fs/io_uring.c

// SPDX-License-Identifier: GPL-2.0
/*
 * Shared application/kernel submission and completion ring pairs, for
 * supporting fast/efficient IO.
 *
 * A note on the read/write ordering memory barriers that are matched between
 * the application and kernel side.
 *
 * After the application reads the CQ ring tail, it must use an
 * appropriate smp_rmb() to pair with the smp_wmb() the kernel uses
 * before writing the tail (using smp_load_acquire to read the tail will
 * do). It also needs a smp_mb() before updating CQ head (ordering the
 * entry load(s) with the head store), pairing with an implicit barrier
 * through a control-dependency in io_get_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;
	__u32 head;
	__u32 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;
	u32				flags;
};

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_nop {
	struct file			*file;
	u64				extra1;
	u64				extra2;
};

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_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),
};

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_nop		nop;
		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,
		.buffer_select		= 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,
		.async_size		= sizeof(struct io_async_msghdr),
	},
	[IORING_OP_RECVMSG] = {
		.needs_file		= 1,
		.unbound_nonreg_file	= 1,
		.pollin			= 1,
		.buffer_select		= 1,
		.needs_async_setup	= 1,
		.async_size		= sizeof(struct io_async_msghdr),
	},
	[IORING_OP_TIMEOUT] = {
		.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,
	},
	[IORING_OP_RECV] = {
		.needs_file		= 1,
		.unbound_nonreg_file	= 1,
		.pollin			= 1,
		.buffer_select		= 1,
		.audit_skip		= 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;
	/* don't recycle if we already did IO to this buffer */
	if (req->flags & REQ_F_PARTIAL_IO)
		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) {
			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(&current->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(struct io_ring_ctx *ctx, u64 user_data,
				 s32 res, u32 cflags)
{
	struct io_uring_cqe *cqe;

	/*
	 * 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);
		return true;
	}
	return io_cqring_event_overflow(ctx, user_data, res, cflags, 0, 0);
}

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

	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);
}

static inline bool __io_fill_cqe32_req_filled(struct io_ring_ctx *ctx,
					      struct io_kiocb *req)
{
	struct io_uring_cqe *cqe;
	u64 extra1 = req->extra1;
	u64 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));
		cqe->big_cqe[0] = extra1;
		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 inline bool __io_fill_cqe_req(struct io_kiocb *req, s32 res, u32 cflags)
{
	trace_io_uring_complete(req->ctx, req, req->cqe.user_data, res, cflags, 0, 0);
	return __io_fill_cqe(req->ctx, req->cqe.user_data, res, cflags);
}

static inline void __io_fill_cqe32_req(struct io_kiocb *req, s32 res, u32 cflags,
				u64 extra1, u64 extra2)
{
	struct io_ring_ctx *ctx = req->ctx;
	struct io_uring_cqe *cqe;

	if (WARN_ON_ONCE(!(ctx->flags & IORING_SETUP_CQE32)))
		return;
	if (req->flags & REQ_F_CQE_SKIP)
		return;

	trace_io_uring_complete(ctx, req, req->cqe.user_data, res, cflags,
				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)) {
		WRITE_ONCE(cqe->user_data, req->cqe.user_data);
		WRITE_ONCE(cqe->res, res);
		WRITE_ONCE(cqe->flags, cflags);
		WRITE_ONCE(cqe->big_cqe[0], extra1);
		WRITE_ONCE(cqe->big_cqe[1], extra2);
		return;
	}

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

static noinline bool io_fill_cqe_aux(struct io_ring_ctx *ctx, u64 user_data,
				     s32 res, u32 cflags)
{
	ctx->cq_extra++;
	trace_io_uring_complete(ctx, NULL, user_data, res, cflags, 0, 0);
	return __io_fill_cqe(ctx, user_data, res, cflags);
}

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))
		__io_fill_cqe_req(req, res, cflags);
	__io_req_complete_put(req);
}

static void __io_req_complete_post32(struct io_kiocb *req, s32 res,
				   u32 cflags, u64 extra1, u64 extra2)
{
	if (!(req->flags & REQ_F_CQE_SKIP))
		__io_fill_cqe32_req(req, res, cflags, extra1, extra2);
	__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 void io_req_complete_post32(struct io_kiocb *req, s32 res,
				   u32 cflags, u64 extra1, u64 extra2)
{
	struct io_ring_ctx *ctx = req->ctx;

	spin_lock(&ctx->completion_lock);
	__io_req_complete_post32(req, res, cflags, extra1, extra2);
	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_complete32(struct io_kiocb *req,
				       unsigned int issue_flags, s32 res,
				       u32 cflags, u64 extra1, u64 extra2)
{
	if (issue_flags & IO_URING_F_COMPLETE_DEFER) {
		io_req_complete_state(req, res, cflags);
		req->extra1 = extra1;
		req->extra2 = extra2;
	} else {
		io_req_complete_post32(req, res, cflags, extra1, extra2);
	}
}

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