Merge branch 'selftests-bpf-xdp-lb-benchmark-fixes'

Puranjay Mohan says:

====================
selftests/bpf: XDP LB benchmark fixes

Changelog:
v1: https://lore.kernel.org/all/20260519163632.2220753-1-puranjay@kernel.org/
Changes in v2:
- Drop patch 3 as it was fixing a situation that can never happen in practice.
- Replace | 1 logic in patch 1 with replacing ^ operator with +

Three bug fixes and one improvement for the XDP LB and batch-timing
benchmarks.

The cold_lru validation was failing a lot because batch_hash could
compute to zero when batch_gen matched the CPU id. Similarly,
pre-populated UDP LRU entries had atime=0 so they'd expire immediately
on any CPU that calibration didn't warm. Both are fixed in patches 1-2.

Patch 3 adds IQR outlier filtering to the timing stats to stabilize
scenarios with high stddev.
====================

Link: https://patch.msgid.link/20260520133338.3392667-1-puranjay@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

3 files changed, 38 insertions, 1 deletions

diff --git a/tools/testing/selftests/bpf/benchs/bench_bpf_timing.c b/tools/testing/selftests/bpf/benchs/bench_bpf_timing.c
index 75a39da69655..e02ad324f7bc 100644
--- a/tools/testing/selftests/bpf/benchs/bench_bpf_timing.c
+++ b/tools/testing/selftests/bpf/benchs/bench_bpf_timing.c
@@ -65,6 +65,31 @@ static int collect_samples(struct bpf_bench_timing *t,
 	return total;
 }
 
+static int filter_outliers_iqr(double *sorted, int n)
+{
+	double q1, q3, iqr, lo, hi;
+	int start = 0, end = n;
+
+	if (n < 8)
+		return n;
+
+	q1 = sorted[n / 4];
+	q3 = sorted[3 * n / 4];
+	iqr = q3 - q1;
+	lo = q1 - 1.5 * iqr;
+	hi = q3 + 1.5 * iqr;
+
+	while (start < end && sorted[start] < lo)
+		start++;
+	while (end > start && sorted[end - 1] > hi)
+		end--;
+
+	if (start > 0)
+		memmove(sorted, sorted + start, (end - start) * sizeof(double));
+
+	return end - start;
+}
+
 static void compute_stats(const double *sorted, int n,
 			  struct timing_stats *s)
 {
@@ -150,6 +175,7 @@ void bpf_bench_timing_report(struct bpf_bench_timing *t, const char *name, const
 		return;
 	}
 
+	total = filter_outliers_iqr(all, total);
 	compute_stats(all, total, &s);
 
 	if (t->machine_readable) {
diff --git a/tools/testing/selftests/bpf/benchs/bench_xdp_lb.c b/tools/testing/selftests/bpf/benchs/bench_xdp_lb.c
index 0b6709a2b03c..8e25bccbde92 100644
--- a/tools/testing/selftests/bpf/benchs/bench_xdp_lb.c
+++ b/tools/testing/selftests/bpf/benchs/bench_xdp_lb.c
@@ -563,12 +563,23 @@ static void create_per_cpu_lru_maps(struct xdp_lb_bench *skel)
 	nr_inner_maps = nr_cpus;
 }
 
+static __u64 ktime_get_ns(void)
+{
+	struct timespec ts;
+
+	clock_gettime(CLOCK_MONOTONIC, &ts);
+	return (__u64)ts.tv_sec * 1000000000ULL + ts.tv_nsec;
+}
+
 static void populate_lru(const struct test_scenario *sc, __u32 real_idx)
 {
 	struct real_pos_lru lru = { .pos = real_idx };
 	struct flow_key fk;
 	int i, err;
 
+	if (sc->ip_proto == IPPROTO_UDP)
+		lru.atime = ktime_get_ns();
+
 	build_flow_key(&fk, sc);
 
 	/* Insert into every per-CPU inner LRU so the entry is found
diff --git a/tools/testing/selftests/bpf/progs/xdp_lb_bench.c b/tools/testing/selftests/bpf/progs/xdp_lb_bench.c
index b9fd848c035d..13777b3dcac8 100644
--- a/tools/testing/selftests/bpf/progs/xdp_lb_bench.c
+++ b/tools/testing/selftests/bpf/progs/xdp_lb_bench.c
@@ -618,7 +618,7 @@ int xdp_lb_bench(struct xdp_md *xdp)
 		__u32 *saddr = data + saddr_off;
 
 		batch_gen++;
-		batch_hash = (batch_gen ^ bpf_get_smp_processor_id()) * KNUTH_HASH_MULT;
+		batch_hash = (batch_gen + bpf_get_smp_processor_id()) * KNUTH_HASH_MULT;
 		if ((void *)(saddr + 1) <= data_end)
 			*saddr ^= batch_hash;
 	}