memcg: dump memory.stat during cgroup OOM for v1

Patch series "memcg: OOM log improvements", v2.

This short patch series brings back some cgroup v1 stats in OOM logs
that were unnecessarily changed before. It also makes memcg OOM logs
less reliant on printk() internals.


This patch (of 2):

Commit c8713d0b2312 ("mm: memcontrol: dump memory.stat during cgroup OOM")
made sure we dump all the stats in memory.stat during a cgroup OOM, but it
also introduced a slight behavioral change.  The code used to print the
non-hierarchical v1 cgroup stats for the entire cgroup subtree, now it
only prints the v2 cgroup stats for the cgroup under OOM.

For cgroup v1 users, this introduces a few problems:

(a) The non-hierarchical stats of the memcg under OOM are no longer
    shown.

(b) A couple of v1-only stats (e.g.  pgpgin, pgpgout) are no longer
    shown.

(c) We show the list of cgroup v2 stats, even in cgroup v1.  This list
    of stats is not tracked with v1 in mind.  While most of the stats seem
    to be working on v1, there may be some stats that are not fully or
    correctly tracked.

Although OOM log is not set in stone, we should not change it for no
reason.  When upgrading the kernel version to a version including commit
c8713d0b2312 ("mm: memcontrol: dump memory.stat during cgroup OOM"), these
behavioral changes are noticed in cgroup v1.

The fix is simple.  Commit c8713d0b2312 ("mm: memcontrol: dump memory.stat
during cgroup OOM") separated stats formatting from stats display for v2,
to reuse the stats formatting in the OOM logs.  Do the same for v1.

Move the v2 specific formatting from memory_stat_format() to
memcg_stat_format(), add memcg1_stat_format() for v1, and make
memory_stat_format() select between them based on cgroup version.  Since
memory_stat_show() now works for both v1 & v2, drop memcg_stat_show().

Link: https://lkml.kernel.org/r/20230428132406.2540811-1-yosryahmed@google.com
Link: https://lkml.kernel.org/r/20230428132406.2540811-3-yosryahmed@google.com
Signed-off-by: Yosry Ahmed <yosryahmed@google.com>
Acked-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Michal Hocko <mhocko@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Petr Mladek <pmladek@suse.com>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Steven Rostedt (Google) <rostedt@goodmis.org>
Cc: Michal Hocko <mhocko@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 35 insertions, 25 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index a79a47f7fc20..a05c53ab5238 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1580,7 +1580,7 @@ static inline unsigned long memcg_page_state_output(struct mem_cgroup *memcg,
 	return memcg_page_state(memcg, item) * memcg_page_state_unit(item);
 }
 
-static void memory_stat_format(struct mem_cgroup *memcg, struct seq_buf *s)
+static void memcg_stat_format(struct mem_cgroup *memcg, struct seq_buf *s)
 {
 	int i;
 
@@ -1633,6 +1633,17 @@ static void memory_stat_format(struct mem_cgroup *memcg, struct seq_buf *s)
 	WARN_ON_ONCE(seq_buf_has_overflowed(s));
 }
 
+static void memcg1_stat_format(struct mem_cgroup *memcg, struct seq_buf *s);
+
+static void memory_stat_format(struct mem_cgroup *memcg, struct seq_buf *s)
+{
+	if (cgroup_subsys_on_dfl(memory_cgrp_subsys))
+		memcg_stat_format(memcg, s);
+	else
+		memcg1_stat_format(memcg, s);
+	WARN_ON_ONCE(seq_buf_has_overflowed(s));
+}
+
 #define K(x) ((x) << (PAGE_SHIFT-10))
 /**
  * mem_cgroup_print_oom_context: Print OOM information relevant to
@@ -4135,9 +4146,8 @@ static const unsigned int memcg1_events[] = {
 	PGMAJFAULT,
 };
 
-static int memcg_stat_show(struct seq_file *m, void *v)
+static void memcg1_stat_format(struct mem_cgroup *memcg, struct seq_buf *s)
 {
-	struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
 	unsigned long memory, memsw;
 	struct mem_cgroup *mi;
 	unsigned int i;
@@ -4152,18 +4162,18 @@ static int memcg_stat_show(struct seq_file *m, void *v)
 		if (memcg1_stats[i] == MEMCG_SWAP && !do_memsw_account())
 			continue;
 		nr = memcg_page_state_local(memcg, memcg1_stats[i]);
-		seq_printf(m, "%s %lu\n", memcg1_stat_names[i],
+		seq_buf_printf(s, "%s %lu\n", memcg1_stat_names[i],
 			   nr * memcg_page_state_unit(memcg1_stats[i]));
 	}
 
