[PATCHSET REPOST] sched, cgroup: implement cgroup v2 interface for cpu controller

[PATCHSET REPOST] sched, cgroup: implement cgroup v2 interface for cpu controller

[Tejun Heo]

Hello,

This patchset implements cgroup v2 interface for cpu controller and a
repost of the following.

 http://lkml.kernel.org/g/1438641689-14655-1-git-send-email-tj@kernel.org

The first patch is folded and applied into v2 documentation.  The
second patch is unchanged.  The third is unchanged from the posted v2.

The patchset got blocked by discussion on in-process hierarchical
resource contorl.  The following message is to restart the discussion.

 http://lkml.kernel.org/g/20160105154503.GC5995@mtj.duckdns.org

While the conclusion hasn't been reached, none of the issues being
debated affects the system level interface and there's no technical
reason to hold off these patches especially given that cgroup v2 is
being released in the coming merge window for memory and io
controllers.

Can we please go ahead with these?

diffstat follows.

 kernel/sched/core.c    |  149 +++++++++++++++++++++++++++++++++++++++++++++++--
 kernel/sched/cpuacct.c |   57 ++++++++++++------
 kernel/sched/cpuacct.h |    5 +
 3 files changed, 189 insertions(+), 22 deletions(-)

Thanks.

-- 
tejun

[PATCHSET REPOST] sched, cgroup: implement cgroup v2 interface for cpu controller

[Tejun Heo]

Hello,

This patchset implements cgroup v2 interface for cpu controller and a
repost of the following.

 http://lkml.kernel.org/g/1438641689-14655-1-git-send-email-tj-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org

The first patch is folded and applied into v2 documentation.  The
second patch is unchanged.  The third is unchanged from the posted v2.

The patchset got blocked by discussion on in-process hierarchical
resource contorl.  The following message is to restart the discussion.

 http://lkml.kernel.org/g/20160105154503.GC5995-qYNAdHglDFBN0TnZuCh8vA@public.gmane.org

While the conclusion hasn't been reached, none of the issues being
debated affects the system level interface and there's no technical
reason to hold off these patches especially given that cgroup v2 is
being released in the coming merge window for memory and io
controllers.

Can we please go ahead with these?

diffstat follows.

 kernel/sched/core.c    |  149 +++++++++++++++++++++++++++++++++++++++++++++++--
 kernel/sched/cpuacct.c |   57 ++++++++++++------
 kernel/sched/cpuacct.h |    5 +
 3 files changed, 189 insertions(+), 22 deletions(-)

Thanks.

-- 
tejun

[PATCH 1/2] sched: Misc preps for cgroup unified hierarchy interface

[Tejun Heo]

Make the following changes in preparation for the cpu controller
interface implementation for the unified hierarchy.  This patch
doesn't cause any functional differences.

* s/cpu_stats_show()/cpu_cfs_stats_show()/

* s/cpu_files/cpu_legacy_files/

* Separate out cpuacct_stats_read() from cpuacct_stats_show().  While
  at it, remove pointless cpuacct_stat_desc[] array.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Li Zefan <lizefan@huawei.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
---
 kernel/sched/core.c    |    8 ++++----
 kernel/sched/cpuacct.c |   33 +++++++++++++++------------------
 2 files changed, 19 insertions(+), 22 deletions(-)

--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -8488,7 +8488,7 @@ static int __cfs_schedulable(struct task
 	return ret;
 }
 
-static int cpu_stats_show(struct seq_file *sf, void *v)
+static int cpu_cfs_stats_show(struct seq_file *sf, void *v)
 {
 	struct task_group *tg = css_tg(seq_css(sf));
 	struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth;
@@ -8528,7 +8528,7 @@ static u64 cpu_rt_period_read_uint(struc
 }
 #endif /* CONFIG_RT_GROUP_SCHED */
 
