Abhishek reported a data-race issue,
BUG: KCSAN: data-race in __ksm_enter / run_store
write to 0xffffffff881edae0 of 8 bytes by task 6542 on cpu 0:
run_store+0x19a/0x2d0 mm/ksm.c:2897
kobj_attr_store+0x44/0x60 lib/kobject.c:824
sysfs_kf_write+0x16f/0x1a0 fs/sysfs/file.c:136
kernfs_fop_write_iter+0x2ae/0x370 fs/kernfs/file.c:291
call_write_iter include/linux/fs.h:2050 [inline]
new_sync_write fs/read_write.c:504 [inline]
vfs_write+0x779/0x900 fs/read_write.c:591
ksys_write+0xde/0x190 fs/read_write.c:644
__do_sys_write fs/read_write.c:656 [inline]
__se_sys_write fs/read_write.c:653 [inline]
__x64_sys_write+0x43/0x50 fs/read_write.c:653
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x3d/0x90 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x44/0xae
read to 0xffffffff881edae0 of 8 bytes by task 6541 on cpu 1:
__ksm_enter+0x114/0x260 mm/ksm.c:2501
ksm_madvise+0x291/0x350 mm/ksm.c:2451
madvise_vma_behavior mm/madvise.c:1039 [inline]
madvise_walk_vmas mm/madvise.c:1221 [inline]
do_madvise+0x656/0xeb0 mm/madvise.c:1399
__do_sys_madvise mm/madvise.c:1412 [inline]
__se_sys_madvise mm/madvise.c:1410 [inline]
__x64_sys_madvise+0x64/0x70 mm/madvise.c:1410
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x3d/0x90 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x44/0xae
Reported by Kernel Concurrency Sanitizer on:
CPU: 1 PID: 6541 Comm: syz-executor2-n Not tainted 5.18.0-rc5+ #107
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014
The ksm_run is alread protected by ksm_thread_mutex in run_store, we
could add this lock in __ksm_enter() to avoid the above issue.
Reported-and-tested-by: Abhishek Shah <[email protected]>
Cc: Gabriel Ryan <[email protected]>
Signed-off-by: Kefeng Wang <[email protected]>
---
mm/ksm.c | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/mm/ksm.c b/mm/ksm.c
index 2f315c69fa2c..3f1908946a6f 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -2507,6 +2507,7 @@ int __ksm_enter(struct mm_struct *mm)
{
struct mm_slot *mm_slot;
int needs_wakeup;
+ bool ksm_run_unmerge;
mm_slot = alloc_mm_slot();
if (!mm_slot)
@@ -2515,6 +2516,10 @@ int __ksm_enter(struct mm_struct *mm)
/* Check ksm_run too? Would need tighter locking */
needs_wakeup = list_empty(&ksm_mm_head.mm_list);
+ mutex_lock(&ksm_thread_mutex);
+ ksm_run_unmerge = !!(ksm_run & KSM_RUN_UNMERGE);
+ mutex_unlock(&ksm_thread_mutex);
+
spin_lock(&ksm_mmlist_lock);
insert_to_mm_slots_hash(mm, mm_slot);
/*
@@ -2527,7 +2532,7 @@ int __ksm_enter(struct mm_struct *mm)
* scanning cursor, otherwise KSM pages in newly forked mms will be
* missed: then we might as well insert at the end of the list.
*/
- if (ksm_run & KSM_RUN_UNMERGE)
+ if (ksm_run_unmerge)
list_add_tail(&mm_slot->mm_list, &ksm_mm_head.mm_list);
else
list_add_tail(&mm_slot->mm_list, &ksm_scan.mm_slot->mm_list);
--
2.35.3
On Tue, Aug 02, 2022 at 11:15:50PM +0800, Kefeng Wang wrote:
> The ksm_run is alread protected by ksm_thread_mutex in run_store, we
> could add this lock in __ksm_enter() to avoid the above issue.
I don't think this is a great fix. Why not protect the store with
ksm_mmlist_lock? ie:
mutex_lock(&ksm_thread_mutex);
wait_while_offlining();
if (ksm_run != flags) {
+ spin_lock(&ksm_mmlist_lock);
ksm_run = flags;
+ spin_unlock(&ksm_mmlist_lock);
if (flags & KSM_RUN_UNMERGE) {
set_current_oom_origin();
err = unmerge_and_remove_all_rmap_items();
clear_current_oom_origin();
if (err) {
+ spin_lock(&ksm_mmlist_lock);
ksm_run = KSM_RUN_STOP;
+ spin_unlock(&ksm_mmlist_lock);
...
(I also don't think this is a real bug, because the call to
unmerge_and_remove_all_rmap_items() will "cure" the misplacement of
items in the list, but there's value in shutting up the tools, I suppose)
On Tue, 2 Aug 2022 23:15:50 +0800 Kefeng Wang <[email protected]> wrote:
> Abhishek reported a data-race issue,
OK, but it would be better to perform an analysis of the alleged bug,
describe the potential effects if the race is hit, etc.
> --- a/mm/ksm.c
> +++ b/mm/ksm.c
> @@ -2507,6 +2507,7 @@ int __ksm_enter(struct mm_struct *mm)
> {
> struct mm_slot *mm_slot;
> int needs_wakeup;
> + bool ksm_run_unmerge;
>
> mm_slot = alloc_mm_slot();
> if (!mm_slot)
> @@ -2515,6 +2516,10 @@ int __ksm_enter(struct mm_struct *mm)
> /* Check ksm_run too? Would need tighter locking */
> needs_wakeup = list_empty(&ksm_mm_head.mm_list);
>
> + mutex_lock(&ksm_thread_mutex);
> + ksm_run_unmerge = !!(ksm_run & KSM_RUN_UNMERGE);
> + mutex_unlock(&ksm_thread_mutex);
>
> spin_lock(&ksm_mmlist_lock);
> insert_to_mm_slots_hash(mm, mm_slot);
> /*
> @@ -2527,7 +2532,7 @@ int __ksm_enter(struct mm_struct *mm)
> * scanning cursor, otherwise KSM pages in newly forked mms will be
> * missed: then we might as well insert at the end of the list.
> */
> - if (ksm_run & KSM_RUN_UNMERGE)
> + if (ksm_run_unmerge)
run_store() can alter ksm_run right here, so __ksm_enter() is still
acting on the old setting?
> list_add_tail(&mm_slot->mm_list, &ksm_mm_head.mm_list);
> else
> list_add_tail(&mm_slot->mm_list, &ksm_scan.mm_slot->mm_list);