Merge tag 'for-5.9/dm-changes' of git://git.kernel.org/pub/scm/linux/…

…kernel/git/device-mapper/linux-dm

Pull device mapper updates from Mike Snitzer:

 - DM multipath locking fixes around m->flags tests and improvements to
   bio-based code so that it follows patterns established by
   request-based code.

 - Request-based DM core improvement to eliminate unnecessary call to
   blk_mq_queue_stopped().

 - Add "panic_on_corruption" error handling mode to DM verity target.

 - DM bufio fix to to perform buffer cleanup from a workqueue rather
   than wait for IO in reclaim context from shrinker.

 - DM crypt improvement to optionally avoid async processing via
   workqueues for reads and/or writes -- via "no_read_workqueue" and
   "no_write_workqueue" features. This more direct IO processing
   improves latency and throughput with faster storage. Avoiding
   workqueue IO submission for writes (DM_CRYPT_NO_WRITE_WORKQUEUE) is a
   requirement for adding zoned block device support to DM crypt.

 - Add zoned block device support to DM crypt. Makes use of
   DM_CRYPT_NO_WRITE_WORKQUEUE and a new optional feature
   (DM_CRYPT_WRITE_INLINE) that allows write completion to wait for
   encryption to complete. This allows write ordering to be preserved,
   which is needed for zoned block devices.

 - Fix DM ebs target's check for REQ_OP_FLUSH.

 - Fix DM core's report zones support to not report more zones than were
   requested.

 - A few small compiler warning fixes.

 - DM dust improvements to return output directly to the user rather
   than require they scrape the system log for output.

* tag 'for-5.9/dm-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
  dm: don't call report zones for more than the user requested
  dm ebs: Fix incorrect checking for REQ_OP_FLUSH
  dm init: Set file local variable static
  dm ioctl: Fix compilation warning
  dm raid: Remove empty if statement
  dm verity: Fix compilation warning
  dm crypt: Enable zoned block device support
  dm crypt: add flags to optionally bypass kcryptd workqueues
  dm bufio: do buffer cleanup from a workqueue
  dm rq: don't call blk_mq_queue_stopped() in dm_stop_queue()
  dm dust: add interface to list all badblocks
  dm dust: report some message results directly back to user
  dm verity: add "panic_on_corruption" error handling mode
  dm mpath: use double checked locking in fast path
  dm mpath: rename current_pgpath to pgpath in multipath_prepare_ioctl
  dm mpath: rework __map_bio()
  dm mpath: factor out multipath_queue_bio
  dm mpath: push locking down to must_push_back_rq()
  dm mpath: take m->lock spinlock when testing QUEUE_IF_NO_PATH
  dm mpath: changes from initial m->flags locking audit

Documentation/admin-guide/device-mapper/dm-dust.rst

@@ -69,10 +69,11 @@ Create the dm-dust device:
         $ sudo dmsetup create dust1 --table '0 33552384 dust /dev/vdb1 0 4096'
 
 Check the status of the read behavior ("bypass" indicates that all I/O
-will be passed through to the underlying device)::
+will be passed through to the underlying device; "verbose" indicates that
+bad block additions, removals, and remaps will be verbosely logged)::
 
         $ sudo dmsetup status dust1
-        0 33552384 dust 252:17 bypass
+        0 33552384 dust 252:17 bypass verbose
 
         $ sudo dd if=/dev/mapper/dust1 of=/dev/null bs=512 count=128 iflag=direct
         128+0 records in
@@ -164,7 +165,7 @@ following message command::
 A message will print with the number of bad blocks currently
 configured on the device::
 
-        kernel: device-mapper: dust: countbadblocks: 895 badblock(s) found
+        countbadblocks: 895 badblock(s) found
 
 Querying for specific bad blocks
 --------------------------------
@@ -176,11 +177,11 @@ following message command::
 
 The following message will print if the block is in the list::
 
-        device-mapper: dust: queryblock: block 72 found in badblocklist
+        dust_query_block: block 72 found in badblocklist
 
 The following message will print if the block is not in the list::
 
-        device-mapper: dust: queryblock: block 72 not found in badblocklist
+        dust_query_block: block 72 not found in badblocklist
 
 The "queryblock" message command will work in both the "enabled"
 and "disabled" modes, allowing the verification of whether a block
@@ -198,12 +199,28 @@ following message command::
 
 After clearing the bad block list, the following message will appear::
 
-        kernel: device-mapper: dust: clearbadblocks: badblocks cleared
+        dust_clear_badblocks: badblocks cleared
 
 If there were no bad blocks to clear, the following message will
 appear::
 
-        kernel: device-mapper: dust: clearbadblocks: no badblocks found
+        dust_clear_badblocks: no badblocks found
+
+Listing the bad block list
+--------------------------
+
+To list all bad blocks in the bad block list (using an example device
+with blocks 1 and 2 in the bad block list), run the following message
+command::
+
+        $ sudo dmsetup message dust1 0 listbadblocks
+        1
+        2
+
+If there are no bad blocks in the bad block list, the command will
+execute with no output::
+
+        $ sudo dmsetup message dust1 0 listbadblocks
 
 Message commands list
 ---------------------
@@ -223,6 +240,7 @@ Single argument message commands::
 
         countbadblocks
         clearbadblocks
+        listbadblocks
         disable
         enable
         quiet

Documentation/admin-guide/device-mapper/verity.rst

@@ -83,6 +83,10 @@ restart_on_corruption
     not compatible with ignore_corruption and requires user space support to
     avoid restart loops.
 
+panic_on_corruption
+    Panic the device when a corrupted block is discovered. This option is
+    not compatible with ignore_corruption and restart_on_corruption.
+
 ignore_zero_blocks
     Do not verify blocks that are expected to contain zeroes and always return
     zeroes instead. This may be useful if the partition contains unused blocks

drivers/md/dm-bufio.c

@@ -108,7 +108,10 @@ struct dm_bufio_client {
 	int async_write_error;
 
 	struct list_head client_list;
+
 	struct shrinker shrinker;
+	struct work_struct shrink_work;
+	atomic_long_t need_shrink;
 };
 
 /*
@@ -1634,8 +1637,7 @@ static unsigned long get_retain_buffers(struct dm_bufio_client *c)
 	return retain_bytes;
 }
 
-static unsigned long __scan(struct dm_bufio_client *c, unsigned long nr_to_scan,
-			    gfp_t gfp_mask)
+static void __scan(struct dm_bufio_client *c)
 {
 	int l;
 	struct dm_buffer *b, *tmp;
@@ -1646,42 +1648,58 @@ static unsigned long __scan(struct dm_bufio_client *c, unsigned long nr_to_scan,
 
 	for (l = 0; l < LIST_SIZE; l++) {
 		list_for_each_entry_safe_reverse(b, tmp, &c->lru[l], lru_list) {
-			if (__try_evict_buffer(b, gfp_mask))
+			if (count - freed <= retain_target)
+				atomic_long_set(&c->need_shrink, 0);
+			if (!atomic_long_read(&c->need_shrink))
+				return;
+			if (__try_evict_buffer(b, GFP_KERNEL)) {
+				atomic_long_dec(&c->need_shrink);
 				freed++;
-			if (!--nr_to_scan || ((count - freed) <= retain_target))
-				return freed;
+			}
 			cond_resched();
 		}
 	}
-	return freed;
 }
 
-static unsigned long
-dm_bufio_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
+static void shrink_work(struct work_struct *w)
+{
+	struct dm_bufio_client *c = container_of(w, struct dm_bufio_client, shrink_work);
+
+	dm_bufio_lock(c);
+	__scan(c);
+	dm_bufio_unlock(c);
+}
+
+static unsigned long dm_bufio_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 {
 	struct dm_bufio_client *c;
-	unsigned long freed;
 
 	c = container_of(shrink, struct dm_bufio_client, shrinker);
-	if (sc->gfp_mask & __GFP_FS)
-		dm_bufio_lock(c);
-	else if (!dm_bufio_trylock(c))
-		return SHRINK_STOP;
+	atomic_long_add(sc->nr_to_scan, &c->need_shrink);
+	queue_work(dm_bufio_wq, &c->shrink_work);
 
-	freed  = __scan(c, sc->nr_to_scan, sc->gfp_mask);
-	dm_bufio_unlock(c);
-	return freed;
+	return sc->nr_to_scan;
 }
 
-static unsigned long
-dm_bufio_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
+static unsigned long dm_bufio_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
 {
 	struct dm_bufio_client *c = container_of(shrink, struct dm_bufio_client, shrinker);
 	unsigned long count = READ_ONCE(c->n_buffers[LIST_CLEAN]) +
 			      READ_ONCE(c->n_buffers[LIST_DIRTY]);
 	unsigned long retain_target = get_retain_buffers(c);
+	unsigned long queued_for_cleanup = atomic_long_read(&c->need_shrink);
+
+	if (unlikely(count < retain_target))
+		count = 0;
+	else
+		count -= retain_target;
 
-	return (count < retain_target) ? 0 : (count - retain_target);
+	if (unlikely(count < queued_for_cleanup))
+		count = 0;
+	else
+		count -= queued_for_cleanup;
+
+	return count;
 }
 
 /*
@@ -1772,6 +1790,9 @@ struct dm_bufio_client *dm_bufio_client_create(struct block_device *bdev, unsign
 		__free_buffer_wake(b);
 	}
 
+	INIT_WORK(&c->shrink_work, shrink_work);
+	atomic_long_set(&c->need_shrink, 0);
+
 	c->shrinker.count_objects = dm_bufio_shrink_count;
 	c->shrinker.scan_objects = dm_bufio_shrink_scan;
 	c->shrinker.seeks = 1;
@@ -1817,6 +1838,7 @@ void dm_bufio_client_destroy(struct dm_bufio_client *c)
 	drop_buffers(c);
 
 	unregister_shrinker(&c->shrinker);
+	flush_work(&c->shrink_work);
 
 	mutex_lock(&dm_bufio_clients_lock);