Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Merge the 'net' tree to get the recent set of netfilter bug fixes in
order to assist with some merge hassles Pablo is going to have to deal
with for upcoming changes.

Signed-off-by: David S. Miller <davem@davemloft.net>

20 files changed, 255 insertions, 126 deletions

diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index fb962efdace..6d59006bfa2 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -201,6 +201,7 @@ int ceph_fs_debugfs_init(struct ceph_fs_client *fsc)
 	int err = -ENOMEM;
 
 	dout("ceph_fs_debugfs_init\n");
+	BUG_ON(!fsc->client->debugfs_dir);
 	fsc->debugfs_congestion_kb =
 		debugfs_create_file("writeback_congestion_kb",
 				    0600,
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 9fff9f3b17e..4b5762ef7c2 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -992,11 +992,15 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
 	if (rinfo->head->is_dentry) {
 		struct inode *dir = req->r_locked_dir;
 
-		err = fill_inode(dir, &rinfo->diri, rinfo->dirfrag,
-				 session, req->r_request_started, -1,
-				 &req->r_caps_reservation);
-		if (err < 0)
-			return err;
+		if (dir) {
+			err = fill_inode(dir, &rinfo->diri, rinfo->dirfrag,
+					 session, req->r_request_started, -1,
+					 &req->r_caps_reservation);
+			if (err < 0)
+				return err;
+		} else {
+			WARN_ON_ONCE(1);
+		}
 	}
 
 	/*
@@ -1004,6 +1008,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
 	 * will have trouble splicing in the virtual snapdir later
 	 */
 	if (rinfo->head->is_dentry && !req->r_aborted &&
+	    req->r_locked_dir &&
 	    (rinfo->head->is_target || strncmp(req->r_dentry->d_name.name,
 					       fsc->mount_options->snapdir_name,
 					       req->r_dentry->d_name.len))) {
diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c
index 8e3fb69fbe6..1396ceb4679 100644
--- a/fs/ceph/ioctl.c
+++ b/fs/ceph/ioctl.c
@@ -42,7 +42,8 @@ static long __validate_layout(struct ceph_mds_client *mdsc,
 	/* validate striping parameters */
 	if ((l->object_size & ~PAGE_MASK) ||
 	    (l->stripe_unit & ~PAGE_MASK) ||
-	    ((unsigned)l->object_size % (unsigned)l->stripe_unit))
+	    (l->stripe_unit != 0 &&
+	     ((unsigned)l->object_size % (unsigned)l->stripe_unit)))
 		return -EINVAL;
 
 	/* make sure it's a valid data pool */
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 1c8b5567080..eedec84c180 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1654,8 +1654,8 @@ SYSCALL_DEFINE1(epoll_create1, int, flags)
 		error = PTR_ERR(file);
 		goto out_free_fd;
 	}
-	fd_install(fd, file);
 	ep->file = file;
+	fd_install(fd, file);
 	return fd;
 
 out_free_fd:
diff --git a/fs/namei.c b/fs/namei.c
index 51e9aa6e39d..a856e7f7b6e 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -352,6 +352,7 @@ int __inode_permission(struct inode *inode, int mask)
 /**
  * sb_permission - Check superblock-level permissions
  * @sb: Superblock of inode to check permission on
+ * @inode: Inode to check permission on
  * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC)
  *
  * Separate out file-system wide checks from inode-specific permission checks.
@@ -656,6 +657,7 @@ int sysctl_protected_hardlinks __read_mostly = 1;
 /**
  * may_follow_link - Check symlink following for unsafe situations
  * @link: The path of the symlink
+ * @nd: nameidata pathwalk data
  *
  * In the case of the sysctl_protected_symlinks sysctl being enabled,
  * CAP_DAC_OVERRIDE needs to be specifically ignored if the symlink is
diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile
index 8bf3a3f6925..b7db60897f9 100644
--- a/fs/nfs/Makefile
+++ b/fs/nfs/Makefile
@@ -12,19 +12,19 @@ nfs-$(CONFIG_ROOT_NFS)	+= nfsroot.o
 nfs-$(CONFIG_SYSCTL)	+= sysctl.o
 nfs-$(CONFIG_NFS_FSCACHE) += fscache.o fscache-index.o
 
-obj-$(CONFIG_NFS_V2) += nfs2.o
-nfs2-y := nfs2super.o proc.o nfs2xdr.o
+obj-$(CONFIG_NFS_V2) += nfsv2.o
+nfsv2-y := nfs2super.o proc.o nfs2xdr.o
 
-obj-$(CONFIG_NFS_V3) += nfs3.o
-nfs3-y := nfs3super.o nfs3client.o nfs3proc.o nfs3xdr.o
-nfs3-$(CONFIG_NFS_V3_ACL) += nfs3acl.o
+obj-$(CONFIG_NFS_V3) += nfsv3.o
+nfsv3-y := nfs3super.o nfs3client.o nfs3proc.o nfs3xdr.o
+nfsv3-$(CONFIG_NFS_V3_ACL) += nfs3acl.o
 
-obj-$(CONFIG_NFS_V4) += nfs4.o
-nfs4-y := nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o nfs4super.o nfs4file.o \
+obj-$(CONFIG_NFS_V4) += nfsv4.o
+nfsv4-y := nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o nfs4super.o nfs4file.o \
 	  delegation.o idmap.o callback.o callback_xdr.o callback_proc.o \
 	  nfs4namespace.o nfs4getroot.o nfs4client.o
-nfs4-$(CONFIG_SYSCTL)	+= nfs4sysctl.o
-nfs4-$(CONFIG_NFS_V4_1)	+= pnfs.o pnfs_dev.o
+nfsv4-$(CONFIG_SYSCTL)	+= nfs4sysctl.o
+nfsv4-$(CONFIG_NFS_V4_1)	+= pnfs.o pnfs_dev.o
 
 obj-$(CONFIG_PNFS_FILE_LAYOUT) += nfs_layout_nfsv41_files.o
 nfs_layout_nfsv41_files-y := nfs4filelayout.o nfs4filelayoutdev.o
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 9fc0d9dfc91..99694442b93 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -105,7 +105,7 @@ struct nfs_subversion *get_nfs_version(unsigned int version)
 
 	if (IS_ERR(nfs)) {
 		mutex_lock(&nfs_version_mutex);
-		request_module("nfs%d", version);
+		request_module("nfsv%d", version);
 		nfs = find_nfs_version(version);
 		mutex_unlock(&nfs_version_mutex);
 	}
diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c
index b701358c39c..a850079467d 100644
--- a/fs/nfs/idmap.c
+++ b/fs/nfs/idmap.c
@@ -61,6 +61,12 @@ struct idmap {
 	struct mutex		idmap_mutex;
 };
 
+struct idmap_legacy_upcalldata {
+	struct rpc_pipe_msg pipe_msg;
+	struct idmap_msg idmap_msg;
+	struct idmap *idmap;
+};
+
 /**
  * nfs_fattr_init_names - initialise the nfs_fattr owner_name/group_name fields
  * @fattr: fully initialised struct nfs_fattr
@@ -324,6 +330,7 @@ static ssize_t nfs_idmap_get_key(const char *name, size_t namelen,
 		ret = nfs_idmap_request_key(&key_type_id_resolver_legacy,
 					    name, namelen, type, data,
 					    data_size, idmap);
+		idmap->idmap_key_cons = NULL;
 		mutex_unlock(&idmap->idmap_mutex);
 	}
 	return ret;
@@ -380,11 +387,13 @@ static const match_table_t nfs_idmap_tokens = {
 static int nfs_idmap_legacy_upcall(struct key_construction *, const char *, void *);
 static ssize_t idmap_pipe_downcall(struct file *, const char __user *,
 				   size_t);
+static void idmap_release_pipe(struct inode *);
 static void idmap_pipe_destroy_msg(struct rpc_pipe_msg *);
 
 static const struct rpc_pipe_ops idmap_upcall_ops = {
 	.upcall		= rpc_pipe_generic_upcall,
 	.downcall	= idmap_pipe_downcall,
+	.release_pipe	= idmap_release_pipe,
 	.destroy_msg	= idmap_pipe_destroy_msg,
 };
 
@@ -616,7 +625,8 @@ void nfs_idmap_quit(void)
 	nfs_idmap_quit_keyring();
 }
 
-static int nfs_idmap_prepare_message(char *desc, struct idmap_msg *im,
+static int nfs_idmap_prepare_message(char *desc, struct idmap *idmap,
+				     struct idmap_msg *im,
 				     struct rpc_pipe_msg *msg)
 {
 	substring_t substr;
@@ -659,6 +669,7 @@ static int nfs_idmap_legacy_upcall(struct key_construction *cons,
 				   const char *op,
 				   void *aux)
 {
+	struct idmap_legacy_upcalldata *data;
 	struct rpc_pipe_msg *msg;
 	struct idmap_msg *im;
 	struct idmap *idmap = (struct idmap *)aux;
@@ -666,15 +677,15 @@ static int nfs_idmap_legacy_upcall(struct key_construction *cons,
 	int ret = -ENOMEM;
 
 	/* msg and im are freed in idmap_pipe_destroy_msg */
-	msg = kmalloc(sizeof(*msg), GFP_KERNEL);
-	if (!msg)
-		goto out0;
-
-	im = kmalloc(sizeof(*im), GFP_KERNEL);
-	if (!im)
+	data = kmalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
 		goto out1;
 
-	ret = nfs_idmap_prepare_message(key->description, im, msg);
+	msg = &data->pipe_msg;
+	im = &data->idmap_msg;
+	data->idmap = idmap;
+
+	ret = nfs_idmap_prepare_message(key->description, idmap, im, msg);
 	if (ret < 0)
 		goto out2;
 
@@ -683,15 +694,15 @@ static int nfs_idmap_legacy_upcall(struct key_construction *cons,
 
 	ret = rpc_queue_upcall(idmap->idmap_pipe, msg);
 	if (ret < 0)
-		goto out2;
+		goto out3;
 
 	return ret;
 
+out3:
+	idmap->idmap_key_cons = NULL;
 out2:
-	kfree(im);
+	kfree(data);
 out1:
-	kfree(msg);
-out0:
 	complete_request_key(cons, ret);
 	return ret;
 }
@@ -749,9 +760,8 @@ idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen)
 	}
 
 	if (!(im.im_status & IDMAP_STATUS_SUCCESS)) {
-		ret = mlen;
-		complete_request_key(cons, -ENOKEY);
-		goto out_incomplete;
+		ret = -ENOKEY;
+		goto out;
 	}
 
 	namelen_in = strnlen(im.im_name, IDMAP_NAMESZ);
@@ -768,16 +778,32 @@ idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen)
 
 out:
 	complete_request_key(cons, ret);
-out_incomplete:
 	return ret;
 }
 
 static void
 idmap_pipe_destroy_msg(struct rpc_pipe_msg *msg)
 {
+	struct idmap_legacy_upcalldata *data = container_of(msg,
+			struct idmap_legacy_upcalldata,
+			pipe_msg);
+	struct idmap *idmap = data->idmap;
+	struct key_construction *cons;
+	if (msg->errno) {
+		cons = ACCESS_ONCE(idmap->idmap_key_cons);
+		idmap->idmap_key_cons = NULL;
+		complete_request_key(cons, msg->errno);
+	}
 	/* Free memory allocated in nfs_idmap_legacy_upcall() */
-	kfree(msg->data);
-	kfree(msg);
+	kfree(data);
+}
+
+static void
+idmap_release_pipe(struct inode *inode)
+{
+	struct rpc_inode *rpci = RPC_I(inode);
+	struct idmap *idmap = (struct idmap *)rpci->private;
+	idmap->idmap_key_cons = NULL;
 }
 
 int nfs_map_name_to_uid(const struct nfs_server *server, const char *name, size_t namelen, __u32 *uid)
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index 0952c791df3..d6b3b5f2d77 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -69,7 +69,7 @@ do_proc_get_root(struct rpc_clnt *client, struct nfs_fh *fhandle,
 	nfs_fattr_init(info->fattr);
 	status = rpc_call_sync(client, &msg, 0);
 	dprintk("%s: reply fsinfo: %d\n", __func__, status);
-	if (!(info->fattr->valid & NFS_ATTR_FATTR)) {
+	if (status == 0 && !(info->fattr->valid & NFS_ATTR_FATTR)) {
 		msg.rpc_proc = &nfs3_procedures[NFS3PROC_GETATTR];
 		msg.rpc_resp = info->fattr;
 		status = rpc_call_sync(client, &msg, 0);
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 3b950dd81e8..da0618aeead 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -205,6 +205,9 @@ extern const struct dentry_operations nfs4_dentry_operations;
 int nfs_atomic_open(struct inode *, struct dentry *, struct file *,
 		    unsigned, umode_t, int *);
 
+/* super.c */
+extern struct file_system_type nfs4_fs_type;
+
 /* nfs4namespace.c */
 rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *);
 struct rpc_clnt *nfs4_create_sec_client(struct rpc_clnt *, struct inode *, struct qstr *);
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index cbcdfaf3250..24eb663f8ed 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -74,7 +74,7 @@ struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *cl_init)
 	return clp;
 
 error:
-	kfree(clp);
+	nfs_free_client(clp);
 	return ERR_PTR(err);
 }
 
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index a99a8d94872..635274140b1 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -3737,9 +3737,10 @@ out:
 static void nfs4_write_cached_acl(struct inode *inode, struct page **pages, size_t pgbase, size_t acl_len)
 {
 	struct nfs4_cached_acl *acl;
+	size_t buflen = sizeof(*acl) + acl_len;
 
-	if (pages && acl_len <= PAGE_SIZE) {
-		acl = kmalloc(sizeof(*acl) + acl_len, GFP_KERNEL);
+	if (pages && buflen <= PAGE_SIZE) {
+		acl = kmalloc(buflen, GFP_KERNEL);
 		if (acl == NULL)
 			goto out;
 		acl->cached = 1;
@@ -3819,7 +3820,7 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu
 	if (ret)
 		goto out_free;
 
-	acl_len = res.acl_len - res.acl_data_offset;
+	acl_len = res.acl_len;
 	if (acl_len > args.acl_len)
 		nfs4_write_cached_acl(inode, NULL, 0, acl_len);
 	else
@@ -6223,11 +6224,58 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
 	dprintk("<-- %s\n", __func__);
 }
 
+static size_t max_response_pages(struct nfs_server *server)
+{
+	u32 max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz;
+	return nfs_page_array_len(0, max_resp_sz);
+}
+
+static void nfs4_free_pages(struct page **pages, size_t size)
+{
+	int i;
+
+	if (!pages)
+		return;
+
+	for (i = 0; i < size; i++) {
+		if (!pages[i])
+			break;
+		__free_page(pages[i]);
+	}
+	kfree(pages);
+}
+
+static struct page **nfs4_alloc_pages(size_t size, gfp_t gfp_flags)
+{
+	struct page **pages;
+	int i;
+
+	pages = kcalloc(size, sizeof(struct page *), gfp_flags);
+	if (!pages) {
+		dprintk("%s: can't alloc array of %zu pages\n", __func__, size);
+		return NULL;
+	}
+
+	for (i = 0; i < size; i++) {
+		pages[i] = alloc_page(gfp_flags);
+		if (!pages[i]) {
+			dprintk("%s: failed to allocate page\n", __func__);
+			nfs4_free_pages(pages, size);
+			return NULL;
+		}
+	}
+
+	return pages;
+}
+
 static void nfs4_layoutget_release(void *calldata)
 {
 	struct nfs4_layoutget *lgp = calldata;
+	struct nfs_server *server = NFS_SERVER(lgp->args.inode);
+	size_t max_pages = max_response_pages(server);
 
 	dprintk("--> %s\n", __func__);
+	nfs4_free_pages(lgp->args.layout.pages, max_pages);
 	put_nfs_open_context(lgp->args.ctx);
 	kfree(calldata);
 	dprintk("<-- %s\n", __func__);
@@ -6239,9 +6287,10 @@ static const struct rpc_call_ops nfs4_layoutget_call_ops = {
 	.rpc_release = nfs4_layoutget_release,
 };
 
-int nfs4_proc_layoutget(struct nfs4_layoutget *lgp)
+void nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags)
 {
 	struct nfs_server *server = NFS_SERVER(lgp->args.inode);
+	size_t max_pages = max_response_pages(server);
 	struct rpc_task *task;
 	struct rpc_message msg = {
 		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_LAYOUTGET],
@@ -6259,12 +6308,19 @@ int nfs4_proc_layoutget(struct nfs4_layoutget *lgp)
 
 	dprintk("--> %s\n", __func__);
 
