Merge branch 'for-4.4/core' of git://git.kernel.dk/linux-block

Pull core block updates from Jens Axboe:
 "This is the core block pull request for 4.4.  I've got a few more
  topic branches this time around, some of them will layer on top of the
  core+drivers changes and will come in a separate round.  So not a huge
  chunk of changes in this round.

  This pull request contains:

   - Enable blk-mq page allocation tracking with kmemleak, from Catalin.

   - Unused prototype removal in blk-mq from Christoph.

   - Cleanup of the q->blk_trace exchange, using cmpxchg instead of two
     xchg()'s, from Davidlohr.

   - A plug flush fix from Jeff.

   - Also from Jeff, a fix that means we don't have to update shared tag
     sets at init time unless we do a state change.  This cuts down boot
     times on thousands of devices a lot with scsi/blk-mq.

   - blk-mq waitqueue barrier fix from Kosuke.

   - Various fixes from Ming:

        - Fixes for segment merging and splitting, and checks, for
          the old core and blk-mq.

        - Potential blk-mq speedup by marking ctx pending at the end
          of a plug insertion batch in blk-mq.

        - direct-io no page dirty on kernel direct reads.

   - A WRITE_SYNC fix for mpage from Roman"

* 'for-4.4/core' of git://git.kernel.dk/linux-block:
  blk-mq: avoid excessive boot delays with large lun counts
  blktrace: re-write setting q->blk_trace
  blk-mq: mark ctx as pending at batch in flush plug path
  blk-mq: fix for trace_block_plug()
  block: check bio_mergeable() early before merging
  blk-mq: check bio_mergeable() early before merging
  block: avoid to merge splitted bio
  block: setup bi_phys_segments after splitting
  block: fix plug list flushing for nomerge queues
  blk-mq: remove unused blk_mq_clone_flush_request prototype
  blk-mq: fix waitqueue_active without memory barrier in block/blk-mq-tag.c
  fs: direct-io: don't dirtying pages for ITER_BVEC/ITER_KVEC direct read
  fs/mpage.c: forgotten WRITE_SYNC in case of data integrity write
  block: kmemleak: Track the page allocations for struct request

block/blk-core.c

@@ -1594,6 +1594,30 @@ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
 	return ret;
 }
 
+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 init_request_from_bio(struct request *req, struct bio *bio)
 {
 	req->cmd_type = REQ_TYPE_FS;
@@ -1641,9 +1665,11 @@ static void blk_queue_bio(struct request_queue *q, struct bio *bio)
 	 * Check if we can merge with the plugged list before grabbing
 	 * any locks.
 	 */
-	if (!blk_queue_nomerges(q) &&
-	    blk_attempt_plug_merge(q, bio, &request_count, NULL))
-		return;
+	if (!blk_queue_nomerges(q)) {
+		if (blk_attempt_plug_merge(q, bio, &request_count, NULL))
+			return;
+	} else
+		request_count = blk_plug_queued_count(q);
 
 	spin_lock_irq(q->queue_lock);
 

block/blk-merge.c

@@ -11,13 +11,16 @@
 
 static struct bio *blk_bio_discard_split(struct request_queue *q,
 					 struct bio *bio,
-					 struct bio_set *bs)
+					 struct bio_set *bs,
+					 unsigned *nsegs)
 {
 	unsigned int max_discard_sectors, granularity;
 	int alignment;
 	sector_t tmp;
 	unsigned split_sectors;
 
+	*nsegs = 1;
+
 	/* Zero-sector (unknown) and one-sector granularities are the same.  */
 	granularity = max(q->limits.discard_granularity >> 9, 1U);
 
@@ -51,8 +54,11 @@ static struct bio *blk_bio_discard_split(struct request_queue *q,
 
 static struct bio *blk_bio_write_same_split(struct request_queue *q,
 					    struct bio *bio,
-					    struct bio_set *bs)
+					    struct bio_set *bs,
+					    unsigned *nsegs)
 {
+	*nsegs = 1;
+
 	if (!q->limits.max_write_same_sectors)
 		return NULL;
 
@@ -64,7 +70,8 @@ static struct bio *blk_bio_write_same_split(struct request_queue *q,
 
 static struct bio *blk_bio_segment_split(struct request_queue *q,
 					 struct bio *bio,
-					 struct bio_set *bs)
+					 struct bio_set *bs,
+					 unsigned *segs)
 {
 	struct bio_vec bv, bvprv, *bvprvp = NULL;
 	struct bvec_iter iter;
@@ -106,24 +113,35 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 		sectors += bv.bv_len >> 9;
 	}
 
+	*segs = nsegs;
 	return NULL;
 split:
+	*segs = nsegs;
 	return bio_split(bio, sectors, GFP_NOIO, bs);
 }
 
 void blk_queue_split(struct request_queue *q, struct bio **bio,
 		     struct bio_set *bs)
 {
-	struct bio *split;
+	struct bio *split, *res;
+	unsigned nsegs;
 
 	if ((*bio)->bi_rw & REQ_DISCARD)
-		split = blk_bio_discard_split(q, *bio, bs);
+		split = blk_bio_discard_split(q, *bio, bs, &nsegs);
 	else if ((*bio)->bi_rw & REQ_WRITE_SAME)
-		split = blk_bio_write_same_split(q, *bio, bs);
+		split = blk_bio_write_same_split(q, *bio, bs, &nsegs);
 	else
-		split = blk_bio_segment_split(q, *bio, q->bio_split);
+		split = blk_bio_segment_split(q, *bio, q->bio_split, &nsegs);
+
+	/* physical segments can be figured out during splitting */
+	res = split ? split : *bio;
+	res->bi_phys_segments = nsegs;
+	bio_set_flag(res, BIO_SEG_VALID);
 
 	if (split) {
+		/* there isn't chance to merge the splitted bio */
+		split->bi_rw |= REQ_NOMERGE;
+
 		bio_chain(split, *bio);
 		generic_make_request(*bio);
 		*bio = split;

block/blk-mq-tag.c

@@ -75,6 +75,10 @@ void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool include_reserve)
 	struct blk_mq_bitmap_tags *bt;
 	int i, wake_index;
 
+	/*
+	 * Make sure all changes prior to this are visible from other CPUs.
+	 */
+	smp_mb();
 	bt = &tags->bitmap_tags;
 	wake_index = atomic_read(&bt->wake_index);
 	for (i = 0; i < BT_WAIT_QUEUES; i++) {

block/blk-mq.c

@@ -9,6 +9,7 @@
 #include <linux/backing-dev.h>
 #include <linux/bio.h>
 #include <linux/blkdev.h>
+#include <linux/kmemleak.h>
 #include <linux/mm.h>
 #include <linux/init.h>
 #include <linux/slab.h>
@@ -989,18 +990,25 @@ void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
 }
 EXPORT_SYMBOL(blk_mq_delay_queue);
 
-static void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx,
-				    struct request *rq, bool at_head)
+static inline void __blk_mq_insert_req_list(struct blk_mq_hw_ctx *hctx,
+					    struct blk_mq_ctx *ctx,
+					    struct request *rq,
+					    bool at_head)
 {
-	struct blk_mq_ctx *ctx = rq->mq_ctx;
-
 	trace_block_rq_insert(hctx->queue, rq);
 
 	if (at_head)
 		list_add(&rq->queuelist, &ctx->rq_list);
 	else
 		list_add_tail(&rq->queuelist, &ctx->rq_list);
+}
 
+static void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx,
+				    struct request *rq, bool at_head)
+{
+	struct blk_mq_ctx *ctx = rq->mq_ctx;
+
+	__blk_mq_insert_req_list(hctx, ctx, rq, at_head);
 	blk_mq_hctx_mark_pending(hctx, ctx);
 }
 
