[RFC PATCH V2 4/9] perf/x86: Enable post-processing monotonic raw conversion

[kan . liang]

From: Kan Liang <kan.liang@xxxxxxxxxxxxxxx>

The raw HW time is from TSC on X86. Preload the HW time for each sample,
once the hw_time is set with the monotonic raw clock by the new perf
tool. Also, dump the conversion information into mmap_page.

For the legacy perf tool which doesn't know the hw_time, nothing is
changed.

Move the x86_pmu_sample_preload() before setup_pebs_time() to utilize
the TSC from a PEBS record.

Signed-off-by: Kan Liang <kan.liang@xxxxxxxxxxxxxxx>
Cc: Ravi Bangoria <ravi.bangoria@xxxxxxx>
---
 arch/x86/events/core.c       | 10 ++++++++++
 arch/x86/events/intel/ds.c   | 14 +++++++++++---
 arch/x86/events/perf_event.h | 12 ++++++++++++
 3 files changed, 33 insertions(+), 3 deletions(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index b19ac54ebeea..7c1dfb8c763d 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2740,6 +2740,16 @@ void arch_perf_update_userpage(struct perf_event *event,
 	if (!event->attr.use_clockid) {
 		userpg->cap_user_time_zero = 1;
 		userpg->time_zero = offset;
+	} else if (perf_event_hw_time(event)) {
+		struct ktime_conv mono;
+
+		userpg->cap_user_time_mono_raw = 1;
+		ktime_get_fast_mono_raw_conv(&mono);
+		userpg->time_mono_last = mono.cycle_last;
+		userpg->time_mono_mult = mono.mult;
+		userpg->time_mono_shift = mono.shift;
+		userpg->time_mono_nsec = mono.xtime_nsec;
+		userpg->time_mono_base = mono.base;
 	}
 
 	cyc2ns_read_end();
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 2f59573ed463..10d4b63c891f 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1574,6 +1574,12 @@ static void setup_pebs_time(struct perf_event *event,
 			    struct perf_sample_data *data,
 			    u64 tsc)
 {
+	u64 time = tsc;
+
+	/* Perf tool does the conversion. No conversion here. */
+	if (perf_event_hw_time(event))
+		goto done;
+
 	/* Converting to a user-defined clock is not supported yet. */
 	if (event->attr.use_clockid != 0)
 		return;
@@ -1588,7 +1594,9 @@ static void setup_pebs_time(struct perf_event *event,
 	if (!using_native_sched_clock() || !sched_clock_stable())
 		return;
 
-	data->time = native_sched_clock_from_tsc(tsc) + __sched_clock_offset;
+	time = native_sched_clock_from_tsc(tsc) + __sched_clock_offset;
+done:
+	data->time = time;
 	data->sample_flags |= PERF_SAMPLE_TIME;
 }
 
@@ -1733,6 +1741,8 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event,
 		}
 	}
 
+	x86_pmu_sample_preload(data, event, cpuc);
+
 	/*
 	 * v3 supplies an accurate time stamp, so we use that
 	 * for the time stamp.
@@ -1741,8 +1751,6 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event,
 	 */
 	if (x86_pmu.intel_cap.pebs_format >= 3)
 		setup_pebs_time(event, data, pebs->tsc);
-
-	x86_pmu_sample_preload(data, event, cpuc);
 }
 
 static void adaptive_pebs_save_regs(struct pt_regs *regs,
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index ae6ec58fde14..0486ee6a7605 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -1185,12 +1185,24 @@ int x86_pmu_handle_irq(struct pt_regs *regs);
 void x86_pmu_show_pmu_cap(int num_counters, int num_counters_fixed,
 			  u64 intel_ctrl);
 
+static inline bool perf_event_hw_time(struct perf_event *event)
+{
+	return (event->attr.hw_time &&
+		event->attr.use_clockid &&
+		(event->attr.clockid == CLOCK_MONOTONIC_RAW));
+}
+
 static inline void x86_pmu_sample_preload(struct perf_sample_data *data,
 					  struct perf_event *event,
 					  struct cpu_hw_events *cpuc)
 {
 	if (has_branch_stack(event))
 		perf_sample_save_brstack(data, event, &cpuc->lbr_stack);
+
+	if (perf_event_hw_time(event)) {
+		data->time = rdtsc();
+		data->sample_flags |= PERF_SAMPLE_TIME;
+	}
 }
 
 extern struct event_constraint emptyconstraint;
-- 
2.35.1