kernel_optimize_test/mm/kasan/generic_report.c
Daniel Axtens 3c5c3cfb9e kasan: support backing vmalloc space with real shadow memory
Patch series "kasan: support backing vmalloc space with real shadow
memory", v11.

Currently, vmalloc space is backed by the early shadow page.  This means
that kasan is incompatible with VMAP_STACK.

This series provides a mechanism to back vmalloc space with real,
dynamically allocated memory.  I have only wired up x86, because that's
the only currently supported arch I can work with easily, but it's very
easy to wire up other architectures, and it appears that there is some
work-in-progress code to do this on arm64 and s390.

This has been discussed before in the context of VMAP_STACK:
 - https://bugzilla.kernel.org/show_bug.cgi?id=202009
 - https://lkml.org/lkml/2018/7/22/198
 - https://lkml.org/lkml/2019/7/19/822

In terms of implementation details:

Most mappings in vmalloc space are small, requiring less than a full
page of shadow space.  Allocating a full shadow page per mapping would
therefore be wasteful.  Furthermore, to ensure that different mappings
use different shadow pages, mappings would have to be aligned to
KASAN_SHADOW_SCALE_SIZE * PAGE_SIZE.

Instead, share backing space across multiple mappings.  Allocate a
backing page when a mapping in vmalloc space uses a particular page of
the shadow region.  This page can be shared by other vmalloc mappings
later on.

We hook in to the vmap infrastructure to lazily clean up unused shadow
memory.

Testing with test_vmalloc.sh on an x86 VM with 2 vCPUs shows that:

 - Turning on KASAN, inline instrumentation, without vmalloc, introuduces
   a 4.1x-4.2x slowdown in vmalloc operations.

 - Turning this on introduces the following slowdowns over KASAN:
     * ~1.76x slower single-threaded (test_vmalloc.sh performance)
     * ~2.18x slower when both cpus are performing operations
       simultaneously (test_vmalloc.sh sequential_test_order=1)

This is unfortunate but given that this is a debug feature only, not the
end of the world.  The benchmarks are also a stress-test for the vmalloc
subsystem: they're not indicative of an overall 2x slowdown!

This patch (of 4):

Hook into vmalloc and vmap, and dynamically allocate real shadow memory
to back the mappings.

Most mappings in vmalloc space are small, requiring less than a full
page of shadow space.  Allocating a full shadow page per mapping would
therefore be wasteful.  Furthermore, to ensure that different mappings
use different shadow pages, mappings would have to be aligned to
KASAN_SHADOW_SCALE_SIZE * PAGE_SIZE.

Instead, share backing space across multiple mappings.  Allocate a
backing page when a mapping in vmalloc space uses a particular page of
the shadow region.  This page can be shared by other vmalloc mappings
later on.

We hook in to the vmap infrastructure to lazily clean up unused shadow
memory.

To avoid the difficulties around swapping mappings around, this code
expects that the part of the shadow region that covers the vmalloc space
will not be covered by the early shadow page, but will be left unmapped.
This will require changes in arch-specific code.

This allows KASAN with VMAP_STACK, and may be helpful for architectures
that do not have a separate module space (e.g.  powerpc64, which I am
currently working on).  It also allows relaxing the module alignment
back to PAGE_SIZE.

Testing with test_vmalloc.sh on an x86 VM with 2 vCPUs shows that:

 - Turning on KASAN, inline instrumentation, without vmalloc, introuduces
   a 4.1x-4.2x slowdown in vmalloc operations.

 - Turning this on introduces the following slowdowns over KASAN:
     * ~1.76x slower single-threaded (test_vmalloc.sh performance)
     * ~2.18x slower when both cpus are performing operations
       simultaneously (test_vmalloc.sh sequential_test_order=3D1)

This is unfortunate but given that this is a debug feature only, not the
end of the world.

