It does not reset PG_slab and memcg_data when KFENCE fails to initialize
kfence pool at runtime. It is reporting a "Bad page state" message when
kfence pool is freed to buddy. The checking of whether it is a compound
head page seems unnecessary sicne we already guarantee this when allocating
kfence pool, removing the check to simplify the code.
Fixes: 0ce20dd84089 ("mm: add Kernel Electric-Fence infrastructure")
Fixes: 8f0b36497303 ("mm: kfence: fix objcgs vector allocation")
Signed-off-by: Muchun Song <[email protected]>
---
mm/kfence/core.c | 30 +++++++++++++++---------------
1 file changed, 15 insertions(+), 15 deletions(-)
diff --git a/mm/kfence/core.c b/mm/kfence/core.c
index 79c94ee55f97..d66092dd187c 100644
--- a/mm/kfence/core.c
+++ b/mm/kfence/core.c
@@ -561,10 +561,6 @@ static unsigned long kfence_init_pool(void)
if (!i || (i % 2))
continue;
- /* Verify we do not have a compound head page. */
- if (WARN_ON(compound_head(&pages[i]) != &pages[i]))
- return addr;
-
__folio_set_slab(slab_folio(slab));
#ifdef CONFIG_MEMCG
slab->memcg_data = (unsigned long)&kfence_metadata[i / 2 - 1].objcg |
@@ -597,12 +593,26 @@ static unsigned long kfence_init_pool(void)
/* Protect the right redzone. */
if (unlikely(!kfence_protect(addr + PAGE_SIZE)))
- return addr;
+ goto reset_slab;
addr += 2 * PAGE_SIZE;
}
return 0;
+
+reset_slab:
+ for (i = 0; i < KFENCE_POOL_SIZE / PAGE_SIZE; i++) {
+ struct slab *slab = page_slab(&pages[i]);
+
+ if (!i || (i % 2))
+ continue;
+#ifdef CONFIG_MEMCG
+ slab->memcg_data = 0;
+#endif
+ __folio_clear_slab(slab_folio(slab));
+ }
+
+ return addr;
}
static bool __init kfence_init_pool_early(void)
@@ -632,16 +642,6 @@ static bool __init kfence_init_pool_early(void)
* fails for the first page, and therefore expect addr==__kfence_pool in
* most failure cases.
*/
- for (char *p = (char *)addr; p < __kfence_pool + KFENCE_POOL_SIZE; p += PAGE_SIZE) {
- struct slab *slab = virt_to_slab(p);
-
- if (!slab)
- continue;
-#ifdef CONFIG_MEMCG
- slab->memcg_data = 0;
-#endif
- __folio_clear_slab(slab_folio(slab));
- }
memblock_free_late(__pa(addr), KFENCE_POOL_SIZE - (addr - (unsigned long)__kfence_pool));
__kfence_pool = NULL;
return false;
--
2.11.0
On Mon, 20 Mar 2023 11:00:59 +0800 Muchun Song <[email protected]> wrote:
> It does not reset PG_slab and memcg_data when KFENCE fails to initialize
> kfence pool at runtime. It is reporting a "Bad page state" message when
> kfence pool is freed to buddy. The checking of whether it is a compound
> head page seems unnecessary sicne we already guarantee this when allocating
> kfence pool, removing the check to simplify the code.
>
> Fixes: 0ce20dd84089 ("mm: add Kernel Electric-Fence infrastructure")
> Fixes: 8f0b36497303 ("mm: kfence: fix objcgs vector allocation")
> Signed-off-by: Muchun Song <[email protected]>
I'm not sure how the -stable maintainers are to handle two Fixes: tags.
Can we narrow it down to one please? I assume 8f0b36497303 triggered
the bad_page() warning?
> On Mar 21, 2023, at 05:29, Andrew Morton <[email protected]> wrote:
>
> On Mon, 20 Mar 2023 11:00:59 +0800 Muchun Song <[email protected]> wrote:
>
>> It does not reset PG_slab and memcg_data when KFENCE fails to initialize
>> kfence pool at runtime. It is reporting a "Bad page state" message when
>> kfence pool is freed to buddy. The checking of whether it is a compound
>> head page seems unnecessary sicne we already guarantee this when allocating
>> kfence pool, removing the check to simplify the code.
>>
>> Fixes: 0ce20dd84089 ("mm: add Kernel Electric-Fence infrastructure")
>> Fixes: 8f0b36497303 ("mm: kfence: fix objcgs vector allocation")
>> Signed-off-by: Muchun Song <[email protected]>
>
> I'm not sure how the -stable maintainers are to handle two Fixes: tags.
> Can we narrow it down to one please? I assume 8f0b36497303 triggered
> the bad_page() warning?
>
Actually, 0ce20dd84089 triggered the PG_slab warning and 8f0b36497303
triggered the "page still charged to cgroup" warning. This patch fixes
both warnings. Moreover, 8f0b36497303 fixes 0ce20dd84089 as well. So I think
we can narrow it down to 0ce20dd84089.
Thanks.
在 2023/3/20 11:00, Muchun Song 写道:
> It does not reset PG_slab and memcg_data when KFENCE fails to initialize
> kfence pool at runtime. It is reporting a "Bad page state" message when
> kfence pool is freed to buddy. The checking of whether it is a compound
> head page seems unnecessary sicne we already guarantee this when allocating
> kfence pool, removing the check to simplify the code.
