// SPDX-License-Identifier: GPL-2.0
/*
* SLUB: A slab allocator that limits cache line use instead of queuing
* objects in per cpu and per node lists.
*
* The allocator synchronizes using per slab locks or atomic operations
* and only uses a centralized lock to manage a pool of partial slabs.
*
* (C) 2007 SGI, Christoph Lameter
* (C) 2011 Linux Foundation, Christoph Lameter
*/
#include <linux/mm.h>
#include <linux/swap.h> /* mm_account_reclaimed_pages() */
#include <linux/module.h>
#include <linux/bit_spinlock.h>
#include <linux/interrupt.h>
#include <linux/swab.h>
#include <linux/bitops.h>
#include <linux/slab.h>
#include "slab.h"
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/kasan.h>
#include <linux/kmsan.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
#include <linux/mempolicy.h>
#include <linux/ctype.h>
#include <linux/stackdepot.h>
#include <linux/debugobjects.h>
#include <linux/kallsyms.h>
#include <linux/kfence.h>
#include <linux/memory.h>
#include <linux/math64.h>
#include <linux/fault-inject.h>
#include <linux/stacktrace.h>
#include <linux/prefetch.h>
#include <linux/memcontrol.h>
#include <linux/random.h>
#include <kunit/test.h>
#include <kunit/test-bug.h>
#include <linux/sort.h>
#include <linux/debugfs.h>
#include <trace/events/kmem.h>
#include "internal.h"
/*
* Lock order:
* 1. slab_mutex (Global Mutex)
* 2. node->list_lock (Spinlock)
* 3. kmem_cache->cpu_slab->lock (Local lock)
* 4. slab_lock(slab) (Only on some arches)
* 5. object_map_lock (Only for debugging)
*
* slab_mutex
*
* The role of the slab_mutex is to protect the list of all the slabs
* and to synchronize major metadata changes to slab cache structures.
* Also synchronizes memory hotplug callbacks.
*
* slab_lock
*
* The slab_lock is a wrapper around the page lock, thus it is a bit
* spinlock.
*
* The slab_lock is only used on arches that do not have the ability
* to do a cmpxchg_double. It only protects:
*
* A. slab->freelist -> List of free objects in a slab
* B. slab->inuse -> Number of objects in use
* C. slab->objects -> Number of objects in slab
* D. slab->frozen -> frozen state
*
* Frozen slabs
*
* If a slab is frozen then it is exempt from list management. It is not
* on any list except per cpu partial list. The processor that froze the
* slab is the one who can perform list operations on the slab. Other
* processors may put objects onto the freelist but the processor that
* froze the slab is the only one that can retrieve the objects from the
* slab's freelist.
*
* list_lock
*
* The list_lock protects the partial and full list on each node and
* the partial slab counter. If taken then no new slabs may be added or
* removed from the lists nor make the number of partial slabs be modified.
* (Note that the total number of slabs is an atomic value that may be
* modified without taking the list lock).
*
* The list_lock is a centralized lock and thus we avoid taking it as
* much as possible. As long as SLUB does not have to handle partial
* slabs, operations can continue without any centralized lock. F.e.
* allocating a long series of objects that fill up slabs does not require
* the list lock.
*
* For debug caches, all allocations are forced to go through a list_lock
* protected region to serialize against concurrent validation.
*
* cpu_slab->lock local lock
*
* This locks protect slowpath manipulation of all kmem_cache_cpu fields
* except the stat counters. This is a percpu structure manipulated only by
* the local cpu, so the lock protects against being preempted or interrupted
* by an irq. Fast path operations rely on lockless operations instead.
*
* On PREEMPT_RT, the local lock neither disables interrupts nor preemption
* which means the lockless fastpath cannot be used as it might interfere with
* an in-progress slow path operations. In this case the local lock is always
* taken but it still utilizes the freelist for the common operations.
*
* lockless fastpaths
*
* The fast path allocation (slab_alloc_node()) and freeing (do_slab_free())
* are fully lockless when satisfied from the percpu slab (and when
* cmpxchg_double is possible to use, otherwise slab_lock is taken).
* They also don't disable preemption or migration or irqs. They rely on
* the transaction id (tid) field to detect being preempted or moved to
* another cpu.
*
* irq, preemption, migration considerations
*
* Interrupts are disabled as part of list_lock or local_lock operations, or
* around the slab_lock operation, in order to make the slab allocator safe
* to use in the context of an irq.
*
* In addition, preemption (or migration on PREEMPT_RT) is disabled in the
* allocation slowpath, bulk allocation, and put_cpu_partial(), so that the
* local cpu doesn't change in the process and e.g. the kmem_cache_cpu pointer
* doesn't have to be revalidated in each section protected by the local lock.
*
* SLUB assigns one slab for allocation to each processor.
* Allocations only occur from these slabs called cpu slabs.
*
* Slabs with free elements are kept on a partial list and during regular
* operations no list for full slabs is used. If an object in a full slab is
* freed then the slab will show up again on the partial lists.
* We track full slabs for debugging purposes though because otherwise we
* cannot scan all objects.
*
* Slabs are freed when they become empty. Teardown and setup is
* minimal so we rely on the page allocators per cpu caches for
* fast frees and allocs.
*
* slab->frozen The slab is frozen and exempt from list processing.
* This means that the slab is dedicated to a purpose
* such as satisfying allocations for a specific
* processor. Objects may be freed in the slab while
* it is frozen but slab_free will then skip the usual
* list operations. It is up to the processor holding
* the slab to integrate the slab into the slab lists
* when the slab is no longer needed.
*
* One use of this flag is to mark slabs that are
* used for allocations. Then such a slab becomes a cpu
* slab. The cpu slab may be equipped with an additional
* freelist that allows lockless access to
* free objects in addition to the regular freelist
* that requires the slab lock.
*
* SLAB_DEBUG_FLAGS Slab requires special handling due to debug
* options set. This moves slab handling out of
* the fast path and disables lockless freelists.
*/
/*
* We could simply use migrate_disable()/enable() but as long as it's a
* function call even on !PREEMPT_RT, use inline preempt_disable() there.
