tools/perf: Allow to select the number of hash buckets

Add the -b/ --buckets argument to specify the number of hash buckets for
the private futex hash. This is directly passed to
    prctl(PR_FUTEX_HASH, PR_FUTEX_HASH_SET_SLOTS, buckets, immutable)

and must return without an error if specified. The `immutable' is 0 by
default and can be set to 1 via the -I/ --immutable argument.
The size of the private hash is verified with PR_FUTEX_HASH_GET_SLOTS.
If PR_FUTEX_HASH_GET_SLOTS failed then it is assumed that an older
kernel was used without the support and that the global hash is used.

Signed-off-by: Sebastian Andrzej Siewior <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Link: https://lore.kernel.org/r/[email protected]

1 files changed, 4 insertions, 0 deletions

diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index 49b3c89b0b35..8d6107f7cd94 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -42,6 +42,7 @@ static unsigned int threads_starting;
 static int futex_flag = 0;
 
 static struct bench_futex_parameters params = {
+	.nbuckets = -1,
 	/*
 	 * How many wakeups to do at a time.
 	 * Default to 1 in order to make the kernel work more.
@@ -50,6 +51,8 @@ static struct bench_futex_parameters params = {
 };
 
 static const struct option options[] = {
+	OPT_INTEGER( 'b', "buckets", &params.nbuckets, "Specify amount of hash buckets"),
+	OPT_BOOLEAN( 'I', "immutable", &params.buckets_immutable, "Make the hash buckets immutable"),
 	OPT_UINTEGER('t', "threads", &params.nthreads, "Specify amount of threads"),
 	OPT_UINTEGER('w', "nwakes",  &params.nwakes, "Specify amount of threads to wake at once"),
 	OPT_BOOLEAN( 's', "silent",  &params.silent, "Silent mode: do not display data/details"),
@@ -93,6 +96,7 @@ static void print_summary(void)
 	       params.nthreads,
 	       waketime_avg / USEC_PER_MSEC,
 	       rel_stddev_stats(waketime_stddev, waketime_avg));
+	futex_print_nbuckets(&params);
 }
 
 static void block_threads(pthread_t *w, struct perf_cpu_map *cpu)