>
> Fixes: 0ce20dd84089 ("mm: add Kernel Electric-Fence infrastructure")
> Fixes: 8f0b36497303 ("mm: kfence: fix objcgs vector allocation")
> Signed-off-by: Muchun Song <[email protected]>
> ---
> mm/kfence/core.c | 30 +++++++++++++++---------------
> 1 file changed, 15 insertions(+), 15 deletions(-)
>
> diff --git a/mm/kfence/core.c b/mm/kfence/core.c
> index 79c94ee55f97..d66092dd187c 100644
> --- a/mm/kfence/core.c
> +++ b/mm/kfence/core.c
> @@ -561,10 +561,6 @@ static unsigned long kfence_init_pool(void)
> if (!i || (i % 2))
> continue;
>
> - /* Verify we do not have a compound head page. */
> - if (WARN_ON(compound_head(&pages[i]) != &pages[i]))
> - return addr;
> -
> __folio_set_slab(slab_folio(slab));
> #ifdef CONFIG_MEMCG
> slab->memcg_data = (unsigned long)&kfence_metadata[i / 2 - 1].objcg |
> @@ -597,12 +593,26 @@ static unsigned long kfence_init_pool(void)
>
> /* Protect the right redzone. */
> if (unlikely(!kfence_protect(addr + PAGE_SIZE)))
> - return addr;
> + goto reset_slab;
>
> addr += 2 * PAGE_SIZE;
> }
>
> return 0;
> +
> +reset_slab:
> + for (i = 0; i < KFENCE_POOL_SIZE / PAGE_SIZE; i++) {
> + struct slab *slab = page_slab(&pages[i]);
> +
> + if (!i || (i % 2))
> + continue;
> +#ifdef CONFIG_MEMCG
> + slab->memcg_data = 0;
> +#endif
> + __folio_clear_slab(slab_folio(slab));
> + }
Can this loop be simplified to this?
for (i = 2; i < KFENCE_POOL_SIZE / PAGE_SIZE; i+=2) {
struct slab *slab = page_slab(&pages[i]);
#ifdef CONFIG_MEMCG
slab->memcg_data = 0;
#endif
__folio_clear_slab(slab_folio(slab));
}
> +
> + return addr;
> }
>
> static bool __init kfence_init_pool_early(void)
> @@ -632,16 +642,6 @@ static bool __init kfence_init_pool_early(void)
> * fails for the first page, and therefore expect addr==__kfence_pool in
> * most failure cases.
> */
> - for (char *p = (char *)addr; p < __kfence_pool + KFENCE_POOL_SIZE; p += PAGE_SIZE) {
> - struct slab *slab = virt_to_slab(p);
> -
> - if (!slab)
> - continue;
> -#ifdef CONFIG_MEMCG
> - slab->memcg_data = 0;
> -#endif
> - __folio_clear_slab(slab_folio(slab));
> - }
> memblock_free_late(__pa(addr), KFENCE_POOL_SIZE - (addr - (unsigned long)__kfence_pool));
> __kfence_pool = NULL;
> return false;
On 2023/3/21 12:14, Peng Zhang wrote:
>
> 在 2023/3/20 11:00, Muchun Song 写道:
>> It does not reset PG_slab and memcg_data when KFENCE fails to initialize
>> kfence pool at runtime. It is reporting a "Bad page state" message when
>> kfence pool is freed to buddy. The checking of whether it is a compound
>> head page seems unnecessary sicne we already guarantee this when
>> allocating
>> kfence pool, removing the check to simplify the code.
>>
>> Fixes: 0ce20dd84089 ("mm: add Kernel Electric-Fence infrastructure")
>> Fixes: 8f0b36497303 ("mm: kfence: fix objcgs vector allocation")
>> Signed-off-by: Muchun Song <[email protected]>
>> ---
>> mm/kfence/core.c | 30 +++++++++++++++---------------
>> 1 file changed, 15 insertions(+), 15 deletions(-)
>>
>> diff --git a/mm/kfence/core.c b/mm/kfence/core.c
>> index 79c94ee55f97..d66092dd187c 100644
>> --- a/mm/kfence/core.c
>> +++ b/mm/kfence/core.c
>> @@ -561,10 +561,6 @@ static unsigned long kfence_init_pool(void)
>> if (!i || (i % 2))
>> continue;
>> - /* Verify we do not have a compound head page. */
>> - if (WARN_ON(compound_head(&pages[i]) != &pages[i]))
>> - return addr;
>> -
>> __folio_set_slab(slab_folio(slab));
>> #ifdef CONFIG_MEMCG
>> slab->memcg_data = (unsigned long)&kfence_metadata[i / 2 -
>> 1].objcg |
>> @@ -597,12 +593,26 @@ static unsigned long kfence_init_pool(void)
>> /* Protect the right redzone. */
>> if (unlikely(!kfence_protect(addr + PAGE_SIZE)))
>> - return addr;
>> + goto reset_slab;
>> addr += 2 * PAGE_SIZE;
>> }
>> return 0;
>> +
>> +reset_slab:
>> + for (i = 0; i < KFENCE_POOL_SIZE / PAGE_SIZE; i++) {
>> + struct slab *slab = page_slab(&pages[i]);
>> +
>> + if (!i || (i % 2))
>> + continue;
>> +#ifdef CONFIG_MEMCG
>> + slab->memcg_data = 0;
>> +#endif
>> + __folio_clear_slab(slab_folio(slab));
>> + }
> Can this loop be simplified to this?
>
> for (i = 2; i < KFENCE_POOL_SIZE / PAGE_SIZE; i+=2) {
> struct slab *slab = page_slab(&pages[i]);
> #ifdef CONFIG_MEMCG
> slab->memcg_data = 0;
> #endif
> __folio_clear_slab(slab_folio(slab));
> }
>
It's a good simplification. The loop setting Pg_slab before this
also can be simplified in the same way. However, I choose a
consistent way to fix this bug. I'd like to send a separate
simplification patch to simplify both two loops instead of
in a bugfix patch.
Thanks.