linux-kernel - [PATCH V4 1/1] perf/x86/intel/uncore: add enable

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: Windows password security audit tool. GUI, reports in PDF.

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

Date:	Thu, 11 Aug 2016 07:31:14 -0700
From:	kan.liang@...el.com
To:	mingo@...hat.com, linux-kernel@...r.kernel.org
Cc:	peterz@...radead.org, tglx@...utronix.de,
	mingo.kernel.org@...il.com, eranian@...gle.com,
	andi@...stfloor.org, Kan Liang <kan.liang@...el.com>
Subject: [PATCH V4 1/1] perf/x86/intel/uncore: add enable_box for client msr uncore

From: Kan Liang <kan.liang@...el.com>

There are some bug reports regarding to the miscount of uncore counters
on some client machines like Sandybridge, Broadwell and Skylake. It is
very likely to be observed on system idle.

This issue is caused by a hardware issue. PERF_GLOBAL_CTL could be
cleared after Package C7, and nothing will be count.
The related errata (HSD 158) could be found in
www.intel.com/content/dam/www/public/us/en/documents/specification-
updates/4th-gen-core-family-desktop-specification-update.pdf

This patch tries to work around this issue by re-enable PERF_GLOBAL_CTL
in enable_box. The workaround does not cover all cases. It helps for new
events after returning from C7. But it cannot prevent C7, it still has
miscount if a counter is already active.
There is no drawback in letting the thing enabled, so it does not need
disable_box here.

Signed-off-by: Kan Liang <kan.liang@...el.com>
---

Changes since V3:
 - Refine the changelog

 arch/x86/events/intel/uncore_snb.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index 97a69db..9d35ec0 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -100,6 +100,12 @@ static void snb_uncore_msr_init_box(struct intel_uncore_box *box)
 	}
 }
 
+static void snb_uncore_msr_enable_box(struct intel_uncore_box *box)
+{
+	wrmsrl(SNB_UNC_PERF_GLOBAL_CTL,
+		SNB_UNC_GLOBAL_CTL_EN | SNB_UNC_GLOBAL_CTL_CORE_ALL);
+}
+
 static void snb_uncore_msr_exit_box(struct intel_uncore_box *box)
 {
 	if (box->pmu->pmu_idx == 0)
@@ -127,6 +133,7 @@ static struct attribute_group snb_uncore_format_group = {
 
 static struct intel_uncore_ops snb_uncore_msr_ops = {
 	.init_box	= snb_uncore_msr_init_box,
+	.enable_box	= snb_uncore_msr_enable_box,
 	.exit_box	= snb_uncore_msr_exit_box,
 	.disable_event	= snb_uncore_msr_disable_event,
 	.enable_event	= snb_uncore_msr_enable_event,
@@ -192,6 +199,12 @@ static void skl_uncore_msr_init_box(struct intel_uncore_box *box)
 	}
 }
 
+static void skl_uncore_msr_enable_box(struct intel_uncore_box *box)
+{
+	wrmsrl(SKL_UNC_PERF_GLOBAL_CTL,
+		SNB_UNC_GLOBAL_CTL_EN | SKL_UNC_GLOBAL_CTL_CORE_ALL);
+}
+
 static void skl_uncore_msr_exit_box(struct intel_uncore_box *box)
 {
 	if (box->pmu->pmu_idx == 0)
@@ -200,6 +213,7 @@ static void skl_uncore_msr_exit_box(struct intel_uncore_box *box)
 
 static struct intel_uncore_ops skl_uncore_msr_ops = {
 	.init_box	= skl_uncore_msr_init_box,
+	.enable_box	= skl_uncore_msr_enable_box,
 	.exit_box	= skl_uncore_msr_exit_box,
 	.disable_event	= snb_uncore_msr_disable_event,
 	.enable_event	= snb_uncore_msr_enable_event,
-- 
2.5.5