blob: 21f71cb6cc06d951a657290421f41170bb3c76cf [file] [log] [blame]
// 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/kmemleak.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
* the cpu slab which is actively allocated from by the processor that
* froze it and it is not on any 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.
*
* CPU partial slabs
*
* The partially empty slabs cached on the CPU partial list are used
* for performance reasons, which speeds up the allocation process.
* These slabs are not frozen, but are also exempt from list management,
* by clearing the PG_workingset flag when moving out of the node
* partial list. Please see __slab_free() for more details.
*
* To sum up, the current scheme is:
* - node partial slab: PG_Workingset && !frozen
* - cpu partial slab: !PG_Workingset && !frozen
* - cpu slab: !PG_Workingset && frozen
* - full slab: !PG_Workingset && !frozen
*
* 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 {
gfp_t flags;
unsigned int orig_size;
void *object;
};
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 slab_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_FLAG_BIT(_SLAB_OBJECT_POISON)
/* Use cmpxchg_double */
#ifdef system_has_freelist_aba
#define __CMPXCHG_DOUBLE __SLAB_FLAG_BIT(_SLAB_CMPXCHG_DOUBLE)
#else
#define __CMPXCHG_DOUBLE __SLAB_FLAG_UNUSED
#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
enum stat_item {
ALLOC_FASTPATH, /* Allocation from cpu slab */
ALLOC_SLOWPATH, /* Allocation by getting a new cpu slab */
FREE_FASTPATH, /* Free to cpu slab */
FREE_SLOWPATH, /* Freeing not to cpu slab */
FREE_FROZEN, /* Freeing to frozen slab */
FREE_ADD_PARTIAL, /* Freeing moves slab to partial list */
FREE_REMOVE_PARTIAL, /* Freeing removes last object */
ALLOC_FROM_PARTIAL, /* Cpu slab acquired from node partial list */
ALLOC_SLAB, /* Cpu slab acquired from page allocator */
ALLOC_REFILL, /* Refill cpu slab from slab freelist */
ALLOC_NODE_MISMATCH, /* Switching cpu slab */
FREE_SLAB, /* Slab freed to the page allocator */
CPUSLAB_FLUSH, /* Abandoning of the cpu slab */
DEACTIVATE_FULL, /* Cpu slab was full when deactivated */
DEACTIVATE_EMPTY, /* Cpu slab was empty when deactivated */
DEACTIVATE_TO_HEAD, /* Cpu slab was moved to the head of partials */
DEACTIVATE_TO_TAIL, /* Cpu slab was moved to the tail of partials */
DEACTIVATE_REMOTE_FREES,/* Slab contained remotely freed objects */
DEACTIVATE_BYPASS, /* Implicit deactivation */
ORDER_FALLBACK, /* Number of times fallback was necessary */
CMPXCHG_DOUBLE_CPU_FAIL,/* Failures of this_cpu_cmpxchg_double */
CMPXCHG_DOUBLE_FAIL, /* Failures of slab freelist update */
CPU_PARTIAL_ALLOC, /* Used cpu partial on alloc */
CPU_PARTIAL_FREE, /* Refill cpu partial on free */
CPU_PARTIAL_NODE, /* Refill cpu partial from node partial */
CPU_PARTIAL_DRAIN, /* Drain cpu partial to node partial */
NR_SLUB_STAT_ITEMS
};
#ifndef CONFIG_SLUB_TINY
/*
* When changing the layout, make sure freelist and tid are still compatible
* with this_cpu_cmpxchg_double() alignment requirements.
*/
struct kmem_cache_cpu {
union {
struct {
void **freelist; /* Pointer to next available object */
unsigned long tid; /* Globally unique transaction id */
};
freelist_aba_t freelist_tid;
};
struct slab *slab; /* The slab from which we are allocating */
#ifdef CONFIG_SLUB_CPU_PARTIAL
struct slab *partial; /* Partially allocated slabs */
#endif
local_lock_t lock; /* Protects the fields above */
#ifdef CONFIG_SLUB_STATS
unsigned int stat[NR_SLUB_STAT_ITEMS];
#endif
};
#endif /* CONFIG_SLUB_TINY */
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
}
static inline
void stat_add(const struct kmem_cache *s, enum stat_item si, int v)
{
#ifdef CONFIG_SLUB_STATS
raw_cpu_add(s->cpu_slab->stat[si], v);
#endif
}
/*
* The slab lists for all objects.
*/
struct kmem_cache_node {
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
};
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)))
/*
* 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 freeptr_t freelist_ptr_encode(const struct kmem_cache *s,
void *ptr, unsigned long ptr_addr)
{
unsigned long encoded;
#ifdef CONFIG_SLAB_FREELIST_HARDENED
encoded = (unsigned long)ptr ^ s->random ^ swab(ptr_addr);
#else
encoded = (unsigned long)ptr;
#endif
return (freeptr_t){.v = encoded};
}
static inline void *freelist_ptr_decode(const struct kmem_cache *s,
freeptr_t ptr, unsigned long ptr_addr)
{
void *decoded;
#ifdef CONFIG_SLAB_FREELIST_HARDENED
decoded = (void *)(ptr.v ^ s->random ^ swab(ptr_addr));
#else
decoded = (void *)ptr.v;
#endif
return decoded;
}
static inline void *get_freepointer(struct kmem_cache *s, void *object)
{
unsigned long ptr_addr;
freeptr_t p;
object = kasan_reset_tag(object);
ptr_addr = (unsigned long)object + s->offset;
p = *(freeptr_t *)(ptr_addr);
return freelist_ptr_decode(s, p, ptr_addr);
}
#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;
freeptr_t 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, (freeptr_t *)freepointer_addr, sizeof(p));
return freelist_ptr_decode(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);
*(freeptr_t *)freeptr_addr = freelist_ptr_encode(s, fp, freeptr_addr);
}
/*
* 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;
}
/* 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;
}
static inline unsigned int slub_get_cpu_partial(struct kmem_cache *s)
{
return s->cpu_partial_slabs;
}
#else
static inline void
slub_set_cpu_partial(struct kmem_cache *s, unsigned int nr_objects)
{
}
static inline unsigned int slub_get_cpu_partial(struct kmem_cache *s)
{
return 0;
}
#endif /* CONFIG_SLUB_CPU_PARTIAL */
/*
* Per slab locking using the pagelock
*/
static __always_inline void slab_lock(struct slab *slab)
{
bit_spin_lock(PG_locked, &slab->__page_flags);
}
static __always_inline void slab_unlock(struct slab *slab)
{
bit_spin_unlock(PG_locked, &slab->__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;
}
/*
* 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);
unsigned int kasan_meta_size;
if (!slub_debug_orig_size(s))
return;
/*
* KASAN can save its free meta data inside of the object at offset 0.
* If this meta data size is larger than 'orig_size', it will overlap
* the data redzone in [orig_size+1, object_size]. Thus, we adjust
* 'orig_size' to be as at least as big as KASAN's meta data.
*/
kasan_meta_size = kasan_metadata_size(s, true);
if (kasan_meta_size > orig_size)
orig_size = kasan_meta_size;
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;
}
#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;
}
static bool slab_in_kunit_test(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;
kunit_put_resource(resource);
return true;
}
#else
static inline bool slab_add_kunit_errors(void) { return false; }
static inline bool slab_in_kunit_test(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();
kmsan_disable_current();
}
static inline void metadata_access_disable(void)
{
kmsan_enable_current();
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();
}
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)
{
pr_err("Slab 0x%p objects=%u used=%u fp=0x%p flags=%pGp\n",
slab, slab->objects, slab->inuse, slab->freelist,
&slab->__page_flags);
}
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) {
/*
* Here and below, avoid overwriting the KMSAN shadow. Keeping
* the shadow makes it possible to distinguish uninit-value
* from use-after-free.
*/
memset_no_sanitize_memory(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_no_sanitize_memory(p, POISON_FREE, poison_size - 1);
memset_no_sanitize_memory(p + poison_size - 1, POISON_END, 1);
}
if (s->flags & SLAB_RED_ZONE)
memset_no_sanitize_memory(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);
}
#ifdef CONFIG_KMSAN
#define pad_check_attributes noinline __no_kmsan_checks
#else
#define pad_check_attributes
#endif
static pad_check_attributes 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);
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 (SLUB_RED_INACTIVE) for inactive objects and with
* 0xcc (SLUB_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 pad_check_attributes 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, kasan_meta_size;
int ret = 1;
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))
ret = 0;
if (!check_bytes_and_report(s, slab, object, "Right Redzone",
endobject, val, s->inuse - s->object_size))
ret = 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)) {
ret = 0;
}
}
} else {
if ((s->flags & SLAB_POISON) && s->object_size < s->inuse) {
if (!check_bytes_and_report(s, slab, p, "Alignment padding",
endobject, POISON_INUSE,
s->inuse - s->object_size))
ret = 0;
}
}
if (s->flags & SLAB_POISON) {
if (val != SLUB_RED_ACTIVE && (s->flags & __OBJECT_POISON)) {
/*
* KASAN can save its free meta data inside of the
* object at offset 0. Thus, skip checking the part of
* the redzone that overlaps with the meta data.
*/
kasan_meta_size = kasan_metadata_size(s, true);
if (kasan_meta_size < s->object_size - 1 &&
!check_bytes_and_report(s, slab, p, "Poison",
p + kasan_meta_size, POISON_FREE,
s->object_size - kasan_meta_size - 1))
ret = 0;
if (kasan_meta_size < s->object_size &&
!check_bytes_and_report(s, slab, p, "End Poison",
p + s->object_size - 1, POISON_END, 1))
ret = 0;
}
/*
* check_pad_bytes cleans up on its own.
*/
if (!check_pad_bytes(s, slab, p))
ret = 0;
}
/*
* Cannot check freepointer while object is allocated if
* object and freepointer overlap.
