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
  ...

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  |

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

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);

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
  */

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 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
 	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);
 }
 

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

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

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,
+};

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;
+}

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 */

fs/nfsd/export.c

@@ -20,6 +20,7 @@
 #include "nfsd.h"
 #include "nfsfh.h"
 #include "netns.h"
+#include "pnfs.h"
 
 #define NFSDDBG_FACILITY	NFSDDBG_EXPORT
 
@@ -545,6 +546,7 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen)
 
 	exp.ex_client = dom;
 	exp.cd = cd;
+	exp.ex_devid_map = NULL;
 
 	/* expiry */
 	err = -EINVAL;
@@ -621,6 +623,8 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen)
 		if (!gid_valid(exp.ex_anon_gid))
 			goto out4;
 		err = 0;
+
+		nfsd4_setup_layout_type(&exp);
 	}
 
 	expp = svc_export_lookup(&exp);
@@ -703,6 +707,7 @@ 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_uuid = NULL;
 	new->cd = item->cd;
 }
@@ -717,6 +722,8 @@ static void export_update(struct cache_head *cnew, struct cache_head *citem)
 	new->ex_anon_uid = item->ex_anon_uid;
 	new->ex_anon_gid = item->ex_anon_gid;
 	new->ex_fsid = item->ex_fsid;
+	new->ex_devid_map = item->ex_devid_map;
+	item->ex_devid_map = NULL;
 	new->ex_uuid = item->ex_uuid;
 	item->ex_uuid = NULL;
 	new->ex_fslocs.locations = item->ex_fslocs.locations;
@@ -725,6 +732,7 @@ 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_nflavors = item->ex_nflavors;
 	for (i = 0; i < MAX_SECINFO_LIST; i++) {
 		new->ex_flavors[i] = item->ex_flavors[i];

fs/nfsd/export.h

@@ -56,6 +56,8 @@ 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;
+	struct nfsd4_deviceid_map *ex_devid_map;
 	struct cache_detail	*cd;
 };
 

fs/nfsd/nfs4callback.c

@@ -546,6 +546,102 @@ static int nfs4_xdr_dec_cb_recall(struct rpc_rqst *rqstp,
 	return status;
 }
 
+#ifdef CONFIG_NFSD_PNFS
+/*
+ * CB_LAYOUTRECALL4args
+ *
+ *	struct layoutrecall_file4 {
+ *		nfs_fh4         lor_fh;
+ *		offset4         lor_offset;
+ *		length4         lor_length;
+ *		stateid4        lor_stateid;
+ *	};
+ *
+ *	union layoutrecall4 switch(layoutrecall_type4 lor_recalltype) {
+ *	case LAYOUTRECALL4_FILE:
+ *		layoutrecall_file4 lor_layout;
+ *	case LAYOUTRECALL4_FSID:
+ *		fsid4              lor_fsid;
+ *	case LAYOUTRECALL4_ALL:
+ *		void;
+ *	};
+ *
+ *	struct CB_LAYOUTRECALL4args {
+ *		layouttype4             clora_type;
+ *		layoutiomode4           clora_iomode;
+ *		bool                    clora_changed;
+ *		layoutrecall4           clora_recall;
+ *	};
+ */
+static void encode_cb_layout4args(struct xdr_stream *xdr,
+				  const struct nfs4_layout_stateid *ls,
+				  struct nfs4_cb_compound_hdr *hdr)
+{
+	__be32 *p;
+
+	BUG_ON(hdr->minorversion == 0);
+
+	p = xdr_reserve_space(xdr, 5 * 4);
+	*p++ = cpu_to_be32(OP_CB_LAYOUTRECALL);
+	*p++ = cpu_to_be32(ls->ls_layout_type);
+	*p++ = cpu_to_be32(IOMODE_ANY);
+	*p++ = cpu_to_be32(1);
+	*p = cpu_to_be32(RETURN_FILE);
+
+	encode_nfs_fh4(xdr, &ls->ls_stid.sc_file->fi_fhandle);
+
+	p = xdr_reserve_space(xdr, 2 * 8);
+	p = xdr_encode_hyper(p, 0);
+	xdr_encode_hyper(p, NFS4_MAX_UINT64);
+
+	encode_stateid4(xdr, &ls->ls_recall_sid);
+
+	hdr->nops++;
+}
+
+static void nfs4_xdr_enc_cb_layout(struct rpc_rqst *req,
+				   struct xdr_stream *xdr,
+				   const struct nfsd4_callback *cb)
+{
+	const struct nfs4_layout_stateid *ls =
+		container_of(cb, struct nfs4_layout_stateid, ls_recall);
+	struct nfs4_cb_compound_hdr hdr = {
+		.ident = 0,
+		.minorversion = cb->cb_minorversion,
+	};
+
+	encode_cb_compound4args(xdr, &hdr);
+	encode_cb_sequence4args(xdr, cb, &hdr);
+	encode_cb_layout4args(xdr, ls, &hdr);
+	encode_cb_nops(&hdr);
+}
+
+static int nfs4_xdr_dec_cb_layout(struct rpc_rqst *rqstp,
+				  struct xdr_stream *xdr,
+				  struct nfsd4_callback *cb)
+{
+	struct nfs4_cb_compound_hdr hdr;
+	enum nfsstat4 nfserr;
+	int status;
+
+	status = decode_cb_compound4res(xdr, &hdr);
+	if (unlikely(status))
+		goto out;
+	if (cb) {
+		status = decode_cb_sequence4res(xdr, cb);
+		if (unlikely(status))
+			goto out;
+	}
+	status = decode_cb_op_status(xdr, OP_CB_LAYOUTRECALL, &nfserr);
+	if (unlikely(status))
+		goto out;
+	if (unlikely(nfserr != NFS4_OK))
+		status = nfs_cb_stat_to_errno(nfserr);
+out:
+	return status;
+}
+#endif /* CONFIG_NFSD_PNFS */
+
 /*
  * RPC procedure tables
  */
@@ -563,6 +659,9 @@ static int nfs4_xdr_dec_cb_recall(struct rpc_rqst *rqstp,
 static struct rpc_procinfo nfs4_cb_procedures[] = {
 	PROC(CB_NULL,	NULL,		cb_null,	cb_null),
 	PROC(CB_RECALL,	COMPOUND,	cb_recall,	cb_recall),
+#ifdef CONFIG_NFSD_PNFS
+	PROC(CB_LAYOUT,	COMPOUND,	cb_layout,	cb_layout),
+#endif
 };
 
 static struct rpc_version nfs_cb_version4 = {

fs/nfsd/nfs4layouts.c

@@ -0,0 +1,721 @@
+/*
+ * Copyright (c) 2014 Christoph Hellwig.
+ */
+#include <linux/kmod.h>
+#include <linux/file.h>
+#include <linux/jhash.h>
+#include <linux/sched.h>
+#include <linux/sunrpc/addr.h>
+
+#include "pnfs.h"
+#include "netns.h"
+#include "trace.h"
+
+#define NFSDDBG_FACILITY                NFSDDBG_PNFS
+
+struct nfs4_layout {
+	struct list_head		lo_perstate;
+	struct nfs4_layout_stateid	*lo_state;
+	struct nfsd4_layout_seg		lo_seg;
+};
+
+static struct kmem_cache *nfs4_layout_cache;
+static struct kmem_cache *nfs4_layout_stateid_cache;
+
+static 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] =  {
+	[LAYOUT_BLOCK_VOLUME]	= &bl_layout_ops,
+};
+
+/* pNFS device ID to export fsid mapping */
+#define DEVID_HASH_BITS	8
+#define DEVID_HASH_SIZE	(1 << DEVID_HASH_BITS)
+#define DEVID_HASH_MASK	(DEVID_HASH_SIZE - 1)
+static u64 nfsd_devid_seq = 1;
+static struct list_head nfsd_devid_hash[DEVID_HASH_SIZE];
+static DEFINE_SPINLOCK(nfsd_devid_lock);
+
+static inline u32 devid_hashfn(u64 idx)
+{
+	return jhash_2words(idx, idx >> 32, 0) & DEVID_HASH_MASK;
+}
+
+static void
+nfsd4_alloc_devid_map(const struct svc_fh *fhp)
+{
+	const struct knfsd_fh *fh = &fhp->fh_handle;
+	size_t fsid_len = key_len(fh->fh_fsid_type);
+	struct nfsd4_deviceid_map *map, *old;
+	int i;
+
+	map = kzalloc(sizeof(*map) + fsid_len, GFP_KERNEL);
+	if (!map)
+		return;
+
+	map->fsid_type = fh->fh_fsid_type;
+	memcpy(&map->fsid, fh->fh_fsid, fsid_len);
+
+	spin_lock(&nfsd_devid_lock);
+	if (fhp->fh_export->ex_devid_map)
+		goto out_unlock;
+
+	for (i = 0; i < DEVID_HASH_SIZE; i++) {
+		list_for_each_entry(old, &nfsd_devid_hash[i], hash) {
+			if (old->fsid_type != fh->fh_fsid_type)
+				continue;
+			if (memcmp(old->fsid, fh->fh_fsid,
+					key_len(old->fsid_type)))
+				continue;
+
+			fhp->fh_export->ex_devid_map = old;
+			goto out_unlock;
+		}
+	}
+
+	map->idx = nfsd_devid_seq++;
+	list_add_tail_rcu(&map->hash, &nfsd_devid_hash[devid_hashfn(map->idx)]);
+	fhp->fh_export->ex_devid_map = map;
+	map = NULL;
+
+out_unlock:
+	spin_unlock(&nfsd_devid_lock);
+	kfree(map);
+}
+
+struct nfsd4_deviceid_map *
+nfsd4_find_devid_map(int idx)
+{
+	struct nfsd4_deviceid_map *map, *ret = NULL;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(map, &nfsd_devid_hash[devid_hashfn(idx)], hash)
+		if (map->idx == idx)
+			ret = map;
+	rcu_read_unlock();
+
+	return ret;
+}
+
+int
+nfsd4_set_deviceid(struct nfsd4_deviceid *id, const struct svc_fh *fhp,
+		u32 device_generation)
+{
+	if (!fhp->fh_export->ex_devid_map) {
+		nfsd4_alloc_devid_map(fhp);
+		if (!fhp->fh_export->ex_devid_map)
+			return -ENOMEM;
+	}
+
+	id->fsid_idx = fhp->fh_export->ex_devid_map->idx;
+	id->generation = device_generation;
+	id->pad = 0;
+	return 0;
+}
+
+void nfsd4_setup_layout_type(struct svc_export *exp)
+{
+	struct super_block *sb = exp->ex_path.mnt->mnt_sb;
+
+	if (exp->ex_flags & NFSEXP_NOPNFS)
+		return;
+
+	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;
+}
+
+static void
+nfsd4_free_layout_stateid(struct nfs4_stid *stid)
+{
+	struct nfs4_layout_stateid *ls = layoutstateid(stid);
+	struct nfs4_client *clp = ls->ls_stid.sc_client;
+	struct nfs4_file *fp = ls->ls_stid.sc_file;
+
+	trace_layoutstate_free(&ls->ls_stid.sc_stateid);
+
+	spin_lock(&clp->cl_lock);
+	list_del_init(&ls->ls_perclnt);
+	spin_unlock(&clp->cl_lock);
+
+	spin_lock(&fp->fi_lock);
+	list_del_init(&ls->ls_perfile);
+	spin_unlock(&fp->fi_lock);
+
+	vfs_setlease(ls->ls_file, F_UNLCK, NULL, (void **)&ls);
+	fput(ls->ls_file);
+
+	if (ls->ls_recalled)
+		atomic_dec(&ls->ls_stid.sc_file->fi_lo_recalls);
+
+	kmem_cache_free(nfs4_layout_stateid_cache, ls);
+}
+
+static int
+nfsd4_layout_setlease(struct nfs4_layout_stateid *ls)
+{
+	struct file_lock *fl;
+	int status;
+
+	fl = locks_alloc_lock();
+	if (!fl)
+		return -ENOMEM;
+	locks_init_lock(fl);
+	fl->fl_lmops = &nfsd4_layouts_lm_ops;
+	fl->fl_flags = FL_LAYOUT;
+	fl->fl_type = F_RDLCK;
+	fl->fl_end = OFFSET_MAX;
+	fl->fl_owner = ls;
+	fl->fl_pid = current->tgid;
+	fl->fl_file = ls->ls_file;
+
+	status = vfs_setlease(fl->fl_file, fl->fl_type, &fl, NULL);
+	if (status) {
+		locks_free_lock(fl);
+		return status;
+	}
+	BUG_ON(fl != NULL);
+	return 0;
+}
+
+static struct nfs4_layout_stateid *
+nfsd4_alloc_layout_stateid(struct nfsd4_compound_state *cstate,
+		struct nfs4_stid *parent, u32 layout_type)
+{
+	struct nfs4_client *clp = cstate->clp;
+	struct nfs4_file *fp = parent->sc_file;
+	struct nfs4_layout_stateid *ls;
+	struct nfs4_stid *stp;
+
+	stp = nfs4_alloc_stid(cstate->clp, nfs4_layout_stateid_cache);
+	if (!stp)
+		return NULL;
+	stp->sc_free = nfsd4_free_layout_stateid;
+	get_nfs4_file(fp);
+	stp->sc_file = fp;
+
+	ls = layoutstateid(stp);
+	INIT_LIST_HEAD(&ls->ls_perclnt);
+	INIT_LIST_HEAD(&ls->ls_perfile);
+	spin_lock_init(&ls->ls_lock);
+	INIT_LIST_HEAD(&ls->ls_layouts);
+	ls->ls_layout_type = layout_type;
+	nfsd4_init_cb(&ls->ls_recall, clp, &nfsd4_cb_layout_ops,
+			NFSPROC4_CLNT_CB_LAYOUT);
+
+	if (parent->sc_type == NFS4_DELEG_STID)
+		ls->ls_file = get_file(fp->fi_deleg_file);
+	else
+		ls->ls_file = find_any_file(fp);
+	BUG_ON(!ls->ls_file);
+
+	if (nfsd4_layout_setlease(ls)) {
+		put_nfs4_file(fp);
+		kmem_cache_free(nfs4_layout_stateid_cache, ls);
+		return NULL;
+	}
+
+	spin_lock(&clp->cl_lock);
+	stp->sc_type = NFS4_LAYOUT_STID;
+	list_add(&ls->ls_perclnt, &clp->cl_lo_states);
+	spin_unlock(&clp->cl_lock);
+
+	spin_lock(&fp->fi_lock);
+	list_add(&ls->ls_perfile, &fp->fi_lo_states);
+	spin_unlock(&fp->fi_lock);
+
+	trace_layoutstate_alloc(&ls->ls_stid.sc_stateid);
+	return ls;
+}
+
+__be32
+nfsd4_preprocess_layout_stateid(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate, stateid_t *stateid,
+		bool create, u32 layout_type, struct nfs4_layout_stateid **lsp)
+{
+	struct nfs4_layout_stateid *ls;
+	struct nfs4_stid *stid;
+	unsigned char typemask = NFS4_LAYOUT_STID;
+	__be32 status;
+
+	if (create)
+		typemask |= (NFS4_OPEN_STID | NFS4_LOCK_STID | NFS4_DELEG_STID);
+
+	status = nfsd4_lookup_stateid(cstate, stateid, typemask, &stid,
+			net_generic(SVC_NET(rqstp), nfsd_net_id));
+	if (status)
+		goto out;
+
+	if (!fh_match(&cstate->current_fh.fh_handle,
+		      &stid->sc_file->fi_fhandle)) {
+		status = nfserr_bad_stateid;
+		goto out_put_stid;
+	}
+
+	if (stid->sc_type != NFS4_LAYOUT_STID) {
+		ls = nfsd4_alloc_layout_stateid(cstate, stid, layout_type);
+		nfs4_put_stid(stid);
+
+		status = nfserr_jukebox;
+		if (!ls)
+			goto out;
+	} else {
+		ls = container_of(stid, struct nfs4_layout_stateid, ls_stid);
+
+		status = nfserr_bad_stateid;
+		if (stateid->si_generation > stid->sc_stateid.si_generation)
+			goto out_put_stid;
+		if (layout_type != ls->ls_layout_type)
+			goto out_put_stid;
+	}
+
+	*lsp = ls;
+	return 0;
+
+out_put_stid:
+	nfs4_put_stid(stid);
+out:
+	return status;
+}
+
+static void
+nfsd4_recall_file_layout(struct nfs4_layout_stateid *ls)
+{
+	spin_lock(&ls->ls_lock);
+	if (ls->ls_recalled)
+		goto out_unlock;
+
+	ls->ls_recalled = true;
+	atomic_inc(&ls->ls_stid.sc_file->fi_lo_recalls);
+	if (list_empty(&ls->ls_layouts))
+		goto out_unlock;
+
+	trace_layout_recall(&ls->ls_stid.sc_stateid);
+
+	atomic_inc(&ls->ls_stid.sc_count);
+	update_stateid(&ls->ls_stid.sc_stateid);
+	memcpy(&ls->ls_recall_sid, &ls->ls_stid.sc_stateid, sizeof(stateid_t));
+	nfsd4_run_cb(&ls->ls_recall);
+
+out_unlock:
+	spin_unlock(&ls->ls_lock);
+}
+
+static inline u64
+layout_end(struct nfsd4_layout_seg *seg)
+{
+	u64 end = seg->offset + seg->length;
+	return end >= seg->offset ? end : NFS4_MAX_UINT64;
+}
+
+static void
+layout_update_len(struct nfsd4_layout_seg *lo, u64 end)
+{
+	if (end == NFS4_MAX_UINT64)
+		lo->length = NFS4_MAX_UINT64;
+	else
+		lo->length = end - lo->offset;
+}
+
+static bool
+layouts_overlapping(struct nfs4_layout *lo, struct nfsd4_layout_seg *s)
+{
+	if (s->iomode != IOMODE_ANY && s->iomode != lo->lo_seg.iomode)
+		return false;
+	if (layout_end(&lo->lo_seg) <= s->offset)
+		return false;
+	if (layout_end(s) <= lo->lo_seg.offset)
+		return false;
+	return true;
+}
+
+static bool
+layouts_try_merge(struct nfsd4_layout_seg *lo, struct nfsd4_layout_seg *new)
+{
+	if (lo->iomode != new->iomode)
+		return false;
+	if (layout_end(new) < lo->offset)
+		return false;
+	if (layout_end(lo) < new->offset)
+		return false;
+
+	lo->offset = min(lo->offset, new->offset);
+	layout_update_len(lo, max(layout_end(lo), layout_end(new)));
+	return true;
+}
+
+static __be32
+nfsd4_recall_conflict(struct nfs4_layout_stateid *ls)
+{
+	struct nfs4_file *fp = ls->ls_stid.sc_file;
+	struct nfs4_layout_stateid *l, *n;
+	__be32 nfserr = nfs_ok;
+
+	assert_spin_locked(&fp->fi_lock);
+
+	list_for_each_entry_safe(l, n, &fp->fi_lo_states, ls_perfile) {
+		if (l != ls) {
+			nfsd4_recall_file_layout(l);
+			nfserr = nfserr_recallconflict;
+		}
+	}
+
+	return nfserr;
+}
+
+__be32
+nfsd4_insert_layout(struct nfsd4_layoutget *lgp, struct nfs4_layout_stateid *ls)
+{
+	struct nfsd4_layout_seg *seg = &lgp->lg_seg;
+	struct nfs4_file *fp = ls->ls_stid.sc_file;
+	struct nfs4_layout *lp, *new = NULL;
+	__be32 nfserr;
+
+	spin_lock(&fp->fi_lock);
+	nfserr = nfsd4_recall_conflict(ls);
+	if (nfserr)
+		goto out;
+	spin_lock(&ls->ls_lock);
+	list_for_each_entry(lp, &ls->ls_layouts, lo_perstate) {
+		if (layouts_try_merge(&lp->lo_seg, seg))
+			goto done;
+	}
+	spin_unlock(&ls->ls_lock);
+	spin_unlock(&fp->fi_lock);
+
+	new = kmem_cache_alloc(nfs4_layout_cache, GFP_KERNEL);
+	if (!new)
+		return nfserr_jukebox;
+	memcpy(&new->lo_seg, seg, sizeof(lp->lo_seg));
+	new->lo_state = ls;
+
+	spin_lock(&fp->fi_lock);
+	nfserr = nfsd4_recall_conflict(ls);
+	if (nfserr)
+		goto out;
+	spin_lock(&ls->ls_lock);
+	list_for_each_entry(lp, &ls->ls_layouts, lo_perstate) {
+		if (layouts_try_merge(&lp->lo_seg, seg))
+			goto done;
+	}
+
+	atomic_inc(&ls->ls_stid.sc_count);
+	list_add_tail(&new->lo_perstate, &ls->ls_layouts);
+	new = NULL;
+done:
+	update_stateid(&ls->ls_stid.sc_stateid);
+	memcpy(&lgp->lg_sid, &ls->ls_stid.sc_stateid, sizeof(stateid_t));
+	spin_unlock(&ls->ls_lock);
+out:
+	spin_unlock(&fp->fi_lock);
+	if (new)
+		kmem_cache_free(nfs4_layout_cache, new);
+	return nfserr;
+}
+
+static void
+nfsd4_free_layouts(struct list_head *reaplist)
+{
+	while (!list_empty(reaplist)) {
+		struct nfs4_layout *lp = list_first_entry(reaplist,
+				struct nfs4_layout, lo_perstate);
+
+		list_del(&lp->lo_perstate);
+		nfs4_put_stid(&lp->lo_state->ls_stid);
+		kmem_cache_free(nfs4_layout_cache, lp);
+	}
+}
+
+static void
+nfsd4_return_file_layout(struct nfs4_layout *lp, struct nfsd4_layout_seg *seg,
+		struct list_head *reaplist)
+{
+	struct nfsd4_layout_seg *lo = &lp->lo_seg;
+	u64 end = layout_end(lo);
+
+	if (seg->offset <= lo->offset) {
+		if (layout_end(seg) >= end) {
+			list_move_tail(&lp->lo_perstate, reaplist);
+			return;
+		}
+		end = seg->offset;
+	} else {
+		/* retain the whole layout segment on a split. */
+		if (layout_end(seg) < end) {
+			dprintk("%s: split not supported\n", __func__);
+			return;
+		}
+
+		lo->offset = layout_end(seg);
+	}
+
+	layout_update_len(lo, end);
+}
+
+__be32
+nfsd4_return_file_layouts(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		struct nfsd4_layoutreturn *lrp)
+{
+	struct nfs4_layout_stateid *ls;
+	struct nfs4_layout *lp, *n;
+	LIST_HEAD(reaplist);
+	__be32 nfserr;
+	int found = 0;
+
+	nfserr = nfsd4_preprocess_layout_stateid(rqstp, cstate, &lrp->lr_sid,
+						false, lrp->lr_layout_type,
+						&ls);
+	if (nfserr) {
+		trace_layout_return_lookup_fail(&lrp->lr_sid);
+		return nfserr;
+	}
+
+	spin_lock(&ls->ls_lock);
+	list_for_each_entry_safe(lp, n, &ls->ls_layouts, lo_perstate) {
+		if (layouts_overlapping(lp, &lrp->lr_seg)) {
+			nfsd4_return_file_layout(lp, &lrp->lr_seg, &reaplist);
+			found++;
+		}
+	}
+	if (!list_empty(&ls->ls_layouts)) {
+		if (found) {
+			update_stateid(&ls->ls_stid.sc_stateid);
+			memcpy(&lrp->lr_sid, &ls->ls_stid.sc_stateid,
+				sizeof(stateid_t));
+		}
+		lrp->lrs_present = 1;
+	} else {
+		trace_layoutstate_unhash(&ls->ls_stid.sc_stateid);
+		nfs4_unhash_stid(&ls->ls_stid);
+		lrp->lrs_present = 0;
+	}
+	spin_unlock(&ls->ls_lock);
+
+	nfs4_put_stid(&ls->ls_stid);
+	nfsd4_free_layouts(&reaplist);
+	return nfs_ok;
+}
+
+__be32
+nfsd4_return_client_layouts(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		struct nfsd4_layoutreturn *lrp)
+{
+	struct nfs4_layout_stateid *ls, *n;
+	struct nfs4_client *clp = cstate->clp;
+	struct nfs4_layout *lp, *t;
+	LIST_HEAD(reaplist);
+
+	lrp->lrs_present = 0;
+
+	spin_lock(&clp->cl_lock);
+	list_for_each_entry_safe(ls, n, &clp->cl_lo_states, ls_perclnt) {
+		if (lrp->lr_return_type == RETURN_FSID &&
+		    !fh_fsid_match(&ls->ls_stid.sc_file->fi_fhandle,
+				   &cstate->current_fh.fh_handle))
+			continue;
+
+		spin_lock(&ls->ls_lock);
+		list_for_each_entry_safe(lp, t, &ls->ls_layouts, lo_perstate) {
+			if (lrp->lr_seg.iomode == IOMODE_ANY ||
+			    lrp->lr_seg.iomode == lp->lo_seg.iomode)
+				list_move_tail(&lp->lo_perstate, &reaplist);
+		}
+		spin_unlock(&ls->ls_lock);
+	}
+	spin_unlock(&clp->cl_lock);
+
+	nfsd4_free_layouts(&reaplist);
+	return 0;
+}
+
+static void
+nfsd4_return_all_layouts(struct nfs4_layout_stateid *ls,
+		struct list_head *reaplist)
+{
+	spin_lock(&ls->ls_lock);
+	list_splice_init(&ls->ls_layouts, reaplist);
+	spin_unlock(&ls->ls_lock);
+}
+
+void
+nfsd4_return_all_client_layouts(struct nfs4_client *clp)
+{
+	struct nfs4_layout_stateid *ls, *n;
+	LIST_HEAD(reaplist);
+
+	spin_lock(&clp->cl_lock);
+	list_for_each_entry_safe(ls, n, &clp->cl_lo_states, ls_perclnt)
+		nfsd4_return_all_layouts(ls, &reaplist);
+	spin_unlock(&clp->cl_lock);
+
+	nfsd4_free_layouts(&reaplist);
+}
+
+void
+nfsd4_return_all_file_layouts(struct nfs4_client *clp, struct nfs4_file *fp)
+{
+	struct nfs4_layout_stateid *ls, *n;
+	LIST_HEAD(reaplist);
+
+	spin_lock(&fp->fi_lock);
+	list_for_each_entry_safe(ls, n, &fp->fi_lo_states, ls_perfile) {
+		if (ls->ls_stid.sc_client == clp)
+			nfsd4_return_all_layouts(ls, &reaplist);
+	}
+	spin_unlock(&fp->fi_lock);
+
+	nfsd4_free_layouts(&reaplist);
+}
+
+static void
+nfsd4_cb_layout_fail(struct nfs4_layout_stateid *ls)
+{
+	struct nfs4_client *clp = ls->ls_stid.sc_client;
+	char addr_str[INET6_ADDRSTRLEN];
+	static char *envp[] = {
+		"HOME=/",
+		"TERM=linux",
+		"PATH=/sbin:/usr/sbin:/bin:/usr/bin",
+		NULL
+	};
+	char *argv[8];
+	int error;
+
+	rpc_ntop((struct sockaddr *)&clp->cl_addr, addr_str, sizeof(addr_str));
+
+	nfsd4_cb_layout_fail(ls);
+
+	printk(KERN_WARNING
+		"nfsd: client %s failed to respond to layout recall. "
+		"  Fencing..\n", addr_str);
+
+	argv[0] = "/sbin/nfsd-recall-failed";
+	argv[1] = addr_str;
+	argv[2] = ls->ls_file->f_path.mnt->mnt_sb->s_id;
+	argv[3] = NULL;
+
+	error = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_PROC);
+	if (error) {
+		printk(KERN_ERR "nfsd: fence failed for client %s: %d!\n",
+			addr_str, error);
+	}
+}
+
+static int
+nfsd4_cb_layout_done(struct nfsd4_callback *cb, struct rpc_task *task)
+{
+	struct nfs4_layout_stateid *ls =
+		container_of(cb, struct nfs4_layout_stateid, ls_recall);
+	LIST_HEAD(reaplist);
+
+	switch (task->tk_status) {
+	case 0:
+		return 1;
+	case -NFS4ERR_NOMATCHING_LAYOUT:
+		trace_layout_recall_done(&ls->ls_stid.sc_stateid);
+		task->tk_status = 0;
+		return 1;
+	case -NFS4ERR_DELAY:
+		/* Poll the client until it's done with the layout */
+		/* FIXME: cap number of retries.
+		 * The pnfs standard states that we need to only expire
+		 * the client after at-least "lease time" .eg lease-time * 2
+		 * when failing to communicate a recall
+		 */
+		rpc_delay(task, HZ/100); /* 10 mili-seconds */
+		return 0;
+	default:
+		/*
+		 * Unknown error or non-responding client, we'll need to fence.
+		 */
+		nfsd4_cb_layout_fail(ls);
+		return -1;
+	}
+}
+
+static void
+nfsd4_cb_layout_release(struct nfsd4_callback *cb)
+{
+	struct nfs4_layout_stateid *ls =
+		container_of(cb, struct nfs4_layout_stateid, ls_recall);
+	LIST_HEAD(reaplist);
+
+	trace_layout_recall_release(&ls->ls_stid.sc_stateid);
+
+	nfsd4_return_all_layouts(ls, &reaplist);
+	nfsd4_free_layouts(&reaplist);
+	nfs4_put_stid(&ls->ls_stid);
+}
+
+static struct nfsd4_callback_ops nfsd4_cb_layout_ops = {
+	.done		= nfsd4_cb_layout_done,
+	.release	= nfsd4_cb_layout_release,
+};
+
+static bool
+nfsd4_layout_lm_break(struct file_lock *fl)
+{
+	/*
+	 * We don't want the locks code to timeout the lease for us;
+	 * we'll remove it ourself if a layout isn't returned
+	 * in time:
+	 */
+	fl->fl_break_time = 0;
+	nfsd4_recall_file_layout(fl->fl_owner);
+	return false;
+}
+
+static int
+nfsd4_layout_lm_change(struct file_lock *onlist, int arg,
+		struct list_head *dispose)
+{
+	BUG_ON(!(arg & F_UNLCK));
+	return lease_modify(onlist, arg, dispose);
+}
+
+static const struct lock_manager_operations nfsd4_layouts_lm_ops = {
+	.lm_break	= nfsd4_layout_lm_break,
+	.lm_change	= nfsd4_layout_lm_change,
+};
+
+int
+nfsd4_init_pnfs(void)
+{
+	int i;
+
+	for (i = 0; i < DEVID_HASH_SIZE; i++)
+		INIT_LIST_HEAD(&nfsd_devid_hash[i]);
+
+	nfs4_layout_cache = kmem_cache_create("nfs4_layout",
+			sizeof(struct nfs4_layout), 0, 0, NULL);
+	if (!nfs4_layout_cache)
+		return -ENOMEM;
+
+	nfs4_layout_stateid_cache = kmem_cache_create("nfs4_layout_stateid",
+			sizeof(struct nfs4_layout_stateid), 0, 0, NULL);
+	if (!nfs4_layout_stateid_cache) {
+		kmem_cache_destroy(nfs4_layout_cache);
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+void
+nfsd4_exit_pnfs(void)
+{
+	int i;
+
+	kmem_cache_destroy(nfs4_layout_cache);
+	kmem_cache_destroy(nfs4_layout_stateid_cache);
+
+	for (i = 0; i < DEVID_HASH_SIZE; i++) {
+		struct nfsd4_deviceid_map *map, *n;
+
+		list_for_each_entry_safe(map, n, &nfsd_devid_hash[i], hash)
+			kfree(map);
+	}
+}

fs/nfsd/nfs4proc.c

@@ -43,6 +43,8 @@
 #include "current_stateid.h"
 #include "netns.h"
 #include "acl.h"
+#include "pnfs.h"
+#include "trace.h"
 
