1 files changed, 197 insertions, 420 deletions

diff --git a/fs/io_uring.c b/fs/io_uring.c
index a8413f006417..659f8ecba5b7 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -63,7 +63,6 @@
 #include <net/sock.h>
 #include <net/af_unix.h>
 #include <net/scm.h>
-#include <net/busy_poll.h>
 #include <linux/anon_inodes.h>
 #include <linux/sched/mm.h>
 #include <linux/uaccess.h>
@@ -112,8 +111,7 @@
 			IOSQE_IO_DRAIN | IOSQE_CQE_SKIP_SUCCESS)
 
 #define IO_REQ_CLEAN_FLAGS (REQ_F_BUFFER_SELECTED | REQ_F_NEED_CLEANUP | \
-				REQ_F_POLLED | REQ_F_INFLIGHT | REQ_F_CREDS | \
-				REQ_F_ASYNC_DATA)
+				REQ_F_POLLED | REQ_F_CREDS | REQ_F_ASYNC_DATA)
 
 #define IO_TCTX_REFS_CACHE_NR	(1U << 10)
 
@@ -412,11 +410,6 @@ struct io_ring_ctx {
 	struct list_head	sqd_list;
 
 	unsigned long		check_cq_overflow;
-#ifdef CONFIG_NET_RX_BUSY_POLL
-	/* used to track busy poll napi_id */
-	struct list_head	napi_list;
-	spinlock_t		napi_lock;	/* napi_list lock */
-#endif
 
 	struct {
 		unsigned		cached_cq_tail;
@@ -500,7 +493,6 @@ struct io_uring_task {
 	const struct io_ring_ctx *last;
 	struct io_wq		*io_wq;
 	struct percpu_counter	inflight;
-	atomic_t		inflight_tracked;
 	atomic_t		in_idle;
 
 	spinlock_t		task_lock;
@@ -592,7 +584,8 @@ 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;
+	u32				len;
+	u32				flags;
 };
 
 struct io_connect {
@@ -654,10 +647,10 @@ struct io_epoll {
 
 struct io_splice {
 	struct file			*file_out;
-	struct file			*file_in;
 	loff_t				off_out;
 	loff_t				off_in;
 	u64				len;
+	int				splice_fd_in;
 	unsigned int			flags;
 };
 
@@ -1182,8 +1175,11 @@ static int __io_register_rsrc_update(struct io_ring_ctx *ctx, unsigned type,
 				     struct io_uring_rsrc_update2 *up,
 				     unsigned nr_args);
 static void io_clean_op(struct io_kiocb *req);
-static struct file *io_file_get(struct io_ring_ctx *ctx,
-				struct io_kiocb *req, int fd, bool fixed);
+static inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd,
+					     unsigned issue_flags);
+static inline struct file *io_file_get_normal(struct io_kiocb *req, int fd);
+static void io_drop_inflight_file(struct io_kiocb *req);
+static bool io_assign_file(struct io_kiocb *req, unsigned int issue_flags);
 static void __io_queue_sqe(struct io_kiocb *req);
 static void io_rsrc_put_work(struct work_struct *work);
 
@@ -1313,13 +1309,20 @@ static void io_rsrc_refs_refill(struct io_ring_ctx *ctx)
 }
 
 static inline void io_req_set_rsrc_node(struct io_kiocb *req,
-					struct io_ring_ctx *ctx)
+					struct io_ring_ctx *ctx,
+					unsigned int issue_flags)
 {
 	if (!req->fixed_rsrc_refs) {
 		req->fixed_rsrc_refs = &ctx->rsrc_node->refs;
-		ctx->rsrc_cached_refs--;
-		if (unlikely(ctx->rsrc_cached_refs < 0))
-			io_rsrc_refs_refill(ctx);
+
+		if (!(issue_flags & IO_URING_F_UNLOCKED)) {
+			lockdep_assert_held(&ctx->uring_lock);
+			ctx->rsrc_cached_refs--;
+			if (unlikely(ctx->rsrc_cached_refs < 0))
+				io_rsrc_refs_refill(ctx);
+		} else {
+			percpu_ref_get(req->fixed_rsrc_refs);
+		}
 	}
 }
 
@@ -1424,29 +1427,9 @@ static bool io_match_task(struct io_kiocb *head, struct task_struct *task,
 			  bool cancel_all)
 	__must_hold(&req->ctx->timeout_lock)
 {
-	struct io_kiocb *req;
-
 	if (task && head->task != task)
 		return false;
-	if (cancel_all)
-		return true;
-
-	io_for_each_link(req, head) {
-		if (req->flags & REQ_F_INFLIGHT)
-			return true;
-	}
-	return false;
-}
-
-static bool io_match_linked(struct io_kiocb *head)
-{
-	struct io_kiocb *req;
-
-	io_for_each_link(req, head) {
-		if (req->flags & REQ_F_INFLIGHT)
-			return true;
-	}
-	return false;
+	return cancel_all;
 }
 
