Merge tag 'for-6.5/io_uring-2023-06-23' of git://git.kernel.dk/linux

Pull io_uring updates from Jens Axboe:
 "Nothing major in this release, just a bunch of cleanups and some
  optimizations around networking mostly.

   - clean up file request flags handling (Christoph)

   - clean up request freeing and CQ locking (Pavel)

   - support for using pre-registering the io_uring fd at setup time
     (Josh)

   - Add support for user allocated ring memory, rather than having the
     kernel allocate it. Mostly for packing rings into a huge page (me)

   - avoid an unnecessary double retry on receive (me)

   - maintain ordering for task_work, which also improves performance
     (me)

   - misc cleanups/fixes (Pavel, me)"

* tag 'for-6.5/io_uring-2023-06-23' of git://git.kernel.dk/linux: (39 commits)
  io_uring: merge conditional unlock flush helpers
  io_uring: make io_cq_unlock_post static
  io_uring: inline __io_cq_unlock
  io_uring: fix acquire/release annotations
  io_uring: kill io_cq_unlock()
  io_uring: remove IOU_F_TWQ_FORCE_NORMAL
  io_uring: don't batch task put on reqs free
  io_uring: move io_clean_op()
  io_uring: inline io_dismantle_req()
  io_uring: remove io_free_req_tw
  io_uring: open code io_put_req_find_next
  io_uring: add helpers to decode the fixed file file_ptr
  io_uring: use io_file_from_index in io_msg_grab_file
  io_uring: use io_file_from_index in __io_sync_cancel
  io_uring: return REQ_F_ flags from io_file_get_flags
  io_uring: remove io_req_ffs_set
  io_uring: remove a confusing comment above io_file_get_flags
  io_uring: remove the mode variable in io_file_get_flags
  io_uring: remove __io_file_supports_nowait
  io_uring: wait interruptibly for request completions on exit
  ...

21 files changed, 416 insertions, 334 deletions

diff --git a/block/fops.c b/block/fops.c
index 18dedb730493..4faeada05b23 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -481,7 +481,7 @@ static int blkdev_open(struct inode *inode, struct file *filp)
 	 * during an unstable branch.
 	 */
 	filp->f_flags |= O_LARGEFILE;
-	filp->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC;
+	filp->f_mode |= FMODE_BUF_RASYNC;
 
 	if (filp->f_flags & O_NDELAY)
 		filp->f_mode |= FMODE_NDELAY;
@@ -494,6 +494,9 @@ static int blkdev_open(struct inode *inode, struct file *filp)
 	if (IS_ERR(bdev))
 		return PTR_ERR(bdev);
 
+	if (bdev_nowait(bdev))
+		filp->f_mode |= FMODE_NOWAIT;
+
 	filp->private_data = bdev;
 	filp->f_mapping = bdev->bd_inode->i_mapping;
 	filp->f_wb_err = filemap_sample_wb_err(filp->f_mapping);
diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index f15e7330b75a..b97744e05551 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -521,7 +521,7 @@ static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req,
 	if (cookie != NULL && blk_rq_is_poll(req))
 		nvme_uring_task_cb(ioucmd, IO_URING_F_UNLOCKED);
 	else
-		io_uring_cmd_complete_in_task(ioucmd, nvme_uring_task_cb);
+		io_uring_cmd_do_in_task_lazy(ioucmd, nvme_uring_task_cb);
 
 	return RQ_END_IO_FREE;
 }
@@ -543,7 +543,7 @@ static enum rq_end_io_ret nvme_uring_cmd_end_io_meta(struct request *req,
 	if (cookie != NULL && blk_rq_is_poll(req))
 		nvme_uring_task_meta_cb(ioucmd, IO_URING_F_UNLOCKED);
 	else
-		io_uring_cmd_complete_in_task(ioucmd, nvme_uring_task_meta_cb);
+		io_uring_cmd_do_in_task_lazy(ioucmd, nvme_uring_task_meta_cb);
 
