From: Frederic Weisbecker <frederic@kernel.org>
To: LKML <linux-kernel@vger.kernel.org>
Cc: Frederic Weisbecker <frederic@kernel.org>,
Peter Zijlstra <peterz@infradead.org>,
Wanpeng Li <wanpengli@tencent.com>,
Thomas Gleixner <tglx@linutronix.de>,
Yauheni Kaliuta <yauheni.kaliuta@redhat.com>,
Ingo Molnar <mingo@kernel.org>, Rik van Riel <riel@redhat.com>
Subject: [PATCH 04/25] vtime: Spare a seqcount lock/unlock cycle on context switch
Date: Wed, 14 Nov 2018 03:45:48 +0100 [thread overview]
Message-ID: <1542163569-20047-5-git-send-email-frederic@kernel.org> (raw)
In-Reply-To: <1542163569-20047-1-git-send-email-frederic@kernel.org>
On context switch we are locking the vtime seqcount of the scheduling-out
task twice:
* On vtime_task_switch_common(), when we flush the pending vtime through
vtime_account_system() / vtime_account_idle()
* On arch_vtime_task_switch() to reset the vtime state.
This is pointless as these actions can be performed without the need
to unlock/lock in the middle. The reason these steps are separated is to
consolidate a very small amount of common code between
CONFIG_VIRT_CPU_ACCOUNTING_GEN and CONFIG_VIRT_CPU_ACCOUNTING_NATIVE.
Performance in this fast path is definetly a priority over artificial
code factorization so split the task switch code between GEN and
NATIVE and mutualize the parts than can run under a single seqcount
locked 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@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wanpeng Li <wanpengli@tencent.com>
Cc: Ingo Molnar <mingo@kernel.org>
---
include/linux/vtime.h | 32 ++++++++++++++++----------------
kernel/sched/cputime.c | 38 +++++++++++++++++++++-----------------
2 files changed, 37 insertions(+), 33 deletions(-)
diff --git a/include/linux/vtime.h b/include/linux/vtime.h
index 2fd247f..d9160ab 100644
--- a/include/linux/vtime.h
+++ b/include/linux/vtime.h
@@ -14,8 +14,12 @@ struct task_struct;
* vtime_accounting_cpu_enabled() definitions/declarations
*/
#if defined(CONFIG_VIRT_CPU_ACCOUNTING_NATIVE)
+
static inline bool vtime_accounting_cpu_enabled(void) { return true; }
+extern void vtime_task_switch(struct task_struct *prev);
+
#elif defined(CONFIG_VIRT_CPU_ACCOUNTING_GEN)
+
/*
* Checks if vtime is enabled on some CPU. Cputime readers want to be careful
* in that case and compute the tickless cputime.
@@ -36,33 +40,29 @@ static inline bool vtime_accounting_cpu_enabled(void)
return false;
}
+
+extern void vtime_task_switch_generic(struct task_struct *prev);
+
+static inline void vtime_task_switch(struct task_struct *prev)
+{
+ if (vtime_accounting_cpu_enabled())
+ vtime_task_switch_generic(prev);
+}
+
#else /* !CONFIG_VIRT_CPU_ACCOUNTING */
+
static inline bool vtime_accounting_cpu_enabled(void) { return false; }
-#endif
+static inline void vtime_task_switch(struct task_struct *prev) { }
+#endif
/*
* Common vtime APIs
*/
#ifdef CONFIG_VIRT_CPU_ACCOUNTING
-
-#ifdef __ARCH_HAS_VTIME_TASK_SWITCH
-extern void vtime_task_switch(struct task_struct *prev);
-#else
-extern void vtime_common_task_switch(struct task_struct *prev);
-static inline void vtime_task_switch(struct task_struct *prev)
-{
- if (vtime_accounting_cpu_enabled())
- vtime_common_task_switch(prev);
-}
-#endif /* __ARCH_HAS_VTIME_TASK_SWITCH */
-
extern void vtime_account_kernel(struct task_struct *tsk);
extern void vtime_account_idle(struct task_struct *tsk);
-
#else /* !CONFIG_VIRT_CPU_ACCOUNTING */
-
-static inline void vtime_task_switch(struct task_struct *prev) { }
static inline void vtime_account_kernel(struct task_struct *tsk) { }
#endif /* !CONFIG_VIRT_CPU_ACCOUNTING */
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 63f10ac..facc665 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -404,9 +404,10 @@ static inline void irqtime_account_process_tick(struct task_struct *p, int user_
/*
* Use precise platform statistics if available:
*/
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+
# ifndef __ARCH_HAS_VTIME_TASK_SWITCH
-void vtime_common_task_switch(struct task_struct *prev)
+void vtime_task_switch(struct task_struct *prev)
{
if (is_idle_task(prev))
vtime_account_idle(prev);
@@ -417,10 +418,7 @@ void vtime_common_task_switch(struct task_struct *prev)
arch_vtime_task_switch(prev);
}
# endif
-#endif /* CONFIG_VIRT_CPU_ACCOUNTING */
-
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
/*
* Archs that account the whole time spent in the idle task
* (outside irq) as idle time can rely on this and just implement
@@ -730,19 +728,25 @@ static void vtime_account_guest(struct task_struct *tsk,
}
}
-void vtime_account_kernel(struct task_struct *tsk)
+static void __vtime_account_kernel(struct task_struct *tsk,
+ struct vtime *vtime)
{
- struct vtime *vtime = &tsk->vtime;
-
- if (!vtime_delta(vtime))
- return;
-
- write_seqcount_begin(&vtime->seqcount);
/* We might have scheduled out from guest path */
if (tsk->flags & PF_VCPU)
vtime_account_guest(tsk, vtime);
else
vtime_account_system(tsk, vtime);
+}
+
+void vtime_account_kernel(struct task_struct *tsk)
+{
+ struct vtime *vtime = &tsk->vtime;
+
+ if (!vtime_delta(vtime))
+ return;
+
+ write_seqcount_begin(&vtime->seqcount);
+ __vtime_account_kernel(tsk, vtime);
write_seqcount_end(&vtime->seqcount);
}
@@ -800,18 +804,18 @@ EXPORT_SYMBOL_GPL(vtime_guest_exit);
void vtime_account_idle(struct task_struct *tsk)
{
- struct vtime *vtime = &tsk->vtime;
-
- write_seqcount_begin(&vtime->seqcount);
account_idle_time(get_vtime_delta(&tsk->vtime));
- write_seqcount_end(&vtime->seqcount);
}
-void arch_vtime_task_switch(struct task_struct *prev)
+void vtime_task_switch_generic(struct task_struct *prev)
{
struct vtime *vtime = &prev->vtime;
write_seqcount_begin(&vtime->seqcount);
+ if (is_idle_task(prev))
+ vtime_account_idle(prev);
+ else
+ __vtime_account_kernel(prev, vtime);
vtime->state = VTIME_INACTIVE;
write_seqcount_end(&vtime->seqcount);
--
2.7.4
next prev parent reply other threads:[~2018-11-14 2:46 UTC|newest]
Thread overview: 45+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-11-14 2:45 [PATCH 00/25] sched/nohz: Make kcpustat vtime aware (Fix kcpustat on nohz_full) Frederic Weisbecker
2018-11-14 2:45 ` [PATCH 01/25] sched/vtime: Fix guest/system mis-accounting on task switch Frederic Weisbecker
2018-11-14 2:45 ` [PATCH 02/25] sched/vtime: Protect idle accounting under vtime seqcount Frederic Weisbecker
2018-11-20 13:19 ` Peter Zijlstra
2018-11-14 2:45 ` [PATCH 03/25] vtime: Rename vtime_account_system() to vtime_account_kernel() Frederic Weisbecker
2018-11-14 2:45 ` Frederic Weisbecker [this message]
2018-11-20 13:25 ` [PATCH 04/25] vtime: Spare a seqcount lock/unlock cycle on context switch Peter Zijlstra
