (struct parport *); void (*match_port)(struct parport *); int (*probe)(struct pardevice *); struct device_driver driver; - bool devmodel; - struct list_head list; }; #define to_parport_driver(n) container_of(n, struct parport_driver, driver) @@ -301,9 +298,6 @@ int __must_check __parport_register_driver(struct parport_driver *, * to receive notifications about ports being found in the * system, as well as ports no longer available. * - * If devmodel is true then the new device model is used - * for registration. - * * The @driver structure is allocated by the caller and must not be * deallocated until after calling parport_unregister_driver(). * diff --git a/include/linux/part_stat.h b/include/linux/part_stat.h index abeba356bc3f..ac8c44dd8237 100644 --- a/include/linux/part_stat.h +++ b/include/linux/part_stat.h @@ -59,7 +59,7 @@ static inline void part_stat_set_all(struct block_device *part, int value) #define part_stat_add(part, field, addnd) do { \ __part_stat_add((part), field, addnd); \ - if ((part)->bd_partno) \ + if (bdev_is_partition(part)) \ __part_stat_add(bdev_whole(part), field, addnd); \ } while (0) diff --git a/include/linux/path.h b/include/linux/path.h index 475225a03d0d..7ea389dc764b 100644 --- a/include/linux/path.h +++ b/include/linux/path.h @@ -18,10 +18,13 @@ static inline int path_equal(const struct path *path1, const struct path *path2) return path1->mnt == path2->mnt && path1->dentry == path2->dentry; } -static inline void path_put_init(struct path *path) -{ - path_put(path); - *path = (struct path) { }; -} +/* + * Cleanup macro for use with __free(path_put). Avoids dereference and + * copying @path unlike DEFINE_FREE(). path_put() will handle the empty + * path correctly just ensure @path is initialized: + * + * struct path path __free(path_put) = {}; + */ +#define __free_path_put path_put #endif /* _LINUX_PATH_H */ diff --git a/include/linux/pci-ats.h b/include/linux/pci-ats.h index df54cd5b15db..0e8b74e63767 100644 --- a/include/linux/pci-ats.h +++ b/include/linux/pci-ats.h @@ -8,6 +8,7 @@ /* Address Translation Service */ bool pci_ats_supported(struct pci_dev *dev); int pci_enable_ats(struct pci_dev *dev, int ps); +int pci_prepare_ats(struct pci_dev *dev, int ps); void pci_disable_ats(struct pci_dev *dev); int pci_ats_queue_depth(struct pci_dev *dev); int pci_ats_page_aligned(struct pci_dev *dev); @@ -16,6 +17,8 @@ static inline bool pci_ats_supported(struct pci_dev *d) { return false; } static inline int pci_enable_ats(struct pci_dev *d, int ps) { return -ENODEV; } +static inline int pci_prepare_ats(struct pci_dev *dev, int ps) +{ return -ENODEV; } static inline void pci_disable_ats(struct pci_dev *d) { } static inline int pci_ats_queue_depth(struct pci_dev *d) { return -ENODEV; } diff --git a/include/linux/pci-bwctrl.h b/include/linux/pci-bwctrl.h new file mode 100644 index 000000000000..cee07127455b --- /dev/null +++ b/include/linux/pci-bwctrl.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * PCIe bandwidth controller + * + * Copyright (C) 2023-2024 Intel Corporation + */ + +#ifndef LINUX_PCI_BWCTRL_H +#define LINUX_PCI_BWCTRL_H + +#include <linux/pci.h> + +struct thermal_cooling_device; + +#ifdef CONFIG_PCIE_THERMAL +struct thermal_cooling_device *pcie_cooling_device_register(struct pci_dev *port); +void pcie_cooling_device_unregister(struct thermal_cooling_device *cdev); +#else +static inline struct thermal_cooling_device *pcie_cooling_device_register(struct pci_dev *port) +{ + return NULL; +} +static inline void pcie_cooling_device_unregister(struct thermal_cooling_device *cdev) +{ +} +#endif + +#endif diff --git a/include/linux/pci-ecam.h b/include/linux/pci-ecam.h index 3a4860bd2758..3a10f8cfc3ad 100644 --- a/include/linux/pci-ecam.h +++ b/include/linux/pci-ecam.h @@ -45,6 +45,10 @@ struct pci_ecam_ops { unsigned int bus_shift; struct pci_ops pci_ops; int (*init)(struct pci_config_window *); + int (*enable_device)(struct pci_host_bridge *, + struct pci_dev *); + void (*disable_device)(struct pci_host_bridge *, + struct pci_dev *); }; /* diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h index cc2f70d061c8..e818e3fdcded 100644 --- a/include/linux/pci-epc.h +++ b/include/linux/pci-epc.h @@ -33,10 +33,42 @@ pci_epc_interface_string(enum pci_epc_interface_type type) } /** + * struct pci_epc_map - information about EPC memory for mapping a RC PCI + * address range + * @pci_addr: start address of the RC PCI address range to map + * @pci_size: size of the RC PCI address range mapped from @pci_addr + * @map_pci_addr: RC PCI address used as the first address mapped (may be lower + * than @pci_addr) + * @map_size: size of the controller memory needed for mapping the RC PCI address + * range @map_pci_addr..@pci_addr+@pci_size + * @phys_base: base physical address of the allocated EPC memory for mapping the + * RC PCI address range + * @phys_addr: physical address at which @pci_addr is mapped + * @virt_base: base virtual address of the allocated EPC memory for mapping the + * RC PCI address range + * @virt_addr: virtual address at which @pci_addr is mapped + */ +struct pci_epc_map { + u64 pci_addr; + size_t pci_size; + + u64 map_pci_addr; + size_t map_size; + + phys_addr_t phys_base; + phys_addr_t phys_addr; + void __iomem *virt_base; + void __iomem *virt_addr; +}; + +/** * struct pci_epc_ops - set of function pointers for performing EPC operations * @write_header: ops to populate configuration space header * @set_bar: ops to configure the BAR * @clear_bar: ops to reset the BAR + * @align_addr: operation to get the mapping address, mapping size and offset + * into a controller memory window needed to map an RC PCI address + * region * @map_addr: ops to map CPU address to PCI address * @unmap_addr: ops to unmap CPU address and PCI address * @set_msi: ops to set the requested number of MSI interrupts in the MSI @@ -61,6 +93,8 @@ struct pci_epc_ops { struct pci_epf_bar *epf_bar); void (*clear_bar)(struct pci_epc *epc, u8 func_no, u8 vfunc_no, struct pci_epf_bar *epf_bar); + u64 (*align_addr)(struct pci_epc *epc, u64 pci_addr, size_t *size, + size_t *offset); int (*map_addr)(struct pci_epc *epc, u8 func_no, u8 vfunc_no, phys_addr_t addr, u64 pci_addr, size_t size); void (*unmap_addr)(struct pci_epc *epc, u8 func_no, u8 vfunc_no, @@ -128,6 +162,9 @@ 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 + * @domain_nr: PCI domain number of the endpoint controller + * @init_complete: flag to indicate whether the EPC initialization is complete + * or not */ struct pci_epc { struct device dev; @@ -143,9 +180,12 @@ struct pci_epc { /* mutex to protect against concurrent access of EP controller */ struct mutex lock; unsigned long function_num_map; + int domain_nr; + bool init_complete; }; /** + * enum pci_epc_bar_type - configurability of endpoint BAR * @BAR_PROGRAMMABLE: The BAR mask can be configured by the EPC. * @BAR_FIXED: The BAR mask is fixed by the hardware. * @BAR_RESERVED: The BAR should not be touched by an EPF driver. @@ -179,8 +219,6 @@ struct pci_epc_bar_desc { /** * struct pci_epc_features - features supported by a EPC device per function * @linkup_notifier: indicate if the EPC device can notify EPF driver on link up - * @core_init_notifier: indicate cores that can notify about their availability - * for initialization * @msi_capable: indicate if the endpoint function has MSI capability * @msix_capable: indicate if the endpoint function has MSI-X capability * @bar: array specifying the hardware description for each BAR @@ -188,7 +226,6 @@ struct pci_epc_bar_desc { */ struct pci_epc_features { unsigned int linkup_notifier : 1; - unsigned int core_init_notifier : 1; unsigned int msi_capable : 1; unsigned int msix_capable : 1; struct pci_epc_bar_desc bar[PCI_STD_NUM_BARS]; @@ -197,6 +234,8 @@ struct pci_epc_features { #define to_pci_epc(device) container_of((device), struct pci_epc, dev) +#ifdef CONFIG_PCI_ENDPOINT + #define pci_epc_create(dev, ops) \ __pci_epc_create((dev), (ops), THIS_MODULE) #define devm_pci_epc_create(dev, ops) \ @@ -225,7 +264,9 @@ int pci_epc_add_epf(struct pci_epc *epc, struct pci_epf *epf, void pci_epc_linkup(struct pci_epc *epc); void pci_epc_linkdown(struct pci_epc *epc); void pci_epc_init_notify(struct pci_epc *epc); -void pci_epc_bme_notify(struct pci_epc *epc); +void pci_epc_notify_pending_init(struct pci_epc *epc, struct pci_epf *epf); +void pci_epc_deinit_notify(struct pci_epc *epc); +void pci_epc_bus_master_enable_notify(struct pci_epc *epc); void pci_epc_remove_epf(struct pci_epc *epc, struct pci_epf *epf, enum pci_epc_interface_type type); int pci_epc_write_header(struct pci_epc *epc, u8 func_no, u8 vfunc_no, @@ -271,4 +312,18 @@ void __iomem *pci_epc_mem_alloc_addr(struct pci_epc *epc, phys_addr_t *phys_addr, size_t size); void pci_epc_mem_free_addr(struct pci_epc *epc, phys_addr_t phys_addr, void __iomem *virt_addr, size_t size); +int pci_epc_mem_map(struct pci_epc *epc, u8 func_no, u8 vfunc_no, + u64 pci_addr, size_t pci_size, struct pci_epc_map *map); +void pci_epc_mem_unmap(struct pci_epc *epc, u8 func_no, u8 vfunc_no, + struct pci_epc_map *map); + +#else +static inline void pci_epc_init_notify(struct pci_epc *epc) +{ +} + +static inline void pci_epc_deinit_notify(struct pci_epc *epc) +{ +} +#endif /* CONFIG_PCI_ENDPOINT */ #endif /* __LINUX_PCI_EPC_H */ diff --git a/include/linux/pci-epf.h b/include/linux/pci-epf.h index adee6a1b35db..ee6156bcbbd0 100644 --- a/include/linux/pci-epf.h +++ b/include/linux/pci-epf.h @@ -70,16 +70,18 @@ struct pci_epf_ops { /** * struct pci_epc_event_ops - Callbacks for capturing the EPC events - * @core_init: Callback for the EPC initialization complete event + * @epc_init: Callback for the EPC initialization complete event + * @epc_deinit: Callback for the EPC deinitialization event * @link_up: Callback for the EPC link up event * @link_down: Callback for the EPC link down event - * @bme: Callback for the EPC BME (Bus Master Enable) event + * @bus_master_enable: Callback for the EPC Bus Master Enable event */ struct pci_epc_event_ops { - int (*core_init)(struct pci_epf *epf); + int (*epc_init)(struct pci_epf *epf); + void (*epc_deinit)(struct pci_epf *epf); int (*link_up)(struct pci_epf *epf); int (*link_down)(struct pci_epf *epf); - int (*bme)(struct pci_epf *epf); + int (*bus_master_enable)(struct pci_epf *epf); }; /** @@ -105,8 +107,7 @@ struct pci_epf_driver { const struct pci_epf_device_id *id_table; }; -#define to_pci_epf_driver(drv) (container_of((drv), struct pci_epf_driver, \ - driver)) +#define to_pci_epf_driver(drv) container_of_const((drv), struct pci_epf_driver, driver) /** * struct pci_epf_bar - represents the BAR of EPF device @@ -156,7 +157,7 @@ struct pci_epf { struct device dev; const char *name; struct pci_epf_header *header; - struct pci_epf_bar bar[6]; + struct pci_epf_bar bar[PCI_STD_NUM_BARS]; u8 msi_interrupts; u16 msix_interrupts; u8 func_no; @@ -173,7 +174,7 @@ struct pci_epf { /* Below members are to attach secondary EPC to an endpoint function */ struct pci_epc *sec_epc; struct list_head sec_epc_list; - struct pci_epf_bar sec_epc_bar[6]; + struct pci_epf_bar sec_epc_bar[PCI_STD_NUM_BARS]; u8 sec_epc_func_no; struct config_group *group; unsigned int is_bound; diff --git a/include/linux/pci-pwrctrl.h b/include/linux/pci-pwrctrl.h new file mode 100644 index 000000000000..7d439b0675e9 --- /dev/null +++ b/include/linux/pci-pwrctrl.h @@ -0,0 +1,54 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2024 Linaro Ltd. + */ + +#ifndef __PCI_PWRCTRL_H__ +#define __PCI_PWRCTRL_H__ + +#include <linux/notifier.h> +#include <linux/workqueue.h> + +struct device; +struct device_link; + +/* + * This is a simple framework for solving the issue of PCI devices that require + * certain resources (regulators, GPIOs, clocks) to be enabled before the + * device can actually be detected on the PCI bus. + * + * The idea is to reuse the platform bus to populate OF nodes describing the + * PCI device and its resources, let these platform devices probe and enable + * relevant resources and then trigger a rescan of the PCI bus allowing for the + * same device (with a second associated struct device) to be registered with + * the PCI subsystem. + * + * To preserve a correct hierarchy for PCI power management and device reset, + * we create a device link between the power control platform device (parent) + * and the supplied PCI device (child). + */ + +/** + * struct pci_pwrctrl - PCI device power control context. + * @dev: Address of the power controlling device. + * + * An object of this type must be allocated by the PCI power control device and + * passed to the pwrctrl subsystem to trigger a bus rescan and setup a device + * link with the device once it's up. + */ +struct pci_pwrctrl { + struct device *dev; + + /* Private: don't use. */ + struct notifier_block nb; + struct device_link *link; + struct work_struct work; +}; + +void pci_pwrctrl_init(struct pci_pwrctrl *pwrctrl, struct device *dev); +int pci_pwrctrl_device_set_ready(struct pci_pwrctrl *pwrctrl); +void pci_pwrctrl_device_unset_ready(struct pci_pwrctrl *pwrctrl); +int devm_pci_pwrctrl_device_set_ready(struct device *dev, + struct pci_pwrctrl *pwrctrl); + +#endif /* __PCI_PWRCTRL_H__ */ diff --git a/include/linux/pci-tph.h b/include/linux/pci-tph.h new file mode 100644 index 000000000000..c3e806c13d64 --- /dev/null +++ b/include/linux/pci-tph.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * TPH (TLP Processing Hints) + * + * Copyright (C) 2024 Advanced Micro Devices, Inc. + * Eric Van Tassell <Eric.VanTassell@amd.com> + * Wei Huang <wei.huang2@amd.com> + */ +#ifndef LINUX_PCI_TPH_H +#define LINUX_PCI_TPH_H + +/* + * According to the ECN for PCI Firmware Spec, Steering Tag can be different + * depending on the memory type: Volatile Memory or Persistent Memory. When a + * caller query about a target's Steering Tag, it must provide the target's + * tph_mem_type. ECN link: https://members.pcisig.com/wg/PCI-SIG/document/15470. + */ +enum tph_mem_type { + TPH_MEM_TYPE_VM, /* volatile memory */ + TPH_MEM_TYPE_PM /* persistent memory */ +}; + +#ifdef CONFIG_PCIE_TPH +int pcie_tph_set_st_entry(struct pci_dev *pdev, + unsigned int index, u16 tag); +int pcie_tph_get_cpu_st(struct pci_dev *dev, + enum tph_mem_type mem_type, + unsigned int cpu_uid, u16 *tag); +void pcie_disable_tph(struct pci_dev *pdev); +int pcie_enable_tph(struct pci_dev *pdev, int mode); +#else +static inline int pcie_tph_set_st_entry(struct pci_dev *pdev, + unsigned int index, u16 tag) +{ return -EINVAL; } +static inline int pcie_tph_get_cpu_st(struct pci_dev *dev, + enum tph_mem_type mem_type, + unsigned int cpu_uid, u16 *tag) +{ return -EINVAL; } +static inline void pcie_disable_tph(struct pci_dev *pdev) { } +static inline int pcie_enable_tph(struct pci_dev *pdev, int mode) +{ return -EINVAL; } +#endif + +#endif /* LINUX_PCI_TPH_H */ diff --git a/include/linux/pci.h b/include/linux/pci.h index 16493426a04f..47b31ad724fa 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -51,7 +51,7 @@ PCI_STATUS_PARITY) /* Number of reset methods used in pci_reset_fn_methods array in pci.c */ -#define PCI_NUM_RESET_METHODS 7 +#define PCI_NUM_RESET_METHODS 8 #define PCI_RESET_PROBE true #define PCI_RESET_DO_RESET false @@ -313,12 +313,20 @@ struct pci_vpd { }; struct irq_affinity; +struct pcie_bwctrl_data; struct pcie_link_state; struct pci_sriov; struct pci_p2pdma; struct rcec_ea; -/* The pci_dev structure describes PCI devices */ +/* struct pci_dev - describes a PCI device + * + * @supported_speeds: PCIe Supported Link Speeds Vector (+ reserved 0 at + * LSB). 0 when the supported speeds cannot be + * determined (e.g., for Root Complex Integrated + * Endpoints without the relevant Capability + * Registers). + */ struct pci_dev { struct list_head bus_list; /* Node in per-bus list */ struct pci_bus *bus; /* Bus this device is on */ @@ -367,10 +375,12 @@ struct pci_dev { this is D0-D3, D0 being fully functional, and D3 being off. */ u8 pm_cap; /* PM capability offset */ - unsigned int imm_ready:1; /* Supports Immediate Readiness */ unsigned int pme_support:5; /* Bitmask of states from which PME# can be generated */ unsigned int pme_poll:1; /* Poll device's PME status bit */ + unsigned int pinned:1; /* Whether this dev is pinned */ + unsigned int config_rrs_sv:1; /* Config RRS software visibility */ + unsigned int imm_ready:1; /* Supports Immediate Readiness */ unsigned int d1_support:1; /* Low power state D1 is supported */ unsigned int d2_support:1; /* Low power state D2 is supported */ unsigned int no_d1d2:1; /* D1 and D2 are forbidden */ @@ -397,7 +407,7 @@ struct pci_dev { supported from root to here */ #endif unsigned int pasid_no_tlp:1; /* PASID works without TLP Prefix */ - unsigned int eetlp_prefix_path:1; /* End-to-End TLP Prefix */ + unsigned int eetlp_prefix_max:3; /* Max # of End-End TLP Prefixes, 0=not supported */ pci_channel_state_t error_state; /* Current connectivity state */ struct device dev; /* Generic device interface */ @@ -432,6 +442,7 @@ struct pci_dev { unsigned int ats_enabled:1; /* Address Translation Svc */ unsigned int pasid_enabled:1; /* Process Address Space ID */ unsigned int pri_enabled:1; /* Page Request Interface */ + unsigned int tph_enabled:1; /* TLP Processing Hints */ unsigned int is_managed:1; /* Managed via devres */ unsigned int is_msi_managed:1; /* MSI release via devres installed */ unsigned int needs_freset:1; /* Requires fundamental reset */ @@ -493,6 +504,7 @@ struct pci_dev { unsigned int dpc_rp_extensions:1; u8 dpc_rp_log_size; #endif + struct pcie_bwctrl_data *link_bwctrl; #ifdef CONFIG_PCI_ATS union { struct pci_sriov *sriov; /* PF: SR-IOV info */ @@ -516,7 +528,11 @@ struct pci_dev { #ifdef CONFIG_PCI_DOE struct xarray doe_mbs; /* Data Object Exchange mailboxes */ #endif +#ifdef CONFIG_PCI_NPEM + struct npem *npem; /* Native PCIe Enclosure Management */ +#endif u16 acs_cap; /* ACS Capability offset */ + u8 supported_speeds; /* Supported Link Speeds Vector */ phys_addr_t rom; /* Physical address if not from BAR */ size_t romlen; /* Length if not from BAR */ /* @@ -529,6 +545,12 @@ struct pci_dev { /* These methods index pci_reset_fn_methods[] */ u8 reset_methods[PCI_NUM_RESET_METHODS]; /* In priority order */ + +#ifdef CONFIG_PCIE_TPH + u16 tph_cap; /* TPH capability offset */ + u8 tph_mode; /* TPH mode */ + u8 tph_req_type; /* TPH requester type */ +#endif }; static inline struct pci_dev *pci_physfn(struct pci_dev *dev) @@ -573,6 +595,8 @@ struct pci_host_bridge { u8 (*swizzle_irq)(struct pci_dev *, u8 *); /* Platform IRQ swizzler */ int (*map_irq)(const struct pci_dev *, u8, u8); void (*release_fn)(struct pci_host_bridge *); + int (*enable_device)(struct pci_host_bridge *bridge, struct pci_dev *dev); + void (*disable_device)(struct pci_host_bridge *bridge, struct pci_dev *dev); void *release_data; unsigned int ignore_reset_delay:1; /* For entire hierarchy */ unsigned int no_ext_tags:1; /* No Extended Tags */ @@ -621,27 +645,6 @@ void pci_set_host_bridge_release(struct pci_host_bridge *bridge, int pcibios_root_bridge_prepare(struct pci_host_bridge *bridge); -/* - * The first PCI_BRIDGE_RESOURCE_NUM PCI bus resources (those that correspond - * to P2P or CardBus bridge windows) go in a table. Additional ones (for - * buses below host bridges or subtractive decode bridges) go in the list. - * Use pci_bus_for_each_resource() to iterate through all the resources. - */ - -/* - * PCI_SUBTRACTIVE_DECODE means the bridge forwards the window implicitly - * and there's no way to program the bridge with the details of the window. - * This does not apply to ACPI _CRS windows, even with the _DEC subtractive- - * decode bit set, because they are explicit and can be programmed with _SRS. - */ -#define PCI_SUBTRACTIVE_DECODE 0x1 - -struct pci_bus_resource { - struct list_head list; - struct resource *res; - unsigned int flags; -}; - #define PCI_REGION_FLAG_MASK 0x0fU /* These bits of resource flags tell us the PCI region flags */ struct pci_bus { @@ -958,10 +961,8 @@ struct pci_driver { bool driver_managed_dma; }; -static inline struct pci_driver *to_pci_driver(struct device_driver *drv) -{ - return drv ? container_of(drv, struct pci_driver, driver) : NULL; -} +#define to_pci_driver(__drv) \ + ( __drv ? container_of_const(__drv, struct pci_driver, driver) : NULL ) /** * PCI_DEVICE - macro used to describe a specific PCI device @@ -1048,6 +1049,20 @@ static inline struct pci_driver *to_pci_driver(struct device_driver *drv) .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, 0, 0 /** + * PCI_VDEVICE_SUB - describe a specific PCI device/subdevice in a short form + * @vend: the vendor name + * @dev: the 16 bit PCI Device ID + * @subvend: the 16 bit PCI Subvendor ID + * @subdev: the 16 bit PCI Subdevice ID + * + * Generate the pci_device_id struct layout for the specific PCI + * device/subdevice. Private data may follow the output. + */ +#define PCI_VDEVICE_SUB(vend, dev, subvend, subdev) \ + .vendor = PCI_VENDOR_ID_##vend, .device = (dev), \ + .subvendor = (subvend), .subdevice = (subdev), 0, 0 + +/** * PCI_DEVICE_DATA - macro used to describe a specific PCI device in very short form * @vend: the vendor name (without PCI_VENDOR_ID_ prefix) * @dev: the device name (without PCI_DEVICE_ID_<vend>_ prefix) @@ -1077,8 +1092,6 @@ enum { #define PCI_IRQ_MSIX (1 << 2) /* Allow MSI-X interrupts */ #define PCI_IRQ_AFFINITY (1 << 3) /* Auto-assign affinity */ -#define PCI_IRQ_LEGACY PCI_IRQ_INTX /* Deprecated! Use PCI_IRQ_INTX */ - /* These external functions are only available when PCI support is enabled */ #ifdef CONFIG_PCI @@ -1101,7 +1114,7 @@ enum pcie_bus_config_types { extern enum pcie_bus_config_types pcie_bus_config; -extern struct bus_type pci_bus_type; +extern const struct bus_type pci_bus_type; /* Do NOT directly access these two variables, unless you are arch-specific PCI * code, or PCI core code. */ @@ -1273,6 +1286,7 @@ static inline int pcie_capability_clear_and_set_word(struct pci_dev *dev, { switch (pos) { case PCI_EXP_LNKCTL: + case PCI_EXP_LNKCTL2: case PCI_EXP_RTCTL: return pcie_capability_clear_and_set_word_locked(dev, pos, clear, set); @@ -1315,7 +1329,6 @@ int pci_user_write_config_word(struct pci_dev *dev, int where, u16 val); int pci_user_write_config_dword(struct pci_dev *dev, int where, u32 val); int __must_check pci_enable_device(struct pci_dev *dev); -int __must_check pci_enable_device_io(struct pci_dev *dev); int __must_check pci_enable_device_mem(struct pci_dev *dev); int __must_check pci_reenable_device(struct pci_dev *); int __must_check pcim_enable_device(struct pci_dev *pdev); @@ -1498,8 +1511,7 @@ void pci_add_resource(struct list_head *resources, struct resource *res); void pci_add_resource_offset(struct list_head *resources, struct resource *res, resource_size_t offset); void pci_free_resource_list(struct list_head *resources); -void pci_bus_add_resource(struct pci_bus *bus, struct resource *res, - unsigned int flags); +void pci_bus_add_resource(struct pci_bus *bus, struct resource *res); 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); @@ -1552,14 +1564,11 @@ int __must_check pci_bus_alloc_resource(struct pci_bus *bus, struct resource *res, resource_size_t size, resource_size_t align, resource_size_t min, unsigned long type_mask, - resource_size_t (*alignf)(void *, - const struct resource *, - resource_size_t, - resource_size_t), + resource_alignf alignf, void *alignf_data); -int pci_register_io_range(struct fwnode_handle *fwnode, phys_addr_t addr, +int pci_register_io_range(const struct fwnode_handle *fwnode, phys_addr_t addr, resource_size_t size); unsigned long pci_address_to_pio(phys_addr_t addr); phys_addr_t pci_pio_to_address(unsigned long pio); @@ -1626,8 +1635,6 @@ int pci_scan_bridge(struct pci_bus *bus, struct pci_dev *dev, int max, void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), void *userdata); -void pci_walk_bus_locked(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), - void *userdata); int pci_cfg_space_size(struct pci_dev *dev); unsigned char pci_bus_max_busnr(struct pci_bus *bus); void pci_setup_bridge(struct pci_bus *bus); @@ -1648,8 +1655,7 @@ int pci_set_vga_state(struct pci_dev *pdev, bool decode, */ #define PCI_IRQ_VIRTUAL (1 << 4) -#define PCI_IRQ_ALL_TYPES \ - (PCI_IRQ_LEGACY | PCI_IRQ_MSI | PCI_IRQ_MSIX) +#define PCI_IRQ_ALL_TYPES (PCI_IRQ_INTX | PCI_IRQ_MSI | PCI_IRQ_MSIX) #include <linux/dmapool.h> @@ -1658,8 +1664,6 @@ struct msix_entry { u16 entry; /* Driver uses to specify entry, OS writes */ }; -struct msi_domain_template; - #ifdef CONFIG_PCI_MSI int pci_msi_vec_count(struct pci_dev *dev); void pci_disable_msi(struct pci_dev *dev); @@ -1692,11 +1696,6 @@ void pci_msix_free_irq(struct pci_dev *pdev, struct msi_map map); void pci_free_irq_vectors(struct pci_dev *dev); int pci_irq_vector(struct pci_dev *dev, unsigned int nr); const struct cpumask *pci_irq_get_affinity(struct pci_dev *pdev, int vec); -bool pci_create_ims_domain(struct pci_dev *pdev, const struct msi_domain_template *template, - unsigned int hwsize, void *data); -struct msi_map pci_ims_alloc_irq(struct pci_dev *pdev, union msi_instance_cookie *icookie, - const struct irq_affinity_desc *affdesc); -void pci_ims_free_irq(struct pci_dev *pdev, struct msi_map map); #else static inline int pci_msi_vec_count(struct pci_dev *dev) { return -ENOSYS; } @@ -1719,7 +1718,7 @@ pci_alloc_irq_vectors_affinity(struct pci_dev *dev, unsigned int min_vecs, unsigned int max_vecs, unsigned int flags, struct irq_affinity *aff_desc) { - if ((flags & PCI_IRQ_LEGACY) && min_vecs == 1 && dev->irq) + if ((flags & PCI_IRQ_INTX) && min_vecs == 1 && dev->irq) return 1; return -ENOSPC; } @@ -1760,25 +1759,6 @@ static inline const struct cpumask *pci_irq_get_affinity(struct pci_dev *pdev, { return cpu_possible_mask; } - -static inline bool pci_create_ims_domain(struct pci_dev *pdev, - const struct msi_domain_template *template, - unsigned int hwsize, void *data) -{ return false; } - -static inline struct msi_map pci_ims_alloc_irq(struct pci_dev *pdev, - union msi_instance_cookie *icookie, - const struct irq_affinity_desc *affdesc) -{ - struct msi_map map = { .index = -ENOSYS, }; - - return map; -} - -static inline void pci_ims_free_irq(struct pci_dev *pdev, struct msi_map map) -{ -} - #endif /** @@ -1816,22 +1796,36 @@ static inline int pci_irqd_intx_xlate(struct irq_domain *d, #ifdef CONFIG_PCIEPORTBUS extern bool pcie_ports_disabled; extern bool pcie_ports_native; + +int pcie_set_target_speed(struct pci_dev *port, enum pci_bus_speed speed_req, + bool use_lt); #else #define pcie_ports_disabled true #define pcie_ports_native false + +static inline int pcie_set_target_speed(struct pci_dev *port, + enum pci_bus_speed speed_req, + bool use_lt) +{ + return -EOPNOTSUPP; +} #endif -#define PCIE_LINK_STATE_L0S BIT(0) -#define PCIE_LINK_STATE_L1 BIT(1) -#define PCIE_LINK_STATE_CLKPM BIT(2) -#define PCIE_LINK_STATE_L1_1 BIT(3) -#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 |\ +#define PCIE_LINK_STATE_L0S (BIT(0) | BIT(1)) /* Upstr/dwnstr L0s */ +#define PCIE_LINK_STATE_L1 BIT(2) /* L1 state */ +#define PCIE_LINK_STATE_L1_1 BIT(3) /* ASPM L1.1 state */ +#define PCIE_LINK_STATE_L1_2 BIT(4) /* ASPM L1.2 state */ +#define PCIE_LINK_STATE_L1_1_PCIPM BIT(5) /* PCI-PM L1.1 state */ +#define PCIE_LINK_STATE_L1_2_PCIPM BIT(6) /* PCI-PM L1.2 state */ +#define PCIE_LINK_STATE_ASPM_ALL (PCIE_LINK_STATE_L0S |\ + PCIE_LINK_STATE_L1 |\ + PCIE_LINK_STATE_L1_1 |\ + PCIE_LINK_STATE_L1_2 |\ + PCIE_LINK_STATE_L1_1_PCIPM |\ PCIE_LINK_STATE_L1_2_PCIPM) +#define PCIE_LINK_STATE_CLKPM BIT(7) +#define PCIE_LINK_STATE_ALL (PCIE_LINK_STATE_ASPM_ALL |\ + PCIE_LINK_STATE_CLKPM) #ifdef CONFIG_PCIEASPM int pci_disable_link_state(struct pci_dev *pdev, int state); @@ -1914,7 +1908,7 @@ static inline int acpi_pci_bus_find_domain_nr(struct pci_bus *bus) { return 0; } #endif int pci_bus_find_domain_nr(struct pci_bus *bus, struct device *parent); -void pci_bus_release_domain_nr(struct pci_bus *bus, struct device *parent); +void pci_bus_release_domain_nr(struct device *parent, int domain_nr); #endif /* Some architectures require additional setup to direct VGA traffic */ @@ -2014,10 +2008,9 @@ static inline int pci_register_driver(struct pci_driver *drv) static inline void pci_unregister_driver(struct pci_driver *drv) { } static inline u8 pci_find_capability(struct pci_dev *dev, int cap) { return 0; } -static inline int pci_find_next_capability(struct pci_dev *dev, u8 post, - int cap) +static inline u8 pci_find_next_capability(struct pci_dev *dev, u8 post, int cap) { return 0; } -static inline int pci_find_ext_capability(struct pci_dev *dev, int cap) +static inline u16 pci_find_ext_capability(struct pci_dev *dev, int cap) { return 0; } static inline u64 pci_get_dsn(struct pci_dev *dev) @@ -2046,7 +2039,7 @@ static inline int pci_request_regions(struct pci_dev *dev, const char *res_name) { return -EIO; } static inline void pci_release_regions(struct pci_dev *dev) { } -static inline int pci_register_io_range(struct fwnode_handle *fwnode, +static inline int pci_register_io_range(const struct fwnode_handle *fwnode, phys_addr_t addr, resource_size_t size) { return -EINVAL; } @@ -2320,13 +2313,19 @@ static inline void pci_fixup_device(enum pci_fixup_pass pass, struct pci_dev *dev) { } #endif +int pcim_intx(struct pci_dev *pdev, int enabled); +int pcim_request_all_regions(struct pci_dev *pdev, const char *name); void __iomem *pcim_iomap(struct pci_dev *pdev, int bar, unsigned long maxlen); +void __iomem *pcim_iomap_region(struct pci_dev *pdev, int bar, + const char *name); +void pcim_iounmap_region(struct pci_dev *pdev, int bar); void pcim_iounmap(struct pci_dev *pdev, void __iomem *addr); void __iomem * const *pcim_iomap_table(struct pci_dev *pdev); +int pcim_request_region(struct pci_dev *pdev, int bar, const char *name); int pcim_iomap_regions(struct pci_dev *pdev, int mask, const char *name); -int pcim_iomap_regions_request_all(struct pci_dev *pdev, int mask, - const char *name); void pcim_iounmap_regions(struct pci_dev *pdev, int mask); +void __iomem *pcim_iomap_range(struct pci_dev *pdev, int bar, + unsigned long offset, unsigned long len); extern int pci_pci_problems; #define PCIPCI_FAIL 1 /* No PCI PCI DMA */ @@ -2519,7 +2518,12 @@ static inline struct pci_dev *pcie_find_root_port(struct pci_dev *dev) static inline bool pci_dev_is_disconnected(const struct pci_dev *dev) { - return dev->error_state == pci_channel_io_perm_failure; + /* + * error_state is set in pci_dev_set_io_state() using xchg/cmpxchg() + * and read w/o common lock. READ_ONCE() ensures compiler cannot cache + * the value (e.g. inside the loop in pci_dev_wait()). + */ + return READ_ONCE(dev->error_state) == pci_channel_io_perm_failure; } void pci_request_acs(void); @@ -2626,6 +2630,12 @@ pci_host_bridge_acpi_msi_domain(struct pci_bus *bus) { return NULL; } static inline bool pci_pr3_present(struct pci_dev *pdev) { return false; } #endif +#if defined(CONFIG_X86) && defined(CONFIG_ACPI) +bool arch_pci_dev_is_removable(struct pci_dev *pdev); +#else +static inline bool arch_pci_dev_is_removable(struct pci_dev *pdev) { return false; } +#endif + #ifdef CONFIG_EEH static inline struct eeh_dev *pci_dev_to_eeh_dev(struct pci_dev *pdev) { diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index a0c75e467df3..de5deb1a0118 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -121,6 +121,7 @@ #define PCI_CLASS_SERIAL_USB_OHCI 0x0c0310 #define PCI_CLASS_SERIAL_USB_EHCI 0x0c0320 #define PCI_CLASS_SERIAL_USB_XHCI 0x0c0330 +#define PCI_CLASS_SERIAL_USB_CDNS 0x0c0380 #define PCI_CLASS_SERIAL_USB_DEVICE 0x0c03fe #define PCI_CLASS_SERIAL_FIBER 0x0c04 #define PCI_CLASS_SERIAL_SMBUS 0x0c05 @@ -580,6 +581,8 @@ #define PCI_DEVICE_ID_AMD_19H_M78H_DF_F3 0x12fb #define PCI_DEVICE_ID_AMD_1AH_M00H_DF_F3 0x12c3 #define PCI_DEVICE_ID_AMD_1AH_M20H_DF_F3 0x16fb +#define PCI_DEVICE_ID_AMD_1AH_M60H_DF_F3 0x124b +#define PCI_DEVICE_ID_AMD_1AH_M70H_DF_F3 0x12bb #define PCI_DEVICE_ID_AMD_MI200_DF_F3 0x14d3 #define PCI_DEVICE_ID_AMD_MI300_DF_F3 0x152b #define PCI_DEVICE_ID_AMD_VANGOGH_USB 0x163a @@ -2125,6 +2128,8 @@ #define PCI_VENDOR_ID_CHELSIO 0x1425 +#define PCI_VENDOR_ID_EDIMAX 0x1432 + #define PCI_VENDOR_ID_ADLINK 0x144a #define PCI_VENDOR_ID_SAMSUNG 0x144d @@ -2417,6 +2422,9 @@ #define PCI_VENDOR_ID_QCOM 0x17cb #define PCI_VENDOR_ID_CDNS 0x17cd +#define PCI_DEVICE_ID_CDNS_USBSS 0x0100 +#define PCI_DEVICE_ID_CDNS_USB 0x0120 +#define PCI_DEVICE_ID_CDNS_USBSSP 0x0200 #define PCI_VENDOR_ID_ARECA 0x17d3 #define PCI_DEVICE_ID_ARECA_1110 0x1110 @@ -2585,6 +2593,11 @@ #define PCI_VENDOR_ID_REDHAT 0x1b36 +#define PCI_VENDOR_ID_WCHIC 0x1c00 +#define PCI_DEVICE_ID_WCHIC_CH382_0S1P 0x3050 +#define PCI_DEVICE_ID_WCHIC_CH382_2S1P 0x3250 +#define PCI_DEVICE_ID_WCHIC_CH382_2S 0x3253 + #define PCI_VENDOR_ID_SILICOM_DENMARK 0x1c2c #define PCI_VENDOR_ID_AMAZON_ANNAPURNA_LABS 0x1c36 @@ -2598,6 +2611,8 @@ #define PCI_VENDOR_ID_HYGON 0x1d94 +#define PCI_VENDOR_ID_META 0x1d9b + #define PCI_VENDOR_ID_FUNGIBLE 0x1dad #define PCI_VENDOR_ID_HXT 0x1dbf @@ -2607,6 +2622,8 @@ #define PCI_VENDOR_ID_ALIBABA 0x1ded +#define PCI_VENDOR_ID_CXL 0x1e98 + #define PCI_VENDOR_ID_TEHUTI 0x1fc9 #define PCI_DEVICE_ID_TEHUTI_3009 0x3009 #define PCI_DEVICE_ID_TEHUTI_3010 0x3010 @@ -2635,6 +2652,12 @@ #define PCI_VENDOR_ID_AKS 0x416c #define PCI_DEVICE_ID_AKS_ALADDINCARD 0x0100 +#define PCI_VENDOR_ID_WCHCN 0x4348 +#define PCI_DEVICE_ID_WCHCN_CH353_4S 0x3453 +#define PCI_DEVICE_ID_WCHCN_CH353_2S1PF 0x5046 +#define PCI_DEVICE_ID_WCHCN_CH353_1S1P 0x5053 +#define PCI_DEVICE_ID_WCHCN_CH353_2S1P 0x7053 + #define PCI_VENDOR_ID_ACCESSIO 0x494f #define PCI_DEVICE_ID_ACCESSIO_WDG_CSM 0x22c0 @@ -2654,6 +2677,8 @@ #define PCI_DEVICE_ID_DCI_PCCOM8 0x0002 #define PCI_DEVICE_ID_DCI_PCCOM2 0x0004 +#define PCI_VENDOR_ID_GLENFLY 0x6766 + #define PCI_VENDOR_ID_INTEL 0x8086 #define PCI_DEVICE_ID_INTEL_EESSC 0x0008 #define PCI_DEVICE_ID_INTEL_HDA_CML_LP 0x02c8 @@ -2686,8 +2711,10 @@ #define PCI_DEVICE_ID_INTEL_I960 0x0960 #define PCI_DEVICE_ID_INTEL_I960RM 0x0962 #define PCI_DEVICE_ID_INTEL_HDA_HSW_0 0x0a0c +#define PCI_DEVICE_ID_INTEL_DSA_SPR0 0x0b25 #define PCI_DEVICE_ID_INTEL_HDA_HSW_2 0x0c0c #define PCI_DEVICE_ID_INTEL_CENTERTON_ILB 0x0c60 +#define PCI_DEVICE_ID_INTEL_IAX_SPR0 0x0cfe #define PCI_DEVICE_ID_INTEL_HDA_HSW_3 0x0d0c #define PCI_DEVICE_ID_INTEL_HDA_BYT 0x0f04 #define PCI_DEVICE_ID_INTEL_SST_BYT 0x0f28 @@ -3106,6 +3133,8 @@ #define PCI_DEVICE_ID_INTEL_HDA_CML_S 0xa3f0 #define PCI_DEVICE_ID_INTEL_HDA_LNL_P 0xa828 #define PCI_DEVICE_ID_INTEL_S21152BB 0xb152 +#define PCI_DEVICE_ID_INTEL_HDA_BMG 0xe2f7 +#define PCI_DEVICE_ID_INTEL_HDA_PTL 0xe428 #define PCI_DEVICE_ID_INTEL_HDA_CML_R 0xf0c8 #define PCI_DEVICE_ID_INTEL_HDA_RKL_S 0xf1c8 diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index da3a6c30f6d2..733f4ddd2ef1 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -7,11 +7,12 @@ #ifndef __LINUX_PCS_XPCS_H #define __LINUX_PCS_XPCS_H +#include <linux/clk.h> +#include <linux/fwnode.h> +#include <linux/mdio.h> #include <linux/phy.h> #include <linux/phylink.h> - -#define NXP_SJA1105_XPCS_ID 0x00000010 -#define NXP_SJA1110_XPCS_ID 0x00000020 +#include <linux/types.h> /* AN mode */ #define DW_AN_C73 1 @@ -20,32 +21,42 @@ #define DW_AN_C37_1000BASEX 4 #define DW_10GBASER 5 -/* device vendor OUI */ -#define DW_OUI_WX 0x0018fc80 - -/* dev_flag */ -#define DW_DEV_TXGBE BIT(0) +enum dw_xpcs_pcs_id { + DW_XPCS_ID_NATIVE = 0, + NXP_SJA1105_XPCS_ID = 0x00000010, + NXP_SJA1110_XPCS_ID = 0x00000020, + DW_XPCS_ID = 0x7996ced0, + DW_XPCS_ID_MASK = 0xffffffff, +}; -struct xpcs_id; +enum dw_xpcs_pma_id { + DW_XPCS_PMA_ID_NATIVE = 0, + DW_XPCS_PMA_GEN1_3G_ID, + DW_XPCS_PMA_GEN2_3G_ID, + DW_XPCS_PMA_GEN2_6G_ID, + DW_XPCS_PMA_GEN4_3G_ID, + DW_XPCS_PMA_GEN4_6G_ID, + DW_XPCS_PMA_GEN5_10G_ID, + DW_XPCS_PMA_GEN5_12G_ID, + WX_TXGBE_XPCS_PMA_10G_ID = 0x0018fc80, +}; -struct dw_xpcs { - struct mdio_device *mdiodev; - const struct xpcs_id *id; - struct phylink_pcs pcs; - phy_interface_t interface; - int dev_flag; +struct dw_xpcs_info { + u32 pcs; + u32 pma; }; +struct dw_xpcs; + +struct phylink_pcs *xpcs_to_phylink_pcs(struct dw_xpcs *xpcs); int xpcs_get_an_mode(struct dw_xpcs *xpcs, phy_interface_t interface); -void xpcs_link_up(struct phylink_pcs *pcs, unsigned int neg_mode, - phy_interface_t interface, int speed, int duplex); -int xpcs_do_config(struct dw_xpcs *xpcs, phy_interface_t interface, - const unsigned long *advertising, unsigned int neg_mode); -void xpcs_get_interfaces(struct dw_xpcs *xpcs, unsigned long *interfaces); int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns, int enable); -struct dw_xpcs *xpcs_create_mdiodev(struct mii_bus *bus, int addr, - phy_interface_t interface); +struct dw_xpcs *xpcs_create_mdiodev(struct mii_bus *bus, int addr); +struct dw_xpcs *xpcs_create_fwnode(struct fwnode_handle *fwnode); void xpcs_destroy(struct dw_xpcs *xpcs); +struct phylink_pcs *xpcs_create_pcs_mdiodev(struct mii_bus *bus, int addr); +void xpcs_destroy_pcs(struct phylink_pcs *pcs); + #endif /* __LINUX_PCS_XPCS_H */ diff --git a/include/linux/pds/pds_common.h b/include/linux/pds/pds_common.h index 30581e2e04cc..5802e1deef24 100644 --- a/include/linux/pds/pds_common.h +++ b/include/linux/pds/pds_common.h @@ -4,6 +4,8 @@ #ifndef _PDS_COMMON_H_ #define _PDS_COMMON_H_ +#include <linux/notifier.h> + #define PDS_CORE_DRV_NAME "pds_core" /* the device's internal addressing uses up to 52 bits */ diff --git a/include/linux/peci-cpu.h b/include/linux/peci-cpu.h index ff8ae9c26c80..601cdd086bf6 100644 --- a/include/linux/peci-cpu.h +++ b/include/linux/peci-cpu.h @@ -6,6 +6,30 @@ #include <linux/types.h> +/* Copied from x86 <asm/processor.h> */ +#define X86_VENDOR_INTEL 0 + +/* Copied from x86 <asm/cpu_device_id.h> */ +#define VFM_MODEL_BIT 0 +#define VFM_FAMILY_BIT 8 +#define VFM_VENDOR_BIT 16 +#define VFM_RSVD_BIT 24 + +#define VFM_MODEL_MASK GENMASK(VFM_FAMILY_BIT - 1, VFM_MODEL_BIT) +#define VFM_FAMILY_MASK GENMASK(VFM_VENDOR_BIT - 1, VFM_FAMILY_BIT) +#define VFM_VENDOR_MASK GENMASK(VFM_RSVD_BIT - 1, VFM_VENDOR_BIT) + +#define VFM_MODEL(vfm) (((vfm) & VFM_MODEL_MASK) >> VFM_MODEL_BIT) +#define VFM_FAMILY(vfm) (((vfm) & VFM_FAMILY_MASK) >> VFM_FAMILY_BIT) +#define VFM_VENDOR(vfm) (((vfm) & VFM_VENDOR_MASK) >> VFM_VENDOR_BIT) + +#define VFM_MAKE(_vendor, _family, _model) ( \ + ((_model) << VFM_MODEL_BIT) | \ + ((_family) << VFM_FAMILY_BIT) | \ + ((_vendor) << VFM_VENDOR_BIT) \ +) +/* End of copied code */ + #include "../../arch/x86/include/asm/intel-family.h" #define PECI_PCS_PKG_ID 0 /* Package Identifier Read */ diff --git a/include/linux/peci.h b/include/linux/peci.h index 90e241458ef6..3e0bc37591d6 100644 --- a/include/linux/peci.h +++ b/include/linux/peci.h @@ -59,8 +59,7 @@ static inline struct peci_controller *to_peci_controller(void *d) * struct peci_device - PECI device * @dev: device object to register PECI device to the device model * @info: PECI device characteristics - * @info.family: device family - * @info.model: device model + * @info.x86_vfm: device vendor-family-model * @info.peci_revision: PECI revision supported by the PECI device * @info.socket_id: the socket ID represented by the PECI device * @addr: address used on the PECI bus connected to the parent controller @@ -73,8 +72,7 @@ static inline struct peci_controller *to_peci_controller(void *d) struct peci_device { struct device dev; struct { - u16 family; - u8 model; + u32 x86_vfm; u8 peci_revision; u8 socket_id; } info; diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h index ec3573119923..5b520fe86b60 100644 --- a/include/linux/percpu-defs.h +++ b/include/linux/percpu-defs.h @@ -220,15 +220,17 @@ do { \ (void)__vpp_verify; \ } while (0) +#define PERCPU_PTR(__p) \ + (typeof(*(__p)) __force __kernel *)((__force unsigned long)(__p)) + #ifdef CONFIG_SMP /* - * Add an offset to a pointer but keep the pointer as-is. Use RELOC_HIDE() - * to prevent the compiler from making incorrect assumptions about the - * pointer value. The weird cast keeps both GCC and sparse happy. + * Add an offset to a pointer. Use RELOC_HIDE() to prevent the compiler + * from making incorrect assumptions about the pointer value. */ #define SHIFT_PERCPU_PTR(__p, __offset) \ - RELOC_HIDE((typeof(*(__p)) __kernel __force *)(__p), (__offset)) + RELOC_HIDE(PERCPU_PTR(__p), (__offset)) #define per_cpu_ptr(ptr, cpu) \ ({ \ @@ -254,13 +256,13 @@ do { \ #else /* CONFIG_SMP */ -#define VERIFY_PERCPU_PTR(__p) \ +#define per_cpu_ptr(ptr, cpu) \ ({ \ - __verify_pcpu_ptr(__p); \ - (typeof(*(__p)) __kernel __force *)(__p); \ + (void)(cpu); \ + __verify_pcpu_ptr(ptr); \ + PERCPU_PTR(ptr); \ }) -#define per_cpu_ptr(ptr, cpu) ({ (void)(cpu); VERIFY_PERCPU_PTR(ptr); }) #define raw_cpu_ptr(ptr) per_cpu_ptr(ptr, 0) #define this_cpu_ptr(ptr) raw_cpu_ptr(ptr) @@ -475,6 +477,12 @@ do { \ raw_cpu_cmpxchg(pcp, oval, nval); \ }) +#define __this_cpu_try_cmpxchg(pcp, ovalp, nval) \ +({ \ + __this_cpu_preempt_check("try_cmpxchg"); \ + raw_cpu_try_cmpxchg(pcp, ovalp, nval); \ +}) + #define __this_cpu_sub(pcp, val) __this_cpu_add(pcp, -(typeof(pcp))(val)) #define __this_cpu_inc(pcp) __this_cpu_add(pcp, 1) #define __this_cpu_dec(pcp) __this_cpu_sub(pcp, 1) diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h index 36b942b67b7d..c012df33a9f0 100644 --- a/include/linux/percpu-rwsem.h +++ b/include/linux/percpu-rwsem.h @@ -145,7 +145,7 @@ extern void percpu_free_rwsem(struct percpu_rw_semaphore *); #define percpu_rwsem_assert_held(sem) lockdep_assert_held(sem) static inline void percpu_rwsem_release(struct percpu_rw_semaphore *sem, - bool read, unsigned long ip) + unsigned long ip) { lock_release(&sem->dep_map, ip); } diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 8c677f185901..52b5ea663b9f 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -2,19 +2,24 @@ #ifndef __LINUX_PERCPU_H #define __LINUX_PERCPU_H +#include <linux/alloc_tag.h> #include <linux/mmdebug.h> #include <linux/preempt.h> #include <linux/smp.h> -#include <linux/cpumask.h> #include <linux/pfn.h> #include <linux/init.h> #include <linux/cleanup.h> +#include <linux/sched.h> #include <asm/percpu.h> /* enough to cover all DEFINE_PER_CPUs in modules */ #ifdef CONFIG_MODULES +#ifdef CONFIG_MEM_ALLOC_PROFILING +#define PERCPU_MODULE_RESERVE (8 << 13) +#else #define PERCPU_MODULE_RESERVE (8 << 10) +#endif #else #define PERCPU_MODULE_RESERVE 0 #endif @@ -36,7 +41,11 @@ PCPU_MIN_ALLOC_SHIFT) #ifdef CONFIG_RANDOM_KMALLOC_CACHES -#define PERCPU_DYNAMIC_SIZE_SHIFT 12 +# if defined(CONFIG_LOCKDEP) && !defined(CONFIG_PAGE_SIZE_4KB) +# define PERCPU_DYNAMIC_SIZE_SHIFT 13 +# else +# define PERCPU_DYNAMIC_SIZE_SHIFT 12 +#endif /* LOCKDEP and PAGE_SIZE > 4KiB */ #else #define PERCPU_DYNAMIC_SIZE_SHIFT 10 #endif @@ -121,7 +130,6 @@ extern int __init pcpu_page_first_chunk(size_t reserved_size, pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn); #endif -extern void __percpu *__alloc_reserved_percpu(size_t size, size_t align) __alloc_size(1); extern bool __is_kernel_percpu_address(unsigned long addr, unsigned long *can_addr); extern bool is_kernel_percpu_address(unsigned long addr); @@ -129,14 +137,15 @@ extern bool is_kernel_percpu_address(unsigned long addr); extern void __init setup_per_cpu_areas(void); #endif -extern void __percpu *__alloc_percpu_gfp(size_t size, size_t align, gfp_t gfp) __alloc_size(1); -extern void __percpu *__alloc_percpu(size_t size, size_t align) __alloc_size(1); -extern void free_percpu(void __percpu *__pdata); -extern size_t pcpu_alloc_size(void __percpu *__pdata); - -DEFINE_FREE(free_percpu, void __percpu *, free_percpu(_T)) +extern void __percpu *pcpu_alloc_noprof(size_t size, size_t align, bool reserved, + gfp_t gfp) __alloc_size(1); -extern phys_addr_t per_cpu_ptr_to_phys(void *addr); +#define __alloc_percpu_gfp(_size, _align, _gfp) \ + alloc_hooks(pcpu_alloc_noprof(_size, _align, false, _gfp)) +#define __alloc_percpu(_size, _align) \ + alloc_hooks(pcpu_alloc_noprof(_size, _align, false, GFP_KERNEL)) +#define __alloc_reserved_percpu(_size, _align) \ + alloc_hooks(pcpu_alloc_noprof(_size, _align, true, GFP_KERNEL)) #define alloc_percpu_gfp(type, gfp) \ (typeof(type) __percpu *)__alloc_percpu_gfp(sizeof(type), \ @@ -144,6 +153,15 @@ extern phys_addr_t per_cpu_ptr_to_phys(void *addr); #define alloc_percpu(type) \ (typeof(type) __percpu *)__alloc_percpu(sizeof(type), \ __alignof__(type)) +#define alloc_percpu_noprof(type) \ + ((typeof(type) __percpu *)pcpu_alloc_noprof(sizeof(type), \ + __alignof__(type), false, GFP_KERNEL)) + +extern void free_percpu(void __percpu *__pdata); + +DEFINE_FREE(free_percpu, void __percpu *, free_percpu(_T)) + +extern phys_addr_t per_cpu_ptr_to_phys(void *addr); extern unsigned long pcpu_nr_pages(void); diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index b3b34f6670cf..4b5b83677e3f 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -17,10 +17,14 @@ #ifdef CONFIG_ARM_PMU /* - * The ARMv7 CPU PMU supports up to 32 event counters. + * The Armv7 and Armv8.8 or less CPU PMU supports up to 32 event counters. + * The Armv8.9/9.4 CPU PMU supports up to 33 event counters. */ +#ifdef CONFIG_ARM #define ARMPMU_MAX_HWEVENTS 32 - +#else +#define ARMPMU_MAX_HWEVENTS 33 +#endif /* * ARM PMU hw_event flags */ @@ -96,7 +100,7 @@ struct arm_pmu { void (*stop)(struct arm_pmu *); void (*reset)(void *); int (*map_event)(struct perf_event *event); - int num_events; + DECLARE_BITMAP(cntr_mask, ARMPMU_MAX_HWEVENTS); bool secure_access; /* 32-bit ARM only */ #define ARMV8_PMUV3_MAX_COMMON_EVENTS 0x40 DECLARE_BITMAP(pmceid_bitmap, ARMV8_PMUV3_MAX_COMMON_EVENTS); diff --git a/include/linux/perf/arm_pmuv3.h b/include/linux/perf/arm_pmuv3.h index 46377e134d67..d698efba28a2 100644 --- a/include/linux/perf/arm_pmuv3.h +++ b/include/linux/perf/arm_pmuv3.h @@ -6,8 +6,9 @@ #ifndef __PERF_ARM_PMUV3_H #define __PERF_ARM_PMUV3_H -#define ARMV8_PMU_MAX_COUNTERS 32 -#define ARMV8_PMU_COUNTER_MASK (ARMV8_PMU_MAX_COUNTERS - 1) +#define ARMV8_PMU_MAX_GENERAL_COUNTERS 31 +#define ARMV8_PMU_CYCLE_IDX 31 +#define ARMV8_PMU_INSTR_IDX 32 /* Not accessible from AArch32 */ /* * Common architectural and microarchitectural event numbers. @@ -227,8 +228,10 @@ */ #define ARMV8_PMU_OVSR_P GENMASK(30, 0) #define ARMV8_PMU_OVSR_C BIT(31) +#define ARMV8_PMU_OVSR_F BIT_ULL(32) /* arm64 only */ /* Mask for writable bits is both P and C fields */ -#define ARMV8_PMU_OVERFLOWED_MASK (ARMV8_PMU_OVSR_P | ARMV8_PMU_OVSR_C) +#define ARMV8_PMU_OVERFLOWED_MASK (ARMV8_PMU_OVSR_P | ARMV8_PMU_OVSR_C | \ + ARMV8_PMU_OVSR_F) /* * PMXEVTYPER: Event selection reg @@ -254,6 +257,7 @@ #define ARMV8_PMU_USERENR_SW (1 << 1) /* PMSWINC can be written at EL0 */ #define ARMV8_PMU_USERENR_CR (1 << 2) /* Cycle counter can be read at EL0 */ #define ARMV8_PMU_USERENR_ER (1 << 3) /* Event counter can be read at EL0 */ +#define ARMV8_PMU_USERENR_UEN (1 << 4) /* Fine grained per counter access at EL0 */ /* Mask for writable bits */ #define ARMV8_PMU_USERENR_MASK (ARMV8_PMU_USERENR_EN | ARMV8_PMU_USERENR_SW | \ ARMV8_PMU_USERENR_CR | ARMV8_PMU_USERENR_ER) @@ -309,4 +313,6 @@ } \ } while (0) +#include <asm/arm_pmuv3.h> + #endif diff --git a/include/linux/perf/riscv_pmu.h b/include/linux/perf/riscv_pmu.h index 43282e22ebe1..701974639ff2 100644 --- a/include/linux/perf/riscv_pmu.h +++ b/include/linux/perf/riscv_pmu.h @@ -39,6 +39,14 @@ struct cpu_hw_events { DECLARE_BITMAP(used_hw_ctrs, RISCV_MAX_COUNTERS); /* currently enabled firmware counters */ DECLARE_BITMAP(used_fw_ctrs, RISCV_MAX_COUNTERS); + /* The virtual address of the shared memory where counter snapshot will be taken */ + void *snapshot_addr; + /* The physical address of the shared memory where counter snapshot will be taken */ + phys_addr_t snapshot_addr_phys; + /* Boolean flag to indicate setup is already done */ + bool snapshot_set_done; + /* A shadow copy of the counter values to avoid clobbering during multiple SBI calls */ + u64 snapshot_cval_shcopy[RISCV_MAX_COUNTERS]; }; struct riscv_pmu { diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index d2a15c0c6f8a..8333f132f4a9 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -168,6 +168,15 @@ struct hw_perf_event { struct hw_perf_event_extra extra_reg; struct hw_perf_event_extra branch_reg; }; + struct { /* aux / Intel-PT */ + u64 aux_config; + /* + * For AUX area events, aux_paused cannot be a state + * flag because it can be updated asynchronously to + * state. + */ + unsigned int aux_paused; + }; struct { /* software */ struct hrtimer hrtimer; }; @@ -291,6 +300,20 @@ struct perf_event_pmu_context; #define PERF_PMU_CAP_NO_EXCLUDE 0x0040 #define PERF_PMU_CAP_AUX_OUTPUT 0x0080 #define PERF_PMU_CAP_EXTENDED_HW_TYPE 0x0100 +#define PERF_PMU_CAP_AUX_PAUSE 0x0200 + +/** + * pmu::scope + */ +enum perf_pmu_scope { + PERF_PMU_SCOPE_NONE = 0, + PERF_PMU_SCOPE_CORE, + PERF_PMU_SCOPE_DIE, + PERF_PMU_SCOPE_CLUSTER, + PERF_PMU_SCOPE_PKG, + PERF_PMU_SCOPE_SYS_WIDE, + PERF_PMU_MAX_SCOPE, +}; struct perf_output_handle; @@ -315,6 +338,11 @@ struct pmu { */ int capabilities; + /* + * PMU scope + */ + unsigned int scope; + int __percpu *pmu_disable_count; struct perf_cpu_pmu_context __percpu *cpu_pmu_context; atomic_t exclusive_cnt; /* < 0: cpu; > 0: tsk */ @@ -363,6 +391,8 @@ struct pmu { #define PERF_EF_START 0x01 /* start the counter when adding */ #define PERF_EF_RELOAD 0x02 /* reload the counter when starting */ #define PERF_EF_UPDATE 0x04 /* update the counter when stopping */ +#define PERF_EF_PAUSE 0x08 /* AUX area event, pause tracing */ +#define PERF_EF_RESUME 0x10 /* AUX area event, resume tracing */ /* * Adds/Removes a counter to/from the PMU, can be done inside a @@ -402,6 +432,18 @@ struct pmu { * * ->start() with PERF_EF_RELOAD will reprogram the counter * value, must be preceded by a ->stop() with PERF_EF_UPDATE. + * + * ->stop() with PERF_EF_PAUSE will stop as simply as possible. Will not + * overlap another ->stop() with PERF_EF_PAUSE nor ->start() with + * PERF_EF_RESUME. + * + * ->start() with PERF_EF_RESUME will start as simply as possible but + * only if the counter is not otherwise stopped. Will not overlap + * another ->start() with PERF_EF_RESUME nor ->stop() with + * PERF_EF_PAUSE. + * + * Notably, PERF_EF_PAUSE/PERF_EF_RESUME *can* be concurrent with other + * ->stop()/->start() invocations, just not itself. */ void (*start) (struct perf_event *event, int flags); void (*stop) (struct perf_event *event, int flags); @@ -615,10 +657,13 @@ typedef void (*perf_overflow_handler_t)(struct perf_event *, * PERF_EV_CAP_SIBLING: An event with this flag must be a group sibling and * cannot be a group leader. If an event with this flag is detached from the * group it is scheduled out and moved into an unrecoverable ERROR state. + * PERF_EV_CAP_READ_SCOPE: A CPU event that can be read from any CPU of the + * PMU scope where it is active. */ #define PERF_EV_CAP_SOFTWARE BIT(0) #define PERF_EV_CAP_READ_ACTIVE_PKG BIT(1) #define PERF_EV_CAP_SIBLING BIT(2) +#define PERF_EV_CAP_READ_SCOPE BIT(3) #define SWEVENT_HLIST_BITS 8 #define SWEVENT_HLIST_SIZE (1 << SWEVENT_HLIST_BITS) @@ -781,11 +826,12 @@ struct perf_event { unsigned int pending_wakeup; unsigned int pending_kill; unsigned int pending_disable; - unsigned int pending_sigtrap; unsigned long pending_addr; /* SIGTRAP */ struct irq_work pending_irq; + struct irq_work pending_disable_irq; struct callback_head pending_task; unsigned int pending_work; + struct rcuwait pending_work_wait; atomic_t event_limit; @@ -809,11 +855,8 @@ struct perf_event { u64 (*clock)(void); perf_overflow_handler_t overflow_handler; void *overflow_handler_context; -#ifdef CONFIG_BPF_SYSCALL - perf_overflow_handler_t orig_overflow_handler; struct bpf_prog *prog; u64 bpf_cookie; -#endif #ifdef CONFIG_EVENT_TRACING struct trace_event_call *tp_event; @@ -883,6 +926,7 @@ struct perf_event_pmu_context { unsigned int nr_events; unsigned int nr_cgroups; + unsigned int nr_freq; atomic_t refcount; /* event <-> epc */ struct rcu_head rcu_head; @@ -897,6 +941,11 @@ struct perf_event_pmu_context { int rotate_necessary; }; +static inline bool perf_pmu_ctx_is_active(struct perf_event_pmu_context *epc) +{ + return !list_empty(&epc->flexible_active) || !list_empty(&epc->pinned_active); +} + struct perf_event_groups { struct rb_root tree; u64 index; @@ -959,20 +1008,18 @@ struct perf_event_context { struct rcu_head rcu_head; /* - * Sum (event->pending_sigtrap + event->pending_work) + * The count of events for which using the switch-out fast path + * should be avoided. + * + * Sum (event->pending_work + events with + * (attr->inherit && (attr->sample_type & PERF_SAMPLE_READ))) * * The SIGTRAP is targeted at ctx->task, as such it won't do changing * that until the signal is delivered. */ - local_t nr_pending; + local_t nr_no_switch_fast; }; -/* - * Number of contexts where an event can trigger: - * task, softirq, hardirq, nmi. - */ -#define PERF_NR_CONTEXTS 4 - struct perf_cpu_pmu_context { struct perf_event_pmu_context epc; struct perf_event_pmu_context *task_epc; @@ -1232,6 +1279,11 @@ static inline void perf_sample_save_callchain(struct perf_sample_data *data, { int size = 1; + if (!(event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)) + return; + if (WARN_ON_ONCE(data->sample_flags & PERF_SAMPLE_CALLCHAIN)) + return; + data->callchain = perf_callchain(event, regs); size += data->callchain->nr; @@ -1240,12 +1292,18 @@ static inline void perf_sample_save_callchain(struct perf_sample_data *data, } static inline void perf_sample_save_raw_data(struct perf_sample_data *data, + struct perf_event *event, struct perf_raw_record *raw) { struct perf_raw_frag *frag = &raw->frag; u32 sum = 0; int size; + if (!(event->attr.sample_type & PERF_SAMPLE_RAW)) + return; + if (WARN_ON_ONCE(data->sample_flags & PERF_SAMPLE_RAW)) + return; + do { sum += frag->size; if (perf_raw_frag_last(frag)) @@ -1262,6 +1320,11 @@ static inline void perf_sample_save_raw_data(struct perf_sample_data *data, data->sample_flags |= PERF_SAMPLE_RAW; } +static inline bool has_branch_stack(struct perf_event *event) +{ + return event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK; +} + static inline void perf_sample_save_brstack(struct perf_sample_data *data, struct perf_event *event, struct perf_branch_stack *brs, @@ -1269,6 +1332,11 @@ static inline void perf_sample_save_brstack(struct perf_sample_data *data, { int size = sizeof(u64); /* nr */ + if (!has_branch_stack(event)) + return; + if (WARN_ON_ONCE(data->sample_flags & PERF_SAMPLE_BRANCH_STACK)) + return; + if (branch_sample_hw_index(event)) size += sizeof(u64); size += brs->nr * sizeof(struct perf_branch_entry); @@ -1342,8 +1410,10 @@ extern int perf_event_output(struct perf_event *event, struct pt_regs *regs); static inline bool -__is_default_overflow_handler(perf_overflow_handler_t overflow_handler) +is_default_overflow_handler(struct perf_event *event) { + perf_overflow_handler_t overflow_handler = event->overflow_handler; + if (likely(overflow_handler == perf_event_output_forward)) return true; if (unlikely(overflow_handler == perf_event_output_backward)) @@ -1351,22 +1421,6 @@ __is_default_overflow_handler(perf_overflow_handler_t overflow_handler) return false; } -#define is_default_overflow_handler(event) \ - __is_default_overflow_handler((event)->overflow_handler) - -#ifdef CONFIG_BPF_SYSCALL -static inline bool uses_default_overflow_handler(struct perf_event *event) -{ - if (likely(is_default_overflow_handler(event))) - return true; - - return __is_default_overflow_handler(event->orig_overflow_handler); -} -#else -#define uses_default_overflow_handler(event) \ - is_default_overflow_handler(event) -#endif - extern void perf_event_header__init_id(struct perf_event_header *header, struct perf_sample_data *data, @@ -1598,11 +1652,11 @@ extern int sysctl_perf_cpu_time_max_percent; extern void perf_sample_event_took(u64 sample_len_ns); -int perf_event_max_sample_rate_handler(struct ctl_table *table, int write, +int perf_event_max_sample_rate_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); -int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write, +int perf_cpu_time_max_percent_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); -int perf_event_max_stack_handler(struct ctl_table *table, int write, +int perf_event_max_stack_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); /* Access to perf_event_open(2) syscall. */ @@ -1618,13 +1672,7 @@ static inline int perf_is_paranoid(void) return sysctl_perf_event_paranoid > -1; } -static inline int perf_allow_kernel(struct perf_event_attr *attr) -{ - if (sysctl_perf_event_paranoid > 1 && !perfmon_capable()) - return -EACCES; - - return security_perf_event_open(attr, PERF_SECURITY_KERNEL); -} +int perf_allow_kernel(struct perf_event_attr *attr); static inline int perf_allow_cpu(struct perf_event_attr *attr) { @@ -1642,6 +1690,8 @@ static inline int perf_allow_tracepoint(struct perf_event_attr *attr) return security_perf_event_open(attr, PERF_SECURITY_TRACEPOINT); } +extern int perf_exclude_event(struct perf_event *event, struct pt_regs *regs); + extern void perf_event_init(void); extern void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size, struct pt_regs *regs, @@ -1649,19 +1699,34 @@ extern void perf_tp_event(u16 event_type, u64 count, void *record, struct task_struct *task); extern void perf_bp_event(struct perf_event *event, void *data); -#ifndef perf_misc_flags -# define perf_misc_flags(regs) \ +extern unsigned long perf_misc_flags(struct perf_event *event, struct pt_regs *regs); +extern unsigned long perf_instruction_pointer(struct perf_event *event, + struct pt_regs *regs); + +#ifndef perf_arch_misc_flags +# define perf_arch_misc_flags(regs) \ (user_mode(regs) ? PERF_RECORD_MISC_USER : PERF_RECORD_MISC_KERNEL) -# define perf_instruction_pointer(regs) instruction_pointer(regs) +# define perf_arch_instruction_pointer(regs) instruction_pointer(regs) #endif #ifndef perf_arch_bpf_user_pt_regs # define perf_arch_bpf_user_pt_regs(regs) regs #endif -static inline bool has_branch_stack(struct perf_event *event) +#ifndef perf_arch_guest_misc_flags +static inline unsigned long perf_arch_guest_misc_flags(struct pt_regs *regs) { - return event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK; + unsigned long guest_state = perf_guest_state(); + + if (!(guest_state & PERF_GUEST_ACTIVE)) + return 0; + + if (guest_state & PERF_GUEST_USER) + return PERF_RECORD_MISC_GUEST_USER; + else + return PERF_RECORD_MISC_GUEST_KERNEL; } +# define perf_arch_guest_misc_flags(regs) perf_arch_guest_misc_flags(regs) +#endif static inline bool needs_branch_stack(struct perf_event *event) { @@ -1673,6 +1738,13 @@ static inline bool has_aux(struct perf_event *event) return event->pmu->setup_aux; } +static inline bool has_aux_action(struct perf_event *event) +{ + return event->attr.aux_sample_size || + event->attr.aux_pause || + event->attr.aux_resume; +} + static inline bool is_write_backward(struct perf_event *event) { return !!event->attr.write_backward; @@ -1697,6 +1769,14 @@ perf_event_addr_filters(struct perf_event *event) return ifh; } +static inline struct fasync_struct **perf_event_fasync(struct perf_event *event) +{ + /* Only the parent has fasync state */ + if (event->parent) + event = event->parent; + return &event->fasync; +} + extern void perf_event_addr_filters_sync(struct perf_event *event); extern void perf_report_aux_output_id(struct perf_event *event, u64 hw_id); @@ -1817,6 +1897,10 @@ static inline u64 perf_event_pause(struct perf_event *event, bool reset) { return 0; } +static inline int perf_exclude_event(struct perf_event *event, struct pt_regs *regs) +{ + return 0; +} #endif #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL) diff --git a/include/linux/pgalloc_tag.h b/include/linux/pgalloc_tag.h new file mode 100644 index 000000000000..3469c4b20105 --- /dev/null +++ b/include/linux/pgalloc_tag.h @@ -0,0 +1,252 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * page allocation tagging + */ +#ifndef _LINUX_PGALLOC_TAG_H +#define _LINUX_PGALLOC_TAG_H + +#include <linux/alloc_tag.h> + +#ifdef CONFIG_MEM_ALLOC_PROFILING + +#include <linux/page_ext.h> + +extern struct page_ext_operations page_alloc_tagging_ops; +extern unsigned long alloc_tag_ref_mask; +extern int alloc_tag_ref_offs; +extern struct alloc_tag_kernel_section kernel_tags; + +DECLARE_STATIC_KEY_FALSE(mem_profiling_compressed); + +typedef u16 pgalloc_tag_idx; + +union pgtag_ref_handle { + union codetag_ref *ref; /* reference in page extension */ + struct page *page; /* reference in page flags */ +}; + +/* Reserved indexes */ +#define CODETAG_ID_NULL 0 +#define CODETAG_ID_EMPTY 1 +#define CODETAG_ID_FIRST 2 + +#ifdef CONFIG_MODULES + +extern struct alloc_tag_module_section module_tags; + +static inline struct alloc_tag *module_idx_to_tag(pgalloc_tag_idx idx) +{ + return &module_tags.first_tag[idx - kernel_tags.count]; +} + +static inline pgalloc_tag_idx module_tag_to_idx(struct alloc_tag *tag) +{ + return CODETAG_ID_FIRST + kernel_tags.count + (tag - module_tags.first_tag); +} + +#else /* CONFIG_MODULES */ + +static inline struct alloc_tag *module_idx_to_tag(pgalloc_tag_idx idx) +{ + pr_warn("invalid page tag reference %lu\n", (unsigned long)idx); + return NULL; +} + +static inline pgalloc_tag_idx module_tag_to_idx(struct alloc_tag *tag) +{ + pr_warn("invalid page tag 0x%lx\n", (unsigned long)tag); + return CODETAG_ID_NULL; +} + +#endif /* CONFIG_MODULES */ + +static inline void idx_to_ref(pgalloc_tag_idx idx, union codetag_ref *ref) +{ + switch (idx) { + case (CODETAG_ID_NULL): + ref->ct = NULL; + break; + case (CODETAG_ID_EMPTY): + set_codetag_empty(ref); + break; + default: + idx -= CODETAG_ID_FIRST; + ref->ct = idx < kernel_tags.count ? + &kernel_tags.first_tag[idx].ct : + &module_idx_to_tag(idx)->ct; + break; + } +} + +static inline pgalloc_tag_idx ref_to_idx(union codetag_ref *ref) +{ + struct alloc_tag *tag; + + if (!ref->ct) + return CODETAG_ID_NULL; + + if (is_codetag_empty(ref)) + return CODETAG_ID_EMPTY; + + tag = ct_to_alloc_tag(ref->ct); + if (tag >= kernel_tags.first_tag && tag < kernel_tags.first_tag + kernel_tags.count) + return CODETAG_ID_FIRST + (tag - kernel_tags.first_tag); + + return module_tag_to_idx(tag); +} + + + +/* Should be called only if mem_alloc_profiling_enabled() */ +static inline bool get_page_tag_ref(struct page *page, union codetag_ref *ref, + union pgtag_ref_handle *handle) +{ + if (!page) + return false; + + if (static_key_enabled(&mem_profiling_compressed)) { + pgalloc_tag_idx idx; + + idx = (page->flags >> alloc_tag_ref_offs) & alloc_tag_ref_mask; + idx_to_ref(idx, ref); + handle->page = page; + } else { + struct page_ext *page_ext; + union codetag_ref *tmp; + + page_ext = page_ext_get(page); + if (!page_ext) + return false; + + tmp = (union codetag_ref *)page_ext_data(page_ext, &page_alloc_tagging_ops); + ref->ct = tmp->ct; + handle->ref = tmp; + } + + return true; +} + +static inline void put_page_tag_ref(union pgtag_ref_handle handle) +{ + if (WARN_ON(!handle.ref)) + return; + + if (!static_key_enabled(&mem_profiling_compressed)) + page_ext_put((void *)handle.ref - page_alloc_tagging_ops.offset); +} + +static inline void update_page_tag_ref(union pgtag_ref_handle handle, union codetag_ref *ref) +{ + if (static_key_enabled(&mem_profiling_compressed)) { + struct page *page = handle.page; + unsigned long old_flags; + unsigned long flags; + unsigned long idx; + + if (WARN_ON(!page || !ref)) + return; + + idx = (unsigned long)ref_to_idx(ref); + idx = (idx & alloc_tag_ref_mask) << alloc_tag_ref_offs; + do { + old_flags = READ_ONCE(page->flags); + flags = old_flags; + flags &= ~(alloc_tag_ref_mask << alloc_tag_ref_offs); + flags |= idx; + } while (unlikely(!try_cmpxchg(&page->flags, &old_flags, flags))); + } else { + if (WARN_ON(!handle.ref || !ref)) + return; + + handle.ref->ct = ref->ct; + } +} + +static inline void clear_page_tag_ref(struct page *page) +{ + if (mem_alloc_profiling_enabled()) { + union pgtag_ref_handle handle; + union codetag_ref ref; + + if (get_page_tag_ref(page, &ref, &handle)) { + set_codetag_empty(&ref); + update_page_tag_ref(handle, &ref); + put_page_tag_ref(handle); + } + } +} + +static inline void pgalloc_tag_add(struct page *page, struct task_struct *task, + unsigned int nr) +{ + if (mem_alloc_profiling_enabled()) { + union pgtag_ref_handle handle; + union codetag_ref ref; + + if (get_page_tag_ref(page, &ref, &handle)) { + alloc_tag_add(&ref, task->alloc_tag, PAGE_SIZE * nr); + update_page_tag_ref(handle, &ref); + put_page_tag_ref(handle); + } + } +} + +static inline void pgalloc_tag_sub(struct page *page, unsigned int nr) +{ + if (mem_alloc_profiling_enabled()) { + union pgtag_ref_handle handle; + union codetag_ref ref; + + if (get_page_tag_ref(page, &ref, &handle)) { + alloc_tag_sub(&ref, PAGE_SIZE * nr); + update_page_tag_ref(handle, &ref); + put_page_tag_ref(handle); + } + } +} + +static inline struct alloc_tag *pgalloc_tag_get(struct page *page) +{ + struct alloc_tag *tag = NULL; + + if (mem_alloc_profiling_enabled()) { + union pgtag_ref_handle handle; + union codetag_ref ref; + + if (get_page_tag_ref(page, &ref, &handle)) { + alloc_tag_sub_check(&ref); + if (ref.ct) + tag = ct_to_alloc_tag(ref.ct); + put_page_tag_ref(handle); + } + } + + return tag; +} + +static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr) +{ + if (mem_alloc_profiling_enabled() && tag) + this_cpu_sub(tag->counters->bytes, PAGE_SIZE * nr); +} + +void pgalloc_tag_split(struct folio *folio, int old_order, int new_order); +void pgalloc_tag_swap(struct folio *new, struct folio *old); + +void __init alloc_tag_sec_init(void); + +#else /* CONFIG_MEM_ALLOC_PROFILING */ + +static inline void clear_page_tag_ref(struct page *page) {} +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 struct alloc_tag *pgalloc_tag_get(struct page *page) { return NULL; } +static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr) {} +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) {} + +#endif /* CONFIG_MEM_ALLOC_PROFILING */ + +#endif /* _LINUX_PGALLOC_TAG_H */ diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 85fc7554cd52..94d267d02372 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -50,6 +50,8 @@ #define pmd_pgtable(pmd) pmd_page(pmd) #endif +#define pmd_folio(pmd) page_folio(pmd_page(pmd)) + /* * A page table page can be thought of an array like this: pXd_t[PTRS_PER_PxD] * @@ -88,6 +90,27 @@ static inline unsigned long pud_index(unsigned long address) #define pgd_index(a) (((a) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1)) #endif +#ifndef kernel_pte_init +static inline void kernel_pte_init(void *addr) +{ +} +#define kernel_pte_init kernel_pte_init +#endif + +#ifndef pmd_init +static inline void pmd_init(void *addr) +{ +} +#define pmd_init pmd_init +#endif + +#ifndef pud_init +static inline void pud_init(void *addr) +{ +} +#define pud_init pud_init +#endif + #ifndef pte_offset_kernel static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long address) { @@ -149,9 +172,7 @@ static inline pgd_t *pgd_offset_pgd(pgd_t *pgd, unsigned long address) * a shortcut which implies the use of the kernel's pgd, instead * of a process's */ -#ifndef pgd_offset_k #define pgd_offset_k(address) pgd_offset(&init_mm, (address)) -#endif /* * In many cases it is known that a virtual address is mapped at PMD or PTE @@ -447,6 +468,12 @@ static inline void arch_check_zapped_pmd(struct vm_area_struct *vma, } #endif +#ifndef arch_check_zapped_pud +static inline void arch_check_zapped_pud(struct vm_area_struct *vma, pud_t pud) +{ +} +#endif + #ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long address, @@ -459,10 +486,61 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, } #endif +#ifndef clear_young_dirty_ptes +/** + * clear_young_dirty_ptes - Mark PTEs that map consecutive pages of the + * same folio as old/clean. + * @mm: Address space the pages are mapped into. + * @addr: Address the first page is mapped at. + * @ptep: Page table pointer for the first entry. + * @nr: Number of entries to mark old/clean. + * @flags: Flags to modify the PTE batch semantics. + * + * May be overridden by the architecture; otherwise, implemented by + * get_and_clear/modify/set for each pte in the range. + * + * Note that PTE bits in the PTE range besides the PFN can differ. For example, + * some PTEs might be write-protected. + * + * Context: The caller holds the page table lock. The PTEs map consecutive + * pages that belong to the same folio. The PTEs are all in the same PMD. + */ +static inline void clear_young_dirty_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + unsigned int nr, cydp_t flags) +{ + pte_t pte; + + for (;;) { + if (flags == CYDP_CLEAR_YOUNG) + ptep_test_and_clear_young(vma, addr, ptep); + else { + pte = ptep_get_and_clear(vma->vm_mm, addr, ptep); + if (flags & CYDP_CLEAR_YOUNG) + pte = pte_mkold(pte); + if (flags & CYDP_CLEAR_DIRTY) + pte = pte_mkclean(pte); + set_pte_at(vma->vm_mm, addr, ptep, pte); + } + if (--nr == 0) + break; + ptep++; + addr += PAGE_SIZE; + } +} +#endif + static inline void ptep_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - ptep_get_and_clear(mm, addr, ptep); + pte_t pte = ptep_get(ptep); + + pte_clear(mm, addr, ptep); + /* + * No need for ptep_get_and_clear(): page table check doesn't care about + * any bits that could have been set by HW concurrently. + */ + page_table_check_pte_clear(mm, pte); } #ifdef CONFIG_GUP_GET_PXX_LOW_HIGH @@ -685,13 +763,18 @@ static inline void clear_full_ptes(struct mm_struct *mm, unsigned long addr, * fault. This function updates TLB only, do nothing with cache or others. * It is the difference with function update_mmu_cache. */ -#ifndef __HAVE_ARCH_UPDATE_MMU_TLB +#ifndef update_mmu_tlb_range +static inline void update_mmu_tlb_range(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep, unsigned int nr) +{ +} +#endif + static inline void update_mmu_tlb(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { + update_mmu_tlb_range(vma, address, ptep, 1); } -#define __HAVE_ARCH_UPDATE_MMU_TLB -#endif /* * Some architectures may be able to avoid expensive synchronization @@ -708,6 +791,35 @@ static inline void pte_clear_not_present_full(struct mm_struct *mm, } #endif +#ifndef clear_not_present_full_ptes +/** + * clear_not_present_full_ptes - Clear multiple not present PTEs which are + * consecutive in the pgtable. + * @mm: Address space the ptes represent. + * @addr: Address of the first pte. + * @ptep: Page table pointer for the first entry. + * @nr: Number of entries to clear. + * @full: Whether we are clearing a full mm. + * + * May be overridden by the architecture; otherwise, implemented as a simple + * loop over pte_clear_not_present_full(). + * + * Context: The caller holds the page table lock. The PTEs are all not present. + * The PTEs are all in the same PMD. + */ +static inline void clear_not_present_full_ptes(struct mm_struct *mm, + unsigned long addr, pte_t *ptep, unsigned int nr, int full) +{ + for (;;) { + pte_clear_not_present_full(mm, addr, ptep, full); + if (--nr == 0) + break; + ptep++; + addr += PAGE_SIZE; + } +} +#endif + #ifndef __HAVE_ARCH_PTEP_CLEAR_FLUSH extern pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long address, @@ -972,45 +1084,16 @@ static inline int pgd_same(pgd_t pgd_a, pgd_t pgd_b) } #endif -/* - * Use set_p*_safe(), and elide TLB flushing, when confident that *no* - * TLB flush will be required as a result of the "set". For example, use - * in scenarios where it is known ahead of time that the routine is - * setting non-present entries, or re-setting an existing entry to the - * same value. Otherwise, use the typical "set" helpers and flush the - * TLB. - */ -#define set_pte_safe(ptep, pte) \ -({ \ - WARN_ON_ONCE(pte_present(*ptep) && !pte_same(*ptep, pte)); \ - set_pte(ptep, pte); \ -}) - -#define set_pmd_safe(pmdp, pmd) \ -({ \ - WARN_ON_ONCE(pmd_present(*pmdp) && !pmd_same(*pmdp, pmd)); \ - set_pmd(pmdp, pmd); \ -}) - -#define set_pud_safe(pudp, pud) \ -({ \ - WARN_ON_ONCE(pud_present(*pudp) && !pud_same(*pudp, pud)); \ - set_pud(pudp, pud); \ -}) - -#define set_p4d_safe(p4dp, p4d) \ -({ \ - WARN_ON_ONCE(p4d_present(*p4dp) && !p4d_same(*p4dp, p4d)); \ - set_p4d(p4dp, p4d); \ -}) - -#define set_pgd_safe(pgdp, pgd) \ -({ \ - WARN_ON_ONCE(pgd_present(*pgdp) && !pgd_same(*pgdp, pgd)); \ - set_pgd(pgdp, pgd); \ -}) - #ifndef __HAVE_ARCH_DO_SWAP_PAGE +static inline void arch_do_swap_page_nr(struct mm_struct *mm, + struct vm_area_struct *vma, + unsigned long addr, + pte_t pte, pte_t oldpte, + int nr) +{ + +} +#else /* * Some architectures support metadata associated with a page. When a * page is being swapped out, this metadata must be saved so it can be @@ -1019,12 +1102,17 @@ static inline int pgd_same(pgd_t pgd_a, pgd_t pgd_b) * page as metadata for the page. arch_do_swap_page() can restore this * metadata when a page is swapped back in. */ -static inline void arch_do_swap_page(struct mm_struct *mm, - struct vm_area_struct *vma, - unsigned long addr, - pte_t pte, pte_t oldpte) +static inline void arch_do_swap_page_nr(struct mm_struct *mm, + struct vm_area_struct *vma, + unsigned long addr, + pte_t pte, pte_t oldpte, + int nr) { - + for (int i = 0; i < nr; i++) { + arch_do_swap_page(vma->vm_mm, vma, addr + i * PAGE_SIZE, + pte_advance_pfn(pte, i), + pte_advance_pfn(oldpte, i)); + } } #endif @@ -1052,7 +1140,7 @@ static inline int arch_unmap_one(struct mm_struct *mm, * prototypes must be defined in the arch-specific asm/pgtable.h file. */ #ifndef __HAVE_ARCH_PREPARE_TO_SWAP -static inline int arch_prepare_to_swap(struct page *page) +static inline int arch_prepare_to_swap(struct folio *folio) { return 0; } @@ -1079,7 +1167,7 @@ static inline void arch_swap_restore(swp_entry_t entry, struct folio *folio) #endif #ifndef __HAVE_ARCH_MOVE_PTE -#define move_pte(pte, prot, old_addr, new_addr) (pte) +#define move_pte(pte, old_addr, new_addr) (pte) #endif #ifndef pte_accessible @@ -1770,11 +1858,25 @@ typedef unsigned int pgtbl_mod_mask; #endif /* - * p?d_leaf() - true if this entry is a final mapping to a physical address. - * This differs from p?d_huge() by the fact that they are always available (if - * the architecture supports large pages at the appropriate level) even - * if CONFIG_HUGETLB_PAGE is not defined. - * Only meaningful when called on a valid entry. + * pXd_leaf() is the API to check whether a pgtable entry is a huge page + * mapping. It should work globally across all archs, without any + * dependency on CONFIG_* options. For architectures that do not support + * huge mappings on specific levels, below fallbacks will be used. + * + * A leaf pgtable entry should always imply the following: + * + * - It is a "present" entry. IOW, before using this API, please check it + * with pXd_present() first. NOTE: it may not always mean the "present + * bit" is set. For example, PROT_NONE entries are always "present". + * + * - It should _never_ be a swap entry of any type. Above "present" check + * should have guarded this, but let's be crystal clear on this. + * + * - It should contain a huge PFN, which points to a huge page larger than + * PAGE_SIZE of the platform. The PFN format isn't important here. + * + * - It should cover all kinds of huge mappings (e.g., pXd_trans_huge(), + * pXd_devmap(), or hugetlb mappings). */ #ifndef pgd_leaf #define pgd_leaf(x) false @@ -1801,9 +1903,26 @@ typedef unsigned int pgtbl_mod_mask; #ifndef pmd_leaf_size #define pmd_leaf_size(x) PMD_SIZE #endif +#ifndef __pte_leaf_size #ifndef pte_leaf_size #define pte_leaf_size(x) PAGE_SIZE #endif +#define __pte_leaf_size(x,y) pte_leaf_size(y) +#endif + +/* + * We always define pmd_pfn for all archs as it's used in lots of generic + * code. Now it happens too for pud_pfn (and can happen for larger + * mappings too in the future; we're not there yet). Instead of defining + * it for all archs (like pmd_pfn), provide a fallback. + * + * Note that returning 0 here means any arch that didn't define this can + * get severely wrong when it hits a real pud leaf. It's arch's + * responsibility to properly define it when a huge pud is possible. + */ +#ifndef pud_pfn +#define pud_pfn(x) 0 +#endif /* * Some architectures have MMUs that are configurable or selectable at boot @@ -1827,6 +1946,18 @@ typedef unsigned int pgtbl_mod_mask; #define MAX_PTRS_PER_P4D PTRS_PER_P4D #endif +#ifndef pte_pgprot +#define pte_pgprot(x) ((pgprot_t) {0}) +#endif + +#ifndef pmd_pgprot +#define pmd_pgprot(x) ((pgprot_t) {0}) +#endif + +#ifndef pud_pgprot +#define pud_pgprot(x) ((pgprot_t) {0}) +#endif + /* description of effects of mapping type and prot in current implementation. * this is due to the limited x86 page protection hardware. The expected * behavior is in parens: diff --git a/include/linux/phy.h b/include/linux/phy.h index 3f68b8239bb1..19f076a71f94 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -32,19 +32,6 @@ #include <linux/atomic.h> #include <net/eee.h> -#define PHY_DEFAULT_FEATURES (SUPPORTED_Autoneg | \ - SUPPORTED_TP | \ - SUPPORTED_MII) - -#define PHY_10BT_FEATURES (SUPPORTED_10baseT_Half | \ - SUPPORTED_10baseT_Full) - -#define PHY_100BT_FEATURES (SUPPORTED_100baseT_Half | \ - SUPPORTED_100baseT_Full) - -#define PHY_1000BT_FEATURES (SUPPORTED_1000baseT_Half | \ - SUPPORTED_1000baseT_Full) - extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_t1_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_t1s_p2mp_features) __ro_after_init; @@ -62,16 +49,11 @@ extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_eee_cap2_features) __ro_after_init; #define PHY_BASIC_T1S_P2MP_FEATURES ((unsigned long *)&phy_basic_t1s_p2mp_features) #define PHY_GBIT_FEATURES ((unsigned long *)&phy_gbit_features) #define PHY_GBIT_FIBRE_FEATURES ((unsigned long *)&phy_gbit_fibre_features) -#define PHY_GBIT_ALL_PORTS_FEATURES ((unsigned long *)&phy_gbit_all_ports_features) #define PHY_10GBIT_FEATURES ((unsigned long *)&phy_10gbit_features) -#define PHY_10GBIT_FEC_FEATURES ((unsigned long *)&phy_10gbit_fec_features) -#define PHY_10GBIT_FULL_FEATURES ((unsigned long *)&phy_10gbit_full_features) #define PHY_EEE_CAP1_FEATURES ((unsigned long *)&phy_eee_cap1_features) #define PHY_EEE_CAP2_FEATURES ((unsigned long *)&phy_eee_cap2_features) extern const int phy_basic_ports_array[3]; -extern const int phy_fibre_port_array[1]; -extern const int phy_all_ports_features_array[7]; extern const int phy_10_100_features_array[4]; extern const int phy_basic_t1_features_array[3]; extern const int phy_basic_t1s_p2mp_features_array[2]; @@ -128,6 +110,7 @@ extern const int phy_10gbit_features_array[1]; * @PHY_INTERFACE_MODE_10GKR: 10GBASE-KR - with Clause 73 AN * @PHY_INTERFACE_MODE_QUSGMII: Quad Universal SGMII * @PHY_INTERFACE_MODE_1000BASEKX: 1000Base-KX - with Clause 73 AN + * @PHY_INTERFACE_MODE_10G_QXGMII: 10G-QXGMII - 4 ports over 10G USXGMII * @PHY_INTERFACE_MODE_MAX: Book keeping * * Describes the interface between the MAC and PHY. @@ -168,6 +151,7 @@ typedef enum { PHY_INTERFACE_MODE_10GKR, PHY_INTERFACE_MODE_QUSGMII, PHY_INTERFACE_MODE_1000BASEKX, + PHY_INTERFACE_MODE_10G_QXGMII, PHY_INTERFACE_MODE_MAX, } phy_interface_t; @@ -289,11 +273,36 @@ static inline const char *phy_modes(phy_interface_t interface) return "100base-x"; case PHY_INTERFACE_MODE_QUSGMII: return "qusgmii"; + case PHY_INTERFACE_MODE_10G_QXGMII: + return "10g-qxgmii"; default: return "unknown"; } } +/** + * rgmii_clock - map link speed to the clock rate + * @speed: link speed value + * + * Description: maps RGMII supported link speeds + * into the clock rates. + * + * Returns: clock rate or negative errno + */ +static inline long rgmii_clock(int speed) +{ + switch (speed) { + case SPEED_10: + return 2500000; + case SPEED_100: + return 25000000; + case SPEED_1000: + return 125000000; + default: + return -EINVAL; + } +} + #define PHY_INIT_TIMEOUT 100000 #define PHY_FORCE_TIMEOUT 10 @@ -550,6 +559,9 @@ struct macsec_ops; * @drv: Pointer to the driver for this PHY instance * @devlink: Create a link between phy dev and mac dev, if the external phy * used by current mac interface is managed by another mac interface. + * @phyindex: Unique id across the phy's parent tree of phys to address the PHY + * from userspace, similar to ifindex. A zero index means the PHY + * wasn't assigned an id yet. * @phy_id: UID for this device found during discovery * @c45_ids: 802.3-c45 Device Identifiers if is_c45. * @is_c45: Set to true if this PHY uses clause 45 addressing. @@ -594,8 +606,8 @@ struct macsec_ops; * @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 * @enable_tx_lpi: When True, MAC should transmit LPI to PHY + * @eee_active: phylib private state, indicating that EEE has been negotiated * @eee_cfg: User configuration of EEE * @lp_advertising: Current link partner advertised linkmodes * @host_interfaces: PHY interface modes supported by host @@ -612,6 +624,8 @@ struct macsec_ops; * handling shall be postponed until PHY has resumed * @irq_rerun: Flag indicating interrupts occurred while PHY was suspended, * requiring a rerun of the interrupt handler after resume + * @default_timestamp: Flag indicating whether we are using the phy + * timestamp as the default one * @interface: enum phy_interface_t value * @possible_interfaces: bitmap if interface modes that the attached PHY * will switch between depending on media speed. @@ -650,6 +664,7 @@ struct phy_device { struct device_link *devlink; + u32 phyindex; u32 phy_id; struct phy_c45_device_ids c45_ids; @@ -677,6 +692,8 @@ struct phy_device { unsigned irq_suspended:1; unsigned irq_rerun:1; + unsigned default_timestamp:1; + int rate_matching; enum phy_state state; @@ -709,16 +726,15 @@ struct phy_device { /* used for eee validation and configuration*/ __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); - /* Energy efficient ethernet modes which should be prohibited */ - u32 eee_broken_modes; + __ETHTOOL_DECLARE_LINK_MODE_MASK(eee_broken_modes); bool enable_tx_lpi; + bool eee_active; struct eee_config eee_cfg; + /* Host supported PHY interface types. Should be ignored if empty. */ + DECLARE_PHY_INTERFACE_MASK(host_interfaces); + #ifdef CONFIG_LED_TRIGGER_PHY struct phy_led_trigger *phy_led_triggers; unsigned int phy_num_led_triggers; @@ -778,6 +794,7 @@ struct phy_device { /* Generic phy_device::dev_flags */ #define PHY_F_NO_IRQ 0x80000000 +#define PHY_F_RXC_ALWAYS_ON 0x40000000 static inline struct phy_device *to_phy_device(const struct device *dev) { @@ -806,6 +823,24 @@ struct phy_tdr_config { #define PHY_PAIR_ALL -1 /** + * enum link_inband_signalling - in-band signalling modes that are supported + * + * @LINK_INBAND_DISABLE: in-band signalling can be disabled + * @LINK_INBAND_ENABLE: in-band signalling can be enabled without bypass + * @LINK_INBAND_BYPASS: in-band signalling can be enabled with bypass + * + * The possible and required bits can only be used if the valid bit is set. + * If possible is clear, that means inband signalling can not be used. + * Required is only valid when possible is set, and means that inband + * signalling must be used. + */ +enum link_inband_signalling { + LINK_INBAND_DISABLE = BIT(0), + LINK_INBAND_ENABLE = BIT(1), + LINK_INBAND_BYPASS = BIT(2), +}; + +/** * struct phy_plca_cfg - Configuration of the PLCA (Physical Layer Collision * Avoidance) Reconciliation Sublayer. * @@ -864,8 +899,9 @@ struct phy_plca_status { /* Modes for PHY LED configuration */ enum phy_led_modes { - PHY_LED_ACTIVE_LOW = 0, - PHY_LED_INACTIVE_HIGH_IMPEDANCE = 1, + PHY_LED_ACTIVE_HIGH = 0, + PHY_LED_ACTIVE_LOW = 1, + PHY_LED_INACTIVE_HIGH_IMPEDANCE = 2, /* keep it last */ __PHY_LED_MODES_NUM, @@ -944,6 +980,19 @@ struct phy_driver { int (*get_features)(struct phy_device *phydev); /** + * @inband_caps: query whether in-band is supported for the given PHY + * interface mode. Returns a bitmask of bits defined by enum + * link_inband_signalling. + */ + unsigned int (*inband_caps)(struct phy_device *phydev, + phy_interface_t interface); + + /** + * @config_inband: configure in-band mode for the PHY + */ + int (*config_inband)(struct phy_device *phydev, unsigned int modes); + + /** * @get_rate_matching: Get the supported type of rate matching for a * particular phy interface. This is used by phy consumers to determine * whether to advertise lower-speed modes for that interface. It is @@ -1077,6 +1126,53 @@ struct phy_driver { int (*cable_test_get_status)(struct phy_device *dev, bool *finished); /* Get statistics from the PHY using ethtool */ + /** + * @get_phy_stats: Retrieve PHY statistics. + * @dev: The PHY device for which the statistics are retrieved. + * @eth_stats: structure where Ethernet PHY stats will be stored. + * @stats: structure where additional PHY-specific stats will be stored. + * + * Retrieves the supported PHY statistics and populates the provided + * structures. The input structures are pre-initialized with + * `ETHTOOL_STAT_NOT_SET`, and the driver must only modify members + * corresponding to supported statistics. Unmodified members will remain + * set to `ETHTOOL_STAT_NOT_SET` and will not be returned to userspace. + */ + void (*get_phy_stats)(struct phy_device *dev, + struct ethtool_eth_phy_stats *eth_stats, + struct ethtool_phy_stats *stats); + + /** + * @get_link_stats: Retrieve link statistics. + * @dev: The PHY device for which the statistics are retrieved. + * @link_stats: structure where link-specific stats will be stored. + * + * Retrieves link-related statistics for the given PHY device. The input + * structure is pre-initialized with `ETHTOOL_STAT_NOT_SET`, and the + * driver must only modify members corresponding to supported + * statistics. Unmodified members will remain set to + * `ETHTOOL_STAT_NOT_SET` and will not be returned to userspace. + */ + void (*get_link_stats)(struct phy_device *dev, + struct ethtool_link_ext_stats *link_stats); + + /** + * @update_stats: Trigger periodic statistics updates. + * @dev: The PHY device for which statistics updates are triggered. + * + * Periodically gathers statistics from the PHY device to update locally + * maintained 64-bit counters. This is necessary for PHYs that implement + * reduced-width counters (e.g., 16-bit or 32-bit) which can overflow + * more frequently compared to 64-bit counters. By invoking this + * callback, drivers can fetch the current counter values, handle + * overflow detection, and accumulate the results into local 64-bit + * counters for accurate reporting through the `get_phy_stats` and + * `get_link_stats` interfaces. + * + * Return: 0 on success or a negative error code on failure. + */ + int (*update_stats)(struct phy_device *dev); + /** @get_sset_count: Number of statistic counters */ int (*get_sset_count)(struct phy_device *dev); /** @get_strings: Names of the statistic counters */ @@ -1121,7 +1217,7 @@ struct phy_driver { u8 index, enum led_brightness value); /** - * @led_blink_set: Set a PHY LED brightness. Index indicates + * @led_blink_set: Set a PHY LED blinking. Index indicates * which of the PHYs led should be configured to blink. Delays * are in milliseconds and if both are zero then a sensible * default should be chosen. The call should adjust the @@ -1178,7 +1274,7 @@ struct phy_driver { int (*led_polarity_set)(struct phy_device *dev, int index, unsigned long modes); }; -#define to_phy_driver(d) container_of(to_mdio_common_driver(d), \ +#define to_phy_driver(d) container_of_const(to_mdio_common_driver(d), \ struct phy_driver, mdiodrv) #define PHY_ANY_ID "MATCH ANY PHY" @@ -1247,9 +1343,20 @@ size_t phy_speeds(unsigned int *speeds, size_t size, unsigned long *mask); void of_set_phy_supported(struct phy_device *phydev); void of_set_phy_eee_broken(struct phy_device *phydev); +void of_set_phy_timing_role(struct phy_device *phydev); int phy_speed_down_core(struct phy_device *phydev); /** + * phy_set_eee_broken - Mark an EEE mode as broken so that it isn't advertised. + * @phydev: The phy_device struct + * @link_mode: The broken EEE mode + */ +static inline void phy_set_eee_broken(struct phy_device *phydev, u32 link_mode) +{ + linkmode_set_bit(link_mode, phydev->eee_broken_modes); +} + +/** * phy_is_started - Convenience function to check whether PHY is started * @phydev: The phy_device struct */ @@ -1365,12 +1472,13 @@ int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum); * @regnum: The register on the MMD to read * @val: Variable to read the register into * @cond: Break condition (usually involving @val) - * @sleep_us: Maximum time to sleep between reads in us (0 - * tight-loops). Should be less than ~20ms since usleep_range - * is used (see Documentation/timers/timers-howto.rst). + * @sleep_us: Maximum time to sleep between reads in us (0 tight-loops). Please + * read usleep_range() function description for details and + * limitations. * @timeout_us: Timeout in us, 0 means never timeout * @sleep_before_read: if it is true, sleep @sleep_us before read. - * Returns 0 on success and -ETIMEDOUT upon a timeout. In either + * + * Returns: 0 on success and -ETIMEDOUT upon a timeout. In either * case, the last read value at @args is stored in @val. Must not * be called from atomic context if sleep_us or timeout_us are used. */ @@ -1555,6 +1663,9 @@ static inline bool phy_polling_mode(struct phy_device *phydev) if (phydev->drv->flags & PHY_POLL_CABLE_TEST) return true; + if (phydev->drv->update_stats) + return true; + return phydev->irq == PHY_POLL; } @@ -1609,7 +1720,7 @@ static inline bool phy_rxtstamp(struct phy_device *phydev, struct sk_buff *skb, } static inline int phy_ts_info(struct phy_device *phydev, - struct ethtool_ts_info *tsinfo) + struct kernel_ethtool_ts_info *tsinfo) { return phydev->mii_ts->ts_info(phydev->mii_ts, tsinfo); } @@ -1621,6 +1732,21 @@ static inline void phy_txtstamp(struct phy_device *phydev, struct sk_buff *skb, } /** + * phy_is_default_hwtstamp - Is the PHY hwtstamp the default timestamp + * @phydev: Pointer to phy_device + * + * This is used to get default timestamping device taking into account + * the new API choice, which is selecting the timestamping from MAC by + * default if the phydev does not have default_timestamp flag enabled. + * + * Return: True if phy is the default hw timestamp, false otherwise. + */ +static inline bool phy_is_default_hwtstamp(struct phy_device *phydev) +{ + return phy_has_hwtstamp(phydev) && phydev->default_timestamp; +} + +/** * phy_is_internal - Convenience function for testing if a PHY is internal * @phydev: the phy_device struct */ @@ -1753,6 +1879,8 @@ int phy_suspend(struct phy_device *phydev); int phy_resume(struct phy_device *phydev); int __phy_resume(struct phy_device *phydev); int phy_loopback(struct phy_device *phydev, bool enable); +int phy_sfp_connect_phy(void *upstream, struct phy_device *phy); +void phy_sfp_disconnect_phy(void *upstream, struct phy_device *phy); void phy_sfp_attach(void *upstream, struct sfp_bus *bus); void phy_sfp_detach(void *upstream, struct sfp_bus *bus); int phy_sfp_probe(struct phy_device *phydev, @@ -1776,6 +1904,9 @@ int phy_config_aneg(struct phy_device *phydev); int _phy_start_aneg(struct phy_device *phydev); int phy_start_aneg(struct phy_device *phydev); int phy_aneg_done(struct phy_device *phydev); +unsigned int phy_inband_caps(struct phy_device *phydev, + phy_interface_t interface); +int phy_config_inband(struct phy_device *phydev, unsigned int modes); int phy_speed_down(struct phy_device *phydev, bool sync); int phy_speed_up(struct phy_device *phydev); bool phy_check_valid(int speed, int duplex, unsigned long *features); @@ -1853,7 +1984,6 @@ int genphy_read_abilities(struct phy_device *phydev); int genphy_setup_forced(struct phy_device *phydev); int genphy_restart_aneg(struct phy_device *phydev); int genphy_check_and_restart_aneg(struct phy_device *phydev, bool restart); -int genphy_config_eee_advert(struct phy_device *phydev); int __genphy_config_aneg(struct phy_device *phydev, bool changed); int genphy_aneg_done(struct phy_device *phydev); int genphy_update_link(struct phy_device *phydev); @@ -1916,12 +2046,11 @@ int genphy_c45_plca_set_cfg(struct phy_device *phydev, int genphy_c45_plca_get_status(struct phy_device *phydev, struct phy_plca_status *plca_st); int genphy_c45_eee_is_active(struct phy_device *phydev, unsigned long *adv, - unsigned long *lp, bool *is_enabled); + unsigned long *lp); int genphy_c45_ethtool_get_eee(struct phy_device *phydev, struct ethtool_keee *data); int genphy_c45_ethtool_set_eee(struct phy_device *phydev, struct ethtool_keee *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); @@ -1974,6 +2103,7 @@ void phy_advertise_eee_all(struct phy_device *phydev); void phy_support_sym_pause(struct phy_device *phydev); void phy_support_asym_pause(struct phy_device *phydev); void phy_support_eee(struct phy_device *phydev); +void phy_disable_eee(struct phy_device *phydev); void phy_set_sym_pause(struct phy_device *phydev, bool rx, bool tx, bool autoneg); void phy_set_asym_pause(struct phy_device *phydev, bool rx, bool tx); @@ -1998,6 +2128,8 @@ int phy_unregister_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask); int phy_unregister_fixup_for_id(const char *bus_id); int phy_unregister_fixup_for_uid(u32 phy_uid, u32 phy_uid_mask); +int phy_eee_tx_clock_stop_capable(struct phy_device *phydev); +int phy_eee_rx_clock_stop(struct phy_device *phydev, bool clk_stop_enable); int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable); int phy_get_eee_err(struct phy_device *phydev); int phy_ethtool_set_eee(struct phy_device *phydev, struct ethtool_keee *data); @@ -2025,6 +2157,13 @@ int phy_ethtool_get_strings(struct phy_device *phydev, u8 *data); int phy_ethtool_get_sset_count(struct phy_device *phydev); int phy_ethtool_get_stats(struct phy_device *phydev, struct ethtool_stats *stats, u64 *data); + +void __phy_ethtool_get_phy_stats(struct phy_device *phydev, + struct ethtool_eth_phy_stats *phy_stats, + struct ethtool_phy_stats *phydev_stats); +void __phy_ethtool_get_link_ext_stats(struct phy_device *phydev, + struct ethtool_link_ext_stats *link_stats); + int phy_ethtool_get_plca_cfg(struct phy_device *phydev, struct phy_plca_cfg *plca_cfg); int phy_ethtool_set_plca_cfg(struct phy_device *phydev, diff --git a/include/linux/phy/phy-sun4i-usb.h b/include/linux/phy/phy-sun4i-usb.h index 91eb755ee73b..f3e7b13608e4 100644 --- a/include/linux/phy/phy-sun4i-usb.h +++ b/include/linux/phy/phy-sun4i-usb.h @@ -11,7 +11,7 @@ /** * sun4i_usb_phy_set_squelch_detect() - Enable/disable squelch detect * @phy: reference to a sun4i usb phy - * @enabled: wether to enable or disable squelch detect + * @enabled: whether to enable or disable squelch detect */ void sun4i_usb_phy_set_squelch_detect(struct phy *phy, bool enabled); diff --git a/include/linux/phy_link_topology.h b/include/linux/phy_link_topology.h new file mode 100644 index 000000000000..68a59e25821c --- /dev/null +++ b/include/linux/phy_link_topology.h @@ -0,0 +1,82 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * PHY device list allow maintaining a list of PHY devices that are + * part of a netdevice's link topology. PHYs can for example be chained, + * as is the case when using a PHY that exposes an SFP module, on which an + * SFP transceiver that embeds a PHY is connected. + * + * This list can then be used by userspace to leverage individual PHY + * capabilities. + */ +#ifndef __PHY_LINK_TOPOLOGY_H +#define __PHY_LINK_TOPOLOGY_H + +#include <linux/ethtool.h> +#include <linux/netdevice.h> + +struct xarray; +struct phy_device; +struct sfp_bus; + +struct phy_link_topology { + struct xarray phys; + u32 next_phy_index; +}; + +struct phy_device_node { + enum phy_upstream upstream_type; + + union { + struct net_device *netdev; + struct phy_device *phydev; + } upstream; + + struct sfp_bus *parent_sfp_bus; + + struct phy_device *phy; +}; + +#if IS_ENABLED(CONFIG_PHYLIB) +int phy_link_topo_add_phy(struct net_device *dev, + struct phy_device *phy, + enum phy_upstream upt, void *upstream); + +void phy_link_topo_del_phy(struct net_device *dev, struct phy_device *phy); + +static inline struct phy_device * +phy_link_topo_get_phy(struct net_device *dev, u32 phyindex) +{ + struct phy_link_topology *topo = dev->link_topo; + struct phy_device_node *pdn; + + if (!topo) + return NULL; + + pdn = xa_load(&topo->phys, phyindex); + if (pdn) + return pdn->phy; + + return NULL; +} + +#else +static inline int phy_link_topo_add_phy(struct net_device *dev, + struct phy_device *phy, + enum phy_upstream upt, void *upstream) +{ + return 0; +} + +static inline void phy_link_topo_del_phy(struct net_device *dev, + struct phy_device *phy) +{ +} + +static inline struct phy_device * +phy_link_topo_get_phy(struct net_device *dev, u32 phyindex) +{ + return NULL; +} +#endif + +#endif /* __PHY_LINK_TOPOLOGY_H */ diff --git a/include/linux/phylib_stubs.h b/include/linux/phylib_stubs.h index 1279f48c8a70..9d2d6090c86d 100644 --- a/include/linux/phylib_stubs.h +++ b/include/linux/phylib_stubs.h @@ -5,6 +5,9 @@ #include <linux/rtnetlink.h> +struct ethtool_eth_phy_stats; +struct ethtool_link_ext_stats; +struct ethtool_phy_stats; struct kernel_hwtstamp_config; struct netlink_ext_ack; struct phy_device; @@ -19,6 +22,11 @@ struct phylib_stubs { int (*hwtstamp_set)(struct phy_device *phydev, struct kernel_hwtstamp_config *config, struct netlink_ext_ack *extack); + void (*get_phy_stats)(struct phy_device *phydev, + struct ethtool_eth_phy_stats *phy_stats, + struct ethtool_phy_stats *phydev_stats); + void (*get_link_ext_stats)(struct phy_device *phydev, + struct ethtool_link_ext_stats *link_stats); }; static inline int phy_hwtstamp_get(struct phy_device *phydev, @@ -50,6 +58,29 @@ static inline int phy_hwtstamp_set(struct phy_device *phydev, return phylib_stubs->hwtstamp_set(phydev, config, extack); } +static inline void phy_ethtool_get_phy_stats(struct phy_device *phydev, + struct ethtool_eth_phy_stats *phy_stats, + struct ethtool_phy_stats *phydev_stats) +{ + ASSERT_RTNL(); + + if (!phylib_stubs) + return; + + phylib_stubs->get_phy_stats(phydev, phy_stats, phydev_stats); +} + +static inline void phy_ethtool_get_link_ext_stats(struct phy_device *phydev, + struct ethtool_link_ext_stats *link_stats) +{ + ASSERT_RTNL(); + + if (!phylib_stubs) + return; + + phylib_stubs->get_link_ext_stats(phydev, link_stats); +} + #else static inline int phy_hwtstamp_get(struct phy_device *phydev, @@ -65,4 +96,15 @@ static inline int phy_hwtstamp_set(struct phy_device *phydev, return -EOPNOTSUPP; } +static inline void phy_ethtool_get_phy_stats(struct phy_device *phydev, + struct ethtool_eth_phy_stats *phy_stats, + struct ethtool_phy_stats *phydev_stats) +{ +} + +static inline void phy_ethtool_get_link_ext_stats(struct phy_device *phydev, + struct ethtool_link_ext_stats *link_stats) +{ +} + #endif diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 9a57deefcb07..898b00451bbf 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -5,6 +5,8 @@ #include <linux/spinlock.h> #include <linux/workqueue.h> +#include <net/eee.h> + struct device_node; struct ethtool_cmd; struct fwnode_handle; @@ -138,23 +140,39 @@ enum phylink_op_type { * @poll_fixed_state: if true, starts link_poll, * if MAC link is at %MLO_AN_FIXED mode. * @mac_managed_pm: if true, indicate the MAC driver is responsible for PHY PM. - * @ovr_an_inband: if true, override PCS to MLO_AN_INBAND + * @mac_requires_rxc: if true, the MAC always requires a receive clock from PHY. + * The PHY driver should start the clock signal as soon as + * possible and avoid stopping it during suspend events. + * @default_an_inband: if true, defaults to MLO_AN_INBAND rather than + * MLO_AN_PHY. A fixed-link specification will override. + * @eee_rx_clk_stop_enable: if true, PHY can stop the receive clock during LPI * @get_fixed_state: callback to execute to determine the fixed link state, * if MAC link is at %MLO_AN_FIXED mode. * @supported_interfaces: bitmap describing which PHY_INTERFACE_MODE_xxx * are supported by the MAC/PCS. + * @lpi_interfaces: bitmap describing which PHY interface modes can support + * LPI signalling. * @mac_capabilities: MAC pause/speed/duplex capabilities. + * @lpi_capabilities: MAC speeds which can support LPI signalling + * @lpi_timer_default: Default EEE LPI timer setting. + * @eee_enabled_default: If set, EEE will be enabled by phylink at creation time */ struct phylink_config { struct device *dev; enum phylink_op_type type; bool poll_fixed_state; bool mac_managed_pm; - bool ovr_an_inband; + bool mac_requires_rxc; + bool default_an_inband; + bool eee_rx_clk_stop_enable; void (*get_fixed_state)(struct phylink_config *config, struct phylink_link_state *state); DECLARE_PHY_INTERFACE_MASK(supported_interfaces); + DECLARE_PHY_INTERFACE_MASK(lpi_interfaces); unsigned long mac_capabilities; + unsigned long lpi_capabilities; + u32 lpi_timer_default; + bool eee_enabled_default; }; void phylink_limit_mac_speed(struct phylink_config *config, u32 max_speed); @@ -168,6 +186,8 @@ void phylink_limit_mac_speed(struct phylink_config *config, u32 max_speed); * @mac_finish: finish a major reconfiguration of the interface. * @mac_link_down: take the link down. * @mac_link_up: allow the link to come up. + * @mac_disable_tx_lpi: disable LPI. + * @mac_enable_tx_lpi: enable and configure LPI. * * The individual methods are described more fully below. */ @@ -188,6 +208,9 @@ struct phylink_mac_ops { struct phy_device *phy, unsigned int mode, phy_interface_t interface, int speed, int duplex, bool tx_pause, bool rx_pause); + void (*mac_disable_tx_lpi)(struct phylink_config *config); + int (*mac_enable_tx_lpi)(struct phylink_config *config, u32 timer, + bool tx_clk_stop); }; #if 0 /* For kernel-doc purposes only. */ @@ -382,16 +405,49 @@ void mac_link_down(struct phylink_config *config, unsigned int mode, void mac_link_up(struct phylink_config *config, struct phy_device *phy, unsigned int mode, phy_interface_t interface, int speed, int duplex, bool tx_pause, bool rx_pause); + +/** + * mac_disable_tx_lpi() - disable LPI generation at the MAC + * @config: a pointer to a &struct phylink_config. + * + * Disable generation of LPI at the MAC, effectively preventing the MAC + * from indicating that it is idle. + */ +void mac_disable_tx_lpi(struct phylink_config *config); + +/** + * mac_enable_tx_lpi() - configure and enable LPI generation at the MAC + * @config: a pointer to a &struct phylink_config. + * @timer: LPI timeout in microseconds. + * @tx_clk_stop: allow xMII transmit clock to be stopped during LPI + * + * Configure the LPI timeout accordingly. This will only be called when + * the link is already up, to cater for situations where the hardware + * needs to be programmed according to the link speed. + * + * Enable LPI generation at the MAC, and configure whether the xMII transmit + * clock may be stopped. + * + * Returns: 0 on success. Please consult with rmk before returning an error. + */ +int mac_enable_tx_lpi(struct phylink_config *config, u32 timer, + bool tx_clk_stop); #endif struct phylink_pcs_ops; /** * struct phylink_pcs - PHYLINK PCS instance + * @supported_interfaces: describing which PHY_INTERFACE_MODE_xxx + * are supported by this PCS. * @ops: a pointer to the &struct phylink_pcs_ops structure * @phylink: pointer to &struct phylink_config * @neg_mode: provide PCS neg mode via "mode" argument * @poll: poll the PCS for link changes + * @rxc_always_on: The MAC driver requires the reference clock + * to always be on. Standalone PCS drivers which + * do not have access to a PHY device can check + * this instead of PHY_F_RXC_ALWAYS_ON. * * This structure is designed to be embedded within the PCS private data, * and will be passed between phylink and the PCS. @@ -400,15 +456,18 @@ struct phylink_pcs_ops; * the PCS driver. */ struct phylink_pcs { + DECLARE_PHY_INTERFACE_MASK(supported_interfaces); const struct phylink_pcs_ops *ops; struct phylink *phylink; bool neg_mode; bool poll; + bool rxc_always_on; }; /** * struct phylink_pcs_ops - MAC PCS operations structure. * @pcs_validate: validate the link configuration. + * @pcs_inband_caps: query inband support for interface mode. * @pcs_enable: enable the PCS. * @pcs_disable: disable the PCS. * @pcs_pre_config: pre-mac_config method (for errata) @@ -418,17 +477,21 @@ struct phylink_pcs { * @pcs_an_restart: restart 802.3z BaseX autonegotiation. * @pcs_link_up: program the PCS for the resolved link configuration * (where necessary). + * @pcs_pre_init: configure PCS components necessary for MAC hardware + * initialization e.g. RX clock for stmmac. */ struct phylink_pcs_ops { int (*pcs_validate)(struct phylink_pcs *pcs, unsigned long *supported, const struct phylink_link_state *state); + unsigned int (*pcs_inband_caps)(struct phylink_pcs *pcs, + phy_interface_t interface); int (*pcs_enable)(struct phylink_pcs *pcs); void (*pcs_disable)(struct phylink_pcs *pcs); void (*pcs_pre_config)(struct phylink_pcs *pcs, phy_interface_t interface); int (*pcs_post_config)(struct phylink_pcs *pcs, phy_interface_t interface); - void (*pcs_get_state)(struct phylink_pcs *pcs, + void (*pcs_get_state)(struct phylink_pcs *pcs, unsigned int neg_mode, struct phylink_link_state *state); int (*pcs_config)(struct phylink_pcs *pcs, unsigned int neg_mode, phy_interface_t interface, @@ -437,6 +500,7 @@ struct phylink_pcs_ops { void (*pcs_an_restart)(struct phylink_pcs *pcs); void (*pcs_link_up)(struct phylink_pcs *pcs, unsigned int neg_mode, phy_interface_t interface, int speed, int duplex); + int (*pcs_pre_init)(struct phylink_pcs *pcs); }; #if 0 /* For kernel-doc purposes only. */ @@ -458,6 +522,20 @@ int pcs_validate(struct phylink_pcs *pcs, unsigned long *supported, const struct phylink_link_state *state); /** + * pcs_inband_caps - query PCS in-band capabilities for interface mode. + * @pcs: a pointer to a &struct phylink_pcs. + * @interface: interface mode to be queried + * + * Returns zero if it is unknown what in-band signalling is supported by the + * PHY (e.g. because the PHY driver doesn't implement the method.) Otherwise, + * returns a bit mask of the LINK_INBAND_* values from + * &enum link_inband_signalling to describe which inband modes are supported + * for this interface mode. + */ +unsigned int pcs_inband_caps(struct phylink_pcs *pcs, + phy_interface_t interface); + +/** * pcs_enable() - enable the PCS. * @pcs: a pointer to a &struct phylink_pcs. */ @@ -472,6 +550,7 @@ void pcs_disable(struct phylink_pcs *pcs); /** * pcs_get_state() - Read the current inband link state from the hardware * @pcs: a pointer to a &struct phylink_pcs. + * @neg_mode: link negotiation mode (PHYLINK_PCS_NEG_xxx) * @state: a pointer to a &struct phylink_link_state. * * Read the current inband link state from the MAC PCS, reporting the @@ -480,8 +559,11 @@ void pcs_disable(struct phylink_pcs *pcs); * negotiation completion state in @state->an_complete, and link up state * in @state->link. If possible, @state->lp_advertising should also be * populated. + * + * Note that the @neg_mode parameter is always the PHYLINK_PCS_NEG_xxx + * state, not MLO_AN_xxx. */ -void pcs_get_state(struct phylink_pcs *pcs, +void pcs_get_state(struct phylink_pcs *pcs, unsigned int neg_mode, struct phylink_link_state *state); /** @@ -542,6 +624,34 @@ void pcs_an_restart(struct phylink_pcs *pcs); */ void pcs_link_up(struct phylink_pcs *pcs, unsigned int neg_mode, phy_interface_t interface, int speed, int duplex); + +/** + * pcs_pre_init() - Configure PCS components necessary for MAC initialization + * @pcs: a pointer to a &struct phylink_pcs. + * + * This function can be called by MAC drivers through the + * phylink_pcs_pre_init() wrapper, before their hardware is initialized. It + * should not be called after the link is brought up, as reconfiguring the PCS + * at this point could break the link. + * + * Some MAC devices require specific hardware initialization to be performed by + * their associated PCS device before they can properly initialize their own + * hardware. An example of this is the initialization of stmmac controllers, + * which requires an active REF_CLK signal to be provided by the PHY/PCS. + * + * By calling phylink_pcs_pre_init(), MAC drivers can ensure that the PCS is + * setup in a way that allows for successful hardware initialization. + * + * The specific configuration performed by pcs_pre_init() is dependent on the + * model of PCS and the requirements of the MAC device attached to it. PCS + * driver authors should consider whether their target device is to be used in + * conjunction with a MAC device whose driver calls phylink_pcs_pre_init(). MAC + * driver authors should document their requirements for the PCS + * pre-initialization. + * + */ +int pcs_pre_init(struct phylink_pcs *pcs); + #endif struct phylink *phylink_create(struct phylink_config *, @@ -557,10 +667,14 @@ int phylink_fwnode_phy_connect(struct phylink *pl, const struct fwnode_handle *fwnode, u32 flags); void phylink_disconnect_phy(struct phylink *); +int phylink_set_fixed_link(struct phylink *, + const struct phylink_link_state *); void phylink_mac_change(struct phylink *, bool up); void phylink_pcs_change(struct phylink_pcs *, bool up); +int phylink_pcs_pre_init(struct phylink *pl, struct phylink_pcs *pcs); + void phylink_start(struct phylink *); void phylink_stop(struct phylink *); @@ -611,6 +725,7 @@ static inline int phylink_get_link_timer_ns(phy_interface_t interface) case PHY_INTERFACE_MODE_SGMII: case PHY_INTERFACE_MODE_QSGMII: case PHY_INTERFACE_MODE_USXGMII: + case PHY_INTERFACE_MODE_10G_QXGMII: return 1600000; case PHY_INTERFACE_MODE_1000BASEX: @@ -623,8 +738,9 @@ static inline int phylink_get_link_timer_ns(phy_interface_t interface) } void phylink_mii_c22_pcs_decode_state(struct phylink_link_state *state, - u16 bmsr, u16 lpa); + unsigned int neg_mode, u16 bmsr, u16 lpa); void phylink_mii_c22_pcs_get_state(struct mdio_device *pcs, + unsigned int neg_mode, struct phylink_link_state *state); int phylink_mii_c22_pcs_encode_advertisement(phy_interface_t interface, const unsigned long *advertising); diff --git a/include/linux/pid.h b/include/linux/pid.h index a3aad9b4074c..98837a1ff0f3 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -59,6 +59,7 @@ struct pid spinlock_t lock; struct dentry *stashed; u64 ino; + struct rb_node pidfs_node; /* lists of tasks that use this pid */ struct hlist_head tasks[PIDTYPE_MAX]; struct hlist_head inodes; @@ -68,6 +69,7 @@ struct pid struct upid numbers[]; }; +extern seqcount_spinlock_t pidmap_lock_seq; extern struct pid init_struct_pid; struct file; @@ -106,9 +108,6 @@ extern void exchange_tids(struct task_struct *task, struct task_struct *old); extern void transfer_pid(struct task_struct *old, struct task_struct *new, enum pid_type); -extern int pid_max; -extern int pid_max_min, pid_max_max; - /* * look up a PID in the hash table. Must be called with the tasklist_lock * or rcu_read_lock() held. diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index f9f9931e02d6..7c67a5811199 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -30,6 +30,7 @@ struct pid_namespace { struct task_struct *child_reaper; struct kmem_cache *pid_cachep; unsigned int level; + int pid_max; struct pid_namespace *parent; #ifdef CONFIG_BSD_PROCESS_ACCT struct fs_pin *bacct; @@ -38,9 +39,14 @@ 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) + struct work_struct work; +#ifdef CONFIG_SYSCTL + struct ctl_table_set set; + struct ctl_table_header *sysctls; +#if defined(CONFIG_MEMFD_CREATE) int memfd_noexec_scope; #endif +#endif } __randomize_layout; extern struct pid_namespace init_pid_ns; @@ -117,6 +123,8 @@ static inline int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd) extern struct pid_namespace *task_active_pid_ns(struct task_struct *tsk); void pidhash_init(void); void pid_idr_init(void); +int register_pidns_sysctls(struct pid_namespace *pidns); +void unregister_pidns_sysctls(struct pid_namespace *pidns); static inline bool task_is_in_init_pid_ns(struct task_struct *tsk) { diff --git a/include/linux/pidfs.h b/include/linux/pidfs.h index 75bdf9807802..7c830d0dec9a 100644 --- a/include/linux/pidfs.h +++ b/include/linux/pidfs.h @@ -4,5 +4,8 @@ struct file *pidfs_alloc_file(struct pid *pid, unsigned int flags); void __init pidfs_init(void); +void pidfs_add_pid(struct pid *pid); +void pidfs_remove_pid(struct pid *pid); +extern const struct dentry_operations pidfs_dentry_operations; #endif /* _LINUX_PID_FS_H */ diff --git a/include/linux/pinctrl/pinconf-generic.h b/include/linux/pinctrl/pinconf-generic.h index a65d3d078e58..53cfde98433d 100644 --- a/include/linux/pinctrl/pinconf-generic.h +++ b/include/linux/pinctrl/pinconf-generic.h @@ -81,6 +81,8 @@ struct pinctrl_map; * @PIN_CONFIG_INPUT_SCHMITT_ENABLE: control schmitt-trigger mode on the pin. * If the argument != 0, schmitt-trigger mode is enabled. If it's 0, * schmitt-trigger mode is disabled. + * @PIN_CONFIG_INPUT_SCHMITT_UV: this will configure an input pin to run in + * schmitt-trigger mode. The argument is in uV. * @PIN_CONFIG_MODE_LOW_POWER: this will configure the pin for low power * operation, if several modes of operation are supported these can be * passed in the argument on a custom form, else just use argument 1 @@ -132,6 +134,7 @@ enum pin_config_param { PIN_CONFIG_INPUT_ENABLE, PIN_CONFIG_INPUT_SCHMITT, PIN_CONFIG_INPUT_SCHMITT_ENABLE, + PIN_CONFIG_INPUT_SCHMITT_UV, PIN_CONFIG_MODE_LOW_POWER, PIN_CONFIG_MODE_PWM, PIN_CONFIG_OUTPUT, diff --git a/include/linux/platform_data/ad5449.h b/include/linux/platform_data/ad5449.h deleted file mode 100644 index d687ef5726c2..000000000000 --- a/include/linux/platform_data/ad5449.h +++ /dev/null @@ -1,39 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * AD5415, AD5426, AD5429, AD5432, AD5439, AD5443, AD5449 Digital to Analog - * Converter driver. - * - * Copyright 2012 Analog Devices Inc. - * Author: Lars-Peter Clausen <lars@metafoo.de> - */ - -#ifndef __LINUX_PLATFORM_DATA_AD5449_H__ -#define __LINUX_PLATFORM_DATA_AD5449_H__ - -/** - * enum ad5449_sdo_mode - AD5449 SDO pin configuration - * @AD5449_SDO_DRIVE_FULL: Drive the SDO pin with full strength. - * @AD5449_SDO_DRIVE_WEAK: Drive the SDO pin with not full strength. - * @AD5449_SDO_OPEN_DRAIN: Operate the SDO pin in open-drain mode. - * @AD5449_SDO_DISABLED: Disable the SDO pin, in this mode it is not possible to - * read back from the device. - */ -enum ad5449_sdo_mode { - AD5449_SDO_DRIVE_FULL = 0x0, - AD5449_SDO_DRIVE_WEAK = 0x1, - AD5449_SDO_OPEN_DRAIN = 0x2, - AD5449_SDO_DISABLED = 0x3, -}; - -/** - * struct ad5449_platform_data - Platform data for the ad5449 DAC driver - * @sdo_mode: SDO pin mode - * @hardware_clear_to_midscale: Whether asserting the hardware CLR pin sets the - * outputs to midscale (true) or to zero scale(false). - */ -struct ad5449_platform_data { - enum ad5449_sdo_mode sdo_mode; - bool hardware_clear_to_midscale; -}; - -#endif diff --git a/include/linux/platform_data/amd_qdma.h b/include/linux/platform_data/amd_qdma.h new file mode 100644 index 000000000000..967a6ef31cf9 --- /dev/null +++ b/include/linux/platform_data/amd_qdma.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2023-2024, Advanced Micro Devices, Inc. + */ + +#ifndef _PLATDATA_AMD_QDMA_H +#define _PLATDATA_AMD_QDMA_H + +#include <linux/dmaengine.h> + +/** + * struct qdma_queue_info - DMA queue information. This information is used to + * match queue when DMA channel is requested + * @dir: Channel transfer direction + */ +struct qdma_queue_info { + enum dma_transfer_direction dir; +}; + +#define QDMA_FILTER_PARAM(qinfo) ((void *)(qinfo)) + +struct dma_slave_map; + +/** + * struct qdma_platdata - Platform specific data for QDMA engine + * @max_mm_channels: Maximum number of MM DMA channels in each direction + * @device_map: DMA slave map + * @irq_index: The index of first IRQ + * @dma_dev: The device pointer for dma operations + */ +struct qdma_platdata { + u32 max_mm_channels; + u32 irq_index; + struct dma_slave_map *device_map; + struct device *dma_dev; +}; + +#endif /* _PLATDATA_AMD_QDMA_H */ diff --git a/include/linux/platform_data/asoc-s3c.h b/include/linux/platform_data/asoc-s3c.h index f9c00f839e9f..085dd8e8af76 100644 --- a/include/linux/platform_data/asoc-s3c.h +++ b/include/linux/platform_data/asoc-s3c.h @@ -13,8 +13,6 @@ #include <linux/dmaengine.h> -extern void s3c64xx_ac97_setup_gpio(int); - struct samsung_i2s_type { /* If the Primary DAI has 5.1 Channels */ #define QUIRK_PRI_6CHAN (1 << 0) diff --git a/include/linux/platform_data/clk-davinci-pll.h b/include/linux/platform_data/clk-davinci-pll.h deleted file mode 100644 index e55dab1d578b..000000000000 --- a/include/linux/platform_data/clk-davinci-pll.h +++ /dev/null @@ -1,21 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * PLL clock driver for TI Davinci SoCs - * - * Copyright (C) 2018 David Lechner <david@lechnology.com> - */ - -#ifndef __LINUX_PLATFORM_DATA_CLK_DAVINCI_PLL_H__ -#define __LINUX_PLATFORM_DATA_CLK_DAVINCI_PLL_H__ - -#include <linux/regmap.h> - -/** - * davinci_pll_platform_data - * @cfgchip: CFGCHIP syscon regmap - */ -struct davinci_pll_platform_data { - struct regmap *cfgchip; -}; - -#endif /* __LINUX_PLATFORM_DATA_CLK_DAVINCI_PLL_H__ */ diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h index ecc47d5fe239..ecf290a0c98f 100644 --- a/include/linux/platform_data/cros_ec_commands.h +++ b/include/linux/platform_data/cros_ec_commands.h @@ -1312,6 +1312,38 @@ enum ec_feature_code { * The EC supports the AP composing VDMs for us to send. */ EC_FEATURE_TYPEC_AP_VDM_SEND = 46, + /* + * The EC supports system safe mode panic recovery. + */ + EC_FEATURE_SYSTEM_SAFE_MODE = 47, + /* + * The EC will reboot on runtime assertion failures. + */ + EC_FEATURE_ASSERT_REBOOTS = 48, + /* + * The EC image is built with tokenized logging enabled. + */ + EC_FEATURE_TOKENIZED_LOGGING = 49, + /* + * The EC supports triggering an STB dump. + */ + EC_FEATURE_AMD_STB_DUMP = 50, + /* + * The EC supports memory dump commands. + */ + EC_FEATURE_MEMORY_DUMP = 51, + /* + * The EC supports DP2.1 capability + */ + EC_FEATURE_TYPEC_DP2_1 = 52, + /* + * The MCU is System Companion Processor Core 1 + */ + EC_FEATURE_SCP_C1 = 53, + /* + * The EC supports UCSI PPM. + */ + EC_FEATURE_UCSI_PPM = 54, }; #define EC_FEATURE_MASK_0(event_code) BIT(event_code % 32) @@ -3463,6 +3495,34 @@ union __ec_align_offset1 ec_response_get_next_data_v1 { }; BUILD_ASSERT(sizeof(union ec_response_get_next_data_v1) == 16); +union __ec_align_offset1 ec_response_get_next_data_v3 { + uint8_t key_matrix[18]; + + /* Unaligned */ + uint32_t host_event; + uint64_t host_event64; + + struct __ec_todo_unpacked { + /* For aligning the fifo_info */ + uint8_t reserved[3]; + struct ec_response_motion_sense_fifo_info info; + } sensor_fifo; + + uint32_t buttons; + + uint32_t switches; + + uint32_t fp_events; + + uint32_t sysrq; + + /* CEC events from enum mkbp_cec_event */ + uint32_t cec_events; + + uint8_t cec_message[16]; +}; +BUILD_ASSERT(sizeof(union ec_response_get_next_data_v3) == 18); + struct ec_response_get_next_event { uint8_t event_type; /* Followed by event data if any */ @@ -3475,6 +3535,12 @@ struct ec_response_get_next_event_v1 { union ec_response_get_next_data_v1 data; } __ec_align1; +struct ec_response_get_next_event_v3 { + uint8_t event_type; + /* Followed by event data if any */ + union ec_response_get_next_data_v3 data; +} __ec_align1; + /* Bit indices for buttons and switches.*/ /* Buttons */ #define EC_MKBP_POWER_BUTTON 0 @@ -3809,16 +3875,61 @@ struct ec_params_i2c_write { * discharge the battery. */ #define EC_CMD_CHARGE_CONTROL 0x0096 -#define EC_VER_CHARGE_CONTROL 1 +#define EC_VER_CHARGE_CONTROL 3 enum ec_charge_control_mode { CHARGE_CONTROL_NORMAL = 0, CHARGE_CONTROL_IDLE, CHARGE_CONTROL_DISCHARGE, + /* Add no more entry below. */ + CHARGE_CONTROL_COUNT, +}; + +#define EC_CHARGE_MODE_TEXT \ + { \ + [CHARGE_CONTROL_NORMAL] = "NORMAL", \ + [CHARGE_CONTROL_IDLE] = "IDLE", \ + [CHARGE_CONTROL_DISCHARGE] = "DISCHARGE", \ + } + +enum ec_charge_control_cmd { + EC_CHARGE_CONTROL_CMD_SET = 0, + EC_CHARGE_CONTROL_CMD_GET, +}; + +enum ec_charge_control_flag { + EC_CHARGE_CONTROL_FLAG_NO_IDLE = BIT(0), }; struct ec_params_charge_control { - uint32_t mode; /* enum charge_control_mode */ + uint32_t mode; /* enum charge_control_mode */ + + /* Below are the fields added in V2. */ + uint8_t cmd; /* enum ec_charge_control_cmd. */ + uint8_t flags; /* enum ec_charge_control_flag (v3+) */ + /* + * Lower and upper thresholds for battery sustainer. This struct isn't + * named to avoid tainting foreign projects' name spaces. + * + * If charge mode is explicitly set (e.g. DISCHARGE), battery sustainer + * will be disabled. To disable battery sustainer, set mode=NORMAL, + * lower=-1, upper=-1. + */ + struct { + int8_t lower; /* Display SoC in percentage. */ + int8_t upper; /* Display SoC in percentage. */ + } sustain_soc; +} __ec_align4; + +/* Added in v2 */ +struct ec_response_charge_control { + uint32_t mode; /* enum charge_control_mode */ + struct { /* Battery sustainer thresholds */ + int8_t lower; + int8_t upper; + } sustain_soc; + uint8_t flags; /* enum ec_charge_control_flag (v3+) */ + uint8_t reserved; } __ec_align4; /*****************************************************************************/ @@ -4933,8 +5044,11 @@ struct ec_response_pd_status { #define PD_EVENT_POWER_CHANGE BIT(1) #define PD_EVENT_IDENTITY_RECEIVED BIT(2) #define PD_EVENT_DATA_SWAP BIT(3) +#define PD_EVENT_TYPEC BIT(4) +#define PD_EVENT_PPM BIT(5) + struct ec_response_host_event_status { - uint32_t status; /* PD MCU host event status */ + uint32_t status; /* PD MCU host event status */ } __ec_align4; /* Set USB type-C port role and muxes */ @@ -5994,6 +6108,29 @@ struct ec_response_typec_vdm_response { #undef VDO_MAX_SIZE +/* + * UCSI OPM-PPM commands + * + * These commands are used for communication between OPM and PPM. + * Only UCSI3.0 is tested. + */ + +#define EC_CMD_UCSI_PPM_SET 0x0140 + +/* The data size is stored in the host command protocol header. */ +struct ec_params_ucsi_ppm_set { + uint16_t offset; + uint8_t data[]; +} __ec_align2; + +#define EC_CMD_UCSI_PPM_GET 0x0141 + +/* For 'GET' sub-commands, data will be returned as a raw payload. */ +struct ec_params_ucsi_ppm_get { + uint16_t offset; + uint8_t size; +} __ec_align2; + /*****************************************************************************/ /* The command range 0x200-0x2FF is reserved for Rotor. */ diff --git a/include/linux/platform_data/cros_ec_proto.h b/include/linux/platform_data/cros_ec_proto.h index 8865e350c12a..3ec24f445c29 100644 --- a/include/linux/platform_data/cros_ec_proto.h +++ b/include/linux/platform_data/cros_ec_proto.h @@ -42,6 +42,11 @@ #define EC_MAX_RESPONSE_OVERHEAD 32 /* + * ACPI notify value for MKBP host event. + */ +#define ACPI_NOTIFY_CROS_EC_MKBP 0x80 + +/* * EC panic is not covered by the standard (0-F) ACPI notify values. * Arbitrarily choosing B0 to notify ec panic, which is in the 84-BF * device specific ACPI notify range. @@ -185,7 +190,7 @@ struct cros_ec_device { bool host_sleep_v1; struct blocking_notifier_head event_notifier; - struct ec_response_get_next_event_v1 event_data; + struct ec_response_get_next_event_v3 event_data; int event_size; u32 host_event_wake_mask; u32 last_resume_result; @@ -246,6 +251,8 @@ int cros_ec_cmd_xfer(struct cros_ec_device *ec_dev, int cros_ec_cmd_xfer_status(struct cros_ec_device *ec_dev, struct cros_ec_command *msg); +int cros_ec_rwsig_continue(struct cros_ec_device *ec_dev); + int cros_ec_query_all(struct cros_ec_device *ec_dev); int cros_ec_get_next_event(struct cros_ec_device *ec_dev, @@ -261,6 +268,10 @@ int cros_ec_get_sensor_count(struct cros_ec_dev *ec); int cros_ec_cmd(struct cros_ec_device *ec_dev, unsigned int version, int command, const void *outdata, size_t outsize, void *indata, size_t insize); +int cros_ec_cmd_readmem(struct cros_ec_device *ec_dev, u8 offset, u8 size, void *dest); + +int cros_ec_get_cmd_versions(struct cros_ec_device *ec_dev, u16 cmd); + /** * cros_ec_get_time_ns() - Return time in ns. * diff --git a/include/linux/platform_data/cyttsp4.h b/include/linux/platform_data/cyttsp4.h deleted file mode 100644 index 5dc9d2be384b..000000000000 --- a/include/linux/platform_data/cyttsp4.h +++ /dev/null @@ -1,62 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Header file for: - * Cypress TrueTouch(TM) Standard Product (TTSP) touchscreen drivers. - * For use with Cypress Txx3xx parts. - * Supported parts include: - * CY8CTST341 - * CY8CTMA340 - * - * Copyright (C) 2009, 2010, 2011 Cypress Semiconductor, Inc. - * Copyright (C) 2012 Javier Martinez Canillas <javier@dowhile0.org> - * - * Contact Cypress Semiconductor at www.cypress.com (kev@cypress.com) - */ -#ifndef _CYTTSP4_H_ -#define _CYTTSP4_H_ - -#define CYTTSP4_MT_NAME "cyttsp4_mt" -#define CYTTSP4_I2C_NAME "cyttsp4_i2c_adapter" -#define CYTTSP4_SPI_NAME "cyttsp4_spi_adapter" - -#define CY_TOUCH_SETTINGS_MAX 32 - -struct touch_framework { - const uint16_t *abs; - uint8_t size; - uint8_t enable_vkeys; -} __packed; - -struct cyttsp4_mt_platform_data { - struct touch_framework *frmwrk; - unsigned short flags; - char const *inp_dev_name; -}; - -struct touch_settings { - const uint8_t *data; - uint32_t size; - uint8_t tag; -} __packed; - -struct cyttsp4_core_platform_data { - int irq_gpio; - int rst_gpio; - int level_irq_udelay; - int (*xres)(struct cyttsp4_core_platform_data *pdata, - struct device *dev); - int (*init)(struct cyttsp4_core_platform_data *pdata, - int on, struct device *dev); - int (*power)(struct cyttsp4_core_platform_data *pdata, - int on, struct device *dev, atomic_t *ignore_irq); - int (*irq_stat)(struct cyttsp4_core_platform_data *pdata, - struct device *dev); - struct touch_settings *sett[CY_TOUCH_SETTINGS_MAX]; -}; - -struct cyttsp4_platform_data { - struct cyttsp4_core_platform_data *core_pdata; - struct cyttsp4_mt_platform_data *mt_pdata; -}; - -#endif /* _CYTTSP4_H_ */ diff --git a/include/linux/platform_data/davinci_asp.h b/include/linux/platform_data/davinci_asp.h index c8645b2ed3c0..b9c8520b4bd3 100644 --- a/include/linux/platform_data/davinci_asp.h +++ b/include/linux/platform_data/davinci_asp.h @@ -26,16 +26,6 @@ struct davinci_mcasp_pdata { struct gen_pool *sram_pool; /* - * If McBSP peripheral gets the clock from an external pin, - * there are three chooses, that are MCBSP_CLKX, MCBSP_CLKR - * and MCBSP_CLKS. - * Depending on different hardware connections it is possible - * to use this setting to change the behaviour of McBSP - * driver. - */ - int clk_input_pin; - - /* * This flag works when both clock and FS are outputs for the cpu * and makes clock more accurate (FS is not symmetrical and the * clock is very fast. @@ -91,11 +81,6 @@ enum { MCASP_VERSION_OMAP, /* OMAP4/5 */ }; -enum mcbsp_clk_input_pin { - MCBSP_CLKR = 0, /* as in DM365 */ - MCBSP_CLKS, -}; - #define INACTIVE_MODE 0 #define TX_MODE 1 #define RX_MODE 2 diff --git a/include/linux/platform_data/dma-ep93xx.h b/include/linux/platform_data/dma-ep93xx.h deleted file mode 100644 index eb9805bb3fe8..000000000000 --- a/include/linux/platform_data/dma-ep93xx.h +++ /dev/null @@ -1,94 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __ASM_ARCH_DMA_H -#define __ASM_ARCH_DMA_H - -#include <linux/types.h> -#include <linux/dmaengine.h> -#include <linux/dma-mapping.h> - -/* - * M2P channels. - * - * Note that these values are also directly used for setting the PPALLOC - * register. - */ -#define EP93XX_DMA_I2S1 0 -#define EP93XX_DMA_I2S2 1 -#define EP93XX_DMA_AAC1 2 -#define EP93XX_DMA_AAC2 3 -#define EP93XX_DMA_AAC3 4 -#define EP93XX_DMA_I2S3 5 -#define EP93XX_DMA_UART1 6 -#define EP93XX_DMA_UART2 7 -#define EP93XX_DMA_UART3 8 -#define EP93XX_DMA_IRDA 9 -/* M2M channels */ -#define EP93XX_DMA_SSP 10 -#define EP93XX_DMA_IDE 11 - -/** - * struct ep93xx_dma_data - configuration data for the EP93xx dmaengine - * @port: peripheral which is requesting the channel - * @direction: TX/RX channel - * @name: optional name for the channel, this is displayed in /proc/interrupts - * - * This information is passed as private channel parameter in a filter - * function. Note that this is only needed for slave/cyclic channels. For - * memcpy channels %NULL data should be passed. - */ -struct ep93xx_dma_data { - int port; - enum dma_transfer_direction direction; - const char *name; -}; - -/** - * struct ep93xx_dma_chan_data - platform specific data for a DMA channel - * @name: name of the channel, used for getting the right clock for the channel - * @base: mapped registers - * @irq: interrupt number used by this channel - */ -struct ep93xx_dma_chan_data { - const char *name; - void __iomem *base; - int irq; -}; - -/** - * struct ep93xx_dma_platform_data - platform data for the dmaengine driver - * @channels: array of channels which are passed to the driver - * @num_channels: number of channels in the array - * - * This structure is passed to the DMA engine driver via platform data. For - * M2P channels, contract is that even channels are for TX and odd for RX. - * There is no requirement for the M2M channels. - */ -struct ep93xx_dma_platform_data { - struct ep93xx_dma_chan_data *channels; - size_t num_channels; -}; - -static inline bool ep93xx_dma_chan_is_m2p(struct dma_chan *chan) -{ - return !strcmp(dev_name(chan->device->dev), "ep93xx-dma-m2p"); -} - -/** - * ep93xx_dma_chan_direction - returns direction the channel can be used - * @chan: channel - * - * This function can be used in filter functions to find out whether the - * channel supports given DMA direction. Only M2P channels have such - * limitation, for M2M channels the direction is configurable. - */ -static inline enum dma_transfer_direction -ep93xx_dma_chan_direction(struct dma_chan *chan) -{ - if (!ep93xx_dma_chan_is_m2p(chan)) - return DMA_TRANS_NONE; - - /* even channels are for TX, odd for RX */ - return (chan->chan_id % 2 == 0) ? DMA_MEM_TO_DEV : DMA_DEV_TO_MEM; -} - -#endif /* __ASM_ARCH_DMA_H */ diff --git a/include/linux/platform_data/eth-ep93xx.h b/include/linux/platform_data/eth-ep93xx.h deleted file mode 100644 index 8eef637a804d..000000000000 --- a/include/linux/platform_data/eth-ep93xx.h +++ /dev/null @@ -1,10 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_PLATFORM_DATA_ETH_EP93XX -#define _LINUX_PLATFORM_DATA_ETH_EP93XX - -struct ep93xx_eth_data { - unsigned char dev_addr[6]; - unsigned char phy_id; -}; - -#endif diff --git a/include/linux/platform_data/gpio-ath79.h b/include/linux/platform_data/gpio-ath79.h deleted file mode 100644 index 3ea6dd942c27..000000000000 --- a/include/linux/platform_data/gpio-ath79.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Atheros AR7XXX/AR9XXX GPIO controller platform data - * - * Copyright (C) 2015 Alban Bedel <albeu@free.fr> - */ - -#ifndef __LINUX_PLATFORM_DATA_GPIO_ATH79_H -#define __LINUX_PLATFORM_DATA_GPIO_ATH79_H - -struct ath79_gpio_platform_data { - unsigned ngpios; - bool oe_inverted; -}; - -#endif diff --git a/include/linux/platform_data/gpio-davinci.h b/include/linux/platform_data/gpio-davinci.h deleted file mode 100644 index b82e44662efe..000000000000 --- a/include/linux/platform_data/gpio-davinci.h +++ /dev/null @@ -1,21 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * DaVinci GPIO Platform Related Defines - * - * Copyright (C) 2013 Texas Instruments Incorporated - https://www.ti.com/ - */ - -#ifndef __DAVINCI_GPIO_PLATFORM_H -#define __DAVINCI_GPIO_PLATFORM_H - -struct davinci_gpio_platform_data { - bool no_auto_base; - u32 base; - u32 ngpio; - u32 gpio_unbanked; -}; - -/* Convert GPIO signal to GPIO pin number */ -#define GPIO_TO_PIN(bank, gpio) (16 * (bank) + (gpio)) - -#endif diff --git a/include/linux/platform_data/hwmon-s3c.h b/include/linux/platform_data/hwmon-s3c.h index 1707ad4147df..7d21e0c41037 100644 --- a/include/linux/platform_data/hwmon-s3c.h +++ b/include/linux/platform_data/hwmon-s3c.h @@ -33,14 +33,4 @@ struct s3c_hwmon_pdata { struct s3c_hwmon_chcfg *in[8]; }; -/** - * s3c_hwmon_set_platdata - Set platform data for S3C HWMON device - * @pd: Platform data to register to device. - * - * Register the given platform data for use with the S3C HWMON device. - * The call will copy the platform data, so the board definitions can - * make the structure itself __initdata. - */ -extern void __init s3c_hwmon_set_platdata(struct s3c_hwmon_pdata *pd); - #endif /* __HWMON_S3C_H__ */ diff --git a/include/linux/platform_data/i2c-davinci.h b/include/linux/platform_data/i2c-davinci.h deleted file mode 100644 index 98967df07468..000000000000 --- a/include/linux/platform_data/i2c-davinci.h +++ /dev/null @@ -1,26 +0,0 @@ -/* - * DaVinci I2C controller platform_device info - * - * Author: Vladimir Barinov, MontaVista Software, Inc. <source@mvista.com> - * - * 2007 (c) MontaVista Software, Inc. This file is licensed under - * the terms of the GNU General Public License version 2. This program - * is licensed "as is" without any warranty of any kind, whether express - * or implied. -*/ - -#ifndef __ASM_ARCH_I2C_H -#define __ASM_ARCH_I2C_H - -/* All frequencies are expressed in kHz */ -struct davinci_i2c_platform_data { - unsigned int bus_freq; /* standard bus frequency (kHz) */ - unsigned int bus_delay; /* post-transaction delay (usec) */ - bool gpio_recovery; /* Use GPIO recovery method */ - bool has_pfunc; /* Chip has a ICPFUNC register */ -}; - -/* for board setup code */ -void davinci_init_i2c(struct davinci_i2c_platform_data *); - -#endif /* __ASM_ARCH_I2C_H */ diff --git a/include/linux/platform_data/i2c-mux-gpio.h b/include/linux/platform_data/i2c-mux-gpio.h index 5e4c2c272a73..96843aab4d1e 100644 --- a/include/linux/platform_data/i2c-mux-gpio.h +++ b/include/linux/platform_data/i2c-mux-gpio.h @@ -18,16 +18,16 @@ * @values: Array of bitmasks of GPIO settings (low/high) for each * position * @n_values: Number of multiplexer positions (busses to instantiate) - * @classes: Optional I2C auto-detection classes * @idle: Bitmask to write to MUX when idle or GPIO_I2CMUX_NO_IDLE if not used + * @settle_time: Delay to wait when a new bus is selected */ struct i2c_mux_gpio_platform_data { int parent; int base_nr; const unsigned *values; int n_values; - const unsigned *classes; unsigned idle; + u32 settle_time; }; #endif /* _LINUX_I2C_MUX_GPIO_H */ diff --git a/include/linux/platform_data/keypad-ep93xx.h b/include/linux/platform_data/keypad-ep93xx.h deleted file mode 100644 index 3054fced8509..000000000000 --- a/include/linux/platform_data/keypad-ep93xx.h +++ /dev/null @@ -1,32 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __KEYPAD_EP93XX_H -#define __KEYPAD_EP93XX_H - -struct matrix_keymap_data; - -/* flags for the ep93xx_keypad driver */ -#define EP93XX_KEYPAD_DISABLE_3_KEY (1<<0) /* disable 3-key reset */ -#define EP93XX_KEYPAD_DIAG_MODE (1<<1) /* diagnostic mode */ -#define EP93XX_KEYPAD_BACK_DRIVE (1<<2) /* back driving mode */ -#define EP93XX_KEYPAD_TEST_MODE (1<<3) /* scan only column 0 */ -#define EP93XX_KEYPAD_AUTOREPEAT (1<<4) /* enable key autorepeat */ - -/** - * struct ep93xx_keypad_platform_data - platform specific device structure - * @keymap_data: pointer to &matrix_keymap_data - * @debounce: debounce start count; terminal count is 0xff - * @prescale: row/column counter pre-scaler load value - * @flags: see above - */ -struct ep93xx_keypad_platform_data { - struct matrix_keymap_data *keymap_data; - unsigned int debounce; - unsigned int prescale; - unsigned int flags; - unsigned int clk_rate; -}; - -#define EP93XX_MATRIX_ROWS (8) -#define EP93XX_MATRIX_COLS (8) - -#endif /* __KEYPAD_EP93XX_H */ diff --git a/include/linux/platform_data/keypad-nomadik-ske.h b/include/linux/platform_data/keypad-nomadik-ske.h deleted file mode 100644 index 7efabbca1dca..000000000000 --- a/include/linux/platform_data/keypad-nomadik-ske.h +++ /dev/null @@ -1,50 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) ST-Ericsson SA 2010 - * - * Author: Naveen Kumar Gaddipati <naveen.gaddipati@stericsson.com> - * - * ux500 Scroll key and Keypad Encoder (SKE) header - */ - -#ifndef __SKE_H -#define __SKE_H - -#include <linux/input/matrix_keypad.h> - -/* register definitions for SKE peripheral */ -#define SKE_CR 0x00 -#define SKE_VAL0 0x04 -#define SKE_VAL1 0x08 -#define SKE_DBCR 0x0C -#define SKE_IMSC 0x10 -#define SKE_RIS 0x14 -#define SKE_MIS 0x18 -#define SKE_ICR 0x1C - -/* - * Keypad module - */ - -/** - * struct keypad_platform_data - structure for platform specific data - * @init: pointer to keypad init function - * @exit: pointer to keypad deinitialisation function - * @keymap_data: matrix scan code table for keycodes - * @krow: maximum number of rows - * @kcol: maximum number of columns - * @debounce_ms: platform specific debounce time - * @no_autorepeat: flag for auto repetition - * @wakeup_enable: allow waking up the system - */ -struct ske_keypad_platform_data { - int (*init)(void); - int (*exit)(void); - const struct matrix_keymap_data *keymap_data; - u8 krow; - u8 kcol; - u8 debounce_ms; - bool no_autorepeat; - bool wakeup_enable; -}; -#endif /*__SKE_KPD_H*/ diff --git a/include/linux/platform_data/keyscan-davinci.h b/include/linux/platform_data/keyscan-davinci.h deleted file mode 100644 index 260d596ba0af..000000000000 --- a/include/linux/platform_data/keyscan-davinci.h +++ /dev/null @@ -1,29 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Copyright (C) 2009 Texas Instruments, Inc - * - * Author: Miguel Aguilar <miguel.aguilar@ridgerun.com> - */ - -#ifndef DAVINCI_KEYSCAN_H -#define DAVINCI_KEYSCAN_H - -#include <linux/io.h> - -enum davinci_matrix_types { - DAVINCI_KEYSCAN_MATRIX_4X4, - DAVINCI_KEYSCAN_MATRIX_5X3, -}; - -struct davinci_ks_platform_data { - int (*device_enable)(struct device *dev); - unsigned short *keymap; - u32 keymapsize; - u8 rep:1; - u8 strobe; - u8 interval; - u8 matrix_type; -}; - -#endif - diff --git a/include/linux/platform_data/lenovo-yoga-c630.h b/include/linux/platform_data/lenovo-yoga-c630.h new file mode 100644 index 000000000000..5d1f9fb33cfc --- /dev/null +++ b/include/linux/platform_data/lenovo-yoga-c630.h @@ -0,0 +1,44 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2022-2024, Linaro Ltd + * Authors: + * Bjorn Andersson + * Dmitry Baryshkov + */ + +#ifndef _LENOVO_YOGA_C630_DATA_H +#define _LENOVO_YOGA_C630_DATA_H + +struct yoga_c630_ec; +struct notifier_block; + +#define YOGA_C630_MOD_NAME "lenovo_yoga_c630" + +#define YOGA_C630_DEV_UCSI "ucsi" +#define YOGA_C630_DEV_PSY "psy" + +int yoga_c630_ec_read8(struct yoga_c630_ec *ec, u8 addr); +int yoga_c630_ec_read16(struct yoga_c630_ec *ec, u8 addr); + +int yoga_c630_ec_register_notify(struct yoga_c630_ec *ec, struct notifier_block *nb); +void yoga_c630_ec_unregister_notify(struct yoga_c630_ec *ec, struct notifier_block *nb); + +#define YOGA_C630_UCSI_WRITE_SIZE 8 +#define YOGA_C630_UCSI_CCI_SIZE 4 +#define YOGA_C630_UCSI_DATA_SIZE 16 +#define YOGA_C630_UCSI_READ_SIZE (YOGA_C630_UCSI_CCI_SIZE + YOGA_C630_UCSI_DATA_SIZE) + +u16 yoga_c630_ec_ucsi_get_version(struct yoga_c630_ec *ec); +int yoga_c630_ec_ucsi_write(struct yoga_c630_ec *ec, + const u8 req[YOGA_C630_UCSI_WRITE_SIZE]); +int yoga_c630_ec_ucsi_read(struct yoga_c630_ec *ec, + u8 resp[YOGA_C630_UCSI_READ_SIZE]); + +#define LENOVO_EC_EVENT_USB 0x20 +#define LENOVO_EC_EVENT_UCSI 0x21 +#define LENOVO_EC_EVENT_HPD 0x22 +#define LENOVO_EC_EVENT_BAT_STATUS 0x24 +#define LENOVO_EC_EVENT_BAT_INFO 0x25 +#define LENOVO_EC_EVENT_BAT_ADPT_STATUS 0x37 + +#endif diff --git a/include/linux/platform_data/max6639.h b/include/linux/platform_data/max6639.h deleted file mode 100644 index 65bfdb4fdc15..000000000000 --- a/include/linux/platform_data/max6639.h +++ /dev/null @@ -1,15 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_MAX6639_H -#define _LINUX_MAX6639_H - -#include <linux/types.h> - -/* platform data for the MAX6639 temperature sensor and fan control */ - -struct max6639_platform_data { - bool pwm_polarity; /* Polarity low (0) or high (1, default) */ - int ppr; /* Pulses per rotation 1..4 (default == 2) */ - int rpm_range; /* 2000, 4000 (default), 8000 or 16000 */ -}; - -#endif /* _LINUX_MAX6639_H */ diff --git a/include/linux/platform_data/max6697.h b/include/linux/platform_data/max6697.h deleted file mode 100644 index 6fbb70005541..000000000000 --- a/include/linux/platform_data/max6697.h +++ /dev/null @@ -1,33 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * max6697.h - * Copyright (c) 2012 Guenter Roeck <linux@roeck-us.net> - */ - -#ifndef MAX6697_H -#define MAX6697_H - -#include <linux/types.h> - -/* - * For all bit masks: - * bit 0: local temperature - * bit 1..7: remote temperatures - */ -struct max6697_platform_data { - bool smbus_timeout_disable; /* set to disable SMBus timeouts */ - bool extended_range_enable; /* set to enable extended temp range */ - bool beta_compensation; /* set to enable beta compensation */ - u8 alert_mask; /* set bit to 1 to disable alert */ - u8 over_temperature_mask; /* set bit to 1 to disable */ - u8 resistance_cancellation; /* set bit to 0 to disable - * bit mask for MAX6581, - * boolean for other chips - */ - u8 ideality_mask; /* set bit to 0 to disable */ - u8 ideality_value; /* transistor ideality as per - * MAX6581 datasheet - */ -}; - -#endif /* MAX6697_H */ diff --git a/include/linux/platform_data/mcs.h b/include/linux/platform_data/mcs.h deleted file mode 100644 index fcc6f2a1f5c3..000000000000 --- a/include/linux/platform_data/mcs.h +++ /dev/null @@ -1,30 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Copyright (C) 2009 - 2010 Samsung Electronics Co.Ltd - * Author: Joonyoung Shim <jy0922.shim@samsung.com> - * Author: HeungJun Kim <riverful.kim@samsung.com> - */ - -#ifndef __LINUX_MCS_H -#define __LINUX_MCS_H - -#define MCS_KEY_MAP(v, c) ((((v) & 0xff) << 16) | ((c) & 0xffff)) -#define MCS_KEY_VAL(v) (((v) >> 16) & 0xff) -#define MCS_KEY_CODE(v) ((v) & 0xffff) - -struct mcs_platform_data { - void (*poweron)(bool); - void (*cfg_pin)(void); - - /* touchscreen */ - unsigned int x_size; - unsigned int y_size; - - /* touchkey */ - const u32 *keymap; - unsigned int keymap_size; - unsigned int key_maxval; - bool no_autorepeat; -}; - -#endif /* __LINUX_MCS_H */ diff --git a/include/linux/platform_data/media/omap4iss.h b/include/linux/platform_data/media/omap4iss.h deleted file mode 100644 index 2a511a8fcda7..000000000000 --- a/include/linux/platform_data/media/omap4iss.h +++ /dev/null @@ -1,66 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef ARCH_ARM_PLAT_OMAP4_ISS_H -#define ARCH_ARM_PLAT_OMAP4_ISS_H - -#include <linux/i2c.h> - -struct iss_device; - -enum iss_interface_type { - ISS_INTERFACE_CSI2A_PHY1, - ISS_INTERFACE_CSI2B_PHY2, -}; - -/** - * struct iss_csiphy_lane: CSI2 lane position and polarity - * @pos: position of the lane - * @pol: polarity of the lane - */ -struct iss_csiphy_lane { - u8 pos; - u8 pol; -}; - -#define ISS_CSIPHY1_NUM_DATA_LANES 4 -#define ISS_CSIPHY2_NUM_DATA_LANES 1 - -/** - * struct iss_csiphy_lanes_cfg - CSI2 lane configuration - * @data: Configuration of one or two data lanes - * @clk: Clock lane configuration - */ -struct iss_csiphy_lanes_cfg { - struct iss_csiphy_lane data[ISS_CSIPHY1_NUM_DATA_LANES]; - struct iss_csiphy_lane clk; -}; - -/** - * struct iss_csi2_platform_data - CSI2 interface platform data - * @crc: Enable the cyclic redundancy check - * @vpclk_div: Video port output clock control - */ -struct iss_csi2_platform_data { - unsigned crc:1; - unsigned vpclk_div:2; - struct iss_csiphy_lanes_cfg lanecfg; -}; - -struct iss_subdev_i2c_board_info { - struct i2c_board_info *board_info; - int i2c_adapter_id; -}; - -struct iss_v4l2_subdevs_group { - struct iss_subdev_i2c_board_info *subdevs; - enum iss_interface_type interface; - union { - struct iss_csi2_platform_data csi2; - } bus; /* gcc < 4.6.0 chokes on anonymous union initializers */ -}; - -struct iss_platform_data { - struct iss_v4l2_subdevs_group *subdevs; - void (*set_constraints)(struct iss_device *iss, bool enable); -}; - -#endif diff --git a/include/linux/platform_data/microchip-ksz.h b/include/linux/platform_data/microchip-ksz.h index 8c659db4da6b..0e0e8fe6975f 100644 --- a/include/linux/platform_data/microchip-ksz.h +++ b/include/linux/platform_data/microchip-ksz.h @@ -27,7 +27,9 @@ enum ksz_chip_id { KSZ8795_CHIP_ID = 0x8795, KSZ8794_CHIP_ID = 0x8794, KSZ8765_CHIP_ID = 0x8765, - KSZ8830_CHIP_ID = 0x8830, + KSZ88X3_CHIP_ID = 0x8830, + KSZ8864_CHIP_ID = 0x8864, + KSZ8895_CHIP_ID = 0x8895, KSZ9477_CHIP_ID = 0x00947700, KSZ9896_CHIP_ID = 0x00989600, KSZ9897_CHIP_ID = 0x00989700, @@ -40,6 +42,7 @@ enum ksz_chip_id { LAN9372_CHIP_ID = 0x00937200, LAN9373_CHIP_ID = 0x00937300, LAN9374_CHIP_ID = 0x00937400, + LAN9646_CHIP_ID = 0x00964600, }; struct ksz_platform_data { diff --git a/include/linux/platform_data/mmc-pxamci.h b/include/linux/platform_data/mmc-pxamci.h index 7e44e84e7150..652f323b5ecc 100644 --- a/include/linux/platform_data/mmc-pxamci.h +++ b/include/linux/platform_data/mmc-pxamci.h @@ -7,6 +7,7 @@ struct device; struct mmc_host; +struct property_entry; struct pxamci_platform_data { unsigned int ocr_mask; /* available voltages */ @@ -18,7 +19,8 @@ struct pxamci_platform_data { bool gpio_card_ro_invert; /* gpio ro is inverted */ }; -extern void pxa_set_mci_info(struct pxamci_platform_data *info); +extern void pxa_set_mci_info(const struct pxamci_platform_data *info, + const struct property_entry *props); extern void pxa3xx_set_mci2_info(struct pxamci_platform_data *info); extern void pxa3xx_set_mci3_info(struct pxamci_platform_data *info); diff --git a/include/linux/platform_data/mtd-davinci-aemif.h b/include/linux/platform_data/mtd-davinci-aemif.h deleted file mode 100644 index a49826214a39..000000000000 --- a/include/linux/platform_data/mtd-davinci-aemif.h +++ /dev/null @@ -1,36 +0,0 @@ -/* - * TI DaVinci AEMIF support - * - * Copyright 2010 (C) Texas Instruments, Inc. https://www.ti.com/ - * - * This file is licensed under the terms of the GNU General Public License - * version 2. This program is licensed "as is" without any warranty of any - * kind, whether express or implied. - */ -#ifndef _MACH_DAVINCI_AEMIF_H -#define _MACH_DAVINCI_AEMIF_H - -#include <linux/platform_device.h> - -#define NRCSR_OFFSET 0x00 -#define AWCCR_OFFSET 0x04 -#define A1CR_OFFSET 0x10 - -#define ACR_ASIZE_MASK 0x3 -#define ACR_EW_MASK BIT(30) -#define ACR_SS_MASK BIT(31) - -/* All timings in nanoseconds */ -struct davinci_aemif_timing { - u8 wsetup; - u8 wstrobe; - u8 whold; - - u8 rsetup; - u8 rstrobe; - u8 rhold; - - u8 ta; -}; - -#endif diff --git a/include/linux/platform_data/mtd-davinci.h b/include/linux/platform_data/mtd-davinci.h deleted file mode 100644 index dd474dd44848..000000000000 --- a/include/linux/platform_data/mtd-davinci.h +++ /dev/null @@ -1,88 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * mach-davinci/nand.h - * - * Copyright © 2006 Texas Instruments. - * - * Ported to 2.6.23 Copyright © 2008 by - * Sander Huijsen <Shuijsen@optelecom-nkf.com> - * Troy Kisky <troy.kisky@boundarydevices.com> - * Dirk Behme <Dirk.Behme@gmail.com> - * - * -------------------------------------------------------------------------- - */ - -#ifndef __ARCH_ARM_DAVINCI_NAND_H -#define __ARCH_ARM_DAVINCI_NAND_H - -#include <linux/mtd/rawnand.h> - -#define NANDFCR_OFFSET 0x60 -#define NANDFSR_OFFSET 0x64 -#define NANDF1ECC_OFFSET 0x70 - -/* 4-bit ECC syndrome registers */ -#define NAND_4BIT_ECC_LOAD_OFFSET 0xbc -#define NAND_4BIT_ECC1_OFFSET 0xc0 -#define NAND_4BIT_ECC2_OFFSET 0xc4 -#define NAND_4BIT_ECC3_OFFSET 0xc8 -#define NAND_4BIT_ECC4_OFFSET 0xcc -#define NAND_ERR_ADD1_OFFSET 0xd0 -#define NAND_ERR_ADD2_OFFSET 0xd4 -#define NAND_ERR_ERRVAL1_OFFSET 0xd8 -#define NAND_ERR_ERRVAL2_OFFSET 0xdc - -/* NOTE: boards don't need to use these address bits - * for ALE/CLE unless they support booting from NAND. - * They're used unless platform data overrides them. - */ -#define MASK_ALE 0x08 -#define MASK_CLE 0x10 - -struct davinci_nand_pdata { /* platform_data */ - uint32_t mask_ale; - uint32_t mask_cle; - - /* - * 0-indexed chip-select number of the asynchronous - * interface to which the NAND device has been connected. - * - * So, if you have NAND connected to CS3 of DA850, you - * will pass '1' here. Since the asynchronous interface - * on DA850 starts from CS2. - */ - uint32_t core_chipsel; - - /* for packages using two chipselects */ - uint32_t mask_chipsel; - - /* board's default static partition info */ - struct mtd_partition *parts; - unsigned nr_parts; - - /* none == NAND_ECC_ENGINE_TYPE_NONE (strongly *not* advised!!) - * soft == NAND_ECC_ENGINE_TYPE_SOFT - * else == NAND_ECC_ENGINE_TYPE_ON_HOST, according to ecc_bits - * - * All DaVinci-family chips support 1-bit hardware ECC. - * Newer ones also support 4-bit ECC, but are awkward - * using it with large page chips. - */ - enum nand_ecc_engine_type engine_type; - enum nand_ecc_placement ecc_placement; - u8 ecc_bits; - - /* e.g. NAND_BUSWIDTH_16 */ - unsigned options; - /* e.g. NAND_BBT_USE_FLASH */ - unsigned bbt_options; - - /* Main and mirror bbt descriptor overrides */ - struct nand_bbt_descr *bbt_td; - struct nand_bbt_descr *bbt_md; - - /* Access timings */ - struct davinci_aemif_timing *timing; -}; - -#endif /* __ARCH_ARM_DAVINCI_NAND_H */ diff --git a/include/linux/platform_data/omap1_bl.h b/include/linux/platform_data/omap1_bl.h index 5e8b17d77a5f..3d0bab31a0a9 100644 --- a/include/linux/platform_data/omap1_bl.h +++ b/include/linux/platform_data/omap1_bl.h @@ -6,7 +6,6 @@ struct omap_backlight_config { int default_intensity; - int (*set_power)(struct device *dev, int state); }; #endif diff --git a/include/linux/platform_data/sa11x0-serial.h b/include/linux/platform_data/sa11x0-serial.h index 8b79ab08af45..a88096bc74e4 100644 --- a/include/linux/platform_data/sa11x0-serial.h +++ b/include/linux/platform_data/sa11x0-serial.h @@ -10,7 +10,6 @@ #define SA11X0_SERIAL_H struct uart_port; -struct uart_info; /* * This is a temporary structure for registering these diff --git a/include/linux/platform_data/spi-ep93xx.h b/include/linux/platform_data/spi-ep93xx.h deleted file mode 100644 index b439f2a896e0..000000000000 --- a/include/linux/platform_data/spi-ep93xx.h +++ /dev/null @@ -1,15 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __ASM_MACH_EP93XX_SPI_H -#define __ASM_MACH_EP93XX_SPI_H - -struct spi_device; - -/** - * struct ep93xx_spi_info - EP93xx specific SPI descriptor - * @use_dma: use DMA for the transfers - */ -struct ep93xx_spi_info { - bool use_dma; -}; - -#endif /* __ASM_MACH_EP93XX_SPI_H */ diff --git a/include/linux/platform_data/spi-omap2-mcspi.h b/include/linux/platform_data/spi-omap2-mcspi.h index 3b400b1919a9..9e3c15b4ac91 100644 --- a/include/linux/platform_data/spi-omap2-mcspi.h +++ b/include/linux/platform_data/spi-omap2-mcspi.h @@ -16,9 +16,6 @@ struct omap2_mcspi_platform_config { struct omap2_mcspi_device_config { unsigned turbo_mode:1; - - /* toggle chip select after every word */ - unsigned cs_per_word:1; }; #endif diff --git a/include/linux/platform_data/syscon.h b/include/linux/platform_data/syscon.h deleted file mode 100644 index 2c089dd3e2bd..000000000000 --- a/include/linux/platform_data/syscon.h +++ /dev/null @@ -1,9 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef PLATFORM_DATA_SYSCON_H -#define PLATFORM_DATA_SYSCON_H - -struct syscon_platform_data { - const char *label; -}; - -#endif diff --git a/include/linux/platform_data/ti-aemif.h b/include/linux/platform_data/ti-aemif.h deleted file mode 100644 index 77625251df07..000000000000 --- a/include/linux/platform_data/ti-aemif.h +++ /dev/null @@ -1,45 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * TI DaVinci AEMIF platform glue. - * - * Copyright (C) 2017 BayLibre SAS - * - * Author: - * Bartosz Golaszewski <bgolaszewski@baylibre.com> - */ - -#ifndef __TI_DAVINCI_AEMIF_DATA_H__ -#define __TI_DAVINCI_AEMIF_DATA_H__ - -#include <linux/of_platform.h> - -/** - * struct aemif_abus_data - Async bus configuration parameters. - * - * @cs - Chip-select number. - */ -struct aemif_abus_data { - u32 cs; -}; - -/** - * struct aemif_platform_data - Data to set up the TI aemif driver. - * - * @dev_lookup: of_dev_auxdata passed to of_platform_populate() for aemif - * subdevices. - * @cs_offset: Lowest allowed chip-select number. - * @abus_data: Array of async bus configuration entries. - * @num_abus_data: Number of abus entries. - * @sub_devices: Array of platform subdevices. - * @num_sub_devices: Number of subdevices. - */ -struct aemif_platform_data { - struct of_dev_auxdata *dev_lookup; - u32 cs_offset; - struct aemif_abus_data *abus_data; - size_t num_abus_data; - struct platform_device *sub_devices; - size_t num_sub_devices; -}; - -#endif /* __TI_DAVINCI_AEMIF_DATA_H__ */ diff --git a/include/linux/platform_data/ti-sysc.h b/include/linux/platform_data/ti-sysc.h index eb556f988d57..d8f15770a522 100644 --- a/include/linux/platform_data/ti-sysc.h +++ b/include/linux/platform_data/ti-sysc.h @@ -71,7 +71,6 @@ struct sysc_regbits { #define SYSC_QUIRK_SWSUP_SIDLE_ACT BIT(12) #define SYSC_QUIRK_SWSUP_SIDLE BIT(11) #define SYSC_QUIRK_EXT_OPT_CLOCK BIT(10) -#define SYSC_QUIRK_LEGACY_IDLE BIT(9) #define SYSC_QUIRK_RESET_STATUS BIT(8) #define SYSC_QUIRK_NO_IDLE BIT(7) #define SYSC_QUIRK_NO_IDLE_ON_INIT BIT(6) diff --git a/include/linux/platform_data/tmio.h b/include/linux/platform_data/tmio.h new file mode 100644 index 000000000000..b060124ba1ae --- /dev/null +++ b/include/linux/platform_data/tmio.h @@ -0,0 +1,62 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef MFD_TMIO_H +#define MFD_TMIO_H + +#include <linux/platform_device.h> +#include <linux/types.h> + +/* TMIO MMC platform flags */ + +/* + * Some controllers can support a 2-byte block size when the bus width is + * configured in 4-bit mode. + */ +#define TMIO_MMC_BLKSZ_2BYTES BIT(1) + +/* Some controllers can support SDIO IRQ signalling */ +#define TMIO_MMC_SDIO_IRQ BIT(2) + +/* Some features are only available or tested on R-Car Gen2 or later */ +#define TMIO_MMC_MIN_RCAR2 BIT(3) + +/* + * Some controllers require waiting for the SD bus to become idle before + * writing to some registers. + */ +#define TMIO_MMC_HAS_IDLE_WAIT BIT(4) + +/* + * Use the busy timeout feature. Probably all TMIO versions support it. Yet, + * we don't have documentation for old variants, so we enable only known good + * variants with this flag. Can be removed once all variants are known good. + */ +#define TMIO_MMC_USE_BUSY_TIMEOUT BIT(5) + +/* Some controllers have CMD12 automatically issue/non-issue register */ +#define TMIO_MMC_HAVE_CMD12_CTRL BIT(7) + +/* Controller has some SDIO status bits which must be 1 */ +#define TMIO_MMC_SDIO_STATUS_SETBITS BIT(8) + +/* Some controllers have a 32-bit wide data port register */ +#define TMIO_MMC_32BIT_DATA_PORT BIT(9) + +/* Some controllers allows to set SDx actual clock */ +#define TMIO_MMC_CLK_ACTUAL BIT(10) + +/* Some controllers have a CBSY bit */ +#define TMIO_MMC_HAVE_CBSY BIT(11) + +struct tmio_mmc_data { + void *chan_priv_tx; + void *chan_priv_rx; + unsigned int hclk; + unsigned long capabilities; + unsigned long capabilities2; + unsigned long flags; + u32 ocr_mask; /* available voltages */ + dma_addr_t dma_rx_offset; + unsigned int max_blk_count; + unsigned short max_segs; +}; +#endif diff --git a/include/linux/platform_data/uio_pruss.h b/include/linux/platform_data/uio_pruss.h deleted file mode 100644 index f76fa393b802..000000000000 --- a/include/linux/platform_data/uio_pruss.h +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * include/linux/platform_data/uio_pruss.h - * - * Platform data for uio_pruss driver - * - * Copyright (C) 2010-11 Texas Instruments Incorporated - https://www.ti.com/ - */ - -#ifndef _UIO_PRUSS_H_ -#define _UIO_PRUSS_H_ - -/* To configure the PRUSS INTC base offset for UIO driver */ -struct uio_pruss_pdata { - u32 pintc_base; - struct gen_pool *sram_pool; -}; -#endif /* _UIO_PRUSS_H_ */ diff --git a/include/linux/platform_data/x86/asus-wmi.h b/include/linux/platform_data/x86/asus-wmi.h index ab1c7deff118..783e2a336861 100644 --- a/include/linux/platform_data/x86/asus-wmi.h +++ b/include/linux/platform_data/x86/asus-wmi.h @@ -4,6 +4,7 @@ #include <linux/errno.h> #include <linux/types.h> +#include <linux/dmi.h> /* WMI Methods */ #define ASUS_WMI_METHODID_SPEC 0x43455053 /* BIOS SPECification */ @@ -51,6 +52,10 @@ #define ASUS_WMI_DEVID_LED6 0x00020016 #define ASUS_WMI_DEVID_MICMUTE_LED 0x00040017 +/* Disable Camera LED */ +#define ASUS_WMI_DEVID_CAMERA_LED_NEG 0x00060078 /* 0 = on (unused) */ +#define ASUS_WMI_DEVID_CAMERA_LED 0x00060079 /* 1 = on */ + /* Backlight and Brightness */ #define ASUS_WMI_DEVID_ALS_ENABLE 0x00050001 /* Ambient Light Sensor */ #define ASUS_WMI_DEVID_BACKLIGHT 0x00050011 @@ -58,12 +63,14 @@ #define ASUS_WMI_DEVID_KBD_BACKLIGHT 0x00050021 #define ASUS_WMI_DEVID_LIGHT_SENSOR 0x00050022 /* ?? */ #define ASUS_WMI_DEVID_LIGHTBAR 0x00050025 +#define ASUS_WMI_DEVID_OOBE 0x0005002F /* This can only be used to disable the screen, not re-enable */ #define ASUS_WMI_DEVID_SCREENPAD_POWER 0x00050031 /* Writing a brightness re-enables the screen if disabled */ #define ASUS_WMI_DEVID_SCREENPAD_LIGHT 0x00050032 #define ASUS_WMI_DEVID_FAN_BOOST_MODE 0x00110018 #define ASUS_WMI_DEVID_THROTTLE_THERMAL_POLICY 0x00120075 +#define ASUS_WMI_DEVID_THROTTLE_THERMAL_POLICY_VIVO 0x00110019 /* Misc */ #define ASUS_WMI_DEVID_PANEL_OD 0x00050019 @@ -71,6 +78,7 @@ #define ASUS_WMI_DEVID_LID_FLIP 0x00060062 #define ASUS_WMI_DEVID_LID_FLIP_ROG 0x00060077 #define ASUS_WMI_DEVID_MINI_LED_MODE 0x0005001E +#define ASUS_WMI_DEVID_MINI_LED_MODE2 0x0005002E /* Storage */ #define ASUS_WMI_DEVID_CARDREADER 0x00080013 @@ -127,13 +135,18 @@ /* gpu mux switch, 0 = dGPU, 1 = Optimus */ #define ASUS_WMI_DEVID_GPU_MUX 0x00090016 +#define ASUS_WMI_DEVID_GPU_MUX_VIVO 0x00090026 /* TUF laptop RGB modes/colours */ #define ASUS_WMI_DEVID_TUF_RGB_MODE 0x00100056 +#define ASUS_WMI_DEVID_TUF_RGB_MODE2 0x0010005A /* TUF laptop RGB power/state */ #define ASUS_WMI_DEVID_TUF_RGB_STATE 0x00100057 +/* Bootup sound control */ +#define ASUS_WMI_DEVID_BOOT_SOUND 0x00130022 + /* DSTS masks */ #define ASUS_WMI_DSTS_STATUS_BIT 0x00000001 #define ASUS_WMI_DSTS_UNKNOWN_BIT 0x00000002 @@ -154,4 +167,44 @@ static inline int asus_wmi_evaluate_method(u32 method_id, u32 arg0, u32 arg1, } #endif +/* To be used by both hid-asus and asus-wmi to determine which controls kbd_brightness */ +static const struct dmi_system_id asus_use_hid_led_dmi_ids[] = { + { + .matches = { + DMI_MATCH(DMI_PRODUCT_FAMILY, "ROG Zephyrus"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_PRODUCT_FAMILY, "ROG Strix"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_PRODUCT_FAMILY, "ROG Flow"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_PRODUCT_FAMILY, "ProArt P16"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "GA403U"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "GU605M"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "RC71L"), + }, + }, + { }, +}; + #endif /* __PLATFORM_DATA_X86_ASUS_WMI_H */ diff --git a/include/linux/platform_data/intel-mid_wdt.h b/include/linux/platform_data/x86/intel-mid_wdt.h index 8dba70b4b020..e5c0210d0fec 100644 --- a/include/linux/platform_data/intel-mid_wdt.h +++ b/include/linux/platform_data/x86/intel-mid_wdt.h @@ -6,8 +6,8 @@ * Contact: David Cohen <david.a.cohen@linux.intel.com> */ -#ifndef __INTEL_MID_WDT_H__ -#define __INTEL_MID_WDT_H__ +#ifndef __PLATFORM_X86_INTEL_MID_WDT_H_ +#define __PLATFORM_X86_INTEL_MID_WDT_H_ #include <linux/platform_device.h> @@ -16,4 +16,4 @@ struct intel_mid_wdt_pdata { int (*probe)(struct platform_device *pdev); }; -#endif /*__INTEL_MID_WDT_H__*/ +#endif /* __PLATFORM_X86_INTEL_MID_WDT_H_ */ diff --git a/include/linux/platform_data/x86/intel_scu_ipc.h b/include/linux/platform_data/x86/intel_scu_ipc.h new file mode 100644 index 000000000000..b287627759f7 --- /dev/null +++ b/include/linux/platform_data/x86/intel_scu_ipc.h @@ -0,0 +1,72 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PLATFORM_X86_INTEL_SCU_IPC_H_ +#define __PLATFORM_X86_INTEL_SCU_IPC_H_ + +#include <linux/init.h> +#include <linux/ioport.h> +#include <linux/types.h> + +struct device; +struct module; + +struct intel_scu_ipc_dev; + +/** + * struct intel_scu_ipc_data - Data used to configure SCU IPC + * @mem: Base address of SCU IPC MMIO registers + * @irq: The IRQ number used for SCU (optional) + */ +struct intel_scu_ipc_data { + struct resource mem; + int irq; +}; + +struct intel_scu_ipc_dev * +__intel_scu_ipc_register(struct device *parent, + const struct intel_scu_ipc_data *scu_data, + struct module *owner); + +#define intel_scu_ipc_register(parent, scu_data) \ + __intel_scu_ipc_register(parent, scu_data, THIS_MODULE) + +void intel_scu_ipc_unregister(struct intel_scu_ipc_dev *scu); + +struct intel_scu_ipc_dev * +__devm_intel_scu_ipc_register(struct device *parent, + const struct intel_scu_ipc_data *scu_data, + struct module *owner); + +#define devm_intel_scu_ipc_register(parent, scu_data) \ + __devm_intel_scu_ipc_register(parent, scu_data, THIS_MODULE) + +struct intel_scu_ipc_dev *intel_scu_ipc_dev_get(void); +void intel_scu_ipc_dev_put(struct intel_scu_ipc_dev *scu); +struct intel_scu_ipc_dev *devm_intel_scu_ipc_dev_get(struct device *dev); + +int intel_scu_ipc_dev_ioread8(struct intel_scu_ipc_dev *scu, u16 addr, + u8 *data); +int intel_scu_ipc_dev_iowrite8(struct intel_scu_ipc_dev *scu, u16 addr, + u8 data); +int intel_scu_ipc_dev_readv(struct intel_scu_ipc_dev *scu, u16 *addr, + u8 *data, size_t len); +int intel_scu_ipc_dev_writev(struct intel_scu_ipc_dev *scu, u16 *addr, + u8 *data, size_t len); + +int intel_scu_ipc_dev_update(struct intel_scu_ipc_dev *scu, u16 addr, + u8 data, u8 mask); + +int intel_scu_ipc_dev_simple_command(struct intel_scu_ipc_dev *scu, int cmd, + int sub); +int intel_scu_ipc_dev_command_with_size(struct intel_scu_ipc_dev *scu, int cmd, + int sub, const void *in, size_t inlen, + size_t size, void *out, size_t outlen); + +static inline int intel_scu_ipc_dev_command(struct intel_scu_ipc_dev *scu, int cmd, + int sub, const void *in, size_t inlen, + void *out, size_t outlen) +{ + return intel_scu_ipc_dev_command_with_size(scu, cmd, sub, in, inlen, + inlen, out, outlen); +} + +#endif diff --git a/include/linux/platform_data/x86/soc.h b/include/linux/platform_data/x86/soc.h index a5705189e2ac..f981907a5cb0 100644 --- a/include/linux/platform_data/x86/soc.h +++ b/include/linux/platform_data/x86/soc.h @@ -20,7 +20,7 @@ static inline bool soc_intel_is_##soc(void) \ { \ static const struct x86_cpu_id soc##_cpu_ids[] = { \ - X86_MATCH_INTEL_FAM6_MODEL(type, NULL), \ + X86_MATCH_VFM(type, NULL), \ {} \ }; \ const struct x86_cpu_id *id; \ @@ -31,11 +31,11 @@ static inline bool soc_intel_is_##soc(void) \ return false; \ } -SOC_INTEL_IS_CPU(byt, ATOM_SILVERMONT); -SOC_INTEL_IS_CPU(cht, ATOM_AIRMONT); -SOC_INTEL_IS_CPU(apl, ATOM_GOLDMONT); -SOC_INTEL_IS_CPU(glk, ATOM_GOLDMONT_PLUS); -SOC_INTEL_IS_CPU(cml, KABYLAKE_L); +SOC_INTEL_IS_CPU(byt, INTEL_ATOM_SILVERMONT); +SOC_INTEL_IS_CPU(cht, INTEL_ATOM_AIRMONT); +SOC_INTEL_IS_CPU(apl, INTEL_ATOM_GOLDMONT); +SOC_INTEL_IS_CPU(glk, INTEL_ATOM_GOLDMONT_PLUS); +SOC_INTEL_IS_CPU(cml, INTEL_KABYLAKE_L); #undef SOC_INTEL_IS_CPU diff --git a/include/linux/platform_data/zforce_ts.h b/include/linux/platform_data/zforce_ts.h deleted file mode 100644 index 2463a4a856a6..000000000000 --- a/include/linux/platform_data/zforce_ts.h +++ /dev/null @@ -1,15 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* drivers/input/touchscreen/zforce.c - * - * Copyright (C) 2012-2013 MundoReader S.L. - */ - -#ifndef _LINUX_INPUT_ZFORCE_TS_H -#define _LINUX_INPUT_ZFORCE_TS_H - -struct zforce_ts_platdata { - unsigned int x_max; - unsigned int y_max; -}; - -#endif /* _LINUX_INPUT_ZFORCE_TS_H */ diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index 7a41c72c1959..074754c23d33 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -52,7 +52,7 @@ struct platform_device { extern int platform_device_register(struct platform_device *); extern void platform_device_unregister(struct platform_device *); -extern struct bus_type platform_bus_type; +extern const struct bus_type platform_bus_type; extern struct device platform_bus; extern struct resource *platform_get_resource(struct platform_device *, @@ -235,18 +235,7 @@ 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 (*remove)(struct platform_device *); void (*shutdown)(struct platform_device *); int (*suspend)(struct platform_device *, pm_message_t state); int (*resume)(struct platform_device *); diff --git a/include/linux/platform_profile.h b/include/linux/platform_profile.h index e5cbb6841f3a..8ab5b0e8eb2c 100644 --- a/include/linux/platform_profile.h +++ b/include/linux/platform_profile.h @@ -9,6 +9,7 @@ #ifndef _PLATFORM_PROFILE_H_ #define _PLATFORM_PROFILE_H_ +#include <linux/device.h> #include <linux/bitops.h> /* @@ -23,19 +24,34 @@ enum platform_profile_option { PLATFORM_PROFILE_BALANCED, PLATFORM_PROFILE_BALANCED_PERFORMANCE, PLATFORM_PROFILE_PERFORMANCE, + PLATFORM_PROFILE_CUSTOM, PLATFORM_PROFILE_LAST, /*must always be last */ }; -struct platform_profile_handler { - unsigned long choices[BITS_TO_LONGS(PLATFORM_PROFILE_LAST)]; - int (*profile_get)(struct platform_profile_handler *pprof, - enum platform_profile_option *profile); - int (*profile_set)(struct platform_profile_handler *pprof, - enum platform_profile_option profile); +/** + * struct platform_profile_ops - platform profile operations + * @probe: Callback to setup choices available to the new class device. These + * choices will only be enforced when setting a new profile, not when + * getting the current one. + * @profile_get: Callback that will be called when showing the current platform + * profile in sysfs. + * @profile_set: Callback that will be called when storing a new platform + * profile in sysfs. + */ +struct platform_profile_ops { + int (*probe)(void *drvdata, unsigned long *choices); + int (*profile_get)(struct device *dev, enum platform_profile_option *profile); + int (*profile_set)(struct device *dev, enum platform_profile_option profile); }; -int platform_profile_register(struct platform_profile_handler *pprof); -int platform_profile_remove(void); -void platform_profile_notify(void); +struct device *platform_profile_register(struct device *dev, const char *name, + void *drvdata, + const struct platform_profile_ops *ops); +int platform_profile_remove(struct device *dev); +struct device *devm_platform_profile_register(struct device *dev, const char *name, + void *drvdata, + const struct platform_profile_ops *ops); +int platform_profile_cycle(void); +void platform_profile_notify(struct device *dev); #endif /*_PLATFORM_PROFILE_H_*/ diff --git a/include/linux/pldmfw.h b/include/linux/pldmfw.h index 0fc831338226..f5047983004f 100644 --- a/include/linux/pldmfw.h +++ b/include/linux/pldmfw.h @@ -125,9 +125,17 @@ struct pldmfw_ops; * a pointer to their own data, used to implement the device specific * operations. */ + +enum pldmfw_update_mode { + PLDMFW_UPDATE_MODE_FULL, + PLDMFW_UPDATE_MODE_SINGLE_COMPONENT, +}; + struct pldmfw { const struct pldmfw_ops *ops; struct device *dev; + u16 component_identifier; + enum pldmfw_update_mode mode; }; bool pldmfw_op_pci_match_record(struct pldmfw *context, struct pldmfw_record *record); diff --git a/include/linux/pm.h b/include/linux/pm.h index 97b0e23363c8..78855d794342 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -384,12 +384,8 @@ const struct dev_pm_ops name = { \ #ifdef CONFIG_PM #define _EXPORT_DEV_PM_OPS(name, license, ns) _EXPORT_PM_OPS(name, license, ns) -#define EXPORT_PM_FN_GPL(name) EXPORT_SYMBOL_GPL(name) -#define EXPORT_PM_FN_NS_GPL(name, ns) EXPORT_SYMBOL_NS_GPL(name, ns) #else #define _EXPORT_DEV_PM_OPS(name, license, ns) _DISCARD_PM_OPS(name, license, ns) -#define EXPORT_PM_FN_GPL(name) -#define EXPORT_PM_FN_NS_GPL(name, ns) #endif #ifdef CONFIG_PM_SLEEP @@ -570,7 +566,8 @@ const struct dev_pm_ops name = { \ { .event = PM_EVENT_AUTO_RESUME, }) #define PMSG_IS_AUTO(msg) (((msg).event & PM_EVENT_AUTO) != 0) - +#define PMSG_NO_WAKEUP(msg) (((msg).event & \ + (PM_EVENT_FREEZE | PM_EVENT_QUIESCE)) != 0) /* * Device run-time power management status. * @@ -683,6 +680,7 @@ struct dev_pm_info { bool no_pm_callbacks:1; /* Owned by the PM core */ bool async_in_progress:1; /* Owned by the PM core */ bool must_resume:1; /* Owned by the PM core */ + bool set_active:1; /* Owned by the PM core */ bool may_skip_resume:1; /* Set by subsystems */ #else bool should_wakeup:1; diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 772d3280d35f..1aab31370065 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -16,7 +16,7 @@ #include <linux/of.h> #include <linux/notifier.h> #include <linux/spinlock.h> -#include <linux/cpumask.h> +#include <linux/cpumask_types.h> #include <linux/time64.h> /* @@ -30,9 +30,16 @@ * supplier and its PM domain when creating the * device-links. * + * PD_FLAG_REQUIRED_OPP: Assign required_devs for the required OPPs. The + * index of the required OPP must correspond to the + * index in the array of the pd_names. If pd_names + * isn't specified, the index just follows the + * index for the attached PM domain. + * */ #define PD_FLAG_NO_DEV_LINK BIT(0) #define PD_FLAG_DEV_LINK_ON BIT(1) +#define PD_FLAG_REQUIRED_OPP BIT(2) struct dev_pm_domain_attach_data { const char * const *pd_names; @@ -43,6 +50,7 @@ struct dev_pm_domain_attach_data { struct dev_pm_domain_list { struct device **pd_devs; struct device_link **pd_links; + u32 *opp_tokens; u32 num_pds; }; @@ -92,6 +100,10 @@ struct dev_pm_domain_list { * GENPD_FLAG_OPP_TABLE_FW: The genpd provider supports performance states, * but its corresponding OPP tables are not * described in DT, but are given directly by FW. + * + * GENPD_FLAG_DEV_NAME_FW: Instructs genpd to generate an unique device name + * using ida. It is used by genpd providers which + * get their genpd-names directly from FW. */ #define GENPD_FLAG_PM_CLK (1U << 0) #define GENPD_FLAG_IRQ_SAFE (1U << 1) @@ -101,6 +113,7 @@ struct dev_pm_domain_list { #define GENPD_FLAG_RPM_ALWAYS_ON (1U << 5) #define GENPD_FLAG_MIN_RESIDENCY (1U << 6) #define GENPD_FLAG_OPP_TABLE_FW (1U << 7) +#define GENPD_FLAG_DEV_NAME_FW (1U << 8) enum gpd_status { GENPD_STATE_ON = 0, /* PM domain is on */ @@ -134,6 +147,7 @@ struct genpd_governor_data { }; struct genpd_power_state { + const char *name; s64 power_off_latency_ns; s64 power_on_latency_ns; s64 residency_ns; @@ -163,6 +177,7 @@ struct generic_pm_domain { atomic_t sd_count; /* Number of subdomains with power "on" */ enum gpd_status status; /* Current state of the domain */ unsigned int device_count; /* Number of devices */ + unsigned int device_id; /* unique device id */ unsigned int suspended_count; /* System suspend device counter */ unsigned int prepared_count; /* Suspend counter of prepared devices */ unsigned int performance_state; /* Aggregated max performance state */ @@ -175,6 +190,10 @@ struct generic_pm_domain { int (*set_performance_state)(struct generic_pm_domain *genpd, unsigned int state); struct gpd_dev_ops dev_ops; + int (*set_hwmode_dev)(struct generic_pm_domain *domain, + struct device *dev, bool enable); + bool (*get_hwmode_dev)(struct generic_pm_domain *domain, + struct device *dev); int (*attach_dev)(struct generic_pm_domain *domain, struct device *dev); void (*detach_dev)(struct generic_pm_domain *domain, @@ -194,8 +213,11 @@ struct generic_pm_domain { spinlock_t slock; unsigned long lock_flags; }; + struct { + raw_spinlock_t raw_slock; + unsigned long raw_lock_flags; + }; }; - }; static inline struct generic_pm_domain *pd_to_genpd(struct dev_pm_domain *pd) @@ -237,6 +259,8 @@ struct generic_pm_domain_data { unsigned int performance_state; unsigned int default_pstate; unsigned int rpm_pstate; + unsigned int opp_token; + bool hw_mode; void *data; }; @@ -260,12 +284,15 @@ int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd, int pm_genpd_init(struct generic_pm_domain *genpd, struct dev_power_governor *gov, bool is_off); int pm_genpd_remove(struct generic_pm_domain *genpd); +struct device *dev_to_genpd_dev(struct device *dev); int dev_pm_genpd_set_performance_state(struct device *dev, unsigned int state); 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); +int dev_pm_genpd_set_hwmode(struct device *dev, bool enable); +bool dev_pm_genpd_get_hwmode(struct device *dev); extern struct dev_power_governor simple_qos_governor; extern struct dev_power_governor pm_domain_always_on_gov; @@ -307,6 +334,11 @@ static inline int pm_genpd_remove(struct generic_pm_domain *genpd) return -EOPNOTSUPP; } +static inline struct device *dev_to_genpd_dev(struct device *dev) +{ + return ERR_PTR(-EOPNOTSUPP); +} + static inline int dev_pm_genpd_set_performance_state(struct device *dev, unsigned int state) { @@ -334,6 +366,16 @@ static inline ktime_t dev_pm_genpd_get_next_hrtimer(struct device *dev) static inline void dev_pm_genpd_synced_poweroff(struct device *dev) { } +static inline int dev_pm_genpd_set_hwmode(struct device *dev, bool enable) +{ + return -EOPNOTSUPP; +} + +static inline bool dev_pm_genpd_get_hwmode(struct device *dev) +{ + return false; +} + #define simple_qos_governor (*(struct dev_power_governor *)(NULL)) #define pm_domain_always_on_gov (*(struct dev_power_governor *)(NULL)) #endif @@ -450,6 +492,9 @@ struct device *dev_pm_domain_attach_by_name(struct device *dev, int dev_pm_domain_attach_list(struct device *dev, const struct dev_pm_domain_attach_data *data, struct dev_pm_domain_list **list); +int devm_pm_domain_attach_list(struct device *dev, + const struct dev_pm_domain_attach_data *data, + struct dev_pm_domain_list **list); void dev_pm_domain_detach(struct device *dev, bool power_off); void dev_pm_domain_detach_list(struct dev_pm_domain_list *list); int dev_pm_domain_start(struct device *dev); @@ -476,6 +521,14 @@ static inline int dev_pm_domain_attach_list(struct device *dev, { return 0; } + +static inline int devm_pm_domain_attach_list(struct device *dev, + const struct dev_pm_domain_attach_data *data, + struct dev_pm_domain_list **list) +{ + return 0; +} + static inline void dev_pm_domain_detach(struct device *dev, bool power_off) {} static inline void dev_pm_domain_detach_list(struct dev_pm_domain_list *list) {} static inline int dev_pm_domain_start(struct device *dev) diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 065a47382302..c247317aae38 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -62,11 +62,8 @@ typedef int (*config_clks_t)(struct device *dev, struct opp_table *opp_table, * @supported_hw: Array of hierarchy of versions to match. * @supported_hw_count: Number of elements in the array. * @regulator_names: Array of pointers to the names of the regulator, NULL terminated. - * @genpd_names: Null terminated array of pointers containing names of genpd to - * attach. Mutually exclusive with required_devs. - * @virt_devs: Pointer to return the array of genpd virtual devices. Mutually - * exclusive with required_devs. - * @required_devs: Required OPP devices. Mutually exclusive with genpd_names/virt_devs. + * @required_dev: The required OPP device. + * @required_dev_index: The index of the required OPP for the @required_dev. * * This structure contains platform specific OPP configurations for the device. */ @@ -79,9 +76,8 @@ struct dev_pm_opp_config { const unsigned int *supported_hw; unsigned int supported_hw_count; const char * const *regulator_names; - const char * const *genpd_names; - struct device ***virt_devs; - struct device **required_devs; + struct device *required_dev; + unsigned int required_dev_index; }; #define OPP_LEVEL_UNSET U32_MAX @@ -104,8 +100,11 @@ struct dev_pm_opp_data { #if defined(CONFIG_PM_OPP) struct opp_table *dev_pm_opp_get_opp_table(struct device *dev); +void dev_pm_opp_get_opp_table_ref(struct opp_table *opp_table); void dev_pm_opp_put_opp_table(struct opp_table *opp_table); +unsigned long dev_pm_opp_get_bw(struct dev_pm_opp *opp, bool peak, int index); + unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp); int dev_pm_opp_get_supplies(struct dev_pm_opp *opp, struct dev_pm_opp_supply *supplies); @@ -162,6 +161,7 @@ struct dev_pm_opp *dev_pm_opp_find_bw_ceil(struct device *dev, struct dev_pm_opp *dev_pm_opp_find_bw_floor(struct device *dev, unsigned int *bw, int index); +void dev_pm_opp_get(struct dev_pm_opp *opp); void dev_pm_opp_put(struct dev_pm_opp *opp); int dev_pm_opp_add_dynamic(struct device *dev, struct dev_pm_opp_data *opp); @@ -207,8 +207,15 @@ static inline struct opp_table *dev_pm_opp_get_opp_table_indexed(struct device * return ERR_PTR(-EOPNOTSUPP); } +static inline void dev_pm_opp_get_opp_table_ref(struct opp_table *opp_table) {} + static inline void dev_pm_opp_put_opp_table(struct opp_table *opp_table) {} +static inline unsigned long dev_pm_opp_get_bw(struct dev_pm_opp *opp, bool peak, int index) +{ + return 0; +} + static inline unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp) { return 0; @@ -338,6 +345,8 @@ static inline struct dev_pm_opp *dev_pm_opp_find_bw_floor(struct device *dev, return ERR_PTR(-EOPNOTSUPP); } +static inline void dev_pm_opp_get(struct dev_pm_opp *opp) {} + static inline void dev_pm_opp_put(struct dev_pm_opp *opp) {} static inline int @@ -474,8 +483,11 @@ int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpuma struct device_node *dev_pm_opp_of_get_opp_desc_node(struct device *dev); struct device_node *dev_pm_opp_get_of_node(struct dev_pm_opp *opp); int of_get_required_opp_performance_state(struct device_node *np, int index); +bool dev_pm_opp_of_has_required_opp(struct device *dev); int dev_pm_opp_of_find_icc_paths(struct device *dev, struct opp_table *opp_table); int dev_pm_opp_of_register_em(struct device *dev, struct cpumask *cpus); +int dev_pm_opp_calc_power(struct device *dev, unsigned long *uW, + unsigned long *kHz); static inline void dev_pm_opp_of_unregister_em(struct device *dev) { em_dev_unregister_perf_domain(dev); @@ -539,11 +551,22 @@ static inline void dev_pm_opp_of_unregister_em(struct device *dev) { } +static inline int dev_pm_opp_calc_power(struct device *dev, unsigned long *uW, + unsigned long *kHz) +{ + return -EOPNOTSUPP; +} + static inline int of_get_required_opp_performance_state(struct device_node *np, int index) { return -EOPNOTSUPP; } +static inline bool dev_pm_opp_of_has_required_opp(struct device *dev) +{ + return false; +} + static inline int dev_pm_opp_of_find_icc_paths(struct device *dev, struct opp_table *opp_table) { return -EOPNOTSUPP; @@ -661,36 +684,6 @@ static inline void dev_pm_opp_put_config_regulators(int token) dev_pm_opp_clear_config(token); } -/* genpd helpers */ -static inline int dev_pm_opp_attach_genpd(struct device *dev, - const char * const *names, - struct device ***virt_devs) -{ - struct dev_pm_opp_config config = { - .genpd_names = names, - .virt_devs = virt_devs, - }; - - return dev_pm_opp_set_config(dev, &config); -} - -static inline void dev_pm_opp_detach_genpd(int token) -{ - dev_pm_opp_clear_config(token); -} - -static inline int devm_pm_opp_attach_genpd(struct device *dev, - const char * const *names, - struct device ***virt_devs) -{ - struct dev_pm_opp_config config = { - .genpd_names = names, - .virt_devs = virt_devs, - }; - - return devm_pm_opp_set_config(dev, &config); -} - /* prop-name helpers */ static inline int dev_pm_opp_set_prop_name(struct device *dev, const char *name) { diff --git a/include/linux/pm_wakeirq.h b/include/linux/pm_wakeirq.h index d9642c6cf852..25b63ed51b76 100644 --- a/include/linux/pm_wakeirq.h +++ b/include/linux/pm_wakeirq.h @@ -10,6 +10,7 @@ extern int dev_pm_set_wake_irq(struct device *dev, int irq); extern int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq); extern int dev_pm_set_dedicated_wake_irq_reverse(struct device *dev, int irq); extern void dev_pm_clear_wake_irq(struct device *dev); +extern int devm_pm_set_wake_irq(struct device *dev, int irq); #else /* !CONFIG_PM */ @@ -32,5 +33,10 @@ static inline void dev_pm_clear_wake_irq(struct device *dev) { } +static inline int devm_pm_set_wake_irq(struct device *dev, int irq) +{ + return 0; +} + #endif /* CONFIG_PM */ #endif /* _LINUX_PM_WAKEIRQ_H */ diff --git a/include/linux/pm_wakeup.h b/include/linux/pm_wakeup.h index 6eb9adaef52b..d501c09c60cd 100644 --- a/include/linux/pm_wakeup.h +++ b/include/linux/pm_wakeup.h @@ -10,7 +10,7 @@ #define _LINUX_PM_WAKEUP_H #ifndef _DEVICE_H_ -# error "please don't include this file directly" +# error "Please do not include this file directly." #endif #include <linux/types.h> @@ -107,7 +107,7 @@ extern void wakeup_sources_read_unlock(int idx); extern struct wakeup_source *wakeup_sources_walk_start(void); extern struct wakeup_source *wakeup_sources_walk_next(struct wakeup_source *ws); extern int device_wakeup_enable(struct device *dev); -extern int device_wakeup_disable(struct device *dev); +extern void device_wakeup_disable(struct device *dev); extern void device_set_wakeup_capable(struct device *dev, bool capable); extern int device_set_wakeup_enable(struct device *dev, bool enable); extern void __pm_stay_awake(struct wakeup_source *ws); @@ -154,10 +154,9 @@ static inline int device_wakeup_enable(struct device *dev) return 0; } -static inline int device_wakeup_disable(struct device *dev) +static inline void device_wakeup_disable(struct device *dev) { dev->power.should_wakeup = false; - return 0; } static inline int device_set_wakeup_enable(struct device *dev, bool enable) @@ -235,11 +234,27 @@ static inline int device_init_wakeup(struct device *dev, bool enable) if (enable) { device_set_wakeup_capable(dev, true); return device_wakeup_enable(dev); - } else { - device_wakeup_disable(dev); - device_set_wakeup_capable(dev, false); - return 0; } + device_wakeup_disable(dev); + device_set_wakeup_capable(dev, false); + return 0; +} + +static void device_disable_wakeup(void *dev) +{ + device_init_wakeup(dev, false); +} + +/** + * devm_device_init_wakeup - Resource managed device wakeup initialization. + * @dev: Device to handle. + * + * This function is the devm managed version of device_init_wakeup(dev, true). + */ +static inline int devm_device_init_wakeup(struct device *dev) +{ + device_init_wakeup(dev, true); + return devm_add_action_or_reset(dev, device_disable_wakeup, dev); } #endif /* _LINUX_PM_WAKEUP_H */ diff --git a/include/linux/pmbus.h b/include/linux/pmbus.h index fa9f08164c36..884040e1383b 100644 --- a/include/linux/pmbus.h +++ b/include/linux/pmbus.h @@ -73,6 +73,20 @@ */ #define PMBUS_USE_COEFFICIENTS_CMD BIT(5) +/* + * PMBUS_OP_PROTECTED + * Set if the chip OPERATION command is protected and protection is not + * determined by the standard WRITE_PROTECT command. + */ +#define PMBUS_OP_PROTECTED BIT(6) + +/* + * PMBUS_VOUT_PROTECTED + * Set if the chip VOUT_COMMAND command is protected and protection is not + * determined by the standard WRITE_PROTECT command. + */ +#define PMBUS_VOUT_PROTECTED BIT(7) + struct pmbus_platform_data { u32 flags; /* Device specific flags */ diff --git a/include/linux/pnp.h b/include/linux/pnp.h index ddbe7c3ca4ce..b7a7158aaf65 100644 --- a/include/linux/pnp.h +++ b/include/linux/pnp.h @@ -383,7 +383,7 @@ struct pnp_driver { struct device_driver driver; }; -#define to_pnp_driver(drv) container_of(drv, struct pnp_driver, driver) +#define to_pnp_driver(drv) container_of_const(drv, struct pnp_driver, driver) struct pnp_card_driver { struct list_head global_list; @@ -435,8 +435,6 @@ struct pnp_protocol { #define protocol_for_each_dev(protocol, dev) \ list_for_each_entry(dev, &(protocol)->devices, protocol_list) -extern const struct bus_type pnp_bus_type; - #if defined(CONFIG_PNP) /* device management */ @@ -469,6 +467,8 @@ int compare_pnp_id(struct pnp_id *pos, const char *id); int pnp_register_driver(struct pnp_driver *drv); void pnp_unregister_driver(struct pnp_driver *drv); +bool dev_is_pnp(const struct device *dev); + #else /* device management */ @@ -500,6 +500,8 @@ static inline int compare_pnp_id(struct pnp_id *pos, const char *id) { return -E static inline int pnp_register_driver(struct pnp_driver *drv) { return -ENODEV; } static inline void pnp_unregister_driver(struct pnp_driver *drv) { } +static inline bool dev_is_pnp(const struct device *dev) { return false; } + #endif /* CONFIG_PNP */ /** diff --git a/include/linux/poison.h b/include/linux/poison.h index 1f0ee2459f2a..331a9a996fa8 100644 --- a/include/linux/poison.h +++ b/include/linux/poison.h @@ -38,11 +38,8 @@ * Magic nums for obj red zoning. * Placed in the first word before and the first word after an obj. */ -#define RED_INACTIVE 0x09F911029D74E35BULL /* when obj is inactive */ -#define RED_ACTIVE 0xD84156C5635688C0ULL /* when obj is active */ - -#define SLUB_RED_INACTIVE 0xbb -#define SLUB_RED_ACTIVE 0xcc +#define SLUB_RED_INACTIVE 0xbb /* when obj is inactive */ +#define SLUB_RED_ACTIVE 0xcc /* when obj is active */ /* ...and for poisoning */ #define POISON_INUSE 0x5a /* for use-uninitialised poisoning */ @@ -52,12 +49,6 @@ /********** arch/$ARCH/mm/init.c **********/ #define POISON_FREE_INITMEM 0xcc -/********** arch/ia64/hp/common/sba_iommu.c **********/ -/* - * arch/ia64/hp/common/sba_iommu.c uses a 16-byte poison string with a - * value of "SBAIOMMU POISON\0" for spill-over poisoning. - */ - /********** fs/jbd/journal.c **********/ #define JBD_POISON_FREE 0x5b #define JBD2_POISON_FREE 0x5c diff --git a/include/linux/poll.h b/include/linux/poll.h index d1ea4f3714a8..12bb18e8b978 100644 --- a/include/linux/poll.h +++ b/include/linux/poll.h @@ -25,14 +25,14 @@ struct poll_table_struct; -/* +/* * structures and helpers for f_op->poll implementations */ typedef void (*poll_queue_proc)(struct file *, wait_queue_head_t *, struct poll_table_struct *); /* - * Do not touch the structure directly, use the access functions - * poll_does_not_wait() and poll_requested_events() instead. + * Do not touch the structure directly, use the access function + * poll_requested_events() instead. */ typedef struct poll_table_struct { poll_queue_proc _qproc; @@ -41,18 +41,16 @@ typedef struct poll_table_struct { static inline void poll_wait(struct file * filp, wait_queue_head_t * wait_address, poll_table *p) { - if (p && p->_qproc && wait_address) + if (p && p->_qproc) { p->_qproc(filp, wait_address, p); -} - -/* - * Return true if it is guaranteed that poll will not wait. This is the case - * if the poll() of another file descriptor in the set got an event, so there - * is no need for waiting. - */ -static inline bool poll_does_not_wait(const poll_table *p) -{ - return p == NULL || p->_qproc == NULL; + /* + * This memory barrier is paired in the wq_has_sleeper(). + * See the comment above prepare_to_wait(), we need to + * ensure that subsequent tests in this thread can't be + * reordered with __add_wait_queue() in _qproc() paths. + */ + smp_mb(); + } } /* diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index dc7b738de299..f11f10c97bd9 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -5,12 +5,16 @@ #include <linux/alarmtimer.h> #include <linux/list.h> #include <linux/mutex.h> +#include <linux/pid.h> #include <linux/posix-timers_types.h> +#include <linux/rcuref.h> #include <linux/spinlock.h> #include <linux/timerqueue.h> struct kernel_siginfo; struct task_struct; +struct sigqueue; +struct k_itimer; static inline clockid_t make_process_cpuclock(const unsigned int pid, const clockid_t clock) @@ -35,6 +39,8 @@ static inline int clockid_to_fd(const clockid_t clk) #ifdef CONFIG_POSIX_TIMERS +#include <linux/signal_types.h> + /** * cpu_timer - Posix CPU timer representation for k_itimer * @node: timerqueue node to queue in the task/sig @@ -42,6 +48,7 @@ static inline int clockid_to_fd(const clockid_t clk) * @pid: Pointer to target task PID * @elist: List head for the expiry list * @firing: Timer is currently firing + * @nanosleep: Timer is used for nanosleep and is not a regular posix-timer * @handling: Pointer to the task which handles expiry */ struct cpu_timer { @@ -49,7 +56,8 @@ struct cpu_timer { struct timerqueue_head *head; struct pid *pid; struct list_head elist; - int firing; + bool firing; + bool nanosleep; struct task_struct __rcu *handling; }; @@ -101,6 +109,12 @@ static inline void posix_cputimers_rt_watchdog(struct posix_cputimers *pct, pct->bases[CPUCLOCK_SCHED].nextevt = runtime; } +void posixtimer_rearm_itimer(struct task_struct *p); +bool posixtimer_init_sigqueue(struct sigqueue *q); +void posixtimer_send_sigqueue(struct k_itimer *tmr); +bool posixtimer_deliver_signal(struct kernel_siginfo *info, struct sigqueue *timer_sigq); +void posixtimer_free_timer(struct k_itimer *timer); + /* Init task static initializer */ #define INIT_CPU_TIMERBASE(b) { \ .nextevt = U64_MAX, \ @@ -122,6 +136,10 @@ struct cpu_timer { }; static inline void posix_cputimers_init(struct posix_cputimers *pct) { } static inline void posix_cputimers_group_init(struct posix_cputimers *pct, u64 cpu_limit) { } +static inline void posixtimer_rearm_itimer(struct task_struct *p) { } +static inline bool posixtimer_deliver_signal(struct kernel_siginfo *info, + struct sigqueue *timer_sigq) { return false; } +static inline void posixtimer_free_timer(struct k_itimer *timer) { } #endif #ifdef CONFIG_POSIX_CPU_TIMERS_TASK_WORK @@ -132,50 +150,56 @@ static inline void clear_posix_cputimers_work(struct task_struct *p) { } static inline void posix_cputimers_init_work(void) { } #endif -#define REQUEUE_PENDING 1 - /** * struct k_itimer - POSIX.1b interval timer structure. - * @list: List head for binding the timer to signals->posix_timers + * @list: List node for binding the timer to tsk::signal::posix_timers + * @ignored_list: List node for tracking ignored timers in tsk::signal::ignored_posix_timers * @t_hash: Entry in the posix timer hash table * @it_lock: Lock protecting the timer * @kclock: Pointer to the k_clock struct handling this timer * @it_clock: The posix timer clock id * @it_id: The posix timer id for identifying the timer - * @it_active: Marker that timer is active + * @it_status: The status of the timer + * @it_sig_periodic: The periodic status at signal delivery * @it_overrun: The overrun counter for pending signals * @it_overrun_last: The overrun at the time of the last delivered signal - * @it_requeue_pending: Indicator that timer waits for being requeued on - * signal delivery + * @it_signal_seq: Sequence count to control signal delivery + * @it_sigqueue_seq: The sequence count at the point where the signal was queued * @it_sigev_notify: The notify word of sigevent struct for signal delivery * @it_interval: The interval for periodic timers * @it_signal: Pointer to the creators signal struct * @it_pid: The pid of the process/task targeted by the signal * @it_process: The task to wakeup on clock_nanosleep (CPU timers) - * @sigq: Pointer to preallocated sigqueue + * @rcuref: Reference count for life time management + * @sigq: Embedded sigqueue * @it: Union representing the various posix timer type * internals. * @rcu: RCU head for freeing the timer. */ struct k_itimer { - struct list_head list; + struct hlist_node list; + struct hlist_node ignored_list; struct hlist_node t_hash; spinlock_t it_lock; const struct k_clock *kclock; clockid_t it_clock; timer_t it_id; - int it_active; + int it_status; + bool it_sig_periodic; s64 it_overrun; s64 it_overrun_last; - int it_requeue_pending; + unsigned int it_signal_seq; + unsigned int it_sigqueue_seq; int it_sigev_notify; + enum pid_type it_pid_type; ktime_t it_interval; struct signal_struct *it_signal; union { struct pid *it_pid; struct task_struct *it_process; }; - struct sigqueue *sigq; + struct sigqueue sigq; + rcuref_t rcuref; union { struct { struct hrtimer timer; @@ -196,5 +220,29 @@ void set_process_cpu_timer(struct task_struct *task, unsigned int clock_idx, int update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new); -void posixtimer_rearm(struct kernel_siginfo *info); +#ifdef CONFIG_POSIX_TIMERS +static inline void posixtimer_putref(struct k_itimer *tmr) +{ + if (rcuref_put(&tmr->rcuref)) + posixtimer_free_timer(tmr); +} + +static inline void posixtimer_sigqueue_getref(struct sigqueue *q) +{ + struct k_itimer *tmr = container_of(q, struct k_itimer, sigq); + + WARN_ON_ONCE(!rcuref_get(&tmr->rcuref)); +} + +static inline void posixtimer_sigqueue_putref(struct sigqueue *q) +{ + struct k_itimer *tmr = container_of(q, struct k_itimer, sigq); + + posixtimer_putref(tmr); +} +#else /* CONFIG_POSIX_TIMERS */ +static inline void posixtimer_sigqueue_getref(struct sigqueue *q) { } +static inline void posixtimer_sigqueue_putref(struct sigqueue *q) { } +#endif /* !CONFIG_POSIX_TIMERS */ + #endif diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index 0e65b3d634d9..e2d47eb1a7f3 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -28,9 +28,9 @@ struct posix_acl_entry { struct posix_acl { refcount_t a_refcount; - struct rcu_head a_rcu; unsigned int a_count; - struct posix_acl_entry a_entries[]; + struct rcu_head a_rcu; + struct posix_acl_entry a_entries[] __counted_by(a_count); }; #define FOREACH_ACL_ENTRY(pa, acl, pe) \ @@ -62,7 +62,7 @@ posix_acl_release(struct posix_acl *acl) /* posix_acl.c */ extern void posix_acl_init(struct posix_acl *, int); -extern struct posix_acl *posix_acl_alloc(int, gfp_t); +extern struct posix_acl *posix_acl_alloc(unsigned int count, gfp_t flags); extern struct posix_acl *posix_acl_from_mode(umode_t, gfp_t); extern int posix_acl_equiv_mode(const struct posix_acl *, umode_t *); extern int __posix_acl_create(struct posix_acl **, gfp_t, umode_t *); diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h index b9e5bd2b42d3..6b190639b08e 100644 --- a/include/linux/power/bq27xxx_battery.h +++ b/include/linux/power/bq27xxx_battery.h @@ -47,16 +47,8 @@ struct bq27xxx_access_methods { }; struct bq27xxx_reg_cache { - int temperature; - int time_to_empty; - int time_to_empty_avg; - int time_to_full; - int charge_full; - int cycle_count; int capacity; - int energy; int flags; - int health; }; struct bq27xxx_device_info { @@ -69,6 +61,7 @@ struct bq27xxx_device_info { struct bq27xxx_access_methods bus; struct bq27xxx_reg_cache cache; int charge_design_full; + int voltage_min_design; bool removed; unsigned long last_update; union power_supply_propval last_status; diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index 8e5705a56b85..6ed53b292162 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -15,6 +15,8 @@ #include <linux/device.h> #include <linux/workqueue.h> #include <linux/leds.h> +#include <linux/rwsem.h> +#include <linux/list.h> #include <linux/spinlock.h> #include <linux/notifier.h> @@ -40,7 +42,7 @@ enum { }; /* What algorithm is the charger using? */ -enum { +enum power_supply_charge_type { POWER_SUPPLY_CHARGE_TYPE_UNKNOWN = 0, POWER_SUPPLY_CHARGE_TYPE_NONE, POWER_SUPPLY_CHARGE_TYPE_TRICKLE, /* slow speed */ @@ -58,6 +60,7 @@ enum { POWER_SUPPLY_HEALTH_OVERHEAT, POWER_SUPPLY_HEALTH_DEAD, POWER_SUPPLY_HEALTH_OVERVOLTAGE, + POWER_SUPPLY_HEALTH_UNDERVOLTAGE, POWER_SUPPLY_HEALTH_UNSPEC_FAILURE, POWER_SUPPLY_HEALTH_COLD, POWER_SUPPLY_HEALTH_WATCHDOG_TIMER_EXPIRE, @@ -99,6 +102,7 @@ enum power_supply_property { /* Properties of type `int' */ POWER_SUPPLY_PROP_STATUS = 0, POWER_SUPPLY_PROP_CHARGE_TYPE, + POWER_SUPPLY_PROP_CHARGE_TYPES, POWER_SUPPLY_PROP_HEALTH, POWER_SUPPLY_PROP_PRESENT, POWER_SUPPLY_PROP_ONLINE, @@ -236,6 +240,8 @@ struct power_supply_config { char **supplied_to; size_t num_supplicants; + + bool no_wakeup_source; }; /* Description of power supply */ @@ -243,8 +249,8 @@ struct power_supply_desc { const char *name; enum power_supply_type type; u8 charge_behaviours; - const enum power_supply_usb_type *usb_types; - size_t num_usb_types; + u32 charge_types; + u32 usb_types; const enum power_supply_property *properties; size_t num_properties; @@ -280,6 +286,28 @@ struct power_supply_desc { int use_for_apm; }; +struct power_supply_ext { + const char *const name; + u8 charge_behaviours; + const enum power_supply_property *properties; + size_t num_properties; + + int (*get_property)(struct power_supply *psy, + const struct power_supply_ext *ext, + void *data, + enum power_supply_property psp, + union power_supply_propval *val); + int (*set_property)(struct power_supply *psy, + const struct power_supply_ext *ext, + void *data, + enum power_supply_property psp, + const union power_supply_propval *val); + int (*property_is_writeable)(struct power_supply *psy, + const struct power_supply_ext *ext, + void *data, + enum power_supply_property psp); +}; + struct power_supply { const struct power_supply_desc *desc; @@ -299,29 +327,29 @@ struct power_supply { struct delayed_work deferred_register_work; spinlock_t changed_lock; bool changed; + bool update_groups; bool initialized; bool removing; atomic_t use_cnt; struct power_supply_battery_info *battery_info; + struct rw_semaphore extensions_sem; /* protects "extensions" */ + struct list_head extensions; #ifdef CONFIG_THERMAL struct thermal_zone_device *tzd; struct thermal_cooling_device *tcd; #endif #ifdef CONFIG_LEDS_TRIGGERS - struct led_trigger *charging_full_trig; - char *charging_full_trig_name; + struct led_trigger *trig; struct led_trigger *charging_trig; - char *charging_trig_name; struct led_trigger *full_trig; - char *full_trig_name; - struct led_trigger *online_trig; - char *online_trig_name; struct led_trigger *charging_blink_full_solid_trig; - char *charging_blink_full_solid_trig_name; + struct led_trigger *charging_orange_full_green_trig; #endif }; +#define dev_to_psy(__dev) container_of_const(__dev, struct power_supply, dev) + /* * This is recommended structure to specify static power supply parameters. * Generic one, parametrizable for different power supplies. Power supply @@ -741,7 +769,7 @@ struct power_supply_battery_info { int overvoltage_limit_uv; int constant_charge_current_max_ua; int constant_charge_voltage_max_uv; - struct power_supply_maintenance_charge_table *maintenance_charge; + const struct power_supply_maintenance_charge_table *maintenance_charge; int maintenance_charge_size; int alert_low_temp_charge_current_ua; int alert_low_temp_charge_voltage_uv; @@ -756,13 +784,13 @@ struct power_supply_battery_info { int temp_alert_max; int temp_min; int temp_max; - struct power_supply_battery_ocv_table *ocv_table[POWER_SUPPLY_OCV_TEMP_MAX]; + const struct power_supply_battery_ocv_table *ocv_table[POWER_SUPPLY_OCV_TEMP_MAX]; int ocv_table_size[POWER_SUPPLY_OCV_TEMP_MAX]; - struct power_supply_resistance_temp_table *resist_table; + const struct power_supply_resistance_temp_table *resist_table; int resist_table_size; - struct power_supply_vbat_ri_table *vbat2ri_discharging; + const struct power_supply_vbat_ri_table *vbat2ri_discharging; int vbat2ri_discharging_size; - struct power_supply_vbat_ri_table *vbat2ri_charging; + const struct power_supply_vbat_ri_table *vbat2ri_charging; int vbat2ri_charging_size; int bti_resistance_ohm; int bti_resistance_tolerance; @@ -803,19 +831,19 @@ extern bool power_supply_battery_info_has_prop(struct power_supply_battery_info extern int power_supply_battery_info_get_prop(struct power_supply_battery_info *info, enum power_supply_property psp, union power_supply_propval *val); -extern int power_supply_ocv2cap_simple(struct power_supply_battery_ocv_table *table, +extern int power_supply_ocv2cap_simple(const struct power_supply_battery_ocv_table *table, int table_len, int ocv); -extern struct power_supply_battery_ocv_table * +extern const struct power_supply_battery_ocv_table * power_supply_find_ocv2cap_table(struct power_supply_battery_info *info, int temp, int *table_len); extern int power_supply_batinfo_ocv2cap(struct power_supply_battery_info *info, int ocv, int temp); extern int -power_supply_temp2resist_simple(struct power_supply_resistance_temp_table *table, +power_supply_temp2resist_simple(const struct power_supply_resistance_temp_table *table, int table_len, int temp); extern int power_supply_vbat2ri(struct power_supply_battery_info *info, int vbat_uv, bool charging); -extern struct power_supply_maintenance_charge_table * +extern const struct power_supply_maintenance_charge_table * power_supply_get_maintenance_charging_setting(struct power_supply_battery_info *info, int index); extern bool power_supply_battery_bti_in_range(struct power_supply_battery_info *info, int resistance); @@ -829,7 +857,7 @@ extern int power_supply_set_battery_charged(struct power_supply *psy); static inline bool power_supply_supports_maintenance_charging(struct power_supply_battery_info *info) { - struct power_supply_maintenance_charge_table *mt; + const struct power_supply_maintenance_charge_table *mt; mt = power_supply_get_maintenance_charging_setting(info, 0); @@ -869,8 +897,6 @@ static inline int power_supply_set_property(struct power_supply *psy, const union power_supply_propval *val) { return 0; } #endif -extern int power_supply_property_is_writeable(struct power_supply *psy, - enum power_supply_property psp); extern void power_supply_external_power_changed(struct power_supply *psy); extern struct power_supply *__must_check @@ -878,24 +904,24 @@ power_supply_register(struct device *parent, const struct power_supply_desc *desc, const struct power_supply_config *cfg); extern struct power_supply *__must_check -power_supply_register_no_ws(struct device *parent, - const struct power_supply_desc *desc, - const struct power_supply_config *cfg); -extern struct power_supply *__must_check devm_power_supply_register(struct device *parent, const struct power_supply_desc *desc, const struct power_supply_config *cfg); -extern struct power_supply *__must_check -devm_power_supply_register_no_ws(struct device *parent, - const struct power_supply_desc *desc, - const struct power_supply_config *cfg); extern void power_supply_unregister(struct power_supply *psy); extern int power_supply_powers(struct power_supply *psy, struct device *dev); +extern int __must_check +power_supply_register_extension(struct power_supply *psy, + const struct power_supply_ext *ext, + struct device *dev, + void *data); +extern void power_supply_unregister_extension(struct power_supply *psy, + const struct power_supply_ext *ext); + #define to_power_supply(device) container_of(device, struct power_supply, dev) extern void *power_supply_get_drvdata(struct power_supply *psy); -extern int power_supply_for_each_device(void *data, int (*fn)(struct device *dev, void *data)); +extern int power_supply_for_each_psy(void *data, int (*fn)(struct power_supply *psy, void *data)); static inline bool power_supply_is_amp_property(enum power_supply_property psp) { @@ -951,19 +977,6 @@ static inline bool power_supply_is_watt_property(enum power_supply_property psp) return false; } -#ifdef CONFIG_POWER_SUPPLY_HWMON -int power_supply_add_hwmon_sysfs(struct power_supply *psy); -void power_supply_remove_hwmon_sysfs(struct power_supply *psy); -#else -static inline int power_supply_add_hwmon_sysfs(struct power_supply *psy) -{ - return 0; -} - -static inline -void power_supply_remove_hwmon_sysfs(struct power_supply *psy) {} -#endif - #ifdef CONFIG_SYSFS ssize_t power_supply_charge_behaviour_show(struct device *dev, unsigned int available_behaviours, @@ -971,6 +984,11 @@ ssize_t power_supply_charge_behaviour_show(struct device *dev, char *buf); int power_supply_charge_behaviour_parse(unsigned int available_behaviours, const char *buf); +ssize_t power_supply_charge_types_show(struct device *dev, + unsigned int available_types, + enum power_supply_charge_type current_type, + char *buf); +int power_supply_charge_types_parse(unsigned int available_types, const char *buf); #else static inline ssize_t power_supply_charge_behaviour_show(struct device *dev, @@ -986,6 +1004,20 @@ static inline int power_supply_charge_behaviour_parse(unsigned int available_beh { return -EOPNOTSUPP; } + +static inline +ssize_t power_supply_charge_types_show(struct device *dev, + unsigned int available_types, + enum power_supply_charge_type current_type, + char *buf) +{ + return -EOPNOTSUPP; +} + +static inline int power_supply_charge_types_parse(unsigned int available_types, const char *buf) +{ + return -EOPNOTSUPP; +} #endif #endif /* __LINUX_POWER_SUPPLY_H__ */ diff --git a/include/linux/pps_gen_kernel.h b/include/linux/pps_gen_kernel.h new file mode 100644 index 000000000000..022ea0ac4440 --- /dev/null +++ b/include/linux/pps_gen_kernel.h @@ -0,0 +1,78 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * PPS generator API kernel header + * + * Copyright (C) 2024 Rodolfo Giometti <giometti@enneenne.com> + */ + +#ifndef LINUX_PPS_GEN_KERNEL_H +#define LINUX_PPS_GEN_KERNEL_H + +#include <linux/pps_gen.h> +#include <linux/cdev.h> +#include <linux/device.h> + +/* + * Global defines + */ + +#define PPS_GEN_MAX_SOURCES 16 /* should be enough... */ + +struct pps_gen_device; + +/** + * struct pps_gen_source_info - the specific PPS generator info + * @use_system_clock: true, if the system clock is used to generate pulses + * @get_time: query the time stored into the generator clock + * @enable: enable/disable the PPS pulses generation + * + * This is the main generator struct where all needed information must be + * placed before calling the pps_gen_register_source(). + */ +struct pps_gen_source_info { + bool use_system_clock; + + int (*get_time)(struct pps_gen_device *pps_gen, + struct timespec64 *time); + int (*enable)(struct pps_gen_device *pps_gen, bool enable); + +/* private: internal use only */ + struct module *owner; + struct device *parent; /* for device_create */ +}; + +/* The main struct */ +struct pps_gen_device { + struct pps_gen_source_info info; /* PSS generator info */ + bool enabled; /* PSS generator status */ + + unsigned int event; + unsigned int sequence; + + unsigned int last_ev; /* last PPS event id */ + wait_queue_head_t queue; /* PPS event queue */ + + unsigned int id; /* PPS generator unique ID */ + struct cdev cdev; + struct device *dev; + struct fasync_struct *async_queue; /* fasync method */ + spinlock_t lock; +}; + +/* + * Global variables + */ + +extern const struct attribute_group *pps_gen_groups[]; + +/* + * Exported functions + */ + +extern struct pps_gen_device *pps_gen_register_source( + struct pps_gen_source_info *info); +extern void pps_gen_unregister_source(struct pps_gen_device *pps_gen); +extern void pps_gen_event(struct pps_gen_device *pps_gen, + unsigned int event, void *data); + +#endif /* LINUX_PPS_GEN_KERNEL_H */ diff --git a/include/linux/pps_kernel.h b/include/linux/pps_kernel.h index 78c8ac4951b5..c7abce28ed29 100644 --- a/include/linux/pps_kernel.h +++ b/include/linux/pps_kernel.h @@ -56,8 +56,7 @@ struct pps_device { unsigned int id; /* PPS source unique ID */ void const *lookup_cookie; /* For pps_lookup_dev() only */ - struct cdev cdev; - struct device *dev; + struct device dev; struct fasync_struct *async_queue; /* fasync method */ spinlock_t lock; }; diff --git a/include/linux/prandom.h b/include/linux/prandom.h index f7f1e5251c67..f2ed5b72b3d6 100644 --- a/include/linux/prandom.h +++ b/include/linux/prandom.h @@ -10,6 +10,7 @@ #include <linux/types.h> #include <linux/once.h> +#include <linux/percpu.h> #include <linux/random.h> struct rnd_state { diff --git a/include/linux/preempt.h b/include/linux/preempt.h index 7233e9cf1bab..ca86235ac15c 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -481,4 +481,51 @@ DEFINE_LOCK_GUARD_0(preempt, preempt_disable(), preempt_enable()) DEFINE_LOCK_GUARD_0(preempt_notrace, preempt_disable_notrace(), preempt_enable_notrace()) DEFINE_LOCK_GUARD_0(migrate, migrate_disable(), migrate_enable()) +#ifdef CONFIG_PREEMPT_DYNAMIC + +extern bool preempt_model_none(void); +extern bool preempt_model_voluntary(void); +extern bool preempt_model_full(void); +extern bool preempt_model_lazy(void); + +#else + +static inline bool preempt_model_none(void) +{ + return IS_ENABLED(CONFIG_PREEMPT_NONE); +} +static inline bool preempt_model_voluntary(void) +{ + return IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY); +} +static inline bool preempt_model_full(void) +{ + return IS_ENABLED(CONFIG_PREEMPT); +} + +static inline bool preempt_model_lazy(void) +{ + return IS_ENABLED(CONFIG_PREEMPT_LAZY); +} + +#endif + +static inline bool preempt_model_rt(void) +{ + return IS_ENABLED(CONFIG_PREEMPT_RT); +} + +/* + * Does the preemption model allow non-cooperative preemption? + * + * For !CONFIG_PREEMPT_DYNAMIC kernels this is an exact match with + * CONFIG_PREEMPTION; for CONFIG_PREEMPT_DYNAMIC this doesn't work as the + * kernel is *built* with CONFIG_PREEMPTION=y but may run with e.g. the + * PREEMPT_NONE model. + */ +static inline bool preempt_model_preemptible(void) +{ + return preempt_model_full() || preempt_model_lazy() || preempt_model_rt(); +} + #endif /* __LINUX_PREEMPT_H */ diff --git a/include/linux/printk.h b/include/linux/printk.h index 955e31860095..4217a9f412b2 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -9,6 +9,8 @@ #include <linux/ratelimit_types.h> #include <linux/once_lite.h> +struct console; + extern const char linux_banner[]; extern const char linux_proc_banner[]; @@ -60,6 +62,10 @@ static inline const char *printk_skip_headers(const char *buffer) #define CONSOLE_LOGLEVEL_DEFAULT CONFIG_CONSOLE_LOGLEVEL_DEFAULT #define CONSOLE_LOGLEVEL_QUIET CONFIG_CONSOLE_LOGLEVEL_QUIET +int match_devname_and_update_preferred_console(const char *match, + const char *name, + const short idx); + extern int console_printk[]; #define console_loglevel (console_printk[0]) @@ -71,7 +77,7 @@ extern void console_verbose(void); /* strlen("ratelimit") + 1 */ #define DEVKMSG_STR_MAX_SIZE 10 -extern char devkmsg_log_str[]; +extern char devkmsg_log_str[DEVKMSG_STR_MAX_SIZE]; struct ctl_table; extern int suppress_printk; @@ -126,7 +132,7 @@ struct va_format { #define no_printk(fmt, ...) \ ({ \ if (0) \ - printk(fmt, ##__VA_ARGS__); \ + _printk(fmt, ##__VA_ARGS__); \ 0; \ }) @@ -157,15 +163,19 @@ int _printk(const char *fmt, ...); */ __printf(1, 2) __cold int _printk_deferred(const char *fmt, ...); -extern void __printk_safe_enter(void); -extern void __printk_safe_exit(void); +extern void __printk_deferred_enter(void); +extern void __printk_deferred_exit(void); + +extern void printk_force_console_enter(void); +extern void printk_force_console_exit(void); + /* * The printk_deferred_enter/exit macros are available only as a hack for * some code paths that need to defer all printk console printing. Interrupts * must be disabled for the deferred duration. */ -#define printk_deferred_enter __printk_safe_enter -#define printk_deferred_exit __printk_safe_exit +#define printk_deferred_enter() __printk_deferred_enter() +#define printk_deferred_exit() __printk_deferred_exit() /* * Please don't use printk_ratelimit(), because it shares ratelimiting state @@ -192,6 +202,11 @@ void show_regs_print_info(const char *log_lvl); extern asmlinkage void dump_stack_lvl(const char *log_lvl) __cold; extern asmlinkage void dump_stack(void) __cold; void printk_trigger_flush(void); +void console_try_replay_all(void); +void printk_legacy_allow_panic_sync(void); +extern bool nbcon_device_try_acquire(struct console *con); +extern void nbcon_device_release(struct console *con); +void nbcon_atomic_flush_unsafe(void); #else static inline __printf(1, 0) int vprintk(const char *s, va_list args) @@ -217,6 +232,14 @@ static inline void printk_deferred_exit(void) { } +static inline void printk_force_console_enter(void) +{ +} + +static inline void printk_force_console_exit(void) +{ +} + static inline int printk_ratelimit(void) { return 0; @@ -271,6 +294,27 @@ static inline void dump_stack(void) static inline void printk_trigger_flush(void) { } +static inline void console_try_replay_all(void) +{ +} + +static inline void printk_legacy_allow_panic_sync(void) +{ +} + +static inline bool nbcon_device_try_acquire(struct console *con) +{ + return false; +} + +static inline void nbcon_device_release(struct console *con) +{ +} + +static inline void nbcon_atomic_flush_unsafe(void) +{ +} + #endif bool this_cpu_in_panic(void); diff --git a/include/linux/prmt.h b/include/linux/prmt.h index 24da8364b919..c53ab287e932 100644 --- a/include/linux/prmt.h +++ b/include/linux/prmt.h @@ -1,7 +1,14 @@ /* SPDX-License-Identifier: GPL-2.0-only */ +#include <linux/uuid.h> + #ifdef CONFIG_ACPI_PRMT void init_prmt(void); +int acpi_call_prm_handler(guid_t handler_guid, void *param_buffer); #else static inline void init_prmt(void) { } +static inline int acpi_call_prm_handler(guid_t handler_guid, void *param_buffer) +{ + return -EOPNOTSUPP; +} #endif diff --git a/include/linux/profile.h b/include/linux/profile.h index 04ae5ebcb637..3f53cdb0c27c 100644 --- a/include/linux/profile.h +++ b/include/linux/profile.h @@ -4,14 +4,12 @@ #include <linux/kernel.h> #include <linux/init.h> -#include <linux/cpumask.h> #include <linux/cache.h> #include <asm/errno.h> #define CPU_PROFILING 1 #define SCHED_PROFILING 2 -#define SLEEP_PROFILING 3 #define KVM_PROFILING 4 struct proc_dir_entry; diff --git a/include/linux/property.h b/include/linux/property.h index 3a1045eb786c..e214ecd241eb 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -13,6 +13,7 @@ #include <linux/args.h> #include <linux/array_size.h> #include <linux/bits.h> +#include <linux/cleanup.h> #include <linux/fwnode.h> #include <linux/stddef.h> #include <linux/types.h> @@ -36,6 +37,7 @@ struct fwnode_handle *__dev_fwnode(struct device *dev); struct device *: __dev_fwnode)(dev) bool device_property_present(const struct device *dev, const char *propname); +bool device_property_read_bool(const struct device *dev, const char *propname); int device_property_read_u8_array(const struct device *dev, const char *propname, u8 *val, size_t nval); int device_property_read_u16_array(const struct device *dev, const char *propname, @@ -53,6 +55,8 @@ int device_property_match_string(const struct device *dev, bool fwnode_property_present(const struct fwnode_handle *fwnode, const char *propname); +bool fwnode_property_read_bool(const struct fwnode_handle *fwnode, + const char *propname); int fwnode_property_read_u8_array(const struct fwnode_handle *fwnode, const char *propname, u8 *val, size_t nval); @@ -174,25 +178,38 @@ struct fwnode_handle *device_get_next_child_node(const struct device *dev, for (child = device_get_next_child_node(dev, NULL); child; \ child = device_get_next_child_node(dev, child)) +#define device_for_each_child_node_scoped(dev, child) \ + for (struct fwnode_handle *child __free(fwnode_handle) = \ + device_get_next_child_node(dev, NULL); \ + child; child = device_get_next_child_node(dev, child)) + struct fwnode_handle *fwnode_get_named_child_node(const struct fwnode_handle *fwnode, const char *childname); struct fwnode_handle *device_get_named_child_node(const struct device *dev, const char *childname); struct fwnode_handle *fwnode_handle_get(struct fwnode_handle *fwnode); -void fwnode_handle_put(struct fwnode_handle *fwnode); + +/** + * fwnode_handle_put - Drop reference to a device node + * @fwnode: Pointer to the device node to drop the reference to. + * + * This has to be used when terminating device_for_each_child_node() iteration + * with break or return to prevent stale device node references from being left + * behind. + */ +static inline void fwnode_handle_put(struct fwnode_handle *fwnode) +{ + fwnode_call_void_op(fwnode, put); +} + +DEFINE_FREE(fwnode_handle, struct fwnode_handle *, fwnode_handle_put(_T)) int fwnode_irq_get(const struct fwnode_handle *fwnode, unsigned int index); int fwnode_irq_get_byname(const struct fwnode_handle *fwnode, const char *name); unsigned int device_get_child_node_count(const struct device *dev); -static inline bool device_property_read_bool(const struct device *dev, - const char *propname) -{ - return device_property_present(dev, propname); -} - static inline int device_property_read_u8(const struct device *dev, const char *propname, u8 *val) { @@ -243,12 +260,6 @@ static inline int device_property_string_array_count(const struct device *dev, return device_property_read_string_array(dev, propname, NULL, 0); } -static inline bool fwnode_property_read_bool(const struct fwnode_handle *fwnode, - const char *propname) -{ - return fwnode_property_present(fwnode, propname); -} - static inline int fwnode_property_read_u8(const struct fwnode_handle *fwnode, const char *propname, u8 *val) { diff --git a/include/linux/pruss_driver.h b/include/linux/pruss_driver.h index c9a31c567e85..2e18fef1a2e1 100644 --- a/include/linux/pruss_driver.h +++ b/include/linux/pruss_driver.h @@ -144,32 +144,32 @@ static inline int pruss_release_mem_region(struct pruss *pruss, static inline int pruss_cfg_get_gpmux(struct pruss *pruss, enum pruss_pru_id pru_id, u8 *mux) { - return ERR_PTR(-EOPNOTSUPP); + return -EOPNOTSUPP; } static inline int pruss_cfg_set_gpmux(struct pruss *pruss, enum pruss_pru_id pru_id, u8 mux) { - return ERR_PTR(-EOPNOTSUPP); + return -EOPNOTSUPP; } static inline int pruss_cfg_gpimode(struct pruss *pruss, enum pruss_pru_id pru_id, enum pruss_gpi_mode mode) { - return ERR_PTR(-EOPNOTSUPP); + return -EOPNOTSUPP; } static inline int pruss_cfg_miirt_enable(struct pruss *pruss, bool enable) { - return ERR_PTR(-EOPNOTSUPP); + return -EOPNOTSUPP; } static inline int pruss_cfg_xfr_enable(struct pruss *pruss, enum pru_type pru_type, - bool enable); + bool enable) { - return ERR_PTR(-EOPNOTSUPP); + return -EOPNOTSUPP; } #endif /* CONFIG_TI_PRUSS */ diff --git a/include/linux/pse-pd/pse.h b/include/linux/pse-pd/pse.h index fb724c65c77b..c773eeb92d04 100644 --- a/include/linux/pse-pd/pse.h +++ b/include/linux/pse-pd/pse.h @@ -5,55 +5,214 @@ #ifndef _LINUX_PSE_CONTROLLER_H #define _LINUX_PSE_CONTROLLER_H -#include <linux/ethtool.h> #include <linux/list.h> #include <uapi/linux/ethtool.h> +/* Maximum current in uA according to IEEE 802.3-2022 Table 145-1 */ +#define MAX_PI_CURRENT 1920000 +/* Maximum power in mW according to IEEE 802.3-2022 Table 145-16 */ +#define MAX_PI_PW 99900 + struct phy_device; struct pse_controller_dev; +struct netlink_ext_ack; + +/* C33 PSE extended state and substate. */ +struct ethtool_c33_pse_ext_state_info { + enum ethtool_c33_pse_ext_state c33_pse_ext_state; + union { + enum ethtool_c33_pse_ext_substate_error_condition error_condition; + enum ethtool_c33_pse_ext_substate_mr_pse_enable mr_pse_enable; + enum ethtool_c33_pse_ext_substate_option_detect_ted option_detect_ted; + enum ethtool_c33_pse_ext_substate_option_vport_lim option_vport_lim; + enum ethtool_c33_pse_ext_substate_ovld_detected ovld_detected; + enum ethtool_c33_pse_ext_substate_power_not_available power_not_available; + enum ethtool_c33_pse_ext_substate_short_detected short_detected; + u32 __c33_pse_ext_substate; + }; +}; + +struct ethtool_c33_pse_pw_limit_range { + u32 min; + u32 max; +}; /** * struct pse_control_config - PSE control/channel configuration. * - * @admin_cotrol: set PoDL PSE admin control as described in + * @podl_admin_control: set PoDL PSE admin control as described in * IEEE 802.3-2018 30.15.1.2.1 acPoDLPSEAdminControl + * @c33_admin_control: set PSE admin control as described in + * IEEE 802.3-2022 30.9.1.2.1 acPSEAdminControl */ struct pse_control_config { - enum ethtool_podl_pse_admin_state admin_cotrol; + enum ethtool_podl_pse_admin_state podl_admin_control; + enum ethtool_c33_pse_admin_state c33_admin_control; }; /** - * struct pse_control_status - PSE control/channel status. + * struct pse_admin_state - PSE operational state * * @podl_admin_state: operational state of the PoDL PSE * functions. IEEE 802.3-2018 30.15.1.1.2 aPoDLPSEAdminState + * @c33_admin_state: operational state of the PSE + * functions. IEEE 802.3-2022 30.9.1.1.2 aPSEAdminState + */ +struct pse_admin_state { + enum ethtool_podl_pse_admin_state podl_admin_state; + enum ethtool_c33_pse_admin_state c33_admin_state; +}; + +/** + * struct pse_pw_status - PSE power detection status + * * @podl_pw_status: power detection status of the PoDL PSE. * IEEE 802.3-2018 30.15.1.1.3 aPoDLPSEPowerDetectionStatus: + * @c33_pw_status: power detection status of the PSE. + * IEEE 802.3-2022 30.9.1.1.5 aPSEPowerDetectionStatus: */ -struct pse_control_status { +struct pse_pw_status { + enum ethtool_podl_pse_pw_d_status podl_pw_status; + enum ethtool_c33_pse_pw_d_status c33_pw_status; +}; + +/** + * struct pse_ext_state_info - PSE extended state information + * + * @c33_ext_state_info: extended state information of the PSE + */ +struct pse_ext_state_info { + struct ethtool_c33_pse_ext_state_info c33_ext_state_info; +}; + +/** + * struct pse_pw_limit_ranges - PSE power limit configuration range + * + * @c33_pw_limit_ranges: supported power limit configuration range. The driver + * is in charge of the memory allocation. + */ +struct pse_pw_limit_ranges { + struct ethtool_c33_pse_pw_limit_range *c33_pw_limit_ranges; +}; + +/** + * struct ethtool_pse_control_status - PSE control/channel status. + * + * @podl_admin_state: operational state of the PoDL PSE + * functions. IEEE 802.3-2018 30.15.1.1.2 aPoDLPSEAdminState + * @podl_pw_status: power detection status of the PoDL PSE. + * IEEE 802.3-2018 30.15.1.1.3 aPoDLPSEPowerDetectionStatus: + * @c33_admin_state: operational state of the PSE + * functions. IEEE 802.3-2022 30.9.1.1.2 aPSEAdminState + * @c33_pw_status: power detection status of the PSE. + * IEEE 802.3-2022 30.9.1.1.5 aPSEPowerDetectionStatus: + * @c33_pw_class: detected class of a powered PD + * IEEE 802.3-2022 30.9.1.1.8 aPSEPowerClassification + * @c33_actual_pw: power currently delivered by the PSE in mW + * IEEE 802.3-2022 30.9.1.1.23 aPSEActualPower + * @c33_ext_state_info: extended state information of the PSE + * @c33_avail_pw_limit: available power limit of the PSE in mW + * IEEE 802.3-2022 145.2.5.4 pse_avail_pwr + * @c33_pw_limit_ranges: supported power limit configuration range. The driver + * is in charge of the memory allocation + * @c33_pw_limit_nb_ranges: number of supported power limit configuration + * ranges + */ +struct ethtool_pse_control_status { enum ethtool_podl_pse_admin_state podl_admin_state; enum ethtool_podl_pse_pw_d_status podl_pw_status; + enum ethtool_c33_pse_admin_state c33_admin_state; + enum ethtool_c33_pse_pw_d_status c33_pw_status; + u32 c33_pw_class; + u32 c33_actual_pw; + struct ethtool_c33_pse_ext_state_info c33_ext_state_info; + u32 c33_avail_pw_limit; + struct ethtool_c33_pse_pw_limit_range *c33_pw_limit_ranges; + u32 c33_pw_limit_nb_ranges; }; /** * struct pse_controller_ops - PSE controller driver callbacks * - * @ethtool_get_status: get PSE control status for ethtool interface - * @ethtool_set_config: set PSE control configuration over ethtool interface + * @setup_pi_matrix: setup PI matrix of the PSE controller + * @pi_get_admin_state: Get the operational state of the PSE PI. This ops + * is mandatory. + * @pi_get_pw_status: Get the power detection status of the PSE PI. This + * ops is mandatory. + * @pi_get_ext_state: Get the extended state of the PSE PI. + * @pi_get_pw_class: Get the power class of the PSE PI. + * @pi_get_actual_pw: Get actual power of the PSE PI in mW. + * @pi_enable: Configure the PSE PI as enabled. + * @pi_disable: Configure the PSE PI as disabled. + * @pi_get_voltage: Return voltage similarly to get_voltage regulator + * callback in uV. + * @pi_get_pw_limit: Get the configured power limit of the PSE PI in mW. + * @pi_set_pw_limit: Configure the power limit of the PSE PI in mW. + * @pi_get_pw_limit_ranges: Get the supported power limit configuration + * range. The driver is in charge of the memory + * allocation and should return the number of + * ranges. */ struct pse_controller_ops { - int (*ethtool_get_status)(struct pse_controller_dev *pcdev, - unsigned long id, struct netlink_ext_ack *extack, - struct pse_control_status *status); - int (*ethtool_set_config)(struct pse_controller_dev *pcdev, - unsigned long id, struct netlink_ext_ack *extack, - const struct pse_control_config *config); + int (*setup_pi_matrix)(struct pse_controller_dev *pcdev); + int (*pi_get_admin_state)(struct pse_controller_dev *pcdev, int id, + struct pse_admin_state *admin_state); + int (*pi_get_pw_status)(struct pse_controller_dev *pcdev, int id, + struct pse_pw_status *pw_status); + int (*pi_get_ext_state)(struct pse_controller_dev *pcdev, int id, + struct pse_ext_state_info *ext_state_info); + int (*pi_get_pw_class)(struct pse_controller_dev *pcdev, int id); + int (*pi_get_actual_pw)(struct pse_controller_dev *pcdev, int id); + int (*pi_enable)(struct pse_controller_dev *pcdev, int id); + int (*pi_disable)(struct pse_controller_dev *pcdev, int id); + int (*pi_get_voltage)(struct pse_controller_dev *pcdev, int id); + int (*pi_get_pw_limit)(struct pse_controller_dev *pcdev, + int id); + int (*pi_set_pw_limit)(struct pse_controller_dev *pcdev, + int id, int max_mW); + int (*pi_get_pw_limit_ranges)(struct pse_controller_dev *pcdev, int id, + struct pse_pw_limit_ranges *pw_limit_ranges); }; struct module; struct device_node; struct of_phandle_args; struct pse_control; +struct ethtool_pse_control_status; + +/* PSE PI pairset pinout can either be Alternative A or Alternative B */ +enum pse_pi_pairset_pinout { + ALTERNATIVE_A, + ALTERNATIVE_B, +}; + +/** + * struct pse_pi_pairset - PSE PI pairset entity describing the pinout + * alternative ant its phandle + * + * @pinout: description of the pinout alternative + * @np: device node pointer describing the pairset phandle + */ +struct pse_pi_pairset { + enum pse_pi_pairset_pinout pinout; + struct device_node *np; +}; + +/** + * struct pse_pi - PSE PI (Power Interface) entity as described in + * IEEE 802.3-2022 145.2.4 + * + * @pairset: table of the PSE PI pinout alternative for the two pairset + * @np: device node pointer of the PSE PI node + * @rdev: regulator represented by the PSE PI + * @admin_state_enabled: PI enabled state + */ +struct pse_pi { + struct pse_pi_pairset pairset[2]; + struct device_node *np; + struct regulator_dev *rdev; + bool admin_state_enabled; +}; /** * struct pse_controller_dev - PSE controller entity that might @@ -64,10 +223,11 @@ struct pse_control; * @pse_control_head: head of internal list of requested PSE controls * @dev: corresponding driver model device struct * @of_pse_n_cells: number of cells in PSE line specifiers - * @of_xlate: translation function to translate from specifier as found in the - * device tree to id as given to the PSE control ops * @nr_lines: number of PSE controls in this controller device * @lock: Mutex for serialization access to the PSE controller + * @types: types of the PSE controller + * @pi: table of PSE PIs described in this controller device + * @no_of_pse_pi: flag set if the pse_pis devicetree node is not used */ struct pse_controller_dev { const struct pse_controller_ops *ops; @@ -76,10 +236,11 @@ struct pse_controller_dev { struct list_head pse_control_head; struct device *dev; int of_pse_n_cells; - int (*of_xlate)(struct pse_controller_dev *pcdev, - const struct of_phandle_args *pse_spec); unsigned int nr_lines; struct mutex lock; + enum ethtool_pse_types types; + struct pse_pi *pi; + bool no_of_pse_pi; }; #if IS_ENABLED(CONFIG_PSE_CONTROLLER) @@ -94,10 +255,16 @@ void pse_control_put(struct pse_control *psec); int pse_ethtool_get_status(struct pse_control *psec, struct netlink_ext_ack *extack, - struct pse_control_status *status); + struct ethtool_pse_control_status *status); int pse_ethtool_set_config(struct pse_control *psec, struct netlink_ext_ack *extack, const struct pse_control_config *config); +int pse_ethtool_set_pw_limit(struct pse_control *psec, + struct netlink_ext_ack *extack, + const unsigned int pw_limit); + +bool pse_has_podl(struct pse_control *psec); +bool pse_has_c33(struct pse_control *psec); #else @@ -112,16 +279,33 @@ static inline void pse_control_put(struct pse_control *psec) static inline int pse_ethtool_get_status(struct pse_control *psec, struct netlink_ext_ack *extack, - struct pse_control_status *status) + struct ethtool_pse_control_status *status) { - return -ENOTSUPP; + return -EOPNOTSUPP; } static inline int pse_ethtool_set_config(struct pse_control *psec, struct netlink_ext_ack *extack, const struct pse_control_config *config) { - return -ENOTSUPP; + return -EOPNOTSUPP; +} + +static inline int pse_ethtool_set_pw_limit(struct pse_control *psec, + struct netlink_ext_ack *extack, + const unsigned int pw_limit) +{ + return -EOPNOTSUPP; +} + +static inline bool pse_has_podl(struct pse_control *psec) +{ + return false; +} + +static inline bool pse_has_c33(struct pse_control *psec) +{ + return false; } #endif diff --git a/include/linux/pseudo_fs.h b/include/linux/pseudo_fs.h index 730f77381d55..2503f7625d65 100644 --- a/include/linux/pseudo_fs.h +++ b/include/linux/pseudo_fs.h @@ -5,6 +5,7 @@ struct pseudo_fs_context { const struct super_operations *ops; + const struct export_operations *eops; const struct xattr_handler * const *xattr; const struct dentry_operations *dops; unsigned long magic; diff --git a/include/linux/psp-platform-access.h b/include/linux/psp-platform-access.h index c1dc87fc536b..1504fb012c05 100644 --- a/include/linux/psp-platform-access.h +++ b/include/linux/psp-platform-access.h @@ -6,8 +6,9 @@ #include <linux/psp.h> enum psp_platform_access_msg { - PSP_CMD_NONE = 0x0, - PSP_I2C_REQ_BUS_CMD = 0x64, + PSP_CMD_NONE = 0x0, + PSP_CMD_HSTI_QUERY = 0x14, + PSP_I2C_REQ_BUS_CMD = 0x64, PSP_DYNAMIC_BOOST_GET_NONCE, PSP_DYNAMIC_BOOST_SET_UID, PSP_DYNAMIC_BOOST_GET_PARAMETER, diff --git a/include/linux/psp-sev.h b/include/linux/psp-sev.h index 3705c2044fc0..903ddfea8585 100644 --- a/include/linux/psp-sev.h +++ b/include/linux/psp-sev.h @@ -658,6 +658,7 @@ struct sev_data_snp_launch_update { * @id_auth_paddr: system physical address of ID block authentication structure * @id_block_en: indicates whether ID block is present * @auth_key_en: indicates whether author key is present in authentication structure + * @vcek_disabled: indicates whether use of VCEK is allowed for attestation reports * @rsvd: reserved * @host_data: host-supplied data for guest, not interpreted by firmware */ @@ -667,7 +668,8 @@ struct sev_data_snp_launch_finish { u64 id_auth_paddr; u8 id_block_en:1; u8 auth_key_en:1; - u64 rsvd:62; + u8 vcek_disabled:1; + u64 rsvd:61; u8 host_data[32]; } __packed; diff --git a/include/linux/pstore.h b/include/linux/pstore.h index 638507a3c8ff..fed601053c51 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -182,7 +182,7 @@ struct pstore_info { struct module *owner; const char *name; - spinlock_t buf_lock; + raw_spinlock_t buf_lock; char *buf; size_t bufsize; diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h index 1b5a953c6bbc..3a74f69e0b59 100644 --- a/include/linux/ptp_classify.h +++ b/include/linux/ptp_classify.h @@ -10,7 +10,7 @@ #ifndef _PTP_CLASSIFY_H_ #define _PTP_CLASSIFY_H_ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/ip.h> #include <linux/ktime.h> #include <linux/skbuff.h> diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 6e4b8206c7d0..0d68d09bedd1 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -47,10 +47,12 @@ struct system_device_crosststamp; * struct ptp_system_timestamp - system time corresponding to a PHC timestamp * @pre_ts: system timestamp before capturing PHC * @post_ts: system timestamp after capturing PHC + * @clockid: clock-base used for capturing the system timestamps */ struct ptp_system_timestamp { struct timespec64 pre_ts; struct timespec64 post_ts; + clockid_t clockid; }; /** @@ -305,7 +307,7 @@ static inline u64 adjust_by_scaled_ppm(u64 base, long scaled_ppm) * @info: Structure describing the new clock. * @parent: Pointer to the parent device of the new clock. * - * Returns a valid pointer on success or PTR_ERR on failure. If PHC + * Returns: a valid pointer on success or PTR_ERR on failure. If PHC * support is missing at the configuration level, this function * returns NULL, and drivers are expected to gracefully handle that * case separately. @@ -443,7 +445,7 @@ int ptp_get_vclocks_index(int pclock_index, int **vclock_index); * @hwtstamp: timestamp * @vclock_index: phc index of ptp vclock. * - * Returns converted timestamp, or 0 on error. + * Returns: converted timestamp, or 0 on error. */ ktime_t ptp_convert_timestamp(const ktime_t *hwtstamp, int vclock_index); #else @@ -457,14 +459,40 @@ static inline ktime_t ptp_convert_timestamp(const ktime_t *hwtstamp, static inline void ptp_read_system_prets(struct ptp_system_timestamp *sts) { - if (sts) - ktime_get_real_ts64(&sts->pre_ts); + if (sts) { + switch (sts->clockid) { + case CLOCK_REALTIME: + ktime_get_real_ts64(&sts->pre_ts); + break; + case CLOCK_MONOTONIC: + ktime_get_ts64(&sts->pre_ts); + break; + case CLOCK_MONOTONIC_RAW: + ktime_get_raw_ts64(&sts->pre_ts); + break; + default: + break; + } + } } static inline void ptp_read_system_postts(struct ptp_system_timestamp *sts) { - if (sts) - ktime_get_real_ts64(&sts->post_ts); + if (sts) { + switch (sts->clockid) { + case CLOCK_REALTIME: + ktime_get_real_ts64(&sts->post_ts); + break; + case CLOCK_MONOTONIC: + ktime_get_ts64(&sts->post_ts); + break; + case CLOCK_MONOTONIC_RAW: + ktime_get_raw_ts64(&sts->post_ts); + break; + default: + break; + } + } } #endif diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h index 808f9d3ee546..551329220e4f 100644 --- a/include/linux/ptr_ring.h +++ b/include/linux/ptr_ring.h @@ -464,11 +464,11 @@ static inline int ptr_ring_consume_batched_bh(struct ptr_ring *r, /* Not all gfp_t flags (besides GFP_KERNEL) are allowed. See * documentation for vmalloc for which of them are legal. */ -static inline void **__ptr_ring_init_queue_alloc(unsigned int size, gfp_t gfp) +static inline void **__ptr_ring_init_queue_alloc_noprof(unsigned int size, gfp_t gfp) { if (size > KMALLOC_MAX_SIZE / sizeof(void *)) return NULL; - return kvmalloc_array(size, sizeof(void *), gfp | __GFP_ZERO); + return kvmalloc_array_noprof(size, sizeof(void *), gfp | __GFP_ZERO); } static inline void __ptr_ring_set_size(struct ptr_ring *r, int size) @@ -484,9 +484,9 @@ static inline void __ptr_ring_set_size(struct ptr_ring *r, int size) r->batch = 1; } -static inline int ptr_ring_init(struct ptr_ring *r, int size, gfp_t gfp) +static inline int ptr_ring_init_noprof(struct ptr_ring *r, int size, gfp_t gfp) { - r->queue = __ptr_ring_init_queue_alloc(size, gfp); + r->queue = __ptr_ring_init_queue_alloc_noprof(size, gfp); if (!r->queue) return -ENOMEM; @@ -497,6 +497,7 @@ static inline int ptr_ring_init(struct ptr_ring *r, int size, gfp_t gfp) return 0; } +#define ptr_ring_init(...) alloc_hooks(ptr_ring_init_noprof(__VA_ARGS__)) /* * Return entries into ring. Destroy entries that don't fit. @@ -587,11 +588,11 @@ static inline void **__ptr_ring_swap_queue(struct ptr_ring *r, void **queue, * In particular if you consume ring in interrupt or BH context, you must * disable interrupts/BH when doing so. */ -static inline int ptr_ring_resize(struct ptr_ring *r, int size, gfp_t gfp, +static inline int ptr_ring_resize_noprof(struct ptr_ring *r, int size, gfp_t gfp, void (*destroy)(void *)) { unsigned long flags; - void **queue = __ptr_ring_init_queue_alloc(size, gfp); + void **queue = __ptr_ring_init_queue_alloc_noprof(size, gfp); void **old; if (!queue) @@ -609,39 +610,39 @@ static inline int ptr_ring_resize(struct ptr_ring *r, int size, gfp_t gfp, return 0; } +#define ptr_ring_resize(...) alloc_hooks(ptr_ring_resize_noprof(__VA_ARGS__)) /* * Note: producer lock is nested within consumer lock, so if you * resize you must make sure all uses nest correctly. - * In particular if you consume ring in interrupt or BH context, you must - * disable interrupts/BH when doing so. + * In particular if you consume ring in BH context, you must + * disable BH when doing so. */ -static inline int ptr_ring_resize_multiple(struct ptr_ring **rings, - unsigned int nrings, - int size, - gfp_t gfp, void (*destroy)(void *)) +static inline int ptr_ring_resize_multiple_bh_noprof(struct ptr_ring **rings, + unsigned int nrings, + int size, gfp_t gfp, + void (*destroy)(void *)) { - unsigned long flags; void ***queues; int i; - queues = kmalloc_array(nrings, sizeof(*queues), gfp); + queues = kmalloc_array_noprof(nrings, sizeof(*queues), gfp); if (!queues) goto noqueues; for (i = 0; i < nrings; ++i) { - queues[i] = __ptr_ring_init_queue_alloc(size, gfp); + queues[i] = __ptr_ring_init_queue_alloc_noprof(size, gfp); if (!queues[i]) goto nomem; } for (i = 0; i < nrings; ++i) { - spin_lock_irqsave(&(rings[i])->consumer_lock, flags); + spin_lock_bh(&(rings[i])->consumer_lock); spin_lock(&(rings[i])->producer_lock); queues[i] = __ptr_ring_swap_queue(rings[i], queues[i], size, gfp, destroy); spin_unlock(&(rings[i])->producer_lock); - spin_unlock_irqrestore(&(rings[i])->consumer_lock, flags); + spin_unlock_bh(&(rings[i])->consumer_lock); } for (i = 0; i < nrings; ++i) @@ -660,6 +661,8 @@ nomem: noqueues: return -ENOMEM; } +#define ptr_ring_resize_multiple_bh(...) \ + alloc_hooks(ptr_ring_resize_multiple_bh_noprof(__VA_ARGS__)) static inline void ptr_ring_cleanup(struct ptr_ring *r, void (*destroy)(void *)) { diff --git a/include/linux/pwm.h b/include/linux/pwm.h index 4a6568dfdf3f..a2df509056ac 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -2,10 +2,14 @@ #ifndef __LINUX_PWM_H #define __LINUX_PWM_H +#include <linux/device.h> #include <linux/err.h> +#include <linux/module.h> #include <linux/mutex.h> #include <linux/of.h> +MODULE_IMPORT_NS("PWM"); + struct pwm_chip; /** @@ -45,6 +49,31 @@ enum { PWMF_EXPORTED = 1, }; +/** + * struct pwm_waveform - description of a PWM waveform + * @period_length_ns: PWM period + * @duty_length_ns: PWM duty cycle + * @duty_offset_ns: offset of the rising edge from the period's start + * + * This is a representation of a PWM waveform alternative to struct pwm_state + * below. It's more expressive than struct pwm_state as it contains a + * duty_offset_ns and so can represent offsets other than zero (with .polarity = + * PWM_POLARITY_NORMAL) and period - duty_cycle (.polarity = + * PWM_POLARITY_INVERSED). + * + * Note there is no explicit bool for enabled. A "disabled" PWM is represented + * by .period_length_ns = 0. Note further that the behaviour of a "disabled" PWM + * is undefined. Depending on the hardware's capabilities it might drive the + * active or inactive level, go high-z or even continue to toggle. + * + * The unit for all three members is nanoseconds. + */ +struct pwm_waveform { + u64 period_length_ns; + u64 duty_length_ns; + u64 duty_offset_ns; +}; + /* * struct pwm_state - state of a PWM channel * @period: PWM period (in nanoseconds) @@ -247,16 +276,30 @@ struct pwm_capture { * @request: optional hook for requesting a PWM * @free: optional hook for freeing a PWM * @capture: capture and report PWM signal + * @sizeof_wfhw: size (in bytes) of driver specific waveform presentation + * @round_waveform_tohw: convert a struct pwm_waveform to driver specific presentation + * @round_waveform_fromhw: convert a driver specific waveform presentation to struct pwm_waveform + * @read_waveform: read driver specific waveform presentation from hardware + * @write_waveform: write driver specific waveform presentation to hardware * @apply: atomically apply a new PWM config - * @get_state: get the current PWM state. This function is only - * called once per PWM device when the PWM chip is - * registered. + * @get_state: get the current PWM state. */ struct pwm_ops { int (*request)(struct pwm_chip *chip, struct pwm_device *pwm); void (*free)(struct pwm_chip *chip, struct pwm_device *pwm); int (*capture)(struct pwm_chip *chip, struct pwm_device *pwm, struct pwm_capture *result, unsigned long timeout); + + size_t sizeof_wfhw; + int (*round_waveform_tohw)(struct pwm_chip *chip, struct pwm_device *pwm, + const struct pwm_waveform *wf, void *wfhw); + int (*round_waveform_fromhw)(struct pwm_chip *chip, struct pwm_device *pwm, + const void *wfhw, struct pwm_waveform *wf); + int (*read_waveform)(struct pwm_chip *chip, struct pwm_device *pwm, + void *wfhw); + int (*write_waveform)(struct pwm_chip *chip, struct pwm_device *pwm, + const void *wfhw); + int (*apply)(struct pwm_chip *chip, struct pwm_device *pwm, const struct pwm_state *state); int (*get_state)(struct pwm_chip *chip, struct pwm_device *pwm, @@ -272,11 +315,14 @@ struct pwm_ops { * @npwm: number of PWMs controlled by this chip * @of_xlate: request a PWM device given a device tree PWM specifier * @atomic: can the driver's ->apply() be called in atomic context - * @driver_data: Private pointer for driver specific info + * @uses_pwmchip_alloc: signals if pwmchip_allow was used to allocate this chip + * @operational: signals if the chip can be used (or is already deregistered) + * @nonatomic_lock: mutex for nonatomic chips + * @atomic_lock: mutex for atomic chips * @pwms: array of PWM devices allocated by the framework */ struct pwm_chip { - struct device *dev; + struct device dev; const struct pwm_ops *ops; struct module *owner; unsigned int id; @@ -287,37 +333,61 @@ struct pwm_chip { bool atomic; /* only used internally by the PWM framework */ - void *driver_data; - struct pwm_device *pwms; + bool uses_pwmchip_alloc; + bool operational; + union { + /* + * depending on the chip being atomic or not either the mutex or + * the spinlock is used. It protects .operational and + * synchronizes the callbacks in .ops + */ + struct mutex nonatomic_lock; + spinlock_t atomic_lock; + }; + struct pwm_device pwms[] __counted_by(npwm); }; +/** + * pwmchip_supports_waveform() - checks if the given chip supports waveform callbacks + * @chip: The pwm_chip to test + * + * Returns true iff the pwm chip support the waveform functions like + * pwm_set_waveform_might_sleep() and pwm_round_waveform_might_sleep() + */ +static inline bool pwmchip_supports_waveform(struct pwm_chip *chip) +{ + /* + * only check for .write_waveform(). If that is available, + * .round_waveform_tohw() and .round_waveform_fromhw() asserted to be + * available, too, in pwmchip_add(). + */ + return chip->ops->write_waveform != NULL; +} + static inline struct device *pwmchip_parent(const struct pwm_chip *chip) { - return chip->dev; + return chip->dev.parent; } static inline void *pwmchip_get_drvdata(struct pwm_chip *chip) { - /* - * After pwm_chip got a dedicated struct device, this can be replaced by - * dev_get_drvdata(&chip->dev); - */ - return chip->driver_data; + return dev_get_drvdata(&chip->dev); } static inline void pwmchip_set_drvdata(struct pwm_chip *chip, void *data) { - /* - * After pwm_chip got a dedicated struct device, this can be replaced by - * dev_set_drvdata(&chip->dev, data); - */ - chip->driver_data = data; + dev_set_drvdata(&chip->dev, data); } #if IS_ENABLED(CONFIG_PWM) -/* PWM user APIs */ + +/* PWM consumer APIs */ +int pwm_round_waveform_might_sleep(struct pwm_device *pwm, struct pwm_waveform *wf); +int pwm_get_waveform_might_sleep(struct pwm_device *pwm, struct pwm_waveform *wf); +int pwm_set_waveform_might_sleep(struct pwm_device *pwm, const struct pwm_waveform *wf, bool exact); int pwm_apply_might_sleep(struct pwm_device *pwm, const struct pwm_state *state); int pwm_apply_atomic(struct pwm_device *pwm, const struct pwm_state *state); +int pwm_get_state_hw(struct pwm_device *pwm, struct pwm_state *state); int pwm_adjust_config(struct pwm_device *pwm); /** @@ -400,9 +470,6 @@ static inline bool pwm_might_sleep(struct pwm_device *pwm) } /* PWM provider APIs */ -int pwm_capture(struct pwm_device *pwm, struct pwm_capture *result, - unsigned long timeout); - void pwmchip_put(struct pwm_chip *chip); struct pwm_chip *pwmchip_alloc(struct device *parent, unsigned int npwm, size_t sizeof_priv); struct pwm_chip *devm_pwmchip_alloc(struct device *parent, unsigned int npwm, size_t sizeof_priv); @@ -414,10 +481,6 @@ void pwmchip_remove(struct pwm_chip *chip); int __devm_pwmchip_add(struct device *dev, struct pwm_chip *chip, struct module *owner); #define devm_pwmchip_add(dev, chip) __devm_pwmchip_add(dev, chip, THIS_MODULE) -struct pwm_device *pwm_request_from_chip(struct pwm_chip *chip, - unsigned int index, - const char *label); - struct pwm_device *of_pwm_xlate_with_flags(struct pwm_chip *chip, const struct of_phandle_args *args); struct pwm_device *of_pwm_single_xlate(struct pwm_chip *chip, @@ -449,6 +512,11 @@ static inline int pwm_apply_atomic(struct pwm_device *pwm, return -EOPNOTSUPP; } +static inline int pwm_get_state_hw(struct pwm_device *pwm, struct pwm_state *state) +{ + return -EOPNOTSUPP; +} + static inline int pwm_adjust_config(struct pwm_device *pwm) { return -EOPNOTSUPP; @@ -472,13 +540,6 @@ 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 void pwmchip_put(struct pwm_chip *chip) { } @@ -512,14 +573,6 @@ static inline int devm_pwmchip_add(struct device *dev, struct pwm_chip *chip) return -EINVAL; } -static inline struct pwm_device *pwm_request_from_chip(struct pwm_chip *chip, - unsigned int index, - const char *label) -{ - might_sleep(); - return ERR_PTR(-ENODEV); -} - static inline struct pwm_device *pwm_get(struct device *dev, const char *consumer) { @@ -581,13 +634,6 @@ static inline void pwm_apply_args(struct pwm_device *pwm) pwm_apply_might_sleep(pwm, &state); } -/* only for backwards-compatibility, new code should not use this */ -static inline int pwm_apply_state(struct pwm_device *pwm, - const struct pwm_state *state) -{ - return pwm_apply_might_sleep(pwm, state); -} - struct pwm_lookup { struct list_head list; const char *provider; @@ -628,17 +674,4 @@ static inline void pwm_remove_table(struct pwm_lookup *table, size_t num) } #endif -#ifdef CONFIG_PWM_SYSFS -void pwmchip_sysfs_export(struct pwm_chip *chip); -void pwmchip_sysfs_unexport(struct pwm_chip *chip); -#else -static inline void pwmchip_sysfs_export(struct pwm_chip *chip) -{ -} - -static inline void pwmchip_sysfs_unexport(struct pwm_chip *chip) -{ -} -#endif /* CONFIG_PWM_SYSFS */ - #endif /* __LINUX_PWM_H */ diff --git a/include/linux/pwm_backlight.h b/include/linux/pwm_backlight.h index cdd2ac366bc7..0bf80e98d5b4 100644 --- a/include/linux/pwm_backlight.h +++ b/include/linux/pwm_backlight.h @@ -19,7 +19,6 @@ struct platform_pwm_backlight_data { int (*notify)(struct device *dev, int brightness); void (*notify_after)(struct device *dev, int brightness); void (*exit)(struct device *dev); - int (*check_fb)(struct device *dev, struct fb_info *info); }; #endif diff --git a/include/linux/pwrseq/consumer.h b/include/linux/pwrseq/consumer.h new file mode 100644 index 000000000000..7d583b4f266e --- /dev/null +++ b/include/linux/pwrseq/consumer.h @@ -0,0 +1,56 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2024 Linaro Ltd. + */ + +#ifndef __POWER_SEQUENCING_CONSUMER_H__ +#define __POWER_SEQUENCING_CONSUMER_H__ + +#include <linux/err.h> + +struct device; +struct pwrseq_desc; + +#if IS_ENABLED(CONFIG_POWER_SEQUENCING) + +struct pwrseq_desc * __must_check +pwrseq_get(struct device *dev, const char *target); +void pwrseq_put(struct pwrseq_desc *desc); + +struct pwrseq_desc * __must_check +devm_pwrseq_get(struct device *dev, const char *target); + +int pwrseq_power_on(struct pwrseq_desc *desc); +int pwrseq_power_off(struct pwrseq_desc *desc); + +#else /* CONFIG_POWER_SEQUENCING */ + +static inline struct pwrseq_desc * __must_check +pwrseq_get(struct device *dev, const char *target) +{ + return ERR_PTR(-ENOSYS); +} + +static inline void pwrseq_put(struct pwrseq_desc *desc) +{ +} + +static inline struct pwrseq_desc * __must_check +devm_pwrseq_get(struct device *dev, const char *target) +{ + return ERR_PTR(-ENOSYS); +} + +static inline int pwrseq_power_on(struct pwrseq_desc *desc) +{ + return -ENOSYS; +} + +static inline int pwrseq_power_off(struct pwrseq_desc *desc) +{ + return -ENOSYS; +} + +#endif /* CONFIG_POWER_SEQUENCING */ + +#endif /* __POWER_SEQUENCING_CONSUMER_H__ */ diff --git a/include/linux/pwrseq/provider.h b/include/linux/pwrseq/provider.h new file mode 100644 index 000000000000..cbc3607cbfcf --- /dev/null +++ b/include/linux/pwrseq/provider.h @@ -0,0 +1,75 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2024 Linaro Ltd. + */ + +#ifndef __POWER_SEQUENCING_PROVIDER_H__ +#define __POWER_SEQUENCING_PROVIDER_H__ + +struct device; +struct module; +struct pwrseq_device; + +typedef int (*pwrseq_power_state_func)(struct pwrseq_device *); +typedef int (*pwrseq_match_func)(struct pwrseq_device *, struct device *); + +/** + * struct pwrseq_unit_data - Configuration of a single power sequencing + * unit. + * @name: Name of the unit. + * @deps: Units that must be enabled before this one and disabled after it + * in the order they come in this array. Must be NULL-terminated. + * @enable: Callback running the part of the power-on sequence provided by + * this unit. + * @disable: Callback running the part of the power-off sequence provided + * by this unit. + */ +struct pwrseq_unit_data { + const char *name; + const struct pwrseq_unit_data **deps; + pwrseq_power_state_func enable; + pwrseq_power_state_func disable; +}; + +/** + * struct pwrseq_target_data - Configuration of a power sequencing target. + * @name: Name of the target. + * @unit: Final unit that this target must reach in order to be considered + * enabled. + * @post_enable: Callback run after the target unit has been enabled, *after* + * the state lock has been released. It's useful for implementing + * boot-up delays without blocking other users from powering up + * using the same power sequencer. + */ +struct pwrseq_target_data { + const char *name; + const struct pwrseq_unit_data *unit; + pwrseq_power_state_func post_enable; +}; + +/** + * struct pwrseq_config - Configuration used for registering a new provider. + * @parent: Parent device for the sequencer. Must be set. + * @owner: Module providing this device. + * @drvdata: Private driver data. + * @match: Provider callback used to match the consumer device to the sequencer. + * @targets: Array of targets for this power sequencer. Must be NULL-terminated. + */ +struct pwrseq_config { + struct device *parent; + struct module *owner; + void *drvdata; + pwrseq_match_func match; + const struct pwrseq_target_data **targets; +}; + +struct pwrseq_device * +pwrseq_device_register(const struct pwrseq_config *config); +void pwrseq_device_unregister(struct pwrseq_device *pwrseq); +struct pwrseq_device * +devm_pwrseq_device_register(struct device *dev, + const struct pwrseq_config *config); + +void *pwrseq_device_get_drvdata(struct pwrseq_device *pwrseq); + +#endif /* __POWER_SEQUENCING_PROVIDER_H__ */ diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h index cd1973e6ac4b..844a2743ca94 100644 --- a/include/linux/pxa2xx_ssp.h +++ b/include/linux/pxa2xx_ssp.h @@ -217,9 +217,9 @@ enum pxa_ssp_type { PXA27x_SSP, PXA3xx_SSP, PXA168_SSP, - MMP2_SSP, PXA910_SSP, CE4100_SSP, + MMP2_SSP, MRFLD_SSP, QUARK_X1000_SSP, /* Keep LPSS types sorted with lpss_platforms[] */ diff --git a/include/linux/qat/qat_mig_dev.h b/include/linux/qat/qat_mig_dev.h new file mode 100644 index 000000000000..dbbb6a063dd2 --- /dev/null +++ b/include/linux/qat/qat_mig_dev.