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@gmail.com
Link: https://lkml.kernel.org/r/20210521030156.2612074-2-nao.horiguchi@gmail.com
Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Reviewed-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Cc: Aili Yao <yaoaili@kingsoft.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: David Hildenbrand <david@redhat.com>
Cc: Jue Wang <juew@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>

diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 85ad98c00fd9dba37644ea8e7066353a4f69a7eb..c4aa318ec9a8a76b4e6f8515b85ec6a82d6537f9 100644 (file)
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1381,6 +1381,8 @@ out:
        return rc;
 }
 
+static DEFINE_MUTEX(mf_mutex);
+
 /**
  * memory_failure - Handle memory failure of a page.
  * @pfn: Page Number of the corrupted page
@@ -1404,7 +1406,7 @@ int memory_failure(unsigned long pfn, int flags)
        struct page *hpage;
        struct page *orig_head;
        struct dev_pagemap *pgmap;
-       int res;
+       int res = 0;
        unsigned long page_flags;
        bool retry = true;
 
@@ -1424,13 +1426,18 @@ int memory_failure(unsigned long pfn, int flags)
                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);
@@ -1463,17 +1470,19 @@ 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);
        }
@@ -1497,7 +1506,7 @@ 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;
        }
 
        /*
@@ -1517,14 +1526,14 @@ 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))
@@ -1543,7 +1552,7 @@ 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;
        }
 
        /*
@@ -1552,13 +1561,15 @@ 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);