Merge branch 'for-2.6.30' of git://linux-nfs.org/~bfields/linux

* 'for-2.6.30' of git://linux-nfs.org/~bfields/linux: (81 commits)
  nfsd41: define nfsd4_set_statp as noop for !CONFIG_NFSD_V4
  nfsd41: define NFSD_DRC_SIZE_SHIFT in set_max_drc
  nfsd41: Documentation/filesystems/nfs41-server.txt
  nfsd41: CREATE_EXCLUSIVE4_1
  nfsd41: SUPPATTR_EXCLCREAT attribute
  nfsd41: support for 3-word long attribute bitmask
  nfsd: dynamically skip encoded fattr bitmap in _nfsd4_verify
  nfsd41: pass writable attrs mask to nfsd4_decode_fattr
  nfsd41: provide support for minor version 1 at rpc level
  nfsd41: control nfsv4.1 svc via /proc/fs/nfsd/versions
  nfsd41: add OPEN4_SHARE_ACCESS_WANT nfs4_stateid bmap
  nfsd41: access_valid
  nfsd41: clientid handling
  nfsd41: check encode size for sessions maxresponse cached
  nfsd41: stateid handling
  nfsd: pass nfsd4_compound_state* to nfs4_preprocess_{state,seq}id_op
  nfsd41: destroy_session operation
  nfsd41: non-page DRC for solo sequence responses
  nfsd41: Add a create session replay cache
  nfsd41: create_session operation
  ...

11 files changed, 1999 insertions, 374 deletions

diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index 44d7d04dab9..503b9da159a 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -1,6 +1,7 @@
 config NFSD
 	tristate "NFS server support"
 	depends on INET
+	depends on FILE_LOCKING
 	select LOCKD
 	select SUNRPC
 	select EXPORTFS
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index 9dbd2eb9128..7c9fe838f03 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -18,6 +18,7 @@
 #include <linux/unistd.h>
 #include <linux/slab.h>
 #include <linux/major.h>
+#include <linux/magic.h>
 
 #include <linux/sunrpc/svc.h>
 #include <linux/nfsd/nfsd.h>
@@ -202,6 +203,7 @@ nfsd3_proc_write(struct svc_rqst *rqstp, struct nfsd3_writeargs *argp,
 					 struct nfsd3_writeres  *resp)
 {
 	__be32	nfserr;
+	unsigned long cnt = argp->len;
 
 	dprintk("nfsd: WRITE(3)    %s %d bytes at %ld%s\n",
 				SVCFH_fmt(&argp->fh),
@@ -214,9 +216,9 @@ nfsd3_proc_write(struct svc_rqst *rqstp, struct nfsd3_writeargs *argp,
 	nfserr = nfsd_write(rqstp, &resp->fh, NULL,
 				   argp->offset,
 				   rqstp->rq_vec, argp->vlen,
-				   argp->len,
+				   &cnt,
 				   &resp->committed);
-	resp->count = argp->count;
+	resp->count = cnt;
 	RETURN_STATUS(nfserr);
 }
 
@@ -569,7 +571,7 @@ nfsd3_proc_fsinfo(struct svc_rqst * rqstp, struct nfsd_fhandle    *argp,
 		struct super_block *sb = argp->fh.fh_dentry->d_inode->i_sb;
 
 		/* Note that we don't care for remote fs's here */
-		if (sb->s_magic == 0x4d44 /* MSDOS_SUPER_MAGIC */) {
+		if (sb->s_magic == MSDOS_SUPER_MAGIC) {
 			resp->f_properties = NFS3_FSF_BILLYBOY;
 		}
 		resp->f_maxfilesize = sb->s_maxbytes;
@@ -610,7 +612,7 @@ nfsd3_proc_pathconf(struct svc_rqst * rqstp, struct nfsd_fhandle      *argp,
 			resp->p_link_max = EXT2_LINK_MAX;
 			resp->p_name_max = EXT2_NAME_LEN;
 			break;
-		case 0x4d44:	/* MSDOS_SUPER_MAGIC */
+		case MSDOS_SUPER_MAGIC:
 			resp->p_case_insensitive = 1;
 			resp->p_case_preserving  = 0;
 			break;
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index c464181b599..290289bd44f 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -218,7 +218,7 @@ static int
 encode_cb_recall(struct xdr_stream *xdr, struct nfs4_cb_recall *cb_rec)
 {
 	__be32 *p;
-	int len = cb_rec->cbr_fhlen;
+	int len = cb_rec->cbr_fh.fh_size;
 
 	RESERVE_SPACE(12+sizeof(cb_rec->cbr_stateid) + len);
 	WRITE32(OP_CB_RECALL);
@@ -226,7 +226,7 @@ encode_cb_recall(struct xdr_stream *xdr, struct nfs4_cb_recall *cb_rec)
 	WRITEMEM(&cb_rec->cbr_stateid.si_opaque, sizeof(stateid_opaque_t));
 	WRITE32(cb_rec->cbr_trunc);
 	WRITE32(len);
-	WRITEMEM(cb_rec->cbr_fhval, len);
+	WRITEMEM(&cb_rec->cbr_fh.fh_base, len);
 	return 0;
 }
 
