polyphony 0.45.0 → 0.46.0

data/ext/liburing/liburing/README.md

@@ -0,0 +1,4 @@
+## Updating the liburing source code
+
+- copy liburing/src/**/* into ext/liburing
+- move ext/liburing/include/**/* to ext/liburing/

data/ext/liburing/liburing/barrier.h

@@ -0,0 +1,73 @@
+/* SPDX-License-Identifier: MIT */
+#ifndef LIBURING_BARRIER_H
+#define LIBURING_BARRIER_H
+
+/*
+From the kernel documentation file refcount-vs-atomic.rst:
+
+A RELEASE memory ordering guarantees that all prior loads and
+stores (all po-earlier instructions) on the same CPU are completed
+before the operation. It also guarantees that all po-earlier
+stores on the same CPU and all propagated stores from other CPUs
+must propagate to all other CPUs before the release operation
+(A-cumulative property). This is implemented using
+:c:func:`smp_store_release`.
+
+An ACQUIRE memory ordering guarantees that all post loads and
+stores (all po-later instructions) on the same CPU are
+completed after the acquire operation. It also guarantees that all
+po-later stores on the same CPU must propagate to all other CPUs
+after the acquire operation executes. This is implemented using
+:c:func:`smp_acquire__after_ctrl_dep`.
+*/
+
+#ifdef __cplusplus
+#include <atomic>
+
+template <typename T>
+static inline void IO_URING_WRITE_ONCE(T &var, T val)
+{
+	std::atomic_store_explicit(reinterpret_cast<std::atomic<T> *>(&var),
+				   val, std::memory_order_relaxed);
+}
+template <typename T>
+static inline T IO_URING_READ_ONCE(const T &var)
+{
+	return std::atomic_load_explicit(
+		reinterpret_cast<const std::atomic<T> *>(&var),
+		std::memory_order_relaxed);
+}
+
+template <typename T>
+static inline void io_uring_smp_store_release(T *p, T v)
+{
+	std::atomic_store_explicit(reinterpret_cast<std::atomic<T> *>(p), v,
+				   std::memory_order_release);
+}
+
+template <typename T>
+static inline T io_uring_smp_load_acquire(const T *p)
+{
+	return std::atomic_load_explicit(
+		reinterpret_cast<const std::atomic<T> *>(p),
+		std::memory_order_acquire);
+}
+#else
+#include <stdatomic.h>
+
+#define IO_URING_WRITE_ONCE(var, val)				\
+	atomic_store_explicit((_Atomic typeof(var) *)&(var),	\
+			      (val), memory_order_relaxed)
+#define IO_URING_READ_ONCE(var)					\
+	atomic_load_explicit((_Atomic typeof(var) *)&(var),	\
+			     memory_order_relaxed)
+
+#define io_uring_smp_store_release(p, v)			\
+	atomic_store_explicit((_Atomic typeof(*(p)) *)(p), (v), \
+			      memory_order_release)
+#define io_uring_smp_load_acquire(p)				\
+	atomic_load_explicit((_Atomic typeof(*(p)) *)(p),	\
+			     memory_order_acquire)
+#endif
+
+#endif /* defined(LIBURING_BARRIER_H) */

data/ext/liburing/liburing/compat.h

@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: MIT */
+#ifndef LIBURING_COMPAT_H
+#define LIBURING_COMPAT_H
+
+#include <linux/time_types.h>
+
+#include <inttypes.h>
+
+struct open_how {
+	uint64_t	flags;
+	uint64_t	mode;
+	uint64_t	resolve;
+};
+
+#endif

data/ext/liburing/liburing/io_uring.h

@@ -0,0 +1,343 @@
+/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) OR MIT */
+/*
+ * Header file for the io_uring interface.
+ *
+ * Copyright (C) 2019 Jens Axboe
+ * Copyright (C) 2019 Christoph Hellwig
+ */
+#ifndef LINUX_IO_URING_H
+#define LINUX_IO_URING_H
+
+#include <linux/fs.h>
+#include <linux/types.h>
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/*
+ * IO submission data structure (Submission Queue Entry)
+ */
+struct io_uring_sqe {
+	__u8	opcode;		/* type of operation for this sqe */
+	__u8	flags;		/* IOSQE_ flags */
+	__u16	ioprio;		/* ioprio for the request */
+	__s32	fd;		/* file descriptor to do IO on */
+	union {
+		__u64	off;	/* offset into file */
+		__u64	addr2;
+	};
+	union {
+		__u64	addr;	/* pointer to buffer or iovecs */
+		__u64	splice_off_in;
+	};
+	__u32	len;		/* buffer size or number of iovecs */
+	union {
+		__kernel_rwf_t	rw_flags;
+		__u32		fsync_flags;
+		__u16		poll_events;	/* compatibility */
+		__u32		poll32_events;	/* word-reversed for BE */
+		__u32		sync_range_flags;
+		__u32		msg_flags;
+		__u32		timeout_flags;
+		__u32		accept_flags;
+		__u32		cancel_flags;
+		__u32		open_flags;
+		__u32		statx_flags;
+		__u32		fadvise_advice;
+		__u32		splice_flags;
+	};
+	__u64	user_data;	/* data to be passed back at completion time */
+	union {
+		struct {
+			/* pack this to avoid bogus arm OABI complaints */
+			union {
+				/* index into fixed buffers, if used */
+				__u16	buf_index;
+				/* for grouped buffer selection */
+				__u16	buf_group;
+			} __attribute__((packed));
+			/* personality to use, if used */
+			__u16	personality;
+			__s32	splice_fd_in;
+		};
+		__u64	__pad2[3];
+	};
+};
+
+enum {
+	IOSQE_FIXED_FILE_BIT,
+	IOSQE_IO_DRAIN_BIT,
+	IOSQE_IO_LINK_BIT,
+	IOSQE_IO_HARDLINK_BIT,
+	IOSQE_ASYNC_BIT,
+	IOSQE_BUFFER_SELECT_BIT,
+};
+
+/*
+ * sqe->flags
+ */
+/* use fixed fileset */
+#define IOSQE_FIXED_FILE	(1U << IOSQE_FIXED_FILE_BIT)
+/* issue after inflight IO */
+#define IOSQE_IO_DRAIN		(1U << IOSQE_IO_DRAIN_BIT)
+/* links next sqe */
+#define IOSQE_IO_LINK		(1U << IOSQE_IO_LINK_BIT)
+/* like LINK, but stronger */
+#define IOSQE_IO_HARDLINK	(1U << IOSQE_IO_HARDLINK_BIT)
+/* always go async */
+#define IOSQE_ASYNC		(1U << IOSQE_ASYNC_BIT)
+/* select buffer from sqe->buf_group */
+#define IOSQE_BUFFER_SELECT	(1U << IOSQE_BUFFER_SELECT_BIT)
+
+/*
+ * io_uring_setup() flags
+ */
+#define IORING_SETUP_IOPOLL	(1U << 0)	/* io_context is polled */
+#define IORING_SETUP_SQPOLL	(1U << 1)	/* SQ poll thread */
+#define IORING_SETUP_SQ_AFF	(1U << 2)	/* sq_thread_cpu is valid */
+#define IORING_SETUP_CQSIZE	(1U << 3)	/* app defines CQ size */
+#define IORING_SETUP_CLAMP	(1U << 4)	/* clamp SQ/CQ ring sizes */
+#define IORING_SETUP_ATTACH_WQ	(1U << 5)	/* attach to existing wq */
+#define IORING_SETUP_R_DISABLED	(1U << 6)	/* start with ring disabled */
+
+enum {
+	IORING_OP_NOP,
+	IORING_OP_READV,
+	IORING_OP_WRITEV,
+	IORING_OP_FSYNC,
