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
  ...

block/blk-core.c

@@ -693,11 +693,20 @@ blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id)
 	if (!uninit_q)
 		return NULL;
 
+	uninit_q->flush_rq = kzalloc(sizeof(struct request), GFP_KERNEL);
+	if (!uninit_q->flush_rq)
+		goto out_cleanup_queue;
+
 	q = blk_init_allocated_queue(uninit_q, rfn, lock);
 	if (!q)
-		blk_cleanup_queue(uninit_q);
-
+		goto out_free_flush_rq;
 	return q;
+
+out_free_flush_rq:
+	kfree(uninit_q->flush_rq);
+out_cleanup_queue:
+	blk_cleanup_queue(uninit_q);
+	return NULL;
 }
 EXPORT_SYMBOL(blk_init_queue_node);
 
@@ -1127,7 +1136,7 @@ static struct request *blk_old_get_request(struct request_queue *q, int rw,
 struct request *blk_get_request(struct request_queue *q, int rw, gfp_t gfp_mask)
 {
 	if (q->mq_ops)
-		return blk_mq_alloc_request(q, rw, gfp_mask, false);
+		return blk_mq_alloc_request(q, rw, gfp_mask);
 	else
 		return blk_old_get_request(q, rw, gfp_mask);
 }
@@ -1278,6 +1287,11 @@ void __blk_put_request(struct request_queue *q, struct request *req)
 	if (unlikely(!q))
 		return;
 
+	if (q->mq_ops) {
+		blk_mq_free_request(req);
+		return;
+	}
+
 	blk_pm_put_request(req);
 
 	elv_completed_request(q, req);

block/blk-exec.c

@@ -65,7 +65,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 	 * be resued after dying flag is set
 	 */
 	if (q->mq_ops) {
-		blk_mq_insert_request(q, rq, true);
+		blk_mq_insert_request(q, rq, at_head, true);
 		return;
 	}
 

block/blk-flush.c

@@ -130,20 +130,26 @@ static void blk_flush_restore_request(struct request *rq)
 	blk_clear_rq_complete(rq);
 }
 
-static void mq_flush_data_run(struct work_struct *work)
+static void mq_flush_run(struct work_struct *work)
 {
 	struct request *rq;
 
-	rq = container_of(work, struct request, mq_flush_data);
+	rq = container_of(work, struct request, mq_flush_work);
 
 	memset(&rq->csd, 0, sizeof(rq->csd));
 	blk_mq_run_request(rq, true, false);
 }
 
-static void blk_mq_flush_data_insert(struct request *rq)
+static bool blk_flush_queue_rq(struct request *rq)
 {
-	INIT_WORK(&rq->mq_flush_data, mq_flush_data_run);
-	kblockd_schedule_work(rq->q, &rq->mq_flush_data);
+	if (rq->q->mq_ops) {
+		INIT_WORK(&rq->mq_flush_work, mq_flush_run);
+		kblockd_schedule_work(rq->q, &rq->mq_flush_work);
+		return false;
+	} else {
+		list_add_tail(&rq->queuelist, &rq->q->queue_head);
+		return true;
+	}
 }
 
 /**
@@ -187,12 +193,7 @@ static bool blk_flush_complete_seq(struct request *rq, unsigned int seq,
 
 	case REQ_FSEQ_DATA:
 		list_move_tail(&rq->flush.list, &q->flush_data_in_flight);
-		if (q->mq_ops)
-			blk_mq_flush_data_insert(rq);
-		else {
-			list_add(&rq->queuelist, &q->queue_head);
-			queued = true;
-		}
+		queued = blk_flush_queue_rq(rq);
 		break;
 
 	case REQ_FSEQ_DONE:
@@ -216,9 +217,6 @@ static bool blk_flush_complete_seq(struct request *rq, unsigned int seq,
 	}
 
 	kicked = blk_kick_flush(q);
-	/* blk_mq_run_flush will run queue */
-	if (q->mq_ops)
-		return queued;
 	return kicked | queued;
 }
 
@@ -230,10 +228,9 @@ static void flush_end_io(struct request *flush_rq, int error)
 	struct request *rq, *n;
 	unsigned long flags = 0;
 
-	if (q->mq_ops) {
-		blk_mq_free_request(flush_rq);
+	if (q->mq_ops)
 		spin_lock_irqsave(&q->mq_flush_lock, flags);
-	}
+
 	running = &q->flush_queue[q->flush_running_idx];
 	BUG_ON(q->flush_pending_idx == q->flush_running_idx);
 
