linux_dsm_epyc7002/arch/powerpc/kernel/kprobes.c
Naveen N. Rao 290e307076 powerpc/kprobes: Fix handling of function offsets on ABIv2
commit 239aeba764 ("perf powerpc: Fix kprobe and kretprobe handling with
kallsyms on ppc64le") changed how we use the offset field in struct kprobe on
ABIv2. perf now offsets from the global entry point if an offset is specified
and otherwise chooses the local entry point.

Fix the same in kernel for kprobe API users. We do this by extending
kprobe_lookup_name() to accept an additional parameter to indicate the offset
specified with the kprobe registration. If offset is 0, we return the local
function entry and return the global entry point otherwise.

With:
  # cd /sys/kernel/debug/tracing/
  # echo "p _do_fork" >> kprobe_events
  # echo "p _do_fork+0x10" >> kprobe_events

before this patch:
  # cat ../kprobes/list
  c0000000000d0748  k  _do_fork+0x8    [DISABLED]
  c0000000000d0758  k  _do_fork+0x18    [DISABLED]
  c0000000000412b0  k  kretprobe_trampoline+0x0    [OPTIMIZED]

and after:
  # cat ../kprobes/list
  c0000000000d04c8  k  _do_fork+0x8    [DISABLED]
  c0000000000d04d0  k  _do_fork+0x10    [DISABLED]
  c0000000000412b0  k  kretprobe_trampoline+0x0    [OPTIMIZED]

Acked-by: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-04-20 23:18:55 +10:00

