Merge tag 'io_uring-5.8-2020-06-11' of git://git.kernel.dk/linux-block

Pull io_uring fixes from Jens Axboe:
 "A few late stragglers in here. In particular:

   - Validate full range for provided buffers (Bijan)

   - Fix bad use of kfree() in buffer registration failure (Denis)

   - Don't allow close of ring itself, it's not fully safe. Making it
     fully safe would require making the system call more expensive,
     which isn't worth it.

   - Buffer selection fix

   - Regression fix for O_NONBLOCK retry

   - Make IORING_OP_ACCEPT honor O_NONBLOCK (Jiufei)

   - Restrict opcode handling for SQ/IOPOLL (Pavel)

   - io-wq work handling cleanups and improvements (Pavel, Xiaoguang)

   - IOPOLL race fix (Xiaoguang)"

* tag 'io_uring-5.8-2020-06-11' of git://git.kernel.dk/linux-block:
  io_uring: fix io_kiocb.flags modification race in IOPOLL mode
  io_uring: check file O_NONBLOCK state for accept
  io_uring: avoid unnecessary io_wq_work copy for fast poll feature
  io_uring: avoid whole io_wq_work copy for requests completed inline
  io_uring: allow O_NONBLOCK async retry
  io_wq: add per-wq work handler instead of per work
  io_uring: don't arm a timeout through work.func
  io_uring: remove custom ->func handlers
  io_uring: don't derive close state from ->func
  io_uring: use kvfree() in io_sqe_buffer_register()
  io_uring: validate the full range of provided buffers for access
  io_uring: re-set iov base/len for buffer select retry
  io_uring: move send/recv IOPOLL check into prep
  io_uring: deduplicate io_openat{,2}_prep()
  io_uring: do build_open_how() only once
  io_uring: fix {SQ,IO}POLL with unsupported opcodes
  io_uring: disallow close of ring itself

3 files changed, 201 insertions, 241 deletions

diff --git a/fs/io-wq.c b/fs/io-wq.c
index a5e90ac39e4d..0b65a912b036 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -111,6 +111,7 @@ struct io_wq {
 	unsigned long state;
 
 	free_work_fn *free_work;
+	io_wq_work_fn *do_work;
 
 	struct task_struct *manager;
 	struct user_struct *user;
@@ -523,7 +524,7 @@ get_next:
 
 			hash = io_get_work_hash(work);
 			linked = old_work = work;
-			linked->func(&linked);
+			wq->do_work(&linked);
 			linked = (old_work == linked) ? NULL : linked;
 
 			work = next_hashed;
@@ -780,7 +781,7 @@ static void io_run_cancel(struct io_wq_work *work, struct io_wqe *wqe)
 		struct io_wq_work *old_work = work;
 
 		work->flags |= IO_WQ_WORK_CANCEL;
-		work->func(&work);
+		wq->do_work(&work);
 		work = (work == old_work) ? NULL : work;
 		wq->free_work(old_work);
 	} while (work);
@@ -1018,7 +1019,7 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data)
 	int ret = -ENOMEM, node;
 	struct io_wq *wq;
 
-	if (WARN_ON_ONCE(!data->free_work))
+	if (WARN_ON_ONCE(!data->free_work || !data->do_work))
 		return ERR_PTR(-EINVAL);
 
 	wq = kzalloc(sizeof(*wq), GFP_KERNEL);
@@ -1032,6 +1033,7 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data)
 	}
 
 	wq->free_work = data->free_work;
+	wq->do_work = data->do_work;
 
 	/* caller must already hold a reference to this */
 	wq->user = data->user;
@@ -1088,7 +1090,7 @@ err:
 
 bool io_wq_get(struct io_wq *wq, struct io_wq_data *data)
 {
-	if (data->free_work != wq->free_work)
+	if (data->free_work != wq->free_work || data->do_work != wq->do_work)
 		return false;
 
 	return refcount_inc_not_zero(&wq->use_refs);
diff --git a/fs/io-wq.h b/fs/io-wq.h
index 5ba12de7572f..8e138fa88b9f 100644
--- a/fs/io-wq.h
+++ b/fs/io-wq.h
@@ -85,7 +85,6 @@ static inline void wq_list_del(struct io_wq_work_list *list,
 
 struct io_wq_work {
 	struct io_wq_work_node list;
-	void (*func)(struct io_wq_work **);
 	struct files_struct *files;
 	struct mm_struct *mm;
 	const struct cred *creds;
@@ -94,11 +93,6 @@ struct io_wq_work {
 	pid_t task_pid;
 };
 
