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

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.
  *

net/socket.c

@@ -2279,33 +2279,23 @@ static bool sock_use_custom_sol_socket(const struct socket *sock)
 	return test_bit(SOCK_CUSTOM_SOCKOPT, &sock->flags);
 }
 
-/*
- *	Set a socket option. Because we don't know the option lengths we have
- *	to pass the user mode parameter for the protocols to sort out.
- */
-int __sys_setsockopt(int fd, int level, int optname, char __user *user_optval,
-		int optlen)
+int do_sock_setsockopt(struct socket *sock, bool compat, int level,
+		       int optname, sockptr_t optval, int optlen)
 {
-	sockptr_t optval = USER_SOCKPTR(user_optval);
 	const struct proto_ops *ops;
 	char *kernel_optval = NULL;
-	int err, fput_needed;
-	struct socket *sock;
+	int err;
 
 	if (optlen < 0)
 		return -EINVAL;
 
-	sock = sockfd_lookup_light(fd, &err, &fput_needed);
-	if (!sock)
-		return err;
-
 	err = security_socket_setsockopt(sock, level, optname);
 	if (err)
 		goto out_put;
 
-	if (!in_compat_syscall())
+	if (!compat)
 		err = BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock->sk, &level, &optname,
-						     user_optval, &optlen,
+						     optval, &optlen,
 						     &kernel_optval);
 	if (err < 0)
 		goto out_put;
@@ -2326,6 +2316,27 @@ int __sys_setsockopt(int fd, int level, int optname, char __user *user_optval,
 					    optlen);
 	kfree(kernel_optval);
 out_put:
+	return err;
+}
+EXPORT_SYMBOL(do_sock_setsockopt);
+
+/* Set a socket option. Because we don't know the option lengths we have
+ * to pass the user mode parameter for the protocols to sort out.
+ */
+int __sys_setsockopt(int fd, int level, int optname, char __user *user_optval,
+		     int optlen)
+{
+	sockptr_t optval = USER_SOCKPTR(user_optval);
+	bool compat = in_compat_syscall();
+	int err, fput_needed;
+	struct socket *sock;
+
+	sock = sockfd_lookup_light(fd, &err, &fput_needed);
+	if (!sock)
+		return err;
+
+	err = do_sock_setsockopt(sock, compat, level, optname, optval, optlen);
+
 	fput_light(sock->file, fput_needed);
 	return err;
 }
@@ -2339,43 +2350,62 @@ SYSCALL_DEFINE5(setsockopt, int, fd, int, level, int, optname,
 INDIRECT_CALLABLE_DECLARE(bool tcp_bpf_bypass_getsockopt(int level,
 							 int optname));
 
-/*
- *	Get a socket option. Because we don't know the option lengths we have
- *	to pass a user mode parameter for the protocols to sort out.
- */
-int __sys_getsockopt(int fd, int level, int optname, char __user *optval,
-		int __user *optlen)
+int do_sock_getsockopt(struct socket *sock, bool compat, int level,
+		       int optname, sockptr_t optval, sockptr_t optlen)
 {
 	int max_optlen __maybe_unused;
 	const struct proto_ops *ops;
-	int err, fput_needed;
-	struct socket *sock;
-
-	sock = sockfd_lookup_light(fd, &err, &fput_needed);
-	if (!sock)
-		return err;
+	int err;
 
 	err = security_socket_getsockopt(sock, level, optname);
 	if (err)
-		goto out_put;
+		return err;
 
-	if (!in_compat_syscall())
+	if (!compat)
 		max_optlen = BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen);
 
 	ops = READ_ONCE(sock->ops);
-	if (level == SOL_SOCKET)
-		err = sock_getsockopt(sock, level, optname, optval, optlen);
-	else if (unlikely(!ops->getsockopt))
+	if (level == SOL_SOCKET) {
+		err = sk_getsockopt(sock->sk, level, optname, optval, optlen);
+	} else if (unlikely(!ops->getsockopt)) {
 		err = -EOPNOTSUPP;
-	else
-		err = ops->getsockopt(sock, level, optname, optval,
-					    optlen);
+	} else {
+		if (WARN_ONCE(optval.is_kernel || optlen.is_kernel,
+			      "Invalid argument type"))
+			return -EOPNOTSUPP;
 
