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

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

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

#include <uapi/linux/io_uring.h>

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

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

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

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

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

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

struct fixed_file_table {
        struct file             **files;
};

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

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

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

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

struct io_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;
};

struct io_sq_data {
        refcount_t              refs;
        struct mutex            lock;

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

        struct task_struct      *thread;
        struct wait_queue_head  wait;
};

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

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

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

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

                wait_queue_head_t       inflight_wait;
                struct io_uring_sqe     *sq_sqes;
        } ____cacheline_aligned_in_smp;

        struct io_rings *rings;

        /* IO offload */
        struct io_wq            *io_wq;

        /*
         * For SQPOLL usage - we hold a reference to the parent task, so we
         * have access to the ->files
         */
        struct task_struct      *sqo_task;

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

#ifdef CONFIG_BLK_CGROUP
        struct cgroup_subsys_state      *sqo_blkcg_css;
#endif

        struct io_sq_data       *sq_data;       /* if using sq thread polling */

        struct wait_queue_head  sqo_sq_wait;
        struct wait_queue_entry sqo_wait_entry;
        struct list_head        sqd_list;

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

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

        struct user_struct      *user;

        const struct cred       *creds;

#ifdef CONFIG_AUDIT
        kuid_t                  loginuid;
        unsigned int            sessionid;
#endif

        struct completion       ref_comp;
        struct completion       sq_thread_comp;

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

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

        struct idr              io_buffer_idr;

        struct idr              personality_idr;

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

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

        struct {
                spinlock_t              completion_lock;

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

                spinlock_t              inflight_lock;
                struct list_head        inflight_list;
        } ____cacheline_aligned_in_smp;

        struct delayed_work             file_put_work;
        struct llist_head               file_put_llist;

        struct work_struct              exit_work;
        struct io_restriction           restrictions;
};

/*
 * First field must be the file pointer in all the
 * iocb unions! See also 'struct kiocb' in <linux/fs.h>
 */
struct io_poll_iocb {
        struct file                     *file;
        union {
                struct wait_queue_head  *head;
                u64                     addr;
        };
        __poll_t                        events;
        bool                            done;
        bool                            canceled;
        struct wait_queue_entry         wait;
};

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

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

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

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

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

struct io_timeout {
        struct file                     *file;
        u32                             off;
        u32                             target_seq;
        struct list_head                list;
};

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

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

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

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

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

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

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

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

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

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

struct io_provide_buf {
        struct file                     *file;
        __u64                           addr;
        __s32                           len;
        __u32                           bgid;
        __u16                           nbufs;
        __u16                           bid;
};

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

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

struct io_async_connect {
        struct sockaddr_storage         address;
};

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

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

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

        REQ_F_LINK_HEAD_BIT,
        REQ_F_FAIL_LINK_BIT,
        REQ_F_INFLIGHT_BIT,
        REQ_F_CUR_POS_BIT,
        REQ_F_NOWAIT_BIT,
        REQ_F_LINK_TIMEOUT_BIT,
        REQ_F_ISREG_BIT,
        REQ_F_NEED_CLEANUP_BIT,
        REQ_F_POLLED_BIT,
        REQ_F_BUFFER_SELECTED_BIT,
        REQ_F_NO_FILE_TABLE_BIT,
        REQ_F_WORK_INITIALIZED_BIT,
        REQ_F_LTIMEOUT_ACTIVE_BIT,

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

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

        /* head of a link */
        REQ_F_LINK_HEAD         = BIT(REQ_F_LINK_HEAD_BIT),
        /* fail rest of links */
        REQ_F_FAIL_LINK         = BIT(REQ_F_FAIL_LINK_BIT),
        /* on inflight list */
        REQ_F_INFLIGHT          = BIT(REQ_F_INFLIGHT_BIT),
        /* read/write uses file position */
        REQ_F_CUR_POS           = BIT(REQ_F_CUR_POS_BIT),
        /* must not punt to workers */
        REQ_F_NOWAIT            = BIT(REQ_F_NOWAIT_BIT),
        /* has or had linked timeout */
        REQ_F_LINK_TIMEOUT      = BIT(REQ_F_LINK_TIMEOUT_BIT),
        /* regular file */
        REQ_F_ISREG             = BIT(REQ_F_ISREG_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),
        /* doesn't need file table for this request */
        REQ_F_NO_FILE_TABLE     = BIT(REQ_F_NO_FILE_TABLE_BIT),
        /* io_wq_work is initialized */
        REQ_F_WORK_INITIALIZED  = BIT(REQ_F_WORK_INITIALIZED_BIT),
        /* linked timeout is active, i.e. prepared by link's head */
        REQ_F_LTIMEOUT_ACTIVE   = BIT(REQ_F_LTIMEOUT_ACTIVE_BIT),
};

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

/*
 * NOTE! Each of the iocb union members has the file pointer
 * as the first entry in their struct definition. So you can
 * access the file pointer through any of the sub-structs,
 * or directly as just 'ki_filp' in this struct.
 */
struct io_kiocb {
        union {
                struct file             *file;
                struct io_rw            rw;
                struct io_poll_iocb     poll;
                struct io_accept        accept;
                struct io_sync          sync;
                struct io_cancel        cancel;
                struct io_timeout       timeout;
                struct io_timeout_rem   timeout_rem;
                struct io_connect       connect;
                struct io_sr_msg        sr_msg;
                struct io_open          open;
                struct io_close         close;
                struct io_files_update  files_update;
                struct io_fadvise       fadvise;
                struct io_madvise       madvise;
                struct io_epoll         epoll;
                struct io_splice        splice;
                struct io_provide_buf   pbuf;
                struct io_statx         statx;
                /* use only after cleaning per-op data, see io_clean_op() */
                struct io_completion    compl;
        };

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

        u16                             buf_index;
        u32                             result;

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

        struct list_head                link_list;

        /*
         * 1. used with ctx->iopoll_list with reads/writes
         * 2. to track reqs with ->files (see io_op_def::file_table)
         */
        struct list_head                inflight_entry;

        struct percpu_ref               *fixed_file_refs;
        struct callback_head            task_work;
        /* for polled requests, i.e. IORING_OP_POLL_ADD and async armed poll */
        struct hlist_node               hash_node;
        struct async_poll               *apoll;
        struct io_wq_work               work;
};

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

#define IO_IOPOLL_BATCH                 8

struct io_comp_state {
        unsigned int            nr;
        struct list_head        list;
        struct io_ring_ctx      *ctx;
};

struct io_submit_state {
        struct blk_plug         plug;

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

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

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

struct io_op_def {
        /* needs req->file assigned */
        unsigned                needs_file : 1;
        /* don't fail if file grab fails */
        unsigned                needs_file_no_error : 1;
        /* hash wq insertion if file is a regular file */
        unsigned                hash_reg_file : 1;
        /* unbound wq insertion if file is a non-regular file */
        unsigned                unbound_nonreg_file : 1;
        /* opcode is not supported by this kernel */
        unsigned                not_supported : 1;
        /* set if opcode supports polled "wait" */
        unsigned                pollin : 1;
        unsigned                pollout : 1;
        /* op supports buffer selection */
        unsigned                buffer_select : 1;
        /* must always have async data allocated */
        unsigned                needs_async_data : 1;
        /* size of async data needed, if any */
        unsigned short          async_size;
        unsigned                work_flags;
};

static const struct io_op_def io_op_defs[] = {
        [IORING_OP_NOP] = {},
        [IORING_OP_READV] = {
                .needs_file             = 1,
                .unbound_nonreg_file    = 1,
                .pollin                 = 1,
                .buffer_select          = 1,
                .needs_async_data       = 1,
                .async_size             = sizeof(struct io_async_rw),
                .work_flags             = IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG,
        },
        [IORING_OP_WRITEV] = {
                .needs_file             = 1,
                .hash_reg_file          = 1,
                .unbound_nonreg_file    = 1,
                .pollout                = 1,
                .needs_async_data       = 1,
                .async_size             = sizeof(struct io_async_rw),
                .work_flags             = IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG |
                                                IO_WQ_WORK_FSIZE,
        },
        [IORING_OP_FSYNC] = {
                .needs_file             = 1,
                .work_flags             = IO_WQ_WORK_BLKCG,
        },
        [IORING_OP_READ_FIXED] = {
                .needs_file             = 1,
                .unbound_nonreg_file    = 1,
                .pollin                 = 1,
                .async_size             = sizeof(struct io_async_rw),
                .work_flags             = IO_WQ_WORK_BLKCG | IO_WQ_WORK_MM,
        },
        [IORING_OP_WRITE_FIXED] = {
                .needs_file             = 1,
                .hash_reg_file          = 1,
                .unbound_nonreg_file    = 1,
                .pollout                = 1,
                .async_size             = sizeof(struct io_async_rw),
                .work_flags             = IO_WQ_WORK_BLKCG | IO_WQ_WORK_FSIZE |
                                                IO_WQ_WORK_MM,
        },
        [IORING_OP_POLL_ADD] = {
                .needs_file             = 1,
                .unbound_nonreg_file    = 1,
        },
        [IORING_OP_POLL_REMOVE] = {},
        [IORING_OP_SYNC_FILE_RANGE] = {
                .needs_file             = 1,
                .work_flags             = IO_WQ_WORK_BLKCG,
        },
        [IORING_OP_SENDMSG] = {
                .needs_file             = 1,
                .unbound_nonreg_file    = 1,
                .pollout                = 1,
                .needs_async_data       = 1,
                .async_size             = sizeof(struct io_async_msghdr),
                .work_flags             = IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG |
                                                IO_WQ_WORK_FS,
        },
        [IORING_OP_RECVMSG] = {
                .needs_file             = 1,
                .unbound_nonreg_file    = 1,
                .pollin                 = 1,
                .buffer_select          = 1,
                .needs_async_data       = 1,
                .async_size             = sizeof(struct io_async_msghdr),
                .work_flags             = IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG |
                                                IO_WQ_WORK_FS,
        },
        [IORING_OP_TIMEOUT] = {
                .needs_async_data       = 1,
                .async_size             = sizeof(struct io_timeout_data),
                .work_flags             = IO_WQ_WORK_MM,
        },
        [IORING_OP_TIMEOUT_REMOVE] = {},
        [IORING_OP_ACCEPT] = {
                .needs_file             = 1,
                .unbound_nonreg_file    = 1,
                .pollin                 = 1,
                .work_flags             = IO_WQ_WORK_MM | IO_WQ_WORK_FILES,
        },
        [IORING_OP_ASYNC_CANCEL] = {},
        [IORING_OP_LINK_TIMEOUT] = {
                .needs_async_data       = 1,
                .async_size             = sizeof(struct io_timeout_data),
                .work_flags             = IO_WQ_WORK_MM,
        },
        [IORING_OP_CONNECT] = {
                .needs_file             = 1,
                .unbound_nonreg_file    = 1,
                .pollout                = 1,
                .needs_async_data       = 1,
                .async_size             = sizeof(struct io_async_connect),
                .work_flags             = IO_WQ_WORK_MM,
        },
        [IORING_OP_FALLOCATE] = {
                .needs_file             = 1,
                .work_flags             = IO_WQ_WORK_BLKCG | IO_WQ_WORK_FSIZE,
        },
        [IORING_OP_OPENAT] = {
                .work_flags             = IO_WQ_WORK_FILES | IO_WQ_WORK_BLKCG |
                                                IO_WQ_WORK_FS,
        },
        [IORING_OP_CLOSE] = {
                .needs_file             = 1,
                .needs_file_no_error    = 1,
                .work_flags             = IO_WQ_WORK_FILES | IO_WQ_WORK_BLKCG,
        },
        [IORING_OP_FILES_UPDATE] = {
                .work_flags             = IO_WQ_WORK_FILES | IO_WQ_WORK_MM,
        },
        [IORING_OP_STATX] = {
                .work_flags             = IO_WQ_WORK_FILES | IO_WQ_WORK_MM |
                                                IO_WQ_WORK_FS | IO_WQ_WORK_BLKCG,
        },
        [IORING_OP_READ] = {
                .needs_file             = 1,
                .unbound_nonreg_file    = 1,
                .pollin                 = 1,
                .buffer_select          = 1,
                .async_size             = sizeof(struct io_async_rw),
                .work_flags             = IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG,
        },
        [IORING_OP_WRITE] = {
                .needs_file             = 1,
                .unbound_nonreg_file    = 1,
                .pollout                = 1,
                .async_size             = sizeof(struct io_async_rw),
                .work_flags             = IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG |
                                                IO_WQ_WORK_FSIZE,
        },
        [IORING_OP_FADVISE] = {
                .needs_file             = 1,
                .work_flags             = IO_WQ_WORK_BLKCG,
        },
        [IORING_OP_MADVISE] = {
                .work_flags             = IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG,
        },
        [IORING_OP_SEND] = {
                .needs_file             = 1,
                .unbound_nonreg_file    = 1,
                .pollout                = 1,
                .work_flags             = IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG,
        },
        [IORING_OP_RECV] = {
                .needs_file             = 1,
                .unbound_nonreg_file    = 1,
                .pollin                 = 1,
                .buffer_select          = 1,
                .work_flags             = IO_WQ_WORK_MM | IO_WQ_WORK_BLKCG,
        },
        [IORING_OP_OPENAT2] = {
                .work_flags             = IO_WQ_WORK_FILES | IO_WQ_WORK_FS |
                                                IO_WQ_WORK_BLKCG,
        },
        [IORING_OP_EPOLL_CTL] = {
                .unbound_nonreg_file    = 1,
                .work_flags             = IO_WQ_WORK_FILES,
        },
        [IORING_OP_SPLICE] = {
                .needs_file             = 1,
                .hash_reg_file          = 1,
                .unbound_nonreg_file    = 1,
                .work_flags             = IO_WQ_WORK_BLKCG,
        },
        [IORING_OP_PROVIDE_BUFFERS] = {},
        [IORING_OP_REMOVE_BUFFERS] = {},
        [IORING_OP_TEE] = {
                .needs_file             = 1,
                .hash_reg_file          = 1,
                .unbound_nonreg_file    = 1,
        },
};

enum io_mem_account {
        ACCT_LOCKED,
        ACCT_PINNED,
};

static void __io_complete_rw(struct io_kiocb *req, long res, long res2,
                             struct io_comp_state *cs);
static void io_cqring_fill_event(struct io_kiocb *req, long res);
static void io_put_req(struct io_kiocb *req);
static void io_put_req_deferred(struct io_kiocb *req, int nr);
static void io_double_put_req(struct io_kiocb *req);
static struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req);
static void __io_queue_linked_timeout(struct io_kiocb *req);
static void io_queue_linked_timeout(struct io_kiocb *req);
static int __io_sqe_files_update(struct io_ring_ctx *ctx,
                                 struct io_uring_files_update *ip,
                                 unsigned nr_args);
static void __io_clean_op(struct io_kiocb *req);
static struct file *io_file_get(struct io_submit_state *state,
                                struct io_kiocb *req, int fd, bool fixed);
static void __io_queue_sqe(struct io_kiocb *req, struct io_comp_state *cs);
static void io_file_put_work(struct work_struct *work);

static ssize_t io_import_iovec(int rw, struct io_kiocb *req,
                               struct iovec **iovec, struct iov_iter *iter,
                               bool needs_lock);
static int io_setup_async_rw(struct io_kiocb *req, const struct iovec *iovec,
                             const struct iovec *fast_iov,
                             struct iov_iter *iter, bool force);

static struct kmem_cache *req_cachep;

static const struct file_operations io_uring_fops;

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

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

static inline void io_clean_op(struct io_kiocb *req)
{
        if (req->flags & (REQ_F_NEED_CLEANUP | REQ_F_BUFFER_SELECTED |
                          REQ_F_INFLIGHT))
                __io_clean_op(req);
}

static void io_sq_thread_drop_mm(void)
{
        struct mm_struct *mm = current->mm;

        if (mm) {
                kthread_unuse_mm(mm);
                mmput(mm);
                current->mm = NULL;

        }
}

static int __io_sq_thread_acquire_mm(struct io_ring_ctx *ctx)
{
        struct mm_struct *mm;

        if (current->mm)
                return 0;

        /* Should never happen */
        if (unlikely(!(ctx->flags & IORING_SETUP_SQPOLL)))
                return -EFAULT;

        task_lock(ctx->sqo_task);
        mm = ctx->sqo_task->mm;
        if (unlikely(!mm || !mmget_not_zero(mm)))
                mm = NULL;
        task_unlock(ctx->sqo_task);

        if (mm) {
                kthread_use_mm(mm);
                return 0;
        }

        return -EFAULT;
}

static int io_sq_thread_acquire_mm(struct io_ring_ctx *ctx,
                                   struct io_kiocb *req)
{
        if (!(io_op_defs[req->opcode].work_flags & IO_WQ_WORK_MM))
                return 0;
        return __io_sq_thread_acquire_mm(ctx);
}

static void io_sq_thread_associate_blkcg(struct io_ring_ctx *ctx,
                                         struct cgroup_subsys_state **cur_css)

{
#ifdef CONFIG_BLK_CGROUP
        /* puts the old one when swapping */
        if (*cur_css != ctx->sqo_blkcg_css) {
                kthread_associate_blkcg(ctx->sqo_blkcg_css);
                *cur_css = ctx->sqo_blkcg_css;
        }
#endif
}

static void io_sq_thread_unassociate_blkcg(void)
{
#ifdef CONFIG_BLK_CGROUP
        kthread_associate_blkcg(NULL);
#endif
}

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

/*
 * None of these are dereferenced, they are simply used to check if any of
 * them have changed. If we're under current and check they are still the
 * same, we're fine to grab references to them for actual out-of-line use.
 */
static void io_init_identity(struct io_identity *id)
{
        id->files = current->files;
        id->mm = current->mm;
#ifdef CONFIG_BLK_CGROUP
        rcu_read_lock();
        id->blkcg_css = blkcg_css();
        rcu_read_unlock();
#endif
        id->creds = current_cred();
        id->nsproxy = current->nsproxy;
        id->fs = current->fs;
        id->fsize = rlimit(RLIMIT_FSIZE);
#ifdef CONFIG_AUDIT
        id->loginuid = current->loginuid;
        id->sessionid = current->sessionid;
#endif
        refcount_set(&id->count, 1);
}

static inline void __io_req_init_async(struct io_kiocb *req)
{
        memset(&req->work, 0, sizeof(req->work));
        req->flags |= REQ_F_WORK_INITIALIZED;
}

/*
 * Note: must call io_req_init_async() for the first time you
 * touch any members of io_wq_work.
 */
static inline void io_req_init_async(struct io_kiocb *req)
{
        struct io_uring_task *tctx = current->io_uring;

        if (req->flags & REQ_F_WORK_INITIALIZED)
                return;

        __io_req_init_async(req);

        /* Grab a ref if this isn't our static identity */
        req->work.identity = tctx->identity;
        if (tctx->identity != &tctx->__identity)
                refcount_inc(&req->work.identity->count);
}

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

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

        complete(&ctx->ref_comp);
}

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

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

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

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

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

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

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

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

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

        return false;
}

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

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

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

static void io_put_identity(struct io_uring_task *tctx, struct io_kiocb *req)
{
        if (req->work.identity == &tctx->__identity)
                return;
        if (refcount_dec_and_test(&req->work.identity->count))
                kfree(req->work.identity);
}

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

        req->flags &= ~REQ_F_WORK_INITIALIZED;

        if (req->work.flags & IO_WQ_WORK_MM) {
                mmdrop(req->work.identity->mm);
                req->work.flags &= ~IO_WQ_WORK_MM;
        }
#ifdef CONFIG_BLK_CGROUP
        if (req->work.flags & IO_WQ_WORK_BLKCG) {
                css_put(req->work.identity->blkcg_css);
                req->work.flags &= ~IO_WQ_WORK_BLKCG;
        }
#endif
        if (req->work.flags & IO_WQ_WORK_CREDS) {
                put_cred(req->work.identity->creds);
                req->work.flags &= ~IO_WQ_WORK_CREDS;
        }
        if (req->work.flags & IO_WQ_WORK_FS) {
                struct fs_struct *fs = req->work.identity->fs;

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

        io_put_identity(req->task->io_uring, req);
}

/*
 * Create a private copy of io_identity, since some fields don't match
 * the current context.
 */
static bool io_identity_cow(struct io_kiocb *req)
{
        struct io_uring_task *tctx = current->io_uring;
        const struct cred *creds = NULL;
        struct io_identity *id;

        if (req->work.flags & IO_WQ_WORK_CREDS)
                creds = req->work.identity->creds;

        id = kmemdup(req->work.identity, sizeof(*id), GFP_KERNEL);
        if (unlikely(!id)) {
                req->work.flags |= IO_WQ_WORK_CANCEL;
                return false;
        }

        /*
         * We can safely just re-init the creds we copied  Either the field
         * matches the current one, or we haven't grabbed it yet. The only
         * exception is ->creds, through registered personalities, so handle
         * that one separately.
         */
        io_init_identity(id);
        if (creds)
                id->creds = creds;

        /* add one for this request */
        refcount_inc(&id->count);

        /* drop tctx and req identity references, if needed */
        if (tctx->identity != &tctx->__identity &&
            refcount_dec_and_test(&tctx->identity->count))
                kfree(tctx->identity);
        if (req->work.identity != &tctx->__identity &&
            refcount_dec_and_test(&req->work.identity->count))
                kfree(req->work.identity);

        req->work.identity = id;
        tctx->identity = id;
        return true;
}

static bool io_grab_identity(struct io_kiocb *req)
{
        const struct io_op_def *def = &io_op_defs[req->opcode];
        struct io_identity *id = req->work.identity;
        struct io_ring_ctx *ctx = req->ctx;

        if (def->work_flags & IO_WQ_WORK_FSIZE) {
                if (id->fsize != rlimit(RLIMIT_FSIZE))
                        return false;
                req->work.flags |= IO_WQ_WORK_FSIZE;
        }
#ifdef CONFIG_BLK_CGROUP
        if (!(req->work.flags & IO_WQ_WORK_BLKCG) &&
            (def->work_flags & IO_WQ_WORK_BLKCG)) {
                rcu_read_lock();
                if (id->blkcg_css != blkcg_css()) {
                        rcu_read_unlock();
                        return false;
                }
                /*
                 * This should be rare, either the cgroup is dying or the task
                 * is moving cgroups. Just punt to root for the handful of ios.
                 */
                if (css_tryget_online(id->blkcg_css))
                        req->work.flags |= IO_WQ_WORK_BLKCG;
                rcu_read_unlock();
        }
#endif
        if (!(req->work.flags & IO_WQ_WORK_CREDS)) {
                if (id->creds != current_cred())
                        return false;
                get_cred(id->creds);
                req->work.flags |= IO_WQ_WORK_CREDS;
        }
#ifdef CONFIG_AUDIT
        if (!uid_eq(current->loginuid, id->loginuid) ||
            current->sessionid != id->sessionid)
                return false;
#endif
        if (!(req->work.flags & IO_WQ_WORK_FS) &&
            (def->work_flags & IO_WQ_WORK_FS)) {
                if (current->fs != id->fs)
                        return false;
                spin_lock(&id->fs->lock);
                if (!id->fs->in_exec) {
                        id->fs->users++;
                        req->work.flags |= IO_WQ_WORK_FS;
                } else {
                        req->work.flags |= IO_WQ_WORK_CANCEL;
                }
                spin_unlock(&current->fs->lock);
        }
        if (!(req->work.flags & IO_WQ_WORK_FILES) &&
            (def->work_flags & IO_WQ_WORK_FILES) &&
            !(req->flags & REQ_F_NO_FILE_TABLE)) {
                if (id->files != current->files ||
                    id->nsproxy != current->nsproxy)
                        return false;
                atomic_inc(&id->files->count);
                get_nsproxy(id->nsproxy);
                req->flags |= REQ_F_INFLIGHT;

                spin_lock_irq(&ctx->inflight_lock);
                list_add(&req->inflight_entry, &ctx->inflight_list);
                spin_unlock_irq(&ctx->inflight_lock);
                req->work.flags |= IO_WQ_WORK_FILES;
        }

        return true;
}

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;
        struct io_identity *id;

        io_req_init_async(req);
        id = req->work.identity;

        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 (def->unbound_nonreg_file)
                        req->work.flags |= IO_WQ_WORK_UNBOUND;
        }

        /* ->mm can never change on us */
        if (!(req->work.flags & IO_WQ_WORK_MM) &&
            (def->work_flags & IO_WQ_WORK_MM)) {
                mmgrab(id->mm);
                req->work.flags |= IO_WQ_WORK_MM;
        }

        /* if we fail grabbing identity, we must COW, regrab, and retry */
        if (io_grab_identity(req))
                return;

        if (!io_identity_cow(req))
                return;

        /* can't fail at this point */
        if (!io_grab_identity(req))
                WARN_ON(1);
}

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

        io_prep_async_work(req);
        if (req->flags & REQ_F_LINK_HEAD)
                list_for_each_entry(cur, &req->link_list, link_list)
                        io_prep_async_work(cur);
}

static struct io_kiocb *__io_queue_async_work(struct io_kiocb *req)
{
        struct io_ring_ctx *ctx = req->ctx;
        struct io_kiocb *link = io_prep_linked_timeout(req);

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

static void io_queue_async_work(struct io_kiocb *req)
{
        struct io_kiocb *link;

        /* init ->work of the whole link before punting */
        io_prep_async_link(req);
        link = __io_queue_async_work(req);

        if (link)
                io_queue_linked_timeout(link);
}

static void io_kill_timeout(struct io_kiocb *req)
{
        struct io_timeout_data *io = req->async_data;
        int ret;

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

static bool io_task_match(struct io_kiocb *req, struct task_struct *tsk)
{
        struct io_ring_ctx *ctx = req->ctx;

        if (!tsk || req->task == tsk)
                return true;
        if (ctx->flags & IORING_SETUP_SQPOLL) {
                if (ctx->sq_data && req->task == ctx->sq_data->thread)
                        return true;
        }
        return false;
}

/*
 * Returns true if we found and killed one or more timeouts
 */
static bool io_kill_timeouts(struct io_ring_ctx *ctx, struct task_struct *tsk)
{
        struct io_kiocb *req, *tmp;
        int canceled = 0;

        spin_lock_irq(&ctx->completion_lock);
        list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) {
                if (io_task_match(req, tsk)) {
                        io_kill_timeout(req);
                        canceled++;
                }
        }
        spin_unlock_irq(&ctx->completion_lock);
        return canceled != 0;
}

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

                if (req_need_defer(de->req, de->seq))
                        break;
                list_del_init(&de->list);
                /* punt-init is done before queueing for defer */
                link = __io_queue_async_work(de->req);
                if (link) {
                        __io_queue_linked_timeout(link);
                        /* drop submission reference */
                        io_put_req_deferred(link, 1);
                }
                kfree(de);
        } while (!list_empty(&ctx->defer_list));
}

