Merge branch 'move-ld_abs-to-native-BPF'

Daniel Borkmann says:

====================
This set simplifies BPF JITs significantly by moving ld_abs/ld_ind
to native BPF, for details see individual patches. Main rationale
is in patch 'implement ld_abs/ld_ind in native bpf'. Thanks!

v1 -> v2:
  - Added missing seen_lds_abs in LDX_MSH and use X = A
    initially due to being preserved on func call.
  - Added a large batch of cBPF tests into test_bpf.
  - Added x32 removal of LD_ABS/LD_IND, so all JITs are
    covered.
====================

Signed-off-by: Alexei Starovoitov <[email protected]>

2 files changed, 291 insertions, 8 deletions

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 8daef7326bb7..83a95ae388dd 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1801,6 +1801,30 @@ union bpf_attr {
  * 	Return
  * 		a non-negative value equal to or less than size on success, or
  * 		a negative error in case of failure.
+ *
+ * int skb_load_bytes_relative(const struct sk_buff *skb, u32 offset, void *to, u32 len, u32 start_header)
+ * 	Description
+ * 		This helper is similar to **bpf_skb_load_bytes**\ () in that
+ * 		it provides an easy way to load *len* bytes from *offset*
+ * 		from the packet associated to *skb*, into the buffer pointed
+ * 		by *to*. The difference to **bpf_skb_load_bytes**\ () is that
+ * 		a fifth argument *start_header* exists in order to select a
+ * 		base offset to start from. *start_header* can be one of:
+ *
+ * 		**BPF_HDR_START_MAC**
+ * 			Base offset to load data from is *skb*'s mac header.
+ * 		**BPF_HDR_START_NET**
+ * 			Base offset to load data from is *skb*'s network header.
+ *
+ * 		In general, "direct packet access" is the preferred method to
+ * 		access packet data, however, this helper is in particular useful
+ * 		in socket filters where *skb*\ **->data** does not always point
+ * 		to the start of the mac header and where "direct packet access"
+ * 		is not available.
+ *
+ * 	Return
+ * 		0 on success, or a negative error in case of failure.
+ *
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -1870,7 +1894,8 @@ union bpf_attr {
 	FN(bind),			\
 	FN(xdp_adjust_tail),		\
 	FN(skb_get_xfrm_state),		\
-	FN(get_stack),
+	FN(get_stack),			\
+	FN(skb_load_bytes_relative),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -1931,6 +1956,12 @@ enum bpf_adj_room_mode {
 	BPF_ADJ_ROOM_NET,
 };
 
+/* Mode for BPF_FUNC_skb_load_bytes_relative helper. */
+enum bpf_hdr_start_off {
+	BPF_HDR_START_MAC,
+	BPF_HDR_START_NET,
+};
+
 /* user accessible mirror of in-kernel sk_buff.
  * new fields can only be added to the end of this structure
  */
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 1acafe26498b..275b4570b5b8 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -47,7 +47,7 @@
 # define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
 #endif
 
-#define MAX_INSNS	512
+#define MAX_INSNS	BPF_MAXINSNS
 #define MAX_FIXUPS	8
 #define MAX_NR_MAPS	4
 #define POINTER_VALUE	0xcafe4all
@@ -77,6 +77,8 @@ struct bpf_test {
 	} result, result_unpriv;
 	enum bpf_prog_type prog_type;
 	uint8_t flags;
+	__u8 data[TEST_DATA_LEN];
+	void (*fill_helper)(struct bpf_test *self);
 };
 
 /* Note we want this to be 64 bit aligned so that the end of our array is
@@ -94,6 +96,62 @@ struct other_val {
 	long long bar;
 };
 