The full benchmark results are:

Performance

                              No KASAN      KASAN original x baseline  KASAN vmalloc x baseline    x KASAN

fix_size_alloc_test             662004            11404956      17.23       19144610      28.92       1.68
full_fit_alloc_test             710950            12029752      16.92       13184651      18.55       1.10
long_busy_list_alloc_test      9431875            43990172       4.66       82970178       8.80       1.89
random_size_alloc_test         5033626            23061762       4.58       47158834       9.37       2.04
fix_align_alloc_test           1252514            15276910      12.20       31266116      24.96       2.05
random_size_align_alloc_te     1648501            14578321       8.84       25560052      15.51       1.75
align_shift_alloc_test             147                 830       5.65           5692      38.72       6.86
pcpu_alloc_test                  80732              125520       1.55         140864       1.74       1.12
Total Cycles              119240774314        763211341128       6.40  1390338696894      11.66       1.82

Sequential, 2 cpus

                              No KASAN      KASAN original x baseline  KASAN vmalloc x baseline    x KASAN

fix_size_alloc_test            1423150            14276550      10.03       27733022      19.49       1.94
full_fit_alloc_test            1754219            14722640       8.39       15030786       8.57       1.02
long_busy_list_alloc_test     11451858            52154973       4.55      107016027       9.34       2.05
random_size_alloc_test         5989020            26735276       4.46       68885923      11.50       2.58
fix_align_alloc_test           2050976            20166900       9.83       50491675      24.62       2.50
random_size_align_alloc_te     2858229            17971700       6.29       38730225      13.55       2.16
align_shift_alloc_test             405                6428      15.87          26253      64.82       4.08
pcpu_alloc_test                 127183              151464       1.19         216263       1.70       1.43
Total Cycles               54181269392        308723699764       5.70   650772566394      12.01       2.11
fix_size_alloc_test            1420404            14289308      10.06       27790035      19.56       1.94
full_fit_alloc_test            1736145            14806234       8.53       15274301       8.80       1.03
long_busy_list_alloc_test     11404638            52270785       4.58      107550254       9.43       2.06
random_size_alloc_test         6017006            26650625       4.43       68696127      11.42       2.58
fix_align_alloc_test           2045504            20280985       9.91       50414862      24.65       2.49
random_size_align_alloc_te     2845338            17931018       6.30       38510276      13.53       2.15
align_shift_alloc_test             472                3760       7.97           9656      20.46       2.57
pcpu_alloc_test                 118643              132732       1.12         146504       1.23       1.10
Total Cycles               54040011688        309102805492       5.72   651325675652      12.05       2.11

[dja@axtens.net: fixups]
  Link: http://lkml.kernel.org/r/20191120052719.7201-1-dja@axtens.net
Link: https://bugzilla.kernel.org/show_bug.cgi?id=3D202009
Link: http://lkml.kernel.org/r/20191031093909.9228-2-dja@axtens.net
Signed-off-by: Mark Rutland <mark.rutland@arm.com> [shadow rework]
Signed-off-by: Daniel Axtens <dja@axtens.net>
Co-developed-by: Mark Rutland <mark.rutland@arm.com>
Acked-by: Vasily Gorbik <gor@linux.ibm.com>
Reviewed-by: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Christophe Leroy <christophe.leroy@c-s.fr>
Cc: Qian Cai <cai@lca.pw>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-12-01 12:59:05 -08:00

154 lines
4.1 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* This file contains generic KASAN specific error reporting code.
*
* Copyright (c) 2014 Samsung Electronics Co., Ltd.
* Author: Andrey Ryabinin <ryabinin.a.a@gmail.com>
*
* Some code borrowed from https://github.com/xairy/kasan-prototype by
* Andrey Konovalov <andreyknvl@gmail.com>
*
* 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.
*
*/
#include <linux/bitops.h>
#include <linux/ftrace.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/printk.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/stackdepot.h>
#include <linux/stacktrace.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/kasan.h>
#include <linux/module.h>
#include <asm/sections.h>
#include "kasan.h"
#include "../slab.h"
void *find_first_bad_addr(void *addr, size_t size)
{
void *p = addr;
while (p < addr + size && !(*(u8 *)kasan_mem_to_shadow(p)))
p += KASAN_SHADOW_SCALE_SIZE;
return p;
}
static const char *get_shadow_bug_type(struct kasan_access_info *info)
{
const char *bug_type = "unknown-crash";
u8 *shadow_addr;
shadow_addr = (u8 *)kasan_mem_to_shadow(info->first_bad_addr);
/*
* If shadow byte value is in [0, KASAN_SHADOW_SCALE_SIZE) we can look
* at the next shadow byte to determine the type of the bad access.
*/
if (*shadow_addr > 0 && *shadow_addr <= KASAN_SHADOW_SCALE_SIZE - 1)
shadow_addr++;
switch (*shadow_addr) {
case 0 ... KASAN_SHADOW_SCALE_SIZE - 1:
/*
* In theory it's still possible to see these shadow values
* due to a data race in the kernel code.
*/
bug_type = "out-of-bounds";
break;
case KASAN_PAGE_REDZONE:
case KASAN_KMALLOC_REDZONE:
bug_type = "slab-out-of-bounds";
break;
case KASAN_GLOBAL_REDZONE:
bug_type = "global-out-of-bounds";
break;
case KASAN_STACK_LEFT:
case KASAN_STACK_MID:
case KASAN_STACK_RIGHT:
case KASAN_STACK_PARTIAL:
bug_type = "stack-out-of-bounds";
break;
case KASAN_FREE_PAGE:
case KASAN_KMALLOC_FREE:
bug_type = "use-after-free";
break;
case KASAN_ALLOCA_LEFT:
case KASAN_ALLOCA_RIGHT:
bug_type = "alloca-out-of-bounds";
break;
case KASAN_VMALLOC_INVALID:
bug_type = "vmalloc-out-of-bounds";
break;
}
return bug_type;
}
static const char *get_wild_bug_type(struct kasan_access_info *info)
{
const char *bug_type = "unknown-crash";
if ((unsigned long)info->access_addr < PAGE_SIZE)
bug_type = "null-ptr-deref";
else if ((unsigned long)info->access_addr < TASK_SIZE)
bug_type = "user-memory-access";
else
bug_type = "wild-memory-access";
return bug_type;
}
const char *get_bug_type(struct kasan_access_info *info)
{
if (addr_has_shadow(info->access_addr))
return get_shadow_bug_type(info);
return get_wild_bug_type(info);
}
#define DEFINE_ASAN_REPORT_LOAD(size) \
void __asan_report_load##size##_noabort(unsigned long addr) \
{ \
kasan_report(addr, size, false, _RET_IP_); \
} \
EXPORT_SYMBOL(__asan_report_load##size##_noabort)
#define DEFINE_ASAN_REPORT_STORE(size) \
void __asan_report_store##size##_noabort(unsigned long addr) \
{ \
kasan_report(addr, size, true, _RET_IP_); \
} \
EXPORT_SYMBOL(__asan_report_store##size##_noabort)
DEFINE_ASAN_REPORT_LOAD(1);
DEFINE_ASAN_REPORT_LOAD(2);
DEFINE_ASAN_REPORT_LOAD(4);
DEFINE_ASAN_REPORT_LOAD(8);
DEFINE_ASAN_REPORT_LOAD(16);
DEFINE_ASAN_REPORT_STORE(1);
DEFINE_ASAN_REPORT_STORE(2);
DEFINE_ASAN_REPORT_STORE(4);
DEFINE_ASAN_REPORT_STORE(8);
DEFINE_ASAN_REPORT_STORE(16);
void __asan_report_load_n_noabort(unsigned long addr, size_t size)
{
kasan_report(addr, size, false, _RET_IP_);
}
EXPORT_SYMBOL(__asan_report_load_n_noabort);
void __asan_report_store_n_noabort(unsigned long addr, size_t size)
{
kasan_report(addr, size, true, _RET_IP_);
}
EXPORT_SYMBOL(__asan_report_store_n_noabort);