From e27f928ee1cb068ac6c18ea244351a4c90a61139 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Tue, 24 May 2022 10:56:14 -0600
Subject: 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>
---
 io_uring/io_uring.c | 491 +---------------------------------------------------
 1 file changed, 3 insertions(+), 488 deletions(-)

(limited to 'io_uring/io_uring.c')

diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 75d8c31a59d5..ff7886c35490 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -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;
-- 
cgit v1.2.3