base.c 54.4 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13
/*
 *  linux/fs/proc/base.c
 *
 *  Copyright (C) 1991, 1992 Linus Torvalds
 *
 *  proc base directory handling functions
 *
 *  1999, Al Viro. Rewritten. Now it covers the whole per-process part.
 *  Instead of using magical inumbers to determine the kind of object
 *  we allocate and fill in-core inodes upon lookup. They don't even
 *  go into icache. We cache the reference to task_struct upon lookup too.
 *  Eventually it should become a filesystem in its own. We don't use the
 *  rest of procfs anymore.
M
Mauricio Lin 已提交
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
 *
 *
 *  Changelog:
 *  17-Jan-2005
 *  Allan Bezerra
 *  Bruna Moreira <bruna.moreira@indt.org.br>
 *  Edjard Mota <edjard.mota@indt.org.br>
 *  Ilias Biris <ilias.biris@indt.org.br>
 *  Mauricio Lin <mauricio.lin@indt.org.br>
 *
 *  Embedded Linux Lab - 10LE Instituto Nokia de Tecnologia - INdT
 *
 *  A new process specific entry (smaps) included in /proc. It shows the
 *  size of rss for each memory area. The maps entry lacks information
 *  about physical memory size (rss) for each mapped file, i.e.,
 *  rss information for executables and library files.
 *  This additional information is useful for any tools that need to know
 *  about physical memory consumption for a process specific library.
 *
 *  Changelog:
 *  21-Feb-2005
 *  Embedded Linux Lab - 10LE Instituto Nokia de Tecnologia - INdT
 *  Pud inclusion in the page table walking.
 *
 *  ChangeLog:
 *  10-Mar-2005
 *  10LE Instituto Nokia de Tecnologia - INdT:
 *  A better way to walks through the page table as suggested by Hugh Dickins.
 *
 *  Simo Piiroinen <simo.piiroinen@nokia.com>:
 *  Smaps information related to shared, private, clean and dirty pages.
 *
 *  Paul Mundt <paul.mundt@nokia.com>:
 *  Overall revision about smaps.
L
Linus Torvalds 已提交
48 49 50 51 52 53 54 55 56 57
 */

#include <asm/uaccess.h>

#include <linux/config.h>
#include <linux/errno.h>
#include <linux/time.h>
#include <linux/proc_fs.h>
#include <linux/stat.h>
#include <linux/init.h>
58
#include <linux/capability.h>
L
Linus Torvalds 已提交
59 60 61 62 63 64 65
#include <linux/file.h>
#include <linux/string.h>
#include <linux/seq_file.h>
#include <linux/namei.h>
#include <linux/namespace.h>
#include <linux/mm.h>
#include <linux/smp_lock.h>
66
#include <linux/rcupdate.h>
L
Linus Torvalds 已提交
67 68 69 70 71 72 73
#include <linux/kallsyms.h>
#include <linux/mount.h>
#include <linux/security.h>
#include <linux/ptrace.h>
#include <linux/seccomp.h>
#include <linux/cpuset.h>
#include <linux/audit.h>
A
Al Viro 已提交
74
#include <linux/poll.h>
L
Linus Torvalds 已提交
75 76
#include "internal.h"

77 78 79 80 81 82 83 84 85 86
/* NOTE:
 *	Implementing inode permission operations in /proc is almost
 *	certainly an error.  Permission checks need to happen during
 *	each system call not at open time.  The reason is that most of
 *	what we wish to check for permissions in /proc varies at runtime.
 *
 *	The classic example of a problem is opening file descriptors
 *	in /proc for a task before it execs a suid executable.
 */

L
Linus Torvalds 已提交
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
/*
 * For hysterical raisins we keep the same inumbers as in the old procfs.
 * Feel free to change the macro below - just keep the range distinct from
 * inumbers of the rest of procfs (currently those are in 0x0000--0xffff).
 * As soon as we'll get a separate superblock we will be able to forget
 * about magical ranges too.
 */

#define fake_ino(pid,ino) (((pid)<<16)|(ino))

enum pid_directory_inos {
	PROC_TGID_INO = 2,
	PROC_TGID_TASK,
	PROC_TGID_STATUS,
	PROC_TGID_MEM,
#ifdef CONFIG_SECCOMP
	PROC_TGID_SECCOMP,
#endif
	PROC_TGID_CWD,
	PROC_TGID_ROOT,
	PROC_TGID_EXE,
	PROC_TGID_FD,
	PROC_TGID_ENVIRON,
	PROC_TGID_AUXV,
	PROC_TGID_CMDLINE,
	PROC_TGID_STAT,
	PROC_TGID_STATM,
	PROC_TGID_MAPS,
115
	PROC_TGID_NUMA_MAPS,
L
Linus Torvalds 已提交
116
	PROC_TGID_MOUNTS,
117
	PROC_TGID_MOUNTSTATS,
L
Linus Torvalds 已提交
118
	PROC_TGID_WCHAN,
Y
Yoshinori Sato 已提交
119
#ifdef CONFIG_MMU
M
Mauricio Lin 已提交
120
	PROC_TGID_SMAPS,
Y
Yoshinori Sato 已提交
121
#endif
L
Linus Torvalds 已提交
122 123 124 125 126 127 128 129 130 131 132 133
#ifdef CONFIG_SCHEDSTATS
	PROC_TGID_SCHEDSTAT,
#endif
#ifdef CONFIG_CPUSETS
	PROC_TGID_CPUSET,
#endif
#ifdef CONFIG_SECURITY
	PROC_TGID_ATTR,
	PROC_TGID_ATTR_CURRENT,
	PROC_TGID_ATTR_PREV,
	PROC_TGID_ATTR_EXEC,
	PROC_TGID_ATTR_FSCREATE,
134
	PROC_TGID_ATTR_KEYCREATE,
L
Linus Torvalds 已提交
135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156
#endif
#ifdef CONFIG_AUDITSYSCALL
	PROC_TGID_LOGINUID,
#endif
	PROC_TGID_OOM_SCORE,
	PROC_TGID_OOM_ADJUST,
	PROC_TID_INO,
	PROC_TID_STATUS,
	PROC_TID_MEM,
#ifdef CONFIG_SECCOMP
	PROC_TID_SECCOMP,
#endif
	PROC_TID_CWD,
	PROC_TID_ROOT,
	PROC_TID_EXE,
	PROC_TID_FD,
	PROC_TID_ENVIRON,
	PROC_TID_AUXV,
	PROC_TID_CMDLINE,
	PROC_TID_STAT,
	PROC_TID_STATM,
	PROC_TID_MAPS,
157
	PROC_TID_NUMA_MAPS,
L
Linus Torvalds 已提交
158
	PROC_TID_MOUNTS,
159
	PROC_TID_MOUNTSTATS,
L
Linus Torvalds 已提交
160
	PROC_TID_WCHAN,
Y
Yoshinori Sato 已提交
161
#ifdef CONFIG_MMU
M
Mauricio Lin 已提交
162
	PROC_TID_SMAPS,
Y
Yoshinori Sato 已提交
163
#endif
L
Linus Torvalds 已提交
164 165 166 167 168 169 170 171 172 173 174 175
#ifdef CONFIG_SCHEDSTATS
	PROC_TID_SCHEDSTAT,
#endif
#ifdef CONFIG_CPUSETS
	PROC_TID_CPUSET,
#endif
#ifdef CONFIG_SECURITY
	PROC_TID_ATTR,
	PROC_TID_ATTR_CURRENT,
	PROC_TID_ATTR_PREV,
	PROC_TID_ATTR_EXEC,
	PROC_TID_ATTR_FSCREATE,
176
	PROC_TID_ATTR_KEYCREATE,
L
Linus Torvalds 已提交
177 178 179 180 181 182
#endif
#ifdef CONFIG_AUDITSYSCALL
	PROC_TID_LOGINUID,
#endif
	PROC_TID_OOM_SCORE,
	PROC_TID_OOM_ADJUST,
183 184 185

	/* Add new entries before this */
	PROC_TID_FD_DIR = 0x8000,	/* 0x8000-0xffff */
L
Linus Torvalds 已提交
186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206
};

struct pid_entry {
	int type;
	int len;
	char *name;
	mode_t mode;
};

