Merge tag 'nfsd-4.19-1' of git://linux-nfs.org/~bfields/linux

Pull nfsd updates from Bruce Fields:
 "Chuck Lever fixed a problem with NFSv4.0 callbacks over GSS from
  multi-homed servers.

  The only new feature is a minor bit of protocol (change_attr_type)
  which the client doesn't even use yet.

  Other than that, various bugfixes and cleanup"

* tag 'nfsd-4.19-1' of git://linux-nfs.org/~bfields/linux: (27 commits)
  sunrpc: Add comment defining gssd upcall API keywords
  nfsd: Remove callback_cred
  nfsd: Use correct credential for NFSv4.0 callback with GSS
  sunrpc: Extract target name into svc_cred
  sunrpc: Enable the kernel to specify the hostname part of service principals
  sunrpc: Don't use stack buffer with scatterlist
  rpc: remove unneeded variable 'ret' in rdma_listen_handler
  nfsd: use true and false for boolean values
  nfsd: constify write_op[]
  fs/nfsd: Delete invalid assignment statements in nfsd4_decode_exchange_id
  NFSD: Handle full-length symlinks
  NFSD: Refactor the generic write vector fill helper
  svcrdma: Clean up Read chunk path
  svcrdma: Avoid releasing a page in svc_xprt_release()
  nfsd: Mark expected switch fall-through
  sunrpc: remove redundant variables 'checksumlen','blocksize' and 'data'
  nfsd: fix leaked file lock with nfs exported overlayfs
  nfsd: don't advertise a SCSI layout for an unsupported request_queue
  nfsd: fix corrupted reply to badly ordered compound
  nfsd: clarify check_op_ordering
  ...

fs/lockd/clntlock.c

@@ -187,7 +187,7 @@ __be32 nlmclnt_grant(const struct sockaddr *addr, const struct nlm_lock *lock)
 			continue;
 		if (!rpc_cmp_addr(nlm_addr(block->b_host), addr))
 			continue;
-		if (nfs_compare_fh(NFS_FH(file_inode(fl_blocked->fl_file)) ,fh) != 0)
+		if (nfs_compare_fh(NFS_FH(locks_inode(fl_blocked->fl_file)), fh) != 0)
 			continue;
 		/* Alright, we found a lock. Set the return status
 		 * and wake up the caller

fs/lockd/clntproc.c

@@ -128,7 +128,7 @@ static void nlmclnt_setlockargs(struct nlm_rqst *req, struct file_lock *fl)
 	char *nodename = req->a_host->h_rpcclnt->cl_nodename;
 
 	nlmclnt_next_cookie(&argp->cookie);
-	memcpy(&lock->fh, NFS_FH(file_inode(fl->fl_file)), sizeof(struct nfs_fh));
+	memcpy(&lock->fh, NFS_FH(locks_inode(fl->fl_file)), sizeof(struct nfs_fh));
 	lock->caller  = nodename;
 	lock->oh.data = req->a_owner;
 	lock->oh.len  = snprintf(req->a_owner, sizeof(req->a_owner), "%u@%s",

fs/lockd/svclock.c

@@ -405,8 +405,8 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file,
 	__be32			ret;
 
 	dprintk("lockd: nlmsvc_lock(%s/%ld, ty=%d, pi=%d, %Ld-%Ld, bl=%d)\n",
-				file_inode(file->f_file)->i_sb->s_id,
-				file_inode(file->f_file)->i_ino,
+				locks_inode(file->f_file)->i_sb->s_id,
+				locks_inode(file->f_file)->i_ino,
 				lock->fl.fl_type, lock->fl.fl_pid,
 				(long long)lock->fl.fl_start,
 				(long long)lock->fl.fl_end,
@@ -511,8 +511,8 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file,
 	__be32			ret;
 
 	dprintk("lockd: nlmsvc_testlock(%s/%ld, ty=%d, %Ld-%Ld)\n",
-				file_inode(file->f_file)->i_sb->s_id,
-				file_inode(file->f_file)->i_ino,
+				locks_inode(file->f_file)->i_sb->s_id,
+				locks_inode(file->f_file)->i_ino,
 				lock->fl.fl_type,
 				(long long)lock->fl.fl_start,
 				(long long)lock->fl.fl_end);
@@ -566,8 +566,8 @@ nlmsvc_unlock(struct net *net, struct nlm_file *file, struct nlm_lock *lock)
 	int	error;
 
 	dprintk("lockd: nlmsvc_unlock(%s/%ld, pi=%d, %Ld-%Ld)\n",
-				file_inode(file->f_file)->i_sb->s_id,
-				file_inode(file->f_file)->i_ino,
+				locks_inode(file->f_file)->i_sb->s_id,
+				locks_inode(file->f_file)->i_ino,
 				lock->fl.fl_pid,
 				(long long)lock->fl.fl_start,
 				(long long)lock->fl.fl_end);
@@ -595,8 +595,8 @@ nlmsvc_cancel_blocked(struct net *net, struct nlm_file *file, struct nlm_lock *l
 	int status = 0;
 
 	dprintk("lockd: nlmsvc_cancel(%s/%ld, pi=%d, %Ld-%Ld)\n",
-				file_inode(file->f_file)->i_sb->s_id,
-				file_inode(file->f_file)->i_ino,
+				locks_inode(file->f_file)->i_sb->s_id,
+				locks_inode(file->f_file)->i_ino,
 				lock->fl.fl_pid,
 				(long long)lock->fl.fl_start,
 				(long long)lock->fl.fl_end);

fs/lockd/svcsubs.c

@@ -44,7 +44,7 @@ static inline void nlm_debug_print_fh(char *msg, struct nfs_fh *f)
 
 static inline void nlm_debug_print_file(char *msg, struct nlm_file *file)
 {
-	struct inode *inode = file_inode(file->f_file);
+	struct inode *inode = locks_inode(file->f_file);
 
 	dprintk("lockd: %s %s/%ld\n",
 		msg, inode->i_sb->s_id, inode->i_ino);
@@ -414,7 +414,7 @@ nlmsvc_match_sb(void *datap, struct nlm_file *file)
 {
 	struct super_block *sb = datap;
 
-	return sb == file_inode(file->f_file)->i_sb;
+	return sb == locks_inode(file->f_file)->i_sb;
 }
 
 /**

fs/nfsd/netns.h

@@ -102,6 +102,7 @@ struct nfsd_net {
 
 	time_t nfsd4_lease;
 	time_t nfsd4_grace;
+	bool somebody_reclaimed;
 
 	bool nfsd_net_up;
 	bool lockd_up;

fs/nfsd/nfs3proc.c

@@ -202,7 +202,8 @@ nfsd3_proc_write(struct svc_rqst *rqstp)
 
 	fh_copy(&resp->fh, &argp->fh);
 	resp->committed = argp->stable;
-	nvecs = svc_fill_write_vector(rqstp, &argp->first, cnt);
+	nvecs = svc_fill_write_vector(rqstp, rqstp->rq_arg.pages,
+				      &argp->first, cnt);
 	if (!nvecs)
 		RETURN_STATUS(nfserr_io);
 	nfserr = nfsd_write(rqstp, &resp->fh, argp->offset,
@@ -289,6 +290,7 @@ nfsd3_proc_symlink(struct svc_rqst *rqstp)
 		RETURN_STATUS(nfserr_nametoolong);
 
 	argp->tname = svc_fill_symlink_pathname(rqstp, &argp->first,
+						page_address(rqstp->rq_arg.pages[0]),
 						argp->tlen);
 	if (IS_ERR(argp->tname))
 		RETURN_STATUS(nfserrno(PTR_ERR(argp->tname)));
@@ -302,6 +304,7 @@ nfsd3_proc_symlink(struct svc_rqst *rqstp)
 	fh_init(&resp->fh, NFS3_FHSIZE);
 	nfserr = nfsd_symlink(rqstp, &resp->dirfh, argp->fname, argp->flen,
 						   argp->tname, &resp->fh);
+	kfree(argp->tname);
 	RETURN_STATUS(nfserr);
 }
 

fs/nfsd/nfs4callback.c

@@ -746,30 +746,17 @@ static int max_cb_time(struct net *net)
 	return max(nn->nfsd4_lease/10, (time_t)1) * HZ;
 }
 
