linux-stable/arch/sparc/kernel/kprobes.c
Tejun Heo 5a0e3ad6af include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files.  percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.

percpu.h -> slab.h dependency is about to be removed.  Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability.  As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.

  http://userweb.kernel.org/~tj/misc/slabh-sweep.py

The script does the followings.

* Scan files for gfp and slab usages and update includes such that
  only the necessary includes are there.  ie. if only gfp is used,
  gfp.h, if slab is used, slab.h.

* When the script inserts a new include, it looks at the include
  blocks and try to put the new include such that its order conforms
  to its surrounding.  It's put in the include block which contains
  core kernel includes, in the same order that the rest are ordered -
  alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
  doesn't seem to be any matching order.

* If the script can't find a place to put a new include (mostly
  because the file doesn't have fitting include block), it prints out
  an error message indicating which .h file needs to be added to the
  file.

The conversion was done in the following steps.

1. The initial automatic conversion of all .c files updated slightly
   over 4000 files, deleting around 700 includes and adding ~480 gfp.h
   and ~3000 slab.h inclusions.  The script emitted errors for ~400
   files.

2. Each error was manually checked.  Some didn't need the inclusion,
   some needed manual addition while adding it to implementation .h or
   embedding .c file was more appropriate for others.  This step added
   inclusions to around 150 files.

3. The script was run again and the output was compared to the edits
   from #2 to make sure no file was left behind.

4. Several build tests were done and a couple of problems were fixed.
   e.g. lib/decompress_*.c used malloc/free() wrappers around slab
   APIs requiring slab.h to be added manually.

5. The script was run on all .h files but without automatically
   editing them as sprinkling gfp.h and slab.h inclusions around .h
   files could easily lead to inclusion dependency hell.  Most gfp.h
   inclusion directives were ignored as stuff from gfp.h was usually
   wildly available and often used in preprocessor macros.  Each
   slab.h inclusion directive was examined and added manually as
   necessary.

6. percpu.h was updated not to include slab.h.

7. Build test were done on the following configurations and failures
   were fixed.  CONFIG_GCOV_KERNEL was turned off for all tests (as my
   distributed build env didn't work with gcov compiles) and a few
   more options had to be turned off depending on archs to make things
   build (like ipr on powerpc/64 which failed due to missing writeq).

   * x86 and x86_64 UP and SMP allmodconfig and a custom test config.
   * powerpc and powerpc64 SMP allmodconfig
   * sparc and sparc64 SMP allmodconfig
   * ia64 SMP allmodconfig
   * s390 SMP allmodconfig
   * alpha SMP allmodconfig
   * um on x86_64 SMP allmodconfig

8. percpu.h modifications were reverted so that it could be applied as
   a separate patch and serve as bisection point.

Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.

Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-30 22:02:32 +09:00

597 lines
16 KiB
C

/* arch/sparc64/kernel/kprobes.c
*
* Copyright (C) 2004 David S. Miller <davem@davemloft.net>
*/
#include <linux/kernel.h>
#include <linux/kprobes.h>
#include <linux/module.h>
#include <linux/kdebug.h>
#include <linux/slab.h>
#include <asm/signal.h>
#include <asm/cacheflush.h>
#include <asm/uaccess.h>
/* We do not have hardware single-stepping on sparc64.
* So we implement software single-stepping with breakpoint
* traps. The top-level scheme is similar to that used
* in the x86 kprobes implementation.
*
* In the kprobe->ainsn.insn[] array we store the original
* instruction at index zero and a break instruction at
* index one.
*
* When we hit a kprobe we:
* - Run the pre-handler
* - Remember "regs->tnpc" and interrupt level stored in
* "regs->tstate" so we can restore them later
* - Disable PIL interrupts
* - Set regs->tpc to point to kprobe->ainsn.insn[0]
* - Set regs->tnpc to point to kprobe->ainsn.insn[1]
* - Mark that we are actively in a kprobe
*
* At this point we wait for the second breakpoint at
* kprobe->ainsn.insn[1] to hit. When it does we:
* - Run the post-handler
* - Set regs->tpc to "remembered" regs->tnpc stored above,
* restore the PIL interrupt level in "regs->tstate" as well
* - Make any adjustments necessary to regs->tnpc in order
* to handle relative branches correctly. See below.
* - Mark that we are no longer actively in a kprobe.
*/
DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
struct kretprobe_blackpoint kretprobe_blacklist[] = {{NULL, NULL}};
int __kprobes arch_prepare_kprobe(struct kprobe *p)
{
if ((unsigned long) p->addr & 0x3UL)
return -EILSEQ;
p->ainsn.insn[0] = *p->addr;
flushi(&p->ainsn.insn[0]);
p->ainsn.insn[1] = BREAKPOINT_INSTRUCTION_2;
flushi(&p->ainsn.insn[1]);
p->opcode = *p->addr;
return 0;
}
void __kprobes arch_arm_kprobe(struct kprobe *p)
{
*p->addr = BREAKPOINT_INSTRUCTION;
flushi(p->addr);
}
void __kprobes arch_disarm_kprobe(struct kprobe *p)
{
*p->addr = p->opcode;
flushi(p->addr);
}
static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb)
{
kcb->prev_kprobe.kp = kprobe_running();
kcb->prev_kprobe.status = kcb->kprobe_status;
kcb->prev_kprobe.orig_tnpc = kcb->kprobe_orig_tnpc;
kcb->prev_kprobe.orig_tstate_pil = kcb->kprobe_orig_tstate_pil;
}
static void __kprobes 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_orig_tnpc = kcb->prev_kprobe.orig_tnpc;
kcb->kprobe_orig_tstate_pil = kcb->prev_kprobe.orig_tstate_pil;
}
static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
struct kprobe_ctlblk *kcb)
{
__get_cpu_var(current_kprobe) = p;
kcb->kprobe_orig_tnpc = regs->tnpc;
kcb->kprobe_orig_tstate_pil = (regs->tstate & TSTATE_PIL);
}
static void __kprobes prepare_singlestep(struct kprobe *p, struct pt_regs *regs,
struct kprobe_ctlblk *kcb)
{
regs->tstate |= TSTATE_PIL;
/*single step inline, if it a breakpoint instruction*/
if (p->opcode == BREAKPOINT_INSTRUCTION) {
regs->tpc = (unsigned long) p->addr;
regs->tnpc = kcb->kprobe_orig_tnpc;
} else {
regs->tpc = (unsigned long) &p->ainsn.insn[0];
regs->tnpc = (unsigned long) &p->ainsn.insn[1];
}
}
static int __kprobes kprobe_handler(struct pt_regs *regs)
{
struct kprobe *p;
void *addr = (void *) regs->tpc;
int ret = 0;
struct kprobe_ctlblk *kcb;
/*
* We don't want to be preempted for the entire
* duration of kprobe processing
*/
preempt_disable();
kcb = get_kprobe_ctlblk();
if (kprobe_running()) {
p = get_kprobe(addr);
if (p) {
if (kcb->kprobe_status == KPROBE_HIT_SS) {
regs->tstate = ((regs->tstate & ~TSTATE_PIL) |
kcb->kprobe_orig_tstate_pil);
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);
kcb->kprobe_status = KPROBE_REENTER;
prepare_singlestep(p, regs, kcb);
return 1;
} else {
if (*(u32 *)addr != BREAKPOINT_INSTRUCTION) {
/* The breakpoint instruction was removed by
* another cpu right after we hit, no further
* handling of this interrupt is appropriate
*/
ret = 1;
goto no_kprobe;
}
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 (*(u32 *)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.
*/
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))
return 1;
ss_probe:
prepare_singlestep(p, regs, kcb);
kcb->kprobe_status = KPROBE_HIT_SS;
return 1;
no_kprobe:
preempt_enable_no_resched();
return ret;
}
/* If INSN is a relative control transfer instruction,
* return the corrected branch destination value.
*
* regs->tpc and regs->tnpc still hold the values of the
* program counters at the time of trap due to the execution
* of the BREAKPOINT_INSTRUCTION_2 at p->ainsn.insn[1]
*
*/
static unsigned long __kprobes relbranch_fixup(u32 insn, struct kprobe *p,
struct pt_regs *regs)
{
unsigned long real_pc = (unsigned long) p->addr;
