fs/io_uring.c

// 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/kthread.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/fs_struct.h>
#include <linux/splice.h>
#include <linux/task_work.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)

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;
};

struct io_mapped_ubuf {
	u64		ubuf;
	size_t		len;
	struct		bio_vec *bvec;
	unsigned int	nr_bvecs;
};

struct fixed_file_table {
	struct file		**files;
};

struct fixed_file_ref_node {
	struct percpu_ref		refs;
	struct list_head		node;
	struct list_head		file_list;
	struct fixed_file_data		*file_data;
	struct llist_node		llist;
};

struct fixed_file_data {
	struct fixed_file_table		*table;
	struct io_ring_ctx		*ctx;

	struct percpu_ref		*cur_refs;
	struct percpu_ref		refs;
	struct completion		done;
	struct list_head		ref_list;
	spinlock_t			lock;
};

struct io_buffer {
	struct list_head list;
	__u64 addr;
	__s32 len;
	__u16 bid;
};

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

	struct {
		unsigned int		flags;
		unsigned int		compat: 1;
		unsigned int		account_mem: 1;
		unsigned int		cq_overflow_flushed: 1;
		unsigned int		drain_next: 1;
		unsigned int		eventfd_async: 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;
		atomic_t		cached_cq_overflow;
		unsigned long		sq_check_overflow;

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

		wait_queue_head_t	inflight_wait;
		struct io_uring_sqe	*sq_sqes;
	} ____cacheline_aligned_in_smp;

	struct io_rings	*rings;

	/* IO offload */
	struct io_wq		*io_wq;
	struct task_struct	*sqo_thread;	/* if using sq thread polling */
	struct mm_struct	*sqo_mm;
	wait_queue_head_t	sqo_wait;

	/*
	 * 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 fixed_file_data	*file_data;
	unsigned		nr_user_files;
	int 			ring_fd;
	struct file 		*ring_file;

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

	struct user_struct	*user;

	const struct cred	*creds;

	struct completion	ref_comp;
	struct completion	sq_thread_comp;

	/* if all else fails... */
	struct io_kiocb		*fallback_req;

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

	struct idr		io_buffer_idr;

	struct idr		personality_idr;

	struct {
		unsigned		cached_cq_tail;
		unsigned		cq_entries;
		unsigned		cq_mask;
		atomic_t		cq_timeouts;
		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 {
		struct mutex		uring_lock;
		wait_queue_head_t	wait;
	} ____cacheline_aligned_in_smp;

	struct {
		spinlock_t		completion_lock;

		/*
		 * ->poll_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	poll_list;
		struct hlist_head	*cancel_hash;
		unsigned		cancel_hash_bits;
		bool			poll_multi_file;

		spinlock_t		inflight_lock;
		struct list_head	inflight_list;
	} ____cacheline_aligned_in_smp;

	struct delayed_work		file_put_work;
	struct llist_head		file_put_llist;

	struct work_struct		exit_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;
	union {
		struct wait_queue_head	*head;
		u64			addr;
	};
	__poll_t			events;
	bool				done;
	bool				canceled;
	struct wait_queue_entry		wait;
};

struct io_close {
	struct file			*file;
	struct file			*put_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;
	u64				addr;
	int				flags;
	u32				off;
	u32				target_seq;
};

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 user_msghdr __user *msg;
		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_files_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;
	__s32				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_async_connect {
	struct sockaddr_storage		address;
};

struct io_async_msghdr {
	struct iovec			fast_iov[UIO_FASTIOV];
	struct iovec			*iov;
	struct sockaddr __user		*uaddr;
	struct msghdr			msg;
	struct sockaddr_storage		addr;
};

struct io_async_rw {
	struct iovec			fast_iov[UIO_FASTIOV];
	struct iovec			*iov;
	ssize_t				nr_segs;
	ssize_t				size;
};

struct io_async_ctx {
	union {
		struct io_async_rw	rw;
		struct io_async_msghdr	msg;
		struct io_async_connect	connect;
		struct io_timeout_data	timeout;
	};
};

enum {
	REQ_F_FIXED_FILE_BIT	= IOSQE_FIXED_FILE_BIT,
	REQ_F_IO_DRAIN_BIT	= IOSQE_IO_DRAIN_BIT,
	REQ_F_LINK_BIT		= IOSQE_IO_LINK_BIT,
	REQ_F_HARDLINK_BIT	= IOSQE_IO_HARDLINK_BIT,
	REQ_F_FORCE_ASYNC_BIT	= IOSQE_ASYNC_BIT,
	REQ_F_BUFFER_SELECT_BIT	= IOSQE_BUFFER_SELECT_BIT,

	REQ_F_LINK_HEAD_BIT,
	REQ_F_LINK_NEXT_BIT,
	REQ_F_FAIL_LINK_BIT,
	REQ_F_INFLIGHT_BIT,
	REQ_F_CUR_POS_BIT,
	REQ_F_NOWAIT_BIT,
	REQ_F_LINK_TIMEOUT_BIT,
	REQ_F_TIMEOUT_BIT,
	REQ_F_ISREG_BIT,
	REQ_F_MUST_PUNT_BIT,
	REQ_F_TIMEOUT_NOSEQ_BIT,
	REQ_F_COMP_LOCKED_BIT,
	REQ_F_NEED_CLEANUP_BIT,
	REQ_F_OVERFLOW_BIT,
	REQ_F_POLLED_BIT,
	REQ_F_BUFFER_SELECTED_BIT,
	REQ_F_NO_FILE_TABLE_BIT,
	REQ_F_QUEUE_TIMEOUT_BIT,
	REQ_F_WORK_INITIALIZED_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),

	/* head of a link */
	REQ_F_LINK_HEAD		= BIT(REQ_F_LINK_HEAD_BIT),
	/* already grabbed next link */
	REQ_F_LINK_NEXT		= BIT(REQ_F_LINK_NEXT_BIT),
	/* fail rest of links */
	REQ_F_FAIL_LINK		= BIT(REQ_F_FAIL_LINK_BIT),
	/* on inflight list */
	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 linked timeout */
	REQ_F_LINK_TIMEOUT	= BIT(REQ_F_LINK_TIMEOUT_BIT),
	/* timeout request */
	REQ_F_TIMEOUT		= BIT(REQ_F_TIMEOUT_BIT),
	/* regular file */
	REQ_F_ISREG		= BIT(REQ_F_ISREG_BIT),
	/* must be punted even for NONBLOCK */
	REQ_F_MUST_PUNT		= BIT(REQ_F_MUST_PUNT_BIT),
	/* no timeout sequence */
	REQ_F_TIMEOUT_NOSEQ	= BIT(REQ_F_TIMEOUT_NOSEQ_BIT),
	/* completion under lock */
	REQ_F_COMP_LOCKED	= BIT(REQ_F_COMP_LOCKED_BIT),
	/* needs cleanup */
	REQ_F_NEED_CLEANUP	= BIT(REQ_F_NEED_CLEANUP_BIT),
	/* in overflow list */
	REQ_F_OVERFLOW		= BIT(REQ_F_OVERFLOW_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),
	/* doesn't need file table for this request */
	REQ_F_NO_FILE_TABLE	= BIT(REQ_F_NO_FILE_TABLE_BIT),
	/* needs to queue linked timeout */
	REQ_F_QUEUE_TIMEOUT	= BIT(REQ_F_QUEUE_TIMEOUT_BIT),
	/* io_wq_work is initialized */
	REQ_F_WORK_INITIALIZED	= BIT(REQ_F_WORK_INITIALIZED_BIT),
};

struct async_poll {
	struct io_poll_iocb	poll;
	struct io_wq_work	work;
};

/*
 * 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_accept	accept;
		struct io_sync		sync;
		struct io_cancel	cancel;
		struct io_timeout	timeout;
		struct io_connect	connect;
		struct io_sr_msg	sr_msg;
		struct io_open		open;
		struct io_close		close;
		struct io_files_update	files_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_async_ctx		*io;
	int				cflags;
	u8				opcode;
	/* polled IO has completed */
	u8				iopoll_completed;

	u16				buf_index;

	struct io_ring_ctx	*ctx;
	struct list_head	list;
	unsigned int		flags;
	refcount_t		refs;
	struct task_struct	*task;
	unsigned long		fsize;
	u64			user_data;
	u32			result;
	u32			sequence;

	struct list_head	link_list;

	struct list_head	inflight_entry;

	struct percpu_ref	*fixed_file_refs;

	union {
		/*
		 * Only commands that never go async can use the below fields,
		 * obviously. Right now only IORING_OP_POLL_ADD uses them, and
		 * async armed poll handlers for regular commands. The latter
		 * restore the work, if needed.
		 */
		struct {
			struct callback_head	task_work;
			struct hlist_node	hash_node;
			struct async_poll	*apoll;
		};
		struct io_wq_work	work;
	};
};

#define IO_PLUG_THRESHOLD		2
#define IO_IOPOLL_BATCH			8

struct io_submit_state {
	struct blk_plug		plug;

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

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

struct io_op_def {
	/* needs req->io allocated for deferral/async */
	unsigned		async_ctx : 1;
	/* needs current->mm setup, does mm access */
	unsigned		needs_mm : 1;
	/* needs req->file assigned */
	unsigned		needs_file : 1;
	/* don't fail if file grab fails */
	unsigned		needs_file_no_error : 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;
	/* needs file table */
	unsigned		file_table : 1;
	/* needs ->fs */
	unsigned		needs_fs : 1;
	/* set if opcode supports polled "wait" */
	unsigned		pollin : 1;
	unsigned		pollout : 1;
	/* op supports buffer selection */
	unsigned		buffer_select : 1;
};

static const struct io_op_def io_op_defs[] = {
	[IORING_OP_NOP] = {},
	[IORING_OP_READV] = {
		.async_ctx		= 1,
		.needs_mm		= 1,
		.needs_file		= 1,
		.unbound_nonreg_file	= 1,
		.pollin			= 1,
		.buffer_select		= 1,
	},
	[IORING_OP_WRITEV] = {
		.async_ctx		= 1,
		.needs_mm		= 1,
		.needs_file		= 1,
		.hash_reg_file		= 1,
		.unbound_nonreg_file	= 1,
		.pollout		= 1,
	},
	[IORING_OP_FSYNC] = {
		.needs_file		= 1,
	},
	[IORING_OP_READ_FIXED] = {
		.needs_file		= 1,
		.unbound_nonreg_file	= 1,
		.pollin			= 1,
	},
	[IORING_OP_WRITE_FIXED] = {
		.needs_file		= 1,
		.hash_reg_file		= 1,
		.unbound_nonreg_file	= 1,
		.pollout		= 1,
	},
	[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] = {
		.async_ctx		= 1,
		.needs_mm		= 1,
		.needs_file		= 1,
		.unbound_nonreg_file	= 1,
		.needs_fs		= 1,
		.pollout		= 1,
	},
	[IORING_OP_RECVMSG] = {
		.async_ctx		= 1,
		.needs_mm		= 1,
		.needs_file		= 1,
		.unbound_nonreg_file	= 1,
		.needs_fs		= 1,
		.pollin			= 1,
		.buffer_select		= 1,
	},
	[IORING_OP_TIMEOUT] = {
		.async_ctx		= 1,
		.needs_mm		= 1,
	},
	[IORING_OP_TIMEOUT_REMOVE] = {},
	[IORING_OP_ACCEPT] = {
		.needs_mm		= 1,
		.needs_file		= 1,
		.unbound_nonreg_file	= 1,
		.file_table		= 1,
		.pollin			= 1,
	},
	[IORING_OP_ASYNC_CANCEL] = {},
	[IORING_OP_LINK_TIMEOUT] = {
		.async_ctx		= 1,
		.needs_mm		= 1,
	},
	[IORING_OP_CONNECT] = {
		.async_ctx		= 1,
		.needs_mm		= 1,
		.needs_file		= 1,
		.unbound_nonreg_file	= 1,
		.pollout		= 1,
	},
	[IORING_OP_FALLOCATE] = {
		.needs_file		= 1,
	},
	[IORING_OP_OPENAT] = {
		.file_table		= 1,
		.needs_fs		= 1,
	},
	[IORING_OP_CLOSE] = {
		.needs_file		= 1,
		.needs_file_no_error	= 1,
		.file_table		= 1,
	},
	[IORING_OP_FILES_UPDATE] = {
		.needs_mm		= 1,
		.file_table		= 1,
	},
	[IORING_OP_STATX] = {
		.needs_mm		= 1,
		.needs_fs		= 1,
		.file_table		= 1,
	},
	[IORING_OP_READ] = {
		.needs_mm		= 1,
		.needs_file		= 1,
		.unbound_nonreg_file	= 1,
		.pollin			= 1,
		.buffer_select		= 1,
	},
	[IORING_OP_WRITE] = {
		.needs_mm		= 1,
		.needs_file		= 1,
		.unbound_nonreg_file	= 1,
		.pollout		= 1,
	},
	[IORING_OP_FADVISE] = {
		.needs_file		= 1,
	},
	[IORING_OP_MADVISE] = {
		.needs_mm		= 1,
	},
	[IORING_OP_SEND] = {
		.needs_mm		= 1,
		.needs_file		= 1,
		.unbound_nonreg_file	= 1,
		.pollout		= 1,
	},
	[IORING_OP_RECV] = {
		.needs_mm		= 1,
		.needs_file		= 1,
		.unbound_nonreg_file	= 1,
		.pollin			= 1,
		.buffer_select		= 1,
	},
	[IORING_OP_OPENAT2] = {
		.file_table		= 1,
		.needs_fs		= 1,
	},
	[IORING_OP_EPOLL_CTL] = {
		.unbound_nonreg_file	= 1,
		.file_table		= 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,
	},
};

static void io_wq_submit_work(struct io_wq_work **workptr);
static void io_cqring_fill_event(struct io_kiocb *req, long res);
static void io_put_req(struct io_kiocb *req);
static void __io_double_put_req(struct io_kiocb *req);
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_sqe_files_update(struct io_ring_ctx *ctx,
				 struct io_uring_files_update *ip,
				 unsigned nr_args);
static int io_grab_files(struct io_kiocb *req);
static void io_cleanup_req(struct io_kiocb *req);
static int io_file_get(struct io_submit_state *state, struct io_kiocb *req,
		       int fd, struct file **out_file, bool fixed);
static void __io_queue_sqe(struct io_kiocb *req,
			   const struct io_uring_sqe *sqe);

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);

static void io_file_put_work(struct work_struct *work);

/*
 * Note: must call io_req_init_async() for the first time you
 * touch any members of io_wq_work.
 */
static inline void io_req_init_async(struct io_kiocb *req)
{
	if (req->flags & REQ_F_WORK_INITIALIZED)
		return;

	memset(&req->work, 0, sizeof(req->work));
	req->flags |= REQ_F_WORK_INITIALIZED;
}

static inline bool io_async_submit(struct io_ring_ctx *ctx)
{
	return ctx->flags & IORING_SETUP_SQPOLL;
}

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 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;

	ctx->fallback_req = kmem_cache_alloc(req_cachep, GFP_KERNEL);
	if (!ctx->fallback_req)
		goto err;

	/*
	 * 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);

	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_wait);
	init_waitqueue_head(&ctx->cq_wait);
	INIT_LIST_HEAD(&ctx->cq_overflow_list);
	init_completion(&ctx->ref_comp);
	init_completion(&ctx->sq_thread_comp);
	idr_init(&ctx->io_buffer_idr);
	idr_init(&ctx->personality_idr);
	mutex_init(&ctx->uring_lock);
	init_waitqueue_head(&ctx->wait);
	spin_lock_init(&ctx->completion_lock);
	INIT_LIST_HEAD(&ctx->poll_list);
	INIT_LIST_HEAD(&ctx->defer_list);
	INIT_LIST_HEAD(&ctx->timeout_list);
	init_waitqueue_head(&ctx->inflight_wait);
	spin_lock_init(&ctx->inflight_lock);
	INIT_LIST_HEAD(&ctx->inflight_list);
	INIT_DELAYED_WORK(&ctx->file_put_work, io_file_put_work);
	init_llist_head(&ctx->file_put_llist);
	return ctx;
err:
	if (ctx->fallback_req)
		kmem_cache_free(req_cachep, ctx->fallback_req);
	kfree(ctx->cancel_hash);
	kfree(ctx);
	return NULL;
}

static inline bool __req_need_defer(struct io_kiocb *req)
{
	struct io_ring_ctx *ctx = req->ctx;

	return req->sequence != ctx->cached_cq_tail
				+ atomic_read(&ctx->cached_cq_overflow);
}

static inline bool req_need_defer(struct io_kiocb *req)
{
	if (unlikely(req->flags & REQ_F_IO_DRAIN))
		return __req_need_defer(req);

	return false;
}

static void __io_commit_cqring(struct io_ring_ctx *ctx)
{
	struct io_rings *rings = ctx->rings;

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

	if (wq_has_sleeper(&ctx->cq_wait)) {
		wake_up_interruptible(&ctx->cq_wait);
		kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN);
	}
}

static inline void io_req_work_grab_env(struct io_kiocb *req,
					const struct io_op_def *def)
{
	if (!req->work.mm && def->needs_mm) {
		mmgrab(current->mm);
		req->work.mm = current->mm;
	}
	if (!req->work.creds)
		req->work.creds = get_current_cred();
	if (!req->work.fs && def->needs_fs) {
		spin_lock(&current->fs->lock);
		if (!current->fs->in_exec) {
			req->work.fs = current->fs;
			req->work.fs->users++;
		} else {
			req->work.flags |= IO_WQ_WORK_CANCEL;
		}
		spin_unlock(&current->fs->lock);
	}
	if (!req->work.task_pid)
		req->work.task_pid = task_pid_vnr(current);
}

static inline void io_req_work_drop_env(struct io_kiocb *req)
{
	if (!(req->flags & REQ_F_WORK_INITIALIZED))
		return;

	if (req->work.mm) {
		mmdrop(req->work.mm);
		req->work.mm = NULL;
	}
	if (req->work.creds) {
		put_cred(req->work.creds);
		req->work.creds = NULL;
	}
	if (req->work.fs) {
		struct fs_struct *fs = req->work.fs;

		spin_lock(&req->work.fs->lock);
		if (--fs->users)
			fs = NULL;
		spin_unlock(&req->work.fs->lock);
		if (fs)
			free_fs_struct(fs);
	}
}

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

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

	io_req_work_grab_env(req, def);

	*link = io_prep_linked_timeout(req);
}

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

	io_prep_async_work(req, &link);

	trace_io_uring_queue_async_work(ctx, io_wq_is_hashed(&req->work), req,
					&req->work, req->flags);
	io_wq_enqueue(ctx->io_wq, &req->work);

	if (link)
		io_queue_linked_timeout(link);
}

static void io_kill_timeout(struct io_kiocb *req)
{
	int ret;

	ret = hrtimer_try_to_cancel(&req->io->timeout.timer);
	if (ret != -1) {
		atomic_inc(&req->ctx->cq_timeouts);
		list_del_init(&req->list);
		req->flags |= REQ_F_COMP_LOCKED;
		io_cqring_fill_event(req, 0);
		io_put_req(req);
	}
}

static void io_kill_timeouts(struct io_ring_ctx *ctx)
{
	struct io_kiocb *req, *tmp;

	spin_lock_irq(&ctx->completion_lock);
	list_for_each_entry_safe(req, tmp, &ctx->timeout_list, list)
		io_kill_timeout(req);
	spin_unlock_irq(&ctx->completion_lock);
}

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

		if (req_need_defer(req))
			break;
		list_del_init(&req->list);
		io_queue_async_work(req);
	} while (!list_empty(&ctx->defer_list));
}

static void io_flush_timeouts(struct io_ring_ctx *ctx)
{
	while (!list_empty(&ctx->timeout_list)) {
		struct io_kiocb *req = list_first_entry(&ctx->timeout_list,
							struct io_kiocb, list);

		if (req->flags & REQ_F_TIMEOUT_NOSEQ)
			break;
		if (req->timeout.target_seq != ctx->cached_cq_tail
					- atomic_read(&ctx->cq_timeouts))
			break;

		list_del_init(&req->list);
		io_kill_timeout(req);
	}
}

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

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

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

	tail = ctx->cached_cq_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 (tail - READ_ONCE(rings->cq.head) == rings->cq_ring_entries)
		return NULL;

