On Mon, 16 Jan 2023 19:39:01 +0000 Jiaqi Yan <jiaqiyan@xxxxxxxxxx> wrote:
> 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/pages_*
>
> --- 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->pages_ignored;
What is the locking here, to prevent concurrent increments?
> + break;
> + case MF_FAILED:
> + ++mf_stats->pages_failed;
> + break;
> + case MF_DELAYED:
> + ++mf_stats->pages_delayed;
> + break;
> + case MF_RECOVERED:
> + ++mf_stats->pages_recovered;
> + break;
> + default:
> + WARN_ONCE(1, "Memory failure: mf_result=%d is not properly handled", result);
> + break;
> + }
> + ++mf_stats->pages_poisoned;
> +}
