mirror of
https://github.com/torvalds/linux.git
synced 2024-11-29 23:51:37 +00:00
3c61529405
When exploiting memory vulnerabilities, "heap spraying" is a common technique targeting those related to dynamic memory allocation (i.e. the "heap"), and it plays an important role in a successful exploitation. Basically, it is to overwrite the memory area of vulnerable object by triggering allocation in other subsystems or modules and therefore getting a reference to the targeted memory location. It's usable on various types of vulnerablity including use after free (UAF), heap out- of-bound write and etc. There are (at least) two reasons why the heap can be sprayed: 1) generic slab caches are shared among different subsystems and modules, and 2) dedicated slab caches could be merged with the generic ones. Currently these two factors cannot be prevented at a low cost: the first one is a widely used memory allocation mechanism, and shutting down slab merging completely via `slub_nomerge` would be overkill. To efficiently prevent heap spraying, we propose the following approach: to create multiple copies of generic slab caches that will never be merged, and random one of them will be used at allocation. The random selection is based on the address of code that calls `kmalloc()`, which means it is static at runtime (rather than dynamically determined at each time of allocation, which could be bypassed by repeatedly spraying in brute force). In other words, the randomness of cache selection will be with respect to the code address rather than time, i.e. allocations in different code paths would most likely pick different caches, although kmalloc() at each place would use the same cache copy whenever it is executed. In this way, the vulnerable object and memory allocated in other subsystems and modules will (most probably) be on different slab caches, which prevents the object from being sprayed. Meanwhile, the static random selection is further enhanced with a per-boot random seed, which prevents the attacker from finding a usable kmalloc that happens to pick the same cache with the vulnerable subsystem/module by analyzing the open source code. In other words, with the per-boot seed, the random selection is static during each time the system starts and runs, but not across different system startups. The overhead of performance has been tested on a 40-core x86 server by comparing the results of `perf bench all` between the kernels with and without this patch based on the latest linux-next kernel, which shows minor difference. A subset of benchmarks are listed below: sched/ sched/ syscall/ mem/ mem/ messaging pipe basic memcpy memset (sec) (sec) (sec) (GB/sec) (GB/sec) control1 0.019 5.459 0.733 15.258789 51.398026 control2 0.019 5.439 0.730 16.009221 48.828125 control3 0.019 5.282 0.735 16.009221 48.828125 control_avg 0.019 5.393 0.733 15.759077 49.684759 experiment1 0.019 5.374 0.741 15.500992 46.502976 experiment2 0.019 5.440 0.746 16.276042 51.398026 experiment3 0.019 5.242 0.752 15.258789 51.398026 experiment_avg 0.019 5.352 0.746 15.678608 49.766343 The overhead of memory usage was measured by executing `free` after boot on a QEMU VM with 1GB total memory, and as expected, it's positively correlated with # of cache copies: control 4 copies 8 copies 16 copies total 969.8M 968.2M 968.2M 968.2M used 20.0M 21.9M 24.1M 26.7M free 936.9M 933.6M 931.4M 928.6M available 932.2M 928.8M 926.6M 923.9M Co-developed-by: Xiu Jianfeng <xiujianfeng@huawei.com> Signed-off-by: Xiu Jianfeng <xiujianfeng@huawei.com> Signed-off-by: GONG, Ruiqi <gongruiqi@huaweicloud.com> Reviewed-by: Kees Cook <keescook@chromium.org> Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Acked-by: Dennis Zhou <dennis@kernel.org> # percpu Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
894 lines
24 KiB
C
894 lines
24 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef MM_SLAB_H
|
|
#define MM_SLAB_H
|
|
/*
|
|
* Internal slab definitions
|
|
*/
|
|
void __init kmem_cache_init(void);
|
|
|
|
#ifdef CONFIG_64BIT
|
|
# ifdef system_has_cmpxchg128
|
|
# define system_has_freelist_aba() system_has_cmpxchg128()
|
|
# define try_cmpxchg_freelist try_cmpxchg128
|
|
# endif
|
|
#define this_cpu_try_cmpxchg_freelist this_cpu_try_cmpxchg128
|
|
typedef u128 freelist_full_t;
|
|
#else /* CONFIG_64BIT */
|
|
# ifdef system_has_cmpxchg64
|
|
# define system_has_freelist_aba() system_has_cmpxchg64()
|
|
# define try_cmpxchg_freelist try_cmpxchg64
|
|
# endif
|
|
#define this_cpu_try_cmpxchg_freelist this_cpu_try_cmpxchg64
|
|
typedef u64 freelist_full_t;
|
|
#endif /* CONFIG_64BIT */
|
|
|
|
#if defined(system_has_freelist_aba) && !defined(CONFIG_HAVE_ALIGNED_STRUCT_PAGE)
|
|
#undef system_has_freelist_aba
|
|
#endif
|
|
|
|
/*
|
|
* Freelist pointer and counter to cmpxchg together, avoids the typical ABA
|
|
* problems with cmpxchg of just a pointer.
|
|
*/
|
|
typedef union {
|
|
struct {
|
|
void *freelist;
|
|
unsigned long counter;
|
|
};
|
|
freelist_full_t full;
|
|
} freelist_aba_t;
|
|
|
|
/* Reuses the bits in struct page */
|
|
struct slab {
|
|
unsigned long __page_flags;
|
|
|
|
#if defined(CONFIG_SLAB)
|
|
|
|
struct kmem_cache *slab_cache;
|
|
union {
|
|
struct {
|
|
struct list_head slab_list;
|
|
void *freelist; /* array of free object indexes */
|
|
void *s_mem; /* first object */
|
|
};
|
|
struct rcu_head rcu_head;
|
|
};
|
|
unsigned int active;
|
|
|
|
#elif defined(CONFIG_SLUB)
|
|
|
|
struct kmem_cache *slab_cache;
|
|
union {
|
|
struct {
|
|
union {
|
|
struct list_head slab_list;
|
|
#ifdef CONFIG_SLUB_CPU_PARTIAL
|
|
struct {
|
|
struct slab *next;
|
|
int slabs; /* Nr of slabs left */
|
|
};
|
|
#endif
|
|
};
|
|
/* Double-word boundary */
|
|
union {
|
|
struct {
|
|
void *freelist; /* first free object */
|
|
union {
|
|
unsigned long counters;
|
|
struct {
|
|
unsigned inuse:16;
|
|
unsigned objects:15;
|
|
unsigned frozen:1;
|
|
};
|
|
};
|
|
};
|
|
#ifdef system_has_freelist_aba
|
|
freelist_aba_t freelist_counter;
|
|
#endif
|
|
};
|
|
};
|
|
struct rcu_head rcu_head;
|
|
};
|
|
unsigned int __unused;
|
|
|
|
#else
|
|
#error "Unexpected slab allocator configured"
|
|
#endif
|
|
|
|
atomic_t __page_refcount;
|
|
#ifdef CONFIG_MEMCG
|
|
unsigned long memcg_data;
|
|
#endif
|
|
};
|
|
|
|
#define SLAB_MATCH(pg, sl) \
|
|
static_assert(offsetof(struct page, pg) == offsetof(struct slab, sl))
|
|
SLAB_MATCH(flags, __page_flags);
|
|
SLAB_MATCH(compound_head, slab_cache); /* Ensure bit 0 is clear */
|
|
SLAB_MATCH(_refcount, __page_refcount);
|
|
#ifdef CONFIG_MEMCG
|
|
SLAB_MATCH(memcg_data, memcg_data);
|
|
#endif
|
|
#undef SLAB_MATCH
|
|
static_assert(sizeof(struct slab) <= sizeof(struct page));
|
|
#if defined(system_has_freelist_aba) && defined(CONFIG_SLUB)
|
|
static_assert(IS_ALIGNED(offsetof(struct slab, freelist), sizeof(freelist_aba_t)));
|
|
#endif
|
|
|
|
/**
|
|
* folio_slab - Converts from folio to slab.
|
|
* @folio: The folio.
|
|
*
|
|
* Currently struct slab is a different representation of a folio where
|
|
* folio_test_slab() is true.
|
|
*
|
|
* Return: The slab which contains this folio.
|
|
*/
|
|
#define folio_slab(folio) (_Generic((folio), \
|
|
const struct folio *: (const struct slab *)(folio), \
|
|
struct folio *: (struct slab *)(folio)))
|
|
|
|
/**
|
|
* slab_folio - The folio allocated for a slab
|
|
* @slab: The slab.
|
|
*
|
|
* Slabs are allocated as folios that contain the individual objects and are
|
|
* using some fields in the first struct page of the folio - those fields are
|
|
* now accessed by struct slab. It is occasionally necessary to convert back to
|
|
* a folio in order to communicate with the rest of the mm. Please use this
|
|
* helper function instead of casting yourself, as the implementation may change
|
|
* in the future.
|
|
*/
|
|
#define slab_folio(s) (_Generic((s), \
|
|
const struct slab *: (const struct folio *)s, \
|
|
struct slab *: (struct folio *)s))
|
|
|
|
/**
|
|
* page_slab - Converts from first struct page to slab.
|
|
* @p: The first (either head of compound or single) page of slab.
|
|
*
|
|
* A temporary wrapper to convert struct page to struct slab in situations where
|
|
* we know the page is the compound head, or single order-0 page.
|
|
*
|
|
* Long-term ideally everything would work with struct slab directly or go
|
|
* through folio to struct slab.
|
|
*
|
|
* Return: The slab which contains this page
|
|
*/
|
|
#define page_slab(p) (_Generic((p), \
|
|
const struct page *: (const struct slab *)(p), \
|
|
struct page *: (struct slab *)(p)))
|
|
|
|
/**
|
|
* slab_page - The first struct page allocated for a slab
|
|
* @slab: The slab.
|
|
*
|
|
* A convenience wrapper for converting slab to the first struct page of the
|
|
* underlying folio, to communicate with code not yet converted to folio or
|
|
* struct slab.
|
|
*/
|
|
#define slab_page(s) folio_page(slab_folio(s), 0)
|
|
|
|
/*
|
|
* If network-based swap is enabled, sl*b must keep track of whether pages
|
|
* were allocated from pfmemalloc reserves.
|
|
*/
|
|
static inline bool slab_test_pfmemalloc(const struct slab *slab)
|
|
{
|
|
return folio_test_active((struct folio *)slab_folio(slab));
|
|
}
|
|
|
|
static inline void slab_set_pfmemalloc(struct slab *slab)
|
|
{
|
|
folio_set_active(slab_folio(slab));
|
|
}
|
|
|
|
static inline void slab_clear_pfmemalloc(struct slab *slab)
|
|
{
|
|
folio_clear_active(slab_folio(slab));
|
|
}
|
|
|
|
static inline void __slab_clear_pfmemalloc(struct slab *slab)
|
|
{
|
|
__folio_clear_active(slab_folio(slab));
|
|
}
|
|
|
|
static inline void *slab_address(const struct slab *slab)
|
|
{
|
|
return folio_address(slab_folio(slab));
|
|
}
|
|
|
|
static inline int slab_nid(const struct slab *slab)
|
|
{
|
|
return folio_nid(slab_folio(slab));
|
|
}
|
|
|
|
static inline pg_data_t *slab_pgdat(const struct slab *slab)
|
|
{
|
|
return folio_pgdat(slab_folio(slab));
|
|
}
|
|
|
|
static inline struct slab *virt_to_slab(const void *addr)
|
|
{
|
|
struct folio *folio = virt_to_folio(addr);
|
|
|
|
if (!folio_test_slab(folio))
|
|
return NULL;
|
|
|
|
return folio_slab(folio);
|
|
}
|
|
|
|
static inline int slab_order(const struct slab *slab)
|
|
{
|
|
return folio_order((struct folio *)slab_folio(slab));
|
|
}
|
|
|
|
static inline size_t slab_size(const struct slab *slab)
|
|
{
|
|
return PAGE_SIZE << slab_order(slab);
|
|
}
|
|
|
|
#ifdef CONFIG_SLAB
|
|
#include <linux/slab_def.h>
|
|
#endif
|
|
|
|
#ifdef CONFIG_SLUB
|
|
#include <linux/slub_def.h>
|
|
#endif
|
|
|
|
#include <linux/memcontrol.h>
|
|
#include <linux/fault-inject.h>
|
|
#include <linux/kasan.h>
|
|
#include <linux/kmemleak.h>
|
|
#include <linux/random.h>
|
|
#include <linux/sched/mm.h>
|
|
#include <linux/list_lru.h>
|
|
|
|
/*
|
|
* State of the slab allocator.
|
|
*
|
|
* This is used to describe the states of the allocator during bootup.
|
|
* Allocators use this to gradually bootstrap themselves. Most allocators
|
|
* have the problem that the structures used for managing slab caches are
|
|
* allocated from slab caches themselves.
|
|
*/
|
|
enum slab_state {
|
|
DOWN, /* No slab functionality yet */
|
|
PARTIAL, /* SLUB: kmem_cache_node available */
|
|
PARTIAL_NODE, /* SLAB: kmalloc size for node struct available */
|
|
UP, /* Slab caches usable but not all extras yet */
|
|
FULL /* Everything is working */
|
|
};
|
|
|
|
extern enum slab_state slab_state;
|
|
|
|
/* The slab cache mutex protects the management structures during changes */
|
|
extern struct mutex slab_mutex;
|
|
|
|
/* The list of all slab caches on the system */
|
|
extern struct list_head slab_caches;
|
|
|
|
/* The slab cache that manages slab cache information */
|
|
extern struct kmem_cache *kmem_cache;
|
|
|
|
/* A table of kmalloc cache names and sizes */
|
|
extern const struct kmalloc_info_struct {
|
|
const char *name[NR_KMALLOC_TYPES];
|
|
unsigned int size;
|
|
} kmalloc_info[];
|
|
|
|
/* Kmalloc array related functions */
|
|
void setup_kmalloc_cache_index_table(void);
|
|
void create_kmalloc_caches(slab_flags_t);
|
|
|
|
/* Find the kmalloc slab corresponding for a certain size */
|
|
struct kmem_cache *kmalloc_slab(size_t size, gfp_t flags, unsigned long caller);
|
|
|
|
void *__kmem_cache_alloc_node(struct kmem_cache *s, gfp_t gfpflags,
|
|
int node, size_t orig_size,
|
|
unsigned long caller);
|
|