 /*
@@ -1456,24 +1439,9 @@ static bool io_match_linked(struct io_kiocb *head)
 static bool io_match_task_safe(struct io_kiocb *head, struct task_struct *task,
 			       bool cancel_all)
 {
-	bool matched;
-
 	if (task && head->task != task)
 		return false;
-	if (cancel_all)
-		return true;
-
-	if (head->flags & REQ_F_LINK_TIMEOUT) {
-		struct io_ring_ctx *ctx = head->ctx;
-
-		/* protect against races with linked timeouts */
-		spin_lock_irq(&ctx->timeout_lock);
-		matched = io_match_linked(head);
-		spin_unlock_irq(&ctx->timeout_lock);
-	} else {
-		matched = io_match_linked(head);
-	}
-	return matched;
+	return cancel_all;
 }
 
 static inline bool req_has_async_data(struct io_kiocb *req)
@@ -1595,10 +1563,6 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
 	INIT_WQ_LIST(&ctx->locked_free_list);
 	INIT_DELAYED_WORK(&ctx->fallback_work, io_fallback_req_func);
 	INIT_WQ_LIST(&ctx->submit_state.compl_reqs);
-#ifdef CONFIG_NET_RX_BUSY_POLL
-	INIT_LIST_HEAD(&ctx->napi_list);
-	spin_lock_init(&ctx->napi_lock);
-#endif
 	return ctx;
 err:
 	kfree(ctx->dummy_ubuf);
@@ -1636,14 +1600,6 @@ static inline bool io_req_ffs_set(struct io_kiocb *req)
 	return req->flags & REQ_F_FIXED_FILE;
 }
 
-static inline void io_req_track_inflight(struct io_kiocb *req)
-{
-	if (!(req->flags & REQ_F_INFLIGHT)) {
-		req->flags |= REQ_F_INFLIGHT;
-		atomic_inc(&current->io_uring->inflight_tracked);
-	}
-}
-
 static struct io_kiocb *__io_prep_linked_timeout(struct io_kiocb *req)
 {
 	if (WARN_ON_ONCE(!req->link))
@@ -1687,14 +1643,6 @@ static void io_prep_async_work(struct io_kiocb *req)
 		if (def->unbound_nonreg_file)
 			req->work.flags |= IO_WQ_WORK_UNBOUND;
 	}
-
-	switch (req->opcode) {
-	case IORING_OP_SPLICE:
-	case IORING_OP_TEE:
-		if (!S_ISREG(file_inode(req->splice.file_in)->i_mode))
-			req->work.flags |= IO_WQ_WORK_UNBOUND;
-		break;
-	}
 }
 
 static void io_prep_async_link(struct io_kiocb *req)
@@ -1788,12 +1736,11 @@ static __cold void io_flush_timeouts(struct io_ring_ctx *ctx)
 	__must_hold(&ctx->completion_lock)
 {
 	u32 seq = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts);
+	struct io_kiocb *req, *tmp;
 
 	spin_lock_irq(&ctx->timeout_lock);
-	while (!list_empty(&ctx->timeout_list)) {
+	list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) {
 		u32 events_needed, events_got;
-		struct io_kiocb *req = list_first_entry(&ctx->timeout_list,
-						struct io_kiocb, timeout.list);
 
 		if (io_is_timeout_noseq(req))
 			break;
@@ -1810,7 +1757,6 @@ static __cold void io_flush_timeouts(struct io_ring_ctx *ctx)
 		if (events_got < events_needed)
 			break;
 
-		list_del_init(&req->timeout.list);
 		io_kill_timeout(req, 0);
 	}
 	ctx->cq_last_tm_flush = seq;
@@ -2562,6 +2508,8 @@ static void io_req_task_work_add(struct io_kiocb *req, bool priority)
 
 	WARN_ON_ONCE(!tctx);
 
+	io_drop_inflight_file(req);
+
 	spin_lock_irqsave(&tctx->task_lock, flags);
 	if (priority)
 		wq_list_add_tail(&req->io_task_work.node, &tctx->prior_task_list);
@@ -3186,42 +3134,11 @@ static inline bool io_file_supports_nowait(struct io_kiocb *req)
 
 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;
-	struct file *file = req->file;
 	unsigned ioprio;
 	int ret;
 
-	if (!io_req_ffs_set(req))
-		req->flags |= io_file_get_flags(file) << REQ_F_SUPPORT_NOWAIT_BIT;
-
 	kiocb->ki_pos = READ_ONCE(sqe->off);
-	kiocb->ki_flags = iocb_flags(file);
-	ret = kiocb_set_rw_flags(kiocb, READ_ONCE(sqe->rw_flags));
-	if (unlikely(ret))
-		return ret;
-
-	/*
-	 * If the file is marked O_NONBLOCK, still allow retry for it if it
-	 * supports async. Otherwise it's impossible to use O_NONBLOCK files
-	 * reliably. If not, or it IOCB_NOWAIT is set, don't retry.
-	 */
-	if ((kiocb->ki_flags & IOCB_NOWAIT) ||
-	    ((file->f_flags & O_NONBLOCK) && !io_file_supports_nowait(req)))
-		req->flags |= REQ_F_NOWAIT;
-
-	if (ctx->flags & IORING_SETUP_IOPOLL) {
-		if (!(kiocb->ki_flags & IOCB_DIRECT) || !file->f_op->iopoll)
-			return -EOPNOTSUPP;
-
-		kiocb->ki_flags |= IOCB_HIPRI | IOCB_ALLOC_CACHE;
-		kiocb->ki_complete = io_complete_rw_iopoll;
-		req->iopoll_completed = 0;
-	} else {
-		if (kiocb->ki_flags & IOCB_HIPRI)
-			return -EINVAL;
-		kiocb->ki_complete = io_complete_rw;
-	}
 
 	ioprio = READ_ONCE(sqe->ioprio);
 	if (ioprio) {
@@ -3237,6 +3154,7 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	req->imu = NULL;
 	req->rw.addr = READ_ONCE(sqe->addr);
 	req->rw.len = READ_ONCE(sqe->len);
+	req->rw.flags = READ_ONCE(sqe->rw_flags);
 	req->buf_index = READ_ONCE(sqe->buf_index);
 	return 0;
 }
@@ -3367,7 +3285,8 @@ static int __io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter
 	return 0;
 }
 
-static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter)
+static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter,
+			   unsigned int issue_flags)
 {
 	struct io_mapped_ubuf *imu = req->imu;
 	u16 index, buf_index = req->buf_index;
@@ -3377,7 +3296,7 @@ static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter)
 
 		if (unlikely(buf_index >= ctx->nr_user_bufs))
 			return -EFAULT;
-		io_req_set_rsrc_node(req, ctx);
+		io_req_set_rsrc_node(req, ctx, issue_flags);
 		index = array_index_nospec(buf_index, ctx->nr_user_bufs);
 		imu = READ_ONCE(ctx->user_bufs[index]);
 		req->imu = imu;
@@ -3539,7 +3458,7 @@ static struct iovec *__io_import_iovec(int rw, struct io_kiocb *req,
 	ssize_t ret;
 
 	if (opcode == IORING_OP_READ_FIXED || opcode == IORING_OP_WRITE_FIXED) {
-		ret = io_import_fixed(req, rw, iter);
+		ret = io_import_fixed(req, rw, iter, issue_flags);
 		if (ret)
 			return ERR_PTR(ret);
 		return NULL;
@@ -3740,13 +3659,6 @@ static inline int io_rw_prep_async(struct io_kiocb *req, int rw)
 	return 0;
 }
 
-static int io_read_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
-{
-	if (unlikely(!(req->file->f_mode & FMODE_READ)))
-		return -EBADF;
-	return io_prep_rw(req, sqe);
-}
-
 /*
  * This is our waitqueue callback handler, registered through __folio_lock_async()
  * when we initially tried to do the IO with the iocb armed our waitqueue.
@@ -3834,6 +3746,49 @@ static bool need_read_all(struct io_kiocb *req)
 		S_ISBLK(file_inode(req->file)->i_mode);
 }
 
+static int io_rw_init_file(struct io_kiocb *req, fmode_t mode)
+{
+	struct kiocb *kiocb = &req->rw.kiocb;
+	struct io_ring_ctx *ctx = req->ctx;
+	struct file *file = req->file;
+	int ret;
+
+	if (unlikely(!file || !(file->f_mode & mode)))
+		return -EBADF;
+
+	if (!io_req_ffs_set(req))
+		req->flags |= io_file_get_flags(file) << REQ_F_SUPPORT_NOWAIT_BIT;
+
+	kiocb->ki_flags = iocb_flags(file);
+	ret = kiocb_set_rw_flags(kiocb, req->rw.flags);
+	if (unlikely(ret))
+		return ret;
+
+	/*
+	 * If the file is marked O_NONBLOCK, still allow retry for it if it
+	 * supports async. Otherwise it's impossible to use O_NONBLOCK files
+	 * reliably. If not, or it IOCB_NOWAIT is set, don't retry.
+	 */
+	if ((kiocb->ki_flags & IOCB_NOWAIT) ||
+	    ((file->f_flags & O_NONBLOCK) && !io_file_supports_nowait(req)))
+		req->flags |= REQ_F_NOWAIT;
+
+	if (ctx->flags & IORING_SETUP_IOPOLL) {
+		if (!(kiocb->ki_flags & IOCB_DIRECT) || !file->f_op->iopoll)
+			return -EOPNOTSUPP;
+
+		kiocb->ki_flags |= IOCB_HIPRI | IOCB_ALLOC_CACHE;
+		kiocb->ki_complete = io_complete_rw_iopoll;
+		req->iopoll_completed = 0;
+	} else {
+		if (kiocb->ki_flags & IOCB_HIPRI)
+			return -EINVAL;
+		kiocb->ki_complete = io_complete_rw;
+	}
+
+	return 0;
+}
+
 static int io_read(struct io_kiocb *req, unsigned int issue_flags)
 {
 	struct io_rw_state __s, *s = &__s;
@@ -3869,6 +3824,9 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags)
 		iov_iter_restore(&s->iter, &s->iter_state);
 		iovec = NULL;
 	}
+	ret = io_rw_init_file(req, FMODE_READ);
+	if (unlikely(ret))
+		return ret;
 	req->result = iov_iter_count(&s->iter);
 
 	if (force_nonblock) {
@@ -3972,13 +3930,6 @@ out_free:
 	return 0;
 }
 
-static int io_write_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
-{
-	if (unlikely(!(req->file->f_mode & FMODE_WRITE)))
-		return -EBADF;
-	return io_prep_rw(req, sqe);
-}
-
 static int io_write(struct io_kiocb *req, unsigned int issue_flags)
 {
 	struct io_rw_state __s, *s = &__s;
@@ -3999,6 +3950,9 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags)
 		iov_iter_restore(&s->iter, &s->iter_state);
 		iovec = NULL;
 	}
+	ret = io_rw_init_file(req, FMODE_WRITE);
+	if (unlikely(ret))
+		return ret;
 	req->result = iov_iter_count(&s->iter);
 
 	if (force_nonblock) {
@@ -4369,18 +4323,11 @@ static int __io_splice_prep(struct io_kiocb *req,
 	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(req->ctx, 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;
+	sp->splice_fd_in = READ_ONCE(sqe->splice_fd_in);
 	return 0;
 }
 
