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>

1 files changed, 57 insertions, 31 deletions

diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index bbd57ca0634a..3a7b0a0bf469 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -73,22 +73,12 @@ struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev)
 EXPORT_SYMBOL_GPL(fs_dax_get_by_bdev);
 #endif
 
-/**
- * __bdev_dax_supported() - Check if the device supports dax for filesystem
- * @bdev: block device to check
- * @blocksize: The block size of the device
- *
- * This is a library function for filesystems to check if the block device
- * can be mounted with dax option.
- *
- * Return: true if supported, false if unsupported
- */
-bool __bdev_dax_supported(struct block_device *bdev, int blocksize)
+bool __generic_fsdax_supported(struct dax_device *dax_dev,
+		struct block_device *bdev, int blocksize, sector_t start,
+		sector_t sectors)
 {
-	struct dax_device *dax_dev;
 	bool dax_enabled = false;
 	pgoff_t pgoff, pgoff_end;
-	struct request_queue *q;
 	char buf[BDEVNAME_SIZE];
 	void *kaddr, *end_kaddr;
 	pfn_t pfn, end_pfn;
@@ -102,21 +92,14 @@ bool __bdev_dax_supported(struct block_device *bdev, int blocksize)
 		return false;
 	}
 
-	q = bdev_get_queue(bdev);
-	if (!q || !blk_queue_dax(q)) {
-		pr_debug("%s: error: request queue doesn't support dax\n",
-				bdevname(bdev, buf));
-		return false;
-	}
-
-	err = bdev_dax_pgoff(bdev, 0, PAGE_SIZE, &pgoff);
+	err = bdev_dax_pgoff(bdev, start, PAGE_SIZE, &pgoff);
 	if (err) {
 		pr_debug("%s: error: unaligned partition for dax\n",
 				bdevname(bdev, buf));
 		return false;
 	}
 
-	last_page = PFN_DOWN(i_size_read(bdev->bd_inode) - 1) * 8;
+	last_page = PFN_DOWN((start + sectors - 1) * 512) * PAGE_SIZE / 512;
 	err = bdev_dax_pgoff(bdev, last_page, PAGE_SIZE, &pgoff_end);
 	if (err) {
 		pr_debug("%s: error: unaligned partition for dax\n",
@@ -124,20 +107,11 @@ bool __bdev_dax_supported(struct block_device *bdev, int blocksize)
 		return false;
 	}
 
-	dax_dev = dax_get_by_host(bdev->bd_disk->disk_name);
-	if (!dax_dev) {
-		pr_debug("%s: error: device does not support dax\n",
-				bdevname(bdev, buf));
-		return false;
-	}
-
 	id = dax_read_lock();
 	len = dax_direct_access(dax_dev, pgoff, 1, &kaddr, &pfn);
 	len2 = dax_direct_access(dax_dev, pgoff_end, 1, &end_kaddr, &end_pfn);
 	dax_read_unlock(id);
 
-	put_dax(dax_dev);
-
 	if (len < 1 || len2 < 1) {
 		pr_debug("%s: error: dax access failed (%ld)\n",
 				bdevname(bdev, buf), len < 1 ? len : len2);
@@ -178,6 +152,49 @@ bool __bdev_dax_supported(struct block_device *bdev, int blocksize)
 	}
 	return true;
 }
+EXPORT_SYMBOL_GPL(__generic_fsdax_supported);
+
+/**
+ * __bdev_dax_supported() - Check if the device supports dax for filesystem
+ * @bdev: block device to check
+ * @blocksize: The block size of the device
+ *
+ * This is a library function for filesystems to check if the block device
+ * can be mounted with dax option.
+ *
+ * Return: true if supported, false if unsupported
+ */
+bool __bdev_dax_supported(struct block_device *bdev, int blocksize)
+{
+	struct dax_device *dax_dev;
+	struct request_queue *q;
+	char buf[BDEVNAME_SIZE];
+	bool ret;
+	int id;
+
+	q = bdev_get_queue(bdev);
+	if (!q || !blk_queue_dax(q)) {
+		pr_debug("%s: error: request queue doesn't support dax\n",
+				bdevname(bdev, buf));
+		return false;
+	}
+
+	dax_dev = dax_get_by_host(bdev->bd_disk->disk_name);
+	if (!dax_dev) {
+		pr_debug("%s: error: device does not support dax\n",
+				bdevname(bdev, buf));
+		return false;
+	}
+
+	id = dax_read_lock();
+	ret = dax_supported(dax_dev, bdev, blocksize, 0,
+			i_size_read(bdev->bd_inode) / 512);
+	dax_read_unlock(id);
+
+	put_dax(dax_dev);
+
+	return ret;
+}
 EXPORT_SYMBOL_GPL(__bdev_dax_supported);
 #endif
 
@@ -303,6 +320,15 @@ long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
 }
 EXPORT_SYMBOL_GPL(dax_direct_access);
 
+bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev,
+		int blocksize, sector_t start, sector_t len)
+{
+	if (!dax_alive(dax_dev))
+		return false;
+
+	return dax_dev->ops->dax_supported(dax_dev, bdev, blocksize, start, len);
+}
+
 size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
 		size_t bytes, struct iov_iter *i)
 {