}
EXPORT_SYMBOL(blk_dump_rq_flags);
-/*
- * Make sure that plugs that were pending when this function was entered,
- * are now complete and requests pushed to the queue.
-*/
-static inline void queue_sync_plugs(struct request_queue *q)
-{
- /*
- * If the current process is plugged and has barriers submitted,
- * we will livelock if we don't unplug first.
- */
- blk_flush_plug(current);
-}
-
static void blk_delay_work(struct work_struct *work)
{
struct request_queue *q;
*/
void blk_delay_queue(struct request_queue *q, unsigned long msecs)
{
- schedule_delayed_work(&q->delay_work, msecs_to_jiffies(msecs));
+ queue_delayed_work(kblockd_workqueue, &q->delay_work,
+ msecs_to_jiffies(msecs));
}
EXPORT_SYMBOL(blk_delay_queue);
**/
void blk_stop_queue(struct request_queue *q)
{
- cancel_delayed_work(&q->delay_work);
+ __cancel_delayed_work(&q->delay_work);
queue_flag_set(QUEUE_FLAG_STOPPED, q);
}
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 blk_throtl_exit() to be called with queue lock initialized.
+ *
*/
void blk_sync_queue(struct request_queue *q)
{
del_timer_sync(&q->timeout);
- throtl_shutdown_timer_wq(q);
cancel_delayed_work_sync(&q->delay_work);
- queue_sync_plugs(q);
}
EXPORT_SYMBOL(blk_sync_queue);
* 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;
- /*
- * Only recurse once to avoid overrunning the stack, let the unplug
- * handling reinvoke the handler shortly if we already got there.
- */
- if (!queue_flag_test_and_set(QUEUE_FLAG_REENTER, q)) {
- q->request_fn(q);
- queue_flag_clear(QUEUE_FLAG_REENTER, q);
- } else
- queue_delayed_work(kblockd_workqueue, &q->delay_work, 0);
+ q->request_fn(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.
+ */
+void blk_run_queue_async(struct request_queue *q)
+{
+ if (likely(!blk_queue_stopped(q))) {
+ __cancel_delayed_work(&q->delay_work);
+ queue_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
{
kobject_put(&q->kobj);
}
+EXPORT_SYMBOL(blk_put_queue);
+/*
+ * Note: If a driver supplied the queue lock, it should not zap that lock
+ * unexpectedly as some queue cleanup components like elevator_exit() and
+ * blk_throtl_exit() need queue lock.
+ */
void blk_cleanup_queue(struct request_queue *q)
{
/*
if (q->elevator)
elevator_exit(q->elevator);
+ blk_throtl_exit(q);
+
blk_put_queue(q);
}
EXPORT_SYMBOL(blk_cleanup_queue);
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;
+
return q;
}
EXPORT_SYMBOL(blk_alloc_queue_node);
q->prep_rq_fn = NULL;
q->unprep_rq_fn = NULL;
q->queue_flags = QUEUE_FLAG_DEFAULT;
- q->queue_lock = lock;
+
+ /* Override internal queue lock with supplied lock pointer */
+ if (lock)
+ q->queue_lock = lock;
/*
* This also sets hw/phys segments, boundary and size
return 1;
}
+EXPORT_SYMBOL(blk_get_queue);
static inline void blk_free_request(struct request_queue *q, struct request *rq)
{
- BUG_ON(rq->cmd_flags & REQ_ON_PLUG);
-
if (rq->cmd_flags & REQ_ELVPRIV)
elv_put_request(q, rq);
mempool_free(rq, q->rq.rq_pool);
{
struct request *rq;
+ if (unlikely(test_bit(QUEUE_FLAG_DEAD, &q->queue_flags)))
+ return NULL;
+
BUG_ON(rw != READ && rw != WRITE);
spin_lock_irq(q->queue_lock);
{
const int ff = bio->bi_rw & REQ_FAILFAST_MASK;
- /*
- * Debug stuff, kill later
- */
- if (!rq_mergeable(req)) {
- blk_dump_rq_flags(req, "back");
- return false;
- }
-
if (!ll_back_merge_fn(q, req, bio))
return false;
req->ioprio = ioprio_best(req->ioprio, bio_prio(bio));
drive_stat_acct(req, 0);
+ elv_bio_merged(q, req, bio);
return true;
}
struct request *req, struct bio *bio)
{
const int ff = bio->bi_rw & REQ_FAILFAST_MASK;
- sector_t sector;
-
- /*
- * Debug stuff, kill later
- */
- if (!rq_mergeable(req)) {
- blk_dump_rq_flags(req, "front");
- return false;
- }
if (!ll_front_merge_fn(q, req, bio))
return false;
if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff)
blk_rq_set_mixed_merge(req);
- sector = bio->bi_sector;
-
bio->bi_next = req->bio;
req->bio = bio;
req->ioprio = ioprio_best(req->ioprio, bio_prio(bio));
drive_stat_acct(req, 0);
+ elv_bio_merged(q, req, bio);
return true;
}
/*
* Attempts to merge with the plugged list in the current process. Returns
- * true if merge was succesful, otherwise false.
+ * true if merge was successful, otherwise false.
*/
static bool attempt_plug_merge(struct task_struct *tsk, struct request_queue *q,
struct bio *bio)
el_ret = elv_merge(q, &req, bio);
if (el_ret == ELEVATOR_BACK_MERGE) {
- BUG_ON(req->cmd_flags & REQ_ON_PLUG);
if (bio_attempt_back_merge(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) {
- BUG_ON(req->cmd_flags & REQ_ON_PLUG);
if (bio_attempt_front_merge(q, req, bio)) {
if (!attempt_front_merge(q, req))
elv_merged_request(q, req, el_ret);
init_request_from_bio(req, bio);
if (test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags) ||
- bio_flagged(bio, BIO_CPU_AFFINE)) {
- req->cpu = blk_cpu_to_group(get_cpu());
- put_cpu();
- }
+ bio_flagged(bio, BIO_CPU_AFFINE))
+ req->cpu = raw_smp_processor_id();
plug = current->plug;
if (plug) {
- if (!plug->should_sort && !list_empty(&plug->list)) {
+ /*
+ * If this is the first request added after a plug, fire
+ * of a plug trace. If others have been added before, check
+ * if we have multiple devices in this plug. If so, make a
+ * note to sort the list before dispatch.
+ */
+ if (list_empty(&plug->list))
+ trace_block_plug(q);
+ else if (!plug->should_sort) {
struct request *__rq;
__rq = list_entry_rq(plug->list.prev);
if (__rq->q != q)
plug->should_sort = 1;
}
- /*
- * Debug flag, kill later
- */
- req->cmd_flags |= REQ_ON_PLUG;
+ if (plug->count >= BLK_MAX_REQUEST_COUNT)
+ blk_flush_plug_list(plug, false);
+ plug->count++;
list_add_tail(&req->queuelist, &plug->list);
drive_stat_acct(req, 1);
} else {
}
__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)
{
- struct hd_struct *part = bio->bi_bdev->bd_part;
-
- if (part_to_disk(part)->part0.make_it_fail || 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 IS_ERR(dir) ? PTR_ERR(dir) : 0;
}
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 */
old_dev = 0;
do {
char b[BDEVNAME_SIZE];
+ struct hd_struct *part;
q = bdev_get_queue(bio->bi_bdev);
if (unlikely(!q)) {
if (unlikely(test_bit(QUEUE_FLAG_DEAD, &q->queue_flags)))
goto end_io;
- if (should_fail_request(bio))
+ part = bio->bi_bdev->bd_part;
+ if (should_fail_request(part, bio->bi_size) ||
+ should_fail_request(&part_to_disk(part)->part0,
+ bio->bi_size))
goto end_io;
/*
goto end_io;
}
- blk_throtl_bio(q, &bio);
+ if (blk_throtl_bio(q, &bio))
+ goto end_io;
/*
* If bio = NULL, bio has been throttled and will be submitted
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;
-#ifdef CONFIG_FAIL_MAKE_REQUEST
- if (rq->rq_disk && rq->rq_disk->part0.make_it_fail &&
- should_fail(&fail_make_request, blk_rq_bytes(rq)))
+ if (rq->rq_disk &&
+ should_fail_request(&rq->rq_disk->part0, blk_rq_bytes(rq)))
return -EIO;
-#endif
spin_lock_irqsave(q->queue_lock, flags);
*/
BUG_ON(blk_queued_rq(rq));
- add_acct_request(q, rq, ELEVATOR_INSERT_BACK);
+ if (rq->cmd_flags & (REQ_FLUSH|REQ_FUA))
+ where = ELEVATOR_INSERT_FLUSH;
+
+ add_acct_request(q, rq, where);
spin_unlock_irqrestore(q->queue_lock, flags);
return 0;
if (error && req->cmd_type == REQ_TYPE_FS &&
!(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)blk_rq_pos(req));
+ 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 -EIO:
+ default:
+ error_type = "I/O";
+ break;
+ }
+ printk(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);
* size, something has gone terribly wrong.
*/
if (blk_rq_bytes(req) < blk_rq_cur_bytes(req)) {
- printk(KERN_ERR "blk: request botched\n");
+ blk_dump_rq_flags(req, "request botched");
req->__data_len = blk_rq_cur_bytes(req);
}
* %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,
+bool __blk_end_bidi_request(struct request *rq, int error,
unsigned int nr_bytes, unsigned int bidi_bytes)
{
if (blk_update_bidi_request(rq, error, nr_bytes, bidi_bytes))
plug->magic = PLUG_MAGIC;
INIT_LIST_HEAD(&plug->list);
+ INIT_LIST_HEAD(&plug->cb_list);
plug->should_sort = 0;
+ plug->count = 0;
/*
* If this is a nested plug, don't actually assign it. It will be
struct request *rqa = container_of(a, struct request, queuelist);
struct request *rqb = container_of(b, struct request, queuelist);
- return !(rqa->q == rqb->q);
+ return !(rqa->q <= rqb->q);
+}
+
+/*
+ * 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 we are punting this to kblockd, then we can safely drop
+ * the queue_lock before waking kblockd (which needs to take
+ * this lock).
+ */
+ if (from_schedule) {
+ spin_unlock(q->queue_lock);
+ blk_run_queue_async(q);
+ } else {
+ __blk_run_queue(q);
+ spin_unlock(q->queue_lock);
+ }
+
+}
+
+static void flush_plug_callbacks(struct blk_plug *plug)
+{
+ LIST_HEAD(callbacks);
+
+ if (list_empty(&plug->cb_list))
+ return;
+
+ 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);
+ }
}
-static void flush_plug_list(struct blk_plug *plug)
+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;
BUG_ON(plug->magic != PLUG_MAGIC);
+ flush_plug_callbacks(plug);
if (list_empty(&plug->list))
return;
- if (plug->should_sort)
- list_sort(NULL, &plug->list, plug_rq_cmp);
+ list_splice_init(&plug->list, &list);
+ plug->count = 0;
+
+ if (plug->should_sort) {
+ list_sort(NULL, &list, plug_rq_cmp);
+ plug->should_sort = 0;
+ }
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(&plug->list)) {
- rq = list_entry_rq(plug->list.next);
+ while (!list_empty(&list)) {
+ rq = list_entry_rq(list.next);
list_del_init(&rq->queuelist);
- BUG_ON(!(rq->cmd_flags & REQ_ON_PLUG));
BUG_ON(!rq->q);
if (rq->q != q) {
- if (q) {
- __blk_run_queue(q);
- spin_unlock(q->queue_lock);
- }
+ /*
+ * This drops the queue lock
+ */
+ if (q)
+ queue_unplugged(q, depth, from_schedule);
q = rq->q;
+ depth = 0;
spin_lock(q->queue_lock);
}
- rq->cmd_flags &= ~REQ_ON_PLUG;
-
/*
* rq is already accounted, so use raw insert
*/
- __elv_add_request(q, rq, ELEVATOR_INSERT_SORT);
- }
+ 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);
- if (q) {
- __blk_run_queue(q);
- spin_unlock(q->queue_lock);
+ depth++;
}
- BUG_ON(!list_empty(&plug->list));
- local_irq_restore(flags);
-}
-
-static void __blk_finish_plug(struct task_struct *tsk, struct blk_plug *plug)
-{
- flush_plug_list(plug);
+ /*
+ * This drops the queue lock
+ */
+ if (q)
+ queue_unplugged(q, depth, from_schedule);
- if (plug == tsk->plug)
- tsk->plug = NULL;
+ local_irq_restore(flags);
}
void blk_finish_plug(struct blk_plug *plug)
{
- if (plug)
- __blk_finish_plug(current, plug);
-}
-EXPORT_SYMBOL(blk_finish_plug);
+ blk_flush_plug_list(plug, false);
-void __blk_flush_plug(struct task_struct *tsk, struct blk_plug *plug)
-{
- __blk_finish_plug(tsk, plug);
- tsk->plug = plug;
+ if (plug == current->plug)
+ current->plug = NULL;
}
-EXPORT_SYMBOL(__blk_flush_plug);
+EXPORT_SYMBOL(blk_finish_plug);
int __init blk_dev_init(void)
{