@@ -263,49 +260,14 @@ static void flush_end_io(struct request *flush_rq, int error)
 	 * kblockd.
 	 */
 	if (queued || q->flush_queue_delayed) {
-		if (!q->mq_ops)
-			blk_run_queue_async(q);
-		else
-		/*
-		 * This can be optimized to only run queues with requests
-		 * queued if necessary.
-		 */
-			blk_mq_run_queues(q, true);
+		WARN_ON(q->mq_ops);
+		blk_run_queue_async(q);
 	}
 	q->flush_queue_delayed = 0;
 	if (q->mq_ops)
 		spin_unlock_irqrestore(&q->mq_flush_lock, flags);
 }
 
-static void mq_flush_work(struct work_struct *work)
-{
-	struct request_queue *q;
-	struct request *rq;
-
-	q = container_of(work, struct request_queue, mq_flush_work);
-
-	/* We don't need set REQ_FLUSH_SEQ, it's for consistency */
-	rq = blk_mq_alloc_request(q, WRITE_FLUSH|REQ_FLUSH_SEQ,
-		__GFP_WAIT|GFP_ATOMIC, true);
-	rq->cmd_type = REQ_TYPE_FS;
-	rq->end_io = flush_end_io;
-
-	blk_mq_run_request(rq, true, false);
-}
-
-/*
- * We can't directly use q->flush_rq, because it doesn't have tag and is not in
- * hctx->rqs[]. so we must allocate a new request, since we can't sleep here,
- * so offload the work to workqueue.
- *
- * Note: we assume a flush request finished in any hardware queue will flush
- * the whole disk cache.
- */
-static void mq_run_flush(struct request_queue *q)
-{
-	kblockd_schedule_work(q, &q->mq_flush_work);
-}
-
 /**
  * blk_kick_flush - consider issuing flush request
  * @q: request_queue being kicked
@@ -340,19 +302,31 @@ static bool blk_kick_flush(struct request_queue *q)
 	 * different from running_idx, which means flush is in flight.
 	 */
 	q->flush_pending_idx ^= 1;
+
 	if (q->mq_ops) {
-		mq_run_flush(q);
-		return true;
+		struct blk_mq_ctx *ctx = first_rq->mq_ctx;
+		struct blk_mq_hw_ctx *hctx = q->mq_ops->map_queue(q, ctx->cpu);
+
+		blk_mq_rq_init(hctx, q->flush_rq);
+		q->flush_rq->mq_ctx = ctx;
+
+		/*
+		 * Reuse the tag value from the fist waiting request,
+		 * with blk-mq the tag is generated during request
+		 * allocation and drivers can rely on it being inside
+		 * the range they asked for.
+		 */
+		q->flush_rq->tag = first_rq->tag;
+	} else {
+		blk_rq_init(q, q->flush_rq);
 	}
 
-	blk_rq_init(q, &q->flush_rq);
-	q->flush_rq.cmd_type = REQ_TYPE_FS;
-	q->flush_rq.cmd_flags = WRITE_FLUSH | REQ_FLUSH_SEQ;
-	q->flush_rq.rq_disk = first_rq->rq_disk;
-	q->flush_rq.end_io = flush_end_io;
+	q->flush_rq->cmd_type = REQ_TYPE_FS;
+	q->flush_rq->cmd_flags = WRITE_FLUSH | REQ_FLUSH_SEQ;
+	q->flush_rq->rq_disk = first_rq->rq_disk;
+	q->flush_rq->end_io = flush_end_io;
 
-	list_add_tail(&q->flush_rq.queuelist, &q->queue_head);
-	return true;
+	return blk_flush_queue_rq(q->flush_rq);
 }
 
 static void flush_data_end_io(struct request *rq, int error)
@@ -558,5 +532,4 @@ EXPORT_SYMBOL(blkdev_issue_flush);
 void blk_mq_init_flush(struct request_queue *q)
 {
 	spin_lock_init(&q->mq_flush_lock);
-	INIT_WORK(&q->mq_flush_work, mq_flush_work);
 }

block/blk-lib.c

@@ -119,6 +119,14 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 
 		atomic_inc(&bb.done);
 		submit_bio(type, bio);
+
+		/*
+		 * We can loop for a long time in here, if someone does
+		 * full device discards (like mkfs). Be nice and allow
+		 * us to schedule out to avoid softlocking if preempt
+		 * is disabled.
+		 */
+		cond_resched();
 	}
 	blk_finish_plug(&plug);
 

block/blk-merge.c

@@ -21,6 +21,16 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 	if (!bio)
 		return 0;
 
