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

Pull block IO fixes from Jens Axboe:
 "Second round of updates and fixes for 3.14-rc2.  Most of this stuff
  has been queued up for a while.  The notable exception is the blk-mq
  changes, which are naturally a bit more in flux still.

  The pull request contains:

   - Two bug fixes for the new immutable vecs, causing crashes with raid
     or swap.  From Kent.

   - Various blk-mq tweaks and fixes from Christoph.  A fix for
     integrity bio's from Nic.

   - A few bcache fixes from Kent and Darrick Wong.

   - xen-blk{front,back} fixes from David Vrabel, Matt Rushton, Nicolas
     Swenson, and Roger Pau Monne.

   - Fix for a vec miscount with integrity vectors from Martin.

   - Minor annotations or fixes from Masanari Iida and Rashika Kheria.

   - Tweak to null_blk to do more normal FIFO processing of requests
     from Shlomo Pongratz.

   - Elevator switching bypass fix from Tejun.

   - Softlockup in blkdev_issue_discard() fix when !CONFIG_PREEMPT from
     me"

* 'for-linus' of git://git.kernel.dk/linux-block: (31 commits)
  block: add cond_resched() to potentially long running ioctl discard loop
  xen-blkback: init persistent_purge_work work_struct
  blk-mq: pair blk_mq_start_request / blk_mq_requeue_request
  blk-mq: dont assume rq->errors is set when returning an error from ->queue_rq
  block: Fix cloning of discard/write same bios
  block: Fix type mismatch in ssize_t_blk_mq_tag_sysfs_show
  blk-mq: rework flush sequencing logic
  null_blk: use blk_complete_request and blk_mq_complete_request
  virtio_blk: use blk_mq_complete_request
  blk-mq: rework I/O completions
  fs: Add prototype declaration to appropriate header file include/linux/bio.h
  fs: Mark function as static in fs/bio-integrity.c
  block/null_blk: Fix completion processing from LIFO to FIFO
  block: Explicitly handle discard/write same segments
  block: Fix nr_vecs for inline integrity vectors
  blk-mq: Add bio_integrity setup to blk_mq_make_request
  blk-mq: initialize sg_reserved_size
  blk-mq: handle dma_drain_size
  blk-mq: divert __blk_put_request for MQ ops
  blk-mq: support at_head inserations for blk_execute_rq
  ...

1 files changed, 87 insertions, 56 deletions

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 57039fcd9c93..1fa9dd153fde 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -226,15 +226,14 @@ static struct request *blk_mq_alloc_request_pinned(struct request_queue *q,
 	return rq;
 }
 
-struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
-		gfp_t gfp, bool reserved)
+struct request *blk_mq_alloc_request(struct request_queue *q, int rw, gfp_t gfp)
 {
 	struct request *rq;
 
 	if (blk_mq_queue_enter(q))
 		return NULL;
 
-	rq = blk_mq_alloc_request_pinned(q, rw, gfp, reserved);
+	rq = blk_mq_alloc_request_pinned(q, rw, gfp, false);
 	if (rq)
 		blk_mq_put_ctx(rq->mq_ctx);
 	return rq;
@@ -258,7 +257,7 @@ EXPORT_SYMBOL(blk_mq_alloc_reserved_request);
 /*
  * Re-init and set pdu, if we have it
  */
-static void blk_mq_rq_init(struct blk_mq_hw_ctx *hctx, struct request *rq)
+void blk_mq_rq_init(struct blk_mq_hw_ctx *hctx, struct request *rq)
 {
 	blk_rq_init(hctx->queue, rq);
 
@@ -305,7 +304,7 @@ static void blk_mq_bio_endio(struct request *rq, struct bio *bio, int error)
 		bio_endio(bio, error);
 }
 
-void blk_mq_complete_request(struct request *rq, int error)
+void blk_mq_end_io(struct request *rq, int error)
 {
 	struct bio *bio = rq->bio;
 	unsigned int bytes = 0;
@@ -330,48 +329,55 @@ void blk_mq_complete_request(struct request *rq, int error)
 	else
 		blk_mq_free_request(rq);
 }
+EXPORT_SYMBOL(blk_mq_end_io);
 
-void __blk_mq_end_io(struct request *rq, int error)
-{
-	if (!blk_mark_rq_complete(rq))
-		blk_mq_complete_request(rq, error);
-}
-
-static void blk_mq_end_io_remote(void *data)
+static void __blk_mq_complete_request_remote(void *data)
 {
 	struct request *rq = data;
 