@@ -4395,20 +4342,29 @@ static int io_tee_prep(struct io_kiocb *req,
 static int io_tee(struct io_kiocb *req, unsigned int issue_flags)
 {
 	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;
+	struct file *in;
 	long ret = 0;
 
 	if (issue_flags & IO_URING_F_NONBLOCK)
 		return -EAGAIN;
+
+	if (sp->flags & SPLICE_F_FD_IN_FIXED)
+		in = io_file_get_fixed(req, sp->splice_fd_in, IO_URING_F_UNLOCKED);
+	else
+		in = io_file_get_normal(req, sp->splice_fd_in);
+	if (!in) {
+		ret = -EBADF;
+		goto done;
+	}
+
 	if (sp->len)
 		ret = do_tee(in, out, sp->len, flags);
 
 	if (!(sp->flags & SPLICE_F_FD_IN_FIXED))
 		io_put_file(in);
-	req->flags &= ~REQ_F_NEED_CLEANUP;
-
+done:
 	if (ret != sp->len)
 		req_set_fail(req);
 	io_req_complete(req, ret);
@@ -4427,15 +4383,24 @@ static int io_splice_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 static int io_splice(struct io_kiocb *req, unsigned int issue_flags)
 {
 	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;
+	struct file *in;
 	long ret = 0;
 
 	if (issue_flags & IO_URING_F_NONBLOCK)
 		return -EAGAIN;
 
+	if (sp->flags & SPLICE_F_FD_IN_FIXED)
+		in = io_file_get_fixed(req, sp->splice_fd_in, IO_URING_F_UNLOCKED);
+	else
+		in = io_file_get_normal(req, sp->splice_fd_in);
+	if (!in) {
+		ret = -EBADF;
+		goto done;
+	}
+
 	poff_in = (sp->off_in == -1) ? NULL : &sp->off_in;
 	poff_out = (sp->off_out == -1) ? NULL : &sp->off_out;
 
@@ -4444,8 +4409,7 @@ static int io_splice(struct io_kiocb *req, unsigned int issue_flags)
 
 	if (!(sp->flags & SPLICE_F_FD_IN_FIXED))
 		io_put_file(in);
-	req->flags &= ~REQ_F_NEED_CLEANUP;
-
+done:
 	if (ret != sp->len)
 		req_set_fail(req);
 	io_req_complete(req, ret);
@@ -4513,9 +4477,6 @@ static int io_fsync_prep(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 ||
@@ -5757,108 +5718,6 @@ IO_NETOP_FN(send);
 IO_NETOP_FN(recv);
 #endif /* CONFIG_NET */
 
-#ifdef CONFIG_NET_RX_BUSY_POLL
-
-#define NAPI_TIMEOUT			(60 * SEC_CONVERSION)
-
-struct napi_entry {
-	struct list_head	list;
-	unsigned int		napi_id;
-	unsigned long		timeout;
-};
-
-/*
- * Add busy poll NAPI ID from sk.
- */
-static void io_add_napi(struct file *file, struct io_ring_ctx *ctx)
-{
-	unsigned int napi_id;
-	struct socket *sock;
-	struct sock *sk;
-	struct napi_entry *ne;
-
-	if (!net_busy_loop_on())
-		return;
-
-	sock = sock_from_file(file);
-	if (!sock)
-		return;
-
-	sk = sock->sk;
-	if (!sk)
-		return;
-
-	napi_id = READ_ONCE(sk->sk_napi_id);
-
-	/* Non-NAPI IDs can be rejected */
-	if (napi_id < MIN_NAPI_ID)
-		return;
-
-	spin_lock(&ctx->napi_lock);
-	list_for_each_entry(ne, &ctx->napi_list, list) {
-		if (ne->napi_id == napi_id) {
-			ne->timeout = jiffies + NAPI_TIMEOUT;
-			goto out;
-		}
-	}
-
-	ne = kmalloc(sizeof(*ne), GFP_NOWAIT);
-	if (!ne)
-		goto out;
-
-	ne->napi_id = napi_id;
-	ne->timeout = jiffies + NAPI_TIMEOUT;
-	list_add_tail(&ne->list, &ctx->napi_list);
-out:
-	spin_unlock(&ctx->napi_lock);
-}
-
-static inline void io_check_napi_entry_timeout(struct napi_entry *ne)
-{
-	if (time_after(jiffies, ne->timeout)) {
-		list_del(&ne->list);
-		kfree(ne);
-	}
-}
-
-/*
- * Busy poll if globally on and supporting sockets found
- */
-static bool io_napi_busy_loop(struct list_head *napi_list)
-{
-	struct napi_entry *ne, *n;
-
-	list_for_each_entry_safe(ne, n, napi_list, list) {
-		napi_busy_loop(ne->napi_id, NULL, NULL, true,
-			       BUSY_POLL_BUDGET);
-		io_check_napi_entry_timeout(ne);
-	}
-	return !list_empty(napi_list);
-}
-
-static void io_free_napi_list(struct io_ring_ctx *ctx)
-{
-	spin_lock(&ctx->napi_lock);
-	while (!list_empty(&ctx->napi_list)) {
-		struct napi_entry *ne =
-			list_first_entry(&ctx->napi_list, struct napi_entry,
-					 list);
-
-		list_del(&ne->list);
-		kfree(ne);
-	}
-	spin_unlock(&ctx->napi_lock);
-}
-#else
-static inline void io_add_napi(struct file *file, struct io_ring_ctx *ctx)
-{
-}
-
-static inline void io_free_napi_list(struct io_ring_ctx *ctx)
-{
-}
-#endif /* CONFIG_NET_RX_BUSY_POLL */
-
 struct io_poll_table {
 	struct poll_table_struct pt;
 	struct io_kiocb *req;
@@ -5972,7 +5831,7 @@ static void io_poll_remove_entries(struct io_kiocb *req)
  * either spurious wakeup or multishot CQE is served. 0 when it's done with
  * the request, then the mask is stored in req->result.
  */
-static int io_poll_check_events(struct io_kiocb *req)
+static int io_poll_check_events(struct io_kiocb *req, bool locked)
 {
 	struct io_ring_ctx *ctx = req->ctx;
 	struct io_poll_iocb *poll = io_poll_get_single(req);
@@ -5994,7 +5853,10 @@ static int io_poll_check_events(struct io_kiocb *req)
 		if (!req->result) {
 			struct poll_table_struct pt = { ._key = req->cflags };
 
-			req->result = vfs_poll(req->file, &pt) & req->cflags;
+			if (unlikely(!io_assign_file(req, IO_URING_F_UNLOCKED)))
+				req->result = -EBADF;
+			else
+				req->result = vfs_poll(req->file, &pt) & req->cflags;
 		}
 
 		/* multishot, just fill an CQE and proceed */
@@ -6010,7 +5872,6 @@ static int io_poll_check_events(struct io_kiocb *req)
 			if (unlikely(!filled))
 				return -ECANCELED;
 			io_cqring_ev_posted(ctx);
-			io_add_napi(req->file, ctx);
 		} else if (req->result) {
 			return 0;
 		}
@@ -6029,7 +5890,7 @@ static void io_poll_task_func(struct io_kiocb *req, bool *locked)
 	struct io_ring_ctx *ctx = req->ctx;
 	int ret;
 
-	ret = io_poll_check_events(req);
+	ret = io_poll_check_events(req, *locked);
 	if (ret > 0)
 		return;
 
@@ -6054,7 +5915,7 @@ static void io_apoll_task_func(struct io_kiocb *req, bool *locked)
 	struct io_ring_ctx *ctx = req->ctx;
 	int ret;
 
-	ret = io_poll_check_events(req);
+	ret = io_poll_check_events(req, *locked);
 	if (ret > 0)
 		return;
 
@@ -6261,7 +6122,6 @@ static int __io_arm_poll_handler(struct io_kiocb *req,
 		__io_poll_execute(req, mask, poll->events);
 		return 0;
 	}
-	io_add_napi(req->file, req->ctx);
 
 	/*
 	 * Release ownership. If someone tried to queue a tw while it was
@@ -6766,6 +6626,7 @@ static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 	if (data->ts.tv_sec < 0 || data->ts.tv_nsec < 0)
 		return -EINVAL;
 
+	INIT_LIST_HEAD(&req->timeout.list);
 	data->mode = io_translate_timeout_mode(flags);
 	hrtimer_init(&data->timer, io_timeout_get_clock(data), data->mode);
 
@@ -6992,11 +6853,10 @@ static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	case IORING_OP_READV:
 	case IORING_OP_READ_FIXED:
 	case IORING_OP_READ:
-		return io_read_prep(req, sqe);
 	case IORING_OP_WRITEV:
 	case IORING_OP_WRITE_FIXED:
 	case IORING_OP_WRITE:
-		return io_write_prep(req, sqe);
+		return io_prep_rw(req, sqe);
 	case IORING_OP_POLL_ADD:
 		return io_poll_add_prep(req, sqe);
 	case IORING_OP_POLL_REMOVE:
@@ -7179,11 +7039,6 @@ static void io_clean_op(struct io_kiocb *req)
 			kfree(io->free_iov);
 			break;
 			}
-		case IORING_OP_SPLICE:
-		case IORING_OP_TEE:
-			if (!(req->splice.flags & SPLICE_F_FD_IN_FIXED))
-				io_put_file(req->splice.file_in);
-			break;
 		case IORING_OP_OPENAT:
 		case IORING_OP_OPENAT2:
 			if (req->open.filename)
@@ -7218,11 +7073,6 @@ static void io_clean_op(struct io_kiocb *req)
 		kfree(req->apoll);
 		req->apoll = NULL;
 	}
-	if (req->flags & REQ_F_INFLIGHT) {
-		struct io_uring_task *tctx = req->task->io_uring;
-
-		atomic_dec(&tctx->inflight_tracked);
-	}
 	if (req->flags & REQ_F_CREDS)
 		put_cred(req->creds);
 	if (req->flags & REQ_F_ASYNC_DATA) {
@@ -7232,6 +7082,23 @@ static void io_clean_op(struct io_kiocb *req)
 	req->flags &= ~IO_REQ_CLEAN_FLAGS;
 }
 
+static bool io_assign_file(struct io_kiocb *req, unsigned int issue_flags)
+{
+	if (req->file || !io_op_defs[req->opcode].needs_file)
+		return true;
+
+	if (req->flags & REQ_F_FIXED_FILE)
+		req->file = io_file_get_fixed(req, req->work.fd, issue_flags);
+	else
+		req->file = io_file_get_normal(req, req->work.fd);
+	if (req->file)
+		return true;
+
+	req_set_fail(req);
+	req->result = -EBADF;
+	return false;
+}
+
 static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
 {
 	const struct cred *creds = NULL;
@@ -7242,6 +7109,8 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
 
 	if (!io_op_defs[req->opcode].audit_skip)
 		audit_uring_entry(req->opcode);
+	if (unlikely(!io_assign_file(req, issue_flags)))
+		return -EBADF;
 
 	switch (req->opcode) {
 	case IORING_OP_NOP:
@@ -7386,10 +7255,11 @@ static struct io_wq_work *io_wq_free_work(struct io_wq_work *work)
 static void io_wq_submit_work(struct io_wq_work *work)
 {
 	struct io_kiocb *req = container_of(work, struct io_kiocb, work);
+	const struct io_op_def *def = &io_op_defs[req->opcode];
 	unsigned int issue_flags = IO_URING_F_UNLOCKED;
 	bool needs_poll = false;
 	struct io_kiocb *timeout;
-	int ret = 0;
+	int ret = 0, err = -ECANCELED;
 
 	/* one will be dropped by ->io_free_work() after returning to io-wq */
 	if (!(req->flags & REQ_F_REFCOUNT))
@@ -7401,14 +7271,18 @@ static void io_wq_submit_work(struct io_wq_work *work)
 	if (timeout)
 		io_queue_linked_timeout(timeout);
 
+	if (!io_assign_file(req, issue_flags)) {
+		err = -EBADF;
+		work->flags |= IO_WQ_WORK_CANCEL;
+	}
+
 	/* either cancelled or io-wq is dying, so don't touch tctx->iowq */
 	if (work->flags & IO_WQ_WORK_CANCEL) {
-		io_req_task_queue_fail(req, -ECANCELED);
+		io_req_task_queue_fail(req, err);
 		return;
 	}
 
 	if (req->flags & REQ_F_FORCE_ASYNC) {
-		const struct io_op_def *def = &io_op_defs[req->opcode];
 		bool opcode_poll = def->pollin || def->pollout;
 
 		if (opcode_poll && file_can_poll(req->file)) {
@@ -7465,46 +7339,56 @@ static void io_fixed_file_set(struct io_fixed_file *file_slot, struct file *file
 	file_slot->file_ptr = file_ptr;
 }
 
-static inline struct file *io_file_get_fixed(struct io_ring_ctx *ctx,
-					     struct io_kiocb *req, int fd)
+static inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd,
+					     unsigned int issue_flags)
 {
-	struct file *file;
+	struct io_ring_ctx *ctx = req->ctx;
+	struct file *file = NULL;
 	unsigned long file_ptr;
 
+	if (issue_flags & IO_URING_F_UNLOCKED)
+		mutex_lock(&ctx->uring_lock);
+
 	if (unlikely((unsigned int)fd >= ctx->nr_user_files))
-		return NULL;
+		goto out;
 	fd = array_index_nospec(fd, ctx->nr_user_files);
 	file_ptr = io_fixed_file_slot(&ctx->file_table, fd)->file_ptr;
 	file = (struct file *) (file_ptr & FFS_MASK);
 	file_ptr &= ~FFS_MASK;
 	/* mask in overlapping REQ_F and FFS bits */
 	req->flags |= (file_ptr << REQ_F_SUPPORT_NOWAIT_BIT);
-	io_req_set_rsrc_node(req, ctx);
+	io_req_set_rsrc_node(req, ctx, 0);
+out:
+	if (issue_flags & IO_URING_F_UNLOCKED)
+		mutex_unlock(&ctx->uring_lock);
 	return file;
 }
 
-static struct file *io_file_get_normal(struct io_ring_ctx *ctx,
-				       struct io_kiocb *req, int fd)
+/*
+ * Drop the file for requeue operations. Only used of req->file is the
+ * io_uring descriptor itself.
+ */
+static void io_drop_inflight_file(struct io_kiocb *req)
+{
+	if (unlikely(req->flags & REQ_F_INFLIGHT)) {
+		fput(req->file);
+		req->file = NULL;
+		req->flags &= ~REQ_F_INFLIGHT;
+	}
+}
+
+static struct file *io_file_get_normal(struct io_kiocb *req, int fd)
 {
 	struct file *file = fget(fd);
 
-	trace_io_uring_file_get(ctx, req, req->user_data, fd);
+	trace_io_uring_file_get(req->ctx, req, req->user_data, fd);
 
 	/* we don't allow fixed io_uring files */
-	if (file && unlikely(file->f_op == &io_uring_fops))
-		io_req_track_inflight(req);
+	if (file && file->f_op == &io_uring_fops)
+		req->flags |= REQ_F_INFLIGHT;
 	return file;
 }
 
-static inline struct file *io_file_get(struct io_ring_ctx *ctx,
-				       struct io_kiocb *req, int fd, bool fixed)
-{
-	if (fixed)
-		return io_file_get_fixed(ctx, req, fd);
-	else
-		return io_file_get_normal(ctx, req, fd);
-}
-
 static void io_req_task_link_timeout(struct io_kiocb *req, bool *locked)
 {
 	struct io_kiocb *prev = req->timeout.prev;
@@ -7744,6 +7628,8 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	if (io_op_defs[opcode].needs_file) {
 		struct io_submit_state *state = &ctx->submit_state;
 
+		req->work.fd = READ_ONCE(sqe->fd);
+
 		/*
 		 * Plug now if we have more than 2 IO left after this, and the
 		 * target is potentially a read/write to block based storage.
@@ -7753,11 +7639,6 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
 			state->need_plug = false;
 			blk_start_plug_nr_ios(&state->plug, state->submit_nr);
 		}
-
-		req->file = io_file_get(ctx, req, READ_ONCE(sqe->fd),
-					(sqe_flags & IOSQE_FIXED_FILE));
-		if (unlikely(!req->file))
-			return -EBADF;
 	}
 
 	personality = READ_ONCE(sqe->personality);
@@ -8032,13 +7913,7 @@ static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries)
 		    !(ctx->flags & IORING_SETUP_R_DISABLED))
 			ret = io_submit_sqes(ctx, to_submit);
 		mutex_unlock(&ctx->uring_lock);
-#ifdef CONFIG_NET_RX_BUSY_POLL
-		spin_lock(&ctx->napi_lock);
-		if (!list_empty(&ctx->napi_list) &&
-		    io_napi_busy_loop(&ctx->napi_list))
-			++ret;
-		spin_unlock(&ctx->napi_lock);
-#endif
+
 		if (to_submit && wq_has_sleeper(&ctx->sqo_sq_wait))
 			wake_up(&ctx->sqo_sq_wait);
 		if (creds)
@@ -8176,9 +8051,6 @@ struct io_wait_queue {
 	struct io_ring_ctx *ctx;
 	unsigned cq_tail;
 	unsigned nr_timeouts;
-#ifdef CONFIG_NET_RX_BUSY_POLL
-	unsigned busy_poll_to;
-#endif
 };
 
 static inline bool io_should_wake(struct io_wait_queue *iowq)
@@ -8240,87 +8112,6 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx,
 	return 1;
 }
 
