Merge tag 'nfs-for-3.12-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client updates from Trond Myklebust:
 "Highlights include:

   - Fix NFSv4 recovery so that it doesn't recover lost locks in cases
     such as lease loss due to a network partition, where doing so may
     result in data corruption.  Add a kernel parameter to control
     choice of legacy behaviour or not.
   - Performance improvements when 2 processes are writing to the same
     file.
   - Flush data to disk when an RPCSEC_GSS session timeout is imminent.
   - Implement NFSv4.1 SP4_MACH_CRED state protection to prevent other
     NFS clients from being able to manipulate our lease and file
     locking state.
   - Allow sharing of RPCSEC_GSS caches between different rpc clients.
   - Fix the broken NFSv4 security auto-negotiation between client and
     server.
   - Fix rmdir() to wait for outstanding sillyrename unlinks to complete
   - Add a tracepoint framework for debugging NFSv4 state recovery
     issues.
   - Add tracing to the generic NFS layer.
   - Add tracing for the SUNRPC socket connection state.
   - Clean up the rpc_pipefs mount/umount event management.
   - Merge more patches from Chuck in preparation for NFSv4 migration
     support"

* tag 'nfs-for-3.12-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (107 commits)
  NFSv4: use mach cred for SECINFO_NO_NAME w/ integrity
  NFS: nfs_compare_super shouldn't check the auth flavour unless 'sec=' was set
  NFSv4: Allow security autonegotiation for submounts
  NFSv4: Disallow security negotiation for lookups when 'sec=' is specified
  NFSv4: Fix security auto-negotiation
  NFS: Clean up nfs_parse_security_flavors()
  NFS: Clean up the auth flavour array mess
  NFSv4.1 Use MDS auth flavor for data server connection
  NFS: Don't check lock owner compatability unless file is locked (part 2)
  NFS: Don't check lock owner compatibility in writes unless file is locked
  nfs4: Map NFS4ERR_WRONG_CRED to EPERM
  nfs4.1: Add SP4_MACH_CRED write and commit support
  nfs4.1: Add SP4_MACH_CRED stateid support
  nfs4.1: Add SP4_MACH_CRED secinfo support
  nfs4.1: Add SP4_MACH_CRED cleanup support
  nfs4.1: Add state protection handler
  nfs4.1: Minimal SP4_MACH_CRED implementation
  SUNRPC: Replace pointer values with task->tk_pid and rpc_clnt->cl_clid
  SUNRPC: Add an identifier for struct rpc_clnt
  SUNRPC: Ensure rpc_task->tk_pid is available for tracepoints
  ...

Documentation/kernel-parameters.txt

@@ -1899,6 +1899,18 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			The default is to send the implementation identification
 			information.
 	
+	nfs.recover_lost_locks =
+			[NFSv4] Attempt to recover locks that were lost due
+			to a lease timeout on the server. Please note that
+			doing this risks data corruption, since there are
+			no guarantees that the file will remain unchanged
+			after the locks are lost.
+			If you want to enable the kernel legacy behaviour of
+			attempting to recover these locks, then set this
+			parameter to '1'.
+			The default parameter value of '0' causes the kernel
+			not to attempt recovery of lost locks.
+
 	nfsd.nfs4_disable_idmapping=
 			[NFSv4] When set to the default of '1', the NFSv4
 			server will return only numeric uids and gids to

fs/nfs/Makefile

@@ -4,9 +4,10 @@
 
 obj-$(CONFIG_NFS_FS) += nfs.o
 
+CFLAGS_nfstrace.o += -I$(src)
 nfs-y 			:= client.o dir.o file.o getroot.o inode.o super.o \
 			   direct.o pagelist.o read.o symlink.o unlink.o \
-			   write.o namespace.o mount_clnt.o
+			   write.o namespace.o mount_clnt.o nfstrace.o
 nfs-$(CONFIG_ROOT_NFS)	+= nfsroot.o
 nfs-$(CONFIG_SYSCTL)	+= sysctl.o
 nfs-$(CONFIG_NFS_FSCACHE) += fscache.o fscache-index.o
@@ -19,12 +20,14 @@ nfsv3-y := nfs3super.o nfs3client.o nfs3proc.o nfs3xdr.o
 nfsv3-$(CONFIG_NFS_V3_ACL) += nfs3acl.o
 
 obj-$(CONFIG_NFS_V4) += nfsv4.o
+CFLAGS_nfs4trace.o += -I$(src)
 nfsv4-y := nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o nfs4super.o nfs4file.o \
 	  delegation.o idmap.o callback.o callback_xdr.o callback_proc.o \
-	  nfs4namespace.o nfs4getroot.o nfs4client.o dns_resolve.o
+	  nfs4namespace.o nfs4getroot.o nfs4client.o nfs4session.o \
+	  dns_resolve.o nfs4trace.o
 nfsv4-$(CONFIG_NFS_USE_LEGACY_DNS) += cache_lib.o
 nfsv4-$(CONFIG_SYSCTL)	+= nfs4sysctl.o
-nfsv4-$(CONFIG_NFS_V4_1)	+= nfs4session.o pnfs.o pnfs_dev.o
+nfsv4-$(CONFIG_NFS_V4_1)	+= pnfs.o pnfs_dev.o
 
 obj-$(CONFIG_PNFS_FILE_LAYOUT) += nfs_layout_nfsv41_files.o
 nfs_layout_nfsv41_files-y := nfs4filelayout.o nfs4filelayoutdev.o

fs/nfs/callback_proc.c

@@ -15,6 +15,7 @@
 #include "internal.h"
 #include "pnfs.h"
 #include "nfs4session.h"
+#include "nfs4trace.h"
 
 #ifdef NFS_DEBUG
 #define NFSDBG_FACILITY NFSDBG_CALLBACK
@@ -93,6 +94,7 @@ __be32 nfs4_callback_recall(struct cb_recallargs *args, void *dummy,
 	default:
 		res = htonl(NFS4ERR_RESOURCE);
 	}
+	trace_nfs4_recall_delegation(inode, -ntohl(res));
 	iput(inode);
 out:
 	dprintk("%s: exit with status = %d\n", __func__, ntohl(res));
@@ -301,14 +303,14 @@ validate_seqid(struct nfs4_slot_table *tbl, struct cb_sequenceargs * args)
 {
 	struct nfs4_slot *slot;
 
-	dprintk("%s enter. slotid %d seqid %d\n",
+	dprintk("%s enter. slotid %u seqid %u\n",
 		__func__, args->csa_slotid, args->csa_sequenceid);
 
 	if (args->csa_slotid >= NFS41_BC_MAX_CALLBACKS)
 		return htonl(NFS4ERR_BADSLOT);
 
 	slot = tbl->slots + args->csa_slotid;
-	dprintk("%s slot table seqid: %d\n", __func__, slot->seq_nr);
+	dprintk("%s slot table seqid: %u\n", __func__, slot->seq_nr);
 
 	/* Normal */
 	if (likely(args->csa_sequenceid == slot->seq_nr + 1)) {
@@ -318,7 +320,7 @@ validate_seqid(struct nfs4_slot_table *tbl, struct cb_sequenceargs * args)
 
 	/* Replay */
 	if (args->csa_sequenceid == slot->seq_nr) {
-		dprintk("%s seqid %d is a replay\n",
+		dprintk("%s seqid %u is a replay\n",
 			__func__, args->csa_sequenceid);
 		/* Signal process_op to set this error on next op */
 		if (args->csa_cachethis == 0)
@@ -462,6 +464,7 @@ __be32 nfs4_callback_sequence(struct cb_sequenceargs *args,
 	} else
 		res->csr_status = status;
 
+	trace_nfs4_cb_sequence(args, res, status);
 	dprintk("%s: exit with status = %d res->csr_status %d\n", __func__,
 		ntohl(status), ntohl(res->csr_status));
 	return status;
@@ -518,7 +521,7 @@ __be32 nfs4_callback_recallslot(struct cb_recallslotargs *args, void *dummy,
 	if (!cps->clp) /* set in cb_sequence */
 		goto out;
 
-	dprintk_rcu("NFS: CB_RECALL_SLOT request from %s target highest slotid %d\n",
+	dprintk_rcu("NFS: CB_RECALL_SLOT request from %s target highest slotid %u\n",
 		rpc_peeraddr2str(cps->clp->cl_rpcclient, RPC_DISPLAY_ADDR),
 		args->crsa_target_highest_slotid);
 

fs/nfs/client.c

@@ -501,8 +501,7 @@ nfs_get_client(const struct nfs_client_initdata *cl_init,
 					&nn->nfs_client_list);
 			spin_unlock(&nn->nfs_client_lock);
 			new->cl_flags = cl_init->init_flags;
-			return rpc_ops->init_client(new, timeparms, ip_addr,
-						    authflavour);
+			return rpc_ops->init_client(new, timeparms, ip_addr);
 		}
 
 		spin_unlock(&nn->nfs_client_lock);
@@ -694,13 +693,12 @@ EXPORT_SYMBOL_GPL(nfs_init_server_rpcclient);
  * @clp: nfs_client to initialise
  * @timeparms: timeout parameters for underlying RPC transport
  * @ip_addr: IP presentation address (not used)
- * @authflavor: authentication flavor for underlying RPC transport
  *
  * Returns pointer to an NFS client, or an ERR_PTR value.
  */
 struct nfs_client *nfs_init_client(struct nfs_client *clp,
 		    const struct rpc_timeout *timeparms,
-		    const char *ip_addr, rpc_authflavor_t authflavour)
+		    const char *ip_addr)
 {
 	int error;
 

fs/nfs/delegation.c

@@ -20,6 +20,7 @@
 #include "nfs4_fs.h"
 #include "delegation.h"
 #include "internal.h"
+#include "nfs4trace.h"
 
 static void nfs_free_delegation(struct nfs_delegation *delegation)
 {
@@ -160,6 +161,7 @@ void nfs_inode_reclaim_delegation(struct inode *inode, struct rpc_cred *cred,
 			spin_unlock(&delegation->lock);
 			put_rpccred(oldcred);
 			rcu_read_unlock();
+			trace_nfs4_reclaim_delegation(inode, res->delegation_type);
 		} else {
 			/* We appear to have raced with a delegation return. */
 			spin_unlock(&delegation->lock);
@@ -344,6 +346,7 @@ int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct
 	spin_lock(&inode->i_lock);
 	nfsi->cache_validity |= NFS_INO_REVAL_FORCED;
 	spin_unlock(&inode->i_lock);
+	trace_nfs4_set_delegation(inode, res->delegation_type);
 
 out:
 	spin_unlock(&clp->cl_lock);

fs/nfs/dir.c

@@ -43,6 +43,8 @@
 #include "internal.h"
 #include "fscache.h"
 
+#include "nfstrace.h"
+
 /* #define NFS_DEBUG_VERBOSE 1 */
 
 static int nfs_opendir(struct inode *, struct file *);
@@ -1100,7 +1102,9 @@ static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
 	if (IS_ERR(label))
 		goto out_error;
 
+	trace_nfs_lookup_revalidate_enter(dir, dentry, flags);
 	error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr, label);
+	trace_nfs_lookup_revalidate_exit(dir, dentry, flags, error);
 	if (error)
 		goto out_bad;
 	if (nfs_compare_fh(NFS_FH(inode), fhandle))
@@ -1312,6 +1316,7 @@ struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned in
 
 	parent = dentry->d_parent;
 	/* Protect against concurrent sillydeletes */
+	trace_nfs_lookup_enter(dir, dentry, flags);
 	nfs_block_sillyrename(parent);
 	error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr, label);
 	if (error == -ENOENT)
@@ -1338,6 +1343,7 @@ struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned in
 	nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
 out_unblock_sillyrename:
 	nfs_unblock_sillyrename(parent);
+	trace_nfs_lookup_exit(dir, dentry, flags, error);
 	nfs4_label_free(label);
 out:
 	nfs_free_fattr(fattr);
@@ -1392,7 +1398,6 @@ static int nfs_finish_open(struct nfs_open_context *ctx,
 	nfs_file_set_open_context(file, ctx);
 
 out:
-	put_nfs_open_context(ctx);
 	return err;
 }
 
@@ -1404,6 +1409,7 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
 	struct dentry *res;
 	struct iattr attr = { .ia_valid = ATTR_OPEN };
 	struct inode *inode;
+	unsigned int lookup_flags = 0;
 	int err;
 
 	/* Expect a negative dentry */
@@ -1412,6 +1418,10 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
 	dfprintk(VFS, "NFS: atomic_open(%s/%ld), %s\n",
 			dir->i_sb->s_id, dir->i_ino, dentry->d_name.name);
 
+	err = nfs_check_flags(open_flags);
+	if (err)
+		return err;
+
 	/* NFS only supports OPEN on regular files */
 	if ((open_flags & O_DIRECTORY)) {
 		if (!d_unhashed(dentry)) {
@@ -1422,6 +1432,7 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
 			 */
 			return -ENOENT;
 		}
+		lookup_flags = LOOKUP_OPEN|LOOKUP_DIRECTORY;
 		goto no_open;
 	}
 
@@ -1442,12 +1453,14 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
 	if (IS_ERR(ctx))
 		goto out;
 
