Merge tag 'nfsd-4.9' of git://linux-nfs.org/~bfields/linux

Pull nfsd updates from Bruce Fields:
 "Some RDMA work and some good bugfixes, and two new features that could
  benefit from user testing:

   - Anna Schumacker contributed a simple NFSv4.2 COPY implementation.
     COPY is already supported on the client side, so a call to
     copy_file_range() on a recent client should now result in a
     server-side copy that doesn't require all the data to make a round
     trip to the client and back.

   - Jeff Layton implemented callbacks to notify clients when contended
     locks become available, which should reduce latency on workloads
     with contended locks"

* tag 'nfsd-4.9' of git://linux-nfs.org/~bfields/linux:
  NFSD: Implement the COPY call
  nfsd: handle EUCLEAN
  nfsd: only WARN once on unmapped errors
  exportfs: be careful to only return expected errors.
  nfsd4: setclientid_confirm with unmatched verifier should fail
  nfsd: randomize SETCLIENTID reply to help distinguish servers
  nfsd: set the MAY_NOTIFY_LOCK flag in OPEN replies
  nfs: add a new NFS4_OPEN_RESULT_MAY_NOTIFY_LOCK constant
  nfsd: add a LRU list for blocked locks
  nfsd: have nfsd4_lock use blocking locks for v4.1+ locks
  nfsd: plumb in a CB_NOTIFY_LOCK operation
  NFSD: fix corruption in notifier registration
  svcrdma: support Remote Invalidation
  svcrdma: Server-side support for rpcrdma_connect_private
  rpcrdma: RDMA/CM private message data structure
  svcrdma: Skip put_page() when send_reply() fails
  svcrdma: Tail iovec leaves an orphaned DMA mapping
  nfsd: fix dprintk in nfsd4_encode_getdeviceinfo
  nfsd: eliminate cb_minorversion field
  nfsd: don't set a FL_LAYOUT lease for flexfiles layouts

fs/exportfs/expfs.c

@@ -428,10 +428,10 @@ struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid,
 	if (!nop || !nop->fh_to_dentry)
 		return ERR_PTR(-ESTALE);
 	result = nop->fh_to_dentry(mnt->mnt_sb, fid, fh_len, fileid_type);
-	if (!result)
-		result = ERR_PTR(-ESTALE);
-	if (IS_ERR(result))
-		return result;
+	if (PTR_ERR(result) == -ENOMEM)
+		return ERR_CAST(result);
+	if (IS_ERR_OR_NULL(result))
+		return ERR_PTR(-ESTALE);
 
 	if (d_is_dir(result)) {
 		/*
@@ -541,6 +541,8 @@ struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid,
 
  err_result:
 	dput(result);
+	if (err != -ENOMEM)
+		err = -ESTALE;
 	return ERR_PTR(err);
 }
 EXPORT_SYMBOL_GPL(exportfs_decode_fh);

fs/nfsd/flexfilelayout.c

@@ -126,6 +126,7 @@ nfsd4_ff_proc_getdeviceinfo(struct super_block *sb, struct svc_rqst *rqstp,
 const struct nfsd4_layout_ops ff_layout_ops = {
 	.notify_types		=
 			NOTIFY_DEVICEID4_DELETE | NOTIFY_DEVICEID4_CHANGE,
+	.disable_recalls	= true,
 	.proc_getdeviceinfo	= nfsd4_ff_proc_getdeviceinfo,
 	.encode_getdeviceinfo	= nfsd4_ff_encode_getdeviceinfo,
 	.proc_layoutget		= nfsd4_ff_proc_layoutget,

fs/nfsd/netns.h

@@ -84,6 +84,7 @@ struct nfsd_net {
 	struct list_head client_lru;
 	struct list_head close_lru;
 	struct list_head del_recall_lru;
+	struct list_head blocked_locks_lru;
 
 	struct delayed_work laundromat_work;
 

fs/nfsd/nfs4callback.c

@@ -448,7 +448,7 @@ static int decode_cb_sequence4res(struct xdr_stream *xdr,
 {
 	int status;
 
-	if (cb->cb_minorversion == 0)
+	if (cb->cb_clp->cl_minorversion == 0)
 		return 0;
 
 	status = decode_cb_op_status(xdr, OP_CB_SEQUENCE, &cb->cb_seq_status);
@@ -485,7 +485,7 @@ static void nfs4_xdr_enc_cb_recall(struct rpc_rqst *req, struct xdr_stream *xdr,
 	const struct nfs4_delegation *dp = cb_to_delegation(cb);
 	struct nfs4_cb_compound_hdr hdr = {
 		.ident = cb->cb_clp->cl_cb_ident,
-		.minorversion = cb->cb_minorversion,
+		.minorversion = cb->cb_clp->cl_minorversion,
 	};
 
 	encode_cb_compound4args(xdr, &hdr);
@@ -594,7 +594,7 @@ static void nfs4_xdr_enc_cb_layout(struct rpc_rqst *req,
 		container_of(cb, struct nfs4_layout_stateid, ls_recall);
 	struct nfs4_cb_compound_hdr hdr = {
 		.ident = 0,
-		.minorversion = cb->cb_minorversion,
+		.minorversion = cb->cb_clp->cl_minorversion,
 	};
 
 	encode_cb_compound4args(xdr, &hdr);
@@ -623,6 +623,62 @@ static int nfs4_xdr_dec_cb_layout(struct rpc_rqst *rqstp,
 }
 #endif /* CONFIG_NFSD_PNFS */
 
