cifs: Implement splice_read to pass down ITER_BVEC not ITER_PIPE

Provide cifs_splice_read() to use a bvec rather than an pipe iterator as
the latter cannot so easily be split and advanced, which is necessary to
pass an iterator down to the bottom levels.  Upstream cifs gets around this
problem by using iov_iter_get_pages() to prefill the pipe and then passing
the list of pages down.

This is done by:

 (1) Bulk-allocate a bunch of pages to carry as much of the requested
     amount of data as possible, but without overrunning the available
     slots in the pipe and add them to an ITER_BVEC.

 (2) Synchronously call ->read_iter() to read into the buffer.

 (3) Discard any unused pages.

 (4) Load the remaining pages into the pipe in order and advance the head
     pointer.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Steve French <sfrench@samba.org>
cc: Shyam Prasad N <nspmangalore@gmail.com>
cc: Rohith Surabattula <rohiths.msft@gmail.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: Al Viro <viro@zeniv.linux.org.uk>
cc: linux-cifs@vger.kernel.org

fs/cifs/cifsfs.c

@@ -1328,7 +1328,7 @@ const struct file_operations cifs_file_ops = {
 	.fsync = cifs_fsync,
 	.flush = cifs_flush,
 	.mmap  = cifs_file_mmap,
-	.splice_read = generic_file_splice_read,
+	.splice_read = cifs_splice_read,
 	.splice_write = iter_file_splice_write,
 	.llseek = cifs_llseek,
 	.unlocked_ioctl	= cifs_ioctl,
@@ -1348,7 +1348,7 @@ const struct file_operations cifs_file_strict_ops = {
 	.fsync = cifs_strict_fsync,
 	.flush = cifs_flush,
 	.mmap = cifs_file_strict_mmap,
-	.splice_read = generic_file_splice_read,
+	.splice_read = cifs_splice_read,
 	.splice_write = iter_file_splice_write,
 	.llseek = cifs_llseek,
 	.unlocked_ioctl	= cifs_ioctl,
@@ -1368,7 +1368,7 @@ const struct file_operations cifs_file_direct_ops = {
 	.fsync = cifs_fsync,
 	.flush = cifs_flush,
 	.mmap = cifs_file_mmap,
-	.splice_read = generic_file_splice_read,
+	.splice_read = cifs_splice_read,
 	.splice_write = iter_file_splice_write,
 	.unlocked_ioctl  = cifs_ioctl,
 	.copy_file_range = cifs_copy_file_range,
@@ -1386,7 +1386,7 @@ const struct file_operations cifs_file_nobrl_ops = {
 	.fsync = cifs_fsync,
 	.flush = cifs_flush,
 	.mmap  = cifs_file_mmap,
-	.splice_read = generic_file_splice_read,
+	.splice_read = cifs_splice_read,
 	.splice_write = iter_file_splice_write,
 	.llseek = cifs_llseek,
 	.unlocked_ioctl	= cifs_ioctl,
@@ -1404,7 +1404,7 @@ const struct file_operations cifs_file_strict_nobrl_ops = {
 	.fsync = cifs_strict_fsync,
 	.flush = cifs_flush,
 	.mmap = cifs_file_strict_mmap,
-	.splice_read = generic_file_splice_read,
+	.splice_read = cifs_splice_read,
 	.splice_write = iter_file_splice_write,
 	.llseek = cifs_llseek,
 	.unlocked_ioctl	= cifs_ioctl,
@@ -1422,7 +1422,7 @@ const struct file_operations cifs_file_direct_nobrl_ops = {
 	.fsync = cifs_fsync,
 	.flush = cifs_flush,
 	.mmap = cifs_file_mmap,
-	.splice_read = generic_file_splice_read,
+	.splice_read = cifs_splice_read,
 	.splice_write = iter_file_splice_write,
 	.unlocked_ioctl  = cifs_ioctl,
 	.copy_file_range = cifs_copy_file_range,

fs/cifs/cifsfs.h

@@ -100,6 +100,9 @@ extern ssize_t cifs_strict_readv(struct kiocb *iocb, struct iov_iter *to);
 extern ssize_t cifs_user_writev(struct kiocb *iocb, struct iov_iter *from);
 extern ssize_t cifs_direct_writev(struct kiocb *iocb, struct iov_iter *from);
 extern ssize_t cifs_strict_writev(struct kiocb *iocb, struct iov_iter *from);
+extern ssize_t cifs_splice_read(struct file *in, loff_t *ppos,
+				struct pipe_inode_info *pipe, size_t len,
+				unsigned int flags);
 extern int cifs_flock(struct file *pfile, int cmd, struct file_lock *plock);
 extern int cifs_lock(struct file *, int, struct file_lock *);
 extern int cifs_fsync(struct file *, loff_t, loff_t, int);

fs/cifs/file.c

@@ -5258,3 +5258,95 @@ const struct address_space_operations cifs_addr_ops_smallbuf = {
 	.invalidate_folio = cifs_invalidate_folio,
 	.launder_folio = cifs_launder_folio,
 };
+
+/*
+ * Splice data from a file into a pipe.
+ */
+ssize_t cifs_splice_read(struct file *file, loff_t *ppos,
+			 struct pipe_inode_info *pipe, size_t len,
+			 unsigned int flags)
+{
+	LIST_HEAD(pages);
+	struct iov_iter to;
+	struct bio_vec *bv;
+	struct kiocb kiocb;
+	struct page *page;
+	unsigned int head;
+	ssize_t ret;
+	size_t used, npages, chunk, remain, reclaim;
+	int i;
+
+	/* Work out how much data we can actually add into the pipe */
+	used = pipe_occupancy(pipe->head, pipe->tail);
+	npages = max_t(ssize_t, pipe->max_usage - used, 0);
+	len = min(len, npages * PAGE_SIZE);
+	npages = DIV_ROUND_UP(len, PAGE_SIZE);
+
+	bv = kmalloc(array_size(npages, sizeof(bv[0])), GFP_KERNEL);
+	if (!bv)
+		return -ENOMEM;
+
+	npages = alloc_pages_bulk_list(GFP_USER, npages, &pages);
+	if (!npages) {
+		kfree(bv);
+		return -ENOMEM;
+	}
+
+	remain = len = min(len, npages * PAGE_SIZE);
+
+	for (i = 0; i < npages; i++) {
+		chunk = min(PAGE_SIZE, remain);
+		page = list_first_entry(&pages, struct page, lru);
+		list_del_init(&page->lru);
+		bv[i].bv_page = page;
+		bv[i].bv_offset = 0;
+		bv[i].bv_len = chunk;
+		remain -= chunk;
+	}
+
+	/* Do the I/O */
+	iov_iter_bvec(&to, ITER_DEST, bv, npages, len);
+	init_sync_kiocb(&kiocb, file);
+	kiocb.ki_pos = *ppos;
+	ret = call_read_iter(file, &kiocb, &to);
+
+	reclaim = npages * PAGE_SIZE;
+	remain = 0;
+	if (ret > 0) {
+		reclaim -= ret;
+		remain = ret;
+		*ppos = kiocb.ki_pos;
+		file_accessed(file);
+	} else if (ret < 0) {
+		/*
+		 * callers of ->splice_read() expect -EAGAIN on
+		 * "can't put anything in there", rather than -EFAULT.
+		 */
+		if (ret == -EFAULT)
+			ret = -EAGAIN;
+	}
+
+	/* Free any pages that didn't get touched at all. */
+	for (; reclaim >= PAGE_SIZE; reclaim -= PAGE_SIZE)
+		__free_page(bv[--npages].bv_page);
+
+	/* Push the remaining pages into the pipe. */
+	head = pipe->head;
+	for (i = 0; i < npages; i++) {
+		struct pipe_buffer *buf = &pipe->bufs[head & (pipe->ring_size - 1)];
+
+		chunk = min(remain, PAGE_SIZE);
+		*buf = (struct pipe_buffer) {
+			.ops	= &default_pipe_buf_ops,
+			.page	= bv[i].bv_page,
+			.offset	= 0,
+			.len	= chunk,
+		};
+		head++;
+		remain -= chunk;
+	}
+	pipe->head = head;
+
+	kfree(bv);
+	return ret;
+}