kprobes.c

linux-2.6.15.6

/*
 *  Kernel Probes (KProbes)
 *  arch/i386/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 contributions from
 *		Rusty Russell).
 * 2004-July	Suparna Bhattacharya <[e-mail]> added jumper probes
 *		interface to access function arguments.
 * 2005-May	Hien Nguyen <[e-mail]>, Jim Keniston
 *		<[e-mail]> and Prasanna S Panchamukhi
 *		<[e-mail]> added function-return probes.
 */

#include <linux/config.h>
#include <linux/kprobes.h>
#include <linux/ptrace.h>
#include <linux/preempt.h>
#include <asm/cacheflush.h>
#include <asm/kdebug.h>
#include <asm/desc.h>

void jprobe_return_end(void);

DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);

/*
 * returns non-zero if opcode modifies the interrupt flag.
 */
static inline int is_IF_modifier(kprobe_opcode_t opcode)
{
	switch (opcode) {
	case 0xfa:		/* cli */
	case 0xfb:		/* sti */
	case 0xcf:		/* iret/iretd */
	case 0x9d:		/* popf/popfd */
		return 1;
	}
	return 0;
}

int __kprobes arch_prepare_kprobe(struct kprobe *p)
{
	return 0;
}

void __kprobes arch_copy_kprobe(struct kprobe *p)
{
	memcpy(p->ainsn.insn, p->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
	p->opcode = *p->addr;
}

void __kprobes arch_arm_kprobe(struct kprobe *p)
{
	*p->addr = BREAKPOINT_INSTRUCTION;
	flush_icache_range((unsigned long) p->addr,
			   (unsigned long) p->addr + sizeof(kprobe_opcode_t));
}

void __kprobes arch_disarm_kprobe(struct kprobe *p)
{
	*p->addr = p->opcode;
	flush_icache_range((unsigned long) p->addr,
			   (unsigned long) p->addr + sizeof(kprobe_opcode_t));
}

void __kprobes arch_remove_kprobe(struct kprobe *p)
{
}

static inline void save_previous_kprobe(struct kprobe_ctlblk *kcb)
{
	kcb->prev_kprobe.kp = kprobe_running();
	kcb->prev_kprobe.status = kcb->kprobe_status;
	kcb->prev_kprobe.old_eflags = kcb->kprobe_old_eflags;
	kcb->prev_kprobe.saved_eflags = kcb->kprobe_saved_eflags;
}

static inline void restore_previous_kprobe(struct kprobe_ctlblk *kcb)
{
	__get_cpu_var(current_kprobe) = kcb->prev_kprobe.kp;
	kcb->kprobe_status = kcb->prev_kprobe.status;
	kcb->kprobe_old_eflags = kcb->prev_kprobe.old_eflags;
	kcb->kprobe_saved_eflags = kcb->prev_kprobe.saved_eflags;
}

static inline void set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
				struct kprobe_ctlblk *kcb)
{
	__get_cpu_var(current_kprobe) = p;
	kcb->kprobe_saved_eflags = kcb->kprobe_old_eflags
		= (regs->eflags & (TF_MASK | IF_MASK));
	if (is_IF_modifier(p->opcode))
		kcb->kprobe_saved_eflags &= ~IF_MASK;
}

static inline void prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
{
	regs->eflags |= TF_MASK;
	regs->eflags &= ~IF_MASK;
	/*single step inline if the instruction is an int3*/
	if (p->opcode == BREAKPOINT_INSTRUCTION)
		regs->eip = (unsigned long)p->addr;
	else
		regs->eip = (unsigned long)&p->ainsn.insn;
}

/* Called with kretprobe_lock held */
void __kprobes arch_prepare_kretprobe(struct kretprobe *rp,
				      struct pt_regs *regs)
{
	unsigned long *sara = (unsigned long *)&regs->esp;
        struct kretprobe_instance *ri;

        if ((ri = get_free_rp_inst(rp)) != NULL) {
                ri->rp = rp;
                ri->task = current;
		ri->ret_addr = (kprobe_opcode_t *) *sara;

		/* Replace the return addr with trampoline addr */
		*sara = (unsigned long) &kretprobe_trampoline;

                add_rp_inst(ri);
        } else {
                rp->nmissed++;
        }
}

/*
 * Interrupts are disabled on entry as trap3 is an interrupt gate and they
 * remain disabled thorough out this function.
 */
static int __kprobes kprobe_handler(struct pt_regs *regs)
{
	struct kprobe *p;
	int ret = 0;
	kprobe_opcode_t *addr = NULL;
	unsigned long *lp;
	struct kprobe_ctlblk *kcb;

	/*
	 * We don't want to be preempted for the entire
	 * duration of kprobe processing
	 */
	preempt_disable();
	kcb = get_kprobe_ctlblk();

	/* Check if the application is using LDT entry for its code segment and
	 * calculate the address by reading the base address from the LDT entry.
	 */
	if ((regs->xcs & 4) && (current->mm)) {
		lp = (unsigned long *) ((unsigned long)((regs->xcs >> 3) * 8)
					+ (char *) current->mm->context.ldt);
		addr = (kprobe_opcode_t *) (get_desc_base(lp) + regs->eip -
						sizeof(kprobe_opcode_t));
	} else {
		addr = (kprobe_opcode_t *)(regs->eip - sizeof(kprobe_opcode_t));
	}
	/* Check we're not actually recursing */
	if (kprobe_running()) {
		p = get_kprobe(addr);
		if (p) {
			if (kcb->kprobe_status == KPROBE_HIT_SS &&
				*p->ainsn.insn == BREAKPOINT_INSTRUCTION) {
				regs->eflags &= ~TF_MASK;
				regs->eflags |= kcb->kprobe_saved_eflags;
				goto no_kprobe;
			}
			/* We have reentered the kprobe_handler(), since
			 * another probe was hit while within the handler.
			 * We here save the original kprobes variables and
			 * just single step on the instruction of the new probe
			 * without calling any user handlers.
			 */
			save_previous_kprobe(kcb);
			set_current_kprobe(p, regs, kcb);
			kprobes_inc_nmissed_count(p);
			prepare_singlestep(p, regs);
			kcb->kprobe_status = KPROBE_REENTER;
			return 1;
		} else {
			p = __get_cpu_var(current_kprobe);
			if (p->break_handler && p->break_handler(p, regs)) {
				goto ss_probe;
			}
		}
		goto no_kprobe;
	}

	p = get_kprobe(addr);
	if (!p) {
		if (regs->eflags & VM_MASK) {
			/* We are in virtual-8086 mode. Return 0 */
			goto no_kprobe;
		}

		if (*addr != BREAKPOINT_INSTRUCTION) {
			/*
			 * The breakpoint instruction was removed right
			 * after we hit it.  Another cpu has removed
			 * either a probepoint or a debugger breakpoint
			 * at this address.  In either case, no further
			 * handling of this interrupt is appropriate.
			 * Back up over the (now missing) int3 and run
			 * the original instruction.
			 */
			regs->eip -= sizeof(kprobe_opcode_t);
			ret = 1;
		}
		/* Not one of ours: let kernel handle it */
		goto no_kprobe;
	}

	set_current_kprobe(p, regs, kcb);
	kcb->kprobe_status = KPROBE_HIT_ACTIVE;

	if (p->pre_handler && p->pre_handler(p, regs))
		/* handler has already set things up, so skip ss setup */
		return 1;

ss_probe:
	prepare_singlestep(p, regs);
	kcb->kprobe_status = KPROBE_HIT_SS;
	return 1;

no_kprobe:
	preempt_enable_no_resched();
	return ret;
}

/*
 * For function-return probes, init_kprobes() establishes a probepoint
 * here. When a retprobed function returns, this probe is hit and
 * trampoline_probe_handler() runs, calling the kretprobe's handler.
 */
 void kretprobe_trampoline_holder(void)
 {
 	asm volatile (  ".global kretprobe_trampoline\n"
 			"kretprobe_trampoline: \n"
 			"nop\n");
 }

/*
 * Called when we hit the probe point at kretprobe_trampoline
 */
int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
{
        struct kretprobe_instance *ri = NULL;
        struct hlist_head *head;
        struct hlist_node *node, *tmp;
	unsigned long flags, orig_ret_address = 0;
	unsigned long trampoline_address =(unsigned long)&kretprobe_trampoline;

	spin_lock_irqsave(&kretprobe_lock, flags);
        head = kretprobe_inst_table_head(current);

	/*
	 * It is possible to have multiple instances associated with a given
	 * task either because an multiple functions in the call path
	 * have a return probe installed on them, and/or more then one return
	 * return probe was registered for a target function.
	 *
	 * We can handle this because: