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
|
/*
* Copyright (C) 2002 Jeff Dike (jdike@karaya.com)
* Licensed under the GPL
*/
#include "linux/sched.h"
#include "linux/signal.h"
#include "linux/kernel.h"
#include "linux/interrupt.h"
#include "linux/ptrace.h"
#include "asm/system.h"
#include "asm/pgalloc.h"
#include "asm/ptrace.h"
#include "asm/tlbflush.h"
#include "irq_user.h"
#include "signal_user.h"
#include "kern_util.h"
#include "user_util.h"
#include "os.h"
#include "kern.h"
#include "sigcontext.h"
#include "time_user.h"
#include "mem_user.h"
#include "tlb.h"
#include "mode.h"
#include "init.h"
#include "tt.h"
void *switch_to_tt(void *prev, void *next, void *last)
{
struct task_struct *from, *to, *prev_sched;
unsigned long flags;
int err, vtalrm, alrm, prof, cpu;
char c;
from = prev;
to = next;
to->thread.prev_sched = from;
cpu = from->thread_info->cpu;
if(cpu == 0)
forward_interrupts(to->thread.mode.tt.extern_pid);
#ifdef CONFIG_SMP
forward_ipi(cpu_data[cpu].ipi_pipe[0], to->thread.mode.tt.extern_pid);
#endif
local_irq_save(flags);
vtalrm = change_sig(SIGVTALRM, 0);
alrm = change_sig(SIGALRM, 0);
prof = change_sig(SIGPROF, 0);
forward_pending_sigio(to->thread.mode.tt.extern_pid);
c = 0;
set_current(to);
err = os_write_file(to->thread.mode.tt.switch_pipe[1], &c, sizeof(c));
if(err != sizeof(c))
panic("write of switch_pipe failed, err = %d", -err);
if(from->thread.mode.tt.switch_pipe[0] == -1)
os_kill_process(os_getpid(), 0);
err = os_read_file(from->thread.mode.tt.switch_pipe[0], &c, sizeof(c));
if(err != sizeof(c))
panic("read of switch_pipe failed, errno = %d", -err);
/* If the process that we have just scheduled away from has exited,
* then it needs to be killed here. The reason is that, even though
* it will kill itself when it next runs, that may be too late. Its
* stack will be freed, possibly before then, and if that happens,
* we have a use-after-free situation. So, it gets killed here
* in case it has not already killed itself.
*/
prev_sched = current->thread.prev_sched;
if(prev_sched->thread.mode.tt.switch_pipe[0] == -1)
os_kill_process(prev_sched->thread.mode.tt.extern_pid, 1);
change_sig(SIGVTALRM, vtalrm);
change_sig(SIGALRM, alrm);
change_sig(SIGPROF, prof);
arch_switch();
flush_tlb_all();
local_irq_restore(flags);
return(current->thread.prev_sched);
}
void release_thread_tt(struct task_struct *task)
{
int pid = task->thread.mode.tt.extern_pid;
/*
* We first have to kill the other process, before
* closing its switch_pipe. Else it might wake up
* and receive "EOF" before we could kill it.
*/
if(os_getpid() != pid)
os_kill_process(pid, 0);
os_close_file(task->thread.mode.tt.switch_pipe[0]);
os_close_file(task->thread.mode.tt.switch_pipe[1]);
/* use switch_pipe as flag: thread is released */
task->thread.mode.tt.switch_pipe[0] = -1;
}
void suspend_new_thread(int fd)
{
int err;
char c;
os_stop_process(os_getpid());
err = os_read_file(fd, &c, sizeof(c));
if(err != sizeof(c))
panic("read failed in suspend_new_thread, err = %d", -err);
}
void schedule_tail(task_t *prev);
static void new_thread_handler(int sig)
{
unsigned long disable;
int (*fn)(void *);
void *arg;
fn = current->thread.request.u.thread.proc;
arg = current->thread.request.u.thread.arg;
UPT_SC(¤t->thread.regs.regs) = (void *) (&sig + 1);
disable = (1 << (SIGVTALRM - 1)) | (1 << (SIGALRM - 1)) |
(1 << (SIGIO - 1)) | (1 << (SIGPROF - 1));
SC_SIGMASK(UPT_SC(¤t->thread.regs.regs)) &= ~disable;
suspend_new_thread(current->thread.mode.tt.switch_pipe[0]);
force_flush_all();
if(current->thread.prev_sched != NULL)
schedule_tail(current->thread.prev_sched);
current->thread.prev_sched = NULL;
init_new_thread_signals(1);
enable_timer();
free_page(current->thread.temp_stack);
set_cmdline("(kernel thread)");
change_sig(SIGUSR1, 1);
change_sig(SIGVTALRM, 1);
change_sig(SIGPROF, 1);
local_irq_enable();
if(!run_kernel_thread(fn, arg, ¤t->thread.exec_buf))
do_exit(0);
/* XXX No set_user_mode here because a newly execed process will
* immediately segfault on its non-existent IP, coming straight back
* to the signal handler, which will call set_user_mode on its way
* out. This should probably change since it's confusing.
