linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Frederic Weisbecker <frederic@kernel.org>
To: Peter Zijlstra <peterz@infradead.org>, Ingo Molnar <mingo@kernel.org>
Cc: LKML <linux-kernel@vger.kernel.org>,
	Frederic Weisbecker <frederic@kernel.org>,
	Jacek Anaszewski <jacek.anaszewski@gmail.com>,
	Wanpeng Li <wanpengli@tencent.com>,
	"Rafael J . Wysocki" <rjw@rjwysocki.net>,
	Benjamin Herrenschmidt <benh@kernel.crashing.org>,
	Rik van Riel <riel@surriel.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Yauheni Kaliuta <yauheni.kaliuta@redhat.com>,
	Viresh Kumar <viresh.kumar@linaro.org>,
	Pavel Machek <pavel@ucw.cz>
Subject: [PATCH 2/6] sched/vtime: Bring all-in-one kcpustat accessor for vtime fields
Date: Wed, 20 Nov 2019 00:22:14 +0100	[thread overview]
Message-ID: <20191119232218.4206-3-frederic@kernel.org> (raw)
In-Reply-To: <20191119232218.4206-1-frederic@kernel.org>

Many callsites want to fetch the values of system, user, user_nice, guest
or guest_nice kcpustat fields altogether or at least a pair of these.

In that case calling kcpustat_field() for each requested field brings
unecessary overhead when we could fetch all of them in a row.

So provide kcpustat_cputime() that fetches all vtime sensitive fields
under the same RCU and seqcount block.

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Cc: Yauheni Kaliuta <yauheni.kaliuta@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Rik van Riel <riel@surriel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wanpeng Li <wanpengli@tencent.com>
Cc: Ingo Molnar <mingo@kernel.org>
---
 include/linux/kernel_stat.h |  23 ++++++
 kernel/sched/cputime.c      | 139 ++++++++++++++++++++++++++++++------
 2 files changed, 142 insertions(+), 20 deletions(-)

diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index 79781196eb25..6bd70e464c61 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -78,15 +78,38 @@ static inline unsigned int kstat_cpu_irqs_sum(unsigned int cpu)
 	return kstat_cpu(cpu).irqs_sum;
 }
 
+
+static inline void kcpustat_cputime_raw(u64 *cpustat, u64 *user, u64 *nice,
+					u64 *system, u64 *guest, u64 *guest_nice)
+{
+	*user = cpustat[CPUTIME_USER];
+	*nice = cpustat[CPUTIME_NICE];
+	*system = cpustat[CPUTIME_SYSTEM];
+	*guest = cpustat[CPUTIME_GUEST];
+	*guest_nice = cpustat[CPUTIME_GUEST_NICE];
+}
+
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
 extern u64 kcpustat_field(struct kernel_cpustat *kcpustat,
 			  enum cpu_usage_stat usage, int cpu);
+extern void kcpustat_cputime(struct kernel_cpustat *kcpustat, int cpu,
+			     u64 *user, u64 *nice, u64 *system,
+			     u64 *guest, u64 *guest_nice);
 #else
 static inline u64 kcpustat_field(struct kernel_cpustat *kcpustat,
 				 enum cpu_usage_stat usage, int cpu)
 {
 	return kcpustat->cpustat[usage];
 }
+
+static inline void kcpustat_cputime(struct kernel_cpustat *kcpustat, int cpu,
+				    u64 *user, u64 *nice, u64 *system,
+				    u64 *guest, u64 *guest_nice)
+{
+	kcpustat_cputime_raw(kcpustat->cpustat, user, nice,
+			     system, guest, guest_nice);
+}
+
 #endif
 
 extern void account_user_time(struct task_struct *, u64);
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index b2cf544e2109..f576bbb1f4ee 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -912,6 +912,30 @@ void task_cputime(struct task_struct *t, u64 *utime, u64 *stime)
 	} while (read_seqcount_retry(&vtime->seqcount, seq));
 }
 
+static int vtime_state_check(struct vtime *vtime, int cpu)
+{
+	/*
+	 * We raced against context switch, fetch the
+	 * kcpustat task again.
+	 */
+	if (vtime->cpu != cpu && vtime->cpu != -1)
+		return -EAGAIN;
+
+	/*
+	 * Two possible things here:
+	 * 1) We are seeing the scheduling out task (prev) or any past one.
+	 * 2) We are seeing the scheduling in task (next) but it hasn't
+	 *    passed though vtime_task_switch() yet so the pending
+	 *    cputime of the prev task may not be flushed yet.
+	 *
+	 * Case 1) is ok but 2) is not. So wait for a safe VTIME state.
+	 */
+	if (vtime->state == VTIME_INACTIVE)
+		return -EAGAIN;
+
+	return 0;
+}
+
 static u64 kcpustat_user_vtime(struct vtime *vtime)
 {
 	if (vtime->state == VTIME_USER)
@@ -933,26 +957,9 @@ static int kcpustat_field_vtime(u64 *cpustat,
 	do {
 		seq = read_seqcount_begin(&vtime->seqcount);
 
-		/*
-		 * We raced against context switch, fetch the
-		 * kcpustat task again.
-		 */
-		if (vtime->cpu != cpu && vtime->cpu != -1)
-			return -EAGAIN;
-
-		/*
-		 * Two possible things here:
-		 * 1) We are seeing the scheduling out task (prev) or any past one.
-		 * 2) We are seeing the scheduling in task (next) but it hasn't
-		 *    passed though vtime_task_switch() yet so the pending
-		 *    cputime of the prev task may not be flushed yet.
-		 *
-		 * Case 1) is ok but 2) is not. So wait for a safe VTIME state.
-		 */
-		if (vtime->state == VTIME_INACTIVE)
-			return -EAGAIN;
-
-		err = 0;
+		err = vtime_state_check(vtime, cpu);
+		if (err < 0)
+			return err;
 
