kprobes.c 32.1 KB
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 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 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 1127 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 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 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 1250 1251 1252 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 1282 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 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344
/*
 *  Kernel Probes (KProbes)
 *  kernel/kprobes.c
 *
 * 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.
 *
 * Copyright (C) IBM Corporation, 2002, 2004
 *
 * 2002-Oct	Created by Vamsi Krishna S <vamsi_krishna@in.ibm.com> Kernel
 *		Probes initial implementation (includes suggestions from
 *		Rusty Russell).
 * 2004-Aug	Updated by Prasanna S Panchamukhi <prasanna@in.ibm.com> with
 *		hlists and exceptions notifier as suggested by Andi Kleen.
 * 2004-July	Suparna Bhattacharya <suparna@in.ibm.com> added jumper probes
 *		interface to access function arguments.
 * 2004-Sep	Prasanna S Panchamukhi <prasanna@in.ibm.com> Changed Kprobes
 *		exceptions notifier to be first on the priority list.
 * 2005-May	Hien Nguyen <hien@us.ibm.com>, Jim Keniston
 *		<jkenisto@us.ibm.com> and Prasanna S Panchamukhi
 *		<prasanna@in.ibm.com> added function-return probes.
 */
#include <linux/kprobes.h>
#include <linux/hash.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/stddef.h>
#include <linux/module.h>
#include <linux/moduleloader.h>
#include <linux/kallsyms.h>
#include <linux/freezer.h>
#include <linux/seq_file.h>
#include <linux/debugfs.h>
#include <linux/kdebug.h>

#include <asm-generic/sections.h>
#include <asm/cacheflush.h>
#include <asm/errno.h>
#include <asm/uaccess.h>

#define KPROBE_HASH_BITS 6
#define KPROBE_TABLE_SIZE (1 << KPROBE_HASH_BITS)


/*
 * Some oddball architectures like 64bit powerpc have function descriptors
 * so this must be overridable.
 */
#ifndef kprobe_lookup_name
#define kprobe_lookup_name(name, addr) \
	addr = ((kprobe_opcode_t *)(kallsyms_lookup_name(name)))
#endif

static int kprobes_initialized;
static struct hlist_head kprobe_table[KPROBE_TABLE_SIZE];
static struct hlist_head kretprobe_inst_table[KPROBE_TABLE_SIZE];

/* NOTE: change this value only with kprobe_mutex held */
static bool kprobe_enabled;

DEFINE_MUTEX(kprobe_mutex);		/* Protects kprobe_table */
static DEFINE_PER_CPU(struct kprobe *, kprobe_instance) = NULL;
static struct {
	spinlock_t lock ____cacheline_aligned;
} kretprobe_table_locks[KPROBE_TABLE_SIZE];

static spinlock_t *kretprobe_table_lock_ptr(unsigned long hash)
{
	return &(kretprobe_table_locks[hash].lock);
}

/*
 * Normally, functions that we'd want to prohibit kprobes in, are marked
 * __kprobes. But, there are cases where such functions already belong to
 * a different section (__sched for preempt_schedule)
 *
 * For such cases, we now have a blacklist
 */
static struct kprobe_blackpoint kprobe_blacklist[] = {
	{"preempt_schedule",},
	{NULL}    /* Terminator */
};

#ifdef __ARCH_WANT_KPROBES_INSN_SLOT
/*
 * kprobe->ainsn.insn points to the copy of the instruction to be
 * single-stepped. x86_64, POWER4 and above have no-exec support and
 * stepping on the instruction on a vmalloced/kmalloced/data page
 * is a recipe for disaster
 */
#define INSNS_PER_PAGE	(PAGE_SIZE/(MAX_INSN_SIZE * sizeof(kprobe_opcode_t)))

struct kprobe_insn_page {
	struct hlist_node hlist;
	kprobe_opcode_t *insns;		/* Page of instruction slots */
	char slot_used[INSNS_PER_PAGE];
	int nused;
	int ngarbage;
};

enum kprobe_slot_state {
	SLOT_CLEAN = 0,
	SLOT_DIRTY = 1,
	SLOT_USED = 2,
};

static struct hlist_head kprobe_insn_pages;
static int kprobe_garbage_slots;
static int collect_garbage_slots(void);

static int __kprobes check_safety(void)
{
	int ret = 0;
#if defined(CONFIG_PREEMPT) && defined(CONFIG_PM)
	ret = freeze_processes();
	if (ret == 0) {
		struct task_struct *p, *q;
		do_each_thread(p, q) {
			if (p != current && p->state == TASK_RUNNING &&
			    p->pid != 0) {
				printk("Check failed: %s is running\n",p->comm);
				ret = -1;
				goto loop_end;
			}
		} while_each_thread(p, q);
	}
loop_end:
	thaw_processes();
#else
	synchronize_sched();
#endif
	return ret;
}

