Commit-ID: 8d4e6c4caa12dafbcba138e5450b7af17b0b2194
Gitweb: http://git.kernel.org/tip/8d4e6c4caa12dafbcba138e5450b7af17b0b2194
Author: Alexander Shishkin <[email protected]>
AuthorDate: Thu, 30 Mar 2017 18:39:56 +0300
Committer: Ingo Molnar <[email protected]>
CommitDate: Tue, 29 Aug 2017 15:09:24 +0200
perf/core, pt, bts: Get rid of itrace_started
I just noticed that hw.itrace_started and hw.config are aliased to the
same location. Now, the PT driver happens to use both, which works out
fine by sheer luck:
- STORE(hw.itrace_start) is ordered before STORE(hw.config), in the
program order, although there are no compiler barriers to ensure that,
- to the perf_log_itrace_start() hw.itrace_start looks set at the same
time as when it is intended to be set because both stores happen in the
same path,
- hw.config is never reset to zero in the PT driver.
Now, the use of hw.config by the PT driver makes more sense (it being a
HW PMU) than messing around with itrace_started, which is an awkward API
to begin with.
This patch replaces hw.itrace_started with an attach_state bit and an
API call for the PMU drivers to use to communicate the condition.
Signed-off-by: Alexander Shishkin <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Cc: Arnaldo Carvalho de Melo <[email protected]>
Cc: Arnaldo Carvalho de Melo <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Stephane Eranian <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Vince Weaver <[email protected]>
Cc: [email protected]
Link:
http://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
---
arch/x86/events/intel/bts.c | 2 +-
arch/x86/events/intel/pt.c | 5 +++--
include/linux/perf_event.h | 5 ++---
kernel/events/core.c | 7 ++++++-
4 files changed, 12 insertions(+), 7 deletions(-)
diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c
index ddd8d35..16076eb 100644
--- a/arch/x86/events/intel/bts.c
+++ b/arch/x86/events/intel/bts.c
@@ -268,7 +268,7 @@ static void bts_event_start(struct perf_event *event, int
flags)
bts->ds_back.bts_absolute_maximum = cpuc->ds->bts_absolute_maximum;
bts->ds_back.bts_interrupt_threshold =
cpuc->ds->bts_interrupt_threshold;
- event->hw.itrace_started = 1;
+ perf_event_itrace_started(event);
event->hw.state = 0;
__bts_event_start(event);
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index ae8324d..81fd41d 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -471,8 +471,9 @@ static void pt_config(struct perf_event *event)
struct pt *pt = this_cpu_ptr(&pt_ctx);
u64 reg;
- if (!event->hw.itrace_started) {
- event->hw.itrace_started = 1;
+ /* First round: clear STATUS, in particular the PSB byte counter. */
+ if (!event->hw.config) {
+ perf_event_itrace_started(event);
wrmsrl(MSR_IA32_RTIT_STATUS, 0);
}
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index c00cd4b..adda0aa 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -147,9 +147,6 @@ struct hw_perf_event {
struct list_head cqm_groups_entry;
struct list_head cqm_group_entry;
};
- struct { /* itrace */
- int itrace_started;
- };
struct { /* amd_power */
u64 pwr_acc;
u64 ptsc;
@@ -541,6 +538,7 @@ struct swevent_hlist {
#define PERF_ATTACH_GROUP 0x02
#define PERF_ATTACH_TASK 0x04
#define PERF_ATTACH_TASK_DATA 0x08
+#define PERF_ATTACH_ITRACE 0x10
struct perf_cgroup;
struct ring_buffer;
@@ -864,6 +862,7 @@ extern int perf_aux_output_skip(struct perf_output_handle
*handle,
unsigned long size);
extern void *perf_get_aux(struct perf_output_handle *handle);
extern void perf_aux_output_flag(struct perf_output_handle *handle, u64 flags);
+extern void perf_event_itrace_started(struct perf_event *event);
extern int perf_pmu_register(struct pmu *pmu, const char *name, int type);
extern void perf_pmu_unregister(struct pmu *pmu);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index e5467e1..77fd6b1 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7301,6 +7301,11 @@ static void perf_log_throttle(struct perf_event *event,
int enable)
perf_output_end(&handle);
}
+void perf_event_itrace_started(struct perf_event *event)
+{
+ event->attach_state |= PERF_ATTACH_ITRACE;
+}
+
static void perf_log_itrace_start(struct perf_event *event)
{
struct perf_output_handle handle;
@@ -7316,7 +7321,7 @@ static void perf_log_itrace_start(struct perf_event
*event)
event = event->parent;
if (!(event->pmu->capabilities & PERF_PMU_CAP_ITRACE) ||
- event->hw.itrace_started)
+ event->attach_state & PERF_ATTACH_ITRACE)
return;
rec.header.type = PERF_RECORD_ITRACE_START;
