xref: /kernel/linux/linux-5.10/fs/nfs/inode.c (revision 8c2ecf20)
1// SPDX-License-Identifier: GPL-2.0-only
2/*
3 *  linux/fs/nfs/inode.c
4 *
5 *  Copyright (C) 1992  Rick Sladkey
6 *
7 *  nfs inode and superblock handling functions
8 *
9 *  Modularised by Alan Cox <alan@lxorguk.ukuu.org.uk>, while hacking some
10 *  experimental NFS changes. Modularisation taken straight from SYS5 fs.
11 *
12 *  Change to nfs_read_super() to permit NFS mounts to multi-homed hosts.
13 *  J.S.Peatfield@damtp.cam.ac.uk
14 *
15 */
16
17#include <linux/module.h>
18#include <linux/init.h>
19#include <linux/sched/signal.h>
20#include <linux/time.h>
21#include <linux/kernel.h>
22#include <linux/mm.h>
23#include <linux/string.h>
24#include <linux/stat.h>
25#include <linux/errno.h>
26#include <linux/unistd.h>
27#include <linux/sunrpc/clnt.h>
28#include <linux/sunrpc/stats.h>
29#include <linux/sunrpc/metrics.h>
30#include <linux/nfs_fs.h>
31#include <linux/nfs_mount.h>
32#include <linux/nfs4_mount.h>
33#include <linux/lockd/bind.h>
34#include <linux/seq_file.h>
35#include <linux/mount.h>
36#include <linux/vfs.h>
37#include <linux/inet.h>
38#include <linux/nfs_xdr.h>
39#include <linux/slab.h>
40#include <linux/compat.h>
41#include <linux/freezer.h>
42#include <linux/uaccess.h>
43#include <linux/iversion.h>
44
45#include "nfs4_fs.h"
46#include "callback.h"
47#include "delegation.h"
48#include "iostat.h"
49#include "internal.h"
50#include "fscache.h"
51#include "pnfs.h"
52#include "nfs.h"
53#include "netns.h"
54#include "sysfs.h"
55
56#include "nfstrace.h"
57
58#define NFSDBG_FACILITY		NFSDBG_VFS
59
60#define NFS_64_BIT_INODE_NUMBERS_ENABLED	1
61
62/* Default is to see 64-bit inode numbers */
63static bool enable_ino64 = NFS_64_BIT_INODE_NUMBERS_ENABLED;
64
65static int nfs_update_inode(struct inode *, struct nfs_fattr *);
66
67static struct kmem_cache * nfs_inode_cachep;
68
69static inline unsigned long
70nfs_fattr_to_ino_t(struct nfs_fattr *fattr)
71{
72	return nfs_fileid_to_ino_t(fattr->fileid);
73}
74
75static int nfs_wait_killable(int mode)
76{
77	freezable_schedule_unsafe();
78	if (signal_pending_state(mode, current))
79		return -ERESTARTSYS;
80	return 0;
81}
82
83int nfs_wait_bit_killable(struct wait_bit_key *key, int mode)
84{
85	return nfs_wait_killable(mode);
86}
87EXPORT_SYMBOL_GPL(nfs_wait_bit_killable);
88
89/**
90 * nfs_compat_user_ino64 - returns the user-visible inode number
91 * @fileid: 64-bit fileid
92 *
93 * This function returns a 32-bit inode number if the boot parameter
94 * nfs.enable_ino64 is zero.
95 */
96u64 nfs_compat_user_ino64(u64 fileid)
97{
98#ifdef CONFIG_COMPAT
99	compat_ulong_t ino;
100#else
101	unsigned long ino;
102#endif
103
104	if (enable_ino64)
105		return fileid;
106	ino = fileid;
107	if (sizeof(ino) < sizeof(fileid))
108		ino ^= fileid >> (sizeof(fileid)-sizeof(ino)) * 8;
109	return ino;
110}
111
112int nfs_drop_inode(struct inode *inode)
113{
114	return NFS_STALE(inode) || generic_drop_inode(inode);
115}
116EXPORT_SYMBOL_GPL(nfs_drop_inode);
117
118void nfs_clear_inode(struct inode *inode)
119{
120	/*
121	 * The following should never happen...
122	 */
123	WARN_ON_ONCE(nfs_have_writebacks(inode));
124	WARN_ON_ONCE(!list_empty(&NFS_I(inode)->open_files));
125	nfs_zap_acl_cache(inode);
126	nfs_access_zap_cache(inode);
127	nfs_fscache_clear_inode(inode);
128}
129EXPORT_SYMBOL_GPL(nfs_clear_inode);
130
131void nfs_evict_inode(struct inode *inode)
132{
133	truncate_inode_pages_final(&inode->i_data);
134	clear_inode(inode);
135	nfs_clear_inode(inode);
136}
137
138int nfs_sync_inode(struct inode *inode)
139{
140	inode_dio_wait(inode);
141	return nfs_wb_all(inode);
142}
143EXPORT_SYMBOL_GPL(nfs_sync_inode);
144
145/**
146 * nfs_sync_mapping - helper to flush all mmapped dirty data to disk
147 * @mapping: pointer to struct address_space
148 */
149int nfs_sync_mapping(struct address_space *mapping)
150{
151	int ret = 0;
152
153	if (mapping->nrpages != 0) {
154		unmap_mapping_range(mapping, 0, 0, 0);
155		ret = nfs_wb_all(mapping->host);
156	}
157	return ret;
158}
159
160static int nfs_attribute_timeout(struct inode *inode)
161{
162	struct nfs_inode *nfsi = NFS_I(inode);
163
164	return !time_in_range_open(jiffies, nfsi->read_cache_jiffies, nfsi->read_cache_jiffies + nfsi->attrtimeo);
165}
166
167static bool nfs_check_cache_invalid_delegated(struct inode *inode, unsigned long flags)
168{
169	unsigned long cache_validity = READ_ONCE(NFS_I(inode)->cache_validity);
170
171	/* Special case for the pagecache or access cache */
172	if (flags == NFS_INO_REVAL_PAGECACHE &&
173	    !(cache_validity & NFS_INO_REVAL_FORCED))
174		return false;
175	return (cache_validity & flags) != 0;
176}
177
178static bool nfs_check_cache_invalid_not_delegated(struct inode *inode, unsigned long flags)
179{
180	unsigned long cache_validity = READ_ONCE(NFS_I(inode)->cache_validity);
181
182	if ((cache_validity & flags) != 0)
183		return true;
184	if (nfs_attribute_timeout(inode))
185		return true;
186	return false;
187}
188
189bool nfs_check_cache_invalid(struct inode *inode, unsigned long flags)
190{
191	if (NFS_PROTO(inode)->have_delegation(inode, FMODE_READ))
192		return nfs_check_cache_invalid_delegated(inode, flags);
193
194	return nfs_check_cache_invalid_not_delegated(inode, flags);
195}
196EXPORT_SYMBOL_GPL(nfs_check_cache_invalid);
197
198#ifdef CONFIG_NFS_V4_2
199static bool nfs_has_xattr_cache(const struct nfs_inode *nfsi)
200{
201	return nfsi->xattr_cache != NULL;
202}
203#else
204static bool nfs_has_xattr_cache(const struct nfs_inode *nfsi)
205{
206	return false;
207}
208#endif
209
210static void nfs_set_cache_invalid(struct inode *inode, unsigned long flags)
211{
212	struct nfs_inode *nfsi = NFS_I(inode);
213	bool have_delegation = NFS_PROTO(inode)->have_delegation(inode, FMODE_READ);
214
215	if (have_delegation) {
216		if (!(flags & NFS_INO_REVAL_FORCED))
217			flags &= ~NFS_INO_INVALID_OTHER;
218		flags &= ~(NFS_INO_INVALID_CHANGE
219				| NFS_INO_INVALID_SIZE
220				| NFS_INO_REVAL_PAGECACHE
221				| NFS_INO_INVALID_XATTR);
222	} else if (flags & NFS_INO_REVAL_PAGECACHE)
223		flags |= NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_SIZE;
224
225	if (!nfs_has_xattr_cache(nfsi))
226		flags &= ~NFS_INO_INVALID_XATTR;
227	if (inode->i_mapping->nrpages == 0)
228		flags &= ~(NFS_INO_INVALID_DATA|NFS_INO_DATA_INVAL_DEFER);
229	nfsi->cache_validity |= flags;
230	if (flags & NFS_INO_INVALID_DATA)
231		nfs_fscache_invalidate(inode);
232}
233
234/*
235 * Invalidate the local caches
236 */
237static void nfs_zap_caches_locked(struct inode *inode)
238{
239	struct nfs_inode *nfsi = NFS_I(inode);
240	int mode = inode->i_mode;
241
242	nfs_inc_stats(inode, NFSIOS_ATTRINVALIDATE);
243
244	nfsi->attrtimeo = NFS_MINATTRTIMEO(inode);
245	nfsi->attrtimeo_timestamp = jiffies;
246
247	memset(NFS_I(inode)->cookieverf, 0, sizeof(NFS_I(inode)->cookieverf));
248	if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) {
249		nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR
250					| NFS_INO_INVALID_DATA
251					| NFS_INO_INVALID_ACCESS
252					| NFS_INO_INVALID_ACL
253					| NFS_INO_INVALID_XATTR
254					| NFS_INO_REVAL_PAGECACHE);
255	} else
256		nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR
257					| NFS_INO_INVALID_ACCESS
258					| NFS_INO_INVALID_ACL
259					| NFS_INO_INVALID_XATTR
260					| NFS_INO_REVAL_PAGECACHE);
261	nfs_zap_label_cache_locked(nfsi);
262}
263
264void nfs_zap_caches(struct inode *inode)
265{
266	spin_lock(&inode->i_lock);
267	nfs_zap_caches_locked(inode);
268	spin_unlock(&inode->i_lock);
269}
270
271void nfs_zap_mapping(struct inode *inode, struct address_space *mapping)
272{
273	if (mapping->nrpages != 0) {
274		spin_lock(&inode->i_lock);
275		nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA);
276		spin_unlock(&inode->i_lock);
277	}
278}
279
280void nfs_zap_acl_cache(struct inode *inode)
281{
282	void (*clear_acl_cache)(struct inode *);
283
284	clear_acl_cache = NFS_PROTO(inode)->clear_acl_cache;
285	if (clear_acl_cache != NULL)
286		clear_acl_cache(inode);
287	spin_lock(&inode->i_lock);
288	NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_ACL;
289	spin_unlock(&inode->i_lock);
290}
291EXPORT_SYMBOL_GPL(nfs_zap_acl_cache);
292
293void nfs_invalidate_atime(struct inode *inode)
294{
295	spin_lock(&inode->i_lock);
296	nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATIME);
297	spin_unlock(&inode->i_lock);
298}
299EXPORT_SYMBOL_GPL(nfs_invalidate_atime);
300
301/*
302 * Invalidate, but do not unhash, the inode.
303 * NB: must be called with inode->i_lock held!
304 */
305static void nfs_set_inode_stale_locked(struct inode *inode)
306{
307	set_bit(NFS_INO_STALE, &NFS_I(inode)->flags);
308	nfs_zap_caches_locked(inode);
309	trace_nfs_set_inode_stale(inode);
310}
311
312void nfs_set_inode_stale(struct inode *inode)
313{
314	spin_lock(&inode->i_lock);
315	nfs_set_inode_stale_locked(inode);
316	spin_unlock(&inode->i_lock);
317}
318
319struct nfs_find_desc {
320	struct nfs_fh		*fh;
321	struct nfs_fattr	*fattr;
322};
323
324/*
325 * In NFSv3 we can have 64bit inode numbers. In order to support
326 * this, and re-exported directories (also seen in NFSv2)
327 * we are forced to allow 2 different inodes to have the same
328 * i_ino.
