Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Alexei Starovoitov says: ==================== pull-request: bpf-next 2020-09-23 The following pull-request contains BPF updates for your *net-next* tree. We've added 95 non-merge commits during the last 22 day(s) which contain a total of 124 files changed, 4211 insertions(+), 2040 deletions(-). The main changes are: 1) Full multi function support in libbpf, from Andrii. 2) Refactoring of function argument checks, from Lorenz. 3) Make bpf_tail_call compatible with functions (subprograms), from Maciej. 4) Program metadata support, from YiFei. 5) bpf iterator optimizations, from Yonghong. ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
2020-09-23 13:11:11 -07:00
parent 1a26e88d53 dc3652d3f0
commit 6d772f328d
124 changed files with 4217 additions and 2046 deletions
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -238,7 +238,6 @@ struct bpf_call_arg_meta {
 	u64 msize_max_value;
 	int ref_obj_id;
 	int func_id;
-	u32 btf_id;
 };

 struct btf *btf_vmlinux;
@@ -436,6 +435,15 @@ static bool arg_type_may_be_refcounted(enum bpf_arg_type type)
 	return type == ARG_PTR_TO_SOCK_COMMON;
 }

+static bool arg_type_may_be_null(enum bpf_arg_type type)
+{
+	return type == ARG_PTR_TO_MAP_VALUE_OR_NULL ||
+	       type == ARG_PTR_TO_MEM_OR_NULL ||
+	       type == ARG_PTR_TO_CTX_OR_NULL ||
+	       type == ARG_PTR_TO_SOCKET_OR_NULL ||
+	       type == ARG_PTR_TO_ALLOC_MEM_OR_NULL;
+}
+
 /* Determine whether the function releases some resources allocated by another
 * function call. The first reference type argument will be assumed to be
 * released by release_reference().
@@ -1490,6 +1498,13 @@ static int check_subprogs(struct bpf_verifier_env *env)
 	for (i = 0; i < insn_cnt; i++) {
 		u8 code = insn[i].code;

+		if (code == (BPF_JMP | BPF_CALL) &&
+		    insn[i].imm == BPF_FUNC_tail_call &&
+		    insn[i].src_reg != BPF_PSEUDO_CALL)
+			subprog[cur_subprog].has_tail_call = true;
+		if (BPF_CLASS(code) == BPF_LD &&
+		    (BPF_MODE(code) == BPF_ABS || BPF_MODE(code) == BPF_IND))
+			subprog[cur_subprog].has_ld_abs = true;
 		if (BPF_CLASS(code) != BPF_JMP && BPF_CLASS(code) != BPF_JMP32)
 			goto next;
 		if (BPF_OP(code) == BPF_EXIT || BPF_OP(code) == BPF_CALL)
@@ -2979,10 +2994,37 @@ static int check_max_stack_depth(struct bpf_verifier_env *env)
 	int depth = 0, frame = 0, idx = 0, i = 0, subprog_end;
 	struct bpf_subprog_info *subprog = env->subprog_info;
 	struct bpf_insn *insn = env->prog->insnsi;
+	bool tail_call_reachable = false;
 	int ret_insn[MAX_CALL_FRAMES];
 	int ret_prog[MAX_CALL_FRAMES];
+	int j;

 process_func:
+	/* protect against potential stack overflow that might happen when
+	 * bpf2bpf calls get combined with tailcalls. Limit the caller's stack
+	 * depth for such case down to 256 so that the worst case scenario
+	 * would result in 8k stack size (32 which is tailcall limit * 256 =
+	 * 8k).
+	 *
+	 * To get the idea what might happen, see an example:
+	 * func1 -> sub rsp, 128
+	 *  subfunc1 -> sub rsp, 256
+	 *  tailcall1 -> add rsp, 256
+	 *   func2 -> sub rsp, 192 (total stack size = 128 + 192 = 320)
+	 *   subfunc2 -> sub rsp, 64
+	 *   subfunc22 -> sub rsp, 128
+	 *   tailcall2 -> add rsp, 128
+	 *    func3 -> sub rsp, 32 (total stack size 128 + 192 + 64 + 32 = 416)
+	 *
+	 * tailcall will unwind the current stack frame but it will not get rid
+	 * of caller's stack as shown on the example above.
+	 */
+	if (idx && subprog[idx].has_tail_call && depth >= 256) {
+		verbose(env,
+			"tail_calls are not allowed when call stack of previous frames is %d bytes. Too large\n",
+			depth);
+		return -EACCES;
+	}
 	/* round up to 32-bytes, since this is granularity
 	 * of interpreter stack size
 	 */
@@ -3011,6 +3053,10 @@ continue_func:
 				  i);
 			return -EFAULT;
 		}
+
+		if (subprog[idx].has_tail_call)
+			tail_call_reachable = true;
+
 		frame++;
 		if (frame >= MAX_CALL_FRAMES) {
 			verbose(env, "the call stack of %d frames is too deep !\n",
@@ -3019,6 +3065,15 @@ continue_func:
 		}
 		goto process_func;
 	}
+	/* if tail call got detected across bpf2bpf calls then mark each of the
+	 * currently present subprog frames as tail call reachable subprogs;
+	 * this info will be utilized by JIT so that we will be preserving the
+	 * tail call counter throughout bpf2bpf calls combined with tailcalls
+	 */
+	if (tail_call_reachable)
+		for (j = 0; j < frame; j++)
+			subprog[ret_prog[j]].tail_call_reachable = true;
+
 	/* end of for() loop means the last insn of the 'subprog'
 	 * was reached. Doesn't matter whether it was JA or EXIT
 	 */
@@ -3594,18 +3649,6 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
 	struct bpf_func_state *state = func(env, reg);
 	int err, min_off, max_off, i, j, slot, spi;

