The following random segfault is observed from time to time with
map_hugetlb selftest:
root@localhost:~# ./map_hugetlb 1 19
524288 kB hugepages
Mapping 1 Mbytes
Segmentation fault
[ 31.219972] map_hugetlb[365]: segfault (11) at 117 nip 77974f8c lr 779a6834 code 1 in ld-2.23.so[77966000+21000]
[ 31.220192] map_hugetlb[365]: code: 9421ffc0 480318d1 93410028 90010044 9361002c 93810030 93a10034 93c10038
[ 31.220307] map_hugetlb[365]: code: 93e1003c 93210024 8123007c 81430038 <80e90004> 814a0004 7f443a14 813a0004
[ 31.221911] BUG: Bad rss-counter state mm:(ptrval) type:MM_FILEPAGES val:33
[ 31.229362] BUG: Bad rss-counter state mm:(ptrval) type:MM_ANONPAGES val:5
This fault is due to hugetlb_free_pgd_range() freeing page tables
that are also used by regular pages.
As explain in the comment at the beginning of
hugetlb_free_pgd_range(), the verification done in free_pgd_range()
on floor and ceiling is not done here, which means
hugetlb_free_pte_range() can free outside the expected range.
As the verification cannot be done in hugetlb_free_pgd_range(), it
must be done in hugetlb_free_pte_range().
Fixes: b250c8c08c79 ("powerpc/8xx: Manage 512k huge pages as standard pages.")
Cc: [email protected]
Signed-off-by: Christophe Leroy <[email protected]>
---
arch/powerpc/mm/hugetlbpage.c | 18 ++++++++++++++++--
1 file changed, 16 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 26292544630f..e7ae2a2c4545 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -330,10 +330,24 @@ static void free_hugepd_range(struct mmu_gather *tlb, hugepd_t *hpdp, int pdshif
get_hugepd_cache_index(pdshift - shift));
}
-static void hugetlb_free_pte_range(struct mmu_gather *tlb, pmd_t *pmd, unsigned long addr)
+static void hugetlb_free_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
+ unsigned long addr, unsigned long end,
+ unsigned long floor, unsigned long ceiling)
{
+ unsigned long start = addr;
pgtable_t token = pmd_pgtable(*pmd);
+ start &= PMD_MASK;
+ if (start < floor)
+ return;
+ if (ceiling) {
+ ceiling &= PMD_MASK;
+ if (!ceiling)
+ return;
+ }
+ if (end - 1 > ceiling - 1)
+ return;
+
pmd_clear(pmd);
pte_free_tlb(tlb, token, addr);
mm_dec_nr_ptes(tlb->mm);
@@ -363,7 +377,7 @@ static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
*/
WARN_ON(!IS_ENABLED(CONFIG_PPC_8xx));
- hugetlb_free_pte_range(tlb, pmd, addr);
+ hugetlb_free_pte_range(tlb, pmd, addr, end, floor, ceiling);
continue;
}
--
2.25.0
Christophe Leroy <[email protected]> writes:
> The following random segfault is observed from time to time with
> map_hugetlb selftest:
>
> root@localhost:~# ./map_hugetlb 1 19
> 524288 kB hugepages
> Mapping 1 Mbytes
> Segmentation fault
>
> [ 31.219972] map_hugetlb[365]: segfault (11) at 117 nip 77974f8c lr 779a6834 code 1 in ld-2.23.so[77966000+21000]
> [ 31.220192] map_hugetlb[365]: code: 9421ffc0 480318d1 93410028 90010044 9361002c 93810030 93a10034 93c10038
> [ 31.220307] map_hugetlb[365]: code: 93e1003c 93210024 8123007c 81430038 <80e90004> 814a0004 7f443a14 813a0004
> [ 31.221911] BUG: Bad rss-counter state mm:(ptrval) type:MM_FILEPAGES val:33
> [ 31.229362] BUG: Bad rss-counter state mm:(ptrval) type:MM_ANONPAGES val:5
>
> This fault is due to hugetlb_free_pgd_range() freeing page tables
> that are also used by regular pages.
>
> As explain in the comment at the beginning of
> hugetlb_free_pgd_range(), the verification done in free_pgd_range()
> on floor and ceiling is not done here, which means
> hugetlb_free_pte_range() can free outside the expected range.
>
> As the verification cannot be done in hugetlb_free_pgd_range(), it
> must be done in hugetlb_free_pte_range().
>
Reviewed-by: Aneesh Kumar K.V <[email protected]>
> Fixes: b250c8c08c79 ("powerpc/8xx: Manage 512k huge pages as standard pages.")