 #ifdef CONFIG_NFSD_V4_SECURITY_LABEL
 #include <linux/security.h>
@@ -1178,6 +1180,259 @@ nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	return status == nfserr_same ? nfs_ok : status;
 }
 
+#ifdef CONFIG_NFSD_PNFS
+static const struct nfsd4_layout_ops *
+nfsd4_layout_verify(struct svc_export *exp, unsigned int layout_type)
+{
+	if (!exp->ex_layout_type) {
+		dprintk("%s: export does not support pNFS\n", __func__);
+		return NULL;
+	}
+
+	if (exp->ex_layout_type != layout_type) {
+		dprintk("%s: layout type %d not supported\n",
+			__func__, layout_type);
+		return NULL;
+	}
+
+	return nfsd4_layout_ops[layout_type];
+}
+
+static __be32
+nfsd4_getdeviceinfo(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		struct nfsd4_getdeviceinfo *gdp)
+{
+	const struct nfsd4_layout_ops *ops;
+	struct nfsd4_deviceid_map *map;
+	struct svc_export *exp;
+	__be32 nfserr;
+
+	dprintk("%s: layout_type %u dev_id [0x%llx:0x%x] maxcnt %u\n",
+	       __func__,
+	       gdp->gd_layout_type,
+	       gdp->gd_devid.fsid_idx, gdp->gd_devid.generation,
+	       gdp->gd_maxcount);
+
+	map = nfsd4_find_devid_map(gdp->gd_devid.fsid_idx);
+	if (!map) {
+		dprintk("%s: couldn't find device ID to export mapping!\n",
+			__func__);
+		return nfserr_noent;
+	}
+
+	exp = rqst_exp_find(rqstp, map->fsid_type, map->fsid);
+	if (IS_ERR(exp)) {
+		dprintk("%s: could not find device id\n", __func__);
+		return nfserr_noent;
+	}
+
+	nfserr = nfserr_layoutunavailable;
+	ops = nfsd4_layout_verify(exp, gdp->gd_layout_type);
+	if (!ops)
+		goto out;
+
+	nfserr = nfs_ok;
+	if (gdp->gd_maxcount != 0)
+		nfserr = ops->proc_getdeviceinfo(exp->ex_path.mnt->mnt_sb, gdp);
+
+	gdp->gd_notify_types &= ops->notify_types;
+	exp_put(exp);
+out:
+	return nfserr;
+}
+
+static __be32
+nfsd4_layoutget(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		struct nfsd4_layoutget *lgp)
+{
+	struct svc_fh *current_fh = &cstate->current_fh;
+	const struct nfsd4_layout_ops *ops;
+	struct nfs4_layout_stateid *ls;
+	__be32 nfserr;
+	int accmode;
+
+	switch (lgp->lg_seg.iomode) {
+	case IOMODE_READ:
+		accmode = NFSD_MAY_READ;
+		break;
+	case IOMODE_RW:
+		accmode = NFSD_MAY_READ | NFSD_MAY_WRITE;
+		break;
+	default:
+		dprintk("%s: invalid iomode %d\n",
+			__func__, lgp->lg_seg.iomode);
+		nfserr = nfserr_badiomode;
+		goto out;
+	}
+
+	nfserr = fh_verify(rqstp, current_fh, 0, accmode);
+	if (nfserr)
+		goto out;
+
+	nfserr = nfserr_layoutunavailable;
+	ops = nfsd4_layout_verify(current_fh->fh_export, lgp->lg_layout_type);
+	if (!ops)
+		goto out;
+
+	/*
+	 * Verify minlength and range as per RFC5661:
+	 *  o  If loga_length is less than loga_minlength,
+	 *     the metadata server MUST return NFS4ERR_INVAL.
+	 *  o  If the sum of loga_offset and loga_minlength exceeds
+	 *     NFS4_UINT64_MAX, and loga_minlength is not
+	 *     NFS4_UINT64_MAX, the error NFS4ERR_INVAL MUST result.
+	 *  o  If the sum of loga_offset and loga_length exceeds
+	 *     NFS4_UINT64_MAX, and loga_length is not NFS4_UINT64_MAX,
+	 *     the error NFS4ERR_INVAL MUST result.
+	 */
+	nfserr = nfserr_inval;
+	if (lgp->lg_seg.length < lgp->lg_minlength ||
+	    (lgp->lg_minlength != NFS4_MAX_UINT64 &&
+	     lgp->lg_minlength > NFS4_MAX_UINT64 - lgp->lg_seg.offset) ||
+	    (lgp->lg_seg.length != NFS4_MAX_UINT64 &&
+	     lgp->lg_seg.length > NFS4_MAX_UINT64 - lgp->lg_seg.offset))
+		goto out;
+	if (lgp->lg_seg.length == 0)
+		goto out;
+
+	nfserr = nfsd4_preprocess_layout_stateid(rqstp, cstate, &lgp->lg_sid,
+						true, lgp->lg_layout_type, &ls);
+	if (nfserr) {
+		trace_layout_get_lookup_fail(&lgp->lg_sid);
+		goto out;
+	}
+
+	nfserr = nfserr_recallconflict;
+	if (atomic_read(&ls->ls_stid.sc_file->fi_lo_recalls))
+		goto out_put_stid;
+
+	nfserr = ops->proc_layoutget(current_fh->fh_dentry->d_inode,
+				     current_fh, lgp);
+	if (nfserr)
+		goto out_put_stid;
+
+	nfserr = nfsd4_insert_layout(lgp, ls);
+
+out_put_stid:
+	nfs4_put_stid(&ls->ls_stid);
+out:
+	return nfserr;
+}
+
+static __be32
+nfsd4_layoutcommit(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		struct nfsd4_layoutcommit *lcp)
+{
+	const struct nfsd4_layout_seg *seg = &lcp->lc_seg;
+	struct svc_fh *current_fh = &cstate->current_fh;
+	const struct nfsd4_layout_ops *ops;
+	loff_t new_size = lcp->lc_last_wr + 1;
+	struct inode *inode;
+	struct nfs4_layout_stateid *ls;
+	__be32 nfserr;
+
+	nfserr = fh_verify(rqstp, current_fh, 0, NFSD_MAY_WRITE);
+	if (nfserr)
+		goto out;
+
+	nfserr = nfserr_layoutunavailable;
+	ops = nfsd4_layout_verify(current_fh->fh_export, lcp->lc_layout_type);
+	if (!ops)
+		goto out;
+	inode = current_fh->fh_dentry->d_inode;
+
+	nfserr = nfserr_inval;
+	if (new_size <= seg->offset) {
+		dprintk("pnfsd: last write before layout segment\n");
+		goto out;
+	}
+	if (new_size > seg->offset + seg->length) {
+		dprintk("pnfsd: last write beyond layout segment\n");
+		goto out;
+	}
+	if (!lcp->lc_newoffset && new_size > i_size_read(inode)) {
+		dprintk("pnfsd: layoutcommit beyond EOF\n");
+		goto out;
+	}
+
+	nfserr = nfsd4_preprocess_layout_stateid(rqstp, cstate, &lcp->lc_sid,
+						false, lcp->lc_layout_type,
+						&ls);
+	if (nfserr) {
+		trace_layout_commit_lookup_fail(&lcp->lc_sid);
+		/* fixup error code as per RFC5661 */
+		if (nfserr == nfserr_bad_stateid)
+			nfserr = nfserr_badlayout;
+		goto out;
+	}
+
+	nfserr = ops->proc_layoutcommit(inode, lcp);
+	if (nfserr)
+		goto out_put_stid;
+
+	if (new_size > i_size_read(inode)) {
+		lcp->lc_size_chg = 1;
+		lcp->lc_newsize = new_size;
+	} else {
+		lcp->lc_size_chg = 0;
+	}
+
+out_put_stid:
+	nfs4_put_stid(&ls->ls_stid);
+out:
+	return nfserr;
+}
+
+static __be32
+nfsd4_layoutreturn(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		struct nfsd4_layoutreturn *lrp)
+{
+	struct svc_fh *current_fh = &cstate->current_fh;
+	__be32 nfserr;
+
+	nfserr = fh_verify(rqstp, current_fh, 0, NFSD_MAY_NOP);
+	if (nfserr)
+		goto out;
+
+	nfserr = nfserr_layoutunavailable;
+	if (!nfsd4_layout_verify(current_fh->fh_export, lrp->lr_layout_type))
+		goto out;
+
+	switch (lrp->lr_seg.iomode) {
+	case IOMODE_READ:
+	case IOMODE_RW:
+	case IOMODE_ANY:
+		break;
+	default:
+		dprintk("%s: invalid iomode %d\n", __func__,
+			lrp->lr_seg.iomode);
+		nfserr = nfserr_inval;
+		goto out;
+	}
+
+	switch (lrp->lr_return_type) {
+	case RETURN_FILE:
+		nfserr = nfsd4_return_file_layouts(rqstp, cstate, lrp);
+		break;
+	case RETURN_FSID:
+	case RETURN_ALL:
+		nfserr = nfsd4_return_client_layouts(rqstp, cstate, lrp);
+		break;
+	default:
+		dprintk("%s: invalid return_type %d\n", __func__,
+			lrp->lr_return_type);
+		nfserr = nfserr_inval;
+		break;
+	}
+out:
+	return nfserr;
+}
+#endif /* CONFIG_NFSD_PNFS */
+
 /*
  * NULL call.
  */
@@ -1679,6 +1934,36 @@ static inline u32 nfsd4_create_session_rsize(struct svc_rqst *rqstp, struct nfsd
 		op_encode_channel_attrs_maxsz) * sizeof(__be32);
 }
 
+#ifdef CONFIG_NFSD_PNFS
+/*
+ * At this stage we don't really know what layout driver will handle the request,
+ * so we need to define an arbitrary upper bound here.
+ */
+#define MAX_LAYOUT_SIZE		128
+static inline u32 nfsd4_layoutget_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+{
+	return (op_encode_hdr_size +
+		1 /* logr_return_on_close */ +
+		op_encode_stateid_maxsz +
+		1 /* nr of layouts */ +
+		MAX_LAYOUT_SIZE) * sizeof(__be32);
+}
+
+static inline u32 nfsd4_layoutcommit_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+{
+	return (op_encode_hdr_size +
+		1 /* locr_newsize */ +
+		2 /* ns_size */) * sizeof(__be32);
+}
+
+static inline u32 nfsd4_layoutreturn_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+{
+	return (op_encode_hdr_size +
+		1 /* lrs_stateid */ +
+		op_encode_stateid_maxsz) * sizeof(__be32);
+}
+#endif /* CONFIG_NFSD_PNFS */
+
 static struct nfsd4_operation nfsd4_ops[] = {
 	[OP_ACCESS] = {
 		.op_func = (nfsd4op_func)nfsd4_access,
@@ -1966,6 +2251,31 @@ static struct nfsd4_operation nfsd4_ops[] = {
 		.op_get_currentstateid = (stateid_getter)nfsd4_get_freestateid,
 		.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
 	},
+#ifdef CONFIG_NFSD_PNFS
+	[OP_GETDEVICEINFO] = {
+		.op_func = (nfsd4op_func)nfsd4_getdeviceinfo,
+		.op_flags = ALLOWED_WITHOUT_FH,
+		.op_name = "OP_GETDEVICEINFO",
+	},
+	[OP_LAYOUTGET] = {
+		.op_func = (nfsd4op_func)nfsd4_layoutget,
+		.op_flags = OP_MODIFIES_SOMETHING,
+		.op_name = "OP_LAYOUTGET",
+		.op_rsize_bop = (nfsd4op_rsize)nfsd4_layoutget_rsize,
+	},
+	[OP_LAYOUTCOMMIT] = {
+		.op_func = (nfsd4op_func)nfsd4_layoutcommit,
+		.op_flags = OP_MODIFIES_SOMETHING,
+		.op_name = "OP_LAYOUTCOMMIT",
+		.op_rsize_bop = (nfsd4op_rsize)nfsd4_layoutcommit_rsize,
+	},
+	[OP_LAYOUTRETURN] = {
+		.op_func = (nfsd4op_func)nfsd4_layoutreturn,
+		.op_flags = OP_MODIFIES_SOMETHING,
+		.op_name = "OP_LAYOUTRETURN",
+		.op_rsize_bop = (nfsd4op_rsize)nfsd4_layoutreturn_rsize,
+	},
+#endif /* CONFIG_NFSD_PNFS */
 
 	/* NFSv4.2 operations */
 	[OP_ALLOCATE] = {

fs/nfsd/nfs4state.c

@@ -48,6 +48,7 @@
 #include "current_stateid.h"
 
 #include "netns.h"
+#include "pnfs.h"
 
 #define NFSDDBG_FACILITY                NFSDDBG_PROC
 
@@ -150,16 +151,6 @@ renew_client_locked(struct nfs4_client *clp)
 	clp->cl_time = get_seconds();
 }
 
-static inline void
-renew_client(struct nfs4_client *clp)
-{
-	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
-
-	spin_lock(&nn->client_lock);
-	renew_client_locked(clp);
-	spin_unlock(&nn->client_lock);
-}
-
 static void put_client_renew_locked(struct nfs4_client *clp)
 {
 	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
@@ -282,7 +273,7 @@ static void nfsd4_free_file_rcu(struct rcu_head *rcu)
 	kmem_cache_free(file_slab, fp);
 }
 
-static inline void
+void
 put_nfs4_file(struct nfs4_file *fi)
 {
 	might_lock(&state_lock);
@@ -295,12 +286,6 @@ put_nfs4_file(struct nfs4_file *fi)
 	}
 }
 
-static inline void
-get_nfs4_file(struct nfs4_file *fi)
-{
-	atomic_inc(&fi->fi_ref);
-}
-
 static struct file *
 __nfs4_get_fd(struct nfs4_file *f, int oflag)
 {
@@ -358,7 +343,7 @@ find_readable_file(struct nfs4_file *f)
 	return ret;
 }
 
-static struct file *
+struct file *
 find_any_file(struct nfs4_file *f)
 {
 	struct file *ret;
@@ -408,14 +393,6 @@ static unsigned int file_hashval(struct knfsd_fh *fh)
 	return nfsd_fh_hashval(fh) & (FILE_HASH_SIZE - 1);
 }
 
-static bool nfsd_fh_match(struct knfsd_fh *fh1, struct knfsd_fh *fh2)
-{
-	return fh1->fh_size == fh2->fh_size &&
-		!memcmp(fh1->fh_base.fh_pad,
-				fh2->fh_base.fh_pad,
-				fh1->fh_size);
-}
-
 static struct hlist_head file_hashtbl[FILE_HASH_SIZE];
 
 static void
@@ -494,7 +471,7 @@ static void nfs4_file_put_access(struct nfs4_file *fp, u32 access)
 		__nfs4_file_put_access(fp, O_RDONLY);
 }
 
-static struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl,
+struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl,
 					 struct kmem_cache *slab)
 {
 	struct nfs4_stid *stid;
@@ -688,17 +665,17 @@ static void nfs4_put_deleg_lease(struct nfs4_file *fp)
 	struct file *filp = NULL;
 
 	spin_lock(&fp->fi_lock);
-	if (fp->fi_deleg_file && atomic_dec_and_test(&fp->fi_delegees))
+	if (fp->fi_deleg_file && --fp->fi_delegees == 0)
 		swap(filp, fp->fi_deleg_file);
 	spin_unlock(&fp->fi_lock);
 
 	if (filp) {
-		vfs_setlease(filp, F_UNLCK, NULL, NULL);
+		vfs_setlease(filp, F_UNLCK, NULL, (void **)&fp);
 		fput(filp);
 	}
 }
 
