linux/arch/x86/boot/compressed/pagetable.c
Thomas Garnier 021182e52f 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 <thgarnie@google.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
Cc: Alexander Kuleshov <kuleshovmail@gmail.com>
Cc: Alexander Popov <alpopov@ptsecurity.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Borislav Petkov <bp@suse.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Dave Young <dyoung@redhat.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Jan Beulich <JBeulich@suse.com>
Cc: Joerg Roedel <jroedel@suse.de>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Lv Zheng <lv.zheng@intel.com>
Cc: Mark Salter <msalter@redhat.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Matt Fleming <matt@codeblueprint.co.uk>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephen Smalley <sds@tycho.nsa.gov>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Toshi Kani <toshi.kani@hpe.com>
Cc: Xiao Guangrong <guangrong.xiao@linux.intel.com>
Cc: Yinghai Lu <yinghai@kernel.org>
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 <mingo@kernel.org>
2016-07-08 17:35:15 +02:00

139 lines
4.0 KiB
C

/*
* This code is used on x86_64 to create page table identity mappings on
* demand by building up a new set of page tables (or appending to the
* existing ones), and then switching over to them when ready.
*
* Copyright (C) 2015-2016 Yinghai Lu
* Copyright (C) 2016 Kees Cook
*/
/*
* Since we're dealing with identity mappings, physical and virtual
* addresses are the same, so override these defines which are ultimately
* used by the headers in misc.h.
*/
#define __pa(x) ((unsigned long)(x))
#define __va(x) ((void *)((unsigned long)(x)))
#include "misc.h"
/* These actually do the work of building the kernel identity maps. */
#include <asm/init.h>
#include <asm/pgtable.h>
/* 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. */
unsigned long __force_order;
/* Used to track our page table allocation area. */
struct alloc_pgt_data {
unsigned char *pgt_buf;
unsigned long pgt_buf_size;
unsigned long pgt_buf_offset;
};
/*
* Allocates space for a page table entry, using struct alloc_pgt_data
* above. Besides the local callers, this is used as the allocation
* callback in mapping_info below.
*/
static void *alloc_pgt_page(void *context)
{
struct alloc_pgt_data *pages = (struct alloc_pgt_data *)context;
unsigned char *entry;
/* Validate there is space available for a new page. */
if (pages->pgt_buf_offset >= pages->pgt_buf_size) {
debug_putstr("out of pgt_buf in " __FILE__ "!?\n");
debug_putaddr(pages->pgt_buf_offset);
debug_putaddr(pages->pgt_buf_size);
return NULL;
}
entry = pages->pgt_buf + pages->pgt_buf_offset;
pages->pgt_buf_offset += PAGE_SIZE;
return entry;
}
/* Used to track our allocated page tables. */
static struct alloc_pgt_data pgt_data;
/* The top level page table entry pointer. */
static unsigned long level4p;
/*
* Mapping information structure passed to kernel_ident_mapping_init().
* Due to relocation, pointers must be assigned at run time not build time.
*/
static struct x86_mapping_info mapping_info = {
.pmd_flag = __PAGE_KERNEL_LARGE_EXEC,
};
/* Locates and clears a region for a new top level page table. */
void initialize_identity_maps(void)
{
/* Init mapping_info with run-time function/buffer pointers. */
mapping_info.alloc_pgt_page = alloc_pgt_page;
mapping_info.context = &pgt_data;
/*
* It should be impossible for this not to already be true,
* but since calling this a second time would rewind the other
* counters, let's just make sure this is reset too.
*/
pgt_data.pgt_buf_offset = 0;
/*
* If we came here via startup_32(), cr3 will be _pgtable already
* and we must append to the existing area instead of entirely
* overwriting it.
*/
level4p = read_cr3();
if (level4p == (unsigned long)_pgtable) {
debug_putstr("booted via startup_32()\n");
pgt_data.pgt_buf = _pgtable + BOOT_INIT_PGT_SIZE;
pgt_data.pgt_buf_size = BOOT_PGT_SIZE - BOOT_INIT_PGT_SIZE;
memset(pgt_data.pgt_buf, 0, pgt_data.pgt_buf_size);
} else {
debug_putstr("booted via startup_64()\n");
pgt_data.pgt_buf = _pgtable;
pgt_data.pgt_buf_size = BOOT_PGT_SIZE;
memset(pgt_data.pgt_buf, 0, pgt_data.pgt_buf_size);
level4p = (unsigned long)alloc_pgt_page(&pgt_data);
}
}
/*
* Adds the specified range to what will become the new identity mappings.
* Once all ranges have been added, the new mapping is activated by calling
* finalize_identity_maps() below.
*/
void add_identity_map(unsigned long start, unsigned long size)
{
unsigned long end = start + size;
/* Align boundary to 2M. */
start = round_down(start, PMD_SIZE);
end = round_up(end, PMD_SIZE);
if (start >= end)
return;
/* Build the mapping. */
kernel_ident_mapping_init(&mapping_info, (pgd_t *)level4p,
start, end);
}
/*
* This switches the page tables to the new level4 that has been built
* via calls to add_identity_map() above. If booted via startup_32(),
* this is effectively a no-op.
*/
void finalize_identity_maps(void)
{
write_cr3(level4p);
}