Merge tag 'dm-3.13-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm

Pull device mapper fixes from Mike Snitzer:
 "A set of device-mapper fixes for 3.13.

  A fix for possible memory corruption during DM table load, fix a
  possible leak of snapshot space in case of a crash, fix a possible
  deadlock due to a shared workqueue in the delay target, fix to
  initialize read-only module parameters that are used to export metrics
  for dm stats and dm bufio.

  Quite a few stable fixes were identified for both the thin-
  provisioning and caching targets as a result of increased regression
  testing using the device-mapper-test-suite (dmts).  The most notable
  of these are the reference counting fixes for the space map btree that
  is used by the dm-array interface -- without these the dm-cache
  metadata will leak, resulting in dm-cache devices running out of
  metadata blocks.  Also, some important fixes related to the
  thin-provisioning target's transition to read-only mode on error"

* tag 'dm-3.13-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
  dm array: fix a reference counting bug in shadow_ablock
  dm space map: disallow decrementing a reference count below zero
  dm stats: initialize read-only module parameter
  dm bufio: initialize read-only module parameters
  dm cache: actually resize cache
  dm cache: update Documentation for invalidate_cblocks's range syntax
  dm cache policy mq: fix promotions to occur as expected
  dm thin: allow pool in read-only mode to transition to read-write mode
  dm thin: re-establish read-only state when switching to fail mode
  dm thin: always fallback the pool mode if commit fails
  dm thin: switch to read-only mode if metadata space is exhausted
  dm thin: switch to read only mode if a mapping insert fails
  dm space map metadata: return on failure in sm_metadata_new_block
  dm table: fail dm_table_create on dm_round_up overflow
  dm snapshot: avoid snapshot space leak on crash
  dm delay: fix a possible deadlock due to shared workqueue

1 files changed, 64 insertions, 7 deletions

diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index aec57d76db5d..944690bafd93 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -66,6 +66,18 @@ struct dm_snapshot {
 
 	atomic_t pending_exceptions_count;
 
+	/* Protected by "lock" */
+	sector_t exception_start_sequence;
+
+	/* Protected by kcopyd single-threaded callback */
+	sector_t exception_complete_sequence;
+
+	/*
+	 * A list of pending exceptions that completed out of order.
+	 * Protected by kcopyd single-threaded callback.
+	 */
+	struct list_head out_of_order_list;
+
 	mempool_t *pending_pool;
 
 	struct dm_exception_table pending;
@@ -173,6 +185,14 @@ struct dm_snap_pending_exception {
 	 */
 	int started;
 
+	/* There was copying error. */
+	int copy_error;
+
+	/* A sequence number, it is used for in-order completion. */
+	sector_t exception_sequence;
+
+	struct list_head out_of_order_entry;
+
 	/*
 	 * For writing a complete chunk, bypassing the copy.
 	 */
@@ -1094,6 +1114,9 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	s->valid = 1;
 	s->active = 0;
 	atomic_set(&s->pending_exceptions_count, 0);
+	s->exception_start_sequence = 0;
+	s->exception_complete_sequence = 0;
+	INIT_LIST_HEAD(&s->out_of_order_list);
 	init_rwsem(&s->lock);
 	INIT_LIST_HEAD(&s->list);
 	spin_lock_init(&s->pe_lock);
@@ -1443,6 +1466,19 @@ static void commit_callback(void *context, int success)
 	pending_complete(pe, success);
 }
 
+static void complete_exception(struct dm_snap_pending_exception *pe)
+{
+	struct dm_snapshot *s = pe->snap;
+
+	if (unlikely(pe->copy_error))
+		pending_complete(pe, 0);
+
+	else
+		/* Update the metadata if we are persistent */
+		s->store->type->commit_exception(s->store, &pe->e,
+						 commit_callback, pe);
+}
+
 /*
  * Called when the copy I/O has finished.  kcopyd actually runs
  * this code so don't block.
@@ -1452,13 +1488,32 @@ static void copy_callback(int read_err, unsigned long write_err, void *context)
 	struct dm_snap_pending_exception *pe = context;
 	struct dm_snapshot *s = pe->snap;
 
-	if (read_err || write_err)
-		pending_complete(pe, 0);
+	pe->copy_error = read_err || write_err;
 
-	else
-		/* Update the metadata if we are persistent */
-		s->store->type->commit_exception(s->store, &pe->e,
-						 commit_callback, pe);
+	if (pe->exception_sequence == s->exception_complete_sequence) {
+		s->exception_complete_sequence++;
+		complete_exception(pe);
+
+		while (!list_empty(&s->out_of_order_list)) {
+			pe = list_entry(s->out_of_order_list.next,
+					struct dm_snap_pending_exception, out_of_order_entry);
+			if (pe->exception_sequence != s->exception_complete_sequence)
+				break;
+			s->exception_complete_sequence++;
+			list_del(&pe->out_of_order_entry);
+			complete_exception(pe);
+		}
+	} else {
+		struct list_head *lh;
+		struct dm_snap_pending_exception *pe2;
+
+		list_for_each_prev(lh, &s->out_of_order_list) {
+			pe2 = list_entry(lh, struct dm_snap_pending_exception, out_of_order_entry);
+			if (pe2->exception_sequence < pe->exception_sequence)
+				break;
+		}
+		list_add(&pe->out_of_order_entry, lh);
+	}
 }
 
 /*
@@ -1553,6 +1608,8 @@ __find_pending_exception(struct dm_snapshot *s,
 		return NULL;
 	}
 
+	pe->exception_sequence = s->exception_start_sequence++;
+
 	dm_insert_exception(&s->pending, &pe->e);
 
 	return pe;
@@ -2192,7 +2249,7 @@ static struct target_type origin_target = {
 
 static struct target_type snapshot_target = {
 	.name    = "snapshot",
-	.version = {1, 11, 1},
+	.version = {1, 12, 0},
 	.module  = THIS_MODULE,
 	.ctr     = snapshot_ctr,
 	.dtr     = snapshot_dtr,