cregit-Linux how code gets into the kernel

Release 4.9 block/blk-mq.c

Directory: block
/*
 * Block multiqueue core code
 *
 * Copyright (C) 2013-2014 Jens Axboe
 * Copyright (C) 2013-2014 Christoph Hellwig
 */
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/backing-dev.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/kmemleak.h>
#include <linux/mm.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/workqueue.h>
#include <linux/smp.h>
#include <linux/llist.h>
#include <linux/list_sort.h>
#include <linux/cpu.h>
#include <linux/cache.h>
#include <linux/sched/sysctl.h>
#include <linux/delay.h>
#include <linux/crash_dump.h>
#include <linux/prefetch.h>

#include <trace/events/block.h>

#include <linux/blk-mq.h>
#include "blk.h"
#include "blk-mq.h"
#include "blk-mq-tag.h"

static DEFINE_MUTEX(all_q_mutex);
static LIST_HEAD(all_q_list);

/*
 * Check if any of the ctx's have pending work in this hardware queue
 */

static bool blk_mq_hctx_has_pending(struct blk_mq_hw_ctx *hctx) { return sbitmap_any_bit_set(&hctx->ctx_map); }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe1785.00%266.67%
omar sandovalomar sandoval315.00%133.33%
Total20100.00%3100.00%

/* * Mark this ctx as having pending work in this hardware queue */
static void blk_mq_hctx_mark_pending(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx) { if (!sbitmap_test_bit(&hctx->ctx_map, ctx->index_hw)) sbitmap_set_bit(&hctx->ctx_map, ctx->index_hw); }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe3376.74%266.67%
omar sandovalomar sandoval1023.26%133.33%
Total43100.00%3100.00%


static void blk_mq_hctx_clear_pending(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx) { sbitmap_clear_bit(&hctx->ctx_map, ctx->index_hw); }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe2382.14%266.67%
omar sandovalomar sandoval517.86%133.33%
Total28100.00%3100.00%


void blk_mq_freeze_queue_start(struct request_queue *q) { int freeze_depth; freeze_depth = atomic_inc_return(&q->mq_freeze_depth); if (freeze_depth == 1) { percpu_ref_kill(&q->q_usage_counter); blk_mq_run_hw_queues(q, false); } }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe1736.96%111.11%
tejun heotejun heo1634.78%555.56%
christoph hellwigchristoph hellwig919.57%111.11%
mike snitzermike snitzer36.52%111.11%
dan williamsdan williams12.17%111.11%
Total46100.00%9100.00%

EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_start);
static void blk_mq_freeze_queue_wait(struct request_queue *q) { wait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->q_usage_counter)); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo1661.54%240.00%
lei minglei ming623.08%120.00%
jens axboejens axboe311.54%120.00%
dan williamsdan williams13.85%120.00%
Total26100.00%5100.00%

/* * Guarantee no request is in use, so we can change any data structure of * the queue afterward. */
void blk_freeze_queue(struct request_queue *q) { /* * In the !blk_mq case we are only calling this to kill the * q_usage_counter, otherwise this increases the freeze depth * and waits for it to return to zero. For this reason there is * no blk_unfreeze_queue(), and blk_freeze_queue() is not * exported to drivers as the only user for unfreeze is blk_mq. */ blk_mq_freeze_queue_start(q); blk_mq_freeze_queue_wait(q); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo1990.48%150.00%
dan williamsdan williams29.52%150.00%
Total21100.00%2100.00%


void blk_mq_freeze_queue(struct request_queue *q) { /* * ...just an alias to keep freeze and unfreeze actions balanced * in the blk_mq_* namespace */ blk_freeze_queue(q); }

Contributors

PersonTokensPropCommitsCommitProp
dan williamsdan williams16100.00%1100.00%
Total16100.00%1100.00%

EXPORT_SYMBOL_GPL(blk_mq_freeze_queue);
void blk_mq_unfreeze_queue(struct request_queue *q) { int freeze_depth; freeze_depth = atomic_dec_return(&q->mq_freeze_depth); WARN_ON_ONCE(freeze_depth < 0); if (!freeze_depth) { percpu_ref_reinit(&q->q_usage_counter); wake_up_all(&q->mq_freeze_wq); } }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe3158.49%120.00%
tejun heotejun heo1120.75%240.00%
christoph hellwigchristoph hellwig1018.87%120.00%
dan williamsdan williams11.89%120.00%
Total53100.00%5100.00%

EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue);
void blk_mq_wake_waiters(struct request_queue *q) { struct blk_mq_hw_ctx *hctx; unsigned int i; queue_for_each_hw_ctx(q, hctx, i) if (blk_mq_hw_queue_mapped(hctx)) blk_mq_tag_wakeup_all(hctx->tags, true); /* * If we are called because the queue has now been marked as * dying, we need to ensure that processes currently waiting on * the queue are notified as well. */ wake_up_all(&q->mq_freeze_wq); }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe4382.69%150.00%
keith buschkeith busch917.31%150.00%
Total52100.00%2100.00%


bool blk_mq_can_queue(struct blk_mq_hw_ctx *hctx) { return blk_mq_has_free_tags(hctx->tags); }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe18100.00%1100.00%
Total18100.00%1100.00%

EXPORT_SYMBOL(blk_mq_can_queue);
static void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx, struct request *rq, int op, unsigned int op_flags) { if (blk_queue_io_stat(q)) op_flags |= REQ_IO_STAT; INIT_LIST_HEAD(&rq->queuelist); /* csd/requeue_work/fifo_time is initialized before use */ rq->q = q; rq->mq_ctx = ctx; req_set_op_attrs(rq, op, op_flags); /* do not touch atomic flags, it needs atomic ops against the timer */ rq->cpu = -1; INIT_HLIST_NODE(&rq->hash); RB_CLEAR_NODE(&rq->rb_node); rq->rq_disk = NULL; rq->part = NULL; rq->start_time = jiffies; #ifdef CONFIG_BLK_CGROUP rq->rl = NULL; set_start_time_ns(rq); rq->io_start_time_ns = 0; #endif rq->nr_phys_segments = 0; #if defined(CONFIG_BLK_DEV_INTEGRITY) rq->nr_integrity_segments = 0; #endif rq->special = NULL; /* tag was already set */ rq->errors = 0; rq->cmd = rq->__cmd; rq->extra_len = 0; rq->sense_len = 0; rq->resid_len = 0; rq->sense = NULL; INIT_LIST_HEAD(&rq->timeout_list); rq->timeout = 0; rq->end_io = NULL; rq->end_io_data = NULL; rq->next_rq = NULL; ctx->rq_dispatched[rw_is_sync(op, op_flags)]++; }

Contributors

PersonTokensPropCommitsCommitProp
christoph hellwigchristoph hellwig15162.14%111.11%
jens axboejens axboe6426.34%444.44%
michael christiemichael christie156.17%222.22%
tony battersbytony battersby83.29%111.11%
lei minglei ming52.06%111.11%
Total243100.00%9100.00%


static struct request * __blk_mq_alloc_request(struct blk_mq_alloc_data *data, int op, int op_flags) { struct request *rq; unsigned int tag; tag = blk_mq_get_tag(data); if (tag != BLK_MQ_TAG_FAIL) { rq = data->hctx->tags->rqs[tag]; if (blk_mq_tag_busy(data->hctx)) { rq->cmd_flags = REQ_MQ_INFLIGHT; atomic_inc(&data->hctx->nr_active); } rq->tag = tag; blk_mq_rq_ctx_init(data->q, data->ctx, rq, op, op_flags); return rq; } return NULL; }

Contributors

PersonTokensPropCommitsCommitProp
christoph hellwigchristoph hellwig9282.14%133.33%
lei minglei ming1311.61%133.33%
michael christiemichael christie76.25%133.33%
Total112100.00%3100.00%


struct request *blk_mq_alloc_request(struct request_queue *q, int rw, unsigned int flags) { struct blk_mq_ctx *ctx; struct blk_mq_hw_ctx *hctx; struct request *rq; struct blk_mq_alloc_data alloc_data; int ret; ret = blk_queue_enter(q, flags & BLK_MQ_REQ_NOWAIT); if (ret) return ERR_PTR(ret); ctx = blk_mq_get_ctx(q); hctx = blk_mq_map_queue(q, ctx->cpu); blk_mq_set_alloc_data(&alloc_data, q, flags, ctx, hctx); rq = __blk_mq_alloc_request(&alloc_data, rw, 0); blk_mq_put_ctx(ctx); if (!rq) { blk_queue_exit(q); return ERR_PTR(-EWOULDBLOCK); } rq->__data_len = 0; rq->__sector = (sector_t) -1; rq->bio = rq->biotail = NULL; return rq; }

Contributors

PersonTokensPropCommitsCommitProp
christoph hellwigchristoph hellwig5735.85%642.86%
jens axboejens axboe4427.67%214.29%
joe lawrencejoe lawrence2515.72%17.14%
lei minglei ming2213.84%17.14%
keith buschkeith busch74.40%214.29%
michael christiemichael christie21.26%17.14%
dan williamsdan williams21.26%17.14%
Total159100.00%14100.00%

EXPORT_SYMBOL(blk_mq_alloc_request);
struct request *blk_mq_alloc_request_hctx(struct request_queue *q, int rw, unsigned int flags, unsigned int hctx_idx) { struct blk_mq_hw_ctx *hctx; struct blk_mq_ctx *ctx; struct request *rq; struct blk_mq_alloc_data alloc_data; int ret; /* * If the tag allocator sleeps we could get an allocation for a * different hardware context. No need to complicate the low level * allocator for this for the rare use case of a command tied to * a specific queue. */ if (WARN_ON_ONCE(!(flags & BLK_MQ_REQ_NOWAIT))) return ERR_PTR(-EINVAL); if (hctx_idx >= q->nr_hw_queues) return ERR_PTR(-EIO); ret = blk_queue_enter(q, true); if (ret) return ERR_PTR(ret); /* * Check if the hardware context is actually mapped to anything. * If not tell the caller that it should skip this queue. */ hctx = q->queue_hw_ctx[hctx_idx]; if (!blk_mq_hw_queue_mapped(hctx)) { ret = -EXDEV; goto out_queue_exit; } ctx = __blk_mq_get_ctx(q, cpumask_first(hctx->cpumask)); blk_mq_set_alloc_data(&alloc_data, q, flags, ctx, hctx); rq = __blk_mq_alloc_request(&alloc_data, rw, 0); if (!rq) { ret = -EWOULDBLOCK; goto out_queue_exit; } return rq; out_queue_exit: blk_queue_exit(q); return ERR_PTR(ret); }

Contributors

PersonTokensPropCommitsCommitProp
ming linming lin16482.83%150.00%
christoph hellwigchristoph hellwig3417.17%150.00%
Total198100.00%2100.00%

