1 files changed, 165 insertions, 40 deletions

diff --git a/fs/splice.c b/fs/splice.c
index 7a9565d8ec4f..004eb1c4ce31 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -33,6 +33,7 @@
 #include <linux/fsnotify.h>
 #include <linux/security.h>
 #include <linux/gfp.h>
+#include <linux/net.h>
 #include <linux/socket.h>
 #include <linux/sched/signal.h>
 
@@ -415,30 +416,6 @@ const struct pipe_buf_operations nosteal_pipe_buf_ops = {
 };
 EXPORT_SYMBOL(nosteal_pipe_buf_ops);
 
-/*
- * Send 'sd->len' bytes to socket from 'sd->file' at position 'sd->pos'
- * using sendpage(). Return the number of bytes sent.
- */
-static int pipe_to_sendpage(struct pipe_inode_info *pipe,
-			    struct pipe_buffer *buf, struct splice_desc *sd)
-{
-	struct file *file = sd->u.file;
-	loff_t pos = sd->pos;
-	int more;
-
-	if (!likely(file->f_op->sendpage))
-		return -EINVAL;
-
-	more = (sd->flags & SPLICE_F_MORE) ? MSG_MORE : 0;
-
-	if (sd->len < sd->total_len &&
-	    pipe_occupancy(pipe->head, pipe->tail) > 1)
-		more |= MSG_SENDPAGE_NOTLAST;
-
-	return file->f_op->sendpage(file, buf->page, buf->offset,
-				    sd->len, &pos, more);
-}
-
 static void wakeup_pipe_writers(struct pipe_inode_info *pipe)
 {
 	smp_mb();
@@ -619,7 +596,7 @@ static void splice_from_pipe_end(struct pipe_inode_info *pipe, struct splice_des
  * Description:
  *    This function does little more than loop over the pipe and call
  *    @actor to do the actual moving of a single struct pipe_buffer to
- *    the desired destination. See pipe_to_file, pipe_to_sendpage, or
+ *    the desired destination. See pipe_to_file, pipe_to_sendmsg, or
  *    pipe_to_user.
  *
  */
@@ -800,8 +777,9 @@ done:
 
 EXPORT_SYMBOL(iter_file_splice_write);
 
+#ifdef CONFIG_NET
 /**
- * generic_splice_sendpage - splice data from a pipe to a socket
+ * splice_to_socket - splice data from a pipe to a socket
  * @pipe:	pipe to splice from
  * @out:	socket to write to
  * @ppos:	position in @out
@@ -813,13 +791,129 @@ EXPORT_SYMBOL(iter_file_splice_write);
  *    is involved.
  *
  */
-ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe, struct file *out,
-				loff_t *ppos, size_t len, unsigned int flags)
+ssize_t splice_to_socket(struct pipe_inode_info *pipe, struct file *out,
+			 loff_t *ppos, size_t len, unsigned int flags)
 {
-	return splice_from_pipe(pipe, out, ppos, len, flags, pipe_to_sendpage);
-}
+	struct socket *sock = sock_from_file(out);
+	struct bio_vec bvec[16];
+	struct msghdr msg = {};
+	ssize_t ret = 0;
+	size_t spliced = 0;
+	bool need_wakeup = false;
+
+	pipe_lock(pipe);
+
+	while (len > 0) {
+		unsigned int head, tail, mask, bc = 0;
+		size_t remain = len;
+
+		/*
+		 * Check for signal early to make process killable when there
+		 * are always buffers available
+		 */
+		ret = -ERESTARTSYS;
+		if (signal_pending(current))
+			break;
+
+		while (pipe_empty(pipe->head, pipe->tail)) {
+			ret = 0;
+			if (!pipe->writers)
+				goto out;
+
+			if (spliced)
+				goto out;
+
+			ret = -EAGAIN;
+			if (flags & SPLICE_F_NONBLOCK)
+				goto out;
+
+			ret = -ERESTARTSYS;
+			if (signal_pending(current))
+				goto out;
+
+			if (need_wakeup) {
+				wakeup_pipe_writers(pipe);
+				need_wakeup = false;
+			}
+
+			pipe_wait_readable(pipe);
+		}
+
+		head = pipe->head;
+		tail = pipe->tail;
+		mask = pipe->ring_size - 1;
+
+		while (!pipe_empty(head, tail)) {
+			struct pipe_buffer *buf = &pipe->bufs[tail & mask];
+			size_t seg;
+
+			if (!buf->len) {
+				tail++;
+				continue;
+			}
+
+			seg = min_t(size_t, remain, buf->len);
+
+			ret = pipe_buf_confirm(pipe, buf);
+			if (unlikely(ret)) {
+				if (ret == -ENODATA)
+					ret = 0;
+				break;
+			}
 
-EXPORT_SYMBOL(generic_splice_sendpage);
+			bvec_set_page(&bvec[bc++], buf->page, seg, buf->offset);
+			remain -= seg;
+			if (remain == 0 || bc >= ARRAY_SIZE(bvec))
+				break;
+			tail++;
+		}
+
+		if (!bc)
+			break;
+
+		msg.msg_flags = MSG_SPLICE_PAGES;
+		if (flags & SPLICE_F_MORE)
+			msg.msg_flags |= MSG_MORE;
+		if (remain && pipe_occupancy(pipe->head, tail) > 0)
+			msg.msg_flags |= MSG_MORE;
+
+		iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, bvec, bc,
+			      len - remain);
+		ret = sock_sendmsg(sock, &msg);
+		if (ret <= 0)
+			break;
+
+		spliced += ret;
+		len -= ret;
+		tail = pipe->tail;
+		while (ret > 0) {
+			struct pipe_buffer *buf = &pipe->bufs[tail & mask];
+			size_t seg = min_t(size_t, ret, buf->len);
+
+			buf->offset += seg;
+			buf->len -= seg;
+			ret -= seg;
+
+			if (!buf->len) {
+				pipe_buf_release(pipe, buf);
+				tail++;
+			}
+		}
+
+		if (tail != pipe->tail) {
+			pipe->tail = tail;
+			if (pipe->files)
+				need_wakeup = true;
+		}
+	}
+
+out:
+	pipe_unlock(pipe);
+	if (need_wakeup)
+		wakeup_pipe_writers(pipe);
+	return spliced ?: ret;
+}
+#endif
 
 static int warn_unsupported(struct file *file, const char *op)
 {
@@ -840,6 +934,17 @@ 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);
+}
+
 /**
  * vfs_splice_read - Read data from a file and splice it into a pipe
  * @in:		File to splice from
@@ -944,13 +1049,17 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd,
 	 */
 	bytes = 0;
 	len = sd->total_len;
+
+	/* Don't block on output, we have to drain the direct pipe. */
 	flags = sd->flags;
+	sd->flags &= ~SPLICE_F_NONBLOCK;
 
 	/*
-	 * Don't block on output, we have to drain the direct pipe.
+	 * We signal MORE until we've read sufficient data to fulfill the
+	 * request and we keep signalling it if the caller set it.
 	 */
-	sd->flags &= ~SPLICE_F_NONBLOCK;
 	more = sd->flags & SPLICE_F_MORE;
+	sd->flags |= SPLICE_F_MORE;
 
 	WARN_ON_ONCE(!pipe_empty(pipe->head, pipe->tail));
 
@@ -960,20 +1069,18 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd,
 
 		ret = vfs_splice_read(in, &pos, pipe, len, flags);
 		if (unlikely(ret <= 0))
-			goto out_release;
+			goto read_failure;
 
 		read_len = ret;
 		sd->total_len = read_len;
 
 		/*
-		 * If more data is pending, set SPLICE_F_MORE
-		 * If this is the last data and SPLICE_F_MORE was not set
-		 * initially, clears it.
+		 * If we now have sufficient data to fulfill the request then
+		 * we clear SPLICE_F_MORE if it was not set initially.
 		 */
-		if (read_len < len)
-			sd->flags |= SPLICE_F_MORE;
-		else if (!more)
+		if (read_len >= len && !more)
 			sd->flags &= ~SPLICE_F_MORE;
+
 		/*
 		 * NOTE: nonblocking mode only applies to the input. We
 		 * must not do the output in nonblocking mode as then we
@@ -1000,6 +1107,15 @@ done:
 	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
@@ -1028,6 +1144,14 @@ 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
@@ -1053,6 +1177,7 @@ 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;