diff options
Diffstat (limited to 'include/linux')
128 files changed, 2599 insertions, 649 deletions
diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 4d5ee84c468b..7dd24acd9ffe 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1164,8 +1164,6 @@ int acpi_subsys_suspend_noirq(struct device *dev); int acpi_subsys_suspend(struct device *dev); int acpi_subsys_freeze(struct device *dev); int acpi_subsys_poweroff(struct device *dev); -void acpi_ec_mark_gpe_for_wake(void); -void acpi_ec_set_gpe_wake_mask(u8 action); int acpi_subsys_restore_early(struct device *dev); #else static inline int acpi_subsys_prepare(struct device *dev) { return 0; } @@ -1176,6 +1174,12 @@ static inline int acpi_subsys_suspend(struct device *dev) { return 0; } static inline int acpi_subsys_freeze(struct device *dev) { return 0; } static inline int acpi_subsys_poweroff(struct device *dev) { return 0; } static inline int acpi_subsys_restore_early(struct device *dev) { return 0; } +#endif + +#if defined(CONFIG_ACPI_EC) && defined(CONFIG_PM_SLEEP) +void acpi_ec_mark_gpe_for_wake(void); +void acpi_ec_set_gpe_wake_mask(u8 action); +#else static inline void acpi_ec_mark_gpe_for_wake(void) {} static inline void acpi_ec_set_gpe_wake_mask(u8 action) {} #endif diff --git a/include/linux/alloc_tag.h b/include/linux/alloc_tag.h index 1f0a9ff23a2c..941deffc590d 100644 --- a/include/linux/alloc_tag.h +++ b/include/linux/alloc_tag.h @@ -135,18 +135,21 @@ 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) +static inline bool __alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag) { alloc_tag_add_check(ref, tag); if (!ref || !tag) - return; + return false; ref->ct = &tag->ct; + return true; } -static inline void alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag) +static inline bool alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag) { - __alloc_tag_ref_set(ref, tag); + if (unlikely(!__alloc_tag_ref_set(ref, tag))) + return false; + /* * We need in increment the call counter every time we have a new * allocation or when we split a large allocation into smaller ones. @@ -154,12 +157,13 @@ static inline void alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *t * counter because when we free each part the counter will be decremented. */ this_cpu_inc(tag->counters->calls); + return true; } static inline void alloc_tag_add(union codetag_ref *ref, struct alloc_tag *tag, size_t bytes) { - alloc_tag_ref_set(ref, tag); - this_cpu_add(tag->counters->bytes, bytes); + if (likely(alloc_tag_ref_set(ref, tag))) + this_cpu_add(tag->counters->bytes, bytes); } static inline void alloc_tag_sub(union codetag_ref *ref, size_t bytes) diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h index b721f360d759..4a952c4885ed 100644 --- a/include/linux/arch_topology.h +++ b/include/linux/arch_topology.h @@ -11,10 +11,6 @@ void topology_normalize_cpu_scale(void); int topology_update_cpu_topology(void); -#ifdef CONFIG_ACPI_CPPC_LIB -void topology_init_cpu_capacity_cppc(void); -#endif - struct device_node; bool topology_parse_cpu_capacity(struct device_node *cpu_node, int cpu); diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index f59099a213d0..67f6fdf2e7cd 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -315,8 +315,6 @@ u32 arm_smccc_get_version(void); void __init arm_smccc_version_init(u32 version, enum arm_smccc_conduit conduit); -extern u64 smccc_has_sve_hint; - /** * arm_smccc_get_soc_id_version() * @@ -415,15 +413,6 @@ struct arm_smccc_quirk { }; /** - * __arm_smccc_sve_check() - Set the SVE hint bit when doing SMC calls - * - * Sets the SMCCC hint bit to indicate if there is live state in the SVE - * registers, this modifies x0 in place and should never be called from C - * code. - */ -asmlinkage unsigned long __arm_smccc_sve_check(unsigned long x0); - -/** * __arm_smccc_smc() - make SMC calls * @a0-a7: arguments passed in registers 0 to 7 * @res: result values from registers 0 to 3 @@ -490,20 +479,6 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, #endif -/* nVHE hypervisor doesn't have a current thread so needs separate checks */ -#if defined(CONFIG_ARM64_SVE) && !defined(__KVM_NVHE_HYPERVISOR__) - -#define SMCCC_SVE_CHECK ALTERNATIVE("nop \n", "bl __arm_smccc_sve_check \n", \ - ARM64_SVE) -#define smccc_sve_clobbers "x16", "x30", "cc", - -#else - -#define SMCCC_SVE_CHECK -#define smccc_sve_clobbers - -#endif - #define __constraint_read_2 "r" (arg0) #define __constraint_read_3 __constraint_read_2, "r" (arg1) #define __constraint_read_4 __constraint_read_3, "r" (arg2) @@ -574,12 +549,11 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, register unsigned long r3 asm("r3"); \ CONCATENATE(__declare_arg_, \ COUNT_ARGS(__VA_ARGS__))(__VA_ARGS__); \ - asm volatile(SMCCC_SVE_CHECK \ - inst "\n" : \ + asm volatile(inst "\n" : \ "=r" (r0), "=r" (r1), "=r" (r2), "=r" (r3) \ : CONCATENATE(__constraint_read_, \ COUNT_ARGS(__VA_ARGS__)) \ - : smccc_sve_clobbers "memory"); \ + : "memory"); \ if (___res) \ *___res = (typeof(*___res)){r0, r1, r2, r3}; \ } while (0) @@ -628,7 +602,7 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, asm ("" : \ : CONCATENATE(__constraint_read_, \ COUNT_ARGS(__VA_ARGS__)) \ - : smccc_sve_clobbers "memory"); \ + : "memory"); \ if (___res) \ ___res->a0 = SMCCC_RET_NOT_SUPPORTED; \ } while (0) diff --git a/include/linux/asn1_decoder.h b/include/linux/asn1_decoder.h index 83f9c6e1e5e9..b41bce82a191 100644 --- a/include/linux/asn1_decoder.h +++ b/include/linux/asn1_decoder.h @@ -9,6 +9,7 @@ #define _LINUX_ASN1_DECODER_H #include <linux/asn1.h> +#include <linux/types.h> struct asn1_decoder; diff --git a/include/linux/asn1_encoder.h b/include/linux/asn1_encoder.h index 08cd0c2ad34f..d17484dffb74 100644 --- a/include/linux/asn1_encoder.h +++ b/include/linux/asn1_encoder.h @@ -6,7 +6,6 @@ #include <linux/types.h> #include <linux/asn1.h> #include <linux/asn1_ber_bytecode.h> -#include <linux/bug.h> #define asn1_oid_len(oid) (sizeof(oid)/sizeof(u32)) unsigned char * diff --git a/include/linux/backing-file.h b/include/linux/backing-file.h index 4b61b0e57720..2eed0ffb5e8f 100644 --- a/include/linux/backing-file.h +++ b/include/linux/backing-file.h @@ -16,7 +16,7 @@ struct backing_file_ctx { const struct cred *cred; struct file *user_file; void (*accessed)(struct file *); - void (*end_write)(struct file *); + void (*end_write)(struct file *, loff_t, ssize_t); }; struct file *backing_file_open(const struct path *user_path, int flags, diff --git a/include/linux/bio-integrity.h b/include/linux/bio-integrity.h index dd831c269e99..dbf0f74c1529 100644 --- a/include/linux/bio-integrity.h +++ b/include/linux/bio-integrity.h @@ -72,7 +72,7 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio, gfp_t gfp, unsigned int nr); int bio_integrity_add_page(struct bio *bio, struct page *page, unsigned int len, unsigned int offset); -int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t len, u32 seed); +int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t len); void bio_integrity_unmap_user(struct bio *bio); bool bio_integrity_prep(struct bio *bio); void bio_integrity_advance(struct bio *bio, unsigned int bytes_done); @@ -99,7 +99,7 @@ static inline void bioset_integrity_free(struct bio_set *bs) } static inline int bio_integrity_map_user(struct bio *bio, void __user *ubuf, - ssize_t len, u32 seed) + ssize_t len) { return -EINVAL; } diff --git a/include/linux/bio.h b/include/linux/bio.h index faceadb040f9..60830a6a5939 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -418,8 +418,6 @@ bool __must_check bio_add_folio(struct bio *bio, struct folio *folio, size_t len, size_t off); extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *, unsigned int, unsigned int); -int bio_add_zone_append_page(struct bio *bio, struct page *page, - unsigned int len, unsigned int offset); void __bio_add_page(struct bio *bio, struct page *page, unsigned int len, unsigned int off); void bio_add_folio_nofail(struct bio *bio, struct folio *folio, size_t len, @@ -677,6 +675,23 @@ static inline void bio_clear_polled(struct bio *bio) bio->bi_opf &= ~REQ_POLLED; } +/** + * bio_is_zone_append - is this a zone append bio? + * @bio: bio to check + * + * Check if @bio is a zone append operation. Core block layer code and end_io + * handlers must use this instead of an open coded REQ_OP_ZONE_APPEND check + * because the block layer can rewrite REQ_OP_ZONE_APPEND to REQ_OP_WRITE if + * it is not natively supported. + */ +static inline bool bio_is_zone_append(struct bio *bio) +{ + if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED)) + return false; + return bio_op(bio) == REQ_OP_ZONE_APPEND || + bio_flagged(bio, BIO_EMULATES_ZONE_APPEND); +} + struct bio *blk_next_bio(struct bio *bio, struct block_device *bdev, unsigned int nr_pages, blk_opf_t opf, gfp_t gfp); struct bio *bio_chain_and_submit(struct bio *prev, struct bio *new); diff --git a/include/linux/blk-integrity.h b/include/linux/blk-integrity.h index 676f8f860c47..c7eae0bfb013 100644 --- a/include/linux/blk-integrity.h +++ b/include/linux/blk-integrity.h @@ -28,7 +28,7 @@ static inline bool queue_limits_stack_integrity_bdev(struct queue_limits *t, int blk_rq_map_integrity_sg(struct request *, struct scatterlist *); int blk_rq_count_integrity_sg(struct request_queue *, struct bio *); int blk_rq_integrity_map_user(struct request *rq, void __user *ubuf, - ssize_t bytes, u32 seed); + ssize_t bytes); static inline bool blk_integrity_queue_supports_integrity(struct request_queue *q) @@ -104,8 +104,7 @@ static inline int blk_rq_map_integrity_sg(struct request *q, } static inline int blk_rq_integrity_map_user(struct request *rq, void __user *ubuf, - ssize_t bytes, - u32 seed) + ssize_t bytes) { return -EINVAL; } diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 4fecf46ef681..c596e0e4cb75 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -156,9 +156,6 @@ struct request { struct blk_crypto_keyslot *crypt_keyslot; #endif - enum rw_hint write_hint; - unsigned short ioprio; - enum mq_rq_state state; atomic_t ref; @@ -222,7 +219,9 @@ static inline bool blk_rq_is_passthrough(struct request *rq) static inline unsigned short req_get_ioprio(struct request *req) { - return req->ioprio; + if (req->bio) + return req->bio->bi_ioprio; + return 0; } #define rq_data_dir(rq) (op_is_write(req_op(rq)) ? WRITE : READ) @@ -230,62 +229,61 @@ static inline unsigned short req_get_ioprio(struct request *req) #define rq_dma_dir(rq) \ (op_is_write(req_op(rq)) ? DMA_TO_DEVICE : DMA_FROM_DEVICE) -#define rq_list_add(listptr, rq) do { \ - (rq)->rq_next = *(listptr); \ - *(listptr) = rq; \ -} while (0) - -#define rq_list_add_tail(lastpptr, rq) do { \ - (rq)->rq_next = NULL; \ - **(lastpptr) = rq; \ - *(lastpptr) = &rq->rq_next; \ -} while (0) - -#define rq_list_pop(listptr) \ -({ \ - struct request *__req = NULL; \ - if ((listptr) && *(listptr)) { \ - __req = *(listptr); \ - *(listptr) = __req->rq_next; \ - } \ - __req; \ -}) +static inline int rq_list_empty(const struct rq_list *rl) +{ + return rl->head == NULL; +} -#define rq_list_peek(listptr) \ -({ \ - struct request *__req = NULL; \ - if ((listptr) && *(listptr)) \ - __req = *(listptr); \ - __req; \ -}) +static inline void rq_list_init(struct rq_list *rl) +{ + rl->head = NULL; + rl->tail = NULL; +} -#define rq_list_for_each(listptr, pos) \ - for (pos = rq_list_peek((listptr)); pos; pos = rq_list_next(pos)) +static inline void rq_list_add_tail(struct rq_list *rl, struct request *rq) +{ + rq->rq_next = NULL; + if (rl->tail) + rl->tail->rq_next = rq; + else + rl->head = rq; + rl->tail = rq; +} -#define rq_list_for_each_safe(listptr, pos, nxt) \ - for (pos = rq_list_peek((listptr)), nxt = rq_list_next(pos); \ - pos; pos = nxt, nxt = pos ? rq_list_next(pos) : NULL) +static inline void rq_list_add_head(struct rq_list *rl, struct request *rq) +{ + rq->rq_next = rl->head; + rl->head = rq; + if (!rl->tail) + rl->tail = rq; +} -#define rq_list_next(rq) (rq)->rq_next -#define rq_list_empty(list) ((list) == (struct request *) NULL) +static inline struct request *rq_list_pop(struct rq_list *rl) +{ + struct request *rq = rl->head; -/** - * rq_list_move() - move a struct request from one list to another - * @src: The source list @rq is currently in - * @dst: The destination list that @rq will be appended to - * @rq: The request to move - * @prev: The request preceding @rq in @src (NULL if @rq is the head) - */ -static inline void rq_list_move(struct request **src, struct request **dst, - struct request *rq, struct request *prev) + if (rq) { + rl->head = rl->head->rq_next; + if (!rl->head) + rl->tail = NULL; + rq->rq_next = NULL; + } + + return rq; +} + +static inline struct request *rq_list_peek(struct rq_list *rl) { - if (prev) - prev->rq_next = rq->rq_next; - else - *src = rq->rq_next; - rq_list_add(dst, rq); + return rl->head; } +#define rq_list_for_each(rl, pos) \ + for (pos = rq_list_peek((rl)); (pos); pos = pos->rq_next) + +#define rq_list_for_each_safe(rl, pos, nxt) \ + for (pos = rq_list_peek((rl)), nxt = pos->rq_next; \ + pos; pos = nxt, nxt = pos ? pos->rq_next : NULL) + /** * enum blk_eh_timer_return - How the timeout handler should proceed * @BLK_EH_DONE: The block driver completed the command or will complete it at @@ -577,7 +575,7 @@ struct blk_mq_ops { * empty the @rqlist completely, then the rest will be queued * individually by the block layer upon return. */ - void (*queue_rqs)(struct request **rqlist); + void (*queue_rqs)(struct rq_list *rqlist); /** * @get_budget: Reserve budget before queue request, once .queue_rq is @@ -857,12 +855,6 @@ void blk_mq_end_request_batch(struct io_comp_batch *ib); */ static inline bool blk_mq_need_time_stamp(struct request *rq) { - /* - * passthrough io doesn't use iostat accounting, cgroup stats - * and io scheduler functionalities. - */ - if (blk_rq_is_passthrough(rq)) - return false; return (rq->rq_flags & (RQF_IO_STAT | RQF_STATS | RQF_USE_SCHED)); } @@ -892,7 +884,7 @@ static inline bool blk_mq_add_to_batch(struct request *req, else if (iob->complete != complete) return false; iob->need_ts |= blk_mq_need_time_stamp(req); - rq_list_add(&iob->req_list, req); + rq_list_add_tail(&iob->req_list, req); return true; } @@ -925,6 +917,8 @@ void blk_freeze_queue_start(struct request_queue *q); void blk_mq_freeze_queue_wait(struct request_queue *q); int blk_mq_freeze_queue_wait_timeout(struct request_queue *q, unsigned long timeout); +void blk_mq_unfreeze_queue_non_owner(struct request_queue *q); +void blk_freeze_queue_start_non_owner(struct request_queue *q); void blk_mq_map_queues(struct blk_mq_queue_map *qmap); void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues); @@ -989,7 +983,6 @@ static inline void blk_rq_bio_prep(struct request *rq, struct bio *bio, rq->nr_phys_segments = nr_segs; rq->__data_len = bio->bi_iter.bi_size; rq->bio = rq->biotail = bio; - rq->ioprio = bio_prio(bio); } void blk_mq_hctx_set_fq_lock_class(struct blk_mq_hw_ctx *hctx, diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 50c3b959da28..a1fd0ddce5cf 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -25,6 +25,7 @@ #include <linux/uuid.h> #include <linux/xarray.h> #include <linux/file.h> +#include <linux/lockdep.h> struct module; struct request_queue; @@ -194,7 +195,7 @@ struct gendisk { unsigned int nr_zones; unsigned int zone_capacity; unsigned int last_zone_capacity; - unsigned long *conv_zones_bitmap; + unsigned long __rcu *conv_zones_bitmap; unsigned int zone_wplugs_hash_bits; spinlock_t zone_wplugs_lock; struct mempool_s *zone_wplugs_pool; @@ -349,6 +350,9 @@ typedef unsigned int __bitwise blk_flags_t; /* I/O topology is misaligned */ #define BLK_FLAG_MISALIGNED ((__force blk_flags_t)(1u << 1)) +/* passthrough command IO accounting */ +#define BLK_FLAG_IOSTATS_PASSTHROUGH ((__force blk_flags_t)(1u << 2)) + struct queue_limits { blk_features_t features; blk_flags_t flags; @@ -371,6 +375,7 @@ struct queue_limits { unsigned int max_user_discard_sectors; unsigned int max_secure_erase_sectors; unsigned int max_write_zeroes_sectors; + unsigned int max_hw_zone_append_sectors; unsigned int max_zone_append_sectors; unsigned int discard_granularity; unsigned int discard_alignment; @@ -471,6 +476,11 @@ struct request_queue { struct xarray hctx_table; struct percpu_ref q_usage_counter; + struct lock_class_key io_lock_cls_key; + struct lockdep_map io_lockdep_map; + + struct lock_class_key q_lock_cls_key; + struct lockdep_map q_lockdep_map; struct request *last_merge; @@ -566,6 +576,10 @@ struct request_queue { struct throtl_data *td; #endif struct rcu_head rcu_head; +#ifdef CONFIG_LOCKDEP + struct task_struct *mq_freeze_owner; + int mq_freeze_owner_depth; +#endif wait_queue_head_t mq_freeze_wq; /* * Protect concurrent access to q_usage_counter by @@ -617,6 +631,8 @@ void blk_queue_flag_clear(unsigned int flag, struct request_queue *q); test_bit(QUEUE_FLAG_NOXMERGES, &(q)->queue_flags) #define blk_queue_nonrot(q) (!((q)->limits.features & BLK_FEAT_ROTATIONAL)) #define blk_queue_io_stat(q) ((q)->limits.features & BLK_FEAT_IO_STAT) +#define blk_queue_passthrough_stat(q) \ + ((q)->limits.flags & BLK_FLAG_IOSTATS_PASSTHROUGH) #define blk_queue_dax(q) ((q)->limits.features & BLK_FEAT_DAX) #define blk_queue_pci_p2pdma(q) ((q)->limits.features & BLK_FEAT_PCI_P2PDMA) #ifdef CONFIG_BLK_RQ_ALLOC_TIME @@ -725,6 +741,9 @@ static inline unsigned int blk_queue_depth(struct request_queue *q) #define for_each_bio(_bio) \ for (; _bio; _bio = _bio->bi_next) +int __must_check add_disk_fwnode(struct device *parent, struct gendisk *disk, + const struct attribute_group **groups, + struct fwnode_handle *fwnode); int __must_check device_add_disk(struct device *parent, struct gendisk *disk, const struct attribute_group **groups); static inline int __must_check add_disk(struct gendisk *disk) @@ -929,6 +948,7 @@ queue_limits_start_update(struct request_queue *q) int queue_limits_commit_update(struct request_queue *q, struct queue_limits *lim); int queue_limits_set(struct request_queue *q, struct queue_limits *lim); +int blk_validate_limits(struct queue_limits *lim); /** * queue_limits_cancel_update - cancel an atomic update of queue limits @@ -986,6 +1006,11 @@ extern void blk_put_queue(struct request_queue *); void blk_mark_disk_dead(struct gendisk *disk); +struct rq_list { + struct request *head; + struct request *tail; +}; + #ifdef CONFIG_BLOCK /* * blk_plug permits building a queue of related requests by holding the I/O @@ -999,10 +1024,10 @@ void blk_mark_disk_dead(struct gendisk *disk); * blk_flush_plug() is called. */ struct blk_plug { - struct request *mq_list; /* blk-mq requests */ + struct rq_list mq_list; /* blk-mq requests */ /* if ios_left is > 1, we can batch tag/rq allocations */ - struct request *cached_rq; + struct rq_list cached_rqs; u64 cur_ktime; unsigned short nr_ios; @@ -1145,6 +1170,11 @@ enum blk_default_limits { */ #define BLK_DEF_MAX_SECTORS_CAP 2560u +static inline struct queue_limits *bdev_limits(struct block_device *bdev) +{ + return &bdev_get_queue(bdev)->limits; +} + static inline unsigned long queue_segment_boundary(const struct request_queue *q) { return q->limits.seg_boundary_mask; @@ -1185,25 +1215,9 @@ static inline unsigned int queue_max_segment_size(const struct request_queue *q) return q->limits.max_segment_size; } -static inline unsigned int -queue_limits_max_zone_append_sectors(const 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; - - return queue_limits_max_zone_append_sectors(&q->limits); -} - static inline bool queue_emulates_zone_append(struct request_queue *q) { - return blk_queue_is_zoned(q) && !q->limits.max_zone_append_sectors; + return blk_queue_is_zoned(q) && !q->limits.max_hw_zone_append_sectors; } static inline bool bdev_emulates_zone_append(struct block_device *bdev) @@ -1214,7 +1228,7 @@ static inline bool bdev_emulates_zone_append(struct block_device *bdev) static inline unsigned int bdev_max_zone_append_sectors(struct block_device *bdev) { - return queue_max_zone_append_sectors(bdev_get_queue(bdev)); + return bdev_limits(bdev)->max_zone_append_sectors; } static inline unsigned int bdev_max_segments(struct block_device *bdev) @@ -1279,23 +1293,23 @@ unsigned int bdev_discard_alignment(struct block_device *bdev); static inline unsigned int bdev_max_discard_sectors(struct block_device *bdev) { - return bdev_get_queue(bdev)->limits.max_discard_sectors; + return bdev_limits(bdev)->max_discard_sectors; } static inline unsigned int bdev_discard_granularity(struct block_device *bdev) { - return bdev_get_queue(bdev)->limits.discard_granularity; + return bdev_limits(bdev)->discard_granularity; } static inline unsigned int bdev_max_secure_erase_sectors(struct block_device *bdev) { - return bdev_get_queue(bdev)->limits.max_secure_erase_sectors; + return bdev_limits(bdev)->max_secure_erase_sectors; } static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev) { - return bdev_get_queue(bdev)->limits.max_write_zeroes_sectors; + return bdev_limits(bdev)->max_write_zeroes_sectors; } static inline bool bdev_nonrot(struct block_device *bdev) @@ -1331,7 +1345,7 @@ static inline bool bdev_write_cache(struct block_device *bdev) static inline bool bdev_fua(struct block_device *bdev) { - return bdev_get_queue(bdev)->limits.features & BLK_FEAT_FUA; + return bdev_limits(bdev)->features & BLK_FEAT_FUA; } static inline bool bdev_nowait(struct block_device *bdev) @@ -1376,6 +1390,33 @@ static inline bool bdev_is_zone_start(struct block_device *bdev, return bdev_offset_from_zone_start(bdev, sector) == 0; } +/** + * bdev_zone_is_seq - check if a sector belongs to a sequential write zone + * @bdev: block device to check + * @sector: sector number + * + * Check if @sector on @bdev is contained in a sequential write required zone. + */ +static inline bool bdev_zone_is_seq(struct block_device *bdev, sector_t sector) +{ + bool is_seq = false; + +#if IS_ENABLED(CONFIG_BLK_DEV_ZONED) + if (bdev_is_zoned(bdev)) { + struct gendisk *disk = bdev->bd_disk; + unsigned long *bitmap; + + rcu_read_lock(); + bitmap = rcu_dereference(disk->conv_zones_bitmap); + is_seq = !bitmap || + !test_bit(disk_zone_no(disk, sector), bitmap); + rcu_read_unlock(); + } +#endif + + return is_seq; +} + static inline int queue_dma_alignment(const struct request_queue *q) { return q->limits.dma_alignment; @@ -1648,7 +1689,7 @@ int bdev_thaw(struct block_device *bdev); void bdev_fput(struct file *bdev_file); struct io_comp_batch { - struct request *req_list; + struct rq_list req_list; bool need_ts; void (*complete)(struct io_comp_batch *); }; @@ -1674,6 +1715,22 @@ static inline bool bdev_can_atomic_write(struct block_device *bdev) return true; } +static inline unsigned int +bdev_atomic_write_unit_min_bytes(struct block_device *bdev) +{ + if (!bdev_can_atomic_write(bdev)) + return 0; + return queue_atomic_write_unit_min_bytes(bdev_get_queue(bdev)); +} + +static inline unsigned int +bdev_atomic_write_unit_max_bytes(struct block_device *bdev) +{ + if (!bdev_can_atomic_write(bdev)) + return 0; + return queue_atomic_write_unit_max_bytes(bdev_get_queue(bdev)); +} + #define DEFINE_IO_COMP_BATCH(name) struct io_comp_batch name = { } #endif /* _LINUX_BLKDEV_H */ diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 19d8ca8ac960..bdadb0bb6cec 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -635,6 +635,7 @@ enum bpf_type_flag { */ PTR_UNTRUSTED = BIT(6 + BPF_BASE_TYPE_BITS), + /* MEM can be uninitialized. */ MEM_UNINIT = BIT(7 + BPF_BASE_TYPE_BITS), /* DYNPTR points to memory local to the bpf program. */ @@ -700,6 +701,13 @@ enum bpf_type_flag { */ MEM_ALIGNED = BIT(17 + BPF_BASE_TYPE_BITS), + /* MEM is being written to, often combined with MEM_UNINIT. Non-presence + * of MEM_WRITE means that MEM is only being read. MEM_WRITE without the + * MEM_UNINIT means that memory needs to be initialized since it is also + * read. + */ + MEM_WRITE = BIT(18 + BPF_BASE_TYPE_BITS), + __BPF_TYPE_FLAG_MAX, __BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1, }; @@ -758,10 +766,10 @@ enum bpf_arg_type { ARG_PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_SOCKET, ARG_PTR_TO_STACK_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_STACK, ARG_PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_BTF_ID, - /* pointer to memory does not need to be initialized, helper function must fill - * all bytes or clear them in error case. + /* Pointer to memory does not need to be initialized, since helper function + * fills all bytes or clears them in error case. */ - ARG_PTR_TO_UNINIT_MEM = MEM_UNINIT | ARG_PTR_TO_MEM, + ARG_PTR_TO_UNINIT_MEM = MEM_UNINIT | MEM_WRITE | ARG_PTR_TO_MEM, /* Pointer to valid memory of size known at compile time. */ ARG_PTR_TO_FIXED_SIZE_MEM = MEM_FIXED_SIZE | ARG_PTR_TO_MEM, diff --git a/include/linux/bpf_mem_alloc.h b/include/linux/bpf_mem_alloc.h index aaf004d94322..e45162ef59bb 100644 --- a/include/linux/bpf_mem_alloc.h +++ b/include/linux/bpf_mem_alloc.h @@ -33,6 +33,9 @@ int bpf_mem_alloc_percpu_init(struct bpf_mem_alloc *ma, struct obj_cgroup *objcg int bpf_mem_alloc_percpu_unit_init(struct bpf_mem_alloc *ma, int size); void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma); +/* Check the allocation size for kmalloc equivalent allocator */ +int bpf_mem_alloc_check_size(bool percpu, size_t size); + /* kmalloc/kfree equivalent: */ void *bpf_mem_alloc(struct bpf_mem_alloc *ma, size_t size); void bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr); diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 9f2a6b83b49e..fa78f49d4a9a 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -146,6 +146,7 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_XDP, xdp) BPF_LINK_TYPE(BPF_LINK_TYPE_NETFILTER, netfilter) BPF_LINK_TYPE(BPF_LINK_TYPE_TCX, tcx) BPF_LINK_TYPE(BPF_LINK_TYPE_NETKIT, netkit) +BPF_LINK_TYPE(BPF_LINK_TYPE_SOCKMAP, sockmap) #endif #ifdef CONFIG_PERF_EVENTS BPF_LINK_TYPE(BPF_LINK_TYPE_PERF_EVENT, perf) diff --git a/include/linux/ceph/decode.h b/include/linux/ceph/decode.h index 04f3ace5787b..8fc1aed64113 100644 --- a/include/linux/ceph/decode.h +++ b/include/linux/ceph/decode.h @@ -6,7 +6,7 @@ #include <linux/bug.h> #include <linux/slab.h> #include <linux/time.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/ceph/types.h> diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 4497d0a6772c..15fb566d3f46 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -4,7 +4,7 @@ #include <linux/ceph/ceph_debug.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/backing-dev.h> #include <linux/completion.h> #include <linux/exportfs.h> diff --git a/include/linux/cleanup.h b/include/linux/cleanup.h index 038b2d523bf8..966fcc5ff8ef 100644 --- a/include/linux/cleanup.h +++ b/include/linux/cleanup.h @@ -234,7 +234,7 @@ const volatile void * __must_check_fn(const volatile void *val) * DEFINE_CLASS(fdget, struct fd, fdput(_T), fdget(fd), int fd) * * CLASS(fdget, f)(fd); - * if (!fd_file(f)) + * if (fd_empty(f)) * return -EBADF; * * // use 'f' without concern @@ -273,6 +273,12 @@ static inline class_##_name##_t class_##_name##ext##_constructor(_init_args) \ * an anonymous instance of the (guard) class, not recommended for * conditional locks. * + * if_not_guard(name, args...) { <error handling> }: + * convenience macro for conditional guards that calls the statement that + * follows only if the lock was not acquired (typically an error return). + * + * Only for conditional locks. + * * scoped_guard (name, args...) { }: * similar to CLASS(name, scope)(args), except the variable (with the * explicit name 'scope') is declard in a for-loop such that its scope is @@ -285,14 +291,20 @@ static inline class_##_name##_t class_##_name##ext##_constructor(_init_args) \ * similar to scoped_guard(), except it does fail when the lock * acquire fails. * + * Only for conditional locks. */ +#define __DEFINE_CLASS_IS_CONDITIONAL(_name, _is_cond) \ +static __maybe_unused const bool class_##_name##_is_conditional = _is_cond + #define DEFINE_GUARD(_name, _type, _lock, _unlock) \ + __DEFINE_CLASS_IS_CONDITIONAL(_name, false); \ DEFINE_CLASS(_name, _type, if (_T) { _unlock; }, ({ _lock; _T; }), _type _T); \ static inline void * class_##_name##_lock_ptr(class_##_name##_t *_T) \ - { return *_T; } + { return (void *)(__force unsigned long)*_T; } #define DEFINE_GUARD_COND(_name, _ext, _condlock) \ + __DEFINE_CLASS_IS_CONDITIONAL(_name##_ext, true); \ EXTEND_CLASS(_name, _ext, \ ({ void *_t = _T; if (_T && !