sched/psi: Remove NR_ONCPU task accounting

We put all fields updated by the scheduler in the first cacheline of
struct psi_group_cpu for performance.

Since we want add another PSI_IRQ_FULL to track IRQ/SOFTIRQ pressure,
we need to reclaim space first. This patch remove NR_ONCPU task accounting
in struct psi_group_cpu, use one bit in state_mask to track instead.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Chengming Zhou <zhouchengming@bytedance.com>
Tested-by: Chengming Zhou <zhouchengming@bytedance.com>
Link: https://lore.kernel.org/r/20220825164111.29534-7-zhouchengming@bytedance.com

include/linux/psi_types.h

@@ -15,13 +15,6 @@ enum psi_task_count {
 	NR_IOWAIT,
 	NR_MEMSTALL,
 	NR_RUNNING,
-	/*
-	 * 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,
 	/*
 	 * For IO and CPU stalls the presence of running/oncpu tasks
 	 * in the domain means a partial rather than a full stall.
@@ -32,16 +25,18 @@ enum psi_task_count {
 	 * threads and memstall ones.
 	 */
 	NR_MEMSTALL_RUNNING,
-	NR_PSI_TASK_COUNTS = 5,
+	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)
 #define TSK_MEMSTALL_RUNNING	(1 << NR_MEMSTALL_RUNNING)
 
+/* Only one task can be scheduled, no corresponding task count */
+#define TSK_ONCPU	(1 << NR_PSI_TASK_COUNTS)
+
 /* Resources that workloads could be stalled on */
 enum psi_res {
 	PSI_IO,
@@ -68,6 +63,9 @@ enum psi_states {
 	NR_PSI_STATES = 7,
 };
 
+/* Use one bit in the state mask to track TSK_ONCPU */
+#define PSI_ONCPU	(1 << NR_PSI_STATES)
+
 enum psi_aggregators {
 	PSI_AVGS = 0,
 	PSI_POLL,

kernel/sched/psi.c

@@ -212,7 +212,7 @@ void __init psi_init(void)
 	group_init(&psi_system);
 }
 
-static bool test_state(unsigned int *tasks, enum psi_states state)
+static bool test_state(unsigned int *tasks, enum psi_states state, bool oncpu)
 {
 	switch (state) {
 	case PSI_IO_SOME:
@@ -225,9 +225,9 @@ static bool test_state(unsigned int *tasks, enum psi_states state)
 		return unlikely(tasks[NR_MEMSTALL] &&
 			tasks[NR_RUNNING] == tasks[NR_MEMSTALL_RUNNING]);
 	case PSI_CPU_SOME:
-		return unlikely(tasks[NR_RUNNING] > tasks[NR_ONCPU]);
+		return unlikely(tasks[NR_RUNNING] > oncpu);
 	case PSI_CPU_FULL:
-		return unlikely(tasks[NR_RUNNING] && !tasks[NR_ONCPU]);
+		return unlikely(tasks[NR_RUNNING] && !oncpu);
 	case PSI_NONIDLE:
 		return tasks[NR_IOWAIT] || tasks[NR_MEMSTALL] ||
 			tasks[NR_RUNNING];
@@ -689,9 +689,9 @@ static void psi_group_change(struct psi_group *group, int cpu,
 			     bool wake_clock)
 {
 	struct psi_group_cpu *groupc;
-	u32 state_mask = 0;
 	unsigned int t, m;
 	enum psi_states s;
+	u32 state_mask;
 
 	groupc = per_cpu_ptr(group->pcpu, cpu);
 
@@ -707,17 +707,36 @@ static void psi_group_change(struct psi_group *group, int cpu,
 
 	record_times(groupc, now);
 
+	/*
+	 * Start with TSK_ONCPU, which doesn't have a corresponding
+	 * task count - it's just a boolean flag directly encoded in
+	 * the state mask. Clear, set, or carry the current state if
+	 * no changes are requested.
+	 */
+	if (unlikely(clear & TSK_ONCPU)) {
+		state_mask = 0;
+		clear &= ~TSK_ONCPU;
+	} else if (unlikely(set & TSK_ONCPU)) {
+		state_mask = PSI_ONCPU;
+		set &= ~TSK_ONCPU;
+	} else {
+		state_mask = groupc->state_mask & PSI_ONCPU;
+	}
+
+	/*
+	 * The rest of the state mask is calculated based on the task
+	 * counts. Update those first, then construct the mask.
+	 */
 	for (t = 0, m = clear; m; m &= ~(1 << t), t++) {
 		if (!(m & (1 << t)))
 			continue;
 		if (groupc->tasks[t]) {
 			groupc->tasks[t]--;
 		} else if (!psi_bug) {
-			printk_deferred(KERN_ERR "psi: task underflow! cpu=%d t=%d tasks=[%u %u %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],
-					groupc->tasks[3], groupc->tasks[4],
+					groupc->tasks[3], clear, set);
-					clear, set);
 			psi_bug = 1;
 		}
 	}
@@ -726,9 +745,8 @@ static void psi_group_change(struct psi_group *group, int cpu,
 		if (set & (1 << t))
 			groupc->tasks[t]++;
 
-	/* Calculate state mask representing active states */
 	for (s = 0; s < NR_PSI_STATES; s++) {
-		if (test_state(groupc->tasks, s))
+		if (test_state(groupc->tasks, s, state_mask & PSI_ONCPU))
 			state_mask |= (1 << s);
 	}
 
@@ -740,7 +758,7 @@ static void psi_group_change(struct psi_group *group, int cpu,
 	 * task in a cgroup is in_memstall, the corresponding groupc
 	 * on that cpu is in PSI_MEM_FULL state.
 	 */
-	if (unlikely(groupc->tasks[NR_ONCPU] && cpu_curr(cpu)->in_memstall))
+	if (unlikely((state_mask & PSI_ONCPU) && cpu_curr(cpu)->in_memstall))
 		state_mask |= (1 << PSI_MEM_FULL);
 
 	groupc->state_mask = state_mask;
@@ -828,7 +846,8 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next,
 		 */
 		iter = NULL;
 		while ((group = iterate_groups(next, &iter))) {
-			if (per_cpu_ptr(group->pcpu, cpu)->tasks[NR_ONCPU]) {
+			if (per_cpu_ptr(group->pcpu, cpu)->state_mask &
+			    PSI_ONCPU) {
 				common = group;
 				break;
 			}