[PATCH] cgroup: add cpu.stat.percpu for per-CPU cgroup stats

[Willy Barro Raffel <willybar@amazon.com>]

Expose per-CPU subtree_bstat via a new cgroupfs file cpu.stat.percpu.
Each line shows one CPU cumulative stats in io.stat-style key=value
format:

  cpu0 usage_usec=123 user_usec=45 system_usec=78 nice_usec=0
  cpu1 usage_usec=456 user_usec=123 system_usec=333 nice_usec=0

This completes the interface left as a TODO in commit 7716f383a583
("Merge tag 'cgroup-for-6.6' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup")
which added per-CPU subtree_bstat but only exposed it via BPF/drgn.

Signed-off-by: Willy Barro Raffel <willybar@amazon.com>
Reviewed-by: Justinien Bouron <jbouron@amazon.com>
Reviewed-by: Gunnar Kudrjavets <gunnarku@amazon.com>
---
 kernel/cgroup/cgroup-internal.h |  1 +
 kernel/cgroup/cgroup.c          | 10 +++++++++
 kernel/cgroup/rstat.c           | 36 +++++++++++++++++++++++++++++++++
 3 files changed, 47 insertions(+)

diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h
index 3bfe37693d68..28aff03975f2 100644
--- a/kernel/cgroup/cgroup-internal.h
+++ b/kernel/cgroup/cgroup-internal.h
@@ -277,6 +277,7 @@ int css_rstat_init(struct cgroup_subsys_state *css);
 void css_rstat_exit(struct cgroup_subsys_state *css);
 int ss_rstat_init(struct cgroup_subsys *ss);
 void cgroup_base_stat_cputime_show(struct seq_file *seq);
+void cgroup_base_stat_cputime_show_percpu(struct seq_file *seq);
 
 /*
  * namespace.c
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index be1d71dda317..652fae15d7c5 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -3968,6 +3968,12 @@ static int cpu_local_stat_show(struct seq_file *seq, void *v)
 	return ret;
 }
 
+
+static int cpu_percpu_stat_show(struct seq_file *seq, void *v)
+{
+	cgroup_base_stat_cputime_show_percpu(seq);
+	return 0;
+}
 #ifdef CONFIG_PSI
 static int cgroup_io_pressure_show(struct seq_file *seq, void *v)
 {
@@ -5499,6 +5505,10 @@ static struct cftype cgroup_base_files[] = {
 		.name = "cpu.stat.local",
 		.seq_show = cpu_local_stat_show,
 	},
+	{
+		.name = "cpu.stat.percpu",
+		.seq_show = cpu_percpu_stat_show,
+	},
 	{ }	/* terminate */
 };
 
diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index 150e5871e66f..f1aaed87180c 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -743,6 +743,42 @@ void cgroup_base_stat_cputime_show(struct seq_file *seq)
 	cgroup_force_idle_show(seq, &bstat);
 }
 
+
+void cgroup_base_stat_cputime_show_percpu(struct seq_file *seq)
+{
+	struct cgroup *cgrp = seq_css(seq)->cgroup;
+	int cpu;
+
+	css_rstat_flush(&cgrp->self);
+
+	for_each_possible_cpu(cpu) {
+		struct cgroup_rstat_base_cpu *rstatbc;
+		struct cgroup_base_stat bstat;
+		unsigned int seq_cnt;
+
+		/* Reacquire for each CPU to avoid disabling IRQs too long */
+		__css_rstat_lock(&cgrp->self, cpu);
+		rstatbc = cgroup_rstat_base_cpu(cgrp, cpu);
+		do {
+			seq_cnt = __u64_stats_fetch_begin(&rstatbc->bsync);
+			bstat = rstatbc->subtree_bstat;
+		} while (__u64_stats_fetch_retry(&rstatbc->bsync, seq_cnt));
+		__css_rstat_unlock(&cgrp->self, cpu);
+
+		do_div(bstat.cputime.sum_exec_runtime, NSEC_PER_USEC);
+		do_div(bstat.cputime.utime, NSEC_PER_USEC);
+		do_div(bstat.cputime.stime, NSEC_PER_USEC);
+		do_div(bstat.ntime, NSEC_PER_USEC);
+
+		seq_printf(seq, "cpu%d usage_usec=%llu user_usec=%llu system_usec=%llu nice_usec=%llu\n",
+			   cpu,
+			   bstat.cputime.sum_exec_runtime,
+			   bstat.cputime.utime,
+			   bstat.cputime.stime,
+			   bstat.ntime);
+	}
+}
+
 /* Add bpf kfuncs for css_rstat_updated() and css_rstat_flush() */
 BTF_KFUNCS_START(bpf_rstat_kfunc_ids)
 BTF_ID_FLAGS(func, css_rstat_updated)
-- 
2.50.1 (Apple Git-155)