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
|
/*
* Copyright 2011 Paul Mackerras, IBM Corp. <paulus@au1.ibm.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.
*/
#include <linux/cpu.h>
#include <linux/kvm_host.h>
#include <linux/preempt.h>
#include <linux/export.h>
#include <linux/sched.h>
#include <linux/spinlock.h>
#include <linux/init.h>
#include <linux/memblock.h>
#include <linux/sizes.h>
#include <linux/cma.h>
#include <linux/bitops.h>
#include <asm/cputable.h>
#include <asm/kvm_ppc.h>
#include <asm/kvm_book3s.h>
#include <asm/archrandom.h>
#include <asm/xics.h>
#include <asm/dbell.h>
#include <asm/cputhreads.h>
#define KVM_CMA_CHUNK_ORDER 18
/*
* Hash page table alignment on newer cpus(CPU_FTR_ARCH_206)
* should be power of 2.
*/
#define HPT_ALIGN_PAGES ((1 << 18) >> PAGE_SHIFT) /* 256k */
/*
* By default we reserve 5% of memory for hash pagetable allocation.
*/
static unsigned long kvm_cma_resv_ratio = 5;
static struct cma *kvm_cma;
static int __init early_parse_kvm_cma_resv(char *p)
{
pr_debug("%s(%s)\n", __func__, p);
if (!p)
return -EINVAL;
return kstrtoul(p, 0, &kvm_cma_resv_ratio);
}
early_param("kvm_cma_resv_ratio", early_parse_kvm_cma_resv);
struct page *kvm_alloc_hpt(unsigned long nr_pages)
{
VM_BUG_ON(order_base_2(nr_pages) < KVM_CMA_CHUNK_ORDER - PAGE_SHIFT);
return cma_alloc(kvm_cma, nr_pages, order_base_2(HPT_ALIGN_PAGES));
}
EXPORT_SYMBOL_GPL(kvm_alloc_hpt);
void kvm_release_hpt(struct page *page, unsigned long nr_pages)
{
cma_release(kvm_cma, page, nr_pages);
}
EXPORT_SYMBOL_GPL(kvm_release_hpt);
/**
* kvm_cma_reserve() - reserve area for kvm hash pagetable
*
* This function reserves memory from early allocator. It should be
* called by arch specific code once the memblock allocator
* has been activated and all other subsystems have already allocated/reserved
* memory.
*/
void __init kvm_cma_reserve(void)
{
unsigned long align_size;
struct memblock_region *reg;
phys_addr_t selected_size = 0;
/*
* We need CMA reservation only when we are in HV mode
*/
if (!cpu_has_feature(CPU_FTR_HVMODE))
return;
/*
* We cannot use memblock_phys_mem_size() here, because
* memblock_analyze() has not been called yet.
*/
for_each_memblock(memory, reg)
selected_size += memblock_region_memory_end_pfn(reg) -
memblock_region_memory_base_pfn(reg);
selected_size = (selected_size * kvm_cma_resv_ratio / 100) << PAGE_SHIFT;
if (selected_size) {
pr_debug("%s: reserving %ld MiB for global area\n", __func__,
(unsigned long)selected_size / SZ_1M);
align_size = HPT_ALIGN_PAGES << PAGE_SHIFT;
cma_declare_contiguous(0, selected_size, 0, align_size,
KVM_CMA_CHUNK_ORDER - PAGE_SHIFT, false, &kvm_cma);
}
}
/*
* Real-mode H_CONFER implementation.
* We check if we are the only vcpu out of this virtual core
* still running in the guest and not ceded. If so, we pop up
* to the virtual-mode implementation; if not, just return to
* the guest.
*/
long int kvmppc_rm_h_confer(struct kvm_vcpu *vcpu, int target,
unsigned int yield_count)
{
struct kvmppc_vcore *vc = vcpu->arch.vcore;
int threads_running;
int threads_ceded;
int threads_conferring;
u64 stop = get_tb() + 10 * tb_ticks_per_usec;
int rv = H_SUCCESS; /* => don't yield */
set_bit(vcpu->arch.ptid, &vc->conferring_threads);
while ((get_tb() < stop) && !VCORE_IS_EXITING(vc)) {
threads_running = VCORE_ENTRY_MAP(vc);
threads_ceded = vc->napping_threads;
threads_conferring = vc->conferring_threads;
if ((threads_ceded | threads_conferring) == threads_running) {
rv = H_TOO_HARD; /* => do yield */
break;
}
}
clear_bit(vcpu->arch.ptid, &vc->conferring_threads);
return rv;
}
/*
* When running HV mode KVM we need to block certain operations while KVM VMs
* exist in the system. We use a counter of VMs to track this.
