4 files changed, 65 insertions, 26 deletions

diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index 4b97b86da926..765fc7348b66 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -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) {
@@ -625,9 +625,23 @@ 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 +650,8 @@ 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 +847,7 @@ 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 +943,7 @@ 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 +983,30 @@ 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 +1260,7 @@ 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..9eb34e24b4fe 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);
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index c2014a0aa206..84973c6a856a 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -125,8 +125,10 @@ 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_LIST_HEAD(&blkif->pending_free);
 
@@ -259,6 +261,17 @@ 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;