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

Pull block layer updates from Jens Axboe:
 "I've got a few bits pending for 3.8 final, that I better get sent out.
  It's all been sitting for a while, I consider it safe.

  It contains:

   - Two bug fixes for mtip32xx, fixing a driver hang and a crash.

   - A few-liner protocol error fix for drbd.

   - A few fixes for the xen block front/back driver, fixing a potential
     data corruption issue.

   - A race fix for disk_clear_events(), causing spurious warnings.  Out
     of the Chrome OS base.

   - A deadlock fix for disk_clear_events(), moving it to the a
     unfreezable workqueue.  Also from the Chrome OS base."

* 'for-linus' of git://git.kernel.dk/linux-block:
  drbd: fix potential protocol error and resulting disconnect/reconnect
  mtip32xx: fix for crash when the device surprise removed during rebuild
  mtip32xx: fix for driver hang after a command timeout
  block: prevent race/cleanup
  block: remove deadlock in disk_clear_events
  xen-blkfront: handle bvecs with partial data
  llist/xen-blkfront: implement safe version of llist_for_each_entry
  xen-blkback: implement safe iterator for the list of persistent grants

block/genhd.c

@@ -35,6 +35,8 @@ static DEFINE_IDR(ext_devt_idr);
 
 static struct device_type disk_type;
 
+static void disk_check_events(struct disk_events *ev,
+			      unsigned int *clearing_ptr);
 static void disk_alloc_events(struct gendisk *disk);
 static void disk_add_events(struct gendisk *disk);
 static void disk_del_events(struct gendisk *disk);
@@ -1549,6 +1551,7 @@ unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask)
 	const struct block_device_operations *bdops = disk->fops;
 	struct disk_events *ev = disk->ev;
 	unsigned int pending;
+	unsigned int clearing = mask;
 
 	if (!ev) {
 		/* for drivers still using the old ->media_changed method */
@@ -1558,34 +1561,53 @@ unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask)
 		return 0;
 	}
 
-	/* tell the workfn about the events being cleared */
+	disk_block_events(disk);
+
+	/*
+	 * store the union of mask and ev->clearing on the stack so that the
+	 * race with disk_flush_events does not cause ambiguity (ev->clearing
+	 * can still be modified even if events are blocked).
+	 */
 	spin_lock_irq(&ev->lock);
-	ev->clearing |= mask;
+	clearing |= ev->clearing;
+	ev->clearing = 0;
 	spin_unlock_irq(&ev->lock);
 
-	/* uncondtionally schedule event check and wait for it to finish */
-	disk_block_events(disk);
-	queue_delayed_work(system_freezable_wq, &ev->dwork, 0);
-	flush_delayed_work(&ev->dwork);
-	__disk_unblock_events(disk, false);
+	disk_check_events(ev, &clearing);
+	/*
+	 * if ev->clearing is not 0, the disk_flush_events got called in the
+	 * middle of this function, so we want to run the workfn without delay.
+	 */
+	__disk_unblock_events(disk, ev->clearing ? true : false);
 
 	/* then, fetch and clear pending events */
 	spin_lock_irq(&ev->lock);
-	WARN_ON_ONCE(ev->clearing & mask);	/* cleared by workfn */
 	pending = ev->pending & mask;
 	ev->pending &= ~mask;
 	spin_unlock_irq(&ev->lock);
+	WARN_ON_ONCE(clearing & mask);
 
 	return pending;
 }
 
+/*
+ * Separate this part out so that a different pointer for clearing_ptr can be
+ * passed in for disk_clear_events.
+ */
 static void disk_events_workfn(struct work_struct *work)
 {
 	struct delayed_work *dwork = to_delayed_work(work);
 	struct disk_events *ev = container_of(dwork, struct disk_events, dwork);
+
+	disk_check_events(ev, &ev->clearing);
+}
+
+static void disk_check_events(struct disk_events *ev,
+			      unsigned int *clearing_ptr)
+{
 	struct gendisk *disk = ev->disk;
 	char *envp[ARRAY_SIZE(disk_uevents) + 1] = { };
-	unsigned int clearing = ev->clearing;
+	unsigned int clearing = *clearing_ptr;
 	unsigned int events;
 	unsigned long intv;
 	int nr_events = 0, i;
@@ -1598,7 +1620,7 @@ static void disk_events_workfn(struct work_struct *work)
 
 	events &= ~ev->pending;
 	ev->pending |= events;
-	ev->clearing &= ~clearing;
+	*clearing_ptr &= ~clearing;
 
 	intv = disk_events_poll_jiffies(disk);
 	if (!ev->block && intv)

drivers/block/drbd/drbd_req.c

@@ -168,7 +168,7 @@ static void wake_all_senders(struct drbd_tconn *tconn) {
 }
 
 /* must hold resource->req_lock */
-static void start_new_tl_epoch(struct drbd_tconn *tconn)
+void start_new_tl_epoch(struct drbd_tconn *tconn)
 {
 	/* no point closing an epoch, if it is empty, anyways. */
 	if (tconn->current_tle_writes == 0)

drivers/block/drbd/drbd_req.h

@@ -267,6 +267,7 @@ struct bio_and_error {
 	int error;
 };
 