 	return RQ_END_IO_NONE;
 }
diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index 7fe31b2cd02f..bb9c666bd584 100644
--- a/include/linux/io_uring.h
+++ b/include/linux/io_uring.h
@@ -46,13 +46,23 @@ int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
 			      struct iov_iter *iter, void *ioucmd);
 void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, ssize_t res2,
 			unsigned issue_flags);
-void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd,
-			void (*task_work_cb)(struct io_uring_cmd *, unsigned));
 struct sock *io_uring_get_socket(struct file *file);
 void __io_uring_cancel(bool cancel_all);
 void __io_uring_free(struct task_struct *tsk);
 void io_uring_unreg_ringfd(void);
 const char *io_uring_get_opcode(u8 opcode);
+void __io_uring_cmd_do_in_task(struct io_uring_cmd *ioucmd,
+			    void (*task_work_cb)(struct io_uring_cmd *, unsigned),
+			    unsigned flags);
+/* users should follow semantics of IOU_F_TWQ_LAZY_WAKE */
+void io_uring_cmd_do_in_task_lazy(struct io_uring_cmd *ioucmd,
+			void (*task_work_cb)(struct io_uring_cmd *, unsigned));
+
+static inline void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd,
+			void (*task_work_cb)(struct io_uring_cmd *, unsigned))
+{
+	__io_uring_cmd_do_in_task(ioucmd, task_work_cb, 0);
+}
 
 static inline void io_uring_files_cancel(void)
 {
@@ -85,6 +95,10 @@ static inline void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd,
 			void (*task_work_cb)(struct io_uring_cmd *, unsigned))
 {
 }
+static inline void io_uring_cmd_do_in_task_lazy(struct io_uring_cmd *ioucmd,
+			void (*task_work_cb)(struct io_uring_cmd *, unsigned))
+{
+}
 static inline struct sock *io_uring_get_socket(struct file *file)
 {
 	return NULL;
diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index 1b2a20a42413..f04ce513fadb 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -211,6 +211,16 @@ struct io_ring_ctx {
 		unsigned int		compat: 1;
 
 		enum task_work_notify_mode	notify_method;
+
+		/*
+		 * If IORING_SETUP_NO_MMAP is used, then the below holds
+		 * the gup'ed pages for the two rings, and the sqes.
+		 */
+		unsigned short		n_ring_pages;
+		unsigned short		n_sqe_pages;
+		struct page		**ring_pages;
+		struct page		**sqe_pages;
+
 		struct io_rings			*rings;
 		struct task_struct		*submitter_task;
 		struct percpu_ref		refs;
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 0716cb17e436..f222d263bc55 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -173,6 +173,18 @@ enum {
  */
 #define IORING_SETUP_DEFER_TASKRUN	(1U << 13)
 
+/*
+ * Application provides the memory for the rings
+ */
+#define IORING_SETUP_NO_MMAP		(1U << 14)
+
+/*
+ * Register the ring fd in itself for use with
+ * IORING_REGISTER_USE_REGISTERED_RING; return a registered fd index rather
+ * than an fd.
+ */
+#define IORING_SETUP_REGISTERED_FD_ONLY	(1U << 15)
+
 enum io_uring_op {
 	IORING_OP_NOP,
 	IORING_OP_READV,
@@ -406,7 +418,7 @@ struct io_sqring_offsets {
 	__u32 dropped;
 	__u32 array;
 	__u32 resv1;
-	__u64 resv2;
+	__u64 user_addr;
 };
 
 /*
@@ -425,7 +437,7 @@ struct io_cqring_offsets {
 	__u32 cqes;
 	__u32 flags;
 	__u32 resv1;
-	__u64 resv2;
+	__u64 user_addr;
 };
 
 /*
diff --git a/io_uring/cancel.c b/io_uring/cancel.c
index b4f5dfacc0c3..58c46c852bdd 100644
--- a/io_uring/cancel.c
+++ b/io_uring/cancel.c
@@ -216,13 +216,10 @@ static int __io_sync_cancel(struct io_uring_task *tctx,
 	/* fixed must be grabbed every time since we drop the uring_lock */
 	if ((cd->flags & IORING_ASYNC_CANCEL_FD) &&
 	    (cd->flags & IORING_ASYNC_CANCEL_FD_FIXED)) {
-		unsigned long file_ptr;
-
 		if (unlikely(fd >= ctx->nr_user_files))
 			return -EBADF;
 		fd = array_index_nospec(fd, ctx->nr_user_files);
-		file_ptr = io_fixed_file_slot(&ctx->file_table, fd)->file_ptr;
-		cd->file = (struct file *) (file_ptr & FFS_MASK);
+		cd->file = io_file_from_index(&ctx->file_table, fd);
 		if (!cd->file)
 			return -EBADF;
 	}
diff --git a/io_uring/filetable.c b/io_uring/filetable.c
index 0f6fa791a47d..e7d749991de4 100644
--- a/io_uring/filetable.c
+++ b/io_uring/filetable.c
@@ -78,10 +78,8 @@ static int io_install_fixed_file(struct io_ring_ctx *ctx, struct file *file,
 	file_slot = io_fixed_file_slot(&ctx->file_table, slot_index);
 
 	if (file_slot->file_ptr) {
-		struct file *old_file;
-
-		old_file = (struct file *)(file_slot->file_ptr & FFS_MASK);
-		ret = io_queue_rsrc_removal(ctx->file_data, slot_index, old_file);
+		ret = io_queue_rsrc_removal(ctx->file_data, slot_index,
+					    io_slot_file(file_slot));
 		if (ret)
 			return ret;
 