+static void encode_stateowner(struct xdr_stream *xdr, struct nfs4_stateowner *so)
+{
+	__be32	*p;
+
+	p = xdr_reserve_space(xdr, 8 + 4 + so->so_owner.len);
+	p = xdr_encode_opaque_fixed(p, &so->so_client->cl_clientid, 8);
+	xdr_encode_opaque(p, so->so_owner.data, so->so_owner.len);
+}
+
+static void nfs4_xdr_enc_cb_notify_lock(struct rpc_rqst *req,
+					struct xdr_stream *xdr,
+					const struct nfsd4_callback *cb)
+{
+	const struct nfsd4_blocked_lock *nbl =
+		container_of(cb, struct nfsd4_blocked_lock, nbl_cb);
+	struct nfs4_lockowner *lo = (struct nfs4_lockowner *)nbl->nbl_lock.fl_owner;
+	struct nfs4_cb_compound_hdr hdr = {
+		.ident = 0,
+		.minorversion = cb->cb_clp->cl_minorversion,
+	};
+
+	__be32 *p;
+
+	BUG_ON(hdr.minorversion == 0);
+
+	encode_cb_compound4args(xdr, &hdr);
+	encode_cb_sequence4args(xdr, cb, &hdr);
+
+	p = xdr_reserve_space(xdr, 4);
+	*p = cpu_to_be32(OP_CB_NOTIFY_LOCK);
+	encode_nfs_fh4(xdr, &nbl->nbl_fh);
+	encode_stateowner(xdr, &lo->lo_owner);
+	hdr.nops++;
+
+	encode_cb_nops(&hdr);
+}
+
+static int nfs4_xdr_dec_cb_notify_lock(struct rpc_rqst *rqstp,
+					struct xdr_stream *xdr,
+					struct nfsd4_callback *cb)
+{
+	struct nfs4_cb_compound_hdr hdr;
+	int status;
+
+	status = decode_cb_compound4res(xdr, &hdr);
+	if (unlikely(status))
+		return status;
+
+	if (cb) {
+		status = decode_cb_sequence4res(xdr, cb);
+		if (unlikely(status || cb->cb_seq_status))
+			return status;
+	}
+	return decode_cb_op_status(xdr, OP_CB_NOTIFY_LOCK, &cb->cb_status);
+}
+
 /*
  * RPC procedure tables
  */
@@ -643,6 +699,7 @@ static struct rpc_procinfo nfs4_cb_procedures[] = {
 #ifdef CONFIG_NFSD_PNFS
 	PROC(CB_LAYOUT,	COMPOUND,	cb_layout,	cb_layout),
 #endif
+	PROC(CB_NOTIFY_LOCK,	COMPOUND,	cb_notify_lock,	cb_notify_lock),
 };
 
 static struct rpc_version nfs_cb_version4 = {
@@ -862,7 +919,6 @@ static void nfsd4_cb_prepare(struct rpc_task *task, void *calldata)
 	struct nfs4_client *clp = cb->cb_clp;
 	u32 minorversion = clp->cl_minorversion;
 
-	cb->cb_minorversion = minorversion;
 	/*
 	 * cb_seq_status is only set in decode_cb_sequence4res,
 	 * and so will remain 1 if an rpc level failure occurs.

fs/nfsd/nfs4layouts.c

@@ -174,7 +174,8 @@ nfsd4_free_layout_stateid(struct nfs4_stid *stid)
 	list_del_init(&ls->ls_perfile);
 	spin_unlock(&fp->fi_lock);
 
-	vfs_setlease(ls->ls_file, F_UNLCK, NULL, (void **)&ls);
+	if (!nfsd4_layout_ops[ls->ls_layout_type]->disable_recalls)
+		vfs_setlease(ls->ls_file, F_UNLCK, NULL, (void **)&ls);
 	fput(ls->ls_file);
 
 	if (ls->ls_recalled)
@@ -189,6 +190,9 @@ nfsd4_layout_setlease(struct nfs4_layout_stateid *ls)
 	struct file_lock *fl;
 	int status;
 
