Merge tag 'nfsd-4.8' of git://linux-nfs.org/~bfields/linux

Pull nfsd updates from Bruce Fields:
 "Highlights:

   - Trond made a change to the server's tcp logic that allows a fast
     client to better take advantage of high bandwidth networks, but may
     increase the risk that a single client could starve other clients;
     a new sunrpc.svc_rpc_per_connection_limit parameter should help
     mitigate this in the (hopefully unlikely) event this becomes a
     problem in practice.

   - Tom Haynes added a minimal flex-layout pnfs server, which is of no
     use in production for now--don't build it unless you're doing
     client testing or further server development"

* tag 'nfsd-4.8' of git://linux-nfs.org/~bfields/linux: (32 commits)
  nfsd: remove some dead code in nfsd_create_locked()
  nfsd: drop unnecessary MAY_EXEC check from create
  nfsd: clean up bad-type check in nfsd_create_locked
  nfsd: remove unnecessary positive-dentry check
  nfsd: reorganize nfsd_create
  nfsd: check d_can_lookup in fh_verify of directories
  nfsd: remove redundant zero-length check from create
  nfsd: Make creates return EEXIST instead of EACCES
  SUNRPC: Detect immediate closure of accepted sockets
  SUNRPC: accept() may return sockets that are still in SYN_RECV
  nfsd: allow nfsd to advertise multiple layout types
  nfsd: Close race between nfsd4_release_lockowner and nfsd4_lock
  nfsd/blocklayout: Make sure calculate signature/designator length aligned
  xfs: abstract block export operations from nfsd layouts
  SUNRPC: Remove unused callback xpo_adjust_wspace()
  SUNRPC: Change TCP socket space reservation
  SUNRPC: Add a server side per-connection limit
  SUNRPC: Micro optimisation for svc_data_ready
  SUNRPC: Call the default socket callbacks instead of open coding
  SUNRPC: lock the socket while detaching it
  ...

Documentation/kernel-parameters.txt

@@ -3877,6 +3877,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			using these two parameters to set the minimum and
 			maximum port values.
 
+	sunrpc.svc_rpc_per_connection_limit=
+			[NFS,SUNRPC]
+			Limit the number of requests that the server will
+			process in parallel from a single connection.
+			The default value is 0 (no limit).
+
 	sunrpc.pool_mode=
 			[NFS]
 			Control how the NFS server code allocates CPUs to

fs/Kconfig

@@ -70,6 +70,12 @@ config FS_POSIX_ACL
 config EXPORTFS
 	tristate
 
+config EXPORTFS_BLOCK_OPS
+	bool "Enable filesystem export operations for block IO"
+	help
+	  This option enables the export operations for a filesystem to support
+	  external block IO.
+
 config FILE_LOCKING
 	bool "Enable POSIX file locking API" if EXPERT
 	default y

fs/nfsd/Kconfig

@@ -90,6 +90,7 @@ config NFSD_BLOCKLAYOUT
 	bool "NFSv4.1 server support for pNFS block layouts"
 	depends on NFSD_V4 && BLOCK
 	select NFSD_PNFS
+	select EXPORTFS_BLOCK_OPS
 	help
 	  This option enables support for the exporting pNFS block layouts
 	  in the kernel's NFS server. The pNFS block layout enables NFS
@@ -102,6 +103,7 @@ config NFSD_SCSILAYOUT
 	bool "NFSv4.1 server support for pNFS SCSI layouts"
 	depends on NFSD_V4 && BLOCK
 	select NFSD_PNFS
+	select EXPORTFS_BLOCK_OPS
 	help
 	  This option enables support for the exporting pNFS SCSI layouts
 	  in the kernel's NFS server. The pNFS SCSI layout enables NFS
@@ -111,6 +113,23 @@ config NFSD_SCSILAYOUT
 
 	  If unsure, say N.
 
+config NFSD_FLEXFILELAYOUT
+	bool "NFSv4.1 server support for pNFS Flex File layouts"
+	depends on NFSD_V4
+	select NFSD_PNFS
+	help
+	  This option enables support for the exporting pNFS Flex File
+	  layouts in the kernel's NFS server. The pNFS Flex File  layout
+	  enables NFS clients to directly perform I/O to NFSv3 devices
+	  accesible to both the server and the clients.  See
+	  draft-ietf-nfsv4-flex-files for more details.
+
+	  Warning, this server implements the bare minimum functionality
+	  to be a flex file server - it is for testing the client,
+	  not for use in production.
+
+	  If unsure, say N.
+
 config NFSD_V4_SECURITY_LABEL
 	bool "Provide Security Label support for NFSv4 server"
 	depends on NFSD_V4 && SECURITY

fs/nfsd/Makefile

@@ -20,3 +20,4 @@ nfsd-$(CONFIG_NFSD_V4)	+= nfs4proc.o nfs4xdr.o nfs4state.o nfs4idmap.o \
 nfsd-$(CONFIG_NFSD_PNFS) += nfs4layouts.o
 nfsd-$(CONFIG_NFSD_BLOCKLAYOUT) += blocklayout.o blocklayoutxdr.o
 nfsd-$(CONFIG_NFSD_SCSILAYOUT) += blocklayout.o blocklayoutxdr.o
+nfsd-$(CONFIG_NFSD_FLEXFILELAYOUT) += flexfilelayout.o flexfilelayoutxdr.o

fs/nfsd/blocklayout.c

@@ -163,6 +163,7 @@ nfsd4_block_get_device_info_simple(struct super_block *sb,
 
 static __be32
 nfsd4_block_proc_getdeviceinfo(struct super_block *sb,
+		struct svc_rqst *rqstp,
 		struct nfs4_client *clp,
 		struct nfsd4_getdeviceinfo *gdp)
 {
@@ -355,6 +356,7 @@ nfsd4_block_get_device_info_scsi(struct super_block *sb,
 
 static __be32
 nfsd4_scsi_proc_getdeviceinfo(struct super_block *sb,
+		struct svc_rqst *rqstp,
 		struct nfs4_client *clp,
 		struct nfsd4_getdeviceinfo *gdp)
 {

fs/nfsd/blocklayoutxdr.c

@@ -44,7 +44,7 @@ nfsd4_block_encode_volume(struct xdr_stream *xdr, struct pnfs_block_volume *b)
 
 	switch (b->type) {
 	case PNFS_BLOCK_VOLUME_SIMPLE:
-		len = 4 + 4 + 8 + 4 + b->simple.sig_len;
+		len = 4 + 4 + 8 + 4 + (XDR_QUADLEN(b->simple.sig_len) << 2);
 		p = xdr_reserve_space(xdr, len);
 		if (!p)
 			return -ETOOSMALL;
@@ -55,7 +55,7 @@ nfsd4_block_encode_volume(struct xdr_stream *xdr, struct pnfs_block_volume *b)
 		p = xdr_encode_opaque(p, b->simple.sig, b->simple.sig_len);
 		break;
 	case PNFS_BLOCK_VOLUME_SCSI:
-		len = 4 + 4 + 4 + 4 + b->scsi.designator_len + 8;
+		len = 4 + 4 + 4 + 4 + (XDR_QUADLEN(b->scsi.designator_len) << 2) + 8;
 		p = xdr_reserve_space(xdr, len);
 		if (!p)
 			return -ETOOSMALL;

fs/nfsd/export.c

@@ -706,7 +706,7 @@ static void svc_export_init(struct cache_head *cnew, struct cache_head *citem)
 	new->ex_fslocs.locations = NULL;
 	new->ex_fslocs.locations_count = 0;
 	new->ex_fslocs.migrated = 0;
-	new->ex_layout_type = 0;
+	new->ex_layout_types = 0;
 	new->ex_uuid = NULL;
 	new->cd = item->cd;
 }
@@ -731,7 +731,7 @@ static void export_update(struct cache_head *cnew, struct cache_head *citem)
 	item->ex_fslocs.locations_count = 0;
 	new->ex_fslocs.migrated = item->ex_fslocs.migrated;
 	item->ex_fslocs.migrated = 0;
-	new->ex_layout_type = item->ex_layout_type;
+	new->ex_layout_types = item->ex_layout_types;
 	new->ex_nflavors = item->ex_nflavors;
 	for (i = 0; i < MAX_SECINFO_LIST; i++) {
 		new->ex_flavors[i] = item->ex_flavors[i];
@@ -954,6 +954,16 @@ __be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp)
 		    rqstp->rq_cred.cr_flavor == RPC_AUTH_UNIX)
 			return 0;
 	}
+
+	/* If the compound op contains a spo_must_allowed op,
+	 * it will be sent with integrity/protection which
+	 * will have to be expressly allowed on mounts that
+	 * don't support it
+	 */
+
+	if (nfsd4_spo_must_allow(rqstp))
+		return 0;
+
 	return nfserr_wrongsec;
 }
 

fs/nfsd/export.h

@@ -57,7 +57,7 @@ struct svc_export {
 	struct nfsd4_fs_locations ex_fslocs;
 	uint32_t		ex_nflavors;
 	struct exp_flavor_info	ex_flavors[MAX_SECINFO_LIST];
-	enum pnfs_layouttype	ex_layout_type;
+	u32			ex_layout_types;
 	struct nfsd4_deviceid_map *ex_devid_map;
 	struct cache_detail	*cd;
 };

