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
  ...

Author: torvalds

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

@@ -2,13 +2,19 @@
 # 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
 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