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
  ...

6 files changed, 105 insertions, 95 deletions

diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index 3107282a9741..091b9ea14feb 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -60,7 +60,9 @@ enum {
 	NULL_IRQ_NONE		= 0,
 	NULL_IRQ_SOFTIRQ	= 1,
 	NULL_IRQ_TIMER		= 2,
+};
 
+enum {
 	NULL_Q_BIO		= 0,
 	NULL_Q_RQ		= 1,
 	NULL_Q_MQ		= 2,
@@ -172,18 +174,20 @@ static struct nullb_cmd *alloc_cmd(struct nullb_queue *nq, int can_wait)
 
 static void end_cmd(struct nullb_cmd *cmd)
 {
-	if (cmd->rq) {
-		if (queue_mode == NULL_Q_MQ)
-			blk_mq_end_io(cmd->rq, 0);
-		else {
-			INIT_LIST_HEAD(&cmd->rq->queuelist);
-			blk_end_request_all(cmd->rq, 0);
-		}
-	} else if (cmd->bio)
+	switch (queue_mode)  {
+	case NULL_Q_MQ:
+		blk_mq_end_io(cmd->rq, 0);
+		return;
+	case NULL_Q_RQ:
+		INIT_LIST_HEAD(&cmd->rq->queuelist);
+		blk_end_request_all(cmd->rq, 0);
+		break;
+	case NULL_Q_BIO:
 		bio_endio(cmd->bio, 0);
+		break;
+	}
 
-	if (queue_mode != NULL_Q_MQ)
-		free_cmd(cmd);
+	free_cmd(cmd);
 }
 
 static enum hrtimer_restart null_cmd_timer_expired(struct hrtimer *timer)
@@ -195,6 +199,7 @@ static enum hrtimer_restart null_cmd_timer_expired(struct hrtimer *timer)
 	cq = &per_cpu(completion_queues, smp_processor_id());
 
 	while ((entry = llist_del_all(&cq->list)) != NULL) {
+		entry = llist_reverse_order(entry);
 		do {
 			cmd = container_of(entry, struct nullb_cmd, ll_list);
 			end_cmd(cmd);
@@ -221,61 +226,31 @@ static void null_cmd_end_timer(struct nullb_cmd *cmd)
 
 static void null_softirq_done_fn(struct request *rq)
 {
-	blk_end_request_all(rq, 0);
-}
-
-#ifdef CONFIG_SMP
-
-static void null_ipi_cmd_end_io(void *data)
-{
-	struct completion_queue *cq;
-	struct llist_node *entry, *next;
-	struct nullb_cmd *cmd;
-
-	cq = &per_cpu(completion_queues, smp_processor_id());
-
-	entry = llist_del_all(&cq->list);
-
-	while (entry) {
-		next = entry->next;
-		cmd = llist_entry(entry, struct nullb_cmd, ll_list);
-		end_cmd(cmd);
-		entry = next;
-	}
-}
-
-static void null_cmd_end_ipi(struct nullb_cmd *cmd)
-{
-	struct call_single_data *data = &cmd->csd;
-	int cpu = get_cpu();
-	struct completion_queue *cq = &per_cpu(completion_queues, cpu);
-
-	cmd->ll_list.next = NULL;
-
-	if (llist_add(&cmd->ll_list, &cq->list)) {
-		data->func = null_ipi_cmd_end_io;
-		data->flags = 0;
-		__smp_call_function_single(cpu, data, 0);
-	}
-
-	put_cpu();
+	end_cmd(rq->special);
 }
 
-#endif /* CONFIG_SMP */
-
 static inline void null_handle_cmd(struct nullb_cmd *cmd)
 {
 	/* Complete IO by inline, softirq or timer */
 	switch (irqmode) {
-	case NULL_IRQ_NONE:
-		end_cmd(cmd);
-		break;
 	case NULL_IRQ_SOFTIRQ:
-#ifdef CONFIG_SMP
-		null_cmd_end_ipi(cmd);
-#else
+		switch (queue_mode)  {
+		case NULL_Q_MQ:
+			blk_mq_complete_request(cmd->rq);
+			break;
+		case NULL_Q_RQ:
+			blk_complete_request(cmd->rq);
+			break;
+		case NULL_Q_BIO:
+			/*
+			 * XXX: no proper submitting cpu information available.
+			 */
+			end_cmd(cmd);
+			break;
+		}
+		break;
+	case NULL_IRQ_NONE:
 		end_cmd(cmd);
-#endif
 		break;
 	case NULL_IRQ_TIMER:
 		null_cmd_end_timer(cmd);
@@ -411,6 +386,7 @@ static struct blk_mq_ops null_mq_ops = {
 	.queue_rq       = null_queue_rq,
 	.map_queue      = blk_mq_map_queue,
 	.init_hctx	= null_init_hctx,
+	.complete	= null_softirq_done_fn,
 };
 
 static struct blk_mq_reg null_mq_reg = {
@@ -609,13 +585,6 @@ static int __init null_init(void)
 {
 	unsigned int i;
 