-	if (reg->type != PTR_TO_STACK) {
-		/* Allow zero-byte read from NULL, regardless of pointer type */
-		if (zero_size_allowed && access_size == 0 &&
-		    register_is_null(reg))
-			return 0;
-
-		verbose(env, "R%d type=%s expected=%s\n", regno,
-			reg_type_str[reg->type],
-			reg_type_str[PTR_TO_STACK]);
-		return -EACCES;
-	}
-
 	if (tnum_is_const(reg->var_off)) {
 		min_off = max_off = reg->var_off.value + reg->off;
 		err = __check_stack_boundary(env, regno, min_off, access_size,
@@ -3750,9 +3793,19 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
 					   access_size, zero_size_allowed,
 					   "rdwr",
 					   &env->prog->aux->max_rdwr_access);
-	default: /* scalar_value|ptr_to_stack or invalid ptr */
+	case PTR_TO_STACK:
 		return check_stack_boundary(env, regno, access_size,
 					    zero_size_allowed, meta);
+	default: /* scalar_value or invalid ptr */
+		/* Allow zero-byte read from NULL, regardless of pointer type */
+		if (zero_size_allowed && access_size == 0 &&
+		    register_is_null(reg))
+			return 0;
+
+		verbose(env, "R%d type=%s expected=%s\n", regno,
+			reg_type_str[reg->type],
+			reg_type_str[PTR_TO_STACK]);
+		return -EACCES;
 	}
 }

@@ -3784,10 +3837,6 @@ static int process_spin_lock(struct bpf_verifier_env *env, int regno,
 	struct bpf_map *map = reg->map_ptr;
 	u64 val = reg->var_off.value;

-	if (reg->type != PTR_TO_MAP_VALUE) {
-		verbose(env, "R%d is not a pointer to map_value\n", regno);
-		return -EINVAL;
-	}
 	if (!is_const) {
 		verbose(env,
 			"R%d doesn't have constant offset. bpf_spin_lock has to be at the constant offset\n",
@@ -3854,12 +3903,6 @@ static bool arg_type_is_mem_size(enum bpf_arg_type type)
 	       type == ARG_CONST_SIZE_OR_ZERO;
 }

-static bool arg_type_is_alloc_mem_ptr(enum bpf_arg_type type)
-{
-	return type == ARG_PTR_TO_ALLOC_MEM ||
-	       type == ARG_PTR_TO_ALLOC_MEM_OR_NULL;
-}
-
 static bool arg_type_is_alloc_size(enum bpf_arg_type type)
 {
 	return type == ARG_CONST_ALLOC_SIZE_OR_ZERO;
@@ -3908,14 +3951,114 @@ static int resolve_map_arg_type(struct bpf_verifier_env *env,
 	return 0;
 }

