[PATCH V3 6/6] tools/perf: Enable perf script to present the DTL entries

[Athira Rajeev]

The process_event() function in "builtin-script.c" invokes
perf_sample__fprintf_synth() for displaying PERF_TYPE_SYNTH
type events.

   if (attr->type == PERF_TYPE_SYNTH && PRINT_FIELD(SYNTH))
   	perf_sample__fprintf_synth(sample, evsel, fp);

perf_sample__fprintf_synth() process the sample depending on the value
in evsel->core.attr.config. Introduce perf_sample__fprintf_synth_vpadtl()
and invoke this for PERF_SYNTH_POWERPC_VPA_DTL

Sample output:

   ./perf record -a -e sched:*,vpa_dtl/dtl_all/ -c 1000000000 sleep 1
   [ perf record: Woken up 1 times to write data ]
   [ perf record: Captured and wrote 0.300 MB perf.data ]

   ./perf script
            perf   13322 [002]   233.835807:                     sched:sched_switch: perf:13322 [120] R ==> migration/2:27 [0]
     migration/2      27 [002]   233.835811:               sched:sched_migrate_task: comm=perf pid=13322 prio=120 orig_cpu=2 dest_cpu=3
     migration/2      27 [002]   233.835818:               sched:sched_stat_runtime: comm=migration/2 pid=27 runtime=9214 [ns]
     migration/2      27 [002]   233.835819:                     sched:sched_switch: migration/2:27 [0] S ==> swapper/2:0 [120]
         swapper       0 [002]   233.835822:                                vpa-dtl: timebase: 338954486062657 dispatch_reason:decrementer_interrupt, preempt_reason:H_CEDE, enqueue_to_dispatch_time:435,			ready_to_enqueue_time:0, waiting_to_ready_time:34775058, processor_id: 202 c0000000000f8094 plpar_hcall_norets_notrace+0x18 ([kernel.kallsyms])
         swapper       0 [001]   233.835886:                                vpa-dtl: timebase: 338954486095398 dispatch_reason:priv_doorbell, preempt_reason:H_CEDE, enqueue_to_dispatch_time:542,			ready_to_enqueue_time:0, waiting_to_ready_time:1245360, processor_id: 201 c0000000000f8094 plpar_hcall_norets_notrace+0x18 ([kernel.kallsyms])

Tested-by: Venkat Rao Bagalkote <venkat88 at linux.ibm.com>
Signed-off-by: Athira Rajeev <atrajeev at linux.ibm.com>
---
Changelog:
v3:
Addressed review comments from Adrian
- Remove unnecessary line continuation and line length
- Return number of chars printed for perf_sample__fprintf_synth_vpadtl

- Added Tested by from Venkat

v2:
Addressed review comments from Adrian
- Removed default callback and used perf_sample__fprintf_synth_vpadtl
- fix build failure when using NO_AUXTRACE=1 by
  adding code around HAVE_AUXTRACE_SUPPORT

 tools/perf/builtin-script.c | 30 ++++++++++++++++++++++++++++++
 tools/perf/util/event.h     |  3 +++
 2 files changed, 33 insertions(+)

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index d9fbdcf72f25..bda5e4914ee7 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -43,6 +43,7 @@
 #include <linux/stringify.h>
 #include <linux/time64.h>
 #include <linux/zalloc.h>
+#include <linux/unaligned.h>
 #include <sys/utsname.h>
 #include "asm/bug.h"
 #include "util/mem-events.h"
@@ -2003,6 +2004,33 @@ static int perf_sample__fprintf_synth_iflag_chg(struct perf_sample *sample, FILE
 	return len + perf_sample__fprintf_pt_spacing(len, fp);
 }
 
+#ifdef HAVE_AUXTRACE_SUPPORT
+static int perf_sample__fprintf_synth_vpadtl(struct perf_sample *data, FILE *fp)
+{
+	struct powerpc_vpadtl_entry *dtl = (struct powerpc_vpadtl_entry *)data->raw_data;
+	int len;
+
+	len = fprintf(fp, "timebase: %" PRIu64 " dispatch_reason:%s, preempt_reason:%s,\n"
+			"enqueue_to_dispatch_time:%d, ready_to_enqueue_time:%d,"
+			"waiting_to_ready_time:%d, processor_id: %d",
+			get_unaligned_be64(&dtl->timebase),
+			dispatch_reasons[dtl->dispatch_reason],
+			preempt_reasons[dtl->preempt_reason],
+			be32_to_cpu(dtl->enqueue_to_dispatch_time),
+			be32_to_cpu(dtl->ready_to_enqueue_time),
+			be32_to_cpu(dtl->waiting_to_ready_time),
+			be16_to_cpu(dtl->processor_id));
+
+	return len;
+}
+#else
+static int perf_sample__fprintf_synth_vpadtl(struct perf_sample *data __maybe_unused,
+		FILE *fp __maybe_unused)
+{
+	return 0;
+}
+#endif
+
 static int perf_sample__fprintf_synth(struct perf_sample *sample,
 				      struct evsel *evsel, FILE *fp)
 {
@@ -2025,6 +2053,8 @@ static int perf_sample__fprintf_synth(struct perf_sample *sample,
 		return perf_sample__fprintf_synth_evt(sample, fp);
 	case PERF_SYNTH_INTEL_IFLAG_CHG:
 		return perf_sample__fprintf_synth_iflag_chg(sample, fp);
+	case PERF_SYNTH_POWERPC_VPA_DTL:
+		return perf_sample__fprintf_synth_vpadtl(sample, fp);
 	default:
 		break;
 	}
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 7e0e58979e9c..64c63b59d617 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -271,6 +271,9 @@ struct powerpc_vpadtl_entry {
 	u64     srr1;
 };
 
+extern const char *dispatch_reasons[11];
+extern const char *preempt_reasons[10];
+
 static inline void *perf_synth__raw_data(void *p)
 {
 	return p + 4;
-- 
2.47.1