2019-09-25 14:42 ` Frederic Weisbecker
2018-11-14 2:45 ` [PATCH 05/25] sched/vtime: Record CPU under seqcount for kcpustat needs Frederic Weisbecker
2018-11-14 2:45 ` [PATCH 06/25] sched/cputime: Add vtime idle task state Frederic Weisbecker
2018-11-14 2:45 ` [PATCH 07/25] sched/cputime: Add vtime guest " Frederic Weisbecker
2018-11-14 2:45 ` [PATCH 08/25] vtime: Exit vtime before exit_notify() Frederic Weisbecker
2018-11-20 13:54 ` Peter Zijlstra
2018-11-14 2:45 ` [PATCH 09/25] kcpustat: Track running task following vtime sequences Frederic Weisbecker
2018-11-20 13:58 ` Peter Zijlstra
2018-11-14 2:45 ` [PATCH 10/25] context_tracking: Remove context_tracking_active() Frederic Weisbecker
2018-11-14 2:45 ` [PATCH 11/25] context_tracking: s/context_tracking_is_enabled/context_tracking_enabled() Frederic Weisbecker
2018-11-14 2:45 ` [PATCH 12/25] context_tracking: Rename context_tracking_is_cpu_enabled() to context_tracking_enabled_this_cpu() Frederic Weisbecker
2018-11-14 2:45 ` [PATCH 13/25] context_tracking: Introduce context_tracking_enabled_cpu() Frederic Weisbecker
2018-11-20 14:02 ` Peter Zijlstra
2018-11-14 2:45 ` [PATCH 14/25] sched/vtime: Rename vtime_accounting_cpu_enabled() to vtime_accounting_enabled_this_cpu() Frederic Weisbecker
2018-11-14 2:45 ` [PATCH 15/25] sched/vtime: Introduce vtime_accounting_enabled_cpu() Frederic Weisbecker
2018-11-20 14:04 ` Peter Zijlstra
2018-11-14 2:46 ` [PATCH 16/25] sched/cputime: Allow to pass cputime index on user/guest accounting Frederic Weisbecker
2018-11-14 2:46 ` [PATCH 17/25] sched/cputime: Standardize the kcpustat index based accounting functions Frederic Weisbecker
2018-11-14 2:46 ` [PATCH 18/25] vtime: Track nice-ness on top of context switch Frederic Weisbecker
2018-11-20 14:09 ` Peter Zijlstra
2018-11-14 2:46 ` [PATCH 19/25] sched/vite: Handle nice updates under vtime Frederic Weisbecker
2018-11-20 14:17 ` Peter Zijlstra
2018-11-26 15:53 ` Frederic Weisbecker
2018-11-26 16:11 ` Peter Zijlstra
2018-11-26 18:41 ` Frederic Weisbecker
2018-11-14 2:46 ` [PATCH 20/25] sched/kcpustat: Introduce vtime-aware kcpustat accessor Frederic Weisbecker
2018-11-20 14:23 ` Peter Zijlstra
2018-11-20 22:40 ` Frederic Weisbecker
2018-11-21 8:18 ` Peter Zijlstra
2018-11-21 8:35 ` Peter Zijlstra
2018-11-21 16:33 ` Frederic Weisbecker
2018-11-14 2:46 ` [PATCH 21/25] procfs: Use vtime aware " Frederic Weisbecker
2018-11-20 14:24 ` Peter Zijlstra
2018-11-20 22:31 ` Frederic Weisbecker
2018-11-14 2:46 ` [PATCH 22/25] cpufreq: " Frederic Weisbecker
2018-11-14 2:46 ` [PATCH 23/25] leds: Use vtime aware kcpustat accessors Frederic Weisbecker
2018-11-14 2:46 ` [PATCH 24/25] rackmeter: " Frederic Weisbecker
2018-11-14 2:46 ` [PATCH 25/25] sched/vtime: Clarify vtime_task_switch() argument layout 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=1542163569-20047-5-git-send-email-frederic@kernel.org \
--to=frederic@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=peterz@infradead.org \
--cc=riel@redhat.com \
--cc=tglx@linutronix.de \
--cc=wanpengli@tencent.com \
--cc=yauheni.kaliuta@redhat.com \
/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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
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).