selftests/bpf: add few verifier scale tests

Add 3 basic tests that stress verifier scalability.

test_verif_scale1.c calls non-inlined jhash() function 90 times on
different position in the packet.
This test simulates network packet parsing.
jhash function is ~140 instructions and main program is ~1200 insns.

test_verif_scale2.c force inlines jhash() function 90 times.
This program is ~15k instructions long.

test_verif_scale3.c calls non-inlined jhash() function 90 times on
But this time jhash has to process 32-bytes from the packet
instead of 14-bytes in tests 1 and 2.
jhash function is ~230 insns and main program is ~1200 insns.

$ test_progs -s
can be used to see verifier stats.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c

@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+#include <test_progs.h>
+static int libbpf_debug_print(enum libbpf_print_level level,
+			      const char *format, va_list args)
+{
+	if (level != LIBBPF_DEBUG)
+		return 0;
+
+	if (!strstr(format, "verifier log"))
+		return 0;
+	return vfprintf(stderr, "%s", args);
+}
+
+static int check_load(const char *file)
+{
+	struct bpf_prog_load_attr attr;
+	struct bpf_object *obj;
+	int err, prog_fd;
+
+	memset(&attr, 0, sizeof(struct bpf_prog_load_attr));
+	attr.file = file;
+	attr.prog_type = BPF_PROG_TYPE_SCHED_CLS;
+	attr.log_level = 4;
+	err = bpf_prog_load_xattr(&attr, &obj, &prog_fd);
+	bpf_object__close(obj);
+	if (err)
+		error_cnt++;
+	return err;
+}
+
+void test_bpf_verif_scale(void)
+{
+	const char *file1 = "./test_verif_scale1.o";
+	const char *file2 = "./test_verif_scale2.o";
+	const char *file3 = "./test_verif_scale3.o";
+	int err;
+
+	if (verifier_stats)
+		libbpf_set_print(libbpf_debug_print);
+
+	err = check_load(file1);
+	err |= check_load(file2);
+	err |= check_load(file3);
+	if (!err)
+		printf("test_verif_scale:OK\n");
+	else
+		printf("test_verif_scale:FAIL\n");
+}

tools/testing/selftests/bpf/progs/test_jhash.h

@@ -0,0 +1,70 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+
+typedef unsigned int u32;
+
+static __attribute__((always_inline)) u32 rol32(u32 word, unsigned int shift)
+{
+	return (word << shift) | (word >> ((-shift) & 31));
+}
+
+#define __jhash_mix(a, b, c)			\
+{						\
+	a -= c;  a ^= rol32(c, 4);  c += b;	\
+	b -= a;  b ^= rol32(a, 6);  a += c;	\
+	c -= b;  c ^= rol32(b, 8);  b += a;	\
+	a -= c;  a ^= rol32(c, 16); c += b;	\
+	b -= a;  b ^= rol32(a, 19); a += c;	\
+	c -= b;  c ^= rol32(b, 4);  b += a;	\
+}
+
+#define __jhash_final(a, b, c)			\
+{						\
+	c ^= b; c -= rol32(b, 14);		\
+	a ^= c; a -= rol32(c, 11);		\
+	b ^= a; b -= rol32(a, 25);		\
+	c ^= b; c -= rol32(b, 16);		\
+	a ^= c; a -= rol32(c, 4);		\
+	b ^= a; b -= rol32(a, 14);		\
+	c ^= b; c -= rol32(b, 24);		\
+}
+
+#define JHASH_INITVAL		0xdeadbeef
+
+static ATTR
+u32 jhash(const void *key, u32 length, u32 initval)
+{
+	u32 a, b, c;
+	const unsigned char *k = key;
+
+	a = b = c = JHASH_INITVAL + length + initval;
+
+	while (length > 12) {
+		a += *(volatile u32 *)(k);
+		b += *(volatile u32 *)(k + 4);
+		c += *(volatile u32 *)(k + 8);
+		__jhash_mix(a, b, c);
+		length -= 12;
+		k += 12;
+	}
+	switch (length) {
+	case 12: c += (u32)k[11]<<24;
+	case 11: c += (u32)k[10]<<16;
+	case 10: c += (u32)k[9]<<8;
+	case 9:  c += k[8];
+	case 8:  b += (u32)k[7]<<24;
+	case 7:  b += (u32)k[6]<<16;
+	case 6:  b += (u32)k[5]<<8;
+	case 5:  b += k[4];
+	case 4:  a += (u32)k[3]<<24;
+	case 3:  a += (u32)k[2]<<16;
+	case 2:  a += (u32)k[1]<<8;
+	case 1:  a += k[0];
+		 c ^= a;
+		 __jhash_final(a, b, c);
+	case 0: /* Nothing left to add */
+		break;
+	}
+
+	return c;
+}

tools/testing/selftests/bpf/progs/test_verif_scale1.c

@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+#define ATTR __attribute__((noinline))
+#include "test_jhash.h"
+
+SEC("scale90_noinline")
+int balancer_ingress(struct __sk_buff *ctx)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data = (void *)(long)ctx->data;
+	void *ptr;
+	int ret = 0, nh_off, i = 0;
+
+	nh_off = 14;
+
+	/* pragma unroll doesn't work on large loops */
+
+#define C do { \
+	ptr = data + i; \
+	if (ptr + nh_off > data_end) \
+		break; \
+	ctx->tc_index = jhash(ptr, nh_off, ctx->cb[0] + i++); \
+	} while (0);
+#define C30 C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;
+	C30;C30;C30; /* 90 calls */
+	return 0;
+}
+char _license[] SEC("license") = "GPL";

tools/testing/selftests/bpf/progs/test_verif_scale2.c

@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+#define ATTR __attribute__((always_inline))
+#include "test_jhash.h"
+
+SEC("scale90_inline")
+int balancer_ingress(struct __sk_buff *ctx)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data = (void *)(long)ctx->data;
+	void *ptr;
+	int ret = 0, nh_off, i = 0;
+
+	nh_off = 14;
+
+	/* pragma unroll doesn't work on large loops */
+
+#define C do { \
+	ptr = data + i; \
+	if (ptr + nh_off > data_end) \
+		break; \
+	ctx->tc_index = jhash(ptr, nh_off, ctx->cb[0] + i++); \
+	} while (0);
+#define C30 C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;
+	C30;C30;C30; /* 90 calls */
+	return 0;
+}
+char _license[] SEC("license") = "GPL";

tools/testing/selftests/bpf/progs/test_verif_scale3.c

@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+#define ATTR __attribute__((noinline))
+#include "test_jhash.h"
+
+SEC("scale90_noinline32")
+int balancer_ingress(struct __sk_buff *ctx)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data = (void *)(long)ctx->data;
+	void *ptr;
+	int ret = 0, nh_off, i = 0;
+
+	nh_off = 32;
+
+	/* pragma unroll doesn't work on large loops */
+
+#define C do { \
+	ptr = data + i; \
+	if (ptr + nh_off > data_end) \
+		break; \
+	ctx->tc_index = jhash(ptr, nh_off, ctx->cb[0] + i++); \
+	} while (0);
+#define C30 C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;
+	C30;C30;C30; /* 90 calls */
+	return 0;
+}
+char _license[] SEC("license") = "GPL";

tools/testing/selftests/bpf/test_progs.c

@@ -9,6 +9,7 @@
 
 int error_cnt, pass_cnt;
 bool jit_enabled;
+bool verifier_stats = false;
 
 struct ipv4_packet pkt_v4 = {
 	.eth.h_proto = __bpf_constant_htons(ETH_P_IP),
@@ -162,12 +163,15 @@ void *spin_lock_thread(void *arg)
 #include <prog_tests/tests.h>
 #undef DECLARE
 
-int main(void)
+int main(int ac, char **av)
 {
 	srand(time(NULL));
 
 	jit_enabled = is_jit_enabled();
 
+	if (ac == 2 && strcmp(av[1], "-s") == 0)
+		verifier_stats = true;
+
 #define CALL
 #include <prog_tests/tests.h>
 #undef CALL

tools/testing/selftests/bpf/test_progs.h

@@ -40,6 +40,7 @@ typedef __u16 __sum16;
 
 extern int error_cnt, pass_cnt;
 extern bool jit_enabled;
+extern bool verifier_stats;
 
 #define MAGIC_BYTES 123