summaryrefslogtreecommitdiff
path: root/fs/nfs/fscache.c
blob: b55fc7920c3b6a692affefebf75b6f43cedd9b01 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
/* NFS filesystem cache interface
 *
 * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
 * Written by David Howells (dhowells@redhat.com)
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public Licence
 * as published by the Free Software Foundation; either version
 * 2 of the Licence, or (at your option) any later version.
 */

#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/nfs_fs.h>
#include <linux/nfs_fs_sb.h>
#include <linux/in6.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <linux/iversion.h>

#include "internal.h"
#include "iostat.h"
#include "fscache.h"

#define NFSDBG_FACILITY		NFSDBG_FSCACHE

static struct rb_root nfs_fscache_keys = RB_ROOT;
static DEFINE_SPINLOCK(nfs_fscache_keys_lock);

/*
 * Layout of the key for an NFS server cache object.
 */
struct nfs_server_key {
	struct {
		uint16_t	nfsversion;		/* NFS protocol version */
		uint16_t	family;			/* address family */
		__be16		port;			/* IP port */
	} hdr;
	union {
		struct in_addr	ipv4_addr;	/* IPv4 address */
		struct in6_addr ipv6_addr;	/* IPv6 address */
	};
} __packed;

/*
 * Get the per-client index cookie for an NFS client if the appropriate mount
 * flag was set
 * - We always try and get an index cookie for the client, but get filehandle
 *   cookies on a per-superblock basis, depending on the mount flags
 */
void nfs_fscache_get_client_cookie(struct nfs_client *clp)
{
	const struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) &clp->cl_addr;
	const struct sockaddr_in *sin = (struct sockaddr_in *) &clp->cl_addr;
	struct nfs_server_key key;
	uint16_t len = sizeof(key.hdr);

	memset(&key, 0, sizeof(key));
	key.hdr.nfsversion = clp->rpc_ops->version;
	key.hdr.family = clp->cl_addr.ss_family;

	switch (clp->cl_addr.ss_family) {
	case AF_INET:
		key.hdr.port = sin->sin_port;
		key.ipv4_addr = sin->sin_addr;
		len += sizeof(key.ipv4_addr);
		break;

	case AF_INET6:
		key.hdr.port = sin6->sin6_port;
		key.ipv6_addr = sin6->sin6_addr;
		len += sizeof(key.ipv6_addr);
		break;

	default:
		printk(KERN_WARNING "NFS: Unknown network family '%d'\n",
		       clp->cl_addr.ss_family);
		clp->fscache = NULL;
		return;
	}

	/* create a cache index for looking up filehandles */
	clp->fscache = fscache_acquire_cookie(nfs_fscache_netfs.primary_index,
					      &nfs_fscache_server_index_def,
					      &key, len,
					      NULL, 0,
					      clp, 0, true);
	dfprintk(FSCACHE, "NFS: get client cookie (0x%p/0x%p)\n",
		 clp, clp->fscache);
}

/*
 * Dispose of a per-client cookie
 */
void nfs_fscache_release_client_cookie(struct nfs_client *clp)
{
	dfprintk(FSCACHE, "NFS: releasing client cookie (0x%p/0x%p)\n",
		 clp, clp->fscache);

	fscache_relinquish_cookie(clp->fscache, NULL, false);
	clp->fscache = NULL;
}

/*
 * Get the cache cookie for an NFS superblock.  We have to handle
 * uniquification here because the cache doesn't do it for us.
 *
 * The default uniquifier is just an empty string, but it may be overridden
 * either by the 'fsc=xxx' option to mount, or by inheriting it from the parent
 * superblock across an automount point of some nature.
 */
void nfs_fscache_get_super_cookie(struct super_block *sb, const char *uniq, int ulen)
{
	struct nfs_fscache_key *key, *xkey;
	struct nfs_server *nfss = NFS_SB(sb);
	struct rb_node **p, *parent;
	int diff;

	if (!uniq) {
		uniq = "";
		ulen = 1;
	}

	key = kzalloc(sizeof(*key) + ulen, GFP_KERNEL);
	if (!key)
		return;