+extern void start_new_tl_epoch(struct drbd_tconn *tconn);
 extern void drbd_req_destroy(struct kref *kref);
 extern void _req_may_be_done(struct drbd_request *req,
 		struct bio_and_error *m);

drivers/block/drbd/drbd_state.c

@@ -931,6 +931,7 @@ __drbd_set_state(struct drbd_conf *mdev, union drbd_state ns,
 	enum drbd_state_rv rv = SS_SUCCESS;
 	enum sanitize_state_warnings ssw;
 	struct after_state_chg_work *ascw;
+	bool did_remote, should_do_remote;
 
 	os = drbd_read_state(mdev);
 
@@ -981,11 +982,17 @@ __drbd_set_state(struct drbd_conf *mdev, union drbd_state ns,
 	    (os.disk != D_DISKLESS && ns.disk == D_DISKLESS))
 		atomic_inc(&mdev->local_cnt);
 
+	did_remote = drbd_should_do_remote(mdev->state);
 	mdev->state.i = ns.i;
+	should_do_remote = drbd_should_do_remote(mdev->state);
 	mdev->tconn->susp = ns.susp;
 	mdev->tconn->susp_nod = ns.susp_nod;
 	mdev->tconn->susp_fen = ns.susp_fen;
 
+	/* put replicated vs not-replicated requests in seperate epochs */
+	if (did_remote != should_do_remote)
+		start_new_tl_epoch(mdev->tconn);
+
 	if (os.disk == D_ATTACHING && ns.disk >= D_NEGOTIATING)
 		drbd_print_uuids(mdev, "attached to UUIDs");
 

drivers/block/mtip32xx/mtip32xx.c

@@ -626,13 +626,14 @@ static void mtip_timeout_function(unsigned long int data)
 		}
 	}
 
-	if (cmdto_cnt && !test_bit(MTIP_PF_IC_ACTIVE_BIT, &port->flags)) {
+	if (cmdto_cnt) {
 		print_tags(port->dd, "timed out", tagaccum, cmdto_cnt);
-
+		if (!test_bit(MTIP_PF_IC_ACTIVE_BIT, &port->flags)) {
 			mtip_restart_port(port);
-		clear_bit(MTIP_PF_EH_ACTIVE_BIT, &port->flags);
 			wake_up_interruptible(&port->svc_wait);
 		}
+		clear_bit(MTIP_PF_EH_ACTIVE_BIT, &port->flags);
+	}
 
 	if (port->ic_pause_timer) {
 		to  = port->ic_pause_timer + msecs_to_jiffies(1000);
@@ -3887,7 +3888,12 @@ static int mtip_block_remove(struct driver_data *dd)
 	 * Delete our gendisk structure. This also removes the device
 	 * from /dev
 	 */
+	if (dd->disk) {
+		if (dd->disk->queue)
 			del_gendisk(dd->disk);
+		else
+			put_disk(dd->disk);
+	}
 
 	spin_lock(&rssd_index_lock);
 	ida_remove(&rssd_index_ida, dd->index);
@@ -3921,7 +3927,13 @@ static int mtip_block_shutdown(struct driver_data *dd)
 		"Shutting down %s ...\n", dd->disk->disk_name);
 
 	/* Delete our gendisk structure, and cleanup the blk queue. */
+	if (dd->disk) {
+		if (dd->disk->queue)
 			del_gendisk(dd->disk);
+		else
+			put_disk(dd->disk);
+	}
+
 
 	spin_lock(&rssd_index_lock);
 	ida_remove(&rssd_index_ida, dd->index);

drivers/block/xen-blkback/blkback.c

@@ -161,10 +161,12 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif,
 static void make_response(struct xen_blkif *blkif, u64 id,
 			  unsigned short op, int st);
 
-#define foreach_grant(pos, rbtree, node) \
-	for ((pos) = container_of(rb_first((rbtree)), typeof(*(pos)), node); \
+#define foreach_grant_safe(pos, n, rbtree, node) \
+	for ((pos) = container_of(rb_first((rbtree)), typeof(*(pos)), node), \
+	     (n) = rb_next(&(pos)->node); \
 	     &(pos)->node != NULL; \
-	     (pos) = container_of(rb_next(&(pos)->node), typeof(*(pos)), node))
+	     (pos) = container_of(n, typeof(*(pos)), node), \
+	     (n) = (&(pos)->node != NULL) ? rb_next(&(pos)->node) : NULL)
 
 
 static void add_persistent_gnt(struct rb_root *root,
@@ -217,10 +219,11 @@ static void free_persistent_gnts(struct rb_root *root, unsigned int num)
 	struct gnttab_unmap_grant_ref unmap[BLKIF_MAX_SEGMENTS_PER_REQUEST];
 	struct page *pages[BLKIF_MAX_SEGMENTS_PER_REQUEST];
 	struct persistent_gnt *persistent_gnt;
+	struct rb_node *n;
 	int ret = 0;
 	int segs_to_unmap = 0;
 
