Merge branch 'for-3.19/core' of git://git.kernel.dk/linux-block

Pull block driver core update from Jens Axboe:
 "This is the pull request for the core block IO changes for 3.19.  Not
  a huge round this time, mostly lots of little good fixes:

   - Fix a bug in sysfs blktrace interface causing a NULL pointer
     dereference, when enabled/disabled through that API.  From Arianna
     Avanzini.

   - Various updates/fixes/improvements for blk-mq:

        - A set of updates from Bart, mostly fixing buts in the tag
          handling.

        - Cleanup/code consolidation from Christoph.

        - Extend queue_rq API to be able to handle batching issues of IO
          requests. NVMe will utilize this shortly. From me.

        - A few tag and request handling updates from me.

        - Cleanup of the preempt handling for running queues from Paolo.

        - Prevent running of unmapped hardware queues from Ming Lei.

        - Move the kdump memory limiting check to be in the correct
          location, from Shaohua.

        - Initialize all software queues at init time from Takashi. This
          prevents a kobject warning when CPUs are brought online that
          weren't online when a queue was registered.

   - Single writeback fix for I_DIRTY clearing from Tejun.  Queued with
     the core IO changes, since it's just a single fix.

   - Version X of the __bio_add_page() segment addition retry from
     Maurizio.  Hope the Xth time is the charm.

   - Documentation fixup for IO scheduler merging from Jan.

   - Introduce (and use) generic IO stat accounting helpers for non-rq
     drivers, from Gu Zheng.

   - Kill off artificial limiting of max sectors in a request from
     Christoph"

* 'for-3.19/core' of git://git.kernel.dk/linux-block: (26 commits)
  bio: modify __bio_add_page() to accept pages that don't start a new segment
  blk-mq: Fix uninitialized kobject at CPU hotplugging
  blktrace: don't let the sysfs interface remove trace from running list
  blk-mq: Use all available hardware queues
  blk-mq: Micro-optimize bt_get()
  blk-mq: Fix a race between bt_clear_tag() and bt_get()
  blk-mq: Avoid that __bt_get_word() wraps multiple times
  blk-mq: Fix a use-after-free
  blk-mq: prevent unmapped hw queue from being scheduled
  blk-mq: re-check for available tags after running the hardware queue
  blk-mq: fix hang in bt_get()
  blk-mq: move the kdump check to blk_mq_alloc_tag_set
  blk-mq: cleanup tag free handling
  blk-mq: use 'nr_cpu_ids' as highest CPU ID count for hwq <-> cpu map
  blk: introduce generic io stat accounting help function
  blk-mq: handle the single queue case in blk_mq_hctx_next_cpu
  genhd: check for int overflow in disk_expand_part_tbl()
  blk-mq: add blk_mq_free_hctx_request()
  blk-mq: export blk_mq_free_request()
  blk-mq: use get_cpu/put_cpu instead of preempt_disable/preempt_enable
  ...

1 files changed, 31 insertions, 29 deletions

diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 728b9a4d5f561..e3d4e4043b496 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -137,6 +137,7 @@ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx,
 static int __bt_get_word(struct blk_align_bitmap *bm, unsigned int last_tag)
 {
 	int tag, org_last_tag, end;
+	bool wrap = last_tag != 0;
 
 	org_last_tag = last_tag;
 	end = bm->depth;
@@ -148,15 +149,16 @@ restart:
 			 * We started with an offset, start from 0 to
 			 * exhaust the map.
 			 */
-			if (org_last_tag && last_tag) {
-				end = last_tag;
+			if (wrap) {
+				wrap = false;
+				end = org_last_tag;
 				last_tag = 0;
 				goto restart;
 			}
 			return -1;
 		}
 		last_tag = tag + 1;
-	} while (test_and_set_bit_lock(tag, &bm->word));
+	} while (test_and_set_bit(tag, &bm->word));
 
 	return tag;
 }
@@ -246,14 +248,29 @@ static int bt_get(struct blk_mq_alloc_data *data,
 	if (!(data->gfp & __GFP_WAIT))
 		return -1;
 
-	bs = bt_wait_ptr(bt, hctx);
 	do {
+		bs = bt_wait_ptr(bt, hctx);
 		prepare_to_wait(&bs->wait, &wait, TASK_UNINTERRUPTIBLE);
 
 		tag = __bt_get(hctx, bt, last_tag);
 		if (tag != -1)
 			break;
 
+		/*
+		 * We're out of tags on this hardware queue, kick any
+		 * pending IO submits before going to sleep waiting for
+		 * some to complete.
+		 */
+		blk_mq_run_hw_queue(hctx, false);
+
+		/*
+		 * Retry tag allocation after running the hardware queue,
+		 * as running the queue may also have found completions.
+		 */
+		tag = __bt_get(hctx, bt, last_tag);
+		if (tag != -1)
+			break;
+
 		blk_mq_put_ctx(data->ctx);
 
 		io_schedule();
@@ -268,8 +285,6 @@ static int bt_get(struct blk_mq_alloc_data *data,
 			hctx = data->hctx;
 			bt = &hctx->tags->bitmap_tags;
 		}
-		finish_wait(&bs->wait, &wait);
-		bs = bt_wait_ptr(bt, hctx);
 	} while (1);
 
 	finish_wait(&bs->wait, &wait);
@@ -340,11 +355,10 @@ static void bt_clear_tag(struct blk_mq_bitmap_tags *bt, unsigned int tag)
 	struct bt_wait_state *bs;
 	int wait_cnt;
 
-	/*
-	 * The unlock memory barrier need to order access to req in free
-	 * path and clearing tag bit
-	 */
-	clear_bit_unlock(TAG_TO_BIT(bt, tag), &bt->map[index].word);
+	clear_bit(TAG_TO_BIT(bt, tag), &bt->map[index].word);
+
+	/* Ensure that the wait list checks occur after clear_bit(). */
+	smp_mb();
 
 	bs = bt_wake_ptr(bt);
 	if (!bs)
@@ -360,21 +374,6 @@ static void bt_clear_tag(struct blk_mq_bitmap_tags *bt, unsigned int tag)
 	}
 }
 
-static void __blk_mq_put_tag(struct blk_mq_tags *tags, unsigned int tag)
-{
-	BUG_ON(tag >= tags->nr_tags);
-
-	bt_clear_tag(&tags->bitmap_tags, tag);
-}
-
-static void __blk_mq_put_reserved_tag(struct blk_mq_tags *tags,
-				      unsigned int tag)
-{
-	BUG_ON(tag >= tags->nr_reserved_tags);
-
-	bt_clear_tag(&tags->breserved_tags, tag);
-}
-
 void blk_mq_put_tag(struct blk_mq_hw_ctx *hctx, unsigned int tag,
 		    unsigned int *last_tag)
 {
@@ -383,10 +382,13 @@ void blk_mq_put_tag(struct blk_mq_hw_ctx *hctx, unsigned int tag,
 	if (tag >= tags->nr_reserved_tags) {
 		const int real_tag = tag - tags->nr_reserved_tags;
 
-		__blk_mq_put_tag(tags, real_tag);
+		BUG_ON(real_tag >= tags->nr_tags);
+		bt_clear_tag(&tags->bitmap_tags, real_tag);
 		*last_tag = real_tag;
-	} else
-		__blk_mq_put_reserved_tag(tags, tag);
+	} else {
+		BUG_ON(tag >= tags->nr_reserved_tags);
+		bt_clear_tag(&tags->breserved_tags, tag);
+	}
 }
 
 static void bt_for_each(struct blk_mq_hw_ctx *hctx,