9p: use inode->i_lock to protect i_size_write() under 32-bit
commit 5e3cc1ee1405a7eb3487ed24f786dec01b4cbe1f upstream.
Use inode->i_lock to protect i_size_write(), else i_size_read() in
generic_fillattr() may loop infinitely in read_seqcount_begin() when
multiple processes invoke v9fs_vfs_getattr() or v9fs_vfs_getattr_dotl()
simultaneously under 32-bit SMP environment, and a soft lockup will be
triggered as show below:
watchdog: BUG: soft lockup - CPU#5 stuck for 22s! [stat:2217]
Modules linked in:
CPU: 5 PID: 2217 Comm: stat Not tainted 5.0.0-rc1-00005-g7f702faf5a9e #4
Hardware name: Generic DT based system
PC is at generic_fillattr+0x104/0x108
LR is at 0xec497f00
pc : [<802b8898>] lr : [<ec497f00>] psr: 200c0013
sp : ec497e20 ip : ed608030 fp : ec497e3c
r10: 00000000 r9 : ec497f00 r8 : ed608030
r7 : ec497ebc r6 : ec497f00 r5 : ee5c1550 r4 : ee005780
r3 : 0000052d r2 : 00000000 r1 : ec497f00 r0 : ed608030
Flags: nzCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment none
Control: 10c5387d Table: ac48006a DAC: 00000051
CPU: 5 PID: 2217 Comm: stat Not tainted 5.0.0-rc1-00005-g7f702faf5a9e #4
Hardware name: Generic DT based system
Backtrace:
[<8010d974>] (dump_backtrace) from [<8010dc88>] (show_stack+0x20/0x24)
[<8010dc68>] (show_stack) from [<80a1d194>] (dump_stack+0xb0/0xdc)
[<80a1d0e4>] (dump_stack) from [<80109f34>] (show_regs+0x1c/0x20)
[<80109f18>] (show_regs) from [<801d0a80>] (watchdog_timer_fn+0x280/0x2f8)
[<801d0800>] (watchdog_timer_fn) from [<80198658>] (__hrtimer_run_queues+0x18c/0x380)
[<801984cc>] (__hrtimer_run_queues) from [<80198e60>] (hrtimer_run_queues+0xb8/0xf0)
[<80198da8>] (hrtimer_run_queues) from [<801973e8>] (run_local_timers+0x28/0x64)
[<801973c0>] (run_local_timers) from [<80197460>] (update_process_times+0x3c/0x6c)
[<80197424>] (update_process_times) from [<801ab2b8>] (tick_nohz_handler+0xe0/0x1bc)
[<801ab1d8>] (tick_nohz_handler) from [<80843050>] (arch_timer_handler_virt+0x38/0x48)
[<80843018>] (arch_timer_handler_virt) from [<80180a64>] (handle_percpu_devid_irq+0x8c/0x240)
[<801809d8>] (handle_percpu_devid_irq) from [<8017ac20>] (generic_handle_irq+0x34/0x44)
[<8017abec>] (generic_handle_irq) from [<8017b344>] (__handle_domain_irq+0x6c/0xc4)
[<8017b2d8>] (__handle_domain_irq) from [<801022e0>] (gic_handle_irq+0x4c/0x88)
[<80102294>] (gic_handle_irq) from [<80101a30>] (__irq_svc+0x70/0x98)
[<802b8794>] (generic_fillattr) from [<8056b284>] (v9fs_vfs_getattr_dotl+0x74/0xa4)
[<8056b210>] (v9fs_vfs_getattr_dotl) from [<802b8904>] (vfs_getattr_nosec+0x68/0x7c)
[<802b889c>] (vfs_getattr_nosec) from [<802b895c>] (vfs_getattr+0x44/0x48)
[<802b8918>] (vfs_getattr) from [<802b8a74>] (vfs_statx+0x9c/0xec)
[<802b89d8>] (vfs_statx) from [<802b9428>] (sys_lstat64+0x48/0x78)
[<802b93e0>] (sys_lstat64) from [<80101000>] (ret_fast_syscall+0x0/0x28)
[dominique.martinet@cea.fr: updated comment to not refer to a function
in another subsystem]
Link: http://lkml.kernel.org/r/20190124063514.8571-2-houtao1@huawei.com
Cc: stable@vger.kernel.org
Fixes: 7549ae3e81cc ("9p: Use the i_size_[read, write]() macros instead of using inode->i_size directly.")
Reported-by: Xing Gaopeng <xingaopeng@huawei.com>
Signed-off-by: Hou Tao <houtao1@huawei.com>
Signed-off-by: Dominique Martinet <dominique.martinet@cea.fr>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index f8ab4a6..ddd1eb6 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -538,7 +538,7 @@
if (retval)
goto error;
- v9fs_stat2inode(st, inode, sb);
+ v9fs_stat2inode(st, inode, sb, 0);
v9fs_cache_inode_get_cookie(inode);
unlock_new_inode(inode);
return inode;
@@ -1078,7 +1078,7 @@
if (IS_ERR(st))
return PTR_ERR(st);
- v9fs_stat2inode(st, d_inode(dentry), dentry->d_sb);
+ v9fs_stat2inode(st, d_inode(dentry), dentry->d_sb, 0);
generic_fillattr(d_inode(dentry), stat);
p9stat_free(st);
@@ -1156,12 +1156,13 @@
* @stat: Plan 9 metadata (mistat) structure
* @inode: inode to populate
* @sb: superblock of filesystem
+ * @flags: control flags (e.g. V9FS_STAT2INODE_KEEP_ISIZE)
*
*/
void
v9fs_stat2inode(struct p9_wstat *stat, struct inode *inode,
- struct super_block *sb)
+ struct super_block *sb, unsigned int flags)
{
umode_t mode;
char ext[32];
@@ -1202,10 +1203,11 @@
mode = p9mode2perm(v9ses, stat);
mode |= inode->i_mode & ~S_IALLUGO;
inode->i_mode = mode;
- i_size_write(inode, stat->length);
+ if (!(flags & V9FS_STAT2INODE_KEEP_ISIZE))
+ v9fs_i_size_write(inode, stat->length);
/* not real number of blocks, but 512 byte ones ... */
- inode->i_blocks = (i_size_read(inode) + 512 - 1) >> 9;
+ inode->i_blocks = (stat->length + 512 - 1) >> 9;
v9inode->cache_validity &= ~V9FS_INO_INVALID_ATTR;
}
@@ -1402,9 +1404,9 @@
{
int umode;
dev_t rdev;
- loff_t i_size;
struct p9_wstat *st;
struct v9fs_session_info *v9ses;
+ unsigned int flags;
v9ses = v9fs_inode2v9ses(inode);
st = p9_client_stat(fid);
@@ -1417,16 +1419,13 @@
if ((inode->i_mode & S_IFMT) != (umode & S_IFMT))
goto out;
- spin_lock(&inode->i_lock);
/*
* We don't want to refresh inode->i_size,
* because we may have cached data
*/
- i_size = inode->i_size;
- v9fs_stat2inode(st, inode, inode->i_sb);
- if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
- inode->i_size = i_size;
- spin_unlock(&inode->i_lock);
+ flags = (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) ?
+ V9FS_STAT2INODE_KEEP_ISIZE : 0;
+ v9fs_stat2inode(st, inode, inode->i_sb, flags);
out:
p9stat_free(st);
kfree(st);