Merge tag 'for-6.7/io_uring-sockopt-2023-10-30' of git://git.kernel.dk/linux

Pull io_uring {get,set}sockopt support from Jens Axboe:
 "This adds support for using getsockopt and setsockopt via io_uring.

  The main use cases for this is to enable use of direct descriptors,
  rather than first instantiating a normal file descriptor, doing the
  option tweaking needed, then turning it into a direct descriptor. With
  this support, we can avoid needing a regular file descriptor
  completely.

  The net and bpf bits have been signed off on their side"

* tag 'for-6.7/io_uring-sockopt-2023-10-30' of git://git.kernel.dk/linux:
  selftests/bpf/sockopt: Add io_uring support
  io_uring/cmd: Introduce SOCKET_URING_OP_SETSOCKOPT
  io_uring/cmd: Introduce SOCKET_URING_OP_GETSOCKOPT
  io_uring/cmd: return -EOPNOTSUPP if net is disabled
  selftests/net: Extract uring helpers to be reusable
  tools headers: Grab copy of io_uring.h
  io_uring/cmd: Pass compat mode in issue_flags
  net/socket: Break down __sys_getsockopt
  net/socket: Break down __sys_setsockopt
  bpf: Add sockptr support for setsockopt
  bpf: Add sockptr support for getsockopt

4 files changed, 18 insertions, 6 deletions

diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 98b8cea904fe..a789266feac3 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -143,11 +143,12 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
 				   enum cgroup_bpf_attach_type atype);
 
 int __cgroup_bpf_run_filter_setsockopt(struct sock *sock, int *level,
-				       int *optname, char __user *optval,
+				       int *optname, sockptr_t 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 optname, sockptr_t optval,
+				       sockptr_t optlen, int max_optlen,
 				       int retval);
 
 int __cgroup_bpf_run_filter_getsockopt_kern(struct sock *sk, int level,
@@ -392,7 +393,7 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk,
 ({									       \
 	int __ret = 0;							       \
 	if (cgroup_bpf_enabled(CGROUP_GETSOCKOPT))			       \
-		get_user(__ret, optlen);				       \
+		copy_from_sockptr(&__ret, optlen, sizeof(int));		       \
 	__ret;								       \
 })
 
diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index b4391e0a9bc8..aefb73eeeebf 100644
--- a/include/linux/io_uring.h
+++ b/include/linux/io_uring.h
@@ -23,6 +23,7 @@ enum io_uring_cmd_flags {
 
 	/* set when uring wants to cancel a previously issued command */
 	IO_URING_F_CANCEL		= (1 << 11),
+	IO_URING_F_COMPAT		= (1 << 12),
 };
 
 /* only top 8 bits of sqe->uring_cmd_flags for kernel internal use */
diff --git a/include/net/sock.h b/include/net/sock.h
index 242590308d64..1d6931caf0c3 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1864,11 +1864,13 @@ int sk_setsockopt(struct sock *sk, int level, int optname,
 		  sockptr_t optval, unsigned int optlen);
 int sock_setsockopt(struct socket *sock, int level, int op,
 		    sockptr_t optval, unsigned int optlen);
+int do_sock_setsockopt(struct socket *sock, bool compat, int level,
+		       int optname, sockptr_t optval, int optlen);
+int do_sock_getsockopt(struct socket *sock, bool compat, int level,
+		       int optname, sockptr_t optval, sockptr_t optlen);
 
 int sk_getsockopt(struct sock *sk, int level, int optname,
 		  sockptr_t optval, sockptr_t optlen);
-int sock_getsockopt(struct socket *sock, int level, int op,
-		    char __user *optval, int __user *optlen);
 int sock_gettstamp(struct socket *sock, void __user *userstamp,
 		   bool timeval, bool time32);
 struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 425f64eee44e..0f7f6acd0e5a 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -43,6 +43,10 @@ struct io_uring_sqe {
 	union {
 		__u64	addr;	/* pointer to buffer or iovecs */
 		__u64	splice_off_in;
+		struct {
+			__u32	level;
+			__u32	optname;
+		};
 	};
 	__u32	len;		/* buffer size or number of iovecs */
 	union {
@@ -80,6 +84,7 @@ struct io_uring_sqe {
 	union {
 		__s32	splice_fd_in;
 		__u32	file_index;
+		__u32	optlen;
 		struct {
 			__u16	addr_len;
 			__u16	__pad3[1];
@@ -90,6 +95,7 @@ struct io_uring_sqe {
 			__u64	addr3;
 			__u64	__pad2[1];
 		};
+		__u64	optval;
 		/*
 		 * If the ring is initialized with IORING_SETUP_SQE128, then
 		 * this field is used for 80 bytes of arbitrary command data
@@ -736,6 +742,8 @@ struct io_uring_recvmsg_out {
 enum {
 	SOCKET_URING_OP_SIOCINQ		= 0,
 	SOCKET_URING_OP_SIOCOUTQ,
+	SOCKET_URING_OP_GETSOCKOPT,
+	SOCKET_URING_OP_SETSOCKOPT,
 };
 
 #ifdef __cplusplus