[PATCH] psi: fix cpu.pressure for cpu.max and competing cgroups

[Johannes Weiner]

For simplicity, cpu pressure is defined as having more than one
runnable task on a given CPU. This works on the system-level, but it
has limitations in a cgrouped reality: When cpu.max is in use, it
doesn't capture the time in which a task is not executing on the CPU
due to throttling. Likewise, it doesn't capture the time in which a
competing cgroup is occupying the CPU - meaning it only reflects
cgroup-internal competitive pressure, not outside pressure.

Enable tracking of currently executing tasks, and then change the
definition of cpu pressure in a cgroup from

	NR_RUNNING > 1

to

	NR_RUNNING > ON_CPU

which will capture the effects of cpu.max as well as competition from
outside the cgroup.

After this patch, a cgroup running `stress -c 1` with a cpu.max
setting of 5000 10000 shows ~50% continuous CPU pressure.

Signed-off-by: Johannes Weiner <hannes@xxxxxxxxxxx>
---
 include/linux/psi_types.h | 10 +++++++++-
 kernel/sched/core.c       |  2 ++
 kernel/sched/psi.c        | 12 +++++++-----
 kernel/sched/stats.h      | 28 ++++++++++++++++++++++++++++
 4 files changed, 46 insertions(+), 6 deletions(-)

diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h
index 07aaf9b82241..4b7258495a04 100644
--- a/include/linux/psi_types.h
+++ b/include/linux/psi_types.h
@@ -14,13 +14,21 @@ enum psi_task_count {
 	NR_IOWAIT,
 	NR_MEMSTALL,
 	NR_RUNNING,
-	NR_PSI_TASK_COUNTS = 3,
+	/*
+	 * This can't have values other than 0 or 1 and could be
+	 * implemented as a bit flag. But for now we still have room
+	 * in the first cacheline of psi_group_cpu, and this way we
+	 * don't have to special case any state tracking for it.
+	 */
+	NR_ONCPU,
+	NR_PSI_TASK_COUNTS = 4,
 };
 
 /* Task state bitmasks */
 #define TSK_IOWAIT	(1 << NR_IOWAIT)
 #define TSK_MEMSTALL	(1 << NR_MEMSTALL)
 #define TSK_RUNNING	(1 << NR_RUNNING)
+#define TSK_ONCPU	(1 << NR_ONCPU)
 
 /* Resources that workloads could be stalled on */
 enum psi_res {
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 44123b4d14e8..9296e0de7b72 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4072,6 +4072,8 @@ static void __sched notrace __schedule(bool preempt)
 		 */
 		++*switch_count;
 
+		psi_sched_switch(prev, next, !task_on_rq_queued(prev));
+
 		trace_sched_switch(preempt, prev, next);
 
 		/* Also unlocks the rq: */
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index 517e3719027e..fad91da54aab 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -224,7 +224,7 @@ static bool test_state(unsigned int *tasks, enum psi_states state)
 	case PSI_MEM_FULL:
 		return tasks[NR_MEMSTALL] && !tasks[NR_RUNNING];
 	case PSI_CPU_SOME:
-		return tasks[NR_RUNNING] > 1;
+		return tasks[NR_RUNNING] > tasks[NR_ONCPU];
 	case PSI_NONIDLE:
 		return tasks[NR_IOWAIT] || tasks[NR_MEMSTALL] ||
 			tasks[NR_RUNNING];
@@ -694,10 +694,10 @@ static u32 psi_group_change(struct psi_group *group, int cpu,
 		if (!(m & (1 << t)))
 			continue;
 		if (groupc->tasks[t] == 0 && !psi_bug) {
-			printk_deferred(KERN_ERR "psi: task underflow! cpu=%d t=%d tasks=[%u %u %u] clear=%x set=%x\n",
+			printk_deferred(KERN_ERR "psi: task underflow! cpu=%d t=%d tasks=[%u %u %u %u] clear=%x set=%x\n",
 					cpu, t, groupc->tasks[0],
 					groupc->tasks[1], groupc->tasks[2],
-					clear, set);
+					groupc->tasks[3], clear, set);
 			psi_bug = 1;
 		}
 		groupc->tasks[t]--;
@@ -915,9 +915,11 @@ void cgroup_move_task(struct task_struct *task, struct css_set *to)
 
 	rq = task_rq_lock(task, &rf);
 
-	if (task_on_rq_queued(task))
+	if (task_on_rq_queued(task)) {
 		task_flags = TSK_RUNNING;
-	else if (task->in_iowait)
+		if (task_current(rq, task))
+			task_flags |= TSK_ONCPU;
+	} else if (task->in_iowait)
 		task_flags = TSK_IOWAIT;
 
 	if (task->flags & PF_MEMSTALL)
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index ba683fe81a6e..6ff0ac1a803f 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -93,6 +93,14 @@ static inline void psi_dequeue(struct task_struct *p, bool sleep)
 		if (p->flags & PF_MEMSTALL)
 			clear |= TSK_MEMSTALL;
 	} else {
+		/*
+		 * When a task sleeps, schedule() dequeues it before
+		 * switching to the next one. Merge the clearing of
+		 * TSK_RUNNING and TSK_ONCPU to save an unnecessary
+		 * psi_task_change() call in psi_sched_switch().
+		 */
+		clear |= TSK_ONCPU;
+
 		if (p->in_iowait)
 			set |= TSK_IOWAIT;
 	}
@@ -126,6 +134,23 @@ static inline void psi_ttwu_dequeue(struct task_struct *p)
 	}
 }
 
+static inline void psi_sched_switch(struct task_struct *prev,
+				    struct task_struct *next,
+				    bool sleep)
+{
+	if (static_branch_likely(&psi_disabled))
+		return;
+
+	/*
+	 * Clear the TSK_ONCPU state if the task was preempted. If
+	 * it's a voluntary sleep, dequeue will have taken care of it.
+	 */
+	if (!sleep)
+		psi_task_change(prev, TSK_ONCPU, 0);
+
+	psi_task_change(next, 0, TSK_ONCPU);
+}
+
 static inline void psi_task_tick(struct rq *rq)
 {
 	if (static_branch_likely(&psi_disabled))
@@ -138,6 +163,9 @@ static inline void psi_task_tick(struct rq *rq)
 static inline void psi_enqueue(struct task_struct *p, bool wakeup) {}
 static inline void psi_dequeue(struct task_struct *p, bool sleep) {}
 static inline void psi_ttwu_dequeue(struct task_struct *p) {}
+static inline void psi_sched_switch(struct task_struct *prev,
+				    struct task_struct *next,
+				    bool sleep) {}
 static inline void psi_task_tick(struct rq *rq) {}
 #endif /* CONFIG_PSI */
 
-- 
2.24.1