fs/nfsd/flexfilelayout.c

+/*
+ * Copyright (c) 2016 Tom Haynes <loghyr@primarydata.com>
+ *
+ * The following implements a super-simple flex-file server
+ * where the NFSv4.1 mds is also the ds. And the storage is
+ * the same. I.e., writing to the mds via a NFSv4.1 WRITE
+ * goes to the same location as the NFSv3 WRITE.
+ */
+#include <linux/slab.h>
+
+#include <linux/nfsd/debug.h>
+
+#include <linux/sunrpc/addr.h>
+
+#include "flexfilelayoutxdr.h"
+#include "pnfs.h"
+
+#define NFSDDBG_FACILITY	NFSDDBG_PNFS
+
+static __be32
+nfsd4_ff_proc_layoutget(struct inode *inode, const struct svc_fh *fhp,
+		struct nfsd4_layoutget *args)
+{
+	struct nfsd4_layout_seg *seg = &args->lg_seg;
+	u32 device_generation = 0;
+	int error;
+	uid_t u;
+
+	struct pnfs_ff_layout *fl;
+
+	/*
+	 * The super simple flex file server has 1 mirror, 1 data server,
+	 * and 1 file handle. So instead of 4 allocs, do 1 for now.
+	 * Zero it out for the stateid - don't want junk in there!
+	 */
+	error = -ENOMEM;
+	fl = kzalloc(sizeof(*fl), GFP_KERNEL);
+	if (!fl)
+		goto out_error;
+	args->lg_content = fl;
+
+	/*
+	 * Avoid layout commit, try to force the I/O to the DS,
+	 * and for fun, cause all IOMODE_RW layout segments to
+	 * effectively be WRITE only.
+	 */
+	fl->flags = FF_FLAGS_NO_LAYOUTCOMMIT | FF_FLAGS_NO_IO_THRU_MDS |
+		    FF_FLAGS_NO_READ_IO;
+
+	/* Do not allow a IOMODE_READ segment to have write pemissions */
+	if (seg->iomode == IOMODE_READ) {
+		u = from_kuid(&init_user_ns, inode->i_uid) + 1;
+		fl->uid = make_kuid(&init_user_ns, u);
+	} else
+		fl->uid = inode->i_uid;
+	fl->gid = inode->i_gid;
+
+	error = nfsd4_set_deviceid(&fl->deviceid, fhp, device_generation);
+	if (error)
+		goto out_error;
+
+	fl->fh.size = fhp->fh_handle.fh_size;
+	memcpy(fl->fh.data, &fhp->fh_handle.fh_base, fl->fh.size);
+
+	/* Give whole file layout segments */
+	seg->offset = 0;
+	seg->length = NFS4_MAX_UINT64;
+
+	dprintk("GET: 0x%llx:0x%llx %d\n", seg->offset, seg->length,
+		seg->iomode);
+	return 0;
+
+out_error:
+	seg->length = 0;
+	return nfserrno(error);
+}
+
+static __be32
+nfsd4_ff_proc_getdeviceinfo(struct super_block *sb, struct svc_rqst *rqstp,
+		struct nfs4_client *clp, struct nfsd4_getdeviceinfo *gdp)
+{
+	struct pnfs_ff_device_addr *da;
+
+	u16 port;
+	char addr[INET6_ADDRSTRLEN];
+
+	da = kzalloc(sizeof(struct pnfs_ff_device_addr), GFP_KERNEL);
+	if (!da)
+		return nfserrno(-ENOMEM);
+
+	gdp->gd_device = da;
+
+	da->version = 3;
+	da->minor_version = 0;
+
+	da->rsize = svc_max_payload(rqstp);
+	da->wsize = da->rsize;
+
+	rpc_ntop((struct sockaddr *)&rqstp->rq_daddr,
+		 addr, INET6_ADDRSTRLEN);
+	if (rqstp->rq_daddr.ss_family == AF_INET) {
+		struct sockaddr_in *sin;
+
+		sin = (struct sockaddr_in *)&rqstp->rq_daddr;
+		port = ntohs(sin->sin_port);
+		snprintf(da->netaddr.netid, FF_NETID_LEN + 1, "tcp");
+		da->netaddr.netid_len = 3;
+	} else {
+		struct sockaddr_in6 *sin6;
+
+		sin6 = (struct sockaddr_in6 *)&rqstp->rq_daddr;
+		port = ntohs(sin6->sin6_port);
+		snprintf(da->netaddr.netid, FF_NETID_LEN + 1, "tcp6");
+		da->netaddr.netid_len = 4;
+	}
+
+	da->netaddr.addr_len =
+		snprintf(da->netaddr.addr, FF_ADDR_LEN + 1,
+			 "%s.%hhu.%hhu", addr, port >> 8, port & 0xff);
+
+	da->tightly_coupled = false;
+
+	return 0;
+}
+
+const struct nfsd4_layout_ops ff_layout_ops = {
+	.notify_types		=
+			NOTIFY_DEVICEID4_DELETE | NOTIFY_DEVICEID4_CHANGE,
+	.proc_getdeviceinfo	= nfsd4_ff_proc_getdeviceinfo,
+	.encode_getdeviceinfo	= nfsd4_ff_encode_getdeviceinfo,
+	.proc_layoutget		= nfsd4_ff_proc_layoutget,
+	.encode_layoutget	= nfsd4_ff_encode_layoutget,
+};

