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, 84 insertions, 69 deletions

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 245c430a2e41..08f5debd07d1 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -933,33 +933,36 @@ static void bdi_split_work_to_wbs(struct backing_dev_info *bdi,
 
 #endif	/* CONFIG_CGROUP_WRITEBACK */
 
-void wb_start_writeback(struct bdi_writeback *wb, long nr_pages,
-			bool range_cyclic, enum wb_reason reason)
+/*
+ * Add in the number of potentially dirty inodes, because each inode
+ * write can dirty pagecache in the underlying blockdev.
+ */
+static unsigned long get_nr_dirty_pages(void)
 {
-	struct wb_writeback_work *work;
+	return global_node_page_state(NR_FILE_DIRTY) +
+		global_node_page_state(NR_UNSTABLE_NFS) +
+		get_nr_dirty_inodes();
+}
 
+static void wb_start_writeback(struct bdi_writeback *wb, enum wb_reason reason)
+{
 	if (!wb_has_dirty_io(wb))
 		return;
 
 	/*
-	 * This is WB_SYNC_NONE writeback, so if allocation fails just
-	 * wakeup the thread for old dirty data writeback
+	 * All callers of this function want to start writeback of all
+	 * dirty pages. Places like vmscan can call this at a very
+	 * high frequency, causing pointless allocations of tons of
+	 * work items and keeping the flusher threads busy retrieving
+	 * that work. Ensure that we only allow one of them pending and
+	 * inflight at the time.
 	 */
-	work = kzalloc(sizeof(*work),
-		       GFP_NOWAIT | __GFP_NOMEMALLOC | __GFP_NOWARN);
-	if (!work) {
-		trace_writeback_nowork(wb);
-		wb_wakeup(wb);
+	if (test_bit(WB_start_all, &wb->state) ||
+	    test_and_set_bit(WB_start_all, &wb->state))
 		return;
-	}
-
-	work->sync_mode	= WB_SYNC_NONE;
-	work->nr_pages	= nr_pages;
-	work->range_cyclic = range_cyclic;
-	work->reason	= reason;
-	work->auto_free	= 1;
 
-	wb_queue_work(wb, work);
+	wb->start_all_reason = reason;
+	wb_wakeup(wb);
 }
 
 /**
@@ -1814,17 +1817,6 @@ static struct wb_writeback_work *get_next_work_item(struct bdi_writeback *wb)
 	return work;
 }
 
-/*
- * Add in the number of potentially dirty inodes, because each inode
- * write can dirty pagecache in the underlying blockdev.
- */
-static unsigned long get_nr_dirty_pages(void)
-{
-	return global_node_page_state(NR_FILE_DIRTY) +
-		global_node_page_state(NR_UNSTABLE_NFS) +
-		get_nr_dirty_inodes();
-}
-
 static long wb_check_background_flush(struct bdi_writeback *wb)
 {
 	if (wb_over_bg_thresh(wb)) {
@@ -1877,6 +1869,30 @@ static long wb_check_old_data_flush(struct bdi_writeback *wb)
 	return 0;
 }
 
+static long wb_check_start_all(struct bdi_writeback *wb)
+{
+	long nr_pages;
+
+	if (!test_bit(WB_start_all, &wb->state))
+		return 0;
+
+	nr_pages = get_nr_dirty_pages();
+	if (nr_pages) {
+		struct wb_writeback_work work = {
+			.nr_pages	= wb_split_bdi_pages(wb, nr_pages),
+			.sync_mode	= WB_SYNC_NONE,
+			.range_cyclic	= 1,
+			.reason		= wb->start_all_reason,
+		};
+
+		nr_pages = wb_writeback(wb, &work);
+	}
+
+	clear_bit(WB_start_all, &wb->state);
+	return nr_pages;
+}
+
+
 /*
  * Retrieve work items and do the writeback they describe
  */
@@ -1893,6 +1909,11 @@ static long wb_do_writeback(struct bdi_writeback *wb)
 	}
 
 	/*
+	 * Check for a flush-everything request
+	 */
+	wrote += wb_check_start_all(wb);
+
+	/*
 	 * Check for periodic writeback, kupdated() style
 	 */
 	wrote += wb_check_old_data_flush(wb);
@@ -1947,10 +1968,33 @@ void wb_workfn(struct work_struct *work)
 }
 
 /*
- * Start writeback of `nr_pages' pages.  If `nr_pages' is zero, write back
- * the whole world.
+ * Start writeback of `nr_pages' pages on this bdi. If `nr_pages' is zero,
+ * write back the whole world.
  */
-void wakeup_flusher_threads(long nr_pages, enum wb_reason reason)
+static void __wakeup_flusher_threads_bdi(struct backing_dev_info *bdi,
+					 enum wb_reason reason)
+{
+	struct bdi_writeback *wb;
+
+	if (!bdi_has_dirty_io(bdi))
+		return;
+
+	list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node)
+		wb_start_writeback(wb, reason);
+}
+
+void wakeup_flusher_threads_bdi(struct backing_dev_info *bdi,
+				enum wb_reason reason)
+{
+	rcu_read_lock();
+	__wakeup_flusher_threads_bdi(bdi, reason);
+	rcu_read_unlock();
+}
+
+/*
+ * Wakeup the flusher threads to start writeback of all currently dirty pages
+ */
+void wakeup_flusher_threads(enum wb_reason reason)
 {
 	struct backing_dev_info *bdi;
 
@@ -1960,20 +2004,9 @@ void wakeup_flusher_threads(long nr_pages, enum wb_reason reason)
 	if (blk_needs_flush_plug(current))
 		blk_schedule_flush_plug(current);
 
-	if (!nr_pages)
-		nr_pages = get_nr_dirty_pages();
-
 	rcu_read_lock();
-	list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) {
-		struct bdi_writeback *wb;
-
-		if (!bdi_has_dirty_io(bdi))
-			continue;
-
-		list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node)
-			wb_start_writeback(wb, wb_split_bdi_pages(wb, nr_pages),
-					   false, reason);
-	}
+	list_for_each_entry_rcu(bdi, &bdi_list, bdi_list)
+		__wakeup_flusher_threads_bdi(bdi, reason);
 	rcu_read_unlock();
 }
 
@@ -2343,37 +2376,19 @@ void writeback_inodes_sb(struct super_block *sb, enum wb_reason reason)
 EXPORT_SYMBOL(writeback_inodes_sb);
 
 /**
- * try_to_writeback_inodes_sb_nr - try to start writeback if none underway
+ * try_to_writeback_inodes_sb - try to start writeback if none underway
  * @sb: the superblock
- * @nr: the number of pages to write
- * @reason: the reason of writeback
+ * @reason: reason why some writeback work was initiated
  *
- * Invoke writeback_inodes_sb_nr if no writeback is currently underway.
- * Returns 1 if writeback was started, 0 if not.
+ * Invoke __writeback_inodes_sb_nr if no writeback is currently underway.
  */
-bool try_to_writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr,
-				   enum wb_reason reason)
+void try_to_writeback_inodes_sb(struct super_block *sb, enum wb_reason reason)
 {
 	if (!down_read_trylock(&sb->s_umount))
-		return false;
+		return;
 
-	__writeback_inodes_sb_nr(sb, nr, reason, true);
+	__writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason, true);
 	up_read(&sb->s_umount);
-	return true;
-}
-EXPORT_SYMBOL(try_to_writeback_inodes_sb_nr);
-
-/**
- * try_to_writeback_inodes_sb - try to start writeback if none underway
- * @sb: the superblock
- * @reason: reason why some writeback work was initiated
- *
- * Implement by try_to_writeback_inodes_sb_nr()
- * Returns 1 if writeback was started, 0 if not.
- */
-bool try_to_writeback_inodes_sb(struct super_block *sb, enum wb_reason reason)
-{
-	return try_to_writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason);
 }
 EXPORT_SYMBOL(try_to_writeback_inodes_sb);