+	IORING_OP_READ_FIXED,
+	IORING_OP_WRITE_FIXED,
+	IORING_OP_POLL_ADD,
+	IORING_OP_POLL_REMOVE,
+	IORING_OP_SYNC_FILE_RANGE,
+	IORING_OP_SENDMSG,
+	IORING_OP_RECVMSG,
+	IORING_OP_TIMEOUT,
+	IORING_OP_TIMEOUT_REMOVE,
+	IORING_OP_ACCEPT,
+	IORING_OP_ASYNC_CANCEL,
+	IORING_OP_LINK_TIMEOUT,
+	IORING_OP_CONNECT,
+	IORING_OP_FALLOCATE,
+	IORING_OP_OPENAT,
+	IORING_OP_CLOSE,
+	IORING_OP_FILES_UPDATE,
+	IORING_OP_STATX,
+	IORING_OP_READ,
+	IORING_OP_WRITE,
+	IORING_OP_FADVISE,
+	IORING_OP_MADVISE,
+	IORING_OP_SEND,
+	IORING_OP_RECV,
+	IORING_OP_OPENAT2,
+	IORING_OP_EPOLL_CTL,
+	IORING_OP_SPLICE,
+	IORING_OP_PROVIDE_BUFFERS,
+	IORING_OP_REMOVE_BUFFERS,
+	IORING_OP_TEE,
+	IORING_OP_SHUTDOWN,
+
+	/* this goes last, obviously */
+	IORING_OP_LAST,
+};
+
+/*
+ * sqe->fsync_flags
+ */
+#define IORING_FSYNC_DATASYNC	(1U << 0)
+
+/*
+ * sqe->timeout_flags
+ */
+#define IORING_TIMEOUT_ABS	(1U << 0)
+
+/*
+ * sqe->splice_flags
+ * extends splice(2) flags
+ */
+#define SPLICE_F_FD_IN_FIXED	(1U << 31) /* the last bit of __u32 */
+
+/*
+ * IO completion data structure (Completion Queue Entry)
+ */
+struct io_uring_cqe {
+	__u64	user_data;	/* sqe->data submission passed back */
+	__s32	res;		/* result code for this event */
+	__u32	flags;
+};
+
+/*
+ * cqe->flags
+ *
+ * IORING_CQE_F_BUFFER	If set, the upper 16 bits are the buffer ID
+ */
+#define IORING_CQE_F_BUFFER		(1U << 0)
+
+enum {
+	IORING_CQE_BUFFER_SHIFT		= 16,
+};
+
+/*
+ * Magic offsets for the application to mmap the data it needs
+ */
+#define IORING_OFF_SQ_RING		0ULL
+#define IORING_OFF_CQ_RING		0x8000000ULL
+#define IORING_OFF_SQES			0x10000000ULL
+
+/*
+ * Filled with the offset for mmap(2)
+ */
+struct io_sqring_offsets {
+	__u32 head;
+	__u32 tail;
+	__u32 ring_mask;
+	__u32 ring_entries;
+	__u32 flags;
+	__u32 dropped;
+	__u32 array;
+	__u32 resv1;
+	__u64 resv2;
+};
+
+/*
+ * sq_ring->flags
+ */
+#define IORING_SQ_NEED_WAKEUP	(1U << 0) /* needs io_uring_enter wakeup */
+#define IORING_SQ_CQ_OVERFLOW	(1U << 1) /* CQ ring is overflown */
+
+struct io_cqring_offsets {
+	__u32 head;
+	__u32 tail;
+	__u32 ring_mask;
+	__u32 ring_entries;
+	__u32 overflow;
+	__u32 cqes;
+	__u32 flags;
+	__u32 resv1;
+	__u64 resv2;
+};
+
+/*
+ * cq_ring->flags
+ */
+
+/* disable eventfd notifications */
+#define IORING_CQ_EVENTFD_DISABLED	(1U << 0)
+
+/*
+ * io_uring_enter(2) flags
+ */
+#define IORING_ENTER_GETEVENTS	(1U << 0)
+#define IORING_ENTER_SQ_WAKEUP	(1U << 1)
+#define IORING_ENTER_SQ_WAIT	(1U << 2)
+
+/*
+ * Passed in for io_uring_setup(2). Copied back with updated info on success
+ */
+struct io_uring_params {
+	__u32 sq_entries;
+	__u32 cq_entries;
+	__u32 flags;
+	__u32 sq_thread_cpu;
+	__u32 sq_thread_idle;
+	__u32 features;
+	__u32 wq_fd;
+	__u32 resv[3];
+	struct io_sqring_offsets sq_off;
+	struct io_cqring_offsets cq_off;
+};
+
+/*
+ * io_uring_params->features flags
+ */
+#define IORING_FEAT_SINGLE_MMAP		(1U << 0)
+#define IORING_FEAT_NODROP		(1U << 1)
+#define IORING_FEAT_SUBMIT_STABLE	(1U << 2)
+#define IORING_FEAT_RW_CUR_POS		(1U << 3)
+#define IORING_FEAT_CUR_PERSONALITY	(1U << 4)
+#define IORING_FEAT_FAST_POLL		(1U << 5)
+#define IORING_FEAT_POLL_32BITS 	(1U << 6)
+#define IORING_FEAT_SQPOLL_NONFIXED	(1U << 7)
+
+/*
+ * io_uring_register(2) opcodes and arguments
+ */
+enum {
+	IORING_REGISTER_BUFFERS			= 0,
+	IORING_UNREGISTER_BUFFERS		= 1,
+	IORING_REGISTER_FILES			= 2,
+	IORING_UNREGISTER_FILES			= 3,
+	IORING_REGISTER_EVENTFD			= 4,
+	IORING_UNREGISTER_EVENTFD		= 5,
+	IORING_REGISTER_FILES_UPDATE		= 6,
+	IORING_REGISTER_EVENTFD_ASYNC		= 7,
+	IORING_REGISTER_PROBE			= 8,
+	IORING_REGISTER_PERSONALITY		= 9,
+	IORING_UNREGISTER_PERSONALITY		= 10,
+	IORING_REGISTER_RESTRICTIONS		= 11,
+	IORING_REGISTER_ENABLE_RINGS		= 12,
+
+	/* this goes last */
+	IORING_REGISTER_LAST
+};
+
+struct io_uring_files_update {
+	__u32 offset;
+	__u32 resv;
+	__aligned_u64 /* __s32 * */ fds;
+};
+
+#define IO_URING_OP_SUPPORTED	(1U << 0)
+
+struct io_uring_probe_op {
+	__u8 op;
+	__u8 resv;
+	__u16 flags;	/* IO_URING_OP_* flags */
+	__u32 resv2;
+};
+
+struct io_uring_probe {
+	__u8 last_op;	/* last opcode supported */
+	__u8 ops_len;	/* length of ops[] array below */
+	__u16 resv;
+	__u32 resv2[3];
+	struct io_uring_probe_op ops[0];
+};
+
+struct io_uring_restriction {
+	__u16 opcode;
+	union {
+		__u8 register_op; /* IORING_RESTRICTION_REGISTER_OP */
+		__u8 sqe_op;      /* IORING_RESTRICTION_SQE_OP */
+		__u8 sqe_flags;   /* IORING_RESTRICTION_SQE_FLAGS_* */
+	};
+	__u8 resv;
+	__u32 resv2[3];
+};
+
+/*
+ * io_uring_restriction->opcode values
+ */
+enum {
+	/* Allow an io_uring_register(2) opcode */
+	IORING_RESTRICTION_REGISTER_OP		= 0,
+
+	/* Allow an sqe opcode */
+	IORING_RESTRICTION_SQE_OP		= 1,
+
+	/* Allow sqe flags */
+	IORING_RESTRICTION_SQE_FLAGS_ALLOWED	= 2,
+
+	/* Require sqe flags (these flags must be set on each submission) */
+	IORING_RESTRICTION_SQE_FLAGS_REQUIRED	= 3,
+
+	IORING_RESTRICTION_LAST
+};
+
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif

data/ext/liburing/queue.c

@@ -0,0 +1,333 @@
+/* SPDX-License-Identifier: MIT */
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/mman.h>
+#include <unistd.h>
+#include <errno.h>
+#include <string.h>
+#include <stdbool.h>
+
+#include "liburing/compat.h"
+#include "liburing/io_uring.h"
+#include "liburing.h"
+#include "liburing/barrier.h"
+
+#include "syscall.h"
+
+/*
+ * Returns true if we're not using SQ thread (thus nobody submits but us)
+ * or if IORING_SQ_NEED_WAKEUP is set, so submit thread must be explicitly
+ * awakened. For the latter case, we set the thread wakeup flag.
