From: Ma Wupeng <mawupeng1@huawei.com>
Commit 6da6b1d4a7df ("mm/hwpoison: convert TTU_IGNORE_HWPOISON to
TTU_HWPOISON") introduce TTU_HWPOISON to replace TTU_IGNORE_HWPOISON
in order to stop send SIGBUS signal when accessing an error page after
a memory error on a clean folio. However during page migration, anon
folio must be set with TTU_HWPOISON during unmap_*(). For pagecache
we need some policy just like the one in hwpoison_user_mappings to
set this flag. So move this policy from hwpoison_user_mappings to
unmap_poisoned_folio to handle this waring properly.
Waring will be produced during unamp poison folio with the following log:
------------[ cut here ]------------
WARNING: CPU: 1 PID: 365 at mm/rmap.c:1847 try_to_unmap_one+0x8fc/0xd3c
Modules linked in:
CPU: 1 UID: 0 PID: 365 Comm: bash Tainted: G W 6.13.0-rc1-00018-gacdb4bbda7ab #42
Tainted: [W]=WARN
Hardware name: QEMU QEMU Virtual Machine, BIOS 0.0.0 02/06/2015
pstate: 20400005 (nzCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
pc : try_to_unmap_one+0x8fc/0xd3c
lr : try_to_unmap_one+0x3dc/0xd3c
Call trace:
try_to_unmap_one+0x8fc/0xd3c (P)
try_to_unmap_one+0x3dc/0xd3c (L)
rmap_walk_anon+0xdc/0x1f8
rmap_walk+0x3c/0x58
try_to_unmap+0x88/0x90
unmap_poisoned_folio+0x30/0xa8
do_migrate_range+0x4a0/0x568
offline_pages+0x5a4/0x670
memory_block_action+0x17c/0x374
memory_subsys_offline+0x3c/0x78
device_offline+0xa4/0xd0
state_store+0x8c/0xf0
dev_attr_store+0x18/0x2c
sysfs_kf_write+0x44/0x54
kernfs_fop_write_iter+0x118/0x1a8
vfs_write+0x3a8/0x4bc
ksys_write+0x6c/0xf8
__arm64_sys_write+0x1c/0x28
invoke_syscall+0x44/0x100
el0_svc_common.constprop.0+0x40/0xe0
do_el0_svc+0x1c/0x28
el0_svc+0x30/0xd0
el0t_64_sync_handler+0xc8/0xcc
el0t_64_sync+0x198/0x19c
---[ end trace 0000000000000000 ]---
Fixes: 6da6b1d4a7df ("mm/hwpoison: convert TTU_IGNORE_HWPOISON to TTU_HWPOISON")
Signed-off-by: Ma Wupeng <mawupeng1@huawei.com>
Suggested-by: David Hildenbrand <david@redhat.com>
---
mm/internal.h | 5 ++--
mm/memory-failure.c | 61 +++++++++++++++++++++++----------------------
mm/memory_hotplug.c | 3 ++-
3 files changed, 36 insertions(+), 33 deletions(-)
diff --git a/mm/internal.h b/mm/internal.h
index 9826f7dce607..3caee67c0abd 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -1102,7 +1102,7 @@ static inline int find_next_best_node(int node, nodemask_t *used_node_mask)
* mm/memory-failure.c
*/
#ifdef CONFIG_MEMORY_FAILURE
-void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu);
+int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill);
void shake_folio(struct folio *folio);
extern int hwpoison_filter(struct page *p);
@@ -1125,8 +1125,9 @@ unsigned long page_mapped_in_vma(const struct page *page,
struct vm_area_struct *vma);
#else
-static inline void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu)
+static inline int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill);
{
+ return -EBUSY;
}
#endif
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index a7b8ccd29b6f..b5212b6e330a 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1556,8 +1556,34 @@ static int get_hwpoison_page(struct page *p, unsigned long flags)
return ret;
}
-void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu)
+int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill)
{
+ enum ttu_flags ttu = TTU_IGNORE_MLOCK | TTU_SYNC | TTU_HWPOISON;
+ struct address_space *mapping;
+
+ if (folio_test_swapcache(folio)) {
+ pr_err("%#lx: keeping poisoned page in swap cache\n", pfn);
+ ttu &= ~TTU_HWPOISON;
+ }
+
+ /*
+ * Propagate the dirty bit from PTEs to struct page first, because we
+ * need this to decide if we should kill or just drop the page.
+ * XXX: the dirty test could be racy: set_page_dirty() may not always
+ * be called inside page lock (it's recommended but not enforced).
+ */
+ mapping = folio_mapping(folio);
+ if (!must_kill && !folio_test_dirty(folio) && mapping &&
+ mapping_can_writeback(mapping)) {
+ if (folio_mkclean(folio)) {
+ folio_set_dirty(folio);
+ } else {
+ ttu &= ~TTU_HWPOISON;
+ pr_info("%#lx: corrupted page was clean: dropped without side effects\n",
+ pfn);
+ }
+ }
+
if (folio_test_hugetlb(folio) && !folio_test_anon(folio)) {
struct address_space *mapping;
@@ -1572,7 +1598,7 @@ void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu)
if (!mapping) {
pr_info("%#lx: could not lock mapping for mapped hugetlb folio\n",
folio_pfn(folio));
- return;
+ return -EBUSY;
}
try_to_unmap(folio, ttu|TTU_RMAP_LOCKED);
@@ -1580,6 +1606,8 @@ void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu)
} else {
try_to_unmap(folio, ttu);
}
+
+ return folio_mapped(folio) ? -EBUSY : 0;
}
/*
@@ -1589,8 +1617,6 @@ void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu)
static bool hwpoison_user_mappings(struct folio *folio, struct page *p,
unsigned long pfn, int flags)
{
- enum ttu_flags ttu = TTU_IGNORE_MLOCK | TTU_SYNC | TTU_HWPOISON;
- struct address_space *mapping;
LIST_HEAD(tokill);
bool unmap_success;
int forcekill;
@@ -1613,29 +1639,6 @@ static bool hwpoison_user_mappings(struct folio *folio, struct page *p,
if (!folio_mapped(folio))
return true;
- if (folio_test_swapcache(folio)) {
- pr_err("%#lx: keeping poisoned page in swap cache\n", pfn);
- ttu &= ~TTU_HWPOISON;
- }
-
- /*
- * Propagate the dirty bit from PTEs to struct page first, because we
- * need this to decide if we should kill or just drop the page.
- * XXX: the dirty test could be racy: set_page_dirty() may not always
- * be called inside page lock (it's recommended but not enforced).