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

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

static void io_cqring_ev_posted(struct io_ring_ctx *ctx)
{
	if (waitqueue_active(&ctx->wait))
		wake_up(&ctx->wait);
	if (waitqueue_active(&ctx->sqo_wait))
		wake_up(&ctx->sqo_wait);
	if (io_should_trigger_evfd(ctx))
		eventfd_signal(ctx->cq_ev_fd, 1);
}

/* 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;
	struct io_uring_cqe *cqe;
	struct io_kiocb *req;
	unsigned long flags;
	LIST_HEAD(list);

	if (!force) {
		if (list_empty_careful(&ctx->cq_overflow_list))
			return true;
		if ((ctx->cached_cq_tail - READ_ONCE(rings->cq.head) ==
		    rings->cq_ring_entries))
			return false;
	}

	spin_lock_irqsave(&ctx->completion_lock, flags);

	/* if force is set, the ring is going away. always drop after that */
	if (force)
		ctx->cq_overflow_flushed = 1;

	cqe = NULL;
	while (!list_empty(&ctx->cq_overflow_list)) {
		cqe = io_get_cqring(ctx);
		if (!cqe && !force)
			break;

		req = list_first_entry(&ctx->cq_overflow_list, struct io_kiocb,
						list);
		list_move(&req->list, &list);
		req->flags &= ~REQ_F_OVERFLOW;
		if (cqe) {
			WRITE_ONCE(cqe->user_data, req->user_data);
			WRITE_ONCE(cqe->res, req->result);
			WRITE_ONCE(cqe->flags, req->cflags);
		} else {
			WRITE_ONCE(ctx->rings->cq_overflow,
				atomic_inc_return(&ctx->cached_cq_overflow));
		}
	}

	io_commit_cqring(ctx);
	if (cqe) {
		clear_bit(0, &ctx->sq_check_overflow);
		clear_bit(0, &ctx->cq_check_overflow);
	}
	spin_unlock_irqrestore(&ctx->completion_lock, flags);
	io_cqring_ev_posted(ctx);

	while (!list_empty(&list)) {
		req = list_first_entry(&list, struct io_kiocb, list);
		list_del(&req->list);
		io_put_req(req);
	}

	return cqe != NULL;
}

static void __io_cqring_fill_event(struct io_kiocb *req, long res, long cflags)
{
	struct io_ring_ctx *ctx = req->ctx;
	struct io_uring_cqe *cqe;

	trace_io_uring_complete(ctx, req->user_data, res);

	/*
	 * 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, req->user_data);
		WRITE_ONCE(cqe->res, res);
		WRITE_ONCE(cqe->flags, cflags);
	} else if (ctx->cq_overflow_flushed) {
		WRITE_ONCE(ctx->rings->cq_overflow,
				atomic_inc_return(&ctx->cached_cq_overflow));
	} else {
		if (list_empty(&ctx->cq_overflow_list)) {
			set_bit(0, &ctx->sq_check_overflow);
			set_bit(0, &ctx->cq_check_overflow);
		}
		req->flags |= REQ_F_OVERFLOW;
		refcount_inc(&req->refs);
		req->result = res;
		req->cflags = cflags;
		list_add_tail(&req->list, &ctx->cq_overflow_list);
	}
}

static void io_cqring_fill_event(struct io_kiocb *req, long res)
{
	__io_cqring_fill_event(req, res, 0);
}

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

	spin_lock_irqsave(&ctx->completion_lock, flags);
	__io_cqring_fill_event(req, res, cflags);
	io_commit_cqring(ctx);
	spin_unlock_irqrestore(&ctx->completion_lock, flags);

	io_cqring_ev_posted(ctx);
}

static void io_cqring_add_event(struct io_kiocb *req, long res)
{
	__io_cqring_add_event(req, res, 0);
}

static inline bool io_is_fallback_req(struct io_kiocb *req)
{
	return req == (struct io_kiocb *)
			((unsigned long) req->ctx->fallback_req & ~1UL);
}

static struct io_kiocb *io_get_fallback_req(struct io_ring_ctx *ctx)
{
	struct io_kiocb *req;

	req = ctx->fallback_req;
	if (!test_and_set_bit_lock(0, (unsigned long *) &ctx->fallback_req))
		return req;

	return NULL;
}

static struct io_kiocb *io_alloc_req(struct io_ring_ctx *ctx,
				     struct io_submit_state *state)
{
	gfp_t gfp = GFP_KERNEL | __GFP_NOWARN;
	struct io_kiocb *req;

	if (!state) {
		req = kmem_cache_alloc(req_cachep, gfp);
		if (unlikely(!req))
			goto fallback;
	} else if (!state->free_reqs) {
		size_t sz;
		int ret;

		sz = min_t(size_t, state->ios_left, ARRAY_SIZE(state->reqs));
		ret = kmem_cache_alloc_bulk(req_cachep, gfp, sz, 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])
				goto fallback;
			ret = 1;
		}
		state->free_reqs = ret - 1;
		req = state->reqs[ret - 1];
	} else {
		state->free_reqs--;
		req = state->reqs[state->free_reqs];
	}

	return req;
fallback:
	return io_get_fallback_req(ctx);
}

static inline void io_put_file(struct io_kiocb *req, struct file *file,
			  bool fixed)
{
	if (fixed)
		percpu_ref_put(req->fixed_file_refs);
	else
		fput(file);
}

static void __io_req_aux_free(struct io_kiocb *req)
{
	if (req->flags & REQ_F_NEED_CLEANUP)
		io_cleanup_req(req);

	kfree(req->io);
	if (req->file)
		io_put_file(req, req->file, (req->flags & REQ_F_FIXED_FILE));
	if (req->task)
		put_task_struct(req->task);

	io_req_work_drop_env(req);
}

static void __io_free_req(struct io_kiocb *req)
{
	__io_req_aux_free(req);

	if (req->flags & REQ_F_INFLIGHT) {
		struct io_ring_ctx *ctx = req->ctx;
		unsigned long flags;

		spin_lock_irqsave(&ctx->inflight_lock, flags);
		list_del(&req->inflight_entry);
		if (waitqueue_active(&ctx->inflight_wait))
			wake_up(&ctx->inflight_wait);
		spin_unlock_irqrestore(&ctx->inflight_lock, flags);
	}

	percpu_ref_put(&req->ctx->refs);
	if (likely(!io_is_fallback_req(req)))
		kmem_cache_free(req_cachep, req);
	else
		clear_bit_unlock(0, (unsigned long *) &req->ctx->fallback_req);
}

struct req_batch {
	void *reqs[IO_IOPOLL_BATCH];
	int to_free;
	int need_iter;
};