-static void unhash_stid(struct nfs4_stid *s)
+void nfs4_unhash_stid(struct nfs4_stid *s)
 {
 	s->sc_type = 0;
 }
@@ -1006,7 +983,7 @@ static void unhash_lock_stateid(struct nfs4_ol_stateid *stp)
 
 	list_del_init(&stp->st_locks);
 	unhash_ol_stateid(stp);
-	unhash_stid(&stp->st_stid);
+	nfs4_unhash_stid(&stp->st_stid);
 }
 
 static void release_lock_stateid(struct nfs4_ol_stateid *stp)
@@ -1518,7 +1495,12 @@ unhash_session(struct nfsd4_session *ses)
 static int
 STALE_CLIENTID(clientid_t *clid, struct nfsd_net *nn)
 {
-	if (clid->cl_boot == nn->boot_time)
+	/*
+	 * We're assuming the clid was not given out from a boot
+	 * precisely 2^32 (about 136 years) before this one.  That seems
+	 * a safe assumption:
+	 */
+	if (clid->cl_boot == (u32)nn->boot_time)
 		return 0;
 	dprintk("NFSD stale clientid (%08x/%08x) boot_time %08lx\n",
 		clid->cl_boot, clid->cl_id, nn->boot_time);
@@ -1558,6 +1540,9 @@ static struct nfs4_client *alloc_client(struct xdr_netobj name)
 	INIT_LIST_HEAD(&clp->cl_lru);
 	INIT_LIST_HEAD(&clp->cl_callbacks);
 	INIT_LIST_HEAD(&clp->cl_revoked);
+#ifdef CONFIG_NFSD_PNFS
+	INIT_LIST_HEAD(&clp->cl_lo_states);
+#endif
 	spin_lock_init(&clp->cl_lock);
 	rpc_init_wait_queue(&clp->cl_cb_waitq, "Backchannel slot table");
 	return clp;
@@ -1662,6 +1647,7 @@ __destroy_client(struct nfs4_client *clp)
 		nfs4_get_stateowner(&oo->oo_owner);
 		release_openowner(oo);
 	}
+	nfsd4_return_all_client_layouts(clp);
 	nfsd4_shutdown_callback(clp);
 	if (clp->cl_cb_conn.cb_xprt)
 		svc_xprt_put(clp->cl_cb_conn.cb_xprt);
@@ -2145,8 +2131,11 @@ nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp,
 static void
 nfsd4_set_ex_flags(struct nfs4_client *new, struct nfsd4_exchange_id *clid)
 {
-	/* pNFS is not supported */
+#ifdef CONFIG_NFSD_PNFS
+	new->cl_exchange_flags |= EXCHGID4_FLAG_USE_PNFS_MDS;
+#else
 	new->cl_exchange_flags |= EXCHGID4_FLAG_USE_NON_PNFS;
+#endif
 
 	/* Referrals are supported, Migration is not. */
 	new->cl_exchange_flags |= EXCHGID4_FLAG_SUPP_MOVED_REFER;
@@ -3074,6 +3063,10 @@ static void nfsd4_init_file(struct knfsd_fh *fh, unsigned int hashval,
 	fp->fi_share_deny = 0;
 	memset(fp->fi_fds, 0, sizeof(fp->fi_fds));
 	memset(fp->fi_access, 0, sizeof(fp->fi_access));
+#ifdef CONFIG_NFSD_PNFS
+	INIT_LIST_HEAD(&fp->fi_lo_states);
+	atomic_set(&fp->fi_lo_recalls, 0);
+#endif
 	hlist_add_head_rcu(&fp->fi_hash, &file_hashtbl[hashval]);
 }
 
@@ -3300,7 +3293,7 @@ find_file_locked(struct knfsd_fh *fh, unsigned int hashval)
 	struct nfs4_file *fp;
 
 	hlist_for_each_entry_rcu(fp, &file_hashtbl[hashval], fi_hash) {
-		if (nfsd_fh_match(&fp->fi_fhandle, fh)) {
+		if (fh_match(&fp->fi_fhandle, fh)) {
 			if (atomic_inc_not_zero(&fp->fi_ref))
 				return fp;
 		}
@@ -3308,7 +3301,7 @@ find_file_locked(struct knfsd_fh *fh, unsigned int hashval)
 	return NULL;
 }
 
-static struct nfs4_file *
+struct nfs4_file *
 find_file(struct knfsd_fh *fh)
 {
 	struct nfs4_file *fp;
@@ -3856,12 +3849,12 @@ static int nfs4_setlease(struct nfs4_delegation *dp)
 	/* Race breaker */
 	if (fp->fi_deleg_file) {
 		status = 0;
-		atomic_inc(&fp->fi_delegees);
+		++fp->fi_delegees;
 		hash_delegation_locked(dp, fp);
 		goto out_unlock;
 	}
 	fp->fi_deleg_file = filp;
-	atomic_set(&fp->fi_delegees, 1);
+	fp->fi_delegees = 1;
 	hash_delegation_locked(dp, fp);
 	spin_unlock(&fp->fi_lock);
 	spin_unlock(&state_lock);
@@ -3902,7 +3895,7 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh,
 		status = -EAGAIN;
 		goto out_unlock;
 	}
-	atomic_inc(&fp->fi_delegees);
+	++fp->fi_delegees;
 	hash_delegation_locked(dp, fp);
 	status = 0;
 out_unlock:
@@ -4295,7 +4288,7 @@ laundromat_main(struct work_struct *laundry)
 
 static inline __be32 nfs4_check_fh(struct svc_fh *fhp, struct nfs4_ol_stateid *stp)
 {
-	if (!nfsd_fh_match(&fhp->fh_handle, &stp->st_stid.sc_file->fi_fhandle))
+	if (!fh_match(&fhp->fh_handle, &stp->st_stid.sc_file->fi_fhandle))
 		return nfserr_bad_stateid;
 	return nfs_ok;
 }
@@ -4446,7 +4439,7 @@ static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid)
 	return status;
 }
 
-static __be32
+__be32
 nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate,
 		     stateid_t *stateid, unsigned char typemask,
 		     struct nfs4_stid **s, struct nfsd_net *nn)
@@ -4860,6 +4853,9 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	update_stateid(&stp->st_stid.sc_stateid);
 	memcpy(&close->cl_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t));
 
+	nfsd4_return_all_file_layouts(stp->st_stateowner->so_client,
+				      stp->st_stid.sc_file);
+
 	nfsd4_close_open_stateid(stp);
 
 	/* put reference from nfs4_preprocess_seqid_op */

fs/nfsd/nfs4xdr.c

@@ -47,6 +47,7 @@
 #include "state.h"
 #include "cache.h"
 #include "netns.h"
+#include "pnfs.h"
 
 #ifdef CONFIG_NFSD_V4_SECURITY_LABEL
 #include <linux/security.h>
@@ -234,6 +235,26 @@ static char *savemem(struct nfsd4_compoundargs *argp, __be32 *p, int nbytes)
 	return ret;
 }
 
+/*
+ * We require the high 32 bits of 'seconds' to be 0, and
+ * we ignore all 32 bits of 'nseconds'.
+ */
+static __be32
+nfsd4_decode_time(struct nfsd4_compoundargs *argp, struct timespec *tv)
+{
+	DECODE_HEAD;
+	u64 sec;
+
+	READ_BUF(12);
+	p = xdr_decode_hyper(p, &sec);
+	tv->tv_sec = sec;
+	tv->tv_nsec = be32_to_cpup(p++);
+	if (tv->tv_nsec >= (u32)1000000000)
+		return nfserr_inval;
+
+	DECODE_TAIL;
+}
+
 static __be32
 nfsd4_decode_bitmap(struct nfsd4_compoundargs *argp, u32 *bmval)
 {
@@ -267,7 +288,6 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
 {
 	int expected_len, len = 0;
 	u32 dummy32;
-	u64 sec;
 	char *buf;
 
 	DECODE_HEAD;
@@ -358,15 +378,10 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
 		dummy32 = be32_to_cpup(p++);
 		switch (dummy32) {
 		case NFS4_SET_TO_CLIENT_TIME:
-			/* We require the high 32 bits of 'seconds' to be 0, and we ignore
-			   all 32 bits of 'nseconds'. */
-			READ_BUF(12);
 			len += 12;
-			p = xdr_decode_hyper(p, &sec);
-			iattr->ia_atime.tv_sec = (time_t)sec;
-			iattr->ia_atime.tv_nsec = be32_to_cpup(p++);
-			if (iattr->ia_atime.tv_nsec >= (u32)1000000000)
-				return nfserr_inval;
+			status = nfsd4_decode_time(argp, &iattr->ia_atime);
+			if (status)
+				return status;
 			iattr->ia_valid |= (ATTR_ATIME | ATTR_ATIME_SET);
 			break;
 		case NFS4_SET_TO_SERVER_TIME:
@@ -382,15 +397,10 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
 		dummy32 = be32_to_cpup(p++);
 		switch (dummy32) {
 		case NFS4_SET_TO_CLIENT_TIME:
-			/* We require the high 32 bits of 'seconds' to be 0, and we ignore
-			   all 32 bits of 'nseconds'. */
-			READ_BUF(12);
 			len += 12;
-			p = xdr_decode_hyper(p, &sec);
-			iattr->ia_mtime.tv_sec = sec;
-			iattr->ia_mtime.tv_nsec = be32_to_cpup(p++);
-			if (iattr->ia_mtime.tv_nsec >= (u32)1000000000)
-				return nfserr_inval;
+			status = nfsd4_decode_time(argp, &iattr->ia_mtime);
+			if (status)
+				return status;
 			iattr->ia_valid |= (ATTR_MTIME | ATTR_MTIME_SET);
 			break;
 		case NFS4_SET_TO_SERVER_TIME:
@@ -1513,6 +1523,127 @@ static __be32 nfsd4_decode_reclaim_complete(struct nfsd4_compoundargs *argp, str
 	DECODE_TAIL;
 }
 
+#ifdef CONFIG_NFSD_PNFS
+static __be32
+nfsd4_decode_getdeviceinfo(struct nfsd4_compoundargs *argp,
+		struct nfsd4_getdeviceinfo *gdev)
+{
+	DECODE_HEAD;
+	u32 num, i;
+
+	READ_BUF(sizeof(struct nfsd4_deviceid) + 3 * 4);
+	COPYMEM(&gdev->gd_devid, sizeof(struct nfsd4_deviceid));
+	gdev->gd_layout_type = be32_to_cpup(p++);
+	gdev->gd_maxcount = be32_to_cpup(p++);
+	num = be32_to_cpup(p++);
+	if (num) {
+		READ_BUF(4 * num);
+		gdev->gd_notify_types = be32_to_cpup(p++);
+		for (i = 1; i < num; i++) {
+			if (be32_to_cpup(p++)) {
+				status = nfserr_inval;
+				goto out;
+			}
+		}
+	}
+	DECODE_TAIL;
+}
+
+static __be32
+nfsd4_decode_layoutget(struct nfsd4_compoundargs *argp,
+		struct nfsd4_layoutget *lgp)
+{
+	DECODE_HEAD;
+
+	READ_BUF(36);
+	lgp->lg_signal = be32_to_cpup(p++);
+	lgp->lg_layout_type = be32_to_cpup(p++);
+	lgp->lg_seg.iomode = be32_to_cpup(p++);
+	p = xdr_decode_hyper(p, &lgp->lg_seg.offset);
+	p = xdr_decode_hyper(p, &lgp->lg_seg.length);
+	p = xdr_decode_hyper(p, &lgp->lg_minlength);
+	nfsd4_decode_stateid(argp, &lgp->lg_sid);
+	READ_BUF(4);
+	lgp->lg_maxcount = be32_to_cpup(p++);
+
+	DECODE_TAIL;
+}
+
+static __be32
+nfsd4_decode_layoutcommit(struct nfsd4_compoundargs *argp,
+		struct nfsd4_layoutcommit *lcp)
+{
+	DECODE_HEAD;
+	u32 timechange;
+
+	READ_BUF(20);
+	p = xdr_decode_hyper(p, &lcp->lc_seg.offset);
+	p = xdr_decode_hyper(p, &lcp->lc_seg.length);
+	lcp->lc_reclaim = be32_to_cpup(p++);
+	nfsd4_decode_stateid(argp, &lcp->lc_sid);
+	READ_BUF(4);
+	lcp->lc_newoffset = be32_to_cpup(p++);
+	if (lcp->lc_newoffset) {
+		READ_BUF(8);
+		p = xdr_decode_hyper(p, &lcp->lc_last_wr);
+	} else
+		lcp->lc_last_wr = 0;
+	READ_BUF(4);
+	timechange = be32_to_cpup(p++);
+	if (timechange) {
+		status = nfsd4_decode_time(argp, &lcp->lc_mtime);
+		if (status)
+			return status;
+	} else {
+		lcp->lc_mtime.tv_nsec = UTIME_NOW;
+	}
+	READ_BUF(8);
+	lcp->lc_layout_type = be32_to_cpup(p++);
+
+	/*
+	 * Save the layout update in XDR format and let the layout driver deal
+	 * with it later.
+	 */
+	lcp->lc_up_len = be32_to_cpup(p++);
+	if (lcp->lc_up_len > 0) {
+		READ_BUF(lcp->lc_up_len);
+		READMEM(lcp->lc_up_layout, lcp->lc_up_len);
+	}
+
+	DECODE_TAIL;
+}
+
+static __be32
+nfsd4_decode_layoutreturn(struct nfsd4_compoundargs *argp,
+		struct nfsd4_layoutreturn *lrp)
+{
+	DECODE_HEAD;
+
+	READ_BUF(16);
+	lrp->lr_reclaim = be32_to_cpup(p++);
+	lrp->lr_layout_type = be32_to_cpup(p++);
+	lrp->lr_seg.iomode = be32_to_cpup(p++);
+	lrp->lr_return_type = be32_to_cpup(p++);
+	if (lrp->lr_return_type == RETURN_FILE) {
+		READ_BUF(16);
+		p = xdr_decode_hyper(p, &lrp->lr_seg.offset);
+		p = xdr_decode_hyper(p, &lrp->lr_seg.length);
+		nfsd4_decode_stateid(argp, &lrp->lr_sid);
+		READ_BUF(4);
+		lrp->lrf_body_len = be32_to_cpup(p++);
+		if (lrp->lrf_body_len > 0) {
+			READ_BUF(lrp->lrf_body_len);
+			READMEM(lrp->lrf_body, lrp->lrf_body_len);
+		}
+	} else {
+		lrp->lr_seg.offset = 0;
+		lrp->lr_seg.length = NFS4_MAX_UINT64;
+	}
+
+	DECODE_TAIL;
+}
+#endif /* CONFIG_NFSD_PNFS */
+
 static __be32
 nfsd4_decode_fallocate(struct nfsd4_compoundargs *argp,
 		       struct nfsd4_fallocate *fallocate)
@@ -1607,11 +1738,19 @@ static nfsd4_dec nfsd4_dec_ops[] = {
 	[OP_DESTROY_SESSION]	= (nfsd4_dec)nfsd4_decode_destroy_session,
 	[OP_FREE_STATEID]	= (nfsd4_dec)nfsd4_decode_free_stateid,
 	[OP_GET_DIR_DELEGATION]	= (nfsd4_dec)nfsd4_decode_notsupp,
+#ifdef CONFIG_NFSD_PNFS
+	[OP_GETDEVICEINFO]	= (nfsd4_dec)nfsd4_decode_getdeviceinfo,
+	[OP_GETDEVICELIST]	= (nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_LAYOUTCOMMIT]	= (nfsd4_dec)nfsd4_decode_layoutcommit,
+	[OP_LAYOUTGET]		= (nfsd4_dec)nfsd4_decode_layoutget,
+	[OP_LAYOUTRETURN]	= (nfsd4_dec)nfsd4_decode_layoutreturn,
+#else
 	[OP_GETDEVICEINFO]	= (nfsd4_dec)nfsd4_decode_notsupp,
 	[OP_GETDEVICELIST]	= (nfsd4_dec)nfsd4_decode_notsupp,
 	[OP_LAYOUTCOMMIT]	= (nfsd4_dec)nfsd4_decode_notsupp,
 	[OP_LAYOUTGET]		= (nfsd4_dec)nfsd4_decode_notsupp,
 	[OP_LAYOUTRETURN]	= (nfsd4_dec)nfsd4_decode_notsupp,
+#endif
 	[OP_SECINFO_NO_NAME]	= (nfsd4_dec)nfsd4_decode_secinfo_no_name,
 	[OP_SEQUENCE]		= (nfsd4_dec)nfsd4_decode_sequence,
 	[OP_SET_SSV]		= (nfsd4_dec)nfsd4_decode_notsupp,
@@ -2539,6 +2678,30 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp,
 			get_parent_attributes(exp, &stat);
 		p = xdr_encode_hyper(p, stat.ino);
 	}
+#ifdef CONFIG_NFSD_PNFS
+	if ((bmval1 & FATTR4_WORD1_FS_LAYOUT_TYPES) ||
+	    (bmval2 & FATTR4_WORD2_LAYOUT_TYPES)) {
+		if (exp->ex_layout_type) {
+			p = xdr_reserve_space(xdr, 8);
+			if (!p)
+				goto out_resource;
+			*p++ = cpu_to_be32(1);
+			*p++ = cpu_to_be32(exp->ex_layout_type);
+		} else {
+			p = xdr_reserve_space(xdr, 4);
+			if (!p)
+				goto out_resource;
+			*p++ = cpu_to_be32(0);
+		}
+	}
+
+	if (bmval2 & FATTR4_WORD2_LAYOUT_BLKSIZE) {
+		p = xdr_reserve_space(xdr, 4);
+		if (!p)
+			goto out_resource;
+		*p++ = cpu_to_be32(stat.blksize);
+	}
+#endif /* CONFIG_NFSD_PNFS */
 	if (bmval2 & FATTR4_WORD2_SECURITY_LABEL) {
 		status = nfsd4_encode_security_label(xdr, rqstp, context,
 								contextlen);
@@ -2768,16 +2931,17 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen,
 	if (entry_bytes > cd->rd_maxcount)
 		goto fail;
 	cd->rd_maxcount -= entry_bytes;
-	if (!cd->rd_dircount)
-		goto fail;
 	/*
 	 * RFC 3530 14.2.24 describes rd_dircount as only a "hint", so
 	 * let's always let through the first entry, at least:
 	 */
-	name_and_cookie = 4 * XDR_QUADLEN(namlen) + 8;
+	if (!cd->rd_dircount)
+		goto fail;
+	name_and_cookie = 4 + 4 * XDR_QUADLEN(namlen) + 8;
 	if (name_and_cookie > cd->rd_dircount && cd->cookie_offset)
 		goto fail;
 	cd->rd_dircount -= min(cd->rd_dircount, name_and_cookie);
+
 	cd->cookie_offset = cookie_offset;
 skip_entry:
 	cd->common.err = nfs_ok;
@@ -3814,6 +3978,156 @@ nfsd4_encode_test_stateid(struct nfsd4_compoundres *resp, __be32 nfserr,
 	return nfserr;
 }
 
