OpenCloudOS-Kernel/mm/usercopy.c

282 lines
8.8 KiB
C
Raw Normal View History

/*
* This implements the various checks for CONFIG_HARDENED_USERCOPY*,
* which are designed to protect kernel memory from needless exposure
* and overwrite under many unintended conditions. This code is based
* on PAX_USERCOPY, which is:
*
* Copyright (C) 2001-2016 PaX Team, Bradley Spengler, Open Source
* Security Inc.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/sched/task.h>
#include <linux/sched/task_stack.h>
#include <linux/thread_info.h>
#include <asm/sections.h>
/*
* Checks if a given pointer and length is contained by the current
* stack frame (if possible).
*
* Returns:
* NOT_STACK: not at all on the stack
* GOOD_FRAME: fully within a valid stack frame
* GOOD_STACK: fully on the stack (when can't do frame-checking)
* BAD_STACK: error condition (invalid stack position or bad stack frame)
*/
static noinline int check_stack_object(const void *obj, unsigned long len)
{
const void * const stack = task_stack_page(current);
const void * const stackend = stack + THREAD_SIZE;
int ret;
/* Object is not on the stack at all. */
if (obj + len <= stack || stackend <= obj)
return NOT_STACK;
/*
* Reject: object partially overlaps the stack (passing the
* the check above means at least one end is within the stack,
* so if this check fails, the other end is outside the stack).
*/
if (obj < stack || stackend < obj + len)
return BAD_STACK;
/* Check if object is safely within a valid frame. */
ret = arch_within_stack_frames(stack, stackend, obj, len);
if (ret)
return ret;
return GOOD_STACK;
}
/*
* If these functions are reached, then CONFIG_HARDENED_USERCOPY has found
* an unexpected state during a copy_from_user() or copy_to_user() call.
* There are several checks being performed on the buffer by the
* __check_object_size() function. Normal stack buffer usage should never
* trip the checks, and kernel text addressing will always trip the check.
* For cache objects, it is checking that only the whitelisted range of
* bytes for a given cache is being accessed (via the cache's usersize and
* useroffset fields). To adjust a cache whitelist, use the usercopy-aware
* kmem_cache_create_usercopy() function to create the cache (and
* carefully audit the whitelist range).
*/
void usercopy_warn(const char *name, const char *detail, bool to_user,
unsigned long offset, unsigned long len)
{
WARN_ONCE(1, "Bad or missing usercopy whitelist? Kernel memory %s attempt detected %s %s%s%s%s (offset %lu, size %lu)!\n",
to_user ? "exposure" : "overwrite",
to_user ? "from" : "to",
name ? : "unknown?!",
detail ? " '" : "", detail ? : "", detail ? "'" : "",
offset, len);
}
void __noreturn usercopy_abort(const char *name, const char *detail,
bool to_user, unsigned long offset,
unsigned long len)
{
pr_emerg("Kernel memory %s attempt detected %s %s%s%s%s (offset %lu, size %lu)!\n",
to_user ? "exposure" : "overwrite",
to_user ? "from" : "to",
name ? : "unknown?!",
detail ? " '" : "", detail ? : "", detail ? "'" : "",
offset, len);
/*
* For greater effect, it would be nice to do do_group_exit(),
* but BUG() actually hooks all the lock-breaking and per-arch
* Oops code, so that is used here instead.
*/
BUG();
}
/* Returns true if any portion of [ptr,ptr+n) over laps with [low,high). */
static bool overlaps(const unsigned long ptr, unsigned long n,
unsigned long low, unsigned long high)
{
const unsigned long check_low = ptr;
unsigned long check_high = check_low + n;
/* Does not overlap if entirely above or entirely below. */
usercopy: fix overlap check for kernel text When running with a local patch which moves the '_stext' symbol to the very beginning of the kernel text area, I got the following panic with CONFIG_HARDENED_USERCOPY: usercopy: kernel memory exposure attempt detected from ffff88103dfff000 (<linear kernel text>) (4096 bytes) ------------[ cut here ]------------ kernel BUG at mm/usercopy.c:79! invalid opcode: 0000 [#1] SMP ... CPU: 0 PID: 4800 Comm: cp Not tainted 4.8.0-rc3.after+ #1 Hardware name: Dell Inc. PowerEdge R720/0X3D66, BIOS 2.5.4 01/22/2016 task: ffff880817444140 task.stack: ffff880816274000 RIP: 0010:[<ffffffff8121c796>] __check_object_size+0x76/0x413 RSP: 0018:ffff880816277c40 EFLAGS: 00010246 RAX: 000000000000006b RBX: ffff88103dfff000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffff88081f80dfa8 RDI: ffff88081f80dfa8 RBP: ffff880816277c90 R08: 000000000000054c R09: 0000000000000000 R10: 0000000000000005 R11: 0000000000000006 R12: 0000000000001000 R13: ffff88103e000000 R14: ffff88103dffffff R15: 0000000000000001 FS: 00007fb9d1750800(0000) GS:ffff88081f800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000021d2000 CR3: 000000081a08f000 CR4: 00000000001406f0 Stack: ffff880816277cc8 0000000000010000 000000043de07000 0000000000000000 0000000000001000 ffff880816277e60 0000000000001000 ffff880816277e28 000000000000c000 0000000000001000 ffff880816277ce8 ffffffff8136c3a6 Call Trace: [<ffffffff8136c3a6>] copy_page_to_iter_iovec+0xa6/0x1c0 [<ffffffff8136e766>] copy_page_to_iter+0x16/0x90 [<ffffffff811970e3>] generic_file_read_iter+0x3e3/0x7c0 [<ffffffffa06a738d>] ? xfs_file_buffered_aio_write+0xad/0x260 [xfs] [<ffffffff816e6262>] ? down_read+0x12/0x40 [<ffffffffa06a61b1>] xfs_file_buffered_aio_read+0x51/0xc0 [xfs] [<ffffffffa06a6692>] xfs_file_read_iter+0x62/0xb0 [xfs] [<ffffffff812224cf>] __vfs_read+0xdf/0x130 [<ffffffff81222c9e>] vfs_read+0x8e/0x140 [<ffffffff81224195>] SyS_read+0x55/0xc0 [<ffffffff81003a47>] do_syscall_64+0x67/0x160 [<ffffffff816e8421>] entry_SYSCALL64_slow_path+0x25/0x25 RIP: 0033:[<00007fb9d0c33c00>] 0x7fb9d0c33c00 RSP: 002b:00007ffc9c262f28 EFLAGS: 00000246 ORIG_RAX: 0000000000000000 RAX: ffffffffffffffda RBX: fffffffffff8ffff RCX: 00007fb9d0c33c00 RDX: 0000000000010000 RSI: 00000000021c3000 RDI: 0000000000000004 RBP: 00000000021c3000 R08: 0000000000000000 R09: 00007ffc9c264d6c R10: 00007ffc9c262c50 R11: 0000000000000246 R12: 0000000000010000 R13: 00007ffc9c2630b0 R14: 0000000000000004 R15: 0000000000010000 Code: 81 48 0f 44 d0 48 c7 c6 90 4d a3 81 48 c7 c0 bb b3 a2 81 48 0f 44 f0 4d 89 e1 48 89 d9 48 c7 c7 68 16 a3 81 31 c0 e8 f4 57 f7 ff <0f> 0b 48 8d 90 00 40 00 00 48 39 d3 0f 83 22 01 00 00 48 39 c3 RIP [<ffffffff8121c796>] __check_object_size+0x76/0x413 RSP <ffff880816277c40> The checked object's range [ffff88103dfff000, ffff88103e000000) is valid, so there shouldn't have been a BUG. The hardened usercopy code got confused because the range's ending address is the same as the kernel's text starting address at 0xffff88103e000000. The overlap check is slightly off. Fixes: f5509cc18daa ("mm: Hardened usercopy") Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com> Signed-off-by: Kees Cook <keescook@chromium.org>
2016-08-23 00:53:59 +08:00
if (check_low >= high || check_high <= low)
return false;
return true;
}
/* Is this address range in the kernel text area? */
static inline void check_kernel_text_object(const unsigned long ptr,
unsigned long n, bool to_user)
{
unsigned long textlow = (unsigned long)_stext;
unsigned long texthigh = (unsigned long)_etext;
unsigned long textlow_linear, texthigh_linear;
if (overlaps(ptr, n, textlow, texthigh))
usercopy_abort("kernel text", NULL, to_user, ptr - textlow, n);
/*
* Some architectures have virtual memory mappings with a secondary
* mapping of the kernel text, i.e. there is more than one virtual
* kernel address that points to the kernel image. It is usually
* when there is a separate linear physical memory mapping, in that
* __pa() is not just the reverse of __va(). This can be detected
* and checked:
*/
textlow_linear = (unsigned long)lm_alias(textlow);
/* No different mapping: we're done. */
if (textlow_linear == textlow)
return;
/* Check the secondary mapping... */
texthigh_linear = (unsigned long)lm_alias(texthigh);
if (overlaps(ptr, n, textlow_linear, texthigh_linear))
usercopy_abort("linear kernel text", NULL, to_user,
ptr - textlow_linear, n);
}
static inline void check_bogus_address(const unsigned long ptr, unsigned long n,
bool to_user)
{
/* Reject if object wraps past end of memory. */
if (ptr + n < ptr)
usercopy_abort("wrapped address", NULL, to_user, 0, ptr + n);
/* Reject if NULL or ZERO-allocation. */
if (ZERO_OR_NULL_PTR(ptr))
usercopy_abort("null address", NULL, to_user, ptr, n);
}
/* Checks for allocs that are marked in some way as spanning multiple pages. */
static inline void check_page_span(const void *ptr, unsigned long n,
struct page *page, bool to_user)
{
#ifdef CONFIG_HARDENED_USERCOPY_PAGESPAN
const void *end = ptr + n - 1;
struct page *endpage;
bool is_reserved, is_cma;
/*
* Sometimes the kernel data regions are not marked Reserved (see
* check below). And sometimes [_sdata,_edata) does not cover
* rodata and/or bss, so check each range explicitly.
*/
/* Allow reads of kernel rodata region (if not marked as Reserved). */
if (ptr >= (const void *)__start_rodata &&
end <= (const void *)__end_rodata) {
if (!to_user)
usercopy_abort("rodata", NULL, to_user, 0, n);
return;
}
/* Allow kernel data region (if not marked as Reserved). */
if (ptr >= (const void *)_sdata && end <= (const void *)_edata)
return;
/* Allow kernel bss region (if not marked as Reserved). */
if (ptr >= (const void *)__bss_start &&
end <= (const void *)__bss_stop)
return;
/* Is the object wholly within one base page? */
if (likely(((unsigned long)ptr & (unsigned long)PAGE_MASK) ==
((unsigned long)end & (unsigned long)PAGE_MASK)))
return;
/* Allow if fully inside the same compound (__GFP_COMP) page. */
endpage = virt_to_head_page(end);
if (likely(endpage == page))
return;
/*
* Reject if range is entirely either Reserved (i.e. special or
* device memory), or CMA. Otherwise, reject since the object spans
* several independently allocated pages.
*/
is_reserved = PageReserved(page);
is_cma = is_migrate_cma_page(page);
if (!is_reserved && !is_cma)
usercopy_abort("spans multiple pages", NULL, to_user, 0, n);
for (ptr += PAGE_SIZE; ptr <= end; ptr += PAGE_SIZE) {
page = virt_to_head_page(ptr);
if (is_reserved && !PageReserved(page))
usercopy_abort("spans Reserved and non-Reserved pages",
NULL, to_user, 0, n);
if (is_cma && !is_migrate_cma_page(page))
usercopy_abort("spans CMA and non-CMA pages", NULL,
to_user, 0, n);
}
#endif
}
static inline void check_heap_object(const void *ptr, unsigned long n,
bool to_user)
{
struct page *page;
if (!virt_addr_valid(ptr))
return;
page = virt_to_head_page(ptr);
if (PageSlab(page)) {
/* Check slab allocator for flags and size. */
__check_heap_object(ptr, n, page, to_user);
} else {
/* Verify object does not incorrectly span multiple pages. */
check_page_span(ptr, n, page, to_user);
}
}
/*
* Validates that the given object is:
* - not bogus address
* - known-safe heap or stack object
* - not in kernel text
*/
void __check_object_size(const void *ptr, unsigned long n, bool to_user)
{
/* Skip all tests if size is zero. */
if (!n)
return;
/* Check for invalid addresses. */
check_bogus_address((const unsigned long)ptr, n, to_user);
/* Check for bad heap object. */
check_heap_object(ptr, n, to_user);
/* Check for bad stack object. */
switch (check_stack_object(ptr, n)) {
case NOT_STACK:
/* Object is not touching the current process stack. */
break;
case GOOD_FRAME:
case GOOD_STACK:
/*
* Object is either in the correct frame (when it
* is possible to check) or just generally on the
* process stack (when frame checking not available).
*/
return;
default:
usercopy_abort("process stack", NULL, to_user, 0, n);
}
/* Check for object in kernel to avoid text exposure. */
check_kernel_text_object((const unsigned long)ptr, n, to_user);
}
EXPORT_SYMBOL(__check_object_size);