diff options
Diffstat (limited to 'include/linux')
37 files changed, 365 insertions, 392 deletions
diff --git a/include/linux/audit.h b/include/linux/audit.h index d06134ac6245..cece70231138 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -339,7 +339,7 @@ static inline void audit_uring_entry(u8 op) } static inline void audit_uring_exit(int success, long code) { - if (unlikely(!audit_dummy_context())) + if (unlikely(audit_context())) __audit_uring_exit(success, code); } static inline void audit_syscall_entry(int major, unsigned long a0, diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 87ce24d238f3..2bd073fa6bb5 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -17,8 +17,6 @@ #include <linux/backing-dev-defs.h> #include <linux/slab.h> -struct blkcg; - static inline struct backing_dev_info *bdi_get(struct backing_dev_info *bdi) { kref_get(&bdi->refcnt); @@ -154,7 +152,7 @@ struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css, gfp_t gfp); void wb_memcg_offline(struct mem_cgroup *memcg); -void wb_blkcg_offline(struct blkcg *blkcg); +void wb_blkcg_offline(struct cgroup_subsys_state *css); /** * inode_cgwb_enabled - test whether cgroup writeback is enabled on an inode @@ -378,7 +376,7 @@ static inline void wb_memcg_offline(struct mem_cgroup *memcg) { } -static inline void wb_blkcg_offline(struct blkcg *blkcg) +static inline void wb_blkcg_offline(struct cgroup_subsys_state *css) { } diff --git a/include/linux/bio.h b/include/linux/bio.h index 00450fd86bb4..1cf3738ef1ea 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -408,9 +408,7 @@ extern int bioset_init_from_src(struct bio_set *bs, struct bio_set *src); struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs, unsigned int opf, gfp_t gfp_mask, struct bio_set *bs); -struct bio *bio_alloc_kiocb(struct kiocb *kiocb, struct block_device *bdev, - unsigned short nr_vecs, unsigned int opf, struct bio_set *bs); -struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned short nr_iovecs); +struct bio *bio_kmalloc(unsigned short nr_vecs, gfp_t gfp_mask); extern void bio_put(struct bio *); struct bio *bio_alloc_clone(struct block_device *bdev, struct bio *bio_src, @@ -785,6 +783,12 @@ static inline void bio_set_polled(struct bio *bio, struct kiocb *kiocb) bio->bi_opf |= REQ_NOWAIT; } +static inline void bio_clear_polled(struct bio *bio) +{ + /* can't support alloc cache if we turn off polling */ + bio->bi_opf &= ~(REQ_POLLED | REQ_ALLOC_CACHE); +} + struct bio *blk_next_bio(struct bio *bio, struct block_device *bdev, unsigned int nr_pages, unsigned int opf, gfp_t gfp); diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 652cd05b0924..9f40dbc65f82 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -14,265 +14,39 @@ * Nauman Rafique <nauman@google.com> */ -#include <linux/cgroup.h> -#include <linux/percpu.h> -#include <linux/percpu_counter.h> -#include <linux/u64_stats_sync.h> -#include <linux/seq_file.h> -#include <linux/radix-tree.h> -#include <linux/blkdev.h> -#include <linux/atomic.h> -#include <linux/kthread.h> -#include <linux/fs.h> +#include <linux/types.h> + +struct bio; +struct cgroup_subsys_state; +struct request_queue; #define FC_APPID_LEN 129 #ifdef CONFIG_BLK_CGROUP - -enum blkg_iostat_type { - BLKG_IOSTAT_READ, - BLKG_IOSTAT_WRITE, - BLKG_IOSTAT_DISCARD, - - BLKG_IOSTAT_NR, -}; - -struct blkcg_gq; -struct blkg_policy_data; - -struct blkcg { - struct cgroup_subsys_state css; - spinlock_t lock; - refcount_t online_pin; - - struct radix_tree_root blkg_tree; - struct blkcg_gq __rcu *blkg_hint; - struct hlist_head blkg_list; - - struct blkcg_policy_data *cpd[BLKCG_MAX_POLS]; - - struct list_head all_blkcgs_node; -#ifdef CONFIG_BLK_CGROUP_FC_APPID - char fc_app_id[FC_APPID_LEN]; -#endif -#ifdef CONFIG_CGROUP_WRITEBACK - struct list_head cgwb_list; -#endif -}; - -struct blkg_iostat { - u64 bytes[BLKG_IOSTAT_NR]; - u64 ios[BLKG_IOSTAT_NR]; -}; - -struct blkg_iostat_set { - struct u64_stats_sync sync; - struct blkg_iostat cur; - struct blkg_iostat last; -}; - -/* association between a blk cgroup and a request queue */ -struct blkcg_gq { - /* Pointer to the associated request_queue */ - struct request_queue *q; - struct list_head q_node; - struct hlist_node blkcg_node; - struct blkcg *blkcg; - - /* all non-root blkcg_gq's are guaranteed to have access to parent */ - struct blkcg_gq *parent; - - /* reference count */ - struct percpu_ref refcnt; - - /* is this blkg online? protected by both blkcg and q locks */ - bool online; - - struct blkg_iostat_set __percpu *iostat_cpu; - struct blkg_iostat_set iostat; - - struct blkg_policy_data *pd[BLKCG_MAX_POLS]; - - spinlock_t async_bio_lock; - struct bio_list async_bios; - union { - struct work_struct async_bio_work; - struct work_struct free_work; - }; - - atomic_t use_delay; - atomic64_t delay_nsec; - atomic64_t delay_start; - u64 last_delay; - int last_use; - - struct rcu_head rcu_head; -}; - extern struct cgroup_subsys_state * const blkcg_root_css; -void blkcg_destroy_blkgs(struct blkcg *blkcg); void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay); void blkcg_maybe_throttle_current(void); - -static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css) -{ - return css ? container_of(css, struct blkcg, css) : NULL; -} - -/** - * bio_blkcg - grab the blkcg associated with a bio - * @bio: target bio - * - * This returns the blkcg associated with a bio, %NULL if not associated. - * Callers are expected to either handle %NULL or know association has been - * done prior to calling this. - */ -static inline struct blkcg *bio_blkcg(struct bio *bio) -{ - if (bio && bio->bi_blkg) - return bio->bi_blkg->blkcg; - return NULL; -} - -static inline bool blk_cgroup_congested(void) -{ - struct cgroup_subsys_state *css; - bool ret = false; - - rcu_read_lock(); - css = kthread_blkcg(); - if (!css) - css = task_css(current, io_cgrp_id); - while (css) { - if (atomic_read(&css->cgroup->congestion_count)) { - ret = true; - break; - } - css = css->parent; - } - rcu_read_unlock(); - return ret; -} - -/** - * blkcg_parent - get the parent of a blkcg - * @blkcg: blkcg of interest - * - * Return the parent blkcg of @blkcg. Can be called anytime. - */ -static inline struct blkcg *blkcg_parent(struct blkcg *blkcg) -{ - return css_to_blkcg(blkcg->css.parent); -} - -/** - * blkcg_pin_online - pin online state - * @blkcg: blkcg of interest - * - * While pinned, a blkcg is kept online. This is primarily used to - * impedance-match blkg and cgwb lifetimes so that blkg