mm: memory-failure: bump memory failure stats to pglist_data

Right before memory_failure finishes its handling, accumulate poisoned
page's resolution counters to pglist_data's memory_failure_stats, so as to
update the corresponding sysfs entries.

Tested:
1) Start an application to allocate memory buffer chunks
2) Convert random memory buffer addresses to physical addresses
3) Inject memory errors using EINJ at chosen physical addresses
4) Access poisoned memory buffer and recover from SIGBUS
5) Check counter values under
   /sys/devices/system/node/node*/memory_failure/*

Link: https://lkml.kernel.org/r/20230120034622.2698268-3-jiaqiyan@google.com
Signed-off-by: Jiaqi Yan <jiaqiyan@google.com>
Acked-by: David Rientjes <rientjes@google.com>
Acked-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 44eec2e93a0b9e3fb23563d04cabd86e014d06dd..b4b30d9b078272d0a80bc44613fc21d73c1e2a79 100644 (file)
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1227,6 +1227,39 @@ static struct page_state error_states[] = {
 #undef slab
 #undef reserved
 
+static void update_per_node_mf_stats(unsigned long pfn,
+                                    enum mf_result result)
+{
+       int nid = MAX_NUMNODES;
+       struct memory_failure_stats *mf_stats = NULL;
+
+       nid = pfn_to_nid(pfn);
+       if (unlikely(nid < 0 || nid >= MAX_NUMNODES)) {
+               WARN_ONCE(1, "Memory failure: pfn=%#lx, invalid nid=%d", pfn, nid);
+               return;
+       }
+
+       mf_stats = &NODE_DATA(nid)->mf_stats;
+       switch (result) {
+       case MF_IGNORED:
+               ++mf_stats->ignored;
+               break;
+       case MF_FAILED:
+               ++mf_stats->failed;
+               break;
+       case MF_DELAYED:
+               ++mf_stats->delayed;
+               break;
+       case MF_RECOVERED:
+               ++mf_stats->recovered;
+               break;
+       default:
+               WARN_ONCE(1, "Memory failure: mf_result=%d is not properly handled", result);
+               break;
+       }
+       ++mf_stats->total;
+}
+
 /*
  * "Dirty/Clean" indication is not 100% accurate due to the possibility of
  * setting PG_dirty outside page lock. See also comment above set_page_dirty().
@@ -1237,6 +1270,9 @@ static int action_result(unsigned long pfn, enum mf_action_page_type type,
        trace_memory_failure_event(pfn, type, result);
 
        num_poisoned_pages_inc(pfn);
+
+       update_per_node_mf_stats(pfn, result);
+
        pr_err("%#lx: recovery action for %s: %s\n",
                pfn, action_page_types[type], action_name[result]);