static void io_free_req_many(struct io_ring_ctx *ctx, struct req_batch *rb)
{
	if (!rb->to_free)
		return;
	if (rb->need_iter) {
		int i, inflight = 0;
		unsigned long flags;

		for (i = 0; i < rb->to_free; i++) {
			struct io_kiocb *req = rb->reqs[i];

			if (req->flags & REQ_F_INFLIGHT)
				inflight++;
			__io_req_aux_free(req);
		}
		if (!inflight)
			goto do_free;

		spin_lock_irqsave(&ctx->inflight_lock, flags);
		for (i = 0; i < rb->to_free; i++) {
			struct io_kiocb *req = rb->reqs[i];

			if (req->flags & REQ_F_INFLIGHT) {
				list_del(&req->inflight_entry);
				if (!--inflight)
					break;
			}
		}
		spin_unlock_irqrestore(&ctx->inflight_lock, flags);

		if (waitqueue_active(&ctx->inflight_wait))
			wake_up(&ctx->inflight_wait);
	}
do_free:
	kmem_cache_free_bulk(req_cachep, rb->to_free, rb->reqs);
	percpu_ref_put_many(&ctx->refs, rb->to_free);
	rb->to_free = rb->need_iter = 0;
}

static bool io_link_cancel_timeout(struct io_kiocb *req)
{
	struct io_ring_ctx *ctx = req->ctx;
	int ret;

	ret = hrtimer_try_to_cancel(&req->io->timeout.timer);
	if (ret != -1) {
		io_cqring_fill_event(req, -ECANCELED);
		io_commit_cqring(ctx);
		req->flags &= ~REQ_F_LINK_HEAD;
		io_put_req(req);
		return true;
	}

	return false;
}

static void io_req_link_next(struct io_kiocb *req, struct io_kiocb **nxtptr)
{
	struct io_ring_ctx *ctx = req->ctx;
	bool wake_ev = false;

	/* Already got next link */
	if (req->flags & REQ_F_LINK_NEXT)
		return;

	/*
	 * The list should never be empty when we are called here. But could
	 * potentially happen if the chain is messed up, check to be on the
	 * safe side.
	 */
	while (!list_empty(&req->link_list)) {
		struct io_kiocb *nxt = list_first_entry(&req->link_list,
						struct io_kiocb, link_list);

		if (unlikely((req->flags & REQ_F_LINK_TIMEOUT) &&
			     (nxt->flags & REQ_F_TIMEOUT))) {
			list_del_init(&nxt->link_list);
			wake_ev |= io_link_cancel_timeout(nxt);
			req->flags &= ~REQ_F_LINK_TIMEOUT;
			continue;
		}

		list_del_init(&req->link_list);
		if (!list_empty(&nxt->link_list))
			nxt->flags |= REQ_F_LINK_HEAD;
		*nxtptr = nxt;
		break;
	}

	req->flags |= REQ_F_LINK_NEXT;
	if (wake_ev)
		io_cqring_ev_posted(ctx);
}

/*
 * Called if REQ_F_LINK_HEAD is set, and we fail the head request
 */
static void io_fail_links(struct io_kiocb *req)
{
	struct io_ring_ctx *ctx = req->ctx;
	unsigned long flags;

	spin_lock_irqsave(&ctx->completion_lock, flags);

	while (!list_empty(&req->link_list)) {
		struct io_kiocb *link = list_first_entry(&req->link_list,
						struct io_kiocb, link_list);

		list_del_init(&link->link_list);
		trace_io_uring_fail_link(req, link);

		if ((req->flags & REQ_F_LINK_TIMEOUT) &&
		    link->opcode == IORING_OP_LINK_TIMEOUT) {
			io_link_cancel_timeout(link);
		} else {
			io_cqring_fill_event(link, -ECANCELED);
			__io_double_put_req(link);
		}
		req->flags &= ~REQ_F_LINK_TIMEOUT;
	}

	io_commit_cqring(ctx);
	spin_unlock_irqrestore(&ctx->completion_lock, flags);
	io_cqring_ev_posted(ctx);
}

static void io_req_find_next(struct io_kiocb *req, struct io_kiocb **nxt)
{
	if (likely(!(req->flags & REQ_F_LINK_HEAD)))
		return;

	/*
	 * 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_FAIL_LINK) {
		io_fail_links(req);
	} else if ((req->flags & (REQ_F_LINK_TIMEOUT | REQ_F_COMP_LOCKED)) ==
			REQ_F_LINK_TIMEOUT) {
		struct io_ring_ctx *ctx = req->ctx;
		unsigned long flags;

		/*
		 * If this is a timeout link, we could be racing with the
		 * timeout timer. Grab the completion lock for this case to
		 * protect against that.
		 */
		spin_lock_irqsave(&ctx->completion_lock, flags);
		io_req_link_next(req, nxt);
		spin_unlock_irqrestore(&ctx->completion_lock, flags);
	} else {
		io_req_link_next(req, nxt);
	}
}

static void io_free_req(struct io_kiocb *req)
{
	struct io_kiocb *nxt = NULL;

	io_req_find_next(req, &nxt);
	__io_free_req(req);

	if (nxt)
		io_queue_async_work(nxt);
}

static void io_wq_assign_next(struct io_wq_work **workptr, struct io_kiocb *nxt)
{
	struct io_kiocb *link;
	const struct io_op_def *def = &io_op_defs[nxt->opcode];

	if ((nxt->flags & REQ_F_ISREG) && def->hash_reg_file)
		io_wq_hash_work(&nxt->work, file_inode(nxt->file));

	*workptr = &nxt->work;
	link = io_prep_linked_timeout(nxt);
	if (link)
		nxt->flags |= REQ_F_QUEUE_TIMEOUT;
}

/*
 * Drop reference to request, return next in chain (if there is one) if this
 * was the last reference to this request.
 */
__attribute__((nonnull))
static void io_put_req_find_next(struct io_kiocb *req, struct io_kiocb **nxtptr)
{
	if (refcount_dec_and_test(&req->refs)) {
		io_req_find_next(req, nxtptr);
		__io_free_req(req);
	}
}

static void io_put_req(struct io_kiocb *req)
{
	if (refcount_dec_and_test(&req->refs))
		io_free_req(req);
}

static void io_steal_work(struct io_kiocb *req,
			  struct io_wq_work **workptr)
{
	/*
	 * It's in an io-wq worker, so there always should be at least
	 * one reference, which will be dropped in io_put_work() just
	 * after the current handler returns.
	 *
	 * It also means, that if the counter dropped to 1, then there is
	 * no asynchronous users left, so it's safe to steal the next work.
	 */
	if (refcount_read(&req->refs) == 1) {
		struct io_kiocb *nxt = NULL;