+	/*
+	 * This should probably be returning 0, but blk_add_request_payload()
+	 * (Christoph!!!!)
+	 */
+	if (bio->bi_rw & REQ_DISCARD)
+		return 1;
+
+	if (bio->bi_rw & REQ_WRITE_SAME)
+		return 1;
+
 	fbio = bio;
 	cluster = blk_queue_cluster(q);
 	seg_size = 0;
@@ -161,30 +171,60 @@ __blk_segment_map_sg(struct request_queue *q, struct bio_vec *bvec,
 	*bvprv = *bvec;
 }
 
-/*
- * map a request to scatterlist, return number of sg entries setup. Caller
- * must make sure sg can hold rq->nr_phys_segments entries
- */
-int blk_rq_map_sg(struct request_queue *q, struct request *rq,
-		  struct scatterlist *sglist)
+static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio,
+			     struct scatterlist *sglist,
+			     struct scatterlist **sg)
 {
 	struct bio_vec bvec, bvprv = { NULL };
-	struct req_iterator iter;
-	struct scatterlist *sg;
+	struct bvec_iter iter;
 	int nsegs, cluster;
 
 	nsegs = 0;
 	cluster = blk_queue_cluster(q);
 
-	/*
-	 * for each bio in rq
-	 */
-	sg = NULL;
-	rq_for_each_segment(bvec, rq, iter) {
-		__blk_segment_map_sg(q, &bvec, sglist, &bvprv, &sg,
-				     &nsegs, &cluster);
-	} /* segments in rq */
+	if (bio->bi_rw & REQ_DISCARD) {
+		/*
+		 * This is a hack - drivers should be neither modifying the
+		 * biovec, nor relying on bi_vcnt - but because of
+		 * blk_add_request_payload(), a discard bio may or may not have
+		 * a payload we need to set up here (thank you Christoph) and
+		 * bi_vcnt is really the only way of telling if we need to.
+		 */
+
+		if (bio->bi_vcnt)
+			goto single_segment;
+
+		return 0;
+	}
+
+	if (bio->bi_rw & REQ_WRITE_SAME) {
+single_segment:
+		*sg = sglist;
+		bvec = bio_iovec(bio);
+		sg_set_page(*sg, bvec.bv_page, bvec.bv_len, bvec.bv_offset);
+		return 1;
+	}
+
+	for_each_bio(bio)
+		bio_for_each_segment(bvec, bio, iter)
+			__blk_segment_map_sg(q, &bvec, sglist, &bvprv, sg,
+					     &nsegs, &cluster);
 
+	return nsegs;
+}
+
+/*
+ * map a request to scatterlist, return number of sg entries setup. Caller
+ * must make sure sg can hold rq->nr_phys_segments entries
+ */
+int blk_rq_map_sg(struct request_queue *q, struct request *rq,
+		  struct scatterlist *sglist)
+{
+	struct scatterlist *sg = NULL;
+	int nsegs = 0;
+
+	if (rq->bio)
+		nsegs = __blk_bios_map_sg(q, rq->bio, sglist, &sg);
 
 	if (unlikely(rq->cmd_flags & REQ_COPY_USER) &&
 	    (blk_rq_bytes(rq) & q->dma_pad_mask)) {
@@ -230,20 +270,13 @@ EXPORT_SYMBOL(blk_rq_map_sg);
 int blk_bio_map_sg(struct request_queue *q, struct bio *bio,
 		   struct scatterlist *sglist)
 {
-	struct bio_vec bvec, bvprv = { NULL };
-	struct scatterlist *sg;
-	int nsegs, cluster;
-	struct bvec_iter iter;
-
-	nsegs = 0;
-	cluster = blk_queue_cluster(q);
-
-	sg = NULL;
-	bio_for_each_segment(bvec, bio, iter) {
-		__blk_segment_map_sg(q, &bvec, sglist, &bvprv, &sg,
-				     &nsegs, &cluster);
-	} /* segments in bio */
+	struct scatterlist *sg = NULL;
+	int nsegs;
+	struct bio *next = bio->bi_next;
+	bio->bi_next = NULL;
 
+	nsegs = __blk_bios_map_sg(q, bio, sglist, &sg);
+	bio->bi_next = next;
 	if (sg)
 		sg_mark_end(sg);
 

block/blk-mq-tag.c

@@ -184,7 +184,7 @@ void blk_mq_free_tags(struct blk_mq_tags *tags)
 ssize_t blk_mq_tag_sysfs_show(struct blk_mq_tags *tags, char *page)
 {
 	char *orig_page = page;
-	int cpu;
+	unsigned int cpu;
 
 	if (!tags)
 		return 0;