From: Miao Xie <miaox@cn.fujitsu.com>
Date: Thu, 3 Jul 2014 10:22:13 +0000 (+0800)
Subject: Btrfs: fix writing data into the seed filesystem
X-Git-Url: http://git.cdn.openwrt.org/?a=commitdiff_plain;h=d20983b40e828;p=openwrt%2Fstaging%2Fblogic.git

Btrfs: fix writing data into the seed filesystem

If we mounted a seed filesystem with degraded option, and then added a new
device into the seed filesystem, then we found adding device failed because
of the IO failure.

Steps to reproduce:
 # mkfs.btrfs -d raid1 -m raid1 <dev0> <dev1>
 # btrfstune -S 1 <dev0>
 # mount <dev0> -o degraded <mnt>
 # btrfs device add -f <dev2> <mnt>

It is because the original didn't set the chunk on the seed device to be
read-only if the degraded flag was set. It was introduced by patch f48b90756,
which fixed the problem the raid1 filesystem became read-only after one device
of it was missing. But this fix method was not right, we should set the read-only
flag according to the number of the missing devices, not the degraded mount
option, if the number of the missing devices is less than the max error number
that the profile of the chunk tolerates, we don't set it to be read-only.

Cc: Josef Bacik <jbacik@fb.com>
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
Signed-off-by: Chris Mason <clm@fb.com>
---

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index a7a3863e3807..48c357223e56 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -4583,12 +4583,31 @@ out:
 	return ret;
 }
 
+static inline int btrfs_chunk_max_errors(struct map_lookup *map)
+{
+	int max_errors;
+
+	if (map->type & (BTRFS_BLOCK_GROUP_RAID1 |
+			 BTRFS_BLOCK_GROUP_RAID10 |
+			 BTRFS_BLOCK_GROUP_RAID5 |
+			 BTRFS_BLOCK_GROUP_DUP)) {
+		max_errors = 1;
+	} else if (map->type & BTRFS_BLOCK_GROUP_RAID6) {
+		max_errors = 2;
+	} else {
+		max_errors = 0;
+	}
+
+	return max_errors;
+}
+
 int btrfs_chunk_readonly(struct btrfs_root *root, u64 chunk_offset)
 {
 	struct extent_map *em;
 	struct map_lookup *map;
 	struct btrfs_mapping_tree *map_tree = &root->fs_info->mapping_tree;
 	int readonly = 0;
+	int miss_ndevs = 0;
 	int i;
 
 	read_lock(&map_tree->map_tree.lock);
@@ -4597,18 +4616,27 @@ int btrfs_chunk_readonly(struct btrfs_root *root, u64 chunk_offset)
 	if (!em)
 		return 1;
 
-	if (btrfs_test_opt(root, DEGRADED)) {
-		free_extent_map(em);
-		return 0;
-	}
-
 	map = (struct map_lookup *)em->bdev;
 	for (i = 0; i < map->num_stripes; i++) {
+		if (map->stripes[i].dev->missing) {
+			miss_ndevs++;
+			continue;
+		}
+
 		if (!map->stripes[i].dev->writeable) {
 			readonly = 1;
-			break;
+			goto end;
 		}
 	}
+
+	/*
+	 * If the number of missing devices is larger than max errors,
+	 * we can not write the data into that chunk successfully, so
+	 * set it readonly.
+	 */
+	if (miss_ndevs > btrfs_chunk_max_errors(map))
+		readonly = 1;
+end:
 	free_extent_map(em);
 	return readonly;
 }
@@ -5219,16 +5247,8 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 		}
 	}
 
-	if (rw & (REQ_WRITE | REQ_GET_READ_MIRRORS)) {
-		if (map->type & (BTRFS_BLOCK_GROUP_RAID1 |
-				 BTRFS_BLOCK_GROUP_RAID10 |
-				 BTRFS_BLOCK_GROUP_RAID5 |
-				 BTRFS_BLOCK_GROUP_DUP)) {
-			max_errors = 1;
-		} else if (map->type & BTRFS_BLOCK_GROUP_RAID6) {
-			max_errors = 2;
-		}
-	}
+	if (rw & (REQ_WRITE | REQ_GET_READ_MIRRORS))
+		max_errors = btrfs_chunk_max_errors(map);
 
 	if (dev_replace_is_ongoing && (rw & (REQ_WRITE | REQ_DISCARD)) &&
 	    dev_replace->tgtdev != NULL) {