diff options
Diffstat (limited to 'block/blk-core.c')
| -rw-r--r-- | block/blk-core.c | 1697 |
1 files changed, 573 insertions, 1124 deletions
diff --git a/block/blk-core.c b/block/blk-core.c index 8340f69670d8..9866468c72a2 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -14,12 +14,13 @@ */ #include <linux/kernel.h> #include <linux/module.h> -#include <linux/backing-dev.h> #include <linux/bio.h> #include <linux/blkdev.h> -#include <linux/blk-mq.h> +#include <linux/blk-pm.h> +#include <linux/blk-integrity.h> #include <linux/highmem.h> #include <linux/mm.h> +#include <linux/pagemap.h> #include <linux/kernel_stat.h> #include <linux/string.h> #include <linux/init.h> @@ -33,35 +34,37 @@ #include <linux/delay.h> #include <linux/ratelimit.h> #include <linux/pm_runtime.h> -#include <linux/blk-cgroup.h> +#include <linux/t10-pi.h> #include <linux/debugfs.h> #include <linux/bpf.h> +#include <linux/part_stat.h> +#include <linux/sched/sysctl.h> +#include <linux/blk-crypto.h> #define CREATE_TRACE_POINTS #include <trace/events/block.h> #include "blk.h" -#include "blk-mq.h" #include "blk-mq-sched.h" #include "blk-pm.h" -#include "blk-rq-qos.h" +#include "blk-cgroup.h" +#include "blk-throttle.h" -#ifdef CONFIG_DEBUG_FS struct dentry *blk_debugfs_root; -#endif 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); +static DEFINE_IDA(blk_queue_ida); /* * For queue allocation */ -struct kmem_cache *blk_requestq_cachep; +static struct kmem_cache *blk_requestq_cachep; /* * Controlling structure to kblockd @@ -104,21 +107,43 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q) } EXPORT_SYMBOL_GPL(blk_queue_flag_test_and_set); -void blk_rq_init(struct request_queue *q, struct request *rq) +#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_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(enum req_op op) { - 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 = -1; - rq->internal_tag = -1; - rq->start_time_ns = ktime_get_ns(); - rq->part = NULL; + 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(blk_rq_init); +EXPORT_SYMBOL_GPL(blk_op_str); static const struct { int errno; @@ -130,16 +155,24 @@ static const struct { [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_RESV_CONFLICT] = { -EBADE, "reservation conflict" }, [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" }, + [BLK_STS_OFFLINE] = { -ENODEV, "device offline" }, /* 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" }, + + /* Command duration limit device-side timeout */ + [BLK_STS_DURATION_LIMIT] = { -ETIME, "duration limit exceeded" }, + /* everything else not covered above: */ [BLK_STS_IOERR] = { -EIO, "I/O" }, }; @@ -167,50 +200,15 @@ int blk_status_to_errno(blk_status_t status) } EXPORT_SYMBOL_GPL(blk_status_to_errno); -static void print_req_error(struct request *req, blk_status_t status) +const char *blk_status_to_str(blk_status_t status) { 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 flags %x\n", - __func__, blk_errors[idx].name, - req->rq_disk ? req->rq_disk->disk_name : "?", - (unsigned long long)blk_rq_pos(req), - req->cmd_flags); -} - -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); - - /* 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); + return "<null>"; + return blk_errors[idx].name; } -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 @@ -221,7 +219,7 @@ EXPORT_SYMBOL(blk_dump_rq_flags); * 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 ->make_request_fn will not re-add plugging prior to calling + * that its ->submit_bio will not re-add plugging prior to calling * this function. * * This function does not cancel any asynchronous activity arising @@ -257,145 +255,117 @@ void blk_clear_pm_only(struct request_queue *q) } EXPORT_SYMBOL_GPL(blk_clear_pm_only); -void blk_put_queue(struct request_queue *q) +static void blk_free_queue_rcu(struct rcu_head *rcu_head) { - kobject_put(&q->kobj); + struct request_queue *q = container_of(rcu_head, + struct request_queue, rcu_head); + + percpu_ref_exit(&q->q_usage_counter); + kmem_cache_free(blk_requestq_cachep, q); } -EXPORT_SYMBOL(blk_put_queue); -void blk_set_queue_dying(struct request_queue *q) +static void blk_free_queue(struct request_queue *q) { - blk_queue_flag_set(QUEUE_FLAG_DYING, 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); - + blk_free_queue_stats(q->stats); if (queue_is_mq(q)) - blk_mq_wake_waiters(q); + blk_mq_release(q); - /* Make blk_queue_enter() reexamine the DYING flag. */ - wake_up_all(&q->mq_freeze_wq); + ida_free(&blk_queue_ida, q->id); + call_rcu(&q->rcu_head, blk_free_queue_rcu); } -EXPORT_SYMBOL_GPL(blk_set_queue_dying); /** - * blk_cleanup_queue - shutdown a request queue - * @q: request queue to shutdown + * blk_put_queue - decrement the request_queue refcount + * @q: the request_queue structure to decrement the refcount for * - * Mark @q DYING, drain all pending requests, mark @q DEAD, destroy and - * put it. All future requests will be failed immediately with -ENODEV. + * Decrements the refcount of the request_queue and free it when the refcount + * reaches 0. */ -void blk_cleanup_queue(struct request_queue *q) +void blk_put_queue(struct request_queue *q) { - /* mark @q DYING, no new request or merges will be allowed afterwards */ - mutex_lock(&q->sysfs_lock); - blk_set_queue_dying(q); - - blk_queue_flag_set(QUEUE_FLAG_NOMERGES, q); - blk_queue_flag_set(QUEUE_FLAG_NOXMERGES, q); - blk_queue_flag_set(QUEUE_FLAG_DYING, q); - mutex_unlock(&q->sysfs_lock); + if (refcount_dec_and_test(&q->refs)) + blk_free_queue(q); +} +EXPORT_SYMBOL(blk_put_queue); +void blk_queue_start_drain(struct request_queue *q) +{ /* - * Drain all requests queued before DYING marking. Set DEAD flag to - * prevent that q->request_fn() gets invoked after draining finished. + * 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(q); - - rq_qos_exit(q); - - blk_queue_flag_set(QUEUE_FLAG_DEAD, q); - - /* for synchronous bio-based driver finish in-flight integrity i/o */ - blk_flush_integrity(); - - /* @q won't process any more request, flush async actions */ - del_timer_sync(&q->backing_dev_info->laptop_mode_wb_timer); - blk_sync_queue(q); - + blk_freeze_queue_start(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_requests(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); - -struct request_queue *blk_alloc_queue(gfp_t gfp_mask) -{ - return blk_alloc_queue_node(gfp_mask, NUMA_NO_NODE); + blk_mq_wake_waiters(q); + /* Make blk_queue_enter() reexamine the DYING flag. */ + wake_up_all(&q->mq_freeze_wq); } -EXPORT_SYMBOL(blk_alloc_queue); /** * blk_queue_enter() - try to increase q->q_usage_counter * @q: request queue pointer - * @flags: BLK_MQ_REQ_NOWAIT and/or BLK_MQ_REQ_PREEMPT + * @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_PREEMPT; - - while (true) { - bool success = false; - - rcu_read_lock(); - if (percpu_ref_tryget_live(&q->q_usage_counter)) { - /* - * The code that increments the pm_only counter is - * responsible for ensuring that that counter is - * globally visible before the queue is unfrozen. - */ - if (pm || !blk_queue_pm_only(q)) { - success = true; - } else { - percpu_ref_put(&q->q_usage_counter); - } - } - rcu_read_unlock(); - - if (success) - return 0; + const bool pm = flags & BLK_MQ_REQ_PM; + while (!blk_try_enter_queue(q, pm)) { if (flags & BLK_MQ_REQ_NOWAIT) - return -EBUSY; + return -EAGAIN; /* - * 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. + * 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 && - (pm || (blk_pm_request_resume(q), - !blk_queue_pm_only(q)))) || + blk_pm_resume_queue(pm, q)) || blk_queue_dying(q)); if (blk_queue_dying(q)) return -ENODEV; } + + return 0; +} + +int __bio_queue_enter(struct request_queue *q, struct bio *bio) +{ + while (!blk_try_enter_queue(q, false)) { + struct gendisk *disk = bio->bi_bdev->bd_disk; + + if (bio->bi_opf & REQ_NOWAIT) { + if (test_bit(GD_DEAD, &disk->state)) + goto dead; + bio_wouldblock_error(bio); + return -EAGAIN; + } + + /* + * 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) @@ -422,60 +392,38 @@ static void blk_timeout_work(struct work_struct *work) { } -/** - * blk_alloc_queue_node - allocate a request queue - * @gfp_mask: memory allocation flags - * @node_id: NUMA node to allocate memory from - */ -struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) +struct request_queue *blk_alloc_queue(int node_id) { struct request_queue *q; - int ret; - q = kmem_cache_alloc_node(blk_requestq_cachep, - gfp_mask | __GFP_ZERO, node_id); + q = kmem_cache_alloc_node(blk_requestq_cachep, GFP_KERNEL | __GFP_ZERO, + node_id); if (!q) return NULL; - INIT_LIST_HEAD(&q->queue_head); q->last_merge = NULL; - q->id = ida_simple_get(&blk_queue_ida, 0, 0, gfp_mask); + q->id = ida_alloc(&blk_queue_ida, GFP_KERNEL); if (q->id < 0) goto fail_q; - ret = bioset_init(&q->bio_split, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS); - if (ret) - goto fail_id; - - q->backing_dev_info = bdi_alloc_node(gfp_mask, node_id); - if (!q->backing_dev_info) - goto fail_split; - q->stats = blk_alloc_queue_stats(); if (!q->stats) - goto fail_stats; + goto fail_id; - q->backing_dev_info->ra_pages = VM_READAHEAD_PAGES; - q->backing_dev_info->capabilities = BDI_CAP_CGROUP_WRITEBACK; - q->backing_dev_info->name = "block"; q->node = node_id; - timer_setup(&q->backing_dev_info->laptop_mode_wb_timer, - laptop_mode_timer_fn, 0); + 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); -#ifdef CONFIG_BLK_DEV_IO_TRACE - mutex_init(&q->blk_trace_mutex); -#endif + refcount_set(&q->refs, 1); + mutex_init(&q->debugfs_mutex); mutex_init(&q->sysfs_lock); + mutex_init(&q->sysfs_dir_lock); + mutex_init(&q->rq_qos_mutex); spin_lock_init(&q->queue_lock); init_waitqueue_head(&q->mq_freeze_wq); @@ -488,227 +436,38 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) if (percpu_ref_init(&q->q_usage_counter, blk_queue_usage_counter_release, PERCPU_REF_INIT_ATOMIC, GFP_KERNEL)) - goto fail_bdi; + goto fail_stats; - if (blkcg_init_queue(q)) - goto fail_ref; + blk_set_default_limits(&q->limits); + q->nr_requests = BLKDEV_DEFAULT_RQ; return q; -fail_ref: - percpu_ref_exit(&q->q_usage_counter); -fail_bdi: - blk_free_queue_stats(q->stats); fail_stats: - bdi_put(q->backing_dev_info); -fail_split: - bioset_exit(&q->bio_split); + blk_free_queue_stats(q->stats); fail_id: - ida_simple_remove(&blk_queue_ida, q->id); + ida_free(&blk_queue_ida, q->id); fail_q: kmem_cache_free(blk_requestq_cachep, q); return NULL; } -EXPORT_SYMBOL(blk_alloc_queue_node); - -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_PREEMPT)); - - 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); - -bool