From 159eb103ba8c1caf3d54cd3df1fe8fcf3f139afd Mon Sep 17 00:00:00 2001 From: Kees Cook <keescook@chromium.org> Date: Wed, 5 Apr 2017 09:39:08 -0700 Subject: [PATCH] mm: Tighten x86 /dev/mem with zeroing reads Under CONFIG_STRICT_DEVMEM, reading System RAM through /dev/mem is disallowed. However, on x86, the first 1MB was always allowed for BIOS and similar things, regardless of it actually being System RAM. It was possible for heap to end up getting allocated in low 1MB RAM, and then read by things like x86info or dd, which would trip hardened usercopy: usercopy: kernel memory exposure attempt detected from ffff880000090000 (dma-kmalloc-256) (4096 bytes) This changes the x86 exception for the low 1MB by reading back zeros for System RAM areas instead of blindly allowing them. More work is needed to extend this to mmap, but currently mmap doesn't go through usercopy, so hardened usercopy won't Oops the kernel. Change-Id: I27594af6146e7643217e3babcfd088592b7dbd4b Reported-by: Tommi Rantala <tommi.t.rantala@nokia.com> Tested-by: Tommi Rantala <tommi.t.rantala@nokia.com> Signed-off-by: Kees Cook <keescook@chromium.org> --- arch/x86/mm/init.c | 41 ++++++++++++++++------- drivers/char/mem.c | 82 +++++++++++++++++++++++++++++----------------- 2 files changed, 82 insertions(+), 41 deletions(-) diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 4f0cec7e4ffb..713a2e576586 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -305,21 +305,40 @@ unsigned long __init_refok init_memory_mapping(unsigned long start, * devmem_is_allowed() checks to see if /dev/mem access to a certain address * is valid. The argument is a physical page number. * - * - * On x86, access has to be given to the first megabyte of ram because that area - * contains bios code and data regions used by X and dosemu and similar apps. - * Access has to be given to non-kernel-ram areas as well, these contain the PCI - * mmio resources as well as potential bios/acpi data regions. + * On x86, access has to be given to the first megabyte of RAM because that + * area traditionally contains BIOS code and data regions used by X, dosemu, + * and similar apps. Since they map the entire memory range, the whole range + * must be allowed (for mapping), but any areas that would otherwise be + * disallowed are flagged as being "zero filled" instead of rejected. + * Access has to be given to non-kernel-ram areas as well, these contain the + * PCI mmio resources as well as potential bios/acpi data regions. */ int devmem_is_allowed(unsigned long pagenr) { - if (pagenr <= 256) - return 1; - if (iomem_is_exclusive(pagenr << PAGE_SHIFT)) + if (page_is_ram(pagenr)) { + /* + * For disallowed memory regions in the low 1MB range, + * request that the page be shown as all zeros. + */ + if (pagenr < 256) + return 2; + return 0; - if (!page_is_ram(pagenr)) - return 1; - return 0; + } + + /* + * This must follow RAM test, since System RAM is considered a + * restricted resource under CONFIG_STRICT_IOMEM. + */ + if (iomem_is_exclusive(pagenr << PAGE_SHIFT)) { + /* Low 1MB bypasses iomem restrictions. */ + if (pagenr < 256) + return 1; + + return 0; + } + + return 1; } void free_init_pages(char *what, unsigned long begin, unsigned long end) diff --git a/drivers/char/mem.c b/drivers/char/mem.c index 67e19b63199c..3cd71aff7ac0 100644 --- a/drivers/char/mem.c +++ b/drivers/char/mem.c @@ -59,6 +59,10 @@ static inline int valid_mmap_phys_addr_range(unsigned long pfn, size_t size) #if defined(CONFIG_DEVMEM) || defined(CONFIG_DEVKMEM) #ifdef CONFIG_STRICT_DEVMEM +static inline int page_is_allowed(unsigned long pfn) +{ + return devmem_is_allowed(pfn); +} static inline int range_is_allowed(unsigned long pfn, unsigned long size) { u64 from = ((u64)pfn) << PAGE_SHIFT; @@ -78,6 +82,10 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size) return 1; } #else +static inline int page_is_allowed(unsigned long pfn) +{ + return 1; +} static inline int range_is_allowed(unsigned long pfn, unsigned long size) { return 1; @@ -121,23 +129,31 @@ static ssize_t read_mem(struct file *file, char __user *buf, while (count > 0) { unsigned long remaining; + int allowed; sz = size_inside_page(p, count); - if (!range_is_allowed(p >> PAGE_SHIFT, count)) + allowed = page_is_allowed(p >> PAGE_SHIFT); + if (!allowed) return -EPERM; + if (allowed == 2) { + /* Show zeros for restricted memory. */ + remaining = clear_user(buf, sz); + } else { + /* + * On ia64 if a page has been mapped somewhere as + * uncached, then it must also be accessed uncached + * by the kernel or data corruption may occur. + */ + ptr = xlate_dev_mem_ptr(p); + if (!ptr) + return -EFAULT; - /* - * On ia64 if a page has been mapped somewhere as uncached, then - * it must also be accessed uncached by the kernel or data - * corruption may occur. - */ - ptr = xlate_dev_mem_ptr(p); - if (!ptr) - return -EFAULT; + remaining = copy_to_user(buf, ptr, sz); + + unxlate_dev_mem_ptr(p, ptr); + } - remaining = copy_to_user(buf, ptr, sz); - unxlate_dev_mem_ptr(p, ptr); if (remaining) return -EFAULT; @@ -177,30 +193,36 @@ static ssize_t write_mem(struct file *file, const char __user *buf, #endif while (count > 0) { + int allowed; + sz = size_inside_page(p, count); - if (!range_is_allowed(p >> PAGE_SHIFT, sz)) + allowed = page_is_allowed(p >> PAGE_SHIFT); + if (!allowed) return -EPERM; - /* - * On ia64 if a page has been mapped somewhere as uncached, then - * it must also be accessed uncached by the kernel or data - * corruption may occur. - */ - ptr = xlate_dev_mem_ptr(p); - if (!ptr) { - if (written) - break; - return -EFAULT; - } + /* Skip actual writing when a page is marked as restricted. */ + if (allowed == 1) { + /* + * On ia64 if a page has been mapped somewhere as + * uncached, then it must also be accessed uncached + * by the kernel or data corruption may occur. + */ + ptr = xlate_dev_mem_ptr(p); + if (!ptr) { + if (written) + break; + return -EFAULT; + } - copied = copy_from_user(ptr, buf, sz); - unxlate_dev_mem_ptr(p, ptr); - if (copied) { - written += sz - copied; - if (written) - break; - return -EFAULT; + copied = copy_from_user(ptr, buf, sz); + unxlate_dev_mem_ptr(p, ptr); + if (copied) { + written += sz - copied; + if (written) + break; + return -EFAULT; + } } buf += sz;