Merge tag 'sched-psi-2022-10-14' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull PSI updates from Ingo Molnar:

 - Various performance optimizations, resulting in a 4%-9% speedup in
   the mmtests/config-scheduler-perfpipe micro-benchmark.

 - New interface to turn PSI on/off on a per cgroup level.

* tag 'sched-psi-2022-10-14' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/psi: Per-cgroup PSI accounting disable/re-enable interface
  sched/psi: Cache parent psi_group to speed up group iteration
  sched/psi: Consolidate cgroup_psi()
  sched/psi: Add PSI_IRQ to track IRQ/SOFTIRQ pressure
  sched/psi: Remove NR_ONCPU task accounting
  sched/psi: Optimize task switch inside shared cgroups again
  sched/psi: Move private helpers to sched/stats.h
  sched/psi: Save percpu memory when !psi_cgroups_enabled
  sched/psi: Don't create cgroup PSI files when psi_disabled
  sched/psi: Fix periodic aggregation shut off

Documentation/admin-guide/cgroup-v2.rst

@@ -976,6 +976,29 @@ All cgroup core files are prefixed with "cgroup."
 	killing cgroups is a process directed operation, i.e. it affects
 	the whole thread-group.
 
+  cgroup.pressure
+	A read-write single value file that allowed values are "0" and "1".
+	The default is "1".
+
+	Writing "0" to the file will disable the cgroup PSI accounting.
+	Writing "1" to the file will re-enable the cgroup PSI accounting.
+
+	This control attribute is not hierarchical, so disable or enable PSI
+	accounting in a cgroup does not affect PSI accounting in descendants
+	and doesn't need pass enablement via ancestors from root.
+
+	The reason this control attribute exists is that PSI accounts stalls for
+	each cgroup separately and aggregates it at each level of the hierarchy.
+	This may cause non-negligible overhead for some workloads when under
+	deep level of the hierarchy, in which case this control attribute can
+	be used to disable PSI accounting in the non-leaf cgroups.
+
+  irq.pressure
+	A read-write nested-keyed file.
+
+	Shows pressure stall information for IRQ/SOFTIRQ. See
+	:ref:`Documentation/accounting/psi.rst <psi>` for details.
+
 Controllers
 ===========
 

include/linux/cgroup-defs.h

@@ -428,6 +428,9 @@ struct cgroup {
 	struct cgroup_file procs_file;	/* handle for "cgroup.procs" */
 	struct cgroup_file events_file;	/* handle for "cgroup.events" */
 
+	/* handles for "{cpu,memory,io,irq}.pressure" */
+	struct cgroup_file psi_files[NR_PSI_RESOURCES];
+
 	/*
 	 * The bitmask of subsystems enabled on the child cgroups.
 	 * ->subtree_control is the one configured through

include/linux/cgroup.h

@@ -682,11 +682,6 @@ static inline void pr_cont_cgroup_path(struct cgroup *cgrp)
 	pr_cont_kernfs_path(cgrp->kn);
 }
 
-static inline struct psi_group *cgroup_psi(struct cgroup *cgrp)
-{
-	return cgrp->psi;
-}
-
 bool cgroup_psi_enabled(void);
 
 static inline void cgroup_init_kthreadd(void)

include/linux/psi.h

@@ -7,6 +7,7 @@
 #include <linux/sched.h>
 #include <linux/poll.h>
 #include <linux/cgroup-defs.h>
+#include <linux/cgroup.h>
 
 struct seq_file;
 struct css_set;
@@ -18,10 +19,6 @@ extern struct psi_group psi_system;
 
 void psi_init(void);
 
-void psi_task_change(struct task_struct *task, int clear, int set);
-void psi_task_switch(struct task_struct *prev, struct task_struct *next,
-		     bool sleep);
-
 void psi_memstall_enter(unsigned long *flags);
 void psi_memstall_leave(unsigned long *flags);
 
@@ -34,9 +31,15 @@ __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file,
 			poll_table *wait);
 
 #ifdef CONFIG_CGROUPS
+static inline struct psi_group *cgroup_psi(struct cgroup *cgrp)
+{
+	return cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi;
+}
+
 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);
+void psi_cgroup_restart(struct psi_group *group);
 #endif
 
 #else /* CONFIG_PSI */
@@ -58,6 +61,7 @@ static inline void cgroup_move_task(struct task_struct *p, struct css_set *to)
 {
 	rcu_assign_pointer(p->cgroups, to);
 }
+static inline void psi_cgroup_restart(struct psi_group *group) {}
 #endif
 
