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
  ...

Author: torvalds

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);

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;
 }

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;

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;

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;
 };
 
 /*

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;
 	}

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;
 

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)