Origianlly, unpoison_memory() is only used by hwpoison-inject, and
unpoisons a page which is poisoned by hwpoison-inject too. The kernel PTE
entry has no change during software poison/unpoison.
On a virtualization platform, it's possible to fix hardware corrupted page
by hypervisor, typically the hypervisor remaps the error HVA(host virtual
address). So add a new parameter 'const char *reason' to show the reason
called by.
Once the corrupted page gets fixed, the guest kernel needs put page to
buddy. Reuse the page and hit the following issue(Intel Platinum 8260):
BUG: unable to handle page fault for address: ffff888061646000
#PF: supervisor write access in kernel mode
#PF: error_code(0x0002) - not-present page
PGD 2c01067 P4D 2c01067 PUD 61aaa063 PMD 10089b063 PTE 800fffff9e9b9062
Oops: 0002 [#1] PREEMPT SMP NOPTI
CPU: 2 PID: 31106 Comm: stress Kdump: loaded Tainted: G M OE 5.18.0-rc6.bm.1-amd64 #6
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014
RIP: 0010:clear_page_erms+0x7/0x10
The kernel PTE entry of the fixed page is still uncorrected, kernel hits
page fault during prep_new_page. So add 'bool reset_kpte' to get a change
to fix the PTE entry if the page is fixed by hypervisor.
Signed-off-by: zhenwei pi <pizhenwei@bytedance.com>
---
include/linux/mm.h | 2 +-
mm/hwpoison-inject.c | 2 +-
mm/memory-failure.c | 26 +++++++++++++++++++-------
3 files changed, 21 insertions(+), 9 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 665873c2788c..7ba210e86401 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3191,7 +3191,7 @@ enum mf_flags {
extern int memory_failure(unsigned long pfn, int flags);
extern void memory_failure_queue(unsigned long pfn, int flags);
extern void memory_failure_queue_kick(int cpu);
-extern int unpoison_memory(unsigned long pfn);
+extern int unpoison_memory(unsigned long pfn, bool reset_kpte, const char *reason);
extern int sysctl_memory_failure_early_kill;
extern int sysctl_memory_failure_recovery;
extern void shake_page(struct page *p);
diff --git a/mm/hwpoison-inject.c b/mm/hwpoison-inject.c
index 5c0cddd81505..0dd17ba98ade 100644
--- a/mm/hwpoison-inject.c
+++ b/mm/hwpoison-inject.c
@@ -57,7 +57,7 @@ static int hwpoison_unpoison(void *data, u64 val)
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- return unpoison_memory(val);
+ return unpoison_memory(val, false, "hwpoison-inject");
}
DEFINE_DEBUGFS_ATTRIBUTE(hwpoison_fops, NULL, hwpoison_inject, "%lli\n");
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 95c218bb0a37..a46de3be1dd7 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -2132,21 +2132,26 @@ core_initcall(memory_failure_init);
/**
* unpoison_memory - Unpoison a previously poisoned page
* @pfn: Page number of the to be unpoisoned page
+ * @reset_kpte: Reset the PTE entry for kmap
+ * @reason: The callers tells why unpoisoning the page
*
- * Software-unpoison a page that has been poisoned by
- * memory_failure() earlier.
+ * Unpoison a page that has been poisoned by memory_failure() earlier.
*
- * This is only done on the software-level, so it only works
- * for linux injected failures, not real hardware failures
+ * For linux injected failures, there is no need to reset PTE entry.
+ * It's possible to fix hardware memory failure on a virtualization platform,
+ * once hypervisor fixes the failure, guest needs put page back to buddy and
+ * reset the PTE entry in kernel.
*
* Returns 0 for success, otherwise -errno.
*/
-int unpoison_memory(unsigned long pfn)
+int unpoison_memory(unsigned long pfn, bool reset_kpte, const char *reason)
{
struct page *page;
struct page *p;
int ret = -EBUSY;
int freeit = 0;
+ pte_t *kpte;
+ unsigned long addr;
static DEFINE_RATELIMIT_STATE(unpoison_rs, DEFAULT_RATELIMIT_INTERVAL,
DEFAULT_RATELIMIT_BURST);
@@ -2208,8 +2213,15 @@ int unpoison_memory(unsigned long pfn)
mutex_unlock(&mf_mutex);
if (!ret || freeit) {
num_poisoned_pages_dec();
- unpoison_pr_info("Unpoison: Software-unpoisoned page %#lx\n",
- page_to_pfn(p), &unpoison_rs);
+ pr_info("Unpoison: Unpoisoned page %#lx by %s\n",
+ page_to_pfn(p), reason);
+ if (reset_kpte) {
+ preempt_disable();
+ addr = (unsigned long)page_to_virt(p);
+ kpte = virt_to_kpte(addr);
+ set_pte_at(&init_mm, addr, kpte, pfn_pte(pfn, PAGE_KERNEL));
+ preempt_enable();
+ }
}
return ret;
}
--
2.20.1On Fri, May 20, 2022 at 03:06:47PM +0800, zhenwei pi wrote:
> Origianlly, unpoison_memory() is only used by hwpoison-inject, and
> unpoisons a page which is poisoned by hwpoison-inject too. The kernel PTE
> entry has no change during software poison/unpoison.
