Merge tag 'io_uring-5.7-2020-05-08' of git://git.kernel.dk/linux-block

Pull io_uring fixes from Jens Axboe:

 - Fix finish_wait() balancing in file cancelation (Xiaoguang)

 - Ensure early cleanup of resources in ring map failure (Xiaoguang)

 - Ensure IORING_OP_SLICE does the right file mode checks (Pavel)

 - Remove file opening from openat/openat2/statx, it's not needed and
   messes with O_PATH

* tag 'io_uring-5.7-2020-05-08' of git://git.kernel.dk/linux-block:
  io_uring: don't use 'fd' for openat/openat2/statx
  splice: move f_mode checks to do_{splice,tee}()
  io_uring: handle -EFAULT properly in io_uring_setup()
  io_uring: fix mismatched finish_wait() calls in io_uring_cancel_files()

fs/io_uring.c

@@ -680,8 +680,6 @@ struct io_op_def {
 	unsigned		needs_mm : 1;
 	/* needs req->file assigned */
 	unsigned		needs_file : 1;
-	/* needs req->file assigned IFF fd is >= 0 */
-	unsigned		fd_non_neg : 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 */
@@ -784,8 +782,6 @@ static const struct io_op_def io_op_defs[] = {
 		.needs_file		= 1,
 	},
 	[IORING_OP_OPENAT] = {
-		.needs_file		= 1,
-		.fd_non_neg		= 1,
 		.file_table		= 1,
 		.needs_fs		= 1,
 	},
@@ -799,8 +795,6 @@ static const struct io_op_def io_op_defs[] = {
 	},
 	[IORING_OP_STATX] = {
 		.needs_mm		= 1,
-		.needs_file		= 1,
-		.fd_non_neg		= 1,
 		.needs_fs		= 1,
 		.file_table		= 1,
 	},
@@ -837,8 +831,6 @@ static const struct io_op_def io_op_defs[] = {
 		.buffer_select		= 1,
 	},
 	[IORING_OP_OPENAT2] = {
-		.needs_file		= 1,
-		.fd_non_neg		= 1,
 		.file_table		= 1,
 		.needs_fs		= 1,
 	},
@@ -5368,15 +5360,6 @@ static void io_wq_submit_work(struct io_wq_work **workptr)
 	io_steal_work(req, workptr);
 }
 
-static int io_req_needs_file(struct io_kiocb *req, int fd)
-{
-	if (!io_op_defs[req->opcode].needs_file)
-		return 0;
-	if ((fd == -1 || fd == AT_FDCWD) && io_op_defs[req->opcode].fd_non_neg)
-		return 0;
-	return 1;
-}
-
 static inline struct file *io_file_from_index(struct io_ring_ctx *ctx,
 					      int index)
 {
@@ -5414,14 +5397,11 @@ static int io_file_get(struct io_submit_state *state, struct io_kiocb *req,
 }
 
 static int io_req_set_file(struct io_submit_state *state, struct io_kiocb *req,
-			   int fd, unsigned int flags)
+			   int fd)
 {
 	bool fixed;
 
-	if (!io_req_needs_file(req, fd))
-		return 0;
-
-	fixed = (flags & IOSQE_FIXED_FILE);
+	fixed = (req->flags & REQ_F_FIXED_FILE) != 0;
 	if (unlikely(!fixed && req->needs_fixed_file))
 		return -EBADF;
 
@@ -5798,7 +5778,7 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
 		       struct io_submit_state *state, bool async)
 {
 	unsigned int sqe_flags;
-	int id, fd;
+	int id;
 
 	/*
 	 * All io need record the previous position, if LINK vs DARIN,
@@ -5850,8 +5830,10 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
 					IOSQE_ASYNC | IOSQE_FIXED_FILE |
 					IOSQE_BUFFER_SELECT | IOSQE_IO_LINK);
 
-	fd = READ_ONCE(sqe->fd);
-	return io_req_set_file(state, req, fd, sqe_flags);
+	if (!io_op_defs[req->opcode].needs_file)
+		return 0;
+
+	return io_req_set_file(state, req, READ_ONCE(sqe->fd));
 }
 
 static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr,
@@ -7360,11 +7342,9 @@ static int io_uring_release(struct inode *inode, struct file *file)
 static void io_uring_cancel_files(struct io_ring_ctx *ctx,
 				  struct files_struct *files)
 {
-	struct io_kiocb *req;
-	DEFINE_WAIT(wait);
-
 	while (!list_empty_careful(&ctx->inflight_list)) {
-		struct io_kiocb *cancel_req = NULL;
+		struct io_kiocb *cancel_req = NULL, *req;
+		DEFINE_WAIT(wait);
 
 		spin_lock_irq(&ctx->inflight_lock);
 		list_for_each_entry(req, &ctx->inflight_list, inflight_entry) {
@@ -7404,6 +7384,7 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx,
 			 */
 			if (refcount_sub_and_test(2, &cancel_req->refs)) {
 				io_put_req(cancel_req);
+				finish_wait(&ctx->inflight_wait, &wait);
 				continue;
 			}
 		}
@@ -7411,8 +7392,8 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx,
 		io_wq_cancel_work(ctx->io_wq, &cancel_req->work);
 		io_put_req(cancel_req);
 		schedule();
+		finish_wait(&ctx->inflight_wait, &wait);
 	}
-	finish_wait(&ctx->inflight_wait, &wait);
 }
 
 static int io_uring_flush(struct file *file, void *data)
@@ -7761,7 +7742,8 @@ static int io_uring_get_fd(struct io_ring_ctx *ctx)
 	return ret;
 }
 
