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

bd9a3dba · Linus Torvalds <[email protected]> · 2022-10-14 13:03:00 -07:00

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

Commit: bd9a3dba185ce6701b41f0341470d3f53bbbbaed
Parents: 1df046ab · 34f26a15

Merge commit. Changes below are compared with the first parent: 1df046ab.

Changes

9 files changed · +362 −103

File	Status	Add	Del	Content
Documentation/admin-guide/cgroup-v2.rst	modified	+23	−0	View file
include/linux/cgroup-defs.h	modified	+3	−0	View file
include/linux/cgroup.h	modified	+0	−5	View file
include/linux/psi.h	modified	+8	−4	View file
include/linux/psi_types.h	modified	+20	−11	View file
kernel/cgroup/cgroup.c	modified	+95	−9	View file
kernel/sched/core.c	modified	+1	−0	View file
kernel/sched/psi.c	modified	+206	−74	View file
kernel/sched/stats.h	modified	+6	−0	View file

Only the first 600 diff lines are shown. Download the complete patch.

Documentation/admin-guide/cgroup-v2.rst

View file

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index 7bcfb38..dc254a3 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/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

View file

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 8f481d1..6e01f10 100644
--- a/include/linux/cgroup-defs.h
+++ b/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

View file

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 23b102b..f2a9f22 100644
--- a/include/linux/cgroup.h
+++ b/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

View file

diff --git a/include/linux/psi.h b/include/linux/psi.h
index dd74411..b029a84 100644
--- a/include/linux/psi.h
+++ b/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

View file

diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h
index c7fe7c0..6e43727 100644
--- a/include/linux/psi_types.h
+++ b/include/linux/psi_types.h
@@ -16,13 +16,6 @@ enum psi_task_count {
 	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.
 	 * For memory it's not so simple because of page reclaimers:
@@ -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

View file

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 764bdd5..7f48667 100644
--- a/kernel/cgroup/cgroup.c
+++ b/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

View file

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e4ce124..5800b06 100644
--- a/kernel/sched/core.c
+++ b/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/psi.c

View file

diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index 7f60300..ee2ecc0 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -181,6 +181,7 @@ static void group_init(struct psi_group *group)
 {
 	int cpu;
 
+	group->enabled = true;
 	for_each_possible_cpu(cpu)
 		seqcount_init(&per_cpu_ptr(group->pcpu, cpu)->seq);
 	group->avg_last_update = sched_clock();
@@ -201,6 +202,7 @@ void __init psi_init(void)
 {
 	if (!psi_enable) {
 		static_branch_enable(&psi_disabled);
+		static_branch_disable(&psi_cgroups_enabled);
 		return;
 	}
 
@@ -211,7 +213,7 @@ 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:
@@ -224,9 +226,9 @@ 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];
@@ -688,35 +690,53 @@ 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);
 
 	/*
-	 * First we assess the aggregate resource states this CPU's
-	 * tasks have been in since the last change, and account any
-	 * SOME and FULL time these may have resulted in.
-	 *
-	 * Then we update the task counts according to the state
+	 * First we update the task counts according to the state
 	 * change requested through the @clear and @set bits.
+	 *
+	 * Then if the cgroup PSI stats accounting enabled, we
+	 * assess the aggregate resource states this CPU's tasks
+	 * have been in since the last change, and account any
+	 * SOME and FULL time these may have resulted in.
 	 */
 	write_seqcount_begin(&groupc->seq);
 
-	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],
-					clear, set);
+					groupc->tasks[3], clear, set);
 			psi_bug = 1;
 		}
 	}
@@ -725,9 +745,25 @@ static void psi_group_change(struct psi_group *group, int cpu,
 		if (set & (1 << t))
 			groupc->tasks[t]++;
 
-	/* Calculate state mask representing active states */
+	if (!group->enabled) {
+		/*
+		 * On the first group change after disabling PSI, conclude
+		 * the current state and flush its time. This is unlikely
+		 * to matter to the user, but aggregation (get_recent_times)
+		 * may have already incorporated the live state into times_prev;
+		 * avoid a delta sample underflow when PSI is later re-enabled.
+		 */
+		if (unlikely(groupc->state_mask & (1 << PSI_NONIDLE)))
+			record_times(groupc, now);
+
+		groupc->state_mask = state_mask;
+
+		write_seqcount_end(&groupc->seq);
+		return;
+	}
+
 	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);
 	}
 
@@ -739,9 +775,11 @@ 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);
 
+	record_times(groupc, now);
+
 	groupc->state_mask = state_mask;
 
 	write_seqcount_end(&groupc->seq);
@@ -753,27 +791,12 @@ 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;
 }
 
@@ -796,8 +819,6 @@ void psi_task_change(struct task_struct *task, int clear, int set)
 {
 	int cpu = task_cpu(task);
 	struct psi_group *group;
-	bool wake_clock = true;
-	void *iter = NULL;
 	u64 now;
 
 	if (!task->pid)
@@ -806,19 +827,11 @@ void psi_task_change(struct task_struct *task, int clear, int set)
 	psi_flags_change(task, clear, set);
 
 	now = cpu_clock(cpu);
-	/*
-	 * Periodic aggregation shuts off if there is a period of no
-	 * task changes, so we wake it back up if necessary. However,
-	 * don't do this if the task change is the aggregation worker
-	 * itself going to sleep, or we'll ping-pong forever.
-	 */
-	if (unlikely((clear & TSK_RUNNING) &&
-		     (task->flags & PF_WQ_WORKER) &&
-		     wq_worker_last_func(task) == psi_avgs_work))
-		wake_clock = false;

This diff is incomplete. Download the complete patch.

kernel/sched/stats.h

View file

This diff is incomplete. Download the complete patch.