Merge branch 'for-4.15/block' of git://git.kernel.dk/linux-block

Pull core block layer updates from Jens Axboe:
 "This is the main pull request for block storage for 4.15-rc1.

  Nothing out of the ordinary in here, and no API changes or anything
  like that. Just various new features for drivers, core changes, etc.
  In particular, this pull request contains:

   - A patch series from Bart, closing the whole on blk/scsi-mq queue
     quescing.

   - A series from Christoph, building towards hidden gendisks (for
     multipath) and ability to move bio chains around.

   - NVMe
        - Support for native multipath for NVMe (Christoph).
        - Userspace notifications for AENs (Keith).
        - Command side-effects support (Keith).
        - SGL support (Chaitanya Kulkarni)
        - FC fixes and improvements (James Smart)
        - Lots of fixes and tweaks (Various)

   - bcache
        - New maintainer (Michael Lyle)
        - Writeback control improvements (Michael)
        - Various fixes (Coly, Elena, Eric, Liang, et al)

   - lightnvm updates, mostly centered around the pblk interface
     (Javier, Hans, and Rakesh).

   - Removal of unused bio/bvec kmap atomic interfaces (me, Christoph)

   - Writeback series that fix the much discussed hundreds of millions
     of sync-all units. This goes all the way, as discussed previously
     (me).

   - Fix for missing wakeup on writeback timer adjustments (Yafang
     Shao).

   - Fix laptop mode on blk-mq (me).

   - {mq,name} tupple lookup for IO schedulers, allowing us to have
     alias names. This means you can use 'deadline' on both !mq and on
     mq (where it's called mq-deadline). (me).

   - blktrace race fix, oopsing on sg load (me).

   - blk-mq optimizations (me).

   - Obscure waitqueue race fix for kyber (Omar).

   - NBD fixes (Josef).

   - Disable writeback throttling by default on bfq, like we do on cfq
     (Luca Miccio).

   - Series from Ming that enable us to treat flush requests on blk-mq
     like any other request. This is a really nice cleanup.

   - Series from Ming that improves merging on blk-mq with schedulers,
     getting us closer to flipping the switch on scsi-mq again.

   - BFQ updates (Paolo).

   - blk-mq atomic flags memory ordering fixes (Peter Z).

   - Loop cgroup support (Shaohua).

   - Lots of minor fixes from lots of different folks, both for core and
     driver code"

* 'for-4.15/block' of git://git.kernel.dk/linux-block: (294 commits)
  nvme: fix visibility of "uuid" ns attribute
  blk-mq: fixup some comment typos and lengths
  ide: ide-atapi: fix compile error with defining macro DEBUG
  blk-mq: improve tag waiting setup for non-shared tags
  brd: remove unused brd_mutex
  blk-mq: only run the hardware queue if IO is pending
  block: avoid null pointer dereference on null disk
  fs: guard_bio_eod() needs to consider partitions
  xtensa/simdisk: fix compile error
  nvme: expose subsys attribute to sysfs
  nvme: create 'slaves' and 'holders' entries for hidden controllers
  block: create 'slaves' and 'holders' entries for hidden gendisks
  nvme: also expose the namespace identification sysfs files for mpath nodes
  nvme: implement multipath access to nvme subsystems
  nvme: track shared namespaces
  nvme: introduce a nvme_ns_ids structure
  nvme: track subsystems
  block, nvme: Introduce blk_mq_req_flags_t
  block, scsi: Make SCSI quiesce and resume work reliably
  block: Add the QUEUE_FLAG_PREEMPT_ONLY request queue flag
  ...

26 files changed, 1097 insertions, 616 deletions

diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index a4783da90ba8..889a8549d97f 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -108,6 +108,7 @@
 #include "blk-mq-tag.h"
 #include "blk-mq-sched.h"
 #include "bfq-iosched.h"
+#include "blk-wbt.h"
 
 #define BFQ_BFQQ_FNS(name)						\
 void bfq_mark_bfqq_##name(struct bfq_queue *bfqq)			\
@@ -724,6 +725,44 @@ static void bfq_updated_next_req(struct bfq_data *bfqd,
 	}
 }
 
+static unsigned int bfq_wr_duration(struct bfq_data *bfqd)
+{
+	u64 dur;
+
+	if (bfqd->bfq_wr_max_time > 0)
+		return bfqd->bfq_wr_max_time;
+
+	dur = bfqd->RT_prod;
+	do_div(dur, bfqd->peak_rate);
+
+	/*
+	 * Limit duration between 3 and 13 seconds. Tests show that
+	 * higher values than 13 seconds often yield the opposite of
+	 * the desired result, i.e., worsen responsiveness by letting
+	 * non-interactive and non-soft-real-time applications
+	 * preserve weight raising for a too long time interval.
+	 *
+	 * On the other end, lower values than 3 seconds make it
+	 * difficult for most interactive tasks to complete their jobs
+	 * before weight-raising finishes.
+	 */
+	if (dur > msecs_to_jiffies(13000))
+		dur = msecs_to_jiffies(13000);
+	else if (dur < msecs_to_jiffies(3000))
+		dur = msecs_to_jiffies(3000);
+
+	return dur;
+}
+
+/* switch back from soft real-time to interactive weight raising */
+static void switch_back_to_interactive_wr(struct bfq_queue *bfqq,
+					  struct bfq_data *bfqd)
+{
+	bfqq->wr_coeff = bfqd->bfq_wr_coeff;
+	bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
+	bfqq->last_wr_start_finish = bfqq->wr_start_at_switch_to_srt;
+}
+
 static void
 bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_data *bfqd,
 		      struct bfq_io_cq *bic, bool bfq_already_existing)
@@ -750,10 +789,16 @@ bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_data *bfqd,
 	if (bfqq->wr_coeff > 1 && (bfq_bfqq_in_large_burst(bfqq) ||
 	    time_is_before_jiffies(bfqq->last_wr_start_finish +
 				   bfqq->wr_cur_max_time))) {
-		bfq_log_bfqq(bfqq->bfqd, bfqq,
-		    "resume state: switching off wr");
-
-		bfqq->wr_coeff = 1;
+		if (bfqq->wr_cur_max_time == bfqd->bfq_wr_rt_max_time &&
+		    !bfq_bfqq_in_large_burst(bfqq) &&
+		    time_is_after_eq_jiffies(bfqq->wr_start_at_switch_to_srt +
+					     bfq_wr_duration(bfqd))) {
+			switch_back_to_interactive_wr(bfqq, bfqd);
+		} else {
+			bfqq->wr_coeff = 1;
+			bfq_log_bfqq(bfqq->bfqd, bfqq,
+				     "resume state: switching off wr");
+		}
 	}
 
 	/* make sure weight will be updated, however we got here */
@@ -1173,33 +1218,22 @@ static bool bfq_bfqq_update_budg_for_activation(struct bfq_data *bfqd,
 	return wr_or_deserves_wr;
 }
 
-static unsigned int bfq_wr_duration(struct bfq_data *bfqd)
+/*
+ * Return the farthest future time instant according to jiffies
+ * macros.
+ */
+static unsigned long bfq_greatest_from_now(void)
 {
-	u64 dur;
-
-	if (bfqd->bfq_wr_max_time > 0)
-		return bfqd->bfq_wr_max_time;
-
-	dur = bfqd->RT_prod;
-	do_div(dur, bfqd->peak_rate);
-
-	/*
-	 * Limit duration between 3 and 13 seconds. Tests show that
-	 * higher values than 13 seconds often yield the opposite of
-	 * the desired result, i.e., worsen responsiveness by letting
-	 * non-interactive and non-soft-real-time applications
-	 * preserve weight raising for a too long time interval.
-	 *
-	 * On the other end, lower values than 3 seconds make it
-	 * difficult for most interactive tasks to complete their jobs
-	 * before weight-raising finishes.
-	 */
-	if (dur > msecs_to_jiffies(13000))
-		dur = msecs_to_jiffies(13000);
-	else if (dur < msecs_to_jiffies(3000))
-		dur = msecs_to_jiffies(3000);
+	return jiffies + MAX_JIFFY_OFFSET;
+}
 