/* Branch not taken, no mods necessary. */
if (regs->tnpc == regs->tpc + 0x4UL)
return real_pc + 0x8UL;
/* The three cases are call, branch w/prediction,
* and traditional branch.
*/
if ((insn & 0xc0000000) == 0x40000000 ||
(insn & 0xc1c00000) == 0x00400000 ||
(insn & 0xc1c00000) == 0x00800000) {
unsigned long ainsn_addr;
ainsn_addr = (unsigned long) &p->ainsn.insn[0];
/* The instruction did all the work for us
* already, just apply the offset to the correct
* instruction location.
*/
return (real_pc + (regs->tnpc - ainsn_addr));
}
/* It is jmpl or some other absolute PC modification instruction,
* leave NPC as-is.
*/
return regs->tnpc;
}
/* If INSN is an instruction which writes it's PC location
* into a destination register, fix that up.
*/
static void __kprobes retpc_fixup(struct pt_regs *regs, u32 insn,
unsigned long real_pc)
{
unsigned long *slot = NULL;
/* Simplest case is 'call', which always uses %o7 */
if ((insn & 0xc0000000) == 0x40000000) {
slot = &regs->u_regs[UREG_I7];
}
/* 'jmpl' encodes the register inside of the opcode */
if ((insn & 0xc1f80000) == 0x81c00000) {
unsigned long rd = ((insn >> 25) & 0x1f);
if (rd <= 15) {
slot = &regs->u_regs[rd];
} else {
/* Hard case, it goes onto the stack. */
flushw_all();
rd -= 16;
slot = (unsigned long *)
(regs->u_regs[UREG_FP] + STACK_BIAS);
slot += rd;
}
}
if (slot != NULL)
*slot = real_pc;
}
/*
* Called after single-stepping. p->addr is the address of the
* instruction which has been replaced by the breakpoint
* instruction. To avoid the SMP problems that can occur when we
* temporarily put back the original opcode to single-step, we
* single-stepped a copy of the instruction. The address of this
* copy is &p->ainsn.insn[0].
*
* This function prepares to return from the post-single-step
* breakpoint trap.
*/
static void __kprobes resume_execution(struct kprobe *p,
struct pt_regs *regs, struct kprobe_ctlblk *kcb)
{
u32 insn = p->ainsn.insn[0];
regs->tnpc = relbranch_fixup(insn, p, regs);
/* This assignment must occur after relbranch_fixup() */
regs->tpc = kcb->kprobe_orig_tnpc;
retpc_fixup(regs, insn, (unsigned long) p->addr);
regs->tstate = ((regs->tstate & ~TSTATE_PIL) |
kcb->kprobe_orig_tstate_pil);
}
static int __kprobes post_kprobe_handler(struct pt_regs *regs)
{
struct kprobe *cur = kprobe_running();
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
if (!cur)
return 0;
if ((kcb->kprobe_status != KPROBE_REENTER) && cur->post_handler) {
kcb->kprobe_status = KPROBE_HIT_SSDONE;
cur->post_handler(cur, regs, 0);
}
resume_execution(cur, regs, kcb);
/*Restore back the original saved kprobes variables and continue. */
if (kcb->kprobe_status == KPROBE_REENTER) {
restore_previous_kprobe(kcb);
goto out;
}
reset_current_kprobe();
out:
preempt_enable_no_resched();
return 1;
}
int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
{
struct kprobe *cur = kprobe_running();
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
const struct exception_table_entry *entry;
switch(kcb->kprobe_status) {
case KPROBE_HIT_SS:
case KPROBE_REENTER:
/*
* We are here because the instruction being single
* stepped caused a page fault. We reset the current
* kprobe and the tpc points back to the probe address
* and allow the page fault handler to continue as a
* normal page fault.
*/
regs->tpc = (unsigned long)cur->addr;
regs->tnpc = kcb->kprobe_orig_tnpc;
regs->tstate = ((regs->tstate & ~TSTATE_PIL) |
kcb->kprobe_orig_tstate_pil);
if (kcb->kprobe_status == KPROBE_REENTER)
restore_previous_kprobe(kcb);
else
reset_current_kprobe();
preempt_enable_no_resched();
break;
case KPROBE_HIT_ACTIVE:
case KPROBE_HIT_SSDONE:
/*
* We increment the nmissed count for accounting,
* we can also use npre/npostfault count for accouting
* these specific fault cases.
*/
kprobes_inc_nmissed_count(cur);
/*
* We come here because instructions in the pre/post
* handler caused the page_fault, this could happen
* if handler tries to access user space by
* copy_from_user(), get_user() etc. Let the
* user-specified handler try to fix it first.
*/
if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr))
return 1;
/*
* In case the user-specified fault handler returned
* zero, try to fix up.
*/
entry = search_exception_tables(regs->tpc);
if (entry) {
regs->tpc = entry->fixup;
regs->tnpc = regs->tpc + 4;
return 1;
}
/*
* fixup_exception() could not handle it,
* Let do_page_fault() fix it.
*/
break;
default:
break;
}
return 0;
}
/*
* Wrapper routine to for handling exceptions.
*/
int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
unsigned long val, void *data)
{
struct die_args *args = (struct die_args *)data;
int ret = NOTIFY_DONE;
if (args->regs && user_mode(args->regs))
return ret;
switch (val) {
case DIE_DEBUG:
if (kprobe_handler(args->regs))
ret = NOTIFY_STOP;
break;
case DIE_DEBUG_2:
if (post_kprobe_handler(args->regs))
ret = NOTIFY_STOP;
break;
default:
break;
}
return ret;
}
asmlinkage void __kprobes kprobe_trap(unsigned long trap_level,
struct pt_regs *regs)
{
BUG_ON(trap_level != 0x170 && trap_level != 0x171);
if (user_mode(regs)) {
local_irq_enable();
bad_trap(regs, trap_level);
return;
}
/* trap_level == 0x170 --> ta 0x70
* trap_level == 0x171 --> ta 0x71
*/
if (notify_die((trap_level == 0x170) ? DIE_DEBUG : DIE_DEBUG_2,
(trap_level == 0x170) ? "debug" : "debug_2",
regs, 0, trap_level, SIGTRAP) != NOTIFY_STOP)
bad_trap(regs, trap_level);
}
/* Jprobes support. */
int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
{
struct jprobe *jp = container_of(p, struct jprobe, kp);
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
memcpy(&(kcb->jprobe_saved_regs), regs, sizeof(*regs));
regs->tpc = (unsigned long) jp->entry;
regs->tnpc = ((unsigned long) jp->entry) + 0x4UL;
regs->tstate |= TSTATE_PIL;
return 1;
}
void __kprobes jprobe_return(void)
{
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
register unsigned long orig_fp asm("g1");
orig_fp = kcb->jprobe_saved_regs.u_regs[UREG_FP];
__asm__ __volatile__("\n"
"1: cmp %%sp, %0\n\t"
"blu,a,pt %%xcc, 1b\n\t"
" restore\n\t"
".globl jprobe_return_trap_instruction\n"
"jprobe_return_trap_instruction:\n\t"
"ta 0x70"
: /* no outputs */
: "r" (orig_fp));
}
extern void jprobe_return_trap_instruction(void);
int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
{
u32 *addr = (u32 *) regs->tpc;
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
if (addr == (u32 *) jprobe_return_trap_instruction) {
memcpy(regs, &(kcb->jprobe_saved_regs), sizeof(*regs));
preempt_enable_no_resched();
return 1;
}
return 0;
}
/* The value stored in the return address register is actually 2
* instructions before where the callee will return to.
* Sequences usually look something like this
*
* call some_function <--- return register points here
* nop <--- call delay slot
* whatever <--- where callee returns to
*
* To keep trampoline_probe_handler logic simpler, we normalize the
* value kept in ri->ret_addr so we don't need to keep adjusting it
* back and forth.
*/
void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
struct pt_regs *regs)
{
ri->ret_addr = (kprobe_opcode_t *)(regs->u_regs[UREG_RETPC] + 8);
/* Replace the return addr with trampoline addr */
regs->u_regs[UREG_RETPC] =
((unsigned long)kretprobe_trampoline) - 8;
}
/*
* Called when the probe at kretprobe trampoline is hit
*/
int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
{
struct kretprobe_instance *ri = NULL;
struct hlist_head *head, empty_rp;
struct hlist_node *node, *tmp;
unsigned long flags, orig_ret_address = 0;
unsigned long trampoline_address =(unsigned long)&kretprobe_trampoline;
INIT_HLIST_HEAD(&empty_rp);
kretprobe_hash_lock(current, &head, &flags);
/*
* 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 than one return
* return probe was registered for a target function.
*
* We can handle this because:
* - instances are always inserted at the head of the list
* - when multiple return probes are registered for the same
* function, the first instance's ret_addr will point to the
* real return address, and all the rest will point to
* kretprobe_trampoline
*/
hlist_for_each_entry_safe(ri, node, tmp, head, hlist) {
if (ri->task != current)
/* another task is sharing our hash bucket */
continue;
if (ri->rp && ri->rp->handler)
ri->rp->handler(ri, regs);
orig_ret_address = (unsigned long)ri->ret_addr;
recycle_rp_inst(ri, &empty_rp);
if (orig_ret_address != trampoline_address)
/*
* This is the real return address. Any other
* instances associated with this task are for
* other calls deeper on the call stack
*/
break;
}
kretprobe_assert(ri, orig_ret_address, trampoline_address);
regs->tpc = orig_ret_address;
regs->tnpc = orig_ret_address + 4;
reset_current_kprobe();
kretprobe_hash_unlock(current, &flags);
preempt_enable_no_resched();
hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) {
hlist_del(&ri->hlist);
kfree(ri);
}
/*
* By returning a non-zero value, we are telling
* kprobe_handler() that we don't want the post_handler
* to run (and have re-enabled preemption)
*/
return 1;
}
void kretprobe_trampoline_holder(void)
{
asm volatile(".global kretprobe_trampoline\n"
"kretprobe_trampoline:\n"
"\tnop\n"
"\tnop\n");
}
static struct kprobe trampoline_p = {
.addr = (kprobe_opcode_t *) &kretprobe_trampoline,
.pre_handler = trampoline_probe_handler
};
int __init arch_init_kprobes(void)
{
return register_kprobe(&trampoline_p);
}
int __kprobes arch_trampoline_kprobe(struct kprobe *p)
{
if (p->addr == (kprobe_opcode_t *)&kretprobe_trampoline)
return 1;
return 0;
}