Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752737AbdGEKeZ (ORCPT ); Wed, 5 Jul 2017 06:34:25 -0400 Received: from terminus.zytor.com ([65.50.211.136]:59491 "EHLO terminus.zytor.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752357AbdGEKeX (ORCPT ); Wed, 5 Jul 2017 06:34:23 -0400 Date: Wed, 5 Jul 2017 03:29:40 -0700 From: tip-bot for Wanpeng Li Message-ID: Cc: hpa@zytor.com, linux-kernel@vger.kernel.org, torvalds@linux-foundation.org, mingo@kernel.org, fweisbec@gmail.com, peterz@infradead.org, lcapitulino@redhat.com, kernellwp@gmail.com, wanpeng.li@hotmail.com, tglx@linutronix.de, riel@redhat.com Reply-To: riel@redhat.com, tglx@linutronix.de, kernellwp@gmail.com, lcapitulino@redhat.com, wanpeng.li@hotmail.com, mingo@kernel.org, peterz@infradead.org, fweisbec@gmail.com, torvalds@linux-foundation.org, linux-kernel@vger.kernel.org, hpa@zytor.com In-Reply-To: <1498756511-11714-6-git-send-email-fweisbec@gmail.com> References: <1498756511-11714-6-git-send-email-fweisbec@gmail.com> To: linux-tip-commits@vger.kernel.org Subject: [tip:sched/urgent] sched/cputime: Accumulate vtime on top of nsec clocksource Git-Commit-ID: 2a42eb9594a1480b4ead9e036e06ee1290e5fa6d X-Mailer: tip-git-log-daemon Robot-ID: Robot-Unsubscribe: Contact to get blacklisted from these emails MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset=UTF-8 Content-Disposition: inline Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 7979 Lines: 229 Commit-ID: 2a42eb9594a1480b4ead9e036e06ee1290e5fa6d Gitweb: http://git.kernel.org/tip/2a42eb9594a1480b4ead9e036e06ee1290e5fa6d Author: Wanpeng Li AuthorDate: Thu, 29 Jun 2017 19:15:11 +0200 Committer: Ingo Molnar CommitDate: Wed, 5 Jul 2017 09:54:15 +0200 sched/cputime: Accumulate vtime on top of nsec clocksource Currently the cputime source used by vtime is jiffies. When we cross a context boundary and jiffies have changed since the last snapshot, the pending cputime is accounted to the switching out context. This system works ok if the ticks are not aligned across CPUs. If they instead are aligned (ie: all fire at the same time) and the CPUs run in userspace, the jiffies change is only observed on tick exit and therefore the user cputime is accounted as system cputime. This is because the CPU that maintains timekeeping fires its tick at the same time as the others. It updates jiffies in the middle of the tick and the other CPUs see that update on IRQ exit: CPU 0 (timekeeper) CPU 1 ------------------- ------------- jiffies = N ... run in userspace for a jiffy tick entry tick entry (sees jiffies = N) set jiffies = N + 1 tick exit tick exit (sees jiffies = N + 1) account 1 jiffy as stime Fix this with using a nanosec clock source instead of jiffies. The cputime is then accumulated and flushed everytime the pending delta reaches a jiffy in order to mitigate the accounting overhead. [ fweisbec: changelog, rebase on struct vtime, field renames, add delta on cputime readers, keep idle vtime as-is (low overhead accounting), harmonize clock sources. ] Suggested-by: Thomas Gleixner Reported-by: Luiz Capitulino Tested-by: Luiz Capitulino Signed-off-by: Wanpeng Li Signed-off-by: Frederic Weisbecker Reviewed-by: Thomas Gleixner Acked-by: Rik van Riel Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Wanpeng Li Link: http://lkml.kernel.org/r/1498756511-11714-6-git-send-email-fweisbec@gmail.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 3 +++ kernel/sched/cputime.c | 64 +++++++++++++++++++++++++++++++++----------------- 2 files changed, 45 insertions(+), 22 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index eeff8a0..4818126 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -236,6 +236,9 @@ struct vtime { seqcount_t seqcount; unsigned long long starttime; enum vtime_state state; + u64 utime; + u64 stime; + u64 gtime; }; struct sched_info { diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 9ee725e..6e3ea4a 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -681,18 +681,19 @@ void thread_group_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st) #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN static u64 vtime_delta(struct vtime *vtime) { - unsigned long now = READ_ONCE(jiffies); + unsigned long long clock; - if (time_before(now, (unsigned long)vtime->starttime)) + clock = sched_clock_cpu(smp_processor_id()); + if (clock < vtime->starttime) return 0; - return jiffies_to_nsecs(now - vtime->starttime); + return clock - vtime->starttime; } static u64 get_vtime_delta(struct vtime *vtime) { - unsigned long now = READ_ONCE(jiffies); - u64 delta, other; + u64 delta = vtime_delta(vtime); + u64 other; /* * Unlike tick based timing, vtime based timing never has lost @@ -701,17 +702,31 @@ static u64 get_vtime_delta(struct vtime *vtime) * elapsed time. Limit account_other_time to prevent rounding * errors from causing elapsed vtime to go negative. */ - delta = jiffies_to_nsecs(now - vtime->starttime); other = account_other_time(delta); WARN_ON_ONCE(vtime->state == VTIME_INACTIVE); - vtime->starttime = now; + vtime->starttime += delta; return delta - other; } -static void __vtime_account_system(struct task_struct *tsk) +static void __vtime_account_system(struct task_struct *tsk, + struct vtime *vtime) { - account_system_time(tsk, irq_count(), get_vtime_delta(&tsk->vtime)); + vtime->stime += get_vtime_delta(vtime); + if (vtime->stime >= TICK_NSEC) { + account_system_time(tsk, irq_count(), vtime->stime); + vtime->stime = 0; + } +} + +static void vtime_account_guest(struct task_struct *tsk, + struct vtime *vtime) +{ + vtime->gtime += get_vtime_delta(vtime); + if (vtime->gtime >= TICK_NSEC) { + account_guest_time(tsk, vtime->gtime); + vtime->gtime = 0; + } } void vtime_account_system(struct task_struct *tsk) @@ -722,7 +737,11 @@ void vtime_account_system(struct task_struct *tsk) return; write_seqcount_begin(&vtime->seqcount); - __vtime_account_system(tsk); + /* We might have scheduled out from guest path */ + if (current->flags & PF_VCPU) + vtime_account_guest(tsk, vtime); + else + __vtime_account_system(tsk, vtime); write_seqcount_end(&vtime->seqcount); } @@ -731,8 +750,7 @@ void vtime_user_enter(struct task_struct *tsk) struct vtime *vtime = &tsk->vtime; write_seqcount_begin(&vtime->seqcount); - if (vtime_delta(vtime)) - __vtime_account_system(tsk); + __vtime_account_system(tsk, vtime); vtime->state = VTIME_USER; write_seqcount_end(&vtime->seqcount); } @@ -742,8 +760,11 @@ void vtime_user_exit(struct task_struct *tsk) struct vtime *vtime = &tsk->vtime; write_seqcount_begin(&vtime->seqcount); - if (vtime_delta(vtime)) - account_user_time(tsk, get_vtime_delta(vtime)); + vtime->utime += get_vtime_delta(vtime); + if (vtime->utime >= TICK_NSEC) { + account_user_time(tsk, vtime->utime); + vtime->utime = 0; + } vtime->state = VTIME_SYS; write_seqcount_end(&vtime->seqcount); } @@ -759,8 +780,7 @@ void vtime_guest_enter(struct task_struct *tsk) * that can thus safely catch up with a tickless delta. */ write_seqcount_begin(&vtime->seqcount); - if (vtime_delta(vtime)) - __vtime_account_system(tsk); + __vtime_account_system(tsk, vtime); current->flags |= PF_VCPU; write_seqcount_end(&vtime->seqcount); } @@ -771,7 +791,7 @@ void vtime_guest_exit(struct task_struct *tsk) struct vtime *vtime = &tsk->vtime; write_seqcount_begin(&vtime->seqcount); - __vtime_account_system(tsk); + vtime_account_guest(tsk, vtime); current->flags &= ~PF_VCPU; write_seqcount_end(&vtime->seqcount); } @@ -794,7 +814,7 @@ void arch_vtime_task_switch(struct task_struct *prev) write_seqcount_begin(&vtime->seqcount); vtime->state = VTIME_SYS; - vtime->starttime = jiffies; + vtime->starttime = sched_clock_cpu(smp_processor_id()); write_seqcount_end(&vtime->seqcount); } @@ -806,7 +826,7 @@ void vtime_init_idle(struct task_struct *t, int cpu) local_irq_save(flags); write_seqcount_begin(&vtime->seqcount); vtime->state = VTIME_SYS; - vtime->starttime = jiffies; + vtime->starttime = sched_clock_cpu(cpu); write_seqcount_end(&vtime->seqcount); local_irq_restore(flags); } @@ -825,7 +845,7 @@ u64 task_gtime(struct task_struct *t) gtime = t->gtime; if (vtime->state == VTIME_SYS && t->flags & PF_VCPU) - gtime += vtime_delta(vtime); + gtime += vtime->gtime + vtime_delta(vtime); } while (read_seqcount_retry(&vtime->seqcount, seq)); @@ -866,9 +886,9 @@ void task_cputime(struct task_struct *t, u64 *utime, u64 *stime) * the right place. */ if (vtime->state == VTIME_USER || t->flags & PF_VCPU) - *utime += delta; + *utime += vtime->utime + delta; else if (vtime->state == VTIME_SYS) - *stime += delta; + *stime += vtime->stime + delta; } while (read_seqcount_retry(&vtime->seqcount, seq)); } #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */