[RFC PATCH] memcg: introduce kfuncs for fetching memcg stats

[JP Kobryn <inwardvessel@gmail.com>]

The kernel has to perform a significant amount of the work when a user mode
program reads the memory.stat file of a cgroup. Aside from flushing stats,
there is overhead in the string formatting that is done for each stat. Some
perf data is shown below from a program that reads memory.stat 1M times:

26.75%  a.out [kernel.kallsyms] [k] vsnprintf
19.88%  a.out [kernel.kallsyms] [k] format_decode
12.11%  a.out [kernel.kallsyms] [k] number
11.72%  a.out [kernel.kallsyms] [k] string
 8.46%  a.out [kernel.kallsyms] [k] strlen
 4.22%  a.out [kernel.kallsyms] [k] seq_buf_printf
 2.79%  a.out [kernel.kallsyms] [k] memory_stat_format
 1.49%  a.out [kernel.kallsyms] [k] put_dec_trunc8
 1.45%  a.out [kernel.kallsyms] [k] widen_string
 1.01%  a.out [kernel.kallsyms] [k] memcpy_orig

As an alternative to reading memory.stat, introduce new kfuncs to allow
fetching specific memcg stats from within bpf iter/cgroup-based programs.
Reading stats in this manner avoids the overhead of the string formatting
shown above.

Signed-off-by: JP Kobryn <inwardvessel@gmail.com>
---
 mm/memcontrol.c | 67 +++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 67 insertions(+)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 8dd7fbed5a94..aa22dc6f47ee 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -870,6 +870,73 @@ unsigned long memcg_events_local(struct mem_cgroup *memcg, int event)
 }
 #endif
 
+static inline struct mem_cgroup *mem_cgroup_from_cgroup(struct cgroup *cgrp)
+{
+	return cgrp ? mem_cgroup_from_css(cgrp->subsys[memory_cgrp_id]) : NULL;
+}
+
+__bpf_kfunc static void cgroup_flush_memcg_stats(struct cgroup *cgrp)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_cgroup(cgrp);
+
+	if (!memcg)
+		return;
+
+	mem_cgroup_flush_stats(memcg);
+}
+
+__bpf_kfunc static unsigned long node_stat_fetch(struct cgroup *cgrp,
+		enum node_stat_item item)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_cgroup(cgrp);
+
+	if (!memcg)
+		return 0;
+
+	return memcg_page_state_output(memcg, item);
+}
+
+__bpf_kfunc static unsigned long memcg_stat_fetch(struct cgroup *cgrp,
+		enum memcg_stat_item item)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_cgroup(cgrp);
+
+	if (!memcg)
+		return 0;
+
+	return memcg_page_state_output(memcg, item);
+}
+
+__bpf_kfunc static unsigned long vm_event_fetch(struct cgroup *cgrp,
+		enum vm_event_item item)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_cgroup(cgrp);
+
+	if (!memcg)
+		return 0;
+
+	return memcg_events(memcg, item);
+}
+
+BTF_KFUNCS_START(bpf_memcontrol_kfunc_ids)
+BTF_ID_FLAGS(func, cgroup_flush_memcg_stats)
+BTF_ID_FLAGS(func, node_stat_fetch)
+BTF_ID_FLAGS(func, memcg_stat_fetch)
+BTF_ID_FLAGS(func, vm_event_fetch)
+BTF_KFUNCS_END(bpf_memcontrol_kfunc_ids)
+
+static const struct btf_kfunc_id_set bpf_memcontrol_kfunc_set = {
+	.owner          = THIS_MODULE,
+	.set            = &bpf_memcontrol_kfunc_ids,
+};
+
+static int __init bpf_memcontrol_kfunc_init(void)
+{
+	return register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING,
+					 &bpf_memcontrol_kfunc_set);
+}
+late_initcall(bpf_memcontrol_kfunc_init);
+
 struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
 {
 	/*
-- 
2.47.3