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
|
/******************************************************************************
* wait.c
*
* Sleep in hypervisor context for some event to occur.
*
* Copyright (c) 2010, Keir Fraser <keir@xen.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
#include <xen/config.h>
#include <xen/sched.h>
#include <xen/wait.h>
#include <xen/errno.h>
struct waitqueue_vcpu {
struct list_head list;
struct vcpu *vcpu;
#ifdef CONFIG_X86
/*
* Xen/x86 does not have per-vcpu hypervisor stacks. So we must save the
* hypervisor context before sleeping (descheduling), setjmp/longjmp-style.
*/
void *esp;
char *stack;
cpumask_t saved_affinity;
unsigned int wakeup_cpu;
#endif
};
int init_waitqueue_vcpu(struct vcpu *v)
{
struct waitqueue_vcpu *wqv;
wqv = xzalloc(struct waitqueue_vcpu);
if ( wqv == NULL )
return -ENOMEM;
#ifdef CONFIG_X86
wqv->stack = alloc_xenheap_page();
if ( wqv->stack == NULL )
{
xfree(wqv);
return -ENOMEM;
}
#endif
INIT_LIST_HEAD(&wqv->list);
wqv->vcpu = v;
v->waitqueue_vcpu = wqv;
return 0;
}
void destroy_waitqueue_vcpu(struct vcpu *v)
{
struct waitqueue_vcpu *wqv;
wqv = v->waitqueue_vcpu;
if ( wqv == NULL )
return;
BUG_ON(!list_empty(&wqv->list));
#ifdef CONFIG_X86
free_xenheap_page(wqv->stack);
#endif
xfree(wqv);
v->waitqueue_vcpu = NULL;
}
void init_waitqueue_head(struct waitqueue_head *wq)
{
spin_lock_init(&wq->lock);
INIT_LIST_HEAD(&wq->list);
}
void destroy_waitqueue_head(struct waitqueue_head *wq)
{
wake_up_all(wq);
}
void wake_up_nr(struct waitqueue_head *wq, unsigned int nr)
{
struct waitqueue_vcpu *wqv;
spin_lock(&wq->lock);
while ( !list_empty(&wq->list) && nr-- )
{
wqv = list_entry(wq->list.next, struct waitqueue_vcpu, list);
list_del_init(&wqv->list);
vcpu_unpause(wqv->vcpu);
put_domain(wqv->vcpu->domain);
}
spin_unlock(&wq->lock);
}
void wake_up_one(struct waitqueue_head *wq)
{
wake_up_nr(wq, 1);
}
void wake_up_all(struct waitqueue_head *wq)
{
wake_up_nr(wq, UINT_MAX);
}
#ifdef CONFIG_X86
static void __prepare_to_wait(struct waitqueue_vcpu *wqv)
{
struct cpu_info *cpu_info = get_cpu_info();
struct vcpu *curr = current;
unsigned long dummy;
u32 entry_vector = cpu_info->guest_cpu_user_regs.entry_vector;
cpu_info->guest_cpu_user_regs.entry_vector &= ~TRAP_regs_partial;
ASSERT(wqv->esp == 0);
/* Save current VCPU affinity; force wakeup on *this* CPU only. */
wqv->wakeup_cpu = smp_processor_id();
cpumask_copy(&wqv->saved_affinity, curr->cpu_affinity);
if ( vcpu_set_affinity(curr, cpumask_of(wqv->wakeup_cpu)) )
{
gdprintk(XENLOG_ERR, "Unable to set vcpu affinity\n");
domain_crash_synchronous();
}
asm volatile (
"push %%rax; push %%rbx; push %%rdx; "
"push %%rbp; push %%r8; push %%r9; push %%r10; push %%r11; "
"push %%r12; push %%r13; push %%r14; push %%r15; call 1f; "
"1: addq $2f-1b,(%%rsp); sub %%esp,%%ecx; cmp %3,%%ecx; ja 3f; "
"mov %%rsp,%%rsi; 2: rep movsb; mov %%rsp,%%rsi; 3: pop %%rax; "
"pop %%r15; pop %%r14; pop %%r13; pop %%r12; "
"pop %%r11; pop %%r10; pop %%r9; pop %%r8; "
"pop %%rbp; pop %%rdx; pop %%rbx; pop %%rax"
: "=&S" (wqv->esp), "=&c" (dummy), "=&D" (dummy)
: "i" (PAGE_SIZE), "0" (0), "1" (cpu_info), "2" (wqv->stack)
: "memory" );
if ( unlikely(wqv->esp == 0) )
{
gdprintk(XENLOG_ERR, "Stack too large in %s\n", __FUNCTION__);
domain_crash_synchronous();
}
cpu_info->guest_cpu_user_regs.entry_vector = entry_vector;
}
static void __finish_wait(struct waitqueue_vcpu *wqv)
{
wqv->esp = NULL;
(void)vcpu_set_affinity(current, &wqv->saved_affinity);
}
void check_wakeup_from_wait(void)
{
struct waitqueue_vcpu *wqv = current->waitqueue_vcpu;
ASSERT(list_empty(&wqv->list));
if ( likely(wqv->esp == NULL) )
return;
/* Check if we woke up on the wrong CPU. */
if ( unlikely(smp_processor_id() != wqv->wakeup_cpu) )
{
/* Re-set VCPU affinity and re-enter the scheduler. */
struct vcpu *curr = current;
cpumask_copy(&wqv->saved_affinity, curr->cpu_affinity);
if ( vcpu_set_affinity(curr, cpumask_of(wqv->wakeup_cpu)) )
{
gdprintk(XENLOG_ERR, "Unable to set vcpu affinity\n");
domain_crash_synchronous();
}
wait(); /* takes us back into the scheduler */
}
asm volatile (
"mov %1,%%"__OP"sp; jmp *(%0)"
: : "S" (wqv->stack), "D" (wqv->esp),
"c" ((char *)get_cpu_info() - (char *)wqv->esp)
: "memory" );
}
#else /* !CONFIG_X86 */
#define __prepare_to_wait(wqv) ((void)0)
#define __finish_wait(wqv) ((void)0)
#endif
void prepare_to_wait(struct waitqueue_head *wq)
{
struct vcpu *curr = current;
struct waitqueue_vcpu *wqv = curr->waitqueue_vcpu;
ASSERT_NOT_IN_ATOMIC();
__prepare_to_wait(wqv);
ASSERT(list_empty(&wqv->list));
spin_lock(&wq->lock);
list_add_tail(&wqv->list, &wq->list);
vcpu_pause_nosync(curr);
get_knownalive_domain(curr->domain);
spin_unlock(&wq->lock);
}
void finish_wait(struct waitqueue_head *wq)
{
struct vcpu *curr = current;
struct waitqueue_vcpu *wqv = curr->waitqueue_vcpu;
__finish_wait(wqv);
if ( list_empty(&wqv->list) )
return;
spin_lock(&wq->lock);
if ( !list_empty(&wqv->list) )
{
list_del_init(&wqv->list);
vcpu_unpause(curr);
put_domain(curr->domain);
}
spin_unlock(&wq->lock);
}
|