-static struct rpc_cred *callback_cred;
-
-int set_callback_cred(void)
-{
-	if (callback_cred)
-		return 0;
-	callback_cred = rpc_lookup_machine_cred("nfs");
-	if (!callback_cred)
-		return -ENOMEM;
-	return 0;
-}
-
-void cleanup_callback_cred(void)
-{
-	if (callback_cred) {
-		put_rpccred(callback_cred);
-		callback_cred = NULL;
-	}
-}
-
 static struct rpc_cred *get_backchannel_cred(struct nfs4_client *clp, struct rpc_clnt *client, struct nfsd4_session *ses)
 {
 	if (clp->cl_minorversion == 0) {
-		return get_rpccred(callback_cred);
+		char *principal = clp->cl_cred.cr_targ_princ ?
+					clp->cl_cred.cr_targ_princ : "nfs";
+		struct rpc_cred *cred;
+
+		cred = rpc_lookup_machine_cred(principal);
+		if (!IS_ERR(cred))
+			get_rpccred(cred);
+		return cred;
 	} else {
 		struct rpc_auth *auth = client->cl_auth;
 		struct auth_cred acred = {};
@@ -980,6 +967,7 @@ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback
 		break;
 	case -ESERVERFAULT:
 		++session->se_cb_seq_nr;
+		/* Fall through */
 	case 1:
 	case -NFS4ERR_BADSESSION:
 		nfsd4_mark_cb_fault(cb->cb_clp, cb->cb_seq_status);

fs/nfsd/nfs4layouts.c

@@ -133,27 +133,20 @@ void nfsd4_setup_layout_type(struct svc_export *exp)
 	if (!(exp->ex_flags & NFSEXP_PNFS))
 		return;
 
-	/*
-	 * If flex file is configured, use it by default. Otherwise
-	 * check if the file system supports exporting a block-like layout.
-	 * If the block device supports reservations prefer the SCSI layout,
-	 * otherwise advertise the block layout.
-	 */
 #ifdef CONFIG_NFSD_FLEXFILELAYOUT
 	exp->ex_layout_types |= 1 << LAYOUT_FLEX_FILES;
 #endif
 #ifdef CONFIG_NFSD_BLOCKLAYOUT
-	/* overwrite flex file layout selection if needed */
 	if (sb->s_export_op->get_uuid &&
 	    sb->s_export_op->map_blocks &&
 	    sb->s_export_op->commit_blocks)
 		exp->ex_layout_types |= 1 << LAYOUT_BLOCK_VOLUME;
 #endif
 #ifdef CONFIG_NFSD_SCSILAYOUT
-	/* overwrite block layout selection if needed */
 	if (sb->s_export_op->map_blocks &&
 	    sb->s_export_op->commit_blocks &&
-	    sb->s_bdev && sb->s_bdev->bd_disk->fops->pr_ops)
+	    sb->s_bdev && sb->s_bdev->bd_disk->fops->pr_ops &&
+		blk_queue_scsi_passthrough(sb->s_bdev->bd_disk->queue))
 		exp->ex_layout_types |= 1 << LAYOUT_SCSI;
 #endif
 }

fs/nfsd/nfs4proc.c

@@ -354,6 +354,7 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	struct svc_fh *resfh = NULL;
 	struct net *net = SVC_NET(rqstp);
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	bool reclaim = false;
 
