为什么 QEMU return 在填充 PML4 的高半部分时地址错误？

Question

我正在编写一个小型 x86-64 OS 我使用 UEFI 启动。我试图通过将内核的可执行文件移动到 0x800000000000 来使内核成为高半内核。这个地址应该在 PML4 的中间。基本上，我应该填写 PML4 的条目 256 来解决这个较高的一半。我尝试这样做，但我的代码出现三重故障。由于我在 QEMU 上测试内核并使用 GDB 进行调试，因此我在 GDB 中使用 monitor info mem 来查看虚拟地址到物理地址的映射。它返回以下内容：

(gdb) monitor info mem
0000000000000000-0000000000400000 0000000000400000 -rw
ffff800000000000-ffff800000c00000 0000000000c00000 -rw

它映射的不是 0x800000000000，而是 ffff800000000000。这可能就是为什么当我跳到上半部分时代码出现三重错误的原因。这是我的代码的一个小例子：

typedef unsigned char UINT8;
typedef unsigned short UINT16;
typedef unsigned int UINT32;
typedef unsigned long UINT64;

struct GDT{
    UINT64 nullDescriptor;
    
    UINT16 codeLimit;
    UINT16 codeBaseLow;
    UINT8 codeBaseMid;
    UINT8 codeFlags;
    UINT8 codeLimitMid;
    UINT8 codeBaseHigh;
    
    UINT16 dataLimit;
    UINT16 dataBaseLow;
    UINT8 dataBaseMid;
    UINT8 dataFlags;
    UINT8 dataLimitMid;
    UINT8 dataBaseHigh;
}__attribute__((packed));

struct GDTR{
    UINT16 size;
    GDT* address;
}__attribute__((packed));

void main(){
    //Identity mapping for the first 4MB
    UINT64* pml4Ptr = (UINT64*)0x200000;
    *pml4Ptr = 0x20101b;
    
    UINT64* pdpPtr = (UINT64*)0x201000;
    *pdpPtr = 0x20201b;
    
    UINT64* pdPtr = (UINT64*)0x202000;
    *pdPtr = 0x20301b;
    *(pdPtr + 1) = 0x20401b;
    
    UINT64* ptPtr = (UINT64*)0x203000;
    UINT64 physAddr = 0x1b;
    for (UINT32 i = 0; i < 2 * 512; i++){
        *(ptPtr + i) = physAddr;
        physAddr += 0x1000;
    }
    
    //Kernel mapping for the higher half
    *(pml4Ptr + 256) = 0x20601b; //When this is less then 256 I get the right addresses
    
    pdpPtr = (UINT64*)0x206000;
    *pdpPtr = 0x20701b;
    
    pdPtr = (UINT64*)0x207000;
    *pdPtr = 0x20801b;
    *(pdPtr + 1) = 0x20901b;
    *(pdPtr + 2) = 0x20a01b;
    *(pdPtr + 3) = 0x20b01b;
    *(pdPtr + 4) = 0x20c01b;
    *(pdPtr + 5) = 0x20d01b;
    
    ptPtr = (UINT64*)0x208000;
    physAddr = 0x1b;
    for (UINT32 i = 0; i < 6 * 512; i++){
        *(ptPtr + i) = physAddr;
        physAddr += 0x1000;
    }

    asm volatile(
    "movq [=12=]x200018, %rax\n\t"
    "mov %rax, %cr3\n\t"
    "movq [=12=]x375000, %rsp\n\t"
    );
        
    GDT gdt = {
        .nullDescriptor = 0,
        
        .codeLimit = 0x0000,
        .codeBaseLow = 0,
        .codeBaseMid = 0,
        .codeFlags = 0x9a,
        .codeLimitMid = 0xaf,
        .codeBaseHigh = 0,
        
        .dataLimit = 0x0000,
        .dataBaseLow = 0,
        .dataBaseMid = 0,
        .dataFlags = 0x92,
        .dataLimitMid = 0x00,
        .dataBaseHigh = 0
    };
    
