Resguardo inicial

This commit is contained in:
lastdragon
2026-09-06 12:53:21 -06:00
parent 662efe3c2a
commit ad2088d178
94853 changed files with 43200404 additions and 0 deletions
@@ -0,0 +1,8 @@
# SPDX-License-Identifier: GPL-2.0-only
#
# Makefile for kernel probes
#
obj-$(CONFIG_KPROBES) += core.o
obj-$(CONFIG_OPTPROBES) += opt.o
obj-$(CONFIG_KPROBES_ON_FTRACE) += ftrace.o
@@ -0,0 +1,109 @@
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __X86_KERNEL_KPROBES_COMMON_H
#define __X86_KERNEL_KPROBES_COMMON_H
/* Kprobes and Optprobes common header */
#include <asm/asm.h>
#include <asm/frame.h>
#include <asm/insn.h>
#ifdef CONFIG_X86_64
#define SAVE_REGS_STRING \
/* Skip cs, ip, orig_ax. */ \
" subq $24, %rsp\n" \
" pushq %rdi\n" \
" pushq %rsi\n" \
" pushq %rdx\n" \
" pushq %rcx\n" \
" pushq %rax\n" \
" pushq %r8\n" \
" pushq %r9\n" \
" pushq %r10\n" \
" pushq %r11\n" \
" pushq %rbx\n" \
" pushq %rbp\n" \
" pushq %r12\n" \
" pushq %r13\n" \
" pushq %r14\n" \
" pushq %r15\n" \
ENCODE_FRAME_POINTER
#define RESTORE_REGS_STRING \
" popq %r15\n" \
" popq %r14\n" \
" popq %r13\n" \
" popq %r12\n" \
" popq %rbp\n" \
" popq %rbx\n" \
" popq %r11\n" \
" popq %r10\n" \
" popq %r9\n" \
" popq %r8\n" \
" popq %rax\n" \
" popq %rcx\n" \
" popq %rdx\n" \
" popq %rsi\n" \
" popq %rdi\n" \
/* Skip orig_ax, ip, cs */ \
" addq $24, %rsp\n"
#else
#define SAVE_REGS_STRING \
/* Skip cs, ip, orig_ax and gs. */ \
" subl $4*4, %esp\n" \
" pushl %fs\n" \
" pushl %es\n" \
" pushl %ds\n" \
" pushl %eax\n" \
" pushl %ebp\n" \
" pushl %edi\n" \
" pushl %esi\n" \
" pushl %edx\n" \
" pushl %ecx\n" \
" pushl %ebx\n" \
ENCODE_FRAME_POINTER
#define RESTORE_REGS_STRING \
" popl %ebx\n" \
" popl %ecx\n" \
" popl %edx\n" \
" popl %esi\n" \
" popl %edi\n" \
" popl %ebp\n" \
" popl %eax\n" \
/* Skip ds, es, fs, gs, orig_ax, ip, and cs. */\
" addl $7*4, %esp\n"
#endif
/* Ensure if the instruction can be boostable */
extern bool can_boost(struct insn *insn, void *orig_addr);
/* Recover instruction if given address is probed */
extern unsigned long recover_probed_instruction(kprobe_opcode_t *buf,
unsigned long addr);
/*
* Copy an instruction and adjust the displacement if the instruction
* uses the %rip-relative addressing mode.
*/
extern int __copy_instruction(u8 *dest, u8 *src, u8 *real, struct insn *insn);
/* Generate a relative-jump/call instruction */
extern void synthesize_reljump(void *dest, void *from, void *to);
extern void synthesize_relcall(void *dest, void *from, void *to);
#ifdef CONFIG_OPTPROBES
extern int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter);
extern unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr);
#else /* !CONFIG_OPTPROBES */
static inline int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter)
{
return 0;
}
static inline unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr)
{
return addr;
}
#endif
#endif
File diff suppressed because it is too large Load Diff
@@ -0,0 +1,76 @@
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Dynamic Ftrace based Kprobes Optimization
*
* Copyright (C) Hitachi Ltd., 2012
*/
#include <linux/kprobes.h>
#include <linux/ptrace.h>
#include <linux/hardirq.h>
#include <linux/preempt.h>
#include <linux/ftrace.h>
#include <asm/text-patching.h>
#include "common.h"
/* Ftrace callback handler for kprobes -- called under preempt disabled */
void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *ops, struct ftrace_regs *fregs)
{
struct pt_regs *regs = ftrace_get_regs(fregs);
struct kprobe *p;
struct kprobe_ctlblk *kcb;
int bit;
if (unlikely(kprobe_ftrace_disabled))
return;
bit = ftrace_test_recursion_trylock(ip, parent_ip);
if (bit < 0)
return;
p = get_kprobe((kprobe_opcode_t *)ip);
if (unlikely(!p) || kprobe_disabled(p))
goto out;
kcb = get_kprobe_ctlblk();
if (kprobe_running()) {
kprobes_inc_nmissed_count(p);
} else {
unsigned long orig_ip = instruction_pointer(regs);
/* Kprobe handler expects regs->ip = ip + 1 as breakpoint hit */
instruction_pointer_set(regs, ip + INT3_INSN_SIZE);
__this_cpu_write(current_kprobe, p);
kcb->kprobe_status = KPROBE_HIT_ACTIVE;
if (!p->pre_handler || !p->pre_handler(p, regs)) {
if (unlikely(p->post_handler)) {
/*
* Emulate singlestep (and also recover regs->ip)
* as if there is a 5byte nop
*/
instruction_pointer_set(regs, ip + MCOUNT_INSN_SIZE);
kcb->kprobe_status = KPROBE_HIT_SSDONE;
p->post_handler(p, regs, 0);
}
/* Recover IP address */
instruction_pointer_set(regs, orig_ip);
}
/*
* If pre_handler returns !0, it changes regs->ip. We have to
* skip emulating post_handler.
*/
__this_cpu_write(current_kprobe, NULL);
}
out:
ftrace_test_recursion_unlock(bit);
}
NOKPROBE_SYMBOL(kprobe_ftrace_handler);
int arch_prepare_kprobe_ftrace(struct kprobe *p)
{
p->ainsn.insn = NULL;
p->ainsn.boostable = false;
return 0;
}
+551
View File
@@ -0,0 +1,551 @@
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Kernel Probes Jump Optimization (Optprobes)
*
* Copyright (C) IBM Corporation, 2002, 2004
* Copyright (C) Hitachi Ltd., 2012
*/
#include <linux/kprobes.h>
#include <linux/perf_event.h>
#include <linux/ptrace.h>
#include <linux/string.h>
#include <linux/slab.h>
#include <linux/hardirq.h>
#include <linux/preempt.h>
#include <linux/extable.h>
#include <linux/kdebug.h>
#include <linux/kallsyms.h>
#include <linux/kgdb.h>
#include <linux/ftrace.h>
#include <linux/objtool.h>
#include <linux/pgtable.h>
#include <linux/static_call.h>
#include <asm/text-patching.h>
#include <asm/cacheflush.h>
#include <asm/desc.h>
#include <linux/uaccess.h>
#include <asm/alternative.h>
#include <asm/insn.h>
#include <asm/debugreg.h>
#include <asm/set_memory.h>
#include <asm/sections.h>
#include <asm/nospec-branch.h>
#include "common.h"
unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr)
{
struct optimized_kprobe *op;
struct kprobe *kp;
long offs;
int i;
for (i = 0; i < JMP32_INSN_SIZE; i++) {
kp = get_kprobe((void *)addr - i);
/* This function only handles jump-optimized kprobe */
if (kp && kprobe_optimized(kp)) {
op = container_of(kp, struct optimized_kprobe, kp);
/* If op is optimized or under unoptimizing */
if (list_empty(&op->list) || optprobe_queued_unopt(op))
goto found;
}
}
return addr;
found:
/*
* If the kprobe can be optimized, original bytes which can be
* overwritten by jump destination address. In this case, original
* bytes must be recovered from op->optinsn.copied_insn buffer.
*/
if (copy_from_kernel_nofault(buf, (void *)addr,
MAX_INSN_SIZE * sizeof(kprobe_opcode_t)))
return 0UL;
if (addr == (unsigned long)kp->addr) {
buf[0] = kp->opcode;
memcpy(buf + 1, op->optinsn.copied_insn, DISP32_SIZE);
} else {
offs = addr - (unsigned long)kp->addr - 1;
memcpy(buf, op->optinsn.copied_insn + offs, DISP32_SIZE - offs);
}
return (unsigned long)buf;
}
static void synthesize_clac(kprobe_opcode_t *addr)
{
/*
* Can't be static_cpu_has() due to how objtool treats this feature bit.
* This isn't a fast path anyway.
*/
if (!boot_cpu_has(X86_FEATURE_SMAP))
return;
/* Replace the NOP3 with CLAC */
addr[0] = 0x0f;
addr[1] = 0x01;
addr[2] = 0xca;
}
/* Insert a move instruction which sets a pointer to eax/rdi (1st arg). */
static void synthesize_set_arg1(kprobe_opcode_t *addr, unsigned long val)
{
#ifdef CONFIG_X86_64
*addr++ = 0x48;
*addr++ = 0xbf;
#else
*addr++ = 0xb8;
#endif
*(unsigned long *)addr = val;
}
asm (
".pushsection .rodata\n"
".global optprobe_template_entry\n"
"optprobe_template_entry:\n"
#ifdef CONFIG_X86_64
" pushq $" __stringify(__KERNEL_DS) "\n"
/* Save the 'sp - 8', this will be fixed later. */
" pushq %rsp\n"
" pushfq\n"
".global optprobe_template_clac\n"
"optprobe_template_clac:\n"
ASM_NOP3
SAVE_REGS_STRING
" movq %rsp, %rsi\n"
".global optprobe_template_val\n"
"optprobe_template_val:\n"
ASM_NOP5
ASM_NOP5
".global optprobe_template_call\n"
"optprobe_template_call:\n"
ASM_NOP5
/* Copy 'regs->flags' into 'regs->ss'. */
" movq 18*8(%rsp), %rdx\n"
" movq %rdx, 20*8(%rsp)\n"
RESTORE_REGS_STRING
/* Skip 'regs->flags' and 'regs->sp'. */
" addq $16, %rsp\n"
/* And pop flags register from 'regs->ss'. */
" popfq\n"
#else /* CONFIG_X86_32 */
" pushl %ss\n"
/* Save the 'sp - 4', this will be fixed later. */
" pushl %esp\n"
" pushfl\n"
".global optprobe_template_clac\n"
"optprobe_template_clac:\n"
ASM_NOP3
SAVE_REGS_STRING
" movl %esp, %edx\n"
".global optprobe_template_val\n"
"optprobe_template_val:\n"
ASM_NOP5
".global optprobe_template_call\n"
"optprobe_template_call:\n"
ASM_NOP5
/* Copy 'regs->flags' into 'regs->ss'. */
" movl 14*4(%esp), %edx\n"
" movl %edx, 16*4(%esp)\n"
RESTORE_REGS_STRING
/* Skip 'regs->flags' and 'regs->sp'. */
" addl $8, %esp\n"
/* And pop flags register from 'regs->ss'. */
" popfl\n"
#endif
".global optprobe_template_end\n"
"optprobe_template_end:\n"
".popsection\n");
#define TMPL_CLAC_IDX \
((long)optprobe_template_clac - (long)optprobe_template_entry)
#define TMPL_MOVE_IDX \
((long)optprobe_template_val - (long)optprobe_template_entry)
#define TMPL_CALL_IDX \
((long)optprobe_template_call - (long)optprobe_template_entry)
#define TMPL_END_IDX \
((long)optprobe_template_end - (long)optprobe_template_entry)
/* Optimized kprobe call back function: called from optinsn */
static void
optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs)
{
/* This is possible if op is under delayed unoptimizing */
if (kprobe_disabled(&op->kp))
return;
preempt_disable();
if (kprobe_running()) {
kprobes_inc_nmissed_count(&op->kp);
} else {
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
/* Adjust stack pointer */
regs->sp += sizeof(long);
/* Save skipped registers */
regs->cs = __KERNEL_CS;
#ifdef CONFIG_X86_32
regs->gs = 0;
#endif
regs->ip = (unsigned long)op->kp.addr + INT3_INSN_SIZE;
regs->orig_ax = ~0UL;
__this_cpu_write(current_kprobe, &op->kp);
kcb->kprobe_status = KPROBE_HIT_ACTIVE;
opt_pre_handler(&op->kp, regs);
__this_cpu_write(current_kprobe, NULL);
}
preempt_enable();
}
NOKPROBE_SYMBOL(optimized_callback);
static int copy_optimized_instructions(u8 *dest, u8 *src, u8 *real)
{
struct insn insn;
int len = 0, ret;
while (len < JMP32_INSN_SIZE) {
ret = __copy_instruction(dest + len, src + len, real + len, &insn);
if (!ret || !can_boost(&insn, src + len))
return -EINVAL;
len += ret;
}
/* Check whether the address range is reserved */
if (ftrace_text_reserved(src, src + len - 1) ||
alternatives_text_reserved(src, src + len - 1) ||
jump_label_text_reserved(src, src + len - 1) ||
static_call_text_reserved(src, src + len - 1))
return -EBUSY;
return len;
}
/* Check whether insn is indirect jump */
static int insn_is_indirect_jump(struct insn *insn)
{
return ((insn->opcode.bytes[0] == 0xff &&
(X86_MODRM_REG(insn->modrm.value) & 6) == 4) || /* Jump */
insn->opcode.bytes[0] == 0xea); /* Segment based jump */
}
/* Check whether insn jumps into specified address range */
static int insn_jump_into_range(struct insn *insn, unsigned long start, int len)
{
unsigned long target = 0;
switch (insn->opcode.bytes[0]) {
case 0xe0: /* loopne */
case 0xe1: /* loope */
case 0xe2: /* loop */
case 0xe3: /* jcxz */
case 0xe9: /* near relative jump */
case 0xeb: /* short relative jump */
break;
case 0x0f:
if ((insn->opcode.bytes[1] & 0xf0) == 0x80) /* jcc near */
break;
return 0;
default:
if ((insn->opcode.bytes[0] & 0xf0) == 0x70) /* jcc short */
break;
return 0;
}
target = (unsigned long)insn->next_byte + insn->immediate.value;
return (start <= target && target <= start + len);
}
/* Decode whole function to ensure any instructions don't jump into target */
static int can_optimize(unsigned long paddr)
{
unsigned long addr, size = 0, offset = 0;
struct insn insn;
kprobe_opcode_t buf[MAX_INSN_SIZE];
/* Lookup symbol including addr */
if (!kallsyms_lookup_size_offset(paddr, &size, &offset))
return 0;
/*
* Do not optimize in the entry code due to the unstable
* stack handling and registers setup.
*/
if (((paddr >= (unsigned long)__entry_text_start) &&
(paddr < (unsigned long)__entry_text_end)))
return 0;
/* Check there is enough space for a relative jump. */
if (size - offset < JMP32_INSN_SIZE)
return 0;
/* Decode instructions */
addr = paddr - offset;
while (addr < paddr - offset + size) { /* Decode until function end */
unsigned long recovered_insn;
int ret;
if (search_exception_tables(addr))
/*
* Since some fixup code will jumps into this function,
* we can't optimize kprobe in this function.
*/
return 0;
recovered_insn = recover_probed_instruction(buf, addr);
if (!recovered_insn)
return 0;
ret = insn_decode_kernel(&insn, (void *)recovered_insn);
if (ret < 0)
return 0;
#ifdef CONFIG_KGDB
/*
* If there is a dynamically installed kgdb sw breakpoint,
* this function should not be probed.