+struct bpf_reg_types {
+	const enum bpf_reg_type types[10];
+};
+
+static const struct bpf_reg_types map_key_value_types = {
+	.types = {
+		PTR_TO_STACK,
+		PTR_TO_PACKET,
+		PTR_TO_PACKET_META,
+		PTR_TO_MAP_VALUE,
+	},
+};
+
+static const struct bpf_reg_types sock_types = {
+	.types = {
+		PTR_TO_SOCK_COMMON,
+		PTR_TO_SOCKET,
+		PTR_TO_TCP_SOCK,
+		PTR_TO_XDP_SOCK,
+	},
+};
+
+static const struct bpf_reg_types mem_types = {
+	.types = {
+		PTR_TO_STACK,
+		PTR_TO_PACKET,
+		PTR_TO_PACKET_META,
+		PTR_TO_MAP_VALUE,
+		PTR_TO_MEM,
+		PTR_TO_RDONLY_BUF,
+		PTR_TO_RDWR_BUF,
+	},
+};
+
+static const struct bpf_reg_types int_ptr_types = {
+	.types = {
+		PTR_TO_STACK,
+		PTR_TO_PACKET,
+		PTR_TO_PACKET_META,
+		PTR_TO_MAP_VALUE,
+	},
+};
+
+static const struct bpf_reg_types fullsock_types = { .types = { PTR_TO_SOCKET } };
+static const struct bpf_reg_types scalar_types = { .types = { SCALAR_VALUE } };
+static const struct bpf_reg_types context_types = { .types = { PTR_TO_CTX } };
+static const struct bpf_reg_types alloc_mem_types = { .types = { PTR_TO_MEM } };
+static const struct bpf_reg_types const_map_ptr_types = { .types = { CONST_PTR_TO_MAP } };
+static const struct bpf_reg_types btf_ptr_types = { .types = { PTR_TO_BTF_ID } };
+static const struct bpf_reg_types spin_lock_types = { .types = { PTR_TO_MAP_VALUE } };
+
+static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = {
+	[ARG_PTR_TO_MAP_KEY]		= &map_key_value_types,
+	[ARG_PTR_TO_MAP_VALUE]		= &map_key_value_types,
+	[ARG_PTR_TO_UNINIT_MAP_VALUE]	= &map_key_value_types,
+	[ARG_PTR_TO_MAP_VALUE_OR_NULL]	= &map_key_value_types,
+	[ARG_CONST_SIZE]		= &scalar_types,
+	[ARG_CONST_SIZE_OR_ZERO]	= &scalar_types,
+	[ARG_CONST_ALLOC_SIZE_OR_ZERO]	= &scalar_types,
+	[ARG_CONST_MAP_PTR]		= &const_map_ptr_types,
+	[ARG_PTR_TO_CTX]		= &context_types,
+	[ARG_PTR_TO_CTX_OR_NULL]	= &context_types,
+	[ARG_PTR_TO_SOCK_COMMON]	= &sock_types,
+	[ARG_PTR_TO_SOCKET]		= &fullsock_types,
+	[ARG_PTR_TO_SOCKET_OR_NULL]	= &fullsock_types,
+	[ARG_PTR_TO_BTF_ID]		= &btf_ptr_types,
+	[ARG_PTR_TO_SPIN_LOCK]		= &spin_lock_types,
+	[ARG_PTR_TO_MEM]		= &mem_types,
+	[ARG_PTR_TO_MEM_OR_NULL]	= &mem_types,
+	[ARG_PTR_TO_UNINIT_MEM]		= &mem_types,
+	[ARG_PTR_TO_ALLOC_MEM]		= &alloc_mem_types,
+	[ARG_PTR_TO_ALLOC_MEM_OR_NULL]	= &alloc_mem_types,
+	[ARG_PTR_TO_INT]		= &int_ptr_types,
+	[ARG_PTR_TO_LONG]		= &int_ptr_types,
+};
+
+static int check_reg_type(struct bpf_verifier_env *env, u32 regno,
+			  const struct bpf_reg_types *compatible)
+{
+	struct bpf_reg_state *regs = cur_regs(env), *reg = &regs[regno];
+	enum bpf_reg_type expected, type = reg->type;
+	int i, j;
+
+	for (i = 0; i < ARRAY_SIZE(compatible->types); i++) {
+		expected = compatible->types[i];
+		if (expected == NOT_INIT)
+			break;
+
+		if (type == expected)
+			return 0;
+	}
+
+	verbose(env, "R%d type=%s expected=", regno, reg_type_str[type]);
+	for (j = 0; j + 1 < i; j++)
+		verbose(env, "%s, ", reg_type_str[compatible->types[j]]);
+	verbose(env, "%s\n", reg_type_str[compatible->types[j]]);
+	return -EACCES;
+}
+
 static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 			  struct bpf_call_arg_meta *meta,
 			  const struct bpf_func_proto *fn)
 {
 	u32 regno = BPF_REG_1 + arg;
 	struct bpf_reg_state *regs = cur_regs(env), *reg = &regs[regno];
-	enum bpf_reg_type expected_type, type = reg->type;
 	enum bpf_arg_type arg_type = fn->arg_type[arg];
+	const struct bpf_reg_types *compatible;
+	enum bpf_reg_type type = reg->type;
 	int err = 0;

 	if (arg_type == ARG_DONTCARE)
@@ -3948,125 +4091,48 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 			return err;
 	}

-	if (arg_type == ARG_PTR_TO_MAP_KEY ||
-	    arg_type == ARG_PTR_TO_MAP_VALUE ||
-	    arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE ||
-	    arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL) {
-		expected_type = PTR_TO_STACK;
-		if (register_is_null(reg) &&
-		    arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL)
-			/* final test in check_stack_boundary() */;
-		else if (!type_is_pkt_pointer(type) &&
-			 type != PTR_TO_MAP_VALUE &&
-			 type != expected_type)
-			goto err_type;
-	} else if (arg_type == ARG_CONST_SIZE ||
-		   arg_type == ARG_CONST_SIZE_OR_ZERO ||
-		   arg_type == ARG_CONST_ALLOC_SIZE_OR_ZERO) {
-		expected_type = SCALAR_VALUE;
-		if (type != expected_type)
-			goto err_type;
-	} else if (arg_type == ARG_CONST_MAP_PTR) {
-		expected_type = CONST_PTR_TO_MAP;
-		if (type != expected_type)
-			goto err_type;
-	} else if (arg_type == ARG_PTR_TO_CTX ||
-		   arg_type == ARG_PTR_TO_CTX_OR_NULL) {
-		expected_type = PTR_TO_CTX;
-		if (!(register_is_null(reg) &&
-		      arg_type == ARG_PTR_TO_CTX_OR_NULL)) {
-			if (type != expected_type)
-				goto err_type;
-			err = check_ctx_reg(env, reg, regno);
-			if (err < 0)
-				return err;
-		}
-	} else if (arg_type == ARG_PTR_TO_SOCK_COMMON) {
-		expected_type = PTR_TO_SOCK_COMMON;
-		/* Any sk pointer can be ARG_PTR_TO_SOCK_COMMON */
-		if (!type_is_sk_pointer(type))
-			goto err_type;
-		if (reg->ref_obj_id) {
-			if (meta->ref_obj_id) {
-				verbose(env, "verifier internal error: more than one arg with ref_obj_id R%d %u %u\n",
-					regno, reg->ref_obj_id,
-					meta->ref_obj_id);
-				return -EFAULT;
-			}
-			meta->ref_obj_id = reg->ref_obj_id;
-		}
-	} else if (arg_type == ARG_PTR_TO_SOCKET ||
-		   arg_type == ARG_PTR_TO_SOCKET_OR_NULL) {
-		expected_type = PTR_TO_SOCKET;
-		if (!(register_is_null(reg) &&
-		      arg_type == ARG_PTR_TO_SOCKET_OR_NULL)) {
-			if (type != expected_type)
-				goto err_type;
-		}
-	} else if (arg_type == ARG_PTR_TO_BTF_ID) {
-		bool ids_match = false;
+	if (register_is_null(reg) && arg_type_may_be_null(arg_type))
+		/* A NULL register has a SCALAR_VALUE type, so skip
+		 * type checking.
+		 */
+		goto skip_type_check;

-		expected_type = PTR_TO_BTF_ID;
-		if (type != expected_type)
-			goto err_type;
-		if (!fn->check_btf_id) {
-			if (reg->btf_id != meta->btf_id) {
-				ids_match = btf_struct_ids_match(&env->log, reg->off, reg->btf_id,
-								 meta->btf_id);
-				if (!ids_match) {
-					verbose(env, "Helper has type %s got %s in R%d\n",
-						kernel_type_name(meta->btf_id),
-						kernel_type_name(reg->btf_id), regno);
-					return -EACCES;
-				}
-			}
-		} else if (!fn->check_btf_id(reg->btf_id, arg)) {
-			verbose(env, "Helper does not support %s in R%d\n",
-				kernel_type_name(reg->btf_id), regno);
+	compatible = compatible_reg_types[arg_type];
+	if (!compatible) {
+		verbose(env, "verifier internal error: unsupported arg type %d\n", arg_type);
+		return -EFAULT;
+	}

