Merge branch 'for-4.16/block' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:
 "This is the main pull request for block IO related changes for the
  4.16 kernel. Nothing major in this pull request, but a good amount of
  improvements and fixes all over the map. This contains:

   - BFQ improvements, fixes, and cleanups from Angelo, Chiara, and
     Paolo.

   - Support for SMR zones for deadline and mq-deadline from Damien and
     Christoph.

   - Set of fixes for bcache by way of Michael Lyle, including fixes
     from himself, Kent, Rui, Tang, and Coly.

   - Series from Matias for lightnvm with fixes from Hans Holmberg,
     Javier, and Matias. Mostly centered around pblk, and the removing
     rrpc 1.2 in preparation for supporting 2.0.

   - A couple of NVMe pull requests from Christoph. Nothing major in
     here, just fixes and cleanups, and support for command tracing from
     Johannes.

   - Support for blk-throttle for tracking reads and writes separately.
     From Joseph Qi. A few cleanups/fixes also for blk-throttle from
     Weiping.

   - Series from Mike Snitzer that enables dm to register its queue more
     logically, something that's alwways been problematic on dm since
     it's a stacked device.

   - Series from Ming cleaning up some of the bio accessor use, in
     preparation for supporting multipage bvecs.

   - Various fixes from Ming closing up holes around queue mapping and
     quiescing.

   - BSD partition fix from Richard Narron, fixing a problem where we
     can't mount newer (10/11) FreeBSD partitions.

   - Series from Tejun reworking blk-mq timeout handling. The previous
     scheme relied on atomic bits, but it had races where we would think
     a request had timed out if it to reused at the wrong time.

   - null_blk now supports faking timeouts, to enable us to better
     exercise and test that functionality separately. From me.

   - Kill the separate atomic poll bit in the request struct. After
     this, we don't use the atomic bits on blk-mq anymore at all. From
     me.

   - sgl_alloc/free helpers from Bart.

   - Heavily contended tag case scalability improvement from me.

   - Various little fixes and cleanups from Arnd, Bart, Corentin,
     Douglas, Eryu, Goldwyn, and myself"

* 'for-4.16/block' of git://git.kernel.dk/linux-block: (186 commits)
  block: remove smart1,2.h
  nvme: add tracepoint for nvme_complete_rq
  nvme: add tracepoint for nvme_setup_cmd
  nvme-pci: introduce RECONNECTING state to mark initializing procedure
  nvme-rdma: remove redundant boolean for inline_data
  nvme: don't free uuid pointer before printing it
  nvme-pci: Suspend queues after deleting them
  bsg: use pr_debug instead of hand crafted macros
  blk-mq-debugfs: don't allow write on attributes with seq_operations set
  nvme-pci: Fix queue double allocations
  block: Set BIO_TRACE_COMPLETION on new bio during split
  blk-throttle: use queue_is_rq_based
  block: Remove kblockd_schedule_delayed_work{,_on}()
  blk-mq: Avoid that blk_mq_delay_run_hw_queue() introduces unintended delays
  blk-mq: Rename blk_mq_request_direct_issue() into blk_mq_request_issue_directly()
  lib/scatterlist: Fix chaining support in sgl_alloc_order()
  blk-throttle: track read and write request individually
  block: add bdev_read_only() checks to common helpers
  block: fail op_is_write() requests to read-only partitions
  blk-throttle: export io_serviced_recursive, io_service_bytes_recursive
  ...

fs/btrfs/compression.c

@@ -411,7 +411,7 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
 
 static u64 bio_end_offset(struct bio *bio)
 {
-	struct bio_vec *last = &bio->bi_io_vec[bio->bi_vcnt - 1];
+	struct bio_vec *last = bio_last_bvec_all(bio);
 
 	return page_offset(last->bv_page) + last->bv_len + last->bv_offset;
 }
@@ -563,7 +563,7 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	/* we need the actual starting offset of this extent in the file */
 	read_lock(&em_tree->lock);
 	em = lookup_extent_mapping(em_tree,
-				   page_offset(bio->bi_io_vec->bv_page),
+				   page_offset(bio_first_page_all(bio)),
 				   PAGE_SIZE);
 	read_unlock(&em_tree->lock);
 	if (!em)

fs/btrfs/extent_io.c

@@ -2257,7 +2257,7 @@ int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end,
 	return 0;
 }
 