+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 */
+#define PUSH_CNT 51
+	unsigned int len = BPF_MAXINSNS;
+	struct bpf_insn *insn = self->insns;
+	int i = 0, j, k = 0;
+
+	insn[i++] = BPF_MOV64_REG(BPF_REG_6, BPF_REG_1);
+loop:
+	for (j = 0; j < PUSH_CNT; j++) {
+		insn[i++] = BPF_LD_ABS(BPF_B, 0);
+		insn[i] = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0x34, len - i - 2);
+		i++;
+		insn[i++] = BPF_MOV64_REG(BPF_REG_1, BPF_REG_6);
+		insn[i++] = BPF_MOV64_IMM(BPF_REG_2, 1);
+		insn[i++] = BPF_MOV64_IMM(BPF_REG_3, 2);
+		insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+					 BPF_FUNC_skb_vlan_push),
+		insn[i] = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, len - i - 2);
+		i++;
+	}
+
+	for (j = 0; j < PUSH_CNT; j++) {
+		insn[i++] = BPF_LD_ABS(BPF_B, 0);
+		insn[i] = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0x34, len - i - 2);
+		i++;
+		insn[i++] = BPF_MOV64_REG(BPF_REG_1, BPF_REG_6);
+		insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+					 BPF_FUNC_skb_vlan_pop),
+		insn[i] = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, len - i - 2);
+		i++;
+	}
+	if (++k < 5)
+		goto loop;
+
+	for (; i < len - 1; i++)
+		insn[i] = BPF_ALU32_IMM(BPF_MOV, BPF_REG_0, 0xbef);
+	insn[len - 1] = BPF_EXIT_INSN();
+}
+
+static void bpf_fill_jump_around_ld_abs(struct bpf_test *self)
+{
+	struct bpf_insn *insn = self->insns;
+	unsigned int len = BPF_MAXINSNS;
+	int i = 0;
+
+	insn[i++] = BPF_MOV64_REG(BPF_REG_6, BPF_REG_1);
+	insn[i++] = BPF_LD_ABS(BPF_B, 0);
+	insn[i] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 10, len - i - 2);
+	i++;
+	while (i < len - 1)
+		insn[i++] = BPF_LD_ABS(BPF_B, 1);
+	insn[i] = BPF_EXIT_INSN();
+}
+
 static struct bpf_test tests[] = {
 	{
 		"add+sub+mul",
@@ -11725,6 +11783,197 @@ static struct bpf_test tests[] = {
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
+	{
+		"ld_abs: invalid op 1",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_LD_ABS(BPF_DW, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = REJECT,
+		.errstr = "unknown opcode",
+	},
+	{
+		"ld_abs: invalid op 2",
+		.insns = {
+			BPF_MOV32_IMM(BPF_REG_0, 256),
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_LD_IND(BPF_DW, BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = REJECT,
+		.errstr = "unknown opcode",
+	},
+	{
+		"ld_abs: nmap reduced",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_LD_ABS(BPF_H, 12),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0x806, 28),
+			BPF_LD_ABS(BPF_H, 12),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0x806, 26),
+			BPF_MOV32_IMM(BPF_REG_0, 18),
+			BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -64),
+			BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_10, -64),
+			BPF_LD_IND(BPF_W, BPF_REG_7, 14),
+			BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -60),
+			BPF_MOV32_IMM(BPF_REG_0, 280971478),
+			BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -56),
+			BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_10, -56),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_10, -60),
+			BPF_ALU32_REG(BPF_SUB, BPF_REG_0, BPF_REG_7),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 15),
+			BPF_LD_ABS(BPF_H, 12),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0x806, 13),
+			BPF_MOV32_IMM(BPF_REG_0, 22),
+			BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -56),
+			BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_10, -56),
+			BPF_LD_IND(BPF_H, BPF_REG_7, 14),
+			BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -52),
+			BPF_MOV32_IMM(BPF_REG_0, 17366),
+			BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -48),
+			BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_10, -48),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_10, -52),
+			BPF_ALU32_REG(BPF_SUB, BPF_REG_0, BPF_REG_7),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+			BPF_MOV32_IMM(BPF_REG_0, 256),
+			BPF_EXIT_INSN(),
+			BPF_MOV32_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.data = {
+			0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x08, 0x06, 0,
+			0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+			0x10, 0xbf, 0x48, 0xd6, 0x43, 0xd6,
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 256,
+	},
+	{
+		"ld_abs: div + abs, test 1",
+		.insns = {
+			BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_1),
+			BPF_LD_ABS(BPF_B, 3),
+			BPF_ALU64_IMM(BPF_MOV, BPF_REG_2, 2),
+			BPF_ALU32_REG(BPF_DIV, BPF_REG_0, BPF_REG_2),
+			BPF_ALU64_REG(BPF_MOV, BPF_REG_8, BPF_REG_0),
+			BPF_LD_ABS(BPF_B, 4),
+			BPF_ALU64_REG(BPF_ADD, BPF_REG_8, BPF_REG_0),
+			BPF_LD_IND(BPF_B, BPF_REG_8, -70),
+			BPF_EXIT_INSN(),
+		},
+		.data = {
+			10, 20, 30, 40, 50,
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 10,
+	},
+	{
+		"ld_abs: div + abs, test 2",
+		.insns = {
+			BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_1),
+			BPF_LD_ABS(BPF_B, 3),
+			BPF_ALU64_IMM(BPF_MOV, BPF_REG_2, 2),
+			BPF_ALU32_REG(BPF_DIV, BPF_REG_0, BPF_REG_2),
+			BPF_ALU64_REG(BPF_MOV, BPF_REG_8, BPF_REG_0),
+			BPF_LD_ABS(BPF_B, 128),
+			BPF_ALU64_REG(BPF_ADD, BPF_REG_8, BPF_REG_0),
+			BPF_LD_IND(BPF_B, BPF_REG_8, -70),
+			BPF_EXIT_INSN(),
+		},
+		.data = {
+			10, 20, 30, 40, 50,
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 0,
+	},
+	{
+		"ld_abs: div + abs, test 3",
+		.insns = {
+			BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_1),
+			BPF_ALU64_IMM(BPF_MOV, BPF_REG_7, 0),
+			BPF_LD_ABS(BPF_B, 3),
+			BPF_ALU32_REG(BPF_DIV, BPF_REG_0, BPF_REG_7),
+			BPF_EXIT_INSN(),
+		},
+		.data = {
+			10, 20, 30, 40, 50,
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 0,
+	},
+	{
+		"ld_abs: div + abs, test 4",
+		.insns = {
+			BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_1),
+			BPF_ALU64_IMM(BPF_MOV, BPF_REG_7, 0),
+			BPF_LD_ABS(BPF_B, 256),
+			BPF_ALU32_REG(BPF_DIV, BPF_REG_0, BPF_REG_7),
+			BPF_EXIT_INSN(),
+		},
+		.data = {
+			10, 20, 30, 40, 50,
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 0,
+	},
+	{
+		"ld_abs: vlan + abs, test 1",
+		.insns = { },
+		.data = {
+			0x34,
+		},
+		.fill_helper = bpf_fill_ld_abs_vlan_push_pop,
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 0xbef,
+	},
+	{
+		"ld_abs: vlan + abs, test 2",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_LD_ABS(BPF_B, 0),
+			BPF_LD_ABS(BPF_H, 0),
+			BPF_LD_ABS(BPF_W, 0),
+			BPF_MOV64_REG(BPF_REG_7, BPF_REG_6),
+			BPF_MOV64_IMM(BPF_REG_6, 0),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+			BPF_MOV64_IMM(BPF_REG_2, 1),
+			BPF_MOV64_IMM(BPF_REG_3, 2),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_skb_vlan_push),
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_7),
+			BPF_LD_ABS(BPF_B, 0),
+			BPF_LD_ABS(BPF_H, 0),
+			BPF_LD_ABS(BPF_W, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 42),
+			BPF_EXIT_INSN(),
+		},
+		.data = {
+			0x34,
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 42,
+	},
+	{
+		"ld_abs: jump around ld_abs",
+		.insns = { },
+		.data = {
+			10, 11,
+		},
+		.fill_helper = bpf_fill_jump_around_ld_abs,
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 10,
+	},
 };
 
 static int probe_filter_length(const struct bpf_insn *fp)
@@ -11828,7 +12077,7 @@ static int create_map_in_map(void)
 	return outer_map_fd;
 }
 
-static char bpf_vlog[32768];
+static char bpf_vlog[UINT_MAX >> 8];
 
 static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog,
 			  int *map_fds)
@@ -11839,6 +12088,9 @@ static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog,
 	int *fixup_prog = test->fixup_prog;
 	int *fixup_map_in_map = test->fixup_map_in_map;
 
+	if (test->fill_helper)
+		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
 	 * that really matters is value size in this case.
@@ -11888,10 +12140,8 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 			   int *passes, int *errors)
 {
 	int fd_prog, expected_ret, reject_from_alignment;
+	int prog_len, prog_type = test->prog_type;
 	struct bpf_insn *prog = test->insns;
-	int prog_len = probe_filter_length(prog);
-	char data_in[TEST_DATA_LEN] = {};
-	int prog_type = test->prog_type;
 	int map_fds[MAX_NR_MAPS];
 	const char *expected_err;
 	uint32_t retval;
@@ -11901,6 +12151,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 		map_fds[i] = -1;
 
 	do_test_fixup(test, prog, map_fds);
+	prog_len = probe_filter_length(prog);
 
 	fd_prog = bpf_verify_program(prog_type ? : BPF_PROG_TYPE_SOCKET_FILTER,
 				     prog, prog_len, test->flags & F_LOAD_WITH_STRICT_ALIGNMENT,
@@ -11940,8 +12191,9 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 	}
 
 	if (fd_prog >= 0) {
-		err = bpf_prog_test_run(fd_prog, 1, data_in, sizeof(data_in),
-					NULL, NULL, &retval, NULL);
+		err = bpf_prog_test_run(fd_prog, 1, test->data,
+					sizeof(test->data), NULL, NULL,
+					&retval, NULL);
 		if (err && errno != 524/*ENOTSUPP*/ && errno != EPERM) {
 			printf("Unexpected bpf_prog_test_run error\n");
 			goto fail_log;