The patch titled
Subject: mm/hwpoison: avoid the impact of hwpoison_filter() return value on mce handler
has been added to the -mm tree. Its filename is
mm-hwpoison-avoid-the-impact-of-hwpoison_filter-return-value-on-mce-handler.patch
This patch should soon appear at
https://ozlabs.org/~akpm/mmots/broken-out/mm-hwpoison-avoid-the-impact-of-hwpoison_filter-return-value-on-mce-handler.patch
and later at
https://ozlabs.org/~akpm/mmotm/broken-out/mm-hwpoison-avoid-the-impact-of-hwpoison_filter-return-value-on-mce-handler.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: luofei <luofei@xxxxxxxxxxxx>
Subject: mm/hwpoison: avoid the impact of hwpoison_filter() return value on mce handler
When the hwpoison page meets the filter conditions, it should not be
regarded as successful memory_failure() processing for mce handler, but
should return a value(-EHWPOISON), otherwise mce handler regards the error
page has been identified and isolated, which may lead to calling
set_mce_nospec() to change page attribute, etc.
Here a new MF_MCE_HANDLE flag is introduced to identify the call from the
mce handler and instruct hwpoison_filter() to return -EHWPOISON, otherwise
return 0 for compatibility with the hwpoison injector.
Link: https://lkml.kernel.org/r/20220221021415.2328992-1-luofei@xxxxxxxxxxxx
Signed-off-by: luofei <luofei@xxxxxxxxxxxx>
Cc: Tony Luck <tony.luck@xxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Cc: Naoya Horiguchi <naoya.horiguchi@xxxxxxx>
Cc: H. Peter Anvin <hpa@xxxxxxxxx>
Cc: Fei Luo <luofei@xxxxxxxxxxxx>
Cc: Miaohe Lin <linmiaohe@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
arch/x86/kernel/cpu/mce/core.c | 15 +++++++++------
include/linux/mm.h | 1 +
mm/memory-failure.c | 14 ++++++++++++--
3 files changed, 22 insertions(+), 8 deletions(-)
--- a/arch/x86/kernel/cpu/mce/core.c~mm-hwpoison-avoid-the-impact-of-hwpoison_filter-return-value-on-mce-handler
+++ a/arch/x86/kernel/cpu/mce/core.c
@@ -612,7 +612,7 @@ static int uc_decode_notifier(struct not
return NOTIFY_DONE;
pfn = mce->addr >> PAGE_SHIFT;
- if (!memory_failure(pfn, 0)) {
+ if (!memory_failure(pfn, MF_MCE_HANDLE)) {
set_mce_nospec(pfn, whole_page(mce));
mce->kflags |= MCE_HANDLED_UC;
}
@@ -1286,7 +1286,7 @@ static void kill_me_now(struct callback_
static void kill_me_maybe(struct callback_head *cb)
{
struct task_struct *p = container_of(cb, struct task_struct, mce_kill_me);
- int flags = MF_ACTION_REQUIRED;
+ int flags = MF_ACTION_REQUIRED | MF_MCE_HANDLE;
int ret;
p->mce_count = 0;
@@ -1303,9 +1303,12 @@ static void kill_me_maybe(struct callbac
}
/*
- * -EHWPOISON from memory_failure() means that it already sent SIGBUS
- * to the current process with the proper error info, so no need to
- * send SIGBUS here again.
+ * -EHWPOISON from memory_failure() means that memory_failure() did
+ * not handle the error event for the following reason:
+ * - SIGBUS has already been sent to the current process with the
+ * proper error info, or
+ * - hwpoison_filter() filtered the event,
+ * so no need to deal with it more.
*/
if (ret == -EHWPOISON)
return;
@@ -1320,7 +1323,7 @@ static void kill_me_never(struct callbac
p->mce_count = 0;
pr_err("Kernel accessed poison in user space at %llx\n", p->mce_addr);
- if (!memory_failure(p->mce_addr >> PAGE_SHIFT, 0))
+ if (!memory_failure(p->mce_addr >> PAGE_SHIFT, MF_MCE_HANDLE))
set_mce_nospec(p->mce_addr >> PAGE_SHIFT, p->mce_whole_page);
}
--- a/include/linux/mm.h~mm-hwpoison-avoid-the-impact-of-hwpoison_filter-return-value-on-mce-handler
+++ a/include/linux/mm.h
@@ -3173,6 +3173,7 @@ enum mf_flags {
MF_MUST_KILL = 1 << 2,
MF_SOFT_OFFLINE = 1 << 3,
MF_UNPOISON = 1 << 4,
+ MF_MCE_HANDLE = 1 << 5,
};
extern int memory_failure(unsigned long pfn, int flags);
extern void memory_failure_queue(unsigned long pfn, int flags);
--- a/mm/memory-failure.c~mm-hwpoison-avoid-the-impact-of-hwpoison_filter-return-value-on-mce-handler
+++ a/mm/memory-failure.c
@@ -1515,7 +1515,10 @@ static int memory_failure_hugetlb(unsign
if (TestClearPageHWPoison(head))
num_poisoned_pages_dec();
unlock_page(head);
- return 0;
+ if (flags & MF_MCE_HANDLE)
+ return -EHWPOISON;
+ else
+ return 0;
}
unlock_page(head);
res = MF_FAILED;
@@ -1602,7 +1605,10 @@ static int memory_failure_dev_pagemap(un
goto out;
if (hwpoison_filter(page)) {
- rc = 0;
+ if (flags & MF_MCE_HANDLE)
+ rc = -EHWPOISON;
+ else
+ rc = 0;
goto unlock;
}
@@ -1830,6 +1836,10 @@ try_again:
num_poisoned_pages_dec();
unlock_page(p);
put_page(p);
+ if (flags & MF_MCE_HANDLE)
+ res = -EHWPOISON;
+ else
+ res = 0;
goto unlock_mutex;
}
_
Patches currently in -mm which might be from luofei@xxxxxxxxxxxx are
mm-hwpoison-avoid-the-impact-of-hwpoison_filter-return-value-on-mce-handler.patch
mm-hwpoison-add-in-use-hugepage-hwpoison-filter-judgement.patch
