[PATCH] f2fs: fix to zero post-EOF data when extending file size

[PATCH] f2fs: fix to zero post-EOF data when extending file size

[Chao Yu]

generic/794  4s ... - output mismatch (see /share/git/fstests/results//generic/794.out.bad)
    --- tests/generic/794.out   2026-06-12 08:46:32.766426241 +0800
    +++ /share/git/fstests/results//generic/794.out.bad 2026-07-05 18:32:55.000000000 +0800
    @@ -1,4 +1,16 @@
     QA output created by 794
     append_write
    +FAIL: non-zero data in gap [4080,4096) after shutdown+remount
    +000000 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a  >ZZZZZZZZZZZZZZZZ<
    +*
    +001000
     truncate_up
    ...
    (Run 'diff -u /share/git/fstests/tests/generic/794.out /share/git/fstests/results//generic/794.out.bad'  to see the entire diff)
Ran: generic/794
Failures: generic/794
Failed 1 of 1 tests

Steps of generic/794:
1. write 4096 bytes to file w/ 0x5a
2. use fiemap to get PBA of first block in file
3. truncate file to 4080
4. umount; write 4096 bytes to file w/ 0x5a directly via PBA; mount
5. extend filesize via
   a) append 4096 from offset 4096, or
   b) truncate 8192, or
   c) fallocate 4096 from offset 4096
6. verify the gap is zeroed in memory [4080,4096)
7. sync range 4096 from offset 4096; shutdown -f (flush meta before shutdown)
8. umount; mount; verify [4080,4096) is zeroed or not.

When extending file size (e.g. via truncate, fallocate, or write) across an
unaligned EOF boundary, we need to ensure that post-EOF data in the partial
page is zeroed out in pagecache and marked dirty, meanwhile, tagging the inode
with FI_ZERO_POST_EOF, so that following checkpoint() and fsync() can persist
the page contain zeroed data before committing inode w/ updated i_size.

This help to prevent stale disk data beyond the previous EOF from being exposed
after remounting or crash recovery.

Since f2fs is a LFS filesystem, we only support direct write via PBA in pinfile,
and pinfile has section-aligned filesize, so in Android, there should no problem,
but for other usage in different environment, let's fix this w/ fsync_mode=strict
mount option.

Cc: stable@kernel.org
Signed-off-by: Chao Yu <chao@kernel.org>
---
 fs/f2fs/checkpoint.c |  4 ++++
 fs/f2fs/f2fs.h       |  1 +
 fs/f2fs/file.c       | 35 ++++++++++++++++++++++++++++++++---
 3 files changed, 37 insertions(+), 3 deletions(-)

diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 064f5b537423..6f486d3a94c7 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -1359,6 +1359,10 @@ static int f2fs_sync_inode_meta(struct f2fs_sb_info *sbi)
 		inode = igrab(&fi->vfs_inode);
 		spin_unlock(&sbi->inode_lock[DIRTY_META]);
 		if (inode) {
+			if (is_inode_flag_set(inode, FI_ZERO_POST_EOF)) {
+				filemap_write_and_wait(inode->i_mapping);
+				clear_inode_flag(inode, FI_ZERO_POST_EOF);
+			}
 			sync_inode_metadata(inode, 0);
 
 			/* it's on eviction */
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 8e2fb0bda467..41be09dad43c 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -939,6 +939,7 @@ enum {
 	FI_ATOMIC_REPLACE,	/* indicate atomic replace */
 	FI_OPENED_FILE,		/* indicate file has been opened */
 	FI_DONATE_FINISHED,	/* indicate page donation of file has been finished */
+	FI_ZERO_POST_EOF,	/* indicate unaligned EOF gap was zeroed in pagecache */
 	FI_MAX,			/* max flag, never be used */
 };
 
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 11cc8d79c235..2e9d585073ec 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -36,21 +36,43 @@
 #include <trace/events/f2fs.h>
 #include <uapi/linux/f2fs.h>
 
+static int fill_zero(struct inode *inode, pgoff_t index,
+					loff_t start, loff_t len);
+
 static void f2fs_zero_post_eof_page(struct inode *inode,
 					loff_t new_size, bool lock)
 {
 	loff_t old_size = i_size_read(inode);
+	unsigned int offset;
 
 	if (old_size >= new_size)
 		return;
 
-	if (mapping_empty(inode->i_mapping))
-		return;
-
 	if (lock)
 		filemap_invalidate_lock(inode->i_mapping);
+
 	/* zero or drop pages only in range of [old_size, new_size] */
 	truncate_inode_pages_range(inode->i_mapping, old_size, new_size);
+
+	/*
+	 * When expanding an unaligned EOF size, zero post-EOF data in
+	 * pagecache and set FI_ZERO_POST_EOF, so following checkpointing
+	 * or fsync can persist correct data to disk before committing
+	 * inode w/ updated i_size.
+	 */
+	if (F2FS_OPTION(F2FS_I_SB(inode)).fsync_mode != FSYNC_MODE_STRICT)
+		goto out_unlock;
+
+	offset = old_size & (PAGE_SIZE - 1);
+	if (offset) {
+		unsigned int len = min_t(loff_t, PAGE_SIZE - offset,
+							new_size - old_size);
+		pgoff_t index = old_size >> PAGE_SHIFT;
+
+		fill_zero(inode, index, offset, len);
+		set_inode_flag(inode, FI_ZERO_POST_EOF);
+	}
+out_unlock:
 	if (lock)
 		filemap_invalidate_unlock(inode->i_mapping);
 }
@@ -304,6 +326,13 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end,
 	if (S_ISDIR(inode->i_mode))
 		goto go_write;
 
+	if (is_inode_flag_set(inode, FI_ZERO_POST_EOF)) {
+		ret = filemap_write_and_wait(inode->i_mapping);
+		if (ret)
+			return ret;
+		clear_inode_flag(inode, FI_ZERO_POST_EOF);
+	}
+
 	/* if fdatasync is triggered, let's do in-place-update */
 	if (datasync || get_dirty_pages(inode) <= SM_I(sbi)->min_fsync_blocks)
 		set_inode_flag(inode, FI_NEED_IPU);
-- 
2.49.0

Re: [f2fs-dev] [PATCH] f2fs: fix to zero post-EOF data when extending file size

[patchwork-bot+f2fs]

Hello:

This patch was applied to jaegeuk/f2fs.git (dev)
by Jaegeuk Kim <jaegeuk@kernel.org>:

On Mon,  6 Jul 2026 07:26:06 +0000 you wrote:
> generic/794  4s ... - output mismatch (see /share/git/fstests/results//generic/794.out.bad)
>     --- tests/generic/794.out   2026-06-12 08:46:32.766426241 +0800
>     +++ /share/git/fstests/results//generic/794.out.bad 2026-07-05 18:32:55.000000000 +0800
>     @@ -1,4 +1,16 @@
>      QA output created by 794
>      append_write
>     +FAIL: non-zero data in gap [4080,4096) after shutdown+remount
>     +000000 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a  >ZZZZZZZZZZZZZZZZ<
>     +*
>     +001000
>      truncate_up
>     ...
>     (Run 'diff -u /share/git/fstests/tests/generic/794.out /share/git/fstests/results//generic/794.out.bad'  to see the entire diff)
> Ran: generic/794
> Failures: generic/794
> Failed 1 of 1 tests
> 
> [...]

Here is the summary with links:
  - [f2fs-dev] f2fs: fix to zero post-EOF data when extending file size
    https://git.kernel.org/jaegeuk/f2fs/c/7e097cad3ac1

You are awesome, thank you!
-- 
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html

Re: [f2fs-dev] [PATCH] f2fs: fix to zero post-EOF data when extending file size

[Jaegeuk Kim]

This causes sysmtem hang during xfstests.

On 07/06, Chao Yu via Linux-f2fs-devel wrote:
> generic/794  4s ... - output mismatch (see /share/git/fstests/results//generic/794.out.bad)
>     --- tests/generic/794.out   2026-06-12 08:46:32.766426241 +0800
>     +++ /share/git/fstests/results//generic/794.out.bad 2026-07-05 18:32:55.000000000 +0800
>     @@ -1,4 +1,16 @@
>      QA output created by 794
>      append_write
>     +FAIL: non-zero data in gap [4080,4096) after shutdown+remount
>     +000000 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a  >ZZZZZZZZZZZZZZZZ<
>     +*
>     +001000
>      truncate_up
>     ...
>     (Run 'diff -u /share/git/fstests/tests/generic/794.out /share/git/fstests/results//generic/794.out.bad'  to see the entire diff)
> Ran: generic/794
> Failures: generic/794
> Failed 1 of 1 tests
> 
> Steps of generic/794:
> 1. write 4096 bytes to file w/ 0x5a
> 2. use fiemap to get PBA of first block in file
> 3. truncate file to 4080
> 4. umount; write 4096 bytes to file w/ 0x5a directly via PBA; mount
> 5. extend filesize via
>    a) append 4096 from offset 4096, or
>    b) truncate 8192, or
>    c) fallocate 4096 from offset 4096
> 6. verify the gap is zeroed in memory [4080,4096)
> 7. sync range 4096 from offset 4096; shutdown -f (flush meta before shutdown)
> 8. umount; mount; verify [4080,4096) is zeroed or not.
> 
> When extending file size (e.g. via truncate, fallocate, or write) across an
> unaligned EOF boundary, we need to ensure that post-EOF data in the partial
> page is zeroed out in pagecache and marked dirty, meanwhile, tagging the inode
> with FI_ZERO_POST_EOF, so that following checkpoint() and fsync() can persist
> the page contain zeroed data before committing inode w/ updated i_size.
> 
> This help to prevent stale disk data beyond the previous EOF from being exposed
> after remounting or crash recovery.
> 
> Since f2fs is a LFS filesystem, we only support direct write via PBA in pinfile,
> and pinfile has section-aligned filesize, so in Android, there should no problem,
> but for other usage in different environment, let's fix this w/ fsync_mode=strict
> mount option.
> 
> Cc: stable@kernel.org
> Signed-off-by: Chao Yu <chao@kernel.org>
> ---
>  fs/f2fs/checkpoint.c |  4 ++++
>  fs/f2fs/f2fs.h       |  1 +
>  fs/f2fs/file.c       | 35 ++++++++++++++++++++++++++++++++---
>  3 files changed, 37 insertions(+), 3 deletions(-)
> 
> diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
> index 064f5b537423..6f486d3a94c7 100644
> --- a/fs/f2fs/checkpoint.c
> +++ b/fs/f2fs/checkpoint.c
> @@ -1359,6 +1359,10 @@ static int f2fs_sync_inode_meta(struct f2fs_sb_info *sbi)
>  		inode = igrab(&fi->vfs_inode);
>  		spin_unlock(&sbi->inode_lock[DIRTY_META]);
>  		if (inode) {
> +			if (is_inode_flag_set(inode, FI_ZERO_POST_EOF)) {
> +				filemap_write_and_wait(inode->i_mapping);
> +				clear_inode_flag(inode, FI_ZERO_POST_EOF);
> +			}
>  			sync_inode_metadata(inode, 0);
>  
>  			/* it's on eviction */
> diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
> index 8e2fb0bda467..41be09dad43c 100644
> --- a/fs/f2fs/f2fs.h
> +++ b/fs/f2fs/f2fs.h
> @@ -939,6 +939,7 @@ enum {
>  	FI_ATOMIC_REPLACE,	/* indicate atomic replace */
>  	FI_OPENED_FILE,		/* indicate file has been opened */
>  	FI_DONATE_FINISHED,	/* indicate page donation of file has been finished */
> +	FI_ZERO_POST_EOF,	/* indicate unaligned EOF gap was zeroed in pagecache */
>  	FI_MAX,			/* max flag, never be used */
>  };
>  
> diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
> index 11cc8d79c235..2e9d585073ec 100644
> --- a/fs/f2fs/file.c
> +++ b/fs/f2fs/file.c
> @@ -36,21 +36,43 @@
>  #include <trace/events/f2fs.h>
>  #include <uapi/linux/f2fs.h>
>  
> +static int fill_zero(struct inode *inode, pgoff_t index,
> +					loff_t start, loff_t len);
> +
>  static void f2fs_zero_post_eof_page(struct inode *inode,
>  					loff_t new_size, bool lock)
>  {
>  	loff_t old_size = i_size_read(inode);
> +	unsigned int offset;
>  
>  	if (old_size >= new_size)
>  		return;
>  
> -	if (mapping_empty(inode->i_mapping))
> -		return;
> -
>  	if (lock)
>  		filemap_invalidate_lock(inode->i_mapping);
> +
>  	/* zero or drop pages only in range of [old_size, new_size] */
>  	truncate_inode_pages_range(inode->i_mapping, old_size, new_size);
> +
> +	/*
> +	 * When expanding an unaligned EOF size, zero post-EOF data in
> +	 * pagecache and set FI_ZERO_POST_EOF, so following checkpointing
> +	 * or fsync can persist correct data to disk before committing
> +	 * inode w/ updated i_size.
> +	 */
> +	if (F2FS_OPTION(F2FS_I_SB(inode)).fsync_mode != FSYNC_MODE_STRICT)
> +		goto out_unlock;
> +
> +	offset = old_size & (PAGE_SIZE - 1);
> +	if (offset) {
> +		unsigned int len = min_t(loff_t, PAGE_SIZE - offset,
> +							new_size - old_size);
> +		pgoff_t index = old_size >> PAGE_SHIFT;
> +
> +		fill_zero(inode, index, offset, len);
> +		set_inode_flag(inode, FI_ZERO_POST_EOF);
> +	}
> +out_unlock:
>  	if (lock)
>  		filemap_invalidate_unlock(inode->i_mapping);
>  }
> @@ -304,6 +326,13 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end,
>  	if (S_ISDIR(inode->i_mode))
>  		goto go_write;
>  
> +	if (is_inode_flag_set(inode, FI_ZERO_POST_EOF)) {
> +		ret = filemap_write_and_wait(inode->i_mapping);
> +		if (ret)
> +			return ret;
> +		clear_inode_flag(inode, FI_ZERO_POST_EOF);
> +	}
> +
>  	/* if fdatasync is triggered, let's do in-place-update */
>  	if (datasync || get_dirty_pages(inode) <= SM_I(sbi)->min_fsync_blocks)
>  		set_inode_flag(inode, FI_NEED_IPU);
> -- 
> 2.49.0
> 
> 
> 
> _______________________________________________
> Linux-f2fs-devel mailing list
> Linux-f2fs-devel@lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel

Re: [f2fs-dev] [PATCH] f2fs: fix to zero post-EOF data when extending file size

[Chao Yu]

On 7/16/26 02:05, Jaegeuk Kim wrote:
> This causes sysmtem hang during xfstests.

Fixed a potential deadlock issue during checkpoint in v2, though I can
not reproduce it.

