auditsc.c 33.4 KB
Newer Older
1
/* auditsc.c -- System-call auditing support
L
Linus Torvalds 已提交
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
 * Handles all system-call specific auditing features.
 *
 * Copyright 2003-2004 Red Hat Inc., Durham, North Carolina.
 * All Rights Reserved.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 *
 * Written by Rickard E. (Rik) Faith <faith@redhat.com>
 *
 * Many of the ideas implemented here are from Stephen C. Tweedie,
 * especially the idea of avoiding a copy by using getname.
 *
 * The method for actual interception of syscall entry and exit (not in
 * this file -- see entry.S) is based on a GPL'd patch written by
 * okir@suse.de and Copyright 2003 SuSE Linux AG.
 *
 */

#include <linux/init.h>
#include <asm/types.h>
A
Alan Cox 已提交
34
#include <asm/atomic.h>
L
Linus Torvalds 已提交
35 36
#include <linux/mm.h>
#include <linux/module.h>
37
#include <linux/mount.h>
38
#include <linux/socket.h>
L
Linus Torvalds 已提交
39 40 41
#include <linux/audit.h>
#include <linux/personality.h>
#include <linux/time.h>
42
#include <linux/kthread.h>
43
#include <linux/netlink.h>
44
#include <linux/compiler.h>
L
Linus Torvalds 已提交
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
#include <asm/unistd.h>

/* 0 = no checking
   1 = put_count checking
   2 = verbose put_count checking
*/
#define AUDIT_DEBUG 0

/* No syscall auditing will take place unless audit_enabled != 0. */
extern int audit_enabled;

/* AUDIT_NAMES is the number of slots we reserve in the audit_context
 * for saving names from getname(). */
#define AUDIT_NAMES    20

/* AUDIT_NAMES_RESERVED is the number of slots we reserve in the
 * audit_context from being used for nameless inodes from
 * path_lookup. */
#define AUDIT_NAMES_RESERVED 7

/* At task start time, the audit_state is set in the audit_context using
   a per-task filter.  At syscall entry, the audit_state is augmented by
   the syscall filter. */
enum audit_state {
	AUDIT_DISABLED,		/* Do not create per-task audit_context.
				 * No syscall-specific audit records can
				 * be generated. */
	AUDIT_SETUP_CONTEXT,	/* Create the per-task audit_context,
				 * but don't necessarily fill it in at
				 * syscall entry time (i.e., filter
				 * instead). */
	AUDIT_BUILD_CONTEXT,	/* Create the per-task audit_context,
				 * and always fill it in at syscall
				 * entry time.  This makes a full
				 * syscall record available if some
				 * other part of the kernel decides it
				 * should be recorded. */
	AUDIT_RECORD_CONTEXT	/* Create the per-task audit_context,
				 * always fill it in at syscall entry
				 * time, and always write out the audit
				 * record at syscall exit time.  */
};

/* When fs/namei.c:getname() is called, we store the pointer in name and
 * we don't let putname() free it (instead we free all of the saved
 * pointers at syscall exit time).
 *
 * Further, in fs/namei.c:path_lookup() we store the inode and device. */
struct audit_names {
	const char	*name;
	unsigned long	ino;
	dev_t		dev;
	umode_t		mode;
	uid_t		uid;
	gid_t		gid;
	dev_t		rdev;
101
	unsigned	flags;
L
Linus Torvalds 已提交
102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119
};

struct audit_aux_data {
	struct audit_aux_data	*next;
	int			type;
};

#define AUDIT_AUX_IPCPERM	0

struct audit_aux_data_ipcctl {
	struct audit_aux_data	d;
	struct ipc_perm		p;
	unsigned long		qbytes;
	uid_t			uid;
	gid_t			gid;
	mode_t			mode;
};

120 121 122 123 124 125 126 127 128 129 130 131
struct audit_aux_data_socketcall {
	struct audit_aux_data	d;
	int			nargs;
	unsigned long		args[0];
};

struct audit_aux_data_sockaddr {
	struct audit_aux_data	d;
	int			len;
	char			a[0];
};

132 133 134 135 136
struct audit_aux_data_path {
	struct audit_aux_data	d;
	struct dentry		*dentry;
	struct vfsmount		*mnt;
};
L
Linus Torvalds 已提交
137 138 139 140 141 142 143 144 145 146 147

/* The per-task audit context. */
struct audit_context {
	int		    in_syscall;	/* 1 if task is in a syscall */
	enum audit_state    state;
	unsigned int	    serial;     /* serial number for record */
	struct timespec	    ctime;      /* time of syscall entry */
	uid_t		    loginuid;   /* login uid (identity) */
	int		    major;      /* syscall number */
	unsigned long	    argv[4];    /* syscall arguments */
	int		    return_valid; /* return code is valid */
148
	long		    return_code;/* syscall return code */
L
Linus Torvalds 已提交
149 150 151
	int		    auditable;  /* 1 if record should be written */
	int		    name_count;
	struct audit_names  names[AUDIT_NAMES];
152 153
	struct dentry *	    pwd;
	struct vfsmount *   pwdmnt;
L
Linus Torvalds 已提交
154 155 156 157 158 159 160 161
	struct audit_context *previous; /* For nested syscalls */
	struct audit_aux_data *aux;

				/* Save things to print about task_struct */
	pid_t		    pid;
	uid_t		    uid, euid, suid, fsuid;
	gid_t		    gid, egid, sgid, fsgid;
	unsigned long	    personality;
162
	int		    arch;
L
Linus Torvalds 已提交
163 164 165 166 167 168 169 170 171 172 173

#if AUDIT_DEBUG
	int		    put_count;
	int		    ino_count;
#endif
};

				/* Public API */
/* There are three lists of rules -- one to search at task creation
 * time, one to search at syscall entry time, and another to search at
 * syscall exit time. */
174 175 176 177 178 179 180 181 182 183
static struct list_head audit_filter_list[AUDIT_NR_FILTERS] = {
	LIST_HEAD_INIT(audit_filter_list[0]),
	LIST_HEAD_INIT(audit_filter_list[1]),
	LIST_HEAD_INIT(audit_filter_list[2]),
	LIST_HEAD_INIT(audit_filter_list[3]),
	LIST_HEAD_INIT(audit_filter_list[4]),
#if AUDIT_NR_FILTERS != 5
#error Fix audit_filter_list initialiser
#endif
};
L
Linus Torvalds 已提交
184 185 186 187 188 189 190

struct audit_entry {
	struct list_head  list;
	struct rcu_head   rcu;
	struct audit_rule rule;
};

191 192
extern int audit_pid;

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
/* Copy rule from user-space to kernel-space.  Called from 
 * audit_add_rule during AUDIT_ADD. */
static inline int audit_copy_rule(struct audit_rule *d, struct audit_rule *s)
{
	int i;

	if (s->action != AUDIT_NEVER
	    && s->action != AUDIT_POSSIBLE
	    && s->action != AUDIT_ALWAYS)
		return -1;
	if (s->field_count < 0 || s->field_count > AUDIT_MAX_FIELDS)
		return -1;
	if ((s->flags & ~AUDIT_FILTER_PREPEND) >= AUDIT_NR_FILTERS)
		return -1;

	d->flags	= s->flags;
	d->action	= s->action;
	d->field_count	= s->field_count;
	for (i = 0; i < d->field_count; i++) {
		d->fields[i] = s->fields[i];
		d->values[i] = s->values[i];
	}
	for (i = 0; i < AUDIT_BITMASK_SIZE; i++) d->mask[i] = s->mask[i];
	return 0;
}

L
Linus Torvalds 已提交
219
/* Check to see if two rules are identical.  It is called from
220
 * audit_add_rule during AUDIT_ADD and 
L
Linus Torvalds 已提交
221
 * audit_del_rule during AUDIT_DEL. */
222
static inline int audit_compare_rule(struct audit_rule *a, struct audit_rule *b)
L
Linus Torvalds 已提交
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
{
	int i;

	if (a->flags != b->flags)
		return 1;

	if (a->action != b->action)
		return 1;

	if (a->field_count != b->field_count)
		return 1;

	for (i = 0; i < a->field_count; i++) {
		if (a->fields[i] != b->fields[i]
		    || a->values[i] != b->values[i])
			return 1;
	}

	for (i = 0; i < AUDIT_BITMASK_SIZE; i++)
		if (a->mask[i] != b->mask[i])
			return 1;

	return 0;
}

/* Note that audit_add_rule and audit_del_rule are called via
 * audit_receive() in audit.c, and are protected by
 * audit_netlink_sem. */
251
static inline int audit_add_rule(struct audit_rule *rule,
252
				  struct list_head *list)
L
Linus Torvalds 已提交
253
{
254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270
	struct audit_entry  *entry;

	/* Do not use the _rcu iterator here, since this is the only
	 * addition routine. */
	list_for_each_entry(entry, list, list) {
		if (!audit_compare_rule(rule, &entry->rule)) {
			return -EEXIST;
		}
	}

	if (!(entry = kmalloc(sizeof(*entry), GFP_KERNEL)))
		return -ENOMEM;
	if (audit_copy_rule(&entry->rule, rule)) {
		kfree(entry);
		return -EINVAL;
	}

271 272
	if (entry->rule.flags & AUDIT_FILTER_PREPEND) {
		entry->rule.flags &= ~AUDIT_FILTER_PREPEND;
L
Linus Torvalds 已提交
273 274 275 276
		list_add_rcu(&entry->list, list);
	} else {
		list_add_tail_rcu(&entry->list, list);
	}
277 278

	return 0;
L
Linus Torvalds 已提交
279 280
}

281
static inline void audit_free_rule(struct rcu_head *head)
L
Linus Torvalds 已提交
282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303
{
	struct audit_entry *e = container_of(head, struct audit_entry, rcu);
	kfree(e);
}

/* Note that audit_add_rule and audit_del_rule are called via
 * audit_receive() in audit.c, and are protected by
 * audit_netlink_sem. */
static inline int audit_del_rule(struct audit_rule *rule,
				 struct list_head *list)
{
	struct audit_entry  *e;

	/* Do not use the _rcu iterator here, since this is the only
	 * deletion routine. */
	list_for_each_entry(e, list, list) {
		if (!audit_compare_rule(rule, &e->rule)) {
			list_del_rcu(&e->list);
			call_rcu(&e->rcu, audit_free_rule);
			return 0;
		}
	}
304
	return -ENOENT;		/* No matching rule */
L
Linus Torvalds 已提交
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
static int audit_list_rules(void *_dest)
{
	int pid, seq;
	int *dest = _dest;
	struct audit_entry *entry;
	int i;

	pid = dest[0];
	seq = dest[1];
	kfree(dest);

	down(&audit_netlink_sem);