+ */
+static inline bool sq_ring_needs_enter(struct io_uring *ring, unsigned *flags)
+{
+	if (!(ring->flags & IORING_SETUP_SQPOLL))
+		return true;
+	if (IO_URING_READ_ONCE(*ring->sq.kflags) & IORING_SQ_NEED_WAKEUP) {
+		*flags |= IORING_ENTER_SQ_WAKEUP;
+		return true;
+	}
+
+	return false;
+}
+
+static inline bool cq_ring_needs_flush(struct io_uring *ring)
+{
+	return IO_URING_READ_ONCE(*ring->sq.kflags) & IORING_SQ_CQ_OVERFLOW;
+}
+
+static int __io_uring_peek_cqe(struct io_uring *ring,
+			       struct io_uring_cqe **cqe_ptr)
+{
+	struct io_uring_cqe *cqe;
+	unsigned head;
+	int err = 0;
+
+	do {
+		io_uring_for_each_cqe(ring, head, cqe)
+			break;
+		if (cqe) {
+			if (cqe->user_data == LIBURING_UDATA_TIMEOUT) {
+				if (cqe->res < 0)
+					err = cqe->res;
+				io_uring_cq_advance(ring, 1);
+				if (!err)
+					continue;
+				cqe = NULL;
+			}
+		}
+		break;
+	} while (1);
+
+	*cqe_ptr = cqe;
+	return err;
+}
+
+int __io_uring_get_cqe(struct io_uring *ring, struct io_uring_cqe **cqe_ptr,
+		       unsigned submit, unsigned wait_nr, sigset_t *sigmask)
+{
+	struct io_uring_cqe *cqe = NULL;
+	const int to_wait = wait_nr;
+	int ret = 0, err;
+
+	do {
+		bool cq_overflow_flush = false;
+		unsigned flags = 0;
+
+		err = __io_uring_peek_cqe(ring, &cqe);
+		if (err)
+			break;
+		if (!cqe && !to_wait && !submit) {
+			if (!cq_ring_needs_flush(ring)) {
+				err = -EAGAIN;
+				break;
+			}
+			cq_overflow_flush = true;
+		}
+		if (wait_nr && cqe)
+			wait_nr--;
+		if (wait_nr || cq_overflow_flush)
+			flags = IORING_ENTER_GETEVENTS;
+		if (submit)
+			sq_ring_needs_enter(ring, &flags);
+		if (wait_nr || submit || cq_overflow_flush)
+			ret = __sys_io_uring_enter(ring->ring_fd, submit,
+						   wait_nr, flags, sigmask);
+		if (ret < 0) {
+			err = -errno;
+		} else if (ret == (int)submit) {
+			submit = 0;
+			/*
+			 * When SETUP_IOPOLL is set, __sys_io_uring enter()
+			 * must be called to reap new completions but the call
+			 * won't be made if both wait_nr and submit are zero
+			 * so preserve wait_nr.
