diff options
Diffstat (limited to 'block/blk-core.c')
| -rw-r--r-- | block/blk-core.c | 3472 |
1 files changed, 2374 insertions, 1098 deletions
diff --git a/block/blk-core.c b/block/blk-core.c index fef79ccb2a1..6f8dba161bf 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -16,6 +16,7 @@ #include <linux/backing-dev.h> #include <linux/bio.h> #include <linux/blkdev.h> +#include <linux/blk-mq.h> #include <linux/highmem.h> #include <linux/mm.h> #include <linux/kernel_stat.h> @@ -26,19 +27,31 @@ #include <linux/swap.h> #include <linux/writeback.h> #include <linux/task_io_accounting_ops.h> -#include <linux/interrupt.h> -#include <linux/cpu.h> -#include <linux/blktrace_api.h> #include <linux/fault-inject.h> +#include <linux/list_sort.h> +#include <linux/delay.h> +#include <linux/ratelimit.h> +#include <linux/pm_runtime.h> + +#define CREATE_TRACE_POINTS +#include <trace/events/block.h> #include "blk.h" +#include "blk-cgroup.h" +#include "blk-mq.h" + +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); -static int __make_request(struct request_queue *q, struct bio *bio); +DEFINE_IDA(blk_queue_ida); /* * For the allocated request tables */ -static struct kmem_cache *request_cachep; +struct kmem_cache *request_cachep = NULL; /* * For queue allocation @@ -50,29 +63,6 @@ struct kmem_cache *blk_requestq_cachep; */ static struct workqueue_struct *kblockd_workqueue; -static DEFINE_PER_CPU(struct list_head, blk_cpu_done); - -static void drive_stat_acct(struct request *rq, int new_io) -{ - struct hd_struct *part; - int rw = rq_data_dir(rq); - - if (!blk_fs_request(rq) || !rq->rq_disk) - return; - - part = get_part(rq->rq_disk, rq->sector); - if (!new_io) - __all_stat_inc(rq->rq_disk, part, merges[rw], rq->sector); - else { - disk_round_stats(rq->rq_disk); - rq->rq_disk->in_flight++; - if (part) { - part_round_stats(part); - part->in_flight++; - } - } -} - void blk_queue_congestion_threshold(struct request_queue *q) { int nr; @@ -113,71 +103,54 @@ void blk_rq_init(struct request_queue *q, struct request *rq) memset(rq, 0, sizeof(*rq)); INIT_LIST_HEAD(&rq->queuelist); - INIT_LIST_HEAD(&rq->donelist); + INIT_LIST_HEAD(&rq->timeout_list); + rq->cpu = -1; rq->q = q; - rq->sector = rq->hard_sector = (sector_t) -1; + rq->__sector = (sector_t) -1; INIT_HLIST_NODE(&rq->hash); RB_CLEAR_NODE(&rq->rb_node); rq->cmd = rq->__cmd; + rq->cmd_len = BLK_MAX_CDB; rq->tag = -1; - rq->ref_count = 1; + rq->start_time = jiffies; + set_start_time_ns(rq); + rq->part = NULL; } EXPORT_SYMBOL(blk_rq_init); static void req_bio_endio(struct request *rq, struct bio *bio, unsigned int nbytes, int error) { - struct request_queue *q = rq->q; - - if (&q->bar_rq != rq) { - if (error) - clear_bit(BIO_UPTODATE, &bio->bi_flags); - else if (!test_bit(BIO_UPTODATE, &bio->bi_flags)) - error = -EIO; - - if (unlikely(nbytes > bio->bi_size)) { - printk(KERN_ERR "%s: want %u bytes done, %u left\n", - __func__, nbytes, bio->bi_size); - nbytes = bio->bi_size; - } + if (error) + clear_bit(BIO_UPTODATE, &bio->bi_flags); + else if (!test_bit(BIO_UPTODATE, &bio->bi_flags)) + error = -EIO; - bio->bi_size -= nbytes; - bio->bi_sector += (nbytes >> 9); + if (unlikely(rq->cmd_flags & REQ_QUIET)) + set_bit(BIO_QUIET, &bio->bi_flags); - if (bio_integrity(bio)) - bio_integrity_advance(bio, nbytes); + bio_advance(bio, nbytes); - if (bio->bi_size == 0) - bio_endio(bio, error); - } else { - - /* - * Okay, this is the barrier request in progress, just - * record the error; - */ - if (error && !q->orderr) - q->orderr = error; - } + /* don't actually finish bio if it's part of flush sequence */ + if (bio->bi_iter.bi_size == 0 && !(rq->cmd_flags & REQ_FLUSH_SEQ)) + bio_endio(bio, error); } void blk_dump_rq_flags(struct request *rq, char *msg) { int bit; - printk(KERN_INFO "%s: dev %s: type=%x, flags=%x\n", msg, + printk(KERN_INFO "%s: dev %s: type=%x, flags=%llx\n", msg, rq->rq_disk ? rq->rq_disk->disk_name : "?", rq->cmd_type, - rq->cmd_flags); - - printk(KERN_INFO " sector %llu, nr/cnr %lu/%u\n", - (unsigned long long)rq->sector, - rq->nr_sectors, - rq->current_nr_sectors); - printk(KERN_INFO " bio %p, biotail %p, buffer %p, data %p, len %u\n", - rq->bio, rq->biotail, - rq->buffer, rq->data, - rq->data_len); - - if (blk_pc_request(rq)) { + (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)); + + if (rq->cmd_type == REQ_TYPE_BLOCK_PC) { printk(KERN_INFO " cdb: "); for (bit = 0; bit < BLK_MAX_CDB; bit++) printk("%02x ", rq->cmd[bit]); @@ -186,126 +159,33 @@ void blk_dump_rq_flags(struct request *rq, char *msg) } EXPORT_SYMBOL(blk_dump_rq_flags); -/* - * "plug" the device if there are no outstanding requests: this will - * force the transfer to start only after we have put all the requests - * on the list. - * - * This is called with interrupts off and no requests on the queue and - * with the queue lock held. - */ -void blk_plug_device(struct request_queue *q) -{ - WARN_ON(!irqs_disabled()); - - /* - * don't plug a stopped queue, it must be paired with blk_start_queue() - * which will restart the queueing - */ - if (blk_queue_stopped(q)) - return; - - if (!queue_flag_test_and_set(QUEUE_FLAG_PLUGGED, q)) { - mod_timer(&q->unplug_timer, jiffies + q->unplug_delay); - blk_add_trace_generic(q, NULL, 0, BLK_TA_PLUG); - } -} -EXPORT_SYMBOL(blk_plug_device); - -/* - * remove the queue from the plugged list, if present. called with - * queue lock held and interrupts disabled. - */ -int blk_remove_plug(struct request_queue *q) -{ - WARN_ON(!irqs_disabled()); - - if (!queue_flag_test_and_clear(QUEUE_FLAG_PLUGGED, q)) - return 0; - - del_timer(&q->unplug_timer); - return 1; -} -EXPORT_SYMBOL(blk_remove_plug); - -/* - * remove the plug and let it rip.. - */ -void __generic_unplug_device(struct request_queue *q) +static void blk_delay_work(struct work_struct *work) { - if (unlikely(blk_queue_stopped(q))) - return; - - if (!blk_remove_plug(q)) - return; + struct request_queue *q; - q->request_fn(q); + q = container_of(work, struct request_queue, delay_work.work); + spin_lock_irq(q->queue_lock); + __blk_run_queue(q); + spin_unlock_irq(q->queue_lock); } -EXPORT_SYMBOL(__generic_unplug_device); /** - * generic_unplug_device - fire a request queue - * @q: The &struct request_queue in question + * blk_delay_queue - restart queueing after defined interval + * @q: The &struct request_queue in question + * @msecs: Delay in msecs * * Description: - * Linux uses plugging to build bigger requests queues before letting - * the device have at them. If a queue is plugged, the I/O scheduler - * is still adding and merging requests on the queue. Once the queue - * gets unplugged, the request_fn defined for the queue is invoked and - * transfers started. - **/ -void generic_unplug_device(struct request_queue *q) -{ - if (blk_queue_plugged(q)) { - spin_lock_irq(q->queue_lock); - __generic_unplug_device(q); - spin_unlock_irq(q->queue_lock); - } -} -EXPORT_SYMBOL(generic_unplug_device); - -static void blk_backing_dev_unplug(struct backing_dev_info *bdi, - struct page *page) -{ - struct request_queue *q = bdi->unplug_io_data; - - blk_unplug(q); -} - -void blk_unplug_work(struct work_struct *work) -{ - struct request_queue *q = - container_of(work, struct request_queue, unplug_work); - - blk_add_trace_pdu_int(q, BLK_TA_UNPLUG_IO, NULL, - q->rq.count[READ] + q->rq.count[WRITE]); - - q->unplug_fn(q); -} - -void blk_unplug_timeout(unsigned long data) -{ - struct request_queue *q = (struct request_queue *)data; - - blk_add_trace_pdu_int(q, BLK_TA_UNPLUG_TIMER, NULL, - q->rq.count[READ] + q->rq.count[WRITE]); - - kblockd_schedule_work(&q->unplug_work); -} - -void blk_unplug(struct request_queue *q) + * Sometimes queueing needs to be postponed for a little while, to allow + * resources to come back. This function will make sure that queueing is + * restarted around the specified time. Queue lock must be held. + */ +void blk_delay_queue(struct request_queue *q, unsigned long msecs) { - /* - * devices don't necessarily have an ->unplug_fn defined - */ - if (q->unplug_fn) { - blk_add_trace_pdu_int(q, BLK_TA_UNPLUG_IO, NULL, - q->rq.count[READ] + q->rq.count[WRITE]); - - q->unplug_fn(q); - } + if (likely(!blk_queue_dead(q))) + queue_delayed_work(kblockd_workqueue, &q->delay_work, + msecs_to_jiffies(msecs)); } -EXPORT_SYMBOL(blk_unplug); +EXPORT_SYMBOL(blk_delay_queue); /** * blk_start_queue - restart a previously stopped queue @@ -321,18 +201,7 @@ void blk_start_queue(struct request_queue *q) WARN_ON(!irqs_disabled()); queue_flag_clear(QUEUE_FLAG_STOPPED, q); - - /* - * one level of recursion is ok and is much faster than kicking - * the unplug handling - */ - if (!queue_flag_test_and_set(QUEUE_FLAG_REENTER, q)) { - q->request_fn(q); - queue_flag_clear(QUEUE_FLAG_REENTER, q); - } else { - blk_plug_device(q); - kblockd_schedule_work(&q->unplug_work); - } + __blk_run_queue(q); } EXPORT_SYMBOL(blk_start_queue); @@ -352,7 +221,7 @@ EXPORT_SYMBOL(blk_start_queue); **/ void blk_stop_queue(struct request_queue *q) { - blk_remove_plug(q); + cancel_delayed_work(&q->delay_work); queue_flag_set(QUEUE_FLAG_STOPPED, q); } EXPORT_SYMBOL(blk_stop_queue); @@ -370,41 +239,96 @@ EXPORT_SYMBOL(blk_stop_queue); * that its ->make_request_fn 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 elevaotor_exit() + * and blkcg_exit_queue() to be called with queue lock initialized. + * */ void blk_sync_queue(struct request_queue *q) { - del_timer_sync(&q->unplug_timer); - kblockd_flush_work(&q->unplug_work); + del_timer_sync(&q->timeout); + + if (q->mq_ops) { + struct blk_mq_hw_ctx *hctx; + int i; + + queue_for_each_hw_ctx(q, hctx, i) { + cancel_delayed_work_sync(&hctx->run_work); + cancel_delayed_work_sync(&hctx->delay_work); + } + } else { + cancel_delayed_work_sync(&q->delay_work); + } } EXPORT_SYMBOL(blk_sync_queue); /** - * blk_run_queue - run a single device queue + * __blk_run_queue_uncond - run a queue whether or not it has been stopped * @q: The queue to run + * + * Description: + * Invoke request handling on a queue if there are any pending requests. + * May be used to restart request handling after a request has completed. + * This variant runs the queue whether or not the queue has been + * stopped. Must be called with the queue lock held and interrupts + * disabled. See also @blk_run_queue. */ -void __blk_run_queue(struct request_queue *q) +inline void __blk_run_queue_uncond(struct request_queue *q) { - blk_remove_plug(q); + if (unlikely(blk_queue_dead(q))) + return; /* - * Only recurse once to avoid overrunning the stack, let the unplug - * handling reinvoke the handler shortly if we already got there. + * Some request_fn implementations, e.g. scsi_request_fn(), unlock + * the queue lock internally. As a result multiple threads may be + * running such a request function concurrently. Keep track of the + * number of active request_fn invocations such that blk_drain_queue() + * can wait until all these request_fn calls have finished. */ - if (!elv_queue_empty(q)) { - if (!queue_flag_test_and_set(QUEUE_FLAG_REENTER, q)) { - q->request_fn(q); - queue_flag_clear(QUEUE_FLAG_REENTER, q); - } else { - blk_plug_device(q); - kblockd_schedule_work(&q->unplug_work); - } - } + q->request_fn_active++; + q->request_fn(q); + q->request_fn_active--; +} + +/** + * __blk_run_queue - run a single device queue + * @q: The queue to run + * + * Description: + * See @blk_run_queue. This variant must be called with the queue lock + * held and interrupts disabled. + */ +void __blk_run_queue(struct request_queue *q) +{ + if (unlikely(blk_queue_stopped(q))) + return; + + __blk_run_queue_uncond(q); } EXPORT_SYMBOL(__blk_run_queue); /** + * blk_run_queue_async - run a single device queue in workqueue context + * @q: The queue to run + * + * Description: + * Tells kblockd to perform the equivalent of @blk_run_queue on behalf + * of us. The caller must hold the queue lock. + */ +void blk_run_queue_async(struct request_queue *q) +{ + if (likely(!blk_queue_stopped(q) && !blk_queue_dead(q))) + mod_delayed_work(kblockd_workqueue, &q->delay_work, 0); +} +EXPORT_SYMBOL(blk_run_queue_async); + +/** * blk_run_queue - run a single device queue * @q: The queue to run + * + * Description: + * Invoke request handling on this queue, if it has pending work to do. + * May be used to restart queueing when a request has completed. */ void blk_run_queue(struct request_queue *q) { @@ -420,42 +344,226 @@ void blk_put_queue(struct request_queue *q) { kobject_put(&q->kobj); } +EXPORT_SYMBOL(blk_put_queue); + +/** + * __blk_drain_queue - drain requests from request_queue + * @q: queue to drain + * @drain_all: whether to drain all requests or only the ones w/ ELVPRIV + * + * Drain requests from @q. If @drain_all is set, all requests are drained. + * If not, only ELVPRIV requests are drained. The caller is responsible + * for ensuring that no new requests which need to be drained are queued. + */ +static void __blk_drain_queue(struct request_queue *q, bool drain_all) + __releases(q->queue_lock) + __acquires(q->queue_lock) +{ + int i; + + lockdep_assert_held(q->queue_lock); + + while (true) { + bool drain = false; + + /* + * The caller might be trying to drain @q before its + * elevator is initialized. + */ + if (q->elevator) + elv_drain_elevator(q); + + blkcg_drain_queue(q); + + /* + * This function might be called on a queue which failed + * driver init after queue creation or is not yet fully + * active yet. Some drivers (e.g. fd and loop) get unhappy + * in such cases. Kick queue iff dispatch queue has + * something on it and @q has request_fn set. + */ + if (!list_empty(&q->queue_head) && q->request_fn) + __blk_run_queue(q); + + drain |= q->nr_rqs_elvpriv; + drain |= q->request_fn_active; + /* + * Unfortunately, requests are queued at and tracked from + * multiple places and there's no single counter which can + * be drained. Check all the queues and counters. + */ + if (drain_all) { + drain |= !list_empty(&q->queue_head); + for (i = 0; i < 2; i++) { + drain |= q->nr_rqs[i]; + drain |= q->in_flight[i]; + drain |= !list_empty(&q->flush_queue[i]); + } + } + + if (!drain) + break; + + spin_unlock_irq(q->queue_lock); + + msleep(10); + + spin_lock_irq(q->queue_lock); + } + + /* + * With queue marked dead, any woken up waiter will fail the + * allocation path, so the wakeup chaining is lost and we're + * left with hung waiters. We need to wake up those waiters. + */ + if (q->request_fn) { + struct request_list *rl; + + blk_queue_for_each_rl(rl, q) + for (i = 0; i < ARRAY_SIZE(rl->wait); i++) + wake_up_all(&rl->wait[i]); + } +} + +/** + * blk_queue_bypass_start - enter queue bypass mode + * @q: queue of interest + * + * In bypass mode, only the dispatch FIFO queue of @q is used. This + * function makes @q enter bypass mode and drains all requests which were + * throttled or issued before. On return, it's guaranteed that no request + * is being throttled or has ELVPRIV set and blk_queue_bypass() %true + * inside queue or RCU read lock. + */ +void blk_queue_bypass_start(struct request_queue *q) +{ + bool drain; + + spin_lock_irq(q->queue_lock); + drain = !q->bypass_depth++; + queue_flag_set(QUEUE_FLAG_BYPASS, q); + spin_unlock_irq(q->queue_lock); + + if (drain) { + spin_lock_irq(q->queue_lock); + __blk_drain_queue(q, false); + spin_unlock_irq(q->queue_lock); + + /* ensure blk_queue_bypass() is %true inside RCU read lock */ + synchronize_rcu(); + } +} +EXPORT_SYMBOL_GPL(blk_queue_bypass_start); + +/** + * blk_queue_bypass_end - leave queue bypass mode + * @q: queue of interest + * + * Leave bypass mode and restore the normal queueing behavior. + */ +void blk_queue_bypass_end(struct request_queue *q) +{ + spin_lock_irq(q->queue_lock); + if (!