[PATCH v12 4/4] eal: add PMU support to tracing library

[Tomasz Duszynski <tduszynski@marvell.com>]

In order to profile app one needs to store significant amount of samples
somewhere for an analysis later on. Since trace library supports
storing data in a CTF format lets take advantage of that and add a
dedicated PMU tracepoint.

Signed-off-by: Tomasz Duszynski <tduszynski@marvell.com>
---
 app/test/test_trace_perf.c               | 10 ++++
 doc/guides/prog_guide/profile_app.rst    |  5 ++
 doc/guides/prog_guide/trace_lib.rst      | 32 +++++++++++++
 lib/eal/common/eal_common_trace.c        | 13 ++++-
 lib/eal/common/eal_common_trace_points.c |  5 ++
 lib/eal/include/rte_eal_trace.h          | 13 +++++
 lib/eal/meson.build                      |  3 ++
 lib/eal/version.map                      |  3 ++
 lib/pmu/rte_pmu.c                        | 61 ++++++++++++++++++++++++
 lib/pmu/rte_pmu.h                        | 14 ++++++
 lib/pmu/version.map                      |  1 +
 11 files changed, 159 insertions(+), 1 deletion(-)

diff --git a/app/test/test_trace_perf.c b/app/test/test_trace_perf.c
index 8257cc02be..f1f2e74136 100644
--- a/app/test/test_trace_perf.c
+++ b/app/test/test_trace_perf.c
@@ -114,6 +114,10 @@ worker_fn_##func(void *arg) \
 #define GENERIC_DOUBLE rte_eal_trace_generic_double(3.66666)
 #define GENERIC_STR rte_eal_trace_generic_str("hello world")
 #define VOID_FP app_dpdk_test_fp()
+#ifdef RTE_EXEC_ENV_LINUX
+/* 0 corresponds first event passed via --trace= */
+#define READ_PMU rte_eal_trace_pmu_read(0)
+#endif
 
 WORKER_DEFINE(GENERIC_VOID)
 WORKER_DEFINE(GENERIC_U64)
@@ -122,6 +126,9 @@ WORKER_DEFINE(GENERIC_FLOAT)
 WORKER_DEFINE(GENERIC_DOUBLE)
 WORKER_DEFINE(GENERIC_STR)
 WORKER_DEFINE(VOID_FP)
+#ifdef RTE_EXEC_ENV_LINUX
+WORKER_DEFINE(READ_PMU)
+#endif
 
 static void
 run_test(const char *str, lcore_function_t f, struct test_data *data, size_t sz)
@@ -174,6 +181,9 @@ test_trace_perf(void)
 	run_test("double", worker_fn_GENERIC_DOUBLE, data, sz);
 	run_test("string", worker_fn_GENERIC_STR, data, sz);
 	run_test("void_fp", worker_fn_VOID_FP, data, sz);
+#ifdef RTE_EXEC_ENV_LINUX
+	run_test("read_pmu", worker_fn_READ_PMU, data, sz);
+#endif
 
 	rte_free(data);
 	return TEST_SUCCESS;
diff --git a/doc/guides/prog_guide/profile_app.rst b/doc/guides/prog_guide/profile_app.rst
index ecb90a0d94..d73d919521 100644
--- a/doc/guides/prog_guide/profile_app.rst
+++ b/doc/guides/prog_guide/profile_app.rst
@@ -33,6 +33,11 @@ As of now implementation imposes certain limitations:
 
 * Each EAL lcore measures same group of events
 
+Alternatively tracing library can be used which offers dedicated tracepoint
+``rte_eal_trace_pmu_event()``.
+
+Refer to :doc:`../prog_guide/trace_lib` for more details.
+
 
 Profiling on x86
 ----------------
diff --git a/doc/guides/prog_guide/trace_lib.rst b/doc/guides/prog_guide/trace_lib.rst
index d9b17abe90..378abccd72 100644
--- a/doc/guides/prog_guide/trace_lib.rst
+++ b/doc/guides/prog_guide/trace_lib.rst
@@ -46,6 +46,7 @@ DPDK tracing library features
   trace format and is compatible with ``LTTng``.
   For detailed information, refer to
   `Common Trace Format <https://diamon.org/ctf/>`_.
+- Support reading PMU events on ARM64 and x86-64 (Intel)
 
 How to add a tracepoint?
 ------------------------
@@ -139,6 +140,37 @@ the user must use ``RTE_TRACE_POINT_FP`` instead of ``RTE_TRACE_POINT``.
 ``RTE_TRACE_POINT_FP`` is compiled out by default and it can be enabled using
 the ``enable_trace_fp`` option for meson build.
 
