The only caller of perf_evsel__alloc_fd is __perf_evsel__open, which
already has to explicitly handle the case when evsel->system_wide is
true (and therefore nthreads == 1), such that the number of FDs opened
matches the number of FDs it allocates space for.
Remove the duplicate logic and have perf_evsel__alloc_fd trust its
caller to provide the right number of threads.
Signed-off-by: Mark Rutland <mark.rutl...@arm.com>
Cc: Alexander Shishkin <alexander.shish...@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <a...@kernel.org>
Cc: Jiri Olsa <jo...@kernel.org>
---
tools/perf/util/evsel.c | 3 ---
1 file changed, 3 deletions(-)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 5d7037e..a1fa1c2 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -926,9 +926,6 @@ static int perf_evsel__alloc_fd(struct perf_evsel *evsel,
int ncpus, int nthread
{
int cpu, thread;
- if (evsel->system_wide)
- nthreads = 1;
-
evsel->fd = xyarray__new(ncpus, nthreads, sizeof(int));
if (evsel->fd) {
--
1.9.1