- */
- mapping = folio_mapping(folio);
- if (!(flags & MF_MUST_KILL) && !folio_test_dirty(folio) && mapping &&
- mapping_can_writeback(mapping)) {
- if (folio_mkclean(folio)) {
- folio_set_dirty(folio);
- } else {
- ttu &= ~TTU_HWPOISON;
- pr_info("%#lx: corrupted page was clean: dropped without side effects\n",
- pfn);
- }
- }
-
/*
* First collect all the processes that have the page
* mapped in dirty form. This has to be done before try_to_unmap,
@@ -1643,9 +1646,7 @@ static bool hwpoison_user_mappings(struct folio *folio, struct page *p,
*/
collect_procs(folio, p, &tokill, flags & MF_ACTION_REQUIRED);
- unmap_poisoned_folio(folio, ttu);
-
- unmap_success = !folio_mapped(folio);
+ unmap_success = !unmap_poisoned_folio(folio, pfn, flags & MF_MUST_KILL);
if (!unmap_success)
pr_err("%#lx: failed to unmap page (folio mapcount=%d)\n",
pfn, folio_mapcount(folio));
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index c43b4e7fb298..3de661e57e92 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1806,7 +1806,8 @@ static void do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
if (WARN_ON(folio_test_lru(folio)))
folio_isolate_lru(folio);
if (folio_mapped(folio))
- unmap_poisoned_folio(folio, TTU_IGNORE_MLOCK);
+ unmap_poisoned_folio(folio, pfn, false);
+
continue;
}
--
2.43.0On 16.01.25 07:16, Wupeng Ma wrote:
> From: Ma Wupeng <mawupeng1@huawei.com>
>
> Commit 6da6b1d4a7df ("mm/hwpoison: convert TTU_IGNORE_HWPOISON to
> TTU_HWPOISON") introduce TTU_HWPOISON to replace TTU_IGNORE_HWPOISON
> in order to stop send SIGBUS signal when accessing an error page after
> a memory error on a clean folio. However during page migration, anon
> folio must be set with TTU_HWPOISON during unmap_*(). For pagecache
> we need some policy just like the one in hwpoison_user_mappings to
> set this flag. So move this policy from hwpoison_user_mappings to
> unmap_poisoned_folio to handle this waring properly.
>
> Waring will be produced during unamp poison folio with the following log:
>
> ------------[ cut here ]------------
> WARNING: CPU: 1 PID: 365 at mm/rmap.c:1847 try_to_unmap_one+0x8fc/0xd3c
> Modules linked in:
> CPU: 1 UID: 0 PID: 365 Comm: bash Tainted: G W 6.13.0-rc1-00018-gacdb4bbda7ab #42
> Tainted: [W]=WARN
> Hardware name: QEMU QEMU Virtual Machine, BIOS 0.0.0 02/06/2015
> pstate: 20400005 (nzCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
> pc : try_to_unmap_one+0x8fc/0xd3c
> lr : try_to_unmap_one+0x3dc/0xd3c
> Call trace:
> try_to_unmap_one+0x8fc/0xd3c (P)
> try_to_unmap_one+0x3dc/0xd3c (L)
> rmap_walk_anon+0xdc/0x1f8
> rmap_walk+0x3c/0x58
> try_to_unmap+0x88/0x90
> unmap_poisoned_folio+0x30/0xa8
> do_migrate_range+0x4a0/0x568
> offline_pages+0x5a4/0x670
> memory_block_action+0x17c/0x374
> memory_subsys_offline+0x3c/0x78
> device_offline+0xa4/0xd0
> state_store+0x8c/0xf0
> dev_attr_store+0x18/0x2c
> sysfs_kf_write+0x44/0x54
> kernfs_fop_write_iter+0x118/0x1a8
> vfs_write+0x3a8/0x4bc
> ksys_write+0x6c/0xf8
> __arm64_sys_write+0x1c/0x28
> invoke_syscall+0x44/0x100
> el0_svc_common.constprop.0+0x40/0xe0
> do_el0_svc+0x1c/0x28
> el0_svc+0x30/0xd0
> el0t_64_sync_handler+0xc8/0xcc
> el0t_64_sync+0x198/0x19c
> ---[ end trace 0000000000000000 ]---
>
> Fixes: 6da6b1d4a7df ("mm/hwpoison: convert TTU_IGNORE_HWPOISON to TTU_HWPOISON")
> Signed-off-by: Ma Wupeng <mawupeng1@huawei.com>
> Suggested-by: David Hildenbrand <david@redhat.com>
Your SOB should probably come last.
With or without moving folio_mapped() into unmap_poisoned_folio():
Acked-by: David Hildenbrand <david@redhat.com>
--
Cheers,
David / dhildenb
On 2025/1/16 14:16, Wupeng Ma wrote:
> From: Ma Wupeng <mawupeng1@huawei.com>
Thanks for your patch. Some nits below.
>
> Commit 6da6b1d4a7df ("mm/hwpoison: convert TTU_IGNORE_HWPOISON to
> TTU_HWPOISON") introduce TTU_HWPOISON to replace TTU_IGNORE_HWPOISON
> in order to stop send SIGBUS signal when accessing an error page after
> a memory error on a clean folio. However during page migration, anon
> folio must be set with TTU_HWPOISON during unmap_*(). For pagecache
> we need some policy just like the one in hwpoison_user_mappings to
> set this flag. So move this policy from hwpoison_user_mappings to
> unmap_poisoned_folio to handle this waring properly.
