diff options
Diffstat (limited to 'include/linux')
279 files changed, 5829 insertions, 2855 deletions
diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 34829f2c517a..28c3fb2bef0d 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -242,9 +242,6 @@ 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 @@ -267,8 +264,6 @@ 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); - #ifndef PHYS_CPUID_INVALID typedef u32 phys_cpuid_t; #define PHYS_CPUID_INVALID (phys_cpuid_t)(-1) @@ -421,7 +416,7 @@ 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); @@ -573,9 +568,13 @@ 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_PRM_SUPPORT 0x00200000 #define OSC_SB_FFH_OPR_SUPPORT 0x00400000 @@ -1233,7 +1232,7 @@ 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 +1245,7 @@ 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 +1258,10 @@ 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) 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/alloc_tag.h b/include/linux/alloc_tag.h new file mode 100644 index 000000000000..afc9e259a2d3 --- /dev/null +++ b/include/linux/alloc_tag.h @@ -0,0 +1,216 @@ +/* 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/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); + +#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) {} + +#endif /* CONFIG_MEM_ALLOC_PROFILING_DEBUG */ + +#ifdef CONFIG_MEM_ALLOC_PROFILING + +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 accound 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_tags") = { \ + .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_tags") = { \ + .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, + "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"); +} + +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 void __alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag) +{ + ref->ct = &tag->ct; + /* + * 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); +} + +static inline void alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag) +{ + alloc_tag_add_check(ref, tag); + if (!ref || !tag) + return; + + __alloc_tag_ref_set(ref, tag); +} + +static inline void alloc_tag_add(union codetag_ref *ref, struct alloc_tag *tag, size_t bytes) +{ + alloc_tag_add_check(ref, tag); + if (!ref || !tag) + return; + + __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) \ +({ \ + struct alloc_tag * __maybe_unused _old = alloc_tag_save(_tag); \ + typeof(_do_alloc) _res = _do_alloc; \ + alloc_tag_restore(_tag, _old); \ + _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..958a55bcc708 100644 --- a/include/linux/amba/bus.h +++ b/include/linux/amba/bus.h @@ -112,11 +112,18 @@ extern struct bus_type amba_bustype; #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 *); #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; } diff --git a/include/linux/amd-pstate.h b/include/linux/amd-pstate.h index d21838835abd..d58fc022ec46 100644 --- a/include/linux/amd-pstate.h +++ b/include/linux/amd-pstate.h @@ -49,13 +49,17 @@ struct amd_aperf_mperf { * @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 + * @min_limit_perf: Cached value of the performance corresponding to policy->min + * @max_limit_perf: Cached value of the performance corresponding to policy->max + * @min_limit_freq: Cached value of policy->min (in khz) + * @max_limit_freq: Cached value of policy->max (in khz) + * @max_freq: the frequency (in khz) that mapped to highest_perf + * @min_freq: the frequency (in khz) that mapped to lowest_perf + * @nominal_freq: the frequency (in khz) that mapped to nominal_perf + * @lowest_nonlinear_freq: the frequency (in khz) 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 + * @freq: current cpu frequency value (in khz) * @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, @@ -124,4 +128,10 @@ static const char * const amd_pstate_mode_string[] = { [AMD_PSTATE_GUIDED] = "guided", NULL, }; + +struct quirk_entry { + u32 nominal_freq; + u32 lowest_freq; +}; + #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..b721f360d759 100644 --- a/include/linux/arch_topology.h +++ b/include/linux/arch_topology.h @@ -60,14 +60,14 @@ 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/arm_ffa.h b/include/linux/arm_ffa.h index c906f666ff5d..c82d56768101 100644 --- a/include/linux/arm_ffa.h +++ b/include/linux/arm_ffa.h @@ -126,6 +126,7 @@ /* FFA Bus/Device/Driver related */ struct ffa_device { u32 id; + u32 properties; int vm_id; bool mode_32bit; uuid_t uuid; @@ -221,12 +222,29 @@ 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 +254,14 @@ 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; +}; + struct ffa_mem_region_addr_range { /* The base IPA of the constituent memory region, aligned to 4 kiB */ u64 address; @@ -396,6 +422,7 @@ 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); }; struct ffa_mem_ops { diff --git a/include/linux/bio.h b/include/linux/bio.h index 875d792bffff..d5379548d684 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -615,6 +615,13 @@ 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) { @@ -824,5 +831,9 @@ static inline void bio_clear_polled(struct bio *bio) 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..8c4768c44a01 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -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 @@ -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))) +#define bitmap_size(nbits) (ALIGN(nbits, BITS_PER_LONG) / BITS_PER_BYTE) + static 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; @@ -234,7 +240,7 @@ static inline void bitmap_zero(unsigned long *dst, unsigned int nbits) static 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; @@ -245,7 +251,7 @@ static inline void bitmap_fill(unsigned long *dst, unsigned int nbits) static 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; @@ -722,38 +728,83 @@ static inline void bitmap_from_u64(unsigned long *dst, u64 mask) } /** - * 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 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; + + if (unlikely(!nbits || nbits > BITS_PER_LONG)) + return 0; + + if (space >= nbits) + return (map[index] >> offset) & BITMAP_LAST_WORD_MASK(nbits); - return (map[index] >> offset) & 0xFF; + 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) -{ - const size_t index = BIT_WORD(start); - const unsigned long offset = start % BITS_PER_LONG; - - map[index] &= ~(0xFFUL << offset); +static inline void bitmap_write(unsigned long *map, unsigned long value, + unsigned long start, unsigned long nbits) +{ + 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] &= (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..3112ae7d6524 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -21,6 +21,8 @@ #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); @@ -80,6 +82,7 @@ __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 +203,7 @@ 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); @@ -236,7 +239,7 @@ 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) @@ -252,7 +255,7 @@ 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; @@ -272,23 +275,11 @@ 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/blk-mq.h b/include/linux/blk-mq.h index d3d8fd8e229b..89ba6b16fe8b 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -54,8 +54,8 @@ typedef __u32 __bitwise req_flags_t; /* 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)) +/* The request completion needs to be signaled to zone write pluging. */ +#define RQF_ZONE_WRITE_PLUGGING ((__force req_flags_t)(1 << 20)) /* ->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)) @@ -1150,85 +1150,4 @@ 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..781c4500491b 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 */ @@ -65,10 +70,6 @@ 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; /* * keep this out-of-line as it's both big and not needed in the fast @@ -88,15 +89,9 @@ 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 +132,13 @@ 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 +147,20 @@ 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) /** * blk_path_error - returns true if error may be path related @@ -234,7 +217,12 @@ 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 @@ -304,7 +292,8 @@ 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 }; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c3e8f7cf96be..aefdda9f4ec7 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -128,6 +128,8 @@ typedef unsigned int __bitwise blk_mode_t; #define BLK_OPEN_WRITE_IOCTL ((__force blk_mode_t)(1 << 4)) /* open is exclusive wrt all other BLK_OPEN_WRITE opens to the device */ #define BLK_OPEN_RESTRICT_WRITES ((__force blk_mode_t)(1 << 5)) +/* return partition scanning errors */ +#define BLK_OPEN_STRICT_SCAN ((__force blk_mode_t)(1 << 6)) struct gendisk { /* @@ -177,22 +179,21 @@ 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 int zone_capacity; unsigned long *conv_zones_bitmap; - unsigned long *seq_zones_wlock; + unsigned int zone_wplugs_hash_bits; + spinlock_t zone_wplugs_lock; + struct mempool_s *zone_wplugs_pool; + struct hlist_head *zone_wplugs_hash; + struct list_head zone_wplugs_err_list; + struct work_struct zone_wplugs_work; + struct workqueue_struct *zone_wplugs_wq; #endif /* CONFIG_BLK_DEV_ZONED */ #if IS_ENABLED(CONFIG_CDROM) @@ -211,11 +212,6 @@ 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 @@ -231,6 +227,19 @@ 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. @@ -329,8 +338,7 @@ 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 @@ -447,8 +455,6 @@ 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; @@ -631,15 +637,6 @@ static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector) return sector >> ilog2(disk->queue->limits.chunk_sectors); } -static inline bool disk_zone_is_seq(struct gendisk *disk, sector_t sector) -{ - 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); -} - static inline void disk_set_max_open_zones(struct gendisk *disk, unsigned int max_open_zones) { @@ -662,6 +659,7 @@ static inline unsigned int bdev_max_active_zones(struct block_device *bdev) return bdev->bd_disk->queue->limits.max_active_zones; } +bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs); #else /* CONFIG_BLK_DEV_ZONED */ static inline unsigned int bdev_nr_zones(struct block_device *bdev) { @@ -672,10 +670,6 @@ 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; @@ -689,6 +683,10 @@ static inline unsigned int bdev_max_active_zones(struct block_device *bdev) { return 0; } +static inline bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs) +{ + return false; +} #endif /* CONFIG_BLK_DEV_ZONED */ static inline unsigned int blk_queue_depth(struct request_queue *q) @@ -720,15 +718,35 @@ 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 u8 bdev_partno(const struct block_device *bdev) +{ + 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 int get_disk_ro(struct gendisk *disk) { - return disk->part0->bd_read_only || + 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) { - 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); @@ -853,9 +871,11 @@ 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); } /* @@ -892,18 +912,25 @@ 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); +/** + * 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); +} + /* * 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, @@ -920,7 +947,6 @@ 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, @@ -928,10 +954,6 @@ extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, 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); @@ -940,17 +962,6 @@ 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 *); @@ -1095,7 +1106,7 @@ 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 { @@ -1154,12 +1165,29 @@ 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 unsigned int queue_limits_max_zone_append_sectors(struct queue_limits *l) +{ + unsigned int max_sectors = min(l->chunk_sectors, l->max_hw_sectors); + + return min_not_zero(l->max_zone_append_sectors, max_sectors); +} + +static inline unsigned int queue_max_zone_append_sectors(struct request_queue *q) { + if (!blk_queue_is_zoned(q)) + return 0; - const struct queue_limits *l = &q->limits; + return queue_limits_max_zone_append_sectors(&q->limits); +} - return min(l->max_zone_append_sectors, l->max_sectors); +static inline bool queue_emulates_zone_append(struct request_queue *q) +{ + return blk_queue_is_zoned(q) && !q->limits.max_zone_append_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 @@ -1301,18 +1329,6 @@ 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); @@ -1328,6 +1344,12 @@ 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) { @@ -1364,11 +1386,6 @@ 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); @@ -1474,7 +1491,7 @@ static inline void bio_end_io_acct(struct bio *bio, unsigned long start_time) } 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); @@ -1505,16 +1522,6 @@ struct blk_holder_ops { * Thaw the file system mounted on the block device. */ int (*thaw)(struct block_device *bdev); - - /* - * If needed, get a reference to the holder. - */ - void (*get_holder)(void *holder); - - /* - * Release the holder. - */ - void (*put_holder)(void *holder); }; /* @@ -1546,6 +1553,8 @@ 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); @@ -1585,6 +1594,7 @@ static inline int early_lookup_bdev(const char *pathname, dev_t *dev) int bdev_freeze(struct block_device *bdev); int bdev_thaw(struct block_device *bdev); +void bdev_fput(struct file *bdev_file); struct io_comp_batch { struct request *req_list; diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h index ca73940e26df..3f4b4ac527ca 100644 --- a/include/linux/bootconfig.h +++ b/include/linux/bootconfig.h @@ -10,6 +10,7 @@ #ifdef __KERNEL__ #include <linux/kernel.h> #include <linux/types.h> +bool __init cmdline_has_extra_options(void); #else /* !__KERNEL__ */ /* * NOTE: This is only for tools/bootconfig, because tools/bootconfig will @@ -287,7 +288,12 @@ int __init xbc_init(const char *buf, size_t size, const char **emsg, int *epos); int __init xbc_get_info(int *node_size, size_t *data_size); /* XBC cleanup data structures */ -void __init xbc_exit(void); +void __init _xbc_exit(bool early); + +static inline void xbc_exit(void) +{ + _xbc_exit(false); +} /* XBC embedded bootconfig data in kernel */ #ifdef CONFIG_BOOT_CONFIG_EMBED diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 4f20f62f9d63..5e694a308081 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 +202,7 @@ 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), }; typedef void (*btf_dtor_kfunc_t)(void *); @@ -238,6 +239,7 @@ struct btf_record { u32 field_mask; int spin_lock_off; int timer_off; + int wq_off; int refcount_off; struct btf_field fields[]; }; @@ -312,6 +314,8 @@ 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"; @@ -340,6 +344,8 @@ 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: @@ -367,6 +373,8 @@ 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: @@ -406,6 +414,7 @@ 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: @@ -525,6 +534,7 @@ 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, @@ -1116,8 +1126,7 @@ 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); @@ -1266,6 +1275,7 @@ 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); @@ -1574,12 +1584,26 @@ struct bpf_link { enum bpf_link_type type; const struct bpf_link_ops *ops; struct bpf_prog *prog; - struct work_struct work; + /* rcu is used before freeing, work can be used to schedule that + * RCU-based freeing before that, so they never overlap + */ + union { + struct rcu_head rcu; + struct work_struct work; + }; }; struct bpf_link_ops { void (*release)(struct bpf_link *link); + /* deallocate link resources callback, called without RCU grace period + * waiting + */ 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 + */ + void (*dealloc_deferred)(struct bpf_link *link); int (*detach)(struct bpf_link *link); int (*update_prog)(struct bpf_link *link, struct bpf_prog *new_prog, struct bpf_prog *old_prog); @@ -1608,6 +1632,12 @@ 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; @@ -2190,6 +2220,7 @@ 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); @@ -2230,31 +2261,14 @@ 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); -} +#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 @@ -2991,6 +3005,7 @@ 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); @@ -3089,6 +3104,11 @@ 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 */ 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_verifier.h b/include/linux/bpf_verifier.h index 7cb1b75eee38..50aa87f8d77f 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -421,11 +421,13 @@ struct bpf_verifier_state { struct bpf_active_lock active_lock; bool speculative; bool active_rcu_lock; + u32 active_preempt_lock; /* 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; @@ -502,6 +504,13 @@ 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 +523,7 @@ 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 { 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/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_ids.h b/include/linux/btf_ids.h index e24aabfe8ecc..c0e3e1426a82 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[]; diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index d78454a4dd1f..e022e40b099e 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -303,12 +303,38 @@ 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 +364,7 @@ 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 +375,7 @@ 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 +463,21 @@ 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/bus/stm32_firewall_device.h b/include/linux/bus/stm32_firewall_device.h new file mode 100644 index 000000000000..18e0a2fc3816 --- /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/cc_platform.h b/include/linux/cc_platform.h index cb0d6cd1c12f..60693a145894 100644 --- a/include/linux/cc_platform.h +++ b/include/linux/cc_platform.h @@ -90,6 +90,14 @@ enum cc_attr { * Examples include TDX Guest. */ CC_ATTR_HOTPLUG_DISABLED, + + /** + * @CC_ATTR_HOST_SEV_SNP: AMD SNP enabled on the host. + * + * The host kernel is running with the necessary features + * enabled to run SEV-SNP guests. + */ + CC_ATTR_HOST_SEV_SNP, }; #ifdef CONFIG_ARCH_HAS_CC_PLATFORM @@ -107,10 +115,14 @@ enum cc_attr { * * FALSE - Specified Confidential Computing attribute is not active */ bool cc_platform_has(enum cc_attr attr); +void cc_platform_set(enum cc_attr attr); +void cc_platform_clear(enum cc_attr attr); #else /* !CONFIG_ARCH_HAS_CC_PLATFORM */ static inline bool cc_platform_has(enum cc_attr attr) { return false; } +static inline void cc_platform_set(enum cc_attr attr) { } +static inline void cc_platform_clear(enum cc_attr attr) { } #endif /* CONFIG_ARCH_HAS_CC_PLATFORM */ 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/cgroup.h b/include/linux/cgroup.h index 34aaf0e87def..2150ca60394b 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -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. diff --git a/include/linux/clk.h b/include/linux/clk.h index 00623f4de5e1..0fa56d672532 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -286,6 +286,11 @@ static inline int clk_rate_exclusive_get(struct clk *clk) return 0; } +static inline int devm_clk_rate_exclusive_get(struct device *dev, struct clk *clk) +{ + return 0; +} + static inline void clk_rate_exclusive_put(struct clk *clk) {} #endif diff --git a/include/linux/closure.h b/include/linux/closure.h index c554c6a08768..99155df162d0 100644 --- a/include/linux/closure.h +++ b/include/linux/closure.h @@ -194,6 +194,18 @@ 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); 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..c2a579ccd455 --- /dev/null +++ b/include/linux/codetag.h @@ -0,0 +1,81 @@ +/* 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; + +/* + * 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); + bool (*module_unload)(struct codetag_type *cttype, + struct codetag_module *cmod); +}; + +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) +void codetag_load_module(struct module *mod); +bool codetag_unload_module(struct module *mod); +#else +static inline void codetag_load_module(struct module *mod) {} +static inline bool codetag_unload_module(struct module *mod) { return true; } +#endif + +#endif /* _LINUX_CODETAG_H */ diff --git a/include/linux/compiler.h b/include/linux/compiler.h index c00cc6c0878a..8c252e073bd8 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -268,7 +268,7 @@ static inline void *offset_to_ptr(const int *off) * - When one operand is a null pointer constant (i.e. when x is an integer * constant expression) and the other is an object pointer (i.e. our * third operand), the conditional operator returns the type of the - * object pointer operand (i.e. "int *). Here, within the sizeof(), we + * object pointer operand (i.e. "int *"). Here, within the sizeof(), we * would then get: * sizeof(*((int *)(...)) == sizeof(int) == 4 * - When one operand is a void pointer (i.e. when x is not an integer diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 2abaa3a825a9..d1a9dbb8e1a7 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -273,15 +273,44 @@ 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 +/* + * 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"))) diff --git a/include/linux/coredump.h b/include/linux/coredump.h index d3eba4360150..0904ba010341 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. diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 272e4e79e15c..861c3bfc5f17 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -221,7 +221,18 @@ void cpuhp_report_idle_dead(void); static inline void cpuhp_report_idle_dead(void) { } #endif /* #ifdef CONFIG_HOTPLUG_CPU */ +#ifdef CONFIG_CPU_MITIGATIONS extern bool cpu_mitigations_off(void); extern bool cpu_mitigations_auto_nosmt(void); +#else +static inline bool cpu_mitigations_off(void) +{ + return true; +} +static inline bool cpu_mitigations_auto_nosmt(void) +{ + return false; +} +#endif #endif /* _LINUX_CPU_H_ */ diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 9956afb9acc2..20f7e98ee8af 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 diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 35e78ddb2b37..7a5785f405b6 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -146,6 +146,7 @@ enum cpuhp_state { CPUHP_AP_IRQ_MIPS_GIC_STARTING, CPUHP_AP_IRQ_LOONGARCH_STARTING, CPUHP_AP_IRQ_SIFIVE_PLIC_STARTING, + CPUHP_AP_IRQ_RISCV_IMSIC_STARTING, CPUHP_AP_ARM_MVEBU_COHERENCY, CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING, CPUHP_AP_PERF_X86_STARTING, diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 1c29947db848..7600e877908f 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -188,6 +188,23 @@ unsigned int cpumask_first_and(const struct cpumask *srcp1, const struct cpumask } /** + * 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 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 * @@ -389,6 +406,29 @@ unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu) } /** + * cpumask_any_and_but - pick a "random" 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 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 @@ -853,7 +893,7 @@ static inline int cpulist_parse(const char *buf, struct cpumask *dstp) */ static inline unsigned int cpumask_size(void) { - return BITS_TO_LONGS(large_cpumask_bits) * sizeof(long); + return bitmap_size(large_cpumask_bits); } /* @@ -1017,11 +1057,6 @@ 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); -} - static inline void set_cpu_possible(unsigned int cpu, bool possible) { diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 0ce6ff0d9c9a..de4cf0ee96f7 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); @@ -185,8 +184,6 @@ 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) { } 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/cxl-event.h b/include/linux/cxl-event.h index 03fa6d50d46f..60b25020281f 100644 --- a/include/linux/cxl-event.h +++ b/include/linux/cxl-event.h @@ -3,6 +3,10 @@ #ifndef _LINUX_CXL_EVENT_H #define _LINUX_CXL_EVENT_H +#include <linux/types.h> +#include <linux/uuid.h> +#include <linux/workqueue_types.h> + /* * Common Event Record Format * CXL rev 3.0 section 8.2.9.2.1; Table 8-42 @@ -91,11 +95,21 @@ struct cxl_event_mem_module { u8 reserved[0x3d]; } __packed; +/* + * General Media or DRAM Event Common Fields + * - provides common access to phys_addr + */ +struct cxl_event_common { + struct cxl_event_record_hdr hdr; + __le64 phys_addr; +} __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; + struct cxl_event_common common; } __packed; /* @@ -140,4 +154,29 @@ struct cxl_cper_event_rec { union cxl_event event; } __packed; +struct cxl_cper_work_data { + enum cxl_event_type event_type; + struct cxl_cper_event_rec rec; +}; + +#ifdef CONFIG_ACPI_APEI_GHES +int cxl_cper_register_work(struct work_struct *work); +int cxl_cper_unregister_work(struct work_struct *work); +int cxl_cper_kfifo_get(struct cxl_cper_work_data *wd); +#else +static inline int cxl_cper_register_work(struct work_struct *work) +{ + return 0; +} + +static inline int cxl_cper_unregister_work(struct work_struct *work) +{ + return 0; +} +static inline int cxl_cper_kfifo_get(struct cxl_cper_work_data *wd) +{ + return 0; +} +#endif + #endif /* _LINUX_CXL_EVENT_H */ diff --git a/include/linux/damon.h b/include/linux/damon.h index 886d07294f4e..f7da65e1ac04 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -297,6 +297,7 @@ 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 +316,7 @@ 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, diff --git a/include/linux/dev_printk.h b/include/linux/dev_printk.h index 6bfe70decc9f..ae80a303c216 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 /* diff --git a/include/linux/devcoredump.h b/include/linux/devcoredump.h index c008169ed2c6..c8f7eb6cc191 100644 --- a/include/linux/devcoredump.h +++ b/include/linux/devcoredump.h @@ -63,6 +63,8 @@ void dev_coredumpm(struct device *dev, struct module *owner, void dev_coredumpsg(struct device *dev, struct scatterlist *table, size_t datalen, gfp_t gfp); + +void dev_coredump_put(struct device *dev); #else static inline void dev_coredumpv(struct device *dev, void *data, size_t datalen, gfp_t gfp) @@ -85,6 +87,9 @@ static inline void dev_coredumpsg(struct device *dev, struct scatterlist *table, { _devcd_free_sgtable(table); } +static inline void dev_coredump_put(struct device *dev) +{ +} #endif /* CONFIG_DEV_COREDUMP */ #endif /* __DEVCOREDUMP_H */ diff --git a/include/linux/device.h b/include/linux/device.h index 97c4b046c09d..d4b50accff26 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -691,6 +691,7 @@ 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. * * At the lowest level, every device in a Linux system is represented by an * instance of struct device. The device structure contains the information @@ -803,6 +804,9 @@ struct device { #ifdef CONFIG_DMA_OPS_BYPASS bool dma_ops_bypass : 1; #endif +#ifdef CONFIG_DMA_NEED_SYNC + bool dma_skip_sync:1; +#endif }; /** @@ -1247,6 +1251,7 @@ void device_link_del(struct device_link *link); void device_link_remove(void *consumer, struct device *supplier); void device_links_supplier_sync_state_pause(void); void device_links_supplier_sync_state_resume(void); +void device_link_wait_removal(void); /* Create alias, so I can be autoloaded. */ #define MODULE_ALIAS_CHARDEV(major,minor) \ 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/dma-buf.h b/include/linux/dma-buf.h index 8ff4add71f88..36216d28d8bd 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -370,8 +370,10 @@ struct dma_buf { */ struct module *owner; +#if IS_ENABLED(CONFIG_DEBUG_FS) /** @list_node: node for dma_buf accounting and debugging. */ struct list_head list_node; +#endif /** @priv: exporter specific private data for this buffer object. */ void *priv; diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index 3eb3589ff43e..edbe13d00776 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -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-chain.h b/include/linux/dma-fence-chain.h index 4bdf0b96da28..ad9e2506c2f4 100644 --- a/include/linux/dma-fence-chain.h +++ b/include/linux/dma-fence-chain.h @@ -86,10 +86,8 @@ dma_fence_chain_contained(struct dma_fence *fence) * * Returns a new struct dma_fence_chain object or NULL on failure. */ -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-map-ops.h b/include/linux/dma-map-ops.h index 4abc60f04209..02a1c825896b 100644 --- a/include/linux/dma-map-ops.h +++ b/include/linux/dma-map-ops.h @@ -18,8 +18,11 @@ struct iommu_ops; * * DMA_F_PCI_P2PDMA_SUPPORTED: Indicates the dma_map_ops implementation can * handle PCI P2PDMA pages in the map_sg/unmap_sg operation. + * DMA_F_CAN_SKIP_SYNC: DMA sync operations can be skipped if the device is + * coherent and it's not an SWIOTLB buffer. */ #define DMA_F_PCI_P2PDMA_SUPPORTED (1 << 0) +#define DMA_F_CAN_SKIP_SYNC (1 << 1) struct dma_map_ops { unsigned int flags; @@ -29,7 +32,7 @@ struct dma_map_ops { 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, @@ -273,6 +276,15 @@ static inline bool dev_is_dma_coherent(struct device *dev) } #endif /* CONFIG_ARCH_HAS_DMA_COHERENCE_H */ +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 +438,9 @@ 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..f693aafe221f 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -117,14 +117,6 @@ 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 +139,6 @@ 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 +186,6 @@ 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 +252,6 @@ 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 +281,82 @@ 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, 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/dmar.h b/include/linux/dmar.h index e34b601b71fd..499bb2c63483 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); 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..281298e77a15 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; + + 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/efi.h b/include/linux/efi.h index d59b0947fba0..418e555459da 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1072,12 +1072,11 @@ 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, 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 770755df852f..1ff52020cf75 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -172,6 +172,7 @@ 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); /** * em_pd_get_efficient_state() - Get an efficient performance state from the EM @@ -245,7 +246,6 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd, * max utilization to the allowed CPU capacity before calculating * effective performance. */ - max_util = map_util_perf(max_util); max_util = min(max_util, allowed_cpu_cap); /* @@ -387,6 +387,10 @@ 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; +} #endif #endif diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 224645f17c33..2ad1ffa4ccb9 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -71,6 +71,12 @@ 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 @@ -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) @@ -608,6 +612,31 @@ static inline void eth_hw_addr_gen(struct net_device *dev, const u8 *base_addr, } /** + * eth_skb_pkt_type - Assign packet type if destination address does not match + * @skb: Assigned a packet type if address does not match @dev address + * @dev: Network device used to compare packet address against + * + * If the destination MAC address of the packet does not match the network + * device address, assign an appropriate packet type. + */ +static inline void eth_skb_pkt_type(struct sk_buff *skb, + const struct net_device *dev) +{ + const struct ethhdr *eth = eth_hdr(skb); + + if (unlikely(!ether_addr_equal_64bits(eth->h_dest, dev->dev_addr))) { + if (unlikely(is_multicast_ether_addr_64bits(eth->h_dest))) { + if (ether_addr_equal_64bits(eth->h_dest, dev->broadcast)) + skb->pkt_type = PACKET_BROADCAST; + else + skb->pkt_type = PACKET_MULTICAST; + } else { + skb->pkt_type = PACKET_OTHERHOST; + } + } +} + +/** * eth_skb_pad - Pad buffer to mininum number of octets for Ethernet frame * @skb: Buffer to pad * diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 9901e563f706..6fd9107d3cc0 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -480,6 +480,26 @@ struct ethtool_rmon_stats { ); }; +/** + * struct ethtool_ts_stats - HW timestamping statistics + * @pkts: Number of packets successfully timestamped by the hardware. + * @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 lost; + u64 err; + ); +}; + #define ETH_MODULE_EEPROM_PAGE_LEN 128 #define ETH_MODULE_MAX_I2C_ADDRESS 0x7f @@ -755,7 +775,10 @@ 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 @@ -898,6 +921,8 @@ struct ethtool_ops { struct ethtool_dump *, void *); int (*set_dump)(struct net_device *, struct ethtool_dump *); int (*get_ts_info)(struct net_device *, struct 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 *, 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..32cef1144117 --- /dev/null +++ b/include/linux/execmem.h @@ -0,0 +1,132 @@ +/* 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 + */ +enum execmem_range_flags { + EXECMEM_KASAN_SHADOW = (1 << 0), +}; + +/** + * 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); + +#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/f2fs_fs.h b/include/linux/f2fs_fs.h index a357287eac1e..41d1d71c36ff 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -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/fb.h b/include/linux/fb.h index 0dd27364d56f..b40754b545ad 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; @@ -694,6 +694,10 @@ extern int fb_deferred_io_fsync(struct file *file, loff_t start, __FB_GEN_DEFAULT_DEFERRED_OPS_RDWR(__prefix, __damage_range, sys) \ __FB_GEN_DEFAULT_DEFERRED_OPS_DRAW(__prefix, __damage_area, sys) +#define FB_GEN_DEFAULT_DEFERRED_DMAMEM_OPS(__prefix, __damage_range, __damage_area) \ + __FB_GEN_DEFAULT_DEFERRED_OPS_RDWR(__prefix, __damage_range, sys) \ + __FB_GEN_DEFAULT_DEFERRED_OPS_DRAW(__prefix, __damage_area, sys) + /* * Initializes struct fb_ops for deferred I/O. */ diff --git a/include/linux/file.h b/include/linux/file.h index 169692cb1906..45d0f4800abd 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -84,6 +84,7 @@ static inline void fdput_pos(struct fd 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) extern int f_dupfd(unsigned int from, struct file *file, unsigned flags); extern int replace_fd(unsigned fd, struct file *file, unsigned flags); diff --git a/include/linux/filter.h b/include/linux/filter.h index c99bc3df2d28..0f12cf01070e 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) @@ -644,14 +676,16 @@ 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); @@ -887,20 +921,22 @@ 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); @@ -957,12 +993,16 @@ 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); +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); diff --git a/include/linux/find.h b/include/linux/find.h index c69598e383c1..28ec5a03393a 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); @@ -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 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 diff --git a/include/linux/firewire.h b/include/linux/firewire.h index dd9f2d765e68..00abe0e5d602 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -463,7 +463,8 @@ struct fw_iso_packet { 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[]; /* tx: Top of 1394 isoch. data_block */ + /* tx: Top of 1394 isoch. data_block */ + u32 header[] __counted_by(header_length); }; #define FW_ISO_CONTEXT_TRANSMIT 0 diff --git a/include/linux/firmware/cirrus/cs_dsp.h b/include/linux/firmware/cirrus/cs_dsp.h index 23384a54d575..82687e07a7c2 100644 --- a/include/linux/firmware/cirrus/cs_dsp.h +++ b/include/linux/firmware/cirrus/cs_dsp.h @@ -238,8 +238,12 @@ 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); diff --git a/include/linux/firmware/qcom/qcom_qseecom.h b/include/linux/firmware/qcom/qcom_qseecom.h index 5c28298a98be..366243ee9609 100644 --- a/include/linux/firmware/qcom/qcom_qseecom.h +++ b/include/linux/firmware/qcom/qcom_qseecom.h @@ -10,6 +10,7 @@ #define __QCOM_QSEECOM_H #include <linux/auxiliary_bus.h> +#include <linux/dma-mapping.h> #include <linux/types.h> #include <linux/firmware/qcom/qcom_scm.h> @@ -25,11 +26,56 @@ 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: Request buffer sent to the app (must be DMA-mappable). + * @req: DMA address of the request buffer sent to the app. * @req_size: Size of the request buffer. - * @rsp: Response buffer, written to by the app (must be DMA-mappable). + * @rsp: DMA address of the response buffer, written to by the app. * @rsp_size: Size of the response buffer. * * Sends a request to the QSEE app associated with the given client and read @@ -43,8 +89,9 @@ struct qseecom_client { * * Return: Zero on success, nonzero on failure. */ -static inline int qcom_qseecom_app_send(struct qseecom_client *client, void *req, size_t req_size, - void *rsp, size_t rsp_size) +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) { 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 ccaf28846054..aaa19f93ac43 100644 --- a/include/linux/firmware/qcom/qcom_scm.h +++ b/include/linux/firmware/qcom/qcom_scm.h @@ -118,8 +118,8 @@ bool qcom_scm_lmh_dcvsh_available(void); #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, void *req, size_t req_size, void *rsp, - size_t rsp_size); +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); #else /* CONFIG_QCOM_QSEECOM */ @@ -128,9 +128,9 @@ static inline int qcom_scm_qseecom_app_get_id(const char *app_name, u32 *app_id) return -EINVAL; } -static inline int qcom_scm_qseecom_app_send(u32 app_id, void *req, - size_t req_size, void *rsp, - size_t rsp_size) +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) { return -EINVAL; } diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index 6aeebe0a6777..d658ae729a02 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 @@ -609,7 +613,7 @@ __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, \ + 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", \ @@ -725,18 +729,20 @@ __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/fprobe.h b/include/linux/fprobe.h index 3e03758151f4..f39869588117 100644 --- a/include/linux/fprobe.h +++ b/include/linux/fprobe.h @@ -7,6 +7,16 @@ #include <linux/ftrace.h> #include <linux/rethook.h> +struct fprobe; + +typedef int (*fprobe_entry_cb)(struct fprobe *fp, unsigned long entry_ip, + unsigned long ret_ip, struct pt_regs *regs, + void *entry_data); + +typedef void (*fprobe_exit_cb)(struct fprobe *fp, unsigned long entry_ip, + unsigned long ret_ip, struct pt_regs *regs, + void *entry_data); + /** * struct fprobe - ftrace based probe. * @ops: The ftrace_ops. @@ -34,12 +44,8 @@ struct fprobe { 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; }; /* This fprobe is soft-disabled. */ diff --git a/include/linux/fs.h b/include/linux/fs.h index a94343f567cb..0283cf366c2a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -73,6 +73,8 @@ 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; @@ -110,21 +112,26 @@ 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)(1 << 6)) + +/* FMODE_* bits 7 to 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. @@ -132,60 +139,53 @@ 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) +#define FMODE_UNSIGNED_OFFSET ((__force fmode_t)(1 << 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) +#define FMODE_NOREUSE ((__force fmode_t)(1 << 23)) -/* File supports non-exclusive O_DIRECT writes from multiple threads */ -#define FMODE_DIO_PARALLEL_WRITE ((__force fmode_t)0x1000000) +/* FMODE_* bit 24 */ /* File is embedded in backing_file object */ -#define FMODE_BACKING ((__force fmode_t)0x2000000) +#define FMODE_BACKING ((__force fmode_t)(1 << 25)) /* File was opened by fanotify and shouldn't generate fanotify events */ -#define FMODE_NONOTIFY ((__force fmode_t)0x4000000) +#define FMODE_NONOTIFY ((__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) - -/* File supports async buffered reads */ -#define FMODE_BUF_RASYNC ((__force fmode_t)0x40000000) - -/* File supports async nowait buffered writes */ -#define FMODE_BUF_WASYNC ((__force fmode_t)0x80000000) +#define FMODE_NOACCOUNT ((__force fmode_t)(1 << 29)) /* * Attribute flags. These should be or-ed together to figure out what @@ -620,8 +620,6 @@ is_uncached_acl(struct posix_acl *acl) #define IOP_XATTR 0x0008 #define IOP_DEFAULT_READLINK 0x0010 -struct fsnotify_mark_connector; - /* * Keep mostly read-only and often accessed (especially for * the RCU path lookup and 'stat' data) fields at the beginning @@ -1033,12 +1031,13 @@ 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); + long prior = atomic_long_fetch_inc_relaxed(&f->f_count); + WARN_ONCE(!prior, "struct file::f_count incremented from zero; use-after-free condition present!