#define E(type,name,mode) {(type),sizeof(name)-1,(name),(mode)}

static struct pid_entry tgid_base_stuff[] = {
	E(PROC_TGID_TASK,      "task",    S_IFDIR|S_IRUGO|S_IXUGO),
	E(PROC_TGID_FD,        "fd",      S_IFDIR|S_IRUSR|S_IXUSR),
	E(PROC_TGID_ENVIRON,   "environ", S_IFREG|S_IRUSR),
	E(PROC_TGID_AUXV,      "auxv",	  S_IFREG|S_IRUSR),
	E(PROC_TGID_STATUS,    "status",  S_IFREG|S_IRUGO),
	E(PROC_TGID_CMDLINE,   "cmdline", S_IFREG|S_IRUGO),
	E(PROC_TGID_STAT,      "stat",    S_IFREG|S_IRUGO),
	E(PROC_TGID_STATM,     "statm",   S_IFREG|S_IRUGO),
	E(PROC_TGID_MAPS,      "maps",    S_IFREG|S_IRUGO),
207 208 209
#ifdef CONFIG_NUMA
	E(PROC_TGID_NUMA_MAPS, "numa_maps", S_IFREG|S_IRUGO),
#endif
L
Linus Torvalds 已提交
210 211 212 213 214 215 216 217
	E(PROC_TGID_MEM,       "mem",     S_IFREG|S_IRUSR|S_IWUSR),
#ifdef CONFIG_SECCOMP
	E(PROC_TGID_SECCOMP,   "seccomp", S_IFREG|S_IRUSR|S_IWUSR),
#endif
	E(PROC_TGID_CWD,       "cwd",     S_IFLNK|S_IRWXUGO),
	E(PROC_TGID_ROOT,      "root",    S_IFLNK|S_IRWXUGO),
	E(PROC_TGID_EXE,       "exe",     S_IFLNK|S_IRWXUGO),
	E(PROC_TGID_MOUNTS,    "mounts",  S_IFREG|S_IRUGO),
218
	E(PROC_TGID_MOUNTSTATS, "mountstats", S_IFREG|S_IRUSR),
Y
Yoshinori Sato 已提交
219
#ifdef CONFIG_MMU
M
Mauricio Lin 已提交
220
	E(PROC_TGID_SMAPS,     "smaps",   S_IFREG|S_IRUGO),
Y
Yoshinori Sato 已提交
221
#endif
L
Linus Torvalds 已提交
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
#ifdef CONFIG_SECURITY
	E(PROC_TGID_ATTR,      "attr",    S_IFDIR|S_IRUGO|S_IXUGO),
#endif
#ifdef CONFIG_KALLSYMS
	E(PROC_TGID_WCHAN,     "wchan",   S_IFREG|S_IRUGO),
#endif
#ifdef CONFIG_SCHEDSTATS
	E(PROC_TGID_SCHEDSTAT, "schedstat", S_IFREG|S_IRUGO),
#endif
#ifdef CONFIG_CPUSETS
	E(PROC_TGID_CPUSET,    "cpuset",  S_IFREG|S_IRUGO),
#endif
	E(PROC_TGID_OOM_SCORE, "oom_score",S_IFREG|S_IRUGO),
	E(PROC_TGID_OOM_ADJUST,"oom_adj", S_IFREG|S_IRUGO|S_IWUSR),
#ifdef CONFIG_AUDITSYSCALL
	E(PROC_TGID_LOGINUID, "loginuid", S_IFREG|S_IWUSR|S_IRUGO),
#endif
	{0,0,NULL,0}
};
static struct pid_entry tid_base_stuff[] = {
	E(PROC_TID_FD,         "fd",      S_IFDIR|S_IRUSR|S_IXUSR),
	E(PROC_TID_ENVIRON,    "environ", S_IFREG|S_IRUSR),
	E(PROC_TID_AUXV,       "auxv",	  S_IFREG|S_IRUSR),
	E(PROC_TID_STATUS,     "status",  S_IFREG|S_IRUGO),
	E(PROC_TID_CMDLINE,    "cmdline", S_IFREG|S_IRUGO),
	E(PROC_TID_STAT,       "stat",    S_IFREG|S_IRUGO),
	E(PROC_TID_STATM,      "statm",   S_IFREG|S_IRUGO),
	E(PROC_TID_MAPS,       "maps",    S_IFREG|S_IRUGO),
250 251 252
#ifdef CONFIG_NUMA
	E(PROC_TID_NUMA_MAPS,  "numa_maps",    S_IFREG|S_IRUGO),
#endif
L
Linus Torvalds 已提交
253 254 255 256 257 258 259 260
	E(PROC_TID_MEM,        "mem",     S_IFREG|S_IRUSR|S_IWUSR),
#ifdef CONFIG_SECCOMP
	E(PROC_TID_SECCOMP,    "seccomp", S_IFREG|S_IRUSR|S_IWUSR),
#endif
	E(PROC_TID_CWD,        "cwd",     S_IFLNK|S_IRWXUGO),
	E(PROC_TID_ROOT,       "root",    S_IFLNK|S_IRWXUGO),
	E(PROC_TID_EXE,        "exe",     S_IFLNK|S_IRWXUGO),
	E(PROC_TID_MOUNTS,     "mounts",  S_IFREG|S_IRUGO),
Y
Yoshinori Sato 已提交
261
#ifdef CONFIG_MMU
M
Mauricio Lin 已提交
262
	E(PROC_TID_SMAPS,      "smaps",   S_IFREG|S_IRUGO),
Y
Yoshinori Sato 已提交
263
#endif
L
Linus Torvalds 已提交
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
#ifdef CONFIG_SECURITY
	E(PROC_TID_ATTR,       "attr",    S_IFDIR|S_IRUGO|S_IXUGO),
#endif
#ifdef CONFIG_KALLSYMS
	E(PROC_TID_WCHAN,      "wchan",   S_IFREG|S_IRUGO),
#endif
#ifdef CONFIG_SCHEDSTATS
	E(PROC_TID_SCHEDSTAT, "schedstat",S_IFREG|S_IRUGO),
#endif
#ifdef CONFIG_CPUSETS
	E(PROC_TID_CPUSET,     "cpuset",  S_IFREG|S_IRUGO),
#endif
	E(PROC_TID_OOM_SCORE,  "oom_score",S_IFREG|S_IRUGO),
	E(PROC_TID_OOM_ADJUST, "oom_adj", S_IFREG|S_IRUGO|S_IWUSR),
#ifdef CONFIG_AUDITSYSCALL
	E(PROC_TID_LOGINUID, "loginuid", S_IFREG|S_IWUSR|S_IRUGO),
#endif
	{0,0,NULL,0}
};

#ifdef CONFIG_SECURITY
static struct pid_entry tgid_attr_stuff[] = {
	E(PROC_TGID_ATTR_CURRENT,  "current",  S_IFREG|S_IRUGO|S_IWUGO),
	E(PROC_TGID_ATTR_PREV,     "prev",     S_IFREG|S_IRUGO),
	E(PROC_TGID_ATTR_EXEC,     "exec",     S_IFREG|S_IRUGO|S_IWUGO),
	E(PROC_TGID_ATTR_FSCREATE, "fscreate", S_IFREG|S_IRUGO|S_IWUGO),
290
	E(PROC_TGID_ATTR_KEYCREATE, "keycreate", S_IFREG|S_IRUGO|S_IWUGO),
L
Linus Torvalds 已提交
291 292 293 294 295 296 297
	{0,0,NULL,0}
};
static struct pid_entry tid_attr_stuff[] = {
	E(PROC_TID_ATTR_CURRENT,   "current",  S_IFREG|S_IRUGO|S_IWUGO),
	E(PROC_TID_ATTR_PREV,      "prev",     S_IFREG|S_IRUGO),
	E(PROC_TID_ATTR_EXEC,      "exec",     S_IFREG|S_IRUGO|S_IWUGO),
	E(PROC_TID_ATTR_FSCREATE,  "fscreate", S_IFREG|S_IRUGO|S_IWUGO),
298
	E(PROC_TID_ATTR_KEYCREATE, "keycreate", S_IFREG|S_IRUGO|S_IWUGO),
L
Linus Torvalds 已提交
299 300 301 302 303 304 305 306 307 308 309
	{0,0,NULL,0}
};
#endif

#undef E

static int proc_fd_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt)
{
	struct task_struct *task = proc_task(inode);
	struct files_struct *files;
	struct file *file;
310
	int fd = proc_fd(inode);
L
Linus Torvalds 已提交
311 312 313

	files = get_files_struct(task);
	if (files) {
314 315 316 317 318
		/*
		 * We are not taking a ref to the file structure, so we must
		 * hold ->file_lock.
		 */
		spin_lock(&files->file_lock);
L
Linus Torvalds 已提交
319 320 321 322
		file = fcheck_files(files, fd);
		if (file) {
			*mnt = mntget(file->f_vfsmnt);
			*dentry = dget(file->f_dentry);
323
			spin_unlock(&files->file_lock);
L
Linus Torvalds 已提交
324 325 326
			put_files_struct(files);
			return 0;
		}
327
		spin_unlock(&files->file_lock);
L
Linus Torvalds 已提交
328 329 330 331 332
		put_files_struct(files);
	}
	return -ENOENT;
}

333
static struct fs_struct *get_fs_struct(struct task_struct *task)
L
Linus Torvalds 已提交
334 335
{
	struct fs_struct *fs;
336 337
	task_lock(task);
	fs = task->fs;
L
Linus Torvalds 已提交
338 339
	if(fs)
		atomic_inc(&fs->count);
340 341 342 343 344 345 346 347
	task_unlock(task);
	return fs;
}

static int proc_cwd_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt)
{
	struct fs_struct *fs = get_fs_struct(proc_task(inode));
	int result = -ENOENT;
L
Linus Torvalds 已提交
348 349 350 351 352 353 354 355 356 357 358 359 360
	if (fs) {
		read_lock(&fs->lock);
		*mnt = mntget(fs->pwdmnt);
		*dentry = dget(fs->pwd);
		read_unlock(&fs->lock);
		result = 0;
		put_fs_struct(fs);
	}
	return result;
}

static int proc_root_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt)
{
361
	struct fs_struct *fs = get_fs_struct(proc_task(inode));
L
Linus Torvalds 已提交
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
	int result = -ENOENT;
	if (fs) {
		read_lock(&fs->lock);
		*mnt = mntget(fs->rootmnt);
		*dentry = dget(fs->root);
		read_unlock(&fs->lock);
		result = 0;
		put_fs_struct(fs);
	}
	return result;
}

#define MAY_PTRACE(task) \
	(task == current || \
	(task->parent == current && \
	(task->ptrace & PT_PTRACED) && \
	 (task->state == TASK_STOPPED || task->state == TASK_TRACED) && \
	 security_ptrace(current,task) == 0))

static int proc_pid_environ(struct task_struct *task, char * buffer)
{
	int res = 0;
	struct mm_struct *mm = get_task_mm(task);
	if (mm) {
		unsigned int len = mm->env_end - mm->env_start;
		if (len > PAGE_SIZE)
			len = PAGE_SIZE;
		res = access_process_vm(task, mm->env_start, buffer, len, 0);
390
		if (!ptrace_may_attach(task))
L
Linus Torvalds 已提交
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
			res = -ESRCH;
		mmput(mm);
	}
	return res;
}

static int proc_pid_cmdline(struct task_struct *task, char * buffer)
{
	int res = 0;
	unsigned int len;
	struct mm_struct *mm = get_task_mm(task);
	if (!mm)
		goto out;
	if (!mm->arg_end)
		goto out_mm;	/* Shh! No looking before we're done */

 	len = mm->arg_end - mm->arg_start;
 
	if (len > PAGE_SIZE)
		len = PAGE_SIZE;
 
	res = access_process_vm(task, mm->arg_start, buffer, len, 0);