-#if !defined(CONFIG_SMP)
-	if (irqmode == NULL_IRQ_SOFTIRQ) {
-		pr_warn("null_blk: softirq completions not available.\n");
-		pr_warn("null_blk: using direct completions.\n");
-		irqmode = NULL_IRQ_NONE;
-	}
-#endif
 	if (bs > PAGE_SIZE) {
 		pr_warn("null_blk: invalid block size\n");
 		pr_warn("null_blk: defaults block size to %lu\n", PAGE_SIZE);
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 6a680d4de7f1..b1cb3f4c4db4 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -110,9 +110,9 @@ static int __virtblk_add_req(struct virtqueue *vq,
 	return virtqueue_add_sgs(vq, sgs, num_out, num_in, vbr, GFP_ATOMIC);
 }
 
-static inline void virtblk_request_done(struct virtblk_req *vbr)
+static inline void virtblk_request_done(struct request *req)
 {
-	struct request *req = vbr->req;
+	struct virtblk_req *vbr = req->special;
 	int error = virtblk_result(vbr);
 
 	if (req->cmd_type == REQ_TYPE_BLOCK_PC) {
@@ -138,7 +138,7 @@ static void virtblk_done(struct virtqueue *vq)
 	do {
 		virtqueue_disable_cb(vq);
 		while ((vbr = virtqueue_get_buf(vblk->vq, &len)) != NULL) {
-			virtblk_request_done(vbr);
+			blk_mq_complete_request(vbr->req);
 			req_done = true;
 		}
 		if (unlikely(virtqueue_is_broken(vq)))
@@ -479,6 +479,7 @@ static struct blk_mq_ops virtio_mq_ops = {
 	.map_queue	= blk_mq_map_queue,
 	.alloc_hctx	= blk_mq_alloc_single_hw_queue,
 	.free_hctx	= blk_mq_free_single_hw_queue,
+	.complete	= virtblk_request_done,
 };
 
 static struct blk_mq_reg virtio_mq_reg = {
diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index 4b97b86da926..64c60edcdfbc 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -299,7 +299,7 @@ static void free_persistent_gnts(struct xen_blkif *blkif, struct rb_root *root,
 	BUG_ON(num != 0);
 }
 
-static void unmap_purged_grants(struct work_struct *work)
+void xen_blkbk_unmap_purged_grants(struct work_struct *work)
 {
 	struct gnttab_unmap_grant_ref unmap[BLKIF_MAX_SEGMENTS_PER_REQUEST];
 	struct page *pages[BLKIF_MAX_SEGMENTS_PER_REQUEST];
@@ -375,7 +375,7 @@ static void purge_persistent_gnt(struct xen_blkif *blkif)
 
 	pr_debug(DRV_PFX "Going to purge %u persistent grants\n", num_clean);
 
-	INIT_LIST_HEAD(&blkif->persistent_purge_list);
+	BUG_ON(!list_empty(&blkif->persistent_purge_list));
 	root = &blkif->persistent_gnts;
 purge_list:
 	foreach_grant_safe(persistent_gnt, n, root, node) {
@@ -420,7 +420,6 @@ finished:
 	blkif->vbd.overflow_max_grants = 0;
 
 	/* We can defer this work */
-	INIT_WORK(&blkif->persistent_purge_work, unmap_purged_grants);
 	schedule_work(&blkif->persistent_purge_work);
 	pr_debug(DRV_PFX "Purged %u/%u\n", (total - num_clean), total);
 	return;
@@ -625,9 +624,23 @@ purge_gnt_list:
 			print_stats(blkif);
 	}
 
-	/* Since we are shutting down remove all pages from the buffer */
-	shrink_free_pagepool(blkif, 0 /* All */);
+	/* Drain pending purge work */
+	flush_work(&blkif->persistent_purge_work);
 
+	if (log_stats)
+		print_stats(blkif);
+
+	blkif->xenblkd = NULL;
+	xen_blkif_put(blkif);
+
+	return 0;
+}
+
+/*
+ * Remove persistent grants and empty the pool of free pages
+ */
+void xen_blkbk_free_caches(struct xen_blkif *blkif)
+{
 	/* Free all persistent grant pages */
 	if (!RB_EMPTY_ROOT(&blkif->persistent_gnts))
 		free_persistent_gnts(blkif, &blkif->persistent_gnts,
@@ -636,13 +649,8 @@ purge_gnt_list:
 	BUG_ON(!RB_EMPTY_ROOT(&blkif->persistent_gnts));
 	blkif->persistent_gnt_c = 0;
 
