From da141706aea52c1a9fbd28cb8d289b78819f5436 Mon Sep 17 00:00:00 2001 From: Laura Abbott Date: Wed, 21 Jan 2015 17:36:06 -0800 Subject: [PATCH] arm64: add better page protections to arm64 Add page protections for arm64 similar to those in arm. This is for security reasons to prevent certain classes of exploits. The current method: - Map all memory as either RWX or RW. We round to the nearest section to avoid creating page tables before everything is mapped - Once everything is mapped, if either end of the RWX section should not be X, we split the PMD and remap as necessary - When initmem is to be freed, we change the permissions back to RW (using stop machine if necessary to flush the TLB) - If CONFIG_DEBUG_RODATA is set, the read only sections are set read only. Acked-by: Ard Biesheuvel Tested-by: Kees Cook Tested-by: Ard Biesheuvel Signed-off-by: Laura Abbott Signed-off-by: Catalin Marinas --- arch/arm64/Kconfig.debug | 23 +++ arch/arm64/include/asm/cacheflush.h | 5 + arch/arm64/kernel/vmlinux.lds.S | 17 ++- arch/arm64/mm/init.c | 1 + arch/arm64/mm/mm.h | 2 + arch/arm64/mm/mmu.c | 211 ++++++++++++++++++++++++---- 6 files changed, 233 insertions(+), 26 deletions(-) diff --git a/arch/arm64/Kconfig.debug b/arch/arm64/Kconfig.debug index 5fdd6dce8061..4a8741073c90 100644 --- a/arch/arm64/Kconfig.debug +++ b/arch/arm64/Kconfig.debug @@ -66,4 +66,27 @@ config DEBUG_SET_MODULE_RONX against certain classes of kernel exploits. If in doubt, say "N". +config DEBUG_RODATA + bool "Make kernel text and rodata read-only" + help + If this is set, kernel text and rodata will be made read-only. This + is to help catch accidental or malicious attempts to change the + kernel's executable code. Additionally splits rodata from kernel + text so it can be made explicitly non-executable. + + If in doubt, say Y + +config DEBUG_ALIGN_RODATA + depends on DEBUG_RODATA && !ARM64_64K_PAGES + bool "Align linker sections up to SECTION_SIZE" + help + If this option is enabled, sections that may potentially be marked as + read only or non-executable will be aligned up to the section size of + the kernel. This prevents sections from being split into pages and + avoids a potential TLB penalty. The downside is an increase in + alignment and potentially wasted space. Turn on this option if + performance is more important than memory pressure. + + If in doubt, say N + endmenu diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h index 7ae31a2cc6c0..67d309cc3b6b 100644 --- a/arch/arm64/include/asm/cacheflush.h +++ b/arch/arm64/include/asm/cacheflush.h @@ -152,4 +152,9 @@ int set_memory_ro(unsigned long addr, int numpages); int set_memory_rw(unsigned long addr, int numpages); int set_memory_x(unsigned long addr, int numpages); int set_memory_nx(unsigned long addr, int numpages); + +#ifdef CONFIG_DEBUG_RODATA +void mark_rodata_ro(void); +#endif + #endif diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index 9965ec87cbec..5d9d2dca530d 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -8,6 +8,7 @@ #include #include #include +#include #include "image.h" @@ -49,6 +50,14 @@ PECOFF_FILE_ALIGNMENT = 0x200; #define PECOFF_EDATA_PADDING #endif +#ifdef CONFIG_DEBUG_ALIGN_RODATA +#define ALIGN_DEBUG_RO . = ALIGN(1< #include #include +#include #include #include @@ -59,21 +60,43 @@ EXPORT_SYMBOL(phys_mem_access_prot); static void __init *early_alloc(unsigned long sz) { void *ptr = __va(memblock_alloc(sz, sz)); + BUG_ON(!ptr); memset(ptr, 0, sz); return ptr; } -static void __init alloc_init_pte(pmd_t *pmd, unsigned long addr, +/* + * remap a PMD into pages + */ +static void split_pmd(pmd_t *pmd, pte_t *pte) +{ + unsigned long pfn = pmd_pfn(*pmd); + int i = 0; + + do { + /* + * Need to have the least restrictive permissions available + * permissions will be fixed up later + */ + set_pte(pte, pfn_pte(pfn, PAGE_KERNEL_EXEC)); + pfn++; + } while (pte++, i++, i < PTRS_PER_PTE); +} + +static void alloc_init_pte(pmd_t *pmd, unsigned long addr, unsigned long end, unsigned long pfn, - pgprot_t prot) + pgprot_t prot, + void *(*alloc)(unsigned long size)) { pte_t *pte; - if (pmd_none(*pmd)) { - pte = early_alloc(PTRS_PER_PTE * sizeof(pte_t)); + if (pmd_none(*pmd) || pmd_bad(*pmd)) { + pte = alloc(PTRS_PER_PTE * sizeof(pte_t)); + if (pmd_sect(*pmd)) + split_pmd(pmd, pte); __pmd_populate(pmd, __pa(pte), PMD_TYPE_TABLE); + flush_tlb_all(); } - BUG_ON(pmd_bad(*pmd)); pte = pte_offset_kernel(pmd, addr); do { @@ -82,9 +105,22 @@ static void __init alloc_init_pte(pmd_t *pmd, unsigned long addr, } while (pte++, addr += PAGE_SIZE, addr != end); } -static void __init alloc_init_pmd(struct mm_struct *mm, pud_t *pud, +void split_pud(pud_t *old_pud, pmd_t *pmd) +{ + unsigned long addr = pud_pfn(*old_pud) << PAGE_SHIFT; + pgprot_t prot = __pgprot(pud_val(*old_pud) ^ addr); + int i = 0; + + do { + set_pmd(pmd, __pmd(addr | prot)); + addr += PMD_SIZE; + } while (pmd++, i++, i < PTRS_PER_PMD); +} + +static void alloc_init_pmd(struct mm_struct *mm, pud_t *pud, unsigned long addr, unsigned long end, - phys_addr_t phys, pgprot_t prot) + phys_addr_t phys, pgprot_t prot, + void *(*alloc)(unsigned long size)) { pmd_t *pmd; unsigned long next; @@ -93,8 +129,16 @@ static void __init alloc_init_pmd(struct mm_struct *mm, pud_t *pud, * Check for initial section mappings in the pgd/pud and remove them. */ if (pud_none(*pud) || pud_bad(*pud)) { - pmd = early_alloc(PTRS_PER_PMD * sizeof(pmd_t)); + pmd = alloc(PTRS_PER_PMD * sizeof(pmd_t)); + if (pud_sect(*pud)) { + /* + * need to have the 1G of mappings continue to be + * present + */ + split_pud(pud, pmd); + } pud_populate(mm, pud, pmd); + flush_tlb_all(); } pmd = pmd_offset(pud, addr); @@ -113,21 +157,34 @@ static void __init alloc_init_pmd(struct mm_struct *mm, pud_t *pud, flush_tlb_all(); } else { alloc_init_pte(pmd, addr, next, __phys_to_pfn(phys), - prot); + prot, alloc); } phys += next - addr; } while (pmd++, addr = next, addr != end); } -static void __init alloc_init_pud(struct mm_struct *mm, pgd_t *pgd, +static inline bool use_1G_block(unsigned long addr, unsigned long next, + unsigned long phys) +{ + if (PAGE_SHIFT != 12) + return false; + + if (((addr | next | phys) & ~PUD_MASK) != 0) + return false; + + return true; +} + +static void alloc_init_pud(struct mm_struct *mm, pgd_t *pgd, unsigned long addr, unsigned long end, - phys_addr_t phys, pgprot_t prot) + phys_addr_t phys, pgprot_t prot, + void *(*alloc)(unsigned long size)) { pud_t *pud; unsigned long next; if (pgd_none(*pgd)) { - pud = early_alloc(PTRS_PER_PUD * sizeof(pud_t)); + pud = alloc(PTRS_PER_PUD * sizeof(pud_t)); pgd_populate(mm, pgd, pud); } BUG_ON(pgd_bad(*pgd)); @@ -139,8 +196,7 @@ static void __init alloc_init_pud(struct mm_struct *mm, pgd_t *pgd, /* * For 4K granule only, attempt to put down a 1GB block */ - if ((PAGE_SHIFT == 12) && - ((addr | next | phys) & ~PUD_MASK) == 0) { + if (use_1G_block(addr, next, phys)) { pud_t old_pud = *pud; set_pud(pud, __pud(phys | pgprot_val(mk_sect_prot(prot)))); @@ -158,7 +214,7 @@ static void __init alloc_init_pud(struct mm_struct *mm, pgd_t *pgd, flush_tlb_all(); } } else { - alloc_init_pmd(mm, pud, addr, next, phys, prot); + alloc_init_pmd(mm, pud, addr, next, phys, prot, alloc); } phys += next - addr; } while (pud++, addr = next, addr != end); @@ -168,9 +224,10 @@ static void __init alloc_init_pud(struct mm_struct *mm, pgd_t *pgd, * Create the page directory entries and any necessary page tables for the * mapping specified by 'md'. */ -static void __init __create_mapping(struct mm_struct *mm, pgd_t *pgd, +static void __create_mapping(struct mm_struct *mm, pgd_t *pgd, phys_addr_t phys, unsigned long virt, - phys_addr_t size, pgprot_t prot) + phys_addr_t size, pgprot_t prot, + void *(*alloc)(unsigned long size)) { unsigned long addr, length, end, next; @@ -180,13 +237,23 @@ static void __init __create_mapping(struct mm_struct *mm, pgd_t *pgd, end = addr + length; do { next = pgd_addr_end(addr, end); - alloc_init_pud(mm, pgd, addr, next, phys, prot); + alloc_init_pud(mm, pgd, addr, next, phys, prot, alloc); phys += next - addr; } while (pgd++, addr = next, addr != end); } -static void __init create_mapping(phys_addr_t phys, unsigned long virt, - phys_addr_t size) +static void *late_alloc(unsigned long size) +{ + void *ptr; + + BUG_ON(size > PAGE_SIZE); + ptr = (void *)__get_free_page(PGALLOC_GFP); + BUG_ON(!ptr); + return ptr; +} + +static void __ref create_mapping(phys_addr_t phys, unsigned long virt, + phys_addr_t size, pgprot_t prot) { if (virt < VMALLOC_START) { pr_warn("BUG: not creating mapping for %pa at 0x%016lx - outside kernel range\n", @@ -194,15 +261,71 @@ static void __init create_mapping(phys_addr_t phys, unsigned long virt, return; } __create_mapping(&init_mm, pgd_offset_k(virt & PAGE_MASK), phys, virt, - size, PAGE_KERNEL_EXEC); + size, prot, early_alloc); } void __init create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot) { - __create_mapping(mm, pgd_offset(mm, virt), phys, virt, size, prot); + __create_mapping(mm, pgd_offset(mm, virt), phys, virt, size, prot, + early_alloc); +} + +static void create_mapping_late(phys_addr_t phys, unsigned long virt, + phys_addr_t size, pgprot_t prot) +{ + if (virt < VMALLOC_START) { + pr_warn("BUG: not creating mapping for %pa at 0x%016lx - outside kernel range\n", + &phys, virt); + return; + } + + return __create_mapping(&init_mm, pgd_offset_k(virt & PAGE_MASK), + phys, virt, size, prot, late_alloc); +} + +#ifdef CONFIG_DEBUG_RODATA +static void __init __map_memblock(phys_addr_t start, phys_addr_t end) +{ + /* + * Set up the executable regions using the existing section mappings + * for now. This will get more fine grained later once all memory + * is mapped + */ + unsigned long kernel_x_start = round_down(__pa(_stext), SECTION_SIZE); + unsigned long kernel_x_end = round_up(__pa(__init_end), SECTION_SIZE); + + if (end < kernel_x_start) { + create_mapping(start, __phys_to_virt(start), + end - start, PAGE_KERNEL); + } else if (start >= kernel_x_end) { + create_mapping(start, __phys_to_virt(start), + end - start, PAGE_KERNEL); + } else { + if (start < kernel_x_start) + create_mapping(start, __phys_to_virt(start), + kernel_x_start - start, + PAGE_KERNEL); + create_mapping(kernel_x_start, + __phys_to_virt(kernel_x_start), + kernel_x_end - kernel_x_start, + PAGE_KERNEL_EXEC); + if (kernel_x_end < end) + create_mapping(kernel_x_end, + __phys_to_virt(kernel_x_end), + end - kernel_x_end, + PAGE_KERNEL); + } + +} +#else +static void __init __map_memblock(phys_addr_t start, phys_addr_t end) +{ + create_mapping(start, __phys_to_virt(start), end - start, + PAGE_KERNEL_EXEC); } +#endif static void __init map_mem(void) { @@ -248,14 +371,53 @@ static void __init map_mem(void) memblock_set_current_limit(limit); } #endif - - create_mapping(start, __phys_to_virt(start), end - start); + __map_memblock(start, end); } /* Limit no longer required. */ memblock_set_current_limit(MEMBLOCK_ALLOC_ANYWHERE); } +void __init fixup_executable(void) +{ +#ifdef CONFIG_DEBUG_RODATA + /* now that we are actually fully mapped, make the start/end more fine grained */ + if (!IS_ALIGNED((unsigned long)_stext, SECTION_SIZE)) { + unsigned long aligned_start = round_down(__pa(_stext), + SECTION_SIZE); + + create_mapping(aligned_start, __phys_to_virt(aligned_start), + __pa(_stext) - aligned_start, + PAGE_KERNEL); + } + + if (!IS_ALIGNED((unsigned long)__init_end, SECTION_SIZE)) { + unsigned long aligned_end = round_up(__pa(__init_end), + SECTION_SIZE); + create_mapping(__pa(__init_end), (unsigned long)__init_end, + aligned_end - __pa(__init_end), + PAGE_KERNEL); + } +#endif +} + +#ifdef CONFIG_DEBUG_RODATA +void mark_rodata_ro(void) +{ + create_mapping_late(__pa(_stext), (unsigned long)_stext, + (unsigned long)_etext - (unsigned long)_stext, + PAGE_KERNEL_EXEC | PTE_RDONLY); + +} +#endif + +void fixup_init(void) +{ + create_mapping_late(__pa(__init_begin), (unsigned long)__init_begin, + (unsigned long)__init_end - (unsigned long)__init_begin, + PAGE_KERNEL); +} + /* * paging_init() sets up the page tables, initialises the zone memory * maps and sets up the zero page. @@ -265,6 +427,7 @@ void __init paging_init(void) void *zero_page; map_mem(); + fixup_executable(); /* * Finally flush the caches and tlb to ensure that we're in a -- 2.20.1