	/* The *_rcu iterators not needed here because we are
	   always called with audit_netlink_sem held. */
	for (i=0; i<AUDIT_NR_FILTERS; i++) {
		list_for_each_entry(entry, &audit_filter_list[i], list)
			audit_send_reply(pid, seq, AUDIT_LIST, 0, 1,
					 &entry->rule, sizeof(entry->rule));
	}
	audit_send_reply(pid, seq, AUDIT_LIST, 1, 1, NULL, 0);
	
	up(&audit_netlink_sem);
	return 0;
}

333 334
int audit_receive_filter(int type, int pid, int uid, int seq, void *data,
							uid_t loginuid)
L
Linus Torvalds 已提交
335
{
336 337
	struct task_struct *tsk;
	int *dest;
L
Linus Torvalds 已提交
338
	int		   err = 0;
339
	unsigned listnr;
L
Linus Torvalds 已提交
340 341 342

	switch (type) {
	case AUDIT_LIST:
343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358
		/* We can't just spew out the rules here because we might fill
		 * the available socket buffer space and deadlock waiting for
		 * auditctl to read from it... which isn't ever going to
		 * happen if we're actually running in the context of auditctl
		 * trying to _send_ the stuff */
		 
		dest = kmalloc(2 * sizeof(int), GFP_KERNEL);
		if (!dest)
			return -ENOMEM;
		dest[0] = pid;
		dest[1] = seq;

		tsk = kthread_run(audit_list_rules, dest, "audit_list_rules");
		if (IS_ERR(tsk)) {
			kfree(dest);
			err = PTR_ERR(tsk);
359
		}
L
Linus Torvalds 已提交
360 361
		break;
	case AUDIT_ADD:
362 363
		listnr =((struct audit_rule *)data)->flags & ~AUDIT_FILTER_PREPEND;
		if (listnr >= AUDIT_NR_FILTERS)
L
Linus Torvalds 已提交
364
			return -EINVAL;
365 366 367 368 369

		err = audit_add_rule(data, &audit_filter_list[listnr]);
		if (!err)
			audit_log(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE,
				  "auid=%u added an audit rule\n", loginuid);
L
Linus Torvalds 已提交
370 371
		break;
	case AUDIT_DEL:
372 373 374 375 376 377
		listnr =((struct audit_rule *)data)->flags & ~AUDIT_FILTER_PREPEND;
		if (listnr >= AUDIT_NR_FILTERS)
			return -EINVAL;

		err = audit_del_rule(data, &audit_filter_list[listnr]);
		if (!err)
378
			audit_log(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE,
379
				  "auid=%u removed an audit rule\n", loginuid);
L
Linus Torvalds 已提交
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
		break;
	default:
		return -EINVAL;
	}

	return err;
}

/* Compare a task_struct with an audit_rule.  Return 1 on match, 0
 * otherwise. */
static int audit_filter_rules(struct task_struct *tsk,
			      struct audit_rule *rule,
			      struct audit_context *ctx,
			      enum audit_state *state)
{
	int i, j;

	for (i = 0; i < rule->field_count; i++) {
		u32 field  = rule->fields[i] & ~AUDIT_NEGATE;
		u32 value  = rule->values[i];
		int result = 0;

		switch (field) {
		case AUDIT_PID:
			result = (tsk->pid == value);
			break;
		case AUDIT_UID:
			result = (tsk->uid == value);
			break;
		case AUDIT_EUID:
			result = (tsk->euid == value);
			break;
		case AUDIT_SUID:
			result = (tsk->suid == value);
			break;
		case AUDIT_FSUID:
			result = (tsk->fsuid == value);
			break;
		case AUDIT_GID:
			result = (tsk->gid == value);
			break;
		case AUDIT_EGID:
			result = (tsk->egid == value);
			break;
		case AUDIT_SGID:
			result = (tsk->sgid == value);
			break;
		case AUDIT_FSGID:
			result = (tsk->fsgid == value);
			break;
		case AUDIT_PERS:
			result = (tsk->personality == value);
			break;
433 434 435 436
		case AUDIT_ARCH:
			if (ctx) 
				result = (ctx->arch == value);
			break;
L
Linus Torvalds 已提交
437 438 439 440 441 442

		case AUDIT_EXIT:
			if (ctx && ctx->return_valid)
				result = (ctx->return_code == value);
			break;
		case AUDIT_SUCCESS:
443 444 445 446 447 448
			if (ctx && ctx->return_valid) {
				if (value)
					result = (ctx->return_valid == AUDITSC_SUCCESS);
				else
					result = (ctx->return_valid == AUDITSC_FAILURE);
			}
L
Linus Torvalds 已提交
449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516
			break;
		case AUDIT_DEVMAJOR:
			if (ctx) {
				for (j = 0; j < ctx->name_count; j++) {
					if (MAJOR(ctx->names[j].dev)==value) {
						++result;
						break;
					}
				}
			}
			break;
		case AUDIT_DEVMINOR:
			if (ctx) {
				for (j = 0; j < ctx->name_count; j++) {
					if (MINOR(ctx->names[j].dev)==value) {
						++result;
						break;
					}
				}
			}
			break;
		case AUDIT_INODE:
			if (ctx) {
				for (j = 0; j < ctx->name_count; j++) {
					if (ctx->names[j].ino == value) {
						++result;
						break;
					}
				}
			}
			break;
		case AUDIT_LOGINUID:
			result = 0;
			if (ctx)
				result = (ctx->loginuid == value);
			break;
		case AUDIT_ARG0:
		case AUDIT_ARG1:
		case AUDIT_ARG2:
		case AUDIT_ARG3:
			if (ctx)
				result = (ctx->argv[field-AUDIT_ARG0]==value);
			break;
		}

		if (rule->fields[i] & AUDIT_NEGATE)
			result = !result;
		if (!result)
			return 0;
	}
	switch (rule->action) {
	case AUDIT_NEVER:    *state = AUDIT_DISABLED;	    break;
	case AUDIT_POSSIBLE: *state = AUDIT_BUILD_CONTEXT;  break;
	case AUDIT_ALWAYS:   *state = AUDIT_RECORD_CONTEXT; break;
	}
	return 1;
}