+#ifdef CONFIG_NFSD_PNFS
+static __be32
+nfsd4_encode_getdeviceinfo(struct nfsd4_compoundres *resp, __be32 nfserr,
+		struct nfsd4_getdeviceinfo *gdev)
+{
+	struct xdr_stream *xdr = &resp->xdr;
+	const struct nfsd4_layout_ops *ops =
+		nfsd4_layout_ops[gdev->gd_layout_type];
+	u32 starting_len = xdr->buf->len, needed_len;
+	__be32 *p;
+
+	dprintk("%s: err %d\n", __func__, nfserr);
+	if (nfserr)
+		goto out;
+
+	nfserr = nfserr_resource;
+	p = xdr_reserve_space(xdr, 4);
+	if (!p)
+		goto out;
+
+	*p++ = cpu_to_be32(gdev->gd_layout_type);
+
+	/* If maxcount is 0 then just update notifications */
+	if (gdev->gd_maxcount != 0) {
+		nfserr = ops->encode_getdeviceinfo(xdr, gdev);
+		if (nfserr) {
+			/*
+			 * We don't bother to burden the layout drivers with
+			 * enforcing gd_maxcount, just tell the client to
+			 * come back with a bigger buffer if it's not enough.
+			 */
+			if (xdr->buf->len + 4 > gdev->gd_maxcount)
+				goto toosmall;
+			goto out;
+		}
+	}
+
+	nfserr = nfserr_resource;
+	if (gdev->gd_notify_types) {
+		p = xdr_reserve_space(xdr, 4 + 4);
+		if (!p)
+			goto out;
+		*p++ = cpu_to_be32(1);			/* bitmap length */
+		*p++ = cpu_to_be32(gdev->gd_notify_types);
+	} else {
+		p = xdr_reserve_space(xdr, 4);
+		if (!p)
+			goto out;
+		*p++ = 0;
+	}
+
+	nfserr = 0;
+out:
+	kfree(gdev->gd_device);
+	dprintk("%s: done: %d\n", __func__, be32_to_cpu(nfserr));
+	return nfserr;
+
+toosmall:
+	dprintk("%s: maxcount too small\n", __func__);
+	needed_len = xdr->buf->len + 4 /* notifications */;
+	xdr_truncate_encode(xdr, starting_len);
+	p = xdr_reserve_space(xdr, 4);
+	if (!p) {
+		nfserr = nfserr_resource;
+	} else {
+		*p++ = cpu_to_be32(needed_len);
+		nfserr = nfserr_toosmall;
+	}
+	goto out;
+}
+
+static __be32
+nfsd4_encode_layoutget(struct nfsd4_compoundres *resp, __be32 nfserr,
+		struct nfsd4_layoutget *lgp)
+{
+	struct xdr_stream *xdr = &resp->xdr;
+	const struct nfsd4_layout_ops *ops =
+		nfsd4_layout_ops[lgp->lg_layout_type];
+	__be32 *p;
+
+	dprintk("%s: err %d\n", __func__, nfserr);
+	if (nfserr)
+		goto out;
+
+	nfserr = nfserr_resource;
+	p = xdr_reserve_space(xdr, 36 + sizeof(stateid_opaque_t));
+	if (!p)
+		goto out;
+
+	*p++ = cpu_to_be32(1);	/* we always set return-on-close */
+	*p++ = cpu_to_be32(lgp->lg_sid.si_generation);
+	p = xdr_encode_opaque_fixed(p, &lgp->lg_sid.si_opaque,
+				    sizeof(stateid_opaque_t));
+
+	*p++ = cpu_to_be32(1);	/* we always return a single layout */
+	p = xdr_encode_hyper(p, lgp->lg_seg.offset);
+	p = xdr_encode_hyper(p, lgp->lg_seg.length);
+	*p++ = cpu_to_be32(lgp->lg_seg.iomode);
+	*p++ = cpu_to_be32(lgp->lg_layout_type);
+
+	nfserr = ops->encode_layoutget(xdr, lgp);
+out:
+	kfree(lgp->lg_content);
+	return nfserr;
+}
+
+static __be32
+nfsd4_encode_layoutcommit(struct nfsd4_compoundres *resp, __be32 nfserr,
+			  struct nfsd4_layoutcommit *lcp)
+{
+	struct xdr_stream *xdr = &resp->xdr;
+	__be32 *p;
+
+	if (nfserr)
+		return nfserr;
+
+	p = xdr_reserve_space(xdr, 4);
+	if (!p)
+		return nfserr_resource;
+	*p++ = cpu_to_be32(lcp->lc_size_chg);
+	if (lcp->lc_size_chg) {
+		p = xdr_reserve_space(xdr, 8);
+		if (!p)
+			return nfserr_resource;
+		p = xdr_encode_hyper(p, lcp->lc_newsize);
+	}
+
+	return nfs_ok;
+}
+
+static __be32
+nfsd4_encode_layoutreturn(struct nfsd4_compoundres *resp, __be32 nfserr,
+		struct nfsd4_layoutreturn *lrp)
+{
+	struct xdr_stream *xdr = &resp->xdr;
+	__be32 *p;
+
+	if (nfserr)
+		return nfserr;
+
+	p = xdr_reserve_space(xdr, 4);
+	if (!p)
+		return nfserr_resource;
+	*p++ = cpu_to_be32(lrp->lrs_present);
+	if (lrp->lrs_present)
+		nfsd4_encode_stateid(xdr, &lrp->lr_sid);
+	return nfs_ok;
+}
+#endif /* CONFIG_NFSD_PNFS */
+
 static __be32
 nfsd4_encode_seek(struct nfsd4_compoundres *resp, __be32 nfserr,
 		  struct nfsd4_seek *seek)
@@ -3890,11 +4204,19 @@ static nfsd4_enc nfsd4_enc_ops[] = {
 	[OP_DESTROY_SESSION]	= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_FREE_STATEID]	= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_GET_DIR_DELEGATION]	= (nfsd4_enc)nfsd4_encode_noop,
+#ifdef CONFIG_NFSD_PNFS
+	[OP_GETDEVICEINFO]	= (nfsd4_enc)nfsd4_encode_getdeviceinfo,
+	[OP_GETDEVICELIST]	= (nfsd4_enc)nfsd4_encode_noop,
+	[OP_LAYOUTCOMMIT]	= (nfsd4_enc)nfsd4_encode_layoutcommit,
+	[OP_LAYOUTGET]		= (nfsd4_enc)nfsd4_encode_layoutget,
+	[OP_LAYOUTRETURN]	= (nfsd4_enc)nfsd4_encode_layoutreturn,
+#else
 	[OP_GETDEVICEINFO]	= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_GETDEVICELIST]	= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_LAYOUTCOMMIT]	= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_LAYOUTGET]		= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_LAYOUTRETURN]	= (nfsd4_enc)nfsd4_encode_noop,
+#endif
 	[OP_SECINFO_NO_NAME]	= (nfsd4_enc)nfsd4_encode_secinfo_no_name,
 	[OP_SEQUENCE]		= (nfsd4_enc)nfsd4_encode_sequence,
 	[OP_SET_SSV]		= (nfsd4_enc)nfsd4_encode_noop,

fs/nfsd/nfsctl.c

@@ -21,6 +21,7 @@
 #include "cache.h"
 #include "state.h"
 #include "netns.h"
+#include "pnfs.h"
 
 /*
  *	We have a single directory with several nodes in it.
@@ -1258,9 +1259,12 @@ static int __init init_nfsd(void)
 	retval = nfsd4_init_slabs();
 	if (retval)
 		goto out_unregister_pernet;
-	retval = nfsd_fault_inject_init(); /* nfsd fault injection controls */
+	retval = nfsd4_init_pnfs();
 	if (retval)
 		goto out_free_slabs;
+	retval = nfsd_fault_inject_init(); /* nfsd fault injection controls */
+	if (retval)
+		goto out_exit_pnfs;
 	nfsd_stat_init();	/* Statistics */
 	retval = nfsd_reply_cache_init();
 	if (retval)
@@ -1282,6 +1286,8 @@ static int __init init_nfsd(void)
 out_free_stat:
 	nfsd_stat_shutdown();
 	nfsd_fault_inject_cleanup();
+out_exit_pnfs:
+	nfsd4_exit_pnfs();
 out_free_slabs:
 	nfsd4_free_slabs();
 out_unregister_pernet:
@@ -1299,6 +1305,7 @@ static void __exit exit_nfsd(void)
 	nfsd_stat_shutdown();
 	nfsd_lockd_shutdown();
 	nfsd4_free_slabs();
+	nfsd4_exit_pnfs();
 	nfsd_fault_inject_cleanup();
 	unregister_filesystem(&nfsd_fs_type);
 	unregister_pernet_subsys(&nfsd_net_ops);

fs/nfsd/nfsd.h

@@ -325,15 +325,27 @@ void		nfsd_lockd_shutdown(void);
 
 #define NFSD4_SUPPORTED_ATTRS_WORD2 0
 
+/* 4.1 */
+#ifdef CONFIG_NFSD_PNFS
+#define PNFSD_SUPPORTED_ATTRS_WORD1	FATTR4_WORD1_FS_LAYOUT_TYPES
+#define PNFSD_SUPPORTED_ATTRS_WORD2 \
+(FATTR4_WORD2_LAYOUT_BLKSIZE	| FATTR4_WORD2_LAYOUT_TYPES)
+#else
+#define PNFSD_SUPPORTED_ATTRS_WORD1	0
+#define PNFSD_SUPPORTED_ATTRS_WORD2	0
+#endif /* CONFIG_NFSD_PNFS */
+
 #define NFSD4_1_SUPPORTED_ATTRS_WORD0 \
 	NFSD4_SUPPORTED_ATTRS_WORD0
 
 #define NFSD4_1_SUPPORTED_ATTRS_WORD1 \
-	NFSD4_SUPPORTED_ATTRS_WORD1
+	(NFSD4_SUPPORTED_ATTRS_WORD1	| PNFSD_SUPPORTED_ATTRS_WORD1)
 
 #define NFSD4_1_SUPPORTED_ATTRS_WORD2 \
-	(NFSD4_SUPPORTED_ATTRS_WORD2 | FATTR4_WORD2_SUPPATTR_EXCLCREAT)
+	(NFSD4_SUPPORTED_ATTRS_WORD2	| PNFSD_SUPPORTED_ATTRS_WORD2 | \
+	 FATTR4_WORD2_SUPPATTR_EXCLCREAT)
 
+/* 4.2 */
 #ifdef CONFIG_NFSD_V4_SECURITY_LABEL
 #define NFSD4_2_SECURITY_ATTRS		FATTR4_WORD2_SECURITY_LABEL
 #else

fs/nfsd/nfsfh.h

@@ -187,6 +187,24 @@ fh_init(struct svc_fh *fhp, int maxsize)
 	return fhp;
 }
 
+static inline bool fh_match(struct knfsd_fh *fh1, struct knfsd_fh *fh2)
+{
+	if (fh1->fh_size != fh2->fh_size)
+		return false;
+	if (memcmp(fh1->fh_base.fh_pad, fh2->fh_base.fh_pad, fh1->fh_size) != 0)
+		return false;
+	return true;
+}
+
+static inline bool fh_fsid_match(struct knfsd_fh *fh1, struct knfsd_fh *fh2)
+{
+	if (fh1->fh_fsid_type != fh2->fh_fsid_type)
+		return false;
+	if (memcmp(fh1->fh_fsid, fh2->fh_fsid, key_len(fh1->fh_fsid_type) != 0))
+		return false;
+	return true;
+}
+
 #ifdef CONFIG_NFSD_V3
 /*
  * The wcc data stored in current_fh should be cleared

fs/nfsd/nfssvc.c

@@ -119,6 +119,7 @@ struct svc_program		nfsd_program = {
 static bool nfsd_supported_minorversions[NFSD_SUPPORTED_MINOR_VERSION + 1] = {
 	[0] = 1,
 	[1] = 1,
+	[2] = 1,
 };
 
 int nfsd_vers(int vers, enum vers_op change)

fs/nfsd/pnfs.h

@@ -0,0 +1,81 @@
+#ifndef _FS_NFSD_PNFS_H
+#define _FS_NFSD_PNFS_H 1
+
+#include <linux/exportfs.h>
+#include <linux/nfsd/export.h>
+
+#include "state.h"
+#include "xdr4.h"
+
+struct xdr_stream;
+
+struct nfsd4_deviceid_map {
+	struct list_head	hash;
+	u64			idx;
+	int			fsid_type;
+	u32			fsid[];
+};
+
+struct nfsd4_layout_ops {
+	u32		notify_types;
+
+	__be32 (*proc_getdeviceinfo)(struct super_block *sb,
+			struct nfsd4_getdeviceinfo *gdevp);
+	__be32 (*encode_getdeviceinfo)(struct xdr_stream *xdr,
+			struct nfsd4_getdeviceinfo *gdevp);
+
+	__be32 (*proc_layoutget)(struct inode *, const struct svc_fh *fhp,
+			struct nfsd4_layoutget *lgp);
+	__be32 (*encode_layoutget)(struct xdr_stream *,
+			struct nfsd4_layoutget *lgp);
+
+	__be32 (*proc_layoutcommit)(struct inode *inode,
+			struct nfsd4_layoutcommit *lcp);
+};
+
+extern const struct nfsd4_layout_ops *nfsd4_layout_ops[];
+extern const struct nfsd4_layout_ops bl_layout_ops;
+
+__be32 nfsd4_preprocess_layout_stateid(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate, stateid_t *stateid,
+		bool create, u32 layout_type, struct nfs4_layout_stateid **lsp);
+__be32 nfsd4_insert_layout(struct nfsd4_layoutget *lgp,
+		struct nfs4_layout_stateid *ls);
+__be32 nfsd4_return_file_layouts(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		struct nfsd4_layoutreturn *lrp);
+__be32 nfsd4_return_client_layouts(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		struct nfsd4_layoutreturn *lrp);
+int nfsd4_set_deviceid(struct nfsd4_deviceid *id, const struct svc_fh *fhp,
+		u32 device_generation);
+struct nfsd4_deviceid_map *nfsd4_find_devid_map(int idx);
+
+#ifdef CONFIG_NFSD_PNFS
+void nfsd4_setup_layout_type(struct svc_export *exp);
+void nfsd4_return_all_client_layouts(struct nfs4_client *);
+void nfsd4_return_all_file_layouts(struct nfs4_client *clp,
+		struct nfs4_file *fp);
+int nfsd4_init_pnfs(void);
+void nfsd4_exit_pnfs(void);
+#else
+static inline void nfsd4_setup_layout_type(struct svc_export *exp)
+{
+}
+
+static inline void nfsd4_return_all_client_layouts(struct nfs4_client *clp)
+{
+}
+static inline void nfsd4_return_all_file_layouts(struct nfs4_client *clp,
+		struct nfs4_file *fp)
+{
+}
+static inline void nfsd4_exit_pnfs(void)
+{
+}
+static inline int nfsd4_init_pnfs(void)
+{
+	return 0;
+}
+#endif /* CONFIG_NFSD_PNFS */
+#endif /* _FS_NFSD_PNFS_H */

