summaryrefslogtreecommitdiff
path: root/mm/memory-failure.c
diff options
context:
space:
mode:
authorJiaqi Yan <jiaqiyan@google.com>2023-07-13 00:18:31 +0000
committerAndrew Morton <akpm@linux-foundation.org>2023-08-18 10:12:26 -0700
commitb79f8eb408d0468df0d6082ed958b67d94adce65 (patch)
treee30fc3f285cca4a99d201aefbba121887cf883d2 /mm/memory-failure.c
parent9e130c4b000b0a3f0bf4b4c8e714bfe3d06ff4cc (diff)
mm/hwpoison: check if a raw page in a hugetlb folio is raw HWPOISON
Add the functionality, is_raw_hwpoison_page_in_hugepage, to tell if a raw page in a hugetlb folio is HWPOISON. This functionality relies on RawHwpUnreliable to be not set; otherwise hugepage's raw HWPOISON list becomes meaningless. is_raw_hwpoison_page_in_hugepage holds mf_mutex in order to synchronize with folio_set_hugetlb_hwpoison and folio_free_raw_hwp who iterate, insert, or delete entry in raw_hwp_list. llist itself doesn't ensure insertion and removal are synchornized with the llist_for_each_entry used by is_raw_hwpoison_page_in_hugepage (unless iterated entries are already deleted from the list). Caller can minimize the overhead of lock cycles by first checking HWPOISON flag of the folio. Exports this functionality to be immediately used in the read operation for hugetlbfs. Link: https://lkml.kernel.org/r/20230713001833.3778937-3-jiaqiyan@google.com Signed-off-by: Jiaqi Yan <jiaqiyan@google.com> Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com> Reviewed-by: Naoya Horiguchi <naoya.horiguchi@nec.com> Reviewed-by: Miaohe Lin <linmiaohe@huawei.com> Cc: James Houghton <jthoughton@google.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.c40
1 files changed, 38 insertions, 2 deletions
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 9422a5770db6..adb0dacbc74e 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -72,6 +72,8 @@ atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0);
static bool hw_memory_failure __read_mostly = false;
+static DEFINE_MUTEX(mf_mutex);
+
void num_poisoned_pages_inc(unsigned long pfn)
{
atomic_long_inc(&num_poisoned_pages);
@@ -1814,6 +1816,7 @@ EXPORT_SYMBOL_GPL(mf_dax_kill_procs);
#endif /* CONFIG_FS_DAX */
#ifdef CONFIG_HUGETLB_PAGE
+
/*
* Struct raw_hwp_page represents information about "raw error page",
* constructing singly linked list from ->_hugetlb_hwpoison field of folio.
@@ -1828,6 +1831,41 @@ static inline struct llist_head *raw_hwp_list_head(struct folio *folio)
return (struct llist_head *)&folio->_hugetlb_hwpoison;
}
+bool is_raw_hwpoison_page_in_hugepage(struct page *page)
+{
+ struct llist_head *raw_hwp_head;
+ struct raw_hwp_page *p;
+ struct folio *folio = page_folio(page);
+ bool ret = false;
+
+ if (!folio_test_hwpoison(folio))
+ return false;
+
+ if (!folio_test_hugetlb(folio))
+ return PageHWPoison(page);
+
+ /*
+ * When RawHwpUnreliable is set, kernel lost track of which subpages
+ * are HWPOISON. So return as if ALL subpages are HWPOISONed.
+ */
+ if (folio_test_hugetlb_raw_hwp_unreliable(folio))
+ return true;
+
+ mutex_lock(&mf_mutex);
+
+ raw_hwp_head = raw_hwp_list_head(folio);
+ llist_for_each_entry(p, raw_hwp_head->first, node) {
+ if (page == p->page) {
+ ret = true;
+ break;
+ }
+ }
+
+ mutex_unlock(&mf_mutex);
+
+ return ret;
+}
+
static unsigned long __folio_free_raw_hwp(struct folio *folio, bool move_flag)
{
struct llist_node *t, *tnode, *head;
@@ -2110,8 +2148,6 @@ out:
return rc;
}
-static DEFINE_MUTEX(mf_mutex);
-
/**
* memory_failure - Handle memory failure of a page.
* @pfn: Page Number of the corrupted page