fs/nfsd/flexfilelayoutxdr.c

+/*
+ * Copyright (c) 2016 Tom Haynes <loghyr@primarydata.com>
+ */
+#include <linux/sunrpc/svc.h>
+#include <linux/nfs4.h>
+
+#include "nfsd.h"
+#include "flexfilelayoutxdr.h"
+
+#define NFSDDBG_FACILITY	NFSDDBG_PNFS
+
+struct ff_idmap {
+	char buf[11];
+	int len;
+};
+
+__be32
+nfsd4_ff_encode_layoutget(struct xdr_stream *xdr,
+		struct nfsd4_layoutget *lgp)
+{
+	struct pnfs_ff_layout *fl = lgp->lg_content;
+	int len, mirror_len, ds_len, fh_len;
+	__be32 *p;
+
+	/*
+	 * Unlike nfsd4_encode_user, we know these will
+	 * always be stringified.
+	 */
+	struct ff_idmap uid;
+	struct ff_idmap gid;
+
+	fh_len = 4 + fl->fh.size;
+
+	uid.len = sprintf(uid.buf, "%u", from_kuid(&init_user_ns, fl->uid));
+	gid.len = sprintf(gid.buf, "%u", from_kgid(&init_user_ns, fl->gid));
+
+	/* 8 + len for recording the length, name, and padding */
+	ds_len = 20 + sizeof(stateid_opaque_t) + 4 + fh_len +
+		 8 + uid.len + 8 + gid.len;
+
+	mirror_len = 4 + ds_len;
+
+	/* The layout segment */
+	len = 20 + mirror_len;
+
+	p = xdr_reserve_space(xdr, sizeof(__be32) + len);
+	if (!p)
+		return nfserr_toosmall;
+
+	*p++ = cpu_to_be32(len);
+	p = xdr_encode_hyper(p, 0);		/* stripe unit of 1 */
+
+	*p++ = cpu_to_be32(1);			/* single mirror */
+	*p++ = cpu_to_be32(1);			/* single data server */
+
+	p = xdr_encode_opaque_fixed(p, &fl->deviceid,
+			sizeof(struct nfsd4_deviceid));
+
+	*p++ = cpu_to_be32(1);			/* efficiency */
+
+	*p++ = cpu_to_be32(fl->stateid.si_generation);
+	p = xdr_encode_opaque_fixed(p, &fl->stateid.si_opaque,
+				    sizeof(stateid_opaque_t));
+
+	*p++ = cpu_to_be32(1);			/* single file handle */
+	p = xdr_encode_opaque(p, fl->fh.data, fl->fh.size);
+
+	p = xdr_encode_opaque(p, uid.buf, uid.len);
+	p = xdr_encode_opaque(p, gid.buf, gid.len);
+
+	*p++ = cpu_to_be32(fl->flags);
+	*p++ = cpu_to_be32(0);			/* No stats collect hint */
+
+	return 0;
+}
+
+__be32
+nfsd4_ff_encode_getdeviceinfo(struct xdr_stream *xdr,
+		struct nfsd4_getdeviceinfo *gdp)
+{
+	struct pnfs_ff_device_addr *da = gdp->gd_device;
+	int len;
+	int ver_len;
+	int addr_len;
+	__be32 *p;
+
+	/* len + padding for two strings */
+	addr_len = 16 + da->netaddr.netid_len + da->netaddr.addr_len;
+	ver_len = 20;
+
+	len = 4 + ver_len + 4 + addr_len;
+
+	p = xdr_reserve_space(xdr, len + sizeof(__be32));
+	if (!p)
+		return nfserr_resource;
+
+	/*
+	 * Fill in the overall length and number of volumes at the beginning
+	 * of the layout.
+	 */
+	*p++ = cpu_to_be32(len);
+	*p++ = cpu_to_be32(1);			/* 1 netaddr */
+	p = xdr_encode_opaque(p, da->netaddr.netid, da->netaddr.netid_len);
+	p = xdr_encode_opaque(p, da->netaddr.addr, da->netaddr.addr_len);
+
+	*p++ = cpu_to_be32(1);			/* 1 versions */
+
+	*p++ = cpu_to_be32(da->version);
+	*p++ = cpu_to_be32(da->minor_version);
+	*p++ = cpu_to_be32(da->rsize);
+	*p++ = cpu_to_be32(da->wsize);
+	*p++ = cpu_to_be32(da->tightly_coupled);
+
+	return 0;
+}

fs/nfsd/flexfilelayoutxdr.h

+/*
+ * Copyright (c) 2016 Tom Haynes <loghyr@primarydata.com>
+ */
+#ifndef _NFSD_FLEXFILELAYOUTXDR_H
+#define _NFSD_FLEXFILELAYOUTXDR_H 1
+
+#include <linux/inet.h>
+#include "xdr4.h"
+
+#define FF_FLAGS_NO_LAYOUTCOMMIT 1
+#define FF_FLAGS_NO_IO_THRU_MDS  2
+#define FF_FLAGS_NO_READ_IO      4
+
+struct xdr_stream;
+
+#define FF_NETID_LEN		(4)
+#define FF_ADDR_LEN		(INET6_ADDRSTRLEN + 8)
+struct pnfs_ff_netaddr {
+	char				netid[FF_NETID_LEN + 1];
+	char				addr[FF_ADDR_LEN + 1];
+	u32				netid_len;
+	u32				addr_len;
+};
+
+struct pnfs_ff_device_addr {
+	struct pnfs_ff_netaddr		netaddr;
+	u32				version;
+	u32				minor_version;
+	u32				rsize;
+	u32				wsize;
+	bool				tightly_coupled;
+};
+
+struct pnfs_ff_layout {
+	u32				flags;
+	u32				stats_collect_hint;
+	kuid_t				uid;
+	kgid_t				gid;
+	struct nfsd4_deviceid		deviceid;
+	stateid_t			stateid;
+	struct nfs_fh			fh;
+};
+
+__be32 nfsd4_ff_encode_getdeviceinfo(struct xdr_stream *xdr,
+		struct nfsd4_getdeviceinfo *gdp);
+__be32 nfsd4_ff_encode_layoutget(struct xdr_stream *xdr,
+		struct nfsd4_layoutget *lgp);
+
+#endif /* _NFSD_FLEXFILELAYOUTXDR_H */

fs/nfsd/nfs4layouts.c

@@ -27,6 +27,9 @@ static const struct nfsd4_callback_ops nfsd4_cb_layout_ops;
 static const struct lock_manager_operations nfsd4_layouts_lm_ops;
 
 const struct nfsd4_layout_ops *nfsd4_layout_ops[LAYOUT_TYPE_MAX] =  {
+#ifdef CONFIG_NFSD_FLEXFILELAYOUT
+	[LAYOUT_FLEX_FILES]	= &ff_layout_ops,
+#endif
 #ifdef CONFIG_NFSD_BLOCKLAYOUT
 	[LAYOUT_BLOCK_VOLUME]	= &bl_layout_ops,
 #endif
@@ -122,28 +125,35 @@ nfsd4_set_deviceid(struct nfsd4_deviceid *id, const struct svc_fh *fhp,
 
 void nfsd4_setup_layout_type(struct svc_export *exp)
 {
+#if defined(CONFIG_NFSD_BLOCKLAYOUT) || defined(CONFIG_NFSD_SCSILAYOUT)
 	struct super_block *sb = exp->ex_path.mnt->mnt_sb;
+#endif
 
 	if (!(exp->ex_flags & NFSEXP_PNFS))
 		return;
 
 	/*
-	 * Check if the file system supports exporting a block-like layout.
+	 * If flex file is configured, use it by default. Otherwise
+	 * check if the file system supports exporting a block-like layout.
 	 * If the block device supports reservations prefer the SCSI layout,
 	 * otherwise advertise the block layout.
 	 */
+#ifdef CONFIG_NFSD_FLEXFILELAYOUT
+	exp->ex_layout_types |= 1 << LAYOUT_FLEX_FILES;
+#endif
 #ifdef CONFIG_NFSD_BLOCKLAYOUT
+	/* overwrite flex file layout selection if needed */
 	if (sb->s_export_op->get_uuid &&
 	    sb->s_export_op->map_blocks &&
 	    sb->s_export_op->commit_blocks)
-		exp->ex_layout_type = LAYOUT_BLOCK_VOLUME;
+		exp->ex_layout_types |= 1 << LAYOUT_BLOCK_VOLUME;
 #endif
 #ifdef CONFIG_NFSD_SCSILAYOUT
 	/* overwrite block layout selection if needed */
 	if (sb->s_export_op->map_blocks &&
 	    sb->s_export_op->commit_blocks &&
 	    sb->s_bdev && sb->s_bdev->bd_disk->fops->pr_ops)
-		exp->ex_layout_type = LAYOUT_SCSI;
+		exp->ex_layout_types |= 1 << LAYOUT_SCSI;
 #endif
 }
 

fs/nfsd/nfs4proc.c

@@ -605,8 +605,7 @@ nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 	fh_init(&resfh, NFS4_FHSIZE);
 
-	status = fh_verify(rqstp, &cstate->current_fh, S_IFDIR,
-			   NFSD_MAY_CREATE);
+	status = fh_verify(rqstp, &cstate->current_fh, S_IFDIR, NFSD_MAY_NOP);
 	if (status)
 		return status;
 
@@ -1219,12 +1218,12 @@ nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 static const struct nfsd4_layout_ops *
 nfsd4_layout_verify(struct svc_export *exp, unsigned int layout_type)
 {
-	if (!exp->ex_layout_type) {
+	if (!exp->ex_layout_types) {
 		dprintk("%s: export does not support pNFS\n", __func__);
 		return NULL;
 	}
 
-	if (exp->ex_layout_type != layout_type) {
+	if (!(exp->ex_layout_types & (1 << layout_type))) {
 		dprintk("%s: layout type %d not supported\n",
 			__func__, layout_type);
 		return NULL;
@@ -1270,7 +1269,7 @@ nfsd4_getdeviceinfo(struct svc_rqst *rqstp,
 	nfserr = nfs_ok;
 	if (gdp->gd_maxcount != 0) {
 		nfserr = ops->proc_getdeviceinfo(exp->ex_path.mnt->mnt_sb,
-					cstate->session->se_client, gdp);
+				rqstp, cstate->session->se_client, gdp);
 	}
 
 	gdp->gd_notify_types &= ops->notify_types;
@@ -2335,6 +2334,45 @@ static struct nfsd4_operation nfsd4_ops[] = {
 	},
 };
 
+/**
+ * nfsd4_spo_must_allow - Determine if the compound op contains an
+ * operation that is allowed to be sent with machine credentials
+ *
+ * @rqstp: a pointer to the struct svc_rqst
+ *
+ * Checks to see if the compound contains a spo_must_allow op
+ * and confirms that it was sent with the proper machine creds.
+ */
+
+bool nfsd4_spo_must_allow(struct svc_rqst *rqstp)
+{
+	struct nfsd4_compoundres *resp = rqstp->rq_resp;
+	struct nfsd4_compoundargs *argp = rqstp->rq_argp;
+	struct nfsd4_op *this = &argp->ops[resp->opcnt - 1];
+	struct nfsd4_compound_state *cstate = &resp->cstate;
+	struct nfs4_op_map *allow = &cstate->clp->cl_spo_must_allow;
+	u32 opiter;
+
+	if (!cstate->minorversion)
+		return false;
+
+	if (cstate->spo_must_allowed == true)
+		return true;
+
+	opiter = resp->opcnt;
+	while (opiter < argp->opcnt) {
+		this = &argp->ops[opiter++];
+		if (test_bit(this->opnum, allow->u.longs) &&
+			cstate->clp->cl_mach_cred &&
+			nfsd4_mach_creds_match(cstate->clp, rqstp)) {
+			cstate->spo_must_allowed = true;
+			return true;
+		}
+	}
+	cstate->spo_must_allowed = false;
+	return false;
+}
+
 int nfsd4_max_reply(struct svc_rqst *rqstp, struct nfsd4_op *op)
 {
 	struct nfsd4_operation *opdesc;

fs/nfsd/nfs4state.c

@@ -1200,27 +1200,6 @@ free_ol_stateid_reaplist(struct list_head *reaplist)
 	}
 }
 
-static void release_lockowner(struct nfs4_lockowner *lo)
-{
-	struct nfs4_client *clp = lo->lo_owner.so_client;
-	struct nfs4_ol_stateid *stp;
-	struct list_head reaplist;
-
-	INIT_LIST_HEAD(&reaplist);
-
-	spin_lock(&clp->cl_lock);
-	unhash_lockowner_locked(lo);
-	while (!list_empty(&lo->lo_owner.so_stateids)) {
-		stp = list_first_entry(&lo->lo_owner.so_stateids,
-				struct nfs4_ol_stateid, st_perstateowner);
-		WARN_ON(!unhash_lock_stateid(stp));
-		put_ol_stateid_locked(stp, &reaplist);
-	}
-	spin_unlock(&clp->cl_lock);
-	free_ol_stateid_reaplist(&reaplist);
-	nfs4_put_stateowner(&lo->lo_owner);
-}
-
 static void release_open_stateid_locks(struct nfs4_ol_stateid *open_stp,
 				       struct list_head *reaplist)
 {
@@ -1972,7 +1951,7 @@ static bool svc_rqst_integrity_protected(struct svc_rqst *rqstp)
 	       service == RPC_GSS_SVC_PRIVACY;
 }
 
-static bool mach_creds_match(struct nfs4_client *cl, struct svc_rqst *rqstp)
+bool nfsd4_mach_creds_match(struct nfs4_client *cl, struct svc_rqst *rqstp)
 {
 	struct svc_cred *cr = &rqstp->rq_cred;
 
@@ -2388,6 +2367,22 @@ nfsd4_exchange_id(struct svc_rqst *rqstp,
 
 	switch (exid->spa_how) {
 	case SP4_MACH_CRED:
+		exid->spo_must_enforce[0] = 0;
+		exid->spo_must_enforce[1] = (
+			1 << (OP_BIND_CONN_TO_SESSION - 32) |
+			1 << (OP_EXCHANGE_ID - 32) |
+			1 << (OP_CREATE_SESSION - 32) |
+			1 << (OP_DESTROY_SESSION - 32) |
+			1 << (OP_DESTROY_CLIENTID - 32));
+
+		exid->spo_must_allow[0] &= (1 << (OP_CLOSE) |
+					1 << (OP_OPEN_DOWNGRADE) |
+					1 << (OP_LOCKU) |
+					1 << (OP_DELEGRETURN));
+
+		exid->spo_must_allow[1] &= (
+					1 << (OP_TEST_STATEID - 32) |
+					1 << (OP_FREE_STATEID - 32));
 		if (!svc_rqst_integrity_protected(rqstp)) {
 			status = nfserr_inval;
 			goto out_nolock;
@@ -2424,7 +2419,7 @@ nfsd4_exchange_id(struct svc_rqst *rqstp,
 				status = nfserr_inval;
 				goto out;
 			}
-			if (!mach_creds_match(conf, rqstp)) {
+			if (!nfsd4_mach_creds_match(conf, rqstp)) {
 				status = nfserr_wrong_cred;
 				goto out;
 			}
@@ -2473,6 +2468,8 @@ nfsd4_exchange_id(struct svc_rqst *rqstp,
 			goto out;
 	}
 	new->cl_minorversion = cstate->minorversion;
+	new->cl_spo_must_allow.u.words[0] = exid->spo_must_allow[0];
+	new->cl_spo_must_allow.u.words[1] = exid->spo_must_allow[1];
 
 	gen_clid(new, nn);
 	add_to_unconfirmed(new);
@@ -2676,7 +2673,7 @@ nfsd4_create_session(struct svc_rqst *rqstp,
 
 	if (conf) {
 		status = nfserr_wrong_cred;
-		if (!mach_creds_match(conf, rqstp))
+		if (!nfsd4_mach_creds_match(conf, rqstp))
 			goto out_free_conn;
 		cs_slot = &conf->cl_cs_slot;
 		status = check_slot_seqid(cr_ses->seqid, cs_slot->sl_seqid, 0);
@@ -2692,7 +2689,7 @@ nfsd4_create_session(struct svc_rqst *rqstp,
 			goto out_free_conn;
 		}
 		status = nfserr_wrong_cred;
-		if (!mach_creds_match(unconf, rqstp))
+		if (!nfsd4_mach_creds_match(unconf, rqstp))
 			goto out_free_conn;
 		cs_slot = &unconf->cl_cs_slot;
 		status = check_slot_seqid(cr_ses->seqid, cs_slot->sl_seqid, 0);
@@ -2801,7 +2798,7 @@ __be32 nfsd4_bind_conn_to_session(struct svc_rqst *rqstp,
 	if (!session)
 		goto out_no_session;
 	status = nfserr_wrong_cred;
-	if (!mach_creds_match(session->se_client, rqstp))
+	if (!nfsd4_mach_creds_match(session->se_client, rqstp))
 		goto out;
 	status = nfsd4_map_bcts_dir(&bcts->dir);
 	if (status)
@@ -2848,7 +2845,7 @@ nfsd4_destroy_session(struct svc_rqst *r,
 	if (!ses)
 		goto out_client_lock;
 	status = nfserr_wrong_cred;
-	if (!mach_creds_match(ses->se_client, r))
+	if (!nfsd4_mach_creds_match(ses->se_client, r))
 		goto out_put_session;
 	status = mark_session_dead_locked(ses, 1 + ref_held_by_me);
 	if (status)
@@ -3087,7 +3084,7 @@ nfsd4_destroy_clientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *csta
 		status = nfserr_stale_clientid;
 		goto out;
 	}
-	if (!mach_creds_match(clp, rqstp)) {
+	if (!nfsd4_mach_creds_match(clp, rqstp)) {
 		clp = NULL;
 		status = nfserr_wrong_cred;
 		goto out;
@@ -3112,7 +3109,7 @@ nfsd4_reclaim_complete(struct svc_rqst *rqstp, struct nfsd4_compound_state *csta
 		 * We don't take advantage of the rca_one_fs case.
 		 * That's OK, it's optional, we can safely ignore it.
 		 */
-		 return nfs_ok;
+		return nfs_ok;
 	}
 
 	status = nfserr_complete_already;
@@ -5945,6 +5942,7 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp,
 	__be32 status;
 	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
 	struct nfs4_client *clp;
+	LIST_HEAD (reaplist);
 