-static int io_uring_create(unsigned entries, struct io_uring_params *p)
+static int io_uring_create(unsigned entries, struct io_uring_params *p,
+			   struct io_uring_params __user *params)
 {
 	struct user_struct *user = NULL;
 	struct io_ring_ctx *ctx;
@@ -7853,6 +7835,14 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p)
 	p->cq_off.overflow = offsetof(struct io_rings, cq_overflow);
 	p->cq_off.cqes = offsetof(struct io_rings, cqes);
 
+	p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP |
+			IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS |
+			IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL;
+
+	if (copy_to_user(params, p, sizeof(*p))) {
+		ret = -EFAULT;
+		goto err;
+	}
 	/*
 	 * Install ring fd as the very last thing, so we don't risk someone
 	 * having closed it before we finish setup
@@ -7861,9 +7851,6 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p)
 	if (ret < 0)
 		goto err;
 
-	p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP |
-			IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS |
-			IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL;
 	trace_io_uring_create(ret, ctx, p->sq_entries, p->cq_entries, p->flags);
 	return ret;
 err:
@@ -7879,7 +7866,6 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p)
 static long io_uring_setup(u32 entries, struct io_uring_params __user *params)
 {
 	struct io_uring_params p;
-	long ret;
 	int i;
 
 	if (copy_from_user(&p, params, sizeof(p)))
@@ -7894,14 +7880,7 @@ static long io_uring_setup(u32 entries, struct io_uring_params __user *params)
 			IORING_SETUP_CLAMP | IORING_SETUP_ATTACH_WQ))
 		return -EINVAL;
 
-	ret = io_uring_create(entries, &p);
-	if (ret < 0)
-		return ret;
-
-	if (copy_to_user(params, &p, sizeof(p)))
-		return -EFAULT;
-
-	return ret;
+	return  io_uring_create(entries, &p, params);
 }
 
 SYSCALL_DEFINE2(io_uring_setup, u32, entries,

fs/splice.c

@@ -1118,6 +1118,10 @@ long do_splice(struct file *in, loff_t __user *off_in,
 	loff_t offset;
 	long ret;
 
+	if (unlikely(!(in->f_mode & FMODE_READ) ||
+		     !(out->f_mode & FMODE_WRITE)))
+		return -EBADF;
+
 	ipipe = get_pipe_info(in);
 	opipe = get_pipe_info(out);
 
@@ -1125,12 +1129,6 @@ long do_splice(struct file *in, loff_t __user *off_in,
 		if (off_in || off_out)
 			return -ESPIPE;
 
-		if (!(in->f_mode & FMODE_READ))
-			return -EBADF;
-
-		if (!(out->f_mode & FMODE_WRITE))
-			return -EBADF;
-
 		/* Splicing to self would be fun, but... */
 		if (ipipe == opipe)
 			return -EINVAL;
@@ -1153,9 +1151,6 @@ long do_splice(struct file *in, loff_t __user *off_in,
 			offset = out->f_pos;
 		}
 
-		if (unlikely(!(out->f_mode & FMODE_WRITE)))
-			return -EBADF;
-
 		if (unlikely(out->f_flags & O_APPEND))
 			return -EINVAL;
 
@@ -1440,15 +1435,11 @@ SYSCALL_DEFINE6(splice, int, fd_in, loff_t __user *, off_in,
 	error = -EBADF;
 	in = fdget(fd_in);
 	if (in.file) {
-		if (in.file->f_mode & FMODE_READ) {
-			out = fdget(fd_out);
-			if (out.file) {
-				if (out.file->f_mode & FMODE_WRITE)
-					error = do_splice(in.file, off_in,
-							  out.file, off_out,
-							  len, flags);
-				fdput(out);
-			}
+		out = fdget(fd_out);
+		if (out.file) {
+			error = do_splice(in.file, off_in, out.file, off_out,
+					  len, flags);
+			fdput(out);
 		}
 		fdput(in);
 	}
@@ -1770,6 +1761,10 @@ static long do_tee(struct file *in, struct file *out, size_t len,
 	struct pipe_inode_info *opipe = get_pipe_info(out);
 	int ret = -EINVAL;
 
+	if (unlikely(!(in->f_mode & FMODE_READ) ||
+		     !(out->f_mode & FMODE_WRITE)))
+		return -EBADF;
+
 	/*
 	 * Duplicate the contents of ipipe to opipe without actually
 	 * copying the data.
@@ -1795,7 +1790,7 @@ static long do_tee(struct file *in, struct file *out, size_t len,
 
 SYSCALL_DEFINE4(tee, int, fdin, int, fdout, size_t, len, unsigned int, flags)
 {
-	struct fd in;
+	struct fd in, out;
 	int error;
 
 	if (unlikely(flags & ~SPLICE_F_ALL))
@@ -1807,14 +1802,10 @@ SYSCALL_DEFINE4(tee, int, fdin, int, fdout, size_t, len, unsigned int, flags)
 	error = -EBADF;
 	in = fdget(fdin);
 	if (in.file) {
-		if (in.file->f_mode & FMODE_READ) {
-			struct fd out = fdget(fdout);
-			if (out.file) {
-				if (out.file->f_mode & FMODE_WRITE)
-					error = do_tee(in.file, out.file,
-							len, flags);
-				fdput(out);
-			}
+		out = fdget(fdout);
+		if (out.file) {
+			error = do_tee(in.file, out.file, len, flags);
+			fdput(out);
 		}
  		fdput(in);
  	}