/* At process creation time, we can determine if system-call auditing is
 * completely disabled for this task.  Since we only have the task
 * structure at this point, we can only check uid and gid.
 */
static enum audit_state audit_filter_task(struct task_struct *tsk)
{
	struct audit_entry *e;
	enum audit_state   state;

	rcu_read_lock();
517
	list_for_each_entry_rcu(e, &audit_filter_list[AUDIT_FILTER_TASK], list) {
L
Linus Torvalds 已提交
518 519 520 521 522 523 524 525 526 527 528
		if (audit_filter_rules(tsk, &e->rule, NULL, &state)) {
			rcu_read_unlock();
			return state;
		}
	}
	rcu_read_unlock();
	return AUDIT_BUILD_CONTEXT;
}

/* At syscall entry and exit time, this filter is called if the
 * audit_state is not low enough that auditing cannot take place, but is
S
Steve Grubb 已提交
529
 * also not high enough that we already know we have to write an audit
L
Linus Torvalds 已提交
530 531 532 533 534 535 536
 * record (i.e., the state is AUDIT_SETUP_CONTEXT or  AUDIT_BUILD_CONTEXT).
 */
static enum audit_state audit_filter_syscall(struct task_struct *tsk,
					     struct audit_context *ctx,
					     struct list_head *list)
{
	struct audit_entry *e;
537
	enum audit_state state;
L
Linus Torvalds 已提交
538

539
	if (audit_pid && tsk->tgid == audit_pid)
540 541
		return AUDIT_DISABLED;

L
Linus Torvalds 已提交
542
	rcu_read_lock();
543 544 545 546 547 548 549 550 551 552 553
	if (!list_empty(list)) {
		    int word = AUDIT_WORD(ctx->major);
		    int bit  = AUDIT_BIT(ctx->major);

		    list_for_each_entry_rcu(e, list, list) {
			    if ((e->rule.mask[word] & bit) == bit
				&& audit_filter_rules(tsk, &e->rule, ctx, &state)) {
				    rcu_read_unlock();
				    return state;
			    }
		    }
L
Linus Torvalds 已提交
554 555 556 557 558
	}
	rcu_read_unlock();
	return AUDIT_BUILD_CONTEXT;
}

559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598
static int audit_filter_user_rules(struct netlink_skb_parms *cb,
			      struct audit_rule *rule,
			      enum audit_state *state)
{
	int i;

	for (i = 0; i < rule->field_count; i++) {
		u32 field  = rule->fields[i] & ~AUDIT_NEGATE;
		u32 value  = rule->values[i];
		int result = 0;

		switch (field) {
		case AUDIT_PID:
			result = (cb->creds.pid == value);
			break;
		case AUDIT_UID:
			result = (cb->creds.uid == value);
			break;
		case AUDIT_GID:
			result = (cb->creds.gid == value);
			break;
		case AUDIT_LOGINUID:
			result = (cb->loginuid == value);
			break;
		}

		if (rule->fields[i] & AUDIT_NEGATE)
			result = !result;
		if (!result)
			return 0;
	}
	switch (rule->action) {
	case AUDIT_NEVER:    *state = AUDIT_DISABLED;	    break;
	case AUDIT_POSSIBLE: *state = AUDIT_BUILD_CONTEXT;  break;
	case AUDIT_ALWAYS:   *state = AUDIT_RECORD_CONTEXT; break;
	}
	return 1;
}

int audit_filter_user(struct netlink_skb_parms *cb, int type)
599 600 601
{
	struct audit_entry *e;
	enum audit_state   state;
602
	int ret = 1;
603 604 605

	rcu_read_lock();
	list_for_each_entry_rcu(e, &audit_filter_list[AUDIT_FILTER_USER], list) {
606
		if (audit_filter_user_rules(cb, &e->rule, &state)) {
607 608 609
			if (state == AUDIT_DISABLED)
				ret = 0;
			break;
610 611 612
		}
	}
	rcu_read_unlock();
613

614
	return ret; /* Audit by default */
615 616
}

L
Linus Torvalds 已提交
617 618 619 620 621 622 623 624 625 626 627 628
/* This should be called with task_lock() held. */
static inline struct audit_context *audit_get_context(struct task_struct *tsk,
						      int return_valid,
						      int return_code)
{
	struct audit_context *context = tsk->audit_context;

	if (likely(!context))
		return NULL;
	context->return_valid = return_valid;
	context->return_code  = return_code;

629
	if (context->in_syscall && !context->auditable) {
L
Linus Torvalds 已提交
630
		enum audit_state state;
631
		state = audit_filter_syscall(tsk, context, &audit_filter_list[AUDIT_FILTER_EXIT]);
L
Linus Torvalds 已提交
632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680
		if (state == AUDIT_RECORD_CONTEXT)
			context->auditable = 1;
	}

	context->pid = tsk->pid;
	context->uid = tsk->uid;
	context->gid = tsk->gid;
	context->euid = tsk->euid;
	context->suid = tsk->suid;
	context->fsuid = tsk->fsuid;
	context->egid = tsk->egid;
	context->sgid = tsk->sgid;
	context->fsgid = tsk->fsgid;
	context->personality = tsk->personality;
	tsk->audit_context = NULL;
	return context;
}

static inline void audit_free_names(struct audit_context *context)
{
	int i;

