// 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_cqe (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/blk-mq.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>
#include <linux/audit.h>
#include <linux/security.h>
#include <linux/xattr.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)
#define IORING_SQPOLL_CAP_ENTRIES_VALUE 8

/* only define max */
#define IORING_MAX_FIXED_FILES	(1U << 20)
#define IORING_MAX_RESTRICTIONS	(IORING_RESTRICTION_LAST + \
				 IORING_REGISTER_LAST + IORING_OP_LAST)

#define IO_RSRC_TAG_TABLE_SHIFT	(PAGE_SHIFT - 3)
#define IO_RSRC_TAG_TABLE_MAX	(1U << IO_RSRC_TAG_TABLE_SHIFT)
#define IO_RSRC_TAG_TABLE_MASK	(IO_RSRC_TAG_TABLE_MAX - 1)

#define IORING_MAX_REG_BUFFERS	(1U << 14)

#define SQE_COMMON_FLAGS (IOSQE_FIXED_FILE | IOSQE_IO_LINK | \
			  IOSQE_IO_HARDLINK | IOSQE_ASYNC)

#define SQE_VALID_FLAGS	(SQE_COMMON_FLAGS | IOSQE_BUFFER_SELECT | \
			IOSQE_IO_DRAIN | IOSQE_CQE_SKIP_SUCCESS)

#define IO_REQ_CLEAN_FLAGS (REQ_F_BUFFER_SELECTED | REQ_F_NEED_CLEANUP | \
				REQ_F_POLLED | REQ_F_INFLIGHT | REQ_F_CREDS | \
				REQ_F_ASYNC_DATA)

#define IO_REQ_CLEAN_SLOW_FLAGS (REQ_F_REFCOUNT | REQ_F_LINK | REQ_F_HARDLINK |\
				 IO_REQ_CLEAN_FLAGS)

#define IO_APOLL_MULTI_POLLED (REQ_F_APOLL_MULTISHOT | REQ_F_POLLED)

#define IO_TCTX_REFS_CACHE_NR	(1U << 10)

struct io_uring {
	u32 head ____cacheline_aligned_in_smp;
	u32 tail ____cacheline_aligned_in_smp;
};

/*
 * This data is shared with the application through the mmap at offsets
 * IORING_OFF_SQ_RING and IORING_OFF_CQ_RING.
 *
 * The offsets to the member fields are published through struct
 * io_sqring_offsets when calling io_uring_setup.
 */
struct io_rings {
	/*
	 * Head and tail offsets into the ring; the offsets need to be
	 * masked to get valid indices.
	 *
	 * The kernel controls head of the sq ring and the tail of the cq ring,
	 * and the application controls tail of the sq ring and the head of the
	 * cq ring.
	 */
	struct io_uring		sq, cq;
	/*
	 * Bitmasks to apply to head and tail offsets (constant, equals
	 * ring_entries - 1)
	 */
	u32			sq_ring_mask, cq_ring_mask;
	/* Ring sizes (constant, power of 2) */
	u32			sq_ring_entries, cq_ring_entries;
	/*
	 * Number of invalid entries dropped by the kernel due to
	 * invalid index stored in array
	 *
	 * Written by the kernel, shouldn't be modified by the
	 * application (i.e. get number of "new events" by comparing to
	 * cached value).
	 *
	 * After a new SQ head value was read by the application this
	 * counter includes all submissions that were dropped reaching
	 * the new SQ head (and possibly more).
	 */
	u32			sq_dropped;
	/*
	 * Runtime SQ flags
	 *
	 * Written by the kernel, shouldn't be modified by the
	 * application.
	 *
	 * The application needs a full memory barrier before checking
	 * for IORING_SQ_NEED_WAKEUP after updating the sq tail.
	 */
	atomic_t		sq_flags;
	/*
	 * Runtime CQ flags
	 *
	 * Written by the application, shouldn't be modified by the
	 * kernel.
	 */
	u32			cq_flags;
	/*
	 * Number of completion events lost because the queue was full;
	 * this should be avoided by the application by making sure
	 * there are not more requests pending than there is space in
	 * the completion queue.
	 *
	 * Written by the kernel, shouldn't be modified by the
	 * application (i.e. get number of "new events" by comparing to
	 * cached value).
	 *
	 * As completion events come in out of order this counter is not
	 * ordered with any other data.
	 */
	u32			cq_overflow;
	/*
	 * Ring buffer of completion events.
	 *
	 * The kernel writes completion events fresh every time they are
	 * produced, so the application is allowed to modify pending
	 * entries.
	 */
	struct io_uring_cqe	cqes[] ____cacheline_aligned_in_smp;
};

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

struct io_ring_ctx;

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

/*
 * FFS_SCM is only available on 64-bit archs, for 32-bit we just define it as 0
 * and define IO_URING_SCM_ALL. For this case, we use SCM for all files as we
 * can't safely always dereference the file when the task has exited and ring
 * cleanup is done. If a file is tracked and part of SCM, then unix gc on
 * process exit may reap it before __io_sqe_files_unregister() is run.
 */
#define FFS_NOWAIT		0x1UL
#define FFS_ISREG		0x2UL
#if defined(CONFIG_64BIT)
#define FFS_SCM			0x4UL
#else
#define IO_URING_SCM_ALL
#define FFS_SCM			0x0UL
#endif
#define FFS_MASK		~(FFS_NOWAIT|FFS_ISREG|FFS_SCM)

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 {
	struct io_fixed_file *files;
	unsigned long *bitmap;
	unsigned int alloc_hint;
};

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;
	unsigned int			nr;
	rsrc_put_fn			*do_put;
	atomic_t			refs;
	struct completion		done;
	bool				quiesce;
};

#define IO_BUFFER_LIST_BUF_PER_PAGE (PAGE_SIZE / sizeof(struct io_uring_buf))
struct io_buffer_list {
	/*
	 * If ->buf_nr_pages is set, then buf_pages/buf_ring are used. If not,
	 * then these are classic provided buffers and ->buf_list is used.
	 */
	union {
		struct list_head buf_list;
		struct {
			struct page **buf_pages;
			struct io_uring_buf_ring *buf_ring;
		};
	};
	__u16 bgid;

	/* below is for ring provided buffers */
	__u16 buf_nr_pages;
	__u16 nr_entries;
	__u16 head;
	__u16 mask;
};

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

struct io_restriction {
	DECLARE_BITMAP(register_op, IORING_REGISTER_LAST);
	DECLARE_BITMAP(sqe_op, IORING_OP_LAST);
	u8 sqe_flags_allowed;
	u8 sqe_flags_required;
	bool registered;
};

enum {
	IO_SQ_THREAD_SHOULD_STOP = 0,
	IO_SQ_THREAD_SHOULD_PARK,
};

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;
};

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

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

struct io_submit_state {
	/* inline/task_work completion list, under ->uring_lock */
	struct io_wq_work_node	free_list;
	/* batch completion logic */
	struct io_wq_work_list	compl_reqs;
	struct io_submit_link	link;

	bool			plug_started;
	bool			need_plug;
	bool			flush_cqes;
	unsigned short		submit_nr;
	struct blk_plug		plug;
};

struct io_ev_fd {
	struct eventfd_ctx	*cq_ev_fd;
	unsigned int		eventfd_async: 1;
	struct rcu_head		rcu;
};

#define BGID_ARRAY	64

struct io_ring_ctx {
	/* const or read-mostly hot data */
	struct {
		struct percpu_ref	refs;

		struct io_rings		*rings;
		unsigned int		flags;
		enum task_work_notify_mode	notify_method;
		unsigned int		compat: 1;
		unsigned int		drain_next: 1;
		unsigned int		restricted: 1;
		unsigned int		off_timeout_used: 1;
		unsigned int		drain_active: 1;
		unsigned int		drain_disabled: 1;
		unsigned int		has_evfd: 1;
		unsigned int		syscall_iopoll: 1;
	} ____cacheline_aligned_in_smp;

	/* submission data */
	struct {
		struct mutex		uring_lock;

		/*
		 * Ring buffer of indices into array of io_uring_sqe, which is
		 * mmapped by the application using the IORING_OFF_SQES offset.
		 *
		 * This indirection could e.g. be used to assign fixed
		 * io_uring_sqe entries to operations and only submit them to
		 * the queue when needed.
		 *
		 * The kernel modifies neither the indices array nor the entries
		 * array.
		 */
		u32			*sq_array;
		struct io_uring_sqe	*sq_sqes;
		unsigned		cached_sq_head;
		unsigned		sq_entries;
		struct list_head	defer_list;

		/*
		 * Fixed resources fast path, should be accessed only under
		 * uring_lock, and updated through io_uring_register(2)
		 */
		struct io_rsrc_node	*rsrc_node;
		int			rsrc_cached_refs;
		atomic_t		cancel_seq;
		struct io_file_table	file_table;
		unsigned		nr_user_files;
		unsigned		nr_user_bufs;
		struct io_mapped_ubuf	**user_bufs;

		struct io_submit_state	submit_state;

		struct io_buffer_list	*io_bl;
		struct xarray		io_bl_xa;
		struct list_head	io_buffers_cache;

		struct list_head	timeout_list;
		struct list_head	ltimeout_list;
		struct list_head	cq_overflow_list;
		struct list_head	apoll_cache;
		struct xarray		personalities;
		u32			pers_next;
		unsigned		sq_thread_idle;
	} ____cacheline_aligned_in_smp;

	/* IRQ completion list, under ->completion_lock */
	struct io_wq_work_list	locked_free_list;
	unsigned int		locked_free_nr;

	const struct cred	*sq_creds;	/* cred used for __io_sq_thread() */
	struct io_sq_data	*sq_data;	/* if using sq thread polling */

	struct wait_queue_head	sqo_sq_wait;
	struct list_head	sqd_list;

	unsigned long		check_cq;

	struct {
		/*
		 * We cache a range of free CQEs we can use, once exhausted it
		 * should go through a slower range setup, see __io_get_cqe()
		 */
		struct io_uring_cqe	*cqe_cached;
		struct io_uring_cqe	*cqe_sentinel;

		unsigned		cached_cq_tail;
		unsigned		cq_entries;
		struct io_ev_fd	__rcu	*io_ev_fd;
		struct wait_queue_head	cq_wait;
		unsigned		cq_extra;
		atomic_t		cq_timeouts;
		unsigned		cq_last_tm_flush;
	} ____cacheline_aligned_in_smp;

	struct {
		spinlock_t		completion_lock;

		spinlock_t		timeout_lock;

		/*
		 * ->iopoll_list is protected by the ctx->uring_lock for
		 * io_uring instances that don't use IORING_SETUP_SQPOLL.
		 * For SQPOLL, only the single threaded io_sq_thread() will
		 * manipulate the list, hence no extra locking is needed there.
		 */
		struct io_wq_work_list	iopoll_list;
		struct hlist_head	*cancel_hash;
		unsigned		cancel_hash_bits;
		bool			poll_multi_queue;

		struct list_head	io_buffers_comp;
	} ____cacheline_aligned_in_smp;

	struct io_restriction		restrictions;

	/* slow path rsrc auxilary data, used by update/register */
	struct {
		struct io_rsrc_node		*rsrc_backup_node;
		struct io_mapped_ubuf		*dummy_ubuf;
		struct io_rsrc_data		*file_data;
		struct io_rsrc_data		*buf_data;

		struct delayed_work		rsrc_put_work;
		struct llist_head		rsrc_put_llist;
		struct list_head		rsrc_ref_list;
		spinlock_t			rsrc_ref_lock;

		struct list_head	io_buffers_pages;
	};

	/* Keep this last, we don't need it for the fast path */
	struct {
		#if defined(CONFIG_UNIX)
			struct socket		*ring_sock;
		#endif
		/* hashed buffered write serialization */
		struct io_wq_hash		*hash_map;

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

		/* ctx exit and cancelation */
		struct llist_head		fallback_llist;
		struct delayed_work		fallback_work;
		struct work_struct		exit_work;
		struct list_head		tctx_list;
		struct completion		ref_comp;
		u32				iowq_limits[2];
		bool				iowq_limits_set;
	};
};

/*
 * Arbitrary limit, can be raised if need be
 */
#define IO_RINGFD_REG_MAX 16

struct io_uring_task {
	/* submission side */
	int			cached_refs;
	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;
	struct io_wq_work_list	prio_task_list;
	struct callback_head	task_work;
	struct file		**registered_rings;
	bool			task_running;
};

/*
 * 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;
	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;
	u32				file_slot;
};

struct io_timeout_data {
	struct io_kiocb			*req;
	struct hrtimer			timer;
	struct timespec64		ts;
	enum hrtimer_mode		mode;
	u32				flags;
};

struct io_accept {
	struct file			*file;
	struct sockaddr __user		*addr;
	int __user			*addr_len;
	int				flags;
	u32				file_slot;
	unsigned long			nofile;
};

struct io_socket {
	struct file			*file;
	int				domain;
	int				type;
	int				protocol;
	int				flags;
	u32				file_slot;
	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;
	u32				flags;
	s32				fd;
};

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;
	/* for linked completions */
	struct io_kiocb			*prev;
};

struct io_timeout_rem {
	struct file			*file;
	u64				addr;

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

struct io_rw {
	/* NOTE: kiocb has the file as the first member, so don't do it here */
	struct kiocb			kiocb;
	u64				addr;
	u32				len;
	rwf_t				flags;
};

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;
	size_t				len;
	size_t				done_io;
	unsigned int			flags;
};

struct io_open {
	struct file			*file;
	int				dfd;
	u32				file_slot;
	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;
	loff_t				off_out;
	loff_t				off_in;
	u64				len;
	int				splice_fd_in;
	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;
	struct filename			*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_mkdir {
	struct file			*file;
	int				dfd;
	umode_t				mode;
	struct filename			*filename;
};

struct io_symlink {
	struct file			*file;
	int				new_dfd;
	struct filename			*oldpath;
	struct filename			*newpath;
};

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

struct io_msg {
	struct file			*file;
	u64 user_data;
	u32 len;
};

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_rw_state {
	struct iov_iter			iter;
	struct iov_iter_state		iter_state;
	struct iovec			fast_iov[UIO_FASTIOV];
};

struct io_async_rw {
	struct io_rw_state		s;
	const struct iovec		*free_iovec;
	size_t				bytes_done;
	struct wait_page_queue		wpq;
};

struct io_xattr {
	struct file			*file;
	struct xattr_ctx		ctx;
	struct filename			*filename;
};

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

	/* first byte is taken by user flags, shift it to not overlap */
	REQ_F_FAIL_BIT		= 8,
	REQ_F_INFLIGHT_BIT,
	REQ_F_CUR_POS_BIT,
	REQ_F_NOWAIT_BIT,
	REQ_F_LINK_TIMEOUT_BIT,
	REQ_F_NEED_CLEANUP_BIT,
	REQ_F_POLLED_BIT,
	REQ_F_BUFFER_SELECTED_BIT,
	REQ_F_BUFFER_RING_BIT,
	REQ_F_COMPLETE_INLINE_BIT,
	REQ_F_REISSUE_BIT,
	REQ_F_CREDS_BIT,
	REQ_F_REFCOUNT_BIT,
	REQ_F_ARM_LTIMEOUT_BIT,
	REQ_F_ASYNC_DATA_BIT,
	REQ_F_SKIP_LINK_CQES_BIT,
	REQ_F_SINGLE_POLL_BIT,
	REQ_F_DOUBLE_POLL_BIT,
	REQ_F_PARTIAL_IO_BIT,
	REQ_F_CQE32_INIT_BIT,
	REQ_F_APOLL_MULTISHOT_BIT,
	/* keep async read/write and isreg together and in order */
	REQ_F_SUPPORT_NOWAIT_BIT,
	REQ_F_ISREG_BIT,

	/* not a real bit, just to check we're not overflowing the space */
	__REQ_F_LAST_BIT,
};

enum {
	/* ctx owns file */
	REQ_F_FIXED_FILE	= BIT(REQ_F_FIXED_FILE_BIT),
	/* drain existing IO first */
	REQ_F_IO_DRAIN		= BIT(REQ_F_IO_DRAIN_BIT),
	/* linked sqes */
	REQ_F_LINK		= BIT(REQ_F_LINK_BIT),
	/* doesn't sever on completion < 0 */
	REQ_F_HARDLINK		= BIT(REQ_F_HARDLINK_BIT),
	/* IOSQE_ASYNC */
	REQ_F_FORCE_ASYNC	= BIT(REQ_F_FORCE_ASYNC_BIT),
	/* IOSQE_BUFFER_SELECT */
	REQ_F_BUFFER_SELECT	= BIT(REQ_F_BUFFER_SELECT_BIT),
	/* IOSQE_CQE_SKIP_SUCCESS */
	REQ_F_CQE_SKIP		= BIT(REQ_F_CQE_SKIP_BIT),

	/* fail rest of links */
	REQ_F_FAIL		= BIT(REQ_F_FAIL_BIT),
	/* on inflight list, should be cancelled and waited on exit reliably */
	REQ_F_INFLIGHT		= BIT(REQ_F_INFLIGHT_BIT),
	/* read/write uses file position */
	REQ_F_CUR_POS		= BIT(REQ_F_CUR_POS_BIT),
	/* must not punt to workers */
	REQ_F_NOWAIT		= BIT(REQ_F_NOWAIT_BIT),
	/* has or had linked timeout */
	REQ_F_LINK_TIMEOUT	= BIT(REQ_F_LINK_TIMEOUT_BIT),
	/* needs cleanup */
	REQ_F_NEED_CLEANUP	= BIT(REQ_F_NEED_CLEANUP_BIT),
	/* already went through poll handler */
	REQ_F_POLLED		= BIT(REQ_F_POLLED_BIT),
	/* buffer already selected */
	REQ_F_BUFFER_SELECTED	= BIT(REQ_F_BUFFER_SELECTED_BIT),
	/* buffer selected from ring, needs commit */
	REQ_F_BUFFER_RING	= BIT(REQ_F_BUFFER_RING_BIT),
	/* completion is deferred through io_comp_state */
	REQ_F_COMPLETE_INLINE	= BIT(REQ_F_COMPLETE_INLINE_BIT),
	/* caller should reissue async */
	REQ_F_REISSUE		= BIT(REQ_F_REISSUE_BIT),
	/* supports async reads/writes */
	REQ_F_SUPPORT_NOWAIT	= BIT(REQ_F_SUPPORT_NOWAIT_BIT),
	/* regular file */
	REQ_F_ISREG		= BIT(REQ_F_ISREG_BIT),
	/* has creds assigned */
	REQ_F_CREDS		= BIT(REQ_F_CREDS_BIT),
	/* skip refcounting if not set */
	REQ_F_REFCOUNT		= BIT(REQ_F_REFCOUNT_BIT),
	/* there is a linked timeout that has to be armed */
	REQ_F_ARM_LTIMEOUT	= BIT(REQ_F_ARM_LTIMEOUT_BIT),
	/* ->async_data allocated */
	REQ_F_ASYNC_DATA	= BIT(REQ_F_ASYNC_DATA_BIT),
	/* don't post CQEs while failing linked requests */
	REQ_F_SKIP_LINK_CQES	= BIT(REQ_F_SKIP_LINK_CQES_BIT),
	/* single poll may be active */
	REQ_F_SINGLE_POLL	= BIT(REQ_F_SINGLE_POLL_BIT),
	/* double poll may active */
	REQ_F_DOUBLE_POLL	= BIT(REQ_F_DOUBLE_POLL_BIT),
	/* request has already done partial IO */
	REQ_F_PARTIAL_IO	= BIT(REQ_F_PARTIAL_IO_BIT),
	/* fast poll multishot mode */
	REQ_F_APOLL_MULTISHOT	= BIT(REQ_F_APOLL_MULTISHOT_BIT),
	/* ->extra1 and ->extra2 are initialised */
	REQ_F_CQE32_INIT	= BIT(REQ_F_CQE32_INIT_BIT),
};

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

typedef void (*io_req_tw_func_t)(struct io_kiocb *req, bool *locked);

struct io_task_work {
	union {
		struct io_wq_work_node	node;
		struct llist_node	fallback_node;
	};
	io_req_tw_func_t		func;
};

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

struct io_cqe {
	__u64	user_data;
	__s32	res;
	/* fd initially, then cflags for completion */
	union {
		__u32	flags;
		int	fd;
	};
};

enum {
	IO_CHECK_CQ_OVERFLOW_BIT,
	IO_CHECK_CQ_DROPPED_BIT,
};

/*
 * 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 'file' 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;
		struct io_mkdir		mkdir;
		struct io_symlink	symlink;
		struct io_hardlink	hardlink;
		struct io_msg		msg;
		struct io_xattr		xattr;
		struct io_socket	sock;
		struct io_uring_cmd	uring_cmd;
	};

	u8				opcode;
	/* polled IO has completed */
	u8				iopoll_completed;
	/*
	 * Can be either a fixed buffer index, or used with provided buffers.
	 * For the latter, before issue it points to the buffer group ID,
	 * and after selection it points to the buffer ID itself.
	 */
	u16				buf_index;
	unsigned int			flags;

	struct io_cqe			cqe;

	struct io_ring_ctx		*ctx;
	struct task_struct		*task;

	struct io_rsrc_node		*rsrc_node;

	union {
		/* store used ubuf, so we can prevent reloading */
		struct io_mapped_ubuf	*imu;

		/* stores selected buf, valid IFF REQ_F_BUFFER_SELECTED is set */
		struct io_buffer	*kbuf;

		/*
		 * stores buffer ID for ring provided buffers, valid IFF
		 * REQ_F_BUFFER_RING is set.
		 */
		struct io_buffer_list	*buf_list;
	};

	union {
		/* used by request caches, completion batching and iopoll */
		struct io_wq_work_node	comp_list;
		/* cache ->apoll->events */
		__poll_t apoll_events;
	};
	atomic_t			refs;
	atomic_t			poll_refs;
	struct io_task_work		io_task_work;
	/* for polled requests, i.e. IORING_OP_POLL_ADD and async armed poll */
	union {
		struct hlist_node	hash_node;
		struct {
			u64		extra1;
			u64		extra2;
		};
	};
	/* internal polling, see IORING_FEAT_FAST_POLL */
	struct async_poll		*apoll;
	/* opcode allocated if it needs to store data for async defer */
	void				*async_data;
	/* linked requests, IFF REQ_F_HARDLINK or REQ_F_LINK are set */
	struct io_kiocb			*link;
	/* custom credentials, valid IFF REQ_F_CREDS is set */
	const struct cred		*creds;
	struct io_wq_work		work;
};

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

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

struct io_cancel_data {
	struct io_ring_ctx *ctx;
	union {
		u64 data;
		struct file *file;
	};
	u32 flags;
	int seq;
};

/*
 * The URING_CMD payload starts at 'cmd' in the first sqe, and continues into
 * the following sqe if SQE128 is used.
 */
#define uring_cmd_pdu_size(is_sqe128)				\
	((1 + !!(is_sqe128)) * sizeof(struct io_uring_sqe) -	\
		offsetof(struct io_uring_sqe, cmd))

struct io_op_def {
	/* needs req->file assigned */
	unsigned		needs_file : 1;
	/* should block plug */
	unsigned		plug : 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;
	/* set if opcode supports polled "wait" */
	unsigned		pollin : 1;
	unsigned		pollout : 1;
	unsigned		poll_exclusive : 1;
	/* op supports buffer selection */
	unsigned		buffer_select : 1;
	/* do prep async if is going to be punted */
	unsigned		needs_async_setup : 1;
	/* opcode is not supported by this kernel */
	unsigned		not_supported : 1;
	/* skip auditing */
	unsigned		audit_skip : 1;
	/* supports ioprio */
	unsigned		ioprio : 1;
	/* supports iopoll */
	unsigned		iopoll : 1;
	/* size of async data needed, if any */
	unsigned short		async_size;
};

static const struct io_op_def io_op_defs[] = {
	[IORING_OP_NOP] = {
		.audit_skip		= 1,
		.iopoll			= 1,
	},
	[IORING_OP_READV] = {
		.needs_file		= 1,
		.unbound_nonreg_file	= 1,
		.pollin			= 1,
		.buffer_select		= 1,
		.needs_async_setup	= 1,
		.plug			= 1,
		.audit_skip		= 1,
		.ioprio			= 1,
		.iopoll			= 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,
		.audit_skip		= 1,
		.ioprio			= 1,
		.iopoll			= 1,
		.async_size		= sizeof(struct io_async_rw),
	},
	[IORING_OP_FSYNC] = {
		.needs_file		= 1,
		.audit_skip		= 1,
	},
	[IORING_OP_READ_FIXED] = {
		.needs_file		= 1,
		.unbound_nonreg_file	= 1,
		.pollin			= 1,
		.plug			= 1,
		.audit_skip		= 1,
		.ioprio			= 1,
		.iopoll			= 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,
		.audit_skip		= 1,
		.ioprio			= 1,
		.iopoll			= 1,
		.async_size		= sizeof(struct io_async_rw),
	},
	[IORING_OP_POLL_ADD] = {
		.needs_file		= 1,
		.unbound_nonreg_file	= 1,
		.audit_skip		= 1,
	},
	[IORING_OP_POLL_REMOVE] = {
		.audit_skip		= 1,
	},
	[IORING_OP_SYNC_FILE_RANGE] = {
		.needs_file		= 1,
		.audit_skip		= 1,
	},
	[IORING_OP_SENDMSG] = {
		.needs_file		= 1,
		.unbound_nonreg_file	= 1,
		.pollout		= 1,
		.needs_async_setup	= 1,
		.ioprio			= 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,
		.ioprio			= 1,
		.async_size		= sizeof(struct io_async_msghdr),
	},
	[IORING_OP_TIMEOUT] = {
		.audit_skip		= 1,
		.async_size		= sizeof(struct io_timeout_data),
	},
	[IORING_OP_TIMEOUT_REMOVE] = {
		/* used by timeout updates' prep() */
		.audit_skip		= 1,
	},
	[IORING_OP_ACCEPT] = {
		.needs_file		= 1,
		.unbound_nonreg_file	= 1,
		.pollin			= 1,
		.poll_exclusive		= 1,
		.ioprio			= 1,	/* used for flags */
	},
	[IORING_OP_ASYNC_CANCEL] = {
		.audit_skip		= 1,
	},
	[IORING_OP_LINK_TIMEOUT] = {
		.audit_skip		= 1,
		.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] = {
		.audit_skip		= 1,
		.iopoll			= 1,
	},
	[IORING_OP_STATX] = {
		.audit_skip		= 1,
	},
	[IORING_OP_READ] = {
		.needs_file		= 1,
		.unbound_nonreg_file	= 1,
		.pollin			= 1,
		.buffer_select		= 1,
		.plug			= 1,
		.audit_skip		= 1,
		.ioprio			= 1,
		.iopoll			= 1,
		.async_size		= sizeof(struct io_async_rw),
	},
	[IORING_OP_WRITE] = {
		.needs_file		= 1,
		.hash_reg_file		= 1,
		.unbound_nonreg_file	= 1,
		.pollout		= 1,
		.plug			= 1,
		.audit_skip		= 1,
		.ioprio			= 1,
		.iopoll			= 1,
		.async_size		= sizeof(struct io_async_rw),
	},
	[IORING_OP_FADVISE] = {
		.needs_file		= 1,
		.audit_skip		= 1,
	},
	[IORING_OP_MADVISE] = {},
	[IORING_OP_SEND] = {
		.needs_file		= 1,
		.unbound_nonreg_file	= 1,
		.pollout		= 1,
		.audit_skip		= 1,
		.ioprio			= 1,
	},
	[IORING_OP_RECV] = {
		.needs_file		= 1,
		.unbound_nonreg_file	= 1,
		.pollin			= 1,
		.buffer_select		= 1,
		.audit_skip		= 1,
		.ioprio			= 1,
	},
	[IORING_OP_OPENAT2] = {
	},
	[IORING_OP_EPOLL_CTL] = {
		.unbound_nonreg_file	= 1,
		.audit_skip		= 1,
	},
	[IORING_OP_SPLICE] = {
		.needs_file		= 1,
		.hash_reg_file		= 1,
		.unbound_nonreg_file	= 1,
		.audit_skip		= 1,
	},
	[IORING_OP_PROVIDE_BUFFERS] = {
		.audit_skip		= 1,
		.iopoll			= 1,
	},
	[IORING_OP_REMOVE_BUFFERS] = {
		.audit_skip		= 1,
		.iopoll			= 1,
	},
	[IORING_OP_TEE] = {
		.needs_file		= 1,
		.hash_reg_file		= 1,
		.unbound_nonreg_file	= 1,
		.audit_skip		= 1,
	},
	[IORING_OP_SHUTDOWN] = {
		.needs_file		= 1,
	},
	[IORING_OP_RENAMEAT] = {},
	[IORING_OP_UNLINKAT] = {},
	[IORING_OP_MKDIRAT] = {},
	[IORING_OP_SYMLINKAT] = {},
	[IORING_OP_LINKAT] = {},
	[IORING_OP_MSG_RING] = {
		.needs_file		= 1,
		.iopoll			= 1,
	},
	[IORING_OP_FSETXATTR] = {
		.needs_file = 1
	},
	[IORING_OP_SETXATTR] = {},
	[IORING_OP_FGETXATTR] = {
		.needs_file = 1
	},
	[IORING_OP_GETXATTR] = {},
	[IORING_OP_SOCKET] = {
		.audit_skip		= 1,
	},
	[IORING_OP_URING_CMD] = {
		.needs_file		= 1,
		.plug			= 1,
		.needs_async_setup	= 1,
		.async_size		= uring_cmd_pdu_size(1),
	},
};

/* requests with any of those set should undergo io_disarm_next() */
#define IO_DISARM_MASK (REQ_F_ARM_LTIMEOUT | REQ_F_LINK_TIMEOUT | REQ_F_FAIL)
#define IO_REQ_LINK_FLAGS (REQ_F_LINK | REQ_F_HARDLINK)

static bool io_disarm_next(struct io_kiocb *req);
static void io_uring_del_tctx_node(unsigned long index);
static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
					 struct task_struct *task,
					 bool cancel_all);
static void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd);

static void __io_req_complete_post(struct io_kiocb *req, s32 res, u32 cflags);
static void io_dismantle_req(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 inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd,
					     unsigned issue_flags);
static struct file *io_file_get_normal(struct io_kiocb *req, int fd);
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_ring_ctx *ctx);
static int io_req_prep_async(struct io_kiocb *req);

static int io_install_fixed_file(struct io_kiocb *req, struct file *file,
				 unsigned int issue_flags, u32 slot_index);
static int __io_close_fixed(struct io_kiocb *req, unsigned int issue_flags,
			    unsigned int offset);
static inline int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags);

static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer);
static void io_eventfd_signal(struct io_ring_ctx *ctx);
static void io_req_tw_post_queue(struct io_kiocb *req, s32 res, u32 cflags);

static struct kmem_cache *req_cachep;

static const struct file_operations io_uring_fops;

const char *io_uring_get_opcode(u8 opcode)
{
	switch ((enum io_uring_op)opcode) {
	case IORING_OP_NOP:
		return "NOP";
	case IORING_OP_READV:
		return "READV";
	case IORING_OP_WRITEV:
		return "WRITEV";
	case IORING_OP_FSYNC:
		return "FSYNC";
	case IORING_OP_READ_FIXED:
		return "READ_FIXED";
	case IORING_OP_WRITE_FIXED:
		return "WRITE_FIXED";
	case IORING_OP_POLL_ADD:
		return "POLL_ADD";
	case IORING_OP_POLL_REMOVE:
		return "POLL_REMOVE";
	case IORING_OP_SYNC_FILE_RANGE:
		return "SYNC_FILE_RANGE";
	case IORING_OP_SENDMSG:
		return "SENDMSG";
	case IORING_OP_RECVMSG:
		return "RECVMSG";
	case IORING_OP_TIMEOUT:
		return "TIMEOUT";
	case IORING_OP_TIMEOUT_REMOVE:
		return "TIMEOUT_REMOVE";
	case IORING_OP_ACCEPT:
		return "ACCEPT";
	case IORING_OP_ASYNC_CANCEL:
		return "ASYNC_CANCEL";
	case IORING_OP_LINK_TIMEOUT:
		return "LINK_TIMEOUT";
	case IORING_OP_CONNECT:
		return "CONNECT";
	case IORING_OP_FALLOCATE:
		return "FALLOCATE";
	case IORING_OP_OPENAT:
		return "OPENAT";
	case IORING_OP_CLOSE:
		return "CLOSE";
	case IORING_OP_FILES_UPDATE:
		return "FILES_UPDATE";
	case IORING_OP_STATX:
		return "STATX";
	case IORING_OP_READ:
		return "READ";
	case IORING_OP_WRITE:
		return "WRITE";
	case IORING_OP_FADVISE:
		return "FADVISE";
	case IORING_OP_MADVISE:
		return "MADVISE";
	case IORING_OP_SEND:
		return "SEND";
	case IORING_OP_RECV:
		return "RECV";
	case IORING_OP_OPENAT2:
		return "OPENAT2";
	case IORING_OP_EPOLL_CTL:
		return "EPOLL_CTL";
	case IORING_OP_SPLICE:
		return "SPLICE";
	case IORING_OP_PROVIDE_BUFFERS:
		return "PROVIDE_BUFFERS";
	case IORING_OP_REMOVE_BUFFERS:
		return "REMOVE_BUFFERS";
	case IORING_OP_TEE:
		return "TEE";
	case IORING_OP_SHUTDOWN:
		return "SHUTDOWN";
	case IORING_OP_RENAMEAT:
		return "RENAMEAT";
	case IORING_OP_UNLINKAT:
		return "UNLINKAT";
	case IORING_OP_MKDIRAT:
		return "MKDIRAT";
	case IORING_OP_SYMLINKAT:
		return "SYMLINKAT";
	case IORING_OP_LINKAT:
		return "LINKAT";
	case IORING_OP_MSG_RING:
		return "MSG_RING";
	case IORING_OP_FSETXATTR:
		return "FSETXATTR";
	case IORING_OP_SETXATTR:
		return "SETXATTR";
	case IORING_OP_FGETXATTR:
		return "FGETXATTR";
	case IORING_OP_GETXATTR:
		return "GETXATTR";
	case IORING_OP_SOCKET:
		return "SOCKET";
	case IORING_OP_URING_CMD:
		return "URING_CMD";
	case IORING_OP_LAST:
		return "INVALID";
	}
	return "INVALID";
}

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);

#if defined(CONFIG_UNIX)
static inline bool io_file_need_scm(struct file *filp)
{
#if defined(IO_URING_SCM_ALL)
	return true;
#else
	return !!unix_get_socket(filp);
#endif
}
#else
static inline bool io_file_need_scm(struct file *filp)
{
	return false;
}
#endif

static void io_ring_submit_unlock(struct io_ring_ctx *ctx, unsigned issue_flags)
{
	lockdep_assert_held(&ctx->uring_lock);
	if (issue_flags & IO_URING_F_UNLOCKED)
		mutex_unlock(&ctx->uring_lock);
}

static void io_ring_submit_lock(struct io_ring_ctx *ctx, unsigned issue_flags)
{
	/*
	 * "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 (issue_flags & IO_URING_F_UNLOCKED)
		mutex_lock(&ctx->uring_lock);
	lockdep_assert_held(&ctx->uring_lock);
}

static inline void io_tw_lock(struct io_ring_ctx *ctx, bool *locked)
{
	if (!*locked) {
		mutex_lock(&ctx->uring_lock);
		*locked = true;
	}
}

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

/*
 * 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)
{
	WARN_ON_ONCE(!(req->flags & REQ_F_REFCOUNT));
	return atomic_inc_not_zero(&req->refs);
}

static inline bool req_ref_put_and_test(struct io_kiocb *req)
{
	if (likely(!(req->flags & REQ_F_REFCOUNT)))
		return true;

	WARN_ON_ONCE(req_ref_zero_or_close_to_overflow(req));
	return atomic_dec_and_test(&req->refs);
}

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

static inline void io_submit_flush_completions(struct io_ring_ctx *ctx)
{
	if (!wq_list_empty(&ctx->submit_state.compl_reqs))
		__io_submit_flush_completions(ctx);
}

static inline void __io_req_set_refcount(struct io_kiocb *req, int nr)
{
	if (!(req->flags & REQ_F_REFCOUNT)) {
		req->flags |= REQ_F_REFCOUNT;
		atomic_set(&req->refs, nr);
	}
}

static inline void io_req_set_refcount(struct io_kiocb *req)
{
	__io_req_set_refcount(req, 1);
}

#define IO_RSRC_REF_BATCH	100

static void io_rsrc_put_node(struct io_rsrc_node *node, int nr)
{
	percpu_ref_put_many(&node->refs, nr);
}

static inline void io_req_put_rsrc_locked(struct io_kiocb *req,
					  struct io_ring_ctx *ctx)
	__must_hold(&ctx->uring_lock)
{
	struct io_rsrc_node *node = req->rsrc_node;

	if (node) {
		if (node == ctx->rsrc_node)
			ctx->rsrc_cached_refs++;
		else
			io_rsrc_put_node(node, 1);
	}
}

static inline void io_req_put_rsrc(struct io_kiocb *req)
{
	if (req->rsrc_node)
		io_rsrc_put_node(req->rsrc_node, 1);
}

static __cold void io_rsrc_refs_drop(struct io_ring_ctx *ctx)
	__must_hold(&ctx->uring_lock)
{
	if (ctx->rsrc_cached_refs) {
		io_rsrc_put_node(ctx->rsrc_node, ctx->rsrc_cached_refs);
		ctx->rsrc_cached_refs = 0;
	}
}

static void io_rsrc_refs_refill(struct io_ring_ctx *ctx)
	__must_hold(&ctx->uring_lock)
{
	ctx->rsrc_cached_refs += IO_RSRC_REF_BATCH;
	percpu_ref_get_many(&ctx->rsrc_node->refs, IO_RSRC_REF_BATCH);
}

static inline void io_req_set_rsrc_node(struct io_kiocb *req,
					struct io_ring_ctx *ctx,
					unsigned int issue_flags)
{
	if (!req->rsrc_node) {
		req->rsrc_node = ctx->rsrc_node;

		if (!(issue_flags & IO_URING_F_UNLOCKED)) {
			lockdep_assert_held(&ctx->uring_lock);
			ctx->rsrc_cached_refs--;
			if (unlikely(ctx->rsrc_cached_refs < 0))
				io_rsrc_refs_refill(ctx);
		} else {
			percpu_ref_get(&req->rsrc_node->refs);
		}
	}
}

static unsigned int __io_put_kbuf(struct io_kiocb *req, struct list_head *list)
{
	if (req->flags & REQ_F_BUFFER_RING) {
		if (req->buf_list)
			req->buf_list->head++;
		req->flags &= ~REQ_F_BUFFER_RING;
	} else {
		list_add(&req->kbuf->list, list);
		req->flags &= ~REQ_F_BUFFER_SELECTED;
	}

	return IORING_CQE_F_BUFFER | (req->buf_index << IORING_CQE_BUFFER_SHIFT);
}

static inline unsigned int io_put_kbuf_comp(struct io_kiocb *req)
{
	lockdep_assert_held(&req->ctx->completion_lock);

	if (!(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)))
		return 0;
	return __io_put_kbuf(req, &req->ctx->io_buffers_comp);
}

static inline unsigned int io_put_kbuf(struct io_kiocb *req,
				       unsigned issue_flags)
{
	unsigned int cflags;

	if (!(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)))
		return 0;

	/*
	 * We can add this buffer back to two lists:
	 *
	 * 1) The io_buffers_cache list. This one is protected by the
	 *    ctx->uring_lock. If we already hold this lock, add back to this
	 *    list as we can grab it from issue as well.
	 * 2) The io_buffers_comp list. This one is protected by the
	 *    ctx->completion_lock.
	 *
	 * We migrate buffers from the comp_list to the issue cache list
	 * when we need one.
	 */
	if (req->flags & REQ_F_BUFFER_RING) {
		/* no buffers to recycle for this case */
		cflags = __io_put_kbuf(req, NULL);
	} else if (issue_flags & IO_URING_F_UNLOCKED) {
		struct io_ring_ctx *ctx = req->ctx;

		spin_lock(&ctx->completion_lock);
		cflags = __io_put_kbuf(req, &ctx->io_buffers_comp);
		spin_unlock(&ctx->completion_lock);
	} else {
		lockdep_assert_held(&req->ctx->uring_lock);

		cflags = __io_put_kbuf(req, &req->ctx->io_buffers_cache);
	}

	return cflags;
}

static struct io_buffer_list *io_buffer_get_list(struct io_ring_ctx *ctx,
						 unsigned int bgid)
{
	if (ctx->io_bl && bgid < BGID_ARRAY)
		return &ctx->io_bl[bgid];

	return xa_load(&ctx->io_bl_xa, bgid);
}

static void io_kbuf_recycle(struct io_kiocb *req, unsigned issue_flags)
{
	struct io_ring_ctx *ctx = req->ctx;
	struct io_buffer_list *bl;
	struct io_buffer *buf;

	if (!(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)))
		return;
	/*
	 * For legacy provided buffer mode, don't recycle if we already did
	 * IO to this buffer. For ring-mapped provided buffer mode, we should
	 * increment ring->head to explicitly monopolize the buffer to avoid
	 * multiple use.
	 */
	if ((req->flags & REQ_F_BUFFER_SELECTED) &&
	    (req->flags & REQ_F_PARTIAL_IO))
		return;

	/*
	 * READV uses fields in `struct io_rw` (len/addr) to stash the selected
	 * buffer data. However if that buffer is recycled the original request
	 * data stored in addr is lost. Therefore forbid recycling for now.
	 */
	if (req->opcode == IORING_OP_READV)
		return;

	/*
	 * We don't need to recycle for REQ_F_BUFFER_RING, we can just clear
	 * the flag and hence ensure that bl->head doesn't get incremented.
	 * If the tail has already been incremented, hang on to it.
	 */
	if (req->flags & REQ_F_BUFFER_RING) {
		if (req->buf_list) {
			if (req->flags & REQ_F_PARTIAL_IO) {
				req->buf_list->head++;
				req->buf_list = NULL;
			} else {
				req->buf_index = req->buf_list->bgid;
				req->flags &= ~REQ_F_BUFFER_RING;
			}
		}
		return;
	}

	io_ring_submit_lock(ctx, issue_flags);

	buf = req->kbuf;
	bl = io_buffer_get_list(ctx, buf->bgid);
	list_add(&buf->list, &bl->buf_list);
	req->flags &= ~REQ_F_BUFFER_SELECTED;
	req->buf_index = buf->bgid;

	io_ring_submit_unlock(ctx, issue_flags);
}

static bool io_match_task(struct io_kiocb *head, struct task_struct *task,
			  bool cancel_all)
	__must_hold(&req->ctx->timeout_lock)
{
	struct io_kiocb *req;

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

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

static bool io_match_linked(struct io_kiocb *head)
{
	struct io_kiocb *req;

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

/*
 * As io_match_task() but protected against racing with linked timeouts.
 * User must not hold timeout_lock.
 */
static bool io_match_task_safe(struct io_kiocb *head, struct task_struct *task,
			       bool cancel_all)
{
	bool matched;

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

	if (head->flags & REQ_F_LINK_TIMEOUT) {
		struct io_ring_ctx *ctx = head->ctx;

		/* protect against races with linked timeouts */
		spin_lock_irq(&ctx->timeout_lock);
		matched = io_match_linked(head);
		spin_unlock_irq(&ctx->timeout_lock);
	} else {
		matched = io_match_linked(head);
	}
	return matched;
}

static inline bool req_has_async_data(struct io_kiocb *req)
{
	return req->flags & REQ_F_ASYNC_DATA;
}

static inline void req_set_fail(struct io_kiocb *req)
{
	req->flags |= REQ_F_FAIL;
	if (req->flags & REQ_F_CQE_SKIP) {
		req->flags &= ~REQ_F_CQE_SKIP;
		req->flags |= REQ_F_SKIP_LINK_CQES;
	}
}

static inline void req_fail_link_node(struct io_kiocb *req, int res)
{
	req_set_fail(req);
	req->cqe.res = res;
}

static inline void io_req_add_to_cache(struct io_kiocb *req, struct io_ring_ctx *ctx)
{
	wq_stack_add_head(&req->comp_list, &ctx->submit_state.free_list);
}

static __cold 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 __cold void io_fallback_req_func(struct work_struct *work)
{
	struct io_ring_ctx *ctx = container_of(work, struct io_ring_ctx,
						fallback_work.work);
	struct llist_node *node = llist_del_all(&ctx->fallback_llist);
	struct io_kiocb *req, *tmp;
	bool locked = false;

	percpu_ref_get(&ctx->refs);
	llist_for_each_entry_safe(req, tmp, node, io_task_work.fallback_node)
		req->io_task_work.func(req, &locked);

	if (locked) {
		io_submit_flush_completions(ctx);
		mutex_unlock(&ctx->uring_lock);
	}
	percpu_ref_put(&ctx->refs);
}

static __cold 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;

	xa_init(&ctx->io_bl_xa);

	/*
	 * 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_LIST_HEAD(&ctx->cq_overflow_list);
	INIT_LIST_HEAD(&ctx->io_buffers_cache);
	INIT_LIST_HEAD(&ctx->apoll_cache);
	init_completion(&ctx->ref_comp);
	xa_init_flags(&ctx->personalities, XA_FLAGS_ALLOC1);
	mutex_init(&ctx->uring_lock);
	init_waitqueue_head(&ctx->cq_wait);
	spin_lock_init(&ctx->completion_lock);
	spin_lock_init(&ctx->timeout_lock);
	INIT_WQ_LIST(&ctx->iopoll_list);
	INIT_LIST_HEAD(&ctx->io_buffers_pages);
	INIT_LIST_HEAD(&ctx->io_buffers_comp);
	INIT_LIST_HEAD(&ctx->defer_list);
	INIT_LIST_HEAD(&ctx->timeout_list);
	INIT_LIST_HEAD(&ctx->ltimeout_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);
	ctx->submit_state.free_list.next = NULL;
	INIT_WQ_LIST(&ctx->locked_free_list);
	INIT_DELAYED_WORK(&ctx->fallback_work, io_fallback_req_func);
	INIT_WQ_LIST(&ctx->submit_state.compl_reqs);
	return ctx;
err:
	kfree(ctx->dummy_ubuf);
	kfree(ctx->cancel_hash);
	kfree(ctx->io_bl);
	xa_destroy(&ctx->io_bl_xa);
	kfree(ctx);
	return NULL;
}

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

	WRITE_ONCE(r->cq_overflow, READ_ONCE(r->cq_overflow) + 1);
	ctx->cq_extra--;
}

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

	return false;
}

static inline bool io_req_ffs_set(struct io_kiocb *req)
{
	return req->flags & REQ_F_FIXED_FILE;
}

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

static struct io_kiocb *__io_prep_linked_timeout(struct io_kiocb *req)
{
	if (WARN_ON_ONCE(!req->link))
		return NULL;

	req->flags &= ~REQ_F_ARM_LTIMEOUT;
	req->flags |= REQ_F_LINK_TIMEOUT;

	/* linked timeouts should have two refs once prep'ed */
	io_req_set_refcount(req);
	__io_req_set_refcount(req->link, 2);
	return req->link;
}

static inline struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req)
{
	if (likely(!(req->flags & REQ_F_ARM_LTIMEOUT)))
		return NULL;
	return __io_prep_linked_timeout(req);
}

static noinline void __io_arm_ltimeout(struct io_kiocb *req)
{
	io_queue_linked_timeout(__io_prep_linked_timeout(req));
}

static inline void io_arm_ltimeout(struct io_kiocb *req)
{
	if (unlikely(req->flags & REQ_F_ARM_LTIMEOUT))
		__io_arm_ltimeout(req);
}

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->flags & REQ_F_CREDS)) {
		req->flags |= REQ_F_CREDS;
		req->creds = get_current_cred();
	}

	req->work.list.next = NULL;
	req->work.flags = 0;
	req->work.cancel_seq = atomic_read(&ctx->cancel_seq);
	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;
	}
}

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

	if (req->flags & REQ_F_LINK_TIMEOUT) {
		struct io_ring_ctx *ctx = req->ctx;

		spin_lock_irq(&ctx->timeout_lock);
		io_for_each_link(cur, req)
			io_prep_async_work(cur);
		spin_unlock_irq(&ctx->timeout_lock);
	} else {
		io_for_each_link(cur, req)
			io_prep_async_work(cur);
	}
}

static inline void io_req_add_compl_list(struct io_kiocb *req)
{
	struct io_submit_state *state = &req->ctx->submit_state;

	if (!(req->flags & REQ_F_CQE_SKIP))
		state->flush_cqes = true;
	wq_list_add_tail(&req->comp_list, &state->compl_reqs);
}

static void io_queue_iowq(struct io_kiocb *req, bool *dont_use)
{
	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);

	/*
	 * Not expected to happen, but if we do have a bug where this _can_
	 * happen, catch it here and ensure the request is marked as
	 * canceled. That will make io-wq go through the usual work cancel
	 * procedure rather than attempt to run this request (or create a new
	 * worker for it).
	 */
	if (WARN_ON_ONCE(!same_thread_group(req->task, current)))
		req->work.flags |= IO_WQ_WORK_CANCEL;

	trace_io_uring_queue_async_work(req->ctx, req, req->cqe.user_data,
					req->opcode, req->flags, &req->work,
					io_wq_is_hashed(&req->work));
	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)
	__must_hold(&req->ctx->timeout_lock)
{
	struct io_timeout_data *io = req->async_data;

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

static __cold void io_queue_deferred(struct io_ring_ctx *ctx)
{
	while (!list_empty(&ctx->defer_list)) {
		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);
	}
}

static __cold void io_flush_timeouts(struct io_ring_ctx *ctx)
	__must_hold(&ctx->completion_lock)
{
	u32 seq = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts);
	struct io_kiocb *req, *tmp;

	spin_lock_irq(&ctx->timeout_lock);
	list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) {
		u32 events_needed, events_got;

		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;

		io_kill_timeout(req, 0);
	}
	ctx->cq_last_tm_flush = seq;
	spin_unlock_irq(&ctx->timeout_lock);
}

static inline void io_commit_cqring(struct io_ring_ctx *ctx)
{
	/* order cqe stores with ring update */
	smp_store_release(&ctx->rings->cq.tail, ctx->cached_cq_tail);
}

static void __io_commit_cqring_flush(struct io_ring_ctx *ctx)
{
	if (ctx->off_timeout_used || ctx->drain_active) {
		spin_lock(&ctx->completion_lock);
		if (ctx->off_timeout_used)
			io_flush_timeouts(ctx);
		if (ctx->drain_active)
			io_queue_deferred(ctx);
		io_commit_cqring(ctx);
		spin_unlock(&ctx->completion_lock);
	}
	if (ctx->has_evfd)
		io_eventfd_signal(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 == ctx->sq_entries;
}

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

/*
 * 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
 */
static noinline struct io_uring_cqe *__io_get_cqe(struct io_ring_ctx *ctx)
{
	struct io_rings *rings = ctx->rings;
	unsigned int off = ctx->cached_cq_tail & (ctx->cq_entries - 1);
	unsigned int shift = 0;
	unsigned int free, queued, len;

	if (ctx->flags & IORING_SETUP_CQE32)
		shift = 1;

	/* userspace may cheat modifying the tail, be safe and do min */
	queued = min(__io_cqring_events(ctx), ctx->cq_entries);
	free = ctx->cq_entries - queued;
	/* we need a contiguous range, limit based on the current array offset */
	len = min(free, ctx->cq_entries - off);
	if (!len)
		return NULL;

	ctx->cached_cq_tail++;
	ctx->cqe_cached = &rings->cqes[off];
	ctx->cqe_sentinel = ctx->cqe_cached + len;
	ctx->cqe_cached++;
	return &rings->cqes[off << shift];
}

static inline struct io_uring_cqe *io_get_cqe(struct io_ring_ctx *ctx)
{
	if (likely(ctx->cqe_cached < ctx->cqe_sentinel)) {
		struct io_uring_cqe *cqe = ctx->cqe_cached;

		if (ctx->flags & IORING_SETUP_CQE32) {
			unsigned int off = ctx->cqe_cached - ctx->rings->cqes;

			cqe += off;
		}

		ctx->cached_cq_tail++;
		ctx->cqe_cached++;
		return cqe;
	}

	return __io_get_cqe(ctx);
}

static void io_eventfd_signal(struct io_ring_ctx *ctx)
{
	struct io_ev_fd *ev_fd;

	rcu_read_lock();
	/*
	 * rcu_dereference ctx->io_ev_fd once and use it for both for checking
	 * and eventfd_signal
	 */
	ev_fd = rcu_dereference(ctx->io_ev_fd);

	/*
	 * Check again if ev_fd exists incase an io_eventfd_unregister call
	 * completed between the NULL check of ctx->io_ev_fd at the start of
	 * the function and rcu_read_lock.
	 */
	if (unlikely(!ev_fd))
		goto out;
	if (READ_ONCE(ctx->rings->cq_flags) & IORING_CQ_EVENTFD_DISABLED)
		goto out;

	if (!ev_fd->eventfd_async || io_wq_current_is_worker())
		eventfd_signal(ev_fd->cq_ev_fd, 1);
out:
	rcu_read_unlock();
}

static inline void io_cqring_wake(struct io_ring_ctx *ctx)
{
	/*
	 * wake_up_all() may seem excessive, but io_wake_function() and
	 * io_should_wake() handle the termination of the loop and only
	 * wake as many waiters as we need to.
	 */
	if (wq_has_sleeper(&ctx->cq_wait))
		wake_up_all(&ctx->cq_wait);
}

/*
 * This should only get called when at least one event has been posted.
 * Some applications rely on the eventfd notification count only changing
 * IFF a new CQE has been added to the CQ ring. There's no depedency on
 * 1:1 relationship between how many times this function is called (and
 * hence the eventfd count) and number of CQEs posted to the CQ ring.
 */
static inline void io_cqring_ev_posted(struct io_ring_ctx *ctx)
{
	if (unlikely(ctx->off_timeout_used || ctx->drain_active ||
		     ctx->has_evfd))
		__io_commit_cqring_flush(ctx);

	io_cqring_wake(ctx);
}

static void io_cqring_ev_posted_iopoll(struct io_ring_ctx *ctx)
{
	if (unlikely(ctx->off_timeout_used || ctx->drain_active ||
		     ctx->has_evfd))
		__io_commit_cqring_flush(ctx);

	if (ctx->flags & IORING_SETUP_SQPOLL)
		io_cqring_wake(ctx);
}

/* Returns true if there are no backlogged entries after the flush */
static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force)
{
	bool all_flushed, posted;
	size_t cqe_size = sizeof(struct io_uring_cqe);

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

	if (ctx->flags & IORING_SETUP_CQE32)
		cqe_size <<= 1;

	posted = false;
	spin_lock(&ctx->completion_lock);
	while (!list_empty(&ctx->cq_overflow_list)) {
		struct io_uring_cqe *cqe = io_get_cqe(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, cqe_size);
		else
			io_account_cq_overflow(ctx);

		posted = true;
		list_del(&ocqe->list);
		kfree(ocqe);
	}

	all_flushed = list_empty(&ctx->cq_overflow_list);
	if (all_flushed) {
		clear_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq);
		atomic_andnot(IORING_SQ_CQ_OVERFLOW, &ctx->rings->sq_flags);
	}

	io_commit_cqring(ctx);
	spin_unlock(&ctx->completion_lock);
	if (posted)
		io_cqring_ev_posted(ctx);
	return all_flushed;
}

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

	if (test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq)) {
		/* 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, false);
		if (ctx->flags & IORING_SETUP_IOPOLL)
			mutex_unlock(&ctx->uring_lock);
	}

	return ret;
}

static 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);
}

/* must to be called somewhat shortly after putting a request */
static inline void io_put_task(struct task_struct *task, int nr)
{
	if (likely(task == current))
		task->io_uring->cached_refs += nr;
	else
		__io_put_task(task, nr);
}

static void io_task_refs_refill(struct io_uring_task *tctx)
{
	unsigned int refill = -tctx->cached_refs + IO_TCTX_REFS_CACHE_NR;

	percpu_counter_add(&tctx->inflight, refill);
	refcount_add(refill, &current->usage);
	tctx->cached_refs += refill;
}

static inline void io_get_task_refs(int nr)
{
	struct io_uring_task *tctx = current->io_uring;

	tctx->cached_refs -= nr;
	if (unlikely(tctx->cached_refs < 0))
		io_task_refs_refill(tctx);
}

static __cold void io_uring_drop_tctx_refs(struct task_struct *task)
{
	struct io_uring_task *tctx = task->io_uring;
	unsigned int refs = tctx->cached_refs;

	if (refs) {
		tctx->cached_refs = 0;
		percpu_counter_sub(&tctx->inflight, refs);
		put_task_struct_many(task, refs);
	}
}

static bool io_cqring_event_overflow(struct io_ring_ctx *ctx, u64 user_data,
				     s32 res, u32 cflags, u64 extra1,
				     u64 extra2)
{
	struct io_overflow_cqe *ocqe;
	size_t ocq_size = sizeof(struct io_overflow_cqe);
	bool is_cqe32 = (ctx->flags & IORING_SETUP_CQE32);

	if (is_cqe32)
		ocq_size += sizeof(struct io_uring_cqe);

	ocqe = kmalloc(ocq_size, GFP_ATOMIC | __GFP_ACCOUNT);
	trace_io_uring_cqe_overflow(ctx, user_data, res, cflags, ocqe);
	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.
		 */
		io_account_cq_overflow(ctx);
		set_bit(IO_CHECK_CQ_DROPPED_BIT, &ctx->check_cq);
		return false;
	}
	if (list_empty(&ctx->cq_overflow_list)) {
		set_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq);
		atomic_or(IORING_SQ_CQ_OVERFLOW, &ctx->rings->sq_flags);

	}
	ocqe->cqe.user_data = user_data;
	ocqe->cqe.res = res;
	ocqe->cqe.flags = cflags;
	if (is_cqe32) {
		ocqe->cqe.big_cqe[0] = extra1;
		ocqe->cqe.big_cqe[1] = extra2;
	}
	list_add_tail(&ocqe->list, &ctx->cq_overflow_list);
	return true;
}

static inline bool __io_fill_cqe_req(struct io_ring_ctx *ctx,
				     struct io_kiocb *req)
{
	struct io_uring_cqe *cqe;

	if (!(ctx->flags & IORING_SETUP_CQE32)) {
		trace_io_uring_complete(req->ctx, req, req->cqe.user_data,
					req->cqe.res, req->cqe.flags, 0, 0);

		/*
		 * 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_cqe(ctx);
		if (likely(cqe)) {
			memcpy(cqe, &req->cqe, sizeof(*cqe));
			return true;
		}

		return io_cqring_event_overflow(ctx, req->cqe.user_data,
						req->cqe.res, req->cqe.flags,
						0, 0);
	} else {
		u64 extra1 = 0, extra2 = 0;

		if (req->flags & REQ_F_CQE32_INIT) {
			extra1 = req->extra1;
			extra2 = req->extra2;
		}

		trace_io_uring_complete(req->ctx, req, req->cqe.user_data,
					req->cqe.res, req->cqe.flags, extra1, extra2);

		/*
		 * 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_cqe(ctx);
		if (likely(cqe)) {
			memcpy(cqe, &req->cqe, sizeof(struct io_uring_cqe));
			WRITE_ONCE(cqe->big_cqe[0], extra1);
			WRITE_ONCE(cqe->big_cqe[1], extra2);
			return true;
		}

		return io_cqring_event_overflow(ctx, req->cqe.user_data,
				req->cqe.res, req->cqe.flags,
				extra1, extra2);
	}
}

static noinline bool io_fill_cqe_aux(struct io_ring_ctx *ctx, u64 user_data,
				     s32 res, u32 cflags)
{
	struct io_uring_cqe *cqe;

	ctx->cq_extra++;
	trace_io_uring_complete(ctx, NULL, user_data, res, cflags, 0, 0);

	/*
	 * 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_cqe(ctx);
	if (likely(cqe)) {
		WRITE_ONCE(cqe->user_data, user_data);
		WRITE_ONCE(cqe->res, res);
		WRITE_ONCE(cqe->flags, cflags);

		if (ctx->flags & IORING_SETUP_CQE32) {
			WRITE_ONCE(cqe->big_cqe[0], 0);
			WRITE_ONCE(cqe->big_cqe[1], 0);
		}
		return true;
	}
	return io_cqring_event_overflow(ctx, user_data, res, cflags, 0, 0);
}

static void __io_req_complete_put(struct io_kiocb *req)
{
	/*
	 * 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_ring_ctx *ctx = req->ctx;

		if (req->flags & IO_REQ_LINK_FLAGS) {
			if (req->flags & IO_DISARM_MASK)
				io_disarm_next(req);
			if (req->link) {
				io_req_task_queue(req->link);
				req->link = NULL;
			}
		}
		io_req_put_rsrc(req);
		/*
		 * Selected buffer deallocation in io_clean_op() assumes that
		 * we don't hold ->completion_lock. Clean them here to avoid
		 * deadlocks.
		 */
		io_put_kbuf_comp(req);
		io_dismantle_req(req);
		io_put_task(req->task, 1);
		wq_list_add_head(&req->comp_list, &ctx->locked_free_list);
		ctx->locked_free_nr++;
	}
}

static void __io_req_complete_post(struct io_kiocb *req, s32 res,
				   u32 cflags)
{
	if (!(req->flags & REQ_F_CQE_SKIP)) {
		req->cqe.res = res;
		req->cqe.flags = cflags;
		__io_fill_cqe_req(req->ctx, req);
	}
	__io_req_complete_put(req);
}

static void io_req_complete_post(struct io_kiocb *req, s32 res, u32 cflags)
{
	struct io_ring_ctx *ctx = req->ctx;

	spin_lock(&ctx->completion_lock);
	__io_req_complete_post(req, res, cflags);
	io_commit_cqring(ctx);
	spin_unlock(&ctx->completion_lock);
	io_cqring_ev_posted(ctx);
}

static inline void io_req_complete_state(struct io_kiocb *req, s32 res,
					 u32 cflags)
{
	req->cqe.res = res;
	req->cqe.flags = cflags;
	req->flags |= REQ_F_COMPLETE_INLINE;
}

static inline void __io_req_complete(struct io_kiocb *req, unsigned issue_flags,
				     s32 res, u32 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, s32 res)
{
	if (res < 0)
		req_set_fail(req);
	__io_req_complete(req, 0, res, 0);
}

static void io_req_complete_failed(struct io_kiocb *req, s32 res)
{
	req_set_fail(req);
	io_req_complete_post(req, res, io_put_kbuf(req, IO_URING_F_UNLOCKED));
}

/*
 * Don't initialise the fields below on every allocation, but do that in
 * advance and keep them valid across allocations.
 */
static void io_preinit_req(struct io_kiocb *req, struct io_ring_ctx *ctx)
{
	req->ctx = ctx;
	req->link = NULL;
	req->async_data = NULL;
	/* not necessary, but safer to zero */
	req->cqe.res = 0;
}

static void io_flush_cached_locked_reqs(struct io_ring_ctx *ctx,
					struct io_submit_state *state)
{
	spin_lock(&ctx->completion_lock);
	wq_list_splice(&ctx->locked_free_list, &state->free_list);
	ctx->locked_free_nr = 0;
	spin_unlock(&ctx->completion_lock);
}

static inline bool io_req_cache_empty(struct io_ring_ctx *ctx)
{
	return !ctx->submit_state.free_list.next;
}

/*
 * A request might get retired back into the request caches even before opcode
 * handlers and io_issue_sqe() are done with it, e.g. inline completion path.
 * Because of that, io_alloc_req() should be called only under ->uring_lock
 * and with extra caution to not get a request that is still worked on.
 */
static __cold bool __io_alloc_req_refill(struct io_ring_ctx *ctx)
	__must_hold(&ctx->uring_lock)
{
	gfp_t gfp = GFP_KERNEL | __GFP_NOWARN;
	void *reqs[IO_REQ_ALLOC_BATCH];
	int ret, i;

	/*
	 * 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 (data_race(ctx->locked_free_nr) > IO_COMPL_BATCH) {
		io_flush_cached_locked_reqs(ctx, &ctx->submit_state);
		if (!io_req_cache_empty(ctx))
			return true;
	}

	ret = kmem_cache_alloc_bulk(req_cachep, gfp, ARRAY_SIZE(reqs), 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)) {
		reqs[0] = kmem_cache_alloc(req_cachep, gfp);
		if (!reqs[0])
			return false;
		ret = 1;
	}

	percpu_ref_get_many(&ctx->refs, ret);
	for (i = 0; i < ret; i++) {
		struct io_kiocb *req = reqs[i];

		io_preinit_req(req, ctx);
		io_req_add_to_cache(req, ctx);
	}
	return true;
}

static inline bool io_alloc_req_refill(struct io_ring_ctx *ctx)
{
	if (unlikely(io_req_cache_empty(ctx)))
		return __io_alloc_req_refill(ctx);
	return true;
}

static inline struct io_kiocb *io_alloc_req(struct io_ring_ctx *ctx)
{
	struct io_wq_work_node *node;

	node = wq_stack_extract(&ctx->submit_state.free_list);
	return container_of(node, struct io_kiocb, comp_list);
}

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

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

	if (unlikely(flags & IO_REQ_CLEAN_FLAGS))
		io_clean_op(req);
	if (!(flags & REQ_F_FIXED_FILE))
		io_put_file(req->file);
}

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

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

	spin_lock(&ctx->completion_lock);
	wq_list_add_head(&req->comp_list, &ctx->locked_free_list);
	ctx->locked_free_nr++;
	spin_unlock(&ctx->completion_lock);
}

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 struct io_kiocb *io_disarm_linked_timeout(struct io_kiocb *req)
	__must_hold(&req->ctx->completion_lock)
	__must_hold(&req->ctx->timeout_lock)
{
	struct io_kiocb *link = req->link;

	if (link && link->opcode == IORING_OP_LINK_TIMEOUT) {
		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) {
			list_del(&link->timeout.list);
			return link;
		}
	}
	return NULL;
}

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

	req->link = NULL;
	while (link) {
		long res = -ECANCELED;

		if (link->flags & REQ_F_FAIL)
			res = link->cqe.res;

		nxt = link->link;
		link->link = NULL;

		trace_io_uring_fail_link(req->ctx, req, req->cqe.user_data,
					req->opcode, link);

		if (ignore_cqes)
			link->flags |= REQ_F_CQE_SKIP;
		else
			link->flags &= ~REQ_F_CQE_SKIP;
		__io_req_complete_post(link, res, 0);
		link = nxt;
	}
}

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

	if (req->flags & REQ_F_ARM_LTIMEOUT) {
		link = req->link;
		req->flags &= ~REQ_F_ARM_LTIMEOUT;
		if (link && link->opcode == IORING_OP_LINK_TIMEOUT) {
			io_remove_next_linked(req);
			io_req_tw_post_queue(link, -ECANCELED, 0);
			posted = true;
		}
	} else if (req->flags & REQ_F_LINK_TIMEOUT) {
		struct io_ring_ctx *ctx = req->ctx;

		spin_lock_irq(&ctx->timeout_lock);
		link = io_disarm_linked_timeout(req);
		spin_unlock_irq(&ctx->timeout_lock);
		if (link) {
			posted = true;
			io_req_tw_post_queue(link, -ECANCELED, 0);
		}
	}
	if (unlikely((req->flags & REQ_F_FAIL) &&
		     !(req->flags & REQ_F_HARDLINK))) {
		posted |= (req->link != NULL);
		io_fail_links(req);
	}
	return posted;
}

static void __io_req_find_next_prep(struct io_kiocb *req)
{
	struct io_ring_ctx *ctx = req->ctx;
	bool posted;

	spin_lock(&ctx->completion_lock);
	posted = io_disarm_next(req);
	io_commit_cqring(ctx);
	spin_unlock(&ctx->completion_lock);
	if (posted)
		io_cqring_ev_posted(ctx);
}

static inline 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 (unlikely(req->flags & IO_DISARM_MASK))
		__io_req_find_next_prep(req);
	nxt = req->link;
	req->link = NULL;
	return nxt;
}

static void ctx_flush_and_put(struct io_ring_ctx *ctx, bool *locked)
{
	if (!ctx)
		return;
	if (ctx->flags & IORING_SETUP_TASKRUN_FLAG)
		atomic_andnot(IORING_SQ_TASKRUN, &ctx->rings->sq_flags);
	if (*locked) {
		io_submit_flush_completions(ctx);
		mutex_unlock(&ctx->uring_lock);
		*locked = false;
	}
	percpu_ref_put(&ctx->refs);
}

static inline void ctx_commit_and_unlock(struct io_ring_ctx *ctx)
{
	io_commit_cqring(ctx);
	spin_unlock(&ctx->completion_lock);
	io_cqring_ev_posted(ctx);
}

static void handle_prev_tw_list(struct io_wq_work_node *node,
				struct io_ring_ctx **ctx, bool *uring_locked)
{
	if (*ctx && !*uring_locked)
		spin_lock(&(*ctx)->completion_lock);

	do {
		struct io_wq_work_node *next = node->next;
		struct io_kiocb *req = container_of(node, struct io_kiocb,
						    io_task_work.node);

		prefetch(container_of(next, struct io_kiocb, io_task_work.node));

		if (req->ctx != *ctx) {
			if (unlikely(!*uring_locked && *ctx))
				ctx_commit_and_unlock(*ctx);

			ctx_flush_and_put(*ctx, uring_locked);
			*ctx = req->ctx;
			/* if not contended, grab and improve batching */
			*uring_locked = mutex_trylock(&(*ctx)->uring_lock);
			percpu_ref_get(&(*ctx)->refs);
			if (unlikely(!*uring_locked))
				spin_lock(&(*ctx)->completion_lock);
		}
		if (likely(*uring_locked))
			req->io_task_work.func(req, uring_locked);
		else
			__io_req_complete_post(req, req->cqe.res,
						io_put_kbuf_comp(req));
		node = next;
	} while (node);

	if (unlikely(!*uring_locked))
		ctx_commit_and_unlock(*ctx);
}

static void handle_tw_list(struct io_wq_work_node *node,
			   struct io_ring_ctx **ctx, bool *locked)
{
	do {
		struct io_wq_work_node *next = node->next;
		struct io_kiocb *req = container_of(node, struct io_kiocb,
						    io_task_work.node);

		prefetch(container_of(next, struct io_kiocb, io_task_work.node));

		if (req->ctx != *ctx) {
			ctx_flush_and_put(*ctx, locked);
			*ctx = req->ctx;
			/* if not contended, grab and improve batching */
			*locked = mutex_trylock(&(*ctx)->uring_lock);
			percpu_ref_get(&(*ctx)->refs);
		}
		req->io_task_work.func(req, locked);
		node = next;
	} while (node);
}

static void tctx_task_work(struct callback_head *cb)
{
	bool uring_locked = false;
	struct io_ring_ctx *ctx = NULL;
	struct io_uring_task *tctx = container_of(cb, struct io_uring_task,
						  task_work);

	while (1) {
		struct io_wq_work_node *node1, *node2;

		spin_lock_irq(&tctx->task_lock);
		node1 = tctx->prio_task_list.first;
		node2 = tctx->task_list.first;
		INIT_WQ_LIST(&tctx->task_list);
		INIT_WQ_LIST(&tctx->prio_task_list);
		if (!node2 && !node1)
			tctx->task_running = false;
		spin_unlock_irq(&tctx->task_lock);
		if (!node2 && !node1)
			break;

		if (node1)
			handle_prev_tw_list(node1, &ctx, &uring_locked);
		if (node2)
			handle_tw_list(node2, &ctx, &uring_locked);
		cond_resched();

		if (data_race(!tctx->task_list.first) &&
		    data_race(!tctx->prio_task_list.first) && uring_locked)
			io_submit_flush_completions(ctx);
	}

	ctx_flush_and_put(ctx, &uring_locked);

	/* relaxed read is enough as only the task itself sets ->in_idle */
	if (unlikely(atomic_read(&tctx->in_idle)))
		io_uring_drop_tctx_refs(current);
}

static void __io_req_task_work_add(struct io_kiocb *req,
				   struct io_uring_task *tctx,
				   struct io_wq_work_list *list)
{
	struct io_ring_ctx *ctx = req->ctx;
	struct io_wq_work_node *node;
	unsigned long flags;
	bool running;

	spin_lock_irqsave(&tctx->task_lock, flags);
	wq_list_add_tail(&req->io_task_work.node, list);
	running = tctx->task_running;
	if (!running)
		tctx->task_running = true;
	spin_unlock_irqrestore(&tctx->task_lock, flags);

	/* task_work already pending, we're done */
	if (running)
		return;

	if (ctx->flags & IORING_SETUP_TASKRUN_FLAG)
		atomic_or(IORING_SQ_TASKRUN, &ctx->rings->sq_flags);

	if (likely(!task_work_add(req->task, &tctx->task_work, ctx->notify_method)))
		return;

	spin_lock_irqsave(&tctx->task_lock, flags);
	tctx->task_running = false;
	node = wq_list_merge(&tctx->prio_task_list, &tctx->task_list);
	spin_unlock_irqrestore(&tctx->task_lock, flags);

	while (node) {
		req = container_of(node, struct io_kiocb, io_task_work.node);
		node = node->next;
		if (llist_add(&req->io_task_work.fallback_node,
			      &req->ctx->fallback_llist))
			schedule_delayed_work(&req->ctx->fallback_work, 1);
	}
}

static void io_req_task_work_add(struct io_kiocb *req)
{
	struct io_uring_task *tctx = req->task->io_uring;

	__io_req_task_work_add(req, tctx, &tctx->task_list);
}

static void io_req_task_prio_work_add(struct io_kiocb *req)
{
	struct io_uring_task *tctx = req->task->io_uring;

	if (req->ctx->flags & IORING_SETUP_SQPOLL)
		__io_req_task_work_add(req, tctx, &tctx->prio_task_list);
	else
		__io_req_task_work_add(req, tctx, &tctx->task_list);
}

static void io_req_tw_post(struct io_kiocb *req, bool *locked)
{
	io_req_complete_post(req, req->cqe.res, req->cqe.flags);
}

static void io_req_tw_post_queue(struct io_kiocb *req, s32 res, u32 cflags)
{
	req->cqe.res = res;
	req->cqe.flags = cflags;
	req->io_task_work.func = io_req_tw_post;
	io_req_task_work_add(req);
}

static void io_req_task_cancel(struct io_kiocb *req, bool *locked)
{
	/* not needed for normal modes, but SQPOLL depends on it */
	io_tw_lock(req->ctx, locked);
	io_req_complete_failed(req, req->cqe.res);
}

static void io_req_task_submit(struct io_kiocb *req, bool *locked)
{
	io_tw_lock(req->ctx, locked);
	/* req->task == current here, checking PF_EXITING is safe */
	if (likely(!(req->task->flags & PF_EXITING)))
		io_queue_sqe(req);
	else
		io_req_complete_failed(req, -EFAULT);
}

static void io_req_task_queue_fail(struct io_kiocb *req, int ret)
{
	req->cqe.res = ret;
	req->io_task_work.func = io_req_task_cancel;
	io_req_task_work_add(req);
}

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

static void io_req_task_queue_reissue(struct io_kiocb *req)
{
	req->io_task_work.func = io_queue_iowq;
	io_req_task_work_add(req);
}

static 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_batch_list(struct io_ring_ctx *ctx,
				struct io_wq_work_node *node)
	__must_hold(&ctx->uring_lock)
{
	struct task_struct *task = NULL;
	int task_refs = 0;

	do {
		struct io_kiocb *req = container_of(node, struct io_kiocb,
						    comp_list);

		if (unlikely(req->flags & IO_REQ_CLEAN_SLOW_FLAGS)) {
			if (req->flags & REQ_F_REFCOUNT) {
				node = req->comp_list.next;
				if (!req_ref_put_and_test(req))
					continue;
			}
			if ((req->flags & REQ_F_POLLED) && req->apoll) {
				struct async_poll *apoll = req->apoll;

				if (apoll->double_poll)
					kfree(apoll->double_poll);
				list_add(&apoll->poll.wait.entry,
						&ctx->apoll_cache);
				req->flags &= ~REQ_F_POLLED;
			}
			if (req->flags & IO_REQ_LINK_FLAGS)
				io_queue_next(req);
			if (unlikely(req->flags & IO_REQ_CLEAN_FLAGS))
				io_clean_op(req);
		}
		if (!(req->flags & REQ_F_FIXED_FILE))
			io_put_file(req->file);

		io_req_put_rsrc_locked(req, ctx);

		if (req->task != task) {
			if (task)
				io_put_task(task, task_refs);
			task = req->task;
			task_refs = 0;
		}
		task_refs++;
		node = req->comp_list.next;
		io_req_add_to_cache(req, ctx);
	} while (node);

	if (task)
		io_put_task(task, task_refs);
}

static void __io_submit_flush_completions(struct io_ring_ctx *ctx)
	__must_hold(&ctx->uring_lock)
{
	struct io_wq_work_node *node, *prev;
	struct io_submit_state *state = &ctx->submit_state;

	if (state->flush_cqes) {
		spin_lock(&ctx->completion_lock);
		wq_list_for_each(node, prev, &state->compl_reqs) {
			struct io_kiocb *req = container_of(node, struct io_kiocb,
						    comp_list);

			if (!(req->flags & REQ_F_CQE_SKIP))
				__io_fill_cqe_req(ctx, req);
		}

		io_commit_cqring(ctx);
		spin_unlock(&ctx->completion_lock);
		io_cqring_ev_posted(ctx);
		state->flush_cqes = false;
	}

	io_free_batch_list(ctx, state->compl_reqs.first);
	INIT_WQ_LIST(&state->compl_reqs);
}

/*
 * 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)) {
		if (unlikely(req->flags & IO_REQ_LINK_FLAGS))
			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_queue_next(req);
		io_free_req(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 inline bool io_run_task_work(void)
{
	if (test_thread_flag(TIF_NOTIFY_SIGNAL) || task_work_pending(current)) {
		__set_current_state(TASK_RUNNING);
		clear_notify_signal();
		if (task_work_pending(current))
			task_work_run();
		return true;
	}

	return false;
}

static int io_do_iopoll(struct io_ring_ctx *ctx, bool force_nonspin)
{
	struct io_wq_work_node *pos, *start, *prev;
	unsigned int poll_flags = BLK_POLL_NOSLEEP;
	DEFINE_IO_COMP_BATCH(iob);
	int nr_events = 0;

	/*
	 * Only spin for completions if we don't have multiple devices hanging
	 * off our complete list.
	 */
	if (ctx->poll_multi_queue || force_nonspin)
		poll_flags |= BLK_POLL_ONESHOT;

	wq_list_for_each(pos, start, &ctx->iopoll_list) {
		struct io_kiocb *req = container_of(pos, struct io_kiocb, comp_list);
		struct kiocb *kiocb = &req->rw.kiocb;
		int ret;

		/*
		 * 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))
			break;

		ret = kiocb->ki_filp->f_op->iopoll(kiocb, &iob, poll_flags);
		if (unlikely(ret < 0))
			return ret;
		else if (ret)
			poll_flags |= BLK_POLL_ONESHOT;

		/* iopoll may have completed current req */
		if (!rq_list_empty(iob.req_list) ||
		    READ_ONCE(req->iopoll_completed))
			break;
	}

	if (!rq_list_empty(iob.req_list))
		iob.complete(&iob);
	else if (!pos)
		return 0;

	prev = start;
	wq_list_for_each_resume(pos, prev) {
		struct io_kiocb *req = container_of(pos, struct io_kiocb, comp_list);

		/* order with io_complete_rw_iopoll(), e.g. ->result updates */
		if (!smp_load_acquire(&req->iopoll_completed))
			break;
		nr_events++;
		if (unlikely(req->flags & REQ_F_CQE_SKIP))
			continue;

		req->cqe.flags = io_put_kbuf(req, 0);
		__io_fill_cqe_req(req->ctx, req);
	}

	if (unlikely(!nr_events))
		return 0;

	io_commit_cqring(ctx);
	io_cqring_ev_posted_iopoll(ctx);
	pos = start ? start->next : ctx->iopoll_list.first;
	wq_list_cut(&ctx->iopoll_list, prev, start);
	io_free_batch_list(ctx, pos);
	return nr_events;
}

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

	mutex_lock(&ctx->uring_lock);
	while (!wq_list_empty(&ctx->iopoll_list)) {
		/* let it sleep and repeat later if can't complete a request */
		if (io_do_iopoll(ctx, true) == 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;
	unsigned long check_cq;

	/*
	 * 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).
	 */
	check_cq = READ_ONCE(ctx->check_cq);
	if (check_cq & BIT(IO_CHECK_CQ_OVERFLOW_BIT))
		__io_cqring_overflow_flush(ctx, false);
	if (io_cqring_events(ctx))
		return 0;

	/*
	 * Similarly do not spin if we have not informed the user of any
	 * dropped CQE.
	 */
	if (unlikely(check_cq & BIT(IO_CHECK_CQ_DROPPED_BIT)))
		return -EBADR;

	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 (wq_list_empty(&ctx->iopoll_list)) {
			u32 tail = ctx->cached_cq_tail;

			mutex_unlock(&ctx->uring_lock);
			io_run_task_work();
			mutex_lock(&ctx->uring_lock);

			/* some requests don't go through iopoll_list */
			if (tail != ctx->cached_cq_tail ||
			    wq_list_empty(&ctx->iopoll_list))
				break;
		}
		ret = io_do_iopoll(ctx, !min);
		if (ret < 0)
			break;
		nr_events += ret;
		ret = 0;
	} while (nr_events < min && !need_resched());

	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 (!req_has_async_data(req))
		return !io_req_prep_async(req);
	iov_iter_restore(&rw->s.iter, &rw->s.iter_state);
	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;
	/*
	 * Play it safe and assume not safe to re-import and reissue if we're
	 * not in the original thread group (or in task context).
	 */
	if (!same_thread_group(req->task, current) || !in_task())
		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 bool __io_complete_rw_common(struct io_kiocb *req, long res)
{
	if (req->rw.kiocb.ki_flags & IOCB_WRITE) {
		kiocb_end_write(req);
		fsnotify_modify(req->file);
	} else {
		fsnotify_access(req->file);
	}
	if (unlikely(res != req->cqe.res)) {
		if ((res == -EAGAIN || res == -EOPNOTSUPP) &&
		    io_rw_should_reissue(req)) {
			req->flags |= REQ_F_REISSUE | REQ_F_PARTIAL_IO;
			return true;
		}
		req_set_fail(req);
		req->cqe.res = res;
	}
	return false;
}

static inline void io_req_task_complete(struct io_kiocb *req, bool *locked)
{
	int res = req->cqe.res;

	if (*locked) {
		io_req_complete_state(req, res, io_put_kbuf(req, 0));
		io_req_add_compl_list(req);
	} else {
		io_req_complete_post(req, res,
					io_put_kbuf(req, IO_URING_F_UNLOCKED));
	}
}

static void __io_complete_rw(struct io_kiocb *req, long res,
			     unsigned int issue_flags)
{
	if (__io_complete_rw_common(req, res))
		return;
	__io_req_complete(req, issue_flags, req->cqe.res,
				io_put_kbuf(req, issue_flags));
}