Thanks,

> 
> On 07/06, Chao Yu via Linux-f2fs-devel wrote:
>> generic/794  4s ... - output mismatch (see /share/git/fstests/results//generic/794.out.bad)
>>      --- tests/generic/794.out   2026-06-12 08:46:32.766426241 +0800
>>      +++ /share/git/fstests/results//generic/794.out.bad 2026-07-05 18:32:55.000000000 +0800
>>      @@ -1,4 +1,16 @@
>>       QA output created by 794
>>       append_write
>>      +FAIL: non-zero data in gap [4080,4096) after shutdown+remount
>>      +000000 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a  >ZZZZZZZZZZZZZZZZ<
>>      +*
>>      +001000
>>       truncate_up
>>      ...
>>      (Run 'diff -u /share/git/fstests/tests/generic/794.out /share/git/fstests/results//generic/794.out.bad'  to see the entire diff)
>> Ran: generic/794
>> Failures: generic/794
>> Failed 1 of 1 tests
>>
>> Steps of generic/794:
>> 1. write 4096 bytes to file w/ 0x5a
>> 2. use fiemap to get PBA of first block in file
>> 3. truncate file to 4080
>> 4. umount; write 4096 bytes to file w/ 0x5a directly via PBA; mount
>> 5. extend filesize via
>>     a) append 4096 from offset 4096, or
>>     b) truncate 8192, or
>>     c) fallocate 4096 from offset 4096
>> 6. verify the gap is zeroed in memory [4080,4096)
>> 7. sync range 4096 from offset 4096; shutdown -f (flush meta before shutdown)
>> 8. umount; mount; verify [4080,4096) is zeroed or not.
>>
>> When extending file size (e.g. via truncate, fallocate, or write) across an
>> unaligned EOF boundary, we need to ensure that post-EOF data in the partial
>> page is zeroed out in pagecache and marked dirty, meanwhile, tagging the inode
>> with FI_ZERO_POST_EOF, so that following checkpoint() and fsync() can persist
>> the page contain zeroed data before committing inode w/ updated i_size.
>>
>> This help to prevent stale disk data beyond the previous EOF from being exposed
>> after remounting or crash recovery.
>>
>> Since f2fs is a LFS filesystem, we only support direct write via PBA in pinfile,
>> and pinfile has section-aligned filesize, so in Android, there should no problem,
>> but for other usage in different environment, let's fix this w/ fsync_mode=strict
>> mount option.
>>
>> Cc: stable@kernel.org
>> Signed-off-by: Chao Yu <chao@kernel.org>
>> ---
>>   fs/f2fs/checkpoint.c |  4 ++++
>>   fs/f2fs/f2fs.h       |  1 +
>>   fs/f2fs/file.c       | 35 ++++++++++++++++++++++++++++++++---
>>   3 files changed, 37 insertions(+), 3 deletions(-)
>>
>> diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
>> index 064f5b537423..6f486d3a94c7 100644
>> --- a/fs/f2fs/checkpoint.c
>> +++ b/fs/f2fs/checkpoint.c
>> @@ -1359,6 +1359,10 @@ static int f2fs_sync_inode_meta(struct f2fs_sb_info *sbi)
>>   		inode = igrab(&fi->vfs_inode);
>>   		spin_unlock(&sbi->inode_lock[DIRTY_META]);
>>   		if (inode) {
>> +			if (is_inode_flag_set(inode, FI_ZERO_POST_EOF)) {
>> +				filemap_write_and_wait(inode->i_mapping);
>> +				clear_inode_flag(inode, FI_ZERO_POST_EOF);
>> +			}
>>   			sync_inode_metadata(inode, 0);
>>   
>>   			/* it's on eviction */
>> diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
>> index 8e2fb0bda467..41be09dad43c 100644
>> --- a/fs/f2fs/f2fs.h
>> +++ b/fs/f2fs/f2fs.h
>> @@ -939,6 +939,7 @@ enum {
>>   	FI_ATOMIC_REPLACE,	/* indicate atomic replace */
>>   	FI_OPENED_FILE,		/* indicate file has been opened */
>>   	FI_DONATE_FINISHED,	/* indicate page donation of file has been finished */
>> +	FI_ZERO_POST_EOF,	/* indicate unaligned EOF gap was zeroed in pagecache */
>>   	FI_MAX,			/* max flag, never be used */
>>   };
>>   
>> diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
>> index 11cc8d79c235..2e9d585073ec 100644
>> --- a/fs/f2fs/file.c
>> +++ b/fs/f2fs/file.c
>> @@ -36,21 +36,43 @@
>>   #include <trace/events/f2fs.h>
>>   #include <uapi/linux/f2fs.h>
>>   
>> +static int fill_zero(struct inode *inode, pgoff_t index,
>> +					loff_t start, loff_t len);
>> +
>>   static void f2fs_zero_post_eof_page(struct inode *inode,
>>   					loff_t new_size, bool lock)
>>   {
>>   	loff_t old_size = i_size_read(inode);
>> +	unsigned int offset;
>>   
>>   	if (old_size >= new_size)
>>   		return;
>>   
>> -	if (mapping_empty(inode->i_mapping))
>> -		return;
>> -
>>   	if (lock)
>>   		filemap_invalidate_lock(inode->i_mapping);
>> +
>>   	/* zero or drop pages only in range of [old_size, new_size] */
>>   	truncate_inode_pages_range(inode->i_mapping, old_size, new_size);
>> +
>> +	/*
>> +	 * When expanding an unaligned EOF size, zero post-EOF data in
>> +	 * pagecache and set FI_ZERO_POST_EOF, so following checkpointing
>> +	 * or fsync can persist correct data to disk before committing
>> +	 * inode w/ updated i_size.
>> +	 */
>> +	if (F2FS_OPTION(F2FS_I_SB(inode)).fsync_mode != FSYNC_MODE_STRICT)
>> +		goto out_unlock;
>> +
>> +	offset = old_size & (PAGE_SIZE - 1);
>> +	if (offset) {
>> +		unsigned int len = min_t(loff_t, PAGE_SIZE - offset,
>> +							new_size - old_size);
>> +		pgoff_t index = old_size >> PAGE_SHIFT;
>> +
>> +		fill_zero(inode, index, offset, len);
>> +		set_inode_flag(inode, FI_ZERO_POST_EOF);
>> +	}
>> +out_unlock:
>>   	if (lock)
>>   		filemap_invalidate_unlock(inode->i_mapping);
>>   }
>> @@ -304,6 +326,13 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end,
>>   	if (S_ISDIR(inode->i_mode))
>>   		goto go_write;
>>   
>> +	if (is_inode_flag_set(inode, FI_ZERO_POST_EOF)) {
>> +		ret = filemap_write_and_wait(inode->i_mapping);
>> +		if (ret)
>> +			return ret;
>> +		clear_inode_flag(inode, FI_ZERO_POST_EOF);
>> +	}
>> +
>>   	/* if fdatasync is triggered, let's do in-place-update */
>>   	if (datasync || get_dirty_pages(inode) <= SM_I(sbi)->min_fsync_blocks)
>>   		set_inode_flag(inode, FI_NEED_IPU);
>> -- 
>> 2.49.0
>>
>>
>>
>> _______________________________________________
>> Linux-f2fs-devel mailing list
>> Linux-f2fs-devel@lists.sourceforge.net
>> https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel

Re: [f2fs-dev] [PATCH] f2fs: fix to zero post-EOF data when extending file size

[Jaegeuk Kim]

On 07/20, Chao Yu via Linux-f2fs-devel wrote:
> On 7/16/26 02:05, Jaegeuk Kim wrote:
> > This causes sysmtem hang during xfstests.
> 
> Fixed a potential deadlock issue during checkpoint in v2, though I can
> not reproduce it.

I got this on generic/269 with v2. I'll dequeue the patch first.

