Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client

Pull ceph updates from Sage Weil:
 "This includes both the first pile of Ceph patches (which I sent to
  torvalds@vger, sigh) and a few new patches that add support for
  fscache for Ceph.  That includes a few fscache core fixes that David
  Howells asked go through the Ceph tree.  (Thanks go to Milosz Tanski
  for putting this feature together)

  This first batch of patches (included here) had (has) several
  important RBD bug fixes, hole punch support, several different
  cleanups in the page cache interactions, improvements in the truncate
  code (new truncate mutex to avoid shenanigans with i_mutex), and a
  series of fixes in the synchronous striping read/write code.

  On top of that is a random collection of small fixes all across the
  tree (error code checks and error path cleanup, obsolete wq flags,
  etc)"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client: (43 commits)
  ceph: use d_invalidate() to invalidate aliases
  ceph: remove ceph_lookup_inode()
  ceph: trivial buildbot warnings fix
  ceph: Do not do invalidate if the filesystem is mounted nofsc
  ceph: page still marked private_2
  ceph: ceph_readpage_to_fscache didn't check if marked
  ceph: clean PgPrivate2 on returning from readpages
  ceph: use fscache as a local presisent cache
  fscache: Netfs function for cleanup post readpages
  FS-Cache: Fix heading in documentation
  CacheFiles: Implement interface to check cache consistency
  FS-Cache: Add interface to check consistency of a cached object
  rbd: fix null dereference in dout
  rbd: fix buffer size for writes to images with snapshots
  libceph: use pg_num_mask instead of pgp_num_mask for pg.seed calc
  rbd: fix I/O error propagation for reads
  ceph: use vfs __set_page_dirty_nobuffers interface instead of doing it inside filesystem
  ceph: allow sync_read/write return partial successed size of read/write.
  ceph: fix bugs about handling short-read for sync read mode.
  ceph: remove useless variable revoked_rdcache
  ...

19 files changed, 1271 insertions, 155 deletions

diff --git a/fs/cachefiles/interface.c b/fs/cachefiles/interface.c
index d4c1206af9fc..43eb5592cdea 100644
--- a/fs/cachefiles/interface.c
+++ b/fs/cachefiles/interface.c
@@ -378,6 +378,31 @@ static void cachefiles_sync_cache(struct fscache_cache *_cache)
 }
 
 /*
+ * check if the backing cache is updated to FS-Cache
+ * - called by FS-Cache when evaluates if need to invalidate the cache
+ */
+static bool cachefiles_check_consistency(struct fscache_operation *op)
+{
+	struct cachefiles_object *object;
+	struct cachefiles_cache *cache;
+	const struct cred *saved_cred;
+	int ret;
+
+	_enter("{OBJ%x}", op->object->debug_id);
+
+	object = container_of(op->object, struct cachefiles_object, fscache);
+	cache = container_of(object->fscache.cache,
+			     struct cachefiles_cache, cache);
+
+	cachefiles_begin_secure(cache, &saved_cred);
+	ret = cachefiles_check_auxdata(object);
+	cachefiles_end_secure(cache, saved_cred);
+
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
  * notification the attributes on an object have changed
  * - called with reads/writes excluded by FS-Cache
  */
@@ -522,4 +547,5 @@ const struct fscache_cache_ops cachefiles_cache_ops = {
 	.write_page		= cachefiles_write_page,
 	.uncache_page		= cachefiles_uncache_page,
 	.dissociate_pages	= cachefiles_dissociate_pages,
+	.check_consistency	= cachefiles_check_consistency,
 };
diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h
index 49382519907a..5349473df1b1 100644
--- a/fs/cachefiles/internal.h
+++ b/fs/cachefiles/internal.h
@@ -235,6 +235,7 @@ extern int cachefiles_set_object_xattr(struct cachefiles_object *object,
 				       struct cachefiles_xattr *auxdata);
 extern int cachefiles_update_object_xattr(struct cachefiles_object *object,
 					  struct cachefiles_xattr *auxdata);
+extern int cachefiles_check_auxdata(struct cachefiles_object *object);
 extern int cachefiles_check_object_xattr(struct cachefiles_object *object,
 					 struct cachefiles_xattr *auxdata);
 extern int cachefiles_remove_object_xattr(struct cachefiles_cache *cache,
diff --git a/fs/cachefiles/xattr.c b/fs/cachefiles/xattr.c
index 2476e5162609..34c88b83e39f 100644
--- a/fs/cachefiles/xattr.c
+++ b/fs/cachefiles/xattr.c
@@ -157,6 +157,42 @@ int cachefiles_update_object_xattr(struct cachefiles_object *object,
 }
 
 /*
+ * check the consistency between the backing cache and the FS-Cache cookie
+ */
+int cachefiles_check_auxdata(struct cachefiles_object *object)
+{
+	struct cachefiles_xattr *auxbuf;
+	struct dentry *dentry = object->dentry;
+	unsigned int dlen;
+	int ret;
+
+	ASSERT(dentry);
+	ASSERT(dentry->d_inode);
+	ASSERT(object->fscache.cookie->def->check_aux);
+
+	auxbuf = kmalloc(sizeof(struct cachefiles_xattr) + 512, GFP_KERNEL);
+	if (!auxbuf)
+		return -ENOMEM;
+
+	auxbuf->len = vfs_getxattr(dentry, cachefiles_xattr_cache,
+				   &auxbuf->type, 512 + 1);
+	if (auxbuf->len < 1)
+		return -ESTALE;
+
+	if (auxbuf->type != object->fscache.cookie->def->type)
+		return -ESTALE;
+
+	dlen = auxbuf->len - 1;
+	ret = fscache_check_aux(&object->fscache, &auxbuf->data, dlen);
+
+	kfree(auxbuf);
+	if (ret != FSCACHE_CHECKAUX_OKAY)
+		return -ESTALE;
+
+	return 0;
+}
+
+/*
  * check the state xattr on a cache file
  * - return -ESTALE if the object should be deleted
  */
diff --git a/fs/ceph/Kconfig b/fs/ceph/Kconfig
index 49bc78243db9..ac9a2ef5bb9b 100644
--- a/fs/ceph/Kconfig
+++ b/fs/ceph/Kconfig
@@ -16,3 +16,12 @@ config CEPH_FS
 
 	  If unsure, say N.
 
+if CEPH_FS
+config CEPH_FSCACHE
+	bool "Enable Ceph client caching support"
+	depends on CEPH_FS=m && FSCACHE || CEPH_FS=y && FSCACHE=y
+	help
+	  Choose Y here to enable persistent, read-only local
+	  caching support for Ceph clients using FS-Cache
+
+endif
diff --git a/fs/ceph/Makefile b/fs/ceph/Makefile
index bd352125e829..32e30106a2f0 100644
--- a/fs/ceph/Makefile
+++ b/fs/ceph/Makefile
@@ -9,3 +9,4 @@ ceph-y := super.o inode.o dir.o file.o locks.o addr.o ioctl.o \
 	mds_client.o mdsmap.o strings.o ceph_frag.o \
 	debugfs.o
 
+ceph-$(CONFIG_CEPH_FSCACHE) += cache.o
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.
  *
diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c
new file mode 100644
index 000000000000..6bfe65e0b038
--- /dev/null
+++ b/fs/ceph/cache.c
@@ -0,0 +1,398 @@
+/*
+ * Ceph cache definitions.
+ *
+ *  Copyright (C) 2013 by Adfin Solutions, Inc. All Rights Reserved.
+ *  Written by Milosz Tanski (milosz@adfin.com)
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#include "super.h"
+#include "cache.h"
+
+struct ceph_aux_inode {
+	struct timespec	mtime;
+	loff_t          size;
+};
+
+struct fscache_netfs ceph_cache_netfs = {
+	.name		= "ceph",
+	.version	= 0,
+};
+
+static uint16_t ceph_fscache_session_get_key(const void *cookie_netfs_data,
+					     void *buffer, uint16_t maxbuf)
+{
+	const struct ceph_fs_client* fsc = cookie_netfs_data;
+	uint16_t klen;
+
+	klen = sizeof(fsc->client->fsid);
+	if (klen > maxbuf)
+		return 0;
+
+	memcpy(buffer, &fsc->client->fsid, klen);
+	return klen;
+}
+
+static const struct fscache_cookie_def ceph_fscache_fsid_object_def = {
+	.name		= "CEPH.fsid",
+	.type		= FSCACHE_COOKIE_TYPE_INDEX,
+	.get_key	= ceph_fscache_session_get_key,
+};
+
+int ceph_fscache_register(void)
+{
+	return fscache_register_netfs(&ceph_cache_netfs);
+}
+
+void ceph_fscache_unregister(void)
+{
+	fscache_unregister_netfs(&ceph_cache_netfs);
+}
+
+int ceph_fscache_register_fs(struct ceph_fs_client* fsc)
+{
+	fsc->fscache = fscache_acquire_cookie(ceph_cache_netfs.primary_index,
+					      &ceph_fscache_fsid_object_def,
+					      fsc);
+
+	if (fsc->fscache == NULL) {
+		pr_err("Unable to resgister fsid: %p fscache cookie", fsc);
+		return 0;
+	}
+
+	fsc->revalidate_wq = alloc_workqueue("ceph-revalidate", 0, 1);
+	if (fsc->revalidate_wq == NULL)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static uint16_t ceph_fscache_inode_get_key(const void *cookie_netfs_data,
+					   void *buffer, uint16_t maxbuf)
+{
+	const struct ceph_inode_info* ci = cookie_netfs_data;
+	uint16_t klen;
+
+	/* use ceph virtual inode (id + snaphot) */
+	klen = sizeof(ci->i_vino);
+	if (klen > maxbuf)
+		return 0;
+
+	memcpy(buffer, &ci->i_vino, klen);
+	return klen;
+}
+
+static uint16_t ceph_fscache_inode_get_aux(const void *cookie_netfs_data,
+					   void *buffer, uint16_t bufmax)
+{
+	struct ceph_aux_inode aux;
+	const struct ceph_inode_info* ci = cookie_netfs_data;
+	const struct inode* inode = &ci->vfs_inode;
+
+	memset(&aux, 0, sizeof(aux));
+	aux.mtime = inode->i_mtime;
+	aux.size = inode->i_size;
+
+	memcpy(buffer, &aux, sizeof(aux));
+
+	return sizeof(aux);
+}
+
+static void ceph_fscache_inode_get_attr(const void *cookie_netfs_data,
+					uint64_t *size)
+{
+	const struct ceph_inode_info* ci = cookie_netfs_data;
+	const struct inode* inode = &ci->vfs_inode;
+
+	*size = inode->i_size;
+}
+
+static enum fscache_checkaux ceph_fscache_inode_check_aux(
+	void *cookie_netfs_data, const void *data, uint16_t dlen)
+{
+	struct ceph_aux_inode aux;
+	struct ceph_inode_info* ci = cookie_netfs_data;
+	struct inode* inode = &ci->vfs_inode;
+
+	if (dlen != sizeof(aux))
+		return FSCACHE_CHECKAUX_OBSOLETE;
+
+	memset(&aux, 0, sizeof(aux));
+	aux.mtime = inode->i_mtime;
+	aux.size = inode->i_size;
+
+	if (memcmp(data, &aux, sizeof(aux)) != 0)
+		return FSCACHE_CHECKAUX_OBSOLETE;
+
+	dout("ceph inode 0x%p cached okay", ci);
+	return FSCACHE_CHECKAUX_OKAY;
+}
+
+static void ceph_fscache_inode_now_uncached(void* cookie_netfs_data)
+{
+	struct ceph_inode_info* ci = cookie_netfs_data;
+	struct pagevec pvec;
+	pgoff_t first;
+	int loop, nr_pages;
+
+	pagevec_init(&pvec, 0);
+	first = 0;
+
+	dout("ceph inode 0x%p now uncached", ci);
+
+	while (1) {
+		nr_pages = pagevec_lookup(&pvec, ci->vfs_inode.i_mapping, first,
+					  PAGEVEC_SIZE - pagevec_count(&pvec));
+
+		if (!nr_pages)
+			break;
+
+		for (loop = 0; loop < nr_pages; loop++)
+			ClearPageFsCache(pvec.pages[loop]);
+
+		first = pvec.pages[nr_pages - 1]->index + 1;
+
+		pvec.nr = nr_pages;
+		pagevec_release(&pvec);
+		cond_resched();
+	}
+}
+
+static const struct fscache_cookie_def ceph_fscache_inode_object_def = {
+	.name		= "CEPH.inode",
+	.type		= FSCACHE_COOKIE_TYPE_DATAFILE,
+	.get_key	= ceph_fscache_inode_get_key,
+	.get_attr	= ceph_fscache_inode_get_attr,
+	.get_aux	= ceph_fscache_inode_get_aux,
+	.check_aux	= ceph_fscache_inode_check_aux,
+	.now_uncached	= ceph_fscache_inode_now_uncached,
+};
+
+void ceph_fscache_register_inode_cookie(struct ceph_fs_client* fsc,
+					struct ceph_inode_info* ci)
+{
+	struct inode* inode = &ci->vfs_inode;
+
+	/* No caching for filesystem */
+	if (fsc->fscache == NULL)
+		return;
+
+	/* Only cache for regular files that are read only */
+	if ((ci->vfs_inode.i_mode & S_IFREG) == 0)
+		return;
+
+	/* Avoid multiple racing open requests */
+	mutex_lock(&inode->i_mutex);
+
+	if (ci->fscache)
+		goto done;
+
+	ci->fscache = fscache_acquire_cookie(fsc->fscache,
+					     &ceph_fscache_inode_object_def,
+					     ci);
+done:
+	mutex_unlock(&inode->i_mutex);
+
+}
+
+void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info* ci)
+{
+	struct fscache_cookie* cookie;
+
+	if ((cookie = ci->fscache) == NULL)
+		return;
+
+	ci->fscache = NULL;
+
+	fscache_uncache_all_inode_pages(cookie, &ci->vfs_inode);
+	fscache_relinquish_cookie(cookie, 0);
+}
+
+static void ceph_vfs_readpage_complete(struct page *page, void *data, int error)
+{
+	if (!error)
+		SetPageUptodate(page);
+}
+
+static void ceph_vfs_readpage_complete_unlock(struct page *page, void *data, int error)
+{
+	if (!error)
+		SetPageUptodate(page);
+
+	unlock_page(page);
+}
+
+static inline int cache_valid(struct ceph_inode_info *ci)
+{
+	return ((ceph_caps_issued(ci) & CEPH_CAP_FILE_CACHE) &&
+		(ci->i_fscache_gen == ci->i_rdcache_gen));
+}
+
+
+/* Atempt to read from the fscache,
+ *
+ * This function is called from the readpage_nounlock context. DO NOT attempt to
+ * unlock the page here (or in the callback).
+ */
+int ceph_readpage_from_fscache(struct inode *inode, struct page *page)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	int ret;
+
+	if (!cache_valid(ci))
+		return -ENOBUFS;
+
+	ret = fscache_read_or_alloc_page(ci->fscache, page,
+					 ceph_vfs_readpage_complete, NULL,
+					 GFP_KERNEL);
+
+	switch (ret) {
+		case 0: /* Page found */
+			dout("page read submitted\n");
+			return 0;
+		case -ENOBUFS: /* Pages were not found, and can't be */
+		case -ENODATA: /* Pages were not found */
+			dout("page/inode not in cache\n");
+			return ret;
+		default:
+			dout("%s: unknown error ret = %i\n", __func__, ret);
+			return ret;
+	}
+}
+
+int ceph_readpages_from_fscache(struct inode *inode,
+				  struct address_space *mapping,
+				  struct list_head *pages,
+				  unsigned *nr_pages)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	int ret;
+
+	if (!cache_valid(ci))
+		return -ENOBUFS;
+
+	ret = fscache_read_or_alloc_pages(ci->fscache, mapping, pages, nr_pages,
+					  ceph_vfs_readpage_complete_unlock,
+					  NULL, mapping_gfp_mask(mapping));
+
+	switch (ret) {
+		case 0: /* All pages found */
+			dout("all-page read submitted\n");
+			return 0;
+		case -ENOBUFS: /* Some pages were not found, and can't be */
+		case -ENODATA: /* some pages were not found */
+			dout("page/inode not in cache\n");
+			return ret;
+		default:
+			dout("%s: unknown error ret = %i\n", __func__, ret);
+			return ret;
+	}
+}
+
+void ceph_readpage_to_fscache(struct inode *inode, struct page *page)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	int ret;
+
+	if (!PageFsCache(page))
+		return;
+
+	if (!cache_valid(ci))
+		return;
+
+	ret = fscache_write_page(ci->fscache, page, GFP_KERNEL);
+	if (ret)
+		 fscache_uncache_page(ci->fscache, page);
+}
+
+void ceph_invalidate_fscache_page(struct inode* inode, struct page *page)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+
+	fscache_wait_on_page_write(ci->fscache, page);
+	fscache_uncache_page(ci->fscache, page);
+}
+
+void ceph_fscache_unregister_fs(struct ceph_fs_client* fsc)
+{
+	if (fsc->revalidate_wq)
+		destroy_workqueue(fsc->revalidate_wq);
+
+	fscache_relinquish_cookie(fsc->fscache, 0);
+	fsc->fscache = NULL;
+}
+
+static void ceph_revalidate_work(struct work_struct *work)
+{
+	int issued;
+	u32 orig_gen;
+	struct ceph_inode_info *ci = container_of(work, struct ceph_inode_info,
+						  i_revalidate_work);
+	struct inode *inode = &ci->vfs_inode;
+
+	spin_lock(&ci->i_ceph_lock);
+	issued = __ceph_caps_issued(ci, NULL);
+	orig_gen = ci->i_rdcache_gen;
+	spin_unlock(&ci->i_ceph_lock);
+
+	if (!(issued & CEPH_CAP_FILE_CACHE)) {
+		dout("revalidate_work lost cache before validation %p\n",
+		     inode);
+		goto out;
+	}
+
+	if (!fscache_check_consistency(ci->fscache))
+		fscache_invalidate(ci->fscache);
+
+	spin_lock(&ci->i_ceph_lock);
+	/* Update the new valid generation (backwards sanity check too) */
+	if (orig_gen > ci->i_fscache_gen) {
+		ci->i_fscache_gen = orig_gen;
+	}
+	spin_unlock(&ci->i_ceph_lock);
+
+out:
+	iput(&ci->vfs_inode);
+}
+
+void ceph_queue_revalidate(struct inode *inode)
+{
+	struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb);
+	struct ceph_inode_info *ci = ceph_inode(inode);
+
+	if (fsc->revalidate_wq == NULL || ci->fscache == NULL)
+		return;
+
+	ihold(inode);
+
+	if (queue_work(ceph_sb_to_client(inode->i_sb)->revalidate_wq,
+		       &ci->i_revalidate_work)) {
+		dout("ceph_queue_revalidate %p\n", inode);
+	} else {
+		dout("ceph_queue_revalidate %p failed\n)", inode);
+		iput(inode);
+	}
+}
+
+void ceph_fscache_inode_init(struct ceph_inode_info *ci)
+{
+	ci->fscache = NULL;
+	/* The first load is verifed cookie open time */
+	ci->i_fscache_gen = 1;
+	INIT_WORK(&ci->i_revalidate_work, ceph_revalidate_work);
+}
diff --git a/fs/ceph/cache.h b/fs/ceph/cache.h
new file mode 100644
index 000000000000..ba949408a336
--- /dev/null
+++ b/fs/ceph/cache.h
@@ -0,0 +1,159 @@
+/*
+ * Ceph cache definitions.
+ *
+ *  Copyright (C) 2013 by Adfin Solutions, Inc. All Rights Reserved.
+ *  Written by Milosz Tanski (milosz@adfin.com)
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#ifndef _CEPH_CACHE_H
+#define _CEPH_CACHE_H
+
+#ifdef CONFIG_CEPH_FSCACHE
+
+extern struct fscache_netfs ceph_cache_netfs;
+
+int ceph_fscache_register(void);
+void ceph_fscache_unregister(void);
+
+int ceph_fscache_register_fs(struct ceph_fs_client* fsc);
+void ceph_fscache_unregister_fs(struct ceph_fs_client* fsc);
+
+void ceph_fscache_inode_init(struct ceph_inode_info *ci);
+void ceph_fscache_register_inode_cookie(struct ceph_fs_client* fsc,
+					struct ceph_inode_info* ci);
+void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info* ci);
+
+int ceph_readpage_from_fscache(struct inode *inode, struct page *page);
+int ceph_readpages_from_fscache(struct inode *inode,
+				struct address_space *mapping,
+				struct list_head *pages,
+				unsigned *nr_pages);
+void ceph_readpage_to_fscache(struct inode *inode, struct page *page);
+void ceph_invalidate_fscache_page(struct inode* inode, struct page *page);
+void ceph_queue_revalidate(struct inode *inode);
+
+static inline void ceph_fscache_invalidate(struct inode *inode)
+{
+	fscache_invalidate(ceph_inode(inode)->fscache);
+}
+
+static inline void ceph_fscache_uncache_page(struct inode *inode,
+					     struct page *page)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	return fscache_uncache_page(ci->fscache, page);
+}
+
+static inline int ceph_release_fscache_page(struct page *page, gfp_t gfp)
+{
+	struct inode* inode = page->mapping->host;
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	return fscache_maybe_release_page(ci->fscache, page, gfp);
+}
+
+static inline void ceph_fscache_readpages_cancel(struct inode *inode,
+						 struct list_head *pages)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	return fscache_readpages_cancel(ci->fscache, pages);
+}
+
+#else
+
+static inline int ceph_fscache_register(void)
+{
+	return 0;
+}
+
+static inline void ceph_fscache_unregister(void)
+{
+}
+
+static inline int ceph_fscache_register_fs(struct ceph_fs_client* fsc)
+{
+	return 0;
+}
+
+static inline void ceph_fscache_unregister_fs(struct ceph_fs_client* fsc)
+{
+}
+
+static inline void ceph_fscache_inode_init(struct ceph_inode_info *ci)
+{
+}
+
+static inline void ceph_fscache_register_inode_cookie(struct ceph_fs_client* parent_fsc,
+						      struct ceph_inode_info* ci)
+{
+}
+
+static inline void ceph_fscache_uncache_page(struct inode *inode,
+					     struct page *pages)
+{
+}
+
+static inline int ceph_readpage_from_fscache(struct inode* inode,
+					     struct page *page)
+{
+	return -ENOBUFS;
+}
+
+static inline int ceph_readpages_from_fscache(struct inode *inode,
+					      struct address_space *mapping,
+					      struct list_head *pages,
+					      unsigned *nr_pages)
+{
+	return -ENOBUFS;
+}
+
+static inline void ceph_readpage_to_fscache(struct inode *inode,
+					    struct page *page)
+{
+}
+
+static inline void ceph_fscache_invalidate(struct inode *inode)
+{
+}
+
+static inline void ceph_invalidate_fscache_page(struct inode *inode,
+						struct page *page)
+{
+}
+
+static inline void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info* ci)
+{
+}
+
+static inline int ceph_release_fscache_page(struct page *page, gfp_t gfp)
+{
+	return 1;
+}
+
+static inline void ceph_fscache_readpages_cancel(struct inode *inode,
+						 struct list_head *pages)
+{
+}
+
+static inline void ceph_queue_revalidate(struct inode *inode)
+{
+}
+
+#endif
+
+#endif
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 25442b40c25a..13976c33332e 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -10,6 +10,7 @@
 