-	return dur;
+/*
+ * Return the farthest past time instant according to jiffies
+ * macros.
+ */
+static unsigned long bfq_smallest_from_now(void)
+{
+	return jiffies - MAX_JIFFY_OFFSET;
 }
 
 static void bfq_update_bfqq_wr_on_rq_arrival(struct bfq_data *bfqd,
@@ -1216,7 +1250,19 @@ static void bfq_update_bfqq_wr_on_rq_arrival(struct bfq_data *bfqd,
 			bfqq->wr_coeff = bfqd->bfq_wr_coeff;
 			bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
 		} else {
-			bfqq->wr_start_at_switch_to_srt = jiffies;
+			/*
+			 * No interactive weight raising in progress
+			 * here: assign minus infinity to
+			 * wr_start_at_switch_to_srt, to make sure
+			 * that, at the end of the soft-real-time
+			 * weight raising periods that is starting
+			 * now, no interactive weight-raising period
+			 * may be wrongly considered as still in
+			 * progress (and thus actually started by
+			 * mistake).
+			 */
+			bfqq->wr_start_at_switch_to_srt =
+				bfq_smallest_from_now();
 			bfqq->wr_coeff = bfqd->bfq_wr_coeff *
 				BFQ_SOFTRT_WEIGHT_FACTOR;
 			bfqq->wr_cur_max_time =
@@ -2016,10 +2062,27 @@ static void bfq_bfqq_save_state(struct bfq_queue *bfqq)
 	bic->saved_IO_bound = bfq_bfqq_IO_bound(bfqq);
 	bic->saved_in_large_burst = bfq_bfqq_in_large_burst(bfqq);
 	bic->was_in_burst_list = !hlist_unhashed(&bfqq->burst_list_node);
-	bic->saved_wr_coeff = bfqq->wr_coeff;
-	bic->saved_wr_start_at_switch_to_srt = bfqq->wr_start_at_switch_to_srt;
-	bic->saved_last_wr_start_finish = bfqq->last_wr_start_finish;
-	bic->saved_wr_cur_max_time = bfqq->wr_cur_max_time;
+	if (unlikely(bfq_bfqq_just_created(bfqq) &&
+		     !bfq_bfqq_in_large_burst(bfqq))) {
+		/*
+		 * bfqq being merged right after being created: bfqq
+		 * would have deserved interactive weight raising, but
+		 * did not make it to be set in a weight-raised state,
+		 * because of this early merge.	Store directly the
+		 * weight-raising state that would have been assigned
+		 * to bfqq, so that to avoid that bfqq unjustly fails
+		 * to enjoy weight raising if split soon.
+		 */
+		bic->saved_wr_coeff = bfqq->bfqd->bfq_wr_coeff;
+		bic->saved_wr_cur_max_time = bfq_wr_duration(bfqq->bfqd);
+		bic->saved_last_wr_start_finish = jiffies;
+	} else {
+		bic->saved_wr_coeff = bfqq->wr_coeff;
+		bic->saved_wr_start_at_switch_to_srt =
+			bfqq->wr_start_at_switch_to_srt;
+		bic->saved_last_wr_start_finish = bfqq->last_wr_start_finish;
+		bic->saved_wr_cur_max_time = bfqq->wr_cur_max_time;
+	}
 }
 
 static void
@@ -2897,24 +2960,6 @@ static unsigned long bfq_bfqq_softrt_next_start(struct bfq_data *bfqd,
 		   jiffies + nsecs_to_jiffies(bfqq->bfqd->bfq_slice_idle) + 4);
 }
 
-/*
- * Return the farthest future time instant according to jiffies
- * macros.
- */
-static unsigned long bfq_greatest_from_now(void)
-{
-	return jiffies + MAX_JIFFY_OFFSET;
-}
-
-/*
- * Return the farthest past time instant according to jiffies
- * macros.
- */
-static unsigned long bfq_smallest_from_now(void)
-{
-	return jiffies - MAX_JIFFY_OFFSET;
-}
-
 /**
  * bfq_bfqq_expire - expire a queue.
  * @bfqd: device owning the queue.
@@ -3489,11 +3534,7 @@ static void bfq_update_wr_data(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 					       bfq_wr_duration(bfqd)))
 				bfq_bfqq_end_wr(bfqq);
 			else {
-				/* switch back to interactive wr */
-				bfqq->wr_coeff = bfqd->bfq_wr_coeff;
-				bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
-				bfqq->last_wr_start_finish =
-					bfqq->wr_start_at_switch_to_srt;
+				switch_back_to_interactive_wr(bfqq, bfqd);
 				bfqq->entity.prio_changed = 1;
 			}
 		}
@@ -3685,16 +3726,37 @@ void bfq_put_queue(struct bfq_queue *bfqq)
 	if (bfqq->ref)
 		return;
 
-	if (bfq_bfqq_sync(bfqq))
+	if (!hlist_unhashed(&bfqq->burst_list_node)) {
+		hlist_del_init(&bfqq->burst_list_node);
 		/*
-		 * The fact that this queue is being destroyed does not
-		 * invalidate the fact that this queue may have been
-		 * activated during the current burst. As a consequence,
-		 * although the queue does not exist anymore, and hence
-		 * needs to be removed from the burst list if there,
-		 * the burst size has not to be decremented.
+		 * Decrement also burst size after the removal, if the
+		 * process associated with bfqq is exiting, and thus
+		 * does not contribute to the burst any longer. This
+		 * decrement helps filter out false positives of large
+		 * bursts, when some short-lived process (often due to
+		 * the execution of commands by some service) happens
+		 * to start and exit while a complex application is
+		 * starting, and thus spawning several processes that
+		 * do I/O (and that *must not* be treated as a large
+		 * burst, see comments on bfq_handle_burst).
+		 *
+		 * In particular, the decrement is performed only if:
+		 * 1) bfqq is not a merged queue, because, if it is,
+		 * then this free of bfqq is not triggered by the exit
+		 * of the process bfqq is associated with, but exactly
+		 * by the fact that bfqq has just been merged.
+		 * 2) burst_size is greater than 0, to handle
+		 * unbalanced decrements. Unbalanced decrements may
+		 * happen in te following case: bfqq is inserted into
+		 * the current burst list--without incrementing
+		 * bust_size--because of a split, but the current
+		 * burst list is not the burst list bfqq belonged to
+		 * (see comments on the case of a split in
+		 * bfq_set_request).
 		 */
-		hlist_del_init(&bfqq->burst_list_node);
+		if (bfqq->bic && bfqq->bfqd->burst_size > 0)
+			bfqq->bfqd->burst_size--;
+	}
 
 	kmem_cache_free(bfq_pool, bfqq);
 #ifdef CONFIG_BFQ_GROUP_IOSCHED
@@ -4127,7 +4189,6 @@ static void __bfq_insert_request(struct bfq_data *bfqd, struct request *rq)
 		new_bfqq->allocated++;
 		bfqq->allocated--;
 		new_bfqq->ref++;
-		bfq_clear_bfqq_just_created(bfqq);
 		/*
 		 * If the bic associated with the process
 		 * issuing this request still points to bfqq
@@ -4139,6 +4200,8 @@ static void __bfq_insert_request(struct bfq_data *bfqd, struct request *rq)
 		if (bic_to_bfqq(RQ_BIC(rq), 1) == bfqq)
 			bfq_merge_bfqqs(bfqd, RQ_BIC(rq),
 					bfqq, new_bfqq);
+
+		bfq_clear_bfqq_just_created(bfqq);
 		/*
 		 * rq is about to be enqueued into new_bfqq,
 		 * release rq reference on bfqq
@@ -4424,6 +4487,34 @@ static struct bfq_queue *bfq_get_bfqq_handle_split(struct bfq_data *bfqd,
 		else {
 			bfq_clear_bfqq_in_large_burst(bfqq);
 			if (bic->was_in_burst_list)
+				/*
+				 * If bfqq was in the current
+				 * burst list before being
+				 * merged, then we have to add
+				 * it back. And we do not need
+				 * to increase burst_size, as
+				 * we did not decrement
+				 * burst_size when we removed
+				 * bfqq from the burst list as
+				 * a consequence of a merge
+				 * (see comments in
+				 * bfq_put_queue). In this
+				 * respect, it would be rather
+				 * costly to know whether the
+				 * current burst list is still
+				 * the same burst list from
+				 * which bfqq was removed on
+				 * the merge. To avoid this
+				 * cost, if bfqq was in a
+				 * burst list, then we add
+				 * bfqq to the current burst
+				 * list without any further
+				 * check. This can cause
+				 * inappropriate insertions,
+				 * but rarely enough to not
+				 * harm the detection of large
+				 * bursts significantly.
+				 */
 				hlist_add_head(&bfqq->burst_list_node,
 					       &bfqd->burst_list);
 		}
@@ -4775,7 +4866,7 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
 	bfq_init_root_group(bfqd->root_group, bfqd);
 	bfq_init_entity(&bfqd->oom_bfqq.entity, bfqd->root_group);
 
-
+	wbt_disable_default(q);
 	return 0;
 
 out_free:
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index 5df32907ff3b..23b42e8aa03e 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -485,11 +485,8 @@ EXPORT_SYMBOL(bioset_integrity_create);
 
 void bioset_integrity_free(struct bio_set *bs)
 {
-	if (bs->bio_integrity_pool)
-		mempool_destroy(bs->bio_integrity_pool);
-
-	if (bs->bvec_integrity_pool)
-		mempool_destroy(bs->bvec_integrity_pool);
+	mempool_destroy(bs->bio_integrity_pool);
+	mempool_destroy(bs->bvec_integrity_pool);
 }
 EXPORT_SYMBOL(bioset_integrity_free);
 
diff --git a/block/bio.c b/block/bio.c
index cc60213e56d8..b94a802f8ba3 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -400,7 +400,7 @@ static void punt_bios_to_rescuer(struct bio_set *bs)
 
 /**
  * bio_alloc_bioset - allocate a bio for I/O
- * @gfp_mask:   the GFP_ mask given to the slab allocator
+ * @gfp_mask:   the GFP_* mask given to the slab allocator
  * @nr_iovecs:	number of iovecs to pre-allocate
  * @bs:		the bio_set to allocate from.
  *
@@ -1931,11 +1931,8 @@ void bioset_free(struct bio_set *bs)
 	if (bs->rescue_workqueue)
 		destroy_workqueue(bs->rescue_workqueue);
 
-	if (bs->bio_pool)
-		mempool_destroy(bs->bio_pool);
-
-	if (bs->bvec_pool)
-		mempool_destroy(bs->bvec_pool);
+	mempool_destroy(bs->bio_pool);
+	mempool_destroy(bs->bvec_pool);
 
 	bioset_integrity_free(bs);
 	bio_put_slab(bs);
@@ -2036,37 +2033,6 @@ int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css)
 EXPORT_SYMBOL_GPL(bio_associate_blkcg);
 
 /**
- * bio_associate_current - associate a bio with %current
- * @bio: target bio
- *
- * Associate @bio with %current if it hasn't been associated yet.  Block
- * layer will treat @bio as if it were issued by %current no matter which
- * task actually issues it.
- *
- * This function takes an extra reference of @task's io_context and blkcg
- * which will be put when @bio is released.  The caller must own @bio,
- * ensure %current->io_context exists, and is responsible for synchronizing
- * calls to this function.
- */
-int bio_associate_current(struct bio *bio)
-{
-	struct io_context *ioc;
-
-	if (bio->bi_css)
-		return -EBUSY;
-
-	ioc = current->io_context;
-	if (!ioc)
-		return -ENOENT;
-
-	get_io_context_active(ioc);
-	bio->bi_ioc = ioc;
-	bio->bi_css = task_get_css(current, io_cgrp_id);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(bio_associate_current);
-
-/**
  * bio_disassociate_task - undo bio_associate_current()
  * @bio: target bio
  */
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index d3f56baee936..4117524ca45b 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -1419,6 +1419,11 @@ int blkcg_policy_register(struct blkcg_policy *pol)
 	if (i >= BLKCG_MAX_POLS)
 		goto err_unlock;
 
+	/* Make sure cpd/pd_alloc_fn and cpd/pd_free_fn in pairs */
+	if ((!pol->cpd_alloc_fn ^ !pol->cpd_free_fn) ||
+		(!pol->pd_alloc_fn ^ !pol->pd_free_fn))
+		goto err_unlock;
+
 	/* register @pol */
 	pol->plid = i;
 	blkcg_policy[pol->plid] = pol;
@@ -1452,7 +1457,7 @@ int blkcg_policy_register(struct blkcg_policy *pol)
 	return 0;
 
 err_free_cpds:
-	if (pol->cpd_alloc_fn) {
+	if (pol->cpd_free_fn) {
 		list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) {
 			if (blkcg->cpd[pol->plid]) {
 				pol->cpd_free_fn(blkcg->cpd[pol->plid]);
@@ -1492,7 +1497,7 @@ void blkcg_policy_unregister(struct blkcg_policy *pol)
 	/* remove cpds and unregister */
 	mutex_lock(&blkcg_pol_mutex);
 
-	if (pol->cpd_alloc_fn) {
+	if (pol->cpd_free_fn) {
 		list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) {
 			if (blkcg->cpd[pol->plid]) {
 				pol->cpd_free_fn(blkcg->cpd[pol->plid]);
diff --git a/block/blk-core.c b/block/blk-core.c
index 048be4aa6024..7c54c195e79e 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -333,11 +333,13 @@ EXPORT_SYMBOL(blk_stop_queue);
 void blk_sync_queue(struct request_queue *q)
 {
 	del_timer_sync(&q->timeout);
+	cancel_work_sync(&q->timeout_work);
 
 	if (q->mq_ops) {
 		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 {
@@ -347,6 +349,37 @@ void blk_sync_queue(struct request_queue *q)
 EXPORT_SYMBOL(blk_sync_queue);
 
 /**
+ * blk_set_preempt_only - set QUEUE_FLAG_PREEMPT_ONLY
+ * @q: request queue pointer
+ *
+ * Returns the previous value of the PREEMPT_ONLY flag - 0 if the flag was not
+ * set and 1 if the flag was already set.
+ */
+int blk_set_preempt_only(struct request_queue *q)
+{
+	unsigned long flags;
+	int res;
+
+	spin_lock_irqsave(q->queue_lock, flags);
+	res = queue_flag_test_and_set(QUEUE_FLAG_PREEMPT_ONLY, q);
+	spin_unlock_irqrestore(q->queue_lock, flags);
+
+	return res;
+}
+EXPORT_SYMBOL_GPL(blk_set_preempt_only);
+
+void blk_clear_preempt_only(struct request_queue *q)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(q->queue_lock, flags);
+	queue_flag_clear(QUEUE_FLAG_PREEMPT_ONLY, q);
+	wake_up_all(&q->mq_freeze_wq);
+	spin_unlock_irqrestore(q->queue_lock, flags);
+}
+EXPORT_SYMBOL_GPL(blk_clear_preempt_only);
+
+/**
  * __blk_run_queue_uncond - run a queue whether or not it has been stopped
  * @q:	The queue to run
  *
@@ -610,6 +643,9 @@ void blk_set_queue_dying(struct request_queue *q)
 		}
 		spin_unlock_irq(q->queue_lock);
 	}
+
+	/* Make blk_queue_enter() reexamine the DYING flag. */
+	wake_up_all(&q->mq_freeze_wq);
 }
 EXPORT_SYMBOL_GPL(blk_set_queue_dying);
 
@@ -718,7 +754,7 @@ static void free_request_size(void *element, void *data)
 int blk_init_rl(struct request_list *rl, struct request_queue *q,
 		gfp_t gfp_mask)
 {
-	if (unlikely(rl->rq_pool))
+	if (unlikely(rl->rq_pool) || q->mq_ops)
 		return 0;
 
 	rl->q = q;
@@ -760,15 +796,38 @@ struct request_queue *blk_alloc_queue(gfp_t gfp_mask)
 }
 EXPORT_SYMBOL(blk_alloc_queue);
 
-int blk_queue_enter(struct request_queue *q, bool nowait)
+/**
+ * blk_queue_enter() - try to increase q->q_usage_counter
+ * @q: request queue pointer
+ * @flags: BLK_MQ_REQ_NOWAIT and/or BLK_MQ_REQ_PREEMPT
+ */
+int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags)
 {
+	const bool preempt = flags & BLK_MQ_REQ_PREEMPT;
+
 	while (true) {
+		bool success = false;
 		int ret;
 
-		if (percpu_ref_tryget_live(&q->q_usage_counter))
+		rcu_read_lock_sched();
+		if (percpu_ref_tryget_live(&q->q_usage_counter)) {
+			/*
+			 * The code that sets the PREEMPT_ONLY flag is
+			 * responsible for ensuring that that flag is globally
+			 * visible before the queue is unfrozen.
+			 */
+			if (preempt || !blk_queue_preempt_only(q)) {
+				success = true;
+			} else {
+				percpu_ref_put(&q->q_usage_counter);
+			}
+		}
+		rcu_read_unlock_sched();
+
+		if (success)
 			return 0;
 
-		if (nowait)
+		if (flags & BLK_MQ_REQ_NOWAIT)
 			return -EBUSY;
 
 		/*
@@ -781,7 +840,8 @@ int blk_queue_enter(struct request_queue *q, bool nowait)
 		smp_rmb();
 
 		ret = wait_event_interruptible(q->mq_freeze_wq,
-				!atomic_read(&q->mq_freeze_depth) ||
+				(atomic_read(&q->mq_freeze_depth) == 0 &&
+				 (preempt || !blk_queue_preempt_only(q))) ||
 				blk_queue_dying(q));
 		if (blk_queue_dying(q))
 			return -ENODEV;
@@ -844,6 +904,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_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_WORK(&q->timeout_work, NULL);
 	INIT_LIST_HEAD(&q->queue_head);
 	INIT_LIST_HEAD(&q->timeout_list);
 	INIT_LIST_HEAD(&q->icq_list);
@@ -1154,7 +1215,7 @@ int blk_update_nr_requests(struct request_queue *q, unsigned int nr)
  * @rl: request list to allocate from
  * @op: operation and flags
  * @bio: bio to allocate request for (can be %NULL)
- * @gfp_mask: allocation mask
+ * @flags: BLQ_MQ_REQ_* flags
  *
  * Get a free request from @q.  This function may fail under memory
  * pressure or if @q is dead.
@@ -1164,7 +1225,7 @@ int blk_update_nr_requests(struct request_queue *q, unsigned int nr)
  * 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, gfp_t gfp_mask)
+				     struct bio *bio, blk_mq_req_flags_t flags)
 {
 	struct request_queue *q = rl->q;
 	struct request *rq;
@@ -1173,6 +1234,8 @@ static struct request *__get_request(struct request_list *rl, unsigned int op,
 	struct io_cq *icq = NULL;
 	const bool is_sync = op_is_sync(op);
 	int may_queue;
+	gfp_t gfp_mask = flags & BLK_MQ_REQ_NOWAIT ? GFP_ATOMIC :
+			 __GFP_DIRECT_RECLAIM;
 	req_flags_t rq_flags = RQF_ALLOCED;
 
 	lockdep_assert_held(q->queue_lock);
@@ -1255,6 +1318,8 @@ static struct request *__get_request(struct request_list *rl, unsigned int op,
 	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) {
@@ -1333,7 +1398,7 @@ rq_starved:
  * @q: request_queue to allocate request from
  * @op: operation and flags
  * @bio: bio to allocate request for (can be %NULL)
- * @gfp_mask: allocation mask
+ * @flags: BLK_MQ_REQ_* flags.
  *
  * Get a free request from @q.  If %__GFP_DIRECT_RECLAIM is set in @gfp_mask,
  * this function keeps retrying under memory pressure and fails iff @q is dead.
@@ -1343,7 +1408,7 @@ rq_starved:
  * 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, gfp_t gfp_mask)
+				   struct bio *bio, blk_mq_req_flags_t flags)
 {
 	const bool is_sync = op_is_sync(op);
 	DEFINE_WAIT(wait);
@@ -1355,7 +1420,7 @@ static struct request *get_request(struct request_queue *q, unsigned int op,
 
 	rl = blk_get_rl(q, bio);	/* transferred to @rq on success */
 retry:
-	rq = __get_request(rl, op, bio, gfp_mask);
+	rq = __get_request(rl, op, bio, flags);
 	if (!IS_ERR(rq))
 		return rq;
 
@@ -1364,7 +1429,7 @@ retry:
 		return ERR_PTR(-EAGAIN);
 	}
 
-	if (!gfpflags_allow_blocking(gfp_mask) || unlikely(blk_queue_dying(q))) {
+	if ((flags & BLK_MQ_REQ_NOWAIT) || unlikely(blk_queue_dying(q))) {
 		blk_put_rl(rl);
 		return rq;
 	}
@@ -1391,20 +1456,28 @@ retry:
 	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, gfp_t gfp_mask)
+				unsigned int op, blk_mq_req_flags_t flags)
 {
 	struct request *rq;
+	gfp_t gfp_mask = flags & BLK_MQ_REQ_NOWAIT ? GFP_ATOMIC :
+			 __GFP_DIRECT_RECLAIM;
+	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, gfp_mask);
+	rq = get_request(q, op, NULL, flags);
 	if (IS_ERR(rq)) {
 		spin_unlock_irq(q->queue_lock);
+		blk_queue_exit(q);
 		return rq;
 	}
 
@@ -1415,25 +1488,40 @@ static struct request *blk_old_get_request(struct request_queue *q,
 	return rq;
 }
 