+	trace_nfs_atomic_open_enter(dir, ctx, open_flags);
 	nfs_block_sillyrename(dentry->d_parent);
 	inode = NFS_PROTO(dir)->open_context(dir, ctx, open_flags, &attr);
 	nfs_unblock_sillyrename(dentry->d_parent);
 	if (IS_ERR(inode)) {
-		put_nfs_open_context(ctx);
 		err = PTR_ERR(inode);
+		trace_nfs_atomic_open_exit(dir, ctx, open_flags, err);
+		put_nfs_open_context(ctx);
 		switch (err) {
 		case -ENOENT:
 			d_drop(dentry);
@@ -1468,11 +1481,13 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
 	}
 
 	err = nfs_finish_open(ctx, ctx->dentry, file, open_flags, opened);
+	trace_nfs_atomic_open_exit(dir, ctx, open_flags, err);
+	put_nfs_open_context(ctx);
 out:
 	return err;
 
 no_open:
-	res = nfs_lookup(dir, dentry, 0);
+	res = nfs_lookup(dir, dentry, lookup_flags);
 	err = PTR_ERR(res);
 	if (IS_ERR(res))
 		goto out;
@@ -1596,7 +1611,9 @@ int nfs_create(struct inode *dir, struct dentry *dentry,
 	attr.ia_mode = mode;
 	attr.ia_valid = ATTR_MODE;
 
+	trace_nfs_create_enter(dir, dentry, open_flags);
 	error = NFS_PROTO(dir)->create(dir, dentry, &attr, open_flags);
+	trace_nfs_create_exit(dir, dentry, open_flags, error);
 	if (error != 0)
 		goto out_err;
 	return 0;
@@ -1624,7 +1641,9 @@ nfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev)
 	attr.ia_mode = mode;
 	attr.ia_valid = ATTR_MODE;
 
+	trace_nfs_mknod_enter(dir, dentry);
 	status = NFS_PROTO(dir)->mknod(dir, dentry, &attr, rdev);
+	trace_nfs_mknod_exit(dir, dentry, status);
 	if (status != 0)
 		goto out_err;
 	return 0;
@@ -1648,7 +1667,9 @@ int nfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	attr.ia_valid = ATTR_MODE;
 	attr.ia_mode = mode | S_IFDIR;
 
+	trace_nfs_mkdir_enter(dir, dentry);
 	error = NFS_PROTO(dir)->mkdir(dir, dentry, &attr);
+	trace_nfs_mkdir_exit(dir, dentry, error);
 	if (error != 0)
 		goto out_err;
 	return 0;
@@ -1671,12 +1692,21 @@ int nfs_rmdir(struct inode *dir, struct dentry *dentry)
 	dfprintk(VFS, "NFS: rmdir(%s/%ld), %s\n",
 			dir->i_sb->s_id, dir->i_ino, dentry->d_name.name);
 
+	trace_nfs_rmdir_enter(dir, dentry);
+	if (dentry->d_inode) {
+		nfs_wait_on_sillyrename(dentry);
 		error = NFS_PROTO(dir)->rmdir(dir, &dentry->d_name);
 		/* Ensure the VFS deletes this inode */
-	if (error == 0 && dentry->d_inode != NULL)
+		switch (error) {
+		case 0:
 			clear_nlink(dentry->d_inode);
-	else if (error == -ENOENT)
+			break;
+		case -ENOENT:
 			nfs_dentry_handle_enoent(dentry);
+		}
+	} else
+		error = NFS_PROTO(dir)->rmdir(dir, &dentry->d_name);
+	trace_nfs_rmdir_exit(dir, dentry, error);
 
 	return error;
 }
@@ -1704,6 +1734,7 @@ static int nfs_safe_remove(struct dentry *dentry)
 		goto out;
 	}
 
+	trace_nfs_remove_enter(dir, dentry);
 	if (inode != NULL) {
 		NFS_PROTO(inode)->return_delegation(inode);
 		error = NFS_PROTO(dir)->remove(dir, &dentry->d_name);
@@ -1713,6 +1744,7 @@ static int nfs_safe_remove(struct dentry *dentry)
 		error = NFS_PROTO(dir)->remove(dir, &dentry->d_name);
 	if (error == -ENOENT)
 		nfs_dentry_handle_enoent(dentry);
+	trace_nfs_remove_exit(dir, dentry, error);
 out:
 	return error;
 }
@@ -1730,13 +1762,14 @@ int nfs_unlink(struct inode *dir, struct dentry *dentry)
 	dfprintk(VFS, "NFS: unlink(%s/%ld, %s)\n", dir->i_sb->s_id,
 		dir->i_ino, dentry->d_name.name);
 
+	trace_nfs_unlink_enter(dir, dentry);
 	spin_lock(&dentry->d_lock);
 	if (d_count(dentry) > 1) {
 		spin_unlock(&dentry->d_lock);
 		/* Start asynchronous writeout of the inode */
 		write_inode_now(dentry->d_inode, 0);
 		error = nfs_sillyrename(dir, dentry);
-		return error;
+		goto out;
 	}
 	if (!d_unhashed(dentry)) {
 		__d_drop(dentry);
@@ -1748,6 +1781,8 @@ int nfs_unlink(struct inode *dir, struct dentry *dentry)
 		nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
 	} else if (need_rehash)
 		d_rehash(dentry);
+out:
+	trace_nfs_unlink_exit(dir, dentry, error);
 	return error;
 }
 EXPORT_SYMBOL_GPL(nfs_unlink);
@@ -1794,7 +1829,9 @@ int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
 		memset(kaddr + pathlen, 0, PAGE_SIZE - pathlen);
 	kunmap_atomic(kaddr);
 
+	trace_nfs_symlink_enter(dir, dentry);
 	error = NFS_PROTO(dir)->symlink(dir, dentry, page, pathlen, &attr);
+	trace_nfs_symlink_exit(dir, dentry, error);
 	if (error != 0) {
 		dfprintk(VFS, "NFS: symlink(%s/%ld, %s, %s) error %d\n",
 			dir->i_sb->s_id, dir->i_ino,
@@ -1829,6 +1866,7 @@ nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry)
 		old_dentry->d_parent->d_name.name, old_dentry->d_name.name,
 		dentry->d_parent->d_name.name, dentry->d_name.name);
 
+	trace_nfs_link_enter(inode, dir, dentry);
 	NFS_PROTO(inode)->return_delegation(inode);
 
 	d_drop(dentry);
@@ -1837,6 +1875,7 @@ nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry)
 		ihold(inode);
 		d_add(dentry, inode);
 	}
+	trace_nfs_link_exit(inode, dir, dentry, error);
 	return error;
 }
 EXPORT_SYMBOL_GPL(nfs_link);
@@ -1878,6 +1917,7 @@ int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		 new_dentry->d_parent->d_name.name, new_dentry->d_name.name,
 		 d_count(new_dentry));
 
+	trace_nfs_rename_enter(old_dir, old_dentry, new_dir, new_dentry);
 	/*
 	 * For non-directories, check whether the target is busy and if so,
 	 * make a copy of the dentry and then do a silly-rename. If the
@@ -1924,6 +1964,8 @@ int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 out:
 	if (rehash)
 		d_rehash(rehash);
+	trace_nfs_rename_exit(old_dir, old_dentry,
+			new_dir, new_dentry, error);
 	if (!error) {
 		if (new_inode != NULL)
 			nfs_drop_nlink(new_inode);
@@ -2173,9 +2215,11 @@ static int nfs_do_access(struct inode *inode, struct rpc_cred *cred, int mask)
 	struct nfs_access_entry cache;
 	int status;
 
+	trace_nfs_access_enter(inode);
+
 	status = nfs_access_get_cached(inode, cred, &cache);
 	if (status == 0)
-		goto out;
+		goto out_cached;
 
 	/* Be clever: ask server to check for all possible rights */
 	cache.mask = MAY_EXEC | MAY_WRITE | MAY_READ;
@@ -2188,13 +2232,15 @@ static int nfs_do_access(struct inode *inode, struct rpc_cred *cred, int mask)
 			if (!S_ISDIR(inode->i_mode))
 				set_bit(NFS_INO_STALE, &NFS_I(inode)->flags);
 		}
-		return status;
+		goto out;
 	}
 	nfs_access_add_cache(inode, &cache);
+out_cached:
+	if ((mask & ~cache.mask & (MAY_READ | MAY_WRITE | MAY_EXEC)) != 0)
+		status = -EACCES;
 out:
-	if ((mask & ~cache.mask & (MAY_READ | MAY_WRITE | MAY_EXEC)) == 0)
-		return 0;
-	return -EACCES;
+	trace_nfs_access_exit(inode, status);
+	return status;
 }
 
 static int nfs_open_permission_mask(int openflags)
@@ -2240,11 +2286,6 @@ int nfs_permission(struct inode *inode, int mask)
 		case S_IFLNK:
 			goto out;
 		case S_IFREG:
-			/* NFSv4 has atomic_open... */
-			if (nfs_server_capable(inode, NFS_CAP_ATOMIC_OPEN)
-					&& (mask & MAY_OPEN)
-					&& !(mask & MAY_EXEC))
-				goto out;
 			break;
 		case S_IFDIR:
 			/*

fs/nfs/file.c

@@ -37,6 +37,8 @@
 #include "iostat.h"
 #include "fscache.h"
 
+#include "nfstrace.h"
+
 #define NFSDBG_FACILITY		NFSDBG_FILE
 
 static const struct vm_operations_struct nfs_file_vm_ops;
@@ -294,6 +296,8 @@ nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 	int ret;
 	struct inode *inode = file_inode(file);
 
+	trace_nfs_fsync_enter(inode);
+
 	do {
 		ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
 		if (ret != 0)
@@ -310,6 +314,7 @@ nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 		end = LLONG_MAX;
 	} while (ret == -EAGAIN);
 
+	trace_nfs_fsync_exit(inode, ret);
 	return ret;
 }
 
@@ -406,6 +411,7 @@ static int nfs_write_end(struct file *file, struct address_space *mapping,
 			struct page *page, void *fsdata)
 {
 	unsigned offset = pos & (PAGE_CACHE_SIZE - 1);
+	struct nfs_open_context *ctx = nfs_file_open_context(file);
 	int status;
 
 	dfprintk(PAGECACHE, "NFS: write_end(%s/%s(%ld), %u@%lld)\n",
@@ -441,6 +447,13 @@ static int nfs_write_end(struct file *file, struct address_space *mapping,
 	if (status < 0)
 		return status;
 	NFS_I(mapping->host)->write_io += copied;
+
+	if (nfs_ctx_key_to_expire(ctx)) {
+		status = nfs_wb_all(mapping->host);
+		if (status < 0)
+			return status;
+	}
+
 	return copied;
 }
 
@@ -637,7 +650,8 @@ static int nfs_need_sync_write(struct file *filp, struct inode *inode)
 	if (IS_SYNC(inode) || (filp->f_flags & O_DSYNC))
 		return 1;
 	ctx = nfs_file_open_context(filp);
-	if (test_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags))
+	if (test_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags) ||
+	    nfs_ctx_key_to_expire(ctx))
 		return 1;
 	return 0;
 }
@@ -651,6 +665,10 @@ ssize_t nfs_file_write(struct kiocb *iocb, const struct iovec *iov,
 	ssize_t result;
 	size_t count = iov_length(iov, nr_segs);
 
+	result = nfs_key_timeout_notify(iocb->ki_filp, inode);
+	if (result)
+		return result;
+
 	if (iocb->ki_filp->f_flags & O_DIRECT)
 		return nfs_file_direct_write(iocb, iov, nr_segs, pos, true);
 

fs/nfs/idmap.c

@@ -49,6 +49,7 @@
 
 #include "internal.h"
 #include "netns.h"
+#include "nfs4trace.h"
 
 #define NFS_UINT_MAXLEN 11
 
@@ -63,6 +64,7 @@ struct idmap_legacy_upcalldata {
 };
 
 struct idmap {
+	struct rpc_pipe_dir_object idmap_pdo;
 	struct rpc_pipe		*idmap_pipe;
 	struct idmap_legacy_upcalldata *idmap_upcall_data;
 	struct mutex		idmap_mutex;
@@ -310,7 +312,7 @@ static ssize_t nfs_idmap_get_key(const char *name, size_t namelen,
 	if (ret < 0)
 		goto out_up;
 
-	payload = rcu_dereference(rkey->payload.data);
+	payload = rcu_dereference(rkey->payload.rcudata);
 	if (IS_ERR_OR_NULL(payload)) {
 		ret = PTR_ERR(payload);
 		goto out_up;
@@ -401,16 +403,23 @@ static struct key_type key_type_id_resolver_legacy = {
 	.request_key	= nfs_idmap_legacy_upcall,
 };
 
-static void __nfs_idmap_unregister(struct rpc_pipe *pipe)
+static void nfs_idmap_pipe_destroy(struct dentry *dir,
+		struct rpc_pipe_dir_object *pdo)
 {
-	if (pipe->dentry)
+	struct idmap *idmap = pdo->pdo_data;
+	struct rpc_pipe *pipe = idmap->idmap_pipe;
+
+	if (pipe->dentry) {
 		rpc_unlink(pipe->dentry);
+		pipe->dentry = NULL;
+	}
 }
 
-static int __nfs_idmap_register(struct dentry *dir,
-				     struct idmap *idmap,
-				     struct rpc_pipe *pipe)
+static int nfs_idmap_pipe_create(struct dentry *dir,
+		struct rpc_pipe_dir_object *pdo)
 {
+	struct idmap *idmap = pdo->pdo_data;
+	struct rpc_pipe *pipe = idmap->idmap_pipe;
 	struct dentry *dentry;
 
 	dentry = rpc_mkpipe_dentry(dir, "idmap", idmap, pipe);
@@ -420,36 +429,10 @@ static int __nfs_idmap_register(struct dentry *dir,
 	return 0;
 }
 
-static void nfs_idmap_unregister(struct nfs_client *clp,
-				      struct rpc_pipe *pipe)
-{
-	struct net *net = clp->cl_net;
-	struct super_block *pipefs_sb;
-
-	pipefs_sb = rpc_get_sb_net(net);
-	if (pipefs_sb) {
-		__nfs_idmap_unregister(pipe);
-		rpc_put_sb_net(net);
-	}
-}
-
-static int nfs_idmap_register(struct nfs_client *clp,
-				   struct idmap *idmap,
-				   struct rpc_pipe *pipe)
-{
-	struct net *net = clp->cl_net;
-	struct super_block *pipefs_sb;
-	int err = 0;
-
-	pipefs_sb = rpc_get_sb_net(net);
-	if (pipefs_sb) {
-		if (clp->cl_rpcclient->cl_dentry)
-			err = __nfs_idmap_register(clp->cl_rpcclient->cl_dentry,
-						   idmap, pipe);
-		rpc_put_sb_net(net);
-	}
-	return err;
-}
+static const struct rpc_pipe_dir_object_ops nfs_idmap_pipe_dir_object_ops = {
+	.create = nfs_idmap_pipe_create,
+	.destroy = nfs_idmap_pipe_destroy,
+};
 
 int
 nfs_idmap_new(struct nfs_client *clp)
@@ -462,23 +445,31 @@ nfs_idmap_new(struct nfs_client *clp)
 	if (idmap == NULL)
 		return -ENOMEM;
 
+	rpc_init_pipe_dir_object(&idmap->idmap_pdo,
+			&nfs_idmap_pipe_dir_object_ops,
+			idmap);
+
 	pipe = rpc_mkpipe_data(&idmap_upcall_ops, 0);
 	if (IS_ERR(pipe)) {
 		error = PTR_ERR(pipe);
-		kfree(idmap);
-		return error;
-	}
-	error = nfs_idmap_register(clp, idmap, pipe);
-	if (error) {
-		rpc_destroy_pipe_data(pipe);
-		kfree(idmap);
-		return error;
+		goto err;
 	}
 	idmap->idmap_pipe = pipe;
 	mutex_init(&idmap->idmap_mutex);
 
+	error = rpc_add_pipe_dir_object(clp->cl_net,
+			&clp->cl_rpcclient->cl_pipedir_objects,
+			&idmap->idmap_pdo);
+	if (error)
+		goto err_destroy_pipe;
+
 	clp->cl_idmap = idmap;
 	return 0;
+err_destroy_pipe:
+	rpc_destroy_pipe_data(idmap->idmap_pipe);
+err:
+	kfree(idmap);
+	return error;
 }
 
 void
@@ -488,130 +479,26 @@ nfs_idmap_delete(struct nfs_client *clp)
 
 	if (!idmap)
 		return;
-	nfs_idmap_unregister(clp, idmap->idmap_pipe);
-	rpc_destroy_pipe_data(idmap->idmap_pipe);
 	clp->cl_idmap = NULL;
+	rpc_remove_pipe_dir_object(clp->cl_net,
+			&clp->cl_rpcclient->cl_pipedir_objects,
+			&idmap->idmap_pdo);
+	rpc_destroy_pipe_data(idmap->idmap_pipe);
 	kfree(idmap);
 }
 
-static int __rpc_pipefs_event(struct nfs_client *clp, unsigned long event,
-			      struct super_block *sb)
-{
-	int err = 0;
-
-	switch (event) {
-	case RPC_PIPEFS_MOUNT:
-		err = __nfs_idmap_register(clp->cl_rpcclient->cl_dentry,
-						clp->cl_idmap,
-						clp->cl_idmap->idmap_pipe);
-		break;
-	case RPC_PIPEFS_UMOUNT:
-		if (clp->cl_idmap->idmap_pipe) {
-			struct dentry *parent;
-
-			parent = clp->cl_idmap->idmap_pipe->dentry->d_parent;
-			__nfs_idmap_unregister(clp->cl_idmap->idmap_pipe);
-			/*
-			 * Note: This is a dirty hack. SUNRPC hook has been
-			 * called already but simple_rmdir() call for the
-			 * directory returned with error because of idmap pipe
-			 * inside. Thus now we have to remove this directory
-			 * here.
-			 */
-			if (rpc_rmdir(parent))
-				printk(KERN_ERR "NFS: %s: failed to remove "
-					"clnt dir!\n", __func__);
-		}
-		break;
-	default:
-		printk(KERN_ERR "NFS: %s: unknown event: %ld\n", __func__,
-			event);
-		return -ENOTSUPP;
-	}
-	return err;
-}
-
-static struct nfs_client *nfs_get_client_for_event(struct net *net, int event)
-{
-	struct nfs_net *nn = net_generic(net, nfs_net_id);
-	struct dentry *cl_dentry;
-	struct nfs_client *clp;
-	int err;
-
-restart:
-	spin_lock(&nn->nfs_client_lock);
-	list_for_each_entry(clp, &nn->nfs_client_list, cl_share_link) {
-		/* Wait for initialisation to finish */
-		if (clp->cl_cons_state == NFS_CS_INITING) {
-			atomic_inc(&clp->cl_count);
-			spin_unlock(&nn->nfs_client_lock);
-			err = nfs_wait_client_init_complete(clp);
-			nfs_put_client(clp);
-			if (err)
-				return NULL;
-			goto restart;
-		}
-		/* Skip nfs_clients that failed to initialise */
-		if (clp->cl_cons_state < 0)
-			continue;
-		smp_rmb();
-		if (clp->rpc_ops != &nfs_v4_clientops)
-			continue;
-		cl_dentry = clp->cl_idmap->idmap_pipe->dentry;
-		if (((event == RPC_PIPEFS_MOUNT) && cl_dentry) ||
-		    ((event == RPC_PIPEFS_UMOUNT) && !cl_dentry))
-			continue;
-		atomic_inc(&clp->cl_count);
-		spin_unlock(&nn->nfs_client_lock);
-		return clp;
-	}
-	spin_unlock(&nn->nfs_client_lock);
-	return NULL;
-}
-
-static int rpc_pipefs_event(struct notifier_block *nb, unsigned long event,
-			    void *ptr)
-{
-	struct super_block *sb = ptr;
-	struct nfs_client *clp;
-	int error = 0;
-
-	if (!try_module_get(THIS_MODULE))
-		return 0;
-
-	while ((clp = nfs_get_client_for_event(sb->s_fs_info, event))) {
-		error = __rpc_pipefs_event(clp, event, sb);
-		nfs_put_client(clp);
-		if (error)
-			break;
-	}
-	module_put(THIS_MODULE);
-	return error;
-}
-
-#define PIPEFS_NFS_PRIO		1
-
-static struct notifier_block nfs_idmap_block = {
-	.notifier_call	= rpc_pipefs_event,
-	.priority	= SUNRPC_PIPEFS_NFS_PRIO,
-};
-
 int nfs_idmap_init(void)
 {
 	int ret;
 	ret = nfs_idmap_init_keyring();
 	if (ret != 0)
 		goto out;
-	ret = rpc_pipefs_notifier_register(&nfs_idmap_block);
-	if (ret != 0)
-		nfs_idmap_quit_keyring();
 out:
 	return ret;
 }
 
 void nfs_idmap_quit(void)
 {
-	rpc_pipefs_notifier_unregister(&nfs_idmap_block);
 	nfs_idmap_quit_keyring();
 }
 
@@ -849,6 +736,7 @@ int nfs_map_name_to_uid(const struct nfs_server *server, const char *name, size_
 		if (!uid_valid(*uid))
 			ret = -ERANGE;
 	}
+	trace_nfs4_map_name_to_uid(name, namelen, id, ret);
 	return ret;
 }
 
@@ -865,6 +753,7 @@ int nfs_map_group_to_gid(const struct nfs_server *server, const char *name, size
 		if (!gid_valid(*gid))
 			ret = -ERANGE;
 	}
+	trace_nfs4_map_group_to_gid(name, namelen, id, ret);
 	return ret;
 }
 
@@ -879,6 +768,7 @@ int nfs_map_uid_to_name(const struct nfs_server *server, kuid_t uid, char *buf,
 		ret = nfs_idmap_lookup_name(id, "user", buf, buflen, idmap);
 	if (ret < 0)
 		ret = nfs_map_numeric_to_string(id, buf, buflen);
+	trace_nfs4_map_uid_to_name(buf, ret, id, ret);
 	return ret;
 }
 int nfs_map_gid_to_group(const struct nfs_server *server, kgid_t gid, char *buf, size_t buflen)
@@ -892,5 +782,6 @@ int nfs_map_gid_to_group(const struct nfs_server *server, kgid_t gid, char *buf,
 		ret = nfs_idmap_lookup_name(id, "group", buf, buflen, idmap);
 	if (ret < 0)
 		ret = nfs_map_numeric_to_string(id, buf, buflen);
+	trace_nfs4_map_gid_to_group(buf, ret, id, ret);
 	return ret;
 }

fs/nfs/inode.c

@@ -38,7 +38,6 @@
 #include <linux/slab.h>
 #include <linux/compat.h>
 #include <linux/freezer.h>
-#include <linux/crc32.h>
 
 #include <asm/uaccess.h>
 
@@ -52,6 +51,8 @@
 #include "nfs.h"
 #include "netns.h"
 
+#include "nfstrace.h"
+
 #define NFSDBG_FACILITY		NFSDBG_VFS
 
 #define NFS_64_BIT_INODE_NUMBERS_ENABLED	1
@@ -503,6 +504,8 @@ nfs_setattr(struct dentry *dentry, struct iattr *attr)
 	if ((attr->ia_valid & ~(ATTR_FILE|ATTR_OPEN)) == 0)
 		return 0;
 
+	trace_nfs_setattr_enter(inode);
+
 	/* Write all dirty data */
 	if (S_ISREG(inode->i_mode)) {
 		nfs_inode_dio_wait(inode);
@@ -522,6 +525,7 @@ nfs_setattr(struct dentry *dentry, struct iattr *attr)
 		error = nfs_refresh_inode(inode, fattr);
 	nfs_free_fattr(fattr);
 out:
+	trace_nfs_setattr_exit(inode, error);
 	return error;
 }
 EXPORT_SYMBOL_GPL(nfs_setattr);
@@ -591,6 +595,7 @@ int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
 	int need_atime = NFS_I(inode)->cache_validity & NFS_INO_INVALID_ATIME;
 	int err;
 
+	trace_nfs_getattr_enter(inode);
 	/* Flush out writes to the server in order to update c/mtime.  */
 	if (S_ISREG(inode->i_mode)) {
 		nfs_inode_dio_wait(inode);
@@ -621,6 +626,7 @@ int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
 		stat->ino = nfs_compat_user_ino64(NFS_FILEID(inode));
 	}
 out:
+	trace_nfs_getattr_exit(inode, err);
 	return err;
 }
 EXPORT_SYMBOL_GPL(nfs_getattr);
@@ -875,6 +881,8 @@ __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
 	dfprintk(PAGECACHE, "NFS: revalidating (%s/%Ld)\n",
 		inode->i_sb->s_id, (long long)NFS_FILEID(inode));
 
+	trace_nfs_revalidate_inode_enter(inode);
+
 	if (is_bad_inode(inode))
 		goto out;
 	if (NFS_STALE(inode))
@@ -925,6 +933,7 @@ __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
 	nfs4_label_free(label);
 out:
 	nfs_free_fattr(fattr);
+	trace_nfs_revalidate_inode_exit(inode, status);
 	return status;
 }
 
@@ -981,6 +990,7 @@ static int nfs_invalidate_mapping(struct inode *inode, struct address_space *map
 	spin_unlock(&inode->i_lock);
 	nfs_inc_stats(inode, NFSIOS_DATAINVALIDATE);
 	nfs_fscache_wait_on_invalidate(inode);
+
 	dfprintk(PAGECACHE, "NFS: (%s/%Ld) data cache invalidated\n",
 			inode->i_sb->s_id, (long long)NFS_FILEID(inode));
 	return 0;
@@ -1014,8 +1024,12 @@ int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
 		if (ret < 0)
 			goto out;
 	}
-	if (nfsi->cache_validity & NFS_INO_INVALID_DATA)
+	if (nfsi->cache_validity & NFS_INO_INVALID_DATA) {
+		trace_nfs_invalidate_mapping_enter(inode);
 		ret = nfs_invalidate_mapping(inode, mapping);
+		trace_nfs_invalidate_mapping_exit(inode, ret);
+	}
+
 out:
 	return ret;
 }
@@ -1195,7 +1209,7 @@ u32 _nfs_display_fhandle_hash(const struct nfs_fh *fh)
 {
 	/* wireshark uses 32-bit AUTODIN crc and does a bitwise
 	 * not on the result */
-	return ~crc32(0xFFFFFFFF, &fh->data[0], fh->size);
+	return nfs_fhandle_hash(fh);
 }
 
 /*
@@ -1274,9 +1288,17 @@ static int nfs_inode_attrs_need_update(const struct inode *inode, const struct n
 
 static int nfs_refresh_inode_locked(struct inode *inode, struct nfs_fattr *fattr)
 {
+	int ret;
+
+	trace_nfs_refresh_inode_enter(inode);
+
 	if (nfs_inode_attrs_need_update(inode, fattr))
-		return nfs_update_inode(inode, fattr);
-	return nfs_check_inode_attributes(inode, fattr);
+		ret = nfs_update_inode(inode, fattr);
+	else
+		ret = nfs_check_inode_attributes(inode, fattr);
+
+	trace_nfs_refresh_inode_exit(inode, ret);
+	return ret;
 }
 
 /**

fs/nfs/internal.h

@@ -5,6 +5,7 @@
 #include "nfs4_fs.h"
 #include <linux/mount.h>
 #include <linux/security.h>
+#include <linux/crc32.h>
 
 #define NFS_MS_MASK (MS_RDONLY|MS_NOSUID|MS_NODEV|MS_NOEXEC|MS_SYNCHRONOUS)
 
@@ -185,6 +186,8 @@ extern struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
 					     int ds_addrlen, int ds_proto,
 					     unsigned int ds_timeo,
 					     unsigned int ds_retrans);
+extern struct rpc_clnt *nfs4_find_or_create_ds_client(struct nfs_client *,
+						struct inode *);
 #ifdef CONFIG_PROC_FS
 extern int __init nfs_fs_proc_init(void);
 extern void nfs_fs_proc_exit(void);
@@ -267,7 +270,7 @@ extern struct rpc_procinfo nfs4_procedures[];
 void nfs_close_context(struct nfs_open_context *ctx, int is_sync);
 extern struct nfs_client *nfs_init_client(struct nfs_client *clp,
 			   const struct rpc_timeout *timeparms,
-			   const char *ip_addr, rpc_authflavor_t authflavour);
+			   const char *ip_addr);
 
 /* dir.c */
 extern int nfs_access_cache_shrinker(struct shrinker *shrink,
@@ -355,7 +358,7 @@ extern struct dentry *nfs_get_root(struct super_block *, struct nfs_fh *,
 extern struct dentry *nfs4_get_root(struct super_block *, struct nfs_fh *,
 				    const char *);
 
-extern int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh);
+extern int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh, bool);
 #endif
 
 struct nfs_pgio_completion_ops;
@@ -430,6 +433,8 @@ void nfs_request_remove_commit_list(struct nfs_page *req,
 void nfs_init_cinfo(struct nfs_commit_info *cinfo,
 		    struct inode *inode,
 		    struct nfs_direct_req *dreq);
+int nfs_key_timeout_notify(struct file *filp, struct inode *inode);
+bool nfs_ctx_key_to_expire(struct nfs_open_context *ctx);
 
 #ifdef CONFIG_MIGRATION
 extern int nfs_migrate_page(struct address_space *,
@@ -451,8 +456,7 @@ extern ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq);
 extern void __nfs4_read_done_cb(struct nfs_read_data *);
 extern struct nfs_client *nfs4_init_client(struct nfs_client *clp,
 			    const struct rpc_timeout *timeparms,
-			    const char *ip_addr,
-			    rpc_authflavor_t authflavour);
+			    const char *ip_addr);
 extern int nfs40_walk_client_list(struct nfs_client *clp,
 				struct nfs_client **result,
 				struct rpc_cred *cred);
@@ -575,3 +579,22 @@ u64 nfs_timespec_to_change_attr(const struct timespec *ts)
 {
 	return ((u64)ts->tv_sec << 30) + ts->tv_nsec;
 }
+
+#ifdef CONFIG_CRC32
+/**
+ * nfs_fhandle_hash - calculate the crc32 hash for the filehandle
+ * @fh - pointer to filehandle
+ *
+ * returns a crc32 hash for the filehandle that is compatible with
+ * the one displayed by "wireshark".
+ */
+static inline u32 nfs_fhandle_hash(const struct nfs_fh *fh)
+{
+	return ~crc32_le(0xFFFFFFFF, &fh->data[0], fh->size);
+}
+#else
+static inline u32 nfs_fhandle_hash(const struct nfs_fh *fh)
+{
+	return 0;
+}
+#endif

fs/nfs/nfs3proc.c

@@ -336,8 +336,8 @@ nfs3_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
 	data->arg.create.createmode = NFS3_CREATE_UNCHECKED;
 	if (flags & O_EXCL) {
 		data->arg.create.createmode  = NFS3_CREATE_EXCLUSIVE;
-		data->arg.create.verifier[0] = jiffies;
-		data->arg.create.verifier[1] = current->pid;
+		data->arg.create.verifier[0] = cpu_to_be32(jiffies);
+		data->arg.create.verifier[1] = cpu_to_be32(current->pid);
 	}
 
 	sattr->ia_mode &= ~current_umask();
@@ -826,9 +826,10 @@ static void nfs3_proc_read_setup(struct nfs_read_data *data, struct rpc_message
 	msg->rpc_proc = &nfs3_procedures[NFS3PROC_READ];
 }
 
-static void nfs3_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_data *data)
+static int nfs3_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_data *data)
 {
 	rpc_call_start(task);
+	return 0;
 }
 
 static int nfs3_write_done(struct rpc_task *task, struct nfs_write_data *data)
@@ -847,9 +848,10 @@ static void nfs3_proc_write_setup(struct nfs_write_data *data, struct rpc_messag
 	msg->rpc_proc = &nfs3_procedures[NFS3PROC_WRITE];
 }
 
-static void nfs3_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_data *data)
+static int nfs3_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_data *data)
 {
 	rpc_call_start(task);
+	return 0;
 }
 
 static void nfs3_proc_commit_rpc_prepare(struct rpc_task *task, struct nfs_commit_data *data)

fs/nfs/nfs4_fs.h

@@ -38,17 +38,15 @@ struct nfs4_minor_version_ops {
 	u32	minor_version;
 	unsigned init_caps;
 
-	int	(*call_sync)(struct rpc_clnt *clnt,
-			struct nfs_server *server,
-			struct rpc_message *msg,
-			struct nfs4_sequence_args *args,
-			struct nfs4_sequence_res *res);
+	int	(*init_client)(struct nfs_client *);
+	void	(*shutdown_client)(struct nfs_client *);
 	bool	(*match_stateid)(const nfs4_stateid *,
 			const nfs4_stateid *);
 	int	(*find_root_sec)(struct nfs_server *, struct nfs_fh *,
 			struct nfs_fsinfo *);
 	int	(*free_lock_state)(struct nfs_server *,
 			struct nfs4_lock_state *);
+	const struct rpc_call_ops *call_sync_ops;
 	const struct nfs4_state_recovery_ops *reboot_recovery_ops;
 	const struct nfs4_state_recovery_ops *nograce_recovery_ops;
 	const struct nfs4_state_maintenance_ops *state_renewal_ops;
@@ -135,6 +133,7 @@ struct nfs4_lock_state {
 	struct list_head	ls_locks;	/* Other lock stateids */
 	struct nfs4_state *	ls_state;	/* Pointer to open state */
 #define NFS_LOCK_INITIALIZED 0
+#define NFS_LOCK_LOST        1
 	unsigned long		ls_flags;
 	struct nfs_seqid_counter	ls_seqid;
 	nfs4_stateid		ls_stateid;
@@ -193,7 +192,6 @@ struct nfs4_state_recovery_ops {
 	int (*recover_open)(struct nfs4_state_owner *, struct nfs4_state *);
 	int (*recover_lock)(struct nfs4_state *, struct file_lock *);
 	int (*establish_clid)(struct nfs_client *, struct rpc_cred *);
-	struct rpc_cred * (*get_clid_cred)(struct nfs_client *);
 	int (*reclaim_complete)(struct nfs_client *, struct rpc_cred *);
 	int (*detect_trunking)(struct nfs_client *, struct nfs_client **,
 		struct rpc_cred *);
@@ -223,7 +221,7 @@ struct vfsmount *nfs4_submount(struct nfs_server *, struct dentry *,
 /* nfs4proc.c */
 extern int nfs4_proc_setclientid(struct nfs_client *, u32, unsigned short, struct rpc_cred *, struct nfs4_setclientid_res *);
 extern int nfs4_proc_setclientid_confirm(struct nfs_client *, struct nfs4_setclientid_res *arg, struct rpc_cred *);
-extern int nfs4_proc_get_rootfh(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *);
+extern int nfs4_proc_get_rootfh(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *, bool);
 extern int nfs4_proc_bind_conn_to_session(struct nfs_client *, struct rpc_cred *cred);
 extern int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred);
 extern int nfs4_destroy_clientid(struct nfs_client *clp);
@@ -248,9 +246,6 @@ static inline struct nfs4_session *nfs4_get_session(const struct nfs_server *ser
 	return server->nfs_client->cl_session;
 }
 
-extern int nfs4_setup_sequence(const struct nfs_server *server,
-		struct nfs4_sequence_args *args, struct nfs4_sequence_res *res,
-		struct rpc_task *task);
 extern int nfs41_setup_sequence(struct nfs4_session *session,
 		struct nfs4_sequence_args *args, struct nfs4_sequence_res *res,
 		struct rpc_task *task);
@@ -273,18 +268,63 @@ is_ds_client(struct nfs_client *clp)
 {
 	return clp->cl_exchange_flags & EXCHGID4_FLAG_USE_PNFS_DS;
 }
-#else /* CONFIG_NFS_v4_1 */
-static inline struct nfs4_session *nfs4_get_session(const struct nfs_server *server)
+
+static inline bool
+_nfs4_state_protect(struct nfs_client *clp, unsigned long sp4_mode,
+		    struct rpc_clnt **clntp, struct rpc_message *msg)
 {
-	return NULL;
+	struct rpc_cred *newcred = NULL;
+	rpc_authflavor_t flavor;
+
+	if (test_bit(sp4_mode, &clp->cl_sp4_flags)) {
+		spin_lock(&clp->cl_lock);
+		if (clp->cl_machine_cred != NULL)
+			newcred = get_rpccred(clp->cl_machine_cred);
+		spin_unlock(&clp->cl_lock);
+		if (msg->rpc_cred)
+			put_rpccred(msg->rpc_cred);
+		msg->rpc_cred = newcred;
+
+		flavor = clp->cl_rpcclient->cl_auth->au_flavor;
+		WARN_ON(flavor != RPC_AUTH_GSS_KRB5I &&
+			flavor != RPC_AUTH_GSS_KRB5P);
+		*clntp = clp->cl_rpcclient;
+
+		return true;
+	}
+	return false;
 }
 
-static inline int nfs4_setup_sequence(const struct nfs_server *server,
-		struct nfs4_sequence_args *args, struct nfs4_sequence_res *res,
-		struct rpc_task *task)
+/*
+ * Function responsible for determining if an rpc_message should use the
+ * machine cred under SP4_MACH_CRED and if so switching the credential and
+ * authflavor (using the nfs_client's rpc_clnt which will be krb5i/p).
+ * Should be called before rpc_call_sync/rpc_call_async.
+ */
+static inline void
+nfs4_state_protect(struct nfs_client *clp, unsigned long sp4_mode,
+		   struct rpc_clnt **clntp, struct rpc_message *msg)
 {
-	rpc_call_start(task);
-	return 0;
+	_nfs4_state_protect(clp, sp4_mode, clntp, msg);
+}
+
+/*
+ * Special wrapper to nfs4_state_protect for write.
+ * If WRITE can use machine cred but COMMIT cannot, make sure all writes
+ * that use machine cred use NFS_FILE_SYNC.
+ */
+static inline void
+nfs4_state_protect_write(struct nfs_client *clp, struct rpc_clnt **clntp,
+			 struct rpc_message *msg, struct nfs_write_data *wdata)
+{
+	if (_nfs4_state_protect(clp, NFS_SP4_MACH_CRED_WRITE, clntp, msg) &&
+	    !test_bit(NFS_SP4_MACH_CRED_COMMIT, &clp->cl_sp4_flags))
+		wdata->args.stable = NFS_FILE_SYNC;
+}
+#else /* CONFIG_NFS_v4_1 */
+static inline struct nfs4_session *nfs4_get_session(const struct nfs_server *server)
+{
+	return NULL;
 }
 
 static inline bool
@@ -298,6 +338,18 @@ is_ds_client(struct nfs_client *clp)
 {
 	return false;
 }
+
+static inline void
+nfs4_state_protect(struct nfs_client *clp, unsigned long sp4_flags,
+		   struct rpc_clnt **clntp, struct rpc_message *msg)
+{
+}
+
+static inline void
+nfs4_state_protect_write(struct nfs_client *clp, struct rpc_clnt **clntp,
+			 struct rpc_message *msg, struct nfs_write_data *wdata)
+{
+}
 #endif /* CONFIG_NFS_V4_1 */
 
 extern const struct nfs4_minor_version_ops *nfs_v4_minor_ops[];
@@ -308,6 +360,10 @@ extern const u32 nfs4_pathconf_bitmap[3];
 extern const u32 nfs4_fsinfo_bitmap[3];
 extern const u32 nfs4_fs_locations_bitmap[3];
 
