->splice_write() via ->write_iter()

iter_file_splice_write() - a ->splice_write() instance that gathers the
pipe buffers, builds a bio_vec-based iov_iter covering those and feeds
it to ->write_iter().  A bunch of simple cases coverted to that...

[AV: fixed the braino spotted by Cyrill]

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

1 files changed, 140 insertions, 0 deletions

diff --git a/fs/splice.c b/fs/splice.c
index f99e420..f195a9b 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -32,6 +32,7 @@
 #include <linux/gfp.h>
 #include <linux/socket.h>
 #include <linux/compat.h>
+#include <linux/aio.h>
 #include "internal.h"
 
 /*
@@ -1052,6 +1053,145 @@ generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
 
 EXPORT_SYMBOL(generic_file_splice_write);
 
+/**
+ * iter_file_splice_write - splice data from a pipe to a file
+ * @pipe:	pipe info
+ * @out:	file to write to
+ * @ppos:	position in @out
+ * @len:	number of bytes to splice
+ * @flags:	splice modifier flags
+ *
+ * Description:
+ *    Will either move or copy pages (determined by @flags options) from
+ *    the given pipe inode to the given file.
+ *    This one is ->write_iter-based.
+ *
+ */
+ssize_t
+iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
+			  loff_t *ppos, size_t len, unsigned int flags)
+{
+	struct splice_desc sd = {
+		.total_len = len,
+		.flags = flags,
+		.pos = *ppos,
+		.u.file = out,
+	};
+	int nbufs = pipe->buffers;
+	struct bio_vec *array = kcalloc(nbufs, sizeof(struct bio_vec),
+					GFP_KERNEL);
+	ssize_t ret;
+
+	if (unlikely(!array))
+		return -ENOMEM;
+
+	pipe_lock(pipe);
+
+	splice_from_pipe_begin(&sd);
+	while (sd.total_len) {
+		struct iov_iter from;
+		struct kiocb kiocb;
+		size_t left;
+		int n, idx;
+
+		ret = splice_from_pipe_next(pipe, &sd);
+		if (ret <= 0)
+			break;
+
+		if (unlikely(nbufs < pipe->buffers)) {
+			kfree(array);
+			nbufs = pipe->buffers;
+			array = kcalloc(nbufs, sizeof(struct bio_vec),
+					GFP_KERNEL);
+			if (!array) {
+				ret = -ENOMEM;
+				break;
+			}
+		}
+
+		/* build the vector */
+		left = sd.total_len;
+		for (n = 0, idx = pipe->curbuf; left && n < pipe->nrbufs; n++, idx++) {
+			struct pipe_buffer *buf = pipe->bufs + idx;
+			size_t this_len = buf->len;
+
+			if (this_len > left)
+				this_len = left;
+
+			if (idx == pipe->buffers - 1)
+				idx = -1;
+
+			ret = buf->ops->confirm(pipe, buf);
+			if (unlikely(ret)) {
+				if (ret == -ENODATA)
+					ret = 0;
+				goto done;
+			}
+
+			array[n].bv_page = buf->page;
+			array[n].bv_len = this_len;
+			array[n].bv_offset = buf->offset;
+			left -= this_len;
+		}
+
+		/* ... iov_iter */
+		from.type = ITER_BVEC | WRITE;
+		from.bvec = array;
+		from.nr_segs = n;
+		from.count = sd.total_len - left;
+		from.iov_offset = 0;
+
+		/* ... and iocb */
+		init_sync_kiocb(&kiocb, out);
+		kiocb.ki_pos = sd.pos;
+		kiocb.ki_nbytes = sd.total_len - left;
+
+		/* now, send it */
+		ret = out->f_op->write_iter(&kiocb, &from);
+		if (-EIOCBQUEUED == ret)
+			ret = wait_on_sync_kiocb(&kiocb);
+
+		if (ret <= 0)
+			break;
+
+		sd.num_spliced += ret;
+		sd.total_len -= ret;
+		*ppos = sd.pos = kiocb.ki_pos;
+
+		/* dismiss the fully eaten buffers, adjust the partial one */
+		while (ret) {
+			struct pipe_buffer *buf = pipe->bufs + pipe->curbuf;
+			if (ret >= buf->len) {
+				const struct pipe_buf_operations *ops = buf->ops;
+				ret -= buf->len;
+				buf->len = 0;
+				buf->ops = NULL;
+				ops->release(pipe, buf);
+				pipe->curbuf = (pipe->curbuf + 1) & (pipe->buffers - 1);
+				pipe->nrbufs--;
+				if (pipe->files)
+					sd.need_wakeup = true;
+			} else {
+				buf->offset += ret;
+				buf->len -= ret;
+				ret = 0;
+			}
+		}
+	}
+done:
+	kfree(array);
+	splice_from_pipe_end(pipe, &sd);
+
+	pipe_unlock(pipe);
+
+	if (sd.num_spliced)
+		ret = sd.num_spliced;
+
+	return ret;
+}
+
+EXPORT_SYMBOL(iter_file_splice_write);
+
 static int write_pipe_buf(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
 			  struct splice_desc *sd)
 {