注意:我正在FreeBSD上运行,但是我也将Linux作为标签,因为问题在某种程度上是普遍的,而Linux特定的解决方案对我很感兴趣。
编辑:只是为了确认问题不是特定于FreeBSD,我将模块移植到Linux,并且确实获得了完全相同的行为。下面给出了该模块的Linux版本的代码;它本质上是完全相同的,唯一的主要区别是在Linux中IDT显然具有只读保护,因此我必须禁用cr0
中的写保护位才能使代码正常工作。
我正在学习一些有关在x86-64架构上进行内核开发的知识,目前正在阅读《英特尔开发人员手册》中有关中断处理的内容。作为实践,我正在尝试编写一个小的内核模块,该模块挂接IDT中的条目,但是遇到了问题。我的一般问题是:如何确保始终在以下位置显示钩子(Hook)的代码(或新IDT表的数据,如果您使用lidt
更改整个idtr
而不是仅覆盖IDT的各个条目)内存?我一直遇到的问题是,我将更改IDT条目,触发相应的中断,然后出现双重错误,因为我的 Hook 代码未映射到RAM。总的来说,有什么方法可以避免这个问题?
对于我的情况的详细信息,以下是我编写的FreeBSD LKM的代码,该代码仅覆盖IDT条目中列出的地址以处理零除数故障,并将其替换为asm_hook
的地址,目前它只是无条件的jmp
s回到原始的中断处理程序中。 (将来,我当然会添加更多功能。)
#include <sys/types.h>
#include <sys/param.h>
#include <sys/proc.h>
#include <sys/module.h>
#include <sys/sysent.h>
#include <sys/kernel.h>
#include <sys/syscall.h>
#include <sys/sysproto.h>
#include <sys/systm.h>
//idt entry
struct idte_t {
unsigned short offset_0_15;
unsigned short segment_selector;
unsigned char ist; //interrupt stack table
unsigned char type:4;
unsigned char zero_12:1;
unsigned char dpl:2; //descriptor privilege level
unsigned char p:1; //present flag
unsigned short offset_16_31;
unsigned int offset_32_63;
unsigned int rsv; }
__attribute__((packed))
*zd_idte;
#define ZD_INT 0x00
unsigned long idte_offset; //contains absolute address of original interrupt handler
//idt register
struct idtr_t {
unsigned short lim_val;
struct idte_t *addr; }
__attribute__((packed))
idtr;
__asm__(
".text;"
".global asm_hook;"
"asm_hook:;"
"jmp *(idte_offset);");
extern void asm_hook(void);
static int
init() {
__asm__ __volatile__ (
"cli;"
"sidt %0;"
"sti;"
:: "m"(idtr));
uprintf("[*] idtr dump\n"
"[**] address:\t%p\n"
"[**] lim val:\t0x%x\n"
"[*] end dump\n\n",
idtr.addr, idtr.lim_val);
zd_idte=(idtr.addr)+ZD_INT;
idte_offset=(long)(zd_idte->offset_0_15)|((long)(zd_idte->offset_16_31)<<16)|((long)(zd_idte->offset_32_63)<<32);
uprintf("[*] old idt entry %d:\n"
"[**] addr:\t%p\n"
"[**] segment:\t0x%x\n"
"[**] ist:\t%d\n"
"[**] type:\t%d\n"
"[**] dpl:\t%d\n"
"[**] p:\t\t%d\n"
"[*] end dump\n\n",
ZD_INT, (void *)idte_offset, zd_idte->segment_selector,
zd_idte->ist, zd_idte->type, zd_idte->dpl, zd_idte->p);
if(!zd_idte->p) {
uprintf("[*] fatal: handler segment not present\n");
return ENOSYS; }
__asm__ __volatile__("cli");
zd_idte->offset_0_15=((unsigned long)(&asm_hook))&0xffff;
zd_idte->offset_16_31=((unsigned long)(&asm_hook)>>16)&0xffff;
