io_uring: add io_uring_types.h
This adds definitions of structs that both the core and the various opcode handlers need to know about. Signed-off-by: Jens Axboe <axboe@kernel.dk>
This commit is contained in:
Jens Axboe
parent
4d4c9cff4f
commit
e27f928ee1
|
|
@ -90,6 +90,8 @@
|
|||
#include "../fs/internal.h"
|
||||
#include "io-wq.h"
|
||||
|
||||
#include "io_uring_types.h"
|
||||
|
||||
#define IORING_MAX_ENTRIES 32768
|
||||
#define IORING_MAX_CQ_ENTRIES (2 * IORING_MAX_ENTRIES)
|
||||
#define IORING_SQPOLL_CAP_ENTRIES_VALUE 8
|
||||
|
|
@ -122,89 +124,6 @@
|
|||
|
||||
#define IO_TCTX_REFS_CACHE_NR (1U << 10)
|
||||
|
||||
struct io_uring {
|
||||
u32 head ____cacheline_aligned_in_smp;
|
||||
u32 tail ____cacheline_aligned_in_smp;
|
||||
};
|
||||
|
||||
/*
|
||||
* This data is shared with the application through the mmap at offsets
|
||||
* IORING_OFF_SQ_RING and IORING_OFF_CQ_RING.
|
||||
*
|
||||
* The offsets to the member fields are published through struct
|
||||
* io_sqring_offsets when calling io_uring_setup.
|
||||
*/
|
||||
struct io_rings {
|
||||
/*
|
||||
* Head and tail offsets into the ring; the offsets need to be
|
||||
* masked to get valid indices.
|
||||
*
|
||||
* The kernel controls head of the sq ring and the tail of the cq ring,
|
||||
* and the application controls tail of the sq ring and the head of the
|
||||
* cq ring.
|
||||
*/
|
||||
struct io_uring sq, cq;
|
||||
/*
|
||||
* Bitmasks to apply to head and tail offsets (constant, equals
|
||||
* ring_entries - 1)
|
||||
*/
|
||||
u32 sq_ring_mask, cq_ring_mask;
|
||||
/* Ring sizes (constant, power of 2) */
|
||||
u32 sq_ring_entries, cq_ring_entries;
|
||||
/*
|
||||
* Number of invalid entries dropped by the kernel due to
|
||||
* invalid index stored in array
|
||||
*
|
||||
* Written by the kernel, shouldn't be modified by the
|
||||
* application (i.e. get number of "new events" by comparing to
|
||||
* cached value).
|
||||
*
|
||||
* After a new SQ head value was read by the application this
|
||||
* counter includes all submissions that were dropped reaching
|
||||
* the new SQ head (and possibly more).
|
||||
*/
|
||||
u32 sq_dropped;
|
||||
/*
|
||||
* Runtime SQ flags
|
||||
*
|
||||
* Written by the kernel, shouldn't be modified by the
|
||||
* application.
|
||||
*
|
||||
* The application needs a full memory barrier before checking
|
||||
* for IORING_SQ_NEED_WAKEUP after updating the sq tail.
|
||||
*/
|
||||
atomic_t sq_flags;
|
||||
/*
|
||||
* Runtime CQ flags
|
||||
*
|
||||
* Written by the application, shouldn't be modified by the
|
||||
* kernel.
|
||||
*/
|
||||
u32 cq_flags;
|
||||
/*
|
||||
* Number of completion events lost because the queue was full;
|
||||
* this should be avoided by the application by making sure
|
||||
* there are not more requests pending than there is space in
|
||||
* the completion queue.
|
||||
*
|
||||
* Written by the kernel, shouldn't be modified by the
|
||||
* application (i.e. get number of "new events" by comparing to
|
||||
* cached value).
|
||||
*
|
||||
* As completion events come in out of order this counter is not
|
||||
* ordered with any other data.
|
||||
*/
|
||||
u32 cq_overflow;
|
||||
/*
|
||||
* Ring buffer of completion events.
|
||||
*
|
||||
* The kernel writes completion events fresh every time they are
|
||||
* produced, so the application is allowed to modify pending
|
||||
* entries.
|
||||
*/
|
||||
struct io_uring_cqe cqes[] ____cacheline_aligned_in_smp;
|
||||
};
|
||||
|
||||
struct io_mapped_ubuf {
|
||||
u64 ubuf;
|
||||
u64 ubuf_end;
|
||||
|
|
@ -252,12 +171,6 @@ struct io_rsrc_put {
|
|||
};
|
||||
};
|
||||
|
||||
struct io_file_table {
|
||||
struct io_fixed_file *files;
|
||||
unsigned long *bitmap;
|
||||
unsigned int alloc_hint;
|
||||
};
|
||||
|
||||
struct io_rsrc_node {
|
||||
struct percpu_ref refs;
|
||||
struct list_head node;
|
||||
|
|
@ -310,14 +223,6 @@ struct io_buffer {
|
|||
__u16 bgid;
|
||||
};
|
||||
|
||||
struct io_restriction {
|
||||
DECLARE_BITMAP(register_op, IORING_REGISTER_LAST);
|
||||
DECLARE_BITMAP(sqe_op, IORING_OP_LAST);
|
||||
u8 sqe_flags_allowed;
|
||||
u8 sqe_flags_required;
|
||||
bool registered;
|
||||
};
|
||||
|
||||
enum {
|
||||
IO_SQ_THREAD_SHOULD_STOP = 0,
|
||||
IO_SQ_THREAD_SHOULD_PARK,
|
||||
|
|
@ -347,186 +252,7 @@ struct io_sq_data {
|
|||
#define IO_REQ_CACHE_SIZE 32
|
||||
#define IO_REQ_ALLOC_BATCH 8
|
||||
|
||||
struct io_submit_link {
|
||||
struct io_kiocb *head;
|
||||
struct io_kiocb *last;
|
||||
};
|
||||
|
||||
struct io_submit_state {
|
||||
/* inline/task_work completion list, under ->uring_lock */
|
||||
struct io_wq_work_node free_list;
|
||||
/* batch completion logic */
|
||||
struct io_wq_work_list compl_reqs;
|
||||
struct io_submit_link link;
|
||||
|
||||
bool plug_started;
|
||||
bool need_plug;
|
||||
bool flush_cqes;
|
||||
unsigned short submit_nr;
|
||||
struct blk_plug plug;
|
||||
};
|
||||
|
||||
struct io_ev_fd {
|
||||
struct eventfd_ctx *cq_ev_fd;
|
||||
unsigned int eventfd_async: 1;
|
||||
struct rcu_head rcu;
|
||||
};
|
||||
|
||||
#define BGID_ARRAY 64
|
||||
|
||||
struct io_ring_ctx {
|
||||
/* const or read-mostly hot data */
|
||||
struct {
|
||||
struct percpu_ref refs;
|
||||
|
||||
struct io_rings *rings;
|
||||
unsigned int flags;
|
||||
enum task_work_notify_mode notify_method;
|
||||
unsigned int compat: 1;
|
||||
unsigned int drain_next: 1;
|
||||
unsigned int restricted: 1;
|
||||
unsigned int off_timeout_used: 1;
|
||||
unsigned int drain_active: 1;
|
||||
unsigned int drain_disabled: 1;
|
||||
unsigned int has_evfd: 1;
|
||||
unsigned int syscall_iopoll: 1;
|
||||
} ____cacheline_aligned_in_smp;
|
||||
|
||||
/* submission data */
|
||||
struct {
|
||||
struct mutex uring_lock;
|
||||
|
||||
/*
|
||||
* Ring buffer of indices into array of io_uring_sqe, which is
|
||||
* mmapped by the application using the IORING_OFF_SQES offset.