@@ -361,9 +361,8 @@ static struct rpc_program cb_program = {
 /* Reference counting, callback cleanup, etc., all look racy as heck.
  * And why is cb_set an atomic? */
 
-static int do_probe_callback(void *data)
+static struct rpc_clnt *setup_callback_client(struct nfs4_client *clp)
 {
-	struct nfs4_client *clp = data;
 	struct sockaddr_in	addr;
 	struct nfs4_callback    *cb = &clp->cl_callback;
 	struct rpc_timeout	timeparms = {
@@ -384,17 +383,10 @@ static int do_probe_callback(void *data)
 		.flags		= (RPC_CLNT_CREATE_NOPING | RPC_CLNT_CREATE_QUIET),
 		.client_name    = clp->cl_principal,
 	};
-	struct rpc_message msg = {
-		.rpc_proc       = &nfs4_cb_procedures[NFSPROC4_CLNT_CB_NULL],
-		.rpc_argp       = clp,
-	};
 	struct rpc_clnt *client;
-	int status;
 
-	if (!clp->cl_principal && (clp->cl_flavor >= RPC_AUTH_GSS_KRB5)) {
-		status = nfserr_cb_path_down;
-		goto out_err;
-	}
+	if (!clp->cl_principal && (clp->cl_flavor >= RPC_AUTH_GSS_KRB5))
+		return ERR_PTR(-EINVAL);
 
 	/* Initialize address */
 	memset(&addr, 0, sizeof(addr));
@@ -404,9 +396,29 @@ static int do_probe_callback(void *data)
 
 	/* Create RPC client */
 	client = rpc_create(&args);
+	if (IS_ERR(client))
+		dprintk("NFSD: couldn't create callback client: %ld\n",
+			PTR_ERR(client));
+	return client;
+
+}
+
+static int do_probe_callback(void *data)
+{
+	struct nfs4_client *clp = data;
+	struct nfs4_callback    *cb = &clp->cl_callback;
+	struct rpc_message msg = {
+		.rpc_proc       = &nfs4_cb_procedures[NFSPROC4_CLNT_CB_NULL],
+		.rpc_argp       = clp,
+	};
+	struct rpc_clnt *client;
+	int status;
+
+	client = setup_callback_client(clp);
 	if (IS_ERR(client)) {
-		dprintk("NFSD: couldn't create callback client\n");
 		status = PTR_ERR(client);
+		dprintk("NFSD: couldn't create callback client: %d\n",
+								status);
 		goto out_err;
 	}
 
@@ -422,10 +434,10 @@ static int do_probe_callback(void *data)
 out_release_client:
 	rpc_shutdown_client(client);
 out_err:
-	dprintk("NFSD: warning: no callback path to client %.*s\n",
-		(int)clp->cl_name.len, clp->cl_name.data);
+	dprintk("NFSD: warning: no callback path to client %.*s: error %d\n",
+		(int)clp->cl_name.len, clp->cl_name.data, status);
 	put_nfs4_client(clp);
-	return status;
+	return 0;
 }
 
 /*
@@ -451,7 +463,6 @@ nfsd4_probe_callback(struct nfs4_client *clp)
 
 /*
  * called with dp->dl_count inc'ed.
- * nfs4_lock_state() may or may not have been called.
  */
 void
 nfsd4_cb_recall(struct nfs4_delegation *dp)
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 9fa60a3ad48..b2883e9c638 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -93,6 +93,21 @@ do_open_lookup(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_o
 	open->op_truncate = 0;
 
 	if (open->op_create) {
+		/* FIXME: check session persistence and pnfs flags.
+		 * The nfsv4.1 spec requires the following semantics:
+		 *
+		 * Persistent   | pNFS   | Server REQUIRED | Client Allowed
+		 * Reply Cache  | server |                 |
+		 * -------------+--------+-----------------+--------------------
+		 * no           | no     | EXCLUSIVE4_1    | EXCLUSIVE4_1
+		 *              |        |                 | (SHOULD)
+		 *              |        | and EXCLUSIVE4  | or EXCLUSIVE4
+		 *              |        |                 | (SHOULD NOT)
+		 * no           | yes    | EXCLUSIVE4_1    | EXCLUSIVE4_1
+		 * yes          | no     | GUARDED4        | GUARDED4
+		 * yes          | yes    | GUARDED4        | GUARDED4
+		 */
+
 		/*
 		 * Note: create modes (UNCHECKED,GUARDED...) are the same
 		 * in NFSv4 as in v3.
@@ -103,11 +118,13 @@ do_open_lookup(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_o
 					(u32 *)open->op_verf.data,
 					&open->op_truncate, &created);
 
