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
|
/*
* 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/config.h>
#include <linux/slab.h>
#include <linux/file.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>
#define NFS_PARANOIA 1
static kmem_cache_t *nfs_page_cachep;
static inline struct nfs_page *
nfs_page_alloc(void)
{
struct nfs_page *p;
p = kmem_cache_alloc(nfs_page_cachep, SLAB_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, and avoids
* a possible deadlock when we reach the hard limit on the number
* of dirty pages.
* 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_server *server = NFS_SERVER(inode);
struct nfs_page *req;
/* Deal with hard limits. */
for (;;) {
/* try to allocate the request struct */
req = nfs_page_alloc();
if (req != NULL)
break;
/* Try to free up at least one request in order to stay
* below the hard limit
*/
if (signalled() && (server->flags & NFS_MOUNT_INTR))
return ERR_PTR(-ERESTARTSYS);
yield();
}
/* 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);
req->wb_offset = offset;
req->wb_pgbase = offset;
req->wb_bytes = count;
atomic_set(&req->wb_count, 1);
req->wb_context = get_nfs_open_context(ctx);
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_writeback_locked - Lock a request for writeback
* @req:
*/
int nfs_set_page_writeback_locked(struct nfs_page *req)
{
struct nfs_inode *nfsi = NFS_I(req->wb_context->dentry->d_inode);
if (!nfs_lock_request(req))
return 0;
radix_tree_tag_set(&nfsi->nfs_page_tree, req->wb_index, NFS_PAGE_TAG_WRITEBACK);
return 1;
}
/**
* nfs_clear_page_writeback - Unlock request and wake up sleepers
*/
void nfs_clear_page_writeback(struct nfs_page *req)
{
struct nfs_inode *nfsi = NFS_I(req->wb_context->dentry->d_inode);
spin_lock(&nfsi->req_lock);
radix_tree_tag_clear(&nfsi->nfs_page_tree, req->wb_index, NFS_PAGE_TAG_WRITEBACK);
spin_unlock(&nfsi->req_lock);
nfs_unlock_request(req);
}
/**
* nfs_clear_request - Free up all resources allocated to the request
* @req:
*
* Release page resources associated with a write request after it
* has completed.
*/
void nfs_clear_request(struct nfs_page *req)
{
if (req->wb_page) {
page_cache_release(req->wb_page);
req->wb_page = 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!
*/
void
nfs_release_request(struct nfs_page *req)
{
if (!atomic_dec_and_test(&req->wb_count))
return;
#ifdef NFS_PARANOIA
BUG_ON (!list_empty(&req->wb_list));
BUG_ON (NFS_WBACK_BUSY(req));
#endif
/* Release struct file or cached credential */
nfs_clear_request(req);
put_nfs_open_context(req->wb_context);
nfs_page_free(req);
}
static int nfs_wait_bit_interruptible(void *word)
{
int ret = 0;
if (signal_pending(current))
ret = -ERESTARTSYS;
else
schedule();
return ret;
}
/**
* nfs_wait_on_request - Wait for a request to complete.
* @req: request to wait upon.
*
* Interruptible by signals only if mounted with intr flag.
* The user is responsible for holding a count on the request.
*/
int
nfs_wait_on_request(struct nfs_page *req)
{
struct rpc_clnt *clnt = NFS_CLIENT(req->wb_context->dentry->d_inode);
sigset_t oldmask;
int ret = 0;
if (!test_bit(PG_BUSY, &req->wb_flags))
goto out;
/*
* Note: the call to rpc_clnt_sigmask() suffices to ensure that we
* are not interrupted if intr flag is not set
*/
rpc_clnt_sigmask(clnt, &oldmask);
ret = out_of_line_wait_on_bit(&req->wb_flags, PG_BUSY,
nfs_wait_bit_interruptible, TASK_INTERRUPTIBLE);
rpc_clnt_sigunmask(clnt, &oldmask);
out:
return ret;
}
/**
* nfs_coalesce_requests - Split coalesced requests out from a list.
* @head: source list
* @dst: destination list
* @nmax: maximum number of requests to coalesce
*
* Moves a maximum of 'nmax' elements from one list to another.
* The elements are checked to ensure that they form a contiguous set
* of pages, and that the RPC credentials are the same.
*/
int
nfs_coalesce_requests(struct list_head *head, struct list_head *dst,
unsigned int nmax)
{
struct nfs_page *req = NULL;
unsigned int npages = 0;
while (!list_empty(head)) {
struct nfs_page *prev = req;
req = nfs_list_entry(head->next);
if (prev) {
if (req->wb_context->cred != prev->wb_context->cred)
break;
if (req->wb_context->lockowner != prev->wb_context->lockowner)
break;
if (req->wb_context->state != prev->wb_context->state)
break;
if (req->wb_index != (prev->wb_index + 1))
break;
if (req->wb_pgbase != 0)
break;
}
nfs_list_remove_request(req);
nfs_list_add_request(req, dst);
npages++;
if (req->wb_pgbase + req->wb_bytes != PAGE_CACHE_SIZE)
break;
if (npages >= nmax)
break;
}
return npages;
}
#define NFS_SCAN_MAXENTRIES 16
/**
* nfs_scan_lock_dirty - Scan the radix tree for dirty requests
* @nfsi: NFS inode
* @dst: Destination list
* @idx_start: lower bound of page->index to scan
* @npages: idx_start + npages sets the upper bound to scan.
*
* Moves elements from one of the inode request lists.
* If the number of requests is set to 0, the entire address_space
* starting at index idx_start, is scanned.
* The requests are *not* checked to ensure that they form a contiguous set.
* You must be holding the inode's req_lock when calling this function
*/
int
nfs_scan_lock_dirty(struct nfs_inode *nfsi, struct list_head *dst,
unsigned long idx_start, unsigned int npages)
{
struct nfs_page *pgvec[NFS_SCAN_MAXENTRIES];
struct nfs_page *req;
unsigned long idx_end;
int found, i;
int res;
res = 0;
if (npages == 0)
idx_end = ~0;
else
idx_end = idx_start + npages - 1;
for (;;) {
found = radix_tree_gang_lookup_tag(&nfsi->nfs_page_tree,
(void **)&pgvec[0], idx_start, NFS_SCAN_MAXENTRIES,
NFS_PAGE_TAG_DIRTY);
if (found <= 0)
break;
for (i = 0; i < found; i++) {
req = pgvec[i];
if (req->wb_index > idx_end)
goto out;
idx_start = req->wb_index + 1;
if (nfs_set_page_writeback_locked(req)) {
radix_tree_tag_clear(&nfsi->nfs_page_tree,
req->wb_index, NFS_PAGE_TAG_DIRTY);
nfs_list_remove_request(req);
nfs_list_add_request(req, dst);
res++;
}
}
}
out:
return res;
}
/**
* nfs_scan_list - Scan a list for matching requests
* @head: One of the NFS inode request lists
* @dst: Destination list
* @idx_start: lower bound of page->index to scan
* @npages: idx_start + npages sets the upper bound to scan.
*
* Moves elements from one of the inode request lists.
* If the number of requests is set to 0, the entire address_space
* starting at index idx_start, is scanned.
* The requests are *not* checked to ensure that they form a contiguous set.
* You must be holding the inode's req_lock when calling this function
*/
int
nfs_scan_list(struct list_head *head, struct list_head *dst,
unsigned long idx_start, unsigned int npages)
{
struct list_head *pos, *tmp;
struct
|