*/
if (insn.opcode.bytes[0] == INT3_INSN_OPCODE &&
kgdb_has_hit_break(addr))
return 0;
#endif
/* Recover address */
insn.kaddr = (void *)addr;
insn.next_byte = (void *)(addr + insn.length);
/*
* Check any instructions don't jump into target, indirectly or
* directly.
*
* The indirect case is present to handle a code with jump
* tables. When the kernel uses retpolines, the check should in
* theory additionally look for jumps to indirect thunks.
* However, the kernel built with retpolines or IBT has jump
* tables disabled so the check can be skipped altogether.
*/
if (!IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) &&
!IS_ENABLED(CONFIG_X86_KERNEL_IBT) &&
insn_is_indirect_jump(&insn))
return 0;
if (insn_jump_into_range(&insn, paddr + INT3_INSN_SIZE,
DISP32_SIZE))
return 0;
addr += insn.length;
}
return 1;
}
/* Check optimized_kprobe can actually be optimized. */
int arch_check_optimized_kprobe(struct optimized_kprobe *op)
{
int i;
struct kprobe *p;
for (i = 1; i < op->optinsn.size; i++) {
p = get_kprobe(op->kp.addr + i);
if (p && !kprobe_disarmed(p))
return -EEXIST;
}
return 0;
}
/* Check the addr is within the optimized instructions. */
int arch_within_optimized_kprobe(struct optimized_kprobe *op,
kprobe_opcode_t *addr)
{
return (op->kp.addr <= addr &&
op->kp.addr + op->optinsn.size > addr);
}
/* Free optimized instruction slot */
static
void __arch_remove_optimized_kprobe(struct optimized_kprobe *op, int dirty)
{
u8 *slot = op->optinsn.insn;
if (slot) {
int len = TMPL_END_IDX + op->optinsn.size + JMP32_INSN_SIZE;
/* Record the perf event before freeing the slot */
if (dirty)
perf_event_text_poke(slot, slot, len, NULL, 0);
free_optinsn_slot(slot, dirty);
op->optinsn.insn = NULL;
op->optinsn.size = 0;
}
}
void arch_remove_optimized_kprobe(struct optimized_kprobe *op)
{
__arch_remove_optimized_kprobe(op, 1);
}
/*
* Copy replacing target instructions
* Target instructions MUST be relocatable (checked inside)
* This is called when new aggr(opt)probe is allocated or reused.
*/
int arch_prepare_optimized_kprobe(struct optimized_kprobe *op,
struct kprobe *__unused)
{
u8 *buf = NULL, *slot;
int ret, len;
long rel;
if (!can_optimize((unsigned long)op->kp.addr))
return -EILSEQ;
buf = kzalloc(MAX_OPTINSN_SIZE, GFP_KERNEL);
if (!buf)
return -ENOMEM;
op->optinsn.insn = slot = get_optinsn_slot();
if (!slot) {
ret = -ENOMEM;
goto out;
}
/*
* Verify if the address gap is in 2GB range, because this uses
* a relative jump.
*/
rel = (long)slot - (long)op->kp.addr + JMP32_INSN_SIZE;
if (abs(rel) > 0x7fffffff) {
ret = -ERANGE;
goto err;
}
/* Copy arch-dep-instance from template */
memcpy(buf, optprobe_template_entry, TMPL_END_IDX);
/* Copy instructions into the out-of-line buffer */
ret = copy_optimized_instructions(buf + TMPL_END_IDX, op->kp.addr,
slot + TMPL_END_IDX);
if (ret < 0)
goto err;
op->optinsn.size = ret;
len = TMPL_END_IDX + op->optinsn.size;
synthesize_clac(buf + TMPL_CLAC_IDX);
/* Set probe information */
synthesize_set_arg1(buf + TMPL_MOVE_IDX, (unsigned long)op);
/* Set probe function call */
synthesize_relcall(buf + TMPL_CALL_IDX,
slot + TMPL_CALL_IDX, optimized_callback);
/* Set returning jmp instruction at the tail of out-of-line buffer */
synthesize_reljump(buf + len, slot + len,
(u8 *)op->kp.addr + op->optinsn.size);
len += JMP32_INSN_SIZE;
/*
* Note len = TMPL_END_IDX + op->optinsn.size + JMP32_INSN_SIZE is also
* used in __arch_remove_optimized_kprobe().
*/
/* We have to use text_poke() for instruction buffer because it is RO */
perf_event_text_poke(slot, NULL, 0, buf, len);
text_poke(slot, buf, len);
ret = 0;
out:
kfree(buf);
return ret;
err:
__arch_remove_optimized_kprobe(op, 0);
goto out;
}
/*
* Replace breakpoints (INT3) with relative jumps (JMP.d32).
* Caller must call with locking kprobe_mutex and text_mutex.
*
* The caller will have installed a regular kprobe and after that issued
* syncrhonize_rcu_tasks(), this ensures that the instruction(s) that live in
* the 4 bytes after the INT3 are unused and can now be overwritten.
*/
void arch_optimize_kprobes(struct list_head *oplist)
{
struct optimized_kprobe *op, *tmp;
u8 insn_buff[JMP32_INSN_SIZE];
list_for_each_entry_safe(op, tmp, oplist, list) {
s32 rel = (s32)((long)op->optinsn.insn -
((long)op->kp.addr + JMP32_INSN_SIZE));
WARN_ON(kprobe_disabled(&op->kp));
/* Backup instructions which will be replaced by jump address */
memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_INSN_SIZE,
DISP32_SIZE);
insn_buff[0] = JMP32_INSN_OPCODE;
*(s32 *)(&insn_buff[1]) = rel;
smp_text_poke_single(op->kp.addr, insn_buff, JMP32_INSN_SIZE, NULL);
list_del_init(&op->list);
}
}
/*
* Replace a relative jump (JMP.d32) with a breakpoint (INT3).
*
* After that, we can restore the 4 bytes after the INT3 to undo what
* arch_optimize_kprobes() scribbled. This is safe since those bytes will be
* unused once the INT3 lands.
*/
void arch_unoptimize_kprobe(struct optimized_kprobe *op)
{
u8 new[JMP32_INSN_SIZE] = { INT3_INSN_OPCODE, };
u8 old[JMP32_INSN_SIZE];
u8 *addr = op->kp.addr;
memcpy(old, op->kp.addr, JMP32_INSN_SIZE);
memcpy(new + INT3_INSN_SIZE,
op->optinsn.copied_insn,
JMP32_INSN_SIZE - INT3_INSN_SIZE);
text_poke(addr, new, INT3_INSN_SIZE);
smp_text_poke_sync_each_cpu();
text_poke(addr + INT3_INSN_SIZE,
new + INT3_INSN_SIZE,
JMP32_INSN_SIZE - INT3_INSN_SIZE);
smp_text_poke_sync_each_cpu();
perf_event_text_poke(op->kp.addr, old, JMP32_INSN_SIZE, new, JMP32_INSN_SIZE);
}
/*
* Recover original instructions and breakpoints from relative jumps.
* Caller must call with locking kprobe_mutex.
*/
extern void arch_unoptimize_kprobes(struct list_head *oplist,
struct list_head *done_list)
{
struct optimized_kprobe *op, *tmp;
list_for_each_entry_safe(op, tmp, oplist, list) {
arch_unoptimize_kprobe(op);
list_move(&op->list, done_list);
}
}
int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter)
{
struct optimized_kprobe *op;
if (p->flags & KPROBE_FLAG_OPTIMIZED) {
/* This kprobe is really able to run optimized path. */
op = container_of(p, struct optimized_kprobe, kp);
/* Detour through copied instructions */
regs->ip = (unsigned long)op->optinsn.insn + TMPL_END_IDX;
if (!reenter)
reset_current_kprobe();
return 1;
}
return 0;
}
NOKPROBE_SYMBOL(setup_detour_execution);