+PMU tracepoint
+--------------
+
+Performance monitoring unit (PMU) event values can be read from hardware
+registers using predefined ``rte_pmu_read`` tracepoint.
+
+Tracing is enabled via ``--trace`` EAL option by passing both expression
+matching PMU tracepoint name i.e ``lib.eal.pmu.read`` and expression
+``e=ev1[,ev2,...]`` matching particular events::
+
+    --trace='.*pmu.read\|e=cpu_cycles,l1d_cache'
+
+Event names are available under ``/sys/bus/event_source/devices/PMU/events``
+directory, where ``PMU`` is a placeholder for either a ``cpu`` or a directory
+containing ``cpus``.
+
+In contrary to other tracepoints this does not need any extra variables
+added to source files. Instead, caller passes index which follows the order of
+events specified via ``--trace`` parameter. In the following example index ``0``
+corresponds to ``cpu_cyclces`` while index ``1`` corresponds to ``l1d_cache``.
+
+.. code-block:: c
+
+ ...
+ rte_eal_trace_pmu_read(0);
+ rte_eal_trace_pmu_read(1);
+ ...
+
+PMU tracing support must be explicitly enabled using the ``enable_trace_fp``
+option for meson build.
+
 Event record mode
 -----------------
 
diff --git a/lib/eal/common/eal_common_trace.c b/lib/eal/common/eal_common_trace.c
index 918f49bf4f..5373dbb717 100644
--- a/lib/eal/common/eal_common_trace.c
+++ b/lib/eal/common/eal_common_trace.c
@@ -12,6 +12,9 @@
 #include <rte_errno.h>
 #include <rte_lcore.h>
 #include <rte_per_lcore.h>
+#ifdef RTE_EXEC_ENV_LINUX
+#include <rte_pmu.h>
+#endif
 #include <rte_string_fns.h>
 
 #include "eal_trace.h"
@@ -72,8 +75,13 @@ eal_trace_init(void)
 		goto free_meta;
 
 	/* Apply global configurations */
-	STAILQ_FOREACH(arg, &trace.args, next)
+	STAILQ_FOREACH(arg, &trace.args, next) {
 		trace_args_apply(arg->val);
+#ifdef RTE_EXEC_ENV_LINUX
+		if (rte_pmu_init() == 0)
+			rte_pmu_add_events_by_pattern(arg->val);
+#endif
+	}
 
 	rte_trace_mode_set(trace.mode);
 
@@ -89,6 +97,9 @@ eal_trace_init(void)
 void
 eal_trace_fini(void)
 {
+#ifdef RTE_EXEC_ENV_LINUX
+	rte_pmu_fini();
+#endif
 	trace_mem_free();
 	trace_metadata_destroy();
 	eal_trace_args_free();
diff --git a/lib/eal/common/eal_common_trace_points.c b/lib/eal/common/eal_common_trace_points.c
index 0f1240ea3a..05f7ed83d5 100644
--- a/lib/eal/common/eal_common_trace_points.c
+++ b/lib/eal/common/eal_common_trace_points.c
@@ -100,3 +100,8 @@ RTE_TRACE_POINT_REGISTER(rte_eal_trace_intr_enable,
 	lib.eal.intr.enable)
 RTE_TRACE_POINT_REGISTER(rte_eal_trace_intr_disable,
 	lib.eal.intr.disable)
+
+#ifdef RTE_EXEC_ENV_LINUX
+RTE_TRACE_POINT_REGISTER(rte_eal_trace_pmu_read,
+	lib.eal.pmu.read)
+#endif
diff --git a/lib/eal/include/rte_eal_trace.h b/lib/eal/include/rte_eal_trace.h
index c3d15bbe5e..b7e7f5b085 100644
--- a/lib/eal/include/rte_eal_trace.h
+++ b/lib/eal/include/rte_eal_trace.h
@@ -15,6 +15,9 @@
 extern "C" {
 #endif
 
+#ifdef RTE_EXEC_ENV_LINUX
+#include <rte_pmu.h>
+#endif
 #include <rte_trace_point.h>
 
 /* Generic */
@@ -127,6 +130,16 @@ RTE_TRACE_POINT(
 
 #define RTE_EAL_TRACE_GENERIC_FUNC rte_eal_trace_generic_func(__func__)
 