s/waring/warning/g
>
> Waring will be produced during unamp poison folio with the following log:
s/Waring/Warning/g
>
> ------------[ cut here ]------------
> WARNING: CPU: 1 PID: 365 at mm/rmap.c:1847 try_to_unmap_one+0x8fc/0xd3c
> Modules linked in:
> CPU: 1 UID: 0 PID: 365 Comm: bash Tainted: G W 6.13.0-rc1-00018-gacdb4bbda7ab #42
> Tainted: [W]=WARN
> Hardware name: QEMU QEMU Virtual Machine, BIOS 0.0.0 02/06/2015
> pstate: 20400005 (nzCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
> pc : try_to_unmap_one+0x8fc/0xd3c
> lr : try_to_unmap_one+0x3dc/0xd3c
> Call trace:
> try_to_unmap_one+0x8fc/0xd3c (P)
> try_to_unmap_one+0x3dc/0xd3c (L)
> rmap_walk_anon+0xdc/0x1f8
> rmap_walk+0x3c/0x58
> try_to_unmap+0x88/0x90
> unmap_poisoned_folio+0x30/0xa8
> do_migrate_range+0x4a0/0x568
> offline_pages+0x5a4/0x670
> memory_block_action+0x17c/0x374
> memory_subsys_offline+0x3c/0x78
> device_offline+0xa4/0xd0
> state_store+0x8c/0xf0
> dev_attr_store+0x18/0x2c
> sysfs_kf_write+0x44/0x54
> kernfs_fop_write_iter+0x118/0x1a8
> vfs_write+0x3a8/0x4bc
> ksys_write+0x6c/0xf8
> __arm64_sys_write+0x1c/0x28
> invoke_syscall+0x44/0x100
> el0_svc_common.constprop.0+0x40/0xe0
> do_el0_svc+0x1c/0x28
> el0_svc+0x30/0xd0
> el0t_64_sync_handler+0xc8/0xcc
> el0t_64_sync+0x198/0x19c
> ---[ end trace 0000000000000000 ]---
>
> Fixes: 6da6b1d4a7df ("mm/hwpoison: convert TTU_IGNORE_HWPOISON to TTU_HWPOISON")
> Signed-off-by: Ma Wupeng <mawupeng1@huawei.com>
> Suggested-by: David Hildenbrand <david@redhat.com>
> ---
> mm/internal.h | 5 ++--
> mm/memory-failure.c | 61 +++++++++++++++++++++++----------------------
> mm/memory_hotplug.c | 3 ++-
> 3 files changed, 36 insertions(+), 33 deletions(-)
>
> diff --git a/mm/internal.h b/mm/internal.h
> index 9826f7dce607..3caee67c0abd 100644
> --- a/mm/internal.h
> +++ b/mm/internal.h
> @@ -1102,7 +1102,7 @@ static inline int find_next_best_node(int node, nodemask_t *used_node_mask)
> * mm/memory-failure.c
> */
> #ifdef CONFIG_MEMORY_FAILURE
> -void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu);
> +int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill);
> void shake_folio(struct folio *folio);
> extern int hwpoison_filter(struct page *p);
>
> @@ -1125,8 +1125,9 @@ unsigned long page_mapped_in_vma(const struct page *page,
> struct vm_area_struct *vma);
>
> #else
> -static inline void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu)
> +static inline int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill);
> {
> + return -EBUSY;
> }
> #endif
>
> diff --git a/mm/memory-failure.c b/mm/memory-failure.c
> index a7b8ccd29b6f..b5212b6e330a 100644
> --- a/mm/memory-failure.c
> +++ b/mm/memory-failure.c
> @@ -1556,8 +1556,34 @@ static int get_hwpoison_page(struct page *p, unsigned long flags)
> return ret;
> }
>
> -void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu)
> +int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill)
> {
> + enum ttu_flags ttu = TTU_IGNORE_MLOCK | TTU_SYNC | TTU_HWPOISON;
> + struct address_space *mapping;
> +
> + if (folio_test_swapcache(folio)) {
> + pr_err("%#lx: keeping poisoned page in swap cache\n", pfn);
> + ttu &= ~TTU_HWPOISON;
> + }
> +
> + /*
> + * Propagate the dirty bit from PTEs to struct page first, because we
> + * need this to decide if we should kill or just drop the page.
> + * XXX: the dirty test could be racy: set_page_dirty() may not always
> + * be called inside page lock (it's recommended but not enforced).
> + */
> + mapping = folio_mapping(folio);
> + if (!must_kill && !folio_test_dirty(folio) && mapping &&
> + mapping_can_writeback(mapping)) {
> + if (folio_mkclean(folio)) {
> + folio_set_dirty(folio);
> + } else {
> + ttu &= ~TTU_HWPOISON;
> + pr_info("%#lx: corrupted page was clean: dropped without side effects\n",
> + pfn);
> + }
> + }
> +
> if (folio_test_hugetlb(folio) && !folio_test_anon(folio)) {
> struct address_space *mapping;
>
> @@ -1572,7 +1598,7 @@ void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu)
> if (!mapping) {
> pr_info("%#lx: could not lock mapping for mapped hugetlb folio\n",
> folio_pfn(folio));
> - return;
> + return -EBUSY;
> }
>
> try_to_unmap(folio, ttu|TTU_RMAP_LOCKED);
> @@ -1580,6 +1606,8 @@ void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu)
> } else {
> try_to_unmap(folio, ttu);
> }
> +
> + return folio_mapped(folio) ? -EBUSY : 0;
Do we really need this return value? It's unused in do_migrate_range().
Thanks.
.
On 2025/1/20 14:24, Miaohe Lin wrote:
> On 2025/1/16 14:16, Wupeng Ma wrote:
>> From: Ma Wupeng <mawupeng1@huawei.com>
>
> Thanks for your patch. Some nits below.
>
>>
>> Commit 6da6b1d4a7df ("mm/hwpoison: convert TTU_IGNORE_HWPOISON to
>> TTU_HWPOISON") introduce TTU_HWPOISON to replace TTU_IGNORE_HWPOISON
>> in order to stop send SIGBUS signal when accessing an error page after
>> a memory error on a clean folio. However during page migration, anon
>> folio must be set with TTU_HWPOISON during unmap_*(). For pagecache
>> we need some policy just like the one in hwpoison_user_mappings to
>> set this flag. So move this policy from hwpoison_user_mappings to
>> unmap_poisoned_folio to handle this waring properly.
>
> s/waring/warning/g
Thanks for your reply.
will be fixed later.
>
>>
>> Waring will be produced during unamp poison folio with the following log:
>
> s/Waring/Warning/g
Thanks for your reply.
will be fixed later.
>> if (folio_test_hugetlb(folio) && !folio_test_anon(folio)) {
>> struct address_space *mapping;
>>
>> @@ -1572,7 +1598,7 @@ void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu)
>> if (!mapping) {
>> pr_info("%#lx: could not lock mapping for mapped hugetlb folio\n",
>> folio_pfn(folio));
>> - return;
>> + return -EBUSY;
>> }
>>
>> try_to_unmap(folio, ttu|TTU_RMAP_LOCKED);
>> @@ -1580,6 +1606,8 @@ void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu)
>> } else {
>> try_to_unmap(folio, ttu);
>> }
>> +
>> + return folio_mapped(folio) ? -EBUSY : 0;
>
> Do we really need this return value? It's unused in do_migrate_range().
I suggested it, because the folio_mapped() is nowadays extremely cheap.
It cleans up hwpoison_user_mappings() quite nicely.
Any particular reason we shouldn't be doing that?
--
Cheers,
David / dhildenb
On 2025/1/20 15:49, David Hildenbrand wrote:
>
>>> if (folio_test_hugetlb(folio) && !folio_test_anon(folio)) {
>>> struct address_space *mapping;
>>> @@ -1572,7 +1598,7 @@ void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu)
>>> if (!mapping) {
>>> pr_info("%#lx: could not lock mapping for mapped hugetlb folio\n",
>>> folio_pfn(folio));
>>> - return;
>>> + return -EBUSY;
>>> }
>>> try_to_unmap(folio, ttu|TTU_RMAP_LOCKED);
>>> @@ -1580,6 +1606,8 @@ void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu)
>>> } else {
>>> try_to_unmap(folio, ttu);
>>> }
>>> +
>>> + return folio_mapped(folio) ? -EBUSY : 0;
>>
>> Do we really need this return value? It's unused in do_migrate_range().
>
> I suggested it, because the folio_mapped() is nowadays extremely cheap. It cleans up hwpoison_user_mappings() quite nicely.
>
> Any particular reason we shouldn't be doing that?