+			 */
+			if (!(ring->flags & IORING_SETUP_IOPOLL))
+				wait_nr = 0;
+		} else {
+			submit -= ret;
+		}
+		if (cqe)
+			break;
+	} while (!err);
+
+	*cqe_ptr = cqe;
+	return err;
+}
+
+/*
+ * Fill in an array of IO completions up to count, if any are available.
+ * Returns the amount of IO completions filled.
+ */
+unsigned io_uring_peek_batch_cqe(struct io_uring *ring,
+				 struct io_uring_cqe **cqes, unsigned count)
+{
+	unsigned ready;
+	bool overflow_checked = false;
+
+again:
+	ready = io_uring_cq_ready(ring);
+	if (ready) {
+		unsigned head = *ring->cq.khead;
+		unsigned mask = *ring->cq.kring_mask;
+		unsigned last;
+		int i = 0;
+
+		count = count > ready ? ready : count;
+		last = head + count;
+		for (;head != last; head++, i++)
+			cqes[i] = &ring->cq.cqes[head & mask];
+
+		return count;
+	}
+
+	if (overflow_checked)
+		goto done;
+
+	if (cq_ring_needs_flush(ring)) {
+		__sys_io_uring_enter(ring->ring_fd, 0, 0,
+				     IORING_ENTER_GETEVENTS, NULL);
+		overflow_checked = true;
+		goto again;
+	}
+
+done:
+	return 0;
+}
+
+/*
+ * Sync internal state with kernel ring state on the SQ side. Returns the
+ * number of pending items in the SQ ring, for the shared ring.
+ */
+int __io_uring_flush_sq(struct io_uring *ring)
+{
+	struct io_uring_sq *sq = &ring->sq;
+	const unsigned mask = *sq->kring_mask;
+	unsigned ktail, to_submit;
+
+	if (sq->sqe_head == sq->sqe_tail) {
+		ktail = *sq->ktail;
+		goto out;
+	}
+
+	/*
+	 * Fill in sqes that we have queued up, adding them to the kernel ring
+	 */
+	ktail = *sq->ktail;
+	to_submit = sq->sqe_tail - sq->sqe_head;
+	while (to_submit--) {
+		sq->array[ktail & mask] = sq->sqe_head & mask;
+		ktail++;
+		sq->sqe_head++;
+	}
+
+	/*
+	 * Ensure that the kernel sees the SQE updates before it sees the tail
+	 * update.
+	 */
+	io_uring_smp_store_release(sq->ktail, ktail);
+out:
+	return ktail - *sq->khead;
+}
+
+/*
+ * Like io_uring_wait_cqe(), except it accepts a timeout value as well. Note
+ * that an sqe is used internally to handle the timeout. Applications using
+ * this function must never set sqe->user_data to LIBURING_UDATA_TIMEOUT!
+ *
+ * If 'ts' is specified, the application need not call io_uring_submit() before
+ * calling this function, as we will do that on its behalf. From this it also
+ * follows that this function isn't safe to use for applications that split SQ
+ * and CQ handling between two threads and expect that to work without
+ * synchronization, as this function manipulates both the SQ and CQ side.
+ */
+int io_uring_wait_cqes(struct io_uring *ring, struct io_uring_cqe **cqe_ptr,
+		       unsigned wait_nr, struct __kernel_timespec *ts,
+		       sigset_t *sigmask)
+{
+	unsigned to_submit = 0;
+
+	if (ts) {
+		struct io_uring_sqe *sqe;
+		int ret;
+
+		/*
+		 * If the SQ ring is full, we may need to submit IO first
+		 */
+		sqe = io_uring_get_sqe(ring);
+		if (!sqe) {
+			ret = io_uring_submit(ring);
+			if (ret < 0)
+				return ret;
+			sqe = io_uring_get_sqe(ring);
+			if (!sqe)
+				return -EAGAIN;
+		}
+		io_uring_prep_timeout(sqe, ts, wait_nr, 0);
+		sqe->user_data = LIBURING_UDATA_TIMEOUT;
+		to_submit = __io_uring_flush_sq(ring);
+	}
+
+	return __io_uring_get_cqe(ring, cqe_ptr, to_submit, wait_nr, sigmask);
+}
+
+/*
+ * See io_uring_wait_cqes() - this function is the same, it just always uses
+ * '1' as the wait_nr.
+ */
+int io_uring_wait_cqe_timeout(struct io_uring *ring,
+			      struct io_uring_cqe **cqe_ptr,
+			      struct __kernel_timespec *ts)
+{
+	return io_uring_wait_cqes(ring, cqe_ptr, 1, ts, NULL);
+}
+
+/*
+ * Submit sqes acquired from io_uring_get_sqe() to the kernel.
+ *
+ * Returns number of sqes submitted
+ */
+static int __io_uring_submit(struct io_uring *ring, unsigned submitted,
+			     unsigned wait_nr)
+{
+	unsigned flags;
+	int ret;
+
+	flags = 0;
+	if (sq_ring_needs_enter(ring, &flags) || wait_nr) {
+		if (wait_nr || (ring->flags & IORING_SETUP_IOPOLL))
+			flags |= IORING_ENTER_GETEVENTS;
+
+		ret = __sys_io_uring_enter(ring->ring_fd, submitted, wait_nr,
+						flags, NULL);
+		if (ret < 0)
+			return -errno;
+	} else
+		ret = submitted;
+
+	return ret;
+}
+
+static int __io_uring_submit_and_wait(struct io_uring *ring, unsigned wait_nr)
+{
+	return __io_uring_submit(ring, __io_uring_flush_sq(ring), wait_nr);
+}
+
+/*
+ * Submit sqes acquired from io_uring_get_sqe() to the kernel.
+ *
+ * Returns number of sqes submitted
+ */
+int io_uring_submit(struct io_uring *ring)
+{
+	return __io_uring_submit_and_wait(ring, 0);
+}
+
+/*
+ * Like io_uring_submit(), but allows waiting for events as well.
+ *
+ * Returns number of sqes submitted
+ */
+int io_uring_submit_and_wait(struct io_uring *ring, unsigned wait_nr)
+{
+	return __io_uring_submit_and_wait(ring, wait_nr);
+}
+
+static inline struct io_uring_sqe *
+__io_uring_get_sqe(struct io_uring_sq *sq, unsigned int __head)
+{
+	unsigned int __next = (sq)->sqe_tail + 1;
+	struct io_uring_sqe *__sqe = NULL;
+
+	if (__next - __head <= *(sq)->kring_entries) {
+		__sqe = &(sq)->sqes[(sq)->sqe_tail & *(sq)->kring_mask];
+		(sq)->sqe_tail = __next;
+	}
+	return __sqe;
+}
+
+/*
+ * Return an sqe to fill. Application must later call io_uring_submit()
+ * when it's ready to tell the kernel about it. The caller may call this
+ * function multiple times before calling io_uring_submit().
+ *
+ * Returns a vacant sqe, or NULL if we're full.
+ */
+struct io_uring_sqe *io_uring_get_sqe(struct io_uring *ring)
+{
+	struct io_uring_sq *sq = &ring->sq;
+
+	return __io_uring_get_sqe(sq, io_uring_smp_load_acquire(sq->khead));
+}
+
+int __io_uring_sqring_wait(struct io_uring *ring)
+{
+	int ret;
+
+	ret = __sys_io_uring_enter(ring->ring_fd, 0, 0, IORING_ENTER_SQ_WAIT,
+					NULL);
+	if (ret < 0)
+		ret = -errno;
+	return ret;
+}