[   90.879237] ------------[ cut here ]------------
[   90.881987] kernel BUG at segment.c:2902!
[   90.884058] Oops: invalid opcode: 0000 [#1] SMP NOPTI
[   90.886628] CPU: 7 UID: 0 PID: 2566 Comm: f2fs_ckpt-252:3 Tainted: G           OE       7.2.0-rc5-custom #1 PREEMPT(full)
[   90.891533] Tainted: [O]=OOT_MODULE, [E]=UNSIGNED_MODULE
[   90.894647] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.17.0-debian-1.17.0-1 04/01/2014
[   90.900014] RIP: 0010:new_curseg+0xa17/0xa60 [f2fs]
[   90.902240] Code: 8b 71 48 e9 16 f8 ff ff 4c 8b 69 08 41 8b 84 24 4c 06 00 00 31 d2 41 8b 8c 24 48 06 00 00 f7 f1 89 45 a4 89 f0 e9 e9 fe ff ff <0f> 0b 49 8b 3c 24 68 40 0c 00 00 45 31 c0 31 c9 41 b9 8b ff ff ff
[   90.910818] RSP: 0018:ffffd4acc4167670 EFLAGS: 00010293
[   90.913153] RAX: 00000000000000f8 RBX: 0000000000000000 RCX: 0000000000000000
[   90.916400] RDX: ffffffffffffffff RSI: 00000000000000f8 RDI: 00000000000000f8
[   90.919494] RBP: ffffd4acc41676d0 R08: ffff8d640bdab2a0 R09: ffffffffc10673eb
[   90.923182] R10: 00000000000000f8 R11: 0000000000000014 R12: ffff8d64892c6000
[   90.926315] R13: ffff8d648c236b80 R14: 00000000000000f8 R15: 0000000000000000
[   90.929430] FS:  0000000000000000(0000) GS:ffff8d6504b73000(0000) knlGS:0000000000000000
[   90.933668] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   90.937206] CR2: 00005577fade9868 CR3: 0000000092d82002 CR4: 0000000000372ef0
[   90.940305] Call Trace:
[   90.941486]  <TASK>
[   90.942464]  f2fs_allocate_data_block+0x69b/0xb10 [f2fs]
[   90.944862]  do_write_page+0x72/0x360 [f2fs]
[   90.946798]  ? __folio_start_writeback+0x90/0x1d0
[   90.949485]  f2fs_do_write_node_page+0x35/0x70 [f2fs]
[   90.952813]  __write_node_folio+0x33c/0x640 [f2fs]
[   90.955104]  ? debug_smp_processor_id+0x17/0x20
[   90.957550]  f2fs_sync_node_pages+0x3d8/0x530 [f2fs]
[   90.960954]  block_operations+0x41d/0x590 [f2fs]
[   90.963415]  ? __pfx_issue_checkpoint_thread+0x10/0x10 [f2fs]
[   90.966293]  f2fs_write_checkpoint+0x15a/0x13c0 [f2fs]
[   90.969193]  ? update_load_avg+0x79/0x2e0
[   90.971712]  ? kvm_clock_get_cycles+0x18/0x40
[   90.974030]  ? module_sect_read+0x81/0xc0
[   90.976675]  ? __pfx_issue_checkpoint_thread+0x10/0x10 [f2fs]
[   90.980146]  __write_checkpoint_sync+0x75/0xb0 [f2fs]
[   90.983100]  __checkpoint_and_complete_reqs+0x3b/0x110 [f2fs]
[   90.986332]  ? __pfx_issue_checkpoint_thread+0x10/0x10 [f2fs]
[   90.989853]  issue_checkpoint_thread+0x4b/0x100 [f2fs]
[   90.992622]  ? __pfx_autoremove_wake_function+0x10/0x10
[   90.995875]  kthread+0x10a/0x140
[   90.998141]  ? __pfx_kthread+0x10/0x10
[   91.000585]  ret_from_fork+0x1ef/0x2b0
[   91.002565]  ? __pfx_kthread+0x10/0x10
[   91.004510]  ret_from_fork_asm+0x1a/0x30

> 
> Thanks,
> 
> > 
> > On 07/06, Chao Yu via Linux-f2fs-devel wrote:
> > > generic/794  4s ... - output mismatch (see /share/git/fstests/results//generic/794.out.bad)
> > >      --- tests/generic/794.out   2026-06-12 08:46:32.766426241 +0800
> > >      +++ /share/git/fstests/results//generic/794.out.bad 2026-07-05 18:32:55.000000000 +0800
> > >      @@ -1,4 +1,16 @@
> > >       QA output created by 794
> > >       append_write
> > >      +FAIL: non-zero data in gap [4080,4096) after shutdown+remount
> > >      +000000 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a  >ZZZZZZZZZZZZZZZZ<
> > >      +*
> > >      +001000
> > >       truncate_up
> > >      ...
> > >      (Run 'diff -u /share/git/fstests/tests/generic/794.out /share/git/fstests/results//generic/794.out.bad'  to see the entire diff)
> > > Ran: generic/794
> > > Failures: generic/794
> > > Failed 1 of 1 tests
> > > 
> > > Steps of generic/794:
> > > 1. write 4096 bytes to file w/ 0x5a
> > > 2. use fiemap to get PBA of first block in file
> > > 3. truncate file to 4080
> > > 4. umount; write 4096 bytes to file w/ 0x5a directly via PBA; mount
> > > 5. extend filesize via
> > >     a) append 4096 from offset 4096, or
> > >     b) truncate 8192, or
> > >     c) fallocate 4096 from offset 4096
> > > 6. verify the gap is zeroed in memory [4080,4096)
> > > 7. sync range 4096 from offset 4096; shutdown -f (flush meta before shutdown)
> > > 8. umount; mount; verify [4080,4096) is zeroed or not.
> > > 
> > > When extending file size (e.g. via truncate, fallocate, or write) across an
> > > unaligned EOF boundary, we need to ensure that post-EOF data in the partial
> > > page is zeroed out in pagecache and marked dirty, meanwhile, tagging the inode
> > > with FI_ZERO_POST_EOF, so that following checkpoint() and fsync() can persist
> > > the page contain zeroed data before committing inode w/ updated i_size.
> > > 
> > > This help to prevent stale disk data beyond the previous EOF from being exposed
> > > after remounting or crash recovery.
> > > 
> > > Since f2fs is a LFS filesystem, we only support direct write via PBA in pinfile,
> > > and pinfile has section-aligned filesize, so in Android, there should no problem,
> > > but for other usage in different environment, let's fix this w/ fsync_mode=strict
> > > mount option.
> > > 
> > > Cc: stable@kernel.org
> > > Signed-off-by: Chao Yu <chao@kernel.org>
> > > ---
> > >   fs/f2fs/checkpoint.c |  4 ++++
> > >   fs/f2fs/f2fs.h       |  1 +
> > >   fs/f2fs/file.c       | 35 ++++++++++++++++++++++++++++++++---
> > >   3 files changed, 37 insertions(+), 3 deletions(-)
> > > 
> > > diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
> > > index 064f5b537423..6f486d3a94c7 100644
> > > --- a/fs/f2fs/checkpoint.c
> > > +++ b/fs/f2fs/checkpoint.c
> > > @@ -1359,6 +1359,10 @@ static int f2fs_sync_inode_meta(struct f2fs_sb_info *sbi)
> > >   		inode = igrab(&fi->vfs_inode);
> > >   		spin_unlock(&sbi->inode_lock[DIRTY_META]);
> > >   		if (inode) {
> > > +			if (is_inode_flag_set(inode, FI_ZERO_POST_EOF)) {
> > > +				filemap_write_and_wait(inode->i_mapping);
> > > +				clear_inode_flag(inode, FI_ZERO_POST_EOF);
> > > +			}
> > >   			sync_inode_metadata(inode, 0);
> > >   			/* it's on eviction */
> > > diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
> > > index 8e2fb0bda467..41be09dad43c 100644
> > > --- a/fs/f2fs/f2fs.h
> > > +++ b/fs/f2fs/f2fs.h
> > > @@ -939,6 +939,7 @@ enum {
> > >   	FI_ATOMIC_REPLACE,	/* indicate atomic replace */
> > >   	FI_OPENED_FILE,		/* indicate file has been opened */
> > >   	FI_DONATE_FINISHED,	/* indicate page donation of file has been finished */
> > > +	FI_ZERO_POST_EOF,	/* indicate unaligned EOF gap was zeroed in pagecache */
> > >   	FI_MAX,			/* max flag, never be used */
> > >   };
> > > diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
> > > index 11cc8d79c235..2e9d585073ec 100644
> > > --- a/fs/f2fs/file.c
> > > +++ b/fs/f2fs/file.c
> > > @@ -36,21 +36,43 @@
> > >   #include <trace/events/f2fs.h>
> > >   #include <uapi/linux/f2fs.h>
> > > +static int fill_zero(struct inode *inode, pgoff_t index,
> > > +					loff_t start, loff_t len);
> > > +
> > >   static void f2fs_zero_post_eof_page(struct inode *inode,
> > >   					loff_t new_size, bool lock)
> > >   {
> > >   	loff_t old_size = i_size_read(inode);
> > > +	unsigned int offset;
> > >   	if (old_size >= new_size)
> > >   		return;
> > > -	if (mapping_empty(inode->i_mapping))
> > > -		return;
> > > -
> > >   	if (lock)
> > >   		filemap_invalidate_lock(inode->i_mapping);
> > > +
> > >   	/* zero or drop pages only in range of [old_size, new_size] */
> > >   	truncate_inode_pages_range(inode->i_mapping, old_size, new_size);
> > > +
> > > +	/*
> > > +	 * When expanding an unaligned EOF size, zero post-EOF data in
> > > +	 * pagecache and set FI_ZERO_POST_EOF, so following checkpointing
> > > +	 * or fsync can persist correct data to disk before committing
> > > +	 * inode w/ updated i_size.
> > > +	 */
> > > +	if (F2FS_OPTION(F2FS_I_SB(inode)).fsync_mode != FSYNC_MODE_STRICT)
> > > +		goto out_unlock;
> > > +
> > > +	offset = old_size & (PAGE_SIZE - 1);
> > > +	if (offset) {
> > > +		unsigned int len = min_t(loff_t, PAGE_SIZE - offset,
> > > +							new_size - old_size);
> > > +		pgoff_t index = old_size >> PAGE_SHIFT;
> > > +
> > > +		fill_zero(inode, index, offset, len);
> > > +		set_inode_flag(inode, FI_ZERO_POST_EOF);
> > > +	}
> > > +out_unlock:
> > >   	if (lock)
> > >   		filemap_invalidate_unlock(inode->i_mapping);
> > >   }
> > > @@ -304,6 +326,13 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end,
> > >   	if (S_ISDIR(inode->i_mode))
> > >   		goto go_write;
> > > +	if (is_inode_flag_set(inode, FI_ZERO_POST_EOF)) {
> > > +		ret = filemap_write_and_wait(inode->i_mapping);
> > > +		if (ret)
> > > +			return ret;
> > > +		clear_inode_flag(inode, FI_ZERO_POST_EOF);
> > > +	}
> > > +
> > >   	/* if fdatasync is triggered, let's do in-place-update */
> > >   	if (datasync || get_dirty_pages(inode) <= SM_I(sbi)->min_fsync_blocks)
> > >   		set_inode_flag(inode, FI_NEED_IPU);
> > > -- 
> > > 2.49.0
> > > 
> > > 
> > > 
> > > _______________________________________________
> > > Linux-f2fs-devel mailing list
> > > Linux-f2fs-devel@lists.sourceforge.net
> > > https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel
> 
> 
> 
> _______________________________________________
> Linux-f2fs-devel mailing list
> Linux-f2fs-devel@lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel

Re: [f2fs-dev] [PATCH] f2fs: fix to zero post-EOF data when extending file size

[Chao Yu]

On 7/29/26 11:41, Jaegeuk Kim wrote:
> On 07/20, Chao Yu via Linux-f2fs-devel wrote:
>> On 7/16/26 02:05, Jaegeuk Kim wrote:
>>> This causes sysmtem hang during xfstests.
>>
>> Fixed a potential deadlock issue during checkpoint in v2, though I can
>> not reproduce it.
> 
> I got this on generic/269 with v2. I'll dequeue the patch first.

Oh, sorry, will take a look.

To confirm, do you run generic/269 test w/ fsync_mode=strict mount option?

If so, I guess this patch will run out-of-space since we trigger page writeback
of regular inodes during checkpoint(). :/

Thanks,

> 
> [   90.879237] ------------[ cut here ]------------
> [   90.881987] kernel BUG at segment.c:2902!
> [   90.884058] Oops: invalid opcode: 0000 [#1] SMP NOPTI
> [   90.886628] CPU: 7 UID: 0 PID: 2566 Comm: f2fs_ckpt-252:3 Tainted: G           OE       7.2.0-rc5-custom #1 PREEMPT(full)
> [   90.891533] Tainted: [O]=OOT_MODULE, [E]=UNSIGNED_MODULE
> [   90.894647] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.17.0-debian-1.17.0-1 04/01/2014
> [   90.900014] RIP: 0010:new_curseg+0xa17/0xa60 [f2fs]
> [   90.902240] Code: 8b 71 48 e9 16 f8 ff ff 4c 8b 69 08 41 8b 84 24 4c 06 00 00 31 d2 41 8b 8c 24 48 06 00 00 f7 f1 89 45 a4 89 f0 e9 e9 fe ff ff <0f> 0b 49 8b 3c 24 68 40 0c 00 00 45 31 c0 31 c9 41 b9 8b ff ff ff
> [   90.910818] RSP: 0018:ffffd4acc4167670 EFLAGS: 00010293
> [   90.913153] RAX: 00000000000000f8 RBX: 0000000000000000 RCX: 0000000000000000
> [   90.916400] RDX: ffffffffffffffff RSI: 00000000000000f8 RDI: 00000000000000f8
> [   90.919494] RBP: ffffd4acc41676d0 R08: ffff8d640bdab2a0 R09: ffffffffc10673eb
> [   90.923182] R10: 00000000000000f8 R11: 0000000000000014 R12: ffff8d64892c6000
> [   90.926315] R13: ffff8d648c236b80 R14: 00000000000000f8 R15: 0000000000000000
> [   90.929430] FS:  0000000000000000(0000) GS:ffff8d6504b73000(0000) knlGS:0000000000000000
> [   90.933668] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> [   90.937206] CR2: 00005577fade9868 CR3: 0000000092d82002 CR4: 0000000000372ef0
> [   90.940305] Call Trace:
> [   90.941486]  <TASK>
> [   90.942464]  f2fs_allocate_data_block+0x69b/0xb10 [f2fs]
> [   90.944862]  do_write_page+0x72/0x360 [f2fs]
> [   90.946798]  ? __folio_start_writeback+0x90/0x1d0
> [   90.949485]  f2fs_do_write_node_page+0x35/0x70 [f2fs]
> [   90.952813]  __write_node_folio+0x33c/0x640 [f2fs]
> [   90.955104]  ? debug_smp_processor_id+0x17/0x20
> [   90.957550]  f2fs_sync_node_pages+0x3d8/0x530 [f2fs]
> [   90.960954]  block_operations+0x41d/0x590 [f2fs]
> [   90.963415]  ? __pfx_issue_checkpoint_thread+0x10/0x10 [f2fs]
> [   90.966293]  f2fs_write_checkpoint+0x15a/0x13c0 [f2fs]
> [   90.969193]  ? update_load_avg+0x79/0x2e0
> [   90.971712]  ? kvm_clock_get_cycles+0x18/0x40
> [   90.974030]  ? module_sect_read+0x81/0xc0
> [   90.976675]  ? __pfx_issue_checkpoint_thread+0x10/0x10 [f2fs]
> [   90.980146]  __write_checkpoint_sync+0x75/0xb0 [f2fs]
> [   90.983100]  __checkpoint_and_complete_reqs+0x3b/0x110 [f2fs]
> [   90.986332]  ? __pfx_issue_checkpoint_thread+0x10/0x10 [f2fs]
> [   90.989853]  issue_checkpoint_thread+0x4b/0x100 [f2fs]
> [   90.992622]  ? __pfx_autoremove_wake_function+0x10/0x10
> [   90.995875]  kthread+0x10a/0x140
> [   90.998141]  ? __pfx_kthread+0x10/0x10
> [   91.000585]  ret_from_fork+0x1ef/0x2b0
> [   91.002565]  ? __pfx_kthread+0x10/0x10
> [   91.004510]  ret_from_fork_asm+0x1a/0x30
> 
>>
>> Thanks,
>>
>>>
>>> On 07/06, Chao Yu via Linux-f2fs-devel wrote:
>>>> generic/794  4s ... - output mismatch (see /share/git/fstests/results//generic/794.out.bad)
>>>>      --- tests/generic/794.out   2026-06-12 08:46:32.766426241 +0800
>>>>      +++ /share/git/fstests/results//generic/794.out.bad 2026-07-05 18:32:55.000000000 +0800
>>>>      @@ -1,4 +1,16 @@
>>>>       QA output created by 794
>>>>       append_write
>>>>      +FAIL: non-zero data in gap [4080,4096) after shutdown+remount
>>>>      +000000 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a  >ZZZZZZZZZZZZZZZZ<
>>>>      +*
>>>>      +001000
>>>>       truncate_up
>>>>      ...
>>>>      (Run 'diff -u /share/git/fstests/tests/generic/794.out /share/git/fstests/results//generic/794.out.bad'  to see the entire diff)
>>>> Ran: generic/794
>>>> Failures: generic/794
>>>> Failed 1 of 1 tests
>>>>
>>>> Steps of generic/794:
>>>> 1. write 4096 bytes to file w/ 0x5a
>>>> 2. use fiemap to get PBA of first block in file
>>>> 3. truncate file to 4080
>>>> 4. umount; write 4096 bytes to file w/ 0x5a directly via PBA; mount
>>>> 5. extend filesize via
>>>>     a) append 4096 from offset 4096, or
>>>>     b) truncate 8192, or
>>>>     c) fallocate 4096 from offset 4096
>>>> 6. verify the gap is zeroed in memory [4080,4096)
>>>> 7. sync range 4096 from offset 4096; shutdown -f (flush meta before shutdown)
>>>> 8. umount; mount; verify [4080,4096) is zeroed or not.