void __kmem_cache_free(struct kmem_cache *s, void *x, unsigned long caller);
|
|
|
|
gfp_t kmalloc_fix_flags(gfp_t flags);
|
|
|
|
/* Functions provided by the slab allocators */
|
|
int __kmem_cache_create(struct kmem_cache *, slab_flags_t flags);
|
|
|
|
void __init new_kmalloc_cache(int idx, enum kmalloc_cache_type type,
|
|
slab_flags_t flags);
|
|
extern void create_boot_cache(struct kmem_cache *, const char *name,
|
|
unsigned int size, slab_flags_t flags,
|
|
unsigned int useroffset, unsigned int usersize);
|
|
|
|
int slab_unmergeable(struct kmem_cache *s);
|
|
struct kmem_cache *find_mergeable(unsigned size, unsigned align,
|
|
slab_flags_t flags, const char *name, void (*ctor)(void *));
|
|
struct kmem_cache *
|
|
__kmem_cache_alias(const char *name, unsigned int size, unsigned int align,
|
|
slab_flags_t flags, void (*ctor)(void *));
|
|
|
|
slab_flags_t kmem_cache_flags(unsigned int object_size,
|
|
slab_flags_t flags, const char *name);
|
|
|
|
static inline bool is_kmalloc_cache(struct kmem_cache *s)
|
|
{
|
|
return (s->flags & SLAB_KMALLOC);
|
|
}
|
|
|
|
/* Legal flag mask for kmem_cache_create(), for various configurations */
|
|
#define SLAB_CORE_FLAGS (SLAB_HWCACHE_ALIGN | SLAB_CACHE_DMA | \
|
|
SLAB_CACHE_DMA32 | SLAB_PANIC | \
|
|
SLAB_TYPESAFE_BY_RCU | SLAB_DEBUG_OBJECTS )
|
|
|
|
#if defined(CONFIG_DEBUG_SLAB)
|
|
#define SLAB_DEBUG_FLAGS (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER)
|
|
#elif defined(CONFIG_SLUB_DEBUG)
|
|
#define SLAB_DEBUG_FLAGS (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER | \
|
|
SLAB_TRACE | SLAB_CONSISTENCY_CHECKS)
|
|
#else
|
|
#define SLAB_DEBUG_FLAGS (0)
|
|
#endif
|
|
|
|
#if defined(CONFIG_SLAB)
|
|
#define SLAB_CACHE_FLAGS (SLAB_MEM_SPREAD | SLAB_NOLEAKTRACE | \
|
|
SLAB_RECLAIM_ACCOUNT | SLAB_TEMPORARY | \
|
|
SLAB_ACCOUNT | SLAB_NO_MERGE)
|
|
#elif defined(CONFIG_SLUB)
|
|
#define SLAB_CACHE_FLAGS (SLAB_NOLEAKTRACE | SLAB_RECLAIM_ACCOUNT | \
|
|
SLAB_TEMPORARY | SLAB_ACCOUNT | \
|
|
SLAB_NO_USER_FLAGS | SLAB_KMALLOC | SLAB_NO_MERGE)
|
|
#else
|
|
#define SLAB_CACHE_FLAGS (SLAB_NOLEAKTRACE)
|
|
#endif
|
|
|
|
/* Common flags available with current configuration */
|
|
#define CACHE_CREATE_MASK (SLAB_CORE_FLAGS | SLAB_DEBUG_FLAGS | SLAB_CACHE_FLAGS)
|
|
|
|
/* Common flags permitted for kmem_cache_create */
|
|
#define SLAB_FLAGS_PERMITTED (SLAB_CORE_FLAGS | \
|
|
SLAB_RED_ZONE | \
|
|
SLAB_POISON | \
|
|
SLAB_STORE_USER | \
|
|
SLAB_TRACE | \
|
|
SLAB_CONSISTENCY_CHECKS | \
|
|
SLAB_MEM_SPREAD | \
|
|
SLAB_NOLEAKTRACE | \
|
|
SLAB_RECLAIM_ACCOUNT | \
|
|
SLAB_TEMPORARY | \
|
|
SLAB_ACCOUNT | \
|
|
SLAB_KMALLOC | \
|
|
SLAB_NO_MERGE | \
|
|
SLAB_NO_USER_FLAGS)
|
|
|
|
bool __kmem_cache_empty(struct kmem_cache *);
|
|
int __kmem_cache_shutdown(struct kmem_cache *);
|
|
void __kmem_cache_release(struct kmem_cache *);
|
|
int __kmem_cache_shrink(struct kmem_cache *);
|
|
void slab_kmem_cache_release(struct kmem_cache *);
|
|
|
|
struct seq_file;
|
|
struct file;
|
|
|
|
struct slabinfo {
|
|
unsigned long active_objs;
|
|
unsigned long num_objs;
|
|
unsigned long active_slabs;
|
|
unsigned long num_slabs;
|
|
unsigned long shared_avail;
|
|
unsigned int limit;
|
|
unsigned int batchcount;
|
|
unsigned int shared;
|
|
unsigned int objects_per_slab;
|
|
unsigned int cache_order;
|
|
};
|
|
|
|
void get_slabinfo(struct kmem_cache *s, struct slabinfo *sinfo);
|
|
void slabinfo_show_stats(struct seq_file *m, struct kmem_cache *s);
|
|
ssize_t slabinfo_write(struct file *file, const char __user *buffer,
|
|
size_t count, loff_t *ppos);
|
|
|
|
static inline enum node_stat_item cache_vmstat_idx(struct kmem_cache *s)
|
|
{
|
|
return (s->flags & SLAB_RECLAIM_ACCOUNT) ?
|
|
NR_SLAB_RECLAIMABLE_B : NR_SLAB_UNRECLAIMABLE_B;
|
|
}
|
|
|
|
#ifdef CONFIG_SLUB_DEBUG
|
|
#ifdef CONFIG_SLUB_DEBUG_ON
|
|
DECLARE_STATIC_KEY_TRUE(slub_debug_enabled);
|
|
#else
|
|
DECLARE_STATIC_KEY_FALSE(slub_debug_enabled);
|
|
#endif
|
|
extern void print_tracking(struct kmem_cache *s, void *object);
|
|
long validate_slab_cache(struct kmem_cache *s);
|
|
static inline bool __slub_debug_enabled(void)
|
|
{
|
|
return static_branch_unlikely(&slub_debug_enabled);
|
|
}
|
|
#else
|
|
static inline void print_tracking(struct kmem_cache *s, void *object)
|
|
{
|
|
}
|
|
static inline bool __slub_debug_enabled(void)
|
|
{
|
|
return false;
|
|
}
|
|
#endif
|
|
|
|
/*
|
|
* Returns true if any of the specified slub_debug flags is enabled for the
|
|
* cache. Use only for flags parsed by setup_slub_debug() as it also enables
|
|
* the static key.
|
|
*/
|
|
static inline bool kmem_cache_debug_flags(struct kmem_cache *s, slab_flags_t flags)
|
|
{
|
|
if (IS_ENABLED(CONFIG_SLUB_DEBUG))
|
|
VM_WARN_ON_ONCE(!(flags & SLAB_DEBUG_FLAGS));
|
|
if (__slub_debug_enabled())
|
|
return s->flags & flags;
|
|
return false;
|
|
}
|
|
|
|
#ifdef CONFIG_MEMCG_KMEM
|
|
/*
|
|
* slab_objcgs - get the object cgroups vector associated with a slab
|
|
* @slab: a pointer to the slab struct
|
|
*
|
|
* Returns a pointer to the object cgroups vector associated with the slab,
|
|
* or NULL if no such vector has been associated yet.
|
|
*/
|
|
static inline struct obj_cgroup **slab_objcgs(struct slab *slab)
|
|
{
|
|
unsigned long memcg_data = READ_ONCE(slab->memcg_data);
|
|
|
|
VM_BUG_ON_PAGE(memcg_data && !(memcg_data & MEMCG_DATA_OBJCGS),
|
|
slab_page(slab));
|
|
VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_KMEM, slab_page(slab));
|
|
|
|
return (struct obj_cgroup **)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
|
|
}
|
|
|
|
int memcg_alloc_slab_cgroups(struct slab *slab, struct kmem_cache *s,
|
|
gfp_t gfp, bool new_slab);
|
|
void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat,
|
|
enum node_stat_item idx, int nr);
|
|
|
|
static inline void memcg_free_slab_cgroups(struct slab *slab)
|
|
{
|
|
kfree(slab_objcgs(slab));
|
|
slab->memcg_data = 0;
|
|
}
|
|
|
|
static inline size_t obj_full_size(struct kmem_cache *s)
|
|
{
|
|
/*
|
|
* For each accounted object there is an extra space which is used
|
|
* to store obj_cgroup membership. Charge it too.
|
|
*/
|
|
return s->size + sizeof(struct obj_cgroup *);
|
|
}
|
|
|
|
/*
|
|
* Returns false if the allocation should fail.
|
|
*/
|
|
static inline bool memcg_slab_pre_alloc_hook(struct kmem_cache *s,
|
|
struct list_lru *lru,
|
|
struct obj_cgroup **objcgp,
|
|
size_t objects, gfp_t flags)
|
|
{
|
|
struct obj_cgroup *objcg;
|
|
|
|
if (!memcg_kmem_online())
|
|
return true;
|
|
|
|
if (!(flags & __GFP_ACCOUNT) && !(s->flags & SLAB_ACCOUNT))
|
|
return true;
|
|
|
|
objcg = get_obj_cgroup_from_current();
|
|
if (!objcg)
|
|
return true;
|
|
|
|
if (lru) {
|
|
int ret;
|
|
struct mem_cgroup *memcg;
|
|
|
|
memcg = get_mem_cgroup_from_objcg(objcg);
|
|
ret = memcg_list_lru_alloc(memcg, lru, flags);
|
|
css_put(&memcg->css);
|
|
|
|
if (ret)
|
|
goto out;
|
|
}
|
|
|
|
if (obj_cgroup_charge(objcg, flags, objects * obj_full_size(s)))
|
|
goto out;
|
|
|
|
*objcgp = objcg;
|
|
return true;
|
|
out:
|
|
obj_cgroup_put(objcg);
|
|
return false;
|
|
}
|
|
|
|
static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
|
|
struct obj_cgroup *objcg,
|
|
gfp_t flags, size_t size,
|
|
void **p)
|
|
{
|
|
struct slab *slab;
|
|
unsigned long off;
|
|
size_t i;
|
|
|
|
if (!memcg_kmem_online() || !objcg)
|
|
return;
|
|
|
|
for (i = 0; i < size; i++) {
|
|
if (likely(p[i])) {
|
|
slab = virt_to_slab(p[i]);
|
|
|
|
if (!slab_objcgs(slab) &&
|
|
memcg_alloc_slab_cgroups(slab, s, flags,
|
|
false)) {
|
|
obj_cgroup_uncharge(objcg, obj_full_size(s));
|
|
continue;
|
|
}
|
|
|
|
off = obj_to_index(s, slab, p[i]);
|
|
obj_cgroup_get(objcg);
|
|
slab_objcgs(slab)[off] = objcg;
|
|
mod_objcg_state(objcg, slab_pgdat(slab),
|
|
cache_vmstat_idx(s), obj_full_size(s));
|
|
} else {
|
|
obj_cgroup_uncharge(objcg, obj_full_size(s));
|
|
}
|
|
}
|
|
obj_cgroup_put(objcg);
|
|
}
|
|
|
|
static inline void memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab,
|
|
void **p, int objects)
|
|
{
|
|
struct obj_cgroup **objcgs;
|
|
int i;
|
|
|
|
if (!memcg_kmem_online())
|
|
return;
|
|
|
|
objcgs = slab_objcgs(slab);
|
|
if (!objcgs)
|
|
return;
|
|
|
|
for (i = 0; i < objects; i++) {
|
|
struct obj_cgroup *objcg;
|
|
unsigned int off;
|
|
|
|
off = obj_to_index(s, slab, p[i]);
|
|
objcg = objcgs[off];
|
|
if (!objcg)
|
|
continue;
|
|
|
|
objcgs[off] = NULL;
|
|
obj_cgroup_uncharge(objcg, obj_full_size(s));
|
|
mod_objcg_state(objcg, slab_pgdat(slab), cache_vmstat_idx(s),
|
|
-obj_full_size(s));
|
|
obj_cgroup_put(objcg);
|
|
}
|
|
}
|
|
|
|
#else /* CONFIG_MEMCG_KMEM */
|
|
static inline struct obj_cgroup **slab_objcgs(struct slab *slab)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static inline struct mem_cgroup *memcg_from_slab_obj(void *ptr)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static inline int memcg_alloc_slab_cgroups(struct slab *slab,
|
|
struct kmem_cache *s, gfp_t gfp,
|
|
bool new_slab)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void memcg_free_slab_cgroups(struct slab *slab)
|
|
{
|
|
}
|
|
|
|
static inline bool memcg_slab_pre_alloc_hook(struct kmem_cache *s,
|
|
struct list_lru *lru,
|
|
struct obj_cgroup **objcgp,
|
|
size_t objects, gfp_t flags)
|
|
{
|
|
return true;
|
|
}
|
|
|
|
static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
|
|
struct obj_cgroup *objcg,
|
|
gfp_t flags, size_t size,
|
|
void **p)
|
|
{
|
|
}
|
|
|
|
static inline void memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab,
|
|
void **p, int objects)
|
|
{
|
|
}
|
|
#endif /* CONFIG_MEMCG_KMEM */
|
|
|
|
static inline struct kmem_cache *virt_to_cache(const void *obj)
|
|
{
|
|
struct slab *slab;
|
|
|
|
slab = virt_to_slab(obj);
|
|
if (WARN_ONCE(!slab, "%s: Object is not a Slab page!\n",
|
|
__func__))
|
|
return NULL;
|
|
return slab->slab_cache;
|
|
}
|
|
|
|
static __always_inline void account_slab(struct slab *slab, int order,
|
|
struct kmem_cache *s, gfp_t gfp)
|
|
{
|
|
if (memcg_kmem_online() && (s->flags & SLAB_ACCOUNT))
|
|
memcg_alloc_slab_cgroups(slab, s, gfp, true);
|
|
|
|
mod_node_page_state(slab_pgdat(slab), cache_vmstat_idx(s),
|
|
PAGE_SIZE << order);
|
|
}
|
|
|
|
static __always_inline void unaccount_slab(struct slab *slab, int order,
|
|
struct kmem_cache *s)
|
|
{
|
|
if (memcg_kmem_online())
|
|
memcg_free_slab_cgroups(slab);
|
|
|
|
mod_node_page_state(slab_pgdat(slab), cache_vmstat_idx(s),
|
|
-(PAGE_SIZE << order));
|
|
}
|
|
|
|
static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x)
|
|
{
|
|
struct kmem_cache *cachep;
|
|
|
|
if (!IS_ENABLED(CONFIG_SLAB_FREELIST_HARDENED) &&
|
|
!kmem_cache_debug_flags(s, SLAB_CONSISTENCY_CHECKS))
|
|
return s;
|
|
|
|
cachep = virt_to_cache(x);
|
|
if (WARN(cachep && cachep != s,
|
|
"%s: Wrong slab cache. %s but object is from %s\n",
|
|
__func__, s->name, cachep->name))
|
|
print_tracking(cachep, x);
|
|
return cachep;
|
|
}
|
|
|
|
void free_large_kmalloc(struct folio *folio, void *object);
|
|
|
|
size_t __ksize(const void *objp);
|
|
|
|
static inline size_t slab_ksize(const struct kmem_cache *s)
|
|
{
|
|
#ifndef CONFIG_SLUB
|
|
return s->object_size;
|
|
|
|
#else /* CONFIG_SLUB */
|
|
# ifdef CONFIG_SLUB_DEBUG
|
|
/*
|
|
* Debugging requires use of the padding between object
|
|
* and whatever may come after it.