		io_req_find_next(req, &nxt);
		if (nxt)
			io_wq_assign_next(workptr, nxt);
	}
}

/*
 * Must only be used if we don't need to care about links, usually from
 * within the completion handling itself.
 */
static void __io_double_put_req(struct io_kiocb *req)
{
	/* drop both submit and complete references */
	if (refcount_sub_and_test(2, &req->refs))
		__io_free_req(req);
}

static void io_double_put_req(struct io_kiocb *req)
{
	/* drop both submit and complete references */
	if (refcount_sub_and_test(2, &req->refs))
		io_free_req(req);
}

static unsigned io_cqring_events(struct io_ring_ctx *ctx, bool noflush)
{
	struct io_rings *rings = ctx->rings;

	if (test_bit(0, &ctx->cq_check_overflow)) {
		/*
		 * noflush == true is from the waitqueue handler, just ensure
		 * we wake up the task, and the next invocation will flush the
		 * entries. We cannot safely to it from here.
		 */
		if (noflush && !list_empty(&ctx->cq_overflow_list))
			return -1U;

		io_cqring_overflow_flush(ctx, false);
	}

	/* See comment at the top of this file */
	smp_rmb();
	return ctx->cached_cq_tail - READ_ONCE(rings->cq.head);
}

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 inline bool io_req_multi_free(struct req_batch *rb, struct io_kiocb *req)
{
	if ((req->flags & REQ_F_LINK_HEAD) || io_is_fallback_req(req))
		return false;

	if (req->file || req->io)
		rb->need_iter++;

	rb->reqs[rb->to_free++] = req;
	if (unlikely(rb->to_free == ARRAY_SIZE(rb->reqs)))
		io_free_req_many(req->ctx, rb);
	return true;
}

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

	kbuf = (struct io_buffer *) (unsigned long) req->rw.addr;
	cflags = kbuf->bid << IORING_CQE_BUFFER_SHIFT;
	cflags |= IORING_CQE_F_BUFFER;
	req->rw.addr = 0;
	kfree(kbuf);
	return cflags;
}

/*
 * 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;

	rb.to_free = rb.need_iter = 0;
	while (!list_empty(done)) {
		int cflags = 0;

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

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

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

		if (refcount_dec_and_test(&req->refs) &&
		    !io_req_multi_free(&rb, req))
			io_free_req(req);
	}

	io_commit_cqring(ctx);
	if (ctx->flags & IORING_SETUP_SQPOLL)
		io_cqring_ev_posted(ctx);
	io_free_req_many(ctx, &rb);
}

static void io_iopoll_queue(struct list_head *again)
{
	struct io_kiocb *req;

	do {
		req = list_first_entry(again, struct io_kiocb, list);
		list_del(&req->list);
		refcount_inc(&req->refs);
		io_queue_async_work(req);
	} while (!list_empty(again));
}

static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events,
			long min)
{
	struct io_kiocb *req, *tmp;
	LIST_HEAD(done);
	LIST_HEAD(again);
	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->poll_list, list) {
		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->list, &done);
			continue;
		}
		if (!list_empty(&done))
			break;

		if (req->result == -EAGAIN) {
			list_move_tail(&req->list, &again);
			continue;
		}
		if (!list_empty(&again))
			break;

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

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

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

	if (!list_empty(&again))
		io_iopoll_queue(&again);

	return ret;
}

/*
 * Poll for a minimum of 'min' events. Note that if min == 0 we consider that a
 * non-spinning poll check - we'll still enter the driver poll loop, but only
 * as a non-spinning completion check.
 */
static int io_iopoll_getevents(struct io_ring_ctx *ctx, unsigned int *nr_events,
				long min)
{
	while (!list_empty(&ctx->poll_list) && !need_resched()) {
		int ret;

		ret = io_do_iopoll(ctx, nr_events, min);
		if (ret < 0)
			return ret;
		if (!min || *nr_events >= min)
			return 0;
	}

	return 1;
}

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

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

		io_iopoll_getevents(ctx, &nr_events, 1);

		/*
		 * Ensure we allow local-to-the-cpu processing to take place,
		 * in this case we need to ensure that we reap all events.
		 */
		cond_resched();
	}
	mutex_unlock(&ctx->uring_lock);
}

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

		/*
		 * 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 (io_cqring_events(ctx, false))
			break;

		/*
		 * 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 (!(++iters & 7)) {
			mutex_unlock(&ctx->uring_lock);
			mutex_lock(&ctx->uring_lock);
		}

		if (*nr_events < min)
			tmin = min - *nr_events;

		ret = io_iopoll_getevents(ctx, nr_events, tmin);
		if (ret <= 0)
			break;
		ret = 0;
	} while (min && !*nr_events && !need_resched());

	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 inode *inode = file_inode(req->file);

		__sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE);
	}
	file_end_write(req->file);
}

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

static void io_complete_rw_common(struct kiocb *kiocb, long res)
{
	struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb);
	int cflags = 0;

	if (kiocb->ki_flags & IOCB_WRITE)
		kiocb_end_write(req);

	if (res != req->result)
		req_set_fail_links(req);
	if (req->flags & REQ_F_BUFFER_SELECTED)
		cflags = io_put_kbuf(req);
	__io_cqring_add_event(req, 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_common(kiocb, res);
	io_put_req(req);
}

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 (res != req->result)
		req_set_fail_links(req);
	req->result = res;
	if (res != -EAGAIN)
		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_iopoll_getevents() thread before the issuer is done
 * accessing the kiocb cookie.
 */
static void io_iopoll_req_issued(struct io_kiocb *req)
{
	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->poll_list)) {
		ctx->poll_multi_file = false;
	} else if (!ctx->poll_multi_file) {
		struct io_kiocb *list_req;

		list_req = list_first_entry(&ctx->poll_list, struct io_kiocb,
						list);
		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->list, &ctx->poll_list);
	else
		list_add_tail(&req->list, &ctx->poll_list);

	if ((ctx->flags & IORING_SETUP_SQPOLL) &&
	    wq_has_sleeper(&ctx->sqo_wait))
		wake_up(&ctx->sqo_wait);
}

static void __io_state_file_put(struct io_submit_state *state)
{
	int diff = state->has_refs - state->used_refs;

	if (diff)
		fput_many(state->file, diff);
	state->file = NULL;
}

static inline void io_state_file_put(struct io_submit_state *state)
{
	if (state->file)
		__io_state_file_put(state);
}

/*
 * 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) {
		if (state->fd == fd) {
			state->used_refs++;
			state->ios_left--;
			return state->file;
		}
		__io_state_file_put(state);
	}
	state->file = fget_many(fd, state->ios_left);
	if (!state->file)
		return NULL;

	state->fd = fd;
	state->has_refs = state->ios_left;
	state->used_refs = 1;
	state->ios_left--;
	return state->file;
}

/*
 * 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) || S_ISCHR(mode) || S_ISSOCK(mode))
		return true;
	if (S_ISREG(mode) && file->f_op != &io_uring_fops)
		return true;

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

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

	kiocb->ki_pos = READ_ONCE(sqe->off);
	if (kiocb->ki_pos == -1 && !(req->file->f_mode & FMODE_STREAM)) {
		req->flags |= REQ_F_CUR_POS;
		kiocb->ki_pos = req->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;

	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();

	/* don't allow async punt if RWF_NOWAIT was requested */
	if (kiocb->ki_flags & IOCB_NOWAIT)
		req->flags |= REQ_F_NOWAIT;

	if (force_nonblock)
		kiocb->ki_flags |= IOCB_NOWAIT;

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

	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;
		/* fall through */
	default:
		kiocb->ki_complete(kiocb, ret, 0);
	}
}

static void kiocb_done(struct kiocb *kiocb, ssize_t ret)
{
	struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb);

	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(kiocb, ret, 0);
	else
		io_rw_done(kiocb, ret);
}

static ssize_t io_import_fixed(struct io_kiocb *req, int rw,
			       struct iov_iter *iter)
{
	struct io_ring_ctx *ctx = req->ctx;
	size_t len = req->rw.len;
	struct io_mapped_ubuf *imu;
	u16 index, buf_index;
	size_t offset;
	u64 buf_addr;

	/* attempt to use fixed buffers without having provided iovecs */
	if (unlikely(!ctx->user_bufs))
		return -EFAULT;

	buf_index = req->buf_index;
	if (unlikely(buf_index >= ctx->nr_user_bufs))
		return -EFAULT;

	index = array_index_nospec(buf_index, ctx->nr_user_bufs);
	imu = &ctx->user_bufs[index];
	buf_addr = req->rw.addr;

	/* overflow */
	if (buf_addr + len < buf_addr)
		return -EFAULT;
	/* not inside the mapped region */
	if (buf_addr < imu->ubuf || buf_addr + len > imu->ubuf + imu->len)
		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 len;
}

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 = idr_find(&req->ctx->io_buffer_idr, 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;
			idr_remove(&req->ctx->io_buffer_idr, 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)
		return 0;
	else 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 ssize_t 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;
	ssize_t ret;
	u8 opcode;

	opcode = req->opcode;
	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)) {
				*iovec = NULL;
				return PTR_ERR(buf);
			}
			req->rw.len = sqe_len;
		}

		ret = import_single_range(rw, buf, sqe_len, *iovec, iter);
		*iovec = NULL;
		return ret < 0 ? ret : sqe_len;
	}

	if (req->io) {
		struct io_async_rw *iorw = &req->io->rw;

		*iovec = iorw->iov;
		iov_iter_init(iter, rw, *iovec, iorw->nr_segs, iorw->size);
		if (iorw->iov == iorw->fast_iov)
			*iovec = NULL;
		return iorw->size;
	}

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

#ifdef CONFIG_COMPAT
	if (req->ctx->compat)
		return compat_import_iovec(rw, buf, sqe_len, UIO_FASTIOV,
						iovec, iter);
#endif

	return import_iovec(rw, buf, sqe_len, UIO_FASTIOV, iovec, iter);
}

/*
 * 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 file *file, struct kiocb *kiocb,
			   struct iov_iter *iter)
{
	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 {
			/* fixed buffers import bvec */
			iovec.iov_base = kmap(iter->bvec->bv_page)
						+ iter->iov_offset;
			iovec.iov_len = min(iter->count,
					iter->bvec->bv_len - iter->iov_offset);
		}

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

		if (iov_iter_is_bvec(iter))
			kunmap(iter->bvec->bv_page);

		if (nr < 0) {
			if (!ret)
				ret = nr;
			break;
		}
		ret += nr;
		if (nr != iovec.iov_len)
			break;
		iov_iter_advance(iter, nr);
	}

	return ret;
}

static void io_req_map_rw(struct io_kiocb *req, ssize_t io_size,
			  struct iovec *iovec, struct iovec *fast_iov,
			  struct iov_iter *iter)
{
	req->io->rw.nr_segs = iter->nr_segs;
	req->io->rw.size = io_size;
	req->io->rw.iov = iovec;
	if (!req->io->rw.iov) {
		req->io->rw.iov = req->io->rw.fast_iov;
		if (req->io->rw.iov != fast_iov)
			memcpy(req->io->rw.iov, fast_iov,
			       sizeof(struct iovec) * iter->nr_segs);
	} else {
		req->flags |= REQ_F_NEED_CLEANUP;
	}
}

static inline int __io_alloc_async_ctx(struct io_kiocb *req)
{
	req->io = kmalloc(sizeof(*req->io), GFP_KERNEL);
	return req->io == NULL;
}

static int io_alloc_async_ctx(struct io_kiocb *req)
{
	if (!io_op_defs[req->opcode].async_ctx)
		return 0;

	return  __io_alloc_async_ctx(req);
}

static int io_setup_async_rw(struct io_kiocb *req, ssize_t io_size,
			     struct iovec *iovec, struct iovec *fast_iov,
			     struct iov_iter *iter)
{
	if (!io_op_defs[req->opcode].async_ctx)
		return 0;
	if (!req->io) {
		if (__io_alloc_async_ctx(req))
			return -ENOMEM;

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

static int io_read_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe,
			bool force_nonblock)
{
	struct io_async_ctx *io;
	struct iov_iter iter;
	ssize_t ret;

	ret = io_prep_rw(req, sqe, force_nonblock);
	if (ret)
		return ret;

	if (unlikely(!(req->file->f_mode & FMODE_READ)))
		return -EBADF;

	/* either don't need iovec imported or already have it */
	if (!req->io || req->flags & REQ_F_NEED_CLEANUP)
		return 0;

	io = req->io;
	io->rw.iov = io->rw.fast_iov;
	req->io = NULL;
	ret = io_import_iovec(READ, req, &io->rw.iov, &iter, !force_nonblock);
	req->io = io;
	if (ret < 0)
		return ret;

	io_req_map_rw(req, ret, io->rw.iov, io->rw.fast_iov, &iter);
	return 0;
}

static int io_read(struct io_kiocb *req, bool force_nonblock)
{
	struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
	struct kiocb *kiocb = &req->rw.kiocb;
	struct iov_iter iter;
	size_t iov_count;
	ssize_t io_size, ret;

	ret = io_import_iovec(READ, req, &iovec, &iter, !force_nonblock);
	if (ret < 0)
		return ret;

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

	req->result = 0;
	io_size = ret;
	if (req->flags & REQ_F_LINK_HEAD)
		req->result = io_size;

