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
|
#ifndef _LINUX_SCHED_H
#define _LINUX_SCHED_H
/*
* define DEBUG if you want the wait-queues to have some extra
* debugging code. It's not normally used, but might catch some
* wait-queue coding errors.
*
* #define DEBUG
*/
#include <asm/param.h> /* for HZ */
extern unsigned long event;
#include <linux/binfmts.h>
#include <linux/personality.h>
#include <linux/tasks.h>
#include <linux/kernel.h>
#include <asm/system.h>
#include <asm/semaphore.h>
#include <asm/page.h>
#include <linux/smp.h>
#include <linux/tty.h>
#include <linux/sem.h>
/*
* cloning flags:
*/
#define CSIGNAL 0x000000ff /* signal mask to be sent at exit */
#define CLONE_VM 0x00000100 /* set if VM shared between processes */
#define CLONE_FS 0x00000200 /* set if fs info shared between processes */
#define CLONE_FILES 0x00000400 /* set if open files shared between processes */
#define CLONE_SIGHAND 0x00000800 /* set if signal handlers shared */
#define CLONE_PID 0x00001000 /* set if pid shared */
/*
* These are the constant used to fake the fixed-point load-average
* counting. Some notes:
* - 11 bit fractions expand to 22 bits by the multiplies: this gives
* a load-average precision of 10 bits integer + 11 bits fractional
* - if you want to count load-averages more often, you need more
* precision, or rounding will get you. With 2-second counting freq,
* the EXP_n values would be 1981, 2034 and 2043 if still using only
* 11 bit fractions.
*/
extern unsigned long avenrun[]; /* Load averages */
#define FSHIFT 11 /* nr of bits of precision */
#define FIXED_1 (1<<FSHIFT) /* 1.0 as fixed-point */
#define LOAD_FREQ (5*HZ) /* 5 sec intervals */
#define EXP_1 1884 /* 1/exp(5sec/1min) as fixed-point */
#define EXP_5 2014 /* 1/exp(5sec/5min) */
#define EXP_15 2037 /* 1/exp(5sec/15min) */
#define CALC_LOAD(load,exp,n) \
load *= exp; \
load += n*(FIXED_1-exp); \
load >>= FSHIFT;
#define CT_TO_SECS(x) ((x) / HZ)
#define CT_TO_USECS(x) (((x) % HZ) * 1000000/HZ)
extern int nr_running, nr_tasks;
extern int last_pid;
#define FIRST_TASK task[0]
#define LAST_TASK task[NR_TASKS-1]
#include <linux/head.h>
#include <linux/fs.h>
#include <linux/signal.h>
#include <linux/time.h>
#include <linux/param.h>
#include <linux/resource.h>
#include <linux/ptrace.h>
#include <linux/timer.h>
#include <asm/processor.h>
#define TASK_RUNNING 0
#define TASK_INTERRUPTIBLE 1
#define TASK_UNINTERRUPTIBLE 2
#define TASK_ZOMBIE 3
#define TASK_STOPPED 4
#define TASK_SWAPPING 5
/*
* Scheduling policies
*/
#define SCHED_OTHER 0
#define SCHED_FIFO 1
#define SCHED_RR 2
struct sched_param {
int sched_priority;
};
#ifndef NULL
#define NULL ((void *) 0)
#endif
#ifdef __KERNEL__
#include <asm/spinlock.h>
/*
* This serializes "schedule()" and also protects
* the run-queue from deletions/modifications (but
* _adding_ to the beginning of the run-queue has
* a separate lock).