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

	if (__io_complete_rw_common(req, res))
		return;
	req->cqe.res = res;
	req->io_task_work.func = io_req_task_complete;
	io_req_task_prio_work_add(req);
}

static void io_complete_rw_iopoll(struct kiocb *kiocb, long res)
{
	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->cqe.res)) {
		if (res == -EAGAIN && io_rw_should_reissue(req)) {
			req->flags |= REQ_F_REISSUE | REQ_F_PARTIAL_IO;
			return;
		}
		req->cqe.res = res;
	}

	/* order with io_iopoll_complete() checking ->iopoll_completed */
	smp_store_release(&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, unsigned int issue_flags)
{
	struct io_ring_ctx *ctx = req->ctx;
	const bool needs_lock = issue_flags & IO_URING_F_UNLOCKED;

	/* workqueue context doesn't hold uring_lock, grab it now */
	if (unlikely(needs_lock))
		mutex_lock(&ctx->uring_lock);

	/*
	 * 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 (wq_list_empty(&ctx->iopoll_list)) {
		ctx->poll_multi_queue = false;
	} else if (!ctx->poll_multi_queue) {
		struct io_kiocb *list_req;

		list_req = container_of(ctx->iopoll_list.first, struct io_kiocb,
					comp_list);
		if (list_req->file != req->file)
			ctx->poll_multi_queue = 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))
		wq_list_add_head(&req->comp_list, &ctx->iopoll_list);
	else
		wq_list_add_tail(&req->comp_list, &ctx->iopoll_list);

	if (unlikely(needs_lock)) {
		/*
		 * If IORING_SETUP_SQPOLL is enabled, sqes are either handle
		 * 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 ((ctx->flags & IORING_SETUP_SQPOLL) &&
		    wq_has_sleeper(&ctx->sq_data->wait))
			wake_up(&ctx->sq_data->wait);

		mutex_unlock(&ctx->uring_lock);
	}
}

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_nowait(struct file *file, umode_t 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_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;
	return file->f_mode & FMODE_NOWAIT;
}

/*
 * 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 unsigned int io_file_get_flags(struct file *file)
{
	umode_t mode = file_inode(file)->i_mode;
	unsigned int res = 0;

	if (S_ISREG(mode))
		res |= FFS_ISREG;
	if (__io_file_supports_nowait(file, mode))
		res |= FFS_NOWAIT;
	if (io_file_need_scm(file))
		res |= FFS_SCM;
	return res;
}

static inline bool io_file_supports_nowait(struct io_kiocb *req)
{
	return req->flags & REQ_F_SUPPORT_NOWAIT;
}

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

	kiocb->ki_pos = READ_ONCE(sqe->off);
	/* used for fixed read/write too - just read unconditionally */
	req->buf_index = READ_ONCE(sqe->buf_index);

	if (req->opcode == IORING_OP_READ_FIXED ||
	    req->opcode == IORING_OP_WRITE_FIXED) {
		struct io_ring_ctx *ctx = req->ctx;
		u16 index;

		if (unlikely(req->buf_index >= ctx->nr_user_bufs))
			return -EFAULT;
		index = array_index_nospec(req->buf_index, ctx->nr_user_bufs);
		req->imu = ctx->user_bufs[index];
		io_req_set_rsrc_node(req, ctx, 0);
	}

	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();
	}

	req->rw.addr = READ_ONCE(sqe->addr);
	req->rw.len = READ_ONCE(sqe->len);
	req->rw.flags = READ_ONCE(sqe->rw_flags);
	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);
	}
}

static inline loff_t *io_kiocb_update_pos(struct io_kiocb *req)
{
	struct kiocb *kiocb = &req->rw.kiocb;

	if (kiocb->ki_pos != -1)
		return &kiocb->ki_pos;

	if (!(req->file->f_mode & FMODE_STREAM)) {
		req->flags |= REQ_F_CUR_POS;
		kiocb->ki_pos = req->file->f_pos;
		return &kiocb->ki_pos;
	}

	kiocb->ki_pos = 0;
	return NULL;
}

static void kiocb_done(struct io_kiocb *req, ssize_t ret,
		       unsigned int issue_flags)
{
	struct io_async_rw *io = req->async_data;

	/* add previously done IO, if any */
	if (req_has_async_data(req) && 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 = req->rw.kiocb.ki_pos;
	if (ret >= 0 && (req->rw.kiocb.ki_complete == io_complete_rw))
		__io_complete_rw(req, ret, issue_flags);
	else
		io_rw_done(&req->rw.kiocb, ret);

	if (req->flags & REQ_F_REISSUE) {
		req->flags &= ~REQ_F_REISSUE;
		if (io_resubmit_prep(req))
			io_req_task_queue_reissue(req);
		else
			io_req_task_queue_fail(req, ret);
	}
}

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,
			   unsigned int issue_flags)
{
	if (WARN_ON_ONCE(!req->imu))
		return -EFAULT;
	return __io_import_fixed(req, rw, iter, req->imu);
}

static int io_buffer_add_list(struct io_ring_ctx *ctx,
			      struct io_buffer_list *bl, unsigned int bgid)
{
	bl->bgid = bgid;
	if (bgid < BGID_ARRAY)
		return 0;

	return xa_err(xa_store(&ctx->io_bl_xa, bgid, bl, GFP_KERNEL));
}

static void __user *io_provided_buffer_select(struct io_kiocb *req, size_t *len,
					      struct io_buffer_list *bl)
{
	if (!list_empty(&bl->buf_list)) {
		struct io_buffer *kbuf;

		kbuf = list_first_entry(&bl->buf_list, struct io_buffer, list);
		list_del(&kbuf->list);
		if (*len > kbuf->len)
			*len = kbuf->len;
		req->flags |= REQ_F_BUFFER_SELECTED;
		req->kbuf = kbuf;
		req->buf_index = kbuf->bid;
		return u64_to_user_ptr(kbuf->addr);
	}
	return NULL;
}

static void __user *io_ring_buffer_select(struct io_kiocb *req, size_t *len,
					  struct io_buffer_list *bl,
					  unsigned int issue_flags)
{
	struct io_uring_buf_ring *br = bl->buf_ring;
	struct io_uring_buf *buf;
	__u16 head = bl->head;

	if (unlikely(smp_load_acquire(&br->tail) == head))
		return NULL;

	head &= bl->mask;
	if (head < IO_BUFFER_LIST_BUF_PER_PAGE) {
		buf = &br->bufs[head];
	} else {
		int off = head & (IO_BUFFER_LIST_BUF_PER_PAGE - 1);
		int index = head / IO_BUFFER_LIST_BUF_PER_PAGE;
		buf = page_address(bl->buf_pages[index]);
		buf += off;
	}
	if (*len > buf->len)
		*len = buf->len;
	req->flags |= REQ_F_BUFFER_RING;
	req->buf_list = bl;
	req->buf_index = buf->bid;

	if (issue_flags & IO_URING_F_UNLOCKED || !file_can_poll(req->file)) {
		/*
		 * If we came in unlocked, we have no choice but to consume the
		 * buffer here. This does mean it'll be pinned until the IO
		 * completes. But coming in unlocked means we're in io-wq
		 * context, hence there should be no further retry. For the
		 * locked case, the caller must ensure to call the commit when
		 * the transfer completes (or if we get -EAGAIN and must poll
		 * or retry).
		 */
		req->buf_list = NULL;
		bl->head++;
	}
	return u64_to_user_ptr(buf->addr);
}

static void __user *io_buffer_select(struct io_kiocb *req, size_t *len,
				     unsigned int issue_flags)
{
	struct io_ring_ctx *ctx = req->ctx;
	struct io_buffer_list *bl;
	void __user *ret = NULL;

	io_ring_submit_lock(req->ctx, issue_flags);

	bl = io_buffer_get_list(ctx, req->buf_index);
	if (likely(bl)) {
		if (bl->buf_nr_pages)
			ret = io_ring_buffer_select(req, len, bl, issue_flags);
		else
			ret = io_provided_buffer_select(req, len, bl);
	}
	io_ring_submit_unlock(req->ctx, issue_flags);
	return ret;
}

#ifdef CONFIG_COMPAT
static ssize_t io_compat_import(struct io_kiocb *req, struct iovec *iov,
				unsigned int issue_flags)
{
	struct compat_iovec __user *uiov;
	compat_ssize_t clen;
	void __user *buf;
	size_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_buffer_select(req, &len, issue_flags);
	if (!buf)
		return -ENOBUFS;
	req->rw.addr = (unsigned long) buf;
	iov[0].iov_base = buf;
	req->rw.len = 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,
				      unsigned int issue_flags)
{
	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_buffer_select(req, &len, issue_flags);
	if (!buf)
		return -ENOBUFS;
	req->rw.addr = (unsigned long) buf;
	iov[0].iov_base = buf;
	req->rw.len = iov[0].iov_len = len;
	return 0;
}

static ssize_t io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov,
				    unsigned int issue_flags)
{
	if (req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)) {
		iov[0].iov_base = u64_to_user_ptr(req->rw.addr);
		iov[0].iov_len = req->rw.len;
		return 0;
	}
	if (req->rw.len != 1)
		return -EINVAL;

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

	return __io_iov_buffer_select(req, iov, issue_flags);
}

static inline bool io_do_buffer_select(struct io_kiocb *req)
{
	if (!(req->flags & REQ_F_BUFFER_SELECT))
		return false;
	return !(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING));
}

static struct iovec *__io_import_iovec(int rw, struct io_kiocb *req,
				       struct io_rw_state *s,
				       unsigned int issue_flags)
{
	struct iov_iter *iter = &s->iter;
	u8 opcode = req->opcode;
	struct iovec *iovec;
	void __user *buf;
	size_t sqe_len;
	ssize_t ret;

	if (opcode == IORING_OP_READ_FIXED || opcode == IORING_OP_WRITE_FIXED) {
		ret = io_import_fixed(req, rw, iter, issue_flags);
		if (ret)
			return ERR_PTR(ret);
		return NULL;
	}

	buf = u64_to_user_ptr(req->rw.addr);
	sqe_len = req->rw.len;

	if (opcode == IORING_OP_READ || opcode == IORING_OP_WRITE) {
		if (io_do_buffer_select(req)) {
			buf = io_buffer_select(req, &sqe_len, issue_flags);
			if (!buf)
				return ERR_PTR(-ENOBUFS);
			req->rw.addr = (unsigned long) buf;
			req->rw.len = sqe_len;
		}

		ret = import_single_range(rw, buf, sqe_len, s->fast_iov, iter);
		if (ret)
			return ERR_PTR(ret);
		return NULL;
	}

	iovec = s->fast_iov;
	if (req->flags & REQ_F_BUFFER_SELECT) {
		ret = io_iov_buffer_select(req, iovec, issue_flags);
		if (ret)
			return ERR_PTR(ret);
		iov_iter_init(iter, rw, iovec, 1, iovec->iov_len);
		return NULL;
	}

	ret = __import_iovec(rw, buf, sqe_len, UIO_FASTIOV, &iovec, iter,
			      req->ctx->compat);
	if (unlikely(ret < 0))
		return ERR_PTR(ret);
	return iovec;
}

static inline int io_import_iovec(int rw, struct io_kiocb *req,
				  struct iovec **iovec, struct io_rw_state *s,
				  unsigned int issue_flags)
{
	*iovec = __io_import_iovec(rw, req, s, issue_flags);
	if (unlikely(IS_ERR(*iovec)))
		return PTR_ERR(*iovec);

	iov_iter_save_state(&s->iter, &s->iter_state);
	return 0;
}

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;
	loff_t *ppos;

	/*
	 * 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) &&
	    !(kiocb->ki_filp->f_flags & O_NONBLOCK))
		return -EAGAIN;

	ppos = io_kiocb_ppos(kiocb);

	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, ppos);
		} else {
			nr = file->f_op->write(file, iovec.iov_base,
					       iovec.iov_len, ppos);
		}

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

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

static inline bool 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);
	if (req->async_data) {
		req->flags |= REQ_F_ASYNC_DATA;
		return false;
	}
	return true;
}

static int io_setup_async_rw(struct io_kiocb *req, const struct iovec *iovec,
			     struct io_rw_state *s, bool force)
{
	if (!force && !io_op_defs[req->opcode].needs_async_setup)
		return 0;
	if (!req_has_async_data(req)) {
		struct io_async_rw *iorw;

		if (io_alloc_async_data(req)) {
			kfree(iovec);
			return -ENOMEM;
		}

		io_req_map_rw(req, iovec, s->fast_iov, &s->iter);
		iorw = req->async_data;
		/* we've copied and mapped the iter, ensure state is saved */
		iov_iter_save_state(&iorw->s.iter, &iorw->s.iter_state);
	}
	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;
	int ret;

	/* submission path, ->uring_lock should already be taken */
	ret = io_import_iovec(rw, req, &iov, &iorw->s, 0);
	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_readv_prep_async(struct io_kiocb *req)
{
	return io_rw_prep_async(req, READ);
}

static int io_writev_prep_async(struct io_kiocb *req)
{
	return io_rw_prep_async(req, WRITE);
}

/*
 * This is our waitqueue callback handler, registered through __folio_lock_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);
	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 inline int io_iter_do_read(struct io_kiocb *req, struct iov_iter *iter)
{
	if (likely(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 bool need_read_all(struct io_kiocb *req)
{
	return req->flags & REQ_F_ISREG ||
		S_ISBLK(file_inode(req->file)->i_mode);
}

static int io_rw_init_file(struct io_kiocb *req, fmode_t mode)
{
	struct kiocb *kiocb = &req->rw.kiocb;
	struct io_ring_ctx *ctx = req->ctx;
	struct file *file = req->file;
	int ret;

	if (unlikely(!file || !(file->f_mode & mode)))
		return -EBADF;

	if (!io_req_ffs_set(req))
		req->flags |= io_file_get_flags(file) << REQ_F_SUPPORT_NOWAIT_BIT;

	kiocb->ki_flags = iocb_flags(file);
	ret = kiocb_set_rw_flags(kiocb, req->rw.flags);
	if (unlikely(ret))
		return ret;

	/*
	 * If the file is marked O_NONBLOCK, still allow retry for it if it
	 * supports async. Otherwise it's impossible to use O_NONBLOCK files
	 * reliably. If not, or it IOCB_NOWAIT is set, don't retry.
	 */
	if ((kiocb->ki_flags & IOCB_NOWAIT) ||
	    ((file->f_flags & O_NONBLOCK) && !io_file_supports_nowait(req)))
		req->flags |= REQ_F_NOWAIT;

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

		kiocb->private = NULL;
		kiocb->ki_flags |= IOCB_HIPRI | IOCB_ALLOC_CACHE;
		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;
	}

	return 0;
}

static int io_read(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_rw_state __s, *s = &__s;
	struct iovec *iovec;
	struct kiocb *kiocb = &req->rw.kiocb;
	bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
	struct io_async_rw *rw;
	ssize_t ret, ret2;
	loff_t *ppos;

	if (!req_has_async_data(req)) {
		ret = io_import_iovec(READ, req, &iovec, s, issue_flags);
		if (unlikely(ret < 0))
			return ret;
	} else {
		rw = req->async_data;
		s = &rw->s;

		/*
		 * Safe and required to re-import if we're using provided
		 * buffers, as we dropped the selected one before retry.
		 */
		if (io_do_buffer_select(req)) {
			ret = io_import_iovec(READ, req, &iovec, s, issue_flags);
			if (unlikely(ret < 0))
				return ret;
		}

		/*
		 * We come here from an earlier attempt, restore our state to
		 * match in case it doesn't. It's cheap enough that we don't
		 * need to make this conditional.
		 */
		iov_iter_restore(&s->iter, &s->iter_state);
		iovec = NULL;
	}
	ret = io_rw_init_file(req, FMODE_READ);
	if (unlikely(ret)) {
		kfree(iovec);
		return ret;
	}
	req->cqe.res = iov_iter_count(&s->iter);

	if (force_nonblock) {
		/* If the file doesn't support async, just async punt */
		if (unlikely(!io_file_supports_nowait(req))) {
			ret = io_setup_async_rw(req, iovec, s, true);
			return ret ?: -EAGAIN;
		}
		kiocb->ki_flags |= IOCB_NOWAIT;
	} else {
		/* Ensure we clear previously set non-block flag */
		kiocb->ki_flags &= ~IOCB_NOWAIT;
	}

	ppos = io_kiocb_update_pos(req);

	ret = rw_verify_area(READ, req->file, ppos, req->cqe.res);
	if (unlikely(ret)) {
		kfree(iovec);
		return ret;
	}

	ret = io_iter_do_read(req, &s->iter);

	if (ret == -EAGAIN || (req->flags & REQ_F_REISSUE)) {
		req->flags &= ~REQ_F_REISSUE;
		/* if we can poll, just do that */
		if (req->opcode == IORING_OP_READ && file_can_poll(req->file))
			return -EAGAIN;
		/* 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;
		ret = 0;
	} else if (ret == -EIOCBQUEUED) {
		goto out_free;
	} else if (ret == req->cqe.res || ret <= 0 || !force_nonblock ||
		   (req->flags & REQ_F_NOWAIT) || !need_read_all(req)) {
		/* read all, failed, already did sync or don't want to retry */
		goto done;
	}

	/*
	 * Don't depend on the iter state matching what was consumed, or being
	 * untouched in case of error. Restore it and we'll advance it
	 * manually if we need to.
	 */
	iov_iter_restore(&s->iter, &s->iter_state);

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

	iovec = NULL;
	rw = req->async_data;
	s = &rw->s;
	/*
	 * Now use our persistent iterator and state, if we aren't already.
	 * We've restored and mapped the iter to match.
	 */

	do {
		/*
		 * We end up here because of a partial read, either from
		 * above or inside this loop. Advance the iter by the bytes
		 * that were consumed.
		 */
		iov_iter_advance(&s->iter, ret);
		if (!iov_iter_count(&s->iter))
			break;
		rw->bytes_done += ret;
		iov_iter_save_state(&s->iter, &s->iter_state);

		/* 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, &s->iter);
		if (ret == -EIOCBQUEUED)
			return 0;
		/* we got some bytes, but not all. retry. */
		kiocb->ki_flags &= ~IOCB_WAITQ;
		iov_iter_restore(&s->iter, &s->iter_state);
	} while (ret > 0);
done:
	kiocb_done(req, 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(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_rw_state __s, *s = &__s;
	struct iovec *iovec;
	struct kiocb *kiocb = &req->rw.kiocb;
	bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
	ssize_t ret, ret2;
	loff_t *ppos;

	if (!req_has_async_data(req)) {
		ret = io_import_iovec(WRITE, req, &iovec, s, issue_flags);
		if (unlikely(ret < 0))
			return ret;
	} else {
		struct io_async_rw *rw = req->async_data;

		s = &rw->s;
		iov_iter_restore(&s->iter, &s->iter_state);
		iovec = NULL;
	}
	ret = io_rw_init_file(req, FMODE_WRITE);
	if (unlikely(ret)) {
		kfree(iovec);
		return ret;
	}
	req->cqe.res = iov_iter_count(&s->iter);

	if (force_nonblock) {
		/* If the file doesn't support async, just async punt */
		if (unlikely(!io_file_supports_nowait(req)))
			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;

		kiocb->ki_flags |= IOCB_NOWAIT;
	} else {
		/* Ensure we clear previously set non-block flag */
		kiocb->ki_flags &= ~IOCB_NOWAIT;
	}

	ppos = io_kiocb_update_pos(req);

	ret = rw_verify_area(WRITE, req->file, ppos, req->cqe.res);
	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 (likely(req->file->f_op->write_iter))
		ret2 = call_write_iter(req->file, kiocb, &s->iter);
	else if (req->file->f_op->write)
		ret2 = loop_rw_iter(WRITE, req, &s->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 (ret2 == -EAGAIN && (req->ctx->flags & IORING_SETUP_IOPOLL))
			goto copy_iov;
done:
		kiocb_done(req, ret2, issue_flags);
	} else {
copy_iov:
		iov_iter_restore(&s->iter, &s->iter_state);
		ret = io_setup_async_rw(req, iovec, s, 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 (sqe->buf_index || sqe->splice_fd_in)
		return -EINVAL;
	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;
	io_req_complete(req, ret);
	return 0;
}

static inline void __io_xattr_finish(struct io_kiocb *req)
{
	struct io_xattr *ix = &req->xattr;

	if (ix->filename)
		putname(ix->filename);

	kfree(ix->ctx.kname);
	kvfree(ix->ctx.kvalue);
}

static void io_xattr_finish(struct io_kiocb *req, int ret)
{
	req->flags &= ~REQ_F_NEED_CLEANUP;

	__io_xattr_finish(req);
	io_req_complete(req, ret);
}

static int __io_getxattr_prep(struct io_kiocb *req,
			      const struct io_uring_sqe *sqe)
{
	struct io_xattr *ix = &req->xattr;
	const char __user *name;
	int ret;

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

	ix->filename = NULL;
	ix->ctx.kvalue = NULL;
	name = u64_to_user_ptr(READ_ONCE(sqe->addr));
	ix->ctx.cvalue = u64_to_user_ptr(READ_ONCE(sqe->addr2));
	ix->ctx.size = READ_ONCE(sqe->len);
	ix->ctx.flags = READ_ONCE(sqe->xattr_flags);

	if (ix->ctx.flags)
		return -EINVAL;

	ix->ctx.kname = kmalloc(sizeof(*ix->ctx.kname), GFP_KERNEL);
	if (!ix->ctx.kname)
		return -ENOMEM;

	ret = strncpy_from_user(ix->ctx.kname->name, name,
				sizeof(ix->ctx.kname->name));
	if (!ret || ret == sizeof(ix->ctx.kname->name))
		ret = -ERANGE;
	if (ret < 0) {
		kfree(ix->ctx.kname);
		return ret;
	}

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

static int io_fgetxattr_prep(struct io_kiocb *req,
			     const struct io_uring_sqe *sqe)
{
	return __io_getxattr_prep(req, sqe);
}

static int io_getxattr_prep(struct io_kiocb *req,
			    const struct io_uring_sqe *sqe)
{
	struct io_xattr *ix = &req->xattr;
	const char __user *path;
	int ret;

	ret = __io_getxattr_prep(req, sqe);
	if (ret)
		return ret;

	path = u64_to_user_ptr(READ_ONCE(sqe->addr3));

	ix->filename = getname_flags(path, LOOKUP_FOLLOW, NULL);
	if (IS_ERR(ix->filename)) {
		ret = PTR_ERR(ix->filename);
		ix->filename = NULL;
	}

	return ret;
}

static int io_fgetxattr(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_xattr *ix = &req->xattr;
	int ret;

	if (issue_flags & IO_URING_F_NONBLOCK)
		return -EAGAIN;

	ret = do_getxattr(mnt_user_ns(req->file->f_path.mnt),
			req->file->f_path.dentry,
			&ix->ctx);

	io_xattr_finish(req, ret);
	return 0;
}

static int io_getxattr(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_xattr *ix = &req->xattr;
	unsigned int lookup_flags = LOOKUP_FOLLOW;
	struct path path;
	int ret;

	if (issue_flags & IO_URING_F_NONBLOCK)
		return -EAGAIN;

retry:
	ret = filename_lookup(AT_FDCWD, ix->filename, lookup_flags, &path, NULL);
	if (!ret) {
		ret = do_getxattr(mnt_user_ns(path.mnt),
				path.dentry,
				&ix->ctx);

		path_put(&path);
		if (retry_estale(ret, lookup_flags)) {
			lookup_flags |= LOOKUP_REVAL;
			goto retry;
		}
	}

	io_xattr_finish(req, ret);
	return 0;
}

static int __io_setxattr_prep(struct io_kiocb *req,
			const struct io_uring_sqe *sqe)
{
	struct io_xattr *ix = &req->xattr;
	const char __user *name;
	int ret;

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

	ix->filename = NULL;
	name = u64_to_user_ptr(READ_ONCE(sqe->addr));
	ix->ctx.cvalue = u64_to_user_ptr(READ_ONCE(sqe->addr2));
	ix->ctx.kvalue = NULL;
	ix->ctx.size = READ_ONCE(sqe->len);
	ix->ctx.flags = READ_ONCE(sqe->xattr_flags);

	ix->ctx.kname = kmalloc(sizeof(*ix->ctx.kname), GFP_KERNEL);
	if (!ix->ctx.kname)
		return -ENOMEM;

	ret = setxattr_copy(name, &ix->ctx);
	if (ret) {
		kfree(ix->ctx.kname);
		return ret;
	}

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

static int io_setxattr_prep(struct io_kiocb *req,
			const struct io_uring_sqe *sqe)
{
	struct io_xattr *ix = &req->xattr;
	const char __user *path;
	int ret;

	ret = __io_setxattr_prep(req, sqe);
	if (ret)
		return ret;

	path = u64_to_user_ptr(READ_ONCE(sqe->addr3));

	ix->filename = getname_flags(path, LOOKUP_FOLLOW, NULL);
	if (IS_ERR(ix->filename)) {
		ret = PTR_ERR(ix->filename);
		ix->filename = NULL;
	}

	return ret;
}

static int io_fsetxattr_prep(struct io_kiocb *req,
			const struct io_uring_sqe *sqe)
{
	return __io_setxattr_prep(req, sqe);
}

static int __io_setxattr(struct io_kiocb *req, unsigned int issue_flags,
			struct path *path)
{
	struct io_xattr *ix = &req->xattr;
	int ret;

	ret = mnt_want_write(path->mnt);
	if (!ret) {
		ret = do_setxattr(mnt_user_ns(path->mnt), path->dentry, &ix->ctx);
		mnt_drop_write(path->mnt);
	}

	return ret;
}

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

	if (issue_flags & IO_URING_F_NONBLOCK)
		return -EAGAIN;

	ret = __io_setxattr(req, issue_flags, &req->file->f_path);
	io_xattr_finish(req, ret);

	return 0;
}

static int io_setxattr(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_xattr *ix = &req->xattr;
	unsigned int lookup_flags = LOOKUP_FOLLOW;
	struct path path;
	int ret;

	if (issue_flags & IO_URING_F_NONBLOCK)
		return -EAGAIN;

retry:
	ret = filename_lookup(AT_FDCWD, ix->filename, lookup_flags, &path, NULL);
	if (!ret) {
		ret = __io_setxattr(req, issue_flags, &path);
		path_put(&path);
		if (retry_estale(ret, lookup_flags)) {
			lookup_flags |= LOOKUP_REVAL;
			goto retry;
		}
	}

	io_xattr_finish(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 (sqe->off || sqe->len || sqe->buf_index || sqe->splice_fd_in)
		return -EINVAL;
	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;
	io_req_complete(req, ret);
	return 0;
}

static int io_mkdirat_prep(struct io_kiocb *req,
			    const struct io_uring_sqe *sqe)
{
	struct io_mkdir *mkd = &req->mkdir;
	const char __user *fname;

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

	mkd->dfd = READ_ONCE(sqe->fd);
	mkd->mode = READ_ONCE(sqe->len);

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

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

static int io_mkdirat(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_mkdir *mkd = &req->mkdir;
	int ret;

	if (issue_flags & IO_URING_F_NONBLOCK)
		return -EAGAIN;

	ret = do_mkdirat(mkd->dfd, mkd->filename, mkd->mode);

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

static int io_symlinkat_prep(struct io_kiocb *req,
			    const struct io_uring_sqe *sqe)
{
	struct io_symlink *sl = &req->symlink;
	const char __user *oldpath, *newpath;

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

	sl->new_dfd = READ_ONCE(sqe->fd);
	oldpath = u64_to_user_ptr(READ_ONCE(sqe->addr));
	newpath = u64_to_user_ptr(READ_ONCE(sqe->addr2));

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

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

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

static int io_symlinkat(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_symlink *sl = &req->symlink;
	int ret;

	if (issue_flags & IO_URING_F_NONBLOCK)
		return -EAGAIN;

	ret = do_symlinkat(sl->oldpath, sl->new_dfd, sl->newpath);

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

static int io_linkat_prep(struct io_kiocb *req,
			    const struct io_uring_sqe *sqe)
{
	struct io_hardlink *lnk = &req->hardlink;
	const char __user *oldf, *newf;

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

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

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

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

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

static int io_linkat(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_hardlink *lnk = &req->hardlink;
	int ret;

	if (issue_flags & IO_URING_F_NONBLOCK)
		return -EAGAIN;

	ret = do_linkat(lnk->old_dfd, lnk->oldpath, lnk->new_dfd,
				lnk->newpath, lnk->flags);

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

static void io_uring_cmd_work(struct io_kiocb *req, bool *locked)
{
	req->uring_cmd.task_work_cb(&req->uring_cmd);
}

void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd,
			void (*task_work_cb)(struct io_uring_cmd *))
{
	struct io_kiocb *req = container_of(ioucmd, struct io_kiocb, uring_cmd);

	req->uring_cmd.task_work_cb = task_work_cb;
	req->io_task_work.func = io_uring_cmd_work;
	io_req_task_work_add(req);
}
EXPORT_SYMBOL_GPL(io_uring_cmd_complete_in_task);

static inline void io_req_set_cqe32_extra(struct io_kiocb *req,
					  u64 extra1, u64 extra2)
{
	req->extra1 = extra1;
	req->extra2 = extra2;
	req->flags |= REQ_F_CQE32_INIT;
}

/*
 * Called by consumers of io_uring_cmd, if they originally returned
 * -EIOCBQUEUED upon receiving the command.
 */
void io_uring_cmd_done(struct io_uring_cmd *ioucmd, ssize_t ret, ssize_t res2)
{
	struct io_kiocb *req = container_of(ioucmd, struct io_kiocb, uring_cmd);

	if (ret < 0)
		req_set_fail(req);

	if (req->ctx->flags & IORING_SETUP_CQE32)
		io_req_set_cqe32_extra(req, res2, 0);
	io_req_complete(req, ret);
}
EXPORT_SYMBOL_GPL(io_uring_cmd_done);

static int io_uring_cmd_prep_async(struct io_kiocb *req)
{
	size_t cmd_size;

	cmd_size = uring_cmd_pdu_size(req->ctx->flags & IORING_SETUP_SQE128);

	memcpy(req->async_data, req->uring_cmd.cmd, cmd_size);
	return 0;
}

static int io_uring_cmd_prep(struct io_kiocb *req,
			     const struct io_uring_sqe *sqe)
{
	struct io_uring_cmd *ioucmd = &req->uring_cmd;

	if (sqe->rw_flags || sqe->__pad1)
		return -EINVAL;
	ioucmd->cmd = sqe->cmd;
	ioucmd->cmd_op = READ_ONCE(sqe->cmd_op);
	return 0;
}

static int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_uring_cmd *ioucmd = &req->uring_cmd;
	struct io_ring_ctx *ctx = req->ctx;
	struct file *file = req->file;
	int ret;

	if (!req->file->f_op->uring_cmd)
		return -EOPNOTSUPP;

	if (ctx->flags & IORING_SETUP_SQE128)
		issue_flags |= IO_URING_F_SQE128;
	if (ctx->flags & IORING_SETUP_CQE32)
		issue_flags |= IO_URING_F_CQE32;
	if (ctx->flags & IORING_SETUP_IOPOLL)
		issue_flags |= IO_URING_F_IOPOLL;

	if (req_has_async_data(req))
		ioucmd->cmd = req->async_data;

	ret = file->f_op->uring_cmd(ioucmd, issue_flags);
	if (ret == -EAGAIN) {
		if (!req_has_async_data(req)) {
			if (io_alloc_async_data(req))
				return -ENOMEM;
			io_uring_cmd_prep_async(req);
		}
		return -EAGAIN;
	}

	if (ret != -EIOCBQUEUED)
		io_uring_cmd_done(ioucmd, ret, 0);
	return 0;
}

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;

	sp->len = READ_ONCE(sqe->len);
	sp->flags = READ_ONCE(sqe->splice_flags);
	if (unlikely(sp->flags & ~valid_flags))
		return -EINVAL;
	sp->splice_fd_in = READ_ONCE(sqe->splice_fd_in);
	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 *out = sp->file_out;
	unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED;
	struct file *in;
	long ret = 0;

	if (issue_flags & IO_URING_F_NONBLOCK)
		return -EAGAIN;

	if (sp->flags & SPLICE_F_FD_IN_FIXED)
		in = io_file_get_fixed(req, sp->splice_fd_in, issue_flags);
	else
		in = io_file_get_normal(req, sp->splice_fd_in);
	if (!in) {
		ret = -EBADF;
		goto done;
	}

	if (sp->len)
		ret = do_tee(in, out, sp->len, flags);

	if (!(sp->flags & SPLICE_F_FD_IN_FIXED))
		io_put_file(in);
done:
	if (ret != sp->len)
		req_set_fail(req);
	__io_req_complete(req, 0, ret, 0);
	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 *out = sp->file_out;
	unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED;
	loff_t *poff_in, *poff_out;
	struct file *in;
	long ret = 0;

	if (issue_flags & IO_URING_F_NONBLOCK)
		return -EAGAIN;

	if (sp->flags & SPLICE_F_FD_IN_FIXED)
		in = io_file_get_fixed(req, sp->splice_fd_in, issue_flags);
	else
		in = io_file_get_normal(req, sp->splice_fd_in);
	if (!in) {
		ret = -EBADF;
		goto done;
	}

