linux/block/blk-mq.h
Ming Lei 2a19b28f79 blk-mq: cancel blk-mq dispatch work in both blk_cleanup_queue and disk_release()
For avoiding to slow down queue destroy, we don't call
blk_mq_quiesce_queue() in blk_cleanup_queue(), instead of delaying to
cancel dispatch work in blk_release_queue().

However, this way has caused kernel oops[1], reported by Changhui. The log
shows that scsi_device can be freed before running blk_release_queue(),
which is expected too since scsi_device is released after the scsi disk
is closed and the scsi_device is removed.

Fixes the issue by canceling blk-mq dispatch work in both blk_cleanup_queue()
and disk_release():

1) when disk_release() is run, the disk has been closed, and any sync
dispatch activities have been done, so canceling dispatch work is enough to
quiesce filesystem I/O dispatch activity.

2) in blk_cleanup_queue(), we only focus on passthrough request, and
passthrough request is always explicitly allocated & freed by
its caller, so once queue is frozen, all sync dispatch activity
for passthrough request has been done, then it is enough to just cancel
dispatch work for avoiding any dispatch activity.

[1] kernel panic log
[12622.769416] BUG: kernel NULL pointer dereference, address: 0000000000000300
[12622.777186] #PF: supervisor read access in kernel mode
[12622.782918] #PF: error_code(0x0000) - not-present page
[12622.788649] PGD 0 P4D 0
[12622.791474] Oops: 0000 [#1] PREEMPT SMP PTI
[12622.796138] CPU: 10 PID: 744 Comm: kworker/10:1H Kdump: loaded Not tainted 5.15.0+ #1
[12622.804877] Hardware name: Dell Inc. PowerEdge R730/0H21J3, BIOS 1.5.4 10/002/2015
[12622.813321] Workqueue: kblockd blk_mq_run_work_fn
[12622.818572] RIP: 0010:sbitmap_get+0x75/0x190
[12622.823336] Code: 85 80 00 00 00 41 8b 57 08 85 d2 0f 84 b1 00 00 00 45 31 e4 48 63 cd 48 8d 1c 49 48 c1 e3 06 49 03 5f 10 4c 8d 6b 40 83 f0 01 <48> 8b 33 44 89 f2 4c 89 ef 0f b6 c8 e8 fa f3 ff ff 83 f8 ff 75 58
[12622.844290] RSP: 0018:ffffb00a446dbd40 EFLAGS: 00010202
[12622.850120] RAX: 0000000000000001 RBX: 0000000000000300 RCX: 0000000000000004
[12622.858082] RDX: 0000000000000006 RSI: 0000000000000082 RDI: ffffa0b7a2dfe030
[12622.866042] RBP: 0000000000000004 R08: 0000000000000001 R09: ffffa0b742721334
[12622.874003] R10: 0000000000000008 R11: 0000000000000008 R12: 0000000000000000
[12622.881964] R13: 0000000000000340 R14: 0000000000000000 R15: ffffa0b7a2dfe030
[12622.889926] FS:  0000000000000000(0000) GS:ffffa0baafb40000(0000) knlGS:0000000000000000
[12622.898956] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[12622.905367] CR2: 0000000000000300 CR3: 0000000641210001 CR4: 00000000001706e0
[12622.913328] Call Trace:
[12622.916055]  <TASK>
[12622.918394]  scsi_mq_get_budget+0x1a/0x110
[12622.922969]  __blk_mq_do_dispatch_sched+0x1d4/0x320
[12622.928404]  ? pick_next_task_fair+0x39/0x390
[12622.933268]  __blk_mq_sched_dispatch_requests+0xf4/0x140
[12622.939194]  blk_mq_sched_dispatch_requests+0x30/0x60
[12622.944829]  __blk_mq_run_hw_queue+0x30/0xa0
[12622.949593]  process_one_work+0x1e8/0x3c0
[12622.954059]  worker_thread+0x50/0x3b0
[12622.958144]  ? rescuer_thread+0x370/0x370
[12622.962616]  kthread+0x158/0x180
[12622.966218]  ? set_kthread_struct+0x40/0x40
[12622.970884]  ret_from_fork+0x22/0x30
[12622.974875]  </TASK>
[12622.977309] Modules linked in: scsi_debug rpcsec_gss_krb5 auth_rpcgss nfsv4 dns_resolver nfs lockd grace fscache netfs sunrpc dm_multipath intel_rapl_msr intel_rapl_common dell_wmi_descriptor sb_edac rfkill video x86_pkg_temp_thermal intel_powerclamp dcdbas coretemp kvm_intel kvm mgag200 irqbypass i2c_algo_bit rapl drm_kms_helper ipmi_ssif intel_cstate intel_uncore syscopyarea sysfillrect sysimgblt fb_sys_fops pcspkr cec mei_me lpc_ich mei ipmi_si ipmi_devintf ipmi_msghandler acpi_power_meter drm fuse xfs libcrc32c sr_mod cdrom sd_mod t10_pi sg ixgbe ahci libahci crct10dif_pclmul crc32_pclmul crc32c_intel libata megaraid_sas ghash_clmulni_intel tg3 wdat_wdt mdio dca wmi dm_mirror dm_region_hash dm_log dm_mod [last unloaded: scsi_debug]

