xref: /kernel/linux/linux-6.6/fs/nfsd/nfs4proc.c (revision 62306a36)
1/*
2 *  Server-side procedures for NFSv4.
3 *
4 *  Copyright (c) 2002 The Regents of the University of Michigan.
5 *  All rights reserved.
6 *
7 *  Kendrick Smith <kmsmith@umich.edu>
8 *  Andy Adamson   <andros@umich.edu>
9 *
10 *  Redistribution and use in source and binary forms, with or without
11 *  modification, are permitted provided that the following conditions
12 *  are met:
13 *
14 *  1. Redistributions of source code must retain the above copyright
15 *     notice, this list of conditions and the following disclaimer.
16 *  2. Redistributions in binary form must reproduce the above copyright
17 *     notice, this list of conditions and the following disclaimer in the
18 *     documentation and/or other materials provided with the distribution.
19 *  3. Neither the name of the University nor the names of its
20 *     contributors may be used to endorse or promote products derived
21 *     from this software without specific prior written permission.
22 *
23 *  THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
24 *  WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
25 *  MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
26 *  DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
27 *  FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
28 *  CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
29 *  SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
30 *  BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
31 *  LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
32 *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
33 *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
34 */
35#include <linux/fs_struct.h>
36#include <linux/file.h>
37#include <linux/falloc.h>
38#include <linux/slab.h>
39#include <linux/kthread.h>
40#include <linux/namei.h>
41
42#include <linux/sunrpc/addr.h>
43#include <linux/nfs_ssc.h>
44
45#include "idmap.h"
46#include "cache.h"
47#include "xdr4.h"
48#include "vfs.h"
49#include "current_stateid.h"
50#include "netns.h"
51#include "acl.h"
52#include "pnfs.h"
53#include "trace.h"
54
55static bool inter_copy_offload_enable;
56module_param(inter_copy_offload_enable, bool, 0644);
57MODULE_PARM_DESC(inter_copy_offload_enable,
58		 "Enable inter server to server copy offload. Default: false");
59
60#ifdef CONFIG_NFSD_V4_2_INTER_SSC
61static int nfsd4_ssc_umount_timeout = 900000;		/* default to 15 mins */
62module_param(nfsd4_ssc_umount_timeout, int, 0644);
63MODULE_PARM_DESC(nfsd4_ssc_umount_timeout,
64		"idle msecs before unmount export from source server");
65#endif
66
67#define NFSDDBG_FACILITY		NFSDDBG_PROC
68
69static u32 nfsd_attrmask[] = {
70	NFSD_WRITEABLE_ATTRS_WORD0,
71	NFSD_WRITEABLE_ATTRS_WORD1,
72	NFSD_WRITEABLE_ATTRS_WORD2
73};
74
75static u32 nfsd41_ex_attrmask[] = {
76	NFSD_SUPPATTR_EXCLCREAT_WORD0,
77	NFSD_SUPPATTR_EXCLCREAT_WORD1,
78	NFSD_SUPPATTR_EXCLCREAT_WORD2
79};
80
81static __be32
82check_attr_support(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
83		   u32 *bmval, u32 *writable)
84{
85	struct dentry *dentry = cstate->current_fh.fh_dentry;
86	struct svc_export *exp = cstate->current_fh.fh_export;
87
88	if (!nfsd_attrs_supported(cstate->minorversion, bmval))
89		return nfserr_attrnotsupp;
90	if ((bmval[0] & FATTR4_WORD0_ACL) && !IS_POSIXACL(d_inode(dentry)))
91		return nfserr_attrnotsupp;
92	if ((bmval[2] & FATTR4_WORD2_SECURITY_LABEL) &&
93			!(exp->ex_flags & NFSEXP_SECURITY_LABEL))
94		return nfserr_attrnotsupp;
95	if (writable && !bmval_is_subset(bmval, writable))
96		return nfserr_inval;
97	if (writable && (bmval[2] & FATTR4_WORD2_MODE_UMASK) &&
98			(bmval[1] & FATTR4_WORD1_MODE))
99		return nfserr_inval;
100	return nfs_ok;
101}
102
103static __be32
104nfsd4_check_open_attributes(struct svc_rqst *rqstp,
105	struct nfsd4_compound_state *cstate, struct nfsd4_open *open)
106{
107	__be32 status = nfs_ok;
108
109	if (open->op_create == NFS4_OPEN_CREATE) {
110		if (open->op_createmode == NFS4_CREATE_UNCHECKED
111		    || open->op_createmode == NFS4_CREATE_GUARDED)
112			status = check_attr_support(rqstp, cstate,
113					open->op_bmval, nfsd_attrmask);
114		else if (open->op_createmode == NFS4_CREATE_EXCLUSIVE4_1)
115			status = check_attr_support(rqstp, cstate,
116					open->op_bmval, nfsd41_ex_attrmask);
117	}
118
119	return status;
120}
121
122static int
123is_create_with_attrs(struct nfsd4_open *open)
124{
125	return open->op_create == NFS4_OPEN_CREATE
126		&& (open->op_createmode == NFS4_CREATE_UNCHECKED
127		    || open->op_createmode == NFS4_CREATE_GUARDED
128		    || open->op_createmode == NFS4_CREATE_EXCLUSIVE4_1);
129}
130
131static inline void
132fh_dup2(struct svc_fh *dst, struct svc_fh *src)
133{
134	fh_put(dst);
135	dget(src->fh_dentry);
136	if (src->fh_export)
137		exp_get(src->fh_export);
138	*dst = *src;
139}
140
141static __be32
142do_open_permission(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open *open, int accmode)
143{
144
145	if (open->op_truncate &&
146		!(open->op_share_access & NFS4_SHARE_ACCESS_WRITE))
147		return nfserr_inval;
148
149	accmode |= NFSD_MAY_READ_IF_EXEC;
150
151	if (open->op_share_access & NFS4_SHARE_ACCESS_READ)
152		accmode |= NFSD_MAY_READ;
153	if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE)
154		accmode |= (NFSD_MAY_WRITE | NFSD_MAY_TRUNC);
155	if (open->op_share_deny & NFS4_SHARE_DENY_READ)
156		accmode |= NFSD_MAY_WRITE;
157
158	return fh_verify(rqstp, current_fh, S_IFREG, accmode);
159}
160
161static __be32 nfsd_check_obj_isreg(struct svc_fh *fh)
162{
163	umode_t mode = d_inode(fh->fh_dentry)->i_mode;
164
165	if (S_ISREG(mode))
166		return nfs_ok;
167	if (S_ISDIR(mode))
168		return nfserr_isdir;
169	/*
170	 * Using err_symlink as our catch-all case may look odd; but
171	 * there's no other obvious error for this case in 4.0, and we
172	 * happen to know that it will cause the linux v4 client to do
173	 * the right thing on attempts to open something other than a
174	 * regular file.
175	 */
176	return nfserr_symlink;
177}
178
179static void nfsd4_set_open_owner_reply_cache(struct nfsd4_compound_state *cstate, struct nfsd4_open *open, struct svc_fh *resfh)
180{
181	if (nfsd4_has_session(cstate))
182		return;
183	fh_copy_shallow(&open->op_openowner->oo_owner.so_replay.rp_openfh,
184			&resfh->fh_handle);
185}
186
187static inline bool nfsd4_create_is_exclusive(int createmode)
188{
189	return createmode == NFS4_CREATE_EXCLUSIVE ||
190		createmode == NFS4_CREATE_EXCLUSIVE4_1;
191}
192
193static __be32
194nfsd4_vfs_create(struct svc_fh *fhp, struct dentry *child,
195		 struct nfsd4_open *open)
196{
197	struct file *filp;
198	struct path path;
199	int oflags;
200
201	oflags = O_CREAT | O_LARGEFILE;
202	switch (open->op_share_access & NFS4_SHARE_ACCESS_BOTH) {
203	case NFS4_SHARE_ACCESS_WRITE:
204		oflags |= O_WRONLY;
205		break;
206	case NFS4_SHARE_ACCESS_BOTH:
207		oflags |= O_RDWR;
208		break;
209	default:
210		oflags |= O_RDONLY;
211	}
212
213	path.mnt = fhp->fh_export->ex_path.mnt;
214	path.dentry = child;
215	filp = dentry_create(&path, oflags, open->op_iattr.ia_mode,
216			     current_cred());
217	if (IS_ERR(filp))
218		return nfserrno(PTR_ERR(filp));
219
220	open->op_filp = filp;
221	return nfs_ok;
222}
223
224/*
225 * Implement NFSv4's unchecked, guarded, and exclusive create
226 * semantics for regular files. Open state for this new file is
227 * subsequently fabricated in nfsd4_process_open2().
228 *
229 * Upon return, caller must release @fhp and @resfhp.
230 */
231static __be32
232nfsd4_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp,
233		  struct svc_fh *resfhp, struct nfsd4_open *open)
234{
235	struct iattr *iap = &open->op_iattr;
236	struct nfsd_attrs attrs = {
237		.na_iattr	= iap,
238		.na_seclabel	= &open->op_label,
239	};
240	struct dentry *parent, *child;
241	__u32 v_mtime, v_atime;
242	struct inode *inode;
243	__be32 status;
244	int host_err;
245
246	if (isdotent(open->op_fname, open->op_fnamelen))
247		return nfserr_exist;
248	if (!(iap->ia_valid & ATTR_MODE))
249		iap->ia_mode = 0;
250
251	status = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_EXEC);
252	if (status != nfs_ok)
253		return status;
254	parent = fhp->fh_dentry;
255	inode = d_inode(parent);
256
257	host_err = fh_want_write(fhp);
258	if (host_err)
259		return nfserrno(host_err);
260
261	if (is_create_with_attrs(open))
262		nfsd4_acl_to_attr(NF4REG, open->op_acl, &attrs);
263
264	inode_lock_nested(inode, I_MUTEX_PARENT);
265
266	child = lookup_one_len(open->op_fname, parent, open->op_fnamelen);
267	if (IS_ERR(child)) {
268		status = nfserrno(PTR_ERR(child));
269		goto out;
270	}
271
272	if (d_really_is_negative(child)) {
273		status = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_CREATE);
274		if (status != nfs_ok)
275			goto out;
276	}
277
278	status = fh_compose(resfhp, fhp->fh_export, child, fhp);
279	if (status != nfs_ok)
280		goto out;
281
282	v_mtime = 0;
283	v_atime = 0;
284	if (nfsd4_create_is_exclusive(open->op_createmode)) {
285		u32 *verifier = (u32 *)open->op_verf.data;
286
287		/*
288		 * Solaris 7 gets confused (bugid 4218508) if these have
289		 * the high bit set, as do xfs filesystems without the
290		 * "bigtime" feature. So just clear the high bits. If this
291		 * is ever changed to use different attrs for storing the
292		 * verifier, then do_open_lookup() will also need to be
293		 * fixed accordingly.
294		 */
295		v_mtime = verifier[0] & 0x7fffffff;
296		v_atime = verifier[1] & 0x7fffffff;
297	}
298
299	if (d_really_is_positive(child)) {
300		/* NFSv4 protocol requires change attributes even though
301		 * no change happened.
302		 */
303		status = fh_fill_both_attrs(fhp);
304		if (status != nfs_ok)
305			goto out;
306
307		switch (open->op_createmode) {
308		case NFS4_CREATE_UNCHECKED:
309			if (!d_is_reg(child))
310				break;
311
312			/*
313			 * In NFSv4, we don't want to truncate the file
314			 * now. This would be wrong if the OPEN fails for
315			 * some other reason. Furthermore, if the size is
316			 * nonzero, we should ignore it according to spec!
317			 */
318			open->op_truncate = (iap->ia_valid & ATTR_SIZE) &&
319						!iap->ia_size;
320			break;
321		case NFS4_CREATE_GUARDED:
322			status = nfserr_exist;
323			break;
324		case NFS4_CREATE_EXCLUSIVE:
325			if (d_inode(child)->i_mtime.tv_sec == v_mtime &&
326			    d_inode(child)->i_atime.tv_sec == v_atime &&
327			    d_inode(child)->i_size == 0) {
328				open->op_created = true;
329				break;		/* subtle */
330			}
331			status = nfserr_exist;
332			break;
333		case NFS4_CREATE_EXCLUSIVE4_1:
334			if (d_inode(child)->i_mtime.tv_sec == v_mtime &&
335			    d_inode(child)->i_atime.tv_sec == v_atime &&
336			    d_inode(child)->i_size == 0) {
337				open->op_created = true;
338				goto set_attr;	/* subtle */
339			}
340			status = nfserr_exist;
341		}
342		goto out;
343	}
344
345	if (!IS_POSIXACL(inode))
346		iap->ia_mode &= ~current_umask();
347
348	status = fh_fill_pre_attrs(fhp);
349	if (status != nfs_ok)
350		goto out;
351	status = nfsd4_vfs_create(fhp, child, open);
352	if (status != nfs_ok)
353		goto out;
354	open->op_created = true;
355	fh_fill_post_attrs(fhp);
356
357	/* A newly created file already has a file size of zero. */
358	if ((iap->ia_valid & ATTR_SIZE) && (iap->ia_size == 0))
359		iap->ia_valid &= ~ATTR_SIZE;
360	if (nfsd4_create_is_exclusive(open->op_createmode)) {
361		iap->ia_valid = ATTR_MTIME | ATTR_ATIME |
362				ATTR_MTIME_SET|ATTR_ATIME_SET;
363		iap->ia_mtime.tv_sec = v_mtime;
364		iap->ia_atime.tv_sec = v_atime;
365		iap->ia_mtime.tv_nsec = 0;
366		iap->ia_atime.tv_nsec = 0;
367	}
368
369set_attr:
370	status = nfsd_create_setattr(rqstp, fhp, resfhp, &attrs);
371
372	if (attrs.na_labelerr)
373		open->op_bmval[2] &= ~FATTR4_WORD2_SECURITY_LABEL;
374	if (attrs.na_aclerr)
375		open->op_bmval[0] &= ~FATTR4_WORD0_ACL;
376out:
377	inode_unlock(inode);
378	nfsd_attrs_free(&attrs);
379	if (child && !IS_ERR(child))
380		dput(child);
381	fh_drop_write(fhp);
382	return status;
383}
384
385/**
386 * set_change_info - set up the change_info4 for a reply
387 * @cinfo: pointer to nfsd4_change_info to be populated
388 * @fhp: pointer to svc_fh to use as source
389 *
390 * Many operations in NFSv4 require change_info4 in the reply. This function
391 * populates that from the info that we (should!) have already collected. In
392 * the event that we didn't get any pre-attrs, just zero out both.
393 */
394static void
395set_change_info(struct nfsd4_change_info *cinfo, struct svc_fh *fhp)
396{
397	cinfo->atomic = (u32)(fhp->fh_pre_saved && fhp->fh_post_saved && !fhp->fh_no_atomic_attr);
398	cinfo->before_change = fhp->fh_pre_change;
399	cinfo->after_change = fhp->fh_post_change;
400
401	/*
402	 * If fetching the pre-change attributes failed, then we should
403	 * have already failed the whole operation. We could have still
404	 * failed to fetch post-change attributes however.
405	 *
406	 * If we didn't get post-op attrs, just zero-out the after
407	 * field since we don't know what it should be. If the pre_saved
408	 * field isn't set for some reason, throw warning and just copy
409	 * whatever is in the after field.
410	 */
411	if (WARN_ON_ONCE(!fhp->fh_pre_saved))
412		cinfo->before_change = 0;
413	if (!fhp->fh_post_saved)
414		cinfo->after_change = cinfo->before_change + 1;
415}
416
417static __be32
418do_open_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_open *open, struct svc_fh **resfh)
419{
420	struct svc_fh *current_fh = &cstate->current_fh;
421	int accmode;
422	__be32 status;
423
424	*resfh = kmalloc(sizeof(struct svc_fh), GFP_KERNEL);
425	if (!*resfh)
426		return nfserr_jukebox;
427	fh_init(*resfh, NFS4_FHSIZE);
428	open->op_truncate = false;
429
430	if (open->op_create) {
431		/* FIXME: check session persistence and pnfs flags.
432		 * The nfsv4.1 spec requires the following semantics:
433		 *
434		 * Persistent   | pNFS   | Server REQUIRED | Client Allowed
435		 * Reply Cache  | server |                 |
436		 * -------------+--------+-----------------+--------------------
437		 * no           | no     | EXCLUSIVE4_1    | EXCLUSIVE4_1
438		 *              |        |                 | (SHOULD)
439		 *              |        | and EXCLUSIVE4  | or EXCLUSIVE4
440		 *              |        |                 | (SHOULD NOT)
441		 * no           | yes    | EXCLUSIVE4_1    | EXCLUSIVE4_1
442		 * yes          | no     | GUARDED4        | GUARDED4
443		 * yes          | yes    | GUARDED4        | GUARDED4
444		 */
445
446		current->fs->umask = open->op_umask;
447		status = nfsd4_create_file(rqstp, current_fh, *resfh, open);
448		current->fs->umask = 0;
449
450		/*
451		 * Following rfc 3530 14.2.16, and rfc 5661 18.16.4
452		 * use the returned bitmask to indicate which attributes
453		 * we used to store the verifier:
454		 */
455		if (nfsd4_create_is_exclusive(open->op_createmode) && status == 0)
456			open->op_bmval[1] |= (FATTR4_WORD1_TIME_ACCESS |
457						FATTR4_WORD1_TIME_MODIFY);
458	} else {
459		status = nfsd_lookup(rqstp, current_fh,
460				     open->op_fname, open->op_fnamelen, *resfh);
461		if (status == nfs_ok)
462			/* NFSv4 protocol requires change attributes even though
463			 * no change happened.
464			 */
465			status = fh_fill_both_attrs(current_fh);
466	}
467	if (status)
468		goto out;
469	status = nfsd_check_obj_isreg(*resfh);
470	if (status)
471		goto out;
472
473	nfsd4_set_open_owner_reply_cache(cstate, open, *resfh);
474	accmode = NFSD_MAY_NOP;
475	if (open->op_created ||
476			open->op_claim_type == NFS4_OPEN_CLAIM_DELEGATE_CUR)
477		accmode |= NFSD_MAY_OWNER_OVERRIDE;
478	status = do_open_permission(rqstp, *resfh, open, accmode);
479	set_change_info(&open->op_cinfo, current_fh);
480out:
481	return status;
482}
483
484static __be32
485do_open_fhandle(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_open *open)
486{
487	struct svc_fh *current_fh = &cstate->current_fh;
488	int accmode = 0;
489
490	/* We don't know the target directory, and therefore can not
491	* set the change info
492	*/
493
494	memset(&open->op_cinfo, 0, sizeof(struct nfsd4_change_info));
495
496	nfsd4_set_open_owner_reply_cache(cstate, open, current_fh);
497
498	open->op_truncate = (open->op_iattr.ia_valid & ATTR_SIZE) &&
499		(open->op_iattr.ia_size == 0);
500	/*
501	 * In the delegation case, the client is telling us about an
502	 * open that it *already* performed locally, some time ago.  We
503	 * should let it succeed now if possible.
504	 *
505	 * In the case of a CLAIM_FH open, on the other hand, the client
506	 * may be counting on us to enforce permissions (the Linux 4.1
507	 * client uses this for normal opens, for example).
508	 */
509	if (open->op_claim_type == NFS4_OPEN_CLAIM_DELEG_CUR_FH)
510		accmode = NFSD_MAY_OWNER_OVERRIDE;
511
512	return do_open_permission(rqstp, current_fh, open, accmode);
513}
514
515static void
516copy_clientid(clientid_t *clid, struct nfsd4_session *session)
517{
518	struct nfsd4_sessionid *sid =
519			(struct nfsd4_sessionid *)session->se_sessionid.data;
520
521	clid->cl_boot = sid->clientid.cl_boot;
522	clid->cl_id = sid->clientid.cl_id;
523}
524
525static __be32
526nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
527	   union nfsd4_op_u *u)
528{
529	struct nfsd4_open *open = &u->open;
530	__be32 status;
531	struct svc_fh *resfh = NULL;
532	struct net *net = SVC_NET(rqstp);
533	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
534	bool reclaim = false;
535
536	dprintk("NFSD: nfsd4_open filename %.*s op_openowner %p\n",
537		(int)open->op_fnamelen, open->op_fname,
538		open->op_openowner);
539
540	open->op_filp = NULL;
541	open->op_rqstp = rqstp;
542
543	/* This check required by spec. */
544	if (open->op_create && open->op_claim_type != NFS4_OPEN_CLAIM_NULL)
545		return nfserr_inval;
546
547	open->op_created = false;
548	/*
549	 * RFC5661 18.51.3
550	 * Before RECLAIM_COMPLETE done, server should deny new lock
551	 */
552	if (nfsd4_has_session(cstate) &&
553	    !test_bit(NFSD4_CLIENT_RECLAIM_COMPLETE, &cstate->clp->cl_flags) &&
554	    open->op_claim_type != NFS4_OPEN_CLAIM_PREVIOUS)
555		return nfserr_grace;
556
557	if (nfsd4_has_session(cstate))
558		copy_clientid(&open->op_clientid, cstate->session);
559
560	/* check seqid for replay. set nfs4_owner */
561	status = nfsd4_process_open1(cstate, open, nn);
562	if (status == nfserr_replay_me) {
563		struct nfs4_replay *rp = &open->op_openowner->oo_owner.so_replay;
564		fh_put(&cstate->current_fh);
565		fh_copy_shallow(&cstate->current_fh.fh_handle,
566				&rp->rp_openfh);
567		status = fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_NOP);
568		if (status)
569			dprintk("nfsd4_open: replay failed"
570				" restoring previous filehandle\n");
571		else
572			status = nfserr_replay_me;
573	}
574	if (status)
575		goto out;
576	if (open->op_xdr_error) {
577		status = open->op_xdr_error;
578		goto out;
579	}
580
581	status = nfsd4_check_open_attributes(rqstp, cstate, open);
582	if (status)
583		goto out;
584
585	/* Openowner is now set, so sequence id will get bumped.  Now we need
586	 * these checks before we do any creates: */
587	status = nfserr_grace;
588	if (opens_in_grace(net) && open->op_claim_type != NFS4_OPEN_CLAIM_PREVIOUS)
589		goto out;
590	status = nfserr_no_grace;
591	if (!opens_in_grace(net) && open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS)
592		goto out;
593
594	switch (open->op_claim_type) {
595	case NFS4_OPEN_CLAIM_DELEGATE_CUR:
596	case NFS4_OPEN_CLAIM_NULL:
597		status = do_open_lookup(rqstp, cstate, open, &resfh);
598		if (status)
599			goto out;
600		break;
601	case NFS4_OPEN_CLAIM_PREVIOUS:
602		status = nfs4_check_open_reclaim(cstate->clp);
603		if (status)
604			goto out;
605		open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED;
606		reclaim = true;
607		fallthrough;
608	case NFS4_OPEN_CLAIM_FH:
609	case NFS4_OPEN_CLAIM_DELEG_CUR_FH:
610		status = do_open_fhandle(rqstp, cstate, open);
611		if (status)
612			goto out;
613		resfh = &cstate->current_fh;
614		break;
615	case NFS4_OPEN_CLAIM_DELEG_PREV_FH:
616	case NFS4_OPEN_CLAIM_DELEGATE_PREV:
617		status = nfserr_notsupp;
618		goto out;
619	default:
620		status = nfserr_inval;
621		goto out;
622	}
623
624	status = nfsd4_process_open2(rqstp, resfh, open);
625	if (status && open->op_created)
626		pr_warn("nfsd4_process_open2 failed to open newly-created file: status=%u\n",
627			be32_to_cpu(status));
628	if (reclaim && !status)
629		nn->somebody_reclaimed = true;
630out:
631	if (open->op_filp) {
632		fput(open->op_filp);
633		open->op_filp = NULL;
634	}
635	if (resfh && resfh != &cstate->current_fh) {
636		fh_dup2(&cstate->current_fh, resfh);
637		fh_put(resfh);
638		kfree(resfh);
639	}
640	nfsd4_cleanup_open_state(cstate, open);
641	nfsd4_bump_seqid(cstate, status);
642	return status;
643}
644
645/*
646 * OPEN is the only seqid-mutating operation whose decoding can fail
647 * with a seqid-mutating error (specifically, decoding of user names in
648 * the attributes).  Therefore we have to do some processing to look up
649 * the stateowner so that we can bump the seqid.
650 */
651static __be32 nfsd4_open_omfg(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_op *op)
652{
653	struct nfsd4_open *open = &op->u.open;
654
655	if (!seqid_mutating_err(ntohl(op->status)))
656		return op->status;
657	if (nfsd4_has_session(cstate))
658		return op->status;
659	open->op_xdr_error = op->status;
660	return nfsd4_open(rqstp, cstate, &op->u);
661}
662
663/*
664 * filehandle-manipulating ops.
665 */
666static __be32
667nfsd4_getfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
668	    union nfsd4_op_u *u)
669{
670	u->getfh = &cstate->current_fh;
671	return nfs_ok;
672}
673
674static __be32
675nfsd4_putfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
676	    union nfsd4_op_u *u)
677{
678	struct nfsd4_putfh *putfh = &u->putfh;
679	__be32 ret;
680
681	fh_put(&cstate->current_fh);
682	cstate->current_fh.fh_handle.fh_size = putfh->pf_fhlen;
683	memcpy(&cstate->current_fh.fh_handle.fh_raw, putfh->pf_fhval,
684	       putfh->pf_fhlen);
685	ret = fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_BYPASS_GSS);
686#ifdef CONFIG_NFSD_V4_2_INTER_SSC
687	if (ret == nfserr_stale && putfh->no_verify) {
688		SET_FH_FLAG(&cstate->current_fh, NFSD4_FH_FOREIGN);
689		ret = 0;
690	}
691#endif
692	return ret;
693}
694
695static __be32
696nfsd4_putrootfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
697		union nfsd4_op_u *u)
698{
699	fh_put(&cstate->current_fh);
700
701	return exp_pseudoroot(rqstp, &cstate->current_fh);
702}
703
704static __be32
705nfsd4_restorefh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
706		union nfsd4_op_u *u)
707{
708	if (!cstate->save_fh.fh_dentry)
709		return nfserr_restorefh;
710
711	fh_dup2(&cstate->current_fh, &cstate->save_fh);
712	if (HAS_CSTATE_FLAG(cstate, SAVED_STATE_ID_FLAG)) {
713		memcpy(&cstate->current_stateid, &cstate->save_stateid, sizeof(stateid_t));
714		SET_CSTATE_FLAG(cstate, CURRENT_STATE_ID_FLAG);
715	}
716	return nfs_ok;
717}
718
719static __be32
720nfsd4_savefh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
721	     union nfsd4_op_u *u)
722{
723	fh_dup2(&cstate->save_fh, &cstate->current_fh);
724	if (HAS_CSTATE_FLAG(cstate, CURRENT_STATE_ID_FLAG)) {
725		memcpy(&cstate->save_stateid, &cstate->current_stateid, sizeof(stateid_t));
726		SET_CSTATE_FLAG(cstate, SAVED_STATE_ID_FLAG);
727	}
728	return nfs_ok;
729}
730
731/*
732 * misc nfsv4 ops
733 */
734static __be32
735nfsd4_access(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
736	     union nfsd4_op_u *u)
737{
738	struct nfsd4_access *access = &u->access;
739	u32 access_full;
740
741	access_full = NFS3_ACCESS_FULL;
742	if (cstate->minorversion >= 2)
743		access_full |= NFS4_ACCESS_XALIST | NFS4_ACCESS_XAREAD |
744			       NFS4_ACCESS_XAWRITE;
745
746	if (access->ac_req_access & ~access_full)
747		return nfserr_inval;
748
749	access->ac_resp_access = access->ac_req_access;
750	return nfsd_access(rqstp, &cstate->current_fh, &access->ac_resp_access,
751			   &access->ac_supported);
752}
753
754static void gen_boot_verifier(nfs4_verifier *verifier, struct net *net)
755{
756	__be32 *verf = (__be32 *)verifier->data;
757
758	BUILD_BUG_ON(2*sizeof(*verf) != sizeof(verifier->data));
759
760	nfsd_copy_write_verifier(verf, net_generic(net, nfsd_net_id));
761}
762
763static __be32
764nfsd4_commit(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
765	     union nfsd4_op_u *u)
766{
767	struct nfsd4_commit *commit = &u->commit;
768	struct nfsd_file *nf;
769	__be32 status;
770
771	status = nfsd_file_acquire(rqstp, &cstate->current_fh, NFSD_MAY_WRITE |
772				   NFSD_MAY_NOT_BREAK_LEASE, &nf);
773	if (status != nfs_ok)
774		return status;
775
776	status = nfsd_commit(rqstp, &cstate->current_fh, nf, commit->co_offset,
777			     commit->co_count,
778			     (__be32 *)commit->co_verf.data);
779	nfsd_file_put(nf);
780	return status;
781}
782
783static __be32
784nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
785	     union nfsd4_op_u *u)
786{
787	struct nfsd4_create *create = &u->create;
788	struct nfsd_attrs attrs = {
789		.na_iattr	= &create->cr_iattr,
790		.na_seclabel	= &create->cr_label,
791	};
792	struct svc_fh resfh;
793	__be32 status;
794	dev_t rdev;
795
796	fh_init(&resfh, NFS4_FHSIZE);
797
798	status = fh_verify(rqstp, &cstate->current_fh, S_IFDIR, NFSD_MAY_NOP);
799	if (status)
800		return status;
801
802	status = check_attr_support(rqstp, cstate, create->cr_bmval,
803				    nfsd_attrmask);
804	if (status)
805		return status;
806
807	status = nfsd4_acl_to_attr(create->cr_type, create->cr_acl, &attrs);
808	current->fs->umask = create->cr_umask;
809	switch (create->cr_type) {
810	case NF4LNK:
811		status = nfsd_symlink(rqstp, &cstate->current_fh,
812				      create->cr_name, create->cr_namelen,
813				      create->cr_data, &attrs, &resfh);
814		break;
815
816	case NF4BLK:
817		status = nfserr_inval;
818		rdev = MKDEV(create->cr_specdata1, create->cr_specdata2);
819		if (MAJOR(rdev) != create->cr_specdata1 ||
820		    MINOR(rdev) != create->cr_specdata2)
821			goto out_umask;
822		status = nfsd_create(rqstp, &cstate->current_fh,
823				     create->cr_name, create->cr_namelen,
824				     &attrs, S_IFBLK, rdev, &resfh);
825		break;
826
827	case NF4CHR:
828		status = nfserr_inval;
829		rdev = MKDEV(create->cr_specdata1, create->cr_specdata2);
830		if (MAJOR(rdev) != create->cr_specdata1 ||
831		    MINOR(rdev) != create->cr_specdata2)
832			goto out_umask;
833		status = nfsd_create(rqstp, &cstate->current_fh,
834				     create->cr_name, create->cr_namelen,
835				     &attrs, S_IFCHR, rdev, &resfh);
836		break;
837
838	case NF4SOCK:
839		status = nfsd_create(rqstp, &cstate->current_fh,
840				     create->cr_name, create->cr_namelen,
841				     &attrs, S_IFSOCK, 0, &resfh);
842		break;
843
844	case NF4FIFO:
845		status = nfsd_create(rqstp, &cstate->current_fh,
846				     create->cr_name, create->cr_namelen,
847				     &attrs, S_IFIFO, 0, &resfh);
848		break;
849
850	case NF4DIR:
851		create->cr_iattr.ia_valid &= ~ATTR_SIZE;
852		status = nfsd_create(rqstp, &cstate->current_fh,
853				     create->cr_name, create->cr_namelen,
854				     &attrs, S_IFDIR, 0, &resfh);
855		break;
856
857	default:
858		status = nfserr_badtype;
859	}
860
861	if (status)
862		goto out;
863
864	if (attrs.na_labelerr)
865		create->cr_bmval[2] &= ~FATTR4_WORD2_SECURITY_LABEL;
866	if (attrs.na_aclerr)
867		create->cr_bmval[0] &= ~FATTR4_WORD0_ACL;
868	set_change_info(&create->cr_cinfo, &cstate->current_fh);
869	fh_dup2(&cstate->current_fh, &resfh);
870out:
871	fh_put(&resfh);
872out_umask:
873	current->fs->umask = 0;
874	nfsd_attrs_free(&attrs);
875	return status;
876}
877
878static __be32
879nfsd4_getattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
880	      union nfsd4_op_u *u)
881{
882	struct nfsd4_getattr *getattr = &u->getattr;
883	__be32 status;
884
885	status = fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_NOP);
886	if (status)
887		return status;
888
889	if (getattr->ga_bmval[1] & NFSD_WRITEONLY_ATTRS_WORD1)
890		return nfserr_inval;
891
892	getattr->ga_bmval[0] &= nfsd_suppattrs[cstate->minorversion][0];
893	getattr->ga_bmval[1] &= nfsd_suppattrs[cstate->minorversion][1];
894	getattr->ga_bmval[2] &= nfsd_suppattrs[cstate->minorversion][2];
895
896	getattr->ga_fhp = &cstate->current_fh;
897	return nfs_ok;
898}
899
900static __be32
901nfsd4_link(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
902	   union nfsd4_op_u *u)
903{
904	struct nfsd4_link *link = &u->link;
905	__be32 status;
906
907	status = nfsd_link(rqstp, &cstate->current_fh,
908			   link->li_name, link->li_namelen, &cstate->save_fh);
909	if (!status)
910		set_change_info(&link->li_cinfo, &cstate->current_fh);
911	return status;
912}
913
914static __be32 nfsd4_do_lookupp(struct svc_rqst *rqstp, struct svc_fh *fh)
915{
916	struct svc_fh tmp_fh;
917	__be32 ret;
918
919	fh_init(&tmp_fh, NFS4_FHSIZE);
920	ret = exp_pseudoroot(rqstp, &tmp_fh);
921	if (ret)
922		return ret;
923	if (tmp_fh.fh_dentry == fh->fh_dentry) {
924		fh_put(&tmp_fh);
925		return nfserr_noent;
926	}
927	fh_put(&tmp_fh);
928	return nfsd_lookup(rqstp, fh, "..", 2, fh);
929}
930
931static __be32
932nfsd4_lookupp(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
933	      union nfsd4_op_u *u)
934{
935	return nfsd4_do_lookupp(rqstp, &cstate->current_fh);
936}
937
938static __be32
939nfsd4_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
940	     union nfsd4_op_u *u)
941{
942	return nfsd_lookup(rqstp, &cstate->current_fh,
943			   u->lookup.lo_name, u->lookup.lo_len,
944			   &cstate->current_fh);
945}
946
947static __be32
948nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
949	   union nfsd4_op_u *u)
950{
951	struct nfsd4_read *read = &u->read;
952	__be32 status;
953
954	read->rd_nf = NULL;
955
956	trace_nfsd_read_start(rqstp, &cstate->current_fh,
957			      read->rd_offset, read->rd_length);
958
959	read->rd_length = min_t(u32, read->rd_length, svc_max_payload(rqstp));
960	if (read->rd_offset > (u64)OFFSET_MAX)
961		read->rd_offset = (u64)OFFSET_MAX;
962	if (read->rd_offset + read->rd_length > (u64)OFFSET_MAX)
963		read->rd_length = (u64)OFFSET_MAX - read->rd_offset;
964
965	/*
966	 * If we do a zero copy read, then a client will see read data
967	 * that reflects the state of the file *after* performing the
968	 * following compound.
969	 *
970	 * To ensure proper ordering, we therefore turn off zero copy if
971	 * the client wants us to do more in this compound:
972	 */
973	if (!nfsd4_last_compound_op(rqstp))
974		clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
975
976	/* check stateid */
977	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
978					&read->rd_stateid, RD_STATE,
979					&read->rd_nf, NULL);
980
981	read->rd_rqstp = rqstp;
982	read->rd_fhp = &cstate->current_fh;
983	return status;
984}
985
986
987static void
988nfsd4_read_release(union nfsd4_op_u *u)
989{
990	if (u->read.rd_nf)
991		nfsd_file_put(u->read.rd_nf);
992	trace_nfsd_read_done(u->read.rd_rqstp, u->read.rd_fhp,
993			     u->read.rd_offset, u->read.rd_length);
994}
995
996static __be32
997nfsd4_readdir(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
998	      union nfsd4_op_u *u)
999{
1000	struct nfsd4_readdir *readdir = &u->readdir;
1001	u64 cookie = readdir->rd_cookie;
1002	static const nfs4_verifier zeroverf;
1003
1004	/* no need to check permission - this will be done in nfsd_readdir() */
1005
1006	if (readdir->rd_bmval[1] & NFSD_WRITEONLY_ATTRS_WORD1)
1007		return nfserr_inval;
1008
1009	readdir->rd_bmval[0] &= nfsd_suppattrs[cstate->minorversion][0];
1010	readdir->rd_bmval[1] &= nfsd_suppattrs[cstate->minorversion][1];
1011	readdir->rd_bmval[2] &= nfsd_suppattrs[cstate->minorversion][2];
1012
1013	if ((cookie == 1) || (cookie == 2) ||
1014	    (cookie == 0 && memcmp(readdir->rd_verf.data, zeroverf.data, NFS4_VERIFIER_SIZE)))
1015		return nfserr_bad_cookie;
1016
1017	readdir->rd_rqstp = rqstp;
1018	readdir->rd_fhp = &cstate->current_fh;
1019	return nfs_ok;
1020}
1021
1022static __be32
1023nfsd4_readlink(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
1024	       union nfsd4_op_u *u)
1025{
1026	u->readlink.rl_rqstp = rqstp;
1027	u->readlink.rl_fhp = &cstate->current_fh;
1028	return nfs_ok;
1029}
1030
1031static __be32
1032nfsd4_remove(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
1033	     union nfsd4_op_u *u)
1034{
1035	struct nfsd4_remove *remove = &u->remove;
1036	__be32 status;
1037
1038	if (opens_in_grace(SVC_NET(rqstp)))
1039		return nfserr_grace;
1040	status = nfsd_unlink(rqstp, &cstate->current_fh, 0,
1041			     remove->rm_name, remove->rm_namelen);
1042	if (!status)
1043		set_change_info(&remove->rm_cinfo, &cstate->current_fh);
1044	return status;
1045}
1046
1047static __be32
1048nfsd4_rename(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
1049	     union nfsd4_op_u *u)
1050{
1051	struct nfsd4_rename *rename = &u->rename;
1052	__be32 status;
1053
1054	if (opens_in_grace(SVC_NET(rqstp)))
1055		return nfserr_grace;
1056	status = nfsd_rename(rqstp, &cstate->save_fh, rename->rn_sname,
1057			     rename->rn_snamelen, &cstate->current_fh,
1058			     rename->rn_tname, rename->rn_tnamelen);
1059	if (status)
1060		return status;
1061	set_change_info(&rename->rn_sinfo, &cstate->save_fh);
1062	set_change_info(&rename->rn_tinfo, &cstate->current_fh);
1063	return nfs_ok;
1064}
1065
1066static __be32
1067nfsd4_secinfo(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
1068	      union nfsd4_op_u *u)
1069{
1070	struct nfsd4_secinfo *secinfo = &u->secinfo;
1071	struct svc_export *exp;
1072	struct dentry *dentry;
1073	__be32 err;
1074
1075	err = fh_verify(rqstp, &cstate->current_fh, S_IFDIR, NFSD_MAY_EXEC);
1076	if (err)
1077		return err;
1078	err = nfsd_lookup_dentry(rqstp, &cstate->current_fh,
1079				    secinfo->si_name, secinfo->si_namelen,
1080				    &exp, &dentry);
1081	if (err)
1082		return err;
1083	if (d_really_is_negative(dentry)) {
1084		exp_put(exp);
1085		err = nfserr_noent;
1086	} else
1087		secinfo->si_exp = exp;
1088	dput(dentry);
1089	if (cstate->minorversion)
1090		/* See rfc 5661 section 2.6.3.1.1.8 */
1091		fh_put(&cstate->current_fh);
1092	return err;
1093}
1094
1095static __be32
1096nfsd4_secinfo_no_name(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
1097		union nfsd4_op_u *u)
1098{
1099	__be32 err;
1100
1101	switch (u->secinfo_no_name.sin_style) {
1102	case NFS4_SECINFO_STYLE4_CURRENT_FH:
1103		break;
1104	case NFS4_SECINFO_STYLE4_PARENT:
1105		err = nfsd4_do_lookupp(rqstp, &cstate->current_fh);
1106		if (err)
1107			return err;
1108		break;
1109	default:
1110		return nfserr_inval;
1111	}
1112
1113	u->secinfo_no_name.sin_exp = exp_get(cstate->current_fh.fh_export);
1114	fh_put(&cstate->current_fh);
1115	return nfs_ok;
1116}
1117
1118static void
1119nfsd4_secinfo_release(union nfsd4_op_u *u)
1120{
1121	if (u->secinfo.si_exp)
1122		exp_put(u->secinfo.si_exp);
1123}
1124
1125static void
1126nfsd4_secinfo_no_name_release(union nfsd4_op_u *u)
1127{
1128	if (u->secinfo_no_name.sin_exp)
1129		exp_put(u->secinfo_no_name.sin_exp);
1130}
1131
1132static __be32
1133nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
1134	      union nfsd4_op_u *u)
1135{
1136	struct nfsd4_setattr *setattr = &u->setattr;
1137	struct nfsd_attrs attrs = {
1138		.na_iattr	= &setattr->sa_iattr,
1139		.na_seclabel	= &setattr->sa_label,
1140	};
1141	struct inode *inode;
1142	__be32 status = nfs_ok;
1143	int err;
1144
1145	if (setattr->sa_iattr.ia_valid & ATTR_SIZE) {
1146		status = nfs4_preprocess_stateid_op(rqstp, cstate,
1147				&cstate->current_fh, &setattr->sa_stateid,
1148				WR_STATE, NULL, NULL);
1149		if (status)
1150			return status;
1151	}
1152	err = fh_want_write(&cstate->current_fh);
1153	if (err)
1154		return nfserrno(err);
1155	status = nfs_ok;
1156
1157	status = check_attr_support(rqstp, cstate, setattr->sa_bmval,
1158				    nfsd_attrmask);
1159	if (status)
1160		goto out;
1161
1162	inode = cstate->current_fh.fh_dentry->d_inode;
1163	status = nfsd4_acl_to_attr(S_ISDIR(inode->i_mode) ? NF4DIR : NF4REG,
1164				   setattr->sa_acl, &attrs);
1165
1166	if (status)
1167		goto out;
1168	status = nfsd_setattr(rqstp, &cstate->current_fh, &attrs,
1169				0, (time64_t)0);
1170	if (!status)
1171		status = nfserrno(attrs.na_labelerr);
1172	if (!status)
1173		status = nfserrno(attrs.na_aclerr);
1174out:
1175	nfsd_attrs_free(&attrs);
1176	fh_drop_write(&cstate->current_fh);
1177	return status;
1178}
1179
1180static __be32
1181nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
1182	    union nfsd4_op_u *u)
1183{
1184	struct nfsd4_write *write = &u->write;
1185	stateid_t *stateid = &write->wr_stateid;
1186	struct nfsd_file *nf = NULL;
1187	__be32 status = nfs_ok;
1188	unsigned long cnt;
1189	int nvecs;
1190
1191	if (write->wr_offset > (u64)OFFSET_MAX ||
1192	    write->wr_offset + write->wr_buflen > (u64)OFFSET_MAX)
1193		return nfserr_fbig;
1194
1195	cnt = write->wr_buflen;
1196	trace_nfsd_write_start(rqstp, &cstate->current_fh,
1197			       write->wr_offset, cnt);
1198	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
1199						stateid, WR_STATE, &nf, NULL);
1200	if (status)
1201		return status;
1202
1203	write->wr_how_written = write->wr_stable_how;
1204
1205	nvecs = svc_fill_write_vector(rqstp, &write->wr_payload);
1206	WARN_ON_ONCE(nvecs > ARRAY_SIZE(rqstp->rq_vec));
1207
1208	status = nfsd_vfs_write(rqstp, &cstate->current_fh, nf,
1209				write->wr_offset, rqstp->rq_vec, nvecs, &cnt,
1210				write->wr_how_written,
1211				(__be32 *)write->wr_verifier.data);
1212	nfsd_file_put(nf);
1213
1214	write->wr_bytes_written = cnt;
1215	trace_nfsd_write_done(rqstp, &cstate->current_fh,
1216			      write->wr_offset, cnt);
1217	return status;
1218}
1219
1220static __be32
1221nfsd4_verify_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
1222		  stateid_t *src_stateid, struct nfsd_file **src,
1223		  stateid_t *dst_stateid, struct nfsd_file **dst)
1224{
1225	__be32 status;
1226
1227	if (!cstate->save_fh.fh_dentry)
1228		return nfserr_nofilehandle;
1229
1230	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->save_fh,
1231					    src_stateid, RD_STATE, src, NULL);
1232	if (status)
1233		goto out;
1234
1235	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
1236					    dst_stateid, WR_STATE, dst, NULL);
1237	if (status)
1238		goto out_put_src;
1239
1240	/* fix up for NFS-specific error code */
1241	if (!S_ISREG(file_inode((*src)->nf_file)->i_mode) ||
1242	    !S_ISREG(file_inode((*dst)->nf_file)->i_mode)) {
1243		status = nfserr_wrong_type;
1244		goto out_put_dst;
1245	}
1246
1247out:
1248	return status;
1249out_put_dst:
1250	nfsd_file_put(*dst);
1251	*dst = NULL;
1252out_put_src:
1253	nfsd_file_put(*src);
1254	*src = NULL;
1255	goto out;
1256}
1257
1258static __be32
1259nfsd4_clone(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
1260		union nfsd4_op_u *u)
1261{
1262	struct nfsd4_clone *clone = &u->clone;
1263	struct nfsd_file *src, *dst;
1264	__be32 status;
1265
1266	status = nfsd4_verify_copy(rqstp, cstate, &clone->cl_src_stateid, &src,
1267				   &clone->cl_dst_stateid, &dst);
1268	if (status)
1269		goto out;
1270
1271	status = nfsd4_clone_file_range(rqstp, src, clone->cl_src_pos,
1272			dst, clone->cl_dst_pos, clone->cl_count,
1273			EX_ISSYNC(cstate->current_fh.fh_export));
1274
1275	nfsd_file_put(dst);
1276	nfsd_file_put(src);
1277out:
1278	return status;
1279}
1280
1281static void nfs4_put_copy(struct nfsd4_copy *copy)
1282{
1283	if (!refcount_dec_and_test(&copy->refcount))
1284		return;
1285	kfree(copy->cp_src);
1286	kfree(copy);
1287}
1288
1289static void nfsd4_stop_copy(struct nfsd4_copy *copy)
1290{
1291	if (!test_and_set_bit(NFSD4_COPY_F_STOPPED, &copy->cp_flags))
1292		kthread_stop(copy->copy_task);
1293	nfs4_put_copy(copy);
1294}
1295
1296static struct nfsd4_copy *nfsd4_get_copy(struct nfs4_client *clp)
1297{
1298	struct nfsd4_copy *copy = NULL;
1299
1300	spin_lock(&clp->async_lock);
1301	if (!list_empty(&clp->async_copies)) {
1302		copy = list_first_entry(&clp->async_copies, struct nfsd4_copy,
1303					copies);
1304		refcount_inc(&copy->refcount);
1305	}
1306	spin_unlock(&clp->async_lock);
1307	return copy;
1308}
1309
1310void nfsd4_shutdown_copy(struct nfs4_client *clp)
1311{
1312	struct nfsd4_copy *copy;
1313
1314	while ((copy = nfsd4_get_copy(clp)) != NULL)
1315		nfsd4_stop_copy(copy);
1316}
1317#ifdef CONFIG_NFSD_V4_2_INTER_SSC
1318
1319extern struct file *nfs42_ssc_open(struct vfsmount *ss_mnt,
1320				   struct nfs_fh *src_fh,
1321				   nfs4_stateid *stateid);
1322extern void nfs42_ssc_close(struct file *filep);
1323
1324extern void nfs_sb_deactive(struct super_block *sb);
1325
1326#define NFSD42_INTERSSC_MOUNTOPS "vers=4.2,addr=%s,sec=sys"
1327
1328/*
1329 * setup a work entry in the ssc delayed unmount list.
1330 */
1331static __be32 nfsd4_ssc_setup_dul(struct nfsd_net *nn, char *ipaddr,
1332				  struct nfsd4_ssc_umount_item **nsui)
1333{
1334	struct nfsd4_ssc_umount_item *ni = NULL;
1335	struct nfsd4_ssc_umount_item *work = NULL;
1336	struct nfsd4_ssc_umount_item *tmp;
1337	DEFINE_WAIT(wait);
1338	__be32 status = 0;
1339
1340	*nsui = NULL;
1341	work = kzalloc(sizeof(*work), GFP_KERNEL);
1342try_again:
1343	spin_lock(&nn->nfsd_ssc_lock);
1344	list_for_each_entry_safe(ni, tmp, &nn->nfsd_ssc_mount_list, nsui_list) {
1345		if (strncmp(ni->nsui_ipaddr, ipaddr, sizeof(ni->nsui_ipaddr)))
1346			continue;
1347		/* found a match */
1348		if (ni->nsui_busy) {
1349			/*  wait - and try again */
1350			prepare_to_wait(&nn->nfsd_ssc_waitq, &wait, TASK_IDLE);
1351			spin_unlock(&nn->nfsd_ssc_lock);
1352
1353			/* allow 20secs for mount/unmount for now - revisit */
1354			if (kthread_should_stop() ||
1355					(schedule_timeout(20*HZ) == 0)) {
1356				finish_wait(&nn->nfsd_ssc_waitq, &wait);
1357				kfree(work);
1358				return nfserr_eagain;
1359			}
1360			finish_wait(&nn->nfsd_ssc_waitq, &wait);
1361			goto try_again;
1362		}
1363		*nsui = ni;
1364		refcount_inc(&ni->nsui_refcnt);
1365		spin_unlock(&nn->nfsd_ssc_lock);
1366		kfree(work);
1367
1368		/* return vfsmount in (*nsui)->nsui_vfsmount */
1369		return 0;
1370	}
1371	if (work) {
1372		strscpy(work->nsui_ipaddr, ipaddr, sizeof(work->nsui_ipaddr) - 1);
1373		refcount_set(&work->nsui_refcnt, 2);
1374		work->nsui_busy = true;
1375		list_add_tail(&work->nsui_list, &nn->nfsd_ssc_mount_list);
1376		*nsui = work;
1377	} else
1378		status = nfserr_resource;
1379	spin_unlock(&nn->nfsd_ssc_lock);
1380	return status;
1381}
1382
1383static void nfsd4_ssc_update_dul(struct nfsd_net *nn,
1384				 struct nfsd4_ssc_umount_item *nsui,
1385				 struct vfsmount *ss_mnt)
1386{
1387	spin_lock(&nn->nfsd_ssc_lock);
1388	nsui->nsui_vfsmount = ss_mnt;
1389	nsui->nsui_busy = false;
1390	wake_up_all(&nn->nfsd_ssc_waitq);
1391	spin_unlock(&nn->nfsd_ssc_lock);
1392}
1393
1394static void nfsd4_ssc_cancel_dul(struct nfsd_net *nn,
1395				 struct nfsd4_ssc_umount_item *nsui)
1396{
1397	spin_lock(&nn->nfsd_ssc_lock);
1398	list_del(&nsui->nsui_list);
1399	wake_up_all(&nn->nfsd_ssc_waitq);
1400	spin_unlock(&nn->nfsd_ssc_lock);
1401	kfree(nsui);
1402}
1403
1404/*
1405 * Support one copy source server for now.
1406 */
1407static __be32
1408nfsd4_interssc_connect(struct nl4_server *nss, struct svc_rqst *rqstp,
1409		       struct nfsd4_ssc_umount_item **nsui)
1410{
1411	struct file_system_type *type;
1412	struct vfsmount *ss_mnt;
1413	struct nfs42_netaddr *naddr;
1414	struct sockaddr_storage tmp_addr;
1415	size_t tmp_addrlen, match_netid_len = 3;
1416	char *startsep = "", *endsep = "", *match_netid = "tcp";
1417	char *ipaddr, *dev_name, *raw_data;
1418	int len, raw_len;
1419	__be32 status = nfserr_inval;
1420	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
1421
1422	naddr = &nss->u.nl4_addr;
1423	tmp_addrlen = rpc_uaddr2sockaddr(SVC_NET(rqstp), naddr->addr,
1424					 naddr->addr_len,
1425					 (struct sockaddr *)&tmp_addr,
1426					 sizeof(tmp_addr));
1427	*nsui = NULL;
1428	if (tmp_addrlen == 0)
1429		goto out_err;
1430
1431	if (tmp_addr.ss_family == AF_INET6) {
1432		startsep = "[";
1433		endsep = "]";
1434		match_netid = "tcp6";
1435		match_netid_len = 4;
1436	}
1437
1438	if (naddr->netid_len != match_netid_len ||
1439		strncmp(naddr->netid, match_netid, naddr->netid_len))
1440		goto out_err;
1441
1442	/* Construct the raw data for the vfs_kern_mount call */
1443	len = RPC_MAX_ADDRBUFLEN + 1;
1444	ipaddr = kzalloc(len, GFP_KERNEL);
1445	if (!ipaddr)
1446		goto out_err;
1447
1448	rpc_ntop((struct sockaddr *)&tmp_addr, ipaddr, len);
1449
1450	/* 2 for ipv6 endsep and startsep. 3 for ":/" and trailing '/0'*/
1451
1452	raw_len = strlen(NFSD42_INTERSSC_MOUNTOPS) + strlen(ipaddr);
1453	raw_data = kzalloc(raw_len, GFP_KERNEL);
1454	if (!raw_data)
1455		goto out_free_ipaddr;
1456
1457	snprintf(raw_data, raw_len, NFSD42_INTERSSC_MOUNTOPS, ipaddr);
1458
1459	status = nfserr_nodev;
1460	type = get_fs_type("nfs");
1461	if (!type)
1462		goto out_free_rawdata;
1463
1464	/* Set the server:<export> for the vfs_kern_mount call */
1465	dev_name = kzalloc(len + 5, GFP_KERNEL);
1466	if (!dev_name)
1467		goto out_free_rawdata;
1468	snprintf(dev_name, len + 5, "%s%s%s:/", startsep, ipaddr, endsep);
1469
1470	status = nfsd4_ssc_setup_dul(nn, ipaddr, nsui);
1471	if (status)
1472		goto out_free_devname;
1473	if ((*nsui)->nsui_vfsmount)
1474		goto out_done;
1475
1476	/* Use an 'internal' mount: SB_KERNMOUNT -> MNT_INTERNAL */
1477	ss_mnt = vfs_kern_mount(type, SB_KERNMOUNT, dev_name, raw_data);
1478	module_put(type->owner);
1479	if (IS_ERR(ss_mnt)) {
1480		status = nfserr_nodev;
1481		nfsd4_ssc_cancel_dul(nn, *nsui);
1482		goto out_free_devname;
1483	}
1484	nfsd4_ssc_update_dul(nn, *nsui, ss_mnt);
1485out_done:
1486	status = 0;
1487
1488out_free_devname:
1489	kfree(dev_name);
1490out_free_rawdata:
1491	kfree(raw_data);
1492out_free_ipaddr:
1493	kfree(ipaddr);
1494out_err:
1495	return status;
1496}
1497
1498/*
1499 * Verify COPY destination stateid.
1500 *
1501 * Connect to the source server with NFSv4.1.
1502 * Create the source struct file for nfsd_copy_range.
1503 * Called with COPY cstate:
1504 *    SAVED_FH: source filehandle
1505 *    CURRENT_FH: destination filehandle
1506 */
1507static __be32
1508nfsd4_setup_inter_ssc(struct svc_rqst *rqstp,
1509		      struct nfsd4_compound_state *cstate,
1510		      struct nfsd4_copy *copy)
1511{
1512	struct svc_fh *s_fh = NULL;
1513	stateid_t *s_stid = &copy->cp_src_stateid;
1514	__be32 status = nfserr_inval;
1515
1516	/* Verify the destination stateid and set dst struct file*/
1517	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
1518					    &copy->cp_dst_stateid,
1519					    WR_STATE, &copy->nf_dst, NULL);
1520	if (status)
1521		goto out;
1522
1523	status = nfsd4_interssc_connect(copy->cp_src, rqstp, &copy->ss_nsui);
1524	if (status)
1525		goto out;
1526
1527	s_fh = &cstate->save_fh;
1528
1529	copy->c_fh.size = s_fh->fh_handle.fh_size;
1530	memcpy(copy->c_fh.data, &s_fh->fh_handle.fh_raw, copy->c_fh.size);
1531	copy->stateid.seqid = cpu_to_be32(s_stid->si_generation);
1532	memcpy(copy->stateid.other, (void *)&s_stid->si_opaque,
1533	       sizeof(stateid_opaque_t));
1534
1535	status = 0;
1536out:
1537	return status;
1538}
1539
1540static void
1541nfsd4_cleanup_inter_ssc(struct nfsd4_ssc_umount_item *nsui, struct file *filp,
1542			struct nfsd_file *dst)
1543{
1544	struct nfsd_net *nn = net_generic(dst->nf_net, nfsd_net_id);
1545	long timeout = msecs_to_jiffies(nfsd4_ssc_umount_timeout);
1546
1547	nfs42_ssc_close(filp);
1548	fput(filp);
1549
1550	spin_lock(&nn->nfsd_ssc_lock);
1551	list_del(&nsui->nsui_list);
1552	/*
1553	 * vfsmount can be shared by multiple exports,
1554	 * decrement refcnt. If the count drops to 1 it
1555	 * will be unmounted when nsui_expire expires.
1556	 */
1557	refcount_dec(&nsui->nsui_refcnt);
1558	nsui->nsui_expire = jiffies + timeout;
1559	list_add_tail(&nsui->nsui_list, &nn->nfsd_ssc_mount_list);
1560	spin_unlock(&nn->nfsd_ssc_lock);
1561}
1562
1563#else /* CONFIG_NFSD_V4_2_INTER_SSC */
1564
1565static __be32
1566nfsd4_setup_inter_ssc(struct svc_rqst *rqstp,
1567		      struct nfsd4_compound_state *cstate,
1568		      struct nfsd4_copy *copy)
1569{
1570	return nfserr_inval;
1571}
1572
1573static void
1574nfsd4_cleanup_inter_ssc(struct nfsd4_ssc_umount_item *nsui, struct file *filp,
1575			struct nfsd_file *dst)
1576{
1577}
1578
1579static struct file *nfs42_ssc_open(struct vfsmount *ss_mnt,
1580				   struct nfs_fh *src_fh,
1581				   nfs4_stateid *stateid)
1582{
1583	return NULL;
1584}
1585#endif /* CONFIG_NFSD_V4_2_INTER_SSC */
1586
1587static __be32
1588nfsd4_setup_intra_ssc(struct svc_rqst *rqstp,
1589		      struct nfsd4_compound_state *cstate,
1590		      struct nfsd4_copy *copy)
1591{
1592	return nfsd4_verify_copy(rqstp, cstate, &copy->cp_src_stateid,
1593				 &copy->nf_src, &copy->cp_dst_stateid,
1594				 &copy->nf_dst);
1595}
1596
1597static void nfsd4_cb_offload_release(struct nfsd4_callback *cb)
1598{
1599	struct nfsd4_cb_offload *cbo =
1600		container_of(cb, struct nfsd4_cb_offload, co_cb);
1601
1602	kfree(cbo);
1603}
1604
1605static int nfsd4_cb_offload_done(struct nfsd4_callback *cb,
1606				 struct rpc_task *task)
1607{
1608	struct nfsd4_cb_offload *cbo =
1609		container_of(cb, struct nfsd4_cb_offload, co_cb);
1610
1611	trace_nfsd_cb_offload_done(&cbo->co_res.cb_stateid, task);
1612	return 1;
1613}
1614
1615static const struct nfsd4_callback_ops nfsd4_cb_offload_ops = {
1616	.release = nfsd4_cb_offload_release,
1617	.done = nfsd4_cb_offload_done
1618};
1619
1620static void nfsd4_init_copy_res(struct nfsd4_copy *copy, bool sync)
1621{
1622	copy->cp_res.wr_stable_how =
1623		test_bit(NFSD4_COPY_F_COMMITTED, &copy->cp_flags) ?
1624			NFS_FILE_SYNC : NFS_UNSTABLE;
1625	nfsd4_copy_set_sync(copy, sync);
1626	gen_boot_verifier(&copy->cp_res.wr_verifier, copy->cp_clp->net);
1627}
1628
1629static ssize_t _nfsd_copy_file_range(struct nfsd4_copy *copy,
1630				     struct file *dst,
1631				     struct file *src)
1632{
1633	errseq_t since;
1634	ssize_t bytes_copied = 0;
1635	u64 bytes_total = copy->cp_count;
1636	u64 src_pos = copy->cp_src_pos;
1637	u64 dst_pos = copy->cp_dst_pos;
1638	int status;
1639	loff_t end;
1640
1641	/* See RFC 7862 p.67: */
1642	if (bytes_total == 0)
1643		bytes_total = ULLONG_MAX;
1644	do {
1645		if (kthread_should_stop())
1646			break;
1647		bytes_copied = nfsd_copy_file_range(src, src_pos, dst, dst_pos,
1648						    bytes_total);
1649		if (bytes_copied <= 0)
1650			break;
1651		bytes_total -= bytes_copied;
1652		copy->cp_res.wr_bytes_written += bytes_copied;
1653		src_pos += bytes_copied;
1654		dst_pos += bytes_copied;
1655	} while (bytes_total > 0 && nfsd4_copy_is_async(copy));
1656	/* for a non-zero asynchronous copy do a commit of data */
1657	if (nfsd4_copy_is_async(copy) && copy->cp_res.wr_bytes_written > 0) {
1658		since = READ_ONCE(dst->f_wb_err);
1659		end = copy->cp_dst_pos + copy->cp_res.wr_bytes_written - 1;
1660		status = vfs_fsync_range(dst, copy->cp_dst_pos, end, 0);
1661		if (!status)
1662			status = filemap_check_wb_err(dst->f_mapping, since);
1663		if (!status)
1664			set_bit(NFSD4_COPY_F_COMMITTED, &copy->cp_flags);
1665	}
1666	return bytes_copied;
1667}
1668
1669static __be32 nfsd4_do_copy(struct nfsd4_copy *copy,
1670			    struct file *src, struct file *dst,
1671			    bool sync)
1672{
1673	__be32 status;
1674	ssize_t bytes;
1675
1676	bytes = _nfsd_copy_file_range(copy, dst, src);
1677
1678	/* for async copy, we ignore the error, client can always retry
1679	 * to get the error
1680	 */
1681	if (bytes < 0 && !copy->cp_res.wr_bytes_written)
1682		status = nfserrno(bytes);
1683	else {
1684		nfsd4_init_copy_res(copy, sync);
1685		status = nfs_ok;
1686	}
1687	return status;
1688}
1689
1690static void dup_copy_fields(struct nfsd4_copy *src, struct nfsd4_copy *dst)
1691{
1692	dst->cp_src_pos = src->cp_src_pos;
1693	dst->cp_dst_pos = src->cp_dst_pos;
1694	dst->cp_count = src->cp_count;
1695	dst->cp_flags = src->cp_flags;
1696	memcpy(&dst->cp_res, &src->cp_res, sizeof(src->cp_res));
1697	memcpy(&dst->fh, &src->fh, sizeof(src->fh));
1698	dst->cp_clp = src->cp_clp;
1699	dst->nf_dst = nfsd_file_get(src->nf_dst);
1700	/* for inter, nf_src doesn't exist yet */
1701	if (!nfsd4_ssc_is_inter(src))
1702		dst->nf_src = nfsd_file_get(src->nf_src);
1703
1704	memcpy(&dst->cp_stateid, &src->cp_stateid, sizeof(src->cp_stateid));
1705	memcpy(dst->cp_src, src->cp_src, sizeof(struct nl4_server));
1706	memcpy(&dst->stateid, &src->stateid, sizeof(src->stateid));
1707	memcpy(&dst->c_fh, &src->c_fh, sizeof(src->c_fh));
1708	dst->ss_nsui = src->ss_nsui;
1709}
1710
1711static void release_copy_files(struct nfsd4_copy *copy)
1712{
1713	if (copy->nf_src)
1714		nfsd_file_put(copy->nf_src);
1715	if (copy->nf_dst)
1716		nfsd_file_put(copy->nf_dst);
1717}
1718
1719static void cleanup_async_copy(struct nfsd4_copy *copy)
1720{
1721	nfs4_free_copy_state(copy);
1722	release_copy_files(copy);
1723	if (copy->cp_clp) {
1724		spin_lock(&copy->cp_clp->async_lock);
1725		if (!list_empty(&copy->copies))
1726			list_del_init(&copy->copies);
1727		spin_unlock(&copy->cp_clp->async_lock);
1728	}
1729	nfs4_put_copy(copy);
1730}
1731
1732static void nfsd4_send_cb_offload(struct nfsd4_copy *copy, __be32 nfserr)
1733{
1734	struct nfsd4_cb_offload *cbo;
1735
1736	cbo = kzalloc(sizeof(*cbo), GFP_KERNEL);
1737	if (!cbo)
1738		return;
1739
1740	memcpy(&cbo->co_res, &copy->cp_res, sizeof(copy->cp_res));
1741	memcpy(&cbo->co_fh, &copy->fh, sizeof(copy->fh));
1742	cbo->co_nfserr = nfserr;
1743
1744	nfsd4_init_cb(&cbo->co_cb, copy->cp_clp, &nfsd4_cb_offload_ops,
1745		      NFSPROC4_CLNT_CB_OFFLOAD);
1746	trace_nfsd_cb_offload(copy->cp_clp, &cbo->co_res.cb_stateid,
1747			      &cbo->co_fh, copy->cp_count, nfserr);
1748	nfsd4_run_cb(&cbo->co_cb);
1749}
1750
1751/**
1752 * nfsd4_do_async_copy - kthread function for background server-side COPY
1753 * @data: arguments for COPY operation
1754 *
1755 * Return values:
1756 *   %0: Copy operation is done.
1757 */
1758static int nfsd4_do_async_copy(void *data)
1759{
1760	struct nfsd4_copy *copy = (struct nfsd4_copy *)data;
1761	__be32 nfserr;
1762
1763	if (nfsd4_ssc_is_inter(copy)) {
1764		struct file *filp;
1765
1766		filp = nfs42_ssc_open(copy->ss_nsui->nsui_vfsmount,
1767				      &copy->c_fh, &copy->stateid);
1768		if (IS_ERR(filp)) {
1769			switch (PTR_ERR(filp)) {
1770			case -EBADF:
1771				nfserr = nfserr_wrong_type;
1772				break;
1773			default:
1774				nfserr = nfserr_offload_denied;
1775			}
1776			/* ss_mnt will be unmounted by the laundromat */
1777			goto do_callback;
1778		}
1779		nfserr = nfsd4_do_copy(copy, filp, copy->nf_dst->nf_file,
1780				       false);
1781		nfsd4_cleanup_inter_ssc(copy->ss_nsui, filp, copy->nf_dst);
1782	} else {
1783		nfserr = nfsd4_do_copy(copy, copy->nf_src->nf_file,
1784				       copy->nf_dst->nf_file, false);
1785	}
1786
1787do_callback:
1788	nfsd4_send_cb_offload(copy, nfserr);
1789	cleanup_async_copy(copy);
1790	return 0;
1791}
1792
1793static __be32
1794nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
1795		union nfsd4_op_u *u)
1796{
1797	struct nfsd4_copy *copy = &u->copy;
1798	__be32 status;
1799	struct nfsd4_copy *async_copy = NULL;
1800
1801	if (nfsd4_ssc_is_inter(copy)) {
1802		if (!inter_copy_offload_enable || nfsd4_copy_is_sync(copy)) {
1803			status = nfserr_notsupp;
1804			goto out;
1805		}
1806		status = nfsd4_setup_inter_ssc(rqstp, cstate, copy);
1807		if (status)
1808			return nfserr_offload_denied;
1809	} else {
1810		status = nfsd4_setup_intra_ssc(rqstp, cstate, copy);
1811		if (status)
1812			return status;
1813	}
1814
1815	copy->cp_clp = cstate->clp;
1816	memcpy(&copy->fh, &cstate->current_fh.fh_handle,
1817		sizeof(struct knfsd_fh));
1818	if (nfsd4_copy_is_async(copy)) {
1819		struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
1820
1821		status = nfserrno(-ENOMEM);
1822		async_copy = kzalloc(sizeof(struct nfsd4_copy), GFP_KERNEL);
1823		if (!async_copy)
1824			goto out_err;
1825		INIT_LIST_HEAD(&async_copy->copies);
1826		refcount_set(&async_copy->refcount, 1);
1827		async_copy->cp_src = kmalloc(sizeof(*async_copy->cp_src), GFP_KERNEL);
1828		if (!async_copy->cp_src)
1829			goto out_err;
1830		if (!nfs4_init_copy_state(nn, copy))
1831			goto out_err;
1832		memcpy(&copy->cp_res.cb_stateid, &copy->cp_stateid.cs_stid,
1833			sizeof(copy->cp_res.cb_stateid));
1834		dup_copy_fields(copy, async_copy);
1835		async_copy->copy_task = kthread_create(nfsd4_do_async_copy,
1836				async_copy, "%s", "copy thread");
1837		if (IS_ERR(async_copy->copy_task))
1838			goto out_err;
1839		spin_lock(&async_copy->cp_clp->async_lock);
1840		list_add(&async_copy->copies,
1841				&async_copy->cp_clp->async_copies);
1842		spin_unlock(&async_copy->cp_clp->async_lock);
1843		wake_up_process(async_copy->copy_task);
1844		status = nfs_ok;
1845	} else {
1846		status = nfsd4_do_copy(copy, copy->nf_src->nf_file,
1847				       copy->nf_dst->nf_file, true);
1848	}
1849out:
1850	release_copy_files(copy);
1851	return status;
1852out_err:
1853	if (nfsd4_ssc_is_inter(copy)) {
1854		/*
1855		 * Source's vfsmount of inter-copy will be unmounted
1856		 * by the laundromat. Use copy instead of async_copy
1857		 * since async_copy->ss_nsui might not be set yet.
1858		 */
1859		refcount_dec(&copy->ss_nsui->nsui_refcnt);
1860	}
1861	if (async_copy)
1862		cleanup_async_copy(async_copy);
1863	status = nfserrno(-ENOMEM);
1864	goto out;
1865}
1866
1867static struct nfsd4_copy *
1868find_async_copy_locked(struct nfs4_client *clp, stateid_t *stateid)
1869{
1870	struct nfsd4_copy *copy;
1871
1872	lockdep_assert_held(&clp->async_lock);
1873
1874	list_for_each_entry(copy, &clp->async_copies, copies) {
1875		if (memcmp(&copy->cp_stateid.cs_stid, stateid, NFS4_STATEID_SIZE))
1876			continue;
1877		return copy;
1878	}
1879	return NULL;
1880}
1881
1882static struct nfsd4_copy *
1883find_async_copy(struct nfs4_client *clp, stateid_t *stateid)
1884{
1885	struct nfsd4_copy *copy;
1886
1887	spin_lock(&clp->async_lock);
1888	copy = find_async_copy_locked(clp, stateid);
1889	if (copy)
1890		refcount_inc(&copy->refcount);
1891	spin_unlock(&clp->async_lock);
1892	return copy;
1893}
1894
1895static __be32
1896nfsd4_offload_cancel(struct svc_rqst *rqstp,
1897		     struct nfsd4_compound_state *cstate,
1898		     union nfsd4_op_u *u)
1899{
1900	struct nfsd4_offload_status *os = &u->offload_status;
1901	struct nfsd4_copy *copy;
1902	struct nfs4_client *clp = cstate->clp;
1903
1904	copy = find_async_copy(clp, &os->stateid);
1905	if (!copy) {
1906		struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
1907
1908		return manage_cpntf_state(nn, &os->stateid, clp, NULL);
1909	} else
1910		nfsd4_stop_copy(copy);
1911
1912	return nfs_ok;
1913}
1914
1915static __be32
1916nfsd4_copy_notify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
1917		  union nfsd4_op_u *u)
1918{
1919	struct nfsd4_copy_notify *cn = &u->copy_notify;
1920	__be32 status;
1921	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
1922	struct nfs4_stid *stid;
1923	struct nfs4_cpntf_state *cps;
1924	struct nfs4_client *clp = cstate->clp;
1925
1926	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
1927					&cn->cpn_src_stateid, RD_STATE, NULL,
1928					&stid);
1929	if (status)
1930		return status;
1931
1932	cn->cpn_sec = nn->nfsd4_lease;
1933	cn->cpn_nsec = 0;
1934
1935	status = nfserrno(-ENOMEM);
1936	cps = nfs4_alloc_init_cpntf_state(nn, stid);
1937	if (!cps)
1938		goto out;
1939	memcpy(&cn->cpn_cnr_stateid, &cps->cp_stateid.cs_stid, sizeof(stateid_t));
1940	memcpy(&cps->cp_p_stateid, &stid->sc_stateid, sizeof(stateid_t));
1941	memcpy(&cps->cp_p_clid, &clp->cl_clientid, sizeof(clientid_t));
1942
1943	/* For now, only return one server address in cpn_src, the
1944	 * address used by the client to connect to this server.
1945	 */
1946	cn->cpn_src->nl4_type = NL4_NETADDR;
1947	status = nfsd4_set_netaddr((struct sockaddr *)&rqstp->rq_daddr,
1948				 &cn->cpn_src->u.nl4_addr);
1949	WARN_ON_ONCE(status);
1950	if (status) {
1951		nfs4_put_cpntf_state(nn, cps);
1952		goto out;
1953	}
1954out:
1955	nfs4_put_stid(stid);
1956	return status;
1957}
1958
1959static __be32
1960nfsd4_fallocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
1961		struct nfsd4_fallocate *fallocate, int flags)
1962{
1963	__be32 status;
1964	struct nfsd_file *nf;
1965
1966	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
1967					    &fallocate->falloc_stateid,
1968					    WR_STATE, &nf, NULL);
1969	if (status != nfs_ok)
1970		return status;
1971
1972	status = nfsd4_vfs_fallocate(rqstp, &cstate->current_fh, nf->nf_file,
1973				     fallocate->falloc_offset,
1974				     fallocate->falloc_length,
1975				     flags);
1976	nfsd_file_put(nf);
1977	return status;
1978}
1979
1980static __be32
1981nfsd4_offload_status(struct svc_rqst *rqstp,
1982		     struct nfsd4_compound_state *cstate,
1983		     union nfsd4_op_u *u)
1984{
1985	struct nfsd4_offload_status *os = &u->offload_status;
1986	__be32 status = nfs_ok;
1987	struct nfsd4_copy *copy;
1988	struct nfs4_client *clp = cstate->clp;
1989
1990	spin_lock(&clp->async_lock);
1991	copy = find_async_copy_locked(clp, &os->stateid);
1992	if (copy)
1993		os->count = copy->cp_res.wr_bytes_written;
1994	else
1995		status = nfserr_bad_stateid;
1996	spin_unlock(&clp->async_lock);
1997
1998	return status;
1999}
2000
2001static __be32
2002nfsd4_allocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
2003	       union nfsd4_op_u *u)
2004{
2005	return nfsd4_fallocate(rqstp, cstate, &u->allocate, 0);
2006}
2007
2008static __be32
2009nfsd4_deallocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
2010		 union nfsd4_op_u *u)
2011{
2012	return nfsd4_fallocate(rqstp, cstate, &u->deallocate,
2013			       FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE);
2014}
2015
2016static __be32
2017nfsd4_seek(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
2018	   union nfsd4_op_u *u)
2019{
2020	struct nfsd4_seek *seek = &u->seek;
2021	int whence;
2022	__be32 status;
2023	struct nfsd_file *nf;
2024
2025	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
2026					    &seek->seek_stateid,
2027					    RD_STATE, &nf, NULL);
2028	if (status)
2029		return status;
2030
2031	switch (seek->seek_whence) {
2032	case NFS4_CONTENT_DATA:
2033		whence = SEEK_DATA;
2034		break;
2035	case NFS4_CONTENT_HOLE:
2036		whence = SEEK_HOLE;
2037		break;
2038	default:
2039		status = nfserr_union_notsupp;
2040		goto out;
2041	}
2042
2043	/*
2044	 * Note:  This call does change file->f_pos, but nothing in NFSD
2045	 *        should ever file->f_pos.
2046	 */
2047	seek->seek_pos = vfs_llseek(nf->nf_file, seek->seek_offset, whence);
2048	if (seek->seek_pos < 0)
2049		status = nfserrno(seek->seek_pos);
2050	else if (seek->seek_pos >= i_size_read(file_inode(nf->nf_file)))
2051		seek->seek_eof = true;
2052
2053out:
2054	nfsd_file_put(nf);
2055	return status;
2056}
2057
2058/* This routine never returns NFS_OK!  If there are no other errors, it
2059 * will return NFSERR_SAME or NFSERR_NOT_SAME depending on whether the
2060 * attributes matched.  VERIFY is implemented by mapping NFSERR_SAME
2061 * to NFS_OK after the call; NVERIFY by mapping NFSERR_NOT_SAME to NFS_OK.
2062 */
2063static __be32
2064_nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
2065	     struct nfsd4_verify *verify)
2066{
2067	__be32 *buf, *p;
2068	int count;
2069	__be32 status;
2070
2071	status = fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_NOP);
2072	if (status)
2073		return status;
2074
2075	status = check_attr_support(rqstp, cstate, verify->ve_bmval, NULL);
2076	if (status)
2077		return status;
2078
2079	if ((verify->ve_bmval[0] & FATTR4_WORD0_RDATTR_ERROR)
2080	    || (verify->ve_bmval[1] & NFSD_WRITEONLY_ATTRS_WORD1))
2081		return nfserr_inval;
2082	if (verify->ve_attrlen & 3)
2083		return nfserr_inval;
2084
2085	/* count in words:
2086	 *   bitmap_len(1) + bitmap(2) + attr_len(1) = 4
2087	 */
2088	count = 4 + (verify->ve_attrlen >> 2);
2089	buf = kmalloc(count << 2, GFP_KERNEL);
2090	if (!buf)
2091		return nfserr_jukebox;
2092
2093	p = buf;
2094	status = nfsd4_encode_fattr_to_buf(&p, count, &cstate->current_fh,
2095				    cstate->current_fh.fh_export,
2096				    cstate->current_fh.fh_dentry,
2097				    verify->ve_bmval,
2098				    rqstp, 0);
2099	/*
2100	 * If nfsd4_encode_fattr() ran out of space, assume that's because
2101	 * the attributes are longer (hence different) than those given:
2102	 */
2103	if (status == nfserr_resource)
2104		status = nfserr_not_same;
2105	if (status)
2106		goto out_kfree;
2107
2108	/* skip bitmap */
2109	p = buf + 1 + ntohl(buf[0]);
2110	status = nfserr_not_same;
2111	if (ntohl(*p++) != verify->ve_attrlen)
2112		goto out_kfree;
2113	if (!memcmp(p, verify->ve_attrval, verify->ve_attrlen))
2114		status = nfserr_same;
2115
2116out_kfree:
2117	kfree(buf);
2118	return status;
2119}
2120
2121static __be32
2122nfsd4_nverify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
2123	      union nfsd4_op_u *u)
2124{
2125	__be32 status;
2126
2127	status = _nfsd4_verify(rqstp, cstate, &u->verify);
2128	return status == nfserr_not_same ? nfs_ok : status;
2129}
2130
2131static __be32
2132nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
2133	     union nfsd4_op_u *u)
2134{
2135	__be32 status;
2136
2137	status = _nfsd4_verify(rqstp, cstate, &u->nverify);
2138	return status == nfserr_same ? nfs_ok : status;
2139}
2140
2141#ifdef CONFIG_NFSD_PNFS
2142static const struct nfsd4_layout_ops *
2143nfsd4_layout_verify(struct svc_export *exp, unsigned int layout_type)
2144{
2145	if (!exp->ex_layout_types) {
2146		dprintk("%s: export does not support pNFS\n", __func__);
2147		return NULL;
2148	}
2149
2150	if (layout_type >= LAYOUT_TYPE_MAX ||
2151	    !(exp->ex_layout_types & (1 << layout_type))) {
2152		dprintk("%s: layout type %d not supported\n",
2153			__func__, layout_type);
2154		return NULL;
2155	}
2156
2157	return nfsd4_layout_ops[layout_type];
2158}
2159
2160static __be32
2161nfsd4_getdeviceinfo(struct svc_rqst *rqstp,
2162		struct nfsd4_compound_state *cstate, union nfsd4_op_u *u)
2163{
2164	struct nfsd4_getdeviceinfo *gdp = &u->getdeviceinfo;
2165	const struct nfsd4_layout_ops *ops;
2166	struct nfsd4_deviceid_map *map;
2167	struct svc_export *exp;
2168	__be32 nfserr;
2169
2170	dprintk("%s: layout_type %u dev_id [0x%llx:0x%x] maxcnt %u\n",
2171	       __func__,
2172	       gdp->gd_layout_type,
2173	       gdp->gd_devid.fsid_idx, gdp->gd_devid.generation,
2174	       gdp->gd_maxcount);
2175
2176	map = nfsd4_find_devid_map(gdp->gd_devid.fsid_idx);
2177	if (!map) {
2178		dprintk("%s: couldn't find device ID to export mapping!\n",
2179			__func__);
2180		return nfserr_noent;
2181	}
2182
2183	exp = rqst_exp_find(rqstp, map->fsid_type, map->fsid);
2184	if (IS_ERR(exp)) {
2185		dprintk("%s: could not find device id\n", __func__);
2186		return nfserr_noent;
2187	}
2188
2189	nfserr = nfserr_layoutunavailable;
2190	ops = nfsd4_layout_verify(exp, gdp->gd_layout_type);
2191	if (!ops)
2192		goto out;
2193
2194	nfserr = nfs_ok;
2195	if (gdp->gd_maxcount != 0) {
2196		nfserr = ops->proc_getdeviceinfo(exp->ex_path.mnt->mnt_sb,
2197				rqstp, cstate->clp, gdp);
2198	}
2199
2200	gdp->gd_notify_types &= ops->notify_types;
2201out:
2202	exp_put(exp);
2203	return nfserr;
2204}
2205
2206static void
2207nfsd4_getdeviceinfo_release(union nfsd4_op_u *u)
2208{
2209	kfree(u->getdeviceinfo.gd_device);
2210}
2211
2212static __be32
2213nfsd4_layoutget(struct svc_rqst *rqstp,
2214		struct nfsd4_compound_state *cstate, union nfsd4_op_u *u)
2215{
2216	struct nfsd4_layoutget *lgp = &u->layoutget;
2217	struct svc_fh *current_fh = &cstate->current_fh;
2218	const struct nfsd4_layout_ops *ops;
2219	struct nfs4_layout_stateid *ls;
2220	__be32 nfserr;
2221	int accmode = NFSD_MAY_READ_IF_EXEC;
2222
2223	switch (lgp->lg_seg.iomode) {
2224	case IOMODE_READ:
2225		accmode |= NFSD_MAY_READ;
2226		break;
2227	case IOMODE_RW:
2228		accmode |= NFSD_MAY_READ | NFSD_MAY_WRITE;
2229		break;
2230	default:
2231		dprintk("%s: invalid iomode %d\n",
2232			__func__, lgp->lg_seg.iomode);
2233		nfserr = nfserr_badiomode;
2234		goto out;
2235	}
2236
2237	nfserr = fh_verify(rqstp, current_fh, 0, accmode);
2238	if (nfserr)
2239		goto out;
2240
2241	nfserr = nfserr_layoutunavailable;
2242	ops = nfsd4_layout_verify(current_fh->fh_export, lgp->lg_layout_type);
2243	if (!ops)
2244		goto out;
2245
2246	/*
2247	 * Verify minlength and range as per RFC5661:
2248	 *  o  If loga_length is less than loga_minlength,
2249	 *     the metadata server MUST return NFS4ERR_INVAL.
2250	 *  o  If the sum of loga_offset and loga_minlength exceeds
2251	 *     NFS4_UINT64_MAX, and loga_minlength is not
2252	 *     NFS4_UINT64_MAX, the error NFS4ERR_INVAL MUST result.
2253	 *  o  If the sum of loga_offset and loga_length exceeds
2254	 *     NFS4_UINT64_MAX, and loga_length is not NFS4_UINT64_MAX,
2255	 *     the error NFS4ERR_INVAL MUST result.
2256	 */
2257	nfserr = nfserr_inval;
2258	if (lgp->lg_seg.length < lgp->lg_minlength ||
2259	    (lgp->lg_minlength != NFS4_MAX_UINT64 &&
2260	     lgp->lg_minlength > NFS4_MAX_UINT64 - lgp->lg_seg.offset) ||
2261	    (lgp->lg_seg.length != NFS4_MAX_UINT64 &&
2262	     lgp->lg_seg.length > NFS4_MAX_UINT64 - lgp->lg_seg.offset))
2263		goto out;
2264	if (lgp->lg_seg.length == 0)
2265		goto out;
2266
2267	nfserr = nfsd4_preprocess_layout_stateid(rqstp, cstate, &lgp->lg_sid,
2268						true, lgp->lg_layout_type, &ls);
2269	if (nfserr) {
2270		trace_nfsd_layout_get_lookup_fail(&lgp->lg_sid);
2271		goto out;
2272	}
2273
2274	nfserr = nfserr_recallconflict;
2275	if (atomic_read(&ls->ls_stid.sc_file->fi_lo_recalls))
2276		goto out_put_stid;
2277
2278	nfserr = ops->proc_layoutget(d_inode(current_fh->fh_dentry),
2279				     current_fh, lgp);
2280	if (nfserr)
2281		goto out_put_stid;
2282
2283	nfserr = nfsd4_insert_layout(lgp, ls);
2284
2285out_put_stid:
2286	mutex_unlock(&ls->ls_mutex);
2287	nfs4_put_stid(&ls->ls_stid);
2288out:
2289	return nfserr;
2290}
2291
2292static void
2293nfsd4_layoutget_release(union nfsd4_op_u *u)
2294{
2295	kfree(u->layoutget.lg_content);
2296}
2297
2298static __be32
2299nfsd4_layoutcommit(struct svc_rqst *rqstp,
2300		struct nfsd4_compound_state *cstate, union nfsd4_op_u *u)
2301{
2302	struct nfsd4_layoutcommit *lcp = &u->layoutcommit;
2303	const struct nfsd4_layout_seg *seg = &lcp->lc_seg;
2304	struct svc_fh *current_fh = &cstate->current_fh;
2305	const struct nfsd4_layout_ops *ops;
2306	loff_t new_size = lcp->lc_last_wr + 1;
2307	struct inode *inode;
2308	struct nfs4_layout_stateid *ls;
2309	__be32 nfserr;
2310
2311	nfserr = fh_verify(rqstp, current_fh, 0, NFSD_MAY_WRITE);
2312	if (nfserr)
2313		goto out;
2314
2315	nfserr = nfserr_layoutunavailable;
2316	ops = nfsd4_layout_verify(current_fh->fh_export, lcp->lc_layout_type);
2317	if (!ops)
2318		goto out;
2319	inode = d_inode(current_fh->fh_dentry);
2320
2321	nfserr = nfserr_inval;
2322	if (new_size <= seg->offset) {
2323		dprintk("pnfsd: last write before layout segment\n");
2324		goto out;
2325	}
2326	if (new_size > seg->offset + seg->length) {
2327		dprintk("pnfsd: last write beyond layout segment\n");
2328		goto out;
2329	}
2330	if (!lcp->lc_newoffset && new_size > i_size_read(inode)) {
2331		dprintk("pnfsd: layoutcommit beyond EOF\n");
2332		goto out;
2333	}
2334
2335	nfserr = nfsd4_preprocess_layout_stateid(rqstp, cstate, &lcp->lc_sid,
2336						false, lcp->lc_layout_type,
2337						&ls);
2338	if (nfserr) {
2339		trace_nfsd_layout_commit_lookup_fail(&lcp->lc_sid);
2340		/* fixup error code as per RFC5661 */
2341		if (nfserr == nfserr_bad_stateid)
2342			nfserr = nfserr_badlayout;
2343		goto out;
2344	}
2345
2346	/* LAYOUTCOMMIT does not require any serialization */
2347	mutex_unlock(&ls->ls_mutex);
2348
2349	if (new_size > i_size_read(inode)) {
2350		lcp->lc_size_chg = 1;
2351		lcp->lc_newsize = new_size;
2352	} else {
2353		lcp->lc_size_chg = 0;
2354	}
2355
2356	nfserr = ops->proc_layoutcommit(inode, lcp);
2357	nfs4_put_stid(&ls->ls_stid);
2358out:
2359	return nfserr;
2360}
2361
2362static __be32
2363nfsd4_layoutreturn(struct svc_rqst *rqstp,
2364		struct nfsd4_compound_state *cstate, union nfsd4_op_u *u)
2365{
2366	struct nfsd4_layoutreturn *lrp = &u->layoutreturn;
2367	struct svc_fh *current_fh = &cstate->current_fh;
2368	__be32 nfserr;
2369
2370	nfserr = fh_verify(rqstp, current_fh, 0, NFSD_MAY_NOP);
2371	if (nfserr)
2372		goto out;
2373
2374	nfserr = nfserr_layoutunavailable;
2375	if (!nfsd4_layout_verify(current_fh->fh_export, lrp->lr_layout_type))
2376		goto out;
2377
2378	switch (lrp->lr_seg.iomode) {
2379	case IOMODE_READ:
2380	case IOMODE_RW:
2381	case IOMODE_ANY:
2382		break;
2383	default:
2384		dprintk("%s: invalid iomode %d\n", __func__,
2385			lrp->lr_seg.iomode);
2386		nfserr = nfserr_inval;
2387		goto out;
2388	}
2389
2390	switch (lrp->lr_return_type) {
2391	case RETURN_FILE:
2392		nfserr = nfsd4_return_file_layouts(rqstp, cstate, lrp);
2393		break;
2394	case RETURN_FSID:
2395	case RETURN_ALL:
2396		nfserr = nfsd4_return_client_layouts(rqstp, cstate, lrp);
2397		break;
2398	default:
2399		dprintk("%s: invalid return_type %d\n", __func__,
2400			lrp->lr_return_type);
2401		nfserr = nfserr_inval;
2402		break;
2403	}
2404out:
2405	return nfserr;
2406}
2407#endif /* CONFIG_NFSD_PNFS */
2408
2409static __be32
2410nfsd4_getxattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
2411	       union nfsd4_op_u *u)
2412{
2413	struct nfsd4_getxattr *getxattr = &u->getxattr;
2414
2415	return nfsd_getxattr(rqstp, &cstate->current_fh,
2416			     getxattr->getxa_name, &getxattr->getxa_buf,
2417			     &getxattr->getxa_len);
2418}
2419
2420static __be32
2421nfsd4_setxattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
2422	   union nfsd4_op_u *u)
2423{
2424	struct nfsd4_setxattr *setxattr = &u->setxattr;
2425	__be32 ret;
2426
2427	if (opens_in_grace(SVC_NET(rqstp)))
2428		return nfserr_grace;
2429
2430	ret = nfsd_setxattr(rqstp, &cstate->current_fh, setxattr->setxa_name,
2431			    setxattr->setxa_buf, setxattr->setxa_len,
2432			    setxattr->setxa_flags);
2433
2434	if (!ret)
2435		set_change_info(&setxattr->setxa_cinfo, &cstate->current_fh);
2436
2437	return ret;
2438}
2439
2440static __be32
2441nfsd4_listxattrs(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
2442	   union nfsd4_op_u *u)
2443{
2444	/*
2445	 * Get the entire list, then copy out only the user attributes
2446	 * in the encode function.
2447	 */
2448	return nfsd_listxattr(rqstp, &cstate->current_fh,
2449			     &u->listxattrs.lsxa_buf, &u->listxattrs.lsxa_len);
2450}
2451
2452static __be32
2453nfsd4_removexattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
2454	   union nfsd4_op_u *u)
2455{
2456	struct nfsd4_removexattr *removexattr = &u->removexattr;
2457	__be32 ret;
2458
2459	if (opens_in_grace(SVC_NET(rqstp)))
2460		return nfserr_grace;
2461
2462	ret = nfsd_removexattr(rqstp, &cstate->current_fh,
2463	    removexattr->rmxa_name);
2464
2465	if (!ret)
2466		set_change_info(&removexattr->rmxa_cinfo, &cstate->current_fh);
2467
2468	return ret;
2469}
2470
2471/*
2472 * NULL call.
2473 */
2474static __be32
2475nfsd4_proc_null(struct svc_rqst *rqstp)
2476{
2477	return rpc_success;
2478}
2479
2480static inline void nfsd4_increment_op_stats(u32 opnum)
2481{
2482	if (opnum >= FIRST_NFS4_OP && opnum <= LAST_NFS4_OP)
2483		percpu_counter_inc(&nfsdstats.counter[NFSD_STATS_NFS4_OP(opnum)]);
2484}
2485
2486static const struct nfsd4_operation nfsd4_ops[];
2487
2488static const char *nfsd4_op_name(unsigned opnum);
2489
2490/*
2491 * Enforce NFSv4.1 COMPOUND ordering rules:
2492 *
2493 * Also note, enforced elsewhere:
2494 *	- SEQUENCE other than as first op results in
2495 *	  NFS4ERR_SEQUENCE_POS. (Enforced in nfsd4_sequence().)
2496 *	- BIND_CONN_TO_SESSION must be the only op in its compound.
2497 *	  (Enforced in nfsd4_bind_conn_to_session().)
2498 *	- DESTROY_SESSION must be the final operation in a compound, if
2499 *	  sessionid's in SEQUENCE and DESTROY_SESSION are the same.
2500 *	  (Enforced in nfsd4_destroy_session().)
2501 */
2502static __be32 nfs41_check_op_ordering(struct nfsd4_compoundargs *args)
2503{
2504	struct nfsd4_op *first_op = &args->ops[0];
2505
2506	/* These ordering requirements don't apply to NFSv4.0: */
2507	if (args->minorversion == 0)
2508		return nfs_ok;
2509	/* This is weird, but OK, not our problem: */
2510	if (args->opcnt == 0)
2511		return nfs_ok;
2512	if (first_op->status == nfserr_op_illegal)
2513		return nfs_ok;
2514	if (!(nfsd4_ops[first_op->opnum].op_flags & ALLOWED_AS_FIRST_OP))
2515		return nfserr_op_not_in_session;
2516	if (first_op->opnum == OP_SEQUENCE)
2517		return nfs_ok;
2518	/*
2519	 * So first_op is something allowed outside a session, like
2520	 * EXCHANGE_ID; but then it has to be the only op in the
2521	 * compound:
2522	 */
2523	if (args->opcnt != 1)
2524		return nfserr_not_only_op;
2525	return nfs_ok;
2526}
2527
2528const struct nfsd4_operation *OPDESC(struct nfsd4_op *op)
2529{
2530	return &nfsd4_ops[op->opnum];
2531}
2532
2533bool nfsd4_cache_this_op(struct nfsd4_op *op)
2534{
2535	if (op->opnum == OP_ILLEGAL)
2536		return false;
2537	return OPDESC(op)->op_flags & OP_CACHEME;
2538}
2539
2540static bool need_wrongsec_check(struct svc_rqst *rqstp)
2541{
2542	struct nfsd4_compoundres *resp = rqstp->rq_resp;
2543	struct nfsd4_compoundargs *argp = rqstp->rq_argp;
2544	struct nfsd4_op *this = &argp->ops[resp->opcnt - 1];
2545	struct nfsd4_op *next = &argp->ops[resp->opcnt];
2546	const struct nfsd4_operation *thisd = OPDESC(this);
2547	const struct nfsd4_operation *nextd;
2548
2549	/*
2550	 * Most ops check wronsec on our own; only the putfh-like ops
2551	 * have special rules.
2552	 */
2553	if (!(thisd->op_flags & OP_IS_PUTFH_LIKE))
2554		return false;
2555	/*
2556	 * rfc 5661 2.6.3.1.1.6: don't bother erroring out a
2557	 * put-filehandle operation if we're not going to use the
2558	 * result:
2559	 */
2560	if (argp->opcnt == resp->opcnt)
2561		return false;
2562	if (next->opnum == OP_ILLEGAL)
2563		return false;
2564	nextd = OPDESC(next);
2565	/*
2566	 * Rest of 2.6.3.1.1: certain operations will return WRONGSEC
2567	 * errors themselves as necessary; others should check for them
2568	 * now:
2569	 */
2570	return !(nextd->op_flags & OP_HANDLES_WRONGSEC);
2571}
2572
2573#ifdef CONFIG_NFSD_V4_2_INTER_SSC
2574static void
2575check_if_stalefh_allowed(struct nfsd4_compoundargs *args)
2576{
2577	struct nfsd4_op	*op, *current_op = NULL, *saved_op = NULL;
2578	struct nfsd4_copy *copy;
2579	struct nfsd4_putfh *putfh;
2580	int i;
2581
2582	/* traverse all operation and if it's a COPY compound, mark the
2583	 * source filehandle to skip verification
2584	 */
2585	for (i = 0; i < args->opcnt; i++) {
2586		op = &args->ops[i];
2587		if (op->opnum == OP_PUTFH)
2588			current_op = op;
2589		else if (op->opnum == OP_SAVEFH)
2590			saved_op = current_op;
2591		else if (op->opnum == OP_RESTOREFH)
2592			current_op = saved_op;
2593		else if (op->opnum == OP_COPY) {
2594			copy = (struct nfsd4_copy *)&op->u;
2595			if (!saved_op) {
2596				op->status = nfserr_nofilehandle;
2597				return;
2598			}
2599			putfh = (struct nfsd4_putfh *)&saved_op->u;
2600			if (nfsd4_ssc_is_inter(copy))
2601				putfh->no_verify = true;
2602		}
2603	}
2604}
2605#else
2606static void
2607check_if_stalefh_allowed(struct nfsd4_compoundargs *args)
2608{
2609}
2610#endif
2611
2612/*
2613 * COMPOUND call.
2614 */
2615static __be32
2616nfsd4_proc_compound(struct svc_rqst *rqstp)
2617{
2618	struct nfsd4_compoundargs *args = rqstp->rq_argp;
2619	struct nfsd4_compoundres *resp = rqstp->rq_resp;
2620	struct nfsd4_op	*op;
2621	struct nfsd4_compound_state *cstate = &resp->cstate;
2622	struct svc_fh *current_fh = &cstate->current_fh;
2623	struct svc_fh *save_fh = &cstate->save_fh;
2624	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
2625	__be32		status;
2626
2627	resp->xdr = &rqstp->rq_res_stream;
2628	resp->statusp = resp->xdr->p;
2629
2630	/* reserve space for: NFS status code */
2631	xdr_reserve_space(resp->xdr, XDR_UNIT);
2632
2633	/* reserve space for: taglen, tag, and opcnt */
2634	xdr_reserve_space(resp->xdr, XDR_UNIT * 2 + args->taglen);
2635	resp->taglen = args->taglen;
2636	resp->tag = args->tag;
2637	resp->rqstp = rqstp;
2638	cstate->minorversion = args->minorversion;
2639	fh_init(current_fh, NFS4_FHSIZE);
2640	fh_init(save_fh, NFS4_FHSIZE);
2641	/*
2642	 * Don't use the deferral mechanism for NFSv4; compounds make it
2643	 * too hard to avoid non-idempotency problems.
2644	 */
2645	clear_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
2646
2647	/*
2648	 * According to RFC3010, this takes precedence over all other errors.
2649	 */
2650	status = nfserr_minor_vers_mismatch;
2651	if (nfsd_minorversion(nn, args->minorversion, NFSD_TEST) <= 0)
2652		goto out;
2653
2654	status = nfs41_check_op_ordering(args);
2655	if (status) {
2656		op = &args->ops[0];
2657		op->status = status;
2658		resp->opcnt = 1;
2659		goto encode_op;
2660	}
2661	check_if_stalefh_allowed(args);
2662
2663	rqstp->rq_lease_breaker = (void **)&cstate->clp;
2664
2665	trace_nfsd_compound(rqstp, args->tag, args->taglen, args->client_opcnt);
2666	while (!status && resp->opcnt < args->opcnt) {
2667		op = &args->ops[resp->opcnt++];
2668
2669		if (unlikely(resp->opcnt == NFSD_MAX_OPS_PER_COMPOUND)) {
2670			/* If there are still more operations to process,
2671			 * stop here and report NFS4ERR_RESOURCE. */
2672			if (cstate->minorversion == 0 &&
2673			    args->client_opcnt > resp->opcnt) {
2674				op->status = nfserr_resource;
2675				goto encode_op;
2676			}
2677		}
2678
2679		/*
2680		 * The XDR decode routines may have pre-set op->status;
2681		 * for example, if there is a miscellaneous XDR error
2682		 * it will be set to nfserr_bad_xdr.
2683		 */
2684		if (op->status) {
2685			if (op->opnum == OP_OPEN)
2686				op->status = nfsd4_open_omfg(rqstp, cstate, op);
2687			goto encode_op;
2688		}
2689		if (!current_fh->fh_dentry &&
2690				!HAS_FH_FLAG(current_fh, NFSD4_FH_FOREIGN)) {
2691			if (!(op->opdesc->op_flags & ALLOWED_WITHOUT_FH)) {
2692				op->status = nfserr_nofilehandle;
2693				goto encode_op;
2694			}
2695		} else if (current_fh->fh_export &&
2696			   current_fh->fh_export->ex_fslocs.migrated &&
2697			  !(op->opdesc->op_flags & ALLOWED_ON_ABSENT_FS)) {
2698			op->status = nfserr_moved;
2699			goto encode_op;
2700		}
2701
2702		fh_clear_pre_post_attrs(current_fh);
2703
2704		/* If op is non-idempotent */
2705		if (op->opdesc->op_flags & OP_MODIFIES_SOMETHING) {
2706			/*
2707			 * Don't execute this op if we couldn't encode a
2708			 * successful reply:
2709			 */
2710			u32 plen = op->opdesc->op_rsize_bop(rqstp, op);
2711			/*
2712			 * Plus if there's another operation, make sure
2713			 * we'll have space to at least encode an error:
2714			 */
2715			if (resp->opcnt < args->opcnt)
2716				plen += COMPOUND_ERR_SLACK_SPACE;
2717			op->status = nfsd4_check_resp_size(resp, plen);
2718		}
2719
2720		if (op->status)
2721			goto encode_op;
2722
2723		if (op->opdesc->op_get_currentstateid)
2724			op->opdesc->op_get_currentstateid(cstate, &op->u);
2725		op->status = op->opdesc->op_func(rqstp, cstate, &op->u);
2726
2727		/* Only from SEQUENCE */
2728		if (cstate->status == nfserr_replay_cache) {
2729			dprintk("%s NFS4.1 replay from cache\n", __func__);
2730			status = op->status;
2731			goto out;
2732		}
2733		if (!op->status) {
2734			if (op->opdesc->op_set_currentstateid)
2735				op->opdesc->op_set_currentstateid(cstate, &op->u);
2736
2737			if (op->opdesc->op_flags & OP_CLEAR_STATEID)
2738				clear_current_stateid(cstate);
2739
2740			if (current_fh->fh_export &&
2741					need_wrongsec_check(rqstp))
2742				op->status = check_nfsd_access(current_fh->fh_export, rqstp);
2743		}
2744encode_op:
2745		if (op->status == nfserr_replay_me) {
2746			op->replay = &cstate->replay_owner->so_replay;
2747			nfsd4_encode_replay(resp->xdr, op);
2748			status = op->status = op->replay->rp_status;
2749		} else {
2750			nfsd4_encode_operation(resp, op);
2751			status = op->status;
2752		}
2753
2754		trace_nfsd_compound_status(args->client_opcnt, resp->opcnt,
2755					   status, nfsd4_op_name(op->opnum));
2756
2757		nfsd4_cstate_clear_replay(cstate);
2758		nfsd4_increment_op_stats(op->opnum);
2759	}
2760
2761	fh_put(current_fh);
2762	fh_put(save_fh);
2763	BUG_ON(cstate->replay_owner);
2764out:
2765	cstate->status = status;
2766	/* Reset deferral mechanism for RPC deferrals */
2767	set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
2768	return rpc_success;
2769}
2770
2771#define op_encode_hdr_size		(2)
2772#define op_encode_stateid_maxsz		(XDR_QUADLEN(NFS4_STATEID_SIZE))
2773#define op_encode_verifier_maxsz	(XDR_QUADLEN(NFS4_VERIFIER_SIZE))
2774#define op_encode_change_info_maxsz	(5)
2775#define nfs4_fattr_bitmap_maxsz		(4)
2776
2777/* We'll fall back on returning no lockowner if run out of space: */
2778#define op_encode_lockowner_maxsz	(0)
2779#define op_encode_lock_denied_maxsz	(8 + op_encode_lockowner_maxsz)
2780
2781#define nfs4_owner_maxsz		(1 + XDR_QUADLEN(IDMAP_NAMESZ))
2782
2783#define op_encode_ace_maxsz		(3 + nfs4_owner_maxsz)
2784#define op_encode_delegation_maxsz	(1 + op_encode_stateid_maxsz + 1 + \
2785					 op_encode_ace_maxsz)
2786
2787#define op_encode_channel_attrs_maxsz	(6 + 1 + 1)
2788
2789/*
2790 * The _rsize() helpers are invoked by the NFSv4 COMPOUND decoder, which
2791 * is called before sunrpc sets rq_res.buflen. Thus we have to compute
2792 * the maximum payload size here, based on transport limits and the size
2793 * of the remaining space in the rq_pages array.
2794 */
2795static u32 nfsd4_max_payload(const struct svc_rqst *rqstp)
2796{
2797	u32 buflen;
2798
2799	buflen = (rqstp->rq_page_end - rqstp->rq_next_page) * PAGE_SIZE;
2800	buflen -= rqstp->rq_auth_slack;
2801	buflen -= rqstp->rq_res.head[0].iov_len;
2802	return min_t(u32, buflen, svc_max_payload(rqstp));
2803}
2804
2805static u32 nfsd4_only_status_rsize(const struct svc_rqst *rqstp,
2806				   const struct nfsd4_op *op)
2807{
2808	return (op_encode_hdr_size) * sizeof(__be32);
2809}
2810
2811static u32 nfsd4_status_stateid_rsize(const struct svc_rqst *rqstp,
2812				      const struct nfsd4_op *op)
2813{
2814	return (op_encode_hdr_size + op_encode_stateid_maxsz)* sizeof(__be32);
2815}
2816
2817static u32 nfsd4_access_rsize(const struct svc_rqst *rqstp,
2818			      const struct nfsd4_op *op)
2819{
2820	/* ac_supported, ac_resp_access */
2821	return (op_encode_hdr_size + 2)* sizeof(__be32);
2822}
2823
2824static u32 nfsd4_commit_rsize(const struct svc_rqst *rqstp,
2825			      const struct nfsd4_op *op)
2826{
2827	return (op_encode_hdr_size + op_encode_verifier_maxsz) * sizeof(__be32);
2828}
2829
2830static u32 nfsd4_create_rsize(const struct svc_rqst *rqstp,
2831			      const struct nfsd4_op *op)
2832{
2833	return (op_encode_hdr_size + op_encode_change_info_maxsz
2834		+ nfs4_fattr_bitmap_maxsz) * sizeof(__be32);
2835}
2836
2837/*
2838 * Note since this is an idempotent operation we won't insist on failing
2839 * the op prematurely if the estimate is too large.  We may turn off splice
2840 * reads unnecessarily.
2841 */
2842static u32 nfsd4_getattr_rsize(const struct svc_rqst *rqstp,
2843			       const struct nfsd4_op *op)
2844{
2845	const u32 *bmap = op->u.getattr.ga_bmval;
2846	u32 bmap0 = bmap[0], bmap1 = bmap[1], bmap2 = bmap[2];
2847	u32 ret = 0;
2848
2849	if (bmap0 & FATTR4_WORD0_ACL)
2850		return nfsd4_max_payload(rqstp);
2851	if (bmap0 & FATTR4_WORD0_FS_LOCATIONS)
2852		return nfsd4_max_payload(rqstp);
2853
2854	if (bmap1 & FATTR4_WORD1_OWNER) {
2855		ret += IDMAP_NAMESZ + 4;
2856		bmap1 &= ~FATTR4_WORD1_OWNER;
2857	}
2858	if (bmap1 & FATTR4_WORD1_OWNER_GROUP) {
2859		ret += IDMAP_NAMESZ + 4;
2860		bmap1 &= ~FATTR4_WORD1_OWNER_GROUP;
2861	}
2862	if (bmap0 & FATTR4_WORD0_FILEHANDLE) {
2863		ret += NFS4_FHSIZE + 4;
2864		bmap0 &= ~FATTR4_WORD0_FILEHANDLE;
2865	}
2866	if (bmap2 & FATTR4_WORD2_SECURITY_LABEL) {
2867		ret += NFS4_MAXLABELLEN + 12;
2868		bmap2 &= ~FATTR4_WORD2_SECURITY_LABEL;
2869	}
2870	/*
2871	 * Largest of remaining attributes are 16 bytes (e.g.,
2872	 * supported_attributes)
2873	 */
2874	ret += 16 * (hweight32(bmap0) + hweight32(bmap1) + hweight32(bmap2));
2875	/* bitmask, length */
2876	ret += 20;
2877	return ret;
2878}
2879
2880static u32 nfsd4_getfh_rsize(const struct svc_rqst *rqstp,
2881			     const struct nfsd4_op *op)
2882{
2883	return (op_encode_hdr_size + 1) * sizeof(__be32) + NFS4_FHSIZE;
2884}
2885
2886static u32 nfsd4_link_rsize(const struct svc_rqst *rqstp,
2887			    const struct nfsd4_op *op)
2888{
2889	return (op_encode_hdr_size + op_encode_change_info_maxsz)
2890		* sizeof(__be32);
2891}
2892
2893static u32 nfsd4_lock_rsize(const struct svc_rqst *rqstp,
2894			    const struct nfsd4_op *op)
2895{
2896	return (op_encode_hdr_size + op_encode_lock_denied_maxsz)
2897		* sizeof(__be32);
2898}
2899
2900static u32 nfsd4_open_rsize(const struct svc_rqst *rqstp,
2901			    const struct nfsd4_op *op)
2902{
2903	return (op_encode_hdr_size + op_encode_stateid_maxsz
2904		+ op_encode_change_info_maxsz + 1
2905		+ nfs4_fattr_bitmap_maxsz
2906		+ op_encode_delegation_maxsz) * sizeof(__be32);
2907}
2908
2909static u32 nfsd4_read_rsize(const struct svc_rqst *rqstp,
2910			    const struct nfsd4_op *op)
2911{
2912	u32 rlen = min(op->u.read.rd_length, nfsd4_max_payload(rqstp));
2913
2914	return (op_encode_hdr_size + 2 + XDR_QUADLEN(rlen)) * sizeof(__be32);
2915}
2916
2917static u32 nfsd4_read_plus_rsize(const struct svc_rqst *rqstp,
2918				 const struct nfsd4_op *op)
2919{
2920	u32 rlen = min(op->u.read.rd_length, nfsd4_max_payload(rqstp));
2921	/*
2922	 * If we detect that the file changed during hole encoding, then we
2923	 * recover by encoding the remaining reply as data. This means we need
2924	 * to set aside enough room to encode two data segments.
2925	 */
2926	u32 seg_len = 2 * (1 + 2 + 1);
2927
2928	return (op_encode_hdr_size + 2 + seg_len + XDR_QUADLEN(rlen)) * sizeof(__be32);
2929}
2930
2931static u32 nfsd4_readdir_rsize(const struct svc_rqst *rqstp,
2932			       const struct nfsd4_op *op)
2933{
2934	u32 rlen = min(op->u.readdir.rd_maxcount, nfsd4_max_payload(rqstp));
2935
2936	return (op_encode_hdr_size + op_encode_verifier_maxsz +
2937		XDR_QUADLEN(rlen)) * sizeof(__be32);
2938}
2939
2940static u32 nfsd4_readlink_rsize(const struct svc_rqst *rqstp,
2941				const struct nfsd4_op *op)
2942{
2943	return (op_encode_hdr_size + 1) * sizeof(__be32) + PAGE_SIZE;
2944}
2945
2946static u32 nfsd4_remove_rsize(const struct svc_rqst *rqstp,
2947			      const struct nfsd4_op *op)
2948{
2949	return (op_encode_hdr_size + op_encode_change_info_maxsz)
2950		* sizeof(__be32);
2951}
2952
2953static u32 nfsd4_rename_rsize(const struct svc_rqst *rqstp,
2954			      const struct nfsd4_op *op)
2955{
2956	return (op_encode_hdr_size + op_encode_change_info_maxsz
2957		+ op_encode_change_info_maxsz) * sizeof(__be32);
2958}
2959
2960static u32 nfsd4_sequence_rsize(const struct svc_rqst *rqstp,
2961				const struct nfsd4_op *op)
2962{
2963	return (op_encode_hdr_size
2964		+ XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + 5) * sizeof(__be32);
2965}
2966
2967static u32 nfsd4_test_stateid_rsize(const struct svc_rqst *rqstp,
2968				    const struct nfsd4_op *op)
2969{
2970	return (op_encode_hdr_size + 1 + op->u.test_stateid.ts_num_ids)
2971		* sizeof(__be32);
2972}
2973
2974static u32 nfsd4_setattr_rsize(const struct svc_rqst *rqstp,
2975			       const struct nfsd4_op *op)
2976{
2977	return (op_encode_hdr_size + nfs4_fattr_bitmap_maxsz) * sizeof(__be32);
2978}
2979
2980static u32 nfsd4_secinfo_rsize(const struct svc_rqst *rqstp,
2981			       const struct nfsd4_op *op)
2982{
2983	return (op_encode_hdr_size + RPC_AUTH_MAXFLAVOR *
2984		(4 + XDR_QUADLEN(GSS_OID_MAX_LEN))) * sizeof(__be32);
2985}
2986
2987static u32 nfsd4_setclientid_rsize(const struct svc_rqst *rqstp,
2988				   const struct nfsd4_op *op)
2989{
2990	return (op_encode_hdr_size + 2 + XDR_QUADLEN(NFS4_VERIFIER_SIZE)) *
2991								sizeof(__be32);
2992}
2993
2994static u32 nfsd4_write_rsize(const struct svc_rqst *rqstp,
2995			     const struct nfsd4_op *op)
2996{
2997	return (op_encode_hdr_size + 2 + op_encode_verifier_maxsz) * sizeof(__be32);
2998}
2999
3000static u32 nfsd4_exchange_id_rsize(const struct svc_rqst *rqstp,
3001				   const struct nfsd4_op *op)
3002{
3003	return (op_encode_hdr_size + 2 + 1 + /* eir_clientid, eir_sequenceid */\
3004		1 + 1 + /* eir_flags, spr_how */\
3005		4 + /* spo_must_enforce & _allow with bitmap */\
3006		2 + /*eir_server_owner.so_minor_id */\
3007		/* eir_server_owner.so_major_id<> */\
3008		XDR_QUADLEN(NFS4_OPAQUE_LIMIT) + 1 +\
3009		/* eir_server_scope<> */\
3010		XDR_QUADLEN(NFS4_OPAQUE_LIMIT) + 1 +\
3011		1 + /* eir_server_impl_id array length */\
3012		0 /* ignored eir_server_impl_id contents */) * sizeof(__be32);
3013}
3014
3015static u32 nfsd4_bind_conn_to_session_rsize(const struct svc_rqst *rqstp,
3016					    const struct nfsd4_op *op)
3017{
3018	return (op_encode_hdr_size + \
3019		XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + /* bctsr_sessid */\
3020		2 /* bctsr_dir, use_conn_in_rdma_mode */) * sizeof(__be32);
3021}
3022
3023static u32 nfsd4_create_session_rsize(const struct svc_rqst *rqstp,
3024				      const struct nfsd4_op *op)
3025{
3026	return (op_encode_hdr_size + \
3027		XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + /* sessionid */\
3028		2 + /* csr_sequence, csr_flags */\
3029		op_encode_channel_attrs_maxsz + \
3030		op_encode_channel_attrs_maxsz) * sizeof(__be32);
3031}
3032
3033static u32 nfsd4_copy_rsize(const struct svc_rqst *rqstp,
3034			    const struct nfsd4_op *op)
3035{
3036	return (op_encode_hdr_size +
3037		1 /* wr_callback */ +
3038		op_encode_stateid_maxsz /* wr_callback */ +
3039		2 /* wr_count */ +
3040		1 /* wr_committed */ +
3041		op_encode_verifier_maxsz +
3042		1 /* cr_consecutive */ +
3043		1 /* cr_synchronous */) * sizeof(__be32);
3044}
3045
3046static u32 nfsd4_offload_status_rsize(const struct svc_rqst *rqstp,
3047				      const struct nfsd4_op *op)
3048{
3049	return (op_encode_hdr_size +
3050		2 /* osr_count */ +
3051		1 /* osr_complete<1> optional 0 for now */) * sizeof(__be32);
3052}
3053
3054static u32 nfsd4_copy_notify_rsize(const struct svc_rqst *rqstp,
3055				   const struct nfsd4_op *op)
3056{
3057	return (op_encode_hdr_size +
3058		3 /* cnr_lease_time */ +
3059		1 /* We support one cnr_source_server */ +
3060		1 /* cnr_stateid seq */ +
3061		op_encode_stateid_maxsz /* cnr_stateid */ +
3062		1 /* num cnr_source_server*/ +
3063		1 /* nl4_type */ +
3064		1 /* nl4 size */ +
3065		XDR_QUADLEN(NFS4_OPAQUE_LIMIT) /*nl4_loc + nl4_loc_sz */)
3066		* sizeof(__be32);
3067}
3068
3069#ifdef CONFIG_NFSD_PNFS
3070static u32 nfsd4_getdeviceinfo_rsize(const struct svc_rqst *rqstp,
3071				     const struct nfsd4_op *op)
3072{
3073	u32 rlen = min(op->u.getdeviceinfo.gd_maxcount, nfsd4_max_payload(rqstp));
3074
3075	return (op_encode_hdr_size +
3076		1 /* gd_layout_type*/ +
3077		XDR_QUADLEN(rlen) +
3078		2 /* gd_notify_types */) * sizeof(__be32);
3079}
3080
3081/*
3082 * At this stage we don't really know what layout driver will handle the request,
3083 * so we need to define an arbitrary upper bound here.
3084 */
3085#define MAX_LAYOUT_SIZE		128
3086static u32 nfsd4_layoutget_rsize(const struct svc_rqst *rqstp,
3087				 const struct nfsd4_op *op)
3088{
3089	return (op_encode_hdr_size +
3090		1 /* logr_return_on_close */ +
3091		op_encode_stateid_maxsz +
3092		1 /* nr of layouts */ +
3093		MAX_LAYOUT_SIZE) * sizeof(__be32);
3094}
3095
3096static u32 nfsd4_layoutcommit_rsize(const struct svc_rqst *rqstp,
3097				    const struct nfsd4_op *op)
3098{
3099	return (op_encode_hdr_size +
3100		1 /* locr_newsize */ +
3101		2 /* ns_size */) * sizeof(__be32);
3102}
3103
3104static u32 nfsd4_layoutreturn_rsize(const struct svc_rqst *rqstp,
3105				    const struct nfsd4_op *op)
3106{
3107	return (op_encode_hdr_size +
3108		1 /* lrs_stateid */ +
3109		op_encode_stateid_maxsz) * sizeof(__be32);
3110}
3111#endif /* CONFIG_NFSD_PNFS */
3112
3113
3114static u32 nfsd4_seek_rsize(const struct svc_rqst *rqstp,
3115			    const struct nfsd4_op *op)
3116{
3117	return (op_encode_hdr_size + 3) * sizeof(__be32);
3118}
3119
3120static u32 nfsd4_getxattr_rsize(const struct svc_rqst *rqstp,
3121				const struct nfsd4_op *op)
3122{
3123	u32 rlen = min_t(u32, XATTR_SIZE_MAX, nfsd4_max_payload(rqstp));
3124
3125	return (op_encode_hdr_size + 1 + XDR_QUADLEN(rlen)) * sizeof(__be32);
3126}
3127
3128static u32 nfsd4_setxattr_rsize(const struct svc_rqst *rqstp,
3129				const struct nfsd4_op *op)
3130{
3131	return (op_encode_hdr_size + op_encode_change_info_maxsz)
3132		* sizeof(__be32);
3133}
3134static u32 nfsd4_listxattrs_rsize(const struct svc_rqst *rqstp,
3135				  const struct nfsd4_op *op)
3136{
3137	u32 rlen = min(op->u.listxattrs.lsxa_maxcount, nfsd4_max_payload(rqstp));
3138
3139	return (op_encode_hdr_size + 4 + XDR_QUADLEN(rlen)) * sizeof(__be32);
3140}
3141
3142static u32 nfsd4_removexattr_rsize(const struct svc_rqst *rqstp,
3143				   const struct nfsd4_op *op)
3144{
3145	return (op_encode_hdr_size + op_encode_change_info_maxsz)
3146		* sizeof(__be32);
3147}
3148
3149
3150static const struct nfsd4_operation nfsd4_ops[] = {
3151	[OP_ACCESS] = {
3152		.op_func = nfsd4_access,
3153		.op_name = "OP_ACCESS",
3154		.op_rsize_bop = nfsd4_access_rsize,
3155	},
3156	[OP_CLOSE] = {
3157		.op_func = nfsd4_close,
3158		.op_flags = OP_MODIFIES_SOMETHING,
3159		.op_name = "OP_CLOSE",
3160		.op_rsize_bop = nfsd4_status_stateid_rsize,
3161		.op_get_currentstateid = nfsd4_get_closestateid,
3162		.op_set_currentstateid = nfsd4_set_closestateid,
3163	},
3164	[OP_COMMIT] = {
3165		.op_func = nfsd4_commit,
3166		.op_flags = OP_MODIFIES_SOMETHING,
3167		.op_name = "OP_COMMIT",
3168		.op_rsize_bop = nfsd4_commit_rsize,
3169	},
3170	[OP_CREATE] = {
3171		.op_func = nfsd4_create,
3172		.op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME | OP_CLEAR_STATEID,
3173		.op_name = "OP_CREATE",
3174		.op_rsize_bop = nfsd4_create_rsize,
3175	},
3176	[OP_DELEGRETURN] = {
3177		.op_func = nfsd4_delegreturn,
3178		.op_flags = OP_MODIFIES_SOMETHING,
3179		.op_name = "OP_DELEGRETURN",
3180		.op_rsize_bop = nfsd4_only_status_rsize,
3181		.op_get_currentstateid = nfsd4_get_delegreturnstateid,
3182	},
3183	[OP_GETATTR] = {
3184		.op_func = nfsd4_getattr,
3185		.op_flags = ALLOWED_ON_ABSENT_FS,
3186		.op_rsize_bop = nfsd4_getattr_rsize,
3187		.op_name = "OP_GETATTR",
3188	},
3189	[OP_GETFH] = {
3190		.op_func = nfsd4_getfh,
3191		.op_name = "OP_GETFH",
3192		.op_rsize_bop = nfsd4_getfh_rsize,
3193	},
3194	[OP_LINK] = {
3195		.op_func = nfsd4_link,
3196		.op_flags = ALLOWED_ON_ABSENT_FS | OP_MODIFIES_SOMETHING
3197				| OP_CACHEME,
3198		.op_name = "OP_LINK",
3199		.op_rsize_bop = nfsd4_link_rsize,
3200	},
3201	[OP_LOCK] = {
3202		.op_func = nfsd4_lock,
3203		.op_flags = OP_MODIFIES_SOMETHING |
3204				OP_NONTRIVIAL_ERROR_ENCODE,
3205		.op_name = "OP_LOCK",
3206		.op_rsize_bop = nfsd4_lock_rsize,
3207		.op_set_currentstateid = nfsd4_set_lockstateid,
3208	},
3209	[OP_LOCKT] = {
3210		.op_func = nfsd4_lockt,
3211		.op_flags = OP_NONTRIVIAL_ERROR_ENCODE,
3212		.op_name = "OP_LOCKT",
3213		.op_rsize_bop = nfsd4_lock_rsize,
3214	},
3215	[OP_LOCKU] = {
3216		.op_func = nfsd4_locku,
3217		.op_flags = OP_MODIFIES_SOMETHING,
3218		.op_name = "OP_LOCKU",
3219		.op_rsize_bop = nfsd4_status_stateid_rsize,
3220		.op_get_currentstateid = nfsd4_get_lockustateid,
3221	},
3222	[OP_LOOKUP] = {
3223		.op_func = nfsd4_lookup,
3224		.op_flags = OP_HANDLES_WRONGSEC | OP_CLEAR_STATEID,
3225		.op_name = "OP_LOOKUP",
3226		.op_rsize_bop = nfsd4_only_status_rsize,
3227	},
3228	[OP_LOOKUPP] = {
3229		.op_func = nfsd4_lookupp,
3230		.op_flags = OP_HANDLES_WRONGSEC | OP_CLEAR_STATEID,
3231		.op_name = "OP_LOOKUPP",
3232		.op_rsize_bop = nfsd4_only_status_rsize,
3233	},
3234	[OP_NVERIFY] = {
3235		.op_func = nfsd4_nverify,
3236		.op_name = "OP_NVERIFY",
3237		.op_rsize_bop = nfsd4_only_status_rsize,
3238	},
3239	[OP_OPEN] = {
3240		.op_func = nfsd4_open,
3241		.op_flags = OP_HANDLES_WRONGSEC | OP_MODIFIES_SOMETHING,
3242		.op_name = "OP_OPEN",
3243		.op_rsize_bop = nfsd4_open_rsize,
3244		.op_set_currentstateid = nfsd4_set_openstateid,
3245	},
3246	[OP_OPEN_CONFIRM] = {
3247		.op_func = nfsd4_open_confirm,
3248		.op_flags = OP_MODIFIES_SOMETHING,
3249		.op_name = "OP_OPEN_CONFIRM",
3250		.op_rsize_bop = nfsd4_status_stateid_rsize,
3251	},
3252	[OP_OPEN_DOWNGRADE] = {
3253		.op_func = nfsd4_open_downgrade,
3254		.op_flags = OP_MODIFIES_SOMETHING,
3255		.op_name = "OP_OPEN_DOWNGRADE",
3256		.op_rsize_bop = nfsd4_status_stateid_rsize,
3257		.op_get_currentstateid = nfsd4_get_opendowngradestateid,
3258		.op_set_currentstateid = nfsd4_set_opendowngradestateid,
3259	},
3260	[OP_PUTFH] = {
3261		.op_func = nfsd4_putfh,
3262		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS
3263				| OP_IS_PUTFH_LIKE | OP_CLEAR_STATEID,
3264		.op_name = "OP_PUTFH",
3265		.op_rsize_bop = nfsd4_only_status_rsize,
3266	},
3267	[OP_PUTPUBFH] = {
3268		.op_func = nfsd4_putrootfh,
3269		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS
3270				| OP_IS_PUTFH_LIKE | OP_CLEAR_STATEID,
3271		.op_name = "OP_PUTPUBFH",
3272		.op_rsize_bop = nfsd4_only_status_rsize,
3273	},
3274	[OP_PUTROOTFH] = {
3275		.op_func = nfsd4_putrootfh,
3276		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS
3277				| OP_IS_PUTFH_LIKE | OP_CLEAR_STATEID,
3278		.op_name = "OP_PUTROOTFH",
3279		.op_rsize_bop = nfsd4_only_status_rsize,
3280	},
3281	[OP_READ] = {
3282		.op_func = nfsd4_read,
3283		.op_release = nfsd4_read_release,
3284		.op_name = "OP_READ",
3285		.op_rsize_bop = nfsd4_read_rsize,
3286		.op_get_currentstateid = nfsd4_get_readstateid,
3287	},
3288	[OP_READDIR] = {
3289		.op_func = nfsd4_readdir,
3290		.op_name = "OP_READDIR",
3291		.op_rsize_bop = nfsd4_readdir_rsize,
3292	},
3293	[OP_READLINK] = {
3294		.op_func = nfsd4_readlink,
3295		.op_name = "OP_READLINK",
3296		.op_rsize_bop = nfsd4_readlink_rsize,
3297	},
3298	[OP_REMOVE] = {
3299		.op_func = nfsd4_remove,
3300		.op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME,
3301		.op_name = "OP_REMOVE",
3302		.op_rsize_bop = nfsd4_remove_rsize,
3303	},
3304	[OP_RENAME] = {
3305		.op_func = nfsd4_rename,
3306		.op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME,
3307		.op_name = "OP_RENAME",
3308		.op_rsize_bop = nfsd4_rename_rsize,
3309	},
3310	[OP_RENEW] = {
3311		.op_func = nfsd4_renew,
3312		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS
3313				| OP_MODIFIES_SOMETHING,
3314		.op_name = "OP_RENEW",
3315		.op_rsize_bop = nfsd4_only_status_rsize,
3316
3317	},
3318	[OP_RESTOREFH] = {
3319		.op_func = nfsd4_restorefh,
3320		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS
3321				| OP_IS_PUTFH_LIKE | OP_MODIFIES_SOMETHING,
3322		.op_name = "OP_RESTOREFH",
3323		.op_rsize_bop = nfsd4_only_status_rsize,
3324	},
3325	[OP_SAVEFH] = {
3326		.op_func = nfsd4_savefh,
3327		.op_flags = OP_HANDLES_WRONGSEC | OP_MODIFIES_SOMETHING,
3328		.op_name = "OP_SAVEFH",
3329		.op_rsize_bop = nfsd4_only_status_rsize,
3330	},
3331	[OP_SECINFO] = {
3332		.op_func = nfsd4_secinfo,
3333		.op_release = nfsd4_secinfo_release,
3334		.op_flags = OP_HANDLES_WRONGSEC,
3335		.op_name = "OP_SECINFO",
3336		.op_rsize_bop = nfsd4_secinfo_rsize,
3337	},
3338	[OP_SETATTR] = {
3339		.op_func = nfsd4_setattr,
3340		.op_name = "OP_SETATTR",
3341		.op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME
3342				| OP_NONTRIVIAL_ERROR_ENCODE,
3343		.op_rsize_bop = nfsd4_setattr_rsize,
3344		.op_get_currentstateid = nfsd4_get_setattrstateid,
3345	},
3346	[OP_SETCLIENTID] = {
3347		.op_func = nfsd4_setclientid,
3348		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS
3349				| OP_MODIFIES_SOMETHING | OP_CACHEME
3350				| OP_NONTRIVIAL_ERROR_ENCODE,
3351		.op_name = "OP_SETCLIENTID",
3352		.op_rsize_bop = nfsd4_setclientid_rsize,
3353	},
3354	[OP_SETCLIENTID_CONFIRM] = {
3355		.op_func = nfsd4_setclientid_confirm,
3356		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS
3357				| OP_MODIFIES_SOMETHING | OP_CACHEME,
3358		.op_name = "OP_SETCLIENTID_CONFIRM",
3359		.op_rsize_bop = nfsd4_only_status_rsize,
3360	},
3361	[OP_VERIFY] = {
3362		.op_func = nfsd4_verify,
3363		.op_name = "OP_VERIFY",
3364		.op_rsize_bop = nfsd4_only_status_rsize,
3365	},
3366	[OP_WRITE] = {
3367		.op_func = nfsd4_write,
3368		.op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME,
3369		.op_name = "OP_WRITE",
3370		.op_rsize_bop = nfsd4_write_rsize,
3371		.op_get_currentstateid = nfsd4_get_writestateid,
3372	},
3373	[OP_RELEASE_LOCKOWNER] = {
3374		.op_func = nfsd4_release_lockowner,
3375		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS
3376				| OP_MODIFIES_SOMETHING,
3377		.op_name = "OP_RELEASE_LOCKOWNER",
3378		.op_rsize_bop = nfsd4_only_status_rsize,
3379	},
3380
3381	/* NFSv4.1 operations */
3382	[OP_EXCHANGE_ID] = {
3383		.op_func = nfsd4_exchange_id,
3384		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP
3385				| OP_MODIFIES_SOMETHING,
3386		.op_name = "OP_EXCHANGE_ID",
3387		.op_rsize_bop = nfsd4_exchange_id_rsize,
3388	},
3389	[OP_BACKCHANNEL_CTL] = {
3390		.op_func = nfsd4_backchannel_ctl,
3391		.op_flags = ALLOWED_WITHOUT_FH | OP_MODIFIES_SOMETHING,
3392		.op_name = "OP_BACKCHANNEL_CTL",
3393		.op_rsize_bop = nfsd4_only_status_rsize,
3394	},
3395	[OP_BIND_CONN_TO_SESSION] = {
3396		.op_func = nfsd4_bind_conn_to_session,
3397		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP
3398				| OP_MODIFIES_SOMETHING,
3399		.op_name = "OP_BIND_CONN_TO_SESSION",
3400		.op_rsize_bop = nfsd4_bind_conn_to_session_rsize,
3401	},
3402	[OP_CREATE_SESSION] = {
3403		.op_func = nfsd4_create_session,
3404		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP
3405				| OP_MODIFIES_SOMETHING,
3406		.op_name = "OP_CREATE_SESSION",
3407		.op_rsize_bop = nfsd4_create_session_rsize,
3408	},
3409	[OP_DESTROY_SESSION] = {
3410		.op_func = nfsd4_destroy_session,
3411		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP
3412				| OP_MODIFIES_SOMETHING,
3413		.op_name = "OP_DESTROY_SESSION",
3414		.op_rsize_bop = nfsd4_only_status_rsize,
3415	},
3416	[OP_SEQUENCE] = {
3417		.op_func = nfsd4_sequence,
3418		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP,
3419		.op_name = "OP_SEQUENCE",
3420		.op_rsize_bop = nfsd4_sequence_rsize,
3421	},
3422	[OP_DESTROY_CLIENTID] = {
3423		.op_func = nfsd4_destroy_clientid,
3424		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP
3425				| OP_MODIFIES_SOMETHING,
3426		.op_name = "OP_DESTROY_CLIENTID",
3427		.op_rsize_bop = nfsd4_only_status_rsize,
3428	},
3429	[OP_RECLAIM_COMPLETE] = {
3430		.op_func = nfsd4_reclaim_complete,
3431		.op_flags = ALLOWED_WITHOUT_FH | OP_MODIFIES_SOMETHING,
3432		.op_name = "OP_RECLAIM_COMPLETE",
3433		.op_rsize_bop = nfsd4_only_status_rsize,
3434	},
3435	[OP_SECINFO_NO_NAME] = {
3436		.op_func = nfsd4_secinfo_no_name,
3437		.op_release = nfsd4_secinfo_no_name_release,
3438		.op_flags = OP_HANDLES_WRONGSEC,
3439		.op_name = "OP_SECINFO_NO_NAME",
3440		.op_rsize_bop = nfsd4_secinfo_rsize,
3441	},
3442	[OP_TEST_STATEID] = {
3443		.op_func = nfsd4_test_stateid,
3444		.op_flags = ALLOWED_WITHOUT_FH,
3445		.op_name = "OP_TEST_STATEID",
3446		.op_rsize_bop = nfsd4_test_stateid_rsize,
3447	},
3448	[OP_FREE_STATEID] = {
3449		.op_func = nfsd4_free_stateid,
3450		.op_flags = ALLOWED_WITHOUT_FH | OP_MODIFIES_SOMETHING,
3451		.op_name = "OP_FREE_STATEID",
3452		.op_get_currentstateid = nfsd4_get_freestateid,
3453		.op_rsize_bop = nfsd4_only_status_rsize,
3454	},
3455#ifdef CONFIG_NFSD_PNFS
3456	[OP_GETDEVICEINFO] = {
3457		.op_func = nfsd4_getdeviceinfo,
3458		.op_release = nfsd4_getdeviceinfo_release,
3459		.op_flags = ALLOWED_WITHOUT_FH,
3460		.op_name = "OP_GETDEVICEINFO",
3461		.op_rsize_bop = nfsd4_getdeviceinfo_rsize,
3462	},
3463	[OP_LAYOUTGET] = {
3464		.op_func = nfsd4_layoutget,
3465		.op_release = nfsd4_layoutget_release,
3466		.op_flags = OP_MODIFIES_SOMETHING,
3467		.op_name = "OP_LAYOUTGET",
3468		.op_rsize_bop = nfsd4_layoutget_rsize,
3469	},
3470	[OP_LAYOUTCOMMIT] = {
3471		.op_func = nfsd4_layoutcommit,
3472		.op_flags = OP_MODIFIES_SOMETHING,
3473		.op_name = "OP_LAYOUTCOMMIT",
3474		.op_rsize_bop = nfsd4_layoutcommit_rsize,
3475	},
3476	[OP_LAYOUTRETURN] = {
3477		.op_func = nfsd4_layoutreturn,
3478		.op_flags = OP_MODIFIES_SOMETHING,
3479		.op_name = "OP_LAYOUTRETURN",
3480		.op_rsize_bop = nfsd4_layoutreturn_rsize,
3481	},
3482#endif /* CONFIG_NFSD_PNFS */
3483
3484	/* NFSv4.2 operations */
3485	[OP_ALLOCATE] = {
3486		.op_func = nfsd4_allocate,
3487		.op_flags = OP_MODIFIES_SOMETHING,
3488		.op_name = "OP_ALLOCATE",
3489		.op_rsize_bop = nfsd4_only_status_rsize,
3490	},
3491	[OP_DEALLOCATE] = {
3492		.op_func = nfsd4_deallocate,
3493		.op_flags = OP_MODIFIES_SOMETHING,
3494		.op_name = "OP_DEALLOCATE",
3495		.op_rsize_bop = nfsd4_only_status_rsize,
3496	},
3497	[OP_CLONE] = {
3498		.op_func = nfsd4_clone,
3499		.op_flags = OP_MODIFIES_SOMETHING,
3500		.op_name = "OP_CLONE",
3501		.op_rsize_bop = nfsd4_only_status_rsize,
3502	},
3503	[OP_COPY] = {
3504		.op_func = nfsd4_copy,
3505		.op_flags = OP_MODIFIES_SOMETHING,
3506		.op_name = "OP_COPY",
3507		.op_rsize_bop = nfsd4_copy_rsize,
3508	},
3509	[OP_READ_PLUS] = {
3510		.op_func = nfsd4_read,
3511		.op_release = nfsd4_read_release,
3512		.op_name = "OP_READ_PLUS",
3513		.op_rsize_bop = nfsd4_read_plus_rsize,
3514		.op_get_currentstateid = nfsd4_get_readstateid,
3515	},
3516	[OP_SEEK] = {
3517		.op_func = nfsd4_seek,
3518		.op_name = "OP_SEEK",
3519		.op_rsize_bop = nfsd4_seek_rsize,
3520	},
3521	[OP_OFFLOAD_STATUS] = {
3522		.op_func = nfsd4_offload_status,
3523		.op_name = "OP_OFFLOAD_STATUS",
3524		.op_rsize_bop = nfsd4_offload_status_rsize,
3525	},
3526	[OP_OFFLOAD_CANCEL] = {
3527		.op_func = nfsd4_offload_cancel,
3528		.op_flags = OP_MODIFIES_SOMETHING,
3529		.op_name = "OP_OFFLOAD_CANCEL",
3530		.op_rsize_bop = nfsd4_only_status_rsize,
3531	},
3532	[OP_COPY_NOTIFY] = {
3533		.op_func = nfsd4_copy_notify,
3534		.op_flags = OP_MODIFIES_SOMETHING,
3535		.op_name = "OP_COPY_NOTIFY",
3536		.op_rsize_bop = nfsd4_copy_notify_rsize,
3537	},
3538	[OP_GETXATTR] = {
3539		.op_func = nfsd4_getxattr,
3540		.op_name = "OP_GETXATTR",
3541		.op_rsize_bop = nfsd4_getxattr_rsize,
3542	},
3543	[OP_SETXATTR] = {
3544		.op_func = nfsd4_setxattr,
3545		.op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME,
3546		.op_name = "OP_SETXATTR",
3547		.op_rsize_bop = nfsd4_setxattr_rsize,
3548	},
3549	[OP_LISTXATTRS] = {
3550		.op_func = nfsd4_listxattrs,
3551		.op_name = "OP_LISTXATTRS",
3552		.op_rsize_bop = nfsd4_listxattrs_rsize,
3553	},
3554	[OP_REMOVEXATTR] = {
3555		.op_func = nfsd4_removexattr,
3556		.op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME,
3557		.op_name = "OP_REMOVEXATTR",
3558		.op_rsize_bop = nfsd4_removexattr_rsize,
3559	},
3560};
3561
3562/**
3563 * nfsd4_spo_must_allow - Determine if the compound op contains an
3564 * operation that is allowed to be sent with machine credentials
3565 *
3566 * @rqstp: a pointer to the struct svc_rqst
3567 *
3568 * Checks to see if the compound contains a spo_must_allow op
3569 * and confirms that it was sent with the proper machine creds.
3570 */
3571
3572bool nfsd4_spo_must_allow(struct svc_rqst *rqstp)
3573{
3574	struct nfsd4_compoundres *resp = rqstp->rq_resp;
3575	struct nfsd4_compoundargs *argp = rqstp->rq_argp;
3576	struct nfsd4_op *this;
3577	struct nfsd4_compound_state *cstate = &resp->cstate;
3578	struct nfs4_op_map *allow = &cstate->clp->cl_spo_must_allow;
3579	u32 opiter;
3580
3581	if (!cstate->minorversion)
3582		return false;
3583
3584	if (cstate->spo_must_allowed)
3585		return true;
3586
3587	opiter = resp->opcnt;
3588	while (opiter < argp->opcnt) {
3589		this = &argp->ops[opiter++];
3590		if (test_bit(this->opnum, allow->u.longs) &&
3591			cstate->clp->cl_mach_cred &&
3592			nfsd4_mach_creds_match(cstate->clp, rqstp)) {
3593			cstate->spo_must_allowed = true;
3594			return true;
3595		}
3596	}
3597	cstate->spo_must_allowed = false;
3598	return false;
3599}
3600
3601int nfsd4_max_reply(struct svc_rqst *rqstp, struct nfsd4_op *op)
3602{
3603	if (op->opnum == OP_ILLEGAL || op->status == nfserr_notsupp)
3604		return op_encode_hdr_size * sizeof(__be32);
3605
3606	BUG_ON(OPDESC(op)->op_rsize_bop == NULL);
3607	return OPDESC(op)->op_rsize_bop(rqstp, op);
3608}
3609
3610void warn_on_nonidempotent_op(struct nfsd4_op *op)
3611{
3612	if (OPDESC(op)->op_flags & OP_MODIFIES_SOMETHING) {
3613		pr_err("unable to encode reply to nonidempotent op %u (%s)\n",
3614			op->opnum, nfsd4_op_name(op->opnum));
3615		WARN_ON_ONCE(1);
3616	}
3617}
3618
3619static const char *nfsd4_op_name(unsigned opnum)
3620{
3621	if (opnum < ARRAY_SIZE(nfsd4_ops))
3622		return nfsd4_ops[opnum].op_name;
3623	return "unknown_operation";
3624}
3625
3626static const struct svc_procedure nfsd_procedures4[2] = {
3627	[NFSPROC4_NULL] = {
3628		.pc_func = nfsd4_proc_null,
3629		.pc_decode = nfssvc_decode_voidarg,
3630		.pc_encode = nfssvc_encode_voidres,
3631		.pc_argsize = sizeof(struct nfsd_voidargs),
3632		.pc_argzero = sizeof(struct nfsd_voidargs),
3633		.pc_ressize = sizeof(struct nfsd_voidres),
3634		.pc_cachetype = RC_NOCACHE,
3635		.pc_xdrressize = 1,
3636		.pc_name = "NULL",
3637	},
3638	[NFSPROC4_COMPOUND] = {
3639		.pc_func = nfsd4_proc_compound,
3640		.pc_decode = nfs4svc_decode_compoundargs,
3641		.pc_encode = nfs4svc_encode_compoundres,
3642		.pc_argsize = sizeof(struct nfsd4_compoundargs),
3643		.pc_argzero = offsetof(struct nfsd4_compoundargs, iops),
3644		.pc_ressize = sizeof(struct nfsd4_compoundres),
3645		.pc_release = nfsd4_release_compoundargs,
3646		.pc_cachetype = RC_NOCACHE,
3647		.pc_xdrressize = NFSD_BUFSIZE/4,
3648		.pc_name = "COMPOUND",
3649	},
3650};
3651
3652static DEFINE_PER_CPU_ALIGNED(unsigned long,
3653			      nfsd_count4[ARRAY_SIZE(nfsd_procedures4)]);
3654const struct svc_version nfsd_version4 = {
3655	.vs_vers		= 4,
3656	.vs_nproc		= ARRAY_SIZE(nfsd_procedures4),
3657	.vs_proc		= nfsd_procedures4,
3658	.vs_count		= nfsd_count4,
3659	.vs_dispatch		= nfsd_dispatch,
3660	.vs_xdrsize		= NFS4_SVC_XDRSIZE,
3661	.vs_rpcb_optnl		= true,
3662	.vs_need_cong_ctrl	= true,
3663};
3664