-bool btrfs_check_repairable(struct inode *inode, struct bio *failed_bio,
+bool btrfs_check_repairable(struct inode *inode, unsigned failed_bio_pages,
 			   struct io_failure_record *failrec, int failed_mirror)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
@@ -2281,7 +2281,7 @@ bool btrfs_check_repairable(struct inode *inode, struct bio *failed_bio,
 	 *	a) deliver good data to the caller
 	 *	b) correct the bad sectors on disk
 	 */
-	if (failed_bio->bi_vcnt > 1) {
+	if (failed_bio_pages > 1) {
 		/*
 		 * to fulfill b), we need to know the exact failing sectors, as
 		 * we don't want to rewrite any more than the failed ones. thus,
@@ -2374,6 +2374,7 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
 	int read_mode = 0;
 	blk_status_t status;
 	int ret;
+	unsigned failed_bio_pages = bio_pages_all(failed_bio);
 
 	BUG_ON(bio_op(failed_bio) == REQ_OP_WRITE);
 
@@ -2381,13 +2382,13 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
 	if (ret)
 		return ret;
 
-	if (!btrfs_check_repairable(inode, failed_bio, failrec,
+	if (!btrfs_check_repairable(inode, failed_bio_pages, failrec,
 				    failed_mirror)) {
 		free_io_failure(failure_tree, tree, failrec);
 		return -EIO;
 	}
 
-	if (failed_bio->bi_vcnt > 1)
+	if (failed_bio_pages > 1)
 		read_mode |= REQ_FAILFAST_DEV;
 
 	phy_offset >>= inode->i_sb->s_blocksize_bits;
@@ -2724,7 +2725,7 @@ static int __must_check submit_one_bio(struct bio *bio, int mirror_num,
 				       unsigned long bio_flags)
 {
 	blk_status_t ret = 0;
-	struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
+	struct bio_vec *bvec = bio_last_bvec_all(bio);
 	struct page *page = bvec->bv_page;
 	struct extent_io_tree *tree = bio->bi_private;
 	u64 start;

fs/btrfs/extent_io.h

@@ -540,7 +540,7 @@ void btrfs_free_io_failure_record(struct btrfs_inode *inode, u64 start,
 		u64 end);
 int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end,
 				struct io_failure_record **failrec_ret);
-bool btrfs_check_repairable(struct inode *inode, struct bio *failed_bio,
+bool btrfs_check_repairable(struct inode *inode, unsigned failed_bio_pages,
 			    struct io_failure_record *failrec, int fail_mirror);
 struct bio *btrfs_create_repair_bio(struct inode *inode, struct bio *failed_bio,
 				    struct io_failure_record *failrec,

fs/btrfs/inode.c

@@ -8015,6 +8015,7 @@ static blk_status_t dio_read_error(struct inode *inode, struct bio *failed_bio,
 	int segs;
 	int ret;
 	blk_status_t status;
+	struct bio_vec bvec;
 
 	BUG_ON(bio_op(failed_bio) == REQ_OP_WRITE);
 
@@ -8030,8 +8031,9 @@ static blk_status_t dio_read_error(struct inode *inode, struct bio *failed_bio,
 	}
 
 	segs = bio_segments(failed_bio);
+	bio_get_first_bvec(failed_bio, &bvec);
 	if (segs > 1 ||
-	    (failed_bio->bi_io_vec->bv_len > btrfs_inode_sectorsize(inode)))
+	    (bvec.bv_len > btrfs_inode_sectorsize(inode)))
 		read_mode |= REQ_FAILFAST_DEV;
 
 	isector = start - btrfs_io_bio(failed_bio)->logical;
@@ -8074,7 +8076,7 @@ static void btrfs_retry_endio_nocsum(struct bio *bio)
 	ASSERT(bio->bi_vcnt == 1);
 	io_tree = &BTRFS_I(inode)->io_tree;
 	failure_tree = &BTRFS_I(inode)->io_failure_tree;
-	ASSERT(bio->bi_io_vec->bv_len == btrfs_inode_sectorsize(inode));
+	ASSERT(bio_first_bvec_all(bio)->bv_len == btrfs_inode_sectorsize(inode));
 
 	done->uptodate = 1;
 	ASSERT(!bio_flagged(bio, BIO_CLONED));
@@ -8164,7 +8166,7 @@ static void btrfs_retry_endio(struct bio *bio)
 	uptodate = 1;
 
 	ASSERT(bio->bi_vcnt == 1);
-	ASSERT(bio->bi_io_vec->bv_len == btrfs_inode_sectorsize(done->inode));
+	ASSERT(bio_first_bvec_all(bio)->bv_len == btrfs_inode_sectorsize(done->inode));
 
 	io_tree = &BTRFS_I(inode)->io_tree;
 	failure_tree = &BTRFS_I(inode)->io_failure_tree;