mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-28 11:18:45 +07:00
2b188cc1bb
The submission queue (SQ) and completion queue (CQ) rings are shared between the application and the kernel. This eliminates the need to copy data back and forth to submit and complete IO. IO submissions use the io_uring_sqe data structure, and completions are generated in the form of io_uring_cqe data structures. The SQ ring is an index into the io_uring_sqe array, which makes it possible to submit a batch of IOs without them being contiguous in the ring. The CQ ring is always contiguous, as completion events are inherently unordered, and hence any io_uring_cqe entry can point back to an arbitrary submission. Two new system calls are added for this: io_uring_setup(entries, params) Sets up an io_uring instance for doing async IO. On success, returns a file descriptor that the application can mmap to gain access to the SQ ring, CQ ring, and io_uring_sqes. io_uring_enter(fd, to_submit, min_complete, flags, sigset, sigsetsize) Initiates IO against the rings mapped to this fd, or waits for them to complete, or both. The behavior is controlled by the parameters passed in. If 'to_submit' is non-zero, then we'll try and submit new IO. If IORING_ENTER_GETEVENTS is set, the kernel will wait for 'min_complete' events, if they aren't already available. It's valid to set IORING_ENTER_GETEVENTS and 'min_complete' == 0 at the same time, this allows the kernel to return already completed events without waiting for them. This is useful only for polling, as for IRQ driven IO, the application can just check the CQ ring without entering the kernel. With this setup, it's possible to do async IO with a single system call. Future developments will enable polled IO with this interface, and polled submission as well. The latter will enable an application to do IO without doing ANY system calls at all. For IRQ driven IO, an application only needs to enter the kernel for completions if it wants to wait for them to occur. Each io_uring is backed by a workqueue, to support buffered async IO as well. We will only punt to an async context if the command would need to wait for IO on the device side. Any data that can be accessed directly in the page cache is done inline. This avoids the slowness issue of usual threadpools, since cached data is accessed as quickly as a sync interface. Sample application: http://git.kernel.dk/cgit/fio/plain/t/io_uring.c Reviewed-by: Hannes Reinecke <hare@suse.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
69 lines
1.9 KiB
C
69 lines
1.9 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _LINUX_SCHED_USER_H
|
|
#define _LINUX_SCHED_USER_H
|
|
|
|
#include <linux/uidgid.h>
|
|
#include <linux/atomic.h>
|
|
#include <linux/refcount.h>
|
|
#include <linux/ratelimit.h>
|
|
|
|
struct key;
|
|
|
|
/*
|
|
* Some day this will be a full-fledged user tracking system..
|
|
*/
|
|
struct user_struct {
|
|
refcount_t __count; /* reference count */
|
|
atomic_t processes; /* How many processes does this user have? */
|
|
atomic_t sigpending; /* How many pending signals does this user have? */
|
|
#ifdef CONFIG_FANOTIFY
|
|
atomic_t fanotify_listeners;
|
|
#endif
|
|
#ifdef CONFIG_EPOLL
|
|
atomic_long_t epoll_watches; /* The number of file descriptors currently watched */
|
|
#endif
|
|
#ifdef CONFIG_POSIX_MQUEUE
|
|
/* protected by mq_lock */
|
|
unsigned long mq_bytes; /* How many bytes can be allocated to mqueue? */
|
|
#endif
|
|
unsigned long locked_shm; /* How many pages of mlocked shm ? */
|
|
unsigned long unix_inflight; /* How many files in flight in unix sockets */
|
|
atomic_long_t pipe_bufs; /* how many pages are allocated in pipe buffers */
|
|
|
|
#ifdef CONFIG_KEYS
|
|
struct key *uid_keyring; /* UID specific keyring */
|
|
struct key *session_keyring; /* UID's default session keyring */
|
|
#endif
|
|
|
|
/* Hash table maintenance information */
|
|
struct hlist_node uidhash_node;
|
|
kuid_t uid;
|
|
|
|
#if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL) || \
|
|
defined(CONFIG_NET) || defined(CONFIG_IO_URING)
|
|
atomic_long_t locked_vm;
|
|
#endif
|
|
|
|
/* Miscellaneous per-user rate limit */
|
|
struct ratelimit_state ratelimit;
|
|
};
|
|
|
|
extern int uids_sysfs_init(void);
|
|
|
|
extern struct user_struct *find_user(kuid_t);
|
|
|
|
extern struct user_struct root_user;
|
|
#define INIT_USER (&root_user)
|
|
|
|
|
|
/* per-UID process charging. */
|
|
extern struct user_struct * alloc_uid(kuid_t);
|
|
static inline struct user_struct *get_uid(struct user_struct *u)
|
|
{
|
|
refcount_inc(&u->__count);
|
|
return u;
|
|
}
|
|
extern void free_uid(struct user_struct *);
|
|
|
|
#endif /* _LINUX_SCHED_USER_H */
|