zd_idte->offset_32_63=((unsigned long)(&asm_hook)>>32)&0xffffffff;
__asm__ __volatile__("sti");
uprintf("[*] new idt entry %d:\n"
"[**] addr:\t%p\n"
"[**] segment:\t0x%x\n"
"[**] ist:\t%d\n"
"[**] type:\t%d\n"
"[**] dpl:\t%d\n"
"[**] p:\t\t%d\n"
"[*] end dump\n\n",
ZD_INT, (void *)(\
(long)zd_idte->offset_0_15|((long)zd_idte->offset_16_31<<16)|((long)zd_idte->offset_32_63<<32)),
zd_idte->segment_selector, zd_idte->ist, zd_idte->type, zd_idte->dpl, zd_idte->p);
return 0; }
static void
fini() {
__asm__ __volatile__("cli");
zd_idte->offset_0_15=idte_offset&0xffff;
zd_idte->offset_16_31=(idte_offset>>16)&0xffff;
zd_idte->offset_32_63=(idte_offset>>32)&0xffffffff;
__asm__ __volatile__("sti"); }
static int
load(struct module *module, int cmd, void *arg) {
int error=0;
switch(cmd) {
case MOD_LOAD:
error=init();
break;
case MOD_UNLOAD:
fini();
break;
default:
error=EOPNOTSUPP;
break; }
return error; }
static moduledata_t idt_hook_mod = {
"idt_hook",
load,
NULL };
DECLARE_MODULE(idt_hook, idt_hook_mod, SI_SUB_DRIVERS, SI_ORDER_MIDDLE);
(我还写了另一个LKM,它使用malloc(9)
创建了一个完整的新IDT表并使用lidt
将该表加载到idtr
中,但是在我看来这是一种劣等的方法,因为它只会更改正在运行的特定CPU内核上的IDT,因此无法在多处理器系统中可靠地工作。除非缺少我的东西,否则这是一项准确的评估吗?)无论如何,编译代码并加载内核模块不会导致任何问题:
# kldload ./idt_hook.ko
[*] idtr dump
[**] address: 0xffffffff81fb2c40
[**] lim val: 0xfff
[*] end dump
[*] old idt entry 0:
[**] addr: 0xffffffff81080f90
[**] segment: 0x20
[**] ist: 0
[**] type: 14
[**] dpl: 0
[**] p: 1
[*] end dump
[*] new idt entry 0:
[**] addr: 0xffffffff8281d000
[**] segment: 0x20
[**] ist: 0
[**] type: 14
[**] dpl: 0
[**] p: 1
[*] end dump
但是,当我使用以下命令测试 Hook 时,内核挂起:#include <stdio.h>
int main() {
int x=1, y=0;
printf("x/y=%d\n", x/y);
return 0; }
为了了解发生了什么,我启动了VirtualBox内置调试器,并在IDT的双重故障异常处理程序上设置了一个断点(条目8)。调试显示,我的LKM正确更改了IDT,但是运行上面的零除数代码会引发双重错误。当我尝试访问0xffffffff8281d000
(我的asm_hook
代码的地址)上的内存时,我意识到了这个原因,这在VirtualBox调试器中触发了VERR_PAGE_TABLE_NOT_PRESENT
错误。因此,除非我误解了,否则问题显然是我的asm_hook
在某个时候被从内存中删除了。关于如何解决此问题的任何想法?例如,是否有一种方法可以告诉FreeBSD内核永远不要从RAM中取消映射特定页面?编辑:下面的注释中的Nate Eldredge帮助我找到了我的代码中的一些错误(现已更正),但是不幸的是,问题仍然存在。要提供更多的调试详细信息:首先加载内核模块,然后在VirtualBox调试器中的
asm_hook
代码(0xffffffff8281d000
)列出的地址上设置一个断点。我已通过在该地址处拆解内存来确认它确实包含asm_hook
的代码。 (尽管,正如Nate所指出的那样,它恰好位于页面边界上,这有点奇怪-任何人都不知道为什么会这样吗?)无论如何,当我触发零除数中断时,不幸的是,断点永远不会被击中,而且一旦进入双重故障中断处理程序,当我尝试访问
0xffffffff8281d000
的内存时,VERR_PAGE_TABLE_NOT_PRESENT
错误仍然会标记出来。的确,从RAM换出/取消映射内核部分是FreeBSD设计的一个不寻常的(?)功能,因此也许更好的问题是“是什么导致此页面错误?”
编辑:这是移植到Linux的模块的版本:
#include <linux/init.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <asm/io.h>
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Hooks the zero divisor IDT entry");
MODULE_VERSION("0.01");
struct idte_t {
unsigned short offset_0_15;
unsigned short segment_selector;
unsigned char ist; //interrupt stack table
unsigned char type:4;
unsigned char zero_12:1;
unsigned char dpl:2; //descriptor privilege level
unsigned char p:1; //present flag
unsigned short offset_16_31;
unsigned int offset_32_63;
unsigned int rsv; }
__attribute__((packed))
*zd_idte;
#define ZD_INT 0x00
unsigned long idte_offset; //contains absolute address of original interrupt handler
struct idtr_t {
unsigned short lim_val;
struct idte_t *addr; }
__attribute__((packed))
idtr;
__asm__(
".text;"
".global asm_hook;"
"asm_hook:;"
"jmp *(idte_offset);");
extern void asm_hook(void);
static int __init
idt_init(void) {
__asm__ __volatile__ (
"cli;"
"sidt %0;"
"sti;"
:: "m"(idtr));
printk("[*] idtr dump\n"
"[**] address:\t%px\n"
"[**] lim val:\t0x%x\n"
"[*] end dump\n\n",
idtr.addr, idtr.lim_val);
zd_idte=(idtr.addr)+ZD_INT;
idte_offset=(long)(zd_idte->offset_0_15)|((long)(zd_idte->offset_16_31)<<16)|((long)(zd_idte->offset_32_63)<<32);
printk("[*] old idt entry %d:\n"
"[**] addr:\t%px\n"
"[**] segment:\t0x%x\n"
"[**] ist:\t%d\n"
"[**] type:\t%d\n"
"[**] dpl:\t%d\n"
"[**] p:\t\t%d\n"
"[*] end dump\n\n",
ZD_INT, (void *)idte_offset, zd_idte->segment_selector,
zd_idte->ist, zd_idte->type, zd_idte->dpl, zd_idte->p);
if(!zd_idte->p) {
printk("[*] fatal: handler segment not present\n");
return ENOSYS; }
unsigned long cr0;
__asm__ __volatile__("mov %%cr0, %0" : "=r"(cr0));
cr0 &= ~(long)0x10000;
__asm__ __volatile__("mov %0, %%cr0" :: "r"(cr0));
__asm__ __volatile__("cli");
zd_idte->offset_0_15=((unsigned long)(&asm_hook))&0xffff;
zd_idte->offset_16_31=((unsigned long)(&asm_hook)>>16)&0xffff;
zd_idte->offset_32_63=((unsigned long)(&asm_hook)>>32)&0xffffffff;
__asm__ __volatile__("sti");
cr0 |= 0x10000;
__asm__ __volatile__("mov %0, %%cr0" :: "r"(cr0));
printk("[*] new idt entry %d:\n"
"[**] addr:\t%px\n"
"[**] segment:\t0x%x\n"
"[**] ist:\t%d\n"
"[**] type:\t%d\n"
"[**] dpl:\t%d\n"
"[**] p:\t\t%d\n"
"[*] end dump\n\n",
ZD_INT, (void *)(\
(long)zd_idte->offset_0_15|((long)zd_idte->offset_16_31<<16)|((long)zd_idte->offset_32_63<<32)),
zd_idte->segment_selector, zd_idte->ist, zd_idte->type, zd_idte->dpl, zd_idte->p);
return 0; }
static void __exit
idt_fini(void) {
unsigned long cr0;
__asm__ __volatile__("mov %%cr0, %0" : "=r"(cr0));
cr0 &= ~(long)0x10000;
__asm__ __volatile__("mov %0, %%cr0" :: "r"(cr0));
__asm__ __volatile__("cli");
zd_idte->offset_0_15=idte_offset&0xffff;
zd_idte->offset_16_31=(idte_offset>>16)&0xffff;
zd_idte->offset_32_63=(idte_offset>>32)&0xffffffff;
__asm__ __volatile__("sti");
cr0 |= 0x10000;
__asm__ __volatile__("mov %0, %%cr0" :: "r"(cr0)); }
module_init(idt_init);
module_exit(idt_fini);
最佳答案
编辑07/18/20 :很抱歉,要复活一个已死的帖子,但实际上,故事还有很多。简而言之,问题实际上不在于VirtualBox,而是由于我的代码无法解决崩溃缓解技术,尤其是内核页表隔离。显然,Qemu默认情况下不启用KPTI,这就是为什么该问题似乎是特定于虚拟机管理程序的原因。但是,通过Qemu启用OS X的“Hypervisor框架”(默认情况下确实启用KPTI)导致该模块再次失败。经过大量调查,我终于意识到问题出在KPTI。像许多内核代码一样,显然可加载的内核模块未包含在用户空间页表中。
为了解决这个问题,我必须编写一个新模块,用一个代码片段覆盖内核现有的IRQ处理程序(包括在用户空间页面表中)的代码,并将cr3
更改为一个值,该值将包含我的内核模块的页面条目。 (这是下面代码中的stub
。)然后,我跳到asm_hook
–现在分页了–增加我的计数器变量,恢复cr3
的旧值,然后跳到现有的内核IRQ处理程序。 (因为除法错误处理程序被覆盖,所以我跳到了软断点处理程序。)下面的代码可以用相同的零除程序进行测试。
#include <linux/init.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/kallsyms.h>
#include <asm/io.h>
#include "utilities.h"
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Atticus Stonestrom");
MODULE_DESCRIPTION("Hooks the zero divisor IDT entry");
struct idte_t *idte; //points to the start of the IDT
#define ZD_INT 0x00
#define BP_INT 0x03
unsigned long zd_handler; //contains absolute address of division error IRQ handler
unsigned long bp_handler; //contains absolute address of soft breakpoint IRQ handler
#define STUB_SIZE 0x2b //includes extra 8 bytes for the old value of cr3
unsigned char orig_bytes[STUB_SIZE]; //contains the original bytes of the division error IRQ handler
struct idtr_t idtr; //holds base address and limit value of the IDT
int counter=0;
__asm__(
".text;"
".global asm_hook;"
"asm_hook:;"
"incl counter;"
"movq (bp_handler), %rax;"
"ret;");
extern void asm_hook(void);
__asm__(
".text;"
".global stub;"
"stub:;"
"push %rax;" //bp_handler
"push %rbx;" //new cr3, &asm_hook
"push %rdx;" //old cr3
"mov %cr3, %rdx;"
"mov .CR3(%rip), %rbx;"
"mov %rbx, %cr3;"
"mov $asm_hook, %rbx;"
"call *%rbx;"
"mov %rdx, %cr3;"
"pop %rdx;"
"pop %rbx;"
"xchg %rax, (%rsp);"
"ret;"
".CR3:;"
//will be filled with a valid value of cr3 during module initialization
".quad 0xdeadbeefdeadbeef;");
extern void stub(void);
static int __init
idt_init(void) {
READ_IDT(idtr)
printk("[*] idtr dump\n"
"[**] address:\t0x%px\n"
"[**] lim val:\t0x%x\n"
"[*] end dump\n\n",
idtr.addr, idtr.lim_val);
idte=(idtr.addr);
zd_handler=0
| ((long)((idte+ZD_INT)->offset_0_15))
| ((long)((idte+ZD_INT)->offset_16_31)<<16)
| ((long)((idte+ZD_INT)->offset_32_63)<<32);
printk("[*] idt entry %d:\n"
"[**] addr:\t0x%px\n"
"[**] segment:\t0x%x\n"
"[**] ist:\t%d\n"
"[**] type:\t%d\n"
"[**] dpl:\t%d\n"
"[**] p:\t\t%d\n"
"[*] end dump\n\n",
ZD_INT, (void *)zd_handler, (idte+ZD_INT)->segment_selector,
(idte+ZD_INT)->ist, (idte+ZD_INT)->type, (idte+ZD_INT)->dpl, (idte+ZD_INT)->p);
if(!(idte+ZD_INT)->p) {
printk("[*] fatal: handler segment not present\n");
return ENOSYS; }
bp_handler=0
| ((long)((idte+BP_INT)->offset_0_15))
| ((long)((idte+BP_INT)->offset_16_31)<<16)
| ((long)((idte+BP_INT)->offset_32_63)<<32);
printk("[*] breakpoint handler:\t0x%lx\n\n", bp_handler);
unsigned long cr3;
__asm__ __volatile__("mov %%cr3, %0":"=r"(cr3)::"memory");
printk("[*] cr3:\t0x%lx\n\n", cr3);
memcpy(orig_bytes, (void *)zd_handler, STUB_SIZE);
DISABLE_RW_PROTECTION
__asm__ __volatile__("cli":::"memory");
memcpy((void *)zd_handler, &stub, STUB_SIZE);
*(unsigned long *)(zd_handler+STUB_SIZE-8)=cr3; //fills the .CR3 data section of stub with a value of cr3 guaranteed to have the code asm_hook paged in
__asm__ __volatile__("sti":::"memory");
ENABLE_RW_PROTECTION
return 0; }
static void __exit
idt_fini(void) {
printk("[*] counter: %d\n\n", counter);
DISABLE_RW_PROTECTION
__asm__ __volatile__("cli":::"memory");
memcpy((void *)zd_handler, orig_bytes, STUB_SIZE);
__asm__ __volatile__("sti":::"memory");
ENABLE_RW_PROTECTION }
module_init(idt_init);
module_exit(idt_fini);
utilities.h
仅包含一些相关的IDT宏和structs
,例如:#define DISABLE_RW_PROTECTION \
__asm__ __volatile__( \
"mov %%cr0, %%rax;" \
"and $0xfffffffffffeffff, %%rax;" \
"mov %%rax, %%cr0;" \
:::"rax");
#define ENABLE_RW_PROTECTION \
__asm__ __volatile__( \
"mov %%cr0, %%rax;" \
"or $0x10000, %%rax;" \
"mov %%rax, %%cr0;" \
:::"rax");
struct idte_t {
unsigned short offset_0_15;
unsigned short segment_selector;
unsigned char ist; //interrupt stack table
unsigned char type:4;
unsigned char zero_12:1;
unsigned char dpl:2; //descriptor privilege level
unsigned char p:1; //present flag
unsigned short offset_16_31;
unsigned int offset_32_63;
unsigned int rsv; }
__attribute__((packed));
struct idtr_t {
unsigned short lim_val;
struct idte_t *addr; }
__attribute__((packed));
#define READ_IDT(dst) \
__asm__ __volatile__( \
"cli;" \
"sidt %0;" \
"sti;" \
:: "m"(dst) \
: "memory");
#define WRITE_IDT(src) \
__asm__ __volatile__( \
"cli;" \
"lidt %0;" \
"sti;" \
:: "m"(src) \
: "memory");
删除模块后,dmesg
将显示调用除错处理程序的次数,表示成功。*显然问题不是与我的代码有关,而是与VirtualBox有关。在VirtualBox调试器中玩耍时,我意识到,一旦进入IDT/IRQ处理程序,尝试访问甚至内核内存的某些区域都会标志
VERR_PAGE_TABLE_NOT_PRESENT
错误,因此看起来VirtualBox的实现中的某些内容必须定期换出内核内存的区域。对我来说,这似乎很奇怪,但不幸的是,据我所知,VirtualBox并没有太多的文档。如果有人对这里发生的事情有任何见解,我很想听听。无论如何,我都切换到
qemu
,内核模块在那里完美运行。为了后代,为确认其正常工作,请对模块代码进行以下修改(特别是我更改了Linux):int counter=0;
__asm__(
".text;"
".global asm_hook;"
"asm_hook:;"
"incl counter;"
"jmp *(idte_offset);");
...
static void __exit
idt_fini(void) {
printk("[*] counter:\t%d\n\n", counter);
...
装入内核模块后,请运行几次“除零”程序,然后卸载模块并检查dmesg
以确保其正常工作。因此,总而言之,问题不在于代码,而在于VirtualBox本身。不过,感谢所有尝试提供帮助的人。*
关于c - 避免IDT Hook 中的页面错误,我们在Stack Overflow上找到一个类似的问题:https://stackoverflow.com/questions/62642185/