 	dprintk("nfsd4_release_lockowner clientid: (%08x/%08x):\n",
 		clid->cl_boot, clid->cl_id);
@@ -5975,9 +5973,23 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp,
 		nfs4_get_stateowner(sop);
 		break;
 	}
+	if (!lo) {
+		spin_unlock(&clp->cl_lock);
+		return status;
+	}
+
+	unhash_lockowner_locked(lo);
+	while (!list_empty(&lo->lo_owner.so_stateids)) {
+		stp = list_first_entry(&lo->lo_owner.so_stateids,
+				       struct nfs4_ol_stateid,
+				       st_perstateowner);
+		WARN_ON(!unhash_lock_stateid(stp));
+		put_ol_stateid_locked(stp, &reaplist);
+	}
 	spin_unlock(&clp->cl_lock);
-	if (lo)
-		release_lockowner(lo);
+	free_ol_stateid_reaplist(&reaplist);
+	nfs4_put_stateowner(&lo->lo_owner);
+
 	return status;
 }
 

fs/nfsd/nfs4xdr.c

@@ -1299,16 +1299,14 @@ nfsd4_decode_exchange_id(struct nfsd4_compoundargs *argp,
 		break;
 	case SP4_MACH_CRED:
 		/* spo_must_enforce */
-		READ_BUF(4);
-		dummy = be32_to_cpup(p++);
-		READ_BUF(dummy * 4);
-		p += dummy;
-
+		status = nfsd4_decode_bitmap(argp,
+					exid->spo_must_enforce);
+		if (status)
+			goto out;
 		/* spo_must_allow */
-		READ_BUF(4);
-		dummy = be32_to_cpup(p++);
-		READ_BUF(dummy * 4);
-		p += dummy;
+		status = nfsd4_decode_bitmap(argp, exid->spo_must_allow);
+		if (status)
+			goto out;
 		break;
 	case SP4_SSV:
 		/* ssp_ops */
@@ -2164,22 +2162,20 @@ nfsd4_encode_aclname(struct xdr_stream *xdr, struct svc_rqst *rqstp,
 }
 
 static inline __be32
-nfsd4_encode_layout_type(struct xdr_stream *xdr, enum pnfs_layouttype layout_type)
+nfsd4_encode_layout_types(struct xdr_stream *xdr, u32 layout_types)
 {
-	__be32 *p;
+	__be32		*p;
+	unsigned long	i = hweight_long(layout_types);
 
-	if (layout_type) {
-		p = xdr_reserve_space(xdr, 8);
-		if (!p)
-			return nfserr_resource;
-		*p++ = cpu_to_be32(1);
-		*p++ = cpu_to_be32(layout_type);
-	} else {
-		p = xdr_reserve_space(xdr, 4);
-		if (!p)
-			return nfserr_resource;
-		*p++ = cpu_to_be32(0);
-	}
+	p = xdr_reserve_space(xdr, 4 + 4 * i);
+	if (!p)
+		return nfserr_resource;
+
+	*p++ = cpu_to_be32(i);
+
+	for (i = LAYOUT_NFSV4_1_FILES; i < LAYOUT_TYPE_MAX; ++i)
+		if (layout_types & (1 << i))
+			*p++ = cpu_to_be32(i);
 
 	return 0;
 }
@@ -2754,13 +2750,13 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp,
 	}
 #ifdef CONFIG_NFSD_PNFS
 	if (bmval1 & FATTR4_WORD1_FS_LAYOUT_TYPES) {
-		status = nfsd4_encode_layout_type(xdr, exp->ex_layout_type);
+		status = nfsd4_encode_layout_types(xdr, exp->ex_layout_types);
 		if (status)
 			goto out;
 	}
 
 	if (bmval2 & FATTR4_WORD2_LAYOUT_TYPES) {
-		status = nfsd4_encode_layout_type(xdr, exp->ex_layout_type);
+		status = nfsd4_encode_layout_types(xdr, exp->ex_layout_types);
 		if (status)
 			goto out;
 	}
@@ -3867,14 +3863,6 @@ nfsd4_encode_write(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_w
 	return nfserr;
 }
 
-static const u32 nfs4_minimal_spo_must_enforce[2] = {
-	[1] = 1 << (OP_BIND_CONN_TO_SESSION - 32) |
-	      1 << (OP_EXCHANGE_ID - 32) |
-	      1 << (OP_CREATE_SESSION - 32) |
-	      1 << (OP_DESTROY_SESSION - 32) |
-	      1 << (OP_DESTROY_CLIENTID - 32)
-};
-
 static __be32
 nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr,
 			 struct nfsd4_exchange_id *exid)
@@ -3885,6 +3873,7 @@ nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr,
 	char *server_scope;
 	int major_id_sz;
 	int server_scope_sz;
+	int status = 0;
 	uint64_t minor_id = 0;
 
 	if (nfserr)
@@ -3913,18 +3902,20 @@ nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr,
 	case SP4_NONE:
 		break;
 	case SP4_MACH_CRED:
-		/* spo_must_enforce, spo_must_allow */
-		p = xdr_reserve_space(xdr, 16);
-		if (!p)
-			return nfserr_resource;
-
 		/* spo_must_enforce bitmap: */
-		*p++ = cpu_to_be32(2);
-		*p++ = cpu_to_be32(nfs4_minimal_spo_must_enforce[0]);
-		*p++ = cpu_to_be32(nfs4_minimal_spo_must_enforce[1]);
-		/* empty spo_must_allow bitmap: */
-		*p++ = cpu_to_be32(0);
-
+		status = nfsd4_encode_bitmap(xdr,
+					exid->spo_must_enforce[0],
+					exid->spo_must_enforce[1],
+					exid->spo_must_enforce[2]);
+		if (status)
+			goto out;
+		/* spo_must_allow bitmap: */
+		status = nfsd4_encode_bitmap(xdr,
+					exid->spo_must_allow[0],
+					exid->spo_must_allow[1],
+					exid->spo_must_allow[2]);
+		if (status)
+			goto out;
 		break;
 	default:
 		WARN_ON_ONCE(1);
@@ -3951,6 +3942,8 @@ nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr,
 	/* Implementation id */
 	*p++ = cpu_to_be32(0);	/* zero length nfs_impl_id4 array */
 	return 0;
+out:
+	return status;
 }
 
