summaryrefslogtreecommitdiffstats
path: root/mm/memory-failure.c
diff options
context:
space:
mode:
authorWu Fengguang <fengguang.wu@intel.com>2009-12-16 12:19:58 +0100
committerAndi Kleen <ak@linux.intel.com>2009-12-16 12:19:58 +0100
commit847ce401df392b0704369fd3f75df614ac1414b4 (patch)
tree7c5021386dedea0d12f8a05b00c5267c4d28e426 /mm/memory-failure.c
parent8d22ba1b74aa9420b6032d856446564fb21f8090 (diff)
HWPOISON: Add unpoisoning support
The unpoisoning interface is useful for stress testing tools to reclaim poisoned pages (to prevent OOM) There is no hardware level unpoisioning, so this cannot be used for real memory errors, only for software injected errors. Note that it may leak pages silently - those who have been removed from LRU cache, but not isolated from page cache/swap cache at hwpoison time. Especially the stress test of dirty swap cache pages shall reboot system before exhausting memory. AK: Fix comments, add documentation, add printks, rename symbol Signed-off-by: Wu Fengguang <fengguang.wu@intel.com> Signed-off-by: Andi Kleen <ak@linux.intel.com>
Diffstat (limited to 'mm/memory-failure.c')
-rw-r--r--mm/memory-failure.c68
1 files changed, 68 insertions, 0 deletions
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 5055b940df5..ed6e91c87a5 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -838,6 +838,16 @@ int __memory_failure(unsigned long pfn, int trapno, int flags)
* and in many cases impossible, so we just avoid it here.
*/
lock_page_nosync(p);
+
+ /*
+ * unpoison always clear PG_hwpoison inside page lock
+ */
+ if (!PageHWPoison(p)) {
+ action_result(pfn, "unpoisoned", IGNORED);
+ res = 0;
+ goto out;
+ }
+
wait_on_page_writeback(p);
/*
@@ -893,3 +903,61 @@ void memory_failure(unsigned long pfn, int trapno)
{
__memory_failure(pfn, trapno, 0);
}
+
+/**
+ * unpoison_memory - Unpoison a previously poisoned page
+ * @pfn: Page number of the to be unpoisoned page
+ *
+ * Software-unpoison a page that has been poisoned by
+ * memory_failure() earlier.
+ *
+ * This is only done on the software-level, so it only works
+ * for linux injected failures, not real hardware failures
+ *
+ * Returns 0 for success, otherwise -errno.
+ */
+int unpoison_memory(unsigned long pfn)
+{
+ struct page *page;
+ struct page *p;
+ int freeit = 0;
+
+ if (!pfn_valid(pfn))
+ return -ENXIO;
+
+ p = pfn_to_page(pfn);
+ page = compound_head(p);
+
+ if (!PageHWPoison(p)) {
+ pr_debug("MCE: Page was already unpoisoned %#lx\n", pfn);
+ return 0;
+ }
+
+ if (!get_page_unless_zero(page)) {
+ if (TestClearPageHWPoison(p))
+ atomic_long_dec(&mce_bad_pages);
+ pr_debug("MCE: Software-unpoisoned free page %#lx\n", pfn);
+ return 0;
+ }
+
+ lock_page_nosync(page);
+ /*
+ * This test is racy because PG_hwpoison is set outside of page lock.
+ * That's acceptable because that won't trigger kernel panic. Instead,
+ * the PG_hwpoison page will be caught and isolated on the entrance to
+ * the free buddy page pool.
+ */
+ if (TestClearPageHWPoison(p)) {
+ pr_debug("MCE: Software-unpoisoned page %#lx\n", pfn);
+ atomic_long_dec(&mce_bad_pages);
+ freeit = 1;
+ }
+ unlock_page(page);
+
+ put_page(page);
+ if (freeit)
+ put_page(page);
+
+ return 0;
+}
+EXPORT_SYMBOL(unpoison_memory);