From 021182e52fe01c1f7b126f97fd6ba048dc4234fd Mon Sep 17 00:00:00 2001 From: Thomas Garnier Date: Tue, 21 Jun 2016 17:47:03 -0700 Subject: [PATCH] x86/mm: Enable KASLR for physical mapping memory regions Add the physical mapping in the list of randomized memory regions. The physical memory mapping holds most allocations from boot and heap allocators. Knowing the base address and physical memory size, an attacker can deduce the PDE virtual address for the vDSO memory page. This attack was demonstrated at CanSecWest 2016, in the following presentation: "Getting Physical: Extreme Abuse of Intel Based Paged Systems": https://github.com/n3k/CansecWest2016_Getting_Physical_Extreme_Abuse_of_Intel_Based_Paging_Systems/blob/master/Presentation/CanSec2016_Presentation.pdf (See second part of the presentation). The exploits used against Linux worked successfully against 4.6+ but fail with KASLR memory enabled: https://github.com/n3k/CansecWest2016_Getting_Physical_Extreme_Abuse_of_Intel_Based_Paging_Systems/tree/master/Demos/Linux/exploits Similar research was done at Google leading to this patch proposal. Variants exists to overwrite /proc or /sys objects ACLs leading to elevation of privileges. These variants were tested against 4.6+. The page offset used by the compressed kernel retains the static value since it is not yet randomized during this boot stage. Signed-off-by: Thomas Garnier Signed-off-by: Kees Cook Cc: Alexander Kuleshov Cc: Alexander Popov Cc: Andrew Morton Cc: Andy Lutomirski Cc: Aneesh Kumar K.V Cc: Baoquan He Cc: Boris Ostrovsky Cc: Borislav Petkov Cc: Borislav Petkov Cc: Brian Gerst Cc: Christian Borntraeger Cc: Dan Williams Cc: Dave Hansen Cc: Dave Young Cc: Denys Vlasenko Cc: Dmitry Vyukov Cc: H. Peter Anvin Cc: Jan Beulich Cc: Joerg Roedel Cc: Jonathan Corbet Cc: Josh Poimboeuf Cc: Juergen Gross Cc: Kirill A. Shutemov Cc: Linus Torvalds Cc: Lv Zheng Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Fleming Cc: Peter Zijlstra Cc: Stephen Smalley Cc: Thomas Gleixner Cc: Toshi Kani Cc: Xiao Guangrong Cc: Yinghai Lu Cc: kernel-hardening@lists.openwall.com Cc: linux-doc@vger.kernel.org Link: http://lkml.kernel.org/r/1466556426-32664-7-git-send-email-keescook@chromium.org Signed-off-by: Ingo Molnar --- arch/x86/boot/compressed/pagetable.c | 3 +++ arch/x86/include/asm/kaslr.h | 2 ++ arch/x86/include/asm/page_64_types.h | 11 ++++++++++- arch/x86/kernel/head_64.S | 2 +- arch/x86/mm/kaslr.c | 18 +++++++++++++++--- 5 files changed, 31 insertions(+), 5 deletions(-) diff --git a/arch/x86/boot/compressed/pagetable.c b/arch/x86/boot/compressed/pagetable.c index 6e31a6aac4d3..56589d0a804b 100644 --- a/arch/x86/boot/compressed/pagetable.c +++ b/arch/x86/boot/compressed/pagetable.c @@ -20,6 +20,9 @@ /* These actually do the work of building the kernel identity maps. */ #include #include +/* Use the static base for this part of the boot process */ +#undef __PAGE_OFFSET +#define __PAGE_OFFSET __PAGE_OFFSET_BASE #include "../../mm/ident_map.c" /* Used by pgtable.h asm code to force instruction serialization. */ diff --git a/arch/x86/include/asm/kaslr.h b/arch/x86/include/asm/kaslr.h index 683c9d736314..62b1b815a83a 100644 --- a/arch/x86/include/asm/kaslr.h +++ b/arch/x86/include/asm/kaslr.h @@ -4,6 +4,8 @@ unsigned long kaslr_get_random_long(const char *purpose); #ifdef CONFIG_RANDOMIZE_MEMORY +extern unsigned long page_offset_base; + void kernel_randomize_memory(void); #else static inline void kernel_randomize_memory(void) { } diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h index d5c2f8b40faa..9215e0527647 100644 --- a/arch/x86/include/asm/page_64_types.h +++ b/arch/x86/include/asm/page_64_types.h @@ -1,6 +1,10 @@ #ifndef _ASM_X86_PAGE_64_DEFS_H #define _ASM_X86_PAGE_64_DEFS_H +#ifndef __ASSEMBLY__ +#include +#endif + #ifdef CONFIG_KASAN #define KASAN_STACK_ORDER 1 #else @@ -32,7 +36,12 @@ * hypervisor to fit. Choosing 16 slots here is arbitrary, but it's * what Xen requires. */ -#define __PAGE_OFFSET _AC(0xffff880000000000, UL) +#define __PAGE_OFFSET_BASE _AC(0xffff880000000000, UL) +#ifdef CONFIG_RANDOMIZE_MEMORY +#define __PAGE_OFFSET page_offset_base +#else +#define __PAGE_OFFSET __PAGE_OFFSET_BASE +#endif /* CONFIG_RANDOMIZE_MEMORY */ #define __START_KERNEL_map _AC(0xffffffff80000000, UL) diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index c7920ba69563..9f8efc9f0075 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -38,7 +38,7 @@ #define pud_index(x) (((x) >> PUD_SHIFT) & (PTRS_PER_PUD-1)) -L4_PAGE_OFFSET = pgd_index(__PAGE_OFFSET) +L4_PAGE_OFFSET = pgd_index(__PAGE_OFFSET_BASE) L4_START_KERNEL = pgd_index(__START_KERNEL_map) L3_START_KERNEL = pud_index(__START_KERNEL_map) diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index d5380a48e8fb..609ecf2b37ed 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -43,8 +43,12 @@ * before. You also need to add a BUILD_BUG_ON in kernel_randomize_memory to * ensure that this order is correct and won't be changed. */ -static const unsigned long vaddr_start; -static const unsigned long vaddr_end; +static const unsigned long vaddr_start = __PAGE_OFFSET_BASE; +static const unsigned long vaddr_end = VMALLOC_START; + +/* Default values */ +unsigned long page_offset_base = __PAGE_OFFSET_BASE; +EXPORT_SYMBOL(page_offset_base); /* * Memory regions randomized by KASLR (except modules that use a separate logic @@ -55,6 +59,7 @@ static __initdata struct kaslr_memory_region { unsigned long *base; unsigned long size_tb; } kaslr_regions[] = { + { &page_offset_base, 64/* Maximum */ }, }; /* Get size in bytes used by the memory region */ @@ -77,13 +82,20 @@ void __init kernel_randomize_memory(void) { size_t i; unsigned long vaddr = vaddr_start; - unsigned long rand; + unsigned long rand, memory_tb; struct rnd_state rand_state; unsigned long remain_entropy; if (!kaslr_memory_enabled()) return; + BUG_ON(kaslr_regions[0].base != &page_offset_base); + memory_tb = ((max_pfn << PAGE_SHIFT) >> TB_SHIFT); + + /* Adapt phyiscal memory region size based on available memory */ + if (memory_tb < kaslr_regions[0].size_tb) + kaslr_regions[0].size_tb = memory_tb; + /* Calculate entropy available between regions */ remain_entropy = vaddr_end - vaddr_start; for (i = 0; i < ARRAY_SIZE(kaslr_regions); i++) -- 2.11.0