From: Peter Zijlstra <a.p.zijlstra@chello.nl>
To: mingo@elte.hu, linux-kernel@vger.kernel.org
Cc: paulus@samba.org, eranian@google.com, robert.richter@amd.com,
fweisbec@gmail.com, Arnaldo Carvalho de Melo <acme@infradead.org>,
Peter Zijlstra <a.p.zijlstra@chello.nl>
Subject: [PATCH 4/5] perf, x86: Clear the LBRs on init
Date: Fri, 05 Mar 2010 16:39:30 +0100 [thread overview]
Message-ID: <20100305154128.966563424@chello.nl> (raw)
In-Reply-To: 20100305153926.639506880@chello.nl
[-- Attachment #1: lbr-errata-aak136.patch --]
[-- Type: text/plain, Size: 1916 bytes --]
Some CPUs have errata where the LBR is not cleared on Power-On. So
always clear the LBRs before use.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
arch/x86/kernel/cpu/perf_event_intel.c | 18 ++++++++++++++++--
arch/x86/kernel/cpu/perf_event_intel_lbr.c | 3 +++
2 files changed, 19 insertions(+), 2 deletions(-)
Index: linux-2.6/arch/x86/kernel/cpu/perf_event_intel.c
===================================================================
--- linux-2.6.orig/arch/x86/kernel/cpu/perf_event_intel.c
+++ linux-2.6/arch/x86/kernel/cpu/perf_event_intel.c
@@ -775,6 +775,20 @@ static __initconst struct x86_pmu core_p
.event_constraints = intel_core_event_constraints,
};
+static void intel_pmu_cpu_starting(int cpu)
+{
+ init_debug_store_on_cpu(cpu);
+ /*
+ * Deal with CPUs that don't clear their LBRs on power-up.
+ */
+ intel_pmu_lbr_reset();
+}
+
+static void intel_pmu_cpu_dying(int cpu)
+{
+ fini_debug_store_on_cpu(cpu);
+}
+
static __initconst struct x86_pmu intel_pmu = {
.name = "Intel",
.handle_irq = intel_pmu_handle_irq,
@@ -796,8 +810,8 @@ static __initconst struct x86_pmu intel_
.max_period = (1ULL << 31) - 1,
.get_event_constraints = intel_get_event_constraints,
- .cpu_starting = init_debug_store_on_cpu,
- .cpu_dying = fini_debug_store_on_cpu,
+ .cpu_starting = intel_pmu_cpu_starting,
+ .cpu_dying = intel_pmu_cpu_dying,
};
static void intel_clowertown_quirks(void)
Index: linux-2.6/arch/x86/kernel/cpu/perf_event_intel_lbr.c
===================================================================
--- linux-2.6.orig/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ linux-2.6/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -53,6 +53,9 @@ static void intel_pmu_lbr_reset_64(void)
static void intel_pmu_lbr_reset(void)
{
+ if (!x86_pmu.lbr_nr)
+ return;
+
if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_32)
intel_pmu_lbr_reset_32();
else
--
next prev parent reply other threads:[~2010-03-05 15:43 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-03-05 15:39 [PATCH 0/5] PEBS and LBR fixes Peter Zijlstra
2010-03-05 15:39 ` [PATCH 1/5] perf: Rework the arch CPU-hotplug hooks Peter Zijlstra
2010-03-10 13:10 ` [tip:perf/urgent] perf: Rework and fix " tip-bot for Peter Zijlstra
2010-03-05 15:39 ` [PATCH 2/5] perf, x86: Fix silly bug in data store buffer allocation Peter Zijlstra
2010-03-10 13:20 ` [tip:perf/pebs] " tip-bot for Peter Zijlstra
2010-03-05 15:39 ` [PATCH 3/5] perf, x86: Disable PEBS on clowertown chips Peter Zijlstra
2010-03-05 18:58 ` Stephane Eranian
2010-03-05 19:15 ` Peter Zijlstra
2010-03-05 19:28 ` Stephane Eranian
2010-03-05 19:37 ` Peter Zijlstra
2010-03-05 21:05 ` Peter Zijlstra
2010-03-05 21:22 ` Stephane Eranian
2010-03-05 21:35 ` Peter Zijlstra
2010-03-05 21:38 ` Stephane Eranian
2010-03-05 21:43 ` Peter Zijlstra
2010-03-05 21:57 ` Stephane Eranian
2010-03-05 22:25 ` Peter Zijlstra
2010-03-05 22:33 ` Stephane Eranian
2010-03-10 13:21 ` [tip:perf/pebs] perf, x86: Disable PEBS on clovertown chips tip-bot for Peter Zijlstra
2010-03-05 15:39 ` Peter Zijlstra [this message]
2010-03-10 13:21 ` [tip:perf/pebs] perf, x86: Clear the LBRs on init tip-bot for Peter Zijlstra
2010-03-05 15:39 ` [PATCH 5/5] perf, x86: Robustify PEBS fixup Peter Zijlstra
2010-03-10 13:21 ` [tip:perf/pebs] " tip-bot for 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=20100305154128.966563424@chello.nl \
--to=a.p.zijlstra@chello.nl \
--cc=acme@infradead.org \
--cc=eranian@google.com \
--cc=fweisbec@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=paulus@samba.org \
--cc=robert.richter@amd.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