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright(c) 2024 Intel Corporation */ +#ifndef QAT_MIG_DEV_H_ +#define QAT_MIG_DEV_H_ + +struct pci_dev; + +struct qat_mig_dev { + void *parent_accel_dev; + u8 *state; + u32 setup_size; + u32 remote_setup_size; + u32 state_size; + s32 vf_id; +}; + +struct qat_mig_dev *qat_vfmig_create(struct pci_dev *pdev, int vf_id); +int qat_vfmig_init(struct qat_mig_dev *mdev); +void qat_vfmig_cleanup(struct qat_mig_dev *mdev); +void qat_vfmig_reset(struct qat_mig_dev *mdev); +int qat_vfmig_open(struct qat_mig_dev *mdev); +void qat_vfmig_close(struct qat_mig_dev *mdev); +int qat_vfmig_suspend(struct qat_mig_dev *mdev); +int qat_vfmig_resume(struct qat_mig_dev *mdev); +int qat_vfmig_save_state(struct qat_mig_dev *mdev); +int qat_vfmig_save_setup(struct qat_mig_dev *mdev); +int qat_vfmig_load_state(struct qat_mig_dev *mdev); +int qat_vfmig_load_setup(struct qat_mig_dev *mdev, int size); +void qat_vfmig_destroy(struct qat_mig_dev *mdev); + +#endif /*QAT_MIG_DEV_H_*/ diff --git a/include/linux/quota.h b/include/linux/quota.h index 07071e64abf3..89a0d83ddad0 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -526,7 +526,7 @@ struct quota_info { const struct quota_format_ops *ops[MAXQUOTAS]; /* Operations for each type */ }; -int register_quota_format(struct quota_format_type *fmt); +void register_quota_format(struct quota_format_type *fmt); void unregister_quota_format(struct quota_format_type *fmt); struct quota_module_name { diff --git a/include/linux/random.h b/include/linux/random.h index b0a940af4fff..333cecfca93f 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -145,13 +145,6 @@ declare_get_random_var_wait(u64, u32) declare_get_random_var_wait(long, unsigned long) #undef declare_get_random_var -/* - * This is designed to be standalone for just prandom - * users, but for now we include it from <linux/random.h> - * for legacy reasons. - */ -#include <linux/prandom.h> - #ifdef CONFIG_SMP int random_prepare_cpu(unsigned int cpu); int random_online_cpu(unsigned int cpu); diff --git a/include/linux/randomize_kstack.h b/include/linux/randomize_kstack.h index 6d92b68efbf6..1d982dbdd0d0 100644 --- a/include/linux/randomize_kstack.h +++ b/include/linux/randomize_kstack.h @@ -32,13 +32,19 @@ DECLARE_PER_CPU(u32, kstack_offset); #endif /* - * Use, at most, 10 bits of entropy. We explicitly cap this to keep the - * "VLA" from being unbounded (see above). 10 bits leaves enough room for - * per-arch offset masks to reduce entropy (by removing higher bits, since - * high entropy may overly constrain usable stack space), and for - * compiler/arch-specific stack alignment to remove the lower bits. + * Use, at most, 6 bits of entropy (on 64-bit; 8 on 32-bit). This cap is + * to keep the "VLA" from being unbounded (see above). Additionally clear + * the bottom 4 bits (on 64-bit systems, 2 for 32-bit), since stack + * alignment will always be at least word size. This makes the compiler + * code gen better when it is applying the actual per-arch alignment to + * the final offset. The resulting randomness is reasonable without overly + * constraining usable stack space. */ -#define KSTACK_OFFSET_MAX(x) ((x) & 0x3FF) +#ifdef CONFIG_64BIT +#define KSTACK_OFFSET_MAX(x) ((x) & 0b1111110000) +#else +#define KSTACK_OFFSET_MAX(x) ((x) & 0b1111111100) +#endif /** * add_random_kstack_offset - Increase stack utilization by previously diff --git a/include/linux/range.h b/include/linux/range.h index 6ad0b73cb7ad..d7f98e1285d7 100644 --- a/include/linux/range.h +++ b/include/linux/range.h @@ -13,11 +13,20 @@ 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) +/* True if r1 completely contains r2 */ +static inline bool range_contains(const struct range *r1, + const struct range *r2) { return r1->start <= r2->start && r1->end >= r2->end; } +/* True if any part of r1 overlaps r2 */ +static inline bool range_overlaps(const struct range *r1, + const struct range *r2) +{ + return r1->start <= r2->end && r1->end >= r2->start; +} + int add_range(struct range *range, int az, int nr_range, u64 start, u64 end); @@ -31,4 +40,10 @@ int clean_sort_range(struct range *range, int az); void sort_range(struct range *range, int nr_range); +#define DEFINE_RANGE(_start, _end) \ +(struct range) { \ + .start = (_start), \ + .end = (_end), \ + } + #endif diff --git a/include/linux/ratelimit_types.h b/include/linux/ratelimit_types.h index 002266693e50..765232ce0b5e 100644 --- a/include/linux/ratelimit_types.h +++ b/include/linux/ratelimit_types.h @@ -19,8 +19,8 @@ struct ratelimit_state { int burst; int printed; int missed; + unsigned int flags; unsigned long begin; - unsigned long flags; }; #define RATELIMIT_STATE_INIT_FLAGS(name, interval_init, burst_init, flags_init) { \ diff --git a/include/linux/rbtree.h b/include/linux/rbtree.h index f7edca369eda..8d2ba3749866 100644 --- a/include/linux/rbtree.h +++ b/include/linux/rbtree.h @@ -211,6 +211,43 @@ rb_add(struct rb_node *node, struct rb_root *tree, } /** + * rb_find_add_cached() - find equivalent @node in @tree, or add @node + * @node: node to look-for / insert + * @tree: tree to search / modify + * @cmp: operator defining the node order + * + * Returns the rb_node matching @node, or NULL when no match is found and @node + * is inserted. + */ +static __always_inline struct rb_node * +rb_find_add_cached(struct rb_node *node, struct rb_root_cached *tree, + int (*cmp)(const struct rb_node *new, const struct rb_node *exist)) +{ + bool leftmost = true; + struct rb_node **link = &tree->rb_root.rb_node; + struct rb_node *parent = NULL; + int c; + + while (*link) { + parent = *link; + c = cmp(node, parent); + + if (c < 0) { + link = &parent->rb_left; + } else if (c > 0) { + link = &parent->rb_right; + leftmost = false; + } else { + return parent; + } + } + + rb_link_node(node, parent, link); + rb_insert_color_cached(node, tree, leftmost); + return NULL; +} + +/** * rb_find_add() - find equivalent @node in @tree, or add @node * @node: node to look-for / insert * @tree: tree to search / modify @@ -245,6 +282,42 @@ rb_find_add(struct rb_node *node, struct rb_root *tree, } /** + * rb_find_add_rcu() - find equivalent @node in @tree, or add @node + * @node: node to look-for / insert + * @tree: tree to search / modify + * @cmp: operator defining the node order + * + * Adds a Store-Release for link_node. + * + * Returns the rb_node matching @node, or NULL when no match is found and @node + * is inserted. + */ +static __always_inline struct rb_node * +rb_find_add_rcu(struct rb_node *node, struct rb_root *tree, + int (*cmp)(struct rb_node *, const struct rb_node *)) +{ + struct rb_node **link = &tree->rb_node; + struct rb_node *parent = NULL; + int c; + + while (*link) { + parent = *link; + c = cmp(node, parent); + + if (c < 0) + link = &parent->rb_left; + else if (c > 0) + link = &parent->rb_right; + else + return parent; + } + + rb_link_node_rcu(node, parent, link); + rb_insert_color(node, tree); + return NULL; +} + +/** * rb_find() - find @key in tree @tree * @key: key to match * @tree: tree to search @@ -273,6 +346,37 @@ rb_find(const void *key, const struct rb_root *tree, } /** + * rb_find_rcu() - find @key in tree @tree + * @key: key to match + * @tree: tree to search + * @cmp: operator defining the node order + * + * Notably, tree descent vs concurrent tree rotations is unsound and can result + * in false-negatives. + * + * Returns the rb_node matching @key or NULL. + */ +static __always_inline struct rb_node * +rb_find_rcu(const void *key, const struct rb_root *tree, + int (*cmp)(const void *key, const struct rb_node *)) +{ + struct rb_node *node = tree->rb_node; + + while (node) { + int c = cmp(key, node); + + if (c < 0) + node = rcu_dereference_raw(node->rb_left); + else if (c > 0) + node = rcu_dereference_raw(node->rb_right); + else + return node; + } + + return NULL; +} + +/** * rb_find_first() - find the first @key in @tree * @key: key to match * @tree: tree to search diff --git a/include/linux/rbtree_latch.h b/include/linux/rbtree_latch.h index 6a0999c26c7c..2f630eb8307e 100644 --- a/include/linux/rbtree_latch.h +++ b/include/linux/rbtree_latch.h @@ -14,7 +14,7 @@ * * If we need to allow unconditional lookups (say as required for NMI context * usage) we need a more complex setup; this data structure provides this by - * employing the latch technique -- see @raw_write_seqcount_latch -- to + * employing the latch technique -- see @write_seqcount_latch_begin -- to * implement a latched RB-tree which does allow for unconditional lookups by * virtue of always having (at least) one stable copy of the tree. * @@ -132,7 +132,7 @@ __lt_find(void *key, struct latch_tree_root *ltr, int idx, * @ops: operators defining the node order * * It inserts @node into @root in an ordered fashion such that we can always - * observe one complete tree. See the comment for raw_write_seqcount_latch(). + * observe one complete tree. See the comment for write_seqcount_latch_begin(). * * The inserts use rcu_assign_pointer() to publish the element such that the * tree structure is stored before we can observe the new @node. @@ -145,10 +145,11 @@ latch_tree_insert(struct latch_tree_node *node, struct latch_tree_root *root, const struct latch_tree_ops *ops) { - raw_write_seqcount_latch(&root->seq); + write_seqcount_latch_begin(&root->seq); __lt_insert(node, root, 0, ops->less); - raw_write_seqcount_latch(&root->seq); + write_seqcount_latch(&root->seq); __lt_insert(node, root, 1, ops->less); + write_seqcount_latch_end(&root->seq); } /** @@ -159,7 +160,7 @@ latch_tree_insert(struct latch_tree_node *node, * * Removes @node from the trees @root in an ordered fashion such that we can * always observe one complete tree. See the comment for - * raw_write_seqcount_latch(). + * write_seqcount_latch_begin(). * * It is assumed that @node will observe one RCU quiescent state before being * reused of freed. @@ -172,10 +173,11 @@ latch_tree_erase(struct latch_tree_node *node, struct latch_tree_root *root, const struct latch_tree_ops *ops) { - raw_write_seqcount_latch(&root->seq); + write_seqcount_latch_begin(&root->seq); __lt_erase(node, root, 0); - raw_write_seqcount_latch(&root->seq); + write_seqcount_latch(&root->seq); __lt_erase(node, root, 1); + write_seqcount_latch_end(&root->seq); } /** @@ -204,9 +206,9 @@ latch_tree_find(void *key, struct latch_tree_root *root, unsigned int seq; do { - seq = raw_read_seqcount_latch(&root->seq); + seq = read_seqcount_latch(&root->seq); node = __lt_find(key, root, seq & 1, ops->comp); - } while (raw_read_seqcount_latch_retry(&root->seq, seq)); + } while (read_seqcount_latch_retry(&root->seq, seq)); return node; } diff --git a/include/linux/rcu_segcblist.h b/include/linux/rcu_segcblist.h index 659d13a7ddaa..2fdc2208f1ca 100644 --- a/include/linux/rcu_segcblist.h +++ b/include/linux/rcu_segcblist.h @@ -80,36 +80,35 @@ struct rcu_cblist { * | SEGCBLIST_RCU_CORE | SEGCBLIST_LOCKING | SEGCBLIST_OFFLOADED | * | | * | Callbacks processed by rcu_core() from softirqs or local | - * | rcuc kthread, while holding nocb_lock. Waking up CB and GP kthreads, | - * | allowing nocb_timer to be armed. | + * | rcuc kthread, while holding nocb_lock. Waking up CB and GP kthreads. | * ---------------------------------------------------------------------------- * | * v - * ----------------------------------- - * | | - * v v - * --------------------------------------- ----------------------------------| - * | SEGCBLIST_RCU_CORE | | | SEGCBLIST_RCU_CORE | | - * | SEGCBLIST_LOCKING | | | SEGCBLIST_LOCKING | | - * | SEGCBLIST_OFFLOADED | | | SEGCBLIST_OFFLOADED | | - * | SEGCBLIST_KTHREAD_CB | | SEGCBLIST_KTHREAD_GP | - * | | | | - * | | | | - * | CB kthread woke up and | | GP kthread woke up and | - * | acknowledged SEGCBLIST_OFFLOADED. | | acknowledged SEGCBLIST_OFFLOADED| - * | Processes callbacks concurrently | | | - * | with rcu_core(), holding | | | - * | nocb_lock. | | | - * --------------------------------------- ----------------------------------- - * | | - * ----------------------------------- + * ---------------------------------------------------------------------------- + * | SEGCBLIST_RCU_CORE | SEGCBLIST_LOCKING | SEGCBLIST_OFFLOADED | + * | + unparked CB kthread | + * | | + * | CB kthread got unparked and processes callbacks concurrently with | + * | rcu_core(), holding nocb_lock. | + * --------------------------------------------------------------------------- + * | + * v + * ---------------------------------------------------------------------------| + * | SEGCBLIST_RCU_CORE | | + * | SEGCBLIST_LOCKING | | + * | SEGCBLIST_OFFLOADED | | + * | SEGCBLIST_KTHREAD_GP | + * | + unparked CB kthread | + * | | + * | GP kthread woke up and acknowledged nocb_lock. | + * ---------------------------------------- ----------------------------------- * | * v * |--------------------------------------------------------------------------| - * | SEGCBLIST_LOCKING | | - * | SEGCBLIST_OFFLOADED | | + * | SEGCBLIST_LOCKING | | + * | SEGCBLIST_OFFLOADED | | * | SEGCBLIST_KTHREAD_GP | | - * | SEGCBLIST_KTHREAD_CB | + * | + unparked CB kthread | * | | * | Kthreads handle callbacks holding nocb_lock, local rcu_core() stops | * | handling callbacks. Enable bypass queueing. | @@ -125,8 +124,8 @@ struct rcu_cblist { * |--------------------------------------------------------------------------| * | SEGCBLIST_LOCKING | | * | SEGCBLIST_OFFLOADED | | - * | SEGCBLIST_KTHREAD_CB | | * | SEGCBLIST_KTHREAD_GP | + * | + unparked CB kthread | * | | * | CB/GP kthreads handle callbacks holding nocb_lock, local rcu_core() | * | ignores callbacks. Bypass enqueue is enabled. | @@ -137,11 +136,11 @@ struct rcu_cblist { * | SEGCBLIST_RCU_CORE | | * | SEGCBLIST_LOCKING | | * | SEGCBLIST_OFFLOADED | | - * | SEGCBLIST_KTHREAD_CB | | * | SEGCBLIST_KTHREAD_GP | + * | + unparked CB kthread | * | | * | CB/GP kthreads handle callbacks holding nocb_lock, local rcu_core() | - * | handles callbacks concurrently. Bypass enqueue is enabled. | + * | handles callbacks concurrently. Bypass enqueue is disabled. | * | Invoke RCU core so we make sure not to preempt it in the middle with | * | leaving some urgent work unattended within a jiffy. | * ---------------------------------------------------------------------------- @@ -150,42 +149,31 @@ struct rcu_cblist { * |--------------------------------------------------------------------------| * | SEGCBLIST_RCU_CORE | | * | SEGCBLIST_LOCKING | | - * | SEGCBLIST_KTHREAD_CB | | * | SEGCBLIST_KTHREAD_GP | + * | + unparked CB kthread | * | | * | CB/GP kthreads and local rcu_core() handle callbacks concurrently | - * | holding nocb_lock. Wake up CB and GP kthreads if necessary. Disable | - * | bypass enqueue. | + * | holding nocb_lock. Wake up GP kthread if necessary. | * ---------------------------------------------------------------------------- * | * v - * ----------------------------------- - * | | - * v v - * ---------------------------------------------------------------------------| - * | | | - * | SEGCBLIST_RCU_CORE | | SEGCBLIST_RCU_CORE | | - * | SEGCBLIST_LOCKING | | SEGCBLIST_LOCKING | | - * | SEGCBLIST_KTHREAD_CB | SEGCBLIST_KTHREAD_GP | - * | | | - * | GP kthread woke up and | CB kthread woke up and | - * | acknowledged the fact that | acknowledged the fact that | - * | SEGCBLIST_OFFLOADED got cleared. | SEGCBLIST_OFFLOADED got cleared. | - * | | The CB kthread goes to sleep | - * | The callbacks from the target CPU | until it ever gets re-offloaded. | - * | will be ignored from the GP kthread | | - * | loop. | | + * |--------------------------------------------------------------------------| + * | SEGCBLIST_RCU_CORE | | + * | SEGCBLIST_LOCKING | | + * | + unparked CB kthread | + * | | + * | GP kthread woke up and acknowledged the fact that SEGCBLIST_OFFLOADED | + * | got cleared. The callbacks from the target CPU will be ignored from the| + * | GP kthread loop. | * ---------------------------------------------------------------------------- - * | | - * ----------------------------------- * | * v * ---------------------------------------------------------------------------- * | SEGCBLIST_RCU_CORE | SEGCBLIST_LOCKING | + * | + parked CB kthread | * | | - * | Callbacks processed by rcu_core() from softirqs or local | - * | rcuc kthread, while holding nocb_lock. Forbid nocb_timer to be armed. | - * | Flush pending nocb_timer. Flush nocb bypass callbacks. | + * | CB kthread is parked. Callbacks processed by rcu_core() from softirqs or | + * | local rcuc kthread, while holding nocb_lock. | * ---------------------------------------------------------------------------- * | * v @@ -197,11 +185,7 @@ struct rcu_cblist { * ---------------------------------------------------------------------------- */ #define SEGCBLIST_ENABLED BIT(0) -#define SEGCBLIST_RCU_CORE BIT(1) -#define SEGCBLIST_LOCKING BIT(2) -#define SEGCBLIST_KTHREAD_CB BIT(3) -#define SEGCBLIST_KTHREAD_GP BIT(4) -#define SEGCBLIST_OFFLOADED BIT(5) +#define SEGCBLIST_OFFLOADED BIT(1) struct rcu_segcblist { struct rcu_head *head; diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 3dc1e58865f7..1b11926ddd47 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -30,6 +30,17 @@ static inline void INIT_LIST_HEAD_RCU(struct list_head *list) * way, we must not access it directly */ #define list_next_rcu(list) (*((struct list_head __rcu **)(&(list)->next))) +/* + * Return the ->prev pointer of a list_head in an rcu safe way. Don't + * access it directly. + * + * Any list traversed with list_bidir_prev_rcu() must never use + * list_del_rcu(). Doing so will poison the ->prev pointer that + * list_bidir_prev_rcu() relies on, which will result in segfaults. + * To prevent these segfaults, use list_bidir_del_rcu() instead + * of list_del_rcu(). + */ +#define list_bidir_prev_rcu(list) (*((struct list_head __rcu **)(&(list)->prev))) /** * list_tail_rcu - returns the prev pointer of the head of the list @@ -159,6 +170,39 @@ static inline void list_del_rcu(struct list_head *entry) } /** + * list_bidir_del_rcu - deletes entry from list without re-initialization + * @entry: the element to delete from the list. + * + * In contrast to list_del_rcu() doesn't poison the prev pointer thus + * allowing backwards traversal via list_bidir_prev_rcu(). + * + * Note: list_empty() on entry does not return true after this because + * the entry is in a special undefined state that permits RCU-based + * lockfree reverse traversal. In particular this means that we can not + * poison the forward and backwards pointers that may still be used for + * walking the list. + * + * The caller must take whatever precautions are necessary (such as + * holding appropriate locks) to avoid racing with another list-mutation + * primitive, such as list_bidir_del_rcu() or list_add_rcu(), running on + * this same list. However, it is perfectly legal to run concurrently + * with the _rcu list-traversal primitives, such as + * list_for_each_entry_rcu(). + * + * Note that list_del_rcu() and list_bidir_del_rcu() must not be used on + * the same list. + * + * Note that the caller is not permitted to immediately free + * the newly deleted entry. Instead, either synchronize_rcu() + * or call_rcu() must be used to defer freeing until an RCU + * grace period has elapsed. + */ +static inline void list_bidir_del_rcu(struct list_head *entry) +{ + __list_del_entry(entry); +} + +/** * hlist_del_init_rcu - deletes entry from hash list with re-initialization * @n: the element to delete from the hash list. * @@ -191,7 +235,10 @@ static inline void hlist_del_init_rcu(struct hlist_node *n) * @old : the element to be replaced * @new : the new element to insert * - * The @old entry will be replaced with the @new entry atomically. + * The @old entry will be replaced with the @new entry atomically from + * the perspective of concurrent readers. It is the caller's responsibility + * to synchronize with concurrent updaters, if any. + * * Note: @old should not be empty. */ static inline void list_replace_rcu(struct list_head *old, @@ -519,7 +566,9 @@ static inline void hlist_del_rcu(struct hlist_node *n) * @old : the element to be replaced * @new : the new element to insert * - * The @old entry will be replaced with the @new entry atomically. + * The @old entry will be replaced with the @new entry atomically from + * the perspective of concurrent readers. It is the caller's responsibility + * to synchronize with concurrent updaters, if any. */ static inline void hlist_replace_rcu(struct hlist_node *old, struct hlist_node *new) diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 17d7ed5f3ae6..48e5c03df1dd 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -29,16 +29,17 @@ #include <linux/lockdep.h> #include <linux/cleanup.h> #include <asm/processor.h> -#include <linux/cpumask.h> #include <linux/context_tracking_irq.h> #define ULONG_CMP_GE(a, b) (ULONG_MAX / 2 >= (a) - (b)) #define ULONG_CMP_LT(a, b) (ULONG_MAX / 2 < (a) - (b)) +#define RCU_SEQ_CTR_SHIFT 2 +#define RCU_SEQ_STATE_MASK ((1 << RCU_SEQ_CTR_SHIFT) - 1) + /* Exported common interfaces */ void call_rcu(struct rcu_head *head, rcu_callback_t func); void rcu_barrier_tasks(void); -void rcu_barrier_tasks_rude(void); void synchronize_rcu(void); struct rcu_gp_oldstate; @@ -145,11 +146,18 @@ void rcu_init_nohz(void); int rcu_nocb_cpu_offload(int cpu); int rcu_nocb_cpu_deoffload(int cpu); void rcu_nocb_flush_deferred_wakeup(void); + +#define RCU_NOCB_LOCKDEP_WARN(c, s) RCU_LOCKDEP_WARN(c, s) + #else /* #ifdef CONFIG_RCU_NOCB_CPU */ + static inline void rcu_init_nohz(void) { } static inline int rcu_nocb_cpu_offload(int cpu) { return -EINVAL; } static inline int rcu_nocb_cpu_deoffload(int cpu) { return 0; } static inline void rcu_nocb_flush_deferred_wakeup(void) { } + +#define RCU_NOCB_LOCKDEP_WARN(c, s) + #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ /* @@ -166,6 +174,7 @@ static inline void rcu_nocb_flush_deferred_wakeup(void) { } } while (0) void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func); void synchronize_rcu_tasks(void); +void rcu_tasks_torture_stats_print(char *tt, char *tf); # else # define rcu_tasks_classic_qs(t, preempt) do { } while (0) # define call_rcu_tasks call_rcu @@ -192,6 +201,7 @@ void rcu_tasks_trace_qs_blkd(struct task_struct *t); rcu_tasks_trace_qs_blkd(t); \ } \ } while (0) +void rcu_tasks_trace_torture_stats_print(char *tt, char *tf); # else # define rcu_tasks_trace_qs(t) do { } while (0) # endif @@ -203,13 +213,12 @@ do { \ } while (0) # ifdef CONFIG_TASKS_RUDE_RCU -void call_rcu_tasks_rude(struct rcu_head *head, rcu_callback_t func); void synchronize_rcu_tasks_rude(void); +void rcu_tasks_rude_torture_stats_print(char *tt, char *tf); # endif #define rcu_note_voluntary_context_switch(t) rcu_tasks_qs(t, false) void exit_tasks_rcu_start(void); -void exit_tasks_rcu_stop(void); void exit_tasks_rcu_finish(void); #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */ #define rcu_tasks_classic_qs(t, preempt) do { } while (0) @@ -218,7 +227,6 @@ void exit_tasks_rcu_finish(void); #define call_rcu_tasks call_rcu #define synchronize_rcu_tasks synchronize_rcu static inline void exit_tasks_rcu_start(void) { } -static inline void exit_tasks_rcu_stop(void) { } static inline void exit_tasks_rcu_finish(void) { } #endif /* #else #ifdef CONFIG_TASKS_RCU_GENERIC */ @@ -393,7 +401,7 @@ static inline int debug_lockdep_rcu_enabled(void) */ #define RCU_LOCKDEP_WARN(c, s) \ do { \ - static bool __section(".data.unlikely") __warned; \ + static bool __section(".data..unlikely") __warned; \ if (debug_lockdep_rcu_enabled() && (c) && \ debug_lockdep_rcu_enabled() && !__warned) { \ __warned = true; \ @@ -401,15 +409,15 @@ static inline int debug_lockdep_rcu_enabled(void) } \ } while (0) -#if defined(CONFIG_PROVE_RCU) && !defined(CONFIG_PREEMPT_RCU) +#ifndef CONFIG_PREEMPT_RCU static inline void rcu_preempt_sleep_check(void) { RCU_LOCKDEP_WARN(lock_is_held(&rcu_lock_map), "Illegal context switch in RCU read-side critical section"); } -#else /* #ifdef CONFIG_PROVE_RCU */ +#else // #ifndef CONFIG_PREEMPT_RCU static inline void rcu_preempt_sleep_check(void) { } -#endif /* #else #ifdef CONFIG_PROVE_RCU */ +#endif // #else // #ifndef CONFIG_PREEMPT_RCU #define rcu_sleep_check() \ do { \ @@ -421,11 +429,71 @@ static inline void rcu_preempt_sleep_check(void) { } "Illegal context switch in RCU-sched read-side critical section"); \ } while (0) +// See RCU_LOCKDEP_WARN() for an explanation of the double call to +// debug_lockdep_rcu_enabled(). +static inline bool lockdep_assert_rcu_helper(bool c) +{ + return debug_lockdep_rcu_enabled() && + (c || !rcu_is_watching() || !rcu_lockdep_current_cpu_online()) && + debug_lockdep_rcu_enabled(); +} + +/** + * lockdep_assert_in_rcu_read_lock - WARN if not protected by rcu_read_lock() + * + * Splats if lockdep is enabled and there is no rcu_read_lock() in effect. + */ +#define lockdep_assert_in_rcu_read_lock() \ + WARN_ON_ONCE(lockdep_assert_rcu_helper(!lock_is_held(&rcu_lock_map))) + +/** + * lockdep_assert_in_rcu_read_lock_bh - WARN if not protected by rcu_read_lock_bh() + * + * Splats if lockdep is enabled and there is no rcu_read_lock_bh() in effect. + * Note that local_bh_disable() and friends do not suffice here, instead an + * actual rcu_read_lock_bh() is required. + */ +#define lockdep_assert_in_rcu_read_lock_bh() \ + WARN_ON_ONCE(lockdep_assert_rcu_helper(!lock_is_held(&rcu_bh_lock_map))) + +/** + * lockdep_assert_in_rcu_read_lock_sched - WARN if not protected by rcu_read_lock_sched() + * + * Splats if lockdep is enabled and there is no rcu_read_lock_sched() + * in effect. Note that preempt_disable() and friends do not suffice here, + * instead an actual rcu_read_lock_sched() is required. + */ +#define lockdep_assert_in_rcu_read_lock_sched() \ + WARN_ON_ONCE(lockdep_assert_rcu_helper(!lock_is_held(&rcu_sched_lock_map))) + +/** + * lockdep_assert_in_rcu_reader - WARN if not within some type of RCU reader + * + * Splats if lockdep is enabled and there is no RCU reader of any + * type in effect. Note that regions of code protected by things like + * preempt_disable, local_bh_disable(), and local_irq_disable() all qualify + * as RCU readers. + * + * Note that this will never trigger in PREEMPT_NONE or PREEMPT_VOLUNTARY + * kernels that are not also built with PREEMPT_COUNT. But if you have + * lockdep enabled, you might as well also enable PREEMPT_COUNT. + */ +#define lockdep_assert_in_rcu_reader() \ + WARN_ON_ONCE(lockdep_assert_rcu_helper(!lock_is_held(&rcu_lock_map) && \ + !lock_is_held(&rcu_bh_lock_map) && \ + !lock_is_held(&rcu_sched_lock_map) && \ + preemptible())) + #else /* #ifdef CONFIG_PROVE_RCU */ #define RCU_LOCKDEP_WARN(c, s) do { } while (0 && (c)) #define rcu_sleep_check() do { } while (0) +#define lockdep_assert_in_rcu_read_lock() do { } while (0) +#define lockdep_assert_in_rcu_read_lock_bh() do { } while (0) +#define lockdep_assert_in_rcu_read_lock_sched() do { } while (0) +#define lockdep_assert_in_rcu_reader() do { } while (0) + #endif /* #else #ifdef CONFIG_PROVE_RCU */ /* @@ -809,9 +877,9 @@ static inline void rcu_read_unlock(void) { RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_unlock() used illegally while idle"); + rcu_lock_release(&rcu_lock_map); /* Keep acq info for rls diags. */ __release(RCU); __rcu_read_unlock(); - rcu_lock_release(&rcu_lock_map); /* Keep acq info for rls diags. */ } /** @@ -1090,6 +1158,18 @@ rcu_head_after_call_rcu(struct rcu_head *rhp, rcu_callback_t f) extern int rcu_expedited; extern int rcu_normal; -DEFINE_LOCK_GUARD_0(rcu, rcu_read_lock(), rcu_read_unlock()) +DEFINE_LOCK_GUARD_0(rcu, + do { + rcu_read_lock(); + /* + * sparse doesn't call the cleanup function, + * so just release immediately and don't track + * the context. We don't need to anyway, since + * the whole point of the guard is to not need + * the explicit unlock. + */ + __release(RCU); + } while (0), + rcu_read_unlock()) #endif /* __LINUX_RCUPDATE_H */ diff --git a/include/linux/rcupdate_trace.h b/include/linux/rcupdate_trace.h index eda493200663..e6c44eb428ab 100644 --- a/include/linux/rcupdate_trace.h +++ b/include/linux/rcupdate_trace.h @@ -10,6 +10,7 @@ #include <linux/sched.h> #include <linux/rcupdate.h> +#include <linux/cleanup.h> extern struct lockdep_map rcu_trace_lock_map; @@ -98,4 +99,8 @@ static inline void rcu_read_lock_trace(void) { BUG(); } static inline void rcu_read_unlock_trace(void) { BUG(); } #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ +DEFINE_LOCK_GUARD_0(rcu_tasks_trace, + rcu_read_lock_trace(), + rcu_read_unlock_trace()) + #endif /* __LINUX_RCUPDATE_TRACE_H */ diff --git a/include/linux/rcupdate_wait.h b/include/linux/rcupdate_wait.h index d07f0848802e..f9bed3d3f78d 100644 --- a/include/linux/rcupdate_wait.h +++ b/include/linux/rcupdate_wait.h @@ -19,18 +19,18 @@ struct rcu_synchronize { }; void wakeme_after_rcu(struct rcu_head *head); -void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array, +void __wait_rcu_gp(bool checktiny, unsigned int state, int n, call_rcu_func_t *crcu_array, struct rcu_synchronize *rs_array); -#define _wait_rcu_gp(checktiny, ...) \ -do { \ - call_rcu_func_t __crcu_array[] = { __VA_ARGS__ }; \ - struct rcu_synchronize __rs_array[ARRAY_SIZE(__crcu_array)]; \ - __wait_rcu_gp(checktiny, ARRAY_SIZE(__crcu_array), \ - __crcu_array, __rs_array); \ +#define _wait_rcu_gp(checktiny, state, ...) \ +do { \ + call_rcu_func_t __crcu_array[] = { __VA_ARGS__ }; \ + struct rcu_synchronize __rs_array[ARRAY_SIZE(__crcu_array)]; \ + __wait_rcu_gp(checktiny, state, ARRAY_SIZE(__crcu_array), __crcu_array, __rs_array); \ } while (0) -#define wait_rcu_gp(...) _wait_rcu_gp(false, __VA_ARGS__) +#define wait_rcu_gp(...) _wait_rcu_gp(false, TASK_UNINTERRUPTIBLE, __VA_ARGS__) +#define wait_rcu_gp_state(state, ...) _wait_rcu_gp(false, state, __VA_ARGS__) /** * synchronize_rcu_mult - Wait concurrently for multiple grace periods @@ -54,7 +54,7 @@ do { \ * grace period. */ #define synchronize_rcu_mult(...) \ - _wait_rcu_gp(IS_ENABLED(CONFIG_TINY_RCU), __VA_ARGS__) + _wait_rcu_gp(IS_ENABLED(CONFIG_TINY_RCU), TASK_UNINTERRUPTIBLE, __VA_ARGS__) static inline void cond_resched_rcu(void) { @@ -65,4 +65,15 @@ static inline void cond_resched_rcu(void) #endif } +// Has the current task blocked within its current RCU read-side +// critical section? +static inline bool has_rcu_reader_blocked(void) +{ +#ifdef CONFIG_PREEMPT_RCU + return !list_empty(¤t->rcu_node_entry); +#else + return false; +#endif +} + #endif /* _LINUX_SCHED_RCUPDATE_WAIT_H */ diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index d9ac7b136aea..fe42315f667f 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -111,6 +111,11 @@ static inline void __kvfree_call_rcu(struct rcu_head *head, void *ptr) kvfree(ptr); } +static inline void kvfree_rcu_barrier(void) +{ + rcu_barrier(); +} + #ifdef CONFIG_KASAN_GENERIC void kvfree_call_rcu(struct rcu_head *head, void *ptr); #else @@ -158,9 +163,8 @@ void rcu_scheduler_starting(void); static inline void rcu_end_inkernel_boot(void) { } static inline bool rcu_inkernel_boot_has_ended(void) { return true; } static inline bool rcu_is_watching(void) { return true; } -static inline void rcu_momentary_dyntick_idle(void) { } +static inline void rcu_momentary_eqs(void) { } static inline void kfree_rcu_scheduler_running(void) { } -static inline bool rcu_gp_might_be_stalled(void) { return false; } /* Avoid RCU read-side critical sections leaking across. */ static inline void rcu_all_qs(void) { barrier(); } diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 254244202ea9..27d86d912781 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -35,11 +35,11 @@ static inline void rcu_virt_note_context_switch(void) void synchronize_rcu_expedited(void); void kvfree_call_rcu(struct rcu_head *head, void *ptr); +void kvfree_rcu_barrier(void); void rcu_barrier(void); -void rcu_momentary_dyntick_idle(void); +void rcu_momentary_eqs(void); void kfree_rcu_scheduler_running(void); -bool rcu_gp_might_be_stalled(void); struct rcu_gp_oldstate { unsigned long rgos_norm; diff --git a/include/linux/refcount.h b/include/linux/refcount.h index 59b3b752394d..35f039ecb272 100644 --- a/include/linux/refcount.h +++ b/include/linux/refcount.h @@ -266,12 +266,12 @@ bool __refcount_sub_and_test(int i, refcount_t *r, int *oldp) if (oldp) *oldp = old; - if (old == i) { + if (old > 0 && old == i) { smp_acquire__after_ctrl_dep(); return true; } - if (unlikely(old < 0 || old - i < 0)) + if (unlikely(old <= 0 || old - i < 0)) refcount_warn_saturate(r, REFCOUNT_SUB_UAF); return false; diff --git a/include/linux/regmap.h b/include/linux/regmap.h index b743241cfb7c..3a96d068915f 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -54,7 +54,14 @@ struct sdw_slave; #define REGMAP_UPSHIFT(s) (-(s)) #define REGMAP_DOWNSHIFT(s) (s) -/* An enum of all the supported cache types */ +/* + * The supported cache types, the default is no cache. Any new caches + * should usually use the maple tree cache unless they specifically + * require that there are never any allocations at runtime and can't + * provide defaults in which case they should use the flat cache. The + * rbtree cache *may* have some performance advantage for very low end + * systems that make heavy use of cache syncs but is mainly legacy. + */ enum regcache_type { REGCACHE_NONE, REGCACHE_RBTREE, @@ -106,17 +113,17 @@ struct reg_sequence { * @addr: Address to poll * @val: Unsigned integer variable to read the value into * @cond: Break condition (usually involving @val) - * @sleep_us: Maximum time to sleep between reads in us (0 - * tight-loops). Should be less than ~20ms since usleep_range - * is used (see Documentation/timers/timers-howto.rst). + * @sleep_us: Maximum time to sleep between reads in us (0 tight-loops). Please + * read usleep_range() function description for details and + * limitations. * @timeout_us: Timeout in us, 0 means never timeout * - * Returns 0 on success and -ETIMEDOUT upon a timeout or the regmap_read + * This is modelled after the readx_poll_timeout macros in linux/iopoll.h. + * + * Returns: 0 on success and -ETIMEDOUT upon a timeout or the regmap_read * error return value in case of a error read. In the two former cases, * the last read value at @addr is stored in @val. Must not be called * from atomic context if sleep_us or timeout_us are used. - * - * This is modelled after the readx_poll_timeout macros in linux/iopoll.h. */ #define regmap_read_poll_timeout(map, addr, val, cond, sleep_us, timeout_us) \ ({ \ @@ -133,20 +140,20 @@ struct reg_sequence { * @addr: Address to poll * @val: Unsigned integer variable to read the value into * @cond: Break condition (usually involving @val) - * @delay_us: Time to udelay between reads in us (0 tight-loops). - * Should be less than ~10us since udelay is used - * (see Documentation/timers/timers-howto.rst). + * @delay_us: Time to udelay between reads in us (0 tight-loops). Please + * read udelay() function description for details and + * limitations. * @timeout_us: Timeout in us, 0 means never timeout * - * Returns 0 on success and -ETIMEDOUT upon a timeout or the regmap_read - * error return value in case of a error read. In the two former cases, - * the last read value at @addr is stored in @val. - * * This is modelled after the readx_poll_timeout_atomic macros in linux/iopoll.h. * * Note: In general regmap cannot be used in atomic context. If you want to use * this macro then first setup your regmap for atomic use (flat or no cache * and MMIO regmap). + * + * Returns: 0 on success and -ETIMEDOUT upon a timeout or the regmap_read + * error return value in case of a error read. In the two former cases, + * the last read value at @addr is stored in @val. */ #define regmap_read_poll_timeout_atomic(map, addr, val, cond, delay_us, timeout_us) \ ({ \ @@ -177,17 +184,17 @@ struct reg_sequence { * @field: Regmap field to read from * @val: Unsigned integer variable to read the value into * @cond: Break condition (usually involving @val) - * @sleep_us: Maximum time to sleep between reads in us (0 - * tight-loops). Should be less than ~20ms since usleep_range - * is used (see Documentation/timers/timers-howto.rst). + * @sleep_us: Maximum time to sleep between reads in us (0 tight-loops). Please + * read usleep_range() function description for details and + * limitations. * @timeout_us: Timeout in us, 0 means never timeout * - * Returns 0 on success and -ETIMEDOUT upon a timeout or the regmap_field_read + * This is modelled after the readx_poll_timeout macros in linux/iopoll.h. + * + * Returns: 0 on success and -ETIMEDOUT upon a timeout or the regmap_field_read * error return value in case of a error read. In the two former cases, * the last read value at @addr is stored in @val. Must not be called * from atomic context if sleep_us or timeout_us are used. - * - * This is modelled after the readx_poll_timeout macros in linux/iopoll.h. */ #define regmap_field_read_poll_timeout(field, val, cond, sleep_us, timeout_us) \ ({ \ @@ -297,15 +304,6 @@ typedef void (*regmap_unlock)(void *); * performed on such table (a register is no increment * readable if it belongs to one of the ranges specified * by rd_noinc_table). - * @disable_locking: This regmap is either protected by external means or - * is guaranteed not to be accessed from multiple threads. - * Don't use any locking mechanisms. - * @lock: Optional lock callback (overrides regmap's default lock - * function, based on spinlock or mutex). - * @unlock: As above for unlocking. - * @lock_arg: this field is passed as the only argument of lock/unlock - * functions (ignored in case regular lock/unlock functions - * are not overridden). * @reg_read: Optional callback that if filled will be used to perform * all the reads from the registers. Should only be provided for * devices whose read operation cannot be represented as a simple @@ -323,6 +321,7 @@ typedef void (*regmap_unlock)(void *); * @write: Same as above for writing. * @max_raw_read: Max raw read size that can be used on the device. * @max_raw_write: Max raw write size that can be used on the device. + * @can_sleep: Optional, specifies whether regmap operations can sleep. * @fast_io: Register IO is fast. Use a spinlock instead of a mutex * to perform locking. This field is ignored if custom lock/unlock * functions are used (see fields lock/unlock of struct regmap_config). @@ -331,6 +330,15 @@ typedef void (*regmap_unlock)(void *); * Use it only for "no-bus" cases. * @io_port: Support IO port accessors. Makes sense only when MMIO vs. IO port * access can be distinguished. + * @disable_locking: This regmap is either protected by external means or + * is guaranteed not to be accessed from multiple threads. + * Don't use any locking mechanisms. + * @lock: Optional lock callback (overrides regmap's default lock + * function, based on spinlock or mutex). + * @unlock: As above for unlocking. + * @lock_arg: This field is passed as the only argument of lock/unlock + * functions (ignored in case regular lock/unlock functions + * are not overridden). * @max_register: Optional, specifies the maximum valid register address. * @max_register_is_0: Optional, specifies that zero value in @max_register * should be taken into account. This is a workaround to @@ -373,21 +381,20 @@ typedef void (*regmap_unlock)(void *); * @reg_defaults_raw: Power on reset values for registers (for use with * register cache support). * @num_reg_defaults_raw: Number of elements in reg_defaults_raw. - * @reg_format_endian: Endianness for formatted register addresses. If this is - * DEFAULT, the @reg_format_endian_default value from the - * regmap bus is used. - * @val_format_endian: Endianness for formatted register values. If this is - * DEFAULT, the @reg_format_endian_default value from the - * regmap bus is used. - * - * @ranges: Array of configuration entries for virtual address ranges. - * @num_ranges: Number of range configuration entries. * @use_hwlock: Indicate if a hardware spinlock should be used. * @use_raw_spinlock: Indicate if a raw spinlock should be used. * @hwlock_id: Specify the hardware spinlock id. * @hwlock_mode: The hardware spinlock mode, should be HWLOCK_IRQSTATE, * HWLOCK_IRQ or 0. - * @can_sleep: Optional, specifies whether regmap operations can sleep. + * @reg_format_endian: Endianness for formatted register addresses. If this is + * DEFAULT, the @reg_format_endian_default value from the + * regmap bus is used. + * @val_format_endian: Endianness for formatted register values. If this is + * DEFAULT, the @reg_format_endian_default value from the + * regmap bus is used. + * + * @ranges: Array of configuration entries for virtual address ranges. + * @num_ranges: Number of range configuration entries. */ struct regmap_config { const char *name; @@ -406,11 +413,6 @@ struct regmap_config { bool (*writeable_noinc_reg)(struct device *dev, unsigned int reg); bool (*readable_noinc_reg)(struct device *dev, unsigned int reg); - bool disable_locking; - regmap_lock lock; - regmap_unlock unlock; - void *lock_arg; - int (*reg_read)(void *context, unsigned int reg, unsigned int *val); int (*reg_write)(void *context, unsigned int reg, unsigned int val); int (*reg_update_bits)(void *context, unsigned int reg, @@ -422,9 +424,16 @@ struct regmap_config { size_t max_raw_read; size_t max_raw_write; + bool can_sleep; + bool fast_io; bool io_port; + bool disable_locking; + regmap_lock lock; + regmap_unlock unlock; + void *lock_arg; + unsigned int max_register; bool max_register_is_0; const struct regmap_access_table *wr_table; @@ -448,18 +457,16 @@ struct regmap_config { bool use_relaxed_mmio; bool can_multi_write; - enum regmap_endian reg_format_endian; - enum regmap_endian val_format_endian; - - const struct regmap_range_cfg *ranges; - unsigned int num_ranges; - bool use_hwlock; bool use_raw_spinlock; unsigned int hwlock_id; unsigned int hwlock_mode; - bool can_sleep; + enum regmap_endian reg_format_endian; + enum regmap_endian val_format_endian; + + const struct regmap_range_cfg *ranges; + unsigned int num_ranges; }; /** @@ -499,6 +506,32 @@ struct regmap_range_cfg { unsigned int window_len; }; +/** + * struct regmap_sdw_mbq_cfg - Configuration for Multi-Byte Quantities + * + * @mbq_size: Callback returning the actual size of the given register. + * @deferrable: Callback returning true if the hardware can defer + * transactions to the given register. Deferral should + * only be used by SDCA parts and typically which controls + * are deferrable will be specified in either as a hard + * coded list or from the DisCo tables in the platform + * firmware. + * + * @timeout_us: The time in microseconds after which waiting for a deferred + * transaction should time out. + * @retry_us: The time in microseconds between polls of the function busy + * status whilst waiting for an opportunity to retry a deferred + * transaction. + * + * Provides additional configuration required for SoundWire MBQ register maps. + */ +struct regmap_sdw_mbq_cfg { + int (*mbq_size)(struct device *dev, unsigned int reg); + bool (*deferrable)(struct device *dev, unsigned int reg); + unsigned long timeout_us; + unsigned long retry_us; +}; + struct regmap_async; typedef int (*regmap_hw_write)(void *context, const void *data, @@ -645,6 +678,7 @@ struct regmap *__regmap_init_sdw(struct sdw_slave *sdw, const char *lock_name); struct regmap *__regmap_init_sdw_mbq(struct sdw_slave *sdw, const struct regmap_config *config, + const struct regmap_sdw_mbq_cfg *mbq_config, struct lock_class_key *lock_key, const char *lock_name); struct regmap *__regmap_init_spi_avmm(struct spi_device *spi, @@ -706,6 +740,7 @@ struct regmap *__devm_regmap_init_sdw(struct sdw_slave *sdw, const char *lock_name); struct regmap *__devm_regmap_init_sdw_mbq(struct sdw_slave *sdw, const struct regmap_config *config, + const struct regmap_sdw_mbq_cfg *mbq_config, struct lock_class_key *lock_key, const char *lock_name); struct regmap *__devm_regmap_init_slimbus(struct slim_device *slimbus, @@ -935,7 +970,22 @@ bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg); */ #define regmap_init_sdw_mbq(sdw, config) \ __regmap_lockdep_wrapper(__regmap_init_sdw_mbq, #config, \ - sdw, config) + sdw, config, NULL) + +/** + * regmap_init_sdw_mbq_cfg() - Initialise MBQ SDW register map with config + * + * @sdw: Device that will be interacted with + * @config: Configuration for register map + * @mbq_config: Properties for the MBQ registers + * + * The return value will be an ERR_PTR() on error or a valid pointer + * to a struct regmap. The regmap will be automatically freed by the + * device management code. + */ +#define regmap_init_sdw_mbq_cfg(sdw, config, mbq_config) \ + __regmap_lockdep_wrapper(__regmap_init_sdw_mbq, #config, \ + sdw, config, mbq_config) /** * regmap_init_spi_avmm() - Initialize register map for Intel SPI Slave @@ -1148,7 +1198,22 @@ bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg); */ #define devm_regmap_init_sdw_mbq(sdw, config) \ __regmap_lockdep_wrapper(__devm_regmap_init_sdw_mbq, #config, \ - sdw, config) + sdw, config, NULL) + +/** + * devm_regmap_init_sdw_mbq_cfg() - Initialise managed MBQ SDW register map with config + * + * @sdw: Device that will be interacted with + * @config: Configuration for register map + * @mbq_config: Properties for the MBQ registers + * + * The return value will be an ERR_PTR() on error or a valid pointer + * to a struct regmap. The regmap will be automatically freed by the + * device management code. + */ +#define devm_regmap_init_sdw_mbq_cfg(sdw, config, mbq_config) \ + __regmap_lockdep_wrapper(__devm_regmap_init_sdw_mbq, \ + #config, sdw, config, mbq_config) /** * devm_regmap_init_slimbus() - Initialise managed register map @@ -1230,12 +1295,15 @@ int regmap_multi_reg_write_bypassed(struct regmap *map, int regmap_raw_write_async(struct regmap *map, unsigned int reg, const void *val, size_t val_len); int regmap_read(struct regmap *map, unsigned int reg, unsigned int *val); +int regmap_read_bypassed(struct regmap *map, unsigned int reg, unsigned int *val); int regmap_raw_read(struct regmap *map, unsigned int reg, void *val, size_t val_len); int regmap_noinc_read(struct regmap *map, unsigned int reg, void *val, size_t val_len); int regmap_bulk_read(struct regmap *map, unsigned int reg, void *val, size_t val_count); +int regmap_multi_reg_read(struct regmap *map, const unsigned int *reg, void *val, + size_t val_count); int regmap_update_bits_base(struct regmap *map, unsigned int reg, unsigned int mask, unsigned int val, bool *change, bool async, bool force); @@ -1325,6 +1393,15 @@ static inline int regmap_clear_bits(struct regmap *map, return regmap_update_bits_base(map, reg, bits, 0, NULL, false, false); } +static inline int regmap_assign_bits(struct regmap *map, unsigned int reg, + unsigned int bits, bool value) +{ + if (value) + return regmap_set_bits(map, reg, bits); + else + return regmap_clear_bits(map, reg, bits); +} + int regmap_test_bits(struct regmap *map, unsigned int reg, unsigned int bits); /** @@ -1518,6 +1595,9 @@ struct regmap_irq_chip_data; * struct regmap_irq_chip - Description of a generic regmap irq_chip. * * @name: Descriptive name for IRQ controller. + * @domain_suffix: Name suffix to be appended to end of IRQ domain name. Needed + * when multiple regmap-IRQ controllers are created from same + * device. * * @main_status: Base main status register address. For chips which have * interrupts arranged in separate sub-irq blocks with own IRQ @@ -1603,10 +1683,11 @@ struct regmap_irq_chip_data; */ struct regmap_irq_chip { const char *name; + const char *domain_suffix; unsigned int main_status; unsigned int num_main_status_bits; - struct regmap_irq_sub_irq_map *sub_reg_offsets; + const struct regmap_irq_sub_irq_map *sub_reg_offsets; int num_main_regs; unsigned int status_base; @@ -1739,6 +1820,13 @@ static inline int regmap_read(struct regmap *map, unsigned int reg, return -EINVAL; } +static inline int regmap_read_bypassed(struct regmap *map, unsigned int reg, + unsigned int *val) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + static inline int regmap_raw_read(struct regmap *map, unsigned int reg, void *val, size_t val_len) { @@ -1782,6 +1870,13 @@ static inline int regmap_clear_bits(struct regmap *map, return -EINVAL; } +static inline int regmap_assign_bits(struct regmap *map, unsigned int reg, + unsigned int bits, bool value) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + static inline int regmap_test_bits(struct regmap *map, unsigned int reg, unsigned int bits) { diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index 4660582a3302..ffe912f345ae 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -128,11 +128,11 @@ struct regulator; * * @supply: The name of the supply. Initialised by the user before * using the bulk regulator APIs. + * @consumer: The regulator consumer for the supply. This will be managed + * by the bulk API. * @init_load_uA: After getting the regulator, regulator_set_load() will be * called with this load. Initialised by the user before * using the bulk regulator APIs. - * @consumer: The regulator consumer for the supply. This will be managed - * by the bulk API. * * The regulator APIs provide a series of regulator_bulk_() API calls as * a convenience to consumers which require multiple supplies. This @@ -140,8 +140,8 @@ struct regulator; */ struct regulator_bulk_data { const char *supply; - int init_load_uA; struct regulator *consumer; + int init_load_uA; /* private: Internal use */ int ret; @@ -164,6 +164,7 @@ struct regulator *__must_check devm_regulator_get_optional(struct device *dev, const char *id); int devm_regulator_get_enable(struct device *dev, const char *id); int devm_regulator_get_enable_optional(struct device *dev, const char *id); +int devm_regulator_get_enable_read_voltage(struct device *dev, const char *id); void regulator_put(struct regulator *regulator); void devm_regulator_put(struct regulator *regulator); @@ -199,8 +200,6 @@ int regulator_disable_deferred(struct regulator *regulator, int ms); int __must_check regulator_bulk_get(struct device *dev, int num_consumers, struct regulator_bulk_data *consumers); -int __must_check of_regulator_bulk_get_all(struct device *dev, struct device_node *np, - struct regulator_bulk_data **consumers); int __must_check devm_regulator_bulk_get(struct device *dev, int num_consumers, struct regulator_bulk_data *consumers); void devm_regulator_bulk_put(struct regulator_bulk_data *consumers); @@ -234,6 +233,11 @@ int regulator_sync_voltage(struct regulator *regulator); int regulator_set_current_limit(struct regulator *regulator, int min_uA, int max_uA); int regulator_get_current_limit(struct regulator *regulator); +int regulator_get_unclaimed_power_budget(struct regulator *regulator); +int regulator_request_power_budget(struct regulator *regulator, + unsigned int pw_req); +void regulator_free_power_budget(struct regulator *regulator, + unsigned int pw); int regulator_set_mode(struct regulator *regulator, unsigned int mode); unsigned int regulator_get_mode(struct regulator *regulator); @@ -249,6 +253,7 @@ int regulator_get_hardware_vsel_register(struct regulator *regulator, unsigned *vsel_mask); int regulator_list_hardware_vsel(struct regulator *regulator, unsigned selector); +int regulator_hardware_enable(struct regulator *regulator, bool enable); /* regulator notifier block */ int regulator_register_notifier(struct regulator *regulator, @@ -320,12 +325,18 @@ devm_regulator_get_exclusive(struct device *dev, const char *id) static inline int devm_regulator_get_enable(struct device *dev, const char *id) { - return -ENODEV; + return 0; } static inline int devm_regulator_get_enable_optional(struct device *dev, const char *id) { + return 0; +} + +static inline int devm_regulator_get_enable_read_voltage(struct device *dev, + const char *id) +{ return -ENODEV; } @@ -438,8 +449,10 @@ static inline int devm_regulator_bulk_get(struct device *dev, int num_consumers, return 0; } -static inline int of_regulator_bulk_get_all(struct device *dev, struct device_node *np, - struct regulator_bulk_data **consumers) +static inline int devm_regulator_bulk_get_const( + struct device *dev, int num_consumers, + const struct regulator_bulk_data *in_consumers, + struct regulator_bulk_data **out_consumers) { return 0; } @@ -518,6 +531,22 @@ static inline int regulator_get_current_limit(struct regulator *regulator) return 0; } +static inline int regulator_get_unclaimed_power_budget(struct regulator *regulator) +{ + return INT_MAX; +} + +static inline int regulator_request_power_budget(struct regulator *regulator, + unsigned int pw_req) +{ + return -EOPNOTSUPP; +} + +static inline void regulator_free_power_budget(struct regulator *regulator, + unsigned int pw) +{ +} + static inline int regulator_set_mode(struct regulator *regulator, unsigned int mode) { @@ -564,6 +593,12 @@ static inline int regulator_list_hardware_vsel(struct regulator *regulator, return -EOPNOTSUPP; } +static inline int regulator_hardware_enable(struct regulator *regulator, + bool enable) +{ + return -EOPNOTSUPP; +} + static inline int regulator_register_notifier(struct regulator *regulator, struct notifier_block *nb) { @@ -641,6 +676,38 @@ regulator_is_equal(struct regulator *reg1, struct regulator *reg2) } #endif +#if IS_ENABLED(CONFIG_OF) && IS_ENABLED(CONFIG_REGULATOR) +struct regulator *__must_check of_regulator_get_optional(struct device *dev, + struct device_node *node, + const char *id); +struct regulator *__must_check devm_of_regulator_get_optional(struct device *dev, + struct device_node *node, + const char *id); +int __must_check of_regulator_bulk_get_all(struct device *dev, struct device_node *np, + struct regulator_bulk_data **consumers); +#else +static inline struct regulator *__must_check of_regulator_get_optional(struct device *dev, + struct device_node *node, + const char *id) +{ + return ERR_PTR(-ENODEV); +} + +static inline struct regulator *__must_check devm_of_regulator_get_optional(struct device *dev, + struct device_node *node, + const char *id) +{ + return ERR_PTR(-ENODEV); +} + +static inline int of_regulator_bulk_get_all(struct device *dev, struct device_node *np, + struct regulator_bulk_data **consumers) +{ + return 0; +} + +#endif + static inline int regulator_set_voltage_triplet(struct regulator *regulator, int min_uV, int target_uV, int max_uV) diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 22a07c0900a4..4a216fdba354 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -269,6 +269,11 @@ enum regulator_type { * config but it cannot store it for later usage. * Callback should return 0 on success or negative ERRNO * indicating failure. + * @init_cb: Optional callback called after the parsing of init_data. + * Allows the regulator to perform runtime init if necessary, + * such as synching the regulator and the parsed constraints. + * Callback should return 0 on success or negative ERRNO + * indicating failure. * @id: Numerical identifier for the regulator. * @ops: Regulator operations table. * @irq: Interrupt number for the regulator. @@ -299,6 +304,8 @@ enum regulator_type { * @vsel_range_reg: Register for range selector when using pickable ranges * and ``regulator_map_*_voltage_*_pickable`` functions. * @vsel_range_mask: Mask for register bitfield used for range selector + * @range_applied_by_vsel: A flag to indicate that changes to vsel_range_reg + * are only effective after vsel_reg is written * @vsel_reg: Register for selector when using ``regulator_map_*_voltage_*`` * @vsel_mask: Mask for register bitfield used for selector * @vsel_step: Specify the resolution of selector stepping when setting @@ -363,6 +370,8 @@ struct regulator_desc { int (*of_parse_cb)(struct device_node *, const struct regulator_desc *, struct regulator_config *); + int (*init_cb)(struct regulator_dev *, + struct regulator_config *); int id; unsigned int continuous_voltage_range:1; unsigned n_voltages; @@ -389,6 +398,7 @@ struct regulator_desc { unsigned int vsel_range_reg; unsigned int vsel_range_mask; + bool range_applied_by_vsel; unsigned int vsel_reg; unsigned int vsel_mask; unsigned int vsel_step; @@ -646,6 +656,8 @@ struct regulator_dev { int cached_err; bool use_cached_err; spinlock_t err_lock; + + int pw_requested_mW; }; /* diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h index 0cd76d264727..1fc440c5c4c7 100644 --- a/include/linux/regulator/machine.h +++ b/include/linux/regulator/machine.h @@ -113,6 +113,7 @@ struct notification_limit { * @min_uA: Smallest current consumers may set. * @max_uA: Largest current consumers may set. * @ilim_uA: Maximum input current. + * @pw_budget_mW: Power budget for the regulator in mW. * @system_load: Load that isn't captured by any consumer requests. * * @over_curr_limits: Limits for acting on over current. @@ -185,6 +186,7 @@ struct regulation_constraints { int max_uA; int ilim_uA; + int pw_budget_mW; int system_load; /* used for coupled regulators */ @@ -273,8 +275,6 @@ struct regulator_consumer_supply { * be usable. * @num_consumer_supplies: Number of consumer device supplies. * @consumer_supplies: Consumer device supply configuration. - * - * @regulator_init: Callback invoked when the regulator has been registered. * @driver_data: Data passed to regulator_init. */ struct regulator_init_data { @@ -285,8 +285,7 @@ struct regulator_init_data { int num_consumer_supplies; struct regulator_consumer_supply *consumer_supplies; - /* optional regulator machine specific init */ - int (*regulator_init)(void *driver_data); + /* optional regulator machine specific data */ void *driver_data; /* core does not touch this */ }; diff --git a/include/linux/regulator/pca9450.h b/include/linux/regulator/pca9450.h index 505c908dbb81..b427b5873de1 100644 --- a/include/linux/regulator/pca9450.h +++ b/include/linux/regulator/pca9450.h @@ -9,6 +9,8 @@ enum pca9450_chip_type { PCA9450_TYPE_PCA9450A = 0, PCA9450_TYPE_PCA9450BC, + PCA9450_TYPE_PCA9451A, + PCA9450_TYPE_PCA9452, PCA9450_TYPE_AMOUNT, }; diff --git a/include/linux/remoteproc/mtk_scp.h b/include/linux/remoteproc/mtk_scp.h index 7c2b7cc9fe6c..344ff41c22c7 100644 --- a/include/linux/remoteproc/mtk_scp.h +++ b/include/linux/remoteproc/mtk_scp.h @@ -43,6 +43,7 @@ enum scp_ipi_id { SCP_IPI_CROS_HOST_CMD, SCP_IPI_VDEC_LAT, SCP_IPI_VDEC_CORE, + SCP_IPI_IMGSYS_CMD, SCP_IPI_NS_SERVICE = 0xFF, SCP_IPI_MAX = 0x100, }; diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index a365f67131ec..d94abba1c716 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -2,6 +2,7 @@ #ifndef _RESCTRL_H #define _RESCTRL_H +#include <linux/cacheinfo.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/pid.h> @@ -58,11 +59,45 @@ struct resctrl_staged_config { bool have_new_ctrl; }; +enum resctrl_domain_type { + RESCTRL_CTRL_DOMAIN, + RESCTRL_MON_DOMAIN, +}; + /** - * struct rdt_domain - group of CPUs sharing a resctrl resource + * struct rdt_domain_hdr - common header for different domain types * @list: all instances of this resource * @id: unique id for this instance + * @type: type of this instance * @cpu_mask: which CPUs share this resource + */ +struct rdt_domain_hdr { + struct list_head list; + int id; + enum resctrl_domain_type type; + struct cpumask cpu_mask; +}; + +/** + * struct rdt_ctrl_domain - group of CPUs sharing a resctrl control resource + * @hdr: common header for different domain types + * @plr: pseudo-locked region (if any) associated with domain + * @staged_config: parsed configuration to be applied + * @mbps_val: When mba_sc is enabled, this holds the array of user + * specified control values for mba_sc in MBps, indexed + * by closid + */ +struct rdt_ctrl_domain { + struct rdt_domain_hdr hdr; + struct pseudo_lock_region *plr; + struct resctrl_staged_config staged_config[CDP_NUM_TYPES]; + u32 *mbps_val; +}; + +/** + * struct rdt_mon_domain - group of CPUs sharing a resctrl monitor resource + * @hdr: common header for different domain types + * @ci: cache info for this domain * @rmid_busy_llc: bitmap of which limbo RMIDs are above threshold * @mbm_total: saved state for MBM total bandwidth * @mbm_local: saved state for MBM local bandwidth @@ -70,16 +105,10 @@ struct resctrl_staged_config { * @cqm_limbo: worker to periodically read CQM h/w counters * @mbm_work_cpu: worker CPU for MBM h/w counters * @cqm_work_cpu: worker CPU for CQM h/w counters - * @plr: pseudo-locked region (if any) associated with domain - * @staged_config: parsed configuration to be applied - * @mbps_val: When mba_sc is enabled, this holds the array of user - * specified control values for mba_sc in MBps, indexed - * by closid */ -struct rdt_domain { - struct list_head list; - int id; - struct cpumask cpu_mask; +struct rdt_mon_domain { + struct rdt_domain_hdr hdr; + struct cacheinfo *ci; unsigned long *rmid_busy_llc; struct mbm_state *mbm_total; struct mbm_state *mbm_local; @@ -87,9 +116,6 @@ struct rdt_domain { struct delayed_work cqm_limbo; int mbm_work_cpu; int cqm_work_cpu; - struct pseudo_lock_region *plr; - struct resctrl_staged_config staged_config[CDP_NUM_TYPES]; - u32 *mbps_val; }; /** @@ -150,16 +176,24 @@ struct resctrl_membw { struct rdt_parse_data; struct resctrl_schema; +enum resctrl_scope { + RESCTRL_L2_CACHE = 2, + RESCTRL_L3_CACHE = 3, + RESCTRL_L3_NODE, +}; + /** * struct rdt_resource - attributes of a resctrl resource * @rid: The index of the resource * @alloc_capable: Is allocation available on this machine * @mon_capable: Is monitor feature available on this machine * @num_rmid: Number of RMIDs available - * @cache_level: Which cache level defines scope of this resource + * @ctrl_scope: Scope of this resource for control functions + * @mon_scope: Scope of this resource for monitor functions * @cache: Cache allocation related data * @membw: If the component has bandwidth controls, their properties. - * @domains: RCU list of all domains for this resource + * @ctrl_domains: RCU list of all control domains for this resource + * @mon_domains: RCU list of all monitor domains for this resource * @name: Name to use in "schemata" file. * @data_width: Character width of data when displaying * @default_ctrl: Specifies default cache cbm or memory B/W percent. @@ -174,17 +208,19 @@ struct rdt_resource { bool alloc_capable; bool mon_capable; int num_rmid; - int cache_level; + enum resctrl_scope ctrl_scope; + enum resctrl_scope mon_scope; struct resctrl_cache cache; struct resctrl_membw membw; - struct list_head domains; + struct list_head ctrl_domains; + struct list_head mon_domains; char *name; int data_width; u32 default_ctrl; const char *format_str; int (*parse_ctrlval)(struct rdt_parse_data *data, struct resctrl_schema *s, - struct rdt_domain *d); + struct rdt_ctrl_domain *d); struct list_head evt_list; unsigned long fflags; bool cdp_capable; @@ -212,19 +248,22 @@ struct resctrl_schema { /* The number of closid supported by this resource regardless of CDP */ u32 resctrl_arch_get_num_closid(struct rdt_resource *r); +u32 resctrl_arch_system_num_rmid_idx(void); int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid); /* * Update the ctrl_val and apply this config right now. * Must be called on one of the domain's CPUs. */ -int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_domain *d, +int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_ctrl_domain *d, u32 closid, enum resctrl_conf_type t, u32 cfg_val); -u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_domain *d, +u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_ctrl_domain *d, u32 closid, enum resctrl_conf_type type); -int resctrl_online_domain(struct rdt_resource *r, struct rdt_domain *d); -void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d); +int resctrl_online_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d); +int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d); +void resctrl_offline_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d); +void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d); void resctrl_online_cpu(unsigned int cpu); void resctrl_offline_cpu(unsigned int cpu); @@ -253,7 +292,7 @@ void resctrl_offline_cpu(unsigned int cpu); * Return: * 0 on success, or -EIO, -EINVAL etc on error. */ -int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d, +int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_mon_domain *d, u32 closid, u32 rmid, enum resctrl_event_id eventid, u64 *val, void *arch_mon_ctx); @@ -286,7 +325,7 @@ static inline void resctrl_arch_rmid_read_context_check(void) * * This can be called from any CPU. */ -void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d, +void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_mon_domain *d, u32 closid, u32 rmid, enum resctrl_event_id eventid); @@ -299,7 +338,7 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d, * * This can be called from any CPU. */ -void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_domain *d); +void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_domain *d); extern unsigned int resctrl_rmid_realloc_threshold; extern unsigned int resctrl_rmid_realloc_limit; diff --git a/include/linux/reset.h b/include/linux/reset.h index 514ddf003efc..2986ced69a02 100644 --- a/include/linux/reset.h +++ b/include/linux/reset.h @@ -25,6 +25,48 @@ struct reset_control_bulk_data { struct reset_control *rstc; }; +#define RESET_CONTROL_FLAGS_BIT_SHARED BIT(0) /* not exclusive */ +#define RESET_CONTROL_FLAGS_BIT_OPTIONAL BIT(1) +#define RESET_CONTROL_FLAGS_BIT_ACQUIRED BIT(2) /* iff exclusive, not released */ +#define RESET_CONTROL_FLAGS_BIT_DEASSERTED BIT(3) + +/** + * enum reset_control_flags - Flags that can be passed to the reset_control_get functions + * to determine the type of reset control. + * These values cannot be OR'd. + * + * @RESET_CONTROL_EXCLUSIVE: exclusive, acquired, + * @RESET_CONTROL_EXCLUSIVE_DEASSERTED: exclusive, acquired, deasserted + * @RESET_CONTROL_EXCLUSIVE_RELEASED: exclusive, released, + * @RESET_CONTROL_SHARED: shared + * @RESET_CONTROL_SHARED_DEASSERTED: shared, deasserted + * @RESET_CONTROL_OPTIONAL_EXCLUSIVE: optional, exclusive, acquired + * @RESET_CONTROL_OPTIONAL_EXCLUSIVE_DEASSERTED: optional, exclusive, acquired, deasserted + * @RESET_CONTROL_OPTIONAL_EXCLUSIVE_RELEASED: optional, exclusive, released + * @RESET_CONTROL_OPTIONAL_SHARED: optional, shared + * @RESET_CONTROL_OPTIONAL_SHARED_DEASSERTED: optional, shared, deasserted + */ +enum reset_control_flags { + RESET_CONTROL_EXCLUSIVE = RESET_CONTROL_FLAGS_BIT_ACQUIRED, + RESET_CONTROL_EXCLUSIVE_DEASSERTED = RESET_CONTROL_FLAGS_BIT_ACQUIRED | + RESET_CONTROL_FLAGS_BIT_DEASSERTED, + RESET_CONTROL_EXCLUSIVE_RELEASED = 0, + RESET_CONTROL_SHARED = RESET_CONTROL_FLAGS_BIT_SHARED, + RESET_CONTROL_SHARED_DEASSERTED = RESET_CONTROL_FLAGS_BIT_SHARED | + RESET_CONTROL_FLAGS_BIT_DEASSERTED, + RESET_CONTROL_OPTIONAL_EXCLUSIVE = RESET_CONTROL_FLAGS_BIT_OPTIONAL | + RESET_CONTROL_FLAGS_BIT_ACQUIRED, + RESET_CONTROL_OPTIONAL_EXCLUSIVE_DEASSERTED = RESET_CONTROL_FLAGS_BIT_OPTIONAL | + RESET_CONTROL_FLAGS_BIT_ACQUIRED | + RESET_CONTROL_FLAGS_BIT_DEASSERTED, + RESET_CONTROL_OPTIONAL_EXCLUSIVE_RELEASED = RESET_CONTROL_FLAGS_BIT_OPTIONAL, + RESET_CONTROL_OPTIONAL_SHARED = RESET_CONTROL_FLAGS_BIT_OPTIONAL | + RESET_CONTROL_FLAGS_BIT_SHARED, + RESET_CONTROL_OPTIONAL_SHARED_DEASSERTED = RESET_CONTROL_FLAGS_BIT_OPTIONAL | + RESET_CONTROL_FLAGS_BIT_SHARED | + RESET_CONTROL_FLAGS_BIT_DEASSERTED, +}; + #ifdef CONFIG_RESET_CONTROLLER int reset_control_reset(struct reset_control *rstc); @@ -42,30 +84,25 @@ int reset_control_bulk_acquire(int num_rstcs, struct reset_control_bulk_data *rs void reset_control_bulk_release(int num_rstcs, struct reset_control_bulk_data *rstcs); struct reset_control *__of_reset_control_get(struct device_node *node, - const char *id, int index, bool shared, - bool optional, bool acquired); + const char *id, int index, enum reset_control_flags flags); struct reset_control *__reset_control_get(struct device *dev, const char *id, - int index, bool shared, - bool optional, bool acquired); + int index, enum reset_control_flags flags); void reset_control_put(struct reset_control *rstc); int __reset_control_bulk_get(struct device *dev, int num_rstcs, struct reset_control_bulk_data *rstcs, - bool shared, bool optional, bool acquired); + enum reset_control_flags flags); void reset_control_bulk_put(int num_rstcs, struct reset_control_bulk_data *rstcs); int __device_reset(struct device *dev, bool optional); struct reset_control *__devm_reset_control_get(struct device *dev, - const char *id, int index, bool shared, - bool optional, bool acquired); + const char *id, int index, enum reset_control_flags flags); int __devm_reset_control_bulk_get(struct device *dev, int num_rstcs, struct reset_control_bulk_data *rstcs, - bool shared, bool optional, bool acquired); + enum reset_control_flags flags); struct reset_control *devm_reset_control_array_get(struct device *dev, - bool shared, bool optional); -struct reset_control *of_reset_control_array_get(struct device_node *np, - bool shared, bool optional, - bool acquired); + enum reset_control_flags flags); +struct reset_control *of_reset_control_array_get(struct device_node *np, enum reset_control_flags); int reset_control_get_count(struct device *dev); @@ -116,17 +153,19 @@ static inline int __device_reset(struct device *dev, bool optional) static inline struct reset_control *__of_reset_control_get( struct device_node *node, - const char *id, int index, bool shared, - bool optional, bool acquired) + const char *id, int index, enum reset_control_flags flags) { + bool optional = flags & RESET_CONTROL_FLAGS_BIT_OPTIONAL; + return optional ? NULL : ERR_PTR(-ENOTSUPP); } static inline struct reset_control *__reset_control_get( struct device *dev, const char *id, - int index, bool shared, bool optional, - bool acquired) + int index, enum reset_control_flags flags) { + bool optional = flags & RESET_CONTROL_FLAGS_BIT_OPTIONAL; + return optional ? NULL : ERR_PTR(-ENOTSUPP); } @@ -162,8 +201,10 @@ reset_control_bulk_release(int num_rstcs, struct reset_control_bulk_data *rstcs) static inline int __reset_control_bulk_get(struct device *dev, int num_rstcs, struct reset_control_bulk_data *rstcs, - bool shared, bool optional, bool acquired) + enum reset_control_flags flags) { + bool optional = flags & RESET_CONTROL_FLAGS_BIT_OPTIONAL; + return optional ? 0 : -EOPNOTSUPP; } @@ -174,30 +215,36 @@ reset_control_bulk_put(int num_rstcs, struct reset_control_bulk_data *rstcs) static inline struct reset_control *__devm_reset_control_get( struct device *dev, const char *id, - int index, bool shared, bool optional, - bool acquired) + int index, enum reset_control_flags flags) { + bool optional = flags & RESET_CONTROL_FLAGS_BIT_OPTIONAL; + return optional ? NULL : ERR_PTR(-ENOTSUPP); } static inline int __devm_reset_control_bulk_get(struct device *dev, int num_rstcs, struct reset_control_bulk_data *rstcs, - bool shared, bool optional, bool acquired) + enum reset_control_flags flags) { + bool optional = flags & RESET_CONTROL_FLAGS_BIT_OPTIONAL; + return optional ? 0 : -EOPNOTSUPP; } static inline struct reset_control * -devm_reset_control_array_get(struct device *dev, bool shared, bool optional) +devm_reset_control_array_get(struct device *dev, enum reset_control_flags flags) { + bool optional = flags & RESET_CONTROL_FLAGS_BIT_OPTIONAL; + return optional ? NULL : ERR_PTR(-ENOTSUPP); } static inline struct reset_control * -of_reset_control_array_get(struct device_node *np, bool shared, bool optional, - bool acquired) +of_reset_control_array_get(struct device_node *np, enum reset_control_flags flags) { + bool optional = flags & RESET_CONTROL_FLAGS_BIT_OPTIONAL; + return optional ? NULL : ERR_PTR(-ENOTSUPP); } @@ -236,7 +283,7 @@ static inline int device_reset_optional(struct device *dev) static inline struct reset_control * __must_check reset_control_get_exclusive(struct device *dev, const char *id) { - return __reset_control_get(dev, id, 0, false, false, true); + return __reset_control_get(dev, id, 0, RESET_CONTROL_EXCLUSIVE); } /** @@ -253,7 +300,7 @@ static inline int __must_check reset_control_bulk_get_exclusive(struct device *dev, int num_rstcs, struct reset_control_bulk_data *rstcs) { - return __reset_control_bulk_get(dev, num_rstcs, rstcs, false, false, true); + return __reset_control_bulk_get(dev, num_rstcs, rstcs, RESET_CONTROL_EXCLUSIVE); } /** @@ -274,7 +321,7 @@ static inline struct reset_control * __must_check reset_control_get_exclusive_released(struct device *dev, const char *id) { - return __reset_control_get(dev, id, 0, false, false, false); + return __reset_control_get(dev, id, 0, RESET_CONTROL_EXCLUSIVE_RELEASED); } /** @@ -295,7 +342,7 @@ static inline int __must_check reset_control_bulk_get_exclusive_released(struct device *dev, int num_rstcs, struct reset_control_bulk_data *rstcs) { - return __reset_control_bulk_get(dev, num_rstcs, rstcs, false, false, false); + return __reset_control_bulk_get(dev, num_rstcs, rstcs, RESET_CONTROL_EXCLUSIVE_RELEASED); } /** @@ -316,7 +363,8 @@ static inline int __must_check reset_control_bulk_get_optional_exclusive_released(struct device *dev, int num_rstcs, struct reset_control_bulk_data *rstcs) { - return __reset_control_bulk_get(dev, num_rstcs, rstcs, false, true, false); + return __reset_control_bulk_get(dev, num_rstcs, rstcs, + RESET_CONTROL_OPTIONAL_EXCLUSIVE_RELEASED); } /** @@ -344,7 +392,7 @@ reset_control_bulk_get_optional_exclusive_released(struct device *dev, int num_r static inline struct reset_control *reset_control_get_shared( struct device *dev, const char *id) { - return __reset_control_get(dev, id, 0, true, false, false); + return __reset_control_get(dev, id, 0, RESET_CONTROL_SHARED); } /** @@ -361,7 +409,7 @@ static inline int __must_check reset_control_bulk_get_shared(struct device *dev, int num_rstcs, struct reset_control_bulk_data *rstcs) { - return __reset_control_bulk_get(dev, num_rstcs, rstcs, true, false, false); + return __reset_control_bulk_get(dev, num_rstcs, rstcs, RESET_CONTROL_SHARED); } /** @@ -378,7 +426,7 @@ reset_control_bulk_get_shared(struct device *dev, int num_rstcs, static inline struct reset_control *reset_control_get_optional_exclusive( struct device *dev, const char *id) { - return __reset_control_get(dev, id, 0, false, true, true); + return __reset_control_get(dev, id, 0, RESET_CONTROL_OPTIONAL_EXCLUSIVE); } /** @@ -398,7 +446,7 @@ static inline int __must_check reset_control_bulk_get_optional_exclusive(struct device *dev, int num_rstcs, struct reset_control_bulk_data *rstcs) { - return __reset_control_bulk_get(dev, num_rstcs, rstcs, false, true, true); + return __reset_control_bulk_get(dev, num_rstcs, rstcs, RESET_CONTROL_OPTIONAL_EXCLUSIVE); } /** @@ -415,7 +463,7 @@ reset_control_bulk_get_optional_exclusive(struct device *dev, int num_rstcs, static inline struct reset_control *reset_control_get_optional_shared( struct device *dev, const char *id) { - return __reset_control_get(dev, id, 0, true, true, false); + return __reset_control_get(dev, id, 0, RESET_CONTROL_OPTIONAL_SHARED); } /** @@ -435,7 +483,7 @@ static inline int __must_check reset_control_bulk_get_optional_shared(struct device *dev, int num_rstcs, struct reset_control_bulk_data *rstcs) { - return __reset_control_bulk_get(dev, num_rstcs, rstcs, true, true, false); + return __reset_control_bulk_get(dev, num_rstcs, rstcs, RESET_CONTROL_OPTIONAL_SHARED); } /** @@ -451,7 +499,7 @@ reset_control_bulk_get_optional_shared(struct device *dev, int num_rstcs, static inline struct reset_control *of_reset_control_get_exclusive( struct device_node *node, const char *id) { - return __of_reset_control_get(node, id, 0, false, false, true); + return __of_reset_control_get(node, id, 0, RESET_CONTROL_EXCLUSIVE); } /** @@ -471,7 +519,7 @@ static inline struct reset_control *of_reset_control_get_exclusive( static inline struct reset_control *of_reset_control_get_optional_exclusive( struct device_node *node, const char *id) { - return __of_reset_control_get(node, id, 0, false, true, true); + return __of_reset_control_get(node, id, 0, RESET_CONTROL_OPTIONAL_EXCLUSIVE); } /** @@ -496,7 +544,7 @@ static inline struct reset_control *of_reset_control_get_optional_exclusive( static inline struct reset_control *of_reset_control_get_shared( struct device_node *node, const char *id) { - return __of_reset_control_get(node, id, 0, true, false, false); + return __of_reset_control_get(node, id, 0, RESET_CONTROL_SHARED); } /** @@ -513,7 +561,7 @@ static inline struct reset_control *of_reset_control_get_shared( static inline struct reset_control *of_reset_control_get_exclusive_by_index( struct device_node *node, int index) { - return __of_reset_control_get(node, NULL, index, false, false, true); + return __of_reset_control_get(node, NULL, index, RESET_CONTROL_EXCLUSIVE); } /** @@ -541,7 +589,7 @@ static inline struct reset_control *of_reset_control_get_exclusive_by_index( static inline struct reset_control *of_reset_control_get_shared_by_index( struct device_node *node, int index) { - return __of_reset_control_get(node, NULL, index, true, false, false); + return __of_reset_control_get(node, NULL, index, RESET_CONTROL_SHARED); } /** @@ -560,7 +608,26 @@ static inline struct reset_control * __must_check devm_reset_control_get_exclusive(struct device *dev, const char *id) { - return __devm_reset_control_get(dev, id, 0, false, false, true); + return __devm_reset_control_get(dev, id, 0, RESET_CONTROL_EXCLUSIVE); +} + +/** + * devm_reset_control_get_exclusive_deasserted - resource managed + * reset_control_get_exclusive() + + * reset_control_deassert() + * @dev: device to be reset by the controller + * @id: reset line name + * + * Managed reset_control_get_exclusive() + reset_control_deassert(). For reset + * controllers returned from this function, reset_control_assert() + + * reset_control_put() is called automatically on driver detach. + * + * See reset_control_get_exclusive() for more information. + */ +static inline struct reset_control * __must_check +devm_reset_control_get_exclusive_deasserted(struct device *dev, const char *id) +{ + return __devm_reset_control_get(dev, id, 0, RESET_CONTROL_EXCLUSIVE_DEASSERTED); } /** @@ -580,7 +647,8 @@ static inline int __must_check devm_reset_control_bulk_get_exclusive(struct device *dev, int num_rstcs, struct reset_control_bulk_data *rstcs) { - return __devm_reset_control_bulk_get(dev, num_rstcs, rstcs, false, false, true); + return __devm_reset_control_bulk_get(dev, num_rstcs, rstcs, + RESET_CONTROL_EXCLUSIVE); } /** @@ -599,7 +667,7 @@ static inline struct reset_control * __must_check devm_reset_control_get_exclusive_released(struct device *dev, const char *id) { - return __devm_reset_control_get(dev, id, 0, false, false, false); + return __devm_reset_control_get(dev, id, 0, RESET_CONTROL_EXCLUSIVE_RELEASED); } /** @@ -619,7 +687,8 @@ static inline int __must_check devm_reset_control_bulk_get_exclusive_released(struct device *dev, int num_rstcs, struct reset_control_bulk_data *rstcs) { - return __devm_reset_control_bulk_get(dev, num_rstcs, rstcs, false, false, false); + return __devm_reset_control_bulk_get(dev, num_rstcs, rstcs, + RESET_CONTROL_EXCLUSIVE_RELEASED); } /** @@ -638,7 +707,7 @@ static inline struct reset_control * __must_check devm_reset_control_get_optional_exclusive_released(struct device *dev, const char *id) { - return __devm_reset_control_get(dev, id, 0, false, true, false); + return __devm_reset_control_get(dev, id, 0, RESET_CONTROL_OPTIONAL_EXCLUSIVE_RELEASED); } /** @@ -658,7 +727,8 @@ static inline int __must_check devm_reset_control_bulk_get_optional_exclusive_released(struct device *dev, int num_rstcs, struct reset_control_bulk_data *rstcs) { - return __devm_reset_control_bulk_get(dev, num_rstcs, rstcs, false, true, false); + return __devm_reset_control_bulk_get(dev, num_rstcs, rstcs, + RESET_CONTROL_OPTIONAL_EXCLUSIVE_RELEASED); } /** @@ -673,7 +743,26 @@ devm_reset_control_bulk_get_optional_exclusive_released(struct device *dev, int static inline struct reset_control *devm_reset_control_get_shared( struct device *dev, const char *id) { - return __devm_reset_control_get(dev, id, 0, true, false, false); + return __devm_reset_control_get(dev, id, 0, RESET_CONTROL_SHARED); +} + +/** + * devm_reset_control_get_shared_deasserted - resource managed + * reset_control_get_shared() + + * reset_control_deassert() + * @dev: device to be reset by the controller + * @id: reset line name + * + * Managed reset_control_get_shared() + reset_control_deassert(). For reset + * controllers returned from this function, reset_control_assert() + + * reset_control_put() is called automatically on driver detach. + * + * See devm_reset_control_get_shared() for more information. + */ +static inline struct reset_control * __must_check +devm_reset_control_get_shared_deasserted(struct device *dev, const char *id) +{ + return __devm_reset_control_get(dev, id, 0, RESET_CONTROL_SHARED_DEASSERTED); } /** @@ -693,7 +782,29 @@ static inline int __must_check devm_reset_control_bulk_get_shared(struct device *dev, int num_rstcs, struct reset_control_bulk_data *rstcs) { - return __devm_reset_control_bulk_get(dev, num_rstcs, rstcs, true, false, false); + return __devm_reset_control_bulk_get(dev, num_rstcs, rstcs, RESET_CONTROL_SHARED); +} + +/** + * devm_reset_control_bulk_get_shared_deasserted - resource managed + * reset_control_bulk_get_shared() + + * reset_control_bulk_deassert() + * @dev: device to be reset by the controller + * @num_rstcs: number of entries in rstcs array + * @rstcs: array of struct reset_control_bulk_data with reset line names set + * + * Managed reset_control_bulk_get_shared() + reset_control_bulk_deassert(). For + * reset controllers returned from this function, reset_control_bulk_assert() + + * reset_control_bulk_put() are called automatically on driver detach. + * + * See devm_reset_control_bulk_get_shared() for more information. + */ +static inline int __must_check +devm_reset_control_bulk_get_shared_deasserted(struct device *dev, int num_rstcs, + struct reset_control_bulk_data *rstcs) +{ + return __devm_reset_control_bulk_get(dev, num_rstcs, rstcs, + RESET_CONTROL_SHARED_DEASSERTED); } /** @@ -711,7 +822,26 @@ devm_reset_control_bulk_get_shared(struct device *dev, int num_rstcs, static inline struct reset_control *devm_reset_control_get_optional_exclusive( struct device *dev, const char *id) { - return __devm_reset_control_get(dev, id, 0, false, true, true); + return __devm_reset_control_get(dev, id, 0, RESET_CONTROL_OPTIONAL_EXCLUSIVE); +} + +/** + * devm_reset_control_get_optional_exclusive_deasserted - resource managed + * reset_control_get_optional_exclusive() + + * reset_control_deassert() + * @dev: device to be reset by the controller + * @id: reset line name + * + * Managed reset_control_get_optional_exclusive() + reset_control_deassert(). + * For reset controllers returned from this function, reset_control_assert() + + * reset_control_put() is called automatically on driver detach. + * + * See devm_reset_control_get_optional_exclusive() for more information. + */ +static inline struct reset_control * +devm_reset_control_get_optional_exclusive_deasserted(struct device *dev, const char *id) +{ + return __devm_reset_control_get(dev, id, 0, RESET_CONTROL_OPTIONAL_EXCLUSIVE_DEASSERTED); } /** @@ -731,7 +861,8 @@ static inline int __must_check devm_reset_control_bulk_get_optional_exclusive(struct device *dev, int num_rstcs, struct reset_control_bulk_data *rstcs) { - return __devm_reset_control_bulk_get(dev, num_rstcs, rstcs, false, true, true); + return __devm_reset_control_bulk_get(dev, num_rstcs, rstcs, + RESET_CONTROL_OPTIONAL_EXCLUSIVE); } /** @@ -749,7 +880,26 @@ devm_reset_control_bulk_get_optional_exclusive(struct device *dev, int num_rstcs static inline struct reset_control *devm_reset_control_get_optional_shared( struct device *dev, const char *id) { - return __devm_reset_control_get(dev, id, 0, true, true, false); + return __devm_reset_control_get(dev, id, 0, RESET_CONTROL_OPTIONAL_SHARED); +} + +/** + * devm_reset_control_get_optional_shared_deasserted - resource managed + * reset_control_get_optional_shared() + + * reset_control_deassert() + * @dev: device to be reset by the controller + * @id: reset line name + * + * Managed reset_control_get_optional_shared() + reset_control_deassert(). For + * reset controllers returned from this function, reset_control_assert() + + * reset_control_put() is called automatically on driver detach. + * + * See devm_reset_control_get_optional_shared() for more information. + */ +static inline struct reset_control * +devm_reset_control_get_optional_shared_deasserted(struct device *dev, const char *id) +{ + return __devm_reset_control_get(dev, id, 0, RESET_CONTROL_OPTIONAL_SHARED_DEASSERTED); } /** @@ -769,7 +919,7 @@ static inline int __must_check devm_reset_control_bulk_get_optional_shared(struct device *dev, int num_rstcs, struct reset_control_bulk_data *rstcs) { - return __devm_reset_control_bulk_get(dev, num_rstcs, rstcs, true, true, false); + return __devm_reset_control_bulk_get(dev, num_rstcs, rstcs, RESET_CONTROL_OPTIONAL_SHARED); } /** @@ -787,7 +937,7 @@ devm_reset_control_bulk_get_optional_shared(struct device *dev, int num_rstcs, static inline struct reset_control * devm_reset_control_get_exclusive_by_index(struct device *dev, int index) { - return __devm_reset_control_get(dev, NULL, index, false, false, true); + return __devm_reset_control_get(dev, NULL, index, RESET_CONTROL_EXCLUSIVE); } /** @@ -803,7 +953,7 @@ devm_reset_control_get_exclusive_by_index(struct device *dev, int index) static inline struct reset_control * devm_reset_control_get_shared_by_index(struct device *dev, int index) { - return __devm_reset_control_get(dev, NULL, index, true, false, false); + return __devm_reset_control_get(dev, NULL, index, RESET_CONTROL_SHARED); } /* @@ -851,54 +1001,54 @@ static inline struct reset_control *devm_reset_control_get_by_index( static inline struct reset_control * devm_reset_control_array_get_exclusive(struct device *dev) { - return devm_reset_control_array_get(dev, false, false); + return devm_reset_control_array_get(dev, RESET_CONTROL_EXCLUSIVE); } static inline struct reset_control * devm_reset_control_array_get_shared(struct device *dev) { - return devm_reset_control_array_get(dev, true, false); + return devm_reset_control_array_get(dev, RESET_CONTROL_SHARED); } static inline struct reset_control * devm_reset_control_array_get_optional_exclusive(struct device *dev) { - return devm_reset_control_array_get(dev, false, true); + return devm_reset_control_array_get(dev, RESET_CONTROL_OPTIONAL_EXCLUSIVE); } static inline struct reset_control * devm_reset_control_array_get_optional_shared(struct device *dev) { - return devm_reset_control_array_get(dev, true, true); + return devm_reset_control_array_get(dev, RESET_CONTROL_OPTIONAL_SHARED); } static inline struct reset_control * of_reset_control_array_get_exclusive(struct device_node *node) { - return of_reset_control_array_get(node, false, false, true); + return of_reset_control_array_get(node, RESET_CONTROL_EXCLUSIVE); } static inline struct reset_control * of_reset_control_array_get_exclusive_released(struct device_node *node) { - return of_reset_control_array_get(node, false, false, false); + return of_reset_control_array_get(node, RESET_CONTROL_EXCLUSIVE_RELEASED); } static inline struct reset_control * of_reset_control_array_get_shared(struct device_node *node) { - return of_reset_control_array_get(node, true, false, true); + return of_reset_control_array_get(node, RESET_CONTROL_SHARED); } static inline struct reset_control * of_reset_control_array_get_optional_exclusive(struct device_node *node) { - return of_reset_control_array_get(node, false, true, true); + return of_reset_control_array_get(node, RESET_CONTROL_OPTIONAL_EXCLUSIVE); } static inline struct reset_control * of_reset_control_array_get_optional_shared(struct device_node *node) { - return of_reset_control_array_get(node, true, true, true); + return of_reset_control_array_get(node, RESET_CONTROL_OPTIONAL_SHARED); } #endif diff --git a/include/linux/rfkill.h b/include/linux/rfkill.h index 373003ace639..6816e4c5f3f0 100644 --- a/include/linux/rfkill.h +++ b/include/linux/rfkill.h @@ -147,7 +147,8 @@ void rfkill_destroy(struct rfkill *rfkill); * Prefer to use rfkill_set_hw_state if you don't need any special reason. */ bool rfkill_set_hw_state_reason(struct rfkill *rfkill, - bool blocked, unsigned long reason); + bool blocked, + enum rfkill_hard_block_reasons reason); /** * rfkill_set_hw_state - Set the internal rfkill hardware block state * @rfkill: pointer to the rfkill class to modify. @@ -240,7 +241,7 @@ bool rfkill_soft_blocked(struct rfkill *rfkill); * rfkill_find_type - Helper for finding rfkill type by name * @name: the name of the type * - * Returns enum rfkill_type that corresponds to the name. + * Returns: enum rfkill_type that corresponds to the name. */ enum rfkill_type rfkill_find_type(const char *name); @@ -280,7 +281,7 @@ static inline void rfkill_destroy(struct rfkill *rfkill) static inline bool rfkill_set_hw_state_reason(struct rfkill *rfkill, bool blocked, - unsigned long reason) + enum rfkill_hard_block_reasons reason) { return blocked; } diff --git a/include/linux/rhashtable-types.h b/include/linux/rhashtable-types.h index b6f3797277ff..015c8298bebc 100644 --- a/include/linux/rhashtable-types.h +++ b/include/linux/rhashtable-types.h @@ -9,6 +9,7 @@ #ifndef _LINUX_RHASHTABLE_TYPES_H #define _LINUX_RHASHTABLE_TYPES_H +#include <linux/alloc_tag.h> #include <linux/atomic.h> #include <linux/compiler.h> #include <linux/mutex.h> @@ -88,6 +89,9 @@ struct rhashtable { struct mutex mutex; spinlock_t lock; atomic_t nelems; +#ifdef CONFIG_MEM_ALLOC_PROFILING + struct alloc_tag *alloc_tag; +#endif }; /** @@ -127,9 +131,12 @@ struct rhashtable_iter { bool end_of_table; }; -int rhashtable_init(struct rhashtable *ht, +int rhashtable_init_noprof(struct rhashtable *ht, const struct rhashtable_params *params); -int rhltable_init(struct rhltable *hlt, +#define rhashtable_init(...) alloc_hooks(rhashtable_init_noprof(__VA_ARGS__)) + +int rhltable_init_noprof(struct rhltable *hlt, const struct rhashtable_params *params); +#define rhltable_init(...) alloc_hooks(rhltable_init_noprof(__VA_ARGS__)) #endif /* _LINUX_RHASHTABLE_TYPES_H */ diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 5b5357c0bd8c..8463a128e2f4 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -633,7 +633,7 @@ restart: * @params: hash table parameters * * Computes the hash value for the key and traverses the bucket chain looking - * for a entry with an identical key. The first matching entry is returned. + * for an entry with an identical key. The first matching entry is returned. * * This must only be called under the RCU read lock. * @@ -655,7 +655,7 @@ static inline void *rhashtable_lookup( * @params: hash table parameters * * Computes the hash value for the key and traverses the bucket chain looking - * for a entry with an identical key. The first matching entry is returned. + * for an entry with an identical key. The first matching entry is returned. * * Only use this function when you have other mechanisms guaranteeing * that the object won't go away after the RCU read lock is released. @@ -682,7 +682,7 @@ static inline void *rhashtable_lookup_fast( * @params: hash table parameters * * Computes the hash value for the key and traverses the bucket chain looking - * for a entry with an identical key. All matching entries are returned + * for an entry with an identical key. All matching entries are returned * in a list. * * This must only be called under the RCU read lock. @@ -699,7 +699,7 @@ static inline struct rhlist_head *rhltable_lookup( } /* Internal function, please use rhashtable_insert_fast() instead. This - * function returns the existing element already in hashes in there is a clash, + * function returns the existing element already in hashes if there is a clash, * otherwise it returns an error via ERR_PTR(). */ static inline void *__rhashtable_insert_fast( @@ -1130,7 +1130,7 @@ static inline int rhashtable_remove_fast( * * Since the hash chain is single linked, the removal operation needs to * walk the bucket chain upon removal. The removal operation is thus - * considerable slow if the hash table is not correctly sized. + * considerably slower if the hash table is not correctly sized. * * Will automatically shrink the table if permitted when residency drops * below 30% diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index dc5ae4e96aee..17fbb7855295 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -6,6 +6,8 @@ #include <linux/seq_file.h> #include <linux/poll.h> +#include <uapi/linux/trace_mmap.h> + struct trace_buffer; struct ring_buffer_iter; @@ -87,6 +89,14 @@ void ring_buffer_discard_commit(struct trace_buffer *buffer, struct trace_buffer * __ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *key); +struct trace_buffer *__ring_buffer_alloc_range(unsigned long size, unsigned flags, + int order, unsigned long start, + unsigned long range_size, + struct lock_class_key *key); + +bool ring_buffer_last_boot_delta(struct trace_buffer *buffer, long *text, + long *data); + /* * Because the ring buffer is generic, if other users of the ring buffer get * traced by ftrace, it can produce lockdep warnings. We need to keep each @@ -98,6 +108,18 @@ __ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *k __ring_buffer_alloc((size), (flags), &__key); \ }) +/* + * Because the ring buffer is generic, if other users of the ring buffer get + * traced by ftrace, it can produce lockdep warnings. We need to keep each + * ring buffer's lock class separate. + */ +#define ring_buffer_alloc_range(size, flags, order, start, range_size) \ +({ \ + static struct lock_class_key __key; \ + __ring_buffer_alloc_range((size), (flags), (order), (start), \ + (range_size), &__key); \ +}) + typedef bool (*ring_buffer_cond_fn)(void *data); int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full, ring_buffer_cond_fn cond, void *data); @@ -191,7 +213,6 @@ void ring_buffer_set_clock(struct trace_buffer *buffer, void ring_buffer_set_time_stamp_abs(struct trace_buffer *buffer, bool abs); bool ring_buffer_time_stamp_abs(struct trace_buffer *buffer); -size_t ring_buffer_nr_pages(struct trace_buffer *buffer, int cpu); size_t ring_buffer_nr_dirty_pages(struct trace_buffer *buffer, int cpu); struct buffer_data_read_page; @@ -223,4 +244,8 @@ int trace_rb_cpu_prepare(unsigned int cpu, struct hlist_node *node); #define trace_rb_cpu_prepare NULL #endif +int ring_buffer_map(struct trace_buffer *buffer, int cpu, + struct vm_area_struct *vma); +int ring_buffer_unmap(struct trace_buffer *buffer, int cpu); +int ring_buffer_map_get_reader(struct trace_buffer *buffer, int cpu); #endif /* _LINUX_RING_BUFFER_H */ diff --git a/include/linux/rio.h b/include/linux/rio.h index 2cd637268b4f..3c29f40f3c94 100644 --- a/include/linux/rio.h +++ b/include/linux/rio.h @@ -465,7 +465,7 @@ struct rio_driver { struct device_driver driver; }; -#define to_rio_driver(drv) container_of(drv,struct rio_driver, driver) +#define to_rio_driver(drv) container_of_const(drv,struct rio_driver, driver) union rio_pw_msg { struct { diff --git a/include/linux/rmap.h b/include/linux/rmap.h index b7944a833668..683a04088f3f 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -171,7 +171,7 @@ static inline void anon_vma_merge(struct vm_area_struct *vma, unlink_anon_vmas(next); } -struct anon_vma *folio_get_anon_vma(struct folio *folio); +struct anon_vma *folio_get_anon_vma(const struct folio *folio); /* RMAP flags, currently only relevant for some anon rmap operations. */ typedef int __bitwise rmap_t; @@ -194,12 +194,15 @@ enum rmap_level { RMAP_LEVEL_PMD, }; -static inline void __folio_rmap_sanity_checks(struct folio *folio, - struct page *page, int nr_pages, enum rmap_level level) +static inline void __folio_rmap_sanity_checks(const struct folio *folio, + const struct page *page, int nr_pages, enum rmap_level level) { /* hugetlb folios are handled separately. */ VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio); + /* When (un)mapping zeropages, we should never touch ref+mapcount. */ + VM_WARN_ON_FOLIO(is_zero_folio(folio), folio); + /* * TODO: we get driver-allocated folios that have nothing to do with * the rmap using vm_insert_page(); therefore, we cannot assume that @@ -241,7 +244,7 @@ void folio_add_anon_rmap_ptes(struct folio *, struct page *, int nr_pages, void folio_add_anon_rmap_pmd(struct folio *, struct page *, struct vm_area_struct *, unsigned long address, rmap_t flags); void folio_add_new_anon_rmap(struct folio *, struct vm_area_struct *, - unsigned long address); + unsigned long address, rmap_t flags); void folio_add_file_rmap_ptes(struct folio *, struct page *, int nr_pages, struct vm_area_struct *); #define folio_add_file_rmap_pte(folio, page, vma) \ @@ -273,6 +276,7 @@ static inline int hugetlb_try_dup_anon_rmap(struct folio *folio, ClearPageAnonExclusive(&folio->page); } atomic_inc(&folio->_entire_mapcount); + atomic_inc(&folio->_large_mapcount); return 0; } @@ -284,7 +288,7 @@ static inline int hugetlb_try_share_anon_rmap(struct folio *folio) VM_WARN_ON_FOLIO(!PageAnonExclusive(&folio->page), folio); /* Paired with the memory barrier in try_grab_folio(). */ - if (IS_ENABLED(CONFIG_HAVE_FAST_GUP)) + if (IS_ENABLED(CONFIG_HAVE_GUP_FAST)) smp_mb(); if (unlikely(folio_maybe_dma_pinned(folio))) @@ -295,7 +299,7 @@ static inline int hugetlb_try_share_anon_rmap(struct folio *folio) * This is conceptually a smp_wmb() paired with the smp_rmb() in * gup_must_unshare(). */ - if (IS_ENABLED(CONFIG_HAVE_FAST_GUP)) + if (IS_ENABLED(CONFIG_HAVE_GUP_FAST)) smp_mb__after_atomic(); return 0; } @@ -306,6 +310,7 @@ static inline void hugetlb_add_file_rmap(struct folio *folio) VM_WARN_ON_FOLIO(folio_test_anon(folio), folio); atomic_inc(&folio->_entire_mapcount); + atomic_inc(&folio->_large_mapcount); } static inline void hugetlb_remove_rmap(struct folio *folio) @@ -313,21 +318,31 @@ static inline void hugetlb_remove_rmap(struct folio *folio) VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio); atomic_dec(&folio->_entire_mapcount); + atomic_dec(&folio->_large_mapcount); } static __always_inline void __folio_dup_file_rmap(struct folio *folio, struct page *page, int nr_pages, enum rmap_level level) { + const int orig_nr_pages = nr_pages; + __folio_rmap_sanity_checks(folio, page, nr_pages, level); switch (level) { case RMAP_LEVEL_PTE: + if (!folio_test_large(folio)) { + atomic_inc(&folio->_mapcount); + break; + } + do { atomic_inc(&page->_mapcount); } while (page++, --nr_pages > 0); + atomic_add(orig_nr_pages, &folio->_large_mapcount); break; case RMAP_LEVEL_PMD: atomic_inc(&folio->_entire_mapcount); + atomic_inc(&folio->_large_mapcount); break; } } @@ -347,8 +362,12 @@ static inline void folio_dup_file_rmap_ptes(struct folio *folio, { __folio_dup_file_rmap(folio, page, nr_pages, RMAP_LEVEL_PTE); } -#define folio_dup_file_rmap_pte(folio, page) \ - folio_dup_file_rmap_ptes(folio, page, 1) + +static __always_inline void folio_dup_file_rmap_pte(struct folio *folio, + struct page *page) +{ + __folio_dup_file_rmap(folio, page, 1, RMAP_LEVEL_PTE); +} /** * folio_dup_file_rmap_pmd - duplicate a PMD mapping of a page range of a folio @@ -373,6 +392,7 @@ static __always_inline int __folio_try_dup_anon_rmap(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *src_vma, enum rmap_level level) { + const int orig_nr_pages = nr_pages; bool maybe_pinned; int i; @@ -401,11 +421,20 @@ static __always_inline int __folio_try_dup_anon_rmap(struct folio *folio, if (PageAnonExclusive(page + i)) return -EBUSY; } + + if (!folio_test_large(folio)) { + if (PageAnonExclusive(page)) + ClearPageAnonExclusive(page); + atomic_inc(&folio->_mapcount); + break; + } + do { if (PageAnonExclusive(page)) ClearPageAnonExclusive(page); atomic_inc(&page->_mapcount); } while (page++, --nr_pages > 0); + atomic_add(orig_nr_pages, &folio->_large_mapcount); break; case RMAP_LEVEL_PMD: if (PageAnonExclusive(page)) { @@ -414,6 +443,7 @@ static __always_inline int __folio_try_dup_anon_rmap(struct folio *folio, ClearPageAnonExclusive(page); } atomic_inc(&folio->_entire_mapcount); + atomic_inc(&folio->_large_mapcount); break; } return 0; @@ -448,8 +478,13 @@ static inline int folio_try_dup_anon_rmap_ptes(struct folio *folio, return __folio_try_dup_anon_rmap(folio, page, nr_pages, src_vma, RMAP_LEVEL_PTE); } -#define folio_try_dup_anon_rmap_pte(folio, page, vma) \ - folio_try_dup_anon_rmap_ptes(folio, page, 1, vma) + +static __always_inline int folio_try_dup_anon_rmap_pte(struct folio *folio, + struct page *page, struct vm_area_struct *src_vma) +{ + return __folio_try_dup_anon_rmap(folio, page, 1, src_vma, + RMAP_LEVEL_PTE); +} /** * folio_try_dup_anon_rmap_pmd - try duplicating a PMD mapping of a page range @@ -541,7 +576,7 @@ static __always_inline int __folio_try_share_anon_rmap(struct folio *folio, */ /* Paired with the memory barrier in try_grab_folio(). */ - if (IS_ENABLED(CONFIG_HAVE_FAST_GUP)) + if (IS_ENABLED(CONFIG_HAVE_GUP_FAST)) smp_mb(); if (unlikely(folio_maybe_dma_pinned(folio))) @@ -552,7 +587,7 @@ static __always_inline int __folio_try_share_anon_rmap(struct folio *folio, * This is conceptually a smp_wmb() paired with the smp_rmb() in * gup_must_unshare(). */ - if (IS_ENABLED(CONFIG_HAVE_FAST_GUP)) + if (IS_ENABLED(CONFIG_HAVE_GUP_FAST)) smp_mb__after_atomic(); return 0; } @@ -649,16 +684,6 @@ struct page_vma_mapped_walk { unsigned int flags; }; -#define DEFINE_PAGE_VMA_WALK(name, _page, _vma, _address, _flags) \ - struct page_vma_mapped_walk name = { \ - .pfn = page_to_pfn(_page), \ - .nr_pages = compound_nr(_page), \ - .pgoff = page_to_pgoff(_page), \ - .vma = _vma, \ - .address = _address, \ - .flags = _flags, \ - } - #define DEFINE_FOLIO_VMA_WALK(name, _folio, _vma, _address, _flags) \ struct page_vma_mapped_walk name = { \ .pfn = folio_pfn(_folio), \ @@ -678,12 +703,33 @@ static inline void page_vma_mapped_walk_done(struct page_vma_mapped_walk *pvmw) spin_unlock(pvmw->ptl); } -bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw); - -/* - * Used by swapoff to help locate where page is expected in vma. +/** + * page_vma_mapped_walk_restart - Restart the page table walk. + * @pvmw: Pointer to struct page_vma_mapped_walk. + * + * It restarts the page table walk when changes occur in the page + * table, such as splitting a PMD. Ensures that the PTL held during + * the previous walk is released and resets the state to allow for + * a new walk starting at the current address stored in pvmw->address. */ -unsigned long page_address_in_vma(struct page *, struct vm_area_struct *); +static inline void +page_vma_mapped_walk_restart(struct page_vma_mapped_walk *pvmw) +{ + WARN_ON_ONCE(!pvmw->pmd && !pvmw->pte); + + if (likely(pvmw->ptl)) + spin_unlock(pvmw->ptl); + else + WARN_ON_ONCE(1); + + pvmw->ptl = NULL; + pvmw->pmd = NULL; + pvmw->pte = NULL; +} + +bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw); +unsigned long page_address_in_vma(const struct folio *folio, + const struct page *, const struct vm_area_struct *); /* * Cleans the PTEs of shared mappings. @@ -696,9 +742,12 @@ int folio_mkclean(struct folio *); int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff, struct vm_area_struct *vma); -void remove_migration_ptes(struct folio *src, struct folio *dst, bool locked); +enum rmp_flags { + RMP_LOCKED = 1 << 0, + RMP_USE_SHARED_ZEROPAGE = 1 << 1, +}; -int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma); +void remove_migration_ptes(struct folio *src, struct folio *dst, int flags); /* * rmap_walk_control: To control rmap traversing for specific needs @@ -722,14 +771,14 @@ struct rmap_walk_control { bool (*rmap_one)(struct folio *folio, struct vm_area_struct *vma, unsigned long addr, void *arg); int (*done)(struct folio *folio); - struct anon_vma *(*anon_lock)(struct folio *folio, + struct anon_vma *(*anon_lock)(const struct folio *folio, struct rmap_walk_control *rwc); bool (*invalid_vma)(struct vm_area_struct *vma, void *arg); }; void rmap_walk(struct folio *folio, struct rmap_walk_control *rwc); void rmap_walk_locked(struct folio *folio, struct rmap_walk_control *rwc); -struct anon_vma *folio_lock_anon_vma_read(struct folio *folio, +struct anon_vma *folio_lock_anon_vma_read(const struct folio *folio, struct rmap_walk_control *rwc); #else /* !CONFIG_MMU */ @@ -755,8 +804,4 @@ static inline int folio_mkclean(struct folio *folio) } #endif /* CONFIG_MMU */ -static inline int page_mkclean(struct page *page) -{ - return folio_mkclean(page_folio(page)); -} #endif /* _LINUX_RMAP_H */ diff --git a/include/linux/rolling_buffer.h b/include/linux/rolling_buffer.h new file mode 100644 index 000000000000..ac15b1ffdd83 --- /dev/null +++ b/include/linux/rolling_buffer.h @@ -0,0 +1,61 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* Rolling buffer of folios + * + * Copyright (C) 2024 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#ifndef _ROLLING_BUFFER_H +#define _ROLLING_BUFFER_H + +#include <linux/folio_queue.h> +#include <linux/uio.h> + +/* + * Rolling buffer. Whilst the buffer is live and in use, folios and folio + * queue segments can be added to one end by one thread and removed from the + * other end by another thread. The buffer isn't allowed to be empty; it must + * always have at least one folio_queue in it so that neither side has to + * modify both queue pointers. + * + * The iterator in the buffer is extended as buffers are inserted. It can be + * snapshotted to use a segment of the buffer. + */ +struct rolling_buffer { + struct folio_queue *head; /* Producer's insertion point */ + struct folio_queue *tail; /* Consumer's removal point */ + struct iov_iter iter; /* Iterator tracking what's left in the buffer */ + u8 next_head_slot; /* Next slot in ->head */ + u8 first_tail_slot; /* First slot in ->tail */ +}; + +/* + * Snapshot of a rolling buffer. + */ +struct rolling_buffer_snapshot { + struct folio_queue *curr_folioq; /* Queue segment in which current folio resides */ + unsigned char curr_slot; /* Folio currently being read */ + unsigned char curr_order; /* Order of folio */ +}; + +/* Marks to store per-folio in the internal folio_queue structs. */ +#define ROLLBUF_MARK_1 BIT(0) +#define ROLLBUF_MARK_2 BIT(1) + +int rolling_buffer_init(struct rolling_buffer *roll, unsigned int rreq_id, + unsigned int direction); +int rolling_buffer_make_space(struct rolling_buffer *roll); +ssize_t rolling_buffer_load_from_ra(struct rolling_buffer *roll, + struct readahead_control *ractl, + struct folio_batch *put_batch); +ssize_t rolling_buffer_append(struct rolling_buffer *roll, struct folio *folio, + unsigned int flags); +struct folio_queue *rolling_buffer_delete_spent(struct rolling_buffer *roll); +void rolling_buffer_clear(struct rolling_buffer *roll); + +static inline void rolling_buffer_advance(struct rolling_buffer *roll, size_t amount) +{ + iov_iter_advance(&roll->iter, amount); +} + +#endif /* _ROLLING_BUFFER_H */ diff --git a/include/linux/rpmb.h b/include/linux/rpmb.h new file mode 100644 index 000000000000..cccda73eea4d --- /dev/null +++ b/include/linux/rpmb.h @@ -0,0 +1,123 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2015-2019 Intel Corp. All rights reserved + * Copyright (C) 2021-2022 Linaro Ltd + */ +#ifndef __RPMB_H__ +#define __RPMB_H__ + +#include <linux/device.h> +#include <linux/types.h> + +/** + * enum rpmb_type - type of underlying storage technology + * + * @RPMB_TYPE_EMMC : emmc (JESD84-B50.1) + * @RPMB_TYPE_UFS : UFS (JESD220) + * @RPMB_TYPE_NVME : NVM Express + */ +enum rpmb_type { + RPMB_TYPE_EMMC, + RPMB_TYPE_UFS, + RPMB_TYPE_NVME, +}; + +/** + * struct rpmb_descr - RPMB description provided by the underlying block device + * + * @type : block device type + * @route_frames : routes frames to and from the RPMB device + * @dev_id : unique device identifier read from the hardware + * @dev_id_len : length of unique device identifier + * @reliable_wr_count: number of sectors that can be written in one access + * @capacity : capacity of the device in units of 128K + * + * @dev_id is intended to be used as input when deriving the authenticaion key. + */ +struct rpmb_descr { + enum rpmb_type type; + int (*route_frames)(struct device *dev, u8 *req, unsigned int req_len, + u8 *resp, unsigned int resp_len); + u8 *dev_id; + size_t dev_id_len; + u16 reliable_wr_count; + u16 capacity; +}; + +/** + * struct rpmb_dev - device which can support RPMB partition + * + * @dev : device + * @id : device_id + * @list_node : linked list node + * @descr : RPMB description + */ +struct rpmb_dev { + struct device dev; + int id; + struct list_head list_node; + struct rpmb_descr descr; +}; + +#define to_rpmb_dev(x) container_of((x), struct rpmb_dev, dev) + +#if IS_ENABLED(CONFIG_RPMB) +struct rpmb_dev *rpmb_dev_get(struct rpmb_dev *rdev); +void rpmb_dev_put(struct rpmb_dev *rdev); +struct rpmb_dev *rpmb_dev_find_device(const void *data, + const struct rpmb_dev *start, + int (*match)(struct device *dev, + const void *data)); +int rpmb_interface_register(struct class_interface *intf); +void rpmb_interface_unregister(struct class_interface *intf); +struct rpmb_dev *rpmb_dev_register(struct device *dev, + struct rpmb_descr *descr); +int rpmb_dev_unregister(struct rpmb_dev *rdev); + +int rpmb_route_frames(struct rpmb_dev *rdev, u8 *req, + unsigned int req_len, u8 *resp, unsigned int resp_len); + +#else +static inline struct rpmb_dev *rpmb_dev_get(struct rpmb_dev *rdev) +{ + return NULL; +} + +static inline void rpmb_dev_put(struct rpmb_dev *rdev) { } + +static inline struct rpmb_dev * +rpmb_dev_find_device(const void *data, const struct rpmb_dev *start, + int (*match)(struct device *dev, const void *data)) +{ + return NULL; +} + +static inline int rpmb_interface_register(struct class_interface *intf) +{ + return -EOPNOTSUPP; +} + +static inline void rpmb_interface_unregister(struct class_interface *intf) +{ +} + +static inline struct rpmb_dev * +rpmb_dev_register(struct device *dev, struct rpmb_descr *descr) +{ + return NULL; +} + +static inline int rpmb_dev_unregister(struct rpmb_dev *dev) +{ + return 0; +} + +static inline int rpmb_route_frames(struct rpmb_dev *rdev, u8 *req, + unsigned int req_len, u8 *resp, + unsigned int resp_len) +{ + return -EOPNOTSUPP; +} +#endif /* CONFIG_RPMB */ + +#endif /* __RPMB_H__ */ diff --git a/include/linux/rtc/m48t59.h b/include/linux/rtc/m48t59.h index 9465d5405fe2..373ba77071c6 100644 --- a/include/linux/rtc/m48t59.h +++ b/include/linux/rtc/m48t59.h @@ -56,6 +56,9 @@ struct m48t59_plat_data { void __iomem *ioaddr; /* offset to RTC registers, automatically set according to the type */ unsigned int offset; + + /* YY digits (in RTC) are offset, i.e. year is 1900 + yy_offset + YY */ + int yy_offset; }; #endif /* _LINUX_RTC_M48T59_H_ */ diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index cdfc897f1e3c..4bc2ee0b10b0 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -51,6 +51,10 @@ extern atomic_t dev_unreg_count; extern struct rw_semaphore pernet_ops_rwsem; extern struct rw_semaphore net_rwsem; +#define ASSERT_RTNL() \ + WARN_ONCE(!rtnl_is_locked(), \ + "RTNL: assertion failed at %s (%d)\n", __FILE__, __LINE__) + #ifdef CONFIG_PROVE_LOCKING extern bool lockdep_rtnl_is_held(void); #else @@ -74,7 +78,7 @@ static inline bool lockdep_rtnl_is_held(void) * rtnl_dereference - fetch RCU pointer when updates are prevented by RTNL * @p: The pointer to read, prior to dereferencing * - * Return the value of the specified RCU-protected pointer, but omit + * Return: the value of the specified RCU-protected pointer, but omit * the READ_ONCE(), because caller holds RTNL. */ #define rtnl_dereference(p) \ @@ -92,6 +96,67 @@ static inline bool lockdep_rtnl_is_held(void) #define rcu_replace_pointer_rtnl(rp, p) \ rcu_replace_pointer(rp, p, lockdep_rtnl_is_held()) +#ifdef CONFIG_DEBUG_NET_SMALL_RTNL +void __rtnl_net_lock(struct net *net); +void __rtnl_net_unlock(struct net *net); +void rtnl_net_lock(struct net *net); +void rtnl_net_unlock(struct net *net); +int rtnl_net_trylock(struct net *net); +int rtnl_net_lock_killable(struct net *net); +int rtnl_net_lock_cmp_fn(const struct lockdep_map *a, const struct lockdep_map *b); + +bool rtnl_net_is_locked(struct net *net); + +#define ASSERT_RTNL_NET(net) \ + WARN_ONCE(!rtnl_net_is_locked(net), \ + "RTNL_NET: assertion failed at %s (%d)\n", \ + __FILE__, __LINE__) + +bool lockdep_rtnl_net_is_held(struct net *net); + +#define rcu_dereference_rtnl_net(net, p) \ + rcu_dereference_check(p, lockdep_rtnl_net_is_held(net)) +#define rtnl_net_dereference(net, p) \ + rcu_dereference_protected(p, lockdep_rtnl_net_is_held(net)) +#define rcu_replace_pointer_rtnl_net(net, rp, p) \ + rcu_replace_pointer(rp, p, lockdep_rtnl_net_is_held(net)) +#else +static inline void __rtnl_net_lock(struct net *net) {} +static inline void __rtnl_net_unlock(struct net *net) {} + +static inline void rtnl_net_lock(struct net *net) +{ + rtnl_lock(); +} + +static inline void rtnl_net_unlock(struct net *net) +{ + rtnl_unlock(); +} + +static inline int rtnl_net_trylock(struct net *net) +{ + return rtnl_trylock(); +} + +static inline int rtnl_net_lock_killable(struct net *net) +{ + return rtnl_lock_killable(); +} + +static inline void ASSERT_RTNL_NET(struct net *net) +{ + ASSERT_RTNL(); +} + +#define rcu_dereference_rtnl_net(net, p) \ + rcu_dereference_rtnl(p) +#define rtnl_net_dereference(net, p) \ + rtnl_dereference(p) +#define rcu_replace_pointer_rtnl_net(net, rp, p) \ + rcu_replace_pointer_rtnl(rp, p) +#endif + static inline struct netdev_queue *dev_ingress_queue(struct net_device *dev) { return rtnl_dereference(dev->ingress_queue); @@ -119,9 +184,11 @@ void rtnetlink_init(void); void __rtnl_unlock(void); void rtnl_kfree_skbs(struct sk_buff *head, struct sk_buff *tail); -#define ASSERT_RTNL() \ - WARN_ONCE(!rtnl_is_locked(), \ - "RTNL: assertion failed at %s (%d)\n", __FILE__, __LINE__) +/* Shared by rtnl_fdb_dump() and various ndo_fdb_dump() helpers. */ +struct ndo_fdb_dump_context { + unsigned long ifindex; + unsigned long fdb_idx; +}; extern int ndo_dflt_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, diff --git a/include/linux/rtsx_common.h b/include/linux/rtsx_common.h index bf290ad14c57..da9c8c6b5d50 100644 --- a/include/linux/rtsx_common.h +++ b/include/linux/rtsx_common.h @@ -12,7 +12,6 @@ #define DRV_NAME_RTSX_PCI "rtsx_pci" #define DRV_NAME_RTSX_PCI_SDMMC "rtsx_pci_sdmmc" -#define DRV_NAME_RTSX_PCI_MS "rtsx_pci_ms" #define RTSX_REG_PAIR(addr, val) (((u32)(addr) << 16) | (u8)(val)) diff --git a/include/linux/rtsx_usb.h b/include/linux/rtsx_usb.h index 3247ed8e9ff0..f267a06c6b1e 100644 --- a/include/linux/rtsx_usb.h +++ b/include/linux/rtsx_usb.h @@ -12,6 +12,10 @@ #include <linux/usb.h> +#define DRV_NAME_RTSX_USB "rtsx_usb" +#define DRV_NAME_RTSX_USB_SDMMC "rtsx_usb_sdmmc" +#define DRV_NAME_RTSX_USB_MS "rtsx_usb_ms" + /* related module names */ #define RTSX_USB_SD_CARD 0 #define RTSX_USB_MS_CARD 1 diff --git a/include/linux/rwlock.h b/include/linux/rwlock.h index c0ef596f340b..5b87c6f4a243 100644 --- a/include/linux/rwlock.h +++ b/include/linux/rwlock.h @@ -2,7 +2,7 @@ #define __LINUX_RWLOCK_H #ifndef __LINUX_INSIDE_SPINLOCK_H -# error "please don't include this file directly" +# error "Please do not include this file directly." #endif /* diff --git a/include/linux/rwlock_api_smp.h b/include/linux/rwlock_api_smp.h index dceb0a59b692..31d3d1116323 100644 --- a/include/linux/rwlock_api_smp.h +++ b/include/linux/rwlock_api_smp.h @@ -2,7 +2,7 @@ #define __LINUX_RWLOCK_API_SMP_H #ifndef __LINUX_SPINLOCK_API_SMP_H -# error "please don't include this file directly" +# error "Please do not include this file directly." #endif /* diff --git a/include/linux/rwlock_rt.h b/include/linux/rwlock_rt.h index 8544ff05e594..7d81fc6918ee 100644 --- a/include/linux/rwlock_rt.h +++ b/include/linux/rwlock_rt.h @@ -24,13 +24,13 @@ do { \ __rt_rwlock_init(rwl, #rwl, &__key); \ } while (0) -extern void rt_read_lock(rwlock_t *rwlock); +extern void rt_read_lock(rwlock_t *rwlock) __acquires(rwlock); extern int rt_read_trylock(rwlock_t *rwlock); -extern void rt_read_unlock(rwlock_t *rwlock); -extern void rt_write_lock(rwlock_t *rwlock); -extern void rt_write_lock_nested(rwlock_t *rwlock, int subclass); +extern void rt_read_unlock(rwlock_t *rwlock) __releases(rwlock); +extern void rt_write_lock(rwlock_t *rwlock) __acquires(rwlock); +extern void rt_write_lock_nested(rwlock_t *rwlock, int subclass) __acquires(rwlock); extern int rt_write_trylock(rwlock_t *rwlock); -extern void rt_write_unlock(rwlock_t *rwlock); +extern void rt_write_unlock(rwlock_t *rwlock) __releases(rwlock); static __always_inline void read_lock(rwlock_t *rwlock) { diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h index d662cf136021..189140bf11fc 100644 --- a/include/linux/sbitmap.h +++ b/include/linux/sbitmap.h @@ -36,6 +36,11 @@ struct sbitmap_word { * @cleared: word holding cleared bits */ unsigned long cleared ____cacheline_aligned_in_smp; + + /** + * @swap_lock: serializes simultaneous updates of ->word and ->cleared + */ + raw_spinlock_t swap_lock; } ____cacheline_aligned_in_smp; /** diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h index 77df3d7b18a6..d836e7440ee8 100644 --- a/include/linux/scatterlist.h +++ b/include/linux/scatterlist.h @@ -273,7 +273,7 @@ static inline void sg_unmark_end(struct scatterlist *sg) } /* - * One 64-bit architectures there is a 4-byte padding in struct scatterlist + * On 64-bit architectures there is a 4-byte padding in struct scatterlist * (assuming also CONFIG_NEED_SG_DMA_LENGTH is set). Use this padding for DMA * flags bits to indicate when a specific dma address is a bus address or the * buffer may have been bounced via SWIOTLB. @@ -313,7 +313,7 @@ static inline void sg_dma_mark_bus_address(struct scatterlist *sg) } /** - * sg_unmark_bus_address - Unmark the scatterlist entry as a bus address + * sg_dma_unmark_bus_address - Unmark the scatterlist entry as a bus address * @sg: SG entry * * Description: @@ -332,7 +332,7 @@ static inline void sg_dma_unmark_bus_address(struct scatterlist *sg) * Description: * Returns true if the scatterlist was marked for SWIOTLB bouncing. Not all * elements may have been bounced, so the caller would have to check - * individual SG entries with is_swiotlb_buffer(). + * individual SG entries with swiotlb_find_pool(). */ static inline bool sg_dma_is_swiotlb(struct scatterlist *sg) { diff --git a/include/linux/sched.h b/include/linux/sched.h index 3c2abbc587b4..9632e3318e0d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -13,7 +13,7 @@ #include <asm/processor.h> #include <linux/thread_info.h> #include <linux/preempt.h> -#include <linux/cpumask.h> +#include <linux/cpumask_types.h> #include <linux/cache.h> #include <linux/irqflags_types.h> @@ -36,6 +36,7 @@ #include <linux/signal_types.h> #include <linux/syscall_user_dispatch_types.h> #include <linux/mm_types_task.h> +#include <linux/netdevice_xmit.h> #include <linux/task_io_accounting.h> #include <linux/posix-timers_types.h> #include <linux/restart_block.h> @@ -53,6 +54,7 @@ struct bio_list; struct blk_plug; struct bpf_local_storage; struct bpf_run_ctx; +struct bpf_net_context; struct capture_control; struct cfs_rq; struct fs_struct; @@ -80,6 +82,8 @@ struct task_group; struct task_struct; struct user_event_mm; +#include <linux/sched/ext.h> + /* * Task state bitmask. NOTE! These bits are also * encoded in fs/proc/array.c: get_task_state(). @@ -147,8 +151,9 @@ struct user_event_mm; * Special states are those that do not use the normal wait-loop pattern. See * the comment with set_special_state(). */ -#define is_special_task_state(state) \ - ((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_PARKED | TASK_DEAD)) +#define is_special_task_state(state) \ + ((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_PARKED | \ + TASK_DEAD | TASK_FROZEN)) #ifdef CONFIG_DEBUG_ATOMIC_SLEEP # define debug_normal_state_change(state_value) \ @@ -301,7 +306,7 @@ enum { TASK_COMM_LEN = 16, }; -extern void scheduler_tick(void); +extern void sched_tick(void); #define MAX_SCHEDULE_TIMEOUT LONG_MAX @@ -393,6 +398,12 @@ struct sched_info { /* Time spent waiting on a runqueue: */ unsigned long long run_delay; + /* Max time spent waiting on a runqueue: */ + unsigned long long max_run_delay; + + /* Min time spent waiting on a runqueue: */ + unsigned long long min_run_delay; + /* Timestamps: */ /* When did we last run on a CPU? */ @@ -539,9 +550,14 @@ struct sched_entity { struct rb_node run_node; u64 deadline; u64 min_vruntime; + u64 min_slice; struct list_head group_node; - unsigned int on_rq; + unsigned char on_rq; + unsigned char sched_delayed; + unsigned char rel_deadline; + unsigned char custom_slice; + /* hole */ u64 exec_start; u64 sum_exec_runtime; @@ -637,12 +653,33 @@ struct sched_dl_entity { * * @dl_overrun tells if the task asked to be informed about runtime * overruns. + * + * @dl_server tells if this is a server entity. + * + * @dl_defer tells if this is a deferred or regular server. For + * now only defer server exists. + * + * @dl_defer_armed tells if the deferrable server is waiting + * for the replenishment timer to activate it. + * + * @dl_server_active tells if the dlserver is active(started). + * dlserver is started on first cfs enqueue on an idle runqueue + * and is stopped when a dequeue results in 0 cfs tasks on the + * runqueue. In other words, dlserver is active only when cpu's + * runqueue has atleast one cfs task. + * + * @dl_defer_running tells if the deferrable server is actually + * running, skipping the defer phase. */ unsigned int dl_throttled : 1; unsigned int dl_yielded : 1; unsigned int dl_non_contending : 1; unsigned int dl_overrun : 1; unsigned int dl_server : 1; + unsigned int dl_server_active : 1; + unsigned int dl_defer : 1; + unsigned int dl_defer_armed : 1; + unsigned int dl_defer_running : 1; /* * Bandwidth enforcement timer. Each -deadline task has its @@ -670,7 +707,7 @@ struct sched_dl_entity { */ struct rq *rq; dl_server_has_tasks_f server_has_tasks; - dl_server_pick_f server_pick; + dl_server_pick_f server_pick_task; #ifdef CONFIG_RT_MUTEXES /* @@ -734,6 +771,12 @@ enum perf_event_task_context { perf_nr_task_contexts, }; +/* + * Number of contexts where an event can trigger: + * task, softirq, hardirq, nmi. + */ +#define PERF_NR_CONTEXTS 4 + struct wake_q_node { struct wake_q_node *next; }; @@ -770,6 +813,10 @@ struct task_struct { unsigned int flags; unsigned int ptrace; +#ifdef CONFIG_MEM_ALLOC_PROFILING + struct alloc_tag *alloc_tag; +#endif + #ifdef CONFIG_SMP int on_cpu; struct __call_single_node wake_entry; @@ -798,6 +845,9 @@ struct task_struct { struct sched_rt_entity rt; struct sched_dl_entity dl; struct sched_dl_entity *dl_server; +#ifdef CONFIG_SCHED_CLASS_EXT + struct sched_ext_entity scx; +#endif const struct sched_class *sched_class; #ifdef CONFIG_SCHED_CORE @@ -810,6 +860,7 @@ struct task_struct { struct task_group *sched_task_group; #endif + #ifdef CONFIG_UCLAMP_TASK /* * Clamp values requested for a scheduling entity. @@ -835,6 +886,7 @@ struct task_struct { #endif unsigned int policy; + unsigned long max_allowed_capacity; int nr_cpus_allowed; const cpumask_t *cpus_ptr; cpumask_t *user_cpus_ptr; @@ -898,6 +950,7 @@ struct task_struct { unsigned sched_reset_on_fork:1; unsigned sched_contributes_to_load:1; unsigned sched_migrated:1; + unsigned sched_task_hot:1; /* Force alignment to the next boundary: */ unsigned :0; @@ -928,7 +981,7 @@ struct task_struct { #ifndef TIF_RESTORE_SIGMASK unsigned restore_sigmask:1; #endif -#ifdef CONFIG_MEMCG +#ifdef CONFIG_MEMCG_V1 unsigned in_user_fault:1; #endif #ifdef CONFIG_LRU_GEN @@ -962,14 +1015,16 @@ struct task_struct { #ifdef CONFIG_ARCH_HAS_CPU_PASID unsigned pasid_activated:1; #endif -#ifdef CONFIG_CPU_SUP_INTEL +#ifdef CONFIG_X86_BUS_LOCK_DETECT unsigned reported_split_lock:1; #endif #ifdef CONFIG_TASK_DELAY_ACCT /* delay due to memory thrashing */ unsigned in_thrashing:1; #endif - +#ifdef CONFIG_PREEMPT_RT + struct netdev_xmit net_xmit; +#endif unsigned long atomic_flags; /* Flags requiring atomic access. */ struct restart_block restart_block; @@ -1080,9 +1135,12 @@ struct task_struct { /* * executable name, excluding path. * - * - normally initialized setup_new_exec() - * - access it with [gs]et_task_comm() - * - lock it with task_lock() + * - normally initialized begin_new_exec() + * - set it with set_task_comm() + * - strscpy_pad() to ensure it is always NUL-terminated and + * zero-padded + * - task_lock() to ensure the operation is atomic and the name is + * fully updated. */ char comm[TASK_COMM_LEN]; @@ -1227,7 +1285,6 @@ struct task_struct { /* Sequence number to catch updates: */ seqcount_spinlock_t mems_allowed_seq; int cpuset_mem_spread_rotor; - int cpuset_slab_spread_rotor; #endif #ifdef CONFIG_CGROUPS /* Control Group info protected by css_set_lock: */ @@ -1250,6 +1307,7 @@ struct task_struct { unsigned int futex_state; #endif #ifdef CONFIG_PERF_EVENTS + u8 perf_recursion[PERF_NR_CONTEXTS]; struct perf_event_context *perf_event_ctxp; struct mutex perf_event_mutex; struct list_head perf_event_list; @@ -1323,6 +1381,15 @@ struct task_struct { * with respect to preemption. */ unsigned long rseq_event_mask; +# ifdef CONFIG_DEBUG_RSEQ + /* + * This is a place holder to save a copy of the rseq fields for + * validation of read-only fields. The struct rseq has a + * variable-length array at the end, so it cannot be used + * directly. Reserve a size large enough for the known fields. + */ + char rseq_fields[sizeof(struct rseq)]; +# endif #endif #ifdef CONFIG_SCHED_MM_CID @@ -1396,10 +1463,11 @@ struct task_struct { int curr_ret_depth; /* Stack of return addresses for return function tracing: */ - struct ftrace_ret_stack *ret_stack; + unsigned long *ret_stack; /* Timestamp for last schedule: */ unsigned long long ftrace_timestamp; + unsigned long long ftrace_sleeptime; /* * Number of functions that haven't been traced @@ -1441,19 +1509,18 @@ struct task_struct { unsigned int kcov_softirq; #endif -#ifdef CONFIG_MEMCG +#ifdef CONFIG_MEMCG_V1 struct mem_cgroup *memcg_in_oom; - gfp_t memcg_oom_gfp_mask; - int memcg_oom_order; +#endif +#ifdef CONFIG_MEMCG /* Number of pages to reclaim on returning to userland: */ unsigned int memcg_nr_pages_over_high; /* Used by memcontrol for targeted memcg charge: */ struct mem_cgroup *active_memcg; -#endif -#ifdef CONFIG_MEMCG_KMEM + /* Cache for current->cgroups->memcg->objcg lookups: */ struct obj_cgroup *objcg; #endif @@ -1502,6 +1569,8 @@ struct task_struct { /* Used for BPF run context */ struct bpf_run_ctx *bpf_ctx; #endif + /* Used by BPF for per-TASK xdp storage */ + struct bpf_net_context *bpf_net_context; #ifdef CONFIG_GCC_PLUGIN_STACKLEAK unsigned long lowest_stack; @@ -1584,8 +1653,9 @@ static inline unsigned int __task_state_index(unsigned int tsk_state, * We're lying here, but rather than expose a completely new task state * to userspace, we can make this appear as if the task has gone through * a regular rt_mutex_lock() call. + * Report frozen tasks as uninterruptible. */ - if (tsk_state & TASK_RTLOCK_WAIT) + if ((tsk_state & TASK_RTLOCK_WAIT) || (tsk_state & TASK_FROZEN)) state = TASK_UNINTERRUPTIBLE; return fls(state); @@ -1600,7 +1670,7 @@ static inline char task_index_to_char(unsigned int state) { static const char state_char[] = "RSDTtXZPI"; - BUILD_BUG_ON(1 + ilog2(TASK_REPORT_MAX) != sizeof(state_char) - 1); + BUILD_BUG_ON(TASK_REPORT_MAX * 2 != 1 << (sizeof(state_char) - 1)); return state_char[state]; } @@ -1639,8 +1709,8 @@ extern struct pid *cad_pid; * I am cleaning dirty pages from some other bdi. */ #define PF_KTHREAD 0x00200000 /* I am a kernel thread */ #define PF_RANDOMIZE 0x00400000 /* Randomize virtual address space */ -#define PF_MEMALLOC_NORECLAIM 0x00800000 /* All allocation requests will clear __GFP_DIRECT_RECLAIM */ -#define PF_MEMALLOC_NOWARN 0x01000000 /* All allocation requests will inherit __GFP_NOWARN */ +#define PF__HOLE__00800000 0x00800000 +#define PF__HOLE__01000000 0x01000000 #define PF__HOLE__02000000 0x02000000 #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_mask */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ @@ -1774,7 +1844,8 @@ static inline void do_set_cpus_allowed(struct task_struct *p, const struct cpuma } static inline int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) { - if (!cpumask_test_cpu(0, new_mask)) + /* Opencoded cpumask_test_cpu(0, new_mask) to avoid dependency on cpumask.h */ + if ((*cpumask_bits(new_mask) & 1) == 0) return -EINVAL; return 0; } @@ -1855,7 +1926,7 @@ extern unsigned long init_stack[THREAD_SIZE / sizeof(unsigned long)]; #ifdef CONFIG_THREAD_INFO_IN_TASK # define task_thread_info(task) (&(task)->thread_info) -#elif !defined(__HAVE_THREAD_FUNCTIONS) +#else # define task_thread_info(task) ((struct thread_info *)(task)->stack) #endif @@ -1889,16 +1960,28 @@ static inline void kick_process(struct task_struct *tsk) { } #endif extern void __set_task_comm(struct task_struct *tsk, const char *from, bool exec); +#define set_task_comm(tsk, from) ({ \ + BUILD_BUG_ON(sizeof(from) != TASK_COMM_LEN); \ + __set_task_comm(tsk, from, false); \ +}) -static inline void set_task_comm(struct task_struct *tsk, const char *from) -{ - __set_task_comm(tsk, from, false); -} - -extern char *__get_task_comm(char *to, size_t len, struct task_struct *tsk); +/* + * - Why not use task_lock()? + * User space can randomly change their names anyway, so locking for readers + * doesn't make sense. For writers, locking is probably necessary, as a race + * condition could lead to long-term mixed results. + * The strscpy_pad() in __set_task_comm() can ensure that the task comm is + * always NUL-terminated and zero-padded. Therefore the race condition between + * reader and writer is not an issue. + * + * - BUILD_BUG_ON() can help prevent the buf from being truncated. + * Since the callers don't perform any return value checks, this safeguard is + * necessary. + */ #define get_task_comm(buf, tsk) ({ \ - BUILD_BUG_ON(sizeof(buf) != TASK_COMM_LEN); \ - __get_task_comm(buf, sizeof(buf), tsk); \ + BUILD_BUG_ON(sizeof(buf) < TASK_COMM_LEN); \ + strscpy_pad(buf, (tsk)->comm); \ + buf; \ }) #ifdef CONFIG_SMP @@ -1959,7 +2042,8 @@ static inline void set_tsk_need_resched(struct task_struct *tsk) static inline void clear_tsk_need_resched(struct task_struct *tsk) { - clear_tsk_thread_flag(tsk,TIF_NEED_RESCHED); + atomic_long_andnot(_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY, + (atomic_long_t *)&task_thread_info(tsk)->flags); } static inline int test_tsk_need_resched(struct task_struct *tsk) @@ -2060,47 +2144,6 @@ extern int __cond_resched_rwlock_write(rwlock_t *lock); __cond_resched_rwlock_write(lock); \ }) -#ifdef CONFIG_PREEMPT_DYNAMIC - -extern bool preempt_model_none(void); -extern bool preempt_model_voluntary(void); -extern bool preempt_model_full(void); - -#else - -static inline bool preempt_model_none(void) -{ - return IS_ENABLED(CONFIG_PREEMPT_NONE); -} -static inline bool preempt_model_voluntary(void) -{ - return IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY); -} -static inline bool preempt_model_full(void) -{ - return IS_ENABLED(CONFIG_PREEMPT); -} - -#endif - -static inline bool preempt_model_rt(void) -{ - return IS_ENABLED(CONFIG_PREEMPT_RT); -} - -/* - * Does the preemption model allow non-cooperative preemption? - * - * For !CONFIG_PREEMPT_DYNAMIC kernels this is an exact match with - * CONFIG_PREEMPTION; for CONFIG_PREEMPT_DYNAMIC this doesn't work as the - * kernel is *built* with CONFIG_PREEMPTION=y but may run with e.g. the - * PREEMPT_NONE model. - */ -static inline bool preempt_model_preemptible(void) -{ - return preempt_model_full() || preempt_model_rt(); -} - static __always_inline bool need_resched(void) { return unlikely(tif_need_resched()); @@ -2131,6 +2174,11 @@ static inline void set_task_cpu(struct task_struct *p, unsigned int cpu) #endif /* CONFIG_SMP */ +static inline bool task_is_runnable(struct task_struct *p) +{ + return p->on_rq && !p->se.sched_delayed; +} + extern bool sched_task_on_rq(struct task_struct *p); extern unsigned long get_wchan(struct task_struct *p); extern struct task_struct *cpu_curr_snapshot(int cpu); @@ -2187,4 +2235,23 @@ static inline int sched_core_idle_cpu(int cpu) { return idle_cpu(cpu); } extern void sched_set_stop_task(int cpu, struct task_struct *stop); +#ifdef CONFIG_MEM_ALLOC_PROFILING +static __always_inline struct alloc_tag *alloc_tag_save(struct alloc_tag *tag) +{ + swap(current->alloc_tag, tag); + return tag; +} + +static __always_inline void alloc_tag_restore(struct alloc_tag *tag, struct alloc_tag *old) +{ +#ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG + WARN(current->alloc_tag != tag, "current->alloc_tag was changed:\n"); +#endif + current->alloc_tag = old; +} +#else +#define alloc_tag_save(_tag) NULL +#define alloc_tag_restore(_tag, _old) do {} while (0) +#endif + #endif diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h index 02f5090ffea2..6eb65ceed213 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -8,12 +8,6 @@ #define SUID_DUMP_USER 1 /* Dump as user of process */ #define SUID_DUMP_ROOT 2 /* Dump as root */ -/* mm flags */ - -/* for SUID_DUMP_* above */ -#define MMF_DUMPABLE_BITS 2 -#define MMF_DUMPABLE_MASK ((1 << MMF_DUMPABLE_BITS) - 1) - extern void set_dumpable(struct mm_struct *mm, int value); /* * This returns the actual value of the suid_dumpable flag. For things @@ -31,77 +25,4 @@ static inline int get_dumpable(struct mm_struct *mm) return __get_dumpable(mm->flags); } -/* coredump filter bits */ -#define MMF_DUMP_ANON_PRIVATE 2 -#define MMF_DUMP_ANON_SHARED 3 -#define MMF_DUMP_MAPPED_PRIVATE 4 -#define MMF_DUMP_MAPPED_SHARED 5 -#define MMF_DUMP_ELF_HEADERS 6 -#define MMF_DUMP_HUGETLB_PRIVATE 7 -#define MMF_DUMP_HUGETLB_SHARED 8 -#define MMF_DUMP_DAX_PRIVATE 9 -#define MMF_DUMP_DAX_SHARED 10 - -#define MMF_DUMP_FILTER_SHIFT MMF_DUMPABLE_BITS -#define MMF_DUMP_FILTER_BITS 9 -#define MMF_DUMP_FILTER_MASK \ - (((1 << MMF_DUMP_FILTER_BITS) - 1) << MMF_DUMP_FILTER_SHIFT) -#define MMF_DUMP_FILTER_DEFAULT \ - ((1 << MMF_DUMP_ANON_PRIVATE) | (1 << MMF_DUMP_ANON_SHARED) |\ - (1 << MMF_DUMP_HUGETLB_PRIVATE) | MMF_DUMP_MASK_DEFAULT_ELF) - -#ifdef CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS -# define MMF_DUMP_MASK_DEFAULT_ELF (1 << MMF_DUMP_ELF_HEADERS) -#else -# define MMF_DUMP_MASK_DEFAULT_ELF 0 -#endif - /* leave room for more dump flags */ -#define MMF_VM_MERGEABLE 16 /* KSM may merge identical pages */ -#define MMF_VM_HUGEPAGE 17 /* set when mm is available for - khugepaged */ -/* - * This one-shot flag is dropped due to necessity of changing exe once again - * on NFS restore - */ -//#define MMF_EXE_FILE_CHANGED 18 /* see prctl_set_mm_exe_file() */ - -#define MMF_HAS_UPROBES 19 /* has uprobes */ -#define MMF_RECALC_UPROBES 20 /* MMF_HAS_UPROBES can be wrong */ -#define MMF_OOM_SKIP 21 /* mm is of no interest for the OOM killer */ -#define MMF_UNSTABLE 22 /* mm is unstable for copy_from_user */ -#define MMF_HUGE_ZERO_PAGE 23 /* mm has ever used the global huge zero page */ -#define MMF_DISABLE_THP 24 /* disable THP for all VMAs */ -#define MMF_DISABLE_THP_MASK (1 << MMF_DISABLE_THP) -#define MMF_OOM_REAP_QUEUED 25 /* mm was queued for oom_reaper */ -#define MMF_MULTIPROCESS 26 /* mm is shared between processes */ -/* - * MMF_HAS_PINNED: Whether this mm has pinned any pages. This can be either - * replaced in the future by mm.pinned_vm when it becomes stable, or grow into - * a counter on its own. We're aggresive on this bit for now: even if the - * pinned pages were unpinned later on, we'll still keep this bit set for the - * 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_HAS_MDWE_NO_INHERIT 29 - -#define MMF_VM_MERGE_ANY 30 -#define MMF_VM_MERGE_ANY_MASK (1 << MMF_VM_MERGE_ANY) - -#define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\ - MMF_DISABLE_THP_MASK | MMF_HAS_MDWE_MASK |\ - MMF_VM_MERGE_ANY_MASK) - -static inline unsigned long mmf_init_flags(unsigned long flags) -{ - if (flags & (1UL << MMF_HAS_MDWE_NO_INHERIT)) - flags &= ~((1UL << MMF_HAS_MDWE) | - (1UL << MMF_HAS_MDWE_NO_INHERIT)); - return flags & MMF_INIT_MASK; -} - #endif /* _LINUX_SCHED_COREDUMP_H */ diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h index df3aca89d4f5..3a912ab42bb5 100644 --- a/include/linux/sched/deadline.h +++ b/include/linux/sched/deadline.h @@ -10,16 +10,16 @@ #include <linux/sched.h> -#define MAX_DL_PRIO 0 - -static inline int dl_prio(int prio) +static inline bool dl_prio(int prio) { - if (unlikely(prio < MAX_DL_PRIO)) - return 1; - return 0; + return unlikely(prio < MAX_DL_PRIO); } -static inline int dl_task(struct task_struct *p) +/* + * Returns true if a task has a priority that belongs to DL class. PI-boosted + * tasks will return true. Use dl_policy() to ignore PI-boosted tasks. + */ +static inline bool dl_task(struct task_struct *p) { return dl_prio(p->prio); } diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h new file mode 100644 index 000000000000..1d70a9867fb1 --- /dev/null +++ b/include/linux/sched/ext.h @@ -0,0 +1,216 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * BPF extensible scheduler class: Documentation/scheduler/sched-ext.rst + * + * Copyright (c) 2022 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2022 Tejun Heo <tj@kernel.org> + * Copyright (c) 2022 David Vernet <dvernet@meta.com> + */ +#ifndef _LINUX_SCHED_EXT_H +#define _LINUX_SCHED_EXT_H + +#ifdef CONFIG_SCHED_CLASS_EXT + +#include <linux/llist.h> +#include <linux/rhashtable-types.h> + +enum scx_public_consts { + SCX_OPS_NAME_LEN = 128, + + SCX_SLICE_DFL = 20 * 1000000, /* 20ms */ + SCX_SLICE_INF = U64_MAX, /* infinite, implies nohz */ +}; + +/* + * DSQ (dispatch queue) IDs are 64bit of the format: + * + * Bits: [63] [62 .. 0] + * [ B] [ ID ] + * + * B: 1 for IDs for built-in DSQs, 0 for ops-created user DSQs + * ID: 63 bit ID + * + * Built-in IDs: + * + * Bits: [63] [62] [61..32] [31 .. 0] + * [ 1] [ L] [ R ] [ V ] + * + * 1: 1 for built-in DSQs. + * L: 1 for LOCAL_ON DSQ IDs, 0 for others + * V: For LOCAL_ON DSQ IDs, a CPU number. For others, a pre-defined value. + */ +enum scx_dsq_id_flags { + SCX_DSQ_FLAG_BUILTIN = 1LLU << 63, + SCX_DSQ_FLAG_LOCAL_ON = 1LLU << 62, + + SCX_DSQ_INVALID = SCX_DSQ_FLAG_BUILTIN | 0, + SCX_DSQ_GLOBAL = SCX_DSQ_FLAG_BUILTIN | 1, + SCX_DSQ_LOCAL = SCX_DSQ_FLAG_BUILTIN | 2, + SCX_DSQ_LOCAL_ON = SCX_DSQ_FLAG_BUILTIN | SCX_DSQ_FLAG_LOCAL_ON, + SCX_DSQ_LOCAL_CPU_MASK = 0xffffffffLLU, +}; + +/* + * A dispatch queue (DSQ) can be either a FIFO or p->scx.dsq_vtime ordered + * queue. A built-in DSQ is always a FIFO. The built-in local DSQs are used to + * buffer between the scheduler core and the BPF scheduler. See the + * documentation for more details. + */ +struct scx_dispatch_q { + raw_spinlock_t lock; + struct list_head list; /* tasks in dispatch order */ + struct rb_root priq; /* used to order by p->scx.dsq_vtime */ + u32 nr; + u32 seq; /* used by BPF iter */ + u64 id; + struct rhash_head hash_node; + struct llist_node free_node; + struct rcu_head rcu; +}; + +/* scx_entity.flags */ +enum scx_ent_flags { + SCX_TASK_QUEUED = 1 << 0, /* on ext runqueue */ + SCX_TASK_RESET_RUNNABLE_AT = 1 << 2, /* runnable_at should be reset */ + SCX_TASK_DEQD_FOR_SLEEP = 1 << 3, /* last dequeue was for SLEEP */ + + SCX_TASK_STATE_SHIFT = 8, /* bit 8 and 9 are used to carry scx_task_state */ + SCX_TASK_STATE_BITS = 2, + SCX_TASK_STATE_MASK = ((1 << SCX_TASK_STATE_BITS) - 1) << SCX_TASK_STATE_SHIFT, + + SCX_TASK_CURSOR = 1 << 31, /* iteration cursor, not a task */ +}; + +/* scx_entity.flags & SCX_TASK_STATE_MASK */ +enum scx_task_state { + SCX_TASK_NONE, /* ops.init_task() not called yet */ + SCX_TASK_INIT, /* ops.init_task() succeeded, but task can be cancelled */ + SCX_TASK_READY, /* fully initialized, but not in sched_ext */ + SCX_TASK_ENABLED, /* fully initialized and in sched_ext */ + + SCX_TASK_NR_STATES, +}; + +/* scx_entity.dsq_flags */ +enum scx_ent_dsq_flags { + SCX_TASK_DSQ_ON_PRIQ = 1 << 0, /* task is queued on the priority queue of a dsq */ +}; + +/* + * Mask bits for scx_entity.kf_mask. Not all kfuncs can be called from + * everywhere and the following bits track which kfunc sets are currently + * allowed for %current. This simple per-task tracking works because SCX ops + * nest in a limited way. BPF will likely implement a way to allow and disallow + * kfuncs depending on the calling context which will replace this manual + * mechanism. See scx_kf_allow(). + */ +enum scx_kf_mask { + SCX_KF_UNLOCKED = 0, /* sleepable and not rq locked */ + /* ENQUEUE and DISPATCH may be nested inside CPU_RELEASE */ + SCX_KF_CPU_RELEASE = 1 << 0, /* ops.cpu_release() */ + /* ops.dequeue (in REST) may be nested inside DISPATCH */ + SCX_KF_DISPATCH = 1 << 1, /* ops.dispatch() */ + SCX_KF_ENQUEUE = 1 << 2, /* ops.enqueue() and ops.select_cpu() */ + SCX_KF_SELECT_CPU = 1 << 3, /* ops.select_cpu() */ + SCX_KF_REST = 1 << 4, /* other rq-locked operations */ + + __SCX_KF_RQ_LOCKED = SCX_KF_CPU_RELEASE | SCX_KF_DISPATCH | + SCX_KF_ENQUEUE | SCX_KF_SELECT_CPU | SCX_KF_REST, + __SCX_KF_TERMINAL = SCX_KF_ENQUEUE | SCX_KF_SELECT_CPU | SCX_KF_REST, +}; + +enum scx_dsq_lnode_flags { + SCX_DSQ_LNODE_ITER_CURSOR = 1 << 0, + + /* high 16 bits can be for iter cursor flags */ + __SCX_DSQ_LNODE_PRIV_SHIFT = 16, +}; + +struct scx_dsq_list_node { + struct list_head node; + u32 flags; + u32 priv; /* can be used by iter cursor */ +}; + +/* + * The following is embedded in task_struct and contains all fields necessary + * for a task to be scheduled by SCX. + */ +struct sched_ext_entity { + struct scx_dispatch_q *dsq; + struct scx_dsq_list_node dsq_list; /* dispatch order */ + struct rb_node dsq_priq; /* p->scx.dsq_vtime order */ + u32 dsq_seq; + u32 dsq_flags; /* protected by DSQ lock */ + u32 flags; /* protected by rq lock */ + u32 weight; + s32 sticky_cpu; + s32 holding_cpu; + u32 kf_mask; /* see scx_kf_mask above */ + struct task_struct *kf_tasks[2]; /* see SCX_CALL_OP_TASK() */ + atomic_long_t ops_state; + + struct list_head runnable_node; /* rq->scx.runnable_list */ + unsigned long runnable_at; + +#ifdef CONFIG_SCHED_CORE + u64 core_sched_at; /* see scx_prio_less() */ +#endif + u64 ddsp_dsq_id; + u64 ddsp_enq_flags; + + /* BPF scheduler modifiable fields */ + + /* + * Runtime budget in nsecs. This is usually set through + * scx_bpf_dispatch() but can also be modified directly by the BPF + * scheduler. Automatically decreased by SCX as the task executes. On + * depletion, a scheduling event is triggered. + * + * This value is cleared to zero if the task is preempted by + * %SCX_KICK_PREEMPT and shouldn't be used to determine how long the + * task ran. Use p->se.sum_exec_runtime instead. + */ + u64 slice; + + /* + * Used to order tasks when dispatching to the vtime-ordered priority + * queue of a dsq. This is usually set through scx_bpf_dispatch_vtime() + * but can also be modified directly by the BPF scheduler. Modifying it + * while a task is queued on a dsq may mangle the ordering and is not + * recommended. + */ + u64 dsq_vtime; + + /* + * If set, reject future sched_setscheduler(2) calls updating the policy + * to %SCHED_EXT with -%EACCES. + * + * Can be set from ops.init_task() while the BPF scheduler is being + * loaded (!scx_init_task_args->fork). If set and the task's policy is + * already %SCHED_EXT, the task's policy is rejected and forcefully + * reverted to %SCHED_NORMAL. The number of such events are reported + * through /sys/kernel/debug/sched_ext::nr_rejected. Setting this flag + * during fork is not allowed. + */ + bool disallow; /* reject switching into SCX */ + + /* cold fields */ +#ifdef CONFIG_EXT_GROUP_SCHED + struct cgroup *cgrp_moving_from; +#endif + struct list_head tasks_node; +}; + +void sched_ext_free(struct task_struct *p); +void print_scx_info(const char *log_lvl, struct task_struct *p); +void scx_softlockup(u32 dur_s); + +#else /* !CONFIG_SCHED_CLASS_EXT */ + +static inline void sched_ext_free(struct task_struct *p) {} +static inline void print_scx_info(const char *log_lvl, struct task_struct *p) {} +static inline void scx_softlockup(u32 dur_s) {} + +#endif /* CONFIG_SCHED_CLASS_EXT */ +#endif /* _LINUX_SCHED_EXT_H */ diff --git a/include/linux/sched/hotplug.h b/include/linux/sched/hotplug.h index 412cdaba33eb..17e04859b9a4 100644 --- a/include/linux/sched/hotplug.h +++ b/include/linux/sched/hotplug.h @@ -18,10 +18,6 @@ extern int sched_cpu_dying(unsigned int cpu); # define sched_cpu_dying NULL #endif -#ifdef CONFIG_HOTPLUG_CPU -extern void idle_task_exit(void); -#else static inline void idle_task_exit(void) {} -#endif #endif /* _LINUX_SCHED_HOTPLUG_H */ diff --git a/include/linux/sched/idle.h b/include/linux/sched/idle.h index 478084f9105e..e670ac282333 100644 --- a/include/linux/sched/idle.h +++ b/include/linux/sched/idle.h @@ -5,8 +5,8 @@ #include <linux/sched.h> enum cpu_idle_type { + __CPU_NOT_IDLE = 0, CPU_IDLE, - CPU_NOT_IDLE, CPU_NEWLY_IDLE, CPU_MAX_IDLE_TYPES }; diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h index 2b461129d1fa..d8501f4709b5 100644 --- a/include/linux/sched/isolation.h +++ b/include/linux/sched/isolation.h @@ -7,16 +7,21 @@ #include <linux/tick.h> enum hk_type { - HK_TYPE_TIMER, - HK_TYPE_RCU, - HK_TYPE_MISC, - HK_TYPE_SCHED, - HK_TYPE_TICK, HK_TYPE_DOMAIN, - HK_TYPE_WQ, HK_TYPE_MANAGED_IRQ, - HK_TYPE_KTHREAD, - HK_TYPE_MAX + HK_TYPE_KERNEL_NOISE, + HK_TYPE_MAX, + + /* + * The following housekeeping types are only set by the nohz_full + * boot commandline option. So they can share the same value. + */ + HK_TYPE_TICK = HK_TYPE_KERNEL_NOISE, + HK_TYPE_TIMER = HK_TYPE_KERNEL_NOISE, + HK_TYPE_RCU = HK_TYPE_KERNEL_NOISE, + HK_TYPE_MISC = HK_TYPE_KERNEL_NOISE, + HK_TYPE_WQ = HK_TYPE_KERNEL_NOISE, + HK_TYPE_KTHREAD = HK_TYPE_KERNEL_NOISE }; #ifdef CONFIG_CPU_ISOLATION diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index b6543f9d78d6..928a626725e6 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -8,6 +8,7 @@ #include <linux/mm_types.h> #include <linux/gfp.h> #include <linux/sync_core.h> +#include <linux/sched/coredump.h> /* * Routines for handling mm_structs @@ -178,22 +179,36 @@ static inline void mm_update_next_owner(struct mm_struct *mm) extern void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack); -extern unsigned long -arch_get_unmapped_area(struct file *, unsigned long, unsigned long, - unsigned long, unsigned long); -extern unsigned long + +unsigned long +arch_get_unmapped_area(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags, vm_flags_t vm_flags); +unsigned long arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, - unsigned long len, unsigned long pgoff, - unsigned long flags); + unsigned long len, unsigned long pgoff, + unsigned long flags, vm_flags_t); + +unsigned long mm_get_unmapped_area(struct mm_struct *mm, struct file *filp, + unsigned long addr, unsigned long len, + unsigned long pgoff, unsigned long flags); + +unsigned long mm_get_unmapped_area_vmflags(struct mm_struct *mm, + struct file *filp, + unsigned long addr, + unsigned long len, + unsigned long pgoff, + unsigned long flags, + vm_flags_t vm_flags); unsigned long generic_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, - unsigned long flags); + unsigned long flags, vm_flags_t vm_flags); unsigned long generic_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, - unsigned long flags); + unsigned long flags, vm_flags_t vm_flags); #else static inline void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) {} @@ -236,25 +251,16 @@ static inline gfp_t current_gfp_context(gfp_t flags) { unsigned int pflags = READ_ONCE(current->flags); - if (unlikely(pflags & (PF_MEMALLOC_NOIO | - PF_MEMALLOC_NOFS | - PF_MEMALLOC_NORECLAIM | - PF_MEMALLOC_NOWARN | - PF_MEMALLOC_PIN))) { + if (unlikely(pflags & (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS | PF_MEMALLOC_PIN))) { /* - * Stronger flags before weaker flags: - * NORECLAIM implies NOIO, which in turn implies NOFS + * NOIO implies both NOIO and NOFS and it is a weaker context + * so always make sure it makes precedence */ - if (pflags & PF_MEMALLOC_NORECLAIM) - flags &= ~__GFP_DIRECT_RECLAIM; - else if (pflags & PF_MEMALLOC_NOIO) + if (pflags & PF_MEMALLOC_NOIO) flags &= ~(__GFP_IO | __GFP_FS); else if (pflags & PF_MEMALLOC_NOFS) flags &= ~__GFP_FS; - if (pflags & PF_MEMALLOC_NOWARN) - flags |= __GFP_NOWARN; - if (pflags & PF_MEMALLOC_PIN) flags &= ~__GFP_MOVABLE; } diff --git a/include/linux/sched/prio.h b/include/linux/sched/prio.h index ab83d85e1183..6ab43b4f72f9 100644 --- a/include/linux/sched/prio.h +++ b/include/linux/sched/prio.h @@ -14,6 +14,7 @@ */ #define MAX_RT_PRIO 100 +#define MAX_DL_PRIO 0 #define MAX_PRIO (MAX_RT_PRIO + NICE_WIDTH) #define DEFAULT_PRIO (MAX_RT_PRIO + NICE_WIDTH / 2) diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h index b2b9e6eb9683..4e3338103654 100644 --- a/include/linux/sched/rt.h +++ b/include/linux/sched/rt.h @@ -6,19 +6,40 @@ struct task_struct; -static inline int rt_prio(int prio) +static inline bool rt_prio(int prio) { - if (unlikely(prio < MAX_RT_PRIO)) - return 1; - return 0; + return unlikely(prio < MAX_RT_PRIO && prio >= MAX_DL_PRIO); } -static inline int rt_task(struct task_struct *p) +static inline bool rt_or_dl_prio(int prio) +{ + return unlikely(prio < MAX_RT_PRIO); +} + +/* + * Returns true if a task has a priority that belongs to RT class. PI-boosted + * tasks will return true. Use rt_policy() to ignore PI-boosted tasks. + */ +static inline bool rt_task(struct task_struct *p) { return rt_prio(p->prio); } -static inline bool task_is_realtime(struct task_struct *tsk) +/* + * Returns true if a task has a priority that belongs to RT or DL classes. + * PI-boosted tasks will return true. Use rt_or_dl_task_policy() to ignore + * PI-boosted tasks. + */ +static inline bool rt_or_dl_task(struct task_struct *p) +{ + return rt_or_dl_prio(p->prio); +} + +/* + * Returns true if a task has a policy that belongs to RT or DL classes. + * PI-boosted tasks will return false. + */ +static inline bool rt_or_dl_task_policy(struct task_struct *tsk) { int policy = tsk->policy; diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 0a0e23c45406..d5d03d919df8 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -137,7 +137,8 @@ struct signal_struct { /* POSIX.1b Interval Timers */ unsigned int next_posix_timer_id; - struct list_head posix_timers; + struct hlist_head posix_timers; + struct hlist_head ignored_posix_timers; /* ITIMER_REAL timer for the process */ struct hrtimer real_timer; @@ -276,8 +277,7 @@ static inline void signal_set_stop_flags(struct signal_struct *sig, extern void flush_signals(struct task_struct *); extern void ignore_signals(struct task_struct *); extern void flush_signal_handlers(struct task_struct *, int force_default); -extern int dequeue_signal(struct task_struct *task, sigset_t *mask, - kernel_siginfo_t *info, enum pid_type *type); +extern int dequeue_signal(sigset_t *mask, kernel_siginfo_t *info, enum pid_type *type); static inline int kernel_dequeue_signal(void) { @@ -287,7 +287,7 @@ static inline int kernel_dequeue_signal(void) int ret; spin_lock_irq(&task->sighand->siglock); - ret = dequeue_signal(task, &task->blocked, &__info, &__type); + ret = dequeue_signal(&task->blocked, &__info, &__type); spin_unlock_irq(&task->sighand->siglock); return ret; @@ -339,9 +339,6 @@ extern void force_fatal_sig(int); extern void force_exit_sig(int); extern int send_sig(int, struct task_struct *, int); extern int zap_other_threads(struct task_struct *p); -extern struct sigqueue *sigqueue_alloc(void); -extern void sigqueue_free(struct sigqueue *); -extern int send_sigqueue(struct sigqueue *, struct pid *, enum pid_type); extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *); static inline void clear_notify_signal(void) diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index d362aacf9f89..0f2aeb37bbb0 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -63,7 +63,8 @@ extern asmlinkage void schedule_tail(struct task_struct *prev); extern void init_idle(struct task_struct *idle, int cpu); extern int sched_fork(unsigned long clone_flags, struct task_struct *p); -extern void sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs); +extern int sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs); +extern void sched_cancel_fork(struct task_struct *p); extern void sched_post_fork(struct task_struct *p); extern void sched_dead(struct task_struct *p); @@ -119,6 +120,11 @@ static inline struct task_struct *get_task_struct(struct task_struct *t) return t; } +static inline struct task_struct *tryget_task_struct(struct task_struct *t) +{ + return refcount_inc_not_zero(&t->usage) ? t : NULL; +} + extern void __put_task_struct(struct task_struct *t); extern void __put_task_struct_rcu_cb(struct rcu_head *rhp); diff --git a/include/linux/sched/task_stack.h b/include/linux/sched/task_stack.h index ccd72b978e1f..cffad65bdc6a 100644 --- a/include/linux/sched/task_stack.h +++ b/include/linux/sched/task_stack.h @@ -9,6 +9,7 @@ #include <linux/sched.h> #include <linux/magic.h> #include <linux/refcount.h> +#include <linux/kasan.h> #ifdef CONFIG_THREAD_INFO_IN_TASK @@ -33,7 +34,7 @@ static __always_inline unsigned long *end_of_stack(const struct task_struct *tas #endif } -#elif !defined(__HAVE_THREAD_FUNCTIONS) +#else #define task_stack_page(task) ((void *)(task)->stack) @@ -89,29 +90,18 @@ static inline int object_is_on_stack(const void *obj) { void *stack = task_stack_page(current); + obj = kasan_reset_tag(obj); return (obj >= stack) && (obj < (stack + THREAD_SIZE)); } extern void thread_stack_cache_init(void); #ifdef CONFIG_DEBUG_STACK_USAGE +unsigned long stack_not_used(struct task_struct *p); +#else static inline unsigned long stack_not_used(struct task_struct *p) { - unsigned long *n = end_of_stack(p); - - do { /* Skip over canary */ -# ifdef CONFIG_STACK_GROWSUP - n--; -# else - n++; -# endif - } while (!*n); - -# ifdef CONFIG_STACK_GROWSUP - return (unsigned long)end_of_stack(p) - (unsigned long)n; -# else - return (unsigned long)n - (unsigned long)end_of_stack(p); -# endif + return 0; } #endif extern void set_task_stack_end_magic(struct task_struct *tsk); diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 18572c9ea724..7f3dbafe1817 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -110,11 +110,14 @@ struct sched_domain { unsigned long last_decay_max_lb_cost; #ifdef CONFIG_SCHEDSTATS - /* load_balance() stats */ + /* sched_balance_rq() stats */ unsigned int lb_count[CPU_MAX_IDLE_TYPES]; unsigned int lb_failed[CPU_MAX_IDLE_TYPES]; unsigned int lb_balanced[CPU_MAX_IDLE_TYPES]; - unsigned int lb_imbalance[CPU_MAX_IDLE_TYPES]; + unsigned int lb_imbalance_load[CPU_MAX_IDLE_TYPES]; + unsigned int lb_imbalance_util[CPU_MAX_IDLE_TYPES]; + unsigned int lb_imbalance_task[CPU_MAX_IDLE_TYPES]; + unsigned int lb_imbalance_misfit[CPU_MAX_IDLE_TYPES]; unsigned int lb_gained[CPU_MAX_IDLE_TYPES]; unsigned int lb_hot_gained[CPU_MAX_IDLE_TYPES]; unsigned int lb_nobusyg[CPU_MAX_IDLE_TYPES]; @@ -140,9 +143,7 @@ struct sched_domain { unsigned int ttwu_move_affine; unsigned int ttwu_move_balance; #endif -#ifdef CONFIG_SCHED_DEBUG char *name; -#endif union { void *private; /* used during construction */ struct rcu_head rcu; /* used during destruction */ @@ -198,18 +199,12 @@ struct sched_domain_topology_level { int flags; int numa_level; struct sd_data data; -#ifdef CONFIG_SCHED_DEBUG char *name; -#endif }; extern void __init set_sched_topology(struct sched_domain_topology_level *tl); -#ifdef CONFIG_SCHED_DEBUG # define SD_INIT_NAME(type) .name = #type -#else -# define SD_INIT_NAME(type) -#endif #else /* CONFIG_SMP */ @@ -270,17 +265,17 @@ unsigned long arch_scale_cpu_capacity(int cpu) } #endif -#ifndef arch_scale_thermal_pressure +#ifndef arch_scale_hw_pressure static __always_inline -unsigned long arch_scale_thermal_pressure(int cpu) +unsigned long arch_scale_hw_pressure(int cpu) { return 0; } #endif -#ifndef arch_update_thermal_pressure +#ifndef arch_update_hw_pressure static __always_inline -void arch_update_thermal_pressure(const struct cpumask *cpus, +void arch_update_hw_pressure(const struct cpumask *cpus, unsigned long capped_frequency) { } #endif diff --git a/include/linux/sched/vhost_task.h b/include/linux/sched/vhost_task.h index bc60243d43b3..25446c5d3508 100644 --- a/include/linux/sched/vhost_task.h +++ b/include/linux/sched/vhost_task.h @@ -4,7 +4,8 @@ struct vhost_task; -struct vhost_task *vhost_task_create(bool (*fn)(void *), void *arg, +struct vhost_task *vhost_task_create(bool (*fn)(void *), + void (*handle_kill)(void *), void *arg, const char *name); void vhost_task_start(struct vhost_task *vtsk); void vhost_task_stop(struct vhost_task *vtsk); diff --git a/include/linux/sched/wake_q.h b/include/linux/sched/wake_q.h index 06cd8fb2f409..0f28b4623ad4 100644 --- a/include/linux/sched/wake_q.h +++ b/include/linux/sched/wake_q.h @@ -63,4 +63,38 @@ extern void wake_q_add(struct wake_q_head *head, struct task_struct *task); extern void wake_q_add_safe(struct wake_q_head *head, struct task_struct *task); extern void wake_up_q(struct wake_q_head *head); +/* Spin unlock helpers to unlock and call wake_up_q with preempt disabled */ +static inline +void raw_spin_unlock_wake(raw_spinlock_t *lock, struct wake_q_head *wake_q) +{ + guard(preempt)(); + raw_spin_unlock(lock); + if (wake_q) { + wake_up_q(wake_q); + wake_q_init(wake_q); + } +} + +static inline +void raw_spin_unlock_irq_wake(raw_spinlock_t *lock, struct wake_q_head *wake_q) +{ + guard(preempt)(); + raw_spin_unlock_irq(lock); + if (wake_q) { + wake_up_q(wake_q); + wake_q_init(wake_q); + } +} + +static inline +void raw_spin_unlock_irqrestore_wake(raw_spinlock_t *lock, unsigned long flags, + struct wake_q_head *wake_q) +{ + guard(preempt)(); + raw_spin_unlock_irqrestore(lock, flags); + if (wake_q) { + wake_up_q(wake_q); + wake_q_init(wake_q); + } +} #endif /* _LINUX_SCHED_WAKE_Q_H */ diff --git a/include/linux/scmi_imx_protocol.h b/include/linux/scmi_imx_protocol.h new file mode 100644 index 000000000000..53b356a26414 --- /dev/null +++ b/include/linux/scmi_imx_protocol.h @@ -0,0 +1,60 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * SCMI Message Protocol driver NXP extension header + * + * Copyright 2024 NXP. + */ + +#ifndef _LINUX_SCMI_NXP_PROTOCOL_H +#define _LINUX_SCMI_NXP_PROTOCOL_H + +#include <linux/bitfield.h> +#include <linux/device.h> +#include <linux/notifier.h> +#include <linux/types.h> + +#define SCMI_PROTOCOL_IMX_BBM 0x81 +#define SCMI_PROTOCOL_IMX_MISC 0x84 + +#define SCMI_IMX_VENDOR "NXP" +#define SCMI_IMX_SUBVENDOR "IMX" + +struct scmi_imx_bbm_proto_ops { + int (*rtc_time_set)(const struct scmi_protocol_handle *ph, u32 id, + uint64_t sec); + int (*rtc_time_get)(const struct scmi_protocol_handle *ph, u32 id, + u64 *val); + int (*rtc_alarm_set)(const struct scmi_protocol_handle *ph, u32 id, + bool enable, u64 sec); + int (*button_get)(const struct scmi_protocol_handle *ph, u32 *state); +}; + +enum scmi_nxp_notification_events { + SCMI_EVENT_IMX_BBM_RTC = 0x0, + SCMI_EVENT_IMX_BBM_BUTTON = 0x1, + SCMI_EVENT_IMX_MISC_CONTROL = 0x0, +}; + +struct scmi_imx_bbm_notif_report { + bool is_rtc; + bool is_button; + ktime_t timestamp; + unsigned int rtc_id; + unsigned int rtc_evt; +}; + +struct scmi_imx_misc_ctrl_notify_report { + ktime_t timestamp; + unsigned int ctrl_id; + unsigned int flags; +}; + +struct scmi_imx_misc_proto_ops { + int (*misc_ctrl_set)(const struct scmi_protocol_handle *ph, u32 id, + u32 num, u32 *val); + int (*misc_ctrl_get)(const struct scmi_protocol_handle *ph, u32 id, + u32 *num, u32 *val); + int (*misc_ctrl_req_notify)(const struct scmi_protocol_handle *ph, + u32 ctrl_id, u32 evt_id, u32 flags); +}; +#endif diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index b807141acc14..688466a0e816 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -737,6 +737,89 @@ struct scmi_powercap_proto_ops { u32 *power_thresh_high); }; +enum scmi_pinctrl_selector_type { + PIN_TYPE = 0, + GROUP_TYPE, + FUNCTION_TYPE, +}; + +enum scmi_pinctrl_conf_type { + SCMI_PIN_DEFAULT = 0, + SCMI_PIN_BIAS_BUS_HOLD = 1, + SCMI_PIN_BIAS_DISABLE = 2, + SCMI_PIN_BIAS_HIGH_IMPEDANCE = 3, + SCMI_PIN_BIAS_PULL_UP = 4, + SCMI_PIN_BIAS_PULL_DEFAULT = 5, + SCMI_PIN_BIAS_PULL_DOWN = 6, + SCMI_PIN_DRIVE_OPEN_DRAIN = 7, + SCMI_PIN_DRIVE_OPEN_SOURCE = 8, + SCMI_PIN_DRIVE_PUSH_PULL = 9, + SCMI_PIN_DRIVE_STRENGTH = 10, + SCMI_PIN_INPUT_DEBOUNCE = 11, + SCMI_PIN_INPUT_MODE = 12, + SCMI_PIN_PULL_MODE = 13, + SCMI_PIN_INPUT_VALUE = 14, + SCMI_PIN_INPUT_SCHMITT = 15, + SCMI_PIN_LOW_POWER_MODE = 16, + SCMI_PIN_OUTPUT_MODE = 17, + SCMI_PIN_OUTPUT_VALUE = 18, + SCMI_PIN_POWER_SOURCE = 19, + SCMI_PIN_SLEW_RATE = 20, + SCMI_PIN_OEM_START = 192, + SCMI_PIN_OEM_END = 255, +}; + +/** + * struct scmi_pinctrl_proto_ops - represents the various operations provided + * by SCMI Pinctrl Protocol + * + * @count_get: returns count of the registered elements in given type + * @name_get: returns name by index of given type + * @group_pins_get: returns the set of pins, assigned to the specified group + * @function_groups_get: returns the set of groups, assigned to the specified + * function + * @mux_set: set muxing function for groups of pins + * @settings_get_one: returns one configuration parameter for pin or group + * specified by config_type + * @settings_get_all: returns all configuration parameters for pin or group + * @settings_conf: sets the configuration parameter for pin or group + * @pin_request: aquire pin before selecting mux setting + * @pin_free: frees pin, acquired by request_pin call + */ +struct scmi_pinctrl_proto_ops { + int (*count_get)(const struct scmi_protocol_handle *ph, + enum scmi_pinctrl_selector_type type); + int (*name_get)(const struct scmi_protocol_handle *ph, u32 selector, + enum scmi_pinctrl_selector_type type, + const char **name); + int (*group_pins_get)(const struct scmi_protocol_handle *ph, + u32 selector, const unsigned int **pins, + unsigned int *nr_pins); + int (*function_groups_get)(const struct scmi_protocol_handle *ph, + u32 selector, unsigned int *nr_groups, + const unsigned int **groups); + int (*mux_set)(const struct scmi_protocol_handle *ph, u32 selector, + u32 group); + int (*settings_get_one)(const struct scmi_protocol_handle *ph, + u32 selector, + enum scmi_pinctrl_selector_type type, + enum scmi_pinctrl_conf_type config_type, + u32 *config_value); + int (*settings_get_all)(const struct scmi_protocol_handle *ph, + u32 selector, + enum scmi_pinctrl_selector_type type, + unsigned int *nr_configs, + enum scmi_pinctrl_conf_type *config_types, + u32 *config_values); + int (*settings_conf)(const struct scmi_protocol_handle *ph, + u32 selector, enum scmi_pinctrl_selector_type type, + unsigned int nr_configs, + enum scmi_pinctrl_conf_type *config_type, + u32 *config_value); + int (*pin_request)(const struct scmi_protocol_handle *ph, u32 pin); + int (*pin_free)(const struct scmi_protocol_handle *ph, u32 pin); +}; + /** * struct scmi_notify_ops - represents notifications' operations provided by * SCMI core @@ -783,8 +866,6 @@ struct scmi_notify_ops { const u32 *src_id, struct notifier_block *nb); int (*devm_event_notifier_unregister)(struct scmi_device *sdev, - u8 proto_id, u8 evt_id, - const u32 *src_id, struct notifier_block *nb); int (*event_notifier_register)(const struct scmi_handle *handle, u8 proto_id, u8 evt_id, @@ -844,6 +925,7 @@ enum scmi_std_protocol { SCMI_PROTOCOL_RESET = 0x16, SCMI_PROTOCOL_VOLTAGE = 0x17, SCMI_PROTOCOL_POWERCAP = 0x18, + SCMI_PROTOCOL_PINCTRL = 0x19, }; enum scmi_system_events { @@ -863,7 +945,7 @@ struct scmi_device { struct scmi_handle *handle; }; -#define to_scmi_dev(d) container_of(d, struct scmi_device, dev) +#define to_scmi_dev(d) container_of_const(d, struct scmi_device, dev) struct scmi_device_id { u8 protocol_id; diff --git a/include/linux/screen_info.h b/include/linux/screen_info.h index 75303c126285..6a4a3cec4638 100644 --- a/include/linux/screen_info.h +++ b/include/linux/screen_info.h @@ -49,6 +49,16 @@ static inline u64 __screen_info_lfb_size(const struct screen_info *si, unsigned return lfb_size; } +static inline bool __screen_info_vbe_mode_nonvga(const struct screen_info *si) +{ + /* + * VESA modes typically run on VGA hardware. Set bit 5 signals that this + * is not the case. Drivers can then not make use of VGA resources. See + * Sec 4.4 of the VBE 2.0 spec. + */ + return si->vesa_attributes & BIT(5); +} + static inline unsigned int __screen_info_video_type(unsigned int type) { switch (type) { diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index 709ad84809e1..e45531455d3b 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -32,6 +32,11 @@ static inline int secure_computing(void) } #else extern void secure_computing_strict(int this_syscall); +static inline int __secure_computing(const struct seccomp_data *sd) +{ + secure_computing_strict(sd->nr); + return 0; +} #endif extern long prctl_get_seccomp(void); @@ -50,10 +55,10 @@ struct seccomp_data; #ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER static inline int secure_computing(void) { return 0; } -static inline int __secure_computing(const struct seccomp_data *sd) { return 0; } #else static inline void secure_computing_strict(int this_syscall) { return; } #endif +static inline int __secure_computing(const struct seccomp_data *sd) { return 0; } static inline long prctl_get_seccomp(void) { diff --git a/include/linux/secretmem.h b/include/linux/secretmem.h index acf7e1a3f3de..e918f96881f5 100644 --- a/include/linux/secretmem.h +++ b/include/linux/secretmem.h @@ -6,25 +6,8 @@ extern const struct address_space_operations secretmem_aops; -static inline bool folio_is_secretmem(struct folio *folio) +static inline bool secretmem_mapping(struct address_space *mapping) { - struct address_space *mapping; - - /* - * Using folio_mapping() is quite slow because of the actual call - * instruction. - * We know that secretmem pages are not compound, so we can - * save a couple of cycles here. - */ - if (folio_test_large(folio)) - return false; - - mapping = (struct address_space *) - ((unsigned long)folio->mapping & ~PAGE_MAPPING_FLAGS); - - if (!mapping || mapping != folio->mapping) - return false; - return mapping->a_ops == &secretmem_aops; } @@ -38,7 +21,7 @@ static inline bool vma_is_secretmem(struct vm_area_struct *vma) return false; } -static inline bool folio_is_secretmem(struct folio *folio) +static inline bool secretmem_mapping(struct address_space *mapping) { return false; } diff --git a/include/linux/security.h b/include/linux/security.h index 41a8f667bdfa..980b6c207cad 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -34,6 +34,10 @@ #include <linux/sockptr.h> #include <linux/bpf.h> #include <uapi/linux/lsm.h> +#include <linux/lsm/selinux.h> +#include <linux/lsm/smack.h> +#include <linux/lsm/apparmor.h> +#include <linux/lsm/bpf.h> struct linux_binprm; struct cred; @@ -83,6 +87,18 @@ enum lsm_event { LSM_POLICY_CHANGE, }; +struct dm_verity_digest { + const char *alg; + const u8 *digest; + size_t digest_len; +}; + +enum lsm_integrity_type { + LSM_INT_DMVERITY_SIG_VALID, + LSM_INT_DMVERITY_ROOTHASH, + LSM_INT_FSVERITY_BUILTINSIG_VALID, +}; + /* * These are reasons that can be passed to the security_locked_down() * LSM hook. Lockdown reasons that protect kernel integrity (ie, the @@ -140,6 +156,16 @@ enum lockdown_reason { LOCKDOWN_CONFIDENTIALITY_MAX, }; +/* + * Data exported by the security modules + */ +struct lsm_prop { + struct lsm_prop_selinux selinux; + struct lsm_prop_smack smack; + struct lsm_prop_apparmor apparmor; + struct lsm_prop_bpf bpf; +}; + extern const char *const lockdown_reasons[LOCKDOWN_CONFIDENTIALITY_MAX+1]; extern u32 lsm_active_cnt; extern const struct lsm_id *lsm_idlist[]; @@ -200,6 +226,18 @@ extern unsigned long dac_mmap_min_addr; #endif /* + * A "security context" is the text representation of + * the information used by LSMs. + * This structure contains the string, its length, and which LSM + * it is useful for. + */ +struct lsm_context { + char *context; /* Provided by the module */ + u32 len; + int id; /* Identifies the module */ +}; + +/* * Values used in the task_security_ops calls */ /* setuid or setgid, id0 == uid or gid */ @@ -228,7 +266,7 @@ struct request_sock; #define LSM_UNSAFE_NO_NEW_PRIVS 4 #ifdef CONFIG_MMU -extern int mmap_min_addr_handler(struct ctl_table *table, int write, +extern int mmap_min_addr_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); #endif @@ -257,8 +295,32 @@ static inline const char *kernel_load_data_id_str(enum kernel_load_data_id id) return kernel_load_data_str[id]; } +/** + * lsmprop_init - initialize a lsm_prop structure + * @prop: Pointer to the data to initialize + * + * Set all secid for all modules to the specified value. + */ +static inline void lsmprop_init(struct lsm_prop *prop) +{ + memset(prop, 0, sizeof(*prop)); +} + #ifdef CONFIG_SECURITY +/** + * lsmprop_is_set - report if there is a value in the lsm_prop + * @prop: Pointer to the exported LSM data + * + * Returns true if there is a value set, false otherwise + */ +static inline bool lsmprop_is_set(struct lsm_prop *prop) +{ + const struct lsm_prop empty = {}; + + return !!memcmp(prop, &empty, sizeof(*prop)); +} + int call_blocking_lsm_notifier(enum lsm_event event, void *data); int register_blocking_lsm_notifier(struct notifier_block *nb); int unregister_blocking_lsm_notifier(struct notifier_block *nb); @@ -328,15 +390,15 @@ int security_sb_clone_mnt_opts(const struct super_block *oldsb, int security_move_mount(const struct path *from_path, const struct path *to_path); int security_dentry_init_security(struct dentry *dentry, int mode, const struct qstr *name, - const char **xattr_name, void **ctx, - u32 *ctxlen); + const char **xattr_name, + struct lsm_context *lsmcxt); int security_dentry_create_files_as(struct dentry *dentry, int mode, struct qstr *name, const struct cred *old, struct cred *new); int security_path_notify(const struct path *path, u64 mask, unsigned int obj_type); -int security_inode_alloc(struct inode *inode); +int security_inode_alloc(struct inode *inode, gfp_t gfp); void security_inode_free(struct inode *inode); int security_inode_init_security(struct inode *inode, struct inode *dir, const struct qstr *qstr, @@ -396,9 +458,12 @@ int security_inode_getsecurity(struct mnt_idmap *idmap, void **buffer, bool alloc); int security_inode_setsecurity(struct inode *inode, const char *name, const void *value, size_t size, int flags); int security_inode_listsecurity(struct inode *inode, char *buffer, size_t buffer_size); -void security_inode_getsecid(struct inode *inode, u32 *secid); +void security_inode_getlsmprop(struct inode *inode, struct lsm_prop *prop); int security_inode_copy_up(struct dentry *src, struct cred **new); -int security_inode_copy_up_xattr(const char *name); +int security_inode_copy_up_xattr(struct dentry *src, const char *name); +int security_inode_setintegrity(const struct inode *inode, + enum lsm_integrity_type type, const void *value, + size_t size); int security_kernfs_init_security(struct kernfs_node *kn_dir, struct kernfs_node *kn); int security_file_permission(struct file *file, int mask); @@ -429,6 +494,7 @@ void security_cred_free(struct cred *cred); int security_prepare_creds(struct cred *new, const struct cred *old, gfp_t gfp); void security_transfer_creds(struct cred *new, const struct cred *old); void security_cred_getsecid(const struct cred *c, u32 *secid); +void security_cred_getlsmprop(const struct cred *c, struct lsm_prop *prop); int security_kernel_act_as(struct cred *new, u32 secid); int security_kernel_create_files_as(struct cred *new, struct inode *inode); int security_kernel_module_request(char *kmod_name); @@ -448,8 +514,8 @@ int security_task_fix_setgroups(struct cred *new, const struct cred *old); int security_task_setpgid(struct task_struct *p, pid_t pgid); int security_task_getpgid(struct task_struct *p); int security_task_getsid(struct task_struct *p); -void security_current_getsecid_subj(u32 *secid); -void security_task_getsecid_obj(struct task_struct *p, u32 *secid); +void security_current_getlsmprop_subj(struct lsm_prop *prop); +void security_task_getlsmprop_obj(struct task_struct *p, struct lsm_prop *prop); int security_task_setnice(struct task_struct *p, int nice); int security_task_setioprio(struct task_struct *p, int ioprio); int security_task_getioprio(struct task_struct *p); @@ -467,7 +533,7 @@ int security_task_prctl(int option, unsigned long arg2, unsigned long arg3, void security_task_to_inode(struct task_struct *p, struct inode *inode); int security_create_user_ns(const struct cred *cred); int security_ipc_permission(struct kern_ipc_perm *ipcp, short flag); -void security_ipc_getsecid(struct kern_ipc_perm *ipcp, u32 *secid); +void security_ipc_getlsmprop(struct kern_ipc_perm *ipcp, struct lsm_prop *prop); int security_msg_msg_alloc(struct msg_msg *msg); void security_msg_msg_free(struct msg_msg *msg); int security_msg_queue_alloc(struct kern_ipc_perm *msq); @@ -499,18 +565,35 @@ int security_getprocattr(struct task_struct *p, int lsmid, const char *name, int security_setprocattr(int lsmid, const char *name, void *value, size_t size); int security_netlink_send(struct sock *sk, struct sk_buff *skb); int security_ismaclabel(const char *name); -int security_secid_to_secctx(u32 secid, char **secdata, u32 *seclen); +int security_secid_to_secctx(u32 secid, struct lsm_context *cp); +int security_lsmprop_to_secctx(struct lsm_prop *prop, struct lsm_context *cp); int security_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid); -void security_release_secctx(char *secdata, u32 seclen); +void security_release_secctx(struct lsm_context *cp); void security_inode_invalidate_secctx(struct inode *inode); int security_inode_notifysecctx(struct inode *inode, void *ctx, u32 ctxlen); int security_inode_setsecctx(struct dentry *dentry, void *ctx, u32 ctxlen); -int security_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen); +int security_inode_getsecctx(struct inode *inode, struct lsm_context *cp); int security_locked_down(enum lockdown_reason what); int lsm_fill_user_ctx(struct lsm_ctx __user *uctx, u32 *uctx_len, void *val, size_t val_len, u64 id, u64 flags); +int security_bdev_alloc(struct block_device *bdev); +void security_bdev_free(struct block_device *bdev); +int security_bdev_setintegrity(struct block_device *bdev, + enum lsm_integrity_type type, const void *value, + size_t size); #else /* CONFIG_SECURITY */ +/** + * lsmprop_is_set - report if there is a value in the lsm_prop + * @prop: Pointer to the exported LSM data + * + * Returns true if there is a value set, false otherwise + */ +static inline bool lsmprop_is_set(struct lsm_prop *prop) +{ + return false; +} + static inline int call_blocking_lsm_notifier(enum lsm_event event, void *data) { return 0; @@ -634,7 +717,7 @@ static inline int security_settime64(const struct timespec64 *ts, static inline int security_vm_enough_memory_mm(struct mm_struct *mm, long pages) { - return __vm_enough_memory(mm, pages, cap_vm_enough_memory(mm, pages)); + return __vm_enough_memory(mm, pages, !cap_vm_enough_memory(mm, pages)); } static inline int security_bprm_creds_for_exec(struct linux_binprm *bprm) @@ -769,7 +852,7 @@ static inline int security_path_notify(const struct path *path, u64 mask, return 0; } -static inline int security_inode_alloc(struct inode *inode) +static inline int security_inode_alloc(struct inode *inode, gfp_t gfp) { return 0; } @@ -781,8 +864,7 @@ static inline int security_dentry_init_security(struct dentry *dentry, int mode, const struct qstr *name, const char **xattr_name, - void **ctx, - u32 *ctxlen) + struct lsm_context *lsmcxt) { return -EOPNOTSUPP; } @@ -1000,9 +1082,10 @@ static inline int security_inode_listsecurity(struct inode *inode, char *buffer, return 0; } -static inline void security_inode_getsecid(struct inode *inode, u32 *secid) +static inline void security_inode_getlsmprop(struct inode *inode, + struct lsm_prop *prop) { - *secid = 0; + lsmprop_init(prop); } static inline int security_inode_copy_up(struct dentry *src, struct cred **new) @@ -1010,13 +1093,20 @@ static inline int security_inode_copy_up(struct dentry *src, struct cred **new) return 0; } +static inline int security_inode_setintegrity(const struct inode *inode, + enum lsm_integrity_type type, + const void *value, size_t size) +{ + return 0; +} + static inline int security_kernfs_init_security(struct kernfs_node *kn_dir, struct kernfs_node *kn) { return 0; } -static inline int security_inode_copy_up_xattr(const char *name) +static inline int security_inode_copy_up_xattr(struct dentry *src, const char *name) { return -EOPNOTSUPP; } @@ -1145,6 +1235,10 @@ static inline void security_cred_getsecid(const struct cred *c, u32 *secid) *secid = 0; } +static inline void security_cred_getlsmprop(const struct cred *c, + struct lsm_prop *prop) +{ } + static inline int security_kernel_act_as(struct cred *cred, u32 secid) { return 0; @@ -1222,14 +1316,15 @@ static inline int security_task_getsid(struct task_struct *p) return 0; } -static inline void security_current_getsecid_subj(u32 *secid) +static inline void security_current_getlsmprop_subj(struct lsm_prop *prop) { - *secid = 0; + lsmprop_init(prop); } -static inline void security_task_getsecid_obj(struct task_struct *p, u32 *secid) +static inline void security_task_getlsmprop_obj(struct task_struct *p, + struct lsm_prop *prop) { - *secid = 0; + lsmprop_init(prop); } static inline int security_task_setnice(struct task_struct *p, int nice) @@ -1305,9 +1400,10 @@ static inline int security_ipc_permission(struct kern_ipc_perm *ipcp, return 0; } -static inline void security_ipc_getsecid(struct kern_ipc_perm *ipcp, u32 *secid) +static inline void security_ipc_getlsmprop(struct kern_ipc_perm *ipcp, + struct lsm_prop *prop) { - *secid = 0; + lsmprop_init(prop); } static inline int security_msg_msg_alloc(struct msg_msg *msg) @@ -1441,7 +1537,13 @@ static inline int security_ismaclabel(const char *name) return 0; } -static inline int security_secid_to_secctx(u32 secid, char **secdata, u32 *seclen) +static inline int security_secid_to_secctx(u32 secid, struct lsm_context *cp) +{ + return -EOPNOTSUPP; +} + +static inline int security_lsmprop_to_secctx(struct lsm_prop *prop, + struct lsm_context *cp) { return -EOPNOTSUPP; } @@ -1453,7 +1555,7 @@ static inline int security_secctx_to_secid(const char *secdata, return -EOPNOTSUPP; } -static inline void security_release_secctx(char *secdata, u32 seclen) +static inline void security_release_secctx(struct lsm_context *cp) { } @@ -1469,7 +1571,8 @@ static inline int security_inode_setsecctx(struct dentry *dentry, void *ctx, u32 { return -EOPNOTSUPP; } -static inline int security_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen) +static inline int security_inode_getsecctx(struct inode *inode, + struct lsm_context *cp) { return -EOPNOTSUPP; } @@ -1483,6 +1586,23 @@ static inline int lsm_fill_user_ctx(struct lsm_ctx __user *uctx, { return -EOPNOTSUPP; } + +static inline int security_bdev_alloc(struct block_device *bdev) +{ + return 0; +} + +static inline void security_bdev_free(struct block_device *bdev) +{ +} + +static inline int security_bdev_setintegrity(struct block_device *bdev, + enum lsm_integrity_type type, + const void *value, size_t size) +{ + return 0; +} + #endif /* CONFIG_SECURITY */ #if defined(CONFIG_SECURITY) && defined(CONFIG_WATCH_QUEUE) @@ -2048,15 +2168,17 @@ static inline void security_key_post_create_or_update(struct key *keyring, #ifdef CONFIG_AUDIT #ifdef CONFIG_SECURITY -int security_audit_rule_init(u32 field, u32 op, char *rulestr, void **lsmrule); +int security_audit_rule_init(u32 field, u32 op, char *rulestr, void **lsmrule, + gfp_t gfp); int security_audit_rule_known(struct audit_krule *krule); -int security_audit_rule_match(u32 secid, u32 field, u32 op, void *lsmrule); +int security_audit_rule_match(struct lsm_prop *prop, u32 field, u32 op, + void *lsmrule); void security_audit_rule_free(void *lsmrule); #else static inline int security_audit_rule_init(u32 field, u32 op, char *rulestr, - void **lsmrule) + void **lsmrule, gfp_t gfp) { return 0; } @@ -2066,8 +2188,8 @@ static inline int security_audit_rule_known(struct audit_krule *krule) return 0; } -static inline int security_audit_rule_match(u32 secid, u32 field, u32 op, - void *lsmrule) +static inline int security_audit_rule_match(struct lsm_prop *prop, u32 field, + u32 op, void *lsmrule) { return 0; } @@ -2089,6 +2211,7 @@ struct dentry *securityfs_create_symlink(const char *name, const char *target, const struct inode_operations *iops); extern void securityfs_remove(struct dentry *dentry); +extern void securityfs_recursive_remove(struct dentry *dentry); #else /* CONFIG_SECURITYFS */ @@ -2136,7 +2259,7 @@ extern int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, struct bpf_token *token); extern void security_bpf_prog_free(struct bpf_prog *prog); extern int security_bpf_token_create(struct bpf_token *token, union bpf_attr *attr, - struct path *path); + const struct path *path); extern void security_bpf_token_free(struct bpf_token *token); extern int security_bpf_token_cmd(const struct bpf_token *token, enum bpf_cmd cmd); extern int security_bpf_token_capable(const struct bpf_token *token, int cap); @@ -2176,7 +2299,7 @@ static inline void security_bpf_prog_free(struct bpf_prog *prog) { } static inline int security_bpf_token_create(struct bpf_token *token, union bpf_attr *attr, - struct path *path) + const struct path *path) { return 0; } @@ -2255,4 +2378,12 @@ static inline int security_uring_cmd(struct io_uring_cmd *ioucmd) #endif /* CONFIG_SECURITY */ #endif /* CONFIG_IO_URING */ +#ifdef CONFIG_SECURITY +extern void security_initramfs_populated(void); +#else +static inline void security_initramfs_populated(void) +{ +} +#endif /* CONFIG_SECURITY */ + #endif /* ! __LINUX_SECURITY_H */ diff --git a/include/linux/sed-opal.h b/include/linux/sed-opal.h index 2ac50822554e..80f33a93f944 100644 --- a/include/linux/sed-opal.h +++ b/include/linux/sed-opal.h @@ -52,6 +52,7 @@ static inline bool is_sed_ioctl(unsigned int cmd) case IOC_OPAL_GET_GEOMETRY: case IOC_OPAL_DISCOVERY: case IOC_OPAL_REVERT_LSP: + case IOC_OPAL_SET_SID_PW: return true; } return false; diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index 234bcdb1fba4..2fb266ea69fa 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -7,7 +7,6 @@ #include <linux/string_helpers.h> #include <linux/bug.h> #include <linux/mutex.h> -#include <linux/cpumask.h> #include <linux/nodemask.h> #include <linux/fs.h> #include <linux/cred.h> @@ -118,7 +117,18 @@ void seq_vprintf(struct seq_file *m, const char *fmt, va_list args); __printf(2, 3) void seq_printf(struct seq_file *m, const char *fmt, ...); void seq_putc(struct seq_file *m, char c); -void seq_puts(struct seq_file *m, const char *s); +void __seq_puts(struct seq_file *m, const char *s); + +static __always_inline void seq_puts(struct seq_file *m, const char *s) +{ + if (!__builtin_constant_p(*s)) + __seq_puts(m, s); + else if (s[0] && !s[1]) + seq_putc(m, s[0]); + else + seq_write(m, s, __builtin_strlen(s)); +} + void seq_put_decimal_ull_width(struct seq_file *m, const char *delimiter, unsigned long long num, unsigned int width); void seq_put_decimal_ull(struct seq_file *m, const char *delimiter, diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index d90d8ee29d81..5ce48eab7a2a 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -157,7 +157,7 @@ __seqprop_##lockname##_const_ptr(const seqcount_##lockname##_t *s) \ static __always_inline unsigned \ __seqprop_##lockname##_sequence(const seqcount_##lockname##_t *s) \ { \ - unsigned seq = READ_ONCE(s->seqcount.sequence); \ + unsigned seq = smp_load_acquire(&s->seqcount.sequence); \ \ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) \ return seq; \ @@ -170,7 +170,7 @@ __seqprop_##lockname##_sequence(const seqcount_##lockname##_t *s) \ * Re-read the sequence counter since the (possibly \ * preempted) writer made progress. \ */ \ - seq = READ_ONCE(s->seqcount.sequence); \ + seq = smp_load_acquire(&s->seqcount.sequence); \ } \ \ return seq; \ @@ -208,7 +208,7 @@ static inline const seqcount_t *__seqprop_const_ptr(const seqcount_t *s) static inline unsigned __seqprop_sequence(const seqcount_t *s) { - return READ_ONCE(s->sequence); + return smp_load_acquire(&s->sequence); } static inline bool __seqprop_preemptible(const seqcount_t *s) @@ -263,24 +263,16 @@ SEQCOUNT_LOCKNAME(mutex, struct mutex, true, mutex) #define seqprop_assert(s) __seqprop(s, assert)(s) /** - * __read_seqcount_begin() - begin a seqcount_t read section w/o barrier + * __read_seqcount_begin() - begin a seqcount_t read section * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * - * __read_seqcount_begin is like read_seqcount_begin, but has no smp_rmb() - * barrier. Callers should ensure that smp_rmb() or equivalent ordering is - * provided before actually loading any of the variables that are to be - * protected in this critical section. - * - * Use carefully, only in critical code, and comment how the barrier is - * provided. - * * Return: count to be passed to read_seqcount_retry() */ #define __read_seqcount_begin(s) \ ({ \ unsigned __seq; \ \ - while ((__seq = seqprop_sequence(s)) & 1) \ + while (unlikely((__seq = seqprop_sequence(s)) & 1)) \ cpu_relax(); \ \ kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX); \ @@ -293,13 +285,7 @@ SEQCOUNT_LOCKNAME(mutex, struct mutex, true, mutex) * * Return: count to be passed to read_seqcount_retry() */ -#define raw_read_seqcount_begin(s) \ -({ \ - unsigned _seq = __read_seqcount_begin(s); \ - \ - smp_rmb(); \ - _seq; \ -}) +#define raw_read_seqcount_begin(s) __read_seqcount_begin(s) /** * read_seqcount_begin() - begin a seqcount_t read critical section @@ -328,12 +314,34 @@ SEQCOUNT_LOCKNAME(mutex, struct mutex, true, mutex) ({ \ unsigned __seq = seqprop_sequence(s); \ \ - smp_rmb(); \ kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX); \ __seq; \ }) /** + * raw_seqcount_try_begin() - begin a seqcount_t read critical section + * w/o lockdep and w/o counter stabilization + * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants + * @start: count to be passed to read_seqcount_retry() + * + * Similar to raw_seqcount_begin(), except it enables eliding the critical + * section entirely if odd, instead of doing the speculation knowing it will + * fail. + * + * Useful when counter stabilization is more or less equivalent to taking + * the lock and there is a slowpath that does that. + * + * If true, start will be set to the (even) sequence count read. + * + * Return: true when a read critical section is started. + */ +#define raw_seqcount_try_begin(s, start) \ +({ \ + start = raw_read_seqcount(s); \ + !(start & 1); \ +}) + +/** * raw_seqcount_begin() - begin a seqcount_t read critical section w/o * lockdep and w/o counter stabilization * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants @@ -637,6 +645,23 @@ static __always_inline unsigned raw_read_seqcount_latch(const seqcount_latch_t * } /** + * read_seqcount_latch() - pick even/odd latch data copy + * @s: Pointer to seqcount_latch_t + * + * See write_seqcount_latch() for details and a full reader/writer usage + * example. + * + * Return: sequence counter raw value. Use the lowest bit as an index for + * picking which data copy to read. The full counter must then be checked + * with read_seqcount_latch_retry(). + */ +static __always_inline unsigned read_seqcount_latch(const seqcount_latch_t *s) +{ + kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX); + return raw_read_seqcount_latch(s); +} + +/** * raw_read_seqcount_latch_retry() - end a seqcount_latch_t read section * @s: Pointer to seqcount_latch_t * @start: count, from raw_read_seqcount_latch() @@ -651,8 +676,33 @@ raw_read_seqcount_latch_retry(const seqcount_latch_t *s, unsigned start) } /** + * read_seqcount_latch_retry() - end a seqcount_latch_t read section + * @s: Pointer to seqcount_latch_t + * @start: count, from read_seqcount_latch() + * + * Return: true if a read section retry is required, else false + */ +static __always_inline int +read_seqcount_latch_retry(const seqcount_latch_t *s, unsigned start) +{ + kcsan_atomic_next(0); + return raw_read_seqcount_latch_retry(s, start); +} + +/** * raw_write_seqcount_latch() - redirect latch readers to even/odd copy * @s: Pointer to seqcount_latch_t + */ +static __always_inline void raw_write_seqcount_latch(seqcount_latch_t *s) +{ + smp_wmb(); /* prior stores before incrementing "sequence" */ + s->seqcount.sequence++; + smp_wmb(); /* increment "sequence" before following stores */ +} + +/** + * write_seqcount_latch_begin() - redirect latch readers to odd copy + * @s: Pointer to seqcount_latch_t * * The latch technique is a multiversion concurrency control method that allows * queries during non-atomic modifications. If you can guarantee queries never @@ -680,17 +730,11 @@ raw_read_seqcount_latch_retry(const seqcount_latch_t *s, unsigned start) * * void latch_modify(struct latch_struct *latch, ...) * { - * smp_wmb(); // Ensure that the last data[1] update is visible - * latch->seq.sequence++; - * smp_wmb(); // Ensure that the seqcount update is visible - * + * write_seqcount_latch_begin(&latch->seq); * modify(latch->data[0], ...); - * - * smp_wmb(); // Ensure that the data[0] update is visible - * latch->seq.sequence++; - * smp_wmb(); // Ensure that the seqcount update is visible - * + * write_seqcount_latch(&latch->seq); * modify(latch->data[1], ...); + * write_seqcount_latch_end(&latch->seq); * } * * The query will have a form like:: @@ -701,13 +745,13 @@ raw_read_seqcount_latch_retry(const seqcount_latch_t *s, unsigned start) * unsigned seq, idx; * * do { - * seq = raw_read_seqcount_latch(&latch->seq); + * seq = read_seqcount_latch(&latch->seq); * * idx = seq & 0x01; * entry = data_query(latch->data[idx], ...); * * // This includes needed smp_rmb() - * } while (raw_read_seqcount_latch_retry(&latch->seq, seq)); + * } while (read_seqcount_latch_retry(&latch->seq, seq)); * * return entry; * } @@ -731,11 +775,31 @@ raw_read_seqcount_latch_retry(const seqcount_latch_t *s, unsigned start) * When data is a dynamic data structure; one should use regular RCU * patterns to manage the lifetimes of the objects within. */ -static inline void raw_write_seqcount_latch(seqcount_latch_t *s) +static __always_inline void write_seqcount_latch_begin(seqcount_latch_t *s) { - smp_wmb(); /* prior stores before incrementing "sequence" */ - s->seqcount.sequence++; - smp_wmb(); /* increment "sequence" before following stores */ + kcsan_nestable_atomic_begin(); + raw_write_seqcount_latch(s); +} + +/** + * write_seqcount_latch() - redirect latch readers to even copy + * @s: Pointer to seqcount_latch_t + */ +static __always_inline void write_seqcount_latch(seqcount_latch_t *s) +{ + raw_write_seqcount_latch(s); +} + +/** + * write_seqcount_latch_end() - end a seqcount_latch_t write section + * @s: Pointer to seqcount_latch_t + * + * Marks the end of a seqcount_latch_t writer section, after all copies of the + * latch-protected data have been updated. + */ +static __always_inline void write_seqcount_latch_end(seqcount_latch_t *s) +{ + kcsan_nestable_atomic_end(); } #define __SEQLOCK_UNLOCKED(lockname) \ @@ -769,11 +833,7 @@ static inline void raw_write_seqcount_latch(seqcount_latch_t *s) */ static inline unsigned read_seqbegin(const seqlock_t *sl) { - unsigned ret = read_seqcount_begin(&sl->seqcount); - - kcsan_atomic_next(0); /* non-raw usage, assume closing read_seqretry() */ - kcsan_flat_atomic_begin(); - return ret; + return read_seqcount_begin(&sl->seqcount); } /** @@ -789,12 +849,6 @@ static inline unsigned read_seqbegin(const seqlock_t *sl) */ static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start) { - /* - * Assume not nested: read_seqretry() may be called multiple times when - * completing read critical section. - */ - kcsan_flat_atomic_end(); - return read_seqcount_retry(&sl->seqcount, start); } diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index fd59ed2cca53..144de7a7948d 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -161,8 +161,8 @@ struct uart_8250_port { void (*dl_write)(struct uart_8250_port *up, u32 value); struct uart_8250_em485 *em485; - void (*rs485_start_tx)(struct uart_8250_port *); - void (*rs485_stop_tx)(struct uart_8250_port *); + void (*rs485_start_tx)(struct uart_8250_port *up, bool toggle_ier); + void (*rs485_stop_tx)(struct uart_8250_port *up, bool toggle_ier); /* Serial port overrun backoff */ struct delayed_work overrun_backoff; @@ -193,7 +193,7 @@ void serial8250_do_pm(struct uart_port *port, unsigned int state, unsigned int oldstate); void serial8250_do_set_mctrl(struct uart_port *port, unsigned int mctrl); void serial8250_do_set_divisor(struct uart_port *port, unsigned int baud, - unsigned int quot, unsigned int quot_frac); + unsigned int quot); int fsl8250_handle_irq(struct uart_port *port); int serial8250_handle_irq(struct uart_port *port, unsigned int iir); u16 serial8250_rx_chars(struct uart_8250_port *up, u16 lsr); diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 0a0f6e21d40e..743b4afaad4c 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -11,7 +11,8 @@ #include <linux/compiler.h> #include <linux/console.h> #include <linux/interrupt.h> -#include <linux/circ_buf.h> +#include <linux/lockdep.h> +#include <linux/printk.h> #include <linux/spinlock.h> #include <linux/sched.h> #include <linux/tty.h> @@ -504,7 +505,11 @@ struct uart_port { * The remaining bits are serial-core specific and not modifiable by * userspace. */ +#ifdef CONFIG_HAS_IOPORT #define UPF_FOURPORT ((__force upf_t) ASYNC_FOURPORT /* 1 */ ) +#else +#define UPF_FOURPORT 0 +#endif #define UPF_SAK ((__force upf_t) ASYNC_SAK /* 2 */ ) #define UPF_SPD_HI ((__force upf_t) ASYNC_SPD_HI /* 4 */ ) #define UPF_SPD_VHI ((__force upf_t) ASYNC_SPD_VHI /* 5 */ ) @@ -591,6 +596,95 @@ struct uart_port { void *private_data; /* generic platform data pointer */ }; +/* + * Only for console->device_lock()/_unlock() callbacks and internal + * port lock wrapper synchronization. + */ +static inline void __uart_port_lock_irqsave(struct uart_port *up, unsigned long *flags) +{ + spin_lock_irqsave(&up->lock, *flags); +} + +/* + * Only for console->device_lock()/_unlock() callbacks and internal + * port lock wrapper synchronization. + */ +static inline void __uart_port_unlock_irqrestore(struct uart_port *up, unsigned long flags) +{ + spin_unlock_irqrestore(&up->lock, flags); +} + +/** + * uart_port_set_cons - Safely set the @cons field for a uart + * @up: The uart port to set + * @con: The new console to set to + * + * This function must be used to set @up->cons. It uses the port lock to + * synchronize with the port lock wrappers in order to ensure that the console + * cannot change or disappear while another context is holding the port lock. + */ +static inline void uart_port_set_cons(struct uart_port *up, struct console *con) +{ + unsigned long flags; + + __uart_port_lock_irqsave(up, &flags); + up->cons = con; + __uart_port_unlock_irqrestore(up, flags); +} + +/* Only for internal port lock wrapper usage. */ +static inline bool __uart_port_using_nbcon(struct uart_port *up) +{ + lockdep_assert_held_once(&up->lock); + + if (likely(!uart_console(up))) + return false; + + /* + * @up->cons is only modified under the port lock. Therefore it is + * certain that it cannot disappear here. + * + * @up->cons->node is added/removed from the console list under the + * port lock. Therefore it is certain that the registration status + * cannot change here, thus @up->cons->flags can be read directly. + */ + if (hlist_unhashed_lockless(&up->cons->node) || + !(up->cons->flags & CON_NBCON) || + !up->cons->write_atomic) { + return false; + } + + return true; +} + +/* Only for internal port lock wrapper usage. */ +static inline bool __uart_port_nbcon_try_acquire(struct uart_port *up) +{ + if (!__uart_port_using_nbcon(up)) + return true; + + return nbcon_device_try_acquire(up->cons); +} + +/* Only for internal port lock wrapper usage. */ +static inline void __uart_port_nbcon_acquire(struct uart_port *up) +{ + if (!__uart_port_using_nbcon(up)) + return; + + while (!nbcon_device_try_acquire(up->cons)) + cpu_relax(); +} + +/* Only for internal port lock wrapper usage. */ +static inline void __uart_port_nbcon_release(struct uart_port *up) +{ + if (!__uart_port_using_nbcon(up)) + return; + + nbcon_device_release(up->cons); +} + /** * uart_port_lock - Lock the UART port * @up: Pointer to UART port structure @@ -598,6 +692,7 @@ struct uart_port { static inline void uart_port_lock(struct uart_port *up) { spin_lock(&up->lock); + __uart_port_nbcon_acquire(up); } /** @@ -607,6 +702,7 @@ static inline void uart_port_lock(struct uart_port *up) static inline void uart_port_lock_irq(struct uart_port *up) { spin_lock_irq(&up->lock); + __uart_port_nbcon_acquire(up); } /** @@ -617,6 +713,7 @@ static inline void uart_port_lock_irq(struct uart_port *up) static inline void uart_port_lock_irqsave(struct uart_port *up, unsigned long *flags) { spin_lock_irqsave(&up->lock, *flags); + __uart_port_nbcon_acquire(up); } /** @@ -627,7 +724,15 @@ static inline void uart_port_lock_irqsave(struct uart_port *up, unsigned long *f */ static inline bool uart_port_trylock(struct uart_port *up) { - return spin_trylock(&up->lock); + if (!spin_trylock(&up->lock)) + return false; + + if (!__uart_port_nbcon_try_acquire(up)) { + spin_unlock(&up->lock); + return false; + } + + return true; } /** @@ -639,7 +744,15 @@ static inline bool uart_port_trylock(struct uart_port *up) */ static inline bool uart_port_trylock_irqsave(struct uart_port *up, unsigned long *flags) { - return spin_trylock_irqsave(&up->lock, *flags); + if (!spin_trylock_irqsave(&up->lock, *flags)) + return false; + + if (!__uart_port_nbcon_try_acquire(up)) { + spin_unlock_irqrestore(&up->lock, *flags); + return false; + } + + return true; } /** @@ -648,6 +761,7 @@ static inline bool uart_port_trylock_irqsave(struct uart_port *up, unsigned long */ static inline void uart_port_unlock(struct uart_port *up) { + __uart_port_nbcon_release(up); spin_unlock(&up->lock); } @@ -657,6 +771,7 @@ static inline void uart_port_unlock(struct uart_port *up) */ static inline void uart_port_unlock_irq(struct uart_port *up) { + __uart_port_nbcon_release(up); spin_unlock_irq(&up->lock); } @@ -667,6 +782,7 @@ static inline void uart_port_unlock_irq(struct uart_port *up) */ static inline void uart_port_unlock_irqrestore(struct uart_port *up, unsigned long flags) { + __uart_port_nbcon_release(up); spin_unlock_irqrestore(&up->lock, flags); } @@ -699,7 +815,6 @@ struct uart_state { struct tty_port port; enum uart_pm_state pm_state; - struct circ_buf xmit; atomic_t refcount; wait_queue_head_t remove_wait; @@ -723,10 +838,33 @@ struct uart_state { */ static inline void uart_xmit_advance(struct uart_port *up, unsigned int chars) { - struct circ_buf *xmit = &up->state->xmit; + struct tty_port *tport = &up->state->port; + + kfifo_skip_count(&tport->xmit_fifo, chars); + up->icount.tx += chars; +} + +static inline unsigned int uart_fifo_out(struct uart_port *up, + unsigned char *buf, unsigned int chars) +{ + struct tty_port *tport = &up->state->port; + + chars = kfifo_out(&tport->xmit_fifo, buf, chars); + up->icount.tx += chars; + + return chars; +} + +static inline unsigned int uart_fifo_get(struct uart_port *up, + unsigned char *ch) +{ + struct tty_port *tport = &up->state->port; + unsigned int chars; - xmit->tail = (xmit->tail + chars) & (UART_XMIT_SIZE - 1); + chars = kfifo_get(&tport->xmit_fifo, ch); up->icount.tx += chars; + + return chars; } struct module; @@ -764,7 +902,7 @@ enum UART_TX_FLAGS { for_test, for_post) \ ({ \ struct uart_port *__port = (uport); \ - struct circ_buf *xmit = &__port->state->xmit; \ + struct tty_port *__tport = &__port->state->port; \ unsigned int pending; \ \ for (; (for_test) && (tx_ready); (for_post), __port->icount.tx++) { \ @@ -775,22 +913,22 @@ enum UART_TX_FLAGS { continue; \ } \ \ - if (uart_circ_empty(xmit) || uart_tx_stopped(__port)) \ + if (uart_tx_stopped(__port)) \ + break; \ + \ + if (!kfifo_get(&__tport->xmit_fifo, &(ch))) \ break; \ \ - (ch) = xmit->buf[xmit->tail]; \ (put_char); \ - xmit->tail = (xmit->tail + 1) % UART_XMIT_SIZE; \ } \ \ (tx_done); \ \ - pending = uart_circ_chars_pending(xmit); \ + pending = kfifo_len(&__tport->xmit_fifo); \ if (pending < WAKEUP_CHARS) { \ uart_write_wakeup(__port); \ \ - if (!((flags) & UART_TX_NOSTOP) && pending == 0 && \ - __port->ops->tx_empty(__port)) \ + if (!((flags) & UART_TX_NOSTOP) && pending == 0) \ __port->ops->stop_tx(__port); \ } \ \ @@ -830,6 +968,24 @@ enum UART_TX_FLAGS { }) /** + * uart_port_tx_limited_flags -- transmit helper for uart_port with count limiting with flags + * @port: uart port + * @ch: variable to store a character to be written to the HW + * @flags: %UART_TX_NOSTOP or similar + * @count: a limit of characters to send + * @tx_ready: can HW accept more data function + * @put_char: function to write a character + * @tx_done: function to call after the loop is done + * + * See uart_port_tx_limited() for more details. + */ +#define uart_port_tx_limited_flags(port, ch, flags, count, tx_ready, put_char, tx_done) ({ \ + unsigned int __count = (count); \ + __uart_port_tx(port, ch, flags, tx_ready, put_char, tx_done, __count, \ + __count--); \ +}) + +/** * uart_port_tx -- transmit helper for uart_port * @port: uart port * @ch: variable to store a character to be written to the HW @@ -974,15 +1130,6 @@ bool uart_match_port(const struct uart_port *port1, int uart_suspend_port(struct uart_driver *reg, struct uart_port *port); int uart_resume_port(struct uart_driver *reg, struct uart_port *port); -#define uart_circ_empty(circ) ((circ)->head == (circ)->tail) -#define uart_circ_clear(circ) ((circ)->head = (circ)->tail = 0) - -#define uart_circ_chars_pending(circ) \ - (CIRC_CNT((circ)->head, (circ)->tail, UART_XMIT_SIZE)) - -#define uart_circ_chars_free(circ) \ - (CIRC_SPACE((circ)->head, (circ)->tail, UART_XMIT_SIZE)) - static inline int uart_tx_stopped(struct uart_port *port) { struct tty_struct *tty = port->state->port.tty; diff --git a/include/linux/serial_max3100.h b/include/linux/serial_max3100.h deleted file mode 100644 index befd55c08a7c..000000000000 --- a/include/linux/serial_max3100.h +++ /dev/null @@ -1,48 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * - * Copyright (C) 2007 Christian Pellegrin - */ - - -#ifndef _LINUX_SERIAL_MAX3100_H -#define _LINUX_SERIAL_MAX3100_H 1 - - -/** - * struct plat_max3100 - MAX3100 SPI UART platform data - * @loopback: force MAX3100 in loopback - * @crystal: 1 for 3.6864 Mhz, 0 for 1.8432 - * @max3100_hw_suspend: MAX3100 has a shutdown pin. This is a hook - * called on suspend and resume to activate it. - * @poll_time: poll time for CTS signal in ms, 0 disables (so no hw - * flow ctrl is possible but you have less CPU usage) - * - * You should use this structure in your machine description to specify - * how the MAX3100 is connected. Example: - * - * static struct plat_max3100 max3100_plat_data = { - * .loopback = 0, - * .crystal = 0, - * .poll_time = 100, - * }; - * - * static struct spi_board_info spi_board_info[] = { - * { - * .modalias = "max3100", - * .platform_data = &max3100_plat_data, - * .irq = IRQ_EINT12, - * .max_speed_hz = 5*1000*1000, - * .chip_select = 0, - * }, - * }; - * - **/ -struct plat_max3100 { - int loopback; - int crystal; - void (*max3100_hw_suspend) (int suspend); - int poll_time; -}; - -#endif diff --git a/include/linux/serial_s3c.h b/include/linux/serial_s3c.h index 1672cf0810ef..102aa33d956c 100644 --- a/include/linux/serial_s3c.h +++ b/include/linux/serial_s3c.h @@ -246,24 +246,28 @@ S5PV210_UFCON_TXTRIG4 | \ S5PV210_UFCON_RXTRIG4) -#define APPLE_S5L_UCON_RXTO_ENA 9 -#define APPLE_S5L_UCON_RXTHRESH_ENA 12 -#define APPLE_S5L_UCON_TXTHRESH_ENA 13 -#define APPLE_S5L_UCON_RXTO_ENA_MSK (1 << APPLE_S5L_UCON_RXTO_ENA) -#define APPLE_S5L_UCON_RXTHRESH_ENA_MSK (1 << APPLE_S5L_UCON_RXTHRESH_ENA) -#define APPLE_S5L_UCON_TXTHRESH_ENA_MSK (1 << APPLE_S5L_UCON_TXTHRESH_ENA) +#define APPLE_S5L_UCON_RXTO_ENA 9 +#define APPLE_S5L_UCON_RXTO_LEGACY_ENA 11 +#define APPLE_S5L_UCON_RXTHRESH_ENA 12 +#define APPLE_S5L_UCON_TXTHRESH_ENA 13 +#define APPLE_S5L_UCON_RXTO_ENA_MSK BIT(APPLE_S5L_UCON_RXTO_ENA) +#define APPLE_S5L_UCON_RXTO_LEGACY_ENA_MSK BIT(APPLE_S5L_UCON_RXTO_LEGACY_ENA) +#define APPLE_S5L_UCON_RXTHRESH_ENA_MSK BIT(APPLE_S5L_UCON_RXTHRESH_ENA) +#define APPLE_S5L_UCON_TXTHRESH_ENA_MSK BIT(APPLE_S5L_UCON_TXTHRESH_ENA) #define APPLE_S5L_UCON_DEFAULT (S3C2410_UCON_TXIRQMODE | \ S3C2410_UCON_RXIRQMODE | \ S3C2410_UCON_RXFIFO_TOI) #define APPLE_S5L_UCON_MASK (APPLE_S5L_UCON_RXTO_ENA_MSK | \ + APPLE_S5L_UCON_RXTO_LEGACY_ENA_MSK | \ APPLE_S5L_UCON_RXTHRESH_ENA_MSK | \ APPLE_S5L_UCON_TXTHRESH_ENA_MSK) -#define APPLE_S5L_UTRSTAT_RXTHRESH (1<<4) -#define APPLE_S5L_UTRSTAT_TXTHRESH (1<<5) -#define APPLE_S5L_UTRSTAT_RXTO (1<<9) -#define APPLE_S5L_UTRSTAT_ALL_FLAGS (0x3f0) +#define APPLE_S5L_UTRSTAT_RXTO_LEGACY BIT(3) +#define APPLE_S5L_UTRSTAT_RXTHRESH BIT(4) +#define APPLE_S5L_UTRSTAT_TXTHRESH BIT(5) +#define APPLE_S5L_UTRSTAT_RXTO BIT(9) +#define APPLE_S5L_UTRSTAT_ALL_FLAGS GENMASK(9, 3) #ifndef __ASSEMBLY__ diff --git a/include/linux/serial_sci.h b/include/linux/serial_sci.h index 1c89611e0e06..0f2f50b8d28e 100644 --- a/include/linux/serial_sci.h +++ b/include/linux/serial_sci.h @@ -37,6 +37,7 @@ enum { SCIx_SH7705_SCIF_REGTYPE, SCIx_HSCIF_REGTYPE, SCIx_RZ_SCIFA_REGTYPE, + SCIx_RZV2H_SCIF_REGTYPE, SCIx_NR_REGTYPES, }; diff --git a/include/linux/serio.h b/include/linux/serio.h index 7ca41af93b37..69a47674af65 100644 --- a/include/linux/serio.h +++ b/include/linux/serio.h @@ -6,6 +6,7 @@ #define _SERIO_H +#include <linux/cleanup.h> #include <linux/types.h> #include <linux/interrupt.h> #include <linux/list.h> @@ -80,7 +81,7 @@ struct serio_driver { struct device_driver driver; }; -#define to_serio_driver(d) container_of(d, struct serio_driver, driver) +#define to_serio_driver(d) container_of_const(d, struct serio_driver, driver) int serio_open(struct serio *serio, struct serio_driver *drv); void serio_close(struct serio *serio); @@ -161,4 +162,6 @@ static inline void serio_continue_rx(struct serio *serio) spin_unlock_irq(&serio->lock); } +DEFINE_GUARD(serio_pause_rx, struct serio *, serio_pause_rx(_T), serio_continue_rx(_T)) + #endif diff --git a/include/linux/set_memory.h b/include/linux/set_memory.h index 95ac8398ee72..3030d9245f5a 100644 --- a/include/linux/set_memory.h +++ b/include/linux/set_memory.h @@ -8,10 +8,10 @@ #ifdef CONFIG_ARCH_HAS_SET_MEMORY #include <asm/set_memory.h> #else -static inline int set_memory_ro(unsigned long addr, int numpages) { return 0; } -static inline int set_memory_rw(unsigned long addr, int numpages) { return 0; } -static inline int set_memory_x(unsigned long addr, int numpages) { return 0; } -static inline int set_memory_nx(unsigned long addr, int numpages) { return 0; } +static inline int __must_check set_memory_ro(unsigned long addr, int numpages) { return 0; } +static inline int __must_check set_memory_rw(unsigned long addr, int numpages) { return 0; } +static inline int __must_check set_memory_x(unsigned long addr, int numpages) { return 0; } +static inline int __must_check set_memory_nx(unsigned long addr, int numpages) { return 0; } #endif #ifndef set_memory_rox @@ -34,6 +34,12 @@ static inline int set_direct_map_default_noflush(struct page *page) return 0; } +static inline int set_direct_map_valid_noflush(struct page *page, + unsigned nr, bool valid) +{ + return 0; +} + static inline bool kernel_page_present(struct page *page) { return true; diff --git a/include/linux/sfp.h b/include/linux/sfp.h index 9346cd44814d..60c65cea74f6 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -284,6 +284,12 @@ enum { SFF8024_ID_QSFP_8438 = 0x0c, SFF8024_ID_QSFP_8436_8636 = 0x0d, SFF8024_ID_QSFP28_8636 = 0x11, + SFF8024_ID_QSFP_DD = 0x18, + SFF8024_ID_OSFP = 0x19, + SFF8024_ID_DSFP = 0x1B, + SFF8024_ID_QSFP_PLUS_CMIS = 0x1E, + SFF8024_ID_SFP_DD_CMIS = 0x1F, + SFF8024_ID_SFP_PLUS_CMIS = 0x20, SFF8024_ENCODING_UNSPEC = 0x00, SFF8024_ENCODING_8B10B = 0x01, @@ -544,7 +550,7 @@ struct sfp_upstream_ops { void (*link_down)(void *priv); void (*link_up)(void *priv); int (*connect_phy)(void *priv, struct phy_device *); - void (*disconnect_phy)(void *priv); + void (*disconnect_phy)(void *priv, struct phy_device *); }; #if IS_ENABLED(CONFIG_SFP) @@ -554,7 +560,7 @@ bool sfp_may_have_phy(struct sfp_bus *bus, const struct sfp_eeprom_id *id); void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id, unsigned long *support, unsigned long *interfaces); phy_interface_t sfp_select_interface(struct sfp_bus *bus, - unsigned long *link_modes); + const unsigned long *link_modes); int sfp_get_module_info(struct sfp_bus *bus, struct ethtool_modinfo *modinfo); int sfp_get_module_eeprom(struct sfp_bus *bus, struct ethtool_eeprom *ee, @@ -570,6 +576,7 @@ 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); +const char *sfp_get_name(struct sfp_bus *bus); #else static inline int sfp_parse_port(struct sfp_bus *bus, const struct sfp_eeprom_id *id, @@ -592,7 +599,7 @@ static inline void sfp_parse_support(struct sfp_bus *bus, } static inline phy_interface_t sfp_select_interface(struct sfp_bus *bus, - unsigned long *link_modes) + const unsigned long *link_modes) { return PHY_INTERFACE_MODE_NA; } @@ -648,6 +655,11 @@ static inline int sfp_bus_add_upstream(struct sfp_bus *bus, void *upstream, static inline void sfp_bus_del_upstream(struct sfp_bus *bus) { } + +static inline const char *sfp_get_name(struct sfp_bus *bus) +{ + return NULL; +} #endif #endif diff --git a/include/linux/shm.h b/include/linux/shm.h index c55bef0538e5..1d3d3ae958fb 100644 --- a/include/linux/shm.h +++ b/include/linux/shm.h @@ -16,7 +16,6 @@ struct sysv_shm { long do_shmat(int shmid, char __user *shmaddr, int shmflg, unsigned long *addr, unsigned long shmlba); -bool is_file_shm_hugepages(struct file *file); void exit_shm(struct task_struct *task); #define shm_init_task(task) INIT_LIST_HEAD(&(task)->sysvshm.shm_clist) #else @@ -30,10 +29,6 @@ static inline long do_shmat(int shmid, char __user *shmaddr, { return -ENOSYS; } -static inline bool is_file_shm_hugepages(struct file *file) -{ - return false; -} static inline void exit_shm(struct task_struct *task) { } diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 3fb18f7eb73e..0b273a7b9f01 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -42,10 +42,10 @@ struct shmem_inode_info { struct inode vfs_inode; }; -#define SHMEM_FL_USER_VISIBLE FS_FL_USER_VISIBLE +#define SHMEM_FL_USER_VISIBLE (FS_FL_USER_VISIBLE | FS_CASEFOLD_FL) #define SHMEM_FL_USER_MODIFIABLE \ - (FS_IMMUTABLE_FL | FS_APPEND_FL | FS_NODUMP_FL | FS_NOATIME_FL) -#define SHMEM_FL_INHERITED (FS_NODUMP_FL | FS_NOATIME_FL) + (FS_IMMUTABLE_FL | FS_APPEND_FL | FS_NODUMP_FL | FS_NOATIME_FL | FS_CASEFOLD_FL) +#define SHMEM_FL_INHERITED (FS_NODUMP_FL | FS_NOATIME_FL | FS_CASEFOLD_FL) struct shmem_quota_limits { qsize_t usrquota_bhardlimit; /* Default user quota block hard limit */ @@ -111,11 +111,19 @@ extern void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end); int shmem_unuse(unsigned int type); #ifdef CONFIG_TRANSPARENT_HUGEPAGE -extern bool shmem_is_huge(struct inode *inode, pgoff_t index, bool shmem_huge_force, - struct mm_struct *mm, unsigned long vm_flags); +unsigned long shmem_allowable_huge_orders(struct inode *inode, + struct vm_area_struct *vma, pgoff_t index, + loff_t write_end, bool shmem_huge_force); +bool shmem_hpage_pmd_enabled(void); #else -static __always_inline bool shmem_is_huge(struct inode *inode, pgoff_t index, bool shmem_huge_force, - struct mm_struct *mm, unsigned long vm_flags) +static inline unsigned long shmem_allowable_huge_orders(struct inode *inode, + struct vm_area_struct *vma, pgoff_t index, + loff_t write_end, bool shmem_huge_force) +{ + return 0; +} + +static inline bool shmem_hpage_pmd_enabled(void) { return false; } @@ -141,8 +149,8 @@ enum sgp_type { SGP_FALLOC, /* like SGP_WRITE, but make existing page Uptodate */ }; -int shmem_get_folio(struct inode *inode, pgoff_t index, struct folio **foliop, - enum sgp_type sgp); +int shmem_get_folio(struct inode *inode, pgoff_t index, loff_t write_end, + struct folio **foliop, enum sgp_type sgp); struct folio *shmem_read_folio_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp); diff --git a/include/linux/skb_array.h b/include/linux/skb_array.h index e2d45b7cb619..bf178238a308 100644 --- a/include/linux/skb_array.h +++ b/include/linux/skb_array.h @@ -177,10 +177,11 @@ static inline int skb_array_peek_len_any(struct skb_array *a) return PTR_RING_PEEK_CALL_ANY(&a->ring, __skb_array_len_with_tag); } -static inline int skb_array_init(struct skb_array *a, int size, gfp_t gfp) +static inline int skb_array_init_noprof(struct skb_array *a, int size, gfp_t gfp) { - return ptr_ring_init(&a->ring, size, gfp); + return ptr_ring_init_noprof(&a->ring, size, gfp); } +#define skb_array_init(...) alloc_hooks(skb_array_init_noprof(__VA_ARGS__)) static void __skb_array_destroy_skb(void *ptr) { @@ -198,15 +199,18 @@ static inline int skb_array_resize(struct skb_array *a, int size, gfp_t gfp) return ptr_ring_resize(&a->ring, size, gfp, __skb_array_destroy_skb); } -static inline int skb_array_resize_multiple(struct skb_array **rings, - int nrings, unsigned int size, - gfp_t gfp) +static inline int skb_array_resize_multiple_bh_noprof(struct skb_array **rings, + int nrings, + unsigned int size, + gfp_t gfp) { BUILD_BUG_ON(offsetof(struct skb_array, ring)); - return ptr_ring_resize_multiple((struct ptr_ring **)rings, - nrings, size, gfp, - __skb_array_destroy_skb); + return ptr_ring_resize_multiple_bh_noprof((struct ptr_ring **)rings, + nrings, size, gfp, + __skb_array_destroy_skb); } +#define skb_array_resize_multiple_bh(...) \ + alloc_hooks(skb_array_resize_multiple_bh_noprof(__VA_ARGS__)) static inline void skb_array_cleanup(struct skb_array *a) { diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9d24aec064e8..bb2b751d274a 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -31,6 +31,7 @@ #include <linux/in6.h> #include <linux/if_packet.h> #include <linux/llist.h> +#include <linux/page_frag_cache.h> #include <net/flow.h> #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <linux/netfilter/nf_conntrack_common.h> @@ -353,8 +354,6 @@ struct sk_buff; #define MAX_SKB_FRAGS CONFIG_MAX_SKB_FRAGS -extern int sysctl_max_skb_frags; - /* Set skb_shinfo(skb)->gso_size to this in case you want skb_segment to * segment using its current segmentation instead. */ @@ -527,6 +526,13 @@ enum { #define SKBFL_ALL_ZEROCOPY (SKBFL_ZEROCOPY_FRAG | SKBFL_PURE_ZEROCOPY | \ SKBFL_DONT_ORPHAN | SKBFL_MANAGED_FRAG_REFS) +struct ubuf_info_ops { + void (*complete)(struct sk_buff *, struct ubuf_info *, + bool zerocopy_success); + /* has to be compatible with skb_zcopy_set() */ + int (*link_skb)(struct sk_buff *skb, struct ubuf_info *uarg); +}; + /* * The callback notifies userspace to release buffers when skb DMA is done in * lower device, the skb last reference should be 0 when calling this. @@ -536,8 +542,7 @@ enum { * The desc field is used to track userspace buffer index. */ struct ubuf_info { - void (*callback)(struct sk_buff *, struct ubuf_info *, - bool zerocopy_success); + const struct ubuf_info_ops *ops; refcount_t refcnt; u8 flags; }; @@ -603,11 +608,19 @@ struct skb_shared_info { * Warning : all fields before dataref are cleared in __alloc_skb() */ atomic_t dataref; - unsigned int xdp_frags_size; - /* Intermediate layers must ensure that destructor_arg - * remains valid until skb destructor */ - void * destructor_arg; + union { + struct { + u32 xdp_frags_size; + u32 xdp_frags_truesize; + }; + + /* + * Intermediate layers must ensure that destructor_arg + * remains valid until skb destructor. + */ + void *destructor_arg; + }; /* must be last field, see pskb_expand_head() */ skb_frag_t frags[MAX_SKB_FRAGS]; @@ -702,6 +715,13 @@ typedef unsigned int sk_buff_data_t; typedef unsigned char *sk_buff_data_t; #endif +enum skb_tstamp_type { + SKB_CLOCK_REALTIME, + SKB_CLOCK_MONOTONIC, + SKB_CLOCK_TAI, + __SKB_CLOCK_MAX = SKB_CLOCK_TAI, +}; + /** * DOC: Basic sk_buff geometry * @@ -816,13 +836,13 @@ typedef unsigned char *sk_buff_data_t; * @csum_level: indicates the number of consecutive checksums found in * the packet minus one that have been verified as * CHECKSUM_UNNECESSARY (max 3) + * @unreadable: indicates that at least 1 of the fragments in this skb is + * unreadable. * @dst_pending_confirm: need to confirm neighbour * @decrypted: Decrypted SKB * @slow_gro: state present at GRO time, slower prepare step required - * @mono_delivery_time: When set, skb->tstamp has the - * delivery_time in mono clock base (i.e. EDT). Otherwise, the - * skb->tstamp has the (rcv) timestamp at ingress and - * delivery_time at egress. + * @tstamp_type: When set, skb->tstamp has the + * delivery_time clock base of skb->tstamp. * @napi_id: id of the NAPI struct this skb came from * @sender_cpu: (aka @napi_id) source CPU in XPS * @alloc_cpu: CPU which did the skb allocation. @@ -950,7 +970,7 @@ struct sk_buff { /* private: */ __u8 __mono_tc_offset[0]; /* public: */ - __u8 mono_delivery_time:1; /* See SKB_MONO_DELIVERY_TIME_MASK */ + __u8 tstamp_type:2; /* See skb_tstamp_type */ #ifdef CONFIG_NET_XGRESS __u8 tc_at_ingress:1; /* See TC_AT_INGRESS_MASK */ __u8 tc_skip_classify:1; @@ -992,14 +1012,14 @@ struct sk_buff { #ifdef CONFIG_NETFILTER_SKIP_EGRESS __u8 nf_skip_egress:1; #endif -#ifdef CONFIG_TLS_DEVICE +#ifdef CONFIG_SKB_DECRYPTED __u8 decrypted:1; #endif __u8 slow_gro:1; #if IS_ENABLED(CONFIG_IP_SCTP) __u8 csum_not_inet:1; #endif - + __u8 unreadable:1; #if defined(CONFIG_NET_SCHED) || defined(CONFIG_NET_XGRESS) __u16 tc_index; /* traffic control index */ #endif @@ -1080,15 +1100,16 @@ struct sk_buff { #endif #define PKT_TYPE_OFFSET offsetof(struct sk_buff, __pkt_type_offset) -/* if you move tc_at_ingress or mono_delivery_time +/* if you move tc_at_ingress or tstamp_type * around, you also must adapt these constants. */ #ifdef __BIG_ENDIAN_BITFIELD -#define SKB_MONO_DELIVERY_TIME_MASK (1 << 7) -#define TC_AT_INGRESS_MASK (1 << 6) +#define SKB_TSTAMP_TYPE_MASK (3 << 6) +#define SKB_TSTAMP_TYPE_RSHIFT (6) +#define TC_AT_INGRESS_MASK (1 << 5) #else -#define SKB_MONO_DELIVERY_TIME_MASK (1 << 0) -#define TC_AT_INGRESS_MASK (1 << 1) +#define SKB_TSTAMP_TYPE_MASK (3) +#define TC_AT_INGRESS_MASK (1 << 2) #endif #define SKB_BF_MONO_TC_OFFSET offsetof(struct sk_buff, __mono_tc_offset) @@ -1121,7 +1142,7 @@ static inline bool skb_pfmemalloc(const struct sk_buff *skb) * skb_dst - returns skb dst_entry * @skb: buffer * - * Returns skb dst_entry, regardless of reference taken or not. + * Returns: skb dst_entry, regardless of reference taken or not. */ static inline struct dst_entry *skb_dst(const struct sk_buff *skb) { @@ -1174,15 +1195,6 @@ static inline bool skb_dst_is_noref(const struct sk_buff *skb) return (skb->_skb_refdst & SKB_DST_NOREF) && skb_dst(skb); } -/** - * skb_rtable - Returns the skb &rtable - * @skb: buffer - */ -static inline struct rtable *skb_rtable(const struct sk_buff *skb) -{ - return (struct rtable *)skb_dst(skb); -} - /* For mangling skb->pkt_type from user space side from applications * such as nft, tc, etc, we only allow a conservative subset of * possible pkt_types to be set. @@ -1218,13 +1230,13 @@ static inline bool skb_wifi_acked_valid(const struct sk_buff *skb) * skb_unref - decrement the skb's reference count * @skb: buffer * - * Returns true if we can free the skb. + * Returns: true if we can free the skb. */ static inline bool skb_unref(struct sk_buff *skb) { if (unlikely(!skb)) return false; - if (likely(refcount_read(&skb->users) == 1)) + if (!IS_ENABLED(CONFIG_DEBUG_NET) && likely(refcount_read(&skb->users) == 1)) smp_rmb(); else if (likely(!refcount_dec_and_test(&skb->users))) return false; @@ -1250,8 +1262,14 @@ static inline bool skb_data_unref(const struct sk_buff *skb, return true; } -void __fix_address -kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason); +void __fix_address sk_skb_reason_drop(struct sock *sk, struct sk_buff *skb, + enum skb_drop_reason reason); + +static inline void +kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason) +{ + sk_skb_reason_drop(NULL, skb, reason); +} /** * kfree_skb - free an sk_buff with 'NOT_SPECIFIED' reason @@ -1334,7 +1352,7 @@ struct sk_buff_fclones { * @sk: socket * @skb: buffer * - * Returns true if skb is a fast clone, and its clone is not freed. + * Returns: true if skb is a fast clone, and its clone is not freed. * Some drivers call skb_orphan() in their ndo_start_xmit(), * so we also check that didn't happen. */ @@ -1426,6 +1444,7 @@ void skb_prepare_seq_read(struct sk_buff *skb, unsigned int from, unsigned int skb_seq_read(unsigned int consumed, const u8 **data, struct skb_seq_state *st); void skb_abort_seq_read(struct skb_seq_state *st); +int skb_copy_seq_read(struct skb_seq_state *st, int offset, void *to, int len); unsigned int skb_find_text(struct sk_buff *skb, unsigned int from, unsigned int to, struct ts_config *config); @@ -1497,8 +1516,14 @@ __skb_set_sw_hash(struct sk_buff *skb, __u32 hash, bool is_l4) __skb_set_hash(skb, hash, true, is_l4); } -void __skb_get_hash(struct sk_buff *skb); -u32 __skb_get_hash_symmetric(const struct sk_buff *skb); +u32 __skb_get_hash_symmetric_net(const struct net *net, const struct sk_buff *skb); + +static inline u32 __skb_get_hash_symmetric(const struct sk_buff *skb) +{ + return __skb_get_hash_symmetric_net(NULL, skb); +} + +void __skb_get_hash_net(const struct net *net, struct sk_buff *skb); u32 skb_get_poff(const struct sk_buff *skb); u32 __skb_get_poff(const struct sk_buff *skb, const void *data, const struct flow_keys_basic *keys, int hlen); @@ -1577,10 +1602,18 @@ void skb_flow_dissect_hash(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container); +static inline __u32 skb_get_hash_net(const struct net *net, struct sk_buff *skb) +{ + if (!skb->l4_hash && !skb->sw_hash) + __skb_get_hash_net(net, skb); + + return skb->hash; +} + static inline __u32 skb_get_hash(struct sk_buff *skb) { if (!skb->l4_hash && !skb->sw_hash) - __skb_get_hash(skb); + __skb_get_hash_net(NULL, skb); return skb->hash; } @@ -1615,17 +1648,26 @@ static inline void skb_copy_hash(struct sk_buff *to, const struct sk_buff *from) static inline int skb_cmp_decrypted(const struct sk_buff *skb1, const struct sk_buff *skb2) { -#ifdef CONFIG_TLS_DEVICE +#ifdef CONFIG_SKB_DECRYPTED return skb2->decrypted - skb1->decrypted; #else return 0; #endif } +static inline bool skb_is_decrypted(const struct sk_buff *skb) +{ +#ifdef CONFIG_SKB_DECRYPTED + return skb->decrypted; +#else + return false; +#endif +} + static inline void skb_copy_decrypted(struct sk_buff *to, const struct sk_buff *from) { -#ifdef CONFIG_TLS_DEVICE +#ifdef CONFIG_SKB_DECRYPTED to->decrypted = from->decrypted; #endif } @@ -1662,18 +1704,20 @@ static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset) } #endif +extern const struct ubuf_info_ops msg_zerocopy_ubuf_ops; + struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, struct ubuf_info *uarg); void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref); -void msg_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *uarg, - bool success); - int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk, struct sk_buff *skb, struct iov_iter *from, size_t length); +int zerocopy_fill_skb_from_iter(struct sk_buff *skb, + struct iov_iter *from, size_t length); + static inline int skb_zerocopy_iter_dgram(struct sk_buff *skb, struct msghdr *msg, int len) { @@ -1757,13 +1801,13 @@ static inline void *skb_zcopy_get_nouarg(struct sk_buff *skb) static inline void net_zcopy_put(struct ubuf_info *uarg) { if (uarg) - uarg->callback(NULL, uarg, true); + uarg->ops->complete(NULL, uarg, true); } static inline void net_zcopy_put_abort(struct ubuf_info *uarg, bool have_uref) { if (uarg) { - if (uarg->callback == msg_zerocopy_callback) + if (uarg->ops == &msg_zerocopy_ubuf_ops) msg_zerocopy_put_abort(uarg, have_uref); else if (have_uref) net_zcopy_put(uarg); @@ -1777,7 +1821,7 @@ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy_success) if (uarg) { if (!skb_zcopy_is_nouarg(skb)) - uarg->callback(skb, uarg, zerocopy_success); + uarg->ops->complete(skb, uarg, zerocopy_success); skb_shinfo(skb)->flags &= ~SKBFL_ALL_ZEROCOPY; } @@ -1791,6 +1835,12 @@ static inline void skb_zcopy_downgrade_managed(struct sk_buff *skb) __skb_zcopy_downgrade_managed(skb); } +/* Return true if frags in this skb are readable by the host. */ +static inline bool skb_frags_readable(const struct sk_buff *skb) +{ + return !skb->unreadable; +} + static inline void skb_mark_not_on_list(struct sk_buff *skb) { skb->next = NULL; @@ -2507,10 +2557,17 @@ static inline void skb_len_add(struct sk_buff *skb, int delta) static inline void __skb_fill_netmem_desc(struct sk_buff *skb, int i, netmem_ref netmem, int off, int size) { - struct page *page = netmem_to_page(netmem); + struct page *page; __skb_fill_netmem_desc_noacc(skb_shinfo(skb), i, netmem, off, size); + if (netmem_is_net_iov(netmem)) { + skb->unreadable = true; + return; + } + + page = netmem_to_page(netmem); + /* Propagate page pfmemalloc to the skb if we can. The problem is * that not all callers have unique ownership of the page but rely * on page_is_pfmemalloc doing the right thing(tm). @@ -2633,6 +2690,12 @@ static inline void skb_assert_len(struct sk_buff *skb) #endif /* CONFIG_DEBUG_NET */ } +#if defined(CONFIG_FAIL_SKB_REALLOC) +void skb_might_realloc(struct sk_buff *skb); +#else +static inline void skb_might_realloc(struct sk_buff *skb) {} +#endif + /* * Add data to an sk_buff */ @@ -2733,6 +2796,7 @@ static inline enum skb_drop_reason pskb_may_pull_reason(struct sk_buff *skb, unsigned int len) { DEBUG_NET_WARN_ON_ONCE(len > INT_MAX); + skb_might_realloc(skb); if (likely(len <= skb_headlen(skb))) return SKB_NOT_DROPPED_YET; @@ -2861,9 +2925,19 @@ static inline void skb_reset_inner_headers(struct sk_buff *skb) skb->inner_transport_header = skb->transport_header; } +static inline int skb_mac_header_was_set(const struct sk_buff *skb) +{ + return skb->mac_header != (typeof(skb->mac_header))~0U; +} + static inline void skb_reset_mac_len(struct sk_buff *skb) { - skb->mac_len = skb->network_header - skb->mac_header; + if (!skb_mac_header_was_set(skb)) { + DEBUG_NET_WARN_ON_ONCE(1); + skb->mac_len = 0; + } else { + skb->mac_len = skb->network_header - skb->mac_header; + } } static inline unsigned char *skb_inner_transport_header(const struct sk_buff @@ -2879,7 +2953,10 @@ static inline int skb_inner_transport_offset(const struct sk_buff *skb) static inline void skb_reset_inner_transport_header(struct sk_buff *skb) { - skb->inner_transport_header = skb->data - skb->head; + long offset = skb->data - skb->head; + + DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->inner_transport_header))offset); + skb->inner_transport_header = offset; } static inline void skb_set_inner_transport_header(struct sk_buff *skb, @@ -2896,7 +2973,10 @@ static inline unsigned char *skb_inner_network_header(const struct sk_buff *skb) static inline void skb_reset_inner_network_header(struct sk_buff *skb) { - skb->inner_network_header = skb->data - skb->head; + long offset = skb->data - skb->head; + + DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->inner_network_header))offset); + skb->inner_network_header = offset; } static inline void skb_set_inner_network_header(struct sk_buff *skb, @@ -2918,7 +2998,10 @@ static inline unsigned char *skb_inner_mac_header(const struct sk_buff *skb) static inline void skb_reset_inner_mac_header(struct sk_buff *skb) { - skb->inner_mac_header = skb->data - skb->head; + long offset = skb->data - skb->head; + + DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->inner_mac_header))offset); + skb->inner_mac_header = offset; } static inline void skb_set_inner_mac_header(struct sk_buff *skb, @@ -2940,7 +3023,10 @@ static inline unsigned char *skb_transport_header(const struct sk_buff *skb) static inline void skb_reset_transport_header(struct sk_buff *skb) { - skb->transport_header = skb->data - skb->head; + long offset = skb->data - skb->head; + + DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->transport_header))offset); + skb->transport_header = offset; } static inline void skb_set_transport_header(struct sk_buff *skb, @@ -2957,7 +3043,10 @@ static inline unsigned char *skb_network_header(const struct sk_buff *skb) static inline void skb_reset_network_header(struct sk_buff *skb) { - skb->network_header = skb->data - skb->head; + long offset = skb->data - skb->head; + + DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->network_header))offset); + skb->network_header = offset; } static inline void skb_set_network_header(struct sk_buff *skb, const int offset) @@ -2966,11 +3055,6 @@ static inline void skb_set_network_header(struct sk_buff *skb, const int offset) skb->network_header += offset; } -static inline int skb_mac_header_was_set(const struct sk_buff *skb) -{ - return skb->mac_header != (typeof(skb->mac_header))~0U; -} - static inline unsigned char *skb_mac_header(const struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE(!skb_mac_header_was_set(skb)); @@ -2995,7 +3079,10 @@ static inline void skb_unset_mac_header(struct sk_buff *skb) static inline void skb_reset_mac_header(struct sk_buff *skb) { - skb->mac_header = skb->data - skb->head; + long offset = skb->data - skb->head; + + DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->mac_header))offset); + skb->mac_header = offset; } static inline void skb_set_mac_header(struct sk_buff *skb, const int offset) @@ -3031,6 +3118,21 @@ static inline void skb_mac_header_rebuild(struct sk_buff *skb) } } +/* Move the full mac header up to current network_header. + * Leaves skb->data pointing at offset skb->mac_len into the mac_header. + * Must be provided the complete mac header length. + */ +static inline void skb_mac_header_rebuild_full(struct sk_buff *skb, u32 full_mac_len) +{ + if (skb_mac_header_was_set(skb)) { + const unsigned char *old_mac = skb_mac_header(skb); + + skb_set_mac_header(skb, -full_mac_len); + memmove(skb_mac_header(skb), old_mac, full_mac_len); + __skb_push(skb, full_mac_len - skb->mac_len); + } +} + static inline int skb_checksum_start_offset(const struct sk_buff *skb) { return skb->csum_start - skb_headroom(skb); @@ -3067,9 +3169,15 @@ static inline int skb_inner_network_offset(const struct sk_buff *skb) return skb_inner_network_header(skb) - skb->data; } +static inline enum skb_drop_reason +pskb_network_may_pull_reason(struct sk_buff *skb, unsigned int len) +{ + return pskb_may_pull_reason(skb, skb_network_offset(skb) + len); +} + static inline int pskb_network_may_pull(struct sk_buff *skb, unsigned int len) { - return pskb_may_pull(skb, skb_network_offset(skb) + len); + return pskb_network_may_pull_reason(skb, len) == SKB_NOT_DROPPED_YET; } /* @@ -3147,6 +3255,7 @@ static inline int __pskb_trim(struct sk_buff *skb, unsigned int len) static inline int pskb_trim(struct sk_buff *skb, unsigned int len) { + skb_might_realloc(skb); return (len < skb->len) ? __pskb_trim(skb, len) : 0; } @@ -3350,13 +3459,7 @@ static inline void *napi_alloc_frag_align(unsigned int fragsz, return __napi_alloc_frag_align(fragsz, -align); } -struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, - unsigned int length, gfp_t gfp_mask); -static inline struct sk_buff *napi_alloc_skb(struct napi_struct *napi, - unsigned int length) -{ - return __napi_alloc_skb(napi, length, GFP_ATOMIC); -} +struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int length); void napi_consume_skb(struct sk_buff *skb, int budget); void napi_skb_free_stolen_head(struct sk_buff *skb); @@ -3371,7 +3474,7 @@ void __napi_kfree_skb(struct sk_buff *skb, enum skb_drop_reason reason); * * %NULL is returned if there is no free memory. */ -static inline struct page *__dev_alloc_pages(gfp_t gfp_mask, +static inline struct page *__dev_alloc_pages_noprof(gfp_t gfp_mask, unsigned int order) { /* This piece of code contains several assumptions. @@ -3384,13 +3487,15 @@ static inline struct page *__dev_alloc_pages(gfp_t gfp_mask, */ gfp_mask |= __GFP_COMP | __GFP_MEMALLOC; - return alloc_pages_node(NUMA_NO_NODE, gfp_mask, order); + return alloc_pages_node_noprof(NUMA_NO_NODE, gfp_mask, order); } +#define __dev_alloc_pages(...) alloc_hooks(__dev_alloc_pages_noprof(__VA_ARGS__)) -static inline struct page *dev_alloc_pages(unsigned int order) -{ - return __dev_alloc_pages(GFP_ATOMIC | __GFP_NOWARN, order); -} +/* + * This specialized allocator has to be a macro for its allocations to be + * accounted separately (to have a separate alloc_tag). + */ +#define dev_alloc_pages(_order) __dev_alloc_pages(GFP_ATOMIC | __GFP_NOWARN, _order) /** * __dev_alloc_page - allocate a page for network Rx @@ -3400,15 +3505,17 @@ static inline struct page *dev_alloc_pages(unsigned int order) * * %NULL is returned if there is no free memory. */ -static inline struct page *__dev_alloc_page(gfp_t gfp_mask) +static inline struct page *__dev_alloc_page_noprof(gfp_t gfp_mask) { - return __dev_alloc_pages(gfp_mask, 0); + return __dev_alloc_pages_noprof(gfp_mask, 0); } +#define __dev_alloc_page(...) alloc_hooks(__dev_alloc_page_noprof(__VA_ARGS__)) -static inline struct page *dev_alloc_page(void) -{ - return dev_alloc_pages(0); -} +/* + * This specialized allocator has to be a macro for its allocations to be + * accounted separately (to have a separate alloc_tag). + */ +#define dev_alloc_page() dev_alloc_pages(0) /** * dev_page_is_reusable - check whether a page can be reused for network Rx @@ -3417,7 +3524,7 @@ static inline struct page *dev_alloc_page(void) * A page shouldn't be considered for reusing/recycling if it was allocated * under memory pressure or at a distant memory node. * - * Returns false if this page should be returned to page allocator, true + * Returns: false if this page should be returned to page allocator, true * otherwise. */ static inline bool dev_page_is_reusable(const struct page *page) @@ -3478,105 +3585,70 @@ static inline void skb_frag_off_copy(skb_frag_t *fragto, fragto->offset = fragfrom->offset; } -/** - * skb_frag_page - retrieve the page referred to by a paged fragment - * @frag: the paged fragment - * - * Returns the &struct page associated with @frag. - */ -static inline struct page *skb_frag_page(const skb_frag_t *frag) +/* Return: true if the skb_frag contains a net_iov. */ +static inline bool skb_frag_is_net_iov(const skb_frag_t *frag) { - return netmem_to_page(frag->netmem); -} - -/** - * __skb_frag_ref - take an addition reference on a paged fragment. - * @frag: the paged fragment - * - * Takes an additional reference on the paged fragment @frag. - */ -static inline void __skb_frag_ref(skb_frag_t *frag) -{ - get_page(skb_frag_page(frag)); + return netmem_is_net_iov(frag->netmem); } /** - * skb_frag_ref - take an addition reference on a paged fragment of an skb. - * @skb: the buffer - * @f: the fragment offset. + * skb_frag_net_iov - retrieve the net_iov referred to by fragment + * @frag: the fragment * - * Takes an additional reference on the @f'th paged fragment of @skb. + * Return: the &struct net_iov associated with @frag. Returns NULL if this + * frag has no associated net_iov. */ -static inline void skb_frag_ref(struct sk_buff *skb, int f) -{ - __skb_frag_ref(&skb_shinfo(skb)->frags[f]); -} - -int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb, - unsigned int headroom); -int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb, - struct bpf_prog *prog); -bool napi_pp_put_page(struct page *page, bool napi_safe); - -static inline void -skb_page_unref(const struct sk_buff *skb, struct page *page, bool napi_safe) -{ -#ifdef CONFIG_PAGE_POOL - if (skb->pp_recycle && napi_pp_put_page(page, napi_safe)) - return; -#endif - put_page(page); -} - -static inline void -napi_frag_unref(skb_frag_t *frag, bool recycle, bool napi_safe) +static inline struct net_iov *skb_frag_net_iov(const skb_frag_t *frag) { - struct page *page = skb_frag_page(frag); + if (!skb_frag_is_net_iov(frag)) + return NULL; -#ifdef CONFIG_PAGE_POOL - if (recycle && napi_pp_put_page(page, napi_safe)) - return; -#endif - put_page(page); + return netmem_to_net_iov(frag->netmem); } /** - * __skb_frag_unref - release a reference on a paged fragment. + * skb_frag_page - retrieve the page referred to by a paged fragment * @frag: the paged fragment - * @recycle: recycle the page if allocated via page_pool * - * Releases a reference on the paged fragment @frag - * or recycles the page via the page_pool API. + * Return: the &struct page associated with @frag. Returns NULL if this frag + * has no associated page. */ -static inline void __skb_frag_unref(skb_frag_t *frag, bool recycle) +static inline struct page *skb_frag_page(const skb_frag_t *frag) { - napi_frag_unref(frag, recycle, false); + if (skb_frag_is_net_iov(frag)) + return NULL; + + return netmem_to_page(frag->netmem); } /** - * skb_frag_unref - release a reference on a paged fragment of an skb. - * @skb: the buffer - * @f: the fragment offset + * skb_frag_netmem - retrieve the netmem referred to by a fragment + * @frag: the fragment * - * Releases a reference on the @f'th paged fragment of @skb. + * Return: the &netmem_ref associated with @frag. */ -static inline void skb_frag_unref(struct sk_buff *skb, int f) +static inline netmem_ref skb_frag_netmem(const skb_frag_t *frag) { - struct skb_shared_info *shinfo = skb_shinfo(skb); - - if (!skb_zcopy_managed(skb)) - __skb_frag_unref(&shinfo->frags[f], skb->pp_recycle); + return frag->netmem; } +int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb, + unsigned int headroom); +int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb, + const struct bpf_prog *prog); + /** * skb_frag_address - gets the address of the data contained in a paged fragment * @frag: the paged fragment buffer * - * Returns the address of the data within @frag. The page must already + * Returns: the address of the data within @frag. The page must already * be mapped. */ static inline void *skb_frag_address(const skb_frag_t *frag) { + if (!skb_frag_page(frag)) + return NULL; + return page_address(skb_frag_page(frag)) + skb_frag_off(frag); } @@ -3584,7 +3656,7 @@ static inline void *skb_frag_address(const skb_frag_t *frag) * skb_frag_address_safe - gets the address of the data contained in a paged fragment * @frag: the paged fragment buffer * - * Returns the address of the data within @frag. Checks that the page + * Returns: the address of the data within @frag. Checks that the page * is mapped and returns %NULL otherwise. */ static inline void *skb_frag_address_safe(const skb_frag_t *frag) @@ -3610,7 +3682,7 @@ static inline void skb_frag_page_copy(skb_frag_t *fragto, bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t prio); /** - * skb_frag_dma_map - maps a paged fragment via the DMA API + * __skb_frag_dma_map - maps a paged fragment via the DMA API * @dev: the device to map the fragment to * @frag: the paged fragment to map * @offset: the offset within the fragment (starting at the @@ -3620,15 +3692,36 @@ bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t prio); * * Maps the page associated with @frag to @device. */ -static inline dma_addr_t skb_frag_dma_map(struct device *dev, - const skb_frag_t *frag, - size_t offset, size_t size, - enum dma_data_direction dir) +static inline dma_addr_t __skb_frag_dma_map(struct device *dev, + const skb_frag_t *frag, + size_t offset, size_t size, + enum dma_data_direction dir) { return dma_map_page(dev, skb_frag_page(frag), skb_frag_off(frag) + offset, size, dir); } +#define skb_frag_dma_map(dev, frag, ...) \ + CONCATENATE(_skb_frag_dma_map, \ + COUNT_ARGS(__VA_ARGS__))(dev, frag, ##__VA_ARGS__) + +#define __skb_frag_dma_map1(dev, frag, offset, uf, uo) ({ \ + const skb_frag_t *uf = (frag); \ + size_t uo = (offset); \ + \ + __skb_frag_dma_map(dev, uf, uo, skb_frag_size(uf) - uo, \ + DMA_TO_DEVICE); \ +}) +#define _skb_frag_dma_map1(dev, frag, offset) \ + __skb_frag_dma_map1(dev, frag, offset, __UNIQUE_ID(frag_), \ + __UNIQUE_ID(offset_)) +#define _skb_frag_dma_map0(dev, frag) \ + _skb_frag_dma_map1(dev, frag, 0) +#define _skb_frag_dma_map2(dev, frag, offset, size) \ + __skb_frag_dma_map(dev, frag, offset, size, DMA_TO_DEVICE) +#define _skb_frag_dma_map3(dev, frag, offset, size, dir) \ + __skb_frag_dma_map(dev, frag, offset, size, dir) + static inline struct sk_buff *pskb_copy(struct sk_buff *skb, gfp_t gfp_mask) { @@ -3826,7 +3919,7 @@ static inline int skb_linearize(struct sk_buff *skb) * skb_has_shared_frag - can any frag be overwritten * @skb: buffer to test * - * Return true if the skb has at least one frag that might be modified + * Return: true if the skb has at least one frag that might be modified * by an external entity (as in vmsplice()/sendfile()) */ static inline bool skb_has_shared_frag(const struct sk_buff *skb) @@ -3938,6 +4031,7 @@ int pskb_trim_rcsum_slow(struct sk_buff *skb, unsigned int len); static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len) { + skb_might_realloc(skb); if (likely(len >= skb->len)) return 0; return pskb_trim_rcsum_slow(skb, len); @@ -4058,12 +4152,6 @@ int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset, struct iov_iter *from, int len); int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *frm); void skb_free_datagram(struct sock *sk, struct sk_buff *skb); -void __skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb, int len); -static inline void skb_free_datagram_locked(struct sock *sk, - struct sk_buff *skb) -{ - __skb_free_datagram_locked(sk, skb, 0); -} int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags); int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len); int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len); @@ -4252,7 +4340,7 @@ static inline void skb_get_new_timestampns(const struct sk_buff *skb, static inline void __net_timestamp(struct sk_buff *skb) { skb->tstamp = ktime_get_real(); - skb->mono_delivery_time = 0; + skb->tstamp_type = SKB_CLOCK_REALTIME; } static inline ktime_t net_timedelta(ktime_t t) @@ -4261,10 +4349,36 @@ static inline ktime_t net_timedelta(ktime_t t) } static inline void skb_set_delivery_time(struct sk_buff *skb, ktime_t kt, - bool mono) + u8 tstamp_type) { skb->tstamp = kt; - skb->mono_delivery_time = kt && mono; + + if (kt) + skb->tstamp_type = tstamp_type; + else + skb->tstamp_type = SKB_CLOCK_REALTIME; +} + +static inline void skb_set_delivery_type_by_clockid(struct sk_buff *skb, + ktime_t kt, clockid_t clockid) +{ + u8 tstamp_type = SKB_CLOCK_REALTIME; + + switch (clockid) { + case CLOCK_REALTIME: + break; + case CLOCK_MONOTONIC: + tstamp_type = SKB_CLOCK_MONOTONIC; + break; + case CLOCK_TAI: + tstamp_type = SKB_CLOCK_TAI; + break; + default: + WARN_ON_ONCE(1); + kt = 0; + } + + skb_set_delivery_time(skb, kt, tstamp_type); } DECLARE_STATIC_KEY_FALSE(netstamp_needed_key); @@ -4274,8 +4388,8 @@ DECLARE_STATIC_KEY_FALSE(netstamp_needed_key); */ static inline void skb_clear_delivery_time(struct sk_buff *skb) { - if (skb->mono_delivery_time) { - skb->mono_delivery_time = 0; + if (skb->tstamp_type) { + skb->tstamp_type = SKB_CLOCK_REALTIME; if (static_branch_unlikely(&netstamp_needed_key)) skb->tstamp = ktime_get_real(); else @@ -4285,7 +4399,7 @@ static inline void skb_clear_delivery_time(struct sk_buff *skb) static inline void skb_clear_tstamp(struct sk_buff *skb) { - if (skb->mono_delivery_time) + if (skb->tstamp_type) return; skb->tstamp = 0; @@ -4293,7 +4407,7 @@ static inline void skb_clear_tstamp(struct sk_buff *skb) static inline ktime_t skb_tstamp(const struct sk_buff *skb) { - if (skb->mono_delivery_time) + if (skb->tstamp_type) return 0; return skb->tstamp; @@ -4301,7 +4415,7 @@ static inline ktime_t skb_tstamp(const struct sk_buff *skb) static inline ktime_t skb_tstamp_cond(const struct sk_buff *skb, bool cond) { - if (!skb->mono_delivery_time && skb->tstamp) + if (skb->tstamp_type != SKB_CLOCK_MONOTONIC && skb->tstamp) return skb->tstamp; if (static_branch_unlikely(&netstamp_needed_key) || cond) @@ -4527,7 +4641,7 @@ static inline void __skb_reset_checksum_unnecessary(struct sk_buff *skb) /* Check if we need to perform checksum complete validation. * - * Returns true if checksum complete is needed, false otherwise + * Returns: true if checksum complete is needed, false otherwise * (either checksum is unnecessary or zero checksum is allowed). */ static inline bool __skb_checksum_validate_needed(struct sk_buff *skb, diff --git a/include/linux/skbuff_ref.h b/include/linux/skbuff_ref.h new file mode 100644 index 000000000000..0f3c58007488 --- /dev/null +++ b/include/linux/skbuff_ref.h @@ -0,0 +1,74 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Skb ref helpers. + * + */ + +#ifndef _LINUX_SKBUFF_REF_H +#define _LINUX_SKBUFF_REF_H + +#include <linux/skbuff.h> + +/** + * __skb_frag_ref - take an addition reference on a paged fragment. + * @frag: the paged fragment + * + * Takes an additional reference on the paged fragment @frag. + */ +static inline void __skb_frag_ref(skb_frag_t *frag) +{ + get_page(skb_frag_page(frag)); +} + +/** + * skb_frag_ref - take an addition reference on a paged fragment of an skb. + * @skb: the buffer + * @f: the fragment offset. + * + * Takes an additional reference on the @f'th paged fragment of @skb. + */ +static inline void skb_frag_ref(struct sk_buff *skb, int f) +{ + __skb_frag_ref(&skb_shinfo(skb)->frags[f]); +} + +bool napi_pp_put_page(netmem_ref netmem); + +static inline void skb_page_unref(netmem_ref netmem, bool recycle) +{ +#ifdef CONFIG_PAGE_POOL + if (recycle && napi_pp_put_page(netmem)) + return; +#endif + put_page(netmem_to_page(netmem)); +} + +/** + * __skb_frag_unref - release a reference on a paged fragment. + * @frag: the paged fragment + * @recycle: recycle the page if allocated via page_pool + * + * Releases a reference on the paged fragment @frag + * or recycles the page via the page_pool API. + */ +static inline void __skb_frag_unref(skb_frag_t *frag, bool recycle) +{ + skb_page_unref(skb_frag_netmem(frag), recycle); +} + +/** + * skb_frag_unref - release a reference on a paged fragment of an skb. + * @skb: the buffer + * @f: the fragment offset + * + * Releases a reference on the @f'th paged fragment of @skb. + */ +static inline void skb_frag_unref(struct sk_buff *skb, int f) +{ + struct skb_shared_info *shinfo = skb_shinfo(skb); + + if (!skb_zcopy_managed(skb)) + __skb_frag_unref(&shinfo->frags[f], skb->pp_recycle); +} + +#endif /* _LINUX_SKBUFF_REF_H */ diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index e65ec3fd2799..2cbe0c22a32f 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -58,6 +58,10 @@ struct sk_psock_progs { struct bpf_prog *stream_parser; struct bpf_prog *stream_verdict; struct bpf_prog *skb_verdict; + struct bpf_link *msg_parser_link; + struct bpf_link *stream_parser_link; + struct bpf_link *stream_verdict_link; + struct bpf_link *skb_verdict_link; }; enum sk_psock_state_bits { @@ -313,17 +317,22 @@ static inline void sock_drop(struct sock *sk, struct sk_buff *skb) kfree_skb(skb); } -static inline void sk_psock_queue_msg(struct sk_psock *psock, +static inline bool sk_psock_queue_msg(struct sk_psock *psock, struct sk_msg *msg) { + bool ret; + spin_lock_bh(&psock->ingress_lock); - if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) + if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { list_add_tail(&msg->list, &psock->ingress_msg); - else { + ret = true; + } else { sk_msg_free(psock->sk, msg); kfree(msg); + ret = false; } spin_unlock_bh(&psock->ingress_lock); + return ret; } static inline struct sk_msg *sk_psock_dequeue_msg(struct sk_psock *psock) @@ -410,11 +419,14 @@ void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock); int sk_psock_msg_verdict(struct sock *sk, struct sk_psock *psock, struct sk_msg *msg); -static inline struct sk_psock_link *sk_psock_init_link(void) -{ - return kzalloc(sizeof(struct sk_psock_link), - GFP_ATOMIC | __GFP_NOWARN); -} +/* + * This specialized allocator has to be a macro for its allocations to be + * accounted separately (to have a separate alloc_tag). The typecast is + * intentional to enforce typesafety. + */ +#define sk_psock_init_link() \ + ((struct sk_psock_link *)kzalloc(sizeof(struct sk_psock_link), \ + GFP_ATOMIC | __GFP_NOWARN)) static inline void sk_psock_free_link(struct sk_psock_link *link) { @@ -461,10 +473,12 @@ static inline void sk_psock_put(struct sock *sk, struct sk_psock *psock) static inline void sk_psock_data_ready(struct sock *sk, struct sk_psock *psock) { + read_lock_bh(&sk->sk_callback_lock); if (psock->saved_data_ready) psock->saved_data_ready(sk); else sk->sk_data_ready(sk); + read_unlock_bh(&sk->sk_callback_lock); } static inline void psock_set_prog(struct bpf_prog **pprog, diff --git a/include/linux/slab.h b/include/linux/slab.h index e53cbfa18325..09eedaecf120 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -41,7 +41,7 @@ enum _slab_flag_bits { #ifdef CONFIG_FAILSLAB _SLAB_FAILSLAB, #endif -#ifdef CONFIG_MEMCG_KMEM +#ifdef CONFIG_MEMCG _SLAB_ACCOUNT, #endif #ifdef CONFIG_KASAN_GENERIC @@ -56,6 +56,9 @@ enum _slab_flag_bits { #endif _SLAB_OBJECT_POISON, _SLAB_CMPXCHG_DOUBLE, +#ifdef CONFIG_SLAB_OBJ_EXT + _SLAB_NO_OBJ_EXT, +#endif _SLAB_FLAGS_LAST_BIT }; @@ -74,7 +77,17 @@ enum _slab_flag_bits { #define SLAB_POISON __SLAB_FLAG_BIT(_SLAB_POISON) /* Indicate a kmalloc slab */ #define SLAB_KMALLOC __SLAB_FLAG_BIT(_SLAB_KMALLOC) -/* Align objs on cache lines */ +/** + * define SLAB_HWCACHE_ALIGN - Align objects on cache line boundaries. + * + * Sufficiently large objects are aligned on cache line boundary. For object + * size smaller than a half of cache line size, the alignment is on the half of + * cache line size. In general, if object size is smaller than 1/2^n of cache + * line size, the alignment is adjusted to 1/2^n. + * + * If explicit alignment is also requested by the respective + * &struct kmem_cache_args field, the greater of both is alignments is applied. + */ #define SLAB_HWCACHE_ALIGN __SLAB_FLAG_BIT(_SLAB_HWCACHE_ALIGN) /* Use GFP_DMA memory */ #define SLAB_CACHE_DMA __SLAB_FLAG_BIT(_SLAB_CACHE_DMA) @@ -84,8 +97,8 @@ enum _slab_flag_bits { #define SLAB_STORE_USER __SLAB_FLAG_BIT(_SLAB_STORE_USER) /* Panic if kmem_cache_create() fails */ #define SLAB_PANIC __SLAB_FLAG_BIT(_SLAB_PANIC) -/* - * SLAB_TYPESAFE_BY_RCU - **WARNING** READ THIS! +/** + * define SLAB_TYPESAFE_BY_RCU - **WARNING** READ THIS! * * This delays freeing the SLAB page by a grace period, it does _NOT_ * delay object freeing. This means that if you do kmem_cache_free() @@ -96,20 +109,22 @@ enum _slab_flag_bits { * stays valid, the trick to using this is relying on an independent * object validation pass. Something like: * - * begin: - * rcu_read_lock(); - * obj = lockless_lookup(key); - * if (obj) { - * if (!try_get_ref(obj)) // might fail for free objects - * rcu_read_unlock(); - * goto begin; + * :: * - * if (obj->key != key) { // not the object we expected - * put_ref(obj); - * rcu_read_unlock(); - * goto begin; - * } - * } + * begin: + * rcu_read_lock(); + * obj = lockless_lookup(key); + * if (obj) { + * if (!try_get_ref(obj)) // might fail for free objects + * rcu_read_unlock(); + * goto begin; + * + * if (obj->key != key) { // not the object we expected + * put_ref(obj); + * rcu_read_unlock(); + * goto begin; + * } + * } * rcu_read_unlock(); * * This is useful if we need to approach a kernel structure obliquely, @@ -134,7 +149,6 @@ enum _slab_flag_bits { * * Note that SLAB_TYPESAFE_BY_RCU was originally named SLAB_DESTROY_BY_RCU. */ -/* Defer freeing slabs to RCU */ #define SLAB_TYPESAFE_BY_RCU __SLAB_FLAG_BIT(_SLAB_TYPESAFE_BY_RCU) /* Trace allocations and frees */ #define SLAB_TRACE __SLAB_FLAG_BIT(_SLAB_TRACE) @@ -167,8 +181,13 @@ enum _slab_flag_bits { #else # define SLAB_FAILSLAB __SLAB_FLAG_UNUSED #endif -/* Account to memcg */ -#ifdef CONFIG_MEMCG_KMEM +/** + * define SLAB_ACCOUNT - Account allocations to memcg. + * + * All object allocations from this cache will be memcg accounted, regardless of + * __GFP_ACCOUNT being or not being passed to individual allocations. + */ +#ifdef CONFIG_MEMCG # define SLAB_ACCOUNT __SLAB_FLAG_BIT(_SLAB_ACCOUNT) #else # define SLAB_ACCOUNT __SLAB_FLAG_UNUSED @@ -194,7 +213,13 @@ enum _slab_flag_bits { #endif /* The following flags affect the page allocator grouping pages by mobility */ -/* Objects are reclaimable */ +/** + * define SLAB_RECLAIM_ACCOUNT - Objects are reclaimable. + * + * Use this flag for caches that have an associated shrinker. As a result, slab + * pages are allocated with __GFP_RECLAIMABLE, which affects grouping pages by + * mobility, and are accounted in SReclaimable counter in /proc/meminfo + */ #ifndef CONFIG_SLUB_TINY #define SLAB_RECLAIM_ACCOUNT __SLAB_FLAG_BIT(_SLAB_RECLAIM_ACCOUNT) #else @@ -202,6 +227,19 @@ enum _slab_flag_bits { #endif #define SLAB_TEMPORARY SLAB_RECLAIM_ACCOUNT /* Objects are short-lived */ +/* Slab created using create_boot_cache */ +#ifdef CONFIG_SLAB_OBJ_EXT +#define SLAB_NO_OBJ_EXT __SLAB_FLAG_BIT(_SLAB_NO_OBJ_EXT) +#else +#define SLAB_NO_OBJ_EXT __SLAB_FLAG_UNUSED +#endif + +/* + * freeptr_t represents a SLUB freelist pointer, which might be encoded + * and not dereferenceable if CONFIG_SLAB_FREELIST_HARDENED is enabled. + */ +typedef struct { unsigned long v; } freeptr_t; + /* * ZERO_SIZE_PTR will be returned for zero sized kmalloc requests. * @@ -224,14 +262,173 @@ struct mem_cgroup; */ bool slab_is_available(void); -struct kmem_cache *kmem_cache_create(const char *name, unsigned int size, - unsigned int align, slab_flags_t flags, - void (*ctor)(void *)); -struct kmem_cache *kmem_cache_create_usercopy(const char *name, - unsigned int size, unsigned int align, - slab_flags_t flags, - unsigned int useroffset, unsigned int usersize, - void (*ctor)(void *)); +/** + * struct kmem_cache_args - Less common arguments for kmem_cache_create() + * + * Any uninitialized fields of the structure are interpreted as unused. The + * exception is @freeptr_offset where %0 is a valid value, so + * @use_freeptr_offset must be also set to %true in order to interpret the field + * as used. For @useroffset %0 is also valid, but only with non-%0 + * @usersize. + * + * When %NULL args is passed to kmem_cache_create(), it is equivalent to all + * fields unused. + */ +struct kmem_cache_args { + /** + * @align: The required alignment for the objects. + * + * %0 means no specific alignment is requested. + */ + unsigned int align; + /** + * @useroffset: Usercopy region offset. + * + * %0 is a valid offset, when @usersize is non-%0 + */ + unsigned int useroffset; + /** + * @usersize: Usercopy region size. + * + * %0 means no usercopy region is specified. + */ + unsigned int usersize; + /** + * @freeptr_offset: Custom offset for the free pointer + * in &SLAB_TYPESAFE_BY_RCU caches + * + * By default &SLAB_TYPESAFE_BY_RCU caches place the free pointer + * outside of the object. This might cause the object to grow in size. + * Cache creators that have a reason to avoid this can specify a custom + * free pointer offset in their struct where the free pointer will be + * placed. + * + * Note that placing the free pointer inside the object requires the + * caller to ensure that no fields are invalidated that are required to + * guard against object recycling (See &SLAB_TYPESAFE_BY_RCU for + * details). + * + * Using %0 as a value for @freeptr_offset is valid. If @freeptr_offset + * is specified, %use_freeptr_offset must be set %true. + * + * Note that @ctor currently isn't supported with custom free pointers + * as a @ctor requires an external free pointer. + */ + unsigned int freeptr_offset; + /** + * @use_freeptr_offset: Whether a @freeptr_offset is used. + */ + bool use_freeptr_offset; + /** + * @ctor: A constructor for the objects. + * + * The constructor is invoked for each object in a newly allocated slab + * page. It is the cache user's responsibility to free object in the + * same state as after calling the constructor, or deal appropriately + * with any differences between a freshly constructed and a reallocated + * object. + * + * %NULL means no constructor. + */ + void (*ctor)(void *); +}; + +struct kmem_cache *__kmem_cache_create_args(const char *name, + unsigned int object_size, + struct kmem_cache_args *args, + slab_flags_t flags); +static inline struct kmem_cache * +__kmem_cache_create(const char *name, unsigned int size, unsigned int align, + slab_flags_t flags, void (*ctor)(void *)) +{ + struct kmem_cache_args kmem_args = { + .align = align, + .ctor = ctor, + }; + + return __kmem_cache_create_args(name, size, &kmem_args, flags); +} + +/** + * kmem_cache_create_usercopy - Create a kmem cache with a region suitable + * for copying to userspace. + * @name: A string which is used in /proc/slabinfo to identify this cache. + * @size: The size of objects to be created in this cache. + * @align: The required alignment for the objects. + * @flags: SLAB flags + * @useroffset: Usercopy region offset + * @usersize: Usercopy region size + * @ctor: A constructor for the objects, or %NULL. + * + * This is a legacy wrapper, new code should use either KMEM_CACHE_USERCOPY() + * if whitelisting a single field is sufficient, or kmem_cache_create() with + * the necessary parameters passed via the args parameter (see + * &struct kmem_cache_args) + * + * Return: a pointer to the cache on success, NULL on failure. + */ +static inline struct kmem_cache * +kmem_cache_create_usercopy(const char *name, unsigned int size, + unsigned int align, slab_flags_t flags, + unsigned int useroffset, unsigned int usersize, + void (*ctor)(void *)) +{ + struct kmem_cache_args kmem_args = { + .align = align, + .ctor = ctor, + .useroffset = useroffset, + .usersize = usersize, + }; + + return __kmem_cache_create_args(name, size, &kmem_args, flags); +} + +/* If NULL is passed for @args, use this variant with default arguments. */ +static inline struct kmem_cache * +__kmem_cache_default_args(const char *name, unsigned int size, + struct kmem_cache_args *args, + slab_flags_t flags) +{ + struct kmem_cache_args kmem_default_args = {}; + + /* Make sure we don't get passed garbage. */ + if (WARN_ON_ONCE(args)) + return ERR_PTR(-EINVAL); + + return __kmem_cache_create_args(name, size, &kmem_default_args, flags); +} + +/** + * kmem_cache_create - Create a kmem cache. + * @__name: A string which is used in /proc/slabinfo to identify this cache. + * @__object_size: The size of objects to be created in this cache. + * @__args: Optional arguments, see &struct kmem_cache_args. Passing %NULL + * means defaults will be used for all the arguments. + * + * This is currently implemented as a macro using ``_Generic()`` to call + * either the new variant of the function, or a legacy one. + * + * The new variant has 4 parameters: + * ``kmem_cache_create(name, object_size, args, flags)`` + * + * See __kmem_cache_create_args() which implements this. + * + * The legacy variant has 5 parameters: + * ``kmem_cache_create(name, object_size, align, flags, ctor)`` + * + * The align and ctor parameters map to the respective fields of + * &struct kmem_cache_args + * + * Context: Cannot be called within a interrupt, but can be interrupted. + * + * Return: a pointer to the cache on success, NULL on failure. + */ +#define kmem_cache_create(__name, __object_size, __args, ...) \ + _Generic((__args), \ + struct kmem_cache_args *: __kmem_cache_create_args, \ + void *: __kmem_cache_default_args, \ + default: __kmem_cache_create)(__name, __object_size, __args, __VA_ARGS__) + void kmem_cache_destroy(struct kmem_cache *s); int kmem_cache_shrink(struct kmem_cache *s); @@ -243,30 +440,37 @@ int kmem_cache_shrink(struct kmem_cache *s); * f.e. add ____cacheline_aligned_in_smp to the struct declaration * then the objects will be properly aligned in SMP configurations. */ -#define KMEM_CACHE(__struct, __flags) \ - kmem_cache_create(#__struct, sizeof(struct __struct), \ - __alignof__(struct __struct), (__flags), NULL) +#define KMEM_CACHE(__struct, __flags) \ + __kmem_cache_create_args(#__struct, sizeof(struct __struct), \ + &(struct kmem_cache_args) { \ + .align = __alignof__(struct __struct), \ + }, (__flags)) /* * To whitelist a single field for copying to/from usercopy, use this * macro instead for KMEM_CACHE() above. */ -#define KMEM_CACHE_USERCOPY(__struct, __flags, __field) \ - kmem_cache_create_usercopy(#__struct, \ - sizeof(struct __struct), \ - __alignof__(struct __struct), (__flags), \ - offsetof(struct __struct, __field), \ - sizeof_field(struct __struct, __field), NULL) +#define KMEM_CACHE_USERCOPY(__struct, __flags, __field) \ + __kmem_cache_create_args(#__struct, sizeof(struct __struct), \ + &(struct kmem_cache_args) { \ + .align = __alignof__(struct __struct), \ + .useroffset = offsetof(struct __struct, __field), \ + .usersize = sizeof_field(struct __struct, __field), \ + }, (__flags)) /* * Common kmalloc functions provided by all allocators */ -void * __must_check krealloc(const void *objp, size_t new_size, gfp_t flags) __realloc_size(2); +void * __must_check krealloc_noprof(const void *objp, size_t new_size, + gfp_t flags) __realloc_size(2); +#define krealloc(...) alloc_hooks(krealloc_noprof(__VA_ARGS__)) + void kfree(const void *objp); void kfree_sensitive(const void *objp); size_t __ksize(const void *objp); -DEFINE_FREE(kfree, void *, if (_T) kfree(_T)) +DEFINE_FREE(kfree, void *, if (!IS_ERR_OR_NULL(_T)) kfree(_T)) +DEFINE_FREE(kfree_sensitive, void *, if (_T) kfree_sensitive(_T)) /** * ksize - Report actual allocation size of associated object @@ -394,7 +598,7 @@ enum kmalloc_cache_type { #ifndef CONFIG_ZONE_DMA KMALLOC_DMA = KMALLOC_NORMAL, #endif -#ifndef CONFIG_MEMCG_KMEM +#ifndef CONFIG_MEMCG KMALLOC_CGROUP = KMALLOC_NORMAL, #endif KMALLOC_RANDOM_START = KMALLOC_NORMAL, @@ -407,14 +611,15 @@ enum kmalloc_cache_type { #ifdef CONFIG_ZONE_DMA KMALLOC_DMA, #endif -#ifdef CONFIG_MEMCG_KMEM +#ifdef CONFIG_MEMCG KMALLOC_CGROUP, #endif NR_KMALLOC_TYPES }; -extern struct kmem_cache * -kmalloc_caches[NR_KMALLOC_TYPES][KMALLOC_SHIFT_HIGH + 1]; +typedef struct kmem_cache * kmem_buckets[KMALLOC_SHIFT_HIGH + 1]; + +extern kmem_buckets kmalloc_caches[NR_KMALLOC_TYPES]; /* * Define gfp bits that should not be set for KMALLOC_NORMAL. @@ -422,7 +627,7 @@ kmalloc_caches[NR_KMALLOC_TYPES][KMALLOC_SHIFT_HIGH + 1]; #define KMALLOC_NOT_NORMAL_BITS \ (__GFP_RECLAIMABLE | \ (IS_ENABLED(CONFIG_ZONE_DMA) ? __GFP_DMA : 0) | \ - (IS_ENABLED(CONFIG_MEMCG_KMEM) ? __GFP_ACCOUNT : 0)) + (IS_ENABLED(CONFIG_MEMCG) ? __GFP_ACCOUNT : 0)) extern unsigned long random_kmalloc_seed; @@ -450,7 +655,7 @@ static __always_inline enum kmalloc_cache_type kmalloc_type(gfp_t flags, unsigne */ if (IS_ENABLED(CONFIG_ZONE_DMA) && (flags & __GFP_DMA)) return KMALLOC_DMA; - if (!IS_ENABLED(CONFIG_MEMCG_KMEM) || (flags & __GFP_RECLAIMABLE)) + if (!IS_ENABLED(CONFIG_MEMCG) || (flags & __GFP_RECLAIMABLE)) return KMALLOC_RECLAIM; else return KMALLOC_CGROUP; @@ -513,7 +718,7 @@ static __always_inline unsigned int __kmalloc_index(size_t size, static_assert(PAGE_SHIFT <= 20); #define kmalloc_index(s) __kmalloc_index(s, true) -void *__kmalloc(size_t size, gfp_t flags) __assume_kmalloc_alignment __alloc_size(1); +#include <linux/alloc_tag.h> /** * kmem_cache_alloc - Allocate an object @@ -525,11 +730,49 @@ void *__kmalloc(size_t size, gfp_t flags) __assume_kmalloc_alignment __alloc_siz * * Return: pointer to the new object or %NULL in case of error */ -void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags) __assume_slab_alignment __malloc; -void *kmem_cache_alloc_lru(struct kmem_cache *s, struct list_lru *lru, - gfp_t gfpflags) __assume_slab_alignment __malloc; +void *kmem_cache_alloc_noprof(struct kmem_cache *cachep, + gfp_t flags) __assume_slab_alignment __malloc; +#define kmem_cache_alloc(...) alloc_hooks(kmem_cache_alloc_noprof(__VA_ARGS__)) + +void *kmem_cache_alloc_lru_noprof(struct kmem_cache *s, struct list_lru *lru, + gfp_t gfpflags) __assume_slab_alignment __malloc; +#define kmem_cache_alloc_lru(...) alloc_hooks(kmem_cache_alloc_lru_noprof(__VA_ARGS__)) + +/** + * kmem_cache_charge - memcg charge an already allocated slab memory + * @objp: address of the slab object to memcg charge + * @gfpflags: describe the allocation context + * + * kmem_cache_charge allows charging a slab object to the current memcg, + * primarily in cases where charging at allocation time might not be possible + * because the target memcg is not known (i.e. softirq context) + * + * The objp should be pointer returned by the slab allocator functions like + * kmalloc (with __GFP_ACCOUNT in flags) or kmem_cache_alloc. The memcg charge + * behavior can be controlled through gfpflags parameter, which affects how the + * necessary internal metadata can be allocated. Including __GFP_NOFAIL denotes + * that overcharging is requested instead of failure, but is not applied for the + * internal metadata allocation. + * + * There are several cases where it will return true even if the charging was + * not done: + * More specifically: + * + * 1. For !CONFIG_MEMCG or cgroup_disable=memory systems. + * 2. Already charged slab objects. + * 3. For slab objects from KMALLOC_NORMAL caches - allocated by kmalloc() + * without __GFP_ACCOUNT + * 4. Allocating internal metadata has failed + * + * Return: true if charge was successful otherwise false. + */ +bool kmem_cache_charge(void *objp, gfp_t gfpflags); void kmem_cache_free(struct kmem_cache *s, void *objp); +kmem_buckets *kmem_buckets_create(const char *name, slab_flags_t flags, + unsigned int useroffset, unsigned int usersize, + void (*ctor)(void *)); + /* * Bulk allocation and freeing operations. These are accelerated in an * allocator specific way to avoid taking locks repeatedly or building @@ -538,29 +781,58 @@ void kmem_cache_free(struct kmem_cache *s, void *objp); * Note that interrupts must be enabled when calling these functions. */ void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p); -int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, void **p); + +int kmem_cache_alloc_bulk_noprof(struct kmem_cache *s, gfp_t flags, size_t size, void **p); +#define kmem_cache_alloc_bulk(...) alloc_hooks(kmem_cache_alloc_bulk_noprof(__VA_ARGS__)) static __always_inline void kfree_bulk(size_t size, void **p) { kmem_cache_free_bulk(NULL, size, p); } -void *__kmalloc_node(size_t size, gfp_t flags, int node) __assume_kmalloc_alignment - __alloc_size(1); -void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t flags, int node) __assume_slab_alignment - __malloc; +void *kmem_cache_alloc_node_noprof(struct kmem_cache *s, gfp_t flags, + int node) __assume_slab_alignment __malloc; +#define kmem_cache_alloc_node(...) alloc_hooks(kmem_cache_alloc_node_noprof(__VA_ARGS__)) + +/* + * These macros allow declaring a kmem_buckets * parameter alongside size, which + * can be compiled out with CONFIG_SLAB_BUCKETS=n so that a large number of call + * sites don't have to pass NULL. + */ +#ifdef CONFIG_SLAB_BUCKETS +#define DECL_BUCKET_PARAMS(_size, _b) size_t (_size), kmem_buckets *(_b) +#define PASS_BUCKET_PARAMS(_size, _b) (_size), (_b) +#define PASS_BUCKET_PARAM(_b) (_b) +#else +#define DECL_BUCKET_PARAMS(_size, _b) size_t (_size) +#define PASS_BUCKET_PARAMS(_size, _b) (_size) +#define PASS_BUCKET_PARAM(_b) NULL +#endif + +/* + * The following functions are not to be used directly and are intended only + * for internal use from kmalloc() and kmalloc_node() + * with the exception of kunit tests + */ + +void *__kmalloc_noprof(size_t size, gfp_t flags) + __assume_kmalloc_alignment __alloc_size(1); -void *kmalloc_trace(struct kmem_cache *s, gfp_t flags, size_t size) - __assume_kmalloc_alignment __alloc_size(3); +void *__kmalloc_node_noprof(DECL_BUCKET_PARAMS(size, b), gfp_t flags, int node) + __assume_kmalloc_alignment __alloc_size(1); -void *kmalloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, - int node, size_t size) __assume_kmalloc_alignment - __alloc_size(4); -void *kmalloc_large(size_t size, gfp_t flags) __assume_page_alignment - __alloc_size(1); +void *__kmalloc_cache_noprof(struct kmem_cache *s, gfp_t flags, size_t size) + __assume_kmalloc_alignment __alloc_size(3); -void *kmalloc_large_node(size_t size, gfp_t flags, int node) __assume_page_alignment - __alloc_size(1); +void *__kmalloc_cache_node_noprof(struct kmem_cache *s, gfp_t gfpflags, + int node, size_t size) + __assume_kmalloc_alignment __alloc_size(4); + +void *__kmalloc_large_noprof(size_t size, gfp_t flags) + __assume_page_alignment __alloc_size(1); + +void *__kmalloc_large_node_noprof(size_t size, gfp_t flags, int node) + __assume_page_alignment __alloc_size(1); /** * kmalloc - allocate kernel memory @@ -572,7 +844,8 @@ void *kmalloc_large_node(size_t size, gfp_t flags, int node) __assume_page_align * * The allocated object address is aligned to at least ARCH_KMALLOC_MINALIGN * bytes. For @size of power of two bytes, the alignment is also guaranteed - * to be at least to the size. + * to be at least to the size. For other sizes, the alignment is guaranteed to + * be at least the largest power-of-two divisor of @size. * * The @flags argument may be one of the GFP flags defined at * include/linux/gfp_types.h and described at @@ -616,37 +889,45 @@ void *kmalloc_large_node(size_t size, gfp_t flags, int node) __assume_page_align * Try really hard to succeed the allocation but fail * eventually. */ -static __always_inline __alloc_size(1) void *kmalloc(size_t size, gfp_t flags) +static __always_inline __alloc_size(1) void *kmalloc_noprof(size_t size, gfp_t flags) { if (__builtin_constant_p(size) && size) { unsigned int index; if (size > KMALLOC_MAX_CACHE_SIZE) - return kmalloc_large(size, flags); + return __kmalloc_large_noprof(size, flags); index = kmalloc_index(size); - return kmalloc_trace( + return __kmalloc_cache_noprof( kmalloc_caches[kmalloc_type(flags, _RET_IP_)][index], flags, size); } - return __kmalloc(size, flags); + return __kmalloc_noprof(size, flags); } +#define kmalloc(...) alloc_hooks(kmalloc_noprof(__VA_ARGS__)) + +#define kmem_buckets_alloc(_b, _size, _flags) \ + alloc_hooks(__kmalloc_node_noprof(PASS_BUCKET_PARAMS(_size, _b), _flags, NUMA_NO_NODE)) -static __always_inline __alloc_size(1) void *kmalloc_node(size_t size, gfp_t flags, int node) +#define kmem_buckets_alloc_track_caller(_b, _size, _flags) \ + alloc_hooks(__kmalloc_node_track_caller_noprof(PASS_BUCKET_PARAMS(_size, _b), _flags, NUMA_NO_NODE, _RET_IP_)) + +static __always_inline __alloc_size(1) void *kmalloc_node_noprof(size_t size, gfp_t flags, int node) { if (__builtin_constant_p(size) && size) { unsigned int index; if (size > KMALLOC_MAX_CACHE_SIZE) - return kmalloc_large_node(size, flags, node); + return __kmalloc_large_node_noprof(size, flags, node); index = kmalloc_index(size); - return kmalloc_node_trace( + return __kmalloc_cache_node_noprof( kmalloc_caches[kmalloc_type(flags, _RET_IP_)][index], flags, node, size); } - return __kmalloc_node(size, flags, node); + return __kmalloc_node_noprof(PASS_BUCKET_PARAMS(size, NULL), flags, node); } +#define kmalloc_node(...) alloc_hooks(kmalloc_node_noprof(__VA_ARGS__)) /** * kmalloc_array - allocate memory for an array. @@ -654,16 +935,17 @@ static __always_inline __alloc_size(1) void *kmalloc_node(size_t size, gfp_t fla * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ -static inline __alloc_size(1, 2) void *kmalloc_array(size_t n, size_t size, gfp_t flags) +static inline __alloc_size(1, 2) void *kmalloc_array_noprof(size_t n, size_t size, gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; if (__builtin_constant_p(n) && __builtin_constant_p(size)) - return kmalloc(bytes, flags); - return __kmalloc(bytes, flags); + return kmalloc_noprof(bytes, flags); + return kmalloc_noprof(bytes, flags); } +#define kmalloc_array(...) alloc_hooks(kmalloc_array_noprof(__VA_ARGS__)) /** * krealloc_array - reallocate memory for an array. @@ -671,19 +953,30 @@ static inline __alloc_size(1, 2) void *kmalloc_array(size_t n, size_t size, gfp_ * @new_n: new number of elements to alloc * @new_size: new size of a single member of the array * @flags: the type of memory to allocate (see kmalloc) + * + * If __GFP_ZERO logic is requested, callers must ensure that, starting with the + * initial memory allocation, every subsequent call to this API for the same + * memory allocation is flagged with __GFP_ZERO. Otherwise, it is possible that + * __GFP_ZERO is not fully honored by this API. + * + * See krealloc_noprof() for further details. + * + * In any case, the contents of the object pointed to are preserved up to the + * lesser of the new and old sizes. */ -static inline __realloc_size(2, 3) void * __must_check krealloc_array(void *p, - size_t new_n, - size_t new_size, - gfp_t flags) +static inline __realloc_size(2, 3) void * __must_check krealloc_array_noprof(void *p, + size_t new_n, + size_t new_size, + gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(new_n, new_size, &bytes))) return NULL; - return krealloc(p, bytes, flags); + return krealloc_noprof(p, bytes, flags); } +#define krealloc_array(...) alloc_hooks(krealloc_array_noprof(__VA_ARGS__)) /** * kcalloc - allocate memory for an array. The memory is set to zero. @@ -691,16 +984,14 @@ static inline __realloc_size(2, 3) void * __must_check krealloc_array(void *p, * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ -static inline __alloc_size(1, 2) void *kcalloc(size_t n, size_t size, gfp_t flags) -{ - return kmalloc_array(n, size, flags | __GFP_ZERO); -} +#define kcalloc(n, size, flags) kmalloc_array(n, size, (flags) | __GFP_ZERO) -void *__kmalloc_node_track_caller(size_t size, gfp_t flags, int node, - unsigned long caller) __alloc_size(1); -#define kmalloc_node_track_caller(size, flags, node) \ - __kmalloc_node_track_caller(size, flags, node, \ - _RET_IP_) +void *__kmalloc_node_track_caller_noprof(DECL_BUCKET_PARAMS(size, b), gfp_t flags, int node, + unsigned long caller) __alloc_size(1); +#define kmalloc_node_track_caller_noprof(size, flags, node, caller) \ + __kmalloc_node_track_caller_noprof(PASS_BUCKET_PARAMS(size, NULL), flags, node, caller) +#define kmalloc_node_track_caller(...) \ + alloc_hooks(kmalloc_node_track_caller_noprof(__VA_ARGS__, _RET_IP_)) /* * kmalloc_track_caller is a special version of kmalloc that records the @@ -710,11 +1001,12 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t flags, int node, * allocator where we care about the real place the memory allocation * request comes from. */ -#define kmalloc_track_caller(size, flags) \ - __kmalloc_node_track_caller(size, flags, \ - NUMA_NO_NODE, _RET_IP_) +#define kmalloc_track_caller(...) kmalloc_node_track_caller(__VA_ARGS__, NUMA_NO_NODE) + +#define kmalloc_track_caller_noprof(...) \ + kmalloc_node_track_caller_noprof(__VA_ARGS__, NUMA_NO_NODE, _RET_IP_) -static inline __alloc_size(1, 2) void *kmalloc_array_node(size_t n, size_t size, gfp_t flags, +static inline __alloc_size(1, 2) void *kmalloc_array_node_noprof(size_t n, size_t size, gfp_t flags, int node) { size_t bytes; @@ -722,77 +1014,69 @@ static inline __alloc_size(1, 2) void *kmalloc_array_node(size_t n, size_t size, if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; if (__builtin_constant_p(n) && __builtin_constant_p(size)) - return kmalloc_node(bytes, flags, node); - return __kmalloc_node(bytes, flags, node); + return kmalloc_node_noprof(bytes, flags, node); + return __kmalloc_node_noprof(PASS_BUCKET_PARAMS(bytes, NULL), flags, node); } +#define kmalloc_array_node(...) alloc_hooks(kmalloc_array_node_noprof(__VA_ARGS__)) -static inline __alloc_size(1, 2) void *kcalloc_node(size_t n, size_t size, gfp_t flags, int node) -{ - return kmalloc_array_node(n, size, flags | __GFP_ZERO, node); -} +#define kcalloc_node(_n, _size, _flags, _node) \ + kmalloc_array_node(_n, _size, (_flags) | __GFP_ZERO, _node) /* * Shortcuts */ -static inline void *kmem_cache_zalloc(struct kmem_cache *k, gfp_t flags) -{ - return kmem_cache_alloc(k, flags | __GFP_ZERO); -} +#define kmem_cache_zalloc(_k, _flags) kmem_cache_alloc(_k, (_flags)|__GFP_ZERO) /** * kzalloc - allocate memory. The memory is set to zero. * @size: how many bytes of memory are required. * @flags: the type of memory to allocate (see kmalloc). */ -static inline __alloc_size(1) void *kzalloc(size_t size, gfp_t flags) +static inline __alloc_size(1) void *kzalloc_noprof(size_t size, gfp_t flags) { - return kmalloc(size, flags | __GFP_ZERO); + return kmalloc_noprof(size, flags | __GFP_ZERO); } +#define kzalloc(...) alloc_hooks(kzalloc_noprof(__VA_ARGS__)) +#define kzalloc_node(_size, _flags, _node) kmalloc_node(_size, (_flags)|__GFP_ZERO, _node) -/** - * kzalloc_node - allocate zeroed memory from a particular memory node. - * @size: how many bytes of memory are required. - * @flags: the type of memory to allocate (see kmalloc). - * @node: memory node from which to allocate - */ -static inline __alloc_size(1) void *kzalloc_node(size_t size, gfp_t flags, int node) -{ - return kmalloc_node(size, flags | __GFP_ZERO, node); -} +void *__kvmalloc_node_noprof(DECL_BUCKET_PARAMS(size, b), gfp_t flags, int node) __alloc_size(1); +#define kvmalloc_node_noprof(size, flags, node) \ + __kvmalloc_node_noprof(PASS_BUCKET_PARAMS(size, NULL), flags, node) +#define kvmalloc_node(...) alloc_hooks(kvmalloc_node_noprof(__VA_ARGS__)) -extern void *kvmalloc_node(size_t size, gfp_t flags, int node) __alloc_size(1); -static inline __alloc_size(1) void *kvmalloc(size_t size, gfp_t flags) -{ - return kvmalloc_node(size, flags, NUMA_NO_NODE); -} -static inline __alloc_size(1) void *kvzalloc_node(size_t size, gfp_t flags, int node) -{ - return kvmalloc_node(size, flags | __GFP_ZERO, node); -} -static inline __alloc_size(1) void *kvzalloc(size_t size, gfp_t flags) -{ - return kvmalloc(size, flags | __GFP_ZERO); -} +#define kvmalloc(_size, _flags) kvmalloc_node(_size, _flags, NUMA_NO_NODE) +#define kvmalloc_noprof(_size, _flags) kvmalloc_node_noprof(_size, _flags, NUMA_NO_NODE) +#define kvzalloc(_size, _flags) kvmalloc(_size, (_flags)|__GFP_ZERO) -static inline __alloc_size(1, 2) void *kvmalloc_array(size_t n, size_t size, gfp_t flags) +#define kvzalloc_node(_size, _flags, _node) kvmalloc_node(_size, (_flags)|__GFP_ZERO, _node) +#define kmem_buckets_valloc(_b, _size, _flags) \ + alloc_hooks(__kvmalloc_node_noprof(PASS_BUCKET_PARAMS(_size, _b), _flags, NUMA_NO_NODE)) + +static inline __alloc_size(1, 2) void * +kvmalloc_array_node_noprof(size_t n, size_t size, gfp_t flags, int node) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; - return kvmalloc(bytes, flags); + return kvmalloc_node_noprof(bytes, flags, node); } -static inline __alloc_size(1, 2) void *kvcalloc(size_t n, size_t size, gfp_t flags) -{ - return kvmalloc_array(n, size, flags | __GFP_ZERO); -} +#define kvmalloc_array_noprof(...) kvmalloc_array_node_noprof(__VA_ARGS__, NUMA_NO_NODE) +#define kvcalloc_node_noprof(_n,_s,_f,_node) kvmalloc_array_node_noprof(_n,_s,(_f)|__GFP_ZERO,_node) +#define kvcalloc_noprof(...) kvcalloc_node_noprof(__VA_ARGS__, NUMA_NO_NODE) + +#define kvmalloc_array(...) alloc_hooks(kvmalloc_array_noprof(__VA_ARGS__)) +#define kvcalloc_node(...) alloc_hooks(kvcalloc_node_noprof(__VA_ARGS__)) +#define kvcalloc(...) alloc_hooks(kvcalloc_noprof(__VA_ARGS__)) + +void *kvrealloc_noprof(const void *p, size_t size, gfp_t flags) + __realloc_size(2); +#define kvrealloc(...) alloc_hooks(kvrealloc_noprof(__VA_ARGS__)) -extern void *kvrealloc(const void *p, size_t oldsize, size_t newsize, gfp_t flags) - __realloc_size(3); extern void kvfree(const void *addr); -DEFINE_FREE(kvfree, void *, if (_T) kvfree(_T)) +DEFINE_FREE(kvfree, void *, if (!IS_ERR_OR_NULL(_T)) kvfree(_T)) extern void kvfree_sensitive(const void *addr, size_t len); @@ -815,5 +1099,6 @@ unsigned int kmem_cache_size(struct kmem_cache *s); size_t kmalloc_size_roundup(size_t size); void __init kmem_cache_init_late(void); +void __init kvfree_rcu_init(void); #endif /* _LINUX_SLAB_H */ diff --git a/include/linux/slimbus.h b/include/linux/slimbus.h index 3042385b7b40..a4608d9a9684 100644 --- a/include/linux/slimbus.h +++ b/include/linux/slimbus.h @@ -91,7 +91,7 @@ struct slim_driver { struct device_driver driver; const struct slim_device_id *id_table; }; -#define to_slim_driver(d) container_of(d, struct slim_driver, driver) +#define to_slim_driver(d) container_of_const(d, struct slim_driver, driver) /** * struct slim_val_inf - Slimbus value or information element diff --git a/include/linux/smp.h b/include/linux/smp.h index fcd61dfe2af3..f1aa0952e8c3 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -109,7 +109,7 @@ static inline void on_each_cpu_cond(smp_cond_func_t cond_func, * Architecture specific boot CPU setup. Defined as empty weak function in * init/main.c. Architectures can override it. */ -void smp_prepare_boot_cpu(void); +void __init smp_prepare_boot_cpu(void); #ifdef CONFIG_SMP @@ -294,4 +294,10 @@ int smpcfd_prepare_cpu(unsigned int cpu); int smpcfd_dead_cpu(unsigned int cpu); int smpcfd_dying_cpu(unsigned int cpu); +#ifdef CONFIG_CSD_LOCK_WAIT_DEBUG +bool csd_lock_is_stuck(void); +#else +static inline bool csd_lock_is_stuck(void) { return false; } +#endif + #endif /* __LINUX_SMP_H */ diff --git a/include/linux/soc/apple/rtkit.h b/include/linux/soc/apple/rtkit.h index 8c9ca857ccf6..c06d17599ae7 100644 --- a/include/linux/soc/apple/rtkit.h +++ b/include/linux/soc/apple/rtkit.h @@ -69,7 +69,7 @@ struct apple_rtkit; * Initializes the internal state required to handle RTKit. This * should usually be called within _probe. * - * @dev: Pointer to the device node this coprocessor is assocated with + * @dev: Pointer to the device node this coprocessor is associated 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 @@ -83,7 +83,7 @@ struct apple_rtkit *devm_apple_rtkit_init(struct device *dev, void *cookie, * 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 + * @dev: Pointer to the device node this coprocessor is associated 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 diff --git a/include/linux/soc/cirrus/ep93xx.h b/include/linux/soc/cirrus/ep93xx.h index 56fbe2dc59b1..3e6cf2b25a97 100644 --- a/include/linux/soc/cirrus/ep93xx.h +++ b/include/linux/soc/cirrus/ep93xx.h @@ -2,7 +2,18 @@ #ifndef _SOC_EP93XX_H #define _SOC_EP93XX_H -struct platform_device; +struct regmap; +struct spinlock_t; + +enum ep93xx_soc_model { + EP93XX_9301_SOC, + EP93XX_9307_SOC, + EP93XX_9312_SOC, +}; + +#include <linux/auxiliary_bus.h> +#include <linux/compiler_types.h> +#include <linux/container_of.h> #define EP93XX_CHIP_REV_D0 3 #define EP93XX_CHIP_REV_D1 4 @@ -10,28 +21,18 @@ struct platform_device; #define EP93XX_CHIP_REV_E1 6 #define EP93XX_CHIP_REV_E2 7 -#ifdef CONFIG_ARCH_EP93XX -int ep93xx_pwm_acquire_gpio(struct platform_device *pdev); -void ep93xx_pwm_release_gpio(struct platform_device *pdev); -int ep93xx_ide_acquire_gpio(struct platform_device *pdev); -void ep93xx_ide_release_gpio(struct platform_device *pdev); -int ep93xx_keypad_acquire_gpio(struct platform_device *pdev); -void ep93xx_keypad_release_gpio(struct platform_device *pdev); -int ep93xx_i2s_acquire(void); -void ep93xx_i2s_release(void); -unsigned int ep93xx_chip_revision(void); +struct ep93xx_regmap_adev { + struct auxiliary_device adev; + struct regmap *map; + void __iomem *base; + spinlock_t *lock; + void (*write)(struct regmap *map, spinlock_t *lock, unsigned int reg, + unsigned int val); + void (*update_bits)(struct regmap *map, spinlock_t *lock, + unsigned int reg, unsigned int mask, unsigned int val); +}; -#else -static inline int ep93xx_pwm_acquire_gpio(struct platform_device *pdev) { return 0; } -static inline void ep93xx_pwm_release_gpio(struct platform_device *pdev) {} -static inline int ep93xx_ide_acquire_gpio(struct platform_device *pdev) { return 0; } -static inline void ep93xx_ide_release_gpio(struct platform_device *pdev) {} -static inline int ep93xx_keypad_acquire_gpio(struct platform_device *pdev) { return 0; } -static inline void ep93xx_keypad_release_gpio(struct platform_device *pdev) {} -static inline int ep93xx_i2s_acquire(void) { return 0; } -static inline void ep93xx_i2s_release(void) {} -static inline unsigned int ep93xx_chip_revision(void) { return 0; } - -#endif +#define to_ep93xx_regmap_adev(_adev) \ + container_of((_adev), struct ep93xx_regmap_adev, adev) #endif diff --git a/include/linux/soc/mediatek/dvfsrc.h b/include/linux/soc/mediatek/dvfsrc.h new file mode 100644 index 000000000000..1498b3ed396b --- /dev/null +++ b/include/linux/soc/mediatek/dvfsrc.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * Copyright (c) 2021 MediaTek Inc. + * Copyright (c) 2024 Collabora Ltd. + * AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com> + */ + +#ifndef __MEDIATEK_DVFSRC_H +#define __MEDIATEK_DVFSRC_H + +enum mtk_dvfsrc_cmd { + MTK_DVFSRC_CMD_BW, + MTK_DVFSRC_CMD_HRT_BW, + MTK_DVFSRC_CMD_PEAK_BW, + MTK_DVFSRC_CMD_OPP, + MTK_DVFSRC_CMD_VCORE_LEVEL, + MTK_DVFSRC_CMD_VSCP_LEVEL, + MTK_DVFSRC_CMD_MAX, +}; + +#if IS_ENABLED(CONFIG_MTK_DVFSRC) + +int mtk_dvfsrc_send_request(const struct device *dev, u32 cmd, u64 data); +int mtk_dvfsrc_query_info(const struct device *dev, u32 cmd, int *data); + +#else + +static inline int mtk_dvfsrc_send_request(const struct device *dev, u32 cmd, u64 data) +{ return -ENODEV; } + +static inline int mtk_dvfsrc_query_info(const struct device *dev, u32 cmd, int *data) +{ return -ENODEV; } + +#endif /* CONFIG_MTK_DVFSRC */ + +#endif diff --git a/include/linux/soc/mediatek/infracfg.h b/include/linux/soc/mediatek/infracfg.h index 6c6cccc848f4..9956e18c5ffa 100644 --- a/include/linux/soc/mediatek/infracfg.h +++ b/include/linux/soc/mediatek/infracfg.h @@ -434,6 +434,11 @@ #define MT7622_TOP_AXI_PROT_EN_WB (BIT(2) | BIT(6) | \ BIT(7) | BIT(8)) +#define MT6735_TOP_AXI_PROT_EN_CONN (BIT(2) | BIT(8)) +#define MT6735_TOP_AXI_PROT_EN_MD1 (BIT(24) | BIT(25) | \ + BIT(26) | BIT(27) | \ + BIT(28)) + #define INFRA_TOPAXI_PROTECTEN 0x0220 #define INFRA_TOPAXI_PROTECTSTA1 0x0228 #define INFRA_TOPAXI_PROTECTEN_SET 0x0260 diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h index 649955d2cf5c..0c3906e8ad19 100644 --- a/include/linux/soc/mediatek/mtk-cmdq.h +++ b/include/linux/soc/mediatek/mtk-cmdq.h @@ -14,8 +14,42 @@ #define CMDQ_ADDR_HIGH(addr) ((u32)(((addr) >> 16) & GENMASK(31, 0))) #define CMDQ_ADDR_LOW(addr) ((u16)(addr) | BIT(1)) +/* + * Every cmdq thread has its own SPRs (Specific Purpose Registers), + * so there are 4 * N (threads) SPRs in GCE that shares the same indexes below. + */ +#define CMDQ_THR_SPR_IDX0 (0) +#define CMDQ_THR_SPR_IDX1 (1) +#define CMDQ_THR_SPR_IDX2 (2) +#define CMDQ_THR_SPR_IDX3 (3) + struct cmdq_pkt; +enum cmdq_logic_op { + CMDQ_LOGIC_ASSIGN = 0, + CMDQ_LOGIC_ADD = 1, + CMDQ_LOGIC_SUBTRACT = 2, + CMDQ_LOGIC_MULTIPLY = 3, + CMDQ_LOGIC_XOR = 8, + CMDQ_LOGIC_NOT = 9, + CMDQ_LOGIC_OR = 10, + CMDQ_LOGIC_AND = 11, + CMDQ_LOGIC_LEFT_SHIFT = 12, + CMDQ_LOGIC_RIGHT_SHIFT = 13, + CMDQ_LOGIC_MAX, +}; + +struct cmdq_operand { + /* register type */ + bool reg; + union { + /* index */ + u16 idx; + /* value */ + u16 value; + }; +}; + struct cmdq_client_reg { u8 subsys; u16 offset; @@ -62,17 +96,19 @@ void cmdq_mbox_destroy(struct cmdq_client *client); /** * cmdq_pkt_create() - create a CMDQ packet * @client: the CMDQ mailbox client + * @pkt: the CMDQ packet * @size: required CMDQ buffer size * - * Return: CMDQ packet pointer + * Return: 0 for success; else the error code is returned */ -struct cmdq_pkt *cmdq_pkt_create(struct cmdq_client *client, size_t size); +int cmdq_pkt_create(struct cmdq_client *client, struct cmdq_pkt *pkt, size_t size); /** * cmdq_pkt_destroy() - destroy the CMDQ packet + * @client: the CMDQ mailbox client * @pkt: the CMDQ packet */ -void cmdq_pkt_destroy(struct cmdq_pkt *pkt); +void cmdq_pkt_destroy(struct cmdq_client *client, struct cmdq_pkt *pkt); /** * cmdq_pkt_write() - append write command to the CMDQ packet @@ -174,6 +210,18 @@ int cmdq_pkt_write_s_mask_value(struct cmdq_pkt *pkt, u8 high_addr_reg_idx, u16 addr_low, u32 value, u32 mask); /** + * cmdq_pkt_mem_move() - append memory move command to the CMDQ packet + * @pkt: the CMDQ packet + * @src_addr: source address + * @dst_addr: destination address + * + * Appends a CMDQ command to copy the value found in `src_addr` to `dst_addr`. + * + * Return: 0 for success; else the error code is returned + */ +int cmdq_pkt_mem_move(struct cmdq_pkt *pkt, dma_addr_t src_addr, dma_addr_t dst_addr); + +/** * cmdq_pkt_wfe() - append wait for event command to the CMDQ packet * @pkt: the CMDQ packet * @event: the desired event type to wait @@ -184,6 +232,21 @@ int cmdq_pkt_write_s_mask_value(struct cmdq_pkt *pkt, u8 high_addr_reg_idx, int cmdq_pkt_wfe(struct cmdq_pkt *pkt, u16 event, bool clear); /** + * cmdq_pkt_acquire_event() - append acquire event command to the CMDQ packet + * @pkt: the CMDQ packet + * @event: the desired event to be acquired + * + * User can use cmdq_pkt_acquire_event() as `mutex_lock` and cmdq_pkt_clear_event() + * as `mutex_unlock` to protect some `critical section` instructions between them. + * cmdq_pkt_acquire_event() would wait for event to be cleared. + * After event is cleared by cmdq_pkt_clear_event in other GCE threads, + * cmdq_pkt_acquire_event() would set event and keep executing next instruction. + * + * Return: 0 for success; else the error code is returned + */ +int cmdq_pkt_acquire_event(struct cmdq_pkt *pkt, u16 event); + +/** * cmdq_pkt_clear_event() - append clear event command to the CMDQ packet * @pkt: the CMDQ packet * @event: the desired event to be cleared @@ -235,6 +298,23 @@ int cmdq_pkt_poll_mask(struct cmdq_pkt *pkt, u8 subsys, u16 offset, u32 value, u32 mask); /** + * cmdq_pkt_logic_command() - Append logic command to the CMDQ packet, ask GCE to + * execute an instruction that store the result of logic operation + * with left and right operand into result_reg_idx. + * @pkt: the CMDQ packet + * @result_reg_idx: SPR index that store operation result of left_operand and right_operand + * @left_operand: left operand + * @s_op: the logic operator enum + * @right_operand: right operand + * + * Return: 0 for success; else the error code is returned + */ +int cmdq_pkt_logic_command(struct cmdq_pkt *pkt, u16 result_reg_idx, + struct cmdq_operand *left_operand, + enum cmdq_logic_op s_op, + struct cmdq_operand *right_operand); + +/** * cmdq_pkt_assign() - Append logic assign command to the CMDQ packet, ask GCE * to execute an instruction that set a constant value into * internal register and use as value, mask or address in @@ -248,36 +328,68 @@ int cmdq_pkt_poll_mask(struct cmdq_pkt *pkt, u8 subsys, int cmdq_pkt_assign(struct cmdq_pkt *pkt, u16 reg_idx, u32 value); /** - * cmdq_pkt_jump() - Append jump command to the CMDQ packet, ask GCE - * to execute an instruction that change current thread PC to - * a physical address which should contains more instruction. + * cmdq_pkt_poll_addr() - Append blocking POLL command to CMDQ packet + * @pkt: the CMDQ packet + * @addr: the hardware register address + * @value: the specified target register value + * @mask: the specified target register mask + * + * Appends a polling (POLL) command to the CMDQ packet and asks the GCE + * to execute an instruction that checks for the specified `value` (with + * or without `mask`) to appear in the specified hardware register `addr`. + * All GCE threads will be blocked by this instruction. + * + * Return: 0 for success or negative error code + */ +int cmdq_pkt_poll_addr(struct cmdq_pkt *pkt, dma_addr_t addr, u32 value, u32 mask); + +/** + * cmdq_pkt_jump_abs() - Append jump command to the CMDQ packet, ask GCE + * to execute an instruction that change current thread + * PC to a absolute physical address which should + * contains more instruction. * @pkt: the CMDQ packet - * @addr: physical address of target instruction buffer + * @addr: absolute physical address of target instruction buffer + * @shift_pa: shift bits of physical address in CMDQ instruction. This value + * is got by cmdq_get_shift_pa(). * * Return: 0 for success; else the error code is returned */ -int cmdq_pkt_jump(struct cmdq_pkt *pkt, dma_addr_t addr); +int cmdq_pkt_jump_abs(struct cmdq_pkt *pkt, dma_addr_t addr, u8 shift_pa); + +/* This wrapper has to be removed after all users migrated to jump_abs */ +static inline int cmdq_pkt_jump(struct cmdq_pkt *pkt, dma_addr_t addr, u8 shift_pa) +{ + return cmdq_pkt_jump_abs(pkt, addr, shift_pa); +} /** - * cmdq_pkt_finalize() - Append EOC and jump command to pkt. + * cmdq_pkt_jump_rel() - Append jump command to the CMDQ packet, ask GCE + * to execute an instruction that change current thread + * PC to a physical address with relative offset. The + * target address should contains more instruction. * @pkt: the CMDQ packet + * @offset: relative offset of target instruction buffer from current PC. + * @shift_pa: shift bits of physical address in CMDQ instruction. This value + * is got by cmdq_get_shift_pa(). * * Return: 0 for success; else the error code is returned */ -int cmdq_pkt_finalize(struct cmdq_pkt *pkt); +int cmdq_pkt_jump_rel(struct cmdq_pkt *pkt, s32 offset, u8 shift_pa); /** - * cmdq_pkt_flush_async() - trigger CMDQ to asynchronously execute the CMDQ - * packet and call back at the end of done packet - * @pkt: the CMDQ packet + * cmdq_pkt_eoc() - Append EOC and ask GCE to generate an IRQ at end of execution + * @pkt: The CMDQ packet * - * Return: 0 for success; else the error code is returned + * Appends an End Of Code (EOC) command to the CMDQ packet and asks the GCE + * to generate an interrupt at the end of the execution of all commands in + * the pipeline. + * The EOC command is usually appended to the end of the pipeline to notify + * that all commands are done. * - * Trigger CMDQ to asynchronously execute the CMDQ packet and call back - * at the end of done packet. Note that this is an ASYNC function. When the - * function returned, it may or may not be finished. + * Return: 0 for success or negative error number */ -int cmdq_pkt_flush_async(struct cmdq_pkt *pkt); +int cmdq_pkt_eoc(struct cmdq_pkt *pkt); #else /* IS_ENABLED(CONFIG_MTK_CMDQ) */ @@ -294,12 +406,12 @@ static inline struct cmdq_client *cmdq_mbox_create(struct device *dev, int index static inline void cmdq_mbox_destroy(struct cmdq_client *client) { } -static inline struct cmdq_pkt *cmdq_pkt_create(struct cmdq_client *client, size_t size) +static inline int cmdq_pkt_create(struct cmdq_client *client, struct cmdq_pkt *pkt, size_t size) { - return ERR_PTR(-EINVAL); + return -EINVAL; } -static inline void cmdq_pkt_destroy(struct cmdq_pkt *pkt) { } +static inline void cmdq_pkt_destroy(struct cmdq_client *client, struct cmdq_pkt *pkt) { } static inline int cmdq_pkt_write(struct cmdq_pkt *pkt, u8 subsys, u16 offset, u32 value) { @@ -374,17 +486,27 @@ static inline int cmdq_pkt_assign(struct cmdq_pkt *pkt, u16 reg_idx, u32 value) return -EINVAL; } -static inline int cmdq_pkt_jump(struct cmdq_pkt *pkt, dma_addr_t addr) +static inline int cmdq_pkt_poll_addr(struct cmdq_pkt *pkt, dma_addr_t addr, u32 value, u32 mask) +{ + return -EINVAL; +} + +static inline int cmdq_pkt_jump_abs(struct cmdq_pkt *pkt, dma_addr_t addr, u8 shift_pa) +{ + return -EINVAL; +} + +static inline int cmdq_pkt_jump(struct cmdq_pkt *pkt, dma_addr_t addr, u8 shift_pa) { return -EINVAL; } -static inline int cmdq_pkt_finalize(struct cmdq_pkt *pkt) +static inline int cmdq_pkt_jump_rel(struct cmdq_pkt *pkt, s32 offset, u8 shift_pa) { return -EINVAL; } -static inline int cmdq_pkt_flush_async(struct cmdq_pkt *pkt) +static inline int cmdq_pkt_eoc(struct cmdq_pkt *pkt) { return -EINVAL; } diff --git a/include/linux/soc/mediatek/mtk_sip_svc.h b/include/linux/soc/mediatek/mtk_sip_svc.h index 0761128b4354..abe24a73ee19 100644 --- a/include/linux/soc/mediatek/mtk_sip_svc.h +++ b/include/linux/soc/mediatek/mtk_sip_svc.h @@ -22,6 +22,9 @@ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, MTK_SIP_SMC_CONVENTION, \ ARM_SMCCC_OWNER_SIP, fn_id) +/* DVFSRC SMC calls */ +#define MTK_SIP_DVFSRC_VCOREFS_CONTROL MTK_SIP_SMC_CMD(0x506) + /* IOMMU related SMC call */ #define MTK_SIP_KERNEL_IOMMU_CONTROL MTK_SIP_SMC_CMD(0x514) diff --git a/include/linux/soc/qcom/apr.h b/include/linux/soc/qcom/apr.h index 7161a3183eda..a532d1e4b1f4 100644 --- a/include/linux/soc/qcom/apr.h +++ b/include/linux/soc/qcom/apr.h @@ -162,7 +162,7 @@ struct apr_driver { }; typedef struct apr_driver gpr_driver_t; -#define to_apr_driver(d) container_of(d, struct apr_driver, driver) +#define to_apr_driver(d) container_of_const(d, struct apr_driver, driver) /* * use a macro to avoid include chaining to get THIS_MODULE diff --git a/include/linux/soc/qcom/geni-se.h b/include/linux/soc/qcom/geni-se.h index 0f038a1a0330..2996a3c28ef3 100644 --- a/include/linux/soc/qcom/geni-se.h +++ b/include/linux/soc/qcom/geni-se.h @@ -88,11 +88,15 @@ struct geni_se { #define SE_GENI_M_IRQ_STATUS 0x610 #define SE_GENI_M_IRQ_EN 0x614 #define SE_GENI_M_IRQ_CLEAR 0x618 +#define SE_GENI_M_IRQ_EN_SET 0x61c +#define SE_GENI_M_IRQ_EN_CLEAR 0x620 #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_S_IRQ_EN_SET 0x64c +#define SE_GENI_S_IRQ_EN_CLEAR 0x650 #define SE_GENI_TX_FIFOn 0x700 #define SE_GENI_RX_FIFOn 0x780 #define SE_GENI_TX_FIFO_STATUS 0x800 @@ -101,6 +105,8 @@ struct geni_se { #define SE_GENI_RX_WATERMARK_REG 0x810 #define SE_GENI_RX_RFR_WATERMARK_REG 0x814 #define SE_GENI_IOS 0x908 +#define SE_GENI_M_GP_LENGTH 0x910 +#define SE_GENI_S_GP_LENGTH 0x914 #define SE_DMA_TX_IRQ_STAT 0xc40 #define SE_DMA_TX_IRQ_CLR 0xc44 #define SE_DMA_TX_FSM_RST 0xc58 @@ -234,6 +240,9 @@ struct geni_se { #define IO2_DATA_IN BIT(1) #define RX_DATA_IN BIT(0) +/* SE_GENI_M_GP_LENGTH and SE_GENI_S_GP_LENGTH fields */ +#define GP_LENGTH GENMASK(31, 0) + /* SE_DMA_TX_IRQ_STAT Register fields */ #define TX_DMA_DONE BIT(0) #define TX_EOT BIT(1) @@ -249,8 +258,8 @@ struct geni_se { #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) +#define RX_GENI_CANCEL_IRQ BIT(14) /* SE_HW_PARAM_0 fields */ #define TX_FIFO_WIDTH_MSK GENMASK(29, 24) diff --git a/include/linux/soc/qcom/llcc-qcom.h b/include/linux/soc/qcom/llcc-qcom.h index 1a886666bbb6..8e5d78fb4847 100644 --- a/include/linux/soc/qcom/llcc-qcom.h +++ b/include/linux/soc/qcom/llcc-qcom.h @@ -54,7 +54,19 @@ #define LLCC_CAMEXP4 52 #define LLCC_DISP_WB 53 #define LLCC_DISP_1 54 +#define LLCC_VIEYE 57 +#define LLCC_VIDPTH 58 +#define LLCC_GPUMV 59 +#define LLCC_EVA_LEFT 60 +#define LLCC_EVA_RIGHT 61 +#define LLCC_EVAGAIN 62 +#define LLCC_VIPTH 63 #define LLCC_VIDVSP 64 +#define LLCC_DISP_LEFT 65 +#define LLCC_DISP_RIGHT 66 +#define LLCC_EVCS_LEFT 67 +#define LLCC_EVCS_RIGHT 68 +#define LLCC_SPAD 69 /** * struct llcc_slice_desc - Cache slice descriptor @@ -115,7 +127,8 @@ struct llcc_edac_reg_offset { /** * struct llcc_drv_data - Data associated with the llcc driver * @regmaps: regmaps associated with the llcc device - * @bcast_regmap: regmap associated with llcc broadcast offset + * @bcast_regmap: regmap associated with llcc broadcast OR offset + * @bcast_and_regmap: regmap associated with llcc broadcast AND offset * @cfg: pointer to the data structure for slice configuration * @edac_reg_offset: Offset of the LLCC EDAC registers * @lock: mutex associated with each slice @@ -124,11 +137,13 @@ struct llcc_edac_reg_offset { * @num_banks: Number of llcc banks * @bitmap: Bit map to track the active slice ids * @ecc_irq: interrupt for llcc cache error detection and reporting + * @ecc_irq_configured: 'True' if firmware has already configured the irq propagation * @version: Indicates the LLCC version */ struct llcc_drv_data { struct regmap **regmaps; struct regmap *bcast_regmap; + struct regmap *bcast_and_regmap; const struct llcc_slice_config *cfg; const struct llcc_edac_reg_offset *edac_reg_offset; struct mutex lock; @@ -137,6 +152,7 @@ struct llcc_drv_data { u32 num_banks; unsigned long *bitmap; int ecc_irq; + bool ecc_irq_configured; u32 version; }; diff --git a/include/linux/soc/qcom/pmic_glink.h b/include/linux/soc/qcom/pmic_glink.h index fd124aa18c81..7cddf1027752 100644 --- a/include/linux/soc/qcom/pmic_glink.h +++ b/include/linux/soc/qcom/pmic_glink.h @@ -23,10 +23,11 @@ struct pmic_glink_hdr { 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); +struct pmic_glink_client *devm_pmic_glink_client_alloc(struct device *dev, + unsigned int id, + void (*cb)(const void *, size_t, void *), + void (*pdr)(void *, int), + void *priv); +void pmic_glink_client_register(struct pmic_glink_client *client); #endif diff --git a/include/linux/soc/qcom/smem.h b/include/linux/soc/qcom/smem.h index a36a3b9d4929..f946e3beca21 100644 --- a/include/linux/soc/qcom/smem.h +++ b/include/linux/soc/qcom/smem.h @@ -13,5 +13,8 @@ int qcom_smem_get_free_space(unsigned host); phys_addr_t qcom_smem_virt_to_phys(void *p); int qcom_smem_get_soc_id(u32 *id); +int qcom_smem_get_feature_code(u32 *code); + +int qcom_smem_bust_hwspin_lock_by_host(unsigned int host); #endif diff --git a/include/linux/soc/qcom/socinfo.h b/include/linux/soc/qcom/socinfo.h index e78777bb0f4a..608950443eee 100644 --- a/include/linux/soc/qcom/socinfo.h +++ b/include/linux/soc/qcom/socinfo.h @@ -3,6 +3,8 @@ #ifndef __QCOM_SOCINFO_H__ #define __QCOM_SOCINFO_H__ +#include <linux/types.h> + /* * SMEM item id, used to acquire handles to respective * SMEM region. @@ -12,6 +14,14 @@ #define SMEM_SOCINFO_BUILD_ID_LENGTH 32 #define SMEM_SOCINFO_CHIP_ID_LENGTH 32 +/* + * SoC version type with major number in the upper 16 bits and minor + * number in the lower 16 bits. + */ +#define SOCINFO_MAJOR(ver) (((ver) >> 16) & 0xffff) +#define SOCINFO_MINOR(ver) ((ver) & 0xffff) +#define SOCINFO_VERSION(maj, min) ((((maj) & 0xffff) << 16)|((min) & 0xffff)) + /* Socinfo SMEM item structure */ struct socinfo { __le32 fmt; @@ -74,4 +84,28 @@ struct socinfo { __le32 boot_core; }; +/* Internal feature codes */ +enum qcom_socinfo_feature_code { + /* External feature codes */ + SOCINFO_FC_UNKNOWN = 0x0, + SOCINFO_FC_AA, + SOCINFO_FC_AB, + SOCINFO_FC_AC, + SOCINFO_FC_AD, + SOCINFO_FC_AE, + SOCINFO_FC_AF, + SOCINFO_FC_AG, + SOCINFO_FC_AH, +}; + +/* Internal feature codes */ +/* Valid values: 0 <= n <= 0xf */ +#define SOCINFO_FC_Yn(n) (0xf1 + (n)) +#define SOCINFO_FC_INT_MAX SOCINFO_FC_Yn(0xf) + +/* Product codes */ +#define SOCINFO_PC_UNKNOWN 0 +#define SOCINFO_PCn(n) ((n) + 1) +#define SOCINFO_PC_RESERVE (BIT(31) - 1) + #endif diff --git a/include/linux/soc/samsung/exynos-regs-pmu.h b/include/linux/soc/samsung/exynos-regs-pmu.h index aa840ed043e1..ce1a3790d6fb 100644 --- a/include/linux/soc/samsung/exynos-regs-pmu.h +++ b/include/linux/soc/samsung/exynos-regs-pmu.h @@ -657,4 +657,10 @@ #define EXYNOS5433_PAD_RETENTION_UFS_OPTION (0x3268) #define EXYNOS5433_PAD_RETENTION_FSYSGENIO_OPTION (0x32A8) +/* For Tensor GS101 */ +#define GS101_SYSIP_DAT0 (0x810) +#define GS101_SYSTEM_CONFIGURATION (0x3A00) +#define GS101_PHY_CTRL_USB20 (0x3EB0) +#define GS101_PHY_CTRL_USBDP (0x3EB4) + #endif /* __LINUX_SOC_EXYNOS_REGS_PMU_H */ diff --git a/include/linux/soc/ti/ti_sci_protocol.h b/include/linux/soc/ti/ti_sci_protocol.h index bd0d11af76c5..fd104b666836 100644 --- a/include/linux/soc/ti/ti_sci_protocol.h +++ b/include/linux/soc/ti/ti_sci_protocol.h @@ -195,6 +195,35 @@ struct ti_sci_clk_ops { u64 *current_freq); }; +/* TISCI LPM IO isolation control values */ +#define TISCI_MSG_VALUE_IO_ENABLE 1 +#define TISCI_MSG_VALUE_IO_DISABLE 0 + +/* TISCI LPM constraint state values */ +#define TISCI_MSG_CONSTRAINT_SET 1 +#define TISCI_MSG_CONSTRAINT_CLR 0 + +/** + * struct ti_sci_pm_ops - Low Power Mode (LPM) control operations + * @lpm_wake_reason: Get the wake up source that woke the SoC from LPM + * - source: The wake up source that woke soc from LPM. + * - timestamp: Timestamp at which soc woke. + * @set_device_constraint: Set LPM constraint on behalf of a device + * - id: Device Identifier + * - state: The desired state of device constraint: set or clear. + * @set_latency_constraint: Set LPM resume latency constraint + * - latency: maximum acceptable latency to wake up from low power mode + * - state: The desired state of latency constraint: set or clear. + */ +struct ti_sci_pm_ops { + int (*lpm_wake_reason)(const struct ti_sci_handle *handle, + u32 *source, u64 *timestamp, u8 *pin, u8 *mode); + int (*set_device_constraint)(const struct ti_sci_handle *handle, + u32 id, u8 state); + int (*set_latency_constraint)(const struct ti_sci_handle *handle, + u16 latency, u8 state); +}; + /** * struct ti_sci_resource_desc - Description of TI SCI resource instance range. * @start: Start index of the first resource range. @@ -539,6 +568,7 @@ struct ti_sci_ops { struct ti_sci_core_ops core_ops; struct ti_sci_dev_ops dev_ops; struct ti_sci_clk_ops clk_ops; + struct ti_sci_pm_ops pm_ops; struct ti_sci_rm_core_ops rm_core_ops; struct ti_sci_rm_irq_ops rm_irq_ops; struct ti_sci_rm_ringacc_ops rm_ring_ops; diff --git a/include/linux/socket.h b/include/linux/socket.h index 139c330ccf2c..d18cc47e89bd 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -16,6 +16,7 @@ struct cred; struct socket; struct sock; struct sk_buff; +struct proto_accept_arg; #define __sockaddr_check_size(size) \ BUILD_BUG_ON(((size) > sizeof(struct __kernel_sockaddr_storage))) @@ -75,7 +76,7 @@ struct msghdr { __kernel_size_t msg_controllen; /* ancillary data buffer length */ struct kiocb *msg_iocb; /* ptr to iocb for async requests */ struct ubuf_info *msg_ubuf; - int (*sg_from_iter)(struct sock *sk, struct sk_buff *skb, + int (*sg_from_iter)(struct sk_buff *skb, struct iov_iter *from, size_t length); }; @@ -326,6 +327,7 @@ struct ucred { * plain text and require encryption */ +#define MSG_SOCK_DEVMEM 0x2000000 /* Receive devmem skbs as cmsg */ #define MSG_ZEROCOPY 0x4000000 /* Use user data in kernel path */ #define MSG_SPLICE_PAGES 0x8000000 /* Splice the pages from the iterator in sendmsg() */ #define MSG_FASTOPEN 0x20000000 /* Send data in TCP SYN */ @@ -433,7 +435,7 @@ extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size, extern int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags, struct sockaddr __user *addr, int addr_len); -extern struct file *do_accept(struct file *file, unsigned file_flags, +extern struct file *do_accept(struct file *file, struct proto_accept_arg *arg, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags); extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, @@ -441,11 +443,14 @@ extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, extern int __sys_socket(int family, int type, int protocol); extern struct file *__sys_socket_file(int family, int type, int protocol); extern int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen); +extern int __sys_bind_socket(struct socket *sock, struct sockaddr_storage *address, + int addrlen); extern int __sys_connect_file(struct file *file, struct sockaddr_storage *addr, int addrlen, int file_flags); extern int __sys_connect(int fd, struct sockaddr __user *uservaddr, int addrlen); extern int __sys_listen(int fd, int backlog); +extern int __sys_listen_socket(struct socket *sock, int backlog); extern int __sys_getsockname(int fd, struct sockaddr __user *usockaddr, int __user *usockaddr_len); extern int __sys_getpeername(int fd, struct sockaddr __user *usockaddr, diff --git a/include/linux/sockptr.h b/include/linux/sockptr.h index 317200cd3a60..3e6c8e9d67ae 100644 --- a/include/linux/sockptr.h +++ b/include/linux/sockptr.h @@ -53,6 +53,8 @@ static inline int copy_from_sockptr_offset(void *dst, sockptr_t src, /* Deprecated. * This is unsafe, unless caller checked user provided optlen. * Prefer copy_safe_from_sockptr() instead. + * + * Returns 0 for success, or number of bytes not copied on error. */ static inline int copy_from_sockptr(void *dst, sockptr_t src, size_t size) { @@ -77,7 +79,9 @@ static inline int copy_safe_from_sockptr(void *dst, size_t ksize, { if (optlen < ksize) return -EINVAL; - return copy_from_sockptr(dst, optval, ksize); + if (copy_from_sockptr(dst, optval, ksize)) + return -EFAULT; + return 0; } static inline int copy_struct_from_sockptr(void *dst, size_t ksize, @@ -117,9 +121,9 @@ static inline int copy_to_sockptr(sockptr_t dst, const void *src, size_t size) return copy_to_sockptr_offset(dst, 0, src, size); } -static inline void *memdup_sockptr(sockptr_t src, size_t len) +static inline void *memdup_sockptr_noprof(sockptr_t src, size_t len) { - void *p = kmalloc_track_caller(len, GFP_USER | __GFP_NOWARN); + void *p = kmalloc_track_caller_noprof(len, GFP_USER | __GFP_NOWARN); if (!p) return ERR_PTR(-ENOMEM); @@ -129,10 +133,11 @@ static inline void *memdup_sockptr(sockptr_t src, size_t len) } return p; } +#define memdup_sockptr(...) alloc_hooks(memdup_sockptr_noprof(__VA_ARGS__)) -static inline void *memdup_sockptr_nul(sockptr_t src, size_t len) +static inline void *memdup_sockptr_nul_noprof(sockptr_t src, size_t len) { - char *p = kmalloc_track_caller(len + 1, GFP_KERNEL); + char *p = kmalloc_track_caller_noprof(len + 1, GFP_KERNEL); if (!p) return ERR_PTR(-ENOMEM); @@ -143,6 +148,7 @@ static inline void *memdup_sockptr_nul(sockptr_t src, size_t len) p[len] = '\0'; return p; } +#define memdup_sockptr_nul(...) alloc_hooks(memdup_sockptr_nul_noprof(__VA_ARGS__)) static inline long strncpy_from_sockptr(char *dst, sockptr_t src, size_t count) { diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 66f814b63a43..2d6c30317792 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -4,12 +4,20 @@ #ifndef __SOUNDWIRE_H #define __SOUNDWIRE_H +#include <linux/bitfield.h> #include <linux/bug.h> -#include <linux/lockdep_types.h> +#include <linux/completion.h> +#include <linux/device.h> #include <linux/irq.h> #include <linux/irqdomain.h> +#include <linux/lockdep_types.h> #include <linux/mod_devicetable.h> -#include <linux/bitfield.h> +#include <linux/mutex.h> +#include <linux/types.h> +#include <sound/sdca.h> + +struct dentry; +struct fwnode_handle; struct sdw_bus; struct sdw_slave; @@ -46,6 +54,8 @@ struct sdw_slave; #define SDW_MAX_PORTS 15 #define SDW_VALID_PORT_RANGE(n) ((n) < SDW_MAX_PORTS && (n) >= 1) +#define SDW_MAX_LANES 8 + enum { SDW_PORT_DIRN_SINK = 0, SDW_PORT_DIRN_SOURCE, @@ -226,62 +236,36 @@ enum sdw_clk_stop_mode { /** * struct sdw_dp0_prop - DP0 properties + * @words: wordlengths supported * @max_word: Maximum number of bits in a Payload Channel Sample, 1 to 64 * (inclusive) * @min_word: Minimum number of bits in a Payload Channel Sample, 1 to 64 * (inclusive) * @num_words: number of wordlengths supported - * @words: wordlengths supported + * @ch_prep_timeout: Port-specific timeout value, in milliseconds * @BRA_flow_controlled: Slave implementation results in an OK_NotReady * response * @simple_ch_prep_sm: If channel prepare sequence is required * @imp_def_interrupts: If set, each bit corresponds to support for * implementation-defined interrupts + * @num_lanes: array size of @lane_list + * @lane_list: indicates which Lanes can be used by DP0 * * The wordlengths are specified by Spec as max, min AND number of * discrete values, implementation can define based on the wordlengths they * support */ struct sdw_dp0_prop { + u32 *words; u32 max_word; u32 min_word; u32 num_words; - u32 *words; + u32 ch_prep_timeout; bool BRA_flow_controlled; bool simple_ch_prep_sm; bool imp_def_interrupts; -}; - -/** - * struct sdw_dpn_audio_mode - Audio mode properties for DPn - * @bus_min_freq: Minimum bus frequency, in Hz - * @bus_max_freq: Maximum bus frequency, in Hz - * @bus_num_freq: Number of discrete frequencies supported - * @bus_freq: Discrete bus frequencies, in Hz - * @min_freq: Minimum sampling frequency, in Hz - * @max_freq: Maximum sampling bus frequency, in Hz - * @num_freq: Number of discrete sampling frequency supported - * @freq: Discrete sampling frequencies, in Hz - * @prep_ch_behave: Specifies the dependencies between Channel Prepare - * sequence and bus clock configuration - * If 0, Channel Prepare can happen at any Bus clock rate - * If 1, Channel Prepare sequence shall happen only after Bus clock is - * changed to a frequency supported by this mode or compatible modes - * described by the next field - * @glitchless: Bitmap describing possible glitchless transitions from this - * Audio Mode to other Audio Modes - */ -struct sdw_dpn_audio_mode { - u32 bus_min_freq; - u32 bus_max_freq; - u32 bus_num_freq; - u32 *bus_freq; - u32 max_freq; - u32 min_freq; - u32 num_freq; - u32 *freq; - u32 prep_ch_behave; - u32 glitchless; + int num_lanes; + u32 *lane_list; }; /** @@ -296,24 +280,25 @@ struct sdw_dpn_audio_mode { * @type: Data port type. Full, Simplified or Reduced * @max_grouping: Maximum number of samples that can be grouped together for * a full data port - * @simple_ch_prep_sm: If the port supports simplified channel prepare state - * machine * @ch_prep_timeout: Port-specific timeout value, in milliseconds * @imp_def_interrupts: If set, each bit corresponds to support for * implementation-defined interrupts * @max_ch: Maximum channels supported * @min_ch: Minimum channels supported * @num_channels: Number of discrete channels supported - * @channels: Discrete channels supported * @num_ch_combinations: Number of channel combinations supported + * @channels: Discrete channels supported * @ch_combinations: Channel combinations supported + * @lane_list: indicates which Lanes can be used by DPn + * @num_lanes: array size of @lane_list * @modes: SDW mode supported * @max_async_buffer: Number of samples that this port can buffer in * asynchronous modes + * @port_encoding: Payload Channel Sample encoding schemes supported * @block_pack_mode: Type of block port mode supported * @read_only_wordlength: Read Only wordlength field in DPN_BlockCtrl1 register - * @port_encoding: Payload Channel Sample encoding schemes supported - * @audio_modes: Audio modes supported + * @simple_ch_prep_sm: If the port supports simplified channel prepare state + * machine */ struct sdw_dpn_prop { u32 num; @@ -323,25 +308,29 @@ struct sdw_dpn_prop { u32 *words; enum sdw_dpn_type type; u32 max_grouping; - bool simple_ch_prep_sm; u32 ch_prep_timeout; u32 imp_def_interrupts; u32 max_ch; u32 min_ch; u32 num_channels; - u32 *channels; u32 num_ch_combinations; + u32 *channels; u32 *ch_combinations; + u32 *lane_list; + int num_lanes; u32 modes; u32 max_async_buffer; + u32 port_encoding; bool block_pack_mode; bool read_only_wordlength; - u32 port_encoding; - struct sdw_dpn_audio_mode *audio_modes; + bool simple_ch_prep_sm; }; /** * struct sdw_slave_prop - SoundWire Slave properties + * @dp0_prop: Data Port 0 properties + * @src_dpn_prop: Source Data Port N properties + * @sink_dpn_prop: Sink Data Port N properties * @mipi_revision: Spec version of the implementation * @wake_capable: Wake-up events are supported * @test_mode_capable: If test mode is supported @@ -358,23 +347,27 @@ struct sdw_dpn_prop { * SCP_AddrPage2 * @bank_delay_support: Slave implements bank delay/bridge support registers * SCP_BankDelay and SCP_NextFrame + * @lane_control_support: Slave supports lane control * @p15_behave: Slave behavior when the Master attempts a read to the Port15 * alias - * @lane_control_support: Slave supports lane control * @master_count: Number of Masters present on this Slave * @source_ports: Bitmap identifying source ports * @sink_ports: Bitmap identifying sink ports - * @dp0_prop: Data Port 0 properties - * @src_dpn_prop: Source Data Port N properties - * @sink_dpn_prop: Sink Data Port N properties - * @scp_int1_mask: SCP_INT1_MASK desired settings * @quirks: bitmask identifying deltas from the MIPI specification + * @sdca_interrupt_register_list: indicates which sets of SDCA interrupt status + * and masks are supported + * @commit_register_supported: is PCP_Commit register supported + * @scp_int1_mask: SCP_INT1_MASK desired settings + * @lane_maps: Lane mapping for the slave, only valid if lane_control_support is set * @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. * @use_domain_irq: call actual IRQ handler on slave, as well as callback */ struct sdw_slave_prop { + struct sdw_dp0_prop *dp0_prop; + struct sdw_dpn_prop *src_dpn_prop; + struct sdw_dpn_prop *sink_dpn_prop; u32 mipi_revision; bool wake_capable; bool test_mode_capable; @@ -386,16 +379,16 @@ struct sdw_slave_prop { bool high_PHY_capable; bool paging_support; bool bank_delay_support; - enum sdw_p15_behave p15_behave; bool lane_control_support; + enum sdw_p15_behave p15_behave; u32 master_count; u32 source_ports; u32 sink_ports; - struct sdw_dp0_prop *dp0_prop; - struct sdw_dpn_prop *src_dpn_prop; - struct sdw_dpn_prop *sink_dpn_prop; - u8 scp_int1_mask; u32 quirks; + u32 sdca_interrupt_register_list; + u8 commit_register_supported; + u8 scp_int1_mask; + u8 lane_maps[SDW_MAX_LANES]; bool clock_reg_supported; bool use_domain_irq; }; @@ -404,13 +397,14 @@ struct sdw_slave_prop { /** * struct sdw_master_prop - Master properties + * @clk_gears: Clock gears supported + * @clk_freq: Clock frequencies supported, in Hz + * @quirks: bitmask identifying optional behavior beyond the scope of the MIPI specification * @revision: MIPI spec version of the implementation * @clk_stop_modes: Bitmap, bit N set when clock-stop-modeN supported * @max_clk_freq: Maximum Bus clock frequency, in Hz * @num_clk_gears: Number of clock gears supported - * @clk_gears: Clock gears supported * @num_clk_freq: Number of clock frequencies supported, in Hz - * @clk_freq: Clock frequencies supported, in Hz * @default_frame_rate: Controller default Frame rate, in Hz * @default_row: Number of rows * @default_col: Number of columns @@ -419,24 +413,23 @@ struct sdw_slave_prop { * command * @mclk_freq: clock reference passed to SoundWire Master, in Hz. * @hw_disabled: if true, the Master is not functional, typically due to pin-mux - * @quirks: bitmask identifying optional behavior beyond the scope of the MIPI specification */ struct sdw_master_prop { + u32 *clk_gears; + u32 *clk_freq; + u64 quirks; u32 revision; u32 clk_stop_modes; u32 max_clk_freq; u32 num_clk_gears; - u32 *clk_gears; u32 num_clk_freq; - u32 *clk_freq; u32 default_frame_rate; u32 default_row; u32 default_col; - bool dynamic_frame; u32 err_threshold; u32 mclk_freq; + bool dynamic_frame; bool hw_disabled; - u64 quirks; }; /* Definitions for Master quirks */ @@ -461,6 +454,7 @@ struct sdw_master_prop { int sdw_master_read_prop(struct sdw_bus *bus); int sdw_slave_read_prop(struct sdw_slave *slave); +int sdw_slave_read_lane_mapping(struct sdw_slave *slave); /* * SDW Slave Structures and APIs @@ -486,9 +480,9 @@ struct sdw_slave_id { __u8 sdw_version:4; }; -struct sdw_extended_slave_id { - int link_id; - struct sdw_slave_id id; +struct sdw_peripherals { + int num_peripherals; + struct sdw_slave *array[]; }; /* @@ -543,21 +537,6 @@ enum sdw_reg_bank { }; /** - * struct sdw_bus_conf: Bus configuration - * - * @clk_freq: Clock frequency, in Hz - * @num_rows: Number of rows in frame - * @num_cols: Number of columns in frame - * @bank: Next register bank - */ -struct sdw_bus_conf { - unsigned int clk_freq; - unsigned int num_rows; - unsigned int num_cols; - unsigned int bank; -}; - -/** * struct sdw_prepare_ch: Prepare/De-prepare Data Port channel * * @num: Port number @@ -643,7 +622,6 @@ struct sdw_slave_ops { int (*clk_stop)(struct sdw_slave *slave, enum sdw_clk_stop_mode mode, enum sdw_clk_stop_type type); - }; /** @@ -676,6 +654,7 @@ struct sdw_slave_ops { * @is_mockup_device: status flag used to squelch errors in the command/control * protocol for SoundWire mockup devices * @sdw_dev_lock: mutex used to protect callbacks/remove races + * @sdca_data: structure containing all device data for SDCA helpers */ struct sdw_slave { struct sdw_slave_id id; @@ -699,6 +678,7 @@ struct sdw_slave { bool first_interrupt_done; bool is_mockup_device; struct mutex sdw_dev_lock; /* protect callbacks/remove races */ + struct sdca_device_data sdca_data; }; #define dev_to_sdw_dev(_dev) container_of(_dev, struct sdw_slave, dev) @@ -717,10 +697,7 @@ struct sdw_master_device { container_of(d, struct sdw_master_device, dev) struct sdw_driver { - const char *name; - - int (*probe)(struct sdw_slave *sdw, - const struct sdw_device_id *id); + int (*probe)(struct sdw_slave *sdw, const struct sdw_device_id *id); int (*remove)(struct sdw_slave *sdw); void (*shutdown)(struct sdw_slave *sdw); @@ -739,7 +716,7 @@ struct sdw_driver { SDW_SLAVE_ENTRY_EXT((_mfg_id), (_part_id), 0, 0, (_drv_data)) int sdw_handle_slave_status(struct sdw_bus *bus, - enum sdw_slave_status status[]); + enum sdw_slave_status status[]); /* * SDW master structures and APIs @@ -821,29 +798,28 @@ struct sdw_enable_ch { */ struct sdw_master_port_ops { int (*dpn_set_port_params)(struct sdw_bus *bus, - struct sdw_port_params *port_params, - unsigned int bank); + struct sdw_port_params *port_params, + unsigned int bank); int (*dpn_set_port_transport_params)(struct sdw_bus *bus, - struct sdw_transport_params *transport_params, - enum sdw_reg_bank bank); - int (*dpn_port_prep)(struct sdw_bus *bus, - struct sdw_prepare_ch *prepare_ch); + struct sdw_transport_params *transport_params, + enum sdw_reg_bank bank); + int (*dpn_port_prep)(struct sdw_bus *bus, struct sdw_prepare_ch *prepare_ch); int (*dpn_port_enable_ch)(struct sdw_bus *bus, - struct sdw_enable_ch *enable_ch, unsigned int bank); + struct sdw_enable_ch *enable_ch, unsigned int bank); }; struct sdw_msg; /** - * struct sdw_defer - SDW deffered message - * @length: message length + * struct sdw_defer - SDW deferred message * @complete: message completion * @msg: SDW message + * @length: message length */ struct sdw_defer { + struct sdw_msg *msg; int length; struct completion complete; - struct sdw_msg *msg; }; /** @@ -864,14 +840,11 @@ struct sdw_defer { */ struct sdw_master_ops { int (*read_prop)(struct sdw_bus *bus); - u64 (*override_adr) - (struct sdw_bus *bus, u64 addr); - 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); + u64 (*override_adr)(struct sdw_bus *bus, u64 addr); + 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); int (*set_bus_conf)(struct sdw_bus *bus, - struct sdw_bus_params *params); + struct sdw_bus_params *params); int (*pre_bank_switch)(struct sdw_bus *bus); int (*post_bank_switch)(struct sdw_bus *bus); u32 (*read_ping_status)(struct sdw_bus *bus); @@ -882,70 +855,6 @@ struct sdw_master_ops { int dev_num); }; -/** - * struct sdw_bus - SoundWire bus - * @dev: Shortcut to &bus->md->dev to avoid changing the entire code. - * @md: Master device - * @controller_id: system-unique controller ID. If set to -1, the bus @id will be used. - * @link_id: Link id number, can be 0 to N, unique for each Controller - * @id: bus system-wide unique id - * @slaves: list of Slaves on this bus - * @assigned: Bitmap for Slave device numbers. - * Bit set implies used number, bit clear implies unused number. - * @bus_lock: bus lock - * @msg_lock: message lock - * @compute_params: points to Bus resource management implementation - * @ops: Master callback ops - * @port_ops: Master port callback ops - * @params: Current bus parameters - * @prop: Master properties - * @m_rt_list: List of Master instance of all stream(s) running on Bus. This - * is used to compute and program bus bandwidth, clock, frame shape, - * transport and port parameters - * @debugfs: Bus debugfs - * @domain: IRQ domain - * @defer_msg: Defer message - * @clk_stop_timeout: Clock stop timeout computed - * @bank_switch_timeout: Bank switch timeout computed - * @multi_link: Store bus property that indicates if multi links - * are supported. This flag is populated by drivers after reading - * appropriate firmware (ACPI/DT). - * @hw_sync_min_links: Number of links used by a stream above which - * hardware-based synchronization is required. This value is only - * meaningful if multi_link is set. If set to 1, hardware-based - * synchronization will be used even if a stream only uses a single - * SoundWire segment. - */ -struct sdw_bus { - struct device *dev; - struct sdw_master_device *md; - int controller_id; - unsigned int link_id; - int id; - struct list_head slaves; - DECLARE_BITMAP(assigned, SDW_MAX_DEVICES); - struct mutex bus_lock; - struct lock_class_key bus_lock_key; - struct mutex msg_lock; - struct lock_class_key msg_lock_key; - int (*compute_params)(struct sdw_bus *bus); - const struct sdw_master_ops *ops; - const struct sdw_master_port_ops *port_ops; - struct sdw_bus_params params; - struct sdw_master_prop prop; - struct list_head m_rt_list; -#ifdef CONFIG_DEBUG_FS - struct dentry *debugfs; -#endif - struct irq_chip irq_chip; - struct irq_domain *domain; - struct sdw_defer defer_msg; - unsigned int clk_stop_timeout; - u32 bank_switch_timeout; - bool multi_link; - int hw_sync_min_links; -}; - int sdw_bus_master_add(struct sdw_bus *bus, struct device *parent, struct fwnode_handle *fwnode); void sdw_bus_master_delete(struct sdw_bus *bus); @@ -1021,32 +930,105 @@ struct sdw_stream_params { * @params: Stream parameters * @state: Current state of the stream * @type: Stream type PCM or PDM + * @m_rt_count: Count of Master runtime(s) in this stream * @master_list: List of Master runtime(s) in this stream. * master_list can contain only one m_rt per Master instance * for a stream - * @m_rt_count: Count of Master runtime(s) in this stream */ struct sdw_stream_runtime { const char *name; struct sdw_stream_params params; enum sdw_stream_state state; enum sdw_stream_type type; - struct list_head master_list; int m_rt_count; + struct list_head master_list; +}; + +/** + * struct sdw_bus - SoundWire bus + * @dev: Shortcut to &bus->md->dev to avoid changing the entire code. + * @md: Master device + * @bus_lock_key: bus lock key associated to @bus_lock + * @bus_lock: bus lock + * @slaves: list of Slaves on this bus + * @msg_lock_key: message lock key associated to @msg_lock + * @msg_lock: message lock + * @m_rt_list: List of Master instance of all stream(s) running on Bus. This + * is used to compute and program bus bandwidth, clock, frame shape, + * transport and port parameters + * @defer_msg: Defer message + * @params: Current bus parameters + * @stream_refcount: number of streams currently using this bus + * @ops: Master callback ops + * @port_ops: Master port callback ops + * @prop: Master properties + * @vendor_specific_prop: pointer to non-standard properties + * @hw_sync_min_links: Number of links used by a stream above which + * hardware-based synchronization is required. This value is only + * meaningful if multi_link is set. If set to 1, hardware-based + * synchronization will be used even if a stream only uses a single + * SoundWire segment. + * @controller_id: system-unique controller ID. If set to -1, the bus @id will be used. + * @link_id: Link id number, can be 0 to N, unique for each Controller + * @id: bus system-wide unique id + * @compute_params: points to Bus resource management implementation + * @assigned: Bitmap for Slave device numbers. + * Bit set implies used number, bit clear implies unused number. + * @clk_stop_timeout: Clock stop timeout computed + * @bank_switch_timeout: Bank switch timeout computed + * @domain: IRQ domain + * @irq_chip: IRQ chip + * @debugfs: Bus debugfs (optional) + * @multi_link: Store bus property that indicates if multi links + * are supported. This flag is populated by drivers after reading + * appropriate firmware (ACPI/DT). + * @lane_used_bandwidth: how much bandwidth in bits per second is used by each lane + */ +struct sdw_bus { + struct device *dev; + struct sdw_master_device *md; + struct lock_class_key bus_lock_key; + struct mutex bus_lock; + struct list_head slaves; + struct lock_class_key msg_lock_key; + struct mutex msg_lock; + struct list_head m_rt_list; + struct sdw_defer defer_msg; + struct sdw_bus_params params; + int stream_refcount; + const struct sdw_master_ops *ops; + const struct sdw_master_port_ops *port_ops; + struct sdw_master_prop prop; + void *vendor_specific_prop; + int hw_sync_min_links; + int controller_id; + unsigned int link_id; + int id; + int (*compute_params)(struct sdw_bus *bus, struct sdw_stream_runtime *stream); + DECLARE_BITMAP(assigned, SDW_MAX_DEVICES); + unsigned int clk_stop_timeout; + u32 bank_switch_timeout; + struct irq_chip irq_chip; + struct irq_domain *domain; +#ifdef CONFIG_DEBUG_FS + struct dentry *debugfs; +#endif + bool multi_link; + unsigned int lane_used_bandwidth[SDW_MAX_LANES]; }; struct sdw_stream_runtime *sdw_alloc_stream(const char *stream_name); void sdw_release_stream(struct sdw_stream_runtime *stream); -int sdw_compute_params(struct sdw_bus *bus); +int sdw_compute_params(struct sdw_bus *bus, struct sdw_stream_runtime *stream); int sdw_stream_add_master(struct sdw_bus *bus, - struct sdw_stream_config *stream_config, - const struct sdw_port_config *port_config, - unsigned int num_ports, - struct sdw_stream_runtime *stream); + struct sdw_stream_config *stream_config, + const 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); + 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); @@ -1059,6 +1041,7 @@ int sdw_bus_exit_clk_stop(struct sdw_bus *bus); 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); +bool is_clock_scaling_supported_by_slave(struct sdw_slave *slave); #if IS_ENABLED(CONFIG_SOUNDWIRE) @@ -1070,6 +1053,8 @@ int sdw_stream_add_slave(struct sdw_slave *slave, int sdw_stream_remove_slave(struct sdw_slave *slave, struct sdw_stream_runtime *stream); +int sdw_slave_get_scale_index(struct sdw_slave *slave, u8 *base); + /* messaging and data APIs */ int sdw_read(struct sdw_slave *slave, u32 addr); int sdw_write(struct sdw_slave *slave, u32 addr, u8 value); diff --git a/include/linux/soundwire/sdw_amd.h b/include/linux/soundwire/sdw_amd.h index 28a4eb77717f..799f8578137b 100644 --- a/include/linux/soundwire/sdw_amd.h +++ b/include/linux/soundwire/sdw_amd.h @@ -27,9 +27,11 @@ #define ACP_SDW0 0 #define ACP_SDW1 1 #define AMD_SDW_MAX_MANAGER_COUNT 2 +#define ACP63_PCI_REV_ID 0x63 struct acp_sdw_pdata { u16 instance; + u32 acp_rev; /* mutex to protect acp common register access */ struct mutex *acp_sdw_lock; }; @@ -66,6 +68,7 @@ struct sdw_amd_dai_runtime { * @instance: SoundWire manager instance * @quirks: SoundWire manager quirks * @wake_en_mask: wake enable mask per SoundWire manager + * @acp_rev: acp pci device revision id * @clk_stopped: flag set to true when clock is stopped * @power_mode_mask: flag interprets amd SoundWire manager power mode * @dai_runtime_array: dai runtime array @@ -94,6 +97,7 @@ struct amd_sdw_manager { u32 quirks; u32 wake_en_mask; u32 power_mode_mask; + u32 acp_rev; bool clk_stopped; struct sdw_amd_dai_runtime **dai_runtime_array; @@ -115,25 +119,23 @@ struct sdw_amd_acpi_info { * struct sdw_amd_ctx - context allocated by the controller driver probe * * @count: link count - * @num_slaves: total number of devices exposed across all enabled links * @link_mask: bit-wise mask listing SoundWire links reported by the * Controller - * @ids: array of slave_id, representing Slaves exposed across all enabled - * links * @pdev: platform device structure + * @peripherals: array representing Peripherals exposed across all enabled links */ struct sdw_amd_ctx { int count; - int num_slaves; u32 link_mask; - struct sdw_extended_slave_id *ids; struct platform_device *pdev[AMD_SDW_MAX_MANAGER_COUNT]; + struct sdw_peripherals *peripherals; }; /** * struct sdw_amd_res - Soundwire AMD global resource structure, * typically populated by the DSP driver/Legacy driver * + * @acp_rev: acp pci device revision id * @addr: acp pci device resource start address * @reg_range: ACP register range * @link_mask: bit-wise mask listing links selected by the DSP driver/ @@ -146,6 +148,7 @@ struct sdw_amd_ctx { * @acp_lock: mutex protecting acp common registers access */ struct sdw_amd_res { + u32 acp_rev; u32 addr; u32 reg_range; u32 link_mask; diff --git a/include/linux/soundwire/sdw_intel.h b/include/linux/soundwire/sdw_intel.h index 00bb22d96ae5..580086417e4b 100644 --- a/include/linux/soundwire/sdw_intel.h +++ b/include/linux/soundwire/sdw_intel.h @@ -4,6 +4,7 @@ #ifndef __SDW_INTEL_H #define __SDW_INTEL_H +#include <linux/acpi.h> #include <linux/irqreturn.h> #include <linux/soundwire/sdw.h> @@ -22,6 +23,7 @@ /* LCAP */ #define SDW_SHIM_LCAP 0x0 #define SDW_SHIM_LCAP_LCOUNT_MASK GENMASK(2, 0) +#define SDW_SHIM_LCAP_MLCS_MASK BIT(8) /* LCTL */ #define SDW_SHIM_LCTL 0x4 @@ -30,12 +32,18 @@ #define SDW_SHIM_LCTL_SPA_MASK GENMASK(3, 0) #define SDW_SHIM_LCTL_CPA BIT(8) #define SDW_SHIM_LCTL_CPA_MASK GENMASK(11, 8) +#define SDW_SHIM_LCTL_MLCS_MASK GENMASK(29, 27) +#define SDW_SHIM_MLCS_XTAL_CLK 0x0 +#define SDW_SHIM_MLCS_CARDINAL_CLK 0x1 +#define SDW_SHIM_MLCS_AUDIO_PLL_CLK 0x2 /* SYNC */ #define SDW_SHIM_SYNC 0xC -#define SDW_SHIM_SYNC_SYNCPRD_VAL_24 (24000 / SDW_CADENCE_GSYNC_KHZ - 1) -#define SDW_SHIM_SYNC_SYNCPRD_VAL_38_4 (38400 / SDW_CADENCE_GSYNC_KHZ - 1) +#define SDW_SHIM_SYNC_SYNCPRD_VAL_24 (24000 / SDW_CADENCE_GSYNC_KHZ - 1) +#define SDW_SHIM_SYNC_SYNCPRD_VAL_24_576 (24576 / SDW_CADENCE_GSYNC_KHZ - 1) +#define SDW_SHIM_SYNC_SYNCPRD_VAL_38_4 (38400 / SDW_CADENCE_GSYNC_KHZ - 1) +#define SDW_SHIM_SYNC_SYNCPRD_VAL_96 (96000 / SDW_CADENCE_GSYNC_KHZ - 1) #define SDW_SHIM_SYNC_SYNCPRD GENMASK(14, 0) #define SDW_SHIM_SYNC_SYNCCPU BIT(15) #define SDW_SHIM_SYNC_CMDSYNC_MASK GENMASK(19, 16) @@ -175,6 +183,11 @@ #define SDW_SHIM2_INTEL_VS_ACTMCTL_DODSE BIT(2) #define SDW_SHIM2_INTEL_VS_ACTMCTL_DOAIS GENMASK(4, 3) #define SDW_SHIM2_INTEL_VS_ACTMCTL_DOAISE BIT(5) +#define SDW_SHIM3_INTEL_VS_ACTMCTL_CLSS BIT(6) +#define SDW_SHIM3_INTEL_VS_ACTMCTL_CLDS GENMASK(11, 7) +#define SDW_SHIM3_INTEL_VS_ACTMCTL_DODSE2 GENMASK(13, 12) +#define SDW_SHIM3_INTEL_VS_ACTMCTL_DOAISE2 BIT(14) +#define SDW_SHIM3_INTEL_VS_ACTMCTL_CLDE BIT(15) /** * struct sdw_intel_stream_params_data: configuration passed during @@ -215,7 +228,7 @@ struct sdw_intel_ops { /** * struct sdw_intel_acpi_info - Soundwire Intel information found in ACPI tables * @handle: ACPI controller handle - * @count: link count found with "sdw-master-count" property + * @count: link count found with "sdw-master-count" or "sdw-manager-list" property * @link_mask: bit-wise mask listing links enabled by BIOS menu * * this structure could be expanded to e.g. provide all the _ADR @@ -274,31 +287,28 @@ struct hdac_bus; * hardware capabilities after all power dependencies are settled. * @link_mask: bit-wise mask listing SoundWire links reported by the * Controller - * @num_slaves: total number of devices exposed across all enabled links * @handle: ACPI parent handle * @ldev: information for each link (controller-specific and kept * opaque here) - * @ids: array of slave_id, representing Slaves exposed across all enabled - * links * @link_list: list to handle interrupts across all links * @shim_lock: mutex to handle concurrent rmw access to shared SHIM registers. * @shim_mask: flags to track initialization of SHIM shared registers * @shim_base: sdw shim base. * @alh_base: sdw alh base. + * @peripherals: array representing Peripherals exposed across all enabled links */ struct sdw_intel_ctx { int count; void __iomem *mmio_base; u32 link_mask; - int num_slaves; acpi_handle handle; struct sdw_intel_link_dev **ldev; - struct sdw_extended_slave_id *ids; struct list_head link_list; struct mutex shim_lock; /* lock for access to shared SHIM registers */ u32 shim_mask; u32 shim_base; u32 alh_base; + struct sdw_peripherals *peripherals; }; /** @@ -376,6 +386,7 @@ struct sdw_intel; /* struct intel_sdw_hw_ops - SoundWire ops for Intel platforms. * @debugfs_init: initialize all debugfs capabilities * @debugfs_exit: close and cleanup debugfs capabilities + * @get_link_count: fetch link count from hardware registers * @register_dai: read all PDI information and register DAIs * @check_clock_stop: throw error message if clock is not stopped. * @start_bus: normal start @@ -400,6 +411,8 @@ struct sdw_intel_hw_ops { void (*debugfs_init)(struct sdw_intel *sdw); void (*debugfs_exit)(struct sdw_intel *sdw); + int (*get_link_count)(struct sdw_intel *sdw); + int (*register_dai)(struct sdw_intel *sdw); void (*check_clock_stop)(struct sdw_intel *sdw); @@ -435,4 +448,9 @@ extern const struct sdw_intel_hw_ops sdw_intel_lnl_hw_ops; #define SDW_INTEL_DEV_NUM_IDA_MIN 6 +/* + * Max number of links supported in hardware + */ +#define SDW_INTEL_MAX_LINKS 5 + #endif diff --git a/include/linux/soundwire/sdw_registers.h b/include/linux/soundwire/sdw_registers.h index 138bec908c40..0a5939285583 100644 --- a/include/linux/soundwire/sdw_registers.h +++ b/include/linux/soundwire/sdw_registers.h @@ -4,6 +4,9 @@ #ifndef __SDW_REGISTERS_H #define __SDW_REGISTERS_H +#include <linux/bitfield.h> +#include <linux/bits.h> + /* * SDW registers as defined by MIPI 1.2 Spec */ @@ -13,7 +16,7 @@ #define SDW_REG_NO_PAGE 0x00008000 #define SDW_REG_OPTIONAL_PAGE 0x00010000 -#define SDW_REG_MAX 0x80000000 +#define SDW_REG_MAX 0x48000000 #define SDW_DPN_SIZE 0x100 #define SDW_BANK1_OFFSET 0x10 @@ -329,16 +332,27 @@ * 2:0 Control Number[2:0] */ -#define SDW_SDCA_CTL(fun, ent, ctl, ch) (BIT(30) | \ - (((fun) & 0x7) << 22) | \ - (((ent) & 0x40) << 15) | \ - (((ent) & 0x3f) << 7) | \ - (((ctl) & 0x30) << 15) | \ - (((ctl) & 0x0f) << 3) | \ - (((ch) & 0x38) << 12) | \ - ((ch) & 0x07)) +#define SDW_SDCA_CTL(fun, ent, ctl, ch) (BIT(30) | \ + (((fun) & GENMASK(2, 0)) << 22) | \ + (((ent) & BIT(6)) << 15) | \ + (((ent) & GENMASK(5, 0)) << 7) | \ + (((ctl) & GENMASK(5, 4)) << 15) | \ + (((ctl) & GENMASK(3, 0)) << 3) | \ + (((ch) & GENMASK(5, 3)) << 12) | \ + ((ch) & GENMASK(2, 0))) + +#define SDW_SDCA_CTL_FUNC(reg) FIELD_GET(GENMASK(24, 22), (reg)) +#define SDW_SDCA_CTL_ENT(reg) ((FIELD_GET(BIT(21), (reg)) << 6) | \ + FIELD_GET(GENMASK(12, 7), (reg))) +#define SDW_SDCA_CTL_CSEL(reg) ((FIELD_GET(GENMASK(20, 19), (reg)) << 4) | \ + FIELD_GET(GENMASK(6, 3), (reg))) +#define SDW_SDCA_CTL_CNUM(reg) ((FIELD_GET(GENMASK(17, 15), (reg)) << 3) | \ + FIELD_GET(GENMASK(2, 0), (reg))) #define SDW_SDCA_MBQ_CTL(reg) ((reg) | BIT(13)) #define SDW_SDCA_NEXT_CTL(reg) ((reg) | BIT(14)) +/* Check the reserved and fixed bits in address */ +#define SDW_SDCA_VALID_CTL(reg) (((reg) & (GENMASK(31, 25) | BIT(18) | BIT(13))) == BIT(30)) + #endif /* __SDW_REGISTERS_H */ diff --git a/include/linux/soundwire/sdw_type.h b/include/linux/soundwire/sdw_type.h index 693320b4f5c2..d405935a45fe 100644 --- a/include/linux/soundwire/sdw_type.h +++ b/include/linux/soundwire/sdw_type.h @@ -13,7 +13,7 @@ static inline int is_sdw_slave(const struct device *dev) return dev->type == &sdw_slave_type; } -#define drv_to_sdw_driver(_drv) container_of(_drv, struct sdw_driver, driver) +#define drv_to_sdw_driver(_drv) container_of_const(_drv, struct sdw_driver, driver) #define sdw_register_driver(drv) \ __sdw_register_driver(drv, THIS_MODULE) diff --git a/include/linux/spi/pxa2xx_spi.h b/include/linux/spi/pxa2xx_spi.h deleted file mode 100644 index ca2cd4e30ead..000000000000 --- a/include/linux/spi/pxa2xx_spi.h +++ /dev/null @@ -1,56 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Copyright (C) 2005 Stephen Street / StreetFire Sound Labs - */ -#ifndef __LINUX_SPI_PXA2XX_SPI_H -#define __LINUX_SPI_PXA2XX_SPI_H - -#include <linux/dmaengine.h> -#include <linux/types.h> - -#include <linux/pxa2xx_ssp.h> - -struct dma_chan; - -/* - * The platform data for SSP controller devices - * (resides in device.platform_data). - */ -struct pxa2xx_spi_controller { - u16 num_chipselect; - u8 enable_dma; - u8 dma_burst_size; - bool is_target; - - /* DMA engine specific config */ - dma_filter_fn dma_filter; - void *tx_param; - void *rx_param; - - /* For non-PXA arches */ - struct ssp_device ssp; -}; - -/* - * The controller specific data for SPI target devices - * (resides in spi_board_info.controller_data), - * copied to spi_device.platform_data ... mostly for - * DMA tuning. - */ -struct pxa2xx_spi_chip { - u8 tx_threshold; - u8 tx_hi_threshold; - u8 rx_threshold; - u8 dma_burst_size; - u32 timeout; -}; - -#if defined(CONFIG_ARCH_PXA) || defined(CONFIG_ARCH_MMP) - -#include <linux/clk.h> - -extern void pxa2xx_set_spi_info(unsigned id, struct pxa2xx_spi_controller *info); - -#endif - -#endif /* __LINUX_SPI_PXA2XX_SPI_H */ diff --git a/include/linux/spi/rspi.h b/include/linux/spi/rspi.h deleted file mode 100644 index dbdfcc7a3db2..000000000000 --- a/include/linux/spi/rspi.h +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Renesas SPI driver - * - * Copyright (C) 2012 Renesas Solutions Corp. - */ - -#ifndef __LINUX_SPI_RENESAS_SPI_H__ -#define __LINUX_SPI_RENESAS_SPI_H__ - -struct rspi_plat_data { - unsigned int dma_tx_id; - unsigned int dma_rx_id; - - u16 num_chipselect; -}; - -#endif diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h index f866d5c8ed32..c4830dfaff3d 100644 --- a/include/linux/spi/spi-mem.h +++ b/include/linux/spi/spi-mem.h @@ -15,16 +15,32 @@ #define SPI_MEM_OP_CMD(__opcode, __buswidth) \ { \ + .nbytes = 1, \ .buswidth = __buswidth, \ .opcode = __opcode, \ + } + +#define SPI_MEM_DTR_OP_CMD(__opcode, __buswidth) \ + { \ .nbytes = 1, \ + .opcode = __opcode, \ + .buswidth = __buswidth, \ + .dtr = true, \ } #define SPI_MEM_OP_ADDR(__nbytes, __val, __buswidth) \ { \ .nbytes = __nbytes, \ + .buswidth = __buswidth, \ + .val = __val, \ + } + +#define SPI_MEM_DTR_OP_ADDR(__nbytes, __val, __buswidth) \ + { \ + .nbytes = __nbytes, \ .val = __val, \ .buswidth = __buswidth, \ + .dtr = true, \ } #define SPI_MEM_OP_NO_ADDR { } @@ -35,22 +51,47 @@ .buswidth = __buswidth, \ } +#define SPI_MEM_DTR_OP_DUMMY(__nbytes, __buswidth) \ + { \ + .nbytes = __nbytes, \ + .buswidth = __buswidth, \ + .dtr = true, \ + } + #define SPI_MEM_OP_NO_DUMMY { } #define SPI_MEM_OP_DATA_IN(__nbytes, __buf, __buswidth) \ { \ + .buswidth = __buswidth, \ + .dir = SPI_MEM_DATA_IN, \ + .nbytes = __nbytes, \ + .buf.in = __buf, \ + } + +#define SPI_MEM_DTR_OP_DATA_IN(__nbytes, __buf, __buswidth) \ + { \ .dir = SPI_MEM_DATA_IN, \ .nbytes = __nbytes, \ .buf.in = __buf, \ .buswidth = __buswidth, \ + .dtr = true, \ } #define SPI_MEM_OP_DATA_OUT(__nbytes, __buf, __buswidth) \ { \ + .buswidth = __buswidth, \ + .dir = SPI_MEM_DATA_OUT, \ + .nbytes = __nbytes, \ + .buf.out = __buf, \ + } + +#define SPI_MEM_DTR_OP_DATA_OUT(__nbytes, __buf, __buswidth) \ + { \ .dir = SPI_MEM_DATA_OUT, \ .nbytes = __nbytes, \ .buf.out = __buf, \ .buswidth = __buswidth, \ + .dtr = true, \ } #define SPI_MEM_OP_NO_DATA { } @@ -68,6 +109,9 @@ enum spi_mem_data_dir { SPI_MEM_DATA_OUT, }; +#define SPI_MEM_OP_MAX_FREQ(__freq) \ + .max_freq = __freq + /** * struct spi_mem_op - describes a SPI memory operation * @cmd.nbytes: number of opcode bytes (only 1 or 2 are valid). The opcode is @@ -90,11 +134,16 @@ enum spi_mem_data_dir { * @data.buswidth: number of IO lanes used to send/receive the data * @data.dtr: whether the data should be sent in DTR mode or not * @data.ecc: whether error correction is required or not + * @data.swap16: whether the byte order of 16-bit words is swapped when read + * or written in Octal DTR mode compared to STR mode. * @data.dir: direction of the transfer * @data.nbytes: number of data bytes to send/receive. Can be zero if the * operation does not involve transferring data * @data.buf.in: input buffer (must be DMA-able) * @data.buf.out: output buffer (must be DMA-able) + * @max_freq: frequency limitation wrt this operation. 0 means there is no + * specific constraint and the highest achievable frequency can be + * attempted. */ struct spi_mem_op { struct { @@ -124,7 +173,8 @@ struct spi_mem_op { u8 buswidth; u8 dtr : 1; u8 ecc : 1; - u8 __pad : 6; + u8 swap16 : 1; + u8 __pad : 5; enum spi_mem_data_dir dir; unsigned int nbytes; union { @@ -132,14 +182,17 @@ struct spi_mem_op { const void *out; } buf; } data; + + unsigned int max_freq; }; -#define SPI_MEM_OP(__cmd, __addr, __dummy, __data) \ +#define SPI_MEM_OP(__cmd, __addr, __dummy, __data, ...) \ { \ .cmd = __cmd, \ .addr = __addr, \ .dummy = __dummy, \ .data = __data, \ + __VA_ARGS__ \ } /** @@ -297,10 +350,15 @@ struct spi_controller_mem_ops { * struct spi_controller_mem_caps - SPI memory controller capabilities * @dtr: Supports DTR operations * @ecc: Supports operations with error correction + * @swap16: Supports swapping bytes on a 16 bit boundary when configured in + * Octal DTR + * @per_op_freq: Supports per operation frequency switching */ struct spi_controller_mem_caps { bool dtr; bool ecc; + bool swap16; + bool per_op_freq; }; #define spi_mem_controller_is_capable(ctlr, cap) \ @@ -365,6 +423,8 @@ bool spi_mem_default_supports_op(struct spi_mem *mem, #endif /* CONFIG_SPI_MEM */ int spi_mem_adjust_op_size(struct spi_mem *mem, struct spi_mem_op *op); +void spi_mem_adjust_op_freq(struct spi_mem *mem, struct spi_mem_op *op); +u64 spi_mem_calc_op_duration(struct spi_mem_op *op); bool spi_mem_supports_op(struct spi_mem *mem, const struct spi_mem_op *op); diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index c459809efee4..8497f4747e24 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -351,10 +351,8 @@ struct spi_driver { struct device_driver driver; }; -static inline struct spi_driver *to_spi_driver(struct device_driver *drv) -{ - return drv ? container_of(drv, struct spi_driver, driver) : NULL; -} +#define to_spi_driver(__drv) \ + ( __drv ? container_of_const(__drv, struct spi_driver, driver) : NULL ) extern int __spi_register_driver(struct module *owner, struct spi_driver *sdrv); @@ -447,12 +445,12 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch * @cur_msg_need_completion: Flag used internally to opportunistically skip * the @cur_msg_completion. This flag is used to signal the context that * is running spi_finalize_current_message() that it needs to complete() - * @cur_msg_mapped: message has been mapped for DMA * @fallback: fallback to PIO if DMA transfer return failure with * SPI_TRANS_FAIL_NO_START. * @last_cs_mode_high: was (mode & SPI_CS_HIGH) true on the last call to set_cs. * @last_cs: the last chip_select that is recorded by set_cs, -1 on non chip * selected + * @last_cs_index_mask: bit mask the last chip selects that were used * @xfer_completion: used by core transfer_one_message() * @busy: message pump is busy * @running: message pump is running @@ -500,7 +498,6 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch * controller has native support for memory like operations. * @mem_caps: controller capabilities for the handling of memory operations. * @unprepare_message: undo any work done by prepare_message(). - * @slave_abort: abort the ongoing transfer request on an SPI slave controller * @target_abort: abort the ongoing transfer request on an SPI target controller * @cs_gpiods: Array of GPIO descriptors to use as chip select lines; one per CS * number. Any individual value may be NULL for CS lines that @@ -532,6 +529,9 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch * @queue_empty: signal green light for opportunistically skipping the queue * for spi_sync transfers. * @must_async: disable all fast paths in the core + * @defer_optimize_message: set to true if controller cannot pre-optimize messages + * and needs to defer the optimization step until the message is actually + * being transferred * * Each SPI controller can communicate with one or more @spi_device * children. These make a small bus, sharing MOSI, MISO and SCK signals @@ -707,7 +707,6 @@ struct spi_controller { bool running; bool rt; bool auto_runtime_pm; - bool cur_msg_mapped; bool fallback; bool last_cs_mode_high; s8 last_cs[SPI_CS_CNT_MAX]; @@ -725,10 +724,7 @@ struct spi_controller { struct spi_message *message); int (*unprepare_message)(struct spi_controller *ctlr, struct spi_message *message); - union { - int (*slave_abort)(struct spi_controller *ctlr); - int (*target_abort)(struct spi_controller *ctlr); - }; + int (*target_abort)(struct spi_controller *ctlr); /* * These hooks are for drivers that use a generic implementation @@ -775,6 +771,7 @@ struct spi_controller { /* Flag for enabling opportunistic skipping of the queue in spi_sync */ bool queue_empty; bool must_async; + bool defer_optimize_message; }; static inline void *spi_controller_get_devdata(struct spi_controller *ctlr) @@ -801,11 +798,6 @@ static inline void spi_controller_put(struct spi_controller *ctlr) put_device(&ctlr->dev); } -static inline bool spi_controller_is_slave(struct spi_controller *ctlr) -{ - return IS_ENABLED(CONFIG_SPI_SLAVE) && ctlr->slave; -} - static inline bool spi_controller_is_target(struct spi_controller *ctlr) { return IS_ENABLED(CONFIG_SPI_SLAVE) && ctlr->target; @@ -832,21 +824,6 @@ void spi_take_timestamp_post(struct spi_controller *ctlr, extern struct spi_controller *__spi_alloc_controller(struct device *host, unsigned int size, bool slave); -static inline struct spi_controller *spi_alloc_master(struct device *host, - unsigned int size) -{ - return __spi_alloc_controller(host, size, false); -} - -static inline struct spi_controller *spi_alloc_slave(struct device *host, - unsigned int size) -{ - if (!IS_ENABLED(CONFIG_SPI_SLAVE)) - return NULL; - - return __spi_alloc_controller(host, size, true); -} - static inline struct spi_controller *spi_alloc_host(struct device *dev, unsigned int size) { @@ -866,21 +843,6 @@ struct spi_controller *__devm_spi_alloc_controller(struct device *dev, unsigned int size, bool slave); -static inline struct spi_controller *devm_spi_alloc_master(struct device *dev, - unsigned int size) -{ - return __devm_spi_alloc_controller(dev, size, false); -} - -static inline struct spi_controller *devm_spi_alloc_slave(struct device *dev, - unsigned int size) -{ - if (!IS_ENABLED(CONFIG_SPI_SLAVE)) - return NULL; - - return __devm_spi_alloc_controller(dev, size, true); -} - static inline struct spi_controller *devm_spi_alloc_host(struct device *dev, unsigned int size) { @@ -901,12 +863,29 @@ extern int devm_spi_register_controller(struct device *dev, struct spi_controller *ctlr); extern void spi_unregister_controller(struct spi_controller *ctlr); -#if IS_ENABLED(CONFIG_ACPI) +#if IS_ENABLED(CONFIG_ACPI) && IS_ENABLED(CONFIG_SPI_MASTER) extern struct spi_controller *acpi_spi_find_controller_by_adev(struct acpi_device *adev); extern struct spi_device *acpi_spi_device_alloc(struct spi_controller *ctlr, struct acpi_device *adev, int index); int acpi_spi_count_resources(struct acpi_device *adev); +#else +static inline struct spi_controller *acpi_spi_find_controller_by_adev(struct acpi_device *adev) +{ + return NULL; +} + +static inline struct spi_device *acpi_spi_device_alloc(struct spi_controller *ctlr, + struct acpi_device *adev, + int index) +{ + return ERR_PTR(-ENODEV); +} + +static inline int acpi_spi_count_resources(struct acpi_device *adev) +{ + return 0; +} #endif /* @@ -955,8 +934,8 @@ struct spi_res { * struct spi_transfer - a read/write buffer pair * @tx_buf: data to be written (DMA-safe memory), or NULL * @rx_buf: data to be read (DMA-safe memory), or NULL - * @tx_dma: DMA address of tx_buf, if @spi_message.is_dma_mapped - * @rx_dma: DMA address of rx_buf, if @spi_message.is_dma_mapped + * @tx_dma: DMA address of tx_buf, currently not for client use + * @rx_dma: DMA address of rx_buf, currently not for client use * @tx_nbits: number of bits used for writing. If 0 the default * (SPI_NBITS_SINGLE) is used. * @rx_nbits: number of bits used for reading. If 0 the default @@ -980,6 +959,8 @@ struct spi_res { * transfer this transfer. Set to 0 if the SPI bus driver does * not support it. * @transfer_list: transfers are sequenced through @spi_message.transfers + * @tx_sg_mapped: If true, the @tx_sg is mapped for DMA + * @rx_sg_mapped: If true, the @rx_sg is mapped for DMA * @tx_sg: Scatterlist for transmit, currently not for client use * @rx_sg: Scatterlist for receive, currently not for client use * @ptp_sts_word_pre: The word (subject to bits_per_word semantics) offset @@ -1066,8 +1047,7 @@ struct spi_transfer { /* * It's okay if tx_buf == rx_buf (right?). * For MicroWire, one buffer must be NULL. - * Buffers must work with dma_*map_single() calls, unless - * spi_message.is_dma_mapped reports a pre-existing mapping. + * Buffers must work with dma_*map_single() calls. */ const void *tx_buf; void *rx_buf; @@ -1077,20 +1057,24 @@ struct spi_transfer { #define SPI_TRANS_FAIL_IO BIT(1) u16 error; - dma_addr_t tx_dma; - dma_addr_t rx_dma; + bool tx_sg_mapped; + bool rx_sg_mapped; + struct sg_table tx_sg; struct sg_table rx_sg; + dma_addr_t tx_dma; + dma_addr_t rx_dma; unsigned dummy_data:1; unsigned cs_off:1; unsigned cs_change:1; - unsigned tx_nbits:3; - unsigned rx_nbits:3; + unsigned tx_nbits:4; + unsigned rx_nbits:4; unsigned timestamped:1; #define SPI_NBITS_SINGLE 0x01 /* 1-bit transfer */ #define SPI_NBITS_DUAL 0x02 /* 2-bit transfer */ #define SPI_NBITS_QUAD 0x04 /* 4-bit transfer */ +#define SPI_NBITS_OCTAL 0x08 /* 8-bit transfer */ u8 bits_per_word; struct spi_delay delay; struct spi_delay cs_change_delay; @@ -1111,8 +1095,6 @@ struct spi_transfer { * struct spi_message - one multi-segment SPI transaction * @transfers: list of transfer segments in this transaction * @spi: SPI device to which the transaction is queued - * @is_dma_mapped: if true, the caller provided both DMA and CPU virtual - * addresses for each transfer buffer * @pre_optimized: peripheral driver pre-optimized the message * @optimized: the message is in the optimized state * @prepared: spi_prepare_message was called for the this message @@ -1146,8 +1128,6 @@ struct spi_message { struct spi_device *spi; - unsigned is_dma_mapped:1; - /* spi_optimize_message() was called for this message */ bool pre_optimized; /* __spi_optimize_message() was called for this message */ @@ -1272,10 +1252,11 @@ static inline void spi_message_free(struct spi_message *m) extern int spi_optimize_message(struct spi_device *spi, struct spi_message *msg); extern void spi_unoptimize_message(struct spi_message *msg); +extern int devm_spi_optimize_message(struct device *dev, struct spi_device *spi, + struct spi_message *msg); extern int spi_setup(struct spi_device *spi); extern int spi_async(struct spi_device *spi, struct spi_message *message); -extern int spi_slave_abort(struct spi_device *spi); extern int spi_target_abort(struct spi_device *spi); static inline size_t diff --git a/include/linux/spi/spi_bitbang.h b/include/linux/spi/spi_bitbang.h index b930eca2ef7b..c92cd43a47f4 100644 --- a/include/linux/spi/spi_bitbang.h +++ b/include/linux/spi/spi_bitbang.h @@ -4,6 +4,8 @@ #include <linux/workqueue.h> +typedef u32 (*spi_bb_txrx_word_fn)(struct spi_device *, unsigned int, u32, u8, unsigned int); + struct spi_bitbang { struct mutex lock; u8 busy; @@ -22,15 +24,15 @@ struct spi_bitbang { #define BITBANG_CS_ACTIVE 1 /* normally nCS, active low */ #define BITBANG_CS_INACTIVE 0 + void (*set_mosi_idle)(struct spi_device *spi); /* txrx_bufs() may handle dma mapping for transfers that don't * already have one (transfer.