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
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
|
/*
* Copyright (C) 2006, Rusty Russell <rusty@rustcorp.com.au> IBM Corporation.
* Copyright (C) 2007, Jes Sorensen <jes@sgi.com> SGI.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* 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.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#include <linux/kernel.h>
#include <linux/start_kernel.h>
#include <linux/string.h>
#include <linux/console.h>
#include <linux/screen_info.h>
#include <linux/irq.h>
#include <linux/interrupt.h>
#include <linux/clocksource.h>
#include <linux/clockchips.h>
#include <linux/cpu.h>
#include <linux/lguest.h>
#include <linux/lguest_launcher.h>
#include <asm/paravirt.h>
#include <asm/param.h>
#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/desc.h>
#include <asm/setup.h>
#include <asm/lguest.h>
#include <asm/uaccess.h>
#include <asm/i387.h>
#include "../lg.h"
static int cpu_had_pge;
static struct {
unsigned long offset;
unsigned short segment;
} lguest_entry;
/* Offset from where switcher.S was compiled to where we've copied it */
static unsigned long switcher_offset(void)
{
return SWITCHER_ADDR - (unsigned long)start_switcher_text;
}
/* This cpu's struct lguest_pages. */
static struct lguest_pages *lguest_pages(unsigned int cpu)
{
return &(((struct lguest_pages *)
(SWITCHER_ADDR + SHARED_SWITCHER_PAGES*PAGE_SIZE))[cpu]);
}
static DEFINE_PER_CPU(struct lg_cpu *, last_cpu);
/*S:010
* We approach the Switcher.
*
* Remember that each CPU has two pages which are visible to the Guest when it
* runs on that CPU. This has to contain the state for that Guest: we copy the
* state in just before we run the Guest.
*
* Each Guest has "changed" flags which indicate what has changed in the Guest
* since it last ran. We saw this set in interrupts_and_traps.c and
* segments.c.
*/
static void copy_in_guest_info(struct lg_cpu *cpu, struct lguest_pages *pages)
{
/* Copying all this data can be quite expensive. We usually run the
* same Guest we ran last time (and that Guest hasn't run anywhere else
* meanwhile). If that's not the case, we pretend everything in the
* Guest has changed. */
if (__get_cpu_var(last_cpu) != cpu || cpu->last_pages != pages) {
__get_cpu_var(last_cpu) = cpu;
cpu->last_pages = pages;
cpu->changed = CHANGED_ALL;
}
/* These copies are pretty cheap, so we do them unconditionally: */
/* Save the current Host top-level page directory. */
pages->state.host_cr3 = __pa(current->mm->pgd);
/* Set up the Guest's page tables to see this CPU's pages (and no
* other CPU's pages). */
map_switcher_in_guest(cpu, pages);
/* Set up the two "TSS" members which tell the CPU what stack to use
* for traps which do directly into the Guest (ie. traps at privilege
* level 1). */
pages->state.guest_tss.sp1 = cpu->esp1;
pages->state.guest_tss.ss1 = cpu->ss1;
/* Copy direct-to-Guest trap entries. */
if (cpu->changed & CHANGED_IDT)
copy_traps(cpu, pages->state.guest_idt, default_idt_entries);
/* Copy all GDT entries which the Guest can change. */
if (cpu->changed & CHANGED_GDT)
copy_gdt(cpu, pages->state.guest_gdt);
/* If only the TLS entries have changed, copy them. */
else if (cpu->changed & CHANGED_GDT_TLS)
copy_gdt_tls(cpu, pages->state.guest_gdt);
/* Mark the Guest as unchanged for next time. */
cpu->changed = 0;
}
/* Finally: the code to actually call into the Switcher to run the Guest. */
static void run_guest_once(struct lg_cpu *cpu, struct lguest_pages *pages)
{
/* This is a dummy value we need for GCC's sake. */
unsigned int clobber;
/* Copy the guest-specific information into this CPU's "struct
* lguest_pages". */
copy_in_guest_info(cpu, pages);
/* Set the trap number to 256 (impossible value). If we fault while
* switching to the Guest (bad segment registers or bug), this will
* cause us to abort the Guest. */
cpu->regs->trapnum = 256;
/* Now: we push the "eflags" register on the stack, then do an "lcall".
* This is how we change from using the kernel code segment to using
* the dedicated lguest code segment, as well as jumping into the
* Switcher.
*
* The lcall also pushes the old code segment (KERNEL_CS) onto the
* stack, then the address of this call. This stack layout happens to
* exactly match the stack layout created by an interrupt... */
asm volatile("pushf; lcall *lguest_entry"
/* This is how we tell GCC that %eax ("a") and %ebx ("b")
* are changed by this routine. The "=" means output. */
: "=a"(clobber), "=b"(clobber)
/* %eax contains the pages pointer. ("0" refers to the
* 0-th argument above, ie "a"). %ebx contains the
* physical address of the Guest's top-level page
* directory. */
: "0"(pages), "1"(__pa(cpu->lg->pgdirs[cpu->cpu_pgd].pgdir))
/* We tell gcc that all these registers could change,
* which means we don't have to save and restore them in
* the Switcher. */
: "memory", "%edx", "%ecx", "%edi", "%esi");
}
/*:*/
/*M:002 There are hooks in the scheduler which we can register to tell when we
* get kicked off the CPU (preempt_notifier_register()). This would allow us
* to lazily disable SYSENTER which would regain some performance, and should
* also simplify copy_in_guest_info(). Note that we'd still need to restore
* things when we exit to Launcher userspace, but that's fairly easy.
*
* The hooks were designed for KVM, but we can also put them to good use. :*/
/*H:040 This is the i386-specific code to setup and run the Guest. Interrupts
* are disabled: we own the CPU. */
void lguest_arch_run_guest(struct lg_cpu *cpu)
{
/* Remember the awfully-named TS bit? If the Guest has asked to set it
* we set it now, so we can trap and pass that trap to the Guest if it
* uses the FPU. */
if (cpu->ts)
lguest_set_ts();
/* SYSENTER is an optimized way of doing system calls. We can't allow
* it because it always jumps to privilege level 0. A normal Guest
* won't try it because we don't advertise it in CPUID, but a malicious
* Guest (or malicious Guest userspace program) could, so we tell the
* CPU to disable it before running the Guest. */
if (boot_cpu_has(X86_FEATURE_SEP))
wrmsr(MSR_IA32_SYSENTER_CS, 0, 0);
/* Now we actually run the Guest. It will return when something
* interesting happens, and we can examine its registers to see what it
* was doing. */
run_guest_once(cpu, lguest_pages(raw_smp_processor_id()));
/* Note that the "regs" pointer contains two extra entries which are
* not really registers: a trap number which says what interrupt or
* trap made the switcher code come back, and an error code which some
* traps set. */
/* If the Guest page faulted, then the cr2 register will tell us the
* bad virtual address. We have to grab this now, because once we
* re-enable interrupts an interrupt could fault and thus overwrite
* cr2, or we could even move off to a different CPU. */
if (cpu->regs->trapnum == 14)
cpu->arch.last_pagefault = read_cr2();
/* Similarly, if we took a trap because the Guest used the FPU,
* we have to restore the FPU it expects to see. */
else if (cpu->regs->trapnum == 7)
math_state_restore();
/* Restore SYSENTER if it's supposed to be on. */
if (boot_cpu_has(X86_FEATURE_SEP))
wrmsr(MSR_IA32_SYSENTER_CS, __KERNEL_CS, 0);
}
/*H:130 Now we've examined the hypercall code; our Guest can make requests.
* Our Guest is usually so well behaved; it never tries to do things it isn't
* allowed to, and uses hypercalls instead. Unfortunately, Linux's paravirtual
* infrastructure isn't quite complete, because it doesn't contain replacements
* for the Intel I/O instructions. As a result, the Guest sometimes fumbles
* across one during the boot process as it probes for various things which are
* usually attached to a PC.
*
* When the Guest uses one of these instructions, we get a trap (General
* Protection Fault) and come here. We see if it's one of those troublesome
* instructions and skip over it. We return true if we did. */
static int emulate_insn(struct lg_cpu *cpu)
{
u8 insn;
unsigned int insnlen = 0, in = 0, shift = 0;
/* The eip contains the *virtual* address of the Guest's instruction:
* guest_pa just subtracts the Guest's page_offset. */
unsigned long physaddr = guest_pa(cpu, cpu->regs->eip);
/* This must be the Guest kernel trying to do something, not userspace!
* The bottom two bits of the CS segment register are the privilege
* level. */
if ((cpu->regs->cs & 3) != GUEST_PL)
return 0;
/* Decoding x86 instructions is icky. */
insn = lgread(cpu, physaddr, u8);
/* 0x66 is an "operand prefix". It means it's using the upper 16 bits
of the eax register. */
if (insn == 0x66) {
shift = 16;
/* The instruction is 1 byte so far, read the next byte. */
insnlen = 1;
insn = lgread(cpu, physaddr + insnlen, u8);
}
/* We can ignore the lower bit for the moment and decode the 4 opcodes
* we need to emulate. */
switch (insn & 0xFE) {
case 0xE4: /* in <next byte>,%al */
insnlen += 2;
in = 1;
break;
case 0xEC: /* in (%dx),%al */
insnlen += 1;
in = 1;
break;
case 0xE6: /* out %al,<next byte> */
insnlen += 2;
break;
case 0xEE: /* out %al,(%dx) */
insnlen += 1;
break;
default:
/* OK, we don't know what this is, can't emulate. */
return 0;
}
/* If it was an "IN" instruction, they expect the result to be read
* into %eax, so we change %eax. We always return all-ones, which
* traditionally means "there's nothing there". */
if (in) {
/* Lower bit tells is whether it's a 16 or 32 bit access */
if (insn & 0x1)
cpu->regs->eax = 0xFFFFFFFF;
else
cpu->regs->eax |= (0xFFFF << shift);
}
/* Finally, we've "done" the instruction, so move past it. */
cpu->regs->eip += insnlen;
/* Success! */
return 1;
}
/*H:050 Once we've re-enabled interrupts, we look at why the Guest exited. */
void lguest_arch_handle_trap(struct lg_cpu
|