Merge tag 'for-linus-20190524' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:

 - NVMe pull request from Keith, with fixes from a few folks.

 - bio and sbitmap before atomic barrier fixes (Andrea)

 - Hang fix for blk-mq freeze and unfreeze (Bob)

 - Single segment count regression fix (Christoph)

 - AoE now has a new maintainer

 - tools/io_uring/ Makefile fix, and sync with liburing (me)

* tag 'for-linus-20190524' of git://git.kernel.dk/linux-block: (23 commits)
  tools/io_uring: sync with liburing
  tools/io_uring: fix Makefile for pthread library link
  blk-mq: fix hang caused by freeze/unfreeze sequence
  block: remove the bi_seg_{front,back}_size fields in struct bio
  block: remove the segment size check in bio_will_gap
  block: force an unlimited segment size on queues with a virt boundary
  block: don't decrement nr_phys_segments for physically contigous segments
  sbitmap: fix improper use of smp_mb__before_atomic()
  bio: fix improper use of smp_mb__before_atomic()
  aoe: list new maintainer for aoe driver
  nvme-pci: use blk-mq mapping for unmanaged irqs
  nvme: update MAINTAINERS
  nvme: copy MTFA field from identify controller
  nvme: fix memory leak for power latency tolerance
  nvme: release namespace SRCU protection before performing controller ioctls
  nvme: merge nvme_ns_ioctl into nvme_ioctl
  nvme: remove the ifdef around nvme_nvm_ioctl
  nvme: fix srcu locking on error return in nvme_get_ns_from_disk
  nvme: Fix known effects
  nvme-pci: Sync queues on reset
  ...

Author: torvalds

MAINTAINERS

@@ -2627,7 +2627,7 @@ F:	Documentation/devicetree/bindings/eeprom/at24.txt
 F:	drivers/misc/eeprom/at24.c
 
 ATA OVER ETHERNET (AOE) DRIVER
-M:	"Ed L. Cashin" <[email protected]>
+M:	"Justin Sanders" <[email protected]>
 W:	http://www.openaoe.org/
 S:	Supported
 F:	Documentation/aoe/
@@ -11226,7 +11226,7 @@ F:	drivers/video/fbdev/riva/
 F:	drivers/video/fbdev/nvidia/
 
 NVM EXPRESS DRIVER
-M:	Keith Busch <[email protected]>
+M:	Keith Busch <[email protected]>
 M:	Jens Axboe <[email protected]>
 M:	Christoph Hellwig <[email protected]>
 M:	Sagi Grimberg <[email protected]>

block/blk-core.c

@@ -413,7 +413,7 @@ int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags)
 		smp_rmb();
 
 		wait_event(q->mq_freeze_wq,
-			   (atomic_read(&q->mq_freeze_depth) == 0 &&
+			   (!q->mq_freeze_depth &&
 			    (pm || (blk_pm_request_resume(q),
 				    !blk_queue_pm_only(q)))) ||
 			   blk_queue_dying(q));
@@ -503,6 +503,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 	spin_lock_init(&q->queue_lock);
 
 	init_waitqueue_head(&q->mq_freeze_wq);
+	mutex_init(&q->mq_freeze_lock);
 
 	/*
 	 * Init percpu_ref in atomic mode so that it's faster to shutdown.

block/blk-merge.c

@@ -12,23 +12,6 @@
 
 #include "blk.h"
 
-/*
- * Check if the two bvecs from two bios can be merged to one segment.  If yes,
- * no need to check gap between the two bios since the 1st bio and the 1st bvec
- * in the 2nd bio can be handled in one segment.
- */
-static inline bool bios_segs_mergeable(struct request_queue *q,
-		struct bio *prev, struct bio_vec *prev_last_bv,
-		struct bio_vec *next_first_bv)
-{
-	if (!biovec_phys_mergeable(q, prev_last_bv, next_first_bv))
-		return false;
-	if (prev->bi_seg_back_size + next_first_bv->bv_len >
-			queue_max_segment_size(q))
-		return false;
-	return true;
-}
-
 static inline bool bio_will_gap(struct request_queue *q,
 		struct request *prev_rq, struct bio *prev, struct bio *next)
 {
@@ -60,7 +43,7 @@ static inline bool bio_will_gap(struct request_queue *q,
 	 */
 	bio_get_last_bvec(prev, &pb);
 	bio_get_first_bvec(next, &nb);
-	if (bios_segs_mergeable(q, prev, &pb, &nb))
+	if (biovec_phys_mergeable(q, &pb, &nb))
 		return false;
 	return __bvec_gap_to_prev(q, &pb, nb.bv_offset);
 }
@@ -179,8 +162,7 @@ static unsigned get_max_segment_size(struct request_queue *q,
  * variables.
  */
 static bool bvec_split_segs(struct request_queue *q, struct bio_vec *bv,
-		unsigned *nsegs, unsigned *last_seg_size,
-		unsigned *front_seg_size, unsigned *sectors, unsigned max_segs)
+		unsigned *nsegs, unsigned *sectors, unsigned max_segs)
 {
 	unsigned len = bv->bv_len;
 	unsigned total_len = 0;
@@ -202,28 +184,12 @@ static bool bvec_split_segs(struct request_queue *q, struct bio_vec *bv,
 			break;
 	}
 