#if AUDIT_DEBUG == 2
	if (context->auditable
	    ||context->put_count + context->ino_count != context->name_count) {
		printk(KERN_ERR "audit.c:%d(:%d): major=%d in_syscall=%d"
		       " name_count=%d put_count=%d"
		       " ino_count=%d [NOT freeing]\n",
		       __LINE__,
		       context->serial, context->major, context->in_syscall,
		       context->name_count, context->put_count,
		       context->ino_count);
		for (i = 0; i < context->name_count; i++)
			printk(KERN_ERR "names[%d] = %p = %s\n", i,
			       context->names[i].name,
			       context->names[i].name);
		dump_stack();
		return;
	}
#endif
#if AUDIT_DEBUG
	context->put_count  = 0;
	context->ino_count  = 0;
#endif

	for (i = 0; i < context->name_count; i++)
		if (context->names[i].name)
			__putname(context->names[i].name);
	context->name_count = 0;
681 682 683 684 685 686
	if (context->pwd)
		dput(context->pwd);
	if (context->pwdmnt)
		mntput(context->pwdmnt);
	context->pwd = NULL;
	context->pwdmnt = NULL;
L
Linus Torvalds 已提交
687 688 689 690 691 692 693
}

static inline void audit_free_aux(struct audit_context *context)
{
	struct audit_aux_data *aux;

	while ((aux = context->aux)) {
694 695 696 697 698
		if (aux->type == AUDIT_AVC_PATH) {
			struct audit_aux_data_path *axi = (void *)aux;
			dput(axi->dentry);
			mntput(axi->mnt);
		}
L
Linus Torvalds 已提交
699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777
		context->aux = aux->next;
		kfree(aux);
	}
}

static inline void audit_zero_context(struct audit_context *context,
				      enum audit_state state)
{
	uid_t loginuid = context->loginuid;

	memset(context, 0, sizeof(*context));
	context->state      = state;
	context->loginuid   = loginuid;
}

static inline struct audit_context *audit_alloc_context(enum audit_state state)
{
	struct audit_context *context;

	if (!(context = kmalloc(sizeof(*context), GFP_KERNEL)))
		return NULL;
	audit_zero_context(context, state);
	return context;
}

/* Filter on the task information and allocate a per-task audit context
 * if necessary.  Doing so turns on system call auditing for the
 * specified task.  This is called from copy_process, so no lock is
 * needed. */
int audit_alloc(struct task_struct *tsk)
{
	struct audit_context *context;
	enum audit_state     state;

	if (likely(!audit_enabled))
		return 0; /* Return if not auditing. */

	state = audit_filter_task(tsk);
	if (likely(state == AUDIT_DISABLED))
		return 0;

	if (!(context = audit_alloc_context(state))) {
		audit_log_lost("out of memory in audit_alloc");
		return -ENOMEM;
	}

				/* Preserve login uid */
	context->loginuid = -1;
	if (current->audit_context)
		context->loginuid = current->audit_context->loginuid;

	tsk->audit_context  = context;
	set_tsk_thread_flag(tsk, TIF_SYSCALL_AUDIT);
	return 0;
}

static inline void audit_free_context(struct audit_context *context)
{
	struct audit_context *previous;
	int		     count = 0;

	do {
		previous = context->previous;
		if (previous || (count &&  count < 10)) {
			++count;
			printk(KERN_ERR "audit(:%d): major=%d name_count=%d:"
			       " freeing multiple contexts (%d)\n",
			       context->serial, context->major,
			       context->name_count, count);
		}
		audit_free_names(context);
		audit_free_aux(context);
		kfree(context);
		context  = previous;
	} while (context);
	if (count >= 10)
		printk(KERN_ERR "audit: freed %d contexts\n", count);
}

778 779 780 781 782 783 784
static void audit_log_task_info(struct audit_buffer *ab)
{
	char name[sizeof(current->comm)];
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma;

	get_task_comm(name, current);
785 786
	audit_log_format(ab, " comm=");
	audit_log_untrustedstring(ab, name);
787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805

	if (!mm)
		return;

	down_read(&mm->mmap_sem);
	vma = mm->mmap;
	while (vma) {
		if ((vma->vm_flags & VM_EXECUTABLE) &&
		    vma->vm_file) {
			audit_log_d_path(ab, "exe=",
					 vma->vm_file->f_dentry,
					 vma->vm_file->f_vfsmnt);
			break;
		}
		vma = vma->vm_next;
	}
	up_read(&mm->mmap_sem);
}

A
Al Viro 已提交
806
static void audit_log_exit(struct audit_context *context, gfp_t gfp_mask)
L
Linus Torvalds 已提交
807 808 809
{
	int i;
	struct audit_buffer *ab;
810
	struct audit_aux_data *aux;
L
Linus Torvalds 已提交
811

812
	ab = audit_log_start(context, gfp_mask, AUDIT_SYSCALL);
L
Linus Torvalds 已提交
813 814
	if (!ab)
		return;		/* audit_panic has been called */
815 816
	audit_log_format(ab, "arch=%x syscall=%d",
			 context->arch, context->major);
L
Linus Torvalds 已提交
817 818 819
	if (context->personality != PER_LINUX)
		audit_log_format(ab, " per=%lx", context->personality);
	if (context->return_valid)
820 821 822
		audit_log_format(ab, " success=%s exit=%ld", 
				 (context->return_valid==AUDITSC_SUCCESS)?"yes":"no",
				 context->return_code);
L
Linus Torvalds 已提交
823 824
	audit_log_format(ab,
		  " a0=%lx a1=%lx a2=%lx a3=%lx items=%d"
825 826 827
		  " pid=%d auid=%u uid=%u gid=%u"
		  " euid=%u suid=%u fsuid=%u"
		  " egid=%u sgid=%u fsgid=%u",
L
Linus Torvalds 已提交
828 829 830 831 832 833 834 835 836 837 838
		  context->argv[0],
		  context->argv[1],
		  context->argv[2],
		  context->argv[3],
		  context->name_count,
		  context->pid,
		  context->loginuid,
		  context->uid,
		  context->gid,
		  context->euid, context->suid, context->fsuid,
		  context->egid, context->sgid, context->fsgid);
839
	audit_log_task_info(ab);
L
Linus Torvalds 已提交
840 841
	audit_log_end(ab);

842
	for (aux = context->aux; aux; aux = aux->next) {
843

844
		ab = audit_log_start(context, GFP_KERNEL, aux->type);
L
Linus Torvalds 已提交
845 846 847 848
		if (!ab)
			continue; /* audit_panic has been called */

		switch (aux->type) {
849
		case AUDIT_IPC: {
L
Linus Torvalds 已提交
850 851
			struct audit_aux_data_ipcctl *axi = (void *)aux;
			audit_log_format(ab, 
852
					 " qbytes=%lx iuid=%u igid=%u mode=%x",
L
Linus Torvalds 已提交
853
					 axi->qbytes, axi->uid, axi->gid, axi->mode);
854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869
			break; }

		case AUDIT_SOCKETCALL: {
			int i;
			struct audit_aux_data_socketcall *axs = (void *)aux;
			audit_log_format(ab, "nargs=%d", axs->nargs);
			for (i=0; i<axs->nargs; i++)
				audit_log_format(ab, " a%d=%lx", i, axs->args[i]);
			break; }

		case AUDIT_SOCKADDR: {
			struct audit_aux_data_sockaddr *axs = (void *)aux;

			audit_log_format(ab, "saddr=");
			audit_log_hex(ab, axs->a, axs->len);
			break; }
870 871 872 873 874 875

		case AUDIT_AVC_PATH: {
			struct audit_aux_data_path *axi = (void *)aux;
			audit_log_d_path(ab, "path=", axi->dentry, axi->mnt);
			break; }

L
Linus Torvalds 已提交
876 877 878 879
		}
		audit_log_end(ab);
	}

880
	if (context->pwd && context->pwdmnt) {
881
		ab = audit_log_start(context, GFP_KERNEL, AUDIT_CWD);
882 883 884 885 886
		if (ab) {
			audit_log_d_path(ab, "cwd=", context->pwd, context->pwdmnt);
			audit_log_end(ab);
		}
	}
L
Linus Torvalds 已提交
887
	for (i = 0; i < context->name_count; i++) {
888
		ab = audit_log_start(context, GFP_KERNEL, AUDIT_PATH);
L
Linus Torvalds 已提交
889 890
		if (!ab)
			continue; /* audit_panic has been called */
891

L
Linus Torvalds 已提交
892
		audit_log_format(ab, "item=%d", i);
893 894 895 896
		if (context->names[i].name) {
			audit_log_format(ab, " name=");
			audit_log_untrustedstring(ab, context->names[i].name);
		}
897 898
		audit_log_format(ab, " flags=%x\n", context->names[i].flags);
			 
L
Linus Torvalds 已提交
899 900
		if (context->names[i].ino != (unsigned long)-1)
			audit_log_format(ab, " inode=%lu dev=%02x:%02x mode=%#o"
901
					     " ouid=%u ogid=%u rdev=%02x:%02x",
L
Linus Torvalds 已提交
902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927
					 context->names[i].ino,
					 MAJOR(context->names[i].dev),
					 MINOR(context->names[i].dev),
					 context->names[i].mode,
					 context->names[i].uid,
					 context->names[i].gid,
					 MAJOR(context->names[i].rdev),
					 MINOR(context->names[i].rdev));
		audit_log_end(ab);
	}
}

/* Free a per-task audit context.  Called from copy_process and
 * __put_task_struct. */
void audit_free(struct task_struct *tsk)
{
	struct audit_context *context;

	task_lock(tsk);
	context = audit_get_context(tsk, 0, 0);
	task_unlock(tsk);

	if (likely(!context))
		return;

	/* Check for system calls that do not go through the exit
928 929 930
	 * function (e.g., exit_group), then free context block. 
	 * We use GFP_ATOMIC here because we might be doing this 
	 * in the context of the idle thread */
931
	if (context->in_syscall && context->auditable)
932
		audit_log_exit(context, GFP_ATOMIC);
L
Linus Torvalds 已提交
933 934 935 936 937 938 939 940 941 942 943

	audit_free_context(context);
}

/* Fill in audit context at syscall entry.  This only happens if the
 * audit context was created when the task was created and the state or
 * filters demand the audit context be built.  If the state from the
 * per-task filter or from the per-syscall filter is AUDIT_RECORD_CONTEXT,
 * then the record will be written at syscall exit time (otherwise, it
 * will only be written if another part of the kernel requests that it
 * be written). */
944
void audit_syscall_entry(struct task_struct *tsk, int arch, int major,
L
Linus Torvalds 已提交
945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997
			 unsigned long a1, unsigned long a2,
			 unsigned long a3, unsigned long a4)
{
	struct audit_context *context = tsk->audit_context;
	enum audit_state     state;

	BUG_ON(!context);

	/* This happens only on certain architectures that make system
	 * calls in kernel_thread via the entry.S interface, instead of
	 * with direct calls.  (If you are porting to a new
	 * architecture, hitting this condition can indicate that you
	 * got the _exit/_leave calls backward in entry.S.)
	 *
	 * i386     no
	 * x86_64   no
	 * ppc64    yes (see arch/ppc64/kernel/misc.S)
	 *
	 * This also happens with vm86 emulation in a non-nested manner
	 * (entries without exits), so this case must be caught.
	 */
	if (context->in_syscall) {
		struct audit_context *newctx;

