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
|
/*
* Copyright (c) 1991, 1993
* The Regents of the University of California. All rights reserved.
*
* This code is derived from software contributed to Berkeley by
* The Mach Operating System project at Carnegie-Mellon University.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 3. All advertising materials mentioning features or use of this software
* must display the following acknowledgement:
* This product includes software developed by the University of
* California, Berkeley and its contributors.
* 4. Neither the name of the University nor the names of its contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*
* from: @(#)vm_pager.c 8.6 (Berkeley) 1/12/94
*
*
* Copyright (c) 1987, 1990 Carnegie-Mellon University.
* All rights reserved.
*
* Authors: Avadis Tevanian, Jr., Michael Wayne Young
*
* Permission to use, copy, modify and distribute this software and
* its documentation is hereby granted, provided that both the copyright
* notice and this permission notice appear in all copies of the
* software, derivative works or modified versions, and any portions
* thereof, and that both notices appear in supporting documentation.
*
* CARNEGIE MELLON ALLOWS FREE USE OF THIS SOFTWARE IN ITS "AS IS"
* CONDITION. CARNEGIE MELLON DISCLAIMS ANY LIABILITY OF ANY KIND
* FOR ANY DAMAGES WHATSOEVER RESULTING FROM THE USE OF THIS SOFTWARE.
*
* Carnegie Mellon requests users of this software to return to
*
* Software Distribution Coordinator or Software.Distribution@CS.CMU.EDU
* School of Computer Science
* Carnegie Mellon University
* Pittsburgh PA 15213-3890
*
* any improvements or extensions that they make and grant Carnegie the
* rights to redistribute these changes.
*/
/*
* Paging space routine stubs. Emulates a matchmaker-like interface
* for builtin pagers.
*/
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/kernel.h>
#include <sys/vnode.h>
#include <sys/bio.h>
#include <sys/buf.h>
#include <sys/ucred.h>
#include <sys/malloc.h>
#include <vm/vm.h>
#include <vm/vm_param.h>
#include <vm/vm_object.h>
#include <vm/vm_page.h>
#include <vm/vm_pager.h>
#include <vm/vm_extern.h>
MALLOC_DEFINE(M_VMPGDATA, "VM pgdata", "XXX: VM pager private data");
int cluster_pbuf_freecnt = -1; /* unlimited to begin with */
static int dead_pager_getpages(vm_object_t, vm_page_t *, int, int);
static vm_object_t dead_pager_alloc(void *, vm_ooffset_t, vm_prot_t,
vm_ooffset_t);
static void dead_pager_putpages(vm_object_t, vm_page_t *, int, int, int *);
static boolean_t dead_pager_haspage(vm_object_t, vm_pindex_t, int *, int *);
static void dead_pager_dealloc(vm_object_t);
static int
dead_pager_getpages(obj, ma, count, req)
vm_object_t obj;
vm_page_t *ma;
int count;
int req;
{
return VM_PAGER_FAIL;
}
static vm_object_t
dead_pager_alloc(handle, size, prot, off)
void *handle;
vm_ooffset_t size;
vm_prot_t prot;
vm_ooffset_t off;
{
return NULL;
}
static void
dead_pager_putpages(object, m, count, flags, rtvals)
vm_object_t object;
vm_page_t *m;
int count;
int flags;
int *rtvals;
{
int i;
for (i = 0; i < count; i++) {
rtvals[i] = VM_PAGER_AGAIN;
}
}
static int
dead_pager_haspage(object, pindex, prev, next)
vm_object_t object;
vm_pindex_t pindex;
int *prev;
int *next;
{
if (prev)
*prev = 0;
if (next)
*next = 0;
return FALSE;
}
static void
dead_pager_dealloc(object)
vm_object_t object;
{
return;
}
static struct pagerops deadpagerops = {
.pgo_alloc = dead_pager_alloc,
.pgo_dealloc = dead_pager_dealloc,
.pgo_getpages = dead_pager_getpages,
.pgo_putpages = dead_pager_putpages,
.pgo_haspage = dead_pager_haspage,
};
struct pagerops *pagertab[] = {
&defaultpagerops, /* OBJT_DEFAULT */
&swappagerops, /* OBJT_SWAP */
&vnodepagerops, /* OBJT_VNODE */
&devicepagerops, /* OBJT_DEVICE */
&physpagerops, /* OBJT_PHYS */
&deadpagerops /* OBJT_DEAD */
};
int npagers = sizeof(pagertab) / sizeof(pagertab[0]);
/*
* Kernel address space for mapping pages.
* Used by pagers where KVAs are needed for IO.
*
* XXX needs to be large enough to support the number of pending async
* cleaning requests (NPENDINGIO == 64) * the maximum swap cluster size
* (MAXPHYS == 64k) if you want to get the most efficiency.
*/
#define PAGER_MAP_SIZE (8 * 1024 * 1024)
int pager_map_size = PAGER_MAP_SIZE;
vm_map_t pager_map;
static int bswneeded;
static vm_offset_t swapbkva; /* swap buffers kva */
struct mtx pbuf_mtx;
static TAILQ_HEAD(swqueue, buf) bswlist;
void
vm_pager_init()
{
struct pagerops **pgops;
TAILQ_INIT(&bswlist);
/*
* Initialize known pagers
*/
for (pgops = pagertab; pgops < &pagertab[npagers]; pgops++)
if (pgops && ((*pgops)->pgo_init != NULL))
(*(*pgops)->pgo_init) ();
}
void
vm_pager_bufferinit()
{
struct buf *bp;
int i;
mtx_init(&pbuf_mtx, "pbuf mutex", NULL, MTX_DEF);
bp = swbuf;
/*
* Now set up swap and physical I/O buffer headers.
*/
for (i = 0; i < nswbuf; i++, bp++) {
TAILQ_INSERT_HEAD(&bswlist, bp, b_freelist);
BUF_LOCKINIT(bp);
LIST_INIT(&bp->b_dep);
bp->b_rcred = bp->b_wcred = NOCRED;
bp->b_xflags = 0;
}
cluster_pbuf_freecnt = nswbuf / 2;
swapbkva = kmem_alloc_nofault(pager_map, nswbuf * MAXPHYS);
if (!swapbkva)
panic("Not enough pager_map VM space for physical buffers");
}
/*
* Allocate an instance of a pager of the given type.
* Size, protection and offset parameters are passed in for pagers that
* need to perform page-level validation (e.g. the device pager).
*/
vm_object_t
vm_pager_allocate(objtype_t type, void *handle, vm_ooffset_t size,
vm_prot_t prot, vm_ooffset_t off)
{
vm_object_t ret;
struct pagerops *ops;
ops = pagertab[type];
if (ops)
ret = (*ops->pgo_alloc) (handle, size, prot, off);
else
ret = NULL;
return (ret);
}
/*
* The object must be locked.
*/
void
vm_pager_deallocate(object)
vm_object_t object;
{
VM_OBJECT_LOCK_ASSERT(object, MA_OWNED);
(*pagertab[object->type]->pgo_dealloc) (object);
}
/*
* vm_pager_get_pages() - inline, see vm/vm_pager.h
* vm_pager_put_pages() - inline, see vm/vm_pager.h
* vm_pager_has_page() - inline, see vm/vm_pager.h
* vm_pager_page_inserted() - inline, see vm/vm_pager.h
* vm_pager_page_removed() - inline, see vm/vm_pager.h
*/
vm_offset_t
vm_pager_map_page(m)
vm_page_t m;
{
vm_offset_t kva;
kva = kmem_alloc_wait(pager_map, PAGE_SIZE);
pmap_qenter(kva, &m, 1);
return (kva);
}
void
vm_pager_unmap_page(kva)
vm_offset_t kva;
{
pmap_qremove(kva, 1);
kmem_free_wakeup(pager_map, kva, PAGE_SIZE);
}
vm_object_t
vm_pager_object_lookup(pg_list, handle)
struct pagerlst *pg_list;
void *handle;
{
vm_object_t object;
TAILQ_FOREACH(object, pg_list, pager_object_list)
if (object->handle == handle)
return (object);
return (NULL);
}
/*
* initialize a physical buffer
*/
/*
* XXX This probably belongs in vfs_bio.c
*/
static void
initpbuf(struct buf *bp)
{
bp->b_rcred = NOCRED;
bp->b_wcred = NOCRED;
bp->b_qindex = 0; /* On no queue (QUEUE_NONE) */
bp->b_saveaddr = (caddr_t) (MAXPHYS * (bp - swbuf)) + swapbkva;
bp->b_data = bp->b_saveaddr;
bp->b_kvabase = bp->b_saveaddr;
bp->b_kvasize = MAXPHYS;
bp->b_xflags = 0;
bp->b_flags = 0;
bp->b_ioflags = 0;
bp->b_iodone = NULL;
bp->b_error = 0;
bp->b_magic = B_MAGIC_BIO;
bp->b_op = &buf_ops_bio;
BUF_LOCK(bp, LK_EXCLUSIVE, NULL);
}
/*
* allocate a physical buffer
*
* There are a limited number (nswbuf) of physical buffers. We need
* to make sure that no single subsystem is able to hog all of them,
* so each subsystem implements a counter which is typically initialized
* to 1/2 nswbuf. getpbuf() decrements this counter in allocation and
* increments it on release, and blocks if the counter hits zero. A
* subsystem may initialize the counter to -1 to disable the feature,
* but it must still be sure to match up all uses of getpbuf() with
* relpbuf() using the same variable.
*
* NOTE: pfreecnt can be NULL, but this 'feature' will be removed
* relatively soon when the rest of the subsystems get smart about it. XXX
*/
struct buf *
getpbuf(pfreecnt)
int *pfreecnt;
{
int s;
struct buf *bp;
s = splvm();
mtx_lock(&pbuf_mtx);
for (;;) {
if (pfreecnt) {
while (*pfreecnt == 0) {
msleep(pfreecnt, &pbuf_mtx, PVM, "wswbuf0", 0);
}
}
/* get a bp from the swap buffer header pool */
if ((bp = TAILQ_FIRST(&bswlist)) != NULL)
break;
bswneeded = 1;
msleep(&bswneeded, &pbuf_mtx, PVM, "wswbuf1", 0);
/* loop in case someone else grabbed one */
}
TAILQ_REMOVE(&bswlist, bp, b_freelist);
if (pfreecnt)
--*pfreecnt;
mtx_unlock(&pbuf_mtx);
splx(s);
initpbuf(bp);
return bp;
}
/*
* allocate a physical buffer, if one is available.
*
* Note that there is no NULL hack here - all subsystems using this
* call understand how to use pfreecnt.
*/
struct buf *
trypbuf(pfreecnt)
int *pfreecnt;
{
int s;
struct buf *bp;
s = splvm();
mtx_lock(&pbuf_mtx);
if (*pfreecnt == 0 || (bp = TAILQ_FIRST(&bswlist)) == NULL) {
mtx_unlock(&pbuf_mtx);
splx(s);
return NULL;
}
TAILQ_REMOVE(&bswlist, bp, b_freelist);
--*pfreecnt;
mtx_unlock(&pbuf_mtx);
splx(s);
initpbuf(bp);
return bp;
}
/*
* release a physical buffer
*
* NOTE: pfreecnt can be NULL, but this 'feature' will be removed
* relatively soon when the rest of the subsystems get smart about it. XXX
*/
void
relpbuf(bp, pfreecnt)
struct buf *bp;
int *pfreecnt;
{
int s;
s = splvm();
if (bp->b_rcred != NOCRED) {
crfree(bp->b_rcred);
bp->b_rcred = NOCRED;
}
if (bp->b_wcred != NOCRED) {
crfree(bp->b_wcred);
bp->b_wcred = NOCRED;
}
if (bp->b_vp)
pbrelvp(bp);
BUF_UNLOCK(bp);
mtx_lock(&pbuf_mtx);
TAILQ_INSERT_HEAD(&bswlist, bp, b_freelist);
if (bswneeded) {
bswneeded = 0;
wakeup(&bswneeded);
}
if (pfreecnt) {
if (++*pfreecnt == 1)
wakeup(pfreecnt);
}
mtx_unlock(&pbuf_mtx);
splx(s);
}
|