-	if (!new_nsegs)
-		return !!len;
-
-	/* update front segment size */
-	if (!*nsegs) {
-		unsigned first_seg_size;
-
-		if (new_nsegs == 1)
-			first_seg_size = get_max_segment_size(q, bv->bv_offset);
-		else
-			first_seg_size = queue_max_segment_size(q);
-
-		if (*front_seg_size < first_seg_size)
-			*front_seg_size = first_seg_size;
+	if (new_nsegs) {
+		*nsegs += new_nsegs;
+		if (sectors)
+			*sectors += total_len >> 9;
 	}
 
-	/* update other varibles */
-	*last_seg_size = seg_size;
-	*nsegs += new_nsegs;
-	if (sectors)
-		*sectors += total_len >> 9;
-
 	/* split in the middle of the bvec if len != 0 */
 	return !!len;
 }
@@ -235,8 +201,7 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 {
 	struct bio_vec bv, bvprv, *bvprvp = NULL;
 	struct bvec_iter iter;
-	unsigned seg_size = 0, nsegs = 0, sectors = 0;
-	unsigned front_seg_size = bio->bi_seg_front_size;
+	unsigned nsegs = 0, sectors = 0;
 	bool do_split = true;
 	struct bio *new = NULL;
 	const unsigned max_sectors = get_max_io_size(q, bio);
@@ -260,8 +225,6 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 				/* split in the middle of bvec */
 				bv.bv_len = (max_sectors - sectors) << 9;
 				bvec_split_segs(q, &bv, &nsegs,
-						&seg_size,
-						&front_seg_size,
 						&sectors, max_segs);
 			}
 			goto split;
@@ -275,12 +238,9 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 
 		if (bv.bv_offset + bv.bv_len <= PAGE_SIZE) {
 			nsegs++;
-			seg_size = bv.bv_len;
 			sectors += bv.bv_len >> 9;
-			if (nsegs == 1 && seg_size > front_seg_size)
-				front_seg_size = seg_size;
-		} else if (bvec_split_segs(q, &bv, &nsegs, &seg_size,
-				    &front_seg_size, &sectors, max_segs)) {
+		} else if (bvec_split_segs(q, &bv, &nsegs, &sectors,
+				max_segs)) {
 			goto split;
 		}
 	}
@@ -295,10 +255,6 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 			bio = new;
 	}
 
-	bio->bi_seg_front_size = front_seg_size;
-	if (seg_size > bio->bi_seg_back_size)
-		bio->bi_seg_back_size = seg_size;
-
 	return do_split ? new : NULL;
 }
 
@@ -353,18 +309,13 @@ EXPORT_SYMBOL(blk_queue_split);
 static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 					     struct bio *bio)
 {
-	struct bio_vec uninitialized_var(bv), bvprv = { NULL };
-	unsigned int seg_size, nr_phys_segs;
-	unsigned front_seg_size;
-	struct bio *fbio, *bbio;
+	unsigned int nr_phys_segs = 0;
 	struct bvec_iter iter;
-	bool new_bio = false;
+	struct bio_vec bv;
 
 	if (!bio)
 		return 0;
 
-	front_seg_size = bio->bi_seg_front_size;
-
 	switch (bio_op(bio)) {
 	case REQ_OP_DISCARD:
 	case REQ_OP_SECURE_ERASE:
@@ -374,42 +325,11 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 		return 1;
 	}
 
-	fbio = bio;
-	seg_size = 0;
-	nr_phys_segs = 0;
 	for_each_bio(bio) {
-		bio_for_each_bvec(bv, bio, iter) {
-			if (new_bio) {
-				if (seg_size + bv.bv_len
-				    > queue_max_segment_size(q))
-					goto new_segment;
-				if (!biovec_phys_mergeable(q, &bvprv, &bv))
-					goto new_segment;
-
-				seg_size += bv.bv_len;
-
-				if (nr_phys_segs == 1 && seg_size >
-						front_seg_size)
-					front_seg_size = seg_size;
-
-				continue;
-			}
-new_segment:
-			bvec_split_segs(q, &bv, &nr_phys_segs, &seg_size,
-					&front_seg_size, NULL, UINT_MAX);
-			new_bio = false;
-		}
-		bbio = bio;
-		if (likely(bio->bi_iter.bi_size)) {
-			bvprv = bv;
-			new_bio = true;
-		}
+		bio_for_each_bvec(bv, bio, iter)
+			bvec_split_segs(q, &bv, &nr_phys_segs, NULL, UINT_MAX);
 	}
 
-	fbio->bi_seg_front_size = front_seg_size;
-	if (seg_size > bbio->bi_seg_back_size)
-		bbio->bi_seg_back_size = seg_size;
-
 	return nr_phys_segs;
 }
 
@@ -429,24 +349,6 @@ void blk_recount_segments(struct request_queue *q, struct bio *bio)
 	bio_set_flag(bio, BIO_SEG_VALID);
 }
 
-static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio,
-				   struct bio *nxt)
-{
-	struct bio_vec end_bv = { NULL }, nxt_bv;
-
-	if (bio->bi_seg_back_size + nxt->bi_seg_front_size >
-	    queue_max_segment_size(q))
-		return 0;
-
-	if (!bio_has_data(bio))
-		return 1;
-
-	bio_get_last_bvec(bio, &end_bv);
-	bio_get_first_bvec(nxt, &nxt_bv);
-
-	return biovec_phys_mergeable(q, &end_bv, &nxt_bv);
-}
-
 static inline struct scatterlist *blk_next_sg(struct scatterlist **sg,
 		struct scatterlist *sglist)
 {
@@ -706,8 +608,6 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
 				struct request *next)
 {
 	int total_phys_segments;
-	unsigned int seg_size =
-		req->biotail->bi_seg_back_size + next->bio->bi_seg_front_size;
 
 	if (req_gap_back_merge(req, next->bio))
 		return 0;
@@ -720,14 +620,6 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
 		return 0;
 
 	total_phys_segments = req->nr_phys_segments + next->nr_phys_segments;
-	if (blk_phys_contig_segment(q, req->biotail, next->bio)) {
-		if (req->nr_phys_segments == 1)
-			req->bio->bi_seg_front_size = seg_size;
-		if (next->nr_phys_segments == 1)
-			next->biotail->bi_seg_back_size = seg_size;
-		total_phys_segments--;
-	}
-
 	if (total_phys_segments > queue_max_segments(q))
 		return 0;
 

block/blk-mq.c

@@ -144,13 +144,14 @@ void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part,
 
 void blk_freeze_queue_start(struct request_queue *q)
 {
-	int freeze_depth;
-
-	freeze_depth = atomic_inc_return(&q->mq_freeze_depth);
-	if (freeze_depth == 1) {
+	mutex_lock(&q->mq_freeze_lock);
+	if (++q->mq_freeze_depth == 1) {
 		percpu_ref_kill(&q->q_usage_counter);
+		mutex_unlock(&q->mq_freeze_lock);
 		if (queue_is_mq(q))
 			blk_mq_run_hw_queues(q, false);
+	} else {
+		mutex_unlock(&q->mq_freeze_lock);
 	}
 }
 EXPORT_SYMBOL_GPL(blk_freeze_queue_start);
@@ -199,14 +200,14 @@ EXPORT_SYMBOL_GPL(blk_mq_freeze_queue);
 
 void blk_mq_unfreeze_queue(struct request_queue *q)
 {
-	int freeze_depth;
-
-	freeze_depth = atomic_dec_return(&q->mq_freeze_depth);
-	WARN_ON_ONCE(freeze_depth < 0);
-	if (!freeze_depth) {
+	mutex_lock(&q->mq_freeze_lock);
+	q->mq_freeze_depth--;
+	WARN_ON_ONCE(q->mq_freeze_depth < 0);
+	if (!q->mq_freeze_depth) {
 		percpu_ref_resurrect(&q->q_usage_counter);
 		wake_up_all(&q->mq_freeze_wq);
 	}
+	mutex_unlock(&q->mq_freeze_lock);
 }
 EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue);
 

block/blk-settings.c

@@ -310,6 +310,9 @@ void blk_queue_max_segment_size(struct request_queue *q, unsigned int max_size)
 		       __func__, max_size);
 	}
 
+	/* see blk_queue_virt_boundary() for the explanation */
+	WARN_ON_ONCE(q->limits.virt_boundary_mask);
+
 	q->limits.max_segment_size = max_size;
 }
 EXPORT_SYMBOL(blk_queue_max_segment_size);
@@ -742,6 +745,14 @@ EXPORT_SYMBOL(blk_queue_segment_boundary);
 void blk_queue_virt_boundary(struct request_queue *q, unsigned long mask)
 {
 	q->limits.virt_boundary_mask = mask;
+
+	/*
+	 * Devices that require a virtual boundary do not support scatter/gather
+	 * I/O natively, but instead require a descriptor list entry for each
+	 * page (which might not be idential to the Linux PAGE_SIZE).  Because
+	 * of that they are not limited by our notion of "segment size".
+	 */
+	q->limits.max_segment_size = UINT_MAX;
 }
 EXPORT_SYMBOL(blk_queue_virt_boundary);