// SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991, 1992 Linus Torvalds * Copyright (C) 1994, Karl Keyte: Added support for disk statistics * Elevator latency, (C) 2000 Andrea Arcangeli SuSE * Queue request tables / lock, selectable elevator, Jens Axboe * kernel-doc documentation started by NeilBrown * - July2000 * bio rewrite, highmem i/o, etc, Jens Axboe - may 2001 */ /* * This handles all read/write requests to block devices */ #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #define CREATE_TRACE_POINTS #include #include "blk.h" #include "blk-mq.h" #include "blk-mq-sched.h" #include "blk-pm.h" #include "blk-throttle.h" struct dentry *blk_debugfs_root; EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap); EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap); EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete); EXPORT_TRACEPOINT_SYMBOL_GPL(block_split); EXPORT_TRACEPOINT_SYMBOL_GPL(block_unplug); EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_insert); DEFINE_IDA(blk_queue_ida); /* * For queue allocation */ struct kmem_cache *blk_requestq_cachep; /* * Controlling structure to kblockd */ static struct workqueue_struct *kblockd_workqueue; /** * blk_queue_flag_set - atomically set a queue flag * @flag: flag to be set * @q: request queue */ void blk_queue_flag_set(unsigned int flag, struct request_queue *q) { set_bit(flag, &q->queue_flags); } EXPORT_SYMBOL(blk_queue_flag_set); /** * blk_queue_flag_clear - atomically clear a queue flag * @flag: flag to be cleared * @q: request queue */ void blk_queue_flag_clear(unsigned int flag, struct request_queue *q) { clear_bit(flag, &q->queue_flags); } EXPORT_SYMBOL(blk_queue_flag_clear); /** * blk_queue_flag_test_and_set - atomically test and set a queue flag * @flag: flag to be set * @q: request queue * * Returns the previous value of @flag - 0 if the flag was not set and 1 if * the flag was already set. */ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q) { return test_and_set_bit(flag, &q->queue_flags); } EXPORT_SYMBOL_GPL(blk_queue_flag_test_and_set); void blk_rq_init(struct request_queue *q, struct request *rq) { memset(rq, 0, sizeof(*rq)); INIT_LIST_HEAD(&rq->queuelist); rq->q = q; rq->__sector = (sector_t) -1; INIT_HLIST_NODE(&rq->hash); RB_CLEAR_NODE(&rq->rb_node); rq->tag = BLK_MQ_NO_TAG; rq->internal_tag = BLK_MQ_NO_TAG; rq->start_time_ns = ktime_get_ns(); rq->part = NULL; blk_crypto_rq_set_defaults(rq); } EXPORT_SYMBOL(blk_rq_init); #define REQ_OP_NAME(name) [REQ_OP_##name] = #name static const char *const blk_op_name[] = { REQ_OP_NAME(READ), REQ_OP_NAME(WRITE), REQ_OP_NAME(FLUSH), REQ_OP_NAME(DISCARD), REQ_OP_NAME(SECURE_ERASE), REQ_OP_NAME(ZONE_RESET), REQ_OP_NAME(ZONE_RESET_ALL), REQ_OP_NAME(ZONE_OPEN), REQ_OP_NAME(ZONE_CLOSE), REQ_OP_NAME(ZONE_FINISH), REQ_OP_NAME(ZONE_APPEND), REQ_OP_NAME(WRITE_SAME), REQ_OP_NAME(WRITE_ZEROES), REQ_OP_NAME(DRV_IN), REQ_OP_NAME(DRV_OUT), }; #undef REQ_OP_NAME /** * blk_op_str - Return string XXX in the REQ_OP_XXX. * @op: REQ_OP_XXX. * * Description: Centralize block layer function to convert REQ_OP_XXX into * string format. Useful in the debugging and tracing bio or request. For * invalid REQ_OP_XXX it returns string "UNKNOWN". */ inline const char *blk_op_str(unsigned int op) { const char *op_str = "UNKNOWN"; if (op < ARRAY_SIZE(blk_op_name) && blk_op_name[op]) op_str = blk_op_name[op]; return op_str; } EXPORT_SYMBOL_GPL(blk_op_str); static const struct { int errno; const char *name; } blk_errors[] = { [BLK_STS_OK] = { 0, "" }, [BLK_STS_NOTSUPP] = { -EOPNOTSUPP, "operation not supported" }, [BLK_STS_TIMEOUT] = { -ETIMEDOUT, "timeout" }, [BLK_STS_NOSPC] = { -ENOSPC, "critical space allocation" }, [BLK_STS_TRANSPORT] = { -ENOLINK, "recoverable transport" }, [BLK_STS_TARGET] = { -EREMOTEIO, "critical target" }, [BLK_STS_NEXUS] = { -EBADE, "critical nexus" }, [BLK_STS_MEDIUM] = { -ENODATA, "critical medium" }, [BLK_STS_PROTECTION] = { -EILSEQ, "protection" }, [BLK_STS_RESOURCE] = { -ENOMEM, "kernel resource" }, [BLK_STS_DEV_RESOURCE] = { -EBUSY, "device resource" }, [BLK_STS_AGAIN] = { -EAGAIN, "nonblocking retry" }, /* device mapper special case, should not leak out: */ [BLK_STS_DM_REQUEUE] = { -EREMCHG, "dm internal retry" }, /* zone device specific errors */ [BLK_STS_ZONE_OPEN_RESOURCE] = { -ETOOMANYREFS, "open zones exceeded" }, [BLK_STS_ZONE_ACTIVE_RESOURCE] = { -EOVERFLOW, "active zones exceeded" }, /* everything else not covered above: */ [BLK_STS_IOERR] = { -EIO, "I/O" }, }; blk_status_t errno_to_blk_status(int errno) { int i; for (i = 0; i < ARRAY_SIZE(blk_errors); i++) { if (blk_errors[i].errno == errno) return (__force blk_status_t)i; } return BLK_STS_IOERR; } EXPORT_SYMBOL_GPL(errno_to_blk_status); int blk_status_to_errno(blk_status_t status) { int idx = (__force int)status; if (WARN_ON_ONCE(idx >= ARRAY_SIZE(blk_errors))) return -EIO; return blk_errors[idx].errno; } EXPORT_SYMBOL_GPL(blk_status_to_errno); static void print_req_error(struct request *req, blk_status_t status, const char *caller) { int idx = (__force int)status; if (WARN_ON_ONCE(idx >= ARRAY_SIZE(blk_errors))) return; printk_ratelimited(KERN_ERR "%s: %s error, dev %s, sector %llu op 0x%x:(%s) flags 0x%x " "phys_seg %u prio class %u\n", caller, blk_errors[idx].name, req->rq_disk ? req->rq_disk->disk_name : "?", blk_rq_pos(req), req_op(req), blk_op_str(req_op(req)), req->cmd_flags & ~REQ_OP_MASK, req->nr_phys_segments, IOPRIO_PRIO_CLASS(req->ioprio)); } static void req_bio_endio(struct request *rq, struct bio *bio, unsigned int nbytes, blk_status_t error) { if (error) bio->bi_status = error; if (unlikely(rq->rq_flags & RQF_QUIET)) bio_set_flag(bio, BIO_QUIET); bio_advance(bio, nbytes); if (req_op(rq) == REQ_OP_ZONE_APPEND && error == BLK_STS_OK) { /* * Partial zone append completions cannot be supported as the * BIO fragments may end up not being written sequentially. */ if (bio->bi_iter.bi_size) bio->bi_status = BLK_STS_IOERR; else bio->bi_iter.bi_sector = rq->__sector; } /* don't actually finish bio if it's part of flush sequence */ if (bio->bi_iter.bi_size == 0 && !