From: Jeongjun Park <aha310510@gmail.com>
To: tytso@mit.edu, adilger.kernel@dilger.ca, aneesh.kumar@linux.vnet.ibm.com
Cc: shaggy@austin.ibm.com, akpm@osdl.org, alexandre.ratchov@bull.net,
linux-ext4@vger.kernel.org, linux-kernel@vger.kernel.org,
Jeongjun Park <aha310510@gmail.com>
Subject: [PATCH] ext4: prevent data-race that occur when read/write ext4_group_desc structure members
Date: Wed, 18 Sep 2024 18:21:41 +0900 [thread overview]
Message-ID: <20240918092141.213584-1-aha310510@gmail.com> (raw)
Currently, data-race like [1] occur in fs/ext4/super.c
Since the ext4_group_desc structure does not have a lock to protect its
member variables and there is a possibility that unexpected behavior may
occur in the future if a data-race occurs, I think it would be appropriate
to modify the ext4_group_desc member variables to be read/written atomically.
[1]
==================================================================
BUG: KCSAN: data-race in ext4_free_inodes_count / ext4_free_inodes_set
write to 0xffff88810404300e of 2 bytes by task 6254 on cpu 1:
ext4_free_inodes_set+0x1f/0x80 fs/ext4/super.c:405
__ext4_new_inode+0x15ca/0x2200 fs/ext4/ialloc.c:1216
ext4_symlink+0x242/0x5a0 fs/ext4/namei.c:3391
vfs_symlink+0xca/0x1d0 fs/namei.c:4615
do_symlinkat+0xe3/0x340 fs/namei.c:4641
__do_sys_symlinkat fs/namei.c:4657 [inline]
__se_sys_symlinkat fs/namei.c:4654 [inline]
__x64_sys_symlinkat+0x5e/0x70 fs/namei.c:4654
x64_sys_call+0x1dda/0x2d60 arch/x86/include/generated/asm/syscalls_64.h:267
do_syscall_x64 arch/x86/entry/common.c:52 [inline]
do_syscall_64+0x54/0x120 arch/x86/entry/common.c:83
entry_SYSCALL_64_after_hwframe+0x76/0x7e
read to 0xffff88810404300e of 2 bytes by task 6257 on cpu 0:
ext4_free_inodes_count+0x1c/0x80 fs/ext4/super.c:349
find_group_other fs/ext4/ialloc.c:594 [inline]
__ext4_new_inode+0x6ec/0x2200 fs/ext4/ialloc.c:1017
ext4_symlink+0x242/0x5a0 fs/ext4/namei.c:3391
vfs_symlink+0xca/0x1d0 fs/namei.c:4615
do_symlinkat+0xe3/0x340 fs/namei.c:4641
__do_sys_symlinkat fs/namei.c:4657 [inline]
__se_sys_symlinkat fs/namei.c:4654 [inline]
__x64_sys_symlinkat+0x5e/0x70 fs/namei.c:4654
x64_sys_call+0x1dda/0x2d60 arch/x86/include/generated/asm/syscalls_64.h:267
do_syscall_x64 arch/x86/entry/common.c:52 [inline]
do_syscall_64+0x54/0x120 arch/x86/entry/common.c:83
entry_SYSCALL_64_after_hwframe+0x76/0x7e
value changed: 0x185c -> 0x185b
Fixes: 560671a0d3c9 ("ext4: Use high 16 bits of the block group descriptor's free counts fields")
Fixes: 8fadc1432368 ("[PATCH] ext4: move block number hi bits")
Signed-off-by: Jeongjun Park <aha310510@gmail.com>
---
fs/ext4/super.c | 56 ++++++++++++++++++++++++-------------------------
1 file changed, 28 insertions(+), 28 deletions(-)
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index e72145c4ae5a..9c918cf2eb7e 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -314,113 +314,113 @@ void ext4_superblock_csum_set(struct super_block *sb)
ext4_fsblk_t ext4_block_bitmap(struct super_block *sb,
struct ext4_group_desc *bg)
{
- return le32_to_cpu(bg->bg_block_bitmap_lo) |
+ return le32_to_cpu(READ_ONCE(bg->bg_block_bitmap_lo)) |
(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
- (ext4_fsblk_t)le32_to_cpu(bg->bg_block_bitmap_hi) << 32 : 0);
+ (ext4_fsblk_t)le32_to_cpu(READ_ONCE(bg->bg_block_bitmap_hi)) << 32 : 0);
}
ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb,
struct ext4_group_desc *bg)
{
- return le32_to_cpu(bg->bg_inode_bitmap_lo) |
+ return le32_to_cpu(READ_ONCE(bg->bg_inode_bitmap_lo)) |
(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
- (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_bitmap_hi) << 32 : 0);
+ (ext4_fsblk_t)le32_to_cpu(READ_ONCE(bg->bg_inode_bitmap_hi)) << 32 : 0);
}
ext4_fsblk_t ext4_inode_table(struct super_block *sb,
struct ext4_group_desc *bg)
{
- return le32_to_cpu(bg->bg_inode_table_lo) |
+ return le32_to_cpu(READ_ONCE(bg->bg_inode_table_lo)) |
(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
- (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_table_hi) << 32 : 0);
+ (ext4_fsblk_t)le32_to_cpu(READ_ONCE(bg->bg_inode_table_hi)) << 32 : 0);
}
__u32 ext4_free_group_clusters(struct super_block *sb,
struct ext4_group_desc *bg)
{
- return le16_to_cpu(bg->bg_free_blocks_count_lo) |
+ return le16_to_cpu(READ_ONCE(bg->bg_free_blocks_count_lo)) |
(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
- (__u32)le16_to_cpu(bg->bg_free_blocks_count_hi) << 16 : 0);
+ (__u32)le16_to_cpu(READ_ONCE(bg->bg_free_blocks_count_hi)) << 16 : 0);
}
__u32 ext4_free_inodes_count(struct super_block *sb,
struct ext4_group_desc *bg)
{
- return le16_to_cpu(bg->bg_free_inodes_count_lo) |
+ return le16_to_cpu(READ_ONCE(bg->bg_free_inodes_count_lo)) |
(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
- (__u32)le16_to_cpu(bg->bg_free_inodes_count_hi) << 16 : 0);
+ (__u32)le16_to_cpu(READ_ONCE(bg->bg_free_inodes_count_hi)) << 16 : 0);
}
__u32 ext4_used_dirs_count(struct super_block *sb,
struct ext4_group_desc *bg)
{
- return le16_to_cpu(bg->bg_used_dirs_count_lo) |
+ return le16_to_cpu(READ_ONCE(bg->bg_used_dirs_count_lo)) |
(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
- (__u32)le16_to_cpu(bg->bg_used_dirs_count_hi) << 16 : 0);
+ (__u32)le16_to_cpu(READ_ONCE(bg->bg_used_dirs_count_hi)) << 16 : 0);
}
__u32 ext4_itable_unused_count(struct super_block *sb,
struct ext4_group_desc *bg)
{
- return le16_to_cpu(bg->bg_itable_unused_lo) |
+ return le16_to_cpu(READ_ONCE(bg->bg_itable_unused_lo)) |
(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
- (__u32)le16_to_cpu(bg->bg_itable_unused_hi) << 16 : 0);
+ (__u32)le16_to_cpu(READ_ONCE(bg->bg_itable_unused_hi)) << 16 : 0);
}
void ext4_block_bitmap_set(struct super_block *sb,
struct ext4_group_desc *bg, ext4_fsblk_t blk)
{
- bg->bg_block_bitmap_lo = cpu_to_le32((u32)blk);
+ WRITE_ONCE(bg->bg_block_bitmap_lo, cpu_to_le32((u32)blk));
if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
- bg->bg_block_bitmap_hi = cpu_to_le32(blk >> 32);
+ WRITE_ONCE(bg->bg_block_bitmap_hi, cpu_to_le32(blk >> 32));
}
void ext4_inode_bitmap_set(struct super_block *sb,
struct ext4_group_desc *bg, ext4_fsblk_t blk)
{
- bg->bg_inode_bitmap_lo = cpu_to_le32((u32)blk);
+ WRITE_ONCE(bg->bg_inode_bitmap_lo, cpu_to_le32((u32)blk));
if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
- bg->bg_inode_bitmap_hi = cpu_to_le32(blk >> 32);
+ WRITE_ONCE(bg->bg_inode_bitmap_hi, cpu_to_le32(blk >> 32));
}
void ext4_inode_table_set(struct super_block *sb,
struct ext4_group_desc *bg, ext4_fsblk_t blk)
{
- bg->bg_inode_table_lo = cpu_to_le32((u32)blk);
+ WRITE_ONCE(bg->bg_inode_table_lo, cpu_to_le32((u32)blk));
if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
- bg->bg_inode_table_hi = cpu_to_le32(blk >> 32);
+ WRITE_ONCE(bg->bg_inode_table_hi, cpu_to_le32(blk >> 32));
}
void ext4_free_group_clusters_set(struct super_block *sb,
struct ext4_group_desc *bg, __u32 count)
{
- bg->bg_free_blocks_count_lo = cpu_to_le16((__u16)count);
+ WRITE_ONCE(bg->bg_free_blocks_count_lo, cpu_to_le16((__u16)count));
if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
- bg->bg_free_blocks_count_hi = cpu_to_le16(count >> 16);
+ WRITE_ONCE(bg->bg_free_blocks_count_hi, cpu_to_le16(count >> 16));
}
void ext4_free_inodes_set(struct super_block *sb,
struct ext4_group_desc *bg, __u32 count)
{
- bg->bg_free_inodes_count_lo = cpu_to_le16((__u16)count);
+ WRITE_ONCE(bg->bg_free_inodes_count_lo, cpu_to_le16((__u16)count));
if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
- bg->bg_free_inodes_count_hi = cpu_to_le16(count >> 16);
+ WRITE_ONCE(bg->bg_free_inodes_count_hi, cpu_to_le16(count >> 16));
}
void ext4_used_dirs_set(struct super_block *sb,
struct ext4_group_desc *bg, __u32 count)
{
- bg->bg_used_dirs_count_lo = cpu_to_le16((__u16)count);
+ WRITE_ONCE(bg->bg_used_dirs_count_lo, cpu_to_le16((__u16)count));
if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
- bg->bg_used_dirs_count_hi = cpu_to_le16(count >> 16);
+ WRITE_ONCE(bg->bg_used_dirs_count_hi, cpu_to_le16(count >> 16));
}
void ext4_itable_unused_set(struct super_block *sb,
struct ext4_group_desc *bg, __u32 count)
{
- bg->bg_itable_unused_lo = cpu_to_le16((__u16)count);
+ WRITE_ONCE(bg->bg_itable_unused_lo, cpu_to_le16((__u16)count));
if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
- bg->bg_itable_unused_hi = cpu_to_le16(count >> 16);
+ WRITE_ONCE(bg->bg_itable_unused_hi, cpu_to_le16(count >> 16));
}
static void __ext4_update_tstamp(__le32 *lo, __u8 *hi, time64_t now)
--
next reply other threads:[~2024-09-18 9:21 UTC|newest]
Thread overview: 2+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-09-18 9:21 Jeongjun Park [this message]
2024-09-19 20:36 ` Andreas Dilger
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20240918092141.213584-1-aha310510@gmail.com \
--to=aha310510@gmail.com \
--cc=adilger.kernel@dilger.ca \
--cc=akpm@osdl.org \
--cc=alexandre.ratchov@bull.net \
--cc=aneesh.kumar@linux.vnet.ibm.com \
--cc=linux-ext4@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=shaggy@austin.ibm.com \
--cc=tytso@mit.edu \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®