-#define INIT_IO_WORK(work, _func)				\
-	do {							\
-		*(work) = (struct io_wq_work){ .func = _func };	\
-	} while (0)						\
-
 static inline struct io_wq_work *wq_next_work(struct io_wq_work *work)
 {
 	if (!work->list.next)
@@ -108,10 +102,12 @@ static inline struct io_wq_work *wq_next_work(struct io_wq_work *work)
 }
 
 typedef void (free_work_fn)(struct io_wq_work *);
+typedef void (io_wq_work_fn)(struct io_wq_work **);
 
 struct io_wq_data {
 	struct user_struct *user;
 
+	io_wq_work_fn *do_work;
 	free_work_fn *free_work;
 };
 
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 26f7bc941d01..155f3d830ddb 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -528,7 +528,6 @@ enum {
 	REQ_F_INFLIGHT_BIT,
 	REQ_F_CUR_POS_BIT,
 	REQ_F_NOWAIT_BIT,
-	REQ_F_IOPOLL_COMPLETED_BIT,
 	REQ_F_LINK_TIMEOUT_BIT,
 	REQ_F_TIMEOUT_BIT,
 	REQ_F_ISREG_BIT,
@@ -540,6 +539,8 @@ enum {
 	REQ_F_POLLED_BIT,
 	REQ_F_BUFFER_SELECTED_BIT,
 	REQ_F_NO_FILE_TABLE_BIT,
+	REQ_F_QUEUE_TIMEOUT_BIT,
+	REQ_F_WORK_INITIALIZED_BIT,
 
 	/* not a real bit, just to check we're not overflowing the space */
 	__REQ_F_LAST_BIT,
@@ -571,8 +572,6 @@ enum {
 	REQ_F_CUR_POS		= BIT(REQ_F_CUR_POS_BIT),
 	/* must not punt to workers */
 	REQ_F_NOWAIT		= BIT(REQ_F_NOWAIT_BIT),
-	/* polled IO has completed */
-	REQ_F_IOPOLL_COMPLETED	= BIT(REQ_F_IOPOLL_COMPLETED_BIT),
 	/* has linked timeout */
 	REQ_F_LINK_TIMEOUT	= BIT(REQ_F_LINK_TIMEOUT_BIT),
 	/* timeout request */
@@ -595,6 +594,10 @@ enum {
 	REQ_F_BUFFER_SELECTED	= BIT(REQ_F_BUFFER_SELECTED_BIT),
 	/* doesn't need file table for this request */
 	REQ_F_NO_FILE_TABLE	= BIT(REQ_F_NO_FILE_TABLE_BIT),
+	/* needs to queue linked timeout */
+	REQ_F_QUEUE_TIMEOUT	= BIT(REQ_F_QUEUE_TIMEOUT_BIT),
+	/* io_wq_work is initialized */
+	REQ_F_WORK_INITIALIZED	= BIT(REQ_F_WORK_INITIALIZED_BIT),
 };
 
 struct async_poll {
@@ -633,6 +636,8 @@ struct io_kiocb {
 	struct io_async_ctx		*io;
 	int				cflags;
 	u8				opcode;
+	/* polled IO has completed */
+	u8				iopoll_completed;
 
 	u16				buf_index;
 
@@ -697,6 +702,8 @@ struct io_op_def {
 	unsigned		needs_mm : 1;
 	/* needs req->file assigned */
 	unsigned		needs_file : 1;
+	/* don't fail if file grab fails */
+	unsigned		needs_file_no_error : 1;
 	/* hash wq insertion if file is a regular file */
 	unsigned		hash_reg_file : 1;
 	/* unbound wq insertion if file is a non-regular file */
@@ -803,6 +810,8 @@ static const struct io_op_def io_op_defs[] = {
 		.needs_fs		= 1,
 	},
 	[IORING_OP_CLOSE] = {
+		.needs_file		= 1,
+		.needs_file_no_error	= 1,
 		.file_table		= 1,
 	},
 	[IORING_OP_FILES_UPDATE] = {
@@ -903,6 +912,19 @@ EXPORT_SYMBOL(io_uring_get_socket);
 
 static void io_file_put_work(struct work_struct *work);
 
+/*
+ * Note: must call io_req_init_async() for the first time you
+ * touch any members of io_wq_work.
+ */
+static inline void io_req_init_async(struct io_kiocb *req)
+{
+	if (req->flags & REQ_F_WORK_INITIALIZED)
+		return;
+
+	memset(&req->work, 0, sizeof(req->work));
+	req->flags |= REQ_F_WORK_INITIALIZED;
+}
+
 static inline bool io_async_submit(struct io_ring_ctx *ctx)
 {
 	return ctx->flags & IORING_SETUP_SQPOLL;
@@ -1029,6 +1051,9 @@ static inline void io_req_work_grab_env(struct io_kiocb *req,
 
 static inline void io_req_work_drop_env(struct io_kiocb *req)
 {
+	if (!(req->flags & REQ_F_WORK_INITIALIZED))
+		return;
+
 	if (req->work.mm) {
 		mmdrop(req->work.mm);
 		req->work.mm = NULL;
@@ -1575,16 +1600,6 @@ static void io_free_req(struct io_kiocb *req)
 		io_queue_async_work(nxt);
 }
 
-static void io_link_work_cb(struct io_wq_work **workptr)
-{
-	struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
-	struct io_kiocb *link;
-
-	link = list_first_entry(&req->link_list, struct io_kiocb, link_list);
-	io_queue_linked_timeout(link);
-	io_wq_submit_work(workptr);
-}
-
 static void io_wq_assign_next(struct io_wq_work **workptr, struct io_kiocb *nxt)
 {
 	struct io_kiocb *link;
@@ -1596,7 +1611,7 @@ static void io_wq_assign_next(struct io_wq_work **workptr, struct io_kiocb *nxt)
 	*workptr = &nxt->work;
 	link = io_prep_linked_timeout(nxt);
 	if (link)
-		nxt->work.func = io_link_work_cb;
+		nxt->flags |= REQ_F_QUEUE_TIMEOUT;
 }
 
 /*
@@ -1781,7 +1796,7 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events,
 		 * If we find a request that requires polling, break out
 		 * and complete those lists first, if we have entries there.
 		 */
-		if (req->flags & REQ_F_IOPOLL_COMPLETED) {
+		if (READ_ONCE(req->iopoll_completed)) {
 			list_move_tail(&req->list, &done);
 			continue;
 		}
@@ -1962,7 +1977,7 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2)
 		req_set_fail_links(req);
 	req->result = res;
 	if (res != -EAGAIN)
-		req->flags |= REQ_F_IOPOLL_COMPLETED;
+		WRITE_ONCE(req->iopoll_completed, 1);
 }
 
 /*
@@ -1995,7 +2010,7 @@ static void io_iopoll_req_issued(struct io_kiocb *req)
 	 * For fast devices, IO may have already completed. If it has, add
 	 * it to the front so we find it first.
 	 */
-	if (req->flags & REQ_F_IOPOLL_COMPLETED)
+	if (READ_ONCE(req->iopoll_completed))
 		list_add(&req->list, &ctx->poll_list);
 	else
 		list_add_tail(&req->list, &ctx->poll_list);
@@ -2063,6 +2078,10 @@ static bool io_file_supports_async(struct file *file, int rw)
 	if (S_ISREG(mode) && file->f_op != &io_uring_fops)
 		return true;
 
+	/* any ->read/write should understand O_NONBLOCK */
+	if (file->f_flags & O_NONBLOCK)
+		return true;
+
 	if (!(file->f_mode & FMODE_NOWAIT))
 		return false;
 
@@ -2105,8 +2124,7 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 		kiocb->ki_ioprio = get_current_ioprio();
 
 	/* don't allow async punt if RWF_NOWAIT was requested */
-	if ((kiocb->ki_flags & IOCB_NOWAIT) ||
-	    (req->file->f_flags & O_NONBLOCK))
+	if (kiocb->ki_flags & IOCB_NOWAIT)
 		req->flags |= REQ_F_NOWAIT;
 
 	if (force_nonblock)
@@ -2120,6 +2138,7 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 		kiocb->ki_flags |= IOCB_HIPRI;
 		kiocb->ki_complete = io_complete_rw_iopoll;
 		req->result = 0;
+		req->iopoll_completed = 0;
 	} else {
 		if (kiocb->ki_flags & IOCB_HIPRI)
 			return -EINVAL;
@@ -2358,8 +2377,14 @@ static ssize_t __io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov,
 static ssize_t io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov,
 				    bool needs_lock)
 {
-	if (req->flags & REQ_F_BUFFER_SELECTED)
+	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)
@@ -2741,7 +2766,8 @@ copy_iov:
 			if (ret)
 				goto out_free;
 			/* any defer here is final, must blocking retry */
-			if (!file_can_poll(req->file))
+			if (!(req->flags & REQ_F_NOWAIT) &&
+			    !file_can_poll(req->file))
 				req->flags |= REQ_F_MUST_PUNT;
 			return -EAGAIN;
 		}
@@ -2761,6 +2787,8 @@ static int __io_splice_prep(struct io_kiocb *req,
 
 	if (req->flags & REQ_F_NEED_CLEANUP)
 		return 0;
+	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
+		return -EINVAL;
 
 	sp->file_in = NULL;
 	sp->len = READ_ONCE(sqe->len);
@@ -2775,8 +2803,14 @@ static int __io_splice_prep(struct io_kiocb *req,
 		return ret;
 	req->flags |= REQ_F_NEED_CLEANUP;
 
-	if (!S_ISREG(file_inode(sp->file_in)->i_mode))
+	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;
 }
@@ -2885,23 +2919,15 @@ static int io_prep_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	return 0;
 }
 
-static bool io_req_cancelled(struct io_kiocb *req)
-{
-	if (req->work.flags & IO_WQ_WORK_CANCEL) {
-		req_set_fail_links(req);
-		io_cqring_add_event(req, -ECANCELED);
-		io_put_req(req);
-		return true;
-	}
-
-	return false;
-}
-
-static void __io_fsync(struct io_kiocb *req)
+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);
@@ -2909,58 +2935,16 @@ static void __io_fsync(struct io_kiocb *req)
 		req_set_fail_links(req);
 	io_cqring_add_event(req, ret);
 	io_put_req(req);
-}
-
-static void io_fsync_finish(struct io_wq_work **workptr)
-{
-	struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
-
-	if (io_req_cancelled(req))
-		return;
-	__io_fsync(req);
-	io_steal_work(req, workptr);
-}
-
-static int io_fsync(struct io_kiocb *req, bool force_nonblock)
-{
-	/* fsync always requires a blocking context */
-	if (force_nonblock) {
-		req->work.func = io_fsync_finish;
-		return -EAGAIN;
-	}
-	__io_fsync(req);
 	return 0;
 }
 
-static void __io_fallocate(struct io_kiocb *req)
-{
-	int ret;
-
-	current->signal->rlim[RLIMIT_FSIZE].rlim_cur = req->fsize;
-	ret = vfs_fallocate(req->file, req->sync.mode, req->sync.off,
-				req->sync.len);
-	current->signal->rlim[RLIMIT_FSIZE].rlim_cur = RLIM_INFINITY;
-	if (ret < 0)
-		req_set_fail_links(req);
-	io_cqring_add_event(req, ret);
-	io_put_req(req);
-}
-
-static void io_fallocate_finish(struct io_wq_work **workptr)
-{
-	struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
-
-	if (io_req_cancelled(req))
-		return;
-	__io_fallocate(req);
-	io_steal_work(req, workptr);
-}
-
 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);
@@ -2971,66 +2955,74 @@ static int io_fallocate_prep(struct io_kiocb *req,
 
 static int io_fallocate(struct io_kiocb *req, bool force_nonblock)
 {
+	int ret;
+
 	/* fallocate always requiring blocking context */
-	if (force_nonblock) {
-		req->work.func = io_fallocate_finish;
+	if (force_nonblock)
 		return -EAGAIN;
-	}
 
-	__io_fallocate(req);
+	current->signal->rlim[RLIMIT_FSIZE].rlim_cur = req->fsize;
+	ret = vfs_fallocate(req->file, req->sync.mode, req->sync.off,
+				req->sync.len);
+	current->signal->rlim[RLIMIT_FSIZE].rlim_cur = RLIM_INFINITY;
+	if (ret < 0)
+		req_set_fail_links(req);
+	io_cqring_add_event(req, ret);
+	io_put_req(req);
 	return 0;
 }
 
-static int io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+static int __io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	const char __user *fname;
 	int ret;
 
-	if (sqe->ioprio || sqe->buf_index)
+	if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_SQPOLL)))
 		return -EINVAL;
-	if (req->flags & REQ_F_FIXED_FILE)
+	if (unlikely(sqe->ioprio || sqe->buf_index))
+		return -EINVAL;
+	if (unlikely(req->flags & REQ_F_FIXED_FILE))
 		return -EBADF;
-	if (req->flags & REQ_F_NEED_CLEANUP)
-		return 0;
 
-	req->open.dfd = READ_ONCE(sqe->fd);
-	req->open.how.mode = READ_ONCE(sqe->len);
-	fname = u64_to_user_ptr(READ_ONCE(sqe->addr));
-	req->open.how.flags = READ_ONCE(sqe->open_flags);
-	if (force_o_largefile())
+	/* open.how should be already initialised */
+	if (!(req->open.how.flags & O_PATH) && force_o_largefile())
 		req->open.how.flags |= O_LARGEFILE;
 
+	req->open.dfd = READ_ONCE(sqe->fd);
+	fname = u64_to_user_ptr(READ_ONCE(sqe->addr));
 	req->open.filename = getname(fname);
 	if (IS_ERR(req->open.filename)) {
 		ret = PTR_ERR(req->open.filename);
 		req->open.filename = NULL;
 		return ret;
 	}
-
 	req->open.nofile = rlimit(RLIMIT_NOFILE);
 	req->flags |= REQ_F_NEED_CLEANUP;
 	return 0;
 }
 
+static int io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	u64 flags, mode;
+
+	if (req->flags & REQ_F_NEED_CLEANUP)
+		return 0;
+	mode = READ_ONCE(sqe->len);
+	flags = READ_ONCE(sqe->open_flags);
+	req->open.how = build_open_how(flags, mode);
+	return __io_openat_prep(req, sqe);
+}
+
 static int io_openat2_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	struct open_how __user *how;
-	const char __user *fname;
 	size_t len;
 	int ret;
 
-	if (sqe->ioprio || sqe->buf_index)
-		return -EINVAL;
-	if (req->flags & REQ_F_FIXED_FILE)
-		return -EBADF;
 	if (req->flags & REQ_F_NEED_CLEANUP)
 		return 0;
-
-	req->open.dfd = READ_ONCE(sqe->fd);
-	fname = u64_to_user_ptr(READ_ONCE(sqe->addr));
 	how = u64_to_user_ptr(READ_ONCE(sqe->addr2));
 	len = READ_ONCE(sqe->len);
-
 	if (len < OPEN_HOW_SIZE_VER0)
 		return -EINVAL;
 
@@ -3039,19 +3031,7 @@ static int io_openat2_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	if (ret)
 		return ret;
 
-	if (!(req->open.how.flags & O_PATH) && force_o_largefile())
-		req->open.how.flags |= O_LARGEFILE;
-
-	req->open.filename = getname(fname);
-	if (IS_ERR(req->open.filename)) {
-		ret = PTR_ERR(req->open.filename);
-		req->open.filename = NULL;
-		return ret;
-	}
-
-	req->open.nofile = rlimit(RLIMIT_NOFILE);
-	req->flags |= REQ_F_NEED_CLEANUP;
-	return 0;
+	return __io_openat_prep(req, sqe);
 }
 
 static int io_openat2(struct io_kiocb *req, bool force_nonblock)
@@ -3091,7 +3071,6 @@ err:
 
 static int io_openat(struct io_kiocb *req, bool force_nonblock)
 {
-	req->open.how = build_open_how(req->open.how.flags, req->open.how.mode);
 	return io_openat2(req, force_nonblock);
 }
 
@@ -3180,7 +3159,7 @@ static int io_provide_buffers_prep(struct io_kiocb *req,
 	p->addr = READ_ONCE(sqe->addr);
 	p->len = READ_ONCE(sqe->len);
 
-	if (!access_ok(u64_to_user_ptr(p->addr), p->len))
+	if (!access_ok(u64_to_user_ptr(p->addr), (p->len * p->nbufs)))
 		return -EFAULT;
 
 	p->bgid = READ_ONCE(sqe->buf_group);
@@ -3258,6 +3237,8 @@ static int io_epoll_ctl_prep(struct io_kiocb *req,
 #if defined(CONFIG_EPOLL)
 	if (sqe->ioprio || sqe->buf_index)
 		return -EINVAL;
+	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
+		return -EINVAL;
 
 	req->epoll.epfd = READ_ONCE(sqe->fd);
 	req->epoll.op = READ_ONCE(sqe->len);
@@ -3302,6 +3283,8 @@ static int io_madvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 #if defined(CONFIG_ADVISE_SYSCALLS) && defined(CONFIG_MMU)
 	if (sqe->ioprio || sqe->buf_index || sqe->off)
 		return -EINVAL;
+	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
+		return -EINVAL;
 
 	req->madvise.addr = READ_ONCE(sqe->addr);
 	req->madvise.len = READ_ONCE(sqe->len);
@@ -3336,6 +3319,8 @@ static int io_fadvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	if (sqe->ioprio || sqe->buf_index || sqe->addr)
 		return -EINVAL;
+	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
+		return -EINVAL;
 
 	req->fadvise.offset = READ_ONCE(sqe->off);
 	req->fadvise.len = READ_ONCE(sqe->len);
@@ -3369,6 +3354,8 @@ static int io_fadvise(struct io_kiocb *req, bool force_nonblock)
 
 static int io_statx_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
+	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
+		return -EINVAL;
 	if (sqe->ioprio || sqe->buf_index)
 		return -EINVAL;
 	if (req->flags & REQ_F_FIXED_FILE)
@@ -3409,10 +3396,14 @@ static int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	/*
 	 * If we queue this for async, it must not be cancellable. That would
-	 * leave the 'file' in an undeterminate state.
+	 * leave the 'file' in an undeterminate state, 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_NO_CANCEL;
 
+	if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_SQPOLL)))
+		return -EINVAL;
 	if (sqe->ioprio || sqe->off || sqe->addr || sqe->len ||
 	    sqe->rw_flags || sqe->buf_index)
 		return -EINVAL;
@@ -3420,53 +3411,41 @@ static int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		return -EBADF;
 
 	req->close.fd = READ_ONCE(sqe->fd);
-	return 0;
-}
-
-/* only called when __close_fd_get_file() is done */
-static void __io_close_finish(struct io_kiocb *req)
-{
-	int ret;
-
-	ret = filp_close(req->close.put_file, req->work.files);
-	if (ret < 0)
-		req_set_fail_links(req);
-	io_cqring_add_event(req, ret);
-	fput(req->close.put_file);
-	io_put_req(req);
-}
-
-static void io_close_finish(struct io_wq_work **workptr)
-{
-	struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
+	if ((req->file && req->file->f_op == &io_uring_fops) ||
+	    req->close.fd == req->ctx->ring_fd)
+		return -EBADF;
 
-	/* not cancellable, don't do io_req_cancelled() */
-	__io_close_finish(req);
-	io_steal_work(req, workptr);
+	req->close.put_file = NULL;
+	return 0;
 }
 
 static int io_close(struct io_kiocb *req, bool force_nonblock)
 {
+	struct io_close *close = &req->close;
 	int ret;
 
-	req->close.put_file = NULL;
-	ret = __close_fd_get_file(req->close.fd, &req->close.put_file);
-	if (ret < 0)
-		return (ret == -ENOENT) ? -EBADF : ret;
+	/* might be already done during nonblock submission */
+	if (!close->put_file) {
+		ret = __close_fd_get_file(close->fd, &close->put_file);
+		if (ret < 0)
+			return (ret == -ENOENT) ? -EBADF : ret;
+	}
 
 	/* if the file has a flush method, be safe and punt to async */
-	if (req->close.put_file->f_op->flush && force_nonblock) {
+	if (close->put_file->f_op->flush && force_nonblock) {
 		/* avoid grabbing files - we don't need the files */
 		req->flags |= REQ_F_NO_FILE_TABLE | REQ_F_MUST_PUNT;
-		req->work.func = io_close_finish;
 		return -EAGAIN;
 	}
 
-	/*
-	 * No ->flush(), safely close from here and just punt the
-	 * fput() to async context.
-	 */
-	__io_close_finish(req);
+	/* No ->flush() or already async, safely close from here */
+	ret = filp_close(close->put_file, req->work.files);
+	if (ret < 0)
+		req_set_fail_links(req);
+	io_cqring_add_event(req, ret);
+	fput(close->put_file);
+	close->put_file = NULL;
+	io_put_req(req);
 	return 0;
 }
 
@@ -3488,38 +3467,20 @@ static int io_prep_sfr(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	return 0;
 }
 
-static void __io_sync_file_range(struct io_kiocb *req)
+static int io_sync_file_range(struct io_kiocb *req, bool force_nonblock)
 {
 	int ret;
 
+	/* sync_file_range always requires a blocking context */
+	if (force_nonblock)
+		return -EAGAIN;
+
 	ret = sync_file_range(req->file, req->sync.off, req->sync.len,
 				req->sync.flags);
 	if (ret < 0)
 		req_set_fail_links(req);
 	io_cqring_add_event(req, ret);
 	io_put_req(req);
-}
-
-
-static void io_sync_file_range_finish(struct io_wq_work **workptr)
-{
-	struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
-
-	if (io_req_cancelled(req))
-		return;
-	__io_sync_file_range(req);
-	io_steal_work(req, workptr);
-}
-
-static int io_sync_file_range(struct io_kiocb *req, bool force_nonblock)
-{
-	/* sync_file_range always requires a blocking context */
-	if (force_nonblock) {
-		req->work.func = io_sync_file_range_finish;
-		return -EAGAIN;
-	}
-
-	__io_sync_file_range(req);
 	return 0;
 }
 
@@ -3545,6 +3506,9 @@ static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	struct io_async_ctx *io = req->io;
 	int ret;
 
+	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
+		return -EINVAL;
+
 	sr->msg_flags = READ_ONCE(sqe->msg_flags);
 	sr->msg = u64_to_user_ptr(READ_ONCE(sqe->addr));
 	sr->len = READ_ONCE(sqe->len);
@@ -3574,9 +3538,6 @@ static int io_sendmsg(struct io_kiocb *req, bool force_nonblock)
 	struct socket *sock;
 	int ret;
 
-	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
-		return -EINVAL;
-
 	sock = sock_from_file(req->file, &ret);
 	if (sock) {
 		struct io_async_ctx io;
@@ -3630,9 +3591,6 @@ static int io_send(struct io_kiocb *req, bool force_nonblock)
 	struct socket *sock;
 	int ret;
 
-	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
-		return -EINVAL;
-
 	sock = sock_from_file(req->file, &ret);
 	if (sock) {
 		struct io_sr_msg *sr = &req->sr_msg;
@@ -3785,6 +3743,9 @@ static int io_recvmsg_prep(struct io_kiocb *req,
 	struct io_async_ctx *io = req->io;
 	int ret;
 
+	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
+		return -EINVAL;
+
 	sr->msg_flags = READ_ONCE(sqe->msg_flags);
 	sr->msg = u64_to_user_ptr(READ_ONCE(sqe->addr));
 	sr->len = READ_ONCE(sqe->len);
@@ -3813,9 +3774,6 @@ static int io_recvmsg(struct io_kiocb *req, bool force_nonblock)
 	struct socket *sock;
 	int ret, cflags = 0;
 
-	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
-		return -EINVAL;
-
 	sock = sock_from_file(req->file, &ret);
 	if (sock) {
 		struct io_buffer *kbuf;
@@ -3877,9 +3835,6 @@ static int io_recv(struct io_kiocb *req, bool force_nonblock)
 	struct socket *sock;
 	int ret, cflags = 0;
 
-	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
-		return -EINVAL;
-
 	sock = sock_from_file(req->file, &ret);
 	if (sock) {
 		struct io_sr_msg *sr = &req->sr_msg;
@@ -3947,49 +3902,30 @@ static int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	return 0;
 }
 
-static int __io_accept(struct io_kiocb *req, bool force_nonblock)
+static int io_accept(struct io_kiocb *req, bool force_nonblock)
 {
 	struct io_accept *accept = &req->accept;
-	unsigned file_flags;
+	unsigned int file_flags = force_nonblock ? O_NONBLOCK : 0;
 	int ret;
 
-	file_flags = force_nonblock ? O_NONBLOCK : 0;
+	if (req->file->f_flags & O_NONBLOCK)
+		req->flags |= REQ_F_NOWAIT;
+
 	ret = __sys_accept4_file(req->file, file_flags, accept->addr,
 					accept->addr_len, accept->flags,
 					accept->nofile);
 	if (ret == -EAGAIN && force_nonblock)
 		return -EAGAIN;
-	if (ret == -ERESTARTSYS)
-		ret = -EINTR;
-	if (ret < 0)
+	if (ret < 0) {
+		if (ret == -ERESTARTSYS)
+			ret = -EINTR;
 		req_set_fail_links(req);
+	}
 	io_cqring_add_event(req, ret);
 	io_put_req(req);
 	return 0;
 }
 
-static void io_accept_finish(struct io_wq_work **workptr)
-{
-	struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
-
-	if (io_req_cancelled(req))
-		return;
-	__io_accept(req, false);
-	io_steal_work(req, workptr);
-}
-
-static int io_accept(struct io_kiocb *req, bool force_nonblock)
-{
-	int ret;
-
-	ret = __io_accept(req, force_nonblock);
-	if (ret == -EAGAIN && force_nonblock) {
-		req->work.func = io_accept_finish;
-		return -EAGAIN;
-	}
-	return 0;
-}
-
 static int io_connect_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	struct io_connect *conn = &req->connect;
@@ -4328,7 +4264,8 @@ static void io_async_task_func(struct callback_head *cb)
 	spin_unlock_irq(&ctx->completion_lock);
 
 	/* restore ->work in case we need to retry again */
-	memcpy(&req->work, &apoll->work, sizeof(req->work));
+	if (req->flags & REQ_F_WORK_INITIALIZED)
+		memcpy(&req->work, &apoll->work, sizeof(req->work));
 	kfree(apoll);
 
 	if (!canceled) {
@@ -4425,7 +4362,8 @@ static bool io_arm_poll_handler(struct io_kiocb *req)
 		return false;
 
 	req->flags |= REQ_F_POLLED;
-	memcpy(&apoll->work, &req->work, sizeof(req->work));
+	if (req->flags & REQ_F_WORK_INITIALIZED)
+		memcpy(&apoll->work, &req->work, sizeof(req->work));
 	had_io = req->io != NULL;
 
 	get_task_struct(current);
@@ -4450,7 +4388,8 @@ static bool io_arm_poll_handler(struct io_kiocb *req)
 		if (!had_io)
 			io_poll_remove_double(req);
 		spin_unlock_irq(&ctx->completion_lock);
-		memcpy(&req->work, &apoll->work, sizeof(req->work));
+		if (req->flags & REQ_F_WORK_INITIALIZED)
+			memcpy(&req->work, &apoll->work, sizeof(req->work));
 		kfree(apoll);
 		return false;
 	}
@@ -4495,7 +4434,9 @@ static bool io_poll_remove_one(struct io_kiocb *req)
 			 * io_req_work_drop_env below when dropping the
 			 * final reference.
 			 */
-			memcpy(&req->work, &apoll->work, sizeof(req->work));
+			if (req->flags & REQ_F_WORK_INITIALIZED)
+				memcpy(&req->work, &apoll->work,
+				       sizeof(req->work));
 			kfree(apoll);
 		}
 	}
@@ -4944,6 +4885,8 @@ static int io_req_defer_prep(struct io_kiocb *req,
 	if (!sqe)
 		return 0;
 