	// If the nul at the end of args has been overwritten, then
	// assume application is using setproctitle(3).
	if (res > 0 && buffer[res-1] != '\0' && len < PAGE_SIZE) {
		len = strnlen(buffer, res);
		if (len < res) {
		    res = len;
		} else {
			len = mm->env_end - mm->env_start;
			if (len > PAGE_SIZE - res)
				len = PAGE_SIZE - res;
			res += access_process_vm(task, mm->env_start, buffer+res, len, 0);
			res = strnlen(buffer, res);
		}
	}
out_mm:
	mmput(mm);
out:
	return res;
}

static int proc_pid_auxv(struct task_struct *task, char *buffer)
{
	int res = 0;
	struct mm_struct *mm = get_task_mm(task);
	if (mm) {
		unsigned int nwords = 0;
		do
			nwords += 2;
		while (mm->saved_auxv[nwords - 2] != 0); /* AT_NULL */
		res = nwords * sizeof(mm->saved_auxv[0]);
		if (res > PAGE_SIZE)
			res = PAGE_SIZE;
		memcpy(buffer, mm->saved_auxv, res);
		mmput(mm);
	}
	return res;
}


#ifdef CONFIG_KALLSYMS
/*
 * Provides a wchan file via kallsyms in a proper one-value-per-file format.
 * Returns the resolved symbol.  If that fails, simply return the address.
 */
static int proc_pid_wchan(struct task_struct *task, char *buffer)
{
	char *modname;
	const char *sym_name;
	unsigned long wchan, size, offset;
	char namebuf[KSYM_NAME_LEN+1];

	wchan = get_wchan(task);

	sym_name = kallsyms_lookup(wchan, &size, &offset, &modname, namebuf);
	if (sym_name)
		return sprintf(buffer, "%s", sym_name);
	return sprintf(buffer, "%lu", wchan);
}
#endif /* CONFIG_KALLSYMS */

#ifdef CONFIG_SCHEDSTATS
/*
 * Provides /proc/PID/schedstat
 */
static int proc_pid_schedstat(struct task_struct *task, char *buffer)
{
	return sprintf(buffer, "%lu %lu %lu\n",
			task->sched_info.cpu_time,
			task->sched_info.run_delay,
			task->sched_info.pcnt);
}
#endif

/* The badness from the OOM killer */
unsigned long badness(struct task_struct *p, unsigned long uptime);
static int proc_oom_score(struct task_struct *task, char *buffer)
{
	unsigned long points;
	struct timespec uptime;

	do_posix_clock_monotonic_gettime(&uptime);
	points = badness(task, uptime.tv_sec);
	return sprintf(buffer, "%lu\n", points);
}

/************************************************************************/
/*                       Here the fs part begins                        */
/************************************************************************/

/* permission checks */

505 506 507
/* If the process being read is separated by chroot from the reading process,
 * don't let the reader access the threads.
 */
508
static int proc_check_chroot(struct dentry *de, struct vfsmount *mnt)
L
Linus Torvalds 已提交
509
{
510 511
	struct dentry *base;
	struct vfsmount *our_vfsmnt;
L
Linus Torvalds 已提交
512
	int res = 0;
513

L
Linus Torvalds 已提交
514 515 516 517 518 519 520
	read_lock(&current->fs->lock);
	our_vfsmnt = mntget(current->fs->rootmnt);
	base = dget(current->fs->root);
	read_unlock(&current->fs->lock);

	spin_lock(&vfsmount_lock);

521 522
	while (mnt != our_vfsmnt) {
		if (mnt == mnt->mnt_parent)
L
Linus Torvalds 已提交
523
			goto out;
524 525
		de = mnt->mnt_mountpoint;
		mnt = mnt->mnt_parent;
L
Linus Torvalds 已提交
526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542
	}

	if (!is_subdir(de, base))
		goto out;
	spin_unlock(&vfsmount_lock);

exit:
	dput(base);
	mntput(our_vfsmnt);
	return res;
out:
	spin_unlock(&vfsmount_lock);
	res = -EACCES;
	goto exit;
}

extern struct seq_operations mounts_op;
A
Al Viro 已提交
543 544 545 546 547
struct proc_mounts {
	struct seq_file m;
	int event;
};

L
Linus Torvalds 已提交
548 549 550
static int mounts_open(struct inode *inode, struct file *file)
{
	struct task_struct *task = proc_task(inode);
A
Al Viro 已提交
551 552 553
	struct namespace *namespace;
	struct proc_mounts *p;
	int ret = -EINVAL;
L
Linus Torvalds 已提交
554

A
Al Viro 已提交
555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572
	task_lock(task);
	namespace = task->namespace;
	if (namespace)
		get_namespace(namespace);
	task_unlock(task);

	if (namespace) {
		ret = -ENOMEM;
		p = kmalloc(sizeof(struct proc_mounts), GFP_KERNEL);
		if (p) {
			file->private_data = &p->m;
			ret = seq_open(file, &mounts_op);
			if (!ret) {
				p->m.private = namespace;
				p->event = namespace->event;
				return 0;
			}
			kfree(p);
L
Linus Torvalds 已提交
573
		}
A
Al Viro 已提交
574
		put_namespace(namespace);
L
Linus Torvalds 已提交
575 576 577 578 579 580 581 582 583 584 585 586
	}
	return ret;
}

static int mounts_release(struct inode *inode, struct file *file)
{
	struct seq_file *m = file->private_data;
	struct namespace *namespace = m->private;
	put_namespace(namespace);
	return seq_release(inode, file);
}

A
Al Viro 已提交
587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604
static unsigned mounts_poll(struct file *file, poll_table *wait)
{
	struct proc_mounts *p = file->private_data;
	struct namespace *ns = p->m.private;
	unsigned res = 0;

	poll_wait(file, &ns->poll, wait);

	spin_lock(&vfsmount_lock);
	if (p->event != ns->event) {
		p->event = ns->event;
		res = POLLERR;
	}
	spin_unlock(&vfsmount_lock);

	return res;
}

L
Linus Torvalds 已提交
605 606 607 608 609
static struct file_operations proc_mounts_operations = {
	.open		= mounts_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= mounts_release,
A
Al Viro 已提交
610
	.poll		= mounts_poll,
L
Linus Torvalds 已提交
611 612
};

613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644
extern struct seq_operations mountstats_op;
static int mountstats_open(struct inode *inode, struct file *file)
{
	struct task_struct *task = proc_task(inode);
	int ret = seq_open(file, &mountstats_op);

	if (!ret) {
		struct seq_file *m = file->private_data;
		struct namespace *namespace;
		task_lock(task);
		namespace = task->namespace;
		if (namespace)
			get_namespace(namespace);
		task_unlock(task);

		if (namespace)
			m->private = namespace;
		else {
			seq_release(inode, file);
			ret = -EINVAL;
		}
	}
	return ret;
}

static struct file_operations proc_mountstats_operations = {
	.open		= mountstats_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= mounts_release,
};

L
Linus Torvalds 已提交
645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686
#define PROC_BLOCK_SIZE	(3*1024)		/* 4K page size but our output routines use some slack for overruns */

static ssize_t proc_info_read(struct file * file, char __user * buf,
			  size_t count, loff_t *ppos)
{
	struct inode * inode = file->f_dentry->d_inode;
	unsigned long page;
	ssize_t length;
	struct task_struct *task = proc_task(inode);

	if (count > PROC_BLOCK_SIZE)
		count = PROC_BLOCK_SIZE;
	if (!(page = __get_free_page(GFP_KERNEL)))
		return -ENOMEM;

	length = PROC_I(inode)->op.proc_read(task, (char*)page);

	if (length >= 0)
		length = simple_read_from_buffer(buf, count, ppos, (char *)page, length);
	free_page(page);
	return length;
}

static struct file_operations proc_info_file_operations = {
	.read		= proc_info_read,
};

static int mem_open(struct inode* inode, struct file* file)
{
	file->private_data = (void*)((long)current->self_exec_id);
	return 0;
}

static ssize_t mem_read(struct file * file, char __user * buf,
			size_t count, loff_t *ppos)
{
	struct task_struct *task = proc_task(file->f_dentry->d_inode);
	char *page;
	unsigned long src = *ppos;
	int ret = -ESRCH;
	struct mm_struct *mm;

687
	if (!MAY_PTRACE(task) || !ptrace_may_attach(task))
L
Linus Torvalds 已提交
688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712
		goto out;

	ret = -ENOMEM;
	page = (char *)__get_free_page(GFP_USER);
	if (!page)
		goto out;

	ret = 0;
 
	mm = get_task_mm(task);
	if (!mm)
		goto out_free;

	ret = -EIO;
 
	if (file->private_data != (void*)((long)current->self_exec_id))
		goto out_put;

	ret = 0;
 
	while (count > 0) {
		int this_len, retval;

		this_len = (count > PAGE_SIZE) ? PAGE_SIZE : count;
		retval = access_process_vm(task, src, page, this_len, 0);
713
		if (!retval || !MAY_PTRACE(task) || !ptrace_may_attach(task)) {
L
Linus Torvalds 已提交
714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750
			if (!ret)
				ret = -EIO;
			break;
		}

		if (copy_to_user(buf, page, retval)) {
			ret = -EFAULT;
			break;
		}
 
		ret += retval;
		src += retval;
		buf += retval;
		count -= retval;
	}
	*ppos = src;

out_put:
	mmput(mm);
out_free:
	free_page((unsigned long) page);
out:
	return ret;
}

#define mem_write NULL

#ifndef mem_write
/* This is a security hazard */
static ssize_t mem_write(struct file * file, const char * buf,
			 size_t count, loff_t *ppos)
{
	int copied = 0;
	char *page;
	struct task_struct *task = proc_task(file->f_dentry->d_inode);
	unsigned long dst = *ppos;

751
	if (!MAY_PTRACE(task) || !ptrace_may_attach(task))
L
Linus Torvalds 已提交
752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840
		return -ESRCH;

	page = (char *)__get_free_page(GFP_USER);
	if (!page)
		return -ENOMEM;

	while (count > 0) {
		int this_len, retval;

		this_len = (count > PAGE_SIZE) ? PAGE_SIZE : count;
		if (copy_from_user(page, buf, this_len)) {
			copied = -EFAULT;
			break;
		}
		retval = access_process_vm(task, dst, page, this_len, 1);
		if (!retval) {
			if (!copied)
				copied = -EIO;
			break;
		}
		copied += retval;
		buf += retval;
		dst += retval;
		count -= retval;			
	}
	*ppos = dst;
	free_page((unsigned long) page);
	return copied;
}
#endif

static loff_t mem_lseek(struct file * file, loff_t offset, int orig)
{
	switch (orig) {
	case 0:
		file->f_pos = offset;
		break;
	case 1:
		file->f_pos += offset;
		break;
	default:
		return -EINVAL;
	}
	force_successful_syscall_return();
	return file->f_pos;
}

static struct file_operations proc_mem_operations = {
	.llseek		= mem_lseek,
	.read		= mem_read,
	.write		= mem_write,
	.open		= mem_open,
};

static ssize_t oom_adjust_read(struct file *file, char __user *buf,
				size_t count, loff_t *ppos)
{
	struct task_struct *task = proc_task(file->f_dentry->d_inode);
	char buffer[8];
	size_t len;
	int oom_adjust = task->oomkilladj;
	loff_t __ppos = *ppos;

	len = sprintf(buffer, "%i\n", oom_adjust);
	if (__ppos >= len)
		return 0;
	if (count > len-__ppos)
		count = len-__ppos;
	if (copy_to_user(buf, buffer + __ppos, count))
		return -EFAULT;
	*ppos = __ppos + count;
	return count;
}

static ssize_t oom_adjust_write(struct file *file, const char __user *buf,
				size_t count, loff_t *ppos)
{
	struct task_struct *task = proc_task(file->f_dentry->d_inode);
	char buffer[8], *end;
	int oom_adjust;

	if (!capable(CAP_SYS_RESOURCE))
		return -EPERM;
	memset(buffer, 0, 8);
	if (count > 6)
		count = 6;
	if (copy_from_user(buffer, buf, count))
		return -EFAULT;
	oom_adjust = simple_strtol(buffer, &end, 0);
841
	if ((oom_adjust < -16 || oom_adjust > 15) && oom_adjust != OOM_DISABLE)
L
Linus Torvalds 已提交
842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885
		return -EINVAL;
	if (*end == '\n')
		end++;
	task->oomkilladj = oom_adjust;
	if (end - buffer == 0)
		return -EIO;
	return end - buffer;
}

static struct file_operations proc_oom_adjust_operations = {
	.read		= oom_adjust_read,
	.write		= oom_adjust_write,
};

#ifdef CONFIG_AUDITSYSCALL
#define TMPBUFLEN 21
static ssize_t proc_loginuid_read(struct file * file, char __user * buf,
				  size_t count, loff_t *ppos)
{
	struct inode * inode = file->f_dentry->d_inode;
	struct task_struct *task = proc_task(inode);
	ssize_t length;
	char tmpbuf[TMPBUFLEN];

	length = scnprintf(tmpbuf, TMPBUFLEN, "%u",
				audit_get_loginuid(task->audit_context));
	return simple_read_from_buffer(buf, count, ppos, tmpbuf, length);
}

static ssize_t proc_loginuid_write(struct file * file, const char __user * buf,
				   size_t count, loff_t *ppos)
{
	struct inode * inode = file->f_dentry->d_inode;
	char *page, *tmp;
	ssize_t length;
	struct task_struct *task = proc_task(inode);
	uid_t loginuid;

	if (!capable(CAP_AUDIT_CONTROL))
		return -EPERM;

	if (current != task)
		return -EPERM;

886 887
	if (count >= PAGE_SIZE)
		count = PAGE_SIZE - 1;
L
Linus Torvalds 已提交
888 889 890 891 892 893 894 895 896 897 898 899

	if (*ppos != 0) {
		/* No partial writes. */
		return -EINVAL;
	}
	page = (char*)__get_free_page(GFP_USER);
	if (!page)
		return -ENOMEM;
	length = -EFAULT;
	if (copy_from_user(page, buf, count))
		goto out_free_page;

900
	page[count] = '\0';
L
Linus Torvalds 已提交
901 902 903 904 905 906
	loginuid = simple_strtoul(page, &tmp, 10);
	if (tmp == page) {
		length = -EINVAL;
		goto out_free_page;

	}
S
Steve Grubb 已提交
907
	length = audit_set_loginuid(task, loginuid);
L
Linus Torvalds 已提交
908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976
	if (likely(length == 0))
		length = count;

out_free_page:
	free_page((unsigned long) page);
	return length;
}

static struct file_operations proc_loginuid_operations = {
	.read		= proc_loginuid_read,
	.write		= proc_loginuid_write,
};
#endif

#ifdef CONFIG_SECCOMP
static ssize_t seccomp_read(struct file *file, char __user *buf,
			    size_t count, loff_t *ppos)
{
	struct task_struct *tsk = proc_task(file->f_dentry->d_inode);
	char __buf[20];
	loff_t __ppos = *ppos;
	size_t len;

	/* no need to print the trailing zero, so use only len */
	len = sprintf(__buf, "%u\n", tsk->seccomp.mode);
	if (__ppos >= len)
		return 0;
	if (count > len - __ppos)
		count = len - __ppos;
	if (copy_to_user(buf, __buf + __ppos, count))
		return -EFAULT;
	*ppos = __ppos + count;
	return count;
}

static ssize_t seccomp_write(struct file *file, const char __user *buf,
			     size_t count, loff_t *ppos)
{
	struct task_struct *tsk = proc_task(file->f_dentry->d_inode);
	char __buf[20], *end;
	unsigned int seccomp_mode;

	/* can set it only once to be even more secure */
	if (unlikely(tsk->seccomp.mode))
		return -EPERM;

	memset(__buf, 0, sizeof(__buf));
	count = min(count, sizeof(__buf) - 1);
	if (copy_from_user(__buf, buf, count))
		return -EFAULT;
	seccomp_mode = simple_strtoul(__buf, &end, 0);
	if (*end == '\n')
		end++;
	if (seccomp_mode && seccomp_mode <= NR_SECCOMP_MODES) {
		tsk->seccomp.mode = seccomp_mode;
		set_tsk_thread_flag(tsk, TIF_SECCOMP);
	} else
		return -EINVAL;
	if (unlikely(!(end - __buf)))
		return -EIO;
	return end - __buf;
}

static struct file_operations proc_seccomp_operations = {
	.read		= seccomp_read,
	.write		= seccomp_write,
};
#endif /* CONFIG_SECCOMP */

977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018
static int proc_check_dentry_visible(struct inode *inode,
	struct dentry *dentry, struct vfsmount *mnt)
{
	/* Verify that the current process can already see the
	 * file pointed at by the file descriptor.
	 * This prevents /proc from being an accidental information leak.
	 *
	 * This prevents access to files that are not visible do to
	 * being on the otherside of a chroot, in a different
	 * namespace, or are simply process local (like pipes).
	 */
	struct task_struct *task;
	struct files_struct *task_files, *files;
	int error = -EACCES;

	/* See if the the two tasks share a commone set of
	 * file descriptors.  If so everything is visible.
	 */
	task = proc_task(inode);
	if (!task)
		goto out;
	files = get_files_struct(current);
	task_files = get_files_struct(task);
	if (files && task_files && (files == task_files))
		error = 0;
	if (task_files)
		put_files_struct(task_files);
	if (files)
		put_files_struct(files);
	if (!error)
		goto out;

	/* If the two tasks don't share a common set of file
	 * descriptors see if the destination dentry is already
	 * visible in the current tasks filesystem namespace.
	 */
	error = proc_check_chroot(dentry, mnt);
out:
	return error;

}

1019
static void *proc_pid_follow_link(struct dentry *dentry, struct nameidata *nd)
L
Linus Torvalds 已提交
1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031
{
	struct inode *inode = dentry->d_inode;
	int error = -EACCES;

	/* We don't need a base pointer in the /proc filesystem */
	path_release(nd);

	if (current->fsuid != inode->i_uid && !capable(CAP_DAC_OVERRIDE))
		goto out;

	error = PROC_I(inode)->op.proc_get_link(inode, &nd->dentry, &nd->mnt);
	nd->last_type = LAST_BIND;
1032 1033 1034 1035 1036 1037 1038
	if (error)
		goto out;

	/* Only return files this task can already see */
	error = proc_check_dentry_visible(inode, nd->dentry, nd->mnt);
	if (error)
		path_release(nd);
L
Linus Torvalds 已提交
1039
out:
1040
	return ERR_PTR(error);
L
Linus Torvalds 已提交
1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083
}

static int do_proc_readlink(struct dentry *dentry, struct vfsmount *mnt,
			    char __user *buffer, int buflen)
{
	struct inode * inode;
	char *tmp = (char*)__get_free_page(GFP_KERNEL), *path;
	int len;

	if (!tmp)
		return -ENOMEM;
		
	inode = dentry->d_inode;
	path = d_path(dentry, mnt, tmp, PAGE_SIZE);
	len = PTR_ERR(path);
	if (IS_ERR(path))
		goto out;
	len = tmp + PAGE_SIZE - 1 - path;

	if (len > buflen)
		len = buflen;
	if (copy_to_user(buffer, path, len))
		len = -EFAULT;
 out:
	free_page((unsigned long)tmp);
	return len;
}

static int proc_pid_readlink(struct dentry * dentry, char __user * buffer, int buflen)
{
	int error = -EACCES;
	struct inode *inode = dentry->d_inode;
	struct dentry *de;
	struct vfsmount *mnt = NULL;


	if (current->fsuid != inode->i_uid && !capable(CAP_DAC_OVERRIDE))
		goto out;

	error = PROC_I(inode)->op.proc_get_link(inode, &de, &mnt);
	if (error)
		goto out;

1084 1085 1086 1087 1088
	/* Only return files this task can already see */
	error = proc_check_dentry_visible(inode, de, mnt);
	if (error)
		goto out_put;

L
Linus Torvalds 已提交
1089
	error = do_proc_readlink(de, mnt, buffer, buflen);
1090
out_put:
L
Linus Torvalds 已提交
1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105
	dput(de);
	mntput(mnt);
out:
	return error;
}

static struct inode_operations proc_pid_link_inode_operations = {
	.readlink	= proc_pid_readlink,
	.follow_link	= proc_pid_follow_link
};

#define NUMBUF 10

static int proc_readfd(struct file * filp, void * dirent, filldir_t filldir)
{
1106 1107
	struct dentry *dentry = filp->f_dentry;
	struct inode *inode = dentry->d_inode;
L
Linus Torvalds 已提交
1108 1109 1110 1111 1112
	struct task_struct *p = proc_task(inode);
	unsigned int fd, tid, ino;
	int retval;
	char buf[NUMBUF];
	struct files_struct * files;
1113
	struct fdtable *fdt;
L
Linus Torvalds 已提交
1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127

	retval = -ENOENT;
	if (!pid_alive(p))
		goto out;
	retval = 0;
	tid = p->pid;

	fd = filp->f_pos;
	switch (fd) {
		case 0:
			if (filldir(dirent, ".", 1, 0, inode->i_ino, DT_DIR) < 0)
				goto out;
			filp->f_pos++;
		case 1:
1128
			ino = parent_ino(dentry);
L
Linus Torvalds 已提交
1129 1130 1131 1132 1133 1134 1135
			if (filldir(dirent, "..", 2, 1, ino, DT_DIR) < 0)
				goto out;
			filp->f_pos++;
		default:
			files = get_files_struct(p);
			if (!files)
				goto out;
1136
			rcu_read_lock();
1137
			fdt = files_fdtable(files);
L
Linus Torvalds 已提交
1138
			for (fd = filp->f_pos-2;
1139
			     fd < fdt->max_fds;
L
Linus Torvalds 已提交
1140 1141 1142 1143 1144
			     fd++, filp->f_pos++) {
				unsigned int i,j;

				if (!fcheck_files(files, fd))
					continue;
1145
				rcu_read_unlock();
L
Linus Torvalds 已提交
1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156

				j = NUMBUF;
				i = fd;
				do {
					j--;
					buf[j] = '0' + (i % 10);
					i /= 10;
				} while (i);

				ino = fake_ino(tid, PROC_TID_FD_DIR + fd);
				if (filldir(dirent, buf+j, NUMBUF-j, fd+2, ino, DT_LNK) < 0) {
1157
					rcu_read_lock();
L
Linus Torvalds 已提交
1158 1159
					break;
				}
1160
				rcu_read_lock();
L
Linus Torvalds 已提交
1161
			}
1162
			rcu_read_unlock();
L
Linus Torvalds 已提交
1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249
			put_files_struct(files);
	}
out:
	return retval;
}

static int proc_pident_readdir(struct file *filp,
		void *dirent, filldir_t filldir,
		struct pid_entry *ents, unsigned int nents)
{
	int i;
	int pid;
	struct dentry *dentry = filp->f_dentry;
	struct inode *inode = dentry->d_inode;
	struct pid_entry *p;
	ino_t ino;
	int ret;

	ret = -ENOENT;
	if (!pid_alive(proc_task(inode)))
		goto out;

	ret = 0;
	pid = proc_task(inode)->pid;
	i = filp->f_pos;
	switch (i) {
	case 0:
		ino = inode->i_ino;
		if (filldir(dirent, ".", 1, i, ino, DT_DIR) < 0)
			goto out;
		i++;
		filp->f_pos++;
		/* fall through */
	case 1:
		ino = parent_ino(dentry);
		if (filldir(dirent, "..", 2, i, ino, DT_DIR) < 0)
			goto out;
		i++;
		filp->f_pos++;
		/* fall through */
	default:
		i -= 2;
		if (i >= nents) {
			ret = 1;
			goto out;
		}
		p = ents + i;
		while (p->name) {
			if (filldir(dirent, p->name, p->len, filp->f_pos,
				    fake_ino(pid, p->type), p->mode >> 12) < 0)
				goto out;
			filp->f_pos++;
			p++;
		}
	}

	ret = 1;
out:
	return ret;
}

static int proc_tgid_base_readdir(struct file * filp,
			     void * dirent, filldir_t filldir)
{
	return proc_pident_readdir(filp,dirent,filldir,
				   tgid_base_stuff,ARRAY_SIZE(tgid_base_stuff));
}

static int proc_tid_base_readdir(struct file * filp,
			     void * dirent, filldir_t filldir)
{
	return proc_pident_readdir(filp,dirent,filldir,
				   tid_base_stuff,ARRAY_SIZE(tid_base_stuff));
}

/* building an inode */

static int task_dumpable(struct task_struct *task)
{
	int dumpable = 0;
	struct mm_struct *mm;

	task_lock(task);
	mm = task->mm;
	if (mm)
		dumpable = mm->dumpable;
	task_unlock(task);
A
Alan Cox 已提交
1250 1251 1252
	if(dumpable == 1)
		return 1;
	return 0;
L
Linus Torvalds 已提交
1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281
}


static struct inode *proc_pid_make_inode(struct super_block * sb, struct task_struct *task, int ino)
{
	struct inode * inode;
	struct proc_inode *ei;

	/* We need a new inode */
	
	inode = new_inode(sb);
	if (!inode)
		goto out;

	/* Common stuff */
	ei = PROC_I(inode);
	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
	inode->i_ino = fake_ino(task->pid, ino);

	if (!pid_alive(task))
		goto out_unlock;

	/*
	 * grab the reference to task.
	 */
	get_task_struct(task);
	ei->task = task;
	inode->i_uid = 0;
	inode->i_gid = 0;
1282
	if (task_dumpable(task)) {
L
Linus Torvalds 已提交
1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310
		inode->i_uid = task->euid;
		inode->i_gid = task->egid;
	}
	security_task_to_inode(task, inode);

out:
	return inode;

out_unlock:
	iput(inode);
	return NULL;
}

/* dentry stuff */

/*
 *	Exceptional case: normally we are not allowed to unhash a busy
 * directory. In this case, however, we can do it - no aliasing problems
 * due to the way we treat inodes.
 *
 * Rewrite the inode's ownerships here because the owning task may have
 * performed a setuid(), etc.
 */
static int pid_revalidate(struct dentry *dentry, struct nameidata *nd)
{
	struct inode *inode = dentry->d_inode;
	struct task_struct *task = proc_task(inode);
	if (pid_alive(task)) {
1311
		if (task_dumpable(task)) {
L
Linus Torvalds 已提交
1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328
			inode->i_uid = task->euid;
			inode->i_gid = task->egid;
		} else {
			inode->i_uid = 0;
			inode->i_gid = 0;
		}
		security_task_to_inode(task, inode);
		return 1;
	}
	d_drop(dentry);
	return 0;
}

static int tid_fd_revalidate(struct dentry *dentry, struct nameidata *nd)
{
	struct inode *inode = dentry->d_inode;
	struct task_struct *task = proc_task(inode);
1329
	int fd = proc_fd(inode);
L
Linus Torvalds 已提交
1330 1331 1332 1333
	struct files_struct *files;

	files = get_files_struct(task);
	if (files) {
1334
		rcu_read_lock();
L
Linus Torvalds 已提交
1335
		if (fcheck_files(files, fd)) {
1336
			rcu_read_unlock();
L
Linus Torvalds 已提交
1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347
			put_files_struct(files);
			if (task_dumpable(task)) {
				inode->i_uid = task->euid;
				inode->i_gid = task->egid;
			} else {
				inode->i_uid = 0;
				inode->i_gid = 0;
			}
			security_task_to_inode(task, inode);
			return 1;
		}
1348
		rcu_read_unlock();
L
Linus Torvalds 已提交
1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404
		put_files_struct(files);
	}
	d_drop(dentry);
	return 0;
}

static int pid_delete_dentry(struct dentry * dentry)
{
	/* Is the task we represent dead?
	 * If so, then don't put the dentry on the lru list,
	 * kill it immediately.
	 */
	return !pid_alive(proc_task(dentry->d_inode));
}

static struct dentry_operations tid_fd_dentry_operations =
{
	.d_revalidate	= tid_fd_revalidate,
	.d_delete	= pid_delete_dentry,
};

static struct dentry_operations pid_dentry_operations =
{
	.d_revalidate	= pid_revalidate,
	.d_delete	= pid_delete_dentry,
};

/* Lookups */

static unsigned name_to_int(struct dentry *dentry)
{
	const char *name = dentry->d_name.name;
	int len = dentry->d_name.len;
	unsigned n = 0;

	if (len > 1 && *name == '0')
		goto out;
	while (len-- > 0) {
		unsigned c = *name++ - '0';
		if (c > 9)
			goto out;
		if (n >= (~0U-9)/10)
			goto out;
		n *= 10;
		n += c;
	}
	return n;
out:
	return ~0U;
}

/* SMP-safe */
static struct dentry *proc_lookupfd(struct inode * dir, struct dentry * dentry, struct nameidata *nd)
{
	struct task_struct *task = proc_task(dir);
	unsigned fd = name_to_int(dentry);
1405
	struct dentry *result = ERR_PTR(-ENOENT);
L
Linus Torvalds 已提交
1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419
	struct file * file;
	struct files_struct * files;
	struct inode *inode;
	struct proc_inode *ei;

	if (fd == ~0U)
		goto out;
	if (!pid_alive(task))
		goto out;

	inode = proc_pid_make_inode(dir->i_sb, task, PROC_TID_FD_DIR+fd);
	if (!inode)
		goto out;
	ei = PROC_I(inode);
1420
	ei->fd = fd;
L
Linus Torvalds 已提交
1421 1422 1423 1424
	files = get_files_struct(task);
	if (!files)
		goto out_unlock;
	inode->i_mode = S_IFLNK;
1425 1426 1427 1428 1429 1430

	/*
	 * We are not taking a ref to the file structure, so we must
	 * hold ->file_lock.
	 */
	spin_lock(&files->file_lock);
L
Linus Torvalds 已提交
1431 1432 1433 1434 1435 1436 1437
	file = fcheck_files(files, fd);
	if (!file)
		goto out_unlock2;
	if (file->f_mode & 1)
		inode->i_mode |= S_IRUSR | S_IXUSR;
	if (file->f_mode & 2)
		inode->i_mode |= S_IWUSR | S_IXUSR;
1438
	spin_unlock(&files->file_lock);
L
Linus Torvalds 已提交
1439 1440 1441 1442 1443 1444
	put_files_struct(files);
	inode->i_op = &proc_pid_link_inode_operations;
	inode->i_size = 64;
	ei->op.proc_get_link = proc_fd_link;
	dentry->d_op = &tid_fd_dentry_operations;
	d_add(dentry, inode);
1445 1446 1447 1448 1449
	/* Close the race of the process dying before we return the dentry */
	if (tid_fd_revalidate(dentry, NULL))
		result = NULL;
out:
	return result;
L
Linus Torvalds 已提交
1450 1451

out_unlock2:
1452
	spin_unlock(&files->file_lock);
L
Linus Torvalds 已提交
1453 1454 1455
	put_files_struct(files);
out_unlock:
	iput(inode);
1456
	goto out;
L
Linus Torvalds 已提交
1457 1458 1459 1460
}

static int proc_task_readdir(struct file * filp, void * dirent, filldir_t filldir);
static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd);
1461
static int proc_task_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat);
L
Linus Torvalds 已提交
1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481

static struct file_operations proc_fd_operations = {
	.read		= generic_read_dir,
	.readdir	= proc_readfd,
};

static struct file_operations proc_task_operations = {
	.read		= generic_read_dir,
	.readdir	= proc_task_readdir,
};

/*
 * proc directories can do almost nothing..
 */
static struct inode_operations proc_fd_inode_operations = {
	.lookup		= proc_lookupfd,
};

static struct inode_operations proc_task_inode_operations = {
	.lookup		= proc_task_lookup,
1482
	.getattr	= proc_task_getattr,
L
Linus Torvalds 已提交
1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553
};

#ifdef CONFIG_SECURITY
static ssize_t proc_pid_attr_read(struct file * file, char __user * buf,
				  size_t count, loff_t *ppos)
{
	struct inode * inode = file->f_dentry->d_inode;
	unsigned long page;
	ssize_t length;
	struct task_struct *task = proc_task(inode);

	if (count > PAGE_SIZE)
		count = PAGE_SIZE;
	if (!(page = __get_free_page(GFP_KERNEL)))
		return -ENOMEM;

	length = security_getprocattr(task, 
				      (char*)file->f_dentry->d_name.name, 
				      (void*)page, count);
	if (length >= 0)
		length = simple_read_from_buffer(buf, count, ppos, (char *)page, length);
	free_page(page);
	return length;
}

static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf,
				   size_t count, loff_t *ppos)
{ 
	struct inode * inode = file->f_dentry->d_inode;
	char *page; 
	ssize_t length; 
	struct task_struct *task = proc_task(inode); 

	if (count > PAGE_SIZE) 
		count = PAGE_SIZE; 
	if (*ppos != 0) {
		/* No partial writes. */
		return -EINVAL;
	}
	page = (char*)__get_free_page(GFP_USER); 
	if (!page) 
		return -ENOMEM;
	length = -EFAULT; 
	if (copy_from_user(page, buf, count)) 
		goto out;

	length = security_setprocattr(task, 
				      (char*)file->f_dentry->d_name.name, 
				      (void*)page, count);
out:
	free_page((unsigned long) page);
	return length;
} 

static struct file_operations proc_pid_attr_operations = {
	.read		= proc_pid_attr_read,
	.write		= proc_pid_attr_write,
};

static struct file_operations proc_tid_attr_operations;
static struct inode_operations proc_tid_attr_inode_operations;
static struct file_operations proc_tgid_attr_operations;
static struct inode_operations proc_tgid_attr_inode_operations;
#endif

/* SMP-safe */
static struct dentry *proc_pident_lookup(struct inode *dir, 
					 struct dentry *dentry,
					 struct pid_entry *ents)
{
	struct inode *inode;
1554
	struct dentry *error;
L
Linus Torvalds 已提交
1555 1556 1557 1558
	struct task_struct *task = proc_task(dir);
	struct pid_entry *p;
	struct proc_inode *ei;

1559
	error = ERR_PTR(-ENOENT);
L
Linus Torvalds 已提交
1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573
	inode = NULL;

	if (!pid_alive(task))
		goto out;

	for (p = ents; p->name; p++) {
		if (p->len != dentry->d_name.len)
			continue;
		if (!memcmp(dentry->d_name.name, p->name, p->len))
			break;
	}
	if (!p->name)
		goto out;

1574
	error = ERR_PTR(-EINVAL);
L
Linus Torvalds 已提交
1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586
	inode = proc_pid_make_inode(dir->i_sb, task, p->type);
	if (!inode)
		goto out;

	ei = PROC_I(inode);
	inode->i_mode = p->mode;
	/*
	 * Yes, it does not scale. And it should not. Don't add
	 * new entries into /proc/<tgid>/ without very good reasons.
	 */
	switch(p->type) {
		case PROC_TGID_TASK:
1587
			inode->i_nlink = 2;
L
Linus Torvalds 已提交
1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648
			inode->i_op = &proc_task_inode_operations;
			inode->i_fop = &proc_task_operations;
			break;
		case PROC_TID_FD:
		case PROC_TGID_FD:
			inode->i_nlink = 2;
			inode->i_op = &proc_fd_inode_operations;
			inode->i_fop = &proc_fd_operations;
			break;
		case PROC_TID_EXE:
		case PROC_TGID_EXE:
			inode->i_op = &proc_pid_link_inode_operations;
			ei->op.proc_get_link = proc_exe_link;
			break;
		case PROC_TID_CWD:
		case PROC_TGID_CWD:
			inode->i_op = &proc_pid_link_inode_operations;
			ei->op.proc_get_link = proc_cwd_link;
			break;
		case PROC_TID_ROOT:
		case PROC_TGID_ROOT:
			inode->i_op = &proc_pid_link_inode_operations;
			ei->op.proc_get_link = proc_root_link;
			break;
		case PROC_TID_ENVIRON:
		case PROC_TGID_ENVIRON:
			inode->i_fop = &proc_info_file_operations;
			ei->op.proc_read = proc_pid_environ;
			break;
		case PROC_TID_AUXV:
		case PROC_TGID_AUXV:
			inode->i_fop = &proc_info_file_operations;
			ei->op.proc_read = proc_pid_auxv;
			break;
		case PROC_TID_STATUS:
		case PROC_TGID_STATUS:
			inode->i_fop = &proc_info_file_operations;
			ei->op.proc_read = proc_pid_status;
			break;
		case PROC_TID_STAT:
			inode->i_fop = &proc_info_file_operations;
			ei->op.proc_read = proc_tid_stat;
			break;
		case PROC_TGID_STAT:
			inode->i_fop = &proc_info_file_operations;
			ei->op.proc_read = proc_tgid_stat;
			break;
		case PROC_TID_CMDLINE:
		case PROC_TGID_CMDLINE:
			inode->i_fop = &proc_info_file_operations;
			ei->op.proc_read = proc_pid_cmdline;
			break;
		case PROC_TID_STATM:
		case PROC_TGID_STATM:
			inode->i_fop = &proc_info_file_operations;
			ei->op.proc_read = proc_pid_statm;
			break;
		case PROC_TID_MAPS:
		case PROC_TGID_MAPS:
			inode->i_fop = &proc_maps_operations;
			break;
1649 1650 1651 1652 1653 1654
#ifdef CONFIG_NUMA
		case PROC_TID_NUMA_MAPS:
		case PROC_TGID_NUMA_MAPS:
			inode->i_fop = &proc_numa_maps_operations;
			break;
#endif
L
Linus Torvalds 已提交
1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668
		case PROC_TID_MEM:
		case PROC_TGID_MEM:
			inode->i_fop = &proc_mem_operations;
			break;
#ifdef CONFIG_SECCOMP
		case PROC_TID_SECCOMP:
		case PROC_TGID_SECCOMP:
			inode->i_fop = &proc_seccomp_operations;
			break;
#endif /* CONFIG_SECCOMP */
		case PROC_TID_MOUNTS:
		case PROC_TGID_MOUNTS:
			inode->i_fop = &proc_mounts_operations;
			break;
Y
Yoshinori Sato 已提交
1669
#ifdef CONFIG_MMU
M
Mauricio Lin 已提交
1670 1671 1672 1673
		case PROC_TID_SMAPS:
		case PROC_TGID_SMAPS:
			inode->i_fop = &proc_smaps_operations;
			break;
Y
Yoshinori Sato 已提交
1674
#endif
1675 1676 1677 1678
		case PROC_TID_MOUNTSTATS:
		case PROC_TGID_MOUNTSTATS:
			inode->i_fop = &proc_mountstats_operations;
			break;
L
Linus Torvalds 已提交
1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697
#ifdef CONFIG_SECURITY
		case PROC_TID_ATTR:
			inode->i_nlink = 2;
			inode->i_op = &proc_tid_attr_inode_operations;
			inode->i_fop = &proc_tid_attr_operations;
			break;
		case PROC_TGID_ATTR:
			inode->i_nlink = 2;
			inode->i_op = &proc_tgid_attr_inode_operations;
			inode->i_fop = &proc_tgid_attr_operations;
			break;
		case PROC_TID_ATTR_CURRENT:
		case PROC_TGID_ATTR_CURRENT:
		case PROC_TID_ATTR_PREV:
		case PROC_TGID_ATTR_PREV:
		case PROC_TID_ATTR_EXEC:
		case PROC_TGID_ATTR_EXEC:
		case PROC_TID_ATTR_FSCREATE:
		case PROC_TGID_ATTR_FSCREATE:
1698 1699
		case PROC_TID_ATTR_KEYCREATE:
		case PROC_TGID_ATTR_KEYCREATE:
L
Linus Torvalds 已提交
1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740
			inode->i_fop = &proc_pid_attr_operations;
			break;
#endif
#ifdef CONFIG_KALLSYMS
		case PROC_TID_WCHAN:
		case PROC_TGID_WCHAN:
			inode->i_fop = &proc_info_file_operations;
			ei->op.proc_read = proc_pid_wchan;
			break;
#endif
#ifdef CONFIG_SCHEDSTATS
		case PROC_TID_SCHEDSTAT:
		case PROC_TGID_SCHEDSTAT:
			inode->i_fop = &proc_info_file_operations;
			ei->op.proc_read = proc_pid_schedstat;
			break;
#endif
#ifdef CONFIG_CPUSETS
		case PROC_TID_CPUSET:
		case PROC_TGID_CPUSET:
			inode->i_fop = &proc_cpuset_operations;
			break;
#endif
		case PROC_TID_OOM_SCORE:
		case PROC_TGID_OOM_SCORE:
			inode->i_fop = &proc_info_file_operations;
			ei->op.proc_read = proc_oom_score;
			break;
		case PROC_TID_OOM_ADJUST:
		case PROC_TGID_OOM_ADJUST:
			inode->i_fop = &proc_oom_adjust_operations;
			break;
#ifdef CONFIG_AUDITSYSCALL
		case PROC_TID_LOGINUID:
		case PROC_TGID_LOGINUID:
			inode->i_fop = &proc_loginuid_operations;
			break;
#endif
		default:
			printk("procfs: impossible type (%d)",p->type);
			iput(inode);
1741 1742
			error = ERR_PTR(-EINVAL);
			goto out;
L
Linus Torvalds 已提交
1743 1744 1745
	}
	dentry->d_op = &pid_dentry_operations;
	d_add(dentry, inode);
1746 1747 1748
	/* Close the race of the process dying before we return the dentry */
	if (pid_revalidate(dentry, NULL))
		error = NULL;
L
Linus Torvalds 已提交
1749
out:
1750
	return error;
L
Linus Torvalds 已提交
1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835
}

static struct dentry *proc_tgid_base_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd){
	return proc_pident_lookup(dir, dentry, tgid_base_stuff);
}

static struct dentry *proc_tid_base_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd){
	return proc_pident_lookup(dir, dentry, tid_base_stuff);
}

static struct file_operations proc_tgid_base_operations = {
	.read		= generic_read_dir,
	.readdir	= proc_tgid_base_readdir,
};

static struct file_operations proc_tid_base_operations = {
	.read		= generic_read_dir,
	.readdir	= proc_tid_base_readdir,
};

static struct inode_operations proc_tgid_base_inode_operations = {
	.lookup		= proc_tgid_base_lookup,
};

static struct inode_operations proc_tid_base_inode_operations = {
	.lookup		= proc_tid_base_lookup,
};

#ifdef CONFIG_SECURITY
static int proc_tgid_attr_readdir(struct file * filp,
			     void * dirent, filldir_t filldir)
{
	return proc_pident_readdir(filp,dirent,filldir,
				   tgid_attr_stuff,ARRAY_SIZE(tgid_attr_stuff));
}

static int proc_tid_attr_readdir(struct file * filp,
			     void * dirent, filldir_t filldir)
{
	return proc_pident_readdir(filp,dirent,filldir,
				   tid_attr_stuff,ARRAY_SIZE(tid_attr_stuff));
}

static struct file_operations proc_tgid_attr_operations = {
	.read		= generic_read_dir,
	.readdir	= proc_tgid_attr_readdir,
};

static struct file_operations proc_tid_attr_operations = {
	.read		= generic_read_dir,
	.readdir	= proc_tid_attr_readdir,
};

static struct dentry *proc_tgid_attr_lookup(struct inode *dir,
				struct dentry *dentry, struct nameidata *nd)
{
	return proc_pident_lookup(dir, dentry, tgid_attr_stuff);
}

static struct dentry *proc_tid_attr_lookup(struct inode *dir,
				struct dentry *dentry, struct nameidata *nd)
{
	return proc_pident_lookup(dir, dentry, tid_attr_stuff);
}

static struct inode_operations proc_tgid_attr_inode_operations = {
	.lookup		= proc_tgid_attr_lookup,
};

static struct inode_operations proc_tid_attr_inode_operations = {
	.lookup		= proc_tid_attr_lookup,
};
#endif

/*
 * /proc/self:
 */
static int proc_self_readlink(struct dentry *dentry, char __user *buffer,
			      int buflen)
{
	char tmp[30];
	sprintf(tmp, "%d", current->tgid);
	return vfs_readlink(dentry,buffer,buflen,tmp);
}

1836
static void *proc_self_follow_link(struct dentry *dentry, struct nameidata *nd)
L
Linus Torvalds 已提交
1837 1838 1839
{
	char tmp[30];
	sprintf(tmp, "%d", current->tgid);
1840
	return ERR_PTR(vfs_follow_link(nd,tmp));
L
Linus Torvalds 已提交
1841 1842 1843 1844 1845 1846 1847 1848
}	

static struct inode_operations proc_self_inode_operations = {
	.readlink	= proc_self_readlink,
	.follow_link	= proc_self_follow_link,
};

/**
1849 1850 1851 1852 1853 1854 1855 1856 1857
 * proc_flush_task -  Remove dcache entries for @task from the /proc dcache.
 *
 * @task: task that should be flushed.
 *
 * Looks in the dcache for
 * /proc/@pid
 * /proc/@tgid/task/@pid
 * if either directory is present flushes it and all of it'ts children
 * from the dcache.
L
Linus Torvalds 已提交
1858
 *
1859 1860 1861 1862 1863
 * It is safe and reasonable to cache /proc entries for a task until
 * that task exits.  After that they just clog up the dcache with
 * useless entries, possibly causing useful dcache entries to be
 * flushed instead.  This routine is proved to flush those useless
 * dcache entries at process exit time.
L
Linus Torvalds 已提交
1864
 *
1865 1866 1867
 * NOTE: This routine is just an optimization so it does not guarantee
 *       that no dcache entries will exist at process exit time it
 *       just makes it very unlikely that any will persist.
L
Linus Torvalds 已提交
1868
 */
1869
void proc_flush_task(struct task_struct *task)
L
Linus Torvalds 已提交
1870
{
1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882
	struct dentry *dentry, *leader, *dir;
	char buf[30];
	struct qstr name;

	name.name = buf;
	name.len = snprintf(buf, sizeof(buf), "%d", task->pid);
	dentry = d_hash_and_lookup(proc_mnt->mnt_root, &name);
	if (dentry) {
		shrink_dcache_parent(dentry);
		d_drop(dentry);
		dput(dentry);
	}
L
Linus Torvalds 已提交
1883

1884 1885
	if (thread_group_leader(task))
		goto out;
L
Linus Torvalds 已提交
1886

1887 1888 1889 1890 1891
	name.name = buf;
	name.len = snprintf(buf, sizeof(buf), "%d", task->tgid);
	leader = d_hash_and_lookup(proc_mnt->mnt_root, &name);
	if (!leader)
		goto out;
L
Linus Torvalds 已提交
1892

1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905
	name.name = "task";
	name.len = strlen(name.name);
	dir = d_hash_and_lookup(leader, &name);
	if (!dir)
		goto out_put_leader;

	name.name = buf;
	name.len = snprintf(buf, sizeof(buf), "%d", task->pid);
	dentry = d_hash_and_lookup(dir, &name);
	if (dentry) {
		shrink_dcache_parent(dentry);
		d_drop(dentry);
		dput(dentry);
L
Linus Torvalds 已提交
1906
	}
1907 1908 1909 1910 1911 1912

	dput(dir);
out_put_leader:
	dput(leader);
out:
	return;
L
Linus Torvalds 已提交
1913 1914 1915 1916 1917
}

/* SMP-safe */
struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd)
{
1918
	struct dentry *result = ERR_PTR(-ENOENT);
L
Linus Torvalds 已提交
1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942
	struct task_struct *task;
	struct inode *inode;
	struct proc_inode *ei;
	unsigned tgid;

	if (dentry->d_name.len == 4 && !memcmp(dentry->d_name.name,"self",4)) {
		inode = new_inode(dir->i_sb);
		if (!inode)
			return ERR_PTR(-ENOMEM);
		ei = PROC_I(inode);
		inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
		inode->i_ino = fake_ino(0, PROC_TGID_INO);
		ei->pde = NULL;
		inode->i_mode = S_IFLNK|S_IRWXUGO;
		inode->i_uid = inode->i_gid = 0;
		inode->i_size = 64;
		inode->i_op = &proc_self_inode_operations;
		d_add(dentry, inode);
		return NULL;
	}
	tgid = name_to_int(dentry);
	if (tgid == ~0U)
		goto out;

1943
	rcu_read_lock();
L
Linus Torvalds 已提交
1944 1945 1946
	task = find_task_by_pid(tgid);
	if (task)
		get_task_struct(task);
1947
	rcu_read_unlock();
L
Linus Torvalds 已提交
1948 1949 1950 1951
	if (!task)
		goto out;

	inode = proc_pid_make_inode(dir->i_sb, task, PROC_TGID_INO);
1952 1953
	if (!inode)
		goto out_put_task;
L
Linus Torvalds 已提交
1954 1955 1956 1957 1958

	inode->i_mode = S_IFDIR|S_IRUGO|S_IXUGO;
	inode->i_op = &proc_tgid_base_inode_operations;
	inode->i_fop = &proc_tgid_base_operations;
	inode->i_flags|=S_IMMUTABLE;
1959 1960 1961 1962 1963
#ifdef CONFIG_SECURITY
	inode->i_nlink = 5;
#else
	inode->i_nlink = 4;
#endif
L
Linus Torvalds 已提交
1964

1965
	dentry->d_op = &pid_dentry_operations;
L
Linus Torvalds 已提交
1966 1967

	d_add(dentry, inode);
1968 1969 1970
	/* Close the race of the process dying before we return the dentry */
	if (pid_revalidate(dentry, NULL))
		result = NULL;
L
Linus Torvalds 已提交
1971

1972
out_put_task:
L
Linus Torvalds 已提交
1973 1974
	put_task_struct(task);
out:
1975
	return result;
L
Linus Torvalds 已提交
1976 1977 1978 1979 1980
}

/* SMP-safe */
static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd)
{
1981
	struct dentry *result = ERR_PTR(-ENOENT);
L
Linus Torvalds 已提交
1982 1983 1984 1985 1986 1987 1988 1989 1990
	struct task_struct *task;
	struct task_struct *leader = proc_task(dir);
	struct inode *inode;
	unsigned tid;

	tid = name_to_int(dentry);
	if (tid == ~0U)
		goto out;

1991
	rcu_read_lock();
L
Linus Torvalds 已提交
1992 1993 1994
	task = find_task_by_pid(tid);
	if (task)
		get_task_struct(task);
1995
	rcu_read_unlock();
L
Linus Torvalds 已提交
1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009
	if (!task)
		goto out;
	if (leader->tgid != task->tgid)
		goto out_drop_task;

	inode = proc_pid_make_inode(dir->i_sb, task, PROC_TID_INO);


	if (!inode)
		goto out_drop_task;
	inode->i_mode = S_IFDIR|S_IRUGO|S_IXUGO;
	inode->i_op = &proc_tid_base_inode_operations;
	inode->i_fop = &proc_tid_base_operations;
	inode->i_flags|=S_IMMUTABLE;
2010 2011 2012 2013 2014
#ifdef CONFIG_SECURITY
	inode->i_nlink = 4;
#else
	inode->i_nlink = 3;
#endif
L
Linus Torvalds 已提交
2015

2016
	dentry->d_op = &pid_dentry_operations;
L
Linus Torvalds 已提交
2017 2018

	d_add(dentry, inode);
2019 2020 2021
	/* Close the race of the process dying before we return the dentry */
	if (pid_revalidate(dentry, NULL))
		result = NULL;
L
Linus Torvalds 已提交
2022 2023 2024 2025

out_drop_task:
	put_task_struct(task);
out:
2026
	return result;
L
Linus Torvalds 已提交
2027 2028 2029 2030 2031
}

#define PROC_NUMBUF 10

/*
2032 2033 2034 2035 2036 2037 2038 2039 2040 2041
 * Find the first tgid to return to user space.
 *
 * Usually this is just whatever follows &init_task, but if the users
 * buffer was too small to hold the full list or there was a seek into
 * the middle of the directory we have more work to do.
 *
 * In the case of a short read we start with find_task_by_pid.
 *
 * In the case of a seek we start with &init_task and walk nr
 * threads past it.
L
Linus Torvalds 已提交
2042
 */
2043
static struct task_struct *first_tgid(int tgid, unsigned int nr)
L
Linus Torvalds 已提交
2044
{
2045
	struct task_struct *pos;
2046
	rcu_read_lock();
2047 2048
	if (tgid && nr) {
		pos = find_task_by_pid(tgid);
2049 2050
		if (pos && thread_group_leader(pos))
			goto found;
L
Linus Torvalds 已提交
2051
	}
2052
	/* If nr exceeds the number of processes get out quickly */
2053
	pos = NULL;
2054 2055
	if (nr && nr >= nr_processes())
		goto done;
L
Linus Torvalds 已提交
2056

2057 2058 2059
	/* If we haven't found our starting place yet start with
	 * the init_task and walk nr tasks forward.
	 */
2060 2061 2062 2063 2064 2065
	for (pos = next_task(&init_task); nr > 0; --nr) {
		pos = next_task(pos);
		if (pos == &init_task) {
			pos = NULL;
			goto done;
		}
L
Linus Torvalds 已提交
2066
	}
2067 2068
found:
	get_task_struct(pos);
2069
done:
2070
	rcu_read_unlock();
2071
	return pos;
L
Linus Torvalds 已提交
2072 2073 2074
}

/*
2075 2076 2077 2078
 * Find the next task in the task list.
 * Return NULL if we loop or there is any error.
 *
 * The reference to the input task_struct is released.
L
Linus Torvalds 已提交
2079
 */
2080
static struct task_struct *next_tgid(struct task_struct *start)
L
Linus Torvalds 已提交
2081
{
2082
	struct task_struct *pos;
2083
	rcu_read_lock();
2084 2085 2086 2087 2088 2089 2090 2091 2092
	pos = start;
	if (pid_alive(start))
		pos = next_task(start);
	if (pid_alive(pos) && (pos != &init_task)) {
		get_task_struct(pos);
		goto done;
	}
	pos = NULL;
done:
2093
	rcu_read_unlock();
2094 2095
	put_task_struct(start);
	return pos;
L
Linus Torvalds 已提交
2096 2097 2098 2099 2100 2101 2102
}

/* for the /proc/ directory itself, after non-process stuff has been done */
int proc_pid_readdir(struct file * filp, void * dirent, filldir_t filldir)
{
	char buf[PROC_NUMBUF];
	unsigned int nr = filp->f_pos - FIRST_PROCESS_ENTRY;
2103 2104
	struct task_struct *task;
	int tgid;
L
Linus Torvalds 已提交
2105 2106 2107 2108 2109 2110 2111 2112

	if (!nr) {
		ino_t ino = fake_ino(0,PROC_TGID_INO);
		if (filldir(dirent, "self", 4, filp->f_pos, ino, DT_LNK) < 0)
			return 0;
		filp->f_pos++;
		nr++;
	}
2113
	nr -= 1;
L
Linus Torvalds 已提交
2114 2115 2116 2117

	/* f_version caches the tgid value that the last readdir call couldn't
	 * return. lseek aka telldir automagically resets f_version to 0.
	 */
2118
	tgid = filp->f_version;
L
Linus Torvalds 已提交
2119
	filp->f_version = 0;
2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132
	for (task = first_tgid(tgid, nr);
	     task;
	     task = next_tgid(task), filp->f_pos++) {
		int len;
		ino_t ino;
		tgid = task->pid;
		len = snprintf(buf, sizeof(buf), "%d", tgid);
		ino = fake_ino(tgid, PROC_TGID_INO);
		if (filldir(dirent, buf, len, filp->f_pos, ino, DT_DIR) < 0) {
			/* returning this tgid failed, save it as the first
			 * pid for the next readir call */
			filp->f_version = tgid;
			put_task_struct(task);
L
Linus Torvalds 已提交
2133 2134
			break;
		}
2135 2136 2137
	}
	return 0;
}
L
Linus Torvalds 已提交
2138

2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154
/*
 * Find the first tid of a thread group to return to user space.
 *
 * Usually this is just the thread group leader, but if the users
 * buffer was too small or there was a seek into the middle of the
 * directory we have more work todo.
 *
 * In the case of a short read we start with find_task_by_pid.
 *
 * In the case of a seek we start with the leader and walk nr
 * threads past it.
 */
static struct task_struct *first_tid(struct task_struct *leader, int tid, int nr)
{
	struct task_struct *pos = NULL;
	read_lock(&tasklist_lock);
L
Linus Torvalds 已提交
2155

2156 2157 2158 2159 2160 2161 2162 2163
	/* Attempt to start with the pid of a thread */
	if (tid && (nr > 0)) {
		pos = find_task_by_pid(tid);
		if (pos && (pos->group_leader != leader))
			pos = NULL;
		if (pos)
			nr = 0;
	}
L
Linus Torvalds 已提交
2164

2165 2166 2167 2168 2169 2170 2171 2172 2173 2174
	/* If nr exceeds the number of threads there is nothing todo */
	if (nr) {
		int threads = 0;
		task_lock(leader);
		if (leader->signal)
			threads = atomic_read(&leader->signal->count);
		task_unlock(leader);
		if (nr >= threads)
			goto done;
	}
L
Linus Torvalds 已提交
2175

2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186
	/* If we haven't found our starting place yet start with the
	 * leader and walk nr threads forward.
	 */
	if (!pos && (nr >= 0))
		pos = leader;

	for (; pos && pid_alive(pos); pos = next_thread(pos)) {
		if (--nr > 0)
			continue;
		get_task_struct(pos);
		goto done;
L
Linus Torvalds 已提交
2187
	}
2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213
	pos = NULL;
done:
	read_unlock(&tasklist_lock);
	return pos;
}

/*
 * Find the next thread in the thread list.
 * Return NULL if there is an error or no next thread.
 *
 * The reference to the input task_struct is released.
 */
static struct task_struct *next_tid(struct task_struct *start)
{
	struct task_struct *pos;
	read_lock(&tasklist_lock);
	pos = start;
	if (pid_alive(start))
		pos = next_thread(start);
	if (pid_alive(pos) && (pos != start->group_leader))
		get_task_struct(pos);
	else
		pos = NULL;
	read_unlock(&tasklist_lock);
	put_task_struct(start);
	return pos;
L
Linus Torvalds 已提交
2214 2215 2216 2217 2218 2219 2220 2221
}

/* for the /proc/TGID/task/ directories */
static int proc_task_readdir(struct file * filp, void * dirent, filldir_t filldir)
{
	char buf[PROC_NUMBUF];
	struct dentry *dentry = filp->f_dentry;
	struct inode *inode = dentry->d_inode;
2222 2223
	struct task_struct *leader = proc_task(inode);
	struct task_struct *task;
L
Linus Torvalds 已提交
2224 2225
	int retval = -ENOENT;
	ino_t ino;
2226
	int tid;
L
Linus Torvalds 已提交
2227 2228
	unsigned long pos = filp->f_pos;  /* avoiding "long long" filp->f_pos */

2229
	if (!pid_alive(leader))
L
Linus Torvalds 已提交
2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247
		goto out;
	retval = 0;

	switch (pos) {
	case 0:
		ino = inode->i_ino;
		if (filldir(dirent, ".", 1, pos, ino, DT_DIR) < 0)
			goto out;
		pos++;
		/* fall through */
	case 1:
		ino = parent_ino(dentry);
		if (filldir(dirent, "..", 2, pos, ino, DT_DIR) < 0)
			goto out;
		pos++;
		/* fall through */
	}

2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264
	/* f_version caches the tgid value that the last readdir call couldn't
	 * return. lseek aka telldir automagically resets f_version to 0.
	 */
	tid = filp->f_version;
	filp->f_version = 0;
	for (task = first_tid(leader, tid, pos - 2);
	     task;
	     task = next_tid(task), pos++) {
		int len;
		tid = task->pid;
		len = snprintf(buf, sizeof(buf), "%d", tid);
		ino = fake_ino(tid, PROC_TID_INO);
		if (filldir(dirent, buf, len, pos, ino, DT_DIR < 0)) {
			/* returning this tgid failed, save it as the first
			 * pid for the next readir call */
			filp->f_version = tid;
			put_task_struct(task);
L
Linus Torvalds 已提交
2265
			break;
2266
		}
L
Linus Torvalds 已提交
2267 2268 2269 2270 2271
	}
out:
	filp->f_pos = pos;
	return retval;
}
2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287

static int proc_task_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
{
	struct inode *inode = dentry->d_inode;
	struct task_struct *p = proc_task(inode);
	generic_fillattr(inode, stat);

	if (pid_alive(p)) {
		task_lock(p);
		if (p->signal)
			stat->nlink += atomic_read(&p->signal->count);
		task_unlock(p);
	}

	return 0;
}