bpf: Add tests for the LRU bpf_htab

This patch has some unit tests and a test_lru_dist.

The test_lru_dist reads in the numeric keys from a file.
The files used here are generated by a modified fio-genzipf tool
originated from the fio test suit.  The sample data file can be
found here: https://github.com/iamkafai/bpf-lru

The zipf.* data files have 100k numeric keys and the key is also
ranged from 1 to 100k.

The test_lru_dist outputs the number of unique keys (nr_unique).
F.e. The following means, 61239 of them is unique out of 100k keys.
nr_misses means it cannot be found in the LRU map, so nr_misses
must be >= nr_unique. test_lru_dist also simulates a perfect LRU
map as a comparison:

[root@arch-fb-vm1 ~]# ~/devshare/fb-kernel/linux/samples/bpf/test_lru_dist \
/root/zipf.100k.a1_01.out 4000 1
...
test_parallel_lru_dist (map_type:9 map_flags:0x0):
    task:0 BPF LRU: nr_unique:23093(/100000) nr_misses:31603(/100000)
    task:0 Perfect LRU: nr_unique:23093(/100000 nr_misses:34328(/100000)
....
test_parallel_lru_dist (map_type:9 map_flags:0x2):
    task:0 BPF LRU: nr_unique:23093(/100000) nr_misses:31710(/100000)
    task:0 Perfect LRU: nr_unique:23093(/100000 nr_misses:34328(/100000)

[root@arch-fb-vm1 ~]# ~/devshare/fb-kernel/linux/samples/bpf/test_lru_dist \
/root/zipf.100k.a0_01.out 40000 1
...
test_parallel_lru_dist (map_type:9 map_flags:0x0):
    task:0 BPF LRU: nr_unique:61239(/100000) nr_misses:67054(/100000)
    task:0 Perfect LRU: nr_unique:61239(/100000 nr_misses:66993(/100000)
...
test_parallel_lru_dist (map_type:9 map_flags:0x2):
    task:0 BPF LRU: nr_unique:61239(/100000) nr_misses:67068(/100000)
    task:0 Perfect LRU: nr_unique:61239(/100000 nr_misses:66993(/100000)

LRU map has also been added to map_perf_test:
/* Global LRU */
[root@kerneltest003.31.prn1 ~]# for i in 1 4 8; do echo -n "$i cpus: "; \
./map_perf_test 16 $i | awk '{r += $3}END{print r " updates"}'; done
 1 cpus: 2934082 updates
 4 cpus: 7391434 updates
 8 cpus: 6500576 updates

/* Percpu LRU */
[root@kerneltest003.31.prn1 ~]# for i in 1 4 8; do echo -n "$i cpus: "; \
./map_perf_test 32 $i | awk '{r += $3}END{print r " updates"}'; done
  1 cpus: 2896553 updates
  4 cpus: 9766395 updates
  8 cpus: 17460553 updates

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/samples/bpf/map_perf_test_user.c b/samples/bpf/map_perf_test_user.c
index 3147377..9505b4d 100644
--- a/samples/bpf/map_perf_test_user.c
+++ b/samples/bpf/map_perf_test_user.c
@@ -35,6 +35,8 @@ static __u64 time_get_ns(void)
 #define PERCPU_HASH_PREALLOC	(1 << 1)
 #define HASH_KMALLOC		(1 << 2)
 #define PERCPU_HASH_KMALLOC	(1 << 3)
+#define LRU_HASH_PREALLOC	(1 << 4)
+#define PERCPU_LRU_HASH_PREALLOC	(1 << 5)
 
 static int test_flags = ~0;
 
@@ -50,6 +52,30 @@ static void test_hash_prealloc(int cpu)
 	       cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time));
 }
 
+static void test_lru_hash_prealloc(int cpu)
+{
+	__u64 start_time;
+	int i;
+
+	start_time = time_get_ns();
+	for (i = 0; i < MAX_CNT; i++)
+		syscall(__NR_getpid);
+	printf("%d:lru_hash_map_perf pre-alloc %lld events per sec\n",
+	       cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time));
+}
+
+static void test_percpu_lru_hash_prealloc(int cpu)
+{
+	__u64 start_time;
+	int i;
+
+	start_time = time_get_ns();
+	for (i = 0; i < MAX_CNT; i++)
+		syscall(__NR_getppid);
+	printf("%d:lru_hash_map_perf pre-alloc %lld events per sec\n",
+	       cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time));
+}
+
 static void test_percpu_hash_prealloc(int cpu)
 {
 	__u64 start_time;
@@ -105,6 +131,12 @@ static void loop(int cpu)
 
 	if (test_flags & PERCPU_HASH_KMALLOC)
 		test_percpu_hash_kmalloc(cpu);
+
+	if (test_flags & LRU_HASH_PREALLOC)
+		test_lru_hash_prealloc(cpu);
+
+	if (test_flags & PERCPU_LRU_HASH_PREALLOC)
+		test_percpu_lru_hash_prealloc(cpu);
 }
 
 static void run_perf_test(int tasks)