>
> On a virtualization platform, it's possible to fix hardware corrupted page
> by hypervisor, typically the hypervisor remaps the error HVA(host virtual
> address). So add a new parameter 'const char *reason' to show the reason
> called by.
>
> Once the corrupted page gets fixed, the guest kernel needs put page to
> buddy. Reuse the page and hit the following issue(Intel Platinum 8260):
> BUG: unable to handle page fault for address: ffff888061646000
> #PF: supervisor write access in kernel mode
> #PF: error_code(0x0002) - not-present page
> PGD 2c01067 P4D 2c01067 PUD 61aaa063 PMD 10089b063 PTE 800fffff9e9b9062
> Oops: 0002 [#1] PREEMPT SMP NOPTI
> CPU: 2 PID: 31106 Comm: stress Kdump: loaded Tainted: G M OE 5.18.0-rc6.bm.1-amd64 #6
> Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014
> RIP: 0010:clear_page_erms+0x7/0x10
>
> The kernel PTE entry of the fixed page is still uncorrected, kernel hits
> page fault during prep_new_page. So add 'bool reset_kpte' to get a change
> to fix the PTE entry if the page is fixed by hypervisor.
>
> Signed-off-by: zhenwei pi <pizhenwei@bytedance.com>
> ---
> include/linux/mm.h | 2 +-
> mm/hwpoison-inject.c | 2 +-
> mm/memory-failure.c | 26 +++++++++++++++++++-------
> 3 files changed, 21 insertions(+), 9 deletions(-)
>
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index 665873c2788c..7ba210e86401 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -3191,7 +3191,7 @@ enum mf_flags {
> extern int memory_failure(unsigned long pfn, int flags);
> extern void memory_failure_queue(unsigned long pfn, int flags);
> extern void memory_failure_queue_kick(int cpu);
> -extern int unpoison_memory(unsigned long pfn);
> +extern int unpoison_memory(unsigned long pfn, bool reset_kpte, const char *reason);
> extern int sysctl_memory_failure_early_kill;
> extern int sysctl_memory_failure_recovery;
> extern void shake_page(struct page *p);
> diff --git a/mm/hwpoison-inject.c b/mm/hwpoison-inject.c
> index 5c0cddd81505..0dd17ba98ade 100644
> --- a/mm/hwpoison-inject.c
> +++ b/mm/hwpoison-inject.c
> @@ -57,7 +57,7 @@ static int hwpoison_unpoison(void *data, u64 val)
> if (!capable(CAP_SYS_ADMIN))
> return -EPERM;
>
> - return unpoison_memory(val);
> + return unpoison_memory(val, false, "hwpoison-inject");
> }
>
> DEFINE_DEBUGFS_ATTRIBUTE(hwpoison_fops, NULL, hwpoison_inject, "%lli\n");
> diff --git a/mm/memory-failure.c b/mm/memory-failure.c
> index 95c218bb0a37..a46de3be1dd7 100644
> --- a/mm/memory-failure.c
> +++ b/mm/memory-failure.c
> @@ -2132,21 +2132,26 @@ core_initcall(memory_failure_init);
> /**
> * unpoison_memory - Unpoison a previously poisoned page
> * @pfn: Page number of the to be unpoisoned page
> + * @reset_kpte: Reset the PTE entry for kmap
> + * @reason: The callers tells why unpoisoning the page
> *
> - * Software-unpoison a page that has been poisoned by
> - * memory_failure() earlier.
> + * Unpoison a page that has been poisoned by memory_failure() earlier.
> *
> - * This is only done on the software-level, so it only works
> - * for linux injected failures, not real hardware failures
> + * For linux injected failures, there is no need to reset PTE entry.
