Merge branch 'for-3.20' of git://linux-nfs.org/~bfields/linux

Pull nfsd updates from Bruce Fields:
 "The main change is the pNFS block server support from Christoph, which
  allows an NFS client connected to shared disk to do block IO to the
  shared disk in place of NFS reads and writes.  This also requires xfs
  patches, which should arrive soon through the xfs tree, barring
  unexpected problems.  Support for other filesystems is also possible
  if there's interest.

  Thanks also to Chuck Lever for continuing work to get NFS/RDMA into
  shape"

* 'for-3.20' of git://linux-nfs.org/~bfields/linux: (32 commits)
  nfsd: default NFSv4.2 to on
  nfsd: pNFS block layout driver
  exportfs: add methods for block layout exports
  nfsd: add trace events
  nfsd: update documentation for pNFS support
  nfsd: implement pNFS layout recalls
  nfsd: implement pNFS operations
  nfsd: make find_any_file available outside nfs4state.c
  nfsd: make find/get/put file available outside nfs4state.c
  nfsd: make lookup/alloc/unhash_stid available outside nfs4state.c
  nfsd: add fh_fsid_match helper
  nfsd: move nfsd_fh_match to nfsfh.h
  fs: add FL_LAYOUT lease type
  fs: track fl_owner for leases
  nfs: add LAYOUT_TYPE_MAX enum value
  nfsd: factor out a helper to decode nfstime4 values
  sunrpc/lockd: fix references to the BKL
  nfsd: fix year-2038 nfs4 state problem
  svcrdma: Handle additional inline content
  svcrdma: Move read list XDR round-up logic
  ...

40 files changed, 2562 insertions, 254 deletions

diff --git a/Documentation/filesystems/nfs/nfs41-server.txt b/Documentation/filesystems/nfs/nfs41-server.txt
index c49cd7e796e7..682a59fabe3f 100644
--- a/Documentation/filesystems/nfs/nfs41-server.txt
+++ b/Documentation/filesystems/nfs/nfs41-server.txt
@@ -24,11 +24,6 @@ focuses on the mandatory-to-implement NFSv4.1 Sessions, providing
 "exactly once" semantics and better control and throttling of the
 resources allocated for each client.
 
-Other NFSv4.1 features, Parallel NFS operations in particular,
-are still under development out of tree.
-See http://wiki.linux-nfs.org/wiki/index.php/PNFS_prototype_design
-for more information.
-
 The table below, taken from the NFSv4.1 document, lists
 the operations that are mandatory to implement (REQ), optional
 (OPT), and NFSv4.0 operations that are required not to implement (MNI)
@@ -43,9 +38,7 @@ The OPTIONAL features identified and their abbreviations are as follows:
 The following abbreviations indicate the linux server implementation status.
 	I	Implemented NFSv4.1 operations.
 	NS	Not Supported.
-	NS*	unimplemented optional feature.
-	P	pNFS features implemented out of tree.
-	PNS	pNFS features that are not supported yet (out of tree).
+	NS*	Unimplemented optional feature.
 
