arm64 handles top-down mmap layout in a way that can be easily reused by other architectures, so make it available in mm. This commit also takes the opportunity to: - make use of is_compat_task instead of specific arm64 test test_thread_flag(TIF_32BIT), which allows more genericity and is equivalent. - fix the case where stack randomization should not be taken into account. It then introduces a new define ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT that can be defined by other architectures to benefit from those functions. Suggested-by: Christoph Hellwig <hch@xxxxxxxxxxxxx> Signed-off-by: Alexandre Ghiti <alex@xxxxxxxx> --- arch/arm64/include/asm/processor.h | 2 +- arch/arm64/mm/mmap.c | 72 ---------------------- fs/binfmt_elf.c | 20 ------ include/linux/mm.h | 2 + kernel/sysctl.c | 6 +- mm/util.c | 99 +++++++++++++++++++++++++++++- 6 files changed, 105 insertions(+), 96 deletions(-) diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 5d9ce62bdebd..2358707c31ff 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -274,7 +274,7 @@ static inline void spin_lock_prefetch(const void *ptr) "nop") : : "p" (ptr)); } -#define HAVE_ARCH_PICK_MMAP_LAYOUT +#define ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT #endif diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c index 842c8a5fcd53..c74224421216 100644 --- a/arch/arm64/mm/mmap.c +++ b/arch/arm64/mm/mmap.c @@ -31,78 +31,6 @@ #include <asm/cputype.h> -/* - * Leave enough space between the mmap area and the stack to honour ulimit in - * the face of randomisation. - */ -#define MIN_GAP (SZ_128M) -#define MAX_GAP (STACK_TOP/6*5) - -static int mmap_is_legacy(struct rlimit *rlim_stack) -{ - if (current->personality & ADDR_COMPAT_LAYOUT) - return 1; - - if (rlim_stack->rlim_cur == RLIM_INFINITY) - return 1; - - return sysctl_legacy_va_layout; -} - -unsigned long arch_mmap_rnd(void) -{ - unsigned long rnd; - -#ifdef CONFIG_COMPAT - if (test_thread_flag(TIF_32BIT)) - rnd = get_random_long() & ((1UL << mmap_rnd_compat_bits) - 1); - else -#endif - rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1); - return rnd << PAGE_SHIFT; -} - -static unsigned long mmap_base(unsigned long rnd, struct rlimit *rlim_stack) -{ - unsigned long gap = rlim_stack->rlim_cur; - unsigned long pad = (STACK_RND_MASK << PAGE_SHIFT) + stack_guard_gap; - - /* Values close to RLIM_INFINITY can overflow. */ - if (gap + pad > gap) - gap += pad; - - if (gap < MIN_GAP) - gap = MIN_GAP; - else if (gap > MAX_GAP) - gap = MAX_GAP; - - return PAGE_ALIGN(STACK_TOP - gap - rnd); -} - -/* - * This function, called very early during the creation of a new process VM - * image, sets up which VM layout function to use: - */ -void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) -{ - unsigned long random_factor = 0UL; - - if (current->flags & PF_RANDOMIZE) - random_factor = arch_mmap_rnd(); - - /* - * Fall back to the standard layout if the personality bit is set, or - * if the expected stack growth is unlimited: - */ - if (mmap_is_legacy(rlim_stack)) { - mm->mmap_base = TASK_UNMAPPED_BASE + random_factor; - mm->get_unmapped_area = arch_get_unmapped_area; - } else { - mm->mmap_base = mmap_base(random_factor, rlim_stack); - mm->get_unmapped_area = arch_get_unmapped_area_topdown; - } -} - /* * You really shouldn't be using read() or write() on /dev/mem. This might go * away in the future. diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 7d09d125f148..045f3b29d264 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -662,26 +662,6 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex, * libraries. There is no binary dependent code anywhere else. */ -#ifndef STACK_RND_MASK -#define STACK_RND_MASK (0x7ff >> (PAGE_SHIFT - 12)) /* 8MB of VA */ -#endif - -static unsigned long randomize_stack_top(unsigned long stack_top) -{ - unsigned long random_variable = 0; - - if (current->flags & PF_RANDOMIZE) { - random_variable = get_random_long(); - random_variable &= STACK_RND_MASK; - random_variable <<= PAGE_SHIFT; - } -#ifdef CONFIG_STACK_GROWSUP - return PAGE_ALIGN(stack_top) + random_variable; -#else - return PAGE_ALIGN(stack_top) - random_variable; -#endif -} - static int load_elf_binary(struct linux_binprm *bprm) { struct file *interpreter = NULL; /* to shut gcc up */ diff --git a/include/linux/mm.h b/include/linux/mm.h index 76769749b5a5..087824a5059f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2312,6 +2312,8 @@ extern int install_special_mapping(struct mm_struct *mm, unsigned long addr, unsigned long len, unsigned long flags, struct page **pages); +unsigned long randomize_stack_top(unsigned long stack_top); + extern unsigned long get_unmapped_area(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); extern unsigned long mmap_region(struct file *file, unsigned long addr, diff --git a/kernel/sysctl.c b/kernel/sysctl.c index e5da394d1ca3..ac388f8ccbe4 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -269,7 +269,8 @@ extern struct ctl_table epoll_table[]; extern struct ctl_table firmware_config_table[]; #endif -#ifdef HAVE_ARCH_PICK_MMAP_LAYOUT +#if defined(HAVE_ARCH_PICK_MMAP_LAYOUT) || \ + defined(ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT) int sysctl_legacy_va_layout; #endif @@ -1564,7 +1565,8 @@ static struct ctl_table vm_table[] = { .proc_handler = proc_dointvec, .extra1 = &zero, }, -#ifdef HAVE_ARCH_PICK_MMAP_LAYOUT +#if defined(HAVE_ARCH_PICK_MMAP_LAYOUT) || \ + defined(ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT) { .procname = "legacy_va_layout", .data = &sysctl_legacy_va_layout, diff --git a/mm/util.c b/mm/util.c index d559bde497a9..5a0d4b1e17d9 100644 --- a/mm/util.c +++ b/mm/util.c @@ -14,6 +14,13 @@ #include <linux/hugetlb.h> #include <linux/vmalloc.h> #include <linux/userfaultfd_k.h> +#include <linux/elf.h> +#include <linux/elf-randomize.h> +#include <linux/personality.h> +#include <linux/random.h> +#include <linux/processor.h> +#include <linux/sizes.h> +#include <linux/compat.h> #include <linux/uaccess.h> @@ -291,13 +298,103 @@ int vma_is_stack_for_current(struct vm_area_struct *vma) return (vma->vm_start <= KSTK_ESP(t) && vma->vm_end >= KSTK_ESP(t)); } -#if defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT) +#ifndef STACK_RND_MASK +#define STACK_RND_MASK (0x7ff >> (PAGE_SHIFT - 12)) /* 8MB of VA */ +#endif + +unsigned long randomize_stack_top(unsigned long stack_top) +{ + unsigned long random_variable = 0; + + if (current->flags & PF_RANDOMIZE) { + random_variable = get_random_long(); + random_variable &= STACK_RND_MASK; + random_variable <<= PAGE_SHIFT; + } +#ifdef CONFIG_STACK_GROWSUP + return PAGE_ALIGN(stack_top) + random_variable; +#else + return PAGE_ALIGN(stack_top) - random_variable; +#endif +} + +#ifdef CONFIG_MMU +#ifdef ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT + +#ifdef CONFIG_ARCH_HAS_ELF_RANDOMIZE +unsigned long arch_mmap_rnd(void) +{ + unsigned long rnd; + +#ifdef CONFIG_COMPAT + if (is_compat_task()) + rnd = get_random_long() & ((1UL << mmap_rnd_compat_bits) - 1); + else +#endif + rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1); + + return rnd << PAGE_SHIFT; +} +#endif + +static int mmap_is_legacy(struct rlimit *rlim_stack) +{ + if (current->personality & ADDR_COMPAT_LAYOUT) + return 1; + + if (rlim_stack->rlim_cur == RLIM_INFINITY) + return 1; + + return sysctl_legacy_va_layout; +} + +#define MIN_GAP (SZ_128M) +#define MAX_GAP (STACK_TOP / 6 * 5) + +static unsigned long mmap_base(unsigned long rnd, struct rlimit *rlim_stack) +{ + unsigned long gap = rlim_stack->rlim_cur; + unsigned long pad = stack_guard_gap; + + /* Account for stack randomization if necessary */ + if (current->flags & PF_RANDOMIZE) + pad += (STACK_RND_MASK << PAGE_SHIFT); + + /* Values close to RLIM_INFINITY can overflow. */ + if (gap + pad > gap) + gap += pad; + + if (gap < MIN_GAP) + gap = MIN_GAP; + else if (gap > MAX_GAP) + gap = MAX_GAP; + + return PAGE_ALIGN(STACK_TOP - gap - rnd); +} + +void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) +{ + unsigned long random_factor = 0UL; + + if (current->flags & PF_RANDOMIZE) + random_factor = arch_mmap_rnd(); + + if (mmap_is_legacy(rlim_stack)) { + mm->mmap_base = TASK_UNMAPPED_BASE + random_factor; + mm->get_unmapped_area = arch_get_unmapped_area; + } else { + mm->mmap_base = mmap_base(random_factor, rlim_stack); + mm->get_unmapped_area = arch_get_unmapped_area_topdown; + } +} +#elif !defined(HAVE_ARCH_PICK_MMAP_LAYOUT) void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) { mm->mmap_base = TASK_UNMAPPED_BASE; mm->get_unmapped_area = arch_get_unmapped_area; } #endif +#endif /* CONFIG_MMU */ /* * Like get_user_pages_fast() except its IRQ-safe in that it won't fall -- 2.20.1