	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);
done:
	if (ret != sp->len)
		req_set_fail(req);
	__io_req_complete(req, 0, ret, 0);
	return 0;
}

static int io_nop_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	return 0;
}

/*
 * IORING_OP_NOP just posts a completion event, nothing else.
 */
static int io_nop(struct io_kiocb *req, unsigned int issue_flags)
{
	__io_req_complete(req, issue_flags, 0, 0);
	return 0;
}

static int io_msg_ring_prep(struct io_kiocb *req,
			    const struct io_uring_sqe *sqe)
{
	if (unlikely(sqe->addr || sqe->rw_flags || sqe->splice_fd_in ||
		     sqe->buf_index || sqe->personality))
		return -EINVAL;

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

static int io_msg_ring(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_ring_ctx *target_ctx;
	struct io_msg *msg = &req->msg;
	bool filled;
	int ret;

	ret = -EBADFD;
	if (req->file->f_op != &io_uring_fops)
		goto done;

	ret = -EOVERFLOW;
	target_ctx = req->file->private_data;

	spin_lock(&target_ctx->completion_lock);
	filled = io_fill_cqe_aux(target_ctx, msg->user_data, msg->len, 0);
	io_commit_cqring(target_ctx);
	spin_unlock(&target_ctx->completion_lock);

	if (filled) {
		io_cqring_ev_posted(target_ctx);
		ret = 0;
	}

done:
	if (ret < 0)
		req_set_fail(req);
	__io_req_complete(req, issue_flags, ret, 0);
	/* put file to avoid an attempt to IOPOLL the req */
	io_put_file(req->file);
	req->file = NULL;
	return 0;
}

static int io_fsync_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	if (unlikely(sqe->addr || sqe->buf_index || sqe->splice_fd_in))
		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);
	io_req_complete(req, ret);
	return 0;
}

static int io_fallocate_prep(struct io_kiocb *req,
			     const struct io_uring_sqe *sqe)
{
	if (sqe->buf_index || sqe->rw_flags || sqe->splice_fd_in)
		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)
		fsnotify_modify(req->file);
	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->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.file_slot = READ_ONCE(sqe->file_index);
	if (req->open.file_slot && (req->open.how.flags & O_CLOEXEC))
		return -EINVAL;

	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 mode = READ_ONCE(sqe->len);
	u64 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;

	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_file_bitmap_get(struct io_ring_ctx *ctx)
{
	struct io_file_table *table = &ctx->file_table;
	unsigned long nr = ctx->nr_user_files;
	int ret;

	do {
		ret = find_next_zero_bit(table->bitmap, nr, table->alloc_hint);
		if (ret != nr)
			return ret;

		if (!table->alloc_hint)
			break;

		nr = table->alloc_hint;
		table->alloc_hint = 0;
	} while (1);

	return -ENFILE;
}

/*
 * Note when io_fixed_fd_install() returns error value, it will ensure
 * fput() is called correspondingly.
 */
static int io_fixed_fd_install(struct io_kiocb *req, unsigned int issue_flags,
			       struct file *file, unsigned int file_slot)
{
	bool alloc_slot = file_slot == IORING_FILE_INDEX_ALLOC;
	struct io_ring_ctx *ctx = req->ctx;
	int ret;

	io_ring_submit_lock(ctx, issue_flags);

	if (alloc_slot) {
		ret = io_file_bitmap_get(ctx);
		if (unlikely(ret < 0))
			goto err;
		file_slot = ret;
	} else {
		file_slot--;
	}

	ret = io_install_fixed_file(req, file, issue_flags, file_slot);
	if (!ret && alloc_slot)
		ret = file_slot;
err:
	io_ring_submit_unlock(ctx, issue_flags);
	if (unlikely(ret < 0))
		fput(file);
	return ret;
}

static int io_openat2(struct io_kiocb *req, unsigned int issue_flags)
{
	struct open_flags op;
	struct file *file;
	bool resolve_nonblock, nonblock_set;
	bool fixed = !!req->open.file_slot;
	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;
	}

	if (!fixed) {
		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)) {
		/*
		 * We could hang on to this 'fd' on retrying, 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.
		 */
		if (!fixed)
			put_unused_fd(ret);

		ret = PTR_ERR(file);
		/* only retry if RESOLVE_CACHED wasn't already set by application */
		if (ret == -EAGAIN &&
		    (!resolve_nonblock && (issue_flags & IO_URING_F_NONBLOCK)))
			return -EAGAIN;
		goto err;
	}

	if ((issue_flags & IO_URING_F_NONBLOCK) && !nonblock_set)
		file->f_flags &= ~O_NONBLOCK;
	fsnotify_open(file);

	if (!fixed)
		fd_install(ret, file);
	else
		ret = io_fixed_fd_install(req, issue_flags, file,
						req->open.file_slot);
err:
	putname(req->open.filename);
	req->flags &= ~REQ_F_NEED_CLEANUP;
	if (ret < 0)
		req_set_fail(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->rw_flags || sqe->addr || sqe->len || sqe->off ||
	    sqe->splice_fd_in)
		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_list *bl, unsigned nbufs)
{
	unsigned i = 0;

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

	if (bl->buf_nr_pages) {
		int j;

		i = bl->buf_ring->tail - bl->head;
		for (j = 0; j < bl->buf_nr_pages; j++)
			unpin_user_page(bl->buf_pages[j]);
		kvfree(bl->buf_pages);
		bl->buf_pages = NULL;
		bl->buf_nr_pages = 0;
		/* make sure it's seen as empty */
		INIT_LIST_HEAD(&bl->buf_list);
		return i;
	}

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

		nxt = list_first_entry(&bl->buf_list, struct io_buffer, list);
		list_del(&nxt->list);
		if (++i == nbufs)
			return i;
		cond_resched();
	}
	i++;

	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_list *bl;
	int ret = 0;

	io_ring_submit_lock(ctx, issue_flags);

	ret = -ENOENT;
	bl = io_buffer_get_list(ctx, p->bgid);
	if (bl) {
		ret = -EINVAL;
		/* can't use provide/remove buffers command on mapped buffers */
		if (!bl->buf_nr_pages)
			ret = __io_remove_buffers(ctx, bl, p->nbufs);
	}
	if (ret < 0)
		req_set_fail(req);

	/* complete before unlock, IOPOLL may need the lock */
	__io_req_complete(req, issue_flags, ret, 0);
	io_ring_submit_unlock(ctx, issue_flags);
	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->rw_flags || sqe->splice_fd_in)
		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_refill_buffer_cache(struct io_ring_ctx *ctx)
{
	struct io_buffer *buf;
	struct page *page;
	int bufs_in_page;

	/*
	 * Completions that don't happen inline (eg not under uring_lock) will
	 * add to ->io_buffers_comp. If we don't have any free buffers, check
	 * the completion list and splice those entries first.
	 */
	if (!list_empty_careful(&ctx->io_buffers_comp)) {
		spin_lock(&ctx->completion_lock);
		if (!list_empty(&ctx->io_buffers_comp)) {
			list_splice_init(&ctx->io_buffers_comp,
						&ctx->io_buffers_cache);
			spin_unlock(&ctx->completion_lock);
			return 0;
		}
		spin_unlock(&ctx->completion_lock);
	}

	/*
	 * No free buffers and no completion entries either. Allocate a new
	 * page worth of buffer entries and add those to our freelist.
	 */
	page = alloc_page(GFP_KERNEL_ACCOUNT);
	if (!page)
		return -ENOMEM;

	list_add(&page->lru, &ctx->io_buffers_pages);

	buf = page_address(page);
	bufs_in_page = PAGE_SIZE / sizeof(*buf);
	while (bufs_in_page) {
		list_add_tail(&buf->list, &ctx->io_buffers_cache);
		buf++;
		bufs_in_page--;
	}

	return 0;
}

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

	for (i = 0; i < pbuf->nbufs; i++) {
		if (list_empty(&ctx->io_buffers_cache) &&
		    io_refill_buffer_cache(ctx))
			break;
		buf = list_first_entry(&ctx->io_buffers_cache, struct io_buffer,
					list);
		list_move_tail(&buf->list, &bl->buf_list);
		buf->addr = addr;
		buf->len = min_t(__u32, pbuf->len, MAX_RW_COUNT);
		buf->bid = bid;
		buf->bgid = pbuf->bgid;
		addr += pbuf->len;
		bid++;
		cond_resched();
	}

	return i ? 0 : -ENOMEM;
}

static __cold int io_init_bl_list(struct io_ring_ctx *ctx)
{
	int i;

	ctx->io_bl = kcalloc(BGID_ARRAY, sizeof(struct io_buffer_list),
				GFP_KERNEL);
	if (!ctx->io_bl)
		return -ENOMEM;

	for (i = 0; i < BGID_ARRAY; i++) {
		INIT_LIST_HEAD(&ctx->io_bl[i].buf_list);
		ctx->io_bl[i].bgid = i;
	}

	return 0;
}

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_list *bl;
	int ret = 0;

	io_ring_submit_lock(ctx, issue_flags);

	if (unlikely(p->bgid < BGID_ARRAY && !ctx->io_bl)) {
		ret = io_init_bl_list(ctx);
		if (ret)
			goto err;
	}

	bl = io_buffer_get_list(ctx, p->bgid);
	if (unlikely(!bl)) {
		bl = kzalloc(sizeof(*bl), GFP_KERNEL);
		if (!bl) {
			ret = -ENOMEM;
			goto err;
		}
		INIT_LIST_HEAD(&bl->buf_list);
		ret = io_buffer_add_list(ctx, bl, p->bgid);
		if (ret) {
			kfree(bl);
			goto err;
		}
	}
	/* can't add buffers via this command for a mapped buffer ring */
	if (bl->buf_nr_pages) {
		ret = -EINVAL;
		goto err;
	}

	ret = io_add_buffers(ctx, p, bl);
err:
	if (ret < 0)
		req_set_fail(req);
	/* complete before unlock, IOPOLL may need the lock */
	__io_req_complete(req, issue_flags, ret, 0);
	io_ring_submit_unlock(ctx, issue_flags);
	return 0;
}

static int io_epoll_ctl_prep(struct io_kiocb *req,
			     const struct io_uring_sqe *sqe)
{
#if defined(CONFIG_EPOLL)
	if (sqe->buf_index || sqe->splice_fd_in)
		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(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->buf_index || sqe->off || sqe->splice_fd_in)
		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);
	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->buf_index || sqe->addr || sqe->splice_fd_in)
		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(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)
{
	const char __user *path;

	if (sqe->buf_index || sqe->splice_fd_in)
		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);
	path = 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);

	req->statx.filename = getname_flags(path,
					getname_statx_lookup_flags(req->statx.flags),
					NULL);

	if (IS_ERR(req->statx.filename)) {
		int ret = PTR_ERR(req->statx.filename);

		req->statx.filename = NULL;
		return ret;
	}

	req->flags |= REQ_F_NEED_CLEANUP;
	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);
	io_req_complete(req, ret);
	return 0;
}

static int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	if (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);
	req->close.file_slot = READ_ONCE(sqe->file_index);
	if (req->close.file_slot && req->close.fd)
		return -EINVAL;

	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;
	int ret = -EBADF;

	if (req->close.file_slot) {
		ret = io_close_fixed(req, issue_flags);
		goto err;
	}

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

	file = __close_fd_get_file(close->fd);
	spin_unlock(&files->file_lock);
	if (!file)
		goto err;

	/* No ->flush() or already async, safely close from here */
	ret = filp_close(file, current->files);
err:
	if (ret < 0)
		req_set_fail(req);
	__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)
{
	if (unlikely(sqe->addr || sqe->buf_index || sqe->splice_fd_in))
		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);
	io_req_complete(req, ret);
	return 0;
}

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

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

static int io_shutdown(struct io_kiocb *req, unsigned int issue_flags)
{
	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);
	io_req_complete(req, ret);
	return 0;
}

static bool io_net_retry(struct socket *sock, int flags)
{
	if (!(flags & MSG_WAITALL))
		return false;
	return sock->type == SOCK_STREAM || sock->type == SOCK_SEQPACKET;
}

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(sqe->file_index || sqe->addr2))
		return -EINVAL;

	sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr));
	sr->len = READ_ONCE(sqe->len);
	sr->flags = READ_ONCE(sqe->ioprio);
	if (sr->flags & ~IORING_RECVSEND_POLL_FIRST)
		return -EINVAL;
	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
	sr->done_io = 0;
	return 0;
}

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

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

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

	if (!(req->flags & REQ_F_POLLED) &&
	    (sr->flags & IORING_RECVSEND_POLL_FIRST))
		return io_setup_async_msg(req, kmsg);

	flags = sr->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 (ret < min_ret) {
		if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK))
			return io_setup_async_msg(req, kmsg);
		if (ret == -ERESTARTSYS)
			ret = -EINTR;
		if (ret > 0 && io_net_retry(sock, flags)) {
			sr->done_io += ret;
			req->flags |= REQ_F_PARTIAL_IO;
			return io_setup_async_msg(req, kmsg);
		}
		req_set_fail(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 >= 0)
		ret += sr->done_io;
	else if (sr->done_io)
		ret = sr->done_io;
	__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;

	if (!(req->flags & REQ_F_POLLED) &&
	    (sr->flags & IORING_RECVSEND_POLL_FIRST))
		return -EAGAIN;

	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 = sr->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 (ret < min_ret) {
		if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK))
			return -EAGAIN;
		if (ret == -ERESTARTSYS)
			ret = -EINTR;
		if (ret > 0 && io_net_retry(sock, flags)) {
			sr->len -= ret;
			sr->buf += ret;
			sr->done_io += ret;
			req->flags |= REQ_F_PARTIAL_IO;
			return -EAGAIN;
		}
		req_set_fail(req);
	}
	if (ret >= 0)
		ret += sr->done_io;
	else if (sr->done_io)
		ret = sr->done_io;
	__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 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(sqe->file_index || sqe->addr2))
		return -EINVAL;

	sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr));
	sr->len = READ_ONCE(sqe->len);
	sr->flags = READ_ONCE(sqe->ioprio);
	if (sr->flags & ~IORING_RECVSEND_POLL_FIRST)
		return -EINVAL;
	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
	sr->done_io = 0;
	return 0;
}

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

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

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

	if (!(req->flags & REQ_F_POLLED) &&
	    (sr->flags & IORING_RECVSEND_POLL_FIRST))
		return io_setup_async_msg(req, kmsg);

	if (io_do_buffer_select(req)) {
		void __user *buf;

		buf = io_buffer_select(req, &sr->len, issue_flags);
		if (!buf)
			return -ENOBUFS;
		kmsg->fast_iov[0].iov_base = buf;
		kmsg->fast_iov[0].iov_len = sr->len;
		iov_iter_init(&kmsg->msg.msg_iter, READ, kmsg->fast_iov, 1,
				sr->len);
	}

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

	kmsg->msg.msg_get_inq = 1;
	ret = __sys_recvmsg_sock(sock, &kmsg->msg, sr->umsg, kmsg->uaddr, flags);
	if (ret < min_ret) {
		if (ret == -EAGAIN && force_nonblock)
			return io_setup_async_msg(req, kmsg);
		if (ret == -ERESTARTSYS)
			ret = -EINTR;
		if (ret > 0 && io_net_retry(sock, flags)) {
			sr->done_io += ret;
			req->flags |= REQ_F_PARTIAL_IO;
			return io_setup_async_msg(req, kmsg);
		}
		req_set_fail(req);
	} else if ((flags & MSG_WAITALL) && (kmsg->msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC))) {
		req_set_fail(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 >= 0)
		ret += sr->done_io;
	else if (sr->done_io)
		ret = sr->done_io;
	cflags = io_put_kbuf(req, issue_flags);
	if (kmsg->msg.msg_inq)
		cflags |= IORING_CQE_F_SOCK_NONEMPTY;
	__io_req_complete(req, issue_flags, ret, cflags);
	return 0;
}

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

	if (!(req->flags & REQ_F_POLLED) &&
	    (sr->flags & IORING_RECVSEND_POLL_FIRST))
		return -EAGAIN;

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

	if (io_do_buffer_select(req)) {
		void __user *buf;

		buf = io_buffer_select(req, &sr->len, issue_flags);
		if (!buf)
			return -ENOBUFS;
		sr->buf = buf;
	}

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

	msg.msg_name = NULL;
	msg.msg_namelen = 0;
	msg.msg_control = NULL;
	msg.msg_get_inq = 1;
	msg.msg_flags = 0;
	msg.msg_controllen = 0;
	msg.msg_iocb = NULL;

	flags = sr->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 (ret < min_ret) {
		if (ret == -EAGAIN && force_nonblock)
			return -EAGAIN;
		if (ret == -ERESTARTSYS)
			ret = -EINTR;
		if (ret > 0 && io_net_retry(sock, flags)) {
			sr->len -= ret;
			sr->buf += ret;
			sr->done_io += re