 #endif /* CONFIG_PSI */

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.
@@ -32,22 +25,27 @@ 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,
 	PSI_MEM,
 	PSI_CPU,
-	NR_PSI_RESOURCES = 3,
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+	PSI_IRQ,
+#endif
+	NR_PSI_RESOURCES,
 };
 
 /*
@@ -63,11 +61,17 @@ enum psi_states {
 	PSI_MEM_FULL,
 	PSI_CPU_SOME,
 	PSI_CPU_FULL,
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+	PSI_IRQ_FULL,
+#endif
 	/* Only per-CPU, to weigh the CPU in the global average: */
 	PSI_NONIDLE,
-	NR_PSI_STATES = 7,
+	NR_PSI_STATES,
 };
 
+/* 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,
@@ -147,6 +151,9 @@ struct psi_trigger {
 };
 
 struct psi_group {
+	struct psi_group *parent;
+	bool enabled;
+
 	/* Protects data used by the aggregator */
 	struct mutex avgs_lock;
 
@@ -188,6 +195,8 @@ struct psi_group {
 
 #else /* CONFIG_PSI */
 
+#define NR_PSI_RESOURCES	0
+
 struct psi_group { };
 
 #endif /* CONFIG_PSI */

kernel/cgroup/cgroup.c

@@ -3698,27 +3698,27 @@ static int cpu_stat_show(struct seq_file *seq, void *v)
 static int cgroup_io_pressure_show(struct seq_file *seq, void *v)
 {
 	struct cgroup *cgrp = seq_css(seq)->cgroup;
-	struct psi_group *psi = cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi;
+	struct psi_group *psi = cgroup_psi(cgrp);
 
 	return psi_show(seq, psi, PSI_IO);
 }
 static int cgroup_memory_pressure_show(struct seq_file *seq, void *v)
 {
 	struct cgroup *cgrp = seq_css(seq)->cgroup;
-	struct psi_group *psi = cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi;
+	struct psi_group *psi = cgroup_psi(cgrp);
 
 	return psi_show(seq, psi, PSI_MEM);
 }
 static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v)
 {
 	struct cgroup *cgrp = seq_css(seq)->cgroup;
-	struct psi_group *psi = cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi;
+	struct psi_group *psi = cgroup_psi(cgrp);
 
 	return psi_show(seq, psi, PSI_CPU);
 }
 
-static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf,
-					  size_t nbytes, enum psi_res res)
+static ssize_t pressure_write(struct kernfs_open_file *of, char *buf,
+			      size_t nbytes, enum psi_res res)
 {
 	struct cgroup_file_ctx *ctx = of->priv;
 	struct psi_trigger *new;
@@ -3738,7 +3738,7 @@ static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf,
 		return -EBUSY;
 	}
 
-	psi = cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi;
+	psi = cgroup_psi(cgrp);
 	new = psi_trigger_create(psi, buf, res);
 	if (IS_ERR(new)) {
 		cgroup_put(cgrp);
@@ -3755,21 +3755,86 @@ 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);
+	return 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);
+	return 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);
+	return pressure_write(of, buf, nbytes, PSI_CPU);
+}
+
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+static int cgroup_irq_pressure_show(struct seq_file *seq, void *v)
+{
+	struct cgroup *cgrp = seq_css(seq)->cgroup;
+	struct psi_group *psi = cgroup_psi(cgrp);
+
+	return psi_show(seq, psi, PSI_IRQ);
+}
+
+static ssize_t cgroup_irq_pressure_write(struct kernfs_open_file *of,
+					 char *buf, size_t nbytes,
+					 loff_t off)
+{
+	return pressure_write(of, buf, nbytes, PSI_IRQ);
+}
+#endif
+
+static int cgroup_pressure_show(struct seq_file *seq, void *v)
+{
+	struct cgroup *cgrp = seq_css(seq)->cgroup;
+	struct psi_group *psi = cgroup_psi(cgrp);
+
+	seq_printf(seq, "%d\n", psi->enabled);
+
+	return 0;
+}
+
+static ssize_t cgroup_pressure_write(struct kernfs_open_file *of,
+				     char *buf, size_t nbytes,
+				     loff_t off)
+{
+	ssize_t ret;
+	int enable;
+	struct cgroup *cgrp;
+	struct psi_group *psi;
+
+	ret = kstrtoint(strstrip(buf), 0, &enable);
+	if (ret)
+		return ret;
+
+	if (enable < 0 || enable > 1)
+		return -ERANGE;
+
+	cgrp = cgroup_kn_lock_live(of->kn, false);
+	if (!cgrp)
+		return -ENOENT;
+
+	psi = cgroup_psi(cgrp);
+	if (psi->enabled != enable) {
+		int i;
+
+		/* show or hide {cpu,memory,io,irq}.pressure files */
+		for (i = 0; i < NR_PSI_RESOURCES; i++)
+			cgroup_file_show(&cgrp->psi_files[i], enable);
+
+		psi->enabled = enable;
+		if (enable)
+			psi_cgroup_restart(psi);
+	}
+
+	cgroup_kn_unlock(of->kn);
+
+	return nbytes;
 }
 
