// SPDX-License-Identifier: GPL-2.0
/*
 * Shared application/kernel submission and completion ring pairs, for
 * supporting fast/efficient IO.
 *
 * A note on the read/write ordering memory barriers that are matched between
 * the application and kernel side.
 *
 * After the application reads the CQ ring tail, it must use an
 * appropriate smp_rmb() to pair with the smp_wmb() the kernel uses
 * before writing the tail (using smp_load_acquire to read the tail will
 * do). It also needs a smp_mb() before updating CQ head (ordering the
 * entry load(s) with the head store), pairing with an implicit barrier
 * through a control-dependency in io_get_cqring (smp_store_release to
 * store head will do). Failure to do so could lead to reading invalid
 * CQ entries.
 *
 * Likewise, the application must use an appropriate smp_wmb() before
 * writing the SQ tail (ordering SQ entry stores with the tail store),
 * which pairs with smp_load_acquire in io_get_sqring (smp_store_release
 * to store the tail will do). And it needs a barrier ordering the SQ
 * head load before writing new SQ entries (smp_load_acquire to read
 * head will do).
 *
 * When using the SQ poll thread (IORING_SETUP_SQPOLL), the application
 * needs to check the SQ flags for IORING_SQ_NEED_WAKEUP *after*
 * updating the SQ tail; a full memory barrier smp_mb() is needed
 * between.
 *
 * Also see the examples in the liburing library:
 *
 *	git://git.kernel.dk/liburing
 *
 * io_uring also uses READ/WRITE_ONCE() for _any_ store or load that happens
 * from data shared between the kernel and application. This is done both
 * for ordering purposes, but also to ensure that once a value is loaded from
 * data that the application could potentially modify, it remains stable.
 *
 * Copyright (C) 2018-2019 Jens Axboe
 * Copyright (c) 2018-2019 Christoph Hellwig
 */
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/errno.h>
#include <linux/syscalls.h>
#include <linux/compat.h>
#include <net/compat.h>
#include <linux/refcount.h>
#include <linux/uio.h>
#include <linux/bits.h>

#include <linux/sched/signal.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/fdtable.h>
#include <linux/mm.h>
#include <linux/mman.h>
#include <linux/percpu.h>
#include <linux/slab.h>
#include <linux/blkdev.h>
#include <linux/bvec.h>
#include <linux/net.h>
#include <net/sock.h>
#include <net/af_unix.h>
#include <net/scm.h>
#include <linux/anon_inodes.h>
#include <linux/sched/mm.h>
#include <linux/uaccess.h>
#include <linux/nospec.h>
#include <linux/sizes.h>
#include <linux/hugetlb.h>
#include <linux/highmem.h>
#include <linux/namei.h>
#include <linux/fsnotify.h>
#include <linux/fadvise.h>
#include <linux/eventpoll.h>
#include <linux/splice.h>
#include <linux/task_work.h>
#include <linux/pagemap.h>
#include <linux/io_uring.h>

#define CREATE_TRACE_POINTS
#include <trace/events/io_uring.h>

#include <uapi/linux/io_uring.h>

#include "internal.h"
#include "io-wq.h"

#define IORING_MAX_ENTRIES	32768
#define IORING_MAX_CQ_ENTRIES	(2 * IORING_MAX_ENTRIES)

/*
 * Shift of 9 is 512 entries, or exactly one page on 64-bit archs
 */
#define IORING_FILE_TABLE_SHIFT	9
#define IORING_MAX_FILES_TABLE	(1U << IORING_FILE_TABLE_SHIFT)
#define IORING_FILE_TABLE_MASK	(IORING_MAX_FILES_TABLE - 1)
#define IORING_MAX_FIXED_FILES	(64 * IORING_MAX_FILES_TABLE)
#define IORING_MAX_RESTRICTIONS	(IORING_RESTRICTION_LAST + \
				 IORING_REGISTER_LAST + IORING_OP_LAST)

#define IORING_MAX_REG_BUFFERS	(1U << 14)

#define SQE_VALID_FLAGS	(IOSQE_FIXED_FILE|IOSQE_IO_DRAIN|IOSQE_IO_LINK|	\
				IOSQE_IO_HARDLINK | IOSQE_ASYNC | \
				IOSQE_BUFFER_SELECT)

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.
	 */
	u32			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;
};

enum io_uring_cmd_flags {
	IO_URING_F_NONBLOCK		= 1,
	IO_URING_F_COMPLETE_DEFER	= 2,
};

struct io_mapped_ubuf {
	u64		ubuf;
	u64		ubuf_end;
	unsigned int	nr_bvecs;
	unsigned long	acct_pages;
	struct bio_vec	bvec[];
};

struct io_ring_ctx;

struct io_overflow_cqe {
	struct io_uring_cqe cqe;
	struct list_head list;
};

struct io_fixed_file {
	/* file * with additional FFS_* flags */
	unsigned long file_ptr;
};

struct io_rsrc_put {
	struct list_head list;
	u64 tag;
	union {
		void *rsrc;
		struct file *file;
		struct io_mapped_ubuf *buf;
	};
};

struct io_file_table {
	/* two level table */
	struct io_fixed_file **files;
};

struct io_rsrc_node {
	struct percpu_ref		refs;
	struct list_head		node;
	struct list_head		rsrc_list;
	struct io_rsrc_data		*rsrc_data;
	struct llist_node		llist;
	bool				done;
};

typedef void (rsrc_put_fn)(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc);

struct io_rsrc_data {
	struct io_ring_ctx		*ctx;

	u64				*tags;
	rsrc_put_fn			*do_put;
	atomic_t			refs;
	struct completion		done;
	bool				quiesce;
};

struct io_buffer {
	struct list_head list;
	__u64 addr;
	__u32 len;
	__u16 bid;
};

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,
};

struct io_sq_data {
	refcount_t		refs;
	atomic_t		park_pending;
	struct mutex		lock;

	/* ctx's that are using this sqd */
	struct list_head	ctx_list;

	struct task_struct	*thread;
	struct wait_queue_head	wait;

	unsigned		sq_thread_idle;
	int			sq_cpu;
	pid_t			task_pid;
	pid_t			task_tgid;

	unsigned long		state;
	struct completion	exited;
	struct callback_head	*park_task_work;
};

#define IO_IOPOLL_BATCH			8
#define IO_COMPL_BATCH			32
#define IO_REQ_CACHE_SIZE		32
#define IO_REQ_ALLOC_BATCH		8

struct io_comp_state {
	struct io_kiocb		*reqs[IO_COMPL_BATCH];
	unsigned int		nr;
	unsigned int		locked_free_nr;
	/* inline/task_work completion list, under ->uring_lock */
	struct list_head	free_list;
	/* IRQ completion list, under ->completion_lock */
	struct list_head	locked_free_list;
};

struct io_submit_link {
	struct io_kiocb		*head;
	struct io_kiocb		*last;
};

struct io_submit_state {
	struct blk_plug		plug;
	struct io_submit_link	link;

	/*
	 * io_kiocb alloc cache
	 */
	void			*reqs[IO_REQ_CACHE_SIZE];
	unsigned int		free_reqs;

	bool			plug_started;

	/*
	 * Batch completion logic
	 */
	struct io_comp_state	comp;

	/*
	 * File reference cache
	 */
	struct file		*file;
	unsigned int		fd;
	unsigned int		file_refs;
	unsigned int		ios_left;
};

struct io_ring_ctx {
	struct {
		struct percpu_ref	refs;
	} ____cacheline_aligned_in_smp;

	struct {
		unsigned int		flags;
		unsigned int		compat: 1;
		unsigned int		drain_next: 1;
		unsigned int		eventfd_async: 1;
		unsigned int		restricted: 1;

		/*
		 * 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;
		unsigned		cached_sq_head;
		unsigned		sq_entries;
		unsigned		sq_mask;
		unsigned		sq_thread_idle;
		unsigned		cached_sq_dropped;
		unsigned		cached_cq_overflow;
		unsigned long		sq_check_overflow;

		/* hashed buffered write serialization */
		struct io_wq_hash	*hash_map;

		struct list_head	defer_list;
		struct list_head	timeout_list;
		struct list_head	cq_overflow_list;

		struct io_uring_sqe	*sq_sqes;
	} ____cacheline_aligned_in_smp;

	struct {
		struct mutex		uring_lock;
		wait_queue_head_t	wait;
	} ____cacheline_aligned_in_smp;

	struct io_submit_state		submit_state;

	struct io_rings	*rings;

	/* Only used for accounting purposes */
	struct mm_struct	*mm_account;

	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;

	/*
	 * If used, fixed file set. Writers must ensure that ->refs is dead,
	 * readers must ensure that ->refs is alive as long as the file* is
	 * used. Only updated through io_uring_register(2).
	 */
	struct io_rsrc_data	*file_data;
	struct io_file_table	file_table;
	unsigned		nr_user_files;

	/* if used, fixed mapped user buffers */
	struct io_rsrc_data	*buf_data;
	unsigned		nr_user_bufs;
	struct io_mapped_ubuf	**user_bufs;

	struct user_struct	*user;

	struct completion	ref_comp;

#if defined(CONFIG_UNIX)
	struct socket		*ring_sock;
#endif

	struct xarray		io_buffers;

	struct xarray		personalities;
	u32			pers_next;

	struct {
		unsigned		cached_cq_tail;
		unsigned		cq_entries;
		unsigned		cq_mask;
		atomic_t		cq_timeouts;
		unsigned		cq_last_tm_flush;
		unsigned		cq_extra;
		unsigned long		cq_check_overflow;
		struct wait_queue_head	cq_wait;
		struct fasync_struct	*cq_fasync;
		struct eventfd_ctx	*cq_ev_fd;
	} ____cacheline_aligned_in_smp;

	struct {
		spinlock_t		completion_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 list_head	iopoll_list;
		struct hlist_head	*cancel_hash;
		unsigned		cancel_hash_bits;
		bool			poll_multi_file;
	} ____cacheline_aligned_in_smp;

	struct delayed_work		rsrc_put_work;
	struct llist_head		rsrc_put_llist;
	struct list_head		rsrc_ref_list;
	spinlock_t			rsrc_ref_lock;
	struct io_rsrc_node		*rsrc_node;
	struct io_rsrc_node		*rsrc_backup_node;
	struct io_mapped_ubuf		*dummy_ubuf;

	struct io_restriction		restrictions;

	/* exit task_work */
	struct callback_head		*exit_task_work;

	/* Keep this last, we don't need it for the fast path */
	struct work_struct		exit_work;
	struct list_head		tctx_list;
};

struct io_uring_task {
	/* submission side */
	struct xarray		xa;
	struct wait_queue_head	wait;
	const struct io_ring_ctx *last;
	struct io_wq		*io_wq;
	struct percpu_counter	inflight;
	atomic_t		inflight_tracked;
	atomic_t		in_idle;

	spinlock_t		task_lock;
	struct io_wq_work_list	task_list;
	unsigned long		task_state;
	struct callback_head	task_work;
};

/*
 * First field must be the file pointer in all the
 * iocb unions! See also 'struct kiocb' in <linux/fs.h>
 */
struct io_poll_iocb {
	struct file			*file;
	struct wait_queue_head		*head;
	__poll_t			events;
	bool				done;
	bool				canceled;
	struct wait_queue_entry		wait;
};

struct io_poll_update {
	struct file			*file;
	u64				old_user_data;
	u64				new_user_data;
	__poll_t			events;
	bool				update_events;
	bool				update_user_data;
};

struct io_close {
	struct file			*file;
	int				fd;
};

struct io_timeout_data {
	struct io_kiocb			*req;
	struct hrtimer			timer;
	struct timespec64		ts;
	enum hrtimer_mode		mode;
};

struct io_accept {
	struct file			*file;
	struct sockaddr __user		*addr;
	int __user			*addr_len;
	int				flags;
	unsigned long			nofile;
};

struct io_sync {
	struct file			*file;
	loff_t				len;
	loff_t				off;
	int				flags;
	int				mode;
};

struct io_cancel {
	struct file			*file;
	u64				addr;
};

struct io_timeout {
	struct file			*file;
	u32				off;
	u32				target_seq;
	struct list_head		list;
	/* head of the link, used by linked timeouts only */
	struct io_kiocb			*head;
};

struct io_timeout_rem {
	struct file			*file;
	u64				addr;

	/* timeout update */
	struct timespec64		ts;
	u32				flags;
};

struct io_rw {
	/* NOTE: kiocb has the file as the first member, so don't do it here */
	struct kiocb			kiocb;
	u64				addr;
	u64				len;
};

struct io_connect {
	struct file			*file;
	struct sockaddr __user		*addr;
	int				addr_len;
};

struct io_sr_msg {
	struct file			*file;
	union {
		struct compat_msghdr __user	*umsg_compat;
		struct user_msghdr __user	*umsg;
		void __user			*buf;
	};
	int				msg_flags;
	int				bgid;
	size_t				len;
	struct io_buffer		*kbuf;
};

struct io_open {
	struct file			*file;
	int				dfd;
	struct filename			*filename;
	struct open_how			how;
	unsigned long			nofile;
};

struct io_rsrc_update {
	struct file			*file;
	u64				arg;
	u32				nr_args;
	u32				offset;
};

struct io_fadvise {
	struct file			*file;
	u64				offset;
	u32				len;
	u32				advice;
};

struct io_madvise {
	struct file			*file;
	u64				addr;
	u32				len;
	u32				advice;
};

struct io_epoll {
	struct file			*file;
	int				epfd;
	int				op;
	int				fd;
	struct epoll_event		event;
};

struct io_splice {
	struct file			*file_out;
	struct file			*file_in;
	loff_t				off_out;
	loff_t				off_in;
	u64				len;
	unsigned int			flags;
};

struct io_provide_buf {
	struct file			*file;
	__u64				addr;
	__u32				len;
	__u32				bgid;
	__u16				nbufs;
	__u16				bid;
};

struct io_statx {
	struct file			*file;
	int				dfd;
	unsigned int			mask;
	unsigned int			flags;
	const char __user		*filename;
	struct statx __user		*buffer;
};

struct io_shutdown {
	struct file			*file;
	int				how;
};

struct io_rename {
	struct file			*file;
	int				old_dfd;
	int				new_dfd;
	struct filename			*oldpath;
	struct filename			*newpath;
	int				flags;
};

struct io_unlink {
	struct file			*file;
	int				dfd;
	int				flags;
	struct filename			*filename;
};

struct io_completion {
	struct file			*file;
	struct list_head		list;
	u32				cflags;
};

struct io_async_connect {
	struct sockaddr_storage		address;
};

struct io_async_msghdr {
	struct iovec			fast_iov[UIO_FASTIOV];
	/* points to an allocated iov, if NULL we use fast_iov instead */
	struct iovec			*free_iov;
	struct sockaddr __user		*uaddr;
	struct msghdr			msg;
	struct sockaddr_storage		addr;
};

struct io_async_rw {
	struct iovec			fast_iov[UIO_FASTIOV];
	const struct iovec		*free_iovec;
	struct iov_iter			iter;
	size_t				bytes_done;
	struct wait_page_queue		wpq;
};

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,

	/* first byte is taken by user flags, shift it to not overlap */
	REQ_F_FAIL_LINK_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_LTIMEOUT_ACTIVE_BIT,
	REQ_F_COMPLETE_INLINE_BIT,
	REQ_F_REISSUE_BIT,
	REQ_F_DONT_REISSUE_BIT,
	/* keep async read/write and isreg together and in order */
	REQ_F_ASYNC_READ_BIT,
	REQ_F_ASYNC_WRITE_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),

	/* fail rest of links */
	REQ_F_FAIL_LINK		= BIT(REQ_F_FAIL_LINK_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),
	/* linked timeout is active, i.e. prepared by link's head */
	REQ_F_LTIMEOUT_ACTIVE	= BIT(REQ_F_LTIMEOUT_ACTIVE_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),
	/* don't attempt request reissue, see io_rw_reissue() */
	REQ_F_DONT_REISSUE	= BIT(REQ_F_DONT_REISSUE_BIT),
	/* supports async reads */
	REQ_F_ASYNC_READ	= BIT(REQ_F_ASYNC_READ_BIT),
	/* supports async writes */
	REQ_F_ASYNC_WRITE	= BIT(REQ_F_ASYNC_WRITE_BIT),
	/* regular file */
	REQ_F_ISREG		= BIT(REQ_F_ISREG_BIT),
};

struct async_poll {
	struct io_poll_iocb	poll;
	struct io_poll_iocb	*double_poll;
};

struct io_task_work {
	struct io_wq_work_node	node;
	task_work_func_t	func;
};

enum {
	IORING_RSRC_FILE		= 0,
	IORING_RSRC_BUFFER		= 1,
};

/*
 * NOTE! Each of the iocb 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 'ki_filp' in this struct.
 */
struct io_kiocb {
	union {
		struct file		*file;
		struct io_rw		rw;
		struct io_poll_iocb	poll;
		struct io_poll_update	poll_update;
		struct io_accept	accept;
		struct io_sync		sync;
		struct io_cancel	cancel;
		struct io_timeout	timeout;
		struct io_timeout_rem	timeout_rem;
		struct io_connect	connect;
		struct io_sr_msg	sr_msg;
		struct io_open		open;
		struct io_close		close;
		struct io_rsrc_update	rsrc_update;
		struct io_fadvise	fadvise;
		struct io_madvise	madvise;
		struct io_epoll		epoll;
		struct io_splice	splice;
		struct io_provide_buf	pbuf;
		struct io_statx		statx;
		struct io_shutdown	shutdown;
		struct io_rename	rename;
		struct io_unlink	unlink;
		/* use only after cleaning per-op data, see io_clean_op() */
		struct io_completion	compl;
	};

	/* opcode allocated if it needs to store data for async defer */
	void				*async_data;
	u8				opcode;
	/* polled IO has completed */
	u8				iopoll_completed;

	u16				buf_index;
	u32				result;

	struct io_ring_ctx		*ctx;
	unsigned int			flags;
	atomic_t			refs;
	struct task_struct		*task;
	u64				user_data;

	struct io_kiocb			*link;
	struct percpu_ref		*fixed_rsrc_refs;

	/* used with ctx->iopoll_list with reads/writes */
	struct list_head		inflight_entry;
	union {
		struct io_task_work	io_task_work;
		struct callback_head	task_work;
	};
	/* for polled requests, i.e. IORING_OP_POLL_ADD and async armed poll */
	struct hlist_node		hash_node;
	struct async_poll		*apoll;
	struct io_wq_work		work;
	/* store used ubuf, so we can prevent reloading */
	struct io_mapped_ubuf		*imu;
};

struct io_tctx_node {
	struct list_head	ctx_node;
	struct task_struct	*task;
	struct io_ring_ctx	*ctx;
};

struct io_defer_entry {
	struct list_head	list;
	struct io_kiocb		*req;
	u32			seq;
};

struct io_op_def {
	/* needs req->file assigned */
	unsigned		needs_file : 1;
	/* hash wq insertion if file is a regular file */
	unsigned		hash_reg_file : 1;
	/* unbound wq insertion if file is a non-regular file */
	unsigned		unbound_nonreg_file : 1;
	/* opcode is not supported by this kernel */
	unsigned		not_supported : 1;
	/* set if opcode supports polled "wait" */
	unsigned		pollin : 1;
	unsigned		pollout : 1;
	/* op supports buffer selection */
	unsigned		buffer_select : 1;
	/* do prep async if is going to be punted */
	unsigned		needs_async_setup : 1;
	/* should block plug */
	unsigned		plug : 1;
	/* size of async data needed, if any */
	unsigned short		async_size;
};

static const struct io_op_def io_op_defs[] = {
	[IORING_OP_NOP] = {},
	[IORING_OP_READV] = {
		.needs_file		= 1,
		.unbound_nonreg_file	= 1,
		.pollin			= 1,
		.buffer_select		= 1,
		.needs_async_setup	= 1,
		.plug			= 1,
		.async_size		= sizeof(struct io_async_rw),
	},
	[IORING_OP_WRITEV] = {
		.needs_file		= 1,
		.hash_reg_file		= 1,
		.unbound_nonreg_file	= 1,
		.pollout		= 1,
		.needs_async_setup	= 1,
		.plug			= 1,
		.async_size		= sizeof(struct io_async_rw),
	},
	[IORING_OP_FSYNC] = {
		.needs_file		= 1,
	},
	[IORING_OP_READ_FIXED] = {
		.needs_file		= 1,
		.unbound_nonreg_file	= 1,
		.pollin			= 1,
		.plug			= 1,
		.async_size		= sizeof(struct io_async_rw),
	},
	[IORING_OP_WRITE_FIXED] = {
		.needs_file		= 1,
		.hash_reg_file		= 1,
		.unbound_nonreg_file	= 1,
		.pollout		= 1,
		.plug			= 1,
		.async_size		= sizeof(struct io_async_rw),
	},
	[IORING_OP_POLL_ADD] = {
		.needs_file		= 1,
		.unbound_nonreg_file	= 1,
	},
	[IORING_OP_POLL_REMOVE] = {},
	[IORING_OP_SYNC_FILE_RANGE] = {
		.needs_file		= 1,
	},
	[IORING_OP_SENDMSG] = {
		.needs_file		= 1,
		.unbound_nonreg_file	= 1,
		.pollout		= 1,
		.needs_async_setup	= 1,
		.async_size		= sizeof(struct io_async_msghdr),
	},
	[IORING_OP_RECVMSG] = {
		.needs_file		= 1,
		.unbound_nonreg_file	= 1,
		.pollin			= 1,
		.buffer_select		= 1,
		.needs_async_setup	= 1,
		.async_size		= sizeof(struct io_async_msghdr),
	},
	[IORING_OP_TIMEOUT] = {
		.async_size		= sizeof(struct io_timeout_data),
	},
	[IORING_OP_TIMEOUT_REMOVE] = {
		/* used by timeout updates' prep() */
	},
	[IORING_OP_ACCEPT] = {
		.needs_file		= 1,
		.unbound_nonreg_file	= 1,
		.pollin			= 1,
	},
	[IORING_OP_ASYNC_CANCEL] = {},
	[IORING_OP_LINK_TIMEOUT] = {
		.async_size		= sizeof(struct io_timeout_data),
	},
	[IORING_OP_CONNECT] = {
		.needs_file		= 1,
		.unbound_nonreg_file	= 1,
		.pollout		= 1,
		.needs_async_setup	= 1,
		.async_size		= sizeof(struct io_async_connect),
	},
	[IORING_OP_FALLOCATE] = {
		.needs_file		= 1,
	},
	[IORING_OP_OPENAT] = {},
	[IORING_OP_CLOSE] = {},
	[IORING_OP_FILES_UPDATE] = {},
	[IORING_OP_STATX] = {},
	[IORING_OP_READ] = {
		.needs_file		= 1,
		.unbound_nonreg_file	= 1,
		.pollin			= 1,
		.buffer_select		= 1,
		.plug			= 1,
		.async_size		= sizeof(struct io_async_rw),
	},
	[IORING_OP_WRITE] = {
		.needs_file		= 1,
		.unbound_nonreg_file	= 1,
		.pollout		= 1,
		.plug			= 1,
		.async_size		= sizeof(struct io_async_rw),
	},
	[IORING_OP_FADVISE] = {
		.needs_file		= 1,
	},
	[IORING_OP_MADVISE] = {},
	[IORING_OP_SEND] = {
		.needs_file		= 1,
		.unbound_nonreg_file	= 1,
		.pollout		= 1,
	},
	[IORING_OP_RECV] = {
		.needs_file		= 1,
		.unbound_nonreg_file	= 1,
		.pollin			= 1,
		.buffer_select		= 1,
	},
	[IORING_OP_OPENAT2] = {
	},
	[IORING_OP_EPOLL_CTL] = {
		.unbound_nonreg_file	= 1,
	},
	[IORING_OP_SPLICE] = {
		.needs_file		= 1,
		.hash_reg_file		= 1,
		.unbound_nonreg_file	= 1,
	},
	[IORING_OP_PROVIDE_BUFFERS] = {},
	[IORING_OP_REMOVE_BUFFERS] = {},
	[IORING_OP_TEE] = {
		.needs_file		= 1,
		.hash_reg_file		= 1,
		.unbound_nonreg_file	= 1,
	},
	[IORING_OP_SHUTDOWN] = {
		.needs_file		= 1,
	},
	[IORING_OP_RENAMEAT] = {},
	[IORING_OP_UNLINKAT] = {},
};

static bool io_disarm_next(struct io_kiocb *req);
static void io_uring_del_task_file(unsigned long index);
static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
					 struct task_struct *task,
					 struct files_struct *files);
static void io_uring_cancel_sqpoll(struct io_sq_data *sqd);
static struct io_rsrc_node *io_rsrc_node_alloc(struct io_ring_ctx *ctx);

static bool io_cqring_fill_event(struct io_ring_ctx *ctx, u64 user_data,
				 long res, unsigned int cflags);
static void io_put_req(struct io_kiocb *req);
static void io_put_req_deferred(struct io_kiocb *req, int nr);
static void io_dismantle_req(struct io_kiocb *req);
static void io_put_task(struct task_struct *task, int nr);
static struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req);
static void io_queue_linked_timeout(struct io_kiocb *req);
static int __io_register_rsrc_update(struct io_ring_ctx *ctx, unsigned type,
				     struct io_uring_rsrc_update2 *up,
				     unsigned nr_args);
static void io_clean_op(struct io_kiocb *req);
static struct file *io_file_get(struct io_submit_state *state,
				struct io_kiocb *req, int fd, bool fixed);
static void __io_queue_sqe(struct io_kiocb *req);
static void io_rsrc_put_work(struct work_struct *work);

static void io_req_task_queue(struct io_kiocb *req);
static void io_submit_flush_completions(struct io_comp_state *cs,
					struct io_ring_ctx *ctx);
static bool io_poll_remove_waitqs(struct io_kiocb *req);
static int io_req_prep_async(struct io_kiocb *req);

static struct kmem_cache *req_cachep;

static const struct file_operations io_uring_fops;

struct sock *io_uring_get_socket(struct file *file)
{
#if defined(CONFIG_UNIX)
	if (file->f_op == &io_uring_fops) {
		struct io_ring_ctx *ctx = file->private_data;

		return ctx->ring_sock->sk;
	}
#endif
	return NULL;
}
EXPORT_SYMBOL(io_uring_get_socket);