 		*val = cpustat[usage];
 
@@ -1024,4 +1031,96 @@ u64 kcpustat_field(struct kernel_cpustat *kcpustat,
 	}
 }
 EXPORT_SYMBOL_GPL(kcpustat_field);
+
+static int kcpustat_cputime_vtime(u64 *cpustat, struct task_struct *tsk,
+				  int cpu, u64 *user, u64 *nice,
+				  u64 *system, u64 *guest, u64 *guest_nice)
+{
+	struct vtime *vtime = &tsk->vtime;
+	unsigned int seq;
+	u64 delta;
+	int err;
+
+	do {
+		seq = read_seqcount_begin(&vtime->seqcount);
+
+		err = vtime_state_check(vtime, cpu);
+		if (err < 0)
+			return err;
+
+		kcpustat_cputime_raw(cpustat, user, nice,
+				     system, guest, guest_nice);
+
+		/* Task is sleeping, dead or idle, nothing to add */
+		if (vtime->state < VTIME_SYS)
+			continue;
+
+		delta = vtime_delta(vtime);
+
+		/*
+		 * Task runs either in user (including guest) or kernel space,
+		 * add pending nohz time to the right place.
+		 */
+		if (vtime->state == VTIME_SYS) {
+			*system += vtime->stime + delta;
+		} else if (vtime->state == VTIME_USER) {
+			if (task_nice(tsk) > 0)
+				*nice += vtime->utime + delta;
+			else
+				*user += vtime->utime + delta;
+		} else {
+			WARN_ON_ONCE(vtime->state != VTIME_GUEST);
+			if (task_nice(tsk) > 0) {
+				*guest_nice += vtime->gtime + delta;
+				*nice += vtime->gtime + delta;
+			} else {
+				*guest += vtime->gtime + delta;
+				*user += vtime->gtime + delta;
+			}
+		}
+	} while (read_seqcount_retry(&vtime->seqcount, seq));
+
+	return err;
+}
+
+void kcpustat_cputime(struct kernel_cpustat *kcpustat, int cpu,
+		      u64 *user, u64 *nice, u64 *system,
+		      u64 *guest, u64 *guest_nice)
+{
+	u64 *cpustat = kcpustat->cpustat;
+	struct rq *rq;
+	int err;
+
+	if (!vtime_accounting_enabled_cpu(cpu)) {
+		kcpustat_cputime_raw(cpustat, user, nice,
+				     system, guest, guest_nice);
+		return;
+	}
+
+	rq = cpu_rq(cpu);
+
+	for (;;) {
+		struct task_struct *curr;
+
+		rcu_read_lock();
+		curr = rcu_dereference(rq->curr);
+		if (WARN_ON_ONCE(!curr)) {
+			rcu_read_unlock();
+			kcpustat_cputime_raw(cpustat, user, nice,
+					     system, guest, guest_nice);
+			return;
+		}
+
+		err = kcpustat_cputime_vtime(cpustat, curr, cpu, user,
+					     nice, system, guest, guest_nice);
+		rcu_read_unlock();
+
+		if (!err)
+			return;
+
+		cpu_relax();
+	}
+}
+EXPORT_SYMBOL_GPL(kcpustat_cputime);
+
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */
-- 
2.23.0


  parent reply	other threads:[~2019-11-19 23:22 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-11-19 23:22 [PATCH 0/6] sched/nohz: Make the rest of kcpustat vtime aware v2 Frederic Weisbecker
2019-11-19 23:22 ` [PATCH 1/6] sched/cputime: Support other fields on kcpustat_field() Frederic Weisbecker
2019-11-20 11:51   ` Ingo Molnar
2019-11-20 21:04     ` Peter Zijlstra
2019-11-19 23:22 ` Frederic Weisbecker [this message]
2019-11-20 12:04   ` [PATCH 2/6] sched/vtime: Bring all-in-one kcpustat accessor for vtime fields Ingo Molnar
2019-11-20 15:00     ` Frederic Weisbecker
2019-11-19 23:22 ` [PATCH 3/6] procfs: Use all-in-one vtime aware kcpustat accessor Frederic Weisbecker
2019-11-19 23:22 ` [PATCH 4/6] cpufreq: Use vtime aware kcpustat accessors for user time Frederic Weisbecker
2019-11-19 23:22 ` [PATCH 5/6] leds: Use all-in-one vtime aware kcpustat accessor Frederic Weisbecker
2019-11-19 23:22 ` [PATCH 6/6] rackmeter: Use " Frederic Weisbecker

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20191119232218.4206-3-frederic@kernel.org \
    --to=frederic@kernel.org \
    --cc=benh@kernel.crashing.org \
    --cc=jacek.anaszewski@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=pavel@ucw.cz \
    --cc=peterz@infradead.org \
    --cc=riel@surriel.com \
    --cc=rjw@rjwysocki.net \
    --cc=tglx@linutronix.de \
    --cc=viresh.kumar@linaro.org \
    --cc=wanpengli@tencent.com \
    --cc=yauheni.kaliuta@redhat.com \
    --subject='Re: [PATCH 2/6] sched/vtime: Bring all-in-one kcpustat accessor for vtime fields' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).