	key->nfs_client = nfss->nfs_client;
	key->key.super.s_flags = sb->s_flags & NFS_MS_MASK;
	key->key.nfs_server.flags = nfss->flags;
	key->key.nfs_server.rsize = nfss->rsize;
	key->key.nfs_server.wsize = nfss->wsize;
	key->key.nfs_server.acregmin = nfss->acregmin;
	key->key.nfs_server.acregmax = nfss->acregmax;
	key->key.nfs_server.acdirmin = nfss->acdirmin;
	key->key.nfs_server.acdirmax = nfss->acdirmax;
	key->key.nfs_server.fsid = nfss->fsid;
	key->key.rpc_auth.au_flavor = nfss->client->cl_auth->au_flavor;

	key->key.uniq_len = ulen;
	memcpy(key->key.uniquifier, uniq, ulen);

	spin_lock(&nfs_fscache_keys_lock);
	p = &nfs_fscache_keys.rb_node;
	parent = NULL;
	while (*p) {
		parent = *p;
		xkey = rb_entry(parent, struct nfs_fscache_key, node);

		if (key->nfs_client < xkey->nfs_client)
			goto go_left;
		if (key->nfs_client > xkey->nfs_client)
			goto go_right;

		diff = memcmp(&key->key, &xkey->key, sizeof(key->key));
		if (diff < 0)
			goto go_left;
		if (diff > 0)
			goto go_right;

		if (key->key.uniq_len == 0)
			goto non_unique;
		diff = memcmp(key->key.uniquifier,
			      xkey->key.uniquifier,
			      key->key.uniq_len);
		if (diff < 0)
			goto go_left;
		if (diff > 0)
			goto go_right;
		goto non_unique;

	go_left:
		p = &(*p)->rb_left;
		continue;
	go_right:
		p = &(*p)->rb_right;
	}

	rb_link_node(&key->node, parent, p);
	rb_insert_color(&key->node, &nfs_fscache_keys);
	spin_unlock(&nfs_fscache_keys_lock);
	nfss->fscache_key = key;

	/* create a cache index for looking up filehandles */
	nfss->fscache = fscache_acquire_cookie(nfss->nfs_client->fscache,
					       &nfs_fscache_super_index_def,
					       key, sizeof(*key) + ulen,
					       NULL, 0,
					       nfss, 0, true);
	dfprintk(FSCACHE, "NFS: get superblock cookie (0x%p/0x%p)\n",
		 nfss, nfss->fscache);
	return;

non_unique:
	spin_unlock(&nfs_fscache_keys_lock);
	kfree(key);
	nfss->fscache_key = NULL;
	nfss->fscache = NULL;
	printk(KERN_WARNING "NFS:"
	       " Cache request denied due to non-unique superblock keys\n");
}

/*
 * release a per-superblock cookie
 */
void nfs_fscache_release_super_cookie(struct super_block *sb)
{
	struct nfs_server *nfss = NFS_SB(sb);

	dfprintk(FSCACHE, "NFS: releasing superblock cookie (0x%p/0x%p)\n",
		 nfss, nfss->fscache);

	fscache_relinquish_cookie(nfss->fscache, NULL, false);
	nfss->fscache = NULL;

	if (nfss->fscache_key) {
		spin_lock(&nfs_fscache_keys_lock);
		rb_erase(&nfss->fscache_key->node, &nfs_fscache_keys);
		spin_unlock(&nfs_fscache_keys_lock);
		kfree(nfss->fscache_key);
		nfss->fscache_key = NULL;
	}
}

/*
 * Initialise the per-inode cache cookie pointer for an NFS inode.
 */
void nfs_fscache_init_inode(struct inode *inode)
{
	struct nfs_fscache_inode_auxdata auxdata;
	struct nfs_inode *nfsi = NFS_I(inode);

	nfsi->fscache = NULL;
	if (!S_ISREG(inode->i_mode))
		return;

	memset(&auxdata, 0, sizeof(auxdata));
	auxdata.mtime = nfsi->vfs_inode.i_mtime;
	auxdata.ctime = nfsi->vfs_inode.i_ctime;

	if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4)
		auxdata.change_attr = inode_peek_iversion_raw(&nfsi->vfs_inode);

	nfsi->fscache = fscache_acquire_cookie(NFS_SB(inode->i_sb)->fscache,
					       &nfs_fscache_inode_object_def,
					       nfsi->fh.data, nfsi->fh.size,
					       &auxdata, sizeof(auxdata),
					       nfsi, nfsi->vfs_inode.i_size, false);
}

