summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/cpu/perf_event.c
diff options
context:
space:
mode:
authorStephane Eranian <eranian@google.com>2012-02-09 23:20:54 +0100
committerIngo Molnar <mingo@elte.hu>2012-03-05 14:55:40 +0100
commitff3fb511ba377e8a0a7f553cc352237f70d08121 (patch)
tree1395e265d7cf7f87565315a943334897886f7dda /arch/x86/kernel/cpu/perf_event.c
parentb36817e8863090f1f24e538106ca50fa1d9e4003 (diff)
downloadlinux-ff3fb511ba377e8a0a7f553cc352237f70d08121.tar.gz
linux-ff3fb511ba377e8a0a7f553cc352237f70d08121.tar.xz
linux-ff3fb511ba377e8a0a7f553cc352237f70d08121.zip
perf/x86: Sync branch stack sampling with precise_sampling
If precise sampling is enabled on Intel x86 then perf_event uses PEBS. To correct for the off-by-one error of PEBS, perf_event uses LBR when precise_sample > 1. On Intel x86 PERF_SAMPLE_BRANCH_STACK is implemented using LBR, therefore both features must be coordinated as they may not configure LBR the same way. For PEBS, LBR needs to capture all branches at the priv level of the associated event. This patch checks that the branch type and priv level of BRANCH_STACK is compatible with that of the PEBS LBR requirement, thereby allowing: $ perf record -b any,u -e instructions:upp .... But: $ perf record -b any_call,u -e instructions:upp Is not possible. Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1328826068-11713-5-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
Diffstat (limited to 'arch/x86/kernel/cpu/perf_event.c')
-rw-r--r--arch/x86/kernel/cpu/perf_event.c60
1 files changed, 60 insertions, 0 deletions
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 377931354ac7..cea567483274 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -353,6 +353,36 @@ int x86_setup_perfctr(struct perf_event *event)
return 0;
}
+/*
+ * check that branch_sample_type is compatible with
+ * settings needed for precise_ip > 1 which implies
+ * using the LBR to capture ALL taken branches at the
+ * priv levels of the measurement
+ */
+static inline int precise_br_compat(struct perf_event *event)
+{
+ u64 m = event->attr.branch_sample_type;
+ u64 b = 0;
+
+ /* must capture all branches */
+ if (!(m & PERF_SAMPLE_BRANCH_ANY))
+ return 0;
+
+ m &= PERF_SAMPLE_BRANCH_KERNEL | PERF_SAMPLE_BRANCH_USER;
+
+ if (!event->attr.exclude_user)
+ b |= PERF_SAMPLE_BRANCH_USER;
+
+ if (!event->attr.exclude_kernel)
+ b |= PERF_SAMPLE_BRANCH_KERNEL;
+
+ /*
+ * ignore PERF_SAMPLE_BRANCH_HV, not supported on x86
+ */
+
+ return m == b;
+}
+
int x86_pmu_hw_config(struct perf_event *event)
{
if (event->attr.precise_ip) {
@@ -369,6 +399,36 @@ int x86_pmu_hw_config(struct perf_event *event)
if (event->attr.precise_ip > precise)
return -EOPNOTSUPP;
+ /*
+ * check that PEBS LBR correction does not conflict with
+ * whatever the user is asking with attr->branch_sample_type
+ */
+ if (event->attr.precise_ip > 1) {
+ u64 *br_type = &event->attr.branch_sample_type;
+
+ if (has_branch_stack(event)) {
+ if (!precise_br_compat(event))
+ return -EOPNOTSUPP;
+
+ /* branch_sample_type is compatible */
+
+ } else {
+ /*
+ * user did not specify branch_sample_type
+ *
+ * For PEBS fixups, we capture all
+ * the branches at the priv level of the
+ * event.
+ */
+ *br_type = PERF_SAMPLE_BRANCH_ANY;
+
+ if (!event->attr.exclude_user)
+ *br_type |= PERF_SAMPLE_BRANCH_USER;
+
+ if (!event->attr.exclude_kernel)
+ *br_type |= PERF_SAMPLE_BRANCH_KERNEL;
+ }
+ }
}
/*