dax: Arrange for dax_supported check to span multiple devices

Pankaj reports that starting with commit ad428cdb525a "dax: Check the
end of the block-device capacity with dax_direct_access()" device-mapper
no longer allows dax operation. This results from the stricter checks in
__bdev_dax_supported() that validate that the start and end of a
block-device map to the same 'pagemap' instance.

Teach the dax-core and device-mapper to validate the 'pagemap' on a
per-target basis. This is accomplished by refactoring the
bdev_dax_supported() internals into generic_fsdax_supported() which
takes a sector range to validate. Consequently generic_fsdax_supported()
is suitable to be used in a device-mapper ->iterate_devices() callback.
A new ->dax_supported() operation is added to allow composite devices to
split and route upper-level bdev_dax_supported() requests.

Fixes: ad428cdb525a ("dax: Check the end of the block-device...")
Cc: <stable@vger.kernel.org>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Keith Busch <keith.busch@intel.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Reported-by: Pankaj Gupta <pagupta@redhat.com>
Reviewed-by: Pankaj Gupta <pagupta@redhat.com>
Tested-by: Pankaj Gupta <pagupta@redhat.com>
Tested-by: Vaibhav Jain <vaibhav@linux.ibm.com>
Reviewed-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

3 files changed, 32 insertions, 6 deletions

diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index cde3b49b2a91..350cf0451456 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -880,13 +880,17 @@ void dm_table_set_type(struct dm_table *t, enum dm_queue_mode type)
 }
 EXPORT_SYMBOL_GPL(dm_table_set_type);
 
+/* validate the dax capability of the target device span */
 static int device_supports_dax(struct dm_target *ti, struct dm_dev *dev,
-			       sector_t start, sector_t len, void *data)
+				       sector_t start, sector_t len, void *data)
 {
-	return bdev_dax_supported(dev->bdev, PAGE_SIZE);
+	int blocksize = *(int *) data;
+
+	return generic_fsdax_supported(dev->dax_dev, dev->bdev, blocksize,
+			start, len);
 }
 
-static bool dm_table_supports_dax(struct dm_table *t)
+bool dm_table_supports_dax(struct dm_table *t, int blocksize)
 {
 	struct dm_target *ti;
 	unsigned i;
@@ -899,7 +903,8 @@ static bool dm_table_supports_dax(struct dm_table *t)
 			return false;
 
 		if (!ti->type->iterate_devices ||
-		    !ti->type->iterate_devices(ti, device_supports_dax, NULL))
+		    !ti->type->iterate_devices(ti, device_supports_dax,
+			    &blocksize))
 			return false;
 	}
 
@@ -979,7 +984,7 @@ static int dm_table_determine_type(struct dm_table *t)
 verify_bio_based:
 		/* We must use this table as bio-based */
 		t->type = DM_TYPE_BIO_BASED;
-		if (dm_table_supports_dax(t) ||
+		if (dm_table_supports_dax(t, PAGE_SIZE) ||
 		    (list_empty(devices) && live_md_type == DM_TYPE_DAX_BIO_BASED)) {
 			t->type = DM_TYPE_DAX_BIO_BASED;
 		} else {
@@ -1905,7 +1910,7 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	}
 	blk_queue_write_cache(q, wc, fua);
 
-	if (dm_table_supports_dax(t))
+	if (dm_table_supports_dax(t, PAGE_SIZE))
 		blk_queue_flag_set(QUEUE_FLAG_DAX, q);
 	else
 		blk_queue_flag_clear(QUEUE_FLAG_DAX, q);
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 1fb1333fefec..b7c0ad01084d 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1107,6 +1107,25 @@ static long dm_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
 	return ret;
 }
 
+static bool dm_dax_supported(struct dax_device *dax_dev, struct block_device *bdev,
+		int blocksize, sector_t start, sector_t len)
+{
+	struct mapped_device *md = dax_get_private(dax_dev);
+	struct dm_table *map;
+	int srcu_idx;
+	bool ret;
+
+	map = dm_get_live_table(md, &srcu_idx);
+	if (!map)
+		return false;
+
+	ret = dm_table_supports_dax(map, blocksize);
+
+	dm_put_live_table(md, srcu_idx);
+
+	return ret;
+}
+
 static size_t dm_dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff,
 				    void *addr, size_t bytes, struct iov_iter *i)
 {
@@ -3192,6 +3211,7 @@ static const struct block_device_operations dm_blk_dops = {
 
 static const struct dax_operations dm_dax_ops = {
 	.direct_access = dm_dax_direct_access,
+	.dax_supported = dm_dax_supported,
 	.copy_from_iter = dm_dax_copy_from_iter,
 	.copy_to_iter = dm_dax_copy_to_iter,
 };
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index 2d539b82ec08..17e3db54404c 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -72,6 +72,7 @@ bool dm_table_bio_based(struct dm_table *t);
 bool dm_table_request_based(struct dm_table *t);
 void dm_table_free_md_mempools(struct dm_table *t);
 struct dm_md_mempools *dm_table_get_md_mempools(struct dm_table *t);
+bool dm_table_supports_dax(struct dm_table *t, int blocksize);
 
 void dm_lock_md_type(struct mapped_device *md);
 void dm_unlock_md_type(struct mapped_device *md);