During stress testing with CONFIG_SMP disabled, KASAN reports as below:
==================================================================
BUG: KASAN: use-after-free in __mutex_lock+0xe5/0xc30
Read of size 8 at addr ffff8881094223f8 by task stress/7789
[ 3482.258885]
CPU: 0 PID: 7789 Comm: stress Not tainted 6.0.0-rc1-00002-g0d53d2e882f9 #3
Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011
Call Trace:
<TASK>
..
__mutex_lock+0xe5/0xc30
..
z_erofs_do_read_page+0x8ce/0x1560
..
z_erofs_readahead+0x31c/0x580
..
Freed by task 7787
kasan_save_stack+0x1e/0x40
kasan_set_track+0x20/0x30
kasan_set_free_info+0x20/0x40
__kasan_slab_free+0x10c/0x190
kmem_cache_free+0xed/0x380
rcu_core+0x3d5/0xc90
__do_softirq+0x12d/0x389
[ 3482.295630]
Last potentially related work creation:
kasan_save_stack+0x1e/0x40
__kasan_record_aux_stack+0x97/0xb0
call_rcu+0x3d/0x3f0
erofs_shrink_workstation+0x11f/0x210
erofs_shrink_scan+0xdc/0x170
shrink_slab.constprop.0+0x296/0x530
drop_slab+0x1c/0x70
drop_caches_sysctl_handler+0x70/0x80
proc_sys_call_handler+0x20a/0x2f0
vfs_write+0x555/0x6c0
ksys_write+0xbe/0x160
do_syscall_64+0x3b/0x90
The root cause is that erofs_workgroup_unfreeze() doesn't reset
to orig_val thus it causes a race that the pcluster reuses unexpectedly
before freeing.
Since UP platforms are quite rare now, such path becomes unnecessary.
Let's drop such specific-designed path directly instead.
Fixes: 73f5c66df3e2 ("staging: erofs: fix `erofs_workgroup_{try_to_freeze, unfreeze}'")
Signed-off-by: Gao Xiang <[email protected]>
---
fs/erofs/internal.h | 29 -----------------------------
1 file changed, 29 deletions(-)
diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
index cfee49d33b95..a01cc82795a2 100644
--- a/fs/erofs/internal.h
+++ b/fs/erofs/internal.h
@@ -195,7 +195,6 @@ struct erofs_workgroup {
atomic_t refcount;
};
-#if defined(CONFIG_SMP)
static inline bool erofs_workgroup_try_to_freeze(struct erofs_workgroup *grp,
int val)
{
@@ -224,34 +223,6 @@ static inline int erofs_wait_on_workgroup_freezed(struct erofs_workgroup *grp)
return atomic_cond_read_relaxed(&grp->refcount,
VAL != EROFS_LOCKED_MAGIC);
}
-#else
-static inline bool erofs_workgroup_try_to_freeze(struct erofs_workgroup *grp,
- int val)
-{
- preempt_disable();
- /* no need to spin on UP platforms, let's just disable preemption. */
- if (val != atomic_read(&grp->refcount)) {
- preempt_enable();
- return false;
- }
- return true;
-}
-
-static inline void erofs_workgroup_unfreeze(struct erofs_workgroup *grp,
- int orig_val)
-{
- preempt_enable();
-}
-
-static inline int erofs_wait_on_workgroup_freezed(struct erofs_workgroup *grp)
-{
- int v = atomic_read(&grp->refcount);
-
- /* workgroup is never freezed on uniprocessor systems */
- DBG_BUGON(v == EROFS_LOCKED_MAGIC);
- return v;
-}
-#endif /* !CONFIG_SMP */
#endif /* !CONFIG_EROFS_FS_ZIP */
/* we strictly follow PAGE_SIZE and no buffer head yet */
--
2.24.4
On Fri, 2 Sep 2022 12:57:10 +0800
Gao Xiang <[email protected]> wrote:
> During stress testing with CONFIG_SMP disabled, KASAN reports as below:
>
> ==================================================================
> BUG: KASAN: use-after-free in __mutex_lock+0xe5/0xc30
> Read of size 8 at addr ffff8881094223f8 by task stress/7789
> [ 3482.258885]
> CPU: 0 PID: 7789 Comm: stress Not tainted 6.0.0-rc1-00002-g0d53d2e882f9 #3
> Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011
> Call Trace:
> <TASK>
> ..
> __mutex_lock+0xe5/0xc30
> ..
> z_erofs_do_read_page+0x8ce/0x1560
> ..
> z_erofs_readahead+0x31c/0x580
> ..
> Freed by task 7787
> kasan_save_stack+0x1e/0x40
> kasan_set_track+0x20/0x30
> kasan_set_free_info+0x20/0x40
> __kasan_slab_free+0x10c/0x190
> kmem_cache_free+0xed/0x380
> rcu_core+0x3d5/0xc90
> __do_softirq+0x12d/0x389
> [ 3482.295630]
> Last potentially related work creation:
> kasan_save_stack+0x1e/0x40
> __kasan_record_aux_stack+0x97/0xb0
> call_rcu+0x3d/0x3f0
> erofs_shrink_workstation+0x11f/0x210
> erofs_shrink_scan+0xdc/0x170
> shrink_slab.constprop.0+0x296/0x530
> drop_slab+0x1c/0x70
> drop_caches_sysctl_handler+0x70/0x80
> proc_sys_call_handler+0x20a/0x2f0
> vfs_write+0x555/0x6c0
> ksys_write+0xbe/0x160
> do_syscall_64+0x3b/0x90
>
> The root cause is that erofs_workgroup_unfreeze() doesn't reset
> to orig_val thus it causes a race that the pcluster reuses unexpectedly
> before freeing.
>
> Since UP platforms are quite rare now, such path becomes unnecessary.
> Let's drop such specific-designed path directly instead.
>
> Fixes: 73f5c66df3e2 ("staging: erofs: fix `erofs_workgroup_{try_to_freeze, unfreeze}'")
> Signed-off-by: Gao Xiang <[email protected]>
> ---
> fs/erofs/internal.h | 29 -----------------------------
> 1 file changed, 29 deletions(-)
>
> diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
> index cfee49d33b95..a01cc82795a2 100644
> --- a/fs/erofs/internal.h
> +++ b/fs/erofs/internal.h
> @@ -195,7 +195,6 @@ struct erofs_workgroup {
> atomic_t refcount;
> };
>
> -#if defined(CONFIG_SMP)
> static inline bool erofs_workgroup_try_to_freeze(struct erofs_workgroup *grp,
> int val)
> {
> @@ -224,34 +223,6 @@ static inline int erofs_wait_on_workgroup_freezed(struct erofs_workgroup *grp)
> return atomic_cond_read_relaxed(&grp->refcount,
> VAL != EROFS_LOCKED_MAGIC);
> }
> -#else
> -static inline bool erofs_workgroup_try_to_freeze(struct erofs_workgroup *grp,
> - int val)
> -{
> - preempt_disable();
> - /* no need to spin on UP platforms, let's just disable preemption. */
> - if (val != atomic_read(&grp->refcount)) {
> - preempt_enable();
> - return false;
> - }
> - return true;
> -}
> -
> -static inline void erofs_workgroup_unfreeze(struct erofs_workgroup *grp,
> - int orig_val)
> -{
> - preempt_enable();
> -}
> -
> -static inline int erofs_wait_on_workgroup_freezed(struct erofs_workgroup *grp)
> -{
> - int v = atomic_read(&grp->refcount);
> -
> - /* workgroup is never freezed on uniprocessor systems */
> - DBG_BUGON(v == EROFS_LOCKED_MAGIC);
> - return v;
> -}
> -#endif /* !CONFIG_SMP */
> #endif /* !CONFIG_EROFS_FS_ZIP */
>
Reviewed-by: Yue Hu <[email protected]>
> /* we strictly follow PAGE_SIZE and no buffer head yet */
On 2022/9/2 12:57, Gao Xiang wrote:
> During stress testing with CONFIG_SMP disabled, KASAN reports as below:
>
> ==================================================================
> BUG: KASAN: use-after-free in __mutex_lock+0xe5/0xc30
> Read of size 8 at addr ffff8881094223f8 by task stress/7789
> [ 3482.258885]
> CPU: 0 PID: 7789 Comm: stress Not tainted 6.0.0-rc1-00002-g0d53d2e882f9 #3
> Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011
> Call Trace:
> <TASK>
> ..
> __mutex_lock+0xe5/0xc30
> ..
> z_erofs_do_read_page+0x8ce/0x1560
> ..
> z_erofs_readahead+0x31c/0x580
> ..
> Freed by task 7787
> kasan_save_stack+0x1e/0x40
> kasan_set_track+0x20/0x30
> kasan_set_free_info+0x20/0x40
> __kasan_slab_free+0x10c/0x190
> kmem_cache_free+0xed/0x380
> rcu_core+0x3d5/0xc90
> __do_softirq+0x12d/0x389
> [ 3482.295630]
> Last potentially related work creation:
> kasan_save_stack+0x1e/0x40
> __kasan_record_aux_stack+0x97/0xb0
> call_rcu+0x3d/0x3f0
> erofs_shrink_workstation+0x11f/0x210
> erofs_shrink_scan+0xdc/0x170
> shrink_slab.constprop.0+0x296/0x530
> drop_slab+0x1c/0x70
> drop_caches_sysctl_handler+0x70/0x80
> proc_sys_call_handler+0x20a/0x2f0
> vfs_write+0x555/0x6c0
> ksys_write+0xbe/0x160
> do_syscall_64+0x3b/0x90
>
> The root cause is that erofs_workgroup_unfreeze() doesn't reset
> to orig_val thus it causes a race that the pcluster reuses unexpectedly
> before freeing.
>
> Since UP platforms are quite rare now, such path becomes unnecessary.
> Let's drop such specific-designed path directly instead.
>
> Fixes: 73f5c66df3e2 ("staging: erofs: fix `erofs_workgroup_{try_to_freeze, unfreeze}'")
> Signed-off-by: Gao Xiang <[email protected]>
Reviewed-by: Chao Yu <[email protected]>
Thanks,