@@ -1056,8 +1064,9 @@ static void blk_mq_insert_requests(struct request_queue *q,
 		rq = list_first_entry(list, struct request, queuelist);
 		list_del_init(&rq->queuelist);
 		rq->mq_ctx = ctx;
-		__blk_mq_insert_request(hctx, rq, false);
+		__blk_mq_insert_req_list(hctx, ctx, rq, false);
 	}
+	blk_mq_hctx_mark_pending(hctx, ctx);
 	spin_unlock(&ctx->lock);
 
 	blk_mq_run_hw_queue(hctx, from_schedule);
@@ -1139,7 +1148,7 @@ static inline bool blk_mq_merge_queue_io(struct blk_mq_hw_ctx *hctx,
 					 struct blk_mq_ctx *ctx,
 					 struct request *rq, struct bio *bio)
 {
-	if (!hctx_allow_merges(hctx)) {
+	if (!hctx_allow_merges(hctx) || !bio_mergeable(bio)) {
 		blk_mq_bio_to_request(rq, bio);
 		spin_lock(&ctx->lock);
 insert_rq:
@@ -1267,9 +1276,12 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
 
 	blk_queue_split(q, &bio, q->bio_split);
 
-	if (!is_flush_fua && !blk_queue_nomerges(q) &&
-	    blk_attempt_plug_merge(q, bio, &request_count, &same_queue_rq))
-		return;
+	if (!is_flush_fua && !blk_queue_nomerges(q)) {
+		if (blk_attempt_plug_merge(q, bio, &request_count,
+					   &same_queue_rq))
+			return;
+	} else
+		request_count = blk_plug_queued_count(q);
 
 	rq = blk_mq_map_request(q, bio, &data);
 	if (unlikely(!rq))
@@ -1376,7 +1388,7 @@ static void blk_sq_make_request(struct request_queue *q, struct bio *bio)
 	plug = current->plug;
 	if (plug) {
 		blk_mq_bio_to_request(rq, bio);
-		if (list_empty(&plug->mq_list))
+		if (!request_count)
 			trace_block_plug(q);
 		else if (request_count >= BLK_MAX_REQUEST_COUNT) {
 			blk_flush_plug_list(plug, false);
@@ -1430,6 +1442,11 @@ static void blk_mq_free_rq_map(struct blk_mq_tag_set *set,
 	while (!list_empty(&tags->page_list)) {
 		page = list_first_entry(&tags->page_list, struct page, lru);
 		list_del_init(&page->lru);
+		/*
+		 * Remove kmemleak object previously allocated in
+		 * blk_mq_init_rq_map().
+		 */
+		kmemleak_free(page_address(page));
 		__free_pages(page, page->private);
 	}
 
@@ -1502,6 +1519,11 @@ static struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set,
 		list_add_tail(&page->lru, &tags->page_list);
 
 		p = page_address(page);
+		/*
+		 * Allow kmemleak to scan these pages as they contain pointers
+		 * to additional allocations like via ops->init_request().
+		 */
+		kmemleak_alloc(p, order_to_size(this_order), 1, GFP_KERNEL);
 		entries_per_page = order_to_size(this_order) / rq_size;
 		to_do = min(entries_per_page, set->queue_depth - i);
 		left -= to_do * rq_size;
@@ -1673,7 +1695,7 @@ static int blk_mq_init_hctx(struct request_queue *q,
 	INIT_LIST_HEAD(&hctx->dispatch);
 	hctx->queue = q;
 	hctx->queue_num = hctx_idx;
-	hctx->flags = set->flags;
+	hctx->flags = set->flags & ~BLK_MQ_F_TAG_SHARED;
 
 	blk_mq_init_cpu_notifier(&hctx->cpu_notifier,
 					blk_mq_hctx_notify, hctx);
@@ -1860,27 +1882,26 @@ static void blk_mq_map_swqueue(struct request_queue *q,
 	}
 }
 
