linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: mingo@kernel.org, peterz@infradead.org
Cc: vincent.weaver@maine.edu, eranian@google.com, jolsa@redhat.com,
	linux-kernel@vger.kernel.org
Subject: [PATCH v2 11/11] perf/x86: Simplify put_exclusive_constraints
Date: Fri, 22 May 2015 15:29:16 +0200	[thread overview]
Message-ID: <20150522133136.355195312@infradead.org> (raw)
In-Reply-To: 20150522132905.416122812@infradead.org

[-- Attachment #1: peterz-pmu-sched-10.patch --]
[-- Type: text/plain, Size: 1992 bytes --]

Don't bother with taking locks if we're not actually going to do
anything. Also, drop the _irqsave(), this is very much only called
from IRQ-disabled context.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 arch/x86/kernel/cpu/perf_event_intel.c |   29 +++++++++++++++--------------
 1 file changed, 15 insertions(+), 14 deletions(-)

--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2130,7 +2130,6 @@ static void intel_put_excl_constraints(s
 	struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
 	int tid = cpuc->excl_thread_id;
 	struct intel_excl_states *xl;
-	unsigned long flags = 0; /* keep compiler happy */
 
 	/*
 	 * nothing needed if in group validation mode
@@ -2141,7 +2140,6 @@ static void intel_put_excl_constraints(s
 	if (WARN_ON_ONCE(!excl_cntrs))
 		return;
 
-	xl = &excl_cntrs->states[tid];
 	if (hwc->flags & PERF_X86_EVENT_EXCL_ACCT) {
 		hwc->flags &= ~PERF_X86_EVENT_EXCL_ACCT;
 		if (!--cpuc->n_excl)
@@ -2149,22 +2147,25 @@ static void intel_put_excl_constraints(s
 	}
 
 	/*
-	 * put_constraint may be called from x86_schedule_events()
-	 * which already has the lock held so here make locking
-	 * conditional
+	 * If event was actually assigned, then mark the counter state as
+	 * unused now.
 	 */
-	if (!xl->sched_started)
-		raw_spin_lock_irqsave(&excl_cntrs->lock, flags);
+	if (hwc->idx >= 0) {
+		xl = &excl_cntrs->states[tid];
+
+		/*
+		 * put_constraint may be called from x86_schedule_events()
+		 * which already has the lock held so here make locking
+		 * conditional.
+		 */
+		if (!xl->sched_started)
+			raw_spin_lock(&excl_cntrs->lock);
 
-	/*
-	 * if event was actually assigned, then mark the
-	 * counter state as unused now
-	 */
-	if (hwc->idx >= 0)
 		xl->state[hwc->idx] = INTEL_EXCL_UNUSED;
 
-	if (!xl->sched_started)
-		raw_spin_unlock_irqrestore(&excl_cntrs->lock, flags);
+		if (!xl->sched_started)
+			raw_spin_unlock(&excl_cntrs->lock);
+	}
 }
 
 static void



  parent reply	other threads:[~2015-05-22 13:35 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-05-22 13:29 [PATCH v2 00/11] Various x86 pmu scheduling patches Peter Zijlstra
2015-05-22 13:29 ` [PATCH v2 01/11] perf,x86: Fix event/group validation Peter Zijlstra
2015-05-22 13:40   ` Peter Zijlstra
2015-05-26  9:24     ` Stephane Eranian
2015-05-26 10:12       ` Peter Zijlstra
2015-05-26 11:46         ` Stephane Eranian
2015-05-26 12:16           ` Peter Zijlstra
2015-05-26 12:25             ` Stephane Eranian
2015-05-26 13:22               ` Peter Zijlstra
2015-05-26 13:44                 ` Stephane Eranian
2015-05-22 13:29 ` [PATCH v2 02/11] perf/x86: Improve HT workaround GP counter constraint Peter Zijlstra
2015-05-22 13:42   ` Peter Zijlstra
2015-05-26  9:37   ` Stephane Eranian
2015-05-26 10:15     ` Peter Zijlstra
2015-05-26 11:47       ` Stephane Eranian
2015-05-26 13:19         ` Peter Zijlstra
2015-05-26 16:07           ` Peter Zijlstra
2015-05-27  9:01             ` Stephane Eranian
2015-05-27 10:11               ` Peter Zijlstra
2015-05-27 11:39                 ` Stephane Eranian
2015-05-27 10:13               ` Peter Zijlstra
2015-05-27 11:44                 ` Stephane Eranian
2015-05-26 23:33   ` Andi Kleen
2015-05-27  7:48     ` Peter Zijlstra
2015-05-27 14:00       ` Andi Kleen
2015-05-22 13:29 ` [PATCH v2 03/11] perf/x86: Correct local vs remote sibling state Peter Zijlstra
2015-05-26 11:48   ` Stephane Eranian
2015-05-22 13:29 ` [PATCH v2 04/11] perf/x86: Use lockdep Peter Zijlstra
2015-05-22 13:29 ` [PATCH v2 05/11] perf/x86: Simplify dynamic constraint code somewhat Peter Zijlstra
2015-05-22 13:29 ` [PATCH v2 06/11] perf/x86: Make WARNs consistent Peter Zijlstra
2015-05-22 13:29 ` [PATCH v2 07/11] perf/x86: Move intel_commit_scheduling() Peter Zijlstra
2015-05-22 13:29 ` [PATCH v2 08/11] perf/x86: Remove pointless tests Peter Zijlstra
2015-05-22 13:29 ` [PATCH v2 09/11] perf/x86: Remove intel_excl_states::init_state Peter Zijlstra
2015-05-22 13:29 ` [PATCH v2 10/11] perf,x86: Simplify logic Peter Zijlstra
2015-05-22 13:29 ` Peter Zijlstra [this message]
2015-05-22 13:38   ` [PATCH v2 11/11] perf/x86: Simplify put_exclusive_constraints Peter Zijlstra

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=20150522133136.355195312@infradead.org \
    --to=peterz@infradead.org \
    --cc=eranian@google.com \
    --cc=jolsa@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=vincent.weaver@maine.edu \
    /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).