EXPORT_SYMBOL_GPL(blk_mq_alloc_request_hctx);
static void __blk_mq_free_request(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx, struct request *rq) { const int tag = rq->tag; struct request_queue *q = rq->q; if (rq->cmd_flags & REQ_MQ_INFLIGHT) atomic_dec(&hctx->nr_active); rq->cmd_flags = 0; clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags); blk_mq_put_tag(hctx, ctx, tag); blk_queue_exit(q); }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe6577.38%342.86%
christoph hellwigchristoph hellwig1011.90%114.29%
david hildenbranddavid hildenbrand67.14%114.29%
omar sandovalomar sandoval22.38%114.29%
dan williamsdan williams11.19%114.29%
Total84100.00%7100.00%


void blk_mq_free_hctx_request(struct blk_mq_hw_ctx *hctx, struct request *rq) { struct blk_mq_ctx *ctx = rq->mq_ctx; ctx->rq_completed[rq_is_sync(rq)]++; __blk_mq_free_request(hctx, ctx, rq); }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe44100.00%2100.00%
Total44100.00%2100.00%

EXPORT_SYMBOL_GPL(blk_mq_free_hctx_request);
void blk_mq_free_request(struct request *rq) { blk_mq_free_hctx_request(blk_mq_map_queue(rq->q, rq->mq_ctx->cpu), rq); }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe2485.71%266.67%
christoph hellwigchristoph hellwig414.29%133.33%
Total28100.00%3100.00%

EXPORT_SYMBOL_GPL(blk_mq_free_request);
inline void __blk_mq_end_request(struct request *rq, int error) { blk_account_io_done(rq); if (rq->end_io) { rq->end_io(rq, error); } else { if (unlikely(blk_bidi_rq(rq))) blk_mq_free_request(rq->next_rq); blk_mq_free_request(rq); } }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe3252.46%120.00%
christoph hellwigchristoph hellwig2439.34%360.00%
lei minglei ming58.20%120.00%
Total61100.00%5100.00%

EXPORT_SYMBOL(__blk_mq_end_request);
void blk_mq_end_request(struct request *rq, int error) { if (blk_update_request(rq, error, blk_rq_bytes(rq))) BUG(); __blk_mq_end_request(rq, error); }

Contributors

PersonTokensPropCommitsCommitProp
christoph hellwigchristoph hellwig37100.00%2100.00%
Total37100.00%2100.00%

EXPORT_SYMBOL(blk_mq_end_request);
static void __blk_mq_complete_request_remote(void *data) { struct request *rq = data; rq->q->softirq_done_fn(rq); }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe1869.23%133.33%
christoph hellwigchristoph hellwig830.77%266.67%
Total26100.00%3100.00%


static void blk_mq_ipi_complete_request(struct request *rq) { struct blk_mq_ctx *ctx = rq->mq_ctx; bool shared = false; int cpu; if (!test_bit(QUEUE_FLAG_SAME_COMP, &rq->q->queue_flags)) { rq->q->softirq_done_fn(rq); return; } cpu = get_cpu(); if (!test_bit(QUEUE_FLAG_SAME_FORCE, &rq->q->queue_flags)) shared = cpus_share_cache(cpu, ctx->cpu); if (cpu != ctx->cpu && !shared && cpu_online(ctx->cpu)) { rq->csd.func = __blk_mq_complete_request_remote; rq->csd.info = rq; rq->csd.flags = 0; smp_call_function_single_async(ctx->cpu, &rq->csd); } else { rq->q->softirq_done_fn(rq); } put_cpu(); }

Contributors

PersonTokensPropCommitsCommitProp
christoph hellwigchristoph hellwig9560.51%350.00%
jens axboejens axboe6138.85%233.33%
frederic weisbeckerfrederic weisbecker10.64%116.67%
Total157100.00%6100.00%


static void __blk_mq_complete_request(struct request *rq) { struct request_queue *q = rq->q; if (!q->softirq_done_fn) blk_mq_end_request(rq, rq->errors); else blk_mq_ipi_complete_request(rq); }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe4197.62%266.67%
christoph hellwigchristoph hellwig12.38%133.33%
Total42100.00%3100.00%

/** * blk_mq_complete_request - end I/O on a request * @rq: the request being processed * * Description: * Ends all I/O on a request. It does not handle partial completions. * The actual completion happens out-of-order, through a IPI handler. **/
void blk_mq_complete_request(struct request *rq, int error) { struct request_queue *q = rq->q; if (unlikely(blk_should_fake_timeout(q))) return; if (!blk_mark_rq_complete(rq)) { rq->errors = error; __blk_mq_complete_request(rq); } }

Contributors

PersonTokensPropCommitsCommitProp
christoph hellwigchristoph hellwig4583.33%266.67%
jens axboejens axboe916.67%133.33%
Total54100.00%3100.00%

EXPORT_SYMBOL(blk_mq_complete_request);
int blk_mq_request_started(struct request *rq) { return test_bit(REQ_ATOM_STARTED, &rq->atomic_flags); }

Contributors

PersonTokensPropCommitsCommitProp
keith buschkeith busch21100.00%1100.00%
Total21100.00%1100.00%

EXPORT_SYMBOL_GPL(blk_mq_request_started);
void blk_mq_start_request(struct request *rq) { struct request_queue *q = rq->q; trace_block_rq_issue(q, rq); rq->resid_len = blk_rq_bytes(rq); if (unlikely(blk_bidi_rq(rq))) rq->next_rq->resid_len = blk_rq_bytes(rq->next_rq); blk_add_timer(rq); /* * Ensure that ->deadline is visible before set the started * flag and clear the completed flag. */ smp_mb__before_atomic(); /* * Mark us as started and clear complete. Complete might have been * set if requeue raced with timeout, which then marked it as * complete. So be sure to clear complete again when we start * the request, otherwise we'll ignore the completion event. */ if (!test_bit(REQ_ATOM_STARTED, &rq->atomic_flags)) set_bit(REQ_ATOM_STARTED, &rq->atomic_flags); if (test_bit(REQ_ATOM_COMPLETE, &rq->atomic_flags)) clear_bit(REQ_ATOM_COMPLETE, &rq->atomic_flags); if (q->dma_drain_size && blk_rq_bytes(rq)) { /* * Make sure space for the drain appears. We know we can do * this because max_hw_segments has been adjusted to be one * fewer than the device can handle. */ rq->nr_phys_segments++; } }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe7859.09%555.56%
christoph hellwigchristoph hellwig5138.64%333.33%
lei minglei ming32.27%111.11%
Total132100.00%9100.00%

EXPORT_SYMBOL(blk_mq_start_request);
static void __blk_mq_requeue_request(struct request *rq) { struct request_queue *q = rq->q; trace_block_rq_requeue(q, rq); if (test_and_clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags)) { if (q->dma_drain_size && blk_rq_bytes(rq)) rq->nr_phys_segments--; } }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe3459.65%125.00%
christoph hellwigchristoph hellwig2340.35%375.00%
Total57100.00%4100.00%


void blk_mq_requeue_request(struct request *rq) { __blk_mq_requeue_request(rq); BUG_ON(blk_queued_rq(rq)); blk_mq_add_to_requeue_list(rq, true); }

Contributors

PersonTokensPropCommitsCommitProp
christoph hellwigchristoph hellwig30100.00%2100.00%
Total30100.00%2100.00%

EXPORT_SYMBOL(blk_mq_requeue_request);
static void blk_mq_requeue_work(struct work_struct *work) { struct request_queue *q = container_of(work, struct request_queue, requeue_work.work); LIST_HEAD(rq_list); struct request *rq, *next; unsigned long flags; spin_lock_irqsave(&q->requeue_lock, flags); list_splice_init(&q->requeue_list, &rq_list); spin_unlock_irqrestore(&q->requeue_lock, flags); list_for_each_entry_safe(rq, next, &rq_list, queuelist) { if (!(rq->cmd_flags & REQ_SOFTBARRIER)) continue; rq->cmd_flags &= ~REQ_SOFTBARRIER; list_del_init(&rq->queuelist); blk_mq_insert_request(rq, true, false, false); } while (!list_empty(&rq_list)) { rq = list_entry(rq_list.next, struct request, queuelist); list_del_init(&rq->queuelist); blk_mq_insert_request(rq, false, false, false); } /* * Use the start variant of queue running here, so that running * the requeue work will kick stopped queues. */ blk_mq_start_hw_queues(q); }

Contributors

PersonTokensPropCommitsCommitProp
christoph hellwigchristoph hellwig17297.73%250.00%
mike snitzermike snitzer21.14%125.00%
jens axboejens axboe21.14%125.00%
Total176100.00%4100.00%


void blk_mq_add_to_requeue_list(struct request *rq, bool at_head) { struct request_queue *q = rq->q; unsigned long flags; /* * We abuse this flag that is otherwise used by the I/O scheduler to * request head insertation from the workqueue. */ BUG_ON(rq->cmd_flags & REQ_SOFTBARRIER); spin_lock_irqsave(&q->requeue_lock, flags); if (at_head) { rq->cmd_flags |= REQ_SOFTBARRIER; list_add(&rq->queuelist, &q->requeue_list); } else { list_add_tail(&rq->queuelist, &q->requeue_list); } spin_unlock_irqrestore(&q->requeue_lock, flags); }

Contributors

PersonTokensPropCommitsCommitProp
christoph hellwigchristoph hellwig97100.00%2100.00%
Total97100.00%2100.00%

EXPORT_SYMBOL(blk_mq_add_to_requeue_list);
void blk_mq_cancel_requeue_work(struct request_queue *q) { cancel_delayed_work_sync(&q->requeue_work); }

Contributors

PersonTokensPropCommitsCommitProp
keith buschkeith busch1794.44%150.00%
mike snitzermike snitzer15.56%150.00%
Total18100.00%2100.00%

EXPORT_SYMBOL_GPL(blk_mq_cancel_requeue_work);
void blk_mq_kick_requeue_list(struct request_queue *q) { kblockd_schedule_delayed_work(&q->requeue_work, 0); }

Contributors

PersonTokensPropCommitsCommitProp
christoph hellwigchristoph hellwig1785.00%150.00%
mike snitzermike snitzer315.00%150.00%
Total20100.00%2100.00%

EXPORT_SYMBOL(blk_mq_kick_requeue_list);
void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs) { kblockd_schedule_delayed_work(&q->requeue_work, msecs_to_jiffies(msecs)); }

Contributors

PersonTokensPropCommitsCommitProp
mike snitzermike snitzer27100.00%1100.00%
Total27100.00%1100.00%

EXPORT_SYMBOL(blk_mq_delay_kick_requeue_list);
void blk_mq_abort_requeue_list(struct request_queue *q) { unsigned long flags; LIST_HEAD(rq_list); spin_lock_irqsave(&q->requeue_lock, flags); list_splice_init(&q->requeue_list, &rq_list); spin_unlock_irqrestore(&q->requeue_lock, flags); while (!list_empty(&rq_list)) { struct request *rq; rq = list_first_entry(&rq_list, struct request, queuelist); list_del_init(&rq->queuelist); rq->errors = -EIO; blk_mq_end_request(rq, rq->errors); } }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe103100.00%1100.00%
Total103100.00%1100.00%

EXPORT_SYMBOL(blk_mq_abort_requeue_list);
struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag) { if (tag < tags->nr_tags) { prefetch(tags->rqs[tag]); return tags->rqs[tag]; } return NULL; }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe2757.45%240.00%
hannes reineckehannes reinecke1123.40%120.00%
christoph hellwigchristoph hellwig817.02%120.00%
ming leiming lei12.13%120.00%
Total47100.00%5100.00%

EXPORT_SYMBOL(blk_mq_tag_to_rq); struct blk_mq_timeout_data { unsigned long next; unsigned int next_set; };
void blk_mq_rq_timed_out(struct request *req, bool reserved) { struct blk_mq_ops *ops = req->q->mq_ops; enum blk_eh_timer_return ret = BLK_EH_RESET_TIMER; /* * We know that complete is set at this point. If STARTED isn't set * anymore, then the request isn't active and the "timeout" should * just be ignored. This can happen due to the bitflag ordering. * Timeout first checks if STARTED is set, and if it is, assumes * the request is active. But if we race with completion, then * we both flags will get cleared. So check here again, and ignore * a timeout event with a request that isn't active. */ if (!test_bit(REQ_ATOM_STARTED, &req->atomic_flags)) return; if (ops->timeout) ret = ops->timeout(req, reserved); switch (ret) { case BLK_EH_HANDLED: __blk_mq_complete_request(req); break; case BLK_EH_RESET_TIMER: blk_add_timer(req); blk_clear_rq_complete(req); break; case BLK_EH_NOT_HANDLED: break; default: printk(KERN_ERR "block: bad eh return: %d\n", ret); break; } }

Contributors

PersonTokensPropCommitsCommitProp
christoph hellwigchristoph hellwig6965.71%466.67%
jens axboejens axboe3634.29%233.33%
Total105100.00%6100.00%


static void blk_mq_check_expired(struct blk_mq_hw_ctx *hctx, struct request *rq, void *priv, bool reserved) { struct blk_mq_timeout_data *data = priv; if (!test_bit(REQ_ATOM_STARTED, &rq->atomic_flags)) { /* * If a request wasn't started before the queue was * marked dying, kill it here or it'll go unnoticed. */ if (unlikely(blk_queue_dying(rq->q))) { rq->errors = -EIO; blk_mq_end_request(rq, rq->errors); } return; } if (time_after_eq(jiffies, rq->deadline)) { if (!blk_mark_rq_complete(rq)) blk_mq_rq_timed_out(rq, reserved); } else if (!data->next_set || time_after(data->next, rq->deadline)) { data->next = rq->deadline; data->next_set = 1; } }

Contributors

PersonTokensPropCommitsCommitProp
christoph hellwigchristoph hellwig6747.86%450.00%
jens axboejens axboe4230.00%225.00%
keith buschkeith busch3122.14%225.00%
Total140100.00%8100.00%


static void blk_mq_timeout_work(struct work_struct *work) { struct request_queue *q = container_of(work, struct request_queue, timeout_work); struct blk_mq_timeout_data data = { .next = 0, .next_set = 0, }; int i; /* A deadlock might occur if a request is stuck requiring a * timeout at the same time a queue freeze is waiting * completion, since the timeout code would not be able to * acquire the queue reference here. * * That's why we don't use blk_queue_enter here; instead, we use * percpu_ref_tryget directly, because we need to be able to * obtain a reference even in the short window between the queue * starting to freeze, by dropping the first reference in * blk_mq_freeze_queue_start, and the moment the last request is * consumed, marked by the instant q_usage_counter reaches * zero. */ if (!percpu_ref_tryget(&q->q_usage_counter)) return; blk_mq_queue_tag_busy_iter(q, blk_mq_check_expired, &data); if (data.next_set) { data.next = blk_rq_timeout(round_jiffies_up(data.next)); mod_timer(&q->timeout, data.next); } else { struct blk_mq_hw_ctx *hctx; queue_for_each_hw_ctx(q, hctx, i) { /* the hctx may be unmapped, so check it here */ if (blk_mq_hw_queue_mapped(hctx)) blk_mq_tag_idle(hctx); } } blk_queue_exit(q); }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe6647.83%228.57%
christoph hellwigchristoph hellwig5640.58%342.86%
ming leiming lei107.25%114.29%
gabriel krisman bertazigabriel krisman bertazi64.35%114.29%
Total138100.00%7100.00%

/* * Reverse check our software queue for entries that we could potentially * merge with. Currently includes a hand-wavy stop count of 8, to not spend * too much time checking for merges. */
static bool blk_mq_attempt_merge(struct request_queue *q, struct blk_mq_ctx *ctx, struct bio *bio) { struct request *rq; int checked = 8; list_for_each_entry_reverse(rq, &ctx->rq_list, queuelist) { int el_ret; if (!checked--) break; if (!blk_rq_merge_ok(rq, bio)) continue; el_ret = blk_try_merge(rq, bio); if (el_ret == ELEVATOR_BACK_MERGE) { if (bio_attempt_back_merge(q, rq, bio)) { ctx->rq_merged++; return true; } break; } else if (el_ret == ELEVATOR_FRONT_MERGE) { if (bio_attempt_front_merge(q, rq, bio)) { ctx->rq_merged++; return true; } break; } } return false; }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe135100.00%1100.00%
Total135100.00%1100.00%

struct flush_busy_ctx_data { struct blk_mq_hw_ctx *hctx; struct list_head *list; };
static bool flush_busy_ctx(struct sbitmap *sb, unsigned int bitnr, void *data) { struct flush_busy_ctx_data *flush_data = data; struct blk_mq_hw_ctx *hctx = flush_data->hctx; struct blk_mq_ctx *ctx = hctx->ctxs[bitnr]; sbitmap_clear_bit(sb, bitnr); spin_lock(&ctx->lock); list_splice_tail_init(&ctx->rq_list, flush_data->list); spin_unlock(&ctx->lock); return true; }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe4755.29%150.00%
omar sandovalomar sandoval3844.71%150.00%
Total85100.00%2100.00%

/* * Process software queues that have been marked busy, splicing them * to the for-dispatch */
static void flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list) { struct flush_busy_ctx_data data = { .hctx = hctx, .list = list, }; sbitmap_for_each_set(&hctx->ctx_map, flush_busy_ctx, &data); }

Contributors

PersonTokensPropCommitsCommitProp
omar sandovalomar sandoval4395.56%150.00%
jens axboejens axboe24.44%150.00%
Total45100.00%2100.00%


static inline unsigned int queued_to_index(unsigned int queued) { if (!queued) return 0; return min(BLK_MQ_MAX_DISPATCH_ORDER - 1, ilog2(queued) + 1); }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe35100.00%2100.00%
Total35100.00%2100.00%

/* * Run this hardware queue, pulling any software queues mapped to it in. * Note that this function currently has various problems around ordering * of IO. In particular, we'd like FIFO behaviour on handling existing * items on the hctx->dispatch list. Ignore that for now. */
static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx) { struct request_queue *q = hctx->queue; struct request *rq; LIST_HEAD(rq_list); LIST_HEAD(driver_list); struct list_head *dptr; int queued; if (unlikely(test_bit(BLK_MQ_S_STOPPED, &hctx->state))) return; WARN_ON(!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask) && cpu_online(hctx->next_cpu)); hctx->run++; /* * Touch any software queue that has pending entries. */ flush_busy_ctxs(hctx, &rq_list); /* * If we have previous entries on our dispatch list, grab them * and stuff them at the front for more fair dispatch. */ if (!list_empty_careful(&hctx->dispatch)) { spin_lock(&hctx->lock); if (!list_empty(&hctx->dispatch)) list_splice_init(&hctx->dispatch, &rq_list); spin_unlock(&hctx->lock); } /* * Start off with dptr being NULL, so we start the first request * immediately, even if we have more pending. */ dptr = NULL; /* * Now process all the entries, sending them to the driver. */ queued = 0; while (!list_empty(&rq_list)) { struct blk_mq_queue_data bd; int ret; rq = list_first_entry(&rq_list, struct request, queuelist); list_del_init(&rq->queuelist); bd.rq = rq; bd.list = dptr; bd.last = list_empty(&rq_list); ret = q->mq_ops->queue_rq(hctx, &bd); switch (ret) { case BLK_MQ_RQ_QUEUE_OK: queued++; break; case BLK_MQ_RQ_QUEUE_BUSY: list_add(&rq->queuelist, &rq_list); __blk_mq_requeue_request(rq); break; default: pr_err("blk-mq: bad return on queue: %d\n", ret); case BLK_MQ_RQ_QUEUE_ERROR: rq->errors = -EIO; blk_mq_end_request(rq, rq->errors); break; } if (ret == BLK_MQ_RQ_QUEUE_BUSY) break; /* * We've done the first request. If we have more than 1 * left in the list, set dptr to defer issue. */ if (!dptr && rq_list.next != rq_list.prev) dptr = &driver_list; } hctx->dispatched[queued_to_index(queued)]++; /* * Any items that need requeuing? Stuff them into hctx->dispatch, * that is where we will continue on next queue run. */ if (!list_empty(&rq_list)) { spin_lock(&hctx->lock); list_splice(&rq_list, &hctx->dispatch); spin_unlock(&hctx->lock); /* * the queue is expected stopped with BLK_MQ_RQ_QUEUE_BUSY, but * it's possible the queue is stopped and restarted again * before this. Queue restart will dispatch requests. And since * requests in rq_list aren't added into hctx->dispatch yet, * the requests in rq_list might get lost. * * blk_mq_run_hw_queue() already checks the STOPPED bit **/ blk_mq_run_hw_queue(hctx, true); } }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe36196.01%753.85%
shaohua lishaohua li82.13%17.69%
christoph hellwigchristoph hellwig61.60%430.77%
omar sandovalomar sandoval10.27%17.69%
Total376100.00%13100.00%

