HWPOISON: Be more aggressive at freeing non LRU caches

shake_page handles more types of page caches than lru_drain_all()

- per cpu page allocator pages
- per CPU LRU

Stops early when the page became free.

Used in followon patches.

Signed-off-by: Andi Kleen <ak@linux.intel.com>

2 files changed, 23 insertions, 0 deletions

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 9d65ae4ba0e0..68c84bb2ad3f 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1335,6 +1335,7 @@ extern void memory_failure(unsigned long pfn, int trapno);
 extern int __memory_failure(unsigned long pfn, int trapno, int ref);
 extern int sysctl_memory_failure_early_kill;
 extern int sysctl_memory_failure_recovery;
+extern void shake_page(struct page *p);
 extern atomic_long_t mce_bad_pages;
 
 #endif /* __KERNEL__ */
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 50d4f8d7024a..38fcbb22eab9 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -83,6 +83,28 @@ static int kill_proc_ao(struct task_struct *t, unsigned long addr, int trapno,
 }
 
 /*
+ * When a unknown page type is encountered drain as many buffers as possible
+ * in the hope to turn the page into a LRU or free page, which we can handle.
+ */
+void shake_page(struct page *p)
+{
+	if (!PageSlab(p)) {
+		lru_add_drain_all();
+		if (PageLRU(p))
+			return;
+		drain_all_pages();
+		if (PageLRU(p) || is_free_buddy_page(p))
+			return;
+	}
+	/*
+	 * Could call shrink_slab here (which would also
+	 * shrink other caches). Unfortunately that might
+	 * also access the corrupted page, which could be fatal.
+	 */
+}
+EXPORT_SYMBOL_GPL(shake_page);
+
+/*
  * Kill all processes that have a poisoned page mapped and then isolate
  * the page.
  *