-static struct cftype cpu_files[] = {
+static struct cftype cpu_legacy_files[] = {
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	{
 		.name = "shares",
@@ -8549,7 +8549,7 @@ static struct cftype cpu_files[] = {
 	},
 	{
 		.name = "stat",
-		.seq_show = cpu_stats_show,
+		.seq_show = cpu_cfs_stats_show,
 	},
 #endif
 #ifdef CONFIG_RT_GROUP_SCHED
@@ -8575,7 +8575,7 @@ struct cgroup_subsys cpu_cgrp_subsys = {
 	.fork		= cpu_cgroup_fork,
 	.can_attach	= cpu_cgroup_can_attach,
 	.attach		= cpu_cgroup_attach,
-	.legacy_cftypes	= cpu_files,
+	.legacy_cftypes	= cpu_legacy_files,
 	.early_init	= 1,
 };
 
--- a/kernel/sched/cpuacct.c
+++ b/kernel/sched/cpuacct.c
@@ -177,36 +177,33 @@ static int cpuacct_percpu_seq_show(struc
 	return 0;
 }
 
-static const char * const cpuacct_stat_desc[] = {
-	[CPUACCT_STAT_USER] = "user",
-	[CPUACCT_STAT_SYSTEM] = "system",
-};
-
-static int cpuacct_stats_show(struct seq_file *sf, void *v)
+static void cpuacct_stats_read(struct cpuacct *ca, u64 *userp, u64 *sysp)
 {
-	struct cpuacct *ca = css_ca(seq_css(sf));
 	int cpu;
-	s64 val = 0;
 
+	*userp = 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];
+		*userp += kcpustat->cpustat[CPUTIME_USER];
+		*userp += kcpustat->cpustat[CPUTIME_NICE];
 	}
-	val = cputime64_to_clock_t(val);
-	seq_printf(sf, "%s %lld\n", cpuacct_stat_desc[CPUACCT_STAT_USER], val);
 
-	val = 0;
+	*sysp = 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];
+		*sysp += kcpustat->cpustat[CPUTIME_SYSTEM];
+		*sysp += kcpustat->cpustat[CPUTIME_IRQ];
+		*sysp += kcpustat->cpustat[CPUTIME_SOFTIRQ];
 	}
+}
 
-	val = cputime64_to_clock_t(val);
-	seq_printf(sf, "%s %lld\n", cpuacct_stat_desc[CPUACCT_STAT_SYSTEM], val);
+static int cpuacct_stats_show(struct seq_file *sf, void *v)
+{
+	cputime64_t user, sys;
 
+	cpuacct_stats_read(css_ca(seq_css(sf)), &user, &sys);
+	seq_printf(sf, "user %lld\n", cputime64_to_clock_t(user));
+	seq_printf(sf, "system %lld\n", cputime64_to_clock_t(sys));
 	return 0;
 }
 

[PATCH 1/2] sched: Misc preps for cgroup unified hierarchy interface

[Tejun Heo]

Make the following changes in preparation for the cpu controller
interface implementation for the unified hierarchy.  This patch
doesn't cause any functional differences.

* s/cpu_stats_show()/cpu_cfs_stats_show()/

* s/cpu_files/cpu_legacy_files/

* Separate out cpuacct_stats_read() from cpuacct_stats_show().  While
  at it, remove pointless cpuacct_stat_desc[] array.

Signed-off-by: Tejun Heo <tj-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>
Cc: Ingo Molnar <mingo-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
Cc: Peter Zijlstra <peterz-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org>
Cc: Li Zefan <lizefan-hv44wF8Li93QT0dZR+AlfA@public.gmane.org>
Cc: Johannes Weiner <hannes-druUgvl0LCNAfugRpC6u6w@public.gmane.org>
---
 kernel/sched/core.c    |    8 ++++----
 kernel/sched/cpuacct.c |   33 +++++++++++++++------------------
 2 files changed, 19 insertions(+), 22 deletions(-)

--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -8488,7 +8488,7 @@ static int __cfs_schedulable(struct task
 	return ret;
 }
 
-static int cpu_stats_show(struct seq_file *sf, void *v)
+static int cpu_cfs_stats_show(struct seq_file *sf, void *v)
 {
 	struct task_group *tg = css_tg(seq_css(sf));
 	struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth;
@@ -8528,7 +8528,7 @@ static u64 cpu_rt_period_read_uint(struc
 }
 #endif /* CONFIG_RT_GROUP_SCHED */
 
-static struct cftype cpu_files[] = {
+static struct cftype cpu_legacy_files[] = {
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	{
 		.name = "shares",
@@ -8549,7 +8549,7 @@ static struct cftype cpu_files[] = {
 	},
 	{
 		.name = "stat",
-		.seq_show = cpu_stats_show,
+		.seq_show = cpu_cfs_stats_show,
 	},
 #endif
 #ifdef CONFIG_RT_GROUP_SCHED
@@ -8575,7 +8575,7 @@ struct cgroup_subsys cpu_cgrp_subsys = {
 	.fork		= cpu_cgroup_fork,
 	.can_attach	= cpu_cgroup_can_attach,
 	.attach		= cpu_cgroup_attach,
-	.legacy_cftypes	= cpu_files,
+	.legacy_cftypes	= cpu_legacy_files,
 	.early_init	= 1,
 };
 
--- a/kernel/sched/cpuacct.c
+++ b/kernel/sched/cpuacct.c
@@ -177,36 +177,33 @@ static int cpuacct_percpu_seq_show(struc
 	return 0;
 }
 
-static const char * const cpuacct_stat_desc[] = {
-	[CPUACCT_STAT_USER] = "user",
-	[CPUACCT_STAT_SYSTEM] = "system",
-};
-
-static int cpuacct_stats_show(struct seq_file *sf, void *v)
+static void cpuacct_stats_read(struct cpuacct *ca, u64 *userp, u64 *sysp)
 {
-	struct cpuacct *ca = css_ca(seq_css(sf));
 	int cpu;
-	s64 val = 0;
 
+	*userp = 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];
+		*userp += kcpustat->cpustat[CPUTIME_USER];
+		*userp += kcpustat->cpustat[CPUTIME_NICE];
 	}
-	val = cputime64_to_clock_t(val);
-	seq_printf(sf, "%s %lld\n", cpuacct_stat_desc[CPUACCT_STAT_USER], val);
 
-	val = 0;
+	*sysp = 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];
+		*sysp += kcpustat->cpustat[CPUTIME_SYSTEM];
+		*sysp += kcpustat->cpustat[CPUTIME_IRQ];
+		*sysp += kcpustat->cpustat[CPUTIME_SOFTIRQ];
 	}
+}
 
-	val = cputime64_to_clock_t(val);
-	seq_printf(sf, "%s %lld\n", cpuacct_stat_desc[CPUACCT_STAT_SYSTEM], val);
+static int cpuacct_stats_show(struct seq_file *sf, void *v)
+{
+	cputime64_t user, sys;
 
+	cpuacct_stats_read(css_ca(seq_css(sf)), &user, &sys);
+	seq_printf(sf, "user %lld\n", cputime64_to_clock_t(user));
+	seq_printf(sf, "system %lld\n", cputime64_to_clock_t(sys));
 	return 0;
 }
 

[PATCH 2/2] sched: Implement interface for cgroup unified hierarchy

[Tejun Heo]

While the cpu controller doesn't have any functional problems, there
are a couple interface issues which can be addressed in the v2
interface.

* cpuacct being a separate controller.  This separation is artificial
  and rather pointless as demonstrated by most use cases co-mounting
  the two controllers.  It also forces certain information to be
  accounted twice.

* Use of different time units.  Writable control knobs use
  microseconds, some stat fields use nanoseconds while other cpuacct
  stat fields use centiseconds.

* Control knobs which can't be used in the root cgroup still show up
  in the root.

* Control knob names and semantics aren't consistent with other
  controllers.

This patchset implements cpu controller's interface on the unified
hierarchy which adheres to the controller file conventions described
in Documentation/cgroups/unified-hierarchy.txt.  Overall, the
following changes are made.

* cpuacct is implictly enabled and disabled by cpu and its information
  is reported through "cpu.stat" which now uses microseconds for all
  time durations.  All time duration fields now have "_usec" appended
  to them for clarity.  While this doesn't solve the double accounting
  immediately, once majority of users switch to v2, cpu can directly
  account and report the relevant stats and cpuacct can be disabled on
  the unified hierarchy.

  Note that cpuacct.usage_percpu is currently not included in
  "cpu.stat".  If this information is actually called for, it can be
  added later.

* "cpu.shares" is replaced with "cpu.weight" and operates on the
  standard scale defined by CGROUP_WEIGHT_MIN/DFL/MAX (1, 100, 10000).
  The weight is scaled to scheduler weight so that 100 maps to 1024
  and the ratio relationship is preserved - if weight is W and its
  scaled value is S, W / 100 == S / 1024.  While the mapped range is a
  bit smaller than the orignal scheduler weight range, the dead zones
  on both sides are relatively small and covers wider range than the
  nice value mappings.  This file doesn't make sense in the root
  cgroup and isn't create on root.

* "cpu.cfs_quota_us" and "cpu.cfs_period_us" are replaced by "cpu.max"
  which contains both quota and period.

* "cpu.rt_runtime_us" and "cpu.rt_period_us" are replaced by
  "cpu.rt.max" which contains both runtime and period.

v2: cpu_stats_show() was incorrectly using CONFIG_FAIR_GROUP_SCHED for
    CFS bandwidth stats and also using raw division for u64.  Use
    CONFIG_CFS_BANDWITH and do_div() instead.

    The semantics of "cpu.rt.max" is not fully decided yet.  Dropped
    for now.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Li Zefan <lizefan@huawei.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
---
 kernel/sched/core.c    |  141 +++++++++++++++++++++++++++++++++++++++++++++++++
 kernel/sched/cpuacct.c |   24 ++++++++
 kernel/sched/cpuacct.h |    5 +
 3 files changed, 170 insertions(+)

--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -8567,6 +8567,139 @@ static struct cftype cpu_legacy_files[]
 	{ }	/* terminate */
 };
 
+static int cpu_stats_show(struct seq_file *sf, void *v)
+{
+	cpuacct_cpu_stats_show(sf);
+
+#ifdef CONFIG_CFS_BANDWIDTH
+	{
+		struct task_group *tg = css_tg(seq_css(sf));
+		struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth;
+		u64 throttled_usec;
+
+		throttled_usec = cfs_b->throttled_time;
+		do_div(throttled_usec, NSEC_PER_USEC);
+
+		seq_printf(sf, "nr_periods %d\n"
+			   "nr_throttled %d\n"
+			   "throttled_usec %llu\n",
+			   cfs_b->nr_periods, cfs_b->nr_throttled,
+			   throttled_usec);
+	}
+#endif
+	return 0;
+}
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+static u64 cpu_weight_read_u64(struct cgroup_subsys_state *css,
+			       struct cftype *cft)
+{
+	struct task_group *tg = css_tg(css);
+	u64 weight = scale_load_down(tg->shares);
+
+	return DIV_ROUND_CLOSEST_ULL(weight * CGROUP_WEIGHT_DFL, 1024);
+}
+
+static int cpu_weight_write_u64(struct cgroup_subsys_state *css,
+				struct cftype *cftype, u64 weight)
+{
+	/*
+	 * cgroup weight knobs should use the common MIN, DFL and MAX
+	 * values which are 1, 100 and 10000 respectively.  While it loses
+	 * a bit of range on both ends, it maps pretty well onto the shares
+	 * value used by scheduler and the round-trip conversions preserve
+	 * the original value over the entire range.
+	 */
+	if (weight < CGROUP_WEIGHT_MIN || weight > CGROUP_WEIGHT_MAX)
+		return -ERANGE;
+
+	weight = DIV_ROUND_CLOSEST_ULL(weight * 1024, CGROUP_WEIGHT_DFL);
+
+	return sched_group_set_shares(css_tg(css), scale_load(weight));
+}
+#endif
+
+static void __maybe_unused cpu_period_quota_print(struct seq_file *sf,
+						  long period, long quota)
+{
+	if (quota < 0)
+		seq_puts(sf, "max");
+	else
+		seq_printf(sf, "%ld", quota);
+
+	seq_printf(sf, " %ld\n", period);
+}
+
+/* caller should put the current value in *@periodp before calling */
+static int __maybe_unused cpu_period_quota_parse(char *buf,
+						 u64 *periodp, u64 *quotap)
+{
+	char tok[21];	/* U64_MAX */
+
+	if (!sscanf(buf, "%s %llu", tok, periodp))
+		return -EINVAL;
+
+	*periodp *= NSEC_PER_USEC;
+
+	if (sscanf(tok, "%llu", quotap))
+		*quotap *= NSEC_PER_USEC;
+	else if (!strcmp(tok, "max"))
+		*quotap = RUNTIME_INF;
+	else
+		return -EINVAL;
+
+	return 0;
+}
+
+#ifdef CONFIG_CFS_BANDWIDTH
+static int cpu_max_show(struct seq_file *sf, void *v)
+{
+	struct task_group *tg = css_tg(seq_css(sf));
+
+	cpu_period_quota_print(sf, tg_get_cfs_period(tg), tg_get_cfs_quota(tg));
+	return 0;
+}
+
+static ssize_t cpu_max_write(struct kernfs_open_file *of,
+			     char *buf, size_t nbytes, loff_t off)
+{
+	struct task_group *tg = css_tg(of_css(of));
+	u64 period = tg_get_cfs_period(tg);
+	u64 quota;
+	int ret;
+
+	ret = cpu_period_quota_parse(buf, &period, &quota);
+	if (!ret)
+		ret = tg_set_cfs_bandwidth(tg, period, quota);
+	return ret ?: nbytes;
+}
+#endif
+
+static struct cftype cpu_files[] = {
+	{
+		.name = "stat",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.seq_show = cpu_stats_show,
+	},
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	{
+		.name = "weight",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.read_u64 = cpu_weight_read_u64,
+		.write_u64 = cpu_weight_write_u64,
+	},
+#endif
+#ifdef CONFIG_CFS_BANDWIDTH
+	{
+		.name = "max",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.seq_show = cpu_max_show,
+		.write = cpu_max_write,
+	},
+#endif
+	{ }	/* terminate */
+};
+
 struct cgroup_subsys cpu_cgrp_subsys = {
 	.css_alloc	= cpu_cgroup_css_alloc,
 	.css_free	= cpu_cgroup_css_free,
@@ -8576,7 +8709,15 @@ struct cgroup_subsys cpu_cgrp_subsys = {
 	.can_attach	= cpu_cgroup_can_attach,
 	.attach		= cpu_cgroup_attach,
 	.legacy_cftypes	= cpu_legacy_files,
+	.dfl_cftypes	= cpu_files,
 	.early_init	= 1,
+#ifdef CONFIG_CGROUP_CPUACCT
+	/*
+	 * cpuacct is enabled together with cpu on the unified hierarchy
+	 * and its stats are reported through "cpu.stat".
+	 */
+	.depends_on	= 1 << cpuacct_cgrp_id,
+#endif
 };
 
