Merge branch 'for-4.13/block' of git://git.kernel.dk/linux-block

Pull core block/IO updates from Jens Axboe:
 "This is the main pull request for the block layer for 4.13. Not a huge
  round in terms of features, but there's a lot of churn related to some
  core cleanups.

  Note this depends on the UUID tree pull request, that Christoph
  already sent out.

  This pull request contains:

   - A series from Christoph, unifying the error/stats codes in the
     block layer. We now use blk_status_t everywhere, instead of using
     different schemes for different places.

   - Also from Christoph, some cleanups around request allocation and IO
     scheduler interactions in blk-mq.

   - And yet another series from Christoph, cleaning up how we handle
     and do bounce buffering in the block layer.

   - A blk-mq debugfs series from Bart, further improving on the support
     we have for exporting internal information to aid debugging IO
     hangs or stalls.

   - Also from Bart, a series that cleans up the request initialization
     differences across types of devices.

   - A series from Goldwyn Rodrigues, allowing the block layer to return
     failure if we will block and the user asked for non-blocking.

   - Patch from Hannes for supporting setting loop devices block size to
     that of the underlying device.

   - Two series of patches from Javier, fixing various issues with
     lightnvm, particular around pblk.

   - A series from me, adding support for write hints. This comes with
     NVMe support as well, so applications can help guide data placement
     on flash to improve performance, latencies, and write
     amplification.

   - A series from Ming, improving and hardening blk-mq support for
     stopping/starting and quiescing hardware queues.

   - Two pull requests for NVMe updates. Nothing major on the feature
     side, but lots of cleanups and bug fixes. From the usual crew.

   - A series from Neil Brown, greatly improving the bio rescue set
     support. Most notably, this kills the bio rescue work queues, if we
     don't really need them.

   - Lots of other little bug fixes that are all over the place"

* 'for-4.13/block' of git://git.kernel.dk/linux-block: (217 commits)
  lightnvm: pblk: set line bitmap check under debug
  lightnvm: pblk: verify that cache read is still valid
  lightnvm: pblk: add initialization check
  lightnvm: pblk: remove target using async. I/Os
  lightnvm: pblk: use vmalloc for GC data buffer
  lightnvm: pblk: use right metadata buffer for recovery
  lightnvm: pblk: schedule if data is not ready
  lightnvm: pblk: remove unused return variable
  lightnvm: pblk: fix double-free on pblk init
  lightnvm: pblk: fix bad le64 assignations
  nvme: Makefile: remove dead build rule
  blk-mq: map all HWQ also in hyperthreaded system
  nvmet-rdma: register ib_client to not deadlock in device removal
  nvme_fc: fix error recovery on link down.
  nvmet_fc: fix crashes on bad opcodes
  nvme_fc: Fix crash when nvme controller connection fails.
  nvme_fc: replace ioabort msleep loop with completion
  nvme_fc: fix double calls to nvme_cleanup_cmd()
  nvme-fabrics: verify that a controller returns the correct NQN
  nvme: simplify nvme_dev_attrs_are_visible
  ...

1 files changed, 42 insertions, 40 deletions

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index ef3c98c527c1..556c93060606 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -842,13 +842,12 @@ retry:
 				NULL, EXTENT_LOCKED | EXTENT_DELALLOC,
 				PAGE_UNLOCK | PAGE_CLEAR_DIRTY |
 				PAGE_SET_WRITEBACK);
-		ret = btrfs_submit_compressed_write(inode,
+		if (btrfs_submit_compressed_write(inode,
 				    async_extent->start,
 				    async_extent->ram_size,
 				    ins.objectid,
 				    ins.offset, async_extent->pages,
-				    async_extent->nr_pages);
-		if (ret) {
+				    async_extent->nr_pages)) {
 			struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
 			struct page *p = async_extent->pages[0];
 			const u64 start = async_extent->start;
@@ -1901,11 +1900,11 @@ int btrfs_merge_bio_hook(struct page *page, unsigned long offset,
  * At IO completion time the cums attached on the ordered extent record
  * are inserted into the btree
  */
-static int __btrfs_submit_bio_start(struct inode *inode, struct bio *bio,
-				    int mirror_num, unsigned long bio_flags,
-				    u64 bio_offset)
+static blk_status_t __btrfs_submit_bio_start(struct inode *inode,
+		struct bio *bio, int mirror_num, unsigned long bio_flags,
+		u64 bio_offset)
 {
-	int ret = 0;
+	blk_status_t ret = 0;
 
 	ret = btrfs_csum_one_bio(inode, bio, 0, 0);
 	BUG_ON(ret); /* -ENOMEM */
@@ -1920,16 +1919,16 @@ static int __btrfs_submit_bio_start(struct inode *inode, struct bio *bio,
  * At IO completion time the cums attached on the ordered extent record
  * are inserted into the btree
  */
-static int __btrfs_submit_bio_done(struct inode *inode, struct bio *bio,
-			  int mirror_num, unsigned long bio_flags,
-			  u64 bio_offset)
+static blk_status_t __btrfs_submit_bio_done(struct inode *inode,
+		struct bio *bio, int mirror_num, unsigned long bio_flags,
+		u64 bio_offset)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	int ret;
+	blk_status_t ret;
 
 	ret = btrfs_map_bio(fs_info, bio, mirror_num, 1);
 	if (ret) {
-		bio->bi_error = ret;
+		bio->bi_status = ret;
 		bio_endio(bio);
 	}
 	return ret;
@@ -1939,14 +1938,14 @@ static int __btrfs_submit_bio_done(struct inode *inode, struct bio *bio,
  * extent_io.c submission hook. This does the right thing for csum calculation
  * on write, or reading the csums from the tree before a read
  */
-static int btrfs_submit_bio_hook(struct inode *inode, struct bio *bio,
+static blk_status_t btrfs_submit_bio_hook(struct inode *inode, struct bio *bio,
 			  int mirror_num, unsigned long bio_flags,
 			  u64 bio_offset)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	enum btrfs_wq_endio_type metadata = BTRFS_WQ_ENDIO_DATA;
-	int ret = 0;
+	blk_status_t ret = 0;
 	int skip_sum;
 	int async = !atomic_read(&BTRFS_I(inode)->sync_writers);
 
@@ -1991,8 +1990,8 @@ mapit:
 	ret = btrfs_map_bio(fs_info, bio, mirror_num, 0);
 
 out:
-	if (ret < 0) {
-		bio->bi_error = ret;
+	if (ret) {
+		bio->bi_status = ret;
 		bio_endio(bio);
 	}
 	return ret;
@@ -8037,7 +8036,7 @@ static void btrfs_retry_endio_nocsum(struct bio *bio)
 	struct bio_vec *bvec;
 	int i;
 
-	if (bio->bi_error)
+	if (bio->bi_status)
 		goto end;
 
 	ASSERT(bio->bi_vcnt == 1);
@@ -8116,7 +8115,7 @@ static void btrfs_retry_endio(struct bio *bio)
 	int ret;
 	int i;
 
-	if (bio->bi_error)
+	if (bio->bi_status)
 		goto end;
 
 	uptodate = 1;
@@ -8141,8 +8140,8 @@ end:
 	bio_put(bio);
 }
 
-static int __btrfs_subio_endio_read(struct inode *inode,
-				    struct btrfs_io_bio *io_bio, int err)
+static blk_status_t __btrfs_subio_endio_read(struct inode *inode,
+		struct btrfs_io_bio *io_bio, blk_status_t err)
 {
 	struct btrfs_fs_info *fs_info;
 	struct bio_vec *bvec;
@@ -8184,7 +8183,7 @@ try_again:
 				io_bio->mirror_num,
 				btrfs_retry_endio, &done);
 		if (ret) {
-			err = ret;
+			err = errno_to_blk_status(ret);
 			goto next;
 		}
 
@@ -8211,8 +8210,8 @@ next:
 	return err;
 }
 
-static int btrfs_subio_endio_read(struct inode *inode,
-				  struct btrfs_io_bio *io_bio, int err)
+static blk_status_t btrfs_subio_endio_read(struct inode *inode,
+		struct btrfs_io_bio *io_bio, blk_status_t err)
 {
 	bool skip_csum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
 
@@ -8232,7 +8231,7 @@ static void btrfs_endio_direct_read(struct bio *bio)
 	struct inode *inode = dip->inode;
 	struct bio *dio_bio;
 	struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
-	int err = bio->bi_error;
+	blk_status_t err = bio->bi_status;
 
 	if (dip->flags & BTRFS_DIO_ORIG_BIO_SUBMITTED)
 		err = btrfs_subio_endio_read(inode, io_bio, err);
@@ -8243,11 +8242,11 @@ static void btrfs_endio_direct_read(struct bio *bio)
 
 	kfree(dip);
 
-	dio_bio->bi_error = bio->bi_error;
-	dio_end_io(dio_bio, bio->bi_error);
+	dio_bio->bi_status = bio->bi_status;
+	dio_end_io(dio_bio);
 
 	if (io_bio->end_io)
-		io_bio->end_io(io_bio, err);
+		io_bio->end_io(io_bio, blk_status_to_errno(err));
 	bio_put(bio);
 }
 
@@ -8299,20 +8298,20 @@ static void btrfs_endio_direct_write(struct bio *bio)
 	struct bio *dio_bio = dip->dio_bio;
 
 	__endio_write_update_ordered(dip->inode, dip->logical_offset,
-				     dip->bytes, !bio->bi_error);
+				     dip->bytes, !bio->bi_status);
 
 	kfree(dip);
 
-	dio_bio->bi_error = bio->bi_error;
-	dio_end_io(dio_bio, bio->bi_error);
+	dio_bio->bi_status = bio->bi_status;
+	dio_end_io(dio_bio);
 	bio_put(bio);
 }
 
-static int __btrfs_submit_bio_start_direct_io(struct inode *inode,
+static blk_status_t __btrfs_submit_bio_start_direct_io(struct inode *inode,
 				    struct bio *bio, int mirror_num,
 				    unsigned long bio_flags, u64 offset)
 {
-	int ret;
+	blk_status_t ret;
 	ret = btrfs_csum_one_bio(inode, bio, offset, 1);
 	BUG_ON(ret); /* -ENOMEM */
 	return 0;
@@ -8321,7 +8320,7 @@ static int __btrfs_submit_bio_start_direct_io(struct inode *inode,
 static void btrfs_end_dio_bio(struct bio *bio)
 {
 	struct btrfs_dio_private *dip = bio->bi_private;
-	int err = bio->bi_error;
+	blk_status_t err = bio->bi_status;
 
 	if (err)
 		btrfs_warn(BTRFS_I(dip->inode)->root->fs_info,
@@ -8351,7 +8350,7 @@ static void btrfs_end_dio_bio(struct bio *bio)
 	if (dip->errors) {
 		bio_io_error(dip->orig_bio);
 	} else {
-		dip->dio_bio->bi_error = 0;
+		dip->dio_bio->bi_status = 0;
 		bio_endio(dip->orig_bio);
 	}
 out:
@@ -8368,14 +8367,14 @@ static struct bio *btrfs_dio_bio_alloc(struct block_device *bdev,
 	return bio;
 }
 
-static inline int btrfs_lookup_and_bind_dio_csum(struct inode *inode,
+static inline blk_status_t btrfs_lookup_and_bind_dio_csum(struct inode *inode,
 						 struct btrfs_dio_private *dip,
 						 struct bio *bio,
 						 u64 file_offset)
 {
 	struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
 	struct btrfs_io_bio *orig_io_bio = btrfs_io_bio(dip->orig_bio);
-	int ret;
+	blk_status_t ret;
 
 	/*
 	 * We load all the csum data we need when we submit
@@ -8406,7 +8405,7 @@ static inline int __btrfs_submit_dio_bio(struct bio *bio, struct inode *inode,
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_dio_private *dip = bio->bi_private;
 	bool write = bio_op(bio) == REQ_OP_WRITE;
-	int ret;
+	blk_status_t ret;
 
 	if (async_submit)
 		async_submit = !atomic_read(&BTRFS_I(inode)->sync_writers);
@@ -8649,7 +8648,7 @@ free_ordered:
 	 * callbacks - they require an allocated dip and a clone of dio_bio.
 	 */
 	if (io_bio && dip) {
-		io_bio->bi_error = -EIO;
+		io_bio->bi_status = BLK_STS_IOERR;
 		bio_endio(io_bio);
 		/*
 		 * The end io callbacks free our dip, do the final put on io_bio
@@ -8668,12 +8667,12 @@ free_ordered:
 			unlock_extent(&BTRFS_I(inode)->io_tree, file_offset,
 			      file_offset + dio_bio->bi_iter.bi_size - 1);
 
-		dio_bio->bi_error = -EIO;
+		dio_bio->bi_status = BLK_STS_IOERR;
 		/*
 		 * Releases and cleans up our dio_bio, no need to bio_put()
 		 * nor bio_endio()/bio_io_error() against dio_bio.
 		 */
-		dio_end_io(dio_bio, ret);
+		dio_end_io(dio_bio);
 	}
 	if (io_bio)
 		bio_put(io_bio);
@@ -8755,6 +8754,9 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 			dio_data.overwrite = 1;
 			inode_unlock(inode);
 			relock = true;
+		} else if (iocb->ki_flags & IOCB_NOWAIT) {
+			ret = -EAGAIN;
+			goto out;
 		}
 		ret = btrfs_delalloc_reserve_space(inode, offset, count);
 		if (ret)