[PATCH 0/7] sched: Split cpuacct

[PATCH 0/7] sched: Split cpuacct

[Li Zefan]

- This patchset splits cpuacct out of core scheduler code.
- Plus two small optimizations.

0001-sched-Split-cpuacct-code-out-of-core.c.patch
0002-sched-Split-cpuacct-out-of-sched.h.patch
0003-cpuacct-Add-cpuacct_init.patch
0004-cpuacct-Add-cpuacct_acount_field.patch
0005-cpuacct-Remove-redundant-NULL-checks-in-cpuacct_char.patch
0006-cpuacct-Remove-redundant-NULL-checks-in-cpuacct_acou.patch
0007-cpuacct-Clean-up-cpuacct.h.patch

---
 kernel/sched/Makefile  |   1 +
 kernel/sched/core.c    | 228 +----------------------------------------------
 kernel/sched/cpuacct.c | 303 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 kernel/sched/cpuacct.h |  22 +++++
 kernel/sched/cputime.c |  18 +---
 kernel/sched/sched.h   |  49 +----------
 6 files changed, 330 insertions(+), 291 deletions(-)

[PATCH 1/7] sched: Split cpuacct code out of core.c

[Li Zefan]

Signed-off-by: Li Zefan <lizefan@huawei.com>
---
 kernel/sched/Makefile  |   1 +
 kernel/sched/core.c    | 220 -----------------------------------------------
 kernel/sched/cpuacct.c | 227 +++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 228 insertions(+), 220 deletions(-)
 create mode 100644 kernel/sched/cpuacct.c

diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index f06d249..deaf90e 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -16,3 +16,4 @@ obj-$(CONFIG_SMP) += cpupri.o
 obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o
 obj-$(CONFIG_SCHEDSTATS) += stats.o
 obj-$(CONFIG_SCHED_DEBUG) += debug.o
+obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b7b03cd..8eb3096 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7938,226 +7938,6 @@ struct cgroup_subsys cpu_cgroup_subsys = {
 
 #endif	/* CONFIG_CGROUP_SCHED */
 
-#ifdef CONFIG_CGROUP_CPUACCT
-
-/*
- * CPU accounting code for task groups.
- *
- * Based on the work by Paul Menage (menage@google.com) and Balbir Singh
- * (balbir@in.ibm.com).
- */
-
-struct cpuacct root_cpuacct;
-
-/* create a new cpu accounting group */
-static struct cgroup_subsys_state *cpuacct_css_alloc(struct cgroup *cgrp)
-{
-	struct cpuacct *ca;
-
-	if (!cgrp->parent)
-		return &root_cpuacct.css;
-
-	ca = kzalloc(sizeof(*ca), GFP_KERNEL);
-	if (!ca)
-		goto out;
-
-	ca->cpuusage = alloc_percpu(u64);
-	if (!ca->cpuusage)
-		goto out_free_ca;
-
-	ca->cpustat = alloc_percpu(struct kernel_cpustat);
-	if (!ca->cpustat)
-		goto out_free_cpuusage;
-
-	return &ca->css;
-
-out_free_cpuusage:
-	free_percpu(ca->cpuusage);
-out_free_ca:
-	kfree(ca);
-out:
-	return ERR_PTR(-ENOMEM);
-}
-
-/* destroy an existing cpu accounting group */
-static void cpuacct_css_free(struct cgroup *cgrp)
-{
-	struct cpuacct *ca = cgroup_ca(cgrp);
-
-	free_percpu(ca->cpustat);
-	free_percpu(ca->cpuusage);
-	kfree(ca);
-}
-
-static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu)
-{
-	u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
-	u64 data;
-
-#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;
-#endif
-
-	return data;
-}
-
-static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val)
-{
-	u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
-
-#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;
-#endif
-}
-
-/* return total cpu usage (in nanoseconds) of a group */
-static u64 cpuusage_read(struct cgroup *cgrp, struct cftype *cft)
-{
-	struct cpuacct *ca = cgroup_ca(cgrp);
-	u64 totalcpuusage = 0;
-	int i;
-
-	for_each_present_cpu(i)
-		totalcpuusage += cpuacct_cpuusage_read(ca, i);
-
-	return totalcpuusage;
-}
-
-static int cpuusage_write(struct cgroup *cgrp, struct cftype *cftype,
-								u64 reset)
-{
-	struct cpuacct *ca = cgroup_ca(cgrp);
-	int err = 0;
-	int i;
-
-	if (reset) {
-		err = -EINVAL;
-		goto out;
-	}
-
-	for_each_present_cpu(i)
-		cpuacct_cpuusage_write(ca, i, 0);
-
-out:
-	return err;
-}
-
-static int cpuacct_percpu_seq_read(struct cgroup *cgroup, struct cftype *cft,
-				   struct seq_file *m)
-{
-	struct cpuacct *ca = cgroup_ca(cgroup);
-	u64 percpu;
-	int i;
-
-	for_each_present_cpu(i) {
-		percpu = cpuacct_cpuusage_read(ca, i);
-		seq_printf(m, "%llu ", (unsigned long long) percpu);
-	}
-	seq_printf(m, "\n");
-	return 0;
-}
-
-static const char *cpuacct_stat_desc[] = {
-	[CPUACCT_STAT_USER] = "user",
-	[CPUACCT_STAT_SYSTEM] = "system",
-};
-
-static int cpuacct_stats_show(struct cgroup *cgrp, struct cftype *cft,
-			      struct cgroup_map_cb *cb)
-{
-	struct cpuacct *ca = cgroup_ca(cgrp);
-	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];
-	}
-	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];
-	}
-
-	val = cputime64_to_clock_t(val);
-	cb->fill(cb, cpuacct_stat_desc[CPUACCT_STAT_SYSTEM], val);
-
-	return 0;
-}
-
-static struct cftype files[] = {
-	{
-		.name = "usage",
-		.read_u64 = cpuusage_read,
-		.write_u64 = cpuusage_write,
-	},
-	{
-		.name = "usage_percpu",
-		.read_seq_string = cpuacct_percpu_seq_read,
-	},
-	{
-		.name = "stat",
-		.read_map = cpuacct_stats_show,
-	},
-	{ }	/* terminate */
-};
-
-/*
- * charge this task's execution time to its accounting group.
- *
- * called with rq->lock held.
- */
-void cpuacct_charge(struct task_struct *tsk, u64 cputime)
-{
-	struct cpuacct *ca;
-	int cpu;
-
-	if (unlikely(!cpuacct_subsys.active))
-		return;
-
-	cpu = task_cpu(tsk);
-
-	rcu_read_lock();
-
-	ca = task_ca(tsk);
-
-	for (; ca; ca = parent_ca(ca)) {
-		u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
-		*cpuusage += cputime;
-	}
-
-	rcu_read_unlock();
-}
-
-struct cgroup_subsys cpuacct_subsys = {
-	.name = "cpuacct",
-	.css_alloc = cpuacct_css_alloc,
-	.css_free = cpuacct_css_free,
-	.subsys_id = cpuacct_subsys_id,
-	.base_cftypes = files,
-};
-#endif	/* CONFIG_CGROUP_CPUACCT */
-
 void dump_cpu_task(int cpu)