|
||||
*
|
||||
* This indirection could e.g. be used to assign fixed
|
||||
* io_uring_sqe entries to operations and only submit them to
|
||||
* the queue when needed.
|
||||
*
|
||||
* The kernel modifies neither the indices array nor the entries
|
||||
* array.
|
||||
*/
|
||||
u32 *sq_array;
|
||||
struct io_uring_sqe *sq_sqes;
|
||||
unsigned cached_sq_head;
|
||||
unsigned sq_entries;
|
||||
struct list_head defer_list;
|
||||
|
||||
/*
|
||||
* Fixed resources fast path, should be accessed only under
|
||||
* uring_lock, and updated through io_uring_register(2)
|
||||
*/
|
||||
struct io_rsrc_node *rsrc_node;
|
||||
int rsrc_cached_refs;
|
||||
atomic_t cancel_seq;
|
||||
struct io_file_table file_table;
|
||||
unsigned nr_user_files;
|
||||
unsigned nr_user_bufs;
|
||||
struct io_mapped_ubuf **user_bufs;
|
||||
|
||||
struct io_submit_state submit_state;
|
||||
|
||||
struct io_buffer_list *io_bl;
|
||||
struct xarray io_bl_xa;
|
||||
struct list_head io_buffers_cache;
|
||||
|
||||
struct list_head timeout_list;
|
||||
struct list_head ltimeout_list;
|
||||
struct list_head cq_overflow_list;
|
||||
struct list_head apoll_cache;
|
||||
struct xarray personalities;
|
||||
u32 pers_next;
|
||||
unsigned sq_thread_idle;
|
||||
} ____cacheline_aligned_in_smp;
|
||||
|
||||
/* IRQ completion list, under ->completion_lock */
|
||||
struct io_wq_work_list locked_free_list;
|
||||
unsigned int locked_free_nr;
|
||||
|
||||
const struct cred *sq_creds; /* cred used for __io_sq_thread() */
|
||||
struct io_sq_data *sq_data; /* if using sq thread polling */
|
||||
|
||||
struct wait_queue_head sqo_sq_wait;
|
||||
struct list_head sqd_list;
|
||||
|
||||
unsigned long check_cq;
|
||||
|
||||
struct {
|
||||
/*
|
||||
* We cache a range of free CQEs we can use, once exhausted it
|
||||
* should go through a slower range setup, see __io_get_cqe()
|
||||
*/
|
||||
struct io_uring_cqe *cqe_cached;
|
||||
struct io_uring_cqe *cqe_sentinel;
|
||||
|
||||
unsigned cached_cq_tail;
|
||||
unsigned cq_entries;
|
||||
struct io_ev_fd __rcu *io_ev_fd;
|
||||
struct wait_queue_head cq_wait;
|
||||
unsigned cq_extra;
|
||||
atomic_t cq_timeouts;
|
||||
unsigned cq_last_tm_flush;
|
||||
} ____cacheline_aligned_in_smp;
|
||||
|
||||
struct {
|
||||
spinlock_t completion_lock;
|
||||
|
||||
spinlock_t timeout_lock;
|
||||
|
||||
/*
|
||||
* ->iopoll_list is protected by the ctx->uring_lock for
|
||||
* io_uring instances that don't use IORING_SETUP_SQPOLL.
|
||||
* For SQPOLL, only the single threaded io_sq_thread() will
|
||||
* manipulate the list, hence no extra locking is needed there.