> + * It's possible to fix hardware memory failure on a virtualization platform,
> + * once hypervisor fixes the failure, guest needs put page back to buddy and
> + * reset the PTE entry in kernel.
> *
> * Returns 0 for success, otherwise -errno.
> */
> -int unpoison_memory(unsigned long pfn)
> +int unpoison_memory(unsigned long pfn, bool reset_kpte, const char *reason)
> {
> struct page *page;
> struct page *p;
> int ret = -EBUSY;
> int freeit = 0;
> + pte_t *kpte;
> + unsigned long addr;
These variables are used only in "if (reset_kpte)" block, so you can
move the definitions in it.
> static DEFINE_RATELIMIT_STATE(unpoison_rs, DEFAULT_RATELIMIT_INTERVAL,
> DEFAULT_RATELIMIT_BURST);
>
> @@ -2208,8 +2213,15 @@ int unpoison_memory(unsigned long pfn)
> mutex_unlock(&mf_mutex);
> if (!ret || freeit) {
> num_poisoned_pages_dec();
> - unpoison_pr_info("Unpoison: Software-unpoisoned page %#lx\n",
> - page_to_pfn(p), &unpoison_rs);
> + pr_info("Unpoison: Unpoisoned page %#lx by %s\n",
> + page_to_pfn(p), reason);
Do you need undoing rate limiting here? In the original unpoison's usage,
avoiding flood of "Unpoison: Software-unpoisoned page" messages is helpful.
And unpoison seems to be called from virtio-balloon multiple times when
the backend is 2MB hugepages. If it's right, printing out 512 lines of
"Unpoison: Unpoisoned page 0xXXX by virtio-balloon" messages might not be
so helpful?
Thanks,
Naoya Horiguchi
> + if (reset_kpte) {
> + preempt_disable();
> + addr = (unsigned long)page_to_virt(p);
> + kpte = virt_to_kpte(addr);
> + set_pte_at(&init_mm, addr, kpte, pfn_pte(pfn, PAGE_KERNEL));
> + preempt_enable();
> + }
> }
> return ret;
> }
> --
> 2.20.1
On 5/30/22 13:02, HORIGUCHI NAOYA(堀口 直也) wrote: > On Fri, May 20, 2022 at 03:06:47PM +0800, zhenwei pi wrote: >> Origianlly, unpoison_memory() is only used by hwpoison-inject, and >> unpoisons a page which is poisoned by hwpoison-inject too. The kernel PTE >> entry has no change during software poison/unpoison. >> >> On a virtualization platform, it's possible to fix hardware corrupted page >> by hypervisor, typically the hypervisor remaps the error HVA(host virtual >> address). So add a new parameter 'const char *reason' to show the reason >> called by. >> >> Once the corrupted page gets fixed, the guest kernel needs put page to >> buddy. Reuse the page and hit the following issue(Intel Platinum 8260): >> BUG: unable to handle page fault for address: ffff888061646000 >> #PF: supervisor write access in kernel mode >> #PF: error_code(0x0002) - not-present page >> PGD 2c01067 P4D 2c01067 PUD 61aaa063 PMD 10089b063 PTE 800fffff9e9b9062 >> Oops: 0002 [#1] PREEMPT SMP NOPTI >> CPU: 2 PID: 31106 Comm: stress Kdump: loaded Tainted: G M OE 5.18.0-rc6.bm.1-amd64 #6 >> Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 >> RIP: 0010:clear_page_erms+0x7/0x10 >> >> The kernel PTE entry of the fixed page is still uncorrected, kernel hits >> page fault during prep_new_page. So add 'bool reset_kpte' to get a change >> to fix the PTE entry if the page is fixed by hypervisor. >> >> Signed-off-by: zhenwei pi <pizhenwei@bytedance.com> >> --- >> include/linux/mm.h | 2 +- >> mm/hwpoison-inject.c | 2 +- >> mm/memory-failure.c | 26 +++++++++++++++++++------- >> 3 files changed, 21 insertions(+), 9 deletions(-) >> > > Do you need undoing rate limiting here? In the original unpoison's usage, > avoiding flood of "Unpoison: Software-unpoisoned page" messages is helpful. > > And unpoison seems to be called from virtio-balloon multiple times when > the backend is 2MB hugepages. If it's right, printing out 512 lines of > "Unpoison: Unpoisoned page 0xXXX by virtio-balloon" messages might not be > so helpful? > All the suggestions(include '[PATCH 1/3] memory-failure: Introduce memory failure notifier') are reasonable, I'll fix them in the next version. Thanks a lot! -- zhenwei pi
On 20.05.22 09:06, zhenwei pi wrote:
> Origianlly, unpoison_memory() is only used by hwpoison-inject, and
> unpoisons a page which is poisoned by hwpoison-inject too. The kernel PTE
> entry has no change during software poison/unpoison.
>
> On a virtualization platform, it's possible to fix hardware corrupted page
> by hypervisor, typically the hypervisor remaps the error HVA(host virtual
> address). So add a new parameter 'const char *reason' to show the reason
> called by.
>
> Once the corrupted page gets fixed, the guest kernel needs put page to
> buddy. Reuse the page and hit the following issue(Intel Platinum 8260):
> BUG: unable to handle page fault for address: ffff888061646000
> #PF: supervisor write access in kernel mode
> #PF: error_code(0x0002) - not-present page
> PGD 2c01067 P4D 2c01067 PUD 61aaa063 PMD 10089b063 PTE 800fffff9e9b9062
> Oops: 0002 [#1] PREEMPT SMP NOPTI
> CPU: 2 PID: 31106 Comm: stress Kdump: loaded Tainted: G M OE 5.18.0-rc6.bm.1-amd64 #6
> Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014
> RIP: 0010:clear_page_erms+0x7/0x10
>
> The kernel PTE entry of the fixed page is still uncorrected, kernel hits
> page fault during prep_new_page. So add 'bool reset_kpte' to get a change
> to fix the PTE entry if the page is fixed by hypervisor.
Why don't we want to do that for the hwpoison case?
>
> Signed-off-by: zhenwei pi <pizhenwei@bytedance.com>
> ---
> include/linux/mm.h | 2 +-
> mm/hwpoison-inject.c | 2 +-
> mm/memory-failure.c | 26 +++++++++++++++++++-------
> 3 files changed, 21 insertions(+), 9 deletions(-)
>
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index 665873c2788c..7ba210e86401 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -3191,7 +3191,7 @@ enum mf_flags {
> extern int memory_failure(unsigned long pfn, int flags);
> extern void memory_failure_queue(unsigned long pfn, int flags);
> extern void memory_failure_queue_kick(int cpu);
> -extern int unpoison_memory(unsigned long pfn);
> +extern int unpoison_memory(unsigned long pfn, bool reset_kpte, const char *reason);
> extern int sysctl_memory_failure_early_kill;
> extern int sysctl_memory_failure_recovery;
> extern void shake_page(struct page *p);
> diff --git a/mm/hwpoison-inject.c b/mm/hwpoison-inject.c
> index 5c0cddd81505..0dd17ba98ade 100644
> --- a/mm/hwpoison-inject.c
> +++ b/mm/hwpoison-inject.c
> @@ -57,7 +57,7 @@ static int hwpoison_unpoison(void *data, u64 val)
> if (!capable(CAP_SYS_ADMIN))
> return -EPERM;
>
> - return unpoison_memory(val);
> + return unpoison_memory(val, false, "hwpoison-inject");
s/hwpoison-inject/hwpoison/
or maybe
s/hwpoison-inject/debugfs/
> }
>
> DEFINE_DEBUGFS_ATTRIBUTE(hwpoison_fops, NULL, hwpoison_inject, "%lli\n");
> diff --git a/mm/memory-failure.c b/mm/memory-failure.c
> index 95c218bb0a37..a46de3be1dd7 100644
> --- a/mm/memory-failure.c
> +++ b/mm/memory-failure.c
> @@ -2132,21 +2132,26 @@ core_initcall(memory_failure_init);
> /**
> * unpoison_memory - Unpoison a previously poisoned page
> * @pfn: Page number of the to be unpoisoned page
> + * @reset_kpte: Reset the PTE entry for kmap
> + * @reason: The callers tells why unpoisoning the page
> *
> - * Software-unpoison a page that has been poisoned by
> - * memory_failure() earlier.
> + * Unpoison a page that has been poisoned by memory_failure() earlier.
> *
> - * This is only done on the software-level, so it only works
> - * for linux injected failures, not real hardware failures
> + * For linux injected failures, there is no need to reset PTE entry.
> + * It's possible to fix hardware memory failure on a virtualization platform,
> + * once hypervisor fixes the failure, guest needs put page back to buddy and
> + * reset the PTE entry in kernel.
Why can't we do this unconditionally? Just check if the PTE is poisoned,
and if so, reset it.
--
Thanks,
David / dhildenb
© 2016 - 2026 Red Hat, Inc.