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

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

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

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

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

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

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

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

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

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

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

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

static void io_cqring_mark_overflow(struct io_ring_ctx *ctx)
{
        if (list_empty(&ctx->cq_overflow_list)) {
                clear_bit(0, &ctx->sq_check_overflow);
                clear_bit(0, &ctx->cq_check_overflow);
                ctx->rings->sq_flags &= ~IORING_SQ_CQ_OVERFLOW;
        }
}

static inline bool __io_match_files(struct io_kiocb *req,
                                    struct files_struct *files)
{
        return ((req->flags & REQ_F_WORK_INITIALIZED) &&
                (req->work.flags & IO_WQ_WORK_FILES)) &&
                req->work.identity->files == files;
}

static bool io_match_files(struct io_kiocb *req,
                           struct files_struct *files)
{
        struct io_kiocb *link;

        if (!files)
                return true;
        if (__io_match_files(req, files))
                return true;
        if (req->flags & REQ_F_LINK_HEAD) {
                list_for_each_entry(link, &req->link_list, link_list) {
                        if (__io_match_files(link, files))
                                return true;
                }
        }
        return false;
}

/* Returns true if there are no backlogged entries after the flush */
static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force,
                                     struct task_struct *tsk,
                                     struct files_struct *files)
{
        struct io_rings *rings = ctx->rings;
        struct io_kiocb *req, *tmp;
        struct io_uring_cqe *cqe;
        unsigned long flags;
        LIST_HEAD(list);

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

        spin_lock_irqsave(&ctx->completion_lock, flags);

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

        cqe = NULL;
        list_for_each_entry_safe(req, tmp, &ctx->cq_overflow_list, compl.list) {
                if (tsk && req->task != tsk)
                        continue;
                if (!io_match_files(req, files))
                        continue;

                cqe = io_get_cqring(ctx);
                if (!cqe && !force)
                        break;

                list_move(&req->compl.list, &list);
                if (cqe) {
                        WRITE_ONCE(cqe->user_data, req->user_data);
                        WRITE_ONCE(cqe->res, req->result);
                        WRITE_ONCE(cqe->flags, req->compl.cflags);
                } else {
                        ctx->cached_cq_overflow++;
                        WRITE_ONCE(ctx->rings->cq_overflow,
                                   ctx->cached_cq_overflow);
                }
        }

        io_commit_cqring(ctx);
        io_cqring_mark_overflow(ctx);

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

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

        return cqe != NULL;
}

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

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

        /*
         * If we can't get a cq entry, userspace overflowed the
         * submission (by quite a lot). Increment the overflow count in
         * the ring.
         */
        cqe = io_get_cqring(ctx);
        if (likely(cqe)) {
                WRITE_ONCE(cqe->user_data, req->user_data);
                WRITE_ONCE(cqe->res, res);
                WRITE_ONCE(cqe->flags, cflags);
        } else if (ctx->cq_overflow_flushed ||
                   atomic_read(&req->task->io_uring->in_idle)) {
                /*
                 * If we're in ring overflow flush mode, or in task cancel mode,
                 * then we cannot store the request for later flushing, we need
                 * to drop it on the floor.
                 */
                ctx->cached_cq_overflow++;
                WRITE_ONCE(ctx->rings->cq_overflow, ctx->cached_cq_overflow);
        } else {
                if (list_empty(&ctx->cq_overflow_list)) {
                        set_bit(0, &ctx->sq_check_overflow);
                        set_bit(0, &ctx->cq_check_overflow);
                        ctx->rings->sq_flags |= IORING_SQ_CQ_OVERFLOW;
                }
                io_clean_op(req);
                req->result = res;
                req->compl.cflags = cflags;
                refcount_inc(&req->refs);
                list_add_tail(&req->compl.list, &ctx->cq_overflow_list);
        }
}

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

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

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

        io_cqring_ev_posted(ctx);
}

static void io_submit_flush_completions(struct io_comp_state *cs)
{
        struct io_ring_ctx *ctx = cs->ctx;

        spin_lock_irq(&ctx->completion_lock);
        while (!list_empty(&cs->list)) {
                struct io_kiocb *req;

                req = list_first_entry(&cs->list, struct io_kiocb, compl.list);
                list_del(&req->compl.list);
                __io_cqring_fill_event(req, req->result, req->compl.cflags);

                /*
                 * io_free_req() doesn't care about completion_lock unless one
                 * of these flags is set. REQ_F_WORK_INITIALIZED is in the list
                 * because of a potential deadlock with req->work.fs->lock
                 */
                if (req->flags & (REQ_F_FAIL_LINK|REQ_F_LINK_TIMEOUT
                                 |REQ_F_WORK_INITIALIZED)) {
                        spin_unlock_irq(&ctx->completion_lock);
                        io_put_req(req);
                        spin_lock_irq(&ctx->completion_lock);
                } else {
                        io_put_req(req);
                }
        }
        io_commit_cqring(ctx);
        spin_unlock_irq(&ctx->completion_lock);

        io_cqring_ev_posted(ctx);
        cs->nr = 0;
}

static void __io_req_complete(struct io_kiocb *req, long res, unsigned cflags,
                              struct io_comp_state *cs)
{
        if (!cs) {
                io_cqring_add_event(req, res, cflags);
                io_put_req(req);
        } else {
                io_clean_op(req);
                req->result = res;
                req->compl.cflags = cflags;
                list_add_tail(&req->compl.list, &cs->list);
                if (++cs->nr >= 32)
                        io_submit_flush_completions(cs);
        }
}

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

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

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

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

        return NULL;
}

static struct io_kiocb *io_alloc_req(struct io_ring_ctx *ctx,
                                     struct io_submit_state *state)
{
        if (!state->free_reqs) {
                gfp_t gfp = GFP_KERNEL | __GFP_NOWARN;
                size_t sz;
                int ret;

                sz = min_t(size_t, state->ios_left, ARRAY_SIZE(state->reqs));
                ret = kmem_cache_alloc_bulk(req_cachep, gfp, sz, state->reqs);

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

        state->free_reqs--;
        return state->reqs[state->free_reqs];
fallback:
        return io_get_fallback_req(ctx);
}

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

static void io_dismantle_req(struct io_kiocb *req)
{
        io_clean_op(req);

        if (req->async_data)
                kfree(req->async_data);
        if (req->file)
                io_put_file(req, req->file, (req->flags & REQ_F_FIXED_FILE));

        io_req_clean_work(req);
}

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

        io_dismantle_req(req);

        percpu_counter_dec(&tctx->inflight);
        if (atomic_read(&tctx->in_idle))
                wake_up(&tctx->wait);
        put_task_struct(req->task);

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

static void io_kill_linked_timeout(struct io_kiocb *req)
{
        struct io_ring_ctx *ctx = req->ctx;
        struct io_kiocb *link;
        bool cancelled = false;
        unsigned long flags;

        spin_lock_irqsave(&ctx->completion_lock, flags);
        link = list_first_entry_or_null(&req->link_list, struct io_kiocb,
                                        link_list);
        /*
         * Can happen if a linked timeout fired and link had been like
         * req -> link t-out -> link t-out [-> ...]
         */
        if (link && (link->flags & REQ_F_LTIMEOUT_ACTIVE)) {
                struct io_timeout_data *io = link->async_data;
                int ret;

                list_del_init(&link->link_list);
                ret = hrtimer_try_to_cancel(&io->timer);
                if (ret != -1) {
                        io_cqring_fill_event(link, -ECANCELED);
                        io_commit_cqring(ctx);
                        cancelled = true;
                }
        }
        req->flags &= ~REQ_F_LINK_TIMEOUT;
        spin_unlock_irqrestore(&ctx->completion_lock, flags);

        if (cancelled) {
                io_cqring_ev_posted(ctx);
                io_put_req(link);
        }
}

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

        /*
         * The list should never be empty when we are called here. But could
         * potentially happen if the chain is messed up, check to be on the
         * safe side.
         */
        if (unlikely(list_empty(&req->link_list)))
                return NULL;

        nxt = list_first_entry(&req->link_list, struct io_kiocb, link_list);
        list_del_init(&req->link_list);
        if (!list_empty(&nxt->link_list))
                nxt->flags |= REQ_F_LINK_HEAD;
        return nxt;
}

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

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

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

                io_cqring_fill_event(link, -ECANCELED);

                /*
                 * It's ok to free under spinlock as they're not linked anymore,
                 * but avoid REQ_F_WORK_INITIALIZED because it may deadlock on
                 * work.fs->lock.
                 */
                if (link->flags & REQ_F_WORK_INITIALIZED)
                        io_put_req_deferred(link, 2);
                else
                        io_double_put_req(link);
        }

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

        io_cqring_ev_posted(ctx);
}

static struct io_kiocb *__io_req_find_next(struct io_kiocb *req)
{
        req->flags &= ~REQ_F_LINK_HEAD;
        if (req->flags & REQ_F_LINK_TIMEOUT)
                io_kill_linked_timeout(req);

        /*
         * 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 (likely(!(req->flags & REQ_F_FAIL_LINK)))
                return io_req_link_next(req);
        io_fail_links(req);
        return NULL;
}

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

static int io_req_task_work_add(struct io_kiocb *req, bool twa_signal_ok)
{

        struct task_struct *tsk = req->task;
        struct io_ring_ctx *ctx = req->ctx;
        enum task_work_notify_mode notify;
        int ret;

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

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

        ret = task_work_add(tsk, &req->task_work, notify);
        if (!ret)
                wake_up_process(tsk);

        return ret;
}

static void __io_req_task_cancel(struct io_kiocb *req, int error)
{
        struct io_ring_ctx *ctx = req->ctx;

        spin_lock_irq(&ctx->completion_lock);
        io_cqring_fill_event(req, error);
        io_commit_cqring(ctx);
        spin_unlock_irq(&ctx->completion_lock);

        io_cqring_ev_posted(ctx);
        req_set_fail_links(req);
        io_double_put_req(req);
}

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

        __io_req_task_cancel(req, -ECANCELED);
        percpu_ref_put(&ctx->refs);
}

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

        if (!__io_sq_thread_acquire_mm(ctx)) {
                mutex_lock(&ctx->uring_lock);
                __io_queue_sqe(req, NULL);
                mutex_unlock(&ctx->uring_lock);
        } else {
                __io_req_task_cancel(req, -EFAULT);
        }
}

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

        __io_req_task_submit(req);
        percpu_ref_put(&ctx->refs);
}

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

        init_task_work(&req->task_work, io_req_task_submit);
        percpu_ref_get(&req->ctx->refs);

        ret = io_req_task_work_add(req, true);
        if (unlikely(ret)) {
                struct task_struct *tsk;

                init_task_work(&req->task_work, io_req_task_cancel);
                tsk = io_wq_get_task(req->ctx->io_wq);
                task_work_add(tsk, &req->task_work, TWA_NONE);
                wake_up_process(tsk);
        }
}

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_req(struct io_kiocb *req)
{
        io_queue_next(req);
        __io_free_req(req);
}

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

        struct task_struct      *task;
        int                     task_refs;
};

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

static void __io_req_free_batch_flush(struct io_ring_ctx *ctx,
                                      struct req_batch *rb)
{
        kmem_cache_free_bulk(req_cachep, rb->to_free, rb->reqs);
        percpu_ref_put_many(&ctx->refs, rb->to_free);
        rb->to_free = 0;
}

static void io_req_free_batch_finish(struct io_ring_ctx *ctx,
                                     struct req_batch *rb)
{
        if (rb->to_free)
                __io_req_free_batch_flush(ctx, rb);
        if (rb->task) {
                struct io_uring_task *tctx = rb->task->io_uring;

                percpu_counter_sub(&tctx->inflight, rb->task_refs);
                put_task_struct_many(rb->task, rb->task_refs);
                rb->task = NULL;
        }
}

static void io_req_free_batch(struct req_batch *rb, struct io_kiocb *req)
{
        if (unlikely(io_is_fallback_req(req))) {
                io_free_req(req);
                return;
        }
        if (req->flags & REQ_F_LINK_HEAD)
                io_queue_next(req);

        if (req->task != rb->task) {
                if (rb->task) {
                        struct io_uring_task *tctx = rb->task->io_uring;

                        percpu_counter_sub(&tctx->inflight, rb->task_refs);
                        put_task_struct_many(rb->task, rb->task_refs);
                }
                rb->task = req->task;
                rb->task_refs = 0;
        }
        rb->task_refs++;

        io_dismantle_req(req);
        rb->reqs[rb->to_free++] = req;
        if (unlikely(rb->to_free == ARRAY_SIZE(rb->reqs)))
                __io_req_free_batch_flush(req->ctx, rb);
}

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

        if (refcount_dec_and_test(&req->refs)) {
                nxt = io_req_find_next(req);
                __io_free_req(req);
        }
        return nxt;
}

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

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

        io_free_req(req);
}

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

        init_task_work(&req->task_work, io_put_req_deferred_cb);
        ret = io_req_task_work_add(req, true);
        if (unlikely(ret)) {
                struct task_struct *tsk;

                tsk = io_wq_get_task(req->ctx->io_wq);
                task_work_add(tsk, &req->task_work, TWA_NONE);
                wake_up_process(tsk);
        }
}

static inline void io_put_req_deferred(struct io_kiocb *req, int refs)
{
        if (refcount_sub_and_test(refs, &req->refs))
                io_free_req_deferred(req);
}

static struct io_wq_work *io_steal_work(struct io_kiocb *req)
{
        struct io_kiocb *nxt;

        /*
         * A ref is owned by io-wq in which context we're. So, if that's the
         * last one, it's safe to steal next work. False negatives are Ok,
         * it just will be re-punted async in io_put_work()
         */
        if (refcount_read(&req->refs) != 1)
                return NULL;

        nxt = io_req_find_next(req);
        return nxt ? &nxt->work : NULL;
}

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

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

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

                io_cqring_overflow_flush(ctx, false, NULL, NULL);
        }

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

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

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

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

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

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

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

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

        return false;
}

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

        do {
                req = list_first_entry(again, struct io_kiocb, inflight_entry);
                list_del(&req->inflight_entry);
                __io_complete_rw(req, -EAGAIN, 0, NULL);
        } while (!list_empty(again));
}

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

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

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

                req = list_first_entry(done, struct io_kiocb, inflight_entry);
                if (READ_ONCE(req->result) == -EAGAIN) {
                        req->result = 0;
                        req->iopoll_completed = 0;
                        list_move_tail(&req->inflight_entry, &again);
                        continue;
                }
                list_del(&req->inflight_entry);

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

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

                if (refcount_dec_and_test(&req->refs))
                        io_req_free_batch(&rb, req);
        }

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

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

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

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

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

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

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

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

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

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

        return ret;
}

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

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

        return 1;
}

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

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

                io_do_iopoll(ctx, &nr_events, 0);

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

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

        /*
         * We disallow the app entering submit/complete with polling, but we
         * still need to lock the ring to prevent racing with polled issue
         * that got punted to a workqueue.
         */
        mutex_lock(&ctx->uring_lock);
        do {
                /*
                 * Don't enter poll loop if we already have events pending.
                 * If we do, we can potentially be spinning for commands that
                 * already triggered a CQE (eg in error).
                 */
                if (io_cqring_events(ctx, false))
                        break;

                /*
                 * If a submit got punted to a workqueue, we can have the
                 * application entering polling for a command before it gets
                 * issued. That app will hold the uring_lock for the duration
                 * of the poll right here, so we need to take a breather every
                 * now and then to ensure that the issue has a chance to add
                 * the poll to the issued list. Otherwise we can spin here
                 * forever, while the workqueue is stuck trying to acquire the
                 * very same mutex.
                 */
                if (!(++iters & 7)) {
                        mutex_unlock(&ctx->uring_lock);
                        io_run_task_work();
                        mutex_lock(&ctx->uring_lock);
                }

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

        mutex_unlock(&ctx->uring_lock);
        return ret;
}

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

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

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

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

        if (res != req->result)
                req_set_fail_links(req);
        if (req->flags & REQ_F_BUFFER_SELECTED)
                cflags = io_put_rw_kbuf(req);
        __io_req_complete(req, res, cflags, cs);
}

#ifdef CONFIG_BLOCK
static bool io_resubmit_prep(struct io_kiocb *req, int error)
{
        struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
        ssize_t ret = -ECANCELED;
        struct iov_iter iter;
        int rw;

        if (error) {
                ret = error;
                goto end_req;
        }

        switch (req->opcode) {
        case IORING_OP_READV:
        case IORING_OP_READ_FIXED:
        case IORING_OP_READ:
                rw = READ;
                break;
        case IORING_OP_WRITEV:
        case IORING_OP_WRITE_FIXED:
        case IORING_OP_WRITE:
                rw = WRITE;
                break;
        default:
                printk_once(KERN_WARNING "io_uring: bad opcode in resubmit %d\n",
                                req->opcode);
                goto end_req;
        }

        if (!req->async_data) {
                ret = io_import_iovec(rw, req, &iovec, &iter, false);
                if (ret < 0)
                        goto end_req;
                ret = io_setup_async_rw(req, iovec, inline_vecs, &iter, false);
                if (!ret)
                        return true;
                kfree(iovec);
        } else {
                return true;
        }
end_req:
        req_set_fail_links(req);
        return false;
}
#endif

static bool io_rw_reissue(struct io_kiocb *req, long res)
{
#ifdef CONFIG_BLOCK
        umode_t mode = file_inode(req->file)->i_mode;
        int ret;

        if (!S_ISBLK(mode) && !S_ISREG(mode))
                return false;
        if ((res != -EAGAIN && res != -EOPNOTSUPP) || io_wq_current_is_worker())
                return false;

        ret = io_sq_thread_acquire_mm(req->ctx, req);

        if (io_resubmit_prep(req, ret)) {
                refcount_inc(&req->refs);
                io_queue_async_work(req);
                return true;
        }

#endif
        return false;
}

static void __io_complete_rw(struct io_kiocb *req, long res, long res2,
                             struct io_comp_state *cs)
{
        if (!io_rw_reissue(req, res))
                io_complete_rw_common(&req->rw.kiocb, res, cs);
}

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

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

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

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

        if (res != -EAGAIN && res != req->result)
                req_set_fail_links(req);

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

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

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

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

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

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

static void __io_state_file_put(struct io_submit_state *state)
{
        if (state->has_refs)
                fput_many(state->file, state->has_refs);
        state->file = NULL;
}

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

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

        if (state->file) {
                if (state->fd == fd) {
                        state->has_refs--;
                        return state->file;
                }
                __io_state_file_put(state);
        }
        state->file = fget_many(fd, state->ios_left);
        if (!state->file)
                return NULL;

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

static bool io_bdev_nowait(struct block_device *bdev)
{
#ifdef CONFIG_BLOCK
        return !bdev || blk_queue_nowait(bdev_get_queue(bdev));
#else
        return true;
#endif
}

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

static void kiocb_done(struct kiocb *kiocb, ssize_t ret,
                       struct io_comp_state *cs)
{
        struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb);
        struct io_async_rw *io = req->async_data;

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

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

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

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

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

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

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

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

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

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

        return len;
}

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

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

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

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

        io_ring_submit_lock(req->ctx, needs_lock);

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

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

        io_ring_submit_unlock(req->ctx, needs_lock);

        return kbuf;
}

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

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

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

        compat_ssize_t clen;
        void __user *buf;
        ssize_t len;

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

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

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

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

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

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

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

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

        return __io_iov_buffer_select(req, iov, needs_lock);
}

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

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

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

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

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

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

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

static ssize_t io_import_iovec(int rw, struct io_kiocb *req,
                               struct iovec **iovec, struct iov_iter *iter,
                               bool needs_lock)
{
        struct io_async_rw *iorw = req->async_data;

        if (!iorw)
                return __io_import_iovec(rw, req, iovec, iter, needs_lock);
        *iovec = NULL;
        return iov_iter_count(&iorw->iter);
}

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

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

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

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

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

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

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

        return ret;
}

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

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

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

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

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

        return  __io_alloc_async_data(req);
}

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

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

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

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

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

static int io_read_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
        ssize_t ret;

