btrfs-progs: zoned: support resetting zoned device

All zones of zoned block devices should be reset before writing. Support
this by introducing PREP_DEVICE_ZONED.

btrfs_reset_all_zones() walk all the zones on a device, and reset a zone if
it is sequential required zone, or discard the zone range otherwise.

Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
Signed-off-by: David Sterba <dsterba@suse.com>

common/device-utils.c

@@ -26,6 +26,7 @@
 #include <linux/limits.h>
 #include "kernel-lib/sizes.h"
 #include "kernel-shared/disk-io.h"
+#include "kernel-shared/zoned.h"
 #include "common/device-utils.h"
 #include "common/internal.h"
 #include "common/messages.h"
@@ -50,7 +51,7 @@ static int discard_range(int fd, u64 start, u64 len)
 /*
  * Discard blocks in the given range in 1G chunks, the process is interruptible
  */
-static int discard_blocks(int fd, u64 start, u64 len)
+int discard_blocks(int fd, u64 start, u64 len)
 {
 	while (len > 0) {
 		/* 1G granularity */
@@ -156,6 +157,7 @@ out:
 int btrfs_prepare_device(int fd, const char *file, u64 *block_count_ret,
 		u64 max_block_count, unsigned opflags)
 {
+	struct btrfs_zoned_device_info *zinfo = NULL;
 	u64 block_count;
 	struct stat st;
 	int i, ret;
@@ -174,7 +176,27 @@ int btrfs_prepare_device(int fd, const char *file, u64 *block_count_ret,
 	if (max_block_count)
 		block_count = min(block_count, max_block_count);
 
-	if (opflags & PREP_DEVICE_DISCARD) {
+	if (opflags & PREP_DEVICE_ZONED) {
+		ret = btrfs_get_zone_info(fd, file, &zinfo);
+		if (ret < 0 || !zinfo) {
+			error("zoned: unable to load zone information of %s",
+			      file);
+			return 1;
+		}
+		if (opflags & PREP_DEVICE_VERBOSE)
+			printf("Resetting device zones %s (%u zones) ...\n",
+			       file, zinfo->nr_zones);
+		/*
+		 * We cannot ignore zone reset errors for a zoned block
+		 * device as this could result in the inability to write to
+		 * non-empty sequential zones of the device.
+		 */
+		if (btrfs_reset_all_zones(fd, zinfo)) {
+			error("zoned: failed to reset device '%s' zones: %m",
+			      file);
+			goto err;
+		}
+	} else if (opflags & PREP_DEVICE_DISCARD) {
 		/*
 		 * We intentionally ignore errors from the discard ioctl.  It
 		 * is not necessary for the mkfs functionality but just an
@@ -199,17 +221,22 @@ int btrfs_prepare_device(int fd, const char *file, u64 *block_count_ret,
 	if (ret < 0) {
 		errno = -ret;
 		error("failed to zero device '%s': %m", file);
-		return 1;
+		goto err;
 	}
 
 	ret = btrfs_wipe_existing_sb(fd);
 	if (ret < 0) {
 		error("cannot wipe superblocks on %s", file);
-		return 1;
+		goto err;
 	}
 
+	free(zinfo);
 	*block_count_ret = block_count;
 	return 0;
+
+err:
+	free(zinfo);
+	return 1;
 }
 
 u64 btrfs_device_size(int fd, struct stat *st)

common/device-utils.h

@@ -23,7 +23,9 @@
 #define	PREP_DEVICE_ZERO_END	(1U << 0)
 #define	PREP_DEVICE_DISCARD	(1U << 1)
 #define	PREP_DEVICE_VERBOSE	(1U << 2)
+#define	PREP_DEVICE_ZONED	(1U << 3)
 
+int discard_blocks(int fd, u64 start, u64 len);
 u64 get_partition_size(const char *dev);
 u64 disk_size(const char *path);
 u64 btrfs_device_size(int fd, struct stat *st);

kernel-shared/zoned.c

@@ -357,6 +357,38 @@ static int report_zones(int fd, const char *file,
 	return 0;
 }
 
+/*
+ * Discard blocks in the zones of a zoned block device. Process this with zone
+ * size granularity so that blocks in conventional zones are discarded using
+ * discard_range and blocks in sequential zones are reset though a zone reset.
+ */
+int btrfs_reset_all_zones(int fd, struct btrfs_zoned_device_info *zinfo)
+{
+	unsigned int i;
+	int ret = 0;
+
+	ASSERT(zinfo);
+
+	/* Zone size granularity */
+	for (i = 0; i < zinfo->nr_zones; i++) {
+		if (zinfo->zones[i].type == BLK_ZONE_TYPE_CONVENTIONAL) {
+			ret = discard_blocks(fd,
+					     zinfo->zones[i].start << SECTOR_SHIFT,
+					     zinfo->zone_size);
+			if (ret == EOPNOTSUPP)
+				ret = 0;
+		} else if (zinfo->zones[i].cond != BLK_ZONE_COND_EMPTY) {
+			ret = btrfs_reset_dev_zone(fd, &zinfo->zones[i]);
+		} else {
+			ret = 0;
+		}
+
+		if (ret)
+			return ret;
+	}
+	return fsync(fd);
+}
+
 static int sb_log_location(int fd, struct blk_zone *zones, int rw, u64 *bytenr_ret)
 {
 	u64 wp;

kernel-shared/zoned.h

@@ -94,6 +94,7 @@ bool btrfs_redirty_extent_buffer_for_zoned(struct btrfs_fs_info *fs_info,
 					   u64 start, u64 end);
 int btrfs_reset_chunk_zones(struct btrfs_fs_info *fs_info, u64 devid,
 			    u64 offset, u64 length);
+int btrfs_reset_all_zones(int fd, struct btrfs_zoned_device_info *zinfo);
 
 #else
 
@@ -143,6 +144,12 @@ static inline int btrfs_reset_chunk_zones(struct btrfs_fs_info *fs_info,
 	return 0;
 }
 
+static inline int btrfs_reset_all_zones(int fd,
+					struct btrfs_zoned_device_info *zinfo)
+{
+	return -EOPNOTSUPP;
+}
+
 #endif /* BTRFS_ZONED */
 
 static inline bool btrfs_dev_is_sequential(struct btrfs_device *device, u64 pos)