Re: [RFC 22/22] x86/kaslr: Add option to extend KASLR range from 1GB to 3GB

[Baoquan He <bhe@redhat.com>]

On 07/19/17 at 08:10pm, Baoquan He wrote:
> On 07/18/17 at 03:33pm, Thomas Garnier wrote:
> 
> >  quiet_cmd_relocs = RELOCS  $@
> >        cmd_relocs = $(CMD_RELOCS) $< > $@;$(CMD_RELOCS) --abs-relocs $<
> >  $(obj)/vmlinux.relocs: vmlinux FORCE
> > diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
> > index a0838ab929f2..0a0c80ab1842 100644
> > --- a/arch/x86/boot/compressed/misc.c
> > +++ b/arch/x86/boot/compressed/misc.c
> > @@ -170,10 +170,18 @@ void __puthex(unsigned long value)
> >  }
> >  
> >  #if CONFIG_X86_NEED_RELOCS
> > +
> > +/* Large randomization go lower than -2G and use large relocation table */
> > +#ifdef CONFIG_RANDOMIZE_BASE_LARGE
> > +typedef long rel_t;
> > +#else
> > +typedef int rel_t;
> > +#endif
> > +
> >  static void handle_relocations(void *output, unsigned long output_len,
> >  			       unsigned long virt_addr)
> >  {
> > -	int *reloc;
> > +	rel_t *reloc;
> >  	unsigned long delta, map, ptr;
> >  	unsigned long min_addr = (unsigned long)output;
> >  	unsigned long max_addr = min_addr + (VO___bss_start - VO__text);
> > diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
> > index 3f5f08b010d0..6b65f846dd64 100644
> > --- a/arch/x86/include/asm/page_64_types.h
> > +++ b/arch/x86/include/asm/page_64_types.h
> > @@ -48,7 +48,11 @@
> >  #define __PAGE_OFFSET           __PAGE_OFFSET_BASE
> >  #endif /* CONFIG_RANDOMIZE_MEMORY */
> >  
> > +#ifdef CONFIG_RANDOMIZE_BASE_LARGE
> > +#define __START_KERNEL_map	_AC(0xffffffff00000000, UL)
> > +#else
> >  #define __START_KERNEL_map	_AC(0xffffffff80000000, UL)
> > +#endif /* CONFIG_RANDOMIZE_BASE_LARGE */
> >  
> >  /* See Documentation/x86/x86_64/mm.txt for a description of the memory map. */
> >  #ifdef CONFIG_X86_5LEVEL
> > @@ -65,9 +69,14 @@
> >   * 512MiB by default, leaving 1.5GiB for modules once the page tables
> >   * are fully set up. If kernel ASLR is configured, it can extend the
> >   * kernel page table mapping, reducing the size of the modules area.
> > + * On PIE, we relocate the binary 2G lower so add this extra space.
> >   */
> >  #if defined(CONFIG_RANDOMIZE_BASE)
> > +#ifdef CONFIG_RANDOMIZE_BASE_LARGE
> > +#define KERNEL_IMAGE_SIZE	(_AC(3, UL) * 1024 * 1024 * 1024)
> > +#else
> >  #define KERNEL_IMAGE_SIZE	(1024 * 1024 * 1024)
> > +#endif
> >  #else
> >  #define KERNEL_IMAGE_SIZE	(512 * 1024 * 1024)
> >  #endif
> > diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
> > index 4103e90ff128..235c3f7b46c7 100644
> > --- a/arch/x86/kernel/head64.c
> > +++ b/arch/x86/kernel/head64.c
> > @@ -39,6 +39,7 @@ static unsigned int __initdata next_early_pgt;
> >  pmdval_t early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX);
> >  
> >  #define __head	__section(.head.text)
> > +#define pud_count(x)   (((x + (PUD_SIZE - 1)) & ~(PUD_SIZE - 1)) >> PUD_SHIFT)
> >  
> >  static void __head *fixup_pointer(void *ptr, unsigned long physaddr)
> >  {
> > @@ -54,6 +55,8 @@ unsigned long _text_offset = (unsigned long)(_text - __START_KERNEL_map);
> >  void __head notrace __startup_64(unsigned long physaddr)
> >  {
> >  	unsigned long load_delta, *p;
> > +	unsigned long level3_kernel_start, level3_kernel_count;
> > +	unsigned long level3_fixmap_start;
> >  	pgdval_t *pgd;
> >  	p4dval_t *p4d;
> >  	pudval_t *pud;
> > @@ -74,6 +77,11 @@ void __head notrace __startup_64(unsigned long physaddr)
> >  	if (load_delta & ~PMD_PAGE_MASK)
> >  		for (;;);
> >  
> > +	/* Look at the randomization spread to adapt page table used */
> > +	level3_kernel_start = pud_index(__START_KERNEL_map);
> > +	level3_kernel_count = pud_count(KERNEL_IMAGE_SIZE);
> > +	level3_fixmap_start = level3_kernel_start + level3_kernel_count;
> > +
> >  	/* Fixup the physical addresses in the page table */
> >  
> >  	pgd = fixup_pointer(&early_top_pgt, physaddr);
> > @@ -85,8 +93,9 @@ void __head notrace __startup_64(unsigned long physaddr)
> >  	}
> >  
> >  	pud = fixup_pointer(&level3_kernel_pgt, physaddr);
> > -	pud[510] += load_delta;
> > -	pud[511] += load_delta;
> > +	for (i = 0; i < level3_kernel_count; i++)
> > +		pud[level3_kernel_start + i] += load_delta;
> > +	pud[level3_fixmap_start] += load_delta;
> >  
> >  	pmd = fixup_pointer(level2_fixmap_pgt, physaddr);
> >  	pmd[506] += load_delta;
> > @@ -137,7 +146,7 @@ void __head notrace __startup_64(unsigned long physaddr)
> >  	 */
> >  
> >  	pmd = fixup_pointer(level2_kernel_pgt, physaddr);
> > -	for (i = 0; i < PTRS_PER_PMD; i++) {
> > +	for (i = 0; i < PTRS_PER_PMD * level3_kernel_count; i++) {
> >  		if (pmd[i] & _PAGE_PRESENT)
> >  			pmd[i] += load_delta;
> 
> Wow, this is dangerous. Three pud entries of level3_kernel_pgt all point
> to level2_kernel_pgt, it's out of bound of level2_kernel_pgt and
> overwrite the next data.
> 
> And if only use one page for level2_kernel_pgt, and kernel is randomized
> to cross the pud entry of -4G to -1G, it won't work well.

Sorry, I was wrong, the size of level2_kernel_pgt is decided by
KERNEL_IMAGE_SIZE. So it's not a problem, please ignore this comment.

> 
> >  	}
> > @@ -268,7 +277,8 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data)
> >  	 */
> >  	BUILD_BUG_ON(MODULES_VADDR < __START_KERNEL_map);
> >  	BUILD_BUG_ON(MODULES_VADDR - __START_KERNEL_map < KERNEL_IMAGE_SIZE);
> > -	BUILD_BUG_ON(MODULES_LEN + KERNEL_IMAGE_SIZE > 2*PUD_SIZE);
> > +	BUILD_BUG_ON(!IS_ENABLED(CONFIG_RANDOMIZE_BASE_LARGE) &&
> > +		     MODULES_LEN + KERNEL_IMAGE_SIZE > 2*PUD_SIZE);
> >  	BUILD_BUG_ON((__START_KERNEL_map & ~PMD_MASK) != 0);
> >  	BUILD_BUG_ON((MODULES_VADDR & ~PMD_MASK) != 0);
> >  	BUILD_BUG_ON(!(MODULES_VADDR > __START_KERNEL));
> > diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
> > index 4d0a7e68bfe8..e8b2d6706eca 100644
> > --- a/arch/x86/kernel/head_64.S
> > +++ b/arch/x86/kernel/head_64.S
> > @@ -39,11 +39,15 @@
> >  
> >  #define p4d_index(x)	(((x) >> P4D_SHIFT) & (PTRS_PER_P4D-1))
> >  #define pud_index(x)	(((x) >> PUD_SHIFT) & (PTRS_PER_PUD-1))
> > +#define pud_count(x)   (((x + (PUD_SIZE - 1)) & ~(PUD_SIZE - 1)) >> PUD_SHIFT)
> >  
> >  PGD_PAGE_OFFSET = pgd_index(__PAGE_OFFSET_BASE)
> >  PGD_START_KERNEL = pgd_index(__START_KERNEL_map)
> >  L3_START_KERNEL = pud_index(__START_KERNEL_map)
> >  
> > +/* Adapt page table L3 space based on range of randomization */
> > +L3_KERNEL_ENTRY_COUNT = pud_count(KERNEL_IMAGE_SIZE)
> > +
> >  	.text
> >  	__HEAD
> >  	.code64
> > @@ -396,7 +400,12 @@ NEXT_PAGE(level4_kernel_pgt)
> >  NEXT_PAGE(level3_kernel_pgt)
> >  	.fill	L3_START_KERNEL,8,0
> >  	/* (2^48-(2*1024*1024*1024)-((2^39)*511))/(2^30) = 510 */
> > -	.quad	level2_kernel_pgt - __START_KERNEL_map + _KERNPG_TABLE
> > +	i = 0
> > +	.rept	L3_KERNEL_ENTRY_COUNT
> > +	.quad	level2_kernel_pgt - __START_KERNEL_map + _KERNPG_TABLE \
> > +		+ PAGE_SIZE*i
> > +	i = i + 1
> > +	.endr
> >  	.quad	level2_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE
> >  
> >  NEXT_PAGE(level2_kernel_pgt)
> > -- 
> > 2.13.2.932.g7449e964c-goog
> >