-	if (!in_compat_syscall())
+		err = ops->getsockopt(sock, level, optname, optval.user,
+				      optlen.user);
+	}
+
+	if (!compat)
 		err = BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock->sk, level, optname,
 						     optval, optlen, max_optlen,
 						     err);
-out_put:
+
+	return err;
+}
+EXPORT_SYMBOL(do_sock_getsockopt);
+
+/*
+ *	Get a socket option. Because we don't know the option lengths we have
+ *	to pass a user mode parameter for the protocols to sort out.
+ */
+int __sys_getsockopt(int fd, int level, int optname, char __user *optval,
+		int __user *optlen)
+{
+	int err, fput_needed;
+	struct socket *sock;
+	bool compat;
+
+	sock = sockfd_lookup_light(fd, &err, &fput_needed);
+	if (!sock)
+		return err;
+
+	compat = in_compat_syscall();
+	err = do_sock_getsockopt(sock, compat, level, optname,
+				 USER_SOCKPTR(optval), USER_SOCKPTR(optlen));
+
 	fput_light(sock->file, fput_needed);
 	return err;
 }

tools/include/io_uring/mini_liburing.h

+/* SPDX-License-Identifier: MIT */
+
+#include <linux/io_uring.h>
+#include <sys/mman.h>
+#include <sys/syscall.h>
+#include <stdio.h>
+#include <string.h>
+#include <unistd.h>
+
+struct io_sq_ring {
+	unsigned int *head;
+	unsigned int *tail;
+	unsigned int *ring_mask;
+	unsigned int *ring_entries;
+	unsigned int *flags;
+	unsigned int *array;
+};
+
+struct io_cq_ring {
+	unsigned int *head;
+	unsigned int *tail;
+	unsigned int *ring_mask;
+	unsigned int *ring_entries;
+	struct io_uring_cqe *cqes;
+};
+
+struct io_uring_sq {
+	unsigned int *khead;
+	unsigned int *ktail;
+	unsigned int *kring_mask;
+	unsigned int *kring_entries;
+	unsigned int *kflags;
+	unsigned int *kdropped;
+	unsigned int *array;
+	struct io_uring_sqe *sqes;
+
+	unsigned int sqe_head;
+	unsigned int sqe_tail;
+
+	size_t ring_sz;
+};
+
+struct io_uring_cq {
+	unsigned int *khead;
+	unsigned int *ktail;
+	unsigned int *kring_mask;
+	unsigned int *kring_entries;
+	unsigned int *koverflow;
+	struct io_uring_cqe *cqes;
+
+	size_t ring_sz;
+};
+
+struct io_uring {
+	struct io_uring_sq sq;
+	struct io_uring_cq cq;
+	int ring_fd;
+};
+
+#if defined(__x86_64) || defined(__i386__)
+#define read_barrier()	__asm__ __volatile__("":::"memory")
+#define write_barrier()	__asm__ __volatile__("":::"memory")
+#else
+#define read_barrier()	__sync_synchronize()
+#define write_barrier()	__sync_synchronize()
+#endif
+
+static inline int io_uring_mmap(int fd, struct io_uring_params *p,
+				struct io_uring_sq *sq, struct io_uring_cq *cq)
+{
+	size_t size;
+	void *ptr;
+	int ret;
+
+	sq->ring_sz = p->sq_off.array + p->sq_entries * sizeof(unsigned int);
+	ptr = mmap(0, sq->ring_sz, PROT_READ | PROT_WRITE,
+		   MAP_SHARED | MAP_POPULATE, fd, IORING_OFF_SQ_RING);
+	if (ptr == MAP_FAILED)
+		return -errno;
+	sq->khead = ptr + p->sq_off.head;
+	sq->ktail = ptr + p->sq_off.tail;
+	sq->kring_mask = ptr + p->sq_off.ring_mask;
+	sq->kring_entries = ptr + p->sq_off.ring_entries;
+	sq->kflags = ptr + p->sq_off.flags;
+	sq->kdropped = ptr + p->sq_off.dropped;
+	sq->array = ptr + p->sq_off.array;
+
+	size = p->sq_entries * sizeof(struct io_uring_sqe);
+	sq->sqes = mmap(0, size, PROT_READ | PROT_WRITE,
+			MAP_SHARED | MAP_POPULATE, fd, IORING_OFF_SQES);
+	if (sq->sqes == MAP_FAILED) {
+		ret = -errno;
+err:
+		munmap(sq->khead, sq->ring_sz);
+		return ret;
+	}
+
+	cq->ring_sz = p->cq_off.cqes + p->cq_entries * sizeof(struct io_uring_cqe);
+	ptr = mmap(0, cq->ring_sz, PROT_READ | PROT_WRITE,
+		   MAP_SHARED | MAP_POPULATE, fd, IORING_OFF_CQ_RING);
+	if (ptr == MAP_FAILED) {
+		ret = -errno;
+		munmap(sq->sqes, p->sq_entries * sizeof(struct io_uring_sqe));
+		goto err;
+	}
+	cq->khead = ptr + p->cq_off.head;
+	cq->ktail = ptr + p->cq_off.tail;
+	cq->kring_mask = ptr + p->cq_off.ring_mask;
+	cq->kring_entries = ptr + p->cq_off.ring_entries;
+	cq->koverflow = ptr + p->cq_off.overflow;
+	cq->cqes = ptr + p->cq_off.cqes;
+	return 0;
+}
+
+static inline int io_uring_setup(unsigned int entries,
+				 struct io_uring_params *p)
+{
+	return syscall(__NR_io_uring_setup, entries, p);