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

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

        /* either don't need iovec imported or already have it */
        if (!req->async_data)
                return 0;
        return io_rw_prep_async(req, READ);
}

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

        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);

        init_task_work(&req->task_work, io_req_task_submit);
        percpu_ref_get(&req->ctx->refs);

        /* submit ref gets dropped, acquire a new one */
        refcount_inc(&req->refs);
        ret = io_req_task_work_add(req, true);
        if (unlikely(ret)) {
                struct task_struct *tsk;

                /* queue just for cancelation */
                init_task_work(&req->task_work, io_req_task_cancel);
                tsk = io_wq_get_task(req->ctx->io_wq);
                task_work_add(tsk, &req->task_work, TWA_NONE);
                wake_up_process(tsk);
        }
        return 1;
}

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

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

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

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

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

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

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

        if (rw)
                iter = &rw->iter;

        ret = io_import_iovec(READ, req, &iovec, iter, !force_nonblock);
        if (ret < 0)
                return ret;
        iov_count = iov_iter_count(iter);
        io_size = ret;
        req->result = io_size;
        ret = 0;

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


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

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

        ret = io_iter_do_read(req, iter);

        if (!ret) {
                goto done;
        } else if (ret == -EIOCBQUEUED) {
                ret = 0;
                goto out_free;
        } else if (ret == -EAGAIN) {
                /* IOPOLL retry should happen for io-wq threads */
                if (!force_nonblock && !(req->ctx->flags & IORING_SETUP_IOPOLL))
                        goto done;
                /* no retry on NONBLOCK marked file */
                if (req->file->f_flags & O_NONBLOCK)
                        goto done;
                /* some cases will consume bytes even on error returns */
                iov_iter_revert(iter, iov_count - iov_iter_count(iter));
                ret = 0;
                goto copy_iov;
        } else if (ret < 0) {
                /* make sure -ERESTARTSYS -> -EINTR is done */
                goto done;
        }

        /* read it all, or we did blocking attempt. no retry. */
        if (!iov_iter_count(iter) || !force_nonblock ||
            (req->file->f_flags & O_NONBLOCK))
                goto done;

        io_size -= ret;
copy_iov:
        ret2 = io_setup_async_rw(req, iovec, inline_vecs, iter, true);
        if (ret2) {
                ret = ret2;
                goto out_free;
        }
        if (no_async)
                return -EAGAIN;
        rw = req->async_data;
        /* it's copied and will be cleaned with ->io */
        iovec = NULL;
        /* now use our persistent iterator, if we aren't already */
        iter = &rw->iter;
retry:
        rw->bytes_done += ret;
        /* if we can retry, do so with the callbacks armed */
        if (!io_rw_should_retry(req)) {
                kiocb->ki_flags &= ~IOCB_WAITQ;
                return -EAGAIN;
        }

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

static int io_write_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
        ssize_t ret;

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

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

        /* either don't need iovec imported or already have it */
        if (!req->async_data)
                return 0;
        return io_rw_prep_async(req, WRITE);
}

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

        if (rw)
                iter = &rw->iter;

        ret = io_import_iovec(WRITE, req, &iovec, iter, !force_nonblock);
        if (ret < 0)
                return ret;
        iov_count = iov_iter_count(iter);
        io_size = ret;
        req->result = io_size;

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

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

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

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

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

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

        /*
         * 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 marked file */
        if (ret2 == -EAGAIN && (req->file->f_flags & O_NONBLOCK))
                goto done;
        if (!force_nonblock || ret2 != -EAGAIN) {
                /* IOPOLL retry should happen for io-wq threads */
                if ((req->ctx->flags & IORING_SETUP_IOPOLL) && ret2 == -EAGAIN)
                        goto copy_iov;
done:
                kiocb_done(kiocb, ret2, cs);
        } else {
copy_iov:
                /* some cases will consume bytes even on error returns */
                iov_iter_revert(iter, iov_count - iov_iter_count(iter));
                ret = io_setup_async_rw(req, iovec, inline_vecs, iter, false);
                if (!ret)
                        return -EAGAIN;
        }
out_free:
        /* it's reportedly faster than delegating the null check to kfree() */
        if (iovec)
                kfree(iovec);
        return ret;
}

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

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

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

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

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

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

        return 0;
}

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

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

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

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

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

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

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

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

        if (force_nonblock)
                return -EAGAIN;

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

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

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

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

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

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

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

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

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

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

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

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

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

        /* fsync always requires a blocking context */
        if (force_nonblock)
                return -EAGAIN;

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

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

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

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

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

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

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

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

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

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

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

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

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

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

        return __io_openat_prep(req, sqe);
}

static int io_openat2(struct io_kiocb *req, bool force_nonblock)
{
        struct open_flags op;
        struct file *file;
        int ret;

        if (force_nonblock && !req->open.ignore_nonblock)
                return -EAGAIN;

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

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

        file = do_filp_open(req->open.dfd, req->open.filename, &op);
        if (IS_ERR(file)) {
                put_unused_fd(ret);
                ret = PTR_ERR(file);
                /*
                 * A work-around to ensure that /proc/self works that way
                 * that it should - if we get -EOPNOTSUPP back, then assume
                 * that proc_self_get_link() failed us because we're in async
                 * context. We should be safe to retry this from the task
                 * itself with force_nonblock == false set, as it should not
                 * block on lookup. Would be nice to know this upfront and
                 * avoid the async dance, but doesn't seem feasible.
                 */
                if (ret == -EOPNOTSUPP && io_wq_current_is_worker()) {
                        req->open.ignore_nonblock = true;
                        refcount_inc(&req->refs);
                        io_req_task_queue(req);
                        return 0;
                }
        } else {
                fsnotify_open(file);
                fd_install(ret, file);
        }
err:
        putname(req->open.filename);
        req->flags &= ~REQ_F_NEED_CLEANUP;
        if (ret < 0)
                req_set_fail_links(req);
        io_req_complete(req, ret);
        return 0;
}

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

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

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

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

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

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

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

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

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

        return i;
}

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

        io_ring_submit_lock(ctx, !force_nonblock);

        lockdep_assert_held(&ctx->uring_lock);

        ret = -ENOENT;
        head = idr_find(&ctx->io_buffer_idr, p->bgid);
        if (head)
                ret = __io_remove_buffers(ctx, head, p->bgid, p->nbufs);

        io_ring_submit_lock(ctx, !force_nonblock);
        if (ret < 0)
                req_set_fail_links(req);
        __io_req_complete(req, ret, 0, cs);
        return 0;
}

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

        if (sqe->ioprio || sqe->rw_flags)
                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 (!access_ok(u64_to_user_ptr(p->addr), (p->len * p->nbufs)))
                return -EFAULT;

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

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

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

                buf->addr = addr;
                buf->len = pbuf->len;
                buf->bid = bid;
                addr += pbuf->len;