fs/nfsd/state.h

@@ -92,6 +92,7 @@ struct nfs4_stid {
 /* For a deleg stateid kept around only to process free_stateid's: */
 #define NFS4_REVOKED_DELEG_STID 16
 #define NFS4_CLOSED_DELEG_STID 32
+#define NFS4_LAYOUT_STID 64
 	unsigned char sc_type;
 	stateid_t sc_stateid;
 	struct nfs4_client *sc_client;
@@ -297,6 +298,9 @@ struct nfs4_client {
 	struct list_head	cl_delegations;
 	struct list_head	cl_revoked;	/* unacknowledged, revoked 4.1 state */
 	struct list_head        cl_lru;         /* tail queue */
+#ifdef CONFIG_NFSD_PNFS
+	struct list_head	cl_lo_states;	/* outstanding layout states */
+#endif
 	struct xdr_netobj	cl_name; 	/* id generated by client */
 	nfs4_verifier		cl_verifier; 	/* generated by client */
 	time_t                  cl_time;        /* time of last lease renewal */
@@ -493,9 +497,13 @@ struct nfs4_file {
 	atomic_t		fi_access[2];
 	u32			fi_share_deny;
 	struct file		*fi_deleg_file;
-	atomic_t		fi_delegees;
+	int			fi_delegees;
 	struct knfsd_fh		fi_fhandle;
 	bool			fi_had_conflict;
+#ifdef CONFIG_NFSD_PNFS
+	struct list_head	fi_lo_states;
+	atomic_t		fi_lo_recalls;
+#endif
 };
 
 /*
@@ -528,6 +536,24 @@ static inline struct nfs4_ol_stateid *openlockstateid(struct nfs4_stid *s)
 	return container_of(s, struct nfs4_ol_stateid, st_stid);
 }
 
+struct nfs4_layout_stateid {
+	struct nfs4_stid		ls_stid;
+	struct list_head		ls_perclnt;
+	struct list_head		ls_perfile;
+	spinlock_t			ls_lock;
+	struct list_head		ls_layouts;
+	u32				ls_layout_type;
+	struct file			*ls_file;
+	struct nfsd4_callback		ls_recall;
+	stateid_t			ls_recall_sid;
+	bool				ls_recalled;
+};
+
+static inline struct nfs4_layout_stateid *layoutstateid(struct nfs4_stid *s)
+{
+	return container_of(s, struct nfs4_layout_stateid, ls_stid);
+}
+
 /* flags for preprocess_seqid_op() */
 #define RD_STATE	        0x00000010
 #define WR_STATE	        0x00000020
@@ -535,6 +561,7 @@ static inline struct nfs4_ol_stateid *openlockstateid(struct nfs4_stid *s)
 enum nfsd4_cb_op {
 	NFSPROC4_CLNT_CB_NULL = 0,
 	NFSPROC4_CLNT_CB_RECALL,
+	NFSPROC4_CLNT_CB_LAYOUT,
 	NFSPROC4_CLNT_CB_SEQUENCE,
 };
 
@@ -545,6 +572,12 @@ struct nfsd_net;
 extern __be32 nfs4_preprocess_stateid_op(struct net *net,
 		struct nfsd4_compound_state *cstate,
 		stateid_t *stateid, int flags, struct file **filp);
+__be32 nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate,
+		     stateid_t *stateid, unsigned char typemask,
+		     struct nfs4_stid **s, struct nfsd_net *nn);
+struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl,
+		struct kmem_cache *slab);
+void nfs4_unhash_stid(struct nfs4_stid *s);
 void nfs4_put_stid(struct nfs4_stid *s);
 void nfs4_remove_reclaim_record(struct nfs4_client_reclaim *, struct nfsd_net *);
 extern void nfs4_release_reclaim(struct nfsd_net *);
@@ -567,6 +600,14 @@ extern struct nfs4_client_reclaim *nfs4_client_to_reclaim(const char *name,
 							struct nfsd_net *nn);
 extern bool nfs4_has_reclaimed_state(const char *name, struct nfsd_net *nn);
 
+struct nfs4_file *find_file(struct knfsd_fh *fh);
+void put_nfs4_file(struct nfs4_file *fi);
+static inline void get_nfs4_file(struct nfs4_file *fi)
+{
+	atomic_inc(&fi->fi_ref);
+}
+struct file *find_any_file(struct nfs4_file *f);
+
 /* grace period management */
 void nfsd4_end_grace(struct nfsd_net *nn);
 

fs/nfsd/trace.c

@@ -0,0 +1,5 @@
+
+#include "state.h"
+
+#define CREATE_TRACE_POINTS
+#include "trace.h"

fs/nfsd/trace.h

@@ -0,0 +1,54 @@
+/*
+ * Copyright (c) 2014 Christoph Hellwig.
+ */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM nfsd
+
+#if !defined(_NFSD_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _NFSD_TRACE_H
+
+#include <linux/tracepoint.h>
+
+DECLARE_EVENT_CLASS(nfsd_stateid_class,
+	TP_PROTO(stateid_t *stp),
+	TP_ARGS(stp),
+	TP_STRUCT__entry(
+		__field(u32, cl_boot)
+		__field(u32, cl_id)
+		__field(u32, si_id)
+		__field(u32, si_generation)
+	),
+	TP_fast_assign(
+		__entry->cl_boot = stp->si_opaque.so_clid.cl_boot;
+		__entry->cl_id = stp->si_opaque.so_clid.cl_id;
+		__entry->si_id = stp->si_opaque.so_id;
+		__entry->si_generation = stp->si_generation;
+	),
+	TP_printk("client %08x:%08x stateid %08x:%08x",
+		__entry->cl_boot,
+		__entry->cl_id,
+		__entry->si_id,
+		__entry->si_generation)
+)
+
+#define DEFINE_STATEID_EVENT(name) \
+DEFINE_EVENT(nfsd_stateid_class, name, \
+	TP_PROTO(stateid_t *stp), \
+	TP_ARGS(stp))
+DEFINE_STATEID_EVENT(layoutstate_alloc);
+DEFINE_STATEID_EVENT(layoutstate_unhash);
+DEFINE_STATEID_EVENT(layoutstate_free);
+DEFINE_STATEID_EVENT(layout_get_lookup_fail);
+DEFINE_STATEID_EVENT(layout_commit_lookup_fail);
+DEFINE_STATEID_EVENT(layout_return_lookup_fail);
+DEFINE_STATEID_EVENT(layout_recall);
+DEFINE_STATEID_EVENT(layout_recall_done);
+DEFINE_STATEID_EVENT(layout_recall_fail);
+DEFINE_STATEID_EVENT(layout_recall_release);
+
+#endif /* _NFSD_TRACE_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE trace
+#include <trace/define_trace.h>

fs/nfsd/xdr4.h

@@ -428,6 +428,61 @@ struct nfsd4_reclaim_complete {
 	u32 rca_one_fs;
 };
 
+struct nfsd4_deviceid {
+	u64			fsid_idx;
+	u32			generation;
+	u32			pad;
+};
+
+struct nfsd4_layout_seg {
+	u32			iomode;
+	u64			offset;
+	u64			length;
+};
+
+struct nfsd4_getdeviceinfo {
+	struct nfsd4_deviceid	gd_devid;	/* request */
+	u32			gd_layout_type;	/* request */
+	u32			gd_maxcount;	/* request */
+	u32			gd_notify_types;/* request - response */
+	void			*gd_device;	/* response */
+};
+
+struct nfsd4_layoutget {
+	u64			lg_minlength;	/* request */
+	u32			lg_signal;	/* request */
+	u32			lg_layout_type;	/* request */
+	u32			lg_maxcount;	/* request */
+	stateid_t		lg_sid;		/* request/response */
+	struct nfsd4_layout_seg	lg_seg;		/* request/response */
+	void			*lg_content;	/* response */
+};
+
+struct nfsd4_layoutcommit {
+	stateid_t		lc_sid;		/* request */
+	struct nfsd4_layout_seg	lc_seg;		/* request */
+	u32			lc_reclaim;	/* request */
+	u32			lc_newoffset;	/* request */
+	u64			lc_last_wr;	/* request */
+	struct timespec		lc_mtime;	/* request */
+	u32			lc_layout_type;	/* request */
+	u32			lc_up_len;	/* layout length */
+	void			*lc_up_layout;	/* decoded by callback */
+	u32			lc_size_chg;	/* boolean for response */
+	u64			lc_newsize;	/* response */
+};
+
+struct nfsd4_layoutreturn {
+	u32			lr_return_type;	/* request */
+	u32			lr_layout_type;	/* request */
+	struct nfsd4_layout_seg	lr_seg;		/* request */
+	u32			lr_reclaim;	/* request */
+	u32			lrf_body_len;	/* request */
+	void			*lrf_body;	/* request */
+	stateid_t		lr_sid;		/* request/response */
+	u32			lrs_present;	/* response */
+};
+
 struct nfsd4_fallocate {
 	/* request */
 	stateid_t	falloc_stateid;
@@ -491,6 +546,10 @@ struct nfsd4_op {
 		struct nfsd4_reclaim_complete	reclaim_complete;
 		struct nfsd4_test_stateid	test_stateid;
 		struct nfsd4_free_stateid	free_stateid;
+		struct nfsd4_getdeviceinfo	getdeviceinfo;
+		struct nfsd4_layoutget		layoutget;
+		struct nfsd4_layoutcommit	layoutcommit;
+		struct nfsd4_layoutreturn	layoutreturn;
 
 		/* NFSv4.2 */
 		struct nfsd4_fallocate		allocate;

fs/nfsd/xdr4cb.h

@@ -21,3 +21,10 @@
 #define NFS4_dec_cb_recall_sz		(cb_compound_dec_hdr_sz  +      \
 					cb_sequence_dec_sz +            \
 					op_dec_sz)
+#define NFS4_enc_cb_layout_sz		(cb_compound_enc_hdr_sz +       \
+					cb_sequence_enc_sz +            \
+					1 + 3 +                         \
+					enc_nfs4_fh_sz + 4)
+#define NFS4_dec_cb_layout_sz		(cb_compound_dec_hdr_sz  +      \
+					cb_sequence_dec_sz +            \
+					op_dec_sz)

include/linux/exportfs.h

@@ -4,6 +4,7 @@
 #include <linux/types.h>
 
 struct dentry;
+struct iattr;
 struct inode;
 struct super_block;
 struct vfsmount;
@@ -180,6 +181,21 @@ struct fid {
  *    get_name is not (which is possibly inconsistent)
  */
 
+/* types of block ranges for multipage write mappings. */
+#define IOMAP_HOLE	0x01	/* no blocks allocated, need allocation */
+#define IOMAP_DELALLOC	0x02	/* delayed allocation blocks */
+#define IOMAP_MAPPED	0x03	/* blocks allocated @blkno */
+#define IOMAP_UNWRITTEN	0x04	/* blocks allocated @blkno in unwritten state */
+
+#define IOMAP_NULL_BLOCK -1LL	/* blkno is not valid */
+
+struct iomap {
+	sector_t	blkno;	/* first sector of mapping */
+	loff_t		offset;	/* file offset of mapping, bytes */
+	u64		length;	/* length of mapping, bytes */
+	int		type;	/* type of mapping */
+};
+
 struct export_operations {
 	int (*encode_fh)(struct inode *inode, __u32 *fh, int *max_len,
 			struct inode *parent);
@@ -191,6 +207,13 @@ struct export_operations {
 			struct dentry *child);
 	struct dentry * (*get_parent)(struct dentry *child);
 	int (*commit_metadata)(struct inode *inode);
+
+	int (*get_uuid)(struct super_block *sb, u8 *buf, u32 *len, u64 *offset);
+	int (*map_blocks)(struct inode *inode, loff_t offset,
+			  u64 len, struct iomap *iomap,
+			  bool write, u32 *device_generation);
+	int (*commit_blocks)(struct inode *inode, struct iomap *iomaps,
+			     int nr_iomaps, struct iattr *iattr);
 };
 
 extern int exportfs_encode_inode_fh(struct inode *inode, struct fid *fid,

include/linux/fs.h

@@ -873,6 +873,7 @@ static inline struct file *get_file(struct file *f)
 #define FL_DOWNGRADE_PENDING	256 /* Lease is being downgraded */
 #define FL_UNLOCK_PENDING	512 /* Lease is being broken */
 #define FL_OFDLCK	1024	/* lock is "owned" by struct file */
+#define FL_LAYOUT	2048	/* outstanding pNFS layout */
 
 /*
  * Special return value from posix_lock_file() and vfs_lock_file() for
@@ -2035,6 +2036,16 @@ static inline int break_deleg_wait(struct inode **delegated_inode)
 	return ret;
 }
 
+static inline int break_layout(struct inode *inode, bool wait)
+{
+	smp_mb();
+	if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease))
+		return __break_lease(inode,
+				wait ? O_WRONLY : O_WRONLY | O_NONBLOCK,
+				FL_LAYOUT);
+	return 0;
+}
+
 #else /* !CONFIG_FILE_LOCKING */
 static inline int locks_mandatory_locked(struct file *file)
 {
@@ -2090,6 +2101,11 @@ static inline int break_deleg_wait(struct inode **delegated_inode)
 	return 0;
 }
 
+static inline int break_layout(struct inode *inode, bool wait)
+{
+	return 0;
+}
+
 #endif /* CONFIG_FILE_LOCKING */
 
 /* fs/open.c */

include/linux/nfs4.h

@@ -411,6 +411,7 @@ enum lock_type4 {
 #define FATTR4_WORD1_TIME_MODIFY_SET    (1UL << 22)
 #define FATTR4_WORD1_MOUNTED_ON_FILEID  (1UL << 23)
 #define FATTR4_WORD1_FS_LAYOUT_TYPES    (1UL << 30)
+#define FATTR4_WORD2_LAYOUT_TYPES       (1UL << 0)
 #define FATTR4_WORD2_LAYOUT_BLKSIZE     (1UL << 1)
 #define FATTR4_WORD2_MDSTHRESHOLD       (1UL << 4)
 #define FATTR4_WORD2_SECURITY_LABEL     (1UL << 16)
@@ -517,6 +518,7 @@ enum pnfs_layouttype {
 	LAYOUT_OSD2_OBJECTS = 2,
 	LAYOUT_BLOCK_VOLUME = 3,
 	LAYOUT_FLEX_FILES = 4,
+	LAYOUT_TYPE_MAX
 };
 