	/*
	 * If the file doesn't support async, mark it as REQ_F_MUST_PUNT so
	 * we know to async punt it even if it was opened O_NONBLOCK
	 */
	if (force_nonblock && !io_file_supports_async(req->file, READ))
		goto copy_iov;

	iov_count = iov_iter_count(&iter);
	ret = rw_verify_area(READ, req->file, &kiocb->ki_pos, iov_count);
	if (!ret) {
		ssize_t ret2;

		if (req->file->f_op->read_iter)
			ret2 = call_read_iter(req->file, kiocb, &iter);
		else
			ret2 = loop_rw_iter(READ, req->file, kiocb, &iter);

		/* Catch -EAGAIN return for forced non-blocking submission */
		if (!force_nonblock || ret2 != -EAGAIN) {
			kiocb_done(kiocb, ret2);
		} else {
copy_iov:
			ret = io_setup_async_rw(req, io_size, iovec,
						inline_vecs, &iter);
			if (ret)
				goto out_free;
			/* any defer here is final, must blocking retry */
			if (!(req->flags & REQ_F_NOWAIT) &&
			    !file_can_poll(req->file))
				req->flags |= REQ_F_MUST_PUNT;
			return -EAGAIN;
		}
	}
out_free:
	kfree(iovec);
	req->flags &= ~REQ_F_NEED_CLEANUP;
	return ret;
}

static int io_write_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe,
			 bool force_nonblock)
{
	struct io_async_ctx *io;
	struct iov_iter iter;
	ssize_t ret;

	ret = io_prep_rw(req, sqe, force_nonblock);
	if (ret)
		return ret;

	if (unlikely(!(req->file->f_mode & FMODE_WRITE)))
		return -EBADF;

	req->fsize = rlimit(RLIMIT_FSIZE);

	/* either don't need iovec imported or already have it */
	if (!req->io || req->flags & REQ_F_NEED_CLEANUP)
		return 0;

	io = req->io;
	io->rw.iov = io->rw.fast_iov;
	req->io = NULL;
	ret = io_import_iovec(WRITE, req, &io->rw.iov, &iter, !force_nonblock);
	req->io = io;
	if (ret < 0)
		return ret;

	io_req_map_rw(req, ret, io->rw.iov, io->rw.fast_iov, &iter);
	return 0;
}

static int io_write(struct io_kiocb *req, bool force_nonblock)
{
	struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
	struct kiocb *kiocb = &req->rw.kiocb;
	struct iov_iter iter;
	size_t iov_count;
	ssize_t ret, io_size;

	ret = io_import_iovec(WRITE, req, &iovec, &iter, !force_nonblock);
	if (ret < 0)
		return ret;

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

	req->result = 0;
	io_size = ret;
	if (req->flags & REQ_F_LINK_HEAD)
		req->result = io_size;

	/*
	 * If the file doesn't support async, mark it as REQ_F_MUST_PUNT so
	 * we know to async punt it even if it was opened O_NONBLOCK
	 */
	if (force_nonblock && !io_file_supports_async(req->file, 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;

	iov_count = iov_iter_count(&iter);
	ret = rw_verify_area(WRITE, req->file, &kiocb->ki_pos, iov_count);
	if (!ret) {
		ssize_t ret2;

		/*
		 * 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_FREEZE_WRITE, true);
			__sb_writers_release(file_inode(req->file)->i_sb,
						SB_FREEZE_WRITE);
		}
		kiocb->ki_flags |= IOCB_WRITE;

		if (!force_nonblock)
			current->signal->rlim[RLIMIT_FSIZE].rlim_cur = req->fsize;

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

		if (!force_nonblock)
			current->signal->rlim[RLIMIT_FSIZE].rlim_cur = RLIM_INFINITY;

		/*
		 * 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;
		if (!force_nonblock || ret2 != -EAGAIN) {
			kiocb_done(kiocb, ret2);
		} else {
copy_iov:
			ret = io_setup_async_rw(req, io_size, iovec,
						inline_vecs, &iter);
			if (ret)
				goto out_free;
			/* any defer here is final, must blocking retry */
			if (!(req->flags & REQ_F_NOWAIT) &&
			    !file_can_poll(req->file))
				req->flags |= REQ_F_MUST_PUNT;
			return -EAGAIN;
		}
	}
out_free:
	req->flags &= ~REQ_F_NEED_CLEANUP;
	kfree(iovec);
	return ret;
}

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;
	int ret;

	if (req->flags & REQ_F_NEED_CLEANUP)
		return 0;
	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;

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

	if (!S_ISREG(file_inode(sp->file_in)->i_mode)) {
		/*
		 * Splice operation will be punted aync, and here need to
		 * modify io_wq_work.flags, so initialize io_wq_work firstly.
		 */
		io_req_init_async(req);
		req->work.flags |= IO_WQ_WORK_UNBOUND;
	}

	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, bool force_nonblock)
{
	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 (force_nonblock)
		return -EAGAIN;
	if (sp->len)
		ret = do_tee(in, out, sp->len, flags);

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

	io_cqring_add_event(req, ret);
	if (ret != sp->len)
		req_set_fail_links(req);
	io_put_req(req);
	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, bool force_nonblock)
{
	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 (force_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);

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

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

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

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

	io_cqring_add_event(req, 0);
	io_put_req(req);
	return 0;
}

static int io_prep_fsync(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, bool force_nonblock)
{
	loff_t end = req->sync.off + req->sync.len;
	int ret;

	/* fsync always requires a blocking context */
	if (force_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_cqring_add_event(req, ret);
	io_put_req(req);
	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);
	req->fsize = rlimit(RLIMIT_FSIZE);
	return 0;
}

static int io_fallocate(struct io_kiocb *req, bool force_nonblock)
{
	int ret;

	/* fallocate always requiring blocking context */
	if (force_nonblock)
		return -EAGAIN;

	current->signal->rlim[RLIMIT_FSIZE].rlim_cur = req->fsize;
	ret = vfs_fallocate(req->file, req->sync.mode, req->sync.off,
				req->sync.len);
	current->signal->rlim[RLIMIT_FSIZE].rlim_cur = RLIM_INFINITY;
	if (ret < 0)
		req_set_fail_links(req);
	io_cqring_add_event(req, ret);
	io_put_req(req);
	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(req->ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_SQPOLL)))
		return -EINVAL;
	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 (req->flags & REQ_F_NEED_CLEANUP)
		return 0;
	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 (req->flags & REQ_F_NEED_CLEANUP)
		return 0;
	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, bool force_nonblock)
{
	struct open_flags op;
	struct file *file;
	int ret;

	if (force_nonblock)
		return -EAGAIN;

	ret = build_open_flags(&req->open.how, &op);
	if (ret)
		goto err;

	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);
	if (IS_ERR(file)) {
		put_unused_fd(ret);
		ret = PTR_ERR(file);
	} else {
		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_cqring_add_event(req, ret);
	io_put_req(req);
	return 0;
}

static int io_openat(struct io_kiocb *req, bool force_nonblock)
{
	return io_openat2(req, force_nonblock);
}

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);