> Cc: [email protected]
> Signed-off-by: Christophe Leroy <[email protected]>
> ---
> arch/powerpc/mm/hugetlbpage.c | 18 ++++++++++++++++--
> 1 file changed, 16 insertions(+), 2 deletions(-)
>
> diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
> index 26292544630f..e7ae2a2c4545 100644
> --- a/arch/powerpc/mm/hugetlbpage.c
> +++ b/arch/powerpc/mm/hugetlbpage.c
> @@ -330,10 +330,24 @@ static void free_hugepd_range(struct mmu_gather *tlb, hugepd_t *hpdp, int pdshif
> get_hugepd_cache_index(pdshift - shift));
> }
>
> -static void hugetlb_free_pte_range(struct mmu_gather *tlb, pmd_t *pmd, unsigned long addr)
> +static void hugetlb_free_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
> + unsigned long addr, unsigned long end,
> + unsigned long floor, unsigned long ceiling)
> {
> + unsigned long start = addr;
> pgtable_t token = pmd_pgtable(*pmd);
>
> + start &= PMD_MASK;
> + if (start < floor)
> + return;
> + if (ceiling) {
> + ceiling &= PMD_MASK;
> + if (!ceiling)
> + return;
> + }
> + if (end - 1 > ceiling - 1)
> + return;
> +
We do repeat that for pud/pmd/pte hugetlb_free_range. Can we consolidate
that with comment explaining we are checking if the pgtable entry is
mapping outside the range?
> pmd_clear(pmd);
> pte_free_tlb(tlb, token, addr);
> mm_dec_nr_ptes(tlb->mm);
> @@ -363,7 +377,7 @@ static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
> */
> WARN_ON(!IS_ENABLED(CONFIG_PPC_8xx));
>
> - hugetlb_free_pte_range(tlb, pmd, addr);
> + hugetlb_free_pte_range(tlb, pmd, addr, end, floor, ceiling);
>
> continue;
> }
> --
> 2.25.0
Le 02/09/2020 à 05:23, Aneesh Kumar K.V a écrit :
> Christophe Leroy <[email protected]> writes:
>
>> The following random segfault is observed from time to time with
>> map_hugetlb selftest:
>>
>> root@localhost:~# ./map_hugetlb 1 19
>> 524288 kB hugepages
>> Mapping 1 Mbytes
>> Segmentation fault
>>
>> [ 31.219972] map_hugetlb[365]: segfault (11) at 117 nip 77974f8c lr 779a6834 code 1 in ld-2.23.so[77966000+21000]
>> [ 31.220192] map_hugetlb[365]: code: 9421ffc0 480318d1 93410028 90010044 9361002c 93810030 93a10034 93c10038
>> [ 31.220307] map_hugetlb[365]: code: 93e1003c 93210024 8123007c 81430038 <80e90004> 814a0004 7f443a14 813a0004
>> [ 31.221911] BUG: Bad rss-counter state mm:(ptrval) type:MM_FILEPAGES val:33
>> [ 31.229362] BUG: Bad rss-counter state mm:(ptrval) type:MM_ANONPAGES val:5
>>
>> This fault is due to hugetlb_free_pgd_range() freeing page tables
>> that are also used by regular pages.
>>
>> As explain in the comment at the beginning of
>> hugetlb_free_pgd_range(), the verification done in free_pgd_range()
>> on floor and ceiling is not done here, which means
>> hugetlb_free_pte_range() can free outside the expected range.
>>
>> As the verification cannot be done in hugetlb_free_pgd_range(), it
>> must be done in hugetlb_free_pte_range().
>>
>
> Reviewed-by: Aneesh Kumar K.V <[email protected]>
>
>> Fixes: b250c8c08c79 ("powerpc/8xx: Manage 512k huge pages as standard pages.")
>> Cc: [email protected]
>> Signed-off-by: Christophe Leroy <[email protected]>
>> ---
>> arch/powerpc/mm/hugetlbpage.c | 18 ++++++++++++++++--
>> 1 file changed, 16 insertions(+), 2 deletions(-)
>>
>> diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
>> index 26292544630f..e7ae2a2c4545 100644
>> --- a/arch/powerpc/mm/hugetlbpage.c
>> +++ b/arch/powerpc/mm/hugetlbpage.c
>> @@ -330,10 +330,24 @@ static void free_hugepd_range(struct mmu_gather *tlb, hugepd_t *hpdp, int pdshif
>> get_hugepd_cache_index(pdshift - shift));
>> }
>>
>> -static void hugetlb_free_pte_range(struct mmu_gather *tlb, pmd_t *pmd, unsigned long addr)
>> +static void hugetlb_free_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
>> + unsigned long addr, unsigned long end,
>> + unsigned long floor, unsigned long ceiling)
>> {
>> + unsigned long start = addr;
>> pgtable_t token = pmd_pgtable(*pmd);
>>
>> + start &= PMD_MASK;
>> + if (start < floor)
>> + return;
>> + if (ceiling) {
>> + ceiling &= PMD_MASK;
>> + if (!ceiling)
>> + return;
>> + }
>> + if (end - 1 > ceiling - 1)
>> + return;
>> +
>
> We do repeat that for pud/pmd/pte hugetlb_free_range. Can we consolidate
> that with comment explaining we are checking if the pgtable entry is
> mapping outside the range?
