Merge branch 'for-3.14/core' of git://git.kernel.dk/linux-block

Pull core block IO changes from Jens Axboe:
 "The major piece in here is the immutable bio_ve series from Kent, the
  rest is fairly minor.  It was supposed to go in last round, but
  various issues pushed it to this release instead.  The pull request
  contains:

   - Various smaller blk-mq fixes from different folks.  Nothing major
     here, just minor fixes and cleanups.

   - Fix for a memory leak in the error path in the block ioctl code
     from Christian Engelmayer.

   - Header export fix from CaiZhiyong.

   - Finally the immutable biovec changes from Kent Overstreet.  This
     enables some nice future work on making arbitrarily sized bios
     possible, and splitting more efficient.  Related fixes to immutable
     bio_vecs:

        - dm-cache immutable fixup from Mike Snitzer.
        - btrfs immutable fixup from Muthu Kumar.

  - bio-integrity fix from Nic Bellinger, which is also going to stable"

* 'for-3.14/core' of git://git.kernel.dk/linux-block: (44 commits)
  xtensa: fixup simdisk driver to work with immutable bio_vecs
  block/blk-mq-cpu.c: use hotcpu_notifier()
  blk-mq: for_each_* macro correctness
  block: Fix memory leak in rw_copy_check_uvector() handling
  bio-integrity: Fix bio_integrity_verify segment start bug
  block: remove unrelated header files and export symbol
  blk-mq: uses page->list incorrectly
  blk-mq: use __smp_call_function_single directly
  btrfs: fix missing increment of bi_remaining
  Revert "block: Warn and free bio if bi_end_io is not set"
  block: Warn and free bio if bi_end_io is not set
  blk-mq: fix initializing request's start time
  block: blk-mq: don't export blk_mq_free_queue()
  block: blk-mq: make blk_sync_queue support mq
  block: blk-mq: support draining mq queue
  dm cache: increment bi_remaining when bi_end_io is restored
  block: fixup for generic bio chaining
  block: Really silence spurious compiler warnings
  block: Silence spurious compiler warnings
  block: Kill bio_pair_split()
  ...

1 files changed, 44 insertions, 79 deletions

diff --git a/block/blk-mq.c b/block/blk-mq.c
index c79126e11030..57039fcd9c93 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -27,8 +27,6 @@ static LIST_HEAD(all_q_list);
 
 static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx);
 
-DEFINE_PER_CPU(struct llist_head, ipi_lists);
-
 static struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q,
 					   unsigned int cpu)
 {
@@ -106,10 +104,13 @@ static int blk_mq_queue_enter(struct request_queue *q)
 
 	spin_lock_irq(q->queue_lock);
 	ret = wait_event_interruptible_lock_irq(q->mq_freeze_wq,
-		!blk_queue_bypass(q), *q->queue_lock);
+		!blk_queue_bypass(q) || blk_queue_dying(q),
+		*q->queue_lock);
 	/* inc usage with lock hold to avoid freeze_queue runs here */
-	if (!ret)
+	if (!ret && !blk_queue_dying(q))
 		__percpu_counter_add(&q->mq_usage_counter, 1, 1000000);
+	else if (blk_queue_dying(q))
+		ret = -ENODEV;
 	spin_unlock_irq(q->queue_lock);
 
 	return ret;
@@ -120,6 +121,22 @@ static void blk_mq_queue_exit(struct request_queue *q)
 	__percpu_counter_add(&q->mq_usage_counter, -1, 1000000);
 }
 
+static void __blk_mq_drain_queue(struct request_queue *q)
+{
+	while (true) {
+		s64 count;
+
+		spin_lock_irq(q->queue_lock);
+		count = percpu_counter_sum(&q->mq_usage_counter);
+		spin_unlock_irq(q->queue_lock);
+
+		if (count == 0)
+			break;
+		blk_mq_run_queues(q, false);
+		msleep(10);
+	}
+}
+
 /*
  * Guarantee no request is in use, so we can change any data structure of
  * the queue afterward.
@@ -133,21 +150,13 @@ static void blk_mq_freeze_queue(struct request_queue *q)
 	queue_flag_set(QUEUE_FLAG_BYPASS, q);
 	spin_unlock_irq(q->queue_lock);
 
-	if (!drain)
-		return;
-
-	while (true) {
-		s64 count;
-
-		spin_lock_irq(q->queue_lock);
-		count = percpu_counter_sum(&q->mq_usage_counter);
-		spin_unlock_irq(q->queue_lock);
+	if (drain)
+		__blk_mq_drain_queue(q);
+}
 
-		if (count == 0)
-			break;
-		blk_mq_run_queues(q, false);
-		msleep(10);
-	}
+void blk_mq_drain_queue(struct request_queue *q)
+{
+	__blk_mq_drain_queue(q);
 }
 
 static void blk_mq_unfreeze_queue(struct request_queue *q)
@@ -179,6 +188,8 @@ static void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
 
 	rq->mq_ctx = ctx;
 	rq->cmd_flags = rw_flags;
+	rq->start_time = jiffies;
+	set_start_time_ns(rq);
 	ctx->rq_dispatched[rw_is_sync(rw_flags)]++;
 }
 