bio_attempt_back_merge(struct request_queue *q, struct request *req, - struct bio *bio) -{ - const int ff = bio->bi_opf & REQ_FAILFAST_MASK; - - if (!ll_back_merge_fn(q, req, bio)) - return false; - - trace_block_bio_backmerge(q, req, bio); - - if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff) - blk_rq_set_mixed_merge(req); - - req->biotail->bi_next = bio; - req->biotail = bio; - req->__data_len += bio->bi_iter.bi_size; - - blk_account_io_start(req, false); - return true; -} - -bool bio_attempt_front_merge(struct request_queue *q, struct request *req, - struct bio *bio) -{ - const int ff = bio->bi_opf & REQ_FAILFAST_MASK; - - if (!ll_front_merge_fn(q, req, bio)) - return false; - - trace_block_bio_frontmerge(q, req, bio); - - if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff) - blk_rq_set_mixed_merge(req); - - bio->bi_next = req->bio; - req->bio = bio; - - req->__sector = bio->bi_iter.bi_sector; - req->__data_len += bio->bi_iter.bi_size; - - blk_account_io_start(req, false); - return true; -} - -bool bio_attempt_discard_merge(struct request_queue *q, struct request *req, - struct bio *bio) -{ - unsigned short segments = blk_rq_nr_discard_segments(req); - - if (segments >= queue_max_discard_segments(q)) - goto no_merge; - if (blk_rq_sectors(req) + bio_sectors(bio) > - blk_rq_get_max_sectors(req, blk_rq_pos(req))) - goto no_merge; - - req->biotail->bi_next = bio; - req->biotail = bio; - req->__data_len += bio->bi_iter.bi_size; - req->nr_phys_segments = segments + 1; - - blk_account_io_start(req, false); - return true; -no_merge: - req_set_nomerge(q, req); - return false; -} /** - * blk_attempt_plug_merge - try to merge with %current's plugged list - * @q: request_queue new bio is being queued at - * @bio: new bio being queued - * @same_queue_rq: pointer to &struct request that gets filled in when - * another request associated with @q is found on the plug list - * (optional, may be %NULL) - * - * Determine whether @bio being queued on @q can be merged with a request - * on %current's plugged list. Returns %true if merge was successful, - * otherwise %false. + * blk_get_queue - increment the request_queue refcount + * @q: the request_queue structure to increment the refcount for * - * Plugging coalesces IOs from the same issuer for the same purpose without - * going through @q->queue_lock. As such it's more of an issuing mechanism - * than scheduling, and the request, while may have elvpriv data, is not - * added on the elevator at this point. In addition, we don't have - * reliable access to the elevator outside queue lock. Only check basic - * merging parameters without querying the elevator. + * Increment the refcount of the request_queue kobject. * - * Caller must ensure !blk_queue_nomerges(q) beforehand. + * Context: Any context. */ -bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio, - struct request **same_queue_rq) +bool blk_get_queue(struct request_queue *q) { - struct blk_plug *plug; - struct request *rq; - struct list_head *plug_list; - - plug = current->plug; - if (!plug) + if (unlikely(blk_queue_dying(q))) return false; - - plug_list = &plug->mq_list; - - list_for_each_entry_reverse(rq, plug_list, queuelist) { - bool merged = false; - - if (rq->q == q && same_queue_rq) { - /* - * Only blk-mq multiple hardware queues case checks the - * rq in the same queue, there should be only one such - * rq in a queue - **/ - *same_queue_rq = rq; - } - - if (rq->q != q || !blk_rq_merge_ok(rq, bio)) - continue; - - switch (blk_try_merge(rq, bio)) { - case ELEVATOR_BACK_MERGE: - merged = bio_attempt_back_merge(q, rq, bio); - break; - case ELEVATOR_FRONT_MERGE: - merged = bio_attempt_front_merge(q, rq, bio); - break; - case ELEVATOR_DISCARD_MERGE: - merged = bio_attempt_discard_merge(q, rq, bio); - break; - default: - break; - } - - if (merged) - return true; - } - - return false; -} - -void blk_init_request_from_bio(struct request *req, struct bio *bio) -{ - if (bio->bi_opf & REQ_RAHEAD) - req->cmd_flags |= REQ_FAILFAST_MASK; - - req->__sector = bio->bi_iter.bi_sector; - req->ioprio = bio_prio(bio); - req->write_hint = bio->bi_write_hint; - blk_rq_bio_prep(req->q, req, bio); -} -EXPORT_SYMBOL_GPL(blk_init_request_from_bio); - -static void handle_bad_sector(struct bio *bio, sector_t maxsector) -{ - char b[BDEVNAME_SIZE]; - - printk(KERN_INFO "attempt to access beyond end of device\n"); - printk(KERN_INFO "%s: rw=%d, want=%Lu, limit=%Lu\n", - bio_devname(bio, b), bio->bi_opf, - (unsigned long long)bio_end_sector(bio), - (long long)maxsector); + refcount_inc(&q->refs); + return true; } +EXPORT_SYMBOL(blk_get_queue); #ifdef CONFIG_FAIL_MAKE_REQUEST @@ -720,9 +479,9 @@ static int __init setup_fail_make_request(char *str) } __setup("fail_make_request=", setup_fail_make_request); -static bool should_fail_request(struct hd_struct *part, unsigned int bytes) +bool should_fail_request(struct block_device *part, unsigned int bytes) { - return part->make_it_fail && should_fail(&fail_make_request, bytes); + return part->bd_make_it_fail && should_fail(&fail_make_request, bytes); } static int __init fail_make_request_debugfs(void) @@ -734,41 +493,22 @@ static int __init fail_make_request_debugfs(void) } late_initcall(fail_make_request_debugfs); - -#else /* CONFIG_FAIL_MAKE_REQUEST */ - -static inline bool should_fail_request(struct hd_struct *part, - unsigned int bytes) -{ - return false; -} - #endif /* CONFIG_FAIL_MAKE_REQUEST */ -static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part) +static inline void bio_check_ro(struct bio *bio) { - const int op = bio_op(bio); - - if (part->policy && op_is_write(op)) { - char b[BDEVNAME_SIZE]; - + if (op_is_write(bio_op(bio)) && bdev_read_only(bio->bi_bdev)) { if (op_is_flush(bio->bi_opf) && !bio_sectors(bio)) - return false; - - WARN_ONCE(1, - "generic_make_request: Trying to write " - "to read-only block-device %s (partno %d)\n", - bio_devname(bio, b), part->partno); + return; + pr_warn("Trying to write to read-only block-device %pg\n", + bio->bi_bdev); /* Older lvm-tools actually trigger this */ - return false; } - - return false; } static noinline int should_fail_bio(struct bio *bio) { - if (should_fail_request(&bio->bi_disk->part0, bio->bi_iter.bi_size)) + if (should_fail_request(bdev_whole(bio->bi_bdev), bio->bi_iter.bi_size)) return -EIO; return 0; } @@ -779,14 +519,18 @@ ALLOW_ERROR_INJECTION(should_fail_bio, ERRNO); * 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) +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 && + if (nr_sectors && (nr_sectors > maxsector || bio->bi_iter.bi_sector > maxsector - nr_sectors)) { - handle_bad_sector(bio, maxsector); + pr_info_ratelimited("%s: attempt to access beyond end of device\n" + "%pg: rw=%d, sector=%llu, nr_sectors = %u limit=%llu\n", + current->comm, bio->bi_bdev, bio->bi_opf, + bio->bi_iter.bi_sector, nr_sectors, maxsector); return -EIO; } return 0; @@ -795,109 +539,252 @@ static inline int bio_check_eod(struct bio *bio, sector_t maxsector) /* * Remap block n of partition p to block n+start(p) of the disk. */ -static inline int blk_partition_remap(struct bio *bio) +static int blk_partition_remap(struct bio *bio) { - struct hd_struct *p; - int ret = -EIO; + struct block_device *p = bio->bi_bdev; - rcu_read_lock(); - p = __disk_get_part(bio->bi_disk, bio->bi_partno); - if (unlikely(!p)) - goto out; if (unlikely(should_fail_request(p, bio->bi_iter.bi_size))) - goto out; - if (unlikely(bio_check_ro(bio, p))) - goto out; + 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) +{ + int nr_sectors = bio_sectors(bio); + + /* Only applicable to zoned block devices */ + if (!bdev_is_zoned(bio->bi_bdev)) + return BLK_STS_NOTSUPP; + + /* The bio sector must point to the start of a sequential zone */ + if (!bdev_is_zone_start(bio->bi_bdev, bio->bi_iter.bi_sector) || + !bio_zone_is_seq(bio)) + return BLK_STS_IOERR; /* - * Zone reset does not include bi_size so bio_sectors() is always 0. - * Include a test for the reset op code and perform the remap if needed. + * 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 (bio_sectors(bio) || bio_op(bio) == REQ_OP_ZONE_RESET) { - if (bio_check_eod(bio, part_nr_sects_read(p))) - goto out; - bio->bi_iter.bi_sector += p->start_sect; - trace_block_bio_remap(bio->bi_disk->queue, bio, part_devt(p), - bio->bi_iter.bi_sector - p->start_sect); + 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 void __submit_bio(struct bio *bio) +{ + if (unlikely(!blk_crypto_bio_prep(&bio))) + return; + + if (!bio->bi_bdev->bd_has_submit_bio) { + blk_mq_submit_bio(bio); + } else if (likely(bio_queue_enter(bio) == 0)) { + struct gendisk *disk = bio->bi_bdev->bd_disk; + + disk->fops->submit_bio(bio); + blk_queue_exit(disk->queue); } - bio->bi_partno = 0; - ret = 0; -out: - rcu_read_unlock(); - return ret; } -static noinline_for_stack bool -generic_make_request_checks(struct bio *bio) +/* + * 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, but that haven't been processed yet. + */ +static void __submit_bio_noacct(struct bio *bio) { - struct request_queue *q; - int nr_sectors = bio_sectors(bio); - blk_status_t status = BLK_STS_IOERR; - char b[BDEVNAME_SIZE]; + struct bio_list bio_list_on_stack[2]; - might_sleep(); + BUG_ON(bio->bi_next); - q = bio->bi_disk->queue; - if (unlikely(!q)) { - printk(KERN_ERR - "generic_make_request: Trying to access " - "nonexistent block-device %s (%Lu)\n", - bio_devname(bio, b), (long long)bio->bi_iter.bi_sector); - goto end_io; + bio_list_init(&bio_list_on_stack[0]); + current->bio_list = bio_list_on_stack; + + do { + struct request_queue *q = bdev_get_queue(bio->bi_bdev); + 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 == bdev_get_queue(bio->bi_bdev)) + 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; +} + +void submit_bio_noacct_nocheck(struct bio *bio) +{ + 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); } /* + * 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_has_submit_bio) + __submit_bio_noacct_mq(bio); + else + __submit_bio_noacct(bio); +} + +/** + * 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) +{ + struct block_device *bdev = bio->bi_bdev; + struct request_queue *q = bdev_get_queue(bdev); + blk_status_t status = BLK_STS_IOERR; + + might_sleep(); + + /* * For a REQ_NOWAIT based request, return -EOPNOTSUPP - * if queue is not a request based queue. + * if queue does not support NOWAIT. */ - if ((bio->bi_opf & REQ_NOWAIT) && !queue_is_mq(q)) + if ((bio->bi_opf & REQ_NOWAIT) && !bdev_nowait(bdev)) goto not_supported; if (should_fail_bio(bio)) goto end_io; - - if (bio->bi_partno) { - if (unlikely(blk_partition_remap(bio))) + bio_check_ro(bio); + if (!bio_flagged(bio, BIO_REMAPPED)) { + if (unlikely(bio_check_eod(bio))) goto end_io; - } else { - if (unlikely(bio_check_ro(bio, &bio->bi_disk->part0))) - goto end_io; - if (unlikely(bio_check_eod(bio, get_capacity(bio->bi_disk)))) + if (bdev->bd_partno && unlikely(blk_partition_remap(bio))) goto end_io; } /* - * Filter flush bio's early so that make_request based - * drivers without flush support don't have to worry - * about them. + * 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 (!nr_sectors) { - status = BLK_STS_OK; + if (op_is_flush(bio->bi_opf)) { + if (WARN_ON_ONCE(bio_op(bio) != REQ_OP_WRITE && + bio_op(bio) != REQ_OP_ZONE_APPEND)) goto end_io; + if (!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->bi_opf &= ~REQ_HIPRI; + bio_clear_polled(bio); switch (bio_op(bio)) { case REQ_OP_DISCARD: - if (!blk_queue_discard(q)) + if (!bdev_max_discard_sectors(bdev)) goto not_supported; break; case REQ_OP_SECURE_ERASE: - if (!blk_queue_secure_erase(q)) + if (!bdev_max_secure_erase_sectors(bdev)) goto not_supported; break; - case REQ_OP_WRITE_SAME: - if (!q->limits.max_write_same_sectors) - goto not_supported; + 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: - if (!blk_queue_is_zoned(q)) + case REQ_OP_ZONE_OPEN: + case REQ_OP_ZONE_CLOSE: + case REQ_OP_ZONE_FINISH: + if (!bdev_is_zoned(bio->bi_bdev)) + goto not_supported; + break; + case REQ_OP_ZONE_RESET_ALL: + if (!bdev_is_zoned(bio->bi_bdev) || !blk_queue_zone_resetall(q)) goto not_supported; break; case REQ_OP_WRITE_ZEROES: @@ -908,570 +795,207 @@ generic_make_request_checks(struct bio *bio) break; } - /* - * Various block parts want %current->io_context and lazy ioc - * allocation ends up trading a lot of pain for a small amount of - * memory. Just allocate it upfront. This may fail and block - * layer knows how to live with it. - */ - create_io_context(GFP_ATOMIC, q->node); - - if (!blkcg_bio_issue_check(q, bio)) - return false; - - if (!bio_flagged(bio, BIO_TRACE_COMPLETION)) { - trace_block_bio_queue(q, bio); - /* Now that enqueuing has been traced, we need to trace - * completion as well. - */ - bio_set_flag(bio, BIO_TRACE_COMPLETION); - } - return true; + if (blk_throtl_bio(bio)) + return; + submit_bio_noacct_nocheck(bio); + return; not_supported: status = BLK_STS_NOTSUPP; end_io: bio->bi_status = status; bio_endio(bio); - return false; } - -/** - * generic_make_request - hand a buffer to its device driver for I/O - * @bio: The bio describing the location in memory and on the device. - * - * generic_make_request() is used to make I/O requests of block - * devices. It is passed a &struct bio, which describes the I/O that needs - * to be done. - * - * generic_make_request() does not return any status. The - * success/failure status of the request, along with notification of - * completion, is delivered asynchronously through the bio->bi_end_io - * function described (one day) else where. - * - * The caller of generic_make_request must make sure that bi_io_vec - * are set to describe the memory buffer, and that bi_dev and bi_sector are - * set to describe the device address, and the - * bi_end_io and optionally bi_private are set to describe how - * completion notification should be signaled. - * - * generic_make_request and the drivers it calls may use bi_next if this - * bio happens to be merged with someone else, and may resubmit the bio to - * a lower device by calling into generic_make_request recursively, which - * means the bio should NOT be touched after the call to ->make_request_fn. - */ -blk_qc_t generic_make_request(struct bio *bio) -{ - /* - * bio_list_on_stack[0] contains bios submitted by the current - * make_request_fn. - * bio_list_on_stack[1] contains bios that were submitted before - * the current make_request_fn, but that haven't been processed - * yet. - */ - struct bio_list bio_list_on_stack[2]; - blk_qc_t ret = BLK_QC_T_NONE; - - if (!generic_make_request_checks(bio)) - goto out; - - /* - * We only want one ->make_request_fn to be active at a time, else - * stack usage with stacked devices could be a problem. So use - * current->bio_list to keep a list of requests submited by a - * make_request_fn function. current->bio_list is also used as a - * flag to say if generic_make_request is currently active in this - * task or not. If it is NULL, then no make_request is active. If - * it is non-NULL, then a make_request is active, and new requests - * should be added at the tail - */ - if (current->bio_list) { - bio_list_add(¤t->bio_list[0], bio); - goto out; - } - - /* following loop 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. ->make_request() may indeed add some more bios - * through a recursive call to generic_make_request. 