+	err = check_reg_type(env, regno, compatible);
+	if (err)
+		return err;
+
+	if (type == PTR_TO_BTF_ID) {
+		const u32 *btf_id = fn->arg_btf_id[arg];
+
+		if (!btf_id) {
+			verbose(env, "verifier internal error: missing BTF ID\n");
+			return -EFAULT;
+		}
+
+		if (!btf_struct_ids_match(&env->log, reg->off, reg->btf_id, *btf_id)) {
+			verbose(env, "R%d is of type %s but %s is expected\n",
+				regno, kernel_type_name(reg->btf_id), kernel_type_name(*btf_id));
 			return -EACCES;
 		}
-		if ((reg->off && !ids_match) || !tnum_is_const(reg->var_off) || reg->var_off.value) {
+		if (!tnum_is_const(reg->var_off) || reg->var_off.value) {
 			verbose(env, "R%d is a pointer to in-kernel struct with non-zero offset\n",
 				regno);
 			return -EACCES;
 		}
-	} else if (arg_type == ARG_PTR_TO_SPIN_LOCK) {
-		if (meta->func_id == BPF_FUNC_spin_lock) {
-			if (process_spin_lock(env, regno, true))
-				return -EACCES;
-		} else if (meta->func_id == BPF_FUNC_spin_unlock) {
-			if (process_spin_lock(env, regno, false))
-				return -EACCES;
-		} else {
-			verbose(env, "verifier internal error\n");
-			return -EFAULT;
-		}
-	} else if (arg_type_is_mem_ptr(arg_type)) {
-		expected_type = PTR_TO_STACK;
-		/* One exception here. In case function allows for NULL to be
-		 * passed in as argument, it's a SCALAR_VALUE type. Final test
-		 * happens during stack boundary checking.
-		 */
-		if (register_is_null(reg) &&
-		    (arg_type == ARG_PTR_TO_MEM_OR_NULL ||
-		     arg_type == ARG_PTR_TO_ALLOC_MEM_OR_NULL))
-			/* final test in check_stack_boundary() */;
-		else if (!type_is_pkt_pointer(type) &&
-			 type != PTR_TO_MAP_VALUE &&
-			 type != PTR_TO_MEM &&
-			 type != PTR_TO_RDONLY_BUF &&
-			 type != PTR_TO_RDWR_BUF &&
-			 type != expected_type)
-			goto err_type;
-		meta->raw_mode = arg_type == ARG_PTR_TO_UNINIT_MEM;
-	} else if (arg_type_is_alloc_mem_ptr(arg_type)) {
-		expected_type = PTR_TO_MEM;
-		if (register_is_null(reg) &&
-		    arg_type == ARG_PTR_TO_ALLOC_MEM_OR_NULL)
-			/* final test in check_stack_boundary() */;
-		else if (type != expected_type)
-			goto err_type;
+	} else if (type == PTR_TO_CTX) {
+		err = check_ctx_reg(env, reg, regno);
+		if (err < 0)
+			return err;
+	}
+
+skip_type_check:
+	if (reg->ref_obj_id) {
 		if (meta->ref_obj_id) {
 			verbose(env, "verifier internal error: more than one arg with ref_obj_id R%d %u %u\n",
 				regno, reg->ref_obj_id,
@@ -4074,15 +4140,6 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 			return -EFAULT;
 		}
 		meta->ref_obj_id = reg->ref_obj_id;
-	} else if (arg_type_is_int_ptr(arg_type)) {
-		expected_type = PTR_TO_STACK;
-		if (!type_is_pkt_pointer(type) &&
-		    type != PTR_TO_MAP_VALUE &&
-		    type != expected_type)
-			goto err_type;
-	} else {
-		verbose(env, "unsupported arg_type %d\n", arg_type);
-		return -EFAULT;
 	}

 	if (arg_type == ARG_CONST_MAP_PTR) {
@@ -4121,6 +4178,22 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 		err = check_helper_mem_access(env, regno,
 					      meta->map_ptr->value_size, false,
 					      meta);
+	} else if (arg_type == ARG_PTR_TO_SPIN_LOCK) {
+		if (meta->func_id == BPF_FUNC_spin_lock) {
+			if (process_spin_lock(env, regno, true))
+				return -EACCES;
+		} else if (meta->func_id == BPF_FUNC_spin_unlock) {
+			if (process_spin_lock(env, regno, false))
+				return -EACCES;
+		} else {
+			verbose(env, "verifier internal error\n");
+			return -EFAULT;
+		}
+	} else if (arg_type_is_mem_ptr(arg_type)) {
+		/* The access to this pointer is only checked when we hit the
+		 * next is_mem_size argument below.
+		 */
+		meta->raw_mode = (arg_type == ARG_PTR_TO_UNINIT_MEM);
 	} else if (arg_type_is_mem_size(arg_type)) {
 		bool zero_size_allowed = (arg_type == ARG_CONST_SIZE_OR_ZERO);

@@ -4186,10 +4259,6 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 	}

 	return err;
-err_type:
-	verbose(env, "R%d type=%s expected=%s\n", regno,
-		reg_type_str[type], reg_type_str[expected_type]);
-	return -EACCES;
 }

 static bool may_update_sockmap(struct bpf_verifier_env *env, int func_id)
@@ -4224,6 +4293,11 @@ static bool may_update_sockmap(struct bpf_verifier_env *env, int func_id)
 	return false;
 }