*/
#ifndef CONFIG_PREEMPT_RT
#define slub_get_cpu_ptr(var) get_cpu_ptr(var)
#define slub_put_cpu_ptr(var) put_cpu_ptr(var)
#define USE_LOCKLESS_FAST_PATH() (true)
#else
#define slub_get_cpu_ptr(var) \
({ \
migrate_disable(); \
this_cpu_ptr(var); \
})
#define slub_put_cpu_ptr(var) \
do { \
(void)(var); \
migrate_enable(); \
} while (0)
#define USE_LOCKLESS_FAST_PATH() (false)
#endif
#ifndef CONFIG_SLUB_TINY
#define __fastpath_inline __always_inline
#else
#define __fastpath_inline
#endif
#ifdef CONFIG_SLUB_DEBUG
#ifdef CONFIG_SLUB_DEBUG_ON
DEFINE_STATIC_KEY_TRUE(slub_debug_enabled);
#else
DEFINE_STATIC_KEY_FALSE(slub_debug_enabled);
#endif
#endif /* CONFIG_SLUB_DEBUG */
/* Structure holding parameters for get_partial() call chain */
struct partial_context {
struct slab **slab;
gfp_t flags;
unsigned int orig_size;
};
static inline bool kmem_cache_debug(struct kmem_cache *s)
{
return kmem_cache_debug_flags(s, SLAB_DEBUG_FLAGS);
}
static inline bool slub_debug_orig_size(struct kmem_cache *s)
{
return (kmem_cache_debug_flags(s, SLAB_STORE_USER) &&
(s->flags & SLAB_KMALLOC));
}
void *fixup_red_left(struct kmem_cache *s, void *p)
{
if (kmem_cache_debug_flags(s, SLAB_RED_ZONE))
p += s->red_left_pad;
return p;
}
static inline bool kmem_cache_has_cpu_partial(struct kmem_cache *s)
{
#ifdef CONFIG_SLUB_CPU_PARTIAL
return !kmem_cache_debug(s);
#else
return false;
#endif
}
/*
* Issues still to be resolved:
*
* - Support PAGE_ALLOC_DEBUG. Should be easy to do.
*
* - Variable sizing of the per node arrays
*/
/* Enable to log cmpxchg failures */
#undef SLUB_DEBUG_CMPXCHG
#ifndef CONFIG_SLUB_TINY
/*
* Minimum number of partial slabs. These will be left on the partial
* lists even if they are empty. kmem_cache_shrink may reclaim them.
*/
#define MIN_PARTIAL 5
/*
* Maximum number of desirable partial slabs.
* The existence of more partial slabs makes kmem_cache_shrink
* sort the partial list by the number of objects in use.
*/
#define MAX_PARTIAL 10
#else
#define MIN_PARTIAL 0
#define MAX_PARTIAL 0
#endif
#define DEBUG_DEFAULT_FLAGS (SLAB_CONSISTENCY_CHECKS | SLAB_RED_ZONE | \
SLAB_POISON | SLAB_STORE_USER)
/*
* These debug flags cannot use CMPXCHG because there might be consistency
* issues when checking or reading debug information
*/
#define SLAB_NO_CMPXCHG (SLAB_CONSISTENCY_CHECKS | SLAB_STORE_USER | \
SLAB_TRACE)
/*
* Debugging flags that require metadata to be stored in the slab. These get
* disabled when slub_debug=O is used and a cache's min order increases with
* metadata.
*/
#define DEBUG_METADATA_FLAGS (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER)
#define OO_SHIFT 16
#define OO_MASK ((1 << OO_SHIFT) - 1)
#define MAX_OBJS_PER_PAGE 32767 /* since slab.objects is u15 */
/* Internal SLUB flags */
/* Poison object */
#define __OBJECT_POISON ((slab_flags_t __force)0x80000000U)
/* Use cmpxchg_double */
#ifdef system_has_freelist_aba
#define __CMPXCHG_DOUBLE ((slab_flags_t __force)0x40000000U)
#else
#define __CMPXCHG_DOUBLE ((slab_flags_t __force)0U)
#endif
/*
* Tracking user of a slab.
*/
#define TRACK_ADDRS_COUNT 16
struct track {
unsigned long addr; /* Called from address */
#ifdef CONFIG_STACKDEPOT
depot_stack_handle_t handle;
#endif
int cpu; /* Was running on cpu */
int pid; /* Pid context */
unsigned long when; /* When did the operation occur */
};
enum track_item { TRACK_ALLOC, TRACK_FREE };
#ifdef SLAB_SUPPORTS_SYSFS
static int sysfs_slab_add(struct kmem_cache *);
static int sysfs_slab_alias(struct kmem_cache *, const char *);
#else
static inline int sysfs_slab_add(struct kmem_cache *s) { return 0; }
static inline int sysfs_slab_alias(struct kmem_cache *s, const char *p)
{ return 0; }
#endif
#if defined(CONFIG_DEBUG_FS) && defined(CONFIG_SLUB_DEBUG)
static void debugfs_slab_add(struct kmem_cache *);
#else
static inline void debugfs_slab_add(struct kmem_cache *s) { }
#endif
static inline void stat(const struct kmem_cache *s, enum stat_item si)
{
#ifdef CONFIG_SLUB_STATS
/*
* The rmw is racy on a preemptible kernel but this is acceptable, so
* avoid this_cpu_add()'s irq-disable overhead.
*/
raw_cpu_inc(s->cpu_slab->stat[si]);
#endif
}
/*
* Tracks for which NUMA nodes we have kmem_cache_nodes allocated.
* Corresponds to node_state[N_NORMAL_MEMORY], but can temporarily
* differ during memory hotplug/hotremove operations.
* Protected by slab_mutex.
*/
static nodemask_t slab_nodes;
#ifndef CONFIG_SLUB_TINY
/*
* Workqueue used for flush_cpu_slab().
*/
static struct workqueue_struct *flushwq;
#endif
/********************************************************************
* Core slab cache functions
*******************************************************************/
/*
* Returns freelist pointer (ptr). With hardening, this is obfuscated
* with an XOR of the address where the pointer is held and a per-cache
* random number.
*/
static inline void *freelist_ptr(const struct kmem_cache *s, void *ptr,
unsigned long ptr_addr)
{
#ifdef CONFIG_SLAB_FREELIST_HARDENED
/*
* When CONFIG_KASAN_SW/HW_TAGS is enabled, ptr_addr might be tagged.
* Normally, this doesn't cause any issues, as both set_freepointer()
* and get_freepointer() are called with a pointer with the same tag.
* However, there are some issues with CONFIG_SLUB_DEBUG code. For
* example, when __free_slub() iterates over objects in a cache, it
* passes untagged pointers to check_object(). check_object() in turns
* calls get_freepointer() with an untagged pointer, which causes the
* freepointer to be restored incorrectly.
*/
return (void *)((unsigned long)ptr ^ s->random ^
swab((unsigned long)kasan_reset_tag((void *)ptr_addr)));
#else
return ptr;
#endif
}
/* Returns the freelist pointer recorded at location ptr_addr. */
static inline void *freelist_dereference(const struct kmem_cache *s,
void *ptr_addr)
{
return freelist_ptr(s, (void *)*(unsigned long *)(ptr_addr),
(unsigned long)ptr_addr);
}
static inline void *get_freepointer(struct kmem_cache *s, void *object)
{
object = kasan_reset_tag(object);
return freelist_dereference(s, object + s->offset);
}
#ifndef CONFIG_SLUB_TINY
static void prefetch_freepointer(const struct kmem_cache *s, void *object)
{
prefetchw(object + s->offset);
}
#endif
/*
* When running under KMSAN, get_freepointer_safe() may return an uninitialized
* pointer value in the case the current thread loses the race for the next
* memory chunk in the freelist. In that case this_cpu_cmpxchg_double() in
* slab_alloc_node() will fail, so the uninitialized value won't be used, but
* KMSAN will still check all arguments of cmpxchg because of imperfect
* handling of inline assembly.
* To work around this problem, we apply __no_kmsan_checks to ensure that
* get_freepointer_safe() returns initialized memory.
*/
__no_kmsan_checks
static inline void *get_freepointer_safe(struct kmem_cache *s, void *object)
{
unsigned long freepointer_addr;
void *p;
if (!debug_pagealloc_enabled_static())
return get_freepointer(s, object);
object = kasan_reset_tag(object);
freepointer_addr = (unsigned long)object + s->offset;
copy_from_kernel_nofault(&p, (void **)freepointer_addr, sizeof(p));
return freelist_ptr(s, p, freepointer_addr);
}
static inline void set_freepointer(struct kmem_cache *s, void *object, void *fp)
{
unsigned long freeptr_addr = (unsigned long)object + s->offset;
#ifdef CONFIG_SLAB_FREELIST_HARDENED
BUG_ON(object == fp); /* naive detection of double free or corruption */
#endif
freeptr_addr = (unsigned long)kasan_reset_tag((void *)freeptr_addr);
*(void **)freeptr_addr = freelist_ptr(s, fp, freeptr_addr);
}
/* Loop over all objects in a slab */
#define for_each_object(__p, __s, __addr, __objects) \
for (__p = fixup_red_left(__s, __addr); \
__p < (__addr) + (__objects) * (__s)->size; \
__p += (__s)->size)
static inline unsigned int order_objects(unsigned int order, unsigned int size)
{
return ((unsigned int)PAGE_SIZE << order) / size;
}
static inline struct kmem_cache_order_objects oo_make(unsigned int order,
unsigned int size)
{
struct kmem_cache_order_objects x = {
(order << OO_SHIFT) + order_objects(order, size)
};
return x;
}
static inline unsigned int oo_order(struct kmem_cache_order_objects x)
{
return x.x >> OO_SHIFT;
}
static inline unsigned int oo_objects(struct kmem_cache_order_objects x)
{
return x.x & OO_MASK;
}
#ifdef CONFIG_SLUB_CPU_PARTIAL
static void slub_set_cpu_partial(struct kmem_cache *s, unsigned int nr_objects)
{
unsigned int nr_slabs;
s->cpu_partial = nr_objects;
/*
* We take the number of objects but actually limit the number of
* slabs on the per cpu partial list, in order to limit excessive
* growth of the list. For simplicity we assume that the slabs will
* be half-full.
*/
nr_slabs = DIV_ROUND_UP(nr_objects * 2, oo_objects(s->oo));
s->cpu_partial_slabs = nr_slabs;
}
#else
static inline void
slub_set_cpu_partial(struct kmem_cache *s, unsigned int nr_objects)
{
}
#endif /* CONFIG_SLUB_CPU_PARTIAL */
/*
* Per slab locking using the pagelock
*/
static __always_inline void slab_lock(struct slab *slab)
{
struct page *page = slab_page(slab);
VM_BUG_ON_PAGE(PageTail(page), page);
bit_spin_lock(PG_locked, &page->flags);
}
static __always_inline void slab_unlock(struct slab *slab)
{
struct page *page = slab_page(slab);
VM_BUG_ON_PAGE(PageTail(page), page);
__bit_spin_unlock(PG_locked, &page->flags);
}
static inline bool
__update_freelist_fast(struct slab *slab,
void *freelist_old, unsigned long counters_old,
void *freelist_new, unsigned long counters_new)
{
#ifdef system_has_freelist_aba
freelist_aba_t old = { .freelist = freelist_old, .counter = counters_old };
freelist_aba_t new = { .freelist = freelist_new, .counter = counters_new };
return try_cmpxchg_freelist(&slab->freelist_counter.full, &old.full, new.full);
#else
return false;
#endif
}
static inline bool
__update_freelist_slow(struct slab *slab,
void *freelist_old, unsigned long counters_old,
void *freelist_new, unsigned long counters_new)
{
bool ret = false;
slab_lock(slab);
if (slab->freelist == freelist_old &&
slab->counters == counters_old) {
slab->freelist = freelist_new;
slab->counters = counters_new;
ret = true;
}
slab_unlock(slab);
return ret;
}
/*
* Interrupts must be disabled (for the fallback code to work right), typically
* by an _irqsave() lock variant. On PREEMPT_RT the preempt_disable(), which is
* part of bit_spin_lock(), is sufficient because the policy is not to allow any
* allocation/ free operation in hardirq context. Therefore nothing can
* interrupt the operation.
*/
static inline bool __slab_update_freelist(struct kmem_cache *s, struct slab *slab,
void *freelist_old, unsigned long counters_old,
void *freelist_new, unsigned long counters_new,
const char *n)
{
bool ret;
if (USE_LOCKLESS_FAST_PATH())
lockdep_assert_irqs_disabled();
if (s->flags & __CMPXCHG_DOUBLE) {
ret = __update_freelist_fast(slab, freelist_old, counters_old,
freelist_new, counters_new);
} else {
ret = __update_freelist_slow(slab, freelist_old, counters_old,
freelist_new, counters_new);
}
if (likely(ret))
return true;
cpu_relax();
stat(s, CMPXCHG_DOUBLE_FAIL);
#ifdef SLUB_DEBUG_CMPXCHG
pr_info("%s %s: cmpxchg double redo ", n, s->name);
#endif
return false;
}
static inline bool slab_update_freelist(struct kmem_cache *s, struct slab *slab,
void *freelist_old, unsigned long counters_old,
void *freelist_new, unsigned long counters_new,
const char *n)
{
bool ret;
if (s->flags & __CMPXCHG_DOUBLE) {
ret = __update_freelist_fast(slab, freelist_old, counters_old,
freelist_new, counters_new);
} else {
unsigned long flags;
local_irq_save(flags);
ret = __update_freelist_slow(slab, freelist_old, counters_old,
freelist_new, counters_new);
local_irq_restore(flags);
}
if (likely(ret))
return true;
cpu_relax();
stat(s, CMPXCHG_DOUBLE_FAIL);
#ifdef SLUB_DEBUG_CMPXCHG
pr_info("%s %s: cmpxchg double redo ", n, s->name);
#endif
return false;
}
#ifdef CONFIG_SLUB_DEBUG
static unsigned long object_map[BITS_TO_LONGS(MAX_OBJS_PER_PAGE)];
static DEFINE_SPINLOCK(object_map_lock);
static void __fill_map(unsigned long *obj_map, struct kmem_cache *s,
struct slab *slab)
{
void *addr = slab_address(slab);
void *p;
bitmap_zero(obj_map, slab->objects);
for (p = slab->freelist; p; p = get_freepointer(s, p))
set_bit(__obj_to_index(s, addr, p), obj_map);
}
#if IS_ENABLED(CONFIG_KUNIT)
static bool slab_add_kunit_errors(void)
{
struct kunit_resource *resource;
if (!kunit_get_current_test())
return false;
resource = kunit_find_named_resource(current->kunit_test, "slab_errors");
if (!resource)
return false;
(*(int *)resource->data)++;
kunit_put_resource(resource);
return true;
}
#else
static inline bool slab_add_kunit_errors(void) { return false; }
#endif
static inline unsigned int size_from_object(struct kmem_cache *s)
{
if (s->flags & SLAB_RED_ZONE)
return s->size - s->red_left_pad;
return s->size;
}
static inline void *restore_red_left(struct kmem_cache *s, void *p)
{
if (s->flags & SLAB_RED_ZONE)
p -= s->red_left_pad;
return p;
}
/*
* Debug settings:
*/
#if defined(CONFIG_SLUB_DEBUG_ON)
static slab_flags_t slub_debug = DEBUG_DEFAULT_FLAGS;
#else
static slab_flags_t slub_debug;
#endif
static char *slub_debug_string;
static int disable_higher_order_debug;
/*
* slub is about to manipulate internal object metadata. This memory lies
* outside the range of the allocated object, so accessing it would normally
* be reported by kasan as a bounds error. metadata_access_enable() is used
* to tell kasan that these accesses are OK.
*/
static inline void metadata_access_enable(void)
{
kasan_disable_current();
}
static inline void metadata_access_disable(void)
{
kasan_enable_current();
}
/*
* Object debugging
*/
/* Verify that a pointer has an address that is valid within a slab page */
static inline int check_valid_pointer(struct kmem_cache *s,
struct slab *slab, void *object)
{
void *base;
if (!object)
return 1;
base = slab_address(slab);
object = kasan_reset_tag(object);
object = restore_red_left(s, object);
if (object < base || object >= base + slab->objects * s->size ||
(object - base) % s->size) {
return 0;
}
return 1;
}
static void print_section(char *level, char *text, u8 *addr,
unsigned int length)
{
metadata_access_enable();
print_hex_dump(level, text, DUMP_PREFIX_ADDRESS,
16, 1, kasan_reset_tag((void *)addr), length, 1);
metadata_access_disable();
}
/*
* See comment in calculate_sizes().
*/
static inline bool freeptr_outside_object(struct kmem_cache *s)
{
return s->offset >= s->inuse;
}
/*
* Return offset of the end of info block which is inuse + free pointer if
* not overlapping with object.
*/
static inline unsigned int get_info_end(struct kmem_cache *s)
{
if (freeptr_outside_object(s))
return s->inuse + sizeof(void *);
else
return s->inuse;
}
static struct track *get_track(struct kmem_cache *s, void *object,
enum track_item alloc)
{
struct track *p;
p = object + get_info_end(s);
return kasan_reset_tag(p + alloc);
}
#ifdef CONFIG_STACKDEPOT
static noinline depot_stack_handle_t set_track_prepare(void)
{
depot_stack_handle_t handle;
unsigned long entries[TRACK_ADDRS_COUNT];
unsigned int nr_entries;
nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 3);
handle = stack_depot_save(entries, nr_entries, GFP_NOWAIT);
return handle;
}
#else
static inline depot_stack_handle_t set_track_prepare(void)
{
return 0;
}
#endif
static void set_track_update(struct kmem_cache *s, void *object,
enum track_item alloc, unsigned long addr,
depot_stack_handle_t handle)
{
struct track *p = get_track(s, object, alloc);
#ifdef CONFIG_STACKDEPOT
p->handle = handle;
#endif
p->addr = addr;
p->cpu = smp_processor_id();
p->pid = current->pid;
p->when = jiffies;
}
static __always_inline void set_track(struct kmem_cache *s, void *object,
enum track_item alloc, unsigned long addr)
{
depot_stack_handle_t handle = set_track_prepare();
set_track_update(s, object, alloc, addr, handle);
}
static void init_tracking(struct kmem_cache *s, void *object)
{
struct track *p;
if (!(s->flags & SLAB_STORE_USER))
return;
p = get_track(s, object, TRACK_ALLOC);
memset(p, 0, 2*sizeof(struct track));
}
static void print_track(const char *s, struct track *t, unsigned long pr_time)
{
depot_stack_handle_t handle __maybe_unused;
if (!t->addr)
return;
pr_err("%s in %pS age=%lu cpu=%u pid=%d\n",
s, (void *)t->addr, pr_time - t->when, t->cpu, t->pid);
#ifdef CONFIG_STACKDEPOT
handle = READ_ONCE(t->handle);
if (handle)
stack_depot_print(handle);
else
pr_err("object allocation/free stack trace missing\n");
#endif
}
void print_tracking(struct kmem_cache *s, void *object)
{
unsigned long pr_time = jiffies;
if (!(s->flags & SLAB_STORE_USER))
return;
print_track("Allocated", get_track(s, object, TRACK_ALLOC), pr_time);
print_track("Freed", get_track(s, object, TRACK_FREE), pr_time);
}
static void print_slab_info(const struct slab *slab)
{
struct folio *folio = (struct folio *)slab_folio(slab);
pr_err("Slab 0x%p objects=%u used=%u fp=0x%p flags=%pGp\n",
slab, slab->objects, slab->inuse, slab->freelist,
folio_flags(folio, 0));
}
/*
* kmalloc caches has fixed sizes (mostly power of 2), and kmalloc() API
* family will round up the real request size to these fixed ones, so
* there could be an extra area than what is requested. Save the original
* request size in the meta data area, for better debug and sanity check.
*/
static inline void set_orig_size(struct kmem_cache *s,
void *object, unsigned int orig_size)
{
void *p = kasan_reset_tag(object);
if (!slub_debug_orig_size(s))
return;
#ifdef CONFIG_KASAN_GENERIC
/*
* KASAN could save its free meta data in object's data area at
* offset 0, if the size is larger than 'orig_size', it will
* overlap the data redzone in [orig_size+1, object_size], and
* the check should be skipped.
*/
if (kasan_metadata_size(s, true) > orig_size)
orig_size = s->object_size;
#endif
p += get_info_end(s);
p += sizeof(struct track) * 2;
*(unsigned int *)p = orig_size;
}
static inline unsigned int get_orig_size(struct kmem_cache *s, void *object)
{
void *p = kasan_reset_tag(object);
if (!slub_debug_orig_size(s))
return s->object_size;
p += get_info_end(s);
p += sizeof(struct track) * 2;
return *(unsigned int *)p;
}
void skip_orig_size_check(struct kmem_cache *s, const void *object)
{
set_orig_size(s, (void *)object, s->object_size);
}
static void slab_bug(struct kmem_cache *s, char *fmt, ...)
{
struct va_format vaf;
va_list args;
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
pr_err("=============================================================================\n");
pr_err("BUG %s (%s): %pV\n", s->name, print_tainted(), &vaf);
pr_err("-----------------------------------------------------------------------------\n\n");
va_end(args);
}
__printf(2, 3)
static void slab_fix(struct kmem_cache *s, char *fmt, ...)
{
struct va_format vaf;
va_list args;
if (slab_add_kunit_errors())
return;
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
pr_err("FIX %s: %pV\n", s->name, &vaf);
va_end(args);
}
static void print_trailer(struct kmem_cache *s, struct slab *slab, u8 *p)
{
unsigned int off; /* Offset of last byte */
u8 *addr = slab_address(slab);
print_tracking(s, p);
print_slab_info(slab);
pr_err("Object 0x%p @offset=%tu fp=0x%p\n\n",
p, p - addr, get_freepointer(s, p));
if (s->flags & SLAB_RED_ZONE)
print_section(KERN_ERR, "Redzone ", p - s->red_left_pad,
s->red_left_pad);
else if (p > addr + 16)
print_section(KERN_ERR, "Bytes b4 ", p - 16, 16);
print_section(KERN_ERR, "Object ", p,
min_t(unsigned int, s->object_size, PAGE_SIZE));
if (s->flags & SLAB_RED_ZONE)
print_section(KERN_ERR, "Redzone ", p + s->object_size,
s->inuse - s->object_size);
off = get_info_end(s);
if (s->flags & SLAB_STORE_USER)
off += 2 * sizeof(struct track);
if (slub_debug_orig_size(s))
off += sizeof(unsigned int);
off += kasan_metadata_size(s, false);
if (off != size_from_object(s))
/* Beginning of the filler is the free pointer */
print_section(KERN_ERR, "Padding ", p + off,
size_from_object(s) - off);
dump_stack();
}
static void object_err(struct kmem_cache *s, struct slab *slab,
u8 *object, char *reason)
{
if (slab_add_kunit_errors())
return;
slab_bug(s, "%s", reason);
print_trailer(s, slab, object);
add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
}
static bool freelist_corrupted(struct kmem_cache *s, struct slab *slab,
void **freelist, void *nextfree)
{
if ((s->flags & SLAB_CONSISTENCY_CHECKS) &&
!check_valid_pointer(s, slab, nextfree) && freelist) {
object_err(s, slab, *freelist, "Freechain corrupt");
*freelist = NULL;
slab_fix(s, "Isolate corrupted freechain");
return true;
}
return false;
}
static __printf(3, 4) void slab_err(struct kmem_cache *s, struct slab *slab,
const char *fmt, ...)
{
va_list args;
char buf[100];
if (slab_add_kunit_errors())
return;
va_start(args, fmt);
vsnprintf(buf, sizeof(buf), fmt, args);
va_end(args);
slab_bug(s, "%s", buf);
print_slab_info(slab);
dump_stack();
add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
}
static void init_object(struct kmem_cache *s, void *object, u8 val)
{
u8 *p = kasan_reset_tag(object);
unsigned int poison_size = s->object_size;
if (s->flags & SLAB_RED_ZONE) {
memset(p - s->red_left_pad, val, s->red_left_pad);
if (slub_debug_orig_size(s) && val == SLUB_RED_ACTIVE) {
/*
* Redzone the extra allocated space by kmalloc than
* requested, and the poison size will be limited to
* the original request size accordingly.
*/
poison_size = get_orig_size(s, object);
}
}
if (s->flags & __OBJECT_POISON) {
memset(p, POISON_FREE, poison_size - 1);
p[poison_size - 1] = POISON_END;
}
if (s->flags & SLAB_RED_ZONE)
memset(p + poison_size, val, s->inuse - poison_size);
}
static void restore_bytes(struct kmem_cache *s, char *message, u8 data,
void *from, void *to)
{
slab_fix(s, "Restoring %s 0x%p-0x%p=0x%x", message, from, to - 1, data);
memset(from, data, to - from);
}
static int check_bytes_and_report(struct kmem_cache *s, struct slab *slab,
u8 *object, char *what,
u8 *start, unsigned int value, unsigned int bytes)
{
u8 *fault;
u8 *end;
u8 *addr = slab_address(slab);
metadata_access_enable();
fault = memchr_inv(kasan_reset_tag(start), value, bytes);
metadata_access_disable();
if (!fault)
return 1;
end = start + bytes;
while (end > fault && end[-1] == value)
end--;
if (slab_add_kunit_errors())
goto skip_bug_print;
slab_bug(s, "%s overwritten", what);
pr_err("0x%p-0x%p @offset=%tu. First byte 0x%x instead of 0x%x\n",
fault, end - 1, fault - addr,
fault[0], value);
print_trailer(s, slab, object);
add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
skip_bug_print:
restore_bytes(s, what, value, fault, end);
return 0;
}
/*
* Object layout:
*
* object address
* Bytes of the object to be managed.
* If the freepointer may overlay the object then the free
* pointer is at the middle of the object.
*
* Poisoning uses 0x6b (POISON_FREE) and the last byte is
* 0xa5 (POISON_END)
*
* object + s->object_size
* Padding to reach word boundary. This is also used for Redzoning.
* Padding is extended by another word if Redzoning is enabled and
* object_size == inuse.
*
* We fill with 0xbb (RED_INACTIVE) for inactive objects and with
* 0xcc (RED_ACTIVE) for objects in use.
*
* object + s->inuse
* Meta data starts here.
*
* A. Free pointer (if we cannot overwrite object on free)
* B. Tracking data for SLAB_STORE_USER
* C. Original request size for kmalloc object (SLAB_STORE_USER enabled)
* D. Padding to reach required alignment boundary or at minimum
* one word if debugging is on to be able to detect writes
* before the word boundary.
*
* Padding is done using 0x5a (POISON_INUSE)
*
* object + s->size
* Nothing is used beyond s->size.
*
* If slabcaches are merged then the object_size and inuse boundaries are mostly
* ignored. And therefore no slab options that rely on these boundaries
* may be used with merged slabcaches.
*/
static int check_pad_bytes(struct kmem_cache *s, struct slab *slab, u8 *p)
{
unsigned long off = get_info_end(s); /* The end of info */
if (s->flags & SLAB_STORE_USER) {
/* We also have user information there */
off += 2 * sizeof(struct track);
if (s->flags & SLAB_KMALLOC)
off += sizeof(unsigned int);
}
off += kasan_metadata_size(s, false);
if (size_from_object(s) == off)
return 1;
return check_bytes_and_report(s, slab, p, "Object padding",
p + off, POISON_INUSE, size_from_object(s) - off);
}
/* Check the pad bytes at the end of a slab page */
static void slab_pad_check(struct kmem_cache *s, struct slab *slab)
{
u8 *start;
u8 *fault;
u8 *end;
u8 *pad;
int length;
int remainder;
if (!(s->flags & SLAB_POISON))
return;
start = slab_address(slab);
length = slab_size(slab);
end = start + length;
remainder = length % s->size;
if (!remainder)
return;
pad = end - remainder;
metadata_access_enable();
fault = memchr_inv(kasan_reset_tag(pad), POISON_INUSE, remainder);
metadata_access_disable();
if (!fault)
return;
while (end > fault && end[-1] == POISON_INUSE)
end--;
slab_err(s, slab, "Padding overwritten. 0x%p-0x%p @offset=%tu",
fault, end - 1, fault - start);
print_section(KERN_ERR, "Padding ", pad, remainder);
restore_bytes(s, "slab padding", POISON_INUSE, fault, end);
}
static int check_object(struct kmem_cache *s, struct slab *slab,
void *object, u8 val)
{
u8 *p = object;
u8 *endobject = object + s->object_size;
unsigned int orig_size;
if (s->flags & SLAB_RED_ZONE) {
if (!check_bytes_and_report(s, slab, object, "Left Redzone",
object - s->red_left_pad, val, s->red_left_pad))
return 0;
if (!check_bytes_and_report(s, slab, object, "Right Redzone",
endobject, val, s->inuse - s->object_size))
return 0;
if (slub_debug_orig_size(s) && val == SLUB_RED_ACTIVE) {
orig_size = get_orig_size(s, object);
if (s->object_size > orig_size &&
!check_bytes_and_report(s, slab, object,
"kmalloc Redzone", p + orig_size,
val, s->object_size - orig_size)) {
return 0;
}
}
} else {
if ((s->flags & SLAB_POISON) && s->object_size < s->inuse) {
check_bytes_and_report(s, slab, p, "Alignment padding",
endobject, POISON_INUSE,
s->inuse - s->object_size);
}
}
if (s->flags & SLAB_POISON) {
if (val != SLUB_RED_ACTIVE && (s->flags & __OBJECT_POISON) &&
(!check_bytes_and_report(s, slab, p, "Poison", p,
POISON_FREE, s->object_size - 1) ||
!check_bytes_and_report(s, slab, p, "End Poison",
p + s->object_size - 1, POISON_END, 1)))
return 0;
/*
* check_pad_bytes cleans up on its own.
*/
check_pad_bytes(s, slab, p);
}
if (!freeptr_outside_object(s) && val == SLUB_RED_ACTIVE)
/*
* Object and freepointer overlap. Cannot check
* freepointer while object is allocated.
*/
return 1;
/* Check free pointer validity */
if (!check_valid_pointer(s, slab, get_freepointer(s, p))) {
object_err(s, slab, p, "Freepointer corrupt");
/*
* No choice but to zap it and thus lose the remainder
* of the free objects in this slab. May cause
* another error because the object count is now wrong.
*/
set_freepointer(s, p, NULL);
return 0;
}
return 1;
}
static int check_slab(struct kmem_cache *s, struct slab *slab)
{
int maxobj;
if (!folio_test_slab(slab_folio(slab))) {
slab_err(s, slab, "Not a valid slab page");
return 0;
}
maxobj = order_objects(slab_order(slab), s->size);
if (slab->objects > maxobj) {
slab_err(s, slab, "objects %u > max %u",
slab->objects, maxobj);
return 0;
}
if (slab->inuse > slab->objects) {
slab_err(s, slab, "inuse %u > max %u",
slab->inuse, slab->objects);
return 0;
}
/* Slab_pad_check fixes things up after itself */
slab_pad_check(s, slab);
return 1;
}
/*
* Determine if a certain object in a slab is on the freelist. Must hold the
* slab lock to guarantee that the chains are in a consistent state.
*/
static int on_freelist(struct kmem_cache *s, struct slab *slab, void *search)
{
int nr = 0;
void *fp;
void *object = NULL;
int max_objects;
fp = slab->freelist;
while (fp && nr <= slab->objects) {
if (fp == search)
return 1;
if (!check_valid_pointer(s, slab, fp)) {
if (object) {
object_err(s, slab, object,
"Freechain corrupt");
set_freepointer(s, object, NULL);
} else {
slab_err(s, slab, "Freepointer corrupt");
slab->freelist = NULL;
slab->inuse = slab->objects;
slab_fix(s, "Freelist cleared");
return 0;
}
break;
}
object = fp;
fp = get_freepointer(s, object);
nr++;
}
max_objects = order_objects(slab_order(slab), s->size);
if (max_objects > MAX_OBJS_PER_PAGE)
max_objects = MAX_OBJS_PER_PAGE;
if (slab->objects != max_objects) {
slab_err(s, slab, "Wrong number of objects. Found %d but should be %d",
slab->objects, max_objects);
slab->objects = max_objects;
slab_fix(s, "Number of objects adjusted");
}
if (slab->inuse != slab->objects - nr) {
slab_err(s, slab, "Wrong object count. Counter is %d but counted were %d",
slab->inuse, slab->objects - nr);
slab->inuse = slab->objects - nr;
slab_fix(s, "Object count adjusted");
}
return search == NULL;
}
static void trace(struct kmem_cache *s, struct slab *slab, void *object,
int alloc)
{
if (s->flags & SLAB_TRACE) {
pr_info("TRACE %s %s 0x%p inuse=%d fp=0x%p\n",
s->name,
alloc ? "alloc" : "free",
object, slab->inuse,
slab->freelist);
if (!alloc)
print_section(KERN_INFO, "Object ", (void *)object,
s->object_size);
dump_stack();
}
}
/*
* Tracking of fully allocated slabs for debugging purposes.
*/
static void add_full(struct kmem_cache *s,
struct kmem_cache_node *n, struct slab *slab)
{
if (!(s->flags & SLAB_STORE_USER))
return;
lockdep_assert_held(&n->list_lock);
list_add(&slab->slab_list, &n->full);
}
static void remove_full(struct kmem_cache *s, struct kmem_cache_node *n, struct slab *slab)
{
if (!(s->flags & SLAB_STORE_USER))
return;
lockdep_assert_held(&n->list_lock);
list_del(&slab->slab_list);
}
static inline unsigned long node_nr_slabs(struct kmem_cache_node *n)
{
return atomic_long_read(&n->nr_slabs);
}
static inline void inc_slabs_node(struct kmem_cache *s, int node, int objects)
{
struct kmem_cache_node *n = get_node(s, node);
/*
* May be called early in order to allocate a slab for the
* kmem_cache_node structure. Solve the chicken-egg
* dilemma by deferring the increment of the count during
* bootstrap (see early_kmem_cache_node_alloc).
*/
if (likely(n)) {
atomic_long_inc(&n->nr_slabs);
atomic_long_add(objects, &n->total_objects);
}
}
static inline void dec_slabs_node(struct kmem_cache *s, int node, int objects)
{
struct kmem_cache_node *n = get_node(s, node);
atomic_long_dec(&n->nr_slabs);
atomic_long_sub(objects, &n->total_objects);
}
/* Object debug checks for alloc/free paths */
static void setup_object_debug(struct kmem_cache *s, void *object)
{
if (!kmem_cache_debug_flags(s, SLAB_STORE_USER|SLAB_RED_ZONE|__OBJECT_POISON))
return;
init_object(s, object, SLUB_RED_INACTIVE);
init_tracking(s, object);
}
static
void setup_slab_debug(struct kmem_cache *s, struct slab *slab, void *addr)
{
if (!kmem_cache_debug_flags(s, SLAB_POISON))
return;
metadata_access_enable();
memset(kasan_reset_tag(addr), POISON_INUSE, slab_size(slab));
metadata_access_disable();
}
static inline int alloc_consistency_checks(struct kmem_cache *s,
struct slab *slab, void *object)
{
if (!check_slab(s, slab))
return 0;
if (!check_valid_pointer(s, slab, object)) {
object_err(s, slab, object, "Freelist Pointer check fails");
return 0;
}
if (!check_object(s, slab, object, SLUB_RED_INACTIVE))
return 0;
return 1;
}
static noinline bool alloc_debug_processing(struct kmem_cache *s,
struct slab *slab, void *object, int orig_size)
{
if (s->flags & SLAB_CONSISTENCY_CHECKS) {
if (!alloc_consistency_checks(s, slab, object))
goto bad;
}
/* Success. Perform special debug activities for allocs */
trace(s, slab, object, 1);
set_orig_size(s, object, orig_size);
init_object(s, object, SLUB_RED_ACTIVE);
return true;
bad:
if (folio_test_slab(slab_folio(slab))) {
/*
* If this is a slab page then lets do the best we can
* to avoid issues in the future. Marking all objects
* as used avoids touching the remaining objects.
*/
slab_fix(s, "Marking all objects used");
slab->inuse = slab->objects;
slab->freelist = NULL;
}
return false;
}
static inline int free_consistency_checks(struct kmem_cache *s,
struct slab *slab, void *object, unsigned long addr)
{
if (!check_valid_pointer(s, slab, object)) {
slab_err(s, slab, "Invalid object pointer 0x%p", object);
return 0;
}
if (on_freelist(s, slab, object)) {
object_err(s, slab, object, "Object already free");
return 0;
}
if (!check_object(s, slab, object, SLUB_RED_ACTIVE))
return 0;
if (unlikely(s != slab->slab_cache)) {
if (!folio_test_slab(slab_folio(slab))) {
slab_err(s, slab, "Attempt to free object(0x%p) outside of slab",
object);
} else if (!slab->slab_cache) {
pr_err("SLUB <none>: no slab for object 0x%p.\n",
object);
dump_stack();
} else
object_err(s, slab, object,
"page slab pointer corrupt.");
return 0;
}
return 1;
}
/*
* Parse a block of slub_debug options. Blocks are delimited by ';'
*
* @str: start of block
* @flags: returns parsed flags, or DEBUG_DEFAULT_FLAGS if none specified
* @slabs: return start of list of slabs, or NULL when there's no list
* @init: assume this is initial parsing and not per-kmem-create parsing
*
* returns the start of next block if there's any, or NULL
*/
static char *
parse_slub_debug_flags(char *str, slab_flags_t *flags, char **slabs, bool init)
{
bool higher_order_disable = false;
/* Skip any completely empty blocks */
while (*str && *str == ';')
str++;
if (*str == ',') {
/*
* No options but restriction on slabs. This means full
* debugging for slabs matching a pattern.
*/
*flags = DEBUG_DEFAULT_FLAGS;
goto check_slabs;
}
*flags = 0;
/* Determine which debug features should be switched on */
for (; *str && *str != ',' && *str != ';'; str++) {
switch (tolower(*str)) {
case '-':
*flags = 0;
break;
case 'f':
*flags |= SLAB_CONSISTENCY_CHECKS;
break;
case 'z':
*flags |= SLAB_RED_ZONE;
break;
case 'p':
*flags |= SLAB_POISON;
break;
case 'u':
*flags |= SLAB_STORE_USER;
break;
case 't':
*flags |= SLAB_TRACE;
break;
case 'a':
*flags |= SLAB_FAILSLAB;
break;
case 'o':
/*
* Avoid enabling debugging on caches if its minimum
* order would increase as a result.
*/
higher_order_disable = true;
break;
default:
if (init)
pr_err("slub_debug option '%c' unknown. skipped\n", *str);
}
}
check_slabs:
if (*str == ',')
*slabs = ++str;
else
*slabs = NULL;
/* Skip over the slab list */
while (*str && *str != ';')
str++;
/* Skip any completely empty blocks */
while (*str && *str == ';')
str++;
if (init && higher_order_disable)
disable_higher_order_debug = 1;
if (*str)
return str;
else
return NULL;
}
static int __init setup_slub_debug(char *str)
{
slab_flags_t flags;
slab_flags_t global_flags;
char *saved_str;
char *slab_list;
bool global_slub_debug_changed = false;
bool slab_list_specified = false;
global_flags = DEBUG_DEFAULT_FLAGS;
if (*str++ != '=' || !*str)
/*
* No options specified. Switch on full debugging.
*/
goto out;
saved_str = str;
while (str) {
str = parse_slub_debug_flags(str, &flags, &slab_list, true);
if (!slab_list) {
global_flags = flags;
global_slub_debug_changed = true;
} else {
slab_list_specified = true;
if (flags & SLAB_STORE_USER)
stack_depot_request_early_init();
}
}
/*
* For backwards compatibility, a single list of flags with list of
* slabs means debugging is only changed for those slabs, so the global
* slub_debug should be unchanged (0 or DEBUG_DEFAULT_FLAGS, depending
* on CONFIG_SLUB_DEBUG_ON). We can extended that to multiple lists as
* long as there is no option specifying flags without a slab list.
*/
if (slab_list_specified) {
if (!global_slub_debug_changed)
global_flags = slub_debug;
slub_debug_string = saved_str;
}
out:
slub_debug = global_flags;
if (slub_debug & SLAB_STORE_USER)
stack_depot_request_early_init();
if (slub_debug != 0 || slub_debug_string)
static_branch_enable(&slub_debug_enabled);
else
static_branch_disable(&slub_debug_enabled);
if ((static_branch_unlikely(&init_on_alloc) ||
static_branch_unlikely(&init_on_free)) &&
(slub_debug & SLAB_POISON))
pr_info("mem auto-init: SLAB_POISON will take precedence over init_on_alloc/init_on_free\n");
return 1;
}
__setup("slub_debug", setup_slub_debug);
/*
* kmem_cache_flags - apply debugging options to the cache
* @object_size: the size of an object without meta data
* @flags: flags to set
* @name: name of the cache
*
* Debug option(s) are applied to @flags. In addition to the debug
* option(s), if a slab name (or multiple) is specified i.e.
* slub_debug=<Debug-Options>,<slab name1>,<slab name2> ...
* then only the select slabs will receive the debug option(s).
*/
slab_flags_t kmem_cache_flags(unsigned int object_size,
slab_flags_t flags, const char *name)
{
char *iter;
size_t len;
char *next_block;
slab_flags_t block_flags;
slab_flags_t slub_debug_local = slub_debug;
if (flags & SLAB_NO_USER_FLAGS)
return flags;
/*
* If the slab cache is for debugging (e.g. kmemleak) then
* don't store user (stack trace) information by default,
* but let the user enable it via the command line below.
