mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-24 06:40:54 +07:00
1d9bd5161b
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>
238 lines
6.4 KiB
C
238 lines
6.4 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef INT_BLK_MQ_H
|
|
#define INT_BLK_MQ_H
|
|
|
|
#include "blk-stat.h"
|
|
#include "blk-mq-tag.h"
|
|
|
|
struct blk_mq_tag_set;
|
|
|
|
struct blk_mq_ctx {
|
|
struct {
|
|
spinlock_t lock;
|
|
struct list_head rq_list;
|
|
} ____cacheline_aligned_in_smp;
|
|
|
|
unsigned int cpu;
|
|
unsigned int index_hw;
|
|
|
|
/* incremented at dispatch time */
|
|
unsigned long rq_dispatched[2];
|
|
unsigned long rq_merged;
|
|
|
|
/* incremented at completion time */
|
|
unsigned long ____cacheline_aligned_in_smp rq_completed[2];
|
|
|
|
struct request_queue *queue;
|
|
struct kobject kobj;
|
|
} ____cacheline_aligned_in_smp;
|
|
|
|
/*
|
|
* Bits for request->gstate. The lower two bits carry MQ_RQ_* state value
|
|
* and the upper bits the generation number.
|
|
*/
|
|
enum mq_rq_state {
|
|
MQ_RQ_IDLE = 0,
|
|
MQ_RQ_IN_FLIGHT = 1,
|
|
|
|
MQ_RQ_STATE_BITS = 2,
|
|
MQ_RQ_STATE_MASK = (1 << MQ_RQ_STATE_BITS) - 1,
|
|
MQ_RQ_GEN_INC = 1 << MQ_RQ_STATE_BITS,
|
|
};
|
|
|
|
void blk_mq_freeze_queue(struct request_queue *q);
|
|
void blk_mq_free_queue(struct request_queue *q);
|
|
int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr);
|
|
void blk_mq_wake_waiters(struct request_queue *q);
|
|
bool blk_mq_dispatch_rq_list(struct request_queue *, struct list_head *, bool);
|
|
void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list);
|
|
bool blk_mq_get_driver_tag(struct request *rq, struct blk_mq_hw_ctx **hctx,
|
|
bool wait);
|
|
struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx,
|
|
struct blk_mq_ctx *start);
|
|
|
|
/*
|
|
* Internal helpers for allocating/freeing the request map
|
|
*/
|
|
void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
|
|
unsigned int hctx_idx);
|
|
void blk_mq_free_rq_map(struct blk_mq_tags *tags);
|
|
struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set,
|
|
unsigned int hctx_idx,
|
|
unsigned int nr_tags,
|
|
unsigned int reserved_tags);
|
|
int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
|
|
unsigned int hctx_idx, unsigned int depth);
|
|
|
|
/*
|
|
* Internal helpers for request insertion into sw queues
|
|
*/
|
|
void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
|
|
bool at_head);
|
|
void blk_mq_request_bypass_insert(struct request *rq, bool run_queue);
|
|
void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
|
|
struct list_head *list);
|
|
|
|
/*
|
|
* CPU -> queue mappings
|
|
*/
|
|
extern int blk_mq_hw_queue_to_node(unsigned int *map, unsigned int);
|
|
|
|
static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q,
|
|
int cpu)
|
|
{
|
|
return q->queue_hw_ctx[q->mq_map[cpu]];
|
|
}
|
|
|
|
/*
|
|
* sysfs helpers
|
|
*/
|
|
extern void blk_mq_sysfs_init(struct request_queue *q);
|
|
extern void blk_mq_sysfs_deinit(struct request_queue *q);
|
|
extern int __blk_mq_register_dev(struct device *dev, struct request_queue *q);
|
|
extern int blk_mq_sysfs_register(struct request_queue *q);
|
|
extern void blk_mq_sysfs_unregister(struct request_queue *q);
|
|
extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx);
|
|
|
|
extern void blk_mq_rq_timed_out(struct request *req, bool reserved);
|
|
|
|
void blk_mq_release(struct request_queue *q);
|
|
|
|
/**
|
|
* blk_mq_rq_state() - read the current MQ_RQ_* state of a request
|
|
* @rq: target request.
|
|
*/
|
|
static inline int blk_mq_rq_state(struct request *rq)
|
|
{
|
|
return READ_ONCE(rq->gstate) & MQ_RQ_STATE_MASK;
|
|
}
|
|
|
|
/**
|
|
* blk_mq_rq_update_state() - set the current MQ_RQ_* state of a request
|
|
* @rq: target request.
|
|
* @state: new state to set.
|
|
*
|
|
* Set @rq's state to @state. The caller is responsible for ensuring that
|
|
* there are no other updaters. A request can transition into IN_FLIGHT
|
|
* only from IDLE and doing so increments the generation number.
