summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorJiri Olsa <jolsa@redhat.com>2016-03-01 20:03:52 +0100
committerIngo Molnar <mingo@kernel.org>2016-03-08 12:18:32 +0100
commite72daf3f4d764c47fb71c9bdc7f9c54a503825b1 (patch)
tree0ba39e046d71722ee9247bf3d7de095ac5ed9e93
parent927a5570855836e5d5859a80ce7e91e963545e8f (diff)
perf/x86/intel: Use PAGE_SIZE for PEBS buffer size on Core2
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: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Jiri Olsa <jolsa@kernel.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Andi Kleen <ak@linux.intel.com> Cc: <stable@vger.kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vince Weaver <vincent.weaver@maine.edu> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/20160301190352.GA8355@krava.redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
-rw-r--r--arch/x86/events/intel/ds.c13
-rw-r--r--arch/x86/events/perf_event.h1
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..22ece02d01b6 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);