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
  ...

Documentation/block/biodoc.txt

@@ -942,7 +942,11 @@ elevator_allow_merge_fn		called whenever the block layer determines
 				request safely. The io scheduler may still
 				want to stop a merge at this point if it
 				results in some sort of conflict internally,
-				this hook allows it to do that.
+				this hook allows it to do that. Note however
+				that two *requests* can still be merged at later
+				time. Currently the io scheduler has no way to
+				prevent that. It can only learn about the fact
+				from elevator_merge_req_fn callback.
 
 elevator_dispatch_fn*		fills the dispatch queue with ready requests.
 				I/O schedulers are free to postpone requests by

block/bio.c

@@ -748,6 +748,7 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 				}
 			}
 
+			bio->bi_iter.bi_size += len;
 			goto done;
 		}
 
@@ -764,28 +765,31 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 		return 0;
 
 	/*
-	 * we might lose a segment or two here, but rather that than
-	 * make this too complex.
+	 * setup the new entry, we might clear it again later if we
+	 * cannot add the page
+	 */
+	bvec = &bio->bi_io_vec[bio->bi_vcnt];
+	bvec->bv_page = page;
+	bvec->bv_len = len;
+	bvec->bv_offset = offset;
+	bio->bi_vcnt++;
+	bio->bi_phys_segments++;
+	bio->bi_iter.bi_size += len;
+
+	/*
+	 * Perform a recount if the number of segments is greater
+	 * than queue_max_segments(q).
 	 */
 
-	while (bio->bi_phys_segments >= queue_max_segments(q)) {
+	while (bio->bi_phys_segments > queue_max_segments(q)) {
 
 		if (retried_segments)
-			return 0;
+			goto failed;
 
 		retried_segments = 1;
 		blk_recount_segments(q, bio);
 	}
 
-	/*
-	 * setup the new entry, we might clear it again later if we
-	 * cannot add the page
-	 */
-	bvec = &bio->bi_io_vec[bio->bi_vcnt];
-	bvec->bv_page = page;
-	bvec->bv_len = len;
-	bvec->bv_offset = offset;
-
 	/*
 	 * if queue has other restrictions (eg varying max sector size
 	 * depending on offset), it can specify a merge_bvec_fn in the
@@ -795,31 +799,33 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 		struct bvec_merge_data bvm = {
 			.bi_bdev = bio->bi_bdev,
 			.bi_sector = bio->bi_iter.bi_sector,
-			.bi_size = bio->bi_iter.bi_size,
+			.bi_size = bio->bi_iter.bi_size - len,
 			.bi_rw = bio->bi_rw,
 		};
 
 		/*
 		 * merge_bvec_fn() returns number of bytes it can accept
 		 * at this offset
 		 */
-		if (q->merge_bvec_fn(q, &bvm, bvec) < bvec->bv_len) {
-			bvec->bv_page = NULL;
-			bvec->bv_len = 0;
-			bvec->bv_offset = 0;
-			return 0;
-		}
+		if (q->merge_bvec_fn(q, &bvm, bvec) < bvec->bv_len)
+			goto failed;
 	}
 
 	/* If we may be able to merge these biovecs, force a recount */
-	if (bio->bi_vcnt && (BIOVEC_PHYS_MERGEABLE(bvec-1, bvec)))
+	if (bio->bi_vcnt > 1 && (BIOVEC_PHYS_MERGEABLE(bvec-1, bvec)))
 		bio->bi_flags &= ~(1 << BIO_SEG_VALID);
 
-	bio->bi_vcnt++;
-	bio->bi_phys_segments++;
  done:
-	bio->bi_iter.bi_size += len;
 	return len;
+
+ failed:
+	bvec->bv_page = NULL;
+	bvec->bv_len = 0;
+	bvec->bv_offset = 0;
+	bio->bi_vcnt--;
+	bio->bi_iter.bi_size -= len;
+	blk_recount_segments(q, bio);
+	return 0;
 }
 
 /**
@@ -1739,6 +1745,34 @@ void bio_check_pages_dirty(struct bio *bio)
 	}
 }
 
+void generic_start_io_acct(int rw, unsigned long sectors,
+			   struct hd_struct *part)
+{
+	int cpu = part_stat_lock();
+
+	part_round_stats(cpu, part);
+	part_stat_inc(cpu, part, ios[rw]);
+	part_stat_add(cpu, part, sectors[rw], sectors);
+	part_inc_in_flight(part, rw);
+
+	part_stat_unlock();
+}
+EXPORT_SYMBOL(generic_start_io_acct);
+
+void generic_end_io_acct(int rw, struct hd_struct *part,
+			 unsigned long start_time)
+{
+	unsigned long duration = jiffies - start_time;
+	int cpu = part_stat_lock();
+
+	part_stat_add(cpu, part, ticks[rw], duration);
+	part_round_stats(cpu, part);
+	part_dec_in_flight(part, rw);
+
+	part_stat_unlock();
+}
+EXPORT_SYMBOL(generic_end_io_acct);
+
 #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
 void bio_flush_dcache_pages(struct bio *bi)
 {

block/blk-core.c

@@ -525,6 +525,9 @@ void blk_cleanup_queue(struct request_queue *q)
 	del_timer_sync(&q->backing_dev_info.laptop_mode_wb_timer);
 	blk_sync_queue(q);
 
+	if (q->mq_ops)
+		blk_mq_free_queue(q);
+
 	spin_lock_irq(lock);
 	if (q->queue_lock != &q->__queue_lock)
 		q->queue_lock = &q->__queue_lock;

block/blk-mq-cpumap.c

@@ -17,7 +17,7 @@
 static int cpu_to_queue_index(unsigned int nr_cpus, unsigned int nr_queues,
 			      const int cpu)
 {
-	return cpu / ((nr_cpus + nr_queues - 1) / nr_queues);
+	return cpu * nr_queues / nr_cpus;
 }
 
 static int get_first_sibling(unsigned int cpu)
@@ -90,7 +90,7 @@ unsigned int *blk_mq_make_queue_map(struct blk_mq_tag_set *set)
 	unsigned int *map;
 
 	/* If cpus are offline, map them to first hctx */
-	map = kzalloc_node(sizeof(*map) * num_possible_cpus(), GFP_KERNEL,
+	map = kzalloc_node(sizeof(*map) * nr_cpu_ids, GFP_KERNEL,
 				set->numa_node);
 	if (!map)
 		return NULL;

block/blk-mq-sysfs.c

@@ -390,16 +390,15 @@ static void blk_mq_sysfs_init(struct request_queue *q)
 {
 	struct blk_mq_hw_ctx *hctx;
 	struct blk_mq_ctx *ctx;
-	int i, j;
+	int i;
 
 	kobject_init(&q->mq_kobj, &blk_mq_ktype);
 
-	queue_for_each_hw_ctx(q, hctx, i) {
+	queue_for_each_hw_ctx(q, hctx, i)
 		kobject_init(&hctx->kobj, &blk_mq_hw_ktype);
 
-		hctx_for_each_ctx(hctx, ctx, j)
-			kobject_init(&ctx->kobj, &blk_mq_ctx_ktype);
-	}
+	queue_for_each_ctx(q, ctx, i)
+		kobject_init(&ctx->kobj, &blk_mq_ctx_ktype);
 }
 
 /* see blk_register_queue() */

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 @@ static int __bt_get_word(struct blk_align_bitmap *bm, unsigned int last_tag)
 			 * 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,