 {
 	pr_info("Task dump for CPU %d:\n", cpu);
diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c
new file mode 100644
index 0000000..50ec24b
--- /dev/null
+++ b/kernel/sched/cpuacct.c
@@ -0,0 +1,227 @@
+#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 "sched.h"
+
+/*
+ * CPU accounting code for task groups.
+ *
+ * Based on the work by Paul Menage (menage@google.com) and Balbir Singh
+ * (balbir@in.ibm.com).
+ */
+
+struct cpuacct root_cpuacct;
+
+/* create a new cpu accounting group */
+static struct cgroup_subsys_state *cpuacct_css_alloc(struct cgroup *cgrp)
+{
+	struct cpuacct *ca;
+
+	if (!cgrp->parent)
+		return &root_cpuacct.css;
+
+	ca = kzalloc(sizeof(*ca), GFP_KERNEL);
+	if (!ca)
+		goto out;
+
+	ca->cpuusage = alloc_percpu(u64);
+	if (!ca->cpuusage)
+		goto out_free_ca;
+
+	ca->cpustat = alloc_percpu(struct kernel_cpustat);
+	if (!ca->cpustat)
+		goto out_free_cpuusage;
+
+	return &ca->css;
+
+out_free_cpuusage:
+	free_percpu(ca->cpuusage);
+out_free_ca:
+	kfree(ca);
+out:
+	return ERR_PTR(-ENOMEM);
+}
+
+/* destroy an existing cpu accounting group */
+static void cpuacct_css_free(struct cgroup *cgrp)
+{
+	struct cpuacct *ca = cgroup_ca(cgrp);
+
+	free_percpu(ca->cpustat);
+	free_percpu(ca->cpuusage);
+	kfree(ca);
+}
+
+static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu)
+{
+	u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
+	u64 data;
+
+#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;
+#endif
+
+	return data;
+}
+
+static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val)
+{
+	u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
+
+#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;
+#endif
+}
+
+/* return total cpu usage (in nanoseconds) of a group */
+static u64 cpuusage_read(struct cgroup *cgrp, struct cftype *cft)
+{
+	struct cpuacct *ca = cgroup_ca(cgrp);
+	u64 totalcpuusage = 0;
+	int i;
+
+	for_each_present_cpu(i)
+		totalcpuusage += cpuacct_cpuusage_read(ca, i);
+
+	return totalcpuusage;
+}
+
+static int cpuusage_write(struct cgroup *cgrp, struct cftype *cftype,
+								u64 reset)
+{
+	struct cpuacct *ca = cgroup_ca(cgrp);
+	int err = 0;
+	int i;
+
+	if (reset) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	for_each_present_cpu(i)
+		cpuacct_cpuusage_write(ca, i, 0);
+
+out:
+	return err;
+}
+
+static int cpuacct_percpu_seq_read(struct cgroup *cgroup, struct cftype *cft,
+				   struct seq_file *m)
+{
+	struct cpuacct *ca = cgroup_ca(cgroup);
+	u64 percpu;
+	int i;
+
+	for_each_present_cpu(i) {
+		percpu = cpuacct_cpuusage_read(ca, i);
+		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_stats_show(struct cgroup *cgrp, struct cftype *cft,
+			      struct cgroup_map_cb *cb)
+{
+	struct cpuacct *ca = cgroup_ca(cgrp);
+	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];
+	}
+	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];
+	}
+
+	val = cputime64_to_clock_t(val);
+	cb->fill(cb, cpuacct_stat_desc[CPUACCT_STAT_SYSTEM], val);
+
+	return 0;
+}
+
+static struct cftype files[] = {
+	{
+		.name = "usage",
+		.read_u64 = cpuusage_read,
+		.write_u64 = cpuusage_write,
+	},
+	{
+		.name = "usage_percpu",
+		.read_seq_string = cpuacct_percpu_seq_read,
+	},
+	{
+		.name = "stat",
+		.read_map = cpuacct_stats_show,
+	},
+	{ }	/* terminate */
+};
+
+/*
+ * charge this task's execution time to its accounting group.
+ *
+ * called with rq->lock held.
+ */
+void cpuacct_charge(struct task_struct *tsk, u64 cputime)
+{
+	struct cpuacct *ca;
+	int cpu;
+
+	if (unlikely(!cpuacct_subsys.active))
+		return;
+
+	cpu = task_cpu(tsk);
+
+	rcu_read_lock();
+
+	ca = task_ca(tsk);
+
+	for (; ca; ca = parent_ca(ca)) {
+		u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
+		*cpuusage += cputime;
+	}
+
+	rcu_read_unlock();
+}
+
+struct cgroup_subsys cpuacct_subsys = {
+	.name = "cpuacct",
+	.css_alloc = cpuacct_css_alloc,
+	.css_free = cpuacct_css_free,
+	.subsys_id = cpuacct_subsys_id,
+	.base_cftypes = files,
+};
-- 
1.8.0.2

[PATCH 2/7] sched: Split cpuacct out of sched.h

[Li Zefan]

Add cpuacct.h and let sched.h include it.

Signed-off-by: Li Zefan <lizefan@huawei.com>
---
 kernel/sched/cpuacct.h | 52 ++++++++++++++++++++++++++++++++++++++++++++++++++
 kernel/sched/sched.h   | 49 +----------------------------------------------
 2 files changed, 53 insertions(+), 48 deletions(-)
 create mode 100644 kernel/sched/cpuacct.h

diff --git a/kernel/sched/cpuacct.h b/kernel/sched/cpuacct.h
new file mode 100644
index 0000000..a7f3d4a
--- /dev/null
+++ b/kernel/sched/cpuacct.h
@@ -0,0 +1,52 @@
+/* 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 */
+
+	CPUACCT_STAT_NSTATS,
+};
+
+#ifdef CONFIG_CGROUP_CPUACCT
+
+#include <linux/cgroup.h>
+/* 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;
+};
+
+extern struct cgroup_subsys cpuacct_subsys;
+extern struct cpuacct root_cpuacct;
+
+/* return cpu accounting group corresponding to this container */
+static inline struct cpuacct *cgroup_ca(struct cgroup *cgrp)
+{
+	return container_of(cgroup_subsys_state(cgrp, cpuacct_subsys_id),
+			    struct cpuacct, css);
+}
+
+/* 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)
+{
+	if (!ca || !ca->css.cgroup->parent)
+		return NULL;
+	return cgroup_ca(ca->css.cgroup->parent);
+}
+
+extern void cpuacct_charge(struct task_struct *tsk, u64 cputime);
+
+#else
+
+static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime)
+{
+}
+
+#endif
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index cc03cfd..5bfcaba 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -7,6 +7,7 @@
 #include <linux/stop_machine.h>
 
 #include "cpupri.h"
+#include "cpuacct.h"
 
 extern __read_mostly int scheduler_running;
 
@@ -856,15 +857,6 @@ static const u32 prio_to_wmult[40] = {
  /*  15 */ 119304647, 148102320, 186737708, 238609294, 286331153,
 };
 
-/* 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 */
-
-	CPUACCT_STAT_NSTATS,
-};
-
-
 #define sched_class_highest (&stop_sched_class)
 #define for_each_class(class) \
    for (class = sched_class_highest; class; class = class->next)
@@ -904,45 +896,6 @@ extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime
 
 extern void update_idle_cpu_load(struct rq *this_rq);
 
-#ifdef CONFIG_CGROUP_CPUACCT
-#include <linux/cgroup.h>
-/* 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;
-};
-
-extern struct cgroup_subsys cpuacct_subsys;
-extern struct cpuacct root_cpuacct;
-
-/* return cpu accounting group corresponding to this container */
-static inline struct cpuacct *cgroup_ca(struct cgroup *cgrp)
-{
-	return container_of(cgroup_subsys_state(cgrp, cpuacct_subsys_id),
-			    struct cpuacct, css);
-}
-
-/* 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)
-{
-	if (!ca || !ca->css.cgroup->parent)
-		return NULL;
-	return cgroup_ca(ca->css.cgroup->parent);
-}
-
-extern void cpuacct_charge(struct task_struct *tsk, u64 cputime);
-#else
-static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {}
-#endif
-
 #ifdef CONFIG_PARAVIRT
 static inline u64 steal_ticks(u64 steal)
 {
-- 
1.8.0.2

[PATCH 3/7] cpuacct: Add cpuacct_init()

[Li Zefan]

So we don't open-coded initialization of cpuacct in core.c.

Signed-off-by: Li Zefan <lizefan@huawei.com>
---
 kernel/sched/core.c    | 8 ++------
 kernel/sched/cpuacct.c | 7 +++++++
 kernel/sched/cpuacct.h | 5 +++++
 3 files changed, 14 insertions(+), 6 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 8eb3096..9f5a804 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6860,12 +6860,8 @@ void __init sched_init(void)
 
 #endif /* CONFIG_CGROUP_SCHED */
 
-#ifdef CONFIG_CGROUP_CPUACCT
-	root_cpuacct.cpustat = &kernel_cpustat;
-	root_cpuacct.cpuusage = alloc_percpu(u64);
-	/* Too early, not expected to fail */
-	BUG_ON(!root_cpuacct.cpuusage);
-#endif
+	cpuacct_init();
+
 	for_each_possible_cpu(i) {
 		struct rq *rq;
 
diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c
index 50ec24b..48b5e91 100644
--- a/kernel/sched/cpuacct.c
+++ b/kernel/sched/cpuacct.c
@@ -218,6 +218,13 @@ void cpuacct_charge(struct task_struct *tsk, u64 cputime)
 	rcu_read_unlock();
 }
 