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 ->make_request() again. - */ - 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_disk->queue; - blk_mq_req_flags_t flags = bio->bi_opf & REQ_NOWAIT ? - BLK_MQ_REQ_NOWAIT : 0; - - if (likely(blk_queue_enter(q, flags) == 0)) { - 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]); - ret = q->make_request_fn(q, bio); - - blk_queue_exit(q); - - /* 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_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]); - } else { - if (unlikely(!blk_queue_dying(q) && - (bio->bi_opf & REQ_NOWAIT))) - bio_wouldblock_error(bio); - else - bio_io_error(bio); - } - bio = bio_list_pop(&bio_list_on_stack[0]); - } while (bio); - current->bio_list = NULL; /* deactivate */ - -out: - return ret; -} -EXPORT_SYMBOL(generic_make_request); - -/** - * direct_make_request - hand a buffer directly to its device driver for I/O - * @bio: The bio describing the location in memory and on the device. - * - * This function behaves like generic_make_request(), but does not protect - * against recursion. Must only be used if the called driver is known - * to not call generic_make_request (or direct_make_request) again from - * its make_request function. (Calling direct_make_request again from - * a workqueue is perfectly fine as that doesn't recurse). - */ -blk_qc_t direct_make_request(struct bio *bio) -{ - struct request_queue *q = bio->bi_disk->queue; - bool nowait = bio->bi_opf & REQ_NOWAIT; - blk_qc_t ret; - - if (!generic_make_request_checks(bio)) - return BLK_QC_T_NONE; - - if (unlikely(blk_queue_enter(q, nowait ? BLK_MQ_REQ_NOWAIT : 0))) { - if (nowait && !blk_queue_dying(q)) - bio->bi_status = BLK_STS_AGAIN; - else - bio->bi_status = BLK_STS_IOERR; - bio_endio(bio); - return BLK_QC_T_NONE; - } - - ret = q->make_request_fn(q, bio); - blk_queue_exit(q); - return ret; -} -EXPORT_SYMBOL_GPL(direct_make_request); +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 very similar in purpose to generic_make_request(), and - * uses that function to do most of the work. Both are fairly rough - * interfaces; @bio must be presetup and ready for 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 the caller until ->bi_end_io() has + * been called. */ -blk_qc_t submit_bio(struct bio *bio) +void submit_bio(struct bio *bio) { - /* - * 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_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 (unlikely(block_dump)) { - char b[BDEVNAME_SIZE]; - printk(KERN_DEBUG "%s(%d): %s block %Lu on %s (%u sectors)\n", - current->comm, task_pid_nr(current), - op_is_write(bio_op(bio)) ? "WRITE" : "READ", - (unsigned long long)bio->bi_iter.bi_sector, - bio_devname(bio, b), count); - } + if (bio_op(bio) == REQ_OP_READ) { + task_io_account_read(bio->bi_iter.bi_size); + count_vm_events(PGPGIN, bio_sectors(bio)); + } else if (bio_op(bio) == REQ_OP_WRITE) { + count_vm_events(PGPGOUT, bio_sectors(bio)); } - return generic_make_request(bio); + submit_bio_noacct(bio); } EXPORT_SYMBOL(submit_bio); /** - * blk_cloned_rq_check_limits - Helper function to check a cloned request - * for new the queue limits - * @q: the queue - * @rq: the request being checked + * bio_poll - poll for BIO completions + * @bio: bio to poll for + * @iob: batches of IO + * @flags: BLK_POLL_* flags that control the behavior * - * 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. + * Poll for completions on queue associated with the bio. Returns number of + * completed entries found. * - * 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. + * Note: the caller must either be the context that submitted @bio, or + * be in a RCU critical section to prevent freeing of @bio. */ -static int blk_cloned_rq_check_limits(struct request_queue *q, - struct request *rq) +int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags) { - if (blk_rq_sectors(rq) > blk_queue_get_max_sectors(q, req_op(rq))) { - printk(KERN_ERR "%s: over max size limit. (%u > %u)\n", - __func__, blk_rq_sectors(rq), - blk_queue_get_max_sectors(q, req_op(rq))); - return -EIO; - } - - /* - * queue's settings related to segment counting like q->bounce_pfn - * may differ from that of other stacking queues. - * Recalculate it to check the request correctly on this queue's - * limitation. - */ - 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 -EIO; - } - - return 0; -} + blk_qc_t cookie = READ_ONCE(bio->bi_cookie); + struct block_device *bdev; + struct request_queue *q; + int ret = 0; -/** - * 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) -{ - if (blk_cloned_rq_check_limits(q, rq)) - return BLK_STS_IOERR; + bdev = READ_ONCE(bio->bi_bdev); + if (!bdev) + return 0; - if (rq->rq_disk && - should_fail_request(&rq->rq_disk->part0, blk_rq_bytes(rq))) - return BLK_STS_IOERR; + q = bdev_get_queue(bdev); + if (cookie == BLK_QC_T_NONE || + !test_bit(QUEUE_FLAG_POLL, &q->queue_flags)) + return 0; - if (blk_queue_io_stat(q)) - blk_account_io_start(rq, true); + /* + * As the requests that require a zone lock are not plugged in the + * first place, directly accessing the plug instead of using + * blk_mq_plug() should not have any consequences during flushing for + * zoned devices. + */ + blk_flush_plug(current->plug, false); /* - * Since we have a scheduler attached on the top device, - * bypass a potential scheduler on the bottom device for - * insert. + * We need to be able to enter a frozen queue, similar to how + * timeouts also need to do that. If that is blocked, then we can + * have pending IO when a queue freeze is started, and then the + * wait for the freeze to finish will wait for polled requests to + * timeout as the poller is preventer from entering the queue and + * completing them. As long as we prevent new IO from being queued, + * that should be all that matters. */ - return blk_mq_request_issue_directly(rq, true); + if (!percpu_ref_tryget(&q->q_usage_counter)) + return 0; + if (queue_is_mq(q)) { + ret = blk_mq_poll(q, cookie, iob, flags); + } else { + struct gendisk *disk = q->disk; + + if (disk && disk->fops->poll_bio) + ret = disk->fops->poll_bio(bio, iob, flags); + } + blk_queue_exit(q); + return ret; } -EXPORT_SYMBOL_GPL(blk_insert_cloned_request); +EXPORT_SYMBOL_GPL(bio_poll); -/** - * 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. +/* + * Helper to implement file_operations.iopoll. Requires the bio to be stored + * in iocb->private, and cleared before freeing the bio. */ -unsigned int blk_rq_err_bytes(const struct request *rq) +int iocb_bio_iopoll(struct kiocb *kiocb, struct io_comp_batch *iob, + unsigned int flags) { - 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); + int ret = 0; /* - * 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. + * 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. */ - for (bio = rq->bio; bio; bio = bio->bi_next) { - if ((bio->bi_opf & ff) != ff) - break; - bytes += bio->bi_iter.bi_size; - } + rcu_read_lock(); + bio = READ_ONCE(kiocb->private); + if (bio) + ret = bio_poll(bio, iob, flags); + rcu_read_unlock(); - /* this could lead to infinite loop */ - BUG_ON(blk_rq_bytes(rq) && !bytes); - return bytes; + return ret; } -EXPORT_SYMBOL_GPL(blk_rq_err_bytes); +EXPORT_SYMBOL_GPL(iocb_bio_iopoll); -void blk_account_io_completion(struct request *req, unsigned int bytes) +void update_io_ticks(struct block_device *part, unsigned long now, bool end) { - if (blk_do_io_stat(req)) { - const int sgrp = op_stat_group(req_op(req)); - struct hd_struct *part; - - part_stat_lock(); - part = req->part; - part_stat_add(part, sectors[sgrp], bytes >> 9); - part_stat_unlock(); + unsigned long stamp; +again: + stamp = READ_ONCE(part->bd_stamp); + if (unlikely(time_after(now, stamp))) { + if (likely(try_cmpxchg(&part->bd_stamp, &stamp, now))) + __part_stat_add(part, io_ticks, end ? now - stamp : 1); } -} - -void blk_account_io_done(struct request *req, u64 now) -{ - /* - * Account IO completion. flush_rq isn't accounted as a - * normal IO on queueing nor completion. Accounting the - * containing request is enough. - */ - if (blk_do_io_stat(req) && !(req->rq_flags & RQF_FLUSH_SEQ)) { - const int sgrp = op_stat_group(req_op(req)); - struct hd_struct *part; - - part_stat_lock(); - part = req->part; - - update_io_ticks(part, jiffies); - part_stat_inc(part, ios[sgrp]); - part_stat_add(part, nsecs[sgrp], now - req->start_time_ns); - part_stat_add(part, time_in_queue, nsecs_to_jiffies64(now - req->start_time_ns)); - part_dec_in_flight(req->q, part, rq_data_dir(req)); - - hd_struct_put(part); - part_stat_unlock(); + if (part->bd_partno) { + part = bdev_whole(part); + goto again; } } -void blk_account_io_start(struct request *rq, bool new_io) +unsigned long bdev_start_io_acct(struct block_device *bdev, enum req_op op, + unsigned long start_time) { - struct hd_struct *part; - int rw = rq_data_dir(rq); - - if (!blk_do_io_stat(rq)) - return; - part_stat_lock(); - - if (!new_io) { - part = rq->part; - part_stat_inc(part, merges[rw]); - } else { - part = disk_map_sector_rcu(rq->rq_disk, blk_rq_pos(rq)); - if (!hd_struct_try_get(part)) { - /* - * The partition is already being removed, - * the request will be accounted on the disk only - * - * We take a reference on disk->part0 although that - * partition will never be deleted, so we can treat - * it as any other partition. - */ - part = &rq->rq_disk->part0; - hd_struct_get(part); - } - part_inc_in_flight(rq->q, part, rw); - rq->part = part; - } - - update_io_ticks(part, jiffies); - + update_io_ticks(bdev, start_time, false); + part_stat_local_inc(bdev, in_flight[op_is_write(op)]); part_stat_unlock(); -} - -/* - * 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; + return start_time; } -EXPORT_SYMBOL_GPL(blk_steal_bios); +EXPORT_SYMBOL(bdev_start_io_acct); /** - * blk_update_request - Special helper function for request stacking drivers - * @req: the request being processed - * @error: block status code - * @nr_bytes: number of bytes to complete @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. + * bio_start_io_acct - start I/O accounting for bio based drivers + * @bio: bio to start account for * - * This special helper function is only for request stacking drivers - * (e.g. request-based dm) so that they can handle partial completion. - * Actual device drivers should use blk_end_request instead. - * - * 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 both - * blk_rq_bytes() and in blk_update_request(). - * - * 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) + * Returns the start time that should be passed back to bio_end_io_acct(). + */ +unsigned long bio_start_io_acct(struct bio *bio) { - int total_bytes; - - trace_block_rq_complete(req, blk_status_to_errno(error), nr_bytes); - - if (!req->bio) - return false; - - if (unlikely(error && !blk_rq_is_passthrough(req) && - !(req->rq_flags & RQF_QUIET))) - print_req_error(req, error); - - 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 */ - blk_recalc_rq_segments(req); - } - - return true; + return bdev_start_io_acct(bio->bi_bdev, bio_op(bio), jiffies); } -EXPORT_SYMBOL_GPL(blk_update_request); +EXPORT_SYMBOL_GPL(bio_start_io_acct); -void blk_rq_bio_prep(struct request_queue *q, struct request *rq, - struct bio *bio) +void bdev_end_io_acct(struct block_device *bdev, enum req_op op, + unsigned int sectors, unsigned long start_time) { - if (bio_has_data(bio)) - rq->nr_phys_segments = bio_phys_segments(q, bio); - else if (bio_op(bio) == REQ_OP_DISCARD) - rq->nr_phys_segments = 1; - - rq->__data_len = bio->bi_iter.bi_size; - rq->bio = rq->biotail = bio; + const int sgrp = op_stat_group(op); + unsigned long now = READ_ONCE(jiffies); + unsigned long duration = now - start_time; - if (bio->bi_disk) - rq->rq_disk = bio->bi_disk; + part_stat_lock(); + update_io_ticks(bdev, now, true); + part_stat_inc(bdev, ios[sgrp]); + part_stat_add(bdev, sectors[sgrp], sectors); + part_stat_add(bdev, nsecs[sgrp], jiffies_to_nsecs(duration)); + part_stat_local_dec(bdev, in_flight[op_is_write(op)]); + part_stat_unlock(); } +EXPORT_SYMBOL(bdev_end_io_acct); -#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) +void bio_end_io_acct_remapped(struct bio *bio, unsigned long start_time, + struct block_device *orig_bdev) { - struct req_iterator iter; - struct bio_vec bvec; - - rq_for_each_segment(bvec, rq, iter) - flush_dcache_page(bvec.bv_page); + bdev_end_io_acct(orig_bdev, bio_op(bio), bio_sectors(bio), start_time); } -EXPORT_SYMBOL_GPL(rq_flush_dcache_pages); -#endif +EXPORT_SYMBOL_GPL(bio_end_io_acct_remapped); /** * blk_lld_busy - Check if underlying low-level drivers of a device are busy @@ -1501,111 +1025,12 @@ int blk_lld_busy(struct request_queue *q) } 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); - -/* - * Copy attributes of the original request to the clone request. - * The actual data parts (e.g. ->cmd, ->sense) are not copied. - */ -static void __blk_rq_prep_clone(struct request *dst, struct request *src) -{ - dst->__sector = blk_rq_pos(src); - dst->__data_len = blk_rq_bytes(src); - if (src->rq_flags & RQF_SPECIAL_PAYLOAD) { - dst->rq_flags |= RQF_SPECIAL_PAYLOAD; - dst->special_vec = src->special_vec; - } - dst->nr_phys_segments = src->nr_phys_segments; - dst->ioprio = src->ioprio; - dst->extra_len = src->extra_len; -} - -/** - * 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. - * The actual data parts of @rq_src (e.g. ->cmd, ->sense) - * are not copied, and copying such parts is the caller's responsibility. - * 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; - } - - __blk_rq_prep_clone(rq, rq_src); - - 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_schedule_work_on(int cpu, struct work_struct *work) -{ - return queue_work_on(cpu, kblockd_workqueue, work); -} -EXPORT_SYMBOL(kblockd_schedule_work_on); - int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay) { @@ -1613,6 +1038,31 @@ int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, } 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; + + plug->mq_list = NULL; + 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->has_elevator = 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 @@ -1638,24 +1088,7 @@ EXPORT_SYMBOL(kblockd_mod_delayed_work_on); */ void blk_start_plug(struct blk_plug *plug) { - 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); - INIT_LIST_HEAD(&plug->cb_list); - plug->rq_count = 0; - plug->multiple_queues = false; - - /* - * Store ordering should not be needed here, since a potential - * preempt will imply a full memory barrier - */ - tsk->plug = plug; + blk_start_plug_nr_ios(plug, 1); } EXPORT_SYMBOL(blk_start_plug); @@ -1701,12 +1134,19 @@ struct blk_plug_cb *blk_check_plugged(blk_plug_cb_fn unplug, void *data, } EXPORT_SYMBOL(blk_check_plugged); -void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule) +void __blk_flush_plug(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 (!list_empty(&plug->cb_list)) + flush_plug_callbacks(plug, from_schedule); + blk_mq_flush_plug_list(plug, from_schedule); + /* + * Unconditionally flush out cached requests, even if the unplug + * event came from schedule. Since we know hold references to the + * queue for cached requests, we don't want a blocked task holding + * up a queue freeze/quiesce event. + */ + if (unlikely(!rq_list_empty(plug->cached_rq))) + blk_mq_free_plug_rqs(plug); } /** @@ -1721,21 +1161,32 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule) */ void blk_finish_plug(struct blk_plug *plug) { - if (plug != current->plug) - return; - blk_flush_plug_list(plug, false); - - current->plug = NULL; + if (plug == current->plug) { + __blk_flush_plug(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((__force u32)REQ_OP_LAST >= (1 << REQ_OP_BITS)); BUILD_BUG_ON(REQ_OP_BITS + REQ_FLAG_BITS > 8 * - FIELD_SIZEOF(struct request, cmd_flags)); + sizeof_field(struct request, cmd_flags)); BUILD_BUG_ON(REQ_OP_BITS + REQ_FLAG_BITS > 8 * - FIELD_SIZEOF(struct bio, bi_opf)); + sizeof_field(struct bio, bi_opf)); /* used for unplugging and affects IO latency/throughput - HIGHPRI */ kblockd_workqueue = alloc_workqueue("kblockd", @@ -1746,9 +1197,7 @@ int __init blk_dev_init(void) blk_requestq_cachep = kmem_cache_create("request_queue", sizeof(struct request_queue), 0, SLAB_PANIC, NULL); -#ifdef CONFIG_DEBUG_FS blk_debugfs_root = debugfs_create_dir("block", NULL); -#endif return 0; } |