summaryrefslogtreecommitdiffstats
path: root/drivers/lguest/interrupts_and_traps.c
blob: b2647974e1a717747cf3236534e06ac8e1d6572f (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
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
/*P:800 Interrupts (traps) are complicated enough to earn their own file.
 * There are three classes of interrupts:
 *
 * 1) Real hardware interrupts which occur while we're running the Guest,
 * 2) Interrupts for virtual devices attached to the Guest, and
 * 3) Traps and faults from the Guest.
 *
 * Real hardware interrupts must be delivered to the Host, not the Guest.
 * Virtual interrupts must be delivered to the Guest, but we make them look
 * just like real hardware would deliver them.  Traps from the Guest can be set
 * up to go directly back into the Guest, but sometimes the Host wants to see
 * them first, so we also have a way of "reflecting" them into the Guest as if
 * they had been delivered to it directly. :*/
#include <linux/uaccess.h>
#include "lg.h"

static unsigned long idt_address(u32 lo, u32 hi)
{
	return (lo & 0x0000FFFF) | (hi & 0xFFFF0000);
}

static int idt_type(u32 lo, u32 hi)
{
	return (hi >> 8) & 0xF;
}

static int idt_present(u32 lo, u32 hi)
{
	return (hi & 0x8000);
}

static void push_guest_stack(struct lguest *lg, unsigned long *gstack, u32 val)
{
	*gstack -= 4;
	lgwrite_u32(lg, *gstack, val);
}

static void set_guest_interrupt(struct lguest *lg, u32 lo, u32 hi, int has_err)
{
	unsigned long gstack;
	u32 eflags, ss, irq_enable;

	/* If they want a ring change, we use new stack and push old ss/esp */
	if ((lg->regs->ss&0x3) != GUEST_PL) {
		gstack = guest_pa(lg, lg->esp1);
		ss = lg->ss1;
		push_guest_stack(lg, &gstack, lg->regs->ss);
		push_guest_stack(lg, &gstack, lg->regs->esp);
	} else {
		gstack = guest_pa(lg, lg->regs->esp);
		ss = lg->regs->ss;
	}

	/* We use IF bit in eflags to indicate whether irqs were enabled
	   (it's always 1, since irqs are enabled when guest is running). */
	eflags = lg->regs->eflags;
	if (get_user(irq_enable, &lg->lguest_data->irq_enabled) == 0
	    && !(irq_enable & X86_EFLAGS_IF))
		eflags &= ~X86_EFLAGS_IF;

	push_guest_stack(lg, &gstack, eflags);
	push_guest_stack(lg, &gstack, lg->regs->cs);
	push_guest_stack(lg, &gstack, lg->regs->eip);

	if (has_err)
		push_guest_stack(lg, &gstack, lg->regs->errcode);

	/* Change the real stack so switcher returns to trap handler */
	lg->regs->ss = ss;
	lg->regs->esp = gstack + lg->page_offset;
	lg->regs->cs = (__KERNEL_CS|GUEST_PL);
	lg->regs->eip = idt_address(lo, hi);

	/* Disable interrupts for an interrupt gate. */
	if (idt_type(lo, hi) == 0xE)
		if (put_user(0, &lg->lguest_data->irq_enabled))
			kill_guest(lg, "Disabling interrupts");
}

void maybe_do_interrupt(struct lguest *lg)
{
	unsigned int irq;
	DECLARE_BITMAP(blk, LGUEST_IRQS);
	struct desc_struct *idt;

	if (!lg->lguest_data)
		return;

	/* Mask out any interrupts they have blocked. */
	if (copy_from_user(&blk, lg->lguest_data->blocked_interrupts,
			   sizeof(blk)))
		return;

	bitmap_andnot(blk, lg->irqs_pending, blk, LGUEST_IRQS);

	irq = find_first_bit(blk, LGUEST_IRQS);
	if (irq >= LGUEST_IRQS)
		return;

	if (lg->regs->eip >= lg->noirq_start && lg->regs->eip < lg->noirq_end)
		return;

	/* If they're halted, we re-enable interrupts. */
	if (lg->halted) {
		/* Re-enable interrupts. */
		if (put_user(X86_EFLAGS_IF, &lg->lguest_data->irq_enabled))
			kill_guest(lg, "Re-enabling interrupts");
		lg->halted = 0;
	} else {
		/* Maybe they have interrupts disabled? */
		u32 irq_enabled;
		if (get_user(irq_enabled, &lg->lguest_data->irq_enabled))
			irq_enabled = 0;
		if (!irq_enabled)
			return;
	}

	idt = &lg->idt[FIRST_EXTERNAL_VECTOR+irq];
	if (idt_present(idt->a, idt->b)) {
		clear_bit(irq, lg->irqs_pending);
		set_guest_interrupt(lg, idt->a, idt->b, 0);
	}
}

static int has_err(unsigned int trap)
{
	return (trap == 8 || (trap >= 10 && trap <= 14) || trap == 17);
}

int deliver_trap(struct lguest *lg, unsigned int num)
{
	u32 lo = lg->idt[num].a, hi = lg->idt[num].b;

	if (!idt_present(lo, hi))
		return 0;
	set_guest_interrupt(lg, lo, hi, has_err(num));
	return 1;
}

static int direct_trap(const struct lguest *lg,
		       const struct desc_struct *trap,
		       unsigned int num)
{
	/* Hardware interrupts don't go to guest (except syscall). */
	if (num >= FIRST_EXTERNAL_VECTOR && num != SYSCALL_VECTOR)
		return 0;

	/* We intercept page fault (demand shadow paging & cr2 saving)
	   protection fault (in/out emulation) and device not
	   available (TS handling), and hypercall */
	if (num == 14 || num == 13 || num == 7 || num == LGUEST_TRAP_ENTRY)
		return 0;

	/* Interrupt gates (0xE) or not present (0x0) can't go direct. */
	return idt_type(trap->a, trap->b) == 0xF;
}

void pin_stack_pages(struct lguest *lg)
{
	unsigned int i;

	for (i = 0; i < lg->stack_pages; i++)
		pin_page(lg, lg->esp1 - i * PAGE_SIZE);
}

void guest_set_stack(struct lguest *lg, u32 seg, u32 esp, unsigned int pages)
{
	/* You cannot have a stack segment with priv level 0. */
	if ((seg & 0x3) != GUEST_PL)
		kill_guest(lg, "bad stack segment %i", seg);
	if (pages > 2)
		kill_guest(lg, "bad stack pages %u", pages);
	lg->ss1 = seg;
	lg->esp1 = esp;
	lg->stack_pages = pages;
	pin_stack_pages(lg);
}

/* Set up trap in IDT. */
static void set_trap(struct lguest *lg, struct desc_struct *trap,
		     unsigned int num, u32 lo, u32 hi)
{
	u8 type = idt_type(lo, hi);

	if (!idt_present(lo, hi)) {
		trap->a = trap->b = 0;
		return;
	}

	if (type != 0xE && type != 0xF)
		kill_guest(lg, "bad IDT type %i", type);

	trap->a = ((__KERNEL_CS|GUEST_PL)<<16) | (lo&0x0000FFFF);
	trap->b = (hi&0xFFFFEF00);
}

void load_guest_idt_entry(struct lguest *lg, unsigned int num, u32 lo, u32 hi)
{
	/* Guest never handles: NMI, doublefault, hypercall, spurious irq. */
	if (num == 2 || num == 8 || num == 15 || num == LGUEST_TRAP_ENTRY)
		return;

	lg->changed |= CHANGED_IDT;
	if (num < ARRAY_SIZE(lg->idt))
		set_trap(lg, &lg->idt[num], num, lo, hi);
	else if (num == SYSCALL_VECTOR)
		set_trap(lg, &lg->syscall_idt, num, lo, hi);
}

static void default_idt_entry(struct desc_struct *idt,
			      int trap,
			      const unsigned long handler)
{
	u32 flags = 0x8e00;

	/* They can't "int" into any of them except hypercall. */
	if (trap == LGUEST_TRAP_ENTRY)
		flags |= (GUEST_PL << 13);

	idt->a = (LGUEST_CS<<16) | (handler&0x0000FFFF);
	idt->b = (handler&0xFFFF0000) | flags;
}

void setup_default_idt_entries(struct lguest_ro_state *state,
			       const unsigned long *def)
{
	unsigned int i;

	for (i = 0; i < ARRAY_SIZE(state->guest_idt); i++)
		default_idt_entry(&state->guest_idt[i], i, def[i]);
}

void copy_traps(const struct lguest *lg, struct desc_struct *idt,
		const unsigned long *def)
{
	unsigned int i;

	/* All hardware interrupts are same whatever the guest: only the
	 * traps might be different. */
	for (i = 0; i < FIRST_EXTERNAL_VECTOR; i++) {
		if (direct_trap(lg, &lg->idt[i], i))
			idt[i] = lg->idt[i];
		else
			default_idt_entry(&idt[i], i, def[i]);
	}
	i = SYSCALL_VECTOR;
	if (direct_trap(lg, &lg->syscall_idt, i))
		idt[i] = lg->syscall_idt;
	else
		default_idt_entry(&idt[i], i, def[i]);
}

void guest_set_clockevent(struct lguest *lg, unsigned long delta)
{
	ktime_t expires;

	if (unlikely(delta == 0)) {
		/* Clock event device is shutting down. */
		hrtimer_cancel(&lg->hrt);
		return;
	}

	expires = ktime_add_ns(ktime_get_real(), delta);
	hrtimer_start(&lg->hrt, expires, HRTIMER_MODE_ABS);
}

static enum hrtimer_restart clockdev_fn(struct hrtimer *timer)
{
	struct lguest *lg = container_of(timer, struct lguest, hrt);

	set_bit(0, lg->irqs_pending);
	if (lg->halted)
		wake_up_process(lg->tsk);
	return HRTIMER_NORESTART;
}

void init_clockdev(struct lguest *lg)
{
	hrtimer_init(&lg->hrt, CLOCK_REALTIME, HRTIMER_MODE_ABS);
	lg->hrt.function = clockdev_fn;
}