Merge branch 'for-4.7/core' of git://git.kernel.dk/linux-block

Pull core block layer updates from Jens Axboe:
 "This is the core block IO changes for this merge window.  Nothing
  earth shattering in here, it's mostly just fixes.  In detail:

   - Fix for a long standing issue where wrong ordering in blk-mq caused
     order_to_size() to spew a warning.  From Bart.

   - Async discard support from Christoph.  Basically just splitting our
     sync interface into a submit + wait part.

   - Add a cleaner interface for flagging whether a device has a write
     back cache or not.  We've previously overloaded blk_queue_flush()
     with this, but let's make it more explicit.  Drivers cleaned up and
     updated in the drivers pull request.  From me.

   - Fix for a double check for whether IO accounting is enabled or not.
     From Michael Callahan.

   - Fix for the async discard from Mike Snitzer, reinstating the early
     EOPNOTSUPP return if the device doesn't support discards.

   - Also from Mike, export bio_inc_remaining() so dm can drop it's
     private copy of it.

   - From Ming Lin, add support for passing in an offset for request
     payloads.

   - Tag function export from Sagi, which will be used in NVMe in the
     drivers pull.

   - Two blktrace related fixes from Shaohua.

   - Propagate NOMERGE flag when making a request from a bio, also from
     Shaohua.

   - An optimization to not parse cgroup paths in blk-throttle, if we
     don't need to.  From Shaohua"

* 'for-4.7/core' of git://git.kernel.dk/linux-block:
  blk-mq: fix undefined behaviour in order_to_size()
  blk-throttle: don't parse cgroup path if trace isn't enabled
  blktrace: add missed mask name
  blktrace: delete garbage for message trace
  block: make bio_inc_remaining() interface accessible again
  block: reinstate early return of -EOPNOTSUPP from blkdev_issue_discard
  block: Minor blk_account_io_start usage cleanup
  block: add __blkdev_issue_discard
  block: remove struct bio_batch
  block: copy NOMERGE flag from bio to request
  block: add ability to flag write back caching on a device
  blk-mq: Export tagset iter function
  block: add offset in blk_add_request_payload()
  writeback: Fix performance regression in wb_over_bg_thresh()

8 files changed, 148 insertions, 133 deletions

diff --git a/block/bio.c b/block/bio.c
index 807d25e..0e4aa42 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -311,17 +311,6 @@ static void bio_chain_endio(struct bio *bio)
 	bio_endio(__bio_chain_endio(bio));
 }
 
-/*
- * Increment chain count for the bio. Make sure the CHAIN flag update
- * is visible before the raised count.
- */
-static inline void bio_inc_remaining(struct bio *bio)
-{
-	bio_set_flag(bio, BIO_CHAIN);
-	smp_mb__before_atomic();
-	atomic_inc(&bio->__bi_remaining);
-}
-
 /**
  * bio_chain - chain bio completions
  * @bio: the target bio
diff --git a/block/blk-core.c b/block/blk-core.c
index b60537b..c502277 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1523,6 +1523,7 @@ EXPORT_SYMBOL(blk_put_request);
  * blk_add_request_payload - add a payload to a request
  * @rq: request to update
  * @page: page backing the payload
+ * @offset: offset in page
  * @len: length of the payload.
  *
  * This allows to later add a payload to an already submitted request by
@@ -1533,12 +1534,12 @@ EXPORT_SYMBOL(blk_put_request);
  * discard requests should ever use it.
  */
 void blk_add_request_payload(struct request *rq, struct page *page,
-		unsigned int len)
+		int offset, unsigned int len)
 {
 	struct bio *bio = rq->bio;
 
 	bio->bi_io_vec->bv_page = page;
-	bio->bi_io_vec->bv_offset = 0;
+	bio->bi_io_vec->bv_offset = offset;
 	bio->bi_io_vec->bv_len = len;
 
 	bio->bi_iter.bi_size = len;
diff --git a/block/blk-lib.c b/block/blk-lib.c
index 9ebf653..23d7f30 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -9,82 +9,46 @@
 
 #include "blk.h"
 
-struct bio_batch {
-	atomic_t		done;
-	int			error;
-	struct completion	*wait;
-};
-
-static void bio_batch_end_io(struct bio *bio)
+static struct bio *next_bio(struct bio *bio, int rw, unsigned int nr_pages,
+		gfp_t gfp)
 {
-	struct bio_batch *bb = bio->bi_private;
+	struct bio *new = bio_alloc(gfp, nr_pages);
+
+	if (bio) {
+		bio_chain(bio, new);
+		submit_bio(rw, bio);
+	}
 
-	if (bio->bi_error && bio->bi_error != -EOPNOTSUPP)
-		bb->error = bio->bi_error;
-	if (atomic_dec_and_test(&bb->done))
-		complete(bb->wait);
-	bio_put(bio);
+	return new;
 }
 
-/**
- * blkdev_issue_discard - queue a discard
- * @bdev:	blockdev to issue discard for
- * @sector:	start sector
- * @nr_sects:	number of sectors to discard
- * @gfp_mask:	memory allocation flags (for bio_alloc)
- * @flags:	BLKDEV_IFL_* flags to control behaviour
- *
- * Description:
- *    Issue a discard request for the sectors in question.
- */
-int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
-		sector_t nr_sects, gfp_t gfp_mask, unsigned long flags)
+int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
+		sector_t nr_sects, gfp_t gfp_mask, int type, struct bio **biop)
 {
-	DECLARE_COMPLETION_ONSTACK(wait);
 	struct request_queue *q = bdev_get_queue(bdev);
-	int type = REQ_WRITE | REQ_DISCARD;
+	struct bio *bio = *biop;
 	unsigned int granularity;
 	int alignment;
-	struct bio_batch bb;
-	struct bio *bio;
-	int ret = 0;
-	struct blk_plug plug;
 
 	if (!q)
 		return -ENXIO;
-
 	if (!blk_queue_discard(q))
 		return -EOPNOTSUPP;
+	if ((type & REQ_SECURE) && !blk_queue_secdiscard(q))
+		return -EOPNOTSUPP;
 
 	/* Zero-sector (unknown) and one-sector granularities are the same.  */
 	granularity = max(q->limits.discard_granularity >> 9, 1U);
 	alignment = (bdev_discard_alignment(bdev) >> 9) % granularity;
 
-	if (flags & BLKDEV_DISCARD_SECURE) {
-		if (!blk_queue_secdiscard(q))
-			return -EOPNOTSUPP;
-		type |= REQ_SECURE;
-	}
-
-	atomic_set(&bb.done, 1);
-	bb.error = 0;
-	bb.wait = &wait;
-
-	blk_start_plug(&plug);
 	while (nr_sects) {
 		unsigned int req_sects;
 		sector_t end_sect, tmp;
 
-		bio = bio_alloc(gfp_mask, 1);
-		if (!bio) {
-			ret = -ENOMEM;
-			break;
-		}
-
 		/* Make sure bi_size doesn't overflow */
 		req_sects = min_t(sector_t, nr_sects, UINT_MAX >> 9);
 
-		/*
+		/**
 		 * If splitting a request, and the next starting sector would be
 		 * misaligned, stop the discard at the previous aligned sector.
 		 */
@@ -98,18 +62,14 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 			req_sects = end_sect - sector;
 		}
 
+		bio = next_bio(bio, type, 1, gfp_mask);
 		bio->bi_iter.bi_sector = sector;
-		bio->bi_end_io = bio_batch_end_io;
 		bio->bi_bdev = bdev;
-		bio->bi_private = &bb;
 
 		bio->bi_iter.bi_size = req_sects << 9;
 		nr_sects -= req_sects;
 		sector = end_sect;
 
-		atomic_inc(&bb.done);
-		submit_bio(type, bio);
-
 		/*
 		 * We can loop for a long time in here, if someone does
 		 * full device discards (like mkfs). Be nice and allow
@@ -118,14 +78,44 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		 */
 		cond_resched();
 	}
-	blk_finish_plug(&plug);
 
-	/* Wait for bios in-flight */
-	if (!atomic_dec_and_test(&bb.done))
-		wait_for_completion_io(&wait);
+	*biop = bio;
+	return 0;
+}
+EXPORT_SYMBOL(__blkdev_issue_discard);
+
+/**
+ * blkdev_issue_discard - queue a discard
+ * @bdev:	blockdev to issue discard for
+ * @sector:	start sector
+ * @nr_sects:	number of sectors to discard
+ * @gfp_mask:	memory allocation flags (for bio_alloc)
+ * @flags:	BLKDEV_IFL_* flags to control behaviour
+ *
+ * Description:
+ *    Issue a discard request for the sectors in question.
+ */
+int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
+		sector_t nr_sects, gfp_t gfp_mask, unsigned long flags)
+{
+	int type = REQ_WRITE | REQ_DISCARD;
+	struct bio *bio = NULL;
+	struct blk_plug plug;
+	int ret;
+
+	if (flags & BLKDEV_DISCARD_SECURE)
+		type |= REQ_SECURE;
+
+	blk_start_plug(&plug);
+	ret = __blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask, type,
+			&bio);
+	if (!ret && bio) {
+		ret = submit_bio_wait(type, bio);
+		if (ret == -EOPNOTSUPP)
+			ret = 0;
+	}
+	blk_finish_plug(&plug);
 