*/
}
static int new_thread_proc(void *stack)
{
/* local_irq_disable is needed to block out signals until this thread is
* properly scheduled. Otherwise, the tracing thread will get mighty
* upset about any signals that arrive before that.
* This has the complication that it sets the saved signal mask in
* the sigcontext to block signals. This gets restored when this
* thread (or a descendant, since they get a copy of this sigcontext)
* returns to userspace.
* So, this is compensated for elsewhere.
* XXX There is still a small window until local_irq_disable() actually
* finishes where signals are possible - shouldn't be a problem in
* practice since SIGIO hasn't been forwarded here yet, and the
* local_irq_disable should finish before a SIGVTALRM has time to be
* delivered.
*/
local_irq_disable();
init_new_thread_stack(stack, new_thread_handler);
os_usr1_process(os_getpid());
change_sig(SIGUSR1, 1);
return(0);
}
/* Signal masking - signals are blocked at the start of fork_tramp. They
* are re-enabled when finish_fork_handler is entered by fork_tramp hitting
* itself with a SIGUSR1. set_user_mode has to be run with SIGUSR1 off,
* so it is blocked before it's called. They are re-enabled on sigreturn
* despite the fact that they were blocked when the SIGUSR1 was issued because
* copy_thread copies the parent's sigcontext, including the signal mask
* onto the signal frame.
*/
void finish_fork_handler(int sig)
{
UPT_SC(¤t->thread.regs.regs) = (void *) (&sig + 1);
suspend_new_thread(current->thread.mode.tt.switch_pipe[0]);
force_flush_all();
if(current->thread.prev_sched != NULL)
schedule_tail(current->thread.prev_sched);
current->thread.prev_sched = NULL;
enable_timer();
change_sig(SIGVTALRM, 1);
local_irq_enable();
if(current->mm != current->parent->mm)
protect_memory(uml_reserved, high_physmem - uml_reserved, 1,
1, 0, 1);
task_protections((unsigned long) current_thread);
free_page(current->thread.temp_stack);
local_irq_disable();
change_sig(SIGUSR1, 0);
set_user_mode(current);
}
int fork_tramp(void *stack)
{
local_irq_disable();
arch_init_thread();
init_new_thread_stack(stack, finish_fork_handler);
os_usr1_process(os_getpid());
change_sig(SIGUSR1, 1);
return(0);
}
int copy_thread_tt(int nr, unsigned long clone_flags, unsigned long sp,
unsigned long stack_top, struct task_struct * p,
struct pt_regs *regs)
{
int (*tramp)(void *);
int new_pid, err;
unsigned long stack;
if(current->thread.forking)
tramp = fork_tramp;
else {
tramp = new_thread_proc;
p->thread.request.u.thread = current->thread.request.u.thread;
}
err = os_pipe(p->thread.mode.tt.switch_pipe, 1, 1);
if(err < 0){
printk("copy_thread : pipe failed, err = %d\n", -err);
return(err);
}
stack = alloc_stack(0, 0);
if(stack == 0){
printk(KERN_ERR "copy_thread : failed to allocate "
"temporary stack\n");
return(-ENOMEM);
}
clone_flags &= CLONE_VM;
p->thread.temp_stack = stack;
new_pid = start_fork_tramp(p->thread_info, stack, clone_flags, tramp);
if(new_pid < 0){
printk(KERN_ERR "copy_thread : clone failed - errno = %d\n",
-new_pid);
return(new_pid);
}
if(current->thread.forking){
sc_to_sc(UPT_SC(&p->thread.regs.regs),
UPT_SC(¤t->thread.regs.regs));
SC_SET_SYSCALL_RETURN(UPT_SC(&p->thread.regs.regs), 0);
if(sp != 0) SC_SP(UPT_SC(&p->thread.regs.regs)) = sp;
}
p->thread.mode.tt.extern_pid = new_pid;
current->thread.request.op = OP_FORK;
current->thread.request.u.fork.pid = new_pid;
os_usr1_process(os_getpid());
/* Enable the signal and then disable it to ensure that it is handled
* here, and nowhere else.
