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>

2 files changed, 88 insertions, 2 deletions

diff --git a/include/linux/psi.h b/include/linux/psi.h
index 7006008d5b72..af892c290116 100644
--- a/include/linux/psi.h
+++ b/include/linux/psi.h
@@ -4,6 +4,7 @@
 #include <linux/jump_label.h>
 #include <linux/psi_types.h>
 #include <linux/sched.h>
+#include <linux/poll.h>
 
 struct seq_file;
 struct css_set;
@@ -26,6 +27,13 @@ int psi_show(struct seq_file *s, struct psi_group *group, enum psi_res res);
 int psi_cgroup_alloc(struct cgroup *cgrp);
 void psi_cgroup_free(struct cgroup *cgrp);
 void cgroup_move_task(struct task_struct *p, struct css_set *to);
+
+struct psi_trigger *psi_trigger_create(struct psi_group *group,
+			char *buf, size_t nbytes, enum psi_res res);
+void psi_trigger_replace(void **trigger_ptr, struct psi_trigger *t);
+
+__poll_t psi_trigger_poll(void **trigger_ptr, struct file *file,
+			poll_table *wait);
 #endif
 
 #else /* CONFIG_PSI */
diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h
index 4d1c1f67be18..07aaf9b82241 100644
--- a/include/linux/psi_types.h
+++ b/include/linux/psi_types.h
@@ -1,8 +1,11 @@
 #ifndef _LINUX_PSI_TYPES_H
 #define _LINUX_PSI_TYPES_H
 
+#include <linux/kthread.h>
 #include <linux/seqlock.h>
 #include <linux/types.h>
+#include <linux/kref.h>
+#include <linux/wait.h>
 
 #ifdef CONFIG_PSI
 
@@ -44,6 +47,12 @@ enum psi_states {
 	NR_PSI_STATES = 6,
 };
 
+enum psi_aggregators {
+	PSI_AVGS = 0,
+	PSI_POLL,
+	NR_PSI_AGGREGATORS,
+};
+
 struct psi_group_cpu {
 	/* 1st cacheline updated by the scheduler */
 
@@ -65,7 +74,55 @@ struct psi_group_cpu {
 	/* 2nd cacheline updated by the aggregator */
 
 	/* Delta detection against the sampling buckets */
-	u32 times_prev[NR_PSI_STATES] ____cacheline_aligned_in_smp;
+	u32 times_prev[NR_PSI_AGGREGATORS][NR_PSI_STATES]
+			____cacheline_aligned_in_smp;
+};
+
+/* PSI growth tracking window */
+struct psi_window {
+	/* Window size in ns */
+	u64 size;
+
+	/* Start time of the current window in ns */
+	u64 start_time;
+
+	/* Value at the start of the window */
+	u64 start_value;
+
+	/* Value growth in the previous window */
+	u64 prev_growth;
+};
+
+struct psi_trigger {
+	/* PSI state being monitored by the trigger */
+	enum psi_states state;
+
+	/* User-spacified threshold in ns */
+	u64 threshold;
+
+	/* List node inside triggers list */
+	struct list_head node;
+
+	/* Backpointer needed during trigger destruction */
+	struct psi_group *group;
+
+	/* Wait queue for polling */
+	wait_queue_head_t event_wait;
+
+	/* Pending event flag */
+	int event;
+
+	/* Tracking window */
+	struct psi_window win;
+
+	/*
+	 * Time last event was generated. Used for rate-limiting
+	 * events to one per window
+	 */
+	u64 last_event_time;
+
+	/* Refcounting to prevent premature destruction */
+	struct kref refcount;
 };
 
 struct psi_group {
@@ -79,11 +136,32 @@ struct psi_group {
 	u64 avg_total[NR_PSI_STATES - 1];
 	u64 avg_last_update;
 	u64 avg_next_update;
+
+	/* Aggregator work control */
 	struct delayed_work avgs_work;
 
 	/* Total stall times and sampled pressure averages */
-	u64 total[NR_PSI_STATES - 1];
+	u64 total[NR_PSI_AGGREGATORS][NR_PSI_STATES - 1];
 	unsigned long avg[NR_PSI_STATES - 1][3];
+
+	/* Monitor work control */
+	atomic_t poll_scheduled;
+	struct kthread_worker __rcu *poll_kworker;
+	struct kthread_delayed_work poll_work;
+
+	/* Protects data used by the monitor */
+	struct mutex trigger_lock;
+
+	/* Configured polling triggers */
+	struct list_head triggers;
+	u32 nr_triggers[NR_PSI_STATES - 1];
+	u32 poll_states;
+	u64 poll_min_period;
+
+	/* Total stall times at the start of monitor activation */
+	u64 polling_total[NR_PSI_STATES - 1];
+	u64 polling_next_update;
+	u64 polling_until;
 };
 
 #else /* CONFIG_PSI */