#define io_for_each_link(pos, head) \
	for (pos = (head); pos; pos = pos->link)

static inline void io_req_set_rsrc_node(struct io_kiocb *req)
{
	struct io_ring_ctx *ctx = req->ctx;

	if (!req->fixed_rsrc_refs) {
		req->fixed_rsrc_refs = &ctx->rsrc_node->refs;
		percpu_ref_get(req->fixed_rsrc_refs);
	}
}

static void io_refs_resurrect(struct percpu_ref *ref, struct completion *compl)
{
	bool got = percpu_ref_tryget(ref);

	/* already at zero, wait for ->release() */
	if (!got)
		wait_for_completion(compl);
	percpu_ref_resurrect(ref);
	if (got)
		percpu_ref_put(ref);
}

static bool io_match_task(struct io_kiocb *head,
			  struct task_struct *task,
			  struct files_struct *files)
{
	struct io_kiocb *req;

	if (task && head->task != task)
		return false;
	if (!files)
		return true;

	io_for_each_link(req, head) {
		if (req->flags & REQ_F_INFLIGHT)
			return true;
	}
	return false;
}

static inline void req_set_fail_links(struct io_kiocb *req)
{
	if (req->flags & REQ_F_LINK)
		req->flags |= REQ_F_FAIL_LINK;
}

static void io_ring_ctx_ref_free(struct percpu_ref *ref)
{
	struct io_ring_ctx *ctx = container_of(ref, struct io_ring_ctx, refs);

	complete(&ctx->ref_comp);
}

static inline bool io_is_timeout_noseq(struct io_kiocb *req)
{
	return !req->timeout.off;
}

static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
{
	struct io_ring_ctx *ctx;
	int hash_bits;

	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
	if (!ctx)
		return NULL;

	/*
	 * Use 5 bits less than the max cq entries, that should give us around
	 * 32 entries per hash list if totally full and uniformly spread.
	 */
	hash_bits = ilog2(p->cq_entries);
	hash_bits -= 5;
	if (hash_bits <= 0)
		hash_bits = 1;
	ctx->cancel_hash_bits = hash_bits;
	ctx->cancel_hash = kmalloc((1U << hash_bits) * sizeof(struct hlist_head),
					GFP_KERNEL);
	if (!ctx->cancel_hash)
		goto err;
	__hash_init(ctx->cancel_hash, 1U << hash_bits);

	ctx->dummy_ubuf = kzalloc(sizeof(*ctx->dummy_ubuf), GFP_KERNEL);
	if (!ctx->dummy_ubuf)
		goto err;
	/* set invalid range, so io_import_fixed() fails meeting it */
	ctx->dummy_ubuf->ubuf = -1UL;

	if (percpu_ref_init(&ctx->refs, io_ring_ctx_ref_free,
			    PERCPU_REF_ALLOW_REINIT, GFP_KERNEL))
		goto err;

	ctx->flags = p->flags;
	init_waitqueue_head(&ctx->sqo_sq_wait);
	INIT_LIST_HEAD(&ctx->sqd_list);
	init_waitqueue_head(&ctx->cq_wait);
	INIT_LIST_HEAD(&ctx->cq_overflow_list);
	init_completion(&ctx->ref_comp);
	xa_init_flags(&ctx->io_buffers, XA_FLAGS_ALLOC1);
	xa_init_flags(&ctx->personalities, XA_FLAGS_ALLOC1);
	mutex_init(&ctx->uring_lock);
	init_waitqueue_head(&ctx->wait);
	spin_lock_init(&ctx->completion_lock);
	INIT_LIST_HEAD(&ctx->iopoll_list);
	INIT_LIST_HEAD(&ctx->defer_list);
	INIT_LIST_HEAD(&ctx->timeout_list);
	spin_lock_init(&ctx->rsrc_ref_lock);
	INIT_LIST_HEAD(&ctx->rsrc_ref_list);
	INIT_DELAYED_WORK(&ctx->rsrc_put_work, io_rsrc_put_work);
	init_llist_head(&ctx->rsrc_put_llist);
	INIT_LIST_HEAD(&ctx->tctx_list);
	INIT_LIST_HEAD(&ctx->submit_state.comp.free_list);
	INIT_LIST_HEAD(&ctx->submit_state.comp.locked_free_list);
	return ctx;
err:
	kfree(ctx->dummy_ubuf);
	kfree(ctx->cancel_hash);
	kfree(ctx);
	return NULL;
}

static bool req_need_defer(struct io_kiocb *req, u32 seq)
{
	if (unlikely(req->flags & REQ_F_IO_DRAIN)) {
		struct io_ring_ctx *ctx = req->ctx;

		return seq + ctx->cq_extra != ctx->cached_cq_tail
				+ READ_ONCE(ctx->cached_cq_overflow);
	}

	return false;
}

static void io_req_track_inflight(struct io_kiocb *req)
{
	if (!(req->flags & REQ_F_INFLIGHT)) {
		req->flags |= REQ_F_INFLIGHT;
		atomic_inc(&current->io_uring->inflight_tracked);
	}
}

static void io_prep_async_work(struct io_kiocb *req)
{
	const struct io_op_def *def = &io_op_defs[req->opcode];
	struct io_ring_ctx *ctx = req->ctx;

	if (!req->work.creds)
		req->work.creds = get_current_cred();

	req->work.list.next = NULL;
	req->work.flags = 0;
	if (req->flags & REQ_F_FORCE_ASYNC)
		req->work.flags |= IO_WQ_WORK_CONCURRENT;

	if (req->flags & REQ_F_ISREG) {
		if (def->hash_reg_file || (ctx->flags & IORING_SETUP_IOPOLL))
			io_wq_hash_work(&req->work, file_inode(req->file));
	} else if (!req->file || !S_ISBLK(file_inode(req->file)->i_mode)) {
		if (def->unbound_nonreg_file)
			req->work.flags |= IO_WQ_WORK_UNBOUND;
	}

	switch (req->opcode) {
	case IORING_OP_SPLICE:
	case IORING_OP_TEE:
		if (!S_ISREG(file_inode(req->splice.file_in)->i_mode))
			req->work.flags |= IO_WQ_WORK_UNBOUND;
		break;
	}
}

static void io_prep_async_link(struct io_kiocb *req)
{
	struct io_kiocb *cur;

	io_for_each_link(cur, req)
		io_prep_async_work(cur);
}

static void io_queue_async_work(struct io_kiocb *req)
{
	struct io_ring_ctx *ctx = req->ctx;
	struct io_kiocb *link = io_prep_linked_timeout(req);
	struct io_uring_task *tctx = req->task->io_uring;

	BUG_ON(!tctx);
	BUG_ON(!tctx->io_wq);

	/* init ->work of the whole link before punting */
	io_prep_async_link(req);
	trace_io_uring_queue_async_work(ctx, io_wq_is_hashed(&req->work), req,
					&req->work, req->flags);
	io_wq_enqueue(tctx->io_wq, &req->work);
	if (link)
		io_queue_linked_timeout(link);
}

static void io_kill_timeout(struct io_kiocb *req, int status)
	__must_hold(&req->ctx->completion_lock)
{
	struct io_timeout_data *io = req->async_data;

	if (hrtimer_try_to_cancel(&io->timer) != -1) {
		atomic_set(&req->ctx->cq_timeouts,
			atomic_read(&req->ctx->cq_timeouts) + 1);
		list_del_init(&req->timeout.list);
		io_cqring_fill_event(req->ctx, req->user_data, status, 0);
		io_put_req_deferred(req, 1);
	}
}

static void __io_queue_deferred(struct io_ring_ctx *ctx)
{
	do {
		struct io_defer_entry *de = list_first_entry(&ctx->defer_list,
						struct io_defer_entry, list);

		if (req_need_defer(de->req, de->seq))
			break;
		list_del_init(&de->list);
		io_req_task_queue(de->req);
		kfree(de);
	} while (!list_empty(&ctx->defer_list));
}

static void io_flush_timeouts(struct io_ring_ctx *ctx)
{
	u32 seq;

	if (list_empty(&ctx->timeout_list))
		return;

	seq = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts);

	do {
		u32 events_needed, events_got;
		struct io_kiocb *req = list_first_entry(&ctx->timeout_list,
						struct io_kiocb, timeout.list);

		if (io_is_timeout_noseq(req))
			break;

		/*
		 * Since seq can easily wrap around over time, subtract
		 * the last seq at which timeouts were flushed before comparing.
		 * Assuming not more than 2^31-1 events have happened since,
		 * these subtractions won't have wrapped, so we can check if
		 * target is in [last_seq, current_seq] by comparing the two.
		 */
		events_needed = req->timeout.target_seq - ctx->cq_last_tm_flush;
		events_got = seq - ctx->cq_last_tm_flush;
		if (events_got < events_needed)
			break;

		list_del_init(&req->timeout.list);
		io_kill_timeout(req, 0);
	} while (!list_empty(&ctx->timeout_list));

	ctx->cq_last_tm_flush = seq;
}

static void io_commit_cqring(struct io_ring_ctx *ctx)
{
	io_flush_timeouts(ctx);

	/* order cqe stores with ring update */
	smp_store_release(&ctx->rings->cq.tail, ctx->cached_cq_tail);

	if (unlikely(!list_empty(&ctx->defer_list)))
		__io_queue_deferred(ctx);
}

static inline bool io_sqring_full(struct io_ring_ctx *ctx)
{
	struct io_rings *r = ctx->rings;

	return READ_ONCE(r->sq.tail) - ctx->cached_sq_head == r->sq_ring_entries;
}

static inline unsigned int __io_cqring_events(struct io_ring_ctx *ctx)
{
	return ctx->cached_cq_tail - READ_ONCE(ctx->rings->cq.head);
}

static inline struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx)
{
	struct io_rings *rings = ctx->rings;
	unsigned tail;

	/*
	 * writes to the cq entry need to come after reading head; the
	 * control dependency is enough as we're using WRITE_ONCE to
	 * fill the cq entry
	 */
	if (__io_cqring_events(ctx) == rings->cq_ring_entries)
		return NULL;

	tail = ctx->cached_cq_tail++;
	return &rings->cqes[tail & ctx->cq_mask];
}

static inline bool io_should_trigger_evfd(struct io_ring_ctx *ctx)
{
	if (likely(!ctx->cq_ev_fd))
		return false;
	if (READ_ONCE(ctx->rings->cq_flags) & IORING_CQ_EVENTFD_DISABLED)
		return false;
	return !ctx->eventfd_async || io_wq_current_is_worker();
}

static void io_cqring_ev_posted(struct io_ring_ctx *ctx)
{
	/* see waitqueue_active() comment */
	smp_mb();

	if (waitqueue_active(&ctx->wait))
		wake_up(&ctx->wait);
	if (ctx->sq_data && waitqueue_active(&ctx->sq_data->wait))
		wake_up(&ctx->sq_data->wait);
	if (io_should_trigger_evfd(ctx))
		eventfd_signal(ctx->cq_ev_fd, 1);
	if (waitqueue_active(&ctx->cq_wait)) {
		wake_up_interruptible(&ctx->cq_wait);
		kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN);
	}
}

static void io_cqring_ev_posted_iopoll(struct io_ring_ctx *ctx)
{
	/* see waitqueue_active() comment */
	smp_mb();

	if (ctx->flags & IORING_SETUP_SQPOLL) {
		if (waitqueue_active(&ctx->wait))
			wake_up(&ctx->wait);
	}
	if (io_should_trigger_evfd(ctx))
		eventfd_signal(ctx->cq_ev_fd, 1);
	if (waitqueue_active(&ctx->cq_wait)) {
		wake_up_interruptible(&ctx->cq_wait);
		kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN);
	}
}

/* Returns true if there are no backlogged entries after the flush */
static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force)
{
	struct io_rings *rings = ctx->rings;
	unsigned long flags;
	bool all_flushed, posted;

	if (!force && __io_cqring_events(ctx) == rings->cq_ring_entries)
		return false;

	posted = false;
	spin_lock_irqsave(&ctx->completion_lock, flags);
	while (!list_empty(&ctx->cq_overflow_list)) {
		struct io_uring_cqe *cqe = io_get_cqring(ctx);
		struct io_overflow_cqe *ocqe;

		if (!cqe && !force)
			break;
		ocqe = list_first_entry(&ctx->cq_overflow_list,
					struct io_overflow_cqe, list);
		if (cqe)
			memcpy(cqe, &ocqe->cqe, sizeof(*cqe));
		else
			WRITE_ONCE(ctx->rings->cq_overflow,
				   ++ctx->cached_cq_overflow);
		posted = true;
		list_del(&ocqe->list);
		kfree(ocqe);
	}

	all_flushed = list_empty(&ctx->cq_overflow_list);
	if (all_flushed) {
		clear_bit(0, &ctx->sq_check_overflow);
		clear_bit(0, &ctx->cq_check_overflow);
		ctx->rings->sq_flags &= ~IORING_SQ_CQ_OVERFLOW;
	}

	if (posted)
		io_commit_cqring(ctx);
	spin_unlock_irqrestore(&ctx->completion_lock, flags);
	if (posted)
		io_cqring_ev_posted(ctx);
	return all_flushed;
}

static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force)
{
	bool ret = true;

	if (test_bit(0, &ctx->cq_check_overflow)) {
		/* iopoll syncs against uring_lock, not completion_lock */
		if (ctx->flags & IORING_SETUP_IOPOLL)
			mutex_lock(&ctx->uring_lock);
		ret = __io_cqring_overflow_flush(ctx, force);
		if (ctx->flags & IORING_SETUP_IOPOLL)
			mutex_unlock(&ctx->uring_lock);
	}

	return ret;
}

/*
 * Shamelessly stolen from the mm implementation of page reference checking,
 * see commit f958d7b528b1 for details.
 */
#define req_ref_zero_or_close_to_overflow(req)	\
	((unsigned int) atomic_read(&(req->refs)) + 127u <= 127u)

static inline bool req_ref_inc_not_zero(struct io_kiocb *req)
{
	return atomic_inc_not_zero(&req->refs);
}

static inline bool req_ref_sub_and_test(struct io_kiocb *req, int refs)
{
	WARN_ON_ONCE(req_ref_zero_or_close_to_overflow(req));
	return atomic_sub_and_test(refs, &req->refs);
}

static inline bool req_ref_put_and_test(struct io_kiocb *req)
{
	WARN_ON_ONCE(req_ref_zero_or_close_to_overflow(req));
	return atomic_dec_and_test(&req->refs);
}

static inline void req_ref_put(struct io_kiocb *req)
{
	WARN_ON_ONCE(req_ref_put_and_test(req));
}

static inline void req_ref_get(struct io_kiocb *req)
{
	WARN_ON_ONCE(req_ref_zero_or_close_to_overflow(req));
	atomic_inc(&req->refs);
}

static bool io_cqring_event_overflow(struct io_ring_ctx *ctx, u64 user_data,
				     long res, unsigned int cflags)
{
	struct io_overflow_cqe *ocqe;

	ocqe = kmalloc(sizeof(*ocqe), GFP_ATOMIC | __GFP_ACCOUNT);
	if (!ocqe) {
		/*
		 * If we're in ring overflow flush mode, or in task cancel mode,
		 * or cannot allocate an overflow entry, then we need to drop it
		 * on the floor.
		 */
		WRITE_ONCE(ctx->rings->cq_overflow, ++ctx->cached_cq_overflow);
		return false;
	}
	if (list_empty(&ctx->cq_overflow_list)) {
		set_bit(0, &ctx->sq_check_overflow);
		set_bit(0, &ctx->cq_check_overflow);
		ctx->rings->sq_flags |= IORING_SQ_CQ_OVERFLOW;
	}
	ocqe->cqe.user_data = user_data;
	ocqe->cqe.res = res;
	ocqe->cqe.flags = cflags;
	list_add_tail(&ocqe->list, &ctx->cq_overflow_list);
	return true;
}

static inline bool __io_cqring_fill_event(struct io_ring_ctx *ctx, u64 user_data,
					  long res, unsigned int cflags)
{
	struct io_uring_cqe *cqe;

	trace_io_uring_complete(ctx, user_data, res, cflags);

	/*
	 * If we can't get a cq entry, userspace overflowed the
	 * submission (by quite a lot). Increment the overflow count in
	 * the ring.
	 */
	cqe = io_get_cqring(ctx);
	if (likely(cqe)) {
		WRITE_ONCE(cqe->user_data, user_data);
		WRITE_ONCE(cqe->res, res);
		WRITE_ONCE(cqe->flags, cflags);
		return true;
	}
	return io_cqring_event_overflow(ctx, user_data, res, cflags);
}

/* not as hot to bloat with inlining */
static noinline bool io_cqring_fill_event(struct io_ring_ctx *ctx, u64 user_data,
					  long res, unsigned int cflags)
{
	return __io_cqring_fill_event(ctx, user_data, res, cflags);
}

static void io_req_complete_post(struct io_kiocb *req, long res,
				 unsigned int cflags)
{
	struct io_ring_ctx *ctx = req->ctx;
	unsigned long flags;

	spin_lock_irqsave(&ctx->completion_lock, flags);
	__io_cqring_fill_event(ctx, req->user_data, res, cflags);
	/*
	 * If we're the last reference to this request, add to our locked
	 * free_list cache.
	 */
	if (req_ref_put_and_test(req)) {
		struct io_comp_state *cs = &ctx->submit_state.comp;

		if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK)) {
			if (req->flags & (REQ_F_LINK_TIMEOUT | REQ_F_FAIL_LINK))
				io_disarm_next(req);
			if (req->link) {
				io_req_task_queue(req->link);
				req->link = NULL;
			}
		}
		io_dismantle_req(req);
		io_put_task(req->task, 1);
		list_add(&req->compl.list, &cs->locked_free_list);
		cs->locked_free_nr++;
	} else {
		if (!percpu_ref_tryget(&ctx->refs))
			req = NULL;
	}
	io_commit_cqring(ctx);
	spin_unlock_irqrestore(&ctx->completion_lock, flags);

	if (req) {
		io_cqring_ev_posted(ctx);
		percpu_ref_put(&ctx->refs);
	}
}

static inline bool io_req_needs_clean(struct io_kiocb *req)
{
	return req->flags & (REQ_F_BUFFER_SELECTED | REQ_F_NEED_CLEANUP |
				REQ_F_POLLED | REQ_F_INFLIGHT);
}

static void io_req_complete_state(struct io_kiocb *req, long res,
				  unsigned int cflags)
{
	if (io_req_needs_clean(req))
		io_clean_op(req);
	req->result = res;
	req->compl.cflags = cflags;
	req->flags |= REQ_F_COMPLETE_INLINE;
}

static inline void __io_req_complete(struct io_kiocb *req, unsigned issue_flags,
				     long res, unsigned cflags)
{
	if (issue_flags & IO_URING_F_COMPLETE_DEFER)
		io_req_complete_state(req, res, cflags);
	else
		io_req_complete_post(req, res, cflags);
}

static inline void io_req_complete(struct io_kiocb *req, long res)
{
	__io_req_complete(req, 0, res, 0);
}

static void io_req_complete_failed(struct io_kiocb *req, long res)
{
	req_set_fail_links(req);
	io_put_req(req);
	io_req_complete_post(req, res, 0);
}

static void io_flush_cached_locked_reqs(struct io_ring_ctx *ctx,
					struct io_comp_state *cs)
{
	spin_lock_irq(&ctx->completion_lock);
	list_splice_init(&cs->locked_free_list, &cs->free_list);
	cs->locked_free_nr = 0;
	spin_unlock_irq(&ctx->completion_lock);
}

/* Returns true IFF there are requests in the cache */
static bool io_flush_cached_reqs(struct io_ring_ctx *ctx)
{
	struct io_submit_state *state = &ctx->submit_state;
	struct io_comp_state *cs = &state->comp;
	int nr;

	/*
	 * If we have more than a batch's worth of requests in our IRQ side
	 * locked cache, grab the lock and move them over to our submission
	 * side cache.
	 */
	if (READ_ONCE(cs->locked_free_nr) > IO_COMPL_BATCH)
		io_flush_cached_locked_reqs(ctx, cs);

	nr = state->free_reqs;
	while (!list_empty(&cs->free_list)) {
		struct io_kiocb *req = list_first_entry(&cs->free_list,
						struct io_kiocb, compl.list);

		list_del(&req->compl.list);
		state->reqs[nr++] = req;
		if (nr == ARRAY_SIZE(state->reqs))
			break;
	}

	state->free_reqs = nr;
	return nr != 0;
}

static struct io_kiocb *io_alloc_req(struct io_ring_ctx *ctx)
{
	struct io_submit_state *state = &ctx->submit_state;

