linux-kernel - [PATCH] perf x86: Use PAGE_SIZE for PEBS buffer size on Core2

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

Date:	Tue, 1 Mar 2016 20:03:52 +0100
From:	Jiri Olsa <jolsa@...hat.com>
To:	Peter Zijlstra <peterz@...radead.org>
Cc:	Andi Kleen <andi@...stfloor.org>,
	"Liang, Kan" <kan.liang@...el.com>,
	Arnaldo Carvalho de Melo <acme@...nel.org>,
	Ingo Molnar <mingo@...nel.org>,
	Stephane Eranian <eranian@...gle.com>,
	Wang Nan <wangnan0@...wei.com>,
	LKML <linux-kernel@...r.kernel.org>
Subject: [PATCH] perf x86: Use PAGE_SIZE for PEBS buffer size on Core2

On Tue, Mar 01, 2016 at 07:12:07PM +0100, Peter Zijlstra wrote:

SNIP

> > @@ -1327,6 +1328,7 @@ void __init intel_ds_init(void)
> >  		case 0:
> >  			pr_cont("PEBS fmt0%c, ", pebs_type);
> >  			x86_pmu.pebs_record_size = sizeof(struct pebs_record_core);
> 
> At the very least this wants a comment along the lines of:
> 
> 			/*
> 			 * Using >PAGE_SIZE buffers makes the WRMSR to
> 			 * PERF_GLOBAL_CTRL in intel_pmu_enable_all()
> 			 * mysteriously hang on Core2.
> 			 *
> 			 * As a workaround, we don't do this.
> 			 */
> 
> > +			x86_pmu.pebs_buffer_size = PAGE_SIZE;
> >  			x86_pmu.drain_pebs = intel_pmu_drain_pebs_core;
> >  			break;
> >  
> > diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
> > index 7bb61e32fb29..1ab6279fed1d 100644
> > --- a/arch/x86/events/perf_event.h
> > +++ b/arch/x86/events/perf_event.h
> > @@ -586,6 +586,7 @@ struct x86_pmu {
> >  			pebs_broken	:1,
> >  			pebs_prec_dist	:1;
> >  	int		pebs_record_size;
> > +	int		pebs_buffer_size;
> >  	void		(*drain_pebs)(struct pt_regs *regs);
> >  	struct event_constraint *pebs_constraints;
> >  	void		(*pebs_aliases)(struct perf_event *event);

sending updated patch
jirka


---
Using PAGE_SIZE buffers makes the WRMSR to
PERF_GLOBAL_CTRL in intel_pmu_enable_all()
mysteriously hang on Core2. As a workaround,
we don't do this.

The hard lockup is easily triggered by running
'perf test attr' repeatedly. Most of the time
it gets stuck on sample session with small periods.

  # perf test attr -vv
  14: struct perf_event_attr setup                             :
  --- start ---
  ...
    'PERF_TEST_ATTR=/tmp/tmpuEKz3B /usr/bin/perf record -o /tmp/tmpuEKz3B/perf.data -c 123 kill >/dev/null 2>&1' ret 1

Reported-by: Cc: Arnaldo Carvalho de Melo <acme@...hat.com>
Reviewed-by: Andi Kleen <ak@...ux.intel.com>
Signed-off-by: Jiri Olsa <jolsa@...nel.org>
---
 arch/x86/events/intel/ds.c   | 13 +++++++++++--
 arch/x86/events/perf_event.h |  1 +
 2 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index c8a243d6fc82..b8420c364c5d 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -269,7 +269,7 @@ static int alloc_pebs_buffer(int cpu)
 	if (!x86_pmu.pebs)
 		return 0;
 
-	buffer = kzalloc_node(PEBS_BUFFER_SIZE, GFP_KERNEL, node);
+	buffer = kzalloc_node(x86_pmu.pebs_buffer_size, GFP_KERNEL, node);
 	if (unlikely(!buffer))
 		return -ENOMEM;
 
@@ -286,7 +286,7 @@ static int alloc_pebs_buffer(int cpu)
 		per_cpu(insn_buffer, cpu) = ibuffer;
 	}
 
-	max = PEBS_BUFFER_SIZE / x86_pmu.pebs_record_size;
+	max = x86_pmu.pebs_buffer_size / x86_pmu.pebs_record_size;
 
 	ds->pebs_buffer_base = (u64)(unsigned long)buffer;
 	ds->pebs_index = ds->pebs_buffer_base;
@@ -1319,6 +1319,7 @@ void __init intel_ds_init(void)
 
 	x86_pmu.bts  = boot_cpu_has(X86_FEATURE_BTS);
 	x86_pmu.pebs = boot_cpu_has(X86_FEATURE_PEBS);
+	x86_pmu.pebs_buffer_size = PEBS_BUFFER_SIZE;
 	if (x86_pmu.pebs) {
 		char pebs_type = x86_pmu.intel_cap.pebs_trap ?  '+' : '-';
 		int format = x86_pmu.intel_cap.pebs_format;
@@ -1327,6 +1328,14 @@ void __init intel_ds_init(void)
 		case 0:
 			pr_cont("PEBS fmt0%c, ", pebs_type);
 			x86_pmu.pebs_record_size = sizeof(struct pebs_record_core);
+			/*
+			* Using >PAGE_SIZE buffers makes the WRMSR to
+			* PERF_GLOBAL_CTRL in intel_pmu_enable_all()
+			* mysteriously hang on Core2.
+			*
+			* As a workaround, we don't do this.
+			*/
+			x86_pmu.pebs_buffer_size = PAGE_SIZE;
 			x86_pmu.drain_pebs = intel_pmu_drain_pebs_core;
 			break;
 
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 7bb61e32fb29..1ab6279fed1d 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -586,6 +586,7 @@ struct x86_pmu {
 			pebs_broken	:1,
 			pebs_prec_dist	:1;
 	int		pebs_record_size;
+	int		pebs_buffer_size;
 	void		(*drain_pebs)(struct pt_regs *regs);
 	struct event_constraint *pebs_constraints;
 	void		(*pebs_aliases)(struct perf_event *event);
-- 
2.4.3