-#ifdef CONFIG_NET_RX_BUSY_POLL
-static void io_adjust_busy_loop_timeout(struct timespec64 *ts,
-					struct io_wait_queue *iowq)
-{
-	unsigned busy_poll_to = READ_ONCE(sysctl_net_busy_poll);
-	struct timespec64 pollto = ns_to_timespec64(1000 * (s64)busy_poll_to);
-
-	if (timespec64_compare(ts, &pollto) > 0) {
-		*ts = timespec64_sub(*ts, pollto);
-		iowq->busy_poll_to = busy_poll_to;
-	} else {
-		u64 to = timespec64_to_ns(ts);
-
-		do_div(to, 1000);
-		iowq->busy_poll_to = to;
-		ts->tv_sec = 0;
-		ts->tv_nsec = 0;
-	}
-}
-
-static inline bool io_busy_loop_timeout(unsigned long start_time,
-					unsigned long bp_usec)
-{
-	if (bp_usec) {
-		unsigned long end_time = start_time + bp_usec;
-		unsigned long now = busy_loop_current_time();
-
-		return time_after(now, end_time);
-	}
-	return true;
-}
-
-static bool io_busy_loop_end(void *p, unsigned long start_time)
-{
-	struct io_wait_queue *iowq = p;
-
-	return signal_pending(current) ||
-	       io_should_wake(iowq) ||
-	       io_busy_loop_timeout(start_time, iowq->busy_poll_to);
-}
-
-static void io_blocking_napi_busy_loop(struct list_head *napi_list,
-				       struct io_wait_queue *iowq)
-{
-	unsigned long start_time =
-		list_is_singular(napi_list) ? 0 :
-		busy_loop_current_time();
-
-	do {
-		if (list_is_singular(napi_list)) {
-			struct napi_entry *ne =
-				list_first_entry(napi_list,
-						 struct napi_entry, list);
-
-			napi_busy_loop(ne->napi_id, io_busy_loop_end, iowq,
-				       true, BUSY_POLL_BUDGET);
-			io_check_napi_entry_timeout(ne);
-			break;
-		}
-	} while (io_napi_busy_loop(napi_list) &&
-		 !io_busy_loop_end(iowq, start_time));
-}
-
-static void io_putback_napi_list(struct io_ring_ctx *ctx,
-				 struct list_head *napi_list)
-{
-	struct napi_entry *cne, *lne;
-
-	spin_lock(&ctx->napi_lock);
-	list_for_each_entry(cne, &ctx->napi_list, list)
-		list_for_each_entry(lne, napi_list, list)
-			if (cne->napi_id == lne->napi_id) {
-				list_del(&lne->list);
-				kfree(lne);
-				break;
-			}
-	list_splice(napi_list, &ctx->napi_list);
-	spin_unlock(&ctx->napi_lock);
-}
-#endif /* CONFIG_NET_RX_BUSY_POLL */
-
 /*
  * Wait until events become available, if we don't already have some. The
  * application must reap them itself, as they reside on the shared cq ring.
@@ -8333,9 +8124,6 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 	struct io_rings *rings = ctx->rings;
 	ktime_t timeout = KTIME_MAX;
 	int ret;
-#ifdef CONFIG_NET_RX_BUSY_POLL
-	LIST_HEAD(local_napi_list);
-#endif
 
 	do {
 		io_cqring_overflow_flush(ctx);
@@ -8358,29 +8146,13 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 			return ret;
 	}
 
-#ifdef CONFIG_NET_RX_BUSY_POLL
-	iowq.busy_poll_to = 0;
-	if (!(ctx->flags & IORING_SETUP_SQPOLL)) {
-		spin_lock(&ctx->napi_lock);
-		list_splice_init(&ctx->napi_list, &local_napi_list);
-		spin_unlock(&ctx->napi_lock);
-	}
-#endif
 	if (uts) {
 		struct timespec64 ts;
 
 		if (get_timespec64(&ts, uts))
 			return -EFAULT;
-#ifdef CONFIG_NET_RX_BUSY_POLL
-		if (!list_empty(&local_napi_list))
-			io_adjust_busy_loop_timeout(&ts, &iowq);
-#endif
 		timeout = ktime_add_ns(timespec64_to_ktime(ts), ktime_get_ns());
 	}
-#ifdef CONFIG_NET_RX_BUSY_POLL
-	else if (!list_empty(&local_napi_list))
-		iowq.busy_poll_to = READ_ONCE(sysctl_net_busy_poll);
-#endif
 
 	init_waitqueue_func_entry(&iowq.wq, io_wake_function);
 	iowq.wq.private = current;
@@ -8390,12 +8162,6 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 	iowq.cq_tail = READ_ONCE(ctx->rings->cq.head) + min_events;
 
 	trace_io_uring_cqring_wait(ctx, min_events);
-#ifdef CONFIG_NET_RX_BUSY_POLL
-	if (iowq.busy_poll_to)
-		io_blocking_napi_busy_loop(&local_napi_list, &iowq);
-	if (!list_empty(&local_napi_list))
-		io_putback_napi_list(ctx, &local_napi_list);
-#endif
 	do {
 		/* if we can't even flush overflow, don't wait for more */
 		if (!io_cqring_overflow_flush(ctx)) {
@@ -8864,8 +8630,12 @@ static int __io_sqe_files_scm(struct io_ring_ctx *ctx, int nr, int offset)
 		refcount_add(skb->truesize, &sk->sk_wmem_alloc);
 		skb_queue_head(&sk->sk_receive_queue, skb);
 
-		for (i = 0; i < nr_files; i++)
-			fput(fpl->fp[i]);
+		for (i = 0; i < nr; i++) {
+			struct file *file = io_file_from_index(ctx, i + offset);
+
+			if (file)
+				fput(file);
+		}
 	} else {
 		kfree_skb(skb);
 		free_uid(fpl->user);
@@ -9156,13 +8926,15 @@ static int io_sqe_file_register(struct io_ring_ctx *ctx, struct file *file,
 static int io_queue_rsrc_removal(struct io_rsrc_data *data, unsigned idx,
 				 struct io_rsrc_node *node, void *rsrc)
 {
+	u64 *tag_slot = io_get_tag_slot(data, idx);
 	struct io_rsrc_put *prsrc;
 
 	prsrc = kzalloc(sizeof(*prsrc), GFP_KERNEL);
 	if (!prsrc)
 		return -ENOMEM;
 
-	prsrc->tag = *io_get_tag_slot(data, idx);
+	prsrc->tag = *tag_slot;
+	*tag_slot = 0;
 	prsrc->rsrc = rsrc;
 	list_add(&prsrc->list, &node->rsrc_list);
 	return 0;
@@ -9231,7 +9003,7 @@ static int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags)
 	bool needs_lock = issue_flags & IO_URING_F_UNLOCKED;
 	struct io_fixed_file *file_slot;
 	struct file *file;
-	int ret, i;
+	int ret;
 
 	io_ring_submit_lock(ctx, needs_lock);
 	ret = -ENXIO;
@@ -9244,8 +9016,8 @@ static int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags)
 	if (ret)
 		goto out;
 
-	i = array_index_nospec(offset, ctx->nr_user_files);
-	file_slot = io_fixed_file_slot(&ctx->file_table, i);
+	offset = array_index_nospec(offset, ctx->nr_user_files);
+	file_slot = io_fixed_file_slot(&ctx->file_table, offset);
 	ret = -EBADF;
 	if (!file_slot->file_ptr)
 		goto out;
@@ -9301,8 +9073,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx,
 
 		if (file_slot->file_ptr) {
 			file = (struct file *)(file_slot->file_ptr & FFS_MASK);
-			err = io_queue_rsrc_removal(data, up->offset + done,
-						    ctx->rsrc_node, file);
+			err = io_queue_rsrc_removal(data, i, ctx->rsrc_node, file);
 			if (err)
 				break;
 			file_slot->file_ptr = 0;
@@ -9327,7 +9098,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx,
 				err = -EBADF;
 				break;
 			}
-			*io_get_tag_slot(data, up->offset + done) = tag;
+			*io_get_tag_slot(data, i) = tag;
 			io_fixed_file_set(file_slot, file);
 			err = io_sqe_file_register(ctx, file, i);
 			if (err) {
@@ -9411,7 +9182,6 @@ static __cold int io_uring_alloc_task_context(struct task_struct *task,
 	xa_init(&tctx->xa);
 	init_waitqueue_head(&tctx->wait);
 	atomic_set(&tctx->in_idle, 0);
-	atomic_set(&tctx->inflight_tracked, 0);
 	task->io_uring = tctx;
 	spin_lock_init(&tctx->task_lock);
 	INIT_WQ_LIST(&tctx->task_list);
@@ -9986,7 +9756,7 @@ static int __io_sqe_buffers_update(struct io_ring_ctx *ctx,
 
 		i = array_index_nospec(offset, ctx->nr_user_bufs);
 		if (ctx->user_bufs[i] != ctx->dummy_ubuf) {
-			err = io_queue_rsrc_removal(ctx->buf_data, offset,
+			err = io_queue_rsrc_removal(ctx->buf_data, i,
 						    ctx->rsrc_node, ctx->user_bufs[i]);
 			if (unlikely(err)) {
 				io_buffer_unmap(ctx, &imu);
@@ -10181,7 +9951,6 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx)
 	io_req_caches_free(ctx);
 	if (ctx->hash_map)
 		io_wq_put_hash(ctx->hash_map);
-	io_free_napi_list(ctx);
 	kfree(ctx->cancel_hash);
 	kfree(ctx->dummy_ubuf);
 	kfree(ctx->io_buffers);
@@ -10604,7 +10373,7 @@ static __cold void io_uring_clean_tctx(struct io_uring_task *tctx)
 static s64 tctx_inflight(struct io_uring_task *tctx, bool tracked)
 {
 	if (tracked)
-		return atomic_read(&tctx->inflight_tracked);
+		return 0;
 	return percpu_counter_sum(&tctx->inflight);
 }
 
@@ -11707,7 +11476,15 @@ static __cold int io_register_iowq_aff(struct io_ring_ctx *ctx,
 	if (len > cpumask_size())
 		len = cpumask_size();
 
-	if (copy_from_user(new_mask, arg, len)) {
+	if (in_compat_syscall()) {
+		ret = compat_get_bitmap(cpumask_bits(new_mask),
+					(const compat_ulong_t __user *)arg,
+					len * 8 /* CHAR_BIT */);
+	} else {
+		ret = copy_from_user(new_mask, arg, len);
+	}
+
+	if (ret) {
 		free_cpumask_var(new_mask);
 		return -EFAULT;
 	}