/* * It'd be great if the workqueue API had a way to pass * in a mask and had some smarts for more clever placement. * For now we just round-robin here, switching for every * BLK_MQ_CPU_WORK_BATCH queued items. */
static int blk_mq_hctx_next_cpu(struct blk_mq_hw_ctx *hctx) { if (hctx->queue->nr_hw_queues == 1) return WORK_CPU_UNBOUND; if (--hctx->next_cpu_batch <= 0) { int cpu = hctx->next_cpu, next_cpu; next_cpu = cpumask_next(hctx->next_cpu, hctx->cpumask); if (next_cpu >= nr_cpu_ids) next_cpu = cpumask_first(hctx->cpumask); hctx->next_cpu = next_cpu; hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH; return cpu; } return hctx->next_cpu; }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe6975.00%150.00%
christoph hellwigchristoph hellwig2325.00%150.00%
Total92100.00%2100.00%


void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async) { if (unlikely(test_bit(BLK_MQ_S_STOPPED, &hctx->state) || !blk_mq_hw_queue_mapped(hctx))) return; if (!async && !(hctx->flags & BLK_MQ_F_BLOCKING)) { int cpu = get_cpu(); if (cpumask_test_cpu(cpu, hctx->cpumask)) { __blk_mq_run_hw_queue(hctx); put_cpu(); return; } put_cpu(); } kblockd_schedule_work_on(blk_mq_hctx_next_cpu(hctx), &hctx->run_work); }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe6871.58%660.00%
paolo bonzinipaolo bonzini2021.05%220.00%
ming leiming lei66.32%110.00%
christoph hellwigchristoph hellwig11.05%110.00%
Total95100.00%10100.00%


void blk_mq_run_hw_queues(struct request_queue *q, bool async) { struct blk_mq_hw_ctx *hctx; int i; queue_for_each_hw_ctx(q, hctx, i) { if ((!blk_mq_hctx_has_pending(hctx) && list_empty_careful(&hctx->dispatch)) || test_bit(BLK_MQ_S_STOPPED, &hctx->state)) continue; blk_mq_run_hw_queue(hctx, async); } }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe6292.54%266.67%
mike snitzermike snitzer57.46%133.33%
Total67100.00%3100.00%

EXPORT_SYMBOL(blk_mq_run_hw_queues);
void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx) { cancel_work(&hctx->run_work); cancel_delayed_work(&hctx->delay_work); set_bit(BLK_MQ_S_STOPPED, &hctx->state); }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe2775.00%266.67%
christoph hellwigchristoph hellwig925.00%133.33%
Total36100.00%3100.00%

EXPORT_SYMBOL(blk_mq_stop_hw_queue);
void blk_mq_stop_hw_queues(struct request_queue *q) { struct blk_mq_hw_ctx *hctx; int i; queue_for_each_hw_ctx(q, hctx, i) blk_mq_stop_hw_queue(hctx); }

Contributors

PersonTokensPropCommitsCommitProp
christoph hellwigchristoph hellwig31100.00%1100.00%
Total31100.00%1100.00%

EXPORT_SYMBOL(blk_mq_stop_hw_queues);
void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx) { clear_bit(BLK_MQ_S_STOPPED, &hctx->state); blk_mq_run_hw_queue(hctx, false); }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe27100.00%2100.00%
Total27100.00%2100.00%

EXPORT_SYMBOL(blk_mq_start_hw_queue);
void blk_mq_start_hw_queues(struct request_queue *q) { struct blk_mq_hw_ctx *hctx; int i; queue_for_each_hw_ctx(q, hctx, i) blk_mq_start_hw_queue(hctx); }

Contributors

PersonTokensPropCommitsCommitProp
christoph hellwigchristoph hellwig31100.00%1100.00%
Total31100.00%1100.00%

EXPORT_SYMBOL(blk_mq_start_hw_queues);
void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async) { struct blk_mq_hw_ctx *hctx; int i; queue_for_each_hw_ctx(q, hctx, i) { if (!test_bit(BLK_MQ_S_STOPPED, &hctx->state)) continue; clear_bit(BLK_MQ_S_STOPPED, &hctx->state); blk_mq_run_hw_queue(hctx, async); } }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe5893.55%150.00%
christoph hellwigchristoph hellwig46.45%150.00%
Total62100.00%2100.00%

EXPORT_SYMBOL(blk_mq_start_stopped_hw_queues);
static void blk_mq_run_work_fn(struct work_struct *work) { struct blk_mq_hw_ctx *hctx; hctx = container_of(work, struct blk_mq_hw_ctx, run_work); __blk_mq_run_hw_queue(hctx); }

Contributors

PersonTokensPropCommitsCommitProp
christoph hellwigchristoph hellwig33100.00%1100.00%
Total33100.00%1100.00%


static void blk_mq_delay_work_fn(struct work_struct *work) { struct blk_mq_hw_ctx *hctx; hctx = container_of(work, struct blk_mq_hw_ctx, delay_work.work); if (test_and_clear_bit(BLK_MQ_S_STOPPED, &hctx->state)) __blk_mq_run_hw_queue(hctx); }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe3370.21%150.00%
christoph hellwigchristoph hellwig1429.79%150.00%
Total47100.00%2100.00%


void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs) { if (unlikely(!blk_mq_hw_queue_mapped(hctx))) return; kblockd_schedule_delayed_work_on(blk_mq_hctx_next_cpu(hctx), &hctx->delay_work, msecs_to_jiffies(msecs)); }

Contributors

PersonTokensPropCommitsCommitProp
christoph hellwigchristoph hellwig3681.82%250.00%
ming leiming lei715.91%125.00%
jens axboejens axboe12.27%125.00%
Total44100.00%4100.00%

EXPORT_SYMBOL(blk_mq_delay_queue);
static inline void __blk_mq_insert_req_list(struct blk_mq_hw_ctx *hctx, struct request *rq, bool at_head) { struct blk_mq_ctx *ctx = rq->mq_ctx; trace_block_rq_insert(hctx->queue, rq); if (at_head) list_add(&rq->queuelist, &ctx->rq_list); else list_add_tail(&rq->queuelist, &ctx->rq_list); }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe4565.22%360.00%
christoph hellwigchristoph hellwig2130.43%120.00%
ming leiming lei34.35%120.00%
Total69100.00%5100.00%


static void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, bool at_head) { struct blk_mq_ctx *ctx = rq->mq_ctx; __blk_mq_insert_req_list(hctx, rq, at_head); blk_mq_hctx_mark_pending(hctx, ctx); }

Contributors

PersonTokensPropCommitsCommitProp
ming leiming lei3681.82%150.00%
jens axboejens axboe818.18%150.00%
Total44100.00%2100.00%


void blk_mq_insert_request(struct request *rq, bool at_head, bool run_queue, bool async) { struct blk_mq_ctx *ctx = rq->mq_ctx; struct request_queue *q = rq->q; struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu); spin_lock(&ctx->lock); __blk_mq_insert_request(hctx, rq, at_head); spin_unlock(&ctx->lock); if (run_queue) blk_mq_run_hw_queue(hctx, async); }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe7990.80%240.00%
christoph hellwigchristoph hellwig89.20%360.00%
Total87100.00%5100.00%


static void blk_mq_insert_requests(struct request_queue *q, struct blk_mq_ctx *ctx, struct list_head *list, int depth, bool from_schedule) { struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu); trace_block_unplug(q, depth, !from_schedule); /* * preemption doesn't flush plug list, so it's possible ctx->cpu is * offline now */ spin_lock(&ctx->lock); while (!list_empty(list)) { struct request *rq; rq = list_first_entry(list, struct request, queuelist); BUG_ON(rq->mq_ctx != ctx); list_del_init(&rq->queuelist); __blk_mq_insert_req_list(hctx, rq, false); } blk_mq_hctx_mark_pending(hctx, ctx); spin_unlock(&ctx->lock); blk_mq_run_hw_queue(hctx, from_schedule); }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe11685.93%240.00%
christoph hellwigchristoph hellwig118.15%240.00%
ming leiming lei85.93%120.00%
Total135100.00%5100.00%


static int plug_ctx_cmp(void *priv, struct list_head *a, struct list_head *b) { struct request *rqa = container_of(a, struct request, queuelist); struct request *rqb = container_of(b, struct request, queuelist); return !(rqa->mq_ctx < rqb->mq_ctx || (rqa->mq_ctx == rqb->mq_ctx && blk_rq_pos(rqa) < blk_rq_pos(rqb))); }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe82100.00%1100.00%
Total82100.00%1100.00%


void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule) { struct blk_mq_ctx *this_ctx; struct request_queue *this_q; struct request *rq; LIST_HEAD(list); LIST_HEAD(ctx_list); unsigned int depth; list_splice_init(&plug->mq_list, &list); list_sort(NULL, &list, plug_ctx_cmp); this_q = NULL; this_ctx = NULL; depth = 0; while (!list_empty(&list)) { rq = list_entry_rq(list.next); list_del_init(&rq->queuelist); BUG_ON(!rq->q); if (rq->mq_ctx != this_ctx) { if (this_ctx) { blk_mq_insert_requests(this_q, this_ctx, &ctx_list, depth, from_schedule); } this_ctx = rq->mq_ctx; this_q = rq->q; depth = 0; } depth++; list_add_tail(&rq->queuelist, &ctx_list); } /* * If 'this_ctx' is set, we know we have entries to complete * on 'ctx_list'. Do those. */ if (this_ctx) { blk_mq_insert_requests(this_q, this_ctx, &ctx_list, depth, from_schedule); } }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe192100.00%1100.00%
Total192100.00%1100.00%


static void blk_mq_bio_to_request(struct request *rq, struct bio *bio) { init_request_from_bio(rq, bio); blk_account_io_start(rq, 1); }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe30100.00%1100.00%
Total30100.00%1100.00%


static inline bool hctx_allow_merges(struct blk_mq_hw_ctx *hctx) { return (hctx->flags & BLK_MQ_F_SHOULD_MERGE) && !blk_queue_nomerges(hctx->queue); }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe29100.00%1100.00%
Total29100.00%1100.00%


static inline bool blk_mq_merge_queue_io(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx, struct request *rq, struct bio *bio) { if (!hctx_allow_merges(hctx) || !bio_mergeable(bio)) { blk_mq_bio_to_request(rq, bio); spin_lock(&ctx->lock); insert_rq: __blk_mq_insert_request(hctx, rq, false); spin_unlock(&ctx->lock); return false; } else { struct request_queue *q = hctx->queue; spin_lock(&ctx->lock); if (!blk_mq_attempt_merge(q, ctx, bio)) { blk_mq_bio_to_request(rq, bio); goto insert_rq; } spin_unlock(&ctx->lock); __blk_mq_free_request(hctx, ctx, rq); return true; } }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe13895.83%266.67%
ming leiming lei64.17%133.33%
Total144100.00%3100.00%

struct blk_map_ctx { struct blk_mq_hw_ctx *hctx; struct blk_mq_ctx *ctx; };
static struct request *blk_mq_map_request(struct request_queue *q, struct bio *bio, struct blk_map_ctx *data) { struct blk_mq_hw_ctx *hctx; struct blk_mq_ctx *ctx; struct request *rq; int op = bio_data_dir(bio); int op_flags = 0; struct blk_mq_alloc_data alloc_data; blk_queue_enter_live(q); ctx = blk_mq_get_ctx(q); hctx = blk_mq_map_queue(q, ctx->cpu); if (rw_is_sync(bio_op(bio), bio->bi_opf)) op_flags |= REQ_SYNC; trace_block_getrq(q, bio, op); blk_mq_set_alloc_data(&alloc_data, q, 0, ctx, hctx); rq = __blk_mq_alloc_request(&alloc_data, op, op_flags); data->hctx = alloc_data.hctx; data->ctx = alloc_data.ctx; data->hctx->queued++; return rq; }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe11371.97%327.27%
lei minglei ming2113.38%19.09%
michael christiemichael christie1610.19%218.18%
christoph hellwigchristoph hellwig63.82%436.36%
dan williamsdan williams10.64%19.09%
Total157100.00%11100.00%


static int blk_mq_direct_issue_request(struct request *rq, blk_qc_t *cookie) { int ret; struct request_queue *q = rq->q; struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, rq->mq_ctx->cpu); struct blk_mq_queue_data bd = { .rq = rq, .list = NULL, .last = 1 }; blk_qc_t new_cookie = blk_tag_to_qc_t(rq->tag, hctx->queue_num); /* * For OK queue, we are done. For error, kill it. Any other * error (busy), just add it to our list as we previously * would have done */ ret = q->mq_ops->queue_rq(hctx, &bd); if (ret == BLK_MQ_RQ_QUEUE_OK) { *cookie = new_cookie; return 0; } __blk_mq_requeue_request(rq); if (ret == BLK_MQ_RQ_QUEUE_ERROR) { *cookie = BLK_QC_T_NONE; rq->errors = -EIO; blk_mq_end_request(rq, rq->errors); return 0; } return -1; }

Contributors

PersonTokensPropCommitsCommitProp
shaohua lishaohua li11979.33%133.33%
jens axboejens axboe3020.00%133.33%
christoph hellwigchristoph hellwig10.67%133.33%
Total150100.00%3100.00%

/* * Multiple hardware queue variant. This will not use per-process plugs, * but will attempt to bypass the hctx queueing if we can go straight to * hardware for SYNC IO. */
static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) { const int is_sync = rw_is_sync(bio_op(bio), bio->bi_opf); const int is_flush_fua = bio->bi_opf & (REQ_PREFLUSH | REQ_FUA); struct blk_map_ctx data; struct request *rq; unsigned int request_count = 0; struct blk_plug *plug; struct request *same_queue_rq = NULL; blk_qc_t cookie; blk_queue_bounce(q, &bio); if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) { bio_io_error(bio); return BLK_QC_T_NONE; } blk_queue_split(q, &bio, q->bio_split); if (!is_flush_fua && !blk_queue_nomerges(q) && blk_attempt_plug_merge(q, bio, &request_count, &same_queue_rq)) return BLK_QC_T_NONE; rq = blk_mq_map_request(q, bio, &data); if (unlikely(!rq)) return BLK_QC_T_NONE; cookie = blk_tag_to_qc_t(rq->tag, data.hctx->queue_num); if (unlikely(is_flush_fua)) { blk_mq_bio_to_request(rq, bio); blk_insert_flush(rq); goto run_queue; } plug = current->plug; /* * If the driver supports defer issued based on 'last', then * queue it up like normal since we can potentially save some * CPU this way. */ if (((plug && !blk_queue_nomerges(q)) || is_sync) && !(data.hctx->flags & BLK_MQ_F_DEFER_ISSUE)) { struct request *old_rq = NULL; blk_mq_bio_to_request(rq, bio); /* * We do limited pluging. If the bio can be merged, do that. * Otherwise the existing request in the plug list will be * issued. So the plug list will have one request at most */ if (plug) { /* * The plug list might get flushed before this. If that * happens, same_queue_rq is invalid and plug list is * empty */ if (same_queue_rq && !list_empty(&plug->mq_list)) { old_rq = same_queue_rq; list_del_init(&old_rq->queuelist); } list_add_tail(&rq->queuelist, &plug->mq_list); } else /* is_sync */ old_rq = rq; blk_mq_put_ctx(data.ctx); if (!old_rq) goto done; if (!blk_mq_direct_issue_request(old_rq, &cookie)) goto done; blk_mq_insert_request(old_rq, false, true, true); goto done; } if (!blk_mq_merge_queue_io(data.hctx, data.ctx, rq, bio)) { /* * For a SYNC request, send it to the hardware immediately. For * an ASYNC request, just ensure that we run it later on. The * latter allows for merging opportunities and more efficient * dispatching. */ run_queue: blk_mq_run_hw_queue(data.hctx, !is_sync || is_flush_fua); } blk_mq_put_ctx(data.ctx); done: return cookie; }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe26766.58%850.00%
shaohua lishaohua li11428.43%318.75%
kent overstreetkent overstreet122.99%16.25%
michael christiemichael christie61.50%212.50%
omar sandovalomar sandoval10.25%16.25%
christoph hellwigchristoph hellwig10.25%16.25%
Total401100.00%16100.00%

/* * Single hardware queue variant. This will attempt to use any per-process * plug for merging and IO deferral. */
static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio) { const int is_sync = rw_is_sync(bio_op(bio), bio->bi_opf); const int is_flush_fua = bio->bi_opf & (REQ_PREFLUSH | REQ_FUA); struct blk_plug *plug; unsigned int request_count = 0; struct blk_map_ctx data; struct request *rq; blk_qc_t cookie; blk_queue_bounce(q, &bio); if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) { bio_io_error(bio); return BLK_QC_T_NONE; } blk_queue_split(q, &bio, q->bio_split); if (!is_flush_fua && !blk_queue_nomerges(q)) { if (blk_attempt_plug_merge(q, bio, &request_count, NULL)) return BLK_QC_T_NONE; } else request_count = blk_plug_queued_count(q); rq = blk_mq_map_request(q, bio, &data); if (unlikely(!rq)) return BLK_QC_T_NONE; cookie = blk_tag_to_qc_t(rq->tag, data.hctx->queue_num); if (unlikely(is_flush_fua)) { blk_mq_bio_to_request(rq, bio); blk_insert_flush(rq); goto run_queue; } /* * A task plug currently exists. Since this is completely lockless, * utilize that to temporarily store requests until the task is * either done or scheduled away. */ plug = current->plug; if (plug) { blk_mq_bio_to_request(rq, bio); if (!request_count) trace_block_plug(q); blk_mq_put_ctx(data.ctx); if (request_count >= BLK_MAX_REQUEST_COUNT) { blk_flush_plug_list(plug, false); trace_block_plug(q); } list_add_tail(&rq->queuelist, &plug->mq_list); return cookie; } if (!blk_mq_merge_queue_io(data.hctx, data.ctx, rq, bio)) { /* * For a SYNC request, send it to the hardware immediately. For * an ASYNC request, just ensure that we run it later on. The * latter allows for merging opportunities and more efficient * dispatching. */ run_queue: blk_mq_run_hw_queue(data.hctx, !is_sync || is_flush_fua); } blk_mq_put_ctx(data.ctx); return cookie; }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe26179.33%947.37%
nicholas bellingernicholas bellinger185.47%15.26%
omar sandovalomar sandoval133.95%15.26%
kent overstreetkent overstreet123.65%15.26%
jeff moyerjeff moyer92.74%15.26%
michael christiemichael christie61.82%210.53%
robert elliottrobert elliott51.52%15.26%
shaohua lishaohua li20.61%15.26%
ming leiming lei20.61%15.26%
christoph hellwigchristoph hellwig10.30%15.26%
Total329100.00%19100.00%


static void blk_mq_free_rq_map(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, unsigned int hctx_idx) { struct page *page; if (tags->rqs && set->ops->exit_request) { int i; for (i = 0; i < tags->nr_tags; i++) { if (!tags->rqs[i]) continue; set->ops->exit_request(set->driver_data, tags->rqs[i], hctx_idx, i); tags->rqs[i] = NULL; } } while (!list_empty(&tags->page_list)) { page = list_first_entry(&tags->page_list, struct page, lru); list_del_init(&page->lru); /* * Remove kmemleak object previously allocated in * blk_mq_init_rq_map(). */ kmemleak_free(page_address(page)); __free_pages(page, page->private); } kfree(tags->rqs); blk_mq_free_tags(tags); }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe10663.47%342.86%
christoph hellwigchristoph hellwig5029.94%228.57%
catalin marinascatalin marinas95.39%114.29%
dave hansendave hansen21.20%114.29%
Total167100.00%7100.00%


static size_t order_to_size(unsigned int order) { return (size_t)PAGE_SIZE << order; }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe1477.78%150.00%
lei minglei ming422.22%150.00%
Total18100.00%2100.00%


static struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set, unsigned int hctx_idx) { struct blk_mq_tags *tags; unsigned int i, j, entries_per_page, max_order = 4; size_t rq_size, left; tags = blk_mq_init_tags(set->queue_depth, set->reserved_tags, set->numa_node, BLK_MQ_FLAG_TO_ALLOC_POLICY(set->flags)); if (!tags) return NULL; INIT_LIST_HEAD(&tags->page_list); tags->rqs = kzalloc_node(set->queue_depth * sizeof(struct request *), GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY, set->numa_node); if (!tags->rqs) { blk_mq_free_tags(tags); return NULL; } /* * rq_size is the size of the request plus driver payload, rounded * to the cacheline size */ rq_size = round_up(sizeof(struct request) + set->cmd_size, cache_line_size()); left = rq_size * set->queue_depth; for (i = 0; i < set->queue_depth; ) { int this_order = max_order; struct page *page; int to_do; void *p; while (this_order && left < order_to_size(this_order - 1)) this_order--; do { page = alloc_pages_node(set->numa_node, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO, this_order); if (page) break; if (!this_order--) break; if (order_to_size(this_order) < rq_size) break; } while (1); if (!page) goto fail; page->private = this_order; list_add_tail(&page->lru, &tags->page_list); p = page_address(page); /* * Allow kmemleak to scan these pages as they contain pointers * to additional allocations like via ops->init_request(). */ kmemleak_alloc(p, order_to_size(this_order), 1, GFP_KERNEL); entries_per_page = order_to_size(this_order) / rq_size; to_do = min(entries_per_page, set->queue_depth - i); left -= to_do * rq_size; for (j = 0; j < to_do; j++) { tags->rqs[i] = p; if (set->ops->init_request) { if (set->ops->init_request(set->driver_data, tags->rqs[i], hctx_idx, i, set->numa_node)) { tags->rqs[i] = NULL; goto fail; } } p += rq_size; i++; } } return tags; fail: blk_mq_free_rq_map(set, tags, hctx_idx); return NULL; }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe27965.65%222.22%
christoph hellwigchristoph hellwig11928.00%222.22%
catalin marinascatalin marinas153.53%111.11%
shaohua lishaohua li71.65%111.11%
linus torvaldslinus torvalds20.47%111.11%
bartlomiej zolnierkiewiczbartlomiej zolnierkiewicz20.47%111.11%
dave hansendave hansen10.24%111.11%
Total425100.00%9100.00%

/* * 'cpu' is going away. splice any existing rq_list entries from this * software queue to the hw queue dispatch list, and ensure that it * gets run. */
static int blk_mq_hctx_notify_dead(unsigned int cpu, struct hlist_node *node) { struct blk_mq_hw_ctx *hctx; struct blk_mq_ctx *ctx; LIST_HEAD(tmp); hctx = hlist_entry_safe(node, struct blk_mq_hw_ctx, cpuhp_dead); ctx = __blk_mq_get_ctx(hctx->queue, cpu); spin_lock(&ctx->lock); if (!list_empty(&ctx->rq_list)) { list_splice_init(&ctx->rq_list, &tmp); blk_mq_hctx_clear_pending(hctx, ctx); } spin_unlock(&ctx->lock); if (list_empty(&tmp)) return 0; spin_lock(&hctx->lock); list_splice_tail_init(&tmp, &hctx->dispatch); spin_unlock(&hctx->lock); blk_mq_run_hw_queue(hctx, true); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe12282.43%375.00%
thomas gleixnerthomas gleixner2617.57%125.00%
Total148100.00%4100.00%


static void blk_mq_remove_cpuhp(struct blk_mq_hw_ctx *hctx) { cpuhp_state_remove_instance_nocalls(CPUHP_BLK_MQ_DEAD, &hctx->cpuhp_dead); }

Contributors

PersonTokensPropCommitsCommitProp
thomas gleixnerthomas gleixner1152.38%150.00%
jens axboejens axboe1047.62%150.00%
Total21100.00%2100.00%

/* hctx->ctxs will be freed in queue's release handler */
static void blk_mq_exit_hctx(struct request_queue *q, struct blk_mq_tag_set *set, struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx) { unsigned flush_start_tag = set->queue_depth; blk_mq_tag_idle(hctx); if (set->ops->exit_request) set->ops->exit_request(set->driver_data, hctx->fq->flush_rq, hctx_idx, flush_start_tag + hctx_idx); if (set->ops->exit_hctx) set->ops->exit_hctx(hctx, hctx_idx); blk_mq_remove_cpuhp(hctx); blk_free_flush_queue(hctx->fq); sbitmap_free(&hctx->ctx_map); }

Contributors

PersonTokensPropCommitsCommitProp
lei minglei ming6056.07%116.67%
ming leiming lei3835.51%233.33%
jens axboejens axboe76.54%116.67%
omar sandovalomar sandoval10.93%116.67%
thomas gleixnerthomas gleixner10.93%116.67%
Total107100.00%6100.00%


static void blk_mq_exit_hw_queues(struct request_queue *q, struct blk_mq_tag_set *set, int nr_queue) { struct blk_mq_hw_ctx *hctx; unsigned int i; queue_for_each_hw_ctx(q, hctx, i) { if (i == nr_queue) break; blk_mq_exit_hctx(q, set, hctx, i); } }

Contributors

PersonTokensPropCommitsCommitProp
lei minglei ming3867.86%150.00%
ming leiming lei1832.14%150.00%
Total56100.00%2100.00%


static void blk_mq_free_hw_queues(struct request_queue *q, struct blk_mq_tag_set *set) { struct blk_mq_hw_ctx *hctx; unsigned int i; queue_for_each_hw_ctx(q, hctx, i) free_cpumask_var(hctx->cpumask); }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe2870.00%250.00%
ming leiming lei1025.00%125.00%
christoph hellwigchristoph hellwig25.00%125.00%
Total40100.00%4100.00%


static int blk_mq_init_hctx(struct request_queue *q, struct blk_mq_tag_set *set, struct blk_mq_hw_ctx *hctx, unsigned hctx_idx) { int node; unsigned flush_start_tag = set->queue_depth; node = hctx->numa_node; if (node == NUMA_NO_NODE) node = hctx->numa_node = set->numa_node; INIT_WORK(&hctx->run_work, blk_mq_run_work_fn); INIT_DELAYED_WORK(&hctx->delay_work, blk_mq_delay_work_fn); spin_lock_init(&hctx->lock); INIT_LIST_HEAD(&hctx->dispatch); hctx->queue = q; hctx->queue_num = hctx_idx; hctx->flags = set->flags & ~BLK_MQ_F_TAG_SHARED; cpuhp_state_add_instance_nocalls(CPUHP_BLK_MQ_DEAD, &hctx->cpuhp_dead); hctx->tags = set->tags[hctx_idx]; /* * Allocate space for all possible cpus to avoid allocation at * runtime */ hctx->ctxs = kmalloc_node(nr_cpu_ids * sizeof(void *), GFP_KERNEL, node); if (!hctx->ctxs) goto unregister_cpu_notifier; if (sbitmap_init_node(&hctx->ctx_map, nr_cpu_ids, ilog2(8), GFP_KERNEL, node)) goto free_ctxs; hctx->nr_ctx = 0; if (set->ops->init_hctx && set->ops->init_hctx(hctx, set->driver_data, hctx_idx)) goto free_bitmap; hctx->fq = blk_alloc_flush_queue(q, hctx->numa_node, set->cmd_size); if (!hctx->fq) goto exit_hctx; if (set->ops->init_request && set->ops->init_request(set->driver_data, hctx->fq->flush_rq, hctx_idx, flush_start_tag + hctx_idx, node)) goto free_fq; return 0; free_fq: kfree(hctx->fq); exit_hctx: if (set->ops->exit_hctx) set->ops->exit_hctx(hctx, hctx_idx); free_bitmap: sbitmap_free(&hctx->ctx_map); free_ctxs: kfree(hctx->ctxs); unregister_cpu_notifier: blk_mq_remove_cpuhp(hctx); return -1; }

Contributors

PersonTokensPropCommitsCommitProp
ming leiming lei17048.85%220.00%
jens axboejens axboe13338.22%330.00%
christoph hellwigchristoph hellwig277.76%220.00%
omar sandovalomar sandoval113.16%110.00%
thomas gleixnerthomas gleixner41.15%110.00%
jeff moyerjeff moyer30.86%110.00%
Total348100.00%10100.00%


static void blk_mq_init_cpu_queues(struct request_queue *q, unsigned int nr_hw_queues) { unsigned int i; for_each_possible_cpu(i) { struct blk_mq_ctx *__ctx = per_cpu_ptr(q->queue_ctx, i); struct blk_mq_hw_ctx *hctx; memset(__ctx, 0, sizeof(*__ctx)); __ctx->cpu = i; spin_lock_init(&__ctx->lock); INIT_LIST_HEAD(&__ctx->rq_list); __ctx->queue = q; /* If the cpu isn't online, the cpu is mapped to first hctx */ if (!cpu_online(i)) continue; hctx = blk_mq_map_queue(q, i); /* * Set local node, IFF we have more than one hw queue. If * not, we remain on the home node of the device */ if (nr_hw_queues > 1 && hctx->numa_node == NUMA_NO_NODE) hctx->numa_node = local_memory_node(cpu_to_node(i)); } }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe12596.90%250.00%
raghavendra k t* (same as raghavendra koushik)raghavendra k t* (same as raghavendra koushik)32.33%125.00%
christoph hellwigchristoph hellwig10.78%125.00%
Total129100.00%4100.00%


static void blk_mq_map_swqueue(struct request_queue *q, const struct cpumask *online_mask) { unsigned int i; struct blk_mq_hw_ctx *hctx; struct blk_mq_ctx *ctx; struct blk_mq_tag_set *set = q->tag_set; /* * Avoid others reading imcomplete hctx->cpumask through sysfs */ mutex_lock(&q->sysfs_lock); queue_for_each_hw_ctx(q, hctx, i) { cpumask_clear(hctx->cpumask); hctx->nr_ctx = 0; } /* * Map software to hardware queues */ for_each_possible_cpu(i) { /* If the cpu isn't online, the cpu is mapped to first hctx */ if (!cpumask_test_cpu(i, online_mask)) continue; ctx = per_cpu_ptr(q->queue_ctx, i); hctx = blk_mq_map_queue(q, i); cpumask_set_cpu(i, hctx->cpumask); ctx->index_hw = hctx->nr_ctx; hctx->ctxs[hctx->nr_ctx++] = ctx; } mutex_unlock(&q->sysfs_lock); queue_for_each_hw_ctx(q, hctx, i) { /* * If no software queues are mapped to this hardware queue, * disable it and free the request entries. */ if (!hctx->nr_ctx) { if (set->tags[i]) { blk_mq_free_rq_map(set, set->tags[i], i); set->tags[i] = NULL; } hctx->tags = NULL; continue; } /* unmapped hw queue can be remapped after CPU topo changed */ if (!set->tags[i]) set->tags[i] = blk_mq_init_rq_map(set, i); hctx->tags = set->tags[i]; WARN_ON(!hctx->tags); /* * Set the map size to the number of mapped software queues. * This is more accurate and more efficient than looping * over all possibly mapped software queues. */ sbitmap_resize(&hctx->ctx_map, hctx->nr_ctx); /* * Initialize batch roundrobin counts */ hctx->next_cpu = cpumask_first(hctx->cpumask); hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH; } }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe18163.73%646.15%
ming leiming lei5419.01%17.69%
akinobu mitaakinobu mita269.15%215.38%
thomas gleixnerthomas gleixner124.23%17.69%
omar sandovalomar sandoval51.76%17.69%
chong yuanchong yuan51.76%17.69%
christoph hellwigchristoph hellwig10.35%17.69%
Total284100.00%13100.00%


static void queue_set_hctx_shared(struct request_queue *q, bool shared) { struct blk_mq_hw_ctx *hctx; int i; queue_for_each_hw_ctx(q, hctx, i) { if (shared) hctx->flags |= BLK_MQ_F_TAG_SHARED; else hctx->flags &= ~BLK_MQ_F_TAG_SHARED; } }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe4386.00%150.00%
jeff moyerjeff moyer714.00%150.00%
Total50100.00%2100.00%


static void blk_mq_update_tag_set_depth(struct blk_mq_tag_set *set, bool shared) { struct request_queue *q; list_for_each_entry(q, &set->tag_list, tag_set_list) { blk_mq_freeze_queue(q); queue_set_hctx_shared(q, shared); blk_mq_unfreeze_queue(q); } }