--q->bypass_depth) + queue_flag_clear(QUEUE_FLAG_BYPASS, q); + WARN_ON_ONCE(q->bypass_depth < 0); + spin_unlock_irq(q->queue_lock); +} +EXPORT_SYMBOL_GPL(blk_queue_bypass_end); + +/** + * 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. + */ void blk_cleanup_queue(struct request_queue *q) { + spinlock_t *lock = q->queue_lock; + + /* mark @q DYING, no new request or merges will be allowed afterwards */ mutex_lock(&q->sysfs_lock); - queue_flag_set_unlocked(QUEUE_FLAG_DEAD, q); + queue_flag_set_unlocked(QUEUE_FLAG_DYING, q); + spin_lock_irq(lock); + + /* + * A dying queue is permanently in bypass mode till released. Note + * that, unlike blk_queue_bypass_start(), we aren't performing + * synchronize_rcu() after entering bypass mode to avoid the delay + * as some drivers create and destroy a lot of queues while + * probing. This is still safe because blk_release_queue() will be + * called only after the queue refcnt drops to zero and nothing, + * RCU or not, would be traversing the queue by then. + */ + q->bypass_depth++; + queue_flag_set(QUEUE_FLAG_BYPASS, q); + + queue_flag_set(QUEUE_FLAG_NOMERGES, q); + queue_flag_set(QUEUE_FLAG_NOXMERGES, q); + queue_flag_set(QUEUE_FLAG_DYING, q); + spin_unlock_irq(lock); mutex_unlock(&q->sysfs_lock); - if (q->elevator) - elevator_exit(q->elevator); + /* + * Drain all requests queued before DYING marking. Set DEAD flag to + * prevent that q->request_fn() gets invoked after draining finished. + */ + if (q->mq_ops) { + blk_mq_drain_queue(q); + spin_lock_irq(lock); + } else { + spin_lock_irq(lock); + __blk_drain_queue(q, true); + } + queue_flag_set(QUEUE_FLAG_DEAD, q); + spin_unlock_irq(lock); + + /* @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); + spin_lock_irq(lock); + if (q->queue_lock != &q->__queue_lock) + q->queue_lock = &q->__queue_lock; + spin_unlock_irq(lock); + + /* @q is and will stay empty, shutdown and put */ blk_put_queue(q); } EXPORT_SYMBOL(blk_cleanup_queue); -static int blk_init_free_list(struct request_queue *q) +int blk_init_rl(struct request_list *rl, struct request_queue *q, + gfp_t gfp_mask) { - struct request_list *rl = &q->rq; + if (unlikely(rl->rq_pool)) + return 0; - rl->count[READ] = rl->count[WRITE] = 0; - rl->starved[READ] = rl->starved[WRITE] = 0; - rl->elvpriv = 0; - init_waitqueue_head(&rl->wait[READ]); - init_waitqueue_head(&rl->wait[WRITE]); + rl->q = q; + rl->count[BLK_RW_SYNC] = rl->count[BLK_RW_ASYNC] = 0; + rl->starved[BLK_RW_SYNC] = rl->starved[BLK_RW_ASYNC] = 0; + init_waitqueue_head(&rl->wait[BLK_RW_SYNC]); + init_waitqueue_head(&rl->wait[BLK_RW_ASYNC]); rl->rq_pool = mempool_create_node(BLKDEV_MIN_RQ, mempool_alloc_slab, - mempool_free_slab, request_cachep, q->node); - + mempool_free_slab, request_cachep, + gfp_mask, q->node); if (!rl->rq_pool) return -ENOMEM; return 0; } +void blk_exit_rl(struct request_list *rl) +{ + if (rl->rq_pool) + mempool_destroy(rl->rq_pool); +} + struct request_queue *blk_alloc_queue(gfp_t gfp_mask) { - return blk_alloc_queue_node(gfp_mask, -1); + return blk_alloc_queue_node(gfp_mask, NUMA_NO_NODE); } EXPORT_SYMBOL(blk_alloc_queue); @@ -469,22 +577,69 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) if (!q) return NULL; - q->backing_dev_info.unplug_io_fn = blk_backing_dev_unplug; - q->backing_dev_info.unplug_io_data = q; - err = bdi_init(&q->backing_dev_info); - if (err) { - kmem_cache_free(blk_requestq_cachep, q); - return NULL; - } + q->id = ida_simple_get(&blk_queue_ida, 0, 0, gfp_mask); + if (q->id < 0) + goto fail_q; - init_timer(&q->unplug_timer); + q->backing_dev_info.ra_pages = + (VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE; + q->backing_dev_info.state = 0; + q->backing_dev_info.capabilities = BDI_CAP_MAP_COPY; + q->backing_dev_info.name = "block"; + q->node = node_id; + + err = bdi_init(&q->backing_dev_info); + if (err) + goto fail_id; + + setup_timer(&q->backing_dev_info.laptop_mode_wb_timer, + laptop_mode_timer_fn, (unsigned long) q); + setup_timer(&q->timeout, blk_rq_timed_out_timer, (unsigned long) q); + INIT_LIST_HEAD(&q->queue_head); + INIT_LIST_HEAD(&q->timeout_list); + INIT_LIST_HEAD(&q->icq_list); +#ifdef CONFIG_BLK_CGROUP + INIT_LIST_HEAD(&q->blkg_list); +#endif + INIT_LIST_HEAD(&q->flush_queue[0]); + INIT_LIST_HEAD(&q->flush_queue[1]); + INIT_LIST_HEAD(&q->flush_data_in_flight); + INIT_DELAYED_WORK(&q->delay_work, blk_delay_work); kobject_init(&q->kobj, &blk_queue_ktype); mutex_init(&q->sysfs_lock); spin_lock_init(&q->__queue_lock); + /* + * By default initialize queue_lock to internal lock and driver can + * override it later if need be. + */ + q->queue_lock = &q->__queue_lock; + + /* + * A queue starts its life with bypass turned on to avoid + * unnecessary bypass on/off overhead and nasty surprises during + * init. The initial bypass will be finished when the queue is + * registered by blk_register_queue(). + */ + q->bypass_depth = 1; + __set_bit(QUEUE_FLAG_BYPASS, &q->queue_flags); + + init_waitqueue_head(&q->mq_freeze_wq); + + if (blkcg_init_queue(q)) + goto fail_bdi; + return q; + +fail_bdi: + bdi_destroy(&q->backing_dev_info); +fail_id: + ida_simple_remove(&blk_queue_ida, q->id); +fail_q: + kmem_cache_free(blk_requestq_cachep, q); + return NULL; } EXPORT_SYMBOL(blk_alloc_queue_node); @@ -513,7 +668,7 @@ EXPORT_SYMBOL(blk_alloc_queue_node); * request queue; this lock will be taken also from interrupt context, so irq * disabling is needed for it. * - * Function returns a pointer to the initialized request queue, or NULL if + * Function returns a pointer to the initialized request queue, or %NULL if * it didn't succeed. * * Note: @@ -523,102 +678,96 @@ EXPORT_SYMBOL(blk_alloc_queue_node); struct request_queue *blk_init_queue(request_fn_proc *rfn, spinlock_t *lock) { - return blk_init_queue_node(rfn, lock, -1); + return blk_init_queue_node(rfn, lock, NUMA_NO_NODE); } EXPORT_SYMBOL(blk_init_queue); struct request_queue * blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id) { - struct request_queue *q = blk_alloc_queue_node(GFP_KERNEL, node_id); + struct request_queue *uninit_q, *q; + + uninit_q = blk_alloc_queue_node(GFP_KERNEL, node_id); + if (!uninit_q) + return NULL; + + q = blk_init_allocated_queue(uninit_q, rfn, lock); + if (!q) + blk_cleanup_queue(uninit_q); + + return q; +} +EXPORT_SYMBOL(blk_init_queue_node); +struct request_queue * +blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn, + spinlock_t *lock) +{ if (!q) return NULL; - q->node = node_id; - if (blk_init_free_list(q)) { - kmem_cache_free(blk_requestq_cachep, q); + q->flush_rq = kzalloc(sizeof(struct request), GFP_KERNEL); + if (!q->flush_rq) return NULL; - } - /* - * if caller didn't supply a lock, they get per-queue locking with - * our embedded lock - */ - if (!lock) - lock = &q->__queue_lock; + if (blk_init_rl(&q->root_rl, q, GFP_KERNEL)) + goto fail; q->request_fn = rfn; q->prep_rq_fn = NULL; - q->unplug_fn = generic_unplug_device; - q->queue_flags = (1 << QUEUE_FLAG_CLUSTER); - q->queue_lock = lock; + q->unprep_rq_fn = NULL; + q->queue_flags |= QUEUE_FLAG_DEFAULT; - blk_queue_segment_boundary(q, 0xffffffff); + /* Override internal queue lock with supplied lock pointer */ + if (lock) + q->queue_lock = lock; - blk_queue_make_request(q, __make_request); - blk_queue_max_segment_size(q, MAX_SEGMENT_SIZE); - - blk_queue_max_hw_segments(q, MAX_HW_SEGMENTS); - blk_queue_max_phys_segments(q, MAX_PHYS_SEGMENTS); + /* + * This also sets hw/phys segments, boundary and size + */ + blk_queue_make_request(q, blk_queue_bio); q->sg_reserved_size = INT_MAX; - /* - * all done - */ - if (!elevator_init(q, NULL)) { - blk_queue_congestion_threshold(q); - return q; + /* Protect q->elevator from elevator_change */ + mutex_lock(&q->sysfs_lock); + + /* init elevator */ + if (elevator_init(q, NULL)) { + mutex_unlock(&q->sysfs_lock); + goto fail; } - blk_put_queue(q); + mutex_unlock(&q->sysfs_lock); + + return q; + +fail: + kfree(q->flush_rq); return NULL; } -EXPORT_SYMBOL(blk_init_queue_node); +EXPORT_SYMBOL(blk_init_allocated_queue); -int blk_get_queue(struct request_queue *q) +bool blk_get_queue(struct request_queue *q) { - if (likely(!test_bit(QUEUE_FLAG_DEAD, &q->queue_flags))) { - kobject_get(&q->kobj); - return 0; + if (likely(!blk_queue_dying(q))) { + __blk_get_queue(q); + return true; } - return 1; + return false; } +EXPORT_SYMBOL(blk_get_queue); -static inline void blk_free_request(struct request_queue *q, struct request *rq) +static inline void blk_free_request(struct request_list *rl, struct request *rq) { - if (rq->cmd_flags & REQ_ELVPRIV) - elv_put_request(q, rq); - mempool_free(rq, q->rq.rq_pool); -} - -static struct request * -blk_alloc_request(struct request_queue *q, int rw, int priv, gfp_t gfp_mask) -{ - struct request *rq = mempool_alloc(q->rq.rq_pool, gfp_mask); - - if (!rq) - return NULL; - - blk_rq_init(q, rq); - - /* - * first three bits are identical in rq->cmd_flags and bio->bi_rw, - * see bio.h and blkdev.h - */ - rq->cmd_flags = rw | REQ_ALLOCED; - - if (priv) { - if (unlikely(elv_set_request(q, rq, gfp_mask))) { - mempool_free(rq, q->rq.rq_pool); - return NULL; - } - rq->cmd_flags |= REQ_ELVPRIV; + if (rq->cmd_flags & REQ_ELVPRIV) { + elv_put_request(rl->q, rq); + if (rq->elv.icq) + put_io_context(rq->elv.icq->ioc); } - return rq; + mempool_free(rq, rl->rq_pool); } /* @@ -655,18 +804,23 @@ static void ioc_set_batching(struct request_queue *q, struct io_context *ioc) ioc->last_waited = jiffies; } -static void __freed_request(struct request_queue *q, int rw) +static void __freed_request(struct request_list *rl, int sync) { - struct request_list *rl = &q->rq; + struct request_queue *q = rl->q; - if (rl->count[rw] < queue_congestion_off_threshold(q)) - blk_clear_queue_congested(q, rw); + /* + * bdi isn't aware of blkcg yet. As all async IOs end up root + * blkcg anyway, just use root blkcg state. + */ + if (rl == &q->root_rl && + rl->count[sync] < queue_congestion_off_threshold(q)) + blk_clear_queue_congested(q, sync); - if (rl->count[rw] + 1 <= q->nr_requests) { - if (waitqueue_active(&rl->wait[rw])) - wake_up(&rl->wait[rw]); + if (rl->count[sync] + 1 <= q->nr_requests) { + if (waitqueue_active(&rl->wait[sync])) + wake_up(&rl->wait[sync]); - blk_clear_queue_full(q, rw); + blk_clear_rl_full(rl, sync); } } @@ -674,51 +828,141 @@ static void __freed_request(struct request_queue *q, int rw) * A request has just been released. Account for it, update the full and * congestion status, wake up any waiters. Called under q->queue_lock. */ -static void freed_request(struct request_queue *q, int rw, int priv) +static void freed_request(struct request_list *rl, unsigned int flags) { - struct request_list *rl = &q->rq; + struct request_queue *q = rl->q; + int sync = rw_is_sync(flags); - rl->count[rw]--; - if (priv) - rl->elvpriv--; + q->nr_rqs[sync]--; + rl->count[sync]--; + if (flags & REQ_ELVPRIV) + q->nr_rqs_elvpriv--; - __freed_request(q, rw); + __freed_request(rl, sync); - if (unlikely(rl->starved[rw ^ 1])) - __freed_request(q, rw ^ 1); + if (unlikely(rl->starved[sync ^ 1])) + __freed_request(rl, sync ^ 1); +} + +int blk_update_nr_requests(struct request_queue *q, unsigned int nr) +{ + struct request_list *rl; + + spin_lock_irq(q->queue_lock); + q->nr_requests = nr; + blk_queue_congestion_threshold(q); + + /* congestion isn't cgroup aware and follows root blkcg for now */ + rl = &q->root_rl; + + if (rl->count[BLK_RW_SYNC] >= queue_congestion_on_threshold(q)) + blk_set_queue_congested(q, BLK_RW_SYNC); + else if (rl->count[BLK_RW_SYNC] < queue_congestion_off_threshold(q)) + blk_clear_queue_congested(q, BLK_RW_SYNC); + + if (rl->count[BLK_RW_ASYNC] >= queue_congestion_on_threshold(q)) + blk_set_queue_congested(q, BLK_RW_ASYNC); + else