From: Andi Kleen <andi@firstfloor.org>
To: mingo@kernel.org
Cc: linux-kernel@vger.kernel.org, stable@vger.kernel.org,
peterz@infradead.org, eranian@google.com,
Andi Kleen <ak@linux.intel.com>
Subject: [PATCH 2/2] perf, x86: Don't allow unusual PEBS raw flags
Date: Wed, 24 Apr 2013 16:04:54 -0700 [thread overview]
Message-ID: <1366844694-2770-2-git-send-email-andi@firstfloor.org> (raw)
In-Reply-To: <1366844694-2770-1-git-send-email-andi@firstfloor.org>
From: Andi Kleen <ak@linux.intel.com>
The PEBS documentation in the Intel SDM 18.6.1.1 states:
"""
PEBS events are only valid when the following fields of IA32_PERFEVTSELx are all
zero: AnyThread, Edge, Invert, CMask.
"""
Since we had problems with this earlier, don't allow cmask, any, edge, invert
as raw events, except for the ones explicitly listed as pebs_aliases.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
arch/x86/kernel/cpu/perf_event.h | 2 +-
arch/x86/kernel/cpu/perf_event_intel.c | 24 ++++++++++++++++++++----
2 files changed, 21 insertions(+), 5 deletions(-)
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 7f5c75c..e46f932 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -386,7 +386,7 @@ struct x86_pmu {
int pebs_record_size;
void (*drain_pebs)(struct pt_regs *regs);
struct event_constraint *pebs_constraints;
- void (*pebs_aliases)(struct perf_event *event);
+ bool (*pebs_aliases)(struct perf_event *event);
int max_pebs_events;
/*
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index cc45deb..126c971 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1447,7 +1447,7 @@ static void intel_put_event_constraints(struct cpu_hw_events *cpuc,
intel_put_shared_regs_event_constraints(cpuc, event);
}
-static void intel_pebs_aliases_core2(struct perf_event *event)
+static bool intel_pebs_aliases_core2(struct perf_event *event)
{
if ((event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) {
/*
@@ -1472,10 +1472,12 @@ static void intel_pebs_aliases_core2(struct perf_event *event)
alt_config |= (event->hw.config & ~X86_RAW_EVENT_MASK);
event->hw.config = alt_config;
+ return true;
}
+ return false;
}
-static void intel_pebs_aliases_snb(struct perf_event *event)
+static bool intel_pebs_aliases_snb(struct perf_event *event)
{
if ((event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) {
/*
@@ -1500,7 +1502,9 @@ static void intel_pebs_aliases_snb(struct perf_event *event)
alt_config |= (event->hw.config & ~X86_RAW_EVENT_MASK);
event->hw.config = alt_config;
+ return true;
}
+ return false;
}
static int intel_pmu_hw_config(struct perf_event *event)
@@ -1510,8 +1514,20 @@ static int intel_pmu_hw_config(struct perf_event *event)
if (ret)
return ret;
- if (event->attr.precise_ip && x86_pmu.pebs_aliases)
- x86_pmu.pebs_aliases(event);
+ if (event->attr.precise_ip) {
+ /*
+ * Don't allow unusal flags with PEBS, as that
+ * may confuse the CPU.
+ *
+ * The only exception are explicitely listed pebs_aliases
+ */
+ if ((!x86_pmu.pebs_aliases || !x86_pmu.pebs_aliases(event)) &&
+ (event->attr.config & (ARCH_PERFMON_EVENTSEL_CMASK|
+ ARCH_PERFMON_EVENTSEL_EDGE|
+ ARCH_PERFMON_EVENTSEL_INV|
+ ARCH_PERFMON_EVENTSEL_ANY)))
+ return -EIO;
+ }
if (intel_pmu_needs_lbr_smpl(event)) {
ret = intel_pmu_setup_lbr_filter(event);
--
1.7.7.6
next prev parent reply other threads:[~2013-04-24 23:04 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-04-24 23:04 [PATCH 1/2] Fix perf LBR filtering Andi Kleen
2013-04-24 23:04 ` Andi Kleen [this message]
2013-04-29 22:16 ` [PATCH 2/2] perf, x86: Don't allow unusual PEBS raw flags Stephane Eranian
2013-04-29 22:34 ` Andi Kleen
2013-04-29 23:05 ` Stephane Eranian
2013-05-02 7:37 ` Peter Zijlstra
2013-05-06 17:44 ` Stephane Eranian
2013-05-06 18:52 ` Peter Zijlstra
2013-05-06 22:43 ` Stephane Eranian
2013-05-07 6:48 ` Ingo Molnar
2013-05-07 8:48 ` Peter Zijlstra
2013-05-07 11:04 ` Ingo Molnar
2013-05-07 8:43 ` Peter Zijlstra
2013-04-24 23:20 ` [PATCH 1/2] Fix perf LBR filtering Ben Hutchings
2013-04-24 23:24 ` Greg KH
2013-04-25 16:25 ` Peter Zijlstra
2013-04-25 16:41 ` Andi Kleen
2013-04-25 16:48 ` Peter Zijlstra
2013-04-25 17:00 ` Andi Kleen
2013-04-25 17:18 ` Peter Zijlstra
2013-04-25 17:42 ` Andi Kleen
2013-04-26 7:56 ` Peter Zijlstra
2013-04-26 19:46 ` Andi Kleen
2013-05-01 11:51 ` Ingo Molnar
2013-05-01 11:55 ` 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=1366844694-2770-2-git-send-email-andi@firstfloor.org \
--to=andi@firstfloor.org \
--cc=ak@linux.intel.com \
--cc=eranian@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=peterz@infradead.org \
--cc=stable@vger.kernel.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox