Merge tag 'fscache-rewrite-20220111' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs

Pull fscache rewrite from David Howells:
 "This is a set of patches that rewrites the fscache driver and the
  cachefiles driver, significantly simplifying the code compared to
  what's upstream, removing the complex operation scheduling and object
  state machine in favour of something much smaller and simpler.

  The series is structured such that the first few patches disable
  fscache use by the network filesystems using it, remove the cachefiles
  driver entirely and as much of the fscache driver as can be got away
  with without causing build failures in the network filesystems.

  The patches after that recreate fscache and then cachefiles,
  attempting to add the pieces in a logical order. Finally, the
  filesystems are reenabled and then the very last patch changes the
  documentation.

  [!] Note: I have dropped the cifs patch for the moment, leaving local
      caching in cifs disabled. I've been having trouble getting that
      working. I think I have it done, but it needs more testing (there
      seem to be some test failures occurring with v5.16 also from
      xfstests), so I propose deferring that patch to the end of the
      merge window.

  WHY REWRITE?
  ============

  Fscache's operation scheduling API was intended to handle sequencing
  of cache operations, which were all required (where possible) to run
  asynchronously in parallel with the operations being done by the
  network filesystem, whilst allowing the cache to be brought online and
  offline and to interrupt service for invalidation.

  With the advent of the tmpfile capacity in the VFS, however, an
  opportunity arises to do invalidation much more simply, without having
  to wait for I/O that's actually in progress: Cachefiles can simply
  create a tmpfile, cut over the file pointer for the backing object
  attached to a cookie and abandon the in-progress I/O, dismissing it
  upon completion.

  Future work here would involve using Omar Sandoval's vfs_link() with
  AT_LINK_REPLACE[1] to allow an extant file to be displaced by a new
  hard link from a tmpfile as currently I have to unlink the old file
  first.

  These patches can also simplify the object state handling as I/O
  operations to the cache don't all have to be brought to a stop in
  order to invalidate a file. To that end, and with an eye on to writing
  a new backing cache model in the future, I've taken the opportunity to
  simplify the indexing structure.

  I've separated the index cookie concept from the file cookie concept
  by C type now. The former is now called a "volume cookie" (struct
  fscache_volume) and there is a container of file cookies. There are
  then just the two levels. All the index cookie levels are collapsed
  into a single volume cookie, and this has a single printable string as
  a key. For instance, an AFS volume would have a key of something like
  "afs,example.com,1000555", combining the filesystem name, cell name
  and volume ID. This is freeform, but must not have '/' chars in it.

  I've also eliminated all pointers back from fscache into the network
  filesystem. This required the duplication of a little bit of data in
  the cookie (cookie key, coherency data and file size), but it's not
  actually that much. This gets rid of problems with making sure we keep
  netfs data structures around so that the cache can access them.

  These patches mean that most of the code that was in the drivers
  before is simply gone and those drivers are now almost entirely new
  code. That being the case, there doesn't seem any particular reason to
  try and maintain bisectability across it. Further, there has to be a
  point in the middle where things are cut over as there's a single
  point everything has to go through (ie. /dev/cachefiles) and it can't
  be in use by two drivers at once.

  ISSUES YET OUTSTANDING
  ======================

  There are some issues still outstanding, unaddressed by this patchset,
  that will need fixing in future patchsets, but that don't stop this
  series from being usable:

  (1) The cachefiles driver needs to stop using the backing filesystem's
      metadata to store information about what parts of the cache are
      populated. This is not reliable with modern extent-based
      filesystems.

      Fixing this is deferred to a separate patchset as it involves
      negotiation with the network filesystem and the VM as to how much
      data to download to fulfil a read - which brings me on to (2)...

  (2) NFS (and CIFS with the dropped patch) do not take account of how
      the cache would like I/O to be structured to meet its granularity
      requirements. Previously, the cache used page granularity, which
      was fine as the network filesystems also dealt in page
      granularity, and the backing filesystem (ext4, xfs or whatever)
      did whatever it did out of sight. However, we now have folios to
      deal with and the cache will now have to store its own metadata to
      track its contents.

      The change I'm looking at making for cachefiles is to store
      content bitmaps in one or more xattrs and making a bit in the map
      correspond to something like a 256KiB block. However, the size of
      an xattr and the fact that they have to be read/updated in one go
      means that I'm looking at covering 1GiB of data per 512-byte map
      and storing each map in an xattr. Cachefiles has the potential to
      grow into a fully fledged filesystem of its very own if I'm not
      careful.

      However, I'm also looking at changing things even more radically
      and going to a different model of how the cache is arranged and
      managed - one that's more akin to the way, say, openafs does
      things - which brings me on to (3)...

  (3) The way cachefilesd does culling is very inefficient for large
      caches and it would be better to move it into the kernel if I can
      as cachefilesd has to keep asking the kernel if it can cull a
      file. Changing the way the backend works would allow this to be
      addressed.

  BITS THAT MAY BE CONTROVERSIAL
  ==============================

  There are some bits I've added that may be controversial:

  (1) I've provided a flag, S_KERNEL_FILE, that cachefiles uses to check
      if a files is already being used by some other kernel service
      (e.g. a duplicate cachefiles cache in the same directory) and
      reject it if it is. This isn't entirely necessary, but it helps
      prevent accidental data corruption.

      I don't want to use S_SWAPFILE as that has other effects, but
      quite possibly swapon() should set S_KERNEL_FILE too.

      Note that it doesn't prevent userspace from interfering, though
      perhaps it should. (I have made it prevent a marked directory from
      being rmdir-able).

  (2) Cachefiles wants to keep the backing file for a cookie open whilst
      we might need to write to it from network filesystem writeback.
      The problem is that the network filesystem unuses its cookie when
      its file is closed, and so we have nothing pinning the cachefiles
      file open and it will get closed automatically after a short time
      to avoid EMFILE/ENFILE problems.

      Reopening the cache file, however, is a problem if this is being
      done due to writeback triggered by exit(). Some filesystems will
      oops if we try to open a file in that context because they want to
      access current->fs or suchlike.

      To get around this, I added the following:

      (A) An inode flag, I_PINNING_FSCACHE_WB, to be set on a network
          filesystem inode to indicate that we have a usage count on the
          cookie caching that inode.

      (B) A flag in struct writeback_control, unpinned_fscache_wb, that
          is set when __writeback_single_inode() clears the last dirty
          page from i_pages - at which point it clears
          I_PINNING_FSCACHE_WB and sets this flag.

          This has to be done here so that clearing I_PINNING_FSCACHE_WB
          can be done atomically with the check of PAGECACHE_TAG_DIRTY
          that clears I_DIRTY_PAGES.

      (C) A function, fscache_set_page_dirty(), which if it is not set,
          sets I_PINNING_FSCACHE_WB and calls fscache_use_cookie() to
          pin the cache resources.

      (D) A function, fscache_unpin_writeback(), to be called by
          ->write_inode() to unuse the cookie.

      (E) A function, fscache_clear_inode_writeback(), to be called when
          the inode is evicted, before clear_inode() is called. This
          cleans up any lingering I_PINNING_FSCACHE_WB.

      The network filesystem can then use these tools to make sure that
      fscache_write_to_cache() can write locally modified data to the
      cache as well as to the server.

      For the future, I'm working on write helpers for netfs lib that
      should allow this facility to be removed by keeping track of the
      dirty regions separately - but that's incomplete at the moment and
      is also going to be affected by folios, one way or another, since
      it deals with pages"

Link: https://lore.kernel.org/all/510611.1641942444@warthog.procyon.org.uk/
Tested-by: Dominique Martinet <asmadeus@codewreck.org> # 9p
Tested-by: kafs-testing@auristor.com # afs
Tested-by: Jeff Layton <jlayton@kernel.org> # ceph
Tested-by: Dave Wysochanski <dwysocha@redhat.com> # nfs
Tested-by: Daire Byrne <daire@dneg.com> # nfs

* tag 'fscache-rewrite-20220111' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs: (67 commits)
  9p, afs, ceph, nfs: Use current_is_kswapd() rather than gfpflags_allow_blocking()
  fscache: Add a tracepoint for cookie use/unuse
  fscache: Rewrite documentation
  ceph: add fscache writeback support
  ceph: conversion to new fscache API
  nfs: Implement cache I/O by accessing the cache directly
  nfs: Convert to new fscache volume/cookie API
  9p: Copy local writes to the cache when writing to the server
  9p: Use fscache indexing rewrite and reenable caching
  afs: Skip truncation on the server of data we haven't written yet
  afs: Copy local writes to the cache when writing to the server
  afs: Convert afs to use the new fscache API
  fscache, cachefiles: Display stat of culling events
  fscache, cachefiles: Display stats of no-space events
  cachefiles: Allow cachefiles to actually function
  fscache, cachefiles: Store the volume coherency data
  cachefiles: Implement the I/O routines
  cachefiles: Implement cookie resize for truncate
  cachefiles: Implement begin and end I/O operation
  cachefiles: Implement backing file wrangling
  ...

12 files changed, 262 insertions, 642 deletions

diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile
index 22d11fdc6deb..5f6db37f461e 100644
--- a/fs/nfs/Makefile
+++ b/fs/nfs/Makefile
@@ -12,7 +12,7 @@ nfs-y 			:= client.o dir.o file.o getroot.o inode.o super.o \
 			   export.o sysfs.o fs_context.o
 nfs-$(CONFIG_ROOT_NFS)	+= nfsroot.o
 nfs-$(CONFIG_SYSCTL)	+= sysctl.o
-nfs-$(CONFIG_NFS_FSCACHE) += fscache.o fscache-index.o
+nfs-$(CONFIG_NFS_FSCACHE) += fscache.o
 
 obj-$(CONFIG_NFS_V2) += nfsv2.o
 nfsv2-y := nfs2super.o proc.o nfs2xdr.o
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 1e4dc1ab9312..8d8b85b5a641 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -183,8 +183,6 @@ struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init)
 	clp->cl_net = get_net(cl_init->net);
 
 	clp->cl_principal = "*";
-	nfs_fscache_get_client_cookie(clp);
-
 	return clp;
 
 error_cleanup:
@@ -238,8 +236,6 @@ static void pnfs_init_server(struct nfs_server *server)
  */
 void nfs_free_client(struct nfs_client *clp)
 {
-	nfs_fscache_release_client_cookie(clp);
-
 	/* -EIO all pending I/O */
 	if (!IS_ERR(clp->cl_rpcclient))
 		rpc_shutdown_client(clp->cl_rpcclient);
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 9cff8709c80a..eabfdab543c8 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -59,6 +59,7 @@
 #include "internal.h"
 #include "iostat.h"
 #include "pnfs.h"
+#include "fscache.h"
 
 #define NFSDBG_FACILITY		NFSDBG_VFS
 
@@ -959,6 +960,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter)
 	} else {
 		result = requested;
 	}
+	nfs_fscache_invalidate(inode, FSCACHE_INVAL_DIO_WRITE);
 out_release:
 	nfs_direct_req_release(dreq);
 out:
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 24e7dccce355..76d76acbc594 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -84,6 +84,7 @@ nfs_file_release(struct inode *inode, struct file *filp)
 
 	nfs_inc_stats(inode, NFSIOS_VFSRELEASE);
 	nfs_file_clear_open_context(filp);
+	nfs_fscache_release_file(inode, filp);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(nfs_file_release);
@@ -415,8 +416,7 @@ static void nfs_invalidate_page(struct page *page, unsigned int offset,
 		return;
 	/* Cancel any unstarted writes on this page */
 	nfs_wb_page_cancel(page_file_mapping(page)->host, page);
-
-	nfs_fscache_invalidate_page(page, page->mapping->host);
+	wait_on_page_fscache(page);
 }
 
 /*
@@ -475,12 +475,11 @@ static void nfs_check_dirty_writeback(struct page *page,
 static int nfs_launder_page(struct page *page)
 {
 	struct inode *inode = page_file_mapping(page)->host;
-	struct nfs_inode *nfsi = NFS_I(inode);
 
 	dfprintk(PAGECACHE, "NFS: launder_page(%ld, %llu)\n",
 		inode->i_ino, (long long)page_offset(page));
 
-	nfs_fscache_wait_on_page_write(nfsi, page);
+	wait_on_page_fscache(page);
 	return nfs_wb_page(inode, page);
 }
 
@@ -555,7 +554,11 @@ static vm_fault_t nfs_vm_page_mkwrite(struct vm_fault *vmf)
 	sb_start_pagefault(inode->i_sb);
 
 	/* make sure the cache has finished storing the page */
-	nfs_fscache_wait_on_page_write(NFS_I(inode), page);
+	if (PageFsCache(page) &&
+	    wait_on_page_fscache_killable(vmf->page) < 0) {
+		ret = VM_FAULT_RETRY;
+		goto out;
+	}
 
 	wait_on_bit_action(&NFS_I(inode)->flags, NFS_INO_INVALIDATING,
 			nfs_wait_bit_killable, TASK_KILLABLE);
diff --git a/fs/nfs/fscache-index.c b/fs/nfs/fscache-index.c
deleted file mode 100644
index 573b1da9342c..000000000000
--- a/fs/nfs/fscache-index.c
+++ /dev/null
@@ -1,140 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/* NFS FS-Cache index structure definition
- *
- * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
- * Written by David Howells (dhowells@redhat.com)
- */
-
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/mm.h>
-#include <linux/nfs_fs.h>
-#include <linux/nfs_fs_sb.h>
-#include <linux/in6.h>
-#include <linux/iversion.h>
-
-#include "internal.h"
-#include "fscache.h"
-
-#define NFSDBG_FACILITY		NFSDBG_FSCACHE
-
-/*
- * Define the NFS filesystem for FS-Cache.  Upon registration FS-Cache sticks
- * the cookie for the top-level index object for NFS into here.  The top-level
- * index can than have other cache objects inserted into it.
- */
-struct fscache_netfs nfs_fscache_netfs = {
-	.name		= "nfs",
-	.version	= 0,
-};
-
-/*
- * Register NFS for caching
- */
-int nfs_fscache_register(void)
-{
-	return fscache_register_netfs(&nfs_fscache_netfs);
-}
-
-/*
- * Unregister NFS for caching
- */
-void nfs_fscache_unregister(void)
-{
-	fscache_unregister_netfs(&nfs_fscache_netfs);
-}
-
-/*
- * Define the server object for FS-Cache.  This is used to describe a server
- * object to fscache_acquire_cookie().  It is keyed by the NFS protocol and
- * server address parameters.
- */
-const struct fscache_cookie_def nfs_fscache_server_index_def = {
-	.name		= "NFS.server",
-	.type 		= FSCACHE_COOKIE_TYPE_INDEX,
-};
-
-/*
- * Define the superblock object for FS-Cache.  This is used to describe a
- * superblock object to fscache_acquire_cookie().  It is keyed by all the NFS
- * parameters that might cause a separate superblock.
- */
-const struct fscache_cookie_def nfs_fscache_super_index_def = {
-	.name		= "NFS.super",
-	.type 		= FSCACHE_COOKIE_TYPE_INDEX,
-};
-
-/*
- * Consult the netfs about the state of an object
- * - This function can be absent if the index carries no state data
- * - The netfs data from the cookie being used as the target is
- *   presented, as is the auxiliary data
- */
-static
-enum fscache_checkaux nfs_fscache_inode_check_aux(void *cookie_netfs_data,
-						  const void *data,
-						  uint16_t datalen,
-						  loff_t object_size)
-{
-	struct nfs_fscache_inode_auxdata auxdata;
-	struct nfs_inode *nfsi = cookie_netfs_data;
-
-	if (datalen != sizeof(auxdata))
-		return FSCACHE_CHECKAUX_OBSOLETE;
-
-	memset(&auxdata, 0, sizeof(auxdata));
-	auxdata.mtime_sec  = nfsi->vfs_inode.i_mtime.tv_sec;
-	auxdata.mtime_nsec = nfsi->vfs_inode.i_mtime.tv_nsec;
-	auxdata.ctime_sec  = nfsi->vfs_inode.i_ctime.tv_sec;
-	auxdata.ctime_nsec = nfsi->vfs_inode.i_ctime.tv_nsec;
-
-	if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4)
-		auxdata.change_attr = inode_peek_iversion_raw(&nfsi->vfs_inode);
-
-	if (memcmp(data, &auxdata, datalen) != 0)
-		return FSCACHE_CHECKAUX_OBSOLETE;
-
-	return FSCACHE_CHECKAUX_OKAY;
-}
-
-/*
- * Get an extra reference on a read context.
- * - This function can be absent if the completion function doesn't require a
- *   context.
- * - The read context is passed back to NFS in the event that a data read on the
- *   cache fails with EIO - in which case the server must be contacted to
- *   retrieve the data, which requires the read context for security.
- */
-static void nfs_fh_get_context(void *cookie_netfs_data, void *context)
-{
-	get_nfs_open_context(context);
-}
-
-/*
- * Release an extra reference on a read context.
- * - This function can be absent if the completion function doesn't require a
- *   context.
- */
-static void nfs_fh_put_context(void *cookie_netfs_data, void *context)
-{
-	if (context)
-		put_nfs_open_context(context);
-}
-
-/*
- * Define the inode object for FS-Cache.  This is used to describe an inode
- * object to fscache_acquire_cookie().  It is keyed by the NFS file handle for
- * an inode.
- *
- * Coherency is managed by comparing the copies of i_size, i_mtime and i_ctime
- * held in the cache auxiliary data for the data storage object with those in
- * the inode struct in memory.
- */
-const struct fscache_cookie_def nfs_fscache_inode_object_def = {
-	.name		= "NFS.fh",
-	.type		= FSCACHE_COOKIE_TYPE_DATAFILE,
-	.check_aux	= nfs_fscache_inode_check_aux,
-	.get_context	= nfs_fh_get_context,
-	.put_context	= nfs_fh_put_context,
-};
diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c
index d743629e05e1..cfe901650ab0 100644
--- a/fs/nfs/fscache.c
+++ b/fs/nfs/fscache.c
@@ -22,24 +22,18 @@
 
 #define NFSDBG_FACILITY		NFSDBG_FSCACHE
 
-static struct rb_root nfs_fscache_keys = RB_ROOT;
-static DEFINE_SPINLOCK(nfs_fscache_keys_lock);
+#define NFS_MAX_KEY_LEN 1000
 
-/*
- * Layout of the key for an NFS server cache object.
- */
-struct nfs_server_key {
-	struct {
-		uint16_t	nfsversion;		/* NFS protocol version */
-		uint32_t	minorversion;		/* NFSv4 minor version */
-		uint16_t	family;			/* address family */
-		__be16		port;			/* IP port */
-	} hdr;
-	union {
-		struct in_addr	ipv4_addr;	/* IPv4 address */
-		struct in6_addr ipv6_addr;	/* IPv6 address */
-	};
-} __packed;
+static bool nfs_append_int(char *key, int *_len, unsigned long long x)
+{
+	if (*_len > NFS_MAX_KEY_LEN)
+		return false;
+	if (x == 0)
+		key[(*_len)++] = ',';
+	else
+		*_len += sprintf(key + *_len, ",%llx", x);
+	return true;
+}
 
 /*
  * Get the per-client index cookie for an NFS client if the appropriate mount
@@ -47,160 +41,108 @@ struct nfs_server_key {
  * - We always try and get an index cookie for the client, but get filehandle
  *   cookies on a per-superblock basis, depending on the mount flags
  */
-void nfs_fscache_get_client_cookie(struct nfs_client *clp)
+static bool nfs_fscache_get_client_key(struct nfs_client *clp,
+				       char *key, int *_len)
 {
 	const struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) &clp->cl_addr;
 	const struct sockaddr_in *sin = (struct sockaddr_in *) &clp->cl_addr;
-	struct nfs_server_key key;
-	uint16_t len = sizeof(key.hdr);
 
-	memset(&key, 0, sizeof(key));
-	key.hdr.nfsversion = clp->rpc_ops->version;
-	key.hdr.minorversion = clp->cl_minorversion;
-	key.hdr.family = clp->cl_addr.ss_family;
+	*_len += snprintf(key + *_len, NFS_MAX_KEY_LEN - *_len,
+			  ",%u.%u,%x",
+			  clp->rpc_ops->version,
+			  clp->cl_minorversion,
+			  clp->cl_addr.ss_family);
 
 	switch (clp->cl_addr.ss_family) {
 	case AF_INET:
-		key.hdr.port = sin->sin_port;
-		key.ipv4_addr = sin->sin_addr;
-		len += sizeof(key.ipv4_addr);
-		break;
+		if (!nfs_append_int(key, _len, sin->sin_port) ||
+		    !nfs_append_int(key, _len, sin->sin_addr.s_addr))
+			return false;
+		return true;
 
 	case AF_INET6:
-		key.hdr.port = sin6->sin6_port;
-		key.ipv6_addr = sin6->sin6_addr;
-		len += sizeof(key.ipv6_addr);
-		break;
+		if (!nfs_append_int(key, _len, sin6->sin6_port) ||
+		    !nfs_append_int(key, _len, sin6->sin6_addr.s6_addr32[0]) ||
+		    !nfs_append_int(key, _len, sin6->sin6_addr.s6_addr32[1]) ||
+		    !nfs_append_int(key, _len, sin6->sin6_addr.s6_addr32[2]) ||
+		    !nfs_append_int(key, _len, sin6->sin6_addr.s6_addr32[3]))
+			return false;
+		return true;
 
 	default:
 		printk(KERN_WARNING "NFS: Unknown network family '%d'\n",
 		       clp->cl_addr.ss_family);
-		clp->fscache = NULL;
-		return;
+		return false;
 	}
-
-	/* create a cache index for looking up filehandles */
-	clp->fscache = fscache_acquire_cookie(nfs_fscache_netfs.primary_index,
-					      &nfs_fscache_server_index_def,
-					      &key, len,
-					      NULL, 0,
-					      clp, 0, true);
-	dfprintk(FSCACHE, "NFS: get client cookie (0x%p/0x%p)\n",
-		 clp, clp->fscache);
-}
-
-/*
- * Dispose of a per-client cookie
- */
-void nfs_fscache_release_client_cookie(struct nfs_client *clp)
-{
-	dfprintk(FSCACHE, "NFS: releasing client cookie (0x%p/0x%p)\n",
-		 clp, clp->fscache);
-
-	fscache_relinquish_cookie(clp->fscache, NULL, false);
-	clp->fscache = NULL;
 }
 
 /*
- * Get the cache cookie for an NFS superblock.  We have to handle
- * uniquification here because the cache doesn't do it for us.
+ * Get the cache cookie for an NFS superblock.
  *
  * The default uniquifier is just an empty string, but it may be overridden
  * either by the 'fsc=xxx' option to mount, or by inheriting it from the parent
  * superblock across an automount point of some nature.
  */
-void nfs_fscache_get_super_cookie(struct super_block *sb, const char *uniq, int ulen)
+int nfs_fscache_get_super_cookie(struct super_block *sb, const char *uniq, int ulen)
 {
-	struct nfs_fscache_key *key, *xkey;
+	struct fscache_volume *vcookie;
 	struct nfs_server *nfss = NFS_SB(sb);
-	struct rb_node **p, *parent;
-	int diff;
+	unsigned int len = 3;
+	char *key;
 
-	nfss->fscache_key = NULL;
-	nfss->fscache = NULL;
-	if (!uniq) {
-		uniq = "";
-		ulen = 1;
+	if (uniq) {
+		nfss->fscache_uniq = kmemdup_nul(uniq, ulen, GFP_KERNEL);
+		if (!nfss->fscache_uniq)
+			return -ENOMEM;
 	}
 
-	key = kzalloc(sizeof(*key) + ulen, GFP_KERNEL);
+	key = kmalloc(NFS_MAX_KEY_LEN + 24, GFP_KERNEL);
 	if (!key)
-		return;
-
-	key->nfs_client = nfss->nfs_client;
-	key->key.super.s_flags = sb->s_flags & NFS_SB_MASK;
-	key->key.nfs_server.flags = nfss->flags;
-	key->key.nfs_server.rsize = nfss->rsize;
-	key->key.nfs_server.wsize = nfss->wsize;
-	key->key.nfs_server.acregmin = nfss->acregmin;
-	key->key.nfs_server.acregmax = nfss->acregmax;
-	key->key.nfs_server.acdirmin = nfss->acdirmin;
-	key->key.nfs_server.acdirmax = nfss->acdirmax;
-	key->key.nfs_server.fsid = nfss->fsid;
-	key->key.rpc_auth.au_flavor = nfss->client->cl_auth->au_flavor;
-
-	key->key.uniq_len = ulen;
-	memcpy(key->key.uniquifier, uniq, ulen);
-
-	spin_lock(&nfs_fscache_keys_lock);
-	p = &nfs_fscache_keys.rb_node;
-	parent = NULL;
-	while (*p) {
-		parent = *p;
-		xkey = rb_entry(parent, struct nfs_fscache_key, node);
-
-		if (key->nfs_client < xkey->nfs_client)
-			goto go_left;
-		if (key->nfs_client > xkey->nfs_client)
-			goto go_right;
-
-		diff = memcmp(&key->key, &xkey->key, sizeof(key->key));
-		if (diff < 0)
-			goto go_left;
-		if (diff > 0)
-			goto go_right;
-
-		if (key->key.uniq_len == 0)
-			goto non_unique;
-		diff = memcmp(key->key.uniquifier,
-			      xkey->key.uniquifier,
-			      key->key.uniq_len);
-		if (diff < 0)
-			goto go_left;
-		if (diff > 0)
-			goto go_right;
-		goto non_unique;
-
-	go_left:
-		p = &(*p)->rb_left;
-		continue;
-	go_right:
-		p = &(*p)->rb_right;
+		return -ENOMEM;
+
+	memcpy(key, "nfs", 3);
+	if (!nfs_fscache_get_client_key(nfss->nfs_client, key, &len) ||
+	    !nfs_append_int(key, &len, nfss->fsid.major) ||
+	    !nfs_append_int(key, &len, nfss->fsid.minor) ||
+	    !nfs_append_int(key, &len, sb->s_flags & NFS_SB_MASK) ||
+	    !nfs_append_int(key, &len, nfss->flags) ||
+	    !nfs_append_int(key, &len, nfss->rsize) ||
+	    !nfs_append_int(key, &len, nfss->wsize) ||
+	    !nfs_append_int(key, &len, nfss->acregmin) ||
+	    !nfs_append_int(key, &len, nfss->acregmax) ||
+	    !nfs_append_int(key, &len, nfss->acdirmin) ||
+	    !nfs_append_int(key, &len, nfss->acdirmax) ||
+	    !nfs_append_int(key, &len, nfss->client->cl_auth->au_flavor))
+		goto out;
+
+	if (ulen > 0) {
+		if (ulen > NFS_MAX_KEY_LEN - len)
+			goto out;
+		key[len++] = ',';
+		memcpy(key + len, uniq, ulen);
+		len += ulen;
 	}
-
-	rb_link_node(&key->node, parent, p);
-	rb_insert_color(&key->node, &nfs_fscache_keys);
-	spin_unlock(&nfs_fscache_keys_lock);
-	nfss->fscache_key = key;
+	key[len] = 0;
 
 	/* create a cache index for looking up filehandles */
-	nfss->fscache = fscache_acquire_cookie(nfss->nfs_client->fscache,
-					       &nfs_fscache_super_index_def,
-					       &key->key,
-					       sizeof(key->key) + ulen,
-					       NULL, 0,
-					       nfss, 0, true);
+	vcookie = fscache_acquire_volume(key,
+					 NULL, /* preferred_cache */
+					 NULL, 0 /* coherency_data */);
 	dfprintk(FSCACHE, "NFS: get superblock cookie (0x%p/0x%p)\n",
-		 nfss, nfss->fscache);
-	return;
+		 nfss, vcookie);
+	if (IS_ERR(vcookie)) {
+		if (vcookie != ERR_PTR(-EBUSY)) {
+			kfree(key);
+			return PTR_ERR(vcookie);
+		}
+		pr_err("NFS: Cache volume key already in use (%s)\n", key);
+		vcookie = NULL;
+	}
+	nfss->fscache = vcookie;
 
-non_unique:
-	spin_unlock(&nfs_fscache_keys_lock);
+out:
 	kfree(key);
-	nfss->fscache_key = NULL;
-	nfss->fscache = NULL;
-	printk(KERN_WARNING "NFS:"
-	       " Cache request denied due to non-unique superblock keys\n");
+	return 0;
 }
 
 /*
@@ -213,29 +155,9 @@ void nfs_fscache_release_super_cookie(struct super_block *sb)
 	dfprintk(FSCACHE, "NFS: releasing superblock cookie (0x%p/0x%p)\n",
 		 nfss, nfss->fscache);
 
-	fscache_relinquish_cookie(nfss->fscache, NULL, false);
+	fscache_relinquish_volume(nfss->fscache, NULL, false);
 	nfss->fscache = NULL;
-
-	if (nfss->fscache_key) {
-		spin_lock(&nfs_fscache_keys_lock);
-		rb_erase(&nfss->fscache_key->node, &nfs_fscache_keys);
-		spin_unlock(&nfs_fscache_keys_lock);
-		kfree(nfss->fscache_key);
-		nfss->fscache_key = NULL;
-	}
-}
-
-static void nfs_fscache_update_auxdata(struct nfs_fscache_inode_auxdata *auxdata,
-				  struct nfs_inode *nfsi)
-{
-	memset(auxdata, 0, sizeof(*auxdata));
-	auxdata->mtime_sec  = nfsi->vfs_inode.i_mtime.tv_sec;
-	auxdata->mtime_nsec = nfsi->vfs_inode.i_mtime.tv_nsec;
-	auxdata->ctime_sec  = nfsi->vfs_inode.i_ctime.tv_sec;
-	auxdata->ctime_nsec = nfsi->vfs_inode.i_ctime.tv_nsec;
-
-	if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4)
-		auxdata->change_attr = inode_peek_iversion_raw(&nfsi->vfs_inode);
+	kfree(nfss->fscache_uniq);
 }
 
 /*
@@ -254,10 +176,12 @@ void nfs_fscache_init_inode(struct inode *inode)
 	nfs_fscache_update_auxdata(&auxdata, nfsi);
 
 	nfsi->fscache = fscache_acquire_cookie(NFS_SB(inode->i_sb)->fscache,
-					       &nfs_fscache_inode_object_def,
-					       nfsi->fh.data, nfsi->fh.size,
-					       &auxdata, sizeof(auxdata),
-					       nfsi, nfsi->vfs_inode.i_size, false);
+					       0,
+					       nfsi->fh.data, /* index_key */
+					       nfsi->fh.size,
+					       &auxdata,      /* aux_data */
+					       sizeof(auxdata),
+					       i_size_read(&nfsi->vfs_inode));
 }
 
 /*
@@ -265,24 +189,15 @@ void nfs_fscache_init_inode(struct inode *inode)
  */
 void nfs_fscache_clear_inode(struct inode *inode)
 {
-	struct nfs_fscache_inode_auxdata auxdata;
 	struct nfs_inode *nfsi = NFS_I(inode);
 	struct fscache_cookie *cookie = nfs_i_fscache(inode);
 
 	dfprintk(FSCACHE, "NFS: clear cookie (0x%p/0x%p)\n", nfsi, cookie);
 
-	nfs_fscache_update_auxdata(&auxdata, nfsi);
-	fscache_relinquish_cookie(cookie, &auxdata, false);
+	fscache_relinquish_cookie(cookie, false);
 	nfsi->fscache = NULL;
 }
 
