Because ocfs2_get_dlm_debug() function is called once less here,
ocfs2 file system will trigger the system crash, usually after
ocfs2 file system is unmounted.
this system crash is caused by a generic memory corruption, these
crash backtraces are not always the same, for exapmle,
[ 4106.597432] ocfs2: Unmounting device (253,16) on (node 172167785)
[ 4116.230719] general protection fault: 0000 [#1] SMP PTI
[ 4116.230731] CPU: 3 PID: 14107 Comm: fence_legacy Kdump:
[ 4116.230737] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996)
[ 4116.230772] RIP: 0010:__kmalloc+0xa5/0x2a0
[ 4116.230778] Code: 00 00 4d 8b 07 65 4d 8b
[ 4116.230785] RSP: 0018:ffffaa1fc094bbe8 EFLAGS: 00010286
[ 4116.230790] RAX: 0000000000000000 RBX: d310a8800d7a3faf RCX: 0000000000000000
[ 4116.230794] RDX: 0000000000000000 RSI: 0000000000000dc0 RDI: ffff96e68fc036c0
[ 4116.230798] RBP: d310a8800d7a3faf R08: ffff96e6ffdb10a0 R09: 00000000752e7079
[ 4116.230802] R10: 000000000001c513 R11: 0000000004091041 R12: 0000000000000dc0
[ 4116.230806] R13: 0000000000000039 R14: ffff96e68fc036c0 R15: ffff96e68fc036c0
[ 4116.230811] FS: 00007f699dfba540(0000) GS:ffff96e6ffd80000(0000) knlGS:00000
[ 4116.230815] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 4116.230819] CR2: 000055f3a9d9b768 CR3: 000000002cd1c000 CR4: 00000000000006e0
[ 4116.230833] Call Trace:
[ 4116.230898] ? ext4_htree_store_dirent+0x35/0x100 [ext4]
[ 4116.230924] ext4_htree_store_dirent+0x35/0x100 [ext4]
[ 4116.230957] htree_dirblock_to_tree+0xea/0x290 [ext4]
[ 4116.230989] ext4_htree_fill_tree+0x1c1/0x2d0 [ext4]
[ 4116.231027] ext4_readdir+0x67c/0x9d0 [ext4]
[ 4116.231040] iterate_dir+0x8d/0x1a0
[ 4116.231056] __x64_sys_getdents+0xab/0x130
[ 4116.231063] ? iterate_dir+0x1a0/0x1a0
[ 4116.231076] ? do_syscall_64+0x60/0x1f0
[ 4116.231080] ? __ia32_sys_getdents+0x130/0x130
[ 4116.231086] do_syscall_64+0x60/0x1f0
[ 4116.231151] entry_SYSCALL_64_after_hwframe+0x49/0xbe
[ 4116.231168] RIP: 0033:0x7f699d33a9fb
This regression problem was introduced by commit e581595ea29c ("ocfs:
no need to check return value of debugfs_create functions").
Signed-off-by: Gang He <[email protected]>
---
fs/ocfs2/dlmglue.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 1c4c51f3df60..cda1027d0819 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -3282,6 +3282,7 @@ static void ocfs2_dlm_init_debug(struct ocfs2_super *osb)
debugfs_create_u32("locking_filter", 0600, osb->osb_debug_root,
&dlm_debug->d_filter_secs);
+ ocfs2_get_dlm_debug(dlm_debug);
}
static void ocfs2_dlm_shutdown_debug(struct ocfs2_super *osb)
--
2.12.3
On 19/12/25 14:15, Gang He wrote:
> Because ocfs2_get_dlm_debug() function is called once less here,
> ocfs2 file system will trigger the system crash, usually after
> ocfs2 file system is unmounted.
> this system crash is caused by a generic memory corruption, these
> crash backtraces are not always the same, for exapmle,
>
> [ 4106.597432] ocfs2: Unmounting device (253,16) on (node 172167785)
> [ 4116.230719] general protection fault: 0000 [#1] SMP PTI
> [ 4116.230731] CPU: 3 PID: 14107 Comm: fence_legacy Kdump:
> [ 4116.230737] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996)
> [ 4116.230772] RIP: 0010:__kmalloc+0xa5/0x2a0
> [ 4116.230778] Code: 00 00 4d 8b 07 65 4d 8b
> [ 4116.230785] RSP: 0018:ffffaa1fc094bbe8 EFLAGS: 00010286
> [ 4116.230790] RAX: 0000000000000000 RBX: d310a8800d7a3faf RCX: 0000000000000000
> [ 4116.230794] RDX: 0000000000000000 RSI: 0000000000000dc0 RDI: ffff96e68fc036c0
> [ 4116.230798] RBP: d310a8800d7a3faf R08: ffff96e6ffdb10a0 R09: 00000000752e7079
> [ 4116.230802] R10: 000000000001c513 R11: 0000000004091041 R12: 0000000000000dc0
> [ 4116.230806] R13: 0000000000000039 R14: ffff96e68fc036c0 R15: ffff96e68fc036c0
> [ 4116.230811] FS: 00007f699dfba540(0000) GS:ffff96e6ffd80000(0000) knlGS:00000
> [ 4116.230815] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> [ 4116.230819] CR2: 000055f3a9d9b768 CR3: 000000002cd1c000 CR4: 00000000000006e0
> [ 4116.230833] Call Trace:
> [ 4116.230898] ? ext4_htree_store_dirent+0x35/0x100 [ext4]
> [ 4116.230924] ext4_htree_store_dirent+0x35/0x100 [ext4]
> [ 4116.230957] htree_dirblock_to_tree+0xea/0x290 [ext4]
> [ 4116.230989] ext4_htree_fill_tree+0x1c1/0x2d0 [ext4]
> [ 4116.231027] ext4_readdir+0x67c/0x9d0 [ext4]
> [ 4116.231040] iterate_dir+0x8d/0x1a0
> [ 4116.231056] __x64_sys_getdents+0xab/0x130
> [ 4116.231063] ? iterate_dir+0x1a0/0x1a0
> [ 4116.231076] ? do_syscall_64+0x60/0x1f0
> [ 4116.231080] ? __ia32_sys_getdents+0x130/0x130
> [ 4116.231086] do_syscall_64+0x60/0x1f0
> [ 4116.231151] entry_SYSCALL_64_after_hwframe+0x49/0xbe
> [ 4116.231168] RIP: 0033:0x7f699d33a9fb
>
> This regression problem was introduced by commit e581595ea29c ("ocfs:
> no need to check return value of debugfs_create functions").
>
> Signed-off-by: Gang He <[email protected]>
Thanks, Gang.
Acked-by: Joseph Qi <[email protected]>
Add missing tags as well.
Fixes: e581595ea29c ("ocfs: no need to check return value of debugfs_create functions")
Cc: <[email protected]> v5.3+
> ---
> fs/ocfs2/dlmglue.c | 1 +
> 1 file changed, 1 insertion(+)
>
> diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
> index 1c4c51f3df60..cda1027d0819 100644
> --- a/fs/ocfs2/dlmglue.c
> +++ b/fs/ocfs2/dlmglue.c
> @@ -3282,6 +3282,7 @@ static void ocfs2_dlm_init_debug(struct ocfs2_super *osb)
>
> debugfs_create_u32("locking_filter", 0600, osb->osb_debug_root,
> &dlm_debug->d_filter_secs);
> + ocfs2_get_dlm_debug(dlm_debug);
> }
>
> static void ocfs2_dlm_shutdown_debug(struct ocfs2_super *osb)
>