summaryrefslogtreecommitdiff
path: root/block/blk-core.c
diff options
context:
space:
mode:
Diffstat (limited to 'block/blk-core.c')
-rw-r--r--block/blk-core.c2066
1 files changed, 55 insertions, 2011 deletions
diff --git a/block/blk-core.c b/block/blk-core.c
index deb56932f8c4..c78042975737 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -58,11 +58,6 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(block_unplug);
DEFINE_IDA(blk_queue_ida);
/*
- * For the allocated request tables
- */
-struct kmem_cache *request_cachep;
-
-/*
* For queue allocation
*/
struct kmem_cache *blk_requestq_cachep;
@@ -79,11 +74,7 @@ static struct workqueue_struct *kblockd_workqueue;
*/
void blk_queue_flag_set(unsigned int flag, struct request_queue *q)
{
- unsigned long flags;
-
- spin_lock_irqsave(q->queue_lock, flags);
- queue_flag_set(flag, q);
- spin_unlock_irqrestore(q->queue_lock, flags);
+ set_bit(flag, &q->queue_flags);
}
EXPORT_SYMBOL(blk_queue_flag_set);
@@ -94,11 +85,7 @@ EXPORT_SYMBOL(blk_queue_flag_set);
*/
void blk_queue_flag_clear(unsigned int flag, struct request_queue *q)
{
- unsigned long flags;
-
- spin_lock_irqsave(q->queue_lock, flags);
- queue_flag_clear(flag, q);
- spin_unlock_irqrestore(q->queue_lock, flags);
+ clear_bit(flag, &q->queue_flags);
}
EXPORT_SYMBOL(blk_queue_flag_clear);
@@ -112,85 +99,15 @@ EXPORT_SYMBOL(blk_queue_flag_clear);
*/
bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q)
{
- unsigned long flags;
- bool res;
-
- spin_lock_irqsave(q->queue_lock, flags);
- res = queue_flag_test_and_set(flag, q);
- spin_unlock_irqrestore(q->queue_lock, flags);
-
- return res;
+ return test_and_set_bit(flag, &q->queue_flags);
}
EXPORT_SYMBOL_GPL(blk_queue_flag_test_and_set);
-/**
- * blk_queue_flag_test_and_clear - atomically test and clear a queue flag
- * @flag: flag to be cleared
- * @q: request queue
- *
- * Returns the previous value of @flag - 0 if the flag was not set and 1 if
- * the flag was set.
- */
-bool blk_queue_flag_test_and_clear(unsigned int flag, struct request_queue *q)
-{
- unsigned long flags;
- bool res;
-
- spin_lock_irqsave(q->queue_lock, flags);
- res = queue_flag_test_and_clear(flag, q);
- spin_unlock_irqrestore(q->queue_lock, flags);
-
- return res;
-}
-EXPORT_SYMBOL_GPL(blk_queue_flag_test_and_clear);
-
-static void blk_clear_congested(struct request_list *rl, int sync)
-{
-#ifdef CONFIG_CGROUP_WRITEBACK
- clear_wb_congested(rl->blkg->wb_congested, sync);
-#else
- /*
- * If !CGROUP_WRITEBACK, all blkg's map to bdi->wb and we shouldn't
- * flip its congestion state for events on other blkcgs.
- */
- if (rl == &rl->q->root_rl)
- clear_wb_congested(rl->q->backing_dev_info->wb.congested, sync);
-#endif
-}
-
-static void blk_set_congested(struct request_list *rl, int sync)
-{
-#ifdef CONFIG_CGROUP_WRITEBACK
- set_wb_congested(rl->blkg->wb_congested, sync);
-#else
- /* see blk_clear_congested() */
- if (rl == &rl->q->root_rl)
- set_wb_congested(rl->q->backing_dev_info->wb.congested, sync);
-#endif
-}
-
-void blk_queue_congestion_threshold(struct request_queue *q)
-{
- int nr;
-
- nr = q->nr_requests - (q->nr_requests / 8) + 1;
- if (nr > q->nr_requests)
- nr = q->nr_requests;
- q->nr_congestion_on = nr;
-
- nr = q->nr_requests - (q->nr_requests / 8) - (q->nr_requests / 16) - 1;
- if (nr < 1)
- nr = 1;
- q->nr_congestion_off = nr;
-}
-
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->timeout_list);
- rq->cpu = -1;
rq->q = q;
rq->__sector = (sector_t) -1;
INIT_HLIST_NODE(&rq->hash);
@@ -256,10 +173,11 @@ static void print_req_error(struct request *req, blk_status_t status)
if (WARN_ON_ONCE(idx >= ARRAY_SIZE(blk_errors)))
return;
- printk_ratelimited(KERN_ERR "%s: %s error, dev %s, sector %llu\n",
- __func__, blk_errors[idx].name, req->rq_disk ?
- req->rq_disk->disk_name : "?",
- (unsigned long long)blk_rq_pos(req));
+ printk_ratelimited(KERN_ERR "%s: %s error, dev %s, sector %llu flags %x\n",
+ __func__, blk_errors[idx].name,
+ req->rq_disk ? req->rq_disk->disk_name : "?",
+ (unsigned long long)blk_rq_pos(req),
+ req->cmd_flags);
}
static void req_bio_endio(struct request *rq, struct bio *bio,
@@ -292,99 +210,6 @@ void blk_dump_rq_flags(struct request *rq, char *msg)
}
EXPORT_SYMBOL(blk_dump_rq_flags);
-static void blk_delay_work(struct work_struct *work)
-{
- struct request_queue *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);
-}
-
-/**
- * blk_delay_queue - restart queueing after defined interval
- * @q: The &struct request_queue in question
- * @msecs: Delay in msecs
- *
- * Description:
- * 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.
- */
-void blk_delay_queue(struct request_queue *q, unsigned long msecs)
-{
- lockdep_assert_held(q->queue_lock);
- WARN_ON_ONCE(q->mq_ops);
-
- if (likely(!blk_queue_dead(q)))
- queue_delayed_work(kblockd_workqueue, &q->delay_work,
- msecs_to_jiffies(msecs));
-}
-EXPORT_SYMBOL(blk_delay_queue);
-
-/**
- * blk_start_queue_async - asynchronously restart a previously stopped queue
- * @q: The &struct request_queue in question
- *
- * Description:
- * blk_start_queue_async() will clear the stop flag on the queue, and
- * ensure that the request_fn for the queue is run from an async
- * context.
- **/
-void blk_start_queue_async(struct request_queue *q)
-{
- lockdep_assert_held(q->queue_lock);
- WARN_ON_ONCE(q->mq_ops);
-
- queue_flag_clear(QUEUE_FLAG_STOPPED, q);
- blk_run_queue_async(q);
-}
-EXPORT_SYMBOL(blk_start_queue_async);
-
-/**
- * blk_start_queue - restart a previously stopped queue
- * @q: The &struct request_queue in question
- *
- * Description:
- * blk_start_queue() will clear the stop flag on the queue, and call
- * the request_fn for the queue if it was in a stopped state when
- * entered. Also see blk_stop_queue().
- **/
-void blk_start_queue(struct request_queue *q)
-{
- lockdep_assert_held(q->queue_lock);
- WARN_ON_ONCE(q->mq_ops);
-
- queue_flag_clear(QUEUE_FLAG_STOPPED, q);
- __blk_run_queue(q);
-}
-EXPORT_SYMBOL(blk_start_queue);
-
-/**
- * blk_stop_queue - stop a queue
- * @q: The &struct request_queue in question
- *
- * Description:
- * The Linux block layer assumes that a block driver will consume all
- * entries on the request queue when the request_fn strategy is called.
- * Often this will not happen, because of hardware limitations (queue
- * depth settings). If a device driver gets a 'queue full' response,
- * or if it simply chooses not to queue more I/O at one point, it can
- * call this function to prevent the request_fn from being called until
- * the driver has signalled it's ready to go again. This happens by calling
- * blk_start_queue() to restart queue operations.
- **/
-void blk_stop_queue(struct request_queue *q)
-{
- lockdep_assert_held(q->queue_lock);
- WARN_ON_ONCE(q->mq_ops);
-
- cancel_delayed_work(&q->delay_work);
- queue_flag_set(QUEUE_FLAG_STOPPED, q);
-}
-EXPORT_SYMBOL(blk_stop_queue);
-
/**
* blk_sync_queue - cancel any pending callbacks on a queue
* @q: the queue
@@ -408,15 +233,13 @@ void blk_sync_queue(struct request_queue *q)
del_timer_sync(&q->timeout);
cancel_work_sync(&q->timeout_work);
- if (q->mq_ops) {
+ if (queue_is_mq(q)) {
struct blk_mq_hw_ctx *hctx;
int i;
cancel_delayed_work_sync(&q->requeue_work);
queue_for_each_hw_ctx(q, hctx, i)
cancel_delayed_work_sync(&hctx->run_work);
- } else {
- cancel_delayed_work_sync(&q->delay_work);
}
}
EXPORT_SYMBOL(blk_sync_queue);
@@ -442,250 +265,12 @@ void blk_clear_pm_only(struct request_queue *q)
}
EXPORT_SYMBOL_GPL(blk_clear_pm_only);
-/**
- * __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.
- */
-inline void __blk_run_queue_uncond(struct request_queue *q)
-{
- lockdep_assert_held(q->queue_lock);
- WARN_ON_ONCE(q->mq_ops);
-
- if (unlikely(blk_queue_dead(q)))
- return;
-
- /*
- * 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.
- */
- q->request_fn_active++;
- q->request_fn(q);
- q->request_fn_active--;
-}
-EXPORT_SYMBOL_GPL(__blk_run_queue_uncond);
-
-/**
- * __blk_run_queue - run a single device queue
- * @q: The queue to run
- *
- * Description:
- * See @blk_run_queue.
- */
-void __blk_run_queue(struct request_queue *q)
-{
- lockdep_assert_held(q->queue_lock);
- WARN_ON_ONCE(q->mq_ops);
-
- 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.
- *
- * Note:
- * Since it is not allowed to run q->delay_work after blk_cleanup_queue()
- * has canceled q->delay_work, callers must hold the queue lock to avoid
- * race conditions between blk_cleanup_queue() and blk_run_queue_async().
- */
-void blk_run_queue_async(struct request_queue *q)
-{
- lockdep_assert_held(q->queue_lock);
- WARN_ON_ONCE(q->mq_ops);
-
- 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)
-{
- unsigned long flags;
-
- WARN_ON_ONCE(q->mq_ops);
-
- spin_lock_irqsave(q->queue_lock, flags);
- __blk_run_queue(q);
- spin_unlock_irqrestore(q->queue_lock, flags);
-}
-EXPORT_SYMBOL(blk_run_queue);
-
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);
- WARN_ON_ONCE(q->mq_ops);
-
- 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) {
- struct blk_flush_queue *fq = blk_get_flush_queue(q, NULL);
- drain |= !list_empty(&q->queue_head);
- for (i = 0; i < 2; i++) {
- drain |= q->nr_rqs[i];
- drain |= q->in_flight[i];
- if (fq)
- drain |= !list_empty(&fq->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]);
- }
-}
-
-void blk_drain_queue(struct request_queue *q)
-{
- spin_lock_irq(q->queue_lock);
- __blk_drain_queue(q, true);
- spin_unlock_irq(q->queue_lock);
-}
-
-/**
- * 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)
-{
- WARN_ON_ONCE(q->mq_ops);
-
- spin_lock_irq(q->queue_lock);
- q->bypass_depth++;
- queue_flag_set(QUEUE_FLAG_BYPASS, q);
- spin_unlock_irq(q->queue_lock);
-
- /*
- * Queues start drained. Skip actual draining till init is
- * complete. This avoids lenghty delays during queue init which
- * can happen many times during boot.
- */
- if (blk_queue_init_done(q)) {
- 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.
- *
- * Note: although blk_queue_bypass_start() is only called for blk-sq queues,
- * this function is called for both blk-sq and blk-mq queues.
- */
-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);
-
void blk_set_queue_dying(struct request_queue *q)
{
blk_queue_flag_set(QUEUE_FLAG_DYING, q);
@@ -697,20 +282,8 @@ void blk_set_queue_dying(struct request_queue *q)
*/
blk_freeze_queue_start(q);
- if (q->mq_ops)
+ if (queue_is_mq(q))
blk_mq_wake_waiters(q);
- else {
- struct request_list *rl;
-
- spin_lock_irq(q->queue_lock);
- blk_queue_for_each_rl(rl, q) {
- if (rl->rq_pool) {
- wake_up_all(&rl->wait[BLK_RW_SYNC]);
- wake_up_all(&rl->wait[BLK_RW_ASYNC]);
- }
- }
- spin_unlock_irq(q->queue_lock);
- }
/* Make blk_queue_enter() reexamine the DYING flag. */
wake_up_all(&q->mq_freeze_wq);
@@ -755,29 +328,13 @@ void blk_exit_queue(struct request_queue *q)
*/
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);
blk_set_queue_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);
+ blk_queue_flag_set(QUEUE_FLAG_NOMERGES, q);
+ blk_queue_flag_set(QUEUE_FLAG_NOXMERGES, q);
+ blk_queue_flag_set(QUEUE_FLAG_DYING, q);
mutex_unlock(&q->sysfs_lock);
/*
@@ -788,9 +345,7 @@ void blk_cleanup_queue(struct request_queue *q)
rq_qos_exit(q);
- spin_lock_irq(lock);
- queue_flag_set(QUEUE_FLAG_DEAD, q);
- spin_unlock_irq(lock);
+ blk_queue_flag_set(QUEUE_FLAG_DEAD, q);
/*
* make sure all in-progress dispatch are completed because
@@ -801,7 +356,7 @@ void blk_cleanup_queue(struct request_queue *q)
* We rely on driver to deal with the race in case that queue
* initialization isn't done.
*/
- if (q->mq_ops && blk_queue_init_done(q))
+ if (queue_is_mq(q) && blk_queue_init_done(q))
blk_mq_quiesce_queue(q);
/* for synchronous bio-based driver finish in-flight integrity i/o */
@@ -819,98 +374,19 @@ void blk_cleanup_queue(struct request_queue *q)
blk_exit_queue(q);
- if (q->mq_ops)
+ if (queue_is_mq(q))
blk_mq_free_queue(q);
- percpu_ref_exit(&q->q_usage_counter);
- spin_lock_irq(lock);
- if (q->queue_lock != &q->__queue_lock)
- q->queue_lock = &q->__queue_lock;
- spin_unlock_irq(lock);
+ percpu_ref_exit(&q->q_usage_counter);
/* @q is and will stay empty, shutdown and put */
blk_put_queue(q);
}
EXPORT_SYMBOL(blk_cleanup_queue);
-/* Allocate memory local to the request queue */
-static void *alloc_request_simple(gfp_t gfp_mask, void *data)
-{
- struct request_queue *q = data;
-
- return kmem_cache_alloc_node(request_cachep, gfp_mask, q->node);
-}
-
-static void free_request_simple(void *element, void *data)
-{
- kmem_cache_free(request_cachep, element);
-}
-
-static void *alloc_request_size(gfp_t gfp_mask, void *data)
-{
- struct request_queue *q = data;
- struct request *rq;
-
- rq = kmalloc_node(sizeof(struct request) + q->cmd_size, gfp_mask,
- q->node);
- if (rq && q->init_rq_fn && q->init_rq_fn(q, rq, gfp_mask) < 0) {
- kfree(rq);
- rq = NULL;
- }
- return rq;
-}
-
-static void free_request_size(void *element, void *data)
-{
- struct request_queue *q = data;
-
- if (q->exit_rq_fn)
- q->exit_rq_fn(q, element);
- kfree(element);
-}
-
-int blk_init_rl(struct request_list *rl, struct request_queue *q,
- gfp_t gfp_mask)
-{
- if (unlikely(rl->rq_pool) || q->mq_ops)
- return 0;
-
- 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]);
-
- if (q->cmd_size) {
- rl->rq_pool = mempool_create_node(BLKDEV_MIN_RQ,
- alloc_request_size, free_request_size,
- q, gfp_mask, q->node);
- } else {
- rl->rq_pool = mempool_create_node(BLKDEV_MIN_RQ,
- alloc_request_simple, free_request_simple,
- q, gfp_mask, q->node);
- }
- if (!rl->rq_pool)
- return -ENOMEM;
-
- if (rl != &q->root_rl)
- WARN_ON_ONCE(!blk_get_queue(q));
-
- return 0;
-}
-
-void blk_exit_rl(struct request_queue *q, struct request_list *rl)
-{
- if (rl->rq_pool) {
- mempool_destroy(rl->rq_pool);
- if (rl != &q->root_rl)
- blk_put_queue(q);
- }
-}
-
struct request_queue *blk_alloc_queue(gfp_t gfp_mask)
{
- return blk_alloc_queue_node(gfp_mask, NUMA_NO_NODE, NULL);
+ return blk_alloc_queue_node(gfp_mask, NUMA_NO_NODE);
}
EXPORT_SYMBOL(blk_alloc_queue);
@@ -990,17 +466,8 @@ static void blk_rq_timed_out_timer(struct timer_list *t)
* blk_alloc_queue_node - allocate a request queue
* @gfp_mask: memory allocation flags
* @node_id: NUMA node to allocate memory from
- * @lock: For legacy queues, pointer to a spinlock that will be used to e.g.