|
|
*/
|
|
if (s->flags & (SLAB_RED_ZONE | SLAB_POISON))
|
|
return s->object_size;
|
|
# endif
|
|
if (s->flags & SLAB_KASAN)
|
|
return s->object_size;
|
|
/*
|
|
* If we have the need to store the freelist pointer
|
|
* back there or track user information then we can
|
|
* only use the space before that information.
|
|
*/
|
|
if (s->flags & (SLAB_TYPESAFE_BY_RCU | SLAB_STORE_USER))
|
|
return s->inuse;
|
|
/*
|
|
* Else we can use all the padding etc for the allocation
|
|
*/
|
|
return s->size;
|
|
#endif
|
|
}
|
|
|
|
static inline struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s,
|
|
struct list_lru *lru,
|
|
struct obj_cgroup **objcgp,
|
|
size_t size, gfp_t flags)
|
|
{
|
|
flags &= gfp_allowed_mask;
|
|
|
|
might_alloc(flags);
|
|
|
|
if (should_failslab(s, flags))
|
|
return NULL;
|
|
|
|
if (!memcg_slab_pre_alloc_hook(s, lru, objcgp, size, flags))
|
|
return NULL;
|
|
|
|
return s;
|
|
}
|
|
|
|
static inline void slab_post_alloc_hook(struct kmem_cache *s,
|
|
struct obj_cgroup *objcg, gfp_t flags,
|
|
size_t size, void **p, bool init,
|
|
unsigned int orig_size)
|
|
{
|
|
unsigned int zero_size = s->object_size;
|
|
bool kasan_init = init;
|
|
size_t i;
|
|
|
|
flags &= gfp_allowed_mask;
|
|
|
|
/*
|
|
* For kmalloc object, the allocated memory size(object_size) is likely
|
|
* larger than the requested size(orig_size). If redzone check is
|
|
* enabled for the extra space, don't zero it, as it will be redzoned
|
|
* soon. The redzone operation for this extra space could be seen as a
|
|
* replacement of current poisoning under certain debug option, and
|
|
* won't break other sanity checks.
|
|
*/
|
|
if (kmem_cache_debug_flags(s, SLAB_STORE_USER | SLAB_RED_ZONE) &&
|
|
(s->flags & SLAB_KMALLOC))
|
|
zero_size = orig_size;
|
|
|
|
/*
|
|
* When slub_debug is enabled, avoid memory initialization integrated
|
|
* into KASAN and instead zero out the memory via the memset below with
|
|
* the proper size. Otherwise, KASAN might overwrite SLUB redzones and
|
|
* cause false-positive reports. This does not lead to a performance
|
|
* penalty on production builds, as slub_debug is not intended to be
|
|
* enabled there.
|
|
*/
|
|
if (__slub_debug_enabled())
|
|
kasan_init = false;
|
|
|
|
/*
|
|
* As memory initialization might be integrated into KASAN,
|
|
* kasan_slab_alloc and initialization memset must be
|
|
* kept together to avoid discrepancies in behavior.
|
|
*
|
|
* As p[i] might get tagged, memset and kmemleak hook come after KASAN.
|
|
*/
|
|
for (i = 0; i < size; i++) {
|
|
p[i] = kasan_slab_alloc(s, p[i], flags, kasan_init);
|
|
if (p[i] && init && (!kasan_init || !kasan_has_integrated_init()))
|
|
memset(p[i], 0, zero_size);
|
|
kmemleak_alloc_recursive(p[i], s->object_size, 1,
|
|
s->flags, flags);
|
|
kmsan_slab_alloc(s, p[i], flags);
|
|
}
|
|
|
|
memcg_slab_post_alloc_hook(s, objcg, flags, size, p);
|
|
}
|
|
|
|
/*
|
|
* The slab lists for all objects.
|
|
*/
|
|
struct kmem_cache_node {
|
|
#ifdef CONFIG_SLAB
|
|
raw_spinlock_t list_lock;
|
|
struct list_head slabs_partial; /* partial list first, better asm code */
|
|
struct list_head slabs_full;
|
|
struct list_head slabs_free;
|
|
unsigned long total_slabs; /* length of all slab lists */
|
|
unsigned long free_slabs; /* length of free slab list only */
|
|
unsigned long free_objects;
|
|
unsigned int free_limit;
|
|
unsigned int colour_next; /* Per-node cache coloring */
|
|
struct array_cache *shared; /* shared per node */
|
|
struct alien_cache **alien; /* on other nodes */
|
|
unsigned long next_reap; /* updated without locking */
|
|
int free_touched; /* updated without locking */
|
|
#endif
|
|
|
|
#ifdef CONFIG_SLUB
|
|
spinlock_t list_lock;
|
|
unsigned long nr_partial;
|
|
struct list_head partial;
|
|
#ifdef CONFIG_SLUB_DEBUG
|
|
atomic_long_t nr_slabs;
|
|
atomic_long_t total_objects;
|
|
struct list_head full;
|
|
#endif
|
|
#endif
|
|
|
|
};
|
|
|
|
static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node)
|
|
{
|
|
return s->node[node];
|
|
}
|
|
|
|
/*
|
|
* Iterator over all nodes. The body will be executed for each node that has
|
|
* a kmem_cache_node structure allocated (which is true for all online nodes)
|
|
*/
|
|
#define for_each_kmem_cache_node(__s, __node, __n) \
|
|
for (__node = 0; __node < nr_node_ids; __node++) \
|
|
if ((__n = get_node(__s, __node)))
|
|
|
|
|
|
#if defined(CONFIG_SLAB) || defined(CONFIG_SLUB_DEBUG)
|
|
void dump_unreclaimable_slab(void);
|
|
#else
|
|
static inline void dump_unreclaimable_slab(void)
|
|
{
|
|
}
|
|
#endif
|
|
|
|
void ___cache_free(struct kmem_cache *cache, void *x, unsigned long addr);
|
|
|
|
#ifdef CONFIG_SLAB_FREELIST_RANDOM
|
|
int cache_random_seq_create(struct kmem_cache *cachep, unsigned int count,
|
|
gfp_t gfp);
|
|
void cache_random_seq_destroy(struct kmem_cache *cachep);
|
|
#else
|
|
static inline int cache_random_seq_create(struct kmem_cache *cachep,
|
|
unsigned int count, gfp_t gfp)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline void cache_random_seq_destroy(struct kmem_cache *cachep) { }
|
|
#endif /* CONFIG_SLAB_FREELIST_RANDOM */
|
|
|
|
static inline bool slab_want_init_on_alloc(gfp_t flags, struct kmem_cache *c)
|
|
{
|
|
if (static_branch_maybe(CONFIG_INIT_ON_ALLOC_DEFAULT_ON,
|
|
&init_on_alloc)) {
|
|
if (c->ctor)
|
|
return false;
|
|
if (c->flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON))
|
|
return flags & __GFP_ZERO;
|
|
return true;
|
|
}
|
|
return flags & __GFP_ZERO;
|
|
}
|
|
|
|
static inline bool slab_want_init_on_free(struct kmem_cache *c)
|
|
{
|
|
if (static_branch_maybe(CONFIG_INIT_ON_FREE_DEFAULT_ON,
|
|
&init_on_free))
|
|
return !(c->ctor ||
|
|
(c->flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON)));
|
|
return false;
|
|
}
|
|
|
|
#if defined(CONFIG_DEBUG_FS) && defined(CONFIG_SLUB_DEBUG)
|
|
void debugfs_slab_release(struct kmem_cache *);
|
|
#else
|
|
static inline void debugfs_slab_release(struct kmem_cache *s) { }
|
|
#endif
|
|
|
|
#ifdef CONFIG_PRINTK
|
|
#define KS_ADDRS_COUNT 16
|
|
struct kmem_obj_info {
|
|
void *kp_ptr;
|
|
struct slab *kp_slab;
|
|
void *kp_objp;
|
|
unsigned long kp_data_offset;
|
|
struct kmem_cache *kp_slab_cache;
|
|
void *kp_ret;
|
|
void *kp_stack[KS_ADDRS_COUNT];
|
|
void *kp_free_stack[KS_ADDRS_COUNT];
|
|
};
|
|
void __kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab);
|
|
#endif
|
|
|
|
void __check_heap_object(const void *ptr, unsigned long n,
|
|
const struct slab *slab, bool to_user);
|
|
|
|
#ifdef CONFIG_SLUB_DEBUG
|
|
void skip_orig_size_check(struct kmem_cache *s, const void *object);
|
|
#endif
|
|
|
|
#endif /* MM_SLAB_H */
|