*/
extern rwlock_t tasklist_lock;
extern spinlock_t scheduler_lock;
extern void sched_init(void);
extern void show_state(void);
extern void trap_init(void);
asmlinkage void schedule(void);
/* Open file table structure */
struct files_struct {
int count;
fd_set close_on_exec;
fd_set open_fds;
struct file * fd[NR_OPEN];
};
#define INIT_FILES { \
1, \
{ { 0, } }, \
{ { 0, } }, \
{ NULL, } \
}
struct fs_struct {
int count;
int umask;
struct inode * root, * pwd;
};
#define INIT_FS { \
1, \
0022, \
NULL, NULL \
}
struct mm_struct {
int count;
pgd_t * pgd;
unsigned long context;
unsigned long start_code, end_code, start_data, end_data;
unsigned long start_brk, brk, start_stack, start_mmap;
unsigned long arg_start, arg_end, env_start, env_end;
unsigned long rss, total_vm, locked_vm;
unsigned long def_flags;
struct vm_area_struct * mmap;
struct vm_area_struct * mmap_avl;
struct semaphore mmap_sem;
};
#define INIT_MM { \
1, \
swapper_pg_dir, \
0, \
0, 0, 0, 0, \
0, 0, 0, 0, \
0, 0, 0, 0, \
0, 0, 0, \
0, \
&init_mmap, &init_mmap, MUTEX }
struct signal_struct {
atomic_t count;
struct sigaction action[32];
spinlock_t siglock;
};
#define INIT_SIGNALS { \
ATOMIC_INIT(1), \
{ {0,}, }, \
SPIN_LOCK_UNLOCKED }
struct task_struct {
/* these are hardcoded - don't touch */
volatile long state; /* -1 unrunnable, 0 runnable, >0 stopped */
long counter;
long priority;
unsigned long signal;
unsigned long blocked; /* bitmap of masked signals */
unsigned long flags; /* per process flags, defined below */
int errno;
long debugreg[8]; /* Hardware debugging registers */
struct exec_domain *exec_domain;
/* various fields */
struct linux_binfmt *binfmt;
struct task_struct *next_task, *prev_task;
struct task_struct *next_run, *prev_run;
unsigned long saved_kernel_stack;
unsigned long kernel_stack_page;
int exit_code, exit_signal;
/* ??? */
unsigned long personality;
int dumpable:1;
int did_exec:1;
/* shouldn't this be pid_t? */
int pid;
int pgrp;
int tty_old_pgrp;
int session;
/* boolean value for session group leader */
int leader;
int ngroups;
gid_t groups[NGROUPS];
/*
* pointers to (original) parent process, youngest child, younger sibling,
* older sibling, respectively. (p->father can be replaced with
* p->p_pptr->pid)
*/
struct task_struct *p_opptr, *p_pptr, *p_cptr, *p_ysptr, *p_osptr;
struct wait_queue *wait_chldexit; /* for wait4() */
unsigned short uid,euid,suid,fsuid;
unsigned short gid,egid,sgid,fsgid;
unsigned long timeout, policy, rt_priority;
unsigned long it_real_value, it_prof_value, it_virt_value;
unsigned long it_real_incr, it_prof_incr, it_virt_incr;
struct timer_list real_timer;
long utime, stime, cutime, cstime, start_time;
/* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */
unsigned long min_flt, maj_flt, nswap, cmin_flt, cmaj_flt, cnswap;
int swappable:1;
unsigned long swap_address;
unsigned long old_maj_flt; /* old value of maj_flt */
unsigned long dec_flt; /* page fault count of the last time */
unsigned long swap_cnt; /* number of pages to swap on next pass */
/* limits */
struct rlimit rlim[RLIM_NLIMITS];
unsigned short used_math;
char comm[16];
/* file system info */
int link_count;
struct tty_struct *tty; /* NULL if no tty */
/* ipc stuff */
struct sem_undo *semundo;
struct sem_queue *semsleeping;
/* ldt for this task - used by Wine. If NULL, default_ldt is used */
struct desc_struct *ldt;
/* tss for this task */
struct thread_struct tss;
/* filesystem information */
struct fs_struct *fs;
/* open file information */
struct files_struct *files;
/* memory management info */
struct mm_struct *mm;
/* signal handlers */
struct signal_struct *sig;
/* SMP state */
int processor;
int last_processor;
int lock_depth; /* Lock depth. We can context switch in and out of holding a syscall kernel lock... */
/* Spinlocks for various pieces or per-task state. */
spinlock_t sigmask_lock; /* Protects signal and blocked */
};
/*
* Per process flags
*/
#define PF_ALIGNWARN 0x00000001 /* Print alignment warning msgs */
/* Not implemented yet, only for 486*/
#define PF_PTRACED 0x00000010 /* set if ptrace (0) has been called. */
#define PF_TRACESYS 0x00000020 /* tracing system calls */
#define PF_FORKNOEXEC 0x00000040 /* forked but didn't exec */
#define PF_SUPERPRIV 0x00000100 /* used super-user privileges */
#define PF_DUMPCORE 0x00000200 /* dumped core */
#define PF_SIGNALED 0x00000400 /* killed by a signal */
#define PF_STARTING 0x00000002 /* being created */
#define PF_EXITING 0x00000004 /* getting shut down */
#define PF_USEDFPU 0x00100000 /* Process used the FPU this quantum (SMP only) */
#define PF_DTRACE 0x00200000 /* delayed trace (used on m68k) */
#define PF_ONSIGSTK 0x00400000 /* works on signal stack (m68k only) */
/*
* Limit the stack by to some sane default: root can always
* increase this limit if needed.. 8MB seems reasonable.