{tx,rx}_dma is zero), or use PIO */ int (*txrx_bufs)(struct spi_device *spi, struct spi_transfer *t); /* txrx_word[SPI_MODE_*]() just looks like a shift register */ - u32 (*txrx_word[4])(struct spi_device *spi, - unsigned nsecs, - u32 word, u8 bits, unsigned flags); + spi_bb_txrx_word_fn txrx_word[SPI_MODE_X_MASK + 1]; + int (*set_line_direction)(struct spi_device *spi, bool output); }; diff --git a/include/linux/spi/xilinx_spi.h b/include/linux/spi/xilinx_spi.h index 3934ce789d87..1b8d984668b6 100644 --- a/include/linux/spi/xilinx_spi.h +++ b/include/linux/spi/xilinx_spi.h @@ -2,19 +2,23 @@ #ifndef __LINUX_SPI_XILINX_SPI_H #define __LINUX_SPI_XILINX_SPI_H +#include <linux/types.h> + +struct spi_board_info; + /** * struct xspi_platform_data - Platform data of the Xilinx SPI driver - * @num_chipselect: Number of chip select by the IP. - * @little_endian: If registers should be accessed little endian or not. - * @bits_per_word: Number of bits per word. * @devices: Devices to add when the driver is probed. * @num_devices: Number of devices in the devices array. + * @num_chipselect: Number of chip select by the IP. + * @bits_per_word: Number of bits per word. + * @force_irq: If set, forces QSPI transaction requirements. */ struct xspi_platform_data { - u16 num_chipselect; - u8 bits_per_word; struct spi_board_info *devices; u8 num_devices; + u8 num_chipselect; + u8 bits_per_word; bool force_irq; }; diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 3fcd20de6ca8..63dd8cf3c3c2 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -462,11 +462,10 @@ static __always_inline int spin_is_contended(spinlock_t *lock) */ static inline int spin_needbreak(spinlock_t *lock) { -#ifdef CONFIG_PREEMPTION + if (!preempt_model_preemptible()) + return 0; + return spin_is_contended(lock); -#else - return 0; -#endif } /* @@ -479,11 +478,10 @@ static inline int spin_needbreak(spinlock_t *lock) */ static inline int rwlock_needbreak(rwlock_t *lock) { -#ifdef CONFIG_PREEMPTION + if (!preempt_model_preemptible()) + return 0; + return rwlock_is_contended(lock); -#else - return 0; -#endif } /* diff --git a/include/linux/spinlock_api_smp.h b/include/linux/spinlock_api_smp.h index 89eb6f4c659c..9ecb0ab504e3 100644 --- a/include/linux/spinlock_api_smp.h +++ b/include/linux/spinlock_api_smp.h @@ -2,7 +2,7 @@ #define __LINUX_SPINLOCK_API_SMP_H #ifndef __LINUX_INSIDE_SPINLOCK_H -# error "please don't include this file directly" +# error "Please do not include this file directly." #endif /* diff --git a/include/linux/spinlock_rt.h b/include/linux/spinlock_rt.h index 61c49b16f69a..f6499c37157d 100644 --- a/include/linux/spinlock_rt.h +++ b/include/linux/spinlock_rt.h @@ -16,26 +16,25 @@ static inline void __rt_spin_lock_init(spinlock_t *lock, const char *name, } #endif -#define spin_lock_init(slock) \ +#define __spin_lock_init(slock, name, key, percpu) \ do { \ - static struct lock_class_key __key; \ - \ rt_mutex_base_init(&(slock)->lock); \ - __rt_spin_lock_init(slock, #slock, &__key, false); \ + __rt_spin_lock_init(slock, name, key, percpu); \ } while (0) -#define local_spin_lock_init(slock) \ +#define _spin_lock_init(slock, percpu) \ do { \ static struct lock_class_key __key; \ - \ - rt_mutex_base_init(&(slock)->lock); \ - __rt_spin_lock_init(slock, #slock, &__key, true); \ + __spin_lock_init(slock, #slock, &__key, percpu); \ } while (0) -extern void rt_spin_lock(spinlock_t *lock); -extern void rt_spin_lock_nested(spinlock_t *lock, int subclass); -extern void rt_spin_lock_nest_lock(spinlock_t *lock, struct lockdep_map *nest_lock); -extern void rt_spin_unlock(spinlock_t *lock); +#define spin_lock_init(slock) _spin_lock_init(slock, false) +#define local_spin_lock_init(slock) _spin_lock_init(slock, true) + +extern void rt_spin_lock(spinlock_t *lock) __acquires(lock); +extern void rt_spin_lock_nested(spinlock_t *lock, int subclass) __acquires(lock); +extern void rt_spin_lock_nest_lock(spinlock_t *lock, struct lockdep_map *nest_lock) __acquires(lock); +extern void rt_spin_unlock(spinlock_t *lock) __releases(lock); extern void rt_spin_lock_unlock(spinlock_t *lock); extern int rt_spin_trylock_bh(spinlock_t *lock); extern int rt_spin_trylock(spinlock_t *lock); @@ -132,7 +131,7 @@ static __always_inline void spin_unlock_irqrestore(spinlock_t *lock, #define spin_trylock_irq(lock) \ __cond_lock(lock, rt_spin_trylock(lock)) -#define __spin_trylock_irqsave(lock, flags) \ +#define spin_trylock_irqsave(lock, flags) \ ({ \ int __locked; \ \ @@ -142,9 +141,6 @@ static __always_inline void spin_unlock_irqrestore(spinlock_t *lock, __locked; \ }) -#define spin_trylock_irqsave(lock, flags) \ - __cond_lock(lock, __spin_trylock_irqsave(lock, flags)) - #define spin_is_contended(lock) (((void)(lock), 0)) static inline int spin_is_locked(spinlock_t *lock) diff --git a/include/linux/spinlock_types_up.h b/include/linux/spinlock_types_up.h index 7f86a2016ac5..fc4e2d017c20 100644 --- a/include/linux/spinlock_types_up.h +++ b/include/linux/spinlock_types_up.h @@ -2,7 +2,7 @@ #define __LINUX_SPINLOCK_TYPES_UP_H #ifndef __LINUX_SPINLOCK_TYPES_RAW_H -# error "please don't include this file directly" +# error "Please do not include this file directly." #endif /* diff --git a/include/linux/spinlock_up.h b/include/linux/spinlock_up.h index c87204247592..1e84e71ca495 100644 --- a/include/linux/spinlock_up.h +++ b/include/linux/spinlock_up.h @@ -2,7 +2,7 @@ #define __LINUX_SPINLOCK_UP_H #ifndef __LINUX_INSIDE_SPINLOCK_H -# error "please don't include this file directly" +# error "Please do not include this file directly." #endif #include <asm/processor.h> /* for cpu_relax() */ diff --git a/include/linux/srcu.h b/include/linux/srcu.h index 236610e4a8fa..d7ba46e74f58 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -43,6 +43,12 @@ int init_srcu_struct(struct srcu_struct *ssp); #define __SRCU_DEP_MAP_INIT(srcu_name) #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ +/* Values for SRCU Tree srcu_data ->srcu_reader_flavor, but also used by rcutorture. */ +#define SRCU_READ_FLAVOR_NORMAL 0x1 // srcu_read_lock(). +#define SRCU_READ_FLAVOR_NMI 0x2 // srcu_read_lock_nmisafe(). +#define SRCU_READ_FLAVOR_LITE 0x4 // srcu_read_lock_lite(). +#define SRCU_READ_FLAVOR_ALL 0x7 // All of the above. + #ifdef CONFIG_TINY_SRCU #include <linux/srcutiny.h> #elif defined(CONFIG_TREE_SRCU) @@ -56,11 +62,53 @@ void call_srcu(struct srcu_struct *ssp, struct rcu_head *head, void cleanup_srcu_struct(struct srcu_struct *ssp); int __srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp); void __srcu_read_unlock(struct srcu_struct *ssp, int idx) __releases(ssp); +#ifdef CONFIG_TINY_SRCU +#define __srcu_read_lock_lite __srcu_read_lock +#define __srcu_read_unlock_lite __srcu_read_unlock +#else // #ifdef CONFIG_TINY_SRCU +int __srcu_read_lock_lite(struct srcu_struct *ssp) __acquires(ssp); +void __srcu_read_unlock_lite(struct srcu_struct *ssp, int idx) __releases(ssp); +#endif // #else // #ifdef CONFIG_TINY_SRCU void synchronize_srcu(struct srcu_struct *ssp); + +#define SRCU_GET_STATE_COMPLETED 0x1 + +/** + * get_completed_synchronize_srcu - Return a pre-completed polled state cookie + * + * Returns a value that poll_state_synchronize_srcu() will always treat + * as a cookie whose grace period has already completed. + */ +static inline unsigned long get_completed_synchronize_srcu(void) +{ + return SRCU_GET_STATE_COMPLETED; +} + unsigned long get_state_synchronize_srcu(struct srcu_struct *ssp); unsigned long start_poll_synchronize_srcu(struct srcu_struct *ssp); bool poll_state_synchronize_srcu(struct srcu_struct *ssp, unsigned long cookie); +// Maximum number of unsigned long values corresponding to +// not-yet-completed SRCU grace periods. +#define NUM_ACTIVE_SRCU_POLL_OLDSTATE 2 + +/** + * same_state_synchronize_srcu - Are two old-state values identical? + * @oldstate1: First old-state value. + * @oldstate2: Second old-state value. + * + * The two old-state values must have been obtained from either + * get_state_synchronize_srcu(), start_poll_synchronize_srcu(), or + * get_completed_synchronize_srcu(). Returns @true if the two values are + * identical and @false otherwise. This allows structures whose lifetimes + * are tracked by old-state values to push these values to a list header, + * allowing those structures to be slightly smaller. + */ +static inline bool same_state_synchronize_srcu(unsigned long oldstate1, unsigned long oldstate2) +{ + return oldstate1 == oldstate2; +} + #ifdef CONFIG_NEED_SRCU_NMI_SAFE int __srcu_read_lock_nmisafe(struct srcu_struct *ssp) __acquires(ssp); void __srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx) __releases(ssp); @@ -141,17 +189,6 @@ static inline int srcu_read_lock_held(const struct srcu_struct *ssp) #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ -#define SRCU_NMI_UNKNOWN 0x0 -#define SRCU_NMI_UNSAFE 0x1 -#define SRCU_NMI_SAFE 0x2 - -#if defined(CONFIG_PROVE_RCU) && defined(CONFIG_TREE_SRCU) -void srcu_check_nmi_safety(struct srcu_struct *ssp, bool nmi_safe); -#else -static inline void srcu_check_nmi_safety(struct srcu_struct *ssp, - bool nmi_safe) { } -#endif - /** * srcu_dereference_check - fetch SRCU-protected pointer for later dereferencing @@ -201,33 +238,68 @@ static inline void srcu_check_nmi_safety(struct srcu_struct *ssp, * a mutex that is held elsewhere while calling synchronize_srcu() or * synchronize_srcu_expedited(). * - * Note that srcu_read_lock() and the matching srcu_read_unlock() must - * occur in the same context, for example, it is illegal to invoke - * srcu_read_unlock() in an irq handler if the matching srcu_read_lock() - * was invoked in process context. + * The return value from srcu_read_lock() is guaranteed to be + * non-negative. This value must be passed unaltered to the matching + * srcu_read_unlock(). Note that srcu_read_lock() and the matching + * srcu_read_unlock() must occur in the same context, for example, it is + * illegal to invoke srcu_read_unlock() in an irq handler if the matching + * srcu_read_lock() was invoked in process context. Or, for that matter to + * invoke srcu_read_unlock() from one task and the matching srcu_read_lock() + * from another. */ static inline int srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp) { int retval; - srcu_check_nmi_safety(ssp, false); + srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL); retval = __srcu_read_lock(ssp); srcu_lock_acquire(&ssp->dep_map); return retval; } /** + * srcu_read_lock_lite - register a new reader for an SRCU-protected structure. + * @ssp: srcu_struct in which to register the new reader. + * + * Enter an SRCU read-side critical section, but for a light-weight + * smp_mb()-free reader. See srcu_read_lock() for more information. + * + * If srcu_read_lock_lite() is ever used on an srcu_struct structure, + * then none of the other flavors may be used, whether before, during, + * or after. Note that grace-period auto-expediting is disabled for _lite + * srcu_struct structures because auto-expedited grace periods invoke + * synchronize_rcu_expedited(), IPIs and all. + * + * Note that srcu_read_lock_lite() can be invoked only from those contexts + * where RCU is watching, that is, from contexts where it would be legal + * to invoke rcu_read_lock(). Otherwise, lockdep will complain. + */ +static inline int srcu_read_lock_lite(struct srcu_struct *ssp) __acquires(ssp) +{ + int retval; + + srcu_check_read_flavor_lite(ssp); + retval = __srcu_read_lock_lite(ssp); + rcu_try_lock_acquire(&ssp->dep_map); + return retval; +} + +/** * srcu_read_lock_nmisafe - register a new reader for an SRCU-protected structure. * @ssp: srcu_struct in which to register the new reader. * * Enter an SRCU read-side critical section, but in an NMI-safe manner. * See srcu_read_lock() for more information. + * + * If srcu_read_lock_nmisafe() is ever used on an srcu_struct structure, + * then none of the other flavors may be used, whether before, during, + * or after. */ static inline int srcu_read_lock_nmisafe(struct srcu_struct *ssp) __acquires(ssp) { int retval; - srcu_check_nmi_safety(ssp, true); + srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NMI); retval = __srcu_read_lock_nmisafe(ssp); rcu_try_lock_acquire(&ssp->dep_map); return retval; @@ -239,7 +311,7 @@ srcu_read_lock_notrace(struct srcu_struct *ssp) __acquires(ssp) { int retval; - srcu_check_nmi_safety(ssp, false); + srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL); retval = __srcu_read_lock(ssp); return retval; } @@ -268,7 +340,7 @@ srcu_read_lock_notrace(struct srcu_struct *ssp) __acquires(ssp) static inline int srcu_down_read(struct srcu_struct *ssp) __acquires(ssp) { WARN_ON_ONCE(in_nmi()); - srcu_check_nmi_safety(ssp, false); + srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL); return __srcu_read_lock(ssp); } @@ -283,12 +355,28 @@ static inline void srcu_read_unlock(struct srcu_struct *ssp, int idx) __releases(ssp) { WARN_ON_ONCE(idx & ~0x1); - srcu_check_nmi_safety(ssp, false); + srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL); srcu_lock_release(&ssp->dep_map); __srcu_read_unlock(ssp, idx); } /** + * srcu_read_unlock_lite - unregister a old reader from an SRCU-protected structure. + * @ssp: srcu_struct in which to unregister the old reader. + * @idx: return value from corresponding srcu_read_lock(). + * + * Exit a light-weight SRCU read-side critical section. + */ +static inline void srcu_read_unlock_lite(struct srcu_struct *ssp, int idx) + __releases(ssp) +{ + WARN_ON_ONCE(idx & ~0x1); + srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_LITE); + srcu_lock_release(&ssp->dep_map); + __srcu_read_unlock_lite(ssp, idx); +} + +/** * srcu_read_unlock_nmisafe - unregister a old reader from an SRCU-protected structure. * @ssp: srcu_struct in which to unregister the old reader. * @idx: return value from corresponding srcu_read_lock(). @@ -299,7 +387,7 @@ static inline void srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx) __releases(ssp) { WARN_ON_ONCE(idx & ~0x1); - srcu_check_nmi_safety(ssp, true); + srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NMI); rcu_lock_release(&ssp->dep_map); __srcu_read_unlock_nmisafe(ssp, idx); } @@ -308,7 +396,7 @@ static inline void srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx) static inline notrace void srcu_read_unlock_notrace(struct srcu_struct *ssp, int idx) __releases(ssp) { - srcu_check_nmi_safety(ssp, false); + srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL); __srcu_read_unlock(ssp, idx); } @@ -325,7 +413,7 @@ static inline void srcu_up_read(struct srcu_struct *ssp, int idx) { WARN_ON_ONCE(idx & ~0x1); WARN_ON_ONCE(in_nmi()); - srcu_check_nmi_safety(ssp, false); + srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL); __srcu_read_unlock(ssp, idx); } @@ -343,6 +431,20 @@ static inline void smp_mb__after_srcu_read_unlock(void) /* __srcu_read_unlock has smp_mb() internally so nothing to do here. */ } +/** + * smp_mb__after_srcu_read_lock - ensure full ordering after srcu_read_lock + * + * Converts the preceding srcu_read_lock into a two-way memory barrier. + * + * Call this after srcu_read_lock, to guarantee that all memory operations + * that occur after smp_mb__after_srcu_read_lock will appear to happen after + * the preceding srcu_read_lock. + */ +static inline void smp_mb__after_srcu_read_lock(void) +{ + /* __srcu_read_lock has smp_mb() internally so nothing to do here. */ +} + DEFINE_LOCK_GUARD_1(srcu, struct srcu_struct, _T->idx = srcu_read_lock(_T->lock), srcu_read_unlock(_T->lock, _T->idx), diff --git a/include/linux/srcutiny.h b/include/linux/srcutiny.h index 447133171d95..1321da803274 100644 --- a/include/linux/srcutiny.h +++ b/include/linux/srcutiny.h @@ -64,8 +64,10 @@ static inline int __srcu_read_lock(struct srcu_struct *ssp) { int idx; + preempt_disable(); // Needed for PREEMPT_AUTO idx = ((READ_ONCE(ssp->srcu_idx) + 1) & 0x2) >> 1; WRITE_ONCE(ssp->srcu_lock_nesting[idx], READ_ONCE(ssp->srcu_lock_nesting[idx]) + 1); + preempt_enable(); return idx; } @@ -79,6 +81,9 @@ static inline void srcu_barrier(struct srcu_struct *ssp) synchronize_srcu(ssp); } +#define srcu_check_read_flavor(ssp, read_flavor) do { } while (0) +#define srcu_check_read_flavor_lite(ssp) do { } while (0) + /* Defined here to avoid size increase for non-torture kernels. */ static inline void srcu_torture_stats_print(struct srcu_struct *ssp, char *tt, char *tf) diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 8f3f72480e78..b17814c9d1c7 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -25,7 +25,8 @@ struct srcu_data { /* Read-side state. */ atomic_long_t srcu_lock_count[2]; /* Locks per CPU. */ atomic_long_t srcu_unlock_count[2]; /* Unlocks per CPU. */ - int srcu_nmi_safety; /* NMI-safe srcu_struct structure? */ + int srcu_reader_flavor; /* Reader flavor for srcu_struct structure? */ + /* Values: SRCU_READ_FLAVOR_.* */ /* Update-side state. */ spinlock_t __private lock ____cacheline_internodealigned_in_smp; @@ -129,10 +130,23 @@ struct srcu_struct { #define SRCU_STATE_SCAN1 1 #define SRCU_STATE_SCAN2 2 +/* + * Values for initializing gp sequence fields. Higher values allow wrap arounds to + * occur earlier. + * The second value with state is useful in the case of static initialization of + * srcu_usage where srcu_gp_seq_needed is expected to have some state value in its + * lower bits (or else it will appear to be already initialized within + * the call check_init_srcu_struct()). + */ +#define SRCU_GP_SEQ_INITIAL_VAL ((0UL - 100UL) << RCU_SEQ_CTR_SHIFT) +#define SRCU_GP_SEQ_INITIAL_VAL_WITH_STATE (SRCU_GP_SEQ_INITIAL_VAL - 1) + #define __SRCU_USAGE_INIT(name) \ { \ .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ - .srcu_gp_seq_needed = -1UL, \ + .srcu_gp_seq = SRCU_GP_SEQ_INITIAL_VAL, \ + .srcu_gp_seq_needed = SRCU_GP_SEQ_INITIAL_VAL_WITH_STATE, \ + .srcu_gp_seq_needed_exp = SRCU_GP_SEQ_INITIAL_VAL, \ .work = __DELAYED_WORK_INITIALIZER(name.work, NULL, 0), \ } @@ -191,4 +205,64 @@ void synchronize_srcu_expedited(struct srcu_struct *ssp); void srcu_barrier(struct srcu_struct *ssp); void srcu_torture_stats_print(struct srcu_struct *ssp, char *tt, char *tf); +/* + * Counts the new reader in the appropriate per-CPU element of the + * srcu_struct. Returns an index that must be passed to the matching + * srcu_read_unlock_lite(). + * + * Note that this_cpu_inc() is an RCU read-side critical section either + * because it disables interrupts, because it is a single instruction, + * or because it is a read-modify-write atomic operation, depending on + * the whims of the architecture. + */ +static inline int __srcu_read_lock_lite(struct srcu_struct *ssp) +{ + int idx; + + RCU_LOCKDEP_WARN(!rcu_is_watching(), "RCU must be watching srcu_read_lock_lite()."); + idx = READ_ONCE(ssp->srcu_idx) & 0x1; + this_cpu_inc(ssp->sda->srcu_lock_count[idx].counter); /* Y */ + barrier(); /* Avoid leaking the critical section. */ + return idx; +} + +/* + * Removes the count for the old reader from the appropriate + * per-CPU element of the srcu_struct. Note that this may well be a + * different CPU than that which was incremented by the corresponding + * srcu_read_lock_lite(), but it must be within the same task. + * + * Note that this_cpu_inc() is an RCU read-side critical section either + * because it disables interrupts, because it is a single instruction, + * or because it is a read-modify-write atomic operation, depending on + * the whims of the architecture. + */ +static inline void __srcu_read_unlock_lite(struct srcu_struct *ssp, int idx) +{ + barrier(); /* Avoid leaking the critical section. */ + this_cpu_inc(ssp->sda->srcu_unlock_count[idx].counter); /* Z */ + RCU_LOCKDEP_WARN(!rcu_is_watching(), "RCU must be watching srcu_read_unlock_lite()."); +} + +void __srcu_check_read_flavor(struct srcu_struct *ssp, int read_flavor); + +// Record _lite() usage even for CONFIG_PROVE_RCU=n kernels. +static inline void srcu_check_read_flavor_lite(struct srcu_struct *ssp) +{ + struct srcu_data *sdp = raw_cpu_ptr(ssp->sda); + + if (likely(READ_ONCE(sdp->srcu_reader_flavor) & SRCU_READ_FLAVOR_LITE)) + return; + + // Note that the cmpxchg() in __srcu_check_read_flavor() is fully ordered. + __srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_LITE); +} + +// Record non-_lite() usage only for CONFIG_PROVE_RCU=y kernels. +static inline void srcu_check_read_flavor(struct srcu_struct *ssp, int read_flavor) +{ + if (IS_ENABLED(CONFIG_PROVE_RCU)) + __srcu_check_read_flavor(ssp, read_flavor); +} + #endif diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h index 1f326da289d3..e1fb11e0f12c 100644 --- a/include/linux/ssb/ssb.h +++ b/include/linux/ssb/ssb.h @@ -325,7 +325,7 @@ struct ssb_driver { struct device_driver drv; }; -#define drv_to_ssb_drv(_drv) container_of(_drv, struct ssb_driver, drv) +#define drv_to_ssb_drv(_drv) container_of_const(_drv, struct ssb_driver, drv) extern int __ssb_driver_register(struct ssb_driver *drv, struct module *owner); #define ssb_driver_register(drv) \ @@ -621,14 +621,6 @@ extern u32 ssb_dma_translation(struct ssb_device *dev); #define SSB_DMA_TRANSLATION_MASK 0xC0000000 #define SSB_DMA_TRANSLATION_SHIFT 30 -static inline void __cold __ssb_dma_not_implemented(struct ssb_device *dev) -{ -#ifdef CONFIG_SSB_DEBUG - printk(KERN_ERR "SSB: BUG! Calling DMA API for " - "unsupported bustype %d\n", dev->bus->bustype); -#endif /* DEBUG */ -} - #ifdef CONFIG_SSB_PCIHOST /* PCI-host wrapper driver */ extern int ssb_pcihost_register(struct pci_driver *driver); diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index e9ec32fb97d4..2cc21ffcdaf9 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -147,7 +147,7 @@ static inline int stack_depot_early_init(void) { return 0; } * 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 STACK_DEPOT_FLAG_CAN_ALLOC is required if + * Context: Any context, but unsetting STACK_DEPOT_FLAG_CAN_ALLOC 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). @@ -156,7 +156,7 @@ static inline int stack_depot_early_init(void) { return 0; } */ depot_stack_handle_t stack_depot_save_flags(unsigned long *entries, unsigned int nr_entries, - gfp_t gfp_flags, + gfp_t alloc_flags, depot_flags_t depot_flags); /** @@ -175,7 +175,7 @@ depot_stack_handle_t stack_depot_save_flags(unsigned long *entries, * 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); + unsigned int nr_entries, gfp_t alloc_flags); /** * __stack_depot_get_stack_record - Get a pointer to a stack_record struct diff --git a/include/linux/stat.h b/include/linux/stat.h index 52150570d37a..be7496a6a0dd 100644 --- a/include/linux/stat.h +++ b/include/linux/stat.h @@ -50,9 +50,14 @@ struct kstat { struct timespec64 btime; /* File creation time */ u64 blocks; u64 mnt_id; + u64 change_cookie; + u64 subvol; u32 dio_mem_align; u32 dio_offset_align; - u64 change_cookie; + u32 dio_read_offset_align; + u32 atomic_write_unit_min; + u32 atomic_write_unit_max; + u32 atomic_write_segments_max; }; /* These definitions are internal to the kernel for now. Mainly used by nfsd. */ diff --git a/include/linux/static_call.h b/include/linux/static_call.h index 141e6b176a1b..78a77a4ae0ea 100644 --- a/include/linux/static_call.h +++ b/include/linux/static_call.h @@ -160,6 +160,8 @@ extern void arch_static_call_transform(void *site, void *tramp, void *func, bool #ifdef CONFIG_HAVE_STATIC_CALL_INLINE +extern int static_call_initialized; + extern int __init static_call_init(void); extern void static_call_force_reinit(void); @@ -225,6 +227,8 @@ extern long __static_call_return0(void); #elif defined(CONFIG_HAVE_STATIC_CALL) +#define static_call_initialized 0 + static inline int static_call_init(void) { return 0; } #define DEFINE_STATIC_CALL(name, _func) \ @@ -281,6 +285,8 @@ extern long __static_call_return0(void); #else /* Generic implementation */ +#define static_call_initialized 0 + static inline int static_call_init(void) { return 0; } static inline long __static_call_return0(void) diff --git a/include/linux/stm.h b/include/linux/stm.h index 3b22689512be..2fcbef9608f6 100644 --- a/include/linux/stm.h +++ b/include/linux/stm.h @@ -30,6 +30,16 @@ enum stp_packet_flags { STP_PACKET_TIMESTAMPED = 0x2, }; +/** + * enum stm_source_type - STM source driver + * @STM_USER: any STM trace source + * @STM_FTRACE: ftrace STM source + */ +enum stm_source_type { + STM_USER, + STM_FTRACE, +}; + struct stp_policy; struct stm_device; @@ -106,6 +116,7 @@ struct stm_source_device; * @name: device name, will be used for policy lookup * @src: internal structure, only used by stm class code * @nr_chans: number of channels to allocate + * @type: type of STM source driver represented by stm_source_type * @link: called when this source gets linked to an STM device * @unlink: called when this source is about to get unlinked from its STM * @@ -117,6 +128,7 @@ struct stm_source_data { struct stm_source_device *src; unsigned int percpu; unsigned int nr_chans; + unsigned int type; int (*link)(struct stm_source_data *data); void (*unlink)(struct stm_source_data *data); }; diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index dfa1828cd756..c9878a612e53 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -13,7 +13,7 @@ #define __STMMAC_PLATFORM_DATA #include <linux/platform_device.h> -#include <linux/phy.h> +#include <linux/phylink.h> #define MTL_MAX_RX_QUEUES 8 #define MTL_MAX_TX_QUEUES 8 @@ -33,7 +33,9 @@ #define STMMAC_CSR_20_35M 0x2 /* MDC = clk_scr_i/16 */ #define STMMAC_CSR_35_60M 0x3 /* MDC = clk_scr_i/26 */ #define STMMAC_CSR_150_250M 0x4 /* MDC = clk_scr_i/102 */ -#define STMMAC_CSR_250_300M 0x5 /* MDC = clk_scr_i/122 */ +#define STMMAC_CSR_250_300M 0x5 /* MDC = clk_scr_i/124 */ +#define STMMAC_CSR_300_500M 0x6 /* MDC = clk_scr_i/204 */ +#define STMMAC_CSR_500_800M 0x7 /* MDC = clk_scr_i/324 */ /* MTL algorithms identifiers */ #define MTL_TX_ALGORITHM_WRR 0x0 @@ -82,8 +84,8 @@ struct stmmac_priv; struct stmmac_mdio_bus_data { unsigned int phy_mask; - unsigned int has_xpcs; - unsigned int xpcs_an_inband; + unsigned int pcs_mask; + unsigned int default_an_inband; int *irqs; int probed_phy_irq; bool needs_reset; @@ -100,6 +102,7 @@ struct stmmac_dma_cfg { bool eame; bool multi_msi_en; bool dche; + bool atds; }; #define AXI_BLEN 7 @@ -115,21 +118,6 @@ struct stmmac_axi { bool axi_rb; }; -#define EST_GCL 1024 -struct stmmac_est { - struct mutex lock; - int enable; - u32 btr_reserve[2]; - u32 btr_offset[2]; - u32 btr[2]; - u32 ctr[2]; - u32 ter; - u32 gcl_unaligned[EST_GCL]; - u32 gcl[EST_GCL]; - u32 gcl_size; - u32 max_sdu[MTL_MAX_TX_QUEUES]; -}; - struct stmmac_rxq_cfg { u8 mode_to_use; u32 chan; @@ -152,33 +140,6 @@ struct stmmac_txq_cfg { int tbs_en; }; -/* FPE link state */ -enum stmmac_fpe_state { - FPE_STATE_OFF = 0, - FPE_STATE_CAPABLE = 1, - FPE_STATE_ENTERING_ON = 2, - FPE_STATE_ON = 3, -}; - -/* FPE link-partner hand-shaking mPacket type */ -enum stmmac_mpacket_type { - MPACKET_VERIFY = 0, - MPACKET_RESPONSE = 1, -}; - -enum stmmac_fpe_task_state_t { - __FPE_REMOVING, - __FPE_TASK_SCHED, -}; - -struct stmmac_fpe_cfg { - bool enable; /* FPE enable */ - bool hs_enable; /* FPE handshake enable */ - enum stmmac_fpe_state lp_fpe_state; /* Link Partner FPE state */ - enum stmmac_fpe_state lo_fpe_state; /* Local station FPE state */ - u32 fpe_csr; /* MAC_FPE_CTRL_STS reg cache */ -}; - struct stmmac_safety_feature_cfg { u32 tsoee; u32 mrxpee; @@ -246,8 +207,6 @@ struct plat_stmmacenet_data { struct fwnode_handle *port_node; struct device_node *mdio_node; struct stmmac_dma_cfg *dma_cfg; - struct stmmac_est *est; - struct stmmac_fpe_cfg *fpe_cfg; struct stmmac_safety_feature_cfg *safety_feat_cfg; int clk_csr; int has_gmac; @@ -285,12 +244,16 @@ struct plat_stmmacenet_data { int (*crosststamp)(ktime_t *device, struct system_counterval_t *system, void *ctx); void (*dump_debug_regs)(void *priv); + int (*pcs_init)(struct stmmac_priv *priv); + void (*pcs_exit)(struct stmmac_priv *priv); + struct phylink_pcs *(*select_pcs)(struct stmmac_priv *priv, + phy_interface_t interface); void *bsp_priv; struct clk *stmmac_clk; struct clk *pclk; struct clk *clk_ptp_ref; - unsigned int clk_ptp_rate; - unsigned int clk_ref_rate; + unsigned long clk_ptp_rate; + unsigned long clk_ref_rate; unsigned int mult_fact_100ns; s32 ptp_max_adj; u32 cdc_error_adj; @@ -302,7 +265,7 @@ struct plat_stmmacenet_data { int mac_port_sel_speed; int has_xgmac; u8 vlan_fail_q; - unsigned int eee_usecs_rate; + unsigned long eee_usecs_rate; struct pci_dev *pdev; int int_snapshot_num; int msi_mac_vec; diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h index ea7a74ea7389..3132262a404d 100644 --- a/include/linux/stop_machine.h +++ b/include/linux/stop_machine.h @@ -3,7 +3,7 @@ #define _LINUX_STOP_MACHINE #include <linux/cpu.h> -#include <linux/cpumask.h> +#include <linux/cpumask_types.h> #include <linux/smp.h> #include <linux/list.h> diff --git a/include/linux/string.h b/include/linux/string.h index 9ba8b4597009..86d5d352068b 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -4,6 +4,7 @@ #include <linux/args.h> #include <linux/array_size.h> +#include <linux/cleanup.h> /* for DEFINE_FREE() */ #include <linux/compiler.h> /* for inline */ #include <linux/types.h> /* for size_t */ #include <linux/stddef.h> /* for NULL */ @@ -14,8 +15,8 @@ #include <uapi/linux/string.h> extern char *strndup_user(const char __user *, long); -extern void *memdup_user(const void __user *, size_t); -extern void *vmemdup_user(const void __user *, size_t); +extern void *memdup_user(const void __user *, size_t) __realloc_size(2); +extern void *vmemdup_user(const void __user *, size_t) __realloc_size(2); extern void *memdup_user_nul(const void __user *, size_t); /** @@ -27,7 +28,8 @@ extern void *memdup_user_nul(const void __user *, size_t); * Return: an ERR_PTR() on failure. Result is physically * contiguous, to be freed by kfree(). */ -static inline void *memdup_array_user(const void __user *src, size_t n, size_t size) +static inline __realloc_size(2, 3) +void *memdup_array_user(const void __user *src, size_t n, size_t size) { size_t nbytes; @@ -46,7 +48,8 @@ static inline void *memdup_array_user(const void __user *src, size_t n, size_t s * Return: an ERR_PTR() on failure. Result may be not * physically contiguous. Use kvfree() to free. */ -static inline void *vmemdup_array_user(const void __user *src, size_t n, size_t size) +static inline __realloc_size(2, 3) +void *vmemdup_array_user(const void __user *src, size_t n, size_t size) { size_t nbytes; @@ -74,12 +77,16 @@ ssize_t sized_strscpy(char *, const char *, size_t); * known size. */ #define __strscpy0(dst, src, ...) \ - sized_strscpy(dst, src, sizeof(dst) + __must_be_array(dst)) -#define __strscpy1(dst, src, size) sized_strscpy(dst, src, size) + sized_strscpy(dst, src, sizeof(dst) + __must_be_array(dst) + \ + __must_be_cstr(dst) + __must_be_cstr(src)) +#define __strscpy1(dst, src, size) \ + sized_strscpy(dst, src, size + __must_be_cstr(dst) + __must_be_cstr(src)) #define __strscpy_pad0(dst, src, ...) \ - sized_strscpy_pad(dst, src, sizeof(dst) + __must_be_array(dst)) -#define __strscpy_pad1(dst, src, size) sized_strscpy_pad(dst, src, size) + sized_strscpy_pad(dst, src, sizeof(dst) + __must_be_array(dst) + \ + __must_be_cstr(dst) + __must_be_cstr(src)) +#define __strscpy_pad1(dst, src, size) \ + sized_strscpy_pad(dst, src, size + __must_be_cstr(dst) + __must_be_cstr(src)) /** * strscpy - Copy a C-string into a sized buffer @@ -277,20 +284,37 @@ static inline void memcpy_flushcache(void *dst, const void *src, size_t cnt) void *memchr_inv(const void *s, int c, size_t n); char *strreplace(char *str, char old, char new); +/** + * mem_is_zero - Check if an area of memory is all 0's. + * @s: The memory area + * @n: The size of the area + * + * Return: True if the area of memory is all 0's. + */ +static inline bool mem_is_zero(const void *s, size_t n) +{ + return !memchr_inv(s, 0, n); +} + extern void kfree_const(const void *x); 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 *kmemdup_noprof(const void *src, size_t len, gfp_t gfp) __realloc_size(2); +#define kmemdup(...) alloc_hooks(kmemdup_noprof(__VA_ARGS__)) + 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 void *kmemdup_array(const void *src, size_t element_size, size_t count, gfp_t gfp); +extern void *kmemdup_array(const void *src, size_t count, size_t element_size, gfp_t gfp) + __realloc_size(2, 3); /* lib/argv_split.c */ extern char **argv_split(gfp_t gfp, const char *str, int *argcp); extern void argv_free(char **argv); +DEFINE_FREE(argv_free, char **, if (!IS_ERR_OR_NULL(_T)) argv_free(_T)) + /* lib/cmdline.c */ extern int get_option(char **str, int *pint); extern char *get_options(const char *str, int nints, int *ints); @@ -314,7 +338,6 @@ int __sysfs_match_string(const char * const *array, size_t n, const char *s); #ifdef CONFIG_BINARY_PRINTF int vbin_printf(u32 *bin_buf, size_t size, const char *fmt, va_list args); int bstr_printf(char *buf, size_t size, const char *fmt, const u32 *bin_buf); -int bprintf(u32 *bin_buf, size_t size, const char *fmt, ...) __printf(3, 4); #endif extern ssize_t memory_read_from_buffer(void *to, size_t count, loff_t *ppos, @@ -423,6 +446,55 @@ void memcpy_and_pad(void *dest, size_t dest_len, const void *src, size_t count, } while (0) /** + * memtostr - Copy a possibly non-NUL-term string to a NUL-term string + * @dest: Pointer to destination NUL-terminates string + * @src: Pointer to character array (likely marked as __nonstring) + * + * This is a replacement for strncpy() uses where the source is not + * a NUL-terminated string. + * + * Note that sizes of @dest and @src must be known at compile-time. + */ +#define memtostr(dest, src) do { \ + const size_t _dest_len = __builtin_object_size(dest, 1); \ + const size_t _src_len = __builtin_object_size(src, 1); \ + const size_t _src_chars = strnlen(src, _src_len); \ + const size_t _copy_len = min(_dest_len - 1, _src_chars); \ + \ + BUILD_BUG_ON(!__builtin_constant_p(_dest_len) || \ + !__builtin_constant_p(_src_len) || \ + _dest_len == 0 || _dest_len == (size_t)-1 || \ + _src_len == 0 || _src_len == (size_t)-1); \ + memcpy(dest, src, _copy_len); \ + dest[_copy_len] = '\0'; \ +} while (0) + +/** + * memtostr_pad - Copy a possibly non-NUL-term string to a NUL-term string + * with NUL padding in the destination + * @dest: Pointer to destination NUL-terminates string + * @src: Pointer to character array (likely marked as __nonstring) + * + * This is a replacement for strncpy() uses where the source is not + * a NUL-terminated string. + * + * Note that sizes of @dest and @src must be known at compile-time. + */ +#define memtostr_pad(dest, src) do { \ + const size_t _dest_len = __builtin_object_size(dest, 1); \ + const size_t _src_len = __builtin_object_size(src, 1); \ + const size_t _src_chars = strnlen(src, _src_len); \ + const size_t _copy_len = min(_dest_len - 1, _src_chars); \ + \ + BUILD_BUG_ON(!__builtin_constant_p(_dest_len) || \ + !__builtin_constant_p(_src_len) || \ + _dest_len == 0 || _dest_len == (size_t)-1 || \ + _src_len == 0 || _src_len == (size_t)-1); \ + memcpy(dest, src, _copy_len); \ + memset(&dest[_copy_len], 0, _dest_len - _copy_len); \ +} while (0) + +/** * memset_after - Set a value after a struct member to the end of a struct * * @obj: Address of target struct instance diff --git a/include/linux/string_choices.h b/include/linux/string_choices.h index d9ebe20229f8..120ca0f28e95 100644 --- a/include/linux/string_choices.h +++ b/include/linux/string_choices.h @@ -2,17 +2,32 @@ #ifndef _LINUX_STRING_CHOICES_H_ #define _LINUX_STRING_CHOICES_H_ +/* + * Here provide a series of helpers in the str_$TRUE_$FALSE format (you can + * also expand some helpers as needed), where $TRUE and $FALSE are their + * corresponding literal strings. These helpers can be used in the printing + * and also in other places where constant strings are required. Using these + * helpers offers the following benefits: + * 1) Reducing the hardcoding of strings, which makes the code more elegant + * through these simple literal-meaning helpers. + * 2) Unifying the output, which prevents the same string from being printed + * in various forms, such as enable/disable, enabled/disabled, en/dis. + * 3) Deduping by the linker, which results in a smaller binary file. + */ + #include <linux/types.h> static inline const char *str_enable_disable(bool v) { return v ? "enable" : "disable"; } +#define str_disable_enable(v) str_enable_disable(!(v)) static inline const char *str_enabled_disabled(bool v) { return v ? "enabled" : "disabled"; } +#define str_disabled_enabled(v) str_enabled_disabled(!(v)) static inline const char *str_hi_lo(bool v) { @@ -36,11 +51,25 @@ static inline const char *str_on_off(bool v) { return v ? "on" : "off"; } +#define str_off_on(v) str_on_off(!(v)) static inline const char *str_yes_no(bool v) { return v ? "yes" : "no"; } +#define str_no_yes(v) str_yes_no(!(v)) + +static inline const char *str_up_down(bool v) +{ + return v ? "up" : "down"; +} +#define str_down_up(v) str_up_down(!(v)) + +static inline const char *str_true_false(bool v) +{ + return v ? "true" : "false"; +} +#define str_false_true(v) str_true_false(!(v)) /** * str_plural - Return the simple pluralization based on English counts diff --git a/include/linux/sungem_phy.h b/include/linux/sungem_phy.h index c505f30e8b68..eecc7eb63bfb 100644 --- a/include/linux/sungem_phy.h +++ b/include/linux/sungem_phy.h @@ -40,7 +40,7 @@ enum { /* An instance of a PHY, partially borrowed from mii_if_info */ struct mii_phy { - struct mii_phy_def* def; + const struct mii_phy_def *def; u32 advertising; int mii_id; diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index 35766963dd14..e783132e481f 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -222,6 +222,8 @@ static inline bool cache_is_expired(struct cache_detail *detail, struct cache_he return detail->flush_time >= h->last_refresh; } +extern int cache_check_rcu(struct cache_detail *detail, + struct cache_head *h, struct cache_req *rqstp); extern int cache_check(struct cache_detail *detail, struct cache_head *h, struct cache_req *rqstp); extern void cache_flush(void); diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 5321585c778f..fec976e58174 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -93,6 +93,7 @@ struct rpc_clnt { const struct cred *cl_cred; unsigned int cl_max_connect; /* max number of transports not to the same IP */ struct super_block *pipefs_sb; + atomic_t cl_task_count; }; /* diff --git a/include/linux/sunrpc/gss_asn1.h b/include/linux/sunrpc/gss_asn1.h deleted file mode 100644 index 3ccecd0ad229..000000000000 --- a/include/linux/sunrpc/gss_asn1.h +++ /dev/null @@ -1,81 +0,0 @@ -/* - * linux/include/linux/sunrpc/gss_asn1.h - * - * minimal asn1 for generic encoding/decoding of gss tokens - * - * Adapted from MIT Kerberos 5-1.2.1 lib/include/krb5.h, - * lib/gssapi/krb5/gssapiP_krb5.h, and others - * - * Copyright (c) 2000 The Regents of the University of Michigan. - * All rights reserved. - * - * Andy Adamson <andros@umich.edu> - */ - -/* - * Copyright 1995 by the Massachusetts Institute of Technology. - * All Rights Reserved. - * - * Export of this software from the United States of America may - * require a specific license from the United States Government. - * It is the responsibility of any person or organization contemplating - * export to obtain such a license before exporting. - * - * WITHIN THAT CONSTRAINT, permission to use, copy, modify, and - * distribute this software and its documentation for any purpose and - * without fee is hereby granted, provided that the above copyright - * notice appear in all copies and that both that copyright notice and - * this permission notice appear in supporting documentation, and that - * the name of M.I.T. not be used in advertising or publicity pertaining - * to distribution of the software without specific, written prior - * permission. Furthermore if you modify this software you must label - * your software as modified software and not distribute it in such a - * fashion that it might be confused with the original M.I.T. software. - * M.I.T. makes no representations about the suitability of - * this software for any purpose. It is provided "as is" without express - * or implied warranty. - * - */ - - -#include <linux/sunrpc/gss_api.h> - -#define SIZEOF_INT 4 - -/* from gssapi_err_generic.h */ -#define G_BAD_SERVICE_NAME (-2045022976L) -#define G_BAD_STRING_UID (-2045022975L) -#define G_NOUSER (-2045022974L) -#define G_VALIDATE_FAILED (-2045022973L) -#define G_BUFFER_ALLOC (-2045022972L) -#define G_BAD_MSG_CTX (-2045022971L) -#define G_WRONG_SIZE (-2045022970L) -#define G_BAD_USAGE (-2045022969L) -#define G_UNKNOWN_QOP (-2045022968L) -#define G_NO_HOSTNAME (-2045022967L) -#define G_BAD_HOSTNAME (-2045022966L) -#define G_WRONG_MECH (-2045022965L) -#define G_BAD_TOK_HEADER (-2045022964L) -#define G_BAD_DIRECTION (-2045022963L) -#define G_TOK_TRUNC (-2045022962L) -#define G_REFLECT (-2045022961L) -#define G_WRONG_TOKID (-2045022960L) - -#define g_OID_equal(o1,o2) \ - (((o1)->len == (o2)->len) && \ - (memcmp((o1)->data,(o2)->data,(int) (o1)->len) == 0)) - -u32 g_verify_token_header( - struct xdr_netobj *mech, - int *body_size, - unsigned char **buf_in, - int toksize); - -int g_token_size( - struct xdr_netobj *mech, - unsigned int body_size); - -void g_make_token_header( - struct xdr_netobj *mech, - int body_size, - unsigned char **buf); diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index 78a80bf3fdcb..43950b5237c8 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -40,7 +40,6 @@ #include <crypto/skcipher.h> #include <linux/sunrpc/auth_gss.h> #include <linux/sunrpc/gss_err.h> -#include <linux/sunrpc/gss_asn1.h> /* Length of constant used in key derivation */ #define GSS_KRB5_K5CLENGTH (5) diff --git a/include/linux/sunrpc/rdma_rn.h b/include/linux/sunrpc/rdma_rn.h new file mode 100644 index 000000000000..7d032ca057af --- /dev/null +++ b/include/linux/sunrpc/rdma_rn.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * * Copyright (c) 2024, Oracle and/or its affiliates. + */ + +#ifndef _LINUX_SUNRPC_RDMA_RN_H +#define _LINUX_SUNRPC_RDMA_RN_H + +#include <rdma/ib_verbs.h> + +/** + * rpcrdma_notification - request removal notification + */ +struct rpcrdma_notification { + void (*rn_done)(struct rpcrdma_notification *rn); + u32 rn_index; +}; + +int rpcrdma_rn_register(struct ib_device *device, + struct rpcrdma_notification *rn, + void (*done)(struct rpcrdma_notification *rn)); +void rpcrdma_rn_unregister(struct ib_device *device, + struct rpcrdma_notification *rn); +int rpcrdma_ib_client_register(void); +void rpcrdma_ib_client_unregister(void); + +#endif /* _LINUX_SUNRPC_RDMA_RN_H */ diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 0c77ba488bba..fec1e8a1570c 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -151,13 +151,15 @@ struct rpc_task_setup { #define RPC_WAS_SENT(t) ((t)->tk_flags & RPC_TASK_SENT) #define RPC_IS_MOVEABLE(t) ((t)->tk_flags & RPC_TASK_MOVEABLE) -#define RPC_TASK_RUNNING 0 -#define RPC_TASK_QUEUED 1 -#define RPC_TASK_ACTIVE 2 -#define RPC_TASK_NEED_XMIT 3 -#define RPC_TASK_NEED_RECV 4 -#define RPC_TASK_MSG_PIN_WAIT 5 -#define RPC_TASK_SIGNALLED 6 +enum { + RPC_TASK_RUNNING, + RPC_TASK_QUEUED, + RPC_TASK_ACTIVE, + RPC_TASK_NEED_XMIT, + RPC_TASK_NEED_RECV, + RPC_TASK_MSG_PIN_WAIT, + RPC_TASK_SIGNALLED, +}; #define rpc_test_and_set_running(t) \ test_and_set_bit(RPC_TASK_RUNNING, &(t)->tk_runstate) diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 23617da0e565..74658cca0f38 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -21,6 +21,7 @@ #include <linux/wait.h> #include <linux/mm.h> #include <linux/pagevec.h> +#include <linux/kthread.h> /* * @@ -33,9 +34,9 @@ * node traffic on multi-node NUMA NFS servers. */ struct svc_pool { - unsigned int sp_id; /* pool id; also node id on NUMA */ + unsigned int sp_id; /* pool id; also node id on NUMA */ struct lwq sp_xprts; /* pending transports */ - atomic_t sp_nrthreads; /* # of threads in pool */ + unsigned int sp_nrthreads; /* # of threads in pool */ struct list_head sp_all_threads; /* all server threads */ struct llist_head sp_idle_threads; /* idle server threads */ @@ -66,25 +67,23 @@ enum { * We currently do not support more than one RPC program per daemon. */ struct svc_serv { - struct svc_program * sv_program; /* RPC program */ + struct svc_program * sv_programs; /* RPC programs */ struct svc_stat * sv_stats; /* RPC statistics */ spinlock_t sv_lock; + unsigned int sv_nprogs; /* Number of sv_programs */ unsigned int sv_nrthreads; /* # of server threads */ - unsigned int sv_maxconn; /* max connections allowed or - * '0' causing max to be based - * on number of threads. */ - unsigned int sv_max_payload; /* datagram payload size */ unsigned int sv_max_mesg; /* max_payload + 1 page for overheads */ unsigned int sv_xdrsize; /* XDR buffer size */ struct list_head sv_permsocks; /* all permanent sockets */ struct list_head sv_tempsocks; /* all temporary sockets */ - int sv_tmpcnt; /* count of temporary sockets */ + int sv_tmpcnt; /* count of temporary "valid" sockets */ struct timer_list sv_temptimer; /* timer for aging temporary sockets */ char * sv_name; /* service name */ unsigned int sv_nrpools; /* number of thread pools */ + bool sv_is_pooled; /* is this a pooled service? */ struct svc_pool * sv_pools; /* array of thread pools */ int (*sv_threadfn)(void *data); @@ -231,6 +230,11 @@ struct svc_rqst { struct net *rq_bc_net; /* pointer to backchannel's * net namespace */ + + int rq_err; /* Thread sets this to inidicate + * initialisation success. + */ + unsigned long bc_to_initval; unsigned int bc_to_retries; void ** rq_lease_breaker; /* The v4 client breaking a lease */ @@ -304,6 +308,26 @@ static inline bool svc_thread_should_stop(struct svc_rqst *rqstp) return test_bit(RQ_VICTIM, &rqstp->rq_flags); } +/** + * svc_thread_init_status - report whether thread has initialised successfully + * @rqstp: the thread in question + * @err: errno code + * + * After performing any initialisation that could fail, and before starting + * normal work, each sunrpc svc_thread must call svc_thread_init_status() + * with an appropriate error, or zero. + * + * If zero is passed, the thread is ready and must continue until + * svc_thread_should_stop() returns true. If a non-zero error is passed + * the call will not return - the thread will exit. + */ +static inline void svc_thread_init_status(struct svc_rqst *rqstp, int err) +{ + store_release_wake_up(&rqstp->rq_err, err); + if (err) + kthread_exit(1); +} + struct svc_deferred_req { u32 prot; /* protocol (UDP or TCP) */ struct svc_xprt *xprt; @@ -328,10 +352,9 @@ struct svc_process_info { }; /* - * List of RPC programs on the same transport endpoint + * RPC program - an array of these can use the same transport endpoint */ struct svc_program { - struct svc_program * pg_next; /* other programs (same xprt) */ u32 pg_prog; /* program number */ unsigned int pg_lovers; /* lowest version */ unsigned int pg_hivers; /* highest version */ @@ -398,19 +421,18 @@ struct svc_procedure { /* * Function prototypes. */ -int svc_rpcb_setup(struct svc_serv *serv, struct net *net); +int sunrpc_set_pool_mode(const char *val); +int sunrpc_get_pool_mode(char *val, size_t size); void svc_rpcb_cleanup(struct svc_serv *serv, struct net *net); int svc_bind(struct svc_serv *serv, struct net *net); struct svc_serv *svc_create(struct svc_program *, unsigned int, int (*threadfn)(void *data)); -struct svc_rqst *svc_rqst_alloc(struct svc_serv *serv, - struct svc_pool *pool, int node); bool svc_rqst_replace_page(struct svc_rqst *rqstp, struct page *page); void svc_rqst_release_pages(struct svc_rqst *rqstp); -void svc_rqst_free(struct svc_rqst *); void svc_exit_thread(struct svc_rqst *); struct svc_serv * svc_create_pooled(struct svc_program *prog, + unsigned int nprog, struct svc_stat *stats, unsigned int bufsize, int (*threadfn)(void *data)); @@ -443,11 +465,6 @@ int svc_generic_rpcbind_set(struct net *net, u32 version, int family, unsigned short proto, unsigned short port); -int svc_rpcbind_set_version(struct net *net, - const struct svc_program *progp, - u32 version, int family, - unsigned short proto, - unsigned short port); #define RPC_MAX_ADDRBUFLEN (63U) diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index d33bab33099a..619fc0bd837a 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -48,6 +48,7 @@ #include <linux/sunrpc/rpc_rdma.h> #include <linux/sunrpc/rpc_rdma_cid.h> #include <linux/sunrpc/svc_rdma_pcl.h> +#include <linux/sunrpc/rdma_rn.h> #include <linux/percpu_counter.h> #include <rdma/ib_verbs.h> @@ -76,6 +77,7 @@ struct svcxprt_rdma { struct svc_xprt sc_xprt; /* SVC transport structure */ struct rdma_cm_id *sc_cm_id; /* RDMA connection id */ struct list_head sc_accept_q; /* Conn. waiting accept */ + struct rpcrdma_notification sc_rn; /* removal notification */ int sc_ord; /* RDMA read limit */ int sc_max_send_sges; bool sc_snd_w_inv; /* OK to use Send With Invalidate */ diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index 8e20cd60e2e7..72be60952579 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -99,8 +99,30 @@ enum { XPT_HANDSHAKE, /* xprt requests a handshake */ XPT_TLS_SESSION, /* transport-layer security established */ XPT_PEER_AUTH, /* peer has been authenticated */ + XPT_PEER_VALID, /* peer has presented a filehandle that + * it has access to. It is NOT counted + * in ->sv_tmpcnt. + */ }; +/* + * Maximum number of "tmp" connections - those without XPT_PEER_VALID - + * permitted on any service. + */ +#define XPT_MAX_TMP_CONN 64 + +static inline void svc_xprt_set_valid(struct svc_xprt *xpt) +{ + if (test_bit(XPT_TEMP, &xpt->xpt_flags) && + !test_and_set_bit(XPT_PEER_VALID, &xpt->xpt_flags)) { + struct svc_serv *serv = xpt->xpt_server; + + spin_lock(&serv->sv_lock); + serv->sv_tmpcnt -= 1; + spin_unlock(&serv->sv_lock); + } +} + static inline void unregister_xpt_user(struct svc_xprt *xpt, struct svc_xpt_user *u) { spin_lock(&xpt->xpt_lock); @@ -135,6 +157,9 @@ int svc_reg_xprt_class(struct svc_xprt_class *); void svc_unreg_xprt_class(struct svc_xprt_class *); void svc_xprt_init(struct net *, struct svc_xprt_class *, struct svc_xprt *, struct svc_serv *); +int svc_xprt_create_from_sa(struct svc_serv *serv, const char *xprt_name, + struct net *net, struct sockaddr *sap, + int flags, const struct cred *cred); int svc_xprt_create(struct svc_serv *serv, const char *xprt_name, struct net *net, const int family, const unsigned short port, int flags, @@ -147,6 +172,8 @@ void svc_xprt_copy_addrs(struct svc_rqst *rqstp, struct svc_xprt *xprt); void svc_xprt_close(struct svc_xprt *xprt); int svc_port_is_privileged(struct sockaddr *sin); int svc_print_xprts(char *buf, int maxlen); +struct svc_xprt *svc_find_listener(struct svc_serv *serv, const char *xcl_name, + struct net *net, const struct sockaddr *sa); struct svc_xprt *svc_find_xprt(struct svc_serv *serv, const char *xcl_name, struct net *net, const sa_family_t af, const unsigned short port); diff --git a/include/linux/sunrpc/svcauth.h b/include/linux/sunrpc/svcauth.h index 61c455f1e1f5..2e111153f7cd 100644 --- a/include/linux/sunrpc/svcauth.h +++ b/include/linux/sunrpc/svcauth.h @@ -14,6 +14,7 @@ #include <linux/sunrpc/msg_prot.h> #include <linux/sunrpc/cache.h> #include <linux/sunrpc/gss_api.h> +#include <linux/sunrpc/clnt.h> #include <linux/hash.h> #include <linux/stringhash.h> #include <linux/cred.h> @@ -151,13 +152,16 @@ struct auth_ops { struct svc_xprt; -extern enum svc_auth_status svc_authenticate(struct svc_rqst *rqstp); extern rpc_authflavor_t svc_auth_flavor(struct svc_rqst *rqstp); extern int svc_authorise(struct svc_rqst *rqstp); extern enum svc_auth_status svc_set_client(struct svc_rqst *rqstp); extern int svc_auth_register(rpc_authflavor_t flavor, struct auth_ops *aops); extern void svc_auth_unregister(rpc_authflavor_t flavor); +extern void svcauth_map_clnt_to_svc_cred_local(struct rpc_clnt *clnt, + const struct cred *, + struct svc_cred *); + extern struct auth_domain *unix_domain_find(char *name); extern void auth_domain_put(struct auth_domain *item); extern struct auth_domain *auth_domain_lookup(char *name, struct auth_domain *new); diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h index 7c78ec6356b9..bf45d9e8492a 100644 --- a/include/linux/sunrpc/svcsock.h +++ b/include/linux/sunrpc/svcsock.h @@ -58,8 +58,6 @@ static inline u32 svc_sock_final_rec(struct svc_sock *svsk) */ void svc_recv(struct svc_rqst *rqstp); void svc_send(struct svc_rqst *rqstp); -void svc_drop(struct svc_rqst *); -void svc_sock_update_bufs(struct svc_serv *serv); int svc_addsock(struct svc_serv *serv, struct net *net, const int fd, char *name_return, const size_t len, const struct cred *cred); diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 2f8dc47f1eb0..a2ab813a9800 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -13,7 +13,7 @@ #include <linux/uio.h> #include <asm/byteorder.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/scatterlist.h> struct bio_vec; @@ -681,6 +681,27 @@ xdr_stream_decode_u32(struct xdr_stream *xdr, __u32 *ptr) } /** + * xdr_stream_decode_be32 - Decode a big-endian 32-bit integer + * @xdr: pointer to xdr_stream + * @ptr: location to store integer + * + * Return values: + * %0 on success + * %-EBADMSG on XDR buffer overflow + */ +static inline ssize_t +xdr_stream_decode_be32(struct xdr_stream *xdr, __be32 *ptr) +{ + const size_t count = sizeof(*ptr); + __be32 *p = xdr_inline_decode(xdr, count); + + if (unlikely(!p)) + return -EBADMSG; + *ptr = *p; + return 0; +} + +/** * xdr_stream_decode_u64 - Decode a 64-bit integer * @xdr: pointer to xdr_stream * @ptr: location to store 64-bit integer diff --git a/include/linux/sunrpc/xdrgen/_builtins.h b/include/linux/sunrpc/xdrgen/_builtins.h new file mode 100644 index 000000000000..66ca3ece951a --- /dev/null +++ b/include/linux/sunrpc/xdrgen/_builtins.h @@ -0,0 +1,243 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2024 Oracle and/or its affiliates. + * + * This header defines XDR data type primitives specified in + * Section 4 of RFC 4506, used by RPC programs implemented + * in the Linux kernel. + */ + +#ifndef _SUNRPC_XDRGEN__BUILTINS_H_ +#define _SUNRPC_XDRGEN__BUILTINS_H_ + +#include <linux/sunrpc/xdr.h> + +static inline bool +xdrgen_decode_void(struct xdr_stream *xdr) +{ + return true; +} + +static inline bool +xdrgen_encode_void(struct xdr_stream *xdr) +{ + return true; +} + +static inline bool +xdrgen_decode_bool(struct xdr_stream *xdr, bool *ptr) +{ + __be32 *p = xdr_inline_decode(xdr, XDR_UNIT); + + if (unlikely(!p)) + return false; + *ptr = (*p != xdr_zero); + return true; +} + +static inline bool +xdrgen_encode_bool(struct xdr_stream *xdr, bool val) +{ + __be32 *p = xdr_reserve_space(xdr, XDR_UNIT); + + if (unlikely(!p)) + return false; + *p = val ? xdr_one : xdr_zero; + return true; +} + +static inline bool +xdrgen_decode_int(struct xdr_stream *xdr, s32 *ptr) +{ + __be32 *p = xdr_inline_decode(xdr, XDR_UNIT); + + if (unlikely(!p)) + return false; + *ptr = be32_to_cpup(p); + return true; +} + +static inline bool +xdrgen_encode_int(struct xdr_stream *xdr, s32 val) +{ + __be32 *p = xdr_reserve_space(xdr, XDR_UNIT); + + if (unlikely(!p)) + return false; + *p = cpu_to_be32(val); + return true; +} + +static inline bool +xdrgen_decode_unsigned_int(struct xdr_stream *xdr, u32 *ptr) +{ + __be32 *p = xdr_inline_decode(xdr, XDR_UNIT); + + if (unlikely(!p)) + return false; + *ptr = be32_to_cpup(p); + return true; +} + +static inline bool +xdrgen_encode_unsigned_int(struct xdr_stream *xdr, u32 val) +{ + __be32 *p = xdr_reserve_space(xdr, XDR_UNIT); + + if (unlikely(!p)) + return false; + *p = cpu_to_be32(val); + return true; +} + +static inline bool +xdrgen_decode_long(struct xdr_stream *xdr, s32 *ptr) +{ + __be32 *p = xdr_inline_decode(xdr, XDR_UNIT); + + if (unlikely(!p)) + return false; + *ptr = be32_to_cpup(p); + return true; +} + +static inline bool +xdrgen_encode_long(struct xdr_stream *xdr, s32 val) +{ + __be32 *p = xdr_reserve_space(xdr, XDR_UNIT); + + if (unlikely(!p)) + return false; + *p = cpu_to_be32(val); + return true; +} + +static inline bool +xdrgen_decode_unsigned_long(struct xdr_stream *xdr, u32 *ptr) +{ + __be32 *p = xdr_inline_decode(xdr, XDR_UNIT); + + if (unlikely(!p)) + return false; + *ptr = be32_to_cpup(p); + return true; +} + +static inline bool +xdrgen_encode_unsigned_long(struct xdr_stream *xdr, u32 val) +{ + __be32 *p = xdr_reserve_space(xdr, XDR_UNIT); + + if (unlikely(!p)) + return false; + *p = cpu_to_be32(val); + return true; +} + +static inline bool +xdrgen_decode_hyper(struct xdr_stream *xdr, s64 *ptr) +{ + __be32 *p = xdr_inline_decode(xdr, XDR_UNIT * 2); + + if (unlikely(!p)) + return false; + *ptr = get_unaligned_be64(p); + return true; +} + +static inline bool +xdrgen_encode_hyper(struct xdr_stream *xdr, s64 val) +{ + __be32 *p = xdr_reserve_space(xdr, XDR_UNIT * 2); + + if (unlikely(!p)) + return false; + put_unaligned_be64(val, p); + return true; +} + +static inline bool +xdrgen_decode_unsigned_hyper(struct xdr_stream *xdr, u64 *ptr) +{ + __be32 *p = xdr_inline_decode(xdr, XDR_UNIT * 2); + + if (unlikely(!p)) + return false; + *ptr = get_unaligned_be64(p); + return true; +} + +static inline bool +xdrgen_encode_unsigned_hyper(struct xdr_stream *xdr, u64 val) +{ + __be32 *p = xdr_reserve_space(xdr, XDR_UNIT * 2); + + if (unlikely(!p)) + return false; + put_unaligned_be64(val, p); + return true; +} + +static inline bool +xdrgen_decode_string(struct xdr_stream *xdr, string *ptr, u32 maxlen) +{ + __be32 *p; + u32 len; + + if (unlikely(xdr_stream_decode_u32(xdr, &len) < 0)) + return false; + if (unlikely(maxlen && len > maxlen)) + return false; + if (len != 0) { + p = xdr_inline_decode(xdr, len); + if (unlikely(!p)) + return false; + ptr->data = (unsigned char *)p; + } + ptr->len = len; + return true; +} + +static inline bool +xdrgen_encode_string(struct xdr_stream *xdr, string val, u32 maxlen) +{ + __be32 *p = xdr_reserve_space(xdr, XDR_UNIT + xdr_align_size(val.len)); + + if (unlikely(!p)) + return false; + xdr_encode_opaque(p, val.data, val.len); + return true; +} + +static inline bool +xdrgen_decode_opaque(struct xdr_stream *xdr, opaque *ptr, u32 maxlen) +{ + __be32 *p; + u32 len; + + if (unlikely(xdr_stream_decode_u32(xdr, &len) < 0)) + return false; + if (unlikely(maxlen && len > maxlen)) + return false; + if (len != 0) { + p = xdr_inline_decode(xdr, len); + if (unlikely(!p)) + return false; + ptr->data = (u8 *)p; + } + ptr->len = len; + return true; +} + +static inline bool +xdrgen_encode_opaque(struct xdr_stream *xdr, opaque val) +{ + __be32 *p = xdr_reserve_space(xdr, XDR_UNIT + xdr_align_size(val.len)); + + if (unlikely(!p)) + return false; + xdr_encode_opaque(p, val.data, val.len); + return true; +} + +#endif /* _SUNRPC_XDRGEN__BUILTINS_H_ */ diff --git a/include/linux/sunrpc/xdrgen/_defs.h b/include/linux/sunrpc/xdrgen/_defs.h new file mode 100644 index 000000000000..20c7270aa64d --- /dev/null +++ b/include/linux/sunrpc/xdrgen/_defs.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2024 Oracle and/or its affiliates. + * + * This header defines XDR data type primitives specified in + * Section 4 of RFC 4506, used by RPC programs implemented + * in the Linux kernel. + */ + +#ifndef _SUNRPC_XDRGEN__DEFS_H_ +#define _SUNRPC_XDRGEN__DEFS_H_ + +#define TRUE (true) +#define FALSE (false) + +typedef struct { + u32 len; + unsigned char *data; +} string; + +typedef struct { + u32 len; + u8 *data; +} opaque; + +#define XDR_void (0) +#define XDR_bool (1) +#define XDR_int (1) +#define XDR_unsigned_int (1) +#define XDR_long (1) +#define XDR_unsigned_long (1) +#define XDR_hyper (2) +#define XDR_unsigned_hyper (2) + +#endif /* _SUNRPC_XDRGEN__DEFS_H_ */ diff --git a/include/linux/sunrpc/xdrgen/nfs4_1.h b/include/linux/sunrpc/xdrgen/nfs4_1.h new file mode 100644 index 000000000000..cf21a14aa885 --- /dev/null +++ b/include/linux/sunrpc/xdrgen/nfs4_1.h @@ -0,0 +1,153 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Generated by xdrgen. Manual edits will be lost. */ +/* XDR specification file: ../../Documentation/sunrpc/xdr/nfs4_1.x */ +/* XDR specification modification time: Mon Oct 14 09:10:13 2024 */ + +#ifndef _LINUX_XDRGEN_NFS4_1_DEF_H +#define _LINUX_XDRGEN_NFS4_1_DEF_H + +#include <linux/types.h> +#include <linux/sunrpc/xdrgen/_defs.h> + +typedef s64 int64_t; + +typedef u32 uint32_t; + +typedef struct { + u32 count; + uint32_t *element; +} bitmap4; + +struct nfstime4 { + int64_t seconds; + uint32_t nseconds; +}; + +typedef bool fattr4_offline; + +enum { FATTR4_OFFLINE = 83 }; + +struct open_arguments4 { + bitmap4 oa_share_access; + bitmap4 oa_share_deny; + bitmap4 oa_share_access_want; + bitmap4 oa_open_claim; + bitmap4 oa_create_mode; +}; + +enum open_args_share_access4 { + OPEN_ARGS_SHARE_ACCESS_READ = 1, + OPEN_ARGS_SHARE_ACCESS_WRITE = 2, + OPEN_ARGS_SHARE_ACCESS_BOTH = 3, +}; +typedef enum open_args_share_access4 open_args_share_access4; + +enum open_args_share_deny4 { + OPEN_ARGS_SHARE_DENY_NONE = 0, + OPEN_ARGS_SHARE_DENY_READ = 1, + OPEN_ARGS_SHARE_DENY_WRITE = 2, + OPEN_ARGS_SHARE_DENY_BOTH = 3, +}; +typedef enum open_args_share_deny4 open_args_share_deny4; + +enum open_args_share_access_want4 { + OPEN_ARGS_SHARE_ACCESS_WANT_ANY_DELEG = 3, + OPEN_ARGS_SHARE_ACCESS_WANT_NO_DELEG = 4, + OPEN_ARGS_SHARE_ACCESS_WANT_CANCEL = 5, + OPEN_ARGS_SHARE_ACCESS_WANT_SIGNAL_DELEG_WHEN_RESRC_AVAIL = 17, + OPEN_ARGS_SHARE_ACCESS_WANT_PUSH_DELEG_WHEN_UNCONTENDED = 18, + OPEN_ARGS_SHARE_ACCESS_WANT_DELEG_TIMESTAMPS = 20, + OPEN_ARGS_SHARE_ACCESS_WANT_OPEN_XOR_DELEGATION = 21, +}; +typedef enum open_args_share_access_want4 open_args_share_access_want4; + +enum open_args_open_claim4 { + OPEN_ARGS_OPEN_CLAIM_NULL = 0, + OPEN_ARGS_OPEN_CLAIM_PREVIOUS = 1, + OPEN_ARGS_OPEN_CLAIM_DELEGATE_CUR = 2, + OPEN_ARGS_OPEN_CLAIM_DELEGATE_PREV = 3, + OPEN_ARGS_OPEN_CLAIM_FH = 4, + OPEN_ARGS_OPEN_CLAIM_DELEG_CUR_FH = 5, + OPEN_ARGS_OPEN_CLAIM_DELEG_PREV_FH = 6, +}; +typedef enum open_args_open_claim4 open_args_open_claim4; + +enum open_args_createmode4 { + OPEN_ARGS_CREATEMODE_UNCHECKED4 = 0, + OPEN_ARGS_CREATE_MODE_GUARDED = 1, + OPEN_ARGS_CREATEMODE_EXCLUSIVE4 = 2, + OPEN_ARGS_CREATE_MODE_EXCLUSIVE4_1 = 3, +}; +typedef enum open_args_createmode4 open_args_createmode4; + +typedef struct open_arguments4 fattr4_open_arguments; + +enum { FATTR4_OPEN_ARGUMENTS = 86 }; + +enum { OPEN4_RESULT_NO_OPEN_STATEID = 0x00000010 }; + +typedef struct nfstime4 fattr4_time_deleg_access; + +typedef struct nfstime4 fattr4_time_deleg_modify; + +enum { FATTR4_TIME_DELEG_ACCESS = 84 }; + +enum { FATTR4_TIME_DELEG_MODIFY = 85 }; + +enum { OPEN4_SHARE_ACCESS_WANT_DELEG_MASK = 0xFF00 }; + +enum { OPEN4_SHARE_ACCESS_WANT_NO_PREFERENCE = 0x0000 }; + +enum { OPEN4_SHARE_ACCESS_WANT_READ_DELEG = 0x0100 }; + +enum { OPEN4_SHARE_ACCESS_WANT_WRITE_DELEG = 0x0200 }; + +enum { OPEN4_SHARE_ACCESS_WANT_ANY_DELEG = 0x0300 }; + +enum { OPEN4_SHARE_ACCESS_WANT_NO_DELEG = 0x0400 }; + +enum { OPEN4_SHARE_ACCESS_WANT_CANCEL = 0x0500 }; + +enum { OPEN4_SHARE_ACCESS_WANT_SIGNAL_DELEG_WHEN_RESRC_AVAIL = 0x10000 }; + +enum { OPEN4_SHARE_ACCESS_WANT_PUSH_DELEG_WHEN_UNCONTENDED = 0x20000 }; + +enum { OPEN4_SHARE_ACCESS_WANT_DELEG_TIMESTAMPS = 0x100000 }; + +enum { OPEN4_SHARE_ACCESS_WANT_OPEN_XOR_DELEGATION = 0x200000 }; + +enum open_delegation_type4 { + OPEN_DELEGATE_NONE = 0, + OPEN_DELEGATE_READ = 1, + OPEN_DELEGATE_WRITE = 2, + OPEN_DELEGATE_NONE_EXT = 3, + OPEN_DELEGATE_READ_ATTRS_DELEG = 4, + OPEN_DELEGATE_WRITE_ATTRS_DELEG = 5, +}; +typedef enum open_delegation_type4 open_delegation_type4; + +#define NFS4_int64_t_sz \ + (XDR_hyper) +#define NFS4_uint32_t_sz \ + (XDR_unsigned_int) +#define NFS4_bitmap4_sz (XDR_unsigned_int) +#define NFS4_nfstime4_sz \ + (NFS4_int64_t_sz + NFS4_uint32_t_sz) +#define NFS4_fattr4_offline_sz \ + (XDR_bool) +#define NFS4_open_arguments4_sz \ + (NFS4_bitmap4_sz + NFS4_bitmap4_sz + NFS4_bitmap4_sz + NFS4_bitmap4_sz + NFS4_bitmap4_sz) +#define NFS4_open_args_share_access4_sz (XDR_int) +#define NFS4_open_args_share_deny4_sz (XDR_int) +#define NFS4_open_args_share_access_want4_sz (XDR_int) +#define NFS4_open_args_open_claim4_sz (XDR_int) +#define NFS4_open_args_createmode4_sz (XDR_int) +#define NFS4_fattr4_open_arguments_sz \ + (NFS4_open_arguments4_sz) +#define NFS4_fattr4_time_deleg_access_sz \ + (NFS4_nfstime4_sz) +#define NFS4_fattr4_time_deleg_modify_sz \ + (NFS4_nfstime4_sz) +#define NFS4_open_delegation_type4_sz (XDR_int) + +#endif /* _LINUX_XDRGEN_NFS4_1_DEF_H */ diff --git a/include/linux/sunrpc/xprtmultipath.h b/include/linux/sunrpc/xprtmultipath.h index c0514c684b2c..e411368cdacf 100644 --- a/include/linux/sunrpc/xprtmultipath.h +++ b/include/linux/sunrpc/xprtmultipath.h @@ -75,7 +75,6 @@ extern struct rpc_xprt_switch *xprt_iter_xchg_switch( struct rpc_xprt_switch *newswitch); extern struct rpc_xprt *xprt_iter_xprt(struct rpc_xprt_iter *xpi); -extern struct rpc_xprt *xprt_iter_get_xprt(struct rpc_xprt_iter *xpi); extern struct rpc_xprt *xprt_iter_get_next(struct rpc_xprt_iter *xpi); extern bool rpc_xprt_switch_has_addr(struct rpc_xprt_switch *xps, diff --git a/include/linux/swap.h b/include/linux/swap.h index f53d608daa01..b13b72645db3 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -219,10 +219,10 @@ enum { SWP_STABLE_WRITES = (1 << 11), /* no overwrite PG_writeback pages */ SWP_SYNCHRONOUS_IO = (1 << 12), /* synchronous IO is efficient */ /* add others here before... */ - SWP_SCANNING = (1 << 14), /* refcount in scan_swap_map */ }; #define SWAP_CLUSTER_MAX 32UL +#define SWAP_CLUSTER_MAX_SKIPPED (SWAP_CLUSTER_MAX << 10) #define COMPACT_CLUSTER_MAX SWAP_CLUSTER_MAX /* Bit flag in swap_map */ @@ -243,23 +243,47 @@ enum { * free clusters are organized into a list. We fetch an entry from the list to * get a free cluster. * - * The data field stores next cluster if the cluster is free or cluster usage - * counter otherwise. The flags field determines if a cluster is free. This is - * protected by swap_info_struct.lock. + * The flags field determines if a cluster is free. This is + * protected by cluster lock. */ struct swap_cluster_info { spinlock_t lock; /* * Protect swap_cluster_info fields - * and swap_info_struct->swap_map - * elements correspond to the swap - * cluster + * other than list, and swap_info_struct->swap_map + * elements corresponding to the swap cluster. */ - unsigned int data:24; - unsigned int flags:8; + u16 count; + u8 flags; + u8 order; + struct list_head list; }; -#define CLUSTER_FLAG_FREE 1 /* This cluster is free */ -#define CLUSTER_FLAG_NEXT_NULL 2 /* This cluster has no next cluster */ -#define CLUSTER_FLAG_HUGE 4 /* This cluster is backing a transparent huge page */ + +/* All on-list cluster must have a non-zero flag. */ +enum swap_cluster_flags { + CLUSTER_FLAG_NONE = 0, /* For temporary off-list cluster */ + CLUSTER_FLAG_FREE, + CLUSTER_FLAG_NONFULL, + CLUSTER_FLAG_FRAG, + /* Clusters with flags above are allocatable */ + CLUSTER_FLAG_USABLE = CLUSTER_FLAG_FRAG, + CLUSTER_FLAG_FULL, + CLUSTER_FLAG_DISCARD, + CLUSTER_FLAG_MAX, +}; + +/* + * The first page in the swap file is the swap header, which is always marked + * bad to prevent it from being allocated as an entry. This also prevents the + * cluster to which it belongs being marked free. Therefore 0 is safe to use as + * a sentinel to indicate an entry is not valid. + */ +#define SWAP_ENTRY_INVALID 0 + +#ifdef CONFIG_THP_SWAP +#define SWAP_NR_ORDERS (PMD_ORDER + 1) +#else +#define SWAP_NR_ORDERS 1 +#endif /* * We assign a cluster to each CPU, so each CPU can allocate swap entry from @@ -267,13 +291,8 @@ struct swap_cluster_info { * throughput. */ struct percpu_cluster { - struct swap_cluster_info index; /* Current cluster index */ - unsigned int next; /* Likely next allocation offset */ -}; - -struct swap_cluster_list { - struct swap_cluster_info head; - struct swap_cluster_info tail; + local_lock_t lock; /* Protect the percpu_cluster above */ + unsigned int next[SWAP_NR_ORDERS]; /* Likely next allocation offset */ }; /* @@ -287,21 +306,23 @@ struct swap_info_struct { signed char type; /* strange name for an index */ unsigned int max; /* extent of the swap_map */ unsigned char *swap_map; /* vmalloc'ed array of usage counts */ + unsigned long *zeromap; /* kvmalloc'ed bitmap to track zero pages */ struct swap_cluster_info *cluster_info; /* cluster info. Only for SSD */ - struct swap_cluster_list free_clusters; /* free clusters list */ - unsigned int lowest_bit; /* index of first free in swap_map */ - unsigned int highest_bit; /* index of last free in swap_map */ + struct list_head free_clusters; /* free clusters list */ + struct list_head full_clusters; /* full clusters list */ + struct list_head nonfull_clusters[SWAP_NR_ORDERS]; + /* list of cluster that contains at least one free slot */ + struct list_head frag_clusters[SWAP_NR_ORDERS]; + /* list of cluster that are fragmented or contented */ + atomic_long_t frag_cluster_nr[SWAP_NR_ORDERS]; unsigned int pages; /* total of usable pages of swap */ - unsigned int inuse_pages; /* number of those currently in use */ - unsigned int cluster_next; /* likely index for next allocation */ - unsigned int cluster_nr; /* countdown to next cluster search */ - unsigned int __percpu *cluster_next_cpu; /*percpu index for next allocation */ + atomic_long_t inuse_pages; /* number of those currently in use */ struct percpu_cluster __percpu *percpu_cluster; /* per cpu's swap location */ + struct percpu_cluster *global_cluster; /* Use one global cluster for rotating device */ + spinlock_t global_cluster_lock; /* Serialize usage of global cluster */ struct rb_root swap_extent_root;/* root of the swap extent rbtree */ - struct file *bdev_file; /* open handle of the bdev */ struct block_device *bdev; /* swap device or bdev of swap file */ struct file *swap_file; /* seldom referenced */ - unsigned int old_block_size; /* seldom referenced */ struct completion comp; /* seldom referenced */ spinlock_t lock; /* * protect map scan related fields like @@ -321,7 +342,8 @@ struct swap_info_struct { * list. */ struct work_struct discard_work; /* discard worker */ - struct swap_cluster_list discard_clusters; /* discard clusters list */ + struct work_struct reclaim_work; /* reclaim worker */ + struct list_head discard_clusters; /* discard clusters list */ struct plist_node avail_lists[]; /* * entries in swap_avail_heads, one * entry per node. @@ -344,7 +366,8 @@ static inline swp_entry_t page_swap_entry(struct page *page) } /* linux/mm/workingset.c */ -bool workingset_test_recent(void *shadow, bool file, bool *workingset); +bool workingset_test_recent(void *shadow, bool file, bool *workingset, + bool flush); void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages); void *workingset_eviction(struct folio *folio, struct mem_cgroup *target_memcg); void workingset_refault(struct folio *folio, void *shadow); @@ -394,10 +417,13 @@ extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, #define MEMCG_RECLAIM_MAY_SWAP (1 << 1) #define MEMCG_RECLAIM_PROACTIVE (1 << 2) +#define MIN_SWAPPINESS 0 +#define MAX_SWAPPINESS 200 extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, - unsigned int reclaim_options); + unsigned int reclaim_options, + int *swappiness); extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem, gfp_t gfp_mask, bool noswap, pg_data_t *pgdat, @@ -462,14 +488,14 @@ swp_entry_t folio_alloc_swap(struct folio *folio); bool folio_free_swap(struct folio *folio); void put_swap_folio(struct folio *folio, swp_entry_t entry); extern swp_entry_t get_swap_page_of_type(int); -extern int get_swap_pages(int n, swp_entry_t swp_entries[], int entry_size); +extern int get_swap_pages(int n, swp_entry_t swp_entries[], int order); extern int add_swap_count_continuation(swp_entry_t, gfp_t); -extern void swap_shmem_alloc(swp_entry_t); +extern void swap_shmem_alloc(swp_entry_t, int); extern int swap_duplicate(swp_entry_t); -extern int swapcache_prepare(swp_entry_t); -extern void swap_free(swp_entry_t); +extern int swapcache_prepare(swp_entry_t entry, int nr); +extern void swap_free_nr(swp_entry_t entry, int nr_pages); extern void swapcache_free_entries(swp_entry_t *entries, int n); -extern int free_swap_and_cache(swp_entry_t); +extern void free_swap_and_cache_nr(swp_entry_t entry, int nr); int swap_type_of(dev_t device, sector_t offset); int find_first_swap(dev_t *device); extern unsigned int count_swap_pages(int, int); @@ -518,8 +544,9 @@ static inline void put_swap_device(struct swap_info_struct *si) #define free_pages_and_swap_cache(pages, nr) \ release_pages((pages), (nr)); -/* used to sanity check ptes in zap_pte_range when CONFIG_SWAP=0 */ -#define free_swap_and_cache(e) is_pfn_swap_entry(e) +static inline void free_swap_and_cache_nr(swp_entry_t entry, int nr) +{ +} static inline void free_swap_cache(struct folio *folio) { @@ -530,7 +557,7 @@ static inline int add_swap_count_continuation(swp_entry_t swp, gfp_t gfp_mask) return 0; } -static inline void swap_shmem_alloc(swp_entry_t swp) +static inline void swap_shmem_alloc(swp_entry_t swp, int nr) { } @@ -539,12 +566,12 @@ static inline int swap_duplicate(swp_entry_t swp) return 0; } -static inline int swapcache_prepare(swp_entry_t swp) +static inline int swapcache_prepare(swp_entry_t swp, int nr) { return 0; } -static inline void swap_free(swp_entry_t swp) +static inline void swap_free_nr(swp_entry_t entry, int nr_pages) { } @@ -587,14 +614,15 @@ static inline int add_swap_extent(struct swap_info_struct *sis, } #endif /* CONFIG_SWAP */ -#ifdef CONFIG_THP_SWAP -extern int split_swap_cluster(swp_entry_t entry); -#else -static inline int split_swap_cluster(swp_entry_t entry) +static inline void free_swap_and_cache(swp_entry_t entry) { - return 0; + free_swap_and_cache_nr(entry, 1); +} + +static inline void swap_free(swp_entry_t entry) +{ + swap_free_nr(entry, 1); } -#endif #ifdef CONFIG_MEMCG static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg) diff --git a/include/linux/swap_cgroup.h b/include/linux/swap_cgroup.h index ae73a87775b3..b5ec038069da 100644 --- a/include/linux/swap_cgroup.h +++ b/include/linux/swap_cgroup.h @@ -6,10 +6,8 @@ #if defined(CONFIG_MEMCG) && defined(CONFIG_SWAP) -extern unsigned short swap_cgroup_cmpxchg(swp_entry_t ent, - unsigned short old, unsigned short new); -extern unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id, - unsigned int nr_ents); +extern void swap_cgroup_record(struct folio *folio, swp_entry_t ent); +extern unsigned short swap_cgroup_clear(swp_entry_t ent, unsigned int nr_ents); extern unsigned short lookup_swap_cgroup_id(swp_entry_t ent); extern int swap_cgroup_swapon(int type, unsigned long max_pages); extern void swap_cgroup_swapoff(int type); @@ -17,8 +15,12 @@ extern void swap_cgroup_swapoff(int type); #else static inline -unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id, - unsigned int nr_ents) +void swap_cgroup_record(struct folio *folio, swp_entry_t ent) +{ +} + +static inline +unsigned short swap_cgroup_clear(swp_entry_t ent, unsigned int nr_ents) { return 0; } diff --git a/include/linux/swap_slots.h b/include/linux/swap_slots.h index 15adfb8c813a..840aec3523b2 100644 --- a/include/linux/swap_slots.h +++ b/include/linux/swap_slots.h @@ -16,15 +16,12 @@ struct swap_slots_cache { swp_entry_t *slots; int nr; int cur; - spinlock_t free_lock; /* protects slots_ret, n_ret */ - swp_entry_t *slots_ret; int n_ret; }; void disable_swap_slots_cache_lock(void); void reenable_swap_slots_cache_unlock(void); void enable_swap_slots_cache(void); -void free_swap_slot(swp_entry_t entry); extern bool swap_slot_cache_enabled; diff --git a/include/linux/swapops.h b/include/linux/swapops.h index a5c560a2f8c2..96f26e29fefe 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -334,7 +334,7 @@ static inline bool is_migration_entry_dirty(swp_entry_t entry) extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address); -extern void migration_entry_wait_huge(struct vm_area_struct *vma, pte_t *pte); +extern void migration_entry_wait_huge(struct vm_area_struct *vma, unsigned long addr, pte_t *pte); #else /* CONFIG_MIGRATION */ static inline swp_entry_t make_readable_migration_entry(pgoff_t offset) { @@ -359,7 +359,7 @@ static inline int is_migration_entry(swp_entry_t swp) static inline void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address) { } static inline void migration_entry_wait_huge(struct vm_area_struct *vma, - pte_t *pte) { } + unsigned long addr, pte_t *pte) { } static inline int is_writable_migration_entry(swp_entry_t entry) { return 0; @@ -426,9 +426,19 @@ typedef unsigned long pte_marker; * "Poisoned" here is meant in the very general sense of "future accesses are * invalid", instead of referring very specifically to hardware memory errors. * This marker is meant to represent any of various different causes of this. + * + * Note that, when encountered by the faulting logic, PTEs with this marker will + * result in VM_FAULT_HWPOISON and thus regardless trigger hardware memory error + * logic. */ #define PTE_MARKER_POISONED BIT(1) -#define PTE_MARKER_MASK (BIT(2) - 1) +/* + * Indicates that, on fault, this PTE will case a SIGSEGV signal to be + * sent. This means guard markers behave in effect as if the region were mapped + * PROT_NONE, rather than if they were a memory hole or equivalent. + */ +#define PTE_MARKER_GUARD BIT(2) +#define PTE_MARKER_MASK (BIT(3) - 1) static inline swp_entry_t make_pte_marker_entry(pte_marker marker) { @@ -464,6 +474,18 @@ static inline int is_poisoned_swp_entry(swp_entry_t entry) { return is_pte_marker_entry(entry) && (pte_marker_get(entry) & PTE_MARKER_POISONED); + +} + +static inline swp_entry_t make_guard_swp_entry(void) +{ + return make_pte_marker_entry(PTE_MARKER_GUARD); +} + +static inline int is_guard_swp_entry(swp_entry_t entry) +{ + return is_pte_marker_entry(entry) && + (pte_marker_get(entry) & PTE_MARKER_GUARD); } /* diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index ea23097e351f..3dae0f592063 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -42,24 +42,6 @@ int swiotlb_init_late(size_t size, gfp_t gfp_mask, int (*remap)(void *tlb, unsigned long nslabs)); extern void __init swiotlb_update_mem_attributes(void); -phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t phys, - size_t mapping_size, size_t alloc_size, - unsigned int alloc_aligned_mask, enum dma_data_direction dir, - unsigned long attrs); - -extern void swiotlb_tbl_unmap_single(struct device *hwdev, - phys_addr_t tlb_addr, - size_t mapping_size, - enum dma_data_direction dir, - unsigned long attrs); - -void swiotlb_sync_single_for_device(struct device *dev, phys_addr_t tlb_addr, - size_t size, enum dma_data_direction dir); -void swiotlb_sync_single_for_cpu(struct device *dev, phys_addr_t tlb_addr, - size_t size, enum dma_data_direction dir); -dma_addr_t swiotlb_map(struct device *dev, phys_addr_t phys, - size_t size, enum dma_data_direction dir, unsigned long attrs); - #ifdef CONFIG_SWIOTLB /** @@ -143,37 +125,27 @@ struct io_tlb_mem { #endif }; -#ifdef CONFIG_SWIOTLB_DYNAMIC - -struct io_tlb_pool *swiotlb_find_pool(struct device *dev, phys_addr_t paddr); - -#else - -static inline struct io_tlb_pool *swiotlb_find_pool(struct device *dev, - phys_addr_t paddr) -{ - return &dev->dma_io_tlb_mem->defpool; -} - -#endif +struct io_tlb_pool *__swiotlb_find_pool(struct device *dev, phys_addr_t paddr); /** - * is_swiotlb_buffer() - check if a physical address belongs to a swiotlb + * swiotlb_find_pool() - find swiotlb pool to which a physical address belongs * @dev: Device which has mapped the buffer. * @paddr: Physical address within the DMA buffer. * - * Check if @paddr points into a bounce buffer. + * Find the swiotlb pool that @paddr points into. * * Return: - * * %true if @paddr points into a bounce buffer - * * %false otherwise + * * pool address if @paddr points into a bounce buffer + * * NULL if @paddr does not point into a bounce buffer. As such, this function + * can be used to determine if @paddr denotes a swiotlb bounce buffer. */ -static inline bool is_swiotlb_buffer(struct device *dev, phys_addr_t paddr) +static inline struct io_tlb_pool *swiotlb_find_pool(struct device *dev, + phys_addr_t paddr) { struct io_tlb_mem *mem = dev->dma_io_tlb_mem; if (!mem) - return false; + return NULL; #ifdef CONFIG_SWIOTLB_DYNAMIC /* @@ -182,16 +154,19 @@ static inline bool is_swiotlb_buffer(struct device *dev, phys_addr_t paddr) * If a SWIOTLB address is checked on another CPU, then it was * presumably loaded by the device driver from an unspecified private * data structure. Make sure that this load is ordered before reading - * dev->dma_uses_io_tlb here and mem->pools in swiotlb_find_pool(). + * dev->dma_uses_io_tlb here and mem->pools in __swiotlb_find_pool(). * * This barrier pairs with smp_mb() in swiotlb_find_slots(). */ smp_rmb(); - return READ_ONCE(dev->dma_uses_io_tlb) && - swiotlb_find_pool(dev, paddr); + if (READ_ONCE(dev->dma_uses_io_tlb)) + return __swiotlb_find_pool(dev, paddr); #else - return paddr >= mem->defpool.start && paddr < mem->defpool.end; + if (paddr >= mem->defpool.start && paddr < mem->defpool.end) + return &mem->defpool; #endif + + return NULL; } static inline bool is_swiotlb_force_bounce(struct device *dev) @@ -219,9 +194,10 @@ static inline void swiotlb_dev_init(struct device *dev) { } -static inline bool is_swiotlb_buffer(struct device *dev, phys_addr_t paddr) +static inline struct io_tlb_pool *swiotlb_find_pool(struct device *dev, + phys_addr_t paddr) { - return false; + return NULL; } static inline bool is_swiotlb_force_bounce(struct device *dev) { @@ -260,6 +236,49 @@ static inline phys_addr_t default_swiotlb_limit(void) } #endif /* CONFIG_SWIOTLB */ +phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t phys, + size_t mapping_size, unsigned int alloc_aligned_mask, + enum dma_data_direction dir, unsigned long attrs); +dma_addr_t swiotlb_map(struct device *dev, phys_addr_t phys, + size_t size, enum dma_data_direction dir, unsigned long attrs); + +void __swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr, + size_t mapping_size, enum dma_data_direction dir, + unsigned long attrs, struct io_tlb_pool *pool); +static inline void swiotlb_tbl_unmap_single(struct device *dev, + phys_addr_t addr, size_t size, enum dma_data_direction dir, + unsigned long attrs) +{ + struct io_tlb_pool *pool = swiotlb_find_pool(dev, addr); + + if (unlikely(pool)) + __swiotlb_tbl_unmap_single(dev, addr, size, dir, attrs, pool); +} + +void __swiotlb_sync_single_for_device(struct device *dev, phys_addr_t tlb_addr, + size_t size, enum dma_data_direction dir, + struct io_tlb_pool *pool); +static inline void swiotlb_sync_single_for_device(struct device *dev, + phys_addr_t addr, size_t size, enum dma_data_direction dir) +{ + struct io_tlb_pool *pool = swiotlb_find_pool(dev, addr); + + if (unlikely(pool)) + __swiotlb_sync_single_for_device(dev, addr, size, dir, pool); +} + +void __swiotlb_sync_single_for_cpu(struct device *dev, phys_addr_t tlb_addr, + size_t size, enum dma_data_direction dir, + struct io_tlb_pool *pool); +static inline void swiotlb_sync_single_for_cpu(struct device *dev, + phys_addr_t addr, size_t size, enum dma_data_direction dir) +{ + struct io_tlb_pool *pool = swiotlb_find_pool(dev, addr); + + if (unlikely(pool)) + __swiotlb_sync_single_for_cpu(dev, addr, size, dir, pool); +} + extern void swiotlb_print_info(void); #ifdef CONFIG_DMA_RESTRICTED_POOL diff --git a/include/linux/switchtec.h b/include/linux/switchtec.h index 8d8fac1626bd..cdb58d61c152 100644 --- a/include/linux/switchtec.h +++ b/include/linux/switchtec.h @@ -521,6 +521,6 @@ static inline struct switchtec_dev *to_stdev(struct device *dev) return container_of(dev, struct switchtec_dev, dev); } -extern struct class *switchtec_class; +extern const struct class switchtec_class; #endif diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index e619ac10cd23..c6333204d451 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -77,6 +77,7 @@ struct cachestat_range; struct cachestat; struct statmount; struct mnt_id_req; +struct xattr_args; #include <linux/types.h> #include <linux/aio_abi.h> @@ -322,13 +323,13 @@ asmlinkage long sys_io_pgetevents(aio_context_t ctx_id, long nr, struct io_event __user *events, struct __kernel_timespec __user *timeout, - const struct __aio_sigset *sig); + const struct __aio_sigset __user *sig); asmlinkage long sys_io_pgetevents_time32(aio_context_t ctx_id, long min_nr, long nr, struct io_event __user *events, struct old_timespec32 __user *timeout, - const struct __aio_sigset *sig); + const struct __aio_sigset __user *sig); asmlinkage long sys_io_uring_setup(u32 entries, struct io_uring_params __user *p); asmlinkage long sys_io_uring_enter(unsigned int fd, u32 to_submit, @@ -338,23 +339,35 @@ asmlinkage long sys_io_uring_register(unsigned int fd, unsigned int op, void __user *arg, unsigned int nr_args); asmlinkage long sys_setxattr(const char __user *path, const char __user *name, const void __user *value, size_t size, int flags); +asmlinkage long sys_setxattrat(int dfd, const char __user *path, unsigned int at_flags, + const char __user *name, + const struct xattr_args __user *args, size_t size); asmlinkage long sys_lsetxattr(const char __user *path, const char __user *name, const void __user *value, size_t size, int flags); asmlinkage long sys_fsetxattr(int fd, const char __user *name, const void __user *value, size_t size, int flags); asmlinkage long sys_getxattr(const char __user *path, const char __user *name, void __user *value, size_t size); +asmlinkage long sys_getxattrat(int dfd, const char __user *path, unsigned int at_flags, + const char __user *name, + struct xattr_args __user *args, size_t size); asmlinkage long sys_lgetxattr(const char __user *path, const char __user *name, void __user *value, size_t size); asmlinkage long sys_fgetxattr(int fd, const char __user *name, void __user *value, size_t size); asmlinkage long sys_listxattr(const char __user *path, char __user *list, size_t size); +asmlinkage long sys_listxattrat(int dfd, const char __user *path, + unsigned int at_flags, + char __user *list, size_t size); asmlinkage long sys_llistxattr(const char __user *path, char __user *list, size_t size); asmlinkage long sys_flistxattr(int fd, char __user *list, size_t size); asmlinkage long sys_removexattr(const char __user *path, const char __user *name); +asmlinkage long sys_removexattrat(int dfd, const char __user *path, + unsigned int at_flags, + const char __user *name); asmlinkage long sys_lremovexattr(const char __user *path, const char __user *name); asmlinkage long sys_fremovexattr(int fd, const char __user *name); @@ -418,7 +431,7 @@ asmlinkage long sys_listmount(const struct mnt_id_req __user *req, u64 __user *mnt_ids, size_t nr_mnt_ids, unsigned int flags); asmlinkage long sys_truncate(const char __user *path, long length); -asmlinkage long sys_ftruncate(unsigned int fd, unsigned long length); +asmlinkage long sys_ftruncate(unsigned int fd, off_t length); #if BITS_PER_LONG == 32 asmlinkage long sys_truncate64(const char __user *path, loff_t length); asmlinkage long sys_ftruncate64(unsigned int fd, loff_t length); @@ -441,7 +454,7 @@ asmlinkage long sys_fchown(unsigned int fd, uid_t user, gid_t group); asmlinkage long sys_openat(int dfd, const char __user *filename, int flags, umode_t mode); asmlinkage long sys_openat2(int dfd, const char __user *filename, - struct open_how *how, size_t size); + struct open_how __user *how, size_t size); asmlinkage long sys_close(unsigned int fd); asmlinkage long sys_close_range(unsigned int fd, unsigned int max_fd, unsigned int flags); @@ -555,7 +568,7 @@ asmlinkage long sys_get_robust_list(int pid, asmlinkage long sys_set_robust_list(struct robust_list_head __user *head, size_t len); -asmlinkage long sys_futex_waitv(struct futex_waitv *waiters, +asmlinkage long sys_futex_waitv(struct futex_waitv __user *waiters, unsigned int nr_futexes, unsigned int flags, struct __kernel_timespec __user *timeout, clockid_t clockid); @@ -821,6 +834,7 @@ asmlinkage long sys_process_mrelease(int pidfd, unsigned int flags); asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size, unsigned long prot, unsigned long pgoff, unsigned long flags); +asmlinkage long sys_mseal(unsigned long start, size_t len, unsigned long flags); asmlinkage long sys_mbind(unsigned long start, unsigned long len, unsigned long mode, const unsigned long __user *nmask, @@ -858,12 +872,18 @@ asmlinkage long sys_prlimit64(pid_t pid, unsigned int resource, const struct rlimit64 __user *new_rlim, struct rlimit64 __user *old_rlim); asmlinkage long sys_fanotify_init(unsigned int flags, unsigned int event_f_flags); +#if defined(CONFIG_ARCH_SPLIT_ARG64) +asmlinkage long sys_fanotify_mark(int fanotify_fd, unsigned int flags, + unsigned int mask_1, unsigned int mask_2, + int dfd, const char __user * pathname); +#else asmlinkage long sys_fanotify_mark(int fanotify_fd, unsigned int flags, u64 mask, int fd, const char __user *pathname); +#endif asmlinkage long sys_name_to_handle_at(int dfd, const char __user *name, struct file_handle __user *handle, - int __user *mnt_id, int flag); + void __user *mnt_id, int flag); asmlinkage long sys_open_by_handle_at(int mountdirfd, struct file_handle __user *handle, int flags); @@ -906,7 +926,7 @@ asmlinkage long sys_seccomp(unsigned int op, unsigned int flags, asmlinkage long sys_getrandom(char __user *buf, size_t count, unsigned int flags); asmlinkage long sys_memfd_create(const char __user *uname_ptr, unsigned int flags); -asmlinkage long sys_bpf(int cmd, union bpf_attr *attr, unsigned int size); +asmlinkage long sys_bpf(int cmd, union bpf_attr __user *attr, unsigned int size); asmlinkage long sys_execveat(int dfd, const char __user *filename, const char __user *const __user *argv, const char __user *const __user *envp, int flags); @@ -959,11 +979,11 @@ asmlinkage long sys_cachestat(unsigned int fd, struct cachestat_range __user *cstat_range, struct cachestat __user *cstat, unsigned int flags); asmlinkage long sys_map_shadow_stack(unsigned long addr, unsigned long size, unsigned int flags); -asmlinkage long sys_lsm_get_self_attr(unsigned int attr, struct lsm_ctx *ctx, - u32 *size, u32 flags); -asmlinkage long sys_lsm_set_self_attr(unsigned int attr, struct lsm_ctx *ctx, +asmlinkage long sys_lsm_get_self_attr(unsigned int attr, struct lsm_ctx __user *ctx, + u32 __user *size, u32 flags); +asmlinkage long sys_lsm_set_self_attr(unsigned int attr, struct lsm_ctx __user *ctx, u32 size, u32 flags); -asmlinkage long sys_lsm_list_modules(u64 *ids, u32 *size, u32 flags); +asmlinkage long sys_lsm_list_modules(u64 __user *ids, u32 __user *size, u32 flags); /* * Architecture-specific system calls @@ -972,6 +992,8 @@ asmlinkage long sys_lsm_list_modules(u64 *ids, u32 *size, u32 flags); /* x86 */ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int on); +asmlinkage long sys_uretprobe(void); + /* pciconfig: alpha, arm, arm64, ia64, sparc */ asmlinkage long sys_pciconfig_read(unsigned long bus, unsigned long dfn, unsigned long off, unsigned long len, diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index ee7d33b89e9e..40a6ac6c9713 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -61,38 +61,36 @@ extern const int sysctl_vals[]; extern const unsigned long sysctl_long_vals[]; -typedef int proc_handler(struct ctl_table *ctl, int write, void *buffer, +typedef int proc_handler(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); -int proc_dostring(struct ctl_table *, int, void *, size_t *, loff_t *); -int proc_dobool(struct ctl_table *table, int write, void *buffer, +int proc_dostring(const struct ctl_table *, int, void *, size_t *, loff_t *); +int proc_dobool(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); -int proc_dointvec(struct ctl_table *, int, void *, size_t *, loff_t *); -int proc_douintvec(struct ctl_table *, int, void *, size_t *, loff_t *); -int proc_dointvec_minmax(struct ctl_table *, int, void *, size_t *, loff_t *); -int proc_douintvec_minmax(struct ctl_table *table, int write, void *buffer, +int proc_dointvec(const struct ctl_table *, int, void *, size_t *, loff_t *); +int proc_douintvec(const struct ctl_table *, int, void *, size_t *, loff_t *); +int proc_dointvec_minmax(const struct ctl_table *, int, void *, size_t *, loff_t *); +int proc_douintvec_minmax(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); -int proc_dou8vec_minmax(struct ctl_table *table, int write, void *buffer, +int proc_dou8vec_minmax(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); -int proc_dointvec_jiffies(struct ctl_table *, int, void *, size_t *, loff_t *); -int proc_dointvec_ms_jiffies_minmax(struct ctl_table *table, int write, +int proc_dointvec_jiffies(const struct ctl_table *, int, void *, size_t *, loff_t *); +int proc_dointvec_ms_jiffies_minmax(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); -int proc_dointvec_userhz_jiffies(struct ctl_table *, int, void *, size_t *, +int proc_dointvec_userhz_jiffies(const struct ctl_table *, int, void *, size_t *, loff_t *); -int proc_dointvec_ms_jiffies(struct ctl_table *, int, void *, size_t *, +int proc_dointvec_ms_jiffies(const struct ctl_table *, int, void *, size_t *, loff_t *); -int proc_doulongvec_minmax(struct ctl_table *, int, void *, size_t *, loff_t *); -int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int, void *, +int proc_doulongvec_minmax(const struct ctl_table *, int, void *, size_t *, loff_t *); +int proc_doulongvec_ms_jiffies_minmax(const struct ctl_table *table, int, void *, size_t *, loff_t *); -int proc_do_large_bitmap(struct ctl_table *, int, void *, size_t *, loff_t *); -int proc_do_static_key(struct ctl_table *table, int write, void *buffer, +int proc_do_large_bitmap(const struct ctl_table *, int, void *, size_t *, loff_t *); +int proc_do_static_key(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); /* * Register a set of sysctl names by calling register_sysctl - * with an initialised array of struct ctl_table's. An entry with - * NULL procname terminates the table. table->de will be - * set up by the registration and need not be initialised in advance. + * with an initialised array of struct ctl_table's. * * sysctl names can be mirrored automatically under /proc/sys. The * procname supplied controls /proc naming. @@ -133,21 +131,10 @@ static inline void *proc_sys_poll_event(struct ctl_table_poll *poll) /* A sysctl table is an array of struct ctl_table: */ struct ctl_table { - const char *procname; /* Text ID for /proc/sys, or zero */ + const char *procname; /* Text ID for /proc/sys */ void *data; int maxlen; umode_t mode; - /** - * enum type - Enumeration to differentiate between ctl target types - * @SYSCTL_TABLE_TYPE_DEFAULT: ctl target with no special considerations - * @SYSCTL_TABLE_TYPE_PERMANENTLY_EMPTY: Used to identify a permanently - * empty directory target to serve - * as mount point. - */ - enum { - SYSCTL_TABLE_TYPE_DEFAULT, - SYSCTL_TABLE_TYPE_PERMANENTLY_EMPTY - } type; proc_handler *proc_handler; /* Callback for text formatting */ struct ctl_table_poll *poll; void *extra1; @@ -173,7 +160,7 @@ struct ctl_node { struct ctl_table_header { union { struct { - struct ctl_table *ctl_table; + const struct ctl_table *ctl_table; int ctl_table_size; int used; int count; @@ -182,12 +169,23 @@ struct ctl_table_header { struct rcu_head rcu; }; struct completion *unregistering; - struct ctl_table *ctl_table_arg; + const struct ctl_table *ctl_table_arg; struct ctl_table_root *root; struct ctl_table_set *set; struct ctl_dir *parent; struct ctl_node *node; struct hlist_head inodes; /* head for proc_inode->sysctl_inodes */ + /** + * enum type - Enumeration to differentiate between ctl target types + * @SYSCTL_TABLE_TYPE_DEFAULT: ctl target with no special considerations + * @SYSCTL_TABLE_TYPE_PERMANENTLY_EMPTY: Used to identify a permanently + * empty directory target to serve + * as mount point. + */ + enum { + SYSCTL_TABLE_TYPE_DEFAULT, + SYSCTL_TABLE_TYPE_PERMANENTLY_EMPTY, + } type; }; struct ctl_dir { @@ -205,9 +203,8 @@ struct ctl_table_root { struct ctl_table_set default_set; struct ctl_table_set *(*lookup)(struct ctl_table_root *root); void (*set_ownership)(struct ctl_table_header *head, - struct ctl_table *table, kuid_t *uid, kgid_t *gid); - int (*permissions)(struct ctl_table_header *head, struct ctl_table *table); + int (*permissions)(struct ctl_table_header *head, const struct ctl_table *table); }; #define register_sysctl(path, table) \ @@ -224,13 +221,13 @@ extern void retire_sysctl_set(struct ctl_table_set *set); struct ctl_table_header *__register_sysctl_table( struct ctl_table_set *set, - const char *path, struct ctl_table *table, size_t table_size); -struct ctl_table_header *register_sysctl_sz(const char *path, struct ctl_table *table, + const char *path, const struct ctl_table *table, size_t table_size); +struct ctl_table_header *register_sysctl_sz(const char *path, const struct ctl_table *table, size_t table_size); void unregister_sysctl_table(struct ctl_table_header * table); extern int sysctl_init_bases(void); -extern void __register_sysctl_init(const char *path, struct ctl_table *table, +extern void __register_sysctl_init(const char *path, const struct ctl_table *table, const char *table_name, size_t table_size); #define register_sysctl_init(path, table) \ __register_sysctl_init(path, table, #table, ARRAY_SIZE(table)) @@ -238,7 +235,7 @@ extern struct ctl_table_header *register_sysctl_mount_point(const char *path); void do_sysctl_args(void); bool sysctl_is_alias(char *param); -int do_proc_douintvec(struct ctl_table *table, int write, +int do_proc_douintvec(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos, int (*conv)(unsigned long *lvalp, unsigned int *valp, @@ -252,7 +249,7 @@ extern int no_unaligned_warning; #else /* CONFIG_SYSCTL */ -static inline void register_sysctl_init(const char *path, struct ctl_table *table) +static inline void register_sysctl_init(const char *path, const struct ctl_table *table) { } @@ -262,7 +259,7 @@ static inline struct ctl_table_header *register_sysctl_mount_point(const char *p } static inline struct ctl_table_header *register_sysctl_sz(const char *path, - struct ctl_table *table, + const struct ctl_table *table, size_t table_size) { return NULL; @@ -288,7 +285,7 @@ static inline bool sysctl_is_alias(char *param) } #endif /* CONFIG_SYSCTL */ -int sysctl_max_threads(struct ctl_table *table, int write, void *buffer, +int sysctl_max_threads(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); #endif /* _LINUX_SYSCTL_H */ diff --git a/include/linux/sysfb.h b/include/linux/sysfb.h index c9cb657dad08..07cbab516942 100644 --- a/include/linux/sysfb.h +++ b/include/linux/sysfb.h @@ -58,14 +58,21 @@ struct efifb_dmi_info { #ifdef CONFIG_SYSFB -void sysfb_disable(void); +void sysfb_disable(struct device *dev); + +bool sysfb_handles_screen_info(void); #else /* CONFIG_SYSFB */ -static inline void sysfb_disable(void) +static inline void sysfb_disable(struct device *dev) { } +static inline bool sysfb_handles_screen_info(void) +{ + return false; +} + #endif /* CONFIG_SYSFB */ #ifdef CONFIG_EFI diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 326341c62385..18f7e1fd093c 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -87,6 +87,11 @@ do { \ * SYSFS_GROUP_VISIBLE() when assigning this callback to * specify separate _group_visible() and _attr_visible() * handlers. + * @bin_size: + * Optional: Function to return the size of a binary attribute + * of the group. Will be called repeatedly for each binary + * attribute in the group. Overwrites the size field embedded + * inside the attribute itself. * @attrs: Pointer to NULL terminated list of attributes. * @bin_attrs: Pointer to NULL terminated list of binary attributes. * Either attrs or bin_attrs or both must be provided. @@ -96,9 +101,15 @@ struct attribute_group { umode_t (*is_visible)(struct kobject *, struct attribute *, int); umode_t (*is_bin_visible)(struct kobject *, - struct bin_attribute *, int); + const struct bin_attribute *, int); + size_t (*bin_size)(struct kobject *, + const struct bin_attribute *, + int); struct attribute **attrs; - struct bin_attribute **bin_attrs; + union { + struct bin_attribute **bin_attrs; + const struct bin_attribute *const *bin_attrs_new; + }; }; #define SYSFS_PREALLOC 010000 @@ -191,22 +202,22 @@ struct attribute_group { * attributes, the group visibility is determined by the function * specified to is_visible() not is_bin_visible() */ -#define DEFINE_SYSFS_BIN_GROUP_VISIBLE(name) \ - static inline umode_t sysfs_group_visible_##name( \ - struct kobject *kobj, struct bin_attribute *attr, int n) \ - { \ - if (n == 0 && !name##_group_visible(kobj)) \ - return SYSFS_GROUP_INVISIBLE; \ - return name##_attr_visible(kobj, attr, n); \ +#define DEFINE_SYSFS_BIN_GROUP_VISIBLE(name) \ + static inline umode_t sysfs_group_visible_##name( \ + struct kobject *kobj, const struct bin_attribute *attr, int n) \ + { \ + if (n == 0 && !name##_group_visible(kobj)) \ + return SYSFS_GROUP_INVISIBLE; \ + return name##_attr_visible(kobj, attr, n); \ } -#define DEFINE_SIMPLE_SYSFS_BIN_GROUP_VISIBLE(name) \ - static inline umode_t sysfs_group_visible_##name( \ - struct kobject *kobj, struct bin_attribute *a, int n) \ - { \ - if (n == 0 && !name##_group_visible(kobj)) \ - return SYSFS_GROUP_INVISIBLE; \ - return a->mode; \ +#define DEFINE_SIMPLE_SYSFS_BIN_GROUP_VISIBLE(name) \ + static inline umode_t sysfs_group_visible_##name( \ + struct kobject *kobj, const struct bin_attribute *a, int n) \ + { \ + if (n == 0 && !name##_group_visible(kobj)) \ + return SYSFS_GROUP_INVISIBLE; \ + return a->mode; \ } #define SYSFS_GROUP_VISIBLE(fn) sysfs_group_visible_##fn @@ -282,7 +293,7 @@ __ATTRIBUTE_GROUPS(_name) #define BIN_ATTRIBUTE_GROUPS(_name) \ static const struct attribute_group _name##_group = { \ - .bin_attrs = _name##_attrs, \ + .bin_attrs_new = _name##_attrs, \ }; \ __ATTRIBUTE_GROUPS(_name) @@ -297,11 +308,15 @@ struct bin_attribute { struct address_space *(*f_mapping)(void); ssize_t (*read)(struct file *, struct kobject *, struct bin_attribute *, char *, loff_t, size_t); + ssize_t (*read_new)(struct file *, struct kobject *, const struct bin_attribute *, + char *, loff_t, size_t); ssize_t (*write)(struct file *, struct kobject *, struct bin_attribute *, char *, loff_t, size_t); - loff_t (*llseek)(struct file *, struct kobject *, struct bin_attribute *, + ssize_t (*write_new)(struct file *, struct kobject *, + const struct bin_attribute *, char *, loff_t, size_t); + loff_t (*llseek)(struct file *, struct kobject *, const struct bin_attribute *, loff_t, int); - int (*mmap)(struct file *, struct kobject *, struct bin_attribute *attr, + int (*mmap)(struct file *, struct kobject *, const struct bin_attribute *attr, struct vm_area_struct *vma); }; @@ -317,25 +332,36 @@ struct bin_attribute { */ #define sysfs_bin_attr_init(bin_attr) sysfs_attr_init(&(bin_attr)->attr) +typedef ssize_t __sysfs_bin_rw_handler_new(struct file *, struct kobject *, + const struct bin_attribute *, char *, loff_t, size_t); + /* macros to create static binary attributes easier */ #define __BIN_ATTR(_name, _mode, _read, _write, _size) { \ .attr = { .name = __stringify(_name), .mode = _mode }, \ - .read = _read, \ - .write = _write, \ + .read = _Generic(_read, \ + __sysfs_bin_rw_handler_new * : NULL, \ + default : _read \ + ), \ + .read_new = _Generic(_read, \ + __sysfs_bin_rw_handler_new * : _read, \ + default : NULL \ + ), \ + .write = _Generic(_write, \ + __sysfs_bin_rw_handler_new * : NULL, \ + default : _write \ + ), \ + .write_new = _Generic(_write, \ + __sysfs_bin_rw_handler_new * : _write, \ + default : NULL \ + ), \ .size = _size, \ } -#define __BIN_ATTR_RO(_name, _size) { \ - .attr = { .name = __stringify(_name), .mode = 0444 }, \ - .read = _name##_read, \ - .size = _size, \ -} +#define __BIN_ATTR_RO(_name, _size) \ + __BIN_ATTR(_name, 0444, _name##_read, NULL, _size) -#define __BIN_ATTR_WO(_name, _size) { \ - .attr = { .name = __stringify(_name), .mode = 0200 }, \ - .write = _name##_write, \ - .size = _size, \ -} +#define __BIN_ATTR_WO(_name, _size) \ + __BIN_ATTR(_name, 0200, NULL, _name##_write, _size) #define __BIN_ATTR_RW(_name, _size) \ __BIN_ATTR(_name, 0644, _name##_read, _name##_write, _size) @@ -356,11 +382,8 @@ struct bin_attribute bin_attr_##_name = __BIN_ATTR_WO(_name, _size) struct bin_attribute bin_attr_##_name = __BIN_ATTR_RW(_name, _size) -#define __BIN_ATTR_ADMIN_RO(_name, _size) { \ - .attr = { .name = __stringify(_name), .mode = 0400 }, \ - .read = _name##_read, \ - .size = _size, \ -} +#define __BIN_ATTR_ADMIN_RO(_name, _size) \ + __BIN_ATTR(_name, 0400, _name##_read, NULL, _size) #define __BIN_ATTR_ADMIN_RW(_name, _size) \ __BIN_ATTR(_name, 0600, _name##_read, _name##_write, _size) @@ -371,6 +394,15 @@ struct bin_attribute bin_attr_##_name = __BIN_ATTR_ADMIN_RO(_name, _size) #define BIN_ATTR_ADMIN_RW(_name, _size) \ struct bin_attribute bin_attr_##_name = __BIN_ATTR_ADMIN_RW(_name, _size) +#define __BIN_ATTR_SIMPLE_RO(_name, _mode) \ + __BIN_ATTR(_name, _mode, sysfs_bin_attr_simple_read, NULL, 0) + +#define BIN_ATTR_SIMPLE_RO(_name) \ +struct bin_attribute bin_attr_##_name = __BIN_ATTR_SIMPLE_RO(_name, 0444) + +#define BIN_ATTR_SIMPLE_ADMIN_RO(_name) \ +struct bin_attribute bin_attr_##_name = __BIN_ATTR_SIMPLE_RO(_name, 0400) + struct sysfs_ops { ssize_t (*show)(struct kobject *, struct attribute *, char *); ssize_t (*store)(struct kobject *, struct attribute *, const char *, size_t); @@ -478,6 +510,10 @@ int sysfs_emit(char *buf, const char *fmt, ...); __printf(3, 4) int sysfs_emit_at(char *buf, int at, const char *fmt, ...); +ssize_t sysfs_bin_attr_simple_read(struct file *file, struct kobject *kobj, + const struct bin_attribute *attr, char *buf, + loff_t off, size_t count); + #else /* CONFIG_SYSFS */ static inline int sysfs_create_dir_ns(struct kobject *kobj, const void *ns) @@ -735,6 +771,15 @@ static inline int sysfs_emit_at(char *buf, int at, const char *fmt, ...) { return 0; } + +static inline ssize_t sysfs_bin_attr_simple_read(struct file *file, + struct kobject *kobj, + const struct bin_attribute *attr, + char *buf, loff_t off, + size_t count) +{ + return 0; +} #endif /* CONFIG_SYSFS */ static inline int __must_check sysfs_create_file(struct kobject *kobj, diff --git a/include/linux/t10-pi.h b/include/linux/t10-pi.h index 248f4ac95642..2c59fe3efcd4 100644 --- a/include/linux/t10-pi.h +++ b/include/linux/t10-pi.h @@ -41,18 +41,12 @@ static inline u32 t10_pi_ref_tag(struct request *rq) { unsigned int shift = ilog2(queue_logical_block_size(rq->q)); -#ifdef CONFIG_BLK_DEV_INTEGRITY - if (rq->q->integrity.interval_exp) - shift = rq->q->integrity.interval_exp; -#endif + if (IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY) && + rq->q->limits.integrity.interval_exp) + shift = rq->q->limits.integrity.interval_exp; return blk_rq_pos(rq) >> (shift - SECTOR_SHIFT) & 0xffffffff; } -extern const struct blk_integrity_profile t10_pi_type1_crc; -extern const struct blk_integrity_profile t10_pi_type1_ip; -extern const struct blk_integrity_profile t10_pi_type3_crc; -extern const struct blk_integrity_profile t10_pi_type3_ip; - struct crc64_pi_tuple { __be64 guard_tag; __be16 app_tag; @@ -72,14 +66,10 @@ static inline u64 ext_pi_ref_tag(struct request *rq) { unsigned int shift = ilog2(queue_logical_block_size(rq->q)); -#ifdef CONFIG_BLK_DEV_INTEGRITY - if (rq->q->integrity.interval_exp) - shift = rq->q->integrity.interval_exp; -#endif + if (IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY) && + rq->q->limits.integrity.interval_exp) + shift = rq->q->limits.integrity.interval_exp; return lower_48_bits(blk_rq_pos(rq) >> (shift - SECTOR_SHIFT)); } -extern const struct blk_integrity_profile ext_pi_type1_crc64; -extern const struct blk_integrity_profile ext_pi_type3_crc64; - #endif diff --git a/include/linux/task_work.h b/include/linux/task_work.h index 795ef5a68429..0646804860ff 100644 --- a/include/linux/task_work.h +++ b/include/linux/task_work.h @@ -14,10 +14,11 @@ init_task_work(struct callback_head *twork, task_work_func_t func) } enum task_work_notify_mode { - TWA_NONE, + TWA_NONE = 0, TWA_RESUME, TWA_SIGNAL, TWA_SIGNAL_NO_IPI, + TWA_NMI_CURRENT, }; static inline bool task_work_pending(struct task_struct *task) @@ -30,7 +31,8 @@ int task_work_add(struct task_struct *task, struct callback_head *twork, struct callback_head *task_work_cancel_match(struct task_struct *task, bool (*match)(struct callback_head *, void *data), void *data); -struct callback_head *task_work_cancel(struct task_struct *, task_work_func_t); +struct callback_head *task_work_cancel_func(struct task_struct *, task_work_func_t); +bool task_work_cancel(struct task_struct *task, struct callback_head *cb); void task_work_run(void); static inline void exit_task_work(struct task_struct *task) diff --git a/include/linux/tc.h b/include/linux/tc.h index 1638660abf5e..8416bae9b126 100644 --- a/include/linux/tc.h +++ b/include/linux/tc.h @@ -108,7 +108,7 @@ struct tc_driver { struct device_driver driver; }; -#define to_tc_driver(drv) container_of(drv, struct tc_driver, driver) +#define to_tc_driver(drv) container_of_const(drv, struct tc_driver, driver) /* * Return TURBOchannel clock frequency in Hz. diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 55399ee2a57e..f88daaa76d83 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -200,7 +200,6 @@ struct tcp_sock { /* TX read-mostly hotpath cache lines */ __cacheline_group_begin(tcp_sock_read_tx); - /* timestamp of last sent data packet (for restart window) */ u32 max_window; /* Maximal window ever seen from peer */ u32 rcv_ssthresh; /* Current window clamp */ u32 reordering; /* Packet reordering metric. */ @@ -244,6 +243,7 @@ struct tcp_sock { /* OOO segments go in this rbtree. Socket lock must be held. */ struct rb_root out_of_order_queue; u32 snd_ssthresh; /* Slow start size threshold */ + u8 recvmsg_inq : 1;/* Indicate # of bytes in queue upon recvmsg */ __cacheline_group_end(tcp_sock_read_rx); /* TX read-write hotpath cache lines */ @@ -262,12 +262,10 @@ struct tcp_sock { u32 chrono_stat[3]; /* Time in jiffies for chrono_stat stats */ u32 write_seq; /* Tail(+1) of data held in tcp send buffer */ u32 pushed_seq; /* Last pushed seq, required to talk to windows */ - u32 lsndtime; + u32 lsndtime; /* timestamp of last sent data packet (for restart window) */ u32 mdev_us; /* medium deviation */ u32 rtt_seq; /* sequence number to update rttvar */ u64 tcp_wstamp_ns; /* departure time for next sent data packet */ - u64 tcp_clock_cache; /* cache last tcp_clock_ns() (see tcp_mstamp_refresh()) */ - u64 tcp_mstamp; /* most recent packet received/sent */ struct list_head tsorted_sent_queue; /* time-sorted sent but un-SACKed skbs */ struct sk_buff *highest_sack; /* skb just after the highest * skb with SACKed bit set @@ -284,6 +282,8 @@ struct tcp_sock { * 0x5?10 << 16 + snd_wnd in net byte order */ __be32 pred_flags; + u64 tcp_clock_cache; /* cache last tcp_clock_ns() (see tcp_mstamp_refresh()) */ + u64 tcp_mstamp; /* most recent packet received/sent */ u32 rcv_nxt; /* What we want to receive next */ u32 snd_nxt; /* Next sequence we send */ u32 snd_una; /* First byte we want an ack for */ @@ -370,7 +370,6 @@ struct tcp_sock { tlp_retrans:1, /* TLP is a retransmission */ unused:5; u8 thin_lto : 1,/* Use linear timeouts for thin streams */ - recvmsg_inq : 1,/* Indicate # of bytes in queue upon recvmsg */ fastopen_connect:1, /* FASTOPEN_CONNECT sockopt */ fastopen_no_cookie:1, /* Allow send/recv SYN+data without a cookie */ fastopen_client_fail:2, /* reason why fastopen failed */ diff --git a/include/linux/tee_core.h b/include/linux/tee_core.h new file mode 100644 index 000000000000..a38494d6b5f4 --- /dev/null +++ b/include/linux/tee_core.h @@ -0,0 +1,318 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2024 Linaro Limited + */ + +#ifndef __TEE_CORE_H +#define __TEE_CORE_H + +#include <linux/cdev.h> +#include <linux/device.h> +#include <linux/idr.h> +#include <linux/kref.h> +#include <linux/list.h> +#include <linux/tee.h> +#include <linux/tee_drv.h> +#include <linux/types.h> +#include <linux/uuid.h> + +/* + * The file describes the API provided by the generic TEE driver to the + * specific TEE driver. + */ + +#define TEE_SHM_DYNAMIC BIT(0) /* Dynamic shared memory registered */ + /* in secure world */ +#define TEE_SHM_USER_MAPPED BIT(1) /* Memory mapped in user space */ +#define TEE_SHM_POOL BIT(2) /* Memory allocated from pool */ +#define TEE_SHM_PRIV BIT(3) /* Memory private to TEE driver */ + +#define TEE_DEVICE_FLAG_REGISTERED 0x1 +#define TEE_MAX_DEV_NAME_LEN 32 + +/** + * struct tee_device - TEE Device representation + * @name: name of device + * @desc: description of device + * @id: unique id of device + * @flags: represented by TEE_DEVICE_FLAG_REGISTERED above + * @dev: embedded basic device structure + * @cdev: embedded cdev + * @num_users: number of active users of this device + * @c_no_user: completion used when unregistering the device + * @mutex: mutex protecting @num_users and @idr + * @idr: register of user space shared memory objects allocated or + * registered on this device + * @pool: shared memory pool + */ +struct tee_device { + char name[TEE_MAX_DEV_NAME_LEN]; + const struct tee_desc *desc; + int id; + unsigned int flags; + + struct device dev; + struct cdev cdev; + + size_t num_users; + struct completion c_no_users; + struct mutex mutex; /* protects num_users and idr */ + + struct idr idr; + struct tee_shm_pool *pool; +}; + +/** + * struct tee_driver_ops - driver operations vtable + * @get_version: returns version of driver + * @open: called when the device file is opened + * @release: release this open file + * @open_session: open a new session + * @close_session: close a session + * @system_session: declare session as a system session + * @invoke_func: invoke a trusted function + * @cancel_req: request cancel of an ongoing invoke or open + * @supp_recv: called for supplicant to get a command + * @supp_send: called for supplicant to send a response + * @shm_register: register shared memory buffer in TEE + * @shm_unregister: unregister shared memory buffer in TEE + */ +struct tee_driver_ops { + void (*get_version)(struct tee_device *teedev, + struct tee_ioctl_version_data *vers); + int (*open)(struct tee_context *ctx); + void (*release)(struct tee_context *ctx); + int (*open_session)(struct tee_context *ctx, + struct tee_ioctl_open_session_arg *arg, + struct tee_param *param); + int (*close_session)(struct tee_context *ctx, u32 session); + int (*system_session)(struct tee_context *ctx, u32 session); + int (*invoke_func)(struct tee_context *ctx, + struct tee_ioctl_invoke_arg *arg, + struct tee_param *param); + int (*cancel_req)(struct tee_context *ctx, u32 cancel_id, u32 session); + int (*supp_recv)(struct tee_context *ctx, u32 *func, u32 *num_params, + struct tee_param *param); + int (*supp_send)(struct tee_context *ctx, u32 ret, u32 num_params, + struct tee_param *param); + int (*shm_register)(struct tee_context *ctx, struct tee_shm *shm, + struct page **pages, size_t num_pages, + unsigned long start); + int (*shm_unregister)(struct tee_context *ctx, struct tee_shm *shm); +}; + +/** + * struct tee_desc - Describes the TEE driver to the subsystem + * @name: name of driver + * @ops: driver operations vtable + * @owner: module providing the driver + * @flags: Extra properties of driver, defined by TEE_DESC_* below + */ +#define TEE_DESC_PRIVILEGED 0x1 +struct tee_desc { + const char *name; + const struct tee_driver_ops *ops; + struct module *owner; + u32 flags; +}; + +/** + * tee_device_alloc() - Allocate a new struct tee_device instance + * @teedesc: Descriptor for this driver + * @dev: Parent device for this device + * @pool: Shared memory pool, NULL if not used + * @driver_data: Private driver data for this device + * + * Allocates a new struct tee_device instance. The device is + * removed by tee_device_unregister(). + * + * @returns a pointer to a 'struct tee_device' or an ERR_PTR on failure + */ +struct tee_device *tee_device_alloc(const struct tee_desc *teedesc, + struct device *dev, + struct tee_shm_pool *pool, + void *driver_data); + +/** + * tee_device_register() - Registers a TEE device + * @teedev: Device to register + * + * tee_device_unregister() need to be called to remove the @teedev if + * this function fails. + * + * @returns < 0 on failure + */ +int tee_device_register(struct tee_device *teedev); + +/** + * tee_device_unregister() - Removes a TEE device + * @teedev: Device to unregister + * + * This function should be called to remove the @teedev even if + * tee_device_register() hasn't been called yet. Does nothing if + * @teedev is NULL. + */ +void tee_device_unregister(struct tee_device *teedev); + +/** + * tee_device_set_dev_groups() - Set device attribute groups + * @teedev: Device to register + * @dev_groups: Attribute groups + * + * Assigns the provided @dev_groups to the @teedev to be registered later + * with tee_device_register(). Calling this function is optional, but if + * it's called it must be called before tee_device_register(). + */ +void tee_device_set_dev_groups(struct tee_device *teedev, + const struct attribute_group **dev_groups); + +/** + * tee_session_calc_client_uuid() - Calculates client UUID for session + * @uuid: Resulting UUID + * @connection_method: Connection method for session (TEE_IOCTL_LOGIN_*) + * @connectuon_data: Connection data for opening session + * + * Based on connection method calculates UUIDv5 based client UUID. + * + * For group based logins verifies that calling process has specified + * credentials. + * + * @return < 0 on failure + */ +int tee_session_calc_client_uuid(uuid_t *uuid, u32 connection_method, + const u8 connection_data[TEE_IOCTL_UUID_LEN]); + +/** + * struct tee_shm_pool - shared memory pool + * @ops: operations + * @private_data: private data for the shared memory manager + */ +struct tee_shm_pool { + const struct tee_shm_pool_ops *ops; + void *private_data; +}; + +/** + * struct tee_shm_pool_ops - shared memory pool operations + * @alloc: called when allocating shared memory + * @free: called when freeing shared memory + * @destroy_pool: called when destroying the pool + */ +struct tee_shm_pool_ops { + int (*alloc)(struct tee_shm_pool *pool, struct tee_shm *shm, + size_t size, size_t align); + void (*free)(struct tee_shm_pool *pool, struct tee_shm *shm); + void (*destroy_pool)(struct tee_shm_pool *pool); +}; + +/* + * tee_shm_pool_alloc_res_mem() - Create a shm manager for reserved memory + * @vaddr: Virtual address of start of pool + * @paddr: Physical address of start of pool + * @size: Size in bytes of the pool + * + * @returns pointer to a 'struct tee_shm_pool' or an ERR_PTR on failure. + */ +struct tee_shm_pool *tee_shm_pool_alloc_res_mem(unsigned long vaddr, + phys_addr_t paddr, size_t size, + int min_alloc_order); + +/** + * tee_shm_pool_free() - Free a shared memory pool + * @pool: The shared memory pool to free + * + * The must be no remaining shared memory allocated from this pool when + * this function is called. + */ +static inline void tee_shm_pool_free(struct tee_shm_pool *pool) +{ + pool->ops->destroy_pool(pool); +} + +/** + * tee_get_drvdata() - Return driver_data pointer + * @returns the driver_data pointer supplied to tee_register(). + */ +void *tee_get_drvdata(struct tee_device *teedev); + +/** + * tee_shm_alloc_priv_buf() - Allocate shared memory for private use by specific + * TEE driver + * @ctx: The TEE context for shared memory allocation + * @size: Shared memory allocation size + * @returns a pointer to 'struct tee_shm' on success or an ERR_PTR on failure + */ +struct tee_shm *tee_shm_alloc_priv_buf(struct tee_context *ctx, size_t size); + +int tee_dyn_shm_alloc_helper(struct tee_shm *shm, size_t size, size_t align, + int (*shm_register)(struct tee_context *ctx, + struct tee_shm *shm, + struct page **pages, + size_t num_pages, + unsigned long start)); +void tee_dyn_shm_free_helper(struct tee_shm *shm, + int (*shm_unregister)(struct tee_context *ctx, + struct tee_shm *shm)); + +/** + * tee_shm_is_dynamic() - Check if shared memory object is of the dynamic kind + * @shm: Shared memory handle + * @returns true if object is dynamic shared memory + */ +static inline bool tee_shm_is_dynamic(struct tee_shm *shm) +{ + return shm && (shm->flags & TEE_SHM_DYNAMIC); +} + +/** + * tee_shm_put() - Decrease reference count on a shared memory handle + * @shm: Shared memory handle + */ +void tee_shm_put(struct tee_shm *shm); + +/** + * tee_shm_get_id() - Get id of a shared memory object + * @shm: Shared memory handle + * @returns id + */ +static inline int tee_shm_get_id(struct tee_shm *shm) +{ + return shm->id; +} + +/** + * tee_shm_get_from_id() - Find shared memory object and increase reference + * count + * @ctx: Context owning the shared memory + * @id: Id of shared memory object + * @returns a pointer to 'struct tee_shm' on success or an ERR_PTR on failure + */ +struct tee_shm *tee_shm_get_from_id(struct tee_context *ctx, int id); + +static inline bool tee_param_is_memref(struct tee_param *param) +{ + switch (param->attr & TEE_IOCTL_PARAM_ATTR_TYPE_MASK) { + case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INPUT: + case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT: + case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INOUT: + return true; + default: + return false; + } +} + +/** + * teedev_open() - Open a struct tee_device + * @teedev: Device to open + * + * @return a pointer to struct tee_context on success or an ERR_PTR on failure. + */ +struct tee_context *teedev_open(struct tee_device *teedev); + +/** + * teedev_close_context() - closes a struct tee_context + * @ctx: The struct tee_context to close + */ +void teedev_close_context(struct tee_context *ctx); + +#endif /*__TEE_CORE_H*/ diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h index 71632e3c5f18..a54c203000ed 100644 --- a/include/linux/tee_drv.h +++ b/include/linux/tee_drv.h @@ -1,40 +1,28 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (c) 2015-2022 Linaro Limited + * Copyright (c) 2015-2024 Linaro Limited */ #ifndef __TEE_DRV_H #define __TEE_DRV_H #include <linux/device.h> -#include <linux/idr.h> #include <linux/kref.h> #include <linux/list.h> #include <linux/mod_devicetable.h> #include <linux/tee.h> #include <linux/types.h> -#include <linux/uuid.h> /* - * The file describes the API provided by the generic TEE driver to the - * specific TEE driver. + * The file describes the API provided by the TEE subsystem to the + * TEE client drivers. */ -#define TEE_SHM_DYNAMIC BIT(0) /* Dynamic shared memory registered */ - /* in secure world */ -#define TEE_SHM_USER_MAPPED BIT(1) /* Memory mapped in user space */ -#define TEE_SHM_POOL BIT(2) /* Memory allocated from pool */ -#define TEE_SHM_PRIV BIT(3) /* Memory private to TEE driver */ - -struct device; struct tee_device; -struct tee_shm; -struct tee_shm_pool; /** * struct tee_context - driver specific context on file pointer data * @teedev: pointer to this drivers struct tee_device - * @list_shm: List of shared memory object owned by this context * @data: driver specific context data, managed by the driver * @refcount: reference counter for this structure * @releasing: flag that indicates if context is being released right now. @@ -57,134 +45,6 @@ struct tee_context { bool cap_memref_null; }; -struct tee_param_memref { - size_t shm_offs; - size_t size; - struct tee_shm *shm; -}; - -struct tee_param_value { - u64 a; - u64 b; - u64 c; -}; - -struct tee_param { - u64 attr; - union { - struct tee_param_memref memref; - struct tee_param_value value; - } u; -}; - -/** - * struct tee_driver_ops - driver operations vtable - * @get_version: returns version of driver - * @open: called when the device file is opened - * @release: release this open file - * @open_session: open a new session - * @close_session: close a session - * @system_session: declare session as a system session - * @invoke_func: invoke a trusted function - * @cancel_req: request cancel of an ongoing invoke or open - * @supp_recv: called for supplicant to get a command - * @supp_send: called for supplicant to send a response - * @shm_register: register shared memory buffer in TEE - * @shm_unregister: unregister shared memory buffer in TEE - */ -struct tee_driver_ops { - void (*get_version)(struct tee_device *teedev, - struct tee_ioctl_version_data *vers); - int (*open)(struct tee_context *ctx); - void (*release)(struct tee_context *ctx); - int (*open_session)(struct tee_context *ctx, - struct tee_ioctl_open_session_arg *arg, - struct tee_param *param); - int (*close_session)(struct tee_context *ctx, u32 session); - int (*system_session)(struct tee_context *ctx, u32 session); - int (*invoke_func)(struct tee_context *ctx, - struct tee_ioctl_invoke_arg *arg, - struct tee_param *param); - int (*cancel_req)(struct tee_context *ctx, u32 cancel_id, u32 session); - int (*supp_recv)(struct tee_context *ctx, u32 *func, u32 *num_params, - struct tee_param *param); - int (*supp_send)(struct tee_context *ctx, u32 ret, u32 num_params, - struct tee_param *param); - int (*shm_register)(struct tee_context *ctx, struct tee_shm *shm, - struct page **pages, size_t num_pages, - unsigned long start); - int (*shm_unregister)(struct tee_context *ctx, struct tee_shm *shm); -}; - -/** - * struct tee_desc - Describes the TEE driver to the subsystem - * @name: name of driver - * @ops: driver operations vtable - * @owner: module providing the driver - * @flags: Extra properties of driver, defined by TEE_DESC_* below - */ -#define TEE_DESC_PRIVILEGED 0x1 -struct tee_desc { - const char *name; - const struct tee_driver_ops *ops; - struct module *owner; - u32 flags; -}; - -/** - * tee_device_alloc() - Allocate a new struct tee_device instance - * @teedesc: Descriptor for this driver - * @dev: Parent device for this device - * @pool: Shared memory pool, NULL if not used - * @driver_data: Private driver data for this device - * - * Allocates a new struct tee_device instance. The device is - * removed by tee_device_unregister(). - * - * @returns a pointer to a 'struct tee_device' or an ERR_PTR on failure - */ -struct tee_device *tee_device_alloc(const struct tee_desc *teedesc, - struct device *dev, - struct tee_shm_pool *pool, - void *driver_data); - -/** - * tee_device_register() - Registers a TEE device - * @teedev: Device to register - * - * tee_device_unregister() need to be called to remove the @teedev if - * this function fails. - * - * @returns < 0 on failure - */ -int tee_device_register(struct tee_device *teedev); - -/** - * tee_device_unregister() - Removes a TEE device - * @teedev: Device to unregister - * - * This function should be called to remove the @teedev even if - * tee_device_register() hasn't been called yet. Does nothing if - * @teedev is NULL. - */ -void tee_device_unregister(struct tee_device *teedev); - -/** - * tee_session_calc_client_uuid() - Calculates client UUID for session - * @uuid: Resulting UUID - * @connection_method: Connection method for session (TEE_IOCTL_LOGIN_*) - * @connectuon_data: Connection data for opening session - * - * Based on connection method calculates UUIDv5 based client UUID. - * - * For group based logins verifies that calling process has specified - * credentials. - * - * @return < 0 on failure - */ -int tee_session_calc_client_uuid(uuid_t *uuid, u32 connection_method, - const u8 connection_data[TEE_IOCTL_UUID_LEN]); - /** * struct tee_shm - shared memory object * @ctx: context using the object @@ -195,15 +55,12 @@ int tee_session_calc_client_uuid(uuid_t *uuid, u32 connection_method, * @pages: locked pages from userspace * @num_pages: number of locked pages * @refcount: reference counter - * @flags: defined by TEE_SHM_* in tee_drv.h + * @flags: defined by TEE_SHM_* in tee_core.h * @id: unique id of a shared memory object on this device, shared * with user space * @sec_world_id: * secure world assigned id of this shared memory object, not * used by all drivers - * - * This pool is only supposed to be accessed directly from the TEE - * subsystem and from drivers that implements their own shm pool manager. */ struct tee_shm { struct tee_context *ctx; @@ -219,88 +76,53 @@ struct tee_shm { u64 sec_world_id; }; -/** - * struct tee_shm_pool - shared memory pool - * @ops: operations - * @private_data: private data for the shared memory manager - */ -struct tee_shm_pool { - const struct tee_shm_pool_ops *ops; - void *private_data; +struct tee_param_memref { + size_t shm_offs; + size_t size; + struct tee_shm *shm; }; -/** - * struct tee_shm_pool_ops - shared memory pool operations - * @alloc: called when allocating shared memory - * @free: called when freeing shared memory - * @destroy_pool: called when destroying the pool - */ -struct tee_shm_pool_ops { - int (*alloc)(struct tee_shm_pool *pool, struct tee_shm *shm, - size_t size, size_t align); - void (*free)(struct tee_shm_pool *pool, struct tee_shm *shm); - void (*destroy_pool)(struct tee_shm_pool *pool); +struct tee_param_value { + u64 a; + u64 b; + u64 c; }; -/* - * tee_shm_pool_alloc_res_mem() - Create a shm manager for reserved memory - * @vaddr: Virtual address of start of pool - * @paddr: Physical address of start of pool - * @size: Size in bytes of the pool - * - * @returns pointer to a 'struct tee_shm_pool' or an ERR_PTR on failure. - */ -struct tee_shm_pool *tee_shm_pool_alloc_res_mem(unsigned long vaddr, - phys_addr_t paddr, size_t size, - int min_alloc_order); +struct tee_param { + u64 attr; + union { + struct tee_param_memref memref; + struct tee_param_value value; + } u; +}; /** - * tee_shm_pool_free() - Free a shared memory pool - * @pool: The shared memory pool to free - * - * The must be no remaining shared memory allocated from this pool when - * this function is called. + * tee_shm_alloc_kernel_buf() - Allocate kernel shared memory for a + * particular TEE client driver + * @ctx: The TEE context for shared memory allocation + * @size: Shared memory allocation size + * @returns a pointer to 'struct tee_shm' on success or an ERR_PTR on failure */ -static inline void tee_shm_pool_free(struct tee_shm_pool *pool) -{ - pool->ops->destroy_pool(pool); -} +struct tee_shm *tee_shm_alloc_kernel_buf(struct tee_context *ctx, size_t size); /** - * tee_get_drvdata() - Return driver_data pointer - * @returns the driver_data pointer supplied to tee_register(). + * tee_shm_register_kernel_buf() - Register kernel shared memory for a + * particular TEE client driver + * @ctx: The TEE context for shared memory registration + * @addr: Kernel buffer address + * @length: Kernel buffer length + * @returns a pointer to 'struct tee_shm' on success or an ERR_PTR on failure */ -void *tee_get_drvdata(struct tee_device *teedev); - -struct tee_shm *tee_shm_alloc_priv_buf(struct tee_context *ctx, size_t size); -struct tee_shm *tee_shm_alloc_kernel_buf(struct tee_context *ctx, size_t size); - struct tee_shm *tee_shm_register_kernel_buf(struct tee_context *ctx, void *addr, size_t length); /** - * tee_shm_is_dynamic() - Check if shared memory object is of the dynamic kind - * @shm: Shared memory handle - * @returns true if object is dynamic shared memory - */ -static inline bool tee_shm_is_dynamic(struct tee_shm *shm) -{ - return shm && (shm->flags & TEE_SHM_DYNAMIC); -} - -/** * tee_shm_free() - Free shared memory * @shm: Handle to shared memory to free */ void tee_shm_free(struct tee_shm *shm); /** - * tee_shm_put() - Decrease reference count on a shared memory handle - * @shm: Shared memory handle - */ -void tee_shm_put(struct tee_shm *shm); - -/** * tee_shm_get_va() - Get virtual address of a shared memory plus an offset * @shm: Shared memory handle * @offs: Offset from start of this shared memory @@ -353,25 +175,6 @@ static inline size_t tee_shm_get_page_offset(struct tee_shm *shm) } /** - * tee_shm_get_id() - Get id of a shared memory object - * @shm: Shared memory handle - * @returns id - */ -static inline int tee_shm_get_id(struct tee_shm *shm) -{ - return shm->id; -} - -/** - * tee_shm_get_from_id() - Find shared memory object and increase reference - * count - * @ctx: Context owning the shared memory - * @id: Id of shared memory object - * @returns a pointer to 'struct tee_shm' on success or an ERR_PTR on failure - */ -struct tee_shm *tee_shm_get_from_id(struct tee_context *ctx, int id); - -/** * tee_client_open_context() - Open a TEE context * @start: if not NULL, continue search after this context * @match: function to check TEE device @@ -470,18 +273,6 @@ int tee_client_invoke_func(struct tee_context *ctx, int tee_client_cancel_req(struct tee_context *ctx, struct tee_ioctl_cancel_arg *arg); -static inline bool tee_param_is_memref(struct tee_param *param) -{ - switch (param->attr & TEE_IOCTL_PARAM_ATTR_TYPE_MASK) { - case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INPUT: - case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT: - case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INOUT: - return true; - default: - return false; - } -} - extern const struct bus_type tee_bus_type; /** @@ -507,20 +298,6 @@ struct tee_client_driver { }; #define to_tee_client_driver(d) \ - container_of(d, struct tee_client_driver, driver) - -/** - * teedev_open() - Open a struct tee_device - * @teedev: Device to open - * - * @return a pointer to struct tee_context on success or an ERR_PTR on failure. - */ -struct tee_context *teedev_open(struct tee_device *teedev); - -/** - * teedev_close_context() - closes a struct tee_context - * @ctx: The struct tee_context to close - */ -void teedev_close_context(struct tee_context *ctx); + container_of_const(d, struct tee_client_driver, driver) #endif /*__TEE_DRV_H*/ diff --git a/include/linux/text-patching.h b/include/linux/text-patching.h new file mode 100644 index 000000000000..ad5877ab0855 --- /dev/null +++ b/include/linux/text-patching.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_TEXT_PATCHING_H +#define _LINUX_TEXT_PATCHING_H + +#include <asm/text-patching.h> + +#ifndef text_poke_copy +static inline void *text_poke_copy(void *dst, const void *src, size_t len) +{ + return memcpy(dst, src, len); +} +#define text_poke_copy text_poke_copy +#endif + +#endif /* _LINUX_TEXT_PATCHING_H */ diff --git a/include/linux/thermal.h b/include/linux/thermal.h index c33f50177f51..69f9bedd0ee8 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -55,13 +55,16 @@ enum thermal_notify_event { THERMAL_TZ_BIND_CDEV, /* Cooling dev is bind to the thermal zone */ THERMAL_TZ_UNBIND_CDEV, /* Cooling dev is unbind from the thermal zone */ THERMAL_INSTANCE_WEIGHT_CHANGED, /* Thermal instance weight changed */ + THERMAL_TZ_RESUME, /* Thermal zone is resuming after system sleep */ + THERMAL_TZ_ADD_THRESHOLD, /* Threshold added */ + THERMAL_TZ_DEL_THRESHOLD, /* Threshold deleted */ + THERMAL_TZ_FLUSH_THRESHOLDS, /* All thresholds deleted */ }; /** * struct thermal_trip - representation of a point in temperature domain * @temperature: temperature value in miliCelsius * @hysteresis: relative hysteresis in miliCelsius - * @threshold: trip crossing notification threshold miliCelsius * @type: trip point type * @priv: pointer to driver data associated with this trip * @flags: flags representing binary properties of the trip @@ -69,7 +72,6 @@ enum thermal_notify_event { struct thermal_trip { int temperature; int hysteresis; - int threshold; enum thermal_trip_type type; u8 flags; void *priv; @@ -81,16 +83,28 @@ struct thermal_trip { #define THERMAL_TRIP_FLAG_RW (THERMAL_TRIP_FLAG_RW_TEMP | \ THERMAL_TRIP_FLAG_RW_HYST) +#define THERMAL_TRIP_PRIV_TO_INT(_val_) (uintptr_t)(_val_) +#define THERMAL_INT_TO_TRIP_PRIV(_val_) (void *)(uintptr_t)(_val_) + +struct thermal_zone_device; + +struct cooling_spec { + unsigned long upper; /* Highest cooling state */ + unsigned long lower; /* Lowest cooling state */ + unsigned int weight; /* Cooling device weight */ +}; + struct thermal_zone_device_ops { - int (*bind) (struct thermal_zone_device *, - struct thermal_cooling_device *); - int (*unbind) (struct thermal_zone_device *, - struct thermal_cooling_device *); + bool (*should_bind) (struct thermal_zone_device *, + const struct thermal_trip *, + struct thermal_cooling_device *, + struct cooling_spec *); int (*get_temp) (struct thermal_zone_device *, int *); int (*set_trips) (struct thermal_zone_device *, int, int); int (*change_mode) (struct thermal_zone_device *, enum thermal_device_mode); - int (*set_trip_temp) (struct thermal_zone_device *, int, int); + int (*set_trip_temp) (struct thermal_zone_device *, + const struct thermal_trip *, int); int (*get_crit_temp) (struct thermal_zone_device *, int *); int (*set_emul_temp) (struct thermal_zone_device *, int); int (*get_trend) (struct thermal_zone_device *, @@ -126,110 +140,8 @@ struct thermal_cooling_device { #endif }; -/** - * struct thermal_zone_device - structure for a thermal zone - * @id: unique id number for each thermal zone - * @type: the thermal zone device type - * @device: &struct device for this thermal zone - * @removal: removal completion - * @trip_temp_attrs: attributes for trip points for sysfs: trip temperature - * @trip_type_attrs: attributes for trip points for sysfs: trip type - * @trip_hyst_attrs: attributes for trip points for sysfs: trip hysteresis - * @mode: current mode of this thermal zone - * @devdata: private pointer for device private data - * @num_trips: number of trip points the thermal zone supports - * @passive_delay_jiffies: number of jiffies to wait between polls when - * performing passive cooling. - * @polling_delay_jiffies: number of jiffies to wait between polls when - * checking whether trip points have been crossed (0 for - * interrupt driven systems) - * @temperature: current temperature. This is only for core code, - * drivers should use thermal_zone_get_temp() to get the - * current temperature - * @last_temperature: previous temperature read - * @emul_temperature: emulated temperature when using CONFIG_THERMAL_EMULATION - * @passive: 1 if you've crossed a passive trip point, 0 otherwise. - * @prev_low_trip: the low current temperature if you've crossed a passive - trip point. - * @prev_high_trip: the above current temperature if you've crossed a - passive trip point. - * @need_update: if equals 1, thermal_zone_device_update needs to be invoked. - * @ops: operations this &thermal_zone_device supports - * @tzp: thermal zone parameters - * @governor: pointer to the governor for this thermal zone - * @governor_data: private pointer for governor data - * @thermal_instances: list of &struct thermal_instance of this thermal zone - * @ida: &struct ida to generate unique id for this zone's cooling - * devices - * @lock: lock to protect thermal_instances list - * @node: node in thermal_tz_list (in thermal_core.c) - * @poll_queue: delayed work for polling - * @notify_event: Last notification event - * @suspended: thermal zone suspend indicator - * @trips: array of struct thermal_trip objects - */ -struct thermal_zone_device { - int id; - char type[THERMAL_NAME_LENGTH]; - struct device device; - struct completion removal; - struct attribute_group trips_attribute_group; - struct thermal_attr *trip_temp_attrs; - struct thermal_attr *trip_type_attrs; - struct thermal_attr *trip_hyst_attrs; - enum thermal_device_mode mode; - void *devdata; - int num_trips; - unsigned long passive_delay_jiffies; - unsigned long polling_delay_jiffies; - int temperature; - int last_temperature; - int emul_temperature; - int passive; - int prev_low_trip; - int prev_high_trip; - atomic_t need_update; - struct thermal_zone_device_ops ops; - struct thermal_zone_params *tzp; - struct thermal_governor *governor; - void *governor_data; - struct list_head thermal_instances; - struct ida ida; - struct mutex lock; - struct list_head node; - struct delayed_work poll_queue; - enum thermal_notify_event notify_event; - bool suspended; -#ifdef CONFIG_THERMAL_DEBUGFS - struct thermal_debugfs *debugfs; -#endif - struct thermal_trip trips[] __counted_by(num_trips); -}; - -/** - * struct thermal_governor - structure that holds thermal governor information - * @name: name of the governor - * @bind_to_tz: callback called when binding to a thermal zone. If it - * returns 0, the governor is bound to the thermal zone, - * otherwise it fails. - * @unbind_from_tz: callback called when a governor is unbound from a - * thermal zone. - * @throttle: callback called for every trip point even if temperature is - * below the trip point temperature - * @update_tz: callback called when thermal zone internals have changed, e.g. - * thermal cooling instance was added/removed - * @governor_list: node in thermal_governor_list (in thermal_core.c) - */ -struct thermal_governor { - const char *name; - int (*bind_to_tz)(struct thermal_zone_device *tz); - void (*unbind_from_tz)(struct thermal_zone_device *tz); - int (*throttle)(struct thermal_zone_device *tz, - const struct thermal_trip *trip); - void (*update_tz)(struct thermal_zone_device *tz, - enum thermal_notify_event reason); - struct list_head governor_list; -}; +DEFINE_GUARD(cooling_dev, struct thermal_cooling_device *, mutex_lock(&_T->lock), + mutex_unlock(&_T->lock)) /* Structure to define Thermal Zone parameters */ struct thermal_zone_params { @@ -303,17 +215,12 @@ static inline void devm_thermal_of_zone_unregister(struct device *dev, } #endif -int __thermal_zone_get_trip(struct thermal_zone_device *tz, int trip_id, - struct thermal_trip *trip); -int thermal_zone_get_trip(struct thermal_zone_device *tz, int trip_id, - struct thermal_trip *trip); int for_each_thermal_trip(struct thermal_zone_device *tz, int (*cb)(struct thermal_trip *, void *), void *data); int thermal_zone_for_each_trip(struct thermal_zone_device *tz, int (*cb)(struct thermal_trip *, void *), void *data); -int thermal_zone_get_num_trips(struct thermal_zone_device *tz); void thermal_zone_set_trip_temp(struct thermal_zone_device *tz, struct thermal_trip *trip, int temp); @@ -326,7 +233,8 @@ struct thermal_zone_device *thermal_zone_device_register_with_trips( int num_trips, void *devdata, const struct thermal_zone_device_ops *ops, const struct thermal_zone_params *tzp, - int passive_delay, int polling_delay); + unsigned int passive_delay, + unsigned int polling_delay); struct thermal_zone_device *thermal_tripless_zone_device_register( const char *type, @@ -341,20 +249,6 @@ const char *thermal_zone_device_type(struct thermal_zone_device *tzd); int thermal_zone_device_id(struct thermal_zone_device *tzd); struct device *thermal_zone_device(struct thermal_zone_device *tzd); -int thermal_bind_cdev_to_trip(struct thermal_zone_device *tz, - const struct thermal_trip *trip, - struct thermal_cooling_device *cdev, - unsigned long upper, unsigned long lower, - unsigned int weight); -int thermal_zone_bind_cooling_device(struct thermal_zone_device *, int, - struct thermal_cooling_device *, - unsigned long, unsigned long, - unsigned int); -int thermal_unbind_cdev_from_trip(struct thermal_zone_device *tz, - const struct thermal_trip *trip, - struct thermal_cooling_device *cdev); -int thermal_zone_unbind_cooling_device(struct thermal_zone_device *, int, - struct thermal_cooling_device *); void thermal_zone_device_update(struct thermal_zone_device *, enum thermal_notify_event); @@ -366,7 +260,7 @@ thermal_of_cooling_device_register(struct device_node *np, const char *, void *, struct thermal_cooling_device * devm_thermal_of_cooling_device_register(struct device *dev, struct device_node *np, - char *type, void *devdata, + const 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 *); @@ -374,6 +268,9 @@ 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); int thermal_zone_get_slope(struct thermal_zone_device *tz); int thermal_zone_get_offset(struct thermal_zone_device *tz); +bool thermal_trip_is_bound_to_cdev(struct thermal_zone_device *tz, + const struct thermal_trip *trip, + struct thermal_cooling_device *cdev); int thermal_zone_device_enable(struct thermal_zone_device *tz); int thermal_zone_device_disable(struct thermal_zone_device *tz); @@ -398,6 +295,10 @@ static inline struct thermal_zone_device *thermal_tripless_zone_device_register( static inline void thermal_zone_device_unregister(struct thermal_zone_device *tz) { } +static inline void thermal_zone_device_update(struct thermal_zone_device *tz, + enum thermal_notify_event event) +{ } + static inline struct thermal_cooling_device * thermal_cooling_device_register(const char *type, void *devdata, const struct thermal_cooling_device_ops *ops) @@ -410,7 +311,7 @@ thermal_of_cooling_device_register(struct device_node *np, static inline struct thermal_cooling_device * devm_thermal_of_cooling_device_register(struct device *dev, struct device_node *np, - char *type, void *devdata, + const char *type, void *devdata, const struct thermal_cooling_device_ops *ops) { return ERR_PTR(-ENODEV); diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index 9ea0b28068f4..cf2446c9c30d 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -59,6 +59,14 @@ enum syscall_work_bit { #include <asm/thread_info.h> +#ifndef TIF_NEED_RESCHED_LAZY +#ifdef CONFIG_ARCH_HAS_PREEMPT_LAZY +#error Inconsistent PREEMPT_LAZY +#endif +#define TIF_NEED_RESCHED_LAZY TIF_NEED_RESCHED +#define _TIF_NEED_RESCHED_LAZY _TIF_NEED_RESCHED +#endif + #ifdef __KERNEL__ #ifndef arch_set_restart_data @@ -179,22 +187,27 @@ static __always_inline unsigned long read_ti_thread_flags(struct thread_info *ti #ifdef _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H -static __always_inline bool tif_need_resched(void) +static __always_inline bool tif_test_bit(int bit) { - return arch_test_bit(TIF_NEED_RESCHED, + return arch_test_bit(bit, (unsigned long *)(¤t_thread_info()->flags)); } #else -static __always_inline bool tif_need_resched(void) +static __always_inline bool tif_test_bit(int bit) { - return test_bit(TIF_NEED_RESCHED, + return test_bit(bit, (unsigned long *)(¤t_thread_info()->flags)); } #endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H */ +static __always_inline bool tif_need_resched(void) +{ + return tif_test_bit(TIF_NEED_RESCHED); +} + #ifndef CONFIG_HAVE_ARCH_WITHIN_STACK_FRAMES static inline int arch_within_stack_frames(const void * const stack, const void * const stackend, diff --git a/include/linux/threads.h b/include/linux/threads.h index c34173e6c5f1..1674a471b0b4 100644 --- a/include/linux/threads.h +++ b/include/linux/threads.h @@ -25,13 +25,13 @@ /* * This controls the default maximum pid allocated to a process */ -#define PID_MAX_DEFAULT (CONFIG_BASE_SMALL ? 0x1000 : 0x8000) +#define PID_MAX_DEFAULT (IS_ENABLED(CONFIG_BASE_SMALL) ? 0x1000 : 0x8000) /* * A maximum of 4 million PIDs should be enough for a while. * [NOTE: PID/TIDs are limited to 2^30 ~= 1 billion, see FUTEX_TID_MASK.] */ -#define PID_MAX_LIMIT (CONFIG_BASE_SMALL ? PAGE_SIZE * 8 : \ +#define PID_MAX_LIMIT (IS_ENABLED(CONFIG_BASE_SMALL) ? PAGE_SIZE * 8 : \ (sizeof(long) > 4 ? 4 * 1024 * 1024 : PID_MAX_DEFAULT)) /* diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h index 4338ea9ac4fd..7d902d8c054b 100644 --- a/include/linux/thunderbolt.h +++ b/include/linux/thunderbolt.h @@ -33,7 +33,6 @@ enum tb_cfg_pkg_type { TB_CFG_PKG_ICM_EVENT = 10, TB_CFG_PKG_ICM_CMD = 11, TB_CFG_PKG_ICM_RESP = 12, - TB_CFG_PKG_PREPARE_TO_SLEEP = 13, }; /** diff --git a/include/linux/tick.h b/include/linux/tick.h index 4924a33700b7..b8ddc8e631a3 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -20,12 +20,10 @@ extern void __init tick_init(void); extern void tick_suspend_local(void); /* Should be core only, but XEN resume magic and ARM BL switcher require it */ extern void tick_resume_local(void); -extern void tick_cleanup_dead_cpu(int cpu); #else /* CONFIG_GENERIC_CLOCKEVENTS */ static inline void tick_init(void) { } static inline void tick_suspend_local(void) { } static inline void tick_resume_local(void) { } -static inline void tick_cleanup_dead_cpu(int cpu) { } #endif /* !CONFIG_GENERIC_CLOCKEVENTS */ #if defined(CONFIG_GENERIC_CLOCKEVENTS) && defined(CONFIG_HOTPLUG_CPU) @@ -139,7 +137,6 @@ extern void tick_nohz_irq_exit(void); extern bool tick_nohz_idle_got_tick(void); extern ktime_t tick_nohz_get_next_hrtimer(void); extern ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next); -extern unsigned long tick_nohz_get_idle_calls(void); extern unsigned long tick_nohz_get_idle_calls_cpu(int cpu); extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time); extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time); @@ -252,12 +249,19 @@ static inline void tick_dep_set_task(struct task_struct *tsk, if (tick_nohz_full_enabled()) tick_nohz_dep_set_task(tsk, bit); } + static inline void tick_dep_clear_task(struct task_struct *tsk, enum tick_dep_bits bit) { if (tick_nohz_full_enabled()) tick_nohz_dep_clear_task(tsk, bit); } + +static inline void tick_dep_init_task(struct task_struct *tsk) +{ + atomic_set(&tsk->tick_dep_mask, 0); +} + static inline void tick_dep_set_signal(struct task_struct *tsk, enum tick_dep_bits bit) { @@ -291,6 +295,7 @@ static inline void tick_dep_set_task(struct task_struct *tsk, enum tick_dep_bits bit) { } static inline void tick_dep_clear_task(struct task_struct *tsk, enum tick_dep_bits bit) { } +static inline void tick_dep_init_task(struct task_struct *tsk) { } static inline void tick_dep_set_signal(struct task_struct *tsk, enum tick_dep_bits bit) { } static inline void tick_dep_clear_signal(struct signal_struct *signal, diff --git a/include/linux/time64.h b/include/linux/time64.h index f1bcea8c124a..9934331c7b86 100644 --- a/include/linux/time64.h +++ b/include/linux/time64.h @@ -49,6 +49,11 @@ static inline int timespec64_equal(const struct timespec64 *a, return (a->tv_sec == b->tv_sec) && (a->tv_nsec == b->tv_nsec); } +static inline bool timespec64_is_epoch(const struct timespec64 *ts) +{ + return ts->tv_sec == 0 && ts->tv_nsec == 0; +} + /* * lhs < rhs: return <0 * lhs == rhs: return 0 diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index 84ff2844df2a..e39d4d563b19 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -26,7 +26,7 @@ * occupies a single 64byte cache line. * * The struct is separate from struct timekeeper as it is also used - * for a fast NMI safe accessors. + * for the fast NMI safe accessors. * * @base_real is for the fast NMI safe accessor to allow reading clock * realtime from any context. @@ -44,36 +44,41 @@ struct tk_read_base { /** * struct timekeeper - Structure holding internal timekeeping values. - * @tkr_mono: The readout base structure for CLOCK_MONOTONIC - * @tkr_raw: The readout base structure for CLOCK_MONOTONIC_RAW - * @xtime_sec: Current CLOCK_REALTIME time in seconds - * @ktime_sec: Current CLOCK_MONOTONIC time in seconds - * @wall_to_monotonic: CLOCK_REALTIME to CLOCK_MONOTONIC offset - * @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 - * @clock_was_set_seq: The sequence number of clock was set events - * @cs_was_changed_seq: The sequence number of clocksource change events - * @next_leap_ktime: CLOCK_MONOTONIC time value of a pending leap-second - * @raw_sec: CLOCK_MONOTONIC_RAW time in seconds - * @monotonic_to_boot: CLOCK_MONOTONIC to CLOCK_BOOTTIME offset - * @cycle_interval: Number of clock cycles in one NTP interval - * @xtime_interval: Number of clock shifted nano seconds in one NTP - * interval. - * @xtime_remainder: Shifted nano seconds left over when rounding - * @cycle_interval - * @raw_interval: Shifted raw nano seconds accumulated per NTP interval. - * @ntp_error: Difference between accumulated time and NTP time in ntp - * shifted nano seconds. - * @ntp_error_shift: Shift conversion between clock shifted nano seconds and - * ntp shifted nano seconds. - * @last_warning: Warning ratelimiter (DEBUG_TIMEKEEPING) - * @underflow_seen: Underflow warning flag (DEBUG_TIMEKEEPING) - * @overflow_seen: Overflow warning flag (DEBUG_TIMEKEEPING) + * @tkr_mono: The readout base structure for CLOCK_MONOTONIC + * @xtime_sec: Current CLOCK_REALTIME time in seconds + * @ktime_sec: Current CLOCK_MONOTONIC time in seconds + * @wall_to_monotonic: CLOCK_REALTIME to CLOCK_MONOTONIC offset + * @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 + * @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 + * @cs_was_changed_seq: The sequence number of clocksource change events + * @monotonic_to_boot: CLOCK_MONOTONIC to CLOCK_BOOTTIME offset + * @cycle_interval: Number of clock cycles in one NTP interval + * @xtime_interval: Number of clock shifted nano seconds in one NTP + * interval. + * @xtime_remainder: Shifted nano seconds left over when rounding + * @cycle_interval + * @raw_interval: Shifted raw nano seconds accumulated per NTP interval. + * @next_leap_ktime: CLOCK_MONOTONIC time value of a pending leap-second + * @ntp_tick: The ntp_tick_length() value currently being + * used. This cached copy ensures we consistently + * apply the tick length for an entire tick, as + * ntp_tick_length may change mid-tick, and we don't + * want to apply that new value to the tick in + * progress. + * @ntp_error: Difference between accumulated time and NTP time in ntp + * shifted nano seconds. + * @ntp_error_shift: Shift conversion between clock shifted nano seconds and + * 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 * * Note: For timespec(64) based interfaces wall_to_monotonic is what - * we need to add to xtime (or xtime corrected for sub jiffie times) + * we need to add to xtime (or xtime corrected for sub jiffy times) * to get to monotonic time. Monotonic is pegged at zero at system * boot time, so wall_to_monotonic will be negative, however, we will * ALWAYS keep the tv_nsec part positive so we can use the usual @@ -88,10 +93,28 @@ struct tk_read_base { * * @monotonic_to_boottime is a timespec64 representation of @offs_boot to * accelerate the VDSO update for CLOCK_BOOTTIME. + * + * The cacheline ordering of the structure is optimized for in kernel usage of + * the ktime_get() and ktime_get_ts64() family of time accessors. Struct + * timekeeper is prepended in the core timekeeping code with a sequence count, + * which results in the following cacheline layout: + * + * 0: seqcount, tkr_mono + * 1: xtime_sec ... tai_offset + * 2: tkr_raw, raw_sec + * 3,4: Internal variables + * + * Cacheline 0,1 contain the data which is used for accessing + * CLOCK_MONOTONIC/REALTIME/BOOTTIME/TAI, while cacheline 2 contains the + * data for accessing CLOCK_MONOTONIC_RAW. Cacheline 3,4 are internal + * variables which are only accessed during timekeeper updates once per + * tick. */ struct timekeeper { + /* Cacheline 0 (together with prepended seqcount of timekeeper core): */ struct tk_read_base tkr_mono; - struct tk_read_base tkr_raw; + + /* Cacheline 1: */ u64 xtime_sec; unsigned long ktime_sec; struct timespec64 wall_to_monotonic; @@ -99,43 +122,28 @@ struct timekeeper { ktime_t offs_boot; ktime_t offs_tai; s32 tai_offset; + + /* Cacheline 2: */ + struct tk_read_base tkr_raw; + u64 raw_sec; + + /* Cachline 3 and 4 (timekeeping internal variables): */ unsigned int clock_was_set_seq; u8 cs_was_changed_seq; - ktime_t next_leap_ktime; - u64 raw_sec; + struct timespec64 monotonic_to_boot; - /* The following members are for timekeeping internal use */ u64 cycle_interval; u64 xtime_interval; s64 xtime_remainder; u64 raw_interval; - /* The ntp_tick_length() value currently being used. - * This cached copy ensures we consistently apply the tick - * length for an entire tick, as ntp_tick_length may change - * mid-tick, and we don't want to apply that new value to - * the tick in progress. - */ + + ktime_t next_leap_ktime; u64 ntp_tick; - /* Difference between accumulated time and NTP time in ntp - * shifted nano seconds. */ s64 ntp_error; u32 ntp_error_shift; u32 ntp_err_mult; - /* Flag used to avoid updating NTP twice with same second */ u32 skip_second_overflow; -#ifdef CONFIG_DEBUG_TIMEKEEPING - long last_warning; - /* - * These simple flag variables are managed - * without locks, which is racy, but they are - * ok since we don't really care about being - * super precise about how many events were - * seen, just that a problem was observed. - */ - int underflow_seen; - int overflow_seen; -#endif }; #ifdef CONFIG_GENERIC_TIME_VSYSCALL diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 0ea7823b7f31..542773650200 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -45,6 +45,11 @@ extern void ktime_get_real_ts64(struct timespec64 *tv); extern void ktime_get_coarse_ts64(struct timespec64 *ts); extern void ktime_get_coarse_real_ts64(struct timespec64 *ts); +/* Multigrain timestamp interfaces */ +extern void ktime_get_coarse_real_ts64_mg(struct timespec64 *ts); +extern void ktime_get_real_ts64_mg(struct timespec64 *ts); +extern unsigned long timekeeping_get_mg_floor_swaps(void); + void getboottime64(struct timespec64 *ts); /* @@ -259,22 +264,11 @@ extern bool timekeeping_rtc_skipresume(void); extern void timekeeping_inject_sleeptime64(const struct timespec64 *delta); /** - * struct ktime_timestamps - Simultaneous mono/boot/real timestamps - * @mono: Monotonic timestamp - * @boot: Boottime timestamp - * @real: Realtime timestamp - */ -struct ktime_timestamps { - u64 mono; - u64 boot; - u64 real; -}; - -/** * struct system_time_snapshot - simultaneous raw/real time capture with * counter value * @cycles: Clocksource counter value to produce the system times * @real: Realtime system time + * @boot: Boot time * @raw: Monotonic raw system time * @cs_id: Clocksource ID * @clock_was_set_seq: The sequence number of clock-was-set events @@ -283,6 +277,7 @@ struct ktime_timestamps { struct system_time_snapshot { u64 cycles; ktime_t real; + ktime_t boot; ktime_t raw; enum clocksource_ids cs_id; unsigned int clock_was_set_seq; @@ -310,12 +305,18 @@ struct system_device_crosststamp { * timekeeping code to verify comparability of two cycle values. * The default ID, CSID_GENERIC, does not identify a specific * clocksource. + * @use_nsecs: @cycles is in nanoseconds. */ struct system_counterval_t { u64 cycles; enum clocksource_ids cs_id; + bool use_nsecs; }; +extern bool ktime_real_to_base_clock(ktime_t treal, + enum clocksource_ids base_id, u64 *cycles); +extern bool timekeeping_clocksource_has_base(enum clocksource_ids id); + /* * Get cross timestamp between system clock and device clock */ @@ -332,9 +333,6 @@ extern int get_device_system_crosststamp( */ extern void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot); -/* NMI safe mono/boot/realtime timestamps */ -extern void ktime_get_fast_timestamps(struct ktime_timestamps *snap); - /* * Persistent clock related interfaces */ diff --git a/include/linux/timerqueue.h b/include/linux/timerqueue.h index 62973f7d4610..d306d9dd2207 100644 --- a/include/linux/timerqueue.h +++ b/include/linux/timerqueue.h @@ -37,11 +37,6 @@ static inline bool timerqueue_node_queued(struct timerqueue_node *node) return !RB_EMPTY_NODE(&node->node); } -static inline bool timerqueue_node_expires(struct timerqueue_node *node) -{ - return node->expires; -} - static inline void timerqueue_init_head(struct timerqueue_head *head) { head->rb_root = RB_ROOT_CACHED; diff --git a/include/linux/timex.h b/include/linux/timex.h index 3871b06bd302..4ee32eff3f22 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -139,14 +139,6 @@ unsigned long random_get_entropy_fallback(void); #define MAXSEC 2048 /* max interval between updates (s) */ #define NTP_PHASE_LIMIT ((MAXPHASE / NSEC_PER_USEC) << 5) /* beyond max. dispersion */ -/* - * kernel variables - * Note: maximum error = NTP sync distance = dispersion + delay / 2; - * estimated error = NTP dispersion. - */ -extern unsigned long tick_usec; /* USER_HZ period (usec) */ -extern unsigned long tick_nsec; /* SHIFTED_HZ period (nsec) */ - /* Required to safely shift negative values */ #define shift_right(x, s) ({ \ __typeof__(x) __x = (x); \ diff --git a/include/linux/torture.h b/include/linux/torture.h index 1541454da03e..0134e7221cae 100644 --- a/include/linux/torture.h +++ b/include/linux/torture.h @@ -14,7 +14,7 @@ #include <linux/cache.h> #include <linux/spinlock.h> #include <linux/threads.h> -#include <linux/cpumask.h> +#include <linux/cpumask_types.h> #include <linux/seqlock.h> #include <linux/lockdep.h> #include <linux/completion.h> @@ -130,7 +130,7 @@ void _torture_stop_kthread(char *m, struct task_struct **tp); #endif #if IS_ENABLED(CONFIG_RCU_TORTURE_TEST) || IS_MODULE(CONFIG_RCU_TORTURE_TEST) || IS_ENABLED(CONFIG_LOCK_TORTURE_TEST) || IS_MODULE(CONFIG_LOCK_TORTURE_TEST) -long torture_sched_setaffinity(pid_t pid, const struct cpumask *in_mask); +long torture_sched_setaffinity(pid_t pid, const struct cpumask *in_mask, bool dowarn); #endif #endif /* __LINUX_TORTURE_H */ diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 4ee9d13749ad..20a40ade8030 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -23,6 +23,7 @@ #include <linux/fs.h> #include <linux/highmem.h> #include <crypto/hash_info.h> +#include <crypto/aes.h> #define TPM_DIGEST_SIZE 20 /* Max TPM v1.2 PCR size */ #define TPM_MAX_DIGEST_SIZE SHA512_DIGEST_SIZE @@ -30,17 +31,28 @@ struct tpm_chip; struct trusted_key_payload; struct trusted_key_options; +/* opaque structure, holds auth session parameters like the session key */ +struct tpm2_auth; + +enum tpm2_session_types { + TPM2_SE_HMAC = 0x00, + TPM2_SE_POLICY = 0x01, + TPM2_SE_TRIAL = 0x02, +}; /* if you add a new hash to this, increment TPM_MAX_HASHES below */ enum tpm_algorithms { TPM_ALG_ERROR = 0x0000, TPM_ALG_SHA1 = 0x0004, + TPM_ALG_AES = 0x0006, TPM_ALG_KEYEDHASH = 0x0008, TPM_ALG_SHA256 = 0x000B, TPM_ALG_SHA384 = 0x000C, TPM_ALG_SHA512 = 0x000D, TPM_ALG_NULL = 0x0010, TPM_ALG_SM3_256 = 0x0012, + TPM_ALG_ECC = 0x0023, + TPM_ALG_CFB = 0x0043, }; /* @@ -49,6 +61,11 @@ enum tpm_algorithms { */ #define TPM_MAX_HASHES 5 +enum tpm2_curves { + TPM2_ECC_NONE = 0x0000, + TPM2_ECC_NIST_P256 = 0x0003, +}; + struct tpm_digest { u16 alg_id; u8 digest[TPM_MAX_DIGEST_SIZE]; @@ -116,6 +133,20 @@ struct tpm_chip_seqops { const struct seq_operations *seqops; }; +/* fixed define for the curve we use which is NIST_P256 */ +#define EC_PT_SZ 32 + +/* + * fixed define for the size of a name. This is actually HASHALG size + * plus 2, so 32 for SHA256 + */ +#define TPM2_NAME_SIZE 34 + +/* + * The maximum size for an object context + */ +#define TPM2_MAX_CONTEXT_SIZE 4096 + struct tpm_chip { struct device dev; struct device devs; @@ -170,6 +201,18 @@ struct tpm_chip { /* active locality */ int locality; + +#ifdef CONFIG_TCG_TPM2_HMAC + /* details for communication security via sessions */ + + /* saved context for NULL seed */ + u8 null_key_context[TPM2_MAX_CONTEXT_SIZE]; + /* name of NULL seed */ + u8 null_key_name[TPM2_NAME_SIZE]; + u8 null_ec_key_x[EC_PT_SZ]; + u8 null_ec_key_y[EC_PT_SZ]; + struct tpm2_auth *auth; +#endif }; #define TPM_HEADER_SIZE 10 @@ -194,6 +237,7 @@ enum tpm2_timeouts { enum tpm2_structures { TPM2_ST_NO_SESSIONS = 0x8001, TPM2_ST_SESSIONS = 0x8002, + TPM2_ST_CREATION = 0x8021, }; /* Indicates from what layer of the software stack the error comes from */ @@ -204,6 +248,7 @@ enum tpm2_return_codes { TPM2_RC_SUCCESS = 0x0000, TPM2_RC_HASH = 0x0083, /* RC_FMT1 */ TPM2_RC_HANDLE = 0x008B, + TPM2_RC_INTEGRITY = 0x009F, TPM2_RC_INITIALIZE = 0x0100, /* RC_VER1 */ TPM2_RC_FAILURE = 0x0101, TPM2_RC_DISABLED = 0x0120, @@ -231,6 +276,8 @@ enum tpm2_command_codes { TPM2_CC_CONTEXT_LOAD = 0x0161, TPM2_CC_CONTEXT_SAVE = 0x0162, TPM2_CC_FLUSH_CONTEXT = 0x0165, + TPM2_CC_READ_PUBLIC = 0x0173, + TPM2_CC_START_AUTH_SESS = 0x0176, TPM2_CC_VERIFY_SIGNATURE = 0x0177, TPM2_CC_GET_CAPABILITY = 0x017A, TPM2_CC_GET_RANDOM = 0x017B, @@ -243,9 +290,25 @@ enum tpm2_command_codes { }; enum tpm2_permanent_handles { + TPM2_RH_NULL = 0x40000007, TPM2_RS_PW = 0x40000009, }; +/* Most Significant Octet for key types */ +enum tpm2_mso_type { + TPM2_MSO_NVRAM = 0x01, + TPM2_MSO_SESSION = 0x02, + TPM2_MSO_POLICY = 0x03, + TPM2_MSO_PERMANENT = 0x40, + TPM2_MSO_VOLATILE = 0x80, + TPM2_MSO_PERSISTENT = 0x81, +}; + +static inline enum tpm2_mso_type tpm2_handle_mso(u32 handle) +{ + return handle >> 24; +} + enum tpm2_capabilities { TPM2_CAP_HANDLES = 1, TPM2_CAP_COMMANDS = 2, @@ -284,6 +347,7 @@ enum tpm_chip_flags { TPM_CHIP_FLAG_FIRMWARE_UPGRADE = BIT(7), TPM_CHIP_FLAG_SUSPENDED = BIT(8), TPM_CHIP_FLAG_HWRNG_DISABLED = BIT(9), + TPM_CHIP_FLAG_DISABLE = BIT(10), }; #define to_tpm_chip(d) container_of(d, struct tpm_chip, dev) @@ -297,28 +361,46 @@ struct tpm_header { }; } __packed; -/* A string buffer type for constructing TPM commands. This is based on the - * ideas of string buffer code in security/keys/trusted.h but is heap based - * in order to keep the stack usage minimal. - */ - enum tpm_buf_flags { + /* the capacity exceeded: */ TPM_BUF_OVERFLOW = BIT(0), + /* TPM2B format: */ + TPM_BUF_TPM2B = BIT(1), + /* read out of boundary: */ + TPM_BUF_BOUNDARY_ERROR = BIT(2), }; +/* + * A string buffer type for constructing TPM commands. + */ struct tpm_buf { - unsigned int flags; + u32 flags; + u32 length; u8 *data; + u8 handles; }; enum tpm2_object_attributes { TPM2_OA_FIXED_TPM = BIT(1), + TPM2_OA_ST_CLEAR = BIT(2), TPM2_OA_FIXED_PARENT = BIT(4), + TPM2_OA_SENSITIVE_DATA_ORIGIN = BIT(5), TPM2_OA_USER_WITH_AUTH = BIT(6), + TPM2_OA_ADMIN_WITH_POLICY = BIT(7), + TPM2_OA_NO_DA = BIT(10), + TPM2_OA_ENCRYPTED_DUPLICATION = BIT(11), + TPM2_OA_RESTRICTED = BIT(16), + TPM2_OA_DECRYPT = BIT(17), + TPM2_OA_SIGN = BIT(18), }; enum tpm2_session_attributes { TPM2_SA_CONTINUE_SESSION = BIT(0), + TPM2_SA_AUDIT_EXCLUSIVE = BIT(1), + TPM2_SA_AUDIT_RESET = BIT(3), + TPM2_SA_DECRYPT = BIT(5), + TPM2_SA_ENCRYPT = BIT(6), + TPM2_SA_AUDIT = BIT(7), }; struct tpm2_hash { @@ -326,84 +408,20 @@ struct tpm2_hash { unsigned int tpm_id; }; -static inline void tpm_buf_reset(struct tpm_buf *buf, u16 tag, u32 ordinal) -{ - struct tpm_header *head = (struct tpm_header *)buf->data; - - head->tag = cpu_to_be16(tag); - head->length = cpu_to_be32(sizeof(*head)); - head->ordinal = cpu_to_be32(ordinal); -} - -static inline int tpm_buf_init(struct tpm_buf *buf, u16 tag, u32 ordinal) -{ - buf->data = (u8 *)__get_free_page(GFP_KERNEL); - if (!buf->data) - return -ENOMEM; - - buf->flags = 0; - tpm_buf_reset(buf, tag, ordinal); - return 0; -} - -static inline void tpm_buf_destroy(struct tpm_buf *buf) -{ - free_page((unsigned long)buf->data); -} - -static inline u32 tpm_buf_length(struct tpm_buf *buf) -{ - struct tpm_header *head = (struct tpm_header *)buf->data; - - return be32_to_cpu(head->length); -} - -static inline u16 tpm_buf_tag(struct tpm_buf *buf) -{ - struct tpm_header *head = (struct tpm_header *)buf->data; - - return be16_to_cpu(head->tag); -} - -static inline void tpm_buf_append(struct tpm_buf *buf, - const unsigned char *new_data, - unsigned int new_len) -{ - struct tpm_header *head = (struct tpm_header *)buf->data; - u32 len = tpm_buf_length(buf); - - /* Return silently if overflow has already happened. */ - if (buf->flags & TPM_BUF_OVERFLOW) - return; - - if ((len + new_len) > PAGE_SIZE) { - WARN(1, "tpm_buf: overflow\n"); - buf->flags |= TPM_BUF_OVERFLOW; - return; - } - - memcpy(&buf->data[len], new_data, new_len); - head->length = cpu_to_be32(len + new_len); -} - -static inline void tpm_buf_append_u8(struct tpm_buf *buf, const u8 value) -{ - tpm_buf_append(buf, &value, 1); -} - -static inline void tpm_buf_append_u16(struct tpm_buf *buf, const u16 value) -{ - __be16 value2 = cpu_to_be16(value); - - tpm_buf_append(buf, (u8 *) &value2, 2); -} - -static inline void tpm_buf_append_u32(struct tpm_buf *buf, const u32 value) -{ - __be32 value2 = cpu_to_be32(value); - - tpm_buf_append(buf, (u8 *) &value2, 4); -} +int tpm_buf_init(struct tpm_buf *buf, u16 tag, u32 ordinal); +void tpm_buf_reset(struct tpm_buf *buf, u16 tag, u32 ordinal); +int tpm_buf_init_sized(struct tpm_buf *buf); +void tpm_buf_reset_sized(struct tpm_buf *buf); +void tpm_buf_destroy(struct tpm_buf *buf); +u32 tpm_buf_length(struct tpm_buf *buf); +void tpm_buf_append(struct tpm_buf *buf, const u8 *new_data, u16 new_length); +void tpm_buf_append_u8(struct tpm_buf *buf, const u8 value); +void tpm_buf_append_u16(struct tpm_buf *buf, const u16 value); +void tpm_buf_append_u32(struct tpm_buf *buf, const u32 value); +u8 tpm_buf_read_u8(struct tpm_buf *buf, off_t *offset); +u16 tpm_buf_read_u16(struct tpm_buf *buf, off_t *offset); +u32 tpm_buf_read_u32(struct tpm_buf *buf, off_t *offset); +void tpm_buf_append_handle(struct tpm_chip *chip, struct tpm_buf *buf, u32 handle); /* * Check if TPM device is in the firmware upgrade mode. @@ -415,7 +433,7 @@ static inline bool tpm_is_firmware_upgrade(struct tpm_chip *chip) static inline u32 tpm2_rc_value(u32 rc) { - return (rc & BIT(7)) ? rc & 0xff : rc; + return (rc & BIT(7)) ? rc & 0xbf : rc; } #if defined(CONFIG_TCG_TPM) || defined(CONFIG_TCG_TPM_MODULE) @@ -429,10 +447,19 @@ extern int tpm_pcr_read(struct tpm_chip *chip, u32 pcr_idx, struct tpm_digest *digest); extern int tpm_pcr_extend(struct tpm_chip *chip, u32 pcr_idx, struct tpm_digest *digests); -extern int tpm_send(struct tpm_chip *chip, void *cmd, size_t buflen); extern int tpm_get_random(struct tpm_chip *chip, u8 *data, size_t max); extern struct tpm_chip *tpm_default_chip(void); void tpm2_flush_context(struct tpm_chip *chip, u32 handle); + +static inline void tpm_buf_append_empty_auth(struct tpm_buf *buf, u32 handle) +{ + /* simple authorization for empty auth */ + tpm_buf_append_u32(buf, 9); /* total length of auth */ + tpm_buf_append_u32(buf, handle); + tpm_buf_append_u16(buf, 0); /* nonce len */ + tpm_buf_append_u8(buf, 0); /* attributes */ + tpm_buf_append_u16(buf, 0); /* hmac len */ +} #else static inline int tpm_is_tpm2(struct tpm_chip *chip) { @@ -450,10 +477,6 @@ static inline int tpm_pcr_extend(struct tpm_chip *chip, u32 pcr_idx, return -ENODEV; } -static inline int tpm_send(struct tpm_chip *chip, void *cmd, size_t buflen) -{ - return -ENODEV; -} static inline int tpm_get_random(struct tpm_chip *chip, u8 *data, size_t max) { return -ENODEV; @@ -463,5 +486,79 @@ static inline struct tpm_chip *tpm_default_chip(void) { return NULL; } + +static inline void tpm_buf_append_empty_auth(struct tpm_buf *buf, u32 handle) +{ +} +#endif + +static inline struct tpm2_auth *tpm2_chip_auth(struct tpm_chip *chip) +{ +#ifdef CONFIG_TCG_TPM2_HMAC + return chip->auth; +#else + return NULL; #endif +} + +void tpm_buf_append_name(struct tpm_chip *chip, struct tpm_buf *buf, + u32 handle, u8 *name); +void tpm_buf_append_hmac_session(struct tpm_chip *chip, struct tpm_buf *buf, + u8 attributes, u8 *passphrase, + int passphraselen); +void tpm_buf_append_auth(struct tpm_chip *chip, struct tpm_buf *buf, + u8 attributes, u8 *passphrase, int passphraselen); +static inline void tpm_buf_append_hmac_session_opt(struct tpm_chip *chip, + struct tpm_buf *buf, + u8 attributes, + u8 *passphrase, + int passphraselen) +{ + struct tpm_header *head; + int offset; + + if (tpm2_chip_auth(chip)) { + tpm_buf_append_hmac_session(chip, buf, attributes, passphrase, passphraselen); + } else { + offset = buf->handles * 4 + TPM_HEADER_SIZE; + head = (struct tpm_header *)buf->data; + + /* + * If the only sessions are optional, the command tag must change to + * TPM2_ST_NO_SESSIONS. + */ + if (tpm_buf_length(buf) == offset) + head->tag = cpu_to_be16(TPM2_ST_NO_SESSIONS); + } +} + +#ifdef CONFIG_TCG_TPM2_HMAC + +int tpm2_start_auth_session(struct tpm_chip *chip); +void tpm_buf_fill_hmac_session(struct tpm_chip *chip, struct tpm_buf *buf); +int tpm_buf_check_hmac_response(struct tpm_chip *chip, struct tpm_buf *buf, + int rc); +void tpm2_end_auth_session(struct tpm_chip *chip); +#else +#include <linux/unaligned.h> + +static inline int tpm2_start_auth_session(struct tpm_chip *chip) +{ + return 0; +} +static inline void tpm2_end_auth_session(struct tpm_chip *chip) +{ +} +static inline void tpm_buf_fill_hmac_session(struct tpm_chip *chip, + struct tpm_buf *buf) +{ +} +static inline int tpm_buf_check_hmac_response(struct tpm_chip *chip, + struct tpm_buf *buf, + int rc) +{ + return rc; +} +#endif /* CONFIG_TCG_TPM2_HMAC */ + #endif diff --git a/include/linux/tpm_eventlog.h b/include/linux/tpm_eventlog.h index 7d68a5cc5881..891368e82558 100644 --- a/include/linux/tpm_eventlog.h +++ b/include/linux/tpm_eventlog.h @@ -157,7 +157,7 @@ struct tcg_algorithm_info { * Return: size of the event on success, 0 on failure */ -static __always_inline int __calc_tpm2_event_size(struct tcg_pcr_event2_head *event, +static __always_inline u32 __calc_tpm2_event_size(struct tcg_pcr_event2_head *event, struct tcg_pcr_event *event_header, bool do_mapping) { diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 6f9bdfb09d1d..5caea596fef0 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -184,7 +184,7 @@ unsigned int tracing_gen_ctx_irq_test(unsigned int irqs_status); enum trace_flag_type { TRACE_FLAG_IRQS_OFF = 0x01, - TRACE_FLAG_IRQS_NOSUPPORT = 0x02, + TRACE_FLAG_NEED_RESCHED_LAZY = 0x02, TRACE_FLAG_NEED_RESCHED = 0x04, TRACE_FLAG_HARDIRQ = 0x08, TRACE_FLAG_SOFTIRQ = 0x10, @@ -193,7 +193,6 @@ enum trace_flag_type { TRACE_FLAG_BH_OFF = 0x80, }; -#ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT static inline unsigned int tracing_gen_ctx_flags(unsigned long irqflags) { unsigned int irq_status = irqs_disabled_flags(irqflags) ? @@ -207,17 +206,6 @@ static inline unsigned int tracing_gen_ctx(void) local_save_flags(irqflags); return tracing_gen_ctx_flags(irqflags); } -#else - -static inline unsigned int tracing_gen_ctx_flags(unsigned long irqflags) -{ - return tracing_gen_ctx_irq_test(TRACE_FLAG_IRQS_NOSUPPORT); -} -static inline unsigned int tracing_gen_ctx(void) -{ - return tracing_gen_ctx_irq_test(TRACE_FLAG_IRQS_NOSUPPORT); -} -#endif static inline unsigned int tracing_gen_ctx_dec(void) { @@ -285,7 +273,8 @@ struct trace_event_fields { const char *name; const int size; const int align; - const int is_signed; + const unsigned int is_signed:1; + unsigned int needs_test:1; const int filter_type; const int len; }; @@ -326,7 +315,6 @@ void *trace_event_buffer_reserve(struct trace_event_buffer *fbuffer, void trace_event_buffer_commit(struct trace_event_buffer *fbuffer); enum { - TRACE_EVENT_FL_FILTERED_BIT, TRACE_EVENT_FL_CAP_ANY_BIT, TRACE_EVENT_FL_NO_SET_FILTER_BIT, TRACE_EVENT_FL_IGNORE_ENABLE_BIT, @@ -337,11 +325,11 @@ enum { TRACE_EVENT_FL_EPROBE_BIT, TRACE_EVENT_FL_FPROBE_BIT, TRACE_EVENT_FL_CUSTOM_BIT, + TRACE_EVENT_FL_TEST_STR_BIT, }; /* * Event flags: - * FILTERED - The event has a filter attached * CAP_ANY - Any user can enable for perf * NO_SET_FILTER - Set when filter has error and is to be ignored * IGNORE_ENABLE - For trace internal events, do not enable with debugfs file @@ -354,9 +342,9 @@ enum { * CUSTOM - Event is a custom event (to be attached to an exsiting tracepoint) * This is set when the custom event has not been attached * to a tracepoint yet, then it is cleared when it is. + * TEST_STR - The event has a "%s" that points to a string outside the event */ enum { - TRACE_EVENT_FL_FILTERED = (1 << TRACE_EVENT_FL_FILTERED_BIT), TRACE_EVENT_FL_CAP_ANY = (1 << TRACE_EVENT_FL_CAP_ANY_BIT), TRACE_EVENT_FL_NO_SET_FILTER = (1 << TRACE_EVENT_FL_NO_SET_FILTER_BIT), TRACE_EVENT_FL_IGNORE_ENABLE = (1 << TRACE_EVENT_FL_IGNORE_ENABLE_BIT), @@ -367,6 +355,7 @@ enum { TRACE_EVENT_FL_EPROBE = (1 << TRACE_EVENT_FL_EPROBE_BIT), TRACE_EVENT_FL_FPROBE = (1 << TRACE_EVENT_FL_FPROBE_BIT), TRACE_EVENT_FL_CUSTOM = (1 << TRACE_EVENT_FL_CUSTOM_BIT), + TRACE_EVENT_FL_TEST_STR = (1 << TRACE_EVENT_FL_TEST_STR_BIT), }; #define TRACE_EVENT_FL_UKPROBE (TRACE_EVENT_FL_KPROBE | TRACE_EVENT_FL_UPROBE) @@ -375,13 +364,12 @@ struct trace_event_call { struct list_head list; struct trace_event_class *class; union { - char *name; + const char *name; /* Set TRACE_EVENT_FL_TRACEPOINT flag when using "tp" */ struct tracepoint *tp; }; struct trace_event event; char *print_fmt; - struct event_filter *filter; /* * Static events can disappear with modules, * where as dynamic ones need their own ref count. @@ -680,11 +668,25 @@ struct trace_event_file { * caching and such. Which is mostly OK ;-) */ unsigned long flags; - atomic_t ref; /* ref count for opened files */ + refcount_t ref; /* ref count for opened files */ atomic_t sm_ref; /* soft-mode reference counter */ atomic_t tm_ref; /* trigger-mode reference counter */ }; +#ifdef CONFIG_HIST_TRIGGERS +extern struct irq_work hist_poll_work; +extern wait_queue_head_t hist_poll_wq; + +static inline void hist_poll_wakeup(void) +{ + if (wq_has_sleeper(&hist_poll_wq)) + irq_work_queue(&hist_poll_work); +} + +#define hist_poll_wait(file, wait) \ + poll_wait(file, &hist_poll_wq, wait) +#endif + #define __TRACE_EVENT_FLAGS(name, value) \ static int __init trace_init_flags_##name(void) \ { \ @@ -765,8 +767,11 @@ unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx); int perf_event_attach_bpf_prog(struct perf_event *event, struct bpf_prog *prog, u64 bpf_cookie); void perf_event_detach_bpf_prog(struct perf_event *event); int perf_event_query_prog_array(struct perf_event *event, void __user *info); -int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog); -int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog); + +struct bpf_raw_tp_link; +int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link); +int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link); + struct bpf_raw_event_map *bpf_get_raw_tracepoint(const char *name); void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp); int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, @@ -794,11 +799,12 @@ perf_event_query_prog_array(struct perf_event *event, void __user *info) { return -EOPNOTSUPP; } -static inline int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *p) +struct bpf_raw_tp_link; +static inline int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link) { return -EOPNOTSUPP; } -static inline int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *p) +static inline int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link) { return -EOPNOTSUPP; } @@ -876,7 +882,6 @@ do { \ struct perf_event; DECLARE_PER_CPU(struct pt_regs, perf_trace_regs); -DECLARE_PER_CPU(int, bpf_kprobe_override); extern int perf_trace_init(struct perf_event *event); extern void perf_trace_destroy(struct perf_event *event); @@ -909,31 +914,31 @@ void *perf_trace_buf_alloc(int size, struct pt_regs **regs, int *rctxp); int perf_event_set_bpf_prog(struct perf_event *event, struct bpf_prog *prog, u64 bpf_cookie); void perf_event_free_bpf_prog(struct perf_event *event); -void bpf_trace_run1(struct bpf_prog *prog, u64 arg1); -void bpf_trace_run2(struct bpf_prog *prog, u64 arg1, u64 arg2); -void bpf_trace_run3(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run1(struct bpf_raw_tp_link *link, u64 arg1); +void bpf_trace_run2(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2); +void bpf_trace_run3(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3); -void bpf_trace_run4(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run4(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4); -void bpf_trace_run5(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run5(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5); -void bpf_trace_run6(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run6(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6); -void bpf_trace_run7(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run7(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7); -void bpf_trace_run8(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run8(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7, u64 arg8); -void bpf_trace_run9(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run9(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7, u64 arg8, u64 arg9); -void bpf_trace_run10(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run10(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7, u64 arg8, u64 arg9, u64 arg10); -void bpf_trace_run11(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run11(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7, u64 arg8, u64 arg9, u64 arg10, u64 arg11); -void bpf_trace_run12(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run12(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7, u64 arg8, u64 arg9, u64 arg10, u64 arg11, u64 arg12); void perf_trace_run_bpf_submit(void *raw_data, int size, int rctx, diff --git a/include/linux/trace_recursion.h b/include/linux/trace_recursion.h index d48cd92d2364..ae04054a1be3 100644 --- a/include/linux/trace_recursion.h +++ b/include/linux/trace_recursion.h @@ -44,35 +44,6 @@ enum { */ TRACE_IRQ_BIT, - /* Set if the function is in the set_graph_function file */ - TRACE_GRAPH_BIT, - - /* - * In the very unlikely case that an interrupt came in - * at a start of graph tracing, and we want to trace - * the function in that interrupt, the depth can be greater - * than zero, because of the preempted start of a previous - * trace. In an even more unlikely case, depth could be 2 - * if a softirq interrupted the start of graph tracing, - * followed by an interrupt preempting a start of graph - * tracing in the softirq, and depth can even be 3 - * if an NMI came in at the start of an interrupt function - * that preempted a softirq start of a function that - * preempted normal context!!!! Luckily, it can't be - * greater than 3, so the next two bits are a mask - * of what the depth is when we set TRACE_GRAPH_BIT - */ - - TRACE_GRAPH_DEPTH_START_BIT, - TRACE_GRAPH_DEPTH_END_BIT, - - /* - * To implement set_graph_notrace, if this bit is set, we ignore - * function graph tracing of called functions, until the return - * function is called to clear it. - */ - TRACE_GRAPH_NOTRACE_BIT, - /* Used to prevent recursion recording from recursing. */ TRACE_RECORD_RECURSION_BIT, }; @@ -81,16 +52,6 @@ enum { #define trace_recursion_clear(bit) do { (current)->trace_recursion &= ~(1<<(bit)); } while (0) #define trace_recursion_test(bit) ((current)->trace_recursion & (1<<(bit))) -#define trace_recursion_depth() \ - (((current)->trace_recursion >> TRACE_GRAPH_DEPTH_START_BIT) & 3) -#define trace_recursion_set_depth(depth) \ - do { \ - current->trace_recursion &= \ - ~(3 << TRACE_GRAPH_DEPTH_START_BIT); \ - current->trace_recursion |= \ - ((depth) & 3) << TRACE_GRAPH_DEPTH_START_BIT; \ - } while (0) - #define TRACE_CONTEXT_BITS 4 #define TRACE_FTRACE_START TRACE_FTRACE_BIT @@ -135,7 +96,7 @@ extern void ftrace_record_recursion(unsigned long ip, unsigned long parent_ip); # define do_ftrace_record_recursion(ip, pip) do { } while (0) #endif -#ifdef CONFIG_ARCH_WANTS_NO_INSTR +#ifdef CONFIG_FTRACE_VALIDATE_RCU_IS_WATCHING # define trace_warn_on_no_rcu(ip) \ ({ \ bool __ret = !rcu_is_watching(); \ diff --git a/include/linux/tracefs.h b/include/linux/tracefs.h index 7a5fe17b6bf9..d03f74658716 100644 --- a/include/linux/tracefs.h +++ b/include/linux/tracefs.h @@ -62,6 +62,8 @@ struct eventfs_file; typedef int (*eventfs_callback)(const char *name, umode_t *mode, void **data, const struct file_operations **fops); +typedef void (*eventfs_release)(const char *name, void *data); + /** * struct eventfs_entry - dynamically created eventfs file call back handler * @name: Then name of the dynamic file in an eventfs directory @@ -72,6 +74,7 @@ typedef int (*eventfs_callback)(const char *name, umode_t *mode, void **data, struct eventfs_entry { const char *name; eventfs_callback callback; + eventfs_release release; }; struct eventfs_inode; diff --git a/include/linux/tracepoint-defs.h b/include/linux/tracepoint-defs.h index 4dc4955f0fbf..aebf0571c736 100644 --- a/include/linux/tracepoint-defs.h +++ b/include/linux/tracepoint-defs.h @@ -29,16 +29,22 @@ struct tracepoint_func { int prio; }; +struct tracepoint_ext { + int (*regfunc)(void); + void (*unregfunc)(void); + /* Flags. */ + unsigned int faultable:1; +}; + struct tracepoint { const char *name; /* Tracepoint name */ - struct static_key key; + struct static_key_false key; struct static_call_key *static_call_key; void *static_call_tramp; void *iterator; void *probestub; - int (*regfunc)(void); - void (*unregfunc)(void); struct tracepoint_func __rcu *funcs; + struct tracepoint_ext *ext; }; #ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS @@ -83,7 +89,7 @@ struct bpf_raw_event_map { #ifdef CONFIG_TRACEPOINTS # define tracepoint_enabled(tp) \ - static_key_false(&(__tracepoint_##tp).key) + static_branch_unlikely(&(__tracepoint_##tp).key) #else # define tracepoint_enabled(tracepoint) false #endif diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 689b6d71590e..a351763e6965 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -16,8 +16,8 @@ #include <linux/srcu.h> #include <linux/errno.h> #include <linux/types.h> -#include <linux/cpumask.h> #include <linux/rcupdate.h> +#include <linux/rcupdate_trace.h> #include <linux/tracepoint-defs.h> #include <linux/static_call.h> @@ -33,8 +33,6 @@ struct trace_eval_map { #define TRACEPOINT_DEFAULT_PRIO 10 -extern struct srcu_struct tracepoint_srcu; - extern int tracepoint_probe_register(struct tracepoint *tp, void *probe, void *data); extern int @@ -65,6 +63,13 @@ struct tp_module { bool trace_module_has_bad_taint(struct module *mod); extern int register_tracepoint_module_notifier(struct notifier_block *nb); extern int unregister_tracepoint_module_notifier(struct notifier_block *nb); +void for_each_module_tracepoint(void (*fct)(struct tracepoint *, + struct module *, void *), + void *priv); +void for_each_tracepoint_in_module(struct module *, + void (*fct)(struct tracepoint *, + struct module *, void *), + void *priv); #else static inline bool trace_module_has_bad_taint(struct module *mod) { @@ -80,22 +85,49 @@ int unregister_tracepoint_module_notifier(struct notifier_block *nb) { return 0; } +static inline +void for_each_module_tracepoint(void (*fct)(struct tracepoint *, + struct module *, void *), + void *priv) +{ +} +static inline +void for_each_tracepoint_in_module(struct module *mod, + void (*fct)(struct tracepoint *, + struct module *, void *), + void *priv) +{ +} #endif /* CONFIG_MODULES */ /* * tracepoint_synchronize_unregister must be called between the last tracepoint * probe unregistration and the end of module exit to make sure there is no * caller executing a probe when it is freed. + * + * An alternative is to use the following for batch reclaim associated + * with a given tracepoint: + * + * - tracepoint_is_faultable() == false: call_rcu() + * - tracepoint_is_faultable() == true: call_rcu_tasks_trace() */ #ifdef CONFIG_TRACEPOINTS static inline void tracepoint_synchronize_unregister(void) { - synchronize_srcu(&tracepoint_srcu); + synchronize_rcu_tasks_trace(); synchronize_rcu(); } +static inline bool tracepoint_is_faultable(struct tracepoint *tp) +{ + return tp->ext && tp->ext->faultable; +} #else static inline void tracepoint_synchronize_unregister(void) { } +static inline bool tracepoint_is_faultable(struct tracepoint *tp) +{ + return false; +} #endif #ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS @@ -178,65 +210,16 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) #endif /* CONFIG_HAVE_STATIC_CALL */ /* - * ARCH_WANTS_NO_INSTR archs are expected to have sanitized entry and idle - * code that disallow any/all tracing/instrumentation when RCU isn't watching. - */ -#ifdef CONFIG_ARCH_WANTS_NO_INSTR -#define RCUIDLE_COND(rcuidle) (rcuidle) -#else -/* srcu can't be used from NMI */ -#define RCUIDLE_COND(rcuidle) (rcuidle && in_nmi()) -#endif - -/* - * it_func[0] is never NULL because there is at least one element in the array - * when the array itself is non NULL. + * Declare an exported function that Rust code can call to trigger this + * tracepoint. This function does not include the static branch; that is done + * in Rust to avoid a function call when the tracepoint is disabled. */ -#define __DO_TRACE(name, args, cond, rcuidle) \ - do { \ - int __maybe_unused __idx = 0; \ - \ - if (!(cond)) \ - return; \ - \ - if (WARN_ONCE(RCUIDLE_COND(rcuidle), \ - "Bad RCU usage for tracepoint")) \ - return; \ - \ - /* keep srcu and sched-rcu usage consistent */ \ - preempt_disable_notrace(); \ - \ - /* \ - * For rcuidle callers, use srcu since sched-rcu \ - * doesn't work from the idle path. \ - */ \ - if (rcuidle) { \ - __idx = srcu_read_lock_notrace(&tracepoint_srcu);\ - ct_irq_enter_irqson(); \ - } \ - \ - __DO_TRACE_CALL(name, TP_ARGS(args)); \ - \ - if (rcuidle) { \ - ct_irq_exit_irqson(); \ - srcu_read_unlock_notrace(&tracepoint_srcu, __idx);\ - } \ - \ - preempt_enable_notrace(); \ - } while (0) - -#ifndef MODULE -#define __DECLARE_TRACE_RCU(name, proto, args, cond) \ - static inline void trace_##name##_rcuidle(proto) \ +#define DEFINE_RUST_DO_TRACE(name, proto, args) +#define __DEFINE_RUST_DO_TRACE(name, proto, args) \ + notrace void rust_do_trace_##name(proto) \ { \ - if (static_key_false(&__tracepoint_##name.key)) \ - __DO_TRACE(name, \ - TP_ARGS(args), \ - TP_CONDITION(cond), 1); \ + __do_trace_##name(args); \ } -#else -#define __DECLARE_TRACE_RCU(name, proto, args, cond) -#endif /* * Make sure the alignment of the structure in the __tracepoints section will @@ -249,23 +232,11 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) * 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) \ +#define __DECLARE_TRACE_COMMON(name, proto, args, data_proto) \ extern int __traceiter_##name(data_proto); \ DECLARE_STATIC_CALL(tp_func_##name, __traceiter_##name); \ extern struct tracepoint __tracepoint_##name; \ - static inline void trace_##name(proto) \ - { \ - if (static_key_false(&__tracepoint_##name.key)) \ - __DO_TRACE(name, \ - TP_ARGS(args), \ - TP_CONDITION(cond), 0); \ - if (IS_ENABLED(CONFIG_LOCKDEP) && (cond)) { \ - WARN_ONCE(!rcu_is_watching(), \ - "RCU not watching for tracepoint"); \ - } \ - } \ - __DECLARE_TRACE_RCU(name, PARAMS(proto), PARAMS(args), \ - PARAMS(cond)) \ + extern void rust_do_trace_##name(proto); \ static inline int \ register_trace_##name(void (*probe)(data_proto), void *data) \ { \ @@ -292,15 +263,55 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) static inline bool \ trace_##name##_enabled(void) \ { \ - return static_key_false(&__tracepoint_##name.key); \ + return static_branch_unlikely(&__tracepoint_##name.key);\ + } + +#define __DECLARE_TRACE(name, proto, args, cond, data_proto) \ + __DECLARE_TRACE_COMMON(name, PARAMS(proto), PARAMS(args), PARAMS(data_proto)) \ + static inline void __do_trace_##name(proto) \ + { \ + if (cond) { \ + guard(preempt_notrace)(); \ + __DO_TRACE_CALL(name, TP_ARGS(args)); \ + } \ + } \ + static inline void trace_##name(proto) \ + { \ + if (static_branch_unlikely(&__tracepoint_##name.key)) \ + __do_trace_##name(args); \ + if (IS_ENABLED(CONFIG_LOCKDEP) && (cond)) { \ + WARN_ONCE(!rcu_is_watching(), \ + "RCU not watching for tracepoint"); \ + } \ + } + +#define __DECLARE_TRACE_SYSCALL(name, proto, args, data_proto) \ + __DECLARE_TRACE_COMMON(name, PARAMS(proto), PARAMS(args), PARAMS(data_proto)) \ + static inline void __do_trace_##name(proto) \ + { \ + guard(rcu_tasks_trace)(); \ + __DO_TRACE_CALL(name, TP_ARGS(args)); \ + } \ + static inline void trace_##name(proto) \ + { \ + might_fault(); \ + if (static_branch_unlikely(&__tracepoint_##name.key)) \ + __do_trace_##name(args); \ + if (IS_ENABLED(CONFIG_LOCKDEP)) { \ + WARN_ONCE(!rcu_is_watching(), \ + "RCU not watching for tracepoint"); \ + } \ } /* * We have no guarantee that gcc and the linker won't up-align the tracepoint * structures, so we create an array of pointers that will be used for iteration * on the tracepoints. + * + * it_func[0] is never NULL because there is at least one element in the array + * when the array itself is non NULL. */ -#define DEFINE_TRACE_FN(_name, _reg, _unreg, proto, args) \ +#define __DEFINE_TRACE_EXT(_name, _ext, proto, args) \ static const char __tpstrtab_##_name[] \ __section("__tracepoints_strings") = #_name; \ extern struct static_call_key STATIC_CALL_KEY(tp_func_##_name); \ @@ -309,14 +320,14 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) struct tracepoint __tracepoint_##_name __used \ __section("__tracepoints") = { \ .name = __tpstrtab_##_name, \ - .key = STATIC_KEY_INIT_FALSE, \ + .key = STATIC_KEY_FALSE_INIT, \ .static_call_key = &STATIC_CALL_KEY(tp_func_##_name), \ .static_call_tramp = STATIC_CALL_TRAMP_ADDR(tp_func_##_name), \ .iterator = &__traceiter_##_name, \ .probestub = &__probestub_##_name, \ - .regfunc = _reg, \ - .unregfunc = _unreg, \ - .funcs = NULL }; \ + .funcs = NULL, \ + .ext = _ext, \ + }; \ __TRACEPOINT_ENTRY(_name); \ int __traceiter_##_name(void *__data, proto) \ { \ @@ -337,10 +348,27 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) void __probestub_##_name(void *__data, proto) \ { \ } \ - DEFINE_STATIC_CALL(tp_func_##_name, __traceiter_##_name); + DEFINE_STATIC_CALL(tp_func_##_name, __traceiter_##_name); \ + DEFINE_RUST_DO_TRACE(_name, TP_PROTO(proto), TP_ARGS(args)) + +#define DEFINE_TRACE_FN(_name, _reg, _unreg, _proto, _args) \ + static struct tracepoint_ext __tracepoint_ext_##_name = { \ + .regfunc = _reg, \ + .unregfunc = _unreg, \ + .faultable = false, \ + }; \ + __DEFINE_TRACE_EXT(_name, &__tracepoint_ext_##_name, PARAMS(_proto), PARAMS(_args)); -#define DEFINE_TRACE(name, proto, args) \ - DEFINE_TRACE_FN(name, NULL, NULL, PARAMS(proto), PARAMS(args)); +#define DEFINE_TRACE_SYSCALL(_name, _reg, _unreg, _proto, _args) \ + static struct tracepoint_ext __tracepoint_ext_##_name = { \ + .regfunc = _reg, \ + .unregfunc = _unreg, \ + .faultable = true, \ + }; \ + __DEFINE_TRACE_EXT(_name, &__tracepoint_ext_##_name, PARAMS(_proto), PARAMS(_args)); + +#define DEFINE_TRACE(_name, _proto, _args) \ + __DEFINE_TRACE_EXT(_name, NULL, PARAMS(_proto), PARAMS(_args)); #define EXPORT_TRACEPOINT_SYMBOL_GPL(name) \ EXPORT_SYMBOL_GPL(__tracepoint_##name); \ @@ -353,11 +381,9 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) #else /* !TRACEPOINTS_ENABLED */ -#define __DECLARE_TRACE(name, proto, args, cond, data_proto) \ +#define __DECLARE_TRACE_COMMON(name, proto, args, data_proto) \ static inline void trace_##name(proto) \ { } \ - static inline void trace_##name##_rcuidle(proto) \ - { } \ static inline int \ register_trace_##name(void (*probe)(data_proto), \ void *data) \ @@ -379,7 +405,14 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) return false; \ } +#define __DECLARE_TRACE(name, proto, args, cond, data_proto) \ + __DECLARE_TRACE_COMMON(name, PARAMS(proto), PARAMS(args), PARAMS(data_proto)) + +#define __DECLARE_TRACE_SYSCALL(name, proto, args, data_proto) \ + __DECLARE_TRACE_COMMON(name, PARAMS(proto), PARAMS(args), PARAMS(data_proto)) + #define DEFINE_TRACE_FN(name, reg, unreg, proto, args) +#define DEFINE_TRACE_SYSCALL(name, reg, unreg, proto, args) #define DEFINE_TRACE(name, proto, args) #define EXPORT_TRACEPOINT_SYMBOL_GPL(name) #define EXPORT_TRACEPOINT_SYMBOL(name) @@ -440,6 +473,10 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) cpu_online(raw_smp_processor_id()) && (PARAMS(cond)), \ PARAMS(void *__data, proto)) +#define DECLARE_TRACE_SYSCALL(name, proto, args) \ + __DECLARE_TRACE_SYSCALL(name, PARAMS(proto), PARAMS(args), \ + PARAMS(void *__data, proto)) + #define TRACE_EVENT_FLAGS(event, flag) #define TRACE_EVENT_PERF_PERM(event, expr...) @@ -577,6 +614,9 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) struct, assign, print) \ DECLARE_TRACE_CONDITION(name, PARAMS(proto), \ PARAMS(args), PARAMS(cond)) +#define TRACE_EVENT_SYSCALL(name, proto, args, struct, assign, \ + print, reg, unreg) \ + DECLARE_TRACE_SYSCALL(name, PARAMS(proto), PARAMS(args)) #define TRACE_EVENT_FLAGS(event, flag) diff --git a/include/linux/tsm.h b/include/linux/tsm.h index de8324a2223c..11b0c525be30 100644 --- a/include/linux/tsm.h +++ b/include/linux/tsm.h @@ -4,6 +4,7 @@ #include <linux/sizes.h> #include <linux/types.h> +#include <linux/uuid.h> #define TSM_INBLOB_MAX 64 #define TSM_OUTBLOB_MAX SZ_32K @@ -19,11 +20,17 @@ * @privlevel: optional privilege level to associate with @outblob * @inblob_len: sizeof @inblob * @inblob: arbitrary input data + * @service_provider: optional name of where to obtain the tsm report blob + * @service_guid: optional service-provider service guid to attest + * @service_manifest_version: optional service-provider service manifest version requested */ struct tsm_desc { unsigned int privlevel; size_t inblob_len; u8 inblob[TSM_INBLOB_MAX]; + char *service_provider; + guid_t service_guid; + unsigned int service_manifest_version; }; /** @@ -33,6 +40,8 @@ struct tsm_desc { * @outblob: generated evidence to provider to the attestation agent * @auxblob_len: sizeof(@auxblob) * @auxblob: (optional) auxiliary data to the report (e.g. certificate data) + * @manifestblob_len: sizeof(@manifestblob) + * @manifestblob: (optional) manifest data associated with the report */ struct tsm_report { struct tsm_desc desc; @@ -40,6 +49,42 @@ struct tsm_report { u8 *outblob; size_t auxblob_len; u8 *auxblob; + size_t manifestblob_len; + u8 *manifestblob; +}; + +/** + * enum tsm_attr_index - index used to reference report attributes + * @TSM_REPORT_GENERATION: index of the report generation number attribute + * @TSM_REPORT_PROVIDER: index of the provider name attribute + * @TSM_REPORT_PRIVLEVEL: index of the desired privilege level attribute + * @TSM_REPORT_PRIVLEVEL_FLOOR: index of the minimum allowed privileg level attribute + * @TSM_REPORT_SERVICE_PROVIDER: index of the service provider identifier attribute + * @TSM_REPORT_SERVICE_GUID: index of the service GUID attribute + * @TSM_REPORT_SERVICE_MANIFEST_VER: index of the service manifest version attribute + */ +enum tsm_attr_index { + TSM_REPORT_GENERATION, + TSM_REPORT_PROVIDER, + TSM_REPORT_PRIVLEVEL, + TSM_REPORT_PRIVLEVEL_FLOOR, + TSM_REPORT_SERVICE_PROVIDER, + TSM_REPORT_SERVICE_GUID, + TSM_REPORT_SERVICE_MANIFEST_VER, +}; + +/** + * enum tsm_bin_attr_index - index used to reference binary report attributes + * @TSM_REPORT_INBLOB: index of the binary report input attribute + * @TSM_REPORT_OUTBLOB: index of the binary report output attribute + * @TSM_REPORT_AUXBLOB: index of the binary auxiliary data attribute + * @TSM_REPORT_MANIFESTBLOB: index of the binary manifest data attribute + */ +enum tsm_bin_attr_index { + TSM_REPORT_INBLOB, + TSM_REPORT_OUTBLOB, + TSM_REPORT_AUXBLOB, + TSM_REPORT_MANIFESTBLOB, }; /** @@ -48,22 +93,20 @@ struct tsm_report { * @privlevel_floor: convey base privlevel for nested scenarios * @report_new: Populate @report with the report blob and auxblob * (optional), return 0 on successful population, or -errno otherwise + * @report_attr_visible: show or hide a report attribute entry + * @report_bin_attr_visible: show or hide a report binary attribute entry * * Implementation specific ops, only one is expected to be registered at * a time i.e. only one of "sev-guest", "tdx-guest", etc. */ struct tsm_ops { const char *name; - const unsigned int privlevel_floor; + unsigned int privlevel_floor; int (*report_new)(struct tsm_report *report, void *data); + bool (*report_attr_visible)(int n); + bool (*report_bin_attr_visible)(int n); }; -extern const struct config_item_type tsm_report_default_type; - -/* publish @privlevel, @privlevel_floor, and @auxblob attributes */ -extern const struct config_item_type tsm_report_extra_type; - -int tsm_register(const struct tsm_ops *ops, void *priv, - const struct config_item_type *type); +int tsm_register(const struct tsm_ops *ops, void *priv); int tsm_unregister(const struct tsm_ops *ops); #endif /* __TSM_H */ diff --git a/include/linux/tty.h b/include/linux/tty.h index 2b2e6f0a54d6..2372f9357240 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -145,15 +145,12 @@ struct tty_operations; * @count: count of open processes, reaching zero cancels all the work for * this tty and drops a @kref too (but does not free this tty) * @winsize: size of the terminal "window" (cf. @winsize_mutex) - * @flow: flow settings grouped together, see also @flow.unused + * @flow: flow settings grouped together * @flow.lock: lock for @flow members * @flow.stopped: tty stopped/started by stop_tty()/start_tty() * @flow.tco_stopped: tty stopped/started by %TCOOFF/%TCOON ioctls (it has * precedence over @flow.stopped) - * @flow.unused: alignment for Alpha, so that no members other than @flow.* are - * modified by the same 64b word store. The @flow's __aligned is - * there for the very same reason. - * @ctrl: control settings grouped together, see also @ctrl.unused + * @ctrl: control settings grouped together * @ctrl.lock: lock for @ctrl members * @ctrl.pgrp: process group of this tty (setpgrp(2)) * @ctrl.session: session of this tty (setsid(2)). Writes are protected by both @@ -161,7 +158,6 @@ struct tty_operations; * them. * @ctrl.pktstatus: packet mode status (bitwise OR of %TIOCPKT_ constants) * @ctrl.packet: packet mode enabled - * @ctrl.unused: alignment for Alpha, see @flow.unused for explanation * @hw_stopped: not controlled by the tty layer, under @driver's control for CTS * handling * @receive_room: bytes permitted to feed to @ldisc without any being lost @@ -216,8 +212,7 @@ struct tty_struct { spinlock_t lock; bool stopped; bool tco_stopped; - unsigned long unused[0]; - } __aligned(sizeof(unsigned long)) flow; + } flow; struct { struct pid *pgrp; @@ -225,8 +220,7 @@ struct tty_struct { spinlock_t lock; unsigned char pktstatus; bool packet; - unsigned long unused[0]; - } __aligned(sizeof(unsigned long)) ctrl; + } ctrl; bool hw_stopped; bool closing; diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index 7372124fbf90..d4cdc089f6c3 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -154,6 +154,13 @@ struct serial_struct; * * Optional. Called under the @tty->termios_rwsem. May sleep. * + * @ldisc_ok: ``int ()(struct tty_struct *tty, int ldisc)`` + * + * This routine allows the @tty driver to decide if it can deal + * with a particular @ldisc. + * + * Optional. Called under the @tty->ldisc_sem and @tty->termios_rwsem. + * * @set_ldisc: ``void ()(struct tty_struct *tty)`` * * This routine allows the @tty driver to be notified when the device's @@ -313,7 +320,7 @@ struct serial_struct; * * @poll_init: ``int ()(struct tty_driver *driver, int line, char *options)`` * - * kgdboc support (Documentation/dev-tools/kgdb.rst). This routine is + * kgdboc support (Documentation/process/debugging/kgdb.rst). This routine is * called to initialize the HW for later use by calling @poll_get_char or * @poll_put_char. * @@ -372,6 +379,7 @@ struct tty_operations { void (*hangup)(struct tty_struct *tty); int (*break_ctl)(struct tty_struct *tty, int state); void (*flush_buffer)(struct tty_struct *tty); + int (*ldisc_ok)(struct tty_struct *tty, int ldisc); void (*set_ldisc)(struct tty_struct *tty); void (*wait_until_sent)(struct tty_struct *tty, int timeout); void (*send_xchar)(struct tty_struct *tty, u8 ch); diff --git a/include/linux/turris-omnia-mcu-interface.h b/include/linux/turris-omnia-mcu-interface.h new file mode 100644 index 000000000000..38b45ab00053 --- /dev/null +++ b/include/linux/turris-omnia-mcu-interface.h @@ -0,0 +1,397 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * CZ.NIC's Turris Omnia MCU I2C interface commands definitions + * + * 2024 by Marek Behún <kabel@kernel.org> + */ + +#ifndef __TURRIS_OMNIA_MCU_INTERFACE_H +#define __TURRIS_OMNIA_MCU_INTERFACE_H + +#include <linux/bitfield.h> +#include <linux/bitops.h> +#include <linux/types.h> +#include <linux/unaligned.h> +#include <asm/byteorder.h> + +enum omnia_commands_e { + OMNIA_CMD_GET_STATUS_WORD = 0x01, /* slave sends status word back */ + OMNIA_CMD_GENERAL_CONTROL = 0x02, + OMNIA_CMD_LED_MODE = 0x03, /* default/user */ + OMNIA_CMD_LED_STATE = 0x04, /* LED on/off */ + OMNIA_CMD_LED_COLOR = 0x05, /* LED number + RED + GREEN + BLUE */ + OMNIA_CMD_USER_VOLTAGE = 0x06, + OMNIA_CMD_SET_BRIGHTNESS = 0x07, + OMNIA_CMD_GET_BRIGHTNESS = 0x08, + OMNIA_CMD_GET_RESET = 0x09, + OMNIA_CMD_GET_FW_VERSION_APP = 0x0A, /* 20B git hash number */ + OMNIA_CMD_SET_WATCHDOG_STATE = 0x0B, /* 0 - disable + * 1 - enable / ping + * after boot watchdog is started + * with 2 minutes timeout + */ + + /* OMNIA_CMD_WATCHDOG_STATUS = 0x0C, not implemented anymore */ + + OMNIA_CMD_GET_WATCHDOG_STATE = 0x0D, + OMNIA_CMD_GET_FW_VERSION_BOOT = 0x0E, /* 20B Git hash number */ + OMNIA_CMD_GET_FW_CHECKSUM = 0x0F, /* 4B length, 4B checksum */ + + /* available if FEATURES_SUPPORTED bit set in status word */ + OMNIA_CMD_GET_FEATURES = 0x10, + + /* available if EXT_CMD bit set in features */ + OMNIA_CMD_GET_EXT_STATUS_DWORD = 0x11, + OMNIA_CMD_EXT_CONTROL = 0x12, + OMNIA_CMD_GET_EXT_CONTROL_STATUS = 0x13, + + /* available if NEW_INT_API bit set in features */ + OMNIA_CMD_GET_INT_AND_CLEAR = 0x14, + OMNIA_CMD_GET_INT_MASK = 0x15, + OMNIA_CMD_SET_INT_MASK = 0x16, + + /* available if FLASHING bit set in features */ + OMNIA_CMD_FLASH = 0x19, + + /* available if WDT_PING bit set in features */ + OMNIA_CMD_SET_WDT_TIMEOUT = 0x20, + OMNIA_CMD_GET_WDT_TIMELEFT = 0x21, + + /* available if POWEROFF_WAKEUP bit set in features */ + OMNIA_CMD_SET_WAKEUP = 0x22, + OMNIA_CMD_GET_UPTIME_AND_WAKEUP = 0x23, + OMNIA_CMD_POWER_OFF = 0x24, + + /* available if USB_OVC_PROT_SETTING bit set in features */ + OMNIA_CMD_SET_USB_OVC_PROT = 0x25, + OMNIA_CMD_GET_USB_OVC_PROT = 0x26, + + /* available if TRNG bit set in features */ + OMNIA_CMD_TRNG_COLLECT_ENTROPY = 0x28, + + /* available if CRYPTO bit set in features */ + OMNIA_CMD_CRYPTO_GET_PUBLIC_KEY = 0x29, + OMNIA_CMD_CRYPTO_SIGN_MESSAGE = 0x2A, + OMNIA_CMD_CRYPTO_COLLECT_SIGNATURE = 0x2B, + + /* available if BOARD_INFO it set in features */ + OMNIA_CMD_BOARD_INFO_GET = 0x2C, + OMNIA_CMD_BOARD_INFO_BURN = 0x2D, + + /* available only at address 0x2b (LED-controller) */ + /* available only if LED_GAMMA_CORRECTION bit set in features */ + OMNIA_CMD_SET_GAMMA_CORRECTION = 0x30, + OMNIA_CMD_GET_GAMMA_CORRECTION = 0x31, + + /* available only at address 0x2b (LED-controller) */ + /* available only if PER_LED_CORRECTION bit set in features */ + /* available only if FROM_BIT_16_INVALID bit NOT set in features */ + OMNIA_CMD_SET_LED_CORRECTIONS = 0x32, + OMNIA_CMD_GET_LED_CORRECTIONS = 0x33, +}; + +enum omnia_flashing_commands_e { + OMNIA_FLASH_CMD_UNLOCK = 0x01, + OMNIA_FLASH_CMD_SIZE_AND_CSUM = 0x02, + OMNIA_FLASH_CMD_PROGRAM = 0x03, + OMNIA_FLASH_CMD_RESET = 0x04, +}; + +enum omnia_sts_word_e { + OMNIA_STS_MCU_TYPE_MASK = GENMASK(1, 0), + OMNIA_STS_MCU_TYPE_STM32 = FIELD_PREP_CONST(OMNIA_STS_MCU_TYPE_MASK, 0), + OMNIA_STS_MCU_TYPE_GD32 = FIELD_PREP_CONST(OMNIA_STS_MCU_TYPE_MASK, 1), + OMNIA_STS_MCU_TYPE_MKL = FIELD_PREP_CONST(OMNIA_STS_MCU_TYPE_MASK, 2), + OMNIA_STS_FEATURES_SUPPORTED = BIT(2), + OMNIA_STS_USER_REGULATOR_NOT_SUPPORTED = BIT(3), + OMNIA_STS_CARD_DET = BIT(4), + OMNIA_STS_MSATA_IND = BIT(5), + OMNIA_STS_USB30_OVC = BIT(6), + OMNIA_STS_USB31_OVC = BIT(7), + OMNIA_STS_USB30_PWRON = BIT(8), + OMNIA_STS_USB31_PWRON = BIT(9), + OMNIA_STS_ENABLE_4V5 = BIT(10), + OMNIA_STS_BUTTON_MODE = BIT(11), + OMNIA_STS_BUTTON_PRESSED = BIT(12), + OMNIA_STS_BUTTON_COUNTER_MASK = GENMASK(15, 13), +}; + +enum omnia_ctl_byte_e { + OMNIA_CTL_LIGHT_RST = BIT(0), + OMNIA_CTL_HARD_RST = BIT(1), + /* BIT(2) is currently reserved */ + OMNIA_CTL_USB30_PWRON = BIT(3), + OMNIA_CTL_USB31_PWRON = BIT(4), + OMNIA_CTL_ENABLE_4V5 = BIT(5), + OMNIA_CTL_BUTTON_MODE = BIT(6), + OMNIA_CTL_BOOTLOADER = BIT(7), +}; + +enum omnia_features_e { + OMNIA_FEAT_PERIPH_MCU = BIT(0), + OMNIA_FEAT_EXT_CMDS = BIT(1), + OMNIA_FEAT_WDT_PING = BIT(2), + OMNIA_FEAT_LED_STATE_EXT_MASK = GENMASK(4, 3), + OMNIA_FEAT_LED_STATE_EXT = FIELD_PREP_CONST(OMNIA_FEAT_LED_STATE_EXT_MASK, 1), + OMNIA_FEAT_LED_STATE_EXT_V32 = FIELD_PREP_CONST(OMNIA_FEAT_LED_STATE_EXT_MASK, 2), + OMNIA_FEAT_LED_GAMMA_CORRECTION = BIT(5), + OMNIA_FEAT_NEW_INT_API = BIT(6), + OMNIA_FEAT_BOOTLOADER = BIT(7), + OMNIA_FEAT_FLASHING = BIT(8), + OMNIA_FEAT_NEW_MESSAGE_API = BIT(9), + OMNIA_FEAT_BRIGHTNESS_INT = BIT(10), + OMNIA_FEAT_POWEROFF_WAKEUP = BIT(11), + OMNIA_FEAT_CAN_OLD_MESSAGE_API = BIT(12), + OMNIA_FEAT_TRNG = BIT(13), + OMNIA_FEAT_CRYPTO = BIT(14), + OMNIA_FEAT_BOARD_INFO = BIT(15), + + /* + * Orginally the features command replied only 16 bits. If more were + * read, either the I2C transaction failed or 0xff bytes were sent. + * Therefore to consider bits 16 - 31 valid, one bit (20) was reserved + * to be zero. + */ + + /* Bits 16 - 19 correspond to bits 0 - 3 of status word */ + OMNIA_FEAT_MCU_TYPE_MASK = GENMASK(17, 16), + OMNIA_FEAT_MCU_TYPE_STM32 = FIELD_PREP_CONST(OMNIA_FEAT_MCU_TYPE_MASK, 0), + OMNIA_FEAT_MCU_TYPE_GD32 = FIELD_PREP_CONST(OMNIA_FEAT_MCU_TYPE_MASK, 1), + OMNIA_FEAT_MCU_TYPE_MKL = FIELD_PREP_CONST(OMNIA_FEAT_MCU_TYPE_MASK, 2), + OMNIA_FEAT_FEATURES_SUPPORTED = BIT(18), + OMNIA_FEAT_USER_REGULATOR_NOT_SUPPORTED = BIT(19), + + /* must not be set */ + OMNIA_FEAT_FROM_BIT_16_INVALID = BIT(20), + + OMNIA_FEAT_PER_LED_CORRECTION = BIT(21), + OMNIA_FEAT_USB_OVC_PROT_SETTING = BIT(22), +}; + +enum omnia_ext_sts_dword_e { + OMNIA_EXT_STS_SFP_nDET = BIT(0), + OMNIA_EXT_STS_LED_STATES_MASK = GENMASK(31, 12), + OMNIA_EXT_STS_WLAN0_MSATA_LED = BIT(12), + OMNIA_EXT_STS_WLAN1_LED = BIT(13), + OMNIA_EXT_STS_WLAN2_LED = BIT(14), + OMNIA_EXT_STS_WPAN0_LED = BIT(15), + OMNIA_EXT_STS_WPAN1_LED = BIT(16), + OMNIA_EXT_STS_WPAN2_LED = BIT(17), + OMNIA_EXT_STS_WAN_LED0 = BIT(18), + OMNIA_EXT_STS_WAN_LED1 = BIT(19), + OMNIA_EXT_STS_LAN0_LED0 = BIT(20), + OMNIA_EXT_STS_LAN0_LED1 = BIT(21), + OMNIA_EXT_STS_LAN1_LED0 = BIT(22), + OMNIA_EXT_STS_LAN1_LED1 = BIT(23), + OMNIA_EXT_STS_LAN2_LED0 = BIT(24), + OMNIA_EXT_STS_LAN2_LED1 = BIT(25), + OMNIA_EXT_STS_LAN3_LED0 = BIT(26), + OMNIA_EXT_STS_LAN3_LED1 = BIT(27), + OMNIA_EXT_STS_LAN4_LED0 = BIT(28), + OMNIA_EXT_STS_LAN4_LED1 = BIT(29), + OMNIA_EXT_STS_LAN5_LED0 = BIT(30), + OMNIA_EXT_STS_LAN5_LED1 = BIT(31), +}; + +enum omnia_ext_ctl_e { + OMNIA_EXT_CTL_nRES_MMC = BIT(0), + OMNIA_EXT_CTL_nRES_LAN = BIT(1), + OMNIA_EXT_CTL_nRES_PHY = BIT(2), + OMNIA_EXT_CTL_nPERST0 = BIT(3), + OMNIA_EXT_CTL_nPERST1 = BIT(4), + OMNIA_EXT_CTL_nPERST2 = BIT(5), + OMNIA_EXT_CTL_PHY_SFP = BIT(6), + OMNIA_EXT_CTL_PHY_SFP_AUTO = BIT(7), + OMNIA_EXT_CTL_nVHV_CTRL = BIT(8), +}; + +enum omnia_int_e { + OMNIA_INT_CARD_DET = BIT(0), + OMNIA_INT_MSATA_IND = BIT(1), + OMNIA_INT_USB30_OVC = BIT(2), + OMNIA_INT_USB31_OVC = BIT(3), + OMNIA_INT_BUTTON_PRESSED = BIT(4), + OMNIA_INT_SFP_nDET = BIT(5), + OMNIA_INT_BRIGHTNESS_CHANGED = BIT(6), + OMNIA_INT_TRNG = BIT(7), + OMNIA_INT_MESSAGE_SIGNED = BIT(8), + + OMNIA_INT_LED_STATES_MASK = GENMASK(31, 12), + OMNIA_INT_WLAN0_MSATA_LED = BIT(12), + OMNIA_INT_WLAN1_LED = BIT(13), + OMNIA_INT_WLAN2_LED = BIT(14), + OMNIA_INT_WPAN0_LED = BIT(15), + OMNIA_INT_WPAN1_LED = BIT(16), + OMNIA_INT_WPAN2_LED = BIT(17), + OMNIA_INT_WAN_LED0 = BIT(18), + OMNIA_INT_WAN_LED1 = BIT(19), + OMNIA_INT_LAN0_LED0 = BIT(20), + OMNIA_INT_LAN0_LED1 = BIT(21), + OMNIA_INT_LAN1_LED0 = BIT(22), + OMNIA_INT_LAN1_LED1 = BIT(23), + OMNIA_INT_LAN2_LED0 = BIT(24), + OMNIA_INT_LAN2_LED1 = BIT(25), + OMNIA_INT_LAN3_LED0 = BIT(26), + OMNIA_INT_LAN3_LED1 = BIT(27), + OMNIA_INT_LAN4_LED0 = BIT(28), + OMNIA_INT_LAN4_LED1 = BIT(29), + OMNIA_INT_LAN5_LED0 = BIT(30), + OMNIA_INT_LAN5_LED1 = BIT(31), +}; + +enum omnia_cmd_led_mode_e { + OMNIA_CMD_LED_MODE_LED_MASK = GENMASK(3, 0), + OMNIA_CMD_LED_MODE_USER = BIT(4), +}; + +#define OMNIA_CMD_LED_MODE_LED(_l) FIELD_PREP(OMNIA_CMD_LED_MODE_LED_MASK, _l) + +enum omnia_cmd_led_state_e { + OMNIA_CMD_LED_STATE_LED_MASK = GENMASK(3, 0), + OMNIA_CMD_LED_STATE_ON = BIT(4), +}; + +#define OMNIA_CMD_LED_STATE_LED(_l) FIELD_PREP(OMNIA_CMD_LED_STATE_LED_MASK, _l) + +enum omnia_cmd_poweroff_e { + OMNIA_CMD_POWER_OFF_POWERON_BUTTON = BIT(0), + OMNIA_CMD_POWER_OFF_MAGIC = 0xdead, +}; + +enum omnia_cmd_usb_ovc_prot_e { + OMNIA_CMD_xET_USB_OVC_PROT_PORT_MASK = GENMASK(3, 0), + OMNIA_CMD_xET_USB_OVC_PROT_ENABLE = BIT(4), +}; + +/* Command execution functions */ + +struct i2c_client; + +int omnia_cmd_write_read(const struct i2c_client *client, + void *cmd, unsigned int cmd_len, + void *reply, unsigned int reply_len); + +static inline int omnia_cmd_write(const struct i2c_client *client, void *cmd, + unsigned int len) +{ + return omnia_cmd_write_read(client, cmd, len, NULL, 0); +} + +static inline int omnia_cmd_write_u8(const struct i2c_client *client, u8 cmd, + u8 val) +{ + u8 buf[2] = { cmd, val }; + + return omnia_cmd_write(client, buf, sizeof(buf)); +} + +static inline int omnia_cmd_write_u16(const struct i2c_client *client, u8 cmd, + u16 val) +{ + u8 buf[3]; + + buf[0] = cmd; + put_unaligned_le16(val, &buf[1]); + + return omnia_cmd_write(client, buf, sizeof(buf)); +} + +static inline int omnia_cmd_write_u32(const struct i2c_client *client, u8 cmd, + u32 val) +{ + u8 buf[5]; + + buf[0] = cmd; + put_unaligned_le32(val, &buf[1]); + + return omnia_cmd_write(client, buf, sizeof(buf)); +} + +static inline int omnia_cmd_read(const struct i2c_client *client, u8 cmd, + void *reply, unsigned int len) +{ + return omnia_cmd_write_read(client, &cmd, 1, reply, len); +} + +static inline unsigned int +omnia_compute_reply_length(unsigned long mask, bool interleaved, + unsigned int offset) +{ + if (!mask) + return 0; + + return ((__fls(mask) >> 3) << interleaved) + 1 + offset; +} + +/* Returns 0 on success */ +static inline int omnia_cmd_read_bits(const struct i2c_client *client, u8 cmd, + unsigned long bits, unsigned long *dst) +{ + __le32 reply; + int err; + + if (!bits) { + *dst = 0; + return 0; + } + + err = omnia_cmd_read(client, cmd, &reply, + omnia_compute_reply_length(bits, false, 0)); + if (err) + return err; + + *dst = le32_to_cpu(reply) & bits; + + return 0; +} + +static inline int omnia_cmd_read_bit(const struct i2c_client *client, u8 cmd, + unsigned long bit) +{ + unsigned long reply; + int err; + + err = omnia_cmd_read_bits(client, cmd, bit, &reply); + if (err) + return err; + + return !!reply; +} + +static inline int omnia_cmd_read_u32(const struct i2c_client *client, u8 cmd, + u32 *dst) +{ + __le32 reply; + int err; + + err = omnia_cmd_read(client, cmd, &reply, sizeof(reply)); + if (err) + return err; + + *dst = le32_to_cpu(reply); + + return 0; +} + +static inline int omnia_cmd_read_u16(const struct i2c_client *client, u8 cmd, + u16 *dst) +{ + __le16 reply; + int err; + + err = omnia_cmd_read(client, cmd, &reply, sizeof(reply)); + if (err) + return err; + + *dst = le16_to_cpu(reply); + + return 0; +} + +static inline int omnia_cmd_read_u8(const struct i2c_client *client, u8 cmd, + u8 *reply) +{ + return omnia_cmd_read(client, cmd, reply, sizeof(*reply)); +} + +#endif /* __TURRIS_OMNIA_MCU_INTERFACE_H */ diff --git a/include/linux/types.h b/include/linux/types.h index 2bc8766ba20c..1c509ce8f7f6 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -43,7 +43,7 @@ typedef unsigned long uintptr_t; typedef long intptr_t; #ifdef CONFIG_HAVE_UID16 -/* This is defined by include/asm-{arch}/posix_types.h */ +/* This is defined by arch/{arch}/include/asm/posix_types.h */ typedef __kernel_old_uid_t old_uid_t; typedef __kernel_old_gid_t old_gid_t; #endif /* CONFIG_UID16 */ @@ -115,8 +115,9 @@ typedef u64 u_int64_t; typedef s64 int64_t; #endif -/* this is a special 64bit data type that is 8-byte aligned */ +/* These are the special 64-bit data types that are 8-byte aligned */ #define aligned_u64 __aligned_u64 +#define aligned_s64 __aligned_s64 #define aligned_be64 __aligned_be64 #define aligned_le64 __aligned_le64 diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 3064314f4832..e9c702c1908d 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -5,6 +5,7 @@ #include <linux/fault-inject-usercopy.h> #include <linux/instrumented.h> #include <linux/minmax.h> +#include <linux/nospec.h> #include <linux/sched.h> #include <linux/thread_info.h> @@ -32,6 +33,14 @@ }) #endif +#ifdef masked_user_access_begin + #define can_do_masked_user_access() 1 +#else + #define can_do_masked_user_access() 0 + #define masked_user_access_begin(src) NULL + #define mask_user_address(src) (src) +#endif + /* * Architectures should provide two primitives (raw_copy_{to,from}_user()) * and get rid of their private instances of copy_{to,from}_user() and @@ -138,29 +147,47 @@ __copy_to_user(void __user *to, const void *from, unsigned long n) return raw_copy_to_user(to, from, n); } -#ifdef INLINE_COPY_FROM_USER +/* + * Architectures that #define INLINE_COPY_TO_USER use this function + * directly in the normal copy_to/from_user(), the other ones go + * through an extern _copy_to/from_user(), which expands the same code + * here. + * + * Rust code always uses the extern definition. + */ static inline __must_check unsigned long -_copy_from_user(void *to, const void __user *from, unsigned long n) +_inline_copy_from_user(void *to, const void __user *from, unsigned long n) { unsigned long res = n; might_fault(); - if (!should_fail_usercopy() && likely(access_ok(from, n))) { - instrument_copy_from_user_before(to, from, n); - res = raw_copy_from_user(to, from, n); - instrument_copy_from_user_after(to, from, n, res); + if (should_fail_usercopy()) + goto fail; + if (can_do_masked_user_access()) + from = mask_user_address(from); + else { + if (!access_ok(from, n)) + goto fail; + /* + * Ensure that bad access_ok() speculation will not + * lead to nasty side effects *after* the copy is + * finished: + */ + barrier_nospec(); } - if (unlikely(res)) - memset(to + (n - res), 0, res); + instrument_copy_from_user_before(to, from, n); + res = raw_copy_from_user(to, from, n); + instrument_copy_from_user_after(to, from, n, res); + if (likely(!res)) + return 0; +fail: + memset(to + (n - res), 0, res); return res; } -#else extern __must_check unsigned long _copy_from_user(void *, const void __user *, unsigned long); -#endif -#ifdef INLINE_COPY_TO_USER static inline __must_check unsigned long -_copy_to_user(void __user *to, const void *from, unsigned long n) +_inline_copy_to_user(void __user *to, const void *from, unsigned long n) { might_fault(); if (should_fail_usercopy()) @@ -171,25 +198,32 @@ _copy_to_user(void __user *to, const void *from, unsigned long n) } return n; } -#else extern __must_check unsigned long _copy_to_user(void __user *, const void *, unsigned long); -#endif static __always_inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n) { - if (check_copy_size(to, n, false)) - n = _copy_from_user(to, from, n); - return n; + if (!check_copy_size(to, n, false)) + return n; +#ifdef INLINE_COPY_FROM_USER + return _inline_copy_from_user(to, from, n); +#else + return _copy_from_user(to, from, n); +#endif } static __always_inline unsigned long __must_check copy_to_user(void __user *to, const void *from, unsigned long n) { - if (check_copy_size(from, n, true)) - n = _copy_to_user(to, from, n); - return n; + if (!check_copy_size(from, n, true)) + return n; + +#ifdef INLINE_COPY_TO_USER + return _inline_copy_to_user(to, from, n); +#else + return _copy_to_user(to, from, n); +#endif } #ifndef copy_mc_to_kernel @@ -369,6 +403,103 @@ copy_struct_from_user(void *dst, size_t ksize, const void __user *src, return 0; } +/** + * copy_struct_to_user: copy a struct to userspace + * @dst: Destination address, in userspace. This buffer must be @ksize + * bytes long. + * @usize: (Alleged) size of @dst struct. + * @src: Source address, in kernel space. + * @ksize: Size of @src struct. + * @ignored_trailing: Set to %true if there was a non-zero byte in @src that + * userspace cannot see because they are using an smaller struct. + * + * Copies a struct from kernel space to userspace, in a way that guarantees + * backwards-compatibility for struct syscall arguments (as long as future + * struct extensions are made such that all new fields are *appended* to the + * old struct, and zeroed-out new fields have the same meaning as the old + * struct). + * + * Some syscalls may wish to make sure that userspace knows about everything in + * the struct, and if there is a non-zero value that userspce doesn't know + * about, they want to return an error (such as -EMSGSIZE) or have some other + * fallback (such as adding a "you're missing some information" flag). If + * @ignored_trailing is non-%NULL, it will be set to %true if there was a + * non-zero byte that could not be copied to userspace (ie. was past @usize). + * + * While unconditionally returning an error in this case is the simplest + * solution, for maximum backward compatibility you should try to only return + * -EMSGSIZE if the user explicitly requested the data that couldn't be copied. + * Note that structure sizes can change due to header changes and simple + * recompilations without code changes(!), so if you care about + * @ignored_trailing you probably want to make sure that any new field data is + * associated with a flag. Otherwise you might assume that a program knows + * about data it does not. + * + * @ksize is just sizeof(*src), and @usize should've been passed by userspace. + * The recommended usage is something like the following: + * + * SYSCALL_DEFINE2(foobar, struct foo __user *, uarg, size_t, usize) + * { + * int err; + * bool ignored_trailing; + * struct foo karg = {}; + * + * if (usize > PAGE_SIZE) + * return -E2BIG; + * if (usize < FOO_SIZE_VER0) + * return -EINVAL; + * + * // ... modify karg somehow ... + * + * err = copy_struct_to_user(uarg, usize, &karg, sizeof(karg), + * &ignored_trailing); + * if (err) + * return err; + * if (ignored_trailing) + * return -EMSGSIZE: + * + * // ... + * } + * + * There are three cases to consider: + * * If @usize == @ksize, then it's copied verbatim. + * * If @usize < @ksize, then the kernel is trying to pass userspace a newer + * struct than it supports. Thus we only copy the interoperable portions + * (@usize) and ignore the rest (but @ignored_trailing is set to %true if + * any of the trailing (@ksize - @usize) bytes are non-zero). + * * If @usize > @ksize, then the kernel is trying to pass userspace an older + * struct than userspace supports. In order to make sure the + * unknown-to-the-kernel fields don't contain garbage values, we zero the + * trailing (@usize - @ksize) bytes. + * + * Returns (in all cases, some data may have been copied): + * * -EFAULT: access to userspace failed. + */ +static __always_inline __must_check int +copy_struct_to_user(void __user *dst, size_t usize, const void *src, + size_t ksize, bool *ignored_trailing) +{ + size_t size = min(ksize, usize); + size_t rest = max(ksize, usize) - size; + + /* Double check if ksize is larger than a known object size. */ + if (WARN_ON_ONCE(ksize > __builtin_object_size(src, 1))) + return -E2BIG; + + /* Deal with trailing bytes. */ + if (usize > ksize) { + if (clear_user(dst + size, rest)) + return -EFAULT; + } + if (ignored_trailing) + *ignored_trailing = ksize < usize && + memchr_inv(src + size, 0, rest) != NULL; + /* Copy the interoperable parts of the struct. */ + if (copy_to_user(dst, src, size)) + return -EFAULT; + return 0; +} + bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size); long copy_from_kernel_nofault(void *dst, const void *src, size_t size); diff --git a/include/linux/ubsan.h b/include/linux/ubsan.h index bff7445498de..d8219cbe09ff 100644 --- a/include/linux/ubsan.h +++ b/include/linux/ubsan.h @@ -4,6 +4,11 @@ #ifdef CONFIG_UBSAN_TRAP const char *report_ubsan_failure(struct pt_regs *regs, u32 check_type); +#else +static inline const char *report_ubsan_failure(struct pt_regs *regs, u32 check_type) +{ + return NULL; +} #endif #endif diff --git a/include/linux/udp.h b/include/linux/udp.h index e398e1dbd2d3..0807e21cfec9 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -24,7 +24,7 @@ static inline struct udphdr *udp_hdr(const struct sk_buff *skb) } #define UDP_HTABLE_SIZE_MIN_PERNET 128 -#define UDP_HTABLE_SIZE_MIN (CONFIG_BASE_SMALL ? 128 : 256) +#define UDP_HTABLE_SIZE_MIN (IS_ENABLED(CONFIG_BASE_SMALL) ? 128 : 256) #define UDP_HTABLE_SIZE_MAX 65536 static inline u32 udp_hashfn(const struct net *net, u32 num, u32 mask) @@ -56,6 +56,12 @@ struct udp_sock { int pending; /* Any pending frames ? */ __u8 encap_type; /* Is this an Encapsulation socket? */ +#if !IS_ENABLED(CONFIG_BASE_SMALL) + /* For UDP 4-tuple hash */ + __u16 udp_lrpa_hash; + struct hlist_nulls_node udp_lrpa_node; +#endif + /* * Following member retains the information to create a UDP header * when the socket is uncorked. @@ -206,6 +212,11 @@ static inline void udp_allow_gso(struct sock *sk) #define udp_portaddr_for_each_entry_rcu(__sk, list) \ hlist_for_each_entry_rcu(__sk, list, __sk_common.skc_portaddr_node) +#if !IS_ENABLED(CONFIG_BASE_SMALL) +#define udp_lrpa_for_each_entry_rcu(__up, node, list) \ + hlist_nulls_for_each_entry_rcu(__up, node, list, udp_lrpa_node) +#endif + #define IS_UDPLITE(__sk) (__sk->sk_protocol == IPPROTO_UDPLITE) #endif /* _LINUX_UDP_H */ diff --git a/include/linux/uio.h b/include/linux/uio.h index 00cebe2b70de..8ada84e85447 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -11,6 +11,7 @@ #include <uapi/linux/uio.h> struct page; +struct folio_queue; typedef unsigned int __bitwise iov_iter_extraction_t; @@ -25,6 +26,7 @@ enum iter_type { ITER_IOVEC, ITER_BVEC, ITER_KVEC, + ITER_FOLIOQ, ITER_XARRAY, ITER_DISCARD, }; @@ -66,6 +68,7 @@ struct iov_iter { const struct iovec *__iov; const struct kvec *kvec; const struct bio_vec *bvec; + const struct folio_queue *folioq; struct xarray *xarray; void __user *ubuf; }; @@ -74,10 +77,20 @@ struct iov_iter { }; union { unsigned long nr_segs; + u8 folioq_slot; loff_t xarray_start; }; }; +typedef __u16 uio_meta_flags_t; + +struct uio_meta { + uio_meta_flags_t flags; + u16 app_tag; + u64 seed; + struct iov_iter iter; +}; + static inline const struct iovec *iter_iov(const struct iov_iter *iter) { if (iter->iter_type == ITER_UBUF) @@ -126,6 +139,11 @@ static inline bool iov_iter_is_discard(const struct iov_iter *i) return iov_iter_type(i) == ITER_DISCARD; } +static inline bool iov_iter_is_folioq(const struct iov_iter *i) +{ + return iov_iter_type(i) == ITER_FOLIOQ; +} + static inline bool iov_iter_is_xarray(const struct iov_iter *i) { return iov_iter_type(i) == ITER_XARRAY; @@ -180,6 +198,12 @@ static inline size_t copy_folio_to_iter(struct folio *folio, size_t offset, return copy_page_to_iter(&folio->page, offset, bytes, i); } +static inline size_t copy_folio_from_iter(struct folio *folio, size_t offset, + size_t bytes, struct iov_iter *i) +{ + return copy_page_from_iter(&folio->page, offset, bytes, i); +} + static inline size_t copy_folio_from_iter_atomic(struct folio *folio, size_t offset, size_t bytes, struct iov_iter *i) { @@ -206,6 +230,16 @@ size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) } static __always_inline __must_check +bool copy_to_iter_full(const void *addr, size_t bytes, struct iov_iter *i) +{ + size_t copied = copy_to_iter(addr, bytes, i); + if (likely(copied == bytes)) + return true; + iov_iter_revert(i, copied); + return false; +} + +static __always_inline __must_check bool copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i) { size_t copied = copy_from_iter(addr, bytes, i); @@ -263,6 +297,9 @@ void iov_iter_kvec(struct iov_iter *i, unsigned int direction, const struct kvec void iov_iter_bvec(struct iov_iter *i, unsigned int direction, const struct bio_vec *bvec, unsigned long nr_segs, size_t count); void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count); +void iov_iter_folio_queue(struct iov_iter *i, unsigned int direction, + const struct folio_queue *folioq, + unsigned int first_slot, unsigned int offset, size_t count); void iov_iter_xarray(struct iov_iter *i, unsigned int direction, struct xarray *xarray, loff_t start, size_t count); ssize_t iov_iter_get_pages2(struct iov_iter *i, struct page **pages, diff --git a/include/linux/unaligned.h b/include/linux/unaligned.h new file mode 100644 index 000000000000..4a9651017e3c --- /dev/null +++ b/include/linux/unaligned.h @@ -0,0 +1,146 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_UNALIGNED_H +#define __LINUX_UNALIGNED_H + +/* + * This is the most generic implementation of unaligned accesses + * and should work almost anywhere. + */ +#include <linux/unaligned/packed_struct.h> +#include <asm/byteorder.h> +#include <vdso/unaligned.h> + +#define get_unaligned(ptr) __get_unaligned_t(typeof(*(ptr)), (ptr)) +#define put_unaligned(val, ptr) __put_unaligned_t(typeof(*(ptr)), (val), (ptr)) + +static inline u16 get_unaligned_le16(const void *p) +{ + return le16_to_cpu(__get_unaligned_t(__le16, p)); +} + +static inline u32 get_unaligned_le32(const void *p) +{ + return le32_to_cpu(__get_unaligned_t(__le32, p)); +} + +static inline u64 get_unaligned_le64(const void *p) +{ + return le64_to_cpu(__get_unaligned_t(__le64, p)); +} + +static inline void put_unaligned_le16(u16 val, void *p) +{ + __put_unaligned_t(__le16, cpu_to_le16(val), p); +} + +static inline void put_unaligned_le32(u32 val, void *p) +{ + __put_unaligned_t(__le32, cpu_to_le32(val), p); +} + +static inline void put_unaligned_le64(u64 val, void *p) +{ + __put_unaligned_t(__le64, cpu_to_le64(val), p); +} + +static inline u16 get_unaligned_be16(const void *p) +{ + return be16_to_cpu(__get_unaligned_t(__be16, p)); +} + +static inline u32 get_unaligned_be32(const void *p) +{ + return be32_to_cpu(__get_unaligned_t(__be32, p)); +} + +static inline u64 get_unaligned_be64(const void *p) +{ + return be64_to_cpu(__get_unaligned_t(__be64, p)); +} + +static inline void put_unaligned_be16(u16 val, void *p) +{ + __put_unaligned_t(__be16, cpu_to_be16(val), p); +} + +static inline void put_unaligned_be32(u32 val, void *p) +{ + __put_unaligned_t(__be32, cpu_to_be32(val), p); +} + +static inline void put_unaligned_be64(u64 val, void *p) +{ + __put_unaligned_t(__be64, cpu_to_be64(val), p); +} + +static inline u32 __get_unaligned_be24(const u8 *p) +{ + return p[0] << 16 | p[1] << 8 | p[2]; +} + +static inline u32 get_unaligned_be24(const void *p) +{ + return __get_unaligned_be24(p); +} + +static inline u32 __get_unaligned_le24(const u8 *p) +{ + return p[0] | p[1] << 8 | p[2] << 16; +} + +static inline u32 get_unaligned_le24(const void *p) +{ + return __get_unaligned_le24(p); +} + +static inline void __put_unaligned_be24(const u32 val, u8 *p) +{ + *p++ = (val >> 16) & 0xff; + *p++ = (val >> 8) & 0xff; + *p++ = val & 0xff; +} + +static inline void put_unaligned_be24(const u32 val, void *p) +{ + __put_unaligned_be24(val, p); +} + +static inline void __put_unaligned_le24(const u32 val, u8 *p) +{ + *p++ = val & 0xff; + *p++ = (val >> 8) & 0xff; + *p++ = (val >> 16) & 0xff; +} + +static inline void put_unaligned_le24(const u32 val, void *p) +{ + __put_unaligned_le24(val, p); +} + +static inline void __put_unaligned_be48(const u64 val, u8 *p) +{ + *p++ = (val >> 40) & 0xff; + *p++ = (val >> 32) & 0xff; + *p++ = (val >> 24) & 0xff; + *p++ = (val >> 16) & 0xff; + *p++ = (val >> 8) & 0xff; + *p++ = val & 0xff; +} + +static inline void put_unaligned_be48(const u64 val, void *p) +{ + __put_unaligned_be48(val, p); +} + +static inline u64 __get_unaligned_be48(const u8 *p) +{ + return (u64)p[0] << 40 | (u64)p[1] << 32 | (u64)p[2] << 24 | + p[3] << 16 | p[4] << 8 | p[5]; +} + +static inline u64 get_unaligned_be48(const void *p) +{ + return __get_unaligned_be48(p); +} + +#endif /* __LINUX_UNALIGNED_H */ diff --git a/include/linux/unicode.h b/include/linux/unicode.h index 4d39e6e11a95..5e6b212a2aed 100644 --- a/include/linux/unicode.h +++ b/include/linux/unicode.h @@ -16,6 +16,8 @@ struct utf8data_table; ((unsigned int)(MIN) << UNICODE_MIN_SHIFT) | \ ((unsigned int)(REV))) +#define UTF8_LATEST UNICODE_AGE(12, 1, 0) + static inline u8 unicode_major(unsigned int age) { return (age >> UNICODE_MAJ_SHIFT) & 0xff; @@ -76,4 +78,6 @@ int utf8_casefold_hash(const struct unicode_map *um, const void *salt, struct unicode_map *utf8_load(unsigned int version); void utf8_unload(struct unicode_map *um); +int utf8_parse_version(char *version); + #endif /* _LINUX_UNICODE_H */ diff --git a/include/linux/union_find.h b/include/linux/union_find.h new file mode 100644 index 000000000000..cfd49263c138 --- /dev/null +++ b/include/linux/union_find.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_UNION_FIND_H +#define __LINUX_UNION_FIND_H +/** + * union_find.h - union-find data structure implementation + * + * This header provides functions and structures to implement the union-find + * data structure. The union-find data structure is used to manage disjoint + * sets and supports efficient union and find operations. + * + * See Documentation/core-api/union_find.rst for documentation and samples. + */ + +struct uf_node { + struct uf_node *parent; + unsigned int rank; +}; + +/* This macro is used for static initialization of a union-find node. */ +#define UF_INIT_NODE(node) {.parent = &node, .rank = 0} + +/** + * uf_node_init - Initialize a union-find node + * @node: pointer to the union-find node to be initialized + * + * This function sets the parent of the node to itself and + * initializes its rank to 0. + */ +static inline void uf_node_init(struct uf_node *node) +{ + node->parent = node; + node->rank = 0; +} + +/* find the root of a node */ +struct uf_node *uf_find(struct uf_node *node); + +/* Merge two intersecting nodes */ +void uf_union(struct uf_node *node1, struct uf_node *node2); + +#endif /* __LINUX_UNION_FIND_H */ diff --git a/include/linux/unroll.h b/include/linux/unroll.h new file mode 100644 index 000000000000..d42fd6366373 --- /dev/null +++ b/include/linux/unroll.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * Copyright (C) 2023 Google LLC. + */ + +#ifndef __UNROLL_H +#define __UNROLL_H + +#include <linux/args.h> + +#define UNROLL(N, MACRO, args...) CONCATENATE(__UNROLL_, N)(MACRO, args) + +#define __UNROLL_0(MACRO, args...) +#define __UNROLL_1(MACRO, args...) __UNROLL_0(MACRO, args) MACRO(0, args) +#define __UNROLL_2(MACRO, args...) __UNROLL_1(MACRO, args) MACRO(1, args) +#define __UNROLL_3(MACRO, args...) __UNROLL_2(MACRO, args) MACRO(2, args) +#define __UNROLL_4(MACRO, args...) __UNROLL_3(MACRO, args) MACRO(3, args) +#define __UNROLL_5(MACRO, args...) __UNROLL_4(MACRO, args) MACRO(4, args) +#define __UNROLL_6(MACRO, args...) __UNROLL_5(MACRO, args) MACRO(5, args) +#define __UNROLL_7(MACRO, args...) __UNROLL_6(MACRO, args) MACRO(6, args) +#define __UNROLL_8(MACRO, args...) __UNROLL_7(MACRO, args) MACRO(7, args) +#define __UNROLL_9(MACRO, args...) __UNROLL_8(MACRO, args) MACRO(8, args) +#define __UNROLL_10(MACRO, args...) __UNROLL_9(MACRO, args) MACRO(9, args) +#define __UNROLL_11(MACRO, args...) __UNROLL_10(MACRO, args) MACRO(10, args) +#define __UNROLL_12(MACRO, args...) __UNROLL_11(MACRO, args) MACRO(11, args) +#define __UNROLL_13(MACRO, args...) __UNROLL_12(MACRO, args) MACRO(12, args) +#define __UNROLL_14(MACRO, args...) __UNROLL_13(MACRO, args) MACRO(13, args) +#define __UNROLL_15(MACRO, args...) __UNROLL_14(MACRO, args) MACRO(14, args) +#define __UNROLL_16(MACRO, args...) __UNROLL_15(MACRO, args) MACRO(15, args) +#define __UNROLL_17(MACRO, args...) __UNROLL_16(MACRO, args) MACRO(16, args) +#define __UNROLL_18(MACRO, args...) __UNROLL_17(MACRO, args) MACRO(17, args) +#define __UNROLL_19(MACRO, args...) __UNROLL_18(MACRO, args) MACRO(18, args) +#define __UNROLL_20(MACRO, args...) __UNROLL_19(MACRO, args) MACRO(19, args) + +#endif /* __UNROLL_H */ diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index f46e0ca0169c..b1df7d792fa1 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -15,34 +15,48 @@ #include <linux/rbtree.h> #include <linux/types.h> #include <linux/wait.h> +#include <linux/timer.h> +#include <linux/seqlock.h> +struct uprobe; struct vm_area_struct; struct mm_struct; struct inode; struct notifier_block; struct page; +/* + * Allowed return values from uprobe consumer's handler callback + * with following meaning: + * + * UPROBE_HANDLER_REMOVE + * - Remove the uprobe breakpoint from current->mm. + * UPROBE_HANDLER_IGNORE + * - Ignore ret_handler callback for this consumer. + */ #define UPROBE_HANDLER_REMOVE 1 -#define UPROBE_HANDLER_MASK 1 +#define UPROBE_HANDLER_IGNORE 2 #define MAX_URETPROBE_DEPTH 64 -enum uprobe_filter_ctx { - UPROBE_FILTER_REGISTER, - UPROBE_FILTER_UNREGISTER, - UPROBE_FILTER_MMAP, -}; - struct uprobe_consumer { - int (*handler)(struct uprobe_consumer *self, struct pt_regs *regs); + /* + * handler() can return UPROBE_HANDLER_REMOVE to signal the need to + * unregister uprobe for current process. If UPROBE_HANDLER_REMOVE is + * returned, filter() callback has to be implemented as well and it + * should return false to "confirm" the decision to uninstall uprobe + * for the current process. If filter() is omitted or returns true, + * UPROBE_HANDLER_REMOVE is effectively ignored. + */ + int (*handler)(struct uprobe_consumer *self, struct pt_regs *regs, __u64 *data); int (*ret_handler)(struct uprobe_consumer *self, unsigned long func, - struct pt_regs *regs); - bool (*filter)(struct uprobe_consumer *self, - enum uprobe_filter_ctx ctx, - struct mm_struct *mm); + struct pt_regs *regs, __u64 *data); + bool (*filter)(struct uprobe_consumer *self, struct mm_struct *mm); - struct uprobe_consumer *next; + struct list_head cons_node; + + __u64 id; /* set when uprobe_consumer is registered */ }; #ifdef CONFIG_UPROBES @@ -55,12 +69,66 @@ enum uprobe_task_state { UTASK_SSTEP_TRAPPED, }; +/* The state of hybrid-lifetime uprobe inside struct return_instance */ +enum hprobe_state { + HPROBE_LEASED, /* uretprobes_srcu-protected uprobe */ + HPROBE_STABLE, /* refcounted uprobe */ + HPROBE_GONE, /* NULL uprobe, SRCU expired, refcount failed */ + HPROBE_CONSUMED, /* uprobe "consumed" by uretprobe handler */ +}; + +/* + * Hybrid lifetime uprobe. Represents a uprobe instance that could be either + * SRCU protected (with SRCU protection eventually potentially timing out), + * refcounted using uprobe->ref, or there could be no valid uprobe (NULL). + * + * hprobe's internal state is setup such that background timer thread can + * atomically "downgrade" temporarily RCU-protected uprobe into refcounted one + * (or no uprobe, if refcounting failed). + * + * *stable* pointer always point to the uprobe (or could be NULL if there is + * was no valid underlying uprobe to begin with). + * + * *leased* pointer is the key to achieving race-free atomic lifetime state + * transition and can have three possible states: + * - either the same non-NULL value as *stable*, in which case uprobe is + * SRCU-protected; + * - NULL, in which case uprobe (if there is any) is refcounted; + * - special __UPROBE_DEAD value, which represents an uprobe that was SRCU + * protected initially, but SRCU period timed out and we attempted to + * convert it to refcounted, but refcount_inc_not_zero() failed, because + * uprobe effectively went away (the last consumer unsubscribed). In this + * case it's important to know that *stable* pointer (which still has + * non-NULL uprobe pointer) shouldn't be used, because lifetime of + * underlying uprobe is not guaranteed anymore. __UPROBE_DEAD is just an + * internal marker and is handled transparently by hprobe_fetch() helper. + * + * When uprobe is SRCU-protected, we also record srcu_idx value, necessary for + * SRCU unlocking. + * + * See hprobe_expire() and hprobe_fetch() for details of race-free uprobe + * state transitioning details. It all hinges on atomic xchg() over *leaded* + * pointer. *stable* pointer, once initially set, is not modified concurrently. + */ +struct hprobe { + enum hprobe_state state; + int srcu_idx; + struct uprobe *uprobe; +}; + /* * uprobe_task: Metadata of a task while it singlesteps. */ struct uprobe_task { enum uprobe_task_state state; + unsigned int depth; + struct return_instance *return_instances; + + struct return_instance *ri_pool; + struct timer_list ri_timer; + seqcount_t ri_seqcount; + union { struct { struct arch_uprobe_task autask; @@ -76,19 +144,33 @@ struct uprobe_task { struct uprobe *active_uprobe; unsigned long xol_vaddr; - struct return_instance *return_instances; - unsigned int depth; + struct arch_uprobe *auprobe; +}; + +struct return_consumer { + __u64 cookie; + __u64 id; }; struct return_instance { - struct uprobe *uprobe; + struct hprobe hprobe; unsigned long func; unsigned long stack; /* stack pointer */ unsigned long orig_ret_vaddr; /* original return address */ bool chained; /* true, if instance is nested */ + int cons_cnt; /* total number of session consumers */ struct return_instance *next; /* keep as stack */ -}; + struct rcu_head rcu; + + /* singular pre-allocated return_consumer instance for common case */ + struct return_consumer consumer; + /* + * extra return_consumer instances for rare cases of multiple session consumers, + * contains (cons_cnt - 1) elements + */ + struct return_consumer *extra_consumers; +} ____cacheline_aligned; enum rp_check { RP_CHECK_CALL, @@ -110,10 +192,10 @@ extern bool is_trap_insn(uprobe_opcode_t *insn); extern unsigned long uprobe_get_swbp_addr(struct pt_regs *regs); extern unsigned long uprobe_get_trap_addr(struct pt_regs *regs); extern int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t); -extern int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc); -extern int uprobe_register_refctr(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc); -extern int uprobe_apply(struct inode *inode, loff_t offset, struct uprobe_consumer *uc, bool); -extern void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc); +extern struct uprobe *uprobe_register(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc); +extern int uprobe_apply(struct uprobe *uprobe, struct uprobe_consumer *uc, bool); +extern void uprobe_unregister_nosync(struct uprobe *uprobe, struct uprobe_consumer *uc); +extern void uprobe_unregister_sync(void); extern int uprobe_mmap(struct vm_area_struct *vma); extern void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end); extern void uprobe_start_dup_mmap(void); @@ -138,6 +220,9 @@ extern bool arch_uretprobe_is_alive(struct return_instance *ret, enum rp_check c extern bool arch_uprobe_ignore(struct arch_uprobe *aup, struct pt_regs *regs); extern void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr, void *src, unsigned long len); +extern void uprobe_handle_trampoline(struct pt_regs *regs); +extern void *arch_uprobe_trampoline(unsigned long *psize); +extern unsigned long uprobe_get_trampoline_vaddr(void); #else /* !CONFIG_UPROBES */ struct uprobes_state { }; @@ -148,22 +233,21 @@ static inline void uprobes_init(void) #define uprobe_get_trap_addr(regs) instruction_pointer(regs) -static inline int -uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc) -{ - return -ENOSYS; -} -static inline int uprobe_register_refctr(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc) +static inline struct uprobe * +uprobe_register(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc) { - return -ENOSYS; + return ERR_PTR(-ENOSYS); } static inline int -uprobe_apply(struct inode *inode, loff_t offset, struct uprobe_consumer *uc, bool add) +uprobe_apply(struct uprobe* uprobe, struct uprobe_consumer *uc, bool add) { return -ENOSYS; } static inline void -uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc) +uprobe_unregister_nosync(struct uprobe *uprobe, struct uprobe_consumer *uc) +{ +} +static inline void uprobe_unregister_sync(void) { } static inline int uprobe_mmap(struct vm_area_struct *vma) diff --git a/include/linux/usb.h b/include/linux/usb.h index 9e52179872a5..cfa8005e24f9 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -440,11 +440,6 @@ int __usb_get_extra_descriptor(char *buffer, unsigned size, /* ----------------------------------------------------------------------- */ -/* USB device number allocation bitmap */ -struct usb_devmap { - unsigned long devicemap[128 / (8*sizeof(unsigned long))]; -}; - /* * Allocated per bus (tree of devices) we have: */ @@ -472,7 +467,7 @@ struct usb_bus { * round-robin allocation */ struct mutex devnum_next_mutex; /* devnum_next mutex */ - struct usb_devmap devmap; /* device address allocation map */ + DECLARE_BITMAP(devmap, 128); /* USB device number allocation bitmap */ struct usb_device *root_hub; /* Root hub */ struct usb_bus *hs_companion; /* Companion EHCI bus, if any */ @@ -500,6 +495,12 @@ struct usb_dev_state; struct usb_tt; +enum usb_link_tunnel_mode { + USB_LINK_UNKNOWN = 0, + USB_LINK_NATIVE, + USB_LINK_TUNNELED, +}; + enum usb_port_connect_type { USB_PORT_CONNECT_TYPE_UNKNOWN = 0, USB_PORT_CONNECT_TYPE_HOT_PLUG, @@ -610,6 +611,7 @@ struct usb3_lpm_parameters { * WUSB devices are not, until we authorize them from user space. * FIXME -- complete doc * @authenticated: Crypto authentication passed + * @tunnel_mode: Connection native or tunneled over USB4 * @lpm_capable: device supports LPM * @lpm_devinit_allow: Allow USB3 device initiated LPM, exit latency is in range * @usb2_hw_lpm_capable: device can perform USB2 hardware LPM @@ -719,6 +721,7 @@ struct usb_device { unsigned do_remote_wakeup:1; unsigned reset_resume:1; unsigned port_is_suspended:1; + enum usb_link_tunnel_mode tunnel_mode; int slot_id; struct usb2_lpm_parameters l1_params; @@ -1126,8 +1129,8 @@ static inline int usb_make_path(struct usb_device *dev, char *buf, size_t size) /* ----------------------------------------------------------------------- */ /* Stuff for dynamic usb ids */ +extern struct mutex usb_dynids_lock; struct usb_dynids { - spinlock_t lock; struct list_head list; }; @@ -1176,6 +1179,7 @@ extern ssize_t usb_show_dynids(struct usb_dynids *dynids, char *buf); * post_reset method is called. * @post_reset: Called by usb_reset_device() after the device * has been reset + * @shutdown: Called at shut-down time to quiesce the device. * @id_table: USB drivers use ID table to support hotplugging. * Export this with MODULE_DEVICE_TABLE(usb,...). This must be set * or your driver's probe function will never get called. @@ -1227,6 +1231,8 @@ struct usb_driver { int (*pre_reset)(struct usb_interface *intf); int (*post_reset)(struct usb_interface *intf); + void (*shutdown)(struct usb_interface *intf); + const struct usb_device_id *id_table; const struct attribute_group **dev_groups; @@ -1237,7 +1243,7 @@ struct usb_driver { unsigned int disable_hub_initiated_lpm:1; unsigned int soft_unbind:1; }; -#define to_usb_driver(d) container_of(d, struct usb_driver, driver) +#define to_usb_driver(d) container_of_const(d, struct usb_driver, driver) /** * struct usb_device_driver - identifies USB device driver to usbcore @@ -1288,8 +1294,7 @@ struct usb_device_driver { unsigned int supports_autosuspend:1; unsigned int generic_subclass:1; }; -#define to_usb_device_driver(d) container_of(d, struct usb_device_driver, \ - driver) +#define to_usb_device_driver(d) container_of_const(d, struct usb_device_driver, driver) /** * struct usb_class_driver - identifies a USB driver that wants to use the USB major number diff --git a/include/linux/usb/chipidea.h b/include/linux/usb/chipidea.h index 5a7f96684ea2..ebdfef124b2b 100644 --- a/include/linux/usb/chipidea.h +++ b/include/linux/usb/chipidea.h @@ -65,6 +65,7 @@ struct ci_hdrc_platform_data { #define CI_HDRC_PHY_VBUS_CONTROL BIT(16) #define CI_HDRC_HAS_PORTSC_PEC_MISSED BIT(17) #define CI_HDRC_FORCE_VBUS_ACTIVE_ALWAYS BIT(18) +#define CI_HDRC_HAS_SHORT_PKT_LIMIT BIT(19) enum usb_dr_mode dr_mode; #define CI_HDRC_CONTROLLER_RESET_EVENT 0 #define CI_HDRC_CONTROLLER_STOPPED_EVENT 1 diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index af3cd2aae4bc..6e38fb9d2117 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -256,7 +256,7 @@ int config_ep_by_speed(struct usb_gadget *g, struct usb_function *f, struct usb_ep *_ep); int usb_func_wakeup(struct usb_function *func); -#define MAX_CONFIG_INTERFACES 16 /* arbitrary; max 255 */ +#define MAX_CONFIG_INTERFACES 32 /** * struct usb_configuration - represents one gadget configuration diff --git a/include/linux/usb/func_utils.h b/include/linux/usb/func_utils.h new file mode 100644 index 000000000000..c8795c965109 --- /dev/null +++ b/include/linux/usb/func_utils.h @@ -0,0 +1,86 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * func_utils.h + * + * Utility definitions for USB functions + * + * Copyright (c) 2013 Samsung Electronics Co., Ltd. + * http://www.samsung.com + * + * Author: Andrzej Pietrasiewicz <andrzejtp2010@gmail.com> + */ + +#ifndef _FUNC_UTILS_H_ +#define _FUNC_UTILS_H_ + +#include <linux/usb/gadget.h> +#include <linux/overflow.h> + +/* Variable Length Array Macros **********************************************/ +#define vla_group(groupname) size_t groupname##__next = 0 +#define vla_group_size(groupname) groupname##__next + +#define vla_item(groupname, type, name, n) \ + size_t groupname##_##name##__offset = ({ \ + size_t offset = 0; \ + if (groupname##__next != SIZE_MAX) { \ + size_t align_mask = __alignof__(type) - 1; \ + size_t size = array_size(n, sizeof(type)); \ + offset = (groupname##__next + align_mask) & \ + ~align_mask; \ + if (check_add_overflow(offset, size, \ + &groupname##__next)) { \ + groupname##__next = SIZE_MAX; \ + offset = 0; \ + } \ + } \ + offset; \ + }) + +#define vla_item_with_sz(groupname, type, name, n) \ + size_t groupname##_##name##__sz = array_size(n, sizeof(type)); \ + size_t groupname##_##name##__offset = ({ \ + size_t offset = 0; \ + if (groupname##__next != SIZE_MAX) { \ + size_t align_mask = __alignof__(type) - 1; \ + offset = (groupname##__next + align_mask) & \ + ~align_mask; \ + if (check_add_overflow(offset, groupname##_##name##__sz,\ + &groupname##__next)) { \ + groupname##__next = SIZE_MAX; \ + offset = 0; \ + } \ + } \ + offset; \ + }) + +#define vla_ptr(ptr, groupname, name) \ + ((void *) ((char *)ptr + groupname##_##name##__offset)) + +struct usb_ep; +struct usb_request; + +/** + * alloc_ep_req - returns a usb_request allocated by the gadget driver and + * allocates the request's buffer. + * + * @ep: the endpoint to allocate a usb_request + * @len: usb_requests's buffer suggested size + * + * In case @ep direction is OUT, the @len will be aligned to ep's + * wMaxPacketSize. In order to avoid memory leaks or drops, *always* use + * usb_requests's length (req->length) to refer to the allocated buffer size. + * Requests allocated via alloc_ep_req() *must* be freed by free_ep_req(). + */ +struct usb_request *alloc_ep_req(struct usb_ep *ep, size_t len); + +/* Frees a usb_request previously allocated by alloc_ep_req() */ +static inline void free_ep_req(struct usb_ep *ep, struct usb_request *req) +{ + WARN_ON(req->buf == NULL); + kfree(req->buf); + req->buf = NULL; + usb_ep_free_request(ep, req); +} + +#endif /* _FUNC_UTILS_H_ */ diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 56dda8e1562d..df33333650a0 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -229,18 +229,18 @@ struct usb_ep { const char *name; const struct usb_ep_ops *ops; + const struct usb_endpoint_descriptor *desc; + const struct usb_ss_ep_comp_descriptor *comp_desc; struct list_head ep_list; struct usb_ep_caps caps; bool claimed; bool enabled; - unsigned maxpacket:16; - unsigned maxpacket_limit:16; - unsigned max_streams:16; unsigned mult:2; unsigned maxburst:5; u8 address; - const struct usb_endpoint_descriptor *desc; - const struct usb_ss_ep_comp_descriptor *comp_desc; + u16 maxpacket; + u16 maxpacket_limit; + u16 max_streams; }; /*-------------------------------------------------------------------------*/ diff --git a/include/linux/usb/gadget_configfs.h b/include/linux/usb/gadget_configfs.h index d61aebd68128..6b5d6838f865 100644 --- a/include/linux/usb/gadget_configfs.h +++ b/include/linux/usb/gadget_configfs.h @@ -4,9 +4,6 @@ #include <linux/configfs.h> -int check_user_usb_string(const char *name, - struct usb_gadget_strings *stringtab_dev); - #define GS_STRINGS_W(__struct, __name) \ static ssize_t __struct##_##__name##_store(struct config_item *item, \ const char *page, size_t len) \ @@ -37,7 +34,7 @@ static struct configfs_item_operations struct_in##_langid_item_ops = { \ .release = struct_in##_attr_release, \ }; \ \ -static struct config_item_type struct_in##_langid_type = { \ +static const struct config_item_type struct_in##_langid_type = { \ .ct_item_ops = &struct_in##_langid_item_ops, \ .ct_attrs = struct_in##_langid_attrs, \ .ct_owner = THIS_MODULE, \ @@ -94,7 +91,7 @@ static struct configfs_group_operations struct_in##_strings_ops = { \ .drop_item = &struct_in##_strings_drop, \ }; \ \ -static struct config_item_type struct_in##_strings_type = { \ +static const struct config_item_type struct_in##_strings_type = { \ .ct_group_ops = &struct_in##_strings_ops, \ .ct_owner = THIS_MODULE, \ } diff --git a/include/linux/usb/onboard_dev.h b/include/linux/usb/onboard_dev.h new file mode 100644 index 000000000000..b79db6d193c8 --- /dev/null +++ b/include/linux/usb/onboard_dev.