+	if (nfsd4_layout_ops[ls->ls_layout_type]->disable_recalls)
+		return 0;
+
 	fl = locks_alloc_lock();
 	if (!fl)
 		return -ENOMEM;

fs/nfsd/nfs4proc.c

@@ -1010,46 +1010,96 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 }
 
 static __be32
-nfsd4_clone(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
-		struct nfsd4_clone *clone)
+nfsd4_verify_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
+		  stateid_t *src_stateid, struct file **src,
+		  stateid_t *dst_stateid, struct file **dst)
 {
-	struct file *src, *dst;
 	__be32 status;
 
 	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->save_fh,
-					    &clone->cl_src_stateid, RD_STATE,
-					    &src, NULL);
+					    src_stateid, RD_STATE, src, NULL);
 	if (status) {
 		dprintk("NFSD: %s: couldn't process src stateid!\n", __func__);
 		goto out;
 	}
 
 	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
-					    &clone->cl_dst_stateid, WR_STATE,
-					    &dst, NULL);
+					    dst_stateid, WR_STATE, dst, NULL);
 	if (status) {
 		dprintk("NFSD: %s: couldn't process dst stateid!\n", __func__);
 		goto out_put_src;
 	}
 
 	/* fix up for NFS-specific error code */
-	if (!S_ISREG(file_inode(src)->i_mode) ||
-	    !S_ISREG(file_inode(dst)->i_mode)) {
+	if (!S_ISREG(file_inode(*src)->i_mode) ||
+	    !S_ISREG(file_inode(*dst)->i_mode)) {
 		status = nfserr_wrong_type;
 		goto out_put_dst;
 	}
 
+out:
+	return status;
+out_put_dst:
+	fput(*dst);
+out_put_src:
+	fput(*src);
+	goto out;
+}
+
+static __be32
+nfsd4_clone(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
+		struct nfsd4_clone *clone)
+{
+	struct file *src, *dst;
+	__be32 status;
+
+	status = nfsd4_verify_copy(rqstp, cstate, &clone->cl_src_stateid, &src,
+				   &clone->cl_dst_stateid, &dst);
+	if (status)
+		goto out;
+
 	status = nfsd4_clone_file_range(src, clone->cl_src_pos,
 			dst, clone->cl_dst_pos, clone->cl_count);
 
-out_put_dst:
 	fput(dst);
-out_put_src:
 	fput(src);
 out:
 	return status;
 }
 
+static __be32
+nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
+		struct nfsd4_copy *copy)
+{
+	struct file *src, *dst;
+	__be32 status;
+	ssize_t bytes;
+
+	status = nfsd4_verify_copy(rqstp, cstate, &copy->cp_src_stateid, &src,
+				   &copy->cp_dst_stateid, &dst);
+	if (status)
+		goto out;
+
+	bytes = nfsd_copy_file_range(src, copy->cp_src_pos,
+			dst, copy->cp_dst_pos, copy->cp_count);
+
+	if (bytes < 0)
+		status = nfserrno(bytes);
+	else {
+		copy->cp_res.wr_bytes_written = bytes;
+		copy->cp_res.wr_stable_how = NFS_UNSTABLE;
+		copy->cp_consecutive = 1;
+		copy->cp_synchronous = 1;
+		gen_boot_verifier(&copy->cp_res.wr_verifier, SVC_NET(rqstp));
+		status = nfs_ok;
+	}
+
+	fput(src);
+	fput(dst);
+out:
+	return status;
+}
+
 static __be32
 nfsd4_fallocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		struct nfsd4_fallocate *fallocate, int flags)
@@ -1966,6 +2016,18 @@ static inline u32 nfsd4_create_session_rsize(struct svc_rqst *rqstp, struct nfsd
 		op_encode_channel_attrs_maxsz) * sizeof(__be32);
 }
 
+static inline u32 nfsd4_copy_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+{
+	return (op_encode_hdr_size +
+		1 /* wr_callback */ +
+		op_encode_stateid_maxsz /* wr_callback */ +
+		2 /* wr_count */ +
+		1 /* wr_committed */ +
+		op_encode_verifier_maxsz +
+		1 /* cr_consecutive */ +
+		1 /* cr_synchronous */) * sizeof(__be32);
+}
+
 #ifdef CONFIG_NFSD_PNFS
 /*
  * At this stage we don't really know what layout driver will handle the request,
@@ -2328,6 +2390,12 @@ static struct nfsd4_operation nfsd4_ops[] = {
 		.op_name = "OP_CLONE",
 		.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
 	},
+	[OP_COPY] = {
+		.op_func = (nfsd4op_func)nfsd4_copy,
+		.op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME,
+		.op_name = "OP_COPY",
+		.op_rsize_bop = (nfsd4op_rsize)nfsd4_copy_rsize,
+	},
 	[OP_SEEK] = {
 		.op_func = (nfsd4op_func)nfsd4_seek,
 		.op_name = "OP_SEEK",