|
||||
*/
|
||||
struct io_wq_work_list iopoll_list;
|
||||
struct hlist_head *cancel_hash;
|
||||
unsigned cancel_hash_bits;
|
||||
bool poll_multi_queue;
|
||||
|
||||
struct list_head io_buffers_comp;
|
||||
} ____cacheline_aligned_in_smp;
|
||||
|
||||
struct io_restriction restrictions;
|
||||
|
||||
/* slow path rsrc auxilary data, used by update/register */
|
||||
struct {
|
||||
struct io_rsrc_node *rsrc_backup_node;
|
||||
struct io_mapped_ubuf *dummy_ubuf;
|
||||
struct io_rsrc_data *file_data;
|
||||
struct io_rsrc_data *buf_data;
|
||||
|
||||
struct delayed_work rsrc_put_work;
|
||||
struct llist_head rsrc_put_llist;
|
||||
struct list_head rsrc_ref_list;
|
||||
spinlock_t rsrc_ref_lock;
|
||||
|
||||
struct list_head io_buffers_pages;
|
||||
};
|
||||
|
||||
/* Keep this last, we don't need it for the fast path */
|
||||
struct {
|
||||
#if defined(CONFIG_UNIX)
|
||||
struct socket *ring_sock;
|
||||
#endif
|
||||
/* hashed buffered write serialization */
|
||||
struct io_wq_hash *hash_map;
|
||||
|
||||
/* Only used for accounting purposes */
|
||||
struct user_struct *user;
|
||||
struct mm_struct *mm_account;
|
||||
|
||||
/* ctx exit and cancelation */
|
||||
struct llist_head fallback_llist;
|
||||
struct delayed_work fallback_work;
|
||||
struct work_struct exit_work;
|
||||
struct list_head tctx_list;
|
||||
struct completion ref_comp;
|
||||
u32 iowq_limits[2];
|
||||
bool iowq_limits_set;
|
||||
};
|
||||
};
|
||||
#define BGID_ARRAY 64
|
||||
|
||||
/*
|
||||
* Arbitrary limit, can be raised if need be
|
||||
|
|
@ -808,232 +534,21 @@ struct io_xattr {
|
|||
struct filename *filename;
|
||||
};
|
||||
|
||||
enum {
|
||||
REQ_F_FIXED_FILE_BIT = IOSQE_FIXED_FILE_BIT,
|
||||
REQ_F_IO_DRAIN_BIT = IOSQE_IO_DRAIN_BIT,
|
||||
REQ_F_LINK_BIT = IOSQE_IO_LINK_BIT,
|
||||
REQ_F_HARDLINK_BIT = IOSQE_IO_HARDLINK_BIT,
|
||||
REQ_F_FORCE_ASYNC_BIT = IOSQE_ASYNC_BIT,
|
||||
REQ_F_BUFFER_SELECT_BIT = IOSQE_BUFFER_SELECT_BIT,
|
||||
REQ_F_CQE_SKIP_BIT = IOSQE_CQE_SKIP_SUCCESS_BIT,
|
||||
|
||||
/* first byte is taken by user flags, shift it to not overlap */
|
||||
REQ_F_FAIL_BIT = 8,
|
||||
REQ_F_INFLIGHT_BIT,
|
||||
REQ_F_CUR_POS_BIT,
|
||||
REQ_F_NOWAIT_BIT,
|
||||
REQ_F_LINK_TIMEOUT_BIT,
|
||||
REQ_F_NEED_CLEANUP_BIT,
|
||||
REQ_F_POLLED_BIT,
|
||||
REQ_F_BUFFER_SELECTED_BIT,
|
||||
REQ_F_BUFFER_RING_BIT,
|
||||
REQ_F_COMPLETE_INLINE_BIT,
|
||||
REQ_F_REISSUE_BIT,
|
||||
REQ_F_CREDS_BIT,
|
||||
REQ_F_REFCOUNT_BIT,
|
||||
REQ_F_ARM_LTIMEOUT_BIT,
|
||||
REQ_F_ASYNC_DATA_BIT,
|
||||
REQ_F_SKIP_LINK_CQES_BIT,
|
||||
REQ_F_SINGLE_POLL_BIT,
|
||||
REQ_F_DOUBLE_POLL_BIT,
|
||||
REQ_F_PARTIAL_IO_BIT,
|
||||
REQ_F_CQE32_INIT_BIT,
|
||||
REQ_F_APOLL_MULTISHOT_BIT,
|
||||
REQ_F_CLEAR_POLLIN_BIT,
|
||||
/* keep async read/write and isreg together and in order */
|
||||
REQ_F_SUPPORT_NOWAIT_BIT,
|
||||
REQ_F_ISREG_BIT,
|
||||
|
||||
/* not a real bit, just to check we're not overflowing the space */
|
||||
__REQ_F_LAST_BIT,
|
||||
};
|
||||
|
||||
enum {
|
||||
/* ctx owns file */
|
||||
REQ_F_FIXED_FILE = BIT(REQ_F_FIXED_FILE_BIT),
|
||||
/* drain existing IO first */
|
||||
REQ_F_IO_DRAIN = BIT(REQ_F_IO_DRAIN_BIT),
|
||||
/* linked sqes */
|
||||
REQ_F_LINK = BIT(REQ_F_LINK_BIT),
|
||||
/* doesn't sever on completion < 0 */
|
||||
REQ_F_HARDLINK = BIT(REQ_F_HARDLINK_BIT),
|
||||
/* IOSQE_ASYNC */
|
||||
REQ_F_FORCE_ASYNC = BIT(REQ_F_FORCE_ASYNC_BIT),
|
||||
/* IOSQE_BUFFER_SELECT */
|
||||
REQ_F_BUFFER_SELECT = BIT(REQ_F_BUFFER_SELECT_BIT),
|
||||
/* IOSQE_CQE_SKIP_SUCCESS */
|
||||
REQ_F_CQE_SKIP = BIT(REQ_F_CQE_SKIP_BIT),
|
||||
|
||||
/* fail rest of links */
|
||||
REQ_F_FAIL = BIT(REQ_F_FAIL_BIT),
|
||||
/* on inflight list, should be cancelled and waited on exit reliably */
|
||||
REQ_F_INFLIGHT = BIT(REQ_F_INFLIGHT_BIT),
|
||||
/* read/write uses file position */
|
||||
REQ_F_CUR_POS = BIT(REQ_F_CUR_POS_BIT),
|
||||
/* must not punt to workers */
|
||||
REQ_F_NOWAIT = BIT(REQ_F_NOWAIT_BIT),
|
||||
/* has or had linked timeout */
|
||||
REQ_F_LINK_TIMEOUT = BIT(REQ_F_LINK_TIMEOUT_BIT),
|
||||
/* needs cleanup */
|
||||
REQ_F_NEED_CLEANUP = BIT(REQ_F_NEED_CLEANUP_BIT),
|
||||
/* already went through poll handler */
|
||||
REQ_F_POLLED = BIT(REQ_F_POLLED_BIT),
|
||||
/* buffer already selected */
|
||||
REQ_F_BUFFER_SELECTED = BIT(REQ_F_BUFFER_SELECTED_BIT),
|
||||
/* buffer selected from ring, needs commit */
|
||||
REQ_F_BUFFER_RING = BIT(REQ_F_BUFFER_RING_BIT),
|
||||
/* completion is deferred through io_comp_state */
|
||||
REQ_F_COMPLETE_INLINE = BIT(REQ_F_COMPLETE_INLINE_BIT),
|
||||
/* caller should reissue async */
|
||||
REQ_F_REISSUE = BIT(REQ_F_REISSUE_BIT),
|
||||
/* supports async reads/writes */
|
||||
REQ_F_SUPPORT_NOWAIT = BIT(REQ_F_SUPPORT_NOWAIT_BIT),
|
||||
/* regular file */
|
||||
REQ_F_ISREG = BIT(REQ_F_ISREG_BIT),
|
||||
/* has creds assigned */
|
||||
REQ_F_CREDS = BIT(REQ_F_CREDS_BIT),
|
||||
/* skip refcounting if not set */
|
||||
REQ_F_REFCOUNT = BIT(REQ_F_REFCOUNT_BIT),
|
||||
/* there is a linked timeout that has to be armed */
|
||||
REQ_F_ARM_LTIMEOUT = BIT(REQ_F_ARM_LTIMEOUT_BIT),
|
||||
/* ->async_data allocated */
|
||||
REQ_F_ASYNC_DATA = BIT(REQ_F_ASYNC_DATA_BIT),
|
||||
/* don't post CQEs while failing linked requests */
|
||||
REQ_F_SKIP_LINK_CQES = BIT(REQ_F_SKIP_LINK_CQES_BIT),
|
||||
/* single poll may be active */
|
||||
REQ_F_SINGLE_POLL = BIT(REQ_F_SINGLE_POLL_BIT),
|
||||
/* double poll may active */
|
||||
REQ_F_DOUBLE_POLL = BIT(REQ_F_DOUBLE_POLL_BIT),
|
||||
/* request has already done partial IO */
|
||||
REQ_F_PARTIAL_IO = BIT(REQ_F_PARTIAL_IO_BIT),
|
||||
/* fast poll multishot mode */
|
||||
REQ_F_APOLL_MULTISHOT = BIT(REQ_F_APOLL_MULTISHOT_BIT),
|
||||
/* ->extra1 and ->extra2 are initialised */
|
||||
REQ_F_CQE32_INIT = BIT(REQ_F_CQE32_INIT_BIT),
|
||||
/* recvmsg special flag, clear EPOLLIN */
|
||||
REQ_F_CLEAR_POLLIN = BIT(REQ_F_CLEAR_POLLIN_BIT),
|
||||
};
|
||||
|
||||
struct async_poll {
|
||||
struct io_poll poll;
|
||||
struct io_poll *double_poll;
|
||||
};
|
||||
|
||||
typedef void (*io_req_tw_func_t)(struct io_kiocb *req, bool *locked);
|
||||
|
||||
struct io_task_work {
|
||||
union {
|
||||
struct io_wq_work_node node;
|
||||
struct llist_node fallback_node;
|
||||
};
|
||||
io_req_tw_func_t func;
|
||||
};
|
||||
|
||||
enum {
|
||||
IORING_RSRC_FILE = 0,
|
||||
IORING_RSRC_BUFFER = 1,
|
||||
};
|
||||
|
||||
struct io_cqe {
|
||||
__u64 user_data;
|
||||
__s32 res;
|
||||
/* fd initially, then cflags for completion */
|
||||
union {
|
||||
__u32 flags;
|
||||
int fd;
|
||||
};
|
||||
};
|
||||
|
||||
enum {
|
||||
IO_CHECK_CQ_OVERFLOW_BIT,
|
||||
IO_CHECK_CQ_DROPPED_BIT,
|
||||
};
|
||||
|
||||
/*
|
||||
* Each request type overlays its private data structure on top of this one.
|
||||
* They must not exceed this one in size.
|
||||
*/
|
||||
struct io_cmd_data {
|
||||
struct file *file;
|
||||
/* each command gets 56 bytes of data */
|
||||
__u8 data[56];
|
||||
};
|
||||
|
||||
#define io_kiocb_to_cmd(req) ((void *) &(req)->cmd)
|
||||
#define cmd_to_io_kiocb(ptr) ((struct io_kiocb *) ptr)
|
||||
|
||||
struct io_kiocb {
|
||||
union {
|
||||
/*
|
||||
* NOTE! Each of the io_kiocb union members has the file pointer
|
||||
* as the first entry in their struct definition. So you can
|
||||
* access the file pointer through any of the sub-structs,
|
||||
* or directly as just 'file' in this struct.
|
||||
*/
|
||||
struct file *file;
|
||||
struct io_cmd_data cmd;
|
||||
};
|
||||
|
||||
u8 opcode;
|
||||
/* polled IO has completed */
|
||||
u8 iopoll_completed;
|
||||
/*
|
||||
* Can be either a fixed buffer index, or used with provided buffers.
|
||||
* For the latter, before issue it points to the buffer group ID,
|
||||
* and after selection it points to the buffer ID itself.
|
||||
*/
|
||||
u16 buf_index;
|
||||
unsigned int flags;
|
||||
|
||||
struct io_cqe cqe;
|
||||
|
||||
struct io_ring_ctx *ctx;
|
||||
struct task_struct *task;
|
||||
|
||||
struct io_rsrc_node *rsrc_node;
|
||||
|
||||
union {
|
||||
/* store used ubuf, so we can prevent reloading */
|
||||
struct io_mapped_ubuf *imu;
|
||||
|
||||
/* stores selected buf, valid IFF REQ_F_BUFFER_SELECTED is set */
|
||||
struct io_buffer *kbuf;
|
||||
|
||||
/*
|
||||
* stores buffer ID for ring provided buffers, valid IFF
|
||||
* REQ_F_BUFFER_RING is set.
|
||||
*/
|
||||
struct io_buffer_list *buf_list;
|
||||
};
|
||||
|
||||
union {
|
||||
/* used by request caches, completion batching and iopoll */
|
||||
struct io_wq_work_node comp_list;
|
||||
/* cache ->apoll->events */
|
||||
__poll_t apoll_events;
|
||||
};
|
||||
atomic_t refs;
|
||||
atomic_t poll_refs;
|
||||
struct io_task_work io_task_work;
|
||||
/* for polled requests, i.e. IORING_OP_POLL_ADD and async armed poll */
|
||||
union {
|
||||
struct hlist_node hash_node;
|
||||
struct {
|
||||
u64 extra1;
|
||||
u64 extra2;
|
||||
};
|
||||
};
|
||||
/* internal polling, see IORING_FEAT_FAST_POLL */
|
||||
struct async_poll *apoll;
|
||||
/* opcode allocated if it needs to store data for async defer */
|
||||
void *async_data;
|
||||
/* linked requests, IFF REQ_F_HARDLINK or REQ_F_LINK are set */
|
||||
struct io_kiocb *link;
|
||||
/* custom credentials, valid IFF REQ_F_CREDS is set */
|
||||
const struct cred *creds;
|
||||
struct io_wq_work work;
|
||||
};
|
||||
|
||||
struct io_tctx_node {
|
||||
struct list_head ctx_node;
|
||||
struct task_struct *task;
|
||||
|
|
|
|||
|
|
@ -0,0 +1,496 @@
|
|||
#ifndef IO_URING_TYPES_H
|
||||
#define IO_URING_TYPES_H
|
||||
|
||||
#include <linux/blkdev.h>
|
||||
#include <linux/task_work.h>
|
||||
|
||||
#include "io-wq.h"
|
||||
|
||||
struct io_uring {
|
||||
u32 head ____cacheline_aligned_in_smp;
|
||||
u32 tail ____cacheline_aligned_in_smp;
|
||||
};
|
||||
|
||||
/*
|
||||
* This data is shared with the application through the mmap at offsets
|
||||
* IORING_OFF_SQ_RING and IORING_OFF_CQ_RING.
|
||||
*
|
||||
* The offsets to the member fields are published through struct
|
||||
* io_sqring_offsets when calling io_uring_setup.
|
||||
*/
|
||||
struct io_rings {
|
||||
/*
|
||||
* Head and tail offsets into the ring; the offsets need to be
|
||||
* masked to get valid indices.
|
||||
*
|
||||
* The kernel controls head of the sq ring and the tail of the cq ring,
|
||||
* and the application controls tail of the sq ring and the head of the
|
||||
* cq ring.
|
||||
*/
|
||||
struct io_uring sq, cq;
|
||||
/*
|
||||
* Bitmasks to apply to head and tail offsets (constant, equals
|
||||
* ring_entries - 1)
|
||||
*/
|
||||
u32 sq_ring_mask, cq_ring_mask;
|
||||
/* Ring sizes (constant, power of 2) */
|
||||
u32 sq_ring_entries, cq_ring_entries;
|
||||
/*
|
||||
* Number of invalid entries dropped by the kernel due to
|
||||
* invalid index stored in array
|
||||
*
|
||||
* Written by the kernel, shouldn't be modified by the
|
||||
* application (i.e. get number of "new events" by comparing to
|
||||
* cached value).
|
||||
*
|
||||
* After a new SQ head value was read by the application this
|
||||
* counter includes all submissions that were dropped reaching
|
||||
* the new SQ head (and possibly more).
|
||||
*/
|
||||
u32 sq_dropped;
|
||||
/*
|
||||
* Runtime SQ flags
|
||||
*
|
||||
* Written by the kernel, shouldn't be modified by the
|
||||
* application.
|
||||
*
|
||||
* The application needs a full memory barrier before checking
|
||||
* for IORING_SQ_NEED_WAKEUP after updating the sq tail.
|
||||
*/
|
||||
atomic_t sq_flags;
|
||||
/*
|
||||
* Runtime CQ flags
|
||||
*
|
||||
* Written by the application, shouldn't be modified by the
|
||||
* kernel.
|
||||
*/
|
||||
u32 cq_flags;
|
||||
/*
|
||||
* Number of completion events lost because the queue was full;
|
||||
* this should be avoided by the application by making sure
|
||||
* there are not more requests pending than there is space in
|
||||
* the completion queue.
|
||||
*
|
||||
* Written by the kernel, shouldn't be modified by the
|
||||
* application (i.e. get number of "new events" by comparing to
|
||||
* cached value).
|
||||
*
|
||||
* As completion events come in out of order this counter is not
|
||||
* ordered with any other data.
|
||||
*/
|
||||
u32 cq_overflow;
|
||||
/*
|
||||
* Ring buffer of completion events.
|
||||
*
|
||||
* The kernel writes completion events fresh every time they are
|
||||
* produced, so the application is allowed to modify pending
|
||||
* entries.
|
||||
*/
|
||||
struct io_uring_cqe cqes[] ____cacheline_aligned_in_smp;
|
||||
};
|
||||
|
||||
struct io_restriction {
|
||||
DECLARE_BITMAP(register_op, IORING_REGISTER_LAST);
|
||||
DECLARE_BITMAP(sqe_op, IORING_OP_LAST);
|
||||
u8 sqe_flags_allowed;
|
||||
u8 sqe_flags_required;
|
||||
bool registered;
|
||||
};
|
||||
|
||||
struct io_submit_link {
|
||||
struct io_kiocb *head;
|
||||
struct io_kiocb *last;
|
||||
};
|
||||
|
||||
struct io_submit_state {
|
||||
/* inline/task_work completion list, under ->uring_lock */
|
||||
struct io_wq_work_node free_list;
|
||||
/* batch completion logic */
|
||||
struct io_wq_work_list compl_reqs;
|
||||
struct io_submit_link link;
|
||||
|
||||
bool plug_started;
|
||||
bool need_plug;
|
||||
bool flush_cqes;
|
||||
unsigned short submit_nr;
|
||||
struct blk_plug plug;
|
||||
};
|
||||
|
||||
struct io_ev_fd {
|
||||
struct eventfd_ctx *cq_ev_fd;
|
||||
unsigned int eventfd_async: 1;
|
||||
struct rcu_head rcu;
|
||||
};
|
||||
|
||||
struct io_file_table {
|
||||
struct io_fixed_file *files;
|
||||
unsigned long *bitmap;
|
||||
unsigned int alloc_hint;
|
||||
};
|
||||
|
||||
struct io_ring_ctx {
|
||||
/* const or read-mostly hot data */
|
||||
struct {
|
||||
struct percpu_ref refs;
|
||||
|
||||
struct io_rings *rings;
|
||||
unsigned int flags;
|
||||
enum task_work_notify_mode notify_method;
|
||||
unsigned int compat: 1;
|
||||
unsigned int drain_next: 1;
|
||||
unsigned int restricted: 1;
|
||||
unsigned int off_timeout_used: 1;
|
||||
unsigned int drain_active: 1;
|
||||
unsigned int drain_disabled: 1;
|
||||
unsigned int has_evfd: 1;
|
||||
unsigned int syscall_iopoll: 1;
|
||||
} ____cacheline_aligned_in_smp;
|
||||
|
||||
/* submission data */
|
||||
struct {
|
||||
struct mutex uring_lock;
|
||||
|
||||
/*
|
||||
* Ring buffer of indices into array of io_uring_sqe, which is
|
||||
* mmapped by the application using the IORING_OFF_SQES offset.
