summaryrefslogtreecommitdiff
path: root/mm/memory-failure.c
diff options
context:
space:
mode:
authorJiaqi Yan <jiaqiyan@google.com>2023-07-13 03:18:30 +0300
committerAndrew Morton <akpm@linux-foundation.org>2023-08-18 20:12:26 +0300
commit9e130c4b000b0a3f0bf4b4c8e714bfe3d06ff4cc (patch)
tree178fad0c0b6713184c1ea488b8f908a7e03223c8 /mm/memory-failure.c
parent6852c46c783d20a4c0153d14d2990040e5e6e47e (diff)
downloadlinux-9e130c4b000b0a3f0bf4b4c8e714bfe3d06ff4cc.tar.xz
mm/hwpoison: delete all entries before traversal in __folio_free_raw_hwp
Patch series "Improve hugetlbfs read on HWPOISON hugepages", v4. Today when hardware memory is corrupted in a hugetlb hugepage, kernel leaves the hugepage in pagecache [1]; otherwise future mmap or read will suject to silent data corruption. This is implemented by returning -EIO from hugetlb_read_iter immediately if the hugepage has HWPOISON flag set. Since memory_failure already tracks the raw HWPOISON subpages in a hugepage, a natural improvement is possible: if userspace only asks for healthy subpages in the pagecache, kernel can return these data. This patchset implements this improvement. It consist of three parts. The 1st commit exports the functionality to tell if a subpage inside a hugetlb hugepage is a raw HWPOISON page. The 2nd commit teaches hugetlbfs_read_iter to return as many healthy bytes as possible. The 3rd commit properly tests this new feature. [1] commit 8625147cafaa ("hugetlbfs: don't delete error page from pagecache") This patch (of 4): Traversal on llist (e.g. llist_for_each_safe) is only safe AFTER entries are deleted from the llist. Correct the way __folio_free_raw_hwp deletes and frees raw_hwp_page entries in raw_hwp_list: first llist_del_all, then kfree within llist_for_each_safe. As of today, concurrent adding, deleting, and traversal on raw_hwp_list from hugetlb.c and/or memory-failure.c are fine with each other. Note this is guaranteed partly by the lock-free nature of llist, and partly by holding hugetlb_lock and/or mf_mutex. For example, as llist_del_all is lock-free with itself, folio_clear_hugetlb_hwpoison()s from __update_and_free_hugetlb_folio and memory_failure won't need explicit locking when freeing the raw_hwp_list. New code that manipulates raw_hwp_list must be careful to ensure the concurrency correctness. Link: https://lkml.kernel.org/r/20230713001833.3778937-1-jiaqiyan@google.com Link: https://lkml.kernel.org/r/20230713001833.3778937-2-jiaqiyan@google.com Signed-off-by: Jiaqi Yan <jiaqiyan@google.com> Acked-by: Mike Kravetz <mike.kravetz@oracle.com> Acked-by: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: James Houghton <jthoughton@google.com> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Muchun Song <songmuchun@bytedance.com> Cc: Yang Shi <shy828301@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Diffstat (limited to 'mm/memory-failure.c')
-rw-r--r--mm/memory-failure.c8
1 files changed, 3 insertions, 5 deletions
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 70f44180ef80..9422a5770db6 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1830,12 +1830,11 @@ static inline struct llist_head *raw_hwp_list_head(struct folio *folio)
static unsigned long __folio_free_raw_hwp(struct folio *folio, bool move_flag)
{
- struct llist_head *head;
- struct llist_node *t, *tnode;
+ struct llist_node *t, *tnode, *head;
unsigned long count = 0;
- head = raw_hwp_list_head(folio);
- llist_for_each_safe(tnode, t, head->first) {
+ head = llist_del_all(raw_hwp_list_head(folio));
+ llist_for_each_safe(tnode, t, head) {
struct raw_hwp_page *p = container_of(tnode, struct raw_hwp_page, node);
if (move_flag)
@@ -1845,7 +1844,6 @@ static unsigned long __folio_free_raw_hwp(struct folio *folio, bool move_flag)
kfree(p);
count++;
}
- llist_del_all(head);
return count;
}