mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-12 05:48:40 +00:00
![Ming Lei](/assets/img/avatar_default.png)
The kernfs built-in lock of 'kn->count' is held in sysfs .show/.store path. Meantime, inside block's .show/.store callback, q->sysfs_lock is required. However, when mq & iosched kobjects are removed via blk_mq_unregister_dev() & elv_unregister_queue(), q->sysfs_lock is held too. This way causes AB-BA lock because the kernfs built-in lock of 'kn-count' is required inside kobject_del() too, see the lockdep warning[1]. On the other hand, it isn't necessary to acquire q->sysfs_lock for both blk_mq_unregister_dev() & elv_unregister_queue() because clearing REGISTERED flag prevents storing to 'queue/scheduler' from being happened. Also sysfs write(store) is exclusive, so no necessary to hold the lock for elv_unregister_queue() when it is called in switching elevator path. So split .sysfs_lock into two: one is still named as .sysfs_lock for covering sync .store, the other one is named as .sysfs_dir_lock for covering kobjects and related status change. sysfs itself can handle the race between add/remove kobjects and showing/storing attributes under kobjects. For switching scheduler via storing to 'queue/scheduler', we use the queue flag of QUEUE_FLAG_REGISTERED with .sysfs_lock for avoiding the race, then we can avoid to hold .sysfs_lock during removing/adding kobjects. [1] lockdep warning ====================================================== WARNING: possible circular locking dependency detected 5.3.0-rc3-00044-g73277fc75ea0 #1380 Not tainted ------------------------------------------------------ rmmod/777 is trying to acquire lock: 00000000ac50e981 (kn->count#202){++++}, at: kernfs_remove_by_name_ns+0x59/0x72 but task is already holding lock: 00000000fb16ae21 (&q->sysfs_lock){+.+.}, at: blk_unregister_queue+0x78/0x10b which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&q->sysfs_lock){+.+.}: __lock_acquire+0x95f/0xa2f lock_acquire+0x1b4/0x1e8 __mutex_lock+0x14a/0xa9b blk_mq_hw_sysfs_show+0x63/0xb6 sysfs_kf_seq_show+0x11f/0x196 seq_read+0x2cd/0x5f2 vfs_read+0xc7/0x18c ksys_read+0xc4/0x13e do_syscall_64+0xa7/0x295 entry_SYSCALL_64_after_hwframe+0x49/0xbe -> #0 (kn->count#202){++++}: check_prev_add+0x5d2/0xc45 validate_chain+0xed3/0xf94 __lock_acquire+0x95f/0xa2f lock_acquire+0x1b4/0x1e8 __kernfs_remove+0x237/0x40b kernfs_remove_by_name_ns+0x59/0x72 remove_files+0x61/0x96 sysfs_remove_group+0x81/0xa4 sysfs_remove_groups+0x3b/0x44 kobject_del+0x44/0x94 blk_mq_unregister_dev+0x83/0xdd blk_unregister_queue+0xa0/0x10b del_gendisk+0x259/0x3fa null_del_dev+0x8b/0x1c3 [null_blk] null_exit+0x5c/0x95 [null_blk] __se_sys_delete_module+0x204/0x337 do_syscall_64+0xa7/0x295 entry_SYSCALL_64_after_hwframe+0x49/0xbe other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&q->sysfs_lock); lock(kn->count#202); lock(&q->sysfs_lock); lock(kn->count#202); *** DEADLOCK *** 2 locks held by rmmod/777: #0: 00000000e69bd9de (&lock){+.+.}, at: null_exit+0x2e/0x95 [null_blk] #1: 00000000fb16ae21 (&q->sysfs_lock){+.+.}, at: blk_unregister_queue+0x78/0x10b stack backtrace: CPU: 0 PID: 777 Comm: rmmod Not tainted 5.3.0-rc3-00044-g73277fc75ea0 #1380 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS ?-20180724_192412-buildhw-07.phx4 Call Trace: dump_stack+0x9a/0xe6 check_noncircular+0x207/0x251 ? print_circular_bug+0x32a/0x32a ? find_usage_backwards+0x84/0xb0 check_prev_add+0x5d2/0xc45 validate_chain+0xed3/0xf94 ? check_prev_add+0xc45/0xc45 ? mark_lock+0x11b/0x804 ? check_usage_forwards+0x1ca/0x1ca __lock_acquire+0x95f/0xa2f lock_acquire+0x1b4/0x1e8 ? kernfs_remove_by_name_ns+0x59/0x72 __kernfs_remove+0x237/0x40b ? kernfs_remove_by_name_ns+0x59/0x72 ? kernfs_next_descendant_post+0x7d/0x7d ? strlen+0x10/0x23 ? strcmp+0x22/0x44 kernfs_remove_by_name_ns+0x59/0x72 remove_files+0x61/0x96 sysfs_remove_group+0x81/0xa4 sysfs_remove_groups+0x3b/0x44 kobject_del+0x44/0x94 blk_mq_unregister_dev+0x83/0xdd blk_unregister_queue+0xa0/0x10b del_gendisk+0x259/0x3fa ? disk_events_poll_msecs_store+0x12b/0x12b ? check_flags+0x1ea/0x204 ? mark_held_locks+0x1f/0x7a null_del_dev+0x8b/0x1c3 [null_blk] null_exit+0x5c/0x95 [null_blk] __se_sys_delete_module+0x204/0x337 ? free_module+0x39f/0x39f ? blkcg_maybe_throttle_current+0x8a/0x718 ? rwlock_bug+0x62/0x62 ? __blkcg_punt_bio_submit+0xd0/0xd0 ? trace_hardirqs_on_thunk+0x1a/0x20 ? mark_held_locks+0x1f/0x7a ? do_syscall_64+0x4c/0x295 do_syscall_64+0xa7/0x295 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x7fb696cdbe6b Code: 73 01 c3 48 8b 0d 1d 20 0c 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 008 RSP: 002b:00007ffec9588788 EFLAGS: 00000206 ORIG_RAX: 00000000000000b0 RAX: ffffffffffffffda RBX: 0000559e589137c0 RCX: 00007fb696cdbe6b RDX: 000000000000000a RSI: 0000000000000800 RDI: 0000559e58913828 RBP: 0000000000000000 R08: 00007ffec9587701 R09: 0000000000000000 R10: 00007fb696d4eae0 R11: 0000000000000206 R12: 00007ffec95889b0 R13: 00007ffec95896b3 R14: 0000559e58913260 R15: 0000559e589137c0 Cc: Christoph Hellwig <hch@infradead.org> Cc: Hannes Reinecke <hare@suse.com> Cc: Greg KH <gregkh@linuxfoundation.org> Cc: Mike Snitzer <snitzer@redhat.com> Reviewed-by: Bart Van Assche <bvanassche@acm.org> Signed-off-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
346 lines
10 KiB
C
346 lines
10 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef BLK_INTERNAL_H
|
|
#define BLK_INTERNAL_H
|
|
|
|
#include <linux/idr.h>
|
|
#include <linux/blk-mq.h>
|
|
#include <xen/xen.h>
|
|
#include "blk-mq.h"
|
|
#include "blk-mq-sched.h"
|
|
|
|
/* Max future timer expiry for timeouts */
|
|
#define BLK_MAX_TIMEOUT (5 * HZ)
|
|
|
|
#ifdef CONFIG_DEBUG_FS
|
|
extern struct dentry *blk_debugfs_root;
|
|
#endif
|
|
|
|
struct blk_flush_queue {
|
|
unsigned int flush_queue_delayed:1;
|
|
unsigned int flush_pending_idx:1;
|
|
unsigned int flush_running_idx:1;
|
|
unsigned long flush_pending_since;
|
|
struct list_head flush_queue[2];
|
|
struct list_head flush_data_in_flight;
|
|
struct request *flush_rq;
|
|
|
|
/*
|
|
* flush_rq shares tag with this rq, both can't be active
|
|
* at the same time
|
|
*/
|
|
struct request *orig_rq;
|
|
spinlock_t mq_flush_lock;
|
|
};
|
|
|
|
extern struct kmem_cache *blk_requestq_cachep;
|
|
extern struct kobj_type blk_queue_ktype;
|
|
extern struct ida blk_queue_ida;
|
|
|
|
static inline struct blk_flush_queue *
|
|
blk_get_flush_queue(struct request_queue *q, struct blk_mq_ctx *ctx)
|
|
{
|
|
return blk_mq_map_queue(q, REQ_OP_FLUSH, ctx)->fq;
|
|
}
|
|
|
|
static inline void __blk_get_queue(struct request_queue *q)
|
|
{
|
|
kobject_get(&q->kobj);
|
|
}
|
|
|
|
struct blk_flush_queue *blk_alloc_flush_queue(struct request_queue *q,
|
|
int node, int cmd_size, gfp_t flags);
|
|
void blk_free_flush_queue(struct blk_flush_queue *q);
|
|
|
|
void blk_freeze_queue(struct request_queue *q);
|
|
|
|
static inline void blk_queue_enter_live(struct request_queue *q)
|
|
{
|
|
/*
|
|
* Given that running in generic_make_request() context
|
|
* guarantees that a live reference against q_usage_counter has
|
|
* been established, further references under that same context
|
|
* need not check that the queue has been frozen (marked dead).
|
|
*/
|
|
percpu_ref_get(&q->q_usage_counter);
|
|
}
|
|
|
|
static inline bool biovec_phys_mergeable(struct request_queue *q,
|
|
struct bio_vec *vec1, struct bio_vec *vec2)
|
|
{
|
|
unsigned long mask = queue_segment_boundary(q);
|
|
phys_addr_t addr1 = page_to_phys(vec1->bv_page) + vec1->bv_offset;
|
|
phys_addr_t addr2 = page_to_phys(vec2->bv_page) + vec2->bv_offset;
|
|
|
|
if (addr1 + vec1->bv_len != addr2)
|
|
return false;
|
|
if (xen_domain() && !xen_biovec_phys_mergeable(vec1, vec2->bv_page))
|
|
return false;
|
|
if ((addr1 | mask) != ((addr2 + vec2->bv_len - 1) | mask))
|
|
return false;
|
|
return true;
|
|
}
|
|
|
|
static inline bool __bvec_gap_to_prev(struct request_queue *q,
|
|
struct bio_vec *bprv, unsigned int offset)
|
|
{
|
|
return (offset & queue_virt_boundary(q)) ||
|
|
((bprv->bv_offset + bprv->bv_len) & queue_virt_boundary(q));
|
|
}
|
|
|
|
/*
|
|
* Check if adding a bio_vec after bprv with offset would create a gap in
|
|
* the SG list. Most drivers don't care about this, but some do.
|
|
*/
|
|
static inline bool bvec_gap_to_prev(struct request_queue *q,
|
|
struct bio_vec *bprv, unsigned int offset)
|
|
{
|
|
if (!queue_virt_boundary(q))
|
|
return false;
|
|
return __bvec_gap_to_prev(q, bprv, offset);
|
|
}
|
|
|
|
static inline void blk_rq_bio_prep(struct request *rq, struct bio *bio,
|
|
unsigned int nr_segs)
|
|
{
|
|
rq->nr_phys_segments = nr_segs;
|
|
rq->__data_len = bio->bi_iter.bi_size;
|
|
rq->bio = rq->biotail = bio;
|
|
rq->ioprio = bio_prio(bio);
|
|
|
|
if (bio->bi_disk)
|
|
rq->rq_disk = bio->bi_disk;
|
|
}
|
|
|
|
#ifdef CONFIG_BLK_DEV_INTEGRITY
|
|
void blk_flush_integrity(void);
|
|
bool __bio_integrity_endio(struct bio *);
|
|
static inline bool bio_integrity_endio(struct bio *bio)
|
|
{
|
|
if (bio_integrity(bio))
|
|
return __bio_integrity_endio(bio);
|
|
return true;
|
|
}
|
|
|
|
static inline bool integrity_req_gap_back_merge(struct request *req,
|
|
struct bio *next)
|
|
{
|
|
struct bio_integrity_payload *bip = bio_integrity(req->bio);
|
|
struct bio_integrity_payload *bip_next = bio_integrity(next);
|
|
|
|
return bvec_gap_to_prev(req->q, &bip->bip_vec[bip->bip_vcnt - 1],
|
|
bip_next->bip_vec[0].bv_offset);
|
|
}
|
|
|
|
static inline bool integrity_req_gap_front_merge(struct request *req,
|
|
struct bio *bio)
|
|
{
|
|
struct bio_integrity_payload *bip = bio_integrity(bio);
|
|
struct bio_integrity_payload *bip_next = bio_integrity(req->bio);
|
|
|
|
return bvec_gap_to_prev(req->q, &bip->bip_vec[bip->bip_vcnt - 1],
|
|
bip_next->bip_vec[0].bv_offset);
|
|
}
|
|
#else /* CONFIG_BLK_DEV_INTEGRITY */
|
|
static inline bool integrity_req_gap_back_merge(struct request *req,
|
|
struct bio *next)
|
|
{
|
|
return false;
|
|
}
|
|
static inline bool integrity_req_gap_front_merge(struct request *req,
|
|
struct bio *bio)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
static inline void blk_flush_integrity(void)
|
|
{
|
|
}
|
|
static inline bool bio_integrity_endio(struct bio *bio)
|
|
{
|
|
return true;
|
|
}
|
|
#endif /* CONFIG_BLK_DEV_INTEGRITY */
|
|
|
|
unsigned long blk_rq_timeout(unsigned long timeout);
|
|
void blk_add_timer(struct request *req);
|
|
|
|
bool bio_attempt_front_merge(struct request *req, struct bio *bio,
|
|
unsigned int nr_segs);
|
|
bool bio_attempt_back_merge(struct request *req, struct bio *bio,
|
|
unsigned int nr_segs);
|
|
bool bio_attempt_discard_merge(struct request_queue *q, struct request *req,
|
|
struct bio *bio);
|
|
bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
|
|
unsigned int nr_segs, struct request **same_queue_rq);
|
|
|
|
void blk_account_io_start(struct request *req, bool new_io);
|
|
void blk_account_io_completion(struct request *req, unsigned int bytes);
|
|
void blk_account_io_done(struct request *req, u64 now);
|
|
|
|
/*
|
|
* Internal elevator interface
|
|
*/
|
|
#define ELV_ON_HASH(rq) ((rq)->rq_flags & RQF_HASHED)
|
|
|
|
void blk_insert_flush(struct request *rq);
|
|
|
|
int elevator_init_mq(struct request_queue *q);
|
|
int elevator_switch_mq(struct request_queue *q,
|
|
struct elevator_type *new_e);
|
|
void __elevator_exit(struct request_queue *, struct elevator_queue *);
|
|
int elv_register_queue(struct request_queue *q, bool uevent);
|
|
void elv_unregister_queue(struct request_queue *q);
|
|
|
|
static inline void elevator_exit(struct request_queue *q,
|
|
struct elevator_queue *e)
|
|
{
|
|
blk_mq_sched_free_requests(q);
|
|
__elevator_exit(q, e);
|
|
}
|
|
|
|
struct hd_struct *__disk_get_part(struct gendisk *disk, int partno);
|
|
|
|
#ifdef CONFIG_FAIL_IO_TIMEOUT
|
|
int blk_should_fake_timeout(struct request_queue *);
|
|
ssize_t part_timeout_show(struct device *, struct device_attribute *, char *);
|
|
ssize_t part_timeout_store(struct device *, struct device_attribute *,
|
|
const char *, size_t);
|
|
#else
|
|
static inline int blk_should_fake_timeout(struct request_queue *q)
|
|
{
|
|
return 0;
|
|
}
|
|
#endif
|
|
|
|
void __blk_queue_split(struct request_queue *q, struct bio **bio,
|
|
unsigned int *nr_segs);
|
|
int ll_back_merge_fn(struct request *req, struct bio *bio,
|
|
unsigned int nr_segs);
|
|
int ll_front_merge_fn(struct request *req, struct bio *bio,
|
|
unsigned int nr_segs);
|
|
struct request *attempt_back_merge(struct request_queue *q, struct request *rq);
|
|
struct request *attempt_front_merge(struct request_queue *q, struct request *rq);
|
|
int blk_attempt_req_merge(struct request_queue *q, struct request *rq,
|
|
struct request *next);
|
|
unsigned int blk_recalc_rq_segments(struct request *rq);
|
|
void blk_rq_set_mixed_merge(struct request *rq);
|
|
bool blk_rq_merge_ok(struct request *rq, struct bio *bio);
|
|
enum elv_merge blk_try_merge(struct request *rq, struct bio *bio);
|
|
|
|
int blk_dev_init(void);
|
|
|
|
/*
|
|
* Contribute to IO statistics IFF:
|
|
*
|
|
* a) it's attached to a gendisk, and
|
|
* b) the queue had IO stats enabled when this request was started, and
|
|
* c) it's a file system request
|
|
*/
|
|
static inline bool blk_do_io_stat(struct request *rq)
|
|
{
|
|
return rq->rq_disk &&
|
|
(rq->rq_flags & RQF_IO_STAT) &&
|
|
!blk_rq_is_passthrough(rq);
|
|
}
|
|
|
|
static inline void req_set_nomerge(struct request_queue *q, struct request *req)
|
|
{
|
|
req->cmd_flags |= REQ_NOMERGE;
|
|
if (req == q->last_merge)
|
|
q->last_merge = NULL;
|
|
}
|
|
|
|
/*
|
|
* The max size one bio can handle is UINT_MAX becasue bvec_iter.bi_size
|
|
* is defined as 'unsigned int', meantime it has to aligned to with logical
|
|
* block size which is the minimum accepted unit by hardware.
|
|
*/
|
|
static inline unsigned int bio_allowed_max_sectors(struct request_queue *q)
|
|
{
|
|
return round_down(UINT_MAX, queue_logical_block_size(q)) >> 9;
|
|
}
|
|
|
|
/*
|
|
* Internal io_context interface
|
|
*/
|
|
void get_io_context(struct io_context *ioc);
|
|
struct io_cq *ioc_lookup_icq(struct io_context *ioc, struct request_queue *q);
|
|
struct io_cq *ioc_create_icq(struct io_context *ioc, struct request_queue *q,
|
|
gfp_t gfp_mask);
|
|
void ioc_clear_queue(struct request_queue *q);
|
|
|
|
int create_task_io_context(struct task_struct *task, gfp_t gfp_mask, int node);
|
|
|
|
/**
|
|
* create_io_context - try to create task->io_context
|
|
* @gfp_mask: allocation mask
|
|
* @node: allocation node
|
|
*
|
|
* If %current->io_context is %NULL, allocate a new io_context and install
|
|
* it. Returns the current %current->io_context which may be %NULL if
|
|
* allocation failed.
|
|
*
|
|
* Note that this function can't be called with IRQ disabled because
|
|
* task_lock which protects %current->io_context is IRQ-unsafe.
|
|
*/
|
|
static inline struct io_context *create_io_context(gfp_t gfp_mask, int node)
|
|
{
|
|
WARN_ON_ONCE(irqs_disabled());
|
|
if (unlikely(!current->io_context))
|
|
create_task_io_context(current, gfp_mask, node);
|
|
return current->io_context;
|
|
}
|
|
|
|
/*
|
|
* Internal throttling interface
|
|
*/
|
|
#ifdef CONFIG_BLK_DEV_THROTTLING
|
|
extern void blk_throtl_drain(struct request_queue *q);
|
|
extern int blk_throtl_init(struct request_queue *q);
|
|
extern void blk_throtl_exit(struct request_queue *q);
|
|
extern void blk_throtl_register_queue(struct request_queue *q);
|
|
#else /* CONFIG_BLK_DEV_THROTTLING */
|
|
static inline void blk_throtl_drain(struct request_queue *q) { }
|
|
static inline int blk_throtl_init(struct request_queue *q) { return 0; }
|
|
static inline void blk_throtl_exit(struct request_queue *q) { }
|
|
static inline void blk_throtl_register_queue(struct request_queue *q) { }
|
|
#endif /* CONFIG_BLK_DEV_THROTTLING */
|
|
#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
|
|
extern ssize_t blk_throtl_sample_time_show(struct request_queue *q, char *page);
|
|
extern ssize_t blk_throtl_sample_time_store(struct request_queue *q,
|
|
const char *page, size_t count);
|
|
extern void blk_throtl_bio_endio(struct bio *bio);
|
|
extern void blk_throtl_stat_add(struct request *rq, u64 time);
|
|
#else
|
|
static inline void blk_throtl_bio_endio(struct bio *bio) { }
|
|
static inline void blk_throtl_stat_add(struct request *rq, u64 time) { }
|
|
#endif
|
|
|
|
#ifdef CONFIG_BOUNCE
|
|
extern int init_emergency_isa_pool(void);
|
|
extern void blk_queue_bounce(struct request_queue *q, struct bio **bio);
|
|
#else
|
|
static inline int init_emergency_isa_pool(void)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline void blk_queue_bounce(struct request_queue *q, struct bio **bio)
|
|
{
|
|
}
|
|
#endif /* CONFIG_BOUNCE */
|
|
|
|
#ifdef CONFIG_BLK_CGROUP_IOLATENCY
|
|
extern int blk_iolatency_init(struct request_queue *q);
|
|
#else
|
|
static inline int blk_iolatency_init(struct request_queue *q) { return 0; }
|
|
#endif
|
|
|
|
struct bio *blk_next_bio(struct bio *bio, unsigned int nr_pages, gfp_t gfp);
|
|
|
|
#ifdef CONFIG_BLK_DEV_ZONED
|
|
void blk_queue_free_zone_bitmaps(struct request_queue *q);
|
|
#else
|
|
static inline void blk_queue_free_zone_bitmaps(struct request_queue *q) {}
|
|
#endif
|
|
|
|
#endif /* BLK_INTERNAL_H */
|