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 */
[[email protected] ~]# 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 */
[[email protected] ~]# 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 <[email protected]>
Acked-by: Alexei Starovoitov <[email protected]>
Signed-off-by: David S. Miller <[email protected]>

Author: iamkafai

samples/bpf/Makefile

@@ -2,6 +2,7 @@
 obj- := dummy.o
 
 # List of programs to build
+hostprogs-y := test_lru_dist
 hostprogs-y += sock_example
 hostprogs-y += fds_example
 hostprogs-y += sockex1
@@ -28,6 +29,7 @@ hostprogs-y += trace_event
 hostprogs-y += sampleip
 hostprogs-y += tc_l2_redirect
 
+test_lru_dist-objs := test_lru_dist.o libbpf.o
 sock_example-objs := sock_example.o libbpf.o
 fds_example-objs := bpf_load.o libbpf.o fds_example.o
 sockex1-objs := bpf_load.o libbpf.o sockex1_user.o

samples/bpf/map_perf_test_kern.c

@@ -19,6 +19,21 @@ struct bpf_map_def SEC("maps") hash_map = {
 	.max_entries = MAX_ENTRIES,
 };
 
+struct bpf_map_def SEC("maps") lru_hash_map = {
+	.type = BPF_MAP_TYPE_LRU_HASH,
+	.key_size = sizeof(u32),
+	.value_size = sizeof(long),
+	.max_entries = 10000,
+};
+
+struct bpf_map_def SEC("maps") percpu_lru_hash_map = {
+	.type = BPF_MAP_TYPE_LRU_HASH,
+	.key_size = sizeof(u32),
+	.value_size = sizeof(long),
+	.max_entries = 10000,
+	.map_flags = BPF_F_NO_COMMON_LRU,
+};
+
 struct bpf_map_def SEC("maps") percpu_hash_map = {
 	.type = BPF_MAP_TYPE_PERCPU_HASH,
 	.key_size = sizeof(u32),
@@ -53,6 +68,7 @@ int stress_hmap(struct pt_regs *ctx)
 	value = bpf_map_lookup_elem(&hash_map, &key);
 	if (value)
 		bpf_map_delete_elem(&hash_map, &key);
+
 	return 0;
 }
 
@@ -96,5 +112,28 @@ int stress_percpu_hmap_alloc(struct pt_regs *ctx)
 		bpf_map_delete_elem(&percpu_hash_map_alloc, &key);
 	return 0;
 }
+
+SEC("kprobe/sys_getpid")
+int stress_lru_hmap_alloc(struct pt_regs *ctx)
+{
+	u32 key = bpf_get_prandom_u32();
+	long val = 1;
+
+	bpf_map_update_elem(&lru_hash_map, &key, &val, BPF_ANY);
+
+	return 0;
+}
+
+SEC("kprobe/sys_getppid")
+int stress_percpu_lru_hmap_alloc(struct pt_regs *ctx)
+{
+	u32 key = bpf_get_prandom_u32();
+	long val = 1;
+
+	bpf_map_update_elem(&percpu_lru_hash_map, &key, &val, BPF_ANY);
+
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
 u32 _version SEC("version") = LINUX_VERSION_CODE;

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)