doesn't go offline - * while an associated cgwb is still active. - */ -static inline void blkcg_pin_online(struct blkcg *blkcg) -{ - refcount_inc(&blkcg->online_pin); -} - -/** - * blkcg_unpin_online - unpin online state - * @blkcg: blkcg of interest - * - * This is primarily used to impedance-match blkg and cgwb lifetimes so - * that blkg doesn't go offline while an associated cgwb is still active. - * When this count goes to zero, all active cgwbs have finished so the - * blkcg can continue destruction by calling blkcg_destroy_blkgs(). - */ -static inline void blkcg_unpin_online(struct blkcg *blkcg) -{ - do { - if (!refcount_dec_and_test(&blkcg->online_pin)) - break; - blkcg_destroy_blkgs(blkcg); - blkcg = blkcg_parent(blkcg); - } while (blkcg); -} +bool blk_cgroup_congested(void); +void blkcg_pin_online(struct cgroup_subsys_state *blkcg_css); +void blkcg_unpin_online(struct cgroup_subsys_state *blkcg_css); +struct list_head *blkcg_get_cgwb_list(struct cgroup_subsys_state *css); +struct cgroup_subsys_state *bio_blkcg_css(struct bio *bio); #else /* CONFIG_BLK_CGROUP */ -struct blkcg { -}; - -struct blkcg_gq { -}; - #define blkcg_root_css ((struct cgroup_subsys_state *)ERR_PTR(-EINVAL)) static inline void blkcg_maybe_throttle_current(void) { } static inline bool blk_cgroup_congested(void) { return false; } - -#ifdef CONFIG_BLOCK static inline void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay) { } -static inline struct blkcg *bio_blkcg(struct bio *bio) { return NULL; } -#endif /* CONFIG_BLOCK */ - -#endif /* CONFIG_BLK_CGROUP */ - -#ifdef CONFIG_BLK_CGROUP_FC_APPID -/* - * Sets the fc_app_id field associted to blkcg - * @app_id: application identifier - * @cgrp_id: cgroup id - * @app_id_len: size of application identifier - */ -static inline int blkcg_set_fc_appid(char *app_id, u64 cgrp_id, size_t app_id_len) -{ - struct cgroup *cgrp; - struct cgroup_subsys_state *css; - struct blkcg *blkcg; - int ret = 0; - - if (app_id_len > FC_APPID_LEN) - return -EINVAL; - - cgrp = cgroup_get_from_id(cgrp_id); - if (!cgrp) - return -ENOENT; - css = cgroup_get_e_css(cgrp, &io_cgrp_subsys); - if (!css) { - ret = -ENOENT; - goto out_cgrp_put; - } - blkcg = css_to_blkcg(css); - /* - * There is a slight race condition on setting the appid. - * Worst case an I/O may not find the right id. - * This is no different from the I/O we let pass while obtaining - * the vmid from the fabric. - * Adding the overhead of a lock is not necessary. - */ - strlcpy(blkcg->fc_app_id, app_id, app_id_len); - css_put(css); -out_cgrp_put: - cgroup_put(cgrp); - return ret; -} - -/** - * blkcg_get_fc_appid - get the fc app identifier associated with a bio - * @bio: target bio - * - * On success return the fc_app_id, on failure return NULL - */ -static inline char *blkcg_get_fc_appid(struct bio *bio) +static inline struct cgroup_subsys_state *bio_blkcg_css(struct bio *bio) { - if (bio && bio->bi_blkg && - (bio->bi_blkg->blkcg->fc_app_id[0] != '\0')) - return bio->bi_blkg->blkcg->fc_app_id; return NULL; } -#else -static inline int blkcg_set_fc_appid(char *buf, u64 id, size_t len) { return -EINVAL; } -static inline char *blkcg_get_fc_appid(struct bio *bio) { return NULL; } -#endif /*CONFIG_BLK_CGROUP_FC_APPID*/ +#endif /* CONFIG_BLK_CGROUP */ + +int blkcg_set_fc_appid(char *app_id, u64 cgrp_id, size_t app_id_len); +char *blkcg_get_fc_appid(struct bio *bio); + #endif /* _BLK_CGROUP_H */ diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 1973ef9bd40f..c007d58d2703 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -44,7 +44,7 @@ struct block_device { unsigned long bd_stamp; bool bd_read_only; /* read-only policy */ dev_t bd_dev; - int bd_openers; + atomic_t bd_openers; struct inode * bd_inode; /* will die */ struct super_block * bd_super; void * bd_claiming; @@ -246,9 +246,8 @@ typedef unsigned int blk_qc_t; struct bio { struct bio *bi_next; /* request queue link */ struct block_device *bi_bdev; - unsigned int bi_opf; /* bottom bits req flags, - * top bits REQ_OP. Use - * accessors. + unsigned int bi_opf; /* bottom bits REQ_OP, top bits + * req_flags. */ unsigned short bi_flags; /* BIO_* below */ unsigned short bi_ioprio; @@ -329,7 +328,6 @@ enum { BIO_QOS_MERGED, /* but went through rq_qos merge path */ BIO_REMAPPED, BIO_ZONE_WRITE_LOCKED, /* Owns a zoned device zone write lock */ - BIO_PERCPU_CACHE, /* can participate in per-cpu alloc cache */ BIO_FLAG_LAST }; @@ -409,15 +407,17 @@ enum req_flag_bits { * work item to avoid such priority inversions. */ __REQ_CGROUP_PUNT, + __REQ_POLLED, /* caller polls for completion using bio_poll */ + __REQ_ALLOC_CACHE, /* allocate IO from cache if available */ + __REQ_SWAP, /* swap I/O */ + __REQ_DRV, /* for driver use */ - /* command specific flags for REQ_OP_WRITE_ZEROES: */ + /* + * Command specific flags, keep last: + */ + /* for REQ_OP_WRITE_ZEROES: */ __REQ_NOUNMAP, /* do not free blocks when zeroing */ - __REQ_POLLED, /* caller polls for completion using bio_poll */ - - /* for driver use */ - __REQ_DRV, - __REQ_SWAP, /* swapping request. */ __REQ_NR_BITS, /* stops here */ }; @@ -439,6 +439,7 @@ enum req_flag_bits { #define REQ_NOUNMAP (1ULL << __REQ_NOUNMAP) #define REQ_POLLED (1ULL << __REQ_POLLED) +#define REQ_ALLOC_CACHE (1ULL << __REQ_ALLOC_CACHE) #define REQ_DRV (1ULL << __REQ_DRV) #define REQ_SWAP (1ULL << __REQ_SWAP) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 60d016138997..5bdf2ac9142c 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -176,6 +176,21 @@ 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 + * + * This returns the number of openers for a disk. Note that this value is only + * stable if disk->open_mutex is held. + * + * Note: Due to a quirk in the block layer open code, each open partition is + * only counted once even if there are multiple openers. + */ +static inline unsigned int disk_openers(struct gendisk *disk) +{ + return atomic_read(&disk->part0->bd_openers); +} + /* * The gendisk is refcounted by the part0 block_device, and the bd_device * therein is also used for device model presentation in sysfs. @@ -248,6 +263,7 @@ struct queue_limits { unsigned int io_opt; unsigned int max_discard_sectors; unsigned int max_hw_discard_sectors; + unsigned int max_secure_erase_sectors; unsigned int max_write_zeroes_sectors; unsigned int max_zone_append_sectors; unsigned int discard_granularity; @@ -540,10 +556,8 @@ struct request_queue { #define QUEUE_FLAG_NONROT 6 /* non-rotational device (SSD) */ #define QUEUE_FLAG_VIRT