599 lines
16 KiB
C

/*
* Kernel Probes (KProbes)
*
* 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 contributions from
* Rusty Russell).
* 2004-July Suparna Bhattacharya <suparna@in.ibm.com> added jumper probes
* interface to access function arguments.
* 2004-Nov Ananth N Mavinakayanahalli <ananth@in.ibm.com> kprobes port
* for PPC64
*/
#include <linux/kprobes.h>
#include <linux/ptrace.h>
#include <linux/preempt.h>
#include <linux/extable.h>
#include <linux/kdebug.h>
#include <linux/slab.h>
#include <asm/code-patching.h>
#include <asm/cacheflush.h>
#include <asm/sstep.h>
#include <linux/uaccess.h>
DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
struct kretprobe_blackpoint kretprobe_blacklist[] = {{NULL, NULL}};
kprobe_opcode_t *kprobe_lookup_name(const char *name, unsigned int offset)
{
kprobe_opcode_t *addr;
#ifdef PPC64_ELF_ABI_v2
/* PPC64 ABIv2 needs local entry point */
addr = (kprobe_opcode_t *)kallsyms_lookup_name(name);
if (addr && !offset)
addr = (kprobe_opcode_t *)ppc_function_entry(addr);
#elif defined(PPC64_ELF_ABI_v1)
/*
* 64bit powerpc ABIv1 uses function descriptors:
* - Check for the dot variant of the symbol first.
* - If that fails, try looking up the symbol provided.
*
* This ensures we always get to the actual symbol and not
* the descriptor.
*
* Also handle <module:symbol> format.
*/
char dot_name[MODULE_NAME_LEN + 1 + KSYM_NAME_LEN];
const char *modsym;
bool dot_appended = false;
if ((modsym = strchr(name, ':')) != NULL) {
modsym++;
if (*modsym != '\0' && *modsym != '.') {
/* Convert to <module:.symbol> */
strncpy(dot_name, name, modsym - name);
dot_name[modsym - name] = '.';
dot_name[modsym - name + 1] = '\0';
strncat(dot_name, modsym,
sizeof(dot_name) - (modsym - name) - 2);
dot_appended = true;
} else {
dot_name[0] = '\0';
strncat(dot_name, name, sizeof(dot_name) - 1);
}
} else if (name[0] != '.') {
dot_name[0] = '.';
dot_name[1] = '\0';
strncat(dot_name, name, KSYM_NAME_LEN - 2);
dot_appended = true;
} else {
dot_name[0] = '\0';
strncat(dot_name, name, KSYM_NAME_LEN - 1);
}
addr = (kprobe_opcode_t *)kallsyms_lookup_name(dot_name);
if (!addr && dot_appended) {
/* Let's try the original non-dot symbol lookup */
addr = (kprobe_opcode_t *)kallsyms_lookup_name(name);
}
#else
addr = (kprobe_opcode_t *)kallsyms_lookup_name(name);
#endif
return addr;
}
int __kprobes arch_prepare_kprobe(struct kprobe *p)
{
int ret = 0;
kprobe_opcode_t insn = *p->addr;
if ((unsigned long)p->addr & 0x03) {
printk("Attempt to register kprobe at an unaligned address\n");
ret = -EINVAL;
} else if (IS_MTMSRD(insn) || IS_RFID(insn) || IS_RFI(insn)) {
printk("Cannot register a kprobe on rfi/rfid or mtmsr[d]\n");
ret = -EINVAL;
}
/* insn must be on a special executable page on ppc64. This is
* not explicitly required on ppc32 (right now), but it doesn't hurt */
if (!ret) {
p->ainsn.insn = get_insn_slot();
if (!p->ainsn.insn)
ret = -ENOMEM;
}
if (!ret) {
memcpy(p->ainsn.insn, p->addr,
MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
p->opcode = *p->addr;
flush_icache_range((unsigned long)p->ainsn.insn,
(unsigned long)p->ainsn.insn + sizeof(kprobe_opcode_t));
}
p->ainsn.boostable = 0;
return ret;
}
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)
{
if (p->ainsn.insn) {
free_insn_slot(p->ainsn.insn, 0);
p->ainsn.insn = NULL;
}
}
static void __kprobes prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
{
enable_single_step(regs);
/*
* On powerpc we should single step on the original
* instruction even if the probed insn is a trap
* variant as values in regs could play a part in
* if the trap is taken or not
*/
regs->nip = (unsigned long)p->ainsn.insn;
}
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.saved_msr = kcb->kprobe_saved_msr;
}
static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb)
{
__this_cpu_write(current_kprobe, kcb->prev_kprobe.kp);
kcb->kprobe_status = kcb->prev_kprobe.status;
kcb->kprobe_saved_msr = kcb->prev_kprobe.saved_msr;
}
static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
struct kprobe_ctlblk *kcb)
{
__this_cpu_write(current_kprobe, p);
kcb->kprobe_saved_msr = regs->msr;
}
void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
struct pt_regs *regs)
{
ri->ret_addr = (kprobe_opcode_t *)regs->link;
/* Replace the return addr with trampoline addr */
regs->link = (unsigned long)kretprobe_trampoline;
}
int __kprobes kprobe_handler(struct pt_regs *regs)
{
struct kprobe *p;
int ret = 0;
unsigned int *addr = (unsigned int *)regs->nip;
struct kprobe_ctlblk *kcb;
if (user_mode(regs))
return 0;
/*
* We don't want to be preempted for the entire
* duration of kprobe processing
*/
preempt_disable();
kcb = get_kprobe_ctlblk();
/* Check we're not actually recursing */
if (kprobe_running()) {
p = get_kprobe(addr);
if (p) {
kprobe_opcode_t insn = *p->ainsn.insn;
if (kcb->kprobe_status == KPROBE_HIT_SS &&
is_trap(insn)) {
/* Turn off 'trace' bits */
regs->msr &= ~MSR_SINGLESTEP;
regs->msr |= kcb->kprobe_saved_msr;
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);
kcb->kprobe_saved_msr = regs->msr;
kprobes_inc_nmissed_count(p);
prepare_singlestep(p, regs);
kcb->kprobe_status = KPROBE_REENTER;
return 1;
} else {
if (*addr != BREAKPOINT_INSTRUCTION) {
/* If trap variant, then it belongs not to us */
kprobe_opcode_t cur_insn = *addr;
if (is_trap(cur_insn))
goto no_kprobe;
/* 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 = __this_cpu_read(current_kprobe);
if (p->break_handler && p->break_handler(p, regs)) {
goto ss_probe;
}
}
goto no_kprobe;
}
p = get_kprobe(addr);
if (!p) {
if (*addr != BREAKPOINT_INSTRUCTION) {
/*
* PowerPC has multiple variants of the "trap"
* instruction. If the current instruction is a
* trap variant, it could belong to someone else
*/
kprobe_opcode_t cur_insn = *addr;
if (is_trap(cur_insn))
goto no_kprobe;
/*
* 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;
}
kcb->kprobe_status = KPROBE_HIT_ACTIVE;
set_current_kprobe(p, regs, kcb);
if (p->pre_handler && p->pre_handler(p, regs))
/* handler has already set things up, so skip ss setup */
return 1;
ss_probe:
if (p->ainsn.boostable >= 0) {
unsigned int insn = *p->ainsn.insn;
/* regs->nip is also adjusted if emulate_step returns 1 */
ret = emulate_step(regs, insn);
if (ret > 0) {
/*
* Once this instruction has been boosted
* successfully, set the boostable flag
*/
if (unlikely(p->ainsn.boostable == 0))
p->ainsn.boostable = 1;
if (p->post_handler)
p->post_handler(p, regs, 0);
kcb->kprobe_status = KPROBE_HIT_SSDONE;
reset_current_kprobe();
preempt_enable_no_resched();
return 1;
} else if (ret < 0) {
/*
* We don't allow kprobes on mtmsr(d)/rfi(d), etc.
* So, we should never get here... but, its still
* good to catch them, just in case...
*/
printk("Can't step on instruction %x\n", insn);
BUG();
} else if (ret == 0)
/* This instruction can't be boosted */
p->ainsn.boostable = -1;
}
prepare_singlestep(p, regs);
kcb->kprobe_status = KPROBE_HIT_SS;
return 1;
no_kprobe:
preempt_enable_no_resched();
return ret;
}
/*
* Function return probe trampoline:
* - init_kprobes() establishes a probepoint here
* - When the probed function returns, this probe
* causes the handlers to fire
*/
asm(".global kretprobe_trampoline\n"
".type kretprobe_trampoline, @function\n"
"kretprobe_trampoline:\n"
"nop\n"
"blr\n"
".size kretprobe_trampoline, .-kretprobe_trampoline\n");
/*
* Called when the probe at kretprobe trampoline is hit
*/
static 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 *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, 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->nip = orig_ret_address;
/*
* Make LR point to the orig_ret_address.
* When the 'nop' inside the kretprobe_trampoline
* is optimized, we can do a 'blr' after executing the
* detour buffer code.
*/
regs->link = orig_ret_address;
reset_current_kprobe();
kretprobe_hash_unlock(current, &flags);
preempt_enable_no_resched();
hlist_for_each_entry_safe(ri, 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;
}
/*
* Called after single-stepping. p->addr is the address of the
* instruction whose first byte 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.
*/
int __kprobes kprobe_post_handler(struct pt_regs *regs)
{
struct kprobe *cur = kprobe_running();
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
if (!cur || user_mode(regs))
return 0;
/* make sure we got here for instruction we have a kprobe on */
if (((unsigned long)cur->ainsn.insn + 4) != regs->nip)
return 0;
if ((kcb->kprobe_status != KPROBE_REENTER) && cur->post_handler) {
kcb->kprobe_status = KPROBE_HIT_SSDONE;
cur->post_handler(cur, regs, 0);
}
/* Adjust nip to after the single-stepped instruction */
regs->nip = (unsigned long)cur->addr + 4;
regs->msr |= kcb->kprobe_saved_msr;
/*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();
/*
* if somebody else is singlestepping across a probe point, msr
* will have DE/SE set, in which case, continue the remaining processing
* of do_debug, as if this is not a probe hit.
*/
if (regs->msr & MSR_SINGLESTEP)
return 0;
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 nip points back to the probe address
* and allow the page fault handler to continue as a
* normal page fault.
*/
regs->nip = (unsigned long)cur->addr;
regs->msr &= ~MSR_SINGLESTEP; /* Turn off 'trace' bits */
regs->msr |= kcb->kprobe_saved_msr;
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 accounting
* 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.
*/
if ((entry = search_exception_tables(regs->nip)) != NULL) {
regs->nip = extable_fixup(entry);
return 1;
}
/*
* fixup_exception() could not handle it,
* Let do_page_fault() fix it.
*/
break;
default:
break;
}
return 0;
}
unsigned long arch_deref_entry_point(void *entry)
{
return ppc_global_function_entry(entry);
}
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(struct pt_regs));
/* setup return addr to the jprobe handler routine */
regs->nip = arch_deref_entry_point(jp->entry);
#ifdef PPC64_ELF_ABI_v2
regs->gpr[12] = (unsigned long)jp->entry;
#elif defined(PPC64_ELF_ABI_v1)
regs->gpr[2] = (unsigned long)(((func_descr_t *)jp->entry)->toc);
#endif
return 1;
}
void __used __kprobes jprobe_return(void)
{
asm volatile("trap" ::: "memory");
}
static void __used __kprobes jprobe_return_end(void)
{
};
int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
{
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
/*
* FIXME - we should ideally be validating that we got here 'cos
* of the "trap" in jprobe_return() above, before restoring the
* saved regs...
*/
memcpy(regs, &kcb->jprobe_saved_regs, sizeof(struct pt_regs));
preempt_enable_no_resched();
return 1;
}
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;
}