Commit 84085f87 authored by Alexei Starovoitov's avatar Alexei Starovoitov
Browse files

Merge branch 'enable-bpf_skc-cast-for-networking-progs' 



Martin KaFai Lau says:

====================
This set allows networking prog type to directly read fields from
the in-kernel socket type, e.g. "struct tcp_sock".

Patch 2 has the details on the use case.

v3:
- Pass arg_btf_id instead of fn into check_reg_type() in Patch 1 (Lorenz)
- Move arg_btf_id from func_proto to struct bpf_reg_types in Patch 2 (Lorenz)
- Remove test_sock_fields from .gitignore in Patch 8 (Andrii)
- Add tests to have better coverage on the modified helpers (Alexei)
  Patch 13 is added.
- Use "void *sk" as the helper argument in UAPI bpf.h

v3:
- ARG_PTR_TO_SOCK_COMMON_OR_NULL was attempted in v2.  The _OR_NULL was
  needed because the PTR_TO_BTF_ID could be NULL but note that a could be NULL
  PTR_TO_BTF_ID is not a scalar NULL to the verifier.  "_OR_NULL" implicitly
  gives an expectation that the helper can take a scalar NULL which does
  not make sense in most (except one) helpers.  Passing scalar NULL
  should be rejected at the verification time.

  Thus, this patch uses ARG_PTR_TO_BTF_ID_SOCK_COMMON to specify that the
  helper can take both the btf-id ptr or the legacy PTR_TO_SOCK_COMMON but
  not scalar NULL.  It requires the func_proto to explicitly specify the
  arg_btf_id such that there is a very clear expectation that the helper
  can handle a NULL PTR_TO_BTF_ID.

v2:
- Add ARG_PTR_TO_SOCK_COMMON_OR_NULL (Lorenz)
====================

Signed-off-by: default avatarAlexei Starovoitov <ast@kernel.org>
parents 182bf3f3 9a856cae

include/linux/bpf.h

+1 −0
Original line number Diff line number Diff line
@@ -292,6 +292,7 @@ enum bpf_arg_type { 
	ARG_PTR_TO_ALLOC_MEM,	/* pointer to dynamically allocated memory */

	ARG_PTR_TO_ALLOC_MEM_OR_NULL,	/* pointer to dynamically allocated memory or NULL */

	ARG_CONST_ALLOC_SIZE_OR_ZERO,	/* number of allocated bytes requested */

	ARG_PTR_TO_BTF_ID_SOCK_COMMON,	/* pointer to in-kernel sock_common or bpf-mirrored bpf_sock */

	__BPF_ARG_TYPE_MAX,

};

include/net/bpf_sk_storage.h

+0 −2
Original line number Diff line number Diff line
@@ -20,8 +20,6 @@ void bpf_sk_storage_free(struct sock *sk); 


extern const struct bpf_func_proto bpf_sk_storage_get_proto;

extern const struct bpf_func_proto bpf_sk_storage_delete_proto;

extern const struct bpf_func_proto sk_storage_get_btf_proto;

extern const struct bpf_func_proto sk_storage_delete_btf_proto;



struct bpf_local_storage_elem;

struct bpf_sk_storage_diag;

include/uapi/linux/bpf.h

+8 −7
Original line number Diff line number Diff line
@@ -2512,7 +2512,7 @@ union bpf_attr { 
 *		result is from *reuse*\ **->socks**\ [] using the hash of the

 *		tuple.

 *

 * long bpf_sk_release(struct bpf_sock *sock)

 * long bpf_sk_release(void *sock)

 *	Description

 *		Release the reference held by *sock*. *sock* must be a

 *		non-**NULL** pointer that was returned from
@@ -2692,7 +2692,7 @@ union bpf_attr { 
 *		result is from *reuse*\ **->socks**\ [] using the hash of the

 *		tuple.

 *

 * long bpf_tcp_check_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)

 * long bpf_tcp_check_syncookie(void *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)

 * 	Description

 * 		Check whether *iph* and *th* contain a valid SYN cookie ACK for

 * 		the listening socket in *sk*.
@@ -2861,6 +2861,7 @@ union bpf_attr { 
 *		0 on success.