*/
change_sig(SIGUSR1, 1);
change_sig(SIGUSR1, 0);
err = 0;
return(err);
}
void reboot_tt(void)
{
current->thread.request.op = OP_REBOOT;
os_usr1_process(os_getpid());
change_sig(SIGUSR1, 1);
}
void halt_tt(void)
{
current->thread.request.op = OP_HALT;
os_usr1_process(os_getpid());
change_sig(SIGUSR1, 1);
}
void kill_off_processes_tt(void)
{
struct task_struct *p;
int me;
me = os_getpid();
for_each_process(p){
if(p->thread.mode.tt.extern_pid != me)
os_kill_process(p->thread.mode.tt.extern_pid, 0);
}
if(init_task.thread.mode.tt.extern_pid != me)
os_kill_process(init_task.thread.mode.tt.extern_pid, 0);
}
void initial_thread_cb_tt(void (*proc)(void *), void *arg)
{
if(os_getpid() == tracing_pid){
(*proc)(arg);
}
else {
current->thread.request.op = OP_CB;
current->thread.request.u.cb.proc = proc;
current->thread.request.u.cb.arg = arg;
os_usr1_process(os_getpid());
change_sig(SIGUSR1, 1);
change_sig(SIGUSR1, 0);
}
}
int do_proc_op(void *t, int proc_id)
{
struct task_struct *task;
struct thread_struct *thread;
int op, pid;
task = t;
thread = &task->thread;
op = thread->request.op;
switch(op){
case OP_NONE:
case OP_TRACE_ON:
break;
case OP_EXEC:
pid = thread->request.u.exec.pid;
do_exec(thread->mode.tt.extern_pid, pid);
thread->mode.tt.extern_pid = pid;
cpu_tasks[task->thread_info->cpu].pid = pid;
break;
case OP_FORK:
attach_process(thread->request.u.fork.pid);
break;
case OP_CB:
(*thread->request.u.cb.proc)(thread->request.u.cb.arg);
break;
case OP_REBOOT:
case OP_HALT:
break;
default:
tracer_panic("Bad op in do_proc_op");
break;
}
thread->request.op = OP_NONE;
return(op);
}
void init_idle_tt(void)
{
default_idle();
}
extern void start_kernel(void);
static int start_kernel_proc(void *unused)
{
int pid;
block_signals();
pid = os_getpid();
cpu_tasks[0].pid = pid;
cpu_tasks[0].task = current;
#ifdef CONFIG_SMP
cpu_online_map = cpumask_of_cpu(0);
#endif
if(debug) os_stop_process(pid);
start_kernel();
return(0);
}
void set_tracing(void *task, int tracing)
{
((struct task_struct *) task)->thread.mode.tt.tracing = tracing;
}
int is_tracing(void *t)
{
return (((struct task_struct *) t)->thread.mode.tt.tracing);
}
int set_user_mode(void *t)
{
struct task_struct *task;
task = t ? t : current;
if(task->thread.mode.tt.tracing)
return(1);
task->thread.request.op = OP_TRACE_ON;
os_usr1_process(os_getpid());
return(0);
}
void set_init_pid(int pid)
{
int err;
init_task.thread.mode.tt.extern_pid = pid;
err = os_pipe(init_task.thread.mode.tt.switch_pipe, 1, 1);
if(err)
panic("Can't create switch pipe for init_task, errno = %d",
-err);
}
int start_uml_tt(void)
{
void *sp;
int pages;
pages = (1 << CONFIG_KERNEL_STACK_ORDER);
sp = (void *) ((unsigned long) init_task.thread_info) +
pages * PAGE_SIZE - sizeof(unsigned long);
return(tracer(start_kernel_proc, sp));
}
int external_pid_tt(struct task_struct *task)
{
return(task->thread.mode.tt.extern_pid);
}
int thread_pid_tt(struct task_struct *task)
{
return(task->thread.mode.tt.extern_pid);
}
int is_valid_pid(int pid)
{
struct task_struct *task;
read_lock(&tasklist_lock);
for_each_process(task){
if(task->thread.mode.tt.extern_pid == pid){
read_unlock(&tasklist_lock);
return(1);
}
}
read_unlock(&tasklist_lock);
return(0);
}
/*
* Overrides for Emacs so that we follow Linus's tabbing style.
* Emacs will notice this stuff at the end of the file and automatically
* adjust the settings for this buffer only. This must remain at the end
* of the file.
* ---------------------------------------------------------------------------
* Local variables:
* c-file-style: "linux"
* End:
*/
|