#if defined(__NR_vm86) && defined(__NR_vm86old)
		/* vm86 mode should only be entered once */
		if (major == __NR_vm86 || major == __NR_vm86old)
			return;
#endif
#if AUDIT_DEBUG
		printk(KERN_ERR
		       "audit(:%d) pid=%d in syscall=%d;"
		       " entering syscall=%d\n",
		       context->serial, tsk->pid, context->major, major);
#endif
		newctx = audit_alloc_context(context->state);
		if (newctx) {
			newctx->previous   = context;
			context		   = newctx;
			tsk->audit_context = newctx;
		} else	{
			/* If we can't alloc a new context, the best we
			 * can do is to leak memory (any pending putname
			 * will be lost).  The only other alternative is
			 * to abandon auditing. */
			audit_zero_context(context, context->state);
		}
	}
	BUG_ON(context->in_syscall || context->name_count);

	if (!audit_enabled)
		return;

998
	context->arch	    = arch;
L
Linus Torvalds 已提交
999 1000 1001 1002 1003 1004 1005 1006
	context->major      = major;
	context->argv[0]    = a1;
	context->argv[1]    = a2;
	context->argv[2]    = a3;
	context->argv[3]    = a4;

	state = context->state;
	if (state == AUDIT_SETUP_CONTEXT || state == AUDIT_BUILD_CONTEXT)
1007
		state = audit_filter_syscall(tsk, context, &audit_filter_list[AUDIT_FILTER_ENTRY]);
L
Linus Torvalds 已提交
1008 1009 1010
	if (likely(state == AUDIT_DISABLED))
		return;

1011
	context->serial     = 0;
L
Linus Torvalds 已提交
1012 1013 1014 1015 1016 1017 1018 1019 1020 1021
	context->ctime      = CURRENT_TIME;
	context->in_syscall = 1;
	context->auditable  = !!(state == AUDIT_RECORD_CONTEXT);
}

/* Tear down after system call.  If the audit context has been marked as
 * auditable (either because of the AUDIT_RECORD_CONTEXT state from
 * filtering, or because some other part of the kernel write an audit
 * message), then write out the syscall information.  In call cases,
 * free the names stored from getname(). */
1022
void audit_syscall_exit(struct task_struct *tsk, int valid, long return_code)
L
Linus Torvalds 已提交
1023 1024 1025 1026 1027
{
	struct audit_context *context;

	get_task_struct(tsk);
	task_lock(tsk);
1028
	context = audit_get_context(tsk, valid, return_code);
L
Linus Torvalds 已提交
1029 1030 1031 1032 1033
	task_unlock(tsk);

	/* Not having a context here is ok, since the parent may have
	 * called __put_task_struct. */
	if (likely(!context))
1034
		goto out;
L
Linus Torvalds 已提交
1035

1036
	if (context->in_syscall && context->auditable)
1037
		audit_log_exit(context, GFP_KERNEL);
L
Linus Torvalds 已提交
1038 1039 1040

	context->in_syscall = 0;
	context->auditable  = 0;
1041

L
Linus Torvalds 已提交
1042 1043 1044 1045 1046 1047 1048 1049 1050 1051
	if (context->previous) {
		struct audit_context *new_context = context->previous;
		context->previous  = NULL;
		audit_free_context(context);
		tsk->audit_context = new_context;
	} else {
		audit_free_names(context);
		audit_free_aux(context);
		tsk->audit_context = context;
	}
1052
 out:
L
Linus Torvalds 已提交
1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075
	put_task_struct(tsk);
}

/* Add a name to the list.  Called from fs/namei.c:getname(). */
void audit_getname(const char *name)
{
	struct audit_context *context = current->audit_context;

	if (!context || IS_ERR(name) || !name)
		return;

	if (!context->in_syscall) {
#if AUDIT_DEBUG == 2
		printk(KERN_ERR "%s:%d(:%d): ignoring getname(%p)\n",
		       __FILE__, __LINE__, context->serial, name);
		dump_stack();
#endif
		return;
	}
	BUG_ON(context->name_count >= AUDIT_NAMES);
	context->names[context->name_count].name = name;
	context->names[context->name_count].ino  = (unsigned long)-1;
	++context->name_count;
1076 1077 1078 1079 1080 1081 1082
	if (!context->pwd) {
		read_lock(&current->fs->lock);
		context->pwd = dget(current->fs->pwd);
		context->pwdmnt = mntget(current->fs->pwdmnt);
		read_unlock(&current->fs->lock);
	}
		
L
Linus Torvalds 已提交
1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126
}

/* Intercept a putname request.  Called from
 * include/linux/fs.h:putname().  If we have stored the name from
 * getname in the audit context, then we delay the putname until syscall
 * exit. */
void audit_putname(const char *name)
{
	struct audit_context *context = current->audit_context;

	BUG_ON(!context);
	if (!context->in_syscall) {
#if AUDIT_DEBUG == 2
		printk(KERN_ERR "%s:%d(:%d): __putname(%p)\n",
		       __FILE__, __LINE__, context->serial, name);
		if (context->name_count) {
			int i;
			for (i = 0; i < context->name_count; i++)
				printk(KERN_ERR "name[%d] = %p = %s\n", i,
				       context->names[i].name,
				       context->names[i].name);
		}
#endif
		__putname(name);
	}
#if AUDIT_DEBUG
	else {
		++context->put_count;
		if (context->put_count > context->name_count) {
			printk(KERN_ERR "%s:%d(:%d): major=%d"
			       " in_syscall=%d putname(%p) name_count=%d"
			       " put_count=%d\n",
			       __FILE__, __LINE__,
			       context->serial, context->major,
			       context->in_syscall, name, context->name_count,
			       context->put_count);
			dump_stack();
		}
	}
#endif
}

/* Store the inode and device from a lookup.  Called from
 * fs/namei.c:path_lookup(). */
1127
void audit_inode(const char *name, const struct inode *inode, unsigned flags)
L
Linus Torvalds 已提交
1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152
{
	int idx;
	struct audit_context *context = current->audit_context;

	if (!context->in_syscall)
		return;
	if (context->name_count
	    && context->names[context->name_count-1].name
	    && context->names[context->name_count-1].name == name)
		idx = context->name_count - 1;
	else if (context->name_count > 1
		 && context->names[context->name_count-2].name
		 && context->names[context->name_count-2].name == name)
		idx = context->name_count - 2;
	else {
		/* FIXME: how much do we care about inodes that have no
		 * associated name? */
		if (context->name_count >= AUDIT_NAMES - AUDIT_NAMES_RESERVED)
			return;
		idx = context->name_count++;
		context->names[idx].name = NULL;
#if AUDIT_DEBUG
		++context->ino_count;
#endif
	}
1153 1154 1155 1156 1157 1158 1159
	context->names[idx].flags = flags;
	context->names[idx].ino   = inode->i_ino;
	context->names[idx].dev	  = inode->i_sb->s_dev;
	context->names[idx].mode  = inode->i_mode;
	context->names[idx].uid   = inode->i_uid;
	context->names[idx].gid   = inode->i_gid;
	context->names[idx].rdev  = inode->i_rdev;
L
Linus Torvalds 已提交
1160 1161
}

1162 1163
void auditsc_get_stamp(struct audit_context *ctx,
		       struct timespec *t, unsigned int *serial)
L
Linus Torvalds 已提交
1164
{
1165 1166
	if (!ctx->serial)
		ctx->serial = audit_serial();
1167 1168 1169 1170
	t->tv_sec  = ctx->ctime.tv_sec;
	t->tv_nsec = ctx->ctime.tv_nsec;
	*serial    = ctx->serial;
	ctx->auditable = 1;
L
Linus Torvalds 已提交
1171 1172
}

S
Steve Grubb 已提交
1173
int audit_set_loginuid(struct task_struct *task, uid_t loginuid)
L
Linus Torvalds 已提交
1174
{
S
Steve Grubb 已提交
1175
	if (task->audit_context) {
1176 1177
		struct audit_buffer *ab;

1178
		ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_LOGIN);
1179 1180
		if (ab) {
			audit_log_format(ab, "login pid=%d uid=%u "
1181
				"old auid=%u new auid=%u",
1182 1183 1184 1185
				task->pid, task->uid, 
				task->audit_context->loginuid, loginuid);
			audit_log_end(ab);
		}
S
Steve Grubb 已提交
1186
		task->audit_context->loginuid = loginuid;
L
Linus Torvalds 已提交
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
	}
	return 0;
}

uid_t audit_get_loginuid(struct audit_context *ctx)
{
	return ctx ? ctx->loginuid : -1;
}

int audit_ipc_perms(unsigned long qbytes, uid_t uid, gid_t gid, mode_t mode)
{
	struct audit_aux_data_ipcctl *ax;
	struct audit_context *context = current->audit_context;

	if (likely(!context))
		return 0;

	ax = kmalloc(sizeof(*ax), GFP_KERNEL);
	if (!ax)
		return -ENOMEM;

	ax->qbytes = qbytes;
	ax->uid = uid;
	ax->gid = gid;
	ax->mode = mode;

1213
	ax->d.type = AUDIT_IPC;
L
Linus Torvalds 已提交
1214 1215 1216 1217
	ax->d.next = context->aux;
	context->aux = (void *)ax;
	return 0;
}
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 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260
int audit_socketcall(int nargs, unsigned long *args)
{
	struct audit_aux_data_socketcall *ax;
	struct audit_context *context = current->audit_context;

	if (likely(!context))
		return 0;

	ax = kmalloc(sizeof(*ax) + nargs * sizeof(unsigned long), GFP_KERNEL);
	if (!ax)
		return -ENOMEM;

	ax->nargs = nargs;
	memcpy(ax->args, args, nargs * sizeof(unsigned long));

	ax->d.type = AUDIT_SOCKETCALL;
	ax->d.next = context->aux;
	context->aux = (void *)ax;
	return 0;
}

int audit_sockaddr(int len, void *a)
{
	struct audit_aux_data_sockaddr *ax;
	struct audit_context *context = current->audit_context;

	if (likely(!context))
		return 0;

	ax = kmalloc(sizeof(*ax) + len, GFP_KERNEL);
	if (!ax)
		return -ENOMEM;

	ax->len = len;
	memcpy(ax->a, a, len);

	ax->d.type = AUDIT_SOCKADDR;
	ax->d.next = context->aux;
	context->aux = (void *)ax;
	return 0;
}

1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281
int audit_avc_path(struct dentry *dentry, struct vfsmount *mnt)
{
	struct audit_aux_data_path *ax;
	struct audit_context *context = current->audit_context;

	if (likely(!context))
		return 0;

	ax = kmalloc(sizeof(*ax), GFP_ATOMIC);
	if (!ax)
		return -ENOMEM;

	ax->dentry = dget(dentry);
	ax->mnt = mntget(mnt);

	ax->d.type = AUDIT_AVC_PATH;
	ax->d.next = context->aux;
	context->aux = (void *)ax;
	return 0;
}

1282 1283 1284 1285 1286
void audit_signal_info(int sig, struct task_struct *t)
{
	extern pid_t audit_sig_pid;
	extern uid_t audit_sig_uid;

1287
	if (unlikely(audit_pid && t->tgid == audit_pid)) {
1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298
		if (sig == SIGTERM || sig == SIGHUP) {
			struct audit_context *ctx = current->audit_context;
			audit_sig_pid = current->pid;
			if (ctx)
				audit_sig_uid = ctx->loginuid;
			else
				audit_sig_uid = current->uid;
		}
	}
}