On Sun, Sep 13, 2020 at 12:01 AM Muchun Song [off-list ref] wrote:

In the cgroup v1, we have a numa_stat interface. This is useful for
providing visibility into the numa locality information within an
memcg since the pages are allowed to be allocated from any physical
node. One of the use cases is evaluating application performance by
combining this information with the application's CPU allocation.
But the cgroup v2 does not. So this patch adds the missing information.

Signed-off-by: Muchun Song <redacted>
Suggested-by: Shakeel Butt <redacted>
Reported-by: kernel test robot <redacted>
---

[snip]

+
+static struct numa_stat numa_stats[] = {
+       { "anon", PAGE_SIZE, NR_ANON_MAPPED },
+       { "file", PAGE_SIZE, NR_FILE_PAGES },
+       { "kernel_stack", 1024, NR_KERNEL_STACK_KB },
+       { "shmem", PAGE_SIZE, NR_SHMEM },
+       { "file_mapped", PAGE_SIZE, NR_FILE_MAPPED },
+       { "file_dirty", PAGE_SIZE, NR_FILE_DIRTY },
+       { "file_writeback", PAGE_SIZE, NR_WRITEBACK },
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+       /*
+        * The ratio will be initialized in numa_stats_init(). Because
+        * on some architectures, the macro of HPAGE_PMD_SIZE is not
+        * constant(e.g. powerpc).
+        */
+       { "anon_thp", 0, NR_ANON_THPS },
+#endif
+       { "inactive_anon", PAGE_SIZE, NR_INACTIVE_ANON },
+       { "active_anon", PAGE_SIZE, NR_ACTIVE_ANON },
+       { "inactive_file", PAGE_SIZE, NR_INACTIVE_FILE },
+       { "active_file", PAGE_SIZE, NR_ACTIVE_FILE },
+       { "unevictable", PAGE_SIZE, NR_UNEVICTABLE },
+       { "slab_reclaimable", 1, NR_SLAB_RECLAIMABLE_B },
+       { "slab_unreclaimable", 1, NR_SLAB_UNRECLAIMABLE_B },
+};
+
+static int __init numa_stats_init(void)
+{
+       int i;
+
+       for (i = 0; i < ARRAY_SIZE(numa_stats); i++) {
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+               if (numa_stats[i].idx == NR_ANON_THPS)
+                       numa_stats[i].ratio = HPAGE_PMD_SIZE;
+#endif
+       }

The for loop seems excessive but I don't really have a good alternative.

+
+       return 0;
+}
+pure_initcall(numa_stats_init);
+
+static unsigned long memcg_node_page_state(struct mem_cgroup *memcg,
+                                          unsigned int nid,
+                                          enum node_stat_item idx)
+{
+       VM_BUG_ON(nid >= nr_node_ids);
+       return lruvec_page_state(mem_cgroup_lruvec(memcg, NODE_DATA(nid)), idx);
+}
+
+static const char *memory_numa_stat_format(struct mem_cgroup *memcg)
+{
+       int i;
+       struct seq_buf s;
+
+       /* Reserve a byte for the trailing null */
+       seq_buf_init(&s, kmalloc(PAGE_SIZE, GFP_KERNEL), PAGE_SIZE - 1);
+       if (!s.buffer)
+               return NULL;
+
+       for (i = 0; i < ARRAY_SIZE(numa_stats); i++) {
+               int nid;
+
+               seq_buf_printf(&s, "%s", numa_stats[i].name);
+               for_each_node_state(nid, N_MEMORY) {
+                       u64 size;
+
+                       size = memcg_node_page_state(memcg, nid,
+                                                    numa_stats[i].idx);
+                       size *= numa_stats[i].ratio;
+                       seq_buf_printf(&s, " N%d=%llu", nid, size);
+               }
+               seq_buf_putc(&s, '\n');
+       }
+
+       /* The above should easily fit into one page */
+       if (WARN_ON_ONCE(seq_buf_putc(&s, '\0')))
+               s.buffer[PAGE_SIZE - 1] = '\0';

I think you should follow Michal's recommendation at
http://lkml.kernel.org/r/20200914115724.GO16999@dhcp22.suse.cz