\n"); return f; } @@ -1175,7 +1174,7 @@ 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 */ @@ -1249,7 +1248,7 @@ 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 */ @@ -1261,7 +1260,7 @@ struct super_block { time64_t s_time_max; #ifdef CONFIG_FSNOTIFY __u32 s_fsnotify_mask; - struct fsnotify_mark_connector __rcu *s_fsnotify_marks; + struct fsnotify_sb_info *s_fsnotify_info; #endif /* @@ -1302,12 +1301,6 @@ 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; @@ -2001,8 +1994,11 @@ 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 *); @@ -2015,7 +2011,6 @@ 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 *); @@ -2046,6 +2041,17 @@ 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)) + /* Wrap a directory iterator that needs exclusive inode access */ int wrap_directory_iterator(struct file *, struct dir_context *, int (*) (struct file *, struct dir_context *)); @@ -2105,6 +2111,7 @@ 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, @@ -2239,7 +2246,13 @@ 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) @@ -3071,11 +3084,7 @@ 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) @@ -3326,6 +3335,8 @@ 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, diff --git a/include/linux/fs_parser.h b/include/linux/fs_parser.h index 01542c4b87a2..d3350979115f 100644 --- a/include/linux/fs_parser.h +++ b/include/linux/fs_parser.h @@ -132,4 +132,8 @@ static inline bool fs_validate_description(const char *name, #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) +/* 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.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/fsnotify.h b/include/linux/fsnotify.h index 1a9de119a0f7..4da80e92f804 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); } /* @@ -103,6 +116,12 @@ static inline int fsnotify_file(struct file *file, __u32 mask) return 0; path = &file->f_path; + /* Permission events require group prio >= FSNOTIFY_PRIO_CONTENT */ + if (mask & ALL_FSNOTIFY_PERM_EVENTS && + !fsnotify_sb_has_priority_watchers(path->dentry->d_sb, + FSNOTIFY_PRIO_CONTENT)) + return 0; + return fsnotify_parent(path->dentry, mask, path, FSNOTIFY_EVENT_PATH); } diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 8f40c349b228..4dd6143db271 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -177,6 +177,17 @@ 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 @@ -201,14 +212,7 @@ 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 */ @@ -457,13 +461,6 @@ 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 +468,14 @@ 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 +483,37 @@ 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 +576,7 @@ 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) @@ -758,30 +789,35 @@ 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 */ @@ -845,6 +881,9 @@ 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..e3a83ebd1b33 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -83,7 +83,6 @@ 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) @@ -414,7 +413,6 @@ 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 +424,6 @@ 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; 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..450c2cbcf04b 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; @@ -175,42 +177,46 @@ 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_array_mempolicy_noprof(gfp_t gfp, unsigned long nr_pages, struct page **page_array); +#define alloc_pages_bulk_array_mempolicy(...) \ + alloc_hooks(alloc_pages_bulk_array_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_list(_gfp, _nr_pages, _list) \ + __alloc_pages_bulk(_gfp, numa_mem_id(), NULL, _nr_pages, _list, NULL) -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); -} +#define alloc_pages_bulk_array(_gfp, _nr_pages, _page_array) \ + __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_array_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, NULL, page_array); } +#define alloc_pages_bulk_array_node(...) \ + alloc_hooks(alloc_pages_bulk_array_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); @@ -230,82 +236,104 @@ 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 page *alloc_pages_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, +struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order); +struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order, struct vm_area_struct *vma, unsigned long addr, bool hugepage); #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, +static inline struct page *alloc_pages_mpol_noprof(gfp_t gfp, unsigned int order, struct mempolicy *mpol, pgoff_t ilx, int nid) { - return alloc_pages(gfp, order); + return alloc_pages_noprof(gfp, order); } -static inline struct folio *folio_alloc(gfp_t gfp, unsigned int order) +static inline struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order) { return __folio_alloc_node(gfp, order, numa_node_id()); } -#define vma_alloc_folio(gfp, order, vma, addr, hugepage) \ - folio_alloc(gfp, order) +#define vma_alloc_folio_noprof(gfp, order, vma, addr, hugepage) \ + folio_alloc_noprof(gfp, order) #endif + +#define alloc_pages(...) alloc_hooks(alloc_pages_noprof(__VA_ARGS__)) +#define alloc_pages_mpol(...) alloc_hooks(alloc_pages_mpol_noprof(__VA_ARGS__)) +#define folio_alloc(...) alloc_hooks(folio_alloc_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, false); return &folio->page; } +#define alloc_page_vma(...) alloc_hooks(alloc_page_vma_noprof(__VA_ARGS__)) + +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__)) -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_zeroed_page_noprof(gfp_t gfp_mask); +#define get_zeroed_page(...) alloc_hooks(get_zeroed_page_noprof(__VA_ARGS__)) + +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__)) -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) +__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__)) + +#define __get_free_page(gfp_mask) \ + __get_free_pages((gfp_mask), 0) -#define __get_dma_pages(gfp_mask, order) \ - __get_free_pages((gfp_mask) | GFP_DMA, (order)) +#define __get_dma_pages(gfp_mask, order) \ + __get_free_pages((gfp_mask) | GFP_DMA, (order)) extern void __free_pages(struct page *page, unsigned int order); extern void free_pages(unsigned long addr, unsigned int order); @@ -374,10 +402,14 @@ 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); diff --git a/include/linux/gfp_types.h b/include/linux/gfp_types.h index 868c8fb1bbc1..313be4ad79fd 100644 --- a/include/linux/gfp_types.h +++ b/include/linux/gfp_types.h @@ -2,6 +2,8 @@ #ifndef __LINUX_GFP_TYPES_H #define __LINUX_GFP_TYPES_H +#include <linux/bits.h> + /* The typedef is in types.h but we want the documentation here */ #if 0 /** @@ -53,6 +55,9 @@ enum { #ifdef CONFIG_LOCKDEP ___GFP_NOLOCKDEP_BIT, #endif +#ifdef CONFIG_SLAB_OBJ_EXT + ___GFP_NO_OBJ_EXT_BIT, +#endif ___GFP_LAST_BIT }; @@ -93,6 +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) @@ -133,12 +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 diff --git a/include/linux/gpio.h b/include/linux/gpio.h index 7ecc25c543ce..56ac7e7a2889 100644 --- a/include/linux/gpio.h +++ b/include/linux/gpio.h @@ -74,6 +74,12 @@ 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. @@ -114,8 +120,6 @@ 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 */ @@ -146,11 +150,6 @@ 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 +158,6 @@ 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..0032bb6e7d8f 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 diff --git a/include/linux/gpio/property.h b/include/linux/gpio/property.h index 6c75c8bd44a0..0d2209308002 100644 --- a/include/linux/gpio/property.h +++ b/include/linux/gpio/property.h @@ -2,10 +2,13 @@ #ifndef __LINUX_GPIO_PROPERTY_H #define __LINUX_GPIO_PROPERTY_H -#include <dt-bindings/gpio/gpio.h> /* for GPIO_* flags */ #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/hid.h b/include/linux/hid.h index b12cb1c8e682..8e06d89698e6 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -474,9 +474,9 @@ 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 */ }; diff --git a/include/linux/hid_bpf.h b/include/linux/hid_bpf.h index 7118ac28d468..eec2592dec12 100644 --- a/include/linux/hid_bpf.h +++ b/include/linux/hid_bpf.h @@ -103,6 +103,9 @@ struct hid_bpf_ops { unsigned char reportnum, __u8 *buf, size_t len, enum hid_report_type rtype, enum hid_class_request reqtype); + int (*hid_hw_output_report)(struct hid_device *hdev, __u8 *buf, size_t len); + int (*hid_input_report)(struct hid_device *hid, enum hid_report_type type, + u8 *data, u32 size, int interrupt); struct module *owner; const struct bus_type *bus_type; }; @@ -149,10 +152,8 @@ 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); -} +#define call_hid_bpf_rdesc_fixup(_hdev, _rdesc, _size) \ + ((u8 *)kmemdup(_rdesc, *(_size), GFP_KERNEL)) #endif /* CONFIG_HID_BPF */ diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index de0c89105076..c8d3ec116e29 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -64,9 +64,6 @@ ssize_t single_hugepage_flag_show(struct kobject *kobj, 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) - /* * Mask of all large folio orders supported for anonymous THP; all orders up to * and including PMD_ORDER, except order-0 (which is not "huge") and order-1 @@ -84,17 +81,32 @@ extern struct kobj_attribute shmem_enabled_attr; */ #define THP_ORDERS_ALL (THP_ORDERS_ALL_ANON | THP_ORDERS_ALL_FILE) -#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))) + +#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) + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE extern unsigned long transparent_hugepage_flags; extern unsigned long huge_anon_orders_always; @@ -210,17 +222,15 @@ static inline bool file_thp_enabled(struct vm_area_struct *vma) } 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 +243,12 @@ 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) @@ -252,8 +262,30 @@ 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); +} + +enum mthp_stat_item { + MTHP_STAT_ANON_FAULT_ALLOC, + MTHP_STAT_ANON_FAULT_FALLBACK, + MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE, + MTHP_STAT_ANON_SWPOUT, + MTHP_STAT_ANON_SWPOUT_FALLBACK, + __MTHP_STAT_COUNT +}; + +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 count_mthp_stat(int order, enum mthp_stat_item item) +{ + if (order <= 0 || order > PMD_ORDER) + return; + + this_cpu_inc(mthp_stats.stats[order][item]); } #define transparent_hugepage_use_zero_page() \ @@ -262,8 +294,10 @@ unsigned long thp_vma_allowable_orders(struct vm_area_struct *vma, 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); int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, unsigned int new_order); @@ -344,17 +378,15 @@ 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) @@ -367,8 +399,8 @@ 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)) @@ -378,13 +410,6 @@ static inline bool thp_migration_supported(void) } #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; }) - -#define HPAGE_PUD_SHIFT ({ BUILD_BUG(); 0; }) -#define HPAGE_PUD_MASK ({ BUILD_BUG(); 0; }) -#define HPAGE_PUD_SIZE ({ BUILD_BUG(); 0; }) static inline bool folio_test_pmd_mappable(struct folio *folio) { @@ -404,19 +429,25 @@ 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) { @@ -483,7 +514,7 @@ 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; } @@ -498,7 +529,7 @@ 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; } @@ -509,12 +540,6 @@ 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) -{ - return NULL; -} - static inline bool thp_migration_supported(void) { return false; @@ -535,16 +560,4 @@ static inline int split_folio_to_order(struct folio *folio, int 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..2b3c3a404769 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -174,8 +174,11 @@ 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 +275,9 @@ 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 +297,8 @@ 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 +328,6 @@ 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 +391,6 @@ 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) { @@ -493,16 +475,6 @@ 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 +526,13 @@ 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) @@ -747,7 +715,8 @@ int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list); struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve); struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, - nodemask_t *nmask, gfp_t gfp_mask); + nodemask_t *nmask, gfp_t gfp_mask, + bool allow_alloc_fallback); 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 +828,9 @@ 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 +857,8 @@ 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 @@ -970,6 +939,30 @@ 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) { @@ -1065,7 +1058,8 @@ static inline struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, 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 +1144,12 @@ 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 +1175,11 @@ 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 +1220,12 @@ 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, diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 6ef0557b4bff..96ceb4095425 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -832,6 +832,7 @@ struct vmbus_gpadl { u32 gpadl_handle; u32 size; void *buffer; + bool decrypted; }; struct vmbus_channel { 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/ieee80211.h b/include/linux/ieee80211.h index 3385a2cc5b09..de2dce743ee2 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1287,6 +1287,24 @@ 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; @@ -2742,9 +2760,11 @@ 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 @@ -5166,7 +5186,7 @@ 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); @@ -5302,7 +5322,7 @@ 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; } /** 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_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_tpmi.h b/include/linux/intel_tpmi.h index a3529b962be6..1e880cb0f454 100644 --- a/include/linux/intel_tpmi.h +++ b/include/linux/intel_tpmi.h @@ -27,16 +27,22 @@ enum intel_tpmi_id { /** * 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; 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..e123d5e17b52 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -11,7 +11,6 @@ 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) @@ -45,11 +44,6 @@ 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..447fbfd32215 100644 --- a/include/linux/io_uring/cmd.h +++ b/include/linux/io_uring/cmd.h @@ -26,12 +26,25 @@ static inline const void *io_uring_sqe_cmd(const struct io_uring_sqe *sqe) #if defined(CONFIG_IO_URING) int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw, struct iov_iter *iter, void *ioucmd); + +/* + * 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, ssize_t 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); @@ -56,6 +69,17 @@ static inline void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd, } #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)) 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 e24893625085..7a6b190c7da7 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -13,7 +13,7 @@ enum { * A hint to not wake right away but delay until there are enough of * tw's queued to match the number of CQEs the task is waiting for. * - * Must not be used wirh requests generating more than one CQE. + * Must not be used with requests generating more than one CQE. * It's also ignored unless IORING_SETUP_DEFER_TASKRUN is set. */ IOU_F_TWQ_LAZY_WAKE = 1, @@ -205,6 +205,7 @@ 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; @@ -219,7 +220,7 @@ struct io_ev_fd { }; struct io_alloc_cache { - struct io_wq_work_node list; + void **entries; unsigned int nr_cached; unsigned int max_cached; size_t elem_size; @@ -294,12 +295,13 @@ struct io_ring_ctx { struct io_submit_state submit_state; - struct io_buffer_list *io_bl; struct xarray io_bl_xa; struct io_hash_table cancel_table_locked; 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 @@ -342,14 +344,8 @@ struct io_ring_ctx { 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; @@ -372,9 +368,6 @@ 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; @@ -439,8 +432,6 @@ struct io_ring_ctx { }; struct io_tw_state { - /* ->uring_lock is taken, callbacks can use io_tw_lock to lock it */ - bool locked; }; enum { @@ -481,6 +472,7 @@ enum { REQ_F_CAN_POLL_BIT, REQ_F_BL_EMPTY_BIT, REQ_F_BL_NO_RECYCLE_BIT, + REQ_F_BUFFERS_COMMIT_BIT, /* not a real bit, just to check we're not overflowing the space */ __REQ_F_LAST_BIT, @@ -559,6 +551,8 @@ enum { 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), }; typedef void (*io_req_tw_func_t)(struct io_kiocb *req, struct io_tw_state *ts); diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 2e925b5eba53..7bc8dff7cf6d 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -69,8 +69,7 @@ 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; @@ -518,6 +517,7 @@ static inline int __iommu_copy_struct_from_user_array( * 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. + * @domain_alloc_sva: Allocate an iommu_domain for Shared Virtual Addressing. * @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 @@ -558,6 +558,8 @@ struct iommu_ops { struct device *dev, u32 flags, struct iommu_domain *parent, 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_device *(*probe_device)(struct device *dev); void (*release_device)(struct device *dev); @@ -578,7 +580,8 @@ 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); + void (*remove_dev_pasid)(struct device *dev, ioasid_t pasid, + struct iommu_domain *domain); const struct iommu_domain_ops *default_domain_ops; unsigned long pgsize_bitmap; @@ -1445,9 +1448,6 @@ 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 +1458,6 @@ 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; 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/irq.h b/include/linux/irq.h index 97baa937ab5b..a217e1029c1d 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -115,7 +115,7 @@ 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. 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..faf0b800b1b0 --- /dev/null +++ b/include/linux/irqchip/riscv-imsic.h @@ -0,0 +1,87 @@ +/* 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 <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 + +#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_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 147feebd508c..3f003d5fde53 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -114,7 +114,7 @@ do { \ # define lockdep_softirq_enter() do { } while (0) # define lockdep_softirq_exit() do { } while (0) # define lockdep_hrtimer_enter(__hrtimer) false -# define lockdep_hrtimer_exit(__context) do { } while (0) +# define lockdep_hrtimer_exit(__context) do { (void)(__context); } while (0) # define lockdep_posixtimer_enter() do { } while (0) # define lockdep_posixtimer_exit() do { } while (0) # define lockdep_irq_work_enter(__work) do { } while (0) diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 971f3e826e15..ab04c1c27fae 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -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 +1588,8 @@ 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); -} +#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 +1602,8 @@ 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); -} +#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) { @@ -1696,7 +1694,7 @@ 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 +1705,7 @@ 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)); diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index f0a949b7c973..f5a2727ca4a9 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -216,6 +216,7 @@ 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 +266,8 @@ 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)) diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h index 9935f7ecbfb9..9c042c6384bb 100644 --- a/include/linux/kernel_stat.h +++ b/include/linux/kernel_stat.h @@ -79,6 +79,14 @@ 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/kfifo.h b/include/linux/kfifo.h index 0b35a41440ff..6b28d642f332 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; 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/kprobes.h b/include/linux/kprobes.h index 0ff44d6633e3..5fcbc254d186 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -378,11 +378,15 @@ 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 +499,9 @@ 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/ksm.h b/include/linux/ksm.h index 401348e9f92b..52c63a9c5a9c 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -45,16 +45,16 @@ static inline void ksm_might_unmap_zero_page(struct mm_struct *mm, pte_t pte) static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) { - int ret; + if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags)) + return __ksm_enter(mm); - if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags)) { - ret = __ksm_enter(mm); - if (ret) - return ret; - } + return 0; +} - 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 +81,9 @@ 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(struct folio *folio, struct page *page, + struct list_head *to_kill, int force_early); long ksm_process_profit(struct mm_struct *); -#endif /* CONFIG_PROC_FS */ #else /* !CONFIG_KSM */ @@ -107,6 +101,11 @@ static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) return 0; } +static inline int ksm_execve(struct mm_struct *mm) +{ + return 0; +} + static inline void ksm_exit(struct