 Operations
 
@@ -70,13 +63,13 @@ I  | DESTROY_SESSION      | REQ        |              | Section 18.37  |
 I  | EXCHANGE_ID          | REQ        |              | Section 18.35  |
 I  | FREE_STATEID         | REQ        |              | Section 18.38  |
    | GETATTR              | REQ        |              | Section 18.7   |
-P  | GETDEVICEINFO        | OPT        | pNFS (REQ)   | Section 18.40  |
-P  | GETDEVICELIST        | OPT        | pNFS (OPT)   | Section 18.41  |
+I  | GETDEVICEINFO        | OPT        | pNFS (REQ)   | Section 18.40  |
+NS*| GETDEVICELIST        | OPT        | pNFS (OPT)   | Section 18.41  |
    | GETFH                | REQ        |              | Section 18.8   |
 NS*| GET_DIR_DELEGATION   | OPT        | DDELG (REQ)  | Section 18.39  |
-P  | LAYOUTCOMMIT         | OPT        | pNFS (REQ)   | Section 18.42  |
-P  | LAYOUTGET            | OPT        | pNFS (REQ)   | Section 18.43  |
-P  | LAYOUTRETURN         | OPT        | pNFS (REQ)   | Section 18.44  |
+I  | LAYOUTCOMMIT         | OPT        | pNFS (REQ)   | Section 18.42  |
+I  | LAYOUTGET            | OPT        | pNFS (REQ)   | Section 18.43  |
+I  | LAYOUTRETURN         | OPT        | pNFS (REQ)   | Section 18.44  |
    | LINK                 | OPT        |              | Section 18.9   |
    | LOCK                 | REQ        |              | Section 18.10  |
    | LOCKT                | REQ        |              | Section 18.11  |
@@ -122,9 +115,9 @@ Callback Operations
    |                         | MNI       | or OPT)     |               |
    +-------------------------+-----------+-------------+---------------+
    | CB_GETATTR              | OPT       | FDELG (REQ) | Section 20.1  |
-P  | CB_LAYOUTRECALL         | OPT       | pNFS (REQ)  | Section 20.3  |
+I  | CB_LAYOUTRECALL         | OPT       | pNFS (REQ)  | Section 20.3  |
 NS*| CB_NOTIFY               | OPT       | DDELG (REQ) | Section 20.4  |
-P  | CB_NOTIFY_DEVICEID      | OPT       | pNFS (OPT)  | Section 20.12 |
+NS*| CB_NOTIFY_DEVICEID      | OPT       | pNFS (OPT)  | Section 20.12 |
 NS*| CB_NOTIFY_LOCK          | OPT       |             | Section 20.11 |
 NS*| CB_PUSH_DELEG           | OPT       | FDELG (OPT) | Section 20.5  |
    | CB_RECALL               | OPT       | FDELG,      | Section 20.2  |
diff --git a/Documentation/filesystems/nfs/pnfs-block-server.txt b/Documentation/filesystems/nfs/pnfs-block-server.txt
new file mode 100644
index 000000000000..2143673cf154
--- /dev/null
+++ b/Documentation/filesystems/nfs/pnfs-block-server.txt
@@ -0,0 +1,37 @@
+pNFS block layout server user guide
+
+The Linux NFS server now supports the pNFS block layout extension.  In this
+case the NFS server acts as Metadata Server (MDS) for pNFS, which in addition
+to handling all the metadata access to the NFS export also hands out layouts
+to the clients to directly access the underlying block devices that are
+shared with the client.
+
+To use pNFS block layouts with with the Linux NFS server the exported file
+system needs to support the pNFS block layouts (currently just XFS), and the
+file system must sit on shared storage (typically iSCSI) that is accessible
+to the clients in addition to the MDS.  As of now the file system needs to
+sit directly on the exported volume, striping or concatenation of
+volumes on the MDS and clients is not supported yet.
+
+On the server, pNFS block volume support is automatically if the file system
+support it.  On the client make sure the kernel has the CONFIG_PNFS_BLOCK
+option enabled, the blkmapd daemon from nfs-utils is running, and the
+file system is mounted using the NFSv4.1 protocol version (mount -o vers=4.1).
+
+If the nfsd server needs to fence a non-responding client it calls
+/sbin/nfsd-recall-failed with the first argument set to the IP address of
+the client, and the second argument set to the device node without the /dev
+prefix for the file system to be fenced. Below is an example file that shows
+how to translate the device into a serial number from SCSI EVPD 0x80:
+
+cat > /sbin/nfsd-recall-failed << EOF
+#!/bin/sh
+
+CLIENT="$1"
+DEV="/dev/$2"
+EVPD=`sg_inq --page=0x80 ${DEV} | \
+	grep "Unit serial number:" | \
+	awk -F ': ' '{print $2}'`
+
+echo "fencing client ${CLIENT} serial ${EVPD}" >> /var/log/pnfsd-fence.log
+EOF
diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
index 56598742dde4..5581e020644b 100644
--- a/fs/lockd/svclock.c
+++ b/fs/lockd/svclock.c
@@ -57,8 +57,8 @@ static DEFINE_SPINLOCK(nlm_blocked_lock);
 static const char *nlmdbg_cookie2a(const struct nlm_cookie *cookie)
 {
 	/*
-	 * We can get away with a static buffer because we're only
-	 * called with BKL held.
+	 * We can get away with a static buffer because this is only called
+	 * from lockd, which is single-threaded.
 	 */
 	static char buf[2*NLM_MAXCOOKIELEN+1];
 	unsigned int i, len = sizeof(buf);
diff --git a/fs/lockd/xdr.c b/fs/lockd/xdr.c
index 9340e7e10ef6..5b651daad518 100644
--- a/fs/lockd/xdr.c
+++ b/fs/lockd/xdr.c
@@ -95,14 +95,6 @@ nlm_decode_fh(__be32 *p, struct nfs_fh *f)
 	return p + XDR_QUADLEN(NFS2_FHSIZE);
 }
 
-static inline __be32 *
-nlm_encode_fh(__be32 *p, struct nfs_fh *f)
-{
-	*p++ = htonl(NFS2_FHSIZE);
-	memcpy(p, f->data, NFS2_FHSIZE);
-	return p + XDR_QUADLEN(NFS2_FHSIZE);
-}
-
 /*
  * Encode and decode owner handle
  */
diff --git a/fs/locks.c b/fs/locks.c
index 4d0d41163a50..4753218f308e 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -137,7 +137,7 @@
 
 #define IS_POSIX(fl)	(fl->fl_flags & FL_POSIX)
 #define IS_FLOCK(fl)	(fl->fl_flags & FL_FLOCK)
-#define IS_LEASE(fl)	(fl->fl_flags & (FL_LEASE|FL_DELEG))
+#define IS_LEASE(fl)	(fl->fl_flags & (FL_LEASE|FL_DELEG|FL_LAYOUT))
 #define IS_OFDLCK(fl)	(fl->fl_flags & FL_OFDLCK)
 
 static bool lease_breaking(struct file_lock *fl)
@@ -1371,6 +1371,8 @@ static void time_out_leases(struct inode *inode, struct list_head *dispose)
 
 static bool leases_conflict(struct file_lock *lease, struct file_lock *breaker)
 {
+	if ((breaker->fl_flags & FL_LAYOUT) != (lease->fl_flags & FL_LAYOUT))
+		return false;
 	if ((breaker->fl_flags & FL_DELEG) && (lease->fl_flags & FL_LEASE))
 		return false;
 	return locks_conflict(breaker, lease);
@@ -1594,11 +1596,14 @@ int fcntl_getlease(struct file *filp)
  * conflict with the lease we're trying to set.
  */
 static int
-check_conflicting_open(const struct dentry *dentry, const long arg)
+check_conflicting_open(const struct dentry *dentry, const long arg, int flags)
 {
 	int ret = 0;
 	struct inode *inode = dentry->d_inode;
 
+	if (flags & FL_LAYOUT)
+		return 0;
+
 	if ((arg == F_RDLCK) && (atomic_read(&inode->i_writecount) > 0))
 		return -EAGAIN;
 
@@ -1647,7 +1652,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
 
 	spin_lock(&ctx->flc_lock);
 	time_out_leases(inode, &dispose);
-	error = check_conflicting_open(dentry, arg);
+	error = check_conflicting_open(dentry, arg, lease->fl_flags);
 	if (error)
 		goto out;
 
@@ -1661,7 +1666,8 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
 	 */
 	error = -EAGAIN;
 	list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
-		if (fl->fl_file == filp) {
+		if (fl->fl_file == filp &&
+		    fl->fl_owner == lease->fl_owner) {
 			my_fl = fl;
 			continue;
 		}
@@ -1702,7 +1708,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
 	 * precedes these checks.
 	 */
 	smp_mb();
-	error = check_conflicting_open(dentry, arg);
+	error = check_conflicting_open(dentry, arg, lease->fl_flags);
 	if (error) {
 		locks_unlink_lock_ctx(lease, &ctx->flc_lease_cnt);
 		goto out;
@@ -1721,7 +1727,7 @@ out:
 	return error;
 }
 