+void __init cpuacct_init(void)
+{
+	root_cpuacct.cpustat = &kernel_cpustat;
+	root_cpuacct.cpuusage = alloc_percpu(u64);
+	BUG_ON(!root_cpuacct.cpuusage); /* Too early, not expected to fail */
+}
+
 struct cgroup_subsys cpuacct_subsys = {
 	.name = "cpuacct",
 	.css_alloc = cpuacct_css_alloc,
diff --git a/kernel/sched/cpuacct.h b/kernel/sched/cpuacct.h
index a7f3d4a..551acd7 100644
--- a/kernel/sched/cpuacct.h
+++ b/kernel/sched/cpuacct.h
@@ -41,10 +41,15 @@ static inline struct cpuacct *parent_ca(struct cpuacct *ca)
 	return cgroup_ca(ca->css.cgroup->parent);
 }
 
+extern void cpuacct_init(void);
 extern void cpuacct_charge(struct task_struct *tsk, u64 cputime);
 
 #else
 
+static inline void cpuacct_init(void)
+{
+}
+
 static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime)
 {
 }
-- 
1.8.0.2

[PATCH 4/7] cpuacct: Add cpuacct_acount_field()

[Li Zefan]

So we can remove open-coded cpuacct code in cputime.c.

Signed-off-by: Li Zefan <lizefan@huawei.com>
---
 kernel/sched/cpuacct.c | 23 +++++++++++++++++++++++
 kernel/sched/cpuacct.h |  6 ++++++
 kernel/sched/cputime.c | 18 +-----------------
 3 files changed, 30 insertions(+), 17 deletions(-)

diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c
index 48b5e91..72bd971 100644
--- a/kernel/sched/cpuacct.c
+++ b/kernel/sched/cpuacct.c
@@ -218,6 +218,29 @@ void cpuacct_charge(struct task_struct *tsk, u64 cputime)
 	rcu_read_unlock();
 }
 
+/*
+ * Add user/system time to cpuacct.
+ *
+ * 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)
+{
+	struct kernel_cpustat *kcpustat;
+	struct cpuacct *ca;
+
+	if (unlikely(!cpuacct_subsys.active))
+		return;
+
+	rcu_read_lock();
+	ca = task_ca(p);
+	while (ca && (ca != &root_cpuacct)) {
+		kcpustat = this_cpu_ptr(ca->cpustat);
+		kcpustat->cpustat[index] += val;
+		ca = parent_ca(ca);
+	}
+	rcu_read_unlock();
+}
+
 void __init cpuacct_init(void)
 {
 	root_cpuacct.cpustat = &kernel_cpustat;
diff --git a/kernel/sched/cpuacct.h b/kernel/sched/cpuacct.h
index 551acd7..bd0409b 100644
--- a/kernel/sched/cpuacct.h
+++ b/kernel/sched/cpuacct.h
@@ -43,6 +43,7 @@ static inline struct cpuacct *parent_ca(struct cpuacct *ca)
 
 extern void cpuacct_init(void);
 extern void cpuacct_charge(struct task_struct *tsk, u64 cputime);
+extern void cpuacct_account_field(struct task_struct *p, int index, u64 val);
 
 #else
 
@@ -54,4 +55,9 @@ static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime)
 {
 }
 
+static inline void
+cpuacct_account_field(struct task_struct *p, int index, u64 val)
+{
+}
+
 #endif
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index ed12cbb..a5129c7 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -115,10 +115,6 @@ static int irqtime_account_si_update(void)
 static inline void task_group_account_field(struct task_struct *p, int index,
 					    u64 tmp)
 {
-#ifdef CONFIG_CGROUP_CPUACCT
-	struct kernel_cpustat *kcpustat;
-	struct cpuacct *ca;
-#endif
 	/*
 	 * Since all updates are sure to touch the root cgroup, we
 	 * get ourselves ahead and touch it first. If the root cgroup
@@ -127,19 +123,7 @@ static inline void task_group_account_field(struct task_struct *p, int index,
 	 */
 	__get_cpu_var(kernel_cpustat).cpustat[index] += tmp;
 
-#ifdef CONFIG_CGROUP_CPUACCT
-	if (unlikely(!cpuacct_subsys.active))
-		return;
-
-	rcu_read_lock();
-	ca = task_ca(p);
-	while (ca && (ca != &root_cpuacct)) {
-		kcpustat = this_cpu_ptr(ca->cpustat);
-		kcpustat->cpustat[index] += tmp;
-		ca = parent_ca(ca);
-	}
-	rcu_read_unlock();
-#endif
+	cpuacct_account_field(p, index, tmp);
 }
 
 /*
-- 
1.8.0.2

[PATCH 5/7] cpuacct: Remove redundant NULL checks in cpuacct_charge()

[Li Zefan]

This is micro optimization for the hot path.

- We don't need to check if @ca is NULL in parent_ca().
- We don't need to check if @ca is NULL in the beginning of the for loop.

Signed-off-by: Li Zefan <lizefan@huawei.com>
---
 kernel/sched/cpuacct.c | 6 +++++-
 kernel/sched/cpuacct.h | 2 +-
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c
index 72bd971..b2aaaba 100644
--- a/kernel/sched/cpuacct.c
+++ b/kernel/sched/cpuacct.c
@@ -210,9 +210,13 @@ void cpuacct_charge(struct task_struct *tsk, u64 cputime)
 
 	ca = task_ca(tsk);
 
-	for (; ca; ca = parent_ca(ca)) {
+	while (true) {
 		u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
 		*cpuusage += cputime;
+
+		ca = parent_ca(ca);
+		if (!ca)
+			break;
 	}
 
 	rcu_read_unlock();
diff --git a/kernel/sched/cpuacct.h b/kernel/sched/cpuacct.h
index bd0409b..45c1682 100644
--- a/kernel/sched/cpuacct.h
+++ b/kernel/sched/cpuacct.h
@@ -36,7 +36,7 @@ static inline struct cpuacct *task_ca(struct task_struct *tsk)
 
 static inline struct cpuacct *parent_ca(struct cpuacct *ca)
 {
-	if (!ca || !ca->css.cgroup->parent)
+	if (!ca->css.cgroup->parent)
 		return NULL;
 	return cgroup_ca(ca->css.cgroup->parent);
 }
-- 
1.8.0.2

[PATCH 6/7] cpuacct: Remove redundant NULL checks in cpuacct_acount_field()

[Li Zefan]

This is a micro optimazation for a hot path.

- We don't need to check if @ca returned from task_ca() is NULL.
- We don't need to check if @ca returned from parent_ca() is NULL.

Signed-off-by: Li Zefan <lizefan@huawei.com>
---
 kernel/sched/cpuacct.c | 4 ++--
 kernel/sched/cpuacct.h | 5 +++++
 2 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c
index b2aaaba..071ae8d 100644
--- a/kernel/sched/cpuacct.c
+++ b/kernel/sched/cpuacct.c
@@ -237,10 +237,10 @@ void cpuacct_account_field(struct task_struct *p, int index, u64 val)
 
 	rcu_read_lock();
 	ca = task_ca(p);
-	while (ca && (ca != &root_cpuacct)) {
+	while (ca != &root_cpuacct) {
 		kcpustat = this_cpu_ptr(ca->cpustat);
 		kcpustat->cpustat[index] += val;
-		ca = parent_ca(ca);
+		ca = __parent_ca(ca);
 	}
 	rcu_read_unlock();
 }
diff --git a/kernel/sched/cpuacct.h b/kernel/sched/cpuacct.h
index 45c1682..b2f79ad 100644
--- a/kernel/sched/cpuacct.h
+++ b/kernel/sched/cpuacct.h
@@ -34,6 +34,11 @@ static inline struct cpuacct *task_ca(struct task_struct *tsk)
 			    struct cpuacct, css);
 }
 
+static inline struct cpuacct *__parent_ca(struct cpuacct *ca)
+{
+	return cgroup_ca(ca->css.cgroup->parent);
+}
+
 static inline struct cpuacct *parent_ca(struct cpuacct *ca)
 {
 	if (!ca->css.cgroup->parent)
-- 
1.8.0.2

[PATCH 7/7] cpuacct: Clean up cpuacct.h

[Li Zefan]

Now most of the code in cpuacct.h can be moved to cpuacct.c

Signed-off-by: Li Zefan <lizefan@huawei.com>
---
 kernel/sched/cpuacct.c | 44 +++++++++++++++++++++++++++++++++++++++++++-
 kernel/sched/cpuacct.h | 46 ----------------------------------------------
 2 files changed, 43 insertions(+), 47 deletions(-)

diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c
index 071ae8d..9305fd2 100644
--- a/kernel/sched/cpuacct.c
+++ b/kernel/sched/cpuacct.c
@@ -16,7 +16,49 @@
  * (balbir@in.ibm.com).
  */
 
-struct cpuacct root_cpuacct;
+/* 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 */
+
+	CPUACCT_STAT_NSTATS,
+};
+
+/* 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;
+};
+
+/* return cpu accounting group corresponding to this container */
+static inline struct cpuacct *cgroup_ca(struct cgroup *cgrp)
+{
+	return container_of(cgroup_subsys_state(cgrp, cpuacct_subsys_id),
+			    struct cpuacct, css);
+}
+
+/* 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);
+}
+
+static inline struct cpuacct *parent_ca(struct cpuacct *ca)
+{
+	if (!ca->css.cgroup->parent)
+		return NULL;
+	return cgroup_ca(ca->css.cgroup->parent);
+}
+
+static struct cpuacct root_cpuacct;
 
 /* create a new cpu accounting group */
 static struct cgroup_subsys_state *cpuacct_css_alloc(struct cgroup *cgrp)
diff --git a/kernel/sched/cpuacct.h b/kernel/sched/cpuacct.h
index b2f79ad..51cd76e 100644
--- a/kernel/sched/cpuacct.h
+++ b/kernel/sched/cpuacct.h
@@ -1,51 +1,5 @@
-/* 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 */
-
-	CPUACCT_STAT_NSTATS,
-};
-
 #ifdef CONFIG_CGROUP_CPUACCT
 
-#include <linux/cgroup.h>
-/* 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;
-};
-
-extern struct cgroup_subsys cpuacct_subsys;
-extern struct cpuacct root_cpuacct;
-
-/* return cpu accounting group corresponding to this container */
-static inline struct cpuacct *cgroup_ca(struct cgroup *cgrp)
-{
-	return container_of(cgroup_subsys_state(cgrp, cpuacct_subsys_id),
-			    struct cpuacct, css);
-}
-
-/* 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);
-}
-
-static inline struct cpuacct *parent_ca(struct cpuacct *ca)
-{
-	if (!ca->css.cgroup->parent)
-		return NULL;
-	return cgroup_ca(ca->css.cgroup->parent);
-}
-
 extern void cpuacct_init(void);
 extern void cpuacct_charge(struct task_struct *tsk, u64 cputime);
 extern void cpuacct_account_field(struct task_struct *p, int index, u64 val);
-- 
1.8.0.2

Re: [PATCH 0/7] sched: Split cpuacct

[Li Zefan]

Please ignore this patchset. It's not based on the right kernel
version..

On 2013/3/28 12:11, Li Zefan wrote:
> - This patchset splits cpuacct out of core scheduler code.
> - Plus two small optimizations.
> 
> 0001-sched-Split-cpuacct-code-out-of-core.c.patch
> 0002-sched-Split-cpuacct-out-of-sched.h.patch
> 0003-cpuacct-Add-cpuacct_init.patch
> 0004-cpuacct-Add-cpuacct_acount_field.patch
> 0005-cpuacct-Remove-redundant-NULL-checks-in-cpuacct_char.patch
> 0006-cpuacct-Remove-redundant-NULL-checks-in-cpuacct_acou.patch
> 0007-cpuacct-Clean-up-cpuacct.h.patch
> 
> ---
>  kernel/sched/Makefile  |   1 +
>  kernel/sched/core.c    | 228 +----------------------------------------------
>  kernel/sched/cpuacct.c | 303 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
>  kernel/sched/cpuacct.h |  22 +++++
>  kernel/sched/cputime.c |  18 +---
>  kernel/sched/sched.h   |  49 +----------
>  6 files changed, 330 insertions(+), 291 deletions(-)
>