 /* used for both layout return and recall */

include/linux/sunrpc/svc.h

@@ -110,7 +110,7 @@ struct svc_serv {
  * We use sv_nrthreads as a reference count.  svc_destroy() drops
  * this refcount, so we need to bump it up around operations that
  * change the number of threads.  Horrible, but there it is.
- * Should be called with the BKL held.
+ * Should be called with the "service mutex" held.
  */
 static inline void svc_get(struct svc_serv *serv)
 {

include/linux/sunrpc/svc_rdma.h

@@ -77,6 +77,7 @@ struct svc_rdma_op_ctxt {
 	enum ib_wr_opcode wr_op;
 	enum ib_wc_status wc_status;
 	u32 byte_len;
+	u32 position;
 	struct svcxprt_rdma *xprt;
 	unsigned long flags;
 	enum dma_data_direction direction;
@@ -148,6 +149,10 @@ struct svcxprt_rdma {
 	struct ib_cq         *sc_rq_cq;
 	struct ib_cq         *sc_sq_cq;
 	struct ib_mr         *sc_phys_mr;	/* MR for server memory */
+	int		     (*sc_reader)(struct svcxprt_rdma *,
+					  struct svc_rqst *,
+					  struct svc_rdma_op_ctxt *,
+					  int *, u32 *, u32, u32, u64, bool);
 	u32		     sc_dev_caps;	/* distilled device caps */
 	u32		     sc_dma_lkey;	/* local dma key */
 	unsigned int	     sc_frmr_pg_list_len;
@@ -176,8 +181,6 @@ struct svcxprt_rdma {
 #define RPCRDMA_MAX_REQ_SIZE    4096
 
 /* svc_rdma_marshal.c */
-extern void svc_rdma_rcl_chunk_counts(struct rpcrdma_read_chunk *,
-				      int *, int *);
 extern int svc_rdma_xdr_decode_req(struct rpcrdma_msg **, struct svc_rqst *);
 extern int svc_rdma_xdr_decode_deferred_req(struct svc_rqst *);
 extern int svc_rdma_xdr_encode_error(struct svcxprt_rdma *,
@@ -195,6 +198,12 @@ extern int svc_rdma_xdr_get_reply_hdr_len(struct rpcrdma_msg *);
 
 /* svc_rdma_recvfrom.c */
 extern int svc_rdma_recvfrom(struct svc_rqst *);
+extern int rdma_read_chunk_lcl(struct svcxprt_rdma *, struct svc_rqst *,
+			       struct svc_rdma_op_ctxt *, int *, u32 *,
+			       u32, u32, u64, bool);
+extern int rdma_read_chunk_frmr(struct svcxprt_rdma *, struct svc_rqst *,
+				struct svc_rdma_op_ctxt *, int *, u32 *,
+				u32, u32, u64, bool);
 
 /* svc_rdma_sendto.c */
 extern int svc_rdma_sendto(struct svc_rqst *);

include/uapi/linux/nfsd/debug.h

@@ -32,6 +32,7 @@
 #define NFSDDBG_REPCACHE	0x0080
 #define NFSDDBG_XDR		0x0100
 #define NFSDDBG_LOCKD		0x0200
+#define NFSDDBG_PNFS		0x0400
 #define NFSDDBG_ALL		0x7FFF
 #define NFSDDBG_NOCHANGE	0xFFFF
 

include/uapi/linux/nfsd/export.h

@@ -47,8 +47,10 @@
  * exported filesystem.
  */
 #define	NFSEXP_V4ROOT		0x10000
+#define NFSEXP_NOPNFS		0x20000
+
 /* All flags that we claim to support.  (Note we don't support NOACL.) */
-#define NFSEXP_ALLFLAGS		0x1FE7F
+#define NFSEXP_ALLFLAGS		0x3FE7F
 
 /* The flags that may vary depending on security flavor: */
 #define NFSEXP_SECINFO_FLAGS	(NFSEXP_READONLY | NFSEXP_ROOTSQUASH \

net/sunrpc/svc.c

@@ -768,8 +768,8 @@ svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs)
 EXPORT_SYMBOL_GPL(svc_set_num_threads);
 
 /*
- * Called from a server thread as it's exiting. Caller must hold the BKL or
- * the "service mutex", whichever is appropriate for the service.
+ * Called from a server thread as it's exiting. Caller must hold the "service
+ * mutex" for the service.
  */
 void
 svc_exit_thread(struct svc_rqst *rqstp)

net/sunrpc/svc_xprt.c

@@ -42,7 +42,7 @@ static LIST_HEAD(svc_xprt_class_list);
  *	svc_pool->sp_lock protects most of the fields of that pool.
  *	svc_serv->sv_lock protects sv_tempsocks, sv_permsocks, sv_tmpcnt.
  *	when both need to be taken (rare), svc_serv->sv_lock is first.
- *	BKL protects svc_serv->sv_nrthread.
+ *	The "service mutex" protects svc_serv->sv_nrthread.
  *	svc_sock->sk_lock protects the svc_sock->sk_deferred list
  *             and the ->sk_info_authunix cache.
  *
@@ -67,7 +67,6 @@ static LIST_HEAD(svc_xprt_class_list);
  *		  that no other thread will be using the transport or will
  *		  try to set XPT_DEAD.
  */
-
 int svc_reg_xprt_class(struct svc_xprt_class *xcl)
 {
 	struct svc_xprt_class *cl;

net/sunrpc/xprtrdma/svc_rdma_marshal.c

@@ -70,22 +70,6 @@ static u32 *decode_read_list(u32 *va, u32 *vaend)
 	return (u32 *)&ch->rc_position;
 }
 
-/*
- * Determine number of chunks and total bytes in chunk list. The chunk
- * list has already been verified to fit within the RPCRDMA header.
- */
-void svc_rdma_rcl_chunk_counts(struct rpcrdma_read_chunk *ch,
-			       int *ch_count, int *byte_count)
-{
-	/* compute the number of bytes represented by read chunks */
-	*byte_count = 0;
-	*ch_count = 0;
-	for (; ch->rc_discrim != 0; ch++) {
-		*byte_count = *byte_count + ntohl(ch->rc_target.rs_length);
-		*ch_count = *ch_count + 1;
-	}
-}
-
 /*
  * Decodes a write chunk list. The expected format is as follows:
  *    descrim  : xdr_one

net/sunrpc/xprtrdma/svc_rdma_recvfrom.c

@@ -43,7 +43,6 @@
 #include <linux/sunrpc/debug.h>
 #include <linux/sunrpc/rpc_rdma.h>
 #include <linux/spinlock.h>
-#include <linux/highmem.h>
 #include <asm/unaligned.h>
 #include <rdma/ib_verbs.h>
 #include <rdma/rdma_cm.h>
@@ -60,6 +59,7 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp,
 			       struct svc_rdma_op_ctxt *ctxt,
 			       u32 byte_count)
 {
+	struct rpcrdma_msg *rmsgp;
 	struct page *page;
 	u32 bc;
 	int sge_no;
@@ -82,7 +82,14 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp,
 	/* If data remains, store it in the pagelist */
 	rqstp->rq_arg.page_len = bc;
 	rqstp->rq_arg.page_base = 0;
-	rqstp->rq_arg.pages = &rqstp->rq_pages[1];
+
+	/* RDMA_NOMSG: RDMA READ data should land just after RDMA RECV data */
+	rmsgp = (struct rpcrdma_msg *)rqstp->rq_arg.head[0].iov_base;
+	if (be32_to_cpu(rmsgp->rm_type) == RDMA_NOMSG)
+		rqstp->rq_arg.pages = &rqstp->rq_pages[0];
+	else
+		rqstp->rq_arg.pages = &rqstp->rq_pages[1];
+
 	sge_no = 1;
 	while (bc && sge_no < ctxt->count) {
 		page = ctxt->pages[sge_no];
@@ -95,14 +102,6 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp,
 	rqstp->rq_respages = &rqstp->rq_pages[sge_no];
 	rqstp->rq_next_page = rqstp->rq_respages + 1;
 
-	/* We should never run out of SGE because the limit is defined to
-	 * support the max allowed RPC data length
-	 */
-	BUG_ON(bc && (sge_no == ctxt->count));
-	BUG_ON((rqstp->rq_arg.head[0].iov_len + rqstp->rq_arg.page_len)
-	       != byte_count);
-	BUG_ON(rqstp->rq_arg.len != byte_count);
-
 	/* If not all pages were used from the SGL, free the remaining ones */
 	bc = sge_no;
 	while (sge_no < ctxt->count) {
@@ -125,26 +124,16 @@ static int rdma_read_max_sge(struct svcxprt_rdma *xprt, int sge_count)
 		return min_t(int, sge_count, xprt->sc_max_sge);
 }
 
-typedef int (*rdma_reader_fn)(struct svcxprt_rdma *xprt,
-			      struct svc_rqst *rqstp,
-			      struct svc_rdma_op_ctxt *head,
-			      int *page_no,
-			      u32 *page_offset,
-			      u32 rs_handle,
-			      u32 rs_length,
-			      u64 rs_offset,
-			      int last);
-
 /* Issue an RDMA_READ using the local lkey to map the data sink */
-static int rdma_read_chunk_lcl(struct svcxprt_rdma *xprt,
-			       struct svc_rqst *rqstp,
-			       struct svc_rdma_op_ctxt *head,
-			       int *page_no,
-			       u32 *page_offset,
-			       u32 rs_handle,
-			       u32 rs_length,
-			       u64 rs_offset,
-			       int last)
+int rdma_read_chunk_lcl(struct svcxprt_rdma *xprt,
+			struct svc_rqst *rqstp,
+			struct svc_rdma_op_ctxt *head,
+			int *page_no,
+			u32 *page_offset,
+			u32 rs_handle,
+			u32 rs_length,
+			u64 rs_offset,
+			bool last)
 {
 	struct ib_send_wr read_wr;
 	int pages_needed = PAGE_ALIGN(*page_offset + rs_length) >> PAGE_SHIFT;
@@ -229,15 +218,15 @@ static int rdma_read_chunk_lcl(struct svcxprt_rdma *xprt,
 }
 
 /* Issue an RDMA_READ using an FRMR to map the data sink */
-static int rdma_read_chunk_frmr(struct svcxprt_rdma *xprt,
-				struct svc_rqst *rqstp,
-				struct svc_rdma_op_ctxt *head,
-				int *page_no,
-				u32 *page_offset,
-				u32 rs_handle,
-				u32 rs_length,
-				u64 rs_offset,
-				int last)
+int rdma_read_chunk_frmr(struct svcxprt_rdma *xprt,
+			 struct svc_rqst *rqstp,
+			 struct svc_rdma_op_ctxt *head,
+			 int *page_no,
+			 u32 *page_offset,
+			 u32 rs_handle,
+			 u32 rs_length,
+			 u64 rs_offset,
+			 bool last)
 {
 	struct ib_send_wr read_wr;
 	struct ib_send_wr inv_wr;
@@ -365,24 +354,84 @@ static int rdma_read_chunk_frmr(struct svcxprt_rdma *xprt,
 	return ret;
 }
 
+static unsigned int
+rdma_rcl_chunk_count(struct rpcrdma_read_chunk *ch)
+{
+	unsigned int count;
+
+	for (count = 0; ch->rc_discrim != xdr_zero; ch++)
+		count++;
+	return count;
+}
+
+/* If there was additional inline content, append it to the end of arg.pages.
+ * Tail copy has to be done after the reader function has determined how many
+ * pages are needed for RDMA READ.
+ */
+static int
+rdma_copy_tail(struct svc_rqst *rqstp, struct svc_rdma_op_ctxt *head,
+	       u32 position, u32 byte_count, u32 page_offset, int page_no)
+{
+	char *srcp, *destp;
+	int ret;
+
+	ret = 0;
+	srcp = head->arg.head[0].iov_base + position;
+	byte_count = head->arg.head[0].iov_len - position;
+	if (byte_count > PAGE_SIZE) {
+		dprintk("svcrdma: large tail unsupported\n");
+		return 0;
+	}
+
+	/* Fit as much of the tail on the current page as possible */
+	if (page_offset != PAGE_SIZE) {
+		destp = page_address(rqstp->rq_arg.pages[page_no]);
+		destp += page_offset;
+		while (byte_count--) {
+			*destp++ = *srcp++;
+			page_offset++;
+			if (page_offset == PAGE_SIZE && byte_count)
+				goto more;
+		}
+		goto done;
+	}
+
+more:
+	/* Fit the rest on the next page */
+	page_no++;
+	destp = page_address(rqstp->rq_arg.pages[page_no]);
+	while (byte_count--)
+		*destp++ = *srcp++;
+
+	rqstp->rq_respages = &rqstp->rq_arg.pages[page_no+1];
+	rqstp->rq_next_page = rqstp->rq_respages + 1;
+
+done:
+	byte_count = head->arg.head[0].iov_len - position;
+	head->arg.page_len += byte_count;
+	head->arg.len += byte_count;
+	head->arg.buflen += byte_count;
+	return 1;
+}
+
 static int rdma_read_chunks(struct svcxprt_rdma *xprt,
 			    struct rpcrdma_msg *rmsgp,
 			    struct svc_rqst *rqstp,
 			    struct svc_rdma_op_ctxt *head)
 {
-	int page_no, ch_count, ret;
+	int page_no, ret;
 	struct rpcrdma_read_chunk *ch;
-	u32 page_offset, byte_count;
+	u32 handle, page_offset, byte_count;
+	u32 position;
 	u64 rs_offset;
-	rdma_reader_fn reader;
+	bool last;
 
 	/* If no read list is present, return 0 */
 	ch = svc_rdma_get_read_chunk(rmsgp);
 	if (!ch)
 		return 0;
 
-	svc_rdma_rcl_chunk_counts(ch, &ch_count, &byte_count);
-	if (ch_count > RPCSVC_MAXPAGES)
+	if (rdma_rcl_chunk_count(ch) > RPCSVC_MAXPAGES)
 		return -EINVAL;
 
 	/* The request is completed when the RDMA_READs complete. The
@@ -391,34 +440,41 @@ static int rdma_read_chunks(struct svcxprt_rdma *xprt,
 	 */
 	head->arg.head[0] = rqstp->rq_arg.head[0];
 	head->arg.tail[0] = rqstp->rq_arg.tail[0];
-	head->arg.pages = &head->pages[head->count];
 	head->hdr_count = head->count;
 	head->arg.page_base = 0;
 	head->arg.page_len = 0;
 	head->arg.len = rqstp->rq_arg.len;
 	head->arg.buflen = rqstp->rq_arg.buflen;
 
-	/* Use FRMR if supported */
-	if (xprt->sc_dev_caps & SVCRDMA_DEVCAP_FAST_REG)
-		reader = rdma_read_chunk_frmr;
-	else
-		reader = rdma_read_chunk_lcl;
+	ch = (struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0];
+	position = be32_to_cpu(ch->rc_position);
 
-	page_no = 0; page_offset = 0;
-	for (ch = (struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0];
-	     ch->rc_discrim != 0; ch++) {
+	/* RDMA_NOMSG: RDMA READ data should land just after RDMA RECV data */
+	if (position == 0) {
+		head->arg.pages = &head->pages[0];
+		page_offset = head->byte_len;
+	} else {
+		head->arg.pages = &head->pages[head->count];
+		page_offset = 0;
+	}
 
+	ret = 0;
+	page_no = 0;
+	for (; ch->rc_discrim != xdr_zero; ch++) {
+		if (be32_to_cpu(ch->rc_position) != position)
+			goto err;
+
+		handle = be32_to_cpu(ch->rc_target.rs_handle),
+		byte_count = be32_to_cpu(ch->rc_target.rs_length);
 		xdr_decode_hyper((__be32 *)&ch->rc_target.rs_offset,
 				 &rs_offset);
-		byte_count = ntohl(ch->rc_target.rs_length);
 
 		while (byte_count > 0) {
-			ret = reader(xprt, rqstp, head,
-				     &page_no, &page_offset,
-				     ntohl(ch->rc_target.rs_handle),
-				     byte_count, rs_offset,
-				     ((ch+1)->rc_discrim == 0) /* last */
-				     );
+			last = (ch + 1)->rc_discrim == xdr_zero;
+			ret = xprt->sc_reader(xprt, rqstp, head,
+					      &page_no, &page_offset,
+					      handle, byte_count,
+					      rs_offset, last);
 			if (ret < 0)
 				goto err;
 			byte_count -= ret;
@@ -426,7 +482,24 @@ static int rdma_read_chunks(struct svcxprt_rdma *xprt,
 			head->arg.buflen += ret;
 		}
 	}
+
+	/* Read list may need XDR round-up (see RFC 5666, s. 3.7) */
+	if (page_offset & 3) {
+		u32 pad = 4 - (page_offset & 3);
+
+		head->arg.page_len += pad;
+		head->arg.len += pad;
+		head->arg.buflen += pad;
+		page_offset += pad;
+	}
+
 	ret = 1;
+	if (position && position < head->arg.head[0].iov_len)
+		ret = rdma_copy_tail(rqstp, head, position,
+				     byte_count, page_offset, page_no);
+	head->arg.head[0].iov_len = position;
+	head->position = position;
+
  err:
 	/* Detach arg pages. svc_recv will replenish them */
 	for (page_no = 0;
@@ -436,47 +509,33 @@ static int rdma_read_chunks(struct svcxprt_rdma *xprt,
 	return ret;
 }
 
