All of lore.kernel.org
 help / color / mirror / Atom feed
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
To: Ingo Molnar <mingo@elte.hu>
Cc: Paul Mackerras <paulus@samba.org>,
	Corey Ashford <cjashfor@linux.vnet.ibm.com>,
	linux-kernel@vger.kernel.org,
	Peter Zijlstra <a.p.zijlstra@chello.nl>
Subject: [PATCH 13/15] perf_counter: rework the task clock software counter
Date: Mon, 06 Apr 2009 11:45:11 +0200	[thread overview]
Message-ID: <20090406094518.445450972@chello.nl> (raw)
In-Reply-To: 20090406094458.977814421@chello.nl

[-- Attachment #1: perf_counter-sw-task-clock.patch --]
[-- Type: text/plain, Size: 2973 bytes --]

Rework the task clock software counter to use the context time instead
of the task runtime clock, this removes the last such user.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
 kernel/perf_counter.c |   42 ++++++++++++------------------------------
 1 file changed, 12 insertions(+), 30 deletions(-)

Index: linux-2.6/kernel/perf_counter.c
===================================================================
--- linux-2.6.orig/kernel/perf_counter.c
+++ linux-2.6/kernel/perf_counter.c
@@ -974,9 +974,6 @@ int perf_counter_task_disable(void)
 	curr_rq_lock_irq_save(&flags);
 	cpu = smp_processor_id();
 
-	/* force the update of the task clock: */
-	__task_delta_exec(curr, 1);
-
 	perf_counter_task_sched_out(curr, cpu);
 
 	spin_lock(&ctx->lock);
@@ -1017,9 +1014,6 @@ int perf_counter_task_enable(void)
 	curr_rq_lock_irq_save(&flags);
 	cpu = smp_processor_id();
 
-	/* force the update of the task clock: */
-	__task_delta_exec(curr, 1);
-
 	perf_counter_task_sched_out(curr, cpu);
 
 	spin_lock(&ctx->lock);
@@ -2347,38 +2341,28 @@ static const struct hw_perf_counter_ops 
  * Software counter: task time clock
  */
 
-/*
- * Called from within the scheduler:
- */
-static u64 task_clock_perf_counter_val(struct perf_counter *counter, int update)
-{
-	struct task_struct *curr = counter->task;
-	u64 delta;
-
-	delta = __task_delta_exec(curr, update);
-
-	return curr->se.sum_exec_runtime + delta;
-}
-
-static void task_clock_perf_counter_update(struct perf_counter *counter, u64 now)
+static void task_clock_perf_counter_update(struct perf_counter *counter)
 {
-	u64 prev;
+	u64 prev, now;
 	s64 delta;
 
-	prev = atomic64_read(&counter->hw.prev_count);
-
-	atomic64_set(&counter->hw.prev_count, now);
+	update_context_time(counter->ctx);
+	now = counter->ctx->time;
 
+	prev = atomic64_xchg(&counter->hw.prev_count, now);
 	delta = now - prev;
-
 	atomic64_add(delta, &counter->count);
 }
 
 static int task_clock_perf_counter_enable(struct perf_counter *counter)
 {
 	struct hw_perf_counter *hwc = &counter->hw;
+	u64 now;
+
+	update_context_time(counter->ctx);
+	now = counter->ctx->time;
 
-	atomic64_set(&hwc->prev_count, task_clock_perf_counter_val(counter, 0));
+	atomic64_set(&hwc->prev_count, now);
 	hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	hwc->hrtimer.function = perf_swcounter_hrtimer;
 	if (hwc->irq_period) {
@@ -2393,14 +2377,12 @@ static int task_clock_perf_counter_enabl
 static void task_clock_perf_counter_disable(struct perf_counter *counter)
 {
 	hrtimer_cancel(&counter->hw.hrtimer);
-	task_clock_perf_counter_update(counter,
-			task_clock_perf_counter_val(counter, 0));
+	task_clock_perf_counter_update(counter);
 }
 
 static void task_clock_perf_counter_read(struct perf_counter *counter)
 {
-	task_clock_perf_counter_update(counter,
-			task_clock_perf_counter_val(counter, 1));
+	task_clock_perf_counter_update(counter);
 }
 
 static const struct hw_perf_counter_ops perf_ops_task_clock = {

-- 


  parent reply	other threads:[~2009-04-06  9:48 UTC|newest]