- * serialize calls to the legacy .request_fn() callback. Ignored for
- * blk-mq request queues.
- *
- * Note: pass the queue lock as the third argument to this function instead of
- * setting the queue lock pointer explicitly to avoid triggering a sporadic
- * crash in the blkcg code. This function namely calls blkcg_init_queue() and
- * the queue lock pointer must be set before blkcg_init_queue() is called.
*/
-struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id,
- spinlock_t *lock)
+struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
{
struct request_queue *q;
int ret;
@@ -1012,8 +479,6 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id,
INIT_LIST_HEAD(&q->queue_head);
q->last_merge = NULL;
- q->end_sector = 0;
- q->boundary_rq = NULL;
q->id = ida_simple_get(&blk_queue_ida, 0, 0, gfp_mask);
if (q->id < 0)
@@ -1041,12 +506,10 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id,
laptop_mode_timer_fn, 0);
timer_setup(&q->timeout, blk_rq_timed_out_timer, 0);
INIT_WORK(&q->timeout_work, NULL);
- INIT_LIST_HEAD(&q->timeout_list);
INIT_LIST_HEAD(&q->icq_list);
#ifdef CONFIG_BLK_CGROUP
INIT_LIST_HEAD(&q->blkg_list);
#endif
- INIT_DELAYED_WORK(&q->delay_work, blk_delay_work);
kobject_init(&q->kobj, &blk_queue_ktype);
@@ -1054,18 +517,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id,
mutex_init(&q->blk_trace_mutex);
#endif
mutex_init(&q->sysfs_lock);
- spin_lock_init(&q->__queue_lock);
-
- q->queue_lock = 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;
- queue_flag_set_unlocked(QUEUE_FLAG_BYPASS, q);
+ spin_lock_init(&q->queue_lock);
init_waitqueue_head(&q->mq_freeze_wq);
@@ -1099,105 +551,6 @@ fail_q:
}
EXPORT_SYMBOL(blk_alloc_queue_node);
-/**
- * blk_init_queue - prepare a request queue for use with a block device
- * @rfn: The function to be called to process requests that have been
- * placed on the queue.
- * @lock: Request queue spin lock
- *
- * Description:
- * If a block device wishes to use the standard request handling procedures,
- * which sorts requests and coalesces adjacent requests, then it must
- * call blk_init_queue(). The function @rfn will be called when there
- * are requests on the queue that need to be processed. If the device
- * supports plugging, then @rfn may not be called immediately when requests
- * are available on the queue, but may be called at some time later instead.
- * Plugged queues are generally unplugged when a buffer belonging to one
- * of the requests on the queue is needed, or due to memory pressure.
- *
- * @rfn is not required, or even expected, to remove all requests off the
- * queue, but only as many as it can handle at a time. If it does leave
- * requests on the queue, it is responsible for arranging that the requests
- * get dealt with eventually.
- *
- * The queue spin lock must be held while manipulating the requests on the
- * 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
- * it didn't succeed.
- *
- * Note:
- * blk_init_queue() must be paired with a blk_cleanup_queue() call
- * when the block device is deactivated (such as at module unload).
- **/
-
-struct request_queue *blk_init_queue(request_fn_proc *rfn, spinlock_t *lock)
-{
- 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;
-
- q = blk_alloc_queue_node(GFP_KERNEL, node_id, lock);
- if (!q)
- return NULL;
-
- q->request_fn = rfn;
- if (blk_init_allocated_queue(q) < 0) {
- blk_cleanup_queue(q);
- return NULL;
- }
-
- return q;
-}
-EXPORT_SYMBOL(blk_init_queue_node);
-
-static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio);
-
-
-int blk_init_allocated_queue(struct request_queue *q)
-{
- WARN_ON_ONCE(q->mq_ops);
-
- q->fq = blk_alloc_flush_queue(q, NUMA_NO_NODE, q->cmd_size, GFP_KERNEL);
- if (!q->fq)
- return -ENOMEM;
-
- if (q->init_rq_fn && q->init_rq_fn(q, q->fq->flush_rq, GFP_KERNEL))
- goto out_free_flush_queue;
-
- if (blk_init_rl(&q->root_rl, q, GFP_KERNEL))
- goto out_exit_flush_rq;
-
- INIT_WORK(&q->timeout_work, blk_timeout_work);
- q->queue_flags |= QUEUE_FLAG_DEFAULT;
-
- /*
- * This also sets hw/phys segments, boundary and size
- */
- blk_queue_make_request(q, blk_queue_bio);
-
- q->sg_reserved_size = INT_MAX;
-
- if (elevator_init(q))
- goto out_exit_flush_rq;
- return 0;
-
-out_exit_flush_rq:
- if (q->exit_rq_fn)
- q->exit_rq_fn(q, q->fq->flush_rq);
-out_free_flush_queue:
- blk_free_flush_queue(q->fq);
- q->fq = NULL;
- return -ENOMEM;
-}
-EXPORT_SYMBOL(blk_init_allocated_queue);
-
bool blk_get_queue(struct request_queue *q)
{
if (likely(!blk_queue_dying(q))) {
@@ -1209,406 +562,6 @@ bool blk_get_queue(struct request_queue *q)
}
EXPORT_SYMBOL(blk_get_queue);
-static inline void blk_free_request(struct request_list *rl, struct request *rq)
-{
- if (rq->rq_flags & RQF_ELVPRIV) {
- elv_put_request(rl->q, rq);
- if (rq->elv.icq)
- put_io_context(rq->elv.icq->ioc);
- }
-
- mempool_free(rq, rl->rq_pool);
-}
-
-/*
- * ioc_batching returns true if the ioc is a valid batching request and
- * should be given priority access to a request.
- */
-static inline int ioc_batching(struct request_queue *q, struct io_context *ioc)
-{
- if (!ioc)
- return 0;
-
- /*
- * Make sure the process is able to allocate at least 1 request
- * even if the batch times out, otherwise we could theoretically
- * lose wakeups.
- */
- return ioc->nr_batch_requests == q->nr_batching ||
- (ioc->nr_batch_requests > 0
- && time_before(jiffies, ioc->last_waited + BLK_BATCH_TIME));
-}
-
-/*
- * ioc_set_batching sets ioc to be a new "batcher" if it is not one. This
- * will cause the process to be a "batcher" on all queues in the system. This
- * is the behaviour we want though - once it gets a wakeup it should be given
- * a nice run.
- */
-static void ioc_set_batching(struct request_queue *q, struct io_context *ioc)
-{
- if (!ioc || ioc_batching(q, ioc))
- return;
-
- ioc->nr_batch_requests = q->nr_batching;
- ioc->last_waited = jiffies;
-}
-
-static void __freed_request(struct request_list *rl, int sync)
-{
- struct request_queue *q = rl->q;
-
- if (rl->count[sync] < queue_congestion_off_threshold(q))
- blk_clear_congested(rl, sync);
-
- if (rl->count[sync] + 1 <= q->nr_requests) {
- if (waitqueue_active(&rl->wait[sync]))
- wake_up(&rl->wait[sync]);
-
- blk_clear_rl_full(rl, sync);
- }
-}
-
-/*
- * 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_list *rl, bool sync,
- req_flags_t rq_flags)
-{
- struct request_queue *q = rl->q;
-
- q->nr_rqs[sync]--;
- rl->count[sync]--;
- if (rq_flags & RQF_ELVPRIV)
- q->nr_rqs_elvpriv--;
-
- __freed_request(rl, sync);
-
- 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;
- int on_thresh, off_thresh;
-
- WARN_ON_ONCE(q->mq_ops);
-
- spin_lock_irq(q->queue_lock);
- q->nr_requests = nr;
- blk_queue_congestion_threshold(q);
- on_thresh = queue_congestion_on_threshold(q);
- off_thresh = queue_congestion_off_threshold(q);
-
- blk_queue_for_each_rl(rl, q) {
- if (rl->count[BLK_RW_SYNC] >= on_thresh)
- blk_set_congested(rl, BLK_RW_SYNC);
- else if (rl->count[BLK_RW_SYNC] < off_thresh)
- blk_clear_congested(rl, BLK_RW_SYNC);
-
- if (rl->count[BLK_RW_ASYNC] >= on_thresh)
- blk_set_congested(rl, BLK_RW_ASYNC);
- else if (rl->count[BLK_RW_ASYNC] < off_thresh)
- blk_clear_congested(rl, BLK_RW_ASYNC);
-
- 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;
-}
-
-/**
- * __get_request - get a free request
- * @rl: request list to allocate from
- * @op: operation and flags
- * @bio: bio to allocate request for (can be %NULL)
- * @flags: BLQ_MQ_REQ_* flags
- * @gfp_mask: allocator flags
- *
- * Get a free request from @q. This function may fail under memory
- * pressure or if @q is dead.
- *
- * Must be called with @q->queue_lock held and,
- * Returns ERR_PTR on failure, with @q->queue_lock held.
- * Returns request pointer on success, with @q->queue_lock *not held*.
- */
-static struct request *__get_request(struct request_list *rl, unsigned int op,
- struct bio *bio, blk_mq_req_flags_t flags, 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 = op_is_sync(op);
- int may_queue;
- req_flags_t rq_flags = RQF_ALLOCED;
-
- lockdep_assert_held(q->queue_lock);
-
- if (unlikely(blk_queue_dying(q)))
- return ERR_PTR(-ENODEV);
-
- may_queue = elv_may_queue(q, op);
- if (may_queue == ELV_MQUEUE_NO)
- goto rq_starved;
-
- 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_rl_full(rl, is_sync)) {
- ioc_set_batching(q, ioc);
- blk_set_rl_full(rl, is_sync);
- } else {
- if (may_queue != ELV_MQUEUE_MUST
- && !ioc_batching(q, ioc)) {
- /*
- * The queue is full and the allocating
- * process is not a "batcher", and not
- * exempted by the IO scheduler
- */
- return ERR_PTR(-ENOMEM);
- }
- }
- }
- blk_set_congested(rl, is_sync);
- }
-
- /*
- * Only allow batching queuers to allocate up to 50% over the defined
- * limit of requests, otherwise we could have thousands of requests
- * allocated with any setting of ->nr_requests
- */
- if (rl->count[is_sync] >= (3 * q->nr_requests / 2))
- return ERR_PTR(-ENOMEM);
-
- q->nr_rqs[is_sync]++;
- rl->count[is_sync]++;
- rl->starved[is_sync] = 0;
-
- /*
- * Decide whether the new request will be managed by elevator. If
- * so, mark @rq_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.
- *
- * Flush requests do not use the elevator so skip initialization.
- * This allows a request to share the flush and elevator data.
- *
- * Also, lookup icq while holding queue_lock. If it doesn't exist,
- * it will be created after releasing queue_lock.
- */
- if (!op_is_flush(op) && !blk_queue_bypass(q)) {
- rq_flags |= RQF_ELVPRIV;
- q->nr_rqs_elvpriv++;
- if (et->icq_cache && ioc)
- icq = ioc_lookup_icq(ioc, q);
- }
-
- if (blk_queue_io_stat(q))
- rq_flags |= RQF_IO_STAT;
- spin_unlock_irq(q->queue_lock);
-
- /* allocate and init request */
- rq = mempool_alloc(rl->rq_pool, gfp_mask);
- if (!rq)
- goto fail_alloc;
-
- blk_rq_init(q, rq);
- blk_rq_set_rl(rq, rl);
- rq->cmd_flags = op;
- rq->rq_flags = rq_flags;
- if (flags & BLK_MQ_REQ_PREEMPT)
- rq->rq_flags |= RQF_PREEMPT;
-
- /* init elvpriv */
- if (rq_flags & RQF_ELVPRIV) {
- if (unlikely(et->icq_cache && !icq)) {
- if (ioc)
- icq = ioc_create_icq(ioc, q, gfp_mask);
- if (!icq)
- goto fail_elvpriv;
- }
-
- 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
- * not count toward the nr_batch_requests limit. There will always
- * be some limit enforced by BLK_BATCH_TIME.
- */
- if (ioc_batching(q, ioc))
- ioc->nr_batch_requests--;
-
- trace_block_getrq(q, bio, op);
- 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: dev %s: request aux data allocation failed, iosched may be disturbed\n",
- __func__, dev_name(q->backing_dev_info->dev));
-
- rq->rq_flags &= ~RQF_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, is_sync, rq_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 ERR_PTR(-ENOMEM);
-}
-
-/**
- * get_request - get a free request
- * @q: request_queue to allocate request from
- * @op: operation and flags
- * @bio: bio to allocate request for (can be %NULL)
- * @flags: BLK_MQ_REQ_* flags.
- * @gfp: allocator flags
- *
- * Get a free request from @q. If %BLK_MQ_REQ_NOWAIT is set in @flags,
- * this function keeps retrying under memory pressure and fails iff @q is dead.
- *
- * Must be called with @q->queue_lock held and,
- * Returns ERR_PTR on failure, with @q->queue_lock held.
- * Returns request pointer on success, with @q->queue_lock *not held*.