 #include "super.h"
 #include "mds_client.h"
+#include "cache.h"
 #include <linux/ceph/decode.h>
 #include <linux/ceph/messenger.h>
 
@@ -479,8 +480,9 @@ static void __check_cap_issue(struct ceph_inode_info *ci, struct ceph_cap *cap,
 	 * i_rdcache_gen.
 	 */
 	if ((issued & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) &&
-	    (had & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) == 0)
+	    (had & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) == 0) {
 		ci->i_rdcache_gen++;
+	}
 
 	/*
 	 * if we are newly issued FILE_SHARED, mark dir not complete; we
@@ -2072,19 +2074,17 @@ static int try_get_cap_refs(struct ceph_inode_info *ci, int need, int want,
 	/* finish pending truncate */
 	while (ci->i_truncate_pending) {
 		spin_unlock(&ci->i_ceph_lock);
-		if (!(need & CEPH_CAP_FILE_WR))
-			mutex_lock(&inode->i_mutex);
 		__ceph_do_pending_vmtruncate(inode);
-		if (!(need & CEPH_CAP_FILE_WR))
-			mutex_unlock(&inode->i_mutex);
 		spin_lock(&ci->i_ceph_lock);
 	}
 
-	if (need & CEPH_CAP_FILE_WR) {
+	have = __ceph_caps_issued(ci, &implemented);
+
+	if (have & need & CEPH_CAP_FILE_WR) {
 		if (endoff >= 0 && endoff > (loff_t)ci->i_max_size) {
 			dout("get_cap_refs