psi: introduce psi monitor

Psi monitor aims to provide a low-latency short-term pressure detection
mechanism configurable by users.  It allows users to monitor psi metrics
growth and trigger events whenever a metric raises above user-defined
threshold within user-defined time window.

Time window and threshold are both expressed in usecs.  Multiple psi
resources with different thresholds and window sizes can be monitored
concurrently.

Psi monitors activate when system enters stall state for the monitored
psi metric and deactivate upon exit from the stall state.  While system
is in the stall state psi signal growth is monitored at a rate of 10
times per tracking window.  Min window size is 500ms, therefore the min
monitoring interval is 50ms.  Max window size is 10s with monitoring
interval of 1s.

When activated psi monitor stays active for at least the duration of one
tracking window to avoid repeated activations/deactivations when psi
signal is bouncing.

Notifications to the users are rate-limited to one per tracking window.

Link: http://lkml.kernel.org/r/20190319235619.260832-8-surenb@google.com
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Li Zefan <lizefan@huawei.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

kernel/cgroup/cgroup.c

@@ -3550,7 +3550,65 @@ static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v)
 {
 	return psi_show(seq, &seq_css(seq)->cgroup->psi, PSI_CPU);
 }
-#endif
+
+static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf,
+					  size_t nbytes, enum psi_res res)
+{
+	struct psi_trigger *new;
+	struct cgroup *cgrp;
+
+	cgrp = cgroup_kn_lock_live(of->kn, false);
+	if (!cgrp)
+		return -ENODEV;
+
+	cgroup_get(cgrp);
+	cgroup_kn_unlock(of->kn);
+
+	new = psi_trigger_create(&cgrp->psi, buf, nbytes, res);
+	if (IS_ERR(new)) {
+		cgroup_put(cgrp);
+		return PTR_ERR(new);
+	}
+
+	psi_trigger_replace(&of->priv, new);
+
+	cgroup_put(cgrp);
+
+	return nbytes;
+}
+
+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);
+}
+
+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);
+}
+
+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);
+}
+
+static __poll_t cgroup_pressure_poll(struct kernfs_open_file *of,
+					  poll_table *pt)
+{
+	return psi_trigger_poll(&of->priv, of->file, pt);
+}
+
+static void cgroup_pressure_release(struct kernfs_open_file *of)
+{
+	psi_trigger_replace(&of->priv, NULL);
+}
+#endif /* CONFIG_PSI */
 
 static int cgroup_freeze_show(struct seq_file *seq, void *v)
 {
@@ -4745,18 +4803,27 @@ static struct cftype cgroup_base_files[] = {
 		.name = "io.pressure",
 		.flags = CFTYPE_NOT_ON_ROOT,
 		.seq_show = cgroup_io_pressure_show,
+		.write = cgroup_io_pressure_write,
+		.poll = cgroup_pressure_poll,
+		.release = cgroup_pressure_release,
 	},
 	{
 		.name = "memory.pressure",
 		.flags = CFTYPE_NOT_ON_ROOT,
 		.seq_show = cgroup_memory_pressure_show,
+		.write = cgroup_memory_pressure_write,
+		.poll = cgroup_pressure_poll,
+		.release = cgroup_pressure_release,
 	},
 	{
 		.name = "cpu.pressure",
 		.flags = CFTYPE_NOT_ON_ROOT,
 		.seq_show = cgroup_cpu_pressure_show,
+		.write = cgroup_cpu_pressure_write,
+		.poll = cgroup_pressure_poll,
+		.release = cgroup_pressure_release,
 	},
-#endif
+#endif /* CONFIG_PSI */
 	{ }	/* terminate */
 };