I was trying to keep code more clean (IMO) but no strong opinion.
Thanks.
.
On 20.01.25 08:49, David Hildenbrand wrote:
>
>>> if (folio_test_hugetlb(folio) && !folio_test_anon(folio)) {
>>> struct address_space *mapping;
>>>
>>> @@ -1572,7 +1598,7 @@ void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu)
>>> if (!mapping) {
>>> pr_info("%#lx: could not lock mapping for mapped hugetlb folio\n",
>>> folio_pfn(folio));
>>> - return;
>>> + return -EBUSY;
>>> }
>>>
>>> try_to_unmap(folio, ttu|TTU_RMAP_LOCKED);
>>> @@ -1580,6 +1606,8 @@ void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu)
>>> } else {
>>> try_to_unmap(folio, ttu);
>>> }
>>> +
>>> + return folio_mapped(folio) ? -EBUSY : 0;
>>
>> Do we really need this return value? It's unused in do_migrate_range().
>
> I suggested it, because the folio_mapped() is nowadays extremely cheap.
> It cleans up hwpoison_user_mappings() quite nicely.
I'm also wondering, if in do_migrate_range(), we want to
pr_warn_ratelimit() in case still mapped after the call. IIUC, we don't
really expect this to happen with SYNC set.
--
Cheers,
David / dhildenb
On 2025/1/20 16:46, David Hildenbrand wrote:
> On 20.01.25 08:49, David Hildenbrand wrote:
>>
>>>> if (folio_test_hugetlb(folio) && !folio_test_anon(folio)) {
>>>> struct address_space *mapping;
>>>> @@ -1572,7 +1598,7 @@ void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu)
>>>> if (!mapping) {
>>>> pr_info("%#lx: could not lock mapping for mapped hugetlb folio\n",
>>>> folio_pfn(folio));
>>>> - return;
>>>> + return -EBUSY;
>>>> }
>>>> try_to_unmap(folio, ttu|TTU_RMAP_LOCKED);
>>>> @@ -1580,6 +1606,8 @@ void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu)
>>>> } else {
>>>> try_to_unmap(folio, ttu);
>>>> }
>>>> +
>>>> + return folio_mapped(folio) ? -EBUSY : 0;
>>>
>>> Do we really need this return value? It's unused in do_migrate_range().
>>
>> I suggested it, because the folio_mapped() is nowadays extremely cheap.
>> It cleans up hwpoison_user_mappings() quite nicely.
>
> I'm also wondering, if in do_migrate_range(), we want to pr_warn_ratelimit() in case still mapped after the call. IIUC, we don't really expect this to happen with SYNC set.
Do you mean TTU_SYNC? It seems it's not set.
There might be a race will hit the proposed pr_warn_ratelimit():
/* Assume folio is isolated for reclaim, so memory_failure failed to handle it at first time. Then it's put back to LRU. */
do_migrate_range
folio_test_hwpoison
folio_mapped
<folio is isolated for reclaim again.>
unmap_poisoned_folio
<folio is put buck.>
pr_warn_ratelimit(folio_mapped)
But I might be miss something. And even this race is possible, it should be really hard to hit.
Thanks.
.
On 21.01.25 04:20, Miaohe Lin wrote:
> On 2025/1/20 16:46, David Hildenbrand wrote:
>> On 20.01.25 08:49, David Hildenbrand wrote:
>>>
>>>>> if (folio_test_hugetlb(folio) && !folio_test_anon(folio)) {
>>>>> struct address_space *mapping;
>>>>> @@ -1572,7 +1598,7 @@ void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu)
>>>>> if (!mapping) {
>>>>> pr_info("%#lx: could not lock mapping for mapped hugetlb folio\n",
>>>>> folio_pfn(folio));
>>>>> - return;
>>>>> + return -EBUSY;
>>>>> }
>>>>> try_to_unmap(folio, ttu|TTU_RMAP_LOCKED);
>>>>> @@ -1580,6 +1606,8 @@ void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu)
>>>>> } else {
>>>>> try_to_unmap(folio, ttu);
>>>>> }
>>>>> +
>>>>> + return folio_mapped(folio) ? -EBUSY : 0;
>>>>
>>>> Do we really need this return value? It's unused in do_migrate_range().
>>>
>>> I suggested it, because the folio_mapped() is nowadays extremely cheap.
>>> It cleans up hwpoison_user_mappings() quite nicely.
>>
>> I'm also wondering, if in do_migrate_range(), we want to pr_warn_ratelimit() in case still mapped after the call. IIUC, we don't really expect this to happen with SYNC set.
>
> Do you mean TTU_SYNC? It seems it's not set.
With your patch it will be now, which is the right thing to do I think.
>
> There might be a race will hit the proposed pr_warn_ratelimit():
>
> /* Assume folio is isolated for reclaim, so memory_failure failed to handle it at first time. Then it's put back to LRU. */
> do_migrate_range
> folio_test_hwpoison
> folio_mapped
> <folio is isolated for reclaim again.>
> unmap_poisoned_folio
> <folio is put buck.>
> pr_warn_ratelimit(folio_mapped)
>
> But I might be miss something. And even this race is possible, it should be really hard to hit.
Does try_to_unmap() care about isolation? Skimming over the code, I
don't think so. I assume once we take the folio lock, races with reclaim
are impossible.
In any case, the race is unexpected, so pr_warn_() would be helpful and
not harmful.
Memory offlining code will later simply skip all PageHWPoison() pages,
independent of the refcount as it seems. Failing to unmap might not be
handled correctly at all ... I think this might be problematic in other
regard (e.g., GUP references), but failing to unmap is "obviously" bad I
think :)
--
Cheers,
David / dhildenb
On 2025/1/21 15:58, David Hildenbrand wrote:
> On 21.01.25 04:20, Miaohe Lin wrote:
>> On 2025/1/20 16:46, David Hildenbrand wrote:
>>> On 20.01.25 08:49, David Hildenbrand wrote:
>>>>
>>>>>> if (folio_test_hugetlb(folio) && !folio_test_anon(folio)) {
>>>>>> struct address_space *mapping;
>>>>>> @@ -1572,7 +1598,7 @@ void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu)
>>>>>> if (!mapping) {
>>>>>> pr_info("%#lx: could not lock mapping for mapped hugetlb folio\n",
>>>>>> folio_pfn(folio));
>>>>>> - return;
>>>>>> + return -EBUSY;
>>>>>> }
>>>>>> try_to_unmap(folio, ttu|TTU_RMAP_LOCKED);
>>>>>> @@ -1580,6 +1606,8 @@ void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu)
>>>>>> } else {
>>>>>> try_to_unmap(folio, ttu);
>>>>>> }
>>>>>> +
>>>>>> + return folio_mapped(folio) ? -EBUSY : 0;
>>>>>
>>>>> Do we really need this return value? It's unused in do_migrate_range().
>>>>
>>>> I suggested it, because the folio_mapped() is nowadays extremely cheap.