mm_struct *mm) { } @@ -115,12 +114,10 @@ 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, +static inline void collect_procs_ksm(struct folio *folio, 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/kvm_host.h b/include/linux/kvm_host.h index 48f31dcd318a..692c01e41a18 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -193,8 +193,6 @@ 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 @@ -259,7 +257,6 @@ 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; }; @@ -273,7 +270,6 @@ struct kvm_gfn_range { 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 { 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/libata.h b/include/linux/libata.h index 324d792e7c78..13fb41d25da6 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1152,12 +1152,19 @@ extern int ata_std_bios_param(struct scsi_device *sdev, 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); +int ata_scsi_device_configure(struct scsi_device *sdev, + struct queue_limits *lim); extern void ata_scsi_slave_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); @@ -1244,7 +1251,8 @@ extern struct ata_port *ata_sas_port_alloc(struct ata_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 *); +int ata_sas_device_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); @@ -1410,13 +1418,13 @@ extern const struct attribute_group *ata_common_sdev_groups[]; __ATA_BASE_SHT(drv_name), \ .can_queue = ATA_DEF_QUEUE, \ .tag_alloc_policy = BLK_TAG_ALLOC_RR, \ - .slave_configure = ata_scsi_slave_config + .device_configure = ata_scsi_device_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 + .device_configure = ata_scsi_device_configure #define ATA_BASE_SHT(drv_name) \ ATA_SUBBASE_SHT(drv_name), \ diff --git a/include/linux/linkmode.h b/include/linux/linkmode.h index 287f590ed56b..d94bfd9ac8cc 100644 --- a/include/linux/linkmode.h +++ b/include/linux/linkmode.h @@ -43,29 +43,10 @@ static inline int linkmode_andnot(unsigned long *dst, const unsigned long *src1, 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/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/lockdep.h b/include/linux/lockdep.h index 08b0d1d9d78b..5e51b0de4c4b 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -297,6 +297,9 @@ extern void lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie); .wait_type_inner = _wait_type, \ .lock_type = LD_LOCK_WAIT_OVERRIDE, } +#define lock_map_assert_held(l) \ + lockdep_assert(lock_is_held(l) != LOCK_STATE_NOT_HELD) + #else /* !CONFIG_LOCKDEP */ static inline void lockdep_init_task(struct task_struct *task) @@ -388,6 +391,8 @@ extern int lockdep_is_held(const void *); #define DEFINE_WAIT_OVERRIDE_MAP(_name, _wait_type) \ struct lockdep_map __maybe_unused _name = {} +#define lock_map_assert_held(l) do { (void)(l); } while (0) + #endif /* !LOCKDEP */ #ifdef CONFIG_PROVE_LOCKING diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 334e00efbde4..f804b76cde44 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -176,7 +176,8 @@ 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(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, kernfs_init_security, struct kernfs_node *kn_dir, struct kernfs_node *kn) LSM_HOOK(int, 0, file_permission, struct file *file, int mask) 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/math64.h b/include/linux/math64.h index bf74478926d4..d34def7f9a8c 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 */ diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 394fd0a887ae..030d34e9d117 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -83,6 +83,8 @@ enum mem_cgroup_events_target { struct memcg_vmstats_percpu; struct memcg_vmstats; +struct lruvec_stats_percpu; +struct lruvec_stats; struct mem_cgroup_reclaim_iter { struct mem_cgroup *position; @@ -90,25 +92,6 @@ struct mem_cgroup_reclaim_iter { 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]; -}; - /* * per-node information in memory controller. */ @@ -116,7 +99,7 @@ struct mem_cgroup_per_node { struct lruvec lruvec; struct lruvec_stats_percpu __percpu *lruvec_stats_percpu; - struct lruvec_stats lruvec_stats; + struct lruvec_stats *lruvec_stats; unsigned long lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS]; @@ -349,15 +332,32 @@ 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); @@ -388,10 +388,10 @@ 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 +409,10 @@ 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); } /* @@ -469,11 +469,11 @@ static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio) 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); } /* @@ -506,17 +506,17 @@ 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) @@ -552,7 +552,7 @@ 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; } @@ -818,7 +818,8 @@ 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) @@ -973,7 +974,8 @@ 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); +void __mod_memcg_state(struct mem_cgroup *memcg, enum memcg_stat_item 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) @@ -994,7 +996,7 @@ static inline void mem_cgroup_unlock_pages(void) /* 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 +1006,7 @@ 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; @@ -1019,48 +1021,13 @@ static inline void mod_memcg_page_state(struct page *page, } 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 +1040,6 @@ 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); @@ -1535,19 +1492,19 @@ 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 +1533,6 @@ 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) { @@ -1632,6 +1584,19 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, } #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_KMEM + 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); diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h index 69e781900082..0d70788558f4 100644 --- a/include/linux/memory-tiers.h +++ b/include/linux/memory-tiers.h @@ -48,6 +48,9 @@ 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); @@ -136,5 +139,15 @@ 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/mempolicy.h b/include/linux/mempolicy.h index 931b118336f4..1add16f21612 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -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/mfd/axp20x.h b/include/linux/mfd/axp20x.h index f1755163dd9f..8c0a33a2e9ce 100644 --- a/include/linux/mfd/axp20x.h +++ b/include/linux/mfd/axp20x.h @@ -19,6 +19,7 @@ enum axp20x_variants { AXP223_ID, AXP288_ID, AXP313A_ID, + AXP717_ID, AXP803_ID, AXP806_ID, AXP809_ID, @@ -104,15 +105,47 @@ 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 AXP717_ON_INDICATE 0x00 +#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_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 AXP806_STARTUP_SRC 0x00 #define AXP806_CHIP_ID 0x03 #define AXP806_PWR_OUT_CTRL1 0x10 @@ -434,6 +467,27 @@ 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_REG_ID_MAX, +}; + +enum { AXP806_DCDCA = 0, AXP806_DCDCB, AXP806_DCDCC, @@ -732,6 +786,40 @@ 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, diff --git a/include/linux/mhi.h b/include/linux/mhi.h index 77b8c0a26674..cde01e133a1b 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -630,13 +630,29 @@ 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 */ 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..d7bb31d9a446 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 { \ @@ -1336,6 +1336,9 @@ 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) @@ -1359,6 +1362,9 @@ 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) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index bf9324a31ae9..779cfdf2e9d6 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -85,7 +85,7 @@ enum mlx5_sqp_t { }; enum { - MLX5_MAX_PORTS = 4, + MLX5_MAX_PORTS = 8, }; enum { @@ -862,6 +862,7 @@ 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; @@ -1374,11 +1375,4 @@ static inline bool mlx5_is_macsec_roce_supported(struct mlx5_core_dev *mdev) 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); - #endif /* MLX5_DRIVER_H */ diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index c940b329a475..f468763478ae 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -416,7 +416,10 @@ 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]; @@ -525,6 +528,12 @@ union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits { 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 +559,8 @@ 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]; @@ -846,7 +856,11 @@ 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 +890,9 @@ 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 { @@ -1469,7 +1485,9 @@ enum { }; struct mlx5_ifc_cmd_hca_cap_bits { - u8 reserved_at_0[0x10]; + u8 reserved_at_0[0x6]; + u8 page_request_disable[0x1]; + u8 reserved_at_7[0x9]; u8 shared_object_to_user_object_allowed[0x1]; u8 reserved_at_13[0xe]; u8 vhca_resource_manager[0x1]; @@ -1668,7 +1686,8 @@ 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]; @@ -2004,7 +2023,13 @@ struct mlx5_ifc_cmd_hca_cap_2_bits { u8 reserved_at_3a0[0x10]; 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[0x400]; }; enum mlx5_ifc_flow_destination_type { @@ -4361,10 +4386,10 @@ 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 { @@ -9793,7 +9818,21 @@ 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[0x20]; }; struct mlx5_ifc_ppcnt_reg_bits { @@ -10165,7 +10204,9 @@ struct mlx5_ifc_mtutc_reg_bits { }; struct mlx5_ifc_pcam_enhanced_features_bits { - u8 reserved_at_0[0x68]; + u8 reserved_at_0[0x48]; + 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]; diff --git a/include/linux/mm.h b/include/linux/mm.h index 0436b919f1c7..9849dfda44d4 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> @@ -1199,7 +1200,7 @@ static inline int is_vmalloc_or_module_addr(const void *x) * debugging purposes - it does not include PTE-mapped sub-pages; look * at folio_mapcount() or page_mapcount() instead. */ -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; @@ -1223,48 +1224,60 @@ static inline void page_mapcount_reset(struct page *page) * a large folio, it includes the number of times this page is mapped * as part of that folio. * - * The result is undefined for pages which cannot be mapped into userspace. - * For example SLAB or special types of pages. See function page_has_type(). - * They use this field in struct page differently. + * 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 < PAGE_MAPCOUNT_RESERVE + 1) + mapcount = 0; if (unlikely(PageCompound(page))) mapcount += folio_entire_mapcount(page_folio(page)); return mapcount; } -int folio_total_mapcount(struct folio *folio); +static inline int folio_large_mapcount(const struct folio *folio) +{ + VM_WARN_ON_FOLIO(!folio_test_large(folio), folio); + return atomic_read(&folio->_large_mapcount) + 1; +} /** - * folio_mapcount() - Calculate the number of mappings of this folio. + * folio_mapcount() - Number of mappings of this folio. * @folio: The folio. * - * 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. + * 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. + * + * For ordindary folios, each user page table entry (PTE/PMD/PUD/...) counts + * exactly once. + * + * 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; + /* Handle page_has_type() pages */ + if (mapcount < PAGE_MAPCOUNT_RESERVE + 1) + mapcount = 0; + return mapcount; + } + return folio_large_mapcount(folio); } /** @@ -1273,11 +1286,9 @@ 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; } /* @@ -1285,11 +1296,9 @@ 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) @@ -1315,8 +1324,6 @@ void folio_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) { @@ -1434,27 +1441,22 @@ 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) @@ -1573,7 +1575,7 @@ 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); } @@ -2067,7 +2069,7 @@ 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; @@ -2162,21 +2164,64 @@ static inline size_t folio_size(struct folio *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"). + * + * 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. + * + * For small anonymous folios (except KSM folios) and anonymous hugetlb folios, + * the return value will be exactly correct, because they can only be mapped + * at most once into an MM, and they cannot be partially mapped. + * + * 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. + * #. For (small) KSM folios, the return value can wrongly indicate "mapped + * shared" (false positive), when the folio is mapped multiple times into + * the same MM. + * + * Further, this function only considers current page table mappings that + * are tracked using the folio mapcount(s). * - * Return: The estimated number of processes sharing a folio. + * 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); + + /* 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; } #ifndef HAVE_ARCH_MAKE_PAGE_ACCESSIBLE @@ -2207,11 +2252,6 @@ static inline int arch_make_folio_accessible(struct folio *folio) */ #include <linux/vmstat.h> -static __always_inline void *lowmem_page_address(const struct page *page) -{ - return page_to_virt(page); -} - #if defined(CONFIG_HIGHMEM) && !defined(WANT_PAGE_VIRTUAL) #define HASHED_PAGE_VIRTUAL #endif @@ -2234,6 +2274,11 @@ void set_page_address(struct page *page, void *virtual); void page_address_init(void); #endif +static __always_inline void *lowmem_page_address(const struct page *page) +{ + return page_to_virt(page); +} + #if !defined(HASHED_PAGE_VIRTUAL) && !defined(WANT_PAGE_VIRTUAL) #define page_address(page) lowmem_page_address(page) #define set_page_address(page, address) do { } while(0) @@ -2391,12 +2436,8 @@ 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, +int follow_pte(struct vm_area_struct *vma, 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); @@ -2550,7 +2591,7 @@ extern unsigned long move_page_tables(struct vm_area_struct *vma, 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); +bool 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) { /* @@ -2857,12 +2898,13 @@ 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 @@ -3132,6 +3174,14 @@ extern void reserve_bootmem_region(phys_addr_t start, /* Free the reserved page into the buddy system, so it gets managed. */ static inline void free_reserved_page(struct page *page) { + if (mem_alloc_profiling_enabled()) { + union codetag_ref *ref = get_page_tag_ref(page); + + if (ref) { + set_codetag_empty(ref); + put_page_tag_ref(ref); + } + } ClearPageReserved(page); init_page_count(page); __free_page(page); @@ -3193,8 +3243,6 @@ 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, @@ -3210,7 +3258,6 @@ 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); @@ -3222,9 +3269,6 @@ 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, ...); @@ -3383,7 +3427,16 @@ extern int install_special_mapping(struct mm_struct *mm, 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, @@ -3429,6 +3482,7 @@ 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); @@ -3722,7 +3776,14 @@ DECLARE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_FREE_DEFAULT_ON, init_on_free); static inline bool want_init_on_free(void) { return static_branch_maybe(CONFIG_INIT_ON_FREE_DEFAULT_ON, - &init_on_free); + &init_on_free); +} + +DECLARE_STATIC_KEY_MAYBE(CONFIG_INIT_MLOCKED_ON_FREE_DEFAULT_ON, init_mlocked_on_free); +static inline bool want_init_mlocked_on_free(void) +{ + return static_branch_maybe(CONFIG_INIT_MLOCKED_ON_FREE_DEFAULT_ON, + &init_mlocked_on_free); } extern bool _debug_pagealloc_enabled_early; @@ -3785,24 +3846,22 @@ 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 */ @@ -3812,9 +3871,9 @@ 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 @@ -3969,7 +4028,6 @@ 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 @@ -4202,4 +4260,7 @@ static inline bool pfn_is_unaccepted_memory(unsigned long pfn) return range_contains_unaccepted_memory(paddr, paddr + PAGE_SIZE); } +void vma_pgtable_walk_begin(struct vm_area_struct *vma); +void vma_pgtable_walk_end(struct vm_area_struct *vma); + #endif /* _LINUX_MM_H */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 5240bd7bca33..24323c7d0bd4 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -169,7 +169,7 @@ struct page { /* Usage count. *DO NOT USE DIRECTLY*. See page_ref.h */ atomic_t _refcount; -#ifdef CONFIG_MEMCG +#ifdef CONFIG_SLAB_OBJ_EXT unsigned long memcg_data; #endif @@ -289,7 +289,8 @@ 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. @@ -331,7 +332,7 @@ struct folio { }; atomic_t _mapcount; atomic_t _refcount; -#ifdef CONFIG_MEMCG +#ifdef CONFIG_SLAB_OBJ_EXT unsigned long memcg_data; #endif #if defined(WANT_PAGE_VIRTUAL) @@ -348,8 +349,8 @@ 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; @@ -671,6 +672,9 @@ struct vm_area_struct { }; #ifdef CONFIG_PER_VMA_LOCK + /* Flag to indicate areas detached from the mm->mm_mt tree */ + bool detached; + /* * Can only be written (using WRITE_ONCE()) while holding both: * - mmap_lock (in write mode) @@ -687,9 +691,6 @@ struct vm_area_struct { */ int vm_lock_seq; struct vma_lock *vm_lock; - - /* Flag to indicate areas detached from the mm->mm_mt tree */ - bool detached; #endif /* @@ -777,11 +778,7 @@ 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 @@ -1170,14 +1167,15 @@ static inline void mm_init_cid(struct mm_struct *mm) 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) { - 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); return 0; } +#define mm_alloc_cid(...) alloc_hooks(mm_alloc_cid_noprof(__VA_ARGS__)) static inline void mm_destroy_cid(struct mm_struct *mm) { @@ -1370,6 +1368,15 @@ 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: diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index 8d38dcb6d044..de9dc20b01ba 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -60,16 +60,14 @@ 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 diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 5894bf912f7b..88c6a76042ee 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -433,8 +433,8 @@ struct mmc_host { 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 */ 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/mmu_notifier.h b/include/linux/mmu_notifier.h index f349e08a9dfe..d39ebb10caeb 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 { @@ -650,11 +612,6 @@ 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) -{ -} - static inline void mmu_notifier_invalidate_range_start(struct mmu_notifier_range *range) { @@ -693,7 +650,6 @@ 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..8f9c9590a42c 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 diff --git a/include/linux/module.h b/include/linux/module.h index 1153b0d99a80..ffa1c603163c 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -605,6 +605,11 @@ 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); @@ -857,6 +862,10 @@ void *dereference_module_function_descriptor(struct module *mod, void *ptr) return ptr; } +static inline bool module_is_coming(struct module *mod) +{ + return false; +} #endif /* CONFIG_MODULES */ #ifdef CONFIG_SYSFS diff --git a/include/linux/moduleloader.h b/include/linux/moduleloader.h index 89b1e0ed9811..e395461d59e5 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). */ @@ -129,12 +122,4 @@ 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/msi.h b/include/linux/msi.h index 26d07e23052e..dc27cf3903d5 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -573,8 +573,6 @@ 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), }; /** @@ -676,6 +674,12 @@ int platform_device_msi_init_and_alloc_irqs(struct device *dev, unsigned int nve 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/namei.h b/include/linux/namei.h index 74e0cc14ebf8..967aa9ea9f96 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -44,6 +44,7 @@ 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) diff --git a/include/linux/net.h b/include/linux/net.h index 15df6d5f27a7..688320b79fcc 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); 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/netdevice.h b/include/linux/netdevice.h index cb37817d6382..d20c6c99eb88 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -59,7 +59,7 @@ 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_name_node; @@ -1327,7 +1327,7 @@ 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); @@ -1583,7 +1583,8 @@ 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); @@ -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 @@ -2338,6 +2340,8 @@ 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 @@ -2367,8 +2371,8 @@ struct net_device { struct sfp_bus *sfp_bus; struct lock_class_key *qdisc_tx_busylock; bool proto_down; + bool threaded; unsigned wol_enabled:1; - unsigned threaded:1; struct list_head net_notifier_list; @@ -3133,6 +3137,7 @@ 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, @@ -3203,6 +3208,7 @@ struct softnet_data { struct softnet_data *rps_ipi_list; #endif + unsigned int received_rps; bool in_net_rx_action; bool in_napi_threaded_poll; @@ -3235,11 +3241,11 @@ 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; @@ -3248,21 +3254,6 @@ 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); static inline int dev_recursion_level(void) @@ -3270,23 +3261,6 @@ 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) -{ - __this_cpu_inc(softnet_data.xmit.recursion); -} - -static inline void dev_xmit_recursion_dec(void) -{ - __this_cpu_dec(softnet_data.xmit.recursion); -} - void __netif_schedule(struct Qdisc *q); void netif_schedule_queue(struct netdev_queue *txq); @@ -4127,6 +4101,8 @@ 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, @@ -4545,6 +4521,9 @@ 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, diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 100cbb261269..ca56a4428043 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -20,95 +20,24 @@ #include <linux/uio.