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

Author: torvalds

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;								       \
 })
 

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 */

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,

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

io_uring/uring_cmd.c

@@ -175,6 +175,8 @@ int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags)
 		issue_flags |= IO_URING_F_SQE128;
 	if (ctx->flags & IORING_SETUP_CQE32)
 		issue_flags |= IO_URING_F_CQE32;
+	if (ctx->compat)
+		issue_flags |= IO_URING_F_COMPAT;
 	if (ctx->flags & IORING_SETUP_IOPOLL) {
 		if (!file->f_op->uring_cmd_iopoll)
 			return -EOPNOTSUPP;
@@ -212,6 +214,52 @@ int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
 }
 EXPORT_SYMBOL_GPL(io_uring_cmd_import_fixed);
 
+static inline int io_uring_cmd_getsockopt(struct socket *sock,
+					  struct io_uring_cmd *cmd,
+					  unsigned int issue_flags)
+{
+	bool compat = !!(issue_flags & IO_URING_F_COMPAT);
+	int optlen, optname, level, err;
+	void __user *optval;
+
+	level = READ_ONCE(cmd->sqe->level);
+	if (level != SOL_SOCKET)
+		return -EOPNOTSUPP;
+
+	optval = u64_to_user_ptr(READ_ONCE(cmd->sqe->optval));
+	optname = READ_ONCE(cmd->sqe->optname);
+	optlen = READ_ONCE(cmd->sqe->optlen);
+
+	err = do_sock_getsockopt(sock, compat, level, optname,
+				 USER_SOCKPTR(optval),
+				 KERNEL_SOCKPTR(&optlen));
+	if (err)
+		return err;
+
+	/* On success, return optlen */
+	return optlen;
+}
+
+static inline int io_uring_cmd_setsockopt(struct socket *sock,
+					  struct io_uring_cmd *cmd,
+					  unsigned int issue_flags)
+{
+	bool compat = !!(issue_flags & IO_URING_F_COMPAT);
+	int optname, optlen, level;
+	void __user *optval;
+	sockptr_t optval_s;
+
+	optval = u64_to_user_ptr(READ_ONCE(cmd->sqe->optval));
+	optname = READ_ONCE(cmd->sqe->optname);
+	optlen = READ_ONCE(cmd->sqe->optlen);
+	level = READ_ONCE(cmd->sqe->level);
+	optval_s = USER_SOCKPTR(optval);
+
+	return do_sock_setsockopt(sock, compat, level, optname, optval_s,
+				  optlen);
+}
+
+#if defined(CONFIG_NET)
 int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags)
 {
 	struct socket *sock = cmd->file->private_data;
@@ -233,8 +281,13 @@ int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags)
 		if (ret)
 			return ret;
 		return arg;
+	case SOCKET_URING_OP_GETSOCKOPT:
+		return io_uring_cmd_getsockopt(sock, cmd, issue_flags);
+	case SOCKET_URING_OP_SETSOCKOPT:
+		return io_uring_cmd_setsockopt(sock, cmd, issue_flags);
 	default:
 		return -EOPNOTSUPP;
 	}
 }
 EXPORT_SYMBOL_GPL(io_uring_cmd_sock);
+#endif

kernel/bpf/cgroup.c

@@ -1800,7 +1800,7 @@ static bool sockopt_buf_allocated(struct bpf_sockopt_kern *ctx,
 }
 
 int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level,
-				       int *optname, char __user *optval,
+				       int *optname, sockptr_t optval,
 				       int *optlen, char **kernel_optval)
 {
 	struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
@@ -1823,7 +1823,8 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level,
 
 	ctx.optlen = *optlen;
 
-	if (copy_from_user(ctx.optval, optval, min(*optlen, max_optlen)) != 0) {
+	if (copy_from_sockptr(ctx.optval, optval,
+			      min(*optlen, max_optlen))) {
 		ret = -EFAULT;
 		goto out;
 	}
@@ -1890,8 +1891,8 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level,
 }
 
 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)
 {
 	struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
@@ -1918,8 +1919,8 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
 		 * one that kernel returned as well to let
 		 * BPF programs inspect the value.
 		 */
-
-		if (get_user(ctx.optlen, optlen)) {
+		if (copy_from_sockptr(&ctx.optlen, optlen,
+				      sizeof(ctx.optlen))) {
 			ret = -EFAULT;
 			goto out;
 		}
@@ -1930,8 +1931,8 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
 		}
 		orig_optlen = ctx.optlen;
 
-		if (copy_from_user(ctx.optval, optval,
-				   min(ctx.optlen, max_optlen)) != 0) {
+		if (copy_from_sockptr(ctx.optval, optval,
+				      min(ctx.optlen, max_optlen))) {
 			ret = -EFAULT;
 			goto out;
 		}
@@ -1945,7 +1946,8 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
 	if (ret < 0)
 		goto out;
 
-	if (optval && (ctx.optlen > max_optlen || ctx.optlen < 0)) {
+	if (!sockptr_is_null(optval) &&
+	    (ctx.optlen > max_optlen || ctx.optlen < 0)) {
 		if (orig_optlen > PAGE_SIZE && ctx.optlen >= 0) {
 			pr_info_once("bpf getsockopt: ignoring program buffer with optlen=%d (max_optlen=%d)\n",
 				     ctx.optlen, max_optlen);
@@ -1957,11 +1959,12 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
 	}
 
 	if (ctx.optlen != 0) {
-		if (optval && copy_to_user(optval, ctx.optval, ctx.optlen)) {
+		if (!sockptr_is_null(optval) &&
+		    copy_to_sockptr(optval, ctx.optval, ctx.optlen)) {
 			ret = -EFAULT;
 			goto out;
 		}
-		if (put_user(ctx.optlen, optlen)) {
+		if (copy_to_sockptr(optlen, &ctx.optlen, sizeof(ctx.optlen))) {
 			ret = -EFAULT;
 			goto out;
 		}

net/core/sock.c

@@ -2003,14 +2003,6 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
 	return 0;
 }
 
-int sock_getsockopt(struct socket *sock, int level, int optname,
-		    char __user *optval, int __user *optlen)
-{
-	return sk_getsockopt(sock->sk, level, optname,
-			     USER_SOCKPTR(optval),
-			     USER_SOCKPTR(optlen));
-}
-
 /*
  * Initialize an sk_lock.
  *