>>>> It cleans up hwpoison_user_mappings() quite nicely.
>>>
>>> I'm also wondering, if in do_migrate_range(), we want to pr_warn_ratelimit() in case still mapped after the call. IIUC, we don't really expect this to happen with SYNC set.
>>
>> Do you mean TTU_SYNC? It seems it's not set.
>
> With your patch it will be now, which is the right thing to do I think.
>
>>
>> There might be a race will hit the proposed pr_warn_ratelimit():
>>
>> /* Assume folio is isolated for reclaim, so memory_failure failed to handle it at first time. Then it's put back to LRU. */
>> do_migrate_range
>> folio_test_hwpoison
>> folio_mapped
>> <folio is isolated for reclaim again.>
>> unmap_poisoned_folio
>> <folio is put buck.>
>> pr_warn_ratelimit(folio_mapped)
>>
>> But I might be miss something. And even this race is possible, it should be really hard to hit.
>
> Does try_to_unmap() care about isolation? Skimming over the code, I don't think so. I assume once we take the folio lock, races with reclaim are impossible.
I think you're right. I missed folio lock in above race.
>
> In any case, the race is unexpected, so pr_warn_() would be helpful and not harmful.
>
> Memory offlining code will later simply skip all PageHWPoison() pages, independent of the refcount as it seems. Failing to unmap might not be handled correctly at all ... I think this might be problematic in other regard (e.g., GUP references), but failing to unmap is "obviously" bad I think :)
Agree with you.
Thanks.
.
Hi Wupeng,
kernel test robot noticed the following build warnings:
[auto build test WARNING on akpm-mm/mm-everything]
url: https://github.com/intel-lab-lkp/linux/commits/Wupeng-Ma/mm-memory-failure-update-ttu-flag-inside-unmap_poisoned_folio/20250116-142614
base: https://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm.git mm-everything
patch link: https://lore.kernel.org/r/20250116061657.227027-2-mawupeng1%40huawei.com
patch subject: [PATCH v2 1/3] mm: memory-failure: update ttu flag inside unmap_poisoned_folio
config: x86_64-buildonly-randconfig-002-20250117 (https://download.01.org/0day-ci/archive/20250117/202501171215.KLa8VDaS-lkp@intel.com/config)
compiler: gcc-12 (Debian 12.2.0-14) 12.2.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20250117/202501171215.KLa8VDaS-lkp@intel.com/reproduce)
If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202501171215.KLa8VDaS-lkp@intel.com/
All warnings (new ones prefixed by >>):
In file included from mm/memory_hotplug.c:41:
mm/internal.h:1142:1: error: expected identifier or '(' before '{' token
1142 | {
| ^
>> mm/internal.h:1141:19: warning: 'unmap_poisoned_folio' used but never defined
1141 | static inline int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill);
| ^~~~~~~~~~~~~~~~~~~~
vim +/unmap_poisoned_folio +1141 mm/internal.h
1121
1122 extern u32 hwpoison_filter_dev_major;
1123 extern u32 hwpoison_filter_dev_minor;
1124 extern u64 hwpoison_filter_flags_mask;
1125 extern u64 hwpoison_filter_flags_value;
1126 extern u64 hwpoison_filter_memcg;
1127 extern u32 hwpoison_filter_enable;
1128 #define MAGIC_HWPOISON 0x48575053U /* HWPS */
1129 void SetPageHWPoisonTakenOff(struct page *page);
1130 void ClearPageHWPoisonTakenOff(struct page *page);
1131 bool take_page_off_buddy(struct page *page);
1132 bool put_page_back_buddy(struct page *page);
1133 struct task_struct *task_early_kill(struct task_struct *tsk, int force_early);
1134 void add_to_kill_ksm(struct task_struct *tsk, const struct page *p,
1135 struct vm_area_struct *vma, struct list_head *to_kill,
1136 unsigned long ksm_addr);
1137 unsigned long page_mapped_in_vma(const struct page *page,
1138 struct vm_area_struct *vma);
1139
1140 #else
> 1141 static inline int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill);
1142 {
1143 return -EBUSY;
1144 }
1145 #endif
1146
--
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki
Hi Wupeng,
kernel test robot noticed the following build errors:
[auto build test ERROR on akpm-mm/mm-everything]
url: https://github.com/intel-lab-lkp/linux/commits/Wupeng-Ma/mm-memory-failure-update-ttu-flag-inside-unmap_poisoned_folio/20250116-142614
base: https://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm.git mm-everything
patch link: https://lore.kernel.org/r/20250116061657.227027-2-mawupeng1%40huawei.com
patch subject: [PATCH v2 1/3] mm: memory-failure: update ttu flag inside unmap_poisoned_folio
config: s390-randconfig-002-20250117 (https://download.01.org/0day-ci/archive/20250117/202501171201.GNMkmauO-lkp@intel.com/config)
compiler: clang version 20.0.0git (https://github.com/llvm/llvm-project c23f2417dc5f6dc371afb07af5627ec2a9d373a0)
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20250117/202501171201.GNMkmauO-lkp@intel.com/reproduce)
If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202501171201.GNMkmauO-lkp@intel.com/
All errors (new ones prefixed by >>):
In file included from mm/mprotect.c:12:
In file included from include/linux/pagewalk.h:5:
In file included from include/linux/mm.h:2224:
include/linux/vmstat.h:504:43: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum numa_stat_item') [-Wenum-enum-conversion]
504 | return vmstat_text[NR_VM_ZONE_STAT_ITEMS +
| ~~~~~~~~~~~~~~~~~~~~~ ^
505 | item];
| ~~~~
include/linux/vmstat.h:511:43: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum numa_stat_item') [-Wenum-enum-conversion]
511 | return vmstat_text[NR_VM_ZONE_STAT_ITEMS +
| ~~~~~~~~~~~~~~~~~~~~~ ^
512 | NR_VM_NUMA_EVENT_ITEMS +
| ~~~~~~~~~~~~~~~~~~~~~~
include/linux/vmstat.h:524:43: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum numa_stat_item') [-Wenum-enum-conversion]
524 | return vmstat_text[NR_VM_ZONE_STAT_ITEMS +
| ~~~~~~~~~~~~~~~~~~~~~ ^
525 | NR_VM_NUMA_EVENT_ITEMS +
| ~~~~~~~~~~~~~~~~~~~~~~
In file included from mm/mprotect.c:30:
include/linux/mm_inline.h:47:41: warning: arithmetic between different enumeration types ('enum node_stat_item' and 'enum lru_list') [-Wenum-enum-conversion]
47 | __mod_lruvec_state(lruvec, NR_LRU_BASE + lru, nr_pages);
| ~~~~~~~~~~~ ^ ~~~
include/linux/mm_inline.h:49:22: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum lru_list') [-Wenum-enum-conversion]
49 | NR_ZONE_LRU_BASE + lru, nr_pages);
| ~~~~~~~~~~~~~~~~ ^ ~~~
In file included from mm/mprotect.c:41:
>> mm/internal.h:1142:1: error: expected identifier or '('
1142 | {
| ^
5 warnings and 1 error generated.
--
In file included from mm/vmscan.c:15:
In file included from include/linux/mm.h:2224:
include/linux/vmstat.h:504:43: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum numa_stat_item') [-Wenum-enum-conversion]
504 | return vmstat_text[NR_VM_ZONE_STAT_ITEMS +
| ~~~~~~~~~~~~~~~~~~~~~ ^
505 | item];
| ~~~~
include/linux/vmstat.h:511:43: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum numa_stat_item') [-Wenum-enum-conversion]
511 | return vmstat_text[NR_VM_ZONE_STAT_ITEMS +
| ~~~~~~~~~~~~~~~~~~~~~ ^
512 | NR_VM_NUMA_EVENT_ITEMS +
| ~~~~~~~~~~~~~~~~~~~~~~
include/linux/vmstat.h:524:43: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum numa_stat_item') [-Wenum-enum-conversion]
524 | return vmstat_text[NR_VM_ZONE_STAT_ITEMS +
| ~~~~~~~~~~~~~~~~~~~~~ ^
525 | NR_VM_NUMA_EVENT_ITEMS +
| ~~~~~~~~~~~~~~~~~~~~~~
In file included from mm/vmscan.c:30:
include/linux/mm_inline.h:47:41: warning: arithmetic between different enumeration types ('enum node_stat_item' and 'enum lru_list') [-Wenum-enum-conversion]
47 | __mod_lruvec_state(lruvec, NR_LRU_BASE + lru, nr_pages);
| ~~~~~~~~~~~ ^ ~~~
include/linux/mm_inline.h:49:22: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum lru_list') [-Wenum-enum-conversion]
49 | NR_ZONE_LRU_BASE + lru, nr_pages);
| ~~~~~~~~~~~~~~~~ ^ ~~~
In file included from mm/vmscan.c:68:
>> mm/internal.h:1142:1: error: expected identifier or '('
1142 | {
| ^
mm/vmscan.c:409:51: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum lru_list') [-Wenum-enum-conversion]
409 | size += zone_page_state(zone, NR_ZONE_LRU_BASE + lru);
| ~~~~~~~~~~~~~~~~ ^ ~~~
mm/vmscan.c:1770:4: warning: arithmetic between different enumeration types ('enum vm_event_item' and 'enum zone_type') [-Wenum-enum-conversion]
1770 | __count_zid_vm_events(PGSCAN_SKIP, zid, nr_skipped[zid]);
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
include/linux/vmstat.h:139:34: note: expanded from macro '__count_zid_vm_events'
139 | __count_vm_events(item##_NORMAL - ZONE_NORMAL + zid, delta)
| ~~~~~~~~~~~~~ ^ ~~~~~~~~~~~
mm/vmscan.c:2276:51: warning: arithmetic between different enumeration types ('enum node_stat_item' and 'enum lru_list') [-Wenum-enum-conversion]
2276 | inactive = lruvec_page_state(lruvec, NR_LRU_BASE + inactive_lru);
| ~~~~~~~~~~~ ^ ~~~~~~~~~~~~
mm/vmscan.c:2277:49: warning: arithmetic between different enumeration types ('enum node_stat_item' and 'enum lru_list') [-Wenum-enum-conversion]
2277 | active = lruvec_page_state(lruvec, NR_LRU_BASE + active_lru);
| ~~~~~~~~~~~ ^ ~~~~~~~~~~
mm/vmscan.c:6292:3: warning: arithmetic between different enumeration types ('enum vm_event_item' and 'enum zone_type') [-Wenum-enum-conversion]
6292 | __count_zid_vm_events(ALLOCSTALL, sc->reclaim_idx, 1);
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
include/linux/vmstat.h:139:34: note: expanded from macro '__count_zid_vm_events'
139 | __count_vm_events(item##_NORMAL - ZONE_NORMAL + zid, delta)
| ~~~~~~~~~~~~~ ^ ~~~~~~~~~~~
10 warnings and 1 error generated.
--
In file included from mm/page_alloc.c:19:
In file included from include/linux/mm.h:2224:
include/linux/vmstat.h:504:43: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum numa_stat_item') [-Wenum-enum-conversion]
504 | return vmstat_text[NR_VM_ZONE_STAT_ITEMS +
| ~~~~~~~~~~~~~~~~~~~~~ ^
505 | item];
| ~~~~
include/linux/vmstat.h:511:43: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum numa_stat_item') [-Wenum-enum-conversion]
511 | return vmstat_text[NR_VM_ZONE_STAT_ITEMS +
| ~~~~~~~~~~~~~~~~~~~~~ ^
512 | NR_VM_NUMA_EVENT_ITEMS +
| ~~~~~~~~~~~~~~~~~~~~~~
include/linux/vmstat.h:524:43: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum numa_stat_item') [-Wenum-enum-conversion]
524 | return vmstat_text[NR_VM_ZONE_STAT_ITEMS +
| ~~~~~~~~~~~~~~~~~~~~~ ^
525 | NR_VM_NUMA_EVENT_ITEMS +
| ~~~~~~~~~~~~~~~~~~~~~~
In file included from mm/page_alloc.c:44:
include/linux/mm_inline.h:47:41: warning: arithmetic between different enumeration types ('enum node_stat_item' and 'enum lru_list') [-Wenum-enum-conversion]
47 | __mod_lruvec_state(lruvec, NR_LRU_BASE + lru, nr_pages);
| ~~~~~~~~~~~ ^ ~~~
include/linux/mm_inline.h:49:22: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum lru_list') [-Wenum-enum-conversion]
49 | NR_ZONE_LRU_BASE + lru, nr_pages);
| ~~~~~~~~~~~~~~~~ ^ ~~~
In file included from mm/page_alloc.c:59:
>> mm/internal.h:1142:1: error: expected identifier or '('
1142 | {
| ^
mm/page_alloc.c:2933:2: warning: arithmetic between different enumeration types ('enum vm_event_item' and 'enum zone_type') [-Wenum-enum-conversion]
2933 | __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order);
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
include/linux/vmstat.h:139:34: note: expanded from macro '__count_zid_vm_events'
139 | __count_vm_events(item##_NORMAL - ZONE_NORMAL + zid, delta)
| ~~~~~~~~~~~~~ ^ ~~~~~~~~~~~
mm/page_alloc.c:3050:3: warning: arithmetic between different enumeration types ('enum vm_event_item' and 'enum zone_type') [-Wenum-enum-conversion]
3050 | __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order);
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
include/linux/vmstat.h:139:34: note: expanded from macro '__count_zid_vm_events'
139 | __count_vm_events(item##_NORMAL - ZONE_NORMAL + zid, delta)
| ~~~~~~~~~~~~~ ^ ~~~~~~~~~~~
mm/page_alloc.c:4683:2: warning: arithmetic between different enumeration types ('enum vm_event_item' and 'enum zone_type') [-Wenum-enum-conversion]
4683 | __count_zid_vm_events(PGALLOC, zone_idx(zone), nr_account);
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
include/linux/vmstat.h:139:34: note: expanded from macro '__count_zid_vm_events'
139 | __count_vm_events(item##_NORMAL - ZONE_NORMAL + zid, delta)
| ~~~~~~~~~~~~~ ^ ~~~~~~~~~~~
8 warnings and 1 error generated.
vim +1142 mm/internal.h
31d3d3484f9bd2 Wu Fengguang 2009-12-16 1121
7c116f2b0dbac4 Wu Fengguang 2009-12-16 1122 extern u32 hwpoison_filter_dev_major;
7c116f2b0dbac4 Wu Fengguang 2009-12-16 1123 extern u32 hwpoison_filter_dev_minor;
478c5ffc0b5052 Wu Fengguang 2009-12-16 1124 extern u64 hwpoison_filter_flags_mask;
478c5ffc0b5052 Wu Fengguang 2009-12-16 1125 extern u64 hwpoison_filter_flags_value;
4fd466eb46a6a9 Andi Kleen 2009-12-16 1126 extern u64 hwpoison_filter_memcg;
1bfe5febe34d2b Haicheng Li 2009-12-16 1127 extern u32 hwpoison_filter_enable;
3a78f77fd1fb82 Miaohe Lin 2024-06-12 1128 #define MAGIC_HWPOISON 0x48575053U /* HWPS */
3a78f77fd1fb82 Miaohe Lin 2024-06-12 1129 void SetPageHWPoisonTakenOff(struct page *page);
3a78f77fd1fb82 Miaohe Lin 2024-06-12 1130 void ClearPageHWPoisonTakenOff(struct page *page);
3a78f77fd1fb82 Miaohe Lin 2024-06-12 1131 bool take_page_off_buddy(struct page *page);
3a78f77fd1fb82 Miaohe Lin 2024-06-12 1132 bool put_page_back_buddy(struct page *page);
3a78f77fd1fb82 Miaohe Lin 2024-06-12 1133 struct task_struct *task_early_kill(struct task_struct *tsk, int force_early);
68158bfa3dbd4a Matthew Wilcox (Oracle 2024-10-05 1134) void add_to_kill_ksm(struct task_struct *tsk, const struct page *p,
3a78f77fd1fb82 Miaohe Lin 2024-06-12 1135 struct vm_area_struct *vma, struct list_head *to_kill,
3a78f77fd1fb82 Miaohe Lin 2024-06-12 1136 unsigned long ksm_addr);
68158bfa3dbd4a Matthew Wilcox (Oracle 2024-10-05 1137) unsigned long page_mapped_in_vma(const struct page *page,
68158bfa3dbd4a Matthew Wilcox (Oracle 2024-10-05 1138) struct vm_area_struct *vma);
eb36c5873b96e8 Al Viro 2012-05-30 1139
16038c4fffd802 Kefeng Wang 2024-08-27 1140 #else
2b5df10a15dc74 Ma Wupeng 2025-01-16 1141 static inline int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill);
16038c4fffd802 Kefeng Wang 2024-08-27 @1142 {
2b5df10a15dc74 Ma Wupeng 2025-01-16 1143 return -EBUSY;
16038c4fffd802 Kefeng Wang 2024-08-27 1144 }
16038c4fffd802 Kefeng Wang 2024-08-27 1145 #endif
16038c4fffd802 Kefeng Wang 2024-08-27 1146
--
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki
Hi Wupeng,
kernel test robot noticed the following build errors:
[auto build test ERROR on akpm-mm/mm-everything]
url: https://github.com/intel-lab-lkp/linux/commits/Wupeng-Ma/mm-memory-failure-update-ttu-flag-inside-unmap_poisoned_folio/20250116-142614
base: https://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm.git mm-everything
patch link: https://lore.kernel.org/r/20250116061657.227027-2-mawupeng1%40huawei.com
patch subject: [PATCH v2 1/3] mm: memory-failure: update ttu flag inside unmap_poisoned_folio
config: s390-randconfig-001-20250117 (https://download.01.org/0day-ci/archive/20250117/202501171300.SYkofFQ6-lkp@intel.com/config)
compiler: s390-linux-gcc (GCC) 14.2.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20250117/202501171300.SYkofFQ6-lkp@intel.com/reproduce)
If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202501171300.SYkofFQ6-lkp@intel.com/
All error/warnings (new ones prefixed by >>):
In file included from mm/page_isolation.c:13:
>> mm/internal.h:1142:1: error: expected identifier or '(' before '{' token
1142 | {
| ^
>> mm/internal.h:1141:19: warning: 'unmap_poisoned_folio' declared 'static' but never defined [-Wunused-function]
1141 | static inline int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill);
| ^~~~~~~~~~~~~~~~~~~~
--
In file included from mm/damon/paddr.c:19:
>> mm/damon/../internal.h:1142:1: error: expected identifier or '(' before '{' token
1142 | {
| ^
>> mm/damon/../internal.h:1141:19: warning: 'unmap_poisoned_folio' declared 'static' but never defined [-Wunused-function]
1141 | static inline int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill);
| ^~~~~~~~~~~~~~~~~~~~
vim +1142 mm/internal.h
31d3d3484f9bd2 Wu Fengguang 2009-12-16 1121
7c116f2b0dbac4 Wu Fengguang 2009-12-16 1122 extern u32 hwpoison_filter_dev_major;
7c116f2b0dbac4 Wu Fengguang 2009-12-16 1123 extern u32 hwpoison_filter_dev_minor;
478c5ffc0b5052 Wu Fengguang 2009-12-16 1124 extern u64 hwpoison_filter_flags_mask;
478c5ffc0b5052 Wu Fengguang 2009-12-16 1125 extern u64 hwpoison_filter_flags_value;
4fd466eb46a6a9 Andi Kleen 2009-12-16 1126 extern u64 hwpoison_filter_memcg;
1bfe5febe34d2b Haicheng Li 2009-12-16 1127 extern u32 hwpoison_filter_enable;
3a78f77fd1fb82 Miaohe Lin 2024-06-12 1128 #define MAGIC_HWPOISON 0x48575053U /* HWPS */
3a78f77fd1fb82 Miaohe Lin 2024-06-12 1129 void SetPageHWPoisonTakenOff(struct page *page);
3a78f77fd1fb82 Miaohe Lin 2024-06-12 1130 void ClearPageHWPoisonTakenOff(struct page *page);
3a78f77fd1fb82 Miaohe Lin 2024-06-12 1131 bool take_page_off_buddy(struct page *page);
3a78f77fd1fb82 Miaohe Lin 2024-06-12 1132 bool put_page_back_buddy(struct page *page);
3a78f77fd1fb82 Miaohe Lin 2024-06-12 1133 struct task_struct *task_early_kill(struct task_struct *tsk, int force_early);
68158bfa3dbd4a Matthew Wilcox (Oracle 2024-10-05 1134) void add_to_kill_ksm(struct task_struct *tsk, const struct page *p,
3a78f77fd1fb82 Miaohe Lin 2024-06-12 1135 struct vm_area_struct *vma, struct list_head *to_kill,
3a78f77fd1fb82 Miaohe Lin 2024-06-12 1136 unsigned long ksm_addr);
68158bfa3dbd4a Matthew Wilcox (Oracle 2024-10-05 1137) unsigned long page_mapped_in_vma(const struct page *page,
68158bfa3dbd4a Matthew Wilcox (Oracle 2024-10-05 1138) struct vm_area_struct *vma);
eb36c5873b96e8 Al Viro 2012-05-30 1139
16038c4fffd802 Kefeng Wang 2024-08-27 1140 #else
2b5df10a15dc74 Ma Wupeng 2025-01-16 @1141 static inline int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill);
16038c4fffd802 Kefeng Wang 2024-08-27 @1142 {
2b5df10a15dc74 Ma Wupeng 2025-01-16 1143 return -EBUSY;
16038c4fffd802 Kefeng Wang 2024-08-27 1144 }
16038c4fffd802 Kefeng Wang 2024-08-27 1145 #endif
16038c4fffd802 Kefeng Wang 2024-08-27 1146
--
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki
On 2025/1/17 11:57, kernel test robot wrote:
> Hi Wupeng,
>
> kernel test robot noticed the following build errors:
Thanks.
Will be fixed later.
>
> [auto build test ERROR on akpm-mm/mm-everything]
>
> url: https://github.com/intel-lab-lkp/linux/commits/Wupeng-Ma/mm-memory-failure-update-ttu-flag-inside-unmap_poisoned_folio/20250116-142614
> base: https://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm.git mm-everything
> patch link: https://lore.kernel.org/r/20250116061657.227027-2-mawupeng1%40huawei.com
> patch subject: [PATCH v2 1/3] mm: memory-failure: update ttu flag inside unmap_poisoned_folio
> config: s390-randconfig-001-20250117 (https://download.01.org/0day-ci/archive/20250117/202501171300.SYkofFQ6-lkp@intel.com/config)
> compiler: s390-linux-gcc (GCC) 14.2.0
> reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20250117/202501171300.SYkofFQ6-lkp@intel.com/reproduce)
>
> If you fix the issue in a separate patch/commit (i.e. not just a new version of
> the same patch/commit), kindly add following tags
> | Reported-by: kernel test robot <lkp@intel.com>
> | Closes: https://lore.kernel.org/oe-kbuild-all/202501171300.SYkofFQ6-lkp@intel.com/
>
> All error/warnings (new ones prefixed by >>):
>
> In file included from mm/page_isolation.c:13:
>>> mm/internal.h:1142:1: error: expected identifier or '(' before '{' token
> 1142 | {
> | ^
>>> mm/internal.h:1141:19: warning: 'unmap_poisoned_folio' declared 'static' but never defined [-Wunused-function]
> 1141 | static inline int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill);
> | ^~~~~~~~~~~~~~~~~~~~
> --
> In file included from mm/damon/paddr.c:19:
>>> mm/damon/../internal.h:1142:1: error: expected identifier or '(' before '{' token
> 1142 | {
> | ^
>>> mm/damon/../internal.h:1141:19: warning: 'unmap_poisoned_folio' declared 'static' but never defined [-Wunused-function]
> 1141 | static inline int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill);
> | ^~~~~~~~~~~~~~~~~~~~
>
>
> vim +1142 mm/internal.h
>
> 31d3d3484f9bd2 Wu Fengguang 2009-12-16 1121
> 7c116f2b0dbac4 Wu Fengguang 2009-12-16 1122 extern u32 hwpoison_filter_dev_major;
> 7c116f2b0dbac4 Wu Fengguang 2009-12-16 1123 extern u32 hwpoison_filter_dev_minor;
> 478c5ffc0b5052 Wu Fengguang 2009-12-16 1124 extern u64 hwpoison_filter_flags_mask;
> 478c5ffc0b5052 Wu Fengguang 2009-12-16 1125 extern u64 hwpoison_filter_flags_value;
> 4fd466eb46a6a9 Andi Kleen 2009-12-16 1126 extern u64 hwpoison_filter_memcg;
> 1bfe5febe34d2b Haicheng Li 2009-12-16 1127 extern u32 hwpoison_filter_enable;
> 3a78f77fd1fb82 Miaohe Lin 2024-06-12 1128 #define MAGIC_HWPOISON 0x48575053U /* HWPS */
> 3a78f77fd1fb82 Miaohe Lin 2024-06-12 1129 void SetPageHWPoisonTakenOff(struct page *page);
> 3a78f77fd1fb82 Miaohe Lin 2024-06-12 1130 void ClearPageHWPoisonTakenOff(struct page *page);
> 3a78f77fd1fb82 Miaohe Lin 2024-06-12 1131 bool take_page_off_buddy(struct page *page);
> 3a78f77fd1fb82 Miaohe Lin 2024-06-12 1132 bool put_page_back_buddy(struct page *page);
> 3a78f77fd1fb82 Miaohe Lin 2024-06-12 1133 struct task_struct *task_early_kill(struct task_struct *tsk, int force_early);
> 68158bfa3dbd4a Matthew Wilcox (Oracle 2024-10-05 1134) void add_to_kill_ksm(struct task_struct *tsk, const struct page *p,
> 3a78f77fd1fb82 Miaohe Lin 2024-06-12 1135 struct vm_area_struct *vma, struct list_head *to_kill,
> 3a78f77fd1fb82 Miaohe Lin 2024-06-12 1136 unsigned long ksm_addr);
> 68158bfa3dbd4a Matthew Wilcox (Oracle 2024-10-05 1137) unsigned long page_mapped_in_vma(const struct page *page,
> 68158bfa3dbd4a Matthew Wilcox (Oracle 2024-10-05 1138) struct vm_area_struct *vma);
> eb36c5873b96e8 Al Viro 2012-05-30 1139
> 16038c4fffd802 Kefeng Wang 2024-08-27 1140 #else
> 2b5df10a15dc74 Ma Wupeng 2025-01-16 @1141 static inline int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill);
> 16038c4fffd802 Kefeng Wang 2024-08-27 @1142 {
> 2b5df10a15dc74 Ma Wupeng 2025-01-16 1143 return -EBUSY;
> 16038c4fffd802 Kefeng Wang 2024-08-27 1144 }
> 16038c4fffd802 Kefeng Wang 2024-08-27 1145 #endif
> 16038c4fffd802 Kefeng Wang 2024-08-27 1146
>
© 2016 - 2025 Red Hat, Inc.