1 files changed, 198 insertions, 129 deletions

diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c
index dbb7e2cd95eb..23a56ba12d81 100644
--- a/kernel/sched/cpuacct.c
+++ b/kernel/sched/cpuacct.c
@@ -1,14 +1,4 @@
-#include <linux/cgroup.h>
-#include <linux/slab.h>
-#include <linux/percpu.h>
-#include <linux/spinlock.h>
-#include <linux/cpumask.h>
-#include <linux/seq_file.h>
-#include <linux/rcupdate.h>
-#include <linux/kernel_stat.h>
-#include <linux/err.h>
-
-#include "sched.h"
+// SPDX-License-Identifier: GPL-2.0
 
 /*
  * CPU accounting code for task groups.
@@ -16,8 +6,10 @@
  * Based on the work by Paul Menage (menage@google.com) and Balbir Singh
  * (balbir@in.ibm.com).
  */
+#include <linux/sched/cputime.h>
+#include "sched.h"
 
-/* Time spent by the tasks of the cpu accounting group executing in ... */
+/* Time spent by the tasks of the CPU accounting group executing in ... */
 enum cpuacct_stat_index {
 	CPUACCT_STAT_USER,	/* ... user mode */
 	CPUACCT_STAT_SYSTEM,	/* ... kernel mode */
@@ -25,38 +17,33 @@ enum cpuacct_stat_index {
 	CPUACCT_STAT_NSTATS,
 };
 
-/* track cpu usage of a group of tasks and its child groups */
+static const char * const cpuacct_stat_desc[] = {
+	[CPUACCT_STAT_USER] = "user",
+	[CPUACCT_STAT_SYSTEM] = "system",
+};
+
+/* track CPU usage of a group of tasks and its child groups */
 struct cpuacct {
-	struct cgroup_subsys_state css;
-	/* cpuusage holds pointer to a u64-type object on every cpu */
-	u64 __percpu *cpuusage;
-	struct kernel_cpustat __percpu *cpustat;
+	struct cgroup_subsys_state	css;
+	/* cpuusage holds pointer to a u64-type object on every CPU */
+	u64 __percpu	*cpuusage;
+	struct kernel_cpustat __percpu	*cpustat;
 };
 
-/* return cpu accounting group corresponding to this container */
-static inline struct cpuacct *cgroup_ca(struct cgroup *cgrp)
+static inline struct cpuacct *css_ca(struct cgroup_subsys_state *css)
 {
-	return container_of(cgroup_subsys_state(cgrp, cpuacct_subsys_id),
-			    struct cpuacct, css);
+	return css ? container_of(css, struct cpuacct, css) : NULL;
 }
 
-/* return cpu accounting group to which this task belongs */
+/* Return CPU accounting group to which this task belongs */
 static inline struct cpuacct *task_ca(struct task_struct *tsk)
 {
-	return container_of(task_subsys_state(tsk, cpuacct_subsys_id),
-			    struct cpuacct, css);
-}
-
-static inline struct cpuacct *__parent_ca(struct cpuacct *ca)
-{
-	return cgroup_ca(ca->css.cgroup->parent);
+	return css_ca(task_css(tsk, cpuacct_cgrp_id));
 }
 
 static inline struct cpuacct *parent_ca(struct cpuacct *ca)
 {
-	if (!ca->css.cgroup->parent)
-		return NULL;
-	return cgroup_ca(ca->css.cgroup->parent);
+	return css_ca(ca->css.parent);
 }
 
 static DEFINE_PER_CPU(u64, root_cpuacct_cpuusage);
@@ -65,12 +52,13 @@ static struct cpuacct root_cpuacct = {
 	.cpuusage	= &root_cpuacct_cpuusage,
 };
 
-/* create a new cpu accounting group */
-static struct cgroup_subsys_state *cpuacct_css_alloc(struct cgroup *cgrp)
+/* Create a new CPU accounting group */
+static struct cgroup_subsys_state *
+cpuacct_css_alloc(struct cgroup_subsys_state *parent_css)
 {
 	struct cpuacct *ca;
 
-	if (!cgrp->parent)
+	if (!parent_css)
 		return &root_cpuacct.css;
 
 	ca = kzalloc(sizeof(*ca), GFP_KERNEL);
@@ -95,128 +83,210 @@ out:
 	return ERR_PTR(-ENOMEM);
 }
 
-/* destroy an existing cpu accounting group */
-static void cpuacct_css_free(struct cgroup *cgrp)
+/* Destroy an existing CPU accounting group */
+static void cpuacct_css_free(struct cgroup_subsys_state *css)
 {
-	struct cpuacct *ca = cgroup_ca(cgrp);
+	struct cpuacct *ca = css_ca(css);
 
 	free_percpu(ca->cpustat);
 	free_percpu(ca->cpuusage);
 	kfree(ca);
 }
 
-static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu)
+static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu,
+				 enum cpuacct_stat_index index)
 {
 	u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
+	u64 *cpustat = per_cpu_ptr(ca->cpustat, cpu)->cpustat;
 	u64 data;
 
+	/*
+	 * We allow index == CPUACCT_STAT_NSTATS here to read
+	 * the sum of usages.
+	 */
+	if (WARN_ON_ONCE(index > CPUACCT_STAT_NSTATS))
+		return 0;
+
 #ifndef CONFIG_64BIT
 	/*
 	 * Take rq->lock to make 64-bit read safe on 32-bit platforms.
 	 */
-	raw_spin_lock_irq(&cpu_rq(cpu)->lock);
-	data = *cpuusage;
-	raw_spin_unlock_irq(&cpu_rq(cpu)->lock);
-#else
-	data = *cpuusage;
+	raw_spin_rq_lock_irq(cpu_rq(cpu));
+#endif
+
+	switch (index) {
+	case CPUACCT_STAT_USER:
+		data = cpustat[CPUTIME_USER] + cpustat[CPUTIME_NICE];
+		break;
+	case CPUACCT_STAT_SYSTEM:
+		data = cpustat[CPUTIME_SYSTEM] + cpustat[CPUTIME_IRQ] +
+			cpustat[CPUTIME_SOFTIRQ];
+		break;
+	case CPUACCT_STAT_NSTATS:
+		data = *cpuusage;
+		break;
+	}
+
+#ifndef CONFIG_64BIT
+	raw_spin_rq_unlock_irq(cpu_rq(cpu));
 #endif
 
 	return data;
 }
 
-static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val)
+static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu)
 {
 	u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
+	u64 *cpustat = per_cpu_ptr(ca->cpustat, cpu)->cpustat;
+
+	/* Don't allow to reset global kernel_cpustat */
+	if (ca == &root_cpuacct)
+		return;
 
 #ifndef CONFIG_64BIT
 	/*
 	 * Take rq->lock to make 64-bit write safe on 32-bit platforms.
 	 */
-	raw_spin_lock_irq(&cpu_rq(cpu)->lock);
-	*cpuusage = val;
-	raw_spin_unlock_irq(&cpu_rq(cpu)->lock);
-#else
-	*cpuusage = val;
+	raw_spin_rq_lock_irq(cpu_rq(cpu));
+#endif
+	*cpuusage = 0;
+	cpustat[CPUTIME_USER] = cpustat[CPUTIME_NICE] = 0;
+	cpustat[CPUTIME_SYSTEM] = cpustat[CPUTIME_IRQ] = 0;
+	cpustat[CPUTIME_SOFTIRQ] = 0;
+
+#ifndef CONFIG_64BIT
+	raw_spin_rq_unlock_irq(cpu_rq(cpu));
 #endif
 }
 
-/* return total cpu usage (in nanoseconds) of a group */
-static u64 cpuusage_read(struct cgroup *cgrp, struct cftype *cft)
+/* Return total CPU usage (in nanoseconds) of a group */
+static u64 __cpuusage_read(struct cgroup_subsys_state *css,
+			   enum cpuacct_stat_index index)
 {
-	struct cpuacct *ca = cgroup_ca(cgrp);
+	struct cpuacct *ca = css_ca(css);
 	u64 totalcpuusage = 0;
 	int i;
 
-	for_each_present_cpu(i)
-		totalcpuusage += cpuacct_cpuusage_read(ca, i);
+	for_each_possible_cpu(i)
+		totalcpuusage += cpuacct_cpuusage_read(ca, i, index);
 
 	return totalcpuusage;
 }
 
-static int cpuusage_write(struct cgroup *cgrp, struct cftype *cftype,
-								u64 reset)
+static u64 cpuusage_user_read(struct cgroup_subsys_state *css,
+			      struct cftype *cft)
 {
-	struct cpuacct *ca = cgroup_ca(cgrp);
-	int err = 0;
-	int i;
+	return __cpuusage_read(css, CPUACCT_STAT_USER);
+}
 
-	if (reset) {
-		err = -EINVAL;
-		goto out;
-	}
+static u64 cpuusage_sys_read(struct cgroup_subsys_state *css,
+			     struct cftype *cft)
+{
+	return __cpuusage_read(css, CPUACCT_STAT_SYSTEM);
+}
+
+static u64 cpuusage_read(struct cgroup_subsys_state *css, struct cftype *cft)
+{
+	return __cpuusage_read(css, CPUACCT_STAT_NSTATS);
+}
 
-	for_each_present_cpu(i)
-		cpuacct_cpuusage_write(ca, i, 0);
+static int cpuusage_write(struct cgroup_subsys_state *css, struct cftype *cft,
+			  u64 val)
+{
+	struct cpuacct *ca = css_ca(css);
+	int cpu;
 
-out:
-	return err;
+	/*
+	 * Only allow '0' here to do a reset.
+	 */
+	if (val)
+		return -EINVAL;
+
+	for_each_possible_cpu(cpu)
+		cpuacct_cpuusage_write(ca, cpu);
+
+	return 0;
 }
 
-static int cpuacct_percpu_seq_read(struct cgroup *cgroup, struct cftype *cft,
-				   struct seq_file *m)
+static int __cpuacct_percpu_seq_show(struct seq_file *m,
+				     enum cpuacct_stat_index index)
 {
-	struct cpuacct *ca = cgroup_ca(cgroup);
+	struct cpuacct *ca = css_ca(seq_css(m));
 	u64 percpu;
 	int i;
 
-	for_each_present_cpu(i) {
-		percpu = cpuacct_cpuusage_read(ca, i);
+	for_each_possible_cpu(i) {
+		percpu = cpuacct_cpuusage_read(ca, i, index);
 		seq_printf(m, "%llu ", (unsigned long long) percpu);
 	}
 	seq_printf(m, "\n");
 	return 0;
 }
 
-static const char * const cpuacct_stat_desc[] = {
-	[CPUACCT_STAT_USER] = "user",
-	[CPUACCT_STAT_SYSTEM] = "system",
-};
+static int cpuacct_percpu_user_seq_show(struct seq_file *m, void *V)
+{
+	return __cpuacct_percpu_seq_show(m, CPUACCT_STAT_USER);
+}
+
+static int cpuacct_percpu_sys_seq_show(struct seq_file *m, void *V)
+{
+	return __cpuacct_percpu_seq_show(m, CPUACCT_STAT_SYSTEM);
+}
+
+static int cpuacct_percpu_seq_show(struct seq_file *m, void *V)
+{
+	return __cpuacct_percpu_seq_show(m, CPUACCT_STAT_NSTATS);
+}
 
-static int cpuacct_stats_show(struct cgroup *cgrp, struct cftype *cft,
-			      struct cgroup_map_cb *cb)
+static int cpuacct_all_seq_show(struct seq_file *m, void *V)
 {
-	struct cpuacct *ca = cgroup_ca(cgrp);
+	struct cpuacct *ca = css_ca(seq_css(m));
+	int index;
 	int cpu;
-	s64 val = 0;
 
-	for_each_online_cpu(cpu) {
-		struct kernel_cpustat *kcpustat = per_cpu_ptr(ca->cpustat, cpu);
-		val += kcpustat->cpustat[CPUTIME_USER];
-		val += kcpustat->cpustat[CPUTIME_NICE];
+	seq_puts(m, "cpu");
+	for (index = 0; index < CPUACCT_STAT_NSTATS; index++)
+		seq_printf(m, " %s", cpuacct_stat_desc[index]);
+	seq_puts(m, "\n");
+
+	for_each_possible_cpu(cpu) {
+		seq_printf(m, "%d", cpu);
+		for (index = 0; index < CPUACCT_STAT_NSTATS; index++)
+			seq_printf(m, " %llu",
+				   cpuacct_cpuusage_read(ca, cpu, index));
+		seq_puts(m, "\n");
 	}
-	val = cputime64_to_clock_t(val);
-	cb->fill(cb, cpuacct_stat_desc[CPUACCT_STAT_USER], val);
-
-	val = 0;
-	for_each_online_cpu(cpu) {
-		struct kernel_cpustat *kcpustat = per_cpu_ptr(ca->cpustat, cpu);
-		val += kcpustat->cpustat[CPUTIME_SYSTEM];
-		val += kcpustat->cpustat[CPUTIME_IRQ];
-		val += kcpustat->cpustat[CPUTIME_SOFTIRQ];
+	return 0;
+}
+
+static int cpuacct_stats_show(struct seq_file *sf, void *v)
+{
+	struct cpuacct *ca = css_ca(seq_css(sf));
+	struct task_cputime cputime;
+	u64 val[CPUACCT_STAT_NSTATS];
+	int cpu;
+	int stat;
+
+	memset(&cputime, 0, sizeof(cputime));
+	for_each_possible_cpu(cpu) {
+		u64 *cpustat = per_cpu_ptr(ca->cpustat, cpu)->cpustat;
+
+		cputime.utime += cpustat[CPUTIME_USER];
+		cputime.utime += cpustat[CPUTIME_NICE];
+		cputime.stime += cpustat[CPUTIME_SYSTEM];
+		cputime.stime += cpustat[CPUTIME_IRQ];
+		cputime.stime += cpustat[CPUTIME_SOFTIRQ];
+
+		cputime.sum_exec_runtime += *per_cpu_ptr(ca->cpuusage, cpu);
 	}
 
-	val = cputime64_to_clock_t(val);
-	cb->fill(cb, cpuacct_stat_desc[CPUACCT_STAT_SYSTEM], val);
+	cputime_adjust(&cputime, &seq_css(sf)->cgroup->prev_cputime,
+		&val[CPUACCT_STAT_USER], &val[CPUACCT_STAT_SYSTEM]);
+
+	for (stat = 0; stat < CPUACCT_STAT_NSTATS; stat++) {
+		seq_printf(sf, "%s %llu\n", cpuacct_stat_desc[stat],
+			nsec_to_clock_t(val[stat]));
+	}
 
 	return 0;
 }
@@ -228,12 +298,32 @@ static struct cftype files[] = {
 		.write_u64 = cpuusage_write,
 	},
 	{
+		.name = "usage_user",
+		.read_u64 = cpuusage_user_read,
+	},
+	{
+		.name = "usage_sys",
+		.read_u64 = cpuusage_sys_read,
+	},
+	{
 		.name = "usage_percpu",
-		.read_seq_string = cpuacct_percpu_seq_read,
+		.seq_show = cpuacct_percpu_seq_show,
+	},
+	{
+		.name = "usage_percpu_user",
+		.seq_show = cpuacct_percpu_user_seq_show,
+	},
+	{
+		.name = "usage_percpu_sys",
+		.seq_show = cpuacct_percpu_sys_seq_show,
+	},
+	{
+		.name = "usage_all",
+		.seq_show = cpuacct_all_seq_show,
 	},
 	{
 		.name = "stat",
-		.read_map = cpuacct_stats_show,
+		.seq_show = cpuacct_stats_show,
 	},
 	{ }	/* terminate */
 };
@@ -245,25 +335,13 @@ static struct cftype files[] = {
  */
 void cpuacct_charge(struct task_struct *tsk, u64 cputime)
 {
+	unsigned int cpu = task_cpu(tsk);
 	struct cpuacct *ca;
-	int cpu;
-
-	cpu = task_cpu(tsk);
-
-	rcu_read_lock();
 
-	ca = task_ca(tsk);
+	lockdep_assert_rq_held(cpu_rq(cpu));
 
-	while (true) {
-		u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
-		*cpuusage += cputime;
-
-		ca = parent_ca(ca);
-		if (!ca)
-			break;
-	}
-
-	rcu_read_unlock();
+	for (ca = task_ca(tsk); ca; ca = parent_ca(ca))
+		*per_cpu_ptr(ca->cpuusage, cpu) += cputime;
 }
 
 /*
@@ -271,26 +349,17 @@ void cpuacct_charge(struct task_struct *tsk, u64 cputime)
  *
  * Note: it's the caller that updates the account of the root cgroup.
  */
-void cpuacct_account_field(struct task_struct *p, int index, u64 val)
+void cpuacct_account_field(struct task_struct *tsk, int index, u64 val)
 {
-	struct kernel_cpustat *kcpustat;
 	struct cpuacct *ca;
 
-	rcu_read_lock();
-	ca = task_ca(p);
-	while (ca != &root_cpuacct) {
-		kcpustat = this_cpu_ptr(ca->cpustat);
-		kcpustat->cpustat[index] += val;
-		ca = __parent_ca(ca);
-	}
-	rcu_read_unlock();
+	for (ca = task_ca(tsk); ca != &root_cpuacct; ca = parent_ca(ca))
+		__this_cpu_add(ca->cpustat->cpustat[index], val);
 }
 
-struct cgroup_subsys cpuacct_subsys = {
-	.name		= "cpuacct",
+struct cgroup_subsys cpuacct_cgrp_subsys = {
 	.css_alloc	= cpuacct_css_alloc,
 	.css_free	= cpuacct_css_free,
-	.subsys_id	= cpuacct_subsys_id,
-	.base_cftypes	= files,
-	.early_init	= 1,
+	.legacy_cftypes	= files,
+	.early_init	= true,
 };