mirror of
https://github.com/torvalds/linux.git
synced 2024-11-14 16:12:02 +00:00
cabdf74e6b
kfence_metadata is currently a static array. For the purpose of allocating scalable __kfence_pool, we first change it to runtime allocation of metadata. Since the size of an object of kfence_metadata is 1160 bytes, we can save at least 72 pages (with default 256 objects) without enabling kfence. [akpm@linux-foundation.org: restore newline, per Marco] Link: https://lkml.kernel.org/r/20230718073019.52513-1-zhangpeng.00@bytedance.com Signed-off-by: Peng Zhang <zhangpeng.00@bytedance.com> Reviewed-by: Marco Elver <elver@google.com> Cc: Alexander Potapenko <glider@google.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Muchun Song <muchun.song@linux.dev> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
146 lines
4.3 KiB
C
146 lines
4.3 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/*
|
|
* Kernel Electric-Fence (KFENCE). For more info please see
|
|
* Documentation/dev-tools/kfence.rst.
|
|
*
|
|
* Copyright (C) 2020, Google LLC.
|
|
*/
|
|
|
|
#ifndef MM_KFENCE_KFENCE_H
|
|
#define MM_KFENCE_KFENCE_H
|
|
|
|
#include <linux/mm.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/spinlock.h>
|
|
#include <linux/types.h>
|
|
|
|
#include "../slab.h" /* for struct kmem_cache */
|
|
|
|
/*
|
|
* Get the canary byte pattern for @addr. Use a pattern that varies based on the
|
|
* lower 3 bits of the address, to detect memory corruptions with higher
|
|
* probability, where similar constants are used.
|
|
*/
|
|
#define KFENCE_CANARY_PATTERN_U8(addr) ((u8)0xaa ^ (u8)((unsigned long)(addr) & 0x7))
|
|
|
|
/*
|
|
* Define a continuous 8-byte canary starting from a multiple of 8. The canary
|
|
* of each byte is only related to the lowest three bits of its address, so the
|
|
* canary of every 8 bytes is the same. 64-bit memory can be filled and checked
|
|
* at a time instead of byte by byte to improve performance.
|
|
*/
|
|
#define KFENCE_CANARY_PATTERN_U64 ((u64)0xaaaaaaaaaaaaaaaa ^ (u64)(le64_to_cpu(0x0706050403020100)))
|
|
|
|
/* Maximum stack depth for reports. */
|
|
#define KFENCE_STACK_DEPTH 64
|
|
|
|
/* KFENCE object states. */
|
|
enum kfence_object_state {
|
|
KFENCE_OBJECT_UNUSED, /* Object is unused. */
|
|
KFENCE_OBJECT_ALLOCATED, /* Object is currently allocated. */
|
|
KFENCE_OBJECT_FREED, /* Object was allocated, and then freed. */
|
|
};
|
|
|
|
/* Alloc/free tracking information. */
|
|
struct kfence_track {
|
|
pid_t pid;
|
|
int cpu;
|
|
u64 ts_nsec;
|
|
int num_stack_entries;
|
|
unsigned long stack_entries[KFENCE_STACK_DEPTH];
|
|
};
|
|
|
|
/* KFENCE metadata per guarded allocation. */
|
|
struct kfence_metadata {
|
|
struct list_head list; /* Freelist node; access under kfence_freelist_lock. */
|
|
struct rcu_head rcu_head; /* For delayed freeing. */
|
|
|
|
/*
|
|
* Lock protecting below data; to ensure consistency of the below data,
|
|
* since the following may execute concurrently: __kfence_alloc(),
|
|
* __kfence_free(), kfence_handle_page_fault(). However, note that we
|
|
* cannot grab the same metadata off the freelist twice, and multiple
|
|
* __kfence_alloc() cannot run concurrently on the same metadata.
|
|
*/
|
|
raw_spinlock_t lock;
|
|
|
|
/* The current state of the object; see above. */
|
|
enum kfence_object_state state;
|
|
|
|
/*
|
|
* Allocated object address; cannot be calculated from size, because of
|
|
* alignment requirements.
|
|
*
|
|
* Invariant: ALIGN_DOWN(addr, PAGE_SIZE) is constant.
|
|
*/
|
|
unsigned long addr;
|
|
|
|
/*
|
|
* The size of the original allocation.
|
|
*/
|
|
size_t size;
|
|
|
|
/*
|
|
* The kmem_cache cache of the last allocation; NULL if never allocated
|
|
* or the cache has already been destroyed.
|
|
*/
|
|
struct kmem_cache *cache;
|
|
|
|
/*
|
|
* In case of an invalid access, the page that was unprotected; we
|
|
* optimistically only store one address.
|
|
*/
|
|
unsigned long unprotected_page;
|
|
|
|
/* Allocation and free stack information. */
|
|
struct kfence_track alloc_track;
|
|
struct kfence_track free_track;
|
|
/* For updating alloc_covered on frees. */
|
|
u32 alloc_stack_hash;
|
|
#ifdef CONFIG_MEMCG
|
|
struct obj_cgroup *objcg;
|
|
#endif
|
|
};
|
|
|
|
#define KFENCE_METADATA_SIZE PAGE_ALIGN(sizeof(struct kfence_metadata) * \
|
|
CONFIG_KFENCE_NUM_OBJECTS)
|
|
|
|
extern struct kfence_metadata *kfence_metadata;
|
|
|
|
static inline struct kfence_metadata *addr_to_metadata(unsigned long addr)
|
|
{
|
|
long index;
|
|
|
|
/* The checks do not affect performance; only called from slow-paths. */
|
|
|
|
if (!is_kfence_address((void *)addr))
|
|
return NULL;
|
|
|
|
/*
|
|
* May be an invalid index if called with an address at the edge of
|
|
* __kfence_pool, in which case we would report an "invalid access"
|
|
* error.
|
|
*/
|
|
index = (addr - (unsigned long)__kfence_pool) / (PAGE_SIZE * 2) - 1;
|
|
if (index < 0 || index >= CONFIG_KFENCE_NUM_OBJECTS)
|
|
return NULL;
|
|
|
|
return &kfence_metadata[index];
|
|
}
|
|
|
|
/* KFENCE error types for report generation. */
|
|
enum kfence_error_type {
|
|
KFENCE_ERROR_OOB, /* Detected a out-of-bounds access. */
|
|
KFENCE_ERROR_UAF, /* Detected a use-after-free access. */
|
|
KFENCE_ERROR_CORRUPTION, /* Detected a memory corruption on free. */
|
|
KFENCE_ERROR_INVALID, /* Invalid access of unknown type. */
|
|
KFENCE_ERROR_INVALID_FREE, /* Invalid free. */
|
|
};
|
|
|
|
void kfence_report_error(unsigned long address, bool is_write, struct pt_regs *regs,
|
|
const struct kfence_metadata *meta, enum kfence_error_type type);
|
|
|
|
void kfence_print_object(struct seq_file *seq, const struct kfence_metadata *meta);
|
|
|
|
#endif /* MM_KFENCE_KFENCE_H */
|