-	__blk_mq_end_io(rq, rq->errors);
+	rq->q->softirq_done_fn(rq);
 }
 
-/*
- * End IO on this request on a multiqueue enabled driver. We'll either do
- * it directly inline, or punt to a local IPI handler on the matching
- * remote CPU.
- */
-void blk_mq_end_io(struct request *rq, int error)
+void __blk_mq_complete_request(struct request *rq)
 {
 	struct blk_mq_ctx *ctx = rq->mq_ctx;
 	int cpu;
 
-	if (!ctx->ipi_redirect)
-		return __blk_mq_end_io(rq, error);
+	if (!ctx->ipi_redirect) {
+		rq->q->softirq_done_fn(rq);
+		return;
+	}
 
 	cpu = get_cpu();
 	if (cpu != ctx->cpu && cpu_online(ctx->cpu)) {
-		rq->errors = error;
-		rq->csd.func = blk_mq_end_io_remote;
+		rq->csd.func = __blk_mq_complete_request_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);
+		rq->q->softirq_done_fn(rq);
 	}
 	put_cpu();
 }
-EXPORT_SYMBOL(blk_mq_end_io);
 
-static void blk_mq_start_request(struct request *rq)
+/**
+ * blk_mq_complete_request - end I/O on a request
+ * @rq:		the request being processed
+ *
+ * Description:
+ *	Ends all I/O on a request. It does not handle partial completions.
+ *	The actual completion happens out-of-order, through a IPI handler.
+ **/
+void blk_mq_complete_request(struct request *rq)
+{
+	if (unlikely(blk_should_fake_timeout(rq->q)))
+		return;
+	if (!blk_mark_rq_complete(rq))
+		__blk_mq_complete_request(rq);
+}
+EXPORT_SYMBOL(blk_mq_complete_request);
+
+static void blk_mq_start_request(struct request *rq, bool last)
 {
 	struct request_queue *q = rq->q;
 
@@ -384,6 +390,25 @@ static void blk_mq_start_request(struct request *rq)
 	 */
 	rq->deadline = jiffies + q->rq_timeout;
 	set_bit(REQ_ATOM_STARTED, &rq->atomic_flags);
+
+	if (q->dma_drain_size && blk_rq_bytes(rq)) {
+		/*
+		 * Make sure space for the drain appears.  We know we can do
+		 * this because max_hw_segments has been adjusted to be one
+		 * fewer than the device can handle.
+		 */
+		rq->nr_phys_segments++;
+	}
+
+	/*
+	 * Flag the last request in the series so that drivers know when IO
+	 * should be kicked off, if they don't do it on a per-request basis.
+	 *
+	 * Note: the flag isn't the only condition drivers should do kick off.
+	 * If drive is busy, the last request might not have the bit set.
+	 */
+	if (last)
+		rq->cmd_flags |= REQ_END;
 }
 
 static void blk_mq_requeue_request(struct request *rq)
@@ -392,6 +417,11 @@ static void blk_mq_requeue_request(struct request *rq)
 
 	trace_block_rq_requeue(q, rq);
 	clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags);
+
+	rq->cmd_flags &= ~REQ_END;
+
+	if (q->dma_drain_size && blk_rq_bytes(rq))
+		rq->nr_phys_segments--;
 }
 
 struct blk_mq_timeout_data {
@@ -559,19 +589,8 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 
 		rq = list_first_entry(&rq_list, struct request, queuelist);
 		list_del_init(&rq->queuelist);
-		blk_mq_start_request(rq);
 
-		/*
-		 * Last request in the series. Flag it as such, this
-		 * enables drivers to know when IO should be kicked off,
-		 * if they don't do it on a per-request basis.
-		 *
-		 * Note: the flag isn't the only condition drivers
-		 * should do kick off. If drive is busy, the last
-		 * request might not have the bit set.
-		 */
-		if (list_empty(&rq_list))
-			rq->cmd_flags |= REQ_END;
+		blk_mq_start_request(rq, list_empty(&rq_list));
 
 		ret = q->mq_ops->queue_rq(hctx, rq);
 		switch (ret) {
@@ -589,8 +608,8 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 			break;
 		default:
 			pr_err("blk-mq: bad return on queue: %d\n", ret);
-			rq->errors = -EIO;
 		case BLK_MQ_RQ_QUEUE_ERROR:
+			rq->errors = -EIO;
 			blk_mq_end_io(rq, rq->errors);
 			break;
 		}
@@ -693,13 +712,16 @@ static void blk_mq_work_fn(struct work_struct *work)
 }
 
 static void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx,
-				    struct request *rq)
+				    struct request *rq, bool at_head)
 {
 	struct blk_mq_ctx *ctx = rq->mq_ctx;
 
 	trace_block_rq_insert(hctx->queue, rq);
 