-	foreach_grant(persistent_gnt, root, node) {
+	foreach_grant_safe(persistent_gnt, n, root, node) {
 		BUG_ON(persistent_gnt->handle ==
 			BLKBACK_INVALID_HANDLE);
 		gnttab_set_unmap_op(&unmap[segs_to_unmap],
@@ -230,9 +233,6 @@ static void free_persistent_gnts(struct rb_root *root, unsigned int num)
 			persistent_gnt->handle);
 
 		pages[segs_to_unmap] = persistent_gnt->page;
-		rb_erase(&persistent_gnt->node, root);
-		kfree(persistent_gnt);
-		num--;
 
 		if (++segs_to_unmap == BLKIF_MAX_SEGMENTS_PER_REQUEST ||
 			!rb_next(&persistent_gnt->node)) {
@@ -241,6 +241,10 @@ static void free_persistent_gnts(struct rb_root *root, unsigned int num)
 			BUG_ON(ret);
 			segs_to_unmap = 0;
 		}
+
+		rb_erase(&persistent_gnt->node, root);
+		kfree(persistent_gnt);
+		num--;
 	}
 	BUG_ON(num != 0);
 }

drivers/block/xen-blkfront.c

@@ -792,6 +792,7 @@ static void blkif_free(struct blkfront_info *info, int suspend)
 {
 	struct llist_node *all_gnts;
 	struct grant *persistent_gnt;
+	struct llist_node *n;
 
 	/* Prevent new requests being issued until we fix things up. */
 	spin_lock_irq(&info->io_lock);
@@ -804,7 +805,7 @@ static void blkif_free(struct blkfront_info *info, int suspend)
 	/* Remove all persistent grants */
 	if (info->persistent_gnts_c) {
 		all_gnts = llist_del_all(&info->persistent_gnts);
-		llist_for_each_entry(persistent_gnt, all_gnts, node) {
+		llist_for_each_entry_safe(persistent_gnt, n, all_gnts, node) {
 			gnttab_end_foreign_access(persistent_gnt->gref, 0, 0UL);
 			__free_page(pfn_to_page(persistent_gnt->pfn));
 			kfree(persistent_gnt);
@@ -835,7 +836,7 @@ static void blkif_free(struct blkfront_info *info, int suspend)
 static void blkif_completion(struct blk_shadow *s, struct blkfront_info *info,
 			     struct blkif_response *bret)
 {
-	int i;
+	int i = 0;
 	struct bio_vec *bvec;
 	struct req_iterator iter;
 	unsigned long flags;
@@ -852,7 +853,8 @@ static void blkif_completion(struct blk_shadow *s, struct blkfront_info *info,
 		 */
 		rq_for_each_segment(bvec, s->request, iter) {
 			BUG_ON((bvec->bv_offset + bvec->bv_len) > PAGE_SIZE);
-			i = offset >> PAGE_SHIFT;
+			if (bvec->bv_offset < offset)
+				i++;
 			BUG_ON(i >= s->req.u.rw.nr_segments);
 			shared_data = kmap_atomic(
 				pfn_to_page(s->grants_used[i]->pfn));
@@ -861,7 +863,7 @@ static void blkif_completion(struct blk_shadow *s, struct blkfront_info *info,
 				bvec->bv_len);
 			bvec_kunmap_irq(bvec_data, &flags);
 			kunmap_atomic(shared_data);
-			offset += bvec->bv_len;
+			offset = bvec->bv_offset + bvec->bv_len;
 		}
 	}
 	/* Add the persistent grant into the list of free grants */

include/linux/llist.h

@@ -124,6 +124,31 @@ static inline void init_llist_head(struct llist_head *list)
 	     &(pos)->member != NULL;					\
 	     (pos) = llist_entry((pos)->member.next, typeof(*(pos)), member))
 
+/**
+ * llist_for_each_entry_safe - iterate safely against remove over some entries
+ * of lock-less list of given type.
+ * @pos:	the type * to use as a loop cursor.
+ * @n:		another type * to use as a temporary storage.
+ * @node:	the fist entry of deleted list entries.
+ * @member:	the name of the llist_node with the struct.
+ *
+ * In general, some entries of the lock-less list can be traversed
+ * safely only after being removed from list, so start with an entry
+ * instead of list head. This variant allows removal of entries
+ * as we iterate.
+ *
+ * If being used on entries deleted from lock-less list directly, the
+ * traverse order is from the newest to the oldest added entry.  If
+ * you want to traverse from the oldest to the newest, you must
+ * reverse the order by yourself before traversing.
+ */
+#define llist_for_each_entry_safe(pos, n, node, member)		\
+	for ((pos) = llist_entry((node), typeof(*(pos)), member),	\
+	     (n) = (pos)->member.next;					\
+	     &(pos)->member != NULL;					\
+	     (pos) = llist_entry(n, typeof(*(pos)), member),		\
+	     (n) = (&(pos)->member != NULL) ? (pos)->member.next : NULL)
+
 /**
  * llist_empty - tests whether a lock-less list is empty
  * @head:	the list to test