-		/* If we ever decide to use different attrs to store the
-		 * verifier in nfsd_create_v3, then we'll need to change this
+		/*
+		 * Following rfc 3530 14.2.16, use the returned bitmask
+		 * to indicate which attributes we used to store the
+		 * verifier:
 		 */
 		if (open->op_createmode == NFS4_CREATE_EXCLUSIVE && status == 0)
-			open->op_bmval[1] |= (FATTR4_WORD1_TIME_ACCESS |
+			open->op_bmval[1] = (FATTR4_WORD1_TIME_ACCESS |
 						FATTR4_WORD1_TIME_MODIFY);
 	} else {
 		status = nfsd_lookup(rqstp, current_fh,
@@ -118,13 +135,11 @@ do_open_lookup(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_o
 		goto out;
 
 	set_change_info(&open->op_cinfo, current_fh);
-
-	/* set reply cache */
 	fh_dup2(current_fh, &resfh);
-	open->op_stateowner->so_replay.rp_openfh_len = resfh.fh_handle.fh_size;
-	memcpy(open->op_stateowner->so_replay.rp_openfh,
-			&resfh.fh_handle.fh_base, resfh.fh_handle.fh_size);
 
+	/* set reply cache */
+	fh_copy_shallow(&open->op_stateowner->so_replay.rp_openfh,
+			&resfh.fh_handle);
 	if (!created)
 		status = do_open_permission(rqstp, current_fh, open,
 					    NFSD_MAY_NOP);
@@ -150,10 +165,8 @@ do_open_fhandle(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_
 	memset(&open->op_cinfo, 0, sizeof(struct nfsd4_change_info));
 
 	/* set replay cache */
-	open->op_stateowner->so_replay.rp_openfh_len = current_fh->fh_handle.fh_size;
-	memcpy(open->op_stateowner->so_replay.rp_openfh,
-		&current_fh->fh_handle.fh_base,
-		current_fh->fh_handle.fh_size);
+	fh_copy_shallow(&open->op_stateowner->so_replay.rp_openfh,
+			&current_fh->fh_handle);
 
 	open->op_truncate = (open->op_iattr.ia_valid & ATTR_SIZE) &&
 		(open->op_iattr.ia_size == 0);
@@ -164,12 +177,23 @@ do_open_fhandle(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_
 	return status;
 }
 
+static void
+copy_clientid(clientid_t *clid, struct nfsd4_session *session)
+{
+	struct nfsd4_sessionid *sid =
+			(struct nfsd4_sessionid *)session->se_sessionid.data;
+
+	clid->cl_boot = sid->clientid.cl_boot;
+	clid->cl_id = sid->clientid.cl_id;
+}
 
 static __be32
 nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	   struct nfsd4_open *open)
 {
 	__be32 status;
+	struct nfsd4_compoundres *resp;
+
 	dprintk("NFSD: nfsd4_open filename %.*s op_stateowner %p\n",
 		(int)open->op_fname.len, open->op_fname.data,
 		open->op_stateowner);
@@ -178,16 +202,19 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	if (open->op_create && open->op_claim_type != NFS4_OPEN_CLAIM_NULL)
 		return nfserr_inval;
 
+	if (nfsd4_has_session(cstate))
+		copy_clientid(&open->op_clientid, cstate->session);
+
 	nfs4_lock_state();
 
 	/* check seqid for replay. set nfs4_owner */
-	status = nfsd4_process_open1(open);
+	resp = rqstp->rq_resp;
+	status = nfsd4_process_open1(&resp->cstate, open);
 	if (status == nfserr_replay_me) {
 		struct nfs4_replay *rp = &open->op_stateowner->so_replay;
 		fh_put(&cstate->current_fh);
-		cstate->current_fh.fh_handle.fh_size = rp->rp_openfh_len;
-		memcpy(&cstate->current_fh.fh_handle.fh_base, rp->rp_openfh,
-				rp->rp_openfh_len);
+		fh_copy_shallow(&cstate->current_fh.fh_handle,
+				&rp->rp_openfh);
 		status = fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_NOP);
 		if (status)
 			dprintk("nfsd4_open: replay failed"
@@ -209,10 +236,6 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 	switch (open->op_claim_type) {
 		case NFS4_OPEN_CLAIM_DELEGATE_CUR:
-			status = nfserr_inval;
-			if (open->op_create)
-				goto out;
-			/* fall through */
 		case NFS4_OPEN_CLAIM_NULL:
 			/*
 			 * (1) set CURRENT_FH to the file being opened,
@@ -455,8 +478,9 @@ nfsd4_getattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	if (getattr->ga_bmval[1] & NFSD_WRITEONLY_ATTRS_WORD1)
 		return nfserr_inval;
 
-	getattr->ga_bmval[0] &= NFSD_SUPPORTED_ATTRS_WORD0;
-	getattr->ga_bmval[1] &= NFSD_SUPPORTED_ATTRS_WORD1;
+	getattr->ga_bmval[0] &= nfsd_suppattrs0(cstate->minorversion);
+	getattr->ga_bmval[1] &= nfsd_suppattrs1(cstate->minorversion);
+	getattr->ga_bmval[2] &= nfsd_suppattrs2(cstate->minorversion);
 
 	getattr->ga_fhp = &cstate->current_fh;
 	return nfs_ok;
@@ -520,9 +544,8 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 	nfs4_lock_state();
 	/* check stateid */
-	if ((status = nfs4_preprocess_stateid_op(&cstate->current_fh,
-				&read->rd_stateid,
-				CHECK_FH | RD_STATE, &read->rd_filp))) {
+	if ((status = nfs4_preprocess_stateid_op(cstate, &read->rd_stateid,
+						 RD_STATE, &read->rd_filp))) {
 		dprintk("NFSD: nfsd4_read: couldn't process stateid!\n");
 		goto out;
 	}
@@ -548,8 +571,9 @@ nfsd4_readdir(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	if (readdir->rd_bmval[1] & NFSD_WRITEONLY_ATTRS_WORD1)
 		return nfserr_inval;
 
