Re: [PATCH v3 7/7] x86, kaslr, 64bit: Set new or extra ident_mapping

[Kees Cook]

On Sat, Mar 7, 2015 at 2:07 PM, Yinghai Lu <yinghai@xxxxxxxxxx> wrote:
> First, aslr will support to put random VO above 4G, so we must set ident
> mapping for the range even we come from startup_32 path.
>
> Second, when boot from 64bit bootloader, bootloader set ident mapping,
> and boot via ZO (arch/x86/boot/compressed/vmlinux) startup_64.
> Those pages for pagetable need to be avoided when we select new random
> VO (vmlinux) base. Otherwise decompressor would overwrite them during
> decompressing.
>
> One solution: go through pagetable and find out every page is used by
> pagetable for every mem_aovid checking but we will need extra code.
>
> Other solution: create new ident mapping instead, and pages for pagetable
> will sit in _pagetable section of ZO, and they are in mem_avoid array already.
> In this way, we can reuse the code for setting ident mapping.
>
> The _pgtable will be shared 32bit and 64bit path to reduce init_size,
> as now ZO _rodata to _end will contribute init_size.
>
> Need to increase pgt buffer size.
> When boot via startup_64, as we need to cover old VO, params, cmdline
> and new VO, in extreme case we could have them all cross 512G boundary,
> will need (2+2)*4 pages with 2M mapping. And need 2 for first 2M for vga ram.
> Plus one for level4. Total will be 19 pages.
> When boot via startup_32, aslr would move new VO above 4G, we need set extra
> ident mapping for new VO, pgt buffer come from _pgtable offset 6 pages.
> should only need (2+2) pages at most when it cross 512G boundary.
> So 19 pages could make both pathes happy.
>
>
> -v3: add mapping for first 2M with video ram when X86_VERBOSE_BOOTUP is set.
>      Don't need to set mapping for setup_data, as it is already late
>      in boot/ZO stage, will not access it until VO stage, and VO stage
>      will use early_memmap or kernel address to access them.
>
> Cc: Kees Cook <keescook@xxxxxxxxxxxx>
> Cc: Jiri Kosina <jkosina@xxxxxxx>
> Cc: Borislav Petkov <bp@xxxxxxx>
> Cc: Matt Fleming <matt.fleming@xxxxxxxxx>
> Signed-off-by: Yinghai Lu <yinghai@xxxxxxxxxx>
> ---
>  arch/x86/boot/compressed/aslr.c     | 21 ++++++++
>  arch/x86/boot/compressed/head_64.S  |  4 +-
>  arch/x86/boot/compressed/misc_pgt.c | 98 +++++++++++++++++++++++++++++++++++++
>  arch/x86/include/asm/boot.h         | 19 +++++++
>  4 files changed, 140 insertions(+), 2 deletions(-)
>  create mode 100644 arch/x86/boot/compressed/misc_pgt.c
>
> diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c
> index a279514..34eb652 100644
> --- a/arch/x86/boot/compressed/aslr.c
> +++ b/arch/x86/boot/compressed/aslr.c
> @@ -1,3 +1,8 @@
> +#ifdef CONFIG_X86_64
> +#define __pa(x)  ((unsigned long)(x))
> +#define __va(x)  ((void *)((unsigned long)(x)))
> +#endif
> +
>  #include "misc.h"
>
>  #include <asm/msr.h>
> @@ -21,6 +26,8 @@ struct kaslr_setup_data {
>         __u8 data[1];
>  } kaslr_setup_data;
>
> +#include "misc_pgt.c"

Shouldn't this just be a normal built .o file that is linked together
in the Makefile, specifically tracking CONFIG_RANDOMIZE_BASE as aslr.o
already is?

-Kees

> +
>  #define I8254_PORT_CONTROL     0x43
>  #define I8254_PORT_COUNTER0    0x40
>  #define I8254_CMD_READBACK     0xC0
> @@ -160,6 +167,7 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size,
>         unsafe = (unsigned long)input + input_size;
>         mem_avoid[0].start = unsafe;
>         mem_avoid[0].size = unsafe_len;
> +       fill_pagetable(output, init_size);
>
>         /* Avoid initrd. */
>         initrd_start  = (u64)real_mode->ext_ramdisk_image << 32;
> @@ -168,6 +176,7 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size,
>         initrd_size |= real_mode->hdr.ramdisk_size;
>         mem_avoid[1].start = initrd_start;
>         mem_avoid[1].size = initrd_size;
> +       /* don't need to set mapping for initrd */
>
>         /* Avoid kernel command line. */
>         cmd_line  = (u64)real_mode->ext_cmd_line_ptr << 32;
> @@ -178,10 +187,19 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size,
>                 ;
>         mem_avoid[2].start = cmd_line;
>         mem_avoid[2].size = cmd_line_size;
> +       fill_pagetable(cmd_line, cmd_line_size);
>
>         /* Avoid params */
>         mem_avoid[3].start = (unsigned long)real_mode;
>         mem_avoid[3].size = sizeof(*real_mode);
> +       fill_pagetable((unsigned long)real_mode, sizeof(*real_mode));
> +
> +       /* don't need to set mapping for setup_data */
> +
> +#ifdef CONFIG_X86_VERBOSE_BOOTUP
> +       /* for video ram */
> +       fill_pagetable(0, PMD_SIZE);
> +#endif
>  }
>
>  /* Does this memory vector overlap a known avoided area? */
> @@ -362,6 +380,9 @@ unsigned char *choose_kernel_location(struct boot_params *params,
>                 goto out;
>
>         choice = random;
> +
> +       fill_pagetable(choice, init_size);
> +       switch_pagetable();
>  out:
>         return (unsigned char *)choice;
>  }
> diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
> index 69015b5..1b6e34a 100644
> --- a/arch/x86/boot/compressed/head_64.S
> +++ b/arch/x86/boot/compressed/head_64.S
> @@ -125,7 +125,7 @@ ENTRY(startup_32)
>         /* Initialize Page tables to 0 */
>         leal    pgtable(%ebx), %edi
>         xorl    %eax, %eax
> -       movl    $((4096*6)/4), %ecx
> +       movl    $(BOOT_INIT_PGT_SIZE/4), %ecx
>         rep     stosl
>
>         /* Build Level 4 */
> @@ -477,4 +477,4 @@ boot_stack_end:
>         .section ".pgtable","a",@nobits
>         .balign 4096
>  pgtable:
> -       .fill 6*4096, 1, 0
> +       .fill BOOT_PGT_SIZE, 1, 0
> diff --git a/arch/x86/boot/compressed/misc_pgt.c b/arch/x86/boot/compressed/misc_pgt.c
> new file mode 100644
> index 0000000..b55982c
> --- /dev/null
> +++ b/arch/x86/boot/compressed/misc_pgt.c
> @@ -0,0 +1,98 @@
> +
> +#ifdef CONFIG_X86_64
> +#include <asm/init.h>
> +#include <asm/pgtable.h>
> +
> +#include "../../mm/ident_map.c"
> +
> +struct alloc_pgt_data {
> +       unsigned char *pgt_buf;
> +       unsigned long pgt_buf_size;
> +       unsigned long pgt_buf_offset;
> +};
> +
> +static void *alloc_pgt_page(void *context)
> +{
> +       struct alloc_pgt_data *d = (struct alloc_pgt_data *)context;
> +       unsigned char *p = (unsigned char *)d->pgt_buf;
> +
> +       if (d->pgt_buf_offset >= d->pgt_buf_size) {
> +               debug_putstr("out of pgt_buf in misc.c\n");
> +               return NULL;
> +       }
> +
> +       p += d->pgt_buf_offset;
> +       d->pgt_buf_offset += PAGE_SIZE;
> +
> +       return p;
> +}
> +
> +/*
> + * Use a normal definition of memset() from string.c. There are already
> + * included header files which expect a definition of memset() and by
> + * the time we define memset macro, it is too late.
> + */
> +#undef memset
> +#define memzero(s, n)   memset((s), 0, (n))
> +
> +unsigned long __force_order;
> +static struct alloc_pgt_data pgt_data;
> +static struct x86_mapping_info mapping_info;
> +static pgd_t *level4p;
> +
> +extern unsigned char _pgtable[];
> +static void fill_pagetable(unsigned long start, unsigned long size)
> +{
> +       unsigned long end = start + size;
> +
> +       if (!level4p) {
> +               pgt_data.pgt_buf_offset = 0;
> +               mapping_info.alloc_pgt_page = alloc_pgt_page;
> +               mapping_info.context = &pgt_data;
> +               mapping_info.pmd_flag = __PAGE_KERNEL_LARGE_EXEC;
> +
> +               /*
> +                * come from startup_32 ?
> +                * then cr3 is _pgtable, we can reuse it.
> +                */
> +               level4p = (pgd_t *)read_cr3();
> +               if ((unsigned long)level4p == (unsigned long)_pgtable) {
> +                       pgt_data.pgt_buf = (unsigned char *)_pgtable +
> +                                                BOOT_INIT_PGT_SIZE;
> +                       pgt_data.pgt_buf_size = BOOT_PGT_SIZE -
> +                                                BOOT_INIT_PGT_SIZE;
> +
> +                       debug_putstr("boot via startup_32\n");
> +               } else {
> +                       pgt_data.pgt_buf = (unsigned char *)_pgtable;
> +                       pgt_data.pgt_buf_size = BOOT_PGT_SIZE;
> +
> +                       debug_putstr("boot via startup_64\n");
> +                       level4p = (pgd_t *)alloc_pgt_page(&pgt_data);
> +               }
> +               memset((unsigned char *)pgt_data.pgt_buf, 0,
> +                        pgt_data.pgt_buf_size);
> +       }
> +
> +       /* align boundary to 2M */
> +       start = round_down(start, PMD_SIZE);
> +       end = round_up(end, PMD_SIZE);
> +       if (start >= end)
> +               return;
> +
> +       kernel_ident_mapping_init(&mapping_info, level4p, start, end);
> +}
> +
> +static void switch_pagetable(void)
> +{
> +       write_cr3((unsigned long)level4p);
> +}
> +
> +#else
> +static void fill_pagetable(unsigned long start, unsigned long size)
> +{
> +}
> +static void switch_pagetable(void)
> +{
> +}
> +#endif
> diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h
> index 4fa687a..7b23908 100644
> --- a/arch/x86/include/asm/boot.h
> +++ b/arch/x86/include/asm/boot.h
> @@ -32,7 +32,26 @@
>  #endif /* !CONFIG_KERNEL_BZIP2 */
>
>  #ifdef CONFIG_X86_64
> +
>  #define BOOT_STACK_SIZE        0x4000
> +
> +#define BOOT_INIT_PGT_SIZE (6*4096)
> +#ifdef CONFIG_RANDOMIZE_BASE
> +/*
> + * 1 page for level4, 2 pages for first 2M.
> + * (2+2)*4 pages for kernel, param, cmd_line, random kernel
> + * if all cross 512G boundary.
> + * So total will be 19 pages.
> + */
> +#ifdef CONFIG_X86_VERBOSE_BOOTUP
> +#define BOOT_PGT_SIZE (19*4096)
> +#else
> +#define BOOT_PGT_SIZE (17*4096)
> +#endif
> +#else
> +#define BOOT_PGT_SIZE BOOT_INIT_PGT_SIZE
> +#endif
> +
>  #else
>  #define BOOT_STACK_SIZE        0x1000
>  #endif
> --
> 1.8.4.5
>



-- 
Kees Cook
Chrome OS Security
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/