I was thinking about refactoring that into a helper and add all the
necessary comments to explain what it does.
Will do that in a followup series if you are OK. This patch is a bug fix
and also have to go through stable.
Christophe
On 9/2/20 1:41 PM, Christophe Leroy wrote:
>
>
> Le 02/09/2020 à 05:23, Aneesh Kumar K.V a écrit :
>> Christophe Leroy <[email protected]> writes:
>>
>>> The following random segfault is observed from time to time with
>>> map_hugetlb selftest:
>>>
>>> root@localhost:~# ./map_hugetlb 1 19
>>> 524288 kB hugepages
>>> Mapping 1 Mbytes
>>> Segmentation fault
>>>
>>> [ 31.219972] map_hugetlb[365]: segfault (11) at 117 nip 77974f8c lr
>>> 779a6834 code 1 in ld-2.23.so[77966000+21000]
>>> [ 31.220192] map_hugetlb[365]: code: 9421ffc0 480318d1 93410028
>>> 90010044 9361002c 93810030 93a10034 93c10038
>>> [ 31.220307] map_hugetlb[365]: code: 93e1003c 93210024 8123007c
>>> 81430038 <80e90004> 814a0004 7f443a14 813a0004
>>> [ 31.221911] BUG: Bad rss-counter state mm:(ptrval)
>>> type:MM_FILEPAGES val:33
>>> [ 31.229362] BUG: Bad rss-counter state mm:(ptrval)
>>> type:MM_ANONPAGES val:5
>>>
>>> This fault is due to hugetlb_free_pgd_range() freeing page tables
>>> that are also used by regular pages.
>>>
>>> As explain in the comment at the beginning of
>>> hugetlb_free_pgd_range(), the verification done in free_pgd_range()
>>> on floor and ceiling is not done here, which means
>>> hugetlb_free_pte_range() can free outside the expected range.
>>>
>>> As the verification cannot be done in hugetlb_free_pgd_range(), it
>>> must be done in hugetlb_free_pte_range().
>>>
>>
>> Reviewed-by: Aneesh Kumar K.V <[email protected]>
>>
>>> Fixes: b250c8c08c79 ("powerpc/8xx: Manage 512k huge pages as standard
>>> pages.")
>>> Cc: [email protected]
>>> Signed-off-by: Christophe Leroy <[email protected]>
>>> ---
>>> arch/powerpc/mm/hugetlbpage.c | 18 ++++++++++++++++--
>>> 1 file changed, 16 insertions(+), 2 deletions(-)
>>>
>>> diff --git a/arch/powerpc/mm/hugetlbpage.c
>>> b/arch/powerpc/mm/hugetlbpage.c
>>> index 26292544630f..e7ae2a2c4545 100644
>>> --- a/arch/powerpc/mm/hugetlbpage.c
>>> +++ b/arch/powerpc/mm/hugetlbpage.c
>>> @@ -330,10 +330,24 @@ static void free_hugepd_range(struct mmu_gather
>>> *tlb, hugepd_t *hpdp, int pdshif
>>> get_hugepd_cache_index(pdshift - shift));
>>> }
>>> -static void hugetlb_free_pte_range(struct mmu_gather *tlb, pmd_t
>>> *pmd, unsigned long addr)
>>> +static void hugetlb_free_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
>>> + unsigned long addr, unsigned long end,
>>> + unsigned long floor, unsigned long ceiling)
>>> {
>>> + unsigned long start = addr;
>>> pgtable_t token = pmd_pgtable(*pmd);
>>> + start &= PMD_MASK;
>>> + if (start < floor)
>>> + return;
>>> + if (ceiling) {
>>> + ceiling &= PMD_MASK;
>>> + if (!ceiling)
>>> + return;
>>> + }
>>> + if (end - 1 > ceiling - 1)
>>> + return;
>>> +
>>
>> We do repeat that for pud/pmd/pte hugetlb_free_range. Can we consolidate
>> that with comment explaining we are checking if the pgtable entry is
>> mapping outside the range?
>
> I was thinking about refactoring that into a helper and add all the
> necessary comments to explain what it does.
>
> Will do that in a followup series if you are OK. This patch is a bug fix
> and also have to go through stable.
>
agreed.
Thanks.
-aneesh
On Mon, 31 Aug 2020 07:58:19 +0000 (UTC), Christophe Leroy wrote:
> The following random segfault is observed from time to time with
> map_hugetlb selftest:
>
> root@localhost:~# ./map_hugetlb 1 19
> 524288 kB hugepages
> Mapping 1 Mbytes
> Segmentation fault
>
> [...]
Applied to powerpc/next.
[1/1] powerpc: Fix random segfault when freeing hugetlb range
https://git.kernel.org/powerpc/c/542db12a9c42d1ce70c45091765e02f74c129f43
cheers