329 */
330static int
331nfs_find_actor(struct inode *inode, void *opaque)
332{
333	struct nfs_find_desc	*desc = (struct nfs_find_desc *)opaque;
334	struct nfs_fh		*fh = desc->fh;
335	struct nfs_fattr	*fattr = desc->fattr;
336
337	if (NFS_FILEID(inode) != fattr->fileid)
338		return 0;
339	if (inode_wrong_type(inode, fattr->mode))
340		return 0;
341	if (nfs_compare_fh(NFS_FH(inode), fh))
342		return 0;
343	if (is_bad_inode(inode) || NFS_STALE(inode))
344		return 0;
345	return 1;
346}
347
348static int
349nfs_init_locked(struct inode *inode, void *opaque)
350{
351	struct nfs_find_desc	*desc = (struct nfs_find_desc *)opaque;
352	struct nfs_fattr	*fattr = desc->fattr;
353
354	set_nfs_fileid(inode, fattr->fileid);
355	inode->i_mode = fattr->mode;
356	nfs_copy_fh(NFS_FH(inode), desc->fh);
357	return 0;
358}
359
360#ifdef CONFIG_NFS_V4_SECURITY_LABEL
361static void nfs_clear_label_invalid(struct inode *inode)
362{
363	spin_lock(&inode->i_lock);
364	NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_LABEL;
365	spin_unlock(&inode->i_lock);
366}
367
368void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr,
369					struct nfs4_label *label)
370{
371	int error;
372
373	if (label == NULL)
374		return;
375
376	if ((fattr->valid & NFS_ATTR_FATTR_V4_SECURITY_LABEL) && inode->i_security) {
377		error = security_inode_notifysecctx(inode, label->label,
378				label->len);
379		if (error)
380			printk(KERN_ERR "%s() %s %d "
381					"security_inode_notifysecctx() %d\n",
382					__func__,
383					(char *)label->label,
384					label->len, error);
385		nfs_clear_label_invalid(inode);
386	}
387}
388
389struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags)
390{
391	struct nfs4_label *label = NULL;
392	int minor_version = server->nfs_client->cl_minorversion;
393
394	if (minor_version < 2)
395		return label;
396
397	if (!(server->caps & NFS_CAP_SECURITY_LABEL))
398		return label;
399
400	label = kzalloc(sizeof(struct nfs4_label), flags);
401	if (label == NULL)
402		return ERR_PTR(-ENOMEM);
403
404	label->label = kzalloc(NFS4_MAXLABELLEN, flags);
405	if (label->label == NULL) {
406		kfree(label);
407		return ERR_PTR(-ENOMEM);
408	}
409	label->len = NFS4_MAXLABELLEN;
410
411	return label;
412}
413EXPORT_SYMBOL_GPL(nfs4_label_alloc);
414#else
415void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr,
416					struct nfs4_label *label)
417{
418}
419#endif
420EXPORT_SYMBOL_GPL(nfs_setsecurity);
421
422/* Search for inode identified by fh, fileid and i_mode in inode cache. */
423struct inode *
424nfs_ilookup(struct super_block *sb, struct nfs_fattr *fattr, struct nfs_fh *fh)
425{
426	struct nfs_find_desc desc = {
427		.fh	= fh,
428		.fattr	= fattr,
429	};
430	struct inode *inode;
431	unsigned long hash;
432
433	if (!(fattr->valid & NFS_ATTR_FATTR_FILEID) ||
434	    !(fattr->valid & NFS_ATTR_FATTR_TYPE))
435		return NULL;
436
437	hash = nfs_fattr_to_ino_t(fattr);
438	inode = ilookup5(sb, hash, nfs_find_actor, &desc);
439
440	dprintk("%s: returning %p\n", __func__, inode);
441	return inode;
442}
443
444/*
445 * This is our front-end to iget that looks up inodes by file handle
446 * instead of inode number.
447 */
448struct inode *
449nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, struct nfs4_label *label)
450{
451	struct nfs_find_desc desc = {
452		.fh	= fh,
453		.fattr	= fattr
454	};
455	struct inode *inode = ERR_PTR(-ENOENT);
456	unsigned long hash;
457
458	nfs_attr_check_mountpoint(sb, fattr);
459
460	if (nfs_attr_use_mounted_on_fileid(fattr))
461		fattr->fileid = fattr->mounted_on_fileid;
462	else if ((fattr->valid & NFS_ATTR_FATTR_FILEID) == 0)
463		goto out_no_inode;
464	if ((fattr->valid & NFS_ATTR_FATTR_TYPE) == 0)
465		goto out_no_inode;
466
467	hash = nfs_fattr_to_ino_t(fattr);
468
469	inode = iget5_locked(sb, hash, nfs_find_actor, nfs_init_locked, &desc);
470	if (inode == NULL) {
471		inode = ERR_PTR(-ENOMEM);
472		goto out_no_inode;
473	}
474
475	if (inode->i_state & I_NEW) {
476		struct nfs_inode *nfsi = NFS_I(inode);
477		unsigned long now = jiffies;
478
479		/* We set i_ino for the few things that still rely on it,
480		 * such as stat(2) */
481		inode->i_ino = hash;
482
483		/* We can't support update_atime(), since the server will reset it */
484		inode->i_flags |= S_NOATIME|S_NOCMTIME;
485		inode->i_mode = fattr->mode;
486		nfsi->cache_validity = 0;
487		if ((fattr->valid & NFS_ATTR_FATTR_MODE) == 0
488				&& nfs_server_capable(inode, NFS_CAP_MODE))
489			nfs_set_cache_invalid(inode, NFS_INO_INVALID_OTHER);
490		/* Why so? Because we want revalidate for devices/FIFOs, and
491		 * that's precisely what we have in nfs_file_inode_operations.
492		 */
493		inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->file_inode_ops;
494		if (S_ISREG(inode->i_mode)) {
495			inode->i_fop = NFS_SB(sb)->nfs_client->rpc_ops->file_ops;
496			inode->i_data.a_ops = &nfs_file_aops;
497		} else if (S_ISDIR(inode->i_mode)) {
498			inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->dir_inode_ops;
499			inode->i_fop = &nfs_dir_operations;
500			inode->i_data.a_ops = &nfs_dir_aops;
501			/* Deal with crossing mountpoints */
502			if (fattr->valid & NFS_ATTR_FATTR_MOUNTPOINT ||
503					fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) {
504				if (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL)
505					inode->i_op = &nfs_referral_inode_operations;
506				else
507					inode->i_op = &nfs_mountpoint_inode_operations;
508				inode->i_fop = NULL;
509				inode->i_flags |= S_AUTOMOUNT;
510			}
511		} else if (S_ISLNK(inode->i_mode)) {
512			inode->i_op = &nfs_symlink_inode_operations;
513			inode_nohighmem(inode);
514		} else
515			init_special_inode(inode, inode->i_mode, fattr->rdev);
516
517		memset(&inode->i_atime, 0, sizeof(inode->i_atime));
518		memset(&inode->i_mtime, 0, sizeof(inode->i_mtime));
519		memset(&inode->i_ctime, 0, sizeof(inode->i_ctime));
520		inode_set_iversion_raw(inode, 0);
521		inode->i_size = 0;
522		clear_nlink(inode);
523		inode->i_uid = make_kuid(&init_user_ns, -2);
524		inode->i_gid = make_kgid(&init_user_ns, -2);
525		inode->i_blocks = 0;
526		memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf));
527		nfsi->write_io = 0;
528		nfsi->read_io = 0;
529
530		nfsi->read_cache_jiffies = fattr->time_start;
531		nfsi->attr_gencount = fattr->gencount;
532		if (fattr->valid & NFS_ATTR_FATTR_ATIME)
533			inode->i_atime = fattr->atime;
534		else if (nfs_server_capable(inode, NFS_CAP_ATIME))
535			nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATIME);
536		if (fattr->valid & NFS_ATTR_FATTR_MTIME)
537			inode->i_mtime = fattr->mtime;
538		else if (nfs_server_capable(inode, NFS_CAP_MTIME))
539			nfs_set_cache_invalid(inode, NFS_INO_INVALID_MTIME);
540		if (fattr->valid & NFS_ATTR_FATTR_CTIME)
541			inode->i_ctime = fattr->ctime;
542		else if (nfs_server_capable(inode, NFS_CAP_CTIME))
543			nfs_set_cache_invalid(inode, NFS_INO_INVALID_CTIME);
544		if (fattr->valid & NFS_ATTR_FATTR_CHANGE)
545			inode_set_iversion_raw(inode, fattr->change_attr);
546		else
547			nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE);
548		if (fattr->valid & NFS_ATTR_FATTR_SIZE)
549			inode->i_size = nfs_size_to_loff_t(fattr->size);
550		else
551			nfs_set_cache_invalid(inode, NFS_INO_INVALID_SIZE);
552		if (fattr->valid & NFS_ATTR_FATTR_NLINK)
553			set_nlink(inode, fattr->nlink);
554		else if (nfs_server_capable(inode, NFS_CAP_NLINK))
555			nfs_set_cache_invalid(inode, NFS_INO_INVALID_OTHER);
556		if (fattr->valid & NFS_ATTR_FATTR_OWNER)
557			inode->i_uid = fattr->uid;
558		else if (nfs_server_capable(inode, NFS_CAP_OWNER))
559			nfs_set_cache_invalid(inode, NFS_INO_INVALID_OTHER);
560		if (fattr->valid & NFS_ATTR_FATTR_GROUP)
561			inode->i_gid = fattr->gid;
562		else if (nfs_server_capable(inode, NFS_CAP_OWNER_GROUP))
563			nfs_set_cache_invalid(inode, NFS_INO_INVALID_OTHER);
564		if (nfs_server_capable(inode, NFS_CAP_XATTR))
565			nfs_set_cache_invalid(inode, NFS_INO_INVALID_XATTR);
566		if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED)
567			inode->i_blocks = fattr->du.nfs2.blocks;
568		if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) {
569			/*
570			 * report the blocks in 512byte units
571			 */
572			inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used);
573		}
574
575		if (nfsi->cache_validity != 0)
576			nfsi->cache_validity |= NFS_INO_REVAL_FORCED;
577
578		nfs_setsecurity(inode, fattr, label);
579
580		nfsi->attrtimeo = NFS_MINATTRTIMEO(inode);
581		nfsi->attrtimeo_timestamp = now;
582		nfsi->access_cache = RB_ROOT;
583
584		nfs_fscache_init_inode(inode);
585
586		unlock_new_inode(inode);
587	} else {
588		int err = nfs_refresh_inode(inode, fattr);
589		if (err < 0) {
590			iput(inode);
591			inode = ERR_PTR(err);
592			goto out_no_inode;
593		}
594	}
595	dprintk("NFS: nfs_fhget(%s/%Lu fh_crc=0x%08x ct=%d)\n",
596		inode->i_sb->s_id,
597		(unsigned long long)NFS_FILEID(inode),
598		nfs_display_fhandle_hash(fh),
599		atomic_read(&inode->i_count));
600
601out:
602	return inode;
603
604out_no_inode:
605	dprintk("nfs_fhget: iget failed with error %ld\n", PTR_ERR(inode));
606	goto out;
607}
608EXPORT_SYMBOL_GPL(nfs_fhget);
609
610#define NFS_VALID_ATTRS (ATTR_MODE|ATTR_UID|ATTR_GID|ATTR_SIZE|ATTR_ATIME|ATTR_ATIME_SET|ATTR_MTIME|ATTR_MTIME_SET|ATTR_FILE|ATTR_OPEN)
611
612int
613nfs_setattr(struct dentry *dentry, struct iattr *attr)
614{
615	struct inode *inode = d_inode(dentry);
616	struct nfs_fattr *fattr;
617	int error = 0;
618
619	nfs_inc_stats(inode, NFSIOS_VFSSETATTR);
620
621	/* skip mode change if it's just for clearing setuid/setgid */
622	if (attr->ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID))
623		attr->ia_valid &= ~ATTR_MODE;
624
625	if (attr->ia_valid & ATTR_SIZE) {
626		BUG_ON(!S_ISREG(inode->i_mode));
627
628		error = inode_newsize_ok(inode, attr->ia_size);
629		if (error)
630			return error;
631
632		if (attr->ia_size == i_size_read(inode))
633			attr->ia_valid &= ~ATTR_SIZE;
634	}
635
636	/* Optimization: if the end result is no change, don't RPC */
637	attr->ia_valid &= NFS_VALID_ATTRS;
638	if ((attr->ia_valid & ~(ATTR_FILE|ATTR_OPEN)) == 0)
639		return 0;
640
641	trace_nfs_setattr_enter(inode);
642
643	/* Write all dirty data */
644	if (S_ISREG(inode->i_mode))
645		nfs_sync_inode(inode);
646
647	fattr = nfs_alloc_fattr();
648	if (fattr == NULL) {
649		error = -ENOMEM;
650		goto out;
651	}
652
653	error = NFS_PROTO(inode)->setattr(dentry, fattr, attr);
654	if (error == 0)
655		error = nfs_refresh_inode(inode, fattr);
656	nfs_free_fattr(fattr);
657out:
658	trace_nfs_setattr_exit(inode, error);
659	return error;
660}
661EXPORT_SYMBOL_GPL(nfs_setattr);
662
663/**
664 * nfs_vmtruncate - unmap mappings "freed" by truncate() syscall
665 * @inode: inode of the file used
666 * @offset: file offset to start truncating
667 *
668 * This is a copy of the common vmtruncate, but with the locking
669 * corrected to take into account the fact that NFS requires
670 * inode->i_size to be updated under the inode->i_lock.