+	io_req_init_async(req);
+
 	if (io_op_defs[req->opcode].file_table) {
 		ret = io_grab_files(req);
 		if (unlikely(ret))
@@ -5381,12 +5324,26 @@ static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 	return 0;
 }
 
+static void io_arm_async_linked_timeout(struct io_kiocb *req)
+{
+	struct io_kiocb *link;
+
+	/* link head's timeout is queued in io_queue_async_work() */
+	if (!(req->flags & REQ_F_QUEUE_TIMEOUT))
+		return;
+
+	link = list_first_entry(&req->link_list, struct io_kiocb, link_list);
+	io_queue_linked_timeout(link);
+}
+
 static void io_wq_submit_work(struct io_wq_work **workptr)
 {
 	struct io_wq_work *work = *workptr;
 	struct io_kiocb *req = container_of(work, struct io_kiocb, work);
 	int ret = 0;
 
+	io_arm_async_linked_timeout(req);
+
 	/* if NO_CANCEL is set, we must still run the work */
 	if ((work->flags & (IO_WQ_WORK_CANCEL|IO_WQ_WORK_NO_CANCEL)) ==
 				IO_WQ_WORK_CANCEL) {
@@ -5437,19 +5394,20 @@ static int io_file_get(struct io_submit_state *state, struct io_kiocb *req,
 			return -EBADF;
 		fd = array_index_nospec(fd, ctx->nr_user_files);
 		file = io_file_from_index(ctx, fd);
-		if (!file)
-			return -EBADF;
-		req->fixed_file_refs = ctx->file_data->cur_refs;
-		percpu_ref_get(req->fixed_file_refs);
+		if (file) {
+			req->fixed_file_refs = ctx->file_data->cur_refs;
+			percpu_ref_get(req->fixed_file_refs);
+		}
 	} else {
 		trace_io_uring_file_get(ctx, fd);
 		file = __io_file_get(state, fd);
-		if (unlikely(!file))
-			return -EBADF;
 	}
 
-	*out_file = file;
-	return 0;
+	if (file || io_op_defs[req->opcode].needs_file_no_error) {
+		*out_file = file;
+		return 0;
+	}
+	return -EBADF;
 }
 
 static int io_req_set_file(struct io_submit_state *state, struct io_kiocb *req,
@@ -5583,7 +5541,8 @@ static void __io_queue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 again:
 	linked_timeout = io_prep_linked_timeout(req);
 
-	if (req->work.creds && req->work.creds != current_cred()) {
+	if ((req->flags & REQ_F_WORK_INITIALIZED) && req->work.creds &&
+	    req->work.creds != current_cred()) {
 		if (old_creds)
 			revert_creds(old_creds);
 		if (old_creds == req->work.creds)
@@ -5606,6 +5565,8 @@ again:
 			goto exit;
 		}
 punt:
+		io_req_init_async(req);
+
 		if (io_op_defs[req->opcode].file_table) {
 			ret = io_grab_files(req);
 			if (ret)
@@ -5858,7 +5819,6 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	refcount_set(&req->refs, 2);
 	req->task = NULL;
 	req->result = 0;
-	INIT_IO_WORK(&req->work, io_wq_submit_work);
 
 	if (unlikely(req->opcode >= IORING_OP_LAST))
 		return -EINVAL;
@@ -5880,6 +5840,7 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
 
 	id = READ_ONCE(sqe->personality);
 	if (id) {
+		io_req_init_async(req);
 		req->work.creds = idr_find(&ctx->personality_idr, id);
 		if (unlikely(!req->work.creds))
 			return -EINVAL;
@@ -6874,6 +6835,7 @@ static int io_init_wq_offload(struct io_ring_ctx *ctx,
 
 	data.user = ctx->user;
 	data.free_work = io_free_work;
+	data.do_work = io_wq_submit_work;
 
 	if (!(p->flags & IORING_SETUP_ATTACH_WQ)) {
 		/* Do QD, or 4 * CPUS, whatever is smallest */
@@ -7155,8 +7117,8 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg,
 
 		ret = 0;
 		if (!pages || nr_pages > got_pages) {
-			kfree(vmas);
-			kfree(pages);
+			kvfree(vmas);
+			kvfree(pages);
 			pages = kvmalloc_array(nr_pages, sizeof(struct page *),
 						GFP_KERNEL);
 			vmas = kvmalloc_array(nr_pages,