bpf: Allow rewriting to ports under ip_unprivileged_port_start

At the moment, BPF_CGROUP_INET{4,6}_BIND hooks can rewrite user_port
to the privileged ones (< ip_unprivileged_port_start), but it will
be rejected later on in the __inet_bind or __inet6_bind.

Let's add another return value to indicate that CAP_NET_BIND_SERVICE
check should be ignored. Use the same idea as we currently use
in cgroup/egress where bit #1 indicates CN. Instead, for
cgroup/bind{4,6}, bit #1 indicates that CAP_NET_BIND_SERVICE should
be bypassed.

v5:
- rename flags to be less confusing (Andrey Ignatov)
- rework BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY to work on flags
  and accept BPF_RET_SET_CN (no behavioral changes)

v4:
- Add missing IPv6 support (Martin KaFai Lau)

v3:
- Update description (Martin KaFai Lau)
- Fix capability restore in selftest (Martin KaFai Lau)

v2:
- Switch to explicit return code (Martin KaFai Lau)

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Andrey Ignatov <rdna@fb.com>
Link: https://lore.kernel.org/bpf/20210127193140.3170382-1-sdf@google.com

3 files changed, 63 insertions, 29 deletions

diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 0748fd87969e..c42e02b4d84b 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -125,7 +125,8 @@ int __cgroup_bpf_run_filter_sk(struct sock *sk,
 int __cgroup_bpf_run_filter_sock_addr(struct sock *sk,
 				      struct sockaddr *uaddr,
 				      enum bpf_attach_type type,
-				      void *t_ctx);
+				      void *t_ctx,
+				      u32 *flags);
 
 int __cgroup_bpf_run_filter_sock_ops(struct sock *sk,
 				     struct bpf_sock_ops_kern *sock_ops,
@@ -231,30 +232,48 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key,
 
 #define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, type)				       \
 ({									       \
+	u32 __unused_flags;						       \
 	int __ret = 0;							       \
 	if (cgroup_bpf_enabled(type))					       \
 		__ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type,     \
-							  NULL);	       \
+							  NULL,		       \
+							  &__unused_flags);    \
 	__ret;								       \
 })
 
 #define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, type, t_ctx)		       \
 ({									       \
+	u32 __unused_flags;						       \
 	int __ret = 0;							       \
 	if (cgroup_bpf_enabled(type))	{				       \
 		lock_sock(sk);						       \
 		__ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type,     \
-							  t_ctx);	       \
+							  t_ctx,	       \
+							  &__unused_flags);    \
 		release_sock(sk);					       \
 	}								       \
 	__ret;								       \
 })
 
-#define BPF_CGROUP_RUN_PROG_INET4_BIND_LOCK(sk, uaddr)			       \
-	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET4_BIND, NULL)
-
-#define BPF_CGROUP_RUN_PROG_INET6_BIND_LOCK(sk, uaddr)			       \
-	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET6_BIND, NULL)
+/* BPF_CGROUP_INET4_BIND and BPF_CGROUP_INET6_BIND can return extra flags
+ * via upper bits of return code. The only flag that is supported
+ * (at bit position 0) is to indicate CAP_NET_BIND_SERVICE capability check
+ * should be bypassed (BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE).
+ */
+#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, type, bind_flags)	       \
+({									       \
+	u32 __flags = 0;						       \
+	int __ret = 0;							       \
+	if (cgroup_bpf_enabled(type))	{				       \
+		lock_sock(sk);						       \
+		__ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type,     \
+							  NULL, &__flags);     \
+		release_sock(sk);					       \
+		if (__flags & BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE)	       \
+			*bind_flags |= BIND_NO_CAP_NET_BIND_SERVICE;	       \
+	}								       \
+	__ret;								       \
+})
 
