sched/psi: Per-cgroup PSI accounting disable/re-enable interface

PSI accounts stalls for each cgroup separately and aggregates it
at each level of the hierarchy. This may cause non-negligible overhead
for some workloads when under deep level of the hierarchy.

commit 3958e2d0c34e ("cgroup: make per-cgroup pressure stall tracking configurable")
make PSI to skip per-cgroup stall accounting, only account system-wide
to avoid this each level overhead.

But for our use case, we also want leaf cgroup PSI stats accounted for
userspace adjustment on that cgroup, apart from only system-wide adjustment.

So this patch introduce a per-cgroup PSI accounting disable/re-enable
interface "cgroup.pressure", which is a read-write single value file that
allowed values are "0" and "1", the defaults is "1" so per-cgroup
PSI stats is enabled by default.

Implementation details:

It should be relatively straight-forward to disable and re-enable
state aggregation, time tracking, averaging on a per-cgroup level,
if we can live with losing history from while it was disabled.
I.e. the avgs will restart from 0, total= will have gaps.

But it's hard or complex to stop/restart groupc->tasks[] updates,
which is not implemented in this patch. So we always update
groupc->tasks[] and PSI_ONCPU bit in psi_group_change() even when
the cgroup PSI stats is disabled.

Suggested-by: Johannes Weiner <hannes@cmpxchg.org>
Suggested-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Link: https://lkml.kernel.org/r/20220907090332.2078-1-zhouchengming@bytedance.com

1 files changed, 64 insertions, 6 deletions

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 772b35d65d1f05..fa1cf836b66a36 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -3708,8 +3708,8 @@ static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v)
 	return psi_show(seq, psi, PSI_CPU);
 }
 
-static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf,
-					  size_t nbytes, enum psi_res res)
+static ssize_t pressure_write(struct kernfs_open_file *of, char *buf,
+			      size_t nbytes, enum psi_res res)
 {
 	struct cgroup_file_ctx *ctx = of->priv;
 	struct psi_trigger *new;
@@ -3746,21 +3746,21 @@ static ssize_t cgroup_io_pressure_write(struct kernfs_open_file *of,
 					  char *buf, size_t nbytes,
 					  loff_t off)
 {
-	return cgroup_pressure_write(of, buf, nbytes, PSI_IO);
+	return pressure_write(of, buf, nbytes, PSI_IO);
 }
 
 static ssize_t cgroup_memory_pressure_write(struct kernfs_open_file *of,
 					  char *buf, size_t nbytes,
 					  loff_t off)
 {
-	return cgroup_pressure_write(of, buf, nbytes, PSI_MEM);
+	return pressure_write(of, buf, nbytes, PSI_MEM);
 }
 
 static ssize_t cgroup_cpu_pressure_write(struct kernfs_open_file *of,
 					  char *buf, size_t nbytes,
 					  loff_t off)
 {
-	return cgroup_pressure_write(of, buf, nbytes, PSI_CPU);
+	return pressure_write(of, buf, nbytes, PSI_CPU);
 }
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
@@ -3776,10 +3776,58 @@ static ssize_t cgroup_irq_pressure_write(struct kernfs_open_file *of,
 					 char *buf, size_t nbytes,
 					 loff_t off)
 {
-	return cgroup_pressure_write(of, buf, nbytes, PSI_IRQ);
+	return pressure_write(of, buf, nbytes, PSI_IRQ);
 }
 #endif
 
+static int cgroup_pressure_show(struct seq_file *seq, void *v)
+{
+	struct cgroup *cgrp = seq_css(seq)->cgroup;
+	struct psi_group *psi = cgroup_psi(cgrp);
+
+	seq_printf(seq, "%d\n", psi->enabled);
+
+	return 0;
+}
+
+static ssize_t cgroup_pressure_write(struct kernfs_open_file *of,
+				     char *buf, size_t nbytes,
+				     loff_t off)
+{
+	ssize_t ret;
+	int enable;
+	struct cgroup *cgrp;
+	struct psi_group *psi;
+
+	ret = kstrtoint(strstrip(buf), 0, &enable);
+	if (ret)
+		return ret;
+
+	if (enable < 0 || enable > 1)
+		return -ERANGE;
+
+	cgrp = cgroup_kn_lock_live(of->kn, false);
+	if (!cgrp)
+		return -ENOENT;
+
+	psi = cgroup_psi(cgrp);
+	if (psi->enabled != enable) {
+		int i;
+
+		/* show or hide {cpu,memory,io,irq}.pressure files */
+		for (i = 0; i < NR_PSI_RESOURCES; i++)
+			cgroup_file_show(&cgrp->psi_files[i], enable);
+
+		psi->enabled = enable;
+		if (enable)
+			psi_cgroup_restart(psi);
+	}
+
+	cgroup_kn_unlock(of->kn);
+
+	return nbytes;
+}
+
 static __poll_t cgroup_pressure_poll(struct kernfs_open_file *of,
 					  poll_table *pt)
 {
@@ -5175,6 +5223,7 @@ static struct cftype cgroup_base_files[] = {
 	{
 		.name = "io.pressure",
 		.flags = CFTYPE_PRESSURE,
+		.file_offset = offsetof(struct cgroup, psi_files[PSI_IO]),
 		.seq_show = cgroup_io_pressure_show,
 		.write = cgroup_io_pressure_write,
 		.poll = cgroup_pressure_poll,
@@ -5183,6 +5232,7 @@ static struct cftype cgroup_base_files[] = {
 	{
 		.name = "memory.pressure",
 		.flags = CFTYPE_PRESSURE,
+		.file_offset = offsetof(struct cgroup, psi_files[PSI_MEM]),
 		.seq_show = cgroup_memory_pressure_show,
 		.write = cgroup_memory_pressure_write,
 		.poll = cgroup_pressure_poll,
@@ -5191,6 +5241,7 @@ static struct cftype cgroup_base_files[] = {
 	{
 		.name = "cpu.pressure",
 		.flags = CFTYPE_PRESSURE,
+		.file_offset = offsetof(struct cgroup, psi_files[PSI_CPU]),
 		.seq_show = cgroup_cpu_pressure_show,
 		.write = cgroup_cpu_pressure_write,
 		.poll = cgroup_pressure_poll,
@@ -5200,12 +5251,19 @@ static struct cftype cgroup_base_files[] = {
 	{
 		.name = "irq.pressure",
 		.flags = CFTYPE_PRESSURE,
+		.file_offset = offsetof(struct cgroup, psi_files[PSI_IRQ]),
 		.seq_show = cgroup_irq_pressure_show,
 		.write = cgroup_irq_pressure_write,
 		.poll = cgroup_pressure_poll,
 		.release = cgroup_pressure_release,
 	},
 #endif
+	{
+		.name = "cgroup.pressure",
+		.flags = CFTYPE_PRESSURE,
+		.seq_show = cgroup_pressure_show,
+		.write = cgroup_pressure_write,
+	},
 #endif /* CONFIG_PSI */
 	{ }	/* terminate */
 };