+}
+
+static inline int io_uring_enter(int fd, unsigned int to_submit,
+				 unsigned int min_complete,
+				 unsigned int flags, sigset_t *sig)
+{
+	return syscall(__NR_io_uring_enter, fd, to_submit, min_complete,
+		       flags, sig, _NSIG / 8);
+}
+
+static inline int io_uring_queue_init(unsigned int entries,
+				      struct io_uring *ring,
+				      unsigned int flags)
+{
+	struct io_uring_params p;
+	int fd, ret;
+
+	memset(ring, 0, sizeof(*ring));
+	memset(&p, 0, sizeof(p));
+	p.flags = flags;
+
+	fd = io_uring_setup(entries, &p);
+	if (fd < 0)
+		return fd;
+	ret = io_uring_mmap(fd, &p, &ring->sq, &ring->cq);
+	if (!ret)
+		ring->ring_fd = fd;
+	else
+		close(fd);
+	return ret;
+}
+
+/* Get a sqe */
+static inline struct io_uring_sqe *io_uring_get_sqe(struct io_uring *ring)
+{
+	struct io_uring_sq *sq = &ring->sq;
+
+	if (sq->sqe_tail + 1 - sq->sqe_head > *sq->kring_entries)
+		return NULL;
+	return &sq->sqes[sq->sqe_tail++ & *sq->kring_mask];
+}
+
+static inline int io_uring_wait_cqe(struct io_uring *ring,
+				    struct io_uring_cqe **cqe_ptr)
+{
+	struct io_uring_cq *cq = &ring->cq;
+	const unsigned int mask = *cq->kring_mask;
+	unsigned int head = *cq->khead;
+	int ret;
+
+	*cqe_ptr = NULL;
+	do {
+		read_barrier();
+		if (head != *cq->ktail) {
+			*cqe_ptr = &cq->cqes[head & mask];
+			break;
+		}
+		ret = io_uring_enter(ring->ring_fd, 0, 1,
+				     IORING_ENTER_GETEVENTS, NULL);
+		if (ret < 0)
+			return -errno;
+	} while (1);
+
+	return 0;
+}
+
+static inline int io_uring_submit(struct io_uring *ring)
+{
+	struct io_uring_sq *sq = &ring->sq;
+	const unsigned int mask = *sq->kring_mask;
+	unsigned int ktail, submitted, to_submit;
+	int ret;
+
+	read_barrier();
+	if (*sq->khead != *sq->ktail) {
+		submitted = *sq->kring_entries;
+		goto submit;
+	}
+	if (sq->sqe_head == sq->sqe_tail)
+		return 0;
+
+	ktail = *sq->ktail;
+	to_submit = sq->sqe_tail - sq->sqe_head;
+	for (submitted = 0; submitted < to_submit; submitted++) {
+		read_barrier();
+		sq->array[ktail++ & mask] = sq->sqe_head++ & mask;
+	}
+	if (!submitted)
+		return 0;
+
+	if (*sq->ktail != ktail) {
+		write_barrier();
+		*sq->ktail = ktail;
+		write_barrier();
+	}
+submit:
+	ret = io_uring_enter(ring->ring_fd, submitted, 0,
+			     IORING_ENTER_GETEVENTS, NULL);
+	return ret < 0 ? -errno : ret;
+}
+
+static inline void io_uring_queue_exit(struct io_uring *ring)
+{
+	struct io_uring_sq *sq = &ring->sq;
+
+	munmap(sq->sqes, *sq->kring_entries * sizeof(struct io_uring_sqe));
+	munmap(sq->khead, sq->ring_sz);
+	close(ring->ring_fd);
+}
+
+/* Prepare and send the SQE */
+static inline void io_uring_prep_cmd(struct io_uring_sqe *sqe, int op,
+				     int sockfd,
+				     int level, int optname,
+				     const void *optval,
+				     int optlen)
+{
+	memset(sqe, 0, sizeof(*sqe));
+	sqe->opcode = (__u8)IORING_OP_URING_CMD;
+	sqe->fd = sockfd;
+	sqe->cmd_op = op;
+
+	sqe->level = level;
+	sqe->optname = optname;
+	sqe->optval = (unsigned long long)optval;
+	sqe->optlen = optlen;
+}
+
+static inline int io_uring_register_buffers(struct io_uring *ring,
+					    const struct iovec *iovecs,
+					    unsigned int nr_iovecs)
+{
+	int ret;
+
+	ret = syscall(__NR_io_uring_register, ring->ring_fd,
+		      IORING_REGISTER_BUFFERS, iovecs, nr_iovecs);
+	return (ret < 0) ? -errno : ret;
+}
+
+static inline void io_uring_prep_send(struct io_uring_sqe *sqe, int sockfd,
+				      const void *buf, size_t len, int flags)
+{
+	memset(sqe, 0, sizeof(*sqe));
+	sqe->opcode = (__u8)IORING_OP_SEND;
+	sqe->fd = sockfd;
+	sqe->addr = (unsigned long)buf;
+	sqe->len = len;
+	sqe->msg_flags = (__u32)flags;
+}
+
+static inline void io_uring_prep_sendzc(struct io_uring_sqe *sqe, int sockfd,
+					const void *buf, size_t len, int flags,
+					unsigned int zc_flags)
+{
+	io_uring_prep_send(sqe, sockfd, buf, len, flags);
+	sqe->opcode = (__u8)IORING_OP_SEND_ZC;
+	sqe->ioprio = zc_flags;
+}
+
+static inline void io_uring_cqe_seen(struct io_uring *ring)
+{
+	*(&ring->cq)->khead += 1;
+	write_barrier();
+}