+static bool allow_tail_call_in_subprogs(struct bpf_verifier_env *env)
+{
+	return env->prog->jit_requested && IS_ENABLED(CONFIG_X86_64);
+}
+
 static int check_map_func_compatibility(struct bpf_verifier_env *env,
 					struct bpf_map *map, int func_id)
 {
@@ -4339,8 +4413,8 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 	case BPF_FUNC_tail_call:
 		if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY)
 			goto error;
-		if (env->subprog_cnt > 1) {
-			verbose(env, "tail_calls are not allowed in programs with bpf-to-bpf calls\n");
+		if (env->subprog_cnt > 1 && !allow_tail_call_in_subprogs(env)) {
+			verbose(env, "tail_calls are not allowed in non-JITed programs with bpf-to-bpf calls\n");
 			return -EINVAL;
 		}
 		break;
@@ -4495,10 +4569,22 @@ static bool check_refcount_ok(const struct bpf_func_proto *fn, int func_id)
 	return count <= 1;
 }

+static bool check_btf_id_ok(const struct bpf_func_proto *fn)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(fn->arg_type); i++)
+		if (fn->arg_type[i] == ARG_PTR_TO_BTF_ID && !fn->arg_btf_id[i])
+			return false;
+
+	return true;
+}
+
 static int check_func_proto(const struct bpf_func_proto *fn, int func_id)
 {
 	return check_raw_mode_ok(fn) &&
 	       check_arg_pair_ok(fn) &&
+	       check_btf_id_ok(fn) &&
 	       check_refcount_ok(fn, func_id) ? 0 : -EINVAL;
 }

@@ -4894,11 +4980,6 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 	meta.func_id = func_id;
 	/* check args */
 	for (i = 0; i < 5; i++) {
-		if (!fn->check_btf_id) {
-			err = btf_resolve_helper_id(&env->log, fn, i);
-			if (err > 0)
-				meta.btf_id = err;
-		}
 		err = check_func_arg(env, i, &meta, fn);
 		if (err)
 			return err;
@@ -5317,6 +5398,10 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 			dst, reg_type_str[ptr_reg->type]);
 		return -EACCES;
 	case CONST_PTR_TO_MAP:
+		/* smin_val represents the known value */
+		if (known && smin_val == 0 && opcode == BPF_ADD)
+			break;
+		/* fall-through */
 	case PTR_TO_PACKET_END:
 	case PTR_TO_SOCKET:
 	case PTR_TO_SOCKET_OR_NULL:
@@ -7461,18 +7546,6 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
 		return -EINVAL;
 	}

-	if (env->subprog_cnt > 1) {
-		/* when program has LD_ABS insn JITs and interpreter assume
-		 * that r1 == ctx == skb which is not the case for callees
-		 * that can have arbitrary arguments. It's problematic
-		 * for main prog as well since JITs would need to analyze
-		 * all functions in order to make proper register save/restore
-		 * decisions in the main prog. Hence disallow LD_ABS with calls
-		 */
-		verbose(env, "BPF_LD_[ABS|IND] instructions cannot be mixed with bpf-to-bpf calls\n");
-		return -EINVAL;
-	}
-
 	if (insn->dst_reg != BPF_REG_0 || insn->off != 0 ||
 	    BPF_SIZE(insn->code) == BPF_DW ||
 	    (mode == BPF_ABS && insn->src_reg != BPF_REG_0)) {
@@ -7883,6 +7956,23 @@ err_free:
 	return ret;
 }

+static int check_abnormal_return(struct bpf_verifier_env *env)
+{
+	int i;
+
+	for (i = 1; i < env->subprog_cnt; i++) {
+		if (env->subprog_info[i].has_ld_abs) {
+			verbose(env, "LD_ABS is not allowed in subprogs without BTF\n");
+			return -EINVAL;
+		}
+		if (env->subprog_info[i].has_tail_call) {
+			verbose(env, "tail_call is not allowed in subprogs without BTF\n");
+			return -EINVAL;
+		}
+	}
+	return 0;
+}
+
 /* The minimum supported BTF func info size */
 #define MIN_BPF_FUNCINFO_SIZE	8
 #define MAX_FUNCINFO_REC_SIZE	252
@@ -7891,20 +7981,24 @@ static int check_btf_func(struct bpf_verifier_env *env,
 			  const union bpf_attr *attr,
 			  union bpf_attr __user *uattr)
 {
+	const struct btf_type *type, *func_proto, *ret_type;
 	u32 i, nfuncs, urec_size, min_size;
 	u32 krec_size = sizeof(struct bpf_func_info);
 	struct bpf_func_info *krecord;
 	struct bpf_func_info_aux *info_aux = NULL;
-	const struct btf_type *type;
 	struct bpf_prog *prog;
 	const struct btf *btf;
 	void __user *urecord;
 	u32 prev_offset = 0;
+	bool scalar_return;
 	int ret = -ENOMEM;

 	nfuncs = attr->func_info_cnt;
-	if (!nfuncs)
+	if (!nfuncs) {
+		if (check_abnormal_return(env))
+			return -EINVAL;
 		return 0;
+	}

 	if (nfuncs != env->subprog_cnt) {
 		verbose(env, "number of funcs in func_info doesn't match number of subprogs\n");
@@ -7952,25 +8046,23 @@ static int check_btf_func(struct bpf_verifier_env *env,
 		}