@@ -140,7 +138,6 @@ int io_fixed_fd_install(struct io_kiocb *req, unsigned int issue_flags,
 int io_fixed_fd_remove(struct io_ring_ctx *ctx, unsigned int offset)
 {
 	struct io_fixed_file *file_slot;
-	struct file *file;
 	int ret;
 
 	if (unlikely(!ctx->file_data))
@@ -153,8 +150,8 @@ int io_fixed_fd_remove(struct io_ring_ctx *ctx, unsigned int offset)
 	if (!file_slot->file_ptr)
 		return -EBADF;
 
-	file = (struct file *)(file_slot->file_ptr & FFS_MASK);
-	ret = io_queue_rsrc_removal(ctx->file_data, offset, file);
+	ret = io_queue_rsrc_removal(ctx->file_data, offset,
+				    io_slot_file(file_slot));
 	if (ret)
 		return ret;
 
diff --git a/io_uring/filetable.h b/io_uring/filetable.h
index 351111ff8882..b47adf170c31 100644
--- a/io_uring/filetable.h
+++ b/io_uring/filetable.h
@@ -5,10 +5,6 @@
 #include <linux/file.h>
 #include <linux/io_uring_types.h>
 
-#define FFS_NOWAIT		0x1UL
-#define FFS_ISREG		0x2UL
-#define FFS_MASK		~(FFS_NOWAIT|FFS_ISREG)
-
 bool io_alloc_file_tables(struct io_file_table *table, unsigned nr_files);
 void io_free_file_tables(struct io_file_table *table);
 
@@ -43,21 +39,31 @@ io_fixed_file_slot(struct io_file_table *table, unsigned i)
 	return &table->files[i];
 }
 
+#define FFS_NOWAIT		0x1UL
+#define FFS_ISREG		0x2UL
+#define FFS_MASK		~(FFS_NOWAIT|FFS_ISREG)
+
+static inline unsigned int io_slot_flags(struct io_fixed_file *slot)
+{
+	return (slot->file_ptr & ~FFS_MASK) << REQ_F_SUPPORT_NOWAIT_BIT;
+}
+
+static inline struct file *io_slot_file(struct io_fixed_file *slot)
+{
+	return (struct file *)(slot->file_ptr & FFS_MASK);
+}
+
 static inline struct file *io_file_from_index(struct io_file_table *table,
 					      int index)
 {
-	struct io_fixed_file *slot = io_fixed_file_slot(table, index);
-
-	return (struct file *) (slot->file_ptr & FFS_MASK);
+	return io_slot_file(io_fixed_file_slot(table, index));
 }
 
 static inline void io_fixed_file_set(struct io_fixed_file *file_slot,
 				     struct file *file)
 {
-	unsigned long file_ptr = (unsigned long) file;
-
-	file_ptr |= io_file_get_flags(file);
-	file_slot->file_ptr = file_ptr;
+	file_slot->file_ptr = (unsigned long)file |
+		(io_file_get_flags(file) >> REQ_F_SUPPORT_NOWAIT_BIT);
 }
 
 static inline void io_reset_alloc_hint(struct io_ring_ctx *ctx)
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 3bca7a79efda..1b53a2ab0a27 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -95,6 +95,7 @@
 
 #include "timeout.h"
 #include "poll.h"
+#include "rw.h"
 #include "alloc_cache.h"
 
 #define IORING_MAX_ENTRIES	32768
@@ -145,8 +146,6 @@ static bool io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
 					 struct task_struct *task,
 					 bool cancel_all);
 
-static void io_dismantle_req(struct io_kiocb *req);
-static void io_clean_op(struct io_kiocb *req);
 static void io_queue_sqe(struct io_kiocb *req);
 static void io_move_task_work_from_local(struct io_ring_ctx *ctx);
 static void __io_submit_flush_completions(struct io_ring_ctx *ctx);
@@ -367,6 +366,39 @@ static bool req_need_defer(struct io_kiocb *req, u32 seq)
 	return false;
 }
 