*/
#define _STK_LIM (8*1024*1024)
#define DEF_PRIORITY (20*HZ/100) /* 200 ms time slices */
/*
* INIT_TASK is used to set up the first task table, touch at
* your own risk!. Base=0, limit=0x1fffff (=2MB)
*/
#define INIT_TASK \
/* state etc */ { 0,DEF_PRIORITY,DEF_PRIORITY,0,0,0,0, \
/* debugregs */ { 0, }, \
/* exec domain */&default_exec_domain, \
/* binfmt */ NULL, \
/* schedlink */ &init_task,&init_task, &init_task, &init_task, \
/* stack */ 0,(unsigned long) &init_kernel_stack, \
/* ec,brk... */ 0,0,0,0,0, \
/* pid etc.. */ 0,0,0,0,0, \
/* suppl grps*/ 0, {0,}, \
/* proc links*/ &init_task,&init_task,NULL,NULL,NULL,NULL, \
/* uid etc */ 0,0,0,0,0,0,0,0, \
/* timeout */ 0,SCHED_OTHER,0,0,0,0,0,0,0, \
/* timer */ { NULL, NULL, 0, 0, it_real_fn }, \
/* utime */ 0,0,0,0,0, \
/* flt */ 0,0,0,0,0,0, \
/* swp */ 0,0,0,0,0, \
/* rlimits */ INIT_RLIMITS, \
/* math */ 0, \
/* comm */ "swapper", \
/* fs info */ 0,NULL, \
/* ipc */ NULL, NULL, \
/* ldt */ NULL, \
/* tss */ INIT_TSS, \
/* fs */ &init_fs, \
/* files */ &init_files, \
/* mm */ &init_mm, \
/* signals */ &init_signals, \
/* SMP */ 0,0,0, \
}
extern struct mm_struct init_mm;
extern struct task_struct init_task;
extern struct task_struct *task[NR_TASKS];
extern struct task_struct *last_task_used_math;
#include <asm/current.h>
extern unsigned long volatile jiffies;
extern unsigned long itimer_ticks;
extern unsigned long itimer_next;
extern struct timeval xtime;
extern int need_resched;
extern void do_timer(struct pt_regs *);
extern unsigned int * prof_buffer;
extern unsigned long prof_len;
extern unsigned long prof_shift;
extern int securelevel; /* system security level */
#define CURRENT_TIME (xtime.tv_sec)
extern void sleep_on(struct wait_queue ** p);
extern void interruptible_sleep_on(struct wait_queue ** p);
extern void wake_up(struct wait_queue ** p);
extern void wake_up_interruptible(struct wait_queue ** p);
extern void wake_up_process(struct task_struct * tsk);
extern void notify_parent(struct task_struct * tsk);
extern void force_sig(unsigned long sig,struct task_struct * p);
extern int send_sig(unsigned long sig,struct task_struct * p,int priv);
extern int in_group_p(gid_t grp);
extern int request_irq(unsigned int irq,
void (*handler)(int, void *, struct pt_regs *),
unsigned long flags,
const char *device,
void *dev_id);
extern void free_irq(unsigned int irq, void *dev_id);
/*
* This has now become a routine instead of a macro, it sets a flag if
* it returns true (to do BSD-style accounting where the process is flagged
* if it uses root privs). The implication of this is that you should do
* normal permissions checks first, and check suser() last.