 		/* check insn_off */
+		ret = -EINVAL;
 		if (i == 0) {
 			if (krecord[i].insn_off) {
 				verbose(env,
 					"nonzero insn_off %u for the first func info record",
 					krecord[i].insn_off);
-				ret = -EINVAL;
 				goto err_free;
 			}
 		} else if (krecord[i].insn_off <= prev_offset) {
 			verbose(env,
 				"same or smaller insn offset (%u) than previous func info record (%u)",
 				krecord[i].insn_off, prev_offset);
-			ret = -EINVAL;
 			goto err_free;
 		}

 		if (env->subprog_info[i].start != krecord[i].insn_off) {
 			verbose(env, "func_info BTF section doesn't match subprog layout in BPF program\n");
-			ret = -EINVAL;
 			goto err_free;
 		}

@@ -7979,10 +8071,26 @@ static int check_btf_func(struct bpf_verifier_env *env,
 		if (!type || !btf_type_is_func(type)) {
 			verbose(env, "invalid type id %d in func info",
 				krecord[i].type_id);
-			ret = -EINVAL;
 			goto err_free;
 		}
 		info_aux[i].linkage = BTF_INFO_VLEN(type->info);
+
+		func_proto = btf_type_by_id(btf, type->type);
+		if (unlikely(!func_proto || !btf_type_is_func_proto(func_proto)))
+			/* btf_func_check() already verified it during BTF load */
+			goto err_free;
+		ret_type = btf_type_skip_modifiers(btf, func_proto->type, NULL);
+		scalar_return =
+			btf_type_is_small_int(ret_type) || btf_type_is_enum(ret_type);
+		if (i && !scalar_return && env->subprog_info[i].has_ld_abs) {
+			verbose(env, "LD_ABS is only allowed in functions that return 'int'.\n");
+			goto err_free;
+		}
+		if (i && !scalar_return && env->subprog_info[i].has_tail_call) {
+			verbose(env, "tail_call is only allowed in functions that return 'int'.\n");
+			goto err_free;
+		}
+
 		prev_offset = krecord[i].insn_off;
 		urecord += urec_size;
 	}
@@ -8143,8 +8251,11 @@ static int check_btf_info(struct bpf_verifier_env *env,
 	struct btf *btf;
 	int err;

-	if (!attr->func_info_cnt && !attr->line_info_cnt)
+	if (!attr->func_info_cnt && !attr->line_info_cnt) {
+		if (check_abnormal_return(env))
+			return -EINVAL;
 		return 0;
+	}

 	btf = btf_get_by_fd(attr->prog_btf_fd);
 	if (IS_ERR(btf))
@@ -9619,6 +9730,18 @@ static void adjust_subprog_starts(struct bpf_verifier_env *env, u32 off, u32 len
 	}
 }

+static void adjust_poke_descs(struct bpf_prog *prog, u32 len)
+{
+	struct bpf_jit_poke_descriptor *tab = prog->aux->poke_tab;
+	int i, sz = prog->aux->size_poke_tab;
+	struct bpf_jit_poke_descriptor *desc;
+
+	for (i = 0; i < sz; i++) {
+		desc = &tab[i];
+		desc->insn_idx += len - 1;
+	}
+}
+
 static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 off,
 					    const struct bpf_insn *patch, u32 len)
 {
@@ -9635,6 +9758,7 @@ static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 of
 	if (adjust_insn_aux_data(env, new_prog, off, len))
 		return NULL;
 	adjust_subprog_starts(env, off, len);
+	adjust_poke_descs(new_prog, len);
 	return new_prog;
 }

@@ -10165,6 +10289,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 {
 	struct bpf_prog *prog = env->prog, **func, *tmp;
 	int i, j, subprog_start, subprog_end = 0, len, subprog;
+	struct bpf_map *map_ptr;
 	struct bpf_insn *insn;
 	void *old_bpf_func;
 	int err, num_exentries;
@@ -10232,6 +10357,31 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		func[i]->aux->btf = prog->aux->btf;
 		func[i]->aux->func_info = prog->aux->func_info;