 static __be32

fs/nfsd/nfsd.h

@@ -124,6 +124,7 @@ void nfs4_state_shutdown_net(struct net *net);
 void nfs4_reset_lease(time_t leasetime);
 int nfs4_reset_recoverydir(char *recdir);
 char * nfs4_recoverydir(void);
+bool nfsd4_spo_must_allow(struct svc_rqst *rqstp);
 #else
 static inline int nfsd4_init_slabs(void) { return 0; }
 static inline void nfsd4_free_slabs(void) { }
@@ -134,6 +135,10 @@ static inline void nfs4_state_shutdown_net(struct net *net) { }
 static inline void nfs4_reset_lease(time_t leasetime) { }
 static inline int nfs4_reset_recoverydir(char *recdir) { return 0; }
 static inline char * nfs4_recoverydir(void) {return NULL; }
+static inline bool nfsd4_spo_must_allow(struct svc_rqst *rqstp)
+{
+	return false;
+}
 #endif
 
 /*

fs/nfsd/nfsfh.c

@@ -59,14 +59,20 @@ static int nfsd_acceptable(void *expv, struct dentry *dentry)
  * the write call).
  */
 static inline __be32
-nfsd_mode_check(struct svc_rqst *rqstp, umode_t mode, umode_t requested)
+nfsd_mode_check(struct svc_rqst *rqstp, struct dentry *dentry,
+		umode_t requested)
 {
-	mode &= S_IFMT;
+	umode_t mode = d_inode(dentry)->i_mode & S_IFMT;
 
 	if (requested == 0) /* the caller doesn't care */
 		return nfs_ok;
-	if (mode == requested)
+	if (mode == requested) {
+		if (mode == S_IFDIR && !d_can_lookup(dentry)) {
+			WARN_ON_ONCE(1);
+			return nfserr_notdir;
+		}
 		return nfs_ok;
+	}
 	/*
 	 * v4 has an error more specific than err_notdir which we should
 	 * return in preference to err_notdir:
@@ -298,7 +304,7 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp)
  * that it expects something not of the given type.
  *
  * @access is formed from the NFSD_MAY_* constants defined in
- * include/linux/nfsd/nfsd.h.
+ * fs/nfsd/vfs.h.
  */
 __be32
 fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int access)
@@ -340,7 +346,7 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int access)
 	if (error)
 		goto out;
 
-	error = nfsd_mode_check(rqstp, d_inode(dentry)->i_mode, type);
+	error = nfsd_mode_check(rqstp, dentry, type);
 	if (error)
 		goto out;
 
@@ -533,7 +539,7 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry,
 	 * the reference filehandle (if it is in the same export)
 	 * or the export options.
 	 */
-	 set_version_and_fsid_type(fhp, exp, ref_fh);
+	set_version_and_fsid_type(fhp, exp, ref_fh);
 
 	if (ref_fh == fhp)
 		fh_put(ref_fh);

fs/nfsd/nfsproc.c

@@ -251,9 +251,6 @@ nfsd_proc_create(struct svc_rqst *rqstp, struct nfsd_createargs *argp,
 
 	/* Check for NFSD_MAY_WRITE in nfsd_create if necessary */
 
-	nfserr = nfserr_acces;
-	if (!argp->len)
-		goto done;
 	nfserr = nfserr_exist;
 	if (isdotent(argp->name, argp->len))
 		goto done;
@@ -362,8 +359,8 @@ nfsd_proc_create(struct svc_rqst *rqstp, struct nfsd_createargs *argp,
 	nfserr = 0;
 	if (!inode) {
 		/* File doesn't exist. Create it and set attrs */
-		nfserr = nfsd_create(rqstp, dirfhp, argp->name, argp->len,
-					attr, type, rdev, newfhp);
+		nfserr = nfsd_create_locked(rqstp, dirfhp, argp->name,
+					argp->len, attr, type, rdev, newfhp);
 	} else if (type == S_IFREG) {
 		dprintk("nfsd:   existing %s, valid=%x, size=%ld\n",
 			argp->name, attr->ia_valid, (long) attr->ia_size);

fs/nfsd/nfsxdr.c

@@ -240,7 +240,7 @@ nfssvc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p,
 	 || !(p = decode_filename(p, &args->name, &args->len)))
 		return 0;
 
-	 return xdr_argsize_check(rqstp, p);
+	return xdr_argsize_check(rqstp, p);
 }
 
 int

fs/nfsd/pnfs.h

@@ -21,6 +21,7 @@ struct nfsd4_layout_ops {
 	u32		notify_types;
 
 	__be32 (*proc_getdeviceinfo)(struct super_block *sb,
+			struct svc_rqst *rqstp,
 			struct nfs4_client *clp,
 			struct nfsd4_getdeviceinfo *gdevp);
 	__be32 (*encode_getdeviceinfo)(struct xdr_stream *xdr,
@@ -44,6 +45,9 @@ extern const struct nfsd4_layout_ops bl_layout_ops;
 #ifdef CONFIG_NFSD_SCSILAYOUT
 extern const struct nfsd4_layout_ops scsi_layout_ops;
 #endif
+#ifdef CONFIG_NFSD_FLEXFILELAYOUT
+extern const struct nfsd4_layout_ops ff_layout_ops;
+#endif
 
 __be32 nfsd4_preprocess_layout_stateid(struct svc_rqst *rqstp,
 		struct nfsd4_compound_state *cstate, stateid_t *stateid,