korg/linux
0
0
Fork 0
mirror of https://mirrors.bfsu.edu.cn/git/linux.git synced 2024-09-21 20:22:13 +08:00
Code Issues Packages Projects Releases Wiki Activity
1d9bd5161b
linux/block/blk.h
Tejun Heo 1d9bd5161b blk-mq: replace timeout synchronization with a RCU and generation based scheme 
Currently, blk-mq timeout path synchronizes against the usual
issue/completion path using a complex scheme involving atomic
bitflags, REQ_ATOM_*, memory barriers and subtle memory coherence
rules.  Unfortunately, it contains quite a few holes.

There's a complex dancing around REQ_ATOM_STARTED and
REQ_ATOM_COMPLETE between issue/completion and timeout paths; however,
they don't have a synchronization point across request recycle
instances and it isn't clear what the barriers add.
blk_mq_check_expired() can easily read STARTED from N-2'th iteration,
deadline from N-1'th, blk_mark_rq_complete() against Nth instance.

In fact, it's pretty easy to make blk_mq_check_expired() terminate a
later instance of a request.  If we induce 5 sec delay before
time_after_eq() test in blk_mq_check_expired(), shorten the timeout to
2s, and issue back-to-back large IOs, blk-mq starts timing out
requests spuriously pretty quickly.  Nothing actually timed out.  It
just made the call on a recycle instance of a request and then
terminated a later instance long after the original instance finished.
The scenario isn't theoretical either.

This patch replaces the broken synchronization mechanism with a RCU
and generation number based one.

1. Each request has a u64 generation + state value, which can be
   updated only by the request owner.  Whenever a request becomes
   in-flight, the generation number gets bumped up too.  This provides
   the basis for the timeout path to distinguish different recycle
   instances of the request.

   Also, marking a request in-flight and setting its deadline are
   protected with a seqcount so that the timeout path can fetch both
   values coherently.

2. The timeout path fetches the generation, state and deadline.  If
   the verdict is timeout, it records the generation into a dedicated
   request abortion field and does RCU wait.

3. The completion path is also protected by RCU (from the previous
   patch) and checks whether the current generation number and state
   match the abortion field.  If so, it skips completion.

4. The timeout path, after RCU wait, scans requests again and
   terminates the ones whose generation and state still match the ones
   requested for abortion.

   By now, the timeout path knows that either the generation number
   and state changed if it lost the race or the completion will yield
   to it and can safely timeout the request.

While it's more lines of code, it's conceptually simpler, doesn't
depend on direct use of subtle memory ordering or coherence, and
hopefully doesn't terminate the wrong instance.

While this change makes REQ_ATOM_COMPLETE synchronization unnecessary
between issue/complete and timeout paths, REQ_ATOM_COMPLETE isn't
removed yet as it's still used in other places.  Future patches will
move all state tracking to the new mechanism and remove all bitops in
the hot paths.

Note that this patch adds a comment explaining a race condition in
BLK_EH_RESET_TIMER path.  The race has always been there and this
patch doesn't change it.  It's just documenting the existing race.

v2: - Fixed BLK_EH_RESET_TIMER handling as pointed out by Jianchao.
    - s/request->gstate_seqc/request->gstate_seq/ as suggested by Peter.
    - READ_ONCE() added in blk_mq_rq_update_state() as suggested by Peter.

v3: - Fixed possible extended seqcount / u64_stats_sync read looping
      spotted by Peter.
    - MQ_RQ_IDLE was incorrectly being set in complete_request instead
      of free_request.  Fixed.

v4: - Rebased on top of hctx_lock() refactoring patch.
    - Added comment explaining the use of hctx_lock() in completion path.

v5: - Added comments requested by Bart.
    - Note the addition of BLK_EH_RESET_TIMER race condition in the
      commit message.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: "jianchao.wang" <jianchao.w.wang@oracle.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Bart Van Assche <Bart.VanAssche@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-01-09 09:31:15 -07:00

328 lines
9.6 KiB
C
Raw Blame History

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef BLK_INTERNAL_H
#define BLK_INTERNAL_H
#include <linux/idr.h>
#include <linux/blk-mq.h>
#include "blk-mq.h"
/* Amount of time in which a process may batch requests */
#define BLK_BATCH_TIME (HZ/50UL)
/* Number of requests a "batching" process may submit */
#define BLK_BATCH_REQ 32
/* 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 kmem_cache *request_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)
{
if (q->mq_ops)
return blk_mq_map_queue(q, ctx->cpu)->fq;
return q->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);
void blk_free_flush_queue(struct blk_flush_queue *q);
int blk_init_rl(struct request_list *rl, struct request_queue *q,
gfp_t gfp_mask);
void blk_exit_rl(struct request_queue *q, struct request_list *rl);
void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
struct bio *bio);
void blk_queue_bypass_start(struct request_queue *q);
void blk_queue_bypass_end(struct request_queue *q);
void __blk_queue_free_tags(struct request_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);
}
#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;
}
#else
static inline void blk_flush_integrity(void)
{
}
static inline bool bio_integrity_endio(struct bio *bio)
{
return true;
}
#endif
void blk_timeout_work(struct work_struct *work);
unsigned long blk_rq_timeout(unsigned long timeout);
void blk_add_timer(struct request *req);
void blk_delete_timer(struct request *);
bool bio_attempt_front_merge(struct request_queue *q, struct request *req,
struct bio *bio);
bool bio_attempt_back_merge(struct request_queue *q, struct request *req,
struct bio *bio);
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 *request_count,
struct request **same_queue_rq);
unsigned int blk_plug_queued_count(struct request_queue *q);
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);
/*
* Internal atomic flags for request handling
*/
enum rq_atomic_flags {
REQ_ATOM_COMPLETE = 0,
REQ_ATOM_STARTED,
REQ_ATOM_POLL_SLEPT,
};
/*
* EH timer and IO completion will both attempt to 'grab' the request, make
* sure that only one of them succeeds
*/
static inline int blk_mark_rq_complete(struct request *rq)
{
return test_and_set_bit(REQ_ATOM_COMPLETE, &rq->atomic_flags);
}
static inline void blk_clear_rq_complete(struct request *rq)
{
clear_bit(REQ_ATOM_COMPLETE, &rq->atomic_flags);
}
/*
* Internal elevator interface
*/
#define ELV_ON_HASH(rq) ((rq)->rq_flags & RQF_HASHED)
void blk_insert_flush(struct request *rq);
static inline void elv_activate_rq(struct request_queue *q, struct request *rq)
{
struct elevator_queue *e = q->elevator;
if (e->type->ops.sq.elevator_activate_req_fn)
e->type->ops.sq.elevator_activate_req_fn(q, rq);
}
static inline void elv_deactivate_rq(struct request_queue *q, struct request *rq)
{
struct elevator_queue *e = q->elevator;
if (e->type->ops.sq.elevator_deactivate_req_fn)
e->type->ops.sq.elevator_deactivate_req_fn(q, rq);
}
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
int ll_back_merge_fn(struct request_queue *q, struct request *req,
struct bio *bio);
int ll_front_merge_fn(struct request_queue *q, struct request *req,
struct bio *bio);
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);
void 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);
void blk_queue_congestion_threshold(struct request_queue *q);
int blk_dev_init(void);
/*
* Return the threshold (number of used requests) at which the queue is
* considered to be congested. It include a little hysteresis to keep the
* context switch rate down.
*/
static inline int queue_congestion_on_threshold(struct request_queue *q)
{
return q->nr_congestion_on;
}
/*
* The threshold at which a queue is considered to be uncongested
*/
static inline int queue_congestion_off_threshold(struct request_queue *q)
{
return q->nr_congestion_off;
}
extern int blk_update_nr_requests(struct request_queue *, unsigned int);
/*
* 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 int 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;
}
/*
* 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);
/**
* rq_ioc - determine io_context for request allocation
* @bio: request being allocated is for this bio (can be %NULL)
*
* Determine io_context to use for request allocation for @bio. May return
* %NULL if %current->io_context doesn't exist.
*/
static inline struct io_context *rq_ioc(struct bio *bio)
{
#ifdef CONFIG_BLK_CGROUP
if (bio && bio->bi_ioc)
return bio->bi_ioc;
#endif
return current->io_context;
}
/**
* 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 */
#endif /* BLK_INTERNAL_H */
Reference in New Issue View Git Blame Copy Permalink