| 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: <1421246975-202879-1-git-send-email-alexander.shishkin@linux.intel.com>
Date: Wed, 14 Jan 2015 16:49:35 +0200
From: Alexander Shishkin <alexander.shishkin@...ux.intel.com>
To: Peter Zijlstra <a.p.zijlstra@...llo.nl>
Cc: Ingo Molnar <mingo@...hat.com>, linux-kernel@...r.kernel.org,
Robert Richter <rric@...nel.org>,
Frederic Weisbecker <fweisbec@...il.com>,
Mike Galbraith <efault@....de>,
Paul Mackerras <paulus@...ba.org>,
Stephane Eranian <eranian@...gle.com>,
Andi Kleen <ak@...ux.intel.com>, kan.liang@...el.com,
adrian.hunter@...el.com, markus.t.metzger@...el.com,
mathieu.poirier@...aro.org, Kaixu Xia <kaixu.xia@...aro.org>,
acme@...radead.org,
Alexander Shishkin <alexander.shishkin@...ux.intel.com>
Subject: [PATCH v10 14/14] perf: add ITRACE_START record to indicate that tracing has started
For counters that generate AUX data that is bound to the context of a
running task, such as instruction tracing, the decoder needs to know
exactly which task is running when the event is first scheduled in,
before the first sched_switch. The decoder's need to know this stems
from the fact that instruction flow trace decoding will almost always
require program's object code in order to reconstruct said flow and
for that we need at least its pid/tid in the perf stream.
To single out such instruction tracing pmus, this patch introduces
ITRACE PMU capability. The reason this is not part of RECORD_AUX
record is that not all pmus capable of generating AUX data need this,
and the opposite is *probably* also true.
While sched_switch covers for most cases, there are two problems with it:
the consumer will need to process events out of order (that is, having
found RECORD_AUX, it will have to skip forward to the nearest sched_switch
to figure out which task it was, then go back to the actual trace to
decode it) and it completely misses the case when the tracing is enabled
and disabled before sched_switch, for example, via PERF_EVENT_IOC_DISABLE.
Signed-off-by: Alexander Shishkin <alexander.shishkin@...ux.intel.com>
---
include/linux/perf_event.h | 4 ++++
include/uapi/linux/perf_event.h | 12 +++++++++++
kernel/events/core.c | 46 +++++++++++++++++++++++++++++++++++++++++
3 files changed, 62 insertions(+)
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index b042732df7..3b6456279b 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -127,6 +127,9 @@ struct hw_perf_event {
/* for tp_event->class */
struct list_head tp_list;
};
+ struct { /* itrace */
+ int itrace_started;
+ };
#ifdef CONFIG_HAVE_HW_BREAKPOINT
struct { /* breakpoint */
/*
@@ -174,6 +177,7 @@ struct perf_event;
#define PERF_PMU_CAP_AUX_NO_SG 0x02
#define PERF_PMU_CAP_AUX_SW_DOUBLEBUF 0x04
#define PERF_PMU_CAP_EXCLUSIVE 0x08
+#define PERF_PMU_CAP_ITRACE 0x10
/**
* struct pmu - generic performance monitoring unit
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 143d961857..6252aa8594 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -764,6 +764,18 @@ enum perf_event_type {
*/
PERF_RECORD_AUX = 11,
+ /*
+ * Indicates that instruction trace has started
+ *
+ * struct {
+ * struct perf_event_header header;
+ * u32 pid;
+ * u32 tid;
+ * struct sample_id sample_id;
+ * };
+ */
+ PERF_RECORD_ITRACE_START = 12,
+
PERF_RECORD_MAX, /* non-ABI */
};
diff --git a/kernel/events/core.c b/kernel/events/core.c
index a7f3eec481..c84ac7b931 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1735,6 +1735,7 @@ static void perf_set_shadow_time(struct perf_event *event,
#define MAX_INTERRUPTS (~0ULL)
static void perf_log_throttle(struct perf_event *event, int enable);
+static void perf_log_itrace_start(struct perf_event *event);
static int
event_sched_in(struct perf_event *event,
@@ -1769,6 +1770,8 @@ event_sched_in(struct perf_event *event,
perf_pmu_disable(event->pmu);
+ perf_log_itrace_start(event);
+
if (event->pmu->add(event, PERF_EF_START)) {
event->state = PERF_EVENT_STATE_INACTIVE;
event->oncpu = -1;
@@ -5724,6 +5727,49 @@ static void perf_log_throttle(struct perf_event *event, int enable)
}
/*
+ * Log the pid and tid of a task that's running when instruction
+ * tracing is enabled, to retain context of the trace in system-wide
+ * mode before the first sched_switch arrives.
+ */
+static void perf_log_itrace_start(struct perf_event *event)
+{
+ struct perf_output_handle handle;
+ struct perf_sample_data sample;
+ struct perf_aux_event {
+ struct perf_event_header header;
+ u32 pid;
+ u32 tid;
+ } rec;
+ int ret;
+
+ if (event->parent)
+ event = event->parent;
+
+ if (!(event->pmu->capabilities & PERF_PMU_CAP_ITRACE) ||
+ event->hw.itrace_started)
+ return;
+
+ event->hw.itrace_started = 1;
+
+ rec.header.type = PERF_RECORD_ITRACE_START;
+ rec.header.misc = 0;
+ rec.header.size = sizeof(rec);
+ rec.pid = perf_event_pid(event, current);
+ rec.tid = perf_event_tid(event, current);
+
+ perf_event_header__init_id(&rec.header, &sample, event);
+ ret = perf_output_begin(&handle, event, rec.header.size);
+
+ if (ret)
+ return;
+
+ perf_output_put(&handle, rec);
+ perf_event__output_id_sample(event, &handle, &sample);
+
+ perf_output_end(&handle);
+}
+
+/*
* Generic event overflow handling, sampling.
*/
--
2.1.4
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists