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
|
/*-
* Copyright (c) 1994 John Dyson
* Copyright (c) 2001 Matt Dillon
*
* 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.
* 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 AUTHOR ``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 AUTHOR 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_machdep.c 7.3 (Berkeley) 5/13/91
* Utah $Hdr: vm_machdep.c 1.16.1.1 89/06/23$
* from: FreeBSD: .../i386/vm_machdep.c,v 1.165 2001/07/04 23:27:04 dillon
*/
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
#include <opt_sched.h>
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/kernel.h>
#include <sys/proc.h>
#include <sys/vmmeter.h>
#include <sys/lock.h>
#include <sys/mutex.h>
#include <sys/sched.h>
#include <sys/sysctl.h>
#include <sys/kthread.h>
#include <sys/unistd.h>
#include <vm/vm.h>
#include <vm/vm_page.h>
static int cnt_prezero;
SYSCTL_INT(_vm_stats_misc, OID_AUTO, cnt_prezero, CTLFLAG_RD,
&cnt_prezero, 0, "");
static int idlezero_enable_default = 1;
TUNABLE_INT("vm.idlezero_enable", &idlezero_enable_default);
/* Defer setting the enable flag until the kthread is running. */
static int idlezero_enable = 0;
SYSCTL_INT(_vm, OID_AUTO, idlezero_enable, CTLFLAG_RW, &idlezero_enable, 0, "");
static int idlezero_maxrun = 16;
SYSCTL_INT(_vm, OID_AUTO, idlezero_maxrun, CTLFLAG_RW, &idlezero_maxrun, 0, "");
TUNABLE_INT("vm.idlezero_maxrun", &idlezero_maxrun);
/*
* Implement the pre-zeroed page mechanism.
*/
#define ZIDLE_LO(v) ((v) * 2 / 3)
#define ZIDLE_HI(v) ((v) * 4 / 5)
static boolean_t wakeup_needed = FALSE;
static int zero_state;
static int
vm_page_zero_check(void)
{
if (!idlezero_enable)
return (0);
/*
* Attempt to maintain approximately 1/2 of our free pages in a
* PG_ZERO'd state. Add some hysteresis to (attempt to) avoid
* generally zeroing a page when the system is near steady-state.
* Otherwise we might get 'flutter' during disk I/O / IPC or
* fast sleeps. We also do not want to be continuously zeroing
* pages because doing so may flush our L1 and L2 caches too much.
*/
if (zero_state && vm_page_zero_count >= ZIDLE_LO(cnt.v_free_count))
return (0);
if (vm_page_zero_count >= ZIDLE_HI(cnt.v_free_count))
return (0);
return (1);
}
static void
vm_page_zero_idle(void)
{
static int free_rover;
vm_page_t m;
mtx_lock(&vm_page_queue_free_mtx);
zero_state = 0;
m = vm_pageq_find(PQ_FREE, free_rover, FALSE);
if (m != NULL && (m->flags & PG_ZERO) == 0) {
vm_pageq_remove_nowakeup(m);
mtx_unlock(&vm_page_queue_free_mtx);
pmap_zero_page_idle(m);
mtx_lock(&vm_page_queue_free_mtx);
m->flags |= PG_ZERO;
vm_pageq_enqueue(PQ_FREE + m->pc, m);
++vm_page_zero_count;
++cnt_prezero;
if (vm_page_zero_count >= ZIDLE_HI(cnt.v_free_count))
zero_state = 1;
}
free_rover = (free_rover + PQ_PRIME2) & PQ_COLORMASK;
mtx_unlock(&vm_page_queue_free_mtx);
}
/* Called by vm_page_free to hint that a new page is available. */
void
vm_page_zero_idle_wakeup(void)
{
mtx_assert(&vm_page_queue_mtx, MA_OWNED);
if (wakeup_needed && vm_page_zero_check()) {
wakeup_needed = FALSE;
wakeup(&zero_state);
}
}
static void
vm_pagezero(void __unused *arg)
{
idlezero_enable = idlezero_enable_default;
for (;;) {
if (vm_page_zero_check()) {
vm_page_zero_idle();
#ifndef PREEMPTION
if (sched_runnable()) {
mtx_lock_spin(&sched_lock);
mi_switch(SW_VOL, NULL);
mtx_unlock_spin(&sched_lock);
}
#endif
} else {
vm_page_lock_queues();
wakeup_needed = TRUE;
msleep(&zero_state, &vm_page_queue_mtx,
PDROP, "pgzero", hz * 300);
}
}
}
static struct proc *pagezero_proc;
static void
pagezero_start(void __unused *arg)
{
int error;
struct thread *td;
error = kthread_create(vm_pagezero, NULL, &pagezero_proc, RFSTOPPED, 0,
"pagezero");
if (error)
panic("pagezero_start: error %d\n", error);
/*
* We're an idle task, don't count us in the load.
*/
PROC_LOCK(pagezero_proc);
pagezero_proc->p_flag |= P_NOLOAD;
PROC_UNLOCK(pagezero_proc);
mtx_lock_spin(&sched_lock);
td = FIRST_THREAD_IN_PROC(pagezero_proc);
sched_class(td, PRI_IDLE);
sched_prio(td, PRI_MAX_IDLE);
sched_add(td, SRQ_BORING);
mtx_unlock_spin(&sched_lock);
}
SYSINIT(pagezero, SI_SUB_KTHREAD_VM, SI_ORDER_ANY, pagezero_start, NULL)
|