-	readdir->rd_bmval[0] &= NFSD_SUPPORTED_ATTRS_WORD0;
-	readdir->rd_bmval[1] &= NFSD_SUPPORTED_ATTRS_WORD1;
+	readdir->rd_bmval[0] &= nfsd_suppattrs0(cstate->minorversion);
+	readdir->rd_bmval[1] &= nfsd_suppattrs1(cstate->minorversion);
+	readdir->rd_bmval[2] &= nfsd_suppattrs2(cstate->minorversion);
 
 	if ((cookie > ~(u32)0) || (cookie == 1) || (cookie == 2) ||
 	    (cookie == 0 && memcmp(readdir->rd_verf.data, zeroverf.data, NFS4_VERIFIER_SIZE)))
@@ -653,8 +677,8 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 	if (setattr->sa_iattr.ia_valid & ATTR_SIZE) {
 		nfs4_lock_state();
-		status = nfs4_preprocess_stateid_op(&cstate->current_fh,
-			&setattr->sa_stateid, CHECK_FH | WR_STATE, NULL);
+		status = nfs4_preprocess_stateid_op(cstate,
+			&setattr->sa_stateid, WR_STATE, NULL);
 		nfs4_unlock_state();
 		if (status) {
 			dprintk("NFSD: nfsd4_setattr: couldn't process stateid!\n");
@@ -685,6 +709,7 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	struct file *filp = NULL;
 	u32 *p;
 	__be32 status = nfs_ok;
+	unsigned long cnt;
 
 	/* no need to check permission - this will be done in nfsd_write() */
 
@@ -692,8 +717,7 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		return nfserr_inval;
 
 	nfs4_lock_state();
-	status = nfs4_preprocess_stateid_op(&cstate->current_fh, stateid,
-					CHECK_FH | WR_STATE, &filp);
+	status = nfs4_preprocess_stateid_op(cstate, stateid, WR_STATE, &filp);
 	if (filp)
 		get_file(filp);
 	nfs4_unlock_state();
@@ -703,7 +727,7 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		return status;
 	}
 
-	write->wr_bytes_written = write->wr_buflen;
+	cnt = write->wr_buflen;
 	write->wr_how_written = write->wr_stable_how;
 	p = (u32 *)write->wr_verifier.data;
 	*p++ = nfssvc_boot.tv_sec;
@@ -711,10 +735,12 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 	status =  nfsd_write(rqstp, &cstate->current_fh, filp,
 			     write->wr_offset, rqstp->rq_vec, write->wr_vlen,
-			     write->wr_buflen, &write->wr_how_written);
+			     &cnt, &write->wr_how_written);
 	if (filp)
 		fput(filp);
 
+	write->wr_bytes_written = cnt;
+
 	if (status == nfserr_symlink)
 		status = nfserr_inval;
 	return status;
@@ -737,8 +763,9 @@ _nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	if (status)
 		return status;
 
-	if ((verify->ve_bmval[0] & ~NFSD_SUPPORTED_ATTRS_WORD0)
-	    || (verify->ve_bmval[1] & ~NFSD_SUPPORTED_ATTRS_WORD1))
+	if ((verify->ve_bmval[0] & ~nfsd_suppattrs0(cstate->minorversion))
+	    || (verify->ve_bmval[1] & ~nfsd_suppattrs1(cstate->minorversion))
+	    || (verify->ve_bmval[2] & ~nfsd_suppattrs2(cstate->minorversion)))
 		return nfserr_attrnotsupp;
 	if ((verify->ve_bmval[0] & FATTR4_WORD0_RDATTR_ERROR)
 	    || (verify->ve_bmval[1] & NFSD_WRITEONLY_ATTRS_WORD1))
@@ -766,7 +793,8 @@ _nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	if (status)
 		goto out_kfree;
 
-	p = buf + 3;
+	/* skip bitmap */
+	p = buf + 1 + ntohl(buf[0]);
 	status = nfserr_not_same;
 	if (ntohl(*p++) != verify->ve_attrlen)
 		goto out_kfree;
@@ -813,39 +841,17 @@ static inline void nfsd4_increment_op_stats(u32 opnum)
 		nfsdstats.nfs4_opcount[opnum]++;
 }
 
-static void cstate_free(struct nfsd4_compound_state *cstate)
-{
-	if (cstate == NULL)
-		return;
-	fh_put(&cstate->current_fh);
-	fh_put(&cstate->save_fh);
-	BUG_ON(cstate->replay_owner);
-	kfree(cstate);
-}
-
-static struct nfsd4_compound_state *cstate_alloc(void)
-{
-	struct nfsd4_compound_state *cstate;
-
-	cstate = kmalloc(sizeof(struct nfsd4_compound_state), GFP_KERNEL);
-	if (cstate == NULL)
-		return NULL;
-	fh_init(&cstate->current_fh, NFS4_FHSIZE);
-	fh_init(&cstate->save_fh, NFS4_FHSIZE);
-	cstate->replay_owner = NULL;
-	return cstate;
-}
-
 typedef __be32(*nfsd4op_func)(struct svc_rqst *, struct nfsd4_compound_state *,
 			      void *);
+enum nfsd4_op_flags {
+	ALLOWED_WITHOUT_FH = 1 << 0,	/* No current filehandle required */
+	ALLOWED_ON_ABSENT_FS = 2 << 0,	/* ops processed on absent fs */
+	ALLOWED_AS_FIRST_OP = 3 << 0,	/* ops reqired first in compound */
+};
 
 struct nfsd4_operation {
 	nfsd4op_func op_func;
 	u32 op_flags;
-/* Most ops require a valid current filehandle; a few don't: */
-#define ALLOWED_WITHOUT_FH 1
-/* GETATTR and ops not listed as returning NFS4ERR_MOVED: */
-#define ALLOWED_ON_ABSENT_FS 2
 	char *op_name;
 };
 
@@ -854,6 +860,51 @@ static struct nfsd4_operation nfsd4_ops[];
 static const char *nfsd4_op_name(unsigned opnum);
 
 /*
+ * This is a replay of a compound for which no cache entry pages
+ * were used. Encode the sequence operation, and if cachethis is FALSE
+ * encode the uncache rep error on the next operation.
+ */
+static __be32
+nfsd4_enc_uncached_replay(struct nfsd4_compoundargs *args,
+			 struct nfsd4_compoundres *resp)
+{
+	struct nfsd4_op *op;
+
+	dprintk("--> %s resp->opcnt %d ce_cachethis %u \n", __func__,
+		resp->opcnt, resp->cstate.slot->sl_cache_entry.ce_cachethis);
+
+	/* Encode the replayed sequence operation */
+	BUG_ON(resp->opcnt != 1);
+	op = &args->ops[resp->opcnt - 1];
+	nfsd4_encode_operation(resp, op);
+
+	/*return nfserr_retry_uncached_rep in next operation. */
+	if (resp->cstate.slot->sl_cache_entry.ce_cachethis == 0) {
+		op = &args->ops[resp->opcnt++];
+		op->status = nfserr_retry_uncached_rep;
+		nfsd4_encode_operation(resp, op);
+	}
+	return op->status;
+}
+
+/*
+ * Enforce NFSv4.1 COMPOUND ordering rules.
+ *
+ * TODO:
+ * - enforce NFS4ERR_NOT_ONLY_OP,
+ * - DESTROY_SESSION MUST be the final operation in the COMPOUND request.
+ */
+static bool nfs41_op_ordering_ok(struct nfsd4_compoundargs *args)
+{
+	if (args->minorversion && args->opcnt > 0) {
+		struct nfsd4_op *op = &args->ops[0];
+		return (op->status == nfserr_op_illegal) ||
+		       (nfsd4_ops[op->opnum].op_flags & ALLOWED_AS_FIRST_OP);
+	}
+	return true;
+}
+
+/*
  * COMPOUND call.
  */
 static __be32
@@ -863,12 +914,13 @@ nfsd4_proc_compound(struct svc_rqst *rqstp,
 {
 	struct nfsd4_op	*op;
 	struct nfsd4_operation *opdesc;
-	struct nfsd4_compound_state *cstate = NULL;
+	struct nfsd4_compound_state *cstate = &resp->cstate;
 	int		slack_bytes;
 	__be32		status;
 
 	resp->xbuf = &rqstp->rq_res;
-	resp->p = rqstp->rq_res.head[0].iov_base + rqstp->rq_res.head[0].iov_len;
+	resp->p = rqstp->rq_res.head[0].iov_base +
+						rqstp->rq_res.head[0].iov_len;
 	resp->tagp = resp->p;
 	/* reserve space for: taglen, tag, and opcnt */
 	resp->p += 2 + XDR_QUADLEN(args->taglen);
@@ -877,18 +929,25 @@ nfsd4_proc_compound(struct svc_rqst *rqstp,
 	resp->tag = args->tag;
 	resp->opcnt = 0;
 	resp->rqstp = rqstp;
+	resp->cstate.minorversion = args->minorversion;
+	resp->cstate.replay_owner = NULL;
+	fh_init(&resp->cstate.current_fh, NFS4_FHSIZE);
+	fh_init(&resp->cstate.save_fh, NFS4_FHSIZE);
+	/* Use the deferral mechanism only for NFSv4.0 compounds */
+	rqstp->rq_usedeferral = (args->minorversion == 0);
 
 	/*
 	 * According to RFC3010, this takes precedence over all other errors.
 	 */
 	status = nfserr_minor_vers_mismatch;
-	if (args->minorversion > NFSD_SUPPORTED_MINOR_VERSION)
+	if (args->minorversion > nfsd_supported_minorversion)
 		goto out;
 
-	status = nfserr_resource;
-	cstate = cstate_alloc();
-	if (cstate == NULL)
-		goto out;
+	if (!nfs41_op_ordering_ok(args)) {
+		op = &args->ops[0];
+		op->status = nfserr_sequence_pos;
+		goto encode_op;
+	}
 
 	status = nfs_ok;
 	while (!status && resp->opcnt < args->opcnt) {
@@ -897,7 +956,6 @@ nfsd4_proc_compound(struct svc_rqst *rqstp,
 		dprintk("nfsv4 compound op #%d/%d: %d (%s)\n",
 			resp->opcnt, args->opcnt, op->opnum,
 			nfsd4_op_name(op->opnum));
-
 		/*
 		 * The XDR decode routines may have pre-set op->status;
 		 * for example, if there is a miscellaneous XDR error
@@ -938,6 +996,15 @@ nfsd4_proc_compound(struct svc_rqst *rqstp,
 			BUG_ON(op->status == nfs_ok);
 
 encode_op:
+		/* Only from SEQUENCE or CREATE_SESSION */
+		if (resp->cstate.status == nfserr_replay_cache) {
+			dprintk("%s NFS4.1 replay from cache\n", __func__);
+			if (nfsd4_not_cached(resp))
+				status = nfsd4_enc_uncached_replay(args, resp);
+			else
+				status = op->status;
+			goto out;
+		}
 		if (op->status == nfserr_replay_me) {
 			op->replay = &cstate->replay_owner->so_replay;
 			nfsd4_encode_replay(resp, op);
@@ -961,15 +1028,24 @@ encode_op:
 
 		nfsd4_increment_op_stats(op->opnum);
 	}
+	if (!rqstp->rq_usedeferral && status == nfserr_dropit) {
+		dprintk("%s Dropit - send NFS4ERR_DELAY\n", __func__);
+		status = nfserr_jukebox;
+	}
 
-	cstate_free(cstate);
+	resp->cstate.status = status;
+	fh_put(&resp->cstate.current_fh);
+	fh_put(&resp->cstate.save_fh);
+	BUG_ON(resp->cstate.replay_owner);
 out:
 	nfsd4_release_compoundargs(args);
+	/* Reset deferral mechanism for RPC deferrals */
+	rqstp->rq_usedeferral = 1;
 	dprintk("nfsv4 compound returned %d\n", ntohl(status));
 	return status;
 }
 
-static struct nfsd4_operation nfsd4_ops[OP_RELEASE_LOCKOWNER+1] = {
+static struct nfsd4_operation nfsd4_ops[] = {
 	[OP_ACCESS] = {
 		.op_func = (nfsd4op_func)nfsd4_access,
 		.op_name = "OP_ACCESS",
@@ -1045,7 +1121,7 @@ static struct nfsd4_operation nfsd4_ops[OP_RELEASE_LOCKOWNER+1] = {
 		.op_name = "OP_PUTFH",
 	},
 	[OP_PUTPUBFH] = {
-		/* unsupported, just for future reference: */
+		.op_func = (nfsd4op_func)nfsd4_putrootfh,
 		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS,
 		.op_name = "OP_PUTPUBFH",
 	},
@@ -1119,6 +1195,28 @@ static struct nfsd4_operation nfsd4_ops[OP_RELEASE_LOCKOWNER+1] = {
 		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS,
 		.op_name = "OP_RELEASE_LOCKOWNER",
 	},
+
+	/* NFSv4.1 operations */
+	[OP_EXCHANGE_ID] = {
+		.op_func = (nfsd4op_func)nfsd4_exchange_id,
+		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP,
+		.op_name = "OP_EXCHANGE_ID",
+	},
+	[OP_CREATE_SESSION] = {
+		.op_func = (nfsd4op_func)nfsd4_create_session,
+		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP,
+		.op_name = "OP_CREATE_SESSION",
+	},
+	[OP_DESTROY_SESSION] = {
+		.op_func = (nfsd4op_func)nfsd4_destroy_session,
+		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP,
+		.op_name = "OP_DESTROY_SESSION",
+	},
+	[OP_SEQUENCE] = {
+		.op_func = (nfsd4op_func)nfsd4_sequence,
+		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP,
+		.op_name = "OP_SEQUENCE",
+	},
 };
 
 static const char *nfsd4_op_name(unsigned opnum)
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index 74f7b67567f..3444c0052a8 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -182,36 +182,26 @@ out_unlock:
 
 typedef int (recdir_func)(struct dentry *, struct dentry *);
 
-struct dentry_list {
-	struct dentry *dentry;
+struct name_list {
+	char name[HEXDIR_LEN];
 	struct list_head list;
 };
 
-struct dentry_list_arg {
-	struct list_head dentries;
-	struct dentry *parent;
-};
-
 static int
-nfsd4_build_dentrylist(void *arg, const char *name, int namlen,
+nfsd4_build_namelist(void *arg, const char *name, int namlen,
 		loff_t offset, u64 ino, unsigned int d_type)
 {
-	struct dentry_list_arg *dla = arg;
-	struct list_head *dentries = &dla->dentries;
-	struct dentry *parent = dla->parent;
-	struct dentry *dentry;
-	struct dentry_list *child;
+	struct list_head *names = arg;
+	struct name_list *entry;
 
