kprobes.c

Kernel code of linux kernel

/*
 *  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 <[e-mail]> Kernel
 *		Probes initial implementation (includes suggestions from
 *		Rusty Russell).
 * 2004-Aug	Updated by Prasanna S Panchamukhi <[e-mail]> with
 *		hlists and exceptions notifier as suggested by Andi Kleen.
 * 2004-July	Suparna Bhattacharya <[e-mail]> added jumper probes
 *		interface to access function arguments.
 * 2004-Sep	Prasanna S Panchamukhi <[e-mail]> Changed Kprobes
 *		exceptions notifier to be first on the priority list.
 * 2005-May	Hien Nguyen <[e-mail]>, Jim Keniston
 *		<[e-mail]> and Prasanna S Panchamukhi
 *		<[e-mail]> 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)