+	lgp->args.layout.pages = nfs4_alloc_pages(max_pages, gfp_flags);
+	if (!lgp->args.layout.pages) {
+		nfs4_layoutget_release(lgp);
+		return;
+	}
+	lgp->args.layout.pglen = max_pages * PAGE_SIZE;
+
 	lgp->res.layoutp = &lgp->args.layout;
 	lgp->res.seq_res.sr_slot = NULL;
 	nfs41_init_sequence(&lgp->args.seq_args, &lgp->res.seq_res, 0);
 	task = rpc_run_task(&task_setup_data);
 	if (IS_ERR(task))
-		return PTR_ERR(task);
+		return;
 	status = nfs4_wait_for_completion_rpc_task(task);
 	if (status == 0)
 		status = task->tk_status;
@@ -6272,7 +6328,7 @@ int nfs4_proc_layoutget(struct nfs4_layoutget *lgp)
 		status = pnfs_layout_process(lgp);
 	rpc_put_task(task);
 	dprintk("<-- %s status=%d\n", __func__, status);
-	return status;
+	return;
 }
 
 static void
@@ -6304,12 +6360,8 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata)
 		return;
 	}
 	spin_lock(&lo->plh_inode->i_lock);
-	if (task->tk_status == 0) {
-		if (lrp->res.lrs_present) {
-			pnfs_set_layout_stateid(lo, &lrp->res.stateid, true);
-		} else
-			BUG_ON(!list_empty(&lo->plh_segs));
-	}
+	if (task->tk_status == 0 && lrp->res.lrs_present)
+		pnfs_set_layout_stateid(lo, &lrp->res.stateid, true);
 	lo->plh_block_lgets--;
 	spin_unlock(&lo->plh_inode->i_lock);
 	dprintk("<-- %s\n", __func__);
diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c
index 12a31a9dbcd..bd61221ad2c 100644
--- a/fs/nfs/nfs4super.c
+++ b/fs/nfs/nfs4super.c
@@ -23,14 +23,6 @@ static struct dentry *nfs4_referral_mount(struct file_system_type *fs_type,
 static struct dentry *nfs4_remote_referral_mount(struct file_system_type *fs_type,
 	int flags, const char *dev_name, void *raw_data);
 
-static struct file_system_type nfs4_fs_type = {
-	.owner		= THIS_MODULE,
-	.name		= "nfs4",
-	.mount		= nfs_fs_mount,
-	.kill_sb	= nfs_kill_super,
-	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
-};
-
 static struct file_system_type nfs4_remote_fs_type = {
 	.owner		= THIS_MODULE,
 	.name		= "nfs4",
@@ -344,14 +336,8 @@ static int __init init_nfs_v4(void)
 	if (err)
 		goto out1;
 
-	err = register_filesystem(&nfs4_fs_type);
-	if (err < 0)
-		goto out2;
-
 	register_nfs_version(&nfs_v4);
 	return 0;
-out2:
-	nfs4_unregister_sysctl();
 out1:
 	nfs_idmap_quit();
 out:
@@ -361,7 +347,6 @@ out:
 static void __exit exit_nfs_v4(void)
 {
 	unregister_nfs_version(&nfs_v4);
-	unregister_filesystem(&nfs4_fs_type);
 	nfs4_unregister_sysctl();
 	nfs_idmap_quit();
 }
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index ca13483edd6..1bfbd67c556 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -5045,22 +5045,19 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req,
 			 struct nfs_getaclres *res)
 {
 	unsigned int savep;
-	__be32 *bm_p;
 	uint32_t attrlen,
 		 bitmap[3] = {0};
 	int status;
-	size_t page_len = xdr->buf->page_len;
+	unsigned int pg_offset;
 
 	res->acl_len = 0;
 	if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0)
 		goto out;
 