 static __poll_t cgroup_pressure_poll(struct kernfs_open_file *of,
@@ -3789,6 +3854,9 @@ static void cgroup_pressure_release(struct kernfs_open_file *of)
 
 bool cgroup_psi_enabled(void)
 {
+	if (static_branch_likely(&psi_disabled))
+		return false;
+
 	return (cgroup_feature_disable_mask & (1 << OPT_FEATURE_PRESSURE)) == 0;
 }
 
@@ -5175,6 +5243,7 @@ static struct cftype cgroup_psi_files[] = {
 #ifdef CONFIG_PSI
 	{
 		.name = "io.pressure",
+		.file_offset = offsetof(struct cgroup, psi_files[PSI_IO]),
 		.seq_show = cgroup_io_pressure_show,
 		.write = cgroup_io_pressure_write,
 		.poll = cgroup_pressure_poll,
@@ -5182,6 +5251,7 @@ static struct cftype cgroup_psi_files[] = {
 	},
 	{
 		.name = "memory.pressure",
+		.file_offset = offsetof(struct cgroup, psi_files[PSI_MEM]),
 		.seq_show = cgroup_memory_pressure_show,
 		.write = cgroup_memory_pressure_write,
 		.poll = cgroup_pressure_poll,
@@ -5189,11 +5259,27 @@ static struct cftype cgroup_psi_files[] = {
 	},
 	{
 		.name = "cpu.pressure",
+		.file_offset = offsetof(struct cgroup, psi_files[PSI_CPU]),
 		.seq_show = cgroup_cpu_pressure_show,
 		.write = cgroup_cpu_pressure_write,
 		.poll = cgroup_pressure_poll,
 		.release = cgroup_pressure_release,
 	},
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+	{
+		.name = "irq.pressure",
+		.file_offset = offsetof(struct cgroup, psi_files[PSI_IRQ]),
+		.seq_show = cgroup_irq_pressure_show,
+		.write = cgroup_irq_pressure_write,
+		.poll = cgroup_pressure_poll,
+		.release = cgroup_pressure_release,
+	},
+#endif
+	{
+		.name = "cgroup.pressure",
+		.seq_show = cgroup_pressure_show,
+		.write = cgroup_pressure_write,
+	},
 #endif /* CONFIG_PSI */
 	{ }	/* terminate */
 };

kernel/sched/core.c

@@ -701,6 +701,7 @@ static void update_rq_clock_task(struct rq *rq, s64 delta)
 
 	rq->prev_irq_time += irq_delta;
 	delta -= irq_delta;
+	psi_account_irqtime(rq->curr, irq_delta);
 #endif
 #ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
 	if (static_key_false((&paravirt_steal_rq_enabled))) {

kernel/sched/stats.h

@@ -107,6 +107,11 @@ __schedstats_from_se(struct sched_entity *se)
 }
 
 #ifdef CONFIG_PSI
+void psi_task_change(struct task_struct *task, int clear, int set);
+void psi_task_switch(struct task_struct *prev, struct task_struct *next,
+		     bool sleep);
+void psi_account_irqtime(struct task_struct *task, u32 delta);
+
 /*
  * PSI tracks state that persists across sleeps, such as iowaits and
  * memory stalls. As a result, it has to distinguish between sleeps,
@@ -201,6 +206,7 @@ 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_account_irqtime(struct task_struct *task, u32 delta) {}
 #endif /* CONFIG_PSI */
 
 #ifdef CONFIG_SCHED_INFO