ceph: support ceph_pagelist for message payload

The ceph_pagelist is a simple list of whole pages, strung together via
their lru list_head.  It facilitates encoding to a "buffer" of unknown
size.  Allow its use in place of the ceph_msg page vector.

This will be used to fix the huge buffer preallocation woes of MDS
reconnection.

Signed-off-by: Sage Weil <sage@newdream.net>

1 files changed, 54 insertions, 0 deletions

diff --git a/fs/ceph/pagelist.c b/fs/ceph/pagelist.c
new file mode 100644
index 000000000000..370e93695474
--- /dev/null
+++ b/fs/ceph/pagelist.c
@@ -0,0 +1,54 @@
+
+#include <linux/pagemap.h>
+#include <linux/highmem.h>
+
+#include "pagelist.h"
+
+int ceph_pagelist_release(struct ceph_pagelist *pl)
+{
+	if (pl->mapped_tail)
+		kunmap(pl->mapped_tail);
+	while (!list_empty(&pl->head)) {
+		struct page *page = list_first_entry(&pl->head, struct page,
+						     lru);
+		list_del(&page->lru);
+		__free_page(page);
+	}
+	return 0;
+}
+
+static int ceph_pagelist_addpage(struct ceph_pagelist *pl)
+{
+	struct page *page = alloc_page(GFP_NOFS);
+	if (!page)
+		return -ENOMEM;
+	pl->room += PAGE_SIZE;
+	list_add_tail(&page->lru, &pl->head);
+	if (pl->mapped_tail)
+		kunmap(pl->mapped_tail);
+	pl->mapped_tail = kmap(page);
+	return 0;
+}
+
+int ceph_pagelist_append(struct ceph_pagelist *pl, void *buf, size_t len)
+{
+	while (pl->room < len) {
+		size_t bit = pl->room;
+		int ret;
+
+		memcpy(pl->mapped_tail + (pl->length & ~PAGE_CACHE_MASK),
+		       buf, bit);
+		pl->length += bit;
+		pl->room -= bit;
+		buf += bit;
+		len -= bit;
+		ret = ceph_pagelist_addpage(pl);
+		if (ret)
+			return ret;
+	}
+
+	memcpy(pl->mapped_tail + (pl->length & ~PAGE_CACHE_MASK), buf, len);
+	pl->length += len;
+	pl->room -= len;
+	return 0;
+}