Merge branch 'bpf-verifier-scalability'

Alexei Starovoitov says:

====================
v1->v2:
- fixed typo in patch 1
- added a patch to convert kcalloc to kvcalloc
- added a patch to verbose 16-bit jump offset check
- added a test with 1m insns

This patch set is the first step to be able to accept large programs.
The verifier still suffers from its brute force algorithm and
large programs can easily hit 1M insn_processed limit.
A lot more work is necessary to be able to verify large programs.

v1:
Realize two key ideas to speed up verification speed by ~20 times
1. every 'branching' instructions records all verifier states.
   not all of them are useful for search pruning.
   add a simple heuristic to keep states that were successful in search pruning
   and remove those that were not
2. mark_reg_read walks parentage chain of registers to mark parents as LIVE_READ.
   Once the register is marked there is no need to remark it again in the future.
   Hence stop walking the chain once first LIVE_READ is seen.

1st optimization gives 10x speed up on large programs
and 2nd optimization reduces the cost of mark_reg_read from ~40% of cpu to <1%.
Combined the deliver ~20x speedup on large programs.

Faster and bounded verification time allows to increase insn_processed
limit to 1 million from 130k.
Worst case it takes 1/10 of a second to process that many instructions
and peak memory consumption is peak_states * sizeof(struct bpf_verifier_state)
which is around ~5Mbyte.

Increase insn_per_program limit for root to insn_processed limit.

Add verification stats and stress tests for verifier scalability.
====================

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

9 files changed, 250 insertions, 10 deletions

diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
new file mode 100644
index 000000000000..23b159d95c3f
--- /dev/null
+++ b/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");
+}
diff --git a/tools/testing/selftests/bpf/progs/test_jhash.h b/tools/testing/selftests/bpf/progs/test_jhash.h
new file mode 100644
index 000000000000..3d12c11a8d47
--- /dev/null
+++ b/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;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_verif_scale1.c b/tools/testing/selftests/bpf/progs/test_verif_scale1.c
new file mode 100644
index 000000000000..f3236ce35f31
--- /dev/null
+++ b/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";
diff --git a/tools/testing/selftests/bpf/progs/test_verif_scale2.c b/tools/testing/selftests/bpf/progs/test_verif_scale2.c
new file mode 100644
index 000000000000..77830693eccb
--- /dev/null
+++ b/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";
diff --git a/tools/testing/selftests/bpf/progs/test_verif_scale3.c b/tools/testing/selftests/bpf/progs/test_verif_scale3.c
new file mode 100644
index 000000000000..1848da04ea41
--- /dev/null
+++ b/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";
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 5d10aee9e277..bf5c90998916 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/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
diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h
index 51a07367cd43..f095e1d4c657 100644
--- a/tools/testing/selftests/bpf/test_progs.h
+++ b/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
 
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 19b5d03acc2a..75ef63b42f2c 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -50,6 +50,7 @@
 #include "../../../include/linux/filter.h"
 
 #define MAX_INSNS	BPF_MAXINSNS
+#define MAX_TEST_INSNS	1000000
 #define MAX_FIXUPS	8
 #define MAX_NR_MAPS	14
 #define MAX_TEST_RUNS	8
@@ -66,6 +67,7 @@ static int skips;
 struct bpf_test {
 	const char *descr;
 	struct bpf_insn	insns[MAX_INSNS];
+	struct bpf_insn	*fill_insns;
 	int fixup_map_hash_8b[MAX_FIXUPS];
 	int fixup_map_hash_48b[MAX_FIXUPS];
 	int fixup_map_hash_16b[MAX_FIXUPS];
@@ -83,6 +85,7 @@ struct bpf_test {
 	const char *errstr;
 	const char *errstr_unpriv;
 	uint32_t retval, retval_unpriv, insn_processed;
+	int prog_len;
 	enum {
 		UNDEF,
 		ACCEPT,
@@ -119,10 +122,11 @@ struct other_val {
 
 static void bpf_fill_ld_abs_vlan_push_pop(struct bpf_test *self)
 {
-	/* test: {skb->data[0], vlan_push} x 68 + {skb->data[0], vlan_pop} x 68 */
+	/* test: {skb->data[0], vlan_push} x 51 + {skb->data[0], vlan_pop} x 51 */
 #define PUSH_CNT 51
-	unsigned int len = BPF_MAXINSNS;
-	struct bpf_insn *insn = self->insns;
+	/* jump range is limited to 16 bit. PUSH_CNT of ld_abs needs room */
+	unsigned int len = (1 << 15) - PUSH_CNT * 2 * 5 * 6;
+	struct bpf_insn *insn = self->fill_insns;
 	int i = 0, j, k = 0;
 
 	insn[i++] = BPF_MOV64_REG(BPF_REG_6, BPF_REG_1);
@@ -156,12 +160,14 @@ loop:
 	for (; i < len - 1; i++)
 		insn[i] = BPF_ALU32_IMM(BPF_MOV, BPF_REG_0, 0xbef);
 	insn[len - 1] = BPF_EXIT_INSN();
+	self->prog_len = len;
 }
 
 static void bpf_fill_jump_around_ld_abs(struct bpf_test *self)
 {
-	struct bpf_insn *insn = self->insns;
-	unsigned int len = BPF_MAXINSNS;
+	struct bpf_insn *insn = self->fill_insns;
+	/* jump range is limited to 16 bit. every ld_abs is replaced by 6 insns */
+	unsigned int len = (1 << 15) / 6;
 	int i = 0;
 
 	insn[i++] = BPF_MOV64_REG(BPF_REG_6, BPF_REG_1);
@@ -171,11 +177,12 @@ static void bpf_fill_jump_around_ld_abs(struct bpf_test *self)
 	while (i < len - 1)
 		insn[i++] = BPF_LD_ABS(BPF_B, 1);
 	insn[i] = BPF_EXIT_INSN();
+	self->prog_len = i + 1;
 }
 
 static void bpf_fill_rand_ld_dw(struct bpf_test *self)
 {
-	struct bpf_insn *insn = self->insns;
+	struct bpf_insn *insn = self->fill_insns;
 	uint64_t res = 0;
 	int i = 0;
 
@@ -193,6 +200,7 @@ static void bpf_fill_rand_ld_dw(struct bpf_test *self)
 	insn[i++] = BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 32);
 	insn[i++] = BPF_ALU64_REG(BPF_XOR, BPF_REG_0, BPF_REG_1);
 	insn[i] = BPF_EXIT_INSN();
+	self->prog_len = i + 1;
 	res ^= (res >> 32);
 	self->retval = (uint32_t)res;
 }
@@ -520,8 +528,10 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type,
 	int *fixup_percpu_cgroup_storage = test->fixup_percpu_cgroup_storage;
 	int *fixup_map_spin_lock = test->fixup_map_spin_lock;
 
-	if (test->fill_helper)
+	if (test->fill_helper) {
+		test->fill_insns = calloc(MAX_TEST_INSNS, sizeof(struct bpf_insn));
 		test->fill_helper(test);
+	}
 
 	/* Allocating HTs with 1 elem is fine here, since we only test
 	 * for verifier and not do a runtime lookup, so the only thing
@@ -718,12 +728,17 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 		prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
 	fixup_skips = skips;
 	do_test_fixup(test, prog_type, prog, map_fds);
+	if (test->fill_insns) {
+		prog = test->fill_insns;
+		prog_len = test->prog_len;
+	} else {
+		prog_len = probe_filter_length(prog);
+	}
 	/* If there were some map skips during fixup due to missing bpf
 	 * features, skip this test.
 	 */
 	if (fixup_skips != skips)
 		return;
-	prog_len = probe_filter_length(prog);
 
 	pflags = 0;
 	if (test->flags & F_LOAD_WITH_STRICT_ALIGNMENT)
@@ -731,7 +746,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 	if (test->flags & F_NEEDS_EFFICIENT_UNALIGNED_ACCESS)
 		pflags |= BPF_F_ANY_ALIGNMENT;
 	fd_prog = bpf_verify_program(prog_type, prog, prog_len, pflags,
-				     "GPL", 0, bpf_vlog, sizeof(bpf_vlog), 1);
+				     "GPL", 0, bpf_vlog, sizeof(bpf_vlog), 4);
 	if (fd_prog < 0 && !bpf_probe_prog_type(prog_type, 0)) {
 		printf("SKIP (unsupported program type %d)\n", prog_type);
 		skips++;
@@ -830,6 +845,8 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 		goto fail_log;
 	}
 close_fds:
+	if (test->fill_insns)
+		free(test->fill_insns);
 	close(fd_prog);
 	for (i = 0; i < MAX_NR_MAPS; i++)
 		close(map_fds[i]);
diff --git a/tools/testing/selftests/bpf/verifier/ld_dw.c b/tools/testing/selftests/bpf/verifier/ld_dw.c
index d2c75b889598..0f18e62f0099 100644
--- a/tools/testing/selftests/bpf/verifier/ld_dw.c
+++ b/tools/testing/selftests/bpf/verifier/ld_dw.c
@@ -34,3 +34,12 @@
 	.result = ACCEPT,
 	.retval = 5,
 },
+{
+	"ld_dw: xor semi-random 64 bit imms, test 5",
+	.insns = { },
+	.data = { },
+	.fill_helper = bpf_fill_rand_ld_dw,
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	.result = ACCEPT,
+	.retval = 1000000 - 6,
+},