tools/testing/selftests/bpf/prog_tests/sockopt.c

 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
+#include <io_uring/mini_liburing.h>
 #include "cgroup_helpers.h"
 
 static char bpf_log_buf[4096];
@@ -38,6 +39,7 @@ static struct sockopt_test {
 	socklen_t			get_optlen_ret;
 
 	enum sockopt_test_error		error;
+	bool				io_uring_support;
 } tests[] = {
 
 	/* ==================== getsockopt ====================  */
@@ -251,7 +253,9 @@ static struct sockopt_test {
 		.attach_type = BPF_CGROUP_GETSOCKOPT,
 		.expected_attach_type = BPF_CGROUP_GETSOCKOPT,
 
+		.get_level = SOL_SOCKET,
 		.get_optlen = 64,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "getsockopt: deny bigger ctx->optlen",
@@ -276,6 +280,7 @@ static struct sockopt_test {
 		.get_optlen = 64,
 
 		.error = EFAULT_GETSOCKOPT,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "getsockopt: ignore >PAGE_SIZE optlen",
@@ -318,6 +323,7 @@ static struct sockopt_test {
 		.get_optval = {}, /* the changes are ignored */
 		.get_optlen = PAGE_SIZE + 1,
 		.error = EOPNOTSUPP_GETSOCKOPT,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "getsockopt: support smaller ctx->optlen",
@@ -337,8 +343,10 @@ static struct sockopt_test {
 		.attach_type = BPF_CGROUP_GETSOCKOPT,
 		.expected_attach_type = BPF_CGROUP_GETSOCKOPT,
 
+		.get_level = SOL_SOCKET,
 		.get_optlen = 64,
 		.get_optlen_ret = 32,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "getsockopt: deny writing to ctx->optval",
@@ -518,6 +526,7 @@ static struct sockopt_test {
 		.set_level = 123,
 
 		.set_optlen = 1,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "setsockopt: allow changing ctx->level",
@@ -572,6 +581,7 @@ static struct sockopt_test {
 		.set_optname = 123,
 
 		.set_optlen = 1,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "setsockopt: allow changing ctx->optname",
@@ -624,6 +634,7 @@ static struct sockopt_test {
 		.expected_attach_type = BPF_CGROUP_SETSOCKOPT,
 
 		.set_optlen = 64,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "setsockopt: ctx->optlen == -1 is ok",
@@ -640,6 +651,7 @@ static struct sockopt_test {
 		.expected_attach_type = BPF_CGROUP_SETSOCKOPT,
 
 		.set_optlen = 64,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "setsockopt: deny ctx->optlen < 0 (except -1)",
@@ -658,6 +670,7 @@ static struct sockopt_test {
 		.set_optlen = 4,
 
 		.error = EFAULT_SETSOCKOPT,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "setsockopt: deny ctx->optlen > input optlen",
@@ -675,6 +688,7 @@ static struct sockopt_test {
 		.set_optlen = 64,
 
 		.error = EFAULT_SETSOCKOPT,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "setsockopt: ignore >PAGE_SIZE optlen",
@@ -940,7 +954,89 @@ static int load_prog(const struct bpf_insn *insns,
 	return fd;
 }
 
-static int run_test(int cgroup_fd, struct sockopt_test *test)
+/* Core function that handles io_uring ring initialization,
+ * sending SQE with sockopt command and waiting for the CQE.
+ */
+static int uring_sockopt(int op, int fd, int level, int optname,
+			 const void *optval, socklen_t optlen)
+{
+	struct io_uring_cqe *cqe;
+	struct io_uring_sqe *sqe;
+	struct io_uring ring;
+	int err;
+
+	err = io_uring_queue_init(1, &ring, 0);
+	if (!ASSERT_OK(err, "io_uring initialization"))
+		return err;
+
+	sqe = io_uring_get_sqe(&ring);
+	if (!ASSERT_NEQ(sqe, NULL, "Get an SQE")) {
+		err = -1;
+		goto fail;
+	}
+
+	io_uring_prep_cmd(sqe, op, fd, level, optname, optval, optlen);
+
+	err = io_uring_submit(&ring);
+	if (!ASSERT_EQ(err, 1, "Submit SQE"))
+		goto fail;
+
+	err = io_uring_wait_cqe(&ring, &cqe);
+	if (!ASSERT_OK(err, "Wait for CQE"))
+		goto fail;
+
+	err = cqe->res;
+
+fail:
+	io_uring_queue_exit(&ring);
+
+	return err;
+}
+
+static int uring_setsockopt(int fd, int level, int optname, const void *optval,
+			    socklen_t optlen)
+{
+	return uring_sockopt(SOCKET_URING_OP_SETSOCKOPT, fd, level, optname,
+			     optval, optlen);
+}
+
+static int uring_getsockopt(int fd, int level, int optname, void *optval,
+			    socklen_t *optlen)
+{
+	int ret = uring_sockopt(SOCKET_URING_OP_GETSOCKOPT, fd, level, optname,
+				optval, *optlen);
+	if (ret < 0)
+		return ret;
+
+	/* Populate optlen back to be compatible with systemcall interface,
+	 * and simplify the test.
+	 */
+	*optlen = ret;
+
+	return 0;
+}
+
+/* Execute the setsocktopt operation */
+static int call_setsockopt(bool use_io_uring, int fd, int level, int optname,
+			   const void *optval, socklen_t optlen)
+{
+	if (use_io_uring)
+		return uring_setsockopt(fd, level, optname, optval, optlen);
+
+	return setsockopt(fd, level, optname, optval, optlen);
+}
+
+/* Execute the getsocktopt operation */
+static int call_getsockopt(bool use_io_uring, int fd, int level, int optname,
+			   void *optval, socklen_t *optlen)
+{
+	if (use_io_uring)
+		return uring_getsockopt(fd, level, optname, optval, optlen);
+
+	return getsockopt(fd, level, optname, optval, optlen);
+}
+
+static int run_test(int cgroup_fd, struct sockopt_test *test, bool use_io_uring)
 {
 	int sock_fd, err, prog_fd;
 	void *optval = NULL;
@@ -980,8 +1076,9 @@ static int run_test(int cgroup_fd, struct sockopt_test *test)
 			test->set_optlen = num_pages * sysconf(_SC_PAGESIZE) + remainder;
 		}
 
-		err = setsockopt(sock_fd, test->set_level, test->set_optname,
-				 test->set_optval, test->set_optlen);
+		err = call_setsockopt(use_io_uring, sock_fd, test->set_level,
+				      test->set_optname, test->set_optval,
+				      test->set_optlen);
 		if (err) {
 			if (errno == EPERM && test->error == EPERM_SETSOCKOPT)
 				goto close_sock_fd;
@@ -1008,8 +1105,8 @@ static int run_test(int cgroup_fd, struct sockopt_test *test)
 		socklen_t expected_get_optlen = test->get_optlen_ret ?:
 			test->get_optlen;
 
-		err = getsockopt(sock_fd, test->get_level, test->get_optname,
-				 optval, &optlen);
+		err = call_getsockopt(use_io_uring, sock_fd, test->get_level,
+				      test->get_optname, optval, &optlen);
 		if (err) {
 			if (errno == EOPNOTSUPP && test->error == EOPNOTSUPP_GETSOCKOPT)
 				goto free_optval;
@@ -1063,7 +1160,11 @@ void test_sockopt(void)
 		if (!test__start_subtest(tests[i].descr))
 			continue;
 
-		ASSERT_OK(run_test(cgroup_fd, &tests[i]), tests[i].descr);
+		ASSERT_OK(run_test(cgroup_fd, &tests[i], false),
+			  tests[i].descr);
+		if (tests[i].io_uring_support)
+			ASSERT_OK(run_test(cgroup_fd, &tests[i], true),
+				  tests[i].descr);
 	}
 
 	close(cgroup_fd);

tools/testing/selftests/net/Makefile

@@ -100,6 +100,7 @@ $(OUTPUT)/reuseport_bpf_numa: LDLIBS += -lnuma
 $(OUTPUT)/tcp_mmap: LDLIBS += -lpthread -lcrypto
 $(OUTPUT)/tcp_inq: LDLIBS += -lpthread
 $(OUTPUT)/bind_bhash: LDLIBS += -lpthread
+$(OUTPUT)/io_uring_zerocopy_tx: CFLAGS += -I../../../include/
 
 # Rules to generate bpf obj nat6to4.o
 CLANG ?= clang

tools/testing/selftests/net/io_uring_zerocopy_tx.c

@@ -36,6 +36,8 @@
 #include <sys/un.h>
 #include <sys/wait.h>
 
+#include <io_uring/mini_liburing.h>
+
 #define NOTIF_TAG 0xfffffffULL
 #define NONZC_TAG 0
 #define ZC_TAG 1
@@ -60,272 +62,6 @@ static struct sockaddr_storage cfg_dst_addr;
 
 static char payload[IP_MAXPACKET] __attribute__((aligned(4096)));
 
-struct io_sq_ring {
-	unsigned *head;
-	unsigned *tail;
-	unsigned *ring_mask;
-	unsigned *ring_entries;
-	unsigned *flags;
-	unsigned *array;
-};
-
-struct io_cq_ring {
-	unsigned *head;
-	unsigned *tail;
-	unsigned *ring_mask;
-	unsigned *ring_entries;
-	struct io_uring_cqe *cqes;
-};
-
-struct io_uring_sq {
-	unsigned *khead;
-	unsigned *ktail;
-	unsigned *kring_mask;
-	unsigned *kring_entries;
-	unsigned *kflags;
-	unsigned *kdropped;
-	unsigned *array;
-	struct io_uring_sqe *sqes;
-
-	unsigned sqe_head;
-	unsigned sqe_tail;
-
-	size_t ring_sz;
-};
-
-struct io_uring_cq {
-	unsigned *khead;
-	unsigned *ktail;
-	unsigned *kring_mask;
-	unsigned *kring_entries;
-	unsigned *koverflow;
-	struct io_uring_cqe *cqes;
-
-	size_t ring_sz;
-};
-
-struct io_uring {
-	struct io_uring_sq sq;
-	struct io_uring_cq cq;
-	int ring_fd;
-};
-
-#ifdef __alpha__
-# ifndef __NR_io_uring_setup
-#  define __NR_io_uring_setup		535
-# endif
-# ifndef __NR_io_uring_enter
-#  define __NR_io_uring_enter		536
-# endif
-# ifndef __NR_io_uring_register
-#  define __NR_io_uring_register	537
-# endif
-#else /* !__alpha__ */
-# ifndef __NR_io_uring_setup
-#  define __NR_io_uring_setup		425
-# endif
-# ifndef __NR_io_uring_enter
-#  define __NR_io_uring_enter		426
-# endif
-# ifndef __NR_io_uring_register
-#  define __NR_io_uring_register	427
-# endif
-#endif
-
-#if defined(__x86_64) || defined(__i386__)
-#define read_barrier()	__asm__ __volatile__("":::"memory")
-#define write_barrier()	__asm__ __volatile__("":::"memory")
-#else
-
-#define read_barrier()	__sync_synchronize()
-#define write_barrier()	__sync_synchronize()
-#endif
-
-static int io_uring_setup(unsigned int entries, struct io_uring_params *p)
-{
-	return syscall(__NR_io_uring_setup, entries, p);
-}
-
-static int io_uring_enter(int fd, unsigned int to_submit,
-			  unsigned int min_complete,
-			  unsigned int flags, sigset_t *sig)
-{
-	return syscall(__NR_io_uring_enter, fd, to_submit, min_complete,
-			flags, sig, _NSIG / 8);
-}
-
-static int io_uring_register_buffers(struct io_uring *ring,
-				     const struct iovec *iovecs,
-				     unsigned nr_iovecs)
-{
-	int ret;
-
-	ret = syscall(__NR_io_uring_register, ring->ring_fd,
-		      IORING_REGISTER_BUFFERS, iovecs, nr_iovecs);
-	return (ret < 0) ? -errno : ret;
-}
-
-static int io_uring_mmap(int fd, struct io_uring_params *p,
-			 struct io_uring_sq *sq, struct io_uring_cq *cq)
-{
-	size_t size;
-	void *ptr;
-	int ret;
-
-	sq->ring_sz = p->sq_off.array + p->sq_entries * sizeof(unsigned);
-	ptr = mmap(0, sq->ring_sz, PROT_READ | PROT_WRITE,
-		   MAP_SHARED | MAP_POPULATE, fd, IORING_OFF_SQ_RING);
-	if (ptr == MAP_FAILED)
-		return -errno;
-	sq->khead = ptr + p->sq_off.head;
-	sq->ktail = ptr + p->sq_off.tail;
-	sq->kring_mask = ptr + p->sq_off.ring_mask;
-	sq->kring_entries = ptr + p->sq_off.ring_entries;
-	sq->kflags = ptr + p->sq_off.flags;
-	sq->kdropped = ptr + p->sq_off.dropped;
-	sq->array = ptr + p->sq_off.array;
-
-	size = p->sq_entries * sizeof(struct io_uring_sqe);
-	sq->sqes = mmap(0, size, PROT_READ | PROT_WRITE,
-			MAP_SHARED | MAP_POPULATE, fd, IORING_OFF_SQES);
-	if (sq->sqes == MAP_FAILED) {
-		ret = -errno;
-err:
-		munmap(sq->khead, sq->ring_sz);
-		return ret;
-	}
-
-	cq->ring_sz = p->cq_off.cqes + p->cq_entries * sizeof(struct io_uring_cqe);
-	ptr = mmap(0, cq->ring_sz, PROT_READ | PROT_WRITE,
-			MAP_SHARED | MAP_POPULATE, fd, IORING_OFF_CQ_RING);
-	if (ptr == MAP_FAILED) {
-		ret = -errno;
-		munmap(sq->sqes, p->sq_entries * sizeof(struct io_uring_sqe));
-		goto err;
-	}
-	cq->khead = ptr + p->cq_off.head;
-	cq->ktail = ptr + p->cq_off.tail;
-	cq->kring_mask = ptr + p->cq_off.ring_mask;
-	cq->kring_entries = ptr + p->cq_off.ring_entries;
-	cq->koverflow = ptr + p->cq_off.overflow;
-	cq->cqes = ptr + p->cq_off.cqes;
-	return 0;
-}
-
-static int io_uring_queue_init(unsigned entries, struct io_uring *ring,
-			       unsigned flags)
-{
-	struct io_uring_params p;
-	int fd, ret;
-
-	memset(ring, 0, sizeof(*ring));
-	memset(&p, 0, sizeof(p));
-	p.flags = flags;
-
-	fd = io_uring_setup(entries, &p);
-	if (fd < 0)
-		return fd;
-	ret = io_uring_mmap(fd, &p, &ring->sq, &ring->cq);
-	if (!ret)
-		ring->ring_fd = fd;
-	else
-		close(fd);
-	return ret;
-}
-
-static int io_uring_submit(struct io_uring *ring)
-{
-	struct io_uring_sq *sq = &ring->sq;
-	const unsigned mask = *sq->kring_mask;
-	unsigned ktail, submitted, to_submit;
-	int ret;
-
-	read_barrier();
-	if (*sq->khead != *sq->ktail) {
-		submitted = *sq->kring_entries;
-		goto submit;
-	}
-	if (sq->sqe_head == sq->sqe_tail)
-		return 0;
-
-	ktail = *sq->ktail;
-	to_submit = sq->sqe_tail - sq->sqe_head;
-	for (submitted = 0; submitted < to_submit; submitted++) {
-		read_barrier();
-		sq->array[ktail++ & mask] = sq->sqe_head++ & mask;
-	}
-	if (!submitted)
-		return 0;
-
-	if (*sq->ktail != ktail) {
-		write_barrier();
-		*sq->ktail = ktail;
-		write_barrier();
-	}
-submit:
-	ret = io_uring_enter(ring->ring_fd, submitted, 0,
-				IORING_ENTER_GETEVENTS, NULL);
-	return ret < 0 ? -errno : ret;
-}
-
-static inline void io_uring_prep_send(struct io_uring_sqe *sqe, int sockfd,
-				      const void *buf, size_t len, int flags)
-{
-	memset(sqe, 0, sizeof(*sqe));
-	sqe->opcode = (__u8) IORING_OP_SEND;
-	sqe->fd = sockfd;
-	sqe->addr = (unsigned long) buf;
-	sqe->len = len;
-	sqe->msg_flags = (__u32) flags;
-}
-
-static inline void io_uring_prep_sendzc(struct io_uring_sqe *sqe, int sockfd,
-				        const void *buf, size_t len, int flags,
-				        unsigned zc_flags)
-{
-	io_uring_prep_send(sqe, sockfd, buf, len, flags);
-	sqe->opcode = (__u8) IORING_OP_SEND_ZC;
-	sqe->ioprio = zc_flags;
-}
-
-static struct io_uring_sqe *io_uring_get_sqe(struct io_uring *ring)
-{
-	struct io_uring_sq *sq = &ring->sq;
-
-	if (sq->sqe_tail + 1 - sq->sqe_head > *sq->kring_entries)
-		return NULL;
-	return &sq->sqes[sq->sqe_tail++ & *sq->kring_mask];
-}
-
-static int io_uring_wait_cqe(struct io_uring *ring, struct io_uring_cqe **cqe_ptr)
-{
-	struct io_uring_cq *cq = &ring->cq;
-	const unsigned mask = *cq->kring_mask;
-	unsigned head = *cq->khead;
-	int ret;
-
-	*cqe_ptr = NULL;
-	do {
-		read_barrier();
-		if (head != *cq->ktail) {
-			*cqe_ptr = &cq->cqes[head & mask];
-			break;
-		}
-		ret = io_uring_enter(ring->ring_fd, 0, 1,
-					IORING_ENTER_GETEVENTS, NULL);
-		if (ret < 0)
-			return -errno;
-	} while (1);
-
-	return 0;
-}
-
-static inline void io_uring_cqe_seen(struct io_uring *ring)
-{
-	*(&ring->cq)->khead += 1;
-	write_barrier();
-}
-
 static unsigned long gettimeofday_ms(void)
 {
 	struct timeval tv;