+void nfs40_shutdown_client(struct nfs_client *);
+void nfs41_shutdown_client(struct nfs_client *);
+int nfs40_init_client(struct nfs_client *);
+int nfs41_init_client(struct nfs_client *);
 void nfs4_free_client(struct nfs_client *);
 
 struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *);
@@ -319,7 +375,7 @@ extern void nfs4_kill_renewd(struct nfs_client *);
 extern void nfs4_renew_state(struct work_struct *);
 
 /* nfs4state.c */
-struct rpc_cred *nfs4_get_setclientid_cred(struct nfs_client *clp);
+struct rpc_cred *nfs4_get_clid_cred(struct nfs_client *clp);
 struct rpc_cred *nfs4_get_machine_cred_locked(struct nfs_client *clp);
 struct rpc_cred *nfs4_get_renew_cred_locked(struct nfs_client *clp);
 int nfs4_discover_server_trunking(struct nfs_client *clp,
@@ -327,7 +383,6 @@ int nfs4_discover_server_trunking(struct nfs_client *clp,
 int nfs40_discover_server_trunking(struct nfs_client *clp,
 			struct nfs_client **, struct rpc_cred *);
 #if defined(CONFIG_NFS_V4_1)
-struct rpc_cred *nfs4_get_exchange_id_cred(struct nfs_client *clp);
 int nfs41_discover_server_trunking(struct nfs_client *clp,
 			struct nfs_client **, struct rpc_cred *);
 extern void nfs4_schedule_session_recovery(struct nfs4_session *, int);
@@ -382,6 +437,7 @@ struct dentry *nfs4_try_mount(int, const char *, struct nfs_mount_info *, struct
 extern bool nfs4_disable_idmapping;
 extern unsigned short max_session_slots;
 extern unsigned short send_implementation_id;
+extern bool recover_lost_locks;
 
 #define NFS4_CLIENT_ID_UNIQ_LEN		(64)
 extern char nfs4_client_id_uniquifier[NFS4_CLIENT_ID_UNIQ_LEN];
@@ -429,6 +485,8 @@ static inline bool nfs4_valid_open_stateid(const struct nfs4_state *state)
 
 #define nfs4_close_state(a, b) do { } while (0)
 #define nfs4_close_sync(a, b) do { } while (0)
+#define nfs4_state_protect(a, b, c, d) do { } while (0)
+#define nfs4_state_protect_write(a, b, c, d) do { } while (0)
 
 #endif /* CONFIG_NFS_V4 */
 #endif /* __LINUX_FS_NFS_NFS4_FS.H */

fs/nfs/nfs4client.c

@@ -41,19 +41,138 @@ static int nfs_get_cb_ident_idr(struct nfs_client *clp, int minorversion)
 }
 
 #ifdef CONFIG_NFS_V4_1
-static void nfs4_shutdown_session(struct nfs_client *clp)
+/**
+ * Per auth flavor data server rpc clients
+ */
+struct nfs4_ds_server {
+	struct list_head	list;   /* ds_clp->cl_ds_clients */
+	struct rpc_clnt		*rpc_clnt;
+};
+
+/**
+ * Common lookup case for DS I/O
+ */
+static struct nfs4_ds_server *
+nfs4_find_ds_client(struct nfs_client *ds_clp, rpc_authflavor_t flavor)
+{
+	struct nfs4_ds_server *dss;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(dss, &ds_clp->cl_ds_clients, list) {
+		if (dss->rpc_clnt->cl_auth->au_flavor != flavor)
+			continue;
+		goto out;
+	}
+	dss = NULL;
+out:
+	rcu_read_unlock();
+	return dss;
+}
+
+static struct nfs4_ds_server *
+nfs4_add_ds_client(struct nfs_client *ds_clp, rpc_authflavor_t flavor,
+			   struct nfs4_ds_server *new)
+{
+	struct nfs4_ds_server *dss;
+
+	spin_lock(&ds_clp->cl_lock);
+	list_for_each_entry(dss, &ds_clp->cl_ds_clients, list) {
+		if (dss->rpc_clnt->cl_auth->au_flavor != flavor)
+			continue;
+		goto out;
+	}
+	if (new)
+		list_add_rcu(&new->list, &ds_clp->cl_ds_clients);
+	dss = new;
+out:
+	spin_unlock(&ds_clp->cl_lock); /* need some lock to protect list */
+	return dss;
+}
+
+static struct nfs4_ds_server *
+nfs4_alloc_ds_server(struct nfs_client *ds_clp, rpc_authflavor_t flavor)
+{
+	struct nfs4_ds_server *dss;
+
+	dss = kmalloc(sizeof(*dss), GFP_NOFS);
+	if (dss == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	dss->rpc_clnt = rpc_clone_client_set_auth(ds_clp->cl_rpcclient, flavor);
+	if (IS_ERR(dss->rpc_clnt)) {
+		int err = PTR_ERR(dss->rpc_clnt);
+		kfree (dss);
+		return ERR_PTR(err);
+	}
+	INIT_LIST_HEAD(&dss->list);
+
+	return dss;
+}
+
+static void
+nfs4_free_ds_server(struct nfs4_ds_server *dss)
+{
+	rpc_release_client(dss->rpc_clnt);
+	kfree(dss);
+}
+
+/**
+* Find or create a DS rpc client with th MDS server rpc client auth flavor
+* in the nfs_client cl_ds_clients list.
+*/
+struct rpc_clnt *
+nfs4_find_or_create_ds_client(struct nfs_client *ds_clp, struct inode *inode)
+{
+	struct nfs4_ds_server *dss, *new;
+	rpc_authflavor_t flavor = NFS_SERVER(inode)->client->cl_auth->au_flavor;
+
+	dss = nfs4_find_ds_client(ds_clp, flavor);
+	if (dss != NULL)
+		goto out;
+	new = nfs4_alloc_ds_server(ds_clp, flavor);
+	if (IS_ERR(new))
+		return ERR_CAST(new);
+	dss = nfs4_add_ds_client(ds_clp, flavor, new);
+	if (dss != new)
+		nfs4_free_ds_server(new);
+out:
+	return dss->rpc_clnt;
+}
+EXPORT_SYMBOL_GPL(nfs4_find_or_create_ds_client);
+
+static void
+nfs4_shutdown_ds_clients(struct nfs_client *clp)
+{
+	struct nfs4_ds_server *dss;
+	LIST_HEAD(shutdown_list);
+
+	while (!list_empty(&clp->cl_ds_clients)) {
+		dss = list_entry(clp->cl_ds_clients.next,
+					struct nfs4_ds_server, list);
+		list_del(&dss->list);
+		rpc_shutdown_client(dss->rpc_clnt);
+		kfree (dss);
+	}
+}
+
+void nfs41_shutdown_client(struct nfs_client *clp)
 {
 	if (nfs4_has_session(clp)) {
+		nfs4_shutdown_ds_clients(clp);
 		nfs4_destroy_session(clp->cl_session);
 		nfs4_destroy_clientid(clp);
 	}
 
 }
-#else /* CONFIG_NFS_V4_1 */
-static void nfs4_shutdown_session(struct nfs_client *clp)
+#endif	/* CONFIG_NFS_V4_1 */
+
+void nfs40_shutdown_client(struct nfs_client *clp)
 {
+	if (clp->cl_slot_tbl) {
+		nfs4_release_slot_table(clp->cl_slot_tbl);
+		kfree(clp->cl_slot_tbl);
+	}
 }
-#endif /* CONFIG_NFS_V4_1 */
 
 struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *cl_init)
 {
@@ -73,6 +192,7 @@ struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *cl_init)
 
 	spin_lock_init(&clp->cl_lock);
 	INIT_DELAYED_WORK(&clp->cl_renewd, nfs4_renew_state);
+	INIT_LIST_HEAD(&clp->cl_ds_clients);
 	rpc_init_wait_queue(&clp->cl_rpcwaitq, "NFS client");
 	clp->cl_state = 1 << NFS4CLNT_LEASE_EXPIRED;
 	clp->cl_minorversion = cl_init->minorversion;
@@ -97,7 +217,7 @@ static void nfs4_shutdown_client(struct nfs_client *clp)
 {
 	if (__test_and_clear_bit(NFS_CS_RENEWD, &clp->cl_res_state))
 		nfs4_kill_renewd(clp);
-	nfs4_shutdown_session(clp);
+	clp->cl_mvops->shutdown_client(clp);
 	nfs4_destroy_callback(clp);
 	if (__test_and_clear_bit(NFS_CS_IDMAP, &clp->cl_res_state))
 		nfs_idmap_delete(clp);
@@ -144,14 +264,44 @@ static int nfs4_init_callback(struct nfs_client *clp)
 	return 0;
 }
 
-/*
- * Initialize the minor version specific parts of an NFS4 client record
+/**
+ * nfs40_init_client - nfs_client initialization tasks for NFSv4.0
+ * @clp - nfs_client to initialize
+ *
+ * Returns zero on success, or a negative errno if some error occurred.
  */
-static int nfs4_init_client_minor_version(struct nfs_client *clp)
+int nfs40_init_client(struct nfs_client *clp)
 {
+	struct nfs4_slot_table *tbl;
+	int ret;
+
+	tbl = kzalloc(sizeof(*tbl), GFP_NOFS);
+	if (tbl == NULL)
+		return -ENOMEM;
+
+	ret = nfs4_setup_slot_table(tbl, NFS4_MAX_SLOT_TABLE,
+					"NFSv4.0 transport Slot table");
+	if (ret) {
+		kfree(tbl);
+		return ret;
+	}
+
+	clp->cl_slot_tbl = tbl;
+	return 0;
+}
+
 #if defined(CONFIG_NFS_V4_1)
-	if (clp->cl_mvops->minor_version) {
+
+/**
+ * nfs41_init_client - nfs_client initialization tasks for NFSv4.1+
+ * @clp - nfs_client to initialize
+ *
+ * Returns zero on success, or a negative errno if some error occurred.
+ */
+int nfs41_init_client(struct nfs_client *clp)
+{
 	struct nfs4_session *session = NULL;
+
 	/*
 	 * Create the session and mark it expired.
 	 * When a SEQUENCE operation encounters the expired session
@@ -162,6 +312,7 @@ static int nfs4_init_client_minor_version(struct nfs_client *clp)
 		return -ENOMEM;
 
 	clp->cl_session = session;
+
 	/*
 	 * The create session reply races with the server back
 	 * channel probe. Mark the client NFS_CS_SESSION_INITING
@@ -169,9 +320,21 @@ static int nfs4_init_client_minor_version(struct nfs_client *clp)
 	 * nfs_client struct
 	 */
 	nfs_mark_client_ready(clp, NFS_CS_SESSION_INITING);
-	}
+	return 0;
+}
+
 #endif	/* CONFIG_NFS_V4_1 */
 
+/*
+ * Initialize the minor version specific parts of an NFS4 client record
+ */
+static int nfs4_init_client_minor_version(struct nfs_client *clp)
+{
+	int ret;
+
+	ret = clp->cl_mvops->init_client(clp);
+	if (ret)
+		return ret;
 	return nfs4_init_callback(clp);
 }
 
@@ -187,8 +350,7 @@ static int nfs4_init_client_minor_version(struct nfs_client *clp)
  */
 struct nfs_client *nfs4_init_client(struct nfs_client *clp,
 				    const struct rpc_timeout *timeparms,
-				    const char *ip_addr,
-				    rpc_authflavor_t authflavour)
+				    const char *ip_addr)
 {
 	char buf[INET6_ADDRSTRLEN + 1];
 	struct nfs_client *old;
@@ -723,7 +885,7 @@ static void nfs4_session_set_rwsize(struct nfs_server *server)
 }
 
 static int nfs4_server_common_setup(struct nfs_server *server,
-		struct nfs_fh *mntfh)
+		struct nfs_fh *mntfh, bool auth_probe)
 {
 	struct nfs_fattr *fattr;
 	int error;
@@ -755,7 +917,7 @@ static int nfs4_server_common_setup(struct nfs_server *server,
 
 
 	/* Probe the root fh to retrieve its FSID and filehandle */
-	error = nfs4_get_rootfh(server, mntfh);
+	error = nfs4_get_rootfh(server, mntfh, auth_probe);
 	if (error < 0)
 		goto out;
 
@@ -787,6 +949,7 @@ static int nfs4_server_common_setup(struct nfs_server *server,
 static int nfs4_init_server(struct nfs_server *server,
 		const struct nfs_parsed_mount_data *data)
 {
+	rpc_authflavor_t pseudoflavor = RPC_AUTH_UNIX;
 	struct rpc_timeout timeparms;
 	int error;
 
