summaryrefslogtreecommitdiffstats
path: root/arch/powerpc/kvm/book3s_hv_builtin.c
blob: b9615ba5b083a6ddeea76b878925396561b5fb42 (plain)
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
/*
 * 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/bootmem.h>
#include <linux/init.h>
#include <linux/memblock.h>
#include <linux/sizes.h>
#include <linux/cma.h>

#include <asm/cputable.h>
#include <asm/kvm_ppc.h>
#include <asm/kvm_book3s.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;
/*
 * We allocate RMAs (real mode areas) for KVM guests from the KVM CMA area.
 * Each RMA has to be physically contiguous and of a size that the
 * hardware supports.  PPC970 and POWER7 support 64MB, 128MB and 256MB,
 * and other larger sizes.  Since we are unlikely to be allocate that
 * much physically contiguous memory after the system is up and running,
 * we preallocate a set of RMAs in early boot using CMA.
 * should be power of 2.
 */
unsigned long kvm_rma_pages = (1 << 27) >> PAGE_SHIFT;	/* 128MB */
EXPORT_SYMBOL_GPL(kvm_rma_pages);

static struct cma *kvm_cma;

/* Work out RMLS (real mode limit selector) field value for a given RMA size.
   Assumes POWER7 or PPC970. */
static inline int lpcr_rmls(unsigned long rma_size)
{
	switch (rma_size) {
	case 32ul << 20:	/* 32 MB */
		if (cpu_has_feature(CPU_FTR_ARCH_206))
			return 8;	/* only supported on POWER7 */
		return -1;
	case 64ul << 20:	/* 64 MB */
		return 3;
	case 128ul << 20:	/* 128 MB */
		return 7;
	case 256ul << 20:	/* 256 MB */
		return 4;
	case 1ul << 30:		/* 1 GB */
		return 2;
	case 16ul << 30:	/* 16 GB */
		return 1;
	case 256ul << 30:	/* 256 GB */
		return 0;
	default:
		return -1;
	}
}

static int __init early_parse_rma_size(char *p)
{
	unsigned long kvm_rma_size;

	pr_debug("%s(%s)\n", __func__, p);
	if (!p)
		return -EINVAL;
	kvm_rma_size = memparse(p, &p);
	/*
	 * Check that the requested size is one supported in hardware
	 */
	if (lpcr_rmls(kvm_rma_size) < 0) {
		pr_err("RMA size of 0x%lx not supported\n", kvm_rma_size);
		return -EINVAL;
	}
	kvm_rma_pages = kvm_rma_size >> PAGE_SHIFT;
	return 0;
}
early_param("kvm_rma_size", early_parse_rma_size);

struct kvm_rma_info *kvm_alloc_rma()
{
	struct page *page;
	struct kvm_rma_info *ri;

	ri = kmalloc(sizeof(struct kvm_rma_info), GFP_KERNEL);
	if (!ri)
		return NULL;
	page = cma_alloc(kvm_cma, kvm_rma_pages, order_base_2(kvm_rma_pages));
	if (!page)
		goto err_out;
	atomic_set(&ri->use_count, 1);
	ri->base_pfn = page_to_pfn(page);
	return ri;
err_out:
	kfree(ri);
	return NULL;
}
EXPORT_SYMBOL_GPL(kvm_alloc_rma);

void kvm_release_rma(struct kvm_rma_info *ri)
{
	if (atomic_dec_and_test(&ri->use_count)) {
		cma_release(kvm_cma, pfn_to_page(ri->base_pfn), kvm_rma_pages);
		kfree(ri);
	}
}
EXPORT_SYMBOL_GPL(kvm_release_rma);

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)
{
	unsigned long align_pages = HPT_ALIGN_PAGES;

	VM_BUG_ON(order_base_2(nr_pages) < KVM_CMA_CHUNK_ORDER - PAGE_SHIFT);

	/* Old CPUs require HPT aligned on a multiple of its size */
	if (!cpu_has_feature(CPU_FTR_ARCH_206))
		align_pages = nr_pages;
	return cma_alloc(kvm_cma, nr_pages, order_base_2(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 early allocator (memblock or bootmem)
 * 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 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);
		/*
		 * Old CPUs require HPT aligned on a multiple of its size. So for them
		 * make the alignment as max size we could request.
		 */
		if (!cpu_has_feature(CPU_FTR_ARCH_206))
			align_size = __rounddown_pow_of_two(selected_size);
		else
			align_size = HPT_ALIGN_PAGES << PAGE_SHIFT;

		align_size = max(kvm_rma_pages << PAGE_SHIFT, align_size);
		cma_declare_contiguous(0, selected_size, 0, align_size,
			KVM_CMA_CHUNK_ORDER - PAGE_SHIFT, false, &kvm_cma);
	}
}

/*
 * 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);