mirror of
https://git.proxmox.com/git/mirror_ubuntu-kernels.git
synced 2025-11-13 07:40:02 +00:00
8eb8284b41
This patch prepares the slab allocator to handle caches having annotations
(useroffset and usersize) defining usercopy regions.
This patch is modified from Brad Spengler/PaX Team's PAX_USERCOPY
whitelisting code in the last public patch of grsecurity/PaX based on
my understanding of the code. Changes or omissions from the original
code are mine and don't reflect the original grsecurity/PaX code.
Currently, hardened usercopy performs dynamic bounds checking on slab
cache objects. This is good, but still leaves a lot of kernel memory
available to be copied to/from userspace in the face of bugs. To further
restrict what memory is available for copying, this creates a way to
whitelist specific areas of a given slab cache object for copying to/from
userspace, allowing much finer granularity of access control. Slab caches
that are never exposed to userspace can declare no whitelist for their
objects, thereby keeping them unavailable to userspace via dynamic copy
operations. (Note, an implicit form of whitelisting is the use of constant
sizes in usercopy operations and get_user()/put_user(); these bypass
hardened usercopy checks since these sizes cannot change at runtime.)
To support this whitelist annotation, usercopy region offset and size
members are added to struct kmem_cache. The slab allocator receives a
new function, kmem_cache_create_usercopy(), that creates a new cache
with a usercopy region defined, suitable for declaring spans of fields
within the objects that get copied to/from userspace.
In this patch, the default kmem_cache_create() marks the entire allocation
as whitelisted, leaving it semantically unchanged. Once all fine-grained
whitelists have been added (in subsequent patches), this will be changed
to a usersize of 0, making caches created with kmem_cache_create() not
copyable to/from userspace.
After the entire usercopy whitelist series is applied, less than 15%
of the slab cache memory remains exposed to potential usercopy bugs
after a fresh boot:
Total Slab Memory: 48074720
Usercopyable Memory: 6367532 13.2%
task_struct 0.2% 4480/1630720
RAW 0.3% 300/96000
RAWv6 2.1% 1408/64768
ext4_inode_cache 3.0% 269760/8740224
dentry 11.1% 585984/5273856
mm_struct 29.1% 54912/188448
kmalloc-8 100.0% 24576/24576
kmalloc-16 100.0% 28672/28672
kmalloc-32 100.0% 81920/81920
kmalloc-192 100.0% 96768/96768
kmalloc-128 100.0% 143360/143360
names_cache 100.0% 163840/163840
kmalloc-64 100.0% 167936/167936
kmalloc-256 100.0% 339968/339968
kmalloc-512 100.0% 350720/350720
kmalloc-96 100.0% 455616/455616
kmalloc-8192 100.0% 655360/655360
kmalloc-1024 100.0% 812032/812032
kmalloc-4096 100.0% 819200/819200
kmalloc-2048 100.0% 1310720/1310720
After some kernel build workloads, the percentage (mainly driven by
dentry and inode caches expanding) drops under 10%:
Total Slab Memory: 95516184
Usercopyable Memory: 8497452 8.8%
task_struct 0.2% 4000/1456000
RAW 0.3% 300/96000
RAWv6 2.1% 1408/64768
ext4_inode_cache 3.0% 1217280/39439872
dentry 11.1% 1623200/14608800
mm_struct 29.1% 73216/251264
kmalloc-8 100.0% 24576/24576
kmalloc-16 100.0% 28672/28672
kmalloc-32 100.0% 94208/94208
kmalloc-192 100.0% 96768/96768
kmalloc-128 100.0% 143360/143360
names_cache 100.0% 163840/163840
kmalloc-64 100.0% 245760/245760
kmalloc-256 100.0% 339968/339968
kmalloc-512 100.0% 350720/350720
kmalloc-96 100.0% 563520/563520
kmalloc-8192 100.0% 655360/655360
kmalloc-1024 100.0% 794624/794624
kmalloc-4096 100.0% 819200/819200
kmalloc-2048 100.0% 1257472/1257472
Signed-off-by: David Windsor <dave@nullcore.net>
[kees: adjust commit log, split out a few extra kmalloc hunks]
[kees: add field names to function declarations]
[kees: convert BUGs to WARNs and fail closed]
[kees: add attack surface reduction analysis to commit log]
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: linux-mm@kvack.org
Cc: linux-xfs@vger.kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Acked-by: Christoph Lameter <cl@linux.com>
107 lines
2.5 KiB
C
107 lines
2.5 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _LINUX_SLAB_DEF_H
|
|
#define _LINUX_SLAB_DEF_H
|
|
|
|
#include <linux/reciprocal_div.h>
|
|
|
|
/*
|
|
* Definitions unique to the original Linux SLAB allocator.
|
|
*/
|
|
|
|
struct kmem_cache {
|
|
struct array_cache __percpu *cpu_cache;
|
|
|
|
/* 1) Cache tunables. Protected by slab_mutex */
|
|
unsigned int batchcount;
|
|
unsigned int limit;
|
|
unsigned int shared;
|
|
|
|
unsigned int size;
|
|
struct reciprocal_value reciprocal_buffer_size;
|
|
/* 2) touched by every alloc & free from the backend */
|
|
|
|
slab_flags_t flags; /* constant flags */
|
|
unsigned int num; /* # of objs per slab */
|
|
|
|
/* 3) cache_grow/shrink */
|
|
/* order of pgs per slab (2^n) */
|
|
unsigned int gfporder;
|
|
|
|
/* force GFP flags, e.g. GFP_DMA */
|
|
gfp_t allocflags;
|
|
|
|
size_t colour; /* cache colouring range */
|
|
unsigned int colour_off; /* colour offset */
|
|
struct kmem_cache *freelist_cache;
|
|
unsigned int freelist_size;
|
|
|
|
/* constructor func */
|
|
void (*ctor)(void *obj);
|
|
|
|
/* 4) cache creation/removal */
|
|
const char *name;
|
|
struct list_head list;
|
|
int refcount;
|
|
int object_size;
|
|
int align;
|
|
|
|
/* 5) statistics */
|
|
#ifdef CONFIG_DEBUG_SLAB
|
|
unsigned long num_active;
|
|
unsigned long num_allocations;
|
|
unsigned long high_mark;
|
|
unsigned long grown;
|
|
unsigned long reaped;
|
|
unsigned long errors;
|
|
unsigned long max_freeable;
|
|
unsigned long node_allocs;
|
|
unsigned long node_frees;
|
|
unsigned long node_overflow;
|
|
atomic_t allochit;
|
|
atomic_t allocmiss;
|
|
atomic_t freehit;
|
|
atomic_t freemiss;
|
|
#ifdef CONFIG_DEBUG_SLAB_LEAK
|
|
atomic_t store_user_clean;
|
|
#endif
|
|
|
|
/*
|
|
* If debugging is enabled, then the allocator can add additional
|
|
* fields and/or padding to every object. size contains the total
|
|
* object size including these internal fields, the following two
|
|
* variables contain the offset to the user object and its size.
|
|
*/
|
|
int obj_offset;
|
|
#endif /* CONFIG_DEBUG_SLAB */
|
|
|
|
#ifdef CONFIG_MEMCG
|
|
struct memcg_cache_params memcg_params;
|
|
#endif
|
|
#ifdef CONFIG_KASAN
|
|
struct kasan_cache kasan_info;
|
|
#endif
|
|
|
|
#ifdef CONFIG_SLAB_FREELIST_RANDOM
|
|
unsigned int *random_seq;
|
|
#endif
|
|
|
|
size_t useroffset; /* Usercopy region offset */
|
|
size_t usersize; /* Usercopy region size */
|
|
|
|
struct kmem_cache_node *node[MAX_NUMNODES];
|
|
};
|
|
|
|
static inline void *nearest_obj(struct kmem_cache *cache, struct page *page,
|
|
void *x)
|
|
{
|
|
void *object = x - (x - page->s_mem) % cache->size;
|
|
void *last_object = page->s_mem + (cache->num - 1) * cache->size;
|
|
|
|
if (unlikely(object > last_object))
|
|
return last_object;
|
|
else
|
|
return object;
|
|
}
|
|
|
|
#endif /* _LINUX_SLAB_DEF_H */
|