Contributors

PersonTokensPropCommitsCommitProp
jeff moyerjeff moyer3984.78%150.00%
jens axboejens axboe715.22%150.00%
Total46100.00%2100.00%


static void blk_mq_del_queue_tag_set(struct request_queue *q) { struct blk_mq_tag_set *set = q->tag_set; mutex_lock(&set->tag_list_lock); list_del_init(&q->tag_set_list); if (list_is_singular(&set->tag_list)) { /* just transitioned to unshared */ set->flags &= ~BLK_MQ_F_TAG_SHARED; /* update existing queue */ blk_mq_update_tag_set_depth(set, false); } mutex_unlock(&set->tag_list_lock); }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe4968.06%150.00%
jeff moyerjeff moyer2331.94%150.00%
Total72100.00%2100.00%


static void blk_mq_add_queue_tag_set(struct blk_mq_tag_set *set, struct request_queue *q) { q->tag_set = set; mutex_lock(&set->tag_list_lock); /* Check to see if we're transitioning to shared (from 1 to 2 queues). */ if (!list_empty(&set->tag_list) && !(set->flags & BLK_MQ_F_TAG_SHARED)) { set->flags |= BLK_MQ_F_TAG_SHARED; /* update existing queue */ blk_mq_update_tag_set_depth(set, true); } if (set->flags & BLK_MQ_F_TAG_SHARED) queue_set_hctx_shared(q, true); list_add_tail(&q->tag_set_list, &set->tag_list); mutex_unlock(&set->tag_list_lock); }

Contributors

PersonTokensPropCommitsCommitProp
jeff moyerjeff moyer5250.49%150.00%
jens axboejens axboe5149.51%150.00%
Total103100.00%2100.00%

/* * It is the actual release handler for mq, but we do it from * request queue's release handler for avoiding use-after-free * and headache because q->mq_kobj shouldn't have been introduced, * but we can't group ctx/kctx kobj without it. */
void blk_mq_release(struct request_queue *q) { struct blk_mq_hw_ctx *hctx; unsigned int i; /* hctx kobj stays in hctx */ queue_for_each_hw_ctx(q, hctx, i) { if (!hctx) continue; kfree(hctx->ctxs); kfree(hctx); } q->mq_map = NULL; kfree(q->queue_hw_ctx); /* ctx kobj stays in queue_ctx */ free_percpu(q->queue_ctx); }

Contributors

PersonTokensPropCommitsCommitProp
ming leiming lei4463.77%133.33%
lei minglei ming1521.74%133.33%
akinobu mitaakinobu mita1014.49%133.33%
Total69100.00%3100.00%


struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set) { struct request_queue *uninit_q, *q; uninit_q = blk_alloc_queue_node(GFP_KERNEL, set->numa_node); if (!uninit_q) return ERR_PTR(-ENOMEM); q = blk_mq_init_allocated_queue(set, uninit_q); if (IS_ERR(q)) blk_cleanup_queue(uninit_q); return q; }

Contributors

PersonTokensPropCommitsCommitProp
mike snitzermike snitzer5582.09%133.33%
jens axboejens axboe1014.93%133.33%
christoph hellwigchristoph hellwig22.99%133.33%
Total67100.00%3100.00%

EXPORT_SYMBOL(blk_mq_init_queue);
static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set, struct request_queue *q) { int i, j; struct blk_mq_hw_ctx **hctxs = q->queue_hw_ctx; blk_mq_sysfs_unregister(q); for (i = 0; i < set->nr_hw_queues; i++) { int node; if (hctxs[i]) continue; node = blk_mq_hw_queue_to_node(q->mq_map, i); hctxs[i] = kzalloc_node(sizeof(struct blk_mq_hw_ctx), GFP_KERNEL, node); if (!hctxs[i]) break; if (!zalloc_cpumask_var_node(&hctxs[i]->cpumask, GFP_KERNEL, node)) { kfree(hctxs[i]); hctxs[i] = NULL; break; } atomic_set(&hctxs[i]->nr_active, 0); hctxs[i]->numa_node = node; hctxs[i]->queue_num = i; if (blk_mq_init_hctx(q, set, hctxs[i], i)) { free_cpumask_var(hctxs[i]->cpumask); kfree(hctxs[i]); hctxs[i] = NULL; break; } blk_mq_hctx_kobj_init(hctxs[i]); } for (j = i; j < q->nr_hw_queues; j++) { struct blk_mq_hw_ctx *hctx = hctxs[j]; if (hctx) { if (hctx->tags) { blk_mq_free_rq_map(set, hctx->tags, j); set->tags[j] = NULL; } blk_mq_exit_hctx(q, set, hctx, j); free_cpumask_var(hctx->cpumask); kobject_put(&hctx->kobj); kfree(hctx->ctxs); kfree(hctx); hctxs[j] = NULL; } } q->nr_hw_queues = i; blk_mq_sysfs_register(q); }

Contributors

PersonTokensPropCommitsCommitProp
keith buschkeith busch20159.47%110.00%
jens axboejens axboe11534.02%550.00%
mike snitzermike snitzer123.55%110.00%
christoph hellwigchristoph hellwig92.66%220.00%
fang weifang wei10.30%110.00%
Total338100.00%10100.00%


struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, struct request_queue *q) { /* mark the queue as mq asap */ q->mq_ops = set->ops; q->queue_ctx = alloc_percpu(struct blk_mq_ctx); if (!q->queue_ctx) goto err_exit; q->queue_hw_ctx = kzalloc_node(nr_cpu_ids * sizeof(*(q->queue_hw_ctx)), GFP_KERNEL, set->numa_node); if (!q->queue_hw_ctx) goto err_percpu; q->mq_map = set->mq_map; blk_mq_realloc_hw_ctxs(set, q); if (!q->nr_hw_queues) goto err_hctxs; INIT_WORK(&q->timeout_work, blk_mq_timeout_work); blk_queue_rq_timeout(q, set->timeout ? set->timeout : 30 * HZ); q->nr_queues = nr_cpu_ids; q->queue_flags |= QUEUE_FLAG_MQ_DEFAULT; if (!(set->flags & BLK_MQ_F_SG_MERGE)) q->queue_flags |= 1 << QUEUE_FLAG_NO_SG_MERGE; q->sg_reserved_size = INT_MAX; INIT_DELAYED_WORK(&q->requeue_work, blk_mq_requeue_work); INIT_LIST_HEAD(&q->requeue_list); spin_lock_init(&q->requeue_lock); if (q->nr_hw_queues > 1) blk_queue_make_request(q, blk_mq_make_request); else blk_queue_make_request(q, blk_sq_make_request); /* * Do this after blk_queue_make_request() overrides it... */ q->nr_requests = set->queue_depth; if (set->ops->complete) blk_queue_softirq_done(q, set->ops->complete); blk_mq_init_cpu_queues(q, set->nr_hw_queues); get_online_cpus(); mutex_lock(&all_q_mutex); list_add_tail(&q->all_q_node, &all_q_list); blk_mq_add_queue_tag_set(set, q); blk_mq_map_swqueue(q, cpu_online_mask); mutex_unlock(&all_q_mutex); put_online_cpus(); return q; err_hctxs: kfree(q->queue_hw_ctx); err_percpu: free_percpu(q->queue_ctx); err_exit: q->mq_ops = NULL; return ERR_PTR(-ENOMEM); }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe15546.27%939.13%
keith buschkeith busch8224.48%14.35%
christoph hellwigchristoph hellwig5616.72%626.09%
akinobu mitaakinobu mita144.18%28.70%
lin minglin ming113.28%14.35%
fang weifang wei82.39%14.35%
lei minglei ming51.49%14.35%
ming leiming lei30.90%14.35%
mike snitzermike snitzer10.30%14.35%
Total335100.00%23100.00%

EXPORT_SYMBOL(blk_mq_init_allocated_queue);
void blk_mq_free_queue(struct request_queue *q) { struct blk_mq_tag_set *set = q->tag_set; mutex_lock(&all_q_mutex); list_del_init(&q->all_q_node); mutex_unlock(&all_q_mutex); blk_mq_del_queue_tag_set(q); blk_mq_exit_hw_queues(q, set, set->nr_hw_queues); blk_mq_free_hw_queues(q, set); }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe2946.77%360.00%
akinobu mitaakinobu mita2032.26%120.00%
lei minglei ming1320.97%120.00%
Total62100.00%5100.00%

/* Basically redo blk_mq_init_queue with queue frozen */
static void blk_mq_queue_reinit(struct request_queue *q, const struct cpumask *online_mask) { WARN_ON_ONCE(!atomic_read(&q->mq_freeze_depth)); blk_mq_sysfs_unregister(q); /* * redo blk_mq_init_cpu_queues and blk_mq_init_hw_queues. FIXME: maybe * we should change hctx numa_node according to new topology (this * involves free and re-allocate memory, worthy doing?) */ blk_mq_map_swqueue(q, online_mask); blk_mq_sysfs_register(q); }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe3165.96%240.00%
akinobu mitaakinobu mita817.02%120.00%
christoph hellwigchristoph hellwig48.51%120.00%
tejun heotejun heo48.51%120.00%
Total47100.00%5100.00%

/* * New online cpumask which is going to be set in this hotplug event. * Declare this cpumasks as global as cpu-hotplug operation is invoked * one-by-one and dynamically allocating this could result in a failure. */ static struct cpumask cpuhp_online_new;
static void blk_mq_queue_reinit_work(void) { struct request_queue *q; mutex_lock(&all_q_mutex); /* * We need to freeze and reinit all existing queues. Freezing * involves synchronous wait for an RCU grace period and doing it * one by one may take a long time. Start freezing all queues in * one swoop and then wait for the completions so that freezing can * take place in parallel. */ list_for_each_entry(q, &all_q_list, all_q_node) blk_mq_freeze_queue_start(q); list_for_each_entry(q, &all_q_list, all_q_node) { blk_mq_freeze_queue_wait(q); /* * timeout handler can't touch hw queue during the * reinitialization */ del_timer_sync(&q->timeout); } list_for_each_entry(q, &all_q_list, all_q_node) blk_mq_queue_reinit(q, &cpuhp_online_new); list_for_each_entry(q, &all_q_list, all_q_node) blk_mq_unfreeze_queue(q); mutex_unlock(&all_q_mutex); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo4043.48%120.00%
jens axboejens axboe3538.04%120.00%
ming leiming lei1111.96%120.00%
sebastian andrzej siewiorsebastian andrzej siewior44.35%120.00%
akinobu mitaakinobu mita22.17%120.00%
Total92100.00%5100.00%


static int blk_mq_queue_reinit_dead(unsigned int cpu) { cpumask_copy(&cpuhp_online_new, cpu_online_mask); blk_mq_queue_reinit_work(); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
sebastian andrzej siewiorsebastian andrzej siewior24100.00%2100.00%
Total24100.00%2100.00%

/* * Before hotadded cpu starts handling requests, new mappings must be * established. Otherwise, these requests in hw queue might never be * dispatched. * * For example, there is a single hw queue (hctx) and two CPU queues (ctx0 * for CPU0, and ctx1 for CPU1). * * Now CPU1 is just onlined and a request is inserted into ctx1->rq_list * and set bit0 in pending bitmap as ctx1->index_hw is still zero. * * And then while running hw queue, flush_busy_ctxs() finds bit0 is set in * pending bitmap and tries to retrieve requests in hctx->ctxs[0]->rq_list. * But htx->ctxs[0] is a pointer to ctx0, so the request in ctx1->rq_list * is ignored. */
static int blk_mq_queue_reinit_prepare(unsigned int cpu) { cpumask_copy(&cpuhp_online_new, cpu_online_mask); cpumask_set_cpu(cpu, &cpuhp_online_new); blk_mq_queue_reinit_work(); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
sebastian andrzej siewiorsebastian andrzej siewior2990.62%150.00%
jens axboejens axboe39.38%150.00%
Total32100.00%2100.00%


static int __blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set) { int i; for (i = 0; i < set->nr_hw_queues; i++) { set->tags[i] = blk_mq_init_rq_map(set, i); if (!set->tags[i]) goto out_unwind; } return 0; out_unwind: while (--i >= 0) blk_mq_free_rq_map(set, set->tags[i], i); return -ENOMEM; }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe88100.00%1100.00%
Total88100.00%1100.00%

/* * Allocate the request maps associated with this tag_set. Note that this * may reduce the depth asked for, if memory is tight. set->queue_depth * will be updated to reflect the allocated depth. */
static int blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set) { unsigned int depth; int err; depth = set->queue_depth; do { err = __blk_mq_alloc_rq_maps(set); if (!err) break; set->queue_depth >>= 1; if (set->queue_depth < set->reserved_tags + BLK_MQ_TAG_MIN) { err = -ENOMEM; break; } } while (set->queue_depth); if (!set->queue_depth || err) { pr_err("blk-mq: failed to allocate request map\n"); return -ENOMEM; } if (depth != set->queue_depth) pr_info("blk-mq: reduced tag depth (%u -> %u)\n", depth, set->queue_depth); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe115100.00%1100.00%
Total115100.00%1100.00%

/* * Alloc a tag set to be associated with one or more request queues. * May fail with EINVAL for various error conditions. May adjust the * requested depth down, if if it too large. In that case, the set * value will be stored in set->queue_depth. */
int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set) { int ret; BUILD_BUG_ON(BLK_MQ_MAX_DEPTH > 1 << BLK_MQ_UNIQUE_TAG_BITS); if (!set->nr_hw_queues) return -EINVAL; if (!set->queue_depth) return -EINVAL; if (set->queue_depth < set->reserved_tags + BLK_MQ_TAG_MIN) return -EINVAL; if (!set->ops->queue_rq) return -EINVAL; if (set->queue_depth > BLK_MQ_MAX_DEPTH) { pr_info("blk-mq: reduced tag depth to %u\n", BLK_MQ_MAX_DEPTH); set->queue_depth = BLK_MQ_MAX_DEPTH; } /* * If a crashdump is active, then we are potentially in a very * memory constrained environment. Limit us to 1 queue and * 64 tags to prevent using too much memory. */ if (is_kdump_kernel()) { set->nr_hw_queues = 1; set->queue_depth = min(64U, set->queue_depth); } /* * There is no use for more h/w queues than cpus. */ if (set->nr_hw_queues > nr_cpu_ids) set->nr_hw_queues = nr_cpu_ids; set->tags = kzalloc_node(nr_cpu_ids * sizeof(struct blk_mq_tags *), GFP_KERNEL, set->numa_node); if (!set->tags) return -ENOMEM; ret = -ENOMEM; set->mq_map = kzalloc_node(sizeof(*set->mq_map) * nr_cpu_ids, GFP_KERNEL, set->numa_node); if (!set->mq_map) goto out_free_tags; if (set->ops->map_queues) ret = set->ops->map_queues(set); else ret = blk_mq_map_queues(set); if (ret) goto out_free_mq_map; ret = blk_mq_alloc_rq_maps(set); if (ret) goto out_free_mq_map; mutex_init(&set->tag_list_lock); INIT_LIST_HEAD(&set->tag_list); return 0; out_free_mq_map: kfree(set->mq_map); set->mq_map = NULL; out_free_tags: kfree(set->tags); set->tags = NULL; return ret; }

Contributors

PersonTokensPropCommitsCommitProp
christoph hellwigchristoph hellwig20265.37%327.27%
jens axboejens axboe4614.89%327.27%
shaohua lishaohua li278.74%19.09%
keith buschkeith busch175.50%19.09%
bart van asschebart van assche92.91%19.09%
robert elliottrobert elliott72.27%19.09%
lei minglei ming10.32%19.09%
Total309100.00%11100.00%

EXPORT_SYMBOL(blk_mq_alloc_tag_set);
void blk_mq_free_tag_set(struct blk_mq_tag_set *set) { int i; for (i = 0; i < nr_cpu_ids; i++) { if (set->tags[i]) blk_mq_free_rq_map(set, set->tags[i], i); } kfree(set->mq_map); set->mq_map = NULL; kfree(set->tags); set->tags = NULL; }

Contributors

PersonTokensPropCommitsCommitProp
christoph hellwigchristoph hellwig5267.53%233.33%
jens axboejens axboe1114.29%116.67%
lei minglei ming79.09%116.67%
robert elliottrobert elliott67.79%116.67%
keith buschkeith busch11.30%116.67%
Total77100.00%6100.00%

EXPORT_SYMBOL(blk_mq_free_tag_set);
int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr) { struct blk_mq_tag_set *set = q->tag_set; struct blk_mq_hw_ctx *hctx; int i, ret; if (!set || nr > set->queue_depth) return -EINVAL; ret = 0; queue_for_each_hw_ctx(q, hctx, i) { if (!hctx->tags) continue; ret = blk_mq_tag_update_depth(hctx->tags, nr); if (ret) break; } if (!ret) q->nr_requests = nr; return ret; }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe9292.00%150.00%
keith buschkeith busch88.00%150.00%
Total100100.00%2100.00%


void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues) { struct request_queue *q; if (nr_hw_queues > nr_cpu_ids) nr_hw_queues = nr_cpu_ids; if (nr_hw_queues < 1 || nr_hw_queues == set->nr_hw_queues) return; list_for_each_entry(q, &set->tag_list, tag_set_list) blk_mq_freeze_queue(q); set->nr_hw_queues = nr_hw_queues; list_for_each_entry(q, &set->tag_list, tag_set_list) { blk_mq_realloc_hw_ctxs(set, q); if (q->nr_hw_queues > 1) blk_queue_make_request(q, blk_mq_make_request); else blk_queue_make_request(q, blk_sq_make_request); blk_mq_queue_reinit(q, cpu_online_mask); } list_for_each_entry(q, &set->tag_list, tag_set_list) blk_mq_unfreeze_queue(q); }

Contributors

PersonTokensPropCommitsCommitProp
keith buschkeith busch120100.00%1100.00%
Total120100.00%1100.00%

EXPORT_SYMBOL_GPL(blk_mq_update_nr_hw_queues);
void blk_mq_disable_hotplug(void) { mutex_lock(&all_q_mutex); }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe13100.00%1100.00%
Total13100.00%1100.00%


void blk_mq_enable_hotplug(void) { mutex_unlock(&all_q_mutex); }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe13100.00%1100.00%
Total13100.00%1100.00%


static int __init blk_mq_init(void) { cpuhp_setup_state_multi(CPUHP_BLK_MQ_DEAD, "block/mq:dead", NULL, blk_mq_hctx_notify_dead); cpuhp_setup_state_nocalls(CPUHP_BLK_MQ_PREPARE, "block/mq:prepare", blk_mq_queue_reinit_prepare, blk_mq_queue_reinit_dead); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe1750.00%133.33%
thomas gleixnerthomas gleixner1029.41%133.33%
sebastian andrzej siewiorsebastian andrzej siewior720.59%133.33%
Total34100.00%3100.00%

subsys_initcall(blk_mq_init);

Overall Contributors

PersonTokensPropCommitsCommitProp
jens axboejens axboe540853.90%6031.41%
christoph hellwigchristoph hellwig198819.81%4322.51%
keith buschkeith busch5395.37%105.24%
ming leiming lei4284.27%115.76%
shaohua lishaohua li2772.76%63.14%
lei minglei ming2192.18%115.76%
ming linming lin1691.68%10.52%
omar sandovalomar sandoval1411.41%42.09%
jeff moyerjeff moyer1331.33%21.05%
mike snitzermike snitzer1251.25%31.57%
tejun heotejun heo1071.07%63.14%
akinobu mitaakinobu mita800.80%52.62%
sebastian andrzej siewiorsebastian andrzej siewior710.71%21.05%
thomas gleixnerthomas gleixner640.64%21.05%
michael christiemichael christie520.52%31.57%
catalin marinascatalin marinas270.27%10.52%
joe lawrencejoe lawrence250.25%10.52%
dan williamsdan williams250.25%10.52%
kent overstreetkent overstreet240.24%10.52%
paolo bonzinipaolo bonzini200.20%21.05%
nicholas bellingernicholas bellinger180.18%10.52%
robert elliottrobert elliott180.18%21.05%
lin minglin ming110.11%10.52%
hannes reineckehannes reinecke110.11%10.52%
bart van asschebart van assche90.09%10.52%
fang weifang wei90.09%10.52%
tony battersbytony battersby80.08%10.52%
david hildenbranddavid hildenbrand60.06%10.52%
gabriel krisman bertazigabriel krisman bertazi60.06%10.52%
chong yuanchong yuan50.05%10.52%
dave hansendave hansen30.03%10.52%
raghavendra k t* (same as raghavendra koushik)raghavendra k t* (same as raghavendra koushik)30.03%10.52%
bartlomiej zolnierkiewiczbartlomiej zolnierkiewicz20.02%10.52%
linus torvaldslinus torvalds20.02%10.52%
frederic weisbeckerfrederic weisbecker10.01%10.52%
Total10034100.00%191100.00%
Directory: block