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
|
// SPDX-License-Identifier: GPL-2.0
/*
* Hyper-V specific APIC code.
*
* Copyright (C) 2018, Microsoft, Inc.
*
* Author : K. Y. Srinivasan <kys@microsoft.com>
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published
* by the Free Software Foundation.
*
* 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, GOOD TITLE or
* NON INFRINGEMENT. See the GNU General Public License for more
* details.
*
*/
#include <linux/types.h>
#include <linux/vmalloc.h>
#include <linux/mm.h>
#include <linux/clockchips.h>
#include <linux/hyperv.h>
#include <linux/slab.h>
#include <linux/cpuhotplug.h>
#include <asm/hypervisor.h>
#include <asm/mshyperv.h>
#include <asm/apic.h>
#include <asm/trace/hyperv.h>
static struct apic orig_apic;
static u64 hv_apic_icr_read(void)
{
u64 reg_val;
rdmsrl(HV_X64_MSR_ICR, reg_val);
return reg_val;
}
static void hv_apic_icr_write(u32 low, u32 id)
{
u64 reg_val;
reg_val = SET_APIC_DEST_FIELD(id);
reg_val = reg_val << 32;
reg_val |= low;
wrmsrl(HV_X64_MSR_ICR, reg_val);
}
static u32 hv_apic_read(u32 reg)
{
u32 reg_val, hi;
switch (reg) {
case APIC_EOI:
rdmsr(HV_X64_MSR_EOI, reg_val, hi);
(void)hi;
return reg_val;
case APIC_TASKPRI:
rdmsr(HV_X64_MSR_TPR, reg_val, hi);
(void)hi;
return reg_val;
default:
return native_apic_mem_read(reg);
}
}
static void hv_apic_write(u32 reg, u32 val)
{
switch (reg) {
case APIC_EOI:
wrmsr(HV_X64_MSR_EOI, val, 0);
break;
case APIC_TASKPRI:
wrmsr(HV_X64_MSR_TPR, val, 0);
break;
default:
native_apic_mem_write(reg, val);
}
}
static void hv_apic_eoi_write(u32 reg, u32 val)
{
struct hv_vp_assist_page *hvp = hv_vp_assist_page[smp_processor_id()];
if (hvp && (xchg(&hvp->apic_assist, 0) & 0x1))
return;
wrmsr(HV_X64_MSR_EOI, val, 0);
}
/*
* IPI implementation on Hyper-V.
*/
static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector,
bool exclude_self)
{
struct hv_send_ipi_ex **arg;
struct hv_send_ipi_ex *ipi_arg;
unsigned long flags;
int nr_bank = 0;
u64 status = HV_STATUS_INVALID_PARAMETER;
if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED))
return false;
local_irq_save(flags);
arg = (struct hv_send_ipi_ex **)this_cpu_ptr(hyperv_pcpu_input_arg);
ipi_arg = *arg;
if (unlikely(!ipi_arg))
goto ipi_mask_ex_done;
ipi_arg->vector = vector;
ipi_arg->reserved = 0;
ipi_arg->vp_set.valid_bank_mask = 0;
if (!cpumask_equal(mask, cpu_present_mask)) {
ipi_arg->vp_set.format = HV_GENERIC_SET_SPARSE_4K;
if (exclude_self)
nr_bank = cpumask_to_vpset_noself(&(ipi_arg->vp_set), mask);
else
nr_bank = cpumask_to_vpset(&(ipi_arg->vp_set), mask);
}
if (nr_bank < 0)
goto ipi_mask_ex_done;
if (!nr_bank)
ipi_arg->vp_set.format = HV_GENERIC_SET_ALL;
status = hv_do_rep_hypercall(HVCALL_SEND_IPI_EX, 0, nr_bank,
ipi_arg, NULL);
ipi_mask_ex_done:
local_irq_restore(flags);
return hv_result_success(status);
}
static bool __send_ipi_mask(const struct cpumask *mask, int vector,
bool exclude_self)
{
int cur_cpu, vcpu, this_cpu = smp_processor_id();
struct hv_send_ipi ipi_arg;
u64 status;
unsigned int weight;
trace_hyperv_send_ipi_mask(mask, vector);
weight = cpumask_weight(mask);
/*
* Do nothing if
* 1. the mask is empty
* 2. the mask only contains self when exclude_self is true
*/
if (weight == 0 ||
(exclude_self && weight == 1 && cpumask_test_cpu(this_cpu, mask)))
return true;
if (!hv_hypercall_pg)
return false;
if ((vector < HV_IPI_LOW_VECTOR) || (vector > HV_IPI_HIGH_VECTOR))
return false;
/*
* From the supplied CPU set we need to figure out if we can get away
* with cheaper HVCALL_SEND_IPI hypercall. This is possible when the
* highest VP number in the set is < 64. As VP numbers are usually in
* ascending order and match Linux CPU ids, here is an optimization:
* we check the VP number for the highest bit in the supplied set first
* so we can quickly find out if using HVCALL_SEND_IPI_EX hypercall is
* a must. We will also check all VP numbers when walking the supplied
* CPU set to remain correct in all cases.
*/
if (hv_cpu_number_to_vp_number(cpumask_last(mask)) >= 64)
goto do_ex_hypercall;
ipi_arg.vector = vector;
ipi_arg.cpu_mask = 0;
for_each_cpu(cur_cpu, mask) {
if (exclude_self && cur_cpu == this_cpu)
continue;
vcpu = hv_cpu_number_to_vp_number(cur_cpu);
if (vcpu == VP_INVAL)
return false;
/*
* This particular version of the IPI hypercall can
* only target upto 64 CPUs.
*/
if (vcpu >= 64)
goto do_ex_hypercall;
__set_bit(vcpu, (unsigned long *)&ipi_arg.cpu_mask);
}
status = hv_do_fast_hypercall16(HVCALL_SEND_IPI, ipi_arg.vector,
ipi_arg.cpu_mask);
return hv_result_success(status);
do_ex_hypercall:
return __send_ipi_mask_ex(mask, vector, exclude_self);
}
static bool __send_ipi_one(int cpu, int vector)
{
int vp = hv_cpu_number_to_vp_number(cpu);
u64 status;
trace_hyperv_send_ipi_one(cpu, vector);
if (!hv_hypercall_pg || (vp == VP_INVAL))
return false;
if ((vector < HV_IPI_LOW_VECTOR) || (vector > HV_IPI_HIGH_VECTOR))
return false;
if (vp >= 64)
return __send_ipi_mask_ex(cpumask_of(cpu), vector, false);
status = hv_do_fast_hypercall16(HVCALL_SEND_IPI, vector, BIT_ULL(vp));
return hv_result_success(status);
}
static void hv_send_ipi(int cpu, int vector)
{
if (!__send_ipi_one(cpu, vector))
orig_apic.send_IPI(cpu, vector);
}
static void hv_send_ipi_mask(const struct cpumask *mask, int vector)
{
if (!__send_ipi_mask(mask, vector, false))
orig_apic.send_IPI_mask(mask, vector);
}
static void hv_send_ipi_mask_allbutself(const struct cpumask *mask, int vector)
{
if (!__send_ipi_mask(mask, vector, true))
orig_apic.send_IPI_mask_allbutself(mask, vector);
}
static void hv_send_ipi_allbutself(int vector)
{
hv_send_ipi_mask_allbutself(cpu_online_mask, vector);
}
static void hv_send_ipi_all(int vector)
{
if (!__send_ipi_mask(cpu_online_mask, vector, false))
orig_apic.send_IPI_all(vector);
}
static void hv_send_ipi_self(int vector)
{
if (!__send_ipi_one(smp_processor_id(), vector))
orig_apic.send_IPI_self(vector);
}
void __init hv_apic_init(void)
{
if (ms_hyperv.hints & HV_X64_CLUSTER_IPI_RECOMMENDED) {
pr_info("Hyper-V: Using IPI hypercalls\n");
/*
* Set the IPI entry points.
*/
orig_apic = *apic;
apic->send_IPI = hv_send_ipi;
apic->send_IPI_mask = hv_send_ipi_mask;
apic->send_IPI_mask_allbutself = hv_send_ipi_mask_allbutself;
apic->send_IPI_allbutself = hv_send_ipi_allbutself;
apic->send_IPI_all = hv_send_ipi_all;
apic->send_IPI_self = hv_send_ipi_self;
}
if (ms_hyperv.hints & HV_X64_APIC_ACCESS_RECOMMENDED) {
pr_info("Hyper-V: Using enlightened APIC (%s mode)",
x2apic_enabled() ? "x2apic" : "xapic");
/*
* When in x2apic mode, don't use the Hyper-V specific APIC
* accessors since the field layout in the ICR register is
* different in x2apic mode. Furthermore, the architectural
* x2apic MSRs function just as well as the Hyper-V
* synthetic APIC MSRs, so there's no benefit in having
* separate Hyper-V accessors for x2apic mode. The only
* exception is hv_apic_eoi_write, because it benefits from
* lazy EOI when available, but the same accessor works for
* both xapic and x2apic because the field layout is the same.
*/
apic_set_eoi_write(hv_apic_eoi_write);
if (!x2apic_enabled()) {
apic->read = hv_apic_read;
apic->write = hv_apic_write;
apic->icr_write = hv_apic_icr_write;
apic->icr_read = hv_apic_icr_read;
}
}
}
|