	BUILD_BUG_ON(IO_REQ_ALLOC_BATCH > ARRAY_SIZE(state->reqs));

	if (!state->free_reqs) {
		gfp_t gfp = GFP_KERNEL | __GFP_NOWARN;
		int ret;

		if (io_flush_cached_reqs(ctx))
			goto got_req;

		ret = kmem_cache_alloc_bulk(req_cachep, gfp, IO_REQ_ALLOC_BATCH,
					    state->reqs);

		/*
		 * Bulk alloc is all-or-nothing. If we fail to get a batch,
		 * retry single alloc to be on the safe side.
		 */
		if (unlikely(ret <= 0)) {
			state->reqs[0] = kmem_cache_alloc(req_cachep, gfp);
			if (!state->reqs[0])
				return NULL;
			ret = 1;
		}
		state->free_reqs = ret;
	}
got_req:
	state->free_reqs--;
	return state->reqs[state->free_reqs];
}

static inline void io_put_file(struct file *file)
{
	if (file)
		fput(file);
}

static void io_dismantle_req(struct io_kiocb *req)
{
	unsigned int flags = req->flags;

	if (io_req_needs_clean(req))
		io_clean_op(req);
	if (!(flags & REQ_F_FIXED_FILE))
		io_put_file(req->file);
	if (req->fixed_rsrc_refs)
		percpu_ref_put(req->fixed_rsrc_refs);
	if (req->async_data)
		kfree(req->async_data);
	if (req->work.creds) {
		put_cred(req->work.creds);
		req->work.creds = NULL;
	}
}

/* must to be called somewhat shortly after putting a request */
static inline void io_put_task(struct task_struct *task, int nr)
{
	struct io_uring_task *tctx = task->io_uring;

	percpu_counter_sub(&tctx->inflight, nr);
	if (unlikely(atomic_read(&tctx->in_idle)))
		wake_up(&tctx->wait);
	put_task_struct_many(task, nr);
}

static void __io_free_req(struct io_kiocb *req)
{
	struct io_ring_ctx *ctx = req->ctx;

	io_dismantle_req(req);
	io_put_task(req->task, 1);

	kmem_cache_free(req_cachep, req);
	percpu_ref_put(&ctx->refs);
}

static inline void io_remove_next_linked(struct io_kiocb *req)
{
	struct io_kiocb *nxt = req->link;

	req->link = nxt->link;
	nxt->link = NULL;
}

static bool io_kill_linked_timeout(struct io_kiocb *req)
	__must_hold(&req->ctx->completion_lock)
{
	struct io_kiocb *link = req->link;

	/*
	 * Can happen if a linked timeout fired and link had been like
	 * req -> link t-out -> link t-out [-> ...]
	 */
	if (link && (link->flags & REQ_F_LTIMEOUT_ACTIVE)) {
		struct io_timeout_data *io = link->async_data;

		io_remove_next_linked(req);
		link->timeout.head = NULL;
		if (hrtimer_try_to_cancel(&io->timer) != -1) {
			io_cqring_fill_event(link->ctx, link->user_data,
					     -ECANCELED, 0);
			io_put_req_deferred(link, 1);
			return true;
		}
	}
	return false;
}

static void io_fail_links(struct io_kiocb *req)
	__must_hold(&req->ctx->completion_lock)
{
	struct io_kiocb *nxt, *link = req->link;

	req->link = NULL;
	while (link) {
		nxt = link->link;
		link->link = NULL;

		trace_io_uring_fail_link(req, link);
		io_cqring_fill_event(link->ctx, link->user_data, -ECANCELED, 0);
		io_put_req_deferred(link, 2);
		link = nxt;
	}
}

static bool io_disarm_next(struct io_kiocb *req)
	__must_hold(&req->ctx->completion_lock)
{
	bool posted = false;

	if (likely(req->flags & REQ_F_LINK_TIMEOUT))
		posted = io_kill_linked_timeout(req);
	if (unlikely((req->flags & REQ_F_FAIL_LINK) &&
		     !(req->flags & REQ_F_HARDLINK))) {
		posted |= (req->link != NULL);
		io_fail_links(req);
	}
	return posted;
}

static struct io_kiocb *__io_req_find_next(struct io_kiocb *req)
{
	struct io_kiocb *nxt;

	/*
	 * If LINK is set, we have dependent requests in this chain. If we
	 * didn't fail this request, queue the first one up, moving any other
	 * dependencies to the next request. In case of failure, fail the rest
	 * of the chain.
	 */
	if (req->flags & (REQ_F_LINK_TIMEOUT | REQ_F_FAIL_LINK)) {
		struct io_ring_ctx *ctx = req->ctx;
		unsigned long flags;
		bool posted;

		spin_lock_irqsave(&ctx->completion_lock, flags);
		posted = io_disarm_next(req);
		if (posted)
			io_commit_cqring(req->ctx);
		spin_unlock_irqrestore(&ctx->completion_lock, flags);
		if (posted)
			io_cqring_ev_posted(ctx);
	}
	nxt = req->link;
	req->link = NULL;
	return nxt;
}

static inline struct io_kiocb *io_req_find_next(struct io_kiocb *req)
{
	if (likely(!(req->flags & (REQ_F_LINK|REQ_F_HARDLINK))))
		return NULL;
	return __io_req_find_next(req);
}

static void ctx_flush_and_put(struct io_ring_ctx *ctx)
{
	if (!ctx)
		return;
	if (ctx->submit_state.comp.nr) {
		mutex_lock(&ctx->uring_lock);
		io_submit_flush_completions(&ctx->submit_state.comp, ctx);
		mutex_unlock(&ctx->uring_lock);
	}
	percpu_ref_put(&ctx->refs);
}

static bool __tctx_task_work(struct io_uring_task *tctx)
{
	struct io_ring_ctx *ctx = NULL;
	struct io_wq_work_list list;
	struct io_wq_work_node *node;

	if (wq_list_empty(&tctx->task_list))
		return false;

	spin_lock_irq(&tctx->task_lock);
	list = tctx->task_list;
	INIT_WQ_LIST(&tctx->task_list);
	spin_unlock_irq(&tctx->task_lock);

	node = list.first;
	while (node) {
		struct io_wq_work_node *next = node->next;
		struct io_kiocb *req;

		req = container_of(node, struct io_kiocb, io_task_work.node);
		if (req->ctx != ctx) {
			ctx_flush_and_put(ctx);
			ctx = req->ctx;
			percpu_ref_get(&ctx->refs);
		}

		req->task_work.func(&req->task_work);
		node = next;
	}

	ctx_flush_and_put(ctx);
	return list.first != NULL;
}

static void tctx_task_work(struct callback_head *cb)
{
	struct io_uring_task *tctx = container_of(cb, struct io_uring_task, task_work);

	clear_bit(0, &tctx->task_state);

	while (__tctx_task_work(tctx))
		cond_resched();
}

static int io_req_task_work_add(struct io_kiocb *req)
{
	struct task_struct *tsk = req->task;
	struct io_uring_task *tctx = tsk->io_uring;
	enum task_work_notify_mode notify;
	struct io_wq_work_node *node, *prev;
	unsigned long flags;
	int ret = 0;

	if (unlikely(tsk->flags & PF_EXITING))
		return -ESRCH;

	WARN_ON_ONCE(!tctx);

	spin_lock_irqsave(&tctx->task_lock, flags);
	wq_list_add_tail(&req->io_task_work.node, &tctx->task_list);
	spin_unlock_irqrestore(&tctx->task_lock, flags);

	/* task_work already pending, we're done */
	if (test_bit(0, &tctx->task_state) ||
	    test_and_set_bit(0, &tctx->task_state))
		return 0;

	/*
	 * SQPOLL kernel thread doesn't need notification, just a wakeup. For
	 * all other cases, use TWA_SIGNAL unconditionally to ensure we're
	 * processing task_work. There's no reliable way to tell if TWA_RESUME
	 * will do the job.
	 */
	notify = (req->ctx->flags & IORING_SETUP_SQPOLL) ? TWA_NONE : TWA_SIGNAL;

	if (!task_work_add(tsk, &tctx->task_work, notify)) {
		wake_up_process(tsk);
		return 0;
	}

	/*
	 * Slow path - we failed, find and delete work. if the work is not
	 * in the list, it got run and we're fine.
	 */
	spin_lock_irqsave(&tctx->task_lock, flags);
	wq_list_for_each(node, prev, &tctx->task_list) {
		if (&req->io_task_work.node == node) {
			wq_list_del(&tctx->task_list, node, prev);
			ret = 1;
			break;
		}
	}
	spin_unlock_irqrestore(&tctx->task_lock, flags);
	clear_bit(0, &tctx->task_state);
	return ret;
}

static bool io_run_task_work_head(struct callback_head **work_head)
{
	struct callback_head *work, *next;
	bool executed = false;

	do {
		work = xchg(work_head, NULL);
		if (!work)
			break;

		do {
			next = work->next;
			work->func(work);
			work = next;
			cond_resched();
		} while (work);
		executed = true;
	} while (1);

	return executed;
}

static void io_task_work_add_head(struct callback_head **work_head,
				  struct callback_head *task_work)
{
	struct callback_head *head;

	do {
		head = READ_ONCE(*work_head);
		task_work->next = head;
	} while (cmpxchg(work_head, head, task_work) != head);
}

static void io_req_task_work_add_fallback(struct io_kiocb *req,
					  task_work_func_t cb)
{
	init_task_work(&req->task_work, cb);
	io_task_work_add_head(&req->ctx->exit_task_work, &req->task_work);
}

static void io_req_task_cancel(struct callback_head *cb)
{
	struct io_kiocb *req = container_of(cb, struct io_kiocb, task_work);
	struct io_ring_ctx *ctx = req->ctx;

	/* ctx is guaranteed to stay alive while we hold uring_lock */
	mutex_lock(&ctx->uring_lock);
	io_req_complete_failed(req, req->result);
	mutex_unlock(&ctx->uring_lock);
}

static void __io_req_task_submit(struct io_kiocb *req)
{
	struct io_ring_ctx *ctx = req->ctx;

	/* ctx stays valid until unlock, even if we drop all ours ctx->refs */
	mutex_lock(&ctx->uring_lock);
	if (!(current->flags & PF_EXITING) && !current->in_execve)
		__io_queue_sqe(req);
	else
		io_req_complete_failed(req, -EFAULT);
	mutex_unlock(&ctx->uring_lock);
}

static void io_req_task_submit(struct callback_head *cb)
{
	struct io_kiocb *req = container_of(cb, struct io_kiocb, task_work);

	__io_req_task_submit(req);
}

static void io_req_task_queue_fail(struct io_kiocb *req, int ret)
{
	req->result = ret;
	req->task_work.func = io_req_task_cancel;

	if (unlikely(io_req_task_work_add(req)))
		io_req_task_work_add_fallback(req, io_req_task_cancel);
}

static void io_req_task_queue(struct io_kiocb *req)
{
	req->task_work.func = io_req_task_submit;

	if (unlikely(io_req_task_work_add(req)))
		io_req_task_queue_fail(req, -ECANCELED);
}

static inline void io_queue_next(struct io_kiocb *req)
{
	struct io_kiocb *nxt = io_req_find_next(req);

	if (nxt)
		io_req_task_queue(nxt);
}

static void io_free_req(struct io_kiocb *req)
{
	io_queue_next(req);
	__io_free_req(req);
}

struct req_batch {
	struct task_struct	*task;
	int			task_refs;
	int			ctx_refs;
};

static inline void io_init_req_batch(struct req_batch *rb)
{
	rb->task_refs = 0;
	rb->ctx_refs = 0;
	rb->task = NULL;
}

static void io_req_free_batch_finish(struct io_ring_ctx *ctx,
				     struct req_batch *rb)
{
	if (rb->task)
		io_put_task(rb->task, rb->task_refs);
	if (rb->ctx_refs)
		percpu_ref_put_many(&ctx->refs, rb->ctx_refs);
}

static void io_req_free_batch(struct req_batch *rb, struct io_kiocb *req,
			      struct io_submit_state *state)
{
	io_queue_next(req);
	io_dismantle_req(req);

	if (req->task != rb->task) {
		if (rb->task)
			io_put_task(rb->task, rb->task_refs);
		rb->task = req->task;
		rb->task_refs = 0;
	}
	rb->task_refs++;
	rb->ctx_refs++;

	if (state->free_reqs != ARRAY_SIZE(state->reqs))
		state->reqs[state->free_reqs++] = req;
	else
		list_add(&req->compl.list, &state->comp.free_list);
}

static void io_submit_flush_completions(struct io_comp_state *cs,
					struct io_ring_ctx *ctx)
{
	int i, nr = cs->nr;
	struct io_kiocb *req;
	struct req_batch rb;

	io_init_req_batch(&rb);
	spin_lock_irq(&ctx->completion_lock);
	for (i = 0; i < nr; i++) {
		req = cs->reqs[i];
		__io_cqring_fill_event(ctx, req->user_data, req->result,
					req->compl.cflags);
	}
	io_commit_cqring(ctx);
	spin_unlock_irq(&ctx->completion_lock);

	io_cqring_ev_posted(ctx);
	for (i = 0; i < nr; i++) {
		req = cs->reqs[i];

		/* submission and completion refs */
		if (req_ref_sub_and_test(req, 2))
			io_req_free_batch(&rb, req, &ctx->submit_state);
	}

	io_req_free_batch_finish(ctx, &rb);
	cs->nr = 0;
}

/*
 * Drop reference to request, return next in chain (if there is one) if this
 * was the last reference to this request.
 */
static inline struct io_kiocb *io_put_req_find_next(struct io_kiocb *req)
{
	struct io_kiocb *nxt = NULL;

	if (req_ref_put_and_test(req)) {
		nxt = io_req_find_next(req);
		__io_free_req(req);
	}
	return nxt;
}

static inline void io_put_req(struct io_kiocb *req)
{
	if (req_ref_put_and_test(req))
		io_free_req(req);
}

static void io_put_req_deferred_cb(struct callback_head *cb)
{
	struct io_kiocb *req = container_of(cb, struct io_kiocb, task_work);

	io_free_req(req);
}

static void io_free_req_deferred(struct io_kiocb *req)
{
	req->task_work.func = io_put_req_deferred_cb;
	if (unlikely(io_req_task_work_add(req)))
		io_req_task_work_add_fallback(req, io_put_req_deferred_cb);
}

static inline void io_put_req_deferred(struct io_kiocb *req, int refs)
{
	if (req_ref_sub_and_test(req, refs))
		io_free_req_deferred(req);
}

static unsigned io_cqring_events(struct io_ring_ctx *ctx)
{
	/* See comment at the top of this file */
	smp_rmb();
	return __io_cqring_events(ctx);
}

static inline unsigned int io_sqring_entries(struct io_ring_ctx *ctx)
{
	struct io_rings *rings = ctx->rings;

	/* make sure SQ entry isn't read before tail */
	return smp_load_acquire(&rings->sq.tail) - ctx->cached_sq_head;
}

static unsigned int io_put_kbuf(struct io_kiocb *req, struct io_buffer *kbuf)
{
	unsigned int cflags;

	cflags = kbuf->bid << IORING_CQE_BUFFER_SHIFT;
	cflags |= IORING_CQE_F_BUFFER;
	req->flags &= ~REQ_F_BUFFER_SELECTED;
	kfree(kbuf);
	return cflags;
}

static inline unsigned int io_put_rw_kbuf(struct io_kiocb *req)
{
	struct io_buffer *kbuf;

	kbuf = (struct io_buffer *) (unsigned long) req->rw.addr;
	return io_put_kbuf(req, kbuf);
}

static inline bool io_run_task_work(void)
{
	/*
	 * Not safe to run on exiting task, and the task_work handling will
	 * not add work to such a task.
	 */
	if (unlikely(current->flags & PF_EXITING))
		return false;
	if (current->task_works) {
		__set_current_state(TASK_RUNNING);
		task_work_run();
		return true;
	}

	return false;
}

/*
 * Find and free completed poll iocbs
 */
static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
			       struct list_head *done)
{
	struct req_batch rb;
	struct io_kiocb *req;

	/* order with ->result store in io_complete_rw_iopoll() */
	smp_rmb();

	io_init_req_batch(&rb);
	while (!list_empty(done)) {
		int cflags = 0;

		req = list_first_entry(done, struct io_kiocb, inflight_entry);
		list_del(&req->inflight_entry);

		if (READ_ONCE(req->result) == -EAGAIN &&
		    !(req->flags & REQ_F_DONT_REISSUE)) {
			req->iopoll_completed = 0;
			req_ref_get(req);
			io_queue_async_work(req);
			continue;
		}

		if (req->flags & REQ_F_BUFFER_SELECTED)
			cflags = io_put_rw_kbuf(req);

		__io_cqring_fill_event(ctx, req->user_data, req->result, cflags);
		(*nr_events)++;

		if (req_ref_put_and_test(req))
			io_req_free_batch(&rb, req, &ctx->submit_state);
	}

	io_commit_cqring(ctx);
	io_cqring_ev_posted_iopoll(ctx);
	io_req_free_batch_finish(ctx, &rb);
}

static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events,
			long min)
{
	struct io_kiocb *req, *tmp;
	LIST_HEAD(done);
	bool spin;
	int ret;

	/*
	 * Only spin for completions if we don't have multiple devices hanging
	 * off our complete list, and we're under the requested amount.
	 */
	spin = !ctx->poll_multi_file && *nr_events < min;

	ret = 0;
	list_for_each_entry_safe(req, tmp, &ctx->iopoll_list, inflight_entry) {
		struct kiocb *kiocb = &req->rw.kiocb;

		/*
		 * Move completed and retryable entries to our local lists.
		 * If we find a request that requires polling, break out
		 * and complete those lists first, if we have entries there.
		 */
		if (READ_ONCE(req->iopoll_completed)) {
			list_move_tail(&req->inflight_entry, &done);
			continue;
		}
		if (!list_empty(&done))
			break;

		ret = kiocb->ki_filp->f_op->iopoll(kiocb, spin);
		if (ret < 0)
			break;

		/* iopoll may have completed current req */
		if (READ_ONCE(req->iopoll_completed))
			list_move_tail(&req->inflight_entry, &done);

		if (ret && spin)
			spin = false;
		ret = 0;
	}

	if (!list_empty(&done))
		io_iopoll_complete(ctx, nr_events, &done);

	return ret;
}

/*
 * We can't just wait for polled events to come to us, we have to actively
 * find and complete them.
 */
static void io_iopoll_try_reap_events(struct io_ring_ctx *ctx)
{
	if (!(ctx->flags & IORING_SETUP_IOPOLL))
		return;

	mutex_lock(&ctx->uring_lock);
	while (!list_empty(&ctx->iopoll_list)) {
		unsigned int nr_events = 0;

		io_do_iopoll(ctx, &nr_events, 0);

		/* let it sleep and repeat later if can't complete a request */
		if (nr_events == 0)
			break;
		/*
		 * Ensure we allow local-to-the-cpu processing to take place,
		 * in this case we need to ensure that we reap all events.
		 * Also let task_work, etc. to progress by releasing the mutex
		 */
		if (need_resched()) {
			mutex_unlock(&ctx->uring_lock);
			cond_resched();
			mutex_lock(&ctx->uring_lock);
		}
	}
	mutex_unlock(&ctx->uring_lock);
}

static int io_iopoll_check(struct io_ring_ctx *ctx, long min)
{
	unsigned int nr_events = 0;
	int ret = 0;

	/*
	 * We disallow the app entering submit/complete with polling, but we
	 * still need to lock the ring to prevent racing with polled issue
	 * that got punted to a workqueue.
	 */
	mutex_lock(&ctx->uring_lock);
	/*
	 * Don't enter poll loop if we already have events pending.
	 * If we do, we can potentially be spinning for commands that
	 * already triggered a CQE (eg in error).
	 */
	if (test_bit(0, &ctx->cq_check_overflow))
		__io_cqring_overflow_flush(ctx, false);
	if (io_cqring_events(ctx))
		goto out;
	do {
		/*
		 * If a submit got punted to a workqueue, we can have the
		 * application entering polling for a command before it gets
		 * issued. That app will hold the uring_lock for the duration
		 * of the poll right here, so we need to take a breather every
		 * now and then to ensure that the issue has a chance to add
		 * the poll to the issued list. Otherwise we can spin here
		 * forever, while the workqueue is stuck trying to acquire the
		 * very same mutex.
		 */
		if (list_empty(&ctx->iopoll_list)) {
			mutex_unlock(&ctx->uring_lock);
			io_run_task_work();
			mutex_lock(&ctx->uring_lock);

			if (list_empty(&ctx->iopoll_list))
				break;
		}
		ret = io_do_iopoll(ctx, &nr_events, min);
	} while (!ret && nr_events < min && !need_resched());
out:
	mutex_unlock(&ctx->uring_lock);
	return ret;
}

static void kiocb_end_write(struct io_kiocb *req)
{
	/*
	 * Tell lockdep we inherited freeze protection from submission
	 * thread.
	 */
	if (req->flags & REQ_F_ISREG) {
		struct super_block *sb = file_inode(req->file)->i_sb;

		__sb_writers_acquired(sb, SB_FREEZE_WRITE);
		sb_end_write(sb);
	}
}

#ifdef CONFIG_BLOCK
static bool io_resubmit_prep(struct io_kiocb *req)
{
	struct io_async_rw *rw = req->async_data;

	if (!rw)
		return !io_req_prep_async(req);
	/* may have left rw->iter inconsistent on -EIOCBQUEUED */
	iov_iter_revert(&rw->iter, req->result - iov_iter_count(&rw->iter));
	return true;
}

static bool io_rw_should_reissue(struct io_kiocb *req)
{
	umode_t mode = file_inode(req->file)->i_mode;
	struct io_ring_ctx *ctx = req->ctx;

	if (!S_ISBLK(mode) && !S_ISREG(mode))
		return false;
	if ((req->flags & REQ_F_NOWAIT) || (io_wq_current_is_worker() &&
	    !(ctx->flags & IORING_SETUP_IOPOLL)))
		return false;
	/*
	 * If ref is dying, we might be running poll reap from the exit work.
	 * Don't attempt to reissue from that path, just let it fail with
	 * -EAGAIN.
	 */
	if (percpu_ref_is_dying(&ctx->refs))
		return false;
	return true;
}
#else
static bool io_resubmit_prep(struct io_kiocb *req)
{
	return false;
}
static bool io_rw_should_reissue(struct io_kiocb *req)
{
	return false;
}
#endif

static void __io_complete_rw(struct io_kiocb *req, long res, long res2,
			     unsigned int issue_flags)
{
	int cflags = 0;

	if (req->rw.kiocb.ki_flags & IOCB_WRITE)
		kiocb_end_write(req);
	if (res != req->result) {
		if ((res == -EAGAIN || res == -EOPNOTSUPP) &&
		    io_rw_should_reissue(req)) {
			req->flags |= REQ_F_REISSUE;
			return;
		}
		req_set_fail_links(req);
	}
	if (req->flags & REQ_F_BUFFER_SELECTED)
		cflags = io_put_rw_kbuf(req);
	__io_req_complete(req, issue_flags, res, cflags);
}

static void io_complete_rw(struct kiocb *kiocb, long res, long res2)
{
	struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb);

	__io_complete_rw(req, res, res2, 0);
}

static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2)
{
	struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb);

	if (kiocb->ki_flags & IOCB_WRITE)
		kiocb_end_write(req);
	if (unlikely(res != req->result)) {
		if (!(res == -EAGAIN && io_rw_should_reissue(req) &&
		    io_resubmit_prep(req))) {
			req_set_fail_links(req);
			req->flags |= REQ_F_DONT_REISSUE;
		}
	}

	WRITE_ONCE(req->result, res);
	/* order with io_iopoll_complete() checking ->result */
	smp_wmb();
	WRITE_ONCE(req->iopoll_completed, 1);
}

/*
 * After the iocb has been issued, it's safe to be found on the poll list.
 * Adding the kiocb to the list AFTER submission ensures that we don't
 * find it from a io_do_iopoll() thread before the issuer is done
 * accessing the kiocb cookie.
 */
static void io_iopoll_req_issued(struct io_kiocb *req, bool in_async)
{
	struct io_ring_ctx *ctx = req->ctx;

	/*
	 * Track whether we have multiple files in our lists. This will impact
	 * how we do polling eventually, not spinning if we're on potentially
	 * different devices.
	 */
	if (list_empty(&ctx->iopoll_list)) {
		ctx->poll_multi_file = false;
	} else if (!ctx->poll_multi_file) {
		struct io_kiocb *list_req;

		list_req = list_first_entry(&ctx->iopoll_list, struct io_kiocb,
						inflight_entry);
		if (list_req->file != req->file)
			ctx->poll_multi_file = true;
	}

	/*
	 * For fast devices, IO may have already completed. If it has, add
	 * it to the front so we find it first.
	 */
	if (READ_ONCE(req->iopoll_completed))
		list_add(&req->inflight_entry, &ctx->iopoll_list);
	else
		list_add_tail(&req->inflight_entry, &ctx->iopoll_list);

	/*
	 * If IORING_SETUP_SQPOLL is enabled, sqes are either handled in sq thread
	 * task context or in io worker task context. If current task context is
	 * sq thread, we don't need to check whether should wake up sq thread.
	 */
	if (in_async && (ctx->flags & IORING_SETUP_SQPOLL) &&
	    wq_has_sleeper(&ctx->sq_data->wait))
		wake_up(&ctx->sq_data->wait);
}

static inline void io_state_file_put(struct io_submit_state *state)
{
	if (state->file_refs) {
		fput_many(state->file, state->file_refs);
		state->file_refs = 0;
	}
}

/*
 * Get as many references to a file as we have IOs left in this submission,
 * assuming most submissions are for one file, or at least that each file
 * has more than one submission.
 */
static struct file *__io_file_get(struct io_submit_state *state, int fd)
{
	if (!state)
		return fget(fd);

	if (state->file_refs) {
		if (state->fd == fd) {
			state->file_refs--;
			return state->file;
		}
		io_state_file_put(state);
	}
	state->file = fget_many(fd, state->ios_left);
	if (unlikely(!state->file))
		return NULL;

	state->fd = fd;
	state->file_refs = state->ios_left - 1;
	return state->file;
}

static bool io_bdev_nowait(struct block_device *bdev)
{
	return !bdev || blk_queue_nowait(bdev_get_queue(bdev));
}

/*
 * If we tracked the file through the SCM inflight mechanism, we could support
 * any file. For now, just ensure that anything potentially problematic is done
 * inline.
 */
static bool __io_file_supports_async(struct file *file, int rw)
{
	umode_t mode = file_inode(file)->i_mode;

	if (S_ISBLK(mode)) {
		if (IS_ENABLED(CONFIG_BLOCK) &&
		    io_bdev_nowait(I_BDEV(file->f_mapping->host)))
			return true;
		return false;
	}
	if (S_ISCHR(mode) || S_ISSOCK(mode))
		return true;
	if (S_ISREG(mode)) {
		if (IS_ENABLED(CONFIG_BLOCK) &&
		    io_bdev_nowait(file->f_inode->i_sb->s_bdev) &&
		    file->f_op != &io_uring_fops)
			return true;
		return false;
	}

	/* any ->read/write should understand O_NONBLOCK */
	if (file->f_flags & O_NONBLOCK)
		return true;

	if (!(file->f_mode & FMODE_NOWAIT))
		return false;

	if (rw == READ)
		return file->f_op->read_iter != NULL;

	return file->f_op->write_iter != NULL;
}

static bool io_file_supports_async(struct io_kiocb *req, int rw)
{
	if (rw == READ && (req->flags & REQ_F_ASYNC_READ))
		return true;
	else if (rw == WRITE && (req->flags & REQ_F_ASYNC_WRITE))
		return true;

	return __io_file_supports_async(req->file, rw);
}

static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	struct io_ring_ctx *ctx = req->ctx;
	struct kiocb *kiocb = &req->rw.kiocb;
	struct file *file = req->file;
	unsigned ioprio;
	int ret;

	if (!(req->flags & REQ_F_ISREG) && S_ISREG(file_inode(file)->i_mode))
		req->flags |= REQ_F_ISREG;

	kiocb->ki_pos = READ_ONCE(sqe->off);
	if (kiocb->ki_pos == -1 && !(file->f_mode & FMODE_STREAM)) {
		req->flags |= REQ_F_CUR_POS;
		kiocb->ki_pos = file->f_pos;
	}
	kiocb->ki_hint = ki_hint_validate(file_write_hint(kiocb->ki_filp));
	kiocb->ki_flags = iocb_flags(kiocb->ki_filp);
	ret = kiocb_set_rw_flags(kiocb, READ_ONCE(sqe->rw_flags));
	if (unlikely(ret))
		return ret;

	/* don't allow async punt for O_NONBLOCK or RWF_NOWAIT */
	if ((kiocb->ki_flags & IOCB_NOWAIT) || (file->f_flags & O_NONBLOCK))
		req->flags |= REQ_F_NOWAIT;

	ioprio = READ_ONCE(sqe->ioprio);
	if (ioprio) {
		ret = ioprio_check_cap(ioprio);
		if (ret)
			return ret;

		kiocb->ki_ioprio = ioprio;
	} else
		kiocb->ki_ioprio = get_current_ioprio();

	if (ctx->flags & IORING_SETUP_IOPOLL) {
		if (!(kiocb->ki_flags & IOCB_DIRECT) ||
		    !kiocb->ki_filp->f_op->iopoll)
			return -EOPNOTSUPP;

		kiocb->ki_flags |= IOCB_HIPRI;
		kiocb->ki_complete = io_complete_rw_iopoll;
		req->iopoll_completed = 0;
	} else {
		if (kiocb->ki_flags & IOCB_HIPRI)
			return -EINVAL;
		kiocb->ki_complete = io_complete_rw;
	}

	if (req->opcode == IORING_OP_READ_FIXED ||
	    req->opcode == IORING_OP_WRITE_FIXED) {
		req->imu = NULL;
		io_req_set_rsrc_node(req);
	}

	req->rw.addr = READ_ONCE(sqe->addr);
	req->rw.len = READ_ONCE(sqe->len);
	req->buf_index = READ_ONCE(sqe->buf_index);
	return 0;
}

static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret)
{
	switch (ret) {
	case -EIOCBQUEUED:
		break;
	case -ERESTARTSYS:
	case -ERESTARTNOINTR:
	case -ERESTARTNOHAND:
	case -ERESTART_RESTARTBLOCK:
		/*
		 * We can't just restart the syscall, since previously
		 * submitted sqes may already be in progress. Just fail this
		 * IO with EINTR.
		 */
		ret = -EINTR;
		fallthrough;
	default:
		kiocb->ki_complete(kiocb, ret, 0);
	}
}

static void kiocb_done(struct kiocb *kiocb, ssize_t ret,
		       unsigned int issue_flags)
{
	struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb);
	struct io_async_rw *io = req->async_data;
	bool check_reissue = kiocb->ki_complete == io_complete_rw;

	/* add previously done IO, if any */
	if (io && io->bytes_done > 0) {
		if (ret < 0)
			ret = io->bytes_done;
		else
			ret += io->bytes_done;
	}

	if (req->flags & REQ_F_CUR_POS)
		req->file->f_pos = kiocb->ki_pos;
	if (ret >= 0 && kiocb->ki_complete == io_complete_rw)
		__io_complete_rw(req, ret, 0, issue_flags);
	else
		io_rw_done(kiocb, ret);

	if (check_reissue && req->flags & REQ_F_REISSUE) {
		req->flags &= ~REQ_F_REISSUE;
		if (io_resubmit_prep(req)) {
			req_ref_get(req);
			io_queue_async_work(req);
		} else {
			int cflags = 0;

			req_set_fail_links(req);
			if (req->flags & REQ_F_BUFFER_SELECTED)
				cflags = io_put_rw_kbuf(req);
			__io_req_complete(req, issue_flags, ret, cflags);
		}
	}
}

static int __io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter,
			     struct io_mapped_ubuf *imu)
{
	size_t len = req->rw.len;
	u64 buf_end, buf_addr = req->rw.addr;
	size_t offset;

	if (unlikely(check_add_overflow(buf_addr, (u64)len, &buf_end)))
		return -EFAULT;
	/* not inside the mapped region */
	if (unlikely(buf_addr < imu->ubuf || buf_end > imu->ubuf_end))
		return -EFAULT;

	/*
	 * May not be a start of buffer, set size appropriately
	 * and advance us to the beginning.
	 */
	offset = buf_addr - imu->ubuf;
	iov_iter_bvec(iter, rw, imu->bvec, imu->nr_bvecs, offset + len);

	if (offset) {
		/*
		 * Don't use iov_iter_advance() here, as it's really slow for
		 * using the latter parts of a big fixed buffer - it iterates
		 * over each segment manually. We can cheat a bit here, because
		 * we know that:
		 *
		 * 1) it's a BVEC iter, we set it up
		 * 2) all bvecs are PAGE_SIZE in size, except potentially the
		 *    first and last bvec
		 *
		 * So just find our index, and adjust the iterator afterwards.
		 * If the offset is within the first bvec (or the whole first
		 * bvec, just use iov_iter_advance(). This makes it easier
		 * since we can just skip the first segment, which may not
		 * be PAGE_SIZE aligned.
		 */
		const struct bio_vec *bvec = imu->bvec;

		if (offset <= bvec->bv_len) {
			iov_iter_advance(iter, offset);
		} else {
			unsigned long seg_skip;

			/* skip first vec */
			offset -= bvec->bv_len;
			seg_skip = 1 + (offset >> PAGE_SHIFT);

			iter->bvec = bvec + seg_skip;
			iter->nr_segs -= seg_skip;
			iter->count -= bvec->bv_len + offset;
			iter->iov_offset = offset & ~PAGE_MASK;
		}
	}

	return 0;
}

static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter)
{
	struct io_ring_ctx *ctx = req->ctx;
	struct io_mapped_ubuf *imu = req->imu;
	u16 index, buf_index = req->buf_index;

	if (likely(!imu)) {
		if (unlikely(buf_index >= ctx->nr_user_bufs))
			return -EFAULT;
		index = array_index_nospec(buf_index, ctx->nr_user_bufs);
		imu = READ_ONCE(ctx->user_bufs[index]);
		req->imu = imu;
	}
	return __io_import_fixed(req, rw, iter, imu);
}

static void io_ring_submit_unlock(struct io_ring_ctx *ctx, bool needs_lock)
{
	if (needs_lock)
		mutex_unlock(&ctx->uring_lock);
}

static void io_ring_submit_lock(struct io_ring_ctx *ctx, bool needs_lock)
{
	/*
	 * "Normal" inline submissions always hold the uring_lock, since we
	 * grab it from the system call. Same is true for the SQPOLL offload.
	 * The only exception is when we've detached the request and issue it
	 * from an async worker thread, grab the lock for that case.
	 */
	if (needs_lock)
		mutex_lock(&ctx->uring_lock);
}

static struct io_buffer *io_buffer_select(struct io_kiocb *req, size_t *len,
					  int bgid, struct io_buffer *kbuf,
					  bool needs_lock)
{
	struct io_buffer *head;

	if (req->flags & REQ_F_BUFFER_SELECTED)
		return kbuf;

	io_ring_submit_lock(req->ctx, needs_lock);

	lockdep_assert_held(&req->ctx->uring_lock);

	head = xa_load(&req->ctx->io_buffers, bgid);
	if (head) {
		if (!list_empty(&head->list)) {
			kbuf = list_last_entry(&head->list, struct io_buffer,
							list);
			list_del(&kbuf->list);
		} else {
			kbuf = head;
			xa_erase(&req->ctx->io_buffers, bgid);
		}
		if (*len > kbuf->len)
			*len = kbuf->len;
	} else {
		kbuf = ERR_PTR(-ENOBUFS);
	}

	io_ring_submit_unlock(req->ctx, needs_lock);

	return kbuf;
}

static void __user *io_rw_buffer_select(struct io_kiocb *req, size_t *len,
					bool needs_lock)
{
	struct io_buffer *kbuf;
	u16 bgid;

	kbuf = (struct io_buffer *) (unsigned long) req->rw.addr;
	bgid = req->buf_index;
	kbuf = io_buffer_select(req, len, bgid, kbuf, needs_lock);
	if (IS_ERR(kbuf))
		return kbuf;
	req->rw.addr = (u64) (unsigned long) kbuf;
	req->flags |= REQ_F_BUFFER_SELECTED;
	return u64_to_user_ptr(kbuf->addr);
}

#ifdef CONFIG_COMPAT
static ssize_t io_compat_import(struct io_kiocb *req, struct iovec *iov,
				bool needs_lock)
{
	struct compat_iovec __user *uiov;
	compat_ssize_t clen;
	void __user *buf;
	ssize_t len;

	uiov = u64_to_user_ptr(req->rw.addr);
	if (!access_ok(uiov, sizeof(*uiov)))
		return -EFAULT;
	if (__get_user(clen, &uiov->iov_len))
		return -EFAULT;
	if (clen < 0)
		return -EINVAL;

	len = clen;
	buf = io_rw_buffer_select(req, &len, needs_lock);
	if (IS_ERR(buf))
		return PTR_ERR(buf);
	iov[0].iov_base = buf;
	iov[0].iov_len = (compat_size_t) len;
	return 0;
}
#endif

static ssize_t __io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov,
				      bool needs_lock)
{
	struct iovec __user *uiov = u64_to_user_ptr(req->rw.addr);
	void __user *buf;
	ssize_t len;

	if (copy_from_user(iov, uiov, sizeof(*uiov)))
		return -EFAULT;

	len = iov[0].iov_len;
	if (len < 0)
		return -EINVAL;
	buf = io_rw_buffer_select(req, &len, needs_lock);
	if (IS_ERR(buf))
		return PTR_ERR(buf);
	iov[0].iov_base = buf;
	iov[0].iov_len = len;
	return 0;
}

static ssize_t io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov,
				    bool needs_lock)
{
	if (req->flags & REQ_F_BUFFER_SELECTED) {
		struct io_buffer *kbuf;

		kbuf = (struct io_buffer *) (unsigned long) req->rw.addr;
		iov[0].iov_base = u64_to_user_ptr(kbuf->addr);
		iov[0].iov_len = kbuf->len;
		return 0;
	}
	if (req->rw.len != 1)
		return -EINVAL;

#ifdef CONFIG_COMPAT
	if (req->ctx->compat)
		return io_compat_import(req, iov, needs_lock);
#endif

	return __io_iov_buffer_select(req, iov, needs_lock);
}

static int io_import_iovec(int rw, struct io_kiocb *req, struct iovec **iovec,
			   struct iov_iter *iter, bool needs_lock)
{
	void __user *buf = u64_to_user_ptr(req->rw.addr);
	size_t sqe_len = req->rw.len;
	u8 opcode = req->opcode;
	ssize_t ret;

	if (opcode == IORING_OP_READ_FIXED || opcode == IORING_OP_WRITE_FIXED) {
		*iovec = NULL;
		return io_import_fixed(req, rw, iter);
	}

	/* buffer index only valid with fixed read/write, or buffer select  */
	if (req->buf_index && !(req->flags & REQ_F_BUFFER_SELECT))
		return -EINVAL;

	if (opcode == IORING_OP_READ || opcode == IORING_OP_WRITE) {
		if (req->flags & REQ_F_BUFFER_SELECT) {
			buf = io_rw_buffer_select(req, &sqe_len, needs_lock);
			if (IS_ERR(buf))
				return PTR_ERR(buf);
			req->rw.len = sqe_len;
		}

		ret = import_single_range(rw, buf, sqe_len, *iovec, iter);
		*iovec = NULL;
		return ret;
	}

	if (req->flags & REQ_F_BUFFER_SELECT) {
		ret = io_iov_buffer_select(req, *iovec, needs_lock);
		if (!ret)
			iov_iter_init(iter, rw, *iovec, 1, (*iovec)->iov_len);
		*iovec = NULL;
		return ret;
	}

	return __import_iovec(rw, buf, sqe_len, UIO_FASTIOV, iovec, iter,
			      req->ctx->compat);
}

static inline loff_t *io_kiocb_ppos(struct kiocb *kiocb)
{
	return (kiocb->ki_filp->f_mode & FMODE_STREAM) ? NULL : &kiocb->ki_pos;
}

/*
 * For files that don't have ->read_iter() and ->write_iter(), handle them
 * by looping over ->read() or ->write() manually.
 */
static ssize_t loop_rw_iter(int rw, struct io_kiocb *req, struct iov_iter *iter)
{
	struct kiocb *kiocb = &req->rw.kiocb;
	struct file *file = req->file;
	ssize_t ret = 0;

	/*
	 * Don't support polled IO through this interface, and we can't
	 * support non-blocking either. For the latter, this just causes
	 * the kiocb to be handled from an async context.
	 */
	if (kiocb->ki_flags & IOCB_HIPRI)
		return -EOPNOTSUPP;
	if (kiocb->ki_flags & IOCB_NOWAIT)
		return -EAGAIN;

	while (iov_iter_count(iter)) {
		struct iovec iovec;
		ssize_t nr;

		if (!iov_iter_is_bvec(iter)) {
			iovec = iov_iter_iovec(iter);
		} else {
			iovec.iov_base = u64_to_user_ptr(req->rw.addr);
			iovec.iov_len = req->rw.len;
		}

		if (rw == READ) {
			nr = file->f_op->read(file, iovec.iov_base,
					      iovec.iov_len, io_kiocb_ppos(kiocb));
		} else {
			nr = file->f_op->write(file, iovec.iov_base,
					       iovec.iov_len, io_kiocb_ppos(kiocb));
		}

		if (nr < 0) {
			if (!ret)
				ret = nr;
			break;
		}
		ret += nr;
		if (nr != iovec.iov_len)
			break;
		req->rw.len -= nr;
		req->rw.addr += nr;
		iov_iter_advance(iter, nr);
	}

	return ret;
}

static void io_req_map_rw(struct io_kiocb *req, const struct iovec *iovec,
			  const struct iovec *fast_iov, struct iov_iter *iter)
{
	struct io_async_rw *rw = req->async_data;

	memcpy(&rw->iter, iter, sizeof(*iter));
	rw->free_iovec = iovec;
	rw->bytes_done = 0;
	/* can only be fixed buffers, no need to do anything */
	if (iov_iter_is_bvec(iter))
		return;
	if (!iovec) {
		unsigned iov_off = 0;

		rw->iter.iov = rw->fast_iov;
		if (iter->iov != fast_iov) {
			iov_off = iter->iov - fast_iov;
			rw->iter.iov += iov_off;
		}
		if (rw->fast_iov != fast_iov)
			memcpy(rw->fast_iov + iov_off, fast_iov + iov_off,
			       sizeof(struct iovec) * iter->nr_segs);
	} else {
		req->flags |= REQ_F_NEED_CLEANUP;
	}
}

static inline int io_alloc_async_data(struct io_kiocb *req)
{
	WARN_ON_ONCE(!io_op_defs[req->opcode].async_size);
	req->async_data = kmalloc(io_op_defs[req->opcode].async_size, GFP_KERNEL);
	return req->async_data == NULL;
}

static int io_setup_async_rw(struct io_kiocb *req, const struct iovec *iovec,
			     const struct iovec *fast_iov,
			     struct iov_iter *iter, bool force)
{
	if (!force && !io_op_defs[req->opcode].needs_async_setup)
		return 0;
	if (!req->async_data) {
		if (io_alloc_async_data(req)) {
			kfree(iovec);
			return -ENOMEM;
		}

		io_req_map_rw(req, iovec, fast_iov, iter);
	}
	return 0;
}

static inline int io_rw_prep_async(struct io_kiocb *req, int rw)
{
	struct io_async_rw *iorw = req->async_data;
	struct iovec *iov = iorw->fast_iov;
	int ret;

	ret = io_import_iovec(rw, req, &iov, &iorw->iter, false);
	if (unlikely(ret < 0))
		return ret;

	iorw->bytes_done = 0;
	iorw->free_iovec = iov;
	if (iov)
		req->flags |= REQ_F_NEED_CLEANUP;
	return 0;
}

static int io_read_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	if (unlikely(!(req->file->f_mode & FMODE_READ)))
		return -EBADF;
	return io_prep_rw(req, sqe);
}

/*
 * This is our waitqueue callback handler, registered through lock_page_async()
 * when we initially tried to do the IO with the iocb armed our waitqueue.
 * This gets called when the page is unlocked, and we generally expect that to
 * happen when the page IO is completed and the page is now uptodate. This will
 * queue a task_work based retry of the operation, attempting to copy the data
 * again. If the latter fails because the page was NOT uptodate, then we will
 * do a thread based blocking retry of the operation. That's the unexpected
 * slow path.
 */
static int io_async_buf_func(struct wait_queue_entry *wait, unsigned mode,
			     int sync, void *arg)
{
	struct wait_page_queue *wpq;
	struct io_kiocb *req = wait->private;
	struct wait_page_key *key = arg;

	wpq = container_of(wait, struct wait_page_queue, wait);

	if (!wake_page_match(wpq, key))
		return 0;

	req->rw.kiocb.ki_flags &= ~IOCB_WAITQ;
	list_del_init(&wait->entry);

	/* submit ref gets dropped, acquire a new one */
	req_ref_get(req);
	io_req_task_queue(req);
	return 1;
}

/*
 * This controls whether a given IO request should be armed for async page
 * based retry. If we return false here, the request is handed to the async
 * worker threads for retry. If we're doing buffered reads on a regular file,
 * we prepare a private wait_page_queue entry and retry the operation. This
 * will either succeed because the page is now uptodate and unlocked, or it
 * will register a callback when the page is unlocked at IO completion. Through
 * that callback, io_uring uses task_work to setup a retry of the operation.
 * That retry will attempt the buffered read again. The retry will generally
 * succeed, or in rare cases where it fails, we then fall back to using the
 * async worker threads for a blocking retry.
 */
static bool io_rw_should_retry(struct io_kiocb *req)
{
	struct io_async_rw *rw = req->async_data;
	struct wait_page_queue *wait = &rw->wpq;
	struct kiocb *kiocb = &req->rw.kiocb;