/*
 * Release a per-inode cookie.
 */
void nfs_fscache_clear_inode(struct inode *inode)
{
	struct nfs_fscache_inode_auxdata auxdata;
	struct nfs_inode *nfsi = NFS_I(inode);
	struct fscache_cookie *cookie = nfs_i_fscache(inode);

	dfprintk(FSCACHE, "NFS: clear cookie (0x%p/0x%p)\n", nfsi, cookie);

	memset(&auxdata, 0, sizeof(auxdata));
	auxdata.mtime = nfsi->vfs_inode.i_mtime;
	auxdata.ctime = nfsi->vfs_inode.i_ctime;
	fscache_relinquish_cookie(cookie, &auxdata, false);
	nfsi->fscache = NULL;
}

static bool nfs_fscache_can_enable(void *data)
{
	struct inode *inode = data;

	return !inode_is_open_for_write(inode);
}

/*
 * Enable or disable caching for a file that is being opened as appropriate.
 * The cookie is allocated when the inode is initialised, but is not enabled at
 * that time.  Enablement is deferred to file-open time to avoid stat() and
 * access() thrashing the cache.
 *
 * For now, with NFS, only regular files that are open read-only will be able
 * to use the cache.
 *
 * We enable the cache for an inode if we open it read-only and it isn't
 * currently open for writing.  We disable the cache if the inode is open
 * write-only.
 *
 * The caller uses the file struct to pin i_writecount on the inode before
 * calling us when a file is opened for writing, so we can make use of that.
 *
 * Note that this may be invoked multiple times in parallel by parallel
 * nfs_open() functions.
 */
void nfs_fscache_open_file(struct inode *inode, struct file *filp)
{
	struct nfs_fscache_inode_auxdata auxdata;
	struct nfs_inode *nfsi = NFS_I(inode);
	struct fscache_cookie *cookie = nfs_i_fscache(inode);

	if (!fscache_cookie_valid(cookie))
		return;

	memset(&auxdata, 0, sizeof(auxdata));
	auxdata.mtime = nfsi->vfs_inode.i_mtime;
	auxdata.ctime = nfsi->vfs_inode.i_ctime;

	if (inode_is_open_for_write(inode)) {
		dfprintk(FSCACHE, "NFS: nfsi 0x%p disabling cache\n", nfsi);
		clear_bit(NFS_INO_FSCACHE, &nfsi->flags);
		fscache_disable_cookie(cookie, &auxdata, true);
		fscache_uncache_all_inode_pages(cookie, inode);
	} else {
		dfprintk(FSCACHE, "NFS: nfsi 0x%p enabling cache\n", nfsi);
		fscache_enable_cookie(cookie, &auxdata, nfsi->vfs_inode.i_size,
				      nfs_fscache_can_enable, inode);
		if (fscache_cookie_enabled(cookie))
			set_bit(NFS_INO_FSCACHE, &NFS_I(inode)->flags);
	}
}
EXPORT_SYMBOL_GPL(nfs_fscache_open_file);

/*
 * Release the caching state associated with a page, if the page isn't busy
 * interacting with the cache.
 * - Returns true (can release page) or false (page busy).
 */
int nfs_fscache_release_page(struct page *page, gfp_t gfp)
{
	if (PageFsCache(page)) {
		struct fscache_cookie *cookie = nfs_i_fscache(page->mapping->host);

		BUG_ON(!cookie);
		dfprintk(FSCACHE, "NFS: fscache releasepage (0x%p/0x%p/0x%p)\n",
			 cookie, page, NFS_I(page->mapping->host));

		if (!fscache_maybe_release_page(cookie, page, gfp))
			return 0;

		nfs_inc_fscache_stats(page->mapping->host,
				      NFSIOS_FSCACHE_PAGES_UNCACHED);
	}

	return 1;
}

/*
 * Release the caching state associated with a page if undergoing complete page
 * invalidation.
 */
void __nfs_fscache_invalidate_page(struct page *page, struct inode *inode)
{
	struct fscache_cookie *cookie = nfs_i_fscache(inode);

	BUG_ON(!cookie);

	dfprintk(FSCACHE, "NFS: fscache invalidatepage (0x%p/0x%p/0x%p)\n",
		 cookie, page, NFS_I(inode));

	fscache_wait_on_page_write(cookie, page);

	BUG_ON(!PageLocked(page));
	fscache_uncache_page(cookie, page);
	nfs_inc_fscache_stats(page->mapping->host,
			      NFSIOS_FSCACHE_PAGES_UNCACHED);
}

/*
 * Handle completion of a page being read from the cache.
 * - Called in process (keventd) context.
 */
static void nfs_readpage_from_fscache_complete(struct page *page,
					       void *context,
					       int error)
{
	dfprintk(FSCACHE,
		 "NFS: readpage_from_fscache_complete (0x%p/0x%p/%d)\n",
		 page, context, error);

	/* if the read completes with an error, we just unlock the page and let
	 * the VM reissue the readpage */
	if (!error) {
		SetPageUptodate(page);
		unlock_page(page);
	} else {
		error = nfs_readpage_async(context, page->mapping->host, page);
		if (error)
			unlock_page(page);
	}
}

/*
 * Retrieve a page from fscache
 */
int __nfs_readpage_from_fscache(struct nfs_open_context *ctx,
				struct inode *inode, struct page *page)
{
	int ret;

	dfprintk(FSCACHE,
		 "NFS: readpage_from_fscache(fsc:%p/p:%p(i:%lx f:%lx)/0x%p)\n",
		 nfs_i_fscache(inode), page, page->index, page->flags, inode);

	ret = fscache_read_or_alloc_page(nfs_i_fscache(inode),
					 page,
					 nfs_readpage_from_fscache_complete,
					 ctx,
					 GFP_KERNEL);

	switch (ret) {
	case 0: /* read BIO submitted (page in fscache) */
		dfprintk(FSCACHE,
			 "NFS:    readpage_from_fscache: BIO submitted\n");
		nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_OK);
		return ret;

	case -ENOBUFS: /* inode not in cache */
	case -ENODATA: /* page not in cache */
		nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL);
		dfprintk(FSCACHE,
			 "NFS:    readpage_from_fscache %d\n", ret);
		return 1;

	default:
		dfprintk(FSCACHE, "NFS:    readpage_from_fscache %d\n", ret);
		nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL);
	}
	return ret;
}

/*
 * Retrieve a set of pages from fscache
 */
int __nfs_readpages_from_fscache(struct nfs_open_context *ctx,
				 struct inode *inode,
				 struct address_space *mapping,
				 struct list_head *pages,
				 unsigned *nr_pages)
{
	unsigned npages = *nr_pages;
	int ret;

	dfprintk(FSCACHE, "NFS: nfs_getpages_from_fscache (0x%p/%u/0x%p)\n",
		 nfs_i_fscache(inode), npages, inode);

	ret = fscache_read_or_alloc_pages(nfs_i_fscache(inode),
					  mapping, pages, nr_pages,
					  nfs_readpage_from_fscache_complete,
					  ctx,
					  mapping_gfp_mask(mapping));
	if (*nr_pages < npages)
		nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_OK,
				      npages);
	if (*nr_pages > 0)
		nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL,
				      *nr_pages);

	switch (ret) {
	case 0: /* read submitted to the cache for all pages */
		BUG_ON(!list_empty(pages));
		BUG_ON(*nr_pages != 0);
		dfprintk(FSCACHE,
			 "NFS: nfs_getpages_from_fscache: submitted\n");

		return ret;

	case -ENOBUFS: /* some pages aren't cached and can't be */
	case -ENODATA: /* some pages aren't cached */
		dfprintk(FSCACHE,
			 "NFS: nfs_getpages_from_fscache: no page: %d\n", ret);
		return 1;

	default:
		dfprintk(FSCACHE,
			 "NFS: nfs_getpages_from_fscache: ret  %d\n", ret);
	}

	return ret;
}

/*
 * Store a newly fetched page in fscache
 * - PG_fscache must be set on the page
 */
void __nfs_readpage_to_fscache(struct inode *inode, struct page *page, int sync)
{
	int ret;

	dfprintk(FSCACHE,
		 "NFS: readpage_to_fscache(fsc:%p/p:%p(i:%lx f:%lx)/%d)\n",
		 nfs_i_fscache(inode), page, page->index, page->flags, sync);

	ret = fscache_write_page(nfs_i_fscache(inode), page,
				 inode->i_size, GFP_KERNEL);
	dfprintk(FSCACHE,
		 "NFS:     readpage_to_fscache: p:%p(i:%lu f:%lx) ret %d\n",
		 page, page->index, page->flags, ret);

	if (ret != 0) {
		fscache_uncache_page(nfs_i_fscache(inode), page);
		nfs_inc_fscache_stats(inode,
				      NFSIOS_FSCACHE_PAGES_WRITTEN_FAIL);
		nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_UNCACHED);
	} else {
		nfs_inc_fscache_stats(inode,
				      NFSIOS_FSCACHE_PAGES_WRITTEN_OK);
	}
}