linux-kernel - [tip:perf/pebs] perf, x86: Fixup the PEBS handler for Core2 cpus

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [day] [month] [year] [list]

Date:	Wed, 10 Mar 2010 13:24:32 GMT
From:	tip-bot for Peter Zijlstra <a.p.zijlstra@...llo.nl>
To:	linux-tip-commits@...r.kernel.org
Cc:	linux-kernel@...r.kernel.org, hpa@...or.com, mingo@...hat.com,
	acme@...radead.org, a.p.zijlstra@...llo.nl, tglx@...utronix.de,
	mingo@...e.hu
Subject: [tip:perf/pebs] perf, x86: Fixup the PEBS handler for Core2 cpus

Commit-ID:  d80c7502ff63aa0d99d8c0c5803d28bbef67a74e
Gitweb:     http://git.kernel.org/tip/d80c7502ff63aa0d99d8c0c5803d28bbef67a74e
Author:     Peter Zijlstra <a.p.zijlstra@...llo.nl>
AuthorDate: Tue, 9 Mar 2010 11:41:02 +0100
Committer:  Ingo Molnar <mingo@...e.hu>
CommitDate: Wed, 10 Mar 2010 13:23:39 +0100

perf, x86: Fixup the PEBS handler for Core2 cpus

Pull the core handler in line with the nhm one, also make sure we always
drain the buffer.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@...llo.nl>
Cc: Arnaldo Carvalho de Melo <acme@...radead.org>
Cc: paulus@...ba.org
Cc: eranian@...gle.com
Cc: robert.richter@....com
Cc: fweisbec@...il.com
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@...e.hu>
---
 arch/x86/kernel/cpu/perf_event_intel_ds.c |   38 ++++++++++++++++++----------
 1 files changed, 24 insertions(+), 14 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 2423694..1bfd59b 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -472,20 +472,39 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
 	struct pt_regs regs;
 	int n;
 
-	if (!event || !ds || !x86_pmu.pebs)
+	if (!ds || !x86_pmu.pebs)
 		return;
 
 	at  = (struct pebs_record_core *)(unsigned long)ds->pebs_buffer_base;
 	top = (struct pebs_record_core *)(unsigned long)ds->pebs_index;
 
-	if (top <= at)
+	/*
+	 * Whatever else happens, drain the thing
+	 */
+	ds->pebs_index = ds->pebs_buffer_base;
+
+	if (!test_bit(0, cpuc->active_mask))
 		return;
 
-	ds->pebs_index = ds->pebs_buffer_base;
+	WARN_ON_ONCE(!event);
+
+	if (!event->attr.precise)
+		return;
+
+	n = top - at;
+	if (n <= 0)
+		return;
 
 	if (!intel_pmu_save_and_restart(event))
 		return;
 
+	/*
+	 * Should not happen, we program the threshold at 1 and do not
+	 * set a reset value.
+	 */
+	WARN_ON_ONCE(n > 1);
+	at += n - 1;
+
 	perf_sample_data_init(&data, 0);
 	data.period = event->hw.last_period;
 
@@ -495,14 +514,6 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
 		data.raw = &raw;
 	}
 
-	n = top - at;
-
-	/*
-	 * Should not happen, we program the threshold at 1 and do not
-	 * set a reset value.
-	 */
-	WARN_ON_ONCE(n > 1);
-
 	/*
 	 * We use the interrupt regs as a base because the PEBS record
 	 * does not contain a full regs set, specifically it seems to
@@ -545,12 +556,11 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 	at  = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base;
 	top = (struct pebs_record_nhm *)(unsigned long)ds->pebs_index;
 
-	if (top <= at)
-		return;
-
 	ds->pebs_index = ds->pebs_buffer_base;
 
 	n = top - at;
+	if (n <= 0)
+		return;
 
 	/*
 	 * Should not happen, we program the threshold at 1 and do not
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/