linux-kernel - [PATCH] f2fs: atomic: fix to avoid racing w/ GC

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [day] [month] [year] [list]
Message-Id: <20240619070042.1197204-1-chao@kernel.org>
Date: Wed, 19 Jun 2024 15:00:42 +0800
From: Chao Yu <chao@...nel.org>
To: jaegeuk@...nel.org
Cc: linux-f2fs-devel@...ts.sourceforge.net,
	linux-kernel@...r.kernel.org,
	Chao Yu <chao@...nel.org>,
	Daeho Jeong <daehojeong@...gle.com>
Subject: [PATCH] f2fs: atomic: fix to avoid racing w/ GC

Case #1:
SQLite App		GC Thread		Kworker		Shrinker
- f2fs_ioc_start_atomic_write

- f2fs_ioc_commit_atomic_write
 - f2fs_commit_atomic_write
  - filemap_write_and_wait_range
  : write atomic_file's data to cow_inode
								echo 3 > drop_caches
								to drop atomic_file's
								cache.
			- f2fs_gc
			 - gc_data_segment
			  - move_data_page
			   - set_page_dirty

						- writepages
						 - f2fs_do_write_data_page
						 : overwrite atomic_file's data
						   to cow_inode
  - f2fs_down_write(&fi->i_gc_rwsem[WRITE])
  - __f2fs_commit_atomic_write
  - f2fs_up_write(&fi->i_gc_rwsem[WRITE])

Case #2:
SQLite App		GC Thread		Kworker
- f2fs_ioc_start_atomic_write

						- __writeback_single_inode
						 - do_writepages
						  - f2fs_write_cache_pages
						   - f2fs_write_single_data_page
						    - f2fs_do_write_data_page
						    : write atomic_file's data to cow_inode
			- f2fs_gc
			 - gc_data_segment
			  - move_data_page
			   - set_page_dirty

						- writepages
						 - f2fs_do_write_data_page
						 : overwrite atomic_file's data to cow_inode
- f2fs_ioc_commit_atomic_write

In above cases racing in between atomic_write and GC, previous
data in atomic_file may be overwrited to cow_file, result in
data corruption.

This patch introduces PAGE_PRIVATE_ATOMIC_WRITE bit flag in page.private,
and use it to indicate that there is last dirty data in atomic file,
and the data should be writebacked into cow_file, if the flag is not
tagged in page, we should never write data across files.

Fixes: 3db1de0e582c ("f2fs: change the current atomic write way")
Cc: Daeho Jeong <daehojeong@...gle.com>
Signed-off-by: Chao Yu <chao@...nel.org>
---
 fs/f2fs/data.c | 10 +++++++++-
 fs/f2fs/f2fs.h |  8 +++++++-
 2 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 0b4f563f2361..22031b9b507c 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -2647,10 +2647,13 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio)
 	struct dnode_of_data dn;
 	struct node_info ni;
 	bool ipu_force = false;
+	bool atomic_commit;
 	int err = 0;
 
 	/* Use COW inode to make dnode_of_data for atomic write */
-	if (f2fs_is_atomic_file(inode))
+	atomic_commit = f2fs_is_atomic_file(inode) &&
+				page_private_atomic(fio->page);
+	if (atomic_commit)
 		set_new_dnode(&dn, F2FS_I(inode)->cow_inode, NULL, NULL, 0);
 	else
 		set_new_dnode(&dn, inode, NULL, NULL, 0);
@@ -2749,6 +2752,8 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio)
 	f2fs_outplace_write_data(&dn, fio);
 	trace_f2fs_do_write_data_page(page_folio(page), OPU);
 	set_inode_flag(inode, FI_APPEND_WRITE);
+	if (atomic_commit)
+		clear_page_private_atomic(page);
 out_writepage:
 	f2fs_put_dnode(&dn);
 out:
@@ -3718,6 +3723,9 @@ static int f2fs_write_end(struct file *file,
 
 	set_page_dirty(page);
 
+	if (f2fs_is_atomic_file(inode))
+		set_page_private_atomic(page);
+
 	if (pos + copied > i_size_read(inode) &&
 	    !f2fs_verity_in_progress(inode)) {
 		f2fs_i_size_write(inode, pos + copied);
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 777497919c62..35dd2d45b0ed 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1413,7 +1413,8 @@ static inline void f2fs_clear_bit(unsigned int nr, char *addr);
  * bit 1	PAGE_PRIVATE_ONGOING_MIGRATION
  * bit 2	PAGE_PRIVATE_INLINE_INODE
  * bit 3	PAGE_PRIVATE_REF_RESOURCE
- * bit 4-	f2fs private data
+ * bit 4	PAGE_PRIVATE_ATOMIC_WRITE
+ * bit 5-	f2fs private data
  *
  * Layout B: lowest bit should be 0
  * page.private is a wrapped pointer.
@@ -1423,6 +1424,7 @@ enum {
 	PAGE_PRIVATE_ONGOING_MIGRATION,		/* data page which is on-going migrating */
 	PAGE_PRIVATE_INLINE_INODE,		/* inode page contains inline data */
 	PAGE_PRIVATE_REF_RESOURCE,		/* dirty page has referenced resources */
+	PAGE_PRIVATE_ATOMIC_WRITE,		/* data page from atomic write path */
 	PAGE_PRIVATE_MAX
 };
 
@@ -2401,14 +2403,17 @@ static inline void clear_page_private_##name(struct page *page) \
 PAGE_PRIVATE_GET_FUNC(nonpointer, NOT_POINTER);
 PAGE_PRIVATE_GET_FUNC(inline, INLINE_INODE);
 PAGE_PRIVATE_GET_FUNC(gcing, ONGOING_MIGRATION);
+PAGE_PRIVATE_GET_FUNC(atomic, ATOMIC_WRITE);
 
 PAGE_PRIVATE_SET_FUNC(reference, REF_RESOURCE);
 PAGE_PRIVATE_SET_FUNC(inline, INLINE_INODE);
 PAGE_PRIVATE_SET_FUNC(gcing, ONGOING_MIGRATION);
+PAGE_PRIVATE_SET_FUNC(atomic, ATOMIC_WRITE);
 
 PAGE_PRIVATE_CLEAR_FUNC(reference, REF_RESOURCE);
 PAGE_PRIVATE_CLEAR_FUNC(inline, INLINE_INODE);
 PAGE_PRIVATE_CLEAR_FUNC(gcing, ONGOING_MIGRATION);
+PAGE_PRIVATE_CLEAR_FUNC(atomic, ATOMIC_WRITE);
 
 static inline unsigned long get_page_private_data(struct page *page)
 {
@@ -2440,6 +2445,7 @@ static inline void clear_page_private_all(struct page *page)
 	clear_page_private_reference(page);
 	clear_page_private_gcing(page);
 	clear_page_private_inline(page);
+	clear_page_private_atomic(page);
 
 	f2fs_bug_on(F2FS_P_SB(page), page_private(page));
 }
-- 
2.40.1