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
|
/*
* Copyright (c) 1982, 1986, 1989, 1993
* The Regents of the University of California. All rights reserved.
*
* 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.
*
* @(#)vm_swap.c 8.5 (Berkeley) 2/17/94
* $FreeBSD$
*/
#include "opt_swap.h"
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/sysproto.h>
#include <sys/buf.h>
#include <sys/proc.h>
#include <sys/namei.h>
#include <sys/dmap.h> /* XXX */
#include <sys/vnode.h>
#include <sys/fcntl.h>
#include <sys/blist.h>
#include <sys/kernel.h>
#include <sys/lock.h>
#include <sys/conf.h>
#include <sys/stat.h>
#include <vm/vm.h>
#include <vm/vm_extern.h>
#include <vm/swap_pager.h>
#include <vm/vm_zone.h>
/*
* Indirect driver for multi-controller paging.
*/
#ifndef NSWAPDEV
#define NSWAPDEV 4
#endif
static struct swdevt should_be_malloced[NSWAPDEV];
static struct swdevt *swdevt = should_be_malloced;
static int nswap; /* first block after the interleaved devs */
static int nswdev = NSWAPDEV;
int vm_swap_size;
static int swapdev_strategy __P((struct vop_strategy_args *ap));
struct vnode *swapdev_vp;
/*
* swapdev_strategy:
*
* VOP_STRATEGY() for swapdev_vp.
* Perform swap strategy interleave device selection.
*
* The bp is expected to be locked and *not* B_DONE on call.
*/
static int
swapdev_strategy(ap)
struct vop_strategy_args /* {
struct vnode *a_vp;
struct buf *a_bp;
} */ *ap;
{
int s, sz, off, seg, index;
register struct swdevt *sp;
struct vnode *vp;
struct buf *bp;
bp = ap->a_bp;
sz = howmany(bp->b_bcount, PAGE_SIZE);
/*
* Convert interleaved swap into per-device swap. Note that
* the block size is left in PAGE_SIZE'd chunks (for the newswap)
* here.
*/
if (nswdev > 1) {
off = bp->b_blkno % dmmax;
if (off + sz > dmmax) {
bp->b_error = EINVAL;
bp->b_flags |= B_ERROR;
biodone(bp);
return 0;
}
seg = bp->b_blkno / dmmax;
index = seg % nswdev;
seg /= nswdev;
bp->b_blkno = seg * dmmax + off;
} else {
index = 0;
}
sp = &swdevt[index];
if (bp->b_blkno + sz > sp->sw_nblks) {
bp->b_error = EINVAL;
bp->b_flags |= B_ERROR;
biodone(bp);
return 0;
}
bp->b_dev = sp->sw_device;
if (sp->sw_vp == NULL) {
bp->b_error = ENODEV;
bp->b_flags |= B_ERROR;
biodone(bp);
return 0;
}
/*
* Convert from PAGE_SIZE'd to DEV_BSIZE'd chunks for the actual I/O
*/
bp->b_blkno = ctodb(bp->b_blkno);
vhold(sp->sw_vp);
s = splvm();
if ((bp->b_flags & B_READ) == 0) {
vp = bp->b_vp;
if (vp) {
vp->v_numoutput--;
if ((vp->v_flag & VBWAIT) && vp->v_numoutput <= 0) {
vp->v_flag &= ~VBWAIT;
wakeup(&vp->v_numoutput);
}
}
sp->sw_vp->v_numoutput++;
}
pbreassignbuf(bp, sp->sw_vp);
splx(s);
VOP_STRATEGY(bp->b_vp, bp);
return 0;
}
/*
* Create a special vnode op vector for swapdev_vp - we only use
* VOP_STRATEGY(), everything else returns an error.
*/
vop_t **swapdev_vnodeop_p;
static struct vnodeopv_entry_desc swapdev_vnodeop_entries[] = {
{ &vop_default_desc, (vop_t *) vop_defaultop },
{ &vop_strategy_desc, (vop_t *) swapdev_strategy },
{ NULL, NULL }
};
static struct vnodeopv_desc swapdev_vnodeop_opv_desc =
{ &swapdev_vnodeop_p, swapdev_vnodeop_entries };
VNODEOP_SET(swapdev_vnodeop_opv_desc);
/*
* System call swapon(name) enables swapping on device name,
* which must be in the swdevsw. Return EBUSY
* if already swapping on this device.