(rq->rq_flags & RQF_FLUSH_SEQ)) bio_endio(bio); } void blk_dump_rq_flags(struct request *rq, char *msg) { printk(KERN_INFO "%s: dev %s: flags=%llx\n", msg, rq->rq_disk ? rq->rq_disk->disk_name : "?", (unsigned long long) rq->cmd_flags); printk(KERN_INFO " sector %llu, nr/cnr %u/%u\n", (unsigned long long)blk_rq_pos(rq), blk_rq_sectors(rq), blk_rq_cur_sectors(rq)); printk(KERN_INFO " bio %p, biotail %p, len %u\n", rq->bio, rq->biotail, blk_rq_bytes(rq)); } EXPORT_SYMBOL(blk_dump_rq_flags); /** * blk_sync_queue - cancel any pending callbacks on a queue * @q: the queue * * Description: * The block layer may perform asynchronous callback activity * on a queue, such as calling the unplug function after a timeout. * A block device may call blk_sync_queue to ensure that any * such activity is cancelled, thus allowing it to release resources * that the callbacks might use. The caller must already have made sure * that its ->submit_bio will not re-add plugging prior to calling * this function. * * This function does not cancel any asynchronous activity arising * out of elevator or throttling code. That would require elevator_exit() * and blkcg_exit_queue() to be called with queue lock initialized. * */ void blk_sync_queue(struct request_queue *q) { del_timer_sync(&q->timeout); cancel_work_sync(&q->timeout_work); } EXPORT_SYMBOL(blk_sync_queue); /** * blk_set_pm_only - increment pm_only counter * @q: request queue pointer */ void blk_set_pm_only(struct request_queue *q) { atomic_inc(&q->pm_only); } EXPORT_SYMBOL_GPL(blk_set_pm_only); void blk_clear_pm_only(struct request_queue *q) { int pm_only; pm_only = atomic_dec_return(&q->pm_only); WARN_ON_ONCE(pm_only < 0); if (pm_only == 0) wake_up_all(&q->mq_freeze_wq); } EXPORT_SYMBOL_GPL(blk_clear_pm_only); /** * blk_put_queue - decrement the request_queue refcount * @q: the request_queue structure to decrement the refcount for * * Decrements the refcount of the request_queue kobject. When this reaches 0 * we'll have blk_release_queue() called. * * Context: Any context, but the last reference must not be dropped from * atomic context. */ void blk_put_queue(struct request_queue *q) { kobject_put(&q->kobj); } EXPORT_SYMBOL(blk_put_queue); void blk_queue_start_drain(struct request_queue *q) { /* * When queue DYING flag is set, we need to block new req * entering queue, so we call blk_freeze_queue_start() to * prevent I/O from crossing blk_queue_enter(). */ blk_freeze_queue_start(q); if (queue_is_mq(q)) blk_mq_wake_waiters(q); /* Make blk_queue_enter() reexamine the DYING flag. */ wake_up_all(&q->mq_freeze_wq); } void blk_set_queue_dying(struct request_queue *q) { blk_queue_flag_set(QUEUE_FLAG_DYING, q); blk_queue_start_drain(q); } EXPORT_SYMBOL_GPL(blk_set_queue_dying); /** * blk_cleanup_queue - shutdown a request queue * @q: request queue to shutdown * * Mark @q DYING, drain all pending requests, mark @q DEAD, destroy and * put it. All future requests will be failed immediately with -ENODEV. * * Context: can sleep */ void blk_cleanup_queue(struct request_queue *q) { /* cannot be called from atomic context */ might_sleep(); WARN_ON_ONCE(blk_queue_registered(q)); /* mark @q DYING, no new request or merges will be allowed afterwards */ blk_set_queue_dying(q); blk_queue_flag_set(QUEUE_FLAG_NOMERGES, q); blk_queue_flag_set(QUEUE_FLAG_NOXMERGES, q); /* * Drain all requests queued before DYING marking. Set DEAD flag to * prevent that blk_mq_run_hw_queues() accesses the hardware queues * after draining finished. */ blk_freeze_queue(q); blk_queue_flag_set(QUEUE_FLAG_DEAD, q); blk_sync_queue(q); if (queue_is_mq(q)) blk_mq_exit_queue(q); /* * In theory, request pool of sched_tags belongs to request queue. * However, the current implementation requires tag_set for freeing * requests, so free the pool now. * * Queue has become frozen, there can't be any in-queue requests, so * it is safe to free requests now. */ mutex_lock(&q->sysfs_lock); if (q->elevator) blk_mq_sched_free_rqs(q); mutex_unlock(&q->sysfs_lock); percpu_ref_exit(&q->q_usage_counter); /* @q is and will stay empty, shutdown and put */ blk_put_queue(q); } EXPORT_SYMBOL(blk_cleanup_queue); static bool blk_try_enter_queue(struct request_queue *q, bool pm) { rcu_read_lock(); if (!percpu_ref_tryget_live(&q->q_usage_counter)) goto fail; /* * The code that increments the pm_only counter must ensure that the * counter is globally visible before the queue is unfrozen. */ if (blk_queue_pm_only(q) && (!pm || queue_rpm_status(q) == RPM_SUSPENDED)) goto fail_put; rcu_read_unlock(); return true; fail_put: percpu_ref_put(&q->q_usage_counter); fail: rcu_read_unlock(); return false; } /** * blk_queue_enter() - try to increase q->q_usage_counter * @q: request queue pointer * @flags: BLK_MQ_REQ_NOWAIT and/or BLK_MQ_REQ_PM */ int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags) { const bool pm = flags & BLK_MQ_REQ_PM; while (!blk_try_enter_queue(q, pm)) { if (flags & BLK_MQ_REQ_NOWAIT) return -EBUSY; /* * read pair of barrier in blk_freeze_queue_start(), we need to * order reading __PERCPU_REF_DEAD flag of .q_usage_counter and * reading .mq_freeze_depth or queue dying flag, otherwise the * following wait may never return if the two reads are * reordered. */ smp_rmb(); wait_event(q->mq_freeze_wq, (!q->mq_freeze_depth && blk_pm_resume_queue(pm, q)) || blk_queue_dying(q)); if (blk_queue_dying(q)) return -ENODEV; } return 0; } static inline int bio_queue_enter(struct bio *bio) { struct gendisk *disk = bio->bi_bdev->bd_disk; struct request_queue *q = disk->queue; while (!blk_try_enter_queue(q, false)) { if (bio->bi_opf & REQ_NOWAIT) { if (test_bit(GD_DEAD, &disk->state)) goto dead; bio_wouldblock_error(bio); return -EBUSY; } /* * read pair of barrier in blk_freeze_queue_start(), we need to * order reading __PERCPU_REF_DEAD flag of .q_usage_counter and * reading .mq_freeze_depth or queue dying flag, otherwise the * following wait may never return if the two reads are * reordered. */ smp_rmb(); wait_event(q->mq_freeze_wq, (!q->mq_freeze_depth && blk_pm_resume_queue(false, q)) || test_bit(GD_DEAD, &disk->state)); if (test_bit(GD_DEAD, &disk->state)) goto dead; } return 0; dead: bio_io_error(bio); return -ENODEV; } void blk_queue_exit(struct request_queue *q) { percpu_ref_put(&q->q_usage_counter); } static void blk_queue_usage_counter_release(struct percpu_ref *ref) { struct request_queue *q = container_of(ref, struct request_queue, q_usage_counter); wake_up_all(&q->mq_freeze_wq); } static void blk_rq_timed_out_timer(struct timer_list *t) { struct request_queue *q = from_timer(q, t, timeout); kblockd_schedule_work(&q->timeout_work); } static void blk_timeout_work(struct work_struct *work) { } struct request_queue *blk_alloc_queue(int node_id) { struct request_queue *q; int ret; q = kmem_cache_alloc_node(blk_requestq_cachep, GFP_KERNEL | __GFP_ZERO, node_id); if (!q) return NULL; q->last_merge = NULL; q->id = ida_simple_get(&blk_queue_ida, 0, 0, GFP_KERNEL); if (q->id < 0) goto fail_q; ret = bioset_init(&q->bio_split, BIO_POOL_SIZE, 0, 0); if (ret) goto fail_id; q->stats = blk_alloc_queue_stats(); if (!q->stats) goto fail_split; q->node = node_id; atomic_set(&q->nr_active_requests_shared_tags, 0); timer_setup(&q->timeout, blk_rq_timed_out_timer, 0); INIT_WORK(&q->timeout_work, blk_timeout_work); INIT_LIST_HEAD(&q->icq_list); #ifdef CONFIG_BLK_CGROUP INIT_LIST_HEAD(&q->blkg_list); #endif kobject_init(&q->kobj, &blk_queue_ktype); mutex_init(&q->debugfs_mutex); mutex_init(&q->sysfs_lock); mutex_init(&q->sysfs_dir_lock); spin_lock_init(&q->queue_lock); init_waitqueue_head(&q->mq_freeze_wq); mutex_init(&q->mq_freeze_lock); /* * Init percpu_ref in atomic mode so that it's faster to shutdown. * See blk_register_queue() for details. */ if (percpu_ref_init(&q->q_usage_counter, blk_queue_usage_counter_release, PERCPU_REF_INIT_ATOMIC, GFP_KERNEL)) goto fail_stats; if (blkcg_init_queue(q)) goto fail_ref; blk_queue_dma_alignment(q, 511); blk_set_default_limits(&q->limits); q->nr_requests = BLKDEV_DEFAULT_RQ; return q; fail_ref: percpu_ref_exit(&q->q_usage_counter); fail_stats: blk_free_queue_stats(q->stats); fail_split: bioset_exit(&q->bio_split); fail_id: ida_simple_remove(&blk_queue_ida, q->id); fail_q: kmem_cache_free(blk_requestq_cachep, q); return NULL; } /** * blk_get_queue - increment the request_queue refcount * @q: the request_queue structure to increment the refcount for * * Increment the refcount of the request_queue kobject. * * Context: Any context. */ bool blk_get_queue(struct request_queue *q) { if (likely(!blk_queue_dying(q))) { __blk_get_queue(q); return true; } return false; } EXPORT_SYMBOL(blk_get_queue); /** * blk_get_request - allocate a request * @q: request queue to allocate a request for * @op: operation (REQ_OP_*) and REQ_* flags, e.g. REQ_SYNC. * @flags: BLK_MQ_REQ_* flags, e.g. BLK_MQ_REQ_NOWAIT. */ struct request *blk_get_request(struct request_queue *q, unsigned int op, blk_mq_req_flags_t flags) { struct request *req; WARN_ON_ONCE(op & REQ_NOWAIT); WARN_ON_ONCE(flags & ~(BLK_MQ_REQ_NOWAIT | BLK_MQ_REQ_PM)); req = blk_mq_alloc_request(q, op, flags); if (!IS_ERR(req) && q->mq_ops->initialize_rq_fn) q->mq_ops->initialize_rq_fn(req); return req; } EXPORT_SYMBOL(blk_get_request); void blk_put_request(struct request *req) { blk_mq_free_request(req); } EXPORT_SYMBOL(blk_put_request); static void handle_bad_sector(struct bio *bio, sector_t maxsector) { char b[BDEVNAME_SIZE]; pr_info_ratelimited("%s: attempt to access beyond end of device\n" "%s: rw=%d, want=%llu, limit=%llu\n", current->comm, bio_devname(bio, b), bio->bi_opf, bio_end_sector(bio), maxsector); } #ifdef CONFIG_FAIL_MAKE_REQUEST static DECLARE_FAULT_ATTR(fail_make_request); static int __init setup_fail_make_request(char *str) { return setup_fault_attr(&fail_make_request, str); } __setup("fail_make_request=", setup_fail_make_request); static bool should_fail_request(struct block_device *part, unsigned int bytes) { return part->bd_make_it_fail && should_fail(&fail_make_request, bytes); } static int __init fail_make_request_debugfs(void) { struct dentry *dir = fault_create_debugfs_attr("fail_make_request", NULL, &fail_make_request); return PTR_ERR_OR_ZERO(dir); } late_initcall(fail_make_request_debugfs); #else /* CONFIG_FAIL_MAKE_REQUEST */ static inline bool should_fail_request(struct block_device *part, unsigned int bytes) { return false; } #endif /* CONFIG_FAIL_MAKE_REQUEST */ static inline bool bio_check_ro(struct bio *bio) { if (op_is_write(bio_op(bio)) && bdev_read_only(bio->bi_bdev)) { char b[BDEVNAME_SIZE]; if (op_is_flush(bio->bi_opf) && !bio_sectors(bio)) return false; WARN_ONCE(1, "Trying to write to read-only block-device %s (partno %d)\n", bio_devname(bio, b), bio->bi_bdev->bd_partno); /* Older lvm-tools actually trigger this */ return false; } return false; } static noinline int should_fail_bio(struct bio *bio) { if (should_fail_request(bdev_whole(bio->bi_bdev), bio->bi_iter.bi_size)) return -EIO; return 0; } ALLOW_ERROR_INJECTION(should_fail_bio, ERRNO); /* * Check whether this bio extends beyond the end of the device or partition. * This may well happen - the kernel calls bread() without checking the size of * the device, e.g., when mounting a file system. */ static inline int bio_check_eod(struct bio *bio) { sector_t maxsector = bdev_nr_sectors(bio->bi_bdev); unsigned int nr_sectors = bio_sectors(bio); if (nr_sectors && maxsector && (nr_sectors > maxsector || bio->bi_iter.bi_sector > maxsector - nr_sectors)) { handle_bad_sector(bio, maxsector); return -EIO; } return 0; } /* * Remap