1 files changed, 63 insertions, 53 deletions

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 5318a3b704f6..6df8bd481425 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -11,6 +11,7 @@
 
 #include "super.h"
 #include "mds_client.h"
+#include "cache.h"
 #include <linux/ceph/osd_client.h>
 
 /*
@@ -70,15 +71,16 @@ static int ceph_set_page_dirty(struct page *page)
 	struct address_space *mapping = page->mapping;
 	struct inode *inode;
 	struct ceph_inode_info *ci;
-	int undo = 0;
 	struct ceph_snap_context *snapc;
+	int ret;
 
 	if (unlikely(!mapping))
 		return !TestSetPageDirty(page);
 
-	if (TestSetPageDirty(page)) {
+	if (PageDirty(page)) {
 		dout("%p set_page_dirty %p idx %lu -- already dirty\n",
 		     mapping->host, page, page->index);
+		BUG_ON(!PagePrivate(page));
 		return 0;
 	}
 
@@ -107,35 +109,19 @@ static int ceph_set_page_dirty(struct page *page)
 	     snapc, snapc->seq, snapc->num_snaps);
 	spin_unlock(&ci->i_ceph_lock);
 
-	/* now adjust page */
-	spin_lock_irq(&mapping->tree_lock);
-	if (page->mapping) {	/* Race with truncate? */
-		WARN_ON_ONCE(!PageUptodate(page));
-		account_page_dirtied(page, page->mapping);
-		radix_tree_tag_set(&mapping->page_tree,
-				page_index(page), PAGECACHE_TAG_DIRTY);
-
-		/*
-		 * Reference snap context in page->private.  Also set
-		 * PagePrivate so that we get invalidatepage callback.
-		 */
-		page->private = (unsigned long)snapc;
-		SetPagePrivate(page);
-	} else {
-		dout("ANON set_page_dirty %p (raced truncate?)\n", page);
-		undo = 1;
-	}
-
-	spin_unlock_irq(&mapping->tree_lock);
-
-	if (undo)
-		/* whoops, we failed to dirty the page */
-		ceph_put_wrbuffer_cap_refs(ci, 1, snapc);
+	/*
+	 * Reference snap context in page->private.  Also set
+	 * PagePrivate so that we get invalidatepage callback.
+	 */
+	BUG_ON(PagePrivate(page));
+	page->private = (unsigned long)snapc;
+	SetPagePrivate(page);
 
-	__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
+	ret = __set_page_dirty_nobuffers(page);
+	WARN_ON(!PageLocked(page));
+	WARN_ON(!page->mapping);
 
-	BUG_ON(!PageDirty(page));
-	return 1;
+	return ret;
 }
 
 /*
@@ -150,11 +136,19 @@ static void ceph_invalidatepage(struct page *page, unsigned int offset,
 	struct ceph_inode_info *ci;
 	struct ceph_snap_context *snapc = page_snap_context(page);
 
-	BUG_ON(!PageLocked(page));
-	BUG_ON(!PagePrivate(page));
-	BUG_ON(!page->mapping);
-
 	inode = page->mapping->host;
+	ci = ceph_inode(inode);
+
+	if (offset != 0 || length != PAGE_CACHE_SIZE) {
+		dout("%p invalidatepage %p idx %lu partial dirty page %u~%u\n",
+		     inode, page, page->index, offset, length);
+		return;
+	}
+
+	ceph_invalidate_fscache_page(inode, page);
+
+	if (!PagePrivate(page))
+		return;
 
 	/*
 	 * We can get non-dirty pages here due to races between
@@ -164,31 +158,28 @@ static void ceph_invalidatepage(struct page *page, unsigned int offset,
 	if (!PageDirty(page))
 		pr_err("%p invalidatepage %p page not dirty\n", inode, page);
 
-	if (offset == 0 && length == PAGE_CACHE_SIZE)
-		ClearPageChecked(page);
+	ClearPageChecked(page);
 
-	ci = ceph_inode(inode);
-	if (offset == 0 && length == PAGE_CACHE_SIZE) {
-		dout("%p invalidatepage %p idx %lu full dirty page\n",
-		     inode, page, page->index);
-		ceph_put_wrbuffer_cap_refs(ci, 1, snapc);
-		ceph_put_snap_context(snapc);
-		page->private = 0;
-		ClearPagePrivate(page);
-	} else {
-		dout("%p invalidatepage %p idx %lu partial dirty page %u(%u)\n",
-		     inode, page, page->index, offset, length);
-	}
+	dout("%p invalidatepage %p idx %lu full dirty page\n",
+	     inode, page, page->index);
+
+	ceph_put_wrbuffer_cap_refs(ci, 1, snapc);
+	ceph_put_snap_context(snapc);
+	page->private = 0;
+	ClearPagePrivate(page);
 }
 