-	if (name && isdotent(name, namlen))
+	if (namlen != HEXDIR_LEN - 1)
 		return 0;
-	dentry = lookup_one_len(name, parent, namlen);
-	if (IS_ERR(dentry))
-		return PTR_ERR(dentry);
-	child = kmalloc(sizeof(*child), GFP_KERNEL);
-	if (child == NULL)
+	entry = kmalloc(sizeof(struct name_list), GFP_KERNEL);
+	if (entry == NULL)
 		return -ENOMEM;
-	child->dentry = dentry;
-	list_add(&child->list, dentries);
+	memcpy(entry->name, name, HEXDIR_LEN - 1);
+	entry->name[HEXDIR_LEN - 1] = '\0';
+	list_add(&entry->list, names);
 	return 0;
 }
 
@@ -220,11 +210,9 @@ nfsd4_list_rec_dir(struct dentry *dir, recdir_func *f)
 {
 	const struct cred *original_cred;
 	struct file *filp;
-	struct dentry_list_arg dla = {
-		.parent = dir,
-	};
-	struct list_head *dentries = &dla.dentries;
-	struct dentry_list *child;
+	LIST_HEAD(names);
+	struct name_list *entry;
+	struct dentry *dentry;
 	int status;
 
 	if (!rec_dir_init)
@@ -233,31 +221,34 @@ nfsd4_list_rec_dir(struct dentry *dir, recdir_func *f)
 	status = nfs4_save_creds(&original_cred);
 	if (status < 0)
 		return status;
-	INIT_LIST_HEAD(dentries);
 
 	filp = dentry_open(dget(dir), mntget(rec_dir.mnt), O_RDONLY,
 			   current_cred());
 	status = PTR_ERR(filp);
 	if (IS_ERR(filp))
 		goto out;
-	INIT_LIST_HEAD(dentries);
-	status = vfs_readdir(filp, nfsd4_build_dentrylist, &dla);
+	status = vfs_readdir(filp, nfsd4_build_namelist, &names);
 	fput(filp);
-	while (!list_empty(dentries)) {
-		child = list_entry(dentries->next, struct dentry_list, list);
-		status = f(dir, child->dentry);
+	while (!list_empty(&names)) {
+		entry = list_entry(names.next, struct name_list, list);
+
+		dentry = lookup_one_len(entry->name, dir, HEXDIR_LEN-1);
+		if (IS_ERR(dentry)) {
+			status = PTR_ERR(dentry);
+			goto out;
+		}
+		status = f(dir, dentry);
+		dput(dentry);
 		if (status)
 			goto out;
-		list_del(&child->list);
-		dput(child->dentry);
-		kfree(child);
+		list_del(&entry->list);
+		kfree(entry);
 	}
 out:
-	while (!list_empty(dentries)) {
-		child = list_entry(dentries->next, struct dentry_list, list);
-		list_del(&child->list);
-		dput(child->dentry);
-		kfree(child);
+	while (!list_empty(&names)) {
+		entry = list_entry(names.next, struct name_list, list);
+		list_del(&entry->list);
+		kfree(entry);
 	}
 	nfs4_reset_creds(original_cred);
 	return status;
@@ -353,7 +344,8 @@ purge_old(struct dentry *parent, struct dentry *child)
 {
 	int status;
 
-	if (nfs4_has_reclaimed_state(child->d_name.name))
+	/* note: we currently use this path only for minorversion 0 */
+	if (nfs4_has_reclaimed_state(child->d_name.name, false))
 		return 0;
 
 	status = nfsd4_clear_clid_dir(parent, child);
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index b6f60f48e94..c65a27b76a9 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -68,6 +68,7 @@ static u32 current_delegid = 1;
 static u32 nfs4_init;
 static stateid_t zerostateid;             /* bits all 0 */
 static stateid_t onestateid;              /* bits all 1 */
+static u64 current_sessionid = 1;
 
 #define ZERO_STATEID(stateid) (!memcmp((stateid), &zerostateid, sizeof(stateid_t)))
 #define ONE_STATEID(stateid)  (!memcmp((stateid), &onestateid, sizeof(stateid_t)))
@@ -75,18 +76,21 @@ static stateid_t onestateid;              /* bits all 1 */
 /* forward declarations */
 static struct nfs4_stateid * find_stateid(stateid_t *stid, int flags);
 static struct nfs4_delegation * find_delegation_stateid(struct inode *ino, stateid_t *stid);
-static void release_stateid_lockowners(struct nfs4_stateid *open_stp);
 static char user_recovery_dirname[PATH_MAX] = "/var/lib/nfs/v4recovery";
 static void nfs4_set_recdir(char *recdir);
 
-/* Locking:
- *
- * client_mutex:
- * 	protects clientid_hashtbl[], clientstr_hashtbl[],
- * 	unconfstr_hashtbl[], uncofid_hashtbl[].
- */
+/* Locking: */
+
+/* Currently used for almost all code touching nfsv4 state: */
 static DEFINE_MUTEX(client_mutex);
 
+/*
+ * Currently used for the del_recall_lru and file hash table.  In an
+ * effort to decrease the scope of the client_mutex, this spinlock may
+ * eventually cover more:
+ */
+static DEFINE_SPINLOCK(recall_lock);
+
 static struct kmem_cache *stateowner_slab = NULL;
 static struct kmem_cache *file_slab = NULL;
 static struct kmem_cache *stateid_slab = NULL;
@@ -117,37 +121,23 @@ opaque_hashval(const void *ptr, int nbytes)
 	return x;
 }
 
-/* forward declarations */
-static void release_stateowner(struct nfs4_stateowner *sop);
-static void release_stateid(struct nfs4_stateid *stp, int flags);
-
-/*
- * Delegation state
- */
-
-/* recall_lock protects the del_recall_lru */
-static DEFINE_SPINLOCK(recall_lock);
 static struct list_head del_recall_lru;
 
-static void
-free_nfs4_file(struct kref *kref)
-{
-	struct nfs4_file *fp = container_of(kref, struct nfs4_file, fi_ref);
-	list_del(&fp->fi_hash);
-	iput(fp->fi_inode);
-	kmem_cache_free(file_slab, fp);
-}
-
 static inline void
 put_nfs4_file(struct nfs4_file *fi)
 {
-	kref_put(&fi->fi_ref, free_nfs4_file);
+	if (atomic_dec_and_lock(&fi->fi_ref, &recall_lock)) {
+		list_del(&fi->fi_hash);
+		spin_unlock(&recall_lock);
+		iput(fi->fi_inode);
+		kmem_cache_free(file_slab, fi);
+	}
 }
 
 static inline void
 get_nfs4_file(struct nfs4_file *fi)
 {
-	kref_get(&fi->fi_ref);
+	atomic_inc(&fi->fi_ref);
 }
 
 static int num_delegations;
@@ -220,9 +210,7 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_stateid *stp, struct svc_f
 	dp->dl_stateid.si_stateownerid = current_delegid++;
 	dp->dl_stateid.si_fileid = 0;
 	dp->dl_stateid.si_generation = 0;
-	dp->dl_fhlen = current_fh->fh_handle.fh_size;
-	memcpy(dp->dl_fhval, &current_fh->fh_handle.fh_base,
-		        current_fh->fh_handle.fh_size);
+	fh_copy_shallow(&dp->dl_fh, &current_fh->fh_handle);
 	dp->dl_time = 0;
 	atomic_set(&dp->dl_count, 1);
 	list_add(&dp->dl_perfile, &fp->fi_delegations);
@@ -311,6 +299,291 @@ static struct list_head	unconf_id_hashtbl[CLIENT_HASH_SIZE];
 static struct list_head client_lru;
 static struct list_head close_lru;
 
+static void unhash_generic_stateid(struct nfs4_stateid *stp)
+{
+	list_del(&stp->st_hash);
+	list_del(&stp->st_perfile);
+	list_del(&stp->st_perstateowner);
+}
+
+static void free_generic_stateid(struct nfs4_stateid *stp)
+{
+	put_nfs4_file(stp->st_file);
+	kmem_cache_free(stateid_slab, stp);
+}
+
+static void release_lock_stateid(struct nfs4_stateid *stp)
+{
+	unhash_generic_stateid(stp);
+	locks_remove_posix(stp->st_vfs_file, (fl_owner_t)stp->st_stateowner);
+	free_generic_stateid(stp);
+}
+
+static void unhash_lockowner(struct nfs4_stateowner *sop)
+{
+	struct nfs4_stateid *stp;
+
+	list_del(&sop->so_idhash);
+	list_del(&sop->so_strhash);
+	list_del(&sop->so_perstateid);
+	while (!list_empty(&sop->so_stateids)) {
+		stp = list_first_entry(&sop->so_stateids,
+				struct nfs4_stateid, st_perstateowner);
+		release_lock_stateid(stp);
+	}
+}
+
+static void release_lockowner(struct nfs4_stateowner *sop)
+{
+	unhash_lockowner(sop);
+	nfs4_put_stateowner(sop);
+}
+
+static void
+release_stateid_lockowners(struct nfs4_stateid *open_stp)
+{
+	struct nfs4_stateowner *lock_sop;
+
+	while (!list_empty(&open_stp->st_lockowners)) {
+		lock_sop = list_entry(open_stp->st_lockowners.next,
+				struct nfs4_stateowner, so_perstateid);
+		/* list_del(&open_stp->st_lockowners);  */
+		BUG_ON(lock_sop->so_is_open_owner);
+		release_lockowner(lock_sop);
+	}
+}
+
+static void release_open_stateid(struct nfs4_stateid *stp)
+{
+	unhash_generic_stateid(stp);
+	release_stateid_lockowners(stp);
+	nfsd_close(stp->st_vfs_file);
+	free_generic_stateid(stp);
+}
+
+static void unhash_openowner(struct nfs4_stateowner *sop)
+{
+	struct nfs4_stateid *stp;
+
+	list_del(&sop->so_idhash);
+	list_del(&sop->so_strhash);
+	list_del(&sop->so_perclient);
+	list_del(&sop->so_perstateid); /* XXX: necessary? */
+	while (!list_empty(&sop->so_stateids)) {
+		stp = list_first_entry(&sop->so_stateids,