OpenCloudOS-Kernel/include/linux/io_uring.h

98 lines
2.4 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0-or-later */
#ifndef _LINUX_IO_URING_H
#define _LINUX_IO_URING_H
#include <linux/sched.h>
#include <linux/xarray.h>
#include <uapi/linux/io_uring.h>
enum io_uring_cmd_flags {
IO_URING_F_COMPLETE_DEFER = 1,
IO_URING_F_UNLOCKED = 2,
/* int's last bit, sign checks are usually faster than a bit test */
IO_URING_F_NONBLOCK = INT_MIN,
/* ctx state flags, for URING_CMD */
IO_URING_F_SQE128 = 4,
IO_URING_F_CQE32 = 8,
IO_URING_F_IOPOLL = 16,
};
struct io_uring_cmd {
struct file *file;
const void *cmd;
union {
/* callback to defer completions to task context */
void (*task_work_cb)(struct io_uring_cmd *cmd);
/* used for polled completion */
void *cookie;
};
u32 cmd_op;
u32 flags;
u8 pdu[32]; /* available inline for free use */
};
#if defined(CONFIG_IO_URING)
int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
struct iov_iter *iter, void *ioucmd);
void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, ssize_t res2);
void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd,
void (*task_work_cb)(struct io_uring_cmd *));
struct sock *io_uring_get_socket(struct file *file);
void __io_uring_cancel(bool cancel_all);
void __io_uring_free(struct task_struct *tsk);
io_uring: add support for registering ring file descriptors Lots of workloads use multiple threads, in which case the file table is shared between them. This makes getting and putting the ring file descriptor for each io_uring_enter(2) system call more expensive, as it involves an atomic get and put for each call. Similarly to how we allow registering normal file descriptors to avoid this overhead, add support for an io_uring_register(2) API that allows to register the ring fds themselves: 1) IORING_REGISTER_RING_FDS - takes an array of io_uring_rsrc_update structs, and registers them with the task. 2) IORING_UNREGISTER_RING_FDS - takes an array of io_uring_src_update structs, and unregisters them. When a ring fd is registered, it is internally represented by an offset. This offset is returned to the application, and the application then uses this offset and sets IORING_ENTER_REGISTERED_RING for the io_uring_enter(2) system call. This works just like using a registered file descriptor, rather than a real one, in an SQE, where IOSQE_FIXED_FILE gets set to tell io_uring that we're using an internal offset/descriptor rather than a real file descriptor. In initial testing, this provides a nice bump in performance for threaded applications in real world cases where the batch count (eg number of requests submitted per io_uring_enter(2) invocation) is low. In a microbenchmark, submitting NOP requests, we see the following increases in performance: Requests per syscall Baseline Registered Increase ---------------------------------------------------------------- 1 ~7030K ~8080K +15% 2 ~13120K ~14800K +13% 4 ~22740K ~25300K +11% Co-developed-by: Xiaoguang Wang <xiaoguang.wang@linux.alibaba.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2022-03-04 23:22:22 +08:00
void io_uring_unreg_ringfd(void);
const char *io_uring_get_opcode(u8 opcode);
static inline void io_uring_files_cancel(void)
{
io_uring: add support for registering ring file descriptors Lots of workloads use multiple threads, in which case the file table is shared between them. This makes getting and putting the ring file descriptor for each io_uring_enter(2) system call more expensive, as it involves an atomic get and put for each call. Similarly to how we allow registering normal file descriptors to avoid this overhead, add support for an io_uring_register(2) API that allows to register the ring fds themselves: 1) IORING_REGISTER_RING_FDS - takes an array of io_uring_rsrc_update structs, and registers them with the task. 2) IORING_UNREGISTER_RING_FDS - takes an array of io_uring_src_update structs, and unregisters them. When a ring fd is registered, it is internally represented by an offset. This offset is returned to the application, and the application then uses this offset and sets IORING_ENTER_REGISTERED_RING for the io_uring_enter(2) system call. This works just like using a registered file descriptor, rather than a real one, in an SQE, where IOSQE_FIXED_FILE gets set to tell io_uring that we're using an internal offset/descriptor rather than a real file descriptor. In initial testing, this provides a nice bump in performance for threaded applications in real world cases where the batch count (eg number of requests submitted per io_uring_enter(2) invocation) is low. In a microbenchmark, submitting NOP requests, we see the following increases in performance: Requests per syscall Baseline Registered Increase ---------------------------------------------------------------- 1 ~7030K ~8080K +15% 2 ~13120K ~14800K +13% 4 ~22740K ~25300K +11% Co-developed-by: Xiaoguang Wang <xiaoguang.wang@linux.alibaba.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2022-03-04 23:22:22 +08:00
if (current->io_uring) {
io_uring_unreg_ringfd();
__io_uring_cancel(false);
io_uring: add support for registering ring file descriptors Lots of workloads use multiple threads, in which case the file table is shared between them. This makes getting and putting the ring file descriptor for each io_uring_enter(2) system call more expensive, as it involves an atomic get and put for each call. Similarly to how we allow registering normal file descriptors to avoid this overhead, add support for an io_uring_register(2) API that allows to register the ring fds themselves: 1) IORING_REGISTER_RING_FDS - takes an array of io_uring_rsrc_update structs, and registers them with the task. 2) IORING_UNREGISTER_RING_FDS - takes an array of io_uring_src_update structs, and unregisters them. When a ring fd is registered, it is internally represented by an offset. This offset is returned to the application, and the application then uses this offset and sets IORING_ENTER_REGISTERED_RING for the io_uring_enter(2) system call. This works just like using a registered file descriptor, rather than a real one, in an SQE, where IOSQE_FIXED_FILE gets set to tell io_uring that we're using an internal offset/descriptor rather than a real file descriptor. In initial testing, this provides a nice bump in performance for threaded applications in real world cases where the batch count (eg number of requests submitted per io_uring_enter(2) invocation) is low. In a microbenchmark, submitting NOP requests, we see the following increases in performance: Requests per syscall Baseline Registered Increase ---------------------------------------------------------------- 1 ~7030K ~8080K +15% 2 ~13120K ~14800K +13% 4 ~22740K ~25300K +11% Co-developed-by: Xiaoguang Wang <xiaoguang.wang@linux.alibaba.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2022-03-04 23:22:22 +08:00
}
}
static inline void io_uring_task_cancel(void)
{
if (current->io_uring)
__io_uring_cancel(true);
}
static inline void io_uring_free(struct task_struct *tsk)
{
if (tsk->io_uring)
__io_uring_free(tsk);
}
#else
static inline int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
struct iov_iter *iter, void *ioucmd)
{
return -EOPNOTSUPP;
}
static inline void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret,
ssize_t ret2)
{
}
static inline void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd,
void (*task_work_cb)(struct io_uring_cmd *))
{
}
static inline struct sock *io_uring_get_socket(struct file *file)
{
return NULL;
}
static inline void io_uring_task_cancel(void)
{
}
static inline void io_uring_files_cancel(void)
{
}
static inline void io_uring_free(struct task_struct *tsk)
{
}
static inline const char *io_uring_get_opcode(u8 opcode)
{
return "";
}
#endif
#endif