	/* never retry for NOWAIT, we just complete with -EAGAIN */
	if (req->flags & REQ_F_NOWAIT)
		return false;

	/* Only for buffered IO */
	if (kiocb->ki_flags & (IOCB_DIRECT | IOCB_HIPRI))
		return false;

	/*
	 * just use poll if we can, and don't attempt if the fs doesn't
	 * support callback based unlocks
	 */
	if (file_can_poll(req->file) || !(req->file->f_mode & FMODE_BUF_RASYNC))
		return false;

	wait->wait.func = io_async_buf_func;
	wait->wait.private = req;
	wait->wait.flags = 0;
	INIT_LIST_HEAD(&wait->wait.entry);
	kiocb->ki_flags |= IOCB_WAITQ;
	kiocb->ki_flags &= ~IOCB_NOWAIT;
	kiocb->ki_waitq = wait;
	return true;
}

static int io_iter_do_read(struct io_kiocb *req, struct iov_iter *iter)
{
	if (req->file->f_op->read_iter)
		return call_read_iter(req->file, &req->rw.kiocb, iter);
	else if (req->file->f_op->read)
		return loop_rw_iter(READ, req, iter);
	else
		return -EINVAL;
}

static int io_read(struct io_kiocb *req, unsigned int issue_flags)
{
	struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
	struct kiocb *kiocb = &req->rw.kiocb;
	struct iov_iter __iter, *iter = &__iter;
	struct io_async_rw *rw = req->async_data;
	ssize_t io_size, ret, ret2;
	bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;

	if (rw) {
		iter = &rw->iter;
		iovec = NULL;
	} else {
		ret = io_import_iovec(READ, req, &iovec, iter, !force_nonblock);
		if (ret < 0)
			return ret;
	}
	io_size = iov_iter_count(iter);
	req->result = io_size;

	/* Ensure we clear previously set non-block flag */
	if (!force_nonblock)
		kiocb->ki_flags &= ~IOCB_NOWAIT;
	else
		kiocb->ki_flags |= IOCB_NOWAIT;

	/* If the file doesn't support async, just async punt */
	if (force_nonblock && !io_file_supports_async(req, READ)) {
		ret = io_setup_async_rw(req, iovec, inline_vecs, iter, true);
		return ret ?: -EAGAIN;
	}

	ret = rw_verify_area(READ, req->file, io_kiocb_ppos(kiocb), io_size);
	if (unlikely(ret)) {
		kfree(iovec);
		return ret;
	}

	ret = io_iter_do_read(req, iter);

	if (ret == -EAGAIN || (req->flags & REQ_F_REISSUE)) {
		req->flags &= ~REQ_F_REISSUE;
		/* IOPOLL retry should happen for io-wq threads */
		if (!force_nonblock && !(req->ctx->flags & IORING_SETUP_IOPOLL))
			goto done;
		/* no retry on NONBLOCK nor RWF_NOWAIT */
		if (req->flags & REQ_F_NOWAIT)
			goto done;
		/* some cases will consume bytes even on error returns */
		iov_iter_revert(iter, io_size - iov_iter_count(iter));
		ret = 0;
	} else if (ret == -EIOCBQUEUED) {
		goto out_free;
	} else if (ret <= 0 || ret == io_size || !force_nonblock ||
		   (req->flags & REQ_F_NOWAIT) || !(req->flags & REQ_F_ISREG)) {
		/* read all, failed, already did sync or don't want to retry */
		goto done;
	}

	ret2 = io_setup_async_rw(req, iovec, inline_vecs, iter, true);
	if (ret2)
		return ret2;

	iovec = NULL;
	rw = req->async_data;
	/* now use our persistent iterator, if we aren't already */
	iter = &rw->iter;

	do {
		io_size -= ret;
		rw->bytes_done += ret;
		/* if we can retry, do so with the callbacks armed */
		if (!io_rw_should_retry(req)) {
			kiocb->ki_flags &= ~IOCB_WAITQ;
			return -EAGAIN;
		}

		/*
		 * Now retry read with the IOCB_WAITQ parts set in the iocb. If
		 * we get -EIOCBQUEUED, then we'll get a notification when the
		 * desired page gets unlocked. We can also get a partial read
		 * here, and if we do, then just retry at the new offset.
		 */
		ret = io_iter_do_read(req, iter);
		if (ret == -EIOCBQUEUED)
			return 0;
		/* we got some bytes, but not all. retry. */
		kiocb->ki_flags &= ~IOCB_WAITQ;
	} while (ret > 0 && ret < io_size);
done:
	kiocb_done(kiocb, ret, issue_flags);
out_free:
	/* it's faster to check here then delegate to kfree */
	if (iovec)
		kfree(iovec);
	return 0;
}

static int io_write_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	if (unlikely(!(req->file->f_mode & FMODE_WRITE)))
		return -EBADF;
	return io_prep_rw(req, sqe);
}

static int io_write(struct io_kiocb *req, unsigned int issue_flags)
{
	struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
	struct kiocb *kiocb = &req->rw.kiocb;
	struct iov_iter __iter, *iter = &__iter;
	struct io_async_rw *rw = req->async_data;
	ssize_t ret, ret2, io_size;
	bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;

	if (rw) {
		iter = &rw->iter;
		iovec = NULL;
	} else {
		ret = io_import_iovec(WRITE, req, &iovec, iter, !force_nonblock);
		if (ret < 0)
			return ret;
	}
	io_size = iov_iter_count(iter);
	req->result = io_size;

	/* Ensure we clear previously set non-block flag */
	if (!force_nonblock)
		kiocb->ki_flags &= ~IOCB_NOWAIT;
	else
		kiocb->ki_flags |= IOCB_NOWAIT;

	/* If the file doesn't support async, just async punt */
	if (force_nonblock && !io_file_supports_async(req, WRITE))
		goto copy_iov;

	/* file path doesn't support NOWAIT for non-direct_IO */
	if (force_nonblock && !(kiocb->ki_flags & IOCB_DIRECT) &&
	    (req->flags & REQ_F_ISREG))
		goto copy_iov;

	ret = rw_verify_area(WRITE, req->file, io_kiocb_ppos(kiocb), io_size);
	if (unlikely(ret))
		goto out_free;

	/*
	 * Open-code file_start_write here to grab freeze protection,
	 * which will be released by another thread in
	 * io_complete_rw().  Fool lockdep by telling it the lock got
	 * released so that it doesn't complain about the held lock when
	 * we return to userspace.
	 */
	if (req->flags & REQ_F_ISREG) {
		sb_start_write(file_inode(req->file)->i_sb);
		__sb_writers_release(file_inode(req->file)->i_sb,
					SB_FREEZE_WRITE);
	}
	kiocb->ki_flags |= IOCB_WRITE;

	if (req->file->f_op->write_iter)
		ret2 = call_write_iter(req->file, kiocb, iter);
	else if (req->file->f_op->write)
		ret2 = loop_rw_iter(WRITE, req, iter);
	else
		ret2 = -EINVAL;

	if (req->flags & REQ_F_REISSUE) {
		req->flags &= ~REQ_F_REISSUE;
		ret2 = -EAGAIN;
	}

	/*
	 * Raw bdev writes will return -EOPNOTSUPP for IOCB_NOWAIT. Just
	 * retry them without IOCB_NOWAIT.
	 */
	if (ret2 == -EOPNOTSUPP && (kiocb->ki_flags & IOCB_NOWAIT))
		ret2 = -EAGAIN;
	/* no retry on NONBLOCK nor RWF_NOWAIT */
	if (ret2 == -EAGAIN && (req->flags & REQ_F_NOWAIT))
		goto done;
	if (!force_nonblock || ret2 != -EAGAIN) {
		/* IOPOLL retry should happen for io-wq threads */
		if ((req->ctx->flags & IORING_SETUP_IOPOLL) && ret2 == -EAGAIN)
			goto copy_iov;
done:
		kiocb_done(kiocb, ret2, issue_flags);
	} else {
copy_iov:
		/* some cases will consume bytes even on error returns */
		iov_iter_revert(iter, io_size - iov_iter_count(iter));
		ret = io_setup_async_rw(req, iovec, inline_vecs, iter, false);
		return ret ?: -EAGAIN;
	}
out_free:
	/* it's reportedly faster than delegating the null check to kfree() */
	if (iovec)
		kfree(iovec);
	return ret;
}

static int io_renameat_prep(struct io_kiocb *req,
			    const struct io_uring_sqe *sqe)
{
	struct io_rename *ren = &req->rename;
	const char __user *oldf, *newf;

	if (unlikely(req->flags & REQ_F_FIXED_FILE))
		return -EBADF;

	ren->old_dfd = READ_ONCE(sqe->fd);
	oldf = u64_to_user_ptr(READ_ONCE(sqe->addr));
	newf = u64_to_user_ptr(READ_ONCE(sqe->addr2));
	ren->new_dfd = READ_ONCE(sqe->len);
	ren->flags = READ_ONCE(sqe->rename_flags);

	ren->oldpath = getname(oldf);
	if (IS_ERR(ren->oldpath))
		return PTR_ERR(ren->oldpath);

	ren->newpath = getname(newf);
	if (IS_ERR(ren->newpath)) {
		putname(ren->oldpath);
		return PTR_ERR(ren->newpath);
	}

	req->flags |= REQ_F_NEED_CLEANUP;
	return 0;
}

static int io_renameat(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_rename *ren = &req->rename;
	int ret;

	if (issue_flags & IO_URING_F_NONBLOCK)
		return -EAGAIN;

	ret = do_renameat2(ren->old_dfd, ren->oldpath, ren->new_dfd,
				ren->newpath, ren->flags);

	req->flags &= ~REQ_F_NEED_CLEANUP;
	if (ret < 0)
		req_set_fail_links(req);
	io_req_complete(req, ret);
	return 0;
}

static int io_unlinkat_prep(struct io_kiocb *req,
			    const struct io_uring_sqe *sqe)
{
	struct io_unlink *un = &req->unlink;
	const char __user *fname;

	if (unlikely(req->flags & REQ_F_FIXED_FILE))
		return -EBADF;

	un->dfd = READ_ONCE(sqe->fd);

	un->flags = READ_ONCE(sqe->unlink_flags);
	if (un->flags & ~AT_REMOVEDIR)
		return -EINVAL;

	fname = u64_to_user_ptr(READ_ONCE(sqe->addr));
	un->filename = getname(fname);
	if (IS_ERR(un->filename))
		return PTR_ERR(un->filename);

	req->flags |= REQ_F_NEED_CLEANUP;
	return 0;
}

static int io_unlinkat(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_unlink *un = &req->unlink;
	int ret;

	if (issue_flags & IO_URING_F_NONBLOCK)
		return -EAGAIN;

	if (un->flags & AT_REMOVEDIR)
		ret = do_rmdir(un->dfd, un->filename);
	else
		ret = do_unlinkat(un->dfd, un->filename);

	req->flags &= ~REQ_F_NEED_CLEANUP;
	if (ret < 0)
		req_set_fail_links(req);
	io_req_complete(req, ret);
	return 0;
}

static int io_shutdown_prep(struct io_kiocb *req,
			    const struct io_uring_sqe *sqe)
{
#if defined(CONFIG_NET)
	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
		return -EINVAL;
	if (sqe->ioprio || sqe->off || sqe->addr || sqe->rw_flags ||
	    sqe->buf_index)
		return -EINVAL;

	req->shutdown.how = READ_ONCE(sqe->len);
	return 0;
#else
	return -EOPNOTSUPP;
#endif
}

static int io_shutdown(struct io_kiocb *req, unsigned int issue_flags)
{
#if defined(CONFIG_NET)
	struct socket *sock;
	int ret;

	if (issue_flags & IO_URING_F_NONBLOCK)
		return -EAGAIN;

	sock = sock_from_file(req->file);
	if (unlikely(!sock))
		return -ENOTSOCK;

	ret = __sys_shutdown_sock(sock, req->shutdown.how);
	if (ret < 0)
		req_set_fail_links(req);
	io_req_complete(req, ret);
	return 0;
#else
	return -EOPNOTSUPP;
#endif
}

static int __io_splice_prep(struct io_kiocb *req,
			    const struct io_uring_sqe *sqe)
{
	struct io_splice* sp = &req->splice;
	unsigned int valid_flags = SPLICE_F_FD_IN_FIXED | SPLICE_F_ALL;

	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
		return -EINVAL;

	sp->file_in = NULL;
	sp->len = READ_ONCE(sqe->len);
	sp->flags = READ_ONCE(sqe->splice_flags);

	if (unlikely(sp->flags & ~valid_flags))
		return -EINVAL;

	sp->file_in = io_file_get(NULL, req, READ_ONCE(sqe->splice_fd_in),
				  (sp->flags & SPLICE_F_FD_IN_FIXED));
	if (!sp->file_in)
		return -EBADF;
	req->flags |= REQ_F_NEED_CLEANUP;
	return 0;
}

static int io_tee_prep(struct io_kiocb *req,
		       const struct io_uring_sqe *sqe)
{
	if (READ_ONCE(sqe->splice_off_in) || READ_ONCE(sqe->off))
		return -EINVAL;
	return __io_splice_prep(req, sqe);
}

static int io_tee(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_splice *sp = &req->splice;
	struct file *in = sp->file_in;
	struct file *out = sp->file_out;
	unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED;
	long ret = 0;

	if (issue_flags & IO_URING_F_NONBLOCK)
		return -EAGAIN;
	if (sp->len)
		ret = do_tee(in, out, sp->len, flags);

	if (!(sp->flags & SPLICE_F_FD_IN_FIXED))
		io_put_file(in);
	req->flags &= ~REQ_F_NEED_CLEANUP;

	if (ret != sp->len)
		req_set_fail_links(req);
	io_req_complete(req, ret);
	return 0;
}

static int io_splice_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	struct io_splice* sp = &req->splice;

	sp->off_in = READ_ONCE(sqe->splice_off_in);
	sp->off_out = READ_ONCE(sqe->off);
	return __io_splice_prep(req, sqe);
}

static int io_splice(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_splice *sp = &req->splice;
	struct file *in = sp->file_in;
	struct file *out = sp->file_out;
	unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED;
	loff_t *poff_in, *poff_out;
	long ret = 0;

	if (issue_flags & IO_URING_F_NONBLOCK)
		return -EAGAIN;

	poff_in = (sp->off_in == -1) ? NULL : &sp->off_in;
	poff_out = (sp->off_out == -1) ? NULL : &sp->off_out;

	if (sp->len)
		ret = do_splice(in, poff_in, out, poff_out, sp->len, flags);

	if (!(sp->flags & SPLICE_F_FD_IN_FIXED))
		io_put_file(in);
	req->flags &= ~REQ_F_NEED_CLEANUP;

	if (ret != sp->len)
		req_set_fail_links(req);
	io_req_complete(req, ret);
	return 0;
}

/*
 * IORING_OP_NOP just posts a completion event, nothing else.
 */
static int io_nop(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_ring_ctx *ctx = req->ctx;

	if (unlikely(ctx->flags & IORING_SETUP_IOPOLL))
		return -EINVAL;

	__io_req_complete(req, issue_flags, 0, 0);
	return 0;
}

static int io_fsync_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	struct io_ring_ctx *ctx = req->ctx;

	if (!req->file)
		return -EBADF;

	if (unlikely(ctx->flags & IORING_SETUP_IOPOLL))
		return -EINVAL;
	if (unlikely(sqe->addr || sqe->ioprio || sqe->buf_index))
		return -EINVAL;

	req->sync.flags = READ_ONCE(sqe->fsync_flags);
	if (unlikely(req->sync.flags & ~IORING_FSYNC_DATASYNC))
		return -EINVAL;

	req->sync.off = READ_ONCE(sqe->off);
	req->sync.len = READ_ONCE(sqe->len);
	return 0;
}

static int io_fsync(struct io_kiocb *req, unsigned int issue_flags)
{
	loff_t end = req->sync.off + req->sync.len;
	int ret;

	/* fsync always requires a blocking context */
	if (issue_flags & IO_URING_F_NONBLOCK)
		return -EAGAIN;

	ret = vfs_fsync_range(req->file, req->sync.off,
				end > 0 ? end : LLONG_MAX,
				req->sync.flags & IORING_FSYNC_DATASYNC);
	if (ret < 0)
		req_set_fail_links(req);
	io_req_complete(req, ret);
	return 0;
}

static int io_fallocate_prep(struct io_kiocb *req,
			     const struct io_uring_sqe *sqe)
{
	if (sqe->ioprio || sqe->buf_index || sqe->rw_flags)
		return -EINVAL;
	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
		return -EINVAL;

	req->sync.off = READ_ONCE(sqe->off);
	req->sync.len = READ_ONCE(sqe->addr);
	req->sync.mode = READ_ONCE(sqe->len);
	return 0;
}

static int io_fallocate(struct io_kiocb *req, unsigned int issue_flags)
{
	int ret;

	/* fallocate always requiring blocking context */
	if (issue_flags & IO_URING_F_NONBLOCK)
		return -EAGAIN;
	ret = vfs_fallocate(req->file, req->sync.mode, req->sync.off,
				req->sync.len);
	if (ret < 0)
		req_set_fail_links(req);
	io_req_complete(req, ret);
	return 0;
}

static int __io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	const char __user *fname;
	int ret;

	if (unlikely(sqe->ioprio || sqe->buf_index))
		return -EINVAL;
	if (unlikely(req->flags & REQ_F_FIXED_FILE))
		return -EBADF;

	/* open.how should be already initialised */
	if (!(req->open.how.flags & O_PATH) && force_o_largefile())
		req->open.how.flags |= O_LARGEFILE;

	req->open.dfd = READ_ONCE(sqe->fd);
	fname = u64_to_user_ptr(READ_ONCE(sqe->addr));
	req->open.filename = getname(fname);
	if (IS_ERR(req->open.filename)) {
		ret = PTR_ERR(req->open.filename);
		req->open.filename = NULL;
		return ret;
	}
	req->open.nofile = rlimit(RLIMIT_NOFILE);
	req->flags |= REQ_F_NEED_CLEANUP;
	return 0;
}

static int io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	u64 flags, mode;

	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
		return -EINVAL;
	mode = READ_ONCE(sqe->len);
	flags = READ_ONCE(sqe->open_flags);
	req->open.how = build_open_how(flags, mode);
	return __io_openat_prep(req, sqe);
}

static int io_openat2_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	struct open_how __user *how;
	size_t len;
	int ret;

	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
		return -EINVAL;
	how = u64_to_user_ptr(READ_ONCE(sqe->addr2));
	len = READ_ONCE(sqe->len);
	if (len < OPEN_HOW_SIZE_VER0)
		return -EINVAL;

	ret = copy_struct_from_user(&req->open.how, sizeof(req->open.how), how,
					len);
	if (ret)
		return ret;

	return __io_openat_prep(req, sqe);
}

static int io_openat2(struct io_kiocb *req, unsigned int issue_flags)
{
	struct open_flags op;
	struct file *file;
	bool nonblock_set;
	bool resolve_nonblock;
	int ret;

	ret = build_open_flags(&req->open.how, &op);
	if (ret)
		goto err;
	nonblock_set = op.open_flag & O_NONBLOCK;
	resolve_nonblock = req->open.how.resolve & RESOLVE_CACHED;
	if (issue_flags & IO_URING_F_NONBLOCK) {
		/*
		 * Don't bother trying for O_TRUNC, O_CREAT, or O_TMPFILE open,
		 * it'll always -EAGAIN
		 */
		if (req->open.how.flags & (O_TRUNC | O_CREAT | O_TMPFILE))
			return -EAGAIN;
		op.lookup_flags |= LOOKUP_CACHED;
		op.open_flag |= O_NONBLOCK;
	}

	ret = __get_unused_fd_flags(req->open.how.flags, req->open.nofile);
	if (ret < 0)
		goto err;

	file = do_filp_open(req->open.dfd, req->open.filename, &op);
	/* only retry if RESOLVE_CACHED wasn't already set by application */
	if ((!resolve_nonblock && (issue_flags & IO_URING_F_NONBLOCK)) &&
	    file == ERR_PTR(-EAGAIN)) {
		/*
		 * We could hang on to this 'fd', but seems like marginal
		 * gain for something that is now known to be a slower path.
		 * So just put it, and we'll get a new one when we retry.
		 */
		put_unused_fd(ret);
		return -EAGAIN;
	}

	if (IS_ERR(file)) {
		put_unused_fd(ret);
		ret = PTR_ERR(file);
	} else {
		if ((issue_flags & IO_URING_F_NONBLOCK) && !nonblock_set)
			file->f_flags &= ~O_NONBLOCK;
		fsnotify_open(file);
		fd_install(ret, file);
	}
err:
	putname(req->open.filename);
	req->flags &= ~REQ_F_NEED_CLEANUP;
	if (ret < 0)
		req_set_fail_links(req);
	__io_req_complete(req, issue_flags, ret, 0);
	return 0;
}

static int io_openat(struct io_kiocb *req, unsigned int issue_flags)
{
	return io_openat2(req, issue_flags);
}

static int io_remove_buffers_prep(struct io_kiocb *req,
				  const struct io_uring_sqe *sqe)
{
	struct io_provide_buf *p = &req->pbuf;
	u64 tmp;

	if (sqe->ioprio || sqe->rw_flags || sqe->addr || sqe->len || sqe->off)
		return -EINVAL;

	tmp = READ_ONCE(sqe->fd);
	if (!tmp || tmp > USHRT_MAX)
		return -EINVAL;

	memset(p, 0, sizeof(*p));
	p->nbufs = tmp;
	p->bgid = READ_ONCE(sqe->buf_group);
	return 0;
}

static int __io_remove_buffers(struct io_ring_ctx *ctx, struct io_buffer *buf,
			       int bgid, unsigned nbufs)
{
	unsigned i = 0;

	/* shouldn't happen */
	if (!nbufs)
		return 0;

	/* the head kbuf is the list itself */
	while (!list_empty(&buf->list)) {
		struct io_buffer *nxt;

		nxt = list_first_entry(&buf->list, struct io_buffer, list);
		list_del(&nxt->list);
		kfree(nxt);
		if (++i == nbufs)
			return i;
	}
	i++;
	kfree(buf);
	xa_erase(&ctx->io_buffers, bgid);

	return i;
}

static int io_remove_buffers(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_provide_buf *p = &req->pbuf;
	struct io_ring_ctx *ctx = req->ctx;
	struct io_buffer *head;
	int ret = 0;
	bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;

	io_ring_submit_lock(ctx, !force_nonblock);

	lockdep_assert_held(&ctx->uring_lock);

	ret = -ENOENT;
	head = xa_load(&ctx->io_buffers, p->bgid);
	if (head)
		ret = __io_remove_buffers(ctx, head, p->bgid, p->nbufs);
	if (ret < 0)
		req_set_fail_links(req);