-static int generic_delete_lease(struct file *filp)
+static int generic_delete_lease(struct file *filp, void *owner)
 {
 	int error = -EAGAIN;
 	struct file_lock *fl, *victim = NULL;
@@ -1737,7 +1743,8 @@ static int generic_delete_lease(struct file *filp)
 
 	spin_lock(&ctx->flc_lock);
 	list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
-		if (fl->fl_file == filp) {
+		if (fl->fl_file == filp &&
+		    fl->fl_owner == owner) {
 			victim = fl;
 			break;
 		}
@@ -1778,13 +1785,14 @@ int generic_setlease(struct file *filp, long arg, struct file_lock **flp,
 
 	switch (arg) {
 	case F_UNLCK:
-		return generic_delete_lease(filp);
+		return generic_delete_lease(filp, *priv);
 	case F_RDLCK:
 	case F_WRLCK:
 		if (!(*flp)->fl_lmops->lm_break) {
 			WARN_ON_ONCE(1);
 			return -ENOLCK;
 		}
+
 		return generic_add_lease(filp, arg, flp, priv);
 	default:
 		return -EINVAL;
@@ -1857,7 +1865,7 @@ static int do_fcntl_add_lease(unsigned int fd, struct file *filp, long arg)
 int fcntl_setlease(unsigned int fd, struct file *filp, long arg)
 {
 	if (arg == F_UNLCK)
-		return vfs_setlease(filp, F_UNLCK, NULL, NULL);
+		return vfs_setlease(filp, F_UNLCK, NULL, (void **)&filp);
 	return do_fcntl_add_lease(fd, filp, arg);
 }
 
diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index 73395156bdb4..683bf718aead 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -82,6 +82,16 @@ config NFSD_V4
 
 	  If unsure, say N.
 
+config NFSD_PNFS
+	bool "NFSv4.1 server support for Parallel NFS (pNFS)"
+	depends on NFSD_V4
+	help
+	  This option enables support for the parallel NFS features of the
+	  minor version 1 of the NFSv4 protocol (RFC5661) in the kernel's NFS
+	  server.
+
+	  If unsure, say N.
+
 config NFSD_V4_SECURITY_LABEL
 	bool "Provide Security Label support for NFSv4 server"
 	depends on NFSD_V4 && SECURITY
diff --git a/fs/nfsd/Makefile b/fs/nfsd/Makefile
index af32ef06b4fe..9a6028e120c6 100644
--- a/fs/nfsd/Makefile
+++ b/fs/nfsd/Makefile
@@ -2,9 +2,14 @@
 # Makefile for the Linux nfs server
 #
 
+ccflags-y += -I$(src)			# needed for trace events
+
 obj-$(CONFIG_NFSD)	+= nfsd.o
 
