f2fs: synchronize atomic write aborts
Commit Message
From: Daeho Jeong <daehojeong@google.com>
To fix a race condition between atomic write aborts, I use the inode
lock and make COW inode to be re-usable thoroughout the whole
atomic file inode lifetime.
Reported-by: syzbot+823000d23b3400619f7c@syzkaller.appspotmail.com
Fixes: 3db1de0e582c ("f2fs: change the current atomic write way")
Signed-off-by: Daeho Jeong <daehojeong@google.com>
---
fs/f2fs/file.c | 44 +++++++++++++++++++++++++++++---------------
fs/f2fs/inode.c | 11 +++++++++--
fs/f2fs/segment.c | 3 ---
fs/f2fs/super.c | 2 --
4 files changed, 38 insertions(+), 22 deletions(-)
Comments
On 2023/2/10 2:18, Daeho Jeong wrote:
> From: Daeho Jeong <daehojeong@google.com>
>
> To fix a race condition between atomic write aborts, I use the inode
> lock and make COW inode to be re-usable thoroughout the whole
> atomic file inode lifetime.
>
> Reported-by: syzbot+823000d23b3400619f7c@syzkaller.appspotmail.com
> Fixes: 3db1de0e582c ("f2fs: change the current atomic write way")
> Signed-off-by: Daeho Jeong <daehojeong@google.com>
> ---
> fs/f2fs/file.c | 44 +++++++++++++++++++++++++++++---------------
> fs/f2fs/inode.c | 11 +++++++++--
> fs/f2fs/segment.c | 3 ---
> fs/f2fs/super.c | 2 --
> 4 files changed, 38 insertions(+), 22 deletions(-)
>
> diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
> index 300eae8b5415..6436c52e7913 100644
> --- a/fs/f2fs/file.c
> +++ b/fs/f2fs/file.c
> @@ -1863,7 +1863,10 @@ static int f2fs_release_file(struct inode *inode, struct file *filp)
> atomic_read(&inode->i_writecount) != 1)
> return 0;
>
> + inode_lock(inode);
> f2fs_abort_atomic_write(inode, true);
> + inode_unlock(inode);
> +
> return 0;
> }
>
> @@ -1878,8 +1881,12 @@ static int f2fs_file_flush(struct file *file, fl_owner_t id)
> * before dropping file lock, it needs to do in ->flush.
> */
> if (F2FS_I(inode)->atomic_write_task == current &&
> - (current->flags & PF_EXITING))
> + (current->flags & PF_EXITING)) {
> + inode_lock(inode);
> f2fs_abort_atomic_write(inode, true);
> + inode_unlock(inode);
> + }
> +
> return 0;
> }
>
> @@ -2085,19 +2092,28 @@ static int f2fs_ioc_start_atomic_write(struct file *filp, bool truncate)
> goto out;
> }
>
> - /* Create a COW inode for atomic write */
> - pinode = f2fs_iget(inode->i_sb, fi->i_pino);
> - if (IS_ERR(pinode)) {
> - f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
> - ret = PTR_ERR(pinode);
> - goto out;
> - }
> + /* Check if the inode already has a COW inode */
> + if (fi->cow_inode == NULL) {
> + /* Create a COW inode for atomic write */
> + pinode = f2fs_iget(inode->i_sb, fi->i_pino);
> + if (IS_ERR(pinode)) {
> + f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
> + ret = PTR_ERR(pinode);
> + goto out;
> + }
>
> - ret = f2fs_get_tmpfile(mnt_userns, pinode, &fi->cow_inode);
> - iput(pinode);
> - if (ret) {
> - f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
> - goto out;
> + ret = f2fs_get_tmpfile(mnt_userns, pinode, &fi->cow_inode);
> + iput(pinode);
> + if (ret) {
> + f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
> + goto out;
> + }
> +
> + set_inode_flag(fi->cow_inode, FI_COW_FILE);
> + clear_inode_flag(fi->cow_inode, FI_INLINE_DATA);
> + } else {
> + /* Reuse the already created COW inode */
> + f2fs_do_truncate_blocks(fi->cow_inode, 0, true);
> }
>
> f2fs_write_inode(inode, NULL);
> @@ -2105,8 +2121,6 @@ static int f2fs_ioc_start_atomic_write(struct file *filp, bool truncate)
> stat_inc_atomic_inode(inode);
>
> set_inode_flag(inode, FI_ATOMIC_FILE);
> - set_inode_flag(fi->cow_inode, FI_COW_FILE);
> - clear_inode_flag(fi->cow_inode, FI_INLINE_DATA);
>
> isize = i_size_read(inode);
> fi->original_i_size = isize;
> diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
> index 28c9c72dda2a..7bf660d4cad9 100644
> --- a/fs/f2fs/inode.c
> +++ b/fs/f2fs/inode.c
> @@ -777,11 +777,18 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
> void f2fs_evict_inode(struct inode *inode)
> {
> struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
> - nid_t xnid = F2FS_I(inode)->i_xattr_nid;
> + struct f2fs_inode_info *fi = F2FS_I(inode);
> + nid_t xnid = fi->i_xattr_nid;
> int err = 0;
>
> f2fs_abort_atomic_write(inode, true);
>
> + if (fi->cow_inode) {
> + clear_inode_flag(fi->cow_inode, FI_COW_FILE);
> + iput(fi->cow_inode);
> + fi->cow_inode = NULL;
> + }
It looks "fi->cow_inode = NULL" here may race w/ cow_inode allocation in
f2fs_ioc_start_atomic_write due to f2fs_write_inode() has not been covered
by inode_lock()? IIUC.
Thanks,
> +
> trace_f2fs_evict_inode(inode);
> truncate_inode_pages_final(&inode->i_data);
>
> @@ -866,7 +873,7 @@ void f2fs_evict_inode(struct inode *inode)
> stat_dec_inline_inode(inode);
> stat_dec_compr_inode(inode);
> stat_sub_compr_blocks(inode,
> - atomic_read(&F2FS_I(inode)->i_compr_blocks));
> + atomic_read(&fi->i_compr_blocks));
>
> if (likely(!f2fs_cp_error(sbi) &&
> !is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
> diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
> index ead3f35f501d..719329c1808c 100644
> --- a/fs/f2fs/segment.c
> +++ b/fs/f2fs/segment.c
> @@ -192,9 +192,6 @@ void f2fs_abort_atomic_write(struct inode *inode, bool clean)
> if (!f2fs_is_atomic_file(inode))
> return;
>
> - clear_inode_flag(fi->cow_inode, FI_COW_FILE);
> - iput(fi->cow_inode);
> - fi->cow_inode = NULL;
> release_atomic_write_cnt(inode);
> clear_inode_flag(inode, FI_ATOMIC_COMMITTED);
> clear_inode_flag(inode, FI_ATOMIC_REPLACE);
> diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
> index c11a161ba5be..aa55dc12aff2 100644
> --- a/fs/f2fs/super.c
> +++ b/fs/f2fs/super.c
> @@ -1427,8 +1427,6 @@ static int f2fs_drop_inode(struct inode *inode)
> atomic_inc(&inode->i_count);
> spin_unlock(&inode->i_lock);
>
> - f2fs_abort_atomic_write(inode, true);
> -
> /* should remain fi->extent_tree for writepage */
> f2fs_destroy_extent_node(inode);
>
On Mon, Feb 13, 2023 at 1:47 AM Chao Yu <chao@kernel.org> wrote:
>
> On 2023/2/10 2:18, Daeho Jeong wrote:
> > From: Daeho Jeong <daehojeong@google.com>
> >
> > To fix a race condition between atomic write aborts, I use the inode
> > lock and make COW inode to be re-usable thoroughout the whole
> > atomic file inode lifetime.
> >
> > Reported-by: syzbot+823000d23b3400619f7c@syzkaller.appspotmail.com
> > Fixes: 3db1de0e582c ("f2fs: change the current atomic write way")
> > Signed-off-by: Daeho Jeong <daehojeong@google.com>
> > ---
> > fs/f2fs/file.c | 44 +++++++++++++++++++++++++++++---------------
> > fs/f2fs/inode.c | 11 +++++++++--
> > fs/f2fs/segment.c | 3 ---
> > fs/f2fs/super.c | 2 --
> > 4 files changed, 38 insertions(+), 22 deletions(-)
> >
> > diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
> > index 300eae8b5415..6436c52e7913 100644
> > --- a/fs/f2fs/file.c
> > +++ b/fs/f2fs/file.c
> > @@ -1863,7 +1863,10 @@ static int f2fs_release_file(struct inode *inode, struct file *filp)
> > atomic_read(&inode->i_writecount) != 1)
> > return 0;
> >
> > + inode_lock(inode);
> > f2fs_abort_atomic_write(inode, true);
> > + inode_unlock(inode);
> > +
> > return 0;
> > }
> >
> > @@ -1878,8 +1881,12 @@ static int f2fs_file_flush(struct file *file, fl_owner_t id)
> > * before dropping file lock, it needs to do in ->flush.