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __LINUX_USB_ONBOARD_DEV_H +#define __LINUX_USB_ONBOARD_DEV_H + +struct usb_device; +struct list_head; + +#if IS_ENABLED(CONFIG_USB_ONBOARD_DEV) +void onboard_dev_create_pdevs(struct usb_device *parent_dev, struct list_head *pdev_list); +void onboard_dev_destroy_pdevs(struct list_head *pdev_list); +#else +static inline void onboard_dev_create_pdevs(struct usb_device *parent_dev, + struct list_head *pdev_list) {} +static inline void onboard_dev_destroy_pdevs(struct list_head *pdev_list) {} +#endif + +#endif /* __LINUX_USB_ONBOARD_DEV_H */ diff --git a/include/linux/usb/onboard_hub.h b/include/linux/usb/onboard_hub.h deleted file mode 100644 index d9373230556e..000000000000 --- a/include/linux/usb/onboard_hub.h +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ - -#ifndef __LINUX_USB_ONBOARD_HUB_H -#define __LINUX_USB_ONBOARD_HUB_H - -struct usb_device; -struct list_head; - -#if IS_ENABLED(CONFIG_USB_ONBOARD_HUB) -void onboard_hub_create_pdevs(struct usb_device *parent_hub, struct list_head *pdev_list); -void onboard_hub_destroy_pdevs(struct list_head *pdev_list); -#else -static inline void onboard_hub_create_pdevs(struct usb_device *parent_hub, - struct list_head *pdev_list) {} -static inline void onboard_hub_destroy_pdevs(struct list_head *pdev_list) {} -#endif - -#endif /* __LINUX_USB_ONBOARD_HUB_H */ diff --git a/include/linux/usb/pd.h b/include/linux/usb/pd.h index d50098fb16b5..3068c3084eb6 100644 --- a/include/linux/usb/pd.h +++ b/include/linux/usb/pd.h @@ -33,7 +33,9 @@ enum pd_ctrl_msg_type { PD_CTRL_FR_SWAP = 19, PD_CTRL_GET_PPS_STATUS = 20, PD_CTRL_GET_COUNTRY_CODES = 21, - /* 22-31 Reserved */ + /* 22-23 Reserved */ + PD_CTRL_GET_REVISION = 24, + /* 25-31 Reserved */ }; enum pd_data_msg_type { @@ -46,7 +48,9 @@ enum pd_data_msg_type { PD_DATA_ALERT = 6, PD_DATA_GET_COUNTRY_INFO = 7, PD_DATA_ENTER_USB = 8, - /* 9-14 Reserved */ + /* 9-11 Reserved */ + PD_DATA_REVISION = 12, + /* 13-14 Reserved */ PD_DATA_VENDOR_DEF = 15, /* 16-31 Reserved */ }; @@ -453,6 +457,20 @@ static inline unsigned int rdo_max_power(u32 rdo) #define EUDO_TBT_SUPPORT BIT(14) #define EUDO_HOST_PRESENT BIT(13) +/* + * Request Message Data Object (PD Revision 3.1+ only) + * -------- + * <31:28> :: Revision Major + * <27:24> :: Revision Minor + * <23:20> :: Version Major + * <19:16> :: Version Minor + * <15:0> :: Reserved, Shall be set to zero + */ + +#define RMDO(rev_maj, rev_min, ver_maj, ver_min) \ + (((rev_maj) & 0xf) << 28 | ((rev_min) & 0xf) << 24 | \ + ((ver_maj) & 0xf) << 20 | ((ver_min) & 0xf) << 16) + /* USB PD timers and counters */ #define PD_T_NO_RESPONSE 5000 /* 4.5 - 5.5 seconds */ #define PD_T_DB_DETECT 10000 /* 10 - 15 seconds */ diff --git a/include/linux/usb/phy.h b/include/linux/usb/phy.h index e4de6bc1f69b..0fa9885a1038 100644 --- a/include/linux/usb/phy.h +++ b/include/linux/usb/phy.h @@ -223,7 +223,6 @@ extern struct usb_phy *devm_usb_get_phy_by_phandle(struct device *dev, extern struct usb_phy *devm_usb_get_phy_by_node(struct device *dev, struct device_node *node, struct notifier_block *nb); extern void usb_put_phy(struct usb_phy *); -extern void devm_usb_put_phy(struct device *dev, struct usb_phy *x); extern void usb_phy_set_event(struct usb_phy *x, unsigned long event); extern void usb_phy_set_charger_current(struct usb_phy *usb_phy, unsigned int mA); @@ -259,10 +258,6 @@ static inline void usb_put_phy(struct usb_phy *x) { } -static inline void devm_usb_put_phy(struct device *dev, struct usb_phy *x) -{ -} - static inline void usb_phy_set_event(struct usb_phy *x, unsigned long event) { } diff --git a/include/linux/usb/renesas_usbhs.h b/include/linux/usb/renesas_usbhs.h index 372898d9eeb0..67bfcda6c7d2 100644 --- a/include/linux/usb/renesas_usbhs.h +++ b/include/linux/usb/renesas_usbhs.h @@ -194,9 +194,4 @@ struct renesas_usbhs_platform_info { struct renesas_usbhs_driver_param driver_param; }; -/* - * macro for platform - */ -#define renesas_usbhs_get_info(pdev)\ - ((struct renesas_usbhs_platform_info *)(pdev)->dev.platform_data) #endif /* RENESAS_USB_H */ diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h index 1a0a4dc87980..75b2b763f1ba 100644 --- a/include/linux/usb/serial.h +++ b/include/linux/usb/serial.h @@ -311,8 +311,11 @@ struct usb_serial_driver { #define to_usb_serial_driver(d) \ container_of(d, struct usb_serial_driver, driver) -int usb_serial_register_drivers(struct usb_serial_driver *const serial_drivers[], - const char *name, const struct usb_device_id *id_table); +#define usb_serial_register_drivers(serial_drivers, name, id_table) \ + __usb_serial_register_drivers(serial_drivers, THIS_MODULE, name, id_table) +int __usb_serial_register_drivers(struct usb_serial_driver *const serial_drivers[], + struct module *owner, const char *name, + const struct usb_device_id *id_table); void usb_serial_deregister_drivers(struct usb_serial_driver *const serial_drivers[]); void usb_serial_port_softint(struct usb_serial_port *port); diff --git a/include/linux/usb/storage.h b/include/linux/usb/storage.h index 2827ce72e502..51be3bb8fccb 100644 --- a/include/linux/usb/storage.h +++ b/include/linux/usb/storage.h @@ -53,7 +53,7 @@ struct bulk_cb_wrap { __le32 Signature; /* contains 'USBC' */ __u32 Tag; /* unique per command id */ __le32 DataTransferLength; /* size of data */ - __u8 Flags; /* direction in bit 0 */ + __u8 Flags; /* direction in bit 7 */ __u8 Lun; /* LUN normally 0 */ __u8 Length; /* length of the CDB */ __u8 CDB[16]; /* max command */ @@ -82,4 +82,12 @@ struct bulk_cs_wrap { #define US_BULK_RESET_REQUEST 0xff #define US_BULK_GET_MAX_LUN 0xfe +/* + * If 4 LUNs are supported then the LUNs would be + * numbered from 0 to 3, and the return value for + * US_BULK_GET_MAX_LUN request would be 3. The valid + * LUN field is 4 bits wide, the upper limit is 0x0f. + */ +#define US_BULK_MAX_LUN_LIMIT 0x0f + #endif diff --git a/include/linux/usb/tcpci.h b/include/linux/usb/tcpci.h index 47a86b8a4a50..f7f5cfbdef12 100644 --- a/include/linux/usb/tcpci.h +++ b/include/linux/usb/tcpci.h @@ -47,6 +47,9 @@ #define TCPC_SINK_FAST_ROLE_SWAP BIT(0) #define TCPC_CONFIG_STD_OUTPUT 0x18 +#define TCPC_CONFIG_STD_OUTPUT_ORIENTATION_MASK BIT(0) +#define TCPC_CONFIG_STD_OUTPUT_ORIENTATION_NORMAL 0 +#define TCPC_CONFIG_STD_OUTPUT_ORIENTATION_FLIPPED 1 #define TCPC_TCPC_CTRL 0x19 #define TCPC_TCPC_CTRL_ORIENTATION BIT(0) @@ -60,15 +63,12 @@ #define TCPC_ROLE_CTRL 0x1a #define TCPC_ROLE_CTRL_DRP BIT(6) -#define TCPC_ROLE_CTRL_RP_VAL_SHIFT 4 -#define TCPC_ROLE_CTRL_RP_VAL_MASK 0x3 +#define TCPC_ROLE_CTRL_RP_VAL GENMASK(5, 4) #define TCPC_ROLE_CTRL_RP_VAL_DEF 0x0 #define TCPC_ROLE_CTRL_RP_VAL_1_5 0x1 #define TCPC_ROLE_CTRL_RP_VAL_3_0 0x2 -#define TCPC_ROLE_CTRL_CC2_SHIFT 2 -#define TCPC_ROLE_CTRL_CC2_MASK 0x3 -#define TCPC_ROLE_CTRL_CC1_SHIFT 0 -#define TCPC_ROLE_CTRL_CC1_MASK 0x3 +#define TCPC_ROLE_CTRL_CC2 GENMASK(3, 2) +#define TCPC_ROLE_CTRL_CC1 GENMASK(1, 0) #define TCPC_ROLE_CTRL_CC_RA 0x0 #define TCPC_ROLE_CTRL_CC_RP 0x1 #define TCPC_ROLE_CTRL_CC_RD 0x2 @@ -89,11 +89,9 @@ #define TCPC_CC_STATUS_TERM BIT(4) #define TCPC_CC_STATUS_TERM_RP 0 #define TCPC_CC_STATUS_TERM_RD 1 +#define TCPC_CC_STATUS_CC2 GENMASK(3, 2) +#define TCPC_CC_STATUS_CC1 GENMASK(1, 0) #define TCPC_CC_STATE_SRC_OPEN 0 -#define TCPC_CC_STATUS_CC2_SHIFT 2 -#define TCPC_CC_STATUS_CC2_MASK 0x3 -#define TCPC_CC_STATUS_CC1_SHIFT 0 -#define TCPC_CC_STATUS_CC1_MASK 0x3 #define TCPC_POWER_STATUS 0x1e #define TCPC_POWER_STATUS_DBG_ACC_CON BIT(7) @@ -127,12 +125,12 @@ #define TCPC_DEV_CAP_2 0x26 #define TCPC_STD_INPUT_CAP 0x28 #define TCPC_STD_OUTPUT_CAP 0x29 +#define TCPC_STD_OUTPUT_CAP_ORIENTATION BIT(0) #define TCPC_MSG_HDR_INFO 0x2e #define TCPC_MSG_HDR_INFO_DATA_ROLE BIT(3) +#define TCPC_MSG_HDR_INFO_REV GENMASK(2, 1) #define TCPC_MSG_HDR_INFO_PWR_ROLE BIT(0) -#define TCPC_MSG_HDR_INFO_REV_SHIFT 1 -#define TCPC_MSG_HDR_INFO_REV_MASK 0x3 #define TCPC_RX_DETECT 0x2f #define TCPC_RX_DETECT_HARD_RESET BIT(5) @@ -150,10 +148,8 @@ #define TCPC_RX_DATA 0x34 /* through 0x4f */ #define TCPC_TRANSMIT 0x50 -#define TCPC_TRANSMIT_RETRY_SHIFT 4 -#define TCPC_TRANSMIT_RETRY_MASK 0x3 -#define TCPC_TRANSMIT_TYPE_SHIFT 0 -#define TCPC_TRANSMIT_TYPE_MASK 0x7 +#define TCPC_TRANSMIT_RETRY GENMASK(5, 4) +#define TCPC_TRANSMIT_TYPE GENMASK(2, 0) #define TCPC_TX_BYTE_CNT 0x51 #define TCPC_TX_HDR 0x52 @@ -174,8 +170,7 @@ #define tcpc_presenting_rd(reg, cc) \ (!(TCPC_ROLE_CTRL_DRP & (reg)) && \ - (((reg) & (TCPC_ROLE_CTRL_## cc ##_MASK << TCPC_ROLE_CTRL_## cc ##_SHIFT)) == \ - (TCPC_ROLE_CTRL_CC_RD << TCPC_ROLE_CTRL_## cc ##_SHIFT))) + FIELD_GET(TCPC_ROLE_CTRL_## cc, reg) == TCPC_ROLE_CTRL_CC_RD) struct tcpci; @@ -186,7 +181,7 @@ struct tcpci; * Optional; Callback to perform chip specific operations when FRS * is sourcing vbus. * @auto_discharge_disconnect: - * Optional; Enables TCPC to autonously discharge vbus on disconnect. + * Optional; Enables TCPC to autonomously discharge vbus on disconnect. * @vbus_vsafe0v: * optional; Set when TCPC can detect whether vbus is at VSAFE0V. * @set_partner_usb_comm_capable: @@ -209,6 +204,9 @@ struct tcpci; * swap following Discover Identity on SOP' occurs. * Return true when the TCPM is allowed to request a Vconn swap * after Discovery Identity on SOP. + * @set_orientation: + * Optional; Enable setting the connector orientation + * CONFIG_STANDARD_OUTPUT (0x18) bit0. */ struct tcpci_data { struct regmap *regmap; @@ -216,6 +214,7 @@ struct tcpci_data { unsigned char auto_discharge_disconnect:1; unsigned char vbus_vsafe0v:1; unsigned char cable_comm_capable:1; + unsigned char set_orientation:1; int (*init)(struct tcpci *tcpci, struct tcpci_data *data); int (*set_vconn)(struct tcpci *tcpci, struct tcpci_data *data, @@ -248,7 +247,7 @@ static inline enum typec_cc_status tcpci_to_typec_cc(unsigned int cc, bool sink) if (sink) return TYPEC_CC_RP_3_0; fallthrough; - case 0x0: + case TCPC_CC_STATE_SRC_OPEN: default: return TYPEC_CC_OPEN; } diff --git a/include/linux/usb/tcpm.h b/include/linux/usb/tcpm.h index 061da9546a81..b22e659f81ba 100644 --- a/include/linux/usb/tcpm.h +++ b/include/linux/usb/tcpm.h @@ -163,7 +163,8 @@ struct tcpc_dev { void (*frs_sourcing_vbus)(struct tcpc_dev *dev); int (*enable_auto_vbus_discharge)(struct tcpc_dev *dev, bool enable); int (*set_auto_vbus_discharge_threshold)(struct tcpc_dev *dev, enum typec_pwr_opmode mode, - bool pps_active, u32 requested_vbus_voltage); + bool pps_active, u32 requested_vbus_voltage, + u32 pps_apdo_min_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); diff --git a/include/linux/usb/tegra_usb_phy.h b/include/linux/usb/tegra_usb_phy.h index 46e73584b6e6..e6c14f2b1f9b 100644 --- a/include/linux/usb/tegra_usb_phy.h +++ b/include/linux/usb/tegra_usb_phy.h @@ -7,11 +7,12 @@ #define __TEGRA_USB_PHY_H #include <linux/clk.h> -#include <linux/gpio.h> #include <linux/regmap.h> #include <linux/reset.h> #include <linux/usb/otg.h> +struct gpio_desc; + /* * utmi_pll_config_in_car_module: true if the UTMI PLL configuration registers * should be set up by clk-tegra, false if by the PHY code diff --git a/include/linux/usb/typec.h b/include/linux/usb/typec.h index b35b427561ab..252af3f77039 100644 --- a/include/linux/usb/typec.h +++ b/include/linux/usb/typec.h @@ -87,6 +87,17 @@ enum typec_orientation { TYPEC_ORIENTATION_REVERSE, }; +enum usb_mode { + USB_MODE_NONE, + USB_MODE_USB2, + USB_MODE_USB3, + USB_MODE_USB4 +}; + +#define USB_CAPABILITY_USB2 BIT(0) +#define USB_CAPABILITY_USB3 BIT(1) +#define USB_CAPABILITY_USB4 BIT(2) + /* * struct enter_usb_data - Enter_USB Message details * @eudo: Enter_USB Data Object @@ -129,6 +140,7 @@ int typec_cable_set_identity(struct typec_cable *cable); * @mode: Index of the Mode * @vdo: VDO returned by Discover Modes USB PD command * @roles: Only for ports. DRP if the mode is available in both roles + * @inactive: Only for ports. Make this port inactive (default is active). * * Description of an Alternate Mode which a connector, cable plug or partner * supports. @@ -139,6 +151,7 @@ struct typec_altmode_desc { u32 vdo; /* Only used with ports */ enum typec_port_data roles; + bool inactive; }; void typec_partner_set_pd_revision(struct typec_partner *partner, u16 pd_revision); @@ -167,6 +180,9 @@ struct typec_port *typec_altmode2port(struct typec_altmode *alt); void typec_altmode_update_active(struct typec_altmode *alt, bool active); +void typec_altmode_set_ops(struct typec_altmode *alt, + const struct typec_altmode_ops *ops); + enum typec_plug_index { TYPEC_PLUG_SOP_P, TYPEC_PLUG_SOP_PP, @@ -206,6 +222,7 @@ struct typec_cable_desc { * @accessory: Audio, Debug or none. * @identity: Discover Identity command data * @pd_revision: USB Power Delivery Specification Revision if supported + * @usb_capability: Supported USB Modes * @attach: Notification about attached USB device * @deattach: Notification about removed USB device * @@ -223,6 +240,7 @@ struct typec_partner_desc { enum typec_accessory accessory; struct usb_pd_identity *identity; u16 pd_revision; /* 0300H = "3.0" */ + u8 usb_capability; void (*attach)(struct typec_partner *partner, struct device *dev); void (*deattach)(struct typec_partner *partner, struct device *dev); @@ -237,6 +255,8 @@ struct typec_partner_desc { * @port_type_set: Set port type * @pd_get: Get available USB Power Delivery Capabilities. * @pd_set: Set USB Power Delivery Capabilities. + * @default_usb_mode_set: USB Mode to be used by default with Enter_USB Message + * @enter_usb_mode: Change the active USB Mode */ struct typec_operations { int (*try_role)(struct typec_port *port, int role); @@ -247,6 +267,8 @@ struct typec_operations { enum typec_port_type type); struct usb_power_delivery **(*pd_get)(struct typec_port *port); int (*pd_set)(struct typec_port *port, struct usb_power_delivery *pd); + int (*default_usb_mode_set)(struct typec_port *port, enum usb_mode mode); + int (*enter_usb_mode)(struct typec_port *port, enum usb_mode mode); }; enum usb_pd_svdm_ver { @@ -264,6 +286,7 @@ enum usb_pd_svdm_ver { * @svdm_version: USB PD Structured VDM version if supported * @prefer_role: Initial role preference (DRP ports). * @accessory: Supported Accessory Modes + * @usb_capability: Supported USB Modes * @fwnode: Optional fwnode of the port * @driver_data: Private pointer for driver specific info * @pd: Optional USB Power Delivery Support @@ -280,6 +303,7 @@ struct typec_capability { int prefer_role; enum typec_accessory accessory[TYPEC_MAX_ACCESSORY]; unsigned int orientation_aware:1; + u8 usb_capability; struct fwnode_handle *fwnode; void *driver_data; @@ -347,6 +371,9 @@ int typec_port_set_usb_power_delivery(struct typec_port *port, struct usb_power_ int typec_partner_set_usb_power_delivery(struct typec_partner *partner, struct usb_power_delivery *pd); +void typec_partner_set_usb_mode(struct typec_partner *partner, enum usb_mode usb_mode); +void typec_port_set_usb_mode(struct typec_port *port, enum usb_mode mode); + /** * struct typec_connector - Representation of Type-C port for external drivers * @attach: notification about device removal diff --git a/include/linux/usb/typec_tbt.h b/include/linux/usb/typec_tbt.h index fa97d7e00f5c..55dcea12082c 100644 --- a/include/linux/usb/typec_tbt.h +++ b/include/linux/usb/typec_tbt.h @@ -44,6 +44,7 @@ struct typec_thunderbolt_data { #define TBT_GEN3_NON_ROUNDED 0 #define TBT_GEN3_GEN4_ROUNDED_NON_ROUNDED 1 +#define TBT_CABLE_ROUNDED BIT(19) #define TBT_CABLE_OPTICAL BIT(21) #define TBT_CABLE_RETIMER BIT(22) #define TBT_CABLE_LINK_TRAINING BIT(23) diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index 9f08a584d707..0b9f1e598e3a 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -76,8 +76,23 @@ struct usbnet { # define EVENT_LINK_CHANGE 11 # define EVENT_SET_RX_MODE 12 # define EVENT_NO_IP_ALIGN 13 +/* This one is special, as it indicates that the device is going away + * there are cyclic dependencies between tasklet, timer and bh + * that must be broken + */ +# define EVENT_UNPLUG 31 }; +static inline bool usbnet_going_away(struct usbnet *ubn) +{ + return test_bit(EVENT_UNPLUG, &ubn->flags); +} + +static inline void usbnet_mark_going_away(struct usbnet *ubn) +{ + set_bit(EVENT_UNPLUG, &ubn->flags); +} + static inline struct usb_driver *driver_of(struct usb_interface *intf) { return to_usb_driver(intf->dev.driver); diff --git a/include/linux/usb/uvc.h b/include/linux/usb/uvc.h index 88d96095bcb1..bce95153e5a6 100644 --- a/include/linux/usb/uvc.h +++ b/include/linux/usb/uvc.h @@ -118,6 +118,9 @@ #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_Y16I \ + { 'Y', '1', '6', '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} @@ -140,6 +143,9 @@ #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_D3DFMT_R5G6B5 \ + {0x7b, 0xeb, 0x36, 0xe4, 0x4f, 0x52, 0xce, 0x11, \ + 0x9f, 0x53, 0x00, 0x20, 0xaf, 0x0b, 0xa7, 0x70} #define UVC_GUID_FORMAT_KSMEDIA_L8_IR \ {0x32, 0x00, 0x00, 0x00, 0x02, 0x00, 0x10, 0x00, \ 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71} diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 6030a8235617..7183e5aca282 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -21,9 +21,11 @@ struct uid_gid_extent { }; struct uid_gid_map { /* 64 bytes -- 1 cache line */ - u32 nr_extents; union { - struct uid_gid_extent extent[UID_GID_MAP_MAX_BASE_EXTENTS]; + struct { + struct uid_gid_extent extent[UID_GID_MAP_MAX_BASE_EXTENTS]; + u32 nr_extents; + }; struct { struct uid_gid_extent *forward; struct uid_gid_extent *reverse; @@ -139,7 +141,8 @@ static inline long get_rlimit_value(struct ucounts *ucounts, enum rlimit_type ty long inc_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v); bool dec_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v); -long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type); +long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type, + bool override_rlimit); void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum rlimit_type type); bool is_rlimit_overlimit(struct ucounts *ucounts, enum rlimit_type type, unsigned long max); diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 05d59f74fc88..75342022d144 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -218,6 +218,9 @@ static inline bool vma_can_userfault(struct vm_area_struct *vma, { vm_flags &= __VM_UFFD_FLAGS; + if (vm_flags & VM_DROPPABLE) + return false; + if ((vm_flags & VM_UFFD_MINOR) && (!is_vm_hugetlb_page(vma) && !vma_is_shmem(vma))) return false; @@ -244,8 +247,16 @@ static inline bool vma_can_userfault(struct vm_area_struct *vma, vma_is_shmem(vma); } +static inline bool vma_has_uffd_without_event_remap(struct vm_area_struct *vma) +{ + struct userfaultfd_ctx *uffd_ctx = vma->vm_userfaultfd_ctx.ctx; + + return uffd_ctx && (uffd_ctx->features & UFFD_FEATURE_EVENT_REMAP) == 0; +} + extern int dup_userfaultfd(struct vm_area_struct *, struct list_head *); extern void dup_userfaultfd_complete(struct list_head *); +void dup_userfaultfd_fail(struct list_head *); extern void mremap_userfaultfd_prep(struct vm_area_struct *, struct vm_userfaultfd_ctx *); @@ -264,6 +275,25 @@ extern void userfaultfd_unmap_complete(struct mm_struct *mm, extern bool userfaultfd_wp_unpopulated(struct vm_area_struct *vma); extern bool userfaultfd_wp_async(struct vm_area_struct *vma); +void userfaultfd_reset_ctx(struct vm_area_struct *vma); + +struct vm_area_struct *userfaultfd_clear_vma(struct vma_iterator *vmi, + struct vm_area_struct *prev, + struct vm_area_struct *vma, + unsigned long start, + unsigned long end); + +int userfaultfd_register_range(struct userfaultfd_ctx *ctx, + struct vm_area_struct *vma, + unsigned long vm_flags, + unsigned long start, unsigned long end, + bool wp_async); + +void userfaultfd_release_new(struct userfaultfd_ctx *ctx); + +void userfaultfd_release_all(struct mm_struct *mm, + struct userfaultfd_ctx *ctx); + #else /* CONFIG_USERFAULTFD */ /* mm helpers */ @@ -329,6 +359,10 @@ static inline void dup_userfaultfd_complete(struct list_head *l) { } +static inline void dup_userfaultfd_fail(struct list_head *l) +{ +} + static inline void mremap_userfaultfd_prep(struct vm_area_struct *vma, struct vm_userfaultfd_ctx *ctx) { @@ -375,6 +409,11 @@ static inline bool userfaultfd_wp_async(struct vm_area_struct *vma) return false; } +static inline bool vma_has_uffd_without_event_remap(struct vm_area_struct *vma) +{ + return false; +} + #endif /* CONFIG_USERFAULTFD */ static inline bool userfaultfd_wp_use_markers(struct vm_area_struct *vma) diff --git a/include/linux/util_macros.h b/include/linux/util_macros.h index 6bb460c3e818..825487fb66fa 100644 --- a/include/linux/util_macros.h +++ b/include/linux/util_macros.h @@ -4,19 +4,6 @@ #include <linux/math.h> -#define __find_closest(x, a, as, op) \ -({ \ - typeof(as) __fc_i, __fc_as = (as) - 1; \ - typeof(x) __fc_x = (x); \ - typeof(*a) const *__fc_a = (a); \ - for (__fc_i = 0; __fc_i < __fc_as; __fc_i++) { \ - if (__fc_x op DIV_ROUND_CLOSEST(__fc_a[__fc_i] + \ - __fc_a[__fc_i + 1], 2)) \ - break; \ - } \ - (__fc_i); \ -}) - /** * find_closest - locate the closest element in a sorted array * @x: The reference value. @@ -25,8 +12,27 @@ * @as: Size of 'a'. * * Returns the index of the element closest to 'x'. + * Note: If using an array of negative numbers (or mixed positive numbers), + * then be sure that 'x' is of a signed-type to get good results. */ -#define find_closest(x, a, as) __find_closest(x, a, as, <=) +#define find_closest(x, a, as) \ +({ \ + typeof(as) __fc_i, __fc_as = (as) - 1; \ + long __fc_mid_x, __fc_x = (x); \ + long __fc_left, __fc_right; \ + typeof(*a) const *__fc_a = (a); \ + for (__fc_i = 0; __fc_i < __fc_as; __fc_i++) { \ + __fc_mid_x = (__fc_a[__fc_i] + __fc_a[__fc_i + 1]) / 2; \ + if (__fc_x <= __fc_mid_x) { \ + __fc_left = __fc_x - __fc_a[__fc_i]; \ + __fc_right = __fc_a[__fc_i + 1] - __fc_x; \ + if (__fc_right < __fc_left) \ + __fc_i++; \ + break; \ + } \ + } \ + (__fc_i); \ +}) /** * find_closest_descending - locate the closest element in a sorted array @@ -36,9 +42,27 @@ * @as: Size of 'a'. * * Similar to find_closest() but 'a' is expected to be sorted in descending - * order. + * order. The iteration is done in reverse order, so that the comparison + * of '__fc_right' & '__fc_left' also works for unsigned numbers. */ -#define find_closest_descending(x, a, as) __find_closest(x, a, as, >=) +#define find_closest_descending(x, a, as) \ +({ \ + typeof(as) __fc_i, __fc_as = (as) - 1; \ + long __fc_mid_x, __fc_x = (x); \ + long __fc_left, __fc_right; \ + typeof(*a) const *__fc_a = (a); \ + for (__fc_i = __fc_as; __fc_i >= 1; __fc_i--) { \ + __fc_mid_x = (__fc_a[__fc_i] + __fc_a[__fc_i - 1]) / 2; \ + if (__fc_x <= __fc_mid_x) { \ + __fc_left = __fc_x - __fc_a[__fc_i]; \ + __fc_right = __fc_a[__fc_i - 1] - __fc_x; \ + if (__fc_right < __fc_left) \ + __fc_i--; \ + break; \ + } \ + } \ + (__fc_i); \ +}) /** * is_insidevar - check if the @ptr points inside the @var memory range. diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 7977ca03ac7a..2e7a30fe6b92 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -582,11 +582,20 @@ void vdpa_set_status(struct vdpa_device *vdev, u8 status); * @dev: vdpa device to remove * Driver need to remove the specified device by calling * _vdpa_unregister_device(). + * @dev_set_attr: change a vdpa device's attr after it was create + * @mdev: parent device to use for device + * @dev: vdpa device structure + * @config:Attributes to be set for the device. + * The driver needs to check the mask of the structure and then set + * the related information to the vdpa device. The driver must return 0 + * if set successfully. */ struct vdpa_mgmtdev_ops { int (*dev_add)(struct vdpa_mgmt_dev *mdev, const char *name, const struct vdpa_dev_set_config *config); void (*dev_del)(struct vdpa_mgmt_dev *mdev, struct vdpa_device *dev); + int (*dev_set_attr)(struct vdpa_mgmt_dev *mdev, struct vdpa_device *dev, + const struct vdpa_dev_set_config *config); }; /** diff --git a/include/linux/verification.h b/include/linux/verification.h index cb2d47f28091..4f3022d081c3 100644 --- a/include/linux/verification.h +++ b/include/linux/verification.h @@ -38,8 +38,6 @@ enum key_being_used_for { VERIFYING_UNSPECIFIED_SIGNATURE, NR__KEY_BEING_USED_FOR }; -extern const char *const key_being_used_for[NR__KEY_BEING_USED_FOR]; - #ifdef CONFIG_SYSTEM_DATA_VERIFICATION struct key; diff --git a/include/linux/vermagic.h b/include/linux/vermagic.h index a54046bf37e5..939ceabcaf06 100644 --- a/include/linux/vermagic.h +++ b/include/linux/vermagic.h @@ -15,10 +15,10 @@ #else #define MODULE_VERMAGIC_SMP "" #endif -#ifdef CONFIG_PREEMPT_BUILD -#define MODULE_VERMAGIC_PREEMPT "preempt " -#elif defined(CONFIG_PREEMPT_RT) +#ifdef CONFIG_PREEMPT_RT #define MODULE_VERMAGIC_PREEMPT "preempt_rt " +#elif defined(CONFIG_PREEMPT_BUILD) +#define MODULE_VERMAGIC_PREEMPT "preempt " #else #define MODULE_VERMAGIC_PREEMPT "" #endif diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 8b1a29820409..000a6cab2d31 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -64,6 +64,7 @@ struct vfio_device { struct completion comp; struct iommufd_access *iommufd_access; void (*put_kvm)(struct kvm *kvm); + struct inode *inode; #if IS_ENABLED(CONFIG_IOMMUFD) struct iommufd_device *iommufd_device; u8 iommufd_attached:1; diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index a2c8b8bba711..fbb472dd99b3 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -93,8 +93,6 @@ struct vfio_pci_core_device { struct list_head sriov_pfs_item; struct vfio_pci_core_device *sriov_pf_core_dev; struct notifier_block nb; - struct mutex vma_lock; - struct list_head vma_list; struct rw_semaphore memory_lock; }; @@ -139,23 +137,26 @@ bool vfio_pci_core_range_intersect_range(loff_t buf_start, size_t buf_cnt, loff_t *buf_offset, size_t *intersect_count, size_t *register_offset); -#define VFIO_IOWRITE_DECLATION(size) \ +#define VFIO_IOWRITE_DECLARATION(size) \ int vfio_pci_core_iowrite##size(struct vfio_pci_core_device *vdev, \ bool test_mem, u##size val, void __iomem *io); -VFIO_IOWRITE_DECLATION(8) -VFIO_IOWRITE_DECLATION(16) -VFIO_IOWRITE_DECLATION(32) +VFIO_IOWRITE_DECLARATION(8) +VFIO_IOWRITE_DECLARATION(16) +VFIO_IOWRITE_DECLARATION(32) #ifdef iowrite64 -VFIO_IOWRITE_DECLATION(64) +VFIO_IOWRITE_DECLARATION(64) #endif -#define VFIO_IOREAD_DECLATION(size) \ +#define VFIO_IOREAD_DECLARATION(size) \ int vfio_pci_core_ioread##size(struct vfio_pci_core_device *vdev, \ bool test_mem, u##size *val, void __iomem *io); -VFIO_IOREAD_DECLATION(8) -VFIO_IOREAD_DECLATION(16) -VFIO_IOREAD_DECLATION(32) +VFIO_IOREAD_DECLARATION(8) +VFIO_IOREAD_DECLARATION(16) +VFIO_IOREAD_DECLARATION(32) +#ifdef ioread64 +VFIO_IOREAD_DECLARATION(64) +#endif #endif /* VFIO_PCI_CORE_H */ diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 26c4325aa373..4d16c13d0df5 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -10,6 +10,7 @@ #include <linux/mod_devicetable.h> #include <linux/gfp.h> #include <linux/dma-mapping.h> +#include <linux/completion.h> /** * struct virtqueue - a queue to register buffers for sending or receiving. @@ -55,6 +56,17 @@ int virtqueue_add_inbuf_ctx(struct virtqueue *vq, void *ctx, gfp_t gfp); +int virtqueue_add_inbuf_premapped(struct virtqueue *vq, + struct scatterlist *sg, unsigned int num, + void *data, + void *ctx, + gfp_t gfp); + +int virtqueue_add_outbuf_premapped(struct virtqueue *vq, + struct scatterlist *sg, unsigned int num, + void *data, + gfp_t gfp); + int virtqueue_add_sgs(struct virtqueue *vq, struct scatterlist *sgs[], unsigned int out_sgs, @@ -81,8 +93,6 @@ bool virtqueue_enable_cb(struct virtqueue *vq); unsigned virtqueue_enable_cb_prepare(struct virtqueue *vq); -int virtqueue_set_dma_premapped(struct virtqueue *_vq); - bool virtqueue_poll(struct virtqueue *vq, unsigned); bool virtqueue_enable_cb_delayed(struct virtqueue *vq); @@ -99,9 +109,11 @@ dma_addr_t virtqueue_get_avail_addr(const struct virtqueue *vq); dma_addr_t virtqueue_get_used_addr(const struct virtqueue *vq); int virtqueue_resize(struct virtqueue *vq, u32 num, - void (*recycle)(struct virtqueue *vq, void *buf)); + void (*recycle)(struct virtqueue *vq, void *buf), + void (*recycle_done)(struct virtqueue *vq)); int virtqueue_reset(struct virtqueue *vq, - void (*recycle)(struct virtqueue *vq, void *buf)); + void (*recycle)(struct virtqueue *vq, void *buf), + void (*recycle_done)(struct virtqueue *vq)); struct virtio_admin_cmd { __le16 opcode; @@ -109,13 +121,18 @@ struct virtio_admin_cmd { __le64 group_member_id; struct scatterlist *data_sg; struct scatterlist *result_sg; + struct completion completion; + u32 result_sg_size; + int ret; }; /** * struct virtio_device - representation of a device using virtio * @index: unique position on the virtio bus * @failed: saved value for VIRTIO_CONFIG_S_FAILED bit (for restore) - * @config_enabled: configuration change reporting enabled + * @config_core_enabled: configuration change reporting enabled by core + * @config_driver_disabled: configuration change reporting disabled by + * a driver * @config_change_pending: configuration change reported while disabled * @config_lock: protects configuration change reporting * @vqs_list_lock: protects @vqs. @@ -126,11 +143,14 @@ struct virtio_admin_cmd { * @vqs: the list of virtqueues for this device. * @features: the features supported by both driver and device. * @priv: private pointer for the driver's use. + * @debugfs_dir: debugfs directory entry. + * @debugfs_filter_features: features to be filtered set by debugfs. */ struct virtio_device { int index; bool failed; - bool config_enabled; + bool config_core_enabled; + bool config_driver_disabled; bool config_change_pending; spinlock_t config_lock; spinlock_t vqs_list_lock; @@ -141,6 +161,10 @@ struct virtio_device { struct list_head vqs; u64 features; void *priv; +#ifdef CONFIG_VIRTIO_DEBUG + struct dentry *debugfs_dir; + u64 debugfs_filter_features; +#endif }; #define dev_to_virtio(_dev) container_of_const(_dev, struct virtio_device, dev) @@ -157,11 +181,17 @@ void __virtqueue_break(struct virtqueue *_vq); void __virtqueue_unbreak(struct virtqueue *_vq); void virtio_config_changed(struct virtio_device *dev); + +void virtio_config_driver_disable(struct virtio_device *dev); +void virtio_config_driver_enable(struct virtio_device *dev); + #ifdef CONFIG_PM_SLEEP int virtio_device_freeze(struct virtio_device *dev); int virtio_device_restore(struct virtio_device *dev); #endif void virtio_reset_device(struct virtio_device *dev); +int virtio_device_reset_prepare(struct virtio_device *dev); +int virtio_device_reset_done(struct virtio_device *dev); size_t virtio_max_dma_size(const struct virtio_device *vdev); @@ -186,6 +216,10 @@ size_t virtio_max_dma_size(const struct virtio_device *vdev); * changes; may be called in interrupt context. * @freeze: optional function to call during suspend/hibernation. * @restore: optional function to call on resume. + * @reset_prepare: optional function to call when a transport specific reset + * occurs. + * @reset_done: optional function to call after transport specific reset + * operation has finished. */ struct virtio_driver { struct device_driver driver; @@ -201,12 +235,11 @@ struct virtio_driver { void (*config_changed)(struct virtio_device *dev); int (*freeze)(struct virtio_device *dev); int (*restore)(struct virtio_device *dev); + int (*reset_prepare)(struct virtio_device *dev); + int (*reset_done)(struct virtio_device *dev); }; -static inline struct virtio_driver *drv_to_virtio(struct device_driver *drv) -{ - return container_of(drv, struct virtio_driver, driver); -} +#define drv_to_virtio(__drv) container_of_const(__drv, struct virtio_driver, driver) /* use a macro to avoid include chaining to get THIS_MODULE */ #define register_virtio_driver(drv) \ @@ -237,4 +270,33 @@ void virtqueue_dma_sync_single_range_for_cpu(struct virtqueue *_vq, dma_addr_t a void virtqueue_dma_sync_single_range_for_device(struct virtqueue *_vq, dma_addr_t addr, unsigned long offset, size_t size, enum dma_data_direction dir); + +#ifdef CONFIG_VIRTIO_DEBUG +void virtio_debug_device_init(struct virtio_device *dev); +void virtio_debug_device_exit(struct virtio_device *dev); +void virtio_debug_device_filter_features(struct virtio_device *dev); +void virtio_debug_init(void); +void virtio_debug_exit(void); +#else +static inline void virtio_debug_device_init(struct virtio_device *dev) +{ +} + +static inline void virtio_debug_device_exit(struct virtio_device *dev) +{ +} + +static inline void virtio_debug_device_filter_features(struct virtio_device *dev) +{ +} + +static inline void virtio_debug_init(void) +{ +} + +static inline void virtio_debug_exit(void) +{ +} +#endif + #endif /* _LINUX_VIRTIO_H */ diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index da9b271b54db..169c7d367fac 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -19,6 +19,20 @@ struct virtio_shm_region { typedef void vq_callback_t(struct virtqueue *); /** + * struct virtqueue_info - Info for a virtqueue passed to find_vqs(). + * @name: virtqueue description. Used mainly for debugging, NULL for + * a virtqueue unused by the driver. + * @callback: A callback to invoke on a used buffer notification. + * NULL for a virtqueue that does not need a callback. + * @ctx: A flag to indicate to maintain an extra context per virtqueue. + */ +struct virtqueue_info { + const char *name; + vq_callback_t *callback; + bool ctx; +}; + +/** * 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, @@ -53,10 +67,7 @@ typedef void vq_callback_t(struct virtqueue *); * vdev: the virtio_device * nvqs: the number of virtqueues to find * vqs: on success, includes new virtqueues - * callbacks: array of callbacks, for each virtqueue - * include a NULL entry for vqs that do not need a callback - * names: array of virtqueue names (mainly for debugging) - * include a NULL entry for vqs unused by driver + * vqs_info: array of virtqueue info structures * Returns 0 on success or error status * @del_vqs: free virtqueues found by find_vqs(). * @synchronize_cbs: synchronize with the virtqueue callbacks (optional) @@ -93,8 +104,6 @@ typedef void vq_callback_t(struct virtqueue *); * Returns 0 on success or error status * If disable_vq_and_reset is set, then enable_vq_after_reset must also be * set. - * @create_avq: create admin virtqueue resource. - * @destroy_avq: destroy admin virtqueue resource. */ struct virtio_config_ops { void (*get)(struct virtio_device *vdev, unsigned offset, @@ -105,9 +114,9 @@ struct virtio_config_ops { u8 (*get_status)(struct virtio_device *vdev); void (*set_status)(struct virtio_device *vdev, u8 status); void (*reset)(struct virtio_device *vdev); - int (*find_vqs)(struct virtio_device *, unsigned nvqs, - struct virtqueue *vqs[], vq_callback_t *callbacks[], - const char * const names[], const bool *ctx, + int (*find_vqs)(struct virtio_device *vdev, unsigned int nvqs, + struct virtqueue *vqs[], + struct virtqueue_info vqs_info[], struct irq_affinity *desc); void (*del_vqs)(struct virtio_device *); void (*synchronize_cbs)(struct virtio_device *); @@ -117,13 +126,11 @@ struct virtio_config_ops { int (*set_vq_affinity)(struct virtqueue *vq, const struct cpumask *cpu_mask); const struct cpumask *(*get_vq_affinity)(struct virtio_device *vdev, - int index); + int index); bool (*get_shm_region)(struct virtio_device *vdev, struct virtio_shm_region *region, u8 id); int (*disable_vq_and_reset)(struct virtqueue *vq); int (*enable_vq_after_reset)(struct virtqueue *vq); - int (*create_avq)(struct virtio_device *vdev); - void (*destroy_avq)(struct virtio_device *vdev); }; /* If driver didn't advertise the feature, it will never appear. */ @@ -211,38 +218,29 @@ static inline bool virtio_has_dma_quirk(const struct virtio_device *vdev) } static inline +int virtio_find_vqs(struct virtio_device *vdev, unsigned int nvqs, + struct virtqueue *vqs[], + struct virtqueue_info vqs_info[], + struct irq_affinity *desc) +{ + return vdev->config->find_vqs(vdev, nvqs, vqs, vqs_info, desc); +} + +static inline struct virtqueue *virtio_find_single_vq(struct virtio_device *vdev, vq_callback_t *c, const char *n) { - vq_callback_t *callbacks[] = { c }; - const char *names[] = { n }; + struct virtqueue_info vqs_info[] = { + { n, c }, + }; struct virtqueue *vq; - int err = vdev->config->find_vqs(vdev, 1, &vq, callbacks, names, NULL, - NULL); + int err = virtio_find_vqs(vdev, 1, &vq, vqs_info, NULL); + if (err < 0) return ERR_PTR(err); return vq; } -static inline -int virtio_find_vqs(struct virtio_device *vdev, unsigned nvqs, - struct virtqueue *vqs[], vq_callback_t *callbacks[], - const char * const names[], - struct irq_affinity *desc) -{ - return vdev->config->find_vqs(vdev, nvqs, vqs, callbacks, names, NULL, desc); -} - -static inline -int virtio_find_vqs_ctx(struct virtio_device *vdev, unsigned nvqs, - struct virtqueue *vqs[], vq_callback_t *callbacks[], - const char * const names[], const bool *ctx, - struct irq_affinity *desc) -{ - return vdev->config->find_vqs(vdev, nvqs, vqs, callbacks, names, ctx, - desc); -} - /** * virtio_synchronize_cbs - synchronize with virtqueue callbacks * @dev: the virtio device diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 4dfa9b69ca8d..02a9f4dc594d 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -103,8 +103,10 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, if (!skb_partial_csum_set(skb, start, off)) return -EINVAL; + if (skb_transport_offset(skb) < nh_min_len) + return -EINVAL; - nh_min_len = max_t(u32, nh_min_len, skb_transport_offset(skb)); + nh_min_len = skb_transport_offset(skb); p_off = nh_min_len + thlen; if (!pskb_may_pull(skb, p_off)) return -EINVAL; @@ -171,6 +173,12 @@ retry: if (gso_type != SKB_GSO_UDP_L4) return -EINVAL; break; + case SKB_GSO_TCPV4: + case SKB_GSO_TCPV6: + if (skb->ip_summed == CHECKSUM_PARTIAL && + skb->csum_offset != offsetof(struct tcphdr, check)) + return -EINVAL; + break; } /* Kernel has a special handling for GSO_BY_FRAGS. */ diff --git a/include/linux/virtio_pci_admin.h b/include/linux/virtio_pci_admin.h index f4a100a0fe2e..dffc92c17ad2 100644 --- a/include/linux/virtio_pci_admin.h +++ b/include/linux/virtio_pci_admin.h @@ -20,4 +20,15 @@ int virtio_pci_admin_legacy_io_notify_info(struct pci_dev *pdev, u64 *bar_offset); #endif +bool virtio_pci_admin_has_dev_parts(struct pci_dev *pdev); +int virtio_pci_admin_mode_set(struct pci_dev *pdev, u8 mode); +int virtio_pci_admin_obj_create(struct pci_dev *pdev, u16 obj_type, u8 operation_type, + u32 *obj_id); +int virtio_pci_admin_obj_destroy(struct pci_dev *pdev, u16 obj_type, u32 id); +int virtio_pci_admin_dev_parts_metadata_get(struct pci_dev *pdev, u16 obj_type, + u32 id, u8 metadata_type, u32 *out); +int virtio_pci_admin_dev_parts_get(struct pci_dev *pdev, u16 obj_type, u32 id, + u8 get_type, struct scatterlist *res_sg, u32 *res_size); +int virtio_pci_admin_dev_parts_set(struct pci_dev *pdev, struct scatterlist *data_sg); + #endif /* _LINUX_VIRTIO_PCI_ADMIN_H */ diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index c82089dee0c8..0387d64e2c66 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -133,6 +133,7 @@ struct virtio_vsock_sock { u32 tx_cnt; u32 peer_fwd_cnt; u32 peer_buf_alloc; + size_t bytes_unsent; /* Protected by rx_lock */ u32 fwd_cnt; @@ -193,6 +194,11 @@ s64 virtio_transport_stream_has_data(struct vsock_sock *vsk); s64 virtio_transport_stream_has_space(struct vsock_sock *vsk); u32 virtio_transport_seqpacket_has_data(struct vsock_sock *vsk); +ssize_t virtio_transport_unsent_bytes(struct vsock_sock *vsk); + +void virtio_transport_consume_skb_sent(struct sk_buff *skb, + bool consume); + int virtio_transport_do_socket_init(struct vsock_sock *vsk, struct vsock_sock *psk); int diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 747943bc8cc2..f70d0958095c 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -50,6 +50,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, PGSTEAL_ANON, PGSTEAL_FILE, #ifdef CONFIG_NUMA + PGSCAN_ZONE_RECLAIM_SUCCESS, PGSCAN_ZONE_RECLAIM_FAILED, #endif PGINODESTEAL, SLABS_SCANNED, KSWAPD_INODESTEAL, @@ -104,6 +105,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, THP_SPLIT_PAGE, THP_SPLIT_PAGE_FAILED, THP_DEFERRED_SPLIT_PAGE, + THP_UNDERUSED_SPLIT_PAGE, THP_SPLIT_PMD, THP_SCAN_EXCEED_NONE_PTE, THP_SCAN_EXCEED_SWAP_PTE, @@ -132,6 +134,8 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, #ifdef CONFIG_SWAP SWAP_RA, SWAP_RA_HIT, + SWPIN_ZERO, + SWPOUT_ZERO, #ifdef CONFIG_KSM KSM_SWPIN_COPY, #endif @@ -154,6 +158,30 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, VMA_LOCK_RETRY, VMA_LOCK_MISS, #endif +#ifdef CONFIG_DEBUG_STACK_USAGE + KSTACK_1K, +#if THREAD_SIZE > 1024 + KSTACK_2K, +#endif +#if THREAD_SIZE > 2048 + KSTACK_4K, +#endif +#if THREAD_SIZE > 4096 + KSTACK_8K, +#endif +#if THREAD_SIZE > 8192 + KSTACK_16K, +#endif +#if THREAD_SIZE > 16384 + KSTACK_32K, +#endif +#if THREAD_SIZE > 32768 + KSTACK_64K, +#endif +#if THREAD_SIZE > 65536 + KSTACK_REST, +#endif +#endif /* CONFIG_DEBUG_STACK_USAGE */ NR_VM_EVENT_ITEMS }; diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 98ea90e90439..31e9ffd936e3 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -2,6 +2,8 @@ #ifndef _LINUX_VMALLOC_H #define _LINUX_VMALLOC_H +#include <linux/alloc_tag.h> +#include <linux/sched.h> #include <linux/spinlock.h> #include <linux/init.h> #include <linux/list.h> @@ -132,32 +134,58 @@ extern void vm_unmap_ram(const void *mem, unsigned int count); extern void *vm_map_ram(struct page **pages, unsigned int count, int node); extern void vm_unmap_aliases(void); -#ifdef CONFIG_MMU -extern unsigned long vmalloc_nr_pages(void); -#else -static inline unsigned long vmalloc_nr_pages(void) { return 0; } -#endif +extern void *vmalloc_noprof(unsigned long size) __alloc_size(1); +#define vmalloc(...) alloc_hooks(vmalloc_noprof(__VA_ARGS__)) + +extern void *vzalloc_noprof(unsigned long size) __alloc_size(1); +#define vzalloc(...) alloc_hooks(vzalloc_noprof(__VA_ARGS__)) + +extern void *vmalloc_user_noprof(unsigned long size) __alloc_size(1); +#define vmalloc_user(...) alloc_hooks(vmalloc_user_noprof(__VA_ARGS__)) + +extern void *vmalloc_node_noprof(unsigned long size, int node) __alloc_size(1); +#define vmalloc_node(...) alloc_hooks(vmalloc_node_noprof(__VA_ARGS__)) -extern void *vmalloc(unsigned long size) __alloc_size(1); -extern void *vzalloc(unsigned long size) __alloc_size(1); -extern void *vmalloc_user(unsigned long size) __alloc_size(1); -extern void *vmalloc_node(unsigned long size, int node) __alloc_size(1); -extern void *vzalloc_node(unsigned long size, int node) __alloc_size(1); -extern void *vmalloc_32(unsigned long size) __alloc_size(1); -extern void *vmalloc_32_user(unsigned long size) __alloc_size(1); -extern void *__vmalloc(unsigned long size, gfp_t gfp_mask) __alloc_size(1); -extern void *__vmalloc_node_range(unsigned long size, unsigned long align, +extern void *vzalloc_node_noprof(unsigned long size, int node) __alloc_size(1); +#define vzalloc_node(...) alloc_hooks(vzalloc_node_noprof(__VA_ARGS__)) + +extern void *vmalloc_32_noprof(unsigned long size) __alloc_size(1); +#define vmalloc_32(...) alloc_hooks(vmalloc_32_noprof(__VA_ARGS__)) + +extern void *vmalloc_32_user_noprof(unsigned long size) __alloc_size(1); +#define vmalloc_32_user(...) alloc_hooks(vmalloc_32_user_noprof(__VA_ARGS__)) + +extern void *__vmalloc_noprof(unsigned long size, gfp_t gfp_mask) __alloc_size(1); +#define __vmalloc(...) alloc_hooks(__vmalloc_noprof(__VA_ARGS__)) + +extern void *__vmalloc_node_range_noprof(unsigned long size, unsigned long align, unsigned long start, unsigned long end, gfp_t gfp_mask, pgprot_t prot, unsigned long vm_flags, int node, const void *caller) __alloc_size(1); -void *__vmalloc_node(unsigned long size, unsigned long align, gfp_t gfp_mask, +#define __vmalloc_node_range(...) alloc_hooks(__vmalloc_node_range_noprof(__VA_ARGS__)) + +void *__vmalloc_node_noprof(unsigned long size, unsigned long align, gfp_t gfp_mask, int node, const void *caller) __alloc_size(1); -void *vmalloc_huge(unsigned long size, gfp_t gfp_mask) __alloc_size(1); +#define __vmalloc_node(...) alloc_hooks(__vmalloc_node_noprof(__VA_ARGS__)) + +void *vmalloc_huge_noprof(unsigned long size, gfp_t gfp_mask) __alloc_size(1); +#define vmalloc_huge(...) alloc_hooks(vmalloc_huge_noprof(__VA_ARGS__)) + +extern void *__vmalloc_array_noprof(size_t n, size_t size, gfp_t flags) __alloc_size(1, 2); +#define __vmalloc_array(...) alloc_hooks(__vmalloc_array_noprof(__VA_ARGS__)) -extern void *__vmalloc_array(size_t n, size_t size, gfp_t flags) __alloc_size(1, 2); -extern void *vmalloc_array(size_t n, size_t size) __alloc_size(1, 2); -extern void *__vcalloc(size_t n, size_t size, gfp_t flags) __alloc_size(1, 2); -extern void *vcalloc(size_t n, size_t size) __alloc_size(1, 2); +extern void *vmalloc_array_noprof(size_t n, size_t size) __alloc_size(1, 2); +#define vmalloc_array(...) alloc_hooks(vmalloc_array_noprof(__VA_ARGS__)) + +extern void *__vcalloc_noprof(size_t n, size_t size, gfp_t flags) __alloc_size(1, 2); +#define __vcalloc(...) alloc_hooks(__vcalloc_noprof(__VA_ARGS__)) + +extern void *vcalloc_noprof(size_t n, size_t size) __alloc_size(1, 2); +#define vcalloc(...) alloc_hooks(vcalloc_noprof(__VA_ARGS__)) + +void * __must_check vrealloc_noprof(const void *p, size_t size, gfp_t flags) + __realloc_size(2); +#define vrealloc(...) alloc_hooks(vrealloc_noprof(__VA_ARGS__)) extern void vfree(const void *addr); extern void vfree_atomic(const void *addr); @@ -174,6 +202,9 @@ extern int remap_vmalloc_range_partial(struct vm_area_struct *vma, extern int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, unsigned long pgoff); +int vmap_pages_range(unsigned long addr, unsigned long end, pgprot_t prot, + struct page **pages, unsigned int page_shift); + /* * Architectures can set this mask to a combination of PGTBL_P?D_MODIFIED values * and let generic vmalloc and ioremap code know when arch_sync_kernel_mappings() @@ -232,12 +263,29 @@ static inline bool is_vm_area_hugepages(const void *addr) #endif } +/* for /proc/kcore */ +long vread_iter(struct iov_iter *iter, const char *addr, size_t count); + +/* + * Internals. Don't use.. + */ +__init void vm_area_add_early(struct vm_struct *vm); +__init void vm_area_register_early(struct vm_struct *vm, size_t align); + +int register_vmap_purge_notifier(struct notifier_block *nb); +int unregister_vmap_purge_notifier(struct notifier_block *nb); + #ifdef CONFIG_MMU +#define VMALLOC_TOTAL (VMALLOC_END - VMALLOC_START) + +unsigned long vmalloc_nr_pages(void); + int vm_area_map_pages(struct vm_struct *area, unsigned long start, unsigned long end, struct page **pages); void vm_area_unmap_pages(struct vm_struct *area, unsigned long start, unsigned long end); void vunmap_range(unsigned long addr, unsigned long end); + static inline void set_vm_flush_reset_perms(void *addr) { struct vm_struct *vm = find_vm_area(addr); @@ -245,24 +293,14 @@ static inline void set_vm_flush_reset_perms(void *addr) if (vm) vm->flags |= VM_FLUSH_RESET_PERMS; } +#else /* !CONFIG_MMU */ +#define VMALLOC_TOTAL 0UL -#else -static inline void set_vm_flush_reset_perms(void *addr) -{ -} -#endif - -/* for /proc/kcore */ -extern long vread_iter(struct iov_iter *iter, const char *addr, size_t count); - -/* - * Internals. Don't use.. - */ -extern __init void vm_area_add_early(struct vm_struct *vm); -extern __init void vm_area_register_early(struct vm_struct *vm, size_t align); +static inline unsigned long vmalloc_nr_pages(void) { return 0; } +static inline void set_vm_flush_reset_perms(void *addr) {} +#endif /* CONFIG_MMU */ -#ifdef CONFIG_SMP -# ifdef CONFIG_MMU +#if defined(CONFIG_MMU) && defined(CONFIG_SMP) struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, const size_t *sizes, int nr_vms, size_t align); @@ -277,22 +315,9 @@ pcpu_get_vm_areas(const unsigned long *offsets, return NULL; } -static inline void -pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms) -{ -} -# endif +static inline void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms) {} #endif -#ifdef CONFIG_MMU -#define VMALLOC_TOTAL (VMALLOC_END - VMALLOC_START) -#else -#define VMALLOC_TOTAL 0UL -#endif - -int register_vmap_purge_notifier(struct notifier_block *nb); -int unregister_vmap_purge_notifier(struct notifier_block *nb); - #if defined(CONFIG_MMU) && defined(CONFIG_PRINTK) bool vmalloc_dump_obj(void *object); #else diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 343906a98d6e..9f3a04345b86 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -17,7 +17,7 @@ extern int sysctl_stat_interval; #define DISABLE_NUMA_STAT 0 extern int sysctl_vm_numa_stat; DECLARE_STATIC_KEY_TRUE(vm_numa_stat_key); -int sysctl_vm_numa_stat_handler(struct ctl_table *table, int write, +int sysctl_vm_numa_stat_handler(const struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos); #endif @@ -32,12 +32,16 @@ struct reclaim_stat { unsigned nr_ref_keep; unsigned nr_unmap_fail; unsigned nr_lazyfree_fail; + unsigned nr_demoted; }; -enum writeback_stat_item { +/* Stat data for system wide items */ +enum vm_stat_item { NR_DIRTY_THRESHOLD, NR_DIRTY_BG_THRESHOLD, - NR_VM_WRITEBACK_STAT_ITEMS, + NR_MEMMAP_PAGES, /* page metadata allocated through buddy allocator */ + NR_MEMMAP_BOOT_PAGES, /* page metadata allocated through boot allocator */ + NR_VM_STAT_ITEMS, }; #ifdef CONFIG_VM_EVENT_COUNTERS @@ -301,7 +305,7 @@ void cpu_vm_stats_fold(int cpu); void refresh_zone_stat_thresholds(void); struct ctl_table; -int vmstat_refresh(struct ctl_table *, int write, void *buffer, size_t *lenp, +int vmstat_refresh(const struct ctl_table *, int write, void *buffer, size_t *lenp, loff_t *ppos); void drain_zonestat(struct zone *zone, struct per_cpu_zonestat *); @@ -487,14 +491,6 @@ static inline void node_stat_sub_folio(struct folio *folio, mod_node_page_state(folio_pgdat(folio), item, -folio_nr_pages(folio)); } -static inline void __mod_zone_freepage_state(struct zone *zone, int nr_pages, - int migratetype) -{ - __mod_zone_page_state(zone, NR_FREE_PAGES, nr_pages); - if (is_migrate_cma(migratetype)) - __mod_zone_page_state(zone, NR_FREE_CMA_PAGES, nr_pages); -} - extern const char * const vmstat_text[]; static inline const char *zone_stat_name(enum zone_stat_item item) @@ -519,15 +515,7 @@ static inline const char *node_stat_name(enum node_stat_item item) static inline const char *lru_list_name(enum lru_list lru) { - return node_stat_name(NR_LRU_BASE + lru) + 3; // skip "nr_" -} - -static inline const char *writeback_stat_name(enum writeback_stat_item item) -{ - return vmstat_text[NR_VM_ZONE_STAT_ITEMS + - NR_VM_NUMA_EVENT_ITEMS + - NR_VM_NODE_STAT_ITEMS + - item]; + return node_stat_name(NR_LRU_BASE + (enum node_stat_item)lru) + 3; // skip "nr_" } #if defined(CONFIG_VM_EVENT_COUNTERS) || defined(CONFIG_MEMCG) @@ -536,7 +524,7 @@ static inline const char *vm_event_name(enum vm_event_item item) return vmstat_text[NR_VM_ZONE_STAT_ITEMS + NR_VM_NUMA_EVENT_ITEMS + NR_VM_NODE_STAT_ITEMS + - NR_VM_WRITEBACK_STAT_ITEMS + + NR_VM_STAT_ITEMS + item]; } #endif /* CONFIG_VM_EVENT_COUNTERS || CONFIG_MEMCG */ @@ -632,4 +620,7 @@ static inline void lruvec_stat_sub_folio(struct folio *folio, { lruvec_stat_mod_folio(folio, idx, -folio_nr_pages(folio)); } + +void memmap_boot_pages_add(long delta); +void memmap_pages_add(long delta); #endif /* _LINUX_VMSTAT_H */ diff --git a/include/linux/vmw_vmci_defs.h b/include/linux/vmw_vmci_defs.h index 6fb663b36f72..60c9eacd2cf3 100644 --- a/include/linux/vmw_vmci_defs.h +++ b/include/linux/vmw_vmci_defs.h @@ -431,11 +431,11 @@ enum { ((((_p)[0] & 0xFF) << 24) | (((_p)[1] & 0xFF) << 16) | ((_p)[2])) /* - * The VMCI IOCTLs. We use identity code 7, as noted in ioctl-number.h, and - * we start at sequence 9f. This gives us the same values that our shipping - * products use, starting at 1951, provided we leave out the direction and - * structure size. Note that VMMon occupies the block following us, starting - * at 2001. + * The VMCI IOCTLs. We use identity code 7, as noted in ioctl-number.rst, + * and we start at sequence 9f. This gives us the same values that our + * shipping products use, starting at 1951, provided we leave out the + * direction and structure size. Note that VMMon occupies the block + * following us, starting at 2001. */ #define IOCTL_VMCI_VERSION _IO(7, 0x9f) /* 1951 */ #define IOCTL_VMCI_INIT_CONTEXT _IO(7, 0xa0) @@ -453,9 +453,7 @@ enum { #define IOCTL_VMCI_CTX_GET_CPT_STATE _IO(7, 0xb1) #define IOCTL_VMCI_CTX_SET_CPT_STATE _IO(7, 0xb2) #define IOCTL_VMCI_GET_CONTEXT_ID _IO(7, 0xb3) -#define IOCTL_VMCI_SOCKETS_VERSION _IO(7, 0xb4) -#define IOCTL_VMCI_SOCKETS_GET_AF_VALUE _IO(7, 0xb8) -#define IOCTL_VMCI_SOCKETS_GET_LOCAL_CID _IO(7, 0xb9) +/*IOCTL_VM_SOCKETS_GET_LOCAL_CID _IO(7, 0xb9)*/ #define IOCTL_VMCI_SET_NOTIFY _IO(7, 0xcb) /* 1995 */ /*IOCTL_VMMON_START _IO(7, 0xd1)*/ /* 2001 */ diff --git a/include/linux/vt_buffer.h b/include/linux/vt_buffer.h index 919d999a8c1d..b6eeb8cb6070 100644 --- a/include/linux/vt_buffer.h +++ b/include/linux/vt_buffer.h @@ -28,45 +28,21 @@ #ifndef VT_BUF_HAVE_MEMSETW static inline void scr_memsetw(u16 *s, u16 c, unsigned int count) { -#ifdef VT_BUF_HAVE_RW - count /= 2; - while (count--) - scr_writew(c, s++); -#else memset16(s, c, count / 2); -#endif } #endif #ifndef VT_BUF_HAVE_MEMCPYW static inline void scr_memcpyw(u16 *d, const u16 *s, unsigned int count) { -#ifdef VT_BUF_HAVE_RW - count /= 2; - while (count--) - scr_writew(scr_readw(s++), d++); -#else memcpy(d, s, count); -#endif } #endif #ifndef VT_BUF_HAVE_MEMMOVEW static inline void scr_memmovew(u16 *d, const u16 *s, unsigned int count) { -#ifdef VT_BUF_HAVE_RW - if (d < s) - scr_memcpyw(d, s, count); - else { - count /= 2; - d += count; - s += count; - while (count--) - scr_writew(scr_readw(--s), --d); - } -#else memmove(d, s, count); -#endif } #endif diff --git a/include/linux/vtime.h b/include/linux/vtime.h index 3684487d01e1..29dd5b91dd7d 100644 --- a/include/linux/vtime.h +++ b/include/linux/vtime.h @@ -5,10 +5,6 @@ #include <linux/context_tracking_state.h> #include <linux/sched.h> -#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE -#include <asm/vtime.h> -#endif - /* * Common vtime APIs */ @@ -18,7 +14,6 @@ extern void vtime_account_idle(struct task_struct *tsk); #endif /* !CONFIG_VIRT_CPU_ACCOUNTING */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN -extern void arch_vtime_task_switch(struct task_struct *tsk); extern void vtime_user_enter(struct task_struct *tsk); extern void vtime_user_exit(struct task_struct *tsk); extern void vtime_guest_enter(struct task_struct *tsk); diff --git a/include/linux/w1.h b/include/linux/w1.h index 9a2a0ef39018..064805bfae3f 100644 --- a/include/linux/w1.h +++ b/include/linux/w1.h @@ -85,7 +85,8 @@ typedef void (*w1_slave_found_callback)(struct w1_master *, u64); * * @data: the first parameter in all the functions below * - * @read_bit: Sample the line level @return the level read (0 or 1) + * @read_bit: Sample the line level + * @return the level read (0 or 1) * * @write_bit: Sets the line level * @@ -95,7 +96,7 @@ typedef void (*w1_slave_found_callback)(struct w1_master *, u64); * touch_bit(1) = write-1 / read cycle * @return the bit read (0 or 1) * - * @read_byte: Reads a bytes. Same as 8 touch_bit(1) calls. + * @read_byte: Reads a byte. Same as 8 touch_bit(1) calls. * @return the byte read * * @write_byte: Writes a byte. Same as 8 touch_bit(x) calls. @@ -114,7 +115,7 @@ typedef void (*w1_slave_found_callback)(struct w1_master *, u64); * @set_pullup: Put out a strong pull-up pulse of the specified duration. * @return -1=Error, 0=completed * - * @search: Really nice hardware can handles the different types of ROM search + * @search: Really nice hardware can handle the different types of ROM search * w1_master* is passed to the slave found callback. * u8 is search_type, W1_SEARCH or W1_ALARM_SEARCH * diff --git a/include/linux/wait.h b/include/linux/wait.h index 8aa3372f21a0..6d90ad974408 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -221,6 +221,7 @@ void __wake_up_pollfree(struct wait_queue_head *wq_head); #define wake_up_all(x) __wake_up(x, TASK_NORMAL, 0, NULL) #define wake_up_locked(x) __wake_up_locked((x), TASK_NORMAL, 1) #define wake_up_all_locked(x) __wake_up_locked((x), TASK_NORMAL, 0) +#define wake_up_sync(x) __wake_up_sync(x, TASK_NORMAL) #define wake_up_interruptible(x) __wake_up(x, TASK_INTERRUPTIBLE, 1, NULL) #define wake_up_interruptible_nr(x, nr) __wake_up(x, TASK_INTERRUPTIBLE, nr, NULL) @@ -541,8 +542,8 @@ do { \ int __ret = 0; \ struct hrtimer_sleeper __t; \ \ - hrtimer_init_sleeper_on_stack(&__t, CLOCK_MONOTONIC, \ - HRTIMER_MODE_REL); \ + hrtimer_setup_sleeper_on_stack(&__t, CLOCK_MONOTONIC, \ + HRTIMER_MODE_REL); \ if ((timeout) != KTIME_MAX) { \ hrtimer_set_expires_range_ns(&__t.timer, timeout, \ current->timer_slack_ns); \ diff --git a/include/linux/wait_bit.h b/include/linux/wait_bit.h index 7725b7579b78..9e29d79fc790 100644 --- a/include/linux/wait_bit.h +++ b/include/linux/wait_bit.h @@ -8,7 +8,7 @@ #include <linux/wait.h> struct wait_bit_key { - void *flags; + unsigned long *flags; int bit_nr; unsigned long timeout; }; @@ -23,14 +23,14 @@ struct wait_bit_queue_entry { typedef int wait_bit_action_f(struct wait_bit_key *key, int mode); -void __wake_up_bit(struct wait_queue_head *wq_head, void *word, int bit); +void __wake_up_bit(struct wait_queue_head *wq_head, unsigned long *word, int bit); int __wait_on_bit(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry, wait_bit_action_f *action, unsigned int mode); int __wait_on_bit_lock(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry, wait_bit_action_f *action, unsigned int mode); -void wake_up_bit(void *word, int bit); -int out_of_line_wait_on_bit(void *word, int, wait_bit_action_f *action, unsigned int mode); -int out_of_line_wait_on_bit_timeout(void *word, int, wait_bit_action_f *action, unsigned int mode, unsigned long timeout); -int out_of_line_wait_on_bit_lock(void *word, int, wait_bit_action_f *action, unsigned int mode); -struct wait_queue_head *bit_waitqueue(void *word, int bit); +void wake_up_bit(unsigned long *word, int bit); +int out_of_line_wait_on_bit(unsigned long *word, int, wait_bit_action_f *action, unsigned int mode); +int out_of_line_wait_on_bit_timeout(unsigned long *word, int, wait_bit_action_f *action, unsigned int mode, unsigned long timeout); +int out_of_line_wait_on_bit_lock(unsigned long *word, int, wait_bit_action_f *action, unsigned int mode); +struct wait_queue_head *bit_waitqueue(unsigned long *word, int bit); extern void __init wait_bit_init(void); int wake_bit_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key); @@ -49,23 +49,24 @@ int wake_bit_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync extern int bit_wait(struct wait_bit_key *key, int mode); extern int bit_wait_io(struct wait_bit_key *key, int mode); extern int bit_wait_timeout(struct wait_bit_key *key, int mode); -extern int bit_wait_io_timeout(struct wait_bit_key *key, int mode); /** * wait_on_bit - wait for a bit to be cleared - * @word: the word being waited on, a kernel virtual address - * @bit: the bit of the word being waited on + * @word: the address containing the bit being waited on + * @bit: the bit at that address being waited on * @mode: the task state to sleep in * - * There is a standard hashed waitqueue table for generic use. This - * is the part of the hashtable's accessor API that waits on a bit. - * For instance, if one were to have waiters on a bitflag, one would - * call wait_on_bit() in threads waiting for the bit to clear. - * One uses wait_on_bit() where one is waiting for the bit to clear, - * but has no intention of setting it. - * Returned value will be zero if the bit was cleared, or non-zero - * if the process received a signal and the mode permitted wakeup - * on that signal. + * Wait for the given bit in an unsigned long or bitmap (see DECLARE_BITMAP()) + * to be cleared. The clearing of the bit must be signalled with + * wake_up_bit(), often as clear_and_wake_up_bit(). + * + * The process will wait on a waitqueue selected by hash from a shared + * pool. It will only be woken on a wake_up for the target bit, even + * if other processes on the same queue are waiting for other bits. + * + * Returned value will be zero if the bit was cleared in which case the + * call has ACQUIRE semantics, or %-EINTR if the process received a + * signal and the mode permitted wake up on that signal. */ static inline int wait_on_bit(unsigned long *word, int bit, unsigned mode) @@ -80,17 +81,20 @@ wait_on_bit(unsigned long *word, int bit, unsigned mode) /** * wait_on_bit_io - wait for a bit to be cleared - * @word: the word being waited on, a kernel virtual address - * @bit: the bit of the word being waited on + * @word: the address containing the bit being waited on + * @bit: the bit at that address being waited on * @mode: the task state to sleep in * - * Use the standard hashed waitqueue table to wait for a bit - * to be cleared. This is similar to wait_on_bit(), but calls - * io_schedule() instead of schedule() for the actual waiting. + * Wait for the given bit in an unsigned long or bitmap (see DECLARE_BITMAP()) + * to be cleared. The clearing of the bit must be signalled with + * wake_up_bit(), often as clear_and_wake_up_bit(). * - * Returned value will be zero if the bit was cleared, or non-zero - * if the process received a signal and the mode permitted wakeup - * on that signal. + * This is similar to wait_on_bit(), but calls io_schedule() instead of + * schedule() for the actual waiting. + * + * Returned value will be zero if the bit was cleared in which case the + * call has ACQUIRE semantics, or %-EINTR if the process received a + * signal and the mode permitted wake up on that signal. */ static inline int wait_on_bit_io(unsigned long *word, int bit, unsigned mode) @@ -104,19 +108,24 @@ wait_on_bit_io(unsigned long *word, int bit, unsigned mode) } /** - * wait_on_bit_timeout - wait for a bit to be cleared or a timeout elapses - * @word: the word being waited on, a kernel virtual address - * @bit: the bit of the word being waited on + * wait_on_bit_timeout - wait for a bit to be cleared or a timeout to elapse + * @word: the address containing the bit being waited on + * @bit: the bit at that address being waited on * @mode: the task state to sleep in * @timeout: timeout, in jiffies * - * Use the standard hashed waitqueue table to wait for a bit - * to be cleared. This is similar to wait_on_bit(), except also takes a - * timeout parameter. + * Wait for the given bit in an unsigned long or bitmap (see + * DECLARE_BITMAP()) to be cleared, or for a timeout to expire. The + * clearing of the bit must be signalled with wake_up_bit(), often as + * clear_and_wake_up_bit(). + * + * This is similar to wait_on_bit(), except it also takes a timeout + * parameter. * - * Returned value will be zero if the bit was cleared before the - * @timeout elapsed, or non-zero if the @timeout elapsed or process - * received a signal and the mode permitted wakeup on that signal. + * Returned value will be zero if the bit was cleared in which case the + * call has ACQUIRE semantics, or %-EINTR if the process received a + * signal and the mode permitted wake up on that signal, or %-EAGAIN if the + * timeout elapsed. */ static inline int wait_on_bit_timeout(unsigned long *word, int bit, unsigned mode, @@ -132,19 +141,21 @@ wait_on_bit_timeout(unsigned long *word, int bit, unsigned mode, /** * wait_on_bit_action - wait for a bit to be cleared - * @word: the word being waited on, a kernel virtual address - * @bit: the bit of the word being waited on + * @word: the address containing the bit waited on + * @bit: the bit at that address being waited on * @action: the function used to sleep, which may take special actions * @mode: the task state to sleep in * - * Use the standard hashed waitqueue table to wait for a bit - * to be cleared, and allow the waiting action to be specified. - * This is like wait_on_bit() but allows fine control of how the waiting - * is done. + * Wait for the given bit in an unsigned long or bitmap (see DECLARE_BITMAP()) + * to be cleared. The clearing of the bit must be signalled with + * wake_up_bit(), often as clear_and_wake_up_bit(). + * + * This is similar to wait_on_bit(), but calls @action() instead of + * schedule() for the actual waiting. * - * Returned value will be zero if the bit was cleared, or non-zero - * if the process received a signal and the mode permitted wakeup - * on that signal. + * Returned value will be zero if the bit was cleared in which case the + * call has ACQUIRE semantics, or the error code returned by @action if + * that call returned non-zero. */ static inline int wait_on_bit_action(unsigned long *word, int bit, wait_bit_action_f *action, @@ -157,23 +168,22 @@ wait_on_bit_action(unsigned long *word, int bit, wait_bit_action_f *action, } /** - * wait_on_bit_lock - wait for a bit to be cleared, when wanting to set it - * @word: the word being waited on, a kernel virtual address - * @bit: the bit of the word being waited on + * wait_on_bit_lock - wait for a bit to be cleared, then set it + * @word: the address containing the bit being waited on + * @bit: the bit of the word being waited on and set * @mode: the task state to sleep in * - * There is a standard hashed waitqueue table for generic use. This - * is the part of the hashtable's accessor API that waits on a bit - * when one intends to set it, for instance, trying to lock bitflags. - * For instance, if one were to have waiters trying to set bitflag - * and waiting for it to clear before setting it, one would call - * wait_on_bit() in threads waiting to be able to set the bit. - * One uses wait_on_bit_lock() where one is waiting for the bit to - * clear with the intention of setting it, and when done, clearing it. + * Wait for the given bit in an unsigned long or bitmap (see + * DECLARE_BITMAP()) to be cleared. The clearing of the bit must be + * signalled with wake_up_bit(), often as clear_and_wake_up_bit(). As + * soon as it is clear, atomically set it and return. * - * Returns zero if the bit was (eventually) found to be clear and was - * set. Returns non-zero if a signal was delivered to the process and - * the @mode allows that signal to wake the process. + * This is similar to wait_on_bit(), but sets the bit before returning. + * + * Returned value will be zero if the bit was successfully set in which + * case the call has the same memory sequencing semantics as + * test_and_clear_bit(), or %-EINTR if the process received a signal and + * the mode permitted wake up on that signal. */ static inline int wait_on_bit_lock(unsigned long *word, int bit, unsigned mode) @@ -185,15 +195,18 @@ wait_on_bit_lock(unsigned long *word, int bit, unsigned mode) } /** - * wait_on_bit_lock_io - wait for a bit to be cleared, when wanting to set it - * @word: the word being waited on, a kernel virtual address - * @bit: the bit of the word being waited on + * wait_on_bit_lock_io - wait for a bit to be cleared, then set it + * @word: the address containing the bit being waited on + * @bit: the bit of the word being waited on and set * @mode: the task state to sleep in * - * Use the standard hashed waitqueue table to wait for a bit - * to be cleared and then to atomically set it. This is similar - * to wait_on_bit(), but calls io_schedule() instead of schedule() - * for the actual waiting. + * Wait for the given bit in an unsigned long or bitmap (see + * DECLARE_BITMAP()) to be cleared. The clearing of the bit must be + * signalled with wake_up_bit(), often as clear_and_wake_up_bit(). As + * soon as it is clear, atomically set it and return. + * + * This is similar to wait_on_bit_lock(), but calls io_schedule() instead + * of schedule(). * * Returns zero if the bit was (eventually) found to be clear and was * set. Returns non-zero if a signal was delivered to the process and @@ -209,21 +222,19 @@ wait_on_bit_lock_io(unsigned long *word, int bit, unsigned mode) } /** - * wait_on_bit_lock_action - wait for a bit to be cleared, when wanting to set it - * @word: the word being waited on, a kernel virtual address - * @bit: the bit of the word being waited on + * wait_on_bit_lock_action - wait for a bit to be cleared, then set it + * @word: the address containing the bit being waited on + * @bit: the bit of the word being waited on and set * @action: the function used to sleep, which may take special actions * @mode: the task state to sleep in * - * Use the standard hashed waitqueue table to wait for a bit - * to be cleared and then to set it, and allow the waiting action - * to be specified. - * This is like wait_on_bit() but allows fine control of how the waiting - * is done. + * This is similar to wait_on_bit_lock(), but calls @action() instead of + * schedule() for the actual waiting. * - * Returns zero if the bit was (eventually) found to be clear and was - * set. Returns non-zero if a signal was delivered to the process and - * the @mode allows that signal to wake the process. + * Returned value will be zero if the bit was successfully set in which + * case the call has the same memory sequencing semantics as + * test_and_clear_bit(), or the error code returned by @action if that + * call returned non-zero. */ static inline int wait_on_bit_lock_action(unsigned long *word, int bit, wait_bit_action_f *action, @@ -269,7 +280,26 @@ __out: __ret; \ #define __wait_var_event(var, condition) \ ___wait_var_event(var, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ schedule()) +#define __wait_var_event_io(var, condition) \ + ___wait_var_event(var, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ + io_schedule()) +/** + * wait_var_event - wait for a variable to be updated and notified + * @var: the address of variable being waited on + * @condition: the condition to wait for + * + * Wait for a @condition to be true, only re-checking when a wake up is + * received for the given @var (an arbitrary kernel address which need + * not be directly related to the given condition, but usually is). + * + * The process will wait on a waitqueue selected by hash from a shared + * pool. It will only be woken on a wake_up for the given address. + * + * The condition should normally use smp_load_acquire() or a similarly + * ordered access to ensure that any changes to memory made before the + * condition became true will be visible after the wait completes. + */ #define wait_var_event(var, condition) \ do { \ might_sleep(); \ @@ -278,10 +308,56 @@ do { \ __wait_var_event(var, condition); \ } while (0) +/** + * wait_var_event_io - wait for a variable to be updated and notified + * @var: the address of variable being waited on + * @condition: the condition to wait for + * + * Wait for an IO related @condition to be true, only re-checking when a + * wake up is received for the given @var (an arbitrary kernel address + * which need not be directly related to the given condition, but + * usually is). + * + * The process will wait on a waitqueue selected by hash from a shared + * pool. It will only be woken on a wake_up for the given address. + * + * This is similar to wait_var_event(), but calls io_schedule() instead + * of schedule(). + * + * The condition should normally use smp_load_acquire() or a similarly + * ordered access to ensure that any changes to memory made before the + * condition became true will be visible after the wait completes. + */ +#define wait_var_event_io(var, condition) \ +do { \ + might_sleep(); \ + if (condition) \ + break; \ + __wait_var_event_io(var, condition); \ +} while (0) + #define __wait_var_event_killable(var, condition) \ ___wait_var_event(var, condition, TASK_KILLABLE, 0, 0, \ schedule()) +/** + * wait_var_event_killable - wait for a variable to be updated and notified + * @var: the address of variable being waited on + * @condition: the condition to wait for + * + * Wait for a @condition to be true or a fatal signal to be received, + * only re-checking the condition when a wake up is received for the given + * @var (an arbitrary kernel address which need not be directly related + * to the given condition, but usually is). + * + * This is similar to wait_var_event() but returns a value which is + * 0 if the condition became true, or %-ERESTARTSYS if a fatal signal + * was received. + * + * The condition should normally use smp_load_acquire() or a similarly + * ordered access to ensure that any changes to memory made before the + * condition became true will be visible after the wait completes. + */ #define wait_var_event_killable(var, condition) \ ({ \ int __ret = 0; \ @@ -296,6 +372,26 @@ do { \ TASK_UNINTERRUPTIBLE, 0, timeout, \ __ret = schedule_timeout(__ret)) +/** + * wait_var_event_timeout - wait for a variable to be updated or a timeout to expire + * @var: the address of variable being waited on + * @condition: the condition to wait for + * @timeout: maximum time to wait in jiffies + * + * Wait for a @condition to be true or a timeout to expire, only + * re-checking the condition when a wake up is received for the given + * @var (an arbitrary kernel address which need not be directly related + * to the given condition, but usually is). + * + * This is similar to wait_var_event() but returns a value which is 0 if + * the timeout expired and the condition was still false, or the + * remaining time left in the timeout (but at least 1) if the condition + * was found to be true. + * + * The condition should normally use smp_load_acquire() or a similarly + * ordered access to ensure that any changes to memory made before the + * condition became true will be visible after the wait completes. + */ #define wait_var_event_timeout(var, condition, timeout) \ ({ \ long __ret = timeout; \ @@ -309,6 +405,23 @@ do { \ ___wait_var_event(var, condition, TASK_INTERRUPTIBLE, 0, 0, \ schedule()) +/** + * wait_var_event_killable - wait for a variable to be updated and notified + * @var: the address of variable being waited on + * @condition: the condition to wait for + * + * Wait for a @condition to be true or a signal to be received, only + * re-checking the condition when a wake up is received for the given + * @var (an arbitrary kernel address which need not be directly related + * to the given condition, but usually is). + * + * This is similar to wait_var_event() but returns a value which is 0 if + * the condition became true, or %-ERESTARTSYS if a signal was received. + * + * The condition should normally use smp_load_acquire() or a similarly + * ordered access to ensure that any changes to memory made before the + * condition became true will be visible after the wait completes. + */ #define wait_var_event_interruptible(var, condition) \ ({ \ int __ret = 0; \ @@ -319,15 +432,122 @@ do { \ }) /** - * clear_and_wake_up_bit - clear a bit and wake up anyone waiting on that bit + * wait_var_event_any_lock - wait for a variable to be updated under a lock + * @var: the address of the variable being waited on + * @condition: condition to wait for + * @lock: the object that is locked to protect updates to the variable + * @type: prefix on lock and unlock operations + * @state: waiting state, %TASK_UNINTERRUPTIBLE etc. + * + * Wait for a condition which can only be reliably tested while holding + * a lock. The variables assessed in the condition will normal be updated + * under the same lock, and the wake up should be signalled with + * wake_up_var_locked() under the same lock. + * + * This is similar to wait_var_event(), but assumes a lock is held + * while calling this function and while updating the variable. * + * This must be called while the given lock is held and the lock will be + * dropped when schedule() is called to wait for a wake up, and will be + * reclaimed before testing the condition again. The functions used to + * unlock and lock the object are constructed by appending _unlock and _lock + * to @type. + * + * Return %-ERESTARTSYS if a signal arrives which is allowed to interrupt + * the wait according to @state. + */ +#define wait_var_event_any_lock(var, condition, lock, type, state) \ +({ \ + int __ret = 0; \ + if (!(condition)) \ + __ret = ___wait_var_event(var, condition, state, 0, 0, \ + type ## _unlock(lock); \ + schedule(); \ + type ## _lock(lock)); \ + __ret; \ +}) + +/** + * wait_var_event_spinlock - wait for a variable to be updated under a spinlock + * @var: the address of the variable being waited on + * @condition: condition to wait for + * @lock: the spinlock which protects updates to the variable + * + * Wait for a condition which can only be reliably tested while holding + * a spinlock. The variables assessed in the condition will normal be updated + * under the same spinlock, and the wake up should be signalled with + * wake_up_var_locked() under the same spinlock. + * + * This is similar to wait_var_event(), but assumes a spinlock is held + * while calling this function and while updating the variable. + * + * This must be called while the given lock is held and the lock will be + * dropped when schedule() is called to wait for a wake up, and will be + * reclaimed before testing the condition again. + */ +#define wait_var_event_spinlock(var, condition, lock) \ + wait_var_event_any_lock(var, condition, lock, spin, TASK_UNINTERRUPTIBLE) + +/** + * wait_var_event_mutex - wait for a variable to be updated under a mutex + * @var: the address of the variable being waited on + * @condition: condition to wait for + * @mutex: the mutex which protects updates to the variable + * + * Wait for a condition which can only be reliably tested while holding + * a mutex. The variables assessed in the condition will normal be + * updated under the same mutex, and the wake up should be signalled + * with wake_up_var_locked() under the same mutex. + * + * This is similar to wait_var_event(), but assumes a mutex is held + * while calling this function and while updating the variable. + * + * This must be called while the given mutex is held and the mutex will be + * dropped when schedule() is called to wait for a wake up, and will be + * reclaimed before testing the condition again. + */ +#define wait_var_event_mutex(var, condition, lock) \ + wait_var_event_any_lock(var, condition, lock, mutex, TASK_UNINTERRUPTIBLE) + +/** + * wake_up_var_protected - wake up waiters for a variable asserting that it is safe + * @var: the address of the variable being waited on + * @cond: the condition which afirms this is safe + * + * When waking waiters which use wait_var_event_any_lock() the waker must be + * holding the reelvant lock to avoid races. This version of wake_up_var() + * asserts that the relevant lock is held and so no barrier is needed. + * The @cond is only tested when CONFIG_LOCKDEP is enabled. + */ +#define wake_up_var_protected(var, cond) \ +do { \ + lockdep_assert(cond); \ + wake_up_var(var); \ +} while (0) + +/** + * wake_up_var_locked - wake up waiters for a variable while holding a spinlock or mutex + * @var: the address of the variable being waited on + * @lock: The spinlock or mutex what protects the variable + * + * Send a wake up for the given variable which should be waited for with + * wait_var_event_spinlock() or wait_var_event_mutex(). Unlike wake_up_var(), + * no extra barriers are needed as the locking provides sufficient sequencing. + */ +#define wake_up_var_locked(var, lock) \ + wake_up_var_protected(var, lockdep_is_held(lock)) + +/** + * clear_and_wake_up_bit - clear a bit and wake up anyone waiting on that bit * @bit: the bit of the word being waited on - * @word: the word being waited on, a kernel virtual address + * @word: the address containing the bit being waited on * - * You can use this helper if bitflags are manipulated atomically rather than - * non-atomically under a lock. + * The designated bit is cleared and any tasks waiting in wait_on_bit() + * or similar will be woken. This call has RELEASE semantics so that + * any changes to memory made before this call are guaranteed to be visible + * after the corresponding wait_on_bit() completes. */ -static inline void clear_and_wake_up_bit(int bit, void *word) +static inline void clear_and_wake_up_bit(int bit, unsigned long *word) { clear_bit_unlock(bit, word); /* See wake_up_bit() for which memory barrier you need to use. */ @@ -335,4 +555,64 @@ static inline void clear_and_wake_up_bit(int bit, void *word) wake_up_bit(word, bit); } +/** + * test_and_clear_wake_up_bit - clear a bit if it was set: wake up anyone waiting on that bit + * @bit: the bit of the word being waited on + * @word: the address of memory containing that bit + * + * If the bit is set and can be atomically cleared, any tasks waiting in + * wait_on_bit() or similar will be woken. This call has the same + * complete ordering semantics as test_and_clear_bit(). Any changes to + * memory made before this call are guaranteed to be visible after the + * corresponding wait_on_bit() completes. + * + * Returns %true if the bit was successfully set and the wake up was sent. + */ +static inline bool test_and_clear_wake_up_bit(int bit, unsigned long *word) +{ + if (!test_and_clear_bit(bit, word)) + return false; + /* no extra barrier required */ + wake_up_bit(word, bit); + return true; +} + +/** + * atomic_dec_and_wake_up - decrement an atomic_t and if zero, wake up waiters + * @var: the variable to dec and test + * + * Decrements the atomic variable and if it reaches zero, send a wake_up to any + * processes waiting on the variable. + * + * This function has the same complete ordering semantics as atomic_dec_and_test. + * + * Returns %true is the variable reaches zero and the wake up was sent. + */ + +static inline bool atomic_dec_and_wake_up(atomic_t *var) +{ + if (!atomic_dec_and_test(var)) + return false; + /* No extra barrier required */ + wake_up_var(var); + return true; +} + +/** + * store_release_wake_up - update a variable and send a wake_up + * @var: the address of the variable to be updated and woken + * @val: the value to store in the variable. + * + * Store the given value in the variable send a wake up to any tasks + * waiting on the variable. All necessary barriers are included to ensure + * the task calling wait_var_event() sees the new value and all values + * written to memory before this call. + */ +#define store_release_wake_up(var, val) \ +do { \ + smp_store_release(var, val); \ + smp_mb(); \ + wake_up_var(var); \ +} while (0) + #endif /* _LINUX_WAIT_BIT_H */ diff --git a/include/linux/wireless.h b/include/linux/wireless.h index e6e34d74dda0..03e5d3fe226d 100644 --- a/include/linux/wireless.h +++ b/include/linux/wireless.h @@ -21,8 +21,7 @@ struct compat_iw_point { __u16 length; __u16 flags; }; -#endif -#ifdef CONFIG_COMPAT + struct __compat_iw_event { __u16 len; /* Real length of this stuff */ __u16 cmd; /* Wireless IOCTL */ @@ -49,5 +48,5 @@ struct __compat_iw_event { #define IW_EV_COMPAT_POINT_LEN \ (IW_EV_COMPAT_LCP_LEN + sizeof(struct compat_iw_point) - \ IW_EV_COMPAT_POINT_OFF) -#endif +#endif /* CONFIG_COMPAT */ #endif /* _LINUX_WIRELESS_H */ diff --git a/include/linux/wmi.h b/include/linux/wmi.h index 63cca3b58d6d..10751c8e5e6a 100644 --- a/include/linux/wmi.h +++ b/include/linux/wmi.h @@ -16,12 +16,16 @@ * struct wmi_device - WMI device structure * @dev: Device associated with this WMI device * @setable: True for devices implementing the Set Control Method + * @driver_override: Driver name to force a match; do not set directly, + * because core frees it; use driver_set_override() to + * set or clear it. * * This represents WMI devices discovered by the WMI driver core. */ struct wmi_device { struct device dev; bool setable; + const char *driver_override; }; /** @@ -30,7 +34,7 @@ struct wmi_device { * * Cast a struct device to a struct wmi_device. */ -#define to_wmi_device(device) container_of(device, struct wmi_device, dev) +#define to_wmi_device(device) container_of_const(device, struct wmi_device, dev) extern acpi_status wmidev_evaluate_method(struct wmi_device *wdev, u8 instance, u32 method_id, @@ -52,6 +56,7 @@ u8 wmidev_instance_count(struct wmi_device *wdev); * @no_singleton: Driver can be instantiated multiple times * @probe: Callback for device binding * @remove: Callback for device unbinding + * @shutdown: Callback for device shutdown * @notify: Callback for receiving WMI events * * This represents WMI drivers which handle WMI devices. @@ -64,9 +69,18 @@ struct wmi_driver { int (*probe)(struct wmi_device *wdev, const void *context); void (*remove)(struct wmi_device *wdev); + void (*shutdown)(struct wmi_device *wdev); void (*notify)(struct wmi_device *device, union acpi_object *data); }; +/** + * to_wmi_driver() - Helper macro to cast a driver to a wmi_driver + * @drv: driver struct + * + * Cast a struct device_driver to a struct wmi_driver. + */ +#define to_wmi_driver(drv) container_of_const(drv, struct wmi_driver, driver) + extern int __must_check __wmi_driver_register(struct wmi_driver *driver, struct module *owner); extern void wmi_driver_unregister(struct wmi_driver *driver); diff --git a/include/linux/wordpart.h b/include/linux/wordpart.h index f6f8f83b15b0..5a7b97bb7c95 100644 --- a/include/linux/wordpart.h +++ b/include/linux/wordpart.h @@ -39,4 +39,19 @@ */ #define REPEAT_BYTE(x) ((~0ul / 0xff) * (x)) +/** + * REPEAT_BYTE_U32 - repeat the value @x multiple times as a u32 value + * @x: value to repeat + * + * NOTE: @x is not checked for > 0xff; larger values produce odd results. + */ +#define REPEAT_BYTE_U32(x) lower_32_bits(REPEAT_BYTE(x)) + +/* Set bits in the first 'n' bytes when loaded from memory */ +#ifdef __LITTLE_ENDIAN +# define aligned_byte_mask(n) ((1UL << 8*(n))-1) +#else +# define aligned_byte_mask(n) (~0xffUL << (BITS_PER_LONG - 8 - 8*(n))) +#endif + #endif // _LINUX_WORDPART_H diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 158784dd189a..b0dc957c3e56 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -12,7 +12,7 @@ #include <linux/lockdep.h> #include <linux/threads.h> #include <linux/atomic.h> -#include <linux/cpumask.h> +#include <linux/cpumask_types.h> #include <linux/rcupdate.h> #include <linux/workqueue_types.h> @@ -51,20 +51,23 @@ enum work_bits { * data contains off-queue information when !WORK_STRUCT_PWQ. * * MSB - * [ pool ID ] [ OFFQ flags ] [ STRUCT flags ] - * 1 bit 4 or 5 bits + * [ pool ID ] [ disable depth ] [ OFFQ flags ] [ STRUCT flags ] + * 16 bits 1 bit 4 or 5 bits */ WORK_OFFQ_FLAG_SHIFT = WORK_STRUCT_FLAG_BITS, - WORK_OFFQ_CANCELING_BIT = WORK_OFFQ_FLAG_SHIFT, + WORK_OFFQ_BH_BIT = WORK_OFFQ_FLAG_SHIFT, WORK_OFFQ_FLAG_END, WORK_OFFQ_FLAG_BITS = WORK_OFFQ_FLAG_END - WORK_OFFQ_FLAG_SHIFT, + WORK_OFFQ_DISABLE_SHIFT = WORK_OFFQ_FLAG_SHIFT + WORK_OFFQ_FLAG_BITS, + WORK_OFFQ_DISABLE_BITS = 16, + /* * When a work item is off queue, the high bits encode off-queue flags * and the last pool it was on. Cap pool ID to 31 bits and use the * highest number to indicate that no pool is associated. */ - WORK_OFFQ_POOL_SHIFT = WORK_OFFQ_FLAG_SHIFT + WORK_OFFQ_FLAG_BITS, + WORK_OFFQ_POOL_SHIFT = WORK_OFFQ_DISABLE_SHIFT + WORK_OFFQ_DISABLE_BITS, WORK_OFFQ_LEFT = BITS_PER_LONG - WORK_OFFQ_POOL_SHIFT, WORK_OFFQ_POOL_BITS = WORK_OFFQ_LEFT <= 31 ? WORK_OFFQ_LEFT : 31, }; @@ -92,11 +95,13 @@ enum wq_misc_consts { WORK_BUSY_RUNNING = 1 << 1, /* maximum string length for set_worker_desc() */ - WORKER_DESC_LEN = 24, + WORKER_DESC_LEN = 32, }; /* Convenience constants - of type 'unsigned long', not 'enum'! */ -#define WORK_OFFQ_CANCELING (1ul << WORK_OFFQ_CANCELING_BIT) +#define WORK_OFFQ_BH (1ul << WORK_OFFQ_BH_BIT) +#define WORK_OFFQ_FLAG_MASK (((1ul << WORK_OFFQ_FLAG_BITS) - 1) << WORK_OFFQ_FLAG_SHIFT) +#define WORK_OFFQ_DISABLE_MASK (((1ul << WORK_OFFQ_DISABLE_BITS) - 1) << WORK_OFFQ_DISABLE_SHIFT) #define WORK_OFFQ_POOL_NONE ((1ul << WORK_OFFQ_POOL_BITS) - 1) #define WORK_STRUCT_NO_POOL (WORK_OFFQ_POOL_NONE << WORK_OFFQ_POOL_SHIFT) #define WORK_STRUCT_PWQ_MASK (~((1ul << WORK_STRUCT_PWQ_SHIFT) - 1)) @@ -180,6 +185,9 @@ struct workqueue_attrs { * Below fields aren't properties of a worker_pool. They only modify how * :c:func:`apply_workqueue_attrs` select pools and thus don't * participate in pool hash calculations or equality comparisons. + * + * If @affn_strict is set, @cpumask isn't a property of a worker_pool + * either. */ /** @@ -404,7 +412,7 @@ enum wq_flags { }; enum wq_consts { - WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */ + WQ_MAX_ACTIVE = 2048, /* I like 2048, better ideas? */ WQ_UNBOUND_MAX_ACTIVE = WQ_MAX_ACTIVE, WQ_DFL_ACTIVE = WQ_MAX_ACTIVE / 2, @@ -465,7 +473,7 @@ void workqueue_softirq_dead(unsigned int cpu); * @fmt: printf format for the name of the workqueue * @flags: WQ_* flags * @max_active: max in-flight work items, 0 for default - * remaining args: args for @fmt + * @...: args for @fmt * * For a per-cpu workqueue, @max_active limits the number of in-flight work * items for each CPU. e.g. @max_active of 1 indicates that each CPU can be @@ -499,6 +507,47 @@ void workqueue_softirq_dead(unsigned int cpu); __printf(1, 4) struct workqueue_struct * alloc_workqueue(const char *fmt, unsigned int flags, int max_active, ...); +#ifdef CONFIG_LOCKDEP +/** + * alloc_workqueue_lockdep_map - allocate a workqueue with user-defined lockdep_map + * @fmt: printf format for the name of the workqueue + * @flags: WQ_* flags + * @max_active: max in-flight work items, 0 for default + * @lockdep_map: user-defined lockdep_map + * @...: args for @fmt + * + * Same as alloc_workqueue but with the a user-define lockdep_map. Useful for + * workqueues created with the same purpose and to avoid leaking a lockdep_map + * on each workqueue creation. + * + * RETURNS: + * Pointer to the allocated workqueue on success, %NULL on failure. + */ +__printf(1, 5) struct workqueue_struct * +alloc_workqueue_lockdep_map(const char *fmt, unsigned int flags, int max_active, + struct lockdep_map *lockdep_map, ...); + +/** + * alloc_ordered_workqueue_lockdep_map - allocate an ordered workqueue with + * user-defined lockdep_map + * + * @fmt: printf format for the name of the workqueue + * @flags: WQ_* flags (only WQ_FREEZABLE and WQ_MEM_RECLAIM are meaningful) + * @lockdep_map: user-defined lockdep_map + * @args: args for @fmt + * + * Same as alloc_ordered_workqueue but with the a user-define lockdep_map. + * Useful for workqueues created with the same purpose and to avoid leaking a + * lockdep_map on each workqueue creation. + * + * RETURNS: + * Pointer to the allocated workqueue on success, %NULL on failure. + */ +#define alloc_ordered_workqueue_lockdep_map(fmt, flags, lockdep_map, args...) \ + alloc_workqueue_lockdep_map(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags), \ + 1, lockdep_map, ##args) +#endif + /** * alloc_ordered_workqueue - allocate an ordered workqueue * @fmt: printf format for the name of the workqueue @@ -559,6 +608,14 @@ extern bool flush_delayed_work(struct delayed_work *dwork); extern bool cancel_delayed_work(struct delayed_work *dwork); extern bool cancel_delayed_work_sync(struct delayed_work *dwork); +extern bool disable_work(struct work_struct *work); +extern bool disable_work_sync(struct work_struct *work); +extern bool enable_work(struct work_struct *work); + +extern bool disable_delayed_work(struct delayed_work *dwork); +extern bool disable_delayed_work_sync(struct delayed_work *dwork); +extern bool enable_delayed_work(struct delayed_work *dwork); + extern bool flush_rcu_work(struct rcu_work *rwork); extern void workqueue_set_max_active(struct workqueue_struct *wq, @@ -666,6 +723,32 @@ static inline bool schedule_work(struct work_struct *work) return queue_work(system_wq, work); } +/** + * enable_and_queue_work - Enable and queue a work item on a specific workqueue + * @wq: The target workqueue + * @work: The work item to be enabled and queued + * + * This function combines the operations of enable_work() and queue_work(), + * providing a convenient way to enable and queue a work item in a single call. + * It invokes enable_work() on @work and then queues it if the disable depth + * reached 0. Returns %true if the disable depth reached 0 and @work is queued, + * and %false otherwise. + * + * Note that @work is always queued when disable depth reaches zero. If the + * desired behavior is queueing only if certain events took place while @work is + * disabled, the user should implement the necessary state tracking and perform + * explicit conditional queueing after enable_work(). + */ +static inline bool enable_and_queue_work(struct workqueue_struct *wq, + struct work_struct *work) +{ + if (enable_work(work)) { + queue_work(wq, work); + return true; + } + return false; +} + /* * Detect attempt to flush system-wide workqueues at compile time when possible. * Warn attempt to flush system-wide workqueues at runtime. diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 9845cb62e40b..d11b903c2edb 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -79,6 +79,9 @@ struct writeback_control { */ struct swap_iocb **swap_plug; + /* Target list for splitting a large folio */ + struct list_head *list; + /* internal fields used by the ->writepages implementation: */ struct folio_batch fbatch; pgoff_t index; @@ -200,7 +203,8 @@ void inode_io_list_del(struct inode *inode); /* writeback.h requires fs.h; it, too, is not included from here. */ static inline void wait_on_inode(struct inode *inode) { - wait_on_bit(&inode->i_state, __I_NEW, TASK_UNINTERRUPTIBLE); + wait_var_event(inode_state_wait_address(inode, __I_NEW), + !(READ_ONCE(inode->i_state) & I_NEW)); } #ifdef CONFIG_CGROUP_WRITEBACK @@ -209,15 +213,12 @@ static inline void wait_on_inode(struct inode *inode) #include <linux/bio.h> 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); void wbc_detach_inode(struct writeback_control *wbc); -void wbc_account_cgroup_owner(struct writeback_control *wbc, struct page *page, +void wbc_account_cgroup_owner(struct writeback_control *wbc, struct folio *folio, size_t bytes); int cgroup_writeback_by_id(u64 bdi_id, int memcg_id, enum wb_reason reason, struct wb_completion *done); -void cgroup_writeback_umount(void); +void cgroup_writeback_umount(struct super_block *sb); bool cleanup_offline_cgwb(struct bdi_writeback *wb); /** @@ -250,22 +251,8 @@ static inline void inode_detach_wb(struct inode *inode) } } -/** - * wbc_attach_fdatawrite_inode - associate wbc and inode for fdatawrite - * @wbc: writeback_control of interest - * @inode: target inode - * - * This function is to be used by __filemap_fdatawrite_range(), which is an - * alternative entry point into writeback code, and first ensures @inode is - * associated with a bdi_writeback and attaches it to @wbc. - */ -static inline void wbc_attach_fdatawrite_inode(struct writeback_control *wbc, - struct inode *inode) -{ - spin_lock(&inode->i_lock); - inode_attach_wb(inode, NULL); - wbc_attach_and_unlock_inode(wbc, inode); -} +void wbc_attach_fdatawrite_inode(struct writeback_control *wbc, + struct inode *inode); /** * wbc_init_bio - writeback specific initializtion of bio @@ -299,13 +286,6 @@ static inline void inode_detach_wb(struct inode *inode) { } -static inline void wbc_attach_and_unlock_inode(struct writeback_control *wbc, - struct inode *inode) - __releases(&inode->i_lock) -{ - spin_unlock(&inode->i_lock); -} - static inline void wbc_attach_fdatawrite_inode(struct writeback_control *wbc, struct inode *inode) { @@ -320,11 +300,11 @@ static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio) } static inline void wbc_account_cgroup_owner(struct writeback_control *wbc, - struct page *page, size_t bytes) + struct folio *folio, size_t bytes) { } -static inline void cgroup_writeback_umount(void) +static inline void cgroup_writeback_umount(struct super_block *sb) { } @@ -350,11 +330,12 @@ extern unsigned int dirty_expire_interval; extern unsigned int dirtytime_expire_interval; extern int laptop_mode; -int dirtytime_interval_handler(struct ctl_table *table, int write, +int dirtytime_interval_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty); unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh); +unsigned long cgwb_calc_thresh(struct bdi_writeback *wb); void wb_update_bandwidth(struct bdi_writeback *wb); diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h index bb763085479a..45ff6f7a872b 100644 --- a/include/linux/ww_mutex.h +++ b/include/linux/ww_mutex.h @@ -65,6 +65,16 @@ struct ww_acquire_ctx { #endif #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; + /** + * @first_lock_dep_map: fake lockdep_map for first locked ww_mutex. + * + * lockdep requires the lockdep_map for the first locked ww_mutex + * in a ww transaction to remain in memory until all ww_mutexes of + * the transaction have been unlocked. Ensure this by keeping a + * fake locked ww_mutex lockdep map between ww_acquire_init() and + * ww_acquire_fini(). + */ + struct lockdep_map first_lock_dep_map; #endif #ifdef CONFIG_DEBUG_WW_MUTEX_SLOWPATH unsigned int deadlock_inject_interval; @@ -146,7 +156,10 @@ static inline void ww_acquire_init(struct ww_acquire_ctx *ctx, debug_check_no_locks_freed((void *)ctx, sizeof(*ctx)); lockdep_init_map(&ctx->dep_map, ww_class->acquire_name, &ww_class->acquire_key, 0); + lockdep_init_map_wait(&ctx->first_lock_dep_map, ww_class->mutex_name, + &ww_class->mutex_key, 0, LD_WAIT_SLEEP); mutex_acquire(&ctx->dep_map, 0, 0, _RET_IP_); + mutex_acquire_nest(&ctx->first_lock_dep_map, 0, 0, &ctx->dep_map, _RET_IP_); #endif #ifdef CONFIG_DEBUG_WW_MUTEX_SLOWPATH ctx->deadlock_inject_interval = 1; @@ -185,6 +198,7 @@ static inline void ww_acquire_done(struct ww_acquire_ctx *ctx) static inline void ww_acquire_fini(struct ww_acquire_ctx *ctx) { #ifdef CONFIG_DEBUG_LOCK_ALLOC + mutex_release(&ctx->first_lock_dep_map, _THIS_IP_); mutex_release(&ctx->dep_map, _THIS_IP_); #endif #ifdef DEBUG_WW_MUTEXES diff --git a/include/linux/wwan.h b/include/linux/wwan.h index 170fdee6339c..a4d6cc0c9f68 100644 --- a/include/linux/wwan.h +++ b/include/linux/wwan.h @@ -17,6 +17,8 @@ * @WWAN_PORT_FIREHOSE: XML based command protocol * @WWAN_PORT_XMMRPC: Control protocol for Intel XMM modems * @WWAN_PORT_FASTBOOT: Fastboot protocol control + * @WWAN_PORT_ADB: ADB protocol control + * @WWAN_PORT_MIPC: MTK MIPC diagnostic interface * * @WWAN_PORT_MAX: Highest supported port types * @WWAN_PORT_UNKNOWN: Special value to indicate an unknown port type @@ -30,6 +32,8 @@ enum wwan_port_type { WWAN_PORT_FIREHOSE, WWAN_PORT_XMMRPC, WWAN_PORT_FASTBOOT, + WWAN_PORT_ADB, + WWAN_PORT_MIPC, /* Add new port types above this line */ @@ -93,7 +97,7 @@ struct wwan_port_caps { * * This function must be balanced with a call to wwan_remove_port(). * - * Returns a valid pointer to wwan_port on success or PTR_ERR on failure + * Returns: a valid pointer to wwan_port on success or PTR_ERR on failure */ struct wwan_port *wwan_create_port(struct device *parent, enum wwan_port_type type, diff --git a/include/linux/xarray.h b/include/linux/xarray.h index cb571dfcf4b1..0b618ec04115 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -12,14 +12,18 @@ #include <linux/bitmap.h> #include <linux/bug.h> #include <linux/compiler.h> +#include <linux/err.h> #include <linux/gfp.h> #include <linux/kconfig.h> -#include <linux/kernel.h> +#include <linux/limits.h> +#include <linux/lockdep.h> #include <linux/rcupdate.h> #include <linux/sched/mm.h> #include <linux/spinlock.h> #include <linux/types.h> +struct list_lru; + /* * The bottom two bits of the entry determine how the XArray interprets * the contents: @@ -1141,12 +1145,12 @@ static inline void xa_release(struct xarray *xa, unsigned long index) * doubled the number of slots per node, we'd get only 3 nodes per 4kB page. */ #ifndef XA_CHUNK_SHIFT -#define XA_CHUNK_SHIFT (CONFIG_BASE_SMALL ? 4 : 6) +#define XA_CHUNK_SHIFT (IS_ENABLED(CONFIG_BASE_SMALL) ? 4 : 6) #endif #define XA_CHUNK_SIZE (1UL << XA_CHUNK_SHIFT) #define XA_CHUNK_MASK (XA_CHUNK_SIZE - 1) #define XA_MAX_MARKS 3 -#define XA_MARK_LONGS DIV_ROUND_UP(XA_CHUNK_SIZE, BITS_PER_LONG) +#define XA_MARK_LONGS BITS_TO_LONGS(XA_CHUNK_SIZE) /* * @count is the count of every non-NULL element in the ->slots array @@ -1548,6 +1552,7 @@ void xas_create_range(struct xa_state *); #ifdef CONFIG_XARRAY_MULTI int xa_get_order(struct xarray *, unsigned long index); +int xas_get_order(struct xa_state *xas); void xas_split(struct xa_state *, void *entry, unsigned int order); void xas_split_alloc(struct xa_state *, void *entry, unsigned int order, gfp_t); #else @@ -1556,6 +1561,11 @@ static inline int xa_get_order(struct xarray *xa, unsigned long index) return 0; } +static inline int xas_get_order(struct xa_state *xas) +{ + return 0; +} + static inline void xas_split(struct xa_state *xas, void *entry, unsigned int order) { diff --git a/include/linux/xattr.h b/include/linux/xattr.h index d20051865800..86b0d47984a1 100644 --- a/include/linux/xattr.h +++ b/include/linux/xattr.h @@ -19,6 +19,10 @@ #include <linux/user_namespace.h> #include <uapi/linux/xattr.h> +/* List of all open_how "versions". */ +#define XATTR_ARGS_SIZE_VER0 16 /* sizeof first published struct */ +#define XATTR_ARGS_SIZE_LATEST XATTR_ARGS_SIZE_VER0 + struct inode; struct dentry; diff --git a/include/linux/xz.h b/include/linux/xz.h index 7285ca5d56e9..58ae1d746c6f 100644 --- a/include/linux/xz.h +++ b/include/linux/xz.h @@ -1,11 +1,10 @@ +/* SPDX-License-Identifier: 0BSD */ + /* * XZ decompressor * * Authors: Lasse Collin <lasse.collin@tukaani.org> * Igor Pavlov <https://7-zip.org/> - * - * This file has been put into the public domain. - * You can do whatever you want with this file. */ #ifndef XZ_H @@ -19,11 +18,6 @@ # include <stdint.h> #endif -/* In Linux, this is used to make extern functions static when needed. */ -#ifndef XZ_EXTERN -# define XZ_EXTERN extern -#endif - /** * enum xz_mode - Operation mode * @@ -143,7 +137,7 @@ struct xz_buf { size_t out_size; }; -/** +/* * struct xz_dec - Opaque type to hold the XZ decoder state */ struct xz_dec; @@ -191,7 +185,7 @@ struct xz_dec; * ready to be used with xz_dec_run(). If memory allocation fails, * xz_dec_init() returns NULL. */ -XZ_EXTERN struct xz_dec *xz_dec_init(enum xz_mode mode, uint32_t dict_max); +struct xz_dec *xz_dec_init(enum xz_mode mode, uint32_t dict_max); /** * xz_dec_run() - Run the XZ decoder @@ -211,7 +205,7 @@ XZ_EXTERN struct xz_dec *xz_dec_init(enum xz_mode mode, uint32_t dict_max); * get that amount valid data from the beginning of the stream. You must use * the multi-call decoder if you don't want to uncompress the whole stream. */ -XZ_EXTERN enum xz_ret xz_dec_run(struct xz_dec *s, struct xz_buf *b); +enum xz_ret xz_dec_run(struct xz_dec *s, struct xz_buf *b); /** * xz_dec_reset() - Reset an already allocated decoder state @@ -224,32 +218,38 @@ XZ_EXTERN enum xz_ret xz_dec_run(struct xz_dec *s, struct xz_buf *b); * xz_dec_run(). Thus, explicit call to xz_dec_reset() is useful only in * multi-call mode. */ -XZ_EXTERN void xz_dec_reset(struct xz_dec *s); +void xz_dec_reset(struct xz_dec *s); /** * xz_dec_end() - Free the memory allocated for the decoder state * @s: Decoder state allocated using xz_dec_init(). If s is NULL, * this function does nothing. */ -XZ_EXTERN void xz_dec_end(struct xz_dec *s); +void xz_dec_end(struct xz_dec *s); -/* - * Decompressor for MicroLZMA, an LZMA variant with a very minimal header. - * See xz_dec_microlzma_alloc() below for details. +/** + * DOC: MicroLZMA decompressor + * + * This MicroLZMA header format was created for use in EROFS but may be used + * by others too. **In most cases one needs the XZ APIs above instead.** * - * These functions aren't used or available in preboot code and thus aren't - * marked with XZ_EXTERN. This avoids warnings about static functions that - * are never defined. + * The compressed format supported by this decoder is a raw LZMA stream + * whose first byte (always 0x00) has been replaced with bitwise-negation + * of the LZMA properties (lc/lp/pb) byte. For example, if lc/lp/pb is + * 3/0/2, the first byte is 0xA2. This way the first byte can never be 0x00. + * Just like with LZMA2, lc + lp <= 4 must be true. The LZMA end-of-stream + * marker must not be used. The unused values are reserved for future use. */ -/** + +/* * struct xz_dec_microlzma - Opaque type to hold the MicroLZMA decoder state */ struct xz_dec_microlzma; /** * xz_dec_microlzma_alloc() - Allocate memory for the MicroLZMA decoder - * @mode XZ_SINGLE or XZ_PREALLOC - * @dict_size LZMA dictionary size. This must be at least 4 KiB and + * @mode: XZ_SINGLE or XZ_PREALLOC + * @dict_size: LZMA dictionary size. This must be at least 4 KiB and * at most 3 GiB. * * In contrast to xz_dec_init(), this function only allocates the memory @@ -262,40 +262,30 @@ struct xz_dec_microlzma; * On success, xz_dec_microlzma_alloc() returns a pointer to * struct xz_dec_microlzma. If memory allocation fails or * dict_size is invalid, NULL is returned. - * - * The compressed format supported by this decoder is a raw LZMA stream - * whose first byte (always 0x00) has been replaced with bitwise-negation - * of the LZMA properties (lc/lp/pb) byte. For example, if lc/lp/pb is - * 3/0/2, the first byte is 0xA2. This way the first byte can never be 0x00. - * Just like with LZMA2, lc + lp <= 4 must be true. The LZMA end-of-stream - * marker must not be used. The unused values are reserved for future use. - * This MicroLZMA header format was created for use in EROFS but may be used - * by others too. */ -extern struct xz_dec_microlzma *xz_dec_microlzma_alloc(enum xz_mode mode, - uint32_t dict_size); +struct xz_dec_microlzma *xz_dec_microlzma_alloc(enum xz_mode mode, + uint32_t dict_size); /** * xz_dec_microlzma_reset() - Reset the MicroLZMA decoder state - * @s Decoder state allocated using xz_dec_microlzma_alloc() - * @comp_size Compressed size of the input stream - * @uncomp_size Uncompressed size of the input stream. A value smaller + * @s: Decoder state allocated using xz_dec_microlzma_alloc() + * @comp_size: Compressed size of the input stream + * @uncomp_size: Uncompressed size of the input stream. A value smaller * than the real uncompressed size of the input stream can * be specified if uncomp_size_is_exact is set to false. * uncomp_size can never be set to a value larger than the * expected real uncompressed size because it would eventually * result in XZ_DATA_ERROR. - * @uncomp_size_is_exact This is an int instead of bool to avoid + * @uncomp_size_is_exact: This is an int instead of bool to avoid * requiring stdbool.h. This should normally be set to true. * When this is set to false, error detection is weaker. */ -extern void xz_dec_microlzma_reset(struct xz_dec_microlzma *s, - uint32_t comp_size, uint32_t uncomp_size, - int uncomp_size_is_exact); +void xz_dec_microlzma_reset(struct xz_dec_microlzma *s, uint32_t comp_size, + uint32_t uncomp_size, int uncomp_size_is_exact); /** * xz_dec_microlzma_run() - Run the MicroLZMA decoder - * @s Decoder state initialized using xz_dec_microlzma_reset() + * @s: Decoder state initialized using xz_dec_microlzma_reset() * @b: Input and output buffers * * This works similarly to xz_dec_run() with a few important differences. @@ -329,15 +319,14 @@ extern void xz_dec_microlzma_reset(struct xz_dec_microlzma *s, * may be changed normally like with XZ_PREALLOC. This way input data can be * provided from non-contiguous memory. */ -extern enum xz_ret xz_dec_microlzma_run(struct xz_dec_microlzma *s, - struct xz_buf *b); +enum xz_ret xz_dec_microlzma_run(struct xz_dec_microlzma *s, struct xz_buf *b); /** * xz_dec_microlzma_end() - Free the memory allocated for the decoder state * @s: Decoder state allocated using xz_dec_microlzma_alloc(). * If s is NULL, this function does nothing. */ -extern void xz_dec_microlzma_end(struct xz_dec_microlzma *s); +void xz_dec_microlzma_end(struct xz_dec_microlzma *s); /* * Standalone build (userspace build or in-kernel build for boot time use) @@ -358,13 +347,13 @@ extern void xz_dec_microlzma_end(struct xz_dec_microlzma *s); * This must be called before any other xz_* function to initialize * the CRC32 lookup table. */ -XZ_EXTERN void xz_crc32_init(void); +void xz_crc32_init(void); /* * Update CRC32 value using the polynomial from IEEE-802.3. To start a new * calculation, the third argument must be zero. To continue the calculation, * the previously returned value is passed as the third argument. */ -XZ_EXTERN uint32_t xz_crc32(const uint8_t *buf, size_t size, uint32_t crc); +uint32_t xz_crc32(const uint8_t *buf, size_t size, uint32_t crc); #endif #endif diff --git a/include/linux/zorro.h b/include/linux/zorro.h index db7416ed6057..f36c8d39553d 100644 --- a/include/linux/zorro.h +++ b/include/linux/zorro.h @@ -52,7 +52,7 @@ struct zorro_driver { struct device_driver driver; }; -#define to_zorro_driver(drv) container_of(drv, struct zorro_driver, driver) +#define to_zorro_driver(drv) container_of_const(drv, struct zorro_driver, driver) #define zorro_for_each_dev(dev) \ diff --git a/include/linux/zpool.h b/include/linux/zpool.h index 3296438eec06..a67d62b79698 100644 --- a/include/linux/zpool.h +++ b/include/linux/zpool.h @@ -53,7 +53,7 @@ void *zpool_map_handle(struct zpool *pool, unsigned long handle, void zpool_unmap_handle(struct zpool *pool, unsigned long handle); -u64 zpool_get_total_size(struct zpool *pool); +u64 zpool_get_total_pages(struct zpool *pool); /** @@ -91,7 +91,7 @@ struct zpool_driver { enum zpool_mapmode mm); void (*unmap)(void *pool, unsigned long handle); - u64 (*total_size)(void *pool); + u64 (*total_pages)(void *pool); }; void zpool_register_driver(struct zpool_driver *driver); diff --git a/include/linux/zstd.h b/include/linux/zstd.h index 113408eef6ec..b2c7cf310c8f 100644 --- a/include/linux/zstd.h +++ b/include/linux/zstd.h @@ -77,6 +77,30 @@ int zstd_min_clevel(void); */ int zstd_max_clevel(void); +/** + * zstd_default_clevel() - default compression level + * + * Return: Default compression level. + */ +int zstd_default_clevel(void); + +/** + * struct zstd_custom_mem - custom memory allocation + */ +typedef ZSTD_customMem zstd_custom_mem; + +/** + * struct zstd_dict_load_method - Dictionary load method. + * See zstd_lib.h. + */ +typedef ZSTD_dictLoadMethod_e zstd_dict_load_method; + +/** + * struct zstd_dict_content_type - Dictionary context type. + * See zstd_lib.h. + */ +typedef ZSTD_dictContentType_e zstd_dict_content_type; + /* ====== Parameter Selection ====== */ /** @@ -136,6 +160,19 @@ typedef ZSTD_parameters zstd_parameters; zstd_parameters zstd_get_params(int level, unsigned long long estimated_src_size); + +/** + * zstd_get_cparams() - returns zstd_compression_parameters for selected level + * @level: The compression level + * @estimated_src_size: The estimated source size to compress or 0 + * if unknown. + * @dict_size: Dictionary size. + * + * Return: The selected zstd_compression_parameters. + */ +zstd_compression_parameters zstd_get_cparams(int level, + unsigned long long estimated_src_size, size_t dict_size); + /* ====== Single-pass Compression ====== */ typedef ZSTD_CCtx zstd_cctx; @@ -180,6 +217,71 @@ zstd_cctx *zstd_init_cctx(void *workspace, size_t workspace_size); size_t zstd_compress_cctx(zstd_cctx *cctx, void *dst, size_t dst_capacity, const void *src, size_t src_size, const zstd_parameters *parameters); +/** + * zstd_create_cctx_advanced() - Create compression context + * @custom_mem: Custom allocator. + * + * Return: NULL on error, pointer to compression context otherwise. + */ +zstd_cctx *zstd_create_cctx_advanced(zstd_custom_mem custom_mem); + +/** + * zstd_free_cctx() - Free compression context + * @cdict: Pointer to compression context. + * + * Return: Always 0. + */ +size_t zstd_free_cctx(zstd_cctx* cctx); + +/** + * struct zstd_cdict - Compression dictionary. + * See zstd_lib.h. + */ +typedef ZSTD_CDict zstd_cdict; + +/** + * zstd_create_cdict_byreference() - Create compression dictionary + * @dict: Pointer to dictionary buffer. + * @dict_size: Size of the dictionary buffer. + * @dict_load_method: Dictionary load method. + * @dict_content_type: Dictionary content type. + * @custom_mem: Memory allocator. + * + * Note, this uses @dict by reference (ZSTD_dlm_byRef), so it should be + * free before zstd_cdict is destroyed. + * + * Return: NULL on error, pointer to compression dictionary + * otherwise. + */ +zstd_cdict *zstd_create_cdict_byreference(const void *dict, size_t dict_size, + zstd_compression_parameters cparams, + zstd_custom_mem custom_mem); + +/** + * zstd_free_cdict() - Free compression dictionary + * @cdict: Pointer to compression dictionary. + * + * Return: Always 0. + */ +size_t zstd_free_cdict(zstd_cdict* cdict); + +/** + * zstd_compress_using_cdict() - compress src into dst using a dictionary + * @cctx: The context. Must have been initialized with zstd_init_cctx(). + * @dst: The buffer to compress src into. + * @dst_capacity: The size of the destination buffer. May be any size, but + * ZSTD_compressBound(srcSize) is guaranteed to be large enough. + * @src: The data to compress. + * @src_size: The size of the data to compress. + * @cdict: The dictionary to be used. + * + * Return: The compressed size or an error, which can be checked using + * zstd_is_error(). + */ +size_t zstd_compress_using_cdict(zstd_cctx *cctx, void *dst, + size_t dst_capacity, const void *src, size_t src_size, + const zstd_cdict *cdict); + /* ====== Single-pass Decompression ====== */ typedef ZSTD_DCtx zstd_dctx; @@ -220,6 +322,71 @@ zstd_dctx *zstd_init_dctx(void *workspace, size_t workspace_size); size_t zstd_decompress_dctx(zstd_dctx *dctx, void *dst, size_t dst_capacity, const void *src, size_t src_size); +/** + * struct zstd_ddict - Decompression dictionary. + * See zstd_lib.h. + */ +typedef ZSTD_DDict zstd_ddict; + +/** + * zstd_create_ddict_byreference() - Create decompression dictionary + * @dict: Pointer to dictionary buffer. + * @dict_size: Size of the dictionary buffer. + * @dict_load_method: Dictionary load method. + * @dict_content_type: Dictionary content type. + * @custom_mem: Memory allocator. + * + * Note, this uses @dict by reference (ZSTD_dlm_byRef), so it should be + * free before zstd_ddict is destroyed. + * + * Return: NULL on error, pointer to decompression dictionary + * otherwise. + */ +zstd_ddict *zstd_create_ddict_byreference(const void *dict, size_t dict_size, + zstd_custom_mem custom_mem); +/** + * zstd_free_ddict() - Free decompression dictionary + * @dict: Pointer to the dictionary. + * + * Return: Always 0. + */ +size_t zstd_free_ddict(zstd_ddict *ddict); + +/** + * zstd_create_dctx_advanced() - Create decompression context + * @custom_mem: Custom allocator. + * + * Return: NULL on error, pointer to decompression context otherwise. + */ +zstd_dctx *zstd_create_dctx_advanced(zstd_custom_mem custom_mem); + +/** + * zstd_free_dctx() -- Free decompression context + * @dctx: Pointer to decompression context. + * Return: Always 0. + */ +size_t zstd_free_dctx(zstd_dctx *dctx); + +/** + * zstd_decompress_using_ddict() - decompress src into dst using a dictionary + * @dctx: The decompression context. + * @dst: The buffer to decompress src into. + * @dst_capacity: The size of the destination buffer. Must be at least as large + * as the decompressed size. If the caller cannot upper bound the + * decompressed size, then it's better to use the streaming API. + * @src: The zstd compressed data to decompress. Multiple concatenated + * frames and skippable frames are allowed. + * @src_size: The exact size of the data to decompress. + * @ddict: The dictionary to be used. + * + * Return: The decompressed size or an error, which can be checked using + * zstd_is_error(). + */ +size_t zstd_decompress_using_ddict(zstd_dctx *dctx, + void *dst, size_t dst_capacity, const void *src, size_t src_size, + const zstd_ddict *ddict); + + /* ====== Streaming Buffers ====== */ /** diff --git a/include/linux/zswap.h b/include/linux/zswap.h index 341aea490070..d961ead91bf1 100644 --- a/include/linux/zswap.h +++ b/include/linux/zswap.h @@ -7,26 +7,24 @@ struct lruvec; -extern u64 zswap_pool_total_size; -extern atomic_t zswap_stored_pages; +extern atomic_long_t zswap_stored_pages; #ifdef CONFIG_ZSWAP struct zswap_lruvec_state { /* - * Number of pages in zswap that should be protected from the shrinker. - * This number is an estimate of the following counts: + * Number of swapped in pages from disk, i.e not found in the zswap pool. * - * a) Recent page faults. - * b) Recent insertion to the zswap LRU. This includes new zswap stores, - * as well as recent zswap LRU rotations. - * - * These pages are likely to be warm, and might incur IO if the are written - * to swap. + * This is consumed and subtracted from the lru size in + * zswap_shrinker_count() to penalize past overshrinking that led to disk + * swapins. The idea is that had we considered this many more pages in the + * LRU active/protected and not written them back, we would not have had to + * swapped them in. */ - atomic_long_t nr_zswap_protected; + atomic_long_t nr_disk_swapins; }; +unsigned long zswap_total_pages(void); bool zswap_store(struct folio *folio); bool zswap_load(struct folio *folio); void zswap_invalidate(swp_entry_t swp); @@ -35,7 +33,8 @@ void zswap_swapoff(int type); void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg); void zswap_lruvec_state_init(struct lruvec *lruvec); void zswap_folio_swapin(struct folio *folio); -bool is_zswap_enabled(void); +bool zswap_is_enabled(void); +bool zswap_never_enabled(void); #else struct zswap_lruvec_state {}; @@ -60,11 +59,16 @@ static inline void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg) {} static inline void zswap_lruvec_state_init(struct lruvec *lruvec) {} static inline void zswap_folio_swapin(struct folio *folio) {} -static inline bool is_zswap_enabled(void) +static inline bool zswap_is_enabled(void) { return false; } +static inline bool zswap_never_enabled(void) +{ + return true; +} + #endif #endif /* _LINUX_ZSWAP_H */ |