*/
#ifndef _SYS_SYSPROTO_H_
struct swapon_args {
char *name;
};
#endif
/* ARGSUSED */
int
swapon(p, uap)
struct proc *p;
struct swapon_args *uap;
{
register struct vnode *vp;
struct nameidata nd;
int error;
error = suser(p);
if (error)
return (error);
NDINIT(&nd, LOOKUP, FOLLOW, UIO_USERSPACE, uap->name, p);
error = namei(&nd);
if (error)
return (error);
NDFREE(&nd, NDF_ONLY_PNBUF);
vp = nd.ni_vp;
vn_isdisk(vp, &error);
if (!error)
error = swaponvp(p, vp, vp->v_rdev, 0);
if (error)
vrele(vp);
return (error);
}
/*
* Swfree(index) frees the index'th portion of the swap map.
* Each of the nswdev devices provides 1/nswdev'th of the swap
* space, which is laid out with blocks of dmmax pages circularly
* among the devices.
*
* The new swap code uses page-sized blocks. The old swap code used
* DEV_BSIZE'd chunks.
*
* XXX locking when multiple swapon's run in parallel
*/
int
swaponvp(p, vp, dev, nblks)
struct proc *p;
struct vnode *vp;
dev_t dev;
u_long nblks;
{
int index;
register struct swdevt *sp;
register swblk_t vsbase;
register long blk;
swblk_t dvbase;
int error;
if (!swapdev_vp) {
error = getnewvnode(VT_NON, NULL, swapdev_vnodeop_p,
&swapdev_vp);
if (error)
panic("Cannot get vnode for swapdev");
swapdev_vp->v_type = VNON; /* Untyped */
}
ASSERT_VOP_UNLOCKED(vp, "swaponvp");
for (sp = swdevt, index = 0 ; index < nswdev; index++, sp++) {
if (sp->sw_vp == vp)
return EBUSY;
if (!sp->sw_vp)
goto found;
}
return EINVAL;
found:
(void) vn_lock(vp, LK_EXCLUSIVE | LK_RETRY, p);
error = VOP_OPEN(vp, FREAD | FWRITE, p->p_ucred, p);
(void) VOP_UNLOCK(vp, 0, p);
if (error)
return (error);
if (nblks == 0 && dev != NODEV && (devsw(dev)->d_psize == 0 ||
(nblks = (*devsw(dev)->d_psize) (dev)) == -1)) {
(void) VOP_CLOSE(vp, FREAD | FWRITE, p->p_ucred, p);
return (ENXIO);
}
if (nblks == 0) {
(void) VOP_CLOSE(vp, FREAD | FWRITE, p->p_ucred, p);
return (ENXIO);
}
/*
* nblks is in DEV_BSIZE'd chunks, convert to PAGE_SIZE'd chunks.
* First chop nblks off to page-align it, then convert.
*
* sw->sw_nblks is in page-sized chunks now too.
*/
nblks &= ~(ctodb(1) - 1);
nblks = dbtoc(nblks);
sp->sw_vp = vp;
sp->sw_dev = dev2udev(dev);
sp->sw_device = dev;
sp->sw_flags |= SW_FREED;
sp->sw_nblks = nblks;
/*
* nblks, nswap, and dmmax are PAGE_SIZE'd parameters now, not
* DEV_BSIZE'd.
*/
if (nblks * nswdev > nswap)
nswap = (nblks+1) * nswdev;
if (swapblist == NULL)
swapblist = blist_create(nswap);
else
blist_resize(&swapblist, nswap, 0);
for (dvbase = dmmax; dvbase < nblks; dvbase += dmmax) {
blk = min(nblks - dvbase, dmmax);
vsbase = index * dmmax + dvbase * nswdev;
blist_free(swapblist, vsbase, blk);
vm_swap_size += blk;
}
return (0);
}
|