*/
if (flags & SLAB_NOLEAKTRACE)
slub_debug_local &= ~SLAB_STORE_USER;
len = strlen(name);
next_block = slub_debug_string;
/* Go through all blocks of debug options, see if any matches our slab's name */
while (next_block) {
next_block = parse_slub_debug_flags(next_block, &block_flags, &iter, false);
if (!iter)
continue;
/* Found a block that has a slab list, search it */
while (*iter) {
char *end, *glob;
size_t cmplen;
end = strchrnul(iter, ',');
if (next_block && next_block < end)
end = next_block - 1;
glob = strnchr(iter, end - iter, '*');
if (glob)
cmplen = glob - iter;
else
cmplen = max_t(size_t, len, (end - iter));
if (!strncmp(name, iter, cmplen)) {
flags |= block_flags;
return flags;
}
if (!*end || *end == ';')
break;
iter = end + 1;
}
}
return flags | slub_debug_local;
}
#else /* !CONFIG_SLUB_DEBUG */
static inline void setup_object_debug(struct kmem_cache *s, void *object) {}
static inline
void setup_slab_debug(struct kmem_cache *s, struct slab *slab, void *addr) {}
static inline bool alloc_debug_processing(struct kmem_cache *s,
struct slab *slab, void *object, int orig_size) { return true; }
static inline bool free_debug_processing(struct kmem_cache *s,
struct slab *slab, void *head, void *tail, int *bulk_cnt,
unsigned long addr, depot_stack_handle_t handle) { return true; }
static inline void slab_pad_check(struct kmem_cache *s, struct slab *slab) {}
static inline int check_object(struct kmem_cache *s, struct slab *slab,
void *object, u8 val) { return 1; }
static inline depot_stack_handle_t set_track_prepare(void) { return 0; }
static inline void set_track(struct kmem_cache *s, void *object,
enum track_item alloc, unsigned long addr) {}
static inline void add_full(struct kmem_cache *s, struct kmem_cache_node *n,
struct slab *slab) {}
static inline void remove_full(struct kmem_cache *s, struct kmem_cache_node *n,
struct slab *slab) {}
slab_flags_t kmem_cache_flags(unsigned int object_size,
slab_flags_t flags, const char *name)
{
return flags;
}
#define slub_debug 0
#define disable_higher_order_debug 0
static inline unsigned long node_nr_slabs(struct kmem_cache_node *n)
{ return 0; }
static inline void inc_slabs_node(struct kmem_cache *s, int node,
int objects) {}
static inline void dec_slabs_node(struct kmem_cache *s, int node,
int objects) {}
#ifndef CONFIG_SLUB_TINY
static bool freelist_corrupted(struct kmem_cache *s, struct slab *slab,
void **freelist, void *nextfree)
{
return false;
}
#endif
#endif /* CONFIG_SLUB_DEBUG */
/*
* Hooks for other subsystems that check memory allocations. In a typical
* production configuration these hooks all should produce no code at all.
*/
static __always_inline bool slab_free_hook(struct kmem_cache *s,
void *x, bool init)
{
kmemleak_free_recursive(x, s->flags);
kmsan_slab_free(s, x);
debug_check_no_locks_freed(x, s->object_size);
if (!(s->flags & SLAB_DEBUG_OBJECTS))
debug_check_no_obj_freed(x, s->object_size);
/* Use KCSAN to help debug racy use-after-free. */
if (!(s->flags & SLAB_TYPESAFE_BY_RCU))
__kcsan_check_access(x, s->object_size,
KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ASSERT);
/*
* As memory initialization might be integrated into KASAN,
* kasan_slab_free and initialization memset's must be
* kept together to avoid discrepancies in behavior.
*
* The initialization memset's clear the object and the metadata,
* but don't touch the SLAB redzone.
*/
if (init) {
int rsize;
if (!kasan_has_integrated_init())
memset(kasan_reset_tag(x), 0, s->object_size);
rsize = (s->flags & SLAB_RED_ZONE) ? s->red_left_pad : 0;
memset((char *)kasan_reset_tag(x) + s->inuse, 0,
s->size - s->inuse - rsize);
}
/* KASAN might put x into memory quarantine, delaying its reuse. */
return kasan_slab_free(s, x, init);
}
static inline bool slab_free_freelist_hook(struct kmem_cache *s,
void **head, void **tail,
int *cnt)
{
void *object;
void *next = *head;
void *old_tail = *tail ? *tail : *head;
if (is_kfence_address(next)) {
slab_free_hook(s, next, false);
return true;
}
/* Head and tail of the reconstructed freelist */
*head = NULL;
*tail = NULL;
do {
object = next;
next = get_freepointer(s, object);
/* If object's reuse doesn't have to be delayed */
if (!slab_free_hook(s, object, slab_want_init_on_free(s))) {
/* Move object to the new freelist */
set_freepointer(s, object, *head);
*head = object;
if (!*tail)
*tail = object;
} else {
/*
* Adjust the reconstructed freelist depth
* accordingly if object's reuse is delayed.
*/
--(*cnt);
}
} while (object != old_tail);
if (*head == *tail)
*tail = NULL;
return *head != NULL;
}
static void *setup_object(struct kmem_cache *s, void *object)
{
setup_object_debug(s, object);
object = kasan_init_slab_obj(s, object);
if (unlikely(s->ctor)) {
kasan_unpoison_object_data(s, object);
s->ctor(object);
kasan_poison_object_data(s, object);
}
return object;
}
/*
* Slab allocation and freeing
*/
static inline struct slab *alloc_slab_page(gfp_t flags, int node,
struct kmem_cache_order_objects oo)
{
struct folio *folio;
struct slab *slab;
unsigned int order = oo_order(oo);
if (node == NUMA_NO_NODE)
folio = (struct folio *)alloc_pages(flags, order);
else
folio = (struct folio *)__alloc_pages_node(node, flags, order);
if (!folio)
return NULL;
slab = folio_slab(folio);
__folio_set_slab(folio);
/* Make the flag visible before any changes to folio->mapping */
smp_wmb();
if (folio_is_pfmemalloc(folio))
slab_set_pfmemalloc(slab);
return slab;
}
#ifdef CONFIG_SLAB_FREELIST_RANDOM
/* Pre-initialize the random sequence cache */
static int init_cache_random_seq(struct kmem_cache *s)
{
unsigned int count = oo_objects(s->oo);
int err;
/* Bailout if already initialised */
if (s->random_seq)
return 0;
err = cache_random_seq_create(s, count, GFP_KERNEL);
if (err) {
pr_err("SLUB: Unable to initialize free list for %s\n",
s->name);
return err;
}
/* Transform to an offset on the set of pages */
if (s->random_seq) {
unsigned int i;
for (i = 0; i < count; i++)
s->random_seq[i] *= s->size;
}
return 0;
}
/* Initialize each random sequence freelist per cache */
static void __init init_freelist_randomization(void)
{
struct kmem_cache *s;
mutex_lock(&slab_mutex);
list_for_each_entry(s, &slab_caches, list)
init_cache_random_seq(s);
mutex_unlock(&slab_mutex);
}
/* Get the next entry on the pre-computed freelist randomized */
static void *next_freelist_entry(struct kmem_cache *s, struct slab *slab,
unsigned long *pos, void *start,
unsigned long page_limit,
unsigned long freelist_count)
{
unsigned int idx;
/*
* If the target page allocation failed, the number of objects on the
* pag