From 65fe935dd2387a4faf15314c73f5e6d31ef0217e Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 13 Jun 2016 15:10:02 -0700 Subject: x86/KASLR, x86/power: Remove x86 hibernation restrictions With the following fix: 70595b479ce1 ("x86/power/64: Fix crash whan the hibernation code passes control to the image kernel") ... there is no longer a problem with hibernation resuming a KASLR-booted kernel image, so remove the restriction. Signed-off-by: Kees Cook Cc: Andy Lutomirski Cc: Baoquan He Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Jonathan Corbet Cc: Len Brown Cc: Linus Torvalds Cc: Linux PM list Cc: Logan Gunthorpe Cc: Pavel Machek Cc: Peter Zijlstra Cc: Stephen Smalley Cc: Thomas Gleixner Cc: Yinghai Lu Cc: linux-doc@vger.kernel.org Link: http://lkml.kernel.org/r/20160613221002.GA29719@www.outflux.net Signed-off-by: Ingo Molnar --- Documentation/kernel-parameters.txt | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'Documentation') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 82b42c958d1c..fa8c6d470ad2 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1803,12 +1803,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted. js= [HW,JOY] Analog joystick See Documentation/input/joystick.txt. - kaslr/nokaslr [X86] - Enable/disable kernel and module base offset ASLR - (Address Space Layout Randomization) if built into - the kernel. When CONFIG_HIBERNATION is selected, - kASLR is disabled by default. When kASLR is enabled, - hibernation will be disabled. + nokaslr [KNL] + When CONFIG_RANDOMIZE_BASE is set, this disables + kernel and module base offset ASLR (Address Space + Layout Randomization). keepinitrd [HW,ARM] -- cgit v1.2.3 From 0483e1fa6e09d4948272680f691dccb1edb9677f Mon Sep 17 00:00:00 2001 From: Thomas Garnier Date: Tue, 21 Jun 2016 17:47:02 -0700 Subject: x86/mm: Implement ASLR for kernel memory regions Randomizes the virtual address space of kernel memory regions for x86_64. This first patch adds the infrastructure and does not randomize any region. The following patches will randomize the physical memory mapping, vmalloc and vmemmap regions. This security feature mitigates exploits relying on predictable kernel addresses. These addresses can be used to disclose the kernel modules base addresses or corrupt specific structures to elevate privileges bypassing the current implementation of KASLR. This feature can be enabled with the CONFIG_RANDOMIZE_MEMORY option. The order of each memory region is not changed. The feature looks at the available space for the regions based on different configuration options and randomizes the base and space between each. The size of the physical memory mapping is the available physical memory. No performance impact was detected while testing the feature. Entropy is generated using the KASLR early boot functions now shared in the lib directory (originally written by Kees Cook). Randomization is done on PGD & PUD page table levels to increase possible addresses. The physical memory mapping code was adapted to support PUD level virtual addresses. This implementation on the best configuration provides 30,000 possible virtual addresses in average for each memory region. An additional low memory page is used to ensure each CPU can start with a PGD aligned virtual address (for realmode). x86/dump_pagetable was updated to correctly display each region. Updated documentation on x86_64 memory layout accordingly. Performance data, after all patches in the series: Kernbench shows almost no difference (-+ less than 1%): Before: Average Optimal load -j 12 Run (std deviation): Elapsed Time 102.63 (1.2695) User Time 1034.89 (1.18115) System Time 87.056 (0.456416) Percent CPU 1092.9 (13.892) Context Switches 199805 (3455.33) Sleeps 97907.8 (900.636) After: Average Optimal load -j 12 Run (std deviation): Elapsed Time 102.489 (1.10636) User Time 1034.86 (1.36053) System Time 87.764 (0.49345) Percent CPU 1095 (12.7715) Context Switches 199036 (4298.1) Sleeps 97681.6 (1031.11) Hackbench shows 0% difference on average (hackbench 90 repeated 10 times): attemp,before,after 1,0.076,0.069 2,0.072,0.069 3,0.066,0.066 4,0.066,0.068 5,0.066,0.067 6,0.066,0.069 7,0.067,0.066 8,0.063,0.067 9,0.067,0.065 10,0.068,0.071 average,0.0677,0.0677 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/1466556426-32664-6-git-send-email-keescook@chromium.org Signed-off-by: Ingo Molnar --- Documentation/x86/x86_64/mm.txt | 4 ++ arch/x86/Kconfig | 17 +++++ arch/x86/include/asm/kaslr.h | 6 ++ arch/x86/include/asm/pgtable.h | 7 +- arch/x86/kernel/setup.c | 3 + arch/x86/mm/Makefile | 1 + arch/x86/mm/dump_pagetables.c | 16 +++-- arch/x86/mm/init.c | 1 + arch/x86/mm/kaslr.c | 152 ++++++++++++++++++++++++++++++++++++++++ 9 files changed, 202 insertions(+), 5 deletions(-) create mode 100644 arch/x86/mm/kaslr.c (limited to 'Documentation') diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt index 5aa738346062..8c7dd5957ae1 100644 --- a/Documentation/x86/x86_64/mm.txt +++ b/Documentation/x86/x86_64/mm.txt @@ -39,4 +39,8 @@ memory window (this size is arbitrary, it can be raised later if needed). The mappings are not part of any other kernel PGD and are only available during EFI runtime calls. +Note that if CONFIG_RANDOMIZE_MEMORY is enabled, the direct mapping of all +physical memory, vmalloc/ioremap space and virtual memory map are randomized. +Their order is preserved but their base will be offset early at boot time. + -Andi Kleen, Jul 2004 diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 930fe88095d3..9719b8eb38d3 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1993,6 +1993,23 @@ config PHYSICAL_ALIGN Don't change this unless you know what you are doing. +config RANDOMIZE_MEMORY + bool "Randomize the kernel memory sections" + depends on X86_64 + depends on RANDOMIZE_BASE + default RANDOMIZE_BASE + ---help--- + Randomizes the base virtual address of kernel memory sections + (physical memory mapping, vmalloc & vmemmap). This security feature + makes exploits relying on predictable memory locations less reliable. + + The order of allocations remains unchanged. Entropy is generated in + the same way as RANDOMIZE_BASE. Current implementation in the optimal + configuration have in average 30,000 different possible virtual + addresses for each memory section. + + If unsure, say N. + config HOTPLUG_CPU bool "Support for hot-pluggable CPUs" depends on SMP diff --git a/arch/x86/include/asm/kaslr.h b/arch/x86/include/asm/kaslr.h index 5547438db5ea..683c9d736314 100644 --- a/arch/x86/include/asm/kaslr.h +++ b/arch/x86/include/asm/kaslr.h @@ -3,4 +3,10 @@ unsigned long kaslr_get_random_long(const char *purpose); +#ifdef CONFIG_RANDOMIZE_MEMORY +void kernel_randomize_memory(void); +#else +static inline void kernel_randomize_memory(void) { } +#endif /* CONFIG_RANDOMIZE_MEMORY */ + #endif diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index d455bef39e9c..5472682a307f 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -732,11 +732,16 @@ void early_alloc_pgt_buf(void); #ifdef CONFIG_X86_64 /* Realmode trampoline initialization. */ extern pgd_t trampoline_pgd_entry; -static inline void __meminit init_trampoline(void) +static inline void __meminit init_trampoline_default(void) { /* Default trampoline pgd value */ trampoline_pgd_entry = init_level4_pgt[pgd_index(__PAGE_OFFSET)]; } +# ifdef CONFIG_RANDOMIZE_MEMORY +void __meminit init_trampoline(void); +# else +# define init_trampoline init_trampoline_default +# endif #else static inline void init_trampoline(void) { } #endif diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index c4e7b3991b60..a2616584b6e9 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -113,6 +113,7 @@ #include #include #include +#include /* * max_low_pfn_mapped: highest direct mapped pfn under 4GB @@ -942,6 +943,8 @@ void __init setup_arch(char **cmdline_p) x86_init.oem.arch_setup(); + kernel_randomize_memory(); + iomem_resource.end = (1ULL << boot_cpu_data.x86_phys_bits) - 1; setup_memory_map(); parse_setup_data(); diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 62c0043a5fd5..96d2b847e09e 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -37,4 +37,5 @@ obj-$(CONFIG_NUMA_EMU) += numa_emulation.o obj-$(CONFIG_X86_INTEL_MPX) += mpx.o obj-$(CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS) += pkeys.o +obj-$(CONFIG_RANDOMIZE_MEMORY) += kaslr.o diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index 99bfb192803f..9a17250bcbe0 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -72,9 +72,9 @@ static struct addr_marker address_markers[] = { { 0, "User Space" }, #ifdef CONFIG_X86_64 { 0x8000000000000000UL, "Kernel Space" }, - { PAGE_OFFSET, "Low Kernel Mapping" }, - { VMALLOC_START, "vmalloc() Area" }, - { VMEMMAP_START, "Vmemmap" }, + { 0/* PAGE_OFFSET */, "Low Kernel Mapping" }, + { 0/* VMALLOC_START */, "vmalloc() Area" }, + { 0/* VMEMMAP_START */, "Vmemmap" }, # ifdef CONFIG_X86_ESPFIX64 { ESPFIX_BASE_ADDR, "ESPfix Area", 16 }, # endif @@ -434,8 +434,16 @@ void ptdump_walk_pgd_level_checkwx(void) static int __init pt_dump_init(void) { + /* + * Various markers are not compile-time constants, so assign them + * here. + */ +#ifdef CONFIG_X86_64 + address_markers[LOW_KERNEL_NR].start_address = PAGE_OFFSET; + address_markers[VMALLOC_START_NR].start_address = VMALLOC_START; + address_markers[VMEMMAP_START_NR].start_address = VMEMMAP_START; +#endif #ifdef CONFIG_X86_32 - /* Not a compile-time constant on x86-32 */ address_markers[VMALLOC_START_NR].start_address = VMALLOC_START; address_markers[VMALLOC_END_NR].start_address = VMALLOC_END; # ifdef CONFIG_HIGHMEM diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 4252acdfcbbd..cc82830bc8c4 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -17,6 +17,7 @@ #include #include /* for MAX_DMA_PFN */ #include +#include /* * We need to define the tracepoints somewhere, and tlb.c diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c new file mode 100644 index 000000000000..d5380a48e8fb --- /dev/null +++ b/arch/x86/mm/kaslr.c @@ -0,0 +1,152 @@ +/* + * This file implements KASLR memory randomization for x86_64. It randomizes + * the virtual address space of kernel memory regions (physical memory + * mapping, vmalloc & vmemmap) for x86_64. This security feature mitigates + * exploits relying on predictable kernel addresses. + * + * Entropy is generated using the KASLR early boot functions now shared in + * the lib directory (originally written by Kees Cook). Randomization is + * done on PGD & PUD page table levels to increase possible addresses. The + * physical memory mapping code was adapted to support PUD level virtual + * addresses. This implementation on the best configuration provides 30,000 + * possible virtual addresses in average for each memory region. An additional + * low memory page is used to ensure each CPU can start with a PGD aligned + * virtual address (for realmode). + * + * The order of each memory region is not changed. The feature looks at + * the available space for the regions based on different configuration + * options and randomizes the base and space between each. The size of the + * physical memory mapping is the available physical memory. + */ + +#include +#include +#include + +#include +#include +#include +#include + +#include "mm_internal.h" + +#define TB_SHIFT 40 + +/* + * Virtual address start and end range for randomization. The end changes base + * on configuration to have the highest amount of space for randomization. + * It increases the possible random position for each randomized region. + * + * You need to add an if/def entry if you introduce a new memory region + * compatible with KASLR. Your entry must be in logical order with memory + * layout. For example, ESPFIX is before EFI because its virtual address is + * 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; + +/* + * Memory regions randomized by KASLR (except modules that use a separate logic + * earlier during boot). The list is ordered based on virtual addresses. This + * order is kept after randomization. + */ +static __initdata struct kaslr_memory_region { + unsigned long *base; + unsigned long size_tb; +} kaslr_regions[] = { +}; + +/* Get size in bytes used by the memory region */ +static inline unsigned long get_padding(struct kaslr_memory_region *region) +{ + return (region->size_tb << TB_SHIFT); +} + +/* + * Apply no randomization if KASLR was disabled at boot or if KASAN + * is enabled. KASAN shadow mappings rely on regions being PGD aligned. + */ +static inline bool kaslr_memory_enabled(void) +{ + return kaslr_enabled() && !config_enabled(CONFIG_KASAN); +} + +/* Initialize base and padding for each memory region randomized with KASLR */ +void __init kernel_randomize_memory(void) +{ + size_t i; + unsigned long vaddr = vaddr_start; + unsigned long rand; + struct rnd_state rand_state; + unsigned long remain_entropy; + + if (!kaslr_memory_enabled()) + return; + + /* Calculate entropy available between regions */ + remain_entropy = vaddr_end - vaddr_start; + for (i = 0; i < ARRAY_SIZE(kaslr_regions); i++) + remain_entropy -= get_padding(&kaslr_regions[i]); + + prandom_seed_state(&rand_state, kaslr_get_random_long("Memory")); + + for (i = 0; i < ARRAY_SIZE(kaslr_regions); i++) { + unsigned long entropy; + + /* + * Select a random virtual address using the extra entropy + * available. + */ + entropy = remain_entropy / (ARRAY_SIZE(kaslr_regions) - i); + prandom_bytes_state(&rand_state, &rand, sizeof(rand)); + entropy = (rand % (entropy + 1)) & PUD_MASK; + vaddr += entropy; + *kaslr_regions[i].base = vaddr; + + /* + * Jump the region and add a minimum padding based on + * randomization alignment. + */ + vaddr += get_padding(&kaslr_regions[i]); + vaddr = round_up(vaddr + 1, PUD_SIZE); + remain_entropy -= entropy; + } +} + +/* + * Create PGD aligned trampoline table to allow real mode initialization + * of additional CPUs. Consume only 1 low memory page. + */ +void __meminit init_trampoline(void) +{ + unsigned long paddr, paddr_next; + pgd_t *pgd; + pud_t *pud_page, *pud_page_tramp; + int i; + + if (!kaslr_memory_enabled()) { + init_trampoline_default(); + return; + } + + pud_page_tramp = alloc_low_page(); + + paddr = 0; + pgd = pgd_offset_k((unsigned long)__va(paddr)); + pud_page = (pud_t *) pgd_page_vaddr(*pgd); + + for (i = pud_index(paddr); i < PTRS_PER_PUD; i++, paddr = paddr_next) { + pud_t *pud, *pud_tramp; + unsigned long vaddr = (unsigned long)__va(paddr); + + pud_tramp = pud_page_tramp + pud_index(paddr); + pud = pud_page + pud_index(vaddr); + paddr_next = (paddr & PUD_MASK) + PUD_SIZE; + + *pud_tramp = *pud; + } + + set_pgd(&trampoline_pgd_entry, + __pgd(_KERNPG_TABLE | __pa(pud_page_tramp))); +} -- cgit v1.2.3