 #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk)				       \
 	((cgroup_bpf_enabled(BPF_CGROUP_INET4_CONNECT) ||		       \
@@ -453,8 +472,7 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map,
 #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET_SOCK_RELEASE(sk) ({ 0; })
-#define BPF_CGROUP_RUN_PROG_INET4_BIND_LOCK(sk, uaddr) ({ 0; })
-#define BPF_CGROUP_RUN_PROG_INET6_BIND_LOCK(sk, uaddr) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, type, flags) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET6_POST_BIND(sk) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr) ({ 0; })
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 1aac2af12fed..321966fc35db 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1073,6 +1073,34 @@ int bpf_prog_array_copy(struct bpf_prog_array *old_array,
 			struct bpf_prog *include_prog,
 			struct bpf_prog_array **new_array);
 
+/* BPF program asks to bypass CAP_NET_BIND_SERVICE in bind. */
+#define BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE			(1 << 0)
+/* BPF program asks to set CN on the packet. */
+#define BPF_RET_SET_CN						(1 << 0)
+
+#define BPF_PROG_RUN_ARRAY_FLAGS(array, ctx, func, ret_flags)		\
+	({								\
+		struct bpf_prog_array_item *_item;			\
+		struct bpf_prog *_prog;					\
+		struct bpf_prog_array *_array;				\
+		u32 _ret = 1;						\
+		u32 func_ret;						\
+		migrate_disable();					\
+		rcu_read_lock();					\
+		_array = rcu_dereference(array);			\
+		_item = &_array->items[0];				\
+		while ((_prog = READ_ONCE(_item->prog))) {		\
+			bpf_cgroup_storage_set(_item->cgroup_storage);	\
+			func_ret = func(_prog, ctx);			\
+			_ret &= (func_ret & 1);				\
+			*(ret_flags) |= (func_ret >> 1);			\
+			_item++;					\
+		}							\
+		rcu_read_unlock();					\
+		migrate_enable();					\
+		_ret;							\
+	 })
+
 #define __BPF_PROG_RUN_ARRAY(array, ctx, func, check_non_null)	\
 	({						\
 		struct bpf_prog_array_item *_item;	\
@@ -1120,25 +1148,11 @@ _out:							\
  */
 #define BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY(array, ctx, func)		\
 	({						\
-		struct bpf_prog_array_item *_item;	\
-		struct bpf_prog *_prog;			\
-		struct bpf_prog_array *_array;		\
-		u32 ret;				\
-		u32 _ret = 1;				\
-		u32 _cn = 0;				\
-		migrate_disable();			\
-		rcu_read_lock();			\
-		_array = rcu_dereference(array);	\
-		_item = &_array->items[0];		\
-		while ((_prog = READ_ONCE(_item->prog))) {		\
-			bpf_cgroup_storage_set(_item->cgroup_storage);	\
-			ret = func(_prog, ctx);		\
-			_ret &= (ret & 1);		\
-			_cn |= (ret & 2);		\
-			_item++;			\
-		}					\
-		rcu_read_unlock();			\
-		migrate_enable();			\
+		u32 _flags = 0;				\
+		bool _cn;				\
+		u32 _ret;				\
+		_ret = BPF_PROG_RUN_ARRAY_FLAGS(array, ctx, func, &_flags); \
+		_cn = _flags & BPF_RET_SET_CN;		\
 		if (_ret)				\
 			_ret = (_cn ? NET_XMIT_CN : NET_XMIT_SUCCESS);	\
 		else					\
diff --git a/include/net/inet_common.h b/include/net/inet_common.h
index cb2818862919..cad2a611efde 100644
--- a/include/net/inet_common.h
+++ b/include/net/inet_common.h
@@ -41,6 +41,8 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len);
 #define BIND_WITH_LOCK			(1 << 1)
 /* Called from BPF program. */
 #define BIND_FROM_BPF			(1 << 2)
+/* Skip CAP_NET_BIND_SERVICE check. */
+#define BIND_NO_CAP_NET_BIND_SERVICE	(1 << 3)
 int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len,
 		u32 flags);
 int inet_getname(struct socket *sock, struct sockaddr *uaddr,