> > */
> > if (F2FS_I(inode)->atomic_write_task == current &&
> > - (current->flags & PF_EXITING))
> > + (current->flags & PF_EXITING)) {
> > + inode_lock(inode);
> > f2fs_abort_atomic_write(inode, true);
> > + inode_unlock(inode);
> > + }
> > +
> > return 0;
> > }
> >
> > @@ -2085,19 +2092,28 @@ static int f2fs_ioc_start_atomic_write(struct file *filp, bool truncate)
> > goto out;
> > }
> >
> > - /* Create a COW inode for atomic write */
> > - pinode = f2fs_iget(inode->i_sb, fi->i_pino);
> > - if (IS_ERR(pinode)) {
> > - f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
> > - ret = PTR_ERR(pinode);
> > - goto out;
> > - }
> > + /* Check if the inode already has a COW inode */
> > + if (fi->cow_inode == NULL) {
> > + /* Create a COW inode for atomic write */
> > + pinode = f2fs_iget(inode->i_sb, fi->i_pino);
> > + if (IS_ERR(pinode)) {
> > + f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
> > + ret = PTR_ERR(pinode);
> > + goto out;
> > + }
> >
> > - ret = f2fs_get_tmpfile(mnt_userns, pinode, &fi->cow_inode);
> > - iput(pinode);
> > - if (ret) {
> > - f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
> > - goto out;
> > + ret = f2fs_get_tmpfile(mnt_userns, pinode, &fi->cow_inode);
> > + iput(pinode);
> > + if (ret) {
> > + f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
> > + goto out;
> > + }
> > +
> > + set_inode_flag(fi->cow_inode, FI_COW_FILE);
> > + clear_inode_flag(fi->cow_inode, FI_INLINE_DATA);
> > + } else {
> > + /* Reuse the already created COW inode */
> > + f2fs_do_truncate_blocks(fi->cow_inode, 0, true);
> > }
> >
> > f2fs_write_inode(inode, NULL);
> > @@ -2105,8 +2121,6 @@ static int f2fs_ioc_start_atomic_write(struct file *filp, bool truncate)
> > stat_inc_atomic_inode(inode);
> >
> > set_inode_flag(inode, FI_ATOMIC_FILE);
> > - set_inode_flag(fi->cow_inode, FI_COW_FILE);
> > - clear_inode_flag(fi->cow_inode, FI_INLINE_DATA);
> >
> > isize = i_size_read(inode);
> > fi->original_i_size = isize;
> > diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
> > index 28c9c72dda2a..7bf660d4cad9 100644
> > --- a/fs/f2fs/inode.c
> > +++ b/fs/f2fs/inode.c
> > @@ -777,11 +777,18 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
> > void f2fs_evict_inode(struct inode *inode)
> > {
> > struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
> > - nid_t xnid = F2FS_I(inode)->i_xattr_nid;
> > + struct f2fs_inode_info *fi = F2FS_I(inode);
> > + nid_t xnid = fi->i_xattr_nid;
> > int err = 0;
> >
> > f2fs_abort_atomic_write(inode, true);
> >
> > + if (fi->cow_inode) {
> > + clear_inode_flag(fi->cow_inode, FI_COW_FILE);
> > + iput(fi->cow_inode);
> > + fi->cow_inode = NULL;
> > + }
>
> It looks "fi->cow_inode = NULL" here may race w/ cow_inode allocation in
> f2fs_ioc_start_atomic_write due to f2fs_write_inode() has not been covered
> by inode_lock()? IIUC.
Sorry, I couldn't understand it, since I couldn't find any relation
between f2fs_ioc_start_atomic_write and f2fs_write_inode. Could you
elaborate more on this? I thought the code might be safe, since it
happens in the inode eviction phase.
>
> Thanks,
>
> > +
> > trace_f2fs_evict_inode(inode);
> > truncate_inode_pages_final(&inode->i_data);
> >
> > @@ -866,7 +873,7 @@ void f2fs_evict_inode(struct inode *inode)
> > stat_dec_inline_inode(inode);
> > stat_dec_compr_inode(inode);
> > stat_sub_compr_blocks(inode,
> > - atomic_read(&F2FS_I(inode)->i_compr_blocks));
> > + atomic_read(&fi->i_compr_blocks));
> >
> > if (likely(!f2fs_cp_error(sbi) &&
> > !is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
> > diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
> > index ead3f35f501d..719329c1808c 100644
> > --- a/fs/f2fs/segment.c
> > +++ b/fs/f2fs/segment.c
> > @@ -192,9 +192,6 @@ void f2fs_abort_atomic_write(struct inode *inode, bool clean)
> > if (!f2fs_is_atomic_file(inode))
> > return;
> >
> > - clear_inode_flag(fi->cow_inode, FI_COW_FILE);
> > - iput(fi->cow_inode);
> > - fi->cow_inode = NULL;
> > release_atomic_write_cnt(inode);
> > clear_inode_flag(inode, FI_ATOMIC_COMMITTED);
> > clear_inode_flag(inode, FI_ATOMIC_REPLACE);
> > diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
> > index c11a161ba5be..aa55dc12aff2 100644
> > --- a/fs/f2fs/super.c
> > +++ b/fs/f2fs/super.c
> > @@ -1427,8 +1427,6 @@ static int f2fs_drop_inode(struct inode *inode)
> > atomic_inc(&inode->i_count);
> > spin_unlock(&inode->i_lock);
> >
> > - f2fs_abort_atomic_write(inode, true);
> > -
> > /* should remain fi->extent_tree for writepage */
> > f2fs_destroy_extent_node(inode);
> >
On 2023/2/14 4:14, Daeho Jeong wrote:
>>> diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
>>> index 28c9c72dda2a..7bf660d4cad9 100644
>>> --- a/fs/f2fs/inode.c
>>> +++ b/fs/f2fs/inode.c
>>> @@ -777,11 +777,18 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
>>> void f2fs_evict_inode(struct inode *inode)
>>> {
>>> struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
>>> - nid_t xnid = F2FS_I(inode)->i_xattr_nid;
>>> + struct f2fs_inode_info *fi = F2FS_I(inode);
>>> + nid_t xnid = fi->i_xattr_nid;
>>> int err = 0;
>>>
>>> f2fs_abort_atomic_write(inode, true);
>>>
>>> + if (fi->cow_inode) {
>>> + clear_inode_flag(fi->cow_inode, FI_COW_FILE);
>>> + iput(fi->cow_inode);
>>> + fi->cow_inode = NULL;
>>> + }
>>
>> It looks "fi->cow_inode = NULL" here may race w/ cow_inode allocation in
>> f2fs_ioc_start_atomic_write due to f2fs_write_inode() has not been covered
>> by inode_lock()? IIUC.
>
> Sorry, I couldn't understand it, since I couldn't find any relation
> between f2fs_ioc_start_atomic_write and f2fs_write_inode. Could you
> elaborate more on this? I thought the code might be safe, since it
> happens in the inode eviction phase.
int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
void f2fs_evict_inode(struct inode *inode)
Oops, it looks I was misled by f2fs_write_inode() above f2fs_evict_inode(),
please ignore my comments, sorry. :(
Thanks,
On 2023/2/10 2:18, Daeho Jeong wrote:
> From: Daeho Jeong <daehojeong@google.com>
>
> To fix a race condition between atomic write aborts, I use the inode
> lock and make COW inode to be re-usable thoroughout the whole
> atomic file inode lifetime.
>
> Reported-by: syzbot+823000d23b3400619f7c@syzkaller.appspotmail.com
> Fixes: 3db1de0e582c ("f2fs: change the current atomic write way")
> Signed-off-by: Daeho Jeong <daehojeong@google.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Thanks,
Hello:
This patch was applied to jaegeuk/f2fs.git (dev)
by Jaegeuk Kim <jaegeuk@kernel.org>:
On Thu, 9 Feb 2023 10:18:19 -0800 you wrote:
> From: Daeho Jeong <daehojeong@google.com>
>
> To fix a race condition between atomic write aborts, I use the inode
> lock and make COW inode to be re-usable thoroughout the whole
> atomic file inode lifetime.
>
> Reported-by: syzbot+823000d23b3400619f7c@syzkaller.appspotmail.com
> Fixes: 3db1de0e582c ("f2fs: change the current atomic write way")
> Signed-off-by: Daeho Jeong <daehojeong@google.com>
>
> [...]
Here is the summary with links:
- [f2fs-dev] f2fs: synchronize atomic write aborts
https://git.kernel.org/jaegeuk/f2fs/c/a46bebd502fe
You are awesome, thank you!
@@ -1863,7 +1863,10 @@ static int f2fs_release_file(struct inode *inode, struct file *filp)
atomic_read(&inode->i_writecount) != 1)
return 0;
+ inode_lock(inode);
f2fs_abort_atomic_write(inode, true);
+ inode_unlock(inode);
+
return 0;
}
@@ -1878,8 +1881,12 @@ static int f2fs_file_flush(struct file *file, fl_owner_t id)
* before dropping file lock, it needs to do in ->flush.
*/
if (F2FS_I(inode)->atomic_write_task == current &&
- (current->flags & PF_EXITING))
+ (current->flags & PF_EXITING)) {
+ inode_lock(inode);
f2fs_abort_atomic_write(inode, true);
+ inode_unlock(inode);
+ }
+
return 0;
}
@@ -2085,19 +2092,28 @@ static int f2fs_ioc_start_atomic_write(struct file *filp, bool truncate)
goto out;
}
- /* Create a COW inode for atomic write */
- pinode = f2fs_iget(inode->i_sb, fi->i_pino);
- if (IS_ERR(pinode)) {
- f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
- ret = PTR_ERR(pinode);
- goto out;
- }
+ /* Check if the inode already has a COW inode */
+ if (fi->cow_inode == NULL) {
+ /* Create a COW inode for atomic write */
+ pinode = f2fs_iget(inode->i_sb, fi->i_pino);
+ if (IS_ERR(pinode)) {
+ f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
+ ret = PTR_ERR(pinode);
+ goto out;
+ }
- ret = f2fs_get_tmpfile(mnt_userns, pinode, &fi->cow_inode);
- iput(pinode);
- if (ret) {
- f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
- goto out;
+ ret = f2fs_get_tmpfile(mnt_userns, pinode, &fi->cow_inode);
+ iput(pinode);
+ if (ret) {
+ f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
+ goto out;
+ }
+
+ set_inode_flag(fi->cow_inode, FI_COW_FILE);
+ clear_inode_flag(fi->cow_inode, FI_INLINE_DATA);
+ } else {
+ /* Reuse the already created COW inode */
+ f2fs_do_truncate_blocks(fi->cow_inode, 0, true);
}
f2fs_write_inode(inode, NULL);
@@ -2105,8 +2121,6 @@ static int f2fs_ioc_start_atomic_write(struct file *filp, bool truncate)
stat_inc_atomic_inode(inode);
set_inode_flag(inode, FI_ATOMIC_FILE);
- set_inode_flag(fi->cow_inode, FI_COW_FILE);
- clear_inode_flag(fi->cow_inode, FI_INLINE_DATA);
isize = i_size_read(inode);
fi->original_i_size = isize;
@@ -777,11 +777,18 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
void f2fs_evict_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- nid_t xnid = F2FS_I(inode)->i_xattr_nid;
+ struct f2fs_inode_info *fi = F2FS_I(inode);
+ nid_t xnid = fi->i_xattr_nid;
int err = 0;
f2fs_abort_atomic_write(inode, true);
+ if (fi->cow_inode) {
+ clear_inode_flag(fi->cow_inode, FI_COW_FILE);
+ iput(fi->cow_inode);
+ fi->cow_inode = NULL;
+ }
+
trace_f2fs_evict_inode(inode);
truncate_inode_pages_final(&inode->i_data);
@@ -866,7 +873,7 @@ void f2fs_evict_inode(struct inode *inode)
stat_dec_inline_inode(inode);
stat_dec_compr_inode(inode);
stat_sub_compr_blocks(inode,
- atomic_read(&F2FS_I(inode)->i_compr_blocks));
+ atomic_read(&fi->i_compr_blocks));
if (likely(!f2fs_cp_error(sbi) &&
!is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
@@ -192,9 +192,6 @@ void f2fs_abort_atomic_write(struct inode *inode, bool clean)
if (!f2fs_is_atomic_file(inode))
return;
- clear_inode_flag(fi->cow_inode, FI_COW_FILE);
- iput(fi->cow_inode);
- fi->cow_inode = NULL;
release_atomic_write_cnt(inode);
clear_inode_flag(inode, FI_ATOMIC_COMMITTED);
clear_inode_flag(inode, FI_ATOMIC_REPLACE);
@@ -1427,8 +1427,6 @@ static int f2fs_drop_inode(struct inode *inode)
atomic_inc(&inode->i_count);
spin_unlock(&inode->i_lock);
- f2fs_abort_atomic_write(inode, true);
-
/* should remain fi->extent_tree for writepage */
f2fs_destroy_extent_node(inode);