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>

1 files changed, 30 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);