|
||||
*
|
||||
* This indirection could e.g. be used to assign fixed
|
||||
* io_uring_sqe entries to operations and only submit them to
|
||||
* the queue when needed.
|
||||
*
|
||||
* The kernel modifies neither the indices array nor the entries
|
||||
* array.
|
||||
*/
|
||||
u32 *sq_array;
|
||||
struct io_uring_sqe *sq_sqes;
|
||||
unsigned cached_sq_head;
|
||||
unsigned sq_entries;
|
||||
struct list_head defer_list;
|
||||
|
||||
/*
|
||||
* Fixed resources fast path, should be accessed only under
|
||||
* uring_lock, and updated through io_uring_register(2)
|
||||
*/
|
||||
struct io_rsrc_node *rsrc_node;
|
||||
int rsrc_cached_refs;
|
||||
atomic_t cancel_seq;
|
||||
struct io_file_table file_table;
|
||||
unsigned nr_user_files;
|
||||
unsigned nr_user_bufs;
|
||||
struct io_mapped_ubuf **user_bufs;
|
||||
|
||||
struct io_submit_state submit_state;
|
||||
|
||||
struct io_buffer_list *io_bl;
|
||||
struct xarray io_bl_xa;
|
||||
struct list_head io_buffers_cache;
|
||||
|
||||
struct list_head timeout_list;
|
||||
struct list_head ltimeout_list;
|
||||
struct list_head cq_overflow_list;
|
||||
struct list_head apoll_cache;
|
||||
struct xarray personalities;
|
||||
u32 pers_next;
|
||||
unsigned sq_thread_idle;
|
||||
} ____cacheline_aligned_in_smp;
|
||||
|
||||
/* IRQ completion list, under ->completion_lock */
|
||||
struct io_wq_work_list locked_free_list;
|
||||
unsigned int locked_free_nr;
|
||||
|
||||
const struct cred *sq_creds; /* cred used for __io_sq_thread() */
|
||||
struct io_sq_data *sq_data; /* if using sq thread polling */
|
||||
|
||||
struct wait_queue_head sqo_sq_wait;
|
||||
struct list_head sqd_list;
|
||||
|
||||
unsigned long check_cq;
|
||||
|
||||
struct {
|
||||
/*
|
||||
* We cache a range of free CQEs we can use, once exhausted it
|
||||
* should go through a slower range setup, see __io_get_cqe()
|
||||
*/
|
||||
struct io_uring_cqe *cqe_cached;
|
||||
struct io_uring_cqe *cqe_sentinel;
|
||||
|
||||
unsigned cached_cq_tail;
|
||||
unsigned cq_entries;
|
||||
struct io_ev_fd __rcu *io_ev_fd;
|
||||
struct wait_queue_head cq_wait;
|
||||
unsigned cq_extra;
|
||||
atomic_t cq_timeouts;
|
||||
unsigned cq_last_tm_flush;
|
||||
} ____cacheline_aligned_in_smp;
|
||||
|
||||
struct {
|
||||
spinlock_t completion_lock;
|
||||
|
||||
spinlock_t timeout_lock;
|
||||
|
||||
/*
|
||||
* ->iopoll_list is protected by the ctx->uring_lock for
|
||||
* io_uring instances that don't use IORING_SETUP_SQPOLL.
|
||||
* For SQPOLL, only the single threaded io_sq_thread() will
|
||||
* manipulate the list, hence no extra locking is needed there.
|
||||
*/
|
||||
struct io_wq_work_list iopoll_list;
|
||||
struct hlist_head *cancel_hash;
|
||||
unsigned cancel_hash_bits;
|
||||
bool poll_multi_queue;
|
||||
|
||||
struct list_head io_buffers_comp;
|
||||
} ____cacheline_aligned_in_smp;
|
||||
|
||||
struct io_restriction restrictions;
|
||||
|
||||
/* slow path rsrc auxilary data, used by update/register */
|
||||
struct {
|
||||
struct io_rsrc_node *rsrc_backup_node;
|
||||
struct io_mapped_ubuf *dummy_ubuf;
|
||||
struct io_rsrc_data *file_data;
|
||||
struct io_rsrc_data *buf_data;
|
||||
|
||||
struct delayed_work rsrc_put_work;
|
||||
struct llist_head rsrc_put_llist;
|
||||
struct list_head rsrc_ref_list;
|
||||
spinlock_t rsrc_ref_lock;
|
||||
|
||||
struct list_head io_buffers_pages;
|
||||
};
|
||||
|
||||
/* Keep this last, we don't need it for the fast path */
|
||||
struct {
|
||||
#if defined(CONFIG_UNIX)
|
||||
struct socket *ring_sock;
|
||||
#endif
|
||||
/* hashed buffered write serialization */
|
||||
struct io_wq_hash *hash_map;
|
||||
|
||||
/* Only used for accounting purposes */
|
||||
struct user_struct *user;
|
||||
struct mm_struct *mm_account;
|
||||
|
||||
/* ctx exit and cancelation */
|
||||
struct llist_head fallback_llist;
|
||||
struct delayed_work fallback_work;
|
||||
struct work_struct exit_work;
|
||||
struct list_head tctx_list;
|
||||
struct completion ref_comp;
|
||||
u32 iowq_limits[2];
|
||||
bool iowq_limits_set;
|
||||
};
|
||||
};
|
||||
|
||||
enum {
|
||||
REQ_F_FIXED_FILE_BIT = IOSQE_FIXED_FILE_BIT,
|
||||
REQ_F_IO_DRAIN_BIT = IOSQE_IO_DRAIN_BIT,
|
||||
REQ_F_LINK_BIT = IOSQE_IO_LINK_BIT,
|
||||
REQ_F_HARDLINK_BIT = IOSQE_IO_HARDLINK_BIT,
|
||||
REQ_F_FORCE_ASYNC_BIT = IOSQE_ASYNC_BIT,
|
||||
REQ_F_BUFFER_SELECT_BIT = IOSQE_BUFFER_SELECT_BIT,
|
||||
REQ_F_CQE_SKIP_BIT = IOSQE_CQE_SKIP_SUCCESS_BIT,
|
||||
|
||||
/* first byte is taken by user flags, shift it to not overlap */
|
||||
REQ_F_FAIL_BIT = 8,
|
||||
REQ_F_INFLIGHT_BIT,
|
||||
REQ_F_CUR_POS_BIT,
|
||||
REQ_F_NOWAIT_BIT,
|
||||
REQ_F_LINK_TIMEOUT_BIT,
|
||||
REQ_F_NEED_CLEANUP_BIT,
|
||||
REQ_F_POLLED_BIT,
|
||||
REQ_F_BUFFER_SELECTED_BIT,
|
||||
REQ_F_BUFFER_RING_BIT,
|
||||
REQ_F_COMPLETE_INLINE_BIT,
|
||||
REQ_F_REISSUE_BIT,
|
||||
REQ_F_CREDS_BIT,
|
||||
REQ_F_REFCOUNT_BIT,
|
||||
REQ_F_ARM_LTIMEOUT_BIT,
|
||||
REQ_F_ASYNC_DATA_BIT,
|
||||
REQ_F_SKIP_LINK_CQES_BIT,
|
||||
REQ_F_SINGLE_POLL_BIT,
|
||||
REQ_F_DOUBLE_POLL_BIT,
|
||||
REQ_F_PARTIAL_IO_BIT,
|
||||
REQ_F_CQE32_INIT_BIT,
|
||||
REQ_F_APOLL_MULTISHOT_BIT,
|
||||
REQ_F_CLEAR_POLLIN_BIT,
|
||||
/* keep async read/write and isreg together and in order */
|
||||
REQ_F_SUPPORT_NOWAIT_BIT,
|
||||
REQ_F_ISREG_BIT,
|
||||
|
||||
/* not a real bit, just to check we're not overflowing the space */
|
||||
__REQ_F_LAST_BIT,
|
||||
};
|
||||
|
||||
enum {
|
||||
/* ctx owns file */
|
||||
REQ_F_FIXED_FILE = BIT(REQ_F_FIXED_FILE_BIT),
|
||||
/* drain existing IO first */
|
||||
REQ_F_IO_DRAIN = BIT(REQ_F_IO_DRAIN_BIT),
|
||||
/* linked sqes */
|
||||
REQ_F_LINK = BIT(REQ_F_LINK_BIT),
|
||||
/* doesn't sever on completion < 0 */
|
||||
REQ_F_HARDLINK = BIT(REQ_F_HARDLINK_BIT),
|
||||
/* IOSQE_ASYNC */
|
||||
REQ_F_FORCE_ASYNC = BIT(REQ_F_FORCE_ASYNC_BIT),
|
||||
/* IOSQE_BUFFER_SELECT */
|
||||
REQ_F_BUFFER_SELECT = BIT(REQ_F_BUFFER_SELECT_BIT),
|
||||
/* IOSQE_CQE_SKIP_SUCCESS */
|
||||
REQ_F_CQE_SKIP = BIT(REQ_F_CQE_SKIP_BIT),
|
||||
|
||||
/* fail rest of links */
|
||||
REQ_F_FAIL = BIT(REQ_F_FAIL_BIT),
|
||||
/* on inflight list, should be cancelled and waited on exit reliably */
|
||||
REQ_F_INFLIGHT = BIT(REQ_F_INFLIGHT_BIT),
|
||||
/* read/write uses file position */
|
||||
REQ_F_CUR_POS = BIT(REQ_F_CUR_POS_BIT),
|
||||
/* must not punt to workers */
|
||||
REQ_F_NOWAIT = BIT(REQ_F_NOWAIT_BIT),
|
||||
/* has or had linked timeout */
|
||||
REQ_F_LINK_TIMEOUT = BIT(REQ_F_LINK_TIMEOUT_BIT),
|
||||
/* needs cleanup */
|
||||
REQ_F_NEED_CLEANUP = BIT(REQ_F_NEED_CLEANUP_BIT),
|
||||
/* already went through poll handler */
|
||||
REQ_F_POLLED = BIT(REQ_F_POLLED_BIT),
|
||||
/* buffer already selected */
|
||||
REQ_F_BUFFER_SELECTED = BIT(REQ_F_BUFFER_SELECTED_BIT),
|
||||
/* buffer selected from ring, needs commit */
|
||||
REQ_F_BUFFER_RING = BIT(REQ_F_BUFFER_RING_BIT),
|
||||
/* completion is deferred through io_comp_state */
|
||||
REQ_F_COMPLETE_INLINE = BIT(REQ_F_COMPLETE_INLINE_BIT),
|
||||
/* caller should reissue async */
|
||||
REQ_F_REISSUE = BIT(REQ_F_REISSUE_BIT),
|
||||
/* supports async reads/writes */
|
||||
REQ_F_SUPPORT_NOWAIT = BIT(REQ_F_SUPPORT_NOWAIT_BIT),
|
||||
/* regular file */
|
||||
REQ_F_ISREG = BIT(REQ_F_ISREG_BIT),
|
||||
/* has creds assigned */
|
||||
REQ_F_CREDS = BIT(REQ_F_CREDS_BIT),
|
||||
/* skip refcounting if not set */
|
||||
REQ_F_REFCOUNT = BIT(REQ_F_REFCOUNT_BIT),
|
||||
/* there is a linked timeout that has to be armed */
|
||||
REQ_F_ARM_LTIMEOUT = BIT(REQ_F_ARM_LTIMEOUT_BIT),
|
||||
/* ->async_data allocated */
|
||||
REQ_F_ASYNC_DATA = BIT(REQ_F_ASYNC_DATA_BIT),
|
||||
/* don't post CQEs while failing linked requests */
|
||||
REQ_F_SKIP_LINK_CQES = BIT(REQ_F_SKIP_LINK_CQES_BIT),
|
||||
/* single poll may be active */
|
||||
REQ_F_SINGLE_POLL = BIT(REQ_F_SINGLE_POLL_BIT),
|
||||
/* double poll may active */
|
||||
REQ_F_DOUBLE_POLL = BIT(REQ_F_DOUBLE_POLL_BIT),
|
||||
/* request has already done partial IO */
|
||||
REQ_F_PARTIAL_IO = BIT(REQ_F_PARTIAL_IO_BIT),
|
||||
/* fast poll multishot mode */
|
||||
REQ_F_APOLL_MULTISHOT = BIT(REQ_F_APOLL_MULTISHOT_BIT),
|
||||
/* ->extra1 and ->extra2 are initialised */
|
||||
REQ_F_CQE32_INIT = BIT(REQ_F_CQE32_INIT_BIT),
|
||||
/* recvmsg special flag, clear EPOLLIN */
|
||||
REQ_F_CLEAR_POLLIN = BIT(REQ_F_CLEAR_POLLIN_BIT),
|
||||
};
|
||||
|
||||
typedef void (*io_req_tw_func_t)(struct io_kiocb *req, bool *locked);
|
||||
|
||||
struct io_task_work {
|
||||
union {
|
||||
struct io_wq_work_node node;
|
||||
struct llist_node fallback_node;
|
||||
};
|
||||
io_req_tw_func_t func;
|
||||
};
|
||||
|
||||
struct io_cqe {
|
||||
__u64 user_data;
|
||||
__s32 res;
|
||||
/* fd initially, then cflags for completion */
|
||||
union {
|
||||
__u32 flags;
|
||||
int fd;
|
||||
};
|
||||
};
|
||||
|
||||
/*
|
||||
* Each request type overlays its private data structure on top of this one.
|
||||
* They must not exceed this one in size.
|
||||
*/
|
||||
struct io_cmd_data {
|
||||
struct file *file;
|
||||
/* each command gets 56 bytes of data */
|
||||
__u8 data[56];
|
||||
};
|
||||
|
||||
#define io_kiocb_to_cmd(req) ((void *) &(req)->cmd)
|
||||
#define cmd_to_io_kiocb(ptr) ((struct io_kiocb *) ptr)
|
||||
|
||||
struct io_kiocb {
|
||||
union {
|
||||
/*
|
||||
* NOTE! Each of the io_kiocb union members has the file pointer
|
||||
* as the first entry in their struct definition. So you can
|
||||
* access the file pointer through any of the sub-structs,
|
||||
* or directly as just 'file' in this struct.
|
||||
*/
|
||||
struct file *file;
|
||||
struct io_cmd_data cmd;
|
||||
};
|
||||
|
||||
u8 opcode;
|
||||
/* polled IO has completed */
|
||||
u8 iopoll_completed;
|
||||
/*
|
||||
* Can be either a fixed buffer index, or used with provided buffers.
|
||||
* For the latter, before issue it points to the buffer group ID,
|
||||
* and after selection it points to the buffer ID itself.
|
||||
*/
|
||||
u16 buf_index;
|
||||
unsigned int flags;
|
||||
|
||||
struct io_cqe cqe;
|
||||
|
||||
struct io_ring_ctx *ctx;
|
||||
struct task_struct *task;
|
||||
|
||||
struct io_rsrc_node *rsrc_node;
|
||||
|
||||
union {
|
||||
/* store used ubuf, so we can prevent reloading */
|
||||
struct io_mapped_ubuf *imu;
|
||||
|
||||
/* stores selected buf, valid IFF REQ_F_BUFFER_SELECTED is set */
|
||||
struct io_buffer *kbuf;
|
||||
|
||||
/*
|
||||
* stores buffer ID for ring provided buffers, valid IFF
|
||||
* REQ_F_BUFFER_RING is set.
|
||||
*/
|
||||
struct io_buffer_list *buf_list;
|
||||
};
|
||||
|
||||
union {
|
||||
/* used by request caches, completion batching and iopoll */
|
||||
struct io_wq_work_node comp_list;
|
||||
/* cache ->apoll->events */
|
||||
__poll_t apoll_events;
|
||||
};
|
||||
atomic_t refs;
|
||||
atomic_t poll_refs;
|
||||
struct io_task_work io_task_work;
|
||||
/* for polled requests, i.e. IORING_OP_POLL_ADD and async armed poll */
|
||||
union {
|
||||
struct hlist_node hash_node;
|
||||
struct {
|
||||
u64 extra1;
|
||||
u64 extra2;
|
||||
};
|
||||
};
|
||||
/* internal polling, see IORING_FEAT_FAST_POLL */
|
||||
struct async_poll *apoll;
|
||||
/* opcode allocated if it needs to store data for async defer */
|
||||
void *async_data;
|
||||
/* linked requests, IFF REQ_F_HARDLINK or REQ_F_LINK are set */
|
||||
struct io_kiocb *link;
|
||||
/* custom credentials, valid IFF REQ_F_CREDS is set */
|
||||
const struct cred *creds;
|
||||
struct io_wq_work work;
|
||||
};
|
||||
|
||||
#endif
|
||||
Loading…
Reference in New Issue