- */
-static struct request *get_request(struct request_queue *q, unsigned int op,
- struct bio *bio, blk_mq_req_flags_t flags, gfp_t gfp)
-{
- const bool is_sync = op_is_sync(op);
- DEFINE_WAIT(wait);
- struct request_list *rl;
- struct request *rq;
-
- lockdep_assert_held(q->queue_lock);
- WARN_ON_ONCE(q->mq_ops);
-
- rl = blk_get_rl(q, bio); /* transferred to @rq on success */
-retry:
- rq = __get_request(rl, op, bio, flags, gfp);
- if (!IS_ERR(rq))
- return rq;
-
- if (op & REQ_NOWAIT) {
- blk_put_rl(rl);
- return ERR_PTR(-EAGAIN);
- }
-
- if ((flags & BLK_MQ_REQ_NOWAIT) || unlikely(blk_queue_dying(q))) {
- blk_put_rl(rl);
- return rq;
- }
-
- /* wait on @rl and retry */
- prepare_to_wait_exclusive(&rl->wait[is_sync], &wait,
- TASK_UNINTERRUPTIBLE);
-
- trace_block_sleeprq(q, bio, op);
-
- spin_unlock_irq(q->queue_lock);
- io_schedule();
-
- /*
- * 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);
-
- spin_lock_irq(q->queue_lock);
- finish_wait(&rl->wait[is_sync], &wait);
-
- goto retry;
-}
-
-/* flags: BLK_MQ_REQ_PREEMPT and/or BLK_MQ_REQ_NOWAIT. */
-static struct request *blk_old_get_request(struct request_queue *q,
- unsigned int op, blk_mq_req_flags_t flags)
-{
- struct request *rq;
- gfp_t gfp_mask = flags & BLK_MQ_REQ_NOWAIT ? GFP_ATOMIC : GFP_NOIO;
- int ret = 0;
-
- WARN_ON_ONCE(q->mq_ops);
-
- /* create ioc upfront */
- create_io_context(gfp_mask, q->node);
-
- ret = blk_queue_enter(q, flags);
- if (ret)
- return ERR_PTR(ret);
- spin_lock_irq(q->queue_lock);
- rq = get_request(q, op, NULL, flags, gfp_mask);
- if (IS_ERR(rq)) {
- spin_unlock_irq(q->queue_lock);
- blk_queue_exit(q);
- return rq;
- }
-
- /* q->queue_lock is unlocked at this point */
- rq->__data_len = 0;
- rq->__sector = (sector_t) -1;
- rq->bio = rq->biotail = NULL;
- return rq;
-}
-
/**
* blk_get_request - allocate a request
* @q: request queue to allocate a request for
@@ -1623,170 +576,17 @@ struct request *blk_get_request(struct request_queue *q, unsigned int op,
WARN_ON_ONCE(op & REQ_NOWAIT);
WARN_ON_ONCE(flags & ~(BLK_MQ_REQ_NOWAIT | BLK_MQ_REQ_PREEMPT));
- if (q->mq_ops) {
- req = blk_mq_alloc_request(q, op, flags);
- if (!IS_ERR(req) && q->mq_ops->initialize_rq_fn)
- q->mq_ops->initialize_rq_fn(req);
- } else {
- req = blk_old_get_request(q, op, flags);
- if (!IS_ERR(req) && q->initialize_rq_fn)
- q->initialize_rq_fn(req);
- }
+ req = blk_mq_alloc_request(q, op, flags);
+ if (!IS_ERR(req) && q->mq_ops->initialize_rq_fn)
+ q->mq_ops->initialize_rq_fn(req);
return req;
}
EXPORT_SYMBOL(blk_get_request);
-/**
- * blk_requeue_request - put a request back on queue
- * @q: request queue where request should be inserted
- * @rq: request to be inserted
- *
- * Description:
- * Drivers often keep queueing requests until the hardware cannot accept
- * more, when that condition happens we need to put the request back
- * on the queue. Must be called with queue lock held.
- */
-void blk_requeue_request(struct request_queue *q, struct request *rq)
-{
- lockdep_assert_held(q->queue_lock);
- WARN_ON_ONCE(q->mq_ops);
-
- blk_delete_timer(rq);
- blk_clear_rq_complete(rq);
- trace_block_rq_requeue(q, rq);
- rq_qos_requeue(q, rq);
-
- if (rq->rq_flags & RQF_QUEUED)
- blk_queue_end_tag(q, rq);
-
- BUG_ON(blk_queued_rq(rq));
-
- elv_requeue_request(q, rq);
-}
-EXPORT_SYMBOL(blk_requeue_request);
-
-static void add_acct_request(struct request_queue *q, struct request *rq,
- int where)
-{
- blk_account_io_start(rq, true);
- __elv_add_request(q, rq, where);
-}
-
-static void part_round_stats_single(struct request_queue *q, int cpu,
- struct hd_struct *part, unsigned long now,
- unsigned int inflight)
-{
- 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;
-}
-
-/**
- * part_round_stats() - Round off the performance stats on a struct disk_stats.
- * @q: target block queue
- * @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
- * time it has been in this state for.
- *
- * Normally, that accounting is done on IO completion, but that can result
- * in more than a second's worth of IO being accounted for within any one
- * second, leading to >100% utilisation. To deal with that, we call this
- * function to do a round-off before returning the results when reading
- * /proc/diskstats. This accounts immediately for all queue usage up to
- * the current jiffies and restarts the counters again.
- */
-void part_round_stats(struct request_queue *q, int cpu, struct hd_struct *part)
-{
- struct hd_struct *part2 = NULL;
- unsigned long now = jiffies;
- unsigned int inflight[2];
- int stats = 0;
-
- if (part->stamp != now)
- stats |= 1;
-
- if (part->partno) {
- part2 = &part_to_disk(part)->part0;
- if (part2->stamp != now)
- stats |= 2;
- }
-
- if (!stats)
- return;
-
- part_in_flight(q, part, inflight);
-
- if (stats & 2)
- part_round_stats_single(q, cpu, part2, now, inflight[1]);
- if (stats & 1)
- part_round_stats_single(q, cpu, part, now, inflight[0]);
-}
-EXPORT_SYMBOL_GPL(part_round_stats);
-
-void __blk_put_request(struct request_queue *q, struct request *req)
-{
- req_flags_t rq_flags = req->rq_flags;
-
- if (unlikely(!q))
- return;
-
- if (q->mq_ops) {
- blk_mq_free_request(req);
- return;
- }
-
- lockdep_assert_held(q->queue_lock);
-
- blk_req_zone_write_unlock(req);
- blk_pm_put_request(req);
- blk_pm_mark_last_busy(req);
-
- elv_completed_request(q, req);
-
- /* this is a bio leak */
- WARN_ON(req->bio != NULL);
-
- rq_qos_done(q, req);
-
- /*
- * Request may not have originated from ll_rw_blk. if not,
- * it didn't come out of our reserved rq pools
- */
- if (rq_flags & RQF_ALLOCED) {
- struct request_list *rl = blk_rq_rl(req);
- bool sync = op_is_sync(req->cmd_flags);
-
- BUG_ON(!list_empty(&req->queuelist));
- BUG_ON(ELV_ON_HASH(req));
-
- blk_free_request(rl, req);
- freed_request(rl, sync, rq_flags);
- blk_put_rl(rl);
- blk_queue_exit(q);
- }
-}
-EXPORT_SYMBOL_GPL(__blk_put_request);
-
void blk_put_request(struct request *req)
{
- struct request_queue *q = req->q;
-
- 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);
- }
+ blk_mq_free_request(req);
}
EXPORT_SYMBOL(blk_put_request);
@@ -1806,7 +606,6 @@ bool bio_attempt_back_merge(struct request_queue *q, struct request *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;
@@ -1830,7 +629,6 @@ bool bio_attempt_front_merge(struct request_queue *q, struct request *req,
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;
@@ -1850,7 +648,6 @@ bool bio_attempt_discard_merge(struct request_queue *q, struct request *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));
req->nr_phys_segments = segments + 1;
blk_account_io_start(req, false);
@@ -1883,7 +680,6 @@ no_merge:
* 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 request **same_queue_rq)
{
struct blk_plug *plug;
@@ -1893,25 +689,19 @@ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
plug = current->plug;
if (!plug)
return false;
- *request_count = 0;
- if (q->mq_ops)
- plug_list = &plug->mq_list;
- else
- plug_list = &plug->list;
+ plug_list = &plug->mq_list;
list_for_each_entry_reverse(rq, plug_list, queuelist) {
bool merged = false;
- if (rq->q == q) {
- (*request_count)++;
+ if (rq->q == q && same_queue_rq) {
/*
* Only blk-mq multiple hardware queues case checks the
* rq in the same queue, there should be only one such
* rq in a queue
**/
- if (same_queue_rq)
- *same_queue_rq = rq;
+ *same_queue_rq = rq;
}
if (rq->q != q || !blk_rq_merge_ok(rq, bio))
@@ -1938,176 +728,18 @@ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
return false;
}
-unsigned int blk_plug_queued_count(struct request_queue *q)
-{
- struct blk_plug *plug;
- struct request *rq;
- struct list_head *plug_list;
- unsigned int ret = 0;
-
- plug = current->plug;
- if (!plug)
- goto out;
-
- if (q->mq_ops)
- plug_list = &plug->mq_list;
- else
- plug_list = &plug->list;
-
- list_for_each_entry(rq, plug_list, queuelist) {
- if (rq->q == q)
- ret++;
- }
-out:
- return ret;
-}
-
void blk_init_request_from_bio(struct request *req, struct bio *bio)
{
- struct io_context *ioc = rq_ioc(bio);
-
if (bio->bi_opf & REQ_RAHEAD)
req->cmd_flags |= REQ_FAILFAST_MASK;
req->__sector = bio->bi_iter.bi_sector;
- if (ioprio_valid(bio_prio(bio)))
- req->ioprio = bio_prio(bio);
- else if (ioc)
- req->ioprio = ioc->ioprio;
- else
- req->ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, 0);
+ req->ioprio = bio_prio(bio);
req->write_hint = bio->bi_write_hint;
blk_rq_bio_prep(req->q, req, bio);
}
EXPORT_SYMBOL_GPL(blk_init_request_from_bio);
-static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
-{
- struct blk_plug *plug;
- int where = ELEVATOR_INSERT_SORT;
- struct request *req, *free;
- unsigned int request_count = 0;
-
- /*
- * low level driver can indicate that it wants pages above a
- * certain limit bounced to low memory (ie for highmem, or even
- * ISA dma in theory)
- */
- blk_queue_bounce(q, &bio);
-
- blk_queue_split(q, &bio);
-
- if (!bio_integrity_prep(bio))
- return BLK_QC_T_NONE;
-
- if (op_is_flush(bio->bi_opf)) {
- spin_lock_irq(q->queue_lock);
- where = ELEVATOR_INSERT_FLUSH;
- goto get_rq;
- }
-
- /*
- * Check if we can merge with the plugged list before grabbing
- * any locks.
- */
- if (!blk_queue_nomerges(q)) {
- if (blk_attempt_plug_merge(q, bio, &request_count, NULL))
- return BLK_QC_T_NONE;
- } else
- request_count = blk_plug_queued_count(q);
-
- spin_lock_irq(q->queue_lock);
-
- switch (elv_merge(q, &req, bio)) {
- case ELEVATOR_BACK_MERGE:
- if (!bio_attempt_back_merge(q, req, bio))
- break;
- elv_bio_merged(q, req, bio);
- free = attempt_back_merge(q, req);
- if (free)
- __blk_put_request(q, free);
- else
- elv_merged_request(q, req, ELEVATOR_BACK_MERGE);
- goto out_unlock;
- case ELEVATOR_FRONT_MERGE:
- if (!bio_attempt_front_merge(q, req, bio))
- break;
- elv_bio_merged(q, req, bio);
- free = attempt_front_merge(q, req);
- if (free)
- __blk_put_request(q, free);
- else
- elv_merged_request(q, req, ELEVATOR_FRONT_MERGE);
- goto out_unlock;
- default:
- break;
- }
-
-get_rq:
- rq_qos_throttle(q, bio, q->queue_lock);
-
- /*
- * Grab a free request. This is might sleep but can not fail.
- * Returns with the queue unlocked.
- */
- blk_queue_enter_live(q);
- req = get_request(q, bio->bi_opf, bio, 0, GFP_NOIO);
- if (IS_ERR(req)) {
- blk_queue_exit(q);
- rq_qos_cleanup(q, bio);
- if (PTR_ERR(req) == -ENOMEM)
- bio->bi_status = BLK_STS_RESOURCE;
- else
- bio->bi_status = BLK_STS_IOERR;
- bio_endio(bio);
- goto out_unlock;
- }
-
- rq_qos_track(q, req, bio);
-
- /*
- * After dropping the lock and possibly sleeping here, our request
- * may now be mergeable after it had proven unmergeable (above).
- * We don't worry about that case for efficiency. It won't happen
- * often, and the elevators are able to handle it.
- */
- blk_init_request_from_bio(req, bio);
-
- if (test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags))
- req->cpu = raw_smp_processor_id();
-
- plug = current->plug;
- if (plug) {
- /*
- * If this is the first request added after a plug, fire
- * of a plug trace.
- *
- * @request_count may become stale because of schedule
- * out, so check plug list again.
- */
- if (!request_count || list_empty(&plug->list))
- trace_block_plug(q);
- else {
- struct request *last = list_entry_rq(plug->list.prev);
- if (request_count >= BLK_MAX_REQUEST_COUNT ||
- blk_rq_bytes(last) >= BLK_PLUG_FLUSH_SIZE) {
- 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);
- }
-
- return BLK_QC_T_NONE;
-}
-
static void handle_bad_sector(struct bio *bio, sector_t maxsector)
{
char b[BDEVNAME_SIZE];
@@ -2259,7 +891,7 @@ generic_make_request_checks(struct bio *bio)
* For a REQ_NOWAIT based request, return -EOPNOTSUPP
* if queue is not a request based queue.
*/
- if ((bio->bi_opf & REQ_NOWAIT) && !queue_is_rq_based(q))
+ if ((bio->bi_opf & REQ_NOWAIT) && !queue_is_mq(q))
goto not_supported;
if (should_fail_bio(bio))
@@ -2289,6 +921,9 @@ generic_make_request_checks(struct bio *bio)
}
}
+ if (!test_bit(QUEUE_FLAG_POLL, &q->queue_flags))
+ bio->bi_opf &= ~REQ_HIPRI;
+
switch (bio_op(bio)) {
case REQ_OP_DISCARD:
if (!blk_queue_discard(q))
@@ -2561,17 +1196,6 @@ blk_qc_t submit_bio(struct bio *bio)
}
EXPORT_SYMBOL(submit_bio);
-bool blk_poll(struct request_queue *q, blk_qc_t cookie)
-{
- if (!q->poll_fn || !blk_qc_t_valid(cookie))
- return false;
-
- if (current->plug)
- blk_flush_plug_list(current->plug, false);
- return q->poll_fn(q, cookie);
-}
-EXPORT_SYMBOL_GPL(blk_poll);
-
/**
* blk_cloned_rq_check_limits - Helper function to check a cloned request
* for new the queue limits
@@ -2619,8 +1243,7 @@ static int blk_cloned_rq_check_limits(struct request_queue *q,
*/
blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *rq)
{
- unsigned long flags;
- int where = ELEVATOR_INSERT_BACK;
+ blk_qc_t unused;
if (blk_cloned_rq_check_limits(q, rq))
return BLK_STS_IOERR;
@@ -2629,38 +1252,15 @@ blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *
should_fail_request(&rq->rq_disk->part0, blk_rq_bytes(rq)))
return BLK_STS_IOERR;
- if (q->mq_ops) {
- if (blk_queue_io_stat(q))
- blk_account_io_start(rq, true);
- /*
- * Since we have a scheduler attached on the top device,
- * bypass a potential scheduler on the bottom device for
- * insert.
- */
- return blk_mq_request_issue_directly(rq);
- }
-
- spin_lock_irqsave(q->queue_lock, flags);
- if (unlikely(blk_queue_dying(q))) {
- spin_unlock_irqrestore(q->queue_lock, flags);
- return BLK_STS_IOERR;
- }
+ if (blk_queue_io_stat(q))
+ blk_account_io_start(rq, true);
/*
- * Submitting request must be dequeued before calling this function
- * because it will be linked to another request_queue
+ * Since we have a scheduler attached on the top device,
+ * bypass a potential scheduler on the bottom device for
+ * insert.
*/
- BUG_ON(blk_queued_rq(rq));
-
- if (op_is_flush(rq->cmd_flags))
- 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 BLK_STS_OK;
+ return blk_mq_try_issue_directly(rq->mq_hctx, rq, &unused, true, true);
}
EXPORT_SYMBOL_GPL(blk_insert_cloned_request);
@@ -2710,11 +1310,10 @@ void blk_account_io_completion(struct request *req, unsigned int bytes)
if (blk_do_io_stat(req)) {
const int sgrp = op_stat_group(req_op(req));
struct hd_struct *part;
- int cpu;
- cpu = part_stat_lock();
+ part_stat_lock();
part = req->part;
- part_stat_add(cpu, part, sectors[sgrp], bytes >> 9);
+ part_stat_add(part, sectors[sgrp], bytes >> 9);
part_stat_unlock();
}
}
@@ -2729,14 +1328,14 @@ void blk_account_io_done(struct request *req, u64 now)
if (blk_do_io_stat(req) && !(req->rq_flags & RQF_FLUSH_SEQ)) {
const int sgrp = op_stat_group(req_op(req));
struct hd_struct *part;
- int cpu;
- cpu = part_stat_lock();
+ part_stat_lock();
part = req->part;
- part_stat_inc(cpu, part, ios[sgrp]);
- part_stat_add(cpu, part, nsecs[sgrp], now - req->start_time_ns);
- part_round_stats(req->q, cpu, part);
+ update_io_ticks(part, jiffies);
+ part_stat_inc(part, ios[sgrp]);
+ part_stat_add(part, nsecs[sgrp], now - req->start_time_ns);
+ part_stat_add(part, time_in_queue, nsecs_to_jiffies64(now - req->start_time_ns));
part_dec_in_flight(req->q, part, rq_data_dir(req));
hd_struct_put(part);
@@ -2748,16 +1347,15 @@ void blk_account_io_start(struct request *rq, bool new_io)
{
struct hd_struct *part;
int rw = rq_data_dir(rq);
- int cpu;
if (!blk_do_io_stat(rq))
return;
- cpu = part_stat_lock();
+ part_stat_lock();
if (!new_io) {
part = rq->part;
- part_stat_inc(cpu, part, merges[rw]);
+ part_stat_inc(part, merges[rw]);
} else {
part = disk_map_sector_rcu(rq->rq_disk, blk_rq_pos(rq));
if (!hd_struct_try_get(part)) {
@@ -2772,232 +1370,14 @@ void blk_account_io_start(struct request *rq, bool new_io)
part = &rq->rq_disk->part0;
hd_struct_get(part);
}
- part_round_stats(rq->q, cpu, part);
part_inc_in_flight(rq->q, part, rw);
rq->part = part;
}
- part_stat_unlock();
-}
-
-static struct request *elv_next_request(struct request_queue *q)
-{
- struct request *rq;
- struct blk_flush_queue *fq = blk_get_flush_queue(q, NULL);
-
- WARN_ON_ONCE(q->mq_ops);
-
- while (1) {
- list_for_each_entry(rq, &q->queue_head, queuelist) {
-#ifdef CONFIG_PM
- /*
- * If a request gets queued in state RPM_SUSPENDED
- * then that's a kernel bug.
- */
- WARN_ON_ONCE(q->rpm_status == RPM_SUSPENDED);
-#endif
- return rq;
- }
-
- /*
- * Flush request is running and flush request isn't queueable
- * in the drive, we can hold the queue till flush request is
- * finished. Even we don't do this, driver can't dispatch next
- * requests and will requeue them. And this can improve
- * throughput too. For example, we have request flush1, write1,
- * flush 2. flush1 is dispatched, then queue is hold, write1
- * isn't inserted to queue. After flush1 is finished, flush2
- * will be dispatched. Since disk cache is already clean,
- * flush2 will be finished very soon, so looks like flush2 is
- * folded to flush1.
- * Since the queue is hold, a flag is set to indicate the queue
- * should be restarted later. Please see flush_end_io() for
- * details.
- */
- if (fq->flush_pending_idx != fq->flush_running_idx &&
- !queue_flush_queueable(q)) {
- fq->flush_queue_delayed = 1;
- return NULL;
- }
- if (unlikely(blk_queue_bypass(q)) ||
- !q->elevator->type->ops.sq.elevator_dispatch_fn(q, 0))
- return NULL;
- }
-}
-
-/**
- * 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.
- */
-struct request *blk_peek_request(struct request_queue *q)
-{
- struct request *rq;
- int ret;
-
- lockdep_assert_held(q->queue_lock);
- WARN_ON_ONCE(q->mq_ops);
-
- while ((rq = elv_next_request(q)) != NULL) {
- if (!(rq->rq_flags & RQF_STARTED)) {
- /*
- * This is the first time the device driver
- * sees this request (possibly after
- * requeueing). Notify IO scheduler.
- */
- if (rq->rq_flags & RQF_SORTED)
- elv_activate_rq(q, rq);
-
- /*
- * 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
- */
- rq->rq_flags |= RQF_STARTED;
- trace_block_rq_issue(q, rq);
- }
-
- if (!q->boundary_rq || q->boundary_rq == rq) {
- q->end_sector = rq_end_sector(rq);
- q->boundary_rq = NULL;
- }
-
- if (rq->rq_flags & RQF_DONTPREP)
- break;
-
- if (q->dma_drain_size && blk_rq_bytes(rq)) {
- /*
- * make sure space for the drain appears we
- * know we can do this because max_hw_segments
- * has been adjusted to be one fewer than the
- * device can handle
- */
- rq->nr_phys_segments++;
- }
-
- if (!q->prep_rq_fn)
- break;
-
- 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. RQF_STARTED will
- * prevent other fs requests from passing this one.
- */
- if (q->dma_drain_size && blk_rq_bytes(rq) &&
- !(rq->rq_flags & RQF_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 || ret == BLKPREP_INVALID) {
- rq->rq_flags |= RQF_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, ret == BLKPREP_INVALID ?
- BLK_STS_TARGET : BLK_STS_IOERR);
- } else {
- printk(KERN_ERR "%s: bad return=%d\n", __func__, ret);
- break;
- }
- }
-
- return rq;
-}
-EXPORT_SYMBOL(blk_peek_request);
-
-static void blk_dequeue_request(struct request *rq)
-{
- struct request_queue *q = rq->q;
+ update_io_ticks(part, jiffies);
- BUG_ON(list_empty(&rq->queuelist));
- BUG_ON(ELV_ON_HASH(rq));
-
- list_del_init(&rq->queuelist);
-
- /*
- * 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)]++;
-}
-
-/**
- * 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.
- */
-void blk_start_request(struct request *req)
-{
- lockdep_assert_held(req->q->queue_lock);
- WARN_ON_ONCE(req->q->mq_ops);
-
- blk_dequeue_request(req);
-
- if (test_bit(QUEUE_FLAG_STATS, &req->q->queue_flags)) {
- req->io_start_time_ns = ktime_get_ns();
-#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
- req->throtl_size = blk_rq_sectors(req);
-#endif
- req->rq_flags |= RQF_STATS;
- rq_qos_issue(req->q, req);
- }
-
- BUG_ON(blk_rq_is_complete(req));
- 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.
- */
-struct request *blk_fetch_request(struct request_queue *q)
-{
- struct request *rq;
-
- lockdep_assert_held(q->queue_lock);
- WARN_ON_ONCE(q->mq_ops);
-
- rq = blk_peek_request(q);
- if (rq)
- blk_start_request(rq);
- return rq;
+ part_stat_unlock();
}
-EXPORT_SYMBOL(blk_fetch_request);
/*
* Steal bios from a request and add them to a bio list.
@@ -3124,255 +1504,6 @@ bool blk_update_request(struct request *req, blk_status_t error,
}
EXPORT_SYMBOL_GPL(blk_update_request);
-static bool blk_update_bidi_request(struct request *rq, blk_status_t error,
- unsigned int nr_bytes,
- unsigned int bidi_bytes)
-{
- if (blk_update_request(rq, error, nr_bytes))
- return true;
-
- /* 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;
-
- if (blk_queue_add_random(rq->q))
- add_disk_randomness(rq->rq_disk);
-
- return false;
-}
-
-/**
- * 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->rq_flags &= ~RQF_DONTPREP;
- if (q->unprep_rq_fn)
- q->unprep_rq_fn(q, req);
-}
-EXPORT_SYMBOL_GPL(blk_unprep_request);
-
-void blk_finish_request(struct request *req, blk_status_t error)
-{
- struct request_queue *q = req->q;
- u64 now = ktime_get_ns();
-
- lockdep_assert_held(req->q->queue_lock);
- WARN_ON_ONCE(q->mq_ops);
-
- if (req->rq_flags & RQF_STATS)
- blk_stat_add(req, now);
-
- if (req->rq_flags & RQF_QUEUED)
- blk_queue_end_tag(q, req);
-
- BUG_ON(blk_queued_rq(req));
-
- if (unlikely(laptop_mode) && !blk_rq_is_passthrough(req))
- laptop_io_completion(req->q->backing_dev_info);
-
- blk_delete_timer(req);
-
- if (req->rq_flags & RQF_DONTPREP)
- blk_unprep_request(req);
-
- blk_account_io_done(req, now);
-
- if (req->end_io) {
- rq_qos_done(q, req);
- req->end_io(req, error);
- } else {
- if (blk_bidi_rq(req))
- __blk_put_request(req->next_rq->q, req->next_rq);
-
- __blk_put_request(q, req);
- }
-}
-EXPORT_SYMBOL(blk_finish_request);
-
-/**
- * blk_end_bidi_request - Complete a bidi request
- * @rq: the request to complete
- * @error: block status code
- * @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, blk_status_t error,
- unsigned int nr_bytes, unsigned int bidi_bytes)
-{
- struct request_queue *q = rq->q;
- unsigned long flags;
-
- WARN_ON_ONCE(q->mq_ops);
-
- if (blk_update_bidi_request(rq, error, nr_bytes, bidi_bytes))
- return true;
-
- spin_lock_irqsave(q->queue_lock, flags);
- blk_finish_request(rq, error);
- spin_unlock_irqrestore(q->queue_lock, flags);
-
- return false;
-}
-
-/**
- * __blk_end_bidi_request - Complete a bidi request with queue lock held
- * @rq: the request to complete
- * @error: block status code
- * @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
- **/
-static bool __blk_end_bidi_request(struct request *rq, blk_status_t error,
- unsigned int nr_bytes, unsigned int bidi_bytes)
-{
- lockdep_assert_held(rq->q->queue_lock);
- WARN_ON_ONCE(rq->q->mq_ops);
-
- if (blk_update_bidi_request(rq, error, nr_bytes, bidi_bytes))
- return true;
-
- blk_finish_request(rq, error);
-
- return false;
-}
-
-/**
- * blk_end_request - Helper function for drivers to complete the request.
- * @rq: the request being processed
- * @error: block status code
- * @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
- **/
-bool blk_end_request(struct request *rq, blk_status_t error,
- unsigned int nr_bytes)
-{
- WARN_ON_ONCE(rq->q->mq_ops);
- return blk_end_bidi_request(rq, error, nr_bytes, 0);
-}
-EXPORT_SYMBOL(blk_end_request);
-
-/**
- * blk_end_request_all - Helper function for drives to finish the request.
- * @rq: the request to finish
- * @error: block status code
- *
- * Description:
- * Completely finish @rq.
- */
-void blk_end_request_all(struct request *rq, blk_status_t 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);
-
-/**
- * __blk_end_request - Helper function for drivers to complete the request.
- * @rq: the request being processed
- * @error: block status code
- * @nr_bytes: number of bytes to complete
- *
- * Description:
- * 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
- **/
-bool __blk_end_request(struct request *rq, blk_status_t error,
- unsigned int nr_bytes)
-{
- lockdep_assert_held(rq->q->queue_lock);
- WARN_ON_ONCE(rq->q->mq_ops);
-
- return __blk_end_bidi_request(rq, error, nr_bytes, 0);
-}
-EXPORT_SYMBOL(__blk_end_request);
-
-/**
- * __blk_end_request_all - Helper function for drives to finish the request.
- * @rq: the request to finish
- * @error: block status code
- *
- * Description:
- * Completely finish @rq. Must be called with queue lock held.
- */
-void __blk_end_request_all(struct request *rq, blk_status_t error)
-{
- bool pending;
- unsigned int bidi_bytes = 0;
-
- lockdep_assert_held(rq->q->queue_lock);
- WARN_ON_ONCE(rq->q->mq_ops);
-
- 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);
-
-/**
- * __blk_end_request_cur - Helper function to finish the current request chunk.
- * @rq: the request to finish the current chunk for
- * @error: block status code
- *
- * Description:
- * Complete the current consecutively mapped chunk from @rq. Must
- * be called with queue lock held.
- *
- * Return:
- * %false - we are done with this request
- * %true - still buffers pending for this request
- */
-bool __blk_end_request_cur(struct request *rq, blk_status_t error)
-{
- return __blk_end_request(rq, error, blk_rq_cur_bytes(rq));
-}
-EXPORT_SYMBOL(__blk_end_request_cur);
-
void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
struct bio *bio)
{
@@ -3428,8 +1559,8 @@ EXPORT_SYMBOL_GPL(rq_flush_dcache_pages);
*/
int blk_lld_busy(struct request_queue *q)
{
- if (q->lld_busy_fn)
- return q->lld_busy_fn(q);
+ if (queue_is_mq(q) && q->mq_ops->busy)
+ return q->mq_ops->busy(q);
return 0;
}
@@ -3460,7 +1591,6 @@ EXPORT_SYMBOL_GPL(blk_rq_unprep_clone);
*/
static void __blk_rq_prep_clone(struct request *dst, struct request *src)
{
- dst->cpu = src->cpu;
dst->__sector = blk_rq_pos(src);
dst->__data_len = blk_rq_bytes(src);
if (src->rq_flags & RQF_SPECIAL_PAYLOAD) {
@@ -3572,9 +1702,11 @@ void blk_start_plug(struct blk_plug *plug)
if (tsk->plug)
return;
- INIT_LIST_HEAD(&plug->list);
INIT_LIST_HEAD(&plug->mq_list);
INIT_LIST_HEAD(&plug->cb_list);
+ plug->rq_count = 0;
+ plug->multiple_queues = false;
+
/*
* Store ordering should not be needed here, since a potential
* preempt will imply a full memory barrier
@@ -3583,36 +1715,6 @@ void blk_start_plug(struct blk_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)
-{
- lockdep_assert_held(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_irq(q->queue_lock);
-}
-
static void flush_plug_callbacks(struct blk_plug *plug, bool from_schedule)
{
LIST_HEAD(callbacks);
@@ -3657,65 +1759,10 @@ EXPORT_SYMBOL(blk_check_plugged);
void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
{
- struct request_queue *q;
- 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;
-
- 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_irq(q->queue_lock);
- }
-
- /*
- * Short-circuit if @q is dead
- */
- if (unlikely(blk_queue_dying(q))) {
- __blk_end_request_all(rq, BLK_STS_IOERR);
- continue;
- }
-
- /*
- * rq is already accounted, so use raw insert
- */
- if (op_is_flush(rq->cmd_flags))
- __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);
}
void blk_finish_plug(struct blk_plug *plug)
@@ -3742,9 +1789,6 @@ int __init blk_dev_init(void)
if (!kblockd_workqueue)
panic("Failed to create kblockd\n");
- request_cachep = kmem_cache_create("blkdev_requests",
- sizeof(struct request), 0, SLAB_PANIC, NULL);
-
blk_requestq_cachep = kmem_cache_create("request_queue",
sizeof(struct request_queue), 0, SLAB_PANIC, NULL);