-	list_add_tail(&rq->queuelist, &ctx->rq_list);
+	if (at_head)
+		list_add(&rq->queuelist, &ctx->rq_list);
+	else
+		list_add_tail(&rq->queuelist, &ctx->rq_list);
 	blk_mq_hctx_mark_pending(hctx, ctx);
 
 	/*
@@ -709,7 +731,7 @@ static void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx,
 }
 
 void blk_mq_insert_request(struct request_queue *q, struct request *rq,
-			   bool run_queue)
+			   bool at_head, bool run_queue)
 {
 	struct blk_mq_hw_ctx *hctx;
 	struct blk_mq_ctx *ctx, *current_ctx;
@@ -728,7 +750,7 @@ void blk_mq_insert_request(struct request_queue *q, struct request *rq,
 			rq->mq_ctx = ctx;
 		}
 		spin_lock(&ctx->lock);
-		__blk_mq_insert_request(hctx, rq);
+		__blk_mq_insert_request(hctx, rq, at_head);
 		spin_unlock(&ctx->lock);
 
 		blk_mq_put_ctx(current_ctx);
@@ -760,7 +782,7 @@ void blk_mq_run_request(struct request *rq, bool run_queue, bool async)
 
 	/* ctx->cpu might be offline */
 	spin_lock(&ctx->lock);
-	__blk_mq_insert_request(hctx, rq);
+	__blk_mq_insert_request(hctx, rq, false);
 	spin_unlock(&ctx->lock);
 
 	blk_mq_put_ctx(current_ctx);
@@ -798,7 +820,7 @@ static void blk_mq_insert_requests(struct request_queue *q,
 		rq = list_first_entry(list, struct request, queuelist);
 		list_del_init(&rq->queuelist);
 		rq->mq_ctx = ctx;
-		__blk_mq_insert_request(hctx, rq);
+		__blk_mq_insert_request(hctx, rq, false);
 	}
 	spin_unlock(&ctx->lock);
 
@@ -888,6 +910,11 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
 
 	blk_queue_bounce(q, &bio);
 
+	if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
+		bio_endio(bio, -EIO);
+		return;
+	}
+
 	if (use_plug && blk_attempt_plug_merge(q, bio, &request_count))
 		return;
 
@@ -950,7 +977,7 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
 		__blk_mq_free_request(hctx, ctx, rq);
 	else {
 		blk_mq_bio_to_request(rq, bio);
-		__blk_mq_insert_request(hctx, rq);
+		__blk_mq_insert_request(hctx, rq, false);
 	}
 
 	spin_unlock(&ctx->lock);
@@ -1309,15 +1336,6 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_reg *reg,
 		reg->queue_depth = BLK_MQ_MAX_DEPTH;
 	}
 
-	/*
-	 * Set aside a tag for flush requests.  It will only be used while
-	 * another flush request is in progress but outside the driver.
-	 *
-	 * TODO: only allocate if flushes are supported
-	 */
-	reg->queue_depth++;
-	reg->reserved_tags++;
-
 	if (reg->queue_depth < (reg->reserved_tags + BLK_MQ_TAG_MIN))
 		return ERR_PTR(-EINVAL);
 
@@ -1360,17 +1378,27 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_reg *reg,
 	q->mq_ops = reg->ops;
 	q->queue_flags |= QUEUE_FLAG_MQ_DEFAULT;
 
+	q->sg_reserved_size = INT_MAX;
+
 	blk_queue_make_request(q, blk_mq_make_request);
 	blk_queue_rq_timed_out(q, reg->ops->timeout);
 	if (reg->timeout)
 		blk_queue_rq_timeout(q, reg->timeout);
 
+	if (reg->ops->complete)
+		blk_queue_softirq_done(q, reg->ops->complete);
+
 	blk_mq_init_flush(q);
 	blk_mq_init_cpu_queues(q, reg->nr_hw_queues);
 
-	if (blk_mq_init_hw_queues(q, reg, driver_data))
+	q->flush_rq = kzalloc(round_up(sizeof(struct request) + reg->cmd_size,
+				cache_line_size()), GFP_KERNEL);
+	if (!q->flush_rq)
 		goto err_hw;
 
+	if (blk_mq_init_hw_queues(q, reg, driver_data))
+		goto err_flush_rq;
+
 	blk_mq_map_swqueue(q);
 
 	mutex_lock(&all_q_mutex);
@@ -1378,6 +1406,9 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_reg *reg,
 	mutex_unlock(&all_q_mutex);
 
 	return q;
+
+err_flush_rq:
+	kfree(q->flush_rq);
 err_hw:
 	kfree(q->mq_map);
 err_map: