summaryrefslogtreecommitdiffstats
path: root/arch/x86/mm/cpu_entry_area.c
blob: 56f9189bbadb4700973d3ff1b1be85c710ffd463 (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
// SPDX-License-Identifier: GPL-2.0

#include <linux/spinlock.h>
#include <linux/percpu.h>
#include <linux/kallsyms.h>
#include <linux/kcore.h>

#include <asm/cpu_entry_area.h>
#include <asm/pgtable.h>
#include <asm/fixmap.h>
#include <asm/desc.h>

static DEFINE_PER_CPU_PAGE_ALIGNED(struct entry_stack_page, entry_stack_storage);

#ifdef CONFIG_X86_64
static DEFINE_PER_CPU_PAGE_ALIGNED(struct exception_stacks, exception_stacks);
DEFINE_PER_CPU(struct cea_exception_stacks*, cea_exception_stacks);
#endif

#if defined(CONFIG_X86_32) && defined(CONFIG_DOUBLEFAULT)
DECLARE_PER_CPU_PAGE_ALIGNED(struct doublefault_stack, doublefault_stack);
#endif

struct cpu_entry_area *get_cpu_entry_area(int cpu)
{
	unsigned long va = CPU_ENTRY_AREA_PER_CPU + cpu * CPU_ENTRY_AREA_SIZE;
	BUILD_BUG_ON(sizeof(struct cpu_entry_area) % PAGE_SIZE != 0);

	return (struct cpu_entry_area *) va;
}
EXPORT_SYMBOL(get_cpu_entry_area);

void cea_set_pte(void *cea_vaddr, phys_addr_t pa, pgprot_t flags)
{
	unsigned long va = (unsigned long) cea_vaddr;
	pte_t pte = pfn_pte(pa >> PAGE_SHIFT, flags);

	/*
	 * The cpu_entry_area is shared between the user and kernel
	 * page tables.  All of its ptes can safely be global.
	 * _PAGE_GLOBAL gets reused to help indicate PROT_NONE for
	 * non-present PTEs, so be careful not to set it in that
	 * case to avoid confusion.
	 */
	if (boot_cpu_has(X86_FEATURE_PGE) &&
	    (pgprot_val(flags) & _PAGE_PRESENT))
		pte = pte_set_flags(pte, _PAGE_GLOBAL);

	set_pte_vaddr(va, pte);
}

static void __init
cea_map_percpu_pages(void *cea_vaddr, void *ptr, int pages, pgprot_t prot)
{
	for ( ; pages; pages--, cea_vaddr+= PAGE_SIZE, ptr += PAGE_SIZE)
		cea_set_pte(cea_vaddr, per_cpu_ptr_to_phys(ptr), prot);
}

static void __init percpu_setup_debug_store(unsigned int cpu)
{
#ifdef CONFIG_CPU_SUP_INTEL
	unsigned int npages;
	void *cea;

	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
		return;

	cea = &get_cpu_entry_area(cpu)->cpu_debug_store;
	npages = sizeof(struct debug_store) / PAGE_SIZE;
	BUILD_BUG_ON(sizeof(struct debug_store) % PAGE_SIZE != 0);
	cea_map_percpu_pages(cea, &per_cpu(cpu_debug_store, cpu), npages,
			     PAGE_KERNEL);

	cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers;
	/*
	 * Force the population of PMDs for not yet allocated per cpu
	 * memory like debug store buffers.
	 */
	npages = sizeof(struct debug_store_buffers) / PAGE_SIZE;
	for (; npages; npages--, cea += PAGE_SIZE)
		cea_set_pte(cea, 0, PAGE_NONE);
#endif
}

#ifdef CONFIG_X86_64

#define cea_map_stack(name) do {					\
	npages = sizeof(estacks->name## _stack) / PAGE_SIZE;		\
	cea_map_percpu_pages(cea->estacks.name## _stack,		\
			estacks->name## _stack, npages, PAGE_KERNEL);	\
	} while (0)

static void __init percpu_setup_exception_stacks(unsigned int cpu)
{
	struct exception_stacks *estacks = per_cpu_ptr(&exception_stacks, cpu);
	struct cpu_entry_area *cea = get_cpu_entry_area(cpu);
	unsigned int npages;

	BUILD_BUG_ON(sizeof(exception_stacks) % PAGE_SIZE != 0);

	per_cpu(cea_exception_stacks, cpu) = &cea->estacks;

	/*
	 * The exceptions stack mappings in the per cpu area are protected
	 * by guard pages so each stack must be mapped separately. DB2 is
	 * not mapped; it just exists to catch triple nesting of #DB.
	 */
	cea_map_stack(DF);
	cea_map_stack(NMI);
	cea_map_stack(DB1);
	cea_map_stack(DB);
	cea_map_stack(MCE);
}
#else
static inline void percpu_setup_exception_stacks(unsigned int cpu)
{
#ifdef CONFIG_DOUBLEFAULT
	struct cpu_entry_area *cea = get_cpu_entry_area(cpu);

	cea_map_percpu_pages(&cea->doublefault_stack,
			     &per_cpu(doublefault_stack, cpu), 1, PAGE_KERNEL);
#endif
}
#endif

/* Setup the fixmap mappings only once per-processor */
static void __init setup_cpu_entry_area(unsigned int cpu)
{
	struct cpu_entry_area *cea = get_cpu_entry_area(cpu);
#ifdef CONFIG_X86_64
	/* On 64-bit systems, we use a read-only fixmap GDT and TSS. */
	pgprot_t gdt_prot = PAGE_KERNEL_RO;
	pgprot_t tss_prot = PAGE_KERNEL_RO;
#else
	/*
	 * On native 32-bit systems, the GDT cannot be read-only because
	 * our double fault handler uses a task gate, and entering through
	 * a task gate needs to change an available TSS to busy.  If the
	 * GDT is read-only, that will triple fault.  The TSS cannot be
	 * read-only because the CPU writes to it on task switches.
	 *
	 * On Xen PV, the GDT must be read-only because the hypervisor
	 * requires it.
	 */
	pgprot_t gdt_prot = boot_cpu_has(X86_FEATURE_XENPV) ?
		PAGE_KERNEL_RO : PAGE_KERNEL;
	pgprot_t tss_prot = PAGE_KERNEL;
#endif

	cea_set_pte(&cea->gdt, get_cpu_gdt_paddr(cpu), gdt_prot);

	cea_map_percpu_pages(&cea->entry_stack_page,
			     per_cpu_ptr(&entry_stack_storage, cpu), 1,
			     PAGE_KERNEL);

	/*
	 * The Intel SDM says (Volume 3, 7.2.1):
	 *
	 *  Avoid placing a page boundary in the part of the TSS that the
	 *  processor reads during a task switch (the first 104 bytes). The
	 *  processor may not correctly perform address translations if a
	 *  boundary occurs in this area. During a task switch, the processor
	 *  reads and writes into the first 104 bytes of each TSS (using
	 *  contiguous physical addresses beginning with the physical address
	 *  of the first byte of the TSS). So, after TSS access begins, if
	 *  part of the 104 bytes is not physically contiguous, the processor
	 *  will access incorrect information without generating a page-fault
	 *  exception.
	 *
	 * There are also a lot of errata involving the TSS spanning a page
	 * boundary.  Assert that we're not doing that.
	 */
	BUILD_BUG_ON((offsetof(struct tss_struct, x86_tss) ^
		      offsetofend(struct tss_struct, x86_tss)) & PAGE_MASK);
	BUILD_BUG_ON(sizeof(struct tss_struct) % PAGE_SIZE != 0);
	/*
	 * VMX changes the host TR limit to 0x67 after a VM exit. This is
	 * okay, since 0x67 covers the size of struct x86_hw_tss. Make sure
	 * that this is correct.
	 */
	BUILD_BUG_ON(offsetof(struct tss_struct, x86_tss) != 0);
	BUILD_BUG_ON(sizeof(struct x86_hw_tss) != 0x68);

	cea_map_percpu_pages(&cea->tss, &per_cpu(cpu_tss_rw, cpu),
			     sizeof(struct tss_struct) / PAGE_SIZE, tss_prot);

#ifdef CONFIG_X86_32
	per_cpu(cpu_entry_area, cpu) = cea;
#endif

	percpu_setup_exception_stacks(cpu);

	percpu_setup_debug_store(cpu);
}

static __init void setup_cpu_entry_area_ptes(void)
{
#ifdef CONFIG_X86_32
	unsigned long start, end;

	/* The +1 is for the readonly IDT: */
	BUILD_BUG_ON((CPU_ENTRY_AREA_PAGES+1)*PAGE_SIZE != CPU_ENTRY_AREA_MAP_SIZE);
	BUILD_BUG_ON(CPU_ENTRY_AREA_TOTAL_SIZE != CPU_ENTRY_AREA_MAP_SIZE);
	BUG_ON(CPU_ENTRY_AREA_BASE & ~PMD_MASK);

	start = CPU_ENTRY_AREA_BASE;
	end = start + CPU_ENTRY_AREA_MAP_SIZE;

	/* Careful here: start + PMD_SIZE might wrap around */
	for (; start < end && start >= CPU_ENTRY_AREA_BASE; start += PMD_SIZE)
		populate_extra_pte(start);
#endif
}

void __init setup_cpu_entry_areas(void)
{
	unsigned int cpu;

	setup_cpu_entry_area_ptes();

	for_each_possible_cpu(cpu)
		setup_cpu_entry_area(cpu);

	/*
	 * This is the last essential update to swapper_pgdir which needs
	 * to be synchronized to initial_page_table on 32bit.
	 */
	sync_initial_page_table();
}