*/
extern inline int suser(void)
{
if (current->euid == 0) {
current->flags |= PF_SUPERPRIV;
return 1;
}
return 0;
}
extern int copy_thread(int, unsigned long, unsigned long, struct task_struct *, struct pt_regs *);
extern void flush_thread(void);
extern void exit_thread(void);
extern void exit_mm(struct task_struct *);
extern void exit_fs(struct task_struct *);
extern void exit_files(struct task_struct *);
extern void exit_sighand(struct task_struct *);
extern int do_execve(char *, char **, char **, struct pt_regs *);
extern int do_fork(unsigned long, unsigned long, struct pt_regs *);
/* See if we have a valid user level fd.
* If it makes sense, return the file structure it references.
* Otherwise return NULL.
*/
extern inline struct file *file_from_fd(const unsigned int fd)
{
if (fd >= NR_OPEN)
return NULL;
/* either valid or null */
return current->files->fd[fd];
}
/*
* The wait-queues are circular lists, and you have to be *very* sure
* to keep them correct. Use only these two functions to add/remove
* entries in the queues.
*/
extern inline void __add_wait_queue(struct wait_queue ** p, struct wait_queue * wait)
{
struct wait_queue *head = *p;
struct wait_queue *next = WAIT_QUEUE_HEAD(p);
if (head)
next = head;
*p = wait;
wait->next = next;
}
extern spinlock_t waitqueue_lock;
extern inline void add_wait_queue(struct wait_queue ** p, struct wait_queue * wait)
{
unsigned long flags;
spin_lock_irqsave(&waitqueue_lock, flags);
__add_wait_queue(p, wait);
spin_unlock_irqrestore(&waitqueue_lock, flags);
}
extern inline void __remove_wait_queue(struct wait_queue ** p, struct wait_queue * wait)
{
struct wait_queue * next = wait->next;
struct wait_queue * head = next;
for (;;) {
struct wait_queue * nextlist = head->next;
if (nextlist == wait)
break;
head = nextlist;
}
head->next = next;
}
extern inline void remove_wait_queue(struct wait_queue ** p, struct wait_queue * wait)
{
unsigned long flags;
spin_lock_irqsave(&waitqueue_lock, flags);
__remove_wait_queue(p, wait);
spin_unlock_irqrestore(&waitqueue_lock, flags);
}
extern inline void poll_wait(struct wait_queue ** wait_address, poll_table * p)
{
struct poll_table_entry * entry;
if (!p || !wait_address)
return;
if (p->nr >= __MAX_POLL_TABLE_ENTRIES)
return;
entry = p->entry + p->nr;
entry->wait_address = wait_address;
entry->wait.task = current;
entry->wait.next = NULL;
add_wait_queue(wait_address,&entry->wait);
p->nr++;
}
#define REMOVE_LINKS(p) do { unsigned long flags; \
write_lock_irqsave(&tasklist_lock, flags); \
(p)->next_task->prev_task = (p)->prev_task; \
(p)->prev_task->next_task = (p)->next_task; \
write_unlock_irqrestore(&tasklist_lock, flags); \
if ((p)->p_osptr) \
(p)->p_osptr->p_ysptr = (p)->p_ysptr; \
if ((p)->p_ysptr) \
(p)->p_ysptr->p_osptr = (p)->p_osptr; \
else \
(p)->p_pptr->p_cptr = (p)->p_osptr; \
} while (0)
#define SET_LINKS(p) do { unsigned long flags; \
write_lock_irqsave(&tasklist_lock, flags); \
(p)->next_task = &init_task; \
(p)->prev_task = init_task.prev_task; \
init_task.prev_task->next_task = (p); \
init_task.prev_task = (p); \
write_unlock_irqrestore(&tasklist_lock, flags); \
(p)->p_ysptr = NULL; \
if (((p)->p_osptr = (p)->p_pptr->p_cptr) != NULL) \
(p)->p_osptr->p_ysptr = p; \
(p)->p_pptr->p_cptr = p; \
} while (0)
#define for_each_task(p) \
for (p = &init_task ; (p = p->next_task) != &init_task ; )
#endif /* __KERNEL__ */
#endif
|