summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorNaoya Horiguchi <naoya.horiguchi@nec.com>2023-02-21 11:59:05 +0300
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>2023-03-10 11:34:25 +0300
commitdeab8114fb67dcb0e6293b665c3c7083fbadff17 (patch)
tree7e95a3262e9b8f092de5c2740d00c61b2642342d
parente6737d97722a729e27d3f2bc6bc3961f286e2b59 (diff)
downloadlinux-deab8114fb67dcb0e6293b665c3c7083fbadff17.tar.xz
mm/hwpoison: convert TTU_IGNORE_HWPOISON to TTU_HWPOISON
commit 6da6b1d4a7df8c35770186b53ef65d388398e139 upstream. After a memory error happens on a clean folio, a process unexpectedly receives SIGBUS when it accesses the error page. This SIGBUS killing is pointless and simply degrades the level of RAS of the system, because the clean folio can be dropped without any data lost on memory error handling as we do for a clean pagecache. When memory_failure() is called on a clean folio, try_to_unmap() is called twice (one from split_huge_page() and one from hwpoison_user_mappings()). The root cause of the issue is that pte conversion to hwpoisoned entry is now done in the first call of try_to_unmap() because PageHWPoison is already set at this point, while it's actually expected to be done in the second call. This behavior disturbs the error handling operation like removing pagecache, which results in the malfunction described above. So convert TTU_IGNORE_HWPOISON into TTU_HWPOISON and set TTU_HWPOISON only when we really intend to convert pte to hwpoison entry. This can prevent other callers of try_to_unmap() from accidentally converting to hwpoison entries. Link: https://lkml.kernel.org/r/20230221085905.1465385-1-naoya.horiguchi@linux.dev Fixes: a42634a6c07d ("readahead: Use a folio in read_pages()") Signed-off-by: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: David Hildenbrand <david@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-rw-r--r--include/linux/rmap.h2
-rw-r--r--mm/memory-failure.c8
-rw-r--r--mm/rmap.c2
3 files changed, 6 insertions, 6 deletions
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index bd3504d11b15..2bdba700bc3e 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -94,7 +94,7 @@ enum ttu_flags {
TTU_SPLIT_HUGE_PMD = 0x4, /* split huge PMD if any */
TTU_IGNORE_MLOCK = 0x8, /* ignore mlock */
TTU_SYNC = 0x10, /* avoid racy checks with PVMW_SYNC */
- TTU_IGNORE_HWPOISON = 0x20, /* corrupted page is recoverable */
+ TTU_HWPOISON = 0x20, /* do convert pte to hwpoison entry */
TTU_BATCH_FLUSH = 0x40, /* Batch TLB flushes where possible
* and caller guarantees they will
* do a final flush if necessary */
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index bead6bccc7f2..4457f9423e2c 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1020,7 +1020,7 @@ static int me_pagecache_dirty(struct page_state *ps, struct page *p)
* cache and swap cache(ie. page is freshly swapped in). So it could be
* referenced concurrently by 2 types of PTEs:
* normal PTEs and swap PTEs. We try to handle them consistently by calling
- * try_to_unmap(TTU_IGNORE_HWPOISON) to convert the normal PTEs to swap PTEs,
+ * try_to_unmap(!TTU_HWPOISON) to convert the normal PTEs to swap PTEs,
* and then
* - clear dirty bit to prevent IO
* - remove from LRU
@@ -1401,7 +1401,7 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn,
int flags, struct page *hpage)
{
struct folio *folio = page_folio(hpage);
- enum ttu_flags ttu = TTU_IGNORE_MLOCK | TTU_SYNC;
+ enum ttu_flags ttu = TTU_IGNORE_MLOCK | TTU_SYNC | TTU_HWPOISON;
struct address_space *mapping;
LIST_HEAD(tokill);
bool unmap_success;
@@ -1431,7 +1431,7 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn,
if (PageSwapCache(p)) {
pr_err("%#lx: keeping poisoned page in swap cache\n", pfn);
- ttu |= TTU_IGNORE_HWPOISON;
+ ttu &= ~TTU_HWPOISON;
}
/*
@@ -1446,7 +1446,7 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn,
if (page_mkclean(hpage)) {
SetPageDirty(hpage);
} else {
- ttu |= TTU_IGNORE_HWPOISON;
+ ttu &= ~TTU_HWPOISON;
pr_info("%#lx: corrupted page was clean: dropped without side effects\n",
pfn);
}
diff --git a/mm/rmap.c b/mm/rmap.c
index 2ec925e5fa6a..7da2d8d097d9 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1623,7 +1623,7 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
/* Update high watermark before we lower rss */
update_hiwater_rss(mm);
- if (PageHWPoison(subpage) && !(flags & TTU_IGNORE_HWPOISON)) {
+ if (PageHWPoison(subpage) && (flags & TTU_HWPOISON)) {
pteval = swp_entry_to_pte(make_hwpoison_entry(subpage));
if (folio_test_hugetlb(folio)) {
hugetlb_count_sub(folio_nr_pages(folio), mm);