bpf: implement getsockopt and setsockopt hooks

Implement new BPF_PROG_TYPE_CGROUP_SOCKOPT program type and
BPF_CGROUP_{G,S}ETSOCKOPT cgroup hooks.

BPF_CGROUP_SETSOCKOPT can modify user setsockopt arguments before
passing them down to the kernel or bypass kernel completely.
BPF_CGROUP_GETSOCKOPT can can inspect/modify getsockopt arguments that
kernel returns.
Both hooks reuse existing PTR_TO_PACKET{,_END} infrastructure.

The buffer memory is pre-allocated (because I don't think there is
a precedent for working with __user memory from bpf). This might be
slow to do for each {s,g}etsockopt call, that's why I've added
__cgroup_bpf_prog_array_is_empty that exits early if there is nothing
attached to a cgroup. Note, however, that there is a race between
__cgroup_bpf_prog_array_is_empty and BPF_PROG_RUN_ARRAY where cgroup
program layout might have changed; this should not be a problem
because in general there is a race between multiple calls to
{s,g}etsocktop and user adding/removing bpf progs from a cgroup.

The return code of the BPF program is handled as follows:
* 0: EPERM
* 1: success, continue with next BPF program in the cgroup chain

v9:
* allow overwriting setsockopt arguments (Alexei Starovoitov):
  * use set_fs (same as kernel_setsockopt)
  * buffer is always kzalloc'd (no small on-stack buffer)

v8:
* use s32 for optlen (Andrii Nakryiko)

v7:
* return only 0 or 1 (Alexei Starovoitov)
* always run all progs (Alexei Starovoitov)
* use optval=0 as kernel bypass in setsockopt (Alexei Starovoitov)
  (decided to use optval=-1 instead, optval=0 might be a valid input)
* call getsockopt hook after kernel handlers (Alexei Starovoitov)

v6:
* rework cgroup chaining; stop as soon as bpf program returns
  0 or 2; see patch with the documentation for the details
* drop Andrii's and Martin's Acked-by (not sure they are comfortable
  with the new state of things)

v5:
* skip copy_to_user() and put_user() when ret == 0 (Martin Lau)

v4:
* don't export bpf_sk_fullsock helper (Martin Lau)
* size != sizeof(__u64) for uapi pointers (Martin Lau)
* offsetof instead of bpf_ctx_range when checking ctx access (Martin Lau)

v3:
* typos in BPF_PROG_CGROUP_SOCKOPT_RUN_ARRAY comments (Andrii Nakryiko)
* reverse christmas tree in BPF_PROG_CGROUP_SOCKOPT_RUN_ARRAY (Andrii
  Nakryiko)
* use __bpf_md_ptr instead of __u32 for optval{,_end} (Martin Lau)
* use BPF_FIELD_SIZEOF() for consistency (Martin Lau)
* new CG_SOCKOPT_ACCESS macro to wrap repeated parts

v2:
* moved bpf_sockopt_kern fields around to remove a hole (Martin Lau)
* aligned bpf_sockopt_kern->buf to 8 bytes (Martin Lau)
* bpf_prog_array_is_empty instead of bpf_prog_array_length (Martin Lau)
* added [0,2] return code check to verifier (Martin Lau)
* dropped unused buf[64] from the stack (Martin Lau)
* use PTR_TO_SOCKET for bpf_sockopt->sk (Martin Lau)
* dropped bpf_target_off from ctx rewrites (Martin Lau)
* use return code for kernel bypass (Martin Lau & Andrii Nakryiko)

Cc: Andrii Nakryiko <[email protected]>
Cc: Martin Lau <[email protected]>
Signed-off-by: Stanislav Fomichev <[email protected]>
Signed-off-by: Alexei Starovoitov <[email protected]>

Author: fomichev

include/linux/bpf-cgroup.h

@@ -124,6 +124,14 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
 				   loff_t *ppos, void **new_buf,
 				   enum bpf_attach_type type);
 
+int __cgroup_bpf_run_filter_setsockopt(struct sock *sock, int *level,
+				       int *optname, char __user *optval,
+				       int *optlen, char **kernel_optval);
+int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
+				       int optname, char __user *optval,
+				       int __user *optlen, int max_optlen,
+				       int retval);
+
 static inline enum bpf_cgroup_storage_type cgroup_storage_type(
 	struct bpf_map *map)
 {
@@ -286,6 +294,38 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key,
 	__ret;								       \
 })
 