|
|
*/
|
|
static inline void blk_mq_rq_update_state(struct request *rq,
|
|
enum mq_rq_state state)
|
|
{
|
|
u64 old_val = READ_ONCE(rq->gstate);
|
|
u64 new_val = (old_val & ~MQ_RQ_STATE_MASK) | state;
|
|
|
|
if (state == MQ_RQ_IN_FLIGHT) {
|
|
WARN_ON_ONCE((old_val & MQ_RQ_STATE_MASK) != MQ_RQ_IDLE);
|
|
new_val += MQ_RQ_GEN_INC;
|
|
}
|
|
|
|
/* avoid exposing interim values */
|
|
WRITE_ONCE(rq->gstate, new_val);
|
|
}
|
|
|
|
static inline struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q,
|
|
unsigned int cpu)
|
|
{
|
|
return per_cpu_ptr(q->queue_ctx, cpu);
|
|
}
|
|
|
|
/*
|
|
* This assumes per-cpu software queueing queues. They could be per-node
|
|
* as well, for instance. For now this is hardcoded as-is. Note that we don't
|
|
* care about preemption, since we know the ctx's are persistent. This does
|
|
* mean that we can't rely on ctx always matching the currently running CPU.
|
|
*/
|
|
static inline struct blk_mq_ctx *blk_mq_get_ctx(struct request_queue *q)
|
|
{
|
|
return __blk_mq_get_ctx(q, get_cpu());
|
|
}
|
|
|
|
static inline void blk_mq_put_ctx(struct blk_mq_ctx *ctx)
|
|
{
|
|
put_cpu();
|
|
}
|
|
|
|
struct blk_mq_alloc_data {
|
|
/* input parameter */
|
|
struct request_queue *q;
|
|
blk_mq_req_flags_t flags;
|
|
unsigned int shallow_depth;
|
|
|
|
/* input & output parameter */
|
|
struct blk_mq_ctx *ctx;
|
|
struct blk_mq_hw_ctx *hctx;
|
|
};
|
|
|
|
static inline struct blk_mq_tags *blk_mq_tags_from_data(struct blk_mq_alloc_data *data)
|
|
{
|
|
if (data->flags & BLK_MQ_REQ_INTERNAL)
|
|
return data->hctx->sched_tags;
|
|
|
|
return data->hctx->tags;
|
|
}
|
|
|
|
static inline bool blk_mq_hctx_stopped(struct blk_mq_hw_ctx *hctx)
|
|
{
|
|
return test_bit(BLK_MQ_S_STOPPED, &hctx->state);
|
|
}
|
|
|
|
static inline bool blk_mq_hw_queue_mapped(struct blk_mq_hw_ctx *hctx)
|
|
{
|
|
return hctx->nr_ctx && hctx->tags;
|
|
}
|
|
|
|
void blk_mq_in_flight(struct request_queue *q, struct hd_struct *part,
|
|
unsigned int inflight[2]);
|
|
|
|
static inline void blk_mq_put_dispatch_budget(struct blk_mq_hw_ctx *hctx)
|
|
{
|
|
struct request_queue *q = hctx->queue;
|
|
|
|
if (q->mq_ops->put_budget)
|
|
q->mq_ops->put_budget(hctx);
|
|
}
|
|
|
|
static inline bool blk_mq_get_dispatch_budget(struct blk_mq_hw_ctx *hctx)
|
|
{
|
|
struct request_queue *q = hctx->queue;
|
|
|
|
if (q->mq_ops->get_budget)
|
|
return q->mq_ops->get_budget(hctx);
|
|
return true;
|
|
}
|
|
|
|
static inline void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx,
|
|
struct request *rq)
|
|
{
|
|
blk_mq_put_tag(hctx, hctx->tags, rq->mq_ctx, rq->tag);
|
|
rq->tag = -1;
|
|
|
|
if (rq->rq_flags & RQF_MQ_INFLIGHT) {
|
|
rq->rq_flags &= ~RQF_MQ_INFLIGHT;
|
|
atomic_dec(&hctx->nr_active);
|
|
}
|
|
}
|
|
|
|
static inline void blk_mq_put_driver_tag_hctx(struct blk_mq_hw_ctx *hctx,
|
|
struct request *rq)
|
|
{
|
|
if (rq->tag == -1 || rq->internal_tag == -1)
|
|
return;
|
|
|
|
__blk_mq_put_driver_tag(hctx, rq);
|
|
}
|
|
|
|
static inline void blk_mq_put_driver_tag(struct request *rq)
|
|
{
|
|
struct blk_mq_hw_ctx *hctx;
|
|
|
|
if (rq->tag == -1 || rq->internal_tag == -1)
|
|
return;
|
|
|
|
hctx = blk_mq_map_queue(rq->q, rq->mq_ctx->cpu);
|
|
__blk_mq_put_driver_tag(hctx, rq);
|
|
}
|
|
|
|
#endif
|