@@ -799,13 +962,16 @@ static int nfs4_init_server(struct nfs_server *server,
 	server->flags = data->flags;
 	server->options = data->options;
 
+	if (data->auth_flavor_len >= 1)
+		pseudoflavor = data->auth_flavors[0];
+
 	/* Get a client record */
 	error = nfs4_set_client(server,
 			data->nfs_server.hostname,
 			(const struct sockaddr *)&data->nfs_server.address,
 			data->nfs_server.addrlen,
 			data->client_address,
-			data->auth_flavors[0],
+			pseudoflavor,
 			data->nfs_server.protocol,
 			&timeparms,
 			data->minorversion,
@@ -825,7 +991,7 @@ static int nfs4_init_server(struct nfs_server *server,
 
 	server->port = data->nfs_server.port;
 
-	error = nfs_init_server_rpcclient(server, &timeparms, data->auth_flavors[0]);
+	error = nfs_init_server_rpcclient(server, &timeparms, pseudoflavor);
 
 error:
 	/* Done */
@@ -843,6 +1009,7 @@ struct nfs_server *nfs4_create_server(struct nfs_mount_info *mount_info,
 				      struct nfs_subversion *nfs_mod)
 {
 	struct nfs_server *server;
+	bool auth_probe;
 	int error;
 
 	dprintk("--> nfs4_create_server()\n");
@@ -851,12 +1018,14 @@ struct nfs_server *nfs4_create_server(struct nfs_mount_info *mount_info,
 	if (!server)
 		return ERR_PTR(-ENOMEM);
 
+	auth_probe = mount_info->parsed->auth_flavor_len < 1;
+
 	/* set up the general RPC client */
 	error = nfs4_init_server(server, mount_info->parsed);
 	if (error < 0)
 		goto error;
 
-	error = nfs4_server_common_setup(server, mount_info->mntfh);
+	error = nfs4_server_common_setup(server, mount_info->mntfh, auth_probe);
 	if (error < 0)
 		goto error;
 
@@ -909,7 +1078,8 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data,
 	if (error < 0)
 		goto error;
 
-	error = nfs4_server_common_setup(server, mntfh);
+	error = nfs4_server_common_setup(server, mntfh,
+			!(parent_server->flags & NFS_MOUNT_SECFLAVOUR));
 	if (error < 0)
 		goto error;
 

fs/nfs/nfs4filelayout.c

@@ -39,6 +39,7 @@
 #include "internal.h"
 #include "delegation.h"
 #include "nfs4filelayout.h"
+#include "nfs4trace.h"
 
 #define NFSDBG_FACILITY         NFSDBG_PNFS_LD
 
@@ -247,6 +248,7 @@ static int filelayout_read_done_cb(struct rpc_task *task,
 	struct nfs_pgio_header *hdr = data->header;
 	int err;
 
+	trace_nfs4_pnfs_read(data, task->tk_status);
 	err = filelayout_async_handle_error(task, data->args.context->state,
 					    data->ds_clp, hdr->lseg);
 
@@ -363,6 +365,7 @@ static int filelayout_write_done_cb(struct rpc_task *task,
 	struct nfs_pgio_header *hdr = data->header;
 	int err;
 
+	trace_nfs4_pnfs_write(data, task->tk_status);
 	err = filelayout_async_handle_error(task, data->args.context->state,
 					    data->ds_clp, hdr->lseg);
 
@@ -395,6 +398,7 @@ static int filelayout_commit_done_cb(struct rpc_task *task,
 {
 	int err;
 
+	trace_nfs4_pnfs_commit_ds(data, task->tk_status);
 	err = filelayout_async_handle_error(task, NULL, data->ds_clp,
 					    data->lseg);
 
@@ -524,6 +528,7 @@ filelayout_read_pagelist(struct nfs_read_data *data)
 	struct nfs_pgio_header *hdr = data->header;
 	struct pnfs_layout_segment *lseg = hdr->lseg;
 	struct nfs4_pnfs_ds *ds;
+	struct rpc_clnt *ds_clnt;
 	loff_t offset = data->args.offset;
 	u32 j, idx;
 	struct nfs_fh *fh;
@@ -538,6 +543,11 @@ filelayout_read_pagelist(struct nfs_read_data *data)
 	ds = nfs4_fl_prepare_ds(lseg, idx);
 	if (!ds)
 		return PNFS_NOT_ATTEMPTED;
+
+	ds_clnt = nfs4_find_or_create_ds_client(ds->ds_clp, hdr->inode);
+	if (IS_ERR(ds_clnt))
+		return PNFS_NOT_ATTEMPTED;
+
 	dprintk("%s USE DS: %s cl_count %d\n", __func__,
 		ds->ds_remotestr, atomic_read(&ds->ds_clp->cl_count));
 
@@ -552,7 +562,7 @@ filelayout_read_pagelist(struct nfs_read_data *data)
 	data->mds_offset = offset;
 
 	/* Perform an asynchronous read to ds */
-	nfs_initiate_read(ds->ds_clp->cl_rpcclient, data,
+	nfs_initiate_read(ds_clnt, data,
 				  &filelayout_read_call_ops, RPC_TASK_SOFTCONN);
 	return PNFS_ATTEMPTED;
 }
@@ -564,6 +574,7 @@ filelayout_write_pagelist(struct nfs_write_data *data, int sync)
 	struct nfs_pgio_header *hdr = data->header;
 	struct pnfs_layout_segment *lseg = hdr->lseg;
 	struct nfs4_pnfs_ds *ds;
+	struct rpc_clnt *ds_clnt;
 	loff_t offset = data->args.offset;
 	u32 j, idx;
 	struct nfs_fh *fh;
@@ -574,6 +585,11 @@ filelayout_write_pagelist(struct nfs_write_data *data, int sync)
 	ds = nfs4_fl_prepare_ds(lseg, idx);
 	if (!ds)
 		return PNFS_NOT_ATTEMPTED;
+
+	ds_clnt = nfs4_find_or_create_ds_client(ds->ds_clp, hdr->inode);
+	if (IS_ERR(ds_clnt))
+		return PNFS_NOT_ATTEMPTED;
+
 	dprintk("%s ino %lu sync %d req %Zu@%llu DS: %s cl_count %d\n",
 		__func__, hdr->inode->i_ino, sync, (size_t) data->args.count,
 		offset, ds->ds_remotestr, atomic_read(&ds->ds_clp->cl_count));
@@ -591,7 +607,7 @@ filelayout_write_pagelist(struct nfs_write_data *data, int sync)
 	data->args.offset = filelayout_get_dserver_offset(lseg, offset);
 
 	/* Perform an asynchronous write */
-	nfs_initiate_write(ds->ds_clp->cl_rpcclient, data,
+	nfs_initiate_write(ds_clnt, data,
 				    &filelayout_write_call_ops, sync,
 				    RPC_TASK_SOFTCONN);
 	return PNFS_ATTEMPTED;
@@ -1101,16 +1117,19 @@ static int filelayout_initiate_commit(struct nfs_commit_data *data, int how)
 {
 	struct pnfs_layout_segment *lseg = data->lseg;
 	struct nfs4_pnfs_ds *ds;
+	struct rpc_clnt *ds_clnt;
 	u32 idx;
 	struct nfs_fh *fh;
 
 	idx = calc_ds_index_from_commit(lseg, data->ds_commit_index);
 	ds = nfs4_fl_prepare_ds(lseg, idx);
-	if (!ds) {
-		prepare_to_resend_writes(data);
-		filelayout_commit_release(data);
-		return -EAGAIN;
-	}
+	if (!ds)
+		goto out_err;
+
+	ds_clnt = nfs4_find_or_create_ds_client(ds->ds_clp, data->inode);
+	if (IS_ERR(ds_clnt))
+		goto out_err;
+
 	dprintk("%s ino %lu, how %d cl_count %d\n", __func__,
 		data->inode->i_ino, how, atomic_read(&ds->ds_clp->cl_count));
 	data->commit_done_cb = filelayout_commit_done_cb;
@@ -1119,9 +1138,13 @@ static int filelayout_initiate_commit(struct nfs_commit_data *data, int how)
 	fh = select_ds_fh_from_commit(lseg, data->ds_commit_index);
 	if (fh)
 		data->args.fh = fh;
-	return nfs_initiate_commit(ds->ds_clp->cl_rpcclient, data,
+	return nfs_initiate_commit(ds_clnt, data,
 				   &filelayout_commit_call_ops, how,
 				   RPC_TASK_SOFTCONN);
+out_err:
+	prepare_to_resend_writes(data);
+	filelayout_commit_release(data);
+	return -EAGAIN;
 }
 
 static int

fs/nfs/nfs4getroot.c

@@ -9,7 +9,7 @@
 
 #define NFSDBG_FACILITY		NFSDBG_CLIENT
 
-int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh)
+int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh, bool auth_probe)
 {
 	struct nfs_fsinfo fsinfo;
 	int ret = -ENOMEM;
@@ -21,7 +21,7 @@ int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh)
 		goto out;
 
 	/* Start by getting the root filehandle from the server */
-	ret = nfs4_proc_get_rootfh(server, mntfh, &fsinfo);
+	ret = nfs4_proc_get_rootfh(server, mntfh, &fsinfo, auth_probe);
 	if (ret < 0) {
 		dprintk("nfs4_get_rootfh: getroot error = %d\n", -ret);
 		goto out;

fs/nfs/nfs4namespace.c

@@ -11,6 +11,7 @@
 #include <linux/mount.h>
 #include <linux/namei.h>
 #include <linux/nfs_fs.h>
+#include <linux/nfs_mount.h>
 #include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/sunrpc/clnt.h>
@@ -369,21 +370,33 @@ static struct vfsmount *nfs_do_refmount(struct rpc_clnt *client, struct dentry *
 struct vfsmount *nfs4_submount(struct nfs_server *server, struct dentry *dentry,
 			       struct nfs_fh *fh, struct nfs_fattr *fattr)
 {
+	rpc_authflavor_t flavor = server->client->cl_auth->au_flavor;
 	struct dentry *parent = dget_parent(dentry);
+	struct inode *dir = parent->d_inode;
+	struct qstr *name = &dentry->d_name;
 	struct rpc_clnt *client;
 	struct vfsmount *mnt;
 
 	/* Look it up again to get its attributes and sec flavor */
-	client = nfs4_proc_lookup_mountpoint(parent->d_inode, &dentry->d_name, fh, fattr);
+	client = nfs4_proc_lookup_mountpoint(dir, name, fh, fattr);
 	dput(parent);
 	if (IS_ERR(client))
 		return ERR_CAST(client);
 
-	if (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL)
+	if (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) {
 		mnt = nfs_do_refmount(client, dentry);
-	else
-		mnt = nfs_do_submount(dentry, fh, fattr, client->cl_auth->au_flavor);
+		goto out;
+	}
 
+	if (client->cl_auth->au_flavor != flavor)
+		flavor = client->cl_auth->au_flavor;
+	else if (!(server->flags & NFS_MOUNT_SECFLAVOUR)) {
+		rpc_authflavor_t new = nfs4_negotiate_security(dir, name);
+		if ((int)new >= 0)
+			flavor = new;
+	}
+	mnt = nfs_do_submount(dentry, fh, fattr, flavor);
+out:
 	rpc_shutdown_client(client);
 	return mnt;
 }

fs/nfs/nfs4session.c

@@ -23,6 +23,14 @@
 
 #define NFSDBG_FACILITY		NFSDBG_STATE
 
+static void nfs4_init_slot_table(struct nfs4_slot_table *tbl, const char *queue)
+{
+	tbl->highest_used_slotid = NFS4_NO_SLOT;
+	spin_lock_init(&tbl->slot_tbl_lock);
+	rpc_init_priority_wait_queue(&tbl->slot_tbl_waitq, queue);
+	init_completion(&tbl->complete);
+}
+
 /*
  * nfs4_shrink_slot_table - free retired slots from the slot table
  */
@@ -44,6 +52,17 @@ static void nfs4_shrink_slot_table(struct nfs4_slot_table  *tbl, u32 newsize)
 	}
 }
 
+/**
+ * nfs4_slot_tbl_drain_complete - wake waiters when drain is complete
+ * @tbl - controlling slot table
+ *
+ */
+void nfs4_slot_tbl_drain_complete(struct nfs4_slot_table *tbl)
+{
+	if (nfs4_slot_tbl_draining(tbl))
+		complete(&tbl->complete);
+}
+
 /*
  * nfs4_free_slot - free a slot and efficiently update slot table.
  *
@@ -76,7 +95,7 @@ void nfs4_free_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *slot)
 			nfs4_slot_tbl_drain_complete(tbl);
 		}
 	}
-	dprintk("%s: slotid %u highest_used_slotid %d\n", __func__,
+	dprintk("%s: slotid %u highest_used_slotid %u\n", __func__,
 		slotid, tbl->highest_used_slotid);
 }
 
@@ -146,9 +165,9 @@ struct nfs4_slot *nfs4_alloc_slot(struct nfs4_slot_table *tbl)
 	ret->generation = tbl->generation;
 
 out:
-	dprintk("<-- %s used_slots=%04lx highest_used=%d slotid=%d \n",
+	dprintk("<-- %s used_slots=%04lx highest_used=%u slotid=%u\n",
 		__func__, tbl->used_slots[0], tbl->highest_used_slotid,
-		!IS_ERR(ret) ? ret->slot_nr : -1);
+		!IS_ERR(ret) ? ret->slot_nr : NFS4_NO_SLOT);
 	return ret;
 }
 
@@ -191,7 +210,7 @@ static int nfs4_realloc_slot_table(struct nfs4_slot_table *tbl,
 {
 	int ret;
 
-	dprintk("--> %s: max_reqs=%u, tbl->max_slots %d\n", __func__,
+	dprintk("--> %s: max_reqs=%u, tbl->max_slots %u\n", __func__,
 		max_reqs, tbl->max_slots);
 
 	if (max_reqs > NFS4_MAX_SLOT_TABLE)
@@ -205,18 +224,36 @@ static int nfs4_realloc_slot_table(struct nfs4_slot_table *tbl,
 	nfs4_reset_slot_table(tbl, max_reqs - 1, ivalue);
 	spin_unlock(&tbl->slot_tbl_lock);
 
-	dprintk("%s: tbl=%p slots=%p max_slots=%d\n", __func__,
+	dprintk("%s: tbl=%p slots=%p max_slots=%u\n", __func__,
 		tbl, tbl->slots, tbl->max_slots);
 out:
 	dprintk("<-- %s: return %d\n", __func__, ret);
 	return ret;
 }
 
-/* Destroy the slot table */
-static void nfs4_destroy_slot_tables(struct nfs4_session *session)
+/**
+ * nfs4_release_slot_table - release resources attached to a slot table
+ * @tbl: slot table to shut down
+ *
+ */
+void nfs4_release_slot_table(struct nfs4_slot_table *tbl)
+{
+	nfs4_shrink_slot_table(tbl, 0);
+}
+
+/**
+ * nfs4_setup_slot_table - prepare a stand-alone slot table for use
+ * @tbl: slot table to set up
+ * @max_reqs: maximum number of requests allowed
+ * @queue: name to give RPC wait queue
+ *
+ * Returns zero on success, or a negative errno.
+ */
+int nfs4_setup_slot_table(struct nfs4_slot_table *tbl, unsigned int max_reqs,
+		const char *queue)
 {
-	nfs4_shrink_slot_table(&session->fc_slot_table, 0);
-	nfs4_shrink_slot_table(&session->bc_slot_table, 0);
+	nfs4_init_slot_table(tbl, queue);
+	return nfs4_realloc_slot_table(tbl, max_reqs, 0);
 }
 
 static bool nfs41_assign_slot(struct rpc_task *task, void *pslot)
@@ -273,6 +310,8 @@ void nfs41_wake_slot_table(struct nfs4_slot_table *tbl)
 	}
 }
 
+#if defined(CONFIG_NFS_V4_1)
+
 static void nfs41_set_max_slotid_locked(struct nfs4_slot_table *tbl,
 		u32 target_highest_slotid)
 {
@@ -383,6 +422,12 @@ void nfs41_update_target_slotid(struct nfs4_slot_table *tbl,
 	spin_unlock(&tbl->slot_tbl_lock);
 }
 
+static void nfs4_destroy_session_slot_tables(struct nfs4_session *session)
+{
+	nfs4_release_slot_table(&session->fc_slot_table);
+	nfs4_release_slot_table(&session->bc_slot_table);
+}
+
 /*
  * Initialize or reset the forechannel and backchannel tables
  */
@@ -405,31 +450,20 @@ int nfs4_setup_session_slot_tables(struct nfs4_session *ses)
 	if (status && tbl->slots == NULL)
 		/* Fore and back channel share a connection so get
 		 * both slot tables or neither */
-		nfs4_destroy_slot_tables(ses);
+		nfs4_destroy_session_slot_tables(ses);
 	return status;
 }
 
 struct nfs4_session *nfs4_alloc_session(struct nfs_client *clp)
 {
 	struct nfs4_session *session;
-	struct nfs4_slot_table *tbl;
 
 	session = kzalloc(sizeof(struct nfs4_session), GFP_NOFS);
 	if (!session)
 		return NULL;
 
-	tbl = &session->fc_slot_table;
-	tbl->highest_used_slotid = NFS4_NO_SLOT;
-	spin_lock_init(&tbl->slot_tbl_lock);
-	rpc_init_priority_wait_queue(&tbl->slot_tbl_waitq, "ForeChannel Slot table");
-	init_completion(&tbl->complete);
-
-	tbl = &session->bc_slot_table;
-	tbl->highest_used_slotid = NFS4_NO_SLOT;
-	spin_lock_init(&tbl->slot_tbl_lock);
-	rpc_init_wait_queue(&tbl->slot_tbl_waitq, "BackChannel Slot table");
-	init_completion(&tbl->complete);
-
+	nfs4_init_slot_table(&session->fc_slot_table, "ForeChannel Slot table");
+	nfs4_init_slot_table(&session->bc_slot_table, "BackChannel Slot table");
 	session->session_state = 1<<NFS4_SESSION_INITING;
 
 	session->clp = clp;
@@ -441,7 +475,7 @@ void nfs4_destroy_session(struct nfs4_session *session)
 	struct rpc_xprt *xprt;
 	struct rpc_cred *cred;
 
-	cred = nfs4_get_exchange_id_cred(session->clp);
+	cred = nfs4_get_clid_cred(session->clp);
 	nfs4_proc_destroy_session(session, cred);
 	if (cred)
 		put_rpccred(cred);
@@ -452,7 +486,7 @@ void nfs4_destroy_session(struct nfs4_session *session)
 	dprintk("%s Destroy backchannel for xprt %p\n",
 		__func__, xprt);
 	xprt_destroy_backchannel(xprt, NFS41_BC_MIN_CALLBACKS);
-	nfs4_destroy_slot_tables(session);
+	nfs4_destroy_session_slot_tables(session);
 	kfree(session);
 }
 
@@ -513,4 +547,4 @@ int nfs4_init_ds_session(struct nfs_client *clp, unsigned long lease_time)
 }
 EXPORT_SYMBOL_GPL(nfs4_init_ds_session);
 
-
+#endif	/* defined(CONFIG_NFS_V4_1) */

fs/nfs/nfs4session.h

@@ -8,7 +8,7 @@
 #define __LINUX_FS_NFS_NFS4SESSION_H
 
 /* maximum number of slots to use */
-#define NFS4_DEF_SLOT_TABLE_SIZE (16U)
+#define NFS4_DEF_SLOT_TABLE_SIZE (64U)
 #define NFS4_MAX_SLOT_TABLE (1024U)
 #define NFS4_NO_SLOT ((u32)-1)
 
@@ -72,10 +72,22 @@ enum nfs4_session_state {
 	NFS4_SESSION_INITING,
 };
 
-#if defined(CONFIG_NFS_V4_1)
+extern int nfs4_setup_slot_table(struct nfs4_slot_table *tbl,
+		unsigned int max_reqs, const char *queue);
+extern void nfs4_release_slot_table(struct nfs4_slot_table *tbl);
 extern struct nfs4_slot *nfs4_alloc_slot(struct nfs4_slot_table *tbl);
 extern void nfs4_free_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *slot);
+extern void nfs4_slot_tbl_drain_complete(struct nfs4_slot_table *tbl);
+bool nfs41_wake_and_assign_slot(struct nfs4_slot_table *tbl,
+		struct nfs4_slot *slot);
+void nfs41_wake_slot_table(struct nfs4_slot_table *tbl);
+
+static inline bool nfs4_slot_tbl_draining(struct nfs4_slot_table *tbl)
+{
+	return !!test_bit(NFS4_SLOT_TBL_DRAINING, &tbl->slot_tbl_state);
+}
 
+#if defined(CONFIG_NFS_V4_1)
 extern void nfs41_set_target_slotid(struct nfs4_slot_table *tbl,
 		u32 target_highest_slotid);
 extern void nfs41_update_target_slotid(struct nfs4_slot_table *tbl,
@@ -89,17 +101,6 @@ extern void nfs4_destroy_session(struct nfs4_session *session);
 extern int nfs4_init_session(struct nfs_client *clp);
 extern int nfs4_init_ds_session(struct nfs_client *, unsigned long);
 
-extern void nfs4_slot_tbl_drain_complete(struct nfs4_slot_table *tbl);
-
-static inline bool nfs4_slot_tbl_draining(struct nfs4_slot_table *tbl)
-{
-	return !!test_bit(NFS4_SLOT_TBL_DRAINING, &tbl->slot_tbl_state);
-}
-
-bool nfs41_wake_and_assign_slot(struct nfs4_slot_table *tbl,
-		struct nfs4_slot *slot);
-void nfs41_wake_slot_table(struct nfs4_slot_table *tbl);
-
 /*
  * Determine if sessions are in use.
  */
@@ -117,6 +118,16 @@ static inline int nfs4_has_persistent_session(const struct nfs_client *clp)
 	return 0;
 }
 
+#ifdef CONFIG_CRC32
+/*
+ * nfs_session_id_hash - calculate the crc32 hash for the session id
+ * @session - pointer to session
+ */
+#define nfs_session_id_hash(sess_id) \
+	(~crc32_le(0xFFFFFFFF, &(sess_id)->data[0], sizeof((sess_id)->data)))
+#else
+#define nfs_session_id_hash(session) (0)
+#endif
 #else /* defined(CONFIG_NFS_V4_1) */
 
 static inline int nfs4_init_session(struct nfs_client *clp)

fs/nfs/nfs4state.c

@@ -154,6 +154,19 @@ struct rpc_cred *nfs4_get_machine_cred_locked(struct nfs_client *clp)
 	return cred;
 }
 
+static void nfs4_root_machine_cred(struct nfs_client *clp)
+{
+	struct rpc_cred *cred, *new;
+
+	new = rpc_lookup_machine_cred(NULL);
+	spin_lock(&clp->cl_lock);
+	cred = clp->cl_machine_cred;
+	clp->cl_machine_cred = new;
+	spin_unlock(&clp->cl_lock);
+	if (cred != NULL)
+		put_rpccred(cred);
+}
+
 static struct rpc_cred *
 nfs4_get_renew_cred_server_locked(struct nfs_server *server)
 {
@@ -202,32 +215,6 @@ struct rpc_cred *nfs4_get_renew_cred_locked(struct nfs_client *clp)
 	return cred;
 }
 
-#if defined(CONFIG_NFS_V4_1)
-
-static int nfs41_setup_state_renewal(struct nfs_client *clp)
-{
-	int status;
-	struct nfs_fsinfo fsinfo;
-
-	if (!test_bit(NFS_CS_CHECK_LEASE_TIME, &clp->cl_res_state)) {
-		nfs4_schedule_state_renewal(clp);
-		return 0;
-	}
-
-	status = nfs4_proc_get_lease_time(clp, &fsinfo);
-	if (status == 0) {
-		/* Update lease time and schedule renewal */
-		spin_lock(&clp->cl_lock);
-		clp->cl_lease_time = fsinfo.lease_time * HZ;
-		clp->cl_last_renewal = jiffies;
-		spin_unlock(&clp->cl_lock);
-
-		nfs4_schedule_state_renewal(clp);
-	}
-
-	return status;
-}
-
 static void nfs4_end_drain_slot_table(struct nfs4_slot_table *tbl)
 {
 	if (test_and_clear_bit(NFS4_SLOT_TBL_DRAINING, &tbl->slot_tbl_state)) {
@@ -241,20 +228,18 @@ static void nfs4_end_drain_session(struct nfs_client *clp)
 {
 	struct nfs4_session *ses = clp->cl_session;
 
+	if (clp->cl_slot_tbl) {
+		nfs4_end_drain_slot_table(clp->cl_slot_tbl);
+		return;
+	}
+
 	if (ses != NULL) {
 		nfs4_end_drain_slot_table(&ses->bc_slot_table);
 		nfs4_end_drain_slot_table(&ses->fc_slot_table);
 	}
 }
 
-/*
- * Signal state manager thread if session fore channel is drained
- */
-void nfs4_slot_tbl_drain_complete(struct nfs4_slot_table *tbl)
-{
-	if (nfs4_slot_tbl_draining(tbl))
-		complete(&tbl->complete);
-}
+#if defined(CONFIG_NFS_V4_1)
 
 static int nfs4_drain_slot_tbl(struct nfs4_slot_table *tbl)
 {
@@ -274,6 +259,9 @@ static int nfs4_begin_drain_session(struct nfs_client *clp)
 	struct nfs4_session *ses = clp->cl_session;
 	int ret = 0;
 
+	if (clp->cl_slot_tbl)
+		return nfs4_drain_slot_tbl(clp->cl_slot_tbl);
+
 	/* back channel */
 	ret = nfs4_drain_slot_tbl(&ses->bc_slot_table);
 	if (ret)
@@ -282,6 +270,30 @@ static int nfs4_begin_drain_session(struct nfs_client *clp)
 	return nfs4_drain_slot_tbl(&ses->fc_slot_table);
 }
 