+#define BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock, level, optname, optval, optlen,   \
+				       kernel_optval)			       \
+({									       \
+	int __ret = 0;							       \
+	if (cgroup_bpf_enabled)						       \
+		__ret = __cgroup_bpf_run_filter_setsockopt(sock, level,	       \
+							   optname, optval,    \
+							   optlen,	       \
+							   kernel_optval);     \
+	__ret;								       \
+})
+
+#define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen)			       \
+({									       \
+	int __ret = 0;							       \
+	if (cgroup_bpf_enabled)						       \
+		get_user(__ret, optlen);				       \
+	__ret;								       \
+})
+
+#define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, optlen,   \
+				       max_optlen, retval)		       \
+({									       \
+	int __ret = retval;						       \
+	if (cgroup_bpf_enabled)						       \
+		__ret = __cgroup_bpf_run_filter_getsockopt(sock, level,	       \
+							   optname, optval,    \
+							   optlen, max_optlen, \
+							   retval);	       \
+	__ret;								       \
+})
+
 int cgroup_bpf_prog_attach(const union bpf_attr *attr,
 			   enum bpf_prog_type ptype, struct bpf_prog *prog);
 int cgroup_bpf_prog_detach(const union bpf_attr *attr,
@@ -357,6 +397,11 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map,
 #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type,major,minor,access) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,pos,nbuf) ({ 0; })
+#define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, \
+				       optlen, max_optlen, retval) ({ retval; })
+#define BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock, level, optname, optval, optlen, \
+				       kernel_optval) ({ 0; })
 
 #define for_each_cgroup_storage_type(stype) for (; false; )
 

include/linux/bpf.h

@@ -518,6 +518,7 @@ struct bpf_prog_array {
 struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags);
 void bpf_prog_array_free(struct bpf_prog_array *progs);
 int bpf_prog_array_length(struct bpf_prog_array *progs);
+bool bpf_prog_array_is_empty(struct bpf_prog_array *array);
 int bpf_prog_array_copy_to_user(struct bpf_prog_array *progs,
 				__u32 __user *prog_ids, u32 cnt);
 
@@ -1051,6 +1052,7 @@ extern const struct bpf_func_proto bpf_spin_unlock_proto;
 extern const struct bpf_func_proto bpf_get_local_storage_proto;
 extern const struct bpf_func_proto bpf_strtol_proto;
 extern const struct bpf_func_proto bpf_strtoul_proto;
+extern const struct bpf_func_proto bpf_tcp_sock_proto;
 
 /* Shared helpers among cBPF and eBPF. */
 void bpf_user_rnd_init_once(void);

include/linux/bpf_types.h

@@ -30,6 +30,7 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, raw_tracepoint_writable)
 #ifdef CONFIG_CGROUP_BPF
 BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev)
 BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SYSCTL, cg_sysctl)
+BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCKOPT, cg_sockopt)
 #endif
 #ifdef CONFIG_BPF_LIRC_MODE2
 BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2)

include/linux/filter.h

@@ -1199,4 +1199,14 @@ struct bpf_sysctl_kern {
 	u64 tmp_reg;
 };
 
+struct bpf_sockopt_kern {
+	struct sock	*sk;
+	u8		*optval;
+	u8		*optval_end;
+	s32		level;
+	s32		optname;
+	s32		optlen;
+	s32		retval;
+};
+
 #endif /* __LINUX_FILTER_H__ */

include/uapi/linux/bpf.h

@@ -170,6 +170,7 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_FLOW_DISSECTOR,
 	BPF_PROG_TYPE_CGROUP_SYSCTL,
 	BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE,
+	BPF_PROG_TYPE_CGROUP_SOCKOPT,
 };
 
 enum bpf_attach_type {
@@ -194,6 +195,8 @@ enum bpf_attach_type {
 	BPF_CGROUP_SYSCTL,
 	BPF_CGROUP_UDP4_RECVMSG,
 	BPF_CGROUP_UDP6_RECVMSG,
+	BPF_CGROUP_GETSOCKOPT,
+	BPF_CGROUP_SETSOCKOPT,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -3541,4 +3544,15 @@ struct bpf_sysctl {
 				 */
 };
 
+struct bpf_sockopt {
+	__bpf_md_ptr(struct bpf_sock *, sk);
+	__bpf_md_ptr(void *, optval);
+	__bpf_md_ptr(void *, optval_end);
+
+	__s32	level;
+	__s32	optname;
+	__s32	optlen;
+	__s32	retval;
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */