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
|
/*
* linux/fs/nfs/pagelist.c
*
* A set of helper functions for managing NFS read and write requests.
* The main purpose of these routines is to provide support for the
* coalescing of several requests into a single RPC call.
*
* Copyright 2000, 2001 (c) Trond Myklebust <trond.myklebust@fys.uio.no>
*
*/
#include <linux/slab.h>
#include <linux/file.h>
#include <linux/sched.h>
#include <linux/sunrpc/clnt.h>
#include <linux/nfs3.h>
#include <linux/nfs4.h>
#include <linux/nfs_page.h>
#include <linux/nfs_fs.h>
#include <linux/nfs_mount.h>
#include "internal.h"
static struct kmem_cache *nfs_page_cachep;
static inline struct nfs_page *
nfs_page_alloc(void)
{
struct nfs_page *p;
p = kmem_cache_alloc(nfs_page_cachep, GFP_KERNEL);
if (p) {
memset(p, 0, sizeof(*p));
INIT_LIST_HEAD(&p->wb_list);
}
return p;
}
static inline void
nfs_page_free(struct nfs_page *p)
{
kmem_cache_free(nfs_page_cachep, p);
}
/**
* nfs_create_request - Create an NFS read/write request.
* @file: file descriptor to use
* @inode: inode to which the request is attached
* @page: page to write
* @offset: starting offset within the page for the write
* @count: number of bytes to read/write
*
* The page must be locked by the caller. This makes sure we never
* create two different requests for the same page.
* User should ensure it is safe to sleep in this function.
*/
struct nfs_page *
nfs_create_request(struct nfs_open_context *ctx, struct inode *inode,
struct page *page,
unsigned int offset, unsigned int count)
{
struct nfs_page *req;
/* try to allocate the request struct */
req = nfs_page_alloc();
if (req == NULL)
return ERR_PTR(-ENOMEM);
/* Initialize the request struct. Initially, we assume a
* long write-back delay. This will be adjusted in
* update_nfs_request below if the region is not locked. */
req->wb_page = page;
atomic_set(&req->wb_complete, 0);
req->wb_index = page->index;
page_cache_get(page);
BUG_ON(PagePrivate(page));
BUG_ON(!PageLocked(page));
BUG_ON(page->mapping->host != inode);
req->wb_offset = offset;
req->wb_pgbase = offset;
req->wb_bytes = count;
req->wb_context = get_nfs_open_context(ctx);
req->wb_lock_context = nfs_get_lock_context(ctx);
kref_init(&req->wb_kref);
return req;
}
/**
* nfs_unlock_request - Unlock request and wake up sleepers.
* @req:
*/
void nfs_unlock_request(struct nfs_page *req)
{
if (!NFS_WBACK_BUSY(req)) {
printk(KERN_ERR "NFS: Invalid unlock attempted\n");
BUG();
}
smp_mb__before_clear_bit();
clear_bit(PG_BUSY, &req->wb_flags);
smp_mb__after_clear_bit();
wake_up_bit(&req->wb_flags, PG_BUSY);
nfs_release_request(req);
}
/**
* nfs_set_page_tag_locked - Tag a request as locked
* @req:
*/
int nfs_set_page_tag_locked(struct nfs_page *req)
{
if (!nfs_lock_request_dontget(req))
return 0;
if (req->wb_page != NULL)
radix_tree_tag_set(&NFS_I(req->wb_context->path.dentry->d_inode)->nfs_page_tree, req->wb_index, NFS_PAGE_TAG_LOCKED);
return 1;
}
/**
* nfs_clear_page_tag_locked - Clear request tag and wake up sleepers
*/
void nfs_clear_page_tag_locked(struct nfs_page *req)
{
if (req->wb_page != NULL) {
struct inode *inode = req->wb_context->path.dentry->d_inode;
struct nfs_inode *nfsi = NFS_I(inode);
spin_lock(&inode->i_lock);
radix_tree_tag_clear(&nfsi->nfs_page_tree, req->wb_index, NFS_PAGE_TAG_LOCKED);
nfs_unlock_request(req);
spin_unlock(&inode->i_lock);
} else
nfs_unlock_request(req);
}
/**
* nfs_clear_request - Free up all resources allocated to the request
* @req:
*
* Release page and open context resources associated with a read/write
* request after it has completed.
*/
void nfs_clear_request(struct nfs_page *req)
{
struct page *page = req->wb_page;
struct nfs_open_context *ctx = req->wb_context;
struct nfs_lock_context *l_ctx = req->wb_lock_context;
if (page != NULL) {
page_cache_release(page);
req->wb_page = NULL;
}
if (l_ctx != NULL) {
nfs_put_lock_context(l_ctx);
req->wb_lock_context = NULL;
}
if (ctx != NULL) {
put_nfs_open_context(ctx);
req->wb_context = NULL;
}
}
/**
* nfs_release_request - Release the count on an NFS read/write request
* @req: request to release
*
* Note: Should never be called with the spinlock held!
*/
static void nfs_free_request(struct kref *kref)
{
struct nfs_page *req = container_of(kref, struct nfs_page, wb_kref);
/* Release struct file and open context */
nfs_clear_request(req);
nfs_page_free(req);
}
void nfs_release_request(struct nfs_page *req)
{
kref_put(&req->wb_kref, nfs_free_request);
}
static int nfs_wait_bit_uninterruptible(void *word)
{
io_schedule();
return 0;
}
/**
* nfs_wait_on_request - Wait for a request to complete.
* @req: request to wait upon.
*
* Interruptible by fatal signals only.
* The user is responsible for holding a count on the request.
*/
int
nfs_wait_on_request(struct nfs_page *req)
{
return wait_on_bit(&req->wb_flags, PG_BUSY,
nfs_wait_bit_uninterruptible,
TASK_UNINTERRUPTIBLE);
}
/**
* nfs_pageio_init - initialise a page io descriptor
* @desc: pointer to descriptor
* @inode: pointer to inode
* @doio: pointer to io function
* @bsize: io block size
* @io_flags: extra parameters for the io function
*/
void nfs_pageio_init(struct nfs_pageio_descriptor *desc,
struct inode *inode,
int (*doio)(struct inode *, struct list_head *, unsigned int, size_t, int),
size_t bsize,
int io_flags)
{
INIT_LIST_HEAD(&desc->pg_list);
desc->pg_bytes_written = 0;
desc->pg_count = 0;
desc->pg_bsize = bsize;
desc->pg_base = 0;
desc->pg_inode = inode;
desc->pg_doio = doio;
desc->pg_ioflags = io_flags;
desc->pg_error = 0;
}
/**
* nfs_can_coalesce_requests - test two requests for compatibility
* @prev: pointer to nfs_page
* @req: pointer to nfs_page
*
* The nfs_page structures 'prev' and 'req' are compared to ensure that the
* page data area they describe is contiguous, and that their RPC
* credentials, NFSv4 open state, and lockowners are the same.
*
* Return 'true' if this is the case, else return 'false'.
*/
static int nfs_can_coalesce_requests(struct nfs_page *prev,
struct nfs_page *req)
{
if (req->wb_context->cred != prev->wb_context->cred)
return 0;
if (req->wb_lock_context->lockowner != prev->wb_lock_context->lockowner)
return 0;
if (req->wb_context->state != prev->wb_context->state)
return 0;
if (req->wb_index != (prev->wb_index + 1))
return 0;
if (req->wb_pgbase != 0)
return 0;
if (prev->wb_pgbase + prev->wb_bytes != PAGE_CACHE_SIZE)
return 0;
return 1;
}
/**
* nfs_pageio_do_add_request - Attempt to coalesce a request into a page list.
* @desc: destination io descriptor
* @req: request
*
* Returns true if the request 'req' was successfully coalesced into the
* existing list of pages 'desc'.
*/
static int nfs_pageio_do_add_request(struct nfs_pageio_descriptor *desc,
struct nfs_page *req)
{
size_t newlen = req->wb_bytes;
if (desc->pg_count != 0) {
struct nfs_page *prev;
/*
* FIXME: ideally we should be able to coalesce all requests
* that are not block boundary aligned, but currently this
* is problematic for the case of bsize < PAGE_CACHE_SIZE,
* since nfs_flush_multi and nfs_pagein_multi assume you
* can have only one struct nfs_page.
*/
if (desc->pg_bsize < PAGE_SIZE)
return 0;
newlen += desc->pg_count;
if (newlen > desc->pg_bsize)
return 0;
prev = nfs_list_entry(desc->pg_list.prev);
if (!nfs_can_coalesce_requests(prev, req))
return 0;
} else
desc->pg_base = req->wb_pgbase;
nfs_list_remove_request(req);
nfs_list_add_request(req, &desc->pg_list);
desc->pg_count = newlen;
return 1;
}
/*
* Helper for nfs_pageio_add_request and nfs_pageio_complete
*/
static void nfs_pageio_doio(struct nfs_pageio_descriptor *desc)
{
if (!list_empty(<
|