QUEUE_FLAG_NONROT /* paravirt device */ #define QUEUE_FLAG_IO_STAT 7 /* do disk/partitions IO accounting */ -#define QUEUE_FLAG_DISCARD 8 /* supports DISCARD */ #define QUEUE_FLAG_NOXMERGES 9 /* No extended merges */ #define QUEUE_FLAG_ADD_RANDOM 10 /* Contributes to random pool */ -#define QUEUE_FLAG_SECERASE 11 /* supports secure erase */ #define QUEUE_FLAG_SAME_FORCE 12 /* force complete on same CPU */ #define QUEUE_FLAG_DEAD 13 /* queue tear-down finished */ #define QUEUE_FLAG_INIT_DONE 14 /* queue is initialized */ @@ -582,11 +596,8 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); test_bit(QUEUE_FLAG_STABLE_WRITES, &(q)->queue_flags) #define blk_queue_io_stat(q) test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags) #define blk_queue_add_random(q) test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags) -#define blk_queue_discard(q) test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags) #define blk_queue_zone_resetall(q) \ test_bit(QUEUE_FLAG_ZONE_RESETALL, &(q)->queue_flags) -#define blk_queue_secure_erase(q) \ - (test_bit(QUEUE_FLAG_SECERASE, &(q)->queue_flags)) #define blk_queue_dax(q) test_bit(QUEUE_FLAG_DAX, &(q)->queue_flags) #define blk_queue_pci_p2pdma(q) \ test_bit(QUEUE_FLAG_PCI_P2PDMA, &(q)->queue_flags) @@ -602,7 +613,6 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); REQ_FAILFAST_DRIVER)) #define blk_queue_quiesced(q) test_bit(QUEUE_FLAG_QUIESCED, &(q)->queue_flags) #define blk_queue_pm_only(q) atomic_read(&(q)->pm_only) -#define blk_queue_fua(q) test_bit(QUEUE_FLAG_FUA, &(q)->queue_flags) #define blk_queue_registered(q) test_bit(QUEUE_FLAG_REGISTERED, &(q)->queue_flags) #define blk_queue_nowait(q) test_bit(QUEUE_FLAG_NOWAIT, &(q)->queue_flags) @@ -950,6 +960,8 @@ 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); @@ -1090,13 +1102,12 @@ static inline long nr_blockdev_pages(void) extern void blk_io_schedule(void); -#define BLKDEV_DISCARD_SECURE (1 << 0) /* issue a secure erase */ - -extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector, - sector_t nr_sects, gfp_t gfp_mask, unsigned long flags); -extern int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, - sector_t nr_sects, gfp_t gfp_mask, int flags, - struct bio **biop); +int blkdev_issue_discard(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp_mask); +int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp_mask, struct bio **biop); +int blkdev_issue_secure_erase(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp); #define BLKDEV_ZERO_NOUNMAP (1 << 0) /* do not free blocks */ #define BLKDEV_ZERO_NOFALLBACK (1 << 1) /* don't write explicit zeroes */ @@ -1115,7 +1126,7 @@ static inline int sb_issue_discard(struct super_block *sb, sector_t block, SECTOR_SHIFT), nr_blocks << (sb->s_blocksize_bits - SECTOR_SHIFT), - gfp_mask, flags); + gfp_mask); } static inline int sb_issue_zeroout(struct super_block *sb, sector_t block, sector_t nr_blocks, gfp_t gfp_mask) @@ -1189,6 +1200,12 @@ static inline unsigned int queue_max_zone_append_sectors(const struct request_qu return min(l->max_zone_append_sectors, l->max_sectors); } +static inline unsigned int +bdev_max_zone_append_sectors(struct block_device *bdev) +{ + return queue_max_zone_append_sectors(bdev_get_queue(bdev)); +} + static inline unsigned queue_logical_block_size(const struct request_queue *q) { int retval = 512; @@ -1246,84 +1263,54 @@ bdev_zone_write_granularity(struct block_device *bdev) return queue_zone_write_granularity(bdev_get_queue(bdev)); } -static inline int queue_alignment_offset(const struct request_queue *q) -{ - if (q->limits.misaligned) - return -1; +int bdev_alignment_offset(struct block_device *bdev); +unsigned int bdev_discard_alignment(struct block_device *bdev); - return q->limits.alignment_offset; +static inline unsigned int bdev_max_discard_sectors(struct block_device *bdev) +{ + return bdev_get_queue(bdev)->limits.max_discard_sectors; } -static inline int queue_limit_alignment_offset(struct queue_limits *lim, sector_t sector) +static inline unsigned int bdev_discard_granularity(struct block_device *bdev) { - unsigned int granularity = max(lim->physical_block_size, lim->io_min); - unsigned int alignment = sector_div(sector, granularity >> SECTOR_SHIFT) - << SECTOR_SHIFT; + return bdev_get_queue(bdev)->limits.discard_granularity; +} - return (granularity + lim->alignment_offset - alignment) % granularity; +static inline unsigned int +bdev_max_secure_erase_sectors(struct block_device *bdev) +{ + return bdev_get_queue(bdev)->limits.max_secure_erase_sectors; } -static inline int bdev_alignment_offset(struct block_device *bdev) +static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); - if (q->limits.misaligned) - return -1; - if (bdev_is_partition(bdev)) - return queue_limit_alignment_offset(&q->limits, - bdev->bd_start_sect); - return q->limits.alignment_offset; + if (q) + return q->limits.max_write_zeroes_sectors; + + return 0; } -static inline int queue_discard_alignment(const struct request_queue *q) +static inline bool bdev_nonrot(struct block_device *bdev) { - if (q->limits.discard_misaligned) - return -1; - - return q->limits.discard_alignment; + return blk_queue_nonrot(bdev_get_queue(bdev)); } -static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector_t sector) +static inline bool bdev_stable_writes(struct block_device *bdev) { - unsigned int alignment, granularity, offset; - - if (!lim->max_discard_sectors) - return 0; - - /* Why are these in bytes, not sectors? */ - alignment = lim->discard_alignment >> SECTOR_SHIFT; - granularity = lim->discard_granularity >> SECTOR_SHIFT; - if (!granularity) - return 0; - - /* Offset of the partition start in 'granularity' sectors */ - offset = sector_div(sector, granularity); - - /* And why do we do this modulus *again* in blkdev_issue_discard()? */ - offset = (granularity + alignment - offset) % granularity; - - /* Turn it back into bytes, gaah */ - return offset << SECTOR_SHIFT; + return test_bit(QUEUE_FLAG_STABLE_WRITES, + &bdev_get_queue(bdev)->queue_flags); } -static inline int bdev_discard_alignment(struct block_device *bdev) +static inline bool bdev_write_cache(struct block_device *bdev) { - struct request_queue *q = bdev_get_queue(bdev); - - if (bdev_is_partition(bdev)) - return queue_limit_discard_alignment(&q->limits, - bdev->bd_start_sect); - return q->limits.discard_alignment; + return test_bit(QUEUE_FLAG_WC, &bdev_get_queue(bdev)->queue_flags); } -static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev) +static inline bool bdev_fua(struct block_device *bdev) { - struct request_queue *q = bdev_get_queue(bdev); - - if (q) - return q->limits.max_write_zeroes_sectors; - - return 0; + return test_bit(QUEUE_FLAG_FUA, &bdev_get_queue(bdev)->queue_flags); } static inline enum blk_zoned_model bdev_zoned_model(struct block_device *bdev) @@ -1491,9 +1478,10 @@ static inline void blk_wake_io_task(struct task_struct *waiter) wake_up_process(waiter); } -unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors, - unsigned int op); -void disk_end_io_acct(struct gendisk *disk, unsigned int op, +unsigned long bdev_start_io_acct(struct block_device *bdev, + unsigned int sectors, unsigned int op, + unsigned long start_time); +void bdev_end_io_acct(struct block_device *bdev, unsigned int op, unsigned long start_time); void bio_start_io_acct_time(struct bio *bio, unsigned long start_time); diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 22501a293fa5..623e22492afa 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -27,12 +27,10 @@ struct blk_trace { atomic_t dropped; }; -struct blkcg; - extern int blk_trace_ioctl(struct block_device *, unsigned, char __user *); extern void blk_trace_shutdown(struct request_queue *); -extern __printf(3, 4) -void __trace_note_message(struct blk_trace *, struct blkcg *blkcg, const char *fmt, ...); +__printf(3, 4) void __blk_trace_note_message(struct blk_trace *bt, + struct cgroup_subsys_state *css, const char *fmt, ...); /** * blk_add_trace_msg - Add a (simple) message to the blktrace stream @@ -47,14 +45,14 @@ void __trace_note_message(struct blk_trace *, struct blkcg *blkcg, const char *f * NOTE: Can not use 'static inline' due to presence of var args... * **/ -#define blk_add_cgroup_trace_msg(q, cg, fmt, ...) \ +#define blk_add_cgroup_trace_msg(q, css, fmt, ...) \ do { \ struct blk_trace *bt; \ \ rcu_read_lock(); \ bt = rcu_dereference((q)->blk_trace); \ if (unlikely(bt)) \ - __trace_note_message(bt, cg, fmt, ##__VA_ARGS__);\ + __blk_trace_note_message(bt, css, fmt, ##__VA_ARGS__);\ rcu_read_unlock(); \ } while (0) #define blk_add_trace_msg(q, fmt, ...) \ diff --git a/include/linux/bpf.h b/include/linux/bpf.h index bdb5298735ce..ecc3d3ec41cf 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2085,6 +2085,8 @@ void bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev, struct net_device *netdev); bool bpf_offload_dev_match(struct bpf_prog *prog, struct net_device *netdev); +void unpriv_ebpf_notify(int new_state); + #if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL) int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr); diff --git a/include/linux/cc_platform.h b/include/linux/cc_platform.h index efd8205282da..cb0d6cd1c12f 100644 --- a/include/linux/cc_platform.h +++ b/include/linux/cc_platform.h @@ -72,6 +72,24 @@ enum cc_attr { * Examples include TDX guest & SEV. */ CC_ATTR_GUEST_UNROLL_STRING_IO, + + /** + * @CC_ATTR_SEV_SNP: Guest SNP is active. + * + * The platform/OS is running as a guest/virtual machine and actively + * using AMD SEV-SNP features. + */ + CC_ATTR_GUEST_SEV_SNP, + + /** + * @CC_ATTR_HOTPLUG_DISABLED: Hotplug is not supported or disabled. + * + * The platform/OS is running as a guest/virtual machine does not + * support CPU hotplug feature. + * + * Examples include TDX Guest. + */ + CC_ATTR_HOTPLUG_DISABLED, }; #ifdef CONFIG_ARCH_HAS_CC_PLATFORM diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h index 0a89f111e00e..67caa909e3e6 100644 --- a/include/linux/cdrom.h +++ b/include/linux/cdrom.h @@ -77,7 +77,6 @@ struct cdrom_device_ops { int (*tray_move) (struct cdrom_device_info *, int); int (*lock_door) (struct cdrom_device_info *, int); int (*select_speed) (struct cdrom_device_info *, int); - int (*select_disc) (struct cdrom_device_info *, int); int (*get_last_session) (struct cdrom_device_info *, struct cdrom_multisession *); int (*get_mcn) (struct cdrom_device_info *, diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 3431011f364d..cba8a6ffc329 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -287,6 +287,9 @@ struct ceph_osd_linger_request { rados_watcherrcb_t errcb; void *data; + struct ceph_pagelist *request_pl; + struct page **notify_id_pages; + struct page ***preply_pages; size_t *preply_len; }; diff --git a/include/linux/cper.h b/include/linux/cper.h index 6a511a1078ca..eacb7dd7b3af 100644 --- a/include/linux/cper.h +++ b/include/linux/cper.h @@ -558,6 +558,7 @@ extern const char *const cper_proc_error_type_strs[4]; u64 cper_next_record_id(void); const char *cper_severity_str(unsigned int); const char *cper_mem_err_type_str(unsigned int); +const char *cper_mem_err_status_str(u64 status); void cper_print_bits(const char *prefix, unsigned int bits, const char * const strs[], unsigned int strs_size); void cper_mem_err_pack(const struct cper_sec_mem_err *, @@ -568,5 +569,7 @@ void cper_print_proc_arm(const char *pfx, const struct cper_sec_proc_arm *proc); void cper_print_proc_ia(const char *pfx, const struct cper_sec_proc_ia *proc); +int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg); +int cper_dimm_err_location(struct cper_mem_err_compact *mem, char *msg); #endif diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 35c7d6db4139..d5595d57f4e5 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -1199,7 +1199,6 @@ static inline void sched_cpufreq_governor_change(struct cpufreq_policy *policy, struct cpufreq_governor *old_gov) { } #endif -extern void arch_freq_prepare_all(void); extern unsigned int arch_freq_get_on_cpu(int cpu); #ifndef arch_set_freq_scale diff --git a/include/linux/efi.h b/include/linux/efi.h index ccd4d3f91c98..db424f3dc3f2 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -213,6 +213,8 @@ struct capsule_info { size_t page_bytes_remain; }; +int efi_capsule_setup_info(struct capsule_info *cap_info, void *kbuff, + size_t hdr_bytes); int __efi_capsule_setup_info(struct capsule_info *cap_info); /* @@ -383,6 +385,7 @@ void efi_native_runtime_setup(void); #define EFI_LOAD_FILE_PROTOCOL_GUID EFI_GUID(0x56ec3091, 0x954c, 0x11d2, 0x8e, 0x3f, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b) #define EFI_LOAD_FILE2_PROTOCOL_GUID EFI_GUID(0x4006c0c1, 0xfcb3, 0x403e, 0x99, 0x6d, 0x4a, 0x6c, 0x87, 0x24, 0xe0, 0x6d) #define EFI_RT_PROPERTIES_TABLE_GUID EFI_GUID(0xeb66918a, 0x7eef, 0x402a, 0x84, 0x2e, 0x93, 0x1d, 0x21, 0xc3, 0x8a, 0xe9) +#define EFI_DXE_SERVICES_TABLE_GUID EFI_GUID(0x05ad34ba, 0x6f02, 0x4214, 0x95, 0x2e, 0x4d, 0xa0, 0x39, 0x8e, 0x2b, 