From: Yunlei He heyunlei@huawei.com
Thread A: Thread B:
-f2fs_remount -sbi->mount_opt.opt = 0; <--- -f2fs_iget -do_read_inode -f2fs_init_extent_tree -F2FS_I(inode)->extent_tree is NULL -default_options && parse_options -remount return <--- -f2fs_map_blocks -f2fs_lookup_extent_tree -f2fs_bug_on(sbi, !et);
The same problem with f2fs_new_inode.
Signed-off-by: Yunlei He heyunlei@huawei.com Signed-off-by: Jaegeuk Kim jaegeuk@kernel.org Signed-off-by: Nikolay Borisov nborisov@suse.com ---
Hello Greg,
I would like to have upstream commit dad48e73127b ("f2fs: fix a bug caused by NULL extent tree") included in the 4.4 stable kernel. This is the backport of it.
fs/f2fs/extent_cache.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-)
diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c index 7ddba812e11b..6827b9c942dc 100644 --- a/fs/f2fs/extent_cache.c +++ b/fs/f2fs/extent_cache.c @@ -172,7 +172,7 @@ void f2fs_drop_largest_extent(struct inode *inode, pgoff_t fofs) __drop_largest_extent(inode, fofs, 1); }
-void f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext) +static void __f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct extent_tree *et; @@ -204,6 +204,14 @@ void f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext) write_unlock(&et->lock); }
+void f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext) +{ + __f2fs_init_extent_tree(inode, i_ext); + + if (!F2FS_I(inode)->extent_tree) + set_inode_flag(F2FS_I(inode), FI_NO_EXTENT); +} + static bool f2fs_lookup_extent_tree(struct inode *inode, pgoff_t pgofs, struct extent_info *ei) {
On Tue, Feb 27, 2018 at 01:23:05PM +0200, Nikolay Borisov wrote:
From: Yunlei He heyunlei@huawei.com
Thread A: Thread B:
-f2fs_remount -sbi->mount_opt.opt = 0; <--- -f2fs_iget -do_read_inode -f2fs_init_extent_tree -F2FS_I(inode)->extent_tree is NULL -default_options && parse_options -remount return <--- -f2fs_map_blocks -f2fs_lookup_extent_tree -f2fs_bug_on(sbi, !et);
The same problem with f2fs_new_inode.
Signed-off-by: Yunlei He heyunlei@huawei.com Signed-off-by: Jaegeuk Kim jaegeuk@kernel.org Signed-off-by: Nikolay Borisov nborisov@suse.com
Hello Greg,
I would like to have upstream commit dad48e73127b ("f2fs: fix a bug caused by NULL extent tree") included in the 4.4 stable kernel. This is the backport of it.
It also needs to go to 4.9.y, right?
Can you provide a backport for that?
thanks,
greg k-h
From: Yunlei He heyunlei@huawei.com
Thread A: Thread B:
-f2fs_remount -sbi->mount_opt.opt = 0; <--- -f2fs_iget -do_read_inode -f2fs_init_extent_tree -F2FS_I(inode)->extent_tree is NULL -default_options && parse_options -remount return <--- -f2fs_map_blocks -f2fs_lookup_extent_tree -f2fs_bug_on(sbi, !et);
The same problem with f2fs_new_inode.
Signed-off-by: Yunlei He heyunlei@huawei.com Signed-off-by: Jaegeuk Kim jaegeuk@kernel.org Signed-off-by: Nikolay Borisov nborisov@suse.com --- Hi,
Here is the 4.9.y backport
fs/f2fs/extent_cache.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-)
diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c index 7b32ce979fe1..63e519658d73 100644 --- a/fs/f2fs/extent_cache.c +++ b/fs/f2fs/extent_cache.c @@ -177,7 +177,7 @@ static void __drop_largest_extent(struct inode *inode, }
/* return true, if inode page is changed */ -bool f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext) +static bool __f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct extent_tree *et; @@ -215,6 +215,16 @@ bool f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext) return false; }
+bool f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext) +{ + bool ret = __f2fs_init_extent_tree(inode, i_ext); + + if (!F2FS_I(inode)->extent_tree) + set_inode_flag(inode, FI_NO_EXTENT); + + return ret; +} + static bool f2fs_lookup_extent_tree(struct inode *inode, pgoff_t pgofs, struct extent_info *ei) {
On Wed, Feb 28, 2018 at 03:46:41PM +0200, Nikolay Borisov wrote:
From: Yunlei He heyunlei@huawei.com
Thread A: Thread B:
-f2fs_remount -sbi->mount_opt.opt = 0; <--- -f2fs_iget -do_read_inode -f2fs_init_extent_tree -F2FS_I(inode)->extent_tree is NULL -default_options && parse_options -remount return <--- -f2fs_map_blocks -f2fs_lookup_extent_tree -f2fs_bug_on(sbi, !et);
The same problem with f2fs_new_inode.
Signed-off-by: Yunlei He heyunlei@huawei.com Signed-off-by: Jaegeuk Kim jaegeuk@kernel.org Signed-off-by: Nikolay Borisov nborisov@suse.com
Hi,
Here is the 4.9.y backport
Thanks, both now applied.
greg k-h
linux-stable-mirror@lists.linaro.org