+static void io_clean_op(struct io_kiocb *req)
+{
+	if (req->flags & REQ_F_BUFFER_SELECTED) {
+		spin_lock(&req->ctx->completion_lock);
+		io_put_kbuf_comp(req);
+		spin_unlock(&req->ctx->completion_lock);
+	}
+
+	if (req->flags & REQ_F_NEED_CLEANUP) {
+		const struct io_cold_def *def = &io_cold_defs[req->opcode];
+
+		if (def->cleanup)
+			def->cleanup(req);
+	}
+	if ((req->flags & REQ_F_POLLED) && req->apoll) {
+		kfree(req->apoll->double_poll);
+		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) {
+		kfree(req->async_data);
+		req->async_data = NULL;
+	}
+	req->flags &= ~IO_REQ_CLEAN_FLAGS;
+}
+
 static inline void io_req_track_inflight(struct io_kiocb *req)
 {
 	if (!(req->flags & REQ_F_INFLIGHT)) {
@@ -423,8 +455,8 @@ static void io_prep_async_work(struct io_kiocb *req)
 	if (req->flags & REQ_F_FORCE_ASYNC)
 		req->work.flags |= IO_WQ_WORK_CONCURRENT;
 
-	if (req->file && !io_req_ffs_set(req))
-		req->flags |= io_file_get_flags(req->file) << REQ_F_SUPPORT_NOWAIT_BIT;
+	if (req->file && !(req->flags & REQ_F_FIXED_FILE))
+		req->flags |= io_file_get_flags(req->file);
 
 	if (req->file && (req->flags & REQ_F_ISREG)) {
 		bool should_hash = def->hash_reg_file;
@@ -594,42 +626,18 @@ void __io_commit_cqring_flush(struct io_ring_ctx *ctx)
 }
 
 static inline void __io_cq_lock(struct io_ring_ctx *ctx)
-	__acquires(ctx->completion_lock)
 {
 	if (!ctx->task_complete)
 		spin_lock(&ctx->completion_lock);
 }
 
-static inline void __io_cq_unlock(struct io_ring_ctx *ctx)
-{
-	if (!ctx->task_complete)
-		spin_unlock(&ctx->completion_lock);
-}
-
 static inline void io_cq_lock(struct io_ring_ctx *ctx)
 	__acquires(ctx->completion_lock)
 {
 	spin_lock(&ctx->completion_lock);
 }
 
-static inline void io_cq_unlock(struct io_ring_ctx *ctx)
-	__releases(ctx->completion_lock)
-{
-	spin_unlock(&ctx->completion_lock);
-}
-
-/* keep it inlined for io_submit_flush_completions() */
 static inline void __io_cq_unlock_post(struct io_ring_ctx *ctx)
-	__releases(ctx->completion_lock)
-{
-	io_commit_cqring(ctx);
-	__io_cq_unlock(ctx);
-	io_commit_cqring_flush(ctx);
-	io_cqring_wake(ctx);
-}
-
-static void __io_cq_unlock_post_flush(struct io_ring_ctx *ctx)
-	__releases(ctx->completion_lock)
 {
 	io_commit_cqring(ctx);
 
@@ -641,13 +649,13 @@ static void __io_cq_unlock_post_flush(struct io_ring_ctx *ctx)
 		 */
 		io_commit_cqring_flush(ctx);
 	} else {
-		__io_cq_unlock(ctx);
+		spin_unlock(&ctx->completion_lock);
 		io_commit_cqring_flush(ctx);
 		io_cqring_wake(ctx);
 	}
 }
 
-void io_cq_unlock_post(struct io_ring_ctx *ctx)
+static void io_cq_unlock_post(struct io_ring_ctx *ctx)
 	__releases(ctx->completion_lock)
 {
 	io_commit_cqring(ctx);
@@ -662,10 +670,10 @@ static void io_cqring_overflow_kill(struct io_ring_ctx *ctx)
 	struct io_overflow_cqe *ocqe;
 	LIST_HEAD(list);
 
-	io_cq_lock(ctx);
+	spin_lock(&ctx->completion_lock);
 	list_splice_init(&ctx->cq_overflow_list, &list);
 	clear_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq);
-	io_cq_unlock(ctx);
+	spin_unlock(&ctx->completion_lock);
 
 	while (!list_empty(&list)) {
 		ocqe = list_first_entry(&list, struct io_overflow_cqe, list);
@@ -722,29 +730,29 @@ static void io_cqring_overflow_flush(struct io_ring_ctx *ctx)
 }
 
 /* can be called by any task */
-static void io_put_task_remote(struct task_struct *task, int nr)
+static void io_put_task_remote(struct task_struct *task)
 {
 	struct io_uring_task *tctx = task->io_uring;
 
-	percpu_counter_sub(&tctx->inflight, nr);
+	percpu_counter_sub(&tctx->inflight, 1);
 	if (unlikely(atomic_read(&tctx->in_cancel)))
 		wake_up(&tctx->wait);
-	put_task_struct_many(task, nr);
+	put_task_struct(task);
 }
 
 /* used by a task to put its own references */
-static void io_put_task_local(struct task_struct *task, int nr)
+static void io_put_task_local(struct task_struct *task)
 {
-	task->io_uring->cached_refs += nr;
+	task->io_uring->cached_refs++;
 }
 
 /* must to be called somewhat shortly after putting a request */
-static inline void io_put_task(struct task_struct *task, int nr)
+static inline void io_put_task(struct task_struct *task)
 {
 	if (likely(task == current))
-		io_put_task_local(task, nr);
+		io_put_task_local(task);
 	else
-		io_put_task_remote(task, nr);
+		io_put_task_remote(task);
 }
 
 void io_task_refs_refill(struct io_uring_task *tctx)
@@ -934,20 +942,19 @@ bool io_post_aux_cqe(struct io_ring_ctx *ctx, u64 user_data, s32 res, u32 cflags
 	return __io_post_aux_cqe(ctx, user_data, res, cflags, true);
 }
 
-bool io_aux_cqe(struct io_ring_ctx *ctx, bool defer, u64 user_data, s32 res, u32 cflags,
+bool io_aux_cqe(const struct io_kiocb *req, bool defer, s32 res, u32 cflags,
 		bool allow_overflow)
 {
+	struct io_ring_ctx *ctx = req->ctx;
+	u64 user_data = req->cqe.user_data;
 	struct io_uring_cqe *cqe;
-	unsigned int length;
 
 	if (!defer)
 		return __io_post_aux_cqe(ctx, user_data, res, cflags, allow_overflow);
 
-	length = ARRAY_SIZE(ctx->submit_state.cqes);
-
 	lockdep_assert_held(&ctx->uring_lock);
 
-	if (ctx->submit_state.cqes_count == length) {
+	if (ctx->submit_state.cqes_count == ARRAY_SIZE(ctx->submit_state.cqes)) {
 		__io_cq_lock(ctx);
 		__io_flush_post_cqes(ctx);
 		/* no need to flush - flush is deferred */
@@ -991,14 +998,18 @@ static void __io_req_complete_post(struct io_kiocb *req, unsigned issue_flags)
 			}
 		}
 		io_put_kbuf_comp(req);
-		io_dismantle_req(req);
+		if (unlikely(req->flags & IO_REQ_CLEAN_FLAGS))
+			io_clean_op(req);
+		if (!(req->flags & REQ_F_FIXED_FILE))
+			io_put_file(req->file);
+
 		rsrc_node = req->rsrc_node;
 		/*
 		 * Selected buffer deallocation in io_clean_op() assumes that
 		 * we don't hold ->completion_lock. Clean them here to avoid
 		 * deadlocks.
 		 */
-		io_put_task_remote(req->task, 1);
+		io_put_task_remote(req->task);
 		wq_list_add_head(&req->comp_list, &ctx->locked_free_list);
 		ctx->locked_free_nr++;
 	}
@@ -1111,36 +1122,13 @@ __cold bool __io_alloc_req_refill(struct io_ring_ctx *ctx)
 	return true;
 }
 
-static inline void io_dismantle_req(struct io_kiocb *req)
-{
-	unsigned int flags = req->flags;
-
-	if (unlikely(flags & IO_REQ_CLEAN_FLAGS))
-		io_clean_op(req);
-	if (!(flags & REQ_F_FIXED_FILE))
-		io_put_file(req->file);
-}
-
-static __cold void io_free_req_tw(struct io_kiocb *req, struct io_tw_state *ts)
-{
-	struct io_ring_ctx *ctx = req->ctx;
-
-	if (req->rsrc_node) {
-		io_tw_lock(ctx, ts);
-		io_put_rsrc_node(ctx, req->rsrc_node);
-	}
-	io_dismantle_req(req);
-	io_put_task_remote(req->task, 1);
-
-	spin_lock(&ctx->completion_lock);
-	wq_list_add_head(&req->comp_list, &ctx->locked_free_list);
-	ctx->locked_free_nr++;
-	spin_unlock(&ctx->completion_lock);
-}
-
 __cold void io_free_req(struct io_kiocb *req)
 {
-	req->io_task_work.func = io_free_req_tw;
+	/* refs were already put, restore them for io_req_task_complete() */
+	req->flags &= ~REQ_F_REFCOUNT;
+	/* we only want to free it, don't post CQEs */
+	req->flags |= REQ_F_CQE_SKIP;
+	req->io_task_work.func = io_req_task_complete;
 	io_req_task_work_add(req);
 }
 
@@ -1205,7 +1193,9 @@ static unsigned int handle_tw_list(struct llist_node *node,
 			ts->locked = mutex_trylock(&(*ctx)->uring_lock);
 			percpu_ref_get(&(*ctx)->refs);
 		}
-		req->io_task_work.func(req, ts);
+		INDIRECT_CALL_2(req->io_task_work.func,
+				io_poll_task_func, io_req_rw_complete,
+				req, ts);
 		node = next;
 		count++;
 		if (unlikely(need_resched())) {
@@ -1303,7 +1293,7 @@ static __cold void io_fallback_tw(struct io_uring_task *tctx)
 	}
 }
 
-static void io_req_local_work_add(struct io_kiocb *req, unsigned flags)
+static inline void io_req_local_work_add(struct io_kiocb *req, unsigned flags)
 {
 	struct io_ring_ctx *ctx = req->ctx;
 	unsigned nr_wait, nr_tw, nr_tw_prev;
@@ -1354,19 +1344,11 @@ static void io_req_local_work_add(struct io_kiocb *req, unsigned flags)
 	wake_up_state(ctx->submitter_task, TASK_INTERRUPTIBLE);
 }
 
-void __io_req_task_work_add(struct io_kiocb *req, unsigned flags)
+static void io_req_normal_work_add(struct io_kiocb *req)
 {
 	struct io_uring_task *tctx = req->task->io_uring;
 	struct io_ring_ctx *ctx = req->ctx;
 
-	if (!(flags & IOU_F_TWQ_FORCE_NORMAL) &&
-	    (ctx->flags & IORING_SETUP_DEFER_TASKRUN)) {
-		rcu_read_lock();
-		io_req_local_work_add(req, flags);
-		rcu_read_unlock();
-		return;
-	}
-
 	/* task_work already pending, we're done */
 	if (!llist_add(&req->io_task_work.node, &tctx->task_list))
 		return;
@@ -1380,6 +1362,17 @@ void __io_req_task_work_add(struct io_kiocb *req, unsigned flags)
 	io_fallback_tw(tctx);
 }
 
+void __io_req_task_work_add(struct io_kiocb *req, unsigned flags)
+{
+	if (req->ctx->flags & IORING_SETUP_DEFER_TASKRUN) {
+		rcu_read_lock();
+		io_req_local_work_add(req, flags);
+		rcu_read_unlock();
+	} else {
+		io_req_normal_work_add(req);
+	}
+}
+
 static void __cold io_move_task_work_from_local(struct io_ring_ctx *ctx)
 {
 	struct llist_node *node;
@@ -1390,7 +1383,7 @@ static void __cold io_move_task_work_from_local(struct io_ring_ctx *ctx)
 						    io_task_work.node);
 
 		node = node->next;
-		__io_req_task_work_add(req, IOU_F_TWQ_FORCE_NORMAL);
+		io_req_normal_work_add(req);
 	}
 }
 
@@ -1405,13 +1398,19 @@ static int __io_run_local_work(struct io_ring_ctx *ctx, struct io_tw_state *ts)
 	if (ctx->flags & IORING_SETUP_TASKRUN_FLAG)
 		atomic_andnot(IORING_SQ_TASKRUN, &ctx->rings->sq_flags);
 again:
-	node = io_llist_xchg(&ctx->work_llist, NULL);
+	/*
+	 * llists are in reverse order, flip it back the right way before
+	 * running the pending items.
+	 */
+	node = llist_reverse_order(io_llist_xchg(&ctx->work_llist, NULL));
 	while (node) {
 		struct llist_node *next = node->next;
 		struct io_kiocb *req = container_of(node, struct io_kiocb,
 						    io_task_work.node);
 		prefetch(container_of(next, struct io_kiocb, io_task_work.node));
-		req->io_task_work.func(req, ts);
+		INDIRECT_CALL_2(req->io_task_work.func,
+				io_poll_task_func, io_req_rw_complete,
+				req, ts);
 		ret++;
 		node = next;
 	}
@@ -1498,9 +1497,6 @@ void io_queue_next(struct io_kiocb *req)
 void io_free_batch_list(struct io_ring_ctx *ctx, struct io_wq_work_node *node)
 	__must_hold(&ctx->uring_lock)
 {
-	struct task_struct *task = NULL;
-	int task_refs = 0;
-
 	do {
 		struct io_kiocb *req = container_of(node, struct io_kiocb,
 						    comp_list);
@@ -1530,19 +1526,10 @@ void io_free_batch_list(struct io_ring_ctx *ctx, struct io_wq_work_node *node)
 
 		io_req_put_rsrc_locked(req, ctx);
 
-		if (req->task != task) {
-			if (task)
-				io_put_task(task, task_refs);
-			task = req->task;
-			task_refs = 0;
-		}
-		task_refs++;
+		io_put_task(req->task);
 		node = req->comp_list.next;
 		io_req_add_to_cache(req, ctx);
 	} while (node);
-
-	if (task)
-		io_put_task(task, task_refs);
 }
 
 static void __io_submit_flush_completions(struct io_ring_ctx *ctx)
@@ -1570,7 +1557,7 @@ static void __io_submit_flush_completions(struct io_ring_ctx *ctx)
 			}
 		}
 	}
-	__io_cq_unlock_post_flush(ctx);
+	__io_cq_unlock_post(ctx);
 
 	if (!wq_list_empty(&ctx->submit_state.compl_reqs)) {
 		io_free_batch_list(ctx, state->compl_reqs.first);
@@ -1578,22 +1565,6 @@ static void __io_submit_flush_completions(struct io_ring_ctx *ctx)
 	}
 }
 
-/*
- * Drop reference to request, return next in chain (if there is one) if this
- * was the last reference to this request.
- */
-static inline struct io_kiocb *io_put_req_find_next(struct io_kiocb *req)
-{
-	struct io_kiocb *nxt = NULL;
-
-	if (req_ref_put_and_test(req)) {
-		if (unlikely(req->flags & IO_REQ_LINK_FLAGS))
-			nxt = io_req_find_next(req);
-		io_free_req(req);
-	}
-	return nxt;
-}
-
 static unsigned io_cqring_events(struct io_ring_ctx *ctx)
 {
 	/* See comment at the top of this file */
@@ -1758,54 +1729,14 @@ static void io_iopoll_req_issued(struct io_kiocb *req, unsigned int issue_flags)
 	}
 }
 
-static bool io_bdev_nowait(struct block_device *bdev)
-{
-	return !bdev || bdev_nowait(bdev);
-}
-
-/*
- * If we tracked the file through the SCM inflight mechanism, we could support
- * any file. For now, just ensure that anything potentially problematic is done
- * inline.
- */
-static bool __io_file_supports_nowait(struct file *file, umode_t mode)
-{
-	if (S_ISBLK(mode)) {
-		if (IS_ENABLED(CONFIG_BLOCK) &&
-		    io_bdev_nowait(I_BDEV(file->f_mapping->host)))
-			return true;
-		return false;
-	}
-	if (S_ISSOCK(mode))
-		return true;
-	if (S_ISREG(mode)) {
-		if (IS_ENABLED(CONFIG_BLOCK) &&
-		    io_bdev_nowait(file->f_inode->i_sb->s_bdev) &&
-		    !io_is_uring_fops(file))
-			return true;
-		return false;
-	}
-
-	/* any ->read/write should understand O_NONBLOCK */
-	if (file->f_flags & O_NONBLOCK)
-		return true;
-	return file->f_mode & FMODE_NOWAIT;
-}
-
-/*
- * If we tracked the file through the SCM inflight mechanism, we could support
- * any file. For now, just ensure that anything potentially problematic is done
- * inline.
- */
 unsigned int io_file_get_flags(struct file *file)
 {
-	umode_t mode = file_inode(file)->i_mode;
 	unsigned int res = 0;
 
-	if (S_ISREG(mode))
-		res |= FFS_ISREG;
-	if (__io_file_supports_nowait(file, mode))
-		res |= FFS_NOWAIT;
+	if (S_ISREG(file_inode(file)->i_mode))
+		res |= REQ_F_ISREG;
+	if ((file->f_flags & O_NONBLOCK) || (file->f_mode & FMODE_NOWAIT))
+		res |= REQ_F_SUPPORT_NOWAIT;
 	return res;
 }
 
@@ -1891,39 +1822,6 @@ queue:
 	spin_unlock(&ctx->completion_lock);
 }
 
-static void io_clean_op(struct io_kiocb *req)
-{
-	if (req->flags & REQ_F_BUFFER_SELECTED) {
-		spin_lock(&req->ctx->completion_lock);
-		io_put_kbuf_comp(req);
-		spin_unlock(&req->ctx->completion_lock);
-	}
-
-	if (req->flags & REQ_F_NEED_CLEANUP) {
-		const struct io_cold_def *def = &io_cold_defs[req->opcode];
-
-		if (def->cleanup)
-			def->cleanup(req);
-	}
-	if ((req->flags & REQ_F_POLLED) && req->apoll) {
-		kfree(req->apoll->double_poll);
-		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) {
-		kfree(req->async_data);
-		req->async_data = NULL;
-	}
-	req->flags &= ~IO_REQ_CLEAN_FLAGS;
-}
-
 static bool io_assign_file(struct io_kiocb *req, const struct io_issue_def *def,
 			   unsigned int issue_flags)
 {
@@ -1986,9 +1884,14 @@ int io_poll_issue(struct io_kiocb *req, struct io_tw_state *ts)
 struct io_wq_work *io_wq_free_work(struct io_wq_work *work)
 {
 	struct io_kiocb *req = container_of(work, struct io_kiocb, work);
+	struct io_kiocb *nxt = NULL;
 
-	req = io_put_req_find_next(req);
-	return req ? &req->work : NULL;
+	if (req_ref_put_and_test(req)) {
+		if (req->flags & IO_REQ_LINK_FLAGS)
+			nxt = io_req_find_next(req);
+		io_free_req(req);
+	}
+	return nxt ? &nxt->work : NULL;
 }
 
 void io_wq_submit_work(struct io_wq_work *work)
@@ -2060,19 +1963,17 @@ inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd,
 				      unsigned int issue_flags)
 {
 	struct io_ring_ctx *ctx = req->ctx;
+	struct io_fixed_file *slot;
 	struct file *file = NULL;
-	unsigned long file_ptr;
 
 	io_ring_submit_lock(ctx, issue_flags);
 
 	if (unlikely((unsigned int)fd >= ctx->nr_user_files))
 		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);
+	slot = io_fixed_file_slot(&ctx->file_table, fd);
+	file = io_slot_file(slot);
+	req->flags |= io_slot_flags(slot);
 	io_req_set_rsrc_node(req, ctx, 0);
 out:
 	io_ring_submit_unlock(ctx, issue_flags);
@@ -2709,11 +2610,96 @@ static void io_mem_free(void *ptr)
 		free_compound_page(page);
 }
 
+static void io_pages_free(struct page ***pages, int npages)
+{
+	struct page **page_array;
+	int i;
+
+	if (!pages)
+		return;
+	page_array = *pages;
+	for (i = 0; i < npages; i++)
+		unpin_user_page(page_array[i]);
+	kvfree(page_array);
+	*pages = NULL;
+}
+
+static void *__io_uaddr_map(struct page ***pages, unsigned short *npages,
+			    unsigned long uaddr, size_t size)
+{
+	struct page **page_array;
+	unsigned int nr_pages;
+	int ret;
+
+	*npages = 0;
+
+	if (uaddr & (PAGE_SIZE - 1) || !size)
+		return ERR_PTR(-EINVAL);
+
+	nr_pages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	if (nr_pages > USHRT_MAX)
+		return ERR_PTR(-EINVAL);
+	page_array = kvmalloc_array(nr_pages, sizeof(struct page *), GFP_KERNEL);
+	if (!page_array)
+		return ERR_PTR(-ENOMEM);
+
+	ret = pin_user_pages_fast(uaddr, nr_pages, FOLL_WRITE | FOLL_LONGTERM,
+					page_array);
+	if (ret != nr_pages) {
+err:
+		io_pages_free(&page_array, ret > 0 ? ret : 0);
+		return ret < 0 ? ERR_PTR(ret) : ERR_PTR(-EFAULT);
+	}
+	/*
+	 * Should be a single page. If the ring is small enough that we can
+	 * use a normal page, that is fine. If we need multiple pages, then
+	 * userspace should use a huge page. That's the only way to guarantee
+	 * that we get contigious memory, outside o