-struct request *blk_get_request(struct request_queue *q, unsigned int op,
-				gfp_t gfp_mask)
+/**
+ * blk_get_request_flags - allocate a request
+ * @q: request queue to allocate a request for
+ * @op: operation (REQ_OP_*) and REQ_* flags, e.g. REQ_SYNC.
+ * @flags: BLK_MQ_REQ_* flags, e.g. BLK_MQ_REQ_NOWAIT.
+ */
+struct request *blk_get_request_flags(struct request_queue *q, unsigned int op,
+				      blk_mq_req_flags_t flags)
 {
 	struct request *req;
 
+	WARN_ON_ONCE(op & REQ_NOWAIT);
+	WARN_ON_ONCE(flags & ~(BLK_MQ_REQ_NOWAIT | BLK_MQ_REQ_PREEMPT));
+
 	if (q->mq_ops) {
-		req = blk_mq_alloc_request(q, op,
-			(gfp_mask & __GFP_DIRECT_RECLAIM) ?
-				0 : BLK_MQ_REQ_NOWAIT);
+		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, gfp_mask);
+		req = blk_old_get_request(q, op, flags);
 		if (!IS_ERR(req) && q->initialize_rq_fn)
 			q->initialize_rq_fn(req);
 	}
 
 	return req;
 }
+EXPORT_SYMBOL(blk_get_request_flags);
+
+struct request *blk_get_request(struct request_queue *q, unsigned int op,
+				gfp_t gfp_mask)
+{
+	return blk_get_request_flags(q, op, gfp_mask & __GFP_DIRECT_RECLAIM ?
+				     0 : BLK_MQ_REQ_NOWAIT);
+}
 EXPORT_SYMBOL(blk_get_request);
 
 /**
@@ -1576,6 +1664,7 @@ void __blk_put_request(struct request_queue *q, struct request *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);
@@ -1857,8 +1946,10 @@ get_rq:
 	 * Grab a free request. This is might sleep but can not fail.
 	 * Returns with the queue unlocked.
 	 */
-	req = get_request(q, bio->bi_opf, bio, GFP_NOIO);
+	blk_queue_enter_live(q);
+	req = get_request(q, bio->bi_opf, bio, 0);
 	if (IS_ERR(req)) {
+		blk_queue_exit(q);
 		__wbt_done(q->rq_wb, wb_acct);
 		if (PTR_ERR(req) == -ENOMEM)
 			bio->bi_status = BLK_STS_RESOURCE;
@@ -2200,8 +2291,10 @@ blk_qc_t generic_make_request(struct bio *bio)
 	current->bio_list = bio_list_on_stack;
 	do {
 		struct request_queue *q = bio->bi_disk->queue;
+		blk_mq_req_flags_t flags = bio->bi_opf & REQ_NOWAIT ?
+			BLK_MQ_REQ_NOWAIT : 0;
 
-		if (likely(blk_queue_enter(q, bio->bi_opf & REQ_NOWAIT) == 0)) {
+		if (likely(blk_queue_enter(q, flags) == 0)) {
 			struct bio_list lower, same;
 
 			/* Create a fresh bio_list for all subordinate requests */
@@ -2242,6 +2335,40 @@ out:
 EXPORT_SYMBOL(generic_make_request);
 
 /**
+ * direct_make_request - hand a buffer directly to its device driver for I/O
+ * @bio:  The bio describing the location in memory and on the device.
+ *
+ * This function behaves like generic_make_request(), but does not protect
+ * against recursion.  Must only be used if the called driver is known
+ * to not call generic_make_request (or direct_make_request) again from
+ * its make_request function.  (Calling direct_make_request again from
+ * a workqueue is perfectly fine as that doesn't recurse).
+ */
+blk_qc_t direct_make_request(struct bio *bio)
+{
+	struct request_queue *q = bio->bi_disk->queue;
+	bool nowait = bio->bi_opf & REQ_NOWAIT;
+	blk_qc_t ret;
+
+	if (!generic_make_request_checks(bio))
+		return BLK_QC_T_NONE;
+
+	if (unlikely(blk_queue_enter(q, nowait ? BLK_MQ_REQ_NOWAIT : 0))) {
+		if (nowait && !blk_queue_dying(q))
+			bio->bi_status = BLK_STS_AGAIN;
+		else
+			bio->bi_status = BLK_STS_IOERR;
+		bio_endio(bio);