From: Filipe Manana fdmanana@suse.com
stable inclusion from stable-v6.6.54 commit f56a6d9c267ec7fa558ede7755551c047b1034cd category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IAYQS2 CVE: CVE-2024-47741
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...
--------------------------------
[ Upstream commit 7ee85f5515e86a4e2a2f51969795920733912bad ]
When doing concurrent lseek(2) system calls against the same file descriptor, using multiple threads belonging to the same process, we have a short time window where a race happens and can result in a memory leak.
The race happens like this:
1) A program opens a file descriptor for a file and then spawns two threads (with the pthreads library for example), lets call them task A and task B;
2) Task A calls lseek with SEEK_DATA or SEEK_HOLE and ends up at file.c:find_desired_extent() while holding a read lock on the inode;
3) At the start of find_desired_extent(), it extracts the file's private_data pointer into a local variable named 'private', which has a value of NULL;
4) Task B also calls lseek with SEEK_DATA or SEEK_HOLE, locks the inode in shared mode and enters file.c:find_desired_extent(), where it also extracts file->private_data into its local variable 'private', which has a NULL value;
5) Because it saw a NULL file private, task A allocates a private structure and assigns to the file structure;
6) Task B also saw a NULL file private so it also allocates its own file private and then assigns it to the same file structure, since both tasks are using the same file descriptor.
At this point we leak the private structure allocated by task A.
Besides the memory leak, there's also the detail that both tasks end up using the same cached state record in the private structure (struct btrfs_file_private::llseek_cached_state), which can result in a use-after-free problem since one task can free it while the other is still using it (only one task took a reference count on it). Also, sharing the cached state is not a good idea since it could result in incorrect results in the future - right now it should not be a problem because it end ups being used only in extent-io-tree.c:count_range_bits() where we do range validation before using the cached state.
Fix this by protecting the private assignment and check of a file while holding the inode's spinlock and keep track of the task that allocated the private, so that it's used only by that task in order to prevent user-after-free issues with the cached state record as well as potentially using it incorrectly in the future.
Fixes: 3c32c7212f16 ("btrfs: use cached state when looking for delalloc ranges with lseek") CC: stable@vger.kernel.org # 6.6+ Reviewed-by: Josef Bacik josef@toxicpanda.com Signed-off-by: Filipe Manana fdmanana@suse.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: ZhangPeng zhangpeng362@huawei.com Conflicts: fs/btrfs/btrfs_inode.h [Context differences.] Signed-off-by: Yifan Qiao qiaoyifan4@huawei.com --- fs/btrfs/btrfs_inode.h | 1 + fs/btrfs/ctree.h | 2 ++ fs/btrfs/file.c | 34 +++++++++++++++++++++++++++++++--- 3 files changed, 34 insertions(+), 3 deletions(-)
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index bda1fdbba666..58c2c863e24c 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -84,6 +84,7 @@ struct btrfs_inode { * the log or not (last_trans, last_sub_trans, last_log_commit, * logged_trans), to access/update new_delalloc_bytes and to update the * VFS' inode number of bytes used. + * Also protects setting struct file::private_data. */ spinlock_t lock;
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 06333a74d6c4..f7bb4c34b984 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -445,6 +445,8 @@ struct btrfs_file_private { void *filldir_buf; u64 last_index; struct extent_state *llseek_cached_state; + /* Task that allocated this structure. */ + struct task_struct *owner_task; };
static inline u32 BTRFS_LEAF_DATA_SIZE(const struct btrfs_fs_info *info) diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 15fd8c00f4c0..fc6c91773bc8 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -3481,7 +3481,7 @@ static bool find_desired_extent_in_hole(struct btrfs_inode *inode, int whence, static loff_t find_desired_extent(struct file *file, loff_t offset, int whence) { struct btrfs_inode *inode = BTRFS_I(file->f_mapping->host); - struct btrfs_file_private *private = file->private_data; + struct btrfs_file_private *private; struct btrfs_fs_info *fs_info = inode->root->fs_info; struct extent_state *cached_state = NULL; struct extent_state **delalloc_cached_state; @@ -3509,7 +3509,19 @@ static loff_t find_desired_extent(struct file *file, loff_t offset, int whence) inode_get_bytes(&inode->vfs_inode) == i_size) return i_size;
- if (!private) { + spin_lock(&inode->lock); + private = file->private_data; + spin_unlock(&inode->lock); + + if (private && private->owner_task != current) { + /* + * Not allocated by us, don't use it as its cached state is used + * by the task that allocated it and we don't want neither to + * mess with it nor get incorrect results because it reflects an + * invalid state for the current task. + */ + private = NULL; + } else if (!private) { private = kzalloc(sizeof(*private), GFP_KERNEL); /* * No worries if memory allocation failed. @@ -3517,7 +3529,23 @@ static loff_t find_desired_extent(struct file *file, loff_t offset, int whence) * lseek SEEK_HOLE/DATA calls to a file when there's delalloc, * so everything will still be correct. */ - file->private_data = private; + if (private) { + bool free = false; + + private->owner_task = current; + + spin_lock(&inode->lock); + if (file->private_data) + free = true; + else + file->private_data = private; + spin_unlock(&inode->lock); + + if (free) { + kfree(private); + private = NULL; + } + } }
if (private)