+#ifdef RTE_EXEC_ENV_LINUX
+RTE_TRACE_POINT_FP(
+	rte_eal_trace_pmu_read,
+	RTE_TRACE_POINT_ARGS(unsigned int index),
+	uint64_t val;
+	val = rte_pmu_read(index);
+	rte_trace_point_emit_u64(val);
+)
+#endif
+
 #ifdef __cplusplus
 }
 #endif
diff --git a/lib/eal/meson.build b/lib/eal/meson.build
index e1d6c4cf17..802b66afee 100644
--- a/lib/eal/meson.build
+++ b/lib/eal/meson.build
@@ -18,6 +18,9 @@ deps += ['log', 'kvargs']
 if not is_windows
     deps += ['telemetry']
 endif
+if is_linux
+    deps += ['pmu']
+endif
 if dpdk_conf.has('RTE_USE_LIBBSD')
     ext_deps += libbsd
 endif
diff --git a/lib/eal/version.map b/lib/eal/version.map
index e3ff412683..17c56f6bf7 100644
--- a/lib/eal/version.map
+++ b/lib/eal/version.map
@@ -396,6 +396,9 @@ EXPERIMENTAL {
 
 	# added in 24.03
 	rte_vfio_get_device_info; # WINDOWS_NO_EXPORT
+
+	# added in 24.11
+	__rte_eal_trace_pmu_read; # WINDOWS_NO_EXPORT
 };
 
 INTERNAL {
diff --git a/lib/pmu/rte_pmu.c b/lib/pmu/rte_pmu.c
index ddccbfb7c6..70f6244980 100644
--- a/lib/pmu/rte_pmu.c
+++ b/lib/pmu/rte_pmu.c
@@ -403,6 +403,67 @@ rte_pmu_add_event(const char *name)
 	return event->index;
 }
 
+static int
+add_events(const char *pattern)
+{
+	char *token, *copy;
+	int ret = 0;
+
+	copy = strdup(pattern);
+	if (copy == NULL)
+		return -ENOMEM;
+
+	token = strtok(copy, ",");
+	while (token) {
+		ret = rte_pmu_add_event(token);
+		if (ret < 0)
+			break;
+
+		token = strtok(NULL, ",");
+	}
+
+	free(copy);
+
+	return ret >= 0 ? 0 : ret;
+}
+
+int
+rte_pmu_add_events_by_pattern(const char *pattern)
+{
+	regmatch_t rmatch;
+	char buf[BUFSIZ];
+	unsigned int num;
+	regex_t reg;
+	int ret;
+
+	/* events are matched against occurrences of e=ev1[,ev2,..] pattern */
+	ret = regcomp(&reg, "e=([_[:alnum:]-],?)+", REG_EXTENDED);
+	if (ret)
+		return -EINVAL;
+
+	for (;;) {
+		if (regexec(&reg, pattern, 1, &rmatch, 0))
+			break;
+
+		num = rmatch.rm_eo - rmatch.rm_so;
+		if (num > sizeof(buf))
+			num = sizeof(buf);
+
+		/* skip e= pattern prefix */
+		memcpy(buf, pattern + rmatch.rm_so + 2, num - 2);
+		buf[num - 2] = '\0';
+		ret = add_events(buf);
+		if (ret)
+			break;
+
+		pattern += rmatch.rm_eo;
+	}
+
+	regfree(&reg);
+
+	return ret;
+}
+
 int
 rte_pmu_init(void)
 {
diff --git a/lib/pmu/rte_pmu.h b/lib/pmu/rte_pmu.h
index a40f69fb5d..78fa6bba19 100644
--- a/lib/pmu/rte_pmu.h
+++ b/lib/pmu/rte_pmu.h
@@ -170,6 +170,20 @@ __rte_experimental
 int
 rte_pmu_add_event(const char *name);
 
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice
+ *
+ * Add events matching pattern to the group of enabled events.
+ *
+ * @param pattern
+ *   Pattern e=ev1[,ev2,...] matching events, where evX is a placeholder for an event listed under
+ *   /sys/bus/event_source/devices/pmu/events.
+ */
+__rte_experimental
+int
+rte_pmu_add_events_by_pattern(const char *pattern);
+
 /**
  * @warning
  * @b EXPERIMENTAL: this API may change without prior notice
diff --git a/lib/pmu/version.map b/lib/pmu/version.map
index d7c80ce4ce..0c98209b4a 100644
--- a/lib/pmu/version.map
+++ b/lib/pmu/version.map
@@ -6,6 +6,7 @@ EXPERIMENTAL {
 	per_lcore__event_group;
 	rte_pmu;
 	rte_pmu_add_event;
+	rte_pmu_add_events_by_pattern;
 	rte_pmu_fini;
 	rte_pmu_init;
 	rte_pmu_read;
-- 
2.34.1