Merge branch 'bpf-improve-verifier-ARG_CONST_SIZE_OR_ZERO-semantics'

Yonghong Song says:

====================
bpf: improve verifier ARG_CONST_SIZE_OR_ZERO semantics

This patch set intends to change verifier ARG_CONST_SIZE_OR_ZERO
semantics so that simpler bpf programs can be written with verifier
acceptance. Patch #1 comment provided the detailed examples and
the patch itself implements the new semantics. Patch #2
changes bpf_probe_read helper arg2 type from
ARG_CONST_SIZE to ARG_CONST_SIZE_OR_ZERO. Patch #3 fixed a few
test cases and added some for better coverage.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

kernel/bpf/verifier.c

@@ -799,12 +799,13 @@ static int check_stack_read(struct bpf_verifier_env *env,
 
 /* check read/write into map element returned by bpf_map_lookup_elem() */
 static int __check_map_access(struct bpf_verifier_env *env, u32 regno, int off,
-			    int size)
+			      int size, bool zero_size_allowed)
 {
 	struct bpf_reg_state *regs = cur_regs(env);
 	struct bpf_map *map = regs[regno].map_ptr;
 
-	if (off < 0 || size <= 0 || off + size > map->value_size) {
+	if (off < 0 || size < 0 || (size == 0 && !zero_size_allowed) ||
+	    off + size > map->value_size) {
 		verbose(env, "invalid access to map value, value_size=%d off=%d size=%d\n",
 			map->value_size, off, size);
 		return -EACCES;
@@ -814,7 +815,7 @@ static int __check_map_access(struct bpf_verifier_env *env, u32 regno, int off,
 
 /* check read/write into a map element with possible variable offset */
 static int check_map_access(struct bpf_verifier_env *env, u32 regno,
-			    int off, int size)
+			    int off, int size, bool zero_size_allowed)
 {
 	struct bpf_verifier_state *state = env->cur_state;
 	struct bpf_reg_state *reg = &state->regs[regno];
@@ -837,7 +838,8 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno,
 			regno);
 		return -EACCES;
 	}
-	err = __check_map_access(env, regno, reg->smin_value + off, size);
+	err = __check_map_access(env, regno, reg->smin_value + off, size,
+				 zero_size_allowed);
 	if (err) {
 		verbose(env, "R%d min value is outside of the array range\n",
 			regno);
@@ -853,7 +855,8 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno,
 			regno);
 		return -EACCES;
 	}
-	err = __check_map_access(env, regno, reg->umax_value + off, size);
+	err = __check_map_access(env, regno, reg->umax_value + off, size,
+				 zero_size_allowed);
 	if (err)
 		verbose(env, "R%d max value is outside of the array range\n",
 			regno);
@@ -889,12 +892,13 @@ static bool may_access_direct_pkt_data(struct bpf_verifier_env *env,
 }
 
 static int __check_packet_access(struct bpf_verifier_env *env, u32 regno,
-				 int off, int size)
+				 int off, int size, bool zero_size_allowed)
 {
 	struct bpf_reg_state *regs = cur_regs(env);
 	struct bpf_reg_state *reg = &regs[regno];
 
-	if (off < 0 || size <= 0 || (u64)off + size > reg->range) {
+	if (off < 0 || size < 0 || (size == 0 && !zero_size_allowed) ||
+	    (u64)off + size > reg->range) {
 		verbose(env, "invalid access to packet, off=%d size=%d, R%d(id=%d,off=%d,r=%d)\n",
 			off, size, regno, reg->id, reg->off, reg->range);
 		return -EACCES;
@@ -903,7 +907,7 @@ static int __check_packet_access(struct bpf_verifier_env *env, u32 regno,
 }
 
 static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off,
-			       int size)
+			       int size, bool zero_size_allowed)
 {
 	struct bpf_reg_state *regs = cur_regs(env);
 	struct bpf_reg_state *reg = &regs[regno];
@@ -922,7 +926,7 @@ static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off,
 			regno);
 		return -EACCES;
 	}
-	err = __check_packet_access(env, regno, off, size);
+	err = __check_packet_access(env, regno, off, size, zero_size_allowed);
 	if (err) {
 		verbose(env, "R%d offset is outside of the packet\n", regno);
 		return err;
@@ -1097,7 +1101,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 			return -EACCES;
 		}
 
-		err = check_map_access(env, regno, off, size);
+		err = check_map_access(env, regno, off, size, false);
 		if (!err && t == BPF_READ && value_regno >= 0)
 			mark_reg_unknown(env, regs, value_regno);
 
@@ -1184,7 +1188,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 				value_regno);
 			return -EACCES;
 		}
-		err = check_packet_access(env, regno, off, size);
+		err = check_packet_access(env, regno, off, size, false);
 		if (!err && t == BPF_READ && value_regno >= 0)
 			mark_reg_unknown(env, regs, value_regno);
 	} else {
@@ -1281,7 +1285,7 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
 	}
 	off = regs[regno].off + regs[regno].var_off.value;
 	if (off >= 0 || off < -MAX_BPF_STACK || off + access_size > 0 ||
-	    access_size <= 0) {
+	    access_size < 0 || (access_size == 0 && !zero_size_allowed)) {
 		verbose(env, "invalid stack type R%d off=%d access_size=%d\n",
 			regno, off, access_size);
 		return -EACCES;
@@ -1319,9 +1323,11 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
 	switch (reg->type) {
 	case PTR_TO_PACKET:
 	case PTR_TO_PACKET_META:
-		return check_packet_access(env, regno, reg->off, access_size);
+		return check_packet_access(env, regno, reg->off, access_size,
+					   zero_size_allowed);
 	case PTR_TO_MAP_VALUE:
-		return check_map_access(env, regno, reg->off, access_size);
+		return check_map_access(env, regno, reg->off, access_size,
+					zero_size_allowed);
 	default: /* scalar_value|ptr_to_stack or invalid ptr */
 		return check_stack_boundary(env, regno, access_size,
 					    zero_size_allowed, meta);
@@ -1415,7 +1421,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 		}
 		if (type_is_pkt_pointer(type))
 			err = check_packet_access(env, regno, reg->off,
-						  meta->map_ptr->key_size);
+						  meta->map_ptr->key_size,
+						  false);
 		else
 			err = check_stack_boundary(env, regno,
 						   meta->map_ptr->key_size,
@@ -1431,7 +1438,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 		}
 		if (type_is_pkt_pointer(type))
 			err = check_packet_access(env, regno, reg->off,
-						  meta->map_ptr->value_size);
+						  meta->map_ptr->value_size,
+						  false);
 		else
 			err = check_stack_boundary(env, regno,
 						   meta->map_ptr->value_size,

kernel/trace/bpf_trace.c

@@ -78,12 +78,16 @@ EXPORT_SYMBOL_GPL(trace_call_bpf);
 
 BPF_CALL_3(bpf_probe_read, void *, dst, u32, size, const void *, unsafe_ptr)
 {
-	int ret;
+	int ret = 0;
+
+	if (unlikely(size == 0))
+		goto out;
 
 	ret = probe_kernel_read(dst, unsafe_ptr, size);
 	if (unlikely(ret < 0))
 		memset(dst, 0, size);
 
+ out:
 	return ret;
 }
 
@@ -92,7 +96,7 @@ static const struct bpf_func_proto bpf_probe_read_proto = {
 	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_UNINIT_MEM,
-	.arg2_type	= ARG_CONST_SIZE,
+	.arg2_type	= ARG_CONST_SIZE_OR_ZERO,
 	.arg3_type	= ARG_ANYTHING,
 };
 

tools/testing/selftests/bpf/test_verifier.c

@@ -3579,7 +3579,7 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
 	{
-		"helper access to packet: test19, cls helper fail range zero",
+		"helper access to packet: test19, cls helper range zero",
 		.insns = {
 			BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
 				    offsetof(struct __sk_buff, data)),
@@ -3599,8 +3599,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.result = REJECT,
-		.errstr = "invalid access to packet",
+		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
 	{
@@ -4379,10 +4378,10 @@ static struct bpf_test tests[] = {
 			BPF_LD_MAP_FD(BPF_REG_1, 0),
 			BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
 			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_MOV64_IMM(BPF_REG_1, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
 			BPF_MOV64_IMM(BPF_REG_3, 0),
-			BPF_EMIT_CALL(BPF_FUNC_probe_read),
+			BPF_EMIT_CALL(BPF_FUNC_probe_write_user),
 			BPF_EXIT_INSN(),
 		},
 		.fixup_map2 = { 3 },
@@ -4486,9 +4485,10 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1,
 				offsetof(struct test_val, foo)),
-			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_1),
+			BPF_MOV64_IMM(BPF_REG_1, 0),
 			BPF_MOV64_IMM(BPF_REG_3, 0),
-			BPF_EMIT_CALL(BPF_FUNC_probe_read),
+			BPF_EMIT_CALL(BPF_FUNC_probe_write_user),
 			BPF_EXIT_INSN(),
 		},
 		.fixup_map2 = { 3 },
@@ -4622,13 +4622,14 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
 			BPF_MOV64_IMM(BPF_REG_3, 0),
 			BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
-			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_1),
+			BPF_MOV64_IMM(BPF_REG_1, 0),
 			BPF_MOV64_IMM(BPF_REG_3, 0),
-			BPF_EMIT_CALL(BPF_FUNC_probe_read),
+			BPF_EMIT_CALL(BPF_FUNC_probe_write_user),
 			BPF_EXIT_INSN(),
 		},
 		.fixup_map2 = { 3 },
-		.errstr = "R1 min value is outside of the array range",
+		.errstr = "R2 min value is outside of the array range",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -4765,13 +4766,14 @@ static struct bpf_test tests[] = {
 			BPF_JMP_IMM(BPF_JGT, BPF_REG_3,
 				offsetof(struct test_val, foo), 4),
 			BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
-			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_1),
+			BPF_MOV64_IMM(BPF_REG_1, 0),
 			BPF_MOV64_IMM(BPF_REG_3, 0),
-			BPF_EMIT_CALL(BPF_FUNC_probe_read),
+			BPF_EMIT_CALL(BPF_FUNC_probe_write_user),
 			BPF_EXIT_INSN(),
 		},
 		.fixup_map2 = { 3 },
-		.errstr = "R1 min value is outside of the array range",
+		.errstr = "R2 min value is outside of the array range",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -5350,7 +5352,7 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_probe_read),
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "invalid stack type R1 off=-64 access_size=0",
+		.errstr = "invalid indirect read from stack off -64+0 size 64",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -5505,7 +5507,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "invalid stack type R1 off=-64 access_size=0",
+		.errstr = "invalid indirect read from stack off -64+0 size 64",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
@@ -5668,7 +5670,7 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
 	{
-		"helper access to variable memory: size = 0 not allowed on != NULL",
+		"helper access to variable memory: size = 0 allowed on != NULL stack pointer",
 		.insns = {
 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
@@ -5681,8 +5683,99 @@ static struct bpf_test tests[] = {
 			BPF_EMIT_CALL(BPF_FUNC_csum_diff),
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "invalid stack type R1 off=-8 access_size=0",
-		.result = REJECT,
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	},
+	{
+		"helper access to variable memory: size = 0 allowed on != NULL map pointer",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_MOV64_IMM(BPF_REG_3, 0),
+			BPF_MOV64_IMM(BPF_REG_4, 0),
+			BPF_MOV64_IMM(BPF_REG_5, 0),
+			BPF_EMIT_CALL(BPF_FUNC_csum_diff),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map1 = { 3 },
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	},
+	{
+		"helper access to variable memory: size possible = 0 allowed on != NULL stack pointer",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 0),
+			BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 8, 7),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
+			BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, 0),
+			BPF_MOV64_IMM(BPF_REG_3, 0),
+			BPF_MOV64_IMM(BPF_REG_4, 0),
+			BPF_MOV64_IMM(BPF_REG_5, 0),
+			BPF_EMIT_CALL(BPF_FUNC_csum_diff),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map1 = { 3 },
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	},
+	{
+		"helper access to variable memory: size possible = 0 allowed on != NULL map pointer",
+		.insns = {
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 0),
+			BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 8, 4),
+			BPF_MOV64_IMM(BPF_REG_3, 0),
+			BPF_MOV64_IMM(BPF_REG_4, 0),
+			BPF_MOV64_IMM(BPF_REG_5, 0),
+			BPF_EMIT_CALL(BPF_FUNC_csum_diff),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map1 = { 3 },
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	},
+	{
+		"helper access to variable memory: size possible = 0 allowed on != NULL packet pointer",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+				    offsetof(struct __sk_buff, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct __sk_buff, data_end)),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_6),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 7),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_6, 0),
+			BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 8, 4),
+			BPF_MOV64_IMM(BPF_REG_3, 0),
+			BPF_MOV64_IMM(BPF_REG_4, 0),
+			BPF_MOV64_IMM(BPF_REG_5, 0),
+			BPF_EMIT_CALL(BPF_FUNC_csum_diff),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	},
 	{