splice, net: Add a splice_eof op to file-ops and socket-ops

Add an optional method, ->splice_eof(), to allow splice to indicate the
premature termination of a splice to struct file_operations and struct
proto_ops.

This is called if sendfile() or splice() encounters all of the following
conditions inside splice_direct_to_actor():

 (1) the user did not set SPLICE_F_MORE (splice only), and

 (2) an EOF condition occurred (->splice_read() returned 0), and

 (3) we haven't read enough to fulfill the request (ie. len > 0 still), and

 (4) we have already spliced at least one byte.

A further patch will modify the behaviour of SPLICE_F_MORE to always be
passed to the actor if either the user set it or we haven't yet read
sufficient data to fulfill the request.

Suggested-by: Linus Torvalds <[email protected]>
Link: https://lore.kernel.org/r/CAHk-=wh=V579PDYvkpnTobCLGczbgxpMgGmmhqiTyE34Cpi5Gg@mail.gmail.com/
Signed-off-by: David Howells <[email protected]>
Reviewed-by: Jakub Kicinski <[email protected]>
cc: Jens Axboe <[email protected]>
cc: Christoph Hellwig <[email protected]>
cc: Al Viro <[email protected]>
cc: Matthew Wilcox <[email protected]>
cc: Jan Kara <[email protected]>
cc: Jeff Layton <[email protected]>
cc: David Hildenbrand <[email protected]>
cc: Christian Brauner <[email protected]>
cc: Chuck Lever <[email protected]>
cc: Boris Pismenny <[email protected]>
cc: John Fastabend <[email protected]>
cc: [email protected]
Signed-off-by: Jakub Kicinski <[email protected]>

Author: dhowells

fs/splice.c

@@ -969,6 +969,17 @@ static long do_splice_from(struct pipe_inode_info *pipe, struct file *out,
 	return out->f_op->splice_write(pipe, out, ppos, len, flags);
 }
 
+/*
+ * Indicate to the caller that there was a premature EOF when reading from the
+ * source and the caller didn't indicate they would be sending more data after
+ * this.
+ */
+static void do_splice_eof(struct splice_desc *sd)
+{
+	if (sd->splice_eof)
+		sd->splice_eof(sd);
+}
+
 /*
  * Attempt to initiate a splice from a file to a pipe.
  */
@@ -1068,7 +1079,7 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd,
 
 		ret = do_splice_to(in, &pos, pipe, len, flags);
 		if (unlikely(ret <= 0))
-			goto out_release;
+			goto read_failure;
 
 		read_len = ret;
 		sd->total_len = read_len;
@@ -1108,6 +1119,15 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd,
 	file_accessed(in);
 	return bytes;
 
+read_failure:
+	/*
+	 * If the user did *not* set SPLICE_F_MORE *and* we didn't hit that
+	 * "use all of len" case that cleared SPLICE_F_MORE, *and* we did a
+	 * "->splice_in()" that returned EOF (ie zero) *and* we have sent at
+	 * least 1 byte *then* we will also do the ->splice_eof() call.
+	 */
+	if (ret == 0 && !more && len > 0 && bytes)
+		do_splice_eof(sd);
 out_release:
 	/*
 	 * If we did an incomplete transfer we must release
@@ -1136,6 +1156,14 @@ static int direct_splice_actor(struct pipe_inode_info *pipe,
 			      sd->flags);
 }
 
+static void direct_file_splice_eof(struct splice_desc *sd)
+{
+	struct file *file = sd->u.file;
+
+	if (file->f_op->splice_eof)
+		file->f_op->splice_eof(file);
+}
+
 /**
  * do_splice_direct - splices data directly between two files
  * @in:		file to splice from
@@ -1161,6 +1189,7 @@ long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
 		.flags		= flags,
 		.pos		= *ppos,
 		.u.file		= out,
+		.splice_eof	= direct_file_splice_eof,
 		.opos		= opos,
 	};
 	long ret;

include/linux/fs.h

@@ -1796,6 +1796,7 @@ struct file_operations {
 	int (*flock) (struct file *, int, struct file_lock *);
 	ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int);
 	ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int);
+	void (*splice_eof)(struct file *file);
 	int (*setlease)(struct file *, long, struct file_lock **, void **);
 	long (*fallocate)(struct file *file, int mode, loff_t offset,
 			  loff_t len);

include/linux/net.h

@@ -210,6 +210,7 @@ struct proto_ops {
 				      int offset, size_t size, int flags);
 	ssize_t 	(*splice_read)(struct socket *sock,  loff_t *ppos,
 				       struct pipe_inode_info *pipe, size_t len, unsigned int flags);
+	void		(*splice_eof)(struct socket *sock);
 	int		(*set_peek_off)(struct sock *sk, int val);
 	int		(*peek_len)(struct socket *sock);
 

include/linux/splice.h

@@ -38,6 +38,7 @@ struct splice_desc {
 		struct file *file;	/* file to read/write */
 		void *data;		/* cookie */
 	} u;
+	void (*splice_eof)(struct splice_desc *sd); /* Unexpected EOF handler */
 	loff_t pos;			/* file position */
 	loff_t *opos;			/* sendfile: output position */
 	size_t num_spliced;		/* number of bytes already spliced */

include/net/sock.h

@@ -1279,6 +1279,7 @@ struct proto {
 					   size_t len, int flags, int *addr_len);
 	int			(*sendpage)(struct sock *sk, struct page *page,
 					int offset, size_t size, int flags);
+	void			(*splice_eof)(struct socket *sock);
 	int			(*bind)(struct sock *sk,
 					struct sockaddr *addr, int addr_len);
 	int			(*bind_add)(struct sock *sk,

net/socket.c

@@ -130,6 +130,7 @@ static int sock_fasync(int fd, struct file *filp, int on);
 static ssize_t sock_splice_read(struct file *file, loff_t *ppos,
 				struct pipe_inode_info *pipe, size_t len,
 				unsigned int flags);
+static void sock_splice_eof(struct file *file);
 
 #ifdef CONFIG_PROC_FS
 static void sock_show_fdinfo(struct seq_file *m, struct file *f)
@@ -163,6 +164,7 @@ static const struct file_operations socket_file_ops = {
 	.fasync =	sock_fasync,
 	.splice_write = splice_to_socket,
 	.splice_read =	sock_splice_read,
+	.splice_eof =	sock_splice_eof,
 	.show_fdinfo =	sock_show_fdinfo,
 };
 
@@ -1076,6 +1078,14 @@ static ssize_t sock_splice_read(struct file *file, loff_t *ppos,
 	return sock->ops->splice_read(sock, ppos, pipe, len, flags);
 }
 
+static void sock_splice_eof(struct file *file)
+{
+	struct socket *sock = file->private_data;
+
+	if (sock->ops->splice_eof)
+		sock->ops->splice_eof(sock);
+}
+
 static ssize_t sock_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
 	struct file *file = iocb->ki_filp;