perf kwork: Add softirq trace BPF support

Implements softirq trace bpf function.

Test cases:
Trace softirq latency without filter:

  # perf kwork -k softirq lat -b
  Starting trace, Hit <Ctrl+C> to stop and report
  ^C
    Kwork Name                     | Cpu  | Avg delay     | Count     | Max delay     | Max delay start     | Max delay end       |
   --------------------------------------------------------------------------------------------------------------------------------
    (s)RCU:9                       | 0005 |      0.281 ms |         3 |      0.338 ms |     111295.752222 s |     111295.752560 s |
    (s)RCU:9                       | 0002 |      0.262 ms |        24 |      1.400 ms |     111301.335986 s |     111301.337386 s |
    (s)SCHED:7                     | 0005 |      0.177 ms |        14 |      0.212 ms |     111295.752270 s |     111295.752481 s |
    (s)RCU:9                       | 0007 |      0.161 ms |        47 |      2.022 ms |     111295.402159 s |     111295.404181 s |
    (s)NET_RX:3                    | 0003 |      0.149 ms |        12 |      1.261 ms |     111301.192964 s |     111301.194225 s |
    (s)TIMER:1                     | 0001 |      0.105 ms |         9 |      0.198 ms |     111301.180191 s |     111301.180389 s |
    ... <SNIP> ...
    (s)NET_RX:3                    | 0002 |      0.098 ms |         6 |      0.124 ms |     111295.403760 s |     111295.403884 s |
    (s)SCHED:7                     | 0001 |      0.093 ms |        19 |      0.242 ms |     111301.180256 s |     111301.180498 s |
    (s)SCHED:7                     | 0007 |      0.078 ms |        15 |      0.188 ms |     111300.064226 s |     111300.064415 s |
    (s)SCHED:7                     | 0004 |      0.077 ms |        11 |      0.213 ms |     111301.361759 s |     111301.361973 s |
    (s)SCHED:7                     | 0000 |      0.063 ms |        33 |      0.805 ms |     111295.401811 s |     111295.402616 s |
    (s)SCHED:7                     | 0003 |      0.063 ms |        14 |      0.085 ms |     111301.192255 s |     111301.192340 s |
   --------------------------------------------------------------------------------------------------------------------------------

Trace softirq latency with cpu filter:

  # perf kwork -k softirq lat -b -C 1
  Starting trace, Hit <Ctrl+C> to stop and report
  ^C
    Kwork Name                     | Cpu  | Avg delay     | Count     | Max delay     | Max delay start     | Max delay end       |
   --------------------------------------------------------------------------------------------------------------------------------
    (s)RCU:9                       | 0001 |      0.178 ms |         5 |      0.572 ms |     111435.534135 s |     111435.534707 s |
   --------------------------------------------------------------------------------------------------------------------------------

Trace softirq latency with name filter:

  # perf kwork -k softirq lat -b -n SCHED
  Starting trace, Hit <Ctrl+C> to stop and report
  ^C
    Kwork Name                     | Cpu  | Avg delay     | Count     | Max delay     | Max delay start     | Max delay end       |
   --------------------------------------------------------------------------------------------------------------------------------
    (s)SCHED:7                     | 0001 |      0.295 ms |        15 |      2.183 ms |     111452.534950 s |     111452.537133 s |
    (s)SCHED:7                     | 0002 |      0.215 ms |        10 |      0.315 ms |     111460.000238 s |     111460.000553 s |
    (s)SCHED:7                     | 0005 |      0.190 ms |        29 |      0.338 ms |     111457.032538 s |     111457.032876 s |
    (s)SCHED:7                     | 0003 |      0.097 ms |        10 |      0.319 ms |     111452.434351 s |     111452.434670 s |
    (s)SCHED:7                     | 0006 |      0.089 ms |         1 |      0.089 ms |     111450.737450 s |     111450.737539 s |
    (s)SCHED:7                     | 0007 |      0.085 ms |        17 |      0.169 ms |     111452.471333 s |     111452.471502 s |
    (s)SCHED:7                     | 0004 |      0.071 ms |        15 |      0.221 ms |     111452.535252 s |     111452.535473 s |
    (s)SCHED:7                     | 0000 |      0.044 ms |        32 |      0.130 ms |     111460.001982 s |     111460.002112 s |
   --------------------------------------------------------------------------------------------------------------------------------
Signed-off-by: Yang Jihong <yangjihong1@huawei.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Clarke <pc@us.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220709015033.38326-17-yangjihong1@huawei.com
[ Add {} for multiline if blocks ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/util/bpf_kwork.c

@@ -98,10 +98,26 @@ static struct kwork_class_bpf kwork_irq_bpf = {
 	.get_work_name = get_work_name_from_map,
 };
 
+static void softirq_load_prepare(struct perf_kwork *kwork)
+{
+	if (kwork->report == KWORK_REPORT_RUNTIME) {
+		bpf_program__set_autoload(skel->progs.report_softirq_entry, true);
+		bpf_program__set_autoload(skel->progs.report_softirq_exit, true);
+	} else if (kwork->report == KWORK_REPORT_LATENCY) {
+		bpf_program__set_autoload(skel->progs.latency_softirq_raise, true);
+		bpf_program__set_autoload(skel->progs.latency_softirq_entry, true);
+	}
+}
+
+static struct kwork_class_bpf kwork_softirq_bpf = {
+	.load_prepare  = softirq_load_prepare,
+	.get_work_name = get_work_name_from_map,
+};
+
 static struct kwork_class_bpf *
 kwork_class_bpf_supported_list[KWORK_CLASS_MAX] = {
 	[KWORK_CLASS_IRQ]       = &kwork_irq_bpf,
-	[KWORK_CLASS_SOFTIRQ]   = NULL,
+	[KWORK_CLASS_SOFTIRQ]   = &kwork_softirq_bpf,
 	[KWORK_CLASS_WORKQUEUE] = NULL,
 };
 

tools/perf/util/bpf_skel/kwork_trace.bpf.c

@@ -221,4 +221,79 @@ int report_irq_handler_exit(struct trace_event_raw_irq_handler_exit *ctx)
 	return update_timeend(&perf_kwork_report, &perf_kwork_time, &key);
 }
 
+static char softirq_name_list[NR_SOFTIRQS][MAX_KWORKNAME] = {
+	{ "HI"       },
+	{ "TIMER"    },
+	{ "NET_TX"   },
+	{ "NET_RX"   },
+	{ "BLOCK"    },
+	{ "IRQ_POLL" },
+	{ "TASKLET"  },
+	{ "SCHED"    },
+	{ "HRTIMER"  },
+	{ "RCU"      },
+};
+
+SEC("tracepoint/irq/softirq_entry")
+int report_softirq_entry(struct trace_event_raw_softirq *ctx)
+{
+	unsigned int vec = ctx->vec;
+	struct work_key key = {
+		.type = KWORK_CLASS_SOFTIRQ,
+		.cpu  = bpf_get_smp_processor_id(),
+		.id   = (__u64)vec,
+	};
+
+	if (vec < NR_SOFTIRQS) {
+		return update_timestart_and_name(&perf_kwork_time,
+						 &perf_kwork_names, &key,
+						 softirq_name_list[vec]);
+	}
+
+	return 0;
+}
+
+SEC("tracepoint/irq/softirq_exit")
+int report_softirq_exit(struct trace_event_raw_softirq *ctx)
+{
+	struct work_key key = {
+		.type = KWORK_CLASS_SOFTIRQ,
+		.cpu  = bpf_get_smp_processor_id(),
+		.id   = (__u64)ctx->vec,
+	};
+
+	return update_timeend(&perf_kwork_report, &perf_kwork_time, &key);
+}
+
+SEC("tracepoint/irq/softirq_raise")
+int latency_softirq_raise(struct trace_event_raw_softirq *ctx)
+{
+	unsigned int vec = ctx->vec;
+	struct work_key key = {
+		.type = KWORK_CLASS_SOFTIRQ,
+		.cpu  = bpf_get_smp_processor_id(),
+		.id   = (__u64)vec,
+	};
+
+	if (vec < NR_SOFTIRQS) {
+		return update_timestart_and_name(&perf_kwork_time,
+						 &perf_kwork_names, &key,
+						 softirq_name_list[vec]);
+	}
+
+	return 0;
+}
+
+SEC("tracepoint/irq/softirq_entry")
+int latency_softirq_entry(struct trace_event_raw_softirq *ctx)
+{
+	struct work_key key = {
+		.type = KWORK_CLASS_SOFTIRQ,
+		.cpu  = bpf_get_smp_processor_id(),
+		.id   = (__u64)ctx->vec,
+	};
+
+	return update_timeend(&perf_kwork_report, &perf_kwork_time, &key);
+}
+
 char LICENSE[] SEC("license") = "Dual BSD/GPL";