@@ -305,7 +316,7 @@ void blk_mq_complete_request(struct request *rq, int error)
 		struct bio *next = bio->bi_next;
 
 		bio->bi_next = NULL;
-		bytes += bio->bi_size;
+		bytes += bio->bi_iter.bi_size;
 		blk_mq_bio_endio(rq, bio, error);
 		bio = next;
 	}
@@ -326,55 +337,12 @@ void __blk_mq_end_io(struct request *rq, int error)
 		blk_mq_complete_request(rq, error);
 }
 
-#if defined(CONFIG_SMP)
-
-/*
- * Called with interrupts disabled.
- */
-static void ipi_end_io(void *data)
-{
-	struct llist_head *list = &per_cpu(ipi_lists, smp_processor_id());
-	struct llist_node *entry, *next;
-	struct request *rq;
-
-	entry = llist_del_all(list);
-
-	while (entry) {
-		next = entry->next;
-		rq = llist_entry(entry, struct request, ll_list);
-		__blk_mq_end_io(rq, rq->errors);
-		entry = next;
-	}
-}
-
-static int ipi_remote_cpu(struct blk_mq_ctx *ctx, const int cpu,
-			  struct request *rq, const int error)
+static void blk_mq_end_io_remote(void *data)
 {
-	struct call_single_data *data = &rq->csd;
-
-	rq->errors = error;
-	rq->ll_list.next = NULL;
+	struct request *rq = data;
 
-	/*
-	 * If the list is non-empty, an existing IPI must already
-	 * be "in flight". If that is the case, we need not schedule
-	 * a new one.
-	 */
-	if (llist_add(&rq->ll_list, &per_cpu(ipi_lists, ctx->cpu))) {
-		data->func = ipi_end_io;
-		data->flags = 0;
-		__smp_call_function_single(ctx->cpu, data, 0);
-	}
-
-	return true;
-}
-#else /* CONFIG_SMP */
-static int ipi_remote_cpu(struct blk_mq_ctx *ctx, const int cpu,
-			  struct request *rq, const int error)
-{
-	return false;
+	__blk_mq_end_io(rq, rq->errors);
 }
-#endif
 
 /*
  * End IO on this request on a multiqueue enabled driver. We'll either do
@@ -390,11 +358,15 @@ void blk_mq_end_io(struct request *rq, int error)
 		return __blk_mq_end_io(rq, error);
 
 	cpu = get_cpu();
-
-	if (cpu == ctx->cpu || !cpu_online(ctx->cpu) ||
-	    !ipi_remote_cpu(ctx, cpu, rq, error))
+	if (cpu != ctx->cpu && cpu_online(ctx->cpu)) {
+		rq->errors = error;
+		rq->csd.func = blk_mq_end_io_remote;
+		rq->csd.info = rq;
+		rq->csd.flags = 0;
+		__smp_call_function_single(ctx->cpu, &rq->csd, 0);
+	} else {
 		__blk_mq_end_io(rq, error);
-
+	}
 	put_cpu();
 }
 EXPORT_SYMBOL(blk_mq_end_io);
@@ -1091,8 +1063,8 @@ static void blk_mq_free_rq_map(struct blk_mq_hw_ctx *hctx)
 	struct page *page;
 
 	while (!list_empty(&hctx->page_list)) {
-		page = list_first_entry(&hctx->page_list, struct page, list);
-		list_del_init(&page->list);
+		page = list_first_entry(&hctx->page_list, struct page, lru);
+		list_del_init(&page->lru);
 		__free_pages(page, page->private);
 	}
 
@@ -1156,7 +1128,7 @@ static int blk_mq_init_rq_map(struct blk_mq_hw_ctx *hctx,
 			break;
 
 		page->private = this_order;
-		list_add_tail(&page->list, &hctx->page_list);
+		list_add_tail(&page->lru, &hctx->page_list);
 
 		p = page_address(page);
 		entries_per_page = order_to_size(this_order) / rq_size;
@@ -1429,7 +1401,6 @@ void blk_mq_free_queue(struct request_queue *q)
 	int i;
 
 	queue_for_each_hw_ctx(q, hctx, i) {
-		cancel_delayed_work_sync(&hctx->delayed_work);
 		kfree(hctx->ctx_map);
 		kfree(hctx->ctxs);
 		blk_mq_free_rq_map(hctx);
@@ -1451,7 +1422,6 @@ void blk_mq_free_queue(struct request_queue *q)
 	list_del_init(&q->all_q_node);
 	mutex_unlock(&all_q_mutex);
 }
-EXPORT_SYMBOL(blk_mq_free_queue);
 
 /* Basically redo blk_mq_init_queue with queue frozen */
 static void blk_mq_queue_reinit(struct request_queue *q)
@@ -1495,11 +1465,6 @@ static int blk_mq_queue_reinit_notify(struct notifier_block *nb,
 
 static int __init blk_mq_init(void)
 {
-	unsigned int i;
-
-	for_each_possible_cpu(i)
-		init_llist_head(&per_cpu(ipi_lists, i));
-
 	blk_mq_cpu_init();
 
 	/* Must be called after percpu_counter_hotcpu_callback() */