-nfsd-y 			:= nfssvc.o nfsctl.o nfsproc.o nfsfh.o vfs.o \
+# this one should be compiled first, as the tracing macros can easily blow up
+nfsd-y			+= trace.o
+
+nfsd-y 			+= nfssvc.o nfsctl.o nfsproc.o nfsfh.o vfs.o \
 			   export.o auth.o lockd.o nfscache.o nfsxdr.o stats.o
 nfsd-$(CONFIG_NFSD_FAULT_INJECTION) += fault_inject.o
 nfsd-$(CONFIG_NFSD_V2_ACL) += nfs2acl.o
@@ -12,3 +17,4 @@ nfsd-$(CONFIG_NFSD_V3)	+= nfs3proc.o nfs3xdr.o
 nfsd-$(CONFIG_NFSD_V3_ACL) += nfs3acl.o
 nfsd-$(CONFIG_NFSD_V4)	+= nfs4proc.o nfs4xdr.o nfs4state.o nfs4idmap.o \
 			   nfs4acl.o nfs4callback.o nfs4recover.o
+nfsd-$(CONFIG_NFSD_PNFS) += nfs4layouts.o blocklayout.o blocklayoutxdr.o
diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c
new file mode 100644
index 000000000000..cdbc78c72542
--- /dev/null
+++ b/fs/nfsd/blocklayout.c
@@ -0,0 +1,189 @@
+/*
+ * Copyright (c) 2014 Christoph Hellwig.
+ */
+#include <linux/exportfs.h>
+#include <linux/genhd.h>
+#include <linux/slab.h>
+
+#include <linux/nfsd/debug.h>
+
+#include "blocklayoutxdr.h"
+#include "pnfs.h"
+
+#define NFSDDBG_FACILITY	NFSDDBG_PNFS
+
+
+static int
+nfsd4_block_get_device_info_simple(struct super_block *sb,
+		struct nfsd4_getdeviceinfo *gdp)
+{
+	struct pnfs_block_deviceaddr *dev;
+	struct pnfs_block_volume *b;
+
+	dev = kzalloc(sizeof(struct pnfs_block_deviceaddr) +
+		      sizeof(struct pnfs_block_volume), GFP_KERNEL);
+	if (!dev)
+		return -ENOMEM;
+	gdp->gd_device = dev;
+
+	dev->nr_volumes = 1;
+	b = &dev->volumes[0];
+
+	b->type = PNFS_BLOCK_VOLUME_SIMPLE;
+	b->simple.sig_len = PNFS_BLOCK_UUID_LEN;
+	return sb->s_export_op->get_uuid(sb, b->simple.sig, &b->simple.sig_len,
+			&b->simple.offset);
+}
+
+static __be32
+nfsd4_block_proc_getdeviceinfo(struct super_block *sb,
+		struct nfsd4_getdeviceinfo *gdp)
+{
+	if (sb->s_bdev != sb->s_bdev->bd_contains)
+		return nfserr_inval;
+	return nfserrno(nfsd4_block_get_device_info_simple(sb, gdp));
+}
+
+static __be32
+nfsd4_block_proc_layoutget(struct inode *inode, const struct svc_fh *fhp,
+		struct nfsd4_layoutget *args)
+{
+	struct nfsd4_layout_seg *seg = &args->lg_seg;
+	struct super_block *sb = inode->i_sb;
+	u32 block_size = (1 << inode->i_blkbits);
+	struct pnfs_block_extent *bex;
+	struct iomap iomap;
+	u32 device_generation = 0;
+	int error;
+
+	/*
+	 * We do not attempt to support I/O smaller than the fs block size,
+	 * or not aligned to it.
+	 */
+	if (args->lg_minlength < block_size) {
+		dprintk("pnfsd: I/O too small\n");
+		goto out_layoutunavailable;
+	}
+	if (seg->offset & (block_size - 1)) {
+		dprintk("pnfsd: I/O misaligned\n");
+		goto out_layoutunavailable;
+	}
+
+	/*
+	 * Some clients barf on non-zero block numbers for NONE or INVALID
+	 * layouts, so make sure to zero the whole structure.
+	 */
+	error = -ENOMEM;
+	bex = kzalloc(sizeof(*bex), GFP_KERNEL);
+	if (!bex)
+		goto out_error;
+	args->lg_content = bex;
+