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-04-06  9:44 [PATCH 00/15] various perf counter bits Peter Zijlstra
2009-04-06  9:44 ` [PATCH 01/15] perf_counter: update mmap() counter read, take 2 Peter Zijlstra
2009-04-07  9:06   ` [tip:perfcounters/core] " Peter Zijlstra
2009-04-06  9:45 ` [PATCH 02/15] perf_counter: add more context information Peter Zijlstra
2009-04-07  9:07   ` [tip:perfcounters/core] " Peter Zijlstra
2009-04-06  9:45 ` [PATCH 03/15] perf_counter: SIGIO support Peter Zijlstra
2009-04-07  9:07   ` [tip:perfcounters/core] " Peter Zijlstra
2009-04-06  9:45 ` [PATCH 04/15] perf_counter: generalize pending infrastructure Peter Zijlstra
2009-04-07  9:07   ` [tip:perfcounters/core] " Peter Zijlstra
2009-04-06  9:45 ` [PATCH 05/15] perf_counter: x86: self-IPI for pending work Peter Zijlstra
2009-04-07  9:07   ` [tip:perfcounters/core] " Peter Zijlstra
2009-04-06  9:45 ` [PATCH 06/15] perf_counter: theres more to overflow than writing events Peter Zijlstra
2009-04-07  9:07   ` [tip:perfcounters/core] " Peter Zijlstra
2009-04-06  9:45 ` [PATCH 07/15] perf_counter: fix the mlock accounting Peter Zijlstra
2009-04-07  9:08   ` [tip:perfcounters/core] " Peter Zijlstra
2009-04-06  9:45 ` [PATCH 08/15] perf_counter: PERF_RECORD_TIME Peter Zijlstra
2009-04-07  9:08   ` [tip:perfcounters/core] " Peter Zijlstra
2009-04-06  9:45 ` [PATCH 09/15] perf_counter: counter overflow limit Peter Zijlstra
2009-04-07  9:08   ` [tip:perfcounters/core] " Peter Zijlstra
2009-04-06  9:45 ` [PATCH 10/15] perf_counter: comment the perf_event_type stuff Peter Zijlstra
2009-04-07  9:08   ` [tip:perfcounters/core] " Peter Zijlstra
2009-04-06  9:45 ` [PATCH 11/15] perf_counter: change event defenition Peter Zijlstra
2009-04-07  9:08   ` [tip:perfcounters/core] perf_counter: change event definition Peter Zijlstra
2009-04-06  9:45 ` [PATCH 12/15] perf_counter: rework context time Peter Zijlstra
2009-04-07  9:09   ` [tip:perfcounters/core] " Peter Zijlstra
2009-04-06  9:45 ` Peter Zijlstra [this message]
2009-04-07  9:09   ` [tip:perfcounters/core] perf_counter: rework the task clock software counter Peter Zijlstra
2009-04-07  9:36   ` [tip:perfcounters/core] x86, perfcounters: add atomic64_xchg() Ingo Molnar
2009-04-07 11:19     ` Paul Mackerras
2009-04-07 13:28       ` Ingo Molnar
2009-04-07 10:06   ` Ingo Molnar
2009-04-06  9:45 ` [PATCH 14/15] perf_counter: remove rq->lock usage Peter Zijlstra
2009-04-07  9:09   ` [tip:perfcounters/core] " Peter Zijlstra
2009-04-06  9:45 ` [PATCH 15/15] perf_counter: minimize context time updates Peter Zijlstra
2009-04-07  9:09   ` [tip:perfcounters/core] " Peter Zijlstra
2009-04-07  9:21 ` [PATCH 00/15] various perf counter bits Ingo Molnar
2009-04-07  9:21   ` Ingo Molnar
2009-04-07  9:33   ` Ingo Molnar
2009-04-07  9:23 ` Ingo Molnar

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=20090406094518.445450972@chello.nl \
    --to=a.p.zijlstra@chello.nl \
    --cc=cjashfor@linux.vnet.ibm.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    --cc=paulus@samba.org \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.