-	bm_p = xdr->p;
-	res->acl_data_offset = be32_to_cpup(bm_p) + 2;
-	res->acl_data_offset <<= 2;
-	/* Check if the acl data starts beyond the allocated buffer */
-	if (res->acl_data_offset > page_len)
-		return -ERANGE;
+	xdr_enter_page(xdr, xdr->buf->page_len);
+
+	/* Calculate the offset of the page data */
+	pg_offset = xdr->buf->head[0].iov_len;
 
 	if ((status = decode_attr_bitmap(xdr, bitmap)) != 0)
 		goto out;
@@ -5074,23 +5071,20 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req,
 		/* The bitmap (xdr len + bitmaps) and the attr xdr len words
 		 * are stored with the acl data to handle the problem of
 		 * variable length bitmaps.*/
-		xdr->p = bm_p;
+		res->acl_data_offset = xdr_stream_pos(xdr) - pg_offset;
 
 		/* We ignore &savep and don't do consistency checks on
 		 * the attr length.  Let userspace figure it out.... */
-		attrlen += res->acl_data_offset;
-		if (attrlen > page_len) {
+		res->acl_len = attrlen;
+		if (attrlen > (xdr->nwords << 2)) {
 			if (res->acl_flags & NFS4_ACL_LEN_REQUEST) {
 				/* getxattr interface called with a NULL buf */
-				res->acl_len = attrlen;
 				goto out;
 			}
-			dprintk("NFS: acl reply: attrlen %u > page_len %zu\n",
-					attrlen, page_len);
+			dprintk("NFS: acl reply: attrlen %u > page_len %u\n",
+					attrlen, xdr->nwords << 2);
 			return -EINVAL;
 		}
-		xdr_read_pages(xdr, attrlen);
-		res->acl_len = attrlen;
 	} else
 		status = -EOPNOTSUPP;
 
diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c
index f50d3e8d6f2..ea6d111b03e 100644
--- a/fs/nfs/objlayout/objio_osd.c
+++ b/fs/nfs/objlayout/objio_osd.c
@@ -570,17 +570,66 @@ static bool objio_pg_test(struct nfs_pageio_descriptor *pgio,
 		return false;
 
 	return pgio->pg_count + req->wb_bytes <=
-			OBJIO_LSEG(pgio->pg_lseg)->layout.max_io_length;
+			(unsigned long)pgio->pg_layout_private;
+}
+
+void objio_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
+{
+	pnfs_generic_pg_init_read(pgio, req);
+	if (unlikely(pgio->pg_lseg == NULL))
+		return; /* Not pNFS */
+
+	pgio->pg_layout_private = (void *)
+				OBJIO_LSEG(pgio->pg_lseg)->layout.max_io_length;
+}
+
+static bool aligned_on_raid_stripe(u64 offset, struct ore_layout *layout,
+				   unsigned long *stripe_end)
+{
+	u32 stripe_off;
+	unsigned stripe_size;
+
+	if (layout->raid_algorithm == PNFS_OSD_RAID_0)
+		return true;
+
+	stripe_size = layout->stripe_unit *
+				(layout->group_width - layout->parity);
+
+	div_u64_rem(offset, stripe_size, &stripe_off);
+	if (!stripe_off)
+		return true;
+
+	*stripe_end = stripe_size - stripe_off;
+	return false;
+}
+
+void objio_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
+{
+	unsigned long stripe_end = 0;
+
+	pnfs_generic_pg_init_write(pgio, req);
+	if (unlikely(pgio->pg_lseg == NULL))
+		return; /* Not pNFS */
+
+	if (req->wb_offset ||
+	    !aligned_on_raid_stripe(req->wb_index * PAGE_SIZE,
+			       &OBJIO_LSEG(pgio->pg_lseg)->layout,
+			       &stripe_end)) {
+		pgio->pg_layout_private = (void *)stripe_end;
+	} else {
+		pgio->pg_layout_private = (void *)
+				OBJIO_LSEG(pgio->pg_lseg)->layout.max_io_length;
+	}
 }
 
 static const struct nfs_pageio_ops objio_pg_read_ops = {
-	.pg_init = pnfs_generic_pg_init_read,
+	.pg_init = objio_init_read,
 	.pg_test = objio_pg_test,
 	.pg_doio = pnfs_generic_pg_readpages,
 };
 