if (rl->count[BLK_RW_ASYNC] < queue_congestion_off_threshold(q)) + blk_clear_queue_congested(q, BLK_RW_ASYNC); + + blk_queue_for_each_rl(rl, q) { + if (rl->count[BLK_RW_SYNC] >= q->nr_requests) { + blk_set_rl_full(rl, BLK_RW_SYNC); + } else { + blk_clear_rl_full(rl, BLK_RW_SYNC); + wake_up(&rl->wait[BLK_RW_SYNC]); + } + + if (rl->count[BLK_RW_ASYNC] >= q->nr_requests) { + blk_set_rl_full(rl, BLK_RW_ASYNC); + } else { + blk_clear_rl_full(rl, BLK_RW_ASYNC); + wake_up(&rl->wait[BLK_RW_ASYNC]); + } + } + + spin_unlock_irq(q->queue_lock); + return 0; } -#define blkdev_free_rq(list) list_entry((list)->next, struct request, queuelist) /* - * Get a free request, queue_lock must be held. - * Returns NULL on failure, with queue_lock held. - * Returns !NULL on success, with queue_lock *not held*. + * Determine if elevator data should be initialized when allocating the + * request associated with @bio. */ -static struct request *get_request(struct request_queue *q, int rw_flags, - struct bio *bio, gfp_t gfp_mask) +static bool blk_rq_should_init_elevator(struct bio *bio) { - struct request *rq = NULL; - struct request_list *rl = &q->rq; - struct io_context *ioc = NULL; - const int rw = rw_flags & 0x01; - int may_queue, priv; + if (!bio) + return true; + + /* + * Flush requests do not use the elevator so skip initialization. + * This allows a request to share the flush and elevator data. + */ + if (bio->bi_rw & (REQ_FLUSH | REQ_FUA)) + return false; + + return true; +} + +/** + * rq_ioc - determine io_context for request allocation + * @bio: request being allocated is for this bio (can be %NULL) + * + * Determine io_context to use for request allocation for @bio. May return + * %NULL if %current->io_context doesn't exist. + */ +static struct io_context *rq_ioc(struct bio *bio) +{ +#ifdef CONFIG_BLK_CGROUP + if (bio && bio->bi_ioc) + return bio->bi_ioc; +#endif + return current->io_context; +} + +/** + * __get_request - get a free request + * @rl: request list to allocate from + * @rw_flags: RW and SYNC flags + * @bio: bio to allocate request for (can be %NULL) + * @gfp_mask: allocation mask + * + * Get a free request from @q. This function may fail under memory + * pressure or if @q is dead. + * + * Must be callled with @q->queue_lock held and, + * Returns %NULL on failure, with @q->queue_lock held. + * Returns !%NULL on success, with @q->queue_lock *not held*. + */ +static struct request *__get_request(struct request_list *rl, int rw_flags, + struct bio *bio, gfp_t gfp_mask) +{ + struct request_queue *q = rl->q; + struct request *rq; + struct elevator_type *et = q->elevator->type; + struct io_context *ioc = rq_ioc(bio); + struct io_cq *icq = NULL; + const bool is_sync = rw_is_sync(rw_flags) != 0; + int may_queue; + + if (unlikely(blk_queue_dying(q))) + return NULL; may_queue = elv_may_queue(q, rw_flags); if (may_queue == ELV_MQUEUE_NO) goto rq_starved; - if (rl->count[rw]+1 >= queue_congestion_on_threshold(q)) { - if (rl->count[rw]+1 >= q->nr_requests) { - ioc = current_io_context(GFP_ATOMIC, q->node); + if (rl->count[is_sync]+1 >= queue_congestion_on_threshold(q)) { + if (rl->count[is_sync]+1 >= q->nr_requests) { /* * The queue will fill after this allocation, so set * it as full, and mark this process as "batching". * This process will be allowed to complete a batch of * requests, others will be blocked. */ - if (!blk_queue_full(q, rw)) { + if (!blk_rl_full(rl, is_sync)) { ioc_set_batching(q, ioc); - blk_set_queue_full(q, rw); + blk_set_rl_full(rl, is_sync); } else { if (may_queue != ELV_MQUEUE_MUST && !ioc_batching(q, ioc)) { @@ -727,11 +971,16 @@ static struct request *get_request(struct request_queue *q, int rw_flags, * process is not a "batcher", and not * exempted by the IO scheduler */ - goto out; + return NULL; } } } - blk_set_queue_congested(q, rw); + /* + * bdi isn't aware of blkcg yet. As all async IOs end up + * root blkcg anyway, just use root blkcg state. + */ + if (rl == &q->root_rl) + blk_set_queue_congested(q, is_sync); } /* @@ -739,44 +988,61 @@ static struct request *get_request(struct request_queue *q, int rw_flags, * limit of requests, otherwise we could have thousands of requests * allocated with any setting of ->nr_requests */ - if (rl->count[rw] >= (3 * q->nr_requests / 2)) - goto out; + if (rl->count[is_sync] >= (3 * q->nr_requests / 2)) + return NULL; - rl->count[rw]++; - rl->starved[rw] = 0; + q->nr_rqs[is_sync]++; + rl->count[is_sync]++; + rl->starved[is_sync] = 0; - priv = !test_bit(QUEUE_FLAG_ELVSWITCH, &q->queue_flags); - if (priv) - rl->elvpriv++; + /* + * Decide whether the new request will be managed by elevator. If + * so, mark @rw_flags and increment elvpriv. Non-zero elvpriv will + * prevent the current elevator from being destroyed until the new + * request is freed. This guarantees icq's won't be destroyed and + * makes creating new ones safe. + * + * Also, lookup icq while holding queue_lock. If it doesn't exist, + * it will be created after releasing queue_lock. + */ + if (blk_rq_should_init_elevator(bio) && !blk_queue_bypass(q)) { + rw_flags |= REQ_ELVPRIV; + q->nr_rqs_elvpriv++; + if (et->icq_cache && ioc) + icq = ioc_lookup_icq(ioc, q); + } + if (blk_queue_io_stat(q)) + rw_flags |= REQ_IO_STAT; spin_unlock_irq(q->queue_lock); - rq = blk_alloc_request(q, rw_flags, priv, gfp_mask); - if (unlikely(!rq)) { - /* - * Allocation failed presumably due to memory. Undo anything - * we might have messed up. - * - * Allocating task should really be put onto the front of the - * wait queue, but this is pretty rare. - */ - spin_lock_irq(q->queue_lock); - freed_request(q, rw, priv); + /* allocate and init request */ + rq = mempool_alloc(rl->rq_pool, gfp_mask); + if (!rq) + goto fail_alloc; - /* - * in the very unlikely event that allocation failed and no - * requests for this direction was pending, mark us starved - * so that freeing of a request in the other direction will - * notice us. another possible fix would be to split the - * rq mempool into READ and WRITE - */ -rq_starved: - if (unlikely(rl->count[rw] == 0)) - rl->starved[rw] = 1; + blk_rq_init(q, rq); + blk_rq_set_rl(rq, rl); + rq->cmd_flags = rw_flags | REQ_ALLOCED; + + /* init elvpriv */ + if (rw_flags & REQ_ELVPRIV) { + if (unlikely(et->icq_cache && !icq)) { + if (ioc) + icq = ioc_create_icq(ioc, q, gfp_mask); + if (!icq) + goto fail_elvpriv; + } - goto out; - } + rq->elv.icq = icq; + if (unlikely(elv_set_request(q, rq, bio, gfp_mask))) + goto fail_elvpriv; + /* @rq->elv.icq holds io_context until @rq is freed */ + if (icq) + get_io_context(icq->ioc); + } +out: /* * ioc may be NULL here, and ioc_batching will be false. That's * OK, if the queue is under the request limit then requests need @@ -786,94 +1052,206 @@ rq_starved: if (ioc_batching(q, ioc)) ioc->nr_batch_requests--; - blk_add_trace_generic(q, bio, rw, BLK_TA_GETRQ); -out: + trace_block_getrq(q, bio, rw_flags & 1); return rq; + +fail_elvpriv: + /* + * elvpriv init failed. ioc, icq and elvpriv aren't mempool backed + * and may fail indefinitely under memory pressure and thus + * shouldn't stall IO. Treat this request as !elvpriv. This will + * disturb iosched and blkcg but weird is bettern than dead. + */ + printk_ratelimited(KERN_WARNING "%s: request aux data allocation failed, iosched may be disturbed\n", + dev_name(q->backing_dev_info.dev)); + + rq->cmd_flags &= ~REQ_ELVPRIV; + rq->elv.icq = NULL; + + spin_lock_irq(q->queue_lock); + q->nr_rqs_elvpriv--; + spin_unlock_irq(q->queue_lock); + goto out; + +fail_alloc: + /* + * Allocation failed presumably due to memory. Undo anything we + * might have messed up. + * + * Allocating task should really be put onto the front of the wait + * queue, but this is pretty rare. + */ + spin_lock_irq(q->queue_lock); + freed_request(rl, rw_flags); + + /* + * in the very unlikely event that allocation failed and no + * requests for this direction was pending, mark us starved so that + * freeing of a request in the other direction will notice + * us. another possible fix would be to split the rq mempool into + * READ and WRITE + */ +rq_starved: + if (unlikely(rl->count[is_sync] == 0)) + rl->starved[is_sync] = 1; + return NULL; } -/* - * No available requests for this queue, unplug the device and wait for some - * requests to become available. +/** + * get_request - get a free request + * @q: request_queue to allocate request from + * @rw_flags: RW and SYNC flags + * @bio: bio to allocate request for (can be %NULL) + * @gfp_mask: allocation mask + * + * Get a free request from @q. If %__GFP_WAIT is set in @gfp_mask, this + * function keeps retrying under memory pressure and fails iff @q is dead. * - * Called with q->queue_lock held, and returns with it unlocked. + * Must be callled with @q->queue_lock held and, + * Returns %NULL on failure, with @q->queue_lock held. + * Returns !%NULL on success, with @q->queue_lock *not held*. */ -static struct request *get_request_wait(struct request_queue *q, int rw_flags, - struct bio *bio) +static struct request *get_request(struct request_queue *q, int rw_flags, + struct bio *bio, gfp_t gfp_mask) { - const int rw = rw_flags & 0x01; + const bool is_sync = rw_is_sync(rw_flags) != 0; + DEFINE_WAIT(wait); + struct request_list *rl; struct request *rq; - rq = get_request(q, rw_flags, bio, GFP_NOIO); - while (!rq) { - DEFINE_WAIT(wait); - struct io_context *ioc; - struct request_list *rl = &q->rq; + rl = blk_get_rl(q, bio); /* transferred to @rq on success */ +retry: + rq = __get_request(rl, rw_flags, bio, gfp_mask); + if (rq) + return rq; - prepare_to_wait_exclusive(&rl->wait[rw], &wait, - TASK_UNINTERRUPTIBLE); + if (!(gfp_mask & __GFP_WAIT) || unlikely(blk_queue_dying(q))) { + blk_put_rl(rl); + return NULL; + } - blk_add_trace_generic(q, bio, rw, BLK_TA_SLEEPRQ); + /* wait on @rl and retry */ + prepare_to_wait_exclusive(&rl->wait[is_sync], &wait, + TASK_UNINTERRUPTIBLE); - __generic_unplug_device(q); - spin_unlock_irq(q->queue_lock); - io_schedule(); + trace_block_sleeprq(q, bio, rw_flags & 1); - /* - * After sleeping, we become a "batching" process and - * will be able to allocate at least one request, and - * up to a big batch of them for a small period time. - * See ioc_batching, ioc_set_batching - */ - ioc = current_io_context(GFP_NOIO, q->node); - ioc_set_batching(q, ioc); + spin_unlock_irq(q->queue_lock); + io_schedule(); - spin_lock_irq(q->queue_lock); - finish_wait(&rl->wait[rw], &wait); + /* + * After sleeping, we become a "batching" process and will be able + * to allocate at least one request, and up to a big batch of them + * for a small period time. See ioc_batching, ioc_set_batching + */ + ioc_set_batching(q, current->io_context); - rq = get_request(q, rw_flags, bio, GFP_NOIO); - }; + spin_lock_irq(q->queue_lock); + finish_wait(&rl->wait[is_sync], &wait); - return rq; + goto retry; } -struct request *blk_get_request(struct request_queue *q, int rw, gfp_t gfp_mask) +static struct request *blk_old_get_request(struct request_queue *q, int rw, + gfp_t gfp_mask) { struct request *rq; BUG_ON(rw != READ && rw != WRITE); + /* create ioc upfront */ + create_io_context(gfp_mask, q->node); + spin_lock_irq(q->queue_lock); - if (gfp_mask & __GFP_WAIT) { - rq = get_request_wait(q, rw, NULL); - } else { - rq = get_request(q, rw, NULL, gfp_mask); - if (!rq) - spin_unlock_irq(q->queue_lock); - } + rq = get_request(q, rw, NULL, gfp_mask); + if (!rq) + spin_unlock_irq(q->queue_lock); /* q->queue_lock is unlocked at this point */ return rq; } + +struct request *blk_get_request(struct request_queue *q, int rw, gfp_t gfp_mask) +{ + if (q->mq_ops) + return blk_mq_alloc_request(q, rw, gfp_mask, false); + else + return blk_old_get_request(q, rw, gfp_mask); +} EXPORT_SYMBOL(blk_get_request); /** - * blk_start_queueing - initiate dispatch of requests to device - * @q: request queue to kick into gear + * blk_make_request - given a bio, allocate a corresponding struct request. + * @q: target request queue + * @bio: The bio describing the memory mappings that will be submitted for IO. + * It may be a chained-bio properly constructed by block/bio layer. + * @gfp_mask: gfp flags to be used for memory allocation + * + * blk_make_request is the parallel of generic_make_request for BLOCK_PC + * type commands. Where the struct request needs to be farther initialized by + * the caller. It is passed a &struct bio, which describes the memory info of + * the I/O transfer. + * + * The caller of blk_make_request must make sure that bi_io_vec + * are set to describe the memory buffers. That bio_data_dir() will return + * the needed direction of the request. (And all bio's in the passed bio-chain + * are properly set accordingly) * - * This is basically a helper to remove the need to know whether a queue - * is plugged or not if someone just wants to initiate dispatch of requests - * for this queue. + * If called under none-sleepable conditions, mapped bio buffers must not + * need bouncing, by calling the appropriate masked or flagged allocator, + * suitable for the target device. Otherwise the call to blk_queue_bounce will + * BUG. * - * The queue lock must be held with interrupts disabled. + * WARNING: When allocating/cloning a bio-chain, careful consideration should be + * given to how you allocate bios. In particular, you cannot use __GFP_WAIT for + * anything but the first bio in the chain. Otherwise you risk waiting for IO + * completion of a bio that hasn't been submitted yet, thus resulting in a + * deadlock. Alternatively bios should be allocated using bio_kmalloc() instead + * of bio_alloc(), as that avoids the mempool deadlock. + * If possible a big IO should be split into smaller parts when allocation + * fails. Partial allocation should not be an error, or you risk a live-lock. */ -void blk_start_queueing(struct request_queue *q) +struct request *blk_make_request(struct request_queue *q, struct bio *bio, + gfp_t gfp_mask) { - if (!blk_queue_plugged(q)) - q->request_fn(q); - else - __generic_unplug_device(q); + struct request *rq = blk_get_request(q, bio_data_dir(bio), gfp_mask); + + if (unlikely(!rq)) + return ERR_PTR(-ENOMEM); + + blk_rq_set_block_pc(rq); + + for_each_bio(bio) { + struct bio *bounce_bio = bio; + int ret; + + blk_queue_bounce(q, &bounce_bio); + ret = blk_rq_append_bio(q, rq, bounce_bio); + if (unlikely(ret)) { + blk_put_request(rq); + return ERR_PTR(ret); + } + } + + return rq; +} +EXPORT_SYMBOL(blk_make_request); + +/** + * blk_rq_set_block_pc - initialize a requeest to type BLOCK_PC + * @rq: request to be initialized + * + */ +void blk_rq_set_block_pc(struct request *rq) +{ + rq->cmd_type = REQ_TYPE_BLOCK_PC; + rq->__data_len = 0; + rq->__sector = (sector_t) -1; + rq->bio = rq->biotail = NULL; + memset(rq->__cmd, 0, sizeof(rq->__cmd)); + rq->cmd = rq->__cmd; } -EXPORT_SYMBOL(blk_start_queueing); +EXPORT_SYMBOL(blk_rq_set_block_pc); /** * blk_requeue_request - put a request back on queue @@ -887,84 +1265,47 @@ EXPORT_SYMBOL(blk_start_queueing); */ void blk_requeue_request(struct request_queue *q, struct request *rq) { - blk_add_trace_rq(q, rq, BLK_TA_REQUEUE); + blk_delete_timer(rq); + blk_clear_rq_complete(rq); + trace_block_rq_requeue(q, rq); if (blk_rq_tagged(rq)) blk_queue_end_tag(q, rq); + BUG_ON(blk_queued_rq(rq)); + elv_requeue_request(q, rq); } EXPORT_SYMBOL(blk_requeue_request); -/** - * blk_insert_request - insert a special request in to a request queue - * @q: request queue where request should be inserted - * @rq: request to be inserted - * @at_head: insert request at head or tail of queue - * @data: private data - * - * Description: - * Many block devices need to execute commands asynchronously, so they don't - * block the whole kernel from preemption during request execution. This is - * accomplished normally by inserting aritficial requests tagged as - * REQ_SPECIAL in to the corresponding request queue, and letting them be - * scheduled for actual execution by the request queue. - * - * We have the option of inserting the head or the tail of the queue. - * Typically we use the tail for new ioctls and so forth. We use the head - * of the queue for things like a QUEUE_FULL message from a device, or a - * host that is unable to accept a particular command. - */ -void blk_insert_request(struct request_queue *q, struct request *rq, - int at_head, void *data) +static void add_acct_request(struct request_queue *q, struct request *rq, + int where) { - int where = at_head ? ELEVATOR_INSERT_FRONT : ELEVATOR_INSERT_BACK; - unsigned long flags; - - /* - * tell I/O scheduler that this isn't a regular read/write (ie it - * must not attempt merges on this) and that it acts as a soft - * barrier - */ - rq->cmd_type = REQ_TYPE_SPECIAL; - rq->cmd_flags |= REQ_SOFTBARRIER; - - rq->special = data; - - spin_lock_irqsave(q->queue_lock, flags); - - /* - * If command is tagged, release the tag - */ - if (blk_rq_tagged(rq)) - blk_queue_end_tag(q, rq); - - drive_stat_acct(rq, 1); - __elv_add_request(q, rq, where, 0); - blk_start_queueing(q); - spin_unlock_irqrestore(q->queue_lock, flags); + blk_account_io_start(rq, true); + __elv_add_request(q, rq, where); } -EXPORT_SYMBOL(blk_insert_request); -/* - * add-request adds a request to the linked list. - * queue lock is held and interrupts disabled, as we muck with the - * request queue list. - */ -static inline void add_request(struct request_queue *q, struct request *req) +static void part_round_stats_single(int cpu, struct hd_struct *part, + unsigned long now) { - drive_stat_acct(req, 1); + int inflight; - /* - * elevator indicated where it wants this request to be - * inserted at elevator_merge time - */ - __elv_add_request(q, req, ELEVATOR_INSERT_SORT, 0); + if (now == part->stamp) + return; + + inflight = part_in_flight(part); + if (inflight) { + __part_stat_add(cpu, part, time_in_queue, + inflight * (now - part->stamp)); + __part_stat_add(cpu, part, io_ticks, (now - part->stamp)); + } + part->stamp = now; } -/* - * disk_round_stats() - Round off the performance stats on a struct - * disk_stats. +/** + * part_round_stats() - Round off the performance stats on a struct disk_stats. + * @cpu: cpu number for stats access + * @part: target partition * * The average IO queue length and utilisation statistics are maintained * by observing the current state of the queue length and the amount of @@ -977,36 +1318,25 @@ static inline void add_request(struct request_queue *q, struct request *req) * /proc/diskstats. This accounts immediately for all queue usage up to * the current jiffies and restarts the counters again. */ -void disk_round_stats(struct gendisk *disk) +void part_round_stats(int cpu, struct hd_struct *part) { unsigned long now = jiffies; - if (now == disk->stamp) - return; - - if (disk->in_flight) { - __disk_stat_add(disk, time_in_queue, - disk->in_flight * (now - disk->stamp)); - __disk_stat_add(disk, io_ticks, (now - disk->stamp)); - } - disk->stamp = now; + if (part->partno) + part_round_stats_single(cpu, &part_to_disk(part)->part0, now); + part_round_stats_single(cpu, part, now); } -EXPORT_SYMBOL_GPL(disk_round_stats); +EXPORT_SYMBOL_GPL(part_round_stats); -void part_round_stats(struct hd_struct *part) +#ifdef CONFIG_PM_RUNTIME +static void blk_pm_put_request(struct request *rq) { - unsigned long now = jiffies; - - if (now == part->stamp) - return; - - if (part->in_flight) { - __part_stat_add(part, time_in_queue, - part->in_flight * (now - part->stamp)); - __part_stat_add(part, io_ticks, (now - part->stamp)); - } - part->stamp = now; + if (rq->q->dev && !(rq->cmd_flags & REQ_PM) && !--rq->q->nr_pending) + pm_runtime_mark_last_busy(rq->q->dev); } +#else +static inline void blk_pm_put_request(struct request *rq) {} +#endif /* * queue lock must be held @@ -1015,76 +1345,212 @@ void __blk_put_request(struct request_queue *q, struct request *req) { if (unlikely(!q)) return; - if (unlikely(--req->ref_count)) + + if (q->mq_ops) { + blk_mq_free_request(req); return; + } + + blk_pm_put_request(req); elv_completed_request(q, req); + /* this is a bio leak */ + WARN_ON(req->bio != NULL); + /* * Request may not have originated from ll_rw_blk. if not, * it didn't come out of our reserved rq pools */ if (req->cmd_flags & REQ_ALLOCED) { - int rw = rq_data_dir(req); - int priv = req->cmd_flags & REQ_ELVPRIV; + unsigned int flags = req->cmd_flags; + struct request_list *rl = blk_rq_rl(req); BUG_ON(!list_empty(&req->queuelist)); - BUG_ON(!hlist_unhashed(&req->hash)); + BUG_ON(ELV_ON_HASH(req)); - blk_free_request(q, req); - freed_request(q, rw, priv); + blk_free_request(rl, req); + freed_request(rl, flags); + blk_put_rl(rl); } } EXPORT_SYMBOL_GPL(__blk_put_request); void blk_put_request(struct request *req) { - unsigned long flags; struct request_queue *q = req->q; - spin_lock_irqsave(q->queue_lock, flags); - __blk_put_request(q, req); - spin_unlock_irqrestore(q->queue_lock, flags); + if (q->mq_ops) + blk_mq_free_request(req); + else { + unsigned long flags; + + spin_lock_irqsave(q->queue_lock, flags); + __blk_put_request(q, req); + spin_unlock_irqrestore(q->queue_lock, flags); + } } EXPORT_SYMBOL(blk_put_request); -void init_request_from_bio(struct request *req, struct bio *bio) +/** + * blk_add_request_payload - add a payload to a request + * @rq: request to update + * @page: page backing the payload + * @len: length of the payload. + * + * This allows to later add a payload to an already submitted request by + * a block driver. The driver needs to take care of freeing the payload + * itself. + * + * Note that this is a quite horrible hack and nothing but handling of + * discard requests should ever use it. + */ +void blk_add_request_payload(struct request *rq, struct page *page, + unsigned int len) { - req->cmd_type = REQ_TYPE_FS; + struct bio *bio = rq->bio; - /* - * inherit FAILFAST from bio (for read-ahead, and explicit FAILFAST) - */ - if (bio_rw_ahead(bio) || bio_failfast(bio)) - req->cmd_flags |= REQ_FAILFAST; + bio->bi_io_vec->bv_page = page; + bio->bi_io_vec->bv_offset = 0; + bio->bi_io_vec->bv_len = len; - /* - * REQ_BARRIER implies no merging, but lets make it explicit - */ - if (unlikely(bio_barrier(bio))) - req->cmd_flags |= (REQ_HARDBARRIER | REQ_NOMERGE); + bio->bi_iter.bi_size = len; + bio->bi_vcnt = 1; + bio->bi_phys_segments = 1; + + rq->__data_len = rq->resid_len = len; + rq->nr_phys_segments = 1; +} +EXPORT_SYMBOL_GPL(blk_add_request_payload); + +bool bio_attempt_back_merge(struct request_queue *q, struct request *req, + struct bio *bio) +{ + const int ff = bio->bi_rw & 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; + req->ioprio = ioprio_best(req->ioprio, bio_prio(bio)); + + 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_rw & 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); - if (bio_sync(bio)) - req->cmd_flags |= REQ_RW_SYNC; - if (bio_rw_meta(bio)) - req->cmd_flags |= REQ_RW_META; + bio->bi_next = req->bio; + req->bio = bio; + + req->__sector = bio->bi_iter.bi_sector; + req->__data_len += bio->bi_iter.bi_size; + req->ioprio = ioprio_best(req->ioprio, bio_prio(bio)); + + blk_account_io_start(req, false); + return true; +} + +/** + * 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 + * @request_count: out parameter for number of traversed plugged requests + * + * 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. + * + * 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. + * + * Caller must ensure !blk_queue_nomerges(q) beforehand. + */ +bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio, + unsigned int *request_count) +{ + struct blk_plug *plug; + struct request *rq; + bool ret = false; + struct list_head *plug_list; + + plug = current->plug; + if (!plug) + goto out; + *request_count = 0; + + if (q->mq_ops) + plug_list = &plug->mq_list; + else + plug_list = &plug->list; + + list_for_each_entry_reverse(rq, plug_list, queuelist) { + int el_ret; + + if (rq->q == q) + (*request_count)++; + + if (rq->q != q || !blk_rq_merge_ok(rq, bio)) + continue; + + el_ret = blk_try_merge(rq, bio); + if (el_ret == ELEVATOR_BACK_MERGE) { + ret = bio_attempt_back_merge(q, rq, bio); + if (ret) + break; + } else if (el_ret == ELEVATOR_FRONT_MERGE) { + ret = bio_attempt_front_merge(q, rq, bio); + if (ret) + break; + } + } +out: + return ret; +} + +void init_request_from_bio(struct request *req, struct bio *bio) +{ + req->cmd_type = REQ_TYPE_FS; + + req->cmd_flags |= bio->bi_rw & REQ_COMMON_MASK; + if (bio->bi_rw & REQ_RAHEAD) + req->cmd_flags |= REQ_FAILFAST_MASK; req->errors = 0; - req->hard_sector = req->sector = bio->bi_sector; + req->__sector = bio->bi_iter.bi_sector; req->ioprio = bio_prio(bio); - req->start_time = jiffies; blk_rq_bio_prep(req->q, req, bio); } -static int __make_request(struct request_queue *q, struct bio *bio) +void blk_queue_bio(struct request_queue *q, struct bio *bio) { + const bool sync = !!(bio->bi_rw & REQ_SYNC); + struct blk_plug *plug; + int el_ret, rw_flags, where = ELEVATOR_INSERT_SORT; struct request *req; - int el_ret, nr_sectors, barrier, err; - const unsigned short prio = bio_prio(bio); - const int sync = bio_sync(bio); - int rw_flags; - - nr_sectors = bio_sectors(bio); + unsigned int request_count = 0; /* * low level driver can indicate that it wants pages above a @@ -1093,66 +1559,42 @@ static int __make_request(struct request_queue *q, struct bio *bio) */ blk_queue_bounce(q, &bio); - barrier = bio_barrier(bio); - if (unlikely(barrier) && (q->next_ordered == QUEUE_ORDERED_NONE)) { - err = -EOPNOTSUPP; - goto end_io; + if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) { + bio_endio(bio, -EIO); + return; } - spin_lock_irq(q->queue_lock); - - if (unlikely(barrier) || elv_queue_empty(q)) + if (bio->bi_rw & (REQ_FLUSH | REQ_FUA)) { + spin_lock_irq(q->queue_lock); + where = ELEVATOR_INSERT_FLUSH; goto get_rq; + } - el_ret = elv_merge(q, &req, bio); - switch (el_ret) { - case ELEVATOR_BACK_MERGE: - BUG_ON(!rq_mergeable(req)); - - if (!ll_back_merge_fn(q, req, bio)) - break; - - blk_add_trace_bio(q, bio, BLK_TA_BACKMERGE); - - req->biotail->bi_next = bio; - req->biotail = bio; - req->nr_sectors = req->hard_nr_sectors += nr_sectors; - req->ioprio = ioprio_best(req->ioprio, prio); - drive_stat_acct(req, 0); - if (!attempt_back_merge(q, req)) - elv_merged_request(q, req, el_ret); - goto out; - - case ELEVATOR_FRONT_MERGE: - BUG_ON(!rq_mergeable(req)); - - if (!ll_front_merge_fn(q, req, bio)) - break; - - blk_add_trace_bio(q, bio, BLK_TA_FRONTMERGE); - - bio->bi_next = req->bio; - req->bio = bio; + /* + * Check if we can merge with the plugged list before grabbing + * any locks. + */ + if (!blk_queue_nomerges(q) && + blk_attempt_plug_merge(q, bio, &request_count)) + return; - /* - * may not be valid. if the low level driver said - * it didn't need a bounce buffer then it better - * not touch req->buffer either... - */ - req->buffer = bio_data(bio); - req->current_nr_sectors = bio_cur_sectors(bio); - req->hard_cur_sectors = req->current_nr_sectors; - req->sector = req->hard_sector = bio->bi_sector; - req->nr_sectors = req->hard_nr_sectors += nr_sectors; - req->ioprio = ioprio_best(req->ioprio, prio); - drive_stat_acct(req, 0); - if (!attempt_front_merge(q, req)) - elv_merged_request(q, req, el_ret); - goto out; + spin_lock_irq(q->queue_lock); - /* ELV_NO_MERGE: elevator says don't/can't merge. */ - default: - ; + el_ret = elv_merge(q, &req, bio); + if (el_ret == ELEVATOR_BACK_MERGE) { + if (bio_attempt_back_merge(q, req, bio)) { + elv_bio_merged(q, req, bio); + if (!attempt_back_merge(q, req)) + elv_merged_request(q, req, el_ret); + goto out_unlock; + } + } else if (el_ret == ELEVATOR_FRONT_MERGE) { + if (bio_attempt_front_merge(q, req, bio)) { + elv_bio_merged(q, req, bio); + if (!attempt_front_merge(q, req)) + elv_merged_request(q, req, el_ret); + goto out_unlock; + } } get_rq: @@ -1163,13 +1605,17 @@ get_rq: */ rw_flags = bio_data_dir(bio); if (sync) - rw_flags |= REQ_RW_SYNC; + rw_flags |= REQ_SYNC; /* * Grab a free request. This is might sleep but can not fail. * Returns with the queue unlocked. */ - req = get_request_wait(q, rw_flags, bio); + req = get_request(q, rw_flags, bio, GFP_NOIO); + if (unlikely(!req)) { + bio_endio(bio, -ENODEV); /* @q is dead */ + goto out_unlock; + } /* * After dropping the lock and possibly sleeping here, our request @@ -1179,21 +1625,34 @@ get_rq: */ init_request_from_bio(req, bio); - spin_lock_irq(q->queue_lock); - if (elv_queue_empty(q)) - blk_plug_device(q); - add_request(q, req); -out: - if (sync) - __generic_unplug_device(q); - - spin_unlock_irq(q->queue_lock); - return 0; + if (test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags)) + req->cpu = raw_smp_processor_id(); -end_io: - bio_endio(bio, err); - return 0; + plug = current->plug; + if (plug) { + /* + * If this is the first request added after a plug, fire + * of a plug trace. + */ + if (!request_count) + trace_block_plug(q); + else { + if (request_count >= BLK_MAX_REQUEST_COUNT) { + blk_flush_plug_list(plug, false); + trace_block_plug(q); + } + } + list_add_tail(&req->queuelist, &plug->list); + blk_account_io_start(req, true); + } else { + spin_lock_irq(q->queue_lock); + add_acct_request(q, req, where); + __blk_run_queue(q); +out_unlock: + spin_unlock_irq(q->queue_lock); + } } +EXPORT_SYMBOL_GPL(blk_queue_bio); /* for device mapper only */ /* * If bio->bi_dev is a partition, remap the location @@ -1205,12 +1664,12 @@ static inline void blk_partition_remap(struct bio *bio) if (bio_sectors(bio) && bdev != bdev->bd_contains) { struct hd_struct *p = bdev->bd_part; - bio->bi_sector += p->start_sect; + bio->bi_iter.bi_sector += p->start_sect; bio->bi_bdev = bdev->bd_contains; - blk_add_trace_remap(bdev_get_queue(bio->bi_bdev), bio, - bdev->bd_dev, bio->bi_sector, - bio->bi_sector - p->start_sect); + trace_block_bio_remap(bdev_get_queue(bio->bi_bdev), bio, + bdev->bd_dev, + bio->bi_iter.bi_sector - p->start_sect); } } @@ -1222,8 +1681,8 @@ static void handle_bad_sector(struct bio *bio) printk(KERN_INFO "%s: rw=%ld, want=%Lu, limit=%Lu\n", bdevname(bio->bi_bdev, b), bio->bi_rw, - (unsigned long long)bio->bi_sector + bio_sectors(bio), - (long long)(bio->bi_bdev->bd_inode->i_size >> 9)); + (unsigned long long)bio_end_sector(bio), + (long long)(i_size_read(bio->bi_bdev->bd_inode) >> 9)); set_bit(BIO_EOF, &bio->bi_flags); } @@ -1238,28 +1697,27 @@ static int __init setup_fail_make_request(char *str) } __setup("fail_make_request=", setup_fail_make_request); -static int should_fail_request(struct bio *bio) +static bool should_fail_request(struct hd_struct *part, unsigned int bytes) { - if ((bio->bi_bdev->bd_disk->flags & GENHD_FL_FAIL) || - (bio->bi_bdev->bd_part && bio->bi_bdev->bd_part->make_it_fail)) - return should_fail(&fail_make_request, bio->bi_size); - - return 0; + return part->make_it_fail && should_fail(&fail_make_request, bytes); } static int __init fail_make_request_debugfs(void) { - return init_fault_attr_dentries(&fail_make_request, - "fail_make_request"); + 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 int should_fail_request(struct bio *bio) +static inline bool should_fail_request(struct hd_struct *part, + unsigned int bytes) { - return 0; + return false; } #endif /* CONFIG_FAIL_MAKE_REQUEST */ @@ -1275,9 +1733,9 @@ static inline int bio_check_eod(struct bio *bio, unsigned int nr_sectors) return 0; /* Test device or partition size, when known. */ - maxsector = bio->bi_bdev->bd_inode->i_size >> 9; + maxsector = i_size_read(bio->bi_bdev->bd_inode) >> 9; if (maxsector) { - sector_t sector = bio->bi_sector; + sector_t sector = bio->bi_iter.bi_sector; if (maxsector < nr_sectors || maxsector - nr_sectors < sector) { /* @@ -1293,202 +1751,213 @@ static inline int bio_check_eod(struct bio *bio, unsigned int nr_sectors) return 0; } -/** - * 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 change bi_dev and - * bi_sector for remaps as it sees fit. So the values of these fields - * should NOT be depended on after the call to generic_make_request. - */ -static inline void __generic_make_request(struct bio *bio) +static noinline_for_stack bool +generic_make_request_checks(struct bio *bio) { struct request_queue *q; - sector_t old_sector; - int ret, nr_sectors = bio_sectors(bio); - dev_t old_dev; + int nr_sectors = bio_sectors(bio); int err = -EIO; + char b[BDEVNAME_SIZE]; + struct hd_struct *part; might_sleep(); if (bio_check_eod(bio, nr_sectors)) goto end_io; + q = bdev_get_queue(bio->bi_bdev); + if (unlikely(!q)) { + printk(KERN_ERR + "generic_make_request: Trying to access " + "nonexistent block-device %s (%Lu)\n", + bdevname(bio->bi_bdev, b), + (long long) bio->bi_iter.bi_sector); + goto end_io; + } + + if (likely(bio_is_rw(bio) && + nr_sectors > queue_max_hw_sectors(q))) { + printk(KERN_ERR "bio too big device %s (%u > %u)\n", + bdevname(bio->bi_bdev, b), + bio_sectors(bio), + queue_max_hw_sectors(q)); + goto end_io; + } + + part = bio->bi_bdev->bd_part; + if (should_fail_request(part, bio->bi_iter.bi_size) || + should_fail_request(&part_to_disk(part)->part0, + bio->bi_iter.bi_size)) + goto end_io; + /* - * Resolve the mapping until finished. (drivers are - * still free to implement/resolve their own stacking - * by explicitly returning 0) - * - * NOTE: we don't repeat the blk_size check for each new device. - * Stacking drivers are expected to know what they are doing. + * If this device has partitions, remap block n + * of partition p to block n+start(p) of the disk. */ - old_sector = -1; - old_dev = 0; - do { - char b[BDEVNAME_SIZE]; + blk_partition_remap(bio); - q = bdev_get_queue(bio->bi_bdev); - if (!q) { - printk(KERN_ERR - "generic_make_request: Trying to access " - "nonexistent block-device %s (%Lu)\n", - bdevname(bio->bi_bdev, b), - (long long) bio->bi_sector); -end_io: - bio_endio(bio, err); - break; - } + if (bio_check_eod(bio, nr_sectors)) + goto end_io; - if (unlikely(nr_sectors > q->max_hw_sectors)) { - printk(KERN_ERR "bio too big device %s (%u > %u)\n", - bdevname(bio->bi_bdev, b), - bio_sectors(bio), - q->max_hw_sectors); + /* + * Filter flush bio's early so that make_request based + * drivers without flush support don't have to worry + * about them. + */ + if ((bio->bi_rw & (REQ_FLUSH | REQ_FUA)) && !q->flush_flags) { + bio->bi_rw &= ~(REQ_FLUSH | REQ_FUA); + if (!nr_sectors) { + err = 0; goto end_io; } + } - if (unlikely(test_bit(QUEUE_FLAG_DEAD, &q->queue_flags))) - goto end_io; - - if (should_fail_request(bio)) - goto end_io; - - /* - * If this device has partitions, remap block n - * of partition p to block n+start(p) of the disk. - */ - blk_partition_remap(bio); - - if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) - goto end_io; + if ((bio->bi_rw & REQ_DISCARD) && + (!blk_queue_discard(q) || + ((bio->bi_rw & REQ_SECURE) && !blk_queue_secdiscard(q)))) { + err = -EOPNOTSUPP; + goto end_io; + } - if (old_sector != -1) - blk_add_trace_remap(q, bio, old_dev, bio->bi_sector, - old_sector); + if (bio->bi_rw & REQ_WRITE_SAME && !bdev_write_same(bio->bi_bdev)) { + err = -EOPNOTSUPP; + goto end_io; + } - blk_add_trace_bio(q, bio, BLK_TA_QUEUE); + /* + * 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); - old_sector = bio->bi_sector; - old_dev = bio->bi_bdev->bd_dev; + if (blk_throtl_bio(q, bio)) + return false; /* throttled, will be resubmitted later */ - if (bio_check_eod(bio, nr_sectors)) - goto end_io; - if (bio_empty_barrier(bio) && !q->prepare_flush_fn) { - err = -EOPNOTSUPP; - goto end_io; - } + trace_block_bio_queue(q, bio); + return true; - ret = q->make_request_fn(q, bio); - } while (ret); +end_io: + bio_endio(bio, err); + return false; } -/* - * 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,tail} to keep a list of requests - * submited by a make_request_fn function. - * current->bio_tail 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 +/** + * 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. */ void generic_make_request(struct bio *bio) { - if (current->bio_tail) { - /* make_request is active */ - *(current->bio_tail) = bio; - bio->bi_next = NULL; - current->bio_tail = &bio->bi_next; + struct bio_list bio_list_on_stack; + + if (!generic_make_request_checks(bio)) + return; + + /* + * 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(current->bio_list, bio); return; } + /* 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 the next (which is NULL) and bio_tail - * to &bio_list, thus initialising the bio_list of new bios to be - * added. __generic_make_request may indeed add some more bios + * 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 fixup bio_list and - * bio_tail or bi_next, and call into __generic_make_request again. - * - * The loop was structured like this to make only one call to - * __generic_make_request (which is important as it is large and - * inlined) and to keep the structure simple. + * 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); + current->bio_list = &bio_list_on_stack; do { - current->bio_list = bio->bi_next; - if (bio->bi_next == NULL) - current->bio_tail = ¤t->bio_list; - else - bio->bi_next = NULL; - __generic_make_request(bio); - bio = current->bio_list; + struct request_queue *q = bdev_get_queue(bio->bi_bdev); + + q->make_request_fn(q, bio); + + bio = bio_list_pop(current->bio_list); } while (bio); - current->bio_tail = NULL; /* deactivate */ + current->bio_list = NULL; /* deactivate */ } EXPORT_SYMBOL(generic_make_request); /** - * submit_bio: submit a bio to the block device layer for I/O + * submit_bio - submit a bio to the block device layer for I/O * @rw: whether to %READ or %WRITE, or maybe to %READA (read ahead) * @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. + * interfaces; @bio must be presetup and ready for I/O. * */ void submit_bio(int rw, struct bio *bio) { - int count = bio_sectors(bio); - bio->bi_rw |= rw; /* * If it's a regular read/write or a barrier with data attached, * go through the normal accounting stuff before submission. */ - if (!bio_empty_barrier(bio)) { + if (bio_has_data(bio)) { + unsigned int count; - BIO_BUG_ON(!bio->bi_size); - BIO_BUG_ON(!bio->bi_io_vec); + if (unlikely(rw & REQ_WRITE_SAME)) + count = bdev_logical_block_size(bio->bi_bdev) >> 9; + else + count = bio_sectors(bio); if (rw & WRITE) { count_vm_events(PGPGOUT, count); } else { - task_io_account_read(bio->bi_size); + 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\n", + printk(KERN_DEBUG "%s(%d): %s block %Lu on %s (%u sectors)\n", current->comm, task_pid_nr(current), (rw & WRITE) ? "WRITE" : "READ", - (unsigned long long)bio->bi_sector, - bdevname(bio->bi_bdev, b)); + (unsigned long long)bio->bi_iter.bi_sector, + bdevname(bio->bi_bdev, b), + count); } } @@ -1497,240 +1966,611 @@ void submit_bio(int rw, struct bio *bio) EXPORT_SYMBOL(submit_bio); /** - * __end_that_request_first - end I/O on a request - * @req: the request being processed - * @error: 0 for success, < 0 for error - * @nr_bytes: number of bytes to complete + * blk_rq_check_limits - Helper function to check a request for the queue limit + * @q: the queue + * @rq: the request being checked * * Description: - * Ends I/O on a number of bytes attached to @req, and sets it up - * for the next range of segments (if any) in the cluster. + * @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. + * + * This function should also be useful for request stacking drivers + * in some cases below, so export this function. + * Request stacking drivers like request-based dm may change the queue + * limits while requests are in the queue (e.g. dm's table swapping). + * Such request stacking drivers should check those requests against + * the new queue limits again when they dispatch those requests, + * although such checkings are also done against the old queue limits + * when submitting requests. + */ +int blk_rq_check_limits(struct request_queue *q, struct request *rq) +{ + if (!rq_mergeable(rq)) + return 0; + + if (blk_rq_sectors(rq) > blk_queue_get_max_sectors(q, rq->cmd_flags)) { + printk(KERN_ERR "%s: over max size limit.\n", __func__); + 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.\n", __func__); + return -EIO; + } + + return 0; +} +EXPORT_SYMBOL_GPL(blk_rq_check_limits); + +/** + * blk_insert_cloned_request - Helper for stacking drivers to submit a request + * @q: the queue to submit the request + * @rq: the request being queued + */ +int blk_insert_cloned_request(struct request_queue *q, struct request *rq) +{ + unsigned long flags; + int where = ELEVATOR_INSERT_BACK; + + if (blk_rq_check_limits(q, rq)) + return -EIO; + + if (rq->rq_disk && + should_fail_request(&rq->rq_disk->part0, blk_rq_bytes(rq))) + return -EIO; + + spin_lock_irqsave(q->queue_lock, flags); + if (unlikely(blk_queue_dying(q))) { + spin_unlock_irqrestore(q->queue_lock, flags); + return -ENODEV; + } + + /* + * Submitting request must be dequeued before calling this function + * because it will be linked to another request_queue + */ + BUG_ON(blk_queued_rq(rq)); + + if (rq->cmd_flags & (REQ_FLUSH|REQ_FUA)) + where = ELEVATOR_INSERT_FLUSH; + + add_acct_request(q, rq, where); + if (where == ELEVATOR_INSERT_FLUSH) + __blk_run_queue(q); + spin_unlock_irqrestore(q->queue_lock, flags); + + return 0; +} +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: - * 0 - we are done with this request, call end_that_request_last() - * 1 - still buffers pending for this request - **/ -static int __end_that_request_first(struct request *req, int error, - int nr_bytes) + * The number of bytes to fail. + * + * Context: + * queue_lock must be held. + */ +unsigned int blk_rq_err_bytes(const struct request *rq) { - int total_bytes, bio_nbytes, next_idx = 0; + unsigned int ff = rq->cmd_flags & REQ_FAILFAST_MASK; + unsigned int bytes = 0; struct bio *bio; - blk_add_trace_rq(req->q, req, BLK_TA_COMPLETE); + if (!(rq->cmd_flags & REQ_MIXED_MERGE)) + return blk_rq_bytes(rq); /* - * for a REQ_BLOCK_PC request, we want to carry any eventual - * sense key with us all the way through + * 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. */ - if (!blk_pc_request(req)) - req->errors = 0; + for (bio = rq->bio; bio; bio = bio->bi_next) { + if ((bio->bi_rw & 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); - if (error && (blk_fs_request(req) && !(req->cmd_flags & REQ_QUIET))) { - printk(KERN_ERR "end_request: I/O error, dev %s, sector %llu\n", - req->rq_disk ? req->rq_disk->disk_name : "?", - (unsigned long long)req->sector); +void blk_account_io_completion(struct request *req, unsigned int bytes) +{ + if (blk_do_io_stat(req)) { + const int rw = rq_data_dir(req); + struct hd_struct *part; + int cpu; + + cpu = part_stat_lock(); + part = req->part; + part_stat_add(cpu, part, sectors[rw], bytes >> 9); + part_stat_unlock(); } +} - if (blk_fs_request(req) && req->rq_disk) { - struct hd_struct *part = get_part(req->rq_disk, req->sector); +void blk_account_io_done(struct request *req) +{ + /* + * 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->cmd_flags & REQ_FLUSH_SEQ)) { + unsigned long duration = jiffies - req->start_time; const int rw = rq_data_dir(req); + struct hd_struct *part; + int cpu; - all_stat_add(req->rq_disk, part, sectors[rw], - nr_bytes >> 9, req->sector); + cpu = part_stat_lock(); + part = req->part; + + part_stat_inc(cpu, part, ios[rw]); + part_stat_add(cpu, part, ticks[rw], duration); + part_round_stats(cpu, part); + part_dec_in_flight(part, rw); + + hd_struct_put(part); + part_stat_unlock(); } +} - total_bytes = bio_nbytes = 0; - while ((bio = req->bio) != NULL) { - int nbytes; +#ifdef CONFIG_PM_RUNTIME +/* + * Don't process normal requests when queue is suspended + * or in the process of suspending/resuming + */ +static struct request *blk_pm_peek_request(struct request_queue *q, + struct request *rq) +{ + if (q->dev && (q->rpm_status == RPM_SUSPENDED || + (q->rpm_status != RPM_ACTIVE && !(rq->cmd_flags & REQ_PM)))) + return NULL; + else + return rq; +} +#else +static inline struct request *blk_pm_peek_request(struct request_queue *q, + struct request *rq) +{ + return rq; +} +#endif - /* - * For an empty barrier request, the low level driver must - * store a potential error location in ->sector. We pass - * that back up in ->bi_sector. - */ - if (blk_empty_barrier(req)) - bio->bi_sector = req->sector; +void blk_account_io_start(struct request *rq, bool new_io) +{ + struct hd_struct *part; + int rw = rq_data_dir(rq); + int cpu; - if (nr_bytes >= bio->bi_size) { - req->bio = bio->bi_next; - nbytes = bio->bi_size; - req_bio_endio(req, bio, nbytes, error); - next_idx = 0; - bio_nbytes = 0; - } else { - int idx = bio->bi_idx + next_idx; + if (!blk_do_io_stat(rq)) + return; - if (unlikely(bio->bi_idx >= bio->bi_vcnt)) { - blk_dump_rq_flags(req, "__end_that"); - printk(KERN_ERR "%s: bio idx %d >= vcnt %d\n", - __func__, bio->bi_idx, bio->bi_vcnt); - break; - } + cpu = part_stat_lock(); + + if (!new_io) { + part = rq->part; + part_stat_inc(cpu, 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_round_stats(cpu, part); + part_inc_in_flight(part, rw); + rq->part = part; + } + + part_stat_unlock(); +} + +/** + * blk_peek_request - peek at the top of a request queue + * @q: request queue to peek at + * + * Description: + * Return the request at the top of @q. The returned request + * should be started using blk_start_request() before LLD starts + * processing it. + * + * Return: + * Pointer to the request at the top of @q if available. Null + * otherwise. + * + * Context: + * queue_lock must be held. + */ +struct request *blk_peek_request(struct request_queue *q) +{ + struct request *rq; + int ret; - nbytes = bio_iovec_idx(bio, idx)->bv_len; - BIO_BUG_ON(nbytes > bio->bi_size); + while ((rq = __elv_next_request(q)) != NULL) { + rq = blk_pm_peek_request(q, rq); + if (!rq) + break; + + if (!(rq->cmd_flags & REQ_STARTED)) { /* - * not a complete bvec done + * This is the first time the device driver + * sees this request (possibly after + * requeueing). Notify IO scheduler. */ - if (unlikely(nbytes > nr_bytes)) { - bio_nbytes += nr_bytes; - total_bytes += nr_bytes; - break; - } + if (rq->cmd_flags & REQ_SORTED) + elv_activate_rq(q, rq); /* - * advance to the next vector + * just mark as started even if we don't start + * it, a request that has been delayed should + * not be passed by new incoming requests */ - next_idx++; - bio_nbytes += nbytes; + rq->cmd_flags |= REQ_STARTED; + trace_block_rq_issue(q, rq); } - total_bytes += nbytes; - nr_bytes -= nbytes; + if (!q->boundary_rq || q->boundary_rq == rq) { + q->end_sector = rq_end_sector(rq); + q->boundary_rq = NULL; + } - bio = req->bio; - if (bio) { + if (rq->cmd_flags & REQ_DONTPREP) + break; + + if (q->dma_drain_size && blk_rq_bytes(rq)) { /* - * end more in this run, or just return 'not-done' + * make sure space for the drain appears we + * know we can do this because max_hw_segments + * has been adjusted to be one fewer than the + * device can handle */ - if (unlikely(nr_bytes <= 0)) - break; + rq->nr_phys_segments++; } - } - /* - * completely done - */ - if (!req->bio) - return 0; + if (!q->prep_rq_fn) + break; - /* - * if the request wasn't completed, update state - */ - if (bio_nbytes) { - req_bio_endio(req, bio, bio_nbytes, error); - bio->bi_idx += next_idx; - bio_iovec(bio)->bv_offset += nr_bytes; - bio_iovec(bio)->bv_len -= nr_bytes; + ret = q->prep_rq_fn(q, rq); + if (ret == BLKPREP_OK) { + break; + } else if (ret == BLKPREP_DEFER) { + /* + * the request may have been (partially) prepped. + * we need to keep this request in the front to + * avoid resource deadlock. REQ_STARTED will + * prevent other fs requests from passing this one. + */ + if (q->dma_drain_size && blk_rq_bytes(rq) && + !(rq->cmd_flags & REQ_DONTPREP)) { + /* + * remove the space for the drain we added + * so that we don't add it again + */ + --rq->nr_phys_segments; + } + + rq = NULL; + break; + } else if (ret == BLKPREP_KILL) { + rq->cmd_flags |= REQ_QUIET; + /* + * Mark this request as started so we don't trigger + * any debug logic in the end I/O path. + */ + blk_start_request(rq); + __blk_end_request_all(rq, -EIO); + } else { + printk(KERN_ERR "%s: bad return=%d\n", __func__, ret); + break; + } } - blk_recalc_rq_sectors(req, total_bytes >> 9); - blk_recalc_rq_segments(req); - return 1; + return rq; } +EXPORT_SYMBOL(blk_peek_request); -/* - * splice the completion data to a local structure and hand off to - * process_completion_queue() to complete the requests - */ -static void blk_done_softirq(struct softirq_action *h) +void blk_dequeue_request(struct request *rq) { - struct list_head *cpu_list, local_list; + struct request_queue *q = rq->q; - local_irq_disable(); - cpu_list = &__get_cpu_var(blk_cpu_done); - list_replace_init(cpu_list, &local_list); - local_irq_enable(); + BUG_ON(list_empty(&rq->queuelist)); + BUG_ON(ELV_ON_HASH(rq)); - while (!list_empty(&local_list)) { - struct request *rq; + list_del_init(&rq->queuelist); - rq = list_entry(local_list.next, struct request, donelist); - list_del_init(&rq->donelist); - rq->q->softirq_done_fn(rq); + /* + * the time frame between a request being removed from the lists + * and to it is freed is accounted as io that is in progress at + * the driver side. + */ + if (blk_account_rq(rq)) { + q->in_flight[rq_is_sync(rq)]++; + set_io_start_time_ns(rq); } } -static int __cpuinit blk_cpu_notify(struct notifier_block *self, - unsigned long action, void *hcpu) +/** + * blk_start_request - start request processing on the driver + * @req: request to dequeue + * + * Description: + * Dequeue @req and start timeout timer on it. This hands off the + * request to the driver. + * + * Block internal functions which don't want to start timer should + * call blk_dequeue_request(). + * + * Context: + * queue_lock must be held. + */ +void blk_start_request(struct request *req) { + blk_dequeue_request(req); + /* - * If a CPU goes away, splice its entries to the current CPU - * and trigger a run of the softirq + * We are now handing the request to the hardware, initialize + * resid_len to full count and add the timeout handler. */ - if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) { - int cpu = (unsigned long) hcpu; - - local_irq_disable(); - list_splice_init(&per_cpu(blk_cpu_done, cpu), - &__get_cpu_var(blk_cpu_done)); - raise_softirq_irqoff(BLOCK_SOFTIRQ); - local_irq_enable(); - } + req->resid_len = blk_rq_bytes(req); + if (unlikely(blk_bidi_rq(req))) + req->next_rq->resid_len = blk_rq_bytes(req->next_rq); - return NOTIFY_OK; + BUG_ON(test_bit(REQ_ATOM_COMPLETE, &req->atomic_flags)); + blk_add_timer(req); } +EXPORT_SYMBOL(blk_start_request); +/** + * blk_fetch_request - fetch a request from a request queue + * @q: request queue to fetch a request from + * + * Description: + * Return the request at the top of @q. The request is started on + * return and LLD can start processing it immediately. + * + * Return: + * Pointer to the request at the top of @q if available. Null + * otherwise. + * + * Context: + * queue_lock must be held. + */ +struct request *blk_fetch_request(struct request_queue *q) +{ + struct request *rq; -static struct notifier_block blk_cpu_notifier __cpuinitdata = { - .notifier_call = blk_cpu_notify, -}; + rq = blk_peek_request(q); + if (rq) + blk_start_request(rq); + return rq; +} +EXPORT_SYMBOL(blk_fetch_request); /** - * blk_complete_request - end I/O on a request + * blk_update_request - Special helper function for request stacking drivers * @req: the request being processed + * @error: %0 for success, < %0 for error + * @nr_bytes: number of bytes to complete @req * * Description: - * Ends all I/O on a request. It does not handle partial completions, - * unless the driver actually implements this in its completion callback - * through requeueing. The actual completion happens out-of-order, - * through a softirq handler. The user must have registered a completion - * callback through blk_queue_softirq_done(). + * 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. + * + * 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. + * + * Return: + * %false - this request doesn't have any more data + * %true - this request has more data **/ +bool blk_update_request(struct request *req, int error, unsigned int nr_bytes) +{ + int total_bytes; + + if (!req->bio) + return false; + + trace_block_rq_complete(req->q, req, nr_bytes); + + /* + * For fs requests, rq is just carrier of independent bio's + * and each partial completion should be handled separately. + * Reset per-request error on each partial completion. + * + * TODO: tj: This is too subtle. It would be better to let + * low level drivers do what they see fit. + */ + if (req->cmd_type == REQ_TYPE_FS) + req->errors = 0; + + if (error && req->cmd_type == REQ_TYPE_FS && + !(req->cmd_flags & REQ_QUIET)) { + char *error_type; + + switch (error) { + case -ENOLINK: + error_type = "recoverable transport"; + break; + case -EREMOTEIO: + error_type = "critical target"; + break; + case -EBADE: + error_type = "critical nexus"; + break; + case -ETIMEDOUT: + error_type = "timeout"; + break; + case -ENOSPC: + error_type = "critical space allocation"; + break; + case -ENODATA: + error_type = "critical medium"; + break; + case -EIO: + default: + error_type = "I/O"; + break; + } + printk_ratelimited(KERN_ERR "end_request: %s error, dev %s, sector %llu\n", + error_type, req->rq_disk ? + req->rq_disk->disk_name : "?", + (unsigned long long)blk_rq_pos(req)); + + } + + 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; + + req_bio_endio(req, bio, bio_bytes, error); -void blk_complete_request(struct request *req) + 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 (req->cmd_type == REQ_TYPE_FS) + req->__sector += total_bytes >> 9; + + /* mixed attributes always follow the first bio */ + if (req->cmd_flags & REQ_MIXED_MERGE) { + req->cmd_flags &= ~REQ_FAILFAST_MASK; + req->cmd_flags |= req->bio->bi_rw & REQ_FAILFAST_MASK; + } + + /* + * 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; +} +EXPORT_SYMBOL_GPL(blk_update_request); + +static bool blk_update_bidi_request(struct request *rq, int error, + unsigned int nr_bytes, + unsigned int bidi_bytes) { - struct list_head *cpu_list; - unsigned long flags; + if (blk_update_request(rq, error, nr_bytes)) + return true; - BUG_ON(!req->q->softirq_done_fn); + /* Bidi request must be completed as a whole */ + if (unlikely(blk_bidi_rq(rq)) && + blk_update_request(rq->next_rq, error, bidi_bytes)) + return true; - local_irq_save(flags); + if (blk_queue_add_random(rq->q)) + add_disk_randomness(rq->rq_disk); - cpu_list = &__get_cpu_var(blk_cpu_done); - list_add_tail(&req->donelist, cpu_list); - raise_softirq_irqoff(BLOCK_SOFTIRQ); + return false; +} - local_irq_restore(flags); +/** + * blk_unprep_request - unprepare a request + * @req: the request + * + * This function makes a request ready for complete resubmission (or + * completion). It happens only after all error handling is complete, + * so represents the appropriate moment to deallocate any resources + * that were allocated to the request in the prep_rq_fn. The queue + * lock is held when calling this. + */ +void blk_unprep_request(struct request *req) +{ + struct request_queue *q = req->q; + + req->cmd_flags &= ~REQ_DONTPREP; + if (q->unprep_rq_fn) + q->unprep_rq_fn(q, req); } -EXPORT_SYMBOL(blk_complete_request); +EXPORT_SYMBOL_GPL(blk_unprep_request); /* * queue lock must be held */ -static void end_that_request_last(struct request *req, int error) +void blk_finish_request(struct request *req, int error) { - struct gendisk *disk = req->rq_disk; - if (blk_rq_tagged(req)) blk_queue_end_tag(req->q, req); - if (blk_queued_rq(req)) - blkdev_dequeue_request(req); + BUG_ON(blk_queued_rq(req)); - if (unlikely(laptop_mode) && blk_fs_request(req)) - laptop_io_completion(); + if (unlikely(laptop_mode) && req->cmd_type == REQ_TYPE_FS) + laptop_io_completion(&req->q->backing_dev_info); - /* - * Account IO completion. bar_rq isn't accounted as a normal - * IO on queueing nor completion. Accounting the containing - * request is enough. - */ - if (disk && blk_fs_request(req) && req != &req->q->bar_rq) { - unsigned long duration = jiffies - req->start_time; - const int rw = rq_data_dir(req); - struct hd_struct *part = get_part(disk, req->sector); - - __all_stat_inc(disk, part, ios[rw], req->sector); - __all_stat_add(disk, part, ticks[rw], duration, req->sector); - disk_round_stats(disk); - disk->in_flight--; - if (part) { - part_round_stats(part); - part->in_flight--; - } - } + blk_delete_timer(req); + + if (req->cmd_flags & REQ_DONTPREP) + blk_unprep_request(req); + + blk_account_io_done(req); if (req->end_io) req->end_io(req, error); @@ -1741,295 +2581,738 @@ static void end_that_request_last(struct request *req, int error) __blk_put_request(req->q, req); } } +EXPORT_SYMBOL(blk_finish_request); -static inline void __end_request(struct request *rq, int uptodate, - unsigned int nr_bytes) +/** + * blk_end_bidi_request - Complete a bidi request + * @rq: the request to complete + * @error: %0 for success, < %0 for error + * @nr_bytes: number of bytes to complete @rq + * @bidi_bytes: number of bytes to complete @rq->next_rq + * + * Description: + * Ends I/O on a number of bytes attached to @rq and @rq->next_rq. + * Drivers that supports bidi can safely call this member for any + * type of request, bidi or uni. In the later case @bidi_bytes is + * just ignored. + * + * Return: + * %false - we are done with this request + * %true - still buffers pending for this request + **/ +static bool blk_end_bidi_request(struct request *rq, int error, + unsigned int nr_bytes, unsigned int bidi_bytes) { - int error = 0; + struct request_queue *q = rq->q; + unsigned long flags; - if (uptodate <= 0) - error = uptodate ? uptodate : -EIO; + if (blk_update_bidi_request(rq, error, nr_bytes, bidi_bytes)) + return true; - __blk_end_request(rq, error, nr_bytes); + spin_lock_irqsave(q->queue_lock, flags); + blk_finish_request(rq, error); + spin_unlock_irqrestore(q->queue_lock, flags); + + return false; } /** - * blk_rq_bytes - Returns bytes left to complete in the entire request - * @rq: the request being processed + * __blk_end_bidi_request - Complete a bidi request with queue lock held + * @rq: the request to complete + * @error: %0 for success, < %0 for error + * @nr_bytes: number of bytes to complete @rq + * @bidi_bytes: number of bytes to complete @rq->next_rq + * + * Description: + * Identical to blk_end_bidi_request() except that queue lock is + * assumed to be locked on entry and remains so on return. + * + * Return: + * %false - we are done with this request + * %true - still buffers pending for this request **/ -unsigned int blk_rq_bytes(struct request *rq) +bool __blk_end_bidi_request(struct request *rq, int error, + unsigned int nr_bytes, unsigned int bidi_bytes) { - if (blk_fs_request(rq)) - return rq->hard_nr_sectors << 9; + if (blk_update_bidi_request(rq, error, nr_bytes, bidi_bytes)) + return true; - return rq->data_len; + blk_finish_request(rq, error); + + return false; } -EXPORT_SYMBOL_GPL(blk_rq_bytes); /** - * blk_rq_cur_bytes - Returns bytes left to complete in the current segment - * @rq: the request being processed + * blk_end_request - Helper function for drivers to complete the request. + * @rq: the request being processed + * @error: %0 for success, < %0 for error + * @nr_bytes: number of bytes to complete + * + * Description: + * Ends I/O on a number of bytes attached to @rq. + * If @rq has leftover, sets it up for the next range of segments. + * + * Return: + * %false - we are done with this request + * %true - still buffers pending for this request **/ -unsigned int blk_rq_cur_bytes(struct request *rq) +bool blk_end_request(struct request *rq, int error, unsigned int nr_bytes) { - if (blk_fs_request(rq)) - return rq->current_nr_sectors << 9; + return blk_end_bidi_request(rq, error, nr_bytes, 0); +} +EXPORT_SYMBOL(blk_end_request); - if (rq->bio) - return rq->bio->bi_size; +/** + * blk_end_request_all - Helper function for drives to finish the request. + * @rq: the request to finish + * @error: %0 for success, < %0 for error + * + * Description: + * Completely finish @rq. + */ +void blk_end_request_all(struct request *rq, int error) +{ + bool pending; + unsigned int bidi_bytes = 0; - return rq->data_len; + if (unlikely(blk_bidi_rq(rq))) + bidi_bytes = blk_rq_bytes(rq->next_rq); + + pending = blk_end_bidi_request(rq, error, blk_rq_bytes(rq), bidi_bytes); + BUG_ON(pending); } -EXPORT_SYMBOL_GPL(blk_rq_cur_bytes); +EXPORT_SYMBOL(blk_end_request_all); /** - * end_queued_request - end all I/O on a queued request - * @rq: the request being processed - * @uptodate: error value or 0/1 uptodate flag + * blk_end_request_cur - Helper function to finish the current request chunk. + * @rq: the request to finish the current chunk for + * @error: %0 for success, < %0 for error * * Description: - * Ends all I/O on a request, and removes it from the block layer queues. - * Not suitable for normal IO completion, unless the driver still has - * the request attached to the block layer. + * Complete the current consecutively mapped chunk from @rq. * - **/ -void end_queued_request(struct request *rq, int uptodate) + * Return: + * %false - we are done with this request + * %true - still buffers pending for this request + */ +bool blk_end_request_cur(struct request *rq, int error) +{ + return blk_end_request(rq, error, blk_rq_cur_bytes(rq)); +} +EXPORT_SYMBOL(blk_end_request_cur); + +/** + * blk_end_request_err - Finish a request till the next failure boundary. + * @rq: the request to finish till the next failure boundary for + * @error: must be negative errno + * + * Description: + * Complete @rq till the next failure boundary. + * + * Return: + * %false - we are done with this request + * %true - still buffers pending for this request + */ +bool blk_end_request_err(struct request *rq, int error) { - __end_request(rq, uptodate, blk_rq_bytes(rq)); + WARN_ON(error >= 0); + return blk_end_request(rq, error, blk_rq_err_bytes(rq)); } -EXPORT_SYMBOL(end_queued_request); +EXPORT_SYMBOL_GPL(blk_end_request_err); /** - * end_dequeued_request - end all I/O on a dequeued request - * @rq: the request being processed - * @uptodate: error value or 0/1 uptodate flag + * __blk_end_request - Helper function for drivers to complete the request. + * @rq: the request being processed + * @error: %0 for success, < %0 for error + * @nr_bytes: number of bytes to complete * * Description: - * Ends all I/O on a request. The request must already have been - * dequeued using blkdev_dequeue_request(), as is normally the case - * for most drivers. + * Must be called with queue lock held unlike blk_end_request(). * + * Return: + * %false - we are done with this request + * %true - still buffers pending for this request **/ -void end_dequeued_request(struct request *rq, int uptodate) +bool __blk_end_request(struct request *rq, int error, unsigned int nr_bytes) { - __end_request(rq, uptodate, blk_rq_bytes(rq)); + return __blk_end_bidi_request(rq, error, nr_bytes, 0); } -EXPORT_SYMBOL(end_dequeued_request); +EXPORT_SYMBOL(__blk_end_request); + +/** + * __blk_end_request_all - Helper function for drives to finish the request. + * @rq: the request to finish + * @error: %0 for success, < %0 for error + * + * Description: + * Completely finish @rq. Must be called with queue lock held. + */ +void __blk_end_request_all(struct request *rq, int error) +{ + bool pending; + unsigned int bidi_bytes = 0; + if (unlikely(blk_bidi_rq(rq))) + bidi_bytes = blk_rq_bytes(rq->next_rq); + + pending = __blk_end_bidi_request(rq, error, blk_rq_bytes(rq), bidi_bytes); + BUG_ON(pending); +} +EXPORT_SYMBOL(__blk_end_request_all); /** - * end_request - end I/O on the current segment of the request - * @req: the request being processed - * @uptodate: error value or 0/1 uptodate flag + * __blk_end_request_cur - Helper function to finish the current request chunk. + * @rq: the request to finish the current chunk for + * @error: %0 for success, < %0 for error * * Description: - * Ends I/O on the current segment of a request. If that is the only - * remaining segment, the request is also completed and freed. - * - * This is a remnant of how older block drivers handled IO completions. - * Modern drivers typically end IO on the full request in one go, unless - * they have a residual value to account for. For that case this function - * isn't really useful, unless the residual just happens to be the - * full current segment. In other words, don't use this function in new - * code. Either use end_request_completely(), or the - * end_that_request_chunk() (along with end_that_request_last()) for - * partial completions. + * Complete the current consecutively mapped chunk from @rq. Must + * be called with queue lock held. * - **/ -void end_request(struct request *req, int uptodate) + * Return: + * %false - we are done with this request + * %true - still buffers pending for this request + */ +bool __blk_end_request_cur(struct request *rq, int error) { - __end_request(req, uptodate, req->hard_cur_sectors << 9); + return __blk_end_request(rq, error, blk_rq_cur_bytes(rq)); } -EXPORT_SYMBOL(end_request); +EXPORT_SYMBOL(__blk_end_request_cur); /** - * blk_end_io - Generic end_io function to complete a request. - * @rq: the request being processed - * @error: 0 for success, < 0 for error - * @nr_bytes: number of bytes to complete @rq - * @bidi_bytes: number of bytes to complete @rq->next_rq - * @drv_callback: function called between completion of bios in the request - * and completion of the request. - * If the callback returns non 0, this helper returns without - * completion of the request. + * __blk_end_request_err - Finish a request till the next failure boundary. + * @rq: the request to finish till the next failure boundary for + * @error: must be negative errno * * Description: - * Ends I/O on a number of bytes attached to @rq and @rq->next_rq. - * If @rq has leftover, sets it up for the next range of segments. + * Complete @rq till the next failure boundary. Must be called + * with queue lock held. * * Return: - * 0 - we are done with this request - * 1 - this request is not freed yet, it still has pending buffers. - **/ -static int blk_end_io(struct request *rq, int error, unsigned int nr_bytes, - unsigned int bidi_bytes, - int (drv_callback)(struct request *)) + * %false - we are done with this request + * %true - still buffers pending for this request + */ +bool __blk_end_request_err(struct request *rq, int error) { - struct request_queue *q = rq->q; - unsigned long flags = 0UL; + WARN_ON(error >= 0); + return __blk_end_request(rq, error, blk_rq_err_bytes(rq)); +} +EXPORT_SYMBOL_GPL(__blk_end_request_err); - if (blk_fs_request(rq) || blk_pc_request(rq)) { - if (__end_that_request_first(rq, error, nr_bytes)) - return 1; +void blk_rq_bio_prep(struct request_queue *q, struct request *rq, + struct bio *bio) +{ + /* Bit 0 (R/W) is identical in rq->cmd_flags and bio->bi_rw */ + rq->cmd_flags |= bio->bi_rw & REQ_WRITE; - /* Bidi request must be completed as a whole */ - if (blk_bidi_rq(rq) && - __end_that_request_first(rq->next_rq, error, bidi_bytes)) - return 1; - } + if (bio_has_data(bio)) + rq->nr_phys_segments = bio_phys_segments(q, bio); - /* Special feature for tricky drivers */ - if (drv_callback && drv_callback(rq)) - return 1; + rq->__data_len = bio->bi_iter.bi_size; + rq->bio = rq->biotail = bio; - add_disk_randomness(rq->rq_disk); + if (bio->bi_bdev) + rq->rq_disk = bio->bi_bdev->bd_disk; +} - spin_lock_irqsave(q->queue_lock, flags); - end_that_request_last(rq, error); - spin_unlock_irqrestore(q->queue_lock, flags); +#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; - return 0; + rq_for_each_segment(bvec, rq, iter) + flush_dcache_page(bvec.bv_page); } +EXPORT_SYMBOL_GPL(rq_flush_dcache_pages); +#endif /** - * blk_end_request - Helper function for drivers to complete the request. - * @rq: the request being processed - * @error: 0 for success, < 0 for error - * @nr_bytes: number of bytes to complete + * blk_lld_busy - Check if underlying low-level drivers of a device are busy + * @q : the queue of the device being checked * * Description: - * Ends I/O on a number of bytes attached to @rq. - * If @rq has leftover, sets it up for the next range of segments. + * 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 - we are done with