0xb9) #define EFI_IMAGE_SECURITY_DATABASE_GUID EFI_GUID(0xd719b2cb, 0x3d3a, 0x4596, 0xa3, 0xbc, 0xda, 0xd0, 0x0e, 0x67, 0x65, 0x6f) #define EFI_SHIM_LOCK_GUID EFI_GUID(0x605dab50, 0xe046, 0x4300, 0xab, 0xb6, 0x3d, 0xd8, 0x10, 0xdd, 0x8b, 0x23) @@ -390,6 +393,7 @@ void efi_native_runtime_setup(void); #define EFI_CERT_SHA256_GUID EFI_GUID(0xc1c41626, 0x504c, 0x4092, 0xac, 0xa9, 0x41, 0xf9, 0x36, 0x93, 0x43, 0x28) #define EFI_CERT_X509_GUID EFI_GUID(0xa5c059a1, 0x94e4, 0x4aa7, 0x87, 0xb5, 0xab, 0x15, 0x5c, 0x2b, 0xf0, 0x72) #define EFI_CERT_X509_SHA256_GUID EFI_GUID(0x3bd2a492, 0x96c0, 0x4079, 0xb4, 0x20, 0xfc, 0xf9, 0x8e, 0xf1, 0x03, 0xed) +#define EFI_CC_BLOB_GUID EFI_GUID(0x067b1f5f, 0xcf26, 0x44c5, 0x85, 0x54, 0x93, 0xd7, 0x77, 0x91, 0x2d, 0x42) /* * This GUID is used to pass to the kernel proper the struct screen_info @@ -405,6 +409,20 @@ void efi_native_runtime_setup(void); #define LINUX_EFI_MEMRESERVE_TABLE_GUID EFI_GUID(0x888eb0c6, 0x8ede, 0x4ff5, 0xa8, 0xf0, 0x9a, 0xee, 0x5c, 0xb9, 0x77, 0xc2) #define LINUX_EFI_INITRD_MEDIA_GUID EFI_GUID(0x5568e427, 0x68fc, 0x4f3d, 0xac, 0x74, 0xca, 0x55, 0x52, 0x31, 0xcc, 0x68) #define LINUX_EFI_MOK_VARIABLE_TABLE_GUID EFI_GUID(0xc451ed2b, 0x9694, 0x45d3, 0xba, 0xba, 0xed, 0x9f, 0x89, 0x88, 0xa3, 0x89) +#define LINUX_EFI_COCO_SECRET_AREA_GUID EFI_GUID(0xadf956ad, 0xe98c, 0x484c, 0xae, 0x11, 0xb5, 0x1c, 0x7d, 0x33, 0x64, 0x47) + +#define RISCV_EFI_BOOT_PROTOCOL_GUID EFI_GUID(0xccd15fec, 0x6f73, 0x4eec, 0x83, 0x95, 0x3e, 0x69, 0xe4, 0xb9, 0x40, 0xbf) + +/* + * This GUID may be installed onto the kernel image's handle as a NULL protocol + * to signal to the stub that the placement of the image should be respected, + * and moving the image in physical memory is undesirable. To ensure + * compatibility with 64k pages kernels with virtually mapped stacks, and to + * avoid defeating physical randomization, this protocol should only be + * installed if the image was placed at a randomized 128k aligned address in + * memory. + */ +#define LINUX_EFI_LOADED_IMAGE_FIXED_GUID EFI_GUID(0xf5a37b6d, 0x3344, 0x42a5, 0xb6, 0xbb, 0x97, 0x86, 0x48, 0xc1, 0x89, 0x0a) /* OEM GUIDs */ #define DELLEMC_EFI_RCI2_TABLE_GUID EFI_GUID(0x2d9f28a2, 0xa886, 0x456a, 0x97, 0xa8, 0xf1, 0x1e, 0xf2, 0x4f, 0xf4, 0x55) @@ -435,6 +453,7 @@ typedef struct { } efi_config_table_type_t; #define EFI_SYSTEM_TABLE_SIGNATURE ((u64)0x5453595320494249ULL) +#define EFI_DXE_SERVICES_TABLE_SIGNATURE ((u64)0x565245535f455844ULL) #define EFI_2_30_SYSTEM_TABLE_REVISION ((2 << 16) | (30)) #define EFI_2_20_SYSTEM_TABLE_REVISION ((2 << 16) | (20)) @@ -596,6 +615,7 @@ extern struct efi { unsigned long tpm_log; /* TPM2 Event Log table */ unsigned long tpm_final_log; /* TPM2 Final Events Log table */ unsigned long mokvar_table; /* MOK variable config table */ + unsigned long coco_secret; /* Confidential computing secret table */ efi_get_time_t *get_time; efi_set_time_t *set_time; @@ -1335,4 +1355,12 @@ extern void efifb_setup_from_dmi(struct screen_info *si, const char *opt); static inline void efifb_setup_from_dmi(struct screen_info *si, const char *opt) { } #endif +struct linux_efi_coco_secret_area { + u64 base_pa; + u64 size; +}; + +/* Header of a populated EFI secret area */ +#define EFI_SECRET_TABLE_HEADER_GUID EFI_GUID(0x1e74f542, 0x71dd, 0x4d66, 0x96, 0x3e, 0xef, 0x42, 0x87, 0xff, 0x17, 0x3b) + #endif /* _LINUX_EFI_H */ diff --git a/include/linux/elfcore.h b/include/linux/elfcore.h index f8e206e82476..346a8b56cdc8 100644 --- a/include/linux/elfcore.h +++ b/include/linux/elfcore.h @@ -84,15 +84,6 @@ static inline void elf_core_copy_regs(elf_gregset_t *elfregs, struct pt_regs *re #endif } -static inline void elf_core_copy_kernel_regs(elf_gregset_t *elfregs, struct pt_regs *regs) -{ -#ifdef ELF_CORE_COPY_KERNEL_REGS - ELF_CORE_COPY_KERNEL_REGS((*elfregs), regs); -#else - elf_core_copy_regs(elfregs, regs); -#endif -} - static inline int elf_core_copy_task_regs(struct task_struct *t, elf_gregset_t* elfregs) { #if defined (ELF_CORE_COPY_TASK_REGS) diff --git a/include/linux/fs.h b/include/linux/fs.h index bbde95387a23..87b5af1d9fbe 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1953,6 +1953,7 @@ struct dir_context { #define REMAP_FILE_ADVISORY (REMAP_FILE_CAN_SHORTEN) struct iov_iter; +struct io_uring_cmd; struct file_operations { struct module *owner; @@ -1995,6 +1996,7 @@ struct file_operations { struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); int (*fadvise)(struct file *, loff_t, loff_t, int); + int (*uring_cmd)(struct io_uring_cmd *ioucmd, unsigned int issue_flags); } __randomize_layout; struct inode_operations { diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 874aabd270c9..cb689264f3e9 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -588,6 +588,22 @@ void gpiochip_relres_irq(struct gpio_chip *gc, unsigned int offset); void gpiochip_disable_irq(struct gpio_chip *gc, unsigned int offset); void gpiochip_enable_irq(struct gpio_chip *gc, unsigned int offset); +/* irq_data versions of the above */ +int gpiochip_irq_reqres(struct irq_data *data); +void gpiochip_irq_relres(struct irq_data *data); + +/* Paste this in your irq_chip structure */ +#define GPIOCHIP_IRQ_RESOURCE_HELPERS \ + .irq_request_resources = gpiochip_irq_reqres, \ + .irq_release_resources = gpiochip_irq_relres + +static inline void gpio_irq_chip_set_chip(struct gpio_irq_chip *girq, + const struct irq_chip *chip) +{ + /* Yes, dropping const is ugly, but it isn't like we have a choice */ + girq->chip = (struct irq_chip *)chip; +} + /* Line status inquiry for drivers */ bool gpiochip_line_is_open_drain(struct gpio_chip *gc, unsigned int offset); bool gpiochip_line_is_open_source(struct gpio_chip *gc, unsigned int offset); diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 1814e698d861..4a2f6cc5a492 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -5,11 +5,37 @@ #include <linux/sched.h> #include <linux/xarray.h> +enum io_uring_cmd_flags { + IO_URING_F_COMPLETE_DEFER = 1, + IO_URING_F_UNLOCKED = 2, + /* int's last bit, sign checks are usually faster than a bit test */ + IO_URING_F_NONBLOCK = INT_MIN, + + /* ctx state flags, for URING_CMD */ + IO_URING_F_SQE128 = 4, + IO_URING_F_CQE32 = 8, + IO_URING_F_IOPOLL = 16, +}; + +struct io_uring_cmd { + struct file *file; + const void *cmd; + /* callback to defer completions to task context */ + void (*task_work_cb)(struct io_uring_cmd *cmd); + u32 cmd_op; + u32 pad; + u8 pdu[32]; /* available inline for free use */ +}; + #if defined(CONFIG_IO_URING) +void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, ssize_t res2); +void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd, + void (*task_work_cb)(struct io_uring_cmd *)); struct sock *io_uring_get_socket(struct file *file); 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); static inline void io_uring_files_cancel(void) { @@ -29,6 +55,14 @@ static inline void io_uring_free(struct task_struct *tsk) __io_uring_free(tsk); } #else +static inline void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, + ssize_t ret2) +{ +} +static inline void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd, + void (*task_work_cb)(struct io_uring_cmd *)) +{ +} static inline struct sock *io_uring_get_socket(struct file *file) { return NULL; @@ -42,6 +76,10 @@ static inline void io_uring_files_cancel(void) static inline void io_uring_free(struct task_struct *tsk) { } +static inline const char *io_uring_get_opcode(u8 opcode) +{ + return ""; +} #endif #endif diff --git a/include/linux/irq.h b/include/linux/irq.h index f92788ccdba2..505308253d23 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -569,6 +569,7 @@ struct irq_chip { * IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND: Invokes __enable_irq()/__disable_irq() for wake irqs * in the suspend path if they are in disabled state * IRQCHIP_AFFINITY_PRE_STARTUP: Default affinity update before startup + * IRQCHIP_IMMUTABLE: Don't ever change anything in this chip */ enum { IRQCHIP_SET_TYPE_MASKED = (1 << 0), @@ -582,6 +583,7 @@ enum { IRQCHIP_SUPPORTS_NMI = (1 << 8), IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND = (1 << 9), IRQCHIP_AFFINITY_PRE_STARTUP = (1 << 10), + IRQCHIP_IMMUTABLE = (1 << 11), }; #include <linux/irqdesc.h> diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 12d91f0dedf9..728691365464 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -127,6 +127,8 @@ #define GICR_PIDR2 GICD_PIDR2 #define GICR_CTLR_ENABLE_LPIS (1UL << 0) +#define GICR_CTLR_CES (1UL << 1) +#define GICR_CTLR_IR (1UL << 2) #define GICR_CTLR_RWP (1UL << 3) #define GICR_TYPER_CPU_NUMBER(r) (((r) >> 8) & 0xffff) diff --git a/include/linux/kthread.h b/include/linux/kthread.h index de5d75bafd66..30e5bec81d2b 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -222,9 +222,5 @@ void kthread_associate_blkcg(struct cgroup_subsys_state *css); struct cgroup_subsys_state *kthread_blkcg(void); #else static inline void kthread_associate_blkcg(struct cgroup_subsys_state *css) { } -static inline struct cgroup_subsys_state *kthread_blkcg(void) -{ - return NULL; -} #endif #endif /* _LINUX_KTHREAD_H */ diff --git a/include/linux/libata.h b/include/linux/libata.h index 9b1d3d8b1252..732de9014626 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -820,7 +820,6 @@ struct ata_port { unsigned int cbl; /* cable type; ATA_CBL_xxx */ struct ata_queued_cmd qcmd[ATA_MAX_QUEUE + 1]; - unsigned long sas_tag_allocated; /* for sas tag allocation only */ u64 qc_active; int nr_active_links; /* #links with active qcs */ unsigned int sas_last_tag; /* track next tag hw expects */ @@ -1111,7 +1110,7 @@ extern void ata_unpack_xfermask(unsigned long xfer_mask, unsigned long *udma_mask); extern u8 ata_xfer_mask2mode(unsigned long xfer_mask); extern unsigned long ata_xfer_mode2mask(u8 xfer_mode); -extern int ata_xfer_mode2shift(unsigned long xfer_mode); +extern int ata_xfer_mode2shift(u8 xfer_mode); extern const char *ata_mode_string(unsigned long xfer_mask); extern unsigned long ata_id_xfermask(const u16 *id); extern int ata_std_qc_defer(struct ata_queued_cmd *qc); diff --git a/include/linux/linkage.h b/include/linux/linkage.h index acb1ad2356f1..1feab6136b5b 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -171,12 +171,9 @@ /* SYM_ALIAS -- use only if you have to */ #ifndef SYM_ALIAS -#define SYM_ALIAS(alias, name, sym_type, linkage) \ - linkage(alias) ASM_NL \ - .set alias, name ASM_NL \ - .type alias sym_type ASM_NL \ - .set .L__sym_size_##alias, .L__sym_size_##name ASM_NL \ - .size alias, .L__sym_size_##alias +#define SYM_ALIAS(alias, name, linkage) \ + linkage(alias) ASM_NL \ + .set alias, name ASM_NL #endif /* === code annotations === */ @@ -261,7 +258,7 @@ */ #ifndef SYM_FUNC_ALIAS #define SYM_FUNC_ALIAS(alias, name) \ - SYM_ALIAS(alias, name, SYM_T_FUNC, SYM_L_GLOBAL) + SYM_ALIAS(alias, name, SYM_L_GLOBAL) #endif /* @@ -269,7 +266,7 @@ */ #ifndef SYM_FUNC_ALIAS_LOCAL #define SYM_FUNC_ALIAS_LOCAL(alias, name) \ - SYM_ALIAS(alias, name, SYM_T_FUNC, SYM_L_LOCAL) + SYM_ALIAS(alias, name, SYM_L_LOCAL) #endif /* @@ -277,7 +274,7 @@ */ #ifndef SYM_FUNC_ALIAS_WEAK #define SYM_FUNC_ALIAS_WEAK(alias, name) \ - SYM_ALIAS(alias, name, SYM_T_FUNC, SYM_L_WEAK) + SYM_ALIAS(alias, name, SYM_L_WEAK) #endif /* SYM_CODE_START -- use for non-C (special) functions */ diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 2c6b9e416225..7c2d77d75a88 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -169,7 +169,7 @@ enum { #define NETIF_F_HW_HSR_FWD __NETIF_F(HW_HSR_FWD) #define NETIF_F_HW_HSR_DUP __NETIF_F(HW_HSR_DUP) -/* Finds the next feature with the highest number of the range of start till 0. +/* Finds the next feature with the highest number of the range of start-1 till 0. */ static inline int find_next_netdev_feature(u64 feature, unsigned long start) { @@ -188,7 +188,7 @@ static inline int find_next_netdev_feature(u64 feature, unsigned long start) for ((bit) = find_next_netdev_feature((mask_addr), \ NETDEV_FEATURE_COUNT); \ (bit) >= 0; \ - (bit) = find_next_netdev_feature((mask_addr), (bit) - 1)) + (bit) = find_next_netdev_feature((mask_addr), (bit))) /* Features valid for ethtool to change */ /* = all defined minus driver/device-class-related */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b1fbe21650bb..f736c020cde2 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -900,7 +900,7 @@ struct net_device_path_stack { struct net_device_path_ctx { const struct net_device *dev; - const u8 *daddr; + u8 daddr[ETH_ALEN]; int num_vlans; struct { diff --git a/include/linux/nvme.h b/include/linux/nvme.h index f626a445d1a8..29ec3e3481ff 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -137,6 +137,7 @@ enum { NVME_REG_CMBMSC = 0x0050, /* Controller Memory Buffer Memory * Space Control */ + NVME_REG_CRTO = 0x0068, /* Controller Ready Timeouts */ NVME_REG_PMRCAP = 0x0e00, /* Persistent Memory Capabilities */ NVME_REG_PMRCTL = 0x0e04, /* Persistent Memory Region Control */ NVME_REG_PMRSTS = 0x0e08, /* Persistent Memory Region Status */ @@ -161,6 +162,9 @@ enum { #define NVME_CMB_BIR(cmbloc) ((cmbloc) & 0x7) #define NVME_CMB_OFST(cmbloc) (((cmbloc) >> 12) & 0xfffff) +#define NVME_CRTO_CRIMT(crto) ((crto) >> 16) +#define NVME_CRTO_CRWMT(crto) ((crto) & 0xffff) + enum { NVME_CMBSZ_SQS = 1 << 0, NVME_CMBSZ_CQS = 1 << 1, @@ -204,8 +208,10 @@ enum { NVME_CC_SHN_MASK = 3 << NVME_CC_SHN_SHIFT, NVME_CC_IOSQES = NVME_NVM_IOSQES << NVME_CC_IOSQES_SHIFT, NVME_CC_IOCQES = NVME_NVM_IOCQES << NVME_CC_IOCQES_SHIFT, - NVME_CAP_CSS_NVM = 1 << 0, - NVME_CAP_CSS_CSI = 1 << 6, + NVME_CC_CRIME = 1 << 24, +}; + +enum { NVME_CSTS_RDY = 1 << 0, NVME_CSTS_CFS = 1 << 1, NVME_CSTS_NSSRO = 1 << 4, @@ -214,10 +220,23 @@ enum { NVME_CSTS_SHST_OCCUR = 1 << 2, NVME_CSTS_SHST_CMPLT = 2 << 2, NVME_CSTS_SHST_MASK = 3 << 2, +}; + +enum { NVME_CMBMSC_CRE = 1 << 0, NVME_CMBMSC_CMSE = 1 << 1, }; +enum { + NVME_CAP_CSS_NVM = 1 << 0, + NVME_CAP_CSS_CSI = 1 << 6, +}; + +enum { + NVME_CAP_CRMS_CRIMS = 1ULL << 59, + NVME_CAP_CRMS_CRWMS = 1ULL << 60, +}; + struct nvme_id_power_state { __le16 max_power; /* centiwatts */ __u8 rsvd2; @@ -405,6 +424,21 @@ struct nvme_id_ns { __u8 vs[3712]; }; +/* I/O Command Set Independent Identify Namespace Data Structure */ +struct nvme_id_ns_cs_indep { + __u8 nsfeat; + __u8 nmic; + __u8 rescap; + __u8 fpi; + __le32 anagrpid; + __u8 nsattr; + __u8 rsvd9; + __le16 nvmsetid; + __le16 endgid; + __u8 nstat; + __u8 rsvd15[4081]; +}; + struct nvme_zns_lbafe { __le64 zsze; __u8 zdes; @@ -469,6 +503,7 @@ enum { NVME_ID_CNS_NS_DESC_LIST = 0x03, NVME_ID_CNS_CS_NS = 0x05, NVME_ID_CNS_CS_CTRL = 0x06, + NVME_ID_CNS_NS_CS_INDEP = 0x08, NVME_ID_CNS_NS_PRESENT_LIST = 0x10, NVME_ID_CNS_NS_PRESENT = 0x11, NVME_ID_CNS_CTRL_NS_LIST = 0x12, @@ -523,6 +558,10 @@ enum { }; enum { + NVME_NSTAT_NRDY = 1 << 0, +}; + +enum { NVME_NVM_NS_16B_GUARD = 0, NVME_NVM_NS_32B_GUARD = 1, NVME_NVM_NS_64B_GUARD = 2, @@ -1583,6 +1622,7 @@ enum { NVME_SC_NS_WRITE_PROTECTED = 0x20, NVME_SC_CMD_INTERRUPTED = 0x21, NVME_SC_TRANSIENT_TR_ERR = 0x22, + NVME_SC_ADMIN_COMMAND_MEDIA_NOT_READY = 0x24, NVME_SC_INVALID_IO_CMD_SET = 0x2C, NVME_SC_LBA_RANGE = 0x80, @@ -1679,9 +1719,11 @@ enum { /* * Path-related Errors: */ + NVME_SC_INTERNAL_PATH_ERROR = 0x300, NVME_SC_ANA_PERSISTENT_LOSS = 0x301, NVME_SC_ANA_INACCESSIBLE = 0x302, NVME_SC_ANA_TRANSITION = 0x303, + NVME_SC_CTRL_PATH_ERROR = 0x360, NVME_SC_HOST_PATH_ERROR = 0x370, NVME_SC_HOST_ABORTED_CMD = 0x371, diff --git a/include/linux/objtool.h b/include/linux/objtool.h index 586d35720f13..b9c1474a571e 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -40,6 +40,8 @@ struct unwind_hint { #ifdef CONFIG_STACK_VALIDATION +#include <asm/asm.h> + #ifndef __ASSEMBLY__ #define UNWIND_HINT(sp_reg, sp_offset, type, end) \ @@ -137,7 +139,7 @@ struct unwind_hint { .macro STACK_FRAME_NON_STANDARD func:req .pushsection .discard.func_stack_frame_non_standard, "aw" - .long \func - . + _ASM_PTR \func .popsection .endm diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index e7c39c200e2b..1a32036c918c 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -196,6 +196,7 @@ void synchronize_rcu_tasks_rude(void); void exit_tasks_rcu_start(void); void exit_tasks_rcu_finish(void); #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */ +#define rcu_tasks_classic_qs(t, preempt) do { } while (0) #define rcu_tasks_qs(t, preempt) do { } while (0) #define rcu_note_voluntary_context_switch(t) do { } while (0) #define call_rcu_tasks call_rcu diff --git a/include/linux/sched.h b/include/linux/sched.h index a8911b1f35aa..6e6174dbf6e8 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -941,6 +941,9 @@ struct task_struct { #ifdef CONFIG_IOMMU_SVA unsigned pasid_activated:1; #endif +#ifdef CONFIG_CPU_SUP_INTEL + unsigned reported_split_lock:1; +#endif unsigned long atomic_flags; /* Flags requiring atomic access. */ @@ -2118,6 +2121,47 @@ static inline void cond_resched_rcu(void) #endif } +#ifdef CONFIG_PREEMPT_DYNAMIC + +extern bool preempt_model_none(void); +extern bool preempt_model_voluntary(void); +extern bool preempt_model_full(void); + +#else + +static inline bool preempt_model_none(void) +{ + return IS_ENABLED(CONFIG_PREEMPT_NONE); +} +static inline bool preempt_model_voluntary(void) +{ + return IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY); +} +static inline bool preempt_model_full(void) +{ + return IS_ENABLED(CONFIG_PREEMPT); +} + +#endif + +static inline bool preempt_model_rt(void) +{ + return IS_ENABLED(CONFIG_PREEMPT_RT); +} + +/* + * Does the preemption model allow non-cooperative preemption? + * + * For !CONFIG_PREEMPT_DYNAMIC kernels this is an exact match with + * CONFIG_PREEMPTION; for CONFIG_PREEMPT_DYNAMIC this doesn't work as the + * kernel is *built* with CONFIG_PREEMPTION=y but may run with e.g. the + * PREEMPT_NONE model. + */ +static inline bool preempt_model_preemptible(void) +{ + return preempt_model_full() || preempt_model_rt(); +} + /* * Does a critical section need to be broken due to another * task waiting?: (technically does not depend on CONFIG_PREEMPTION, diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 3c8b34876744..66b689f6cfcb 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -356,13 +356,22 @@ static inline void clear_notify_signal(void) } /* + * Returns 'true' if kick_process() is needed to force a transition from + * user -> kernel to guarantee expedient run of TWA_SIGNAL based task_work. + */ +static inline bool __set_notify_signal(struct task_struct *task) +{ + return !test_and_set_tsk_thread_flag(task, TIF_NOTIFY_SIGNAL) && + !wake_up_state(task, TASK_INTERRUPTIBLE); +} + +/* * Called to break out of interruptible wait loops, and enter the * exit_to_user_mode_loop(). */ static inline void set_notify_signal(struct task_struct *task) { - if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_SIGNAL) && - !wake_up_state(task, TASK_INTERRUPTIBLE)) + if (__set_notify_signal(task)) kick_process(task); } diff --git a/include/linux/socket.h b/include/linux/socket.h index 6f85f5d957ef..17311ad9f9af 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -50,6 +50,9 @@ struct linger { struct msghdr { void *msg_name; /* ptr to socket address structure */ int msg_namelen; /* size of socket address structure */ + + int msg_inq; /* output, data left in socket */ + struct iov_iter msg_iter; /* data */ /* @@ -62,8 +65,9 @@ struct msghdr { void __user *msg_control_user; }; bool msg_control_is_user : 1; - __kernel_size_t msg_controllen; /* ancillary data buffer length */ + bool msg_get_inq : 1;/* return INQ after receive */ unsigned int msg_flags; /* flags on received message */ + __kernel_size_t msg_controllen; /* ancillary data buffer length */ struct kiocb *msg_iocb; /* ptr to iocb for async requests */ }; @@ -434,6 +438,7 @@ extern struct file *do_accept(struct file *file, unsigned file_flags, extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags); extern int __sys_socket(int family, int type, int protocol); +extern struct file *__sys_socket_file(int family, int type, int protocol); extern int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen); extern int __sys_connect_file(struct file *file, struct sockaddr_storage *addr, int addrlen, int file_flags); diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index cb1f4351e8ba..e3014319d1ad 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -47,11 +47,9 @@ struct srcu_data { */ struct srcu_node { spinlock_t __private lock; - unsigned long srcu_have_cbs[4]; /* GP seq for children */ - /* having CBs, but only */ - /* is > ->srcu_gq_seq. */ - unsigned long srcu_data_have_cbs[4]; /* Which srcu_data structs */ - /* have CBs for given GP? */ + unsigned long srcu_have_cbs[4]; /* GP seq for children having CBs, but only */ + /* if greater than ->srcu_gq_seq. */ + unsigned long srcu_data_have_cbs[4]; /* Which srcu_data structs have CBs for given GP? */ unsigned long srcu_gp_seq_needed_exp; /* Furthest future exp GP. */ struct srcu_node *srcu_parent; /* Next up in tree. */ int grplo; /* Least CPU for node. */ @@ -62,18 +60,24 @@ struct srcu_node { * Per-SRCU-domain structure, similar in function to rcu_state. */ struct srcu_struct { - struct srcu_node node[NUM_RCU_NODES]; /* Combining tree. */ + struct srcu_node *node; /* Combining tree. */ struct srcu_node *level[RCU_NUM_LVLS + 1]; /* First node at each level. */ + int srcu_size_state; /* Small-to-big transition state. */ struct mutex srcu_cb_mutex; /* Serialize CB preparation. */ - spinlock_t __private lock; /* Protect counters */ + spinlock_t __private lock; /* Protect counters and size state. */ struct mutex srcu_gp_mutex; /* Serialize GP work. */ unsigned int srcu_idx; /* Current rdr array element. */ unsigned long srcu_gp_seq; /* Grace-period seq #. */ unsigned long srcu_gp_seq_needed; /* Latest gp_seq needed. */ unsigned long srcu_gp_seq_needed_exp; /* Furthest future exp GP. */ + unsigned long srcu_gp_start; /* Last GP start timestamp (jiffies) */ unsigned long srcu_last_gp_end; /* Last GP end timestamp (ns) */ + unsigned long srcu_size_jiffies; /* Current contention-measurement interval. */ + unsigned long srcu_n_lock_retries; /* Contention events in current interval. */ + unsigned long srcu_n_exp_nodelay; /* # expedited no-delays in current GP phase. */ struct srcu_data __percpu *sda; /* Per-CPU srcu_data array. */ + bool sda_is_static; /* May ->sda be passed to free_percpu()? */ unsigned long srcu_barrier_seq; /* srcu_barrier seq #. */ struct mutex srcu_barrier_mutex; /* Serialize barrier ops. */ struct completion srcu_barrier_completion; @@ -81,10 +85,23 @@ struct srcu_struct { atomic_t srcu_barrier_cpu_cnt; /* # CPUs not yet posting a */ /* callback for the barrier */ /* operation. */ + unsigned long reschedule_jiffies; + unsigned long reschedule_count; struct delayed_work work; struct lockdep_map dep_map; }; +/* Values for size state variable (->srcu_size_state). */ +#define SRCU_SIZE_SMALL 0 +#define SRCU_SIZE_ALLOC 1 +#define SRCU_SIZE_WAIT_BARRIER 2 +#define SRCU_SIZE_WAIT_CALL 3 +#define SRCU_SIZE_WAIT_CBS1 4 +#define SRCU_SIZE_WAIT_CBS2 5 +#define SRCU_SIZE_WAIT_CBS3 6 +#define SRCU_SIZE_WAIT_CBS4 7 +#define SRCU_SIZE_BIG 8 + /* Values for state variable (bottom bits of ->srcu_gp_seq). */ #define SRCU_STATE_IDLE 0 #define SRCU_STATE_SCAN1 1 @@ -121,6 +138,7 @@ struct srcu_struct { #ifdef MODULE # define __DEFINE_SRCU(name, is_static) \ is_static struct srcu_struct name; \ + extern struct srcu_struct * const __srcu_struct_##name; \ struct srcu_struct * const __srcu_struct_##name \ __section("___srcu_struct_ptrs") = &name #else diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index db5149567305..90501404fa49 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -160,7 +160,7 @@ struct rpc_add_xprt_test { #define RPC_CLNT_CREATE_NO_RETRANS_TIMEOUT (1UL << 9) #define RPC_CLNT_CREATE_SOFTERR (1UL << 10) #define RPC_CLNT_CREATE_REUSEPORT (1UL << 11) -#define RPC_CLNT_CREATE_IGNORE_NULL_UNAVAIL (1UL << 12) +#define RPC_CLNT_CREATE_CONNECTED (1UL << 12) struct rpc_clnt *rpc_create(struct rpc_create_args *args); struct rpc_clnt *rpc_bind_new_program(struct rpc_clnt *, diff --git a/include/linux/task_work.h b/include/linux/task_work.h index 897494b597ba..795ef5a68429 100644 --- a/include/linux/task_work.h +++ b/include/linux/task_work.h @@ -17,6 +17,7 @@ enum task_work_notify_mode { TWA_NONE, TWA_RESUME, TWA_SIGNAL, + TWA_SIGNAL_NO_IPI, }; static inline bool task_work_pending(struct task_struct *task) diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 78a98bdff76d..fe1e467ba046 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -177,6 +177,7 @@ static inline u64 ktime_get_raw_ns(void) extern u64 ktime_get_mono_fast_ns(void); extern u64 ktime_get_raw_fast_ns(void); extern u64 ktime_get_boot_fast_ns(void); +extern u64 ktime_get_tai_fast_ns(void); extern u64 ktime_get_real_fast_ns(void); /* diff --git a/include/linux/timer.h b/include/linux/timer.h index fda13c9d1256..648f00105f58 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -196,14 +196,6 @@ extern void init_timers(void); struct hrtimer; extern enum hrtimer_restart it_real_fn(struct hrtimer *); -#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) -struct ctl_table; - -extern unsigned int sysctl_timer_migration; -int timer_migration_handler(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); -#endif - unsigned long __round_jiffies(unsigned long j, int cpu); unsigned long __round_jiffies_relative(unsigned long j, int cpu); unsigned long round_jiffies(unsigned long j); diff --git a/include/linux/torture.h b/include/linux/torture.h index 63fa4196e51c..7038104463e4 100644 --- a/include/linux/torture.h +++ b/include/linux/torture.h @@ -118,7 +118,7 @@ void _torture_stop_kthread(char *m, struct task_struct **tp); _torture_stop_kthread("Stopping " #n " task", &(tp)) #ifdef CONFIG_PREEMPTION -#define torture_preempt_schedule() preempt_schedule() +#define torture_preempt_schedule() __preempt_schedule() #else #define torture_preempt_schedule() do { } while (0) #endif |