 #endif	/* CONFIG_CGROUP_SCHED */
--- a/kernel/sched/cpuacct.c
+++ b/kernel/sched/cpuacct.c
@@ -224,6 +224,30 @@ static struct cftype files[] = {
 	{ }	/* terminate */
 };
 
+/* used to print cpuacct stats in cpu.stat on the unified hierarchy */
+void cpuacct_cpu_stats_show(struct seq_file *sf)
+{
+	struct cgroup_subsys_state *css;
+	u64 usage, user, sys;
+
+	css = cgroup_get_e_css(seq_css(sf)->cgroup, &cpuacct_cgrp_subsys);
+
+	usage = cpuusage_read(css, seq_cft(sf));
+	cpuacct_stats_read(css_ca(css), &user, &sys);
+
+	user *= TICK_NSEC;
+	sys *= TICK_NSEC;
+	do_div(usage, NSEC_PER_USEC);
+	do_div(user, NSEC_PER_USEC);
+	do_div(sys, NSEC_PER_USEC);
+
+	seq_printf(sf, "usage_usec %llu\n"
+		   "user_usec %llu\n"
+		   "system_usec %llu\n", usage, user, sys);
+
+	css_put(css);
+}
+
 /*
  * charge this task's execution time to its accounting group.
  *
--- a/kernel/sched/cpuacct.h
+++ b/kernel/sched/cpuacct.h
@@ -2,6 +2,7 @@
 
 extern void cpuacct_charge(struct task_struct *tsk, u64 cputime);
 extern void cpuacct_account_field(struct task_struct *p, int index, u64 val);
+extern void cpuacct_cpu_stats_show(struct seq_file *sf);
 
 #else
 
@@ -14,4 +15,8 @@ cpuacct_account_field(struct task_struct
 {
 }
 
+static inline void cpuacct_cpu_stats_show(struct seq_file *sf)
+{
+}
+
 #endif