bpf: Introduce bpf_sk_{, ancestor_}cgroup_id helpers

With having ability to lookup sockets in cgroup skb programs it becomes
useful to access cgroup id of retrieved sockets so that policies can be
implemented based on origin cgroup of such socket.

For example, a container running in a cgroup can have cgroup skb ingress
program that can lookup peer socket that is sending packets to a process
inside the container and decide whether those packets should be allowed
or denied based on cgroup id of the peer.

More specifically such ingress program can implement intra-host policy
"allow incoming packets only from this same container and not from any
other container on same host" w/o relying on source IP addresses since
quite often it can be the case that containers share same IP address on
the host.

Introduce two new helpers for this use-case: bpf_sk_cgroup_id() and
bpf_sk_ancestor_cgroup_id().

These helpers are similar to existing bpf_skb_{,ancestor_}cgroup_id
helpers with the only difference that sk is used to get cgroup id
instead of skb, and share code with them.

See documentation in UAPI for more details.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/f5884981249ce911f63e9b57ecd5d7d19154ff39.1589486450.git.rdna@fb.com

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 85cfdffde18270e4009b033c96ab9d90f8f720ad..146c742f1d491a91be76ea5fa06c615530f6a2be 100644 (file)
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3121,6 +3121,38 @@ union bpf_attr {
  *             0 on success, or a negative error in case of failure:
  *
  *             **-EOVERFLOW** if an overflow happened: The same object will be tried again.
+ *
+ * u64 bpf_sk_cgroup_id(struct bpf_sock *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
+ *             returned from **bpf_sk_lookup_xxx**\ (),
+ *             **bpf_sk_fullsock**\ (), etc. The format of returned id is
+ *             same as in **bpf_skb_cgroup_id**\ ().
+ *
+ *             This helper is available only if the kernel was compiled with
+ *             the **CONFIG_SOCK_CGROUP_DATA** configuration option.
+ *     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)
+ *     Description
+ *             Return id of cgroup v2 that is ancestor of cgroup associated
+ *             with the *sk* at the *ancestor_level*.  The root cgroup is at
+ *             *ancestor_level* zero and each step down the hierarchy
+ *             increments the level. If *ancestor_level* == level of cgroup
+ *             associated with *sk*, then return value will be same as that
+ *             of **bpf_sk_cgroup_id**\ ().
+ *
+ *             The helper is useful to implement policies based on cgroups
+ *             that are upper in hierarchy than immediate cgroup associated
+ *             with *sk*.
+ *
+ *             The format of returned id and helper limitations are same as in
+ *             **bpf_sk_cgroup_id**\ ().
+ *     Return
+ *             The id is returned or 0 in case the id could not be retrieved.
  */
 #define __BPF_FUNC_MAPPER(FN)          \
        FN(unspec),                     \
@@ -3250,7 +3282,9 @@ union bpf_attr {
        FN(sk_assign),                  \
        FN(ktime_get_boot_ns),          \
        FN(seq_printf),                 \
-       FN(seq_write),
+       FN(seq_write),                  \
+       FN(sk_cgroup_id),               \
+       FN(sk_ancestor_cgroup_id),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call

diff --git a/net/core/filter.c b/net/core/filter.c
index a47dc5b9dad4fbd74bc86654ab9e10ffa3a37627..5815902bb617fe85f6b47c04a5fecf42c2b5b18d 100644 (file)
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4003,16 +4003,22 @@ static const struct bpf_func_proto bpf_skb_under_cgroup_proto = {
 };
 
 #ifdef CONFIG_SOCK_CGROUP_DATA
+static inline u64 __bpf_sk_cgroup_id(struct sock *sk)
+{
+       struct cgroup *cgrp;
+
+       cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
+       return cgroup_id(cgrp);
+}
+
 BPF_CALL_1(bpf_skb_cgroup_id, const struct sk_buff *, skb)
 {
        struct sock *sk = skb_to_full_sk(skb);
-       struct cgroup *cgrp;
 
        if (!sk || !sk_fullsock(sk))
                return 0;
 
-       cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
-       return cgroup_id(cgrp);
+       return __bpf_sk_cgroup_id(sk);
 }
 
 static const struct bpf_func_proto bpf_skb_cgroup_id_proto = {
@@ -4022,16 +4028,12 @@ static const struct bpf_func_proto bpf_skb_cgroup_id_proto = {
        .arg1_type      = ARG_PTR_TO_CTX,
 };
 
-BPF_CALL_2(bpf_skb_ancestor_cgroup_id, const struct sk_buff *, skb, int,
-          ancestor_level)
+static inline u64 __bpf_sk_ancestor_cgroup_id(struct sock *sk,
+                                             int ancestor_level)
 {
-       struct sock *sk = skb_to_full_sk(skb);
        struct cgroup *ancestor;
        struct cgroup *cgrp;
 
-       if (!sk || !sk_fullsock(sk))
-               return 0;
-
        cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
        ancestor = cgroup_ancestor(cgrp, ancestor_level);
        if (!ancestor)
@@ -4040,6 +4042,17 @@ BPF_CALL_2(bpf_skb_ancestor_cgroup_id, const struct sk_buff *, skb, int,
        return cgroup_id(ancestor);
 }
 
+BPF_CALL_2(bpf_skb_ancestor_cgroup_id, const struct sk_buff *, skb, int,
+          ancestor_level)
+{
+       struct sock *sk = skb_to_full_sk(skb);
+
+       if (!sk || !sk_fullsock(sk))
+               return 0;
+
+       return __bpf_sk_ancestor_cgroup_id(sk, ancestor_level);
+}
+
 static const struct bpf_func_proto bpf_skb_ancestor_cgroup_id_proto = {
        .func           = bpf_skb_ancestor_cgroup_id,
        .gpl_only       = false,
@@ -4047,6 +4060,31 @@ static const struct bpf_func_proto bpf_skb_ancestor_cgroup_id_proto = {
        .arg1_type      = ARG_PTR_TO_CTX,
        .arg2_type      = ARG_ANYTHING,
 };
+
+BPF_CALL_1(bpf_sk_cgroup_id, struct sock *, sk)
+{
+       return __bpf_sk_cgroup_id(sk);
+}
+
+static const struct bpf_func_proto bpf_sk_cgroup_id_proto = {
+       .func           = bpf_sk_cgroup_id,
+       .gpl_only       = false,
+       .ret_type       = RET_INTEGER,
+       .arg1_type      = ARG_PTR_TO_SOCKET,
+};
+
+BPF_CALL_2(bpf_sk_ancestor_cgroup_id, struct sock *, sk, int, ancestor_level)
+{
+       return __bpf_sk_ancestor_cgroup_id(sk, ancestor_level);
+}
+
+static const struct bpf_func_proto bpf_sk_ancestor_cgroup_id_proto = {
+       .func           = bpf_sk_ancestor_cgroup_id,
+       .gpl_only       = false,
+       .ret_type       = RET_INTEGER,
+       .arg1_type      = ARG_PTR_TO_SOCKET,
+       .arg2_type      = ARG_ANYTHING,
+};
 #endif
 
 static unsigned long bpf_xdp_copy(void *dst_buff, const void *src_buff,
@@ -6159,6 +6197,10 @@ cg_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
                return &bpf_skb_cgroup_id_proto;
        case BPF_FUNC_skb_ancestor_cgroup_id:
                return &bpf_skb_ancestor_cgroup_id_proto;
+       case BPF_FUNC_sk_cgroup_id:
+               return &bpf_sk_cgroup_id_proto;
+       case BPF_FUNC_sk_ancestor_cgroup_id:
+               return &bpf_sk_ancestor_cgroup_id_proto;
 #endif
 #ifdef CONFIG_INET
        case BPF_FUNC_sk_lookup_tcp:

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 85cfdffde18270e4009b033c96ab9d90f8f720ad..146c742f1d491a91be76ea5fa06c615530f6a2be 100644 (file)
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3121,6 +3121,38 @@ union bpf_attr {
  *             0 on success, or a negative error in case of failure:
  *
  *             **-EOVERFLOW** if an overflow happened: The same object will be tried again.
+ *
+ * u64 bpf_sk_cgroup_id(struct bpf_sock *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
+ *             returned from **bpf_sk_lookup_xxx**\ (),
+ *             **bpf_sk_fullsock**\ (), etc. The format of returned id is
+ *             same as in **bpf_skb_cgroup_id**\ ().
+ *
+ *             This helper is available only if the kernel was compiled with
+ *             the **CONFIG_SOCK_CGROUP_DATA** configuration option.
+ *     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)
+ *     Description
+ *             Return id of cgroup v2 that is ancestor of cgroup associated
+ *             with the *sk* at the *ancestor_level*.  The root cgroup is at
+ *             *ancestor_level* zero and each step down the hierarchy
+ *             increments the level. If *ancestor_level* == level of cgroup
+ *             associated with *sk*, then return value will be same as that
+ *             of **bpf_sk_cgroup_id**\ ().
+ *
+ *             The helper is useful to implement policies based on cgroups
+ *             that are upper in hierarchy than immediate cgroup associated
+ *             with *sk*.
+ *
+ *             The format of returned id and helper limitations are same as in
+ *             **bpf_sk_cgroup_id**\ ().
+ *     Return
+ *             The id is returned or 0 in case the id could not be retrieved.
  */
 #define __BPF_FUNC_MAPPER(FN)          \
        FN(unspec),                     \
@@ -3250,7 +3282,9 @@ union bpf_attr {
        FN(sk_assign),                  \
        FN(ktime_get_boot_ns),          \
        FN(seq_printf),                 \
-       FN(seq_write),
+       FN(seq_write),                  \
+       FN(sk_cgroup_id),               \
+       FN(sk_ancestor_cgroup_id),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call