bpf: Remove extra lock_sock for TCP_ZEROCOPY_RECEIVE

Add custom implementation of getsockopt hook for TCP_ZEROCOPY_RECEIVE.
We skip generic hooks for TCP_ZEROCOPY_RECEIVE and have a custom
call in do_tcp_getsockopt using the on-stack data. This removes
3% overhead for locking/unlocking the socket.

Without this patch:
     3.38%     0.07%  tcp_mmap  [kernel.kallsyms]  [k] __cgroup_bpf_run_filter_getsockopt
            |
             --3.30%--__cgroup_bpf_run_filter_getsockopt
                       |
                        --0.81%--__kmalloc

With the patch applied:
     0.52%     0.12%  tcp_mmap  [kernel.kallsyms]  [k] __cgroup_bpf_run_filter_getsockopt_kern

Note, exporting uapi/tcp.h requires removing netinet/tcp.h
from test_progs.h because those headers have confliciting
definitions.

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20210115163501.805133-2-sdf@google.com

4 files changed, 32 insertions, 4 deletions

diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 72e69a0e1e8c..bcb2915e6124 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -147,6 +147,10 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
 				       int __user *optlen, int max_optlen,
 				       int retval);
 
+int __cgroup_bpf_run_filter_getsockopt_kern(struct sock *sk, int level,
+					    int optname, void *optval,
+					    int *optlen, int retval);
+
 static inline enum bpf_cgroup_storage_type cgroup_storage_type(
 	struct bpf_map *map)
 {
@@ -364,10 +368,23 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key,
 ({									       \
 	int __ret = retval;						       \
 	if (cgroup_bpf_enabled)						       \
-		__ret = __cgroup_bpf_run_filter_getsockopt(sock, level,	       \
-							   optname, optval,    \
-							   optlen, max_optlen, \
-							   retval);	       \
+		if (!(sock)->sk_prot->bpf_bypass_getsockopt ||		       \
+		    !INDIRECT_CALL_INET_1((sock)->sk_prot->bpf_bypass_getsockopt, \
+					tcp_bpf_bypass_getsockopt,	       \
+					level, optname))		       \
+			__ret = __cgroup_bpf_run_filter_getsockopt(	       \
+				sock, level, optname, optval, optlen,	       \
+				max_optlen, retval);			       \
+	__ret;								       \
+})
+
+#define BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sock, level, optname, optval,      \
+					    optlen, retval)		       \
+({									       \
+	int __ret = retval;						       \
+	if (cgroup_bpf_enabled)						       \
+		__ret = __cgroup_bpf_run_filter_getsockopt_kern(	       \
+			sock, level, optname, optval, optlen, retval);	       \
 	__ret;								       \
 })
 
@@ -452,6 +469,8 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map,
 #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_GETSOCKOPT_KERN(sock, level, optname, optval, \
+					    optlen, retval) ({ retval; })
 #define BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock, level, optname, optval, optlen, \
 				       kernel_optval) ({ 0; })
 
diff --git a/include/linux/indirect_call_wrapper.h b/include/linux/indirect_call_wrapper.h
index 54c02c84906a..cfcfef37b2f1 100644
--- a/include/linux/indirect_call_wrapper.h
+++ b/include/linux/indirect_call_wrapper.h
@@ -60,4 +60,10 @@
 #define INDIRECT_CALL_INET(f, f2, f1, ...) f(__VA_ARGS__)
 #endif
 
+#if IS_ENABLED(CONFIG_INET)
+#define INDIRECT_CALL_INET_1(f, f1, ...) INDIRECT_CALL_1(f, f1, __VA_ARGS__)
+#else
+#define INDIRECT_CALL_INET_1(f, f1, ...) f(__VA_ARGS__)
+#endif
+
 #endif
diff --git a/include/net/sock.h b/include/net/sock.h
index 129d200bccb4..7644ea64a376 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1174,6 +1174,8 @@ struct proto {
 
 	int			(*backlog_rcv) (struct sock *sk,
 						struct sk_buff *skb);
+	bool			(*bpf_bypass_getsockopt)(int level,
+							 int optname);
 
 	void		(*release_cb)(struct sock *sk);
 
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 78d13c88720f..4bb42fb19711 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -403,6 +403,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock,
 		      struct poll_table_struct *wait);
 int tcp_getsockopt(struct sock *sk, int level, int optname,
 		   char __user *optval, int __user *optlen);
+bool tcp_bpf_bypass_getsockopt(int level, int optname);
 int tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
 		   unsigned int optlen);
 void tcp_set_keepalive(struct sock *sk, int val);