block n of partition p to block n+start(p) of the disk. */ static int blk_partition_remap(struct bio *bio) { struct block_device *p = bio->bi_bdev; if (unlikely(should_fail_request(p, bio->bi_iter.bi_size))) return -EIO; if (bio_sectors(bio)) { bio->bi_iter.bi_sector += p->bd_start_sect; trace_block_bio_remap(bio, p->bd_dev, bio->bi_iter.bi_sector - p->bd_start_sect); } bio_set_flag(bio, BIO_REMAPPED); return 0; } /* * Check write append to a zoned block device. */ static inline blk_status_t blk_check_zone_append(struct request_queue *q, struct bio *bio) { sector_t pos = bio->bi_iter.bi_sector; int nr_sectors = bio_sectors(bio); /* Only applicable to zoned block devices */ if (!blk_queue_is_zoned(q)) return BLK_STS_NOTSUPP; /* The bio sector must point to the start of a sequential zone */ if (pos & (blk_queue_zone_sectors(q) - 1) || !blk_queue_zone_is_seq(q, pos)) return BLK_STS_IOERR; /* * Not allowed to cross zone boundaries. Otherwise, the BIO will be * split and could result in non-contiguous sectors being written in * different zones. */ if (nr_sectors > q->limits.chunk_sectors) return BLK_STS_IOERR; /* Make sure the BIO is small enough and will not get split */ if (nr_sectors > q->limits.max_zone_append_sectors) return BLK_STS_IOERR; bio->bi_opf |= REQ_NOMERGE; return BLK_STS_OK; } static noinline_for_stack bool submit_bio_checks(struct bio *bio) { struct block_device *bdev = bio->bi_bdev; struct request_queue *q = bdev->bd_disk->queue; blk_status_t status = BLK_STS_IOERR; struct blk_plug *plug; might_sleep(); plug = blk_mq_plug(q, bio); if (plug && plug->nowait) bio->bi_opf |= REQ_NOWAIT; /* * For a REQ_NOWAIT based request, return -EOPNOTSUPP * if queue does not support NOWAIT. */ if ((bio->bi_opf & REQ_NOWAIT) && !blk_queue_nowait(q)) goto not_supported; if (should_fail_bio(bio)) goto end_io; if (unlikely(bio_check_ro(bio))) goto end_io; if (!bio_flagged(bio, BIO_REMAPPED)) { if (unlikely(bio_check_eod(bio))) goto end_io; if (bdev->bd_partno && unlikely(blk_partition_remap(bio))) goto end_io; } /* * Filter flush bio's early so that bio based drivers without flush * support don't have to worry about them. */ if (op_is_flush(bio->bi_opf) && !test_bit(QUEUE_FLAG_WC, &q->queue_flags)) { bio->bi_opf &= ~(REQ_PREFLUSH | REQ_FUA); if (!bio_sectors(bio)) { status = BLK_STS_OK; goto end_io; } } if (!test_bit(QUEUE_FLAG_POLL, &q->queue_flags)) bio_clear_polled(bio); switch (bio_op(bio)) { case REQ_OP_DISCARD: if (!blk_queue_discard(q)) goto not_supported; break; case REQ_OP_SECURE_ERASE: if (!blk_queue_secure_erase(q)) goto not_supported; break; case REQ_OP_WRITE_SAME: if (!q->limits.max_write_same_sectors) goto not_supported; break; case REQ_OP_ZONE_APPEND: status = blk_check_zone_append(q, bio); if (status != BLK_STS_OK) goto end_io; break; case REQ_OP_ZONE_RESET: case REQ_OP_ZONE_OPEN: case REQ_OP_ZONE_CLOSE: case REQ_OP_ZONE_FINISH: if (!blk_queue_is_zoned(q)) goto not_supported; break; case REQ_OP_ZONE_RESET_ALL: if (!blk_queue_is_zoned(q) || !blk_queue_zone_resetall(q)) goto not_supported; break; case REQ_OP_WRITE_ZEROES: if (!q->limits.max_write_zeroes_sectors) goto not_supported; break; default: break; } /* * Various block parts want %current->io_context, so allocate it up * front rather than dealing with lots of pain to allocate it only * where needed. This may fail and the block layer knows how to live * with it. */ if (unlikely(!current->io_context)) create_task_io_context(current, GFP_ATOMIC, q->node); if (blk_throtl_bio(bio)) { blkcg_bio_issue_init(bio); return false; } blk_cgroup_bio_start(bio); blkcg_bio_issue_init(bio); if (!bio_flagged(bio, BIO_TRACE_COMPLETION)) { trace_block_bio_queue(bio); /* Now that enqueuing has been traced, we need to trace * completion as well. */ bio_set_flag(bio, BIO_TRACE_COMPLETION); } return true; not_supported: status = BLK_STS_NOTSUPP; end_io: bio->bi_status = status; bio_endio(bio); return false; } static void __submit_bio(struct bio *bio) { struct gendisk *disk = bio->bi_bdev->bd_disk; if (unlikely(bio_queue_enter(bio) != 0)) return; if (!submit_bio_checks(bio) || !blk_crypto_bio_prep(&bio)) goto queue_exit; if (!disk->fops->submit_bio) { blk_mq_submit_bio(bio); return; } disk->fops->submit_bio(bio); queue_exit: blk_queue_exit(disk->queue); } /* * The loop in this function may be a bit non-obvious, and so deserves some * explanation: * * - Before entering the loop, bio->bi_next is NULL (as all callers ensure * that), so we have a list with a single bio. * - We pretend that we have just taken it off a longer list, so we assign * bio_list to a pointer to the bio_list_on_stack, thus initialising the * bio_list of new bios to be added. ->submit_bio() may indeed add some more * bios through a recursive call to submit_bio_noacct. If it did, we find a * non-NULL value in bio_list and re-enter the loop from the top. * - In this case we really did just take the bio of the top of the list (no * pretending) and so remove it from bio_list, and call into ->submit_bio() * again. * * bio_list_on_stack[0] contains bios submitted by the current ->submit_bio. * bio_list_on_stack[1] contains bios that were submitted before the current * ->submit_bio_bio, but that haven't been processed yet. */ static void __submit_bio_noacct(struct bio *bio) { struct bio_list bio_list_on_stack[2]; BUG_ON(bio->bi_next); bio_list_init(&bio_list_on_stack[0]); current->bio_list = bio_list_on_stack; do { struct request_queue *q = bio->bi_bdev->bd_disk->queue; struct bio_list lower, same; /* * Create a fresh bio_list for all subordinate requests. */ bio_list_on_stack[1] = bio_list_on_stack[0]; bio_list_init(&bio_list_on_stack[0]); __submit_bio(bio); /* * Sort new bios into those for a lower level and those for the * same level. */ bio_list_init(&lower); bio_list_init(&same); while ((bio = bio_list_pop(&bio_list_on_stack[0])) != NULL) if (q == bio->bi_bdev->bd_disk->queue) bio_list_add(&same, bio); else bio_list_add(&lower, bio); /* * Now assemble so we handle the lowest level first. */ bio_list_merge(&bio_list_on_stack[0], &lower); bio_list_merge(&bio_list_on_stack[0], &same); bio_list_merge(&bio_list_on_stack[0], &bio_list_on_stack[1]); } while ((bio = bio_list_pop(&bio_list_on_stack[0]))); current->bio_list = NULL; } static void __submit_bio_noacct_mq(struct bio *bio) { struct bio_list bio_list[2] = { }; current->bio_list = bio_list; do { __submit_bio(bio); } while ((bio = bio_list_pop(&bio_list[0]))); current->bio_list = NULL; } /** * submit_bio_noacct - re-submit a bio to the block device layer for I/O * @bio: The bio describing the location in memory and on the device. * * This is a version of submit_bio() that shall only be used for I/O that is * resubmitted to lower level drivers by stacking block drivers. All file * systems and other upper level users of the block layer should use * submit_bio() instead. */ void submit_bio_noacct(struct bio *bio) { /* * We only want one ->submit_bio to be active at a time, else stack * usage with stacked devices could be a problem. Use current->bio_list * to collect a list of requests submited by a ->submit_bio method while * it is active, and then process them after it returned. */ if (current->bio_list) bio_list_add(¤t->bio_list[0], bio); else if (!bio->bi_bdev->bd_disk->fops->submit_bio) __submit_bio_noacct_mq(bio); else __submit_bio_noacct(bio); } EXPORT_SYMBOL(submit_bio_noacct); /** * submit_bio - submit a bio to the block device layer for I/O * @bio: The &struct bio which describes the I/O * * submit_bio() is used to submit I/O requests to block devices. It is passed a * fully set up &struct bio that describes the I/O that needs to be done. The * bio will be send to the device described by the bi_bdev field. * * The success/failure status of the request, along with notification of * completion, is delivered asynchronously through the ->bi_end_io() callback * in @bio. The bio must NOT be touched by thecaller until ->bi_end_io() has * been called. */ void submit_bio(struct bio *bio) { if (blkcg_punt_bio_submit(bio)) return; /* * If it's a regular read/write or a barrier with data attached, * go through the normal accounting stuff before submission. */ if (bio_has_data(bio)) { unsigned int count; if (unlikely(bio_op(bio) == REQ_OP_WRITE_SAME)) count = queue_logical_block_size( bio->bi_bdev->bd_disk->queue) >> 9; else count = bio_sectors(bio); if (op_is_write(bio_op(bio))) { count_vm_events(PGPGOUT, count); } else { task_io_account_read(bio->bi_iter.bi_size); count_vm_events(PGPGIN, count); } } /* * If we're reading data that is part of the userspace workingset, count * submission time as memory stall. When the device is congested, or * the submitting cgroup IO-throttled, submission can be a significant * part of overall IO time. */ if (unlikely(bio_op(bio) == REQ_OP_READ && bio_flagged(bio, BIO_WORKINGSET))) { unsigned long pflags; psi_memstall_enter(&pflags); submit_bio_noacct(bio); psi_memstall_leave(&pflags); return; } submit_bio_noacct(bio); } EXPORT_SYMBOL(submit_bio); /** * bio_poll - poll for BIO completions * @bio: bio to poll for * @flags: BLK_POLL_* flags that control the behavior * * Poll for completions on queue associated with the bio. Returns number of * completed entries found. * * Note: the caller must either be the context that submitted @bio, or * be in a RCU critical section to prevent freeing of @bio. */ int bio_poll(struct bio *bio, unsigned int flags) { struct request_queue *q = bio->bi_bdev->bd_disk->queue; blk_qc_t cookie = READ_ONCE(bio->bi_cookie); int ret; if (cookie == BLK_QC_T_NONE || !test_bit(QUEUE_FLAG_POLL, &q->queue_flags)) return 0; if (current->plug) blk_flush_plug_list(current->plug, false); if (blk_queue_enter(q, BLK_MQ_REQ_NOWAIT)) return 0; if (WARN_ON_ONCE(!queue_is_mq(q))) ret = 0; /* not yet implemented, should not happen */ else ret = blk_mq_poll(q, cookie, flags); blk_queue_exit(q); return ret; } EXPORT_SYMBOL_GPL(bio_poll); /* * Helper to implement file_operations.iopoll. Requires the bio to be stored * in iocb->private, and cleared before freeing the bio. */ int iocb_bio_iopoll(struct kiocb *kiocb, unsigned int flags) { struct bio *bio; int ret = 0; /* * Note: the bio cache only uses SLAB_TYPESAFE_BY_RCU, so bio can * point to a freshly allocated bio at this point. If that happens * we have a few cases to consider: * * 1) the bio is beeing initialized and bi_bdev is NULL. We can just * simply nothing in this case * 2) the bio points to a not poll enabled device. bio_poll will catch * this and return 0 * 3) the bio points to a poll capable device, including but not * limited to the one that the original bio pointed to. In this * case we will call into the actual poll method and poll for I/O, * even if we don't need to, but it won't cause harm either. * * For cases 2) and 3) above the RCU grace period ensures that bi_bdev * is still allocated. Because partitions hold a reference to the whole * device bdev and thus disk, the disk is also still valid. Grabbing * a reference to the queue in bio_poll() ensures the hctxs and requests * are still valid as well. */ rcu_read_lock(); bio = READ_ONCE(kiocb->private); if (bio && bio->bi_bdev) ret = bio_poll(bio, flags); rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(iocb_bio_iopoll); /** * blk_cloned_rq_check_limits - Helper function to check a cloned request * for the new queue limits * @q: the queue * @rq: the request being checked * * Description: * @rq may have been made based on weaker limitations of upper-level queues * in request stacking drivers, and it may violate the limitation of @q. * Since the block layer and the underlying device driver trust @rq * after it is inserted to @q, it should be checked against @q before * the insertion using this generic function. * * Request stacking drivers like request-based dm may change the queue * limits when retrying requests on other queues. Those requests need * to be checked against the new queue limits again during dispatch. */ static blk_status_t blk_cloned_rq_check_limits(struct request_queue *q, struct request *rq) { unsigned int max_sectors = blk_queue_get_max_sectors(q, req_op(rq)); if (blk_rq_sectors(rq) > max_sectors) { /* * SCSI device does not have a good way to return if * Write Same/Zero is actually supported. If a device rejects * a non-read/write command (discard, write same,etc.) the * low-level device driver will set the relevant queue limit to * 0 to prevent blk-lib from issuing more of the offending * operations. Commands queued prior to the queue limit being * reset need to be completed with BLK_STS_NOTSUPP to avoid I/O * errors being propagated to upper layers. */ if (max_sectors == 0) return BLK_STS_NOTSUPP; printk(KERN_ERR "%s: over max size limit. (%u > %u)\n", __func__, blk_rq_sectors(rq), max_sectors); return BLK_STS_IOERR; } /* * The queue settings related to segment counting may differ from the * original queue. */ rq->nr_phys_segments = blk_recalc_rq_segments(rq); if (rq->nr_phys_segments > queue_max_segments(q)) { printk(KERN_ERR "%s: over max segments limit. (%hu > %hu)\n", __func__, rq->nr_phys_segments, queue_max_segments(q)); return BLK_STS_IOERR; } return BLK_STS_OK; } /** * blk_insert_cloned_request - Helper for stacking drivers to submit a request * @q: the queue to submit the request * @rq: the request being queued */ blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *rq) { blk_status_t ret; ret = blk_cloned_rq_check_limits(q, rq); if (ret != BLK_STS_OK) return ret; if (rq->rq_disk && should_fail_request(rq->rq_disk->part0, blk_rq_bytes(rq))) return BLK_STS_IOERR; if (blk_crypto_insert_cloned_request(rq)) return BLK_STS_IOERR; blk_account_io_start(rq); /* * Since we have a scheduler attached on the top device, * bypass a potential scheduler on the bottom device for * insert. */ return blk_mq_request_issue_directly(rq, true); } EXPORT_SYMBOL_GPL(blk_insert_cloned_request); /** * blk_rq_err_bytes - determine number of bytes till the next failure boundary * @rq: request to examine * * Description: * A request could be merge of IOs which require different failure * handling. This function determines the number of bytes which * can be failed from the beginning of the request without * crossing into area which need to be retried further. * * Return: * The number of bytes to fail. */ unsigned int blk_rq_err_bytes(const struct request *rq) { unsigned int ff = rq->cmd_flags & REQ_FAILFAST_MASK; unsigned int bytes = 0; struct bio *bio; if (!(rq->rq_flags & RQF_MIXED_MERGE)) return blk_rq_bytes(rq); /* * Currently the only 'mixing' which can happen is between * different fastfail types. We can safely fail portions * which have all the failfast bits that the first one has - * the ones which are at least as eager to fail as the first * one. */ for (bio = rq->bio; bio; bio = bio->bi_next) { if ((bio->bi_opf & ff) != ff) break; bytes += bio->bi_iter.bi_size; } /* this could lead to infinite loop */ BUG_ON(blk_rq_bytes(rq) && !bytes); return bytes; } EXPORT_SYMBOL_GPL(blk_rq_err_bytes); static void update_io_ticks(struct block_device *part, unsigned long now, bool end) { unsigned long stamp; again: stamp = READ_ONCE(part->bd_stamp); if (unlikely(time_after(now, stamp))) { if (likely(cmpxchg(&part->bd_stamp, stamp, now) == stamp)) __part_stat_add(part, io_ticks, end ? now - stamp : 1); } if (part->bd_partno) { part = bdev_whole(part); goto again; } } static void blk_account_io_completion(struct request *req, unsigned int bytes) { if (req->part && blk_do_io_stat(req)) { const int sgrp = op_stat_group(req_op(req)); part_stat_lock(); part_stat_add(req->part, sectors[sgrp], bytes >> 9); part_stat_unlock(); } } void __blk_account_io_done(struct request *req, u64 now) { const int sgrp = op_stat_group(req_op(req)); part_stat_lock(); update_io_ticks(req->part, jiffies, true); part_stat_inc(req->part, ios[sgrp]); part_stat_add(req->part, nsecs[sgrp], now - req->start_time_ns); part_stat_unlock(); } void __blk_account_io_start(struct request *rq) { /* passthrough requests can hold bios that do not have ->bi_bdev set */ if (rq->bio && rq->bio->bi_bdev) rq->part = rq->bio->bi_bdev; else rq->part = rq->rq_disk->part0; part_stat_lock(); update_io_ticks(rq->part, jiffies, false); part_stat_unlock(); } static unsigned long __part_start_io_acct(struct block_device *part, unsigned int sectors, unsigned int op) { const int sgrp = op_stat_group(op); unsigned long now = READ_ONCE(jiffies); part_stat_lock(); update_io_ticks(part, now, false); part_stat_inc(part, ios[sgrp]); part_stat_add(part, sectors[sgrp], sectors); part_stat_local_inc(part, in_flight[op_is_write(op)]); part_stat_unlock(); return now; } /** * bio_start_io_acct - start I/O accounting for bio based drivers * @bio: bio to start account for * * Returns the start time that should be passed back to bio_end_io_acct(). */ unsigned long bio_start_io_acct(struct bio *bio) { return __part_start_io_acct(bio->bi_bdev, bio_sectors(bio), bio_op(bio)); } EXPORT_SYMBOL_GPL(bio_start_io_acct); unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors, unsigned int op) { return __part_start_io_acct(disk->part0, sectors, op); } EXPORT_SYMBOL(disk_start_io_acct); static void __part_end_io_acct(struct block_device *part, unsigned int op, unsigned long start_time) { const int sgrp = op_stat_group(op); unsigned long now = READ_ONCE(jiffies); unsigned long duration = now - start_time; part_stat_lock(); update_io_ticks(part, now, true); part_stat_add(part, nsecs[sgrp], jiffies_to_nsecs(duration)); part_stat_local_dec(part, in_flight[op_is_write(op)]); part_stat_unlock(); } void bio_end_io_acct_remapped(struct bio *bio, unsigned long start_time, struct block_device *orig_bdev) { __part_end_io_acct(orig_bdev, bio_op(bio), start_time); } EXPORT_SYMBOL_GPL(bio_end_io_acct_remapped); void disk_end_io_acct(struct gendisk *disk, unsigned int op, unsigned long start_time) { __part_end_io_acct(disk->part0, op, start_time); } EXPORT_SYMBOL(disk_end_io_acct); /* * Steal bios from a request and add them to a bio list. * The request must not have been partially completed before. */ void blk_steal_bios(struct bio_list *list, struct request *rq) { if (rq->bio) { if (list->tail) list->tail->bi_next = rq->bio; else list->head = rq->bio; list->tail = rq->biotail; rq->bio = NULL; rq->biotail = NULL; } rq->__data_len = 0; } EXPORT_SYMBOL_GPL(blk_steal_bios); /** * blk_update_request - Complete multiple bytes without completing the request * @req: the request being processed * @error: block status code * @nr_bytes: number of bytes to complete for @req * * Description: * Ends I/O on a number of bytes attached to @req, but doesn't complete * the request structure even if @req doesn't have leftover. * If @req has leftover, sets it up for the next range of segments. * * Passing the result of blk_rq_bytes() as @nr_bytes guarantees * %false return from this function. * * Note: * The RQF_SPECIAL_PAYLOAD flag is ignored on purpose in this function * except in the consistency check at the end of this function. * * Return: * %false - this request doesn't have any more data * %true - this request has more data **/ bool blk_update_request(struct request *req, blk_status_t error, unsigned int nr_bytes) { int total_bytes; trace_block_rq_complete(req, blk_status_to_errno(error), nr_bytes); if (!req->bio) return false; #ifdef CONFIG_BLK_DEV_INTEGRITY if (blk_integrity_rq(req) && req_op(req) == REQ_OP_READ && error == BLK_STS_OK) req->q->integrity.profile->complete_fn(req, nr_bytes); #endif if (unlikely(error && !blk_rq_is_passthrough(req) && !(req->rq_flags & RQF_QUIET))) print_req_error(req, error, __func__); blk_account_io_completion(req, nr_bytes); total_bytes = 0; while (req->bio) { struct bio *bio = req->bio; unsigned bio_bytes = min(bio->bi_iter.bi_size, nr_bytes); if (bio_bytes == bio->bi_iter.bi_size) req->bio = bio->bi_next; /* Completion has already been traced */ bio_clear_flag(bio, BIO_TRACE_COMPLETION); req_bio_endio(req, bio, bio_bytes, error); total_bytes += bio_bytes; nr_bytes -= bio_bytes; if (!nr_bytes) break; } /* * completely done */ if (!req->bio) { /* * Reset counters so that the request stacking driver * can find how many bytes remain in the request * later. */ req->__data_len = 0; return false; } req->__data_len -= total_bytes; /* update sector only for requests with clear definition of sector */ if (!blk_rq_is_passthrough(req)) req->__sector += total_bytes >> 9; /* mixed attributes always follow the first bio */ if (req->rq_flags & RQF_MIXED_MERGE) { req->cmd_flags &= ~REQ_FAILFAST_MASK; req->cmd_flags |= req->bio->bi_opf & REQ_FAILFAST_MASK; } if (!(req->rq_flags & RQF_SPECIAL_PAYLOAD)) { /* * If total number of sectors is less than the first segment * size, something has gone terribly wrong. */ if (blk_rq_bytes(req) < blk_rq_cur_bytes(req)) { blk_dump_rq_flags(req, "request botched"); req->__data_len = blk_rq_cur_bytes(req); } /* recalculate the number of segments */ req->nr_phys_segments = blk_recalc_rq_segments(req); } return true; } EXPORT_SYMBOL_GPL(blk_update_request); #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE /** * rq_flush_dcache_pages - Helper function to flush all pages in a request * @rq: the request to be flushed * * Description: * Flush all pages in @rq. */ void rq_flush_dcache_pages(struct request *rq) { struct req_iterator iter; struct bio_vec bvec; rq_for_each_segment(bvec, rq, iter) flush_dcache_page(bvec.bv_page); } EXPORT_SYMBOL_GPL(rq_flush_dcache_pages); #endif /** * blk_lld_busy - Check if underlying low-level drivers of a device are busy * @q : the queue of the device being checked * * Description: * Check if underlying low-level drivers of a device are busy. * If the drivers want to export their busy state, they must set own * exporting function using blk_queue_lld_busy() first. * * Basically, this function is used only by request stacking drivers * to stop dispatching requests to underlying devices when underlying * devices are busy. This behavior helps more I/O merging on the queue * of the request stacking driver and prevents I/O throughput regression * on burst I/O load. * * Return: * 0 - Not busy (The request stacking driver should dispatch request) * 1 - Busy (The request stacking driver should stop dispatching request) */ int blk_lld_busy(struct request_queue *q) { if (queue_is_mq(q) && q->mq_ops->busy) return q->mq_ops->busy(q); return 0; } EXPORT_SYMBOL_GPL(blk_lld_busy); /** * blk_rq_unprep_clone - Helper function to free all bios in a cloned request * @rq: the clone request to be cleaned up * * Description: * Free all bios in @rq for a cloned request. */ void blk_rq_unprep_clone(struct request *rq) { struct bio *bio; while ((bio = rq->bio) != NULL) { rq->bio = bio->bi_next; bio_put(bio); } } EXPORT_SYMBOL_GPL(blk_rq_unprep_clone); /** * blk_rq_prep_clone - Helper function to setup clone request * @rq: the request to be setup * @rq_src: original request to be cloned * @bs: bio_set that bios for clone are allocated from * @gfp_mask: memory allocation mask for bio * @bio_ctr: setup function to be called for each clone bio. * Returns %0 for success, non %0 for failure. * @data: private data to be passed to @bio_ctr * * Description: * Clones bios in @rq_src to @rq, and copies attributes of @rq_src to @rq. * Also, pages which the original bios are pointing to are not copied * and the cloned bios just point same pages. * So cloned bios must be completed before original bios, which means * the caller must complete @rq before @rq_src. */ int blk_rq_prep_clone(struct