(_condlock)) _t = NULL; _t; }), \ class_##_name##_t _T) \ @@ -303,16 +315,48 @@ static inline class_##_name##_t class_##_name##ext##_constructor(_init_args) \ CLASS(_name, __UNIQUE_ID(guard)) #define __guard_ptr(_name) class_##_name##_lock_ptr +#define __is_cond_ptr(_name) class_##_name##_is_conditional -#define scoped_guard(_name, args...) \ - for (CLASS(_name, scope)(args), \ - *done = NULL; __guard_ptr(_name)(&scope) && !done; done = (void *)1) - -#define scoped_cond_guard(_name, _fail, args...) \ - for (CLASS(_name, scope)(args), \ - *done = NULL; !done; done = (void *)1) \ - if (!__guard_ptr(_name)(&scope)) _fail; \ - else +/* + * Helper macro for scoped_guard(). + * + * Note that the "!__is_cond_ptr(_name)" part of the condition ensures that + * compiler would be sure that for the unconditional locks the body of the + * loop (caller-provided code glued to the else clause) could not be skipped. + * It is needed because the other part - "__guard_ptr(_name)(&scope)" - is too + * hard to deduce (even if could be proven true for unconditional locks). + */ +#define __scoped_guard(_name, _label, args...) \ + for (CLASS(_name, scope)(args); \ + __guard_ptr(_name)(&scope) || !__is_cond_ptr(_name); \ + ({ goto _label; })) \ + if (0) { \ +_label: \ + break; \ + } else + +#define scoped_guard(_name, args...) \ + __scoped_guard(_name, __UNIQUE_ID(label), args) + +#define __scoped_cond_guard(_name, _fail, _label, args...) \ + for (CLASS(_name, scope)(args); true; ({ goto _label; })) \ + if (!__guard_ptr(_name)(&scope)) { \ + BUILD_BUG_ON(!__is_cond_ptr(_name)); \ + _fail; \ +_label: \ + break; \ + } else + +#define scoped_cond_guard(_name, _fail, args...) \ + __scoped_cond_guard(_name, _fail, __UNIQUE_ID(label), args) + +#define __if_not_guard(_name, _id, args...) \ + BUILD_BUG_ON(!__is_cond_ptr(_name)); \ + CLASS(_name, _id)(args); \ + if (!__guard_ptr(_name)(&_id)) + +#define if_not_guard(_name, args...) \ + __if_not_guard(_name, __UNIQUE_ID(guard), args) /* * Additional helper macros for generating lock guards with types, either for @@ -347,7 +391,7 @@ static inline void class_##_name##_destructor(class_##_name##_t *_T) \ \ static inline void *class_##_name##_lock_ptr(class_##_name##_t *_T) \ { \ - return _T->lock; \ + return (void *)(__force unsigned long)_T->lock; \ } @@ -369,14 +413,17 @@ static inline class_##_name##_t class_##_name##_constructor(void) \ } #define DEFINE_LOCK_GUARD_1(_name, _type, _lock, _unlock, ...) \ +__DEFINE_CLASS_IS_CONDITIONAL(_name, false); \ __DEFINE_UNLOCK_GUARD(_name, _type, _unlock, __VA_ARGS__) \ __DEFINE_LOCK_GUARD_1(_name, _type, _lock) #define DEFINE_LOCK_GUARD_0(_name, _lock, _unlock, ...) \ +__DEFINE_CLASS_IS_CONDITIONAL(_name, false); \ __DEFINE_UNLOCK_GUARD(_name, void, _unlock, __VA_ARGS__) \ __DEFINE_LOCK_GUARD_0(_name, _lock) #define DEFINE_LOCK_GUARD_1_COND(_name, _ext, _condlock) \ + __DEFINE_CLASS_IS_CONDITIONAL(_name##_ext, true); \ EXTEND_CLASS(_name, _ext, \ ({ class_##_name##_t _t = { .lock = l }, *_T = &_t;\ if (_T->lock && !(_condlock)) _T->lock = NULL; \ diff --git a/include/linux/closure.h b/include/linux/closure.h index 2af44427107d..880fe85e35e9 100644 --- a/include/linux/closure.h +++ b/include/linux/closure.h @@ -454,4 +454,39 @@ do { \ __closure_wait_event(waitlist, _cond); \ } while (0) +#define __closure_wait_event_timeout(waitlist, _cond, _until) \ +({ \ + struct closure cl; \ + long _t; \ + \ + closure_init_stack(&cl); \ + \ + while (1) { \ + closure_wait(waitlist, &cl); \ + if (_cond) { \ + _t = max_t(long, 1L, _until - jiffies); \ + break; \ + } \ + _t = max_t(long, 0L, _until - jiffies); \ + if (!_t) \ + break; \ + closure_sync_timeout(&cl, _t); \ + } \ + closure_wake_up(waitlist); \ + closure_sync(&cl); \ + _t; \ +}) + +/* + * Returns 0 if timeout expired, remaining time in jiffies (at least 1) if + * condition became true + */ +#define closure_wait_event_timeout(waitlist, _cond, _timeout) \ +({ \ + unsigned long _until = jiffies + _timeout; \ + (_cond) \ + ? max_t(long, 1L, _until - jiffies) \ + : __closure_wait_event_timeout(waitlist, _cond, _until);\ +}) + #endif /* _LINUX_CLOSURE_H */ diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index f805adaa316e..cd6f9aae311f 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -80,7 +80,11 @@ #define __noscs __attribute__((__no_sanitize__("shadow-call-stack"))) #endif +#ifdef __SANITIZE_HWADDRESS__ +#define __no_sanitize_address __attribute__((__no_sanitize__("hwaddress"))) +#else #define __no_sanitize_address __attribute__((__no_sanitize_address__)) +#endif #if defined(__SANITIZE_THREAD__) #define __no_sanitize_thread __attribute__((__no_sanitize_thread__)) diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index e0e19d9c1323..7fe0981a7e46 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -1107,10 +1107,9 @@ static inline int parse_perf_domain(int cpu, const char *list_name, const char *cell_name, struct of_phandle_args *args) { - struct device_node *cpu_np; int ret; - cpu_np = of_cpu_device_node_get(cpu); + struct device_node *cpu_np __free(device_node) = of_cpu_device_node_get(cpu); if (!cpu_np) return -ENODEV; @@ -1118,9 +1117,6 @@ static inline int parse_perf_domain(int cpu, const char *list_name, args); if (ret < 0) return ret; - - of_node_put(cpu_np); - return 0; } diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 2361ed4d2b15..f1d151c03164 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -208,7 +208,6 @@ enum cpuhp_state { CPUHP_AP_PERF_X86_UNCORE_ONLINE, CPUHP_AP_PERF_X86_AMD_UNCORE_ONLINE, CPUHP_AP_PERF_X86_AMD_POWER_ONLINE, - CPUHP_AP_PERF_X86_RAPL_ONLINE, CPUHP_AP_PERF_S390_CF_ONLINE, CPUHP_AP_PERF_S390_SF_ONLINE, CPUHP_AP_PERF_ARM_CCI_ONLINE, @@ -227,6 +226,7 @@ enum cpuhp_state { CPUHP_AP_PERF_ARM_APM_XGENE_ONLINE, CPUHP_AP_PERF_ARM_CAVIUM_TX2_UNCORE_ONLINE, CPUHP_AP_PERF_ARM_MARVELL_CN10K_DDR_ONLINE, + CPUHP_AP_PERF_ARM_MRVL_PEM_ONLINE, CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE, CPUHP_AP_PERF_POWERPC_CORE_IMC_ONLINE, CPUHP_AP_PERF_POWERPC_THREAD_IMC_ONLINE, diff --git a/include/linux/device.h b/include/linux/device.h index b4bde8d22697..667cb6db9019 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1078,6 +1078,9 @@ int device_for_each_child(struct device *dev, void *data, int (*fn)(struct device *dev, void *data)); int device_for_each_child_reverse(struct device *dev, void *data, int (*fn)(struct device *dev, void *data)); +int device_for_each_child_reverse_from(struct device *parent, + struct device *from, const void *data, + int (*fn)(struct device *, const void *)); struct device *device_find_child(struct device *dev, void *data, int (*match)(struct device *dev, void *data)); struct device *device_find_child_by_name(struct device *parent, diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 1ff52020cf75..752e0b297582 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -55,6 +55,8 @@ struct em_perf_table { * struct em_perf_domain - Performance domain * @em_table: Pointer to the runtime modifiable em_perf_table * @nr_perf_states: Number of performance states + * @min_perf_state: Minimum allowed Performance State index + * @max_perf_state: Maximum allowed Performance State index * @flags: See "em_perf_domain flags" * @cpus: Cpumask covering the CPUs of the domain. It's here * for performance reasons to avoid potential cache @@ -70,6 +72,8 @@ struct em_perf_table { struct em_perf_domain { struct em_perf_table __rcu *em_table; int nr_perf_states; + int min_perf_state; + int max_perf_state; unsigned long flags; unsigned long cpus[]; }; @@ -173,13 +177,14 @@ void em_table_free(struct em_perf_table __rcu *table); int em_dev_compute_costs(struct device *dev, struct em_perf_state *table, int nr_states); int em_dev_update_chip_binning(struct device *dev); +int em_update_performance_limits(struct em_perf_domain *pd, + unsigned long freq_min_khz, unsigned long freq_max_khz); /** * em_pd_get_efficient_state() - Get an efficient performance state from the EM * @table: List of performance states, in ascending order - * @nr_perf_states: Number of performance states + * @pd: performance domain for which this must be done * @max_util: Max utilization to map with the EM - * @pd_flags: Performance Domain flags * * It is called from the scheduler code quite frequently and as a consequence * doesn't implement any check. @@ -188,13 +193,16 @@ int em_dev_update_chip_binning(struct device *dev); * requirement. */ static inline int -em_pd_get_efficient_state(struct em_perf_state *table, int nr_perf_states, - unsigned long max_util, unsigned long pd_flags) +em_pd_get_efficient_state(struct em_perf_state *table, + struct em_perf_domain *pd, unsigned long max_util) { + unsigned long pd_flags = pd->flags; + int min_ps = pd->min_perf_state; + int max_ps = pd->max_perf_state; struct em_perf_state *ps; int i; - for (i = 0; i < nr_perf_states; i++) { + for (i = min_ps; i <= max_ps; i++) { ps = &table[i]; if (ps->performance >= max_util) { if (pd_flags & EM_PERF_DOMAIN_SKIP_INEFFICIENCIES && @@ -204,7 +212,7 @@ em_pd_get_efficient_state(struct em_perf_state *table, int nr_perf_states, } } - return nr_perf_states - 1; + return max_ps; } /** @@ -253,8 +261,7 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd, * requested performance. */ em_table = rcu_dereference(pd->em_table); - i = em_pd_get_efficient_state(em_table->state, pd->nr_perf_states, - max_util, pd->flags); + i = em_pd_get_efficient_state(em_table->state, pd, max_util); ps = &em_table->state[i]; /* @@ -391,6 +398,12 @@ static inline int em_dev_update_chip_binning(struct device *dev) { return -EINVAL; } +static inline +int em_update_performance_limits(struct em_perf_domain *pd, + unsigned long freq_min_khz, unsigned long freq_max_khz) +{ + return -EINVAL; +} #endif #endif diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h index 1e50cdb83ae5..fc61d0205c97 100644 --- a/include/linux/entry-common.h +++ b/include/linux/entry-common.h @@ -64,7 +64,8 @@ #define EXIT_TO_USER_MODE_WORK \ (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE | \ - _TIF_NEED_RESCHED | _TIF_PATCH_PENDING | _TIF_NOTIFY_SIGNAL | \ + _TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY | \ + _TIF_PATCH_PENDING | _TIF_NOTIFY_SIGNAL | \ ARCH_EXIT_TO_USER_MODE_WORK) /** diff --git a/include/linux/entry-kvm.h b/include/linux/entry-kvm.h index 6813171afccb..16149f6625e4 100644 --- a/include/linux/entry-kvm.h +++ b/include/linux/entry-kvm.h @@ -17,8 +17,9 @@ #endif #define XFER_TO_GUEST_MODE_WORK \ - (_TIF_NEED_RESCHED | _TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL | \ - _TIF_NOTIFY_RESUME | ARCH_XFER_TO_GUEST_MODE_WORK) + (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY | _TIF_SIGPENDING | \ + _TIF_NOTIFY_SIGNAL | _TIF_NOTIFY_RESUME | \ + ARCH_XFER_TO_GUEST_MODE_WORK) struct kvm_vcpu; diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 30114c25ad12..ecf203f01034 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -21,7 +21,7 @@ #include <linux/netdevice.h> #include <linux/random.h> #include <linux/crc32.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <asm/bitsperlong.h> #ifdef __KERNEL__ diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h index 3337745d81bd..0c0d00fcd131 100644 --- a/include/linux/eventpoll.h +++ b/include/linux/eventpoll.h @@ -42,7 +42,7 @@ static inline void eventpoll_release(struct file *file) * because the file in on the way to be removed and nobody ( but * eventpoll ) has still a reference to this file. */ - if (likely(!file->f_ep)) + if (likely(!READ_ONCE(file->f_ep))) return; /* diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h index 893a1d21dc1c..1ab165c2939f 100644 --- a/include/linux/exportfs.h +++ b/include/linux/exportfs.h @@ -250,19 +250,6 @@ struct export_operations { unsigned long flags; }; -/** - * exportfs_lock_op_is_async() - export op supports async lock operation - * @export_ops: the nfs export operations to check - * - * Returns true if the nfs export_operations structure has - * EXPORT_OP_ASYNC_LOCK in their flags set - */ -static inline bool -exportfs_lock_op_is_async(const struct export_operations *export_ops) -{ - return export_ops->flags & EXPORT_OP_ASYNC_LOCK; -} - extern int exportfs_encode_inode_fh(struct inode *inode, struct fid *fid, int *max_len, struct inode *parent, int flags); diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h index 2944d4aa413b..c45306a9f007 100644 --- a/include/linux/fdtable.h +++ b/include/linux/fdtable.h @@ -22,7 +22,6 @@ * as this is the granularity returned by copy_fdset(). */ #define NR_OPEN_DEFAULT BITS_PER_LONG -#define NR_OPEN_MAX ~0U struct fdtable { unsigned int max_fds; @@ -93,10 +92,6 @@ static inline struct file *files_lookup_fd_locked(struct files_struct *files, un return files_lookup_fd_raw(files, fd); } -struct file *lookup_fdget_rcu(unsigned int fd); -struct file *task_lookup_fdget_rcu(struct task_struct *task, unsigned int fd); -struct file *task_lookup_next_fdget_rcu(struct task_struct *task, unsigned int *fd); - static inline bool close_on_exec(unsigned int fd, const struct files_struct *files) { return test_bit(fd, files_fdtable(files)->close_on_exec); @@ -106,17 +101,17 @@ struct task_struct; void put_files_struct(struct files_struct *fs); int unshare_files(void); -struct files_struct *dup_fd(struct files_struct *, unsigned, int *) __latent_entropy; +struct fd_range { + unsigned int from, to; +}; +struct files_struct *dup_fd(struct files_struct *, struct fd_range *) __latent_entropy; void do_close_on_exec(struct files_struct *); int iterate_fd(struct files_struct *, unsigned, int (*)(const void *, struct file *, unsigned), const void *); extern int close_fd(unsigned int fd); -extern int __close_range(unsigned int fd, unsigned int max_fd, unsigned int flags); extern struct file *file_close_fd(unsigned int fd); -extern int unshare_fd(unsigned long unshare_flags, unsigned int max_fds, - struct files_struct **new_fdp); extern struct kmem_cache *files_cachep; diff --git a/include/linux/file.h b/include/linux/file.h index f98de143245a..302f11355b10 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -30,12 +30,6 @@ extern struct file *alloc_file_pseudo_noaccount(struct inode *, struct vfsmount extern struct file *alloc_file_clone(struct file *, int flags, const struct file_operations *); -static inline void fput_light(struct file *file, int fput_needed) -{ - if (fput_needed) - fput(file); -} - /* either a reference to struct file + flags * (cloned vs. borrowed, pos locked), with * flags stored in lower bits of value, @@ -72,6 +66,7 @@ static inline void fdput(struct fd fd) extern struct file *fget(unsigned int fd); extern struct file *fget_raw(unsigned int fd); extern struct file *fget_task(struct task_struct *task, unsigned int fd); +extern struct file *fget_task_next(struct task_struct *task, unsigned int *fd); extern void __f_unlock_pos(struct file *); struct fd fdget(unsigned int fd); @@ -87,6 +82,7 @@ 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) +DEFINE_CLASS(fd_pos, struct fd, fdput_pos(_T), fdget_pos(fd), int fd) extern int f_dupfd(unsigned int from, struct file *file, unsigned flags); extern int replace_fd(unsigned fd, struct file *file, unsigned flags); diff --git a/include/linux/file_ref.h b/include/linux/file_ref.h new file mode 100644 index 000000000000..9b3a8d9b17ab --- /dev/null +++ b/include/linux/file_ref.h @@ -0,0 +1,177 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _LINUX_FILE_REF_H +#define _LINUX_FILE_REF_H + +#include <linux/atomic.h> +#include <linux/preempt.h> +#include <linux/types.h> + +/* + * file_ref is a reference count implementation specifically for use by + * files. It takes inspiration from rcuref but differs in key aspects + * such as support for SLAB_TYPESAFE_BY_RCU type caches. + * + * FILE_REF_ONEREF FILE_REF_MAXREF + * 0x0000000000000000UL 0x7FFFFFFFFFFFFFFFUL + * <-------------------valid -------------------> + * + * FILE_REF_SATURATED + * 0x8000000000000000UL 0xA000000000000000UL 0xBFFFFFFFFFFFFFFFUL + * <-----------------------saturation zone----------------------> + * + * FILE_REF_RELEASED FILE_REF_DEAD + * 0xC000000000000000UL 0xE000000000000000UL + * <-------------------dead zone-------------------> + * + * FILE_REF_NOREF + * 0xFFFFFFFFFFFFFFFFUL + */ + +#ifdef CONFIG_64BIT +#define FILE_REF_ONEREF 0x0000000000000000UL +#define FILE_REF_MAXREF 0x7FFFFFFFFFFFFFFFUL +#define FILE_REF_SATURATED 0xA000000000000000UL +#define FILE_REF_RELEASED 0xC000000000000000UL +#define FILE_REF_DEAD 0xE000000000000000UL +#define FILE_REF_NOREF 0xFFFFFFFFFFFFFFFFUL +#else +#define FILE_REF_ONEREF 0x00000000U +#define FILE_REF_MAXREF 0x7FFFFFFFU +#define FILE_REF_SATURATED 0xA0000000U +#define FILE_REF_RELEASED 0xC0000000U +#define FILE_REF_DEAD 0xE0000000U +#define FILE_REF_NOREF 0xFFFFFFFFU +#endif + +typedef struct { +#ifdef CONFIG_64BIT + atomic64_t refcnt; +#else + atomic_t refcnt; +#endif +} file_ref_t; + +/** + * file_ref_init - Initialize a file reference count + * @ref: Pointer to the reference count + * @cnt: The initial reference count typically '1' + */ +static inline void file_ref_init(file_ref_t *ref, unsigned long cnt) +{ + atomic_long_set(&ref->refcnt, cnt - 1); +} + +bool __file_ref_put(file_ref_t *ref, unsigned long cnt); + +/** + * file_ref_get - Acquire one reference on a file + * @ref: Pointer to the reference count + * + * Similar to atomic_inc_not_zero() but saturates at FILE_REF_MAXREF. + * + * Provides full memory ordering. + * + * Return: False if the attempt to acquire a reference failed. This happens + * when the last reference has been put already. True if a reference + * was successfully acquired + */ +static __always_inline __must_check bool file_ref_get(file_ref_t *ref) +{ + /* + * Unconditionally increase the reference count with full + * ordering. The saturation and dead zones provide enough + * tolerance for this. + * + * If this indicates negative the file in question the fail can + * be freed and immediately reused due to SLAB_TYPSAFE_BY_RCU. + * Hence, unconditionally altering the file reference count to + * e.g., reset the file reference count back to the middle of + * the deadzone risk end up marking someone else's file as dead + * behind their back. + * + * It would be possible to do a careful: + * + * cnt = atomic_long_inc_return(); + * if (likely(cnt >= 0)) + * return true; + * + * and then something like: + * + * if (cnt >= FILE_REF_RELEASE) + * atomic_long_try_cmpxchg(&ref->refcnt, &cnt, FILE_REF_DEAD), + * + * to set the value back to the middle of the deadzone. But it's + * practically impossible to go from FILE_REF_DEAD to + * FILE_REF_ONEREF. It would need 2305843009213693952/2^61 + * file_ref_get()s to resurrect such a dead file. + */ + return !atomic_long_add_negative(1, &ref->refcnt); +} + +/** + * file_ref_inc - Acquire one reference on a file + * @ref: Pointer to the reference count + * + * Acquire an additional reference on a file. Warns if the caller didn't + * already hold a reference. + */ +static __always_inline void file_ref_inc(file_ref_t *ref) +{ + long prior = atomic_long_fetch_inc_relaxed(&ref->refcnt); + WARN_ONCE(prior < 0, "file_ref_inc() on a released file reference"); +} + +/** + * file_ref_put -- Release a file reference + * @ref: Pointer to the reference count + * + * Provides release memory ordering, such that prior loads and stores + * are done before, and provides an acquire ordering on success such + * that free() must come after. + * + * Return: True if this was the last reference with no future references + * possible. This signals the caller that it can safely release + * the object which is protected by the reference counter. + * False if there are still active references or the put() raced + * with a concurrent get()/put() pair. Caller is not allowed to + * release the protected object. + */ +static __always_inline __must_check bool file_ref_put(file_ref_t *ref) +{ + long cnt; + + /* + * While files are SLAB_TYPESAFE_BY_RCU and thus file_ref_put() + * calls don't risk UAFs when a file is recyclyed, it is still + * vulnerable to UAFs caused by freeing the whole slab page once + * it becomes unused. Prevent file_ref_put() from being + * preempted protects against this. + */ + guard(preempt)(); + /* + * Unconditionally decrease the reference count. The saturation + * and dead zones provide enough tolerance for this. If this + * fails then we need to handle the last reference drop and + * cases inside the saturation and dead zones. + */ + cnt = atomic_long_dec_return(&ref->refcnt); + if (cnt >= 0) + return false; + return __file_ref_put(ref, cnt); +} + +/** + * file_ref_read - Read the number of file references + * @ref: Pointer to the reference count + * + * Return: The number of held references (0 ... N) + */ +static inline unsigned long file_ref_read(file_ref_t *ref) +{ + unsigned long c = atomic_long_read(&ref->refcnt); + + /* Return 0 if within the DEAD zone. */ + return c >= FILE_REF_RELEASED ? 0 : c + 1; +} + +#endif diff --git a/include/linux/filelock.h b/include/linux/filelock.h index bb44224c6676..c412ded9171e 100644 --- a/include/linux/filelock.h +++ b/include/linux/filelock.h @@ -180,6 +180,11 @@ static inline void locks_wake_up(struct file_lock *fl) wake_up(&fl->c.flc_wait); } +static inline bool locks_can_async_lock(const struct file_operations *fops) +{ + return !fops->lock || fops->fop_flags & FOP_ASYNC_LOCK; +} + /* fs/locks.c */ void locks_free_lock_context(struct inode *inode); void locks_free_lock(struct file_lock *fl); diff --git a/include/linux/folio_queue.h b/include/linux/folio_queue.h index 955680c3bb5f..3abe614ef5f0 100644 --- a/include/linux/folio_queue.h +++ b/include/linux/folio_queue.h @@ -3,6 +3,12 @@ * * Copyright (C) 2024 Red Hat, Inc. All Rights Reserved. * Written by David Howells ([email protected]) + * + * See: + * + * Documentation/core-api/folio_queue.rst + * + * for a description of the API. */ #ifndef _LINUX_FOLIO_QUEUE_H @@ -33,6 +39,13 @@ struct folio_queue { #endif }; +/** + * folioq_init - Initialise a folio queue segment + * @folioq: The segment to initialise + * + * Initialise a folio queue segment. Note that the folio pointers are + * left uninitialised. + */ static inline void folioq_init(struct folio_queue *folioq) { folio_batch_init(&folioq->vec); @@ -43,62 +56,155 @@ static inline void folioq_init(struct folio_queue *folioq) folioq->marks3 = 0; } +/** + * folioq_nr_slots: Query the capacity of a folio queue segment + * @folioq: The segment to query + * + * Query the number of folios that a particular folio queue segment might hold. + * [!] NOTE: This must not be assumed to be the same for every segment! + */ static inline unsigned int folioq_nr_slots(const struct folio_queue *folioq) { return PAGEVEC_SIZE; } +/** + * folioq_count: Query the occupancy of a folio queue segment + * @folioq: The segment to query + * + * Query the number of folios that have been added to a folio queue segment. + * Note that this is not decreased as folios are removed from a segment. + */ static inline unsigned int folioq_count(struct folio_queue *folioq) { return folio_batch_count(&folioq->vec); } +/** + * folioq_full: Query if a folio queue segment is full + * @folioq: The segment to query + * + * Query if a folio queue segment is fully occupied. Note that this does not + * change if folios are removed from a segment. + */ static inline bool folioq_full(struct folio_queue *folioq) { //return !folio_batch_space(&folioq->vec); return folioq_count(folioq) >= folioq_nr_slots(folioq); } +/** + * folioq_is_marked: Check first folio mark in a folio queue segment + * @folioq: The segment to query + * @slot: The slot number of the folio to query + * + * Determine if the first mark is set for the folio in the specified slot in a + * folio queue segment. + */ static inline bool folioq_is_marked(const struct folio_queue *folioq, unsigned int slot) { return test_bit(slot, &folioq->marks); } +/** + * folioq_mark: Set the first mark on a folio in a folio queue segment + * @folioq: The segment to modify + * @slot: The slot number of the folio to modify + * + * Set the first mark for the folio in the specified slot in a folio queue + * segment. + */ static inline void folioq_mark(struct folio_queue *folioq, unsigned int slot) { set_bit(slot, &folioq->marks); } +/** + * folioq_unmark: Clear the first mark on a folio in a folio queue segment + * @folioq: The segment to modify + * @slot: The slot number of the folio to modify + * + * Clear the first mark for the folio in the specified slot in a folio queue + * segment. + */ static inline void folioq_unmark(struct folio_queue *folioq, unsigned int slot) { clear_bit(slot, &folioq->marks); } +/** + * folioq_is_marked2: Check second folio mark in a folio queue segment + * @folioq: The segment to query + * @slot: The slot number of the folio to query + * + * Determine if the second mark is set for the folio in the specified slot in a + * folio queue segment. + */ static inline bool folioq_is_marked2(const struct folio_queue *folioq, unsigned int slot) { return test_bit(slot, &folioq->marks2); } +/** + * folioq_mark2: Set the second mark on a folio in a folio queue segment + * @folioq: The segment to modify + * @slot: The slot number of the folio to modify + * + * Set the second mark for the folio in the specified slot in a folio queue + * segment. + */ static inline void folioq_mark2(struct folio_queue *folioq, unsigned int slot) { set_bit(slot, &folioq->marks2); } +/** + * folioq_unmark2: Clear the second mark on a folio in a folio queue segment + * @folioq: The segment to modify + * @slot: The slot number of the folio to modify + * + * Clear the second mark for the folio in the specified slot in a folio queue + * segment. + */ static inline void folioq_unmark2(struct folio_queue *folioq, unsigned int slot) { clear_bit(slot, &folioq->marks2); } +/** + * folioq_is_marked3: Check third folio mark in a folio queue segment + * @folioq: The segment to query + * @slot: The slot number of the folio to query + * + * Determine if the third mark is set for the folio in the specified slot in a + * folio queue segment. + */ static inline bool folioq_is_marked3(const struct folio_queue *folioq, unsigned int slot) { return test_bit(slot, &folioq->marks3); } +/** + * folioq_mark3: Set the third mark on a folio in a folio queue segment + * @folioq: The segment to modify + * @slot: The slot number of the folio to modify + * + * Set the third mark for the folio in the specified slot in a folio queue + * segment. + */ static inline void folioq_mark3(struct folio_queue *folioq, unsigned int slot) { set_bit(slot, &folioq->marks3); } +/** + * folioq_unmark3: Clear the third mark on a folio in a folio queue segment + * @folioq: The segment to modify + * @slot: The slot number of the folio to modify + * + * Clear the third mark for the folio in the specified slot in a folio queue + * segment. + */ static inline void folioq_unmark3(struct folio_queue *folioq, unsigned int slot) { clear_bit(slot, &folioq->marks3); @@ -111,6 +217,19 @@ static inline unsigned int __folio_order(struct folio *folio) return folio->_flags_1 & 0xff; } +/** + * folioq_append: Add a folio to a folio queue segment + * @folioq: The segment to add to + * @folio: The folio to add + * + * Add a folio to the tail of the sequence in a folio queue segment, increasing + * the occupancy count and returning the slot number for the folio just added. + * The folio size is extracted and stored in the queue and the marks are left + * unmodified. + * + * Note that it's left up to the caller to check that the segment capacity will + * not be exceeded and to extend the queue. + */ static inline unsigned int folioq_append(struct folio_queue *folioq, struct folio *folio) { unsigned int slot = folioq->vec.nr++; @@ -120,6 +239,19 @@ static inline unsigned int folioq_append(struct folio_queue *folioq, struct foli return slot; } +/** + * folioq_append_mark: Add a folio to a folio queue segment + * @folioq: The segment to add to + * @folio: The folio to add + * + * Add a folio to the tail of the sequence in a folio queue segment, increasing + * the occupancy count and returning the slot number for the folio just added. + * The folio size is extracted and stored in the queue, the first mark is set + * and and the second and third marks are left unmodified. + * + * Note that it's left up to the caller to check that the segment capacity will + * not be exceeded and to extend the queue. + */ static inline unsigned int folioq_append_mark(struct folio_queue *folioq, struct folio *folio) { unsigned int slot = folioq->vec.nr++; @@ -130,21 +262,57 @@ static inline unsigned int folioq_append_mark(struct folio_queue *folioq, struct return slot; } +/** + * folioq_folio: Get a folio from a folio queue segment + * @folioq: The segment to access + * @slot: The folio slot to access + * + * Retrieve the folio in the specified slot from a folio queue segment. Note + * that no bounds check is made and if the slot hasn't been added into yet, the + * pointer will be undefined. If the slot has been cleared, NULL will be + * returned. + */ static inline struct folio *folioq_folio(const struct folio_queue *folioq, unsigned int slot) { return folioq->vec.folios[slot]; } +/** + * folioq_folio_order: Get the order of a folio from a folio queue segment + * @folioq: The segment to access + * @slot: The folio slot to access + * + * Retrieve the order of the folio in the specified slot from a folio queue + * segment. Note that no bounds check is made and if the slot hasn't been + * added into yet, the order returned will be 0. + */ static inline unsigned int folioq_folio_order(const struct folio_queue *folioq, unsigned int slot) { return folioq->orders[slot]; } +/** + * folioq_folio_size: Get the size of a folio from a folio queue segment + * @folioq: The segment to access + * @slot: The folio slot to access + * + * Retrieve the size of the folio in the specified slot from a folio queue + * segment. Note that no bounds check is made and if the slot hasn't been + * added into yet, the size returned will be PAGE_SIZE. + */ static inline size_t folioq_folio_size(const struct folio_queue *folioq, unsigned int slot) { return PAGE_SIZE << folioq_folio_order(folioq, slot); } +/** + * folioq_clear: Clear a folio from a folio queue segment + * @folioq: The segment to clear + * @slot: The folio slot to clear + * + * Clear a folio from a sequence in a folio queue segment and clear its marks. + * The occupancy count is left unchanged. + */ static inline void folioq_clear(struct folio_queue *folioq, unsigned int slot) { folioq->vec.folios[slot] = NULL; diff --git a/include/linux/fs.h b/include/linux/fs.h index e3c603d01337..7e29433c5ecc 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -45,6 +45,8 @@ #include <linux/slab.h> #include <linux/maple_tree.h> #include <linux/rw_hint.h> +#include <linux/file_ref.h> +#include <linux/unicode.h> #include <asm/byteorder.h> #include <uapi/linux/fs.h> @@ -623,6 +625,7 @@ is_uncached_acl(struct posix_acl *acl) #define IOP_NOFOLLOW 0x0004 #define IOP_XATTR 0x0008 #define IOP_DEFAULT_READLINK 0x0010 +#define IOP_MGTIME 0x0020 /* * Keep mostly read-only and often accessed (especially for @@ -1005,7 +1008,7 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index) /** * struct file - Represents a file - * @f_count: reference count + * @f_ref: reference count * @f_lock: Protects f_ep, f_flags. Must not be taken from IRQ context. * @f_mode: FMODE_* flags often used in hotpaths * @f_op: file operations @@ -1030,7 +1033,7 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index) * @f_freeptr: Pointer used by SLAB_TYPESAFE_BY_RCU file cache (don't touch.) */ struct file { - atomic_long_t f_count; + file_ref_t f_ref; spinlock_t f_lock; fmode_t f_mode; const struct file_operations *f_op; @@ -1078,15 +1081,14 @@ struct file_handle { static inline struct file *get_file(struct file *f) { - 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"); + file_ref_inc(&f->f_ref); return f; } struct file *get_file_rcu(struct file __rcu **f); struct file *get_file_active(struct file **f); -#define file_count(x) atomic_long_read(&(x)->f_count) +#define file_count(f) file_ref_read(&(f)->f_ref) #define MAX_NON_LFS ((1UL<<31) - 1) @@ -1584,6 +1586,8 @@ static inline bool fsuidgid_has_mapping(struct super_block *sb, struct timespec64 current_time(struct inode *inode); struct timespec64 inode_set_ctime_current(struct inode *inode); +struct timespec64 inode_set_ctime_deleg(struct inode *inode, + struct timespec64 update); static inline time64_t inode_get_atime_sec(const struct inode *inode) { @@ -1653,6 +1657,17 @@ static inline struct timespec64 inode_set_mtime(struct inode *inode, return inode_set_mtime_to_ts(inode, ts); } +/* + * Multigrain timestamps + * + * Conditionally use fine-grained ctime and mtime timestamps when there + * are users actively observing them via getattr. The primary use-case + * for this is NFS clients that use the ctime to distinguish between + * different states of the file, and that are often fooled by multiple + * operations that occur in the same coarse-grained timer tick. + */ +#define I_CTIME_QUERIED ((u32)BIT(31)) + static inline time64_t inode_get_ctime_sec(const struct inode *inode) { return inode->i_ctime_sec; @@ -1660,7 +1675,7 @@ static inline time64_t inode_get_ctime_sec(const struct inode *inode) static inline long inode_get_ctime_nsec(const struct inode *inode) { - return inode->i_ctime_nsec; + return inode->i_ctime_nsec & ~I_CTIME_QUERIED; } static inline struct timespec64 inode_get_ctime(const struct inode *inode) @@ -1671,13 +1686,7 @@ static inline struct timespec64 inode_get_ctime(const struct inode *inode) return ts; } -static inline struct timespec64 inode_set_ctime_to_ts(struct inode *inode, - struct timespec64 ts) -{ - inode->i_ctime_sec = ts.tv_sec; - inode->i_ctime_nsec = ts.tv_nsec; - return ts; -} +struct timespec64 inode_set_ctime_to_ts(struct inode *inode, struct timespec64 ts); /** * inode_set_ctime - set the ctime in the inode @@ -2116,6 +2125,8 @@ struct file_operations { #define FOP_HUGE_PAGES ((__force fop_flags_t)(1 << 4)) /* Treat loff_t as unsigned (e.g., /dev/mem) */ #define FOP_UNSIGNED_OFFSET ((__force fop_flags_t)(1 << 5)) +/* Supports asynchronous lock callbacks */ +#define FOP_ASYNC_LOCK ((__force fop_flags_t)(1 << 6)) /* Wrap a directory iterator that needs exclusive inode access */ int wrap_directory_iterator(struct file *, struct dir_context *, @@ -2542,6 +2553,7 @@ struct file_system_type { #define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */ #define FS_DISALLOW_NOTIFY_PERM 16 /* Disable fanotify permission events */ #define FS_ALLOW_IDMAP 32 /* FS has been updated to handle vfs idmappings. */ +#define FS_MGTIME 64 /* FS uses multigrain timestamps */ #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ int (*init_fs_context)(struct fs_context *); const struct fs_parameter_spec *parameters; @@ -2565,6 +2577,17 @@ struct file_system_type { #define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME) +/** + * is_mgtime: is this inode using multigrain timestamps + * @inode: inode to test for multigrain timestamps + * + * Return true if the inode uses multigrain timestamps, false otherwise. + */ +static inline bool is_mgtime(const struct inode *inode) +{ + return inode->i_opflags & IOP_MGTIME; +} + extern struct dentry *mount_bdev(struct file_system_type *fs_type, int flags, const char *dev_name, void *data, int (*fill_super)(struct super_block *, void *, int)); @@ -2766,6 +2789,16 @@ extern struct filename *getname_flags(const char __user *, int); extern struct filename *getname_uflags(const char __user *, int); extern struct filename *getname(const char __user *); extern struct filename *getname_kernel(const char *); +extern struct filename *__getname_maybe_null(const char __user *); +static inline struct filename *getname_maybe_null(const char __user *name, int flags) +{ + if (!(flags & AT_EMPTY_PATH)) + return getname(name); + + if (!name) + return NULL; + return __getname_maybe_null(name); +} extern void putname(struct filename *name); extern int finish_open(struct file *file, struct dentry *dentry, @@ -3082,7 +3115,12 @@ extern loff_t default_llseek(struct file *file, loff_t offset, int whence); extern loff_t vfs_llseek(struct file *file, loff_t offset, int whence); -extern int inode_init_always(struct super_block *, struct inode *); +extern int inode_init_always_gfp(struct super_block *, struct inode *, gfp_t); +static inline int inode_init_always(struct super_block *sb, struct inode *inode) +{ + return inode_init_always_gfp(sb, inode, GFP_NOFS); +} + extern void inode_init_once(struct inode *); extern void address_space_init_once(struct address_space *mapping); extern struct inode * igrab(struct inode *); @@ -3321,6 +3359,7 @@ extern void page_put_link(void *); extern int page_symlink(struct inode *inode, const char *symname, int len); extern const struct inode_operations page_symlink_inode_operations; extern void kfree_link(void *); +void fill_mg_cmtime(struct kstat *stat, u32 request_mask, struct inode *inode); void generic_fillattr(struct mnt_idmap *, u32, struct inode *, struct kstat *); void generic_fill_statx_attr(struct inode *inode, struct kstat *stat); void generic_fill_statx_atomic_writes(struct kstat *stat, @@ -3451,6 +3490,54 @@ extern int generic_ci_match(const struct inode *parent, const struct qstr *folded_name, const u8 *de_name, u32 de_name_len); +#if IS_ENABLED(CONFIG_UNICODE) +int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str); +int generic_ci_d_compare(const struct dentry *dentry, unsigned int len, + const char *str, const struct qstr *name); + +/** + * generic_ci_validate_strict_name - Check if a given name is suitable + * for a directory + * + * This functions checks if the proposed filename is valid for the + * parent directory. That means that only valid UTF-8 filenames will be + * accepted for casefold directories from filesystems created with the + * strict encoding flag. That also means that any name will be + * accepted for directories that doesn't have casefold enabled, or + * aren't being strict with the encoding. + * + * @dir: inode of the directory where the new file will be created + * @name: name of the new file + * + * Return: + * * True: if the filename is suitable for this directory. It can be + * true if a given name is not suitable for a strict encoding + * directory, but the directory being used isn't strict + * * False if the filename isn't suitable for this directory. This only + * happens when a directory is casefolded and the filesystem is strict + * about its encoding. + */ +static inline bool generic_ci_validate_strict_name(struct inode *dir, struct qstr *name) +{ + if (!IS_CASEFOLDED(dir) || !sb_has_strict_encoding(dir->i_sb)) + return true; + + /* + * A casefold dir must have a encoding set, unless the filesystem + * is corrupted + */ + if (WARN_ON_ONCE(!dir->i_sb->s_encoding)) + return true; + + return !utf8_validate(dir->i_sb->s_encoding, name); +} +#else +static inline bool generic_ci_validate_strict_name(struct inode *dir, struct qstr *name) +{ + return true; +} +#endif + static inline bool sb_has_encoding(const struct super_block *sb) { #if IS_ENABLED(CONFIG_UNICODE) @@ -3721,6 +3808,6 @@ static inline bool vfs_empty_path(int dfd, const char __user *path) return !c; } -bool generic_atomic_write_valid(struct iov_iter *iter, loff_t pos); +int generic_atomic_write_valid(struct kiocb *iocb, struct iov_iter *iter); #endif /* _LINUX_FS_H */ diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index c13e99cbbf81..4b4bfef6f053 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -160,6 +160,12 @@ extern int get_tree_keyed(struct fs_context *fc, int setup_bdev_super(struct super_block *sb, int sb_flags, struct fs_context *fc); + +#define GET_TREE_BDEV_QUIET_LOOKUP 0x0001 +int get_tree_bdev_flags(struct fs_context *fc, + int (*fill_super)(struct super_block *sb, + struct fs_context *fc), unsigned int flags); + extern int get_tree_bdev(struct fs_context *fc, int (*fill_super)(struct super_block *sb, struct fs_context *fc)); diff --git a/include/linux/fs_parser.h b/include/linux/fs_parser.h index 6cf713a7e6c6..3cef566088fc 100644 --- a/include/linux/fs_parser.h +++ b/include/linux/fs_parser.h @@ -28,7 +28,8 @@ typedef int fs_param_type(struct p_log *, */ fs_param_type fs_param_is_bool, fs_param_is_u32, fs_param_is_s32, fs_param_is_u64, fs_param_is_enum, fs_param_is_string, fs_param_is_blob, fs_param_is_blockdev, - fs_param_is_path, fs_param_is_fd, fs_param_is_uid, fs_param_is_gid; + fs_param_is_path, fs_param_is_fd, fs_param_is_uid, fs_param_is_gid, + fs_param_is_file_or_string; /* * Specification of the type of value a parameter wants. @@ -133,6 +134,8 @@ static inline bool fs_validate_description(const char *name, #define fsparam_bdev(NAME, OPT) __fsparam(fs_param_is_blockdev, NAME, OPT, 0, NULL) #define fsparam_path(NAME, OPT) __fsparam(fs_param_is_path, NAME, OPT, 0, NULL) #define fsparam_fd(NAME, OPT) __fsparam(fs_param_is_fd, NAME, OPT, 0, NULL) +#define fsparam_file_or_string(NAME, OPT) \ + __fsparam(fs_param_is_file_or_string, NAME, OPT, 0, NULL) #define fsparam_uid(NAME, OPT) __fsparam(fs_param_is_uid, NAME, OPT, 0, NULL) #define fsparam_gid(NAME, OPT) __fsparam(fs_param_is_gid, NAME, OPT, 0, NULL) diff --git a/include/linux/fsl/enetc_mdio.h b/include/linux/fsl/enetc_mdio.h index df25fffdc0ae..623ccfcbf39c 100644 --- a/include/linux/fsl/enetc_mdio.h +++ b/include/linux/fsl/enetc_mdio.h @@ -59,7 +59,8 @@ static inline int enetc_mdio_read_c45(struct mii_bus *bus, int phy_id, static inline int enetc_mdio_write_c45(struct mii_bus *bus, int phy_id, int devad, int regnum, u16 value) { return -EINVAL; } -struct enetc_hw *enetc_hw_alloc(struct device *dev, void __iomem *port_regs) +static inline struct enetc_hw *enetc_hw_alloc(struct device *dev, + void __iomem *port_regs) { return ERR_PTR(-EINVAL); } #endif diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 8be029bc50b1..3ecf7768e577 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -217,7 +217,6 @@ struct fsnotify_group { #define FSNOTIFY_GROUP_USER 0x01 /* user allocated group */ #define FSNOTIFY_GROUP_DUPS 0x02 /* allow multiple marks per object */ -#define FSNOTIFY_GROUP_NOFS 0x04 /* group lock is not direct reclaim safe */ int flags; unsigned int owner_flags; /* stored flags of mark_mutex owner */ @@ -268,22 +267,19 @@ struct fsnotify_group { static inline void fsnotify_group_lock(struct fsnotify_group *group) { mutex_lock(&group->mark_mutex); - if (group->flags & FSNOTIFY_GROUP_NOFS) - group->owner_flags = memalloc_nofs_save(); + group->owner_flags = memalloc_nofs_save(); } static inline void fsnotify_group_unlock(struct fsnotify_group *group) { - if (group->flags & FSNOTIFY_GROUP_NOFS) - memalloc_nofs_restore(group->owner_flags); + memalloc_nofs_restore(group->owner_flags); mutex_unlock(&group->mark_mutex); } static inline void fsnotify_group_assert_locked(struct fsnotify_group *group) { WARN_ON_ONCE(!mutex_is_locked(&group->mark_mutex)); - if (group->flags & FSNOTIFY_GROUP_NOFS) - WARN_ON_ONCE(!(current->flags & PF_MEMALLOC_NOFS)); + WARN_ON_ONCE(!(current->flags & PF_MEMALLOC_NOFS)); } /* When calling fsnotify tell it if the data is a path or inode */ diff --git a/include/linux/hdmi.h b/include/linux/hdmi.h index 3bb87bf6bc65..455f855bc084 100644 --- a/include/linux/hdmi.h +++ b/include/linux/hdmi.h @@ -59,6 +59,15 @@ enum hdmi_infoframe_type { #define HDMI_DRM_INFOFRAME_SIZE 26 #define HDMI_VENDOR_INFOFRAME_SIZE 4 +/* + * HDMI 1.3a table 5-14 states that the largest InfoFrame_length is 27, + * not including the packet header or checksum byte. We include the + * checksum byte in HDMI_INFOFRAME_HEADER_SIZE, so this should allow + * HDMI_INFOFRAME_SIZE(MAX) to be the largest buffer we could ever need + * for any HDMI infoframe. + */ +#define HDMI_MAX_INFOFRAME_SIZE 27 + #define HDMI_INFOFRAME_SIZE(type) \ (HDMI_INFOFRAME_HEADER_SIZE + HDMI_ ## type ## _INFOFRAME_SIZE) diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h index 9d7754ad5e9b..6dbd0d49628f 100644 --- a/include/linux/hisi_acc_qm.h +++ b/include/linux/hisi_acc_qm.h @@ -229,6 +229,12 @@ struct hisi_qm_status { struct hisi_qm; +enum acc_err_result { + ACC_ERR_NONE, + ACC_ERR_NEED_RESET, + ACC_ERR_RECOVERED, +}; + struct hisi_qm_err_info { char *acpi_rst; u32 msi_wr_port; @@ -257,9 +263,9 @@ struct hisi_qm_err_ini { void (*close_axi_master_ooo)(struct hisi_qm *qm); void (*open_sva_prefetch)(struct hisi_qm *qm); void (*close_sva_prefetch)(struct hisi_qm *qm); - void (*log_dev_hw_err)(struct hisi_qm *qm, u32 err_sts); void (*show_last_dfx_regs)(struct hisi_qm *qm); void (*err_info_init)(struct hisi_qm *qm); + enum acc_err_result (*get_err_result)(struct hisi_qm *qm); }; struct hisi_qm_cap_info { @@ -274,13 +280,25 @@ struct hisi_qm_cap_info { u32 v3_val; }; +struct hisi_qm_cap_query_info { + u32 type; + const char *name; + u32 offset; + u32 v1_val; + u32 v2_val; + u32 v3_val; +}; + struct hisi_qm_cap_record { u32 type; + const char *name; u32 cap_val; }; struct hisi_qm_cap_tables { + u32 qm_cap_size; struct hisi_qm_cap_record *qm_cap_table; + u32 dev_cap_size; struct hisi_qm_cap_record *dev_cap_table; }; @@ -436,37 +454,6 @@ struct hisi_qp { struct uacce_queue *uacce_q; }; -static inline int q_num_set(const char *val, const struct kernel_param *kp, - unsigned int device) -{ - struct pci_dev *pdev; - u32 n, q_num; - int ret; - - if (!val) - return -EINVAL; - - pdev = pci_get_device(PCI_VENDOR_ID_HUAWEI, device, NULL); - if (!pdev) { - q_num = min_t(u32, QM_QNUM_V1, QM_QNUM_V2); - pr_info("No device found currently, suppose queue number is %u\n", - q_num); - } else { - if (pdev->revision == QM_HW_V1) - q_num = QM_QNUM_V1; - else - q_num = QM_QNUM_V2; - - pci_dev_put(pdev); - } - - ret = kstrtou32(val, 10, &n); - if (ret || n < QM_MIN_QNUM || n > q_num) - return -EINVAL; - - return param_set_int(val, kp); -} - static inline int vfs_num_set(const char *val, const struct kernel_param *kp) { u32 n; @@ -526,6 +513,8 @@ static inline void hisi_qm_del_list(struct hisi_qm *qm, struct hisi_qm_list *qm_ mutex_unlock(&qm_list->lock); } +int hisi_qm_q_num_set(const char *val, const struct kernel_param *kp, + unsigned int device); int hisi_qm_init(struct hisi_qm *qm); void hisi_qm_uninit(struct hisi_qm *qm); int hisi_qm_start(struct hisi_qm *qm); @@ -583,6 +572,9 @@ void hisi_qm_regs_dump(struct seq_file *s, struct debugfs_regset32 *regset); u32 hisi_qm_get_hw_info(struct hisi_qm *qm, const struct hisi_qm_cap_info *info_table, u32 index, bool is_read); +u32 hisi_qm_get_cap_value(struct hisi_qm *qm, + const struct hisi_qm_cap_query_info *info_table, + u32 index, bool is_read); int hisi_qm_set_algs(struct hisi_qm *qm, u64 alg_msk, const struct qm_dev_alg *dev_algs, u32 dev_algs_size); diff --git a/include/linux/host1x.h b/include/linux/host1x.h index 9c8119ed13a4..c4dde3aafcac 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -466,6 +466,7 @@ struct host1x_memory_context { refcount_t ref; struct pid *owner; + struct device_dma_parameters dma_parms; struct device dev; u64 dma_mask; u32 stream_id; diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 67d0ab3c3bba..ef5b80e48599 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -322,6 +322,24 @@ struct thpsize { (transparent_hugepage_flags & \ (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG)) +static inline bool vma_thp_disabled(struct vm_area_struct *vma, + unsigned long vm_flags) +{ + /* + * Explicitly disabled through madvise or prctl, or some + * architectures may disable THP for some mappings, for + * example, s390 kvm. + */ + return (vm_flags & VM_NOHUGEPAGE) || + test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags); +} + +static inline bool thp_disabled_by_hw(void) +{ + /* If the hardware/firmware marked hugepage support disabled. */ + return transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_UNSUPPORTED); +} + unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); unsigned long thp_get_unmapped_area_vmflags(struct file *filp, unsigned long addr, diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h index 5c6a421ad580..3a63dff62d03 100644 --- a/include/linux/hwmon.h +++ b/include/linux/hwmon.h @@ -368,7 +368,9 @@ enum hwmon_intrusion_attributes { /** * struct hwmon_ops - hwmon device operations - * @is_visible: Callback to return attribute visibility. Mandatory. + * @visible: Static visibility. If non-zero, 'is_visible' is ignored. + * @is_visible: Callback to return attribute visibility. Mandatory unless + * 'visible' is non-zero. * Parameters are: * @const void *drvdata: * Pointer to driver-private data structure passed @@ -412,6 +414,7 @@ enum hwmon_intrusion_attributes { * The function returns 0 on success or a negative error number. */ struct hwmon_ops { + umode_t visible; umode_t (*is_visible)(const void *drvdata, enum hwmon_sensor_types type, u32 attr, int channel); int (*read)(struct device *dev, enum hwmon_sensor_types type, diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 30cef3b940eb..456bca45ff05 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -20,7 +20,7 @@ #include <linux/etherdevice.h> #include <linux/bitfield.h> #include <asm/byteorder.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* * DS bit usage diff --git a/include/linux/input.h b/include/linux/input.h index 89a0be6ee0e2..cd866b020a01 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -339,12 +339,16 @@ struct input_handler { * @name: name given to the handle by handler that created it * @dev: input device the handle is attached to * @handler: handler that works with the device through this handle + * @handle_events: event sequence handler. It is set up by the input core + * according to event handling method specified in the @handler. See + * input_handle_setup_event_handler(). + * This method is being called by the input core with interrupts disabled + * and dev->event_lock spinlock held and so it may not sleep. * @d_node: used to put the handle on device's list of attached handles * @h_node: used to put the handle on handler's list of handles from which * it gets events */ struct input_handle { - void *private; int open; @@ -353,6 +357,10 @@ struct input_handle { struct input_dev *dev; struct input_handler *handler; + unsigned int (*handle_events)(struct input_handle *handle, + struct input_value *vals, + unsigned int count); + struct list_head d_node; struct list_head h_node; }; diff --git a/include/linux/io_uring/cmd.h b/include/linux/io_uring/cmd.h index c189d36ad55e..578a3fdf5c71 100644 --- a/include/linux/io_uring/cmd.h +++ b/include/linux/io_uring/cmd.h @@ -110,7 +110,7 @@ static inline void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd, static inline struct task_struct *io_uring_cmd_get_task(struct io_uring_cmd *cmd) { - return cmd_to_io_kiocb(cmd)->task; + return cmd_to_io_kiocb(cmd)->tctx->task; } #endif /* _LINUX_IO_URING_CMD_H */ diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 4b9ba523978d..593c10a02144 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -37,6 +37,7 @@ enum io_uring_cmd_flags { /* set when uring wants to cancel a previously issued command */ IO_URING_F_CANCEL = (1 << 11), IO_URING_F_COMPAT = (1 << 12), + IO_URING_F_TASK_DEAD = (1 << 13), }; struct io_wq_work_node { @@ -55,19 +56,18 @@ struct io_wq_work { int cancel_seq; }; -struct io_fixed_file { - /* file * with additional FFS_* flags */ - unsigned long file_ptr; +struct io_rsrc_data { + unsigned int nr; + struct io_rsrc_node **nodes; }; struct io_file_table { - struct io_fixed_file *files; + struct io_rsrc_data data; unsigned long *bitmap; unsigned int alloc_hint; }; struct io_hash_bucket { - spinlock_t lock; struct hlist_head list; } ____cacheline_aligned_in_smp; @@ -76,6 +76,12 @@ struct io_hash_table { unsigned hash_bits; }; +struct io_mapped_region { + struct page **pages; + void *vmap_ptr; + size_t nr_pages; +}; + /* * Arbitrary limit, can be raised if need be */ @@ -85,6 +91,7 @@ struct io_uring_task { /* submission side */ int cached_refs; const struct io_ring_ctx *last; + struct task_struct *task; struct io_wq *io_wq; struct file *registered_rings[IO_RINGFD_REG_MAX]; @@ -270,7 +277,6 @@ struct io_ring_ctx { * Fixed resources fast path, should be accessed only under * uring_lock, and updated through io_uring_register(2) */ - struct io_rsrc_node *rsrc_node; atomic_t cancel_seq; /* @@ -283,15 +289,13 @@ struct io_ring_ctx { struct io_wq_work_list iopoll_list; struct io_file_table file_table; - struct io_mapped_ubuf **user_bufs; - unsigned nr_user_files; - unsigned nr_user_bufs; + struct io_rsrc_data buf_table; struct io_submit_state submit_state; struct xarray io_bl_xa; - struct io_hash_table cancel_table_locked; + struct io_hash_table cancel_table; struct io_alloc_cache apoll_cache; struct io_alloc_cache netmsg_cache; struct io_alloc_cache rw_cache; @@ -302,6 +306,11 @@ struct io_ring_ctx { * ->uring_cmd() by io_uring_cmd_insert_cancelable() */ struct hlist_head cancelable_uring_cmd; + /* + * For Hybrid IOPOLL, runtime in hybrid polling, without + * scheduling time + */ + u64 hybrid_poll_time; } ____cacheline_aligned_in_smp; struct { @@ -316,6 +325,9 @@ struct io_ring_ctx { unsigned cq_entries; struct io_ev_fd __rcu *io_ev_fd; unsigned cq_extra; + + void *cq_wait_arg; + size_t cq_wait_size; } ____cacheline_aligned_in_smp; /* @@ -342,7 +354,6 @@ struct io_ring_ctx { struct list_head io_buffers_comp; struct list_head cq_overflow_list; - struct io_hash_table cancel_table; struct hlist_head waitid_list; @@ -366,16 +377,6 @@ struct io_ring_ctx { struct wait_queue_head poll_wq; struct io_restriction restrictions; - /* slow path rsrc auxilary data, used by update/register */ - struct io_rsrc_data *file_data; - struct io_rsrc_data *buf_data; - - /* protected by ->uring_lock */ - struct list_head rsrc_ref_list; - struct io_alloc_cache rsrc_node_cache; - struct wait_queue_head rsrc_quiesce_wq; - unsigned rsrc_quiesce; - u32 pers_next; struct xarray personalities; @@ -409,7 +410,7 @@ struct io_ring_ctx { /* napi busy poll default timeout */ ktime_t napi_busy_poll_dt; bool napi_prefer_busy_poll; - bool napi_enabled; + u8 napi_track_mode; DECLARE_HASHTABLE(napi_ht, 4); #endif @@ -418,6 +419,13 @@ struct io_ring_ctx { unsigned evfd_last_cq_tail; /* + * Protection for resize vs mmap races - both the mmap and resize + * side will need to grab this lock, to prevent either side from + * being run concurrently with the other. + */ + struct mutex resize_lock; + + /* * If IORING_SETUP_NO_MMAP is used, then the below holds * the gup'ed pages for the two rings, and the sqes. */ @@ -425,6 +433,9 @@ struct io_ring_ctx { unsigned short n_sqe_pages; struct page **ring_pages; struct page **sqe_pages; + + /* used for optimised request parameter and wait argument passing */ + struct io_mapped_region param_region; }; struct io_tw_state { @@ -447,6 +458,7 @@ enum { REQ_F_LINK_TIMEOUT_BIT, REQ_F_NEED_CLEANUP_BIT, REQ_F_POLLED_BIT, + REQ_F_HYBRID_IOPOLL_STATE_BIT, REQ_F_BUFFER_SELECTED_BIT, REQ_F_BUFFER_RING_BIT, REQ_F_REISSUE_BIT, @@ -459,7 +471,6 @@ enum { REQ_F_DOUBLE_POLL_BIT, REQ_F_APOLL_MULTISHOT_BIT, REQ_F_CLEAR_POLLIN_BIT, - REQ_F_HASH_LOCKED_BIT, /* keep async read/write and isreg together and in order */ REQ_F_SUPPORT_NOWAIT_BIT, REQ_F_ISREG_BIT, @@ -468,6 +479,7 @@ enum { REQ_F_BL_EMPTY_BIT, REQ_F_BL_NO_RECYCLE_BIT, REQ_F_BUFFERS_COMMIT_BIT, + REQ_F_BUF_NODE_BIT, /* not a real bit, just to check we're not overflowing the space */ __REQ_F_LAST_BIT, @@ -506,6 +518,8 @@ enum { REQ_F_NEED_CLEANUP = IO_REQ_FLAG(REQ_F_NEED_CLEANUP_BIT), /* already went through poll handler */ REQ_F_POLLED = IO_REQ_FLAG(REQ_F_POLLED_BIT), + /* every req only blocks once in hybrid poll */ + REQ_F_IOPOLL_STATE = IO_REQ_FLAG(REQ_F_HYBRID_IOPOLL_STATE_BIT), /* buffer already selected */ REQ_F_BUFFER_SELECTED = IO_REQ_FLAG(REQ_F_BUFFER_SELECTED_BIT), /* buffer selected from ring, needs commit */ @@ -534,8 +548,6 @@ enum { REQ_F_APOLL_MULTISHOT = IO_REQ_FLAG(REQ_F_APOLL_MULTISHOT_BIT), /* recvmsg special flag, clear EPOLLIN */ REQ_F_CLEAR_POLLIN = IO_REQ_FLAG(REQ_F_CLEAR_POLLIN_BIT), - /* hashed into ->cancel_hash_locked, protected by ->uring_lock */ - REQ_F_HASH_LOCKED = IO_REQ_FLAG(REQ_F_HASH_LOCKED_BIT), /* don't use lazy poll wake for this request */ REQ_F_POLL_NO_LAZY = IO_REQ_FLAG(REQ_F_POLL_NO_LAZY_BIT), /* file is pollable */ @@ -546,6 +558,8 @@ enum { REQ_F_BL_NO_RECYCLE = IO_REQ_FLAG(REQ_F_BL_NO_RECYCLE_BIT), /* buffer ring head needs incrementing on put */ REQ_F_BUFFERS_COMMIT = IO_REQ_FLAG(REQ_F_BUFFERS_COMMIT_BIT), + /* buf node is valid */ + REQ_F_BUF_NODE = IO_REQ_FLAG(REQ_F_BUF_NODE_BIT), }; typedef void (*io_req_tw_func_t)(struct io_kiocb *req, struct io_tw_state *ts); @@ -615,12 +629,9 @@ struct io_kiocb { struct io_cqe cqe; struct io_ring_ctx *ctx; - struct task_struct *task; + struct io_uring_task *tctx; union { - /* store used ubuf, so we can prevent reloading */ - struct io_mapped_ubuf *imu; - /* stores selected buf, valid IFF REQ_F_BUFFER_SELECTED is set */ struct io_buffer *kbuf; @@ -629,6 +640,8 @@ struct io_kiocb { * REQ_F_BUFFER_RING is set. */ struct io_buffer_list *buf_list; + + struct io_rsrc_node *buf_node; }; union { @@ -638,13 +651,20 @@ struct io_kiocb { __poll_t apoll_events; }; - struct io_rsrc_node *rsrc_node; + struct io_rsrc_node *file_node; atomic_t refs; bool cancel_seq_set; struct io_task_work io_task_work; - /* for polled requests, i.e. IORING_OP_POLL_ADD and async armed poll */ - struct hlist_node hash_node; + union { + /* + * for polled requests, i.e. IORING_OP_POLL_ADD and async armed + * poll + */ + struct hlist_node hash_node; + /* For IOPOLL setup queues, with hybrid polling */ + u64 iopoll_start; + }; /* internal polling, see IORING_FEAT_FAST_POLL */ struct async_poll *apoll; /* opcode allocated if it needs to store data for async defer */ @@ -667,4 +687,9 @@ struct io_overflow_cqe { struct io_uring_cqe cqe; }; +static inline bool io_ctx_cqe32(struct io_ring_ctx *ctx) +{ + return ctx->flags & IORING_SETUP_CQE32; +} + #endif diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 4ad12a3c8bae..27048ec10e1c 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -178,6 +178,7 @@ struct iomap_folio_ops { #else #define IOMAP_DAX 0 #endif /* CONFIG_FS_DAX */ +#define IOMAP_ATOMIC (1 << 9) struct iomap_ops { /* @@ -256,6 +257,39 @@ static inline const struct iomap *iomap_iter_srcmap(const struct iomap_iter *i) return &i->iomap; } +/* + * Return the file offset for the first unchanged block after a short write. + * + * If nothing was written, round @pos down to point at the first block in + * the range, else round up to include the partially written block. + */ +static inline loff_t iomap_last_written_block(struct inode *inode, loff_t pos, + ssize_t written) +{ + if (unlikely(!written)) + return round_down(pos, i_blocksize(inode)); + return round_up(pos + written, i_blocksize(inode)); +} + +/* + * Check if the range needs to be unshared for a FALLOC_FL_UNSHARE_RANGE + * operation. + * + * Don't bother with blocks that are not shared to start with; or mappings that + * cannot be shared, such as inline data, delalloc reservations, holes or + * unwritten extents. + * + * Note that we use srcmap directly instead of iomap_iter_srcmap as unsharing + * requires providing a separate source map, and the presence of one is a good + * indicator that unsharing is needed, unlike IOMAP_F_SHARED which can be set + * for any data that goes into the COW fork for XFS. + */ +static inline bool iomap_want_unshare_iter(const struct iomap_iter *iter) +{ + return (iter->iomap.flags & IOMAP_F_SHARED) && + iter->srcmap.type == IOMAP_MAPPED; +} + ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from, const struct iomap_ops *ops, void *private); int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops); @@ -276,9 +310,9 @@ vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, typedef void (*iomap_punch_t)(struct inode *inode, loff_t offset, loff_t length, struct iomap *iomap); -void iomap_file_buffered_write_punch_delalloc(struct inode *inode, loff_t pos, - loff_t length, ssize_t written, unsigned flag, - struct iomap *iomap, iomap_punch_t punch); +void iomap_write_delalloc_release(struct inode *inode, loff_t start_byte, + loff_t end_byte, unsigned flags, struct iomap *iomap, + iomap_punch_t punch); int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len, const struct iomap_ops *ops); diff --git a/include/linux/irqchip/arm-gic-v4.h b/include/linux/irqchip/arm-gic-v4.h index ecabed6d3307..7f1f11a5e4e4 100644 --- a/include/linux/irqchip/arm-gic-v4.h +++ b/include/linux/irqchip/arm-gic-v4.h @@ -66,10 +66,12 @@ struct its_vpe { bool enabled; bool group; } sgi_config[16]; - atomic_t vmapp_count; }; }; + /* Track the VPE being mapped */ + atomic_t vmapp_count; + /* * Ensures mutual exclusion between affinity setting of the * vPE and vLPI operations using vpe->col_idx. diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 3f003d5fde53..57b074e0cfbb 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -18,6 +18,8 @@ #include <asm/irqflags.h> #include <asm/percpu.h> +struct task_struct; + /* Currently lockdep_softirqs_on/off is used only by lockdep */ #ifdef CONFIG_PROVE_LOCKING extern void lockdep_softirqs_on(unsigned long ip); @@ -25,12 +27,16 @@ extern void lockdep_hardirqs_on_prepare(void); extern void lockdep_hardirqs_on(unsigned long ip); extern void lockdep_hardirqs_off(unsigned long ip); + extern void lockdep_cleanup_dead_cpu(unsigned int cpu, + struct task_struct *idle); #else static inline void lockdep_softirqs_on(unsigned long ip) { } static inline void lockdep_softirqs_off(unsigned long ip) { } static inline void lockdep_hardirqs_on_prepare(void) { } static inline void lockdep_hardirqs_on(unsigned long ip) { } static inline void lockdep_hardirqs_off(unsigned long ip) { } + static inline void lockdep_cleanup_dead_cpu(unsigned int cpu, + struct task_struct *idle) {} #endif #ifdef CONFIG_TRACE_IRQFLAGS diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 8aef9bb6ad57..50f7ea8714bf 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1796,22 +1796,21 @@ static inline unsigned long jbd2_log_space_left(journal_t *journal) static inline u32 jbd2_chksum(journal_t *journal, u32 crc, const void *address, unsigned int length) { - struct { - struct shash_desc shash; - char ctx[JBD_MAX_CHECKSUM_SIZE]; - } desc; + DEFINE_RAW_FLEX(struct shash_desc, desc, __ctx, + DIV_ROUND_UP(JBD_MAX_CHECKSUM_SIZE, + sizeof(*((struct shash_desc *)0)->__ctx))); int err; BUG_ON(crypto_shash_descsize(journal->j_chksum_driver) > JBD_MAX_CHECKSUM_SIZE); - desc.shash.tfm = journal->j_chksum_driver; - *(u32 *)desc.ctx = crc; + desc->tfm = journal->j_chksum_driver; + *(u32 *)desc->__ctx = crc; - err = crypto_shash_update(&desc.shash, address, length); + err = crypto_shash_update(desc, address, length); BUG_ON(err); - return *(u32 *)desc.ctx; + return *(u32 *)desc->__ctx; } /* Return most recent uncommitted transaction */ diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 11690dacd986..ec9c05044d4f 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -54,12 +54,11 @@ static inline long mm_ksm_zero_pages(struct mm_struct *mm) return atomic_long_read(&mm->ksm_zero_pages); } -static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) +static inline void ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) { + /* Adding mm to ksm is best effort on fork. */ if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags)) - return __ksm_enter(mm); - - return 0; + __ksm_enter(mm); } static inline int ksm_execve(struct mm_struct *mm) @@ -107,9 +106,8 @@ static inline int ksm_disable(struct mm_struct *mm) return 0; } -static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) +static inline void ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) { - return 0; } static inline int ksm_execve(struct mm_struct *mm) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index db567d26f7b9..45be36e5285f 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1313,8 +1313,6 @@ void mark_page_dirty(struct kvm *kvm, gfn_t gfn); struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu); struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn); -kvm_pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn); -kvm_pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn); int kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map); void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty); unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn); diff --git a/include/linux/libata.h b/include/linux/libata.h index 9b4a6ff03235..c1a85d46eba6 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -270,9 +270,7 @@ enum { /* bits 24:31 of host->flags are reserved for LLD specific flags */ - /* various lengths of time */ - ATA_TMOUT_BOOT = 30000, /* heuristic */ - ATA_TMOUT_BOOT_QUICK = 7000, /* heuristic */ + /* Various lengths of time */ ATA_TMOUT_INTERNAL_QUICK = 5000, ATA_TMOUT_MAX_PARK = 30000, diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 217f7abf2cbf..67964dc4db95 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -173,7 +173,7 @@ static inline void lockdep_init_map(struct lockdep_map *lock, const char *name, (lock)->dep_map.lock_type) #define lockdep_set_subclass(lock, sub) \ - lockdep_init_map_type(&(lock)->dep_map, #lock, (lock)->dep_map.key, sub,\ + lockdep_init_map_type(&(lock)->dep_map, (lock)->dep_map.name, (lock)->dep_map.key, sub,\ (lock)->dep_map.wait_type_inner, \ (lock)->dep_map.wait_type_outer, \ (lock)->dep_map.lock_type) diff --git a/include/linux/lsm/apparmor.h b/include/linux/lsm/apparmor.h new file mode 100644 index 000000000000..612cbfacb072 --- /dev/null +++ b/include/linux/lsm/apparmor.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Linux Security Module interface to other subsystems. + * AppArmor presents single pointer to an aa_label structure. + */ +#ifndef __LINUX_LSM_APPARMOR_H +#define __LINUX_LSM_APPARMOR_H + +struct aa_label; + +struct lsm_prop_apparmor { +#ifdef CONFIG_SECURITY_APPARMOR + struct aa_label *label; +#endif +}; + +#endif /* ! __LINUX_LSM_APPARMOR_H */ diff --git a/include/linux/lsm/bpf.h b/include/linux/lsm/bpf.h new file mode 100644 index 000000000000..8106e206fcef --- /dev/null +++ b/include/linux/lsm/bpf.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Linux Security Module interface to other subsystems. + * BPF may present a single u32 value. + */ +#ifndef __LINUX_LSM_BPF_H +#define __LINUX_LSM_BPF_H +#include <linux/types.h> + +struct lsm_prop_bpf { +#ifdef CONFIG_BPF_LSM + u32 secid; +#endif +}; + +#endif /* ! __LINUX_LSM_BPF_H */ diff --git a/include/linux/lsm/selinux.h b/include/linux/lsm/selinux.h new file mode 100644 index 000000000000..9455a6b5b910 --- /dev/null +++ b/include/linux/lsm/selinux.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Linux Security Module interface to other subsystems. + * SELinux presents a single u32 value which is known as a secid. + */ +#ifndef __LINUX_LSM_SELINUX_H +#define __LINUX_LSM_SELINUX_H +#include <linux/types.h> + +struct lsm_prop_selinux { +#ifdef CONFIG_SECURITY_SELINUX + u32 secid; +#endif +}; + +#endif /* ! __LINUX_LSM_SELINUX_H */ diff --git a/include/linux/lsm/smack.h b/include/linux/lsm/smack.h new file mode 100644 index 000000000000..ff730dd7a734 --- /dev/null +++ b/include/linux/lsm/smack.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Linux Security Module interface to other subsystems. + * Smack presents a pointer into the global Smack label list. + */ +#ifndef __LINUX_LSM_SMACK_H +#define __LINUX_LSM_SMACK_H + +struct smack_known; + +struct lsm_prop_smack { +#ifdef CONFIG_SECURITY_SMACK + struct smack_known *skp; +#endif +}; + +#endif /* ! __LINUX_LSM_SMACK_H */ diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 9eca013aa5e1..eb2937599cb0 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -176,7 +176,8 @@ LSM_HOOK(int, -EOPNOTSUPP, inode_setsecurity, struct inode *inode, const char *name, const void *value, size_t size, int flags) LSM_HOOK(int, 0, inode_listsecurity, struct inode *inode, char *buffer, size_t buffer_size) -LSM_HOOK(void, LSM_RET_VOID, inode_getsecid, struct inode *inode, u32 *secid) +LSM_HOOK(void, LSM_RET_VOID, inode_getlsmprop, struct inode *inode, + struct lsm_prop *prop) LSM_HOOK(int, 0, inode_copy_up, struct dentry *src, struct cred **new) LSM_HOOK(int, -EOPNOTSUPP, inode_copy_up_xattr, struct dentry *src, const char *name) @@ -217,6 +218,8 @@ LSM_HOOK(int, 0, cred_prepare, struct cred *new, const struct cred *old, LSM_HOOK(void, LSM_RET_VOID, cred_transfer, struct cred *new, const struct cred *old) LSM_HOOK(void, LSM_RET_VOID, cred_getsecid, const struct cred *c, u32 *secid) +LSM_HOOK(void, LSM_RET_VOID, cred_getlsmprop, const struct cred *c, + struct lsm_prop *prop) LSM_HOOK(int, 0, kernel_act_as, struct cred *new, u32 secid) LSM_HOOK(int, 0, kernel_create_files_as, struct cred *new, struct inode *inode) LSM_HOOK(int, 0, kernel_module_request, char *kmod_name) @@ -235,9 +238,9 @@ LSM_HOOK(int, 0, task_fix_setgroups, struct cred *new, const struct cred * old) LSM_HOOK(int, 0, task_setpgid, struct task_struct *p, pid_t pgid) LSM_HOOK(int, 0, task_getpgid, struct task_struct *p) LSM_HOOK(int, 0, task_getsid, struct task_struct *p) -LSM_HOOK(void, LSM_RET_VOID, current_getsecid_subj, u32 *secid) -LSM_HOOK(void, LSM_RET_VOID, task_getsecid_obj, - struct task_struct *p, u32 *secid) +LSM_HOOK(void, LSM_RET_VOID, current_getlsmprop_subj, struct lsm_prop *prop) +LSM_HOOK(void, LSM_RET_VOID, task_getlsmprop_obj, + struct task_struct *p, struct lsm_prop *prop) LSM_HOOK(int, 0, task_setnice, struct task_struct *p, int nice) LSM_HOOK(int, 0, task_setioprio, struct task_struct *p, int ioprio) LSM_HOOK(int, 0, task_getioprio, struct task_struct *p) @@ -256,8 +259,8 @@ LSM_HOOK(void, LSM_RET_VOID, task_to_inode, struct task_struct *p, struct inode *inode) LSM_HOOK(int, 0, userns_create, const struct cred *cred) LSM_HOOK(int, 0, ipc_permission, struct kern_ipc_perm *ipcp, short flag) -LSM_HOOK(void, LSM_RET_VOID, ipc_getsecid, struct kern_ipc_perm *ipcp, - u32 *secid) +LSM_HOOK(void, LSM_RET_VOID, ipc_getlsmprop, struct kern_ipc_perm *ipcp, + struct lsm_prop *prop) LSM_HOOK(int, 0, msg_msg_alloc_security, struct msg_msg *msg) LSM_HOOK(void, LSM_RET_VOID, msg_msg_free_security, struct msg_msg *msg) LSM_HOOK(int, 0, msg_queue_alloc_security, struct kern_ipc_perm *perm) @@ -294,6 +297,8 @@ LSM_HOOK(int, -EINVAL, setprocattr, const char *name, void *value, size_t size) LSM_HOOK(int, 0, ismaclabel, const char *name) LSM_HOOK(int, -EOPNOTSUPP, secid_to_secctx, u32 secid, char **secdata, u32 *seclen) +LSM_HOOK(int, -EOPNOTSUPP, lsmprop_to_secctx, struct lsm_prop *prop, + char **secdata, u32 *seclen) LSM_HOOK(int, 0, secctx_to_secid, const char *secdata, u32 seclen, u32 *secid) LSM_HOOK(void, LSM_RET_VOID, release_secctx, char *secdata, u32 seclen) LSM_HOOK(void, LSM_RET_VOID, inode_invalidate_secctx, struct inode *inode) @@ -416,7 +421,8 @@ LSM_HOOK(void, LSM_RET_VOID, key_post_create_or_update, struct key *keyring, LSM_HOOK(int, 0, audit_rule_init, u32 field, u32 op, char *rulestr, void **lsmrule, gfp_t gfp) LSM_HOOK(int, 0, audit_rule_known, struct audit_krule *krule) -LSM_HOOK(int, 0, audit_rule_match, u32 secid, u32 field, u32 op, void *lsmrule) +LSM_HOOK(int, 0, audit_rule_match, struct lsm_prop *prop, u32 field, u32 op, + void *lsmrule) LSM_HOOK(void, LSM_RET_VOID, audit_rule_free, void *lsmrule) #endif /* CONFIG_AUDIT */ diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 34d2da05f2f1..e1b41554a5fb 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1760,8 +1760,9 @@ static inline int memcg_kmem_id(struct mem_cgroup *memcg) struct mem_cgroup *mem_cgroup_from_slab_obj(void *p); -static inline void count_objcg_event(struct obj_cgroup *objcg, - enum vm_event_item idx) +static inline void count_objcg_events(struct obj_cgroup *objcg, + enum vm_event_item idx, + unsigned long count) { struct mem_cgroup *memcg; @@ -1770,7 +1771,7 @@ static inline void count_objcg_event(struct obj_cgroup *objcg, rcu_read_lock(); memcg = obj_cgroup_memcg(objcg); - count_memcg_events(memcg, idx, 1); + count_memcg_events(memcg, idx, count); rcu_read_unlock(); } @@ -1825,8 +1826,9 @@ static inline struct mem_cgroup *mem_cgroup_from_slab_obj(void *p) return NULL; } -static inline void count_objcg_event(struct obj_cgroup *objcg, - enum vm_event_item idx) +static inline void count_objcg_events(struct obj_cgroup *objcg, + enum vm_event_item idx, + unsigned long count) { } diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 97f6de69f616..96d369112bfa 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -2138,7 +2138,7 @@ struct mlx5_ifc_cmd_hca_cap_2_bits { u8 ts_cqe_metadata_size2wqe_counter[0x5]; u8 reserved_at_250[0x10]; - u8 reserved_at_260[0x120]; + u8 reserved_at_260[0x20]; u8 format_select_dw_gtpu_dw_0[0x8]; u8 format_select_dw_gtpu_dw_1[0x8]; diff --git a/include/linux/mm.h b/include/linux/mm.h index ecf63d2b0582..feb5c8021bef 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -329,12 +329,14 @@ extern unsigned int kobjsize(const void *objp); #define VM_HIGH_ARCH_BIT_3 35 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_BIT_4 36 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_BIT_5 37 /* bit only usable on 64-bit architectures */ +#define VM_HIGH_ARCH_BIT_6 38 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_0 BIT(VM_HIGH_ARCH_BIT_0) #define VM_HIGH_ARCH_1 BIT(VM_HIGH_ARCH_BIT_1) #define VM_HIGH_ARCH_2 BIT(VM_HIGH_ARCH_BIT_2) #define VM_HIGH_ARCH_3 BIT(VM_HIGH_ARCH_BIT_3) #define VM_HIGH_ARCH_4 BIT(VM_HIGH_ARCH_BIT_4) #define VM_HIGH_ARCH_5 BIT(VM_HIGH_ARCH_BIT_5) +#define VM_HIGH_ARCH_6 BIT(VM_HIGH_ARCH_BIT_6) #endif /* CONFIG_ARCH_USES_HIGH_VMA_FLAGS */ #ifdef CONFIG_ARCH_HAS_PKEYS @@ -365,7 +367,17 @@ extern unsigned int kobjsize(const void *objp); * for more details on the guard size. */ # define VM_SHADOW_STACK VM_HIGH_ARCH_5 -#else +#endif + +#if defined(CONFIG_ARM64_GCS) +/* + * arm64's Guarded Control Stack implements similar functionality and + * has similar constraints to shadow stacks. + */ +# define VM_SHADOW_STACK VM_HIGH_ARCH_6 +#endif + +#ifndef VM_SHADOW_STACK # define VM_SHADOW_STACK VM_NONE #endif @@ -3818,8 +3830,9 @@ void *sparse_buffer_alloc(unsigned long size); struct page * __populate_section_memmap(unsigned long pfn, unsigned long nr_pages, int nid, struct vmem_altmap *altmap, struct dev_pagemap *pgmap); -void pmd_init(void *addr); void pud_init(void *addr); +void pmd_init(void *addr); +void kernel_pte_init(void *addr); pgd_t *vmemmap_pgd_populate(unsigned long addr, int node); p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node); pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node); @@ -4219,4 +4232,8 @@ static inline void pgalloc_tag_copy(struct folio *new, struct folio *old) } #endif /* CONFIG_MEM_ALLOC_PROFILING */ +int arch_get_shadow_stack_status(struct task_struct *t, unsigned long __user *status); +int arch_set_shadow_stack_status(struct task_struct *t, unsigned long status); +int arch_lock_shadow_stack_status(struct task_struct *t, unsigned long status); + #endif /* _LINUX_MM_H */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 6e3bdf8e38bc..381d22eba088 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -782,6 +782,7 @@ struct vm_area_struct { struct mm_cid { u64 time; int cid; + int recent_cid; }; #endif @@ -852,6 +853,27 @@ struct mm_struct { * When the next mm_cid scan is due (in jiffies). */ unsigned long mm_cid_next_scan; + /** + * @nr_cpus_allowed: Number of CPUs allowed for mm. + * + * Number of CPUs allowed in the union of all mm's + * threads allowed CPUs. + */ + unsigned int nr_cpus_allowed; + /** + * @max_nr_cid: Maximum number of concurrency IDs allocated. + * + * Track the highest number of concurrency IDs allocated for the + * mm. + */ + atomic_t max_nr_cid; + /** + * @cpus_allowed_lock: Lock protecting mm cpus_allowed. + * + * Provide mutual exclusion for mm cpus_allowed and + * mm nr_cpus_allowed updates. + */ + raw_spinlock_t cpus_allowed_lock; #endif #ifdef CONFIG_MMU atomic_long_t pgtables_bytes; /* size of all page tables */ @@ -1170,18 +1192,30 @@ static inline int mm_cid_clear_lazy_put(int cid) return cid & ~MM_CID_LAZY_PUT; } +/* + * mm_cpus_allowed: Union of all mm's threads allowed CPUs. + */ +static inline cpumask_t *mm_cpus_allowed(struct mm_struct *mm) +{ + unsigned long bitmap = (unsigned long)mm; + + bitmap += offsetof(struct mm_struct, cpu_bitmap); + /* Skip cpu_bitmap */ + bitmap += cpumask_size(); + return (struct cpumask *)bitmap; +} + /* Accessor for struct mm_struct's cidmask. */ static inline cpumask_t *mm_cidmask(struct mm_struct *mm) { - unsigned long cid_bitmap = (unsigned long)mm; + unsigned long cid_bitmap = (unsigned long)mm_cpus_allowed(mm); - cid_bitmap += offsetof(struct mm_struct, cpu_bitmap); - /* Skip cpu_bitmap */ + /* Skip mm_cpus_allowed */ cid_bitmap += cpumask_size(); return (struct cpumask *)cid_bitmap; } -static inline void mm_init_cid(struct mm_struct *mm) +static inline void mm_init_cid(struct mm_struct *mm, struct task_struct *p) { int i; @@ -1189,17 +1223,22 @@ static inline void mm_init_cid(struct mm_struct *mm) struct mm_cid *pcpu_cid = per_cpu_ptr(mm->pcpu_cid, i); pcpu_cid->cid = MM_CID_UNSET; + pcpu_cid->recent_cid = MM_CID_UNSET; pcpu_cid->time = 0; } + mm->nr_cpus_allowed = p->nr_cpus_allowed; + atomic_set(&mm->max_nr_cid, 0); + raw_spin_lock_init(&mm->cpus_allowed_lock); + cpumask_copy(mm_cpus_allowed(mm), &p->cpus_mask); cpumask_clear(mm_cidmask(mm)); } -static inline int mm_alloc_cid_noprof(struct mm_struct *mm) +static inline int mm_alloc_cid_noprof(struct mm_struct *mm, struct task_struct *p) { mm->pcpu_cid = alloc_percpu_noprof(struct mm_cid); if (!mm->pcpu_cid) return -ENOMEM; - mm_init_cid(mm); + mm_init_cid(mm, p); return 0; } #define mm_alloc_cid(...) alloc_hooks(mm_alloc_cid_noprof(__VA_ARGS__)) @@ -1212,16 +1251,31 @@ static inline void mm_destroy_cid(struct mm_struct *mm) static inline unsigned int mm_cid_size(void) { - return cpumask_size(); + return 2 * cpumask_size(); /* mm_cpus_allowed(), mm_cidmask(). */ +} + +static inline void mm_set_cpus_allowed(struct mm_struct *mm, const struct cpumask *cpumask) +{ + struct cpumask *mm_allowed = mm_cpus_allowed(mm); + + if (!mm) + return; + /* The mm_cpus_allowed is the union of each thread allowed CPUs masks. */ + raw_spin_lock(&mm->cpus_allowed_lock); + cpumask_or(mm_allowed, mm_allowed, cpumask); + WRITE_ONCE(mm->nr_cpus_allowed, cpumask_weight(mm_allowed)); + raw_spin_unlock(&mm->cpus_allowed_lock); } #else /* CONFIG_SCHED_MM_CID */ -static inline void mm_init_cid(struct mm_struct *mm) { } -static inline int mm_alloc_cid(struct mm_struct *mm) { return 0; } +static inline void mm_init_cid(struct mm_struct *mm, struct task_struct *p) { } +static inline int mm_alloc_cid(struct mm_struct *mm, struct task_struct *p) { return 0; } static inline void mm_destroy_cid(struct mm_struct *mm) { } + static inline unsigned int mm_cid_size(void) { return 0; } +static inline void mm_set_cpus_allowed(struct mm_struct *mm, const struct cpumask *cpumask) { } #endif /* CONFIG_SCHED_MM_CID */ struct mmu_gather; diff --git a/include/linux/mman.h b/include/linux/mman.h index bcb201ab7a41..a842783ffa62 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -2,6 +2,7 @@ #ifndef _LINUX_MMAN_H #define _LINUX_MMAN_H +#include <linux/fs.h> #include <linux/mm.h> #include <linux/percpu_counter.h> @@ -94,7 +95,7 @@ static inline void vm_unacct_memory(long pages) #endif #ifndef arch_calc_vm_flag_bits -#define arch_calc_vm_flag_bits(flags) 0 +#define arch_calc_vm_flag_bits(file, flags) 0 #endif #ifndef arch_validate_prot @@ -151,13 +152,13 @@ calc_vm_prot_bits(unsigned long prot, unsigned long pkey) * Combine the mmap "flags" argument into "vm_flags" used internally. */ static inline unsigned long -calc_vm_flag_bits(unsigned long flags) +calc_vm_flag_bits(struct file *file, unsigned long flags) { return _calc_vm_trans(flags, MAP_GROWSDOWN, VM_GROWSDOWN ) | _calc_vm_trans(flags, MAP_LOCKED, VM_LOCKED ) | _calc_vm_trans(flags, MAP_SYNC, VM_SYNC ) | _calc_vm_trans(flags, MAP_STACK, VM_NOHUGEPAGE) | - arch_calc_vm_flag_bits(flags); + arch_calc_vm_flag_bits(file, flags); } unsigned long vm_commit_limit(void); @@ -188,16 +189,31 @@ static inline bool arch_memory_deny_write_exec_supported(void) * * d) mmap(PROT_READ | PROT_EXEC) * mmap(PROT_READ | PROT_EXEC | PROT_BTI) + * + * This is only applicable if the user has set the Memory-Deny-Write-Execute + * (MDWE) protection mask for the current process. + * + * @old specifies the VMA flags the VMA originally possessed, and @new the ones + * we propose to set. + * + * Return: false if proposed change is OK, true if not ok and should be denied. */ -static inline bool map_deny_write_exec(struct vm_area_struct *vma, unsigned long vm_flags) +static inline bool map_deny_write_exec(unsigned long old, unsigned long new) { + /* If MDWE is disabled, we have nothing to deny. */ if (!test_bit(MMF_HAS_MDWE, ¤t->mm->flags)) return false; - if ((vm_flags & VM_EXEC) && (vm_flags & VM_WRITE)) + /* If the new VMA is not executable, we have nothing to deny. */ + if (!(new & VM_EXEC)) + return false; + + /* Under MDWE we do not accept newly writably executable VMAs... */ + if (new & VM_WRITE) return true; - if (!(vma->vm_flags & VM_EXEC) && (vm_flags & VM_EXEC)) + /* ...nor previously non-executable VMAs becoming executable. */ + if (!(old & VM_EXEC)) return true; return false; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 17506e4a2835..80bc5640bb60 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -458,9 +458,7 @@ struct lru_gen_folio { enum { MM_LEAF_TOTAL, /* total leaf entries */ - MM_LEAF_OLD, /* old leaf entries */ MM_LEAF_YOUNG, /* young leaf entries */ - MM_NONLEAF_TOTAL, /* total non-leaf entries */ MM_NONLEAF_FOUND, /* non-leaf entries found in Bloom filters */ MM_NONLEAF_ADDED, /* non-leaf entries added to Bloom filters */ NR_MM_STATS @@ -557,7 +555,7 @@ struct lru_gen_memcg { void lru_gen_init_pgdat(struct pglist_data *pgdat); void lru_gen_init_lruvec(struct lruvec *lruvec); -void lru_gen_look_around(struct page_vma_mapped_walk *pvmw); +bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw); void lru_gen_init_memcg(struct mem_cgroup *memcg); void lru_gen_exit_memcg(struct mem_cgroup *memcg); @@ -576,8 +574,9 @@ static inline void lru_gen_init_lruvec(struct lruvec *lruvec) { } -static inline void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) +static inline bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw) { + return false; } static inline void lru_gen_init_memcg(struct mem_cgroup *memcg) @@ -824,6 +823,7 @@ struct zone { unsigned long watermark_boost; unsigned long nr_reserved_highatomic; + unsigned long nr_free_highatomic; /* * We don't know if the memory that we're going to allocate will be diff --git a/include/linux/mtd/map.h b/include/linux/mtd/map.h index b4fa92a6e44b..1b56796f6cb3 100644 --- a/include/linux/mtd/map.h +++ b/include/linux/mtd/map.h @@ -15,7 +15,7 @@ #include <linux/kernel.h> #include <linux/io.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <asm/barrier.h> #ifdef CONFIG_MTD_MAP_BANK_WIDTH_1 diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e87b5e488325..8896705ccd63 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3325,6 +3325,12 @@ static inline void netif_tx_wake_all_queues(struct net_device *dev) static __always_inline void netif_tx_stop_queue(struct netdev_queue *dev_queue) { + /* Paired with READ_ONCE() from dev_watchdog() */ + WRITE_ONCE(dev_queue->trans_start, jiffies); + + /* This barrier is paired with smp_mb() from dev_watchdog() */ + smp_mb__before_atomic(); + /* Must be an atomic op see netif_txq_try_stop() */ set_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state); } @@ -3451,6 +3457,12 @@ static inline void netdev_tx_sent_queue(struct netdev_queue *dev_queue, if (likely(dql_avail(&dev_queue->dql) >= 0)) return; + /* Paired with READ_ONCE() from dev_watchdog() */ + WRITE_ONCE(dev_queue->trans_start, jiffies); + + /* This barrier is paired with smp_mb() from dev_watchdog() */ + smp_mb__before_atomic(); + set_bit(__QUEUE_STATE_STACK_XOFF, &dev_queue->state); /* @@ -5029,6 +5041,24 @@ void netif_set_tso_max_segs(struct net_device *dev, unsigned int segs); void netif_inherit_tso_max(struct net_device *to, const struct net_device *from); +static inline unsigned int +netif_get_gro_max_size(const struct net_device *dev, const struct sk_buff *skb) +{ + /* pairs with WRITE_ONCE() in netif_set_gro(_ipv4)_max_size() */ + return skb->protocol == htons(ETH_P_IPV6) ? + READ_ONCE(dev->gro_max_size) : + READ_ONCE(dev->gro_ipv4_max_size); +} + +static inline unsigned int +netif_get_gso_max_size(const struct net_device *dev, const struct sk_buff *skb) +{ + /* pairs with WRITE_ONCE() in netif_set_gso(_ipv4)_max_size() */ + return skb->protocol == htons(ETH_P_IPV6) ? + READ_ONCE(dev->gso_max_size) : + READ_ONCE(dev->gso_ipv4_max_size); +} + static inline bool netif_is_macsec(const struct net_device *dev) { return dev->priv_flags & IFF_MACSEC; diff --git a/include/linux/netlink.h b/include/linux/netlink.h index b332c2048c75..a48a30842d84 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -239,7 +239,7 @@ int netlink_register_notifier(struct notifier_block *nb); int netlink_unregister_notifier(struct notifier_block *nb); /* finegrained unicast helpers: */ -struct sock *netlink_getsockbyfilp(struct file *filp); +struct sock *netlink_getsockbyfd(int fd); int netlink_attachskb(struct sock *sk, struct sk_buff *skb, long *timeo, struct sock *ssk); void netlink_detachskb(struct sock *sk, struct sk_buff *skb); diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 853df3fcd4c2..b804346a9741 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -249,6 +249,7 @@ struct nfs_server { struct list_head layouts; struct list_head delegations; struct list_head ss_copies; + struct list_head ss_src_copies; unsigned long delegation_gen; unsigned long mig_gen; diff --git a/include/linux/nfslocalio.h b/include/linux/nfslocalio.h index b353abe00357..3982fea79919 100644 --- a/include/linux/nfslocalio.h +++ b/include/linux/nfslocalio.h @@ -32,7 +32,8 @@ typedef struct { struct auth_domain *dom; /* auth_domain for localio */ } nfs_uuid_t; -void nfs_uuid_begin(nfs_uuid_t *); +void nfs_uuid_init(nfs_uuid_t *); +bool nfs_uuid_begin(nfs_uuid_t *); void nfs_uuid_end(nfs_uuid_t *); void nfs_uuid_is_local(const uuid_t *, struct list_head *, struct net *, struct auth_domain *, struct module *); @@ -65,10 +66,25 @@ struct nfsd_file *nfs_open_local_fh(nfs_uuid_t *, struct rpc_clnt *, const struct cred *, const struct nfs_fh *, const fmode_t); +static inline void nfs_to_nfsd_file_put_local(struct nfsd_file *localio) +{ + /* + * Once reference to nfsd_serv is dropped, NFSD could be + * unloaded, so ensure safe return from nfsd_file_put_local() + * by always taking RCU. + */ + rcu_read_lock(); + nfs_to->nfsd_file_put_local(localio); + rcu_read_unlock(); +} + #else /* CONFIG_NFS_LOCALIO */ static inline void nfsd_localio_ops_init(void) { } +static inline void nfs_to_nfsd_file_put_local(struct nfsd_file *localio) +{ +} #endif /* CONFIG_NFS_LOCALIO */ #endif /* __LINUX_NFSLOCALIO_H */ diff --git a/include/linux/nvme.h b/include/linux/nvme.h index b58d9405d65e..0a6e22038ce3 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -327,7 +327,8 @@ struct nvme_id_ctrl { __le32 sanicap; __le32 hmminds; __le16 hmmaxd; - __u8 rsvd338[4]; + __le16 nvmsetidmax; + __le16 endgidmax; __u8 anatt; __u8 anacap; __le32 anagrpmax; @@ -522,6 +523,7 @@ enum { NVME_ID_CNS_NS_DESC_LIST = 0x03, NVME_ID_CNS_CS_NS = 0x05, NVME_ID_CNS_CS_CTRL = 0x06, + NVME_ID_CNS_NS_ACTIVE_LIST_CS = 0x07, NVME_ID_CNS_NS_CS_INDEP = 0x08, NVME_ID_CNS_NS_PRESENT_LIST = 0x10, NVME_ID_CNS_NS_PRESENT = 0x11, @@ -530,6 +532,7 @@ enum { NVME_ID_CNS_SCNDRY_CTRL_LIST = 0x15, NVME_ID_CNS_NS_GRANULARITY = 0x16, NVME_ID_CNS_UUID_LIST = 0x17, + NVME_ID_CNS_ENDGRP_LIST = 0x19, }; enum { @@ -560,6 +563,8 @@ enum { NVME_NS_FLBAS_LBA_SHIFT = 1, NVME_NS_FLBAS_META_EXT = 0x10, NVME_NS_NMIC_SHARED = 1 << 0, + NVME_NS_ROTATIONAL = 1 << 4, + NVME_NS_VWC_NOT_PRESENT = 1 << 5, NVME_LBAF_RP_BEST = 0, NVME_LBAF_RP_BETTER = 1, NVME_LBAF_RP_GOOD = 2, @@ -617,6 +622,40 @@ enum { NVME_NIDT_CSI = 0x04, }; +struct nvme_endurance_group_log { + __u8 egcw; + __u8 egfeat; + __u8 rsvd2; + __u8 avsp; + __u8 avspt; + __u8 pused; + __le16 did; + __u8 rsvd8[24]; + __u8 ee[16]; + __u8 dur[16]; + __u8 duw[16]; + __u8 muw[16]; + __u8 hrc[16]; + __u8 hwc[16]; + __u8 mdie[16]; + __u8 neile[16]; + __u8 tegcap[16]; + __u8 uegcap[16]; + __u8 rsvd192[320]; +}; + +struct nvme_rotational_media_log { + __le16 endgid; + __le16 numa; + __le16 nrs; + __u8 rsvd6[2]; + __le32 spinc; + __le32 fspinc; + __le32 ldc; + __le32 fldc; + __u8 rsvd24[488]; +}; + struct nvme_smart_log { __u8 critical_warning; __u8 temperature[2]; @@ -1244,6 +1283,7 @@ enum { NVME_FEAT_WRITE_PROTECT = 0x84, NVME_FEAT_VENDOR_START = 0xC0, NVME_FEAT_VENDOR_END = 0xFF, + NVME_LOG_SUPPORTED = 0x00, NVME_LOG_ERROR = 0x01, NVME_LOG_SMART = 0x02, NVME_LOG_FW_SLOT = 0x03, @@ -1254,6 +1294,8 @@ enum { NVME_LOG_TELEMETRY_CTRL = 0x08, NVME_LOG_ENDURANCE_GROUP = 0x09, NVME_LOG_ANA = 0x0c, + NVME_LOG_FEATURES = 0x12, + NVME_LOG_RMI = 0x16, NVME_LOG_DISC = 0x70, NVME_LOG_RESERVATION = 0x80, NVME_FWACT_REPL = (0 << 3), @@ -1261,6 +1303,24 @@ enum { NVME_FWACT_ACTV = (2 << 3), }; +struct nvme_supported_log { + __le32 lids[256]; +}; + +enum { + NVME_LIDS_LSUPP = 1 << 0, +}; + +struct nvme_supported_features_log { + __le32 fis[256]; +}; + +enum { + NVME_FIS_FSUPP = 1 << 0, + NVME_FIS_NSCPE = 1 << 20, + NVME_FIS_CSCPE = 1 << 21, +}; + /* NVMe Namespace Write Protect State */ enum { NVME_NS_NO_WRITE_PROTECT = 0, @@ -1281,7 +1341,8 @@ struct nvme_identify { __u8 cns; __u8 rsvd3; __le16 ctrlid; - __u8 rsvd11[3]; + __le16 cnssid; + __u8 rsvd11; __u8 csi; __u32 rsvd12[4]; }; @@ -1389,7 +1450,7 @@ struct nvme_get_log_page_command { __u8 lsp; /* upper 4 bits reserved */ __le16 numdl; __le16 numdu; - __u16 rsvd11; + __le16 lsi; union { struct { __le32 lpol; @@ -2037,4 +2098,72 @@ struct nvme_completion { #define NVME_MINOR(ver) (((ver) >> 8) & 0xff) #define NVME_TERTIARY(ver) ((ver) & 0xff) +enum { + NVME_AEN_RESV_LOG_PAGE_AVALIABLE = 0x00, +}; + +enum { + NVME_PR_LOG_EMPTY_LOG_PAGE = 0x00, + NVME_PR_LOG_REGISTRATION_PREEMPTED = 0x01, + NVME_PR_LOG_RESERVATION_RELEASED = 0x02, + NVME_PR_LOG_RESERVATOIN_PREEMPTED = 0x03, +}; + +enum { + NVME_PR_NOTIFY_BIT_REG_PREEMPTED = 1, + NVME_PR_NOTIFY_BIT_RESV_RELEASED = 2, + NVME_PR_NOTIFY_BIT_RESV_PREEMPTED = 3, +}; + +struct nvme_pr_log { + __le64 count; + __u8 type; + __u8 nr_pages; + __u8 rsvd1[2]; + __le32 nsid; + __u8 rsvd2[48]; +}; + +struct nvmet_pr_register_data { + __le64 crkey; + __le64 nrkey; +}; + +struct nvmet_pr_acquire_data { + __le64 crkey; + __le64 prkey; +}; + +struct nvmet_pr_release_data { + __le64 crkey; +}; + +enum nvme_pr_capabilities { + NVME_PR_SUPPORT_PTPL = 1, + NVME_PR_SUPPORT_WRITE_EXCLUSIVE = 1 << 1, + NVME_PR_SUPPORT_EXCLUSIVE_ACCESS = 1 << 2, + NVME_PR_SUPPORT_WRITE_EXCLUSIVE_REG_ONLY = 1 << 3, + NVME_PR_SUPPORT_EXCLUSIVE_ACCESS_REG_ONLY = 1 << 4, + NVME_PR_SUPPORT_WRITE_EXCLUSIVE_ALL_REGS = 1 << 5, + NVME_PR_SUPPORT_EXCLUSIVE_ACCESS_ALL_REGS = 1 << 6, + NVME_PR_SUPPORT_IEKEY_VER_1_3_DEF = 1 << 7, +}; + +enum nvme_pr_register_action { + NVME_PR_REGISTER_ACT_REG = 0, + NVME_PR_REGISTER_ACT_UNREG = 1, + NVME_PR_REGISTER_ACT_REPLACE = 1 << 1, +}; + +enum nvme_pr_acquire_action { + NVME_PR_ACQUIRE_ACT_ACQUIRE = 0, + NVME_PR_ACQUIRE_ACT_PREEMPT = 1, + NVME_PR_ACQUIRE_ACT_PREEMPT_AND_ABORT = 1 << 1, +}; + +enum nvme_pr_release_action { + NVME_PR_RELEASE_ACT_RELEASE = 0, + NVME_PR_RELEASE_ACT_CLEAR = 1, +}; + #endif /* _LINUX_NVME_H */ diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 1b3a76710487..908ee0aad554 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -543,7 +543,7 @@ FOLIO_FLAG(swapbacked, FOLIO_HEAD_PAGE) * - PG_private and PG_private_2 cause release_folio() and co to be invoked */ PAGEFLAG(Private, private, PF_ANY) -PAGEFLAG(Private2, private_2, PF_ANY) TESTSCFLAG(Private2, private_2, PF_ANY) +FOLIO_FLAG(private_2, FOLIO_HEAD_PAGE) /* owner_2 can be set on tail pages for anon memory */ FOLIO_FLAG(owner_2, FOLIO_HEAD_PAGE) @@ -554,7 +554,7 @@ FOLIO_FLAG(owner_2, FOLIO_HEAD_PAGE) */ TESTPAGEFLAG(Writeback, writeback, PF_NO_TAIL) TESTSCFLAG(Writeback, writeback, PF_NO_TAIL) -PAGEFLAG(MappedToDisk, mappedtodisk, PF_NO_TAIL) +FOLIO_FLAG(mappedtodisk, FOLIO_HEAD_PAGE) /* PG_readahead is only used for reads; PG_reclaim is only for writes */ PAGEFLAG(Reclaim, reclaim, PF_NO_TAIL) @@ -975,12 +975,16 @@ static __always_inline bool folio_test_##fname(const struct folio *folio) \ } \ static __always_inline void __folio_set_##fname(struct folio *folio) \ { \ + if (folio_test_##fname(folio)) \ + return; \ VM_BUG_ON_FOLIO(data_race(folio->page.page_type) != UINT_MAX, \ folio); \ folio->page.page_type = (unsigned int)PGTY_##lname << 24; \ } \ static __always_inline void __folio_clear_##fname(struct folio *folio) \ { \ + if (folio->page.page_type == UINT_MAX) \ + return; \ VM_BUG_ON_FOLIO(!folio_test_##fname(folio), folio); \ folio->page.page_type = UINT_MAX; \ } @@ -993,11 +997,15 @@ static __always_inline int Page##uname(const struct page *page) \ } \ static __always_inline void __SetPage##uname(struct page *page) \ { \ + if (Page##uname(page)) \ + return; \ VM_BUG_ON_PAGE(data_race(page->page_type) != UINT_MAX, page); \ page->page_type = (unsigned int)PGTY_##lname << 24; \ } \ static __always_inline void __ClearPage##uname(struct page *page) \ { \ + if (page->page_type == UINT_MAX) \ + return; \ VM_BUG_ON_PAGE(!Page##uname(page), page); \ page->page_type = UINT_MAX; \ } diff --git a/include/linux/percpu.h b/include/linux/percpu.h index b6321fc49159..52b5ea663b9f 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -41,7 +41,11 @@ PCPU_MIN_ALLOC_SHIFT) #ifdef CONFIG_RANDOM_KMALLOC_CACHES -#define PERCPU_DYNAMIC_SIZE_SHIFT 12 +# if defined(CONFIG_LOCKDEP) && !defined(CONFIG_PAGE_SIZE_4KB) +# define PERCPU_DYNAMIC_SIZE_SHIFT 13 +# else +# define PERCPU_DYNAMIC_SIZE_SHIFT 12 +#endif /* LOCKDEP and PAGE_SIZE > 4KiB */ #else #define PERCPU_DYNAMIC_SIZE_SHIFT 10 #endif diff --git a/include/linux/perf/arm_pmuv3.h b/include/linux/perf/arm_pmuv3.h index 3372c1b56486..d698efba28a2 100644 --- a/include/linux/perf/arm_pmuv3.h +++ b/include/linux/perf/arm_pmuv3.h @@ -257,6 +257,7 @@ #define ARMV8_PMU_USERENR_SW (1 << 1) /* PMSWINC can be written at EL0 */ #define ARMV8_PMU_USERENR_CR (1 << 2) /* Cycle counter can be read at EL0 */ #define ARMV8_PMU_USERENR_ER (1 << 3) /* Event counter can be read at EL0 */ +#define ARMV8_PMU_USERENR_UEN (1 << 4) /* Fine grained per counter access at EL0 */ /* Mask for writable bits */ #define ARMV8_PMU_USERENR_MASK (ARMV8_PMU_USERENR_EN | ARMV8_PMU_USERENR_SW | \ ARMV8_PMU_USERENR_CR | ARMV8_PMU_USERENR_ER) diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index fb908843f209..cb99ec8c9e96 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -170,6 +170,12 @@ struct hw_perf_event { }; struct { /* aux / Intel-PT */ u64 aux_config; + /* + * For AUX area events, aux_paused cannot be a state + * flag because it can be updated asynchronously to + * state. + */ + unsigned int aux_paused; }; struct { /* software */ struct hrtimer hrtimer; @@ -294,6 +300,7 @@ struct perf_event_pmu_context; #define PERF_PMU_CAP_NO_EXCLUDE 0x0040 #define PERF_PMU_CAP_AUX_OUTPUT 0x0080 #define PERF_PMU_CAP_EXTENDED_HW_TYPE 0x0100 +#define PERF_PMU_CAP_AUX_PAUSE 0x0200 /** * pmu::scope @@ -384,6 +391,8 @@ struct pmu { #define PERF_EF_START 0x01 /* start the counter when adding */ #define PERF_EF_RELOAD 0x02 /* reload the counter when starting */ #define PERF_EF_UPDATE 0x04 /* update the counter when stopping */ +#define PERF_EF_PAUSE 0x08 /* AUX area event, pause tracing */ +#define PERF_EF_RESUME 0x10 /* AUX area event, resume tracing */ /* * Adds/Removes a counter to/from the PMU, can be done inside a @@ -423,6 +432,18 @@ struct pmu { * * ->start() with PERF_EF_RELOAD will reprogram the counter * value, must be preceded by a ->stop() with PERF_EF_UPDATE. + * + * ->stop() with PERF_EF_PAUSE will stop as simply as possible. Will not + * overlap another ->stop() with PERF_EF_PAUSE nor ->start() with + * PERF_EF_RESUME. + * + * ->start() with PERF_EF_RESUME will start as simply as possible but + * only if the counter is not otherwise stopped. Will not overlap + * another ->start() with PERF_EF_RESUME nor ->stop() with + * PERF_EF_PAUSE. + * + * Notably, PERF_EF_PAUSE/PERF_EF_RESUME *can* be concurrent with other + * ->stop()/->start() invocations, just not itself. */ void (*start) (struct perf_event *event, int flags); void (*stop) (struct perf_event *event, int flags); @@ -1655,15 +1676,35 @@ extern void perf_tp_event(u16 event_type, u64 count, void *record, struct task_struct *task); extern void perf_bp_event(struct perf_event *event, void *data); -#ifndef perf_misc_flags -# define perf_misc_flags(regs) \ +extern unsigned long perf_misc_flags(struct perf_event *event, struct pt_regs *regs); +extern unsigned long perf_instruction_pointer(struct perf_event *event, + struct pt_regs *regs); + +#ifndef perf_arch_misc_flags +# define perf_arch_misc_flags(regs) \ (user_mode(regs) ? PERF_RECORD_MISC_USER : PERF_RECORD_MISC_KERNEL) -# define perf_instruction_pointer(regs) instruction_pointer(regs) +# define perf_arch_instruction_pointer(regs) instruction_pointer(regs) #endif #ifndef perf_arch_bpf_user_pt_regs # define perf_arch_bpf_user_pt_regs(regs) regs #endif +#ifndef perf_arch_guest_misc_flags +static inline unsigned long perf_arch_guest_misc_flags(struct pt_regs *regs) +{ + unsigned long guest_state = perf_guest_state(); + + if (!(guest_state & PERF_GUEST_ACTIVE)) + return 0; + + if (guest_state & PERF_GUEST_USER) + return PERF_RECORD_MISC_GUEST_USER; + else + return PERF_RECORD_MISC_GUEST_KERNEL; +} +# define perf_arch_guest_misc_flags(regs) perf_arch_guest_misc_flags(regs) +#endif + static inline bool has_branch_stack(struct perf_event *event) { return event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK; @@ -1679,6 +1720,13 @@ static inline bool has_aux(struct perf_event *event) return event->pmu->setup_aux; } +static inline bool has_aux_action(struct perf_event *event) +{ + return event->attr.aux_sample_size || + event->attr.aux_pause || + event->attr.aux_resume; +} + static inline bool is_write_backward(struct perf_event *event) { return !!event->attr.write_backward; diff --git a/include/linux/platform_data/max6639.h b/include/linux/platform_data/max6639.h deleted file mode 100644 index 65bfdb4fdc15..000000000000 --- a/include/linux/platform_data/max6639.h +++ /dev/null @@ -1,15 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_MAX6639_H -#define _LINUX_MAX6639_H - -#include <linux/types.h> - -/* platform data for the MAX6639 temperature sensor and fan control */ - -struct max6639_platform_data { - bool pwm_polarity; /* Polarity low (0) or high (1, default) */ - int ppr; /* Pulses per rotation 1..4 (default == 2) */ - int rpm_range; /* 2000, 4000 (default), 8000 or 16000 */ -}; - -#endif /* _LINUX_MAX6639_H */ diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index b637ec14025f..cf4b11be3709 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -92,6 +92,10 @@ struct dev_pm_domain_list { * GENPD_FLAG_OPP_TABLE_FW: The genpd provider supports performance states, * but its corresponding OPP tables are not * described in DT, but are given directly by FW. + * + * GENPD_FLAG_DEV_NAME_FW: Instructs genpd to generate an unique device name + * using ida. It is used by genpd providers which + * get their genpd-names directly from FW. */ #define GENPD_FLAG_PM_CLK (1U << 0) #define GENPD_FLAG_IRQ_SAFE (1U << 1) @@ -101,6 +105,7 @@ struct dev_pm_domain_list { #define GENPD_FLAG_RPM_ALWAYS_ON (1U << 5) #define GENPD_FLAG_MIN_RESIDENCY (1U << 6) #define GENPD_FLAG_OPP_TABLE_FW (1U << 7) +#define GENPD_FLAG_DEV_NAME_FW (1U << 8) enum gpd_status { GENPD_STATE_ON = 0, /* PM domain is on */ @@ -163,6 +168,7 @@ struct generic_pm_domain { atomic_t sd_count; /* Number of subdomains with power "on" */ enum gpd_status status; /* Current state of the domain */ unsigned int device_count; /* Number of devices */ + unsigned int device_id; /* unique device id */ unsigned int suspended_count; /* System suspend device counter */ unsigned int prepared_count; /* Suspend counter of prepared devices */ unsigned int performance_state; /* Aggregated max performance state */ diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index 0e65b3d634d9..e2d47eb1a7f3 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -28,9 +28,9 @@ struct posix_acl_entry { struct posix_acl { refcount_t a_refcount; - struct rcu_head a_rcu; unsigned int a_count; - struct posix_acl_entry a_entries[]; + struct rcu_head a_rcu; + struct posix_acl_entry a_entries[] __counted_by(a_count); }; #define FOREACH_ACL_ENTRY(pa, acl, pe) \ @@ -62,7 +62,7 @@ posix_acl_release(struct posix_acl *acl) /* posix_acl.c */ extern void posix_acl_init(struct posix_acl *, int); -extern struct posix_acl *posix_acl_alloc(int, gfp_t); +extern struct posix_acl *posix_acl_alloc(unsigned int count, gfp_t flags); extern struct posix_acl *posix_acl_from_mode(umode_t, gfp_t); extern int posix_acl_equiv_mode(const struct posix_acl *, umode_t *); extern int __posix_acl_create(struct posix_acl **, gfp_t, umode_t *); diff --git a/include/linux/prandom.h b/include/linux/prandom.h index f7f1e5251c67..f2ed5b72b3d6 100644 --- a/include/linux/prandom.h +++ b/include/linux/prandom.h @@ -10,6 +10,7 @@ #include <linux/types.h> #include <linux/once.h> +#include <linux/percpu.h> #include <linux/random.h> struct rnd_state { diff --git a/include/linux/preempt.h b/include/linux/preempt.h index ce76f1a45722..ca86235ac15c 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -486,6 +486,7 @@ DEFINE_LOCK_GUARD_0(migrate, migrate_disable(), migrate_enable()) extern bool preempt_model_none(void); extern bool preempt_model_voluntary(void); extern bool preempt_model_full(void); +extern bool preempt_model_lazy(void); #else @@ -502,6 +503,11 @@ static inline bool preempt_model_full(void) return IS_ENABLED(CONFIG_PREEMPT); } +static inline bool preempt_model_lazy(void) +{ + return IS_ENABLED(CONFIG_PREEMPT_LAZY); +} + #endif static inline bool preempt_model_rt(void) @@ -519,7 +525,7 @@ static inline bool preempt_model_rt(void) */ static inline bool preempt_model_preemptible(void) { - return preempt_model_full() || preempt_model_rt(); + return preempt_model_full() || preempt_model_lazy() || preempt_model_rt(); } #endif /* __LINUX_PREEMPT_H */ diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h index 1b5a953c6bbc..3a74f69e0b59 100644 --- a/include/linux/ptp_classify.h +++ b/include/linux/ptp_classify.h @@ -10,7 +10,7 @@ #ifndef _PTP_CLASSIFY_H_ #define _PTP_CLASSIFY_H_ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/ip.h> #include <linux/ktime.h> #include <linux/skbuff.h> diff --git a/include/linux/random.h b/include/linux/random.h index b0a940af4fff..333cecfca93f 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -145,13 +145,6 @@ declare_get_random_var_wait(u64, u32) declare_get_random_var_wait(long, unsigned long) #undef declare_get_random_var -/* - * This is designed to be standalone for just prandom - * users, but for now we include it from <linux/random.h> - * for legacy reasons. - */ -#include <linux/prandom.h> - #ifdef CONFIG_SMP int random_prepare_cpu(unsigned int cpu); int random_online_cpu(unsigned int cpu); diff --git a/include/linux/rbtree_latch.h b/include/linux/rbtree_latch.h index 6a0999c26c7c..2f630eb8307e 100644 --- a/include/linux/rbtree_latch.h +++ b/include/linux/rbtree_latch.h @@ -14,7 +14,7 @@ * * If we need to allow unconditional lookups (say as required for NMI context * usage) we need a more complex setup; this data structure provides this by - * employing the latch technique -- see @raw_write_seqcount_latch -- to + * employing the latch technique -- see @write_seqcount_latch_begin -- to * implement a latched RB-tree which does allow for unconditional lookups by * virtue of always having (at least) one stable copy of the tree. * @@ -132,7 +132,7 @@ __lt_find(void *key, struct latch_tree_root *ltr, int idx, * @ops: operators defining the node order * * It inserts @node into @root in an ordered fashion such that we can always - * observe one complete tree. See the comment for raw_write_seqcount_latch(). + * observe one complete tree. See the comment for write_seqcount_latch_begin(). * * The inserts use rcu_assign_pointer() to publish the element such that the * tree structure is stored before we can observe the new @node. @@ -145,10 +145,11 @@ latch_tree_insert(struct latch_tree_node *node, struct latch_tree_root *root, const struct latch_tree_ops *ops) { - raw_write_seqcount_latch(&root->seq); + write_seqcount_latch_begin(&root->seq); __lt_insert(node, root, 0, ops->less); - raw_write_seqcount_latch(&root->seq); + write_seqcount_latch(&root->seq); __lt_insert(node, root, 1, ops->less); + write_seqcount_latch_end(&root->seq); } /** @@ -159,7 +160,7 @@ latch_tree_insert(struct latch_tree_node *node, * * Removes @node from the trees @root in an ordered fashion such that we can * always observe one complete tree. See the comment for - * raw_write_seqcount_latch(). + * write_seqcount_latch_begin(). * * It is assumed that @node will observe one RCU quiescent state before being * reused of freed. @@ -172,10 +173,11 @@ latch_tree_erase(struct latch_tree_node *node, struct latch_tree_root *root, const struct latch_tree_ops *ops) { - raw_write_seqcount_latch(&root->seq); + write_seqcount_latch_begin(&root->seq); __lt_erase(node, root, 0); - raw_write_seqcount_latch(&root->seq); + write_seqcount_latch(&root->seq); __lt_erase(node, root, 1); + write_seqcount_latch_end(&root->seq); } /** @@ -204,9 +206,9 @@ latch_tree_find(void *key, struct latch_tree_root *root, unsigned int seq; do { - seq = raw_read_seqcount_latch(&root->seq); + seq = read_seqcount_latch(&root->seq); node = __lt_find(key, root, seq & 1, ops->comp); - } while (raw_read_seqcount_latch_retry(&root->seq, seq)); + } while (read_seqcount_latch_retry(&root->seq, seq)); return node; } diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 0ee270b3f5ed..fe42315f667f 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -165,7 +165,6 @@ static inline bool rcu_inkernel_boot_has_ended(void) { return true; } static inline bool rcu_is_watching(void) { return true; } static inline void rcu_momentary_eqs(void) { } static inline void kfree_rcu_scheduler_running(void) { } -static inline bool rcu_gp_might_be_stalled(void) { return false; } /* Avoid RCU read-side critical sections leaking across. */ static inline void rcu_all_qs(void) { barrier(); } diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 90a684f94776..27d86d912781 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -40,7 +40,6 @@ void kvfree_rcu_barrier(void); void rcu_barrier(void); void rcu_momentary_eqs(void); void kfree_rcu_scheduler_running(void); -bool rcu_gp_might_be_stalled(void); struct rcu_gp_oldstate { unsigned long rgos_norm; diff --git a/include/linux/rwlock_rt.h b/include/linux/rwlock_rt.h index 8544ff05e594..7d81fc6918ee 100644 --- a/include/linux/rwlock_rt.h +++ b/include/linux/rwlock_rt.h @@ -24,13 +24,13 @@ do { \ __rt_rwlock_init(rwl, #rwl, &__key); \ } while (0) -extern void rt_read_lock(rwlock_t *rwlock); +extern void rt_read_lock(rwlock_t *rwlock) __acquires(rwlock); extern int rt_read_trylock(rwlock_t *rwlock); -extern void rt_read_unlock(rwlock_t *rwlock); -extern void rt_write_lock(rwlock_t *rwlock); -extern void rt_write_lock_nested(rwlock_t *rwlock, int subclass); +extern void rt_read_unlock(rwlock_t *rwlock) __releases(rwlock); +extern void rt_write_lock(rwlock_t *rwlock) __acquires(rwlock); +extern void rt_write_lock_nested(rwlock_t *rwlock, int subclass) __acquires(rwlock); extern int rt_write_trylock(rwlock_t *rwlock); -extern void rt_write_unlock(rwlock_t *rwlock); +extern void rt_write_unlock(rwlock_t *rwlock) __releases(rwlock); static __always_inline void read_lock(rwlock_t *rwlock) { diff --git a/include/linux/sched.h b/include/linux/sched.h index e6ee4258169a..5a2cdd9d8b10 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1001,7 +1001,7 @@ struct task_struct { #ifdef CONFIG_ARCH_HAS_CPU_PASID unsigned pasid_activated:1; #endif -#ifdef CONFIG_CPU_SUP_INTEL +#ifdef CONFIG_X86_BUS_LOCK_DETECT unsigned reported_split_lock:1; #endif #ifdef CONFIG_TASK_DELAY_ACCT @@ -1681,8 +1681,8 @@ extern struct pid *cad_pid; * I am cleaning dirty pages from some other bdi. */ #define PF_KTHREAD 0x00200000 /* I am a kernel thread */ #define PF_RANDOMIZE 0x00400000 /* Randomize virtual address space */ -#define PF_MEMALLOC_NORECLAIM 0x00800000 /* All allocation requests will clear __GFP_DIRECT_RECLAIM */ -#define PF_MEMALLOC_NOWARN 0x01000000 /* All allocation requests will inherit __GFP_NOWARN */ +#define PF__HOLE__00800000 0x00800000 +#define PF__HOLE__01000000 0x01000000 #define PF__HOLE__02000000 0x02000000 #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_mask */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ @@ -1898,7 +1898,7 @@ extern unsigned long init_stack[THREAD_SIZE / sizeof(unsigned long)]; #ifdef CONFIG_THREAD_INFO_IN_TASK # define task_thread_info(task) (&(task)->thread_info) -#elif !defined(__HAVE_THREAD_FUNCTIONS) +#else # define task_thread_info(task) ((struct thread_info *)(task)->stack) #endif @@ -2002,7 +2002,8 @@ static inline void set_tsk_need_resched(struct task_struct *tsk) static inline void clear_tsk_need_resched(struct task_struct *tsk) { - clear_tsk_thread_flag(tsk,TIF_NEED_RESCHED); + atomic_long_andnot(_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY, + (atomic_long_t *)&task_thread_info(tsk)->flags); } static inline int test_tsk_need_resched(struct task_struct *tsk) @@ -2133,6 +2134,11 @@ static inline void set_task_cpu(struct task_struct *p, unsigned int cpu) #endif /* CONFIG_SMP */ +static inline bool task_is_runnable(struct task_struct *p) +{ + return p->on_rq && !p->se.sched_delayed; +} + extern bool sched_task_on_rq(struct task_struct *p); extern unsigned long get_wchan(struct task_struct *p); extern struct task_struct *cpu_curr_snapshot(int cpu); diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h index 1ddbde64a31b..2799e7284fff 100644 --- a/include/linux/sched/ext.h +++ b/include/linux/sched/ext.h @@ -199,7 +199,6 @@ struct sched_ext_entity { #ifdef CONFIG_EXT_GROUP_SCHED struct cgroup *cgrp_moving_from; #endif - /* must be the last field, see init_scx_entity() */ struct list_head tasks_node; }; diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 07bb8d4181d7..928a626725e6 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -251,25 +251,16 @@ static inline gfp_t current_gfp_context(gfp_t flags) { unsigned int pflags = READ_ONCE(current->flags); - if (unlikely(pflags & (PF_MEMALLOC_NOIO | - PF_MEMALLOC_NOFS | - PF_MEMALLOC_NORECLAIM | - PF_MEMALLOC_NOWARN | - PF_MEMALLOC_PIN))) { + if (unlikely(pflags & (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS | PF_MEMALLOC_PIN))) { /* - * Stronger flags before weaker flags: - * NORECLAIM implies NOIO, which in turn implies NOFS + * NOIO implies both NOIO and NOFS and it is a weaker context + * so always make sure it makes precedence */ - if (pflags & PF_MEMALLOC_NORECLAIM) - flags &= ~__GFP_DIRECT_RECLAIM; - else if (pflags & PF_MEMALLOC_NOIO) + if (pflags & PF_MEMALLOC_NOIO) flags &= ~(__GFP_IO | __GFP_FS); else if (pflags & PF_MEMALLOC_NOFS) flags &= ~__GFP_FS; - if (pflags & PF_MEMALLOC_NOWARN) - flags |= __GFP_NOWARN; - if (pflags & PF_MEMALLOC_PIN) flags &= ~__GFP_MOVABLE; } diff --git a/include/linux/sched/task_stack.h b/include/linux/sched/task_stack.h index bf10bdb487dd..cffad65bdc6a 100644 --- a/include/linux/sched/task_stack.h +++ b/include/linux/sched/task_stack.h @@ -9,6 +9,7 @@ #include <linux/sched.h> #include <linux/magic.h> #include <linux/refcount.h> +#include <linux/kasan.h> #ifdef CONFIG_THREAD_INFO_IN_TASK @@ -33,7 +34,7 @@ static __always_inline unsigned long *end_of_stack(const struct task_struct *tas #endif } -#elif !defined(__HAVE_THREAD_FUNCTIONS) +#else #define task_stack_page(task) ((void *)(task)->stack) @@ -89,6 +90,7 @@ static inline int object_is_on_stack(const void *obj) { void *stack = task_stack_page(current); + obj = kasan_reset_tag(obj); return (obj >= stack) && (obj < (stack + THREAD_SIZE)); } diff --git a/include/linux/security.h b/include/linux/security.h index b86ec2afc691..cbdba435b798 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -34,6 +34,10 @@ #include <linux/sockptr.h> #include <linux/bpf.h> #include <uapi/linux/lsm.h> +#include <linux/lsm/selinux.h> +#include <linux/lsm/smack.h> +#include <linux/lsm/apparmor.h> +#include <linux/lsm/bpf.h> struct linux_binprm; struct cred; @@ -152,6 +156,16 @@ enum lockdown_reason { LOCKDOWN_CONFIDENTIALITY_MAX, }; +/* + * Data exported by the security modules + */ +struct lsm_prop { + struct lsm_prop_selinux selinux; + struct lsm_prop_smack smack; + struct lsm_prop_apparmor apparmor; + struct lsm_prop_bpf bpf; +}; + extern const char *const lockdown_reasons[LOCKDOWN_CONFIDENTIALITY_MAX+1]; extern u32 lsm_active_cnt; extern const struct lsm_id *lsm_idlist[]; @@ -269,8 +283,32 @@ static inline const char *kernel_load_data_id_str(enum kernel_load_data_id id) return kernel_load_data_str[id]; } +/** + * lsmprop_init - initialize a lsm_prop structure + * @prop: Pointer to the data to initialize + * + * Set all secid for all modules to the specified value. + */ +static inline void lsmprop_init(struct lsm_prop *prop) +{ + memset(prop, 0, sizeof(*prop)); +} + #ifdef CONFIG_SECURITY +/** + * lsmprop_is_set - report if there is a value in the lsm_prop + * @prop: Pointer to the exported LSM data + * + * Returns true if there is a value set, false otherwise + */ +static inline bool lsmprop_is_set(struct lsm_prop *prop) +{ + const struct lsm_prop empty = {}; + + return !!memcmp(prop, &empty, sizeof(*prop)); +} + int call_blocking_lsm_notifier(enum lsm_event event, void *data); int register_blocking_lsm_notifier(struct notifier_block *nb); int unregister_blocking_lsm_notifier(struct notifier_block *nb); @@ -348,7 +386,7 @@ int security_dentry_create_files_as(struct dentry *dentry, int mode, struct cred *new); int security_path_notify(const struct path *path, u64 mask, unsigned int obj_type); -int security_inode_alloc(struct inode *inode); +int security_inode_alloc(struct inode *inode, gfp_t gfp); void security_inode_free(struct inode *inode); int security_inode_init_security(struct inode *inode, struct inode *dir, const struct qstr *qstr, @@ -408,7 +446,7 @@ int security_inode_getsecurity(struct mnt_idmap *idmap, void **buffer, bool alloc); int security_inode_setsecurity(struct inode *inode, const char *name, const void *value, size_t size, int flags); int security_inode_listsecurity(struct inode *inode, char *buffer, size_t buffer_size); -void security_inode_getsecid(struct inode *inode, u32 *secid); +void security_inode_getlsmprop(struct inode *inode, struct lsm_prop *prop); int security_inode_copy_up(struct dentry *src, struct cred **new); int security_inode_copy_up_xattr(struct dentry *src, const char *name); int security_inode_setintegrity(const struct inode *inode, @@ -444,6 +482,7 @@ void security_cred_free(struct cred *cred); int security_prepare_creds(struct cred *new, const struct cred *old, gfp_t gfp); void security_transfer_creds(struct cred *new, const struct cred *old); void security_cred_getsecid(const struct cred *c, u32 *secid); +void security_cred_getlsmprop(const struct cred *c, struct lsm_prop *prop); int security_kernel_act_as(struct cred *new, u32 secid); int security_kernel_create_files_as(struct cred *new, struct inode *inode); int security_kernel_module_request(char *kmod_name); @@ -463,8 +502,8 @@ int security_task_fix_setgroups(struct cred *new, const struct cred *old); int security_task_setpgid(struct task_struct *p, pid_t pgid); int security_task_getpgid(struct task_struct *p); int security_task_getsid(struct task_struct *p); -void security_current_getsecid_subj(u32 *secid); -void security_task_getsecid_obj(struct task_struct *p, u32 *secid); +void security_current_getlsmprop_subj(struct lsm_prop *prop); +void security_task_getlsmprop_obj(struct task_struct *p, struct lsm_prop *prop); int security_task_setnice(struct task_struct *p, int nice); int security_task_setioprio(struct task_struct *p, int ioprio); int security_task_getioprio(struct task_struct *p); @@ -482,7 +521,7 @@ int security_task_prctl(int option, unsigned long arg2, unsigned long arg3, void security_task_to_inode(struct task_struct *p, struct inode *inode); int security_create_user_ns(const struct cred *cred); int security_ipc_permission(struct kern_ipc_perm *ipcp, short flag); -void security_ipc_getsecid(struct kern_ipc_perm *ipcp, u32 *secid); +void security_ipc_getlsmprop(struct kern_ipc_perm *ipcp, struct lsm_prop *prop); int security_msg_msg_alloc(struct msg_msg *msg); void security_msg_msg_free(struct msg_msg *msg); int security_msg_queue_alloc(struct kern_ipc_perm *msq); @@ -515,6 +554,7 @@ int security_setprocattr(int lsmid, const char *name, void *value, size_t size); int security_netlink_send(struct sock *sk, struct sk_buff *skb); int security_ismaclabel(const char *name); int security_secid_to_secctx(u32 secid, char **secdata, u32 *seclen); +int security_lsmprop_to_secctx(struct lsm_prop *prop, char **secdata, u32 *seclen); int security_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid); void security_release_secctx(char *secdata, u32 seclen); void security_inode_invalidate_secctx(struct inode *inode); @@ -531,6 +571,17 @@ int security_bdev_setintegrity(struct block_device *bdev, size_t size); #else /* CONFIG_SECURITY */ +/** + * lsmprop_is_set - report if there is a value in the lsm_prop + * @prop: Pointer to the exported LSM data + * + * Returns true if there is a value set, false otherwise + */ +static inline bool lsmprop_is_set(struct lsm_prop *prop) +{ + return false; +} + static inline int call_blocking_lsm_notifier(enum lsm_event event, void *data) { return 0; @@ -789,7 +840,7 @@ static inline int security_path_notify(const struct path *path, u64 mask, return 0; } -static inline int security_inode_alloc(struct inode *inode) +static inline int security_inode_alloc(struct inode *inode, gfp_t gfp) { return 0; } @@ -1020,9 +1071,10 @@ static inline int security_inode_listsecurity(struct inode *inode, char *buffer, return 0; } -static inline void security_inode_getsecid(struct inode *inode, u32 *secid) +static inline void security_inode_getlsmprop(struct inode *inode, + struct lsm_prop *prop) { - *secid = 0; + lsmprop_init(prop); } static inline int security_inode_copy_up(struct dentry *src, struct cred **new) @@ -1172,6 +1224,10 @@ static inline void security_cred_getsecid(const struct cred *c, u32 *secid) *secid = 0; } +static inline void security_cred_getlsmprop(const struct cred *c, + struct lsm_prop *prop) +{ } + static inline int security_kernel_act_as(struct cred *cred, u32 secid) { return 0; @@ -1249,14 +1305,15 @@ static inline int security_task_getsid(struct task_struct *p) return 0; } -static inline void security_current_getsecid_subj(u32 *secid) +static inline void security_current_getlsmprop_subj(struct lsm_prop *prop) { - *secid = 0; + lsmprop_init(prop); } -static inline void security_task_getsecid_obj(struct task_struct *p, u32 *secid) +static inline void security_task_getlsmprop_obj(struct task_struct *p, + struct lsm_prop *prop) { - *secid = 0; + lsmprop_init(prop); } static inline int security_task_setnice(struct task_struct *p, int nice) @@ -1332,9 +1389,10 @@ static inline int security_ipc_permission(struct kern_ipc_perm *ipcp, return 0; } -static inline void security_ipc_getsecid(struct kern_ipc_perm *ipcp, u32 *secid) +static inline void security_ipc_getlsmprop(struct kern_ipc_perm *ipcp, + struct lsm_prop *prop) { - *secid = 0; + lsmprop_init(prop); } static inline int security_msg_msg_alloc(struct msg_msg *msg) @@ -1468,7 +1526,14 @@ static inline int security_ismaclabel(const char *name) return 0; } -static inline int security_secid_to_secctx(u32 secid, char **secdata, u32 *seclen) +static inline int security_secid_to_secctx(u32 secid, char **secdata, + u32 *seclen) +{ + return -EOPNOTSUPP; +} + +static inline int security_lsmprop_to_secctx(struct lsm_prop *prop, + char **secdata, u32 *seclen) { return -EOPNOTSUPP; } @@ -2095,7 +2160,8 @@ static inline void security_key_post_create_or_update(struct key *keyring, int security_audit_rule_init(u32 field, u32 op, char *rulestr, void **lsmrule, gfp_t gfp); int security_audit_rule_known(struct audit_krule *krule); -int security_audit_rule_match(u32 secid, u32 field, u32 op, void *lsmrule); +int security_audit_rule_match(struct lsm_prop *prop, u32 field, u32 op, + void *lsmrule); void security_audit_rule_free(void *lsmrule); #else @@ -2111,8 +2177,8 @@ static inline int security_audit_rule_known(struct audit_krule *krule) return 0; } -static inline int security_audit_rule_match(u32 secid, u32 field, u32 op, - void *lsmrule) +static inline int security_audit_rule_match(struct lsm_prop *prop, u32 field, + u32 op, void *lsmrule) { return 0; } diff --git a/include/linux/sed-opal.h b/include/linux/sed-opal.h index 2ac50822554e..80f33a93f944 100644 --- a/include/linux/sed-opal.h +++ b/include/linux/sed-opal.h @@ -52,6 +52,7 @@ static inline bool is_sed_ioctl(unsigned int cmd) case IOC_OPAL_GET_GEOMETRY: case IOC_OPAL_DISCOVERY: case IOC_OPAL_REVERT_LSP: + case IOC_OPAL_SET_SID_PW: return true; } return false; diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index fffeb754880f..5298765d6ca4 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -622,6 +622,23 @@ static __always_inline unsigned raw_read_seqcount_latch(const seqcount_latch_t * } /** + * read_seqcount_latch() - pick even/odd latch data copy + * @s: Pointer to seqcount_latch_t + * + * See write_seqcount_latch() for details and a full reader/writer usage + * example. + * + * Return: sequence counter raw value. Use the lowest bit as an index for + * picking which data copy to read. The full counter must then be checked + * with read_seqcount_latch_retry(). + */ +static __always_inline unsigned read_seqcount_latch(const seqcount_latch_t *s) +{ + kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX); + return raw_read_seqcount_latch(s); +} + +/** * raw_read_seqcount_latch_retry() - end a seqcount_latch_t read section * @s: Pointer to seqcount_latch_t * @start: count, from raw_read_seqcount_latch() @@ -636,8 +653,33 @@ raw_read_seqcount_latch_retry(const seqcount_latch_t *s, unsigned start) } /** + * read_seqcount_latch_retry() - end a seqcount_latch_t read section + * @s: Pointer to seqcount_latch_t + * @start: count, from read_seqcount_latch() + * + * Return: true if a read section retry is required, else false + */ +static __always_inline int +read_seqcount_latch_retry(const seqcount_latch_t *s, unsigned start) +{ + kcsan_atomic_next(0); + return raw_read_seqcount_latch_retry(s, start); +} + +/** * raw_write_seqcount_latch() - redirect latch readers to even/odd copy * @s: Pointer to seqcount_latch_t + */ +static __always_inline void raw_write_seqcount_latch(seqcount_latch_t *s) +{ + smp_wmb(); /* prior stores before incrementing "sequence" */ + s->seqcount.sequence++; + smp_wmb(); /* increment "sequence" before following stores */ +} + +/** + * write_seqcount_latch_begin() - redirect latch readers to odd copy + * @s: Pointer to seqcount_latch_t * * The latch technique is a multiversion concurrency control method that allows * queries during non-atomic modifications. If you can guarantee queries never @@ -665,17 +707,11 @@ raw_read_seqcount_latch_retry(const seqcount_latch_t *s, unsigned start) * * void latch_modify(struct latch_struct *latch, ...) * { - * smp_wmb(); // Ensure that the last data[1] update is visible - * latch->seq.sequence++; - * smp_wmb(); // Ensure that the seqcount update is visible - * + * write_seqcount_latch_begin(&latch->seq); * modify(latch->data[0], ...); - * - * smp_wmb(); // Ensure that the data[0] update is visible - * latch->seq.sequence++; - * smp_wmb(); // Ensure that the seqcount update is visible - * + * write_seqcount_latch(&latch->seq); * modify(latch->data[1], ...); + * write_seqcount_latch_end(&latch->seq); * } * * The query will have a form like:: @@ -686,13 +722,13 @@ raw_read_seqcount_latch_retry(const seqcount_latch_t *s, unsigned start) * unsigned seq, idx; * * do { - * seq = raw_read_seqcount_latch(&latch->seq); + * seq = read_seqcount_latch(&latch->seq); * * idx = seq & 0x01; * entry = data_query(latch->data[idx], ...); * * // This includes needed smp_rmb() - * } while (raw_read_seqcount_latch_retry(&latch->seq, seq)); + * } while (read_seqcount_latch_retry(&latch->seq, seq)); * * return entry; * } @@ -716,11 +752,31 @@ raw_read_seqcount_latch_retry(const seqcount_latch_t *s, unsigned start) * When data is a dynamic data structure; one should use regular RCU * patterns to manage the lifetimes of the objects within. */ -static inline void raw_write_seqcount_latch(seqcount_latch_t *s) +static __always_inline void write_seqcount_latch_begin(seqcount_latch_t *s) { - smp_wmb(); /* prior stores before incrementing "sequence" */ - s->seqcount.sequence++; - smp_wmb(); /* increment "sequence" before following stores */ + kcsan_nestable_atomic_begin(); + raw_write_seqcount_latch(s); +} + +/** + * write_seqcount_latch() - redirect latch readers to even copy + * @s: Pointer to seqcount_latch_t + */ +static __always_inline void write_seqcount_latch(seqcount_latch_t *s) +{ + raw_write_seqcount_latch(s); +} + +/** + * write_seqcount_latch_end() - end a seqcount_latch_t write section + * @s: Pointer to seqcount_latch_t + * + * Marks the end of a seqcount_latch_t writer section, after all copies of the + * latch-protected data have been updated. + */ +static __always_inline void write_seqcount_latch_end(seqcount_latch_t *s) +{ + kcsan_nestable_atomic_end(); } #define __SEQLOCK_UNLOCKED(lockname) \ @@ -754,11 +810,7 @@ static inline void raw_write_seqcount_latch(seqcount_latch_t *s) */ static inline unsigned read_seqbegin(const seqlock_t *sl) { - unsigned ret = read_seqcount_begin(&sl->seqcount); - - kcsan_atomic_next(0); /* non-raw usage, assume closing read_seqretry() */ - kcsan_flat_atomic_begin(); - return ret; + return read_seqcount_begin(&sl->seqcount); } /** @@ -774,12 +826,6 @@ static inline unsigned read_seqbegin(const seqlock_t *sl) */ static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start) { - /* - * Assume not nested: read_seqretry() may be called multiple times when - * completing read critical section. - */ - kcsan_flat_atomic_end(); - return read_seqcount_retry(&sl->seqcount, start); } diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 515a9a6a3c6f..018da28c01e7 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -42,10 +42,10 @@ struct shmem_inode_info { struct inode vfs_inode; }; -#define SHMEM_FL_USER_VISIBLE FS_FL_USER_VISIBLE +#define SHMEM_FL_USER_VISIBLE (FS_FL_USER_VISIBLE | FS_CASEFOLD_FL) #define SHMEM_FL_USER_MODIFIABLE \ - (FS_IMMUTABLE_FL | FS_APPEND_FL | FS_NODUMP_FL | FS_NOATIME_FL) -#define SHMEM_FL_INHERITED (FS_NODUMP_FL | FS_NOATIME_FL) + (FS_IMMUTABLE_FL | FS_APPEND_FL | FS_NODUMP_FL | FS_NOATIME_FL | FS_CASEFOLD_FL) +#define SHMEM_FL_INHERITED (FS_NODUMP_FL | FS_NOATIME_FL | FS_CASEFOLD_FL) struct shmem_quota_limits { qsize_t usrquota_bhardlimit; /* Default user quota block hard limit */ diff --git a/include/linux/slab.h b/include/linux/slab.h index b35e2db7eb0e..0268ea7abf8b 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -448,6 +448,7 @@ void kfree_sensitive(const void *objp); size_t __ksize(const void *objp); DEFINE_FREE(kfree, void *, if (!IS_ERR_OR_NULL(_T)) kfree(_T)) +DEFINE_FREE(kfree_sensitive, void *, if (_T) kfree_sensitive(_T)) /** * ksize - Report actual allocation size of associated object diff --git a/include/linux/soc/qcom/geni-se.h b/include/linux/soc/qcom/geni-se.h index c3bca9c0bf2c..2996a3c28ef3 100644 --- a/include/linux/soc/qcom/geni-se.h +++ b/include/linux/soc/qcom/geni-se.h @@ -258,8 +258,8 @@ struct geni_se { #define RX_DMA_PARITY_ERR BIT(5) #define RX_DMA_BREAK GENMASK(8, 7) #define RX_GENI_GP_IRQ GENMASK(10, 5) -#define RX_GENI_CANCEL_IRQ BIT(11) #define RX_GENI_GP_IRQ_EXT GENMASK(13, 12) +#define RX_GENI_CANCEL_IRQ BIT(14) /* SE_HW_PARAM_0 fields */ #define TX_FIFO_WIDTH_MSK GENMASK(29, 24) diff --git a/include/linux/soc/qcom/llcc-qcom.h b/include/linux/soc/qcom/llcc-qcom.h index 9e9f528b1370..2f20281d4ad4 100644 --- a/include/linux/soc/qcom/llcc-qcom.h +++ b/include/linux/soc/qcom/llcc-qcom.h @@ -125,6 +125,7 @@ struct llcc_edac_reg_offset { * @num_banks: Number of llcc banks * @bitmap: Bit map to track the active slice ids * @ecc_irq: interrupt for llcc cache error detection and reporting + * @ecc_irq_configured: 'True' if firmware has already configured the irq propagation * @version: Indicates the LLCC version */ struct llcc_drv_data { @@ -139,6 +140,7 @@ struct llcc_drv_data { u32 num_banks; unsigned long *bitmap; int ecc_irq; + bool ecc_irq_configured; u32 version; }; diff --git a/include/linux/sockptr.h b/include/linux/sockptr.h index fc5a206c4043..195debe2b1db 100644 --- a/include/linux/sockptr.h +++ b/include/linux/sockptr.h @@ -77,7 +77,9 @@ static inline int copy_safe_from_sockptr(void *dst, size_t ksize, { if (optlen < ksize) return -EINVAL; - return copy_from_sockptr(dst, optval, ksize); + if (copy_from_sockptr(dst, optval, ksize)) + return -EFAULT; + return 0; } static inline int copy_struct_from_sockptr(void *dst, size_t ksize, diff --git a/include/linux/soundwire/sdw_intel.h b/include/linux/soundwire/sdw_intel.h index 37ae69365fe2..734dc1fa3b5b 100644 --- a/include/linux/soundwire/sdw_intel.h +++ b/include/linux/soundwire/sdw_intel.h @@ -227,7 +227,7 @@ struct sdw_intel_ops { /** * struct sdw_intel_acpi_info - Soundwire Intel information found in ACPI tables * @handle: ACPI controller handle - * @count: link count found with "sdw-master-count" property + * @count: link count found with "sdw-master-count" or "sdw-manager-list" property * @link_mask: bit-wise mask listing links enabled by BIOS menu * * this structure could be expanded to e.g. provide all the _ADR diff --git a/include/linux/spinlock_rt.h b/include/linux/spinlock_rt.h index 61c49b16f69a..f6499c37157d 100644 --- a/include/linux/spinlock_rt.h +++ b/include/linux/spinlock_rt.h @@ -16,26 +16,25 @@ static inline void __rt_spin_lock_init(spinlock_t *lock, const char *name, } #endif -#define spin_lock_init(slock) \ +#define __spin_lock_init(slock, name, key, percpu) \ do { \ - static struct lock_class_key __key; \ - \ rt_mutex_base_init(&(slock)->lock); \ - __rt_spin_lock_init(slock, #slock, &__key, false); \ + __rt_spin_lock_init(slock, name, key, percpu); \ } while (0) -#define local_spin_lock_init(slock) \ +#define _spin_lock_init(slock, percpu) \ do { \ static struct lock_class_key __key; \ - \ - rt_mutex_base_init(&(slock)->lock); \ - __rt_spin_lock_init(slock, #slock, &__key, true); \ + __spin_lock_init(slock, #slock, &__key, percpu); \ } while (0) -extern void rt_spin_lock(spinlock_t *lock); -extern void rt_spin_lock_nested(spinlock_t *lock, int subclass); -extern void rt_spin_lock_nest_lock(spinlock_t *lock, struct lockdep_map *nest_lock); -extern void rt_spin_unlock(spinlock_t *lock); +#define spin_lock_init(slock) _spin_lock_init(slock, false) +#define local_spin_lock_init(slock) _spin_lock_init(slock, true) + +extern void rt_spin_lock(spinlock_t *lock) __acquires(lock); +extern void rt_spin_lock_nested(spinlock_t *lock, int subclass) __acquires(lock); +extern void rt_spin_lock_nest_lock(spinlock_t *lock, struct lockdep_map *nest_lock) __acquires(lock); +extern void rt_spin_unlock(spinlock_t *lock) __releases(lock); extern void rt_spin_lock_unlock(spinlock_t *lock); extern int rt_spin_trylock_bh(spinlock_t *lock); extern int rt_spin_trylock(spinlock_t *lock); @@ -132,7 +131,7 @@ static __always_inline void spin_unlock_irqrestore(spinlock_t *lock, #define spin_trylock_irq(lock) \ __cond_lock(lock, rt_spin_trylock(lock)) -#define __spin_trylock_irqsave(lock, flags) \ +#define spin_trylock_irqsave(lock, flags) \ ({ \ int __locked; \ \ @@ -142,9 +141,6 @@ static __always_inline void spin_unlock_irqrestore(spinlock_t *lock, __locked; \ }) -#define spin_trylock_irqsave(lock, flags) \ - __cond_lock(lock, __spin_trylock_irqsave(lock, flags)) - #define spin_is_contended(lock) (((void)(lock), 0)) static inline int spin_is_locked(spinlock_t *lock) diff --git a/include/linux/srcu.h b/include/linux/srcu.h index 835bbb2d1f88..08339eb8a01c 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -56,6 +56,13 @@ void call_srcu(struct srcu_struct *ssp, struct rcu_head *head, void cleanup_srcu_struct(struct srcu_struct *ssp); int __srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp); void __srcu_read_unlock(struct srcu_struct *ssp, int idx) __releases(ssp); +#ifdef CONFIG_TINY_SRCU +#define __srcu_read_lock_lite __srcu_read_lock +#define __srcu_read_unlock_lite __srcu_read_unlock +#else // #ifdef CONFIG_TINY_SRCU +int __srcu_read_lock_lite(struct srcu_struct *ssp) __acquires(ssp); +void __srcu_read_unlock_lite(struct srcu_struct *ssp, int idx) __releases(ssp); +#endif // #else // #ifdef CONFIG_TINY_SRCU void synchronize_srcu(struct srcu_struct *ssp); #define SRCU_GET_STATE_COMPLETED 0x1 @@ -176,17 +183,6 @@ static inline int srcu_read_lock_held(const struct srcu_struct *ssp) #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ -#define SRCU_NMI_UNKNOWN 0x0 -#define SRCU_NMI_UNSAFE 0x1 -#define SRCU_NMI_SAFE 0x2 - -#if defined(CONFIG_PROVE_RCU) && defined(CONFIG_TREE_SRCU) -void srcu_check_nmi_safety(struct srcu_struct *ssp, bool nmi_safe); -#else -static inline void srcu_check_nmi_safety(struct srcu_struct *ssp, - bool nmi_safe) { } -#endif - /** * srcu_dereference_check - fetch SRCU-protected pointer for later dereferencing @@ -236,33 +232,67 @@ static inline void srcu_check_nmi_safety(struct srcu_struct *ssp, * a mutex that is held elsewhere while calling synchronize_srcu() or * synchronize_srcu_expedited(). * - * Note that srcu_read_lock() and the matching srcu_read_unlock() must - * occur in the same context, for example, it is illegal to invoke - * srcu_read_unlock() in an irq handler if the matching srcu_read_lock() - * was invoked in process context. + * The return value from srcu_read_lock() must be passed unaltered + * to the matching srcu_read_unlock(). Note that srcu_read_lock() and + * the matching srcu_read_unlock() must occur in the same context, for + * example, it is illegal to invoke srcu_read_unlock() in an irq handler + * if the matching srcu_read_lock() was invoked in process context. Or, + * for that matter to invoke srcu_read_unlock() from one task and the + * matching srcu_read_lock() from another. */ static inline int srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp) { int retval; - srcu_check_nmi_safety(ssp, false); + srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL); retval = __srcu_read_lock(ssp); srcu_lock_acquire(&ssp->dep_map); return retval; } /** + * srcu_read_lock_lite - register a new reader for an SRCU-protected structure. + * @ssp: srcu_struct in which to register the new reader. + * + * Enter an SRCU read-side critical section, but for a light-weight + * smp_mb()-free reader. See srcu_read_lock() for more information. + * + * If srcu_read_lock_lite() is ever used on an srcu_struct structure, + * then none of the other flavors may be used, whether before, during, + * or after. Note that grace-period auto-expediting is disabled for _lite + * srcu_struct structures because auto-expedited grace periods invoke + * synchronize_rcu_expedited(), IPIs and all. + * + * Note that srcu_read_lock_lite() can be invoked only from those contexts + * where RCU is watching, that is, from contexts where it would be legal + * to invoke rcu_read_lock(). Otherwise, lockdep will complain. + */ +static inline int srcu_read_lock_lite(struct srcu_struct *ssp) __acquires(ssp) +{ + int retval; + + srcu_check_read_flavor_lite(ssp); + retval = __srcu_read_lock_lite(ssp); + rcu_try_lock_acquire(&ssp->dep_map); + return retval; +} + +/** * srcu_read_lock_nmisafe - register a new reader for an SRCU-protected structure. * @ssp: srcu_struct in which to register the new reader. * * Enter an SRCU read-side critical section, but in an NMI-safe manner. * See srcu_read_lock() for more information. + * + * If srcu_read_lock_nmisafe() is ever used on an srcu_struct structure, + * then none of the other flavors may be used, whether before, during, + * or after. */ static inline int srcu_read_lock_nmisafe(struct srcu_struct *ssp) __acquires(ssp) { int retval; - srcu_check_nmi_safety(ssp, true); + srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NMI); retval = __srcu_read_lock_nmisafe(ssp); rcu_try_lock_acquire(&ssp->dep_map); return retval; @@ -274,7 +304,7 @@ srcu_read_lock_notrace(struct srcu_struct *ssp) __acquires(ssp) { int retval; - srcu_check_nmi_safety(ssp, false); + srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL); retval = __srcu_read_lock(ssp); return retval; } @@ -303,7 +333,7 @@ srcu_read_lock_notrace(struct srcu_struct *ssp) __acquires(ssp) static inline int srcu_down_read(struct srcu_struct *ssp) __acquires(ssp) { WARN_ON_ONCE(in_nmi()); - srcu_check_nmi_safety(ssp, false); + srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL); return __srcu_read_lock(ssp); } @@ -318,12 +348,28 @@ static inline void srcu_read_unlock(struct srcu_struct *ssp, int idx) __releases(ssp) { WARN_ON_ONCE(idx & ~0x1); - srcu_check_nmi_safety(ssp, false); + srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL); srcu_lock_release(&ssp->dep_map); __srcu_read_unlock(ssp, idx); } /** + * srcu_read_unlock_lite - unregister a old reader from an SRCU-protected structure. + * @ssp: srcu_struct in which to unregister the old reader. + * @idx: return value from corresponding srcu_read_lock(). + * + * Exit a light-weight SRCU read-side critical section. + */ +static inline void srcu_read_unlock_lite(struct srcu_struct *ssp, int idx) + __releases(ssp) +{ + WARN_ON_ONCE(idx & ~0x1); + srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_LITE); + srcu_lock_release(&ssp->dep_map); + __srcu_read_unlock_lite(ssp, idx); +} + +/** * srcu_read_unlock_nmisafe - unregister a old reader from an SRCU-protected structure. * @ssp: srcu_struct in which to unregister the old reader. * @idx: return value from corresponding srcu_read_lock(). @@ -334,7 +380,7 @@ static inline void srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx) __releases(ssp) { WARN_ON_ONCE(idx & ~0x1); - srcu_check_nmi_safety(ssp, true); + srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NMI); rcu_lock_release(&ssp->dep_map); __srcu_read_unlock_nmisafe(ssp, idx); } @@ -343,7 +389,7 @@ static inline void srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx) static inline notrace void srcu_read_unlock_notrace(struct srcu_struct *ssp, int idx) __releases(ssp) { - srcu_check_nmi_safety(ssp, false); + srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL); __srcu_read_unlock(ssp, idx); } @@ -360,7 +406,7 @@ static inline void srcu_up_read(struct srcu_struct *ssp, int idx) { WARN_ON_ONCE(idx & ~0x1); WARN_ON_ONCE(in_nmi()); - srcu_check_nmi_safety(ssp, false); + srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL); __srcu_read_unlock(ssp, idx); } diff --git a/include/linux/srcutiny.h b/include/linux/srcutiny.h index 4d96bbdb45f0..1321da803274 100644 --- a/include/linux/srcutiny.h +++ b/include/linux/srcutiny.h @@ -81,6 +81,9 @@ static inline void srcu_barrier(struct srcu_struct *ssp) synchronize_srcu(ssp); } +#define srcu_check_read_flavor(ssp, read_flavor) do { } while (0) +#define srcu_check_read_flavor_lite(ssp) do { } while (0) + /* Defined here to avoid size increase for non-torture kernels. */ static inline void srcu_torture_stats_print(struct srcu_struct *ssp, char *tt, char *tf) diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index ed57598394de..490aeecc6bb4 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -25,7 +25,7 @@ struct srcu_data { /* Read-side state. */ atomic_long_t srcu_lock_count[2]; /* Locks per CPU. */ atomic_long_t srcu_unlock_count[2]; /* Unlocks per CPU. */ - int srcu_nmi_safety; /* NMI-safe srcu_struct structure? */ + int srcu_reader_flavor; /* Reader flavor for srcu_struct structure? */ /* Update-side state. */ spinlock_t __private lock ____cacheline_internodealigned_in_smp; @@ -43,6 +43,11 @@ struct srcu_data { struct srcu_struct *ssp; }; +/* Values for ->srcu_reader_flavor. */ +#define SRCU_READ_FLAVOR_NORMAL 0x1 // srcu_read_lock(). +#define SRCU_READ_FLAVOR_NMI 0x2 // srcu_read_lock_nmisafe(). +#define SRCU_READ_FLAVOR_LITE 0x4 // srcu_read_lock_lite(). + /* * Node in SRCU combining tree, similar in function to rcu_data. */ @@ -204,4 +209,64 @@ void synchronize_srcu_expedited(struct srcu_struct *ssp); void srcu_barrier(struct srcu_struct *ssp); void srcu_torture_stats_print(struct srcu_struct *ssp, char *tt, char *tf); +/* + * Counts the new reader in the appropriate per-CPU element of the + * srcu_struct. Returns an index that must be passed to the matching + * srcu_read_unlock_lite(). + * + * Note that this_cpu_inc() is an RCU read-side critical section either + * because it disables interrupts, because it is a single instruction, + * or because it is a read-modify-write atomic operation, depending on + * the whims of the architecture. + */ +static inline int __srcu_read_lock_lite(struct srcu_struct *ssp) +{ + int idx; + + RCU_LOCKDEP_WARN(!rcu_is_watching(), "RCU must be watching srcu_read_lock_lite()."); + idx = READ_ONCE(ssp->srcu_idx) & 0x1; + this_cpu_inc(ssp->sda->srcu_lock_count[idx].counter); /* Y */ + barrier(); /* Avoid leaking the critical section. */ + return idx; +} + +/* + * Removes the count for the old reader from the appropriate + * per-CPU element of the srcu_struct. Note that this may well be a + * different CPU than that which was incremented by the corresponding + * srcu_read_lock_lite(), but it must be within the same task. + * + * Note that this_cpu_inc() is an RCU read-side critical section either + * because it disables interrupts, because it is a single instruction, + * or because it is a read-modify-write atomic operation, depending on + * the whims of the architecture. + */ +static inline void __srcu_read_unlock_lite(struct srcu_struct *ssp, int idx) +{ + barrier(); /* Avoid leaking the critical section. */ + this_cpu_inc(ssp->sda->srcu_unlock_count[idx].counter); /* Z */ + RCU_LOCKDEP_WARN(!rcu_is_watching(), "RCU must be watching srcu_read_unlock_lite()."); +} + +void __srcu_check_read_flavor(struct srcu_struct *ssp, int read_flavor); + +// Record _lite() usage even for CONFIG_PROVE_RCU=n kernels. +static inline void srcu_check_read_flavor_lite(struct srcu_struct *ssp) +{ + struct srcu_data *sdp = raw_cpu_ptr(ssp->sda); + + if (likely(READ_ONCE(sdp->srcu_reader_flavor) & SRCU_READ_FLAVOR_LITE)) + return; + + // Note that the cmpxchg() in srcu_check_read_flavor() is fully ordered. + __srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_LITE); +} + +// Record non-_lite() usage only for CONFIG_PROVE_RCU=y kernels. +static inline void srcu_check_read_flavor(struct srcu_struct *ssp, int read_flavor) +{ + if (IS_ENABLED(CONFIG_PROVE_RCU)) + __srcu_check_read_flavor(ssp, read_flavor); +} + #endif diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 2f8dc47f1eb0..5f775e104f9a 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -13,7 +13,7 @@ #include <linux/uio.h> #include <asm/byteorder.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/scatterlist.h> struct bio_vec; diff --git a/include/linux/swap.h b/include/linux/swap.h index ca533b478c21..f3e0ac20c2e8 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -335,6 +335,7 @@ struct swap_info_struct { * list. */ struct work_struct discard_work; /* discard worker */ + struct work_struct reclaim_work; /* reclaim worker */ struct list_head discard_clusters; /* discard clusters list */ struct plist_node avail_lists[]; /* * entries in swap_avail_heads, one diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 5758104921e6..c6333204d451 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -77,6 +77,7 @@ struct cachestat_range; struct cachestat; struct statmount; struct mnt_id_req; +struct xattr_args; #include <linux/types.h> #include <linux/aio_abi.h> @@ -338,23 +339,35 @@ asmlinkage long sys_io_uring_register(unsigned int fd, unsigned int op, void __user *arg, unsigned int nr_args); asmlinkage long sys_setxattr(const char __user *path, const char __user *name, const void __user *value, size_t size, int flags); +asmlinkage long sys_setxattrat(int dfd, const char __user *path, unsigned int at_flags, + const char __user *name, + const struct xattr_args __user *args, size_t size); asmlinkage long sys_lsetxattr(const char __user *path, const char __user *name, const void __user *value, size_t size, int flags); asmlinkage long sys_fsetxattr(int fd, const char __user *name, const void __user *value, size_t size, int flags); asmlinkage long sys_getxattr(const char __user *path, const char __user *name, void __user *value, size_t size); +asmlinkage long sys_getxattrat(int dfd, const char __user *path, unsigned int at_flags, + const char __user *name, + struct xattr_args __user *args, size_t size); asmlinkage long sys_lgetxattr(const char __user *path, const char __user *name, void __user *value, size_t size); asmlinkage long sys_fgetxattr(int fd, const char __user *name, void __user *value, size_t size); asmlinkage long sys_listxattr(const char __user *path, char __user *list, size_t size); +asmlinkage long sys_listxattrat(int dfd, const char __user *path, + unsigned int at_flags, + char __user *list, size_t size); asmlinkage long sys_llistxattr(const char __user *path, char __user *list, size_t size); asmlinkage long sys_flistxattr(int fd, char __user *list, size_t size); asmlinkage long sys_removexattr(const char __user *path, const char __user *name); +asmlinkage long sys_removexattrat(int dfd, const char __user *path, + unsigned int at_flags, + const char __user *name); asmlinkage long sys_lremovexattr(const char __user *path, const char __user *name); asmlinkage long sys_fremovexattr(int fd, const char __user *name); diff --git a/include/linux/sysfb.h b/include/linux/sysfb.h index bef5f06a91de..07cbab516942 100644 --- a/include/linux/sysfb.h +++ b/include/linux/sysfb.h @@ -60,12 +60,19 @@ struct efifb_dmi_info { void sysfb_disable(struct device *dev); +bool sysfb_handles_screen_info(void); + #else /* CONFIG_SYSFB */ static inline void sysfb_disable(struct device *dev) { } +static inline bool sysfb_handles_screen_info(void) +{ + return false; +} + #endif /* CONFIG_SYSFB */ #ifdef CONFIG_EFI diff --git a/include/linux/task_work.h b/include/linux/task_work.h index cf5e7e891a77..2964171856e0 100644 --- a/include/linux/task_work.h +++ b/include/linux/task_work.h @@ -14,11 +14,14 @@ init_task_work(struct callback_head *twork, task_work_func_t func) } enum task_work_notify_mode { - TWA_NONE, + TWA_NONE = 0, TWA_RESUME, TWA_SIGNAL, TWA_SIGNAL_NO_IPI, TWA_NMI_CURRENT, + + TWA_FLAGS = 0xff00, + TWAF_NO_ALLOC = 0x0100, }; static inline bool task_work_pending(struct task_struct *task) diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 25ea8fe2313e..754802478b96 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -56,6 +56,9 @@ enum thermal_notify_event { THERMAL_TZ_UNBIND_CDEV, /* Cooling dev is unbind from the thermal zone */ THERMAL_INSTANCE_WEIGHT_CHANGED, /* Thermal instance weight changed */ THERMAL_TZ_RESUME, /* Thermal zone is resuming after system sleep */ + THERMAL_TZ_ADD_THRESHOLD, /* Threshold added */ + THERMAL_TZ_DEL_THRESHOLD, /* Threshold deleted */ + THERMAL_TZ_FLUSH_THRESHOLDS, /* All thresholds deleted */ }; /** @@ -137,6 +140,9 @@ struct thermal_cooling_device { #endif }; +DEFINE_GUARD(cooling_dev, struct thermal_cooling_device *, mutex_lock(&_T->lock), + mutex_unlock(&_T->lock)) + /* Structure to define Thermal Zone parameters */ struct thermal_zone_params { const char *governor_name; diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index 9ea0b28068f4..cf2446c9c30d 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -59,6 +59,14 @@ enum syscall_work_bit { #include <asm/thread_info.h> +#ifndef TIF_NEED_RESCHED_LAZY +#ifdef CONFIG_ARCH_HAS_PREEMPT_LAZY +#error Inconsistent PREEMPT_LAZY +#endif +#define TIF_NEED_RESCHED_LAZY TIF_NEED_RESCHED +#define _TIF_NEED_RESCHED_LAZY _TIF_NEED_RESCHED +#endif + #ifdef __KERNEL__ #ifndef arch_set_restart_data @@ -179,22 +187,27 @@ static __always_inline unsigned long read_ti_thread_flags(struct thread_info *ti #ifdef _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H -static __always_inline bool tif_need_resched(void) +static __always_inline bool tif_test_bit(int bit) { - return arch_test_bit(TIF_NEED_RESCHED, + return arch_test_bit(bit, (unsigned long *)(¤t_thread_info()->flags)); } #else -static __always_inline bool tif_need_resched(void) +static __always_inline bool tif_test_bit(int bit) { - return test_bit(TIF_NEED_RESCHED, + return test_bit(bit, (unsigned long *)(¤t_thread_info()->flags)); } #endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H */ +static __always_inline bool tif_need_resched(void) +{ + return tif_test_bit(TIF_NEED_RESCHED); +} + #ifndef CONFIG_HAVE_ARCH_WITHIN_STACK_FRAMES static inline int arch_within_stack_frames(const void * const stack, const void * const stackend, diff --git a/include/linux/tick.h b/include/linux/tick.h index 72744638c5b0..99c9c5a7252a 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -251,12 +251,19 @@ static inline void tick_dep_set_task(struct task_struct *tsk, if (tick_nohz_full_enabled()) tick_nohz_dep_set_task(tsk, bit); } + static inline void tick_dep_clear_task(struct task_struct *tsk, enum tick_dep_bits bit) { if (tick_nohz_full_enabled()) tick_nohz_dep_clear_task(tsk, bit); } + +static inline void tick_dep_init_task(struct task_struct *tsk) +{ + atomic_set(&tsk->tick_dep_mask, 0); +} + static inline void tick_dep_set_signal(struct task_struct *tsk, enum tick_dep_bits bit) { @@ -290,6 +297,7 @@ static inline void tick_dep_set_task(struct task_struct *tsk, enum tick_dep_bits bit) { } static inline void tick_dep_clear_task(struct task_struct *tsk, enum tick_dep_bits bit) { } +static inline void tick_dep_init_task(struct task_struct *tsk) { } static inline void tick_dep_set_signal(struct task_struct *tsk, enum tick_dep_bits bit) { } static inline void tick_dep_clear_signal(struct signal_struct *signal, diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index fc12a9ba2c88..84a035e86ac8 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -45,6 +45,11 @@ extern void ktime_get_real_ts64(struct timespec64 *tv); extern void ktime_get_coarse_ts64(struct timespec64 *ts); extern void ktime_get_coarse_real_ts64(struct timespec64 *ts); +/* Multigrain timestamp interfaces */ +extern void ktime_get_coarse_real_ts64_mg(struct timespec64 *ts); +extern void ktime_get_real_ts64_mg(struct timespec64 *ts); +extern unsigned long timekeeping_get_mg_floor_swaps(void); + void getboottime64(struct timespec64 *ts); /* diff --git a/include/linux/tpm.h b/include/linux/tpm.h index e93ee8d936a9..20a40ade8030 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -421,6 +421,7 @@ void tpm_buf_append_u32(struct tpm_buf *buf, const u32 value); u8 tpm_buf_read_u8(struct tpm_buf *buf, off_t *offset); u16 tpm_buf_read_u16(struct tpm_buf *buf, off_t *offset); u32 tpm_buf_read_u32(struct tpm_buf *buf, off_t *offset); +void tpm_buf_append_handle(struct tpm_chip *chip, struct tpm_buf *buf, u32 handle); /* * Check if TPM device is in the firmware upgrade mode. @@ -505,6 +506,8 @@ void tpm_buf_append_name(struct tpm_chip *chip, struct tpm_buf *buf, void tpm_buf_append_hmac_session(struct tpm_chip *chip, struct tpm_buf *buf, u8 attributes, u8 *passphrase, int passphraselen); +void tpm_buf_append_auth(struct tpm_chip *chip, struct tpm_buf *buf, + u8 attributes, u8 *passphrase, int passphraselen); static inline void tpm_buf_append_hmac_session_opt(struct tpm_chip *chip, struct tpm_buf *buf, u8 attributes, @@ -537,7 +540,7 @@ 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> +#include <linux/unaligned.h> static inline int tpm2_start_auth_session(struct tpm_chip *chip) { diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 39c7cf82b0c2..e9c702c1908d 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -38,6 +38,7 @@ #else #define can_do_masked_user_access() 0 #define masked_user_access_begin(src) NULL + #define mask_user_address(src) (src) #endif /* @@ -159,19 +160,27 @@ _inline_copy_from_user(void *to, const void __user *from, unsigned long n) { unsigned long res = n; might_fault(); - if (!should_fail_usercopy() && likely(access_ok(from, n))) { + if (should_fail_usercopy()) + goto fail; + if (can_do_masked_user_access()) + from = mask_user_address(from); + else { + if (!access_ok(from, n)) + goto fail; /* * Ensure that bad access_ok() speculation will not * lead to nasty side effects *after* the copy is * finished: */ barrier_nospec(); - instrument_copy_from_user_before(to, from, n); - res = raw_copy_from_user(to, from, n); - instrument_copy_from_user_after(to, from, n, res); } - if (unlikely(res)) - memset(to + (n - res), 0, res); + instrument_copy_from_user_before(to, from, n); + res = raw_copy_from_user(to, from, n); + instrument_copy_from_user_after(to, from, n, res); + if (likely(!res)) + return 0; +fail: + memset(to + (n - res), 0, res); return res; } extern __must_check unsigned long @@ -394,6 +403,103 @@ copy_struct_from_user(void *dst, size_t ksize, const void __user *src, return 0; } +/** + * copy_struct_to_user: copy a struct to userspace + * @dst: Destination address, in userspace. This buffer must be @ksize + * bytes long. + * @usize: (Alleged) size of @dst struct. + * @src: Source address, in kernel space. + * @ksize: Size of @src struct. + * @ignored_trailing: Set to %true if there was a non-zero byte in @src that + * userspace cannot see because they are using an smaller struct. + * + * Copies a struct from kernel space to userspace, in a way that guarantees + * backwards-compatibility for struct syscall arguments (as long as future + * struct extensions are made such that all new fields are *appended* to the + * old struct, and zeroed-out new fields have the same meaning as the old + * struct). + * + * Some syscalls may wish to make sure that userspace knows about everything in + * the struct, and if there is a non-zero value that userspce doesn't know + * about, they want to return an error (such as -EMSGSIZE) or have some other + * fallback (such as adding a "you're missing some information" flag). If + * @ignored_trailing is non-%NULL, it will be set to %true if there was a + * non-zero byte that could not be copied to userspace (ie. was past @usize). + * + * While unconditionally returning an error in this case is the simplest + * solution, for maximum backward compatibility you should try to only return + * -EMSGSIZE if the user explicitly requested the data that couldn't be copied. + * Note that structure sizes can change due to header changes and simple + * recompilations without code changes(!), so if you care about + * @ignored_trailing you probably want to make sure that any new field data is + * associated with a flag. Otherwise you might assume that a program knows + * about data it does not. + * + * @ksize is just sizeof(*src), and @usize should've been passed by userspace. + * The recommended usage is something like the following: + * + * SYSCALL_DEFINE2(foobar, struct foo __user *, uarg, size_t, usize) + * { + * int err; + * bool ignored_trailing; + * struct foo karg = {}; + * + * if (usize > PAGE_SIZE) + * return -E2BIG; + * if (usize < FOO_SIZE_VER0) + * return -EINVAL; + * + * // ... modify karg somehow ... + * + * err = copy_struct_to_user(uarg, usize, &karg, sizeof(karg), + * &ignored_trailing); + * if (err) + * return err; + * if (ignored_trailing) + * return -EMSGSIZE: + * + * // ... + * } + * + * There are three cases to consider: + * * If @usize == @ksize, then it's copied verbatim. + * * If @usize < @ksize, then the kernel is trying to pass userspace a newer + * struct than it supports. Thus we only copy the interoperable portions + * (@usize) and ignore the rest (but @ignored_trailing is set to %true if + * any of the trailing (@ksize - @usize) bytes are non-zero). + * * If @usize > @ksize, then the kernel is trying to pass userspace an older + * struct than userspace supports. In order to make sure the + * unknown-to-the-kernel fields don't contain garbage values, we zero the + * trailing (@usize - @ksize) bytes. + * + * Returns (in all cases, some data may have been copied): + * * -EFAULT: access to userspace failed. + */ +static __always_inline __must_check int +copy_struct_to_user(void __user *dst, size_t usize, const void *src, + size_t ksize, bool *ignored_trailing) +{ + size_t size = min(ksize, usize); + size_t rest = max(ksize, usize) - size; + + /* Double check if ksize is larger than a known object size. */ + if (WARN_ON_ONCE(ksize > __builtin_object_size(src, 1))) + return -E2BIG; + + /* Deal with trailing bytes. */ + if (usize > ksize) { + if (clear_user(dst + size, rest)) + return -EFAULT; + } + if (ignored_trailing) + *ignored_trailing = ksize < usize && + memchr_inv(src + size, 0, rest) != NULL; + /* Copy the interoperable parts of the struct. */ + if (copy_to_user(dst, src, size)) + return -EFAULT; + return 0; +} + bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size); long copy_from_kernel_nofault(void *dst, const void *src, size_t size); diff --git a/include/linux/unaligned.h b/include/linux/unaligned.h new file mode 100644 index 000000000000..4a9651017e3c --- /dev/null +++ b/include/linux/unaligned.h @@ -0,0 +1,146 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_UNALIGNED_H +#define __LINUX_UNALIGNED_H + +/* + * This is the most generic implementation of unaligned accesses + * and should work almost anywhere. + */ +#include <linux/unaligned/packed_struct.h> +#include <asm/byteorder.h> +#include <vdso/unaligned.h> + +#define get_unaligned(ptr) __get_unaligned_t(typeof(*(ptr)), (ptr)) +#define put_unaligned(val, ptr) __put_unaligned_t(typeof(*(ptr)), (val), (ptr)) + +static inline u16 get_unaligned_le16(const void *p) +{ + return le16_to_cpu(__get_unaligned_t(__le16, p)); +} + +static inline u32 get_unaligned_le32(const void *p) +{ + return le32_to_cpu(__get_unaligned_t(__le32, p)); +} + +static inline u64 get_unaligned_le64(const void *p) +{ + return le64_to_cpu(__get_unaligned_t(__le64, p)); +} + +static inline void put_unaligned_le16(u16 val, void *p) +{ + __put_unaligned_t(__le16, cpu_to_le16(val), p); +} + +static inline void put_unaligned_le32(u32 val, void *p) +{ + __put_unaligned_t(__le32, cpu_to_le32(val), p); +} + +static inline void put_unaligned_le64(u64 val, void *p) +{ + __put_unaligned_t(__le64, cpu_to_le64(val), p); +} + +static inline u16 get_unaligned_be16(const void *p) +{ + return be16_to_cpu(__get_unaligned_t(__be16, p)); +} + +static inline u32 get_unaligned_be32(const void *p) +{ + return be32_to_cpu(__get_unaligned_t(__be32, p)); +} + +static inline u64 get_unaligned_be64(const void *p) +{ + return be64_to_cpu(__get_unaligned_t(__be64, p)); +} + +static inline void put_unaligned_be16(u16 val, void *p) +{ + __put_unaligned_t(__be16, cpu_to_be16(val), p); +} + +static inline void put_unaligned_be32(u32 val, void *p) +{ + __put_unaligned_t(__be32, cpu_to_be32(val), p); +} + +static inline void put_unaligned_be64(u64 val, void *p) +{ + __put_unaligned_t(__be64, cpu_to_be64(val), p); +} + +static inline u32 __get_unaligned_be24(const u8 *p) +{ + return p[0] << 16 | p[1] << 8 | p[2]; +} + +static inline u32 get_unaligned_be24(const void *p) +{ + return __get_unaligned_be24(p); +} + +static inline u32 __get_unaligned_le24(const u8 *p) +{ + return p[0] | p[1] << 8 | p[2] << 16; +} + +static inline u32 get_unaligned_le24(const void *p) +{ + return __get_unaligned_le24(p); +} + +static inline void __put_unaligned_be24(const u32 val, u8 *p) +{ + *p++ = (val >> 16) & 0xff; + *p++ = (val >> 8) & 0xff; + *p++ = val & 0xff; +} + +static inline void put_unaligned_be24(const u32 val, void *p) +{ + __put_unaligned_be24(val, p); +} + +static inline void __put_unaligned_le24(const u32 val, u8 *p) +{ + *p++ = val & 0xff; + *p++ = (val >> 8) & 0xff; + *p++ = (val >> 16) & 0xff; +} + +static inline void put_unaligned_le24(const u32 val, void *p) +{ + __put_unaligned_le24(val, p); +} + +static inline void __put_unaligned_be48(const u64 val, u8 *p) +{ + *p++ = (val >> 40) & 0xff; + *p++ = (val >> 32) & 0xff; + *p++ = (val >> 24) & 0xff; + *p++ = (val >> 16) & 0xff; + *p++ = (val >> 8) & 0xff; + *p++ = val & 0xff; +} + +static inline void put_unaligned_be48(const u64 val, void *p) +{ + __put_unaligned_be48(val, p); +} + +static inline u64 __get_unaligned_be48(const u8 *p) +{ + return (u64)p[0] << 40 | (u64)p[1] << 32 | (u64)p[2] << 24 | + p[3] << 16 | p[4] << 8 | p[5]; +} + +static inline u64 get_unaligned_be48(const void *p) +{ + return __get_unaligned_be48(p); +} + +#endif /* __LINUX_UNALIGNED_H */ diff --git a/include/linux/unicode.h b/include/linux/unicode.h index 4d39e6e11a95..5e6b212a2aed 100644 --- a/include/linux/unicode.h +++ b/include/linux/unicode.h @@ -16,6 +16,8 @@ struct utf8data_table; ((unsigned int)(MIN) << UNICODE_MIN_SHIFT) | \ ((unsigned int)(REV))) +#define UTF8_LATEST UNICODE_AGE(12, 1, 0) + static inline u8 unicode_major(unsigned int age) { return (age >> UNICODE_MAJ_SHIFT) & 0xff; @@ -76,4 +78,6 @@ int utf8_casefold_hash(const struct unicode_map *um, const void *salt, struct unicode_map *utf8_load(unsigned int version); void utf8_unload(struct unicode_map *um); +int utf8_parse_version(char *version); + #endif /* _LINUX_UNICODE_H */ diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index 2b294bf1881f..e0a4c2082245 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -15,6 +15,7 @@ #include <linux/rbtree.h> #include <linux/types.h> #include <linux/wait.h> +#include <linux/timer.h> struct uprobe; struct vm_area_struct; @@ -23,8 +24,17 @@ struct inode; struct notifier_block; struct page; +/* + * Allowed return values from uprobe consumer's handler callback + * with following meaning: + * + * UPROBE_HANDLER_REMOVE + * - Remove the uprobe breakpoint from current->mm. + * UPROBE_HANDLER_IGNORE + * - Ignore ret_handler callback for this consumer. + */ #define UPROBE_HANDLER_REMOVE 1 -#define UPROBE_HANDLER_MASK 1 +#define UPROBE_HANDLER_IGNORE 2 #define MAX_URETPROBE_DEPTH 64 @@ -37,13 +47,15 @@ struct uprobe_consumer { * for the current process. If filter() is omitted or returns true, * UPROBE_HANDLER_REMOVE is effectively ignored. */ - int (*handler)(struct uprobe_consumer *self, struct pt_regs *regs); + int (*handler)(struct uprobe_consumer *self, struct pt_regs *regs, __u64 *data); int (*ret_handler)(struct uprobe_consumer *self, unsigned long func, - struct pt_regs *regs); + struct pt_regs *regs, __u64 *data); bool (*filter)(struct uprobe_consumer *self, struct mm_struct *mm); struct list_head cons_node; + + __u64 id; /* set when uprobe_consumer is registered */ }; #ifdef CONFIG_UPROBES @@ -56,12 +68,62 @@ enum uprobe_task_state { UTASK_SSTEP_TRAPPED, }; +/* The state of hybrid-lifetime uprobe inside struct return_instance */ +enum hprobe_state { + HPROBE_LEASED, /* uretprobes_srcu-protected uprobe */ + HPROBE_STABLE, /* refcounted uprobe */ + HPROBE_GONE, /* NULL uprobe, SRCU expired, refcount failed */ + HPROBE_CONSUMED, /* uprobe "consumed" by uretprobe handler */ +}; + +/* + * Hybrid lifetime uprobe. Represents a uprobe instance that could be either + * SRCU protected (with SRCU protection eventually potentially timing out), + * refcounted using uprobe->ref, or there could be no valid uprobe (NULL). + * + * hprobe's internal state is setup such that background timer thread can + * atomically "downgrade" temporarily RCU-protected uprobe into refcounted one + * (or no uprobe, if refcounting failed). + * + * *stable* pointer always point to the uprobe (or could be NULL if there is + * was no valid underlying uprobe to begin with). + * + * *leased* pointer is the key to achieving race-free atomic lifetime state + * transition and can have three possible states: + * - either the same non-NULL value as *stable*, in which case uprobe is + * SRCU-protected; + * - NULL, in which case uprobe (if there is any) is refcounted; + * - special __UPROBE_DEAD value, which represents an uprobe that was SRCU + * protected initially, but SRCU period timed out and we attempted to + * convert it to refcounted, but refcount_inc_not_zero() failed, because + * uprobe effectively went away (the last consumer unsubscribed). In this + * case it's important to know that *stable* pointer (which still has + * non-NULL uprobe pointer) shouldn't be used, because lifetime of + * underlying uprobe is not guaranteed anymore. __UPROBE_DEAD is just an + * internal marker and is handled transparently by hprobe_fetch() helper. + * + * When uprobe is SRCU-protected, we also record srcu_idx value, necessary for + * SRCU unlocking. + * + * See hprobe_expire() and hprobe_fetch() for details of race-free uprobe + * state transitioning details. It all hinges on atomic xchg() over *leaded* + * pointer. *stable* pointer, once initially set, is not modified concurrently. + */ +struct hprobe { + enum hprobe_state state; + int srcu_idx; + struct uprobe *uprobe; +}; + /* * uprobe_task: Metadata of a task while it singlesteps. */ struct uprobe_task { enum uprobe_task_state state; + unsigned int depth; + struct return_instance *return_instances; + union { struct { struct arch_uprobe_task autask; @@ -75,23 +137,30 @@ struct uprobe_task { }; struct uprobe *active_uprobe; + struct timer_list ri_timer; unsigned long xol_vaddr; struct arch_uprobe *auprobe; +}; - struct return_instance *return_instances; - unsigned int depth; +struct return_consumer { + __u64 cookie; + __u64 id; }; struct return_instance { - struct uprobe *uprobe; + struct hprobe hprobe; unsigned long func; unsigned long stack; /* stack pointer */ unsigned long orig_ret_vaddr; /* original return address */ bool chained; /* true, if instance is nested */ + int consumers_cnt; struct return_instance *next; /* keep as stack */ -}; + struct rcu_head rcu; + + struct return_consumer consumers[] __counted_by(consumers_cnt); +} ____cacheline_aligned; enum rp_check { RP_CHECK_CALL, diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 3625096d5f85..7183e5aca282 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -141,7 +141,8 @@ static inline long get_rlimit_value(struct ucounts *ucounts, enum rlimit_type ty long inc_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v); bool dec_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v); -long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type); +long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type, + bool override_rlimit); void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum rlimit_type type); bool is_rlimit_overlimit(struct ucounts *ucounts, enum rlimit_type type, unsigned long max); diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 9fc6ce15c499..cb40f1a1d081 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -249,6 +249,7 @@ static inline bool vma_can_userfault(struct vm_area_struct *vma, extern int dup_userfaultfd(struct vm_area_struct *, struct list_head *); extern void dup_userfaultfd_complete(struct list_head *); +void dup_userfaultfd_fail(struct list_head *); extern void mremap_userfaultfd_prep(struct vm_area_struct *, struct vm_userfaultfd_ctx *); @@ -351,6 +352,10 @@ static inline void dup_userfaultfd_complete(struct list_head *l) { } +static inline void dup_userfaultfd_fail(struct list_head *l) +{ +} + static inline void mremap_userfaultfd_prep(struct vm_area_struct *vma, struct vm_userfaultfd_ctx *ctx) { diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 276ca543ef44..02a9f4dc594d 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -103,8 +103,10 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, if (!skb_partial_csum_set(skb, start, off)) return -EINVAL; + if (skb_transport_offset(skb) < nh_min_len) + return -EINVAL; - nh_min_len = max_t(u32, nh_min_len, skb_transport_offset(skb)); + nh_min_len = skb_transport_offset(skb); p_off = nh_min_len + thlen; if (!pskb_may_pull(skb, p_off)) return -EINVAL; diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index aed952d04132..f70d0958095c 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -134,6 +134,8 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, #ifdef CONFIG_SWAP SWAP_RA, SWAP_RA_HIT, + SWPIN_ZERO, + SWPOUT_ZERO, #ifdef CONFIG_KSM KSM_SWPIN_COPY, #endif diff --git a/include/linux/wait.h b/include/linux/wait.h index 8aa3372f21a0..2b322a9b88a2 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -221,6 +221,7 @@ void __wake_up_pollfree(struct wait_queue_head *wq_head); #define wake_up_all(x) __wake_up(x, TASK_NORMAL, 0, NULL) #define wake_up_locked(x) __wake_up_locked((x), TASK_NORMAL, 1) #define wake_up_all_locked(x) __wake_up_locked((x), TASK_NORMAL, 0) +#define wake_up_sync(x) __wake_up_sync(x, TASK_NORMAL) #define wake_up_interruptible(x) __wake_up(x, TASK_INTERRUPTIBLE, 1, NULL) #define wake_up_interruptible_nr(x, nr) __wake_up(x, TASK_INTERRUPTIBLE, nr, NULL) diff --git a/include/linux/wait_bit.h b/include/linux/wait_bit.h index 7725b7579b78..9e29d79fc790 100644 --- a/include/linux/wait_bit.h +++ b/include/linux/wait_bit.h @@ -8,7 +8,7 @@ #include <linux/wait.h> struct wait_bit_key { - void *flags; + unsigned long *flags; int bit_nr; unsigned long timeout; }; @@ -23,14 +23,14 @@ struct wait_bit_queue_entry { typedef int wait_bit_action_f(struct wait_bit_key *key, int mode); -void __wake_up_bit(struct wait_queue_head *wq_head, void *word, int bit); +void __wake_up_bit(struct wait_queue_head *wq_head, unsigned long *word, int bit); int __wait_on_bit(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry, wait_bit_action_f *action, unsigned int mode); int __wait_on_bit_lock(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry, wait_bit_action_f *action, unsigned int mode); -void wake_up_bit(void *word, int bit); -int out_of_line_wait_on_bit(void *word, int, wait_bit_action_f *action, unsigned int mode); -int out_of_line_wait_on_bit_timeout(void *word, int, wait_bit_action_f *action, unsigned int mode, unsigned long timeout); -int out_of_line_wait_on_bit_lock(void *word, int, wait_bit_action_f *action, unsigned int mode); -struct wait_queue_head *bit_waitqueue(void *word, int bit); +void wake_up_bit(unsigned long *word, int bit); +int out_of_line_wait_on_bit(unsigned long *word, int, wait_bit_action_f *action, unsigned int mode); +int out_of_line_wait_on_bit_timeout(unsigned long *word, int, wait_bit_action_f *action, unsigned int mode, unsigned long timeout); +int out_of_line_wait_on_bit_lock(unsigned long *word, int, wait_bit_action_f *action, unsigned int mode); +struct wait_queue_head *bit_waitqueue(unsigned long *word, int bit); extern void __init wait_bit_init(void); int wake_bit_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key); @@ -49,23 +49,24 @@ int wake_bit_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync extern int bit_wait(struct wait_bit_key *key, int mode); extern int bit_wait_io(struct wait_bit_key *key, int mode); extern int bit_wait_timeout(struct wait_bit_key *key, int mode); -extern int bit_wait_io_timeout(struct wait_bit_key *key, int mode); /** * wait_on_bit - wait for a bit to be cleared - * @word: the word being waited on, a kernel virtual address - * @bit: the bit of the word being waited on + * @word: the address containing the bit being waited on + * @bit: the bit at that address being waited on * @mode: the task state to sleep in * - * There is a standard hashed waitqueue table for generic use. This - * is the part of the hashtable's accessor API that waits on a bit. - * For instance, if one were to have waiters on a bitflag, one would - * call wait_on_bit() in threads waiting for the bit to clear. - * One uses wait_on_bit() where one is waiting for the bit to clear, - * but has no intention of setting it. - * Returned value will be zero if the bit was cleared, or non-zero - * if the process received a signal and the mode permitted wakeup - * on that signal. + * Wait for the given bit in an unsigned long or bitmap (see DECLARE_BITMAP()) + * to be cleared. The clearing of the bit must be signalled with + * wake_up_bit(), often as clear_and_wake_up_bit(). + * + * The process will wait on a waitqueue selected by hash from a shared + * pool. It will only be woken on a wake_up for the target bit, even + * if other processes on the same queue are waiting for other bits. + * + * Returned value will be zero if the bit was cleared in which case the + * call has ACQUIRE semantics, or %-EINTR if the process received a + * signal and the mode permitted wake up on that signal. */ static inline int wait_on_bit(unsigned long *word, int bit, unsigned mode) @@ -80,17 +81,20 @@ wait_on_bit(unsigned long *word, int bit, unsigned mode) /** * wait_on_bit_io - wait for a bit to be cleared - * @word: the word being waited on, a kernel virtual address - * @bit: the bit of the word being waited on + * @word: the address containing the bit being waited on + * @bit: the bit at that address being waited on * @mode: the task state to sleep in * - * Use the standard hashed waitqueue table to wait for a bit - * to be cleared. This is similar to wait_on_bit(), but calls - * io_schedule() instead of schedule() for the actual waiting. + * Wait for the given bit in an unsigned long or bitmap (see DECLARE_BITMAP()) + * to be cleared. The clearing of the bit must be signalled with + * wake_up_bit(), often as clear_and_wake_up_bit(). * - * Returned value will be zero if the bit was cleared, or non-zero - * if the process received a signal and the mode permitted wakeup - * on that signal. + * This is similar to wait_on_bit(), but calls io_schedule() instead of + * schedule() for the actual waiting. + * + * Returned value will be zero if the bit was cleared in which case the + * call has ACQUIRE semantics, or %-EINTR if the process received a + * signal and the mode permitted wake up on that signal. */ static inline int wait_on_bit_io(unsigned long *word, int bit, unsigned mode) @@ -104,19 +108,24 @@ wait_on_bit_io(unsigned long *word, int bit, unsigned mode) } /** - * wait_on_bit_timeout - wait for a bit to be cleared or a timeout elapses - * @word: the word being waited on, a kernel virtual address - * @bit: the bit of the word being waited on + * wait_on_bit_timeout - wait for a bit to be cleared or a timeout to elapse + * @word: the address containing the bit being waited on + * @bit: the bit at that address being waited on * @mode: the task state to sleep in * @timeout: timeout, in jiffies * - * Use the standard hashed waitqueue table to wait for a bit - * to be cleared. This is similar to wait_on_bit(), except also takes a - * timeout parameter. + * Wait for the given bit in an unsigned long or bitmap (see + * DECLARE_BITMAP()) to be cleared, or for a timeout to expire. The + * clearing of the bit must be signalled with wake_up_bit(), often as + * clear_and_wake_up_bit(). + * + * This is similar to wait_on_bit(), except it also takes a timeout + * parameter. * - * Returned value will be zero if the bit was cleared before the - * @timeout elapsed, or non-zero if the @timeout elapsed or process - * received a signal and the mode permitted wakeup on that signal. + * Returned value will be zero if the bit was cleared in which case the + * call has ACQUIRE semantics, or %-EINTR if the process received a + * signal and the mode permitted wake up on that signal, or %-EAGAIN if the + * timeout elapsed. */ static inline int wait_on_bit_timeout(unsigned long *word, int bit, unsigned mode, @@ -132,19 +141,21 @@ wait_on_bit_timeout(unsigned long *word, int bit, unsigned mode, /** * wait_on_bit_action - wait for a bit to be cleared - * @word: the word being waited on, a kernel virtual address - * @bit: the bit of the word being waited on + * @word: the address containing the bit waited on + * @bit: the bit at that address being waited on * @action: the function used to sleep, which may take special actions * @mode: the task state to sleep in * - * Use the standard hashed waitqueue table to wait for a bit - * to be cleared, and allow the waiting action to be specified. - * This is like wait_on_bit() but allows fine control of how the waiting - * is done. + * Wait for the given bit in an unsigned long or bitmap (see DECLARE_BITMAP()) + * to be cleared. The clearing of the bit must be signalled with + * wake_up_bit(), often as clear_and_wake_up_bit(). + * + * This is similar to wait_on_bit(), but calls @action() instead of + * schedule() for the actual waiting. * - * Returned value will be zero if the bit was cleared, or non-zero - * if the process received a signal and the mode permitted wakeup - * on that signal. + * Returned value will be zero if the bit was cleared in which case the + * call has ACQUIRE semantics, or the error code returned by @action if + * that call returned non-zero. */ static inline int wait_on_bit_action(unsigned long *word, int bit, wait_bit_action_f *action, @@ -157,23 +168,22 @@ wait_on_bit_action(unsigned long *word, int bit, wait_bit_action_f *action, } /** - * wait_on_bit_lock - wait for a bit to be cleared, when wanting to set it - * @word: the word being waited on, a kernel virtual address - * @bit: the bit of the word being waited on + * wait_on_bit_lock - wait for a bit to be cleared, then set it + * @word: the address containing the bit being waited on + * @bit: the bit of the word being waited on and set * @mode: the task state to sleep in * - * There is a standard hashed waitqueue table for generic use. This - * is the part of the hashtable's accessor API that waits on a bit - * when one intends to set it, for instance, trying to lock bitflags. - * For instance, if one were to have waiters trying to set bitflag - * and waiting for it to clear before setting it, one would call - * wait_on_bit() in threads waiting to be able to set the bit. - * One uses wait_on_bit_lock() where one is waiting for the bit to - * clear with the intention of setting it, and when done, clearing it. + * Wait for the given bit in an unsigned long or bitmap (see + * DECLARE_BITMAP()) to be cleared. The clearing of the bit must be + * signalled with wake_up_bit(), often as clear_and_wake_up_bit(). As + * soon as it is clear, atomically set it and return. * - * Returns zero if the bit was (eventually) found to be clear and was - * set. Returns non-zero if a signal was delivered to the process and - * the @mode allows that signal to wake the process. + * This is similar to wait_on_bit(), but sets the bit before returning. + * + * Returned value will be zero if the bit was successfully set in which + * case the call has the same memory sequencing semantics as + * test_and_clear_bit(), or %-EINTR if the process received a signal and + * the mode permitted wake up on that signal. */ static inline int wait_on_bit_lock(unsigned long *word, int bit, unsigned mode) @@ -185,15 +195,18 @@ wait_on_bit_lock(unsigned long *word, int bit, unsigned mode) } /** - * wait_on_bit_lock_io - wait for a bit to be cleared, when wanting to set it - * @word: the word being waited on, a kernel virtual address - * @bit: the bit of the word being waited on + * wait_on_bit_lock_io - wait for a bit to be cleared, then set it + * @word: the address containing the bit being waited on + * @bit: the bit of the word being waited on and set * @mode: the task state to sleep in * - * Use the standard hashed waitqueue table to wait for a bit - * to be cleared and then to atomically set it. This is similar - * to wait_on_bit(), but calls io_schedule() instead of schedule() - * for the actual waiting. + * Wait for the given bit in an unsigned long or bitmap (see + * DECLARE_BITMAP()) to be cleared. The clearing of the bit must be + * signalled with wake_up_bit(), often as clear_and_wake_up_bit(). As + * soon as it is clear, atomically set it and return. + * + * This is similar to wait_on_bit_lock(), but calls io_schedule() instead + * of schedule(). * * Returns zero if the bit was (eventually) found to be clear and was * set. Returns non-zero if a signal was delivered to the process and @@ -209,21 +222,19 @@ wait_on_bit_lock_io(unsigned long *word, int bit, unsigned mode) } /** - * wait_on_bit_lock_action - wait for a bit to be cleared, when wanting to set it - * @word: the word being waited on, a kernel virtual address - * @bit: the bit of the word being waited on + * wait_on_bit_lock_action - wait for a bit to be cleared, then set it + * @word: the address containing the bit being waited on + * @bit: the bit of the word being waited on and set * @action: the function used to sleep, which may take special actions * @mode: the task state to sleep in * - * Use the standard hashed waitqueue table to wait for a bit - * to be cleared and then to set it, and allow the waiting action - * to be specified. - * This is like wait_on_bit() but allows fine control of how the waiting - * is done. + * This is similar to wait_on_bit_lock(), but calls @action() instead of + * schedule() for the actual waiting. * - * Returns zero if the bit was (eventually) found to be clear and was - * set. Returns non-zero if a signal was delivered to the process and - * the @mode allows that signal to wake the process. + * Returned value will be zero if the bit was successfully set in which + * case the call has the same memory sequencing semantics as + * test_and_clear_bit(), or the error code returned by @action if that + * call returned non-zero. */ static inline int wait_on_bit_lock_action(unsigned long *word, int bit, wait_bit_action_f *action, @@ -269,7 +280,26 @@ __out: __ret; \ #define __wait_var_event(var, condition) \ ___wait_var_event(var, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ schedule()) +#define __wait_var_event_io(var, condition) \ + ___wait_var_event(var, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ + io_schedule()) +/** + * wait_var_event - wait for a variable to be updated and notified + * @var: the address of variable being waited on + * @condition: the condition to wait for + * + * Wait for a @condition to be true, only re-checking when a wake up is + * received for the given @var (an arbitrary kernel address which need + * not be directly related to the given condition, but usually is). + * + * The process will wait on a waitqueue selected by hash from a shared + * pool. It will only be woken on a wake_up for the given address. + * + * The condition should normally use smp_load_acquire() or a similarly + * ordered access to ensure that any changes to memory made before the + * condition became true will be visible after the wait completes. + */ #define wait_var_event(var, condition) \ do { \ might_sleep(); \ @@ -278,10 +308,56 @@ do { \ __wait_var_event(var, condition); \ } while (0) +/** + * wait_var_event_io - wait for a variable to be updated and notified + * @var: the address of variable being waited on + * @condition: the condition to wait for + * + * Wait for an IO related @condition to be true, only re-checking when a + * wake up is received for the given @var (an arbitrary kernel address + * which need not be directly related to the given condition, but + * usually is). + * + * The process will wait on a waitqueue selected by hash from a shared + * pool. It will only be woken on a wake_up for the given address. + * + * This is similar to wait_var_event(), but calls io_schedule() instead + * of schedule(). + * + * The condition should normally use smp_load_acquire() or a similarly + * ordered access to ensure that any changes to memory made before the + * condition became true will be visible after the wait completes. + */ +#define wait_var_event_io(var, condition) \ +do { \ + might_sleep(); \ + if (condition) \ + break; \ + __wait_var_event_io(var, condition); \ +} while (0) + #define __wait_var_event_killable(var, condition) \ ___wait_var_event(var, condition, TASK_KILLABLE, 0, 0, \ schedule()) +/** + * wait_var_event_killable - wait for a variable to be updated and notified + * @var: the address of variable being waited on + * @condition: the condition to wait for + * + * Wait for a @condition to be true or a fatal signal to be received, + * only re-checking the condition when a wake up is received for the given + * @var (an arbitrary kernel address which need not be directly related + * to the given condition, but usually is). + * + * This is similar to wait_var_event() but returns a value which is + * 0 if the condition became true, or %-ERESTARTSYS if a fatal signal + * was received. + * + * The condition should normally use smp_load_acquire() or a similarly + * ordered access to ensure that any changes to memory made before the + * condition became true will be visible after the wait completes. + */ #define wait_var_event_killable(var, condition) \ ({ \ int __ret = 0; \ @@ -296,6 +372,26 @@ do { \ TASK_UNINTERRUPTIBLE, 0, timeout, \ __ret = schedule_timeout(__ret)) +/** + * wait_var_event_timeout - wait for a variable to be updated or a timeout to expire + * @var: the address of variable being waited on + * @condition: the condition to wait for + * @timeout: maximum time to wait in jiffies + * + * Wait for a @condition to be true or a timeout to expire, only + * re-checking the condition when a wake up is received for the given + * @var (an arbitrary kernel address which need not be directly related + * to the given condition, but usually is). + * + * This is similar to wait_var_event() but returns a value which is 0 if + * the timeout expired and the condition was still false, or the + * remaining time left in the timeout (but at least 1) if the condition + * was found to be true. + * + * The condition should normally use smp_load_acquire() or a similarly + * ordered access to ensure that any changes to memory made before the + * condition became true will be visible after the wait completes. + */ #define wait_var_event_timeout(var, condition, timeout) \ ({ \ long __ret = timeout; \ @@ -309,6 +405,23 @@ do { \ ___wait_var_event(var, condition, TASK_INTERRUPTIBLE, 0, 0, \ schedule()) +/** + * wait_var_event_killable - wait for a variable to be updated and notified + * @var: the address of variable being waited on + * @condition: the condition to wait for + * + * Wait for a @condition to be true or a signal to be received, only + * re-checking the condition when a wake up is received for the given + * @var (an arbitrary kernel address which need not be directly related + * to the given condition, but usually is). + * + * This is similar to wait_var_event() but returns a value which is 0 if + * the condition became true, or %-ERESTARTSYS if a signal was received. + * + * The condition should normally use smp_load_acquire() or a similarly + * ordered access to ensure that any changes to memory made before the + * condition became true will be visible after the wait completes. + */ #define wait_var_event_interruptible(var, condition) \ ({ \ int __ret = 0; \ @@ -319,15 +432,122 @@ do { \ }) /** - * clear_and_wake_up_bit - clear a bit and wake up anyone waiting on that bit + * wait_var_event_any_lock - wait for a variable to be updated under a lock + * @var: the address of the variable being waited on + * @condition: condition to wait for + * @lock: the object that is locked to protect updates to the variable + * @type: prefix on lock and unlock operations + * @state: waiting state, %TASK_UNINTERRUPTIBLE etc. + * + * Wait for a condition which can only be reliably tested while holding + * a lock. The variables assessed in the condition will normal be updated + * under the same lock, and the wake up should be signalled with + * wake_up_var_locked() under the same lock. + * + * This is similar to wait_var_event(), but assumes a lock is held + * while calling this function and while updating the variable. * + * This must be called while the given lock is held and the lock will be + * dropped when schedule() is called to wait for a wake up, and will be + * reclaimed before testing the condition again. The functions used to + * unlock and lock the object are constructed by appending _unlock and _lock + * to @type. + * + * Return %-ERESTARTSYS if a signal arrives which is allowed to interrupt + * the wait according to @state. + */ +#define wait_var_event_any_lock(var, condition, lock, type, state) \ +({ \ + int __ret = 0; \ + if (!(condition)) \ + __ret = ___wait_var_event(var, condition, state, 0, 0, \ + type ## _unlock(lock); \ + schedule(); \ + type ## _lock(lock)); \ + __ret; \ +}) + +/** + * wait_var_event_spinlock - wait for a variable to be updated under a spinlock + * @var: the address of the variable being waited on + * @condition: condition to wait for + * @lock: the spinlock which protects updates to the variable + * + * Wait for a condition which can only be reliably tested while holding + * a spinlock. The variables assessed in the condition will normal be updated + * under the same spinlock, and the wake up should be signalled with + * wake_up_var_locked() under the same spinlock. + * + * This is similar to wait_var_event(), but assumes a spinlock is held + * while calling this function and while updating the variable. + * + * This must be called while the given lock is held and the lock will be + * dropped when schedule() is called to wait for a wake up, and will be + * reclaimed before testing the condition again. + */ +#define wait_var_event_spinlock(var, condition, lock) \ + wait_var_event_any_lock(var, condition, lock, spin, TASK_UNINTERRUPTIBLE) + +/** + * wait_var_event_mutex - wait for a variable to be updated under a mutex + * @var: the address of the variable being waited on + * @condition: condition to wait for + * @mutex: the mutex which protects updates to the variable + * + * Wait for a condition which can only be reliably tested while holding + * a mutex. The variables assessed in the condition will normal be + * updated under the same mutex, and the wake up should be signalled + * with wake_up_var_locked() under the same mutex. + * + * This is similar to wait_var_event(), but assumes a mutex is held + * while calling this function and while updating the variable. + * + * This must be called while the given mutex is held and the mutex will be + * dropped when schedule() is called to wait for a wake up, and will be + * reclaimed before testing the condition again. + */ +#define wait_var_event_mutex(var, condition, lock) \ + wait_var_event_any_lock(var, condition, lock, mutex, TASK_UNINTERRUPTIBLE) + +/** + * wake_up_var_protected - wake up waiters for a variable asserting that it is safe + * @var: the address of the variable being waited on + * @cond: the condition which afirms this is safe + * + * When waking waiters which use wait_var_event_any_lock() the waker must be + * holding the reelvant lock to avoid races. This version of wake_up_var() + * asserts that the relevant lock is held and so no barrier is needed. + * The @cond is only tested when CONFIG_LOCKDEP is enabled. + */ +#define wake_up_var_protected(var, cond) \ +do { \ + lockdep_assert(cond); \ + wake_up_var(var); \ +} while (0) + +/** + * wake_up_var_locked - wake up waiters for a variable while holding a spinlock or mutex + * @var: the address of the variable being waited on + * @lock: The spinlock or mutex what protects the variable + * + * Send a wake up for the given variable which should be waited for with + * wait_var_event_spinlock() or wait_var_event_mutex(). Unlike wake_up_var(), + * no extra barriers are needed as the locking provides sufficient sequencing. + */ +#define wake_up_var_locked(var, lock) \ + wake_up_var_protected(var, lockdep_is_held(lock)) + +/** + * clear_and_wake_up_bit - clear a bit and wake up anyone waiting on that bit * @bit: the bit of the word being waited on - * @word: the word being waited on, a kernel virtual address + * @word: the address containing the bit being waited on * - * You can use this helper if bitflags are manipulated atomically rather than - * non-atomically under a lock. + * The designated bit is cleared and any tasks waiting in wait_on_bit() + * or similar will be woken. This call has RELEASE semantics so that + * any changes to memory made before this call are guaranteed to be visible + * after the corresponding wait_on_bit() completes. */ -static inline void clear_and_wake_up_bit(int bit, void *word) +static inline void clear_and_wake_up_bit(int bit, unsigned long *word) { clear_bit_unlock(bit, word); /* See wake_up_bit() for which memory barrier you need to use. */ @@ -335,4 +555,64 @@ static inline void clear_and_wake_up_bit(int bit, void *word) wake_up_bit(word, bit); } +/** + * test_and_clear_wake_up_bit - clear a bit if it was set: wake up anyone waiting on that bit + * @bit: the bit of the word being waited on + * @word: the address of memory containing that bit + * + * If the bit is set and can be atomically cleared, any tasks waiting in + * wait_on_bit() or similar will be woken. This call has the same + * complete ordering semantics as test_and_clear_bit(). Any changes to + * memory made before this call are guaranteed to be visible after the + * corresponding wait_on_bit() completes. + * + * Returns %true if the bit was successfully set and the wake up was sent. + */ +static inline bool test_and_clear_wake_up_bit(int bit, unsigned long *word) +{ + if (!test_and_clear_bit(bit, word)) + return false; + /* no extra barrier required */ + wake_up_bit(word, bit); + return true; +} + +/** + * atomic_dec_and_wake_up - decrement an atomic_t and if zero, wake up waiters + * @var: the variable to dec and test + * + * Decrements the atomic variable and if it reaches zero, send a wake_up to any + * processes waiting on the variable. + * + * This function has the same complete ordering semantics as atomic_dec_and_test. + * + * Returns %true is the variable reaches zero and the wake up was sent. + */ + +static inline bool atomic_dec_and_wake_up(atomic_t *var) +{ + if (!atomic_dec_and_test(var)) + return false; + /* No extra barrier required */ + wake_up_var(var); + return true; +} + +/** + * store_release_wake_up - update a variable and send a wake_up + * @var: the address of the variable to be updated and woken + * @val: the value to store in the variable. + * + * Store the given value in the variable send a wake up to any tasks + * waiting on the variable. All necessary barriers are included to ensure + * the task calling wait_var_event() sees the new value and all values + * written to memory before this call. + */ +#define store_release_wake_up(var, val) \ +do { \ + smp_store_release(var, val); \ + smp_mb(); \ + wake_up_var(var); \ +} while (0) + #endif /* _LINUX_WAIT_BIT_H */ diff --git a/include/linux/writeback.h b/include/linux/writeback.h index d6db822e4bb3..d11b903c2edb 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -213,11 +213,8 @@ static inline void wait_on_inode(struct inode *inode) #include <linux/bio.h> void __inode_attach_wb(struct inode *inode, struct folio *folio); -void wbc_attach_and_unlock_inode(struct writeback_control *wbc, - struct inode *inode) - __releases(&inode->i_lock); void wbc_detach_inode(struct writeback_control *wbc); -void wbc_account_cgroup_owner(struct writeback_control *wbc, struct page *page, +void wbc_account_cgroup_owner(struct writeback_control *wbc, struct folio *folio, size_t bytes); int cgroup_writeback_by_id(u64 bdi_id, int memcg_id, enum wb_reason reason, struct wb_completion *done); @@ -254,22 +251,8 @@ static inline void inode_detach_wb(struct inode *inode) } } -/** - * wbc_attach_fdatawrite_inode - associate wbc and inode for fdatawrite - * @wbc: writeback_control of interest - * @inode: target inode - * - * This function is to be used by __filemap_fdatawrite_range(), which is an - * alternative entry point into writeback code, and first ensures @inode is - * associated with a bdi_writeback and attaches it to @wbc. - */ -static inline void wbc_attach_fdatawrite_inode(struct writeback_control *wbc, - struct inode *inode) -{ - spin_lock(&inode->i_lock); - inode_attach_wb(inode, NULL); - wbc_attach_and_unlock_inode(wbc, inode); -} +void wbc_attach_fdatawrite_inode(struct writeback_control *wbc, + struct inode *inode); /** * wbc_init_bio - writeback specific initializtion of bio @@ -303,13 +286,6 @@ static inline void inode_detach_wb(struct inode *inode) { } -static inline void wbc_attach_and_unlock_inode(struct writeback_control *wbc, - struct inode *inode) - __releases(&inode->i_lock) -{ - spin_unlock(&inode->i_lock); -} - static inline void wbc_attach_fdatawrite_inode(struct writeback_control *wbc, struct inode *inode) { @@ -324,7 +300,7 @@ static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio) } static inline void wbc_account_cgroup_owner(struct writeback_control *wbc, - struct page *page, size_t bytes) + struct folio *folio, size_t bytes) { } diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h index bb763085479a..a401a2f31a77 100644 --- a/include/linux/ww_mutex.h +++ b/include/linux/ww_mutex.h @@ -65,6 +65,16 @@ struct ww_acquire_ctx { #endif #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; + /** + * @first_lock_dep_map: fake lockdep_map for first locked ww_mutex. + * + * lockdep requires the lockdep_map for the first locked ww_mutex + * in a ww transaction to remain in memory until all ww_mutexes of + * the transaction have been unlocked. Ensure this by keeping a + * fake locked ww_mutex lockdep map between ww_acquire_init() and + * ww_acquire_fini(). + */ + struct lockdep_map first_lock_dep_map; #endif #ifdef CONFIG_DEBUG_WW_MUTEX_SLOWPATH unsigned int deadlock_inject_interval; @@ -146,7 +156,10 @@ static inline void ww_acquire_init(struct ww_acquire_ctx *ctx, debug_check_no_locks_freed((void *)ctx, sizeof(*ctx)); lockdep_init_map(&ctx->dep_map, ww_class->acquire_name, &ww_class->acquire_key, 0); + lockdep_init_map(&ctx->first_lock_dep_map, ww_class->mutex_name, + &ww_class->mutex_key, 0); mutex_acquire(&ctx->dep_map, 0, 0, _RET_IP_); + mutex_acquire_nest(&ctx->first_lock_dep_map, 0, 0, &ctx->dep_map, _RET_IP_); #endif #ifdef CONFIG_DEBUG_WW_MUTEX_SLOWPATH ctx->deadlock_inject_interval = 1; @@ -185,6 +198,7 @@ static inline void ww_acquire_done(struct ww_acquire_ctx *ctx) static inline void ww_acquire_fini(struct ww_acquire_ctx *ctx) { #ifdef CONFIG_DEBUG_LOCK_ALLOC + mutex_release(&ctx->first_lock_dep_map, _THIS_IP_); mutex_release(&ctx->dep_map, _THIS_IP_); #endif #ifdef DEBUG_WW_MUTEXES diff --git a/include/linux/xattr.h b/include/linux/xattr.h index d20051865800..86b0d47984a1 100644 --- a/include/linux/xattr.h +++ b/include/linux/xattr.h @@ -19,6 +19,10 @@ #include <linux/user_namespace.h> #include <uapi/linux/xattr.h> +/* List of all open_how "versions". */ +#define XATTR_ARGS_SIZE_VER0 16 /* sizeof first published struct */ +#define XATTR_ARGS_SIZE_LATEST XATTR_ARGS_SIZE_VER0 + struct inode; struct dentry; |