-/*
- * To avoid a separate RDMA READ just for a handful of zero bytes,
- * RFC 5666 section 3.7 allows the client to omit the XDR zero pad
- * in chunk lists.
- */
-static void
-rdma_fix_xdr_pad(struct xdr_buf *buf)
-{
-	unsigned int page_len = buf->page_len;
-	unsigned int size = (XDR_QUADLEN(page_len) << 2) - page_len;
-	unsigned int offset, pg_no;
-	char *p;
-
-	if (size == 0)
-		return;
-
-	pg_no = page_len >> PAGE_SHIFT;
-	offset = page_len & ~PAGE_MASK;
-	p = page_address(buf->pages[pg_no]);
-	memset(p + offset, 0, size);
-
-	buf->page_len += size;
-	buf->buflen += size;
-	buf->len += size;
-}
-
 static int rdma_read_complete(struct svc_rqst *rqstp,
 			      struct svc_rdma_op_ctxt *head)
 {
 	int page_no;
 	int ret;
 
-	BUG_ON(!head);
-
 	/* Copy RPC pages */
 	for (page_no = 0; page_no < head->count; page_no++) {
 		put_page(rqstp->rq_pages[page_no]);
 		rqstp->rq_pages[page_no] = head->pages[page_no];
 	}
+
+	/* Adjustments made for RDMA_NOMSG type requests */
+	if (head->position == 0) {
+		if (head->arg.len <= head->sge[0].length) {
+			head->arg.head[0].iov_len = head->arg.len -
+							head->byte_len;
+			head->arg.page_len = 0;
+		} else {
+			head->arg.head[0].iov_len = head->sge[0].length -
+								head->byte_len;
+			head->arg.page_len = head->arg.len -
+						head->sge[0].length;
+		}
+	}
+
 	/* Point rq_arg.pages past header */
-	rdma_fix_xdr_pad(&head->arg);
 	rqstp->rq_arg.pages = &rqstp->rq_pages[head->hdr_count];
 	rqstp->rq_arg.page_len = head->arg.page_len;
 	rqstp->rq_arg.page_base = head->arg.page_base;
@@ -501,8 +560,8 @@ static int rdma_read_complete(struct svc_rqst *rqstp,
 	ret = rqstp->rq_arg.head[0].iov_len
 		+ rqstp->rq_arg.page_len
 		+ rqstp->rq_arg.tail[0].iov_len;
-	dprintk("svcrdma: deferred read ret=%d, rq_arg.len =%d, "
-		"rq_arg.head[0].iov_base=%p, rq_arg.head[0].iov_len = %zd\n",
+	dprintk("svcrdma: deferred read ret=%d, rq_arg.len=%u, "
+		"rq_arg.head[0].iov_base=%p, rq_arg.head[0].iov_len=%zu\n",
 		ret, rqstp->rq_arg.len,	rqstp->rq_arg.head[0].iov_base,
 		rqstp->rq_arg.head[0].iov_len);
 
@@ -558,7 +617,6 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 	}
 	dprintk("svcrdma: processing ctxt=%p on xprt=%p, rqstp=%p, status=%d\n",
 		ctxt, rdma_xprt, rqstp, ctxt->wc_status);
-	BUG_ON(ctxt->wc_status != IB_WC_SUCCESS);
 	atomic_inc(&rdma_stat_recv);
 
 	/* Build up the XDR from the receive buffers. */
@@ -591,8 +649,8 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 		+ rqstp->rq_arg.tail[0].iov_len;
 	svc_rdma_put_context(ctxt, 0);
  out:
-	dprintk("svcrdma: ret = %d, rq_arg.len =%d, "
-		"rq_arg.head[0].iov_base=%p, rq_arg.head[0].iov_len = %zd\n",
+	dprintk("svcrdma: ret=%d, rq_arg.len=%u, "
+		"rq_arg.head[0].iov_base=%p, rq_arg.head[0].iov_len=%zd\n",
 		ret, rqstp->rq_arg.len,
 		rqstp->rq_arg.head[0].iov_base,
 		rqstp->rq_arg.head[0].iov_len);

net/sunrpc/xprtrdma/svc_rdma_sendto.c

@@ -60,8 +60,11 @@ static int map_xdr(struct svcxprt_rdma *xprt,
 	u32 page_off;
 	int page_no;
 
-	BUG_ON(xdr->len !=
-	       (xdr->head[0].iov_len + xdr->page_len + xdr->tail[0].iov_len));
+	if (xdr->len !=
+	    (xdr->head[0].iov_len + xdr->page_len + xdr->tail[0].iov_len)) {
+		pr_err("svcrdma: map_xdr: XDR buffer length error\n");
+		return -EIO;
+	}
 
 	/* Skip the first sge, this is for the RPCRDMA header */
 	sge_no = 1;
@@ -150,7 +153,11 @@ static int send_write(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp,
 	int bc;
 	struct svc_rdma_op_ctxt *ctxt;
 
-	BUG_ON(vec->count > RPCSVC_MAXPAGES);
+	if (vec->count > RPCSVC_MAXPAGES) {
+		pr_err("svcrdma: Too many pages (%lu)\n", vec->count);
+		return -EIO;
+	}
+
 	dprintk("svcrdma: RDMA_WRITE rmr=%x, to=%llx, xdr_off=%d, "
 		"write_len=%d, vec->sge=%p, vec->count=%lu\n",
 		rmr, (unsigned long long)to, xdr_off,
@@ -190,7 +197,10 @@ static int send_write(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp,
 		sge_off = 0;
 		sge_no++;
 		xdr_sge_no++;
-		BUG_ON(xdr_sge_no > vec->count);
+		if (xdr_sge_no > vec->count) {
+			pr_err("svcrdma: Too many sges (%d)\n", xdr_sge_no);
+			goto err;
+		}
 		bc -= sge_bytes;
 		if (sge_no == xprt->sc_max_sge)
 			break;
@@ -421,7 +431,10 @@ static int send_reply(struct svcxprt_rdma *rdma,
 		ctxt->sge[sge_no].lkey = rdma->sc_dma_lkey;
 		ctxt->sge[sge_no].length = sge_bytes;
 	}
-	BUG_ON(byte_count != 0);
+	if (byte_count != 0) {
+		pr_err("svcrdma: Could not map %d bytes\n", byte_count);
+		goto err;
+	}
 
 	/* Save all respages in the ctxt and remove them from the
 	 * respages array. They are our pages until the I/O
@@ -442,7 +455,10 @@ static int send_reply(struct svcxprt_rdma *rdma,
 	}
 	rqstp->rq_next_page = rqstp->rq_respages + 1;
 
-	BUG_ON(sge_no > rdma->sc_max_sge);
+	if (sge_no > rdma->sc_max_sge) {
+		pr_err("svcrdma: Too many sges (%d)\n", sge_no);
+		goto err;
+	}
 	memset(&send_wr, 0, sizeof send_wr);
 	ctxt->wr_op = IB_WR_SEND;
 	send_wr.wr_id = (unsigned long)ctxt;
@@ -467,18 +483,6 @@ void svc_rdma_prep_reply_hdr(struct svc_rqst *rqstp)
 {
 }
 
-/*
- * Return the start of an xdr buffer.
- */
-static void *xdr_start(struct xdr_buf *xdr)
-{
-	return xdr->head[0].iov_base -
-		(xdr->len -
-		 xdr->page_len -
-		 xdr->tail[0].iov_len -
-		 xdr->head[0].iov_len);
-}
-
 int svc_rdma_sendto(struct svc_rqst *rqstp)
 {
 	struct svc_xprt *xprt = rqstp->rq_xprt;
@@ -496,8 +500,10 @@ int svc_rdma_sendto(struct svc_rqst *rqstp)
 
 	dprintk("svcrdma: sending response for rqstp=%p\n", rqstp);
 
-	/* Get the RDMA request header. */
-	rdma_argp = xdr_start(&rqstp->rq_arg);
+	/* Get the RDMA request header. The receive logic always
+	 * places this at the start of page 0.
+	 */
+	rdma_argp = page_address(rqstp->rq_pages[0]);
 
 	/* Build an req vec for the XDR */
 	ctxt = svc_rdma_get_context(rdma);

net/sunrpc/xprtrdma/svc_rdma_transport.c

@@ -139,7 +139,6 @@ void svc_rdma_put_context(struct svc_rdma_op_ctxt *ctxt, int free_pages)
 	struct svcxprt_rdma *xprt;
 	int i;
 
-	BUG_ON(!ctxt);
 	xprt = ctxt->xprt;
 	if (free_pages)
 		for (i = 0; i < ctxt->count; i++)
@@ -339,12 +338,14 @@ static void process_context(struct svcxprt_rdma *xprt,
 
 	switch (ctxt->wr_op) {
 	case IB_WR_SEND:
-		BUG_ON(ctxt->frmr);
+		if (ctxt->frmr)
+			pr_err("svcrdma: SEND: ctxt->frmr != NULL\n");
 		svc_rdma_put_context(ctxt, 1);
 		break;
 
 	case IB_WR_RDMA_WRITE:
-		BUG_ON(ctxt->frmr);
+		if (ctxt->frmr)
+			pr_err("svcrdma: WRITE: ctxt->frmr != NULL\n");
 		svc_rdma_put_context(ctxt, 0);
 		break;
 
@@ -353,19 +354,21 @@ static void process_context(struct svcxprt_rdma *xprt,
 		svc_rdma_put_frmr(xprt, ctxt->frmr);
 		if (test_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags)) {
 			struct svc_rdma_op_ctxt *read_hdr = ctxt->read_hdr;
-			BUG_ON(!read_hdr);
-			spin_lock_bh(&xprt->sc_rq_dto_lock);
-			set_bit(XPT_DATA, &xprt->sc_xprt.xpt_flags);
-			list_add_tail(&read_hdr->dto_q,
-				      &xprt->sc_read_complete_q);
-			spin_unlock_bh(&xprt->sc_rq_dto_lock);
+			if (read_hdr) {
+				spin_lock_bh(&xprt->sc_rq_dto_lock);
+				set_bit(XPT_DATA, &xprt->sc_xprt.xpt_flags);
+				list_add_tail(&read_hdr->dto_q,
+					      &xprt->sc_read_complete_q);
+				spin_unlock_bh(&xprt->sc_rq_dto_lock);
+			} else {
+				pr_err("svcrdma: ctxt->read_hdr == NULL\n");
+			}
 			svc_xprt_enqueue(&xprt->sc_xprt);
 		}
 		svc_rdma_put_context(ctxt, 0);
 		break;
 
 	default:
-		BUG_ON(1);
 		printk(KERN_ERR "svcrdma: unexpected completion type, "
 		       "opcode=%d\n",
 		       ctxt->wr_op);
@@ -513,7 +516,10 @@ int svc_rdma_post_recv(struct svcxprt_rdma *xprt)
 	buflen = 0;
 	ctxt->direction = DMA_FROM_DEVICE;
 	for (sge_no = 0; buflen < xprt->sc_max_req_size; sge_no++) {
-		BUG_ON(sge_no >= xprt->sc_max_sge);
+		if (sge_no >= xprt->sc_max_sge) {
+			pr_err("svcrdma: Too many sges (%d)\n", sge_no);
+			goto err_put_ctxt;
+		}
 		page = svc_rdma_get_page();
 		ctxt->pages[sge_no] = page;
 		pa = ib_dma_map_page(xprt->sc_cm_id->device,
@@ -687,7 +693,6 @@ static struct svc_xprt *svc_rdma_create(struct svc_serv *serv,
 {
 	struct rdma_cm_id *listen_id;
 	struct svcxprt_rdma *cma_xprt;
-	struct svc_xprt *xprt;
 	int ret;
 
 	dprintk("svcrdma: Creating RDMA socket\n");
@@ -698,7 +703,6 @@ static struct svc_xprt *svc_rdma_create(struct svc_serv *serv,
 	cma_xprt = rdma_create_xprt(serv, 1);
 	if (!cma_xprt)
 		return ERR_PTR(-ENOMEM);
-	xprt = &cma_xprt->sc_xprt;
 
 	listen_id = rdma_create_id(rdma_listen_handler, cma_xprt, RDMA_PS_TCP,
 				   IB_QPT_RC);
@@ -822,7 +826,7 @@ void svc_rdma_put_frmr(struct svcxprt_rdma *rdma,
 	if (frmr) {
 		frmr_unmap_dma(rdma, frmr);
 		spin_lock_bh(&rdma->sc_frmr_q_lock);
-		BUG_ON(!list_empty(&frmr->frmr_list));
+		WARN_ON_ONCE(!list_empty(&frmr->frmr_list));
 		list_add(&frmr->frmr_list, &rdma->sc_frmr_q);
 		spin_unlock_bh(&rdma->sc_frmr_q_lock);
 	}
@@ -970,10 +974,12 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
 	 * NB:	iWARP requires remote write access for the data sink
 	 *	of an RDMA_READ. IB does not.
 	 */
+	newxprt->sc_reader = rdma_read_chunk_lcl;
 	if (devattr.device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS) {
 		newxprt->sc_frmr_pg_list_len =
 			devattr.max_fast_reg_page_list_len;
 		newxprt->sc_dev_caps |= SVCRDMA_DEVCAP_FAST_REG;
+		newxprt->sc_reader = rdma_read_chunk_frmr;
 	}
 
 	/*
@@ -1125,7 +1131,9 @@ static void __svc_rdma_free(struct work_struct *work)
 	dprintk("svcrdma: svc_rdma_free(%p)\n", rdma);
 
 	/* We should only be called from kref_put */
-	BUG_ON(atomic_read(&rdma->sc_xprt.xpt_ref.refcount) != 0);
+	if (atomic_read(&rdma->sc_xprt.xpt_ref.refcount) != 0)
+		pr_err("svcrdma: sc_xprt still in use? (%d)\n",
+		       atomic_read(&rdma->sc_xprt.xpt_ref.refcount));
 
 	/*
 	 * Destroy queued, but not processed read completions. Note
@@ -1153,8 +1161,12 @@ static void __svc_rdma_free(struct work_struct *work)
 	}
 
 	/* Warn if we leaked a resource or under-referenced */
-	WARN_ON(atomic_read(&rdma->sc_ctxt_used) != 0);
-	WARN_ON(atomic_read(&rdma->sc_dma_used) != 0);
+	if (atomic_read(&rdma->sc_ctxt_used) != 0)
+		pr_err("svcrdma: ctxt still in use? (%d)\n",
+		       atomic_read(&rdma->sc_ctxt_used));
+	if (atomic_read(&rdma->sc_dma_used) != 0)
+		pr_err("svcrdma: dma still in use? (%d)\n",
+		       atomic_read(&rdma->sc_dma_used));
 
 	/* De-allocate fastreg mr */
 	rdma_dealloc_frmr_q(rdma);
@@ -1254,7 +1266,6 @@ int svc_rdma_send(struct svcxprt_rdma *xprt, struct ib_send_wr *wr)
 	if (test_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags))
 		return -ENOTCONN;
 
-	BUG_ON(wr->send_flags != IB_SEND_SIGNALED);
 	wr_count = 1;
 	for (n_wr = wr->next; n_wr; n_wr = n_wr->next)
 		wr_count++;