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
  ...

1 files changed, 72 insertions, 36 deletions

diff --git a/block/blk-lib.c b/block/blk-lib.c
index 63fb971d65745..2bc544ce3d2e5 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -275,6 +275,40 @@ static unsigned int __blkdev_sectors_to_bio_pages(sector_t nr_sects)
 	return min(pages, (sector_t)BIO_MAX_PAGES);
 }
 
+static int __blkdev_issue_zero_pages(struct block_device *bdev,
+		sector_t sector, sector_t nr_sects, gfp_t gfp_mask,
+		struct bio **biop)
+{
+	struct request_queue *q = bdev_get_queue(bdev);
+	struct bio *bio = *biop;
+	int bi_size = 0;
+	unsigned int sz;
+
+	if (!q)
+		return -ENXIO;
+
+	while (nr_sects != 0) {
+		bio = next_bio(bio, __blkdev_sectors_to_bio_pages(nr_sects),
+			       gfp_mask);
+		bio->bi_iter.bi_sector = sector;
+		bio_set_dev(bio, bdev);
+		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
+
+		while (nr_sects != 0) {
+			sz = min((sector_t) PAGE_SIZE, nr_sects << 9);
+			bi_size = bio_add_page(bio, ZERO_PAGE(0), sz, 0);
+			nr_sects -= bi_size >> 9;
+			sector += bi_size >> 9;
+			if (bi_size < sz)
+				break;
+		}
+		cond_resched();
+	}
+
+	*biop = bio;
+	return 0;
+}
+
 /**
  * __blkdev_issue_zeroout - generate number of zero filed write bios
  * @bdev:	blockdev to issue
@@ -288,12 +322,6 @@ static unsigned int __blkdev_sectors_to_bio_pages(sector_t nr_sects)
  *  Zero-fill a block range, either using hardware offload or by explicitly
  *  writing zeroes to the device.
  *
- *  Note that this function may fail with -EOPNOTSUPP if the driver signals
- *  zeroing offload support, but the device fails to process the command (for
- *  some devices there is no non-destructive way to verify whether this
- *  operation is actually supported).  In this case the caller should call
- *  retry the call to blkdev_issue_zeroout() and the fallback path will be used.
- *
  *  If a device is using logical block provisioning, the underlying space will
  *  not be released if %flags contains BLKDEV_ZERO_NOUNMAP.
  *
@@ -305,9 +333,6 @@ int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 		unsigned flags)
 {
 	int ret;
-	int bi_size = 0;
-	struct bio *bio = *biop;
-	unsigned int sz;
 	sector_t bs_mask;
 
 	bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1;
@@ -317,30 +342,10 @@ int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 	ret = __blkdev_issue_write_zeroes(bdev, sector, nr_sects, gfp_mask,
 			biop, flags);
 	if (ret != -EOPNOTSUPP || (flags & BLKDEV_ZERO_NOFALLBACK))
-		goto out;
-
-	ret = 0;
-	while (nr_sects != 0) {
-		bio = next_bio(bio, __blkdev_sectors_to_bio_pages(nr_sects),
-			       gfp_mask);
-		bio->bi_iter.bi_sector = sector;
-		bio_set_dev(bio, bdev);
-		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
-
-		while (nr_sects != 0) {
-			sz = min((sector_t) PAGE_SIZE, nr_sects << 9);
-			bi_size = bio_add_page(bio, ZERO_PAGE(0), sz, 0);
-			nr_sects -= bi_size >> 9;
-			sector += bi_size >> 9;
-			if (bi_size < sz)
-				break;
-		}
-		cond_resched();
-	}
+		return ret;
 
-	*biop = bio;
-out:
-	return ret;
+	return __blkdev_issue_zero_pages(bdev, sector, nr_sects, gfp_mask,
+					 biop);
 }
 EXPORT_SYMBOL(__blkdev_issue_zeroout);
 
@@ -360,18 +365,49 @@ EXPORT_SYMBOL(__blkdev_issue_zeroout);
 int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp_mask, unsigned flags)
 {
-	int ret;
-	struct bio *bio = NULL;
+	int ret = 0;
+	sector_t bs_mask;
+	struct bio *bio;
 	struct blk_plug plug;
+	bool try_write_zeroes = !!bdev_write_zeroes_sectors(bdev);
 
+	bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1;
+	if ((sector | nr_sects) & bs_mask)
+		return -EINVAL;
+
+retry:
+	bio = NULL;
 	blk_start_plug(&plug);
-	ret = __blkdev_issue_zeroout(bdev, sector, nr_sects, gfp_mask,
-			&bio, flags);
+	if (try_write_zeroes) {
+		ret = __blkdev_issue_write_zeroes(bdev, sector, nr_sects,
+						  gfp_mask, &bio, flags);
+	} else if (!(flags & BLKDEV_ZERO_NOFALLBACK)) {
+		ret = __blkdev_issue_zero_pages(bdev, sector, nr_sects,
+						gfp_mask, &bio);
+	} else {
+		/* No zeroing offload support */
+		ret = -EOPNOTSUPP;
+	}
 	if (ret == 0 && bio) {
 		ret = submit_bio_wait(bio);
 		bio_put(bio);
 	}
 	blk_finish_plug(&plug);
+	if (ret && try_write_zeroes) {
+		if (!(flags & BLKDEV_ZERO_NOFALLBACK)) {
+			try_write_zeroes = false;
+			goto retry;
+		}
+		if (!bdev_write_zeroes_sectors(bdev)) {
+			/*
+			 * Zeroing offload support was indicated, but the
+			 * device reported ILLEGAL REQUEST (for some devices
+			 * there is no non-destructive way to verify whether
+			 * WRITE ZEROES is actually supported).
+			 */
+			ret = -EOPNOTSUPP;
+		}
+	}
 
 	return ret;
 }