this request - * 1 - still buffers pending for this request - **/ -int blk_end_request(struct request *rq, int error, unsigned int nr_bytes) + * 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) { - return blk_end_io(rq, error, nr_bytes, 0, NULL); + if (q->lld_busy_fn) + return q->lld_busy_fn(q); + + return 0; } -EXPORT_SYMBOL_GPL(blk_end_request); +EXPORT_SYMBOL_GPL(blk_lld_busy); /** - * __blk_end_request - Helper function for drivers to complete the request. - * @rq: the request being processed - * @error: 0 for success, < 0 for error - * @nr_bytes: number of bytes to complete + * blk_rq_unprep_clone - Helper function to free all bios in a cloned request + * @rq: the clone request to be cleaned up * * Description: - * Must be called with queue lock held unlike blk_end_request(). - * - * Return: - * 0 - we are done with this request - * 1 - still buffers pending for this request - **/ -int __blk_end_request(struct request *rq, int error, unsigned int nr_bytes) + * Free all bios in @rq for a cloned request. + */ +void blk_rq_unprep_clone(struct request *rq) { - if (blk_fs_request(rq) || blk_pc_request(rq)) { - if (__end_that_request_first(rq, error, nr_bytes)) - return 1; + struct bio *bio; + + while ((bio = rq->bio) != NULL) { + rq->bio = bio->bi_next; + + bio_put(bio); } +} +EXPORT_SYMBOL_GPL(blk_rq_unprep_clone); - add_disk_randomness(rq->rq_disk); +/* + * 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->cpu = src->cpu; + dst->cmd_flags = (src->cmd_flags & REQ_CLONE_MASK) | REQ_NOMERGE; + dst->cmd_type = src->cmd_type; + dst->__sector = blk_rq_pos(src); + dst->__data_len = blk_rq_bytes(src); + dst->nr_phys_segments = src->nr_phys_segments; + dst->ioprio = src->ioprio; + dst->extra_len = src->extra_len; +} - end_that_request_last(rq, error); +/** + * 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; + + blk_rq_init(NULL, rq); + + __rq_for_each_bio(bio_src, rq_src) { + bio = bio_clone_bioset(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_delayed_work(struct delayed_work *dwork, + unsigned long delay) +{ + return queue_delayed_work(kblockd_workqueue, dwork, delay); } -EXPORT_SYMBOL_GPL(__blk_end_request); +EXPORT_SYMBOL(kblockd_schedule_delayed_work); + +int kblockd_schedule_delayed_work_on(int cpu, struct delayed_work *dwork, + unsigned long delay) +{ + return queue_delayed_work_on(cpu, kblockd_workqueue, dwork, delay); +} +EXPORT_SYMBOL(kblockd_schedule_delayed_work_on); /** - * blk_end_bidi_request - Helper function for drivers to complete bidi request. - * @rq: the bidi request being processed - * @error: 0 for success, < 0 for error - * @nr_bytes: number of bytes to complete @rq - * @bidi_bytes: number of bytes to complete @rq->next_rq + * blk_start_plug - initialize blk_plug and track it inside the task_struct + * @plug: The &struct blk_plug that needs to be initialized * * Description: - * Ends I/O on a number of bytes attached to @rq and @rq->next_rq. - * - * Return: - * 0 - we are done with this request - * 1 - still buffers pending for this request - **/ -int blk_end_bidi_request(struct request *rq, int error, unsigned int nr_bytes, - unsigned int bidi_bytes) + * 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) +{ + struct task_struct *tsk = current; + + INIT_LIST_HEAD(&plug->list); + INIT_LIST_HEAD(&plug->mq_list); + INIT_LIST_HEAD(&plug->cb_list); + + /* + * If this is a nested plug, don't actually assign it. It will be + * flushed on its own. + */ + if (!tsk->plug) { + /* + * Store ordering should not be needed here, since a potential + * preempt will imply a full memory barrier + */ + tsk->plug = plug; + } +} +EXPORT_SYMBOL(blk_start_plug); + +static int plug_rq_cmp(void *priv, struct list_head *a, struct list_head *b) +{ + struct request *rqa = container_of(a, struct request, queuelist); + struct request *rqb = container_of(b, struct request, queuelist); + + return !(rqa->q < rqb->q || + (rqa->q == rqb->q && blk_rq_pos(rqa) < blk_rq_pos(rqb))); +} + +/* + * If 'from_schedule' is true, then postpone the dispatch of requests + * until a safe kblockd context. We due this to avoid accidental big + * additional stack usage in driver dispatch, in places where the originally + * plugger did not intend it. + */ +static void queue_unplugged(struct request_queue *q, unsigned int depth, + bool from_schedule) + __releases(q->queue_lock) +{ + trace_block_unplug(q, depth, !from_schedule); + + if (from_schedule) + blk_run_queue_async(q); + else + __blk_run_queue(q); + spin_unlock(q->queue_lock); +} + +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) { - return blk_end_io(rq, error, nr_bytes, bidi_bytes, NULL); + 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_GPL(blk_end_bidi_request); +EXPORT_SYMBOL(blk_check_plugged); + +void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule) +{ + struct request_queue *q; + unsigned long flags; + struct request *rq; + LIST_HEAD(list); + unsigned int depth; + + flush_plug_callbacks(plug, from_schedule); + + if (!list_empty(&plug->mq_list)) + blk_mq_flush_plug_list(plug, from_schedule); + + if (list_empty(&plug->list)) + return; + + list_splice_init(&plug->list, &list); + + list_sort(NULL, &list, plug_rq_cmp); + + q = NULL; + depth = 0; + + /* + * Save and disable interrupts here, to avoid doing it for every + * queue lock we have to take. + */ + local_irq_save(flags); + while (!list_empty(&list)) { + rq = list_entry_rq(list.next); + list_del_init(&rq->queuelist); + BUG_ON(!rq->q); + if (rq->q != q) { + /* + * This drops the queue lock + */ + if (q) + queue_unplugged(q, depth, from_schedule); + q = rq->q; + depth = 0; + spin_lock(q->queue_lock); + } + + /* + * Short-circuit if @q is dead + */ + if (unlikely(blk_queue_dying(q))) { + __blk_end_request_all(rq, -ENODEV); + continue; + } + + /* + * rq is already accounted, so use raw insert + */ + if (rq->cmd_flags & (REQ_FLUSH | REQ_FUA)) + __elv_add_request(q, rq, ELEVATOR_INSERT_FLUSH); + else + __elv_add_request(q, rq, ELEVATOR_INSERT_SORT_MERGE); + depth++; + } + + /* + * This drops the queue lock + */ + if (q) + queue_unplugged(q, depth, from_schedule); + + local_irq_restore(flags); +} + +void blk_finish_plug(struct blk_plug *plug) +{ + blk_flush_plug_list(plug, false); + + if (plug == current->plug) + current->plug = NULL; +} +EXPORT_SYMBOL(blk_finish_plug); + +#ifdef CONFIG_PM_RUNTIME /** - * blk_end_request_callback - Special helper function for tricky drivers - * @rq: the request being processed - * @error: 0 for success, < 0 for error - * @nr_bytes: number of bytes to complete - * @drv_callback: function called between completion of bios in the request - * and completion of the request. - * If the callback returns non 0, this helper returns without - * completion of the request. + * blk_pm_runtime_init - Block layer runtime PM initialization routine + * @q: the queue of the device + * @dev: the device the queue belongs to * * Description: - * Ends I/O on a number of bytes attached to @rq. - * If @rq has leftover, sets it up for the next range of segments. + * Initialize runtime-PM-related fields for @q and start auto suspend for + * @dev. Drivers that want to take advantage of request-based runtime PM + * should call this function after @dev has been initialized, and its + * request queue @q has been allocated, and runtime PM for it can not happen + * yet(either due to disabled/forbidden or its usage_count > 0). In most + * cases, driver should call this function before any I/O has taken place. * - * This special helper function is used only for existing tricky drivers. - * (e.g. cdrom_newpc_intr() of ide-cd) - * This interface will be removed when such drivers are rewritten. - * Don't use this interface in other places anymore. + * This function takes care of setting up using auto suspend for the device, + * the autosuspend delay is set to -1 to make runtime suspend impossible + * until an updated value is either set by user or by driver. Drivers do + * not need to touch other autosuspend settings. * - * Return: - * 0 - we are done with this request - * 1 - this request is not freed yet. - * this request still has pending buffers or - * the driver doesn't want to finish this request yet. - **/ -int blk_end_request_callback(struct request *rq, int error, - unsigned int nr_bytes, - int (drv_callback)(struct request *)) + * The block layer runtime PM is request based, so only works for drivers + * that use request as their IO unit instead of those directly use bio's. + */ +void blk_pm_runtime_init(struct request_queue *q, struct device *dev) { - return blk_end_io(rq, error, nr_bytes, 0, drv_callback); + q->dev = dev; + q->rpm_status = RPM_ACTIVE; + pm_runtime_set_autosuspend_delay(q->dev, -1); + pm_runtime_use_autosuspend(q->dev); } -EXPORT_SYMBOL_GPL(blk_end_request_callback); +EXPORT_SYMBOL(blk_pm_runtime_init); -void blk_rq_bio_prep(struct request_queue *q, struct request *rq, - struct bio *bio) +/** + * blk_pre_runtime_suspend - Pre runtime suspend check + * @q: the queue of the device + * + * Description: + * This function will check if runtime suspend is allowed for the device + * by examining if there are any requests pending in the queue. If there + * are requests pending, the device can not be runtime suspended; otherwise, + * the queue's status will be updated to SUSPENDING and the driver can + * proceed to suspend the device. + * + * For the not allowed case, we mark last busy for the device so that + * runtime PM core will try to autosuspend it some time later. + * + * This function should be called near the start of the device's + * runtime_suspend callback. + * + * Return: + * 0 - OK to runtime suspend the device + * -EBUSY - Device should not be runtime suspended + */ +int blk_pre_runtime_suspend(struct request_queue *q) { - /* first two bits are identical in rq->cmd_flags and bio->bi_rw */ - rq->cmd_flags |= (bio->bi_rw & 3); - - rq->nr_phys_segments = bio_phys_segments(q, bio); - rq->nr_hw_segments = bio_hw_segments(q, bio); - rq->current_nr_sectors = bio_cur_sectors(bio); - rq->hard_cur_sectors = rq->current_nr_sectors; - rq->hard_nr_sectors = rq->nr_sectors = bio_sectors(bio); - rq->buffer = bio_data(bio); - rq->data_len = bio->bi_size; + int ret = 0; - rq->bio = rq->biotail = bio; + spin_lock_irq(q->queue_lock); + if (q->nr_pending) { + ret = -EBUSY; + pm_runtime_mark_last_busy(q->dev); + } else { + q->rpm_status = RPM_SUSPENDING; + } + spin_unlock_irq(q->queue_lock); + return ret; +} +EXPORT_SYMBOL(blk_pre_runtime_suspend); - if (bio->bi_bdev) - rq->rq_disk = bio->bi_bdev->bd_disk; +/** + * blk_post_runtime_suspend - Post runtime suspend processing + * @q: the queue of the device + * @err: return value of the device's runtime_suspend function + * + * Description: + * Update the queue's runtime status according to the return value of the + * device's runtime suspend function and mark last busy for the device so + * that PM core will try to auto suspend the device at a later time. + * + * This function should be called near the end of the device's + * runtime_suspend callback. + */ +void blk_post_runtime_suspend(struct request_queue *q, int err) +{ + spin_lock_irq(q->queue_lock); + if (!err) { + q->rpm_status = RPM_SUSPENDED; + } else { + q->rpm_status = RPM_ACTIVE; + pm_runtime_mark_last_busy(q->dev); + } + spin_unlock_irq(q->queue_lock); } +EXPORT_SYMBOL(blk_post_runtime_suspend); -int kblockd_schedule_work(struct work_struct *work) +/** + * blk_pre_runtime_resume - Pre runtime resume processing + * @q: the queue of the device + * + * Description: + * Update the queue's runtime status to RESUMING in preparation for the + * runtime resume of the device. + * + * This function should be called near the start of the device's + * runtime_resume callback. + */ +void blk_pre_runtime_resume(struct request_queue *q) { - return queue_work(kblockd_workqueue, work); + spin_lock_irq(q->queue_lock); + q->rpm_status = RPM_RESUMING; + spin_unlock_irq(q->queue_lock); } -EXPORT_SYMBOL(kblockd_schedule_work); +EXPORT_SYMBOL(blk_pre_runtime_resume); -void kblockd_flush_work(struct work_struct *work) +/** + * blk_post_runtime_resume - Post runtime resume processing + * @q: the queue of the device + * @err: return value of the device's runtime_resume function + * + * Description: + * Update the queue's runtime status according to the return value of the + * device's runtime_resume function. If it is successfully resumed, process + * the requests that are queued into the device's queue when it is resuming + * and then mark last busy and initiate autosuspend for it. + * + * This function should be called near the end of the device's + * runtime_resume callback. + */ +void blk_post_runtime_resume(struct request_queue *q, int err) { - cancel_work_sync(work); + spin_lock_irq(q->queue_lock); + if (!err) { + q->rpm_status = RPM_ACTIVE; + __blk_run_queue(q); + pm_runtime_mark_last_busy(q->dev); + pm_request_autosuspend(q->dev); + } else { + q->rpm_status = RPM_SUSPENDED; + } + spin_unlock_irq(q->queue_lock); } -EXPORT_SYMBOL(kblockd_flush_work); +EXPORT_SYMBOL(blk_post_runtime_resume); +#endif int __init blk_dev_init(void) { - int i; + BUILD_BUG_ON(__REQ_NR_BITS > 8 * + sizeof(((struct request *)0)->cmd_flags)); - kblockd_workqueue = create_workqueue("kblockd"); + /* 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"); @@ -2039,12 +3322,5 @@ int __init blk_dev_init(void) blk_requestq_cachep = kmem_cache_create("blkdev_queue", sizeof(struct request_queue), 0, SLAB_PANIC, NULL); - for_each_possible_cpu(i) - INIT_LIST_HEAD(&per_cpu(blk_cpu_done, i)); - - open_softirq(BLOCK_SOFTIRQ, blk_done_softirq); - register_hotcpu_notifier(&blk_cpu_notifier); - return 0; } - |