/**
 * get_insn_slot() - Find a slot on an executable page for an instruction.
 * We allocate an executable page if there's no room on existing ones.
 */
kprobe_opcode_t __kprobes *get_insn_slot(void)
{
	struct kprobe_insn_page *kip;
	struct hlist_node *pos;

 retry:
	hlist_for_each_entry(kip, pos, &kprobe_insn_pages, hlist) {
		if (kip->nused < INSNS_PER_PAGE) {
			int i;
			for (i = 0; i < INSNS_PER_PAGE; i++) {
				if (kip->slot_used[i] == SLOT_CLEAN) {
					kip->slot_used[i] = SLOT_USED;
					kip->nused++;
					return kip->insns + (i * MAX_INSN_SIZE);
				}
			}
			/* Surprise!  No unused slots.  Fix kip->nused. */
			kip->nused = INSNS_PER_PAGE;
		}
	}

	/* If there are any garbage slots, collect it and try again. */
	if (kprobe_garbage_slots && collect_garbage_slots() == 0) {
		goto retry;
	}
	/* All out of space.  Need to allocate a new page. Use slot 0. */
	kip = kmalloc(sizeof(struct kprobe_insn_page), GFP_KERNEL);
	if (!kip)
		return NULL;

	/*
	 * Use module_alloc so this page is within +/- 2GB of where the
	 * kernel image and loaded module images reside. This is required
	 * so x86_64 can correctly handle the %rip-relative fixups.
	 */
	kip->insns = module_alloc(PAGE_SIZE);
	if (!kip->insns) {
		kfree(kip);
		return NULL;
	}
	INIT_HLIST_NODE(&kip->hlist);
	hlist_add_head(&kip->hlist, &kprobe_insn_pages);
	memset(kip->slot_used, SLOT_CLEAN, INSNS_PER_PAGE);
	kip->slot_used[0] = SLOT_USED;
	kip->nused = 1;
	kip->ngarbage = 0;
	return kip->insns;
}

/* Return 1 if all garbages are collected, otherwise 0. */
static int __kprobes collect_one_slot(struct kprobe_insn_page *kip, int idx)
{
	kip->slot_used[idx] = SLOT_CLEAN;
	kip->nused--;
	if (kip->nused == 0) {
		/*
		 * Page is no longer in use.  Free it unless
		 * it's the last one.  We keep the last one
		 * so as not to have to set it up again the
		 * next time somebody inserts a probe.
		 */
		hlist_del(&kip->hlist);
		if (hlist_empty(&kprobe_insn_pages)) {
			INIT_HLIST_NODE(&kip->hlist);
			hlist_add_head(&kip->hlist,
				       &kprobe_insn_pages);
		} else {
			module_free(NULL, kip->insns);
			kfree(kip);
		}
		return 1;
	}
	return 0;
}

static int __kprobes collect_garbage_slots(void)
{
	struct kprobe_insn_page *kip;
	struct hlist_node *pos, *next;

	/* Ensure no-one is preepmted on the garbages */
	if (check_safety() != 0)
		return -EAGAIN;

	hlist_for_each_entry_safe(kip, pos, next, &kprobe_insn_pages, hlist) {
		int i;
		if (kip->ngarbage == 0)
			continue;
		kip->ngarbage = 0;	/* we will collect all garbages */
		for (i = 0; i < INSNS_PER_PAGE; i++) {
			if (kip->slot_used[i] == SLOT_DIRTY &&
			    collect_one_slot(kip, i))
				break;
		}
	}
	kprobe_garbage_slots = 0;
	return 0;
}

void __kprobes free_insn_slot(kprobe_opcode_t * slot, int dirty)
{
	struct kprobe_insn_page *kip;
	struct hlist_node *pos;

	hlist_for_each_entry(kip, pos, &kprobe_insn_pages, hlist) {
		if (kip->insns <= slot &&
		    slot < kip->insns + (INSNS_PER_PAGE * MAX_INSN_SIZE)) {
			int i = (slot - kip->insns) / MAX_INSN_SIZE;
			if (dirty) {
				kip->slot_used[i] = SLOT_DIRTY;
				kip->ngarbage++;
			} else {
				collect_one_slot(kip, i);
			}
			break;
		}
	}

	if (dirty && ++kprobe_garbage_slots > INSNS_PER_PAGE)
		collect_garbage_slots();
}
#endif

/* We have preemption disabled.. so it is safe to use __ versions */
static inline void set_kprobe_instance(struct kprobe *kp)
{
	__get_cpu_var(kprobe_instance) = kp;
}

static inline void reset_kprobe_instance(void)
{
	__get_cpu_var(kprobe_instance) = NULL;
}

/*
 * This routine is called either:
 * 	- under the kprobe_mutex - during kprobe_[un]register()
 * 				OR
 * 	- with preemption disabled - from arch/xxx/kernel/kprobes.c
 */
struct kprobe __kprobes *get_kprobe(void *addr)
{
	struct hlist_head *head;
	struct hlist_node *node;
	struct kprobe *p;

	head = &kprobe_table[hash_ptr(addr, KPROBE_HASH_BITS)];
	hlist_for_each_entry_rcu(p, node, head, hlist) {
		if (p->addr == addr)
			return p;
	}
	return NULL;
}

/*
 * Aggregate handlers for multiple kprobes support - these handlers
 * take care of invoking the individual kprobe handlers on p->list
 */
static int __kprobes aggr_pre_handler(struct kprobe *p, struct pt_regs *regs)
{
	struct kprobe *kp;

	list_for_each_entry_rcu(kp, &p->list, list) {
		if (kp->pre_handler) {
			set_kprobe_instance(kp);
			if (kp->pre_handler(kp, regs))
				return 1;
		}
		reset_kprobe_instance();
	}
	return 0;
}

static void __kprobes aggr_post_handler(struct kprobe *p, struct pt_regs *regs,
					unsigned long flags)
{
	struct kprobe *kp;

	list_for_each_entry_rcu(kp, &p->list, list) {
		if (kp->post_handler) {
			set_kprobe_instance(kp);
			kp->post_handler(kp, regs, flags);
			reset_kprobe_instance();
		}
	}
}

static int __kprobes aggr_fault_handler(struct kprobe *p, struct pt_regs *regs,
					int trapnr)
{
	struct kprobe *cur = __get_cpu_var(kprobe_instance);

	/*
	 * if we faulted "during" the execution of a user specified
	 * probe handler, invoke just that probe's fault handler
	 */
	if (cur && cur->fault_handler) {
		if (cur->fault_handler(cur, regs, trapnr))
			return 1;
	}
	return 0;
}

static int __kprobes aggr_break_handler(struct kprobe *p, struct pt_regs *regs)
{
	struct kprobe *cur = __get_cpu_var(kprobe_instance);
	int ret = 0;

	if (cur && cur->break_handler) {
		if (cur->break_handler(cur, regs))
			ret = 1;
	}
	reset_kprobe_instance();
	return ret;
}

/* Walks the list and increments nmissed count for multiprobe case */
void __kprobes kprobes_inc_nmissed_count(struct kprobe *p)
{
	struct kprobe *kp;
	if (p->pre_handler != aggr_pre_handler) {
		p->nmissed++;
	} else {
		list_for_each_entry_rcu(kp, &p->list, list)
			kp->nmissed++;
	}
	return;
}

void __kprobes recycle_rp_inst(struct kretprobe_instance *ri,
				struct hlist_head *head)
{
	struct kretprobe *rp = ri->rp;

	/* remove rp inst off the rprobe_inst_table */
	hlist_del(&ri->hlist);
	INIT_HLIST_NODE(&ri->hlist);
	if (likely(rp)) {
		spin_lock(&rp->lock);
		hlist_add_head(&ri->hlist, &rp->free_instances);
		spin_unlock(&rp->lock);
	} else
		/* Unregistering */
		hlist_add_head(&ri->hlist, head);
}

void kretprobe_hash_lock(struct task_struct *tsk,
			 struct hlist_head **head, unsigned long *flags)
{
	unsigned long hash = hash_ptr(tsk, KPROBE_HASH_BITS);
	spinlock_t *hlist_lock;

	*head = &kretprobe_inst_table[hash];
	hlist_lock = kretprobe_table_lock_ptr(hash);
	spin_lock_irqsave(hlist_lock, *flags);
}

void kretprobe_table_lock(unsigned long hash, unsigned long *flags)
{
	spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash);
	spin_lock_irqsave(hlist_lock, *flags);
}

void kretprobe_hash_unlock(struct task_struct *tsk, unsigned long *flags)
{
	unsigned long hash = hash_ptr(tsk, KPROBE_HASH_BITS);
	spinlock_t *hlist_lock;

	hlist_lock = kretprobe_table_lock_ptr(hash);
	spin_unlock_irqrestore(hlist_lock, *flags);
}

void kretprobe_table_unlock(unsigned long hash, unsigned long *flags)
{
	spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash);
	spin_unlock_irqrestore(hlist_lock, *flags);
}

/*
 * This function is called from finish_task_switch when task tk becomes dead,
 * so that we can recycle any function-return probe instances associated
 * with this task. These left over instances represent probed functions
 * that have been called but will never return.
 */
void __kprobes kprobe_flush_task(struct task_struct *tk)
{
	struct kretprobe_instance *ri;
	struct hlist_head *head, empty_rp;
	struct hlist_node *node, *tmp;
	unsigned long hash, flags = 0;

	if (unlikely(!kprobes_initialized))
		/* Early boot.  kretprobe_table_locks not yet initialized. */
		return;

	hash = hash_ptr(tk, KPROBE_HASH_BITS);
	head = &kretprobe_inst_table[hash];
	kretprobe_table_lock(hash, &flags);
	hlist_for_each_entry_safe(ri, node, tmp, head, hlist) {
		if (ri->task == tk)
			recycle_rp_inst(ri, &empty_rp);
	}
	kretprobe_table_unlock(hash, &flags);
	INIT_HLIST_HEAD(&empty_rp);
	hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) {
		hlist_del(&ri->hlist);
		kfree(ri);
	}
}

static inline void free_rp_inst(struct kretprobe *rp)
{
	struct kretprobe_instance *ri;
	struct hlist_node *pos, *next;

	hlist_for_each_entry_safe(ri, pos, next, &rp->free_instances, hlist) {
		hlist_del(&ri->hlist);
		kfree(ri);
	}
}

static void __kprobes cleanup_rp_inst(struct kretprobe *rp)
{
	unsigned long flags, hash;
	struct kretprobe_instance *ri;
	struct hlist_node *pos, *next;
	struct hlist_head *head;

	/* No race here */
	for (hash = 0; hash < KPROBE_TABLE_SIZE; hash++) {
		kretprobe_table_lock(hash, &flags);
		head = &kretprobe_inst_table[hash];
		hlist_for_each_entry_safe(ri, pos, next, head, hlist) {
			if (ri->rp == rp)
				ri->rp = NULL;
		}
		kretprobe_table_unlock(hash, &flags);
	}
	free_rp_inst(rp);
}

/*
 * Keep all fields in the kprobe consistent
 */
static inline void copy_kprobe(struct kprobe *old_p, struct kprobe *p)
{
	memcpy(&p->opcode, &old_p->opcode, sizeof(kprobe_opcode_t));
	memcpy(&p->ainsn, &old_p->ainsn, sizeof(struct arch_specific_insn));
}

/*
* Add the new probe to old_p->list. Fail if this is the
* second jprobe at the address - two jprobes can't coexist
*/
static int __kprobes add_new_kprobe(struct kprobe *old_p, struct kprobe *p)
{
	if (p->break_handler) {
		if (old_p->break_handler)
			return -EEXIST;
		list_add_tail_rcu(&p->list, &old_p->list);
		old_p->break_handler = aggr_break_handler;
	} else
		list_add_rcu(&p->list, &old_p->list);
	if (p->post_handler && !old_p->post_handler)
		old_p->post_handler = aggr_post_handler;
	return 0;
}

/*
 * Fill in the required fields of the "manager kprobe". Replace the
 * earlier kprobe in the hlist with the manager kprobe
 */
static inline void add_aggr_kprobe(struct kprobe *ap, struct kprobe *p)
{
	copy_kprobe(p, ap);
	flush_insn_slot(ap);
	ap->addr = p->addr;
	ap->pre_handler = aggr_pre_handler;
	ap->fault_handler = aggr_fault_handler;
	if (p->post_handler)
		ap->post_handler = aggr_post_handler;
	if (p->break_handler)
		ap->break_handler = aggr_break_handler;

	INIT_LIST_HEAD(&ap->list);
	list_add_rcu(&p->list, &ap->list);

	hlist_replace_rcu(&p->hlist, &ap->hlist);
}

/*
 * This is the second or subsequent kprobe at the address - handle
 * the intricacies
 */
static int __kprobes register_aggr_kprobe(struct kprobe *old_p,
					  struct kprobe *p)
{
	int ret = 0;
	struct kprobe *ap;

	if (old_p->pre_handler == aggr_pre_handler) {
		copy_kprobe(old_p, p);
		ret = add_new_kprobe(old_p, p);
	} else {
		ap = kzalloc(sizeof(struct kprobe), GFP_KERNEL);
		if (!ap)
			return -ENOMEM;
		add_aggr_kprobe(ap, old_p);
		copy_kprobe(ap, p);
		ret = add_new_kprobe(ap, p);
	}
	return ret;
}

static int __kprobes in_kprobes_functions(unsigned long addr)
{
	struct kprobe_blackpoint *kb;

	if (addr >= (unsigned long)__kprobes_text_start &&
	    addr < (unsigned long)__kprobes_text_end)
		return -EINVAL;
	/*
	 * If there exists a kprobe_blacklist, verify and
	 * fail any probe registration in the prohibited area
	 */
	for (kb = kprobe_blacklist; kb->name != NULL; kb++) {
		if (kb->start_addr) {
			if (addr >= kb->start_addr &&
			    addr < (kb->start_addr + kb->range))
				return -EINVAL;
		}
	}
	return 0;
}

/*
 * If we have a symbol_name argument, look it up and add the offset field
 * to it. This way, we can specify a relative address to a symbol.
 */
static kprobe_opcode_t __kprobes *kprobe_addr(struct kprobe *p)
{
	kprobe_opcode_t *addr = p->addr;
	if (p->symbol_name) {
		if (addr)
			return NULL;
		kprobe_lookup_name(p->symbol_name, addr);
	}

	if (!addr)
		return NULL;
	return (kprobe_opcode_t *)(((char *)addr) + p->offset);
}

static int __kprobes __register_kprobe(struct kprobe *p,
	unsigned long called_from)
{
	int ret = 0;
	struct kprobe *old_p;
	struct module *probed_mod;
	kprobe_opcode_t *addr;

	addr = kprobe_addr(p);
	if (!addr)
		return -EINVAL;
	p->addr = addr;

	if (!kernel_text_address((unsigned long) p->addr) ||
	    in_kprobes_functions((unsigned long) p->addr))
		return -EINVAL;

	p->mod_refcounted = 0;

	/*
	 * Check if are we probing a module.
	 */
	probed_mod = module_text_address((unsigned long) p->addr);
	if (probed_mod) {
		struct module *calling_mod = module_text_address(called_from);
		/*
		 * We must allow modules to probe themself and in this case
		 * avoid incrementing the module refcount, so as to allow
		 * unloading of self probing modules.
		 */
		if (calling_mod && calling_mod != probed_mod) {
			if (unlikely(!try_module_get(probed_mod)))
				return -EINVAL;
			p->mod_refcounted = 1;
		} else
			probed_mod = NULL;
	}

	p->nmissed = 0;
	INIT_LIST_HEAD(&p->list);
	mutex_lock(&kprobe_mutex);
	old_p = get_kprobe(p->addr);
	if (old_p) {
		ret = register_aggr_kprobe(old_p, p);
		goto out;
	}

	ret = arch_prepare_kprobe(p);
	if (ret)
		goto out;

	INIT_HLIST_NODE(&p->hlist);
	hlist_add_head_rcu(&p->hlist,
		       &kprobe_table[hash_ptr(p->addr, KPROBE_HASH_BITS)]);

	if (kprobe_enabled)
		arch_arm_kprobe(p);

out:
	mutex_unlock(&kprobe_mutex);

	if (ret && probed_mod)
		module_put(probed_mod);
	return ret;
}

/*
 * Unregister a kprobe without a scheduler synchronization.
 */
static int __kprobes __unregister_kprobe_top(struct kprobe *p)
{
	struct kprobe *old_p, *list_p;

	old_p = get_kprobe(p->addr);
	if (unlikely(!old_p))
		return -EINVAL;

	if (p != old_p) {
		list_for_each_entry_rcu(list_p, &old_p->list, list)
			if (list_p == p)
			/* kprobe p is a valid probe */
				goto valid_p;
		return -EINVAL;
	}
valid_p:
	if (old_p == p ||
	    (old_p->pre_handler == aggr_pre_handler &&
	     list_is_singular(&old_p->list))) {
		/*
		 * Only probe on the hash list. Disarm only if kprobes are
		 * enabled - otherwise, the breakpoint would already have
		 * been removed. We save on flushing icache.
		 */
		if (kprobe_enabled)
			arch_disarm_kprobe(p);
		hlist_del_rcu(&old_p->hlist);
	} else {
		if (p->break_handler)
			old_p->break_handler = NULL;
		if (p->post_handler) {
			list_for_each_entry_rcu(list_p, &old_p->list, list) {
				if ((list_p != p) && (list_p->post_handler))
					goto noclean;
			}
			old_p->post_handler = NULL;
		}
noclean:
		list_del_rcu(&p->list);
	}
	return 0;
}

static void __kprobes __unregister_kprobe_bottom(struct kprobe *p)
{
	struct module *mod;
	struct kprobe *old_p;

	if (p->mod_refcounted) {
		mod = module_text_address((unsigned long)p->addr);
		if (mod)
			module_put(mod);
	}

	if (list_empty(&p->list) || list_is_singular(&p->list)) {
		if (!list_empty(&p->list)) {
			/* "p" is the last child of an aggr_kprobe */
			old_p = list_entry(p->list.next, struct kprobe, list);
			list_del(&p->list);
			kfree(old_p);
		}
		arch_remove_kprobe(p);
	}
}

static int __register_kprobes(struct kprobe **kps, int num,
	unsigned long called_from)
{
	int i, ret = 0;

	if (num <= 0)
		return -EINVAL;
	for (i = 0; i < num; i++) {
		ret = __register_kprobe(kps[i], called_from);
		if (ret < 0) {
			if (i > 0)
				unregister_kprobes(kps, i);
			break;
		}
	}
	return ret;
}

/*
 * Registration and unregistration functions for kprobe.
 */
int __kprobes register_kprobe(struct kprobe *p)
{
	return __register_kprobes(&p, 1,
				  (unsigned long)__builtin_return_address(0));
}

void __kprobes unregister_kprobe(struct kprobe *p)
{
	unregister_kprobes(&p, 1);
}

int __kprobes register_kprobes(struct kprobe **kps, int num)
{
	return __register_kprobes(kps, num,
				  (unsigned long)__builtin_return_address(0));
}

void __kprobes unregister_kprobes(struct kprobe **kps, int num)
{
	int i;

	if (num <= 0)
		return;
	mutex_lock(&kprobe_mutex);
	for (i = 0; i < num; i++)
		if (__unregister_kprobe_top(kps[i]) < 0)
			kps[i]->addr = NULL;
	mutex_unlock(&kprobe_mutex);

	synchronize_sched();
	for (i = 0; i < num; i++)
		if (kps[i]->addr)
			__unregister_kprobe_bottom(kps[i]);
}

static struct notifier_block kprobe_exceptions_nb = {
	.notifier_call = kprobe_exceptions_notify,
	.priority = 0x7fffffff /* we need to be notified first */
};

unsigned long __weak arch_deref_entry_point(void *entry)
{
	return (unsigned long)entry;
}

static int __register_jprobes(struct jprobe **jps, int num,
	unsigned long called_from)
{
	struct jprobe *jp;
	int ret = 0, i;

	if (num <= 0)
		return -EINVAL;
	for (i = 0; i < num; i++) {
		unsigned long addr;
		jp = jps[i];
		addr = arch_deref_entry_point(jp->entry);

		if (!kernel_text_address(addr))
			ret = -EINVAL;
		else {
			/* Todo: Verify probepoint is a function entry point */
			jp->kp.pre_handler = setjmp_pre_handler;
			jp->kp.break_handler = longjmp_break_handler;
			ret = __register_kprobe(&jp->kp, called_from);
		}
		if (ret < 0) {
			if (i > 0)
				unregister_jprobes(jps, i);
			break;
		}
	}
	return ret;
}

int __kprobes register_jprobe(struct jprobe *jp)
{
	return __register_jprobes(&jp, 1,
		(unsigned long)__builtin_return_address(0));
}

void __kprobes unregister_jprobe(struct jprobe *jp)
{
	unregister_jprobes(&jp, 1);
}

int __kprobes register_jprobes(struct jprobe **jps, int num)
{
	return __register_jprobes(jps, num,
		(unsigned long)__builtin_return_address(0));
}

void __kprobes unregister_jprobes(struct jprobe **jps, int num)
{
	int i;

	if (num <= 0)
		return;
	mutex_lock(&kprobe_mutex);
	for (i = 0; i < num; i++)
		if (__unregister_kprobe_top(&jps[i]->kp) < 0)
			jps[i]->kp.addr = NULL;
	mutex_unlock(&kprobe_mutex);

	synchronize_sched();
	for (i = 0; i < num; i++) {
		if (jps[i]->kp.addr)
			__unregister_kprobe_bottom(&jps[i]->kp);
	}
}

#ifdef CONFIG_KRETPROBES
/*
 * This kprobe pre_handler is registered with every kretprobe. When probe
 * hits it will set up the return probe.
 */
static int __kprobes pre_handler_kretprobe(struct kprobe *p,
					   struct pt_regs *regs)
{
	struct kretprobe *rp = container_of(p, struct kretprobe, kp);
	unsigned long hash, flags = 0;
	struct kretprobe_instance *ri;

	/*TODO: consider to only swap the RA after the last pre_handler fired */
	hash = hash_ptr(current, KPROBE_HASH_BITS);
	spin_lock_irqsave(&rp->lock, flags);
	if (!hlist_empty(&rp->free_instances)) {
		ri = hlist_entry(rp->free_instances.first,
				struct kretprobe_instance, hlist);
		hlist_del(&ri->hlist);
		spin_unlock_irqrestore(&rp->lock, flags);

		ri->rp = rp;
		ri->task = current;

		if (rp->entry_handler && rp->entry_handler(ri, regs)) {
			spin_unlock_irqrestore(&rp->lock, flags);
			return 0;
		}

		arch_prepare_kretprobe(ri, regs);

		/* XXX(hch): why is there no hlist_move_head? */
		INIT_HLIST_NODE(&ri->hlist);
		kretprobe_table_lock(hash, &flags);
		hlist_add_head(&ri->hlist, &kretprobe_inst_table[hash]);
		kretprobe_table_unlock(hash, &flags);
	} else {
		rp->nmissed++;
		spin_unlock_irqrestore(&rp->lock, flags);
	}
	return 0;
}

static int __kprobes __register_kretprobe(struct kretprobe *rp,
					  unsigned long called_from)
{
	int ret = 0;
	struct kretprobe_instance *inst;
	int i;
	void *addr;

	if (kretprobe_blacklist_size) {
		addr = kprobe_addr(&rp->kp);
		if (!addr)
			return -EINVAL;

		for (i = 0; kretprobe_blacklist[i].name != NULL; i++) {
			if (kretprobe_blacklist[i].addr == addr)
				return -EINVAL;
		}
	}

	rp->kp.pre_handler = pre_handler_kretprobe;
	rp->kp.post_handler = NULL;
	rp->kp.fault_handler = NULL;
	rp->kp.break_handler = NULL;

	/* Pre-allocate memory for max kretprobe instances */
	if (rp->maxactive <= 0) {
#ifdef CONFIG_PREEMPT
		rp->maxactive = max(10, 2 * NR_CPUS);
#else
		rp->maxactive = NR_CPUS;
#endif
	}
	spin_lock_init(&rp->lock);
	INIT_HLIST_HEAD(&rp->free_instances);
	for (i = 0; i < rp->maxactive; i++) {
		inst = kmalloc(sizeof(struct kretprobe_instance) +
			       rp->data_size, GFP_KERNEL);
		if (inst == NULL) {
			free_rp_inst(rp);
			return -ENOMEM;
		}
		INIT_HLIST_NODE(&inst->hlist);
		hlist_add_head(&inst->hlist, &rp->free_instances);
	}

	rp->nmissed = 0;
	/* Establish function entry probe point */
	ret = __register_kprobe(&rp->kp, called_from);
	if (ret != 0)
		free_rp_inst(rp);
	return ret;
}

static int __register_kretprobes(struct kretprobe **rps, int num,
	unsigned long called_from)
{
	int ret = 0, i;

	if (num <= 0)
		return -EINVAL;
	for (i = 0; i < num; i++) {
		ret = __register_kretprobe(rps[i], called_from);
		if (ret < 0) {
			if (i > 0)
				unregister_kretprobes(rps, i);
			break;
		}
	}
	return ret;
}

int __kprobes register_kretprobe(struct kretprobe *rp)
{
	return __register_kretprobes(&rp, 1,
			(unsigned long)__builtin_return_address(0));
}

void __kprobes unregister_kretprobe(struct kretprobe *rp)
{
	unregister_kretprobes(&rp, 1);
}

int __kprobes register_kretprobes(struct kretprobe **rps, int num)
{
	return __register_kretprobes(rps, num,
			(unsigned long)__builtin_return_address(0));
}

void __kprobes unregister_kretprobes(struct kretprobe **rps, int num)
{
	int i;

	if (num <= 0)
		return;
	mutex_lock(&kprobe_mutex);
	for (i = 0; i < num; i++)
		if (__unregister_kprobe_top(&rps[i]->kp) < 0)
			rps[i]->kp.addr = NULL;
	mutex_unlock(&kprobe_mutex);

	synchronize_sched();
	for (i = 0; i < num; i++) {
		if (rps[i]->kp.addr) {
			__unregister_kprobe_bottom(&rps[i]->kp);
			cleanup_rp_inst(rps[i]);
		}
	}
}

#else /* CONFIG_KRETPROBES */
int __kprobes register_kretprobe(struct kretprobe *rp)
{
	return -ENOSYS;
}

int __kprobes register_kretprobes(struct kretprobe **rps, int num)
{
	return -ENOSYS;
}
void __kprobes unregister_kretprobe(struct kretprobe *rp)
{
}

void __kprobes unregister_kretprobes(struct kretprobe **rps, int num)
{
}

static int __kprobes pre_handler_kretprobe(struct kprobe *p,
					   struct pt_regs *regs)
{
	return 0;
}

#endif /* CONFIG_KRETPROBES */

static int __init init_kprobes(void)
{
	int i, err = 0;
	unsigned long offset = 0, size = 0;
	char *modname, namebuf[128];
	const char *symbol_name;
	void *addr;
	struct kprobe_blackpoint *kb;

	/* FIXME allocate the probe table, currently defined statically */
	/* initialize all list heads */
	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
		INIT_HLIST_HEAD(&kprobe_table[i]);
		INIT_HLIST_HEAD(&kretprobe_inst_table[i]);
		spin_lock_init(&(kretprobe_table_locks[i].lock));
	}

	/*
	 * Lookup and populate the kprobe_blacklist.
	 *
	 * Unlike the kretprobe blacklist, we'll need to determine
	 * the range of addresses that belong to the said functions,
	 * since a kprobe need not necessarily be at the beginning
	 * of a function.
	 */
	for (kb = kprobe_blacklist; kb->name != NULL; kb++) {
		kprobe_lookup_name(kb->name, addr);
		if (!addr)
			continue;

		kb->start_addr = (unsigned long)addr;
		symbol_name = kallsyms_lookup(kb->start_addr,
				&size, &offset, &modname, namebuf);
		if (!symbol_name)
			kb->range = 0;
		else
			kb->range = size;
	}

	if (kretprobe_blacklist_size) {
		/* lookup the function address from its name */
		for (i = 0; kretprobe_blacklist[i].name != NULL; i++) {
			kprobe_lookup_name(kretprobe_blacklist[i].name,
					   kretprobe_blacklist[i].addr);
			if (!kretprobe_blacklist[i].addr)
				printk("kretprobe: lookup failed: %s\n",
				       kretprobe_blacklist[i].name);
		}
	}

	/* By default, kprobes are enabled */
	kprobe_enabled = true;

	err = arch_init_kprobes();
	if (!err)
		err = register_die_notifier(&kprobe_exceptions_nb);
	kprobes_initialized = (err == 0);

	if (!err)
		init_test_probes();
	return err;
}

#ifdef CONFIG_DEBUG_FS
static void __kprobes report_probe(struct seq_file *pi, struct kprobe *p,
		const char *sym, int offset,char *modname)
{
	char *kprobe_type;

	if (p->pre_handler == pre_handler_kretprobe)
		kprobe_type = "r";
	else if (p->pre_handler == setjmp_pre_handler)
		kprobe_type = "j";
	else
		kprobe_type = "k";
	if (sym)
		seq_printf(pi, "%p  %s  %s+0x%x  %s\n", p->addr, kprobe_type,
			sym, offset, (modname ? modname : " "));
	else
		seq_printf(pi, "%p  %s  %p\n", p->addr, kprobe_type, p->addr);
}

static void __kprobes *kprobe_seq_start(struct seq_file *f, loff_t *pos)
{
	return (*pos < KPROBE_TABLE_SIZE) ? pos : NULL;
}

static void __kprobes *kprobe_seq_next(struct seq_file *f, void *v, loff_t *pos)
{
	(*pos)++;
	if (*pos >= KPROBE_TABLE_SIZE)
		return NULL;
	return pos;
}

static void __kprobes kprobe_seq_stop(struct seq_file *f, void *v)
{
	/* Nothing to do */
}

static int __kprobes show_kprobe_addr(struct seq_file *pi, void *v)
{
	struct hlist_head *head;
	struct hlist_node *node;
	struct kprobe *p, *kp;
	const char *sym = NULL;
	unsigned int i = *(loff_t *) v;
	unsigned long offset = 0;
	char *modname, namebuf[128];

