Merge branch 'for-4.10/block' of git://git.kernel.dk/linux-block

Pull block layer updates from Jens Axboe:
 "This is the main block pull request this series. Contrary to previous
  release, I've kept the core and driver changes in the same branch. We
  always ended up having dependencies between the two for obvious
  reasons, so makes more sense to keep them together. That said, I'll
  probably try and keep more topical branches going forward, especially
  for cycles that end up being as busy as this one.

  The major parts of this pull request is:

   - Improved support for O_DIRECT on block devices, with a small
     private implementation instead of using the pig that is
     fs/direct-io.c. From Christoph.

   - Request completion tracking in a scalable fashion. This is utilized
     by two components in this pull, the new hybrid polling and the
     writeback queue throttling code.

   - Improved support for polling with O_DIRECT, adding a hybrid mode
     that combines pure polling with an initial sleep. From me.

   - Support for automatic throttling of writeback queues on the block
     side. This uses feedback from the device completion latencies to
     scale the queue on the block side up or down. From me.

   - Support from SMR drives in the block layer and for SD. From Hannes
     and Shaun.

   - Multi-connection support for nbd. From Josef.

   - Cleanup of request and bio flags, so we have a clear split between
     which are bio (or rq) private, and which ones are shared. From
     Christoph.

   - A set of patches from Bart, that improve how we handle queue
     stopping and starting in blk-mq.

   - Support for WRITE_ZEROES from Chaitanya.

   - Lightnvm updates from Javier/Matias.

   - Supoort for FC for the nvme-over-fabrics code. From James Smart.

   - A bunch of fixes from a whole slew of people, too many to name
     here"

* 'for-4.10/block' of git://git.kernel.dk/linux-block: (182 commits)
  blk-stat: fix a few cases of missing batch flushing
  blk-flush: run the queue when inserting blk-mq flush
  elevator: make the rqhash helpers exported
  blk-mq: abstract out blk_mq_dispatch_rq_list() helper
  blk-mq: add blk_mq_start_stopped_hw_queue()
  block: improve handling of the magic discard payload
  blk-wbt: don't throttle discard or write zeroes
  nbd: use dev_err_ratelimited in io path
  nbd: reset the setup task for NBD_CLEAR_SOCK
  nvme-fabrics: Add FC LLDD loopback driver to test FC-NVME
  nvme-fabrics: Add target support for FC transport
  nvme-fabrics: Add host support for FC transport
  nvme-fabrics: Add FC transport LLDD api definitions
  nvme-fabrics: Add FC transport FC-NVME definitions
  nvme-fabrics: Add FC transport error codes to nvme.h
  Add type 0x28 NVME type code to scsi fc headers
  nvme-fabrics: patch target code in prep for FC transport support
  nvme-fabrics: set sqe.command_id in core not transports
  parser: add u64 number parser
  nvme-rdma: align to generic ib_event logging helper
  ...

fs/btrfs/disk-io.c

@@ -930,7 +930,7 @@ int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct inode *inode,
 
 	atomic_inc(&fs_info->nr_async_submits);
 
-	if (bio->bi_opf & REQ_SYNC)
+	if (op_is_sync(bio->bi_opf))
 		btrfs_set_work_high_priority(&async->work);
 
 	btrfs_queue_work(fs_info->workers, &async->work);
@@ -3485,9 +3485,9 @@ static int write_dev_supers(struct btrfs_device *device,
 		 * to go down lazy.
 		 */
 		if (i == 0)
-			ret = btrfsic_submit_bh(REQ_OP_WRITE, WRITE_FUA, bh);
+			ret = btrfsic_submit_bh(REQ_OP_WRITE, REQ_FUA, bh);
 		else
-			ret = btrfsic_submit_bh(REQ_OP_WRITE, WRITE_SYNC, bh);
+			ret = btrfsic_submit_bh(REQ_OP_WRITE, REQ_SYNC, bh);
 		if (ret)
 			errors++;
 	}
@@ -3551,7 +3551,7 @@ static int write_dev_flush(struct btrfs_device *device, int wait)
 
 	bio->bi_end_io = btrfs_end_empty_barrier;
 	bio->bi_bdev = device->bdev;
-	bio_set_op_attrs(bio, REQ_OP_WRITE, WRITE_FLUSH);
+	bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
 	init_completion(&device->flush_wait);
 	bio->bi_private = &device->flush_wait;
 	device->flush_bio = bio;

fs/btrfs/extent_io.c

@@ -127,7 +127,7 @@ struct extent_page_data {
 	 */
 	unsigned int extent_locked:1;
 
-	/* tells the submit_bio code to use a WRITE_SYNC */
+	/* tells the submit_bio code to use REQ_SYNC */
 	unsigned int sync_io:1;
 };
 
@@ -2047,7 +2047,7 @@ int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical,
 		return -EIO;
 	}
 	bio->bi_bdev = dev->bdev;
-	bio_set_op_attrs(bio, REQ_OP_WRITE, WRITE_SYNC);
+	bio->bi_opf = REQ_OP_WRITE | REQ_SYNC;
 	bio_add_page(bio, page, length, pg_offset);
 
 	if (btrfsic_submit_bio_wait(bio)) {
@@ -2388,7 +2388,7 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
 	struct inode *inode = page->mapping->host;
 	struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
 	struct bio *bio;
-	int read_mode;
+	int read_mode = 0;
 	int ret;
 
 	BUG_ON(bio_op(failed_bio) == REQ_OP_WRITE);
@@ -2404,9 +2404,7 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
 	}
 
 	if (failed_bio->bi_vcnt > 1)
-		read_mode = READ_SYNC | REQ_FAILFAST_DEV;
-	else
-		read_mode = READ_SYNC;
+		read_mode |= REQ_FAILFAST_DEV;
 
 	phy_offset >>= inode->i_sb->s_blocksize_bits;
 	bio = btrfs_create_repair_bio(inode, failed_bio, failrec, page,
@@ -3484,7 +3482,7 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 	unsigned long nr_written = 0;
 
 	if (wbc->sync_mode == WB_SYNC_ALL)
-		write_flags = WRITE_SYNC;
+		write_flags = REQ_SYNC;
 
 	trace___extent_writepage(page, inode, wbc);
 
@@ -3729,7 +3727,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
 	unsigned long i, num_pages;
 	unsigned long bio_flags = 0;
 	unsigned long start, end;
-	int write_flags = (epd->sync_io ? WRITE_SYNC : 0) | REQ_META;
+	int write_flags = (epd->sync_io ? REQ_SYNC : 0) | REQ_META;
 	int ret = 0;
 
 	clear_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags);
@@ -4076,7 +4074,7 @@ static void flush_epd_write_bio(struct extent_page_data *epd)
 		int ret;
 
 		bio_set_op_attrs(epd->bio, REQ_OP_WRITE,
-				 epd->sync_io ? WRITE_SYNC : 0);
+				 epd->sync_io ? REQ_SYNC : 0);
 
 		ret = submit_one_bio(epd->bio, 0, epd->bio_flags);
 		BUG_ON(ret < 0); /* -ENOMEM */

fs/btrfs/inode.c

@@ -7917,7 +7917,7 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio,
 	struct io_failure_record *failrec;
 	struct bio *bio;
 	int isector;
-	int read_mode;
+	int read_mode = 0;
 	int ret;
 
 	BUG_ON(bio_op(failed_bio) == REQ_OP_WRITE);
@@ -7936,9 +7936,7 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio,
 	if ((failed_bio->bi_vcnt > 1)
 		|| (failed_bio->bi_io_vec->bv_len
 			> BTRFS_I(inode)->root->sectorsize))
-		read_mode = READ_SYNC | REQ_FAILFAST_DEV;
-	else
-		read_mode = READ_SYNC;
+		read_mode |= REQ_FAILFAST_DEV;
 
 	isector = start - btrfs_io_bio(failed_bio)->logical;
 	isector >>= inode->i_sb->s_blocksize_bits;
@@ -8427,7 +8425,7 @@ static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip,
 	if (!bio)
 		return -ENOMEM;
 
-	bio_set_op_attrs(bio, bio_op(orig_bio), bio_flags(orig_bio));
+	bio->bi_opf = orig_bio->bi_opf;
 	bio->bi_private = dip;
 	bio->bi_end_io = btrfs_end_dio_bio;
 	btrfs_io_bio(bio)->logical = file_offset;
@@ -8465,8 +8463,7 @@ next_block:
 						  start_sector, GFP_NOFS);
 			if (!bio)
 				goto out_err;
-			bio_set_op_attrs(bio, bio_op(orig_bio),
-					 bio_flags(orig_bio));
+			bio->bi_opf = orig_bio->bi_opf;
 			bio->bi_private = dip;
 			bio->bi_end_io = btrfs_end_dio_bio;
 			btrfs_io_bio(bio)->logical = file_offset;

fs/btrfs/scrub.c

@@ -4440,7 +4440,7 @@ static int write_page_nocow(struct scrub_ctx *sctx,
 	bio->bi_iter.bi_size = 0;
 	bio->bi_iter.bi_sector = physical_for_dev_replace >> 9;
 	bio->bi_bdev = dev->bdev;
-	bio_set_op_attrs(bio, REQ_OP_WRITE, WRITE_SYNC);
+	bio->bi_opf = REQ_OP_WRITE | REQ_SYNC;
 	ret = bio_add_page(bio, page, PAGE_SIZE, 0);
 	if (ret != PAGE_SIZE) {
 leave_with_eio:

fs/btrfs/volumes.c

@@ -6023,7 +6023,7 @@ static void btrfs_end_bio(struct bio *bio)
 				else
 					btrfs_dev_stat_inc(dev,
 						BTRFS_DEV_STAT_READ_ERRS);
-				if ((bio->bi_opf & WRITE_FLUSH) == WRITE_FLUSH)
+				if (bio->bi_opf & REQ_PREFLUSH)
 					btrfs_dev_stat_inc(dev,
 						BTRFS_DEV_STAT_FLUSH_ERRS);
 				btrfs_dev_stat_print_on_error(dev);
@@ -6100,7 +6100,7 @@ static noinline void btrfs_schedule_bio(struct btrfs_root *root,
 	bio->bi_next = NULL;
 
 	spin_lock(&device->io_lock);
-	if (bio->bi_opf & REQ_SYNC)
+	if (op_is_sync(bio->bi_opf))
 		pending_bios = &device->pending_sync_bios;
 	else
 		pending_bios = &device->pending_bios;

fs/btrfs/volumes.h

@@ -62,7 +62,7 @@ struct btrfs_device {
 	int running_pending;
 	/* regular prio bios */
 	struct btrfs_pending_bios pending_bios;
-	/* WRITE_SYNC bios */
+	/* sync bios */
 	struct btrfs_pending_bios pending_sync_bios;
 
 	struct block_device *bdev;