2 files changed, 52 insertions, 14 deletions

diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 78c975d7cd5f..b0ca9c9effe9 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -253,17 +253,35 @@ MODULE_PARM_DESC(max_read_size, "Maximum size of a read request");
 static unsigned int max_write_size = 0;
 module_param(max_write_size, uint, 0644);
 MODULE_PARM_DESC(max_write_size, "Maximum size of a write request");
-static unsigned get_max_request_size(struct crypt_config *cc, bool wrt)
+
+static unsigned get_max_request_sectors(struct dm_target *ti, struct bio *bio)
 {
+	struct crypt_config *cc = ti->private;
 	unsigned val, sector_align;
-	val = !wrt ? READ_ONCE(max_read_size) : READ_ONCE(max_write_size);
-	if (likely(!val))
-		val = !wrt ? DM_CRYPT_DEFAULT_MAX_READ_SIZE : DM_CRYPT_DEFAULT_MAX_WRITE_SIZE;
-	if (wrt || cc->used_tag_size) {
-		if (unlikely(val > BIO_MAX_VECS << PAGE_SHIFT))
-			val = BIO_MAX_VECS << PAGE_SHIFT;
-	}
-	sector_align = max(bdev_logical_block_size(cc->dev->bdev), (unsigned)cc->sector_size);
+	bool wrt = op_is_write(bio_op(bio));
+
+	if (wrt) {
+		/*
+		 * For zoned devices, splitting write operations creates the
+		 * risk of deadlocking queue freeze operations with zone write
+		 * plugging BIO work when the reminder of a split BIO is
+		 * issued. So always allow the entire BIO to proceed.
+		 */
+		if (ti->emulate_zone_append)
+			return bio_sectors(bio);
+
+		val = min_not_zero(READ_ONCE(max_write_size),
+				   DM_CRYPT_DEFAULT_MAX_WRITE_SIZE);
+	} else {
+		val = min_not_zero(READ_ONCE(max_read_size),
+				   DM_CRYPT_DEFAULT_MAX_READ_SIZE);
+	}
+
+	if (wrt || cc->used_tag_size)
+		val = min(val, BIO_MAX_VECS << PAGE_SHIFT);
+
+	sector_align = max(bdev_logical_block_size(cc->dev->bdev),
+			   (unsigned)cc->sector_size);
 	val = round_down(val, sector_align);
 	if (unlikely(!val))
 		val = sector_align;
@@ -3517,7 +3535,7 @@ static int crypt_map(struct dm_target *ti, struct bio *bio)
 	/*
 	 * Check if bio is too large, split as needed.
 	 */
-	max_sectors = get_max_request_size(cc, bio_data_dir(bio) == WRITE);
+	max_sectors = get_max_request_sectors(ti, bio);
 	if (unlikely(bio_sectors(bio) > max_sectors))
 		dm_accept_partial_bio(bio, max_sectors);
 
@@ -3754,6 +3772,17 @@ static void crypt_io_hints(struct dm_target *ti, struct queue_limits *limits)
 		max_t(unsigned int, limits->physical_block_size, cc->sector_size);
 	limits->io_min = max_t(unsigned int, limits->io_min, cc->sector_size);
 	limits->dma_alignment = limits->logical_block_size - 1;
+
+	/*
+	 * For zoned dm-crypt targets, there will be no internal splitting of
+	 * write BIOs to avoid exceeding BIO_MAX_VECS vectors per BIO. But
+	 * without respecting this limit, crypt_alloc_buffer() will trigger a
+	 * BUG(). Avoid this by forcing DM core to split write BIOs to this
+	 * limit.
+	 */
+	if (ti->emulate_zone_append)
+		limits->max_hw_sectors = min(limits->max_hw_sectors,
+					     BIO_MAX_VECS << PAGE_SECTORS_SHIFT);
 }
 
 static struct target_type crypt_target = {
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index c5dcd632404c..a7deeda59a55 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1307,8 +1307,9 @@ out:
 /*
  * A target may call dm_accept_partial_bio only from the map routine.  It is
  * allowed for all bio types except REQ_PREFLUSH, REQ_OP_ZONE_* zone management
- * operations, REQ_OP_ZONE_APPEND (zone append writes) and any bio serviced by
- * __send_duplicate_bios().
+ * operations, zone append writes (native with REQ_OP_ZONE_APPEND or emulated
+ * with write BIOs flagged with BIO_EMULATES_ZONE_APPEND) and any bio serviced
+ * by __send_duplicate_bios().
  *
  * dm_accept_partial_bio informs the dm that the target only wants to process
  * additional n_sectors sectors of the bio and the rest of the data should be
@@ -1341,11 +1342,19 @@ void dm_accept_partial_bio(struct bio *bio, unsigned int n_sectors)
 	unsigned int bio_sectors = bio_sectors(bio);
 
 	BUG_ON(dm_tio_flagged(tio, DM_TIO_IS_DUPLICATE_BIO));
-	BUG_ON(op_is_zone_mgmt(bio_op(bio)));
-	BUG_ON(bio_op(bio) == REQ_OP_ZONE_APPEND);
 	BUG_ON(bio_sectors > *tio->len_ptr);
 	BUG_ON(n_sectors > bio_sectors);
 
+	if (static_branch_unlikely(&zoned_enabled) &&
+	    unlikely(bdev_is_zoned(bio->bi_bdev))) {
+		enum req_op op = bio_op(bio);
+
+		BUG_ON(op_is_zone_mgmt(op));
+		BUG_ON(op == REQ_OP_WRITE);
+		BUG_ON(op == REQ_OP_WRITE_ZEROES);
+		BUG_ON(op == REQ_OP_ZONE_APPEND);
+	}
+
 	*tio->len_ptr -= bio_sectors - n_sectors;
 	bio->bi_iter.bi_size = n_sectors << SECTOR_SHIFT;