 static const struct nfs_pageio_ops objio_pg_write_ops = {
-	.pg_init = pnfs_generic_pg_init_write,
+	.pg_init = objio_init_write,
 	.pg_test = objio_pg_test,
 	.pg_doio = pnfs_generic_pg_writepages,
 };
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 1a6732ed04a..311a79681e2 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -49,6 +49,7 @@ void nfs_pgheader_init(struct nfs_pageio_descriptor *desc,
 	hdr->io_start = req_offset(hdr->req);
 	hdr->good_bytes = desc->pg_count;
 	hdr->dreq = desc->pg_dreq;
+	hdr->layout_private = desc->pg_layout_private;
 	hdr->release = release;
 	hdr->completion_ops = desc->pg_completion_ops;
 	if (hdr->completion_ops->init_hdr)
@@ -268,6 +269,7 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc,
 	desc->pg_error = 0;
 	desc->pg_lseg = NULL;
 	desc->pg_dreq = NULL;
+	desc->pg_layout_private = NULL;
 }
 EXPORT_SYMBOL_GPL(nfs_pageio_init);
 
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 76875bfcf19..2e00feacd4b 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -583,9 +583,6 @@ send_layoutget(struct pnfs_layout_hdr *lo,
 	struct nfs_server *server = NFS_SERVER(ino);
 	struct nfs4_layoutget *lgp;
 	struct pnfs_layout_segment *lseg = NULL;
-	struct page **pages = NULL;
-	int i;
-	u32 max_resp_sz, max_pages;
 
 	dprintk("--> %s\n", __func__);
 
@@ -594,20 +591,6 @@ send_layoutget(struct pnfs_layout_hdr *lo,
 	if (lgp == NULL)
 		return NULL;
 
-	/* allocate pages for xdr post processing */
-	max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz;
-	max_pages = nfs_page_array_len(0, max_resp_sz);
-
-	pages = kcalloc(max_pages, sizeof(struct page *), gfp_flags);
-	if (!pages)
-		goto out_err_free;
-
-	for (i = 0; i < max_pages; i++) {
-		pages[i] = alloc_page(gfp_flags);
-		if (!pages[i])
-			goto out_err_free;
-	}
-
 	lgp->args.minlength = PAGE_CACHE_SIZE;
 	if (lgp->args.minlength > range->length)
 		lgp->args.minlength = range->length;
@@ -616,39 +599,19 @@ send_layoutget(struct pnfs_layout_hdr *lo,
 	lgp->args.type = server->pnfs_curr_ld->id;
 	lgp->args.inode = ino;
 	lgp->args.ctx = get_nfs_open_context(ctx);
-	lgp->args.layout.pages = pages;
-	lgp->args.layout.pglen = max_pages * PAGE_SIZE;
 	lgp->lsegpp = &lseg;
 	lgp->gfp_flags = gfp_flags;
 
 	/* Synchronously retrieve layout information from server and
 	 * store in lseg.
 	 */
-	nfs4_proc_layoutget(lgp);
+	nfs4_proc_layoutget(lgp, gfp_flags);
 	if (!lseg) {
 		/* remember that LAYOUTGET failed and suspend trying */
 		set_bit(lo_fail_bit(range->iomode), &lo->plh_flags);
 	}
 
-	/* free xdr pages */
-	for (i = 0; i < max_pages; i++)
-		__free_page(pages[i]);
-	kfree(pages);
-
 	return lseg;
-
-out_err_free:
-	/* free any allocated xdr pages, lgp as it's not used */
-	if (pages) {
-		for (i = 0; i < max_pages; i++) {
-			if (!pages[i])
-				break;
-			__free_page(pages[i]);
-		}
-		kfree(pages);
-	}
-	kfree(lgp);
-	return NULL;
 }
 
 /*
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 2c6c80503ba..745aa1b39e7 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -172,7 +172,7 @@ extern int nfs4_proc_getdevicelist(struct nfs_server *server,
 				   struct pnfs_devicelist *devlist);
 extern int nfs4_proc_getdeviceinfo(struct nfs_server *server,
 				   struct pnfs_device *dev);
-extern int nfs4_proc_layoutget(struct nfs4_layoutget *lgp);
+extern void nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags);
 extern int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp);
 