-static bool nfs_fscache_can_enable(void *data)
-{
-	struct inode *inode = data;
-
-	return !inode_is_open_for_write(inode);
-}
-
 /*
  * Enable or disable caching for a file that is being opened as appropriate.
  * The cookie is allocated when the inode is initialised, but is not enabled at
@@ -307,100 +222,104 @@ void nfs_fscache_open_file(struct inode *inode, struct file *filp)
 	struct nfs_fscache_inode_auxdata auxdata;
 	struct nfs_inode *nfsi = NFS_I(inode);
 	struct fscache_cookie *cookie = nfs_i_fscache(inode);
+	bool open_for_write = inode_is_open_for_write(inode);
 
 	if (!fscache_cookie_valid(cookie))
 		return;
 
-	nfs_fscache_update_auxdata(&auxdata, nfsi);
-
-	if (inode_is_open_for_write(inode)) {
+	fscache_use_cookie(cookie, open_for_write);
+	if (open_for_write) {
 		dfprintk(FSCACHE, "NFS: nfsi 0x%p disabling cache\n", nfsi);
-		clear_bit(NFS_INO_FSCACHE, &nfsi->flags);
-		fscache_disable_cookie(cookie, &auxdata, true);
-		fscache_uncache_all_inode_pages(cookie, inode);
-	} else {
-		dfprintk(FSCACHE, "NFS: nfsi 0x%p enabling cache\n", nfsi);
-		fscache_enable_cookie(cookie, &auxdata, nfsi->vfs_inode.i_size,
-				      nfs_fscache_can_enable, inode);
-		if (fscache_cookie_enabled(cookie))
-			set_bit(NFS_INO_FSCACHE, &NFS_I(inode)->flags);
+		nfs_fscache_update_auxdata(&auxdata, nfsi);
+		fscache_invalidate(cookie, &auxdata, i_size_read(inode),
+				   FSCACHE_INVAL_DIO_WRITE);
 	}
 }
 EXPORT_SYMBOL_GPL(nfs_fscache_open_file);
 
-/*
- * Release the caching state associated with a page, if the page isn't busy
- * interacting with the cache.
- * - Returns true (can release page) or false (page busy).
- */
-int nfs_fscache_release_page(struct page *page, gfp_t gfp)
+void nfs_fscache_release_file(struct inode *inode, struct file *filp)
 {
-	if (PageFsCache(page)) {
-		struct fscache_cookie *cookie = nfs_i_fscache(page->mapping->host);
-
-		BUG_ON(!cookie);
-		dfprintk(FSCACHE, "NFS: fscache releasepage (0x%p/0x%p/0x%p)\n",
-			 cookie, page, NFS_I(page->mapping->host));
-
-		if (!fscache_maybe_release_page(cookie, page, gfp))
-			return 0;
+	struct nfs_fscache_inode_auxdata auxdata;
+	struct nfs_inode *nfsi = NFS_I(inode);
+	struct fscache_cookie *cookie = nfs_i_fscache(inode);
 
-		nfs_inc_fscache_stats(page->mapping->host,
-				      NFSIOS_FSCACHE_PAGES_UNCACHED);
+	if (fscache_cookie_valid(cookie)) {
+		nfs_fscache_update_auxdata(&auxdata, nfsi);
+		fscache_unuse_cookie(cookie, &auxdata, NULL);
 	}
+}
 
-	return 1;
+static inline void fscache_end_operation(struct netfs_cache_resources *cres)
+{
+	const struct netfs_cache_ops *ops = fscache_operation_valid(cres);
+
+	if (ops)
+		ops->end_operation(cres);
 }
 
 /*
- * Release the caching state associated with a page if undergoing complete page
- * invalidation.
+ * Fallback page reading interface.
  */
-void __nfs_fscache_invalidate_page(struct page *page, struct inode *inode)
+static int fscache_fallback_read_page(struct inode *inode, struct page *page)
 {
+	struct netfs_cache_resources cres;
 	struct fscache_cookie *cookie = nfs_i_fscache(inode);
+	struct iov_iter iter;
+	struct bio_vec bvec[1];
+	int ret;
 
-	BUG_ON(!cookie);
-
-	dfprintk(FSCACHE, "NFS: fscache invalidatepage (0x%p/0x%p/0x%p)\n",
-		 cookie, page, NFS_I(inode));
+	memset(&cres, 0, sizeof(cres));
+	bvec[0].bv_page		= page;
+	bvec[0].bv_offset	= 0;
+	bvec[0].bv_len		= PAGE_SIZE;
+	iov_iter_bvec(&iter, READ, bvec, ARRAY_SIZE(bvec), PAGE_SIZE);
 
-	fscache_wait_on_page_write(cookie, page);
+	ret = fscache_begin_read_operation(&cres, cookie);
+	if (ret < 0)
+		return ret;
 
-	BUG_ON(!PageLocked(page));
-	fscache_uncache_page(cookie, page);
-	nfs_inc_fscache_stats(page->mapping->host,
-			      NFSIOS_FSCACHE_PAGES_UNCACHED);
+	ret = fscache_read(&cres, page_offset(page), &iter, NETFS_READ_HOLE_FAIL,
+			   NULL, NULL);
+	fscache_end_operation(&cres);
+	return ret;
 }
 
 /*
- * Handle completion of a page being read from the cache.
- * - Called in process (keventd) context.
+ * Fallback page writing interface.
  */
-static void nfs_readpage_from_fscache_complete(struct page *page,
-					       void *context,
-					       int error)
+static int fscache_fallback_write_page(struct inode *inode, struct page *page,
+				       bool no_space_allocated_yet)
 {
-	dfprintk(FSCACHE,
-		 "NFS: readpage_from_fscache_complete (0x%p/0x%p/%d)\n",
-		 page, context, error);
-
-	/*
-	 * If the read completes with an error, mark the page with PG_checked,
-	 * unlock the page, and let the VM reissue the readpage.
-	 */
-	if (!error)
-		SetPageUptodate(page);
-	else
-		SetPageChecked(page);
-	unlock_page(page);
+	struct netfs_cache_resources cres;
+	struct fscache_cookie *cookie = nfs_i_fscache(inode);
+	struct iov_iter iter;
+	struct bio_vec bvec[1];
+	loff_t start = page_offset(page);
+	size_t len = PAGE_SIZE;
+	int ret;
+
+	memset(&cres, 0, sizeof(cres));
+	bvec[0].bv_page		= page;
+	bvec[0].bv_offset	= 0;
+	bvec[0].bv_len		= PAGE_SIZE;
+	iov_iter_bvec(&iter, WRITE, bvec, ARRAY_SIZE(bvec), PAGE_SIZE);
+
+	ret = fscache_begin_write_operation(&cres, cookie);
+	if (ret < 0)
+		return ret;
+
+	ret = cres.ops->prepare_write(&cres, &start, &len, i_size_read(inode),
+				      no_space_allocated_yet);
+	if (ret == 0)
+		ret = fscache_write(&cres, page_offset(page), &iter, NULL, NULL);
+	fscache_end_operation(&cres);
+	return ret;
 }
 
 /*
  * Retrieve a page from fscache
  */
-int __nfs_readpage_from_fscache(struct nfs_open_context *ctx,
-				struct inode *inode, struct page *page)
+int __nfs_readpage_from_fscache(struct inode *inode, struct page *page)
 {
 	int ret;
 
@@ -409,112 +328,49 @@ int __nfs_readpage_from_fscache(struct nfs_open_context *ctx,
 		 nfs_i_fscache(inode), page, page->index, page->flags, inode);
 
 	if (PageChecked(page)) {
+		dfprintk(FSCACHE, "NFS:    readpage_from_fscache: PageChecked\n");
 		ClearPageChecked(page);
 		return 1;
 	}
 
-	ret = fscache_read_or_alloc_page(nfs_i_fscache(inode),
-					 page,
-					 nfs_readpage_from_fscache_complete,
-					 ctx,
-					 GFP_KERNEL);
-
-	switch (ret) {
-	case 0: /* read BIO submitted (page in fscache) */
-		dfprintk(FSCACHE,
-			 "NFS:    readpage_from_fscache: BIO submitted\n");
-		nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_OK);
-		return ret;
-
-	case -ENOBUFS: /* inode not in cache */
-	case -ENODATA: /* page not in cache */
+	ret = fscache_fallback_read_page(inode, page);
+	if (ret < 0) {
 		nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL);
 		dfprintk(FSCACHE,
-			 "NFS:    readpage_from_fscache %d\n", ret);
-		return 1;
-
-	default:
-		dfprintk(FSCACHE, "NFS:    readpage_from_fscache %d\n", ret);
-		nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL);
-	}
-	return ret;
-}
-
-/*
- * Retrieve a set of pages from fscache
- */
-int __nfs_readpages_from_fscache(struct nfs_open_context *ctx,
-				 struct inode *inode,
-				 struct address_space *mapping,
-				 struct list_head *pages,
-				 unsigned *nr_pages)
-{
-	unsigned npages = *nr_pages;
-	int ret;
-
-	dfprintk(FSCACHE, "NFS: nfs_getpages_from_fscache (0x%p/%u/0x%p)\n",
-		 nfs_i_fscache(inode), npages, inode);
-
-	ret = fscache_read_or_alloc_pages(nfs_i_fscache(inode),
-					  mapping, pages, nr_pages,
-					  nfs_readpage_from_fscache_complete,
-					  ctx,
-					  mapping_gfp_mask(mapping));
-	if (*nr_pages < npages)
-		nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_OK,
-				      npages);
-	if (*nr_pages > 0)
-		nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL,
-				      *nr_pages);
-
-	switch (ret) {
-	case 0: /* read submitted to the cache for all pages */
-		BUG_ON(!list_empty(pages));
-		BUG_ON(*nr_pages != 0);
-		dfprintk(FSCACHE,
-			 "NFS: nfs_getpages_from_fscache: submitted\n");
-
+			 "NFS:    readpage_from_fscache failed %d\n", ret);
+		SetPageChecked(page);
 		return ret;
-
-	case -ENOBUFS: /* some pages aren't cached and can't be */
-	case -ENODATA: /* some pages aren't cached */
-		dfprintk(FSCACHE,
-			 "NFS: nfs_getpages_from_fscache: no page: %d\n", ret);
-		return 1;
-
-	default:
-		dfprintk(FSCACHE,
-			 "NFS: nfs_getpages_from_fscache: ret  %d\n", ret);
 	}
 
-	return ret;
+	/* Read completed synchronously */
+	dfprintk(FSCACHE, "NFS:    readpage_from_fscache: read successful\n");
+	nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_OK);
+	SetPageUptodate(page);
+	return 0;
 }
 
 /*
- * Store a newly fetched page in fscache
- * - PG_fscache must be set on the page
+ * Store a newly fetched page in fscache.  We can be certain there's no page
+ * stored in the cache as yet otherwise we would've read it from there.
  */
-void __nfs_readpage_to_fscache(struct inode *inode, struct page *page, int sync)
+void __nfs_readpage_to_fscache(struct inode *inode, struct page *page)
 {
 	int ret;
 
 	dfprintk(FSCACHE,
-		 "NFS: readpage_to_fscache(fsc:%p/p:%p(i:%lx f:%lx)/%d)\n",
-		 nfs_i_fscache(inode), page, page->index, page->flags, sync);
+		 "NFS: readpage_to_fscache(fsc:%p/p:%p(i:%lx f:%lx))\n",
+		 nfs_i_fscache(inode), page, page->index, page->flags);
+
+	ret = fscache_fallback_write_page(inode, page, true);
 
-	ret = fscache_write_page(nfs_i_fscache(inode), page,
-				 inode->i_size, GFP_KERNEL);
 	dfprintk(FSCACHE,
 		 "NFS:     readpage_to_fscache: p:%p(i:%lu f:%lx) ret %d\n",
 		 page, page->index, page->flags, ret);
 
 	if (ret != 0) {
-		fscache_uncache_page(nfs_i_fscache(inode), page);
-		nfs_inc_fscache_stats(inode,
-				      NFSIOS_FSCACHE_PAGES_WRITTEN_FAIL);
+		nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_WRITTEN_FAIL);
 		nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_UNCACHED);
 	} else {
-		nfs_inc_fscache_stats(inode,
-				      NFSIOS_FSCACHE_PAGES_WRITTEN_OK);
+		nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_WRITTEN_OK);
 	}
 }
diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h
index 6754c8607230..25a5c0f82392 100644
--- a/fs/nfs/fscache.h
+++ b/fs/nfs/fscache.h
@@ -8,51 +8,16 @@
 #ifndef _NFS_FSCACHE_H
 #define _NFS_FSCACHE_H
 
+#include <linux/swap.h>
 #include <linux/nfs_fs.h>
 #include <linux/nfs_mount.h>
 #include <linux/nfs4_mount.h>
 #include <linux/fscache.h>
+#include <linux/iversion.h>
 
 #ifdef CONFIG_NFS_FSCACHE
 
 /*
- * set of NFS FS-Cache objects that form a superblock key
- */
-struct nfs_fscache_key {
-	struct rb_node		node;
-	struct nfs_client	*nfs_client;	/* the server */
-
-	/* the elements of the unique key - as used by nfs_compare_super() and
-	 * nfs_compare_mount_options() to distinguish superblocks */
-	struct {
-		struct {
-			unsigned long	s_flags;	/* various flags
-							 * (& NFS_MS_MASK) */
-		} super;
-
-		struct {
-			struct nfs_fsid fsid;
-			int		flags;
-			unsigned int	rsize;		/* read size */
-			unsigned int	wsize;		/* write size */
-			unsigned int	acregmin;	/* attr cache timeouts */
-			unsigned int	acregmax;
-			unsigned int	acdirmin;
-			unsigned int	acdirmax;
-		} nfs_server;
-
-		struct {
-			rpc_authflavor_t au_flavor;
-		} rpc_auth;
-
-		/* uniquifier - can be used if nfs_server.flags includes
-		 * NFS_MOUNT_UNSHARED  */
-		u8 uniq_len;
-		char uniquifier[0];
-	} key;
-};
-
-/*
  * Definition of the auxiliary data attached to NFS inode storage objects
  * within the cache.
  *
@@ -70,84 +35,42 @@ struct nfs_fscache_inode_auxdata {
 };
 
 /*
- * fscache-index.c
- */
-extern struct fscache_netfs nfs_fscache_netfs;
-extern const struct fscache_cookie_def nfs_fscache_server_index_def;
-extern const struct fscache_cookie_def nfs_fscache_super_index_def;
-extern const struct fscache_cookie_def nfs_fscache_inode_object_def;
-
-extern int nfs_fscache_register(void);
-extern void nfs_fscache_unregister(void);
-
-/*
  * fscache.c
  */
-extern void nfs_fscache_get_client_cookie(struct nfs_client *);
-extern void nfs_fscache_release_client_cookie(struct nfs_client *);
-
-extern void nfs_fscache_get_super_cookie(struct super_block *, const char *, int);
+extern int nfs_fscache_get_super_cookie(struct super_block *, const char *, int);
 extern void nfs_fscache_release_super_cookie(struct super_block *);
 
 extern void nfs_fscache_init_inode(struct inode *);
 extern void nfs_fscache_clear_inode(struct inode *);
 extern void nfs_fscache_open_file(struct inode *, struct file *);
+extern void nfs_fscache_release_file(struct inode *, struct file *);
 
-extern void __nfs_fscache_invalidate_page(struct page *, struct inode *);
-extern int nfs_fscache_release_page(struct page *, gfp_t);
+extern int __nfs_readpage_from_fscache(struct inode *, struct page *);
+extern void __nfs_read_completion_to_fscache(struct nfs_pgio_header *hdr,
+					     unsigned long bytes);
+extern void __nfs_readpage_to_fscache(struct inode *, struct page *);
 
-extern int __nfs_readpage_from_fscache(struct nfs_open_context *,
-				       struct inode *, struct page *);
-extern int __nfs_readpages_from_fscache(struct nfs_open_context *,
-					struct inode *, struct address_space *,
-					struct list_head *, unsigned *);
-extern void __nfs_readpage_to_fscache(struct inode *, struct page *, int);
-
-/*
- * wait for a page to complete writing to the cache
- */
-static inline void nfs_fscache_wait_on_page_write(struct nfs_inode *nfsi,
-						  struct page *page)
-{
-	if (PageFsCache(page))
-		fscache_wait_on_page_write(nfsi->fscache, page);
-}
-
-/*
- * release the caching state associated with a page if undergoing complete page
- * invalidation
- */
-static inline void nfs_fscache_invalidate_page(struct page *page,
-					       struct inode *inode)
+static inline int nfs_fscache_release_page(struct page *page, gfp_t gfp)
 {
-	if (PageFsCache(page))
-		__nfs_fscache_invalidate_page(page, inode);
+	if (PageFsCache(page)) {
+		if (current_is_kswapd() || !(gfp & __GFP_FS))
+			return false;
+		wait_on_page_fscache(page);
+		fscache_note_page_release(nfs_i_fscache(page->mapping->host));
+		nfs_inc_fscache_stats(page->mapping->host,
+				      NFSIOS_FSCACHE_PAGES_UNCACHED);
+	}
+	return true;
 }
 
 /*
  * Retrieve a page from an inode data storage object.
  */
-static inline int nfs_readpage_from_fscache(struct nfs_open_context *ctx,
-					    struct inode *inode,
+static inline int nfs_readpage_from_fscache(struct inode *inode,
 					    struct page *page)
 {
 	if (NFS_I(inode)->fscache)
-		return __nfs_readpage_from_fscache(ctx, inode, page);
-	return -ENOBUFS;
-}
-
-/*
- * Retrieve a set of pages from an inode data storage object.
- */
-static inline int nfs_readpages_from_fscache(struct nfs_open_context *ctx,
-					     struct inode *inode,
-					     struct address_space *mapping,
-					     struct list_head *pages,
-					     unsigned *nr_pages)
-{
-	if (NFS_I(inode)->fscache)
-		return __nfs_readpages_from_fscache(ctx, inode, mapping, pages,
-						    nr_pages);
+		return __nfs_readpage_from_fscache(inode, page);
 	return -ENOBUFS;
 }
 
@@ -156,27 +79,38 @@ static inline int nfs_readpages_from_fscache(struct nfs_open_context *ctx,
  * in the cache.
  */
 static inline void nfs_readpage_to_fscache(struct inode *inode,
-					   struct page *page,
-					   int sync)
+					   struct page *page)
 {
-	if (PageFsCache(page))
-		__nfs_readpage_to_fscache(inode, page, sync);
+	if (NFS_I(inode)->fscache)
+		__nfs_readpage_to_fscache(inode, page);
 }
 
-/*
- * Invalidate the contents of fscache for this inode.  This will not sleep.
- */
-static inline void nfs_fscache_invalidate(struct inode *inode)
+static inline void nfs_fscache_update_auxdata(struct nfs_fscache_inode_auxdata *auxdata,
+					      struct nfs_inode *nfsi)
 {
-	fscache_invalidate(NFS_I(inode)->fscache);
+	memset(auxdata, 0, sizeof(*auxdata));
+	auxdata->mtime_sec  = nfsi->vfs_inode.i_mtime.tv_sec;
+	auxdata->mtime_nsec = nfsi->vfs_inode.i_mtime.tv_nsec;
+	auxdata->ctime_sec  = nfsi->vfs_inode.i_ctime.tv_sec;
+	auxdata->ctime_nsec = nfsi->vfs_inode.i_ctime.tv_nsec;
+
+	if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4)
+		auxdata->change_attr = inode_peek_iversion_raw(&nfsi->vfs_inode);
 }
 
 /*
- * Wait for an object to finish being invalidated.
+ * Invalidate the contents of fscache for this inode.  This will not sleep.
  */
-static inline void nfs_fscache_wait_on_invalidate(struct inode *inode)
+static inline void nfs_fscache_invalidate(struct inode *inode, int flags)
 {
-	fscache_wait_on_invalidate(NFS_I(inode)->fscache);
+	struct nfs_fscache_inode_auxdata auxdata;
+	struct nfs_inode *nfsi = NFS_I(inode);
+
+	if (nfsi->fscache) {
+		nfs_fscache_update_auxdata(&auxdata, nfsi);
+		fscache_invalidate(nfsi->fscache, &auxdata,
+				   i_size_read(&nfsi->vfs_inode), flags);
+	}
 }
 
 /*
@@ -190,48 +124,28 @@ static inline const char *nfs_server_fscache_state(struct nfs_server *server)
 }
 
 #else /* CONFIG_NFS_FSCACHE */
-static inline int nfs_fscache_register(void) { return 0; }
-static inline void nfs_fscache_unregister(void) {}
-
-static inline void nfs_fscache_get_client_cookie(struct nfs_client *clp) {}
-static inline void nfs_fscache_release_client_cookie(struct nfs_client *clp) {}
-
 static inline void nfs_fscache_release_super_cookie(struct super_block *sb) {}
 
 static inline void nfs_fscache_init_inode(struct inode *inode) {}
 static inline void nfs_fscache_clear_inode(struct inode *inode) {}
 static inline void nfs_fscache_open_file(struct inode *inode,
 					 struct file *filp) {}
+static inline void nfs_fscache_release_file(struct inode *inode, struct file *file) {}
 
 static inline int nfs_fscache_release_page(struct page *page, gfp_t gfp)
 {
 	return 1; /* True: may release page */
 }
-static inline void nfs_fscache_invalidate_page(struct page *page,
-					       struct inode *inode) {}
-static inline void nfs_fscache_wait_on_page_write(struct nfs_inode *nfsi,
-						  struct page *page) {}
-
-static inline int nfs_readpage_from_fscache(struct nfs_open_context *ctx,
-					    struct inode *inode,
+static inline int nfs_readpage_from_fscache(struct inode *inode,
 					    struct page *page)
 {
 	return -ENOBUFS;
 }
-static inline int nfs_readpages_from_fscache(struct nfs_open_context *ctx,
-					     struct inode *inode,
-					     struct address_space *mapping,
-					     struct list_head *pages,
-					     unsigned *nr_pages)
-{
-	return -ENOBUFS;
-}
 static inline void nfs_readpage_to_fscache(struct inode *inode,
-					   struct page *page, int sync) {}
+					   struct page *page) {}
 
 
-static inline void nfs_fscache_invalidate(struct inode *inode) {}
-static inline void nfs_fscache_wait_on_invalidate(struct inode *inode) {}
+static inline void nfs_fscache_invalidate(struct inode *inode, int flags) {}
 
 static inline const char *nfs_server_fscache_state(struct nfs_server *server)
 {
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index fda530d5e764..a918c3a834b6 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -209,7 +209,7 @@ void nfs_set_cache_invalid(struct inode *inode, unsigned long flags)
 	if (!nfs_has_xattr_cache(nfsi))
 		flags &= ~NFS_INO_INVALID_XATTR;
 	if (flags & NFS_INO_INVALID_DATA)
-		nfs_fscache_invalidate(inode);
+		nfs_fscache_invalidate(inode, 0);
 	flags &= ~(NFS_INO_REVAL_PAGECACHE | NFS_INO_REVAL_FORCED);
 
 	nfsi->cache_validity |= flags;
@@ -1289,6 +1289,7 @@ static int nfs_invalidate_mapping(struct inode *inode, struct address_space *map
 {
 	int ret;
 
+	nfs_fscache_invalidate(inode, 0);
 	if (mapping->nrpages != 0) {
 		if (S_ISREG(inode->i_mode)) {
 			ret = nfs_sync_mapping(mapping);
@@ -1300,7 +1301,6 @@ static int nfs_invalidate_mapping(struct inode *inode, struct address_space *map
 			return ret;
 	}
 	nfs_inc_stats(inode, NFSIOS_DATAINVALIDATE);
-	nfs_fscache_wait_on_invalidate(inode);
 
 	dfprintk(PAGECACHE, "NFS: (%s/%Lu) data cache invalidated\n",
 			inode->i_sb->s_id,
@@ -2374,10 +2374,6 @@ static int __init init_nfs_fs(void)
 	if (err < 0)
 		goto out9;
 
-	err = nfs_fscache_register();
-	if (err < 0)
-		goto out8;
-
 	err = nfsiod_start();
 	if (err)
 		goto out7;
@@ -2429,8 +2425,6 @@ out5:
 out6:
 	nfsiod_stop();
 out7:
-	nfs_fscache_unregister();
-out8:
 	unregister_pernet_subsys(&nfs_net_ops);
 out9:
 	nfs_sysfs_exit();
@@ -2445,7 +2439,6 @@ static void __exit exit_nfs_fs(void)
 	nfs_destroy_readpagecache();
 	nfs_destroy_inodecache();
 	nfs_destroy_nfspagecache();
-	nfs_fscache_unregister();
 	unregister_pernet_subsys(&nfs_net_ops);
 	rpc_proc_unregister(&init_net, "nfs");
 	unregister_nfs_fs();
diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
index b3aee261801e..317ce27bdc4b 100644
--- a/fs/nfs/nfstrace.h
+++ b/fs/nfs/nfstrace.h
@@ -42,7 +42,6 @@
 			{ BIT(NFS_INO_ACL_LRU_SET), "ACL_LRU_SET" }, \
 			{ BIT(NFS_INO_INVALIDATING), "INVALIDATING" }, \
 			{ BIT(NFS_INO_FSCACHE), "FSCACHE" }, \
-			{ BIT(NFS_INO_FSCACHE_LOCK), "FSCACHE_LOCK" }, \
 			{ BIT(NFS_INO_LAYOUTCOMMIT), "NEED_LAYOUTCOMMIT" }, \
 			{ BIT(NFS_INO_LAYOUTCOMMITTING), "LAYOUTCOMMIT" }, \
 			{ BIT(NFS_INO_LAYOUTSTATS), "LAYOUTSTATS" }, \
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index d11af2a9299c..eb00229c1a50 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -123,7 +123,7 @@ static void nfs_readpage_release(struct nfs_page *req, int error)
 		struct address_space *mapping = page_file_mapping(page);
 
 		if (PageUptodate(page))
-			nfs_readpage_to_fscache(inode, page, 0);
+			nfs_readpage_to_fscache(inode, page);
 		else if (!PageError(page) && !PagePrivate(page))
 			generic_error_remove_page(mapping, page);
 		unlock_page(page);
@@ -305,6 +305,12 @@ readpage_async_filler(void *data, struct page *page)
 
 	aligned_len = min_t(unsigned int, ALIGN(len, rsize), PAGE_SIZE);
 
+	if (!IS_SYNC(page->mapping->host)) {
+		error = nfs_readpage_from_fscache(page->mapping->host, page);
+		if (error == 0)
+			goto out_unlock;
+	}
+
 	new = nfs_create_request(desc->ctx, page, 0, aligned_len);
 	if (IS_ERR(new))
 		goto out_error;
@@ -320,6 +326,7 @@ readpage_async_filler(void *data, struct page *page)
 	return 0;
 out_error:
 	error = PTR_ERR(new);
+out_unlock:
 	unlock_page(page);
 out:
 	return error;
@@ -366,12 +373,6 @@ int nfs_readpage(struct file *file, struct page *page)
 		desc.ctx = get_nfs_open_context(nfs_file_open_context(file));
 
 	xchg(&desc.ctx->error, 0);
-	if (!IS_SYNC(inode)) {
-		ret = nfs_readpage_from_fscache(desc.ctx, inode, page);
-		if (ret == 0)
-			goto out_wait;
-	}
-
 	nfs_pageio_init_read(&desc.pgio, inode, false,
 			     &nfs_async_read_completion_ops);
 
@@ -381,7 +382,6 @@ int nfs_readpage(struct file *file, struct page *page)
 
 	nfs_pageio_complete_read(&desc.pgio);
 	ret = desc.pgio.pg_error < 0 ? desc.pgio.pg_error : 0;
-out_wait:
 	if (!ret) {
 		ret = wait_on_page_locked_killable(page);
 		if (!PageUptodate(page) && !ret)
@@ -419,14 +419,6 @@ int nfs_readpages(struct file *file, struct address_space *mapping,
 	} else
 		desc.ctx = get_nfs_open_context(nfs_file_open_context(file));
 
-	/* attempt to read as many of the pages as possible from the cache
-	 * - this returns -ENOBUFS immediately if the cookie is negative
-	 */
-	ret = nfs_readpages_from_fscache(desc.ctx, inode, mapping,
-					 pages, &nr_pages);
-	if (ret == 0)
-		goto read_complete; /* all pages were read */
-
 	nfs_pageio_init_read(&desc.pgio, inode, false,
 			     &nfs_async_read_completion_ops);
 
@@ -434,7 +426,6 @@ int nfs_readpages(struct file *file, struct address_space *mapping,
 
 	nfs_pageio_complete_read(&desc.pgio);
 
-read_complete:
 	put_nfs_open_context(desc.ctx);
 out:
 	trace_nfs_aop_readahead_done(inode, nr_pages, ret);
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 3aced401735c..6ab5eeb000dc 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -1204,42 +1204,42 @@ static int nfs_compare_super(struct super_block *sb, struct fs_context *fc)
 }
 
 #ifdef CONFIG_NFS_FSCACHE
-static void nfs_get_cache_cookie(struct super_block *sb,
-				 struct nfs_fs_context *ctx)
+static int nfs_get_cache_cookie(struct super_block *sb,
+				struct nfs_fs_context *ctx)
 {
 	struct nfs_server *nfss = NFS_SB(sb);
 	char *uniq = NULL;
 	int ulen = 0;
 
-	nfss->fscache_key = NULL;
 	nfss->fscache = NULL;
 
 	if (!ctx)
-		return;
+		return 0;
 
 	if (ctx->clone_data.sb) {
 		struct nfs_server *mnt_s = NFS_SB(ctx->clone_data.sb);
 		if (!(mnt_s->options & NFS_OPTION_FSCACHE))
-			return;
-		if (mnt_s->fscache_key) {
-			uniq = mnt_s->fscache_key->key.uniquifier;
-			ulen = mnt_s->fscache_key->key.uniq_len;
+			return 0;
+		if (mnt_s->fscache_uniq) {
+			uniq = mnt_s->fscache_uniq;
+			ulen = strlen(uniq);
 		}
 	} else {
 		if (!(ctx->options & NFS_OPTION_FSCACHE))
-			return;
+			return 0;
 		if (ctx->fscache_uniq) {
 			uniq = ctx->fscache_uniq;
 			ulen = strlen(ctx->fscache_uniq);
 		}
 	}
 
-	nfs_fscache_get_super_cookie(sb, uniq, ulen);
+	return nfs_fscache_get_super_cookie(sb, uniq, ulen);
 }
 #else
-static void nfs_get_cache_cookie(struct super_block *sb,
-				 struct nfs_fs_context *ctx)
+static int nfs_get_cache_cookie(struct super_block *sb,
+				struct nfs_fs_context *ctx)
 {
+	return 0;
 }
 #endif
 
@@ -1299,7 +1299,9 @@ int nfs_get_tree_common(struct fs_context *fc)
 			s->s_blocksize_bits = bsize;
 			s->s_blocksize = 1U << bsize;
 		}
-		nfs_get_cache_cookie(s, ctx);
+		error = nfs_get_cache_cookie(s, ctx);
+		if (error < 0)
+			goto error_splat_super;
 	}
 
 	error = nfs_get_root(s, fc);
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 9b7619ce17a7..987a187bd39a 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -294,6 +294,7 @@ static void nfs_grow_file(struct page *page, unsigned int offset, unsigned int c
 	nfs_inc_stats(inode, NFSIOS_EXTENDWRITE);
 out:
 	spin_unlock(&inode->i_lock);
+	nfs_fscache_invalidate(inode, 0);
 }
 
 /* A writeback failed: mark the page as bad, and invalidate the page cache */
@@ -2125,8 +2126,11 @@ int nfs_migrate_page(struct address_space *mapping, struct page *newpage,
 	if (PagePrivate(page))
 		return -EBUSY;
 
-	if (!nfs_fscache_release_page(page, GFP_KERNEL))
-		return -EBUSY;
+	if (PageFsCache(page)) {
+		if (mode == MIGRATE_ASYNC)
+			return -EBUSY;
+		wait_on_page_fscache(page);
+	}
 
 	return migrate_page(mapping, newpage, page, mode);
 }