	head = &kprobe_table[i];
	preempt_disable();
	hlist_for_each_entry_rcu(p, node, head, hlist) {
		sym = kallsyms_lookup((unsigned long)p->addr, NULL,
					&offset, &modname, namebuf);
		if (p->pre_handler == aggr_pre_handler) {
			list_for_each_entry_rcu(kp, &p->list, list)
				report_probe(pi, kp, sym, offset, modname);
		} else
			report_probe(pi, p, sym, offset, modname);
	}
	preempt_enable();
	return 0;
}

static struct seq_operations kprobes_seq_ops = {
	.start = kprobe_seq_start,
	.next  = kprobe_seq_next,
	.stop  = kprobe_seq_stop,
	.show  = show_kprobe_addr
};

static int __kprobes kprobes_open(struct inode *inode, struct file *filp)
{
	return seq_open(filp, &kprobes_seq_ops);
}

static struct file_operations debugfs_kprobes_operations = {
	.open           = kprobes_open,
	.read           = seq_read,
	.llseek         = seq_lseek,
	.release        = seq_release,
};

static void __kprobes enable_all_kprobes(void)
{
	struct hlist_head *head;
	struct hlist_node *node;
	struct kprobe *p;
	unsigned int i;

	mutex_lock(&kprobe_mutex);

	/* If kprobes are already enabled, just return */
	if (kprobe_enabled)
		goto already_enabled;

	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
		head = &kprobe_table[i];
		hlist_for_each_entry_rcu(p, node, head, hlist)
			arch_arm_kprobe(p);
	}

	kprobe_enabled = true;
	printk(KERN_INFO "Kprobes globally enabled\n");

already_enabled:
	mutex_unlock(&kprobe_mutex);
	return;
}

static void __kprobes disable_all_kprobes(void)
{
	struct hlist_head *head;
	struct hlist_node *node;
	struct kprobe *p;
	unsigned int i;

	mutex_lock(&kprobe_mutex);

	/* If kprobes are already disabled, just return */
	if (!kprobe_enabled)
		goto already_disabled;

	kprobe_enabled = false;
	printk(KERN_INFO "Kprobes globally disabled\n");
	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
		head = &kprobe_table[i];
		hlist_for_each_entry_rcu(p, node, head, hlist) {
			if (!arch_trampoline_kprobe(p))
				arch_disarm_kprobe(p);
		}
	}

	mutex_unlock(&kprobe_mutex);
	/* Allow all currently running kprobes to complete */
	synchronize_sched();
	return;

already_disabled:
	mutex_unlock(&kprobe_mutex);
	return;
}

/*
 * XXX: The debugfs bool file interface doesn't allow for callbacks
 * when the bool state is switched. We can reuse that facility when
 * available
 */
static ssize_t read_enabled_file_bool(struct file *file,
	       char __user *user_buf, size_t count, loff_t *ppos)
{
	char buf[3];

	if (kprobe_enabled)
		buf[0] = '1';
	else
		buf[0] = '0';
	buf[1] = '\n';
	buf[2] = 0x00;
	return simple_read_from_buffer(user_buf, count, ppos, buf, 2);
}

static ssize_t write_enabled_file_bool(struct file *file,
	       const char __user *user_buf, size_t count, loff_t *ppos)
{
	char buf[32];
	int buf_size;

	buf_size = min(count, (sizeof(buf)-1));
	if (copy_from_user(buf, user_buf, buf_size))
		return -EFAULT;

	switch (buf[0]) {
	case 'y':
	case 'Y':
	case '1':
		enable_all_kprobes();
		break;
	case 'n':
	case 'N':
	case '0':
		disable_all_kprobes();
		break;
	}

	return count;
}

static struct file_operations fops_kp = {
	.read =         read_enabled_file_bool,
	.write =        write_enabled_file_bool,
};

static int __kprobes debugfs_kprobe_init(void)
{
	struct dentry *dir, *file;
	unsigned int value = 1;

	dir = debugfs_create_dir("kprobes", NULL);
	if (!dir)
		return -ENOMEM;

	file = debugfs_create_file("list", 0444, dir, NULL,
				&debugfs_kprobes_operations);
	if (!file) {
		debugfs_remove(dir);
		return -ENOMEM;
	}

	file = debugfs_create_file("enabled", 0600, dir,
					&value, &fops_kp);
	if (!file) {
		debugfs_remove(dir);
		return -ENOMEM;
	}

	return 0;
}

late_initcall(debugfs_kprobe_init);
#endif /* CONFIG_DEBUG_FS */

module_init(init_kprobes);

EXPORT_SYMBOL_GPL(register_kprobe);
EXPORT_SYMBOL_GPL(unregister_kprobe);
EXPORT_SYMBOL_GPL(register_kprobes);
EXPORT_SYMBOL_GPL(unregister_kprobes);
EXPORT_SYMBOL_GPL(register_jprobe);
EXPORT_SYMBOL_GPL(unregister_jprobe);
EXPORT_SYMBOL_GPL(register_jprobes);
EXPORT_SYMBOL_GPL(unregister_jprobes);
EXPORT_SYMBOL_GPL(jprobe_return);
EXPORT_SYMBOL_GPL(register_kretprobe);
EXPORT_SYMBOL_GPL(unregister_kretprobe);
EXPORT_SYMBOL_GPL(register_kretprobes);
EXPORT_SYMBOL_GPL(unregister_kretprobes);