The patch titled
Subject: mm/memory-failure: use a mutex to avoid memory_failure() races
has been added to the -mm tree. Its filename is
mm-memory-failure-use-a-mutex-to-avoid-memory_failure-races.patch
This patch should soon appear at
https://ozlabs.org/~akpm/mmots/broken-out/mm-memory-failure-use-a-mutex-to-avoid-memory_failure-races.patch
and later at
https://ozlabs.org/~akpm/mmotm/broken-out/mm-memory-failure-use-a-mutex-to-avoid-memory_failure-races.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: Tony Luck <tony.luck@xxxxxxxxx>
Subject: mm/memory-failure: use a mutex to avoid memory_failure() races
Patch series "mm,hwpoison: fix sending SIGBUS for Action Required MCE", v5.
I wrote this patchset to materialize what I think is the current allowable
solution mentioned by the previous discussion [1]. I simply borrowed
Tony's mutex patch and Aili's return code patch, then I queued another one
to find error virtual address in the best effort manner. I know that this
is not a perfect solution, but should work for some typical case.
[1]: https://lore.kernel.org/linux-mm/20210331192540.2141052f@alex-virtual-machine/
This patch (of 3):
There can be races when multiple CPUs consume poison from the same page.
The first into memory_failure() atomically sets the HWPoison page flag and
begins hunting for tasks that map this page. Eventually it invalidates
those mappings and may send a SIGBUS to the affected tasks.
But while all that work is going on, other CPUs see a "success" return
code from memory_failure() and so they believe the error has been handled
and continue executing.
Fix by wrapping most of the internal parts of memory_failure() in a mutex.
Link: https://lkml.kernel.org/r/20210521030156.2612074-1-nao.horiguchi@xxxxxxxxx
Link: https://lkml.kernel.org/r/20210521030156.2612074-2-nao.horiguchi@xxxxxxxxx
Signed-off-by: Tony Luck <tony.luck@xxxxxxxxx>
Signed-off-by: Naoya Horiguchi <naoya.horiguchi@xxxxxxx>
Reviewed-by: Borislav Petkov <bp@xxxxxxx>
Cc: Aili Yao <yaoaili@xxxxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: David Hildenbrand <david@xxxxxxxxxx>
Cc: Jue Wang <juew@xxxxxxxxxx>
Cc: Oscar Salvador <osalvador@xxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/memory-failure.c | 37 ++++++++++++++++++++++++-------------
1 file changed, 24 insertions(+), 13 deletions(-)
--- a/mm/memory-failure.c~mm-memory-failure-use-a-mutex-to-avoid-memory_failure-races
+++ a/mm/memory-failure.c
@@ -1397,6 +1397,8 @@ out:
return rc;
}
+static DEFINE_MUTEX(mf_mutex);
+
/**
* memory_failure - Handle memory failure of a page.
* @pfn: Page Number of the corrupted page
@@ -1420,7 +1422,7 @@ int memory_failure(unsigned long pfn, in
struct page *hpage;
struct page *orig_head;
struct dev_pagemap *pgmap;
- int res;
+ int res = 0;
unsigned long page_flags;
bool retry = true;
@@ -1440,13 +1442,18 @@ int memory_failure(unsigned long pfn, in
return -ENXIO;
}
+ mutex_lock(&mf_mutex);
+
try_again:
- if (PageHuge(p))
- return memory_failure_hugetlb(pfn, flags);
+ if (PageHuge(p)) {
+ res = memory_failure_hugetlb(pfn, flags);
+ goto unlock_mutex;
+ }
+
if (TestSetPageHWPoison(p)) {
pr_err("Memory failure: %#lx: already hardware poisoned\n",
pfn);
- return 0;
+ goto unlock_mutex;
}
orig_head = hpage = compound_head(p);
@@ -1479,17 +1486,19 @@ try_again:
res = MF_FAILED;
}
action_result(pfn, MF_MSG_BUDDY, res);
- return res == MF_RECOVERED ? 0 : -EBUSY;
+ res = res == MF_RECOVERED ? 0 : -EBUSY;
} else {
action_result(pfn, MF_MSG_KERNEL_HIGH_ORDER, MF_IGNORED);
- return -EBUSY;
+ res = -EBUSY;
}
+ goto unlock_mutex;
}
if (PageTransHuge(hpage)) {
if (try_to_split_thp_page(p, "Memory Failure") < 0) {
action_result(pfn, MF_MSG_UNSPLIT_THP, MF_IGNORED);
- return -EBUSY;
+ res = -EBUSY;
+ goto unlock_mutex;
}
VM_BUG_ON_PAGE(!page_count(p), p);
}
@@ -1513,7 +1522,7 @@ try_again:
if (PageCompound(p) && compound_head(p) != orig_head) {
action_result(pfn, MF_MSG_DIFFERENT_COMPOUND, MF_IGNORED);
res = -EBUSY;
- goto out;
+ goto unlock_page;
}
/*
@@ -1533,14 +1542,14 @@ try_again:
num_poisoned_pages_dec();
unlock_page(p);
put_page(p);
- return 0;
+ goto unlock_mutex;
}
if (hwpoison_filter(p)) {
if (TestClearPageHWPoison(p))
num_poisoned_pages_dec();
unlock_page(p);
put_page(p);
- return 0;
+ goto unlock_mutex;
}
if (!PageTransTail(p) && !PageLRU(p))
@@ -1559,7 +1568,7 @@ try_again:
if (!hwpoison_user_mappings(p, pfn, flags, &p)) {
action_result(pfn, MF_MSG_UNMAP_FAILED, MF_IGNORED);
res = -EBUSY;
- goto out;
+ goto unlock_page;
}
/*
@@ -1568,13 +1577,15 @@ try_again:
if (PageLRU(p) && !PageSwapCache(p) && p->mapping == NULL) {
action_result(pfn, MF_MSG_TRUNCATED_LRU, MF_IGNORED);
res = -EBUSY;
- goto out;
+ goto unlock_page;
}
identify_page_state:
res = identify_page_state(pfn, p, page_flags);
-out:
+unlock_page:
unlock_page(p);
+unlock_mutex:
+ mutex_unlock(&mf_mutex);
return res;
}
EXPORT_SYMBOL_GPL(memory_failure);
_
Patches currently in -mm which might be from tony.luck@xxxxxxxxx are
mm-memory-failure-use-a-mutex-to-avoid-memory_failure-races.patch