Reported-by: ChanghuiZhong <czhong@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: "Martin K. Petersen" <martin.petersen@oracle.com>
Cc: Bart Van Assche <bvanassche@acm.org>
Cc: linux-scsi@vger.kernel.org
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20211116014343.610501-1-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2021-11-15 19:22:13 -07:00

382 lines
11 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_ctxs {
struct kobject kobj;
struct blk_mq_ctx __percpu *queue_ctx;
};
/**
* struct blk_mq_ctx - State for a software queue facing the submitting CPUs
*/
struct blk_mq_ctx {
struct {
spinlock_t lock;
struct list_head rq_lists[HCTX_MAX_TYPES];
} ____cacheline_aligned_in_smp;
unsigned int cpu;
unsigned short index_hw[HCTX_MAX_TYPES];
struct blk_mq_hw_ctx *hctxs[HCTX_MAX_TYPES];
struct request_queue *queue;
struct blk_mq_ctxs *ctxs;
struct kobject kobj;
} ____cacheline_aligned_in_smp;
void blk_mq_submit_bio(struct bio *bio);
int blk_mq_poll(struct request_queue *q, blk_qc_t cookie, struct io_comp_batch *iob,
unsigned int flags);
void blk_mq_exit_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 blk_mq_hw_ctx *hctx, struct list_head *,
unsigned int);
void blk_mq_add_to_requeue_list(struct request *rq, bool at_head,
bool kick_requeue_list);
void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list);
struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx,
struct blk_mq_ctx *start);
void blk_mq_put_rq_ref(struct request *rq);
/*
* 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_map_and_rqs(struct blk_mq_tag_set *set,
unsigned int hctx_idx, unsigned int depth);
void blk_mq_free_map_and_rqs(struct blk_mq_tag_set *set,
struct blk_mq_tags *tags,
unsigned int hctx_idx);
/*
* 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 at_head,
bool run_queue);
void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
struct list_head *list);
/* Used by blk_insert_cloned_request() to issue request directly */
blk_status_t blk_mq_request_issue_directly(struct request *rq, bool last);
void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
struct list_head *list);
/*
* CPU -> queue mappings
*/
extern int blk_mq_hw_queue_to_node(struct blk_mq_queue_map *qmap, unsigned int);
/*
* blk_mq_map_queue_type() - map (hctx_type,cpu) to hardware queue
* @q: request queue
* @type: the hctx type index
* @cpu: CPU
*/
static inline struct blk_mq_hw_ctx *blk_mq_map_queue_type(struct request_queue *q,
enum hctx_type type,
unsigned int cpu)
{
return q->queue_hw_ctx[q->tag_set->map[type].mq_map[cpu]];
}
static inline enum hctx_type blk_mq_get_hctx_type(unsigned int flags)
{
enum hctx_type type = HCTX_TYPE_DEFAULT;
/*
* The caller ensure that if REQ_POLLED, poll must be enabled.
*/
if (flags & REQ_POLLED)
type = HCTX_TYPE_POLL;
else if ((flags & REQ_OP_MASK) == REQ_OP_READ)
type = HCTX_TYPE_READ;
return type;
}
/*
* blk_mq_map_queue() - map (cmd_flags,type) to hardware queue
* @q: request queue
* @flags: request command flags
* @ctx: software queue cpu ctx
*/
static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q,
unsigned int flags,
struct blk_mq_ctx *ctx)
{
return ctx->hctxs[blk_mq_get_hctx_type(flags)];
}
/*
* 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);
void blk_mq_free_plug_rqs(struct blk_plug *plug);
void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule);
void blk_mq_cancel_work_sync(struct request_queue *q);
void blk_mq_release(struct request_queue *q);
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, raw_smp_processor_id());
}
struct blk_mq_alloc_data {
/* input parameter */
struct request_queue *q;
blk_mq_req_flags_t flags;
unsigned int shallow_depth;
unsigned int cmd_flags;
req_flags_t rq_flags;
/* allocate multiple requests/tags in one go */
unsigned int nr_tags;
struct request **cached_rq;
/* input & output parameter */
struct blk_mq_ctx *ctx;
struct blk_mq_hw_ctx *hctx;
};
static inline bool blk_mq_is_shared_tags(unsigned int flags)
{
return flags & BLK_MQ_F_TAG_HCTX_SHARED;
}
static inline struct blk_mq_tags *blk_mq_tags_from_data(struct blk_mq_alloc_data *data)
{
if (!(data->rq_flags & RQF_ELV))
return data->hctx->tags;
return data->hctx->sched_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;
}
unsigned int blk_mq_in_flight(struct request_queue *q,
struct block_device *part);
void blk_mq_in_flight_rw(struct request_queue *q, struct block_device *part,
unsigned int inflight[2]);
static inline void blk_mq_put_dispatch_budget(struct request_queue *q,
int budget_token)
{
if (q->mq_ops->put_budget)
q->mq_ops->put_budget(q, budget_token);
}
static inline int blk_mq_get_dispatch_budget(struct request_queue *q)
{
if (q->mq_ops->get_budget)
return q->mq_ops->get_budget(q);
return 0;
}
static inline void blk_mq_set_rq_budget_token(struct request *rq, int token)
{
if (token < 0)
return;
if (rq->q->mq_ops->set_rq_budget_token)
rq->q->mq_ops->set_rq_budget_token(rq, token);
}
static inline int blk_mq_get_rq_budget_token(struct request *rq)
{
if (rq->q->mq_ops->get_rq_budget_token)
return rq->q->mq_ops->get_rq_budget_token(rq);
return -1;
}
static inline void __blk_mq_inc_active_requests(struct blk_mq_hw_ctx *hctx)
{
if (blk_mq_is_shared_tags(hctx->flags))
atomic_inc(&hctx->queue->nr_active_requests_shared_tags);
else
atomic_inc(&hctx->nr_active);
}
static inline void __blk_mq_sub_active_requests(struct blk_mq_hw_ctx *hctx,
int val)
{
if (blk_mq_is_shared_tags(hctx->flags))
atomic_sub(val, &hctx->queue->nr_active_requests_shared_tags);
else
atomic_sub(val, &hctx->nr_active);
}
static inline void __blk_mq_dec_active_requests(struct blk_mq_hw_ctx *hctx)
{
__blk_mq_sub_active_requests(hctx, 1);
}
static inline int __blk_mq_active_requests(struct blk_mq_hw_ctx *hctx)
{
if (blk_mq_is_shared_tags(hctx->flags))
return atomic_read(&hctx->queue->nr_active_requests_shared_tags);
return atomic_read(&hctx->nr_active);
}
static inline void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx,
struct request *rq)
{
blk_mq_put_tag(hctx->tags, rq->mq_ctx, rq->tag);
rq->tag = BLK_MQ_NO_TAG;
if (rq->rq_flags & RQF_MQ_INFLIGHT) {
rq->rq_flags &= ~RQF_MQ_INFLIGHT;
__blk_mq_dec_active_requests(hctx);
}
}
static inline void blk_mq_put_driver_tag(struct request *rq)
{
if (rq->tag == BLK_MQ_NO_TAG || rq->internal_tag == BLK_MQ_NO_TAG)
return;
__blk_mq_put_driver_tag(rq->mq_hctx, rq);
}
bool __blk_mq_get_driver_tag(struct blk_mq_hw_ctx *hctx, struct request *rq);
static inline bool blk_mq_get_driver_tag(struct request *rq)
{
struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
if (rq->tag != BLK_MQ_NO_TAG &&
!(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) {
hctx->tags->rqs[rq->tag] = rq;
return true;
}
return __blk_mq_get_driver_tag(hctx, rq);
}
static inline void blk_mq_clear_mq_map(struct blk_mq_queue_map *qmap)
{
int cpu;
for_each_possible_cpu(cpu)
qmap->mq_map[cpu] = 0;
}
/*
* blk_mq_plug() - Get caller context plug
* @q: request queue
* @bio : the bio being submitted by the caller context
*
* Plugging, by design, may delay the insertion of BIOs into the elevator in
* order to increase BIO merging opportunities. This however can cause BIO
* insertion order to change from the order in which submit_bio() is being
* executed in the case of multiple contexts concurrently issuing BIOs to a
* device, even if these context are synchronized to tightly control BIO issuing
* order. While this is not a problem with regular block devices, this ordering
* change can cause write BIO failures with zoned block devices as these
* require sequential write patterns to zones. Prevent this from happening by
* ignoring the plug state of a BIO issuing context if the target request queue
* is for a zoned block device and the BIO to plug is a write operation.
*
* Return current->plug if the bio can be plugged and NULL otherwise
*/
static inline struct blk_plug *blk_mq_plug(struct request_queue *q,
struct bio *bio)
{
/*
* For regular block devices or read operations, use the context plug
* which may be NULL if blk_start_plug() was not executed.
*/
if (!blk_queue_is_zoned(q) || !op_is_write(bio_op(bio)))
return current->plug;
/* Zoned block device write operation case: do not plug the BIO */
return NULL;
}
/* Free all requests on the list */
static inline void blk_mq_free_requests(struct list_head *list)
{
while (!list_empty(list)) {
struct request *rq = list_entry_rq(list->next);
list_del_init(&rq->queuelist);
blk_mq_free_request(rq);
}
}
/*
* For shared tag users, we track the number of currently active users
* and attempt to provide a fair share of the tag depth for each of them.
*/
static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx,
struct sbitmap_queue *bt)
{
unsigned int depth, users;
if (!hctx || !(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED))
return true;
/*
* Don't try dividing an ant
*/
if (bt->sb.depth == 1)
return true;
if (blk_mq_is_shared_tags(hctx->flags)) {
struct request_queue *q = hctx->queue;
if (!test_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags))
return true;
} else {
if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state))
return true;
}
users = atomic_read(&hctx->tags->active_queues);
if (!users)
return true;
/*
* Allow at least some tags
*/
depth = max((bt->sb.depth + users - 1) / users, 4U);
return __blk_mq_active_requests(hctx) < depth;
}
#endif