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, 19 insertions, 51 deletions

diff --git a/fs/buffer.c b/fs/buffer.c
index 49b7e9bdcd1d..1c18a22a6013 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -253,27 +253,6 @@ out:
 }
 
 /*
- * Kick the writeback threads then try to free up some ZONE_NORMAL memory.
- */
-static void free_more_memory(void)
-{
-	struct zoneref *z;
-	int nid;
-
-	wakeup_flusher_threads(1024, WB_REASON_FREE_MORE_MEM);
-	yield();
-
-	for_each_online_node(nid) {
-
-		z = first_zones_zonelist(node_zonelist(nid, GFP_NOFS),
-						gfp_zone(GFP_NOFS), NULL);
-		if (z->zone)
-			try_to_free_pages(node_zonelist(nid, GFP_NOFS), 0,
-						GFP_NOFS, NULL);
-	}
-}
-
-/*
  * I/O completion handler for block_read_full_page() - pages
  * which come unlocked at the end of I/O.
  */
@@ -861,16 +840,19 @@ int remove_inode_buffers(struct inode *inode)
  * which may not fail from ordinary buffer allocations.
  */
 struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size,
-		int retry)
+		bool retry)
 {
 	struct buffer_head *bh, *head;
+	gfp_t gfp = GFP_NOFS;
 	long offset;
 
-try_again:
+	if (retry)
+		gfp |= __GFP_NOFAIL;
+
 	head = NULL;
 	offset = PAGE_SIZE;
 	while ((offset -= size) >= 0) {
-		bh = alloc_buffer_head(GFP_NOFS);
+		bh = alloc_buffer_head(gfp);
 		if (!bh)
 			goto no_grow;
 
@@ -896,23 +878,7 @@ no_grow:
 		} while (head);
 	}
 
-	/*
-	 * Return failure for non-async IO requests.  Async IO requests
-	 * are not allowed to fail, so we have to wait until buffer heads
-	 * become available.  But we don't want tasks sleeping with 
-	 * partially complete buffers, so all were released above.
-	 */
-	if (!retry)
-		return NULL;
-
-	/* We're _really_ low on memory. Now we just
-	 * wait for old buffer heads to become free due to
-	 * finishing IO.  Since this is an async request and
-	 * the reserve list is empty, we're sure there are 
-	 * async buffer heads in use.
-	 */
-	free_more_memory();
-	goto try_again;
+	return NULL;
 }
 EXPORT_SYMBOL_GPL(alloc_page_buffers);
 
@@ -1001,8 +967,6 @@ grow_dev_page(struct block_device *bdev, sector_t block,
 	gfp_mask |= __GFP_NOFAIL;
 
 	page = find_or_create_page(inode->i_mapping, index, gfp_mask);
-	if (!page)
-		return ret;
 
 	BUG_ON(!PageLocked(page));
 
@@ -1021,9 +985,7 @@ grow_dev_page(struct block_device *bdev, sector_t block,
 	/*
 	 * Allocate some buffers for this page
 	 */
-	bh = alloc_page_buffers(page, size, 0);
-	if (!bh)
-		goto failed;
+	bh = alloc_page_buffers(page, size, true);
 
 	/*
 	 * Link the page to the buffers and initialise them.  Take the
@@ -1103,8 +1065,6 @@ __getblk_slow(struct block_device *bdev, sector_t block,
 		ret = grow_buffers(bdev, block, size, gfp);
 		if (ret < 0)
 			return NULL;
-		if (ret == 0)
-			free_more_memory();
 	}
 }
 
@@ -1575,7 +1535,7 @@ void create_empty_buffers(struct page *page,
 {
 	struct buffer_head *bh, *head, *tail;
 
-	head = alloc_page_buffers(page, blocksize, 1);
+	head = alloc_page_buffers(page, blocksize, true);
 	bh = head;
 	do {
 		bh->b_state |= b_state;
@@ -2639,7 +2599,7 @@ int nobh_write_begin(struct address_space *mapping,
 	 * Be careful: the buffer linked list is a NULL terminated one, rather
 	 * than the circular one we're used to.
 	 */
-	head = alloc_page_buffers(page, blocksize, 0);
+	head = alloc_page_buffers(page, blocksize, false);
 	if (!head) {
 		ret = -ENOMEM;
 		goto out_release;
@@ -3056,8 +3016,16 @@ void guard_bio_eod(int op, struct bio *bio)
 	sector_t maxsector;
 	struct bio_vec *bvec = &bio->bi_io_vec[bio->bi_vcnt - 1];
 	unsigned truncated_bytes;
+	struct hd_struct *part;
+
+	rcu_read_lock();
+	part = __disk_get_part(bio->bi_disk, bio->bi_partno);
+	if (part)
+		maxsector = part_nr_sects_read(part);
+	else
+		maxsector = get_capacity(bio->bi_disk);
+	rcu_read_unlock();
 
-	maxsector = get_capacity(bio->bi_disk);
 	if (!maxsector)
 		return;