*
* One of the operations we need to block is onlining of secondaries, so we
* protect hv_vm_count with get/put_online_cpus().
*/
static atomic_t hv_vm_count;
void kvm_hv_vm_activated(void)
{
get_online_cpus();
atomic_inc(&hv_vm_count);
put_online_cpus();
}
EXPORT_SYMBOL_GPL(kvm_hv_vm_activated);
void kvm_hv_vm_deactivated(void)
{
get_online_cpus();
atomic_dec(&hv_vm_count);
put_online_cpus();
}
EXPORT_SYMBOL_GPL(kvm_hv_vm_deactivated);
bool kvm_hv_mode_active(void)
{
return atomic_read(&hv_vm_count) != 0;
}
extern int hcall_real_table[], hcall_real_table_end[];
int kvmppc_hcall_impl_hv_realmode(unsigned long cmd)
{
cmd /= 4;
if (cmd < hcall_real_table_end - hcall_real_table &&
hcall_real_table[cmd])
return 1;
return 0;
}
EXPORT_SYMBOL_GPL(kvmppc_hcall_impl_hv_realmode);
int kvmppc_hwrng_present(void)
{
return powernv_hwrng_present();
}
EXPORT_SYMBOL_GPL(kvmppc_hwrng_present);
long kvmppc_h_random(struct kvm_vcpu *vcpu)
{
if (powernv_get_random_real_mode(&vcpu->arch.gpr[4]))
return H_SUCCESS;
return H_HARDWARE;
}
static inline void rm_writeb(unsigned long paddr, u8 val)
{
__asm__ __volatile__("stbcix %0,0,%1"
: : "r" (val), "r" (paddr) : "memory");
}
/*
* Send an interrupt or message to another CPU.
* This can only be called in real mode.
* The caller needs to include any barrier needed to order writes
* to memory vs. the IPI/message.
*/
void kvmhv_rm_send_ipi(int cpu)
{
unsigned long xics_phys;
/* On POWER8 for IPIs to threads in the same core, use msgsnd */
if (cpu_has_feature(CPU_FTR_ARCH_207S) &&
cpu_first_thread_sibling(cpu) ==
cpu_first_thread_sibling(raw_smp_processor_id())) {
unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
msg |= cpu_thread_in_core(cpu);
__asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg));
return;
}
/* Else poke the target with an IPI */
xics_phys = paca[cpu].kvm_hstate.xics_phys;
rm_writeb(xics_phys + XICS_MFRR, IPI_PRIORITY);
}
/*
* The following functions are called from the assembly code
* in book3s_hv_rmhandlers.S.
*/
static void kvmhv_interrupt_vcore(struct kvmppc_vcore *vc, int active)
{
int cpu = vc->pcpu;
/* Order setting of exit map vs. msgsnd/IPI */
smp_mb();
for (; active; active >>= 1, ++cpu)
if (active & 1)
kvmhv_rm_send_ipi(cpu);
}
void kvmhv_commence_exit(int trap)
{
struct kvmppc_vcore *vc = local_paca->kvm_hstate.kvm_vcore;
int ptid = local_paca->kvm_hstate.ptid;
int me, ee;
/* Set our bit in the threads-exiting-guest map in the 0xff00
bits of vcore->entry_exit_map */
me = 0x100 << ptid;
do {
ee = vc->entry_exit_map;
} while (cmpxchg(&vc->entry_exit_map, ee, ee | me) != ee);
/* Are we the first here? */
if ((ee >> 8) != 0)
return;
/*
* Trigger the other threads in this vcore to exit the guest.
* If this is a hypervisor decrementer interrupt then they
* will be already on their way out of the guest.
*/
if (trap != BOOK3S_INTERRUPT_HV_DECREMENTER)
kvmhv_interrupt_vcore(vc, ee & ~(1 << ptid));
}
|