+static int nfs41_setup_state_renewal(struct nfs_client *clp)
+{
+	int status;
+	struct nfs_fsinfo fsinfo;
+
+	if (!test_bit(NFS_CS_CHECK_LEASE_TIME, &clp->cl_res_state)) {
+		nfs4_schedule_state_renewal(clp);
+		return 0;
+	}
+
+	status = nfs4_proc_get_lease_time(clp, &fsinfo);
+	if (status == 0) {
+		/* Update lease time and schedule renewal */
+		spin_lock(&clp->cl_lock);
+		clp->cl_lease_time = fsinfo.lease_time * HZ;
+		clp->cl_last_renewal = jiffies;
+		spin_unlock(&clp->cl_lock);
+
+		nfs4_schedule_state_renewal(clp);
+	}
+
+	return status;
+}
+
 static void nfs41_finish_session_reset(struct nfs_client *clp)
 {
 	clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
@@ -339,62 +351,21 @@ int nfs41_discover_server_trunking(struct nfs_client *clp,
 	return nfs41_walk_client_list(clp, result, cred);
 }
 
-struct rpc_cred *nfs4_get_exchange_id_cred(struct nfs_client *clp)
-{
-	struct rpc_cred *cred;
-
-	spin_lock(&clp->cl_lock);
-	cred = nfs4_get_machine_cred_locked(clp);
-	spin_unlock(&clp->cl_lock);
-	return cred;
-}
-
 #endif /* CONFIG_NFS_V4_1 */
 
-static struct rpc_cred *
-nfs4_get_setclientid_cred_server(struct nfs_server *server)
-{
-	struct nfs_client *clp = server->nfs_client;
-	struct rpc_cred *cred = NULL;
-	struct nfs4_state_owner *sp;
-	struct rb_node *pos;
-
-	spin_lock(&clp->cl_lock);
-	pos = rb_first(&server->state_owners);
-	if (pos != NULL) {
-		sp = rb_entry(pos, struct nfs4_state_owner, so_server_node);
-		cred = get_rpccred(sp->so_cred);
-	}
-	spin_unlock(&clp->cl_lock);
-	return cred;
-}
-
 /**
- * nfs4_get_setclientid_cred - Acquire credential for a setclientid operation
+ * nfs4_get_clid_cred - Acquire credential for a setclientid operation
  * @clp: client state handle
  *
  * Returns an rpc_cred with reference count bumped, or NULL.
  */
-struct rpc_cred *nfs4_get_setclientid_cred(struct nfs_client *clp)
+struct rpc_cred *nfs4_get_clid_cred(struct nfs_client *clp)
 {
-	struct nfs_server *server;
 	struct rpc_cred *cred;
 
 	spin_lock(&clp->cl_lock);
 	cred = nfs4_get_machine_cred_locked(clp);
 	spin_unlock(&clp->cl_lock);
-	if (cred != NULL)
-		goto out;
-
-	rcu_read_lock();
-	list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
-		cred = nfs4_get_setclientid_cred_server(server);
-		if (cred != NULL)
-			break;
-	}
-	rcu_read_unlock();
-
-out:
 	return cred;
 }
 
@@ -998,7 +969,9 @@ static int nfs4_copy_lock_stateid(nfs4_stateid *dst,
 	fl_pid = lockowner->l_pid;
 	spin_lock(&state->state_lock);
 	lsp = __nfs4_find_lock_state(state, fl_owner, fl_pid, NFS4_ANY_LOCK_TYPE);
-	if (lsp != NULL && test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags) != 0) {
+	if (lsp && test_bit(NFS_LOCK_LOST, &lsp->ls_flags))
+		ret = -EIO;
+	else if (lsp != NULL && test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags) != 0) {
 		nfs4_stateid_copy(dst, &lsp->ls_stateid);
 		ret = 0;
 		smp_rmb();
@@ -1038,11 +1011,17 @@ static int nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state)
 int nfs4_select_rw_stateid(nfs4_stateid *dst, struct nfs4_state *state,
 		fmode_t fmode, const struct nfs_lockowner *lockowner)
 {
-	int ret = 0;
+	int ret = nfs4_copy_lock_stateid(dst, state, lockowner);
+	if (ret == -EIO)
+		/* A lost lock - don't even consider delegations */
+		goto out;
 	if (nfs4_copy_delegation_stateid(dst, state->inode, fmode))
 		goto out;
-	ret = nfs4_copy_lock_stateid(dst, state, lockowner);
 	if (ret != -ENOENT)
+		/* nfs4_copy_delegation_stateid() didn't over-write
+		 * dst, so it still has the lock stateid which we now
+		 * choose to use.
+		 */
 		goto out;
 	ret = nfs4_copy_open_stateid(dst, state);
 out:
@@ -1443,6 +1422,7 @@ static int nfs4_reclaim_open_state(struct nfs4_state_owner *sp, const struct nfs
 		if (status >= 0) {
 			status = nfs4_reclaim_locks(state, ops);
 			if (status >= 0) {
+				if (test_bit(NFS_DELEGATED_STATE, &state->flags) != 0) {
 					spin_lock(&state->state_lock);
 					list_for_each_entry(lock, &state->lock_states, ls_locks) {
 						if (!test_bit(NFS_LOCK_INITIALIZED, &lock->ls_flags))
@@ -1451,6 +1431,7 @@ static int nfs4_reclaim_open_state(struct nfs4_state_owner *sp, const struct nfs
 									    "failed!\n", __func__);
 					}
 					spin_unlock(&state->state_lock);
+				}
 				nfs4_put_open_state(state);
 				spin_lock(&sp->so_lock);
 				goto restart;
@@ -1618,7 +1599,7 @@ static void nfs4_state_end_reclaim_reboot(struct nfs_client *clp)
 	if (!nfs4_state_clear_reclaim_reboot(clp))
 		return;
 	ops = clp->cl_mvops->reboot_recovery_ops;
-	cred = ops->get_clid_cred(clp);
+	cred = nfs4_get_clid_cred(clp);
 	nfs4_reclaim_complete(clp, ops, cred);
 	put_rpccred(cred);
 }
@@ -1732,7 +1713,7 @@ static int nfs4_check_lease(struct nfs_client *clp)
 	cred = ops->get_state_renewal_cred_locked(clp);
 	spin_unlock(&clp->cl_lock);
 	if (cred == NULL) {
-		cred = nfs4_get_setclientid_cred(clp);
+		cred = nfs4_get_clid_cred(clp);
 		status = -ENOKEY;
 		if (cred == NULL)
 			goto out;
@@ -1804,7 +1785,7 @@ static int nfs4_establish_lease(struct nfs_client *clp)
 		clp->cl_mvops->reboot_recovery_ops;
 	int status;
 
-	cred = ops->get_clid_cred(clp);
+	cred = nfs4_get_clid_cred(clp);
 	if (cred == NULL)
 		return -ENOENT;
 	status = ops->establish_clid(clp, cred);
@@ -1878,7 +1859,7 @@ int nfs4_discover_server_trunking(struct nfs_client *clp,
 	mutex_lock(&nfs_clid_init_mutex);
 again:
 	status  = -ENOENT;
-	cred = ops->get_clid_cred(clp);
+	cred = nfs4_get_clid_cred(clp);
 	if (cred == NULL)
 		goto out_unlock;
 
@@ -1896,7 +1877,11 @@ int nfs4_discover_server_trunking(struct nfs_client *clp,
 			__func__, status);
 		goto again;
 	case -EACCES:
-		if (i++)
+		if (i++ == 0) {
+			nfs4_root_machine_cred(clp);
+			goto again;
+		}
+		if (i > 2)
 			break;
 	case -NFS4ERR_CLID_INUSE:
 	case -NFS4ERR_WRONGSEC:
@@ -2052,7 +2037,7 @@ static int nfs4_reset_session(struct nfs_client *clp)
 	if (!nfs4_has_session(clp))
 		return 0;
 	nfs4_begin_drain_session(clp);
-	cred = nfs4_get_exchange_id_cred(clp);
+	cred = nfs4_get_clid_cred(clp);
 	status = nfs4_proc_destroy_session(clp->cl_session, cred);
 	switch (status) {
 	case 0:
@@ -2095,7 +2080,7 @@ static int nfs4_bind_conn_to_session(struct nfs_client *clp)
 	if (!nfs4_has_session(clp))
 		return 0;
 	nfs4_begin_drain_session(clp);
-	cred = nfs4_get_exchange_id_cred(clp);
+	cred = nfs4_get_clid_cred(clp);
 	ret = nfs4_proc_bind_conn_to_session(clp, cred);
 	if (cred)
 		put_rpccred(cred);
@@ -2116,7 +2101,6 @@ static int nfs4_bind_conn_to_session(struct nfs_client *clp)
 }
 #else /* CONFIG_NFS_V4_1 */
 static int nfs4_reset_session(struct nfs_client *clp) { return 0; }
-static int nfs4_end_drain_session(struct nfs_client *clp) { return 0; }
 
 static int nfs4_bind_conn_to_session(struct nfs_client *clp)
 {

fs/nfs/nfs4super.c

@@ -253,8 +253,6 @@ struct dentry *nfs4_try_mount(int flags, const char *dev_name,
 
 	dfprintk(MOUNT, "--> nfs4_try_mount()\n");
 
-	if (data->auth_flavors[0] == RPC_AUTH_MAXFLAVOR)
-		data->auth_flavors[0] = RPC_AUTH_UNIX;
 	export_path = data->nfs_server.export_path;
 	data->nfs_server.export_path = "/";
 	root_mnt = nfs_do_root_mount(&nfs4_remote_fs_type, flags, mount_info,

fs/nfs/nfs4trace.c

+/*
+ * Copyright (c) 2013 Trond Myklebust <Trond.Myklebust@netapp.com>
+ */
+#include <linux/nfs_fs.h>
+#include "nfs4_fs.h"
+#include "internal.h"
+#include "nfs4session.h"
+#include "callback.h"
+
+#define CREATE_TRACE_POINTS
+#include "nfs4trace.h"
+
+#ifdef CONFIG_NFS_V4_1
+EXPORT_TRACEPOINT_SYMBOL_GPL(nfs4_pnfs_read);
+EXPORT_TRACEPOINT_SYMBOL_GPL(nfs4_pnfs_write);
+EXPORT_TRACEPOINT_SYMBOL_GPL(nfs4_pnfs_commit_ds);
+#endif

fs/nfs/nfstrace.c

+/*
+ * Copyright (c) 2013 Trond Myklebust <Trond.Myklebust@netapp.com>
+ */
+#include <linux/nfs_fs.h>
+#include <linux/namei.h>
+#include "internal.h"
+
+#define CREATE_TRACE_POINTS
+#include "nfstrace.h"

fs/nfs/pagelist.c

@@ -328,6 +328,19 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc,
 }
 EXPORT_SYMBOL_GPL(nfs_pageio_init);
 
+static bool nfs_match_open_context(const struct nfs_open_context *ctx1,
+		const struct nfs_open_context *ctx2)
+{
+	return ctx1->cred == ctx2->cred && ctx1->state == ctx2->state;
+}
+
+static bool nfs_match_lock_context(const struct nfs_lock_context *l1,
+		const struct nfs_lock_context *l2)
+{
+	return l1->lockowner.l_owner == l2->lockowner.l_owner
+		&& l1->lockowner.l_pid == l2->lockowner.l_pid;
+}
+
 /**
  * nfs_can_coalesce_requests - test two requests for compatibility
  * @prev: pointer to nfs_page
@@ -343,13 +356,10 @@ static bool nfs_can_coalesce_requests(struct nfs_page *prev,
 				      struct nfs_page *req,
 				      struct nfs_pageio_descriptor *pgio)
 {
-	if (req->wb_context->cred != prev->wb_context->cred)
-		return false;
-	if (req->wb_lock_context->lockowner.l_owner != prev->wb_lock_context->lockowner.l_owner)
-		return false;
-	if (req->wb_lock_context->lockowner.l_pid != prev->wb_lock_context->lockowner.l_pid)
+	if (!nfs_match_open_context(req->wb_context, prev->wb_context))
 		return false;
-	if (req->wb_context->state != prev->wb_context->state)
+	if (req->wb_context->dentry->d_inode->i_flock != NULL &&
+	    !nfs_match_lock_context(req->wb_lock_context, prev->wb_lock_context))
 		return false;
 	if (req->wb_pgbase != 0)
 		return false;

fs/nfs/read.c

@@ -513,9 +513,10 @@ static void nfs_readpage_release_common(void *calldata)
 void nfs_read_prepare(struct rpc_task *task, void *calldata)
 {
 	struct nfs_read_data *data = calldata;
-	NFS_PROTO(data->header->inode)->read_rpc_prepare(task, data);
-	if (unlikely(test_bit(NFS_CONTEXT_BAD, &data->args.context->flags)))
-		rpc_exit(task, -EIO);
+	int err;
+	err = NFS_PROTO(data->header->inode)->read_rpc_prepare(task, data);
+	if (err)
+		rpc_exit(task, err);
 }
 
 static const struct rpc_call_ops nfs_read_common_ops = {