summaryrefslogtreecommitdiff
path: root/kernel/events
diff options
context:
space:
mode:
authorDavid Carrillo-Cisneros <davidcc@google.com>2016-08-17 13:55:06 -0700
committerIngo Molnar <mingo@kernel.org>2016-08-18 10:53:59 +0200
commitd6a2f9035bfc27d0e9d78b13635dda9fb017ac01 (patch)
treeff202f5400841b1714a1fe4a61682f75b614e742 /kernel/events
parent4ff6a8debf48a7bf48e93c01da720785070d3a25 (diff)
perf/core: Introduce PMU_EV_CAP_READ_ACTIVE_PKG
Introduce the flag PMU_EV_CAP_READ_ACTIVE_PKG, useful for uncore events, that allows a PMU to signal the generic perf code that an event is readable in the current CPU if the event is active in a CPU in the same package as the current CPU. This is an optimization that avoids a unnecessary IPI for the common case where uncore events are run and read in the same package but in different CPUs. As an example, the IPI removal speeds up perf_read() in my Haswell system as follows: - For event UNC_C_LLC_LOOKUP: From 260 us to 31 us. - For event RAPL's power/energy-cores/: From to 255 us to 27 us. For the optimization to work, all events in the group must have it (similarly to PERF_EV_CAP_SOFTWARE). Signed-off-by: David Carrillo-Cisneros <davidcc@google.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Carrillo-Cisneros <davidcc@google.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul Turner <pjt@google.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vegard Nossum <vegard.nossum@gmail.com> Cc: Vince Weaver <vincent.weaver@maine.edu> Link: http://lkml.kernel.org/r/1471467307-61171-4-git-send-email-davidcc@google.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'kernel/events')
-rw-r--r--kernel/events/core.c25
1 files changed, 23 insertions, 2 deletions
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 8c42a5ae9030..3f07e6cfc1b6 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3424,6 +3424,22 @@ struct perf_read_data {
int ret;
};
+static int find_cpu_to_read(struct perf_event *event, int local_cpu)
+{
+ int event_cpu = event->oncpu;
+ u16 local_pkg, event_pkg;
+
+ if (event->group_caps & PERF_EV_CAP_READ_ACTIVE_PKG) {
+ event_pkg = topology_physical_package_id(event_cpu);
+ local_pkg = topology_physical_package_id(local_cpu);
+
+ if (event_pkg == local_pkg)
+ return local_cpu;
+ }
+
+ return event_cpu;
+}
+
/*
* Cross CPU call to read the hardware event
*/
@@ -3545,7 +3561,7 @@ u64 perf_event_read_local(struct perf_event *event)
static int perf_event_read(struct perf_event *event, bool group)
{
- int ret = 0;
+ int ret = 0, cpu_to_read, local_cpu;
/*
* If event is enabled and currently active on a CPU, update the
@@ -3557,7 +3573,12 @@ static int perf_event_read(struct perf_event *event, bool group)
.group = group,
.ret = 0,
};
- ret = smp_call_function_single(event->oncpu, __perf_event_read, &data, 1);
+
+ local_cpu = get_cpu();
+ cpu_to_read = find_cpu_to_read(event, local_cpu);
+ put_cpu();
+
+ ret = smp_call_function_single(cpu_to_read, __perf_event_read, &data, 1);
/* The event must have been read from an online CPU: */
WARN_ON_ONCE(ret);
ret = ret ? : data.ret;