request *rq, struct request *rq_src, struct bio_set *bs, gfp_t gfp_mask, int (*bio_ctr)(struct bio *, struct bio *, void *), void *data) { struct bio *bio, *bio_src; if (!bs) bs = &fs_bio_set; __rq_for_each_bio(bio_src, rq_src) { bio = bio_clone_fast(bio_src, gfp_mask, bs); if (!bio) goto free_and_out; if (bio_ctr && bio_ctr(bio, bio_src, data)) goto free_and_out; if (rq->bio) { rq->biotail->bi_next = bio; rq->biotail = bio; } else { rq->bio = rq->biotail = bio; } bio = NULL; } /* Copy attributes of the original request to the clone request. */ rq->__sector = blk_rq_pos(rq_src); rq->__data_len = blk_rq_bytes(rq_src); if (rq_src->rq_flags & RQF_SPECIAL_PAYLOAD) { rq->rq_flags |= RQF_SPECIAL_PAYLOAD; rq->special_vec = rq_src->special_vec; } rq->nr_phys_segments = rq_src->nr_phys_segments; rq->ioprio = rq_src->ioprio; if (rq->bio && blk_crypto_rq_bio_prep(rq, rq->bio, gfp_mask) < 0) goto free_and_out; return 0; free_and_out: if (bio) bio_put(bio); blk_rq_unprep_clone(rq); return -ENOMEM; } EXPORT_SYMBOL_GPL(blk_rq_prep_clone); int kblockd_schedule_work(struct work_struct *work) { return queue_work(kblockd_workqueue, work); } EXPORT_SYMBOL(kblockd_schedule_work); int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay) { return mod_delayed_work_on(cpu, kblockd_workqueue, dwork, delay); } EXPORT_SYMBOL(kblockd_mod_delayed_work_on); void blk_start_plug_nr_ios(struct blk_plug *plug, unsigned short nr_ios) { struct task_struct *tsk = current; /* * If this is a nested plug, don't actually assign it. */ if (tsk->plug) return; INIT_LIST_HEAD(&plug->mq_list); plug->cached_rq = NULL; plug->nr_ios = min_t(unsigned short, nr_ios, BLK_MAX_REQUEST_COUNT); plug->rq_count = 0; plug->multiple_queues = false; plug->nowait = false; INIT_LIST_HEAD(&plug->cb_list); /* * Store ordering should not be needed here, since a potential * preempt will imply a full memory barrier */ tsk->plug = plug; } /** * blk_start_plug - initialize blk_plug and track it inside the task_struct * @plug: The &struct blk_plug that needs to be initialized * * Description: * blk_start_plug() indicates to the block layer an intent by the caller * to submit multiple I/O requests in a batch. The block layer may use * this hint to defer submitting I/Os from the caller until blk_finish_plug() * is called. However, the block layer may choose to submit requests * before a call to blk_finish_plug() if the number of queued I/Os * exceeds %BLK_MAX_REQUEST_COUNT, or if the size of the I/O is larger than * %BLK_PLUG_FLUSH_SIZE. The queued I/Os may also be submitted early if * the task schedules (see below). * * Tracking blk_plug inside the task_struct will help with auto-flushing the * pending I/O should the task end up blocking between blk_start_plug() and * blk_finish_plug(). This is important from a performance perspective, but * also ensures that we don't deadlock. For instance, if the task is blocking * for a memory allocation, memory reclaim could end up wanting to free a * page belonging to that request that is currently residing in our private * plug. By flushing the pending I/O when the process goes to sleep, we avoid * this kind of deadlock. */ void blk_start_plug(struct blk_plug *plug) { blk_start_plug_nr_ios(plug, 1); } EXPORT_SYMBOL(blk_start_plug); static void flush_plug_callbacks(struct blk_plug *plug, bool from_schedule) { LIST_HEAD(callbacks); while (!list_empty(&plug->cb_list)) { list_splice_init(&plug->cb_list, &callbacks); while (!list_empty(&callbacks)) { struct blk_plug_cb *cb = list_first_entry(&callbacks, struct blk_plug_cb, list); list_del(&cb->list); cb->callback(cb, from_schedule); } } } struct blk_plug_cb *blk_check_plugged(blk_plug_cb_fn unplug, void *data, int size) { struct blk_plug *plug = current->plug; struct blk_plug_cb *cb; if (!plug) return NULL; list_for_each_entry(cb, &plug->cb_list, list) if (cb->callback == unplug && cb->data == data) return cb; /* Not currently on the callback list */ BUG_ON(size < sizeof(*cb)); cb = kzalloc(size, GFP_ATOMIC); if (cb) { cb->data = data; cb->callback = unplug; list_add(&cb->list, &plug->cb_list); } return cb; } EXPORT_SYMBOL(blk_check_plugged); void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule) { flush_plug_callbacks(plug, from_schedule); if (!list_empty(&plug->mq_list)) blk_mq_flush_plug_list(plug, from_schedule); if (unlikely(!from_schedule && plug->cached_rq)) blk_mq_free_plug_rqs(plug); } /** * blk_finish_plug - mark the end of a batch of submitted I/O * @plug: The &struct blk_plug passed to blk_start_plug() * * Description: * Indicate that a batch of I/O submissions is complete. This function * must be paired with an initial call to blk_start_plug(). The intent * is to allow the block layer to optimize I/O submission. See the * documentation for blk_start_plug() for more information. */ void blk_finish_plug(struct blk_plug *plug) { if (plug != current->plug) return; blk_flush_plug_list(plug, false); current->plug = NULL; } EXPORT_SYMBOL(blk_finish_plug); void blk_io_schedule(void) { /* Prevent hang_check timer from firing at us during very long I/O */ unsigned long timeout = sysctl_hung_task_timeout_secs * HZ / 2; if (timeout) io_schedule_timeout(timeout); else io_schedule(); } EXPORT_SYMBOL_GPL(blk_io_schedule); int __init blk_dev_init(void) { BUILD_BUG_ON(REQ_OP_LAST >= (1 << REQ_OP_BITS)); BUILD_BUG_ON(REQ_OP_BITS + REQ_FLAG_BITS > 8 * sizeof_field(struct request, cmd_flags)); BUILD_BUG_ON(REQ_OP_BITS + REQ_FLAG_BITS > 8 * sizeof_field(struct bio, bi_opf)); /* used for unplugging and affects IO latency/throughput - HIGHPRI */ kblockd_workqueue = alloc_workqueue("kblockd", WQ_MEM_RECLAIM | WQ_HIGHPRI, 0); if (!kblockd_workqueue) panic("Failed to create kblockd\n"); blk_requestq_cachep = kmem_cache_create("request_queue", sizeof(struct request_queue), 0, SLAB_PANIC, NULL); blk_debugfs_root = debugfs_create_dir("block", NULL); return 0; }