-/* just a sanity check */
 static int ceph_releasepage(struct page *page, gfp_t g)
 {
 	struct inode *inode = page->mapping ? page->mapping->host : NULL;
 	dout("%p releasepage %p idx %lu\n", inode, page, page->index);
 	WARN_ON(PageDirty(page));
-	WARN_ON(PagePrivate(page));
-	return 0;
+
+	/* Can we release the page from the cache? */
+	if (!ceph_release_fscache_page(page, g))
+		return 0;
+
+	return !PagePrivate(page);
 }
 
 /*
@@ -198,11 +189,16 @@ static int readpage_nounlock(struct file *filp, struct page *page)
 {
 	struct inode *inode = file_inode(filp);
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_osd_client *osdc = 
+	struct ceph_osd_client *osdc =
 		&ceph_inode_to_client(inode)->client->osdc;
 	int err = 0;
 	u64 len = PAGE_CACHE_SIZE;
 
+	err = ceph_readpage_from_fscache(inode, page);
+
+	if (err == 0)
+		goto out;
+
 	dout("readpage inode %p file %p page %p index %lu\n",
 	     inode, filp, page, page->index);
 	err = ceph_osdc_readpages(osdc, ceph_vino(inode), &ci->i_layout,
@@ -220,6 +216,9 @@ static int readpage_nounlock(struct file *filp, struct page *page)
 	}
 	SetPageUptodate(page);
 
+	if (err == 0)
+		ceph_readpage_to_fscache(inode, page);
+
 out:
 	return err < 0 ? err : 0;
 }
@@ -262,6 +261,7 @@ static void finish_read(struct ceph_osd_request *req, struct ceph_msg *msg)
 		     page->index);
 		flush_dcache_page(page);
 		SetPageUptodate(page);
+		ceph_readpage_to_fscache(inode, page);
 		unlock_page(page);
 		page_cache_release(page);
 		bytes -= PAGE_CACHE_SIZE;
@@ -331,11 +331,12 @@ static int start_read(struct inode *inode, struct list_head *page_list, int max)
 		page = list_entry(page_list->prev, struct page, lru);
 		BUG_ON(PageLocked(page));
 		list_del(&page->lru);
-		
+
  		dout("start_read %p adding %p idx %lu\n", inode, page,
 		     page->index);
 		if (add_to_page_cache_lru(page, &inode->i_data, page->index,
 					  GFP_NOFS)) {
+			ceph_fscache_uncache_page(inode, page);
 			page_cache_release(page);
 			dout("start_read %p add_to_page_cache failed %p\n",
 			     inode, page);
@@ -378,6 +379,12 @@ static int ceph_readpages(struct file *file, struct address_space *mapping,
 	int rc = 0;
 	int max = 0;
 
+	rc = ceph_readpages_from_fscache(mapping->host, mapping, page_list,
+					 &nr_pages);
+
+	if (rc == 0)
+		goto out;
+
 	if (fsc->mount_options->rsize >= PAGE_CACHE_SIZE)
 		max = (fsc->mount_options->rsize + PAGE_CACHE_SIZE - 1)
 			>> PAGE_SHIFT;
@@ -392,6 +399,8 @@ static int ceph_readpages(struct file *file, struct address_space *mapping,
 		BUG_ON(rc == 0);
 	}
 out:
+	ceph_fscache_readpages_cancel(inode, page_list);
+
 	dout("readpages %p file %p ret %d\n", inode, file, rc);
 	return rc;
 }
@@ -497,6 +506,8 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 	    CONGESTION_ON_THRESH(fsc->mount_options->congestion_kb))
 		set_bdi_congested(&fsc->backing_dev_info, BLK_RW_ASYNC);
 
+	ceph_readpage_to_fscache(inode, page);
+
 	set_page_writeback(page);
 	err = ceph_osdc_writepages(osdc, ceph_vino(inode),
 				   &ci->i_layout, snapc,
@@ -552,7 +563,6 @@ static void ceph_release_pages(struct page **pages, int num)
 	pagevec_release(&pvec);
 }
 
-
 /*
  * async writeback completion handler.
  *