sched/psi: Cache parent psi_group to speed up group iteration

We use iterate_groups() to iterate each level psi_group to update
PSI stats, which is a very hot path.

In current code, iterate_groups() have to use multiple branches and
cgroup_parent() to get parent psi_group for each level, which is not
very efficient.

This patch cache parent psi_group in struct psi_group, only need to get
psi_group of task itself first, then just use group->parent to iterate.

Signed-off-by: Chengming Zhou <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Acked-by: Johannes Weiner <[email protected]>
Link: https://lore.kernel.org/r/[email protected]

Author: Chengming Zhou

include/linux/psi_types.h

@@ -151,6 +151,8 @@ struct psi_trigger {
 };
 
 struct psi_group {
+	struct psi_group *parent;
+
 	/* Protects data used by the aggregator */
 	struct mutex avgs_lock;
 

kernel/sched/psi.c

@@ -772,27 +772,12 @@ static void psi_group_change(struct psi_group *group, int cpu,
 		schedule_delayed_work(&group->avgs_work, PSI_FREQ);
 }
 
-static struct psi_group *iterate_groups(struct task_struct *task, void **iter)
+static inline struct psi_group *task_psi_group(struct task_struct *task)
 {
-	if (*iter == &psi_system)
-		return NULL;
-
 #ifdef CONFIG_CGROUPS
-	if (static_branch_likely(&psi_cgroups_enabled)) {
-		struct cgroup *cgroup = NULL;
-
-		if (!*iter)
-			cgroup = task->cgroups->dfl_cgrp;
-		else
-			cgroup = cgroup_parent(*iter);
-
-		if (cgroup && cgroup_parent(cgroup)) {
-			*iter = cgroup;
-			return cgroup_psi(cgroup);
-		}
-	}
+	if (static_branch_likely(&psi_cgroups_enabled))
+		return cgroup_psi(task_dfl_cgroup(task));
 #endif
-	*iter = &psi_system;
 	return &psi_system;
 }
 
@@ -815,7 +800,6 @@ void psi_task_change(struct task_struct *task, int clear, int set)
 {
 	int cpu = task_cpu(task);
 	struct psi_group *group;
-	void *iter = NULL;
 	u64 now;
 
 	if (!task->pid)
@@ -825,16 +809,17 @@ void psi_task_change(struct task_struct *task, int clear, int set)
 
 	now = cpu_clock(cpu);
 
-	while ((group = iterate_groups(task, &iter)))
+	group = task_psi_group(task);
+	do {
 		psi_group_change(group, cpu, clear, set, now, true);
+	} while ((group = group->parent));
 }
 
 void psi_task_switch(struct task_struct *prev, struct task_struct *next,
 		     bool sleep)
 {
 	struct psi_group *group, *common = NULL;
 	int cpu = task_cpu(prev);
-	void *iter;
 	u64 now = cpu_clock(cpu);
 
 	if (next->pid) {
@@ -844,16 +829,16 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next,
 		 * ancestors with @prev, those will already have @prev's
 		 * TSK_ONCPU bit set, and we can stop the iteration there.
 		 */
-		iter = NULL;
-		while ((group = iterate_groups(next, &iter))) {
+		group = task_psi_group(next);
+		do {
 			if (per_cpu_ptr(group->pcpu, cpu)->state_mask &
 			    PSI_ONCPU) {
 				common = group;
 				break;
 			}
 
 			psi_group_change(group, cpu, 0, TSK_ONCPU, now, true);
-		}
+		} while ((group = group->parent));
 	}
 
 	if (prev->pid) {
@@ -886,9 +871,12 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next,
 
 		psi_flags_change(prev, clear, set);
 
-		iter = NULL;
-		while ((group = iterate_groups(prev, &iter)) && group != common)
+		group = task_psi_group(prev);
+		do {
+			if (group == common)
+				break;
 			psi_group_change(group, cpu, clear, set, now, wake_clock);
+		} while ((group = group->parent));
 
 		/*
 		 * TSK_ONCPU is handled up to the common ancestor. If there are
@@ -898,7 +886,7 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next,
 		 */
 		if ((prev->psi_flags ^ next->psi_flags) & ~TSK_ONCPU) {
 			clear &= ~TSK_ONCPU;
-			for (; group; group = iterate_groups(prev, &iter))
+			for (; group; group = group->parent)
 				psi_group_change(group, cpu, clear, set, now, wake_clock);
 		}
 	}
@@ -908,7 +896,6 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next,
 void psi_account_irqtime(struct task_struct *task, u32 delta)
 {
 	int cpu = task_cpu(task);
-	void *iter = NULL;
 	struct psi_group *group;
 	struct psi_group_cpu *groupc;
 	u64 now;
@@ -918,7 +905,8 @@ void psi_account_irqtime(struct task_struct *task, u32 delta)
 
 	now = cpu_clock(cpu);
 
-	while ((group = iterate_groups(task, &iter))) {
+	group = task_psi_group(task);
+	do {
 		groupc = per_cpu_ptr(group->pcpu, cpu);
 
 		write_seqcount_begin(&groupc->seq);
@@ -930,7 +918,7 @@ void psi_account_irqtime(struct task_struct *task, u32 delta)
 
 		if (group->poll_states & (1 << PSI_IRQ_FULL))
 			psi_schedule_poll_work(group, 1);
-	}
+	} while ((group = group->parent));
 }
 #endif
 
@@ -1010,6 +998,7 @@ int psi_cgroup_alloc(struct cgroup *cgroup)
 		return -ENOMEM;
 	}
 	group_init(cgroup->psi);
+	cgroup->psi->parent = cgroup_psi(cgroup_parent(cgroup));
 	return 0;
 }