-static void blk_mq_update_tag_set_depth(struct blk_mq_tag_set *set)
+static void queue_set_hctx_shared(struct request_queue *q, bool shared)
 {
 	struct blk_mq_hw_ctx *hctx;
-	struct request_queue *q;
-	bool shared;
 	int i;
 
-	if (set->tag_list.next == set->tag_list.prev)
-		shared = false;
-	else
-		shared = true;
+	queue_for_each_hw_ctx(q, hctx, i) {
+		if (shared)
+			hctx->flags |= BLK_MQ_F_TAG_SHARED;
+		else
+			hctx->flags &= ~BLK_MQ_F_TAG_SHARED;
+	}
+}
+
+static void blk_mq_update_tag_set_depth(struct blk_mq_tag_set *set, bool shared)
+{
+	struct request_queue *q;
 
 	list_for_each_entry(q, &set->tag_list, tag_set_list) {
 		blk_mq_freeze_queue(q);
-
-		queue_for_each_hw_ctx(q, hctx, i) {
-			if (shared)
-				hctx->flags |= BLK_MQ_F_TAG_SHARED;
-			else
-				hctx->flags &= ~BLK_MQ_F_TAG_SHARED;
-		}
+		queue_set_hctx_shared(q, shared);
 		blk_mq_unfreeze_queue(q);
 	}
 }
@@ -1891,7 +1912,12 @@ static void blk_mq_del_queue_tag_set(struct request_queue *q)
 
 	mutex_lock(&set->tag_list_lock);
 	list_del_init(&q->tag_set_list);
-	blk_mq_update_tag_set_depth(set);
+	if (list_is_singular(&set->tag_list)) {
+		/* just transitioned to unshared */
+		set->flags &= ~BLK_MQ_F_TAG_SHARED;
+		/* update existing queue */
+		blk_mq_update_tag_set_depth(set, false);
+	}
 	mutex_unlock(&set->tag_list_lock);
 }
 
@@ -1901,8 +1927,17 @@ static void blk_mq_add_queue_tag_set(struct blk_mq_tag_set *set,
 	q->tag_set = set;
 
 	mutex_lock(&set->tag_list_lock);
+
+	/* Check to see if we're transitioning to shared (from 1 to 2 queues). */
+	if (!list_empty(&set->tag_list) && !(set->flags & BLK_MQ_F_TAG_SHARED)) {
+		set->flags |= BLK_MQ_F_TAG_SHARED;
+		/* update existing queue */
+		blk_mq_update_tag_set_depth(set, true);
+	}
+	if (set->flags & BLK_MQ_F_TAG_SHARED)
+		queue_set_hctx_shared(q, true);
 	list_add_tail(&q->tag_set_list, &set->tag_list);
-	blk_mq_update_tag_set_depth(set);
+
 	mutex_unlock(&set->tag_list_lock);
 }
 

block/blk-mq.h

@@ -29,8 +29,6 @@ void __blk_mq_complete_request(struct request *rq);
 void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async);
 void blk_mq_freeze_queue(struct request_queue *q);
 void blk_mq_free_queue(struct request_queue *q);
-void blk_mq_clone_flush_request(struct request *flush_rq,
-		struct request *orig_rq);
 int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr);
 void blk_mq_wake_waiters(struct request_queue *q);
 

block/blk.h

@@ -86,6 +86,7 @@ bool bio_attempt_back_merge(struct request_queue *q, struct request *req,
 bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
 			    unsigned int *request_count,
 			    struct request **same_queue_rq);
+unsigned int blk_plug_queued_count(struct request_queue *q);
 
 void blk_account_io_start(struct request *req, bool new_io);
 void blk_account_io_completion(struct request *req, unsigned int bytes);

block/elevator.c

@@ -420,7 +420,7 @@ int elv_merge(struct request_queue *q, struct request **req, struct bio *bio)
 	 * 	noxmerges: Only simple one-hit cache try
 	 * 	merges:	   All merge tries attempted
 	 */
-	if (blk_queue_nomerges(q))
+	if (blk_queue_nomerges(q) || !bio_mergeable(bio))
 		return ELEVATOR_NO_MERGE;
 
