On Wed, Feb 1, 2023 at 10:54 PM Kefeng Wang <wangkefeng.wang@xxxxxxxxxx> wrote:
>
>
>
> On 2023/1/20 11:46, Jiaqi Yan wrote:
> > Today kernel provides following memory error info to userspace, but each
> > has its own disadvantage
> > * HardwareCorrupted in /proc/meminfo: number of bytes poisoned in total,
> > not per NUMA node stats though
> > * ras:memory_failure_event: only available after explicitly enabled
> > * /dev/mcelog provides many useful info about the MCEs, but
> > doesn't capture how memory_failure recovered memory MCEs
> > * kernel logs: userspace needs to process log text
> >
> > Exposes per NUMA node memory error stats as sysfs entries:
> >
> > /sys/devices/system/node/node${X}/memory_failure/total
> > /sys/devices/system/node/node${X}/memory_failure/recovered
> > /sys/devices/system/node/node${X}/memory_failure/ignored
> > /sys/devices/system/node/node${X}/memory_failure/failed
> > /sys/devices/system/node/node${X}/memory_failure/delayed
> >
> > These counters describe how many raw pages are poisoned and after the
> > attempted recoveries by the kernel, their resolutions: how many are
> > recovered, ignored, failed, or delayed respectively. The following
> > math holds for the statistics:
> > * total = recovered + ignored + failed + delayed
> >
> > Acked-by: David Rientjes <rientjes@xxxxxxxxxx>
> > Signed-off-by: Jiaqi Yan <jiaqiyan@xxxxxxxxxx>
> > ---
> > drivers/base/node.c | 3 +++
> > include/linux/mm.h | 5 +++++
> > include/linux/mmzone.h | 28 ++++++++++++++++++++++++++++
> > mm/memory-failure.c | 35 +++++++++++++++++++++++++++++++++++
> > 4 files changed, 71 insertions(+)
> >
> > diff --git a/drivers/base/node.c b/drivers/base/node.c
> > index faf3597a96da..b46db17124f3 100644
> > --- a/drivers/base/node.c
> > +++ b/drivers/base/node.c
> > @@ -586,6 +586,9 @@ static const struct attribute_group *node_dev_groups[] = {
> > &node_dev_group,
> > #ifdef CONFIG_HAVE_ARCH_NODE_DEV_GROUP
> > &arch_node_dev_group,
> > +#endif
> > +#ifdef CONFIG_MEMORY_FAILURE
> > + &memory_failure_attr_group,
> > #endif
> > NULL
> > };
> > diff --git a/include/linux/mm.h b/include/linux/mm.h
> > index f3f196e4d66d..888576884eb9 100644
> > --- a/include/linux/mm.h
> > +++ b/include/linux/mm.h
> > @@ -3521,6 +3521,11 @@ enum mf_action_page_type {
> > MF_MSG_UNKNOWN,
> > };
> >
> > +/*
> > + * Sysfs entries for memory failure handling statistics.
> > + */
> > +extern const struct attribute_group memory_failure_attr_group;
> > +
>
> This should move under CONFIG_MEMORY_FAILURE
Thanks! I will move it around in the new version.
>
> > #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS)
> > extern void clear_huge_page(struct page *page,
> > unsigned long addr_hint,
> > diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
> > index cd28a100d9e4..2c537b31fa7b 100644
> > --- a/include/linux/mmzone.h
> > +++ b/include/linux/mmzone.h
> > @@ -1110,6 +1110,31 @@ struct deferred_split {
> > };
> > #endif
> >
> > +#ifdef CONFIG_MEMORY_FAILURE
> > +/*
> > + * Per NUMA node memory failure handling statistics.
> > + */
> > +struct memory_failure_stats {
> > + /*
> > + * Number of raw pages poisoned.
> > + * Cases not accounted: memory outside kernel control, offline page,
> > + * arch-specific memory_failure (SGX), hwpoison_filter() filtered
> > + * error events, and unpoison actions from hwpoison_unpoison.
> > + */
> > + unsigned long total;
> > + /*
> > + * Recovery results of poisoned raw pages handled by memory_failure,
> > + * in sync with mf_result.
> > + * total = ignored + failed + delayed + recovered.
> > + * total * PAGE_SIZE * #nodes = /proc/meminfo/HardwareCorrupted.
> > + */
> > + unsigned long ignored;
> > + unsigned long failed;
> > + unsigned long delayed;
> > + unsigned long recovered;
> > +};
> > +#endif
> > +
> > /*
> > * On NUMA machines, each NUMA node would have a pg_data_t to describe
> > * it's memory layout. On UMA machines there is a single pglist_data which
> > @@ -1253,6 +1278,9 @@ typedef struct pglist_data {
> > #ifdef CONFIG_NUMA
> > struct memory_tier __rcu *memtier;
> > #endif
> > +#ifdef CONFIG_MEMORY_FAILURE
> > + struct memory_failure_stats mf_stats;
> > +#endif
> > } pg_data_t;
> >
> > #define node_present_pages(nid) (NODE_DATA(nid)->node_present_pages)
> > diff --git a/mm/memory-failure.c b/mm/memory-failure.c
> > index c77a9e37e27e..c628f1db3a4d 100644
> > --- a/mm/memory-failure.c
> > +++ b/mm/memory-failure.c
> > @@ -87,6 +87,41 @@ inline void num_poisoned_pages_sub(unsigned long pfn, long i)
> > memblk_nr_poison_sub(pfn, i);
> > }
> >
> > +/**
> > + * MF_ATTR_RO - Create sysfs entry for each memory failure statistics.
> > + * @_name: name of the file in the per NUMA sysfs directory.
> > + */
> > +#define MF_ATTR_RO(_name) \
> > +static ssize_t _name##_show(struct device *dev, \
> > + struct device_attribute *attr, \
> > + char *buf) \
> > +{ \
> > + struct memory_failure_stats *mf_stats = \
> > + &NODE_DATA(dev->id)->mf_stats; \
> > + return sprintf(buf, "%lu\n", mf_stats->_name); \
> > +} \
> > +static DEVICE_ATTR_RO(_name)
> > +
> > +MF_ATTR_RO(total);
> > +MF_ATTR_RO(ignored);
> > +MF_ATTR_RO(failed);
> > +MF_ATTR_RO(delayed);
> > +MF_ATTR_RO(recovered);
> > +
> > +static struct attribute *memory_failure_attr[] = {
> > + &dev_attr_total.attr,
> > + &dev_attr_ignored.attr,
> > + &dev_attr_failed.attr,
> > + &dev_attr_delayed.attr,
> > + &dev_attr_recovered.attr,
> > + NULL,
> > +};
> > +
> > +const struct attribute_group memory_failure_attr_group = {
> > + .name = "memory_failure",
> > + .attrs = memory_failure_attr,
> > +};
> > +
> > /*
> > * Return values:
> > * 1: the page is dissolved (if needed) and taken off from buddy,
