btrfs: add read policy to set a preferred device

Add read policy that will force all reads to go to the given device
(specified by devid) on the RAID1 profiles.

This will be used for testing, e.g. to read from stale device. Users may
find other use cases.

Can be set in sysfs, the value format is "devid:<devid>" to the file

  /sys/fs/btrfs/FSID/read_policy

Signed-off-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: David Sterba <dsterba@suse.com>

3 files changed, 52 insertions, 1 deletions

diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index e155b7ce1ee5..5211d13d73f8 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -1309,6 +1309,7 @@ static const char *btrfs_read_policy_name[] = {
 	"pid",
 #ifdef CONFIG_BTRFS_EXPERIMENTAL
 	"round-robin",
+	"devid",
 #endif
 };
 
@@ -1364,8 +1365,11 @@ static ssize_t btrfs_read_policy_show(struct kobject *kobj,
 		if (i == BTRFS_READ_POLICY_RR)
 			ret += sysfs_emit_at(buf, ret, ":%u",
 					     READ_ONCE(fs_devices->rr_min_contig_read));
-#endif
 
+		if (i == BTRFS_READ_POLICY_DEVID)
+			ret += sysfs_emit_at(buf, ret, ":%llu",
+					     READ_ONCE(fs_devices->read_devid));
+#endif
 		if (i == policy)
 			ret += sysfs_emit_at(buf, ret, "]");
 	}
@@ -1421,6 +1425,31 @@ static ssize_t btrfs_read_policy_store(struct kobject *kobj,
 
 		return len;
 	}
+
+	if (index == BTRFS_READ_POLICY_DEVID) {
+		if (value != -1) {
+			BTRFS_DEV_LOOKUP_ARGS(args);
+
+			/* Validate input devid. */
+			args.devid = value;
+			if (btrfs_find_device(fs_devices, &args) == NULL)
+				return -EINVAL;
+		} else {
+			/* Set default devid to the devid of the latest device. */
+			value = fs_devices->latest_dev->devid;
+		}
+
+		if (index != READ_ONCE(fs_devices->read_policy) ||
+		    value != READ_ONCE(fs_devices->read_devid)) {
+			WRITE_ONCE(fs_devices->read_policy, index);
+			WRITE_ONCE(fs_devices->read_devid, value);
+
+			btrfs_info(fs_devices->fs_info, "read policy set to '%s:%llu'",
+				   btrfs_read_policy_name[index], value);
+		}
+
+		return len;
+	}
 #endif
 	if (index != READ_ONCE(fs_devices->read_policy)) {
 		WRITE_ONCE(fs_devices->read_policy, index);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index cfe1d5ada5f2..b5fd1aa45c4c 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1331,6 +1331,7 @@ static int open_fs_devices(struct btrfs_fs_devices *fs_devices,
 	fs_devices->read_policy = BTRFS_READ_POLICY_PID;
 #ifdef CONFIG_BTRFS_EXPERIMENTAL
 	fs_devices->rr_min_contig_read = BTRFS_DEFAULT_RR_MIN_CONTIG_READ;
+	fs_devices->read_devid = latest_dev->devid;
 #endif
 
 	return 0;
@@ -5957,6 +5958,19 @@ unsigned long btrfs_full_stripe_len(struct btrfs_fs_info *fs_info,
 }
 
 #ifdef CONFIG_BTRFS_EXPERIMENTAL
+static int btrfs_read_preferred(struct btrfs_chunk_map *map, int first, int num_stripes)
+{
+	for (int index = first; index < first + num_stripes; index++) {
+		const struct btrfs_device *device = map->stripes[index].dev;
+
+		if (device->devid == READ_ONCE(device->fs_devices->read_devid))
+			return index;
+	}
+
+	/* If no read-preferred device is set use the first stripe. */
+	return first;
+}
+
 struct stripe_mirror {
 	u64 devid;
 	int num;
@@ -6046,6 +6060,9 @@ static int find_live_mirror(struct btrfs_fs_info *fs_info,
 	case BTRFS_READ_POLICY_RR:
 		preferred_mirror = btrfs_read_rr(map, first, num_stripes);
 		break;
+	case BTRFS_READ_POLICY_DEVID:
+		preferred_mirror = btrfs_read_preferred(map, first, num_stripes);
+		break;
 #endif
 	}
 
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index f9fe698a9b4b..120f65e21eeb 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -309,6 +309,8 @@ enum btrfs_read_policy {
 #ifdef CONFIG_BTRFS_EXPERIMENTAL
 	/* Balancing RAID1 reads across all striped devices (round-robin). */
 	BTRFS_READ_POLICY_RR,
+	/* Read from a specific device. */
+	BTRFS_READ_POLICY_DEVID,
 #endif
 	BTRFS_NR_READ_POLICY,
 };
@@ -446,6 +448,9 @@ struct btrfs_fs_devices {
 	 */
 	u32 rr_min_contig_read;
 
+	/* Device to be used for reading in case of RAID1. */
+	u64 read_devid;
+
 	/* Checksum mode - offload it or do it synchronously. */
 	enum btrfs_offload_csum_mode offload_csum_mode;
 #endif