| 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
| ||
|
Message-Id: <20210701131732.31602-2-adrian.hunter@intel.com>
Date: Thu, 1 Jul 2021 16:17:30 +0300
From: Adrian Hunter <adrian.hunter@...el.com>
To: Peter Zijlstra <peterz@...radead.org>
Cc: Ingo Molnar <mingo@...hat.com>,
Arnaldo Carvalho de Melo <acme@...nel.org>,
Mark Rutland <mark.rutland@....com>,
Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
Jiri Olsa <jolsa@...hat.com>, Leo Yan <leo.yan@...aro.org>,
Kan Liang <kan.liang@...ux.intel.com>, x86@...nel.org,
linux-perf-users@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: [PATCH V2 1/3] perf/x86: Add new event for AUX output counter index
PEBS-via-PT records contain a mask of applicable counters. To identify
which event belongs to which counter, a side-band event is needed. Until
now, there has been no side-band event, and consequently users were limited
to using a single event.
Add such a side-band event. Note the event is optimised to output only
when the counter index changes for an event. That works only so long as
all PEBS-via-PT events are scheduled together, which they are for a
recording session because they are in a single group.
Also no attribute bit is used to select the new event, so a new
kernel is not compatible with older perf tools. The assumption
being that PEBS-via-PT is sufficiently esoteric that users will not
be troubled by this.
Signed-off-by: Adrian Hunter <adrian.hunter@...el.com>
---
Changes in V2:
Use callback from x86_assign_hw_event
arch/x86/events/core.c | 6 ++++++
arch/x86/events/intel/core.c | 7 +++++++
arch/x86/events/perf_event.h | 1 +
include/linux/perf_event.h | 1 +
include/uapi/linux/perf_event.h | 15 +++++++++++++++
kernel/events/core.c | 30 ++++++++++++++++++++++++++++++
6 files changed, 60 insertions(+)
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 8f71dd72ef95..3b71f54d26c7 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -66,6 +66,8 @@ DEFINE_STATIC_CALL_NULL(x86_pmu_enable_all, *x86_pmu.enable_all);
DEFINE_STATIC_CALL_NULL(x86_pmu_enable, *x86_pmu.enable);
DEFINE_STATIC_CALL_NULL(x86_pmu_disable, *x86_pmu.disable);
+DEFINE_STATIC_CALL_NULL(x86_pmu_assign, *x86_pmu.assign);
+
DEFINE_STATIC_CALL_NULL(x86_pmu_add, *x86_pmu.add);
DEFINE_STATIC_CALL_NULL(x86_pmu_del, *x86_pmu.del);
DEFINE_STATIC_CALL_NULL(x86_pmu_read, *x86_pmu.read);
@@ -1217,6 +1219,8 @@ static inline void x86_assign_hw_event(struct perf_event *event,
hwc->last_cpu = smp_processor_id();
hwc->last_tag = ++cpuc->tags[i];
+ static_call_cond(x86_pmu_assign)(event, idx);
+
switch (hwc->idx) {
case INTEL_PMC_IDX_FIXED_BTS:
case INTEL_PMC_IDX_FIXED_VLBR:
@@ -2005,6 +2009,8 @@ static void x86_pmu_static_call_update(void)
static_call_update(x86_pmu_enable, x86_pmu.enable);
static_call_update(x86_pmu_disable, x86_pmu.disable);
+ static_call_update(x86_pmu_assign, x86_pmu.assign);
+
static_call_update(x86_pmu_add, x86_pmu.add);
static_call_update(x86_pmu_del, x86_pmu.del);
static_call_update(x86_pmu_read, x86_pmu.read);
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index e28892270c58..7a7c3b18acec 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2400,6 +2400,12 @@ static void intel_pmu_disable_event(struct perf_event *event)
intel_pmu_pebs_disable(event);
}
+static void intel_pmu_assign_event(struct perf_event *event, int idx)
+{
+ if (is_pebs_pt(event))
+ perf_report_aux_output_id(event, idx);
+}
+
static void intel_pmu_del_event(struct perf_event *event)
{
if (needs_branch_stack(event))
@@ -4596,6 +4602,7 @@ static __initconst const struct x86_pmu intel_pmu = {
.enable_all = intel_pmu_enable_all,
.enable = intel_pmu_enable_event,
.disable = intel_pmu_disable_event,
+ .assign = intel_pmu_assign_event,
.add = intel_pmu_add_event,
.del = intel_pmu_del_event,
.read = intel_pmu_read_event,
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index ad87cb36f7c8..0a13ca1aad61 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -711,6 +711,7 @@ struct x86_pmu {
void (*enable_all)(int added);
void (*enable)(struct perf_event *);
void (*disable)(struct perf_event *);
+ void (*assign)(struct perf_event *event, int idx);
void (*add)(struct perf_event *);
void (*del)(struct perf_event *);
void (*read)(struct perf_event *event);
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index f5a6a2f069ed..4a25da3883c0 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1397,6 +1397,7 @@ perf_event_addr_filters(struct perf_event *event)
}
extern void perf_event_addr_filters_sync(struct perf_event *event);
+extern void perf_report_aux_output_id(struct perf_event *event, u64 hw_id);
extern int perf_output_begin(struct perf_output_handle *handle,
struct perf_sample_data *data,
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index f92880a15645..c89535de1ec8 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -1141,6 +1141,21 @@ enum perf_event_type {
*/
PERF_RECORD_TEXT_POKE = 20,
+ /*
+ * Data written to the AUX area by hardware due to aux_output, may need
+ * to be matched to the event by an architecture-specific hardware ID.
+ * This records the hardware ID, but requires sample_id to provide the
+ * event ID. e.g. Intel PT uses this record to disambiguate PEBS-via-PT
+ * records from multiple events.
+ *
+ * struct {
+ * struct perf_event_header header;
+ * u64 hw_id;
+ * struct sample_id sample_id;
+ * };
+ */
+ PERF_RECORD_AUX_OUTPUT_HW_ID = 21,
+
PERF_RECORD_MAX, /* non-ABI */
};
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 0ac818b3bea4..62e9838a32b1 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -9053,6 +9053,36 @@ static void perf_log_itrace_start(struct perf_event *event)
perf_output_end(&handle);
}
+void perf_report_aux_output_id(struct perf_event *event, u64 hw_id)
+{
+ struct perf_output_handle handle;
+ struct perf_sample_data sample;
+ struct perf_aux_event {
+ struct perf_event_header header;
+ u64 hw_id;
+ } rec;
+ int ret;
+
+ if (event->parent)
+ event = event->parent;
+
+ rec.header.type = PERF_RECORD_AUX_OUTPUT_HW_ID;
+ rec.header.misc = 0;
+ rec.header.size = sizeof(rec);
+ rec.hw_id = hw_id;
+
+ perf_event_header__init_id(&rec.header, &sample, event);
+ ret = perf_output_begin(&handle, &sample, event, rec.header.size);
+
+ if (ret)
+ return;
+
+ perf_output_put(&handle, rec);
+ perf_event__output_id_sample(event, &handle, &sample);
+
+ perf_output_end(&handle);
+}
+
static int
__perf_event_account_interrupt(struct perf_event *event, int throttle)
{
--
2.17.1
Powered by blists - more mailing lists