    GDT* gdtAddr = &gdt;
    GDTR gdtr = { 23, gdtAddr };
    GDTR* gdtrAddr = &gdtr;
    
    asm volatile("lgdt (%0)" : : "r"(gdtrAddr));
    
    asm volatile(
    "sub , %rsp\n\t"
    "movq , 8(%rsp)\n\t"
    "movabsq $fun, %rax\n\t"
    "mov %rax, (%rsp)\n\t"
    "lretq\n\t"
    "fun:\n\t"
    "movq [=12=]x10, %rax\n\t"
    "mov %ax, %ss\n\t"
    "mov %ax, %es\n\t"
    "mov %ax, %ds\n\t"
    "mov %ax, %gs\n\t"
    "mov %ax, %fs\n\t"
    "hlt"
    );
}

我有一个指向 PML4 地址的指针，然后我 *(pml4Ptr + 256) = 0x20601b;。这应该在没有缓存的情况下将 PML4 的条目 256 映射到 0x206000。内核映射部分下的其余小代码片段应该将 12MB 的数据映射到从物理地址 0 开始的虚拟地址的高半部分。相反，我得到上面的地址，这看起来很奇怪。

如果我用相同的代码 (*(pml4Ptr + 255) = 0x20601b;) 设置 PML4 的条目 255，我得到以下结果：

(gdb) monitor info mem
0000000000000000-0000000000400000 0000000000400000 -rw
00007f8000000000-00007f8000c00000 0000000000c00000 -rw

我居然找到了正确的地址！？当您填充上半部分时，是否存在 QEMU 无法正确处理 PML4 的已知错误，或者我在代码中忽略了什么？

我还直接查看了页表（因为它们位于 RAM 中的静态位置）。我得到以下结果：

user@user-System-Product-Name:~$ hexdump -C result.bin
00000000  3b 10 20 00 00 00 00 00  00 00 00 00 00 00 00 00  |;. .............|
00000010  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  |................|
*
00000800  1b 60 20 00 00 00 00 00  00 00 00 00 00 00 00 00  |.` .............|
00000810  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  |................|
*
00001000  3b 20 20 00 00 00 00 00  00 00 00 00 00 00 00 00  |;  .............|
00001010  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  |................|
*
00002000  1b 30 20 00 00 00 00 00  3b 40 20 00 00 00 00 00  |.0 .....;@ .....|
00002010  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  |................|
*
00003000  1b 00 00 00 00 00 00 00  1b 10 00 00 00 00 00 00  |................|
00003010  1b 20 00 00 00 00 00 00  1b 30 00 00 00 00 00 00  |. .......0......|
00003020  1b 40 00 00 00 00 00 00  1b 50 00 00 00 00 00 00  |.@.......P......|
00003030  1b 60 00 00 00 00 00 00  1b 70 00 00 00 00 00 00  |.`.......p......|
00003040  1b 80 00 00 00 00 00 00  1b 90 00 00 00 00 00 00  |................|
00003050  1b a0 00 00 00 00 00 00  1b b0 00 00 00 00 00 00  |................|
00003060  1b c0 00 00 00 00 00 00  1b d0 00 00 00 00 00 00  |................|
00003070  1b e0 00 00 00 00 00 00  1b f0 00 00 00 00 00 00  |................|
00003080  1b 00 01 00 00 00 00 00  1b 10 01 00 00 00 00 00  |................|
00003090  1b 20 01 00 00 00 00 00  1b 30 01 00 00 00 00 00  |. .......0......|
000030a0  1b 40 01 00 00 00 00 00  1b 50 01 00 00 00 00 00  |.@.......P......|
000030b0  1b 60 01 00 00 00 00 00  1b 70 01 00 00 00 00 00  |.`.......p......|
000030c0  1b 80 01 00 00 00 00 00  1b 90 01 00 00 00 00 00  |................|
000030d0  1b a0 01 00 00 00 00 00  1b b0 01 00 00 00 00 00  |................|
000030e0  1b c0 01 00 00 00 00 00  1b d0 01 00 00 00 00 00  |................|
000030f0  1b e0 01 00 00 00 00 00  1b f0 01 00 00 00 00 00  |................|
00003100  1b 00 02 00 00 00 00 00  1b 10 02 00 00 00 00 00  |................|
00003110  1b 20 02 00 00 00 00 00  1b 30 02 00 00 00 00 00  |. .......0......|
00003120  1b 40 02 00 00 00 00 00  1b 50 02 00 00 00 00 00  |.@.......P......|
00003130  1b 60 02 00 00 00 00 00  1b 70 02 00 00 00 00 00  |.`.......p......|
00003140  1b 80 02 00 00 00 00 00  1b 90 02 00 00 00 00 00  |................|
00003150  1b a0 02 00 00 00 00 00  1b b0 02 00 00 00 00 00  |................|
00003160  1b c0 02 00 00 00 00 00  1b d0 02 00 00 00 00 00  |................|
00003170  1b e0 02 00 00 00 00 00  1b f0 02 00 00 00 00 00  |................|
00003180  1b 00 03 00 00 00 00 00  1b 10 03 00 00 00 00 00  |................|
00003190  1b 20 03 00 00 00 00 00  1b 30 03 00 00 00 00 00  |. .......0......|
000031a0  1b 40 03 00 00 00 00 00  1b 50 03 00 00 00 00 00  |.@.......P......|
000031b0  1b 60 03 00 00 00 00 00  1b 70 03 00 00 00 00 00  |.`.......p......|
000031c0  1b 80 03 00 00 00 00 00  1b 90 03 00 00 00 00 00  |................|
000031d0  1b a0 03 00 00 00 00 00  1b b0 03 00 00 00 00 00  |................|
000031e0  1b c0 03 00 00 00 00 00  1b d0 03 00 00 00 00 00  |................|
000031f0  1b e0 03 00 00 00 00 00  1b f0 03 00 00 00 00 00  |................|
00003200  1b 00 04 00 00 00 00 00  1b 10 04 00 00 00 00 00  |................|
00003210  1b 20 04 00 00 00 00 00  1b 30 04 00 00 00 00 00  |. .......0......|
00003220  1b 40 04 00 00 00 00 00  1b 50 04 00 00 00 00 00  |.@.......P......|
00003230  1b 60 04 00 00 00 00 00  1b 70 04 00 00 00 00 00  |.`.......p......|
00003240  1b 80 04 00 00 00 00 00  1b 90 04 00 00 00 00 00  |................|
00003250  1b a0 04 00 00 00 00 00  1b b0 04 00 00 00 00 00  |................|
00003260  1b c0 04 00 00 00 00 00  1b d0 04 00 00 00 00 00  |................|
00003270  1b e0 04 00 00 00 00 00  1b f0 04 00 00 00 00 00  |................|
00003280  1b 00 05 00 00 00 00 00  1b 10 05 00 00 00 00 00  |................|
...
...
00004fa0  1b 40 3f 00 00 00 00 00  1b 50 3f 00 00 00 00 00  |.@?......P?.....|
00004fb0  1b 60 3f 00 00 00 00 00  1b 70 3f 00 00 00 00 00  |.`?......p?.....|
00004fc0  1b 80 3f 00 00 00 00 00  1b 90 3f 00 00 00 00 00  |..?.......?.....|
00004fd0  1b a0 3f 00 00 00 00 00  1b b0 3f 00 00 00 00 00  |..?.......?.....|
00004fe0  1b c0 3f 00 00 00 00 00  1b d0 3f 00 00 00 00 00  |..?.......?.....|
00004ff0  1b e0 3f 00 00 00 00 00  1b f0 3f 00 00 00 00 00  |..?.......?.....|
00005000  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  |................|
*
00006000  1b 70 20 00 00 00 00 00  00 00 00 00 00 00 00 00  |.p .............|
00006010  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  |................|
*
00007000  1b 80 20 00 00 00 00 00  1b 90 20 00 00 00 00 00  |.. ....... .....|
00007010  1b a0 20 00 00 00 00 00  1b b0 20 00 00 00 00 00  |.. ....... .....|
00007020  1b c0 20 00 00 00 00 00  1b d0 20 00 00 00 00 00  |.. ....... .....|
00007030  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  |................|
*
00008000  1b 00 00 00 00 00 00 00  1b 10 00 00 00 00 00 00  |................|
00008010  1b 20 00 00 00 00 00 00  1b 30 00 00 00 00 00 00  |. .......0......|
00008020  1b 40 00 00 00 00 00 00  1b 50 00 00 00 00 00 00  |.@.......P......|
00008030  1b 60 00 00 00 00 00 00  1b 70 00 00 00 00 00 00  |.`.......p......|
00008040  1b 80 00 00 00 00 00 00  1b 90 00 00 00 00 00 00  |................|
00008050  1b a0 00 00 00 00 00 00  1b b0 00 00 00 00 00 00  |................|
00008060  1b c0 00 00 00 00 00 00  1b d0 00 00 00 00 00 00  |................|
00008070  1b e0 00 00 00 00 00 00  1b f0 00 00 00 00 00 00  |................|
00008080  1b 00 01 00 00 00 00 00  1b 10 01 00 00 00 00 00  |................|
00008090  1b 20 01 00 00 00 00 00  1b 30 01 00 00 00 00 00  |. .......0......|
000080a0  1b 40 01 00 00 00 00 00  1b 50 01 00 00 00 00 00  |.@.......P......|
000080b0  1b 60 01 00 00 00 00 00  1b 70 01 00 00 00 00 00  |.`.......p......|
000080c0  1b 80 01 00 00 00 00 00  1b 90 01 00 00 00 00 00  |................|
000080d0  1b a0 01 00 00 00 00 00  1b b0 01 00 00 00 00 00  |................|
000080e0  1b c0 01 00 00 00 00 00  1b d0 01 00 00 00 00 00  |................|
000080f0  1b e0 01 00 00 00 00 00  1b f0 01 00 00 00 00 00  |................|
00008100  1b 00 02 00 00 00 00 00  1b 10 02 00 00 00 00 00  |................|
00008110  1b 20 02 00 00 00 00 00  1b 30 02 00 00 00 00 00  |. .......0......|
00008120  1b 40 02 00 00 00 00 00  1b 50 02 00 00 00 00 00  |.@.......P......|
00008130  1b 60 02 00 00 00 00 00  1b 70 02 00 00 00 00 00  |.`.......p......|
00008140  1b 80 02 00 00 00 00 00  1b 90 02 00 00 00 00 00  |................|
00008150  1b a0 02 00 00 00 00 00  1b b0 02 00 00 00 00 00  |................|
00008160  1b c0 02 00 00 00 00 00  1b d0 02 00 00 00 00 00  |................|
00008170  1b e0 02 00 00 00 00 00  1b f0 02 00 00 00 00 00  |................|
00008180  1b 00 03 00 00 00 00 00  1b 10 03 00 00 00 00 00  |................|
00008190  1b 20 03 00 00 00 00 00  1b 30 03 00 00 00 00 00  |. .......0......|
000081a0  1b 40 03 00 00 00 00 00  1b 50 03 00 00 00 00 00  |.@.......P......|
000081b0  1b 60 03 00 00 00 00 00  1b 70 03 00 00 00 00 00  |.`.......p......|
000081c0  1b 80 03 00 00 00 00 00  1b 90 03 00 00 00 00 00  |................|
000081d0  1b a0 03 00 00 00 00 00  1b b0 03 00 00 00 00 00  |................|
000081e0  1b c0 03 00 00 00 00 00  1b d0 03 00 00 00 00 00  |................|
000081f0  1b e0 03 00 00 00 00 00  1b f0 03 00 00 00 00 00  |................|
00008200  1b 00 04 00 00 00 00 00  1b 10 04 00 00 00 00 00  |................|
00008210  1b 20 04 00 00 00 00 00  1b 30 04 00 00 00 00 00  |. .......0......|
00008220  1b 40 04 00 00 00 00 00  1b 50 04 00 00 00 00 00  |.@.......P......|
00008230  1b 60 04 00 00 00 00 00  1b 70 04 00 00 00 00 00  |.`.......p......|
00008240  1b 80 04 00 00 00 00 00  1b 90 04 00 00 00 00 00  |................|
00008250  1b a0 04 00 00 00 00 00  1b b0 04 00 00 00 00 00  |................|
00008260  1b c0 04 00 00 00 00 00  1b d0 04 00 00 00 00 00  |................|
00008270  1b e0 04 00 00 00 00 00  1b f0 04 00 00 00 00 00  |................|
00008280  1b 00 05 00 00 00 00 00  1b 10 05 00 00 00 00 00  |................|
00008290  1b 20 05 00 00 00 00 00  1b 30 05 00 00 00 00 00  |. .......0......|
000082a0  1b 40 05 00 00 00 00 00  1b 50 05 00 00 00 00 00  |.@.......P......|
000082b0  1b 60 05 00 00 00 00 00  1b 70 05 00 00 00 00 00  |.`.......p......|
000082c0  1b 80 05 00 00 00 00 00  1b 90 05 00 00 00 00 00  |................|
000082d0  1b a0 05 00 00 00 00 00  1b b0 05 00 00 00 00 00  |................|
000082e0  1b c0 05 00 00 00 00 00  1b d0 05 00 00 00 00 00  |................|
000082f0  1b e0 05 00 00 00 00 00  1b f0 05 00 00 00 00 00  |................|
00008300  1b 00 06 00 00 00 00 00  1b 10 06 00 00 00 00 00  |................|
00008310  1b 20 06 00 00 00 00 00  1b 30 06 00 00 00 00 00  |. .......0......|
00008320  1b 40 06 00 00 00 00 00  1b 50 06 00 00 00 00 00  |.@.......P......|
00008330  1b 60 06 00 00 00 00 00  1b 70 06 00 00 00 00 00  |.`.......p......|
00008340  1b 80 06 00 00 00 00 00  1b 90 06 00 00 00 00 00  |................|
00008350  1b a0 06 00 00 00 00 00  1b b0 06 00 00 00 00 00  |................|
00008360  1b c0 06 00 00 00 00 00  1b d0 06 00 00 00 00 00  |................|
00008370  1b e0 06 00 00 00 00 00  1b f0 06 00 00 00 00 00  |................|
00008380  1b 00 07 00 00 00 00 00  1b 10 07 00 00 00 00 00  |................|
00008390  1b 20 07 00 00 00 00 00  1b 30 07 00 00 00 00 00  |. .......0......|
000083a0  1b 40 07 00 00 00 00 00  1b 50 07 00 00 00 00 00  |.@.......P......|
000083b0  1b 60 07 00 00 00 00 00  1b 70 07 00 00 00 00 00  |.`.......p......|
000083c0  1b 80 07 00 00 00 00 00  1b 90 07 00 00 00 00 00  |................|
000083d0  1b a0 07 00 00 00 00 00  1b b0 07 00 00 00 00 00  |................|
000083e0  1b c0 07 00 00 00 00 00  1b d0 07 00 00 00 00 00  |................|

这个转储似乎是正确的。它从 0x200000 开始。这意味着转储中的地址 0 是 0x200000，地址 0x1000 是 0x201000 等

我用这个脚本编译代码：

g++ -fomit-frame-pointer --static -ffreestanding -nostdlib -mgeneral-regs-only -mno-red-zone -c -m64 Startup/Source/Main.cpp -oStartup/Object/Main.o
ld -entry main --oformat elf64-x86-64 --no-dynamic-linker -static -nostdlib -Ttext-segment=300000 Startup/Object/Main.o -ostartup.elf

谁能指出代码的任何问题或我忽略的任何问题？

Answer 1

0x800000000000 不是规范地址，因此页面目录布局中没有它的位置。（并且尝试取消引用它会 #GP 出错，而不是触发 TLB 未命中 => 页面遍历。）

您有 PML4，因此前 16 个虚拟地址位必须是位 #47 的副本。即指针必须可以表示为 48 位值符号扩展到 64 位。
即 ((int64_t)addr << 16) >> 16 == addr 必须为真。
（右移使用sar算术右移）。
(x86-64 canonical address?).

可用（规范）范围的上半部分实际上确实从ffff800000000000开始，PML4E为它确实紧跟在下半部分的顶部 00007f8000000000.

之后
包含虚拟地址 space.
中空洞的 ASCII 图
关于低半部分顶部的位置是正确的，但是您忘记将符号扩展 0x800000000000 到 64 位以到达高半部分的底部。指针名义上仍然是 64 位，而不仅仅是截断为 48 位。这就是为什么像 ffff800000000000 这样的地址可以存在的原因。

如果您启用了 PML5（例如 Ice Lake 硬件或该功能的软件仿真），额外级别的页面目录将使您获得最多 57 位的虚拟地址 space，从而可以地址 0x800000000000.

另见

为什么 QEMU return 在填充 PML4 的高半部分时地址错误？

Why does QEMU return the wrong addresses when filling the higher half of the PML4?

paging

kernel

x86-64

osdev

page-tables