[PATCH 1/4] Btrfs: move btrfs_{set,clear}_and_info() to ctree.h

[PATCH 1/4] Btrfs: move btrfs_{set,clear}_and_info() to ctree.h

[Wang Shilong]

Signed-off-by: Wang Shilong <wangsl.fnst@cn.fujitsu.com>
---
 fs/btrfs/ctree.h | 14 ++++++++++++++
 fs/btrfs/super.c | 14 --------------
 2 files changed, 14 insertions(+), 14 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index ad1a594..e7c9e1c 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2058,6 +2058,20 @@ struct btrfs_ioctl_defrag_range_args {
 #define btrfs_raw_test_opt(o, opt)	((o) & BTRFS_MOUNT_##opt)
 #define btrfs_test_opt(root, opt)	((root)->fs_info->mount_opt & \
 					 BTRFS_MOUNT_##opt)
+#define btrfs_set_and_info(root, opt, fmt, args...)			\
+{									\
+	if (!btrfs_test_opt(root, opt))					\
+		btrfs_info(root->fs_info, fmt, ##args);			\
+	btrfs_set_opt(root->fs_info->mount_opt, opt);			\
+}
+
+#define btrfs_clear_and_info(root, opt, fmt, args...)			\
+{									\
+	if (btrfs_test_opt(root, opt))					\
+		btrfs_info(root->fs_info, fmt, ##args);			\
+	btrfs_clear_opt(root->fs_info->mount_opt, opt);			\
+}
+
 /*
  * Inode flags
  */
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 994c409..6696980 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -385,20 +385,6 @@ static match_table_t tokens = {
 	{Opt_err, NULL},
 };
 
-#define btrfs_set_and_info(root, opt, fmt, args...)			\
-{									\
-	if (!btrfs_test_opt(root, opt))					\
-		btrfs_info(root->fs_info, fmt, ##args);			\
-	btrfs_set_opt(root->fs_info->mount_opt, opt);			\
-}
-
-#define btrfs_clear_and_info(root, opt, fmt, args...)			\
-{									\
-	if (btrfs_test_opt(root, opt))					\
-		btrfs_info(root->fs_info, fmt, ##args);			\
-	btrfs_clear_opt(root->fs_info->mount_opt, opt);			\
-}
-
 /*
  * Regular mount options parser.  Everything that is needed only when
  * reading in a new superblock is parsed here.
-- 
1.9.0

[PATCH 2/4] Btrfs: avoid triggering bug_on() when we fail to start inode caching task

[Wang Shilong]

When running stress test(including snapshots,balance,fstress), we trigger
the following BUG_ON() which is because we fail to start inode caching task.

[  181.131945] kernel BUG at fs/btrfs/inode-map.c:179!
[  181.137963] invalid opcode: 0000 [#1] SMP
[  181.217096] CPU: 11 PID: 2532 Comm: btrfs Not tainted 3.14.0 #1
[  181.240521] task: ffff88013b621b30 ti: ffff8800b6ada000 task.ti: ffff8800b6ada000
[  181.367506] Call Trace:
[  181.371107]  [<ffffffffa036c1be>] btrfs_return_ino+0x9e/0x110 [btrfs]
[  181.379191]  [<ffffffffa038082b>] btrfs_evict_inode+0x46b/0x4c0 [btrfs]
[  181.387464]  [<ffffffff810b5a70>] ? autoremove_wake_function+0x40/0x40
[  181.395642]  [<ffffffff811dc5fe>] evict+0x9e/0x190
[  181.401882]  [<ffffffff811dcde3>] iput+0xf3/0x180
[  181.408025]  [<ffffffffa03812de>] btrfs_orphan_cleanup+0x1ee/0x430 [btrfs]
[  181.416614]  [<ffffffffa03a6abd>] btrfs_mksubvol.isra.29+0x3bd/0x450 [btrfs]
[  181.425399]  [<ffffffffa03a6cd6>] btrfs_ioctl_snap_create_transid+0x186/0x190 [btrfs]
[  181.435059]  [<ffffffffa03a6e3b>] btrfs_ioctl_snap_create_v2+0xeb/0x130 [btrfs]
[  181.444148]  [<ffffffffa03a9656>] btrfs_ioctl+0xf76/0x2b90 [btrfs]
[  181.451971]  [<ffffffff8117e565>] ? handle_mm_fault+0x475/0xe80
[  181.459509]  [<ffffffff8167ba0c>] ? __do_page_fault+0x1ec/0x520
[  181.467046]  [<ffffffff81185b35>] ? do_mmap_pgoff+0x2f5/0x3c0
[  181.474393]  [<ffffffff811d4da8>] do_vfs_ioctl+0x2d8/0x4b0
[  181.481450]  [<ffffffff811d5001>] SyS_ioctl+0x81/0xa0
[  181.488021]  [<ffffffff81680b69>] system_call_fastpath+0x16/0x1b

We should avoid triggering BUG_ON() here, instead, we output warning messages
and clear inode_cache option.

Signed-off-by: Wang Shilong <wangsl.fnst@cn.fujitsu.com>
---
 fs/btrfs/inode-map.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c
index cc8ca19..8ad529e 100644
--- a/fs/btrfs/inode-map.c
+++ b/fs/btrfs/inode-map.c
@@ -176,7 +176,11 @@ static void start_caching(struct btrfs_root *root)
 
 	tsk = kthread_run(caching_kthread, root, "btrfs-ino-cache-%llu\n",
 			  root->root_key.objectid);
-	BUG_ON(IS_ERR(tsk)); /* -ENOMEM */
+	if (IS_ERR(tsk)) {
+		btrfs_warn(root->fs_info, "failed to start inode caching task");
+		btrfs_clear_and_info(root, CHANGE_INODE_CACHE,
+				"disabling inode map caching");
+	}
 }
 
 int btrfs_find_free_ino(struct btrfs_root *root, u64 *objectid)
-- 
1.9.0

[PATCH 3/4] Btrfs: fix possible memory leaks in open_ctree()

[Wang Shilong]

Fix possible memory leaks in the following error handling paths:

read_tree_block()
btrfs_recover_log_trees
btrfs_commit_super()
btrfs_find_orphan_roots()
btrfs_cleanup_fs_roots()

Signed-off-by: Wang Shilong <wangsl.fnst@cn.fujitsu.com>
---
 fs/btrfs/disk-io.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 6d1ac7d..0e4fb4a 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2864,7 +2864,7 @@ retry_root_backup:
 			printk(KERN_ERR "BTRFS: failed to read log tree\n");
 			free_extent_buffer(log_tree_root->node);
 			kfree(log_tree_root);
-			goto fail_trans_kthread;
+			goto fail_qgroup;
 		}
 		/* returns with log_tree_root freed on success */
 		ret = btrfs_recover_log_trees(log_tree_root);
@@ -2873,24 +2873,24 @@ retry_root_backup:
 				    "Failed to recover log tree");
 			free_extent_buffer(log_tree_root->node);
 			kfree(log_tree_root);
-			goto fail_trans_kthread;
+			goto fail_qgroup;
 		}
 
 		if (sb->s_flags & MS_RDONLY) {
 			ret = btrfs_commit_super(tree_root);
 			if (ret)
-				goto fail_trans_kthread;
+				goto fail_qgroup;
 		}
 	}
 
 	ret = btrfs_find_orphan_roots(tree_root);
 	if (ret)
-		goto fail_trans_kthread;
+		goto fail_qgroup;
 
 	if (!(sb->s_flags & MS_RDONLY)) {
 		ret = btrfs_cleanup_fs_roots(fs_info);
 		if (ret)
-			goto fail_trans_kthread;
+			goto fail_qgroup;
 
 		ret = btrfs_recover_relocation(tree_root);
 		if (ret < 0) {
-- 
1.9.0

[PATCH 4/4] Btrfs: fix inode caching vs tree log

[Wang Shilong]

From: Miao Xie <miaox@cn.fujitsu.com>

Currently, with inode cache enabled, we will reuse its inode id immediately
after unlinking file, we may hit something like following:

|->iput inode
|->return inode id into inode cache
|->create dir,fsync
|->power off

An easy way to reproduce this problem is:

mkfs.btrfs -f /dev/sdb
mount /dev/sdb /mnt -o inode_cache,commit=100
dd if=/dev/zero of=/mnt/data bs=1M count=10 oflag=sync
inode_id=`ls -i /mnt/data | awk '{print $1}'`
rm -f /mnt/data

i=1
while [ 1 ]
do
        mkdir /mnt/dir_$i
        test1=`stat /mnt/dir_$i | grep Inode: | awk '{print $4}'`
        if [ $test1 -eq $inode_id ]
        then
		dd if=/dev/zero of=/mnt/dir_$i/data bs=1M count=1 oflag=sync
		echo b > /proc/sysrq-trigger
	fi
	sleep 1
        i=$(($i+1))
done

mount /dev/sdb /mnt
umount /dev/sdb
btrfs check /dev/sdb

We fix this problem by adding unlinked inode's id into pinned tree,
and we can not reuse them until committing transaction.

Cc: stable@vger.kernel.org
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Wang Shilong <wangsl.fnst@cn.fujitsu.com>
---
Regression test will be sent later
---
 fs/btrfs/inode-map.c | 18 ++----------------
 1 file changed, 2 insertions(+), 16 deletions(-)

diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c
index 8ad529e..86935f5 100644
--- a/fs/btrfs/inode-map.c
+++ b/fs/btrfs/inode-map.c
@@ -209,24 +209,14 @@ again:
 
 void btrfs_return_ino(struct btrfs_root *root, u64 objectid)
 {
-	struct btrfs_free_space_ctl *ctl = root->free_ino_ctl;
 	struct btrfs_free_space_ctl *pinned = root->free_ino_pinned;
 
 	if (!btrfs_test_opt(root, INODE_MAP_CACHE))
 		return;
-
 again:
 	if (root->cached == BTRFS_CACHE_FINISHED) {
-		__btrfs_add_free_space(ctl, objectid, 1);
+		__btrfs_add_free_space(pinned, objectid, 1);
 	} else {
-		/*
-		 * If we are in the process of caching free ino chunks,
-		 * to avoid adding the same inode number to the free_ino
-		 * tree twice due to cross transaction, we'll leave it
-		 * in the pinned tree until a transaction is committed
-		 * or the caching work is done.
-		 */
-
 		down_write(&root->fs_info->commit_root_sem);
 		spin_lock(&root->cache_lock);
 		if (root->cached == BTRFS_CACHE_FINISHED) {
@@ -238,11 +228,7 @@ again:
 
 		start_caching(root);
 
-		if (objectid <= root->cache_progress ||
-		    objectid >= root->highest_objectid)
-			__btrfs_add_free_space(ctl, objectid, 1);
-		else
-			__btrfs_add_free_space(pinned, objectid, 1);
+		__btrfs_add_free_space(pinned, objectid, 1);
 
 		up_write(&root->fs_info->commit_root_sem);
 	}
-- 
1.9.0