[PATCH 2/9] x86, perf: Add support for PEBSv3 profiling

[Andi Kleen]

From: Andi Kleen <ak@xxxxxxxxxxxxxxx>

PEBSv3 is the same as the existing PEBSv2 used on Haswell,
but it adds a new TSC field. Add support to the generic
PEBS handler to handle the new format, and overwrite
the perf time stamp using the new native_sched_clock_from_tsc()
Right now the time stamp is just slightly more accurate,
as it is nearer the actual event trigger point. With
the PEBS threshold > 1 patchkit it will be much more accurate,
avoid the problems with MMAP mismatches earlier.
The accurate time stamping is only implemented for
the default trace clock for now.

v2: Use _skl prefix. Check for default clock_id.
Signed-off-by: Andi Kleen <ak@xxxxxxxxxxxxxxx>
---
 arch/x86/kernel/cpu/perf_event_intel_ds.c | 36 ++++++++++++++++++++++++++++---
 1 file changed, 33 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 813f75d..2eed6fc 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -224,6 +224,19 @@ union hsw_tsx_tuning {
 
 #define PEBS_HSW_TSX_FLAGS	0xff00000000ULL
 
+/* Same as HSW, plus TSC */
+
+struct pebs_record_skl {
+	u64 flags, ip;
+	u64 ax, bx, cx, dx;
+	u64 si, di, bp, sp;
+	u64 r8,  r9,  r10, r11;
+	u64 r12, r13, r14, r15;
+	u64 status, dla, dse, lat;
+	u64 real_ip, tsx_tuning;
+	u64 tsc;
+};
+
 void init_debug_store_on_cpu(int cpu)
 {
 	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
@@ -827,7 +840,7 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
 	return 0;
 }
 
-static inline u64 intel_hsw_weight(struct pebs_record_hsw *pebs)
+static inline u64 intel_hsw_weight(struct pebs_record_skl *pebs)
 {
 	if (pebs->tsx_tuning) {
 		union hsw_tsx_tuning tsx = { .value = pebs->tsx_tuning };
@@ -836,7 +849,7 @@ static inline u64 intel_hsw_weight(struct pebs_record_hsw *pebs)
 	return 0;
 }
 
-static inline u64 intel_hsw_transaction(struct pebs_record_hsw *pebs)
+static inline u64 intel_hsw_transaction(struct pebs_record_skl *pebs)
 {
 	u64 txn = (pebs->tsx_tuning & PEBS_HSW_TSX_FLAGS) >> 32;
 
@@ -858,7 +871,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 	 * unconditionally access the 'extra' entries.
 	 */
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
-	struct pebs_record_hsw *pebs = __pebs;
+	struct pebs_record_skl *pebs = __pebs;
 	struct perf_sample_data data;
 	struct pt_regs regs;
 	u64 sample_type;
@@ -958,6 +971,16 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 			data.txn = intel_hsw_transaction(pebs);
 	}
 
+	/*
+	 * v3 supplies an accurate time stamp, so we use that
+	 * for the time stamp.
+	 *
+	 * We can only do this for the default trace clock.
+	 */
+	if (x86_pmu.intel_cap.pebs_format >= 3 &&
+		event->attr.use_clockid == 0)
+		data.time = native_sched_clock_from_tsc(pebs->tsc);
+
 	if (has_branch_stack(event))
 		data.br_stack = &cpuc->lbr_stack;
 
@@ -1098,6 +1121,13 @@ void __init intel_ds_init(void)
 			x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm;
 			break;
 
+		case 3:
+			pr_cont("PEBS fmt3%c, ", pebs_type);
+			x86_pmu.pebs_record_size =
+						sizeof(struct pebs_record_skl);
+			x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm;
+			break;
+
 		default:
 			printk(KERN_CONT "no PEBS fmt%d%c, ", format, pebs_type);
 			x86_pmu.pebs = 0;
-- 
1.9.3

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/