 	for (i = 0; i < ARRAY_SIZE(memcg1_events); i++)
-		seq_printf(m, "%s %lu\n", vm_event_name(memcg1_events[i]),
-			   memcg_events_local(memcg, memcg1_events[i]));
+		seq_buf_printf(s, "%s %lu\n", vm_event_name(memcg1_events[i]),
+			       memcg_events_local(memcg, memcg1_events[i]));
 
 	for (i = 0; i < NR_LRU_LISTS; i++)
-		seq_printf(m, "%s %lu\n", lru_list_name(i),
-			   memcg_page_state_local(memcg, NR_LRU_BASE + i) *
-			   PAGE_SIZE);
+		seq_buf_printf(s, "%s %lu\n", lru_list_name(i),
+			       memcg_page_state_local(memcg, NR_LRU_BASE + i) *
+			       PAGE_SIZE);
 
 	/* Hierarchical information */
 	memory = memsw = PAGE_COUNTER_MAX;
@@ -4171,11 +4181,11 @@ static int memcg_stat_show(struct seq_file *m, void *v)
 		memory = min(memory, READ_ONCE(mi->memory.max));
 		memsw = min(memsw, READ_ONCE(mi->memsw.max));
 	}
-	seq_printf(m, "hierarchical_memory_limit %llu\n",
-		   (u64)memory * PAGE_SIZE);
+	seq_buf_printf(s, "hierarchical_memory_limit %llu\n",
+		       (u64)memory * PAGE_SIZE);
 	if (do_memsw_account())
-		seq_printf(m, "hierarchical_memsw_limit %llu\n",
-			   (u64)memsw * PAGE_SIZE);
+		seq_buf_printf(s, "hierarchical_memsw_limit %llu\n",
+			       (u64)memsw * PAGE_SIZE);
 
 	for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++) {
 		unsigned long nr;
@@ -4183,19 +4193,19 @@ static int memcg_stat_show(struct seq_file *m, void *v)
 		if (memcg1_stats[i] == MEMCG_SWAP && !do_memsw_account())
 			continue;
 		nr = memcg_page_state(memcg, memcg1_stats[i]);
-		seq_printf(m, "total_%s %llu\n", memcg1_stat_names[i],
+		seq_buf_printf(s, "total_%s %llu\n", memcg1_stat_names[i],
 			   (u64)nr * memcg_page_state_unit(memcg1_stats[i]));
 	}
 
 	for (i = 0; i < ARRAY_SIZE(memcg1_events); i++)
-		seq_printf(m, "total_%s %llu\n",
-			   vm_event_name(memcg1_events[i]),
-			   (u64)memcg_events(memcg, memcg1_events[i]));
+		seq_buf_printf(s, "total_%s %llu\n",
+			       vm_event_name(memcg1_events[i]),
+			       (u64)memcg_events(memcg, memcg1_events[i]));
 
 	for (i = 0; i < NR_LRU_LISTS; i++)
-		seq_printf(m, "total_%s %llu\n", lru_list_name(i),
-			   (u64)memcg_page_state(memcg, NR_LRU_BASE + i) *
-			   PAGE_SIZE);
+		seq_buf_printf(s, "total_%s %llu\n", lru_list_name(i),
+			       (u64)memcg_page_state(memcg, NR_LRU_BASE + i) *
+			       PAGE_SIZE);
 
 #ifdef CONFIG_DEBUG_VM
 	{
@@ -4210,12 +4220,10 @@ static int memcg_stat_show(struct seq_file *m, void *v)
 			anon_cost += mz->lruvec.anon_cost;
 			file_cost += mz->lruvec.file_cost;
 		}
-		seq_printf(m, "anon_cost %lu\n", anon_cost);
-		seq_printf(m, "file_cost %lu\n", file_cost);
+		seq_buf_printf(s, "anon_cost %lu\n", anon_cost);
+		seq_buf_printf(s, "file_cost %lu\n", file_cost);
 	}
 #endif
-
-	return 0;
 }
 
 static u64 mem_cgroup_swappiness_read(struct cgroup_subsys_state *css,
@@ -5059,6 +5067,8 @@ static int mem_cgroup_slab_show(struct seq_file *m, void *p)
 }
 #endif
 
+static int memory_stat_show(struct seq_file *m, void *v);
+
 static struct cftype mem_cgroup_legacy_files[] = {
 	{
 		.name = "usage_in_bytes",
@@ -5091,7 +5101,7 @@ static struct cftype mem_cgroup_legacy_files[] = {
 	},
 	{
 		.name = "stat",
-		.seq_show = memcg_stat_show,
+		.seq_show = memory_stat_show,
 	},
 	{
 		.name = "force_empty",