diff mbox series

[v4,5/5] mm/memory-failure: send SIGBUS in the event of thp split fail

Message ID 20240524215306.2705454-6-jane.chu@oracle.com (mailing list archive)
State New
Headers show
Series Enhance soft hwpoison handling and injection | expand

Commit Message

Jane Chu May 24, 2024, 9:53 p.m. UTC 
While handling hwpoison in a THP page, it is possible that
try_to_split_thp_page() fails. For example, when the THP page has
been RDMA pinned. At this point, the kernel cannot isolate the
poisoned THP page, all it could do is to send a SIGBUS to the user
process with meaningful payload to give user-level recovery a chance.

Signed-off-by: Jane Chu <jane.chu@oracle.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Acked-by: Miaohe Lin <linmiaohe@huawei.com>
---
 mm/memory-failure.c | 34 +++++++++++++++++++++++++++++-----
 1 file changed, 29 insertions(+), 5 deletions(-)
diff mbox series

Patch

diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 85659dd0ea32..dcca7297a94c 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1706,7 +1706,12 @@  static int identify_page_state(unsigned long pfn, struct page *p,
 	return page_action(ps, p, pfn);
 }
 
-static int try_to_split_thp_page(struct page *page)
+/*
+ * When 'release' is 'false', it means that if thp split has failed,
+ * there is still more to do, hence the page refcount we took earlier
+ * is still needed.
+ */
+static int try_to_split_thp_page(struct page *page, bool release)
 {
 	int ret;
 
@@ -1714,7 +1719,7 @@  static int try_to_split_thp_page(struct page *page)
 	ret = split_huge_page(page);
 	unlock_page(page);
 
-	if (unlikely(ret))
+	if (ret && release)
 		put_page(page);
 
 	return ret;
@@ -2186,6 +2191,22 @@  static int memory_failure_dev_pagemap(unsigned long pfn, int flags,
 	return rc;
 }
 
+/*
+ * The calling condition is as such: thp split failed, page might have
+ * been RDMA pinned, not much can be done for recovery.
+ * But a SIGBUS should be delivered with vaddr provided so that the user
+ * application has a chance to recover. Also, application processes'
+ * election for MCE early killed will be honored.
+ */
+static void kill_procs_now(struct page *p, unsigned long pfn, int flags,
+				struct folio *folio)
+{
+	LIST_HEAD(tokill);
+
+	collect_procs(folio, p, &tokill, flags & MF_ACTION_REQUIRED);
+	kill_procs(&tokill, true, pfn, flags);
+}
+
 /**
  * memory_failure - Handle memory failure of a page.
  * @pfn: Page Number of the corrupted page
@@ -2327,8 +2348,11 @@  int memory_failure(unsigned long pfn, int flags)
 		 * page is a valid handlable page.
 		 */
 		folio_set_has_hwpoisoned(folio);
-		if (try_to_split_thp_page(p) < 0) {
-			res = action_result(pfn, MF_MSG_UNSPLIT_THP, MF_IGNORED);
+		if (try_to_split_thp_page(p, false) < 0) {
+			res = -EHWPOISON;
+			kill_procs_now(p, pfn, flags, folio);
+			put_page(p);
+			action_result(pfn, MF_MSG_UNSPLIT_THP, MF_FAILED);
 			goto unlock_mutex;
 		}
 		VM_BUG_ON_PAGE(!page_count(p), p);
@@ -2702,7 +2726,7 @@  static int soft_offline_in_use_page(struct page *page)
 	};
 
 	if (!huge && folio_test_large(folio)) {
-		if (try_to_split_thp_page(page)) {
+		if (try_to_split_thp_page(page, true)) {
 			pr_info("soft offline: %#lx: thp split failed\n", pfn);
 			return -EBUSY;
 		}