671 * Note: must be called with inode->i_lock held!
672 */
673static int nfs_vmtruncate(struct inode * inode, loff_t offset)
674{
675	int err;
676
677	err = inode_newsize_ok(inode, offset);
678	if (err)
679		goto out;
680
681	i_size_write(inode, offset);
682	/* Optimisation */
683	if (offset == 0)
684		NFS_I(inode)->cache_validity &= ~(NFS_INO_INVALID_DATA |
685				NFS_INO_DATA_INVAL_DEFER);
686	NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_SIZE;
687
688	spin_unlock(&inode->i_lock);
689	truncate_pagecache(inode, offset);
690	spin_lock(&inode->i_lock);
691out:
692	return err;
693}
694
695/**
696 * nfs_setattr_update_inode - Update inode metadata after a setattr call.
697 * @inode: pointer to struct inode
698 * @attr: pointer to struct iattr
699 * @fattr: pointer to struct nfs_fattr
700 *
701 * Note: we do this in the *proc.c in order to ensure that
702 *       it works for things like exclusive creates too.
703 */
704void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr,
705		struct nfs_fattr *fattr)
706{
707	/* Barrier: bump the attribute generation count. */
708	nfs_fattr_set_barrier(fattr);
709
710	spin_lock(&inode->i_lock);
711	NFS_I(inode)->attr_gencount = fattr->gencount;
712	if ((attr->ia_valid & ATTR_SIZE) != 0) {
713		nfs_set_cache_invalid(inode, NFS_INO_INVALID_MTIME);
714		nfs_inc_stats(inode, NFSIOS_SETATTRTRUNC);
715		nfs_vmtruncate(inode, attr->ia_size);
716	}
717	if ((attr->ia_valid & (ATTR_MODE|ATTR_UID|ATTR_GID)) != 0) {
718		NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_CTIME;
719		if ((attr->ia_valid & ATTR_MODE) != 0) {
720			int mode = attr->ia_mode & S_IALLUGO;
721			mode |= inode->i_mode & ~S_IALLUGO;
722			inode->i_mode = mode;
723		}
724		if ((attr->ia_valid & ATTR_UID) != 0)
725			inode->i_uid = attr->ia_uid;
726		if ((attr->ia_valid & ATTR_GID) != 0)
727			inode->i_gid = attr->ia_gid;
728		if (fattr->valid & NFS_ATTR_FATTR_CTIME)
729			inode->i_ctime = fattr->ctime;
730		else
731			nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE
732					| NFS_INO_INVALID_CTIME);
733		nfs_set_cache_invalid(inode, NFS_INO_INVALID_ACCESS
734				| NFS_INO_INVALID_ACL);
735	}
736	if (attr->ia_valid & (ATTR_ATIME_SET|ATTR_ATIME)) {
737		NFS_I(inode)->cache_validity &= ~(NFS_INO_INVALID_ATIME
738				| NFS_INO_INVALID_CTIME);
739		if (fattr->valid & NFS_ATTR_FATTR_ATIME)
740			inode->i_atime = fattr->atime;
741		else if (attr->ia_valid & ATTR_ATIME_SET)
742			inode->i_atime = attr->ia_atime;
743		else
744			nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATIME);
745
746		if (fattr->valid & NFS_ATTR_FATTR_CTIME)
747			inode->i_ctime = fattr->ctime;
748		else
749			nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE
750					| NFS_INO_INVALID_CTIME);
751	}
752	if (attr->ia_valid & (ATTR_MTIME_SET|ATTR_MTIME)) {
753		NFS_I(inode)->cache_validity &= ~(NFS_INO_INVALID_MTIME
754				| NFS_INO_INVALID_CTIME);
755		if (fattr->valid & NFS_ATTR_FATTR_MTIME)
756			inode->i_mtime = fattr->mtime;
757		else if (attr->ia_valid & ATTR_MTIME_SET)
758			inode->i_mtime = attr->ia_mtime;
759		else
760			nfs_set_cache_invalid(inode, NFS_INO_INVALID_MTIME);
761
762		if (fattr->valid & NFS_ATTR_FATTR_CTIME)
763			inode->i_ctime = fattr->ctime;
764		else
765			nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE
766					| NFS_INO_INVALID_CTIME);
767	}
768	if (fattr->valid)
769		nfs_update_inode(inode, fattr);
770	spin_unlock(&inode->i_lock);
771}
772EXPORT_SYMBOL_GPL(nfs_setattr_update_inode);
773
774static void nfs_readdirplus_parent_cache_miss(struct dentry *dentry)
775{
776	struct dentry *parent;
777
778	if (!nfs_server_capable(d_inode(dentry), NFS_CAP_READDIRPLUS))
779		return;
780	parent = dget_parent(dentry);
781	nfs_force_use_readdirplus(d_inode(parent));
782	dput(parent);
783}
784
785static void nfs_readdirplus_parent_cache_hit(struct dentry *dentry)
786{
787	struct dentry *parent;
788
789	if (!nfs_server_capable(d_inode(dentry), NFS_CAP_READDIRPLUS))
790		return;
791	parent = dget_parent(dentry);
792	nfs_advise_use_readdirplus(d_inode(parent));
793	dput(parent);
794}
795
796static bool nfs_need_revalidate_inode(struct inode *inode)
797{
798	if (NFS_I(inode)->cache_validity &
799			(NFS_INO_INVALID_ATTR|NFS_INO_INVALID_LABEL))
800		return true;
801	if (nfs_attribute_cache_expired(inode))
802		return true;
803	return false;
804}
805
806int nfs_getattr(const struct path *path, struct kstat *stat,
807		u32 request_mask, unsigned int query_flags)
808{
809	struct inode *inode = d_inode(path->dentry);
810	struct nfs_server *server = NFS_SERVER(inode);
811	unsigned long cache_validity;
812	int err = 0;
813	bool force_sync = query_flags & AT_STATX_FORCE_SYNC;
814	bool do_update = false;
815
816	trace_nfs_getattr_enter(inode);
817
818	if ((query_flags & AT_STATX_DONT_SYNC) && !force_sync) {
819		nfs_readdirplus_parent_cache_hit(path->dentry);
820		goto out_no_update;
821	}
822
823	/* Flush out writes to the server in order to update c/mtime.  */
824	if ((request_mask & (STATX_CTIME | STATX_MTIME)) &&
825	    S_ISREG(inode->i_mode))
826		filemap_write_and_wait(inode->i_mapping);
827
828	/*
829	 * We may force a getattr if the user cares about atime.
830	 *
831	 * Note that we only have to check the vfsmount flags here:
832	 *  - NFS always sets S_NOATIME by so checking it would give a
833	 *    bogus result
834	 *  - NFS never sets SB_NOATIME or SB_NODIRATIME so there is
835	 *    no point in checking those.
836	 */
837	if ((path->mnt->mnt_flags & MNT_NOATIME) ||
838	    ((path->mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode)))
839		request_mask &= ~STATX_ATIME;
840
841	/* Is the user requesting attributes that might need revalidation? */
842	if (!(request_mask & (STATX_MODE|STATX_NLINK|STATX_ATIME|STATX_CTIME|
843					STATX_MTIME|STATX_UID|STATX_GID|
844					STATX_SIZE|STATX_BLOCKS)))
845		goto out_no_revalidate;
846
847	/* Check whether the cached attributes are stale */
848	do_update |= force_sync || nfs_attribute_cache_expired(inode);
849	cache_validity = READ_ONCE(NFS_I(inode)->cache_validity);
850	do_update |= cache_validity &
851		(NFS_INO_INVALID_ATTR|NFS_INO_INVALID_LABEL);
852	if (request_mask & STATX_ATIME)
853		do_update |= cache_validity & NFS_INO_INVALID_ATIME;
854	if (request_mask & (STATX_CTIME|STATX_MTIME))
855		do_update |= cache_validity & NFS_INO_REVAL_PAGECACHE;
856	if (request_mask & STATX_BLOCKS)
857		do_update |= cache_validity & NFS_INO_INVALID_BLOCKS;
858	if (do_update) {
859		/* Update the attribute cache */
860		if (!(server->flags & NFS_MOUNT_NOAC))
861			nfs_readdirplus_parent_cache_miss(path->dentry);
862		else
863			nfs_readdirplus_parent_cache_hit(path->dentry);
864		err = __nfs_revalidate_inode(server, inode);
865		if (err)
866			goto out;
867	} else
868		nfs_readdirplus_parent_cache_hit(path->dentry);
869out_no_revalidate:
870	/* Only return attributes that were revalidated. */
871	stat->result_mask &= request_mask;
872out_no_update:
873	generic_fillattr(inode, stat);
874	stat->ino = nfs_compat_user_ino64(NFS_FILEID(inode));
875	if (S_ISDIR(inode->i_mode))
876		stat->blksize = NFS_SERVER(inode)->dtsize;
877out:
878	trace_nfs_getattr_exit(inode, err);
879	return err;
880}
881EXPORT_SYMBOL_GPL(nfs_getattr);
882
883static void nfs_init_lock_context(struct nfs_lock_context *l_ctx)
884{
885	refcount_set(&l_ctx->count, 1);
886	l_ctx->lockowner = current->files;
887	INIT_LIST_HEAD(&l_ctx->list);
888	atomic_set(&l_ctx->io_count, 0);
889}
890
891static struct nfs_lock_context *__nfs_find_lock_context(struct nfs_open_context *ctx)
892{
893	struct nfs_lock_context *pos;
894
895	list_for_each_entry_rcu(pos, &ctx->lock_context.list, list) {
896		if (pos->lockowner != current->files)
897			continue;
898		if (refcount_inc_not_zero(&pos->count))
899			return pos;
900	}
901	return NULL;
902}
903
904struct nfs_lock_context *nfs_get_lock_context(struct nfs_open_context *ctx)
905{
906	struct nfs_lock_context *res, *new = NULL;
907	struct inode *inode = d_inode(ctx->dentry);
908
909	rcu_read_lock();
910	res = __nfs_find_lock_context(ctx);
911	rcu_read_unlock();
912	if (res == NULL) {
913		new = kmalloc(sizeof(*new), GFP_KERNEL);
914		if (new == NULL)
915			return ERR_PTR(-ENOMEM);
916		nfs_init_lock_context(new);
917		spin_lock(&inode->i_lock);
918		res = __nfs_find_lock_context(ctx);
919		if (res == NULL) {
920			new->open_context = get_nfs_open_context(ctx);
921			if (new->open_context) {
922				list_add_tail_rcu(&new->list,
923						&ctx->lock_context.list);
924				res = new;
925				new = NULL;
926			} else
927				res = ERR_PTR(-EBADF);
928		}
929		spin_unlock(&inode->i_lock);
930		kfree(new);
931	}
932	return res;
933}
934EXPORT_SYMBOL_GPL(nfs_get_lock_context);
935
936void nfs_put_lock_context(struct nfs_lock_context *l_ctx)
937{
938	struct nfs_open_context *ctx = l_ctx->open_context;
939	struct inode *inode = d_inode(ctx->dentry);
940
941	if (!refcount_dec_and_lock(&l_ctx->count, &inode->i_lock))
942		return;
943	list_del_rcu(&l_ctx->list);
944	spin_unlock(&inode->i_lock);
945	put_nfs_open_context(ctx);
946	kfree_rcu(l_ctx, rcu_head);
947}
948EXPORT_SYMBOL_GPL(nfs_put_lock_context);
949
950/**
951 * nfs_close_context - Common close_context() routine NFSv2/v3
952 * @ctx: pointer to context
953 * @is_sync: is this a synchronous close
954 *
955 * Ensure that the attributes are up to date if we're mounted
956 * with close-to-open semantics and we have cached data that will
957 * need to be revalidated on open.
958 */
959void nfs_close_context(struct nfs_open_context *ctx, int is_sync)
960{
961	struct nfs_inode *nfsi;
962	struct inode *inode;
963	struct nfs_server *server;
964
965	if (!(ctx->mode & FMODE_WRITE))
966		return;
967	if (!is_sync)
968		return;
969	inode = d_inode(ctx->dentry);
970	if (NFS_PROTO(inode)->have_delegation(inode, FMODE_READ))
971		return;
972	nfsi = NFS_I(inode);
973	if (inode->i_mapping->nrpages == 0)
974		return;
975	if (nfsi->cache_validity & NFS_INO_INVALID_DATA)
976		return;
977	if (!list_empty(&nfsi->open_files))
978		return;
979	server = NFS_SERVER(inode);
980	if (server->flags & NFS_MOUNT_NOCTO)
981		return;
982	nfs_revalidate_inode(server, inode);
983}
984EXPORT_SYMBOL_GPL(nfs_close_context);
985
986struct nfs_open_context *alloc_nfs_open_context(struct dentry *dentry,
987						fmode_t f_mode,
988						struct file *filp)
989{
990	struct nfs_open_context *ctx;
991
992	ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
993	if (!ctx)
994		return ERR_PTR(-ENOMEM);
995	nfs_sb_active(dentry->d_sb);
996	ctx->dentry = dget(dentry);
997	if (filp)
998		ctx->cred = get_cred(filp->f_cred);
999	else
1000		ctx->cred = get_current_cred();
1001	ctx->ll_cred = NULL;
1002	ctx->state = NULL;
1003	ctx->mode = f_mode;
1004	ctx->flags = 0;
1005	ctx->error = 0;
1006	ctx->flock_owner = (fl_owner_t)filp;
1007	nfs_init_lock_context(&ctx->lock_context);
1008	ctx->lock_context.open_context = ctx;
1009	INIT_LIST_HEAD(&ctx->list);
1010	ctx->mdsthreshold = NULL;
1011	return ctx;
1012}
1013EXPORT_SYMBOL_GPL(alloc_nfs_open_context);
1014
1015struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx)
1016{
1017	if (ctx != NULL && refcount_inc_not_zero(&ctx->lock_context.count))
1018		return ctx;
1019	return NULL;
1020}
1021EXPORT_SYMBOL_GPL(get_nfs_open_context);
1022
1023static void __put_nfs_open_context(struct nfs_open_context *ctx, int is_sync)
1024{
1025	struct inode *inode = d_inode(ctx->dentry);
1026	struct super_block *sb = ctx->dentry->d_sb;
1027
1028	if (!refcount_dec_and_test(&ctx->lock_context.count))
1029		return;
1030	if (!list_empty(&ctx->list)) {
1031		spin_lock(&inode->i_lock);
1032		list_del_rcu(&ctx->list);
1033		spin_unlock(&inode->i_lock);
1034	}
1035	if (inode != NULL)
1036		NFS_PROTO(inode)->close_context(ctx, is_sync);
1037	put_cred(ctx->cred);
1038	dput(ctx->dentry);
1039	nfs_sb_deactive(sb);
1040	put_rpccred(ctx->ll_cred);
1041	kfree(ctx->mdsthreshold);
1042	kfree_rcu(ctx, rcu_head);
1043}
1044
1045void put_nfs_open_context(struct nfs_open_context *ctx)
1046{
1047	__put_nfs_open_context(ctx, 0);
1048}
1049EXPORT_SYMBOL_GPL(put_nfs_open_context);
1050
1051static void put_nfs_open_context_sync(struct nfs_open_context *ctx)
1052{
1053	__put_nfs_open_context(ctx, 1);
1054}
1055
1056/*
1057 * Ensure that mmap has a recent RPC credential for use when writing out
1058 * shared pages
1059 */
1060void nfs_inode_attach_open_context(struct nfs_open_context *ctx)
1061{
1062	struct inode *inode = d_inode(ctx->dentry);
1063	struct nfs_inode *nfsi = NFS_I(inode);
1064
1065	spin_lock(&inode->i_lock);
1066	if (list_empty(&nfsi->open_files) &&
1067	    (nfsi->cache_validity & NFS_INO_DATA_INVAL_DEFER))
1068		nfsi->cache_validity |= NFS_INO_INVALID_DATA |
1069			NFS_INO_REVAL_FORCED;
1070	list_add_tail_rcu(&ctx->list, &nfsi->open_files);
1071	spin_unlock(&inode->i_lock);
1072}
1073EXPORT_SYMBOL_GPL(nfs_inode_attach_open_context);
1074
1075void nfs_file_set_open_context(struct file *filp, struct nfs_open_context *ctx)
1076{
1077	filp->private_data = get_nfs_open_context(ctx);
1078	set_bit(NFS_CONTEXT_FILE_OPEN, &ctx->flags);
1079	if (list_empty(&ctx->list))
1080		nfs_inode_attach_open_context(ctx);
1081}
1082EXPORT_SYMBOL_GPL(nfs_file_set_open_context);
1083
1084/*
1085 * Given an inode, search for an open context with the desired characteristics
1086 */
1087struct nfs_open_context *nfs_find_open_context(struct inode *inode, const struct cred *cred, fmode_t mode)
1088{
1089	struct nfs_inode *nfsi = NFS_I(inode);
1090	struct nfs_open_context *pos, *ctx = NULL;
1091
1092	rcu_read_lock();
1093	list_for_each_entry_rcu(pos, &nfsi->open_files, list) {
1094		if (cred != NULL && cred_fscmp(pos->cred, cred) != 0)
1095			continue;
1096		if ((pos->mode & (FMODE_READ|FMODE_WRITE)) != mode)
1097			continue;
1098		if (!test_bit(NFS_CONTEXT_FILE_OPEN, &pos->flags))
1099			continue;
1100		ctx = get_nfs_open_context(pos);
1101		if (ctx)
1102			break;
1103	}
1104	rcu_read_unlock();
1105	return ctx;
1106}
1107
1108void nfs_file_clear_open_context(struct file *filp)
1109{
1110	struct nfs_open_context *ctx = nfs_file_open_context(filp);
1111
1112	if (ctx) {
1113		struct inode *inode = d_inode(ctx->dentry);
1114
1115		clear_bit(NFS_CONTEXT_FILE_OPEN, &ctx->flags);
1116		/*
1117		 * We fatal error on write before. Try to writeback
1118		 * every page again.
1119		 */
1120		if (ctx->error < 0)
1121			invalidate_inode_pages2(inode->i_mapping);
1122		filp->private_data = NULL;
1123		put_nfs_open_context_sync(ctx);
1124	}
1125}
1126
1127/*
1128 * These allocate and release file read/write context information.
1129 */
1130int nfs_open(struct inode *inode, struct file *filp)
1131{
1132	struct nfs_open_context *ctx;
1133
1134	ctx = alloc_nfs_open_context(file_dentry(filp), filp->f_mode, filp);
1135	if (IS_ERR(ctx))
1136		return PTR_ERR(ctx);
1137	nfs_file_set_open_context(filp, ctx);
1138	put_nfs_open_context(ctx);
1139	nfs_fscache_open_file(inode, filp);
1140	return 0;
1141}
1142
1143/*
1144 * This function is called whenever some part of NFS notices that
1145 * the cached attributes have to be refreshed.
1146 */
1147int
1148__nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
1149{
1150	int		 status = -ESTALE;
1151	struct nfs4_label *label = NULL;
1152	struct nfs_fattr *fattr = NULL;
1153	struct nfs_inode *nfsi = NFS_I(inode);
1154
1155	dfprintk(PAGECACHE, "NFS: revalidating (%s/%Lu)\n",
1156		inode->i_sb->s_id, (unsigned long long)NFS_FILEID(inode));
1157
1158	trace_nfs_revalidate_inode_enter(inode);
1159
1160	if (is_bad_inode(inode))
1161		goto out;
1162	if (NFS_STALE(inode))
1163		goto out;
1164
1165	/* pNFS: Attributes aren't updated until we layoutcommit */
1166	if (S_ISREG(inode->i_mode)) {
1167		status = pnfs_sync_inode(inode, false);
1168		if (status)
1169			goto out;
1170	}
1171
1172	status = -ENOMEM;
1173	fattr = nfs_alloc_fattr();
1174	if (fattr == NULL)
1175		goto out;
1176
1177	nfs_inc_stats(inode, NFSIOS_INODEREVALIDATE);
1178
1179	label = nfs4_label_alloc(NFS_SERVER(inode), GFP_KERNEL);
1180	if (IS_ERR(label)) {
1181		status = PTR_ERR(label);
1182		goto out;
1183	}
1184
1185	status = NFS_PROTO(inode)->getattr(server, NFS_FH(inode), fattr,
1186			label, inode);
1187	if (status != 0) {
1188		dfprintk(PAGECACHE, "nfs_revalidate_inode: (%s/%Lu) getattr failed, error=%d\n",
1189			 inode->i_sb->s_id,
1190			 (unsigned long long)NFS_FILEID(inode), status);
1191		switch (status) {
1192		case -ETIMEDOUT:
1193			/* A soft timeout occurred. Use cached information? */
1194			if (server->flags & NFS_MOUNT_SOFTREVAL)
1195				status = 0;
1196			break;
1197		case -ESTALE:
1198			if (!S_ISDIR(inode->i_mode))
1199				nfs_set_inode_stale(inode);
1200			else
1201				nfs_zap_caches(inode);
1202		}
1203		goto err_out;
1204	}
1205
1206	status = nfs_refresh_inode(inode, fattr);
1207	if (status) {
1208		dfprintk(PAGECACHE, "nfs_revalidate_inode: (%s/%Lu) refresh failed, error=%d\n",
1209			 inode->i_sb->s_id,
1210			 (unsigned long long)NFS_FILEID(inode), status);
1211		goto err_out;
1212	}
1213
1214	if (nfsi->cache_validity & NFS_INO_INVALID_ACL)
1215		nfs_zap_acl_cache(inode);
1216
1217	nfs_setsecurity(inode, fattr, label);
1218
1219	dfprintk(PAGECACHE, "NFS: (%s/%Lu) revalidation complete\n",
1220		inode->i_sb->s_id,
1221		(unsigned long long)NFS_FILEID(inode));
1222
1223err_out:
1224	nfs4_label_free(label);
1225out:
1226	nfs_free_fattr(fattr);
1227	trace_nfs_revalidate_inode_exit(inode, status);
1228	return status;
1229}
1230
1231int nfs_attribute_cache_expired(struct inode *inode)
1232{
1233	if (nfs_have_delegated_attributes(inode))
1234		return 0;
1235	return nfs_attribute_timeout(inode);
1236}
1237
1238/**
1239 * nfs_revalidate_inode - Revalidate the inode attributes
1240 * @server: pointer to nfs_server struct
1241 * @inode: pointer to inode struct
1242 *
1243 * Updates inode attribute information by retrieving the data from the server.
1244 */
1245int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
1246{
1247	if (!nfs_need_revalidate_inode(inode))
1248		return NFS_STALE(inode) ? -ESTALE : 0;
1249	return __nfs_revalidate_inode(server, inode);
1250}
1251EXPORT_SYMBOL_GPL(nfs_revalidate_inode);
1252
1253static int nfs_invalidate_mapping(struct inode *inode, struct address_space *mapping)
1254{
1255	struct nfs_inode *nfsi = NFS_I(inode);
1256	int ret;
1257
1258	if (mapping->nrpages != 0) {
1259		if (S_ISREG(inode->i_mode)) {
1260			ret = nfs_sync_mapping(mapping);
1261			if (ret < 0)
1262				return ret;
1263		}
1264		ret = invalidate_inode_pages2(mapping);
1265		if (ret < 0)
1266			return ret;
1267	}
1268	if (S_ISDIR(inode->i_mode)) {
1269		spin_lock(&inode->i_lock);
1270		memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf));
1271		spin_unlock(&inode->i_lock);
1272	}
1273	nfs_inc_stats(inode, NFSIOS_DATAINVALIDATE);
1274	nfs_fscache_wait_on_invalidate(inode);
1275
1276	dfprintk(PAGECACHE, "NFS: (%s/%Lu) data cache invalidated\n",
1277			inode->i_sb->s_id,
1278			(unsigned long long)NFS_FILEID(inode));
1279	return 0;
1280}
1281
1282bool nfs_mapping_need_revalidate_inode(struct inode *inode)
1283{
1284	return nfs_check_cache_invalid(inode, NFS_INO_REVAL_PAGECACHE) ||
1285		NFS_STALE(inode);
1286}
1287
1288int nfs_revalidate_mapping_rcu(struct inode *inode)
1289{
1290	struct nfs_inode *nfsi = NFS_I(inode);
1291	unsigned long *bitlock = &nfsi->flags;
1292	int ret = 0;
1293
1294	if (IS_SWAPFILE(inode))
1295		goto out;
1296	if (nfs_mapping_need_revalidate_inode(inode)) {
1297		ret = -ECHILD;
1298		goto out;
1299	}
1300	spin_lock(&inode->i_lock);
1301	if (test_bit(NFS_INO_INVALIDATING, bitlock) ||
1302	    (nfsi->cache_validity & NFS_INO_INVALID_DATA))
1303		ret = -ECHILD;
1304	spin_unlock(&inode->i_lock);
1305out:
1306	return ret;
1307}
1308
1309/**
1310 * nfs_revalidate_mapping - Revalidate the pagecache
1311 * @inode: pointer to host inode
1312 * @mapping: pointer to mapping
1313 */
1314int nfs_revalidate_mapping(struct inode *inode,
1315		struct address_space *mapping)
1316{
1317	struct nfs_inode *nfsi = NFS_I(inode);
1318	unsigned long *bitlock = &nfsi->flags;
1319	int ret = 0;
1320
1321	/* swapfiles are not supposed to be shared. */
1322	if (IS_SWAPFILE(inode))
1323		goto out;
1324
1325	if (nfs_mapping_need_revalidate_inode(inode)) {
1326		ret = __nfs_revalidate_inode(NFS_SERVER(inode), inode);
1327		if (ret < 0)
1328			goto out;
1329	}
1330
1331	/*
1332	 * We must clear NFS_INO_INVALID_DATA first to ensure that
1333	 * invalidations that come in while we're shooting down the mappings
1334	 * are respected. But, that leaves a race window where one revalidator
1335	 * can clear the flag, and then another checks it before the mapping
1336	 * gets invalidated. Fix that by serializing access to this part of
1337	 * the function.
1338	 *
1339	 * At the same time, we need to allow other tasks to see whether we
1340	 * might be in the middle of invalidating the pages, so we only set
1341	 * the bit lock here if it looks like we're going to be doing that.
1342	 */
1343	for (;;) {
1344		ret = wait_on_bit_action(bitlock, NFS_INO_INVALIDATING,
1345					 nfs_wait_bit_killable, TASK_KILLABLE);
1346		if (ret)
1347			goto out;
1348		spin_lock(&inode->i_lock);
1349		if (test_bit(NFS_INO_INVALIDATING, bitlock)) {
1350			spin_unlock(&inode->i_lock);
1351			continue;
1352		}
1353		if (nfsi->cache_validity & NFS_INO_INVALID_DATA)
1354			break;
1355		spin_unlock(&inode->i_lock);
1356		goto out;
1357	}
1358
1359	set_bit(NFS_INO_INVALIDATING, bitlock);
1360	smp_wmb();
1361	nfsi->cache_validity &= ~(NFS_INO_INVALID_DATA|
1362			NFS_INO_DATA_INVAL_DEFER);
1363	spin_unlock(&inode->i_lock);
1364	trace_nfs_invalidate_mapping_enter(inode);
1365	ret = nfs_invalidate_mapping(inode, mapping);
1366	trace_nfs_invalidate_mapping_exit(inode, ret);
1367
1368	clear_bit_unlock(NFS_INO_INVALIDATING, bitlock);
1369	smp_mb__after_atomic();
1370	wake_up_bit(bitlock, NFS_INO_INVALIDATING);
1371out:
1372	return ret;
1373}
1374
1375static bool nfs_file_has_writers(struct nfs_inode *nfsi)
1376{
1377	struct inode *inode = &nfsi->vfs_inode;
1378
1379	if (!S_ISREG(inode->i_mode))
1380		return false;
1381	if (list_empty(&nfsi->open_files))
1382		return false;
1383	return inode_is_open_for_write(inode);
1384}
1385
1386static bool nfs_file_has_buffered_writers(struct nfs_inode *nfsi)
1387{
1388	return nfs_file_has_writers(nfsi) && nfs_file_io_is_buffered(nfsi);
1389}
1390
1391static void nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr)
1392{
1393	struct timespec64 ts;
1394
1395	if ((fattr->valid & NFS_ATTR_FATTR_PRECHANGE)
1396			&& (fattr->valid & NFS_ATTR_FATTR_CHANGE)
1397			&& inode_eq_iversion_raw(inode, fattr->pre_change_attr)) {
1398		inode_set_iversion_raw(inode, fattr->change_attr);
1399		if (S_ISDIR(inode->i_mode))
1400			nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA);
1401		else if (nfs_server_capable(inode, NFS_CAP_XATTR))
1402			nfs_set_cache_invalid(inode, NFS_INO_INVALID_XATTR);
1403	}
1404	/* If we have atomic WCC data, we may update some attributes */
1405	ts = inode->i_ctime;
1406	if ((fattr->valid & NFS_ATTR_FATTR_PRECTIME)
1407			&& (fattr->valid & NFS_ATTR_FATTR_CTIME)
1408			&& timespec64_equal(&ts, &fattr->pre_ctime)) {
1409		inode->i_ctime = fattr->ctime;
1410	}
1411
1412	ts = inode->i_mtime;
1413	if ((fattr->valid & NFS_ATTR_FATTR_PREMTIME)
1414			&& (fattr->valid & NFS_ATTR_FATTR_MTIME)
1415			&& timespec64_equal(&ts, &fattr->pre_mtime)) {
1416		inode->i_mtime = fattr->mtime;
1417		if (S_ISDIR(inode->i_mode))
1418			nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA);
1419	}
1420	if ((fattr->valid & NFS_ATTR_FATTR_PRESIZE)
1421			&& (fattr->valid & NFS_ATTR_FATTR_SIZE)
1422			&& i_size_read(inode) == nfs_size_to_loff_t(fattr->pre_size)
1423			&& !nfs_have_writebacks(inode)) {
1424		i_size_write(inode, nfs_size_to_loff_t(fattr->size));
1425	}
1426}
1427
1428/**
1429 * nfs_check_inode_attributes - verify consistency of the inode attribute cache
1430 * @inode: pointer to inode
1431 * @fattr: updated attributes
1432 *
1433 * Verifies the attribute cache. If we have just changed the attributes,
1434 * so that fattr carries weak cache consistency data, then it may
1435 * also update the ctime/mtime/change_attribute.
1436 */
1437static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fattr)
1438{
1439	struct nfs_inode *nfsi = NFS_I(inode);
1440	loff_t cur_size, new_isize;
1441	unsigned long invalid = 0;
1442	struct timespec64 ts;
1443
1444	if (NFS_PROTO(inode)->have_delegation(inode, FMODE_READ))
1445		return 0;
1446
1447	if (!(fattr->valid & NFS_ATTR_FATTR_FILEID)) {
1448		/* Only a mounted-on-fileid? Just exit */
1449		if (fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID)
1450			return 0;
1451	/* Has the inode gone and changed behind our back? */
1452	} else if (nfsi->fileid != fattr->fileid) {
1453		/* Is this perhaps the mounted-on fileid? */
1454		if ((fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) &&
1455		    nfsi->fileid == fattr->mounted_on_fileid)
1456			return 0;
1457		return -ESTALE;
1458	}
1459	if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && inode_wrong_type(inode, fattr->mode))
1460		return -ESTALE;
1461
1462
1463	if (!nfs_file_has_buffered_writers(nfsi)) {
1464		/* Verify a few of the more important attributes */
1465		if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 && !inode_eq_iversion_raw(inode, fattr->change_attr))
1466			invalid |= NFS_INO_INVALID_CHANGE
1467				| NFS_INO_REVAL_PAGECACHE;
1468
1469		ts = inode->i_mtime;
1470		if ((fattr->valid & NFS_ATTR_FATTR_MTIME) && !timespec64_equal(&ts, &fattr->mtime))
1471			invalid |= NFS_INO_INVALID_MTIME;
1472
1473		ts = inode->i_ctime;
1474		if ((fattr->valid & NFS_ATTR_FATTR_CTIME) && !timespec64_equal(&ts, &fattr->ctime))
1475			invalid |= NFS_INO_INVALID_CTIME;
1476
1477		if (fattr->valid & NFS_ATTR_FATTR_SIZE) {
1478			cur_size = i_size_read(inode);
1479			new_isize = nfs_size_to_loff_t(fattr->size);
1480			if (cur_size != new_isize)
1481				invalid |= NFS_INO_INVALID_SIZE
1482					| NFS_INO_REVAL_PAGECACHE;
1483		}
1484	}
1485
1486	/* Have any file permissions changed? */
1487	if ((fattr->valid & NFS_ATTR_FATTR_MODE) && (inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO))
1488		invalid |= NFS_INO_INVALID_ACCESS
1489			| NFS_INO_INVALID_ACL
1490			| NFS_INO_INVALID_OTHER;
1491	if ((fattr->valid & NFS_ATTR_FATTR_OWNER) && !uid_eq(inode->i_uid, fattr->uid))
1492		invalid |= NFS_INO_INVALID_ACCESS
1493			| NFS_INO_INVALID_ACL
1494			| NFS_INO_INVALID_OTHER;
1495	if ((fattr->valid & NFS_ATTR_FATTR_GROUP) && !gid_eq(inode->i_gid, fattr->gid))
1496		invalid |= NFS_INO_INVALID_ACCESS
1497			| NFS_INO_INVALID_ACL
1498			| NFS_INO_INVALID_OTHER;
1499
1500	/* Has the link count changed? */
1501	if ((fattr->valid & NFS_ATTR_FATTR_NLINK) && inode->i_nlink != fattr->nlink)
1502		invalid |= NFS_INO_INVALID_OTHER;
1503
1504	ts = inode->i_atime;
1505	if ((fattr->valid & NFS_ATTR_FATTR_ATIME) && !timespec64_equal(&ts, &fattr->atime))
1506		invalid |= NFS_INO_INVALID_ATIME;
1507
1508	if (invalid != 0)
1509		nfs_set_cache_invalid(inode, invalid);
1510
1511	nfsi->read_cache_jiffies = fattr->time_start;
1512	return 0;
1513}
1514
1515static atomic_long_t nfs_attr_generation_counter;
1516
1517static unsigned long nfs_read_attr_generation_counter(void)
1518{
1519	return atomic_long_read(&nfs_attr_generation_counter);
1520}
1521
1522unsigned long nfs_inc_attr_generation_counter(void)
1523{
1524	return atomic_long_inc_return(&nfs_attr_generation_counter);
1525}
1526EXPORT_SYMBOL_GPL(nfs_inc_attr_generation_counter);
1527
1528void nfs_fattr_init(struct nfs_fattr *fattr)
1529{
1530	fattr->valid = 0;
1531	fattr->time_start = jiffies;
1532	fattr->gencount = nfs_inc_attr_generation_counter();
1533	fattr->owner_name = NULL;
1534	fattr->group_name = NULL;
1535}
1536EXPORT_SYMBOL_GPL(nfs_fattr_init);
1537
1538/**
1539 * nfs_fattr_set_barrier
1540 * @fattr: attributes
1541 *
1542 * Used to set a barrier after an attribute was updated. This
1543 * barrier ensures that older attributes from RPC calls that may
1544 * have raced with our update cannot clobber these new values.
1545 * Note that you are still responsible for ensuring that other
1546 * operations which change the attribute on the server do not
1547 * collide.
1548 */
1549void nfs_fattr_set_barrier(struct nfs_fattr *fattr)
1550{
1551	fattr->gencount = nfs_inc_attr_generation_counter();
1552}
1553
1554struct nfs_fattr *nfs_alloc_fattr(void)
1555{
1556	struct nfs_fattr *fattr;
1557
1558	fattr = kmalloc(sizeof(*fattr), GFP_NOFS);
1559	if (fattr != NULL)
1560		nfs_fattr_init(fattr);
1561	return fattr;
1562}
1563EXPORT_SYMBOL_GPL(nfs_alloc_fattr);
1564
1565struct nfs_fh *nfs_alloc_fhandle(void)
1566{
1567	struct nfs_fh *fh;
1568
1569	fh = kmalloc(sizeof(struct nfs_fh), GFP_NOFS);
1570	if (fh != NULL)
1571		fh->size = 0;
1572	return fh;
1573}
1574EXPORT_SYMBOL_GPL(nfs_alloc_fhandle);
1575
1576#ifdef NFS_DEBUG
1577/*
1578 * _nfs_display_fhandle_hash - calculate the crc32 hash for the filehandle
1579 *                             in the same way that wireshark does
1580 *
1581 * @fh: file handle
1582 *
1583 * For debugging only.
1584 */
1585u32 _nfs_display_fhandle_hash(const struct nfs_fh *fh)
1586{
1587	/* wireshark uses 32-bit AUTODIN crc and does a bitwise
1588	 * not on the result */
1589	return nfs_fhandle_hash(fh);
1590}
1591EXPORT_SYMBOL_GPL(_nfs_display_fhandle_hash);
1592
1593/*
1594 * _nfs_display_fhandle - display an NFS file handle on the console
1595 *
1596 * @fh: file handle to display
1597 * @caption: display caption
1598 *
1599 * For debugging only.
1600 */
1601void _nfs_display_fhandle(const struct nfs_fh *fh, const char *caption)
1602{
1603	unsigned short i;
1604
1605	if (fh == NULL || fh->size == 0) {
1606		printk(KERN_DEFAULT "%s at %p is empty\n", caption, fh);
1607		return;
1608	}
1609
1610	printk(KERN_DEFAULT "%s at %p is %u bytes, crc: 0x%08x:\n",
1611	       caption, fh, fh->size, _nfs_display_fhandle_hash(fh));
1612	for (i = 0; i < fh->size; i += 16) {
1613		__be32 *pos = (__be32 *)&fh->data[i];
1614
1615		switch ((fh->size - i - 1) >> 2) {
1616		case 0:
1617			printk(KERN_DEFAULT " %08x\n",
1618				be32_to_cpup(pos));
1619			break;
1620		case 1:
1621			printk(KERN_DEFAULT " %08x %08x\n",
1622				be32_to_cpup(pos), be32_to_cpup(pos + 1));
1623			break;
1624		case 2:
1625			printk(KERN_DEFAULT " %08x %08x %08x\n",
1626				be32_to_cpup(pos), be32_to_cpup(pos + 1),
1627				be32_to_cpup(pos + 2));
1628			break;
1629		default:
1630			printk(KERN_DEFAULT " %08x %08x %08x %08x\n",
1631				be32_to_cpup(pos), be32_to_cpup(pos + 1),
1632				be32_to_cpup(pos + 2), be32_to_cpup(pos + 3));
1633		}
1634	}
1635}
1636EXPORT_SYMBOL_GPL(_nfs_display_fhandle);
1637#endif
1638
1639/**
1640 * nfs_inode_attrs_need_update - check if the inode attributes need updating
1641 * @inode: pointer to inode
1642 * @fattr: attributes
1643 *
1644 * Attempt to divine whether or not an RPC call reply carrying stale
1645 * attributes got scheduled after another call carrying updated ones.
1646 *
1647 * To do so, the function first assumes that a more recent ctime means
1648 * that the attributes in fattr are newer, however it also attempt to
1649 * catch the case where ctime either didn't change, or went backwards
1650 * (if someone reset the clock on the server) by looking at whether
1651 * or not this RPC call was started after the inode was last updated.
1652 * Note also the check for wraparound of 'attr_gencount'
1653 *
1654 * The function returns 'true' if it thinks the attributes in 'fattr' are
1655 * more recent than the ones cached in the inode.
1656 *
1657 */
1658static int nfs_inode_attrs_need_update(const struct inode *inode, const struct nfs_fattr *fattr)
1659{
1660	unsigned long attr_gencount = NFS_I(inode)->attr_gencount;
1661
1662	return (long)(fattr->gencount - attr_gencount) > 0 ||
1663	       (long)(attr_gencount - nfs_read_attr_generation_counter()) > 0;
1664}
1665
1666static int nfs_refresh_inode_locked(struct inode *inode, struct nfs_fattr *fattr)
1667{
1668	int ret;
1669
1670	trace_nfs_refresh_inode_enter(inode);
1671
1672	if (nfs_inode_attrs_need_update(inode, fattr))
1673		ret = nfs_update_inode(inode, fattr);
1674	else
1675		ret = nfs_check_inode_attributes(inode, fattr);
1676
1677	trace_nfs_refresh_inode_exit(inode, ret);
1678	return ret;
1679}
1680
1681/**
1682 * nfs_refresh_inode - try to update the inode attribute cache
1683 * @inode: pointer to inode
1684 * @fattr: updated attributes
1685 *
1686 * Check that an RPC call that returned attributes has not overlapped with
1687 * other recent updates of the inode metadata, then decide whether it is
1688 * safe to do a full update of the inode attributes, or whether just to
1689 * call nfs_check_inode_attributes.
1690 */
1691int nfs_refresh_inode(struct inode *inode, struct nfs_fattr *fattr)
1692{
1693	int status;
1694
1695	if ((fattr->valid & NFS_ATTR_FATTR) == 0)
1696		return 0;
1697	spin_lock(&inode->i_lock);
1698	status = nfs_refresh_inode_locked(inode, fattr);
1699	spin_unlock(&inode->i_lock);
1700
1701	return status;
1702}
1703EXPORT_SYMBOL_GPL(nfs_refresh_inode);
1704
1705static int nfs_post_op_update_inode_locked(struct inode *inode,
1706		struct nfs_fattr *fattr, unsigned int invalid)
1707{
1708	if (S_ISDIR(inode->i_mode))
1709		invalid |= NFS_INO_INVALID_DATA;
1710	nfs_set_cache_invalid(inode, invalid);
1711	if ((fattr->valid & NFS_ATTR_FATTR) == 0)
1712		return 0;
1713	return nfs_refresh_inode_locked(inode, fattr);
1714}
1715
1716/**
1717 * nfs_post_op_update_inode - try to update the inode attribute cache
1718 * @inode: pointer to inode
1719 * @fattr: updated attributes
1720 *
1721 * After an operation that has changed the inode metadata, mark the
1722 * attribute cache as being invalid, then try to update it.
1723 *
1724 * NB: if the server didn't return any post op attributes, this
1725 * function will force the retrieval of attributes before the next
1726 * NFS request.  Thus it should be used only for operations that
1727 * are expected to change one or more attributes, to avoid
1728 * unnecessary NFS requests and trips through nfs_update_inode().
1729 */
1730int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr)
1731{
1732	int status;
1733
1734	spin_lock(&inode->i_lock);
1735	nfs_fattr_set_barrier(fattr);
1736	status = nfs_post_op_update_inode_locked(inode, fattr,
1737			NFS_INO_INVALID_CHANGE
1738			| NFS_INO_INVALID_CTIME
1739			| NFS_INO_REVAL_FORCED);
1740	spin_unlock(&inode->i_lock);
1741
1742	return status;
1743}
1744EXPORT_SYMBOL_GPL(nfs_post_op_update_inode);
1745
1746/**
1747 * nfs_post_op_update_inode_force_wcc_locked - update the inode attribute cache
1748 * @inode: pointer to inode
1749 * @fattr: updated attributes
1750 *
1751 * After an operation that has changed the inode metadata, mark the
1752 * attribute cache as being invalid, then try to update it. Fake up
1753 * weak cache consistency data, if none exist.
1754 *
1755 * This function is mainly designed to be used by the ->write_done() functions.
1756 */
1757int nfs_post_op_update_inode_force_wcc_locked(struct inode *inode, struct nfs_fattr *fattr)
1758{
1759	int status;
1760
1761	/* Don't do a WCC update if these attributes are already stale */
1762	if ((fattr->valid & NFS_ATTR_FATTR) == 0 ||
1763			!nfs_inode_attrs_need_update(inode, fattr)) {
1764		fattr->valid &= ~(NFS_ATTR_FATTR_PRECHANGE
1765				| NFS_ATTR_FATTR_PRESIZE
1766				| NFS_ATTR_FATTR_PREMTIME
1767				| NFS_ATTR_FATTR_PRECTIME);
1768		goto out_noforce;
1769	}
1770	if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 &&
1771			(fattr->valid & NFS_ATTR_FATTR_PRECHANGE) == 0) {
1772		fattr->pre_change_attr = inode_peek_iversion_raw(inode);
1773		fattr->valid |= NFS_ATTR_FATTR_PRECHANGE;
1774	}
1775	if ((fattr->valid & NFS_ATTR_FATTR_CTIME) != 0 &&
1776			(fattr->valid & NFS_ATTR_FATTR_PRECTIME) == 0) {
1777		fattr->pre_ctime = inode->i_ctime;
1778		fattr->valid |= NFS_ATTR_FATTR_PRECTIME;
1779	}
1780	if ((fattr->valid & NFS_ATTR_FATTR_MTIME) != 0 &&
1781			(fattr->valid & NFS_ATTR_FATTR_PREMTIME) == 0) {
1782		fattr->pre_mtime = inode->i_mtime;
1783		fattr->valid |= NFS_ATTR_FATTR_PREMTIME;
1784	}
1785	if ((fattr->valid & NFS_ATTR_FATTR_SIZE) != 0 &&
1786			(fattr->valid & NFS_ATTR_FATTR_PRESIZE) == 0) {
1787		fattr->pre_size = i_size_read(inode);
1788		fattr->valid |= NFS_ATTR_FATTR_PRESIZE;
1789	}
1790out_noforce:
1791	status = nfs_post_op_update_inode_locked(inode, fattr,
1792			NFS_INO_INVALID_CHANGE
1793			| NFS_INO_INVALID_CTIME
1794			| NFS_INO_INVALID_MTIME
1795			| NFS_INO_INVALID_BLOCKS);
1796	return status;
1797}
1798
1799/**
1800 * nfs_post_op_update_inode_force_wcc - try to update the inode attribute cache
1801 * @inode: pointer to inode
1802 * @fattr: updated attributes
1803 *
1804 * After an operation that has changed the inode metadata, mark the
1805 * attribute cache as being invalid, then try to update it. Fake up
1806 * weak cache consistency data, if none exist.
1807 *
1808 * This function is mainly designed to be used by the ->write_done() functions.
1809 */
1810int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fattr)
1811{
1812	int status;
1813
1814	spin_lock(&inode->i_lock);
1815	nfs_fattr_set_barrier(fattr);
1816	status = nfs_post_op_update_inode_force_wcc_locked(inode, fattr);
1817	spin_unlock(&inode->i_lock);
1818	return status;
1819}
1820EXPORT_SYMBOL_GPL(nfs_post_op_update_inode_force_wcc);
1821
1822
1823/*
1824 * Many nfs protocol calls return the new file attributes after
1825 * an operation.  Here we update the inode to reflect the state
1826 * of the server's inode.
1827 *
1828 * This is a bit tricky because we have to make sure all dirty pages
1829 * have been sent off to the server before calling invalidate_inode_pages.
1830 * To make sure no other process adds more write requests while we try
1831 * our best to flush them, we make them sleep during the attribute refresh.
1832 *
1833 * A very similar scenario holds for the dir cache.
1834 */
1835static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
1836{
1837	struct nfs_server *server;
1838	struct nfs_inode *nfsi = NFS_I(inode);
1839	loff_t cur_isize, new_isize;
1840	unsigned long invalid = 0;
1841	unsigned long now = jiffies;
1842	unsigned long save_cache_validity;
1843	bool have_writers = nfs_file_has_buffered_writers(nfsi);
1844	bool cache_revalidated = true;
1845	bool attr_changed = false;
1846	bool have_delegation;
1847
1848	dfprintk(VFS, "NFS: %s(%s/%lu fh_crc=0x%08x ct=%d info=0x%x)\n",
1849			__func__, inode->i_sb->s_id, inode->i_ino,
1850			nfs_display_fhandle_hash(NFS_FH(inode)),
1851			atomic_read(&inode->i_count), fattr->valid);
1852
1853	if (!(fattr->valid & NFS_ATTR_FATTR_FILEID)) {
1854		/* Only a mounted-on-fileid? Just exit */
1855		if (fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID)
1856			return 0;
1857	/* Has the inode gone and changed behind our back? */
1858	} else if (nfsi->fileid != fattr->fileid) {
1859		/* Is this perhaps the mounted-on fileid? */
1860		if ((fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) &&
1861		    nfsi->fileid == fattr->mounted_on_fileid)
1862			return 0;
1863		printk(KERN_ERR "NFS: server %s error: fileid changed\n"
1864			"fsid %s: expected fileid 0x%Lx, got 0x%Lx\n",
1865			NFS_SERVER(inode)->nfs_client->cl_hostname,
1866			inode->i_sb->s_id, (long long)nfsi->fileid,
1867			(long long)fattr->fileid);
1868		goto out_err;
1869	}
1870
1871	/*
1872	 * Make sure the inode's type hasn't changed.
1873	 */
1874	if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && inode_wrong_type(inode, fattr->mode)) {
1875		/*
1876		* Big trouble! The inode has become a different object.
1877		*/
1878		printk(KERN_DEBUG "NFS: %s: inode %lu mode changed, %07o to %07o\n",
1879				__func__, inode->i_ino, inode->i_mode, fattr->mode);
1880		goto out_err;
1881	}
1882
1883	server = NFS_SERVER(inode);
1884	/* Update the fsid? */
1885	if (S_ISDIR(inode->i_mode) && (fattr->valid & NFS_ATTR_FATTR_FSID) &&
1886			!nfs_fsid_equal(&server->fsid, &fattr->fsid) &&
1887			!IS_AUTOMOUNT(inode))
1888		server->fsid = fattr->fsid;
1889
1890	/* Save the delegation state before clearing cache_validity */
1891	have_delegation = nfs_have_delegated_attributes(inode);
1892
1893	/*
1894	 * Update the read time so we don't revalidate too often.
1895	 */
1896	nfsi->read_cache_jiffies = fattr->time_start;
1897
1898	save_cache_validity = nfsi->cache_validity;
1899	nfsi->cache_validity &= ~(NFS_INO_INVALID_ATTR
1900			| NFS_INO_INVALID_ATIME
1901			| NFS_INO_REVAL_FORCED
1902			| NFS_INO_REVAL_PAGECACHE
1903			| NFS_INO_INVALID_BLOCKS);
1904
1905	/* Do atomic weak cache consistency updates */
1906	nfs_wcc_update_inode(inode, fattr);
1907
1908	if (pnfs_layoutcommit_outstanding(inode)) {
1909		nfsi->cache_validity |=
1910			save_cache_validity &
1911			(NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME |
1912			 NFS_INO_INVALID_MTIME | NFS_INO_INVALID_SIZE |
1913			 NFS_INO_REVAL_FORCED);
1914		cache_revalidated = false;
1915	}
1916
1917	/* More cache consistency checks */
1918	if (fattr->valid & NFS_ATTR_FATTR_CHANGE) {
1919		if (!inode_eq_iversion_raw(inode, fattr->change_attr)) {
1920			/* Could it be a race with writeback? */
1921			if (!(have_writers || have_delegation)) {
1922				invalid |= NFS_INO_INVALID_DATA
1923					| NFS_INO_INVALID_ACCESS
1924					| NFS_INO_INVALID_ACL
1925					| NFS_INO_INVALID_XATTR;
1926				/* Force revalidate of all attributes */
1927				save_cache_validity |= NFS_INO_INVALID_CTIME
1928					| NFS_INO_INVALID_MTIME
1929					| NFS_INO_INVALID_SIZE
1930					| NFS_INO_INVALID_OTHER;
1931				if (S_ISDIR(inode->i_mode))
1932					nfs_force_lookup_revalidate(inode);
1933				dprintk("NFS: change_attr change on server for file %s/%ld\n",
1934						inode->i_sb->s_id,
1935						inode->i_ino);
1936			} else if (!have_delegation)
1937				nfsi->cache_validity |= NFS_INO_DATA_INVAL_DEFER;
1938			inode_set_iversion_raw(inode, fattr->change_attr);
1939			attr_changed = true;
1940		}
1941	} else {
1942		nfsi->cache_validity |= save_cache_validity &
1943				(NFS_INO_INVALID_CHANGE
1944				| NFS_INO_REVAL_PAGECACHE
1945				| NFS_INO_REVAL_FORCED);
1946		cache_revalidated = false;
1947	}
1948
1949	if (fattr->valid & NFS_ATTR_FATTR_MTIME) {
1950		inode->i_mtime = fattr->mtime;
1951	} else if (server->caps & NFS_CAP_MTIME) {
1952		nfsi->cache_validity |= save_cache_validity &
1953				(NFS_INO_INVALID_MTIME
1954				| NFS_INO_REVAL_FORCED);
1955		cache_revalidated = false;
1956	}
1957
1958	if (fattr->valid & NFS_ATTR_FATTR_CTIME) {
1959		inode->i_ctime = fattr->ctime;
1960	} else if (server->caps & NFS_CAP_CTIME) {
1961		nfsi->cache_validity |= save_cache_validity &
1962				(NFS_INO_INVALID_CTIME
1963				| NFS_INO_REVAL_FORCED);
1964		cache_revalidated = false;
1965	}
1966
1967	/* Check if our cached file size is stale */
1968	if (fattr->valid & NFS_ATTR_FATTR_SIZE) {
1969		new_isize = nfs_size_to_loff_t(fattr->size);
1970		cur_isize = i_size_read(inode);
1971		if (new_isize != cur_isize && !have_delegation) {
1972			/* Do we perhaps have any outstanding writes, or has
1973			 * the file grown beyond our last write? */
1974			if (!nfs_have_writebacks(inode) || new_isize > cur_isize) {
1975				i_size_write(inode, new_isize);
1976				if (!have_writers)
1977					invalid |= NFS_INO_INVALID_DATA;
1978				attr_changed = true;
1979			}
1980			dprintk("NFS: isize change on server for file %s/%ld "
1981					"(%Ld to %Ld)\n",
1982					inode->i_sb->s_id,
1983					inode->i_ino,
1984					(long long)cur_isize,
1985					(long long)new_isize);
1986		}
1987	} else {
1988		nfsi->cache_validity |= save_cache_validity &
1989				(NFS_INO_INVALID_SIZE
1990				| NFS_INO_REVAL_PAGECACHE
1991				| NFS_INO_REVAL_FORCED);
1992		cache_revalidated = false;
1993	}
1994
1995
1996	if (fattr->valid & NFS_ATTR_FATTR_ATIME)
1997		inode->i_atime = fattr->atime;
1998	else if (server->caps & NFS_CAP_ATIME) {
1999		nfsi->cache_validity |= save_cache_validity &
2000				(NFS_INO_INVALID_ATIME
2001				| NFS_INO_REVAL_FORCED);
2002		cache_revalidated = false;
2003	}
2004
2005	if (fattr->valid & NFS_ATTR_FATTR_MODE) {
2006		if ((inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO)) {
2007			umode_t newmode = inode->i_mode & S_IFMT;
2008			newmode |= fattr->mode & S_IALLUGO;
2009			inode->i_mode = newmode;
2010			invalid |= NFS_INO_INVALID_ACCESS
2011				| NFS_INO_INVALID_ACL;
2012			attr_changed = true;
2013		}
2014	} else if (server->caps & NFS_CAP_MODE) {
2015		nfsi->cache_validity |= save_cache_validity &
2016				(NFS_INO_INVALID_OTHER
2017				| NFS_INO_REVAL_FORCED);
2018		cache_revalidated = false;
2019	}
2020
2021	if (fattr->valid & NFS_ATTR_FATTR_OWNER) {
2022		if (!uid_eq(inode->i_uid, fattr->uid)) {
2023			invalid |= NFS_INO_INVALID_ACCESS
2024				| NFS_INO_INVALID_ACL;
2025			inode->i_uid = fattr->uid;
2026			attr_changed = true;
2027		}
2028	} else if (server->caps & NFS_CAP_OWNER) {
2029		nfsi->cache_validity |= save_cache_validity &
2030				(NFS_INO_INVALID_OTHER
2031				| NFS_INO_REVAL_FORCED);
2032		cache_revalidated = false;
2033	}
2034
2035	if (fattr->valid & NFS_ATTR_FATTR_GROUP) {
2036		if (!gid_eq(inode->i_gid, fattr->gid)) {
2037			invalid |= NFS_INO_INVALID_ACCESS
2038				| NFS_INO_INVALID_ACL;
2039			inode->i_gid = fattr->gid;
2040			attr_changed = true;
2041		}
2042	} else if (server->caps & NFS_CAP_OWNER_GROUP) {
2043		nfsi->cache_validity |= save_cache_validity &
2044				(NFS_INO_INVALID_OTHER
2045				| NFS_INO_REVAL_FORCED);
2046		cache_revalidated = false;
2047	}
2048
2049	if (fattr->valid & NFS_ATTR_FATTR_NLINK) {
2050		if (inode->i_nlink != fattr->nlink) {
2051			if (S_ISDIR(inode->i_mode))
2052				invalid |= NFS_INO_INVALID_DATA;
2053			set_nlink(inode, fattr->nlink);
2054			attr_changed = true;
2055		}
2056	} else if (server->caps & NFS_CAP_NLINK) {
2057		nfsi->cache_validity |= save_cache_validity &
2058				(NFS_INO_INVALID_OTHER
2059				| NFS_INO_REVAL_FORCED);
2060		cache_revalidated = false;
2061	}
2062
2063	if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) {
2064		/*
2065		 * report the blocks in 512byte units
2066		 */
2067		inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used);
2068	} else if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED)
2069		inode->i_blocks = fattr->du.nfs2.blocks;
2070	else {
2071		nfsi->cache_validity |= save_cache_validity &
2072				(NFS_INO_INVALID_BLOCKS
2073				| NFS_INO_REVAL_FORCED);
2074		cache_revalidated = false;
2075	}
2076
2077	/* Update attrtimeo value if we're out of the unstable period */
2078	if (attr_changed) {
2079		invalid &= ~NFS_INO_INVALID_ATTR;
2080		nfs_inc_stats(inode, NFSIOS_ATTRINVALIDATE);
2081		nfsi->attrtimeo = NFS_MINATTRTIMEO(inode);
2082		nfsi->attrtimeo_timestamp = now;
2083		/* Set barrier to be more recent than all outstanding updates */
2084		nfsi->attr_gencount = nfs_inc_attr_generation_counter();
2085	} else {
2086		if (cache_revalidated) {
2087			if (!time_in_range_open(now, nfsi->attrtimeo_timestamp,
2088				nfsi->attrtimeo_timestamp + nfsi->attrtimeo)) {
2089				nfsi->attrtimeo <<= 1;
2090				if (nfsi->attrtimeo > NFS_MAXATTRTIMEO(inode))
2091					nfsi->attrtimeo = NFS_MAXATTRTIMEO(inode);
2092			}
2093			nfsi->attrtimeo_timestamp = now;
2094		}
2095		/* Set the barrier to be more recent than this fattr */
2096		if ((long)(fattr->gencount - nfsi->attr_gencount) > 0)
2097			nfsi->attr_gencount = fattr->gencount;
2098	}
2099
2100	/* Don't invalidate the data if we were to blame */
2101	if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)
2102				|| S_ISLNK(inode->i_mode)))
2103		invalid &= ~NFS_INO_INVALID_DATA;
2104	nfs_set_cache_invalid(inode, invalid);
2105
2106	return 0;
2107 out_err:
2108	/*
2109	 * No need to worry about unhashing the dentry, as the
2110	 * lookup validation will know that the inode is bad.
2111	 * (But we fall through to invalidate the caches.)
2112	 */
2113	nfs_set_inode_stale_locked(inode);
2114	return -ESTALE;
2115}
2116
2117struct inode *nfs_alloc_inode(struct super_block *sb)
2118{
2119	struct nfs_inode *nfsi;
2120	nfsi = kmem_cache_alloc(nfs_inode_cachep, GFP_KERNEL);
2121	if (!nfsi)
2122		return NULL;
2123	nfsi->flags = 0UL;
2124	nfsi->cache_validity = 0UL;
2125#if IS_ENABLED(CONFIG_NFS_V4)
2126	nfsi->nfs4_acl = NULL;
2127#endif /* CONFIG_NFS_V4 */
2128#ifdef CONFIG_NFS_V4_2
2129	nfsi->xattr_cache = NULL;
2130#endif
2131	return &nfsi->vfs_inode;
2132}
2133EXPORT_SYMBOL_GPL(nfs_alloc_inode);
2134
2135void nfs_free_inode(struct inode *inode)
2136{
2137	kmem_cache_free(nfs_inode_cachep, NFS_I(inode));
2138}
2139EXPORT_SYMBOL_GPL(nfs_free_inode);
2140
2141static inline void nfs4_init_once(struct nfs_inode *nfsi)
2142{
2143#if IS_ENABLED(CONFIG_NFS_V4)
2144	INIT_LIST_HEAD(&nfsi->open_states);
2145	nfsi->delegation = NULL;
2146	init_rwsem(&nfsi->rwsem);
2147	nfsi->layout = NULL;
2148#endif
2149}
2150
2151static void init_once(void *foo)
2152{
2153	struct nfs_inode *nfsi = (struct nfs_inode *) foo;
2154
2155	inode_init_once(&nfsi->vfs_inode);
2156	INIT_LIST_HEAD(&nfsi->open_files);
2157	INIT_LIST_HEAD(&nfsi->access_cache_entry_lru);
2158	INIT_LIST_HEAD(&nfsi->access_cache_inode_lru);
2159	INIT_LIST_HEAD(&nfsi->commit_info.list);
2160	atomic_long_set(&nfsi->nrequests, 0);
2161	atomic_long_set(&nfsi->commit_info.ncommit, 0);
2162	atomic_set(&nfsi->commit_info.rpcs_out, 0);
2163	init_rwsem(&nfsi->rmdir_sem);
2164	mutex_init(&nfsi->commit_mutex);
2165	nfs4_init_once(nfsi);
2166	nfsi->cache_change_attribute = 0;
2167}
2168
2169static int __init nfs_init_inodecache(void)
2170{
2171	nfs_inode_cachep = kmem_cache_create("nfs_inode_cache",
2172					     sizeof(struct nfs_inode),
2173					     0, (SLAB_RECLAIM_ACCOUNT|
2174						SLAB_MEM_SPREAD|SLAB_ACCOUNT),
2175					     init_once);
2176	if (nfs_inode_cachep == NULL)
2177		return -ENOMEM;
2178
2179	return 0;
2180}
2181
2182static void nfs_destroy_inodecache(void)
2183{
2184	/*
2185	 * Make sure all delayed rcu free inodes are flushed before we
2186	 * destroy cache.
2187	 */
2188	rcu_barrier();
2189	kmem_cache_destroy(nfs_inode_cachep);
2190}
2191
2192struct workqueue_struct *nfsiod_workqueue;
2193EXPORT_SYMBOL_GPL(nfsiod_workqueue);
2194
2195/*
2196 * start up the nfsiod workqueue
2197 */
2198static int nfsiod_start(void)
2199{
2200	struct workqueue_struct *wq;
2201	dprintk("RPC:       creating workqueue nfsiod\n");
2202	wq = alloc_workqueue("nfsiod", WQ_MEM_RECLAIM | WQ_UNBOUND, 0);
2203	if (wq == NULL)
2204		return -ENOMEM;
2205	nfsiod_workqueue = wq;
2206	return 0;
2207}
2208
2209/*
2210 * Destroy the nfsiod workqueue
2211 */
2212static void nfsiod_stop(void)
2213{
2214	struct workqueue_struct *wq;
2215
2216	wq = nfsiod_workqueue;
2217	if (wq == NULL)
2218		return;
2219	nfsiod_workqueue = NULL;
2220	destroy_workqueue(wq);
2221}
2222
2223unsigned int nfs_net_id;
2224EXPORT_SYMBOL_GPL(nfs_net_id);
2225
2226static int nfs_net_init(struct net *net)
2227{
2228	struct nfs_net *nn = net_generic(net, nfs_net_id);
2229
2230	nfs_clients_init(net);
2231
2232	if (!rpc_proc_register(net, &nn->rpcstats)) {
2233		nfs_clients_exit(net);
2234		return -ENOMEM;
2235	}
2236
2237	return nfs_fs_proc_net_init(net);
2238}
2239
2240static void nfs_net_exit(struct net *net)
2241{
2242	rpc_proc_unregister(net, "nfs");
2243	nfs_fs_proc_net_exit(net);
2244	nfs_clients_exit(net);
2245}
2246
2247static struct pernet_operations nfs_net_ops = {
2248	.init = nfs_net_init,
2249	.exit = nfs_net_exit,
2250	.id   = &nfs_net_id,
2251	.size = sizeof(struct nfs_net),
2252};
2253
2254/*
2255 * Initialize NFS
2256 */
2257static int __init init_nfs_fs(void)
2258{
2259	int err;
2260
2261	err = nfs_sysfs_init();
2262	if (err < 0)
2263		goto out10;
2264
2265	err = register_pernet_subsys(&nfs_net_ops);
2266	if (err < 0)
2267		goto out9;
2268
2269	err = nfs_fscache_register();
2270	if (err < 0)
2271		goto out8;
2272
2273	err = nfsiod_start();
2274	if (err)
2275		goto out7;
2276
2277	err = nfs_fs_proc_init();
2278	if (err)
2279		goto out6;
2280
2281	err = nfs_init_nfspagecache();
2282	if (err)
2283		goto out5;
2284
2285	err = nfs_init_inodecache();
2286	if (err)
2287		goto out4;
2288
2289	err = nfs_init_readpagecache();
2290	if (err)
2291		goto out3;
2292
2293	err = nfs_init_writepagecache();
2294	if (err)
2295		goto out2;
2296
2297	err = nfs_init_directcache();
2298	if (err)
2299		goto out1;
2300
2301	err = register_nfs_fs();
2302	if (err)
2303		goto out0;
2304
2305	return 0;
2306out0:
2307	nfs_destroy_directcache();
2308out1:
2309	nfs_destroy_writepagecache();
2310out2:
2311	nfs_destroy_readpagecache();
2312out3:
2313	nfs_destroy_inodecache();
2314out4:
2315	nfs_destroy_nfspagecache();
2316out5:
2317	nfs_fs_proc_exit();
2318out6:
2319	nfsiod_stop();
2320out7:
2321	nfs_fscache_unregister();
2322out8:
2323	unregister_pernet_subsys(&nfs_net_ops);
2324out9:
2325	nfs_sysfs_exit();
2326out10:
2327	return err;
2328}
2329
2330static void __exit exit_nfs_fs(void)
2331{
2332	nfs_destroy_directcache();
2333	nfs_destroy_writepagecache();
2334	nfs_destroy_readpagecache();
2335	nfs_destroy_inodecache();
2336	nfs_destroy_nfspagecache();
2337	nfs_fscache_unregister();
2338	unregister_pernet_subsys(&nfs_net_ops);
2339	unregister_nfs_fs();
2340	nfs_fs_proc_exit();
2341	nfsiod_stop();
2342	nfs_sysfs_exit();
2343}
2344
2345/* Not quite true; I just maintain it */
2346MODULE_AUTHOR("Olaf Kirch <okir@monad.swb.de>");
2347MODULE_LICENSE("GPL");
2348module_param(enable_ino64, bool, 0644);
2349
2350module_init(init_nfs_fs)
2351module_exit(exit_nfs_fs)
2352