 	/*

fs/direct-io.c

@@ -120,6 +120,7 @@ struct dio {
 	int page_errors;		/* errno from get_user_pages() */
 	int is_async;			/* is IO async ? */
 	bool defer_completion;		/* defer AIO completion to workqueue? */
+	bool should_dirty;		/* if pages should be dirtied */
 	int io_error;			/* IO error in completion path */
 	unsigned long refcount;		/* direct_io_worker() and bios */
 	struct bio *bio_list;		/* singly linked via bi_private */
@@ -393,7 +394,7 @@ static inline void dio_bio_submit(struct dio *dio, struct dio_submit *sdio)
 	dio->refcount++;
 	spin_unlock_irqrestore(&dio->bio_lock, flags);
 
-	if (dio->is_async && dio->rw == READ)
+	if (dio->is_async && dio->rw == READ && dio->should_dirty)
 		bio_set_pages_dirty(bio);
 
 	if (sdio->submit_io)
@@ -464,14 +465,15 @@ static int dio_bio_complete(struct dio *dio, struct bio *bio)
 	if (bio->bi_error)
 		dio->io_error = -EIO;
 
-	if (dio->is_async && dio->rw == READ) {
+	if (dio->is_async && dio->rw == READ && dio->should_dirty) {
 		bio_check_pages_dirty(bio);	/* transfers ownership */
 		err = bio->bi_error;
 	} else {
 		bio_for_each_segment_all(bvec, bio, i) {
 			struct page *page = bvec->bv_page;
 
-			if (dio->rw == READ && !PageCompound(page))
+			if (dio->rw == READ && !PageCompound(page) &&
+					dio->should_dirty)
 				set_page_dirty_lock(page);
 			page_cache_release(page);
 		}
@@ -1219,6 +1221,7 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
 	spin_lock_init(&dio->bio_lock);
 	dio->refcount = 1;
 
+	dio->should_dirty = (iter->type == ITER_IOVEC);
 	sdio.iter = iter;
 	sdio.final_block_in_request =
 		(offset + iov_iter_count(iter)) >> blkbits;

fs/mpage.c

@@ -485,6 +485,7 @@ static int __mpage_writepage(struct page *page, struct writeback_control *wbc,
 	struct buffer_head map_bh;
 	loff_t i_size = i_size_read(inode);
 	int ret = 0;
+	int wr = (wbc->sync_mode == WB_SYNC_ALL ?  WRITE_SYNC : WRITE);
 
 	if (page_has_buffers(page)) {
 		struct buffer_head *head = page_buffers(page);
@@ -593,7 +594,7 @@ static int __mpage_writepage(struct page *page, struct writeback_control *wbc,
 	 * This page will go to BIO.  Do we need to send this BIO off first?
 	 */
 	if (bio && mpd->last_block_in_bio != blocks[0] - 1)
-		bio = mpage_bio_submit(WRITE, bio);
+		bio = mpage_bio_submit(wr, bio);
 
 alloc_new:
 	if (bio == NULL) {
@@ -620,7 +621,7 @@ static int __mpage_writepage(struct page *page, struct writeback_control *wbc,
 	wbc_account_io(wbc, page, PAGE_SIZE);
 	length = first_unmapped << blkbits;
 	if (bio_add_page(bio, page, length, 0) < length) {
-		bio = mpage_bio_submit(WRITE, bio);
+		bio = mpage_bio_submit(wr, bio);
 		goto alloc_new;
 	}
 
