samples/bpf: add lpm-trie benchmark

Extend the map_perf_test_{user,kern}.c infrastructure to stress test
lpm-trie lookups. We hook into the kprobe on sys_gettid() and measure
the latency depending on trie size and lookup count.

On my Intel Haswell i7-6400U, a single gettid() syscall with an empty
bpf program takes roughly 6.5us on my system. Lookups in empty tries
take ~1.8us on first try, ~0.9us on retries. Lookups in tries with 8192
entries take ~7.1us (on the first _and_ any subsequent try).

Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Reviewed-by: Daniel Mack <daniel@zonque.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/samples/bpf/map_perf_test_kern.c b/samples/bpf/map_perf_test_kern.c
index 7ee1574..a91872a 100644
--- a/samples/bpf/map_perf_test_kern.c
+++ b/samples/bpf/map_perf_test_kern.c
@@ -57,6 +57,14 @@
 	.map_flags = BPF_F_NO_PREALLOC,
 };
 
+struct bpf_map_def SEC("maps") lpm_trie_map_alloc = {
+	.type = BPF_MAP_TYPE_LPM_TRIE,
+	.key_size = 8,
+	.value_size = sizeof(long),
+	.max_entries = 10000,
+	.map_flags = BPF_F_NO_PREALLOC,
+};
+
 SEC("kprobe/sys_getuid")
 int stress_hmap(struct pt_regs *ctx)
 {
@@ -135,5 +143,27 @@
 	return 0;
 }
 
+SEC("kprobe/sys_gettid")
+int stress_lpm_trie_map_alloc(struct pt_regs *ctx)
+{
+	union {
+		u32 b32[2];
+		u8 b8[8];
+	} key;
+	unsigned int i;
+
+	key.b32[0] = 32;
+	key.b8[4] = 192;
+	key.b8[5] = 168;
+	key.b8[6] = 0;
+	key.b8[7] = 1;
+
+#pragma clang loop unroll(full)
+	for (i = 0; i < 32; ++i)
+		bpf_map_lookup_elem(&lpm_trie_map_alloc, &key);
+
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
 u32 _version SEC("version") = LINUX_VERSION_CODE;