-	if (log_stats)
-		print_stats(blkif);
-
-	blkif->xenblkd = NULL;
-	xen_blkif_put(blkif);
-
-	return 0;
+	/* Since we are shutting down remove all pages from the buffer */
+	shrink_free_pagepool(blkif, 0 /* All */);
 }
 
 /*
@@ -838,7 +846,7 @@ static int xen_blkbk_parse_indirect(struct blkif_request *req,
 	struct grant_page **pages = pending_req->indirect_pages;
 	struct xen_blkif *blkif = pending_req->blkif;
 	int indirect_grefs, rc, n, nseg, i;
-	struct blkif_request_segment_aligned *segments = NULL;
+	struct blkif_request_segment *segments = NULL;
 
 	nseg = pending_req->nr_pages;
 	indirect_grefs = INDIRECT_PAGES(nseg);
@@ -934,9 +942,7 @@ static void xen_blk_drain_io(struct xen_blkif *blkif)
 {
 	atomic_set(&blkif->drain, 1);
 	do {
-		/* The initial value is one, and one refcnt taken at the
-		 * start of the xen_blkif_schedule thread. */
-		if (atomic_read(&blkif->refcnt) <= 2)
+		if (atomic_read(&blkif->inflight) == 0)
 			break;
 		wait_for_completion_interruptible_timeout(
 				&blkif->drain_complete, HZ);
@@ -976,17 +982,30 @@ static void __end_block_io_op(struct pending_req *pending_req, int error)
 	 * the proper response on the ring.
 	 */
 	if (atomic_dec_and_test(&pending_req->pendcnt)) {
-		xen_blkbk_unmap(pending_req->blkif,
+		struct xen_blkif *blkif = pending_req->blkif;
+
+		xen_blkbk_unmap(blkif,
 		                pending_req->segments,
 		                pending_req->nr_pages);
-		make_response(pending_req->blkif, pending_req->id,
+		make_response(blkif, pending_req->id,
 			      pending_req->operation, pending_req->status);
-		xen_blkif_put(pending_req->blkif);
-		if (atomic_read(&pending_req->blkif->refcnt) <= 2) {
-			if (atomic_read(&pending_req->blkif->drain))
-				complete(&pending_req->blkif->drain_complete);
+		free_req(blkif, pending_req);
+		/*
+		 * Make sure the request is freed before releasing blkif,
+		 * or there could be a race between free_req and the
+		 * cleanup done in xen_blkif_free during shutdown.
+		 *
+		 * NB: The fact that we might try to wake up pending_free_wq
+		 * before drain_complete (in case there's a drain going on)
+		 * it's not a problem with our current implementation
+		 * because we can assure there's no thread waiting on
+		 * pending_free_wq if there's a drain going on, but it has
+		 * to be taken into account if the current model is changed.
+		 */
+		if (atomic_dec_and_test(&blkif->inflight) && atomic_read(&blkif->drain)) {
+			complete(&blkif->drain_complete);
 		}
-		free_req(pending_req->blkif, pending_req);
+		xen_blkif_put(blkif);
 	}
 }
 
@@ -1240,6 +1259,7 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif,
 	 * below (in "!bio") if we are handling a BLKIF_OP_DISCARD.
 	 */
 	xen_blkif_get(blkif);
+	atomic_inc(&blkif->inflight);
 
 	for (i = 0; i < nseg; i++) {
 		while ((bio == NULL) ||
diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h
index 8d8807563d99..be052773ad03 100644
--- a/drivers/block/xen-blkback/common.h
+++ b/drivers/block/xen-blkback/common.h
@@ -57,7 +57,7 @@
 #define MAX_INDIRECT_SEGMENTS 256
 
 #define SEGS_PER_INDIRECT_FRAME \
-	(PAGE_SIZE/sizeof(struct blkif_request_segment_aligned))
+	(PAGE_SIZE/sizeof(struct blkif_request_segment))
 #define MAX_INDIRECT_PAGES \
 	((MAX_INDIRECT_SEGMENTS + SEGS_PER_INDIRECT_FRAME - 1)/SEGS_PER_INDIRECT_FRAME)
 #define INDIRECT_PAGES(_segs) \
@@ -278,6 +278,7 @@ struct xen_blkif {
 	/* for barrier (drain) requests */
 	struct completion	drain_complete;
 	atomic_t		drain;
+	atomic_t		inflight;
 	/* One thread per one blkif. */
 	struct task_struct	*xenblkd;
 	unsigned int		waiting_reqs;
@@ -376,6 +377,7 @@ int xen_blkif_xenbus_init(void);
 irqreturn_t xen_blkif_be_int(int irq, void *dev_id);
 int xen_blkif_schedule(void *arg);
 int xen_blkif_purge_persistent(void *arg);
+void xen_blkbk_free_caches(struct xen_blkif *blkif);
 
 int xen_blkbk_flush_diskcache(struct xenbus_transaction xbt,
 			      struct backend_info *be, int state);
@@ -383,6 +385,7 @@ int xen_blkbk_flush_diskcache(struct xenbus_transaction xbt,
 int xen_blkbk_barrier(struct xenbus_transaction xbt,
 		      struct backend_info *be, int state);
 struct xenbus_device *xen_blkbk_xenbus(struct backend_info *be);
+void xen_blkbk_unmap_purged_grants(struct work_struct *work);
 
 static inline void blkif_get_x86_32_req(struct blkif_request *dst,
 					struct blkif_x86_32_request *src)
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index c2014a0aa206..9a547e6b6ebf 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -125,8 +125,11 @@ static struct xen_blkif *xen_blkif_alloc(domid_t domid)
 	blkif->persistent_gnts.rb_node = NULL;
 	spin_lock_init(&blkif->free_pages_lock);
 	INIT_LIST_HEAD(&blkif->free_pages);
+	INIT_LIST_HEAD(&blkif->persistent_purge_list);
 	blkif->free_pages_num = 0;
 	atomic_set(&blkif->persistent_gnt_in_use, 0);
+	atomic_set(&blkif->inflight, 0);
+	INIT_WORK(&blkif->persistent_purge_work, xen_blkbk_unmap_purged_grants);
 
 	INIT_LIST_HEAD(&blkif->pending_free);
 
@@ -259,6 +262,17 @@ static void xen_blkif_free(struct xen_blkif *blkif)
 	if (!atomic_dec_and_test(&blkif->refcnt))
 		BUG();
 
+	/* Remove all persistent grants and the cache of ballooned pages. */
+	xen_blkbk_free_caches(blkif);
+
+	/* Make sure everything is drained before shutting down */
+	BUG_ON(blkif->persistent_gnt_c != 0);
+	BUG_ON(atomic_read(&blkif->persistent_gnt_in_use) != 0);
+	BUG_ON(blkif->free_pages_num != 0);
+	BUG_ON(!list_empty(&blkif->persistent_purge_list));
+	BUG_ON(!list_empty(&blkif->free_pages));
+	BUG_ON(!RB_EMPTY_ROOT(&blkif->persistent_gnts));
+
 	/* Check that there is no request in use */
 	list_for_each_entry_safe(req, n, &blkif->pending_free, free_list) {
 		list_del(&req->free_list);
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 8dcfb54f1603..efe1b4761735 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -162,7 +162,7 @@ static DEFINE_SPINLOCK(minor_lock);
 #define DEV_NAME	"xvd"	/* name in /dev */
 
 #define SEGS_PER_INDIRECT_FRAME \
-	(PAGE_SIZE/sizeof(struct blkif_request_segment_aligned))
+	(PAGE_SIZE/sizeof(struct blkif_request_segment))
 #define INDIRECT_GREFS(_segs) \
 	((_segs + SEGS_PER_INDIRECT_FRAME - 1)/SEGS_PER_INDIRECT_FRAME)
 
@@ -393,7 +393,7 @@ static int blkif_queue_request(struct request *req)
 	unsigned long id;
 	unsigned int fsect, lsect;
 	int i, ref, n;
-	struct blkif_request_segment_aligned *segments = NULL;
+	struct blkif_request_segment *segments = NULL;
 
 	/*
 	 * Used to store if we are able to queue the request by just using
@@ -550,7 +550,7 @@ static int blkif_queue_request(struct request *req)
 			} else {
 				n = i % SEGS_PER_INDIRECT_FRAME;
 				segments[n] =
-					(struct blkif_request_segment_aligned) {
+					(struct blkif_request_segment) {
 							.gref       = ref,
 							.first_sect = fsect,
 							.last_sect  = lsect };
@@ -1904,13 +1904,16 @@ static void blkback_changed(struct xenbus_device *dev,
 	case XenbusStateReconfiguring:
 	case XenbusStateReconfigured:
 	case XenbusStateUnknown:
-	case XenbusStateClosed:
 		break;
 
 	case XenbusStateConnected:
 		blkfront_connect(info);
 		break;
 
+	case XenbusStateClosed:
+		if (dev->state == XenbusStateClosed)
+			break;
+		/* Missed the backend's Closing state -- fallthrough */
 	case XenbusStateClosing:
 		blkfront_closing(info);
 		break;