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; /** - * 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 */ @@ -135,6 +64,7 @@ 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 */ @@ -142,7 +72,8 @@ struct netfs_inode { #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_USE_PGPRIV2 31 /* [DEPRECATED] Use PG_private_2 to mark + * write to cache on read */ }; /* @@ -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 +127,33 @@ 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 */ + unsigned int submit_off; /* Folio offset we're submitting from */ + unsigned int submit_len; /* Amount of data left to submit */ + unsigned int submit_max_len; /* 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 { @@ -209,14 +176,17 @@ 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 max_len; /* Maximum size of 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 nr_segs; /* Number of segs in io_iter */ unsigned int max_nr_segs; /* 0 or max number of segments in an iterator */ 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 */ @@ -224,15 +194,20 @@ struct netfs_io_subrequest { #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_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_IN_PROGRESS 8 /* Unlocked when the subrequest completes */ +#define NETFS_SREQ_NEED_RETRY 9 /* Set if the filesystem requests a retry */ +#define NETFS_SREQ_RETRYING 10 /* Set if we're retrying */ +#define NETFS_SREQ_FAILED 11 /* 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_FOR_WRITE, /* This read is to prepare a write */ + NETFS_COPY_TO_CACHE, /* This write is to copy a read to the cache */ NETFS_WRITEBACK, /* This 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 */ @@ -254,26 +229,36 @@ struct netfs_io_request { struct netfs_cache_resources cache_resources; struct list_head proc_link; /* Link in netfs_iorequests */ struct list_head subrequests; /* Contributory I/O operations */ + 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 iov_iter iter; /* Unencrypted-side iterator */ struct iov_iter io_iter; /* I/O (Encrypted-side) iterator */ 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 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 */ 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 */ + 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 */ 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 contiguity; /* Tracking for gaps in the writeback sequence */ + unsigned long long collected_to; /* Point we've collected to */ + unsigned long long cleaned_to; /* Position we've cleaned folios to */ pgoff_t no_unlock_folio; /* Don't unlock this folio after read */ refcount_t ref; unsigned long flags; @@ -287,6 +272,11 @@ struct netfs_io_request { #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_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); }; @@ -295,8 +285,8 @@ 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); @@ -312,10 +302,13 @@ 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 +343,27 @@ 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 +389,7 @@ 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); @@ -410,7 +416,6 @@ 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); @@ -426,9 +431,7 @@ 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); @@ -472,6 +475,7 @@ static inline void netfs_inode_init(struct netfs_inode *ctx, #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; diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index ef8d2d618d5b..0d896ce296ce 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -701,6 +701,12 @@ 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/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/numa.h b/include/linux/numa.h index 915033a75731..1d43371fafd2 100644 --- a/include/linux/numa.h +++ b/include/linux/numa.h @@ -36,12 +36,7 @@ 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) 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/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-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/page-flags.h b/include/linux/page-flags.h index 652d77805e99..104078afe0b1 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -109,7 +109,6 @@ enum pageflags { PG_active, PG_workingset, PG_error, - PG_slab, PG_owner_priv_1, /* Owner use. If pagecache, fs may use*/ PG_arch_1, PG_reserved, @@ -190,7 +189,6 @@ enum pageflags { /* At least one page in this folio has the hwpoison flag set */ PG_has_hwpoisoned = PG_error, - PG_hugetlb = PG_active, PG_large_rmappable = PG_workingset, /* anon or file-backed */ }; @@ -458,30 +456,51 @@ static __always_inline int TestClearPage##uname(struct page *page) \ TESTSETFLAG(uname, lname, policy) \ TESTCLEARFLAG(uname, lname, policy) +#define FOLIO_TEST_FLAG_FALSE(name) \ +static inline bool folio_test_##name(const struct folio *folio) \ +{ return false; } +#define FOLIO_SET_FLAG_NOOP(name) \ +static inline void folio_set_##name(struct folio *folio) { } +#define FOLIO_CLEAR_FLAG_NOOP(name) \ +static inline void folio_clear_##name(struct folio *folio) { } +#define __FOLIO_SET_FLAG_NOOP(name) \ +static inline void __folio_set_##name(struct folio *folio) { } +#define __FOLIO_CLEAR_FLAG_NOOP(name) \ +static inline void __folio_clear_##name(struct folio *folio) { } +#define FOLIO_TEST_SET_FLAG_FALSE(name) \ +static inline bool folio_test_set_##name(struct folio *folio) \ +{ return false; } +#define FOLIO_TEST_CLEAR_FLAG_FALSE(name) \ +static inline bool folio_test_clear_##name(struct folio *folio) \ +{ return false; } + +#define FOLIO_FLAG_FALSE(name) \ +FOLIO_TEST_FLAG_FALSE(name) \ +FOLIO_SET_FLAG_NOOP(name) \ +FOLIO_CLEAR_FLAG_NOOP(name) + #define TESTPAGEFLAG_FALSE(uname, lname) \ -static inline bool folio_test_##lname(const struct folio *folio) { return false; } \ +FOLIO_TEST_FLAG_FALSE(lname) \ static inline int Page##uname(const struct page *page) { return 0; } #define SETPAGEFLAG_NOOP(uname, lname) \ -static inline void folio_set_##lname(struct folio *folio) { } \ +FOLIO_SET_FLAG_NOOP(lname) \ static inline void SetPage##uname(struct page *page) { } #define CLEARPAGEFLAG_NOOP(uname, lname) \ -static inline void folio_clear_##lname(struct folio *folio) { } \ +FOLIO_CLEAR_FLAG_NOOP(lname) \ static inline void ClearPage##uname(struct page *page) { } #define __CLEARPAGEFLAG_NOOP(uname, lname) \ -static inline void __folio_clear_##lname(struct folio *folio) { } \ +__FOLIO_CLEAR_FLAG_NOOP(lname) \ static inline void __ClearPage##uname(struct page *page) { } #define TESTSETFLAG_FALSE(uname, lname) \ -static inline bool folio_test_set_##lname(struct folio *folio) \ -{ return 0; } \ +FOLIO_TEST_SET_FLAG_FALSE(lname) \ static inline int TestSetPage##uname(struct page *page) { return 0; } #define TESTCLEARFLAG_FALSE(uname, lname) \ -static inline bool folio_test_clear_##lname(struct folio *folio) \ -{ return 0; } \ +FOLIO_TEST_CLEAR_FLAG_FALSE(lname) \ static inline int TestClearPage##uname(struct page *page) { return 0; } #define PAGEFLAG_FALSE(uname, lname) TESTPAGEFLAG_FALSE(uname, lname) \ @@ -493,9 +512,9 @@ 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) @@ -504,7 +523,6 @@ PAGEFLAG(Active, active, PF_HEAD) __CLEARPAGEFLAG(Active, active, PF_HEAD) TESTCLEARFLAG(Active, active, PF_HEAD) 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 */ @@ -608,12 +626,19 @@ 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 @@ -668,7 +693,7 @@ 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; } @@ -689,7 +714,7 @@ 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; @@ -716,7 +741,7 @@ static __always_inline bool PageKsm(const struct page *page) TESTPAGEFLAG_FALSE(Ksm, 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. @@ -764,7 +789,7 @@ 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)); } @@ -848,36 +873,13 @@ 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) #else -TESTPAGEFLAG_FALSE(LargeRmappable, large_rmappable) +FOLIO_FLAG_FALSE(large_rmappable) #endif #define PG_head_mask ((1UL << PG_head)) -#ifdef CONFIG_HUGETLB_PAGE -int PageHuge(const struct page *page); -SETPAGEFLAG(HugeTLB, hugetlb, PF_SECOND) -CLEARPAGEFLAG(HugeTLB, hugetlb, PF_SECOND) - -/** - * folio_test_hugetlb - Determine if the folio belongs to hugetlbfs - * @folio: The folio to test. - * - * Context: Any context. Caller should have a reference on the folio to - * prevent it from being turned into a tail page. - * Return: True for hugetlbfs folios, false for anon folios or folios - * belonging to other filesystems. - */ -static inline bool folio_test_hugetlb(const struct folio *folio) -{ - return folio_test_large(folio) && - test_bit(PG_hugetlb, const_folio_flags(folio, 1)); -} -#else -TESTPAGEFLAG_FALSE(Huge, hugetlb) -#endif - #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * PageHuge() only returns true for hugetlbfs pages, but not for @@ -934,33 +936,23 @@ PAGEFLAG_FALSE(HasHWPoisoned, has_hwpoisoned) #endif /* - * Check if a page is currently marked HWPoisoned. Note that this check is - * best effort only and inherently racy: there is no way to synchronize with - * failing hardware. - */ -static inline bool is_page_hwpoison(struct page *page) -{ - if (PageHWPoison(page)) - return true; - return PageHuge(page) && PageHWPoison(compound_head(page)); -} - -/* - * For pages that are never mapped to userspace (and aren't PageSlab), + * For pages that are never mapped to userspace, * 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 page_mapcount() won't be + * low bits so that an underflow or overflow of _mapcount won't be * mistaken for a page type value. */ #define PAGE_TYPE_BASE 0xf0000000 -/* Reserve 0x0000007f to catch underflows of page_mapcount */ +/* 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 +#define PG_slab 0x00001000 #define PageType(page, flag) \ ((page->page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE) @@ -977,35 +969,38 @@ static inline int page_has_type(const struct page *page) return page_type_has_type(page->page_type); } +#define FOLIO_TYPE_OPS(lname, fname) \ +static __always_inline bool folio_test_##fname(const struct folio *folio)\ +{ \ + return folio_test_type(folio, PG_##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; \ +} \ +static __always_inline void __folio_clear_##fname(struct folio *folio) \ +{ \ + VM_BUG_ON_FOLIO(!folio_test_##fname(folio), folio); \ + folio->page.page_type |= PG_##lname; \ +} + #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); \ } \ -static __always_inline int folio_test_##fname(const struct folio *folio)\ -{ \ - return folio_test_type(folio, PG_##lname); \ -} \ static __always_inline void __SetPage##uname(struct page *page) \ { \ VM_BUG_ON_PAGE(!PageType(page, 0), page); \ page->page_type &= ~PG_##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; \ -} \ static __always_inline void __ClearPage##uname(struct page *page) \ { \ VM_BUG_ON_PAGE(!Page##uname(page), page); \ page->page_type |= PG_##lname; \ -} \ -static __always_inline void __folio_clear_##fname(struct folio *folio) \ -{ \ - VM_BUG_ON_FOLIO(!folio_test_##fname(folio), folio); \ - folio->page.page_type |= PG_##lname; \ -} \ +} /* * PageBuddy() indicates that the page is free and in the buddy system @@ -1052,14 +1047,67 @@ PAGE_TYPE_OPS(Table, table, pgtable) */ PAGE_TYPE_OPS(Guard, guard, guard) -extern bool is_free_buddy_page(struct page *page); +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 + +/** + * PageHuge - Determine if the page belongs to hugetlbfs + * @page: The page to test. + * + * Context: Any context. + * Return: True for hugetlbfs pages, false for anon pages or pages + * belonging to other filesystems. + */ +static inline bool PageHuge(const struct page *page) +{ + return folio_test_hugetlb(page_folio(page)); +} + +/* + * Check if a page is currently marked HWPoisoned. Note that this check is + * best effort only and inherently racy: there is no way to synchronize with + * failing hardware. + */ +static inline bool is_page_hwpoison(const struct page *page) +{ + const struct folio *folio; + + if (PageHWPoison(page)) + return true; + folio = page_folio(page); + return folio_test_hugetlb(folio) && PageHWPoison(&folio->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); } @@ -1098,7 +1146,7 @@ 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) /* @@ -1118,7 +1166,7 @@ static __always_inline void __ClearPageAnonExclusive(struct page *page) */ #define PAGE_FLAGS_SECOND \ (0xffUL /* order */ | 1UL << PG_has_hwpoisoned | \ - 1UL << PG_hugetlb | 1UL << PG_large_rmappable) + 1UL << PG_large_rmappable) #define PAGE_FLAGS_PRIVATE \ (1UL << PG_private | 1UL << PG_private_2) diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h index 4ac34392823a..c16db0067090 100644 --- a/include/linux/page-isolation.h +++ b/include/linux/page-isolation.h @@ -34,8 +34,9 @@ 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); 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_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..1acf5bac7f50 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); diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h index 3f2409b968ec..547e82cdc89a 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 @@ -45,7 +45,11 @@ extern unsigned int pageblock_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..3d69589c00a4 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -40,6 +40,8 @@ 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) { @@ -542,24 +544,22 @@ static inline void *detach_page_private(struct page *page) #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; @@ -1014,7 +1014,7 @@ 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 +1144,6 @@ 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 +1155,6 @@ 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 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/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/pci-epc.h b/include/linux/pci-epc.h index cc2f70d061c8..acc5f96161fe 100644 --- a/include/linux/pci-epc.h +++ b/include/linux/pci-epc.h @@ -128,6 +128,8 @@ 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 + * @init_complete: flag to indicate whether the EPC initialization is complete + * or not */ struct pci_epc { struct device dev; @@ -143,6 +145,7 @@ struct pci_epc { /* mutex to protect against concurrent access of EP controller */ struct mutex lock; unsigned long function_num_map; + bool init_complete; }; /** @@ -179,8 +182,6 @@ 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 +189,6 @@ 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]; @@ -225,6 +225,7 @@ 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_notify_pending_init(struct pci_epc *epc, struct pci_epf *epf); void pci_epc_bme_notify(struct pci_epc *epc); void pci_epc_remove_epf(struct pci_epc *epc, struct pci_epf *epf, enum pci_epc_interface_type type); diff --git a/include/linux/pci.h b/include/linux/pci.h index 16493426a04f..fb004fd4e889 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 @@ -413,6 +413,8 @@ struct pci_dev { struct resource driver_exclusive_resource; /* driver exclusive resource ranges */ bool match_driver; /* Skip attaching driver */ + struct lock_class_key cfg_access_key; + struct lockdep_map cfg_access_lock; unsigned int transparent:1; /* Subtractive decode bridge */ unsigned int io_window:1; /* Bridge has I/O window */ @@ -1077,8 +1079,6 @@ 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 @@ -1315,7 +1315,6 @@ 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); @@ -1648,8 +1647,7 @@ 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 +1656,6 @@ 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 +1688,6 @@ 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 +1710,7 @@ 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 +1751,6 @@ 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 /** @@ -1821,17 +1793,21 @@ extern bool pcie_ports_native; #define pcie_ports_native false #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); @@ -2014,10 +1990,9 @@ 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) @@ -2519,7 +2494,12 @@ 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); diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index a0c75e467df3..942a587bb97e 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -580,6 +580,7 @@ #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_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 @@ -2607,6 +2608,8 @@ #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 @@ -2686,8 +2689,10 @@ #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 +3111,7 @@ #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_CML_R 0xf0c8 #define PCI_DEVICE_ID_INTEL_HDA_RKL_S 0xf1c8 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.h b/include/linux/peci.h index 9b3d36aff431..90e241458ef6 100644 --- a/include/linux/peci.h +++ b/include/linux/peci.h @@ -58,7 +58,6 @@ 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 - * @controller: manages the bus segment hosting this PECI device * @info: PECI device characteristics * @info.family: device family * @info.model: device model diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 8c677f185901..03053de557cf 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -2,6 +2,7 @@ #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> @@ -9,12 +10,17 @@ #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 @@ -121,7 +127,6 @@ 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 +134,16 @@ 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 void __percpu *pcpu_alloc_noprof(size_t size, size_t align, bool reserved, + gfp_t gfp) __alloc_size(1); extern size_t pcpu_alloc_size(void __percpu *__pdata); -DEFINE_FREE(free_percpu, void __percpu *, free_percpu(_T)) - -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 +151,15 @@ 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/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..a5304ae8c654 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -809,11 +809,8 @@ 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 +880,7 @@ 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 +895,11 @@ 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; @@ -1342,8 +1345,10 @@ 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 +1356,6 @@ __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, @@ -1697,6 +1686,14 @@ 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); diff --git a/include/linux/pgalloc_tag.h b/include/linux/pgalloc_tag.h new file mode 100644 index 000000000000..86ba5d33e43b --- /dev/null +++ b/include/linux/pgalloc_tag.h @@ -0,0 +1,132 @@ +/* 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; + +static inline union codetag_ref *codetag_ref_from_page_ext(struct page_ext *page_ext) +{ + return (void *)page_ext + page_alloc_tagging_ops.offset; +} + +static inline struct page_ext *page_ext_from_codetag_ref(union codetag_ref *ref) +{ + return (void *)ref - page_alloc_tagging_ops.offset; +} + +/* Should be called only if mem_alloc_profiling_enabled() */ +static inline union codetag_ref *get_page_tag_ref(struct page *page) +{ + if (page) { + struct page_ext *page_ext = page_ext_get(page); + + if (page_ext) + return codetag_ref_from_page_ext(page_ext); + } + return NULL; +} + +static inline void put_page_tag_ref(union codetag_ref *ref) +{ + page_ext_put(page_ext_from_codetag_ref(ref)); +} + +static inline void pgalloc_tag_add(struct page *page, struct task_struct *task, + unsigned int nr) +{ + if (mem_alloc_profiling_enabled()) { + union codetag_ref *ref = get_page_tag_ref(page); + + if (ref) { + alloc_tag_add(ref, task->alloc_tag, PAGE_SIZE * nr); + put_page_tag_ref(ref); + } + } +} + +static inline void pgalloc_tag_sub(struct page *page, unsigned int nr) +{ + if (mem_alloc_profiling_enabled()) { + union codetag_ref *ref = get_page_tag_ref(page); + + if (ref) { + alloc_tag_sub(ref, PAGE_SIZE * nr); + put_page_tag_ref(ref); + } + } +} + +static inline void pgalloc_tag_split(struct page *page, unsigned int nr) +{ + int i; + struct page_ext *page_ext; + union codetag_ref *ref; + struct alloc_tag *tag; + + if (!mem_alloc_profiling_enabled()) + return; + + page_ext = page_ext_get(page); + if (unlikely(!page_ext)) + return; + + ref = codetag_ref_from_page_ext(page_ext); + if (!ref->ct) + goto out; + + tag = ct_to_alloc_tag(ref->ct); + page_ext = page_ext_next(page_ext); + for (i = 1; i < nr; i++) { + /* Set new reference to point to the original tag */ + alloc_tag_ref_set(codetag_ref_from_page_ext(page_ext), tag); + page_ext = page_ext_next(page_ext); + } +out: + page_ext_put(page_ext); +} + +static inline struct alloc_tag *pgalloc_tag_get(struct page *page) +{ + struct alloc_tag *tag = NULL; + + if (mem_alloc_profiling_enabled()) { + union codetag_ref *ref = get_page_tag_ref(page); + + alloc_tag_sub_check(ref); + if (ref && ref->ct) + tag = ct_to_alloc_tag(ref->ct); + put_page_tag_ref(ref); + } + + 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); +} + +#else /* CONFIG_MEM_ALLOC_PROFILING */ + +static inline union codetag_ref *get_page_tag_ref(struct page *page) { return NULL; } +static inline void put_page_tag_ref(union codetag_ref *ref) {} +static inline void pgalloc_tag_add(struct page *page, struct task_struct *task, + unsigned int nr) {} +static inline void pgalloc_tag_sub(struct page *page, unsigned int nr) {} +static inline void pgalloc_tag_split(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) {} + +#endif /* CONFIG_MEM_ALLOC_PROFILING */ + +#endif /* _LINUX_PGALLOC_TAG_H */ diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 85fc7554cd52..18019f037bae 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] * @@ -149,9 +151,7 @@ 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 @@ -459,6 +459,50 @@ 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) { @@ -708,6 +752,35 @@ 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, @@ -1052,7 +1125,7 @@ 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 +1152,7 @@ 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 +1843,25 @@ 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 @@ -1806,6 +1893,20 @@ typedef unsigned int pgtbl_mod_mask; #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 * time. These lead to variable PTRS_PER_x. For statically allocated arrays it * helps to have a static maximum value. diff --git a/include/linux/phy.h b/include/linux/phy.h index 3f68b8239bb1..e6e83304558e 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -778,6 +778,7 @@ 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) { diff --git a/include/linux/phy/phy-dp.h b/include/linux/phy/phy-dp.h index 18cad23642cd..9cce5766bc0b 100644 --- a/include/linux/phy/phy-dp.h +++ b/include/linux/phy/phy-dp.h @@ -8,6 +8,9 @@ #include <linux/types.h> +#define PHY_SUBMODE_DP 0 +#define PHY_SUBMODE_EDP 1 + /** * struct phy_configure_opts_dp - DisplayPort PHY configuration set * diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 9a57deefcb07..5ea6b2ad2396 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -138,6 +138,9 @@ 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. + * @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. * @ovr_an_inband: if true, override PCS to MLO_AN_INBAND * @get_fixed_state: callback to execute to determine the fixed link state, * if MAC link is at %MLO_AN_FIXED mode. @@ -150,6 +153,7 @@ struct phylink_config { enum phylink_op_type type; bool poll_fixed_state; bool mac_managed_pm; + bool mac_requires_rxc; bool ovr_an_inband; void (*get_fixed_state)(struct phylink_config *config, struct phylink_link_state *state); @@ -392,6 +396,10 @@ struct phylink_pcs_ops; * @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. @@ -404,6 +412,7 @@ struct phylink_pcs { struct phylink *phylink; bool neg_mode; bool poll; + bool rxc_always_on; }; /** @@ -418,6 +427,8 @@ 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, @@ -437,6 +448,7 @@ 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. */ @@ -542,6 +554,34 @@ 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 *, @@ -561,6 +601,8 @@ void phylink_disconnect_phy(struct phylink *); 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 *); 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/i2c-mux-gpio.h b/include/linux/platform_data/i2c-mux-gpio.h index 5e4c2c272a73..816a4cd3ccb5 100644 --- a/include/linux/platform_data/i2c-mux-gpio.h +++ b/include/linux/platform_data/i2c-mux-gpio.h @@ -18,7 +18,6 @@ * @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 */ struct i2c_mux_gpio_platform_data { @@ -26,7 +25,6 @@ struct i2c_mux_gpio_platform_data { int base_nr; const unsigned *values; int n_values; - const unsigned *classes; unsigned idle; }; 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/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/x86/asus-wmi.h b/include/linux/platform_data/x86/asus-wmi.h index ab1c7deff118..3eb5cd6773ad 100644 --- a/include/linux/platform_data/x86/asus-wmi.h +++ b/include/linux/platform_data/x86/asus-wmi.h @@ -71,6 +71,7 @@ #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 +128,18 @@ /* 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 diff --git a/include/linux/platform_profile.h b/include/linux/platform_profile.h index e5cbb6841f3a..f5492ed413f3 100644 --- a/include/linux/platform_profile.h +++ b/include/linux/platform_profile.h @@ -36,6 +36,7 @@ struct platform_profile_handler { int platform_profile_register(struct platform_profile_handler *pprof); int platform_profile_remove(void); +int platform_profile_cycle(void); void platform_profile_notify(void); #endif /*_PLATFORM_PROFILE_H_*/ diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 772d3280d35f..f24546a3d3db 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -260,6 +260,7 @@ 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); @@ -307,6 +308,11 @@ 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) { diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 065a47382302..dd7c8441af42 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -476,6 +476,8 @@ 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); 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); @@ -539,6 +541,12 @@ 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; diff --git a/include/linux/pm_wakeup.h b/include/linux/pm_wakeup.h index 6eb9adaef52b..76cd1f9f1365 100644 --- a/include/linux/pm_wakeup.h +++ b/include/linux/pm_wakeup.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 +234,10 @@ 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; } #endif /* _LINUX_PM_WAKEUP_H */ diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h index b9e5bd2b42d3..5180dc9f1706 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 { diff --git a/include/linux/printk.h b/include/linux/printk.h index 955e31860095..dbbd202b1cb3 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -71,7 +71,7 @@ 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 +126,7 @@ struct va_format { #define no_printk(fmt, ...) \ ({ \ if (0) \ - printk(fmt, ##__VA_ARGS__); \ + _printk(fmt, ##__VA_ARGS__); \ 0; \ }) diff --git a/include/linux/profile.h b/include/linux/profile.h index 11db1ec516e2..04ae5ebcb637 100644 --- a/include/linux/profile.h +++ b/include/linux/profile.h @@ -18,13 +18,8 @@ struct proc_dir_entry; struct notifier_block; #if defined(CONFIG_PROFILING) && defined(CONFIG_PROC_FS) -void create_prof_cpu_mask(void); int create_proc_profile(void); #else -static inline void create_prof_cpu_mask(void) -{ -} - static inline int create_proc_profile(void) { return 0; diff --git a/include/linux/pse-pd/pse.h b/include/linux/pse-pd/pse.h index fb724c65c77b..6d07c95dabb9 100644 --- a/include/linux/pse-pd/pse.h +++ b/include/linux/pse-pd/pse.h @@ -15,11 +15,14 @@ struct pse_controller_dev; /** * 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; }; /** @@ -29,25 +32,36 @@ struct pse_control_config { * 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: */ struct 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; }; /** * 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_is_enabled: Return 1 if the PSE PI is enabled, 0 if not. + * May also return negative errno. + * @pi_enable: Configure the PSE PI as enabled. + * @pi_disable: Configure the PSE PI as disabled. */ 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_is_enabled)(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); }; struct module; @@ -55,6 +69,40 @@ struct device_node; struct of_phandle_args; struct pse_control; +/* 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 * provide multiple PSE controls @@ -64,10 +112,11 @@ 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 +125,11 @@ 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) @@ -99,6 +149,9 @@ int pse_ethtool_set_config(struct pse_control *psec, struct netlink_ext_ack *extack, const struct pse_control_config *config); +bool pse_has_podl(struct pse_control *psec); +bool pse_has_c33(struct pse_control *psec); + #else static inline struct pse_control *of_pse_control_get(struct device_node *node) @@ -124,6 +177,16 @@ static inline int pse_ethtool_set_config(struct pse_control *psec, return -ENOTSUPP; } +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 #endif diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h index 808f9d3ee546..fd037c127bb0 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) @@ -609,6 +610,7 @@ 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 @@ -616,21 +618,21 @@ static inline int ptr_ring_resize(struct ptr_ring *r, int size, gfp_t gfp, * 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_multiple(struct ptr_ring **rings, - unsigned int nrings, - int size, - gfp_t gfp, void (*destroy)(void *)) +static inline int ptr_ring_resize_multiple_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; } @@ -660,6 +662,8 @@ nomem: noqueues: return -ENOMEM; } +#define ptr_ring_resize_multiple(...) \ + alloc_hooks(ptr_ring_resize_multiple_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..60b92c2c75ef 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -2,6 +2,7 @@ #ifndef __LINUX_PWM_H #define __LINUX_PWM_H +#include <linux/device.h> #include <linux/err.h> #include <linux/mutex.h> #include <linux/of.h> @@ -272,11 +273,11 @@ 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 * @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; @@ -287,31 +288,23 @@ struct pwm_chip { bool atomic; /* only used internally by the PWM framework */ - void *driver_data; - struct pwm_device *pwms; + bool uses_pwmchip_alloc; + struct pwm_device pwms[] __counted_by(npwm); }; 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) @@ -628,17 +621,4 @@ 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/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/randomize_kstack.h b/include/linux/randomize_kstack.h index 5d868505a94e..6d92b68efbf6 100644 --- a/include/linux/randomize_kstack.h +++ b/include/linux/randomize_kstack.h @@ -80,7 +80,7 @@ DECLARE_PER_CPU(u32, kstack_offset); if (static_branch_maybe(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT, \ &randomize_kstack_offset)) { \ u32 offset = raw_cpu_read(kstack_offset); \ - offset ^= (rand); \ + offset = ror32(offset, 5) ^ (rand); \ raw_cpu_write(kstack_offset, offset); \ } \ } while (0) diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 17d7ed5f3ae6..dfd2399f2cde 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -401,15 +401,15 @@ 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 { \ @@ -809,9 +809,9 @@ 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 +1090,18 @@ 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_wait.h b/include/linux/rcupdate_wait.h index d07f0848802e..303ab9bee155 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) { diff --git a/include/linux/regmap.h b/include/linux/regmap.h index b743241cfb7c..a6bc2980a98b 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -297,15 +297,6 @@ 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 +314,7 @@ 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 +323,15 @@ 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 +374,20 @@ 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 +406,6 @@ 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 +417,16 @@ 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 +450,16 @@ 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; }; /** @@ -1230,6 +1230,7 @@ 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, @@ -1739,6 +1740,13 @@ 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) { diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index 4660582a3302..59d0b9a79e6e 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -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); @@ -320,12 +321,18 @@ 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; } diff --git a/include/linux/regulator/pca9450.h b/include/linux/regulator/pca9450.h index 505c908dbb81..243633c8dceb 100644 --- a/include/linux/regulator/pca9450.h +++ b/include/linux/regulator/pca9450.h @@ -9,6 +9,7 @@ enum pca9450_chip_type { PCA9450_TYPE_PCA9450A = 0, PCA9450_TYPE_PCA9450BC, + PCA9450_TYPE_PCA9451A, 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/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..96d2140b471e 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; @@ -223,4 +225,8 @@ 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/rmap.h b/include/linux/rmap.h index b7944a833668..7229b9baf20d 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -273,6 +273,7 @@ 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 +285,7 @@ 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 +296,7 @@ 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 +307,7 @@ 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 +315,31 @@ 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(&page->_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 +359,12 @@ 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 +389,7 @@ 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 +418,20 @@ 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(&page->_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 +440,7 @@ 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 +475,13 @@ 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 +573,7 @@ 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 +584,7 @@ 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; } @@ -698,7 +730,7 @@ int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff, void remove_migration_ptes(struct folio *src, struct folio *dst, bool locked); -int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma); +unsigned long page_mapped_in_vma(struct page *page, struct vm_area_struct *vma); /* * rmap_walk_control: To control rmap traversing for specific needs diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index cdfc897f1e3c..a7da7dfc06a2 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -7,6 +7,7 @@ #include <linux/netdevice.h> #include <linux/wait.h> #include <linux/refcount.h> +#include <linux/cleanup.h> #include <uapi/linux/rtnetlink.h> extern int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, u32 group, int echo); @@ -46,6 +47,8 @@ extern int rtnl_is_locked(void); extern int rtnl_lock_killable(void); extern bool refcount_dec_and_rtnl_lock(refcount_t *r); +DEFINE_LOCK_GUARD_0(rtnl, rtnl_lock(), rtnl_unlock()) + extern wait_queue_head_t netdev_unregistering_wq; extern atomic_t dev_unreg_count; extern struct rw_semaphore pernet_ops_rwsem; diff --git a/include/linux/rwbase_rt.h b/include/linux/rwbase_rt.h index 29c4e4f243e4..f2394a409c9d 100644 --- a/include/linux/rwbase_rt.h +++ b/include/linux/rwbase_rt.h @@ -31,9 +31,9 @@ static __always_inline bool rw_base_is_locked(const struct rwbase_rt *rwb) return atomic_read(&rwb->readers) != READER_BIAS; } -static inline void rw_base_assert_held_write(const struct rwbase_rt *rwb) +static __always_inline bool rw_base_is_write_locked(const struct rwbase_rt *rwb) { - WARN_ON(atomic_read(&rwb->readers) != WRITER_BIAS); + return atomic_read(&rwb->readers) == WRITER_BIAS; } static __always_inline bool rw_base_is_contended(const struct rwbase_rt *rwb) diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index 4f1c18992f76..c8b543d428b0 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -167,14 +167,14 @@ static __always_inline int rwsem_is_locked(const struct rw_semaphore *sem) return rw_base_is_locked(&sem->rwbase); } -static inline void rwsem_assert_held_nolockdep(const struct rw_semaphore *sem) +static __always_inline void rwsem_assert_held_nolockdep(const struct rw_semaphore *sem) { WARN_ON(!rwsem_is_locked(sem)); } -static inline void rwsem_assert_held_write_nolockdep(const struct rw_semaphore *sem) +static __always_inline void rwsem_assert_held_write_nolockdep(const struct rw_semaphore *sem) { - rw_base_assert_held_write(sem); + WARN_ON(!rw_base_is_write_locked(&sem->rwbase)); } static __always_inline int rwsem_is_contended(struct rw_semaphore *sem) diff --git a/include/linux/sched.h b/include/linux/sched.h index 3c2abbc587b4..61591ac6eab6 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -301,7 +301,7 @@ enum { TASK_COMM_LEN = 16, }; -extern void scheduler_tick(void); +extern void sched_tick(void); #define MAX_SCHEDULE_TIMEOUT LONG_MAX @@ -770,6 +770,10 @@ 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; @@ -810,6 +814,7 @@ struct task_struct { struct task_group *sched_task_group; #endif + #ifdef CONFIG_UCLAMP_TASK /* * Clamp values requested for a scheduling entity. @@ -835,6 +840,7 @@ 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; @@ -1443,8 +1449,6 @@ struct task_struct { #ifdef CONFIG_MEMCG struct mem_cgroup *memcg_in_oom; - gfp_t memcg_oom_gfp_mask; - int memcg_oom_order; /* Number of pages to reclaim on returning to userland: */ unsigned int memcg_nr_pages_over_high; @@ -2187,4 +2191,23 @@ 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 inline struct alloc_tag *alloc_tag_save(struct alloc_tag *tag) +{ + swap(current->alloc_tag, tag); + return tag; +} + +static 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..e62ff805cfc9 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -92,9 +92,12 @@ static inline int get_dumpable(struct mm_struct *mm) #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_VM_MERGE_ANY_MASK | MMF_TOPDOWN_MASK) static inline unsigned long mmf_init_flags(unsigned long flags) { 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/mm.h b/include/linux/sched/mm.h index b6543f9d78d6..91546493c43d 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 @@ -186,6 +187,27 @@ arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); +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 +arch_get_unmapped_area_vmflags(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_vmflags(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags, vm_flags_t); + +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, diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 18572c9ea724..4237daa5ac7a 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -110,7 +110,7 @@ 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]; @@ -270,17 +270,17 @@ 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/scmi_protocol.h b/include/linux/scmi_protocol.h index b807141acc14..3a9bb5b9a9e8 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 { diff --git a/include/linux/secretmem.h b/include/linux/secretmem.h index 35f3a4a8ceb1..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 and LRU so we can - * save a couple of cycles here. - */ - if (folio_test_large(folio) || !folio_test_lru(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..21cf70346b33 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -398,7 +398,7 @@ int security_inode_setsecurity(struct inode *inode, const char *name, const void int security_inode_listsecurity(struct inode *inode, char *buffer, size_t buffer_size); void security_inode_getsecid(struct inode *inode, u32 *secid); 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_kernfs_init_security(struct kernfs_node *kn_dir, struct kernfs_node *kn); int security_file_permission(struct file *file, int mask); @@ -1016,7 +1016,7 @@ static inline int security_kernfs_init_security(struct kernfs_node *kn_dir, 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; } diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index 234bcdb1fba4..8bd4fda6e027 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -118,7 +118,18 @@ 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/sfp.h b/include/linux/sfp.h index 9346cd44814d..a45da7eef9a2 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -554,7 +554,7 @@ 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, @@ -592,7 +592,7 @@ 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; } 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 a4c15db2f5e5..3fb18f7eb73e 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -110,8 +110,17 @@ extern struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, extern void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end); int shmem_unuse(unsigned int type); +#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); +#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) +{ + return false; +} +#endif + #ifdef CONFIG_SHMEM extern unsigned long shmem_swap_usage(struct vm_area_struct *vma); #else diff --git a/include/linux/skb_array.h b/include/linux/skb_array.h index e2d45b7cb619..926496c9cc9c 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 +199,17 @@ 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_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_noprof((struct ptr_ring **)rings, + nrings, size, gfp, + __skb_array_destroy_skb); } +#define skb_array_resize_multiple(...) \ + alloc_hooks(skb_array_resize_multiple_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..1c2902eaebd3 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -353,8 +353,6 @@ 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 +525,13 @@ 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 +541,7 @@ 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; }; @@ -992,7 +996,7 @@ 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; @@ -1174,15 +1178,6 @@ 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. @@ -1615,17 +1610,26 @@ 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 } @@ -1662,14 +1666,13 @@ 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); @@ -1757,13 +1760,13 @@ 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 +1780,7 @@ 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; } @@ -3031,6 +3034,21 @@ 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); @@ -3350,13 +3368,7 @@ 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 +3383,7 @@ 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 +3396,11 @@ 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); -} +#define dev_alloc_pages(_order) __dev_alloc_pages(GFP_ATOMIC | __GFP_NOWARN, _order) /** * __dev_alloc_page - allocate a page for network Rx @@ -3400,15 +3410,13 @@ 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); -} +#define dev_alloc_page() dev_alloc_pages(0) /** * dev_page_is_reusable - check whether a page can be reused for network Rx @@ -3489,85 +3497,10 @@ static inline struct page *skb_frag_page(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)); -} - -/** - * 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]); -} - 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) -{ - struct page *page = skb_frag_page(frag); - -#ifdef CONFIG_PAGE_POOL - if (recycle && napi_pp_put_page(page, napi_safe)) - return; -#endif - put_page(page); -} - -/** - * __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) -{ - napi_frag_unref(frag, recycle, false); -} - -/** - * 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); -} - /** * skb_frag_address - gets the address of the data contained in a paged fragment * @frag: the paged fragment buffer @@ -4058,12 +3991,6 @@ 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); diff --git a/include/linux/skbuff_ref.h b/include/linux/skbuff_ref.h new file mode 100644 index 000000000000..11f0a4063403 --- /dev/null +++ b/include/linux/skbuff_ref.h @@ -0,0 +1,75 @@ +/* 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(struct page *page); + +static inline void +skb_page_unref(struct page *page, bool recycle) +{ +#ifdef CONFIG_PAGE_POOL + if (recycle && napi_pp_put_page(page)) + return; +#endif + put_page(page); +} + +/** + * __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_page(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..c9efda9df285 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 { @@ -410,11 +414,9 @@ 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); -} +#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 +463,12 @@ 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..7247e217e21b 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -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 }; @@ -202,6 +205,13 @@ 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 + /* * ZERO_SIZE_PTR will be returned for zero sized kmalloc requests. * @@ -261,12 +271,15 @@ int kmem_cache_shrink(struct kmem_cache *s); /* * 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)) /** * ksize - Report actual allocation size of associated object @@ -513,7 +526,10 @@ 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> + +void *__kmalloc_noprof(size_t size, gfp_t flags) __assume_kmalloc_alignment __alloc_size(1); +#define __kmalloc(...) alloc_hooks(__kmalloc_noprof(__VA_ARGS__)) /** * kmem_cache_alloc - Allocate an object @@ -525,9 +541,14 @@ 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__)) + void kmem_cache_free(struct kmem_cache *s, void *objp); /* @@ -538,29 +559,40 @@ 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 +void *__kmalloc_node_noprof(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; +#define __kmalloc_node(...) alloc_hooks(__kmalloc_node_noprof(__VA_ARGS__)) -void *kmalloc_trace(struct kmem_cache *s, gfp_t flags, size_t size) +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__)) + +void *kmalloc_trace_noprof(struct kmem_cache *s, gfp_t flags, size_t size) __assume_kmalloc_alignment __alloc_size(3); -void *kmalloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, - int node, size_t size) __assume_kmalloc_alignment +void *kmalloc_node_trace_noprof(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 +#define kmalloc_trace(...) alloc_hooks(kmalloc_trace_noprof(__VA_ARGS__)) + +#define kmalloc_node_trace(...) alloc_hooks(kmalloc_node_trace_noprof(__VA_ARGS__)) + +void *kmalloc_large_noprof(size_t size, gfp_t flags) __assume_page_alignment __alloc_size(1); +#define kmalloc_large(...) alloc_hooks(kmalloc_large_noprof(__VA_ARGS__)) -void *kmalloc_large_node(size_t size, gfp_t flags, int node) __assume_page_alignment +void *kmalloc_large_node_noprof(size_t size, gfp_t flags, int node) __assume_page_alignment __alloc_size(1); +#define kmalloc_large_node(...) alloc_hooks(kmalloc_large_node_noprof(__VA_ARGS__)) /** * kmalloc - allocate kernel memory @@ -616,37 +648,39 @@ 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_trace_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__)) -static __always_inline __alloc_size(1) void *kmalloc_node(size_t size, gfp_t flags, int node) +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_node_trace_noprof( kmalloc_caches[kmalloc_type(flags, _RET_IP_)][index], flags, node, size); } - return __kmalloc_node(size, flags, node); + return __kmalloc_node_noprof(size, flags, node); } +#define kmalloc_node(...) alloc_hooks(kmalloc_node_noprof(__VA_ARGS__)) /** * kmalloc_array - allocate memory for an array. @@ -654,16 +688,17 @@ 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. @@ -672,18 +707,19 @@ static inline __alloc_size(1, 2) void *kmalloc_array(size_t n, size_t size, gfp_ * @new_size: new size of a single member of the array * @flags: the type of memory to allocate (see kmalloc) */ -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 +727,12 @@ 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, +void *kmalloc_node_track_caller_noprof(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_) +#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 +742,12 @@ 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) -static inline __alloc_size(1, 2) void *kmalloc_array_node(size_t n, size_t size, gfp_t flags, +#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_noprof(size_t n, size_t size, gfp_t flags, int node) { size_t bytes; @@ -722,77 +755,65 @@ 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(bytes, 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); -} +extern void *kvmalloc_node_noprof(size_t size, gfp_t flags, int node) __alloc_size(1); +#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) + +#define kvzalloc_node(_size, _flags, _node) kvmalloc_node(_size, (_flags)|__GFP_ZERO, _node) -static inline __alloc_size(1, 2) void *kvmalloc_array(size_t n, size_t size, gfp_t flags) +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) -extern void *kvrealloc(const void *p, size_t oldsize, size_t newsize, gfp_t flags) +#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__)) + +extern void *kvrealloc_noprof(const void *p, size_t oldsize, size_t newsize, gfp_t flags) __realloc_size(3); +#define kvrealloc(...) alloc_hooks(kvrealloc_noprof(__VA_ARGS__)) + 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); diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h index 649955d2cf5c..d4a8e34505e6 100644 --- a/include/linux/soc/mediatek/mtk-cmdq.h +++ b/include/linux/soc/mediatek/mtk-cmdq.h @@ -14,6 +14,15 @@ #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; struct cmdq_client_reg { @@ -62,17 +71,19 @@ 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 +185,18 @@ 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 +207,21 @@ 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 @@ -248,36 +286,76 @@ 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_eoc() - Append EOC and ask GCE to generate an IRQ at end of execution + * @pkt: The CMDQ packet + * + * 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. + * + * Return: 0 for success or negative error number + */ +int cmdq_pkt_eoc(struct cmdq_pkt *pkt); /** - * cmdq_pkt_flush_async() - trigger CMDQ to asynchronously execute the CMDQ - * packet and call back at the end of done packet + * cmdq_pkt_finalize() - Append EOC and jump command to pkt. * @pkt: the CMDQ packet * * Return: 0 for success; else the error code is returned - * - * 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. */ -int cmdq_pkt_flush_async(struct cmdq_pkt *pkt); +int cmdq_pkt_finalize(struct cmdq_pkt *pkt); #else /* IS_ENABLED(CONFIG_MTK_CMDQ) */ @@ -294,12 +372,12 @@ 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 +452,32 @@ 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_finalize(struct cmdq_pkt *pkt) +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_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; +} + +static inline int cmdq_pkt_finalize(struct cmdq_pkt *pkt) { return -EINVAL; } diff --git a/include/linux/socket.h b/include/linux/socket.h index 139c330ccf2c..89d16b90370b 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))) @@ -433,7 +434,7 @@ 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, diff --git a/include/linux/sockptr.h b/include/linux/sockptr.h index 307961b41541..fc5a206c4043 100644 --- a/include/linux/sockptr.h +++ b/include/linux/sockptr.h @@ -50,11 +50,36 @@ static inline int copy_from_sockptr_offset(void *dst, sockptr_t src, return 0; } +/* Deprecated. + * This is unsafe, unless caller checked user provided optlen. + * Prefer copy_safe_from_sockptr() instead. + */ static inline int copy_from_sockptr(void *dst, sockptr_t src, size_t size) { return copy_from_sockptr_offset(dst, src, 0, size); } +/** + * copy_safe_from_sockptr: copy a struct from sockptr + * @dst: Destination address, in kernel space. This buffer must be @ksize + * bytes long. + * @ksize: Size of @dst struct. + * @optval: Source address. (in user or kernel space) + * @optlen: Size of @optval data. + * + * Returns: + * * -EINVAL: @optlen < @ksize + * * -EFAULT: access to userspace failed. + * * 0 : @ksize bytes were copied + */ +static inline int copy_safe_from_sockptr(void *dst, size_t ksize, + sockptr_t optval, unsigned int optlen) +{ + if (optlen < ksize) + return -EINVAL; + return copy_from_sockptr(dst, optval, ksize); +} + static inline int copy_struct_from_sockptr(void *dst, size_t ksize, sockptr_t src, size_t usize) { @@ -92,9 +117,9 @@ 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); @@ -104,10 +129,11 @@ 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); @@ -118,6 +144,7 @@ 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..13e96d8b7423 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -235,6 +235,7 @@ enum sdw_clk_stop_mode { * @BRA_flow_controlled: Slave implementation results in an OK_NotReady * response * @simple_ch_prep_sm: If channel prepare sequence is required + * @ch_prep_timeout: Port-specific timeout value, in milliseconds * @imp_def_interrupts: If set, each bit corresponds to support for * implementation-defined interrupts * @@ -249,6 +250,7 @@ struct sdw_dp0_prop { u32 *words; bool BRA_flow_controlled; bool simple_ch_prep_sm; + u32 ch_prep_timeout; bool imp_def_interrupts; }; @@ -543,21 +545,6 @@ 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 @@ -899,6 +886,7 @@ struct sdw_master_ops { * @port_ops: Master port callback ops * @params: Current bus parameters * @prop: Master properties + * @vendor_specific_prop: pointer to non-standard 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 @@ -933,6 +921,7 @@ struct sdw_bus { const struct sdw_master_port_ops *port_ops; struct sdw_bus_params params; struct sdw_master_prop prop; + void *vendor_specific_prop; struct list_head m_rt_list; #ifdef CONFIG_DEBUG_FS struct dentry *debugfs; diff --git a/include/linux/soundwire/sdw_intel.h b/include/linux/soundwire/sdw_intel.h index 00bb22d96ae5..8e78417156e3 100644 --- a/include/linux/soundwire/sdw_intel.h +++ b/include/linux/soundwire/sdw_intel.h @@ -22,6 +22,7 @@ /* 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 +31,18 @@ #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) diff --git a/include/linux/soundwire/sdw_registers.h b/include/linux/soundwire/sdw_registers.h index 138bec908c40..658b10fa5b20 100644 --- a/include/linux/soundwire/sdw_registers.h +++ b/include/linux/soundwire/sdw_registers.h @@ -13,7 +13,7 @@ #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 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.h b/include/linux/spi/spi.h index c459809efee4..e8e1e798924f 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -453,6 +453,7 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch * @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 @@ -955,8 +956,8 @@ 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 @@ -1066,8 +1067,7 @@ 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; @@ -1111,8 +1111,6 @@ 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 +1144,6 @@ 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 */ 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/srcutiny.h b/include/linux/srcutiny.h index 447133171d95..4d96bbdb45f0 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; } diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h index 1f326da289d3..a2257380c3f1 100644 --- a/include/linux/ssb/ssb.h +++ b/include/linux/ssb/ssb.h @@ -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 3c6caa5abc7c..e9ec32fb97d4 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -44,10 +44,9 @@ typedef u32 depot_stack_handle_t; union handle_parts { depot_stack_handle_t handle; struct { - /* pool_index is offset by 1 */ - u32 pool_index : DEPOT_POOL_INDEX_BITS; - u32 offset : DEPOT_OFFSET_BITS; - u32 extra : STACK_DEPOT_EXTRA_BITS; + u32 pool_index_plus_1 : DEPOT_POOL_INDEX_BITS; + u32 offset : DEPOT_OFFSET_BITS; + u32 extra : STACK_DEPOT_EXTRA_BITS; }; }; diff --git a/include/linux/stat.h b/include/linux/stat.h index 52150570d37a..bf92441dbad2 100644 --- a/include/linux/stat.h +++ b/include/linux/stat.h @@ -53,6 +53,7 @@ struct kstat { u32 dio_mem_align; u32 dio_offset_align; u64 change_cookie; + u64 subvol; }; /* These definitions are internal to the kernel for now. Mainly used by nfsd. */ diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index dfa1828cd756..f92c195c76ed 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -115,21 +115,6 @@ 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; @@ -246,7 +231,6 @@ 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; @@ -285,6 +269,8 @@ 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); void *bsp_priv; struct clk *stmmac_clk; struct clk *pclk; diff --git a/include/linux/string.h b/include/linux/string.h index 9ba8b4597009..60168aa2af07 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -14,8 +14,8 @@ #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 +27,8 @@ 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 +47,8 @@ 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; @@ -282,10 +284,13 @@ 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 element_size, size_t count, gfp_t gfp) + __realloc_size(2, 3); /* lib/argv_split.c */ extern char **argv_split(gfp_t gfp, const char *str, int *argcp); @@ -423,6 +428,55 @@ 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/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 24cd199dd6f3..d33bab33099a 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -210,7 +210,6 @@ struct svc_rdma_recv_ctxt { */ struct svc_rdma_write_info { struct svcxprt_rdma *wi_rdma; - struct list_head wi_list; const struct svc_rdma_chunk *wi_chunk; @@ -239,10 +238,7 @@ struct svc_rdma_send_ctxt { struct ib_cqe sc_cqe; struct xdr_buf sc_hdrbuf; struct xdr_stream sc_stream; - - struct list_head sc_write_info_list; struct svc_rdma_write_info sc_reply_info; - void *sc_xprt_buf; int sc_page_count; int sc_cur_sge_no; @@ -274,14 +270,11 @@ extern void svc_rdma_cc_init(struct svcxprt_rdma *rdma, extern void svc_rdma_cc_release(struct svcxprt_rdma *rdma, struct svc_rdma_chunk_ctxt *cc, enum dma_data_direction dir); -extern void svc_rdma_write_chunk_release(struct svcxprt_rdma *rdma, - struct svc_rdma_send_ctxt *ctxt); extern void svc_rdma_reply_chunk_release(struct svcxprt_rdma *rdma, struct svc_rdma_send_ctxt *ctxt); -extern int svc_rdma_prepare_write_list(struct svcxprt_rdma *rdma, - const struct svc_rdma_pcl *write_pcl, - struct svc_rdma_send_ctxt *sctxt, - const struct xdr_buf *xdr); +extern int svc_rdma_send_write_list(struct svcxprt_rdma *rdma, + const struct svc_rdma_recv_ctxt *rctxt, + const struct xdr_buf *xdr); extern int svc_rdma_prepare_reply_chunk(struct svcxprt_rdma *rdma, const struct svc_rdma_pcl *write_pcl, const struct svc_rdma_pcl *reply_pcl, diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index 8e20cd60e2e7..0981e35a9fed 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -135,6 +135,9 @@ 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 +150,8 @@ 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/swap.h b/include/linux/swap.h index f53d608daa01..bd450023b9a4 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -259,7 +259,20 @@ struct swap_cluster_info { }; #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 */ + +/* + * 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 next is not valid in percpu_cluster. + */ +#define SWAP_NEXT_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 @@ -267,8 +280,7 @@ struct swap_cluster_info { * throughput. */ struct percpu_cluster { - struct swap_cluster_info index; /* Current cluster index */ - unsigned int next; /* Likely next allocation offset */ + unsigned int next[SWAP_NR_ORDERS]; /* Likely next allocation offset */ }; struct swap_cluster_list { @@ -298,10 +310,8 @@ struct swap_info_struct { unsigned int __percpu *cluster_next_cpu; /*percpu index for next allocation */ struct percpu_cluster __percpu *percpu_cluster; /* per cpu's swap location */ 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 @@ -462,14 +472,14 @@ 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 int swap_duplicate(swp_entry_t); extern int swapcache_prepare(swp_entry_t); extern void swap_free(swp_entry_t); 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 +528,9 @@ 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) { @@ -587,14 +598,10 @@ 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); } -#endif #ifdef CONFIG_MEMCG static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg) diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 48b700ba1d18..a5c560a2f8c2 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -390,6 +390,35 @@ static inline bool is_migration_entry_dirty(swp_entry_t entry) } #endif /* CONFIG_MIGRATION */ +#ifdef CONFIG_MEMORY_FAILURE + +/* + * Support for hardware poisoned pages + */ +static inline swp_entry_t make_hwpoison_entry(struct page *page) +{ + BUG_ON(!PageLocked(page)); + return swp_entry(SWP_HWPOISON, page_to_pfn(page)); +} + +static inline int is_hwpoison_entry(swp_entry_t entry) +{ + return swp_type(entry) == SWP_HWPOISON; +} + +#else + +static inline swp_entry_t make_hwpoison_entry(struct page *page) +{ + return swp_entry(0, 0); +} + +static inline int is_hwpoison_entry(swp_entry_t swp) +{ + return 0; +} +#endif + typedef unsigned long pte_marker; #define PTE_MARKER_UFFD_WP BIT(0) @@ -483,8 +512,9 @@ static inline struct folio *pfn_swap_entry_folio(swp_entry_t entry) /* * A pfn swap entry is a special type of swap entry that always has a pfn stored - * in the swap offset. They are used to represent unaddressable device memory - * and to restrict access to a page undergoing migration. + * in the swap offset. They can either be used to represent unaddressable device + * memory, to restrict access to a page undergoing migration or to represent a + * pfn which has been hwpoisoned and unmapped. */ static inline bool is_pfn_swap_entry(swp_entry_t entry) { @@ -492,7 +522,7 @@ static inline bool is_pfn_swap_entry(swp_entry_t entry) BUILD_BUG_ON(SWP_TYPE_SHIFT < SWP_PFN_BITS); return is_migration_entry(entry) || is_device_private_entry(entry) || - is_device_exclusive_entry(entry); + is_device_exclusive_entry(entry) || is_hwpoison_entry(entry); } struct page_vma_mapped_walk; @@ -561,35 +591,6 @@ static inline int is_pmd_migration_entry(pmd_t pmd) } #endif /* CONFIG_ARCH_ENABLE_THP_MIGRATION */ -#ifdef CONFIG_MEMORY_FAILURE - -/* - * Support for hardware poisoned pages - */ -static inline swp_entry_t make_hwpoison_entry(struct page *page) -{ - BUG_ON(!PageLocked(page)); - return swp_entry(SWP_HWPOISON, page_to_pfn(page)); -} - -static inline int is_hwpoison_entry(swp_entry_t entry) -{ - return swp_type(entry) == SWP_HWPOISON; -} - -#else - -static inline swp_entry_t make_hwpoison_entry(struct page *page) -{ - return swp_entry(0, 0); -} - -static inline int is_hwpoison_entry(swp_entry_t swp) -{ - return 0; -} -#endif - static inline int non_swap_entry(swp_entry_t entry) { return swp_type(entry) >= MAX_SWAPFILES; diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index ea23097e351f..14bc10c1bb23 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -43,7 +43,7 @@ int swiotlb_init_late(size_t size, gfp_t gfp_mask, 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, + size_t mapping_size, unsigned int alloc_aligned_mask, enum dma_data_direction dir, unsigned long attrs); diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index ee7d33b89e9e..09db2f2e6488 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -137,17 +137,6 @@ struct ctl_table { 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; @@ -182,12 +171,23 @@ 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 +205,8 @@ 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) \ diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 55399ee2a57e..6a5e08b937b3 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -244,6 +244,7 @@ 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 */ @@ -266,8 +267,6 @@ struct tcp_sock { 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 +283,8 @@ 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 +371,6 @@ 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..efd16ed52315 --- /dev/null +++ b/include/linux/tee_core.h @@ -0,0 +1,306 @@ +/* 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_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..786b9ae6cf4d 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; /** @@ -509,18 +300,4 @@ 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); - #endif /*__TEE_DRV_H*/ diff --git a/include/linux/thermal.h b/include/linux/thermal.h index c33f50177f51..f1155c0439c4 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -61,7 +61,6 @@ enum thermal_notify_event { * 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 +68,6 @@ enum thermal_notify_event { struct thermal_trip { int temperature; int hysteresis; - int threshold; enum thermal_trip_type type; u8 flags; void *priv; @@ -81,6 +79,8 @@ struct thermal_trip { #define THERMAL_TRIP_FLAG_RW (THERMAL_TRIP_FLAG_RW_TEMP | \ THERMAL_TRIP_FLAG_RW_HYST) +struct thermal_zone_device; + struct thermal_zone_device_ops { int (*bind) (struct thermal_zone_device *, struct thermal_cooling_device *); @@ -126,111 +126,6 @@ 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; -}; - /* Structure to define Thermal Zone parameters */ struct thermal_zone_params { const char *governor_name; 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/timecounter.h b/include/linux/timecounter.h index c6540ceea143..0982d1d52b24 100644 --- a/include/linux/timecounter.h +++ b/include/linux/timecounter.h @@ -22,7 +22,7 @@ * * @read: returns the current cycle value * @mask: bitmask for two's complement - * subtraction of non 64 bit counters, + * subtraction of non-64-bit counters, * see CYCLECOUNTER_MASK() helper macro * @mult: cycle to nanosecond multiplier * @shift: cycle to nanosecond divisor (power of two) @@ -35,7 +35,7 @@ struct cyclecounter { }; /** - * struct timecounter - layer above a %struct cyclecounter which counts nanoseconds + * struct timecounter - layer above a &struct cyclecounter which counts nanoseconds * Contains the state needed by timecounter_read() to detect * cycle counter wrap around. Initialize with * timecounter_init(). Also used to convert cycle counts into the @@ -66,6 +66,8 @@ struct timecounter { * @cycles: Cycles * @mask: bit mask for maintaining the 'frac' field * @frac: pointer to storage for the fractional nanoseconds. + * + * Returns: cycle counter cycles converted to nanoseconds */ static inline u64 cyclecounter_cyc2ns(const struct cyclecounter *cc, u64 cycles, u64 mask, u64 *frac) @@ -79,6 +81,7 @@ static inline u64 cyclecounter_cyc2ns(const struct cyclecounter *cc, /** * timecounter_adjtime - Shifts the time of the clock. + * @tc: The &struct timecounter to adjust * @delta: Desired change in nanoseconds. */ static inline void timecounter_adjtime(struct timecounter *tc, s64 delta) @@ -107,6 +110,8 @@ extern void timecounter_init(struct timecounter *tc, * * In other words, keeps track of time since the same epoch as * the function which generated the initial time stamp. + * + * Returns: nanoseconds since the initial time stamp */ extern u64 timecounter_read(struct timecounter *tc); @@ -123,6 +128,8 @@ extern u64 timecounter_read(struct timecounter *tc); * * This allows conversion of cycle counter values which were generated * in the past. + * + * Returns: cycle counter converted to nanoseconds since the initial time stamp */ extern u64 timecounter_cyc2time(const struct timecounter *tc, u64 cycle_tstamp); diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 7e50cbd97f86..0ea7823b7f31 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -22,14 +22,14 @@ extern int do_sys_settimeofday64(const struct timespec64 *tv, const struct timezone *tz); /* - * ktime_get() family: read the current time in a multitude of ways, + * ktime_get() family - read the current time in a multitude of ways. * * The default time reference is CLOCK_MONOTONIC, starting at * boot time but not counting the time spent in suspend. * For other references, use the functions with "real", "clocktai", * "boottime" and "raw" suffixes. * - * To get the time in a different format, use the ones wit + * To get the time in a different format, use the ones with * "ns", "ts64" and "seconds" suffix. * * See Documentation/core-api/timekeeping.rst for more details. @@ -74,6 +74,8 @@ extern u32 ktime_get_resolution_ns(void); /** * ktime_get_real - get the real (wall-) time in ktime_t format + * + * Returns: real (wall) time in ktime_t format */ static inline ktime_t ktime_get_real(void) { @@ -86,10 +88,12 @@ static inline ktime_t ktime_get_coarse_real(void) } /** - * ktime_get_boottime - Returns monotonic time since boot in ktime_t format + * ktime_get_boottime - Get monotonic time since boot in ktime_t format * * This is similar to CLOCK_MONTONIC/ktime_get, but also includes the * time spent in suspend. + * + * Returns: monotonic time since boot in ktime_t format */ static inline ktime_t ktime_get_boottime(void) { @@ -102,7 +106,9 @@ static inline ktime_t ktime_get_coarse_boottime(void) } /** - * ktime_get_clocktai - Returns the TAI time of day in ktime_t format + * ktime_get_clocktai - Get the TAI time of day in ktime_t format + * + * Returns: the TAI time of day in ktime_t format */ static inline ktime_t ktime_get_clocktai(void) { @@ -144,32 +150,60 @@ static inline u64 ktime_get_coarse_clocktai_ns(void) /** * ktime_mono_to_real - Convert monotonic time to clock realtime + * @mono: monotonic time to convert + * + * Returns: time converted to realtime clock */ static inline ktime_t ktime_mono_to_real(ktime_t mono) { return ktime_mono_to_any(mono, TK_OFFS_REAL); } +/** + * ktime_get_ns - Get the current time in nanoseconds + * + * Returns: current time converted to nanoseconds + */ static inline u64 ktime_get_ns(void) { return ktime_to_ns(ktime_get()); } +/** + * ktime_get_real_ns - Get the current real/wall time in nanoseconds + * + * Returns: current real time converted to nanoseconds + */ static inline u64 ktime_get_real_ns(void) { return ktime_to_ns(ktime_get_real()); } +/** + * ktime_get_boottime_ns - Get the monotonic time since boot in nanoseconds + * + * Returns: current boottime converted to nanoseconds + */ static inline u64 ktime_get_boottime_ns(void) { return ktime_to_ns(ktime_get_boottime()); } +/** + * ktime_get_clocktai_ns - Get the current TAI time of day in nanoseconds + * + * Returns: current TAI time converted to nanoseconds + */ static inline u64 ktime_get_clocktai_ns(void) { return ktime_to_ns(ktime_get_clocktai()); } +/** + * ktime_get_raw_ns - Get the raw monotonic time in nanoseconds + * + * Returns: current raw monotonic time converted to nanoseconds + */ static inline u64 ktime_get_raw_ns(void) { return ktime_to_ns(ktime_get_raw()); @@ -224,8 +258,8 @@ extern bool timekeeping_rtc_skipresume(void); extern void timekeeping_inject_sleeptime64(const struct timespec64 *delta); -/* - * struct ktime_timestanps - Simultaneous mono/boot/real timestamps +/** + * struct ktime_timestamps - Simultaneous mono/boot/real timestamps * @mono: Monotonic timestamp * @boot: Boottime timestamp * @real: Realtime timestamp @@ -242,7 +276,8 @@ struct ktime_timestamps { * @cycles: Clocksource counter value to produce the system times * @real: Realtime system time * @raw: Monotonic raw system time - * @clock_was_set_seq: The sequence number of clock was set events + * @cs_id: Clocksource ID + * @clock_was_set_seq: The sequence number of clock-was-set events * @cs_was_changed_seq: The sequence number of clocksource change events */ struct system_time_snapshot { diff --git a/include/linux/timer.h b/include/linux/timer.h index 14a633ba61d6..e67ecd1cbc97 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -22,7 +22,7 @@ #define __TIMER_LOCKDEP_MAP_INITIALIZER(_kn) #endif -/** +/* * @TIMER_DEFERRABLE: A deferrable timer will work normally when the * system is busy, but will not cause a CPU to come out of idle just * to service it; instead, the timer will be serviced when the CPU @@ -140,7 +140,7 @@ static inline void destroy_timer_on_stack(struct timer_list *timer) { } * or not. Callers must ensure serialization wrt. other operations done * to this timer, eg. interrupt contexts, or other CPUs on SMP. * - * return value: 1 if the timer is pending, 0 if not. + * Returns: 1 if the timer is pending, 0 if not. */ static inline int timer_pending(const struct timer_list * timer) { @@ -175,6 +175,10 @@ extern int timer_shutdown(struct timer_list *timer); * See timer_delete_sync() for detailed explanation. * * Do not use in new code. Use timer_delete_sync() instead. + * + * Returns: + * * %0 - The timer was not pending + * * %1 - The timer was pending and deactivated */ static inline int del_timer_sync(struct timer_list *timer) { @@ -188,6 +192,10 @@ static inline int del_timer_sync(struct timer_list *timer) * See timer_delete() for detailed explanation. * * Do not use in new code. Use timer_delete() instead. + * + * Returns: + * * %0 - The timer was not pending + * * %1 - The timer was pending and deactivated */ static inline int del_timer(struct timer_list *timer) { 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/tpm.h b/include/linux/tpm.h index 4ee9d13749ad..c17e4efbb2e5 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 +361,61 @@ 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), }; +/* + * definitions for the canonical template. These are mandated + * by the TCG key template documents + */ + +#define AES_KEY_BYTES AES_KEYSIZE_128 +#define AES_KEY_BITS (AES_KEY_BYTES*8) +#define TPM2_OA_TMPL (TPM2_OA_NO_DA | \ + TPM2_OA_FIXED_TPM | \ + TPM2_OA_FIXED_PARENT | \ + TPM2_OA_SENSITIVE_DATA_ORIGIN | \ + TPM2_OA_USER_WITH_AUTH | \ + TPM2_OA_DECRYPT | \ + TPM2_OA_RESTRICTED) + 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 +423,21 @@ 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); + +u8 *tpm_buf_parameters(struct tpm_buf *buf); /* * Check if TPM device is in the firmware upgrade mode. @@ -415,7 +449,7 @@ 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 +463,19 @@ 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 +493,6 @@ 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 +502,102 @@ 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 +#ifdef CONFIG_TCG_TPM2_HMAC + +int tpm2_start_auth_session(struct tpm_chip *chip); +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); +static inline void tpm_buf_append_hmac_session_opt(struct tpm_chip *chip, + struct tpm_buf *buf, + u8 attributes, + u8 *passphrase, + int passphraselen) +{ + tpm_buf_append_hmac_session(chip, buf, attributes, passphrase, + passphraselen); +} +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 <asm/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_append_name(struct tpm_chip *chip, + struct tpm_buf *buf, + u32 handle, u8 *name) +{ + tpm_buf_append_u32(buf, handle); + /* count the number of handles in the upper bits of flags */ + buf->handles++; +} +static inline void tpm_buf_append_hmac_session(struct tpm_chip *chip, + struct tpm_buf *buf, + u8 attributes, u8 *passphrase, + int passphraselen) +{ + /* offset tells us where the sessions area begins */ + int offset = buf->handles * 4 + TPM_HEADER_SIZE; + u32 len = 9 + passphraselen; + + if (tpm_buf_length(buf) != offset) { + /* not the first session so update the existing length */ + len += get_unaligned_be32(&buf->data[offset]); + put_unaligned_be32(len, &buf->data[offset]); + } else { + tpm_buf_append_u32(buf, len); + } + /* auth handle */ + tpm_buf_append_u32(buf, TPM2_RS_PW); + /* nonce */ + tpm_buf_append_u16(buf, 0); + /* attributes */ + tpm_buf_append_u8(buf, 0); + /* passphrase */ + tpm_buf_append_u16(buf, passphraselen); + tpm_buf_append(buf, passphrase, passphraselen); +} +static inline void tpm_buf_append_hmac_session_opt(struct tpm_chip *chip, + struct tpm_buf *buf, + u8 attributes, + u8 *passphrase, + int passphraselen) +{ + int offset = buf->handles * 4 + TPM_HEADER_SIZE; + struct tpm_header *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); +} +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/trace_events.h b/include/linux/trace_events.h index 6f9bdfb09d1d..9df3e2973626 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -765,8 +765,11 @@ 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 +797,12 @@ 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; } @@ -909,31 +913,31 @@ 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..24ea8ac049b4 100644 --- a/include/linux/trace_recursion.h +++ b/include/linux/trace_recursion.h @@ -135,7 +135,7 @@ 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/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/u64_stats_sync.h b/include/linux/u64_stats_sync.h index ffe48e69b3f3..457879938fc1 100644 --- a/include/linux/u64_stats_sync.h +++ b/include/linux/u64_stats_sync.h @@ -135,10 +135,11 @@ static inline void u64_stats_inc(u64_stats_t *p) p->v++; } -static inline void u64_stats_init(struct u64_stats_sync *syncp) -{ - seqcount_init(&syncp->seq); -} +#define u64_stats_init(syncp) \ + do { \ + struct u64_stats_sync *__s = (syncp); \ + seqcount_init(&__s->seq); \ + } while (0) static inline void __u64_stats_update_begin(struct u64_stats_sync *syncp) { diff --git a/include/linux/udp.h b/include/linux/udp.h index 3748e82b627b..3eb3f2b9a2a0 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) @@ -108,7 +108,7 @@ struct udp_sock { #define udp_assign_bit(nr, sk, val) \ assign_bit(UDP_FLAGS_##nr, &udp_sk(sk)->udp_flags, val) -#define UDP_MAX_SEGMENTS (1 << 6UL) +#define UDP_MAX_SEGMENTS (1 << 7UL) #define udp_sk(ptr) container_of_const(ptr, struct udp_sock, inet.sk) @@ -150,6 +150,24 @@ static inline void udp_cmsg_recv(struct msghdr *msg, struct sock *sk, } } +DECLARE_STATIC_KEY_FALSE(udp_encap_needed_key); +#if IS_ENABLED(CONFIG_IPV6) +DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key); +#endif + +static inline bool udp_encap_needed(void) +{ + if (static_branch_unlikely(&udp_encap_needed_key)) + return true; + +#if IS_ENABLED(CONFIG_IPV6) + if (static_branch_unlikely(&udpv6_encap_needed_key)) + return true; +#endif + + return false; +} + static inline bool udp_unexpected_gso(struct sock *sk, struct sk_buff *skb) { if (!skb_is_gso(skb)) @@ -163,6 +181,16 @@ static inline bool udp_unexpected_gso(struct sock *sk, struct sk_buff *skb) !udp_test_bit(ACCEPT_FRAGLIST, sk)) return true; + /* GSO packets lacking the SKB_GSO_UDP_TUNNEL/_CSUM bits might still + * land in a tunnel as the socket check in udp_gro_receive cannot be + * foolproof. + */ + if (udp_encap_needed() && + READ_ONCE(udp_sk(sk)->encap_rcv) && + !(skb_shinfo(skb)->gso_type & + (SKB_GSO_UDP_TUNNEL | SKB_GSO_UDP_TUNNEL_CSUM))) + return true; + return false; } diff --git a/include/linux/uio.h b/include/linux/uio.h index 00cebe2b70de..7020adedfa08 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -206,6 +206,16 @@ 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); diff --git a/include/linux/virtio.h b/include/linux/virtio.h index b0201747a263..96fea920873b 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -126,6 +126,8 @@ 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; @@ -141,6 +143,10 @@ 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) @@ -170,7 +176,7 @@ size_t virtio_max_dma_size(const struct virtio_device *vdev); /** * struct virtio_driver - operations for a virtio I/O driver - * @driver: underlying device driver (populate name and owner). + * @driver: underlying device driver (populate name). * @id_table: the ids serviced by this driver. * @feature_table: an array of feature numbers supported by this driver. * @feature_table_size: number of entries in the feature table array. @@ -208,7 +214,10 @@ static inline struct virtio_driver *drv_to_virtio(struct device_driver *drv) return container_of(drv, struct virtio_driver, driver); } -int register_virtio_driver(struct virtio_driver *drv); +/* use a macro to avoid include chaining to get THIS_MODULE */ +#define register_virtio_driver(drv) \ + __register_virtio_driver(drv, THIS_MODULE) +int __register_virtio_driver(struct virtio_driver *drv, struct module *owner); void unregister_virtio_driver(struct virtio_driver *drv); /* module_virtio_driver() - Helper macro for drivers that don't do @@ -234,4 +243,33 @@ 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/vmalloc.h b/include/linux/vmalloc.h index 98ea90e90439..e4a631ec430b 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> @@ -138,26 +140,54 @@ extern unsigned long vmalloc_nr_pages(void); static inline unsigned long vmalloc_nr_pages(void) { return 0; } #endif -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 *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 *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_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 *__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 *vcalloc_noprof(size_t n, size_t size) __alloc_size(1, 2); +#define vcalloc(...) alloc_hooks(vcalloc_noprof(__VA_ARGS__)) extern void vfree(const void *addr); extern void vfree_atomic(const void *addr); diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 343906a98d6e..735eae6e272c 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -487,14 +487,6 @@ 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) 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/workqueue.h b/include/linux/workqueue.h index 158784dd189a..fb3993894536 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.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, }; @@ -96,7 +99,9 @@ enum wq_misc_consts { }; /* 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. */ /** @@ -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 @@ -559,6 +567,14 @@ 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 +682,32 @@ 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..112d806ddbe4 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -355,6 +355,7 @@ int dirtytime_interval_handler(struct ctl_table *table, int write, 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/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/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/zswap.h b/include/linux/zswap.h index 341aea490070..2a85b941db97 100644 --- a/include/linux/zswap.h +++ b/include/linux/zswap.h @@ -7,7 +7,6 @@ struct lruvec; -extern u64 zswap_pool_total_size; extern atomic_t zswap_stored_pages; #ifdef CONFIG_ZSWAP @@ -27,6 +26,7 @@ struct zswap_lruvec_state { atomic_long_t nr_zswap_protected; }; +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); |