-	if (bb.error)
-		return bb.error;
 	return ret;
 }
 EXPORT_SYMBOL(blkdev_issue_discard);
@@ -145,11 +135,9 @@ int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
 			    sector_t nr_sects, gfp_t gfp_mask,
 			    struct page *page)
 {
-	DECLARE_COMPLETION_ONSTACK(wait);
 	struct request_queue *q = bdev_get_queue(bdev);
 	unsigned int max_write_same_sectors;
-	struct bio_batch bb;
-	struct bio *bio;
+	struct bio *bio = NULL;
 	int ret = 0;
 
 	if (!q)
@@ -158,21 +146,10 @@ int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
 	/* Ensure that max_write_same_sectors doesn't overflow bi_size */
 	max_write_same_sectors = UINT_MAX >> 9;
 
-	atomic_set(&bb.done, 1);
-	bb.error = 0;
-	bb.wait = &wait;
-
 	while (nr_sects) {
-		bio = bio_alloc(gfp_mask, 1);
-		if (!bio) {
-			ret = -ENOMEM;
-			break;
-		}
-
+		bio = next_bio(bio, REQ_WRITE | REQ_WRITE_SAME, 1, gfp_mask);
 		bio->bi_iter.bi_sector = sector;
-		bio->bi_end_io = bio_batch_end_io;
 		bio->bi_bdev = bdev;
-		bio->bi_private = &bb;
 		bio->bi_vcnt = 1;
 		bio->bi_io_vec->bv_page = page;
 		bio->bi_io_vec->bv_offset = 0;
@@ -186,18 +163,11 @@ int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
 			bio->bi_iter.bi_size = nr_sects << 9;
 			nr_sects = 0;
 		}
-
-		atomic_inc(&bb.done);
-		submit_bio(REQ_WRITE | REQ_WRITE_SAME, bio);
 	}
 
-	/* Wait for bios in-flight */
-	if (!atomic_dec_and_test(&bb.done))
-		wait_for_completion_io(&wait);
-
-	if (bb.error)
-		return bb.error;
-	return ret;
+	if (bio)
+		ret = submit_bio_wait(REQ_WRITE | REQ_WRITE_SAME, bio);
+	return ret != -EOPNOTSUPP ? ret : 0;
 }
 EXPORT_SYMBOL(blkdev_issue_write_same);
 
@@ -216,28 +186,15 @@ static int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 				  sector_t nr_sects, gfp_t gfp_mask)
 {
 	int ret;
-	struct bio *bio;
-	struct bio_batch bb;
+	struct bio *bio = NULL;
 	unsigned int sz;
-	DECLARE_COMPLETION_ONSTACK(wait);
-
-	atomic_set(&bb.done, 1);
-	bb.error = 0;
-	bb.wait = &wait;
 
-	ret = 0;
 	while (nr_sects != 0) {
-		bio = bio_alloc(gfp_mask,
-				min(nr_sects, (sector_t)BIO_MAX_PAGES));
-		if (!bio) {
-			ret = -ENOMEM;
-			break;
-		}
-
+		bio = next_bio(bio, WRITE,
+				min(nr_sects, (sector_t)BIO_MAX_PAGES),
+				gfp_mask);
 		bio->bi_iter.bi_sector = sector;
 		bio->bi_bdev   = bdev;
-		bio->bi_end_io = bio_batch_end_io;
-		bio->bi_private = &bb;
 
 		while (nr_sects != 0) {
 			sz = min((sector_t) PAGE_SIZE >> 9 , nr_sects);
@@ -247,18 +204,11 @@ static int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 			if (ret < (sz << 9))
 				break;
 		}
-		ret = 0;
-		atomic_inc(&bb.done);
-		submit_bio(WRITE, bio);
 	}
 
-	/* Wait for bios in-flight */
-	if (!atomic_dec_and_test(&bb.done))
-		wait_for_completion_io(&wait);
-
-	if (bb.error)
-		return bb.error;
-	return ret;
+	if (bio)
+		return submit_bio_wait(WRITE, bio);
+	return 0;
 }
 
 /**
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index abdbb47..2fd0428 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -474,6 +474,18 @@ void blk_mq_all_tag_busy_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn,
 }
 EXPORT_SYMBOL(blk_mq_all_tag_busy_iter);
 
+void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset,
+		busy_tag_iter_fn *fn, void *priv)
+{
+	int i;
+
+	for (i = 0; i < tagset->nr_hw_queues; i++) {
+		if (tagset->tags && tagset->tags[i])
+			blk_mq_all_tag_busy_iter(tagset->tags[i], fn, priv);
+	}
+}
+EXPORT_SYMBOL(blk_mq_tagset_busy_iter);
+
 void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
 		void *priv)
 {
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 1699baf..7df9c92 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1122,8 +1122,7 @@ static void blk_mq_bio_to_request(struct request *rq, struct bio *bio)
 {
 	init_request_from_bio(rq, bio);
 
-	if (blk_do_io_stat(rq))
-		blk_account_io_start(rq, 1);
+	blk_account_io_start(rq, 1);
 }
 
 static inline bool hctx_allow_merges(struct blk_mq_hw_ctx *hctx)
@@ -1496,7 +1495,7 @@ static struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set,
 		int to_do;
 		void *p;
 
-		while (left < order_to_size(this_order - 1) && this_order)
+		while (this_order && left < order_to_size(this_order - 1))
 			this_order--;
 
 		do {
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 331e4ee..c903bee 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -846,6 +846,32 @@ void blk_queue_flush_queueable(struct request_queue *q, bool queueable)
 }
 EXPORT_SYMBOL_GPL(blk_queue_flush_queueable);
 
+/**
+ * blk_queue_write_cache - configure queue's write cache
+ * @q:		the request queue for the device
+ * @wc:		write back cache on or off
+ * @fua:	device supports FUA writes, if true
+ *
+ * Tell the block layer about the write cache of @q.
+ */
+void blk_queue_write_cache(struct request_queue *q, bool wc, bool fua)
+{
+	spin_lock_irq(q->queue_lock);
+	if (wc) {
+		queue_flag_set(QUEUE_FLAG_WC, q);
+		q->flush_flags = REQ_FLUSH;
+	} else
+		queue_flag_clear(QUEUE_FLAG_WC, q);
+	if (fua) {
+		if (wc)
+			q->flush_flags |= REQ_FUA;
+		queue_flag_set(QUEUE_FLAG_FUA, q);
+	} else
+		queue_flag_clear(QUEUE_FLAG_FUA, q);
+	spin_unlock_irq(q->queue_lock);
+}
+EXPORT_SYMBOL_GPL(blk_queue_write_cache);
+
 static int __init blk_settings_init(void)
 {
 	blk_max_low_pfn = max_low_pfn - 1;
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 995b58d..9920596 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -347,6 +347,38 @@ static ssize_t queue_poll_store(struct request_queue *q, const char *page,
 	return ret;
 }
 
+static ssize_t queue_wc_show(struct request_queue *q, char *page)
+{
+	if (test_bit(QUEUE_FLAG_WC, &q->queue_flags))
+		return sprintf(page, "write back\n");
+
+	return sprintf(page, "write through\n");
+}
+
+static ssize_t queue_wc_store(struct request_queue *q, const char *page,
+			      size_t count)
+{
+	int set = -1;
+
+	if (!strncmp(page, "write back", 10))
+		set = 1;
+	else if (!strncmp(page, "write through", 13) ||
+		 !strncmp(page, "none", 4))
+		set = 0;
+
+	if (set == -1)
+		return -EINVAL;
+
+	spin_lock_irq(q->queue_lock);
+	if (set)
+		queue_flag_set(QUEUE_FLAG_WC, q);
+	else
+		queue_flag_clear(QUEUE_FLAG_WC, q);
+	spin_unlock_irq(q->queue_lock);
+
+	return count;
+}
+
 static struct queue_sysfs_entry queue_requests_entry = {
 	.attr = {.name = "nr_requests", .mode = S_IRUGO | S_IWUSR },
 	.show = queue_requests_show,
@@ -478,6 +510,12 @@ static struct queue_sysfs_entry queue_poll_entry = {
 	.store = queue_poll_store,
 };
 
+static struct queue_sysfs_entry queue_wc_entry = {
+	.attr = {.name = "write_cache", .mode = S_IRUGO | S_IWUSR },
+	.show = queue_wc_show,
+	.store = queue_wc_store,
+};
+
 static struct attribute *default_attrs[] = {
 	&queue_requests_entry.attr,
 	&queue_ra_entry.attr,
@@ -503,6 +541,7 @@ static struct attribute *default_attrs[] = {
 	&queue_iostats_entry.attr,
 	&queue_random_entry.attr,
 	&queue_poll_entry.attr,
+	&queue_wc_entry.attr,
 	NULL,
 };
 
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 2149a1d..47a3e54 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -211,15 +211,14 @@ static struct throtl_data *sq_to_td(struct throtl_service_queue *sq)
  *
  * The messages are prefixed with "throtl BLKG_NAME" if @sq belongs to a
  * throtl_grp; otherwise, just "throtl".
- *
- * TODO: this should be made a function and name formatting should happen
- * after testing whether blktrace is enabled.
  */
 #define throtl_log(sq, fmt, args...)	do {				\
 	struct throtl_grp *__tg = sq_to_tg((sq));			\
 	struct throtl_data *__td = sq_to_td((sq));			\
 									\
 	(void)__td;							\
+	if (likely(!blk_trace_note_message_enabled(__td->queue)))	\
+		break;							\
 	if ((__tg)) {							\
 		char __pbuf[128];					\
 									\