[lttng-dev] [PATCH lttng-ust 2/2] Add perf context support for ARMv7

[Julien Desfossez]

Allow to add perf context to UST traces. ARMv7 does not have a reliable
way to read perf PMU counters entirely from user-space like we do on
x86, so this approach requires a system call everytime a counter needs
to be read which has a significant performance impact.

This generic approach might work on other architecture, but it has not
yet been tested so it is not enabled in the code.

Signed-off-by: Julien Desfossez <jdesfossez at efficios.com>
---
 configure.ac                               |  1 +
 liblttng-ust-ctl/ustctl.c                  |  2 +-
 liblttng-ust/lttng-context-perf-counters.c | 71 ++++++++++++++++++++----------
 3 files changed, 50 insertions(+), 24 deletions(-)

diff --git a/configure.ac b/configure.ac
index de462ff..5475640 100644
--- a/configure.ac
+++ b/configure.ac
@@ -219,6 +219,7 @@ AS_CASE([$host_cpu],
 	[i[[3456]]86], [UST_SUPPORT_FOR_ARCH_PERF_EVENT_COUNTERS=yes],
 	[x86_64], [UST_SUPPORT_FOR_ARCH_PERF_EVENT_COUNTERS=yes],
 	[amd64], [UST_SUPPORT_FOR_ARCH_PERF_EVENT_COUNTERS=yes],
+	[armv7l], [UST_SUPPORT_FOR_ARCH_PERF_EVENT_COUNTERS=yes],
 	[UST_SUPPORT_FOR_ARCH_PERF_EVENT_COUNTERS=no])
 AC_MSG_RESULT([$UST_SUPPORT_FOR_ARCH_PERF_EVENT_COUNTERS])
 
diff --git a/liblttng-ust-ctl/ustctl.c b/liblttng-ust-ctl/ustctl.c
index 0165786..97445d5 100644
--- a/liblttng-ust-ctl/ustctl.c
+++ b/liblttng-ust-ctl/ustctl.c
@@ -1742,7 +1742,7 @@ int ustctl_get_instance_id(struct ustctl_consumer_stream *stream,
 	return client_cb->instance_id(buf, handle, id);
 }
 
-#if defined(__x86_64__) || defined(__i386__)
+#if defined(__x86_64__) || defined(__i386__) || defined(__ARM_ARCH_7A__)
 
 int ustctl_has_perf_counters(void)
 {
diff --git a/liblttng-ust/lttng-context-perf-counters.c b/liblttng-ust/lttng-context-perf-counters.c
index 725b1b4..220686b 100644
--- a/liblttng-ust/lttng-context-perf-counters.c
+++ b/liblttng-ust/lttng-context-perf-counters.c
@@ -91,17 +91,13 @@ uint64_t rdpmc(unsigned int counter)
 	return low | ((uint64_t) high) << 32;
 }
 
-#else /* defined(__x86_64__) || defined(__i386__) */
-
-#error "Perf event counters are only supported on x86 so far."
-
-#endif /* #else defined(__x86_64__) || defined(__i386__) */
-
 static
-uint64_t read_perf_counter(struct perf_event_mmap_page *pc)
+uint64_t read_perf_counter(
+		struct lttng_perf_counter_thread_field *thread_field)
 {
 	uint32_t seq, idx;
 	uint64_t count;
+	struct perf_event_mmap_page *pc = thread_field->pc;
 
 	if (caa_unlikely(!pc))
 		return 0;
@@ -122,6 +118,31 @@ uint64_t read_perf_counter(struct perf_event_mmap_page *pc)
 	return count;
 }
 
+#elif defined (__ARM_ARCH_7A__)
+
+static
+uint64_t read_perf_counter(
+		struct lttng_perf_counter_thread_field *thread_field)
+{
+	uint64_t count;
+	int ret;
+
+	if (caa_unlikely(thread_field->fd < 0))
+		return 0;
+
+	ret = read(thread_field->fd, &count, sizeof(count));
+	if (ret < sizeof(count))
+		return 0;
+
+	return count;
+}
+
+#else /* defined(__x86_64__) || defined(__i386__) || defined(__ARM_ARCH_7A__) */
+
+#error "Perf event counters are only supported on x86 and ARMv7 so far."
+
+#endif /* #else defined(__x86_64__) || defined(__i386__) || defined(__ARM_ARCH_7A__) */
+
 static
 int sys_perf_event_open(struct perf_event_attr *attr,
 		pid_t pid, int cpu, int group_fd,
@@ -144,6 +165,20 @@ int open_perf_fd(struct perf_event_attr *attr)
 }
 
 static
+void close_perf_fd(int fd)
+{
+	int ret;
+
+	if (fd < 0)
+		return;
+
+	ret = close(fd);
+	if (ret) {
+		perror("Error closing LTTng-UST perf memory mapping FD");
+	}
+}
+
+static
 struct perf_event_mmap_page *setup_perf(
 		struct lttng_perf_counter_thread_field *thread_field)
 {
@@ -160,25 +195,10 @@ struct perf_event_mmap_page *setup_perf(
 	thread_field->fd = -1;
 #endif
 
-end:
 	return perf_addr;
 }
 
 static
-void close_perf_fd(int fd)
-{
-	int ret;
-
-	if (fd < 0)
-		return;
-
-	ret = close(fd);
-	if (ret) {
-		perror("Error closing LTTng-UST perf memory mapping FD");
-	}
-}
-
-static
 void unmap_perf_page(struct perf_event_mmap_page *pc)
 {
 	int ret;
@@ -292,7 +312,7 @@ uint64_t wrapper_perf_counter_read(struct lttng_ctx_field *field)
 
 	perf_field = field->u.perf_counter;
 	perf_thread_field = get_thread_field(perf_field);
-	return read_perf_counter(perf_thread_field->pc);
+	return read_perf_counter(perf_thread_field);
 }
 
 static
@@ -413,7 +433,12 @@ int lttng_add_perf_counter_to_ctx(uint32_t type,
 
 	perf_field->attr.type = type;
 	perf_field->attr.config = config;
+#if defined (__ARM_ARCH_7A__)
+	/* exclude_kernel does not work on ARM. */
+	perf_field->attr.exclude_kernel = 0;
+#else
 	perf_field->attr.exclude_kernel = 1;
+#endif
 	CDS_INIT_LIST_HEAD(&perf_field->thread_field_list);
 	field->u.perf_counter = perf_field;
 
-- 
1.9.1