+		for (j = 0; j < prog->aux->size_poke_tab; j++) {
+			u32 insn_idx = prog->aux->poke_tab[j].insn_idx;
+			int ret;
+
+			if (!(insn_idx >= subprog_start &&
+			      insn_idx <= subprog_end))
+				continue;
+
+			ret = bpf_jit_add_poke_descriptor(func[i],
+							  &prog->aux->poke_tab[j]);
+			if (ret < 0) {
+				verbose(env, "adding tail call poke descriptor failed\n");
+				goto out_free;
+			}
+
+			func[i]->insnsi[insn_idx - subprog_start].imm = ret + 1;
+
+			map_ptr = func[i]->aux->poke_tab[ret].tail_call.map;
+			ret = map_ptr->ops->map_poke_track(map_ptr, func[i]->aux);
+			if (ret < 0) {
+				verbose(env, "tracking tail call prog failed\n");
+				goto out_free;
+			}
+		}
+
 		/* Use bpf_prog_F_tag to indicate functions in stack traces.
 		 * Long term would need debug info to populate names
 		 */
@@ -10250,6 +10400,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 				num_exentries++;
 		}
 		func[i]->aux->num_exentries = num_exentries;
+		func[i]->aux->tail_call_reachable = env->subprog_info[i].tail_call_reachable;
 		func[i] = bpf_int_jit_compile(func[i]);
 		if (!func[i]->jited) {
 			err = -ENOTSUPP;
@@ -10257,6 +10408,19 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		}
 		cond_resched();
 	}
+
+	/* Untrack main program's aux structs so that during map_poke_run()
+	 * we will not stumble upon the unfilled poke descriptors; each
+	 * of the main program's poke descs got distributed across subprogs
+	 * and got tracked onto map, so we are sure that none of them will
+	 * be missed after the operation below
+	 */
+	for (i = 0; i < prog->aux->size_poke_tab; i++) {
+		map_ptr = prog->aux->poke_tab[i].tail_call.map;
+
+		map_ptr->ops->map_poke_untrack(map_ptr, prog->aux);
+	}
+
 	/* at this point all bpf functions were successfully JITed
 	 * now populate all bpf_calls with correct addresses and
 	 * run last pass of JIT
@@ -10325,9 +10489,16 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 	bpf_prog_free_unused_jited_linfo(prog);
 	return 0;
 out_free:
-	for (i = 0; i < env->subprog_cnt; i++)
-		if (func[i])
-			bpf_jit_free(func[i]);
+	for (i = 0; i < env->subprog_cnt; i++) {
+		if (!func[i])
+			continue;
+
+		for (j = 0; j < func[i]->aux->size_poke_tab; j++) {
+			map_ptr = func[i]->aux->poke_tab[j].tail_call.map;
+			map_ptr->ops->map_poke_untrack(map_ptr, func[i]->aux);
+		}
+		bpf_jit_free(func[i]);
+	}
 	kfree(func);
 out_undo_insn:
 	/* cleanup main prog to be interpreted */
@@ -10361,6 +10532,13 @@ static int fixup_call_args(struct bpf_verifier_env *env)
 			return err;
 	}
 #ifndef CONFIG_BPF_JIT_ALWAYS_ON
+	if (env->subprog_cnt > 1 && env->prog->aux->tail_call_reachable) {
+		/* When JIT fails the progs with bpf2bpf calls and tail_calls
+		 * have to be rejected, since interpreter doesn't support them yet.
+		 */
+		verbose(env, "tail_calls are not allowed in non-JITed programs with bpf-to-bpf calls\n");
+		return -EINVAL;
+	}
 	for (i = 0; i < prog->len; i++, insn++) {
 		if (insn->code != (BPF_JMP | BPF_CALL) ||
 		    insn->src_reg != BPF_PSEUDO_CALL)
@@ -10524,8 +10702,9 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
 			 * the program array.
 			 */
 			prog->cb_access = 1;
-			env->prog->aux->stack_depth = MAX_BPF_STACK;
-			env->prog->aux->max_pkt_offset = MAX_PACKET_OFF;
+			if (!allow_tail_call_in_subprogs(env))
+				prog->aux->stack_depth = MAX_BPF_STACK;
+			prog->aux->max_pkt_offset = MAX_PACKET_OFF;

 			/* mark bpf_tail_call as different opcode to avoid
 			 * conditional branch in the interpeter for every normal
@@ -10545,6 +10724,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
 					.reason = BPF_POKE_REASON_TAIL_CALL,
 					.tail_call.map = BPF_MAP_PTR(aux->map_ptr_state),
 					.tail_call.key = bpf_map_key_immediate(aux),
+					.insn_idx = i + delta,
 				};

 				ret = bpf_jit_add_poke_descriptor(prog, &desc);