 	dprintk("NFSD: nfsd4_open filename %.*s op_openowner %p\n",
 		(int)open->op_fname.len, open->op_fname.data,
@@ -424,6 +425,7 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 			if (status)
 				goto out;
 			open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED;
+			reclaim = true;
 		case NFS4_OPEN_CLAIM_FH:
 		case NFS4_OPEN_CLAIM_DELEG_CUR_FH:
 			status = do_open_fhandle(rqstp, cstate, open);
@@ -452,6 +454,8 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	WARN(status && open->op_created,
 	     "nfsd4_process_open2 failed to open newly-created file! status=%u\n",
 	     be32_to_cpu(status));
+	if (reclaim && !status)
+		nn->somebody_reclaimed = true;
 out:
 	if (resfh && resfh != &cstate->current_fh) {
 		fh_dup2(&cstate->current_fh, resfh);
@@ -982,24 +986,6 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	return status;
 }
 
-static int fill_in_write_vector(struct kvec *vec, struct nfsd4_write *write)
-{
-        int i = 1;
-        int buflen = write->wr_buflen;
-
-        vec[0].iov_base = write->wr_head.iov_base;
-        vec[0].iov_len = min_t(int, buflen, write->wr_head.iov_len);
-        buflen -= vec[0].iov_len;
-
-        while (buflen) {
-                vec[i].iov_base = page_address(write->wr_pagelist[i - 1]);
-                vec[i].iov_len = min_t(int, PAGE_SIZE, buflen);
-                buflen -= vec[i].iov_len;
-                i++;
-        }
-        return i;
-}
-
 static __be32
 nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	    union nfsd4_op_u *u)
@@ -1027,7 +1013,10 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	write->wr_how_written = write->wr_stable_how;
 	gen_boot_verifier(&write->wr_verifier, SVC_NET(rqstp));
 
-	nvecs = fill_in_write_vector(rqstp->rq_vec, write);
+	nvecs = svc_fill_write_vector(rqstp, write->wr_pagelist,
+				      &write->wr_head, write->wr_buflen);
+	if (!nvecs)
+		return nfserr_io;
 	WARN_ON_ONCE(nvecs > ARRAY_SIZE(rqstp->rq_vec));
 
 	status = nfsd_vfs_write(rqstp, &cstate->current_fh, filp,
@@ -1599,20 +1588,25 @@ static const char *nfsd4_op_name(unsigned opnum);
  */
 static __be32 nfs41_check_op_ordering(struct nfsd4_compoundargs *args)
 {
-	struct nfsd4_op *op = &args->ops[0];
+	struct nfsd4_op *first_op = &args->ops[0];
 
 	/* These ordering requirements don't apply to NFSv4.0: */
 	if (args->minorversion == 0)
 		return nfs_ok;
 	/* This is weird, but OK, not our problem: */
 	if (args->opcnt == 0)
 		return nfs_ok;
-	if (op->status == nfserr_op_illegal)
+	if (first_op->status == nfserr_op_illegal)
 		return nfs_ok;
-	if (!(nfsd4_ops[op->opnum].op_flags & ALLOWED_AS_FIRST_OP))
+	if (!(nfsd4_ops[first_op->opnum].op_flags & ALLOWED_AS_FIRST_OP))
 		return nfserr_op_not_in_session;
-	if (op->opnum == OP_SEQUENCE)
+	if (first_op->opnum == OP_SEQUENCE)
 		return nfs_ok;
+	/*
+	 * So first_op is something allowed outside a session, like
+	 * EXCHANGE_ID; but then it has to be the only op in the
+	 * compound:
+	 */
 	if (args->opcnt != 1)
 		return nfserr_not_only_op;
 	return nfs_ok;
@@ -1726,6 +1720,7 @@ nfsd4_proc_compound(struct svc_rqst *rqstp)
 	if (status) {
 		op = &args->ops[0];
 		op->status = status;
+		resp->opcnt = 1;
 		goto encode_op;
 	}