 /* pnfs.c */
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index ac6a3c55dce..239aff7338e 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -319,6 +319,34 @@ EXPORT_SYMBOL_GPL(nfs_sops);
 static void nfs4_validate_mount_flags(struct nfs_parsed_mount_data *);
 static int nfs4_validate_mount_data(void *options,
 	struct nfs_parsed_mount_data *args, const char *dev_name);
+
+struct file_system_type nfs4_fs_type = {
+	.owner		= THIS_MODULE,
+	.name		= "nfs4",
+	.mount		= nfs_fs_mount,
+	.kill_sb	= nfs_kill_super,
+	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
+};
+EXPORT_SYMBOL_GPL(nfs4_fs_type);
+
+static int __init register_nfs4_fs(void)
+{
+	return register_filesystem(&nfs4_fs_type);
+}
+
+static void unregister_nfs4_fs(void)
+{
+	unregister_filesystem(&nfs4_fs_type);
+}
+#else
+static int __init register_nfs4_fs(void)
+{
+	return 0;
+}
+
+static void unregister_nfs4_fs(void)
+{
+}
 #endif
 
 static struct shrinker acl_shrinker = {
@@ -337,12 +365,18 @@ int __init register_nfs_fs(void)
 	if (ret < 0)
 		goto error_0;
 
-	ret = nfs_register_sysctl();
+	ret = register_nfs4_fs();
 	if (ret < 0)
 		goto error_1;
+
+	ret = nfs_register_sysctl();
+	if (ret < 0)
+		goto error_2;
 	register_shrinker(&acl_shrinker);
 	return 0;
 
+error_2:
+	unregister_nfs4_fs();
 error_1:
 	unregister_filesystem(&nfs_fs_type);
 error_0:
@@ -356,6 +390,7 @@ void __exit unregister_nfs_fs(void)
 {
 	unregister_shrinker(&acl_shrinker);
 	nfs_unregister_sysctl();
+	unregister_nfs4_fs();
 	unregister_filesystem(&nfs_fs_type);
 }
 
@@ -2645,4 +2680,6 @@ MODULE_PARM_DESC(max_session_slots, "Maximum number of outstanding NFSv4.1 "
 module_param(send_implementation_id, ushort, 0644);
 MODULE_PARM_DESC(send_implementation_id,
 		"Send implementation ID with NFSv4.1 exchange_id");
+MODULE_ALIAS("nfs4");
+
 #endif /* CONFIG_NFS_V4 */
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 5829d0ce7cf..e3b55372726 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1814,19 +1814,19 @@ int __init nfs_init_writepagecache(void)
 	nfs_wdata_mempool = mempool_create_slab_pool(MIN_POOL_WRITE,
 						     nfs_wdata_cachep);
 	if (nfs_wdata_mempool == NULL)
-		return -ENOMEM;
+		goto out_destroy_write_cache;
 
 	nfs_cdata_cachep = kmem_cache_create("nfs_commit_data",
 					     sizeof(struct nfs_commit_data),
 					     0, SLAB_HWCACHE_ALIGN,
 					     NULL);
 	if (nfs_cdata_cachep == NULL)
-		return -ENOMEM;
+		goto out_destroy_write_mempool;
 
 	nfs_commit_mempool = mempool_create_slab_pool(MIN_POOL_COMMIT,
 						      nfs_wdata_cachep);
 	if (nfs_commit_mempool == NULL)
-		return -ENOMEM;
+		goto out_destroy_commit_cache;
 
 	/*
 	 * NFS congestion size, scale with available memory.
@@ -1849,11 +1849,20 @@ int __init nfs_init_writepagecache(void)
 		nfs_congestion_kb = 256*1024;
 
 	return 0;
+
+out_destroy_commit_cache:
+	kmem_cache_destroy(nfs_cdata_cachep);
+out_destroy_write_mempool:
+	mempool_destroy(nfs_wdata_mempool);
+out_destroy_write_cache:
+	kmem_cache_destroy(nfs_wdata_cachep);
+	return -ENOMEM;
 }
 
 void nfs_destroy_writepagecache(void)
 {
 	mempool_destroy(nfs_commit_mempool);
+	kmem_cache_destroy(nfs_cdata_cachep);
 	mempool_destroy(nfs_wdata_mempool);
 	kmem_cache_destroy(nfs_wdata_cachep);
 }