	/* complete before unlock, IOPOLL may need the lock */
	__io_req_complete(req, issue_flags, ret, 0);
	io_ring_submit_unlock(ctx, !force_nonblock);
	return 0;
}

static int io_provide_buffers_prep(struct io_kiocb *req,
				   const struct io_uring_sqe *sqe)
{
	unsigned long size, tmp_check;
	struct io_provide_buf *p = &req->pbuf;
	u64 tmp;

	if (sqe->ioprio || sqe->rw_flags)
		return -EINVAL;

	tmp = READ_ONCE(sqe->fd);
	if (!tmp || tmp > USHRT_MAX)
		return -E2BIG;
	p->nbufs = tmp;
	p->addr = READ_ONCE(sqe->addr);
	p->len = READ_ONCE(sqe->len);

	if (check_mul_overflow((unsigned long)p->len, (unsigned long)p->nbufs,
				&size))
		return -EOVERFLOW;
	if (check_add_overflow((unsigned long)p->addr, size, &tmp_check))
		return -EOVERFLOW;

	size = (unsigned long)p->len * p->nbufs;
	if (!access_ok(u64_to_user_ptr(p->addr), size))
		return -EFAULT;

	p->bgid = READ_ONCE(sqe->buf_group);
	tmp = READ_ONCE(sqe->off);
	if (tmp > USHRT_MAX)
		return -E2BIG;
	p->bid = tmp;
	return 0;
}

static int io_add_buffers(struct io_provide_buf *pbuf, struct io_buffer **head)
{
	struct io_buffer *buf;
	u64 addr = pbuf->addr;
	int i, bid = pbuf->bid;

	for (i = 0; i < pbuf->nbufs; i++) {
		buf = kmalloc(sizeof(*buf), GFP_KERNEL);
		if (!buf)
			break;

		buf->addr = addr;
		buf->len = min_t(__u32, pbuf->len, MAX_RW_COUNT);
		buf->bid = bid;
		addr += pbuf->len;
		bid++;
		if (!*head) {
			INIT_LIST_HEAD(&buf->list);
			*head = buf;
		} else {
			list_add_tail(&buf->list, &(*head)->list);
		}
	}

	return i ? i : -ENOMEM;
}

static int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_provide_buf *p = &req->pbuf;
	struct io_ring_ctx *ctx = req->ctx;
	struct io_buffer *head, *list;
	int ret = 0;
	bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;

	io_ring_submit_lock(ctx, !force_nonblock);

	lockdep_assert_held(&ctx->uring_lock);

	list = head = xa_load(&ctx->io_buffers, p->bgid);

	ret = io_add_buffers(p, &head);
	if (ret >= 0 && !list) {
		ret = xa_insert(&ctx->io_buffers, p->bgid, head, GFP_KERNEL);
		if (ret < 0)
			__io_remove_buffers(ctx, head, p->bgid, -1U);
	}
	if (ret < 0)
		req_set_fail_links(req);
	/* complete before unlock, IOPOLL may need the lock */
	__io_req_complete(req, issue_flags, ret, 0);
	io_ring_submit_unlock(ctx, !force_nonblock);
	return 0;
}

static int io_epoll_ctl_prep(struct io_kiocb *req,
			     const struct io_uring_sqe *sqe)
{
#if defined(CONFIG_EPOLL)
	if (sqe->ioprio || sqe->buf_index)
		return -EINVAL;
	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
		return -EINVAL;

	req->epoll.epfd = READ_ONCE(sqe->fd);
	req->epoll.op = READ_ONCE(sqe->len);
	req->epoll.fd = READ_ONCE(sqe->off);

	if (ep_op_has_event(req->epoll.op)) {
		struct epoll_event __user *ev;

		ev = u64_to_user_ptr(READ_ONCE(sqe->addr));
		if (copy_from_user(&req->epoll.event, ev, sizeof(*ev)))
			return -EFAULT;
	}

	return 0;
#else
	return -EOPNOTSUPP;
#endif
}

static int io_epoll_ctl(struct io_kiocb *req, unsigned int issue_flags)
{
#if defined(CONFIG_EPOLL)
	struct io_epoll *ie = &req->epoll;
	int ret;
	bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;

	ret = do_epoll_ctl(ie->epfd, ie->op, ie->fd, &ie->event, force_nonblock);
	if (force_nonblock && ret == -EAGAIN)
		return -EAGAIN;

	if (ret < 0)
		req_set_fail_links(req);
	__io_req_complete(req, issue_flags, ret, 0);
	return 0;
#else
	return -EOPNOTSUPP;
#endif
}

static int io_madvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
#if defined(CONFIG_ADVISE_SYSCALLS) && defined(CONFIG_MMU)
	if (sqe->ioprio || sqe->buf_index || sqe->off)
		return -EINVAL;
	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
		return -EINVAL;

	req->madvise.addr = READ_ONCE(sqe->addr);
	req->madvise.len = READ_ONCE(sqe->len);
	req->madvise.advice = READ_ONCE(sqe->fadvise_advice);
	return 0;
#else
	return -EOPNOTSUPP;
#endif
}

static int io_madvise(struct io_kiocb *req, unsigned int issue_flags)
{
#if defined(CONFIG_ADVISE_SYSCALLS) && defined(CONFIG_MMU)
	struct io_madvise *ma = &req->madvise;
	int ret;

	if (issue_flags & IO_URING_F_NONBLOCK)
		return -EAGAIN;

	ret = do_madvise(current->mm, ma->addr, ma->len, ma->advice);
	if (ret < 0)
		req_set_fail_links(req);
	io_req_complete(req, ret);
	return 0;
#else
	return -EOPNOTSUPP;
#endif
}

static int io_fadvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	if (sqe->ioprio || sqe->buf_index || sqe->addr)
		return -EINVAL;
	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
		return -EINVAL;

	req->fadvise.offset = READ_ONCE(sqe->off);
	req->fadvise.len = READ_ONCE(sqe->len);
	req->fadvise.advice = READ_ONCE(sqe->fadvise_advice);
	return 0;
}

static int io_fadvise(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_fadvise *fa = &req->fadvise;
	int ret;

	if (issue_flags & IO_URING_F_NONBLOCK) {
		switch (fa->advice) {
		case POSIX_FADV_NORMAL:
		case POSIX_FADV_RANDOM:
		case POSIX_FADV_SEQUENTIAL:
			break;
		default:
			return -EAGAIN;
		}
	}

	ret = vfs_fadvise(req->file, fa->offset, fa->len, fa->advice);
	if (ret < 0)
		req_set_fail_links(req);
	__io_req_complete(req, issue_flags, ret, 0);
	return 0;
}

static int io_statx_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
		return -EINVAL;
	if (sqe->ioprio || sqe->buf_index)
		return -EINVAL;
	if (req->flags & REQ_F_FIXED_FILE)
		return -EBADF;

	req->statx.dfd = READ_ONCE(sqe->fd);
	req->statx.mask = READ_ONCE(sqe->len);
	req->statx.filename = u64_to_user_ptr(READ_ONCE(sqe->addr));
	req->statx.buffer = u64_to_user_ptr(READ_ONCE(sqe->addr2));
	req->statx.flags = READ_ONCE(sqe->statx_flags);

	return 0;
}

static int io_statx(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_statx *ctx = &req->statx;
	int ret;

	if (issue_flags & IO_URING_F_NONBLOCK)
		return -EAGAIN;

	ret = do_statx(ctx->dfd, ctx->filename, ctx->flags, ctx->mask,
		       ctx->buffer);

	if (ret < 0)
		req_set_fail_links(req);
	io_req_complete(req, ret);
	return 0;
}

static int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
		return -EINVAL;
	if (sqe->ioprio || sqe->off || sqe->addr || sqe->len ||
	    sqe->rw_flags || sqe->buf_index)
		return -EINVAL;
	if (req->flags & REQ_F_FIXED_FILE)
		return -EBADF;

	req->close.fd = READ_ONCE(sqe->fd);
	return 0;
}

static int io_close(struct io_kiocb *req, unsigned int issue_flags)
{
	struct files_struct *files = current->files;
	struct io_close *close = &req->close;
	struct fdtable *fdt;
	struct file *file = NULL;
	int ret = -EBADF;

	spin_lock(&files->file_lock);
	fdt = files_fdtable(files);
	if (close->fd >= fdt->max_fds) {
		spin_unlock(&files->file_lock);
		goto err;
	}
	file = fdt->fd[close->fd];
	if (!file || file->f_op == &io_uring_fops) {
		spin_unlock(&files->file_lock);
		file = NULL;
		goto err;
	}

	/* if the file has a flush method, be safe and punt to async */
	if (file->f_op->flush && (issue_flags & IO_URING_F_NONBLOCK)) {
		spin_unlock(&files->file_lock);
		return -EAGAIN;
	}

	ret = __close_fd_get_file(close->fd, &file);
	spin_unlock(&files->file_lock);
	if (ret < 0) {
		if (ret == -ENOENT)
			ret = -EBADF;
		goto err;
	}

	/* No ->flush() or already async, safely close from here */
	ret = filp_close(file, current->files);
err:
	if (ret < 0)
		req_set_fail_links(req);
	if (file)
		fput(file);
	__io_req_complete(req, issue_flags, ret, 0);
	return 0;
}

static int io_sfr_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	struct io_ring_ctx *ctx = req->ctx;

	if (unlikely(ctx->flags & IORING_SETUP_IOPOLL))
		return -EINVAL;
	if (unlikely(sqe->addr || sqe->ioprio || sqe->buf_index))
		return -EINVAL;

	req->sync.off = READ_ONCE(sqe->off);
	req->sync.len = READ_ONCE(sqe->len);
	req->sync.flags = READ_ONCE(sqe->sync_range_flags);
	return 0;
}

static int io_sync_file_range(struct io_kiocb *req, unsigned int issue_flags)
{
	int ret;

	/* sync_file_range always requires a blocking context */
	if (issue_flags & IO_URING_F_NONBLOCK)
		return -EAGAIN;

	ret = sync_file_range(req->file, req->sync.off, req->sync.len,
				req->sync.flags);
	if (ret < 0)
		req_set_fail_links(req);
	io_req_complete(req, ret);
	return 0;
}

#if defined(CONFIG_NET)
static int io_setup_async_msg(struct io_kiocb *req,
			      struct io_async_msghdr *kmsg)
{
	struct io_async_msghdr *async_msg = req->async_data;

	if (async_msg)
		return -EAGAIN;
	if (io_alloc_async_data(req)) {
		kfree(kmsg->free_iov);
		return -ENOMEM;
	}
	async_msg = req->async_data;
	req->flags |= REQ_F_NEED_CLEANUP;
	memcpy(async_msg, kmsg, sizeof(*kmsg));
	async_msg->msg.msg_name = &async_msg->addr;
	/* if were using fast_iov, set it to the new one */
	if (!async_msg->free_iov)
		async_msg->msg.msg_iter.iov = async_msg->fast_iov;

	return -EAGAIN;
}

static int io_sendmsg_copy_hdr(struct io_kiocb *req,
			       struct io_async_msghdr *iomsg)
{
	iomsg->msg.msg_name = &iomsg->addr;
	iomsg->free_iov = iomsg->fast_iov;
	return sendmsg_copy_msghdr(&iomsg->msg, req->sr_msg.umsg,
				   req->sr_msg.msg_flags, &iomsg->free_iov);
}

static int io_sendmsg_prep_async(struct io_kiocb *req)
{
	int ret;

	ret = io_sendmsg_copy_hdr(req, req->async_data);
	if (!ret)
		req->flags |= REQ_F_NEED_CLEANUP;
	return ret;
}

static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	struct io_sr_msg *sr = &req->sr_msg;

	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
		return -EINVAL;

	sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr));
	sr->len = READ_ONCE(sqe->len);
	sr->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL;
	if (sr->msg_flags & MSG_DONTWAIT)
		req->flags |= REQ_F_NOWAIT;

#ifdef CONFIG_COMPAT
	if (req->ctx->compat)
		sr->msg_flags |= MSG_CMSG_COMPAT;
#endif
	return 0;
}

static int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_async_msghdr iomsg, *kmsg;
	struct socket *sock;
	unsigned flags;
	int min_ret = 0;
	int ret;

	sock = sock_from_file(req->file);
	if (unlikely(!sock))
		return -ENOTSOCK;

	kmsg = req->async_data;
	if (!kmsg) {
		ret = io_sendmsg_copy_hdr(req, &iomsg);
		if (ret)
			return ret;
		kmsg = &iomsg;
	}

	flags = req->sr_msg.msg_flags;
	if (issue_flags & IO_URING_F_NONBLOCK)
		flags |= MSG_DONTWAIT;
	if (flags & MSG_WAITALL)
		min_ret = iov_iter_count(&kmsg->msg.msg_iter);

	ret = __sys_sendmsg_sock(sock, &kmsg->msg, flags);
	if ((issue_flags & IO_URING_F_NONBLOCK) && ret == -EAGAIN)
		return io_setup_async_msg(req, kmsg);
	if (ret == -ERESTARTSYS)
		ret = -EINTR;

	/* fast path, check for non-NULL to avoid function call */
	if (kmsg->free_iov)
		kfree(kmsg->free_iov);
	req->flags &= ~REQ_F_NEED_CLEANUP;
	if (ret < min_ret)
		req_set_fail_links(req);
	__io_req_complete(req, issue_flags, ret, 0);
	return 0;
}

static int io_send(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_sr_msg *sr = &req->sr_msg;
	struct msghdr msg;
	struct iovec iov;
	struct socket *sock;
	unsigned flags;
	int min_ret = 0;
	int ret;

	sock = sock_from_file(req->file);
	if (unlikely(!sock))
		return -ENOTSOCK;

	ret = import_single_range(WRITE, sr->buf, sr->len, &iov, &msg.msg_iter);
	if (unlikely(ret))
		return ret;

	msg.msg_name = NULL;
	msg.msg_control = NULL;
	msg.msg_controllen = 0;
	msg.msg_namelen = 0;

	flags = req->sr_msg.msg_flags;
	if (issue_flags & IO_URING_F_NONBLOCK)
		flags |= MSG_DONTWAIT;
	if (flags & MSG_WAITALL)
		min_ret = iov_iter_count(&msg.msg_iter);

	msg.msg_flags = flags;
	ret = sock_sendmsg(sock, &msg);
	if ((issue_flags & IO_URING_F_NONBLOCK) && ret == -EAGAIN)
		return -EAGAIN;
	if (ret == -ERESTARTSYS)
		ret = -EINTR;

	if (ret < min_ret)
		req_set_fail_links(req);
	__io_req_complete(req, issue_flags, ret, 0);
	return 0;
}

static int __io_recvmsg_copy_hdr(struct io_kiocb *req,
				 struct io_async_msghdr *iomsg)
{
	struct io_sr_msg *sr = &req->sr_msg;
	struct iovec __user *uiov;
	size_t iov_len;
	int ret;

	ret = __copy_msghdr_from_user(&iomsg->msg, sr->umsg,
					&iomsg->uaddr, &uiov, &iov_len);
	if (ret)
		return ret;

	if (req->flags & REQ_F_BUFFER_SELECT) {
		if (iov_len > 1)
			return -EINVAL;
		if (copy_from_user(iomsg->fast_iov, uiov, sizeof(*uiov)))
			return -EFAULT;
		sr->len = iomsg->fast_iov[0].iov_len;
		iomsg->free_iov = NULL;
	} else {
		iomsg->free_iov = iomsg->fast_iov;
		ret = __import_iovec(READ, uiov, iov_len, UIO_FASTIOV,
				     &iomsg->free_iov, &iomsg->msg.msg_iter,
				     false);
		if (ret > 0)
			ret = 0;
	}

	return ret;
}

#ifdef CONFIG_COMPAT
static int __io_compat_recvmsg_copy_hdr(struct io_kiocb *req,
					struct io_async_msghdr *iomsg)
{
	struct io_sr_msg *sr = &req->sr_msg;
	struct compat_iovec __user *uiov;
	compat_uptr_t ptr;
	compat_size_t len;
	int ret;

	ret = __get_compat_msghdr(&iomsg->msg, sr->umsg_compat, &iomsg->uaddr,
				  &ptr, &len);
	if (ret)
		return ret;

	uiov = compat_ptr(ptr);
	if (req->flags & REQ_F_BUFFER_SELECT) {
		compat_ssize_t clen;

		if (len > 1)
			return -EINVAL;
		if (!access_ok(uiov, sizeof(*uiov)))
			return -EFAULT;
		if (__get_user(clen, &uiov->iov_len))
			return -EFAULT;
		if (clen < 0)
			return -EINVAL;
		sr->len = clen;
		iomsg->free_iov = NULL;
	} else {
		iomsg->free_iov = iomsg->fast_iov;
		ret = __import_iovec(READ, (struct iovec __user *)uiov, len,
				   UIO_FASTIOV, &iomsg->free_iov,
				   &iomsg->msg.msg_iter, true);
		if (ret < 0)
			return ret;
	}

	return 0;
}
#endif

static int io_recvmsg_copy_hdr(struct io_kiocb *req,
			       struct io_async_msghdr *iomsg)
{
	iomsg->msg.msg_name = &iomsg->addr;

#ifdef CONFIG_COMPAT
	if (req->ctx->compat)
		return __io_compat_recvmsg_copy_hdr(req, iomsg);
#endif

	return __io_recvmsg_copy_hdr(req, iomsg);
}

static struct io_buffer *io_recv_buffer_select(struct io_kiocb *req,
					       bool needs_lock)
{
	struct io_sr_msg *sr = &req->sr_msg;
	struct io_buffer *kbuf;

	kbuf = io_buffer_select(req, &sr->len, sr->bgid, sr->kbuf, needs_lock);
	if (IS_ERR(kbuf))
		return kbuf;

	sr->kbuf = kbuf;
	req->flags |= REQ_F_BUFFER_SELECTED;
	return kbuf;
}

static inline unsigned int io_put_recv_kbuf(struct io_kiocb *req)
{
	return io_put_kbuf(req, req->sr_msg.kbuf);
}

static int io_recvmsg_prep_async(struct io_kiocb *req)
{
	int ret;

	ret = io_recvmsg_copy_hdr(req, req->async_data);
	if (!ret)
		req->flags |= REQ_F_NEED_CLEANUP;
	return ret;
}

static int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	struct io_sr_msg *sr = &req->sr_msg;

	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
		return -EINVAL;

	sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr));
	sr->len = READ_ONCE(sqe->len);
	sr->bgid = READ_ONCE(sqe->buf_group);
	sr->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL;
	if (sr->msg_flags & MSG_DONTWAIT)
		req->flags |= REQ_F_NOWAIT;

#ifdef CONFIG_COMPAT
	if (req->ctx->compat)
		sr->msg_flags |= MSG_CMSG_COMPAT;
#endif
	return 0;
}

static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_async_msghdr iomsg, *kmsg;
	struct socket *sock;
	struct io_buffer *kbuf;
	unsigned flags;
	int min_ret = 0;
	int ret, cflags = 0;
	bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;

	sock = sock_from_file(req->file);
	if (unlikely(!sock))
		return -ENOTSOCK;

	kmsg = req->async_data;
	if (!kmsg) {
		ret = io_recvmsg_copy_hdr(req, &iomsg);
		if (ret)
			return ret;
		kmsg = &iomsg;
	}

	if (req->flags & REQ_F_BUFFER_SELECT) {
		kbuf = io_recv_buffer_select(req, !force_nonblock);
		if (IS_ERR(kbuf))
			return PTR_ERR(kbuf);
		kmsg->fast_iov[0].iov_base = u64_to_user_ptr(kbuf->addr);
		kmsg->fast_iov[0].iov_len = req->sr_msg.len;
		iov_iter_init(&kmsg->msg.msg_iter, READ, kmsg->fast_iov,
				1, req->sr_msg.len);
	}

	flags = req->sr_msg.msg_flags;
	if (force_nonblock)
		flags |= MSG_DONTWAIT;
	if (flags & MSG_WAITALL)
		min_ret = iov_iter_count(&kmsg->msg.msg_iter);

	ret = __sys_recvmsg_sock(sock, &kmsg->msg, req->sr_msg.umsg,
					kmsg->uaddr, flags);
	if (force_nonblock && ret == -EAGAIN)
		return io_setup_async_msg(req, kmsg);
	if (ret == -ERESTARTSYS)
		ret = -EINTR;

	if (req->flags & REQ_F_BUFFER_SELECTED)
		cflags = io_put_recv_kbuf(req);
	/* fast path, check for non-NULL to avoid function call */
	if (kmsg->free_iov)
		kfree(kmsg->free_iov);
	req->flags &= ~REQ_F_NEED_CLEANUP;
	if (ret < min_ret || ((flags & MSG_WAITALL) && (kmsg->msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC))))
		req_set_fail_links(req);
	__io_req_complete(req, issue_flags, ret, cflags);
	return 0;
}

static int io_recv(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_buffer *kbuf;
	struct io_sr_msg *sr = &req->sr_msg;
	struct msghdr msg;
	void __user *buf = sr->buf;
	struct socket *sock;
	struct iovec iov;
	unsigned flags;
	int min_ret = 0;
	int ret, cflags = 0;
	bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;

	sock = sock_from_file(req->file);
	if (unlikely(!sock))
		return -ENOTSOCK;

	if (req->flags & REQ_F_BUFFER_SELECT) {
		kbuf = io_recv_buffer_select(req, !force_nonblock);
		if (IS_ERR(kbuf))
			return PTR_ERR(kbuf);
		buf = u64_to_user_ptr(kbuf->addr);
	}

	ret = import_single_range(READ, buf, sr->len, &iov, &msg.msg_iter);
	if (unlikely(ret))
		goto out_free;

	msg.msg_name = NULL;
	msg.msg_control = NULL;
	msg.msg_controllen = 0;
	msg.msg_namelen = 0;
	msg.msg_iocb = NULL;
	msg.msg_flags = 0;

	flags = req->sr_msg.msg_flags;
	if (force_nonblock)
		flags |= MSG_DONTWAIT;
	if (flags & MSG_WAITALL)
		min_ret = iov_iter_count(&msg.msg_iter);

	ret = sock_recvmsg(sock, &msg, flags);
	if (force_nonblock && ret == -EAGAIN)
		return -EAGAIN;
	if (ret == -ERESTARTSYS)
		ret = -EINTR;
out_free:
	if (req->flags & REQ_F_BUFFER_SELECTED)
		cflags = io_put_recv_kbuf(req);
	if (ret < min_ret || ((flags & MSG_WAITALL) && (msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC))))
		req_set_fail_links(req);
	__io_req_complete(req, issue_flags, ret, cflags);
	return 0;
}

static int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	struct io_accept *accept = &req->accept;

	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
		return -EINVAL;
	if (sqe->ioprio || sqe->len || sqe->buf_index)
		return -EINVAL;

	accept->addr = u64_to_user_ptr(READ_ONCE(sqe->addr));
	accept->addr_len = u64_to_user_ptr(READ_ONCE(sqe->addr2));
	accept->flags = READ_ONCE(sqe->accept_flags);
	accept->nofile = rlimit(RLIMIT_NOFILE);
	return 0;
}

static int io_accept(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_accept *accept = &req->accept;
	bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
	unsigned int file_flags = force_nonblock ? O_NONBLOCK : 0;
	int ret;

	if (req->file->f_flags & O_NONBLOCK)
		req->flags |= REQ_F_NOWAIT;

	ret = __sys_accept4_file(req->file, file_flags, accept->addr,
					accept->addr_len, accept->flags,
					accept->nofile);
	if (ret == -EAGAIN && force_nonblock)
		return -EAGAIN;
	if (ret < 0) {
		if (ret == -ERESTARTSYS)
			ret = -EINTR;
		req_set_fail_links(req);
	}
	__io_req_complete(req, issue_flags, ret, 0);
	return 0;
}

static int io_connect_prep_async(struct io_kiocb *req)
{
	struct io_async_connect *io = req->async_data;
	struct io_connect *conn = &req->connect;

	return move_addr_to_kernel(conn->addr, conn->addr_len, &io->address);
}

static int io_connect_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	struct io_connect *conn = &req->connect;

	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
		return -EINVAL;
	if (sqe->ioprio || sqe->len || sqe->buf_index || sqe->rw_flags)
		return -EINVAL;

	conn->addr = u64_to_user_ptr(READ_ONCE(sqe->addr));
	conn->addr_len =  READ_ONCE(sqe->addr2);
	return 0;
}

static int io_connect(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_async_connect __io, *io;
	unsigned file_flags;
	int ret;
	bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;

	if (req->async_data) {
		io = req->async_data;
	} else {
		ret = move_addr_to_kernel(req->connect.addr,
						req->connect.addr_len,
						&__io.address);
		if (ret)
			goto out;
		io = &__io;
	}

	file_flags = force_nonblock ? O_NONBLOCK : 0;

	ret = __sys_connect_file(req->file, &io->address,
					req->connect.addr_len, file_flags);
	if ((ret == -EAGAIN || ret == -EINPROGRESS) && force_nonblock) {
		if (req->async_data)
			return -EAGAIN;
		if (io_alloc_async_data(req)) {
			ret = -ENOMEM;
			goto out;
		}
		memcpy(req->async_data, &__io, sizeof(__io));
		return -EAGAIN;
	}
	if (ret == -ERESTARTSYS)
		ret = -EINTR;
out:
	if (ret < 0)
		req_set_fail_links(req);
	__io_req_complete(req, issue_flags, ret, 0);
	return 0;
}
#else /* !CONFIG_NET */
#define IO_NETOP_FN(op)							\
static int io_##op(struct io_kiocb *req, unsigned int issue_flags)	\
{									\
	return -EOPNOTSUPP;						\
}

#define IO_NETOP_PREP(op)						\
IO_NETOP_FN(op)								\
static int io_##op##_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) \
{									\
	return -EOPNOTSUPP;						\
}									\

#define IO_NETOP_PREP_ASYNC(op)						\
IO_NETOP_PREP(op)							\
static int io_##op##_prep_async(struct io_kiocb *req)			\
{									\
	return -EOPNOTSUPP;						\
}

IO_NETOP_PREP_ASYNC(sendmsg);
IO_NETOP_PREP_ASYNC(recvmsg);
IO_NETOP_PREP_ASYNC(connect);
IO_NETOP_PREP(accept);
IO_NETOP_FN(send);
IO_NETOP_FN(recv);
#endif /* CONFIG_NET */

struct io_poll_table {
	struct poll_table_struct pt;
	struct io_kiocb *req;
	int error;
};

static int __io_async_wake(struct io_kiocb *req, struct io_poll_iocb *poll,
			   __poll_t mask, task_work_func_t func)
{
	int ret;

	/* for instances that support it check for an event match first: */
	if (mask && !(mask & poll->events))
		return 0;

	trace_io_uring_task_add(req->ctx, req->opcode, req->user_data, mask);

	list_del_init(&poll->wait.entry);

	req->result = mask;
	req->task_work.func = func;

	/*
	 * If this fails, then the task is exiting. When a task exits, the
	 * work gets canceled, so just cancel this request as well instead
	 * of executing it. We can't safely execute it anyway, as we may not
	 * have the needed state needed for it anyway.
	 */
	ret = io_req_task_work_add(req);
	if (unlikely(ret)) {
		WRITE_ONCE(poll->canceled, true);
		io_req_task_work_add_fallback(req, func);
	}
	return 1;
}

static bool io_poll_rewait(struct io_kiocb *req, struct io_poll_iocb *poll)
	__acquires(&req->ctx->completion_lock)
{
	struct io_ring_ctx *ctx = req->ctx;

	if (!req->result && !READ_ONCE(poll->canceled)) {
		struct poll_table_struct pt = { ._key = poll->events };

		req->result = vfs_poll(req->file, &pt) & poll->events;
	}

	spin_lock_irq(&ctx->completion_lock);
	if (!req->result && !READ_ONCE(poll->canceled)) {
		add_wait_queue(poll->head, &poll->wait);
		return true;
	}

	return false;
}

static struct io_poll_iocb *io_poll_get_double(struct io_kiocb *req)
{
	/* pure poll stashes this in ->async_data, poll driven retry elsewhere */
	if (req->opcode == IORING_OP_POLL_ADD)
		return req->async_data;
	return req->apoll->double_poll;
}

static struct io_poll_iocb *io_poll_get_single(struct io_kiocb *req)
{
	if (req->opcode == IORING_OP_POLL_ADD)
		return &req->poll;
	return &req->apoll->poll;
}

static void io_poll_remove_double(struct io_kiocb *req)
	__must_hold(&req->ctx->completion_lock)
{
	struct io_poll_iocb *poll = io_poll_get_double(req);

	lockdep_assert_held(&req->ctx->completion_lock);

	if (poll && poll->head) {
		struct wait_queue_head *head = poll->head;

		spin_lock(&head->lock);
		list_del_init(&poll->wait.entry);
		if (poll->wait.private)
			req_ref_put(req);
		poll->head = NULL;
		spin_unlock(&head->lock);
	}
}

static bool io_poll_complete(struct io_kiocb *req, __poll_t mask)
	__must_hold(&req->ctx->completion_lock)
{
	struct io_ring_ctx *ctx = req->ctx;
	unsigned flags = IORING_CQE_F_MORE;
	int error;

	if (READ_ONCE(req->poll.canceled)) {
		error = -ECANCELED;
		req->poll.events |= EPOLLONESHOT;
	} else {
		error = mangle_poll(mask);
	}
	if (req->poll.events & EPOLLONESHOT)
		flags = 0;
	if (!io_cqring_fill_event(ctx, req->user_data, error, flags)) {
		io_poll_remove_waitqs(req);
		req->poll.done = true;
		flags = 0;
	}
	if (flags & IORING_CQE_F_MORE)
		ctx->cq_extra++;

	io_commit_cqring(ctx);
	return !(flags & IORING_CQE_F_MORE);
}

static void io_poll_task_func(struct callback_head *cb)
{
	struct io_kiocb *req = container_of(cb, struct io_kiocb, task_work);
	struct io_ring_ctx *ctx = req->ctx;
	struct io_kiocb *nxt;

	if (io_poll_rewait(req, &req->poll)) {
		spin_unlock_irq(&ctx->completion_lock);
	} else {
		bool done;

		done = io_poll_complete(req, req->result);
		if (done) {
			hash_del(&req->hash_node);
		} else {
			req->result = 0;
			add_wait_queue(req->poll.head, &req->poll.wait);
		}
		spin_unlock_irq(&ctx->completion_lock);
		io_cqring_ev_posted(ctx);

		if (done) {
			nxt = io_put_req_find_next(req);
			if (nxt)
				__io_req_task_submit(nxt);
		}
	}
}

static int io_poll_double_wake(struct wait_queue_entry *wait, unsigned mode,
			       int sync, void *key)
{
	struct io_kiocb *req = wait->private;
	struct io_poll_iocb *poll = io_poll_get_single(req);
	__poll_t mask = key_to_poll(key);

	/* for instances that support it check for an event match first: */
	if (mask && !(mask & poll->events))
		return 0;
	if (!(poll->events & EPOLLONESHOT))
		return poll->wait.func(&poll->wait, mode, sync, key);

	list_del_init(&wait->entry);

	if (poll && poll->head) {
		bool done;

		spin_lock(&poll->head->lock);
		done = list_empty(&poll->wait.entry);
		if (!done)
			list_del_init(&poll->wait.entry);
		/* make sure double remove sees this as being gone */
		wait->private = NULL;
		spin_unlock(&poll->head->lock);
		if (!done) {
			/* use wait func handler, so it matches the rq type */
			poll->wait.func(&poll->wait, mode, sync, key);
		}
	}
	req_ref_put(req);
	return 1;
}

static void io_init_poll_iocb(struct io_poll_iocb *poll, __poll_t events,
			      wait_queue_func_t wake_func)
{
	poll->head = NULL;
	poll->done = false;
	poll->canceled = false;
#define IO_POLL_UNMASK	(EPOLLERR|EPOLLHUP|EPOLLNVAL|EPOLLRDHUP)
	/* mask in events that we always want/need */
	poll->events = events | IO_POLL_UNMASK;
	INIT_LIST_HEAD(&poll->wait.entry);
	init_waitqueue_func_entry(&poll->wait, wake_func);
}

static void __io_queue_proc(struct io_poll_iocb *poll, struct io_poll_table *pt,
			    struct wait_queue_head *head,
			    struct io_poll_iocb **poll_ptr)
{
	struct io_kiocb *req = pt->req;

	/*
	 * If poll->head is already set, it's because the file being polled
	 * uses multiple waitqueues for poll handling (eg one for read, one
	 * for write). Setup a separate io_poll_iocb if this happens.
	 */
	if (unlikely(poll->head)) {
		struct io_poll_iocb *poll_one = poll;

		/* already have a 2nd entry, fail a third attempt */
		if (*poll_ptr) {
			pt->error = -EINVAL;
			return;
		}
		/*
		 * Can't handle multishot for double wait for now, turn it
		 * into one-shot mode.
		 */
		if (!(poll_one->events & EPOLLONESHOT))
			poll_one->events |= EPOLLONESHOT;
		/* double add on the same waitqueue head, ignore */
		if (poll_one->head == head)
			return;
		poll = kmalloc(sizeof(*poll), GFP_ATOMIC);
		if (!poll) {
			pt->error = -ENOMEM;
			return;
		}
		io_init_poll_iocb(poll, poll_one->events, io_poll_double_wake);
		req_ref_get(req);
		poll->wait.private = req;
		*poll_ptr = poll;
	}

	pt->error = 0;
	poll->head = head;

	if (poll->events & EPOLLEXCLUSIVE)
		add_wait_queue_exclusive(head, &poll->wait);
	else
		add_wait_queue(head, &poll->wait);
}

static void io_async_queue_proc(struct file *file, struct wait_queue_head *head,
			       struct poll_table_struct *p)
{
	struct io_poll_table *pt = container_of(p, struct io_poll_table, pt);
	struct async_poll *apoll = pt->req->apoll;

	__io_queue_proc(&apoll->poll, pt, head, &apoll->double_poll);
}

static void io_async_task_func(struct callback_head *cb)
{
	struct io_kiocb *req = container_of(cb, struct io_kiocb, task_work);
	struct async_poll *apoll = req->apoll;
	struct io_ring_ctx *ctx = req->ctx;

	trace_io_uring_task_run(req->ctx, req->opcode, req->user_data);

	if (io_poll_rewait(req, &apoll->poll)) {
		spin_unlock_irq(&ctx->completion_lock);
		return;
	}

	hash_del(&req->hash_node);
	io_poll_remove_double(req);
	spin_unlock_irq(&ctx->completion_lock);

	if (!READ_ONCE(apoll->poll.canceled))
		__io_req_task_submit(req);
	else
		io_req_complete_failed(req, -ECANCELED);
}

static int io_async_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
			void *key)
{
	struct io_kiocb *req = wait->private;
	struct io_poll_iocb *poll = &req->apoll->poll;

	trace_io_uring_poll_wake(req->ctx, req->opcode, req->user_data,
					key_to_poll(key));

	return __io_async_wake(req, poll, key_to_poll(key), io_async_task_func);
}

static void io_poll_req_insert(struct io_kiocb *req)
{
	struct io_ring_ctx *ctx = req->ctx;
	struct hlist_head *list;

	list = &ctx->cancel_hash[hash_long(req->user_data, ctx->cancel_hash_bits)];
	hlist_add_head(&req->hash_node, list);
}

static __poll_t __io_arm_poll_handler(struct io_kiocb *req,
				      struct io_poll_iocb *poll,
				      struct io_poll_table *ipt, __poll_t mask,
				      wait_queue_func_t wake_func)
	__acquires(&ctx->completion_lock)
{
	struct io_ring_ctx *ctx = req->ctx;
	bool cancel = false;

	INIT_HLIST_NODE(&req->hash_node);
	io_init_poll_iocb(poll, mask, wake_func);
	poll->file = req->file;
	poll->wait.private = req;

	ipt->pt._key = mask;
	ipt->req = req;
	ipt->error = -EINVAL;

	mask = vfs_poll(req->file, &ipt->pt) & poll->events;

	spin_lock_irq(&ctx->completion_lock);
	if (likely(poll->head)) {
		spin_lock(&poll->head->lock);
		if (unlikely(list_empty(&poll->wait.entry))) {
			if (ipt->error)
				cancel = true;
			ipt->error = 0;
			mask = 0;
		}
		if ((mask && (poll->events & EPOLLONESHOT)) || ipt->error)
			list_del_init(&poll->wait.entry);
		else if (cancel)
			WRITE_ONCE(poll->canceled, true);
		else if (!poll->done) /* actually waiting for an event */
			io_poll_req_insert(req);
		spin_unlock(&poll->head->lock);
	}

	return mask;
}

static bool io_arm_poll_handler(struct io_kiocb *req)
{
	const struct io_op_def *def = &io_op_defs[req->opcode];
	struct io_ring_ctx *ctx = req->ctx;
	struct async_poll *apoll;
	struct io_poll_table ipt;
	__poll_t mask, ret;
	int rw;

	if (!req->file || !file_can_poll(req->file))
		return false;
	if (req->flags & REQ_F_POLLED)
		return false;
	if (def->pollin)
		rw = READ;
	else if (def->pollout)
		rw = WRITE;
	else
		return false;
	/* if we can't nonblock try, then no point in arming a poll handler */
	if (!io_file_supports_async(req, rw))
		return false;

	apoll = kmalloc(sizeof(*apoll), GFP_ATOMIC);
	if (unlikely(!apoll))
		return false;
	apoll->double_poll = NULL;

	req->flags |= REQ_F_POLLED;
	req->apoll = apoll;

	mask = EPOLLONESHOT;
	if (def->pollin)
		mask |= POLLIN | POLLRDNORM;
	if (def->pollout)
		mask |= POLLOUT | POLLWRNORM;

	/* If reading from MSG_ERRQUEUE using recvmsg, ignore POLLIN */
	if ((req->opcode == IORING_OP_RECVMSG) &&
	    (req->sr_msg.msg_flags & MSG_ERRQUEUE))
		mask &= ~POLLIN;

	mask |= POLLERR | POLLPRI;

	ipt.pt._qproc = io_async_queue_proc;

	ret = __io_arm_poll_handler(req, &apoll->poll, &ipt, mask,
					io_async_wake);
	if (ret || ipt.error) {
		io_poll_remove_double(req);
		spin_unlock_irq(&ctx->completion_lock);
		return false;
	}
	spin_unlock_irq(&ctx->completion_lock);
	trace_io_uring_poll_arm(ctx, req->opcode, req->user_data, mask,
					apoll->poll.events);
	return true;
}

static bool __io_poll_remove_one(struct io_kiocb *req,
				 struct io_poll_iocb *poll, bool do_cancel)
	__must_hold(&req->ctx->completion_lock)
{
	bool do_complete = false;

	if (!poll->head)
		return false;
	spin_lock(&poll->head->lock);
	if (do_cancel)
		WRITE_ONCE(poll->canceled, true);
	if (!list_empty(&poll->wait.entry)) {
		list_del_init(&poll->wait.entry);
		do_complete = true;
	}
	spin_unlock(&poll->head->lock);
	hash_del(&req->hash_node);
	return do_complete;
}

static bool io_poll_remove_waitqs(struct io_kiocb *req)
	__must_hold(&req->ctx->completion_lock)
{
	bool do_complete;

	io_poll_remove_double(req);
	do_complete = __io_poll_remove_one(req, io_poll_get_single(req), true);

	if (req->opcode != IORING_OP_POLL_ADD && do_complete) {
		/* non-poll requests have submit ref still */
		req_ref_put(req);
	}
	return do_complete;
}

static bool io_poll_remove_one(struct io_kiocb *req)
	__must_hold(&req->ctx->completion_lock)
{
	bool do_complete;

	do_complete = io_poll_remove_waitqs(req);
	if (do_complete) {
		io_cqring_fill_event(req->ctx, req->user_data, -ECANCELED, 0);
		io_commit_cqring(req->ctx);
		req_set_fail_links(req);
		io_put_req_deferred(req, 1);
	}

	return do_complete;
}

/*
 * Returns true if we found and killed one or more poll requests
 */
static bool io_poll_remove_all(struct io_ring_ctx *ctx, struct task_struct *tsk,
			       struct files_struct *files)
{
	struct hlist_node *tmp;
	struct io_kiocb *req;
	int posted = 0, i;

	spin_lock_irq(&ctx->completion_lock);
	for (i = 0; i < (1U << ctx->cancel_hash_bits); i++) {
		struct hlist_head *list;

		list = &ctx->cancel_hash[i];
		hlist_for_each_entry_safe(req, tmp, list, hash_node) {
			if (io_match_task(req, tsk, files))
				posted += io_poll_remove_one(req);
		}
	}
	spin_unlock_irq(&ctx->completion_lock);

	if (posted)
		io_cqring_ev_posted(ctx);

	return posted != 0;
}

static struct io_kiocb *io_poll_find(struct io_ring_ctx *ctx, __u64 sqe_addr,
				     bool poll_only)
	__must_hold(&ctx->completion_lock)
{
	struct hlist_head *list;
	struct io_kiocb *req;

	list = &ctx->cancel_hash[hash_long(sqe_addr, ctx->cancel_hash_bits)];
	hlist_for_each_entry(req, list, hash_node) {
		if (sqe_addr != req->user_data)
			continue;
		if (poll_only && req->opcode != IORING_OP_POLL_ADD)
			continue;
		return req;
	}
	return NULL;
}

static int io_poll_cancel(struct io_ring_ctx *ctx, __u64 sqe_addr,
			  bool poll_only)
	__must_hold(&ctx->completion_lock)
{
	struct io_kiocb *req;

	req = io_poll_find(ctx, sqe_addr, poll_only);
	if (!req)
		return -ENOENT;
	if (io_poll_remove_one(req))
		return 0;

	return -EALREADY;
}

static __poll_t io_poll_parse_events(const struct io_uring_sqe *sqe,
				     unsigned int flags)
{
	u32 events;

	events = READ_ONCE(sqe->poll32_events);
#ifdef __BIG_ENDIAN
	events = swahw32(events);
#endif
	if (!(flags & IORING_POLL_ADD_MULTI))
		events |= EPOLLONESHOT;
	return demangle_poll(events) | (events & (EPOLLEXCLUSIVE|EPOLLONESHOT));
}

static int io_poll_update_prep(struct io_kiocb *req,
			       const struct io_uring_sqe *sqe)
{
	struct io_poll_update *upd = &req->poll_update;
	u32 flags;

	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
		return -EINVAL;
	if (sqe->ioprio || sqe->buf_index)
		return -EINVAL;
	flags = READ_ONCE(sqe->len);
	if (flags & ~(IORING_POLL_UPDATE_EVENTS | IORING_POLL_UPDATE_USER_DATA |
		      IORING_POLL_ADD_MULTI))
		return -EINVAL;
	/* meaningless without update */
	if (flags == IORING_POLL_ADD_MULTI)
		return -EINVAL;

	upd->old_user_data = READ_ONCE(sqe->addr);
	upd->update_events = flags & IORING_POLL_UPDATE_EVENTS;
	upd->update_user_data = flags & IORING_POLL_UPDATE_USER_DATA;

	upd->new_user_data = READ_ONCE(sqe->off);
	if (!upd->update_user_data && upd->new_user_data)
		return -EINVAL;
	if (upd->update_events)
		upd->events = io_poll_parse_events(sqe, flags);
	else if (sqe->poll32_events)
		return -EINVAL;

	return 0;
}

static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
			void *key)
{
	struct io_kiocb *req = wait->private;
	struct io_poll_iocb *poll = &req->poll;

	return __io_async_wake(req, poll, key_to_poll(key), io_poll_task_func);
}

static void io_poll_queue_proc(struct file *file, struct wait_queue_head *head,
			       struct poll_table_struct *p)
{
	struct io_poll_table *pt = container_of(p, struct io_poll_table, pt);

	__io_queue_proc(&pt->req->poll, pt, head, (struct io_poll_iocb **) &pt->req->async_data);
}

static int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	struct io_poll_iocb *poll = &req->poll;
	u32 flags;

	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
		return -EINVAL;
	if (sqe->ioprio || sqe->buf_index || sqe->off || sqe->addr)
		return -EINVAL;
	flags = READ_ONCE(sqe->len);
	if (flags & ~IORING_POLL_ADD_MULTI)
		return -EINVAL;

	poll->events = io_poll_parse_events(sqe, flags);
	return 0;
}

static int io_poll_add(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_poll_iocb *poll = &req->poll;
	struct io_ring_ctx *ctx = req->ctx;
	struct io_poll_table ipt;
	__poll_t mask;

	ipt.pt._qproc = io_poll_queue_proc;

	mask = __io_arm_poll_handler(req, &req->poll, &ipt, poll->events,
					io_poll_wake);

	if (mask) { /* no async, we'd stolen it */
		ipt.error = 0;
		io_poll_complete(req, mask);
	}
	spin_unlock_irq(&ctx->completion_lock);

	if (mask) {
		io_cqring_ev_posted(ctx);
		if (poll->events & EPOLLONESHOT)
			io_put_req(req);
	}
	return ipt.error;
}

static int io_poll_update(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_ring_ctx *ctx = req->ctx;
	struct io_kiocb *preq;
	bool completing;
	int ret;

	spin_lock_irq(&ctx->completion_lock);
	preq = io_poll_find(ctx, req->poll_update.old_user_data, true);
	if (!preq) {
		ret = -ENOENT;
		goto err;
	}

	if (!req->poll_update.update_events && !req->poll_update.update_user_data) {
		completing = true;
		ret = io_poll_remove_one(preq) ? 0 : -EALREADY;
		goto err;
	}

	/*
	 * Don't allow racy completion with singleshot, as we cannot safely
	 * update those. For multishot, if we're racing with completion, just
	 * let completion re-add it.
	 */
	completing = !__io_poll_remove_one(preq, &preq->poll, false);
	if (completing && (preq->poll.events & EPOLLONESHOT)) {
		ret = -EALREADY;
		goto err;
	}
	/* we now have a detached poll request. reissue. */
	ret = 0;
err:
	if (ret < 0) {
		spin_unlock_irq(&ctx->completion_lock);
		req_set_fail_links(req);
		io_req_complete(req, ret);
		return 0;
	}
	/* only mask one event flags, keep behavior flags */
	if (req->poll_update.update_events) {
		preq->poll.events &= ~0xffff;
		preq->poll.events |= req->poll_update.events & 0xffff;
		preq->poll.events |= IO_POLL_UNMASK;
	}
	if (req->poll_update.update_user_data)
		preq->user_data = req->poll_update.new_user_data;
	spin_unlock_irq(&ctx->completion_lock);

	/* complete update request, we're done with it */
	io_req_complete(req, ret);

	if (!completing) {
		ret = io_poll_add(preq, issue_flags);
		if (ret < 0) {
			req_set_fail_links(preq);
			io_req_complete(preq, ret);
		}
	}
	return 0;
}

static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer)
{
	struct io_timeout_data *data = container_of(timer,
						struct io_timeout_data, timer);
	struct io_kiocb *req = data->req;
	struct io_ring_ctx *ctx = req->ctx;
	unsigned long flags;

	spin_lock_irqsave(&ctx->completion_lock, flags);
	list_del_init(&req->timeout.list);
	atomic_set(&req->ctx->cq_timeouts,
		atomic_read(&req->ctx->cq_timeouts) + 1);

	io_cqring_fill_event(ctx, req->user_data, -ETIME, 0);
	io_commit_cqring(ctx);
	spin_unlock_irqrestore(&ctx->completion_lock, flags);

	io_cqring_ev_posted(ctx);
	req_set_fail_links(req);
	io_put_req(req);
	return HRTIMER_NORESTART;
}

static struct io_kiocb *io_timeout_extract(struct io_ring_ctx *ctx,
					   __u64 user_data)
	__must_hold(&ctx->completion_lock)
{
	struct io_timeout_data *io;
	struct io_kiocb *req;
	bool found = false;

	list_for_each_entry(req, &ctx->timeout_list, timeout.list) {
		found = user_data == req->user_data;
		if (found)
			break;
	}
	if (!found)
		return ERR_PTR(-ENOENT);

	io = req->async_data;
	if (hrtimer_try_to_cancel(&io->timer) == -1)
		return ERR_PTR(-EALREADY);
	list_del_init(&req->timeout.list);
	return req;
}

static int io_timeout_cancel(struct io_ring_ctx *ctx, __u64 user_data)
	__must_hold(&ctx->completion_lock)
{
	struct io_kiocb *req = io_timeout_extract(ctx, user_data);

	if (IS_ERR(req))
		return PTR_ERR(req);

	req_set_fail_links(req);
	io_cqring_fill_event(ctx, req->user_data, -ECANCELED, 0);
	io_put_req_deferred(req, 1);
	return 0;
}

static int io_timeout_update(struct io_ring_ctx *ctx, __u64 user_data,
			     struct timespec64 *ts, enum hrtimer_mode mode)
	__must_hold(&ctx->completion_lock)
{
	struct io_kiocb *req = io_timeout_extract(ctx, user_data);
	struct io_timeout_data *data;

	if (IS_ERR(req))
		return PTR_ERR(req);

	req->timeout.off = 0; /* noseq */
	data = req->async_data;
	list_add_tail(&req->timeout.list, &ctx->timeout_list);
	hrtimer_init(&data->timer, CLOCK_MONOTONIC, mode);
	data->timer.function = io_timeout_fn;
	hrtimer_start(&data->timer, timespec64_to_ktime(*ts), mode);
	return 0;
}

static int io_timeout_remove_prep(struct io_kiocb *req,
				  const struct io_uring_sqe *sqe)
{
	struct io_timeout_rem *tr = &req->timeout_rem;

	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
		return -EINVAL;
	if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT)))
		return -EINVAL;
	if (sqe->ioprio || sqe->buf_index || sqe->len)
		return -EINVAL;

	tr->addr = READ_ONCE(sqe->addr);
	tr->flags = READ_ONCE(sqe->timeout_flags);
	if (tr->flags & IORING_TIMEOUT_UPDATE) {
		if (tr->flags & ~(IORING_TIMEOUT_UPDATE|IORING_TIMEOUT_ABS))
			return -EINVAL;
		if (get_timespec64(&tr->ts, u64_to_user_ptr(sqe->addr2)))
			return -EFAULT;
	} else if (tr->flags) {
		/* timeout removal doesn't support flags */
		return -EINVAL;
	}

	return 0;
}

static inline enum hrtimer_mode io_translate_timeout_mode(unsigned int flags)
{
	return (flags & IORING_TIMEOUT_ABS) ? HRTIMER_MODE_ABS
					    : HRTIMER_MODE_REL;
}

/*
 * Remove or update an existing timeout command
 */
static int io_timeout_remove(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_timeout_rem *tr = &req->timeout_rem;
	struct io_ring_ctx *ctx = req->ctx;
	int ret;

	spin_lock_irq(&ctx->completion_lock);
	if (!(req->timeout_rem.flags & IORING_TIMEOUT_UPDATE))
		ret = io_timeout_cancel(ctx, tr->addr);
	else
		ret = io_timeout_update(ctx, tr->addr, &tr->ts,
					io_translate_timeout_mode(tr->flags));

	io_cqring_fill_event(ctx, req->user_data, ret, 0);
	io_commit_cqring(ctx);
	spin_unlock_irq(&ctx->completion_lock);
	io_cqring_ev_posted(ctx);
	if (ret < 0)
		req_set_fail_links(req);
	io_put_req(req);
	return 0;
}

static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe,
			   bool is_timeout_link)
{
	struct io_timeout_data *data;
	unsigned flags;
	u32 off = READ_ONCE(sqe->off);

	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
		return -EINVAL;
	if (sqe->ioprio || sqe->buf_index || sqe->len != 1)
		return -EINVAL;
	if (off && is_timeout_link)
		return -EINVAL;
	flags = READ_ONCE(sqe->timeout_flags);
	if (flags & ~IORING_TIMEOUT_ABS)
		return -EINVAL;

	req->timeout.off = off;

	if (!req->async_data && io_alloc_async_data(req))
		return -ENOMEM;

	data = req->async_data;
	data->req = req;

	if (get_timespec64(&data->ts, u64_to_user_ptr(sqe->addr)))
		return -EFAULT;

	data->mode = io_translate_timeout_mode(flags);
	hrtimer_init(&data->timer, CLOCK_MONOTONIC, data->mode);
	if (is_timeout_link)
		io_req_track_inflight(req);
	return 0;
}

static int io_timeout(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_ring_ctx *ctx = req->ctx;
	struct io_timeout_data *data = req->async_data;
	struct list_head *entry;
	u32 tail, off = req->timeout.off;

	spin_lock_irq(&ctx->completion_lock);

	/*
	 * sqe->off holds how many events that need to occur for this
	 * timeout event to be satisfied. If it isn't set, then this is
	 * a pure timeout request, sequence isn't used.
	 */
	if (io_is_timeout_noseq(req)) {
		entry = ctx->timeout_list.prev;
		goto add;
	}

	tail = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts);
	req->timeout.target_seq = tail + off;

	/* Update the last seq here in case io_flush_timeouts() hasn't.
	 * This is safe because ->completion_lock is held, and submissions
	 * and completions are never mixed in the same ->completion_lock section.
	 */
	ctx->cq_last_tm_flush = tail;

	/*
	 * Insertion sort, ensuring the first entry in the list is always
	 * the one we need first.
	 */
	list_for_each_prev(entry, &ctx->timeout_list) {
		struct io_kiocb *nxt = list_entry(entry, struct io_kiocb,
						  timeout.list);

		if (io_is_timeout_noseq(nxt))
			continue;
		/* nxt.seq is behind @tail, otherwise would've been completed */
		if (off >= nxt->timeout.target_seq - tail)
			break;
	}
add:
	list_add(&req->timeout.list, entry);
	data->timer.function = io_timeout_fn;
	hrtimer_start(&data->timer, timespec64_to_ktime(data->ts), data->mode);
	spin_unlock_irq(&ctx->completion_lock);
	return 0;
}

struct io_cancel_data {
	struct io_ring_ctx *ctx;
	u64 user_data;
};

static bool io_cancel_cb(struct io_wq_work *work, void *data)
{
	struct io_kiocb *req = container_of(work, struct io_kiocb, work);
	struct io_cancel_data *cd = data;

	return req->ctx == cd->ctx && req->user_data == cd->user_data;
}

static int io_async_cancel_one(struct io_uring_task *tctx, u64 user_data,
			       struct io_ring_ctx *ctx)
{
	struct io_cancel_data data = { .ctx = ctx, .user_data = user_data, };
	enum io_wq_cancel cancel_ret;
	int ret = 0;

	if (!tctx || !tctx->io_wq)
		return -ENOENT;

	cancel_ret = io_wq_cancel_cb(tctx->io_wq, io_cancel_cb, &data, false);
	switch (cancel_ret) {
	case IO_WQ_CANCEL_OK:
		ret = 0;
		break;
	case IO_WQ_CANCEL_RUNNING:
		ret = -EALREADY;
		break;
	case IO_WQ_CANCEL_NOTFOUND:
		ret = -ENOENT;
		break;
	}

	return ret;
}

static void io_async_find_and_cancel(struct io_ring_ctx *ctx,
				     struct io_kiocb *req, __u64 sqe_addr,
				     int success_ret)
{
	unsigned long flags;
	int ret;

	ret = io_async_cancel_one(req->task->io_uring, sqe_addr, ctx);
	spin_lock_irqsave(&ctx->completion_lock, flags);
	if (ret != -ENOENT)
		goto done;
	ret = io_timeout_cancel(ctx, sqe_addr);
	if (ret != -ENOENT)
		goto done;
	ret = io_poll_cancel(ctx, sqe_addr, false);
done:
	if (!ret)
		ret = success_ret;
	io_cqring_fill_event(ctx, req->user_data, ret, 0);
	io_commit_cqring(ctx);
	spin_unlock_irqrestore(&ctx->completion_lock, flags);
	io_cqring_ev_posted(ctx);

	if (ret < 0)
		req_set_fail_links(req);
}

static int io_async_cancel_prep(struct io_kiocb *req,
				const struct io_uring_sqe *sqe)
{
	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
		return -EINVAL;
	if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT)))
		return -EINVAL;
	if (sqe->ioprio || sqe->off || sqe->len || sqe->cancel_flags)
		return -EINVAL;

	req->cancel.addr = READ_ONCE(sqe->addr);
	return 0;
}

static int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_ring_ctx *ctx = req->ctx;
	u64 sqe_addr = req->cancel.addr;
	struct io_tctx_node *node;
	int ret;

	/* tasks should wait for their io-wq threads, so safe w/o sync */
	ret = io_async_cancel_one(req->task->io_uring, sqe_addr, ctx);
	spin_lock_irq(&ctx->completion_lock);
	if (ret != -ENOENT)
		goto done;
	ret = io_timeout_cancel(ctx, sqe_addr);
	if (ret != -ENOENT)
		goto done;
	ret = io_poll_cancel(ctx, sqe_addr, false);
	if (ret != -ENOENT)
		goto done;
	spin_unlock_irq(&ctx->completion_lock);

	/* slow path, try all io-wq's */
	io_ring_submit_lock(ctx, !(issue_flags & IO_URING_F_NONBLOCK));
	ret = -ENOENT;
	list_for_each_entry(node, &ctx->tctx_list, ctx_node) {
		struct io_uring_task *tctx = node->task->io_uring;

		ret = io_async_cancel_one(tctx, req->cancel.addr, ctx);
		if (ret != -ENOENT)
			break;
	}
	io_ring_submit_unlock(ctx, !(issue_flags & IO_URING_F_NONBLOCK));

	spin_lock_irq(&ctx->completion_lock);
done:
	io_cqring_fill_event(ctx, req->user_data, ret, 0);
	io_commit_cqring(ctx);
	spin_unlock_irq(&ctx->completion_lock);
	io_cqring_ev_posted(ctx);

	if (ret < 0)
		req_set_fail_links(req);
	io_put_req(req);
	return 0;
}

static int io_rsrc_update_prep(struct io_kiocb *req,
				const struct io_uring_sqe *sqe)
{
	if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT)))
		return -EINVAL;
	if (sqe->ioprio || sqe->rw_flags)
		return -EINVAL;

	req->rsrc_update.offset = READ_ONCE(sqe->off);
	req->rsrc_update.nr_args = READ_ONCE(sqe->len);
	if (!req->rsrc_update.nr_args)
		return -EINVAL;
	req->rsrc_update.arg = READ_ONCE(sqe->addr);
	return 0;
}

static int io_files_update(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_ring_ctx *ctx = req->ctx;
	struct io_uring_rsrc_update2 up;
	int ret;

	if (issue_flags & IO_URING_F_NONBLOCK)
		return -EAGAIN;

	up.offset = req->rsrc_update.offset;
	up.data = req->rsrc_update.arg;
	up.nr = 0;
	up.tags = 0;
	up.resv = 0;

	mutex_lock(&ctx->uring_lock);
	ret = __io_register_rsrc_update(ctx, IORING_RSRC_FILE,
					&up, req->rsrc_update.nr_args);
	mutex_unlock(&ctx->uring_lock);

	if (ret < 0)
		req_set_fail_links(req);
	__io_req_complete(req, issue_flags, ret, 0);
	return 0;
}

static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	switch (req->opcode) {
	case IORING_OP_NOP:
		return 0;
	case IORING_OP_READV:
	case IORING_OP_READ_FIXED:
	case IORING_OP_READ:
		return io_read_prep(req, sqe);
	case IORING_OP_WRITEV:
	case IORING_OP_WRITE_FIXED:
	case IORING_OP_WRITE:
		return io_write_prep(req, sqe);
	case IORING_OP_POLL_ADD:
		return io_poll_add_prep(req, sqe);
	case IORING_OP_POLL_REMOVE:
		return io_poll_update_prep(req, sqe);
	case IORING_OP_FSYNC:
		return io_fsync_prep(req, sqe);
	case IORING_OP_SYNC_FILE_RANGE:
		return io_sfr_prep(req, sqe);
	case IORING_OP_SENDMSG:
	case IORING_OP_SEND:
		return io_sendmsg_prep(req, sqe);
	case IORING_OP_RECVMSG:
	case IORING_OP_RECV:
		return io_recvmsg_prep(req, sqe);
	case IORING_OP_CONNECT:
		return io_connect_prep(req, sqe);
	case IORING_OP_TIMEOUT:
		return io_timeout_prep(req, sqe, false);
	case IORING_OP_TIMEOUT_REMOVE:
		return io_timeout_remove_prep(req, sqe);
	case IORING_OP_ASYNC_CANCEL:
		return io_async_cancel_prep(req, sqe);
	case IORING_OP_LINK_TIMEOUT:
		return io_timeout_prep(req, sqe, true);
	case IORING_OP_ACCEPT:
		return io_accept_prep(req, sqe);
	case IORING_OP_FALLOCATE:
		return io_fallocate_prep(req, sqe);
	case IORING_OP_OPENAT:
		return io_openat_prep(req, sqe);
	case IORING_OP_CLOSE:
		return io_close_prep(req, sqe);
	case IORING_OP_FILES_UPDATE:
		return io_rsrc_update_prep(req, sqe);
	case IORING_OP_STATX:
		return io_statx_prep(req, sqe);
	case IORING_OP_FADVISE:
		return io_fadvise_prep(req, sqe);
	case IORING_OP_MADVISE:
		return io_madvise_prep(req, sqe);
	case IORING_OP_OPENAT2:
		return io_openat2_prep(req, sqe);
	case IORING_OP_EPOLL_CTL:
		return io_epoll_ctl_prep(req, sqe);
	case IORING_OP_SPLICE:
		return io_splice_prep(req, sqe);
	case IORING_OP_PROVIDE_BUFFERS:
		return io_provide_buffers_prep(req, sqe);
	case IORING_OP_REMOVE_BUFFERS:
		return io_remove_buffers_prep(req, sqe);
	case IORING_OP_TEE:
		return io_tee_prep(req, sqe);
	case IORING_OP_SHUTDOWN:
		return io_shutdown_prep(req, sqe);
	case IORING_OP_RENAMEAT:
		return io_renameat_prep(req, sqe);
	case IORING_OP_UNLINKAT:
		return io_unlinkat_prep(req, sqe);
	}

	printk_once(KERN_WARNING "io_uring: unhandled opcode %d\n",
			req->opcode);
	return -EINVAL;
}

static int io_req_prep_async(struct io_kiocb *req)
{
	if (!io_op_defs[req->opcode].needs_async_setup)
		return 0;
	if (WARN_ON_ONCE(req->async_data))
		return -EFAULT;
	if (io_alloc_async_data(req))
		return -EAGAIN;

	switch (req->opcode) {
	case IORING_OP_READV:
		return io_rw_prep_async(req, READ);
	case IORING_OP_WRITEV:
		return io_rw_prep_async(req, WRITE);
	case IORING_OP_SENDMSG:
		return io_sendmsg_prep_async(req);
	case IORING_OP_RECVMSG:
		return io_recvmsg_prep_async(req);
	case IORING_OP_CONNECT:
		return io_connect_prep_async(req);
	}
	printk_once(KERN_WARNING "io_uring: prep_async() bad opcode %d\n",
		    req->opcode);
	return -EFAULT;
}

static u32 io_get_sequence(struct io_kiocb *req)
{
	struct io_kiocb *pos;
	struct io_ring_ctx *ctx = req->ctx;
	u32 total_submitted, nr_reqs = 0;

	io_for_each_link(pos, req)
		nr_reqs++;

	total_submitted = ctx->cached_sq_head - ctx->cached_sq_dropped;
	return total_submitted - nr_reqs;
}

static int io_req_defer(struct io_kiocb *req)
{
	struct io_ring_ctx *ctx = req->ctx;
	struct io_defer_entry *de;
	int ret;
	u32 seq;

	/* Still need defer if there is pending req in defer list. */
	if (likely(list_empty_careful(&ctx->defer_list) &&
		!(req->flags & REQ_F_IO_DRAIN)))
		return 0;

	seq = io_get_sequence(req);
	/* Still a chance to pass the sequence check */
	if (!req_need_defer(req, seq) && list_empty_careful(&ctx->defer_list))
		return 0;

	ret = io_req_prep_async(req);
	if (ret)
		return ret;
	io_prep_async_link(req);
	de = kmalloc(sizeof(*de), GFP_KERNEL);
	if (!de)
		return -ENOMEM;

	spin_lock_irq(&ctx->completion_lock);
	if (!req_need_defer(req, seq) && list_empty(&ctx->defer_list)) {
		spin_unlock_irq(&ctx->completion_lock);
		kfree(de);
		io_queue_async_work(req);
		return -EIOCBQUEUED;
	}

	trace_io_uring_defer(ctx, req, req->user_data);
	de->req = req;
	de->seq = seq;
	list_add_tail(&de->list, &ctx->defer_list);
	spin_unlock_irq(&ctx->completion_lock);
	return -EIOCBQUEUED;
}

static void io_clean_op(struct io_kiocb *req)
{
	if (req->flags & REQ_F_BUFFER_SELECTED) {
		switch (req->opcode) {
		case IORING_OP_READV:
		case IORING_OP_READ_FIXED:
		case IORING_OP_READ:
			kfree((void *)(unsigned long)req->rw.addr);
			break;
		case IORING_OP_RECVMSG:
		case IORING_OP_RECV:
			kfree(req->sr_msg.kbuf);
			break;
		}
		req->flags &= ~REQ_F_BUFFER_SELECTED;
	}

	if (req->flags & REQ_F_NEED_CLEANUP) {
		switch (req->opcode) {
		case IORING_OP_READV:
		case IORING_OP_READ_FIXED:
		case IORING_OP_READ:
		case IORING_OP_WRITEV:
		case IORING_OP_WRITE_FIXED:
		case IORING_OP_WRITE: {
			struct io_async_rw *io = req->async_data;
			if (io->free_iovec)
				kfree(io->free_iovec);
			break;
			}
		case IORING_OP_RECVMSG:
		case IORING_OP_SENDMSG: {
			struct io_async_msghdr *io = req->async_data;

			kfree(io->free_iov);
			break;
			}
		case IORING_OP_SPLICE:
		case IORING_OP_TEE:
			if (!(req->splice.flags & SPLICE_F_FD_IN_FIXED))
				io_put_file(req->splice.file_in);
			break;
		case IORING_OP_OPENAT:
		case IORING_OP_OPENAT2:
			if (req->open.filename)
				putname(req->open.filename);
			break;
		case IORING_OP_RENAMEAT:
			putname(req->rename.oldpath);
			putname(req->rename.newpath);
			break;
		case IORING_OP_UNLINKAT:
			putname(req->unlink.filename);
			break;
		}
		req->flags &= ~REQ_F_NEED_CLEANUP;
	}
	if ((req->flags & REQ_F_POLLED) && req->apoll) {
		kfree(req->apoll->double_poll);
		kfree(req->apoll);
		req->apoll = NULL;
	}
	if (req->flags & REQ_F_INFLIGHT) {
		struct io_uring_task *tctx = req->task->io_uring;

		atomic_dec(&tctx->inflight_tracked);
		req->flags &= ~REQ_F_INFLIGHT;
	}
}

static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_ring_ctx *ctx = req->ctx;
	const struct cred *creds = NULL;
	int ret;

	if (req->work.creds && req->work.creds != current_cred())
		creds = override_creds(req->work.creds);

	switch (req->opcode) {
	case IORING_OP_NOP:
		ret = io_nop(req, issue_flags);
		break;
	case IORING_OP_READV:
	case IORING_OP_READ_FIXED:
	case IORING_OP_READ:
		ret = io_read(req, issue_flags);
		break;
	case IORING_OP_WRITEV:
	case IORING_OP_WRITE_FIXED:
	case IORING_OP_WRITE:
		ret = io_write(req, issue_flags);
		break;
	case IORING_OP_FSYNC:
		ret = io_fsync(req, issue_flags);
		break;
	case IORING_OP_POLL_ADD:
		ret = io_poll_add(req, issue_flags);
		break;
	case IORING_OP_POLL_REMOVE:
		ret = io_poll_update(req, issue_flags);
		break;
	case IORING_OP_SYNC_FILE_RANGE:
		ret = io_sync_file_range(req, issue_flags);
		break;
	case IORING_OP_SENDMSG:
		ret = io_sendmsg(req, issue_flags);
		break;
	case IORING_OP_SEND:
		ret = io_send(req, issue_flags);
		break;
	case IORING_OP_RECVMSG:
		ret = io_recvmsg(req, issue_flags);
		break;
	case IORING_OP_RECV:
		ret = io_recv(req, issue_flags);
		break;
	case IORING_OP_TIMEOUT:
		ret = io_timeout(req, issue_flags);
		break;
	case IORING_OP_TIMEOUT_REMOVE:
		ret = io_timeout_remove(req, issue_flags);
		break;
	case IORING_OP_ACCEPT:
		ret = io_accept(req, issue_flags);
		break;
	case IORING_OP_CONNECT:
		ret = io_connect(req, issue_flags);
		break;
	case IORING_OP_ASYNC_CANCEL:
		ret = io_async_cancel(req, issue_flags);
		break;
	case IORING_OP_FALLOCATE:
		ret = io_fallocate(req, issue_flags);
		break;
	case IORING_OP_OPENAT:
		ret = io_openat(req, issue_flags);
		break;
	case IORING_OP_CLOSE:
		ret = io_close(req, issue_flags);
		break;
	case IORING_OP_FILES_UPDATE:
		ret = io_files_update(req, issue_flags);
		break;
	case IORING_OP_STATX:
		ret = io_statx(req, issue_flags);
		break;
	case IORING_OP_FADVISE:
		ret = io_fadvise(req, issue_flags);
		break;
	case IORING_OP_MADVISE:
		ret = io_madvise(req, issue_flags);
		break;
	case IORING_OP_OPENAT2:
		ret = io_openat2(req, issue_flags);
		break;
	case IORING_OP_EPOLL_CTL:
		ret = io_epoll_ctl(req, issue_flags);
		break;