@@ -630,7 +631,7 @@ static int __mpage_writepage(struct page *page, struct writeback_control *wbc,
 	set_page_writeback(page);
 	unlock_page(page);
 	if (boundary || (first_unmapped != blocks_per_page)) {
-		bio = mpage_bio_submit(WRITE, bio);
+		bio = mpage_bio_submit(wr, bio);
 		if (boundary_block) {
 			write_boundary_block(boundary_bdev,
 					boundary_block, 1 << blkbits);
@@ -642,7 +643,7 @@ static int __mpage_writepage(struct page *page, struct writeback_control *wbc,
 
 confused:
 	if (bio)
-		bio = mpage_bio_submit(WRITE, bio);
+		bio = mpage_bio_submit(wr, bio);
 
 	if (mpd->use_writepage) {
 		ret = mapping->a_ops->writepage(page, wbc);
@@ -698,8 +699,11 @@ mpage_writepages(struct address_space *mapping,
 		};
 
 		ret = write_cache_pages(mapping, wbc, __mpage_writepage, &mpd);
-		if (mpd.bio)
-			mpage_bio_submit(WRITE, mpd.bio);
+		if (mpd.bio) {
+			int wr = (wbc->sync_mode == WB_SYNC_ALL ?
+				  WRITE_SYNC : WRITE);
+			mpage_bio_submit(wr, mpd.bio);
+		}
 	}
 	blk_finish_plug(&plug);
 	return ret;
@@ -716,8 +720,11 @@ int mpage_writepage(struct page *page, get_block_t get_block,
 		.use_writepage = 0,
 	};
 	int ret = __mpage_writepage(page, wbc, &mpd);
-	if (mpd.bio)
-		mpage_bio_submit(WRITE, mpd.bio);
+	if (mpd.bio) {
+		int wr = (wbc->sync_mode == WB_SYNC_ALL ?
+			  WRITE_SYNC : WRITE);
+		mpage_bio_submit(wr, mpd.bio);
+	}
 	return ret;
 }
 EXPORT_SYMBOL(mpage_writepage);

kernel/trace/blktrace.c

@@ -437,7 +437,7 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 		       struct block_device *bdev,
 		       struct blk_user_trace_setup *buts)
 {
-	struct blk_trace *old_bt, *bt = NULL;
+	struct blk_trace *bt = NULL;
 	struct dentry *dir = NULL;
 	int ret;
 
@@ -519,11 +519,8 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	bt->trace_state = Blktrace_setup;
 
 	ret = -EBUSY;
-	old_bt = xchg(&q->blk_trace, bt);
-	if (old_bt) {
-		(void) xchg(&q->blk_trace, old_bt);
+	if (cmpxchg(&q->blk_trace, NULL, bt))
 		goto err;
-	}
 
 	if (atomic_inc_return(&blk_probes_ref) == 1)
 		blk_register_tracepoints();
@@ -1481,7 +1478,7 @@ static int blk_trace_remove_queue(struct request_queue *q)
 static int blk_trace_setup_queue(struct request_queue *q,
 				 struct block_device *bdev)
 {
-	struct blk_trace *old_bt, *bt = NULL;
+	struct blk_trace *bt = NULL;
 	int ret = -ENOMEM;
 
 	bt = kzalloc(sizeof(*bt), GFP_KERNEL);
@@ -1497,12 +1494,9 @@ static int blk_trace_setup_queue(struct request_queue *q,
 
 	blk_trace_setup_lba(bt, bdev);
 
-	old_bt = xchg(&q->blk_trace, bt);
-	if (old_bt != NULL) {
-		(void)xchg(&q->blk_trace, old_bt);
-		ret = -EBUSY;
+	ret = -EBUSY;
+	if (cmpxchg(&q->blk_trace, NULL, bt))
 		goto free_bt;
-	}
 
 	if (atomic_inc_return(&blk_probes_ref) == 1)
 		blk_register_tracepoints();