 *

 *		**-ENOENT** if the bpf-local-storage cannot be found.

 *		**-EINVAL** if sk is not a fullsock (e.g. a request_sock).

 *

 * long bpf_send_signal(u32 sig)

 *	Description
@@ -2877,7 +2878,7 @@ union bpf_attr { 
 *

 *		**-EAGAIN** if bpf program can try again.

 *

 * s64 bpf_tcp_gen_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)

 * s64 bpf_tcp_gen_syncookie(void *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)

 *	Description

 *		Try to issue a SYN cookie for the packet with corresponding

 *		IP/TCP headers, *iph* and *th*, on the listening socket in *sk*.
@@ -3106,7 +3107,7 @@ union bpf_attr { 
 * 	Return

 * 		The id is returned or 0 in case the id could not be retrieved.

 *

 * long bpf_sk_assign(struct sk_buff *skb, struct bpf_sock *sk, u64 flags)

 * long bpf_sk_assign(struct sk_buff *skb, void *sk, u64 flags)

 *	Description

 *		Helper is overloaded depending on BPF program type. This

 *		description applies to **BPF_PROG_TYPE_SCHED_CLS** and
@@ -3234,11 +3235,11 @@ union bpf_attr { 
 *

 *		**-EOVERFLOW** if an overflow happened: The same object will be tried again.

 *

 * u64 bpf_sk_cgroup_id(struct bpf_sock *sk)

 * u64 bpf_sk_cgroup_id(void *sk)

 *	Description

 *		Return the cgroup v2 id of the socket *sk*.

 *

 *		*sk* must be a non-**NULL** pointer to a full socket, e.g. one

 *		*sk* must be a non-**NULL** pointer to a socket, e.g. one

 *		returned from **bpf_sk_lookup_xxx**\ (),

 *		**bpf_sk_fullsock**\ (), etc. The format of returned id is

 *		same as in **bpf_skb_cgroup_id**\ ().
@@ -3248,7 +3249,7 @@ union bpf_attr { 
 *	Return

 *		The id is returned or 0 in case the id could not be retrieved.

 *

 * u64 bpf_sk_ancestor_cgroup_id(struct bpf_sock *sk, int ancestor_level)

 * u64 bpf_sk_ancestor_cgroup_id(void *sk, int ancestor_level)

 *	Description

 *		Return id of cgroup v2 that is ancestor of cgroup associated

 *		with the *sk* at the *ancestor_level*.  The root cgroup is at

kernel/bpf/bpf_lsm.c

+2 −2
Original line number Diff line number Diff line
@@ -56,9 +56,9 @@ bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) 
	case BPF_FUNC_inode_storage_delete:

		return &bpf_inode_storage_delete_proto;

	case BPF_FUNC_sk_storage_get:

		return &sk_storage_get_btf_proto;

		return &bpf_sk_storage_get_proto;

	case BPF_FUNC_sk_storage_delete:

		return &sk_storage_delete_btf_proto;

		return &bpf_sk_storage_delete_proto;

	default:

		return tracing_prog_func_proto(func_id, prog);

	}

kernel/bpf/verifier.c

+63 −31
Original line number Diff line number Diff line
@@ -486,7 +486,12 @@ static bool is_acquire_function(enum bpf_func_id func_id, 
static bool is_ptr_cast_function(enum bpf_func_id func_id)

{

	return func_id == BPF_FUNC_tcp_sock ||

		func_id == BPF_FUNC_sk_fullsock;

		func_id == BPF_FUNC_sk_fullsock ||

		func_id == BPF_FUNC_skc_to_tcp_sock ||

		func_id == BPF_FUNC_skc_to_tcp6_sock ||

		func_id == BPF_FUNC_skc_to_udp6_sock ||

		func_id == BPF_FUNC_skc_to_tcp_timewait_sock ||

		func_id == BPF_FUNC_skc_to_tcp_request_sock;

}



/* string representation of 'enum bpf_reg_type' */
@@ -3953,6 +3958,7 @@ static int resolve_map_arg_type(struct bpf_verifier_env *env, 


struct bpf_reg_types {

	const enum bpf_reg_type types[10];

	u32 *btf_id;

};



static const struct bpf_reg_types map_key_value_types = {
@@ -3973,6 +3979,17 @@ static const struct bpf_reg_types sock_types = { 
	},

};



static const struct bpf_reg_types btf_id_sock_common_types = {

	.types = {

		PTR_TO_SOCK_COMMON,

		PTR_TO_SOCKET,

		PTR_TO_TCP_SOCK,

		PTR_TO_XDP_SOCK,

		PTR_TO_BTF_ID,

	},

	.btf_id = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],

};



static const struct bpf_reg_types mem_types = {

	.types = {

		PTR_TO_STACK,
@@ -4014,6 +4031,7 @@ static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = { 
	[ARG_PTR_TO_CTX]		= &context_types,

	[ARG_PTR_TO_CTX_OR_NULL]	= &context_types,

	[ARG_PTR_TO_SOCK_COMMON]	= &sock_types,

	[ARG_PTR_TO_BTF_ID_SOCK_COMMON]	= &btf_id_sock_common_types,

	[ARG_PTR_TO_SOCKET]		= &fullsock_types,

	[ARG_PTR_TO_SOCKET_OR_NULL]	= &fullsock_types,

	[ARG_PTR_TO_BTF_ID]		= &btf_ptr_types,
@@ -4028,19 +4046,27 @@ static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = { 
};



static int check_reg_type(struct bpf_verifier_env *env, u32 regno,

			  const struct bpf_reg_types *compatible)

			  enum bpf_arg_type arg_type,

			  const u32 *arg_btf_id)

{

	struct bpf_reg_state *regs = cur_regs(env), *reg = &regs[regno];

	enum bpf_reg_type expected, type = reg->type;

	const struct bpf_reg_types *compatible;

	int i, j;



	compatible = compatible_reg_types[arg_type];

	if (!compatible) {

		verbose(env, "verifier internal error: unsupported arg type %d\n", arg_type);

		return -EFAULT;

	}



	for (i = 0; i < ARRAY_SIZE(compatible->types); i++) {

		expected = compatible->types[i];

		if (expected == NOT_INIT)

			break;



		if (type == expected)

			return 0;

			goto found;

	}



	verbose(env, "R%d type=%s expected=", regno, reg_type_str[type]);
@@ -4048,6 +4074,33 @@ static int check_reg_type(struct bpf_verifier_env *env, u32 regno, 
		verbose(env, "%s, ", reg_type_str[compatible->types[j]]);

	verbose(env, "%s\n", reg_type_str[compatible->types[j]]);

	return -EACCES;



found:

	if (type == PTR_TO_BTF_ID) {

		if (!arg_btf_id) {

			if (!compatible->btf_id) {

				verbose(env, "verifier internal error: missing arg compatible BTF ID\n");

				return -EFAULT;

			}

			arg_btf_id = compatible->btf_id;

		}



		if (!btf_struct_ids_match(&env->log, reg->off, reg->btf_id,

					  *arg_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(*arg_btf_id));

			return -EACCES;

		}



		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;

		}

	}



	return 0;

}



static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
@@ -4057,7 +4110,6 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg, 
	u32 regno = BPF_REG_1 + arg;

	struct bpf_reg_state *regs = cur_regs(env), *reg = &regs[regno];

	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;
@@ -4097,35 +4149,11 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg, 
		 */

		goto skip_type_check;



	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);

	err = check_reg_type(env, regno, arg_type, fn->arg_btf_id[arg]);

	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 (!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 (type == PTR_TO_CTX) {

	if (type == PTR_TO_CTX) {

		err = check_ctx_reg(env, reg, regno);

		if (err < 0)

			return err;
@@ -4573,10 +4601,14 @@ static bool check_btf_id_ok(const struct bpf_func_proto *fn) 
{

	int i;



	for (i = 0; i < ARRAY_SIZE(fn->arg_type); 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;



		if (fn->arg_type[i] != ARG_PTR_TO_BTF_ID && fn->arg_btf_id[i])

			return false;

	}



	return true;

}

CRA Git | Maintained and supported by SUSTech CRA and CCSE