+	error = sb->s_export_op->map_blocks(inode, seg->offset, seg->length,
+					    &iomap, seg->iomode != IOMODE_READ,
+					    &device_generation);
+	if (error) {
+		if (error == -ENXIO)
+			goto out_layoutunavailable;
+		goto out_error;
+	}
+
+	if (iomap.length < args->lg_minlength) {
+		dprintk("pnfsd: extent smaller than minlength\n");
+		goto out_layoutunavailable;
+	}
+
+	switch (iomap.type) {
+	case IOMAP_MAPPED:
+		if (seg->iomode == IOMODE_READ)
+			bex->es = PNFS_BLOCK_READ_DATA;
+		else
+			bex->es = PNFS_BLOCK_READWRITE_DATA;
+		bex->soff = (iomap.blkno << 9);
+		break;
+	case IOMAP_UNWRITTEN:
+		if (seg->iomode & IOMODE_RW) {
+			/*
+			 * Crack monkey special case from section 2.3.1.
+			 */
+			if (args->lg_minlength == 0) {
+				dprintk("pnfsd: no soup for you!\n");
+				goto out_layoutunavailable;
+			}
+
+			bex->es = PNFS_BLOCK_INVALID_DATA;
+			bex->soff = (iomap.blkno << 9);
+			break;
+		}
+		/*FALLTHRU*/
+	case IOMAP_HOLE:
+		if (seg->iomode == IOMODE_READ) {
+			bex->es = PNFS_BLOCK_NONE_DATA;
+			break;
+		}
+		/*FALLTHRU*/
+	case IOMAP_DELALLOC:
+	default:
+		WARN(1, "pnfsd: filesystem returned %d extent\n", iomap.type);
+		goto out_layoutunavailable;
+	}
+
+	error = nfsd4_set_deviceid(&bex->vol_id, fhp, device_generation);
+	if (error)
+		goto out_error;
+	bex->foff = iomap.offset;
+	bex->len = iomap.length;
+
+	seg->offset = iomap.offset;
+	seg->length = iomap.length;
+
+	dprintk("GET: %lld:%lld %d\n", bex->foff, bex->len, bex->es);
+	return 0;
+
+out_error:
+	seg->length = 0;
+	return nfserrno(error);
+out_layoutunavailable:
+	seg->length = 0;
+	return nfserr_layoutunavailable;
+}
+
+static __be32
+nfsd4_block_proc_layoutcommit(struct inode *inode,
+		struct nfsd4_layoutcommit *lcp)
+{
+	loff_t new_size = lcp->lc_last_wr + 1;
+	struct iattr iattr = { .ia_valid = 0 };
+	struct iomap *iomaps;
+	int nr_iomaps;
+	int error;
+
+	nr_iomaps = nfsd4_block_decode_layoutupdate(lcp->lc_up_layout,
+			lcp->lc_up_len, &iomaps, 1 << inode->i_blkbits);
+	if (nr_iomaps < 0)
+		return nfserrno(nr_iomaps);
+
+	if (lcp->lc_mtime.tv_nsec == UTIME_NOW ||
+	    timespec_compare(&lcp->lc_mtime, &inode->i_mtime) < 0)
+		lcp->lc_mtime = current_fs_time(inode->i_sb);
+	iattr.ia_valid |= ATTR_ATIME | ATTR_CTIME | ATTR_MTIME;
+	iattr.ia_atime = iattr.ia_ctime = iattr.ia_mtime = lcp->lc_mtime;
+
+	if (new_size > i_size_read(inode)) {
+		iattr.ia_valid |= ATTR_SIZE;
+		iattr.ia_size = new_size;
+	}
+
+	error = inode->i_sb->s_export_op->commit_blocks(inode, iomaps,
+			nr_iomaps, &iattr);
+	kfree(iomaps);
+	return nfserrno(error);
+}
+
+const struct nfsd4_layout_ops bl_layout_ops = {
+	.proc_getdeviceinfo	= nfsd4_block_proc_getdeviceinfo,
+	.encode_getdeviceinfo	= nfsd4_block_encode_getdeviceinfo,
+	.proc_layoutget		= nfsd4_block_proc_layoutget,
+	.encode_layoutget	= nfsd4_block_encode_layoutget,
+	.proc_layoutcommit	= nfsd4_block_proc_layoutcommit,
+};
diff --git a/fs/nfsd/blocklayoutxdr.c b/fs/nfsd/blocklayoutxdr.c
new file mode 100644
index 000000000000..9da89fddab33
--- /dev/null
+++ b/fs/nfsd/blocklayoutxdr.c
@@ -0,0 +1,157 @@
+/*
+ * Copyright (c) 2014 Christoph Hellwig.
+ */
+#include <linux/sunrpc/svc.h>
+#include <linux/exportfs.h>
+#include <linux/nfs4.h>
+
+#include "nfsd.h"
+#include "blocklayoutxdr.h"
+
+#define NFSDDBG_FACILITY	NFSDDBG_PNFS
+
+
+__be32
+nfsd4_block_encode_layoutget(struct xdr_stream *xdr,
+		struct nfsd4_layoutget *lgp)
+{
+	struct pnfs_block_extent *b = lgp->lg_content;
+	int len = sizeof(__be32) + 5 * sizeof(__be64) + sizeof(__be32);
+	__be32 *p;
+
+	p = xdr_reserve_space(xdr, sizeof(__be32) + len);
+	if (!p)
+		return nfserr_toosmall;
+
+	*p++ = cpu_to_be32(len);
+	*p++ = cpu_to_be32(1);		/* we always return a single extent */
+
+	p = xdr_encode_opaque_fixed(p, &b->vol_id,
+			sizeof(struct nfsd4_deviceid));
+	p = xdr_encode_hyper(p, b->foff);
+	p = xdr_encode_hyper(p, b->len);
+	p = xdr_encode_hyper(p, b->soff);
+	*p++ = cpu_to_be32(b->es);
+	return 0;
+}
+
+static int
+nfsd4_block_encode_volume(struct xdr_stream *xdr, struct pnfs_block_volume *b)
+{
+	__be32 *p;
+	int len;
+
+	switch (b->type) {
+	case PNFS_BLOCK_VOLUME_SIMPLE:
+		len = 4 + 4 + 8 + 4 + b->simple.sig_len;
+		p = xdr_reserve_space(xdr, len);
+		if (!p)
+			return -ETOOSMALL;
+
+		*p++ = cpu_to_be32(b->type);
+		*p++ = cpu_to_be32(1);	/* single signature */
+		p = xdr_encode_hyper(p, b->simple.offset);
+		p = xdr_encode_opaque(p, b->simple.sig, b->simple.sig_len);
+		break;
+	default:
+		return -ENOTSUPP;
+	}
+
+	return len;
+}
+
+__be32
+nfsd4_block_encode_getdeviceinfo(struct xdr_stream *xdr,
+		struct nfsd4_getdeviceinfo *gdp)
+{
+	struct pnfs_block_deviceaddr *dev = gdp->gd_device;
+	int len = sizeof(__be32), ret, i;
+	__be32 *p;
+
+	p = xdr_reserve_space(xdr, len + sizeof(__be32));
+	if (!p)
+		return nfserr_resource;
+
+	for (i = 0; i < dev->nr_volumes; i++) {
+		ret = nfsd4_block_encode_volume(xdr, &dev->volumes[i]);
+		if (ret < 0)
+			return nfserrno(ret);
+		len += ret;
+	}
+
+	/*
+	 * Fill in the overall length and number of volumes at the beginning
+	 * of the layout.
+	 */
+	*p++ = cpu_to_be32(len);
+	*p++ = cpu_to_be32(dev->nr_volumes);
+	return 0;
+}
+
+int
+nfsd4_block_decode_layoutupdate(__be32 *p, u32 len, struct iomap **iomapp,
+		u32 block_size)
+{
+	struct iomap *iomaps;
+	u32 nr_iomaps, expected, i;
+
+	if (len < sizeof(u32)) {
+		dprintk("%s: extent array too small: %u\n", __func__, len);
+		return -EINVAL;
+	}
+
+	nr_iomaps = be32_to_cpup(p++);
+	expected = sizeof(__be32) + nr_iomaps * NFS4_BLOCK_EXTENT_SIZE;
+	if (len != expected) {
+		dprintk("%s: extent array size mismatch: %u/%u\n",
+			__func__, len, expected);
+		return -EINVAL;
+	}
+
+	iomaps = kcalloc(nr_iomaps, sizeof(*iomaps), GFP_KERNEL);
+	if (!iomaps) {
+		dprintk("%s: failed to allocate extent array\n", __func__);
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < nr_iomaps; i++) {
+		struct pnfs_block_extent bex;
+
+		memcpy(&bex.vol_id, p, sizeof(struct nfsd4_deviceid));
+		p += XDR_QUADLEN(sizeof(struct nfsd4_deviceid));
+
+		p = xdr_decode_hyper(p, &bex.foff);
+		if (bex.foff & (block_size - 1)) {
+			dprintk("%s: unaligned offset %lld\n",
+				__func__, bex.foff);
+			goto fail;
+		}
+		p = xdr_decode_hyper(p, &bex.len);
+		if (bex.len & (block_size - 1)) {
+			dprintk("%s: unaligned length %lld\n",
+				__func__, bex.foff);
+			goto fail;
+		}
+		p = xdr_decode_hyper(p, &bex.soff);
+		if (bex.soff & (block_size - 1)) {
+			dprintk("%s: unaligned disk offset %lld\n",
+				__func__, bex.soff);
+			goto fail;
+		}
+		bex.es = be32_to_cpup(p++);
+		if (bex.es != PNFS_BLOCK_READWRITE_DATA) {
+			dprintk("%s: incorrect extent state %d\n",
+				__func__, bex.es);
+			goto fail;
+		}
+
+		iomaps[i].offset = bex.foff;
+		iomaps[i].length = bex.len;
+	}
+
+	*iomapp = iomaps;
+	return nr_iomaps;
+fail:
+	kfree(iomaps);
+	return -EINVAL;
+}
diff --git a/fs/nfsd/blocklayoutxdr.h b/fs/nfsd/blocklayoutxdr.h
new file mode 100644
index 000000000000..fdc79037c0e7
--- /dev/null
+++ b/fs/nfsd/blocklayoutxdr.h
@@ -0,0 +1,62 @@
+#ifndef _NFSD_BLOCKLAYOUTXDR_H
+#define _NFSD_BLOCKLAYOUTXDR_H 1
+
+#include <linux/blkdev.h>
+#include "xdr4.h"
+
+struct iomap;
+struct xdr_stream;
+
+enum pnfs_block_extent_state {
+	PNFS_BLOCK_READWRITE_DATA	= 0,
+	PNFS_BLOCK_READ_DATA		= 1,
+	PNFS_BLOCK_INVALID_DATA		= 2,
+	PNFS_BLOCK_NONE_DATA		= 3,
+};
+
+struct pnfs_block_extent {
+	struct nfsd4_deviceid		vol_id;
+	u64				foff;
+	u64				len;
+	u64				soff;
+	enum pnfs_block_extent_state	es;
+};
+#define NFS4_BLOCK_EXTENT_SIZE		44
+
+enum pnfs_block_volume_type {
+	PNFS_BLOCK_VOLUME_SIMPLE	= 0,
+	PNFS_BLOCK_VOLUME_SLICE		= 1,
+	PNFS_BLOCK_VOLUME_CONCAT	= 2,
+	PNFS_BLOCK_VOLUME_STRIPE	= 3,
+};
+
+/*
+ * Random upper cap for the uuid length to avoid unbounded allocation.
+ * Not actually limited by the protocol.
+ */
+#define PNFS_BLOCK_UUID_LEN	128
+
+struct pnfs_block_volume {
+	enum pnfs_block_volume_type	type;
+	union {
+		struct {
+			u64		offset;
+			u32		sig_len;
+			u8		sig[PNFS_BLOCK_UUID_LEN];
+		} simple;
+	};
+};
+
+struct pnfs_block_deviceaddr {
+	u32				nr_volumes;
+	struct pnfs_block_volume	volumes[];
+};
+
+__be32 nfsd4_block_encode_getdeviceinfo(struct xdr_stream *xdr,
+		struct nfsd4_getdeviceinfo *gdp);
+__be32 nfsd4_block_encode_layoutget(struct xdr_stream *xdr,
+		struct nfsd4_layoutget *lgp);
+int nfsd4_block_decode_layoutupdate(__be32 *p, u32 len, struct iomap **iomapp,
+		u32 block_size);
+
+#endif /* _NFSD_BLOCKLAYOUTXDR_H */
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index 30a739d896ff..c3e3b6e55ae2 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -20,6 +20,7 @@
 #include "nfsd.h"
 #include "nfsfh.h"
 #include "netns.h"