>>>>
>>>> When extending file size (e.g. via truncate, fallocate, or write) across an
>>>> unaligned EOF boundary, we need to ensure that post-EOF data in the partial
>>>> page is zeroed out in pagecache and marked dirty, meanwhile, tagging the inode
>>>> with FI_ZERO_POST_EOF, so that following checkpoint() and fsync() can persist
>>>> the page contain zeroed data before committing inode w/ updated i_size.
>>>>
>>>> This help to prevent stale disk data beyond the previous EOF from being exposed
>>>> after remounting or crash recovery.
>>>>
>>>> Since f2fs is a LFS filesystem, we only support direct write via PBA in pinfile,
>>>> and pinfile has section-aligned filesize, so in Android, there should no problem,
>>>> but for other usage in different environment, let's fix this w/ fsync_mode=strict
>>>> mount option.
>>>>
>>>> Cc: stable@kernel.org
>>>> Signed-off-by: Chao Yu <chao@kernel.org>
>>>> ---
>>>>   fs/f2fs/checkpoint.c |  4 ++++
>>>>   fs/f2fs/f2fs.h       |  1 +
>>>>   fs/f2fs/file.c       | 35 ++++++++++++++++++++++++++++++++---
>>>>   3 files changed, 37 insertions(+), 3 deletions(-)
>>>>
>>>> diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
>>>> index 064f5b537423..6f486d3a94c7 100644
>>>> --- a/fs/f2fs/checkpoint.c
>>>> +++ b/fs/f2fs/checkpoint.c
>>>> @@ -1359,6 +1359,10 @@ static int f2fs_sync_inode_meta(struct f2fs_sb_info *sbi)
>>>>   		inode = igrab(&fi->vfs_inode);
>>>>   		spin_unlock(&sbi->inode_lock[DIRTY_META]);
>>>>   		if (inode) {
>>>> +			if (is_inode_flag_set(inode, FI_ZERO_POST_EOF)) {
>>>> +				filemap_write_and_wait(inode->i_mapping);
>>>> +				clear_inode_flag(inode, FI_ZERO_POST_EOF);
>>>> +			}
>>>>   			sync_inode_metadata(inode, 0);
>>>>   			/* it's on eviction */
>>>> diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
>>>> index 8e2fb0bda467..41be09dad43c 100644
>>>> --- a/fs/f2fs/f2fs.h
>>>> +++ b/fs/f2fs/f2fs.h
>>>> @@ -939,6 +939,7 @@ enum {
>>>>   	FI_ATOMIC_REPLACE,	/* indicate atomic replace */
>>>>   	FI_OPENED_FILE,		/* indicate file has been opened */
>>>>   	FI_DONATE_FINISHED,	/* indicate page donation of file has been finished */
>>>> +	FI_ZERO_POST_EOF,	/* indicate unaligned EOF gap was zeroed in pagecache */
>>>>   	FI_MAX,			/* max flag, never be used */
>>>>   };
>>>> diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
>>>> index 11cc8d79c235..2e9d585073ec 100644
>>>> --- a/fs/f2fs/file.c
>>>> +++ b/fs/f2fs/file.c
>>>> @@ -36,21 +36,43 @@
>>>>   #include <trace/events/f2fs.h>
>>>>   #include <uapi/linux/f2fs.h>
>>>> +static int fill_zero(struct inode *inode, pgoff_t index,
>>>> +					loff_t start, loff_t len);
>>>> +
>>>>   static void f2fs_zero_post_eof_page(struct inode *inode,
>>>>   					loff_t new_size, bool lock)
>>>>   {
>>>>   	loff_t old_size = i_size_read(inode);
>>>> +	unsigned int offset;
>>>>   	if (old_size >= new_size)
>>>>   		return;
>>>> -	if (mapping_empty(inode->i_mapping))
>>>> -		return;
>>>> -
>>>>   	if (lock)
>>>>   		filemap_invalidate_lock(inode->i_mapping);
>>>> +
>>>>   	/* zero or drop pages only in range of [old_size, new_size] */
>>>>   	truncate_inode_pages_range(inode->i_mapping, old_size, new_size);
>>>> +
>>>> +	/*
>>>> +	 * When expanding an unaligned EOF size, zero post-EOF data in
>>>> +	 * pagecache and set FI_ZERO_POST_EOF, so following checkpointing
>>>> +	 * or fsync can persist correct data to disk before committing
>>>> +	 * inode w/ updated i_size.
>>>> +	 */
>>>> +	if (F2FS_OPTION(F2FS_I_SB(inode)).fsync_mode != FSYNC_MODE_STRICT)
>>>> +		goto out_unlock;
>>>> +
>>>> +	offset = old_size & (PAGE_SIZE - 1);
>>>> +	if (offset) {
>>>> +		unsigned int len = min_t(loff_t, PAGE_SIZE - offset,
>>>> +							new_size - old_size);
>>>> +		pgoff_t index = old_size >> PAGE_SHIFT;
>>>> +
>>>> +		fill_zero(inode, index, offset, len);
>>>> +		set_inode_flag(inode, FI_ZERO_POST_EOF);
>>>> +	}
>>>> +out_unlock:
>>>>   	if (lock)
>>>>   		filemap_invalidate_unlock(inode->i_mapping);
>>>>   }
>>>> @@ -304,6 +326,13 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end,
>>>>   	if (S_ISDIR(inode->i_mode))
>>>>   		goto go_write;
>>>> +	if (is_inode_flag_set(inode, FI_ZERO_POST_EOF)) {
>>>> +		ret = filemap_write_and_wait(inode->i_mapping);
>>>> +		if (ret)
>>>> +			return ret;
>>>> +		clear_inode_flag(inode, FI_ZERO_POST_EOF);
>>>> +	}
>>>> +
>>>>   	/* if fdatasync is triggered, let's do in-place-update */
>>>>   	if (datasync || get_dirty_pages(inode) <= SM_I(sbi)->min_fsync_blocks)
>>>>   		set_inode_flag(inode, FI_NEED_IPU);
>>>> -- 
>>>> 2.49.0
>>>>
>>>>
>>>>
>>>> _______________________________________________
>>>> Linux-f2fs-devel mailing list
>>>> Linux-f2fs-devel@lists.sourceforge.net
>>>> https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel
>>
>>
>>
>> _______________________________________________
>> Linux-f2fs-devel mailing list
>> Linux-f2fs-devel@lists.sourceforge.net
>> https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel

Re: [f2fs-dev] [PATCH] f2fs: fix to zero post-EOF data when extending file size

[Jaegeuk Kim]

On 07/29, Chao Yu via Linux-f2fs-devel wrote:
> On 7/29/26 11:41, Jaegeuk Kim wrote:
> > On 07/20, Chao Yu via Linux-f2fs-devel wrote:
> >> On 7/16/26 02:05, Jaegeuk Kim wrote:
> >>> This causes sysmtem hang during xfstests.
> >>
> >> Fixed a potential deadlock issue during checkpoint in v2, though I can
> >> not reproduce it.
> > 
> > I got this on generic/269 with v2. I'll dequeue the patch first.
> 
> Oh, sorry, will take a look.
> 
> To confirm, do you run generic/269 test w/ fsync_mode=strict mount option?

Yes.

> 
> If so, I guess this patch will run out-of-space since we trigger page writeback
> of regular inodes during checkpoint(). :/
> 
> Thanks,
> 
> > 
> > [   90.879237] ------------[ cut here ]------------
> > [   90.881987] kernel BUG at segment.c:2902!
> > [   90.884058] Oops: invalid opcode: 0000 [#1] SMP NOPTI
> > [   90.886628] CPU: 7 UID: 0 PID: 2566 Comm: f2fs_ckpt-252:3 Tainted: G           OE       7.2.0-rc5-custom #1 PREEMPT(full)
> > [   90.891533] Tainted: [O]=OOT_MODULE, [E]=UNSIGNED_MODULE
> > [   90.894647] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.17.0-debian-1.17.0-1 04/01/2014
> > [   90.900014] RIP: 0010:new_curseg+0xa17/0xa60 [f2fs]
> > [   90.902240] Code: 8b 71 48 e9 16 f8 ff ff 4c 8b 69 08 41 8b 84 24 4c 06 00 00 31 d2 41 8b 8c 24 48 06 00 00 f7 f1 89 45 a4 89 f0 e9 e9 fe ff ff <0f> 0b 49 8b 3c 24 68 40 0c 00 00 45 31 c0 31 c9 41 b9 8b ff ff ff
> > [   90.910818] RSP: 0018:ffffd4acc4167670 EFLAGS: 00010293
> > [   90.913153] RAX: 00000000000000f8 RBX: 0000000000000000 RCX: 0000000000000000
> > [   90.916400] RDX: ffffffffffffffff RSI: 00000000000000f8 RDI: 00000000000000f8
> > [   90.919494] RBP: ffffd4acc41676d0 R08: ffff8d640bdab2a0 R09: ffffffffc10673eb
> > [   90.923182] R10: 00000000000000f8 R11: 0000000000000014 R12: ffff8d64892c6000
> > [   90.926315] R13: ffff8d648c236b80 R14: 00000000000000f8 R15: 0000000000000000
> > [   90.929430] FS:  0000000000000000(0000) GS:ffff8d6504b73000(0000) knlGS:0000000000000000
> > [   90.933668] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> > [   90.937206] CR2: 00005577fade9868 CR3: 0000000092d82002 CR4: 0000000000372ef0
> > [   90.940305] Call Trace:
> > [   90.941486]  <TASK>
> > [   90.942464]  f2fs_allocate_data_block+0x69b/0xb10 [f2fs]
> > [   90.944862]  do_write_page+0x72/0x360 [f2fs]
> > [   90.946798]  ? __folio_start_writeback+0x90/0x1d0
> > [   90.949485]  f2fs_do_write_node_page+0x35/0x70 [f2fs]
> > [   90.952813]  __write_node_folio+0x33c/0x640 [f2fs]
> > [   90.955104]  ? debug_smp_processor_id+0x17/0x20
> > [   90.957550]  f2fs_sync_node_pages+0x3d8/0x530 [f2fs]
> > [   90.960954]  block_operations+0x41d/0x590 [f2fs]
> > [   90.963415]  ? __pfx_issue_checkpoint_thread+0x10/0x10 [f2fs]
> > [   90.966293]  f2fs_write_checkpoint+0x15a/0x13c0 [f2fs]
> > [   90.969193]  ? update_load_avg+0x79/0x2e0
> > [   90.971712]  ? kvm_clock_get_cycles+0x18/0x40
> > [   90.974030]  ? module_sect_read+0x81/0xc0
> > [   90.976675]  ? __pfx_issue_checkpoint_thread+0x10/0x10 [f2fs]
> > [   90.980146]  __write_checkpoint_sync+0x75/0xb0 [f2fs]
> > [   90.983100]  __checkpoint_and_complete_reqs+0x3b/0x110 [f2fs]
> > [   90.986332]  ? __pfx_issue_checkpoint_thread+0x10/0x10 [f2fs]
> > [   90.989853]  issue_checkpoint_thread+0x4b/0x100 [f2fs]
> > [   90.992622]  ? __pfx_autoremove_wake_function+0x10/0x10
> > [   90.995875]  kthread+0x10a/0x140
> > [   90.998141]  ? __pfx_kthread+0x10/0x10
> > [   91.000585]  ret_from_fork+0x1ef/0x2b0
> > [   91.002565]  ? __pfx_kthread+0x10/0x10
> > [   91.004510]  ret_from_fork_asm+0x1a/0x30
> > 
> >>
> >> Thanks,
> >>
> >>>
> >>> On 07/06, Chao Yu via Linux-f2fs-devel wrote:
> >>>> generic/794  4s ... - output mismatch (see /share/git/fstests/results//generic/794.out.bad)
> >>>>      --- tests/generic/794.out   2026-06-12 08:46:32.766426241 +0800
> >>>>      +++ /share/git/fstests/results//generic/794.out.bad 2026-07-05 18:32:55.000000000 +0800
> >>>>      @@ -1,4 +1,16 @@
> >>>>       QA output created by 794
> >>>>       append_write
> >>>>      +FAIL: non-zero data in gap [4080,4096) after shutdown+remount
> >>>>      +000000 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a  >ZZZZZZZZZZZZZZZZ<
> >>>>      +*
> >>>>      +001000
> >>>>       truncate_up
> >>>>      ...
> >>>>      (Run 'diff -u /share/git/fstests/tests/generic/794.out /share/git/fstests/results//generic/794.out.bad'  to see the entire diff)
> >>>> Ran: generic/794
> >>>> Failures: generic/794
> >>>> Failed 1 of 1 tests
> >>>>
> >>>> Steps of generic/794:
> >>>> 1. write 4096 bytes to file w/ 0x5a
> >>>> 2. use fiemap to get PBA of first block in file
> >>>> 3. truncate file to 4080
> >>>> 4. umount; write 4096 bytes to file w/ 0x5a directly via PBA; mount
> >>>> 5. extend filesize via
> >>>>     a) append 4096 from offset 4096, or
> >>>>     b) truncate 8192, or
> >>>>     c) fallocate 4096 from offset 4096
> >>>> 6. verify the gap is zeroed in memory [4080,4096)
> >>>> 7. sync range 4096 from offset 4096; shutdown -f (flush meta before shutdown)
> >>>> 8. umount; mount; verify [4080,4096) is zeroed or not.
> >>>>
> >>>> When extending file size (e.g. via truncate, fallocate, or write) across an
> >>>> unaligned EOF boundary, we need to ensure that post-EOF data in the partial
> >>>> page is zeroed out in pagecache and marked dirty, meanwhile, tagging the inode
> >>>> with FI_ZERO_POST_EOF, so that following checkpoint() and fsync() can persist
> >>>> the page contain zeroed data before committing inode w/ updated i_size.
> >>>>
> >>>> This help to prevent stale disk data beyond the previous EOF from being exposed
> >>>> after remounting or crash recovery.
> >>>>
> >>>> Since f2fs is a LFS filesystem, we only support direct write via PBA in pinfile,
> >>>> and pinfile has section-aligned filesize, so in Android, there should no problem,
> >>>> but for other usage in different environment, let's fix this w/ fsync_mode=strict
> >>>> mount option.
> >>>>
> >>>> Cc: stable@kernel.org
> >>>> Signed-off-by: Chao Yu <chao@kernel.org>
> >>>> ---
> >>>>   fs/f2fs/checkpoint.c |  4 ++++
> >>>>   fs/f2fs/f2fs.h       |  1 +
> >>>>   fs/f2fs/file.c       | 35 ++++++++++++++++++++++++++++++++---
> >>>>   3 files changed, 37 insertions(+), 3 deletions(-)
> >>>>
> >>>> diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
> >>>> index 064f5b537423..6f486d3a94c7 100644
> >>>> --- a/fs/f2fs/checkpoint.c
> >>>> +++ b/fs/f2fs/checkpoint.c
> >>>> @@ -1359,6 +1359,10 @@ static int f2fs_sync_inode_meta(struct f2fs_sb_info *sbi)
> >>>>   		inode = igrab(&fi->vfs_inode);
> >>>>   		spin_unlock(&sbi->inode_lock[DIRTY_META]);
> >>>>   		if (inode) {
> >>>> +			if (is_inode_flag_set(inode, FI_ZERO_POST_EOF)) {
> >>>> +				filemap_write_and_wait(inode->i_mapping);
> >>>> +				clear_inode_flag(inode, FI_ZERO_POST_EOF);
> >>>> +			}
> >>>>   			sync_inode_metadata(inode, 0);
> >>>>   			/* it's on eviction */
> >>>> diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
> >>>> index 8e2fb0bda467..41be09dad43c 100644
> >>>> --- a/fs/f2fs/f2fs.h
> >>>> +++ b/fs/f2fs/f2fs.h
> >>>> @@ -939,6 +939,7 @@ enum {
> >>>>   	FI_ATOMIC_REPLACE,	/* indicate atomic replace */
> >>>>   	FI_OPENED_FILE,		/* indicate file has been opened */
> >>>>   	FI_DONATE_FINISHED,	/* indicate page donation of file has been finished */
> >>>> +	FI_ZERO_POST_EOF,	/* indicate unaligned EOF gap was zeroed in pagecache */
> >>>>   	FI_MAX,			/* max flag, never be used */
> >>>>   };
> >>>> diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
> >>>> index 11cc8d79c235..2e9d585073ec 100644
> >>>> --- a/fs/f2fs/file.c
> >>>> +++ b/fs/f2fs/file.c
> >>>> @@ -36,21 +36,43 @@
> >>>>   #include <trace/events/f2fs.h>
> >>>>   #include <uapi/linux/f2fs.h>
> >>>> +static int fill_zero(struct inode *inode, pgoff_t index,
> >>>> +					loff_t start, loff_t len);
> >>>> +
> >>>>   static void f2fs_zero_post_eof_page(struct inode *inode,
> >>>>   					loff_t new_size, bool lock)
> >>>>   {
> >>>>   	loff_t old_size = i_size_read(inode);
> >>>> +	unsigned int offset;
> >>>>   	if (old_size >= new_size)
> >>>>   		return;
> >>>> -	if (mapping_empty(inode->i_mapping))
> >>>> -		return;
> >>>> -
> >>>>   	if (lock)
> >>>>   		filemap_invalidate_lock(inode->i_mapping);
> >>>> +
> >>>>   	/* zero or drop pages only in range of [old_size, new_size] */
> >>>>   	truncate_inode_pages_range(inode->i_mapping, old_size, new_size);
> >>>> +
> >>>> +	/*
> >>>> +	 * When expanding an unaligned EOF size, zero post-EOF data in
> >>>> +	 * pagecache and set FI_ZERO_POST_EOF, so following checkpointing
> >>>> +	 * or fsync can persist correct data to disk before committing
> >>>> +	 * inode w/ updated i_size.
> >>>> +	 */
> >>>> +	if (F2FS_OPTION(F2FS_I_SB(inode)).fsync_mode != FSYNC_MODE_STRICT)
> >>>> +		goto out_unlock;
> >>>> +
> >>>> +	offset = old_size & (PAGE_SIZE - 1);
> >>>> +	if (offset) {
> >>>> +		unsigned int len = min_t(loff_t, PAGE_SIZE - offset,
> >>>> +							new_size - old_size);
> >>>> +		pgoff_t index = old_size >> PAGE_SHIFT;
> >>>> +
> >>>> +		fill_zero(inode, index, offset, len);
> >>>> +		set_inode_flag(inode, FI_ZERO_POST_EOF);
> >>>> +	}
> >>>> +out_unlock:
> >>>>   	if (lock)
> >>>>   		filemap_invalidate_unlock(inode->i_mapping);
> >>>>   }
> >>>> @@ -304,6 +326,13 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end,
> >>>>   	if (S_ISDIR(inode->i_mode))
> >>>>   		goto go_write;
> >>>> +	if (is_inode_flag_set(inode, FI_ZERO_POST_EOF)) {
> >>>> +		ret = filemap_write_and_wait(inode->i_mapping);
> >>>> +		if (ret)
> >>>> +			return ret;
> >>>> +		clear_inode_flag(inode, FI_ZERO_POST_EOF);
> >>>> +	}
> >>>> +
> >>>>   	/* if fdatasync is triggered, let's do in-place-update */
> >>>>   	if (datasync || get_dirty_pages(inode) <= SM_I(sbi)->min_fsync_blocks)
> >>>>   		set_inode_flag(inode, FI_NEED_IPU);
> >>>> -- 
> >>>> 2.49.0
> >>>>
> >>>>
> >>>>
> >>>> _______________________________________________
> >>>> Linux-f2fs-devel mailing list
> >>>> Linux-f2fs-devel@lists.sourceforge.net
> >>>> https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel
> >>
> >>
> >>
> >> _______________________________________________
> >> Linux-f2fs-devel mailing list
> >> Linux-f2fs-devel@lists.sourceforge.net
> >> https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel
> 
> 
> 
> _______________________________________________
> Linux-f2fs-devel mailing list
> Linux-f2fs-devel@lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel