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
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
|
/*P:200 This contains all the /dev/lguest code, whereby the userspace
* launcher controls and communicates with the Guest. For example,
* the first write will tell us the Guest's memory layout and entry
* point. A read will run the Guest until something happens, such as
* a signal or the Guest doing a NOTIFY out to the Launcher. There is
* also a way for the Launcher to attach eventfds to particular NOTIFY
* values instead of returning from the read() call.
:*/
#include <linux/uaccess.h>
#include <linux/miscdevice.h>
#include <linux/fs.h>
#include <linux/sched.h>
#include <linux/eventfd.h>
#include <linux/file.h>
#include <linux/slab.h>
#include <linux/export.h>
#include "lg.h"
/*L:056
* Before we move on, let's jump ahead and look at what the kernel does when
* it needs to look up the eventfds. That will complete our picture of how we
* use RCU.
*
* The notification value is in cpu->pending_notify: we return true if it went
* to an eventfd.
*/
bool send_notify_to_eventfd(struct lg_cpu *cpu)
{
unsigned int i;
struct lg_eventfd_map *map;
/* We only connect LHCALL_NOTIFY to event fds, not other traps. */
if (cpu->pending.trap != LGUEST_TRAP_ENTRY)
return false;
/*
* This "rcu_read_lock()" helps track when someone is still looking at
* the (RCU-using) eventfds array. It's not actually a lock at all;
* indeed it's a noop in many configurations. (You didn't expect me to
* explain all the RCU secrets here, did you?)
*/
rcu_read_lock();
/*
* rcu_dereference is the counter-side of rcu_assign_pointer(); it
* makes sure we don't access the memory pointed to by
* cpu->lg->eventfds before cpu->lg->eventfds is set. Sounds crazy,
* but Alpha allows this! Paul McKenney points out that a really
* aggressive compiler could have the same effect:
* http://lists.ozlabs.org/pipermail/lguest/2009-July/001560.html
*
* So play safe, use rcu_dereference to get the rcu-protected pointer:
*/
map = rcu_dereference(cpu->lg->eventfds);
/*
* Simple array search: even if they add an eventfd while we do this,
* we'll continue to use the old array and just won't see the new one.
*/
for (i = 0; i < map->num; i++) {
if (map->map[i].addr == cpu->pending.addr) {
eventfd_signal(map->map[i].event, 1);
cpu->pending.trap = 0;
break;
}
}
/* We're done with the rcu-protected variable cpu->lg->eventfds. */
rcu_read_unlock();
/* If we cleared the notification, it's because we found a match. */
return cpu->pending.trap == 0;
}
/*L:055
* One of the more tricksy tricks in the Linux Kernel is a technique called
* Read Copy Update. Since one point of lguest is to teach lguest journeyers
* about kernel coding, I use it here. (In case you're curious, other purposes
* include learning about virtualization and instilling a deep appreciation for
* simplicity and puppies).
*
* We keep a simple array which maps LHCALL_NOTIFY values to eventfds, but we
* add new eventfds without ever blocking readers from accessing the array.
* The current Launcher only does this during boot, so that never happens. But
* Read Copy Update is cool, and adding a lock risks damaging even more puppies
* than this code does.
*
* We allocate a brand new one-larger array, copy the old one and add our new
* element. Then we make the lg eventfd pointer point to the new array.
* That's the easy part: now we need to free the old one, but we need to make
* sure no slow CPU somewhere is still looking at it. That's what
* synchronize_rcu does for us: waits until every CPU has indicated that it has
* moved on to know it's no longer using the old one.
*
* If that's unclear, see http://en.wikipedia.org/wiki/Read-copy-update.
*/
static int add_eventfd(struct lguest *lg, unsigned long addr, int fd)
{
struct lg_eventfd_map *new, *old = lg->eventfds;
/*
* We don't allow notifications on value 0 anyway (pending_notify of
* 0 means "nothing pending").
*/
if (!addr)
return -EINVAL;
/*
* Replace the old array with the new one, carefully: others can
* be accessing it at the same time.
*/
new = kmalloc(sizeof(*new) + sizeof(new->map[0]) * (old->num + 1),
GFP_KERNEL);
if (!new)
return -ENOMEM;
/* First make identical copy. */
memcpy(new->map, old->map, sizeof(old->map[0]) * old->num);
new->num = old->num;
/* Now append new entry. */
new->map[new->num].addr = addr;
new->map[new->num].event = eventfd_ctx_fdget(fd);
if (IS_ERR(new->map[new->num].event)) {
int err = PTR_ERR(new->map[new->num].event);
kfree(new);
return err;
}
new->num++;
/*
* Now put new one in place: rcu_assign_pointer() is a fancy way of
* doing "lg->eventfds = new", but it uses memory barriers to make
* absolutely sure that the contents of "new" written above is nailed
* down before we actually do the assignment.
*
* We have to think about these kinds of things when we're operating on
* live data without locks.
*/
rcu_assign_pointer(lg->eventfds, new);
/*
* We're not in a big hurry. Wait until no one's looking at old
* version, then free it.
*/
synchronize_rcu();
kfree(old);
return 0;
}
/*L:052
* Receiving notifications from the Guest is usually done by attaching a
* particular LHCALL_NOTIFY value to an event filedescriptor. The eventfd will
* become readable when the Guest does an LHCALL_NOTIFY with that value.
*
* This is really convenient for processing each virtqueue in a separate
* thread.
*/
static int attach_eventfd(struct lguest *lg, const unsigned long __user *input)
{
unsigned long addr, fd;
int err;
if (get_user(addr, input) != 0)
return -EFAULT;
input++;
if (get_user(fd, input) != 0)
return -EFAULT;
/*
* Just make sure two callers don't add eventfds at once. We really
* only need to lock against callers adding to the same Guest, so using
* the Big Lguest Lock is overkill. But this is setup, not a fast path.
*/
mutex_lock(&lguest_lock);
err = add_eventfd(lg, addr, fd);
mutex_unlock(&lguest_lock);
return err;
}
/* The Launcher can get the registers, and also set some of them. */
static int getreg_setup(struct lg_cpu *cpu, const unsigned long __user *input)
{
unsigned long which;
/* We re-use the ptrace structure to specify which register to read. */
if (get_user(which, input) != 0)
return -EFAULT;
/*
* We set up the cpu register pointer, and their next read will
* actually get the value (instead of running the guest).
*
* The last argument 'true' says we can access any register.
*/
cpu->reg_read = lguest_arch_regptr(cpu, which, true);
if (!cpu->reg_read)
return -ENOENT;
/* And because this is a write() call, we return the length used. */
return sizeof(unsigned long) * 2;
}
static int setreg(struct lg_cpu *cpu, const unsigned long __user *input)
{
unsigned long which, value, *reg;
/* We re-use the ptrace structure to specify which register to read. */
if (get_user(which, input) != 0)
return -EFAULT;
input++;
if (get_user(value, input) != 0)
return -EFAULT;
/* The last argument 'false' means we can't access all registers. */
reg = lguest_arch_regptr(cpu, which, false);
if (!reg)
return -ENOENT;
*reg = value;
/* And because this is a write() call, we return the length used. */
return sizeof(unsigned long) * 3;
}
/*L:050
* Sending an interrupt is done by writing LHREQ_IRQ and an interrupt
* number to /dev/lguest.
*/
static int user_send_irq(struct lg_cpu *cpu, const unsigned long __user *input)
{
unsigned long irq;
if (get_user(irq, input) != 0)
return -EFAULT;
if (irq >= LGUEST_IRQS)
return -EINVAL;
/*
* Next time the Guest runs, the core code will see if it can deliver
* this interrupt.
*/
set_interrupt(cpu, irq);
return 0;
}
/*L:053
* Deliver a trap: this is used by the Launcher if it can't emulate
* an instruction.
*/
static int trap(struct lg_cpu *cpu, const unsigned long __user *input)
{
unsigned long trapnum;
if (get_user(trapnum, input) != 0)
return -EFAULT;
if (!deliver_trap(cpu, trapnum))
return -EINVAL;
return 0;
}
/*L:040
* Once our Guest is initialized, the Launcher makes it run by reading
* from /dev/lguest.
*/
static ssize_t read(struct file *file, char __user *user, size_t size,loff_t*o)
{
struct lguest *lg = file->private_data;
struct lg_cpu *cpu;
unsigned int cpu_id = *o;
/* You must write LHREQ_INITIALIZE first! */
if (!lg)
return -EINVAL;
/* Watch out for arbitrary vcpu indexes! */
if (cpu_id >= lg->nr_cpus)
return -EINVAL;
cpu = &lg->cpus[cpu_id];
/* If you're not the task which owns the Guest, go away. */
if (current != cpu->tsk)
return -EPERM;
/* If the Guest is already dead, we indicate why */
if (lg->dead) {
size_t len;
/* lg->dead either contains an error code, or a string. */
if (IS_ERR(lg->dead))
return PTR_ERR(lg->dead);
/* We can only return as much as the buffer they read with. */
len = min(size, strlen(lg->dead)+1);
if (copy_to_user(user, lg->dead, len) != 0)
return -EFAULT;
return len;
}
/*
* If we returned from read() last time because the Guest sent I/O,
* clear the flag.
*/
if (cpu->pending.trap)
cpu->pending.trap = 0;
/* Run the Guest until something interesting happens. */
return run_guest(cpu, (unsigned long __user *)user);
}
/*L:025
* This actually initializes a CPU. For the moment, a Guest is only
* uniprocessor, so "id" is always 0.
*/
static int lg_cpu_start(struct lg_cpu *cpu, unsigned id, unsigned long start_ip)
{
/* We have a limited number of CPUs in the lguest struct. */
if (id >= ARRAY_SIZE(cpu->lg->cpus))
return -EINVAL;
/* Set up this CPU's id, and pointer back to the lguest struct. */
cpu->id = id;
cpu->lg = container_of(cpu, struct lguest, cpus[id]);
cpu->lg->nr_cpus++;
/* Each CPU has a timer it can set. */
init_clockdev(cpu);
/*
* We need a complete page for the Guest registers: they are accessible
* to the Guest and we can only grant it access to whole pages.
*/
cpu->regs_page = get_zeroed_page(GFP_KERNEL);
if (!cpu->regs_page)
return -ENOMEM;
/* We actually put the registers at the end of the page. */
cpu->regs = (void *)cpu->regs_page + PAGE_SIZE - sizeof(*cpu->regs);
/*
* Now we initialize the Guest's registers, handing it the start
* address.
*/
lguest_arch_setup_regs(cpu, start_ip);
/*
* We keep a pointer to the Launcher task (ie. current task) for when
* other Guests want to wake this one (eg. console input).
*/
cpu->tsk = current;
/*
* We need to keep a pointer to the Launcher's memory map, because if
* the Launcher dies we need to clean it up. If we don't keep a
* reference, it is destroyed before close() is called.
*/
cpu->mm = get_task_mm(cpu->tsk);
/*
* We remember which CPU's pages this Guest used last, for optimization
* when the same Guest runs on the same CPU twice.
*/
cpu->last_pages = NULL;
/* No error == success. */
return 0;
}
/*L:020
* The initialization write supplies 3 pointer sized (32 or 64 bit) values (in
* addition to the LHREQ_INITIALIZE value). These are:
*
* base: The start of the Guest-physical memory inside the Launcher memory.
*
* pfnlimit: The highest (Guest-physical) page number the Guest should be
* allowed to access. The Guest memory lives inside the Launcher, so it sets
* this to ensure the Guest can only reach its own memory.
*
* start: The first instruction to execute ("eip" in x86-speak).
*/
static int initialize(struct file *file, const unsigned long __user *input)
{
/* "struct lguest" contains all we (the Host) know about a Guest. */
struct lguest *lg;
int err;
unsigned long args[4];
/*
* We grab the Big Lguest lock, which protects against multiple
* simultaneous initializations.
*/
mutex_lock(&lguest_lock);
/* You can't initialize twice! Close the device and start again... */
if (file->private_data) {
err = -EBUSY;
goto unlock;
}
if (copy_from_user(args, input, sizeof(args)) != 0) {
err = -EFAULT;
goto unlock;
}
lg = kzalloc(sizeof(*lg), GFP_KERNEL);
if (!lg) {
err = -ENOMEM;
goto unlock;
}
lg->eventfds = kmalloc(sizeof(*lg->eventfds), GFP_KERNEL);
if (!lg->eventfds) {
err = -ENOMEM;
goto free_lg;
}
lg->eventfds->num = 0;
/* Populate the easy fields of our "struct lguest" */
lg->mem_base = (void __user *)args[0];
lg->pfn_limit = args[1];
lg->device_limit = args[3];
/* This is the first cpu (cpu 0) and it will start booting at args[2] */
err = lg_cpu_start(&lg->cpus[0], 0, args[2]);
if (err)
goto free_eventfds;
/*
* Initialize the Guest's shadow page tables. This allocates
* memory, so can fail.
*/
err = init_guest_pagetable(lg);
if (err)
goto free_regs;
/* We keep our "struct lguest" in the file's private_data. */
file->private_data = lg;
mutex_unlock(&lguest_lock);
/* And because this is a write() call, we return the length used. */
return sizeof(args);
free_regs:
/* FIXME: This should be in free_vcpu */
free_page(lg->cpus[0].regs_page);
free_eventfds:
kfree(lg->eventfds);
free_lg:
kfree(lg);
unlock:
mutex_unlock(&lguest_lock);
return err;
}
/*L:010
* The first operation the Launcher does must be a write. All writes
* start with an unsigned long number: for the first write this must be
* LHREQ_INITIALIZE to set up the Guest. After that the Launcher can use
* writes of other values to send interrupts or set up receipt of notifications.
*
* Note that we overload the "offset" in the /dev/lguest file to indicate what
* CPU number we're dealing with. Currently this is always 0 since we only
* support uniprocessor Guests, but you can see the beginnings of SMP support
* here.
*/
static ssize_t write(struct file *file, const char __user *in,
size_t size, loff_t *off)
{
/*
* Once the Guest is initialized, we hold the "struct lguest" in the
* file private data.
*/
struct lguest *lg = file->private_data;
const unsigned long __user *input = (const unsigned long __user *)in;
unsigned long req;
struct lg_cpu *uninitialized_var(cpu);
unsigned int cpu_id = *off;
/* The first value tells us what this request is. */
if (get_user(req, input) != 0)
return -EFAULT;
input++;
/* If you haven't initialized, you must do that first. */
if (req != LHREQ_INITIALIZE) {
if (!lg || (cpu_id >= lg->nr_cpus))
return -EINVAL;
cpu = &lg->cpus[cpu_id];
/* Once the Guest is dead, you can only read() why it died. */
if (lg->dead)
return -ENOENT;
}
switch (req) {
case LHREQ_INITIALIZE:
return initialize(file, input);
case LHREQ_IRQ:
return user_send_irq(cpu, input);
case LHREQ_EVENTFD:
return attach_eventfd(lg, input);
case LHREQ_GETREG:
return getreg_setup(cpu, input);
case LHREQ_SETREG:
return setreg(cpu, input);
case LHREQ_TRAP:
return trap(cpu, input);
default:
return -EINVAL;
}
}
/*L:060
* The final piece of interface code is the close() routine. It reverses
* everything done in initialize(). This is usually called because the
* Launcher exited.
*
* Note that the close routine returns 0 or a negative error number: it can't
* really fail, but it can whine. I blame Sun for this wart, and K&R C for
* letting them do it.
:*/
static int close(struct inode *inode, struct file *file)
{
struct lguest *lg = file->private_data;
unsigned int i;
/* If we never successfully initialized, there's nothing to clean up */
if (!lg)
return 0;
/*
* We need the big lock, to protect from inter-guest I/O and other
* Launchers initializing guests.
*/
mutex_lock(&lguest_lock);
/* Free up the shadow page tables for the Guest. */
free_guest_pagetable(lg);
for (i = 0; i < lg->nr_cpus; i++) {
/* Cancels the hrtimer set via LHCALL_SET_CLOCKEVENT. */
hrtimer_cancel(&lg->cpus[i].hrt);
/* We can free up the register page we allocated. */
free_page(lg->cpus[i].regs_page);
/*
* Now all the memory cleanups are done, it's safe to release
* the Launcher's memory management structure.
*/
mmput(lg->cpus[i].mm);
}
/* Release any eventfds they registered. */
for (i = 0; i < lg->eventfds->num; i++)
eventfd_ctx_put(lg->eventfds->map[i].event);
kfree(lg->eventfds);
/*
* If lg->dead doesn't contain an error code it will be NULL or a
* kmalloc()ed string, either of which is ok to hand to kfree().
*/
if (!IS_ERR(lg->dead))
kfree(lg->dead);
/* Free the memory allocated to the lguest_struct */
kfree(lg);
/* Release lock and exit. */
mutex_unlock(&lguest_lock);
return 0;
}
/*L:000
* Welcome to our journey through the Launcher!
*
* The Launcher is the Host userspace program which sets up, runs and services
* the Guest. In fact, many comments in the Drivers which refer to "the Host"
* doing things are inaccurate: the Launcher does all the device handling for
* the Guest, but the Guest can't know that.
*
* Just to confuse you: to the Host kernel, the Launcher *is* the Guest and we
* shall see more of that later.
*
* We begin our understanding with the Host kernel interface which the Launcher
* uses: reading and writing a character device called /dev/lguest. All the
* work happens in the read(), write() and close() routines:
*/
static const struct file_operations lguest_fops = {
.owner = THIS_MODULE,
.release = close,
.write = write,
.read = read,
.llseek = default_llseek,
};
/*:*/
/*
* This is a textbook example of a "misc" character device. Populate a "struct
* miscdevice" and register it with misc_register().
*/
static struct miscdevice lguest_dev = {
.minor = MISC_DYNAMIC_MINOR,
.name = "lguest",
.fops = &lguest_fops,
};
int __init lguest_device_init(void)
{
return misc_register(&lguest_dev);
}
void __exit lguest_device_remove(void)
{
misc_deregister(&lguest_dev);
}
|