*/
if ((freeptr_outside_object(s) || val != SLUB_RED_ACTIVE) &&
!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);
ret = 0;
}
if (!ret && !slab_in_kunit_test()) {
print_trailer(s, slab, object);
add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
}
return ret;
}
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);
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 slab_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("slab_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
* slab_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("slab_debug", setup_slub_debug);
__setup_param("slub_debug", slub_debug, setup_slub_debug, 0);
/*
* kmem_cache_flags - apply debugging options to the cache
* @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.
* slab_debug=<Debug-Options>,<slab name1>,<slab name2> ...
* then only the select slabs will receive the debug option(s).
*/
slab_flags_t kmem_cache_flags(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(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 */
#ifdef CONFIG_SLAB_OBJ_EXT
#ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG
static inline void mark_objexts_empty(struct slabobj_ext *obj_exts)
{
struct slabobj_ext *slab_exts;
struct slab *obj_exts_slab;
obj_exts_slab = virt_to_slab(obj_exts);
slab_exts = slab_obj_exts(obj_exts_slab);
if (slab_exts) {
unsigned int offs = obj_to_index(obj_exts_slab->slab_cache,
obj_exts_slab, obj_exts);
/* codetag should be NULL */
WARN_ON(slab_exts[offs].ref.ct);
set_codetag_empty(&slab_exts[offs].ref);
}
}
static inline void mark_failed_objexts_alloc(struct slab *slab)
{
slab->obj_exts = OBJEXTS_ALLOC_FAIL;
}
static inline void handle_failed_objexts_alloc(unsigned long obj_exts,
struct slabobj_ext *vec, unsigned int objects)
{
/*
* If vector previously failed to allocate then we have live
* objects with no tag reference. Mark all references in this
* vector as empty to avoid warnings later on.
*/
if (obj_exts & OBJEXTS_ALLOC_FAIL) {
unsigned int i;
for (i = 0; i < objects; i++)
set_codetag_empty(&vec[i].ref);
}
}
#else /* CONFIG_MEM_ALLOC_PROFILING_DEBUG */
static inline void mark_objexts_empty(struct slabobj_ext *obj_exts) {}
static inline void mark_failed_objexts_alloc(struct slab *slab) {}
static inline void handle_failed_objexts_alloc(unsigned long obj_exts,
struct slabobj_ext *vec, unsigned int objects) {}
#endif /* CONFIG_MEM_ALLOC_PROFILING_DEBUG */
/*
* The allocated objcg pointers array is not accounted directly.
* Moreover, it should not come from DMA buffer and is not readily
* reclaimable. So those GFP bits should be masked off.
*/
#define OBJCGS_CLEAR_MASK (__GFP_DMA | __GFP_RECLAIMABLE | \
__GFP_ACCOUNT | __GFP_NOFAIL)
int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s,
gfp_t gfp, bool new_slab)
{
unsigned int objects = objs_per_slab(s, slab);
unsigned long new_exts;
unsigned long old_exts;
struct slabobj_ext *vec;
gfp &= ~OBJCGS_CLEAR_MASK;
/* Prevent recursive extension vector allocation */
gfp |= __GFP_NO_OBJ_EXT;
vec = kcalloc_node(objects, sizeof(struct slabobj_ext), gfp,
slab_nid(slab));
if (!vec) {
/* Mark vectors which failed to allocate */
if (new_slab)
mark_failed_objexts_alloc(slab);
return -ENOMEM;
}
new_exts = (unsigned long)vec;
#ifdef CONFIG_MEMCG
new_exts |= MEMCG_DATA_OBJEXTS;
#endif
old_exts = READ_ONCE(slab->obj_exts);
handle_failed_objexts_alloc(old_exts, vec, objects);
if (new_slab) {
/*
* If the slab is brand new and nobody can yet access its
* obj_exts, no synchronization is required and obj_exts can
* be simply assigned.
*/
slab->obj_exts = new_exts;
} else if ((old_exts & ~OBJEXTS_FLAGS_MASK) ||
cmpxchg(&slab->obj_exts, old_exts, new_exts) != old_exts) {
/*
* If the slab is already in use, somebody can allocate and
* assign slabobj_exts in parallel. In this case the existing
* objcg vector should be reused.
*/
mark_objexts_empty(vec);
kfree(vec);
return 0;
}
kmemleak_not_leak(vec);
return 0;
}
static inline void free_slab_obj_exts(struct slab *slab)
{
struct slabobj_ext *obj_exts;
obj_exts = slab_obj_exts(slab);
if (!obj_exts)
return;
/*
* obj_exts was created with __GFP_NO_OBJ_EXT flag, therefore its
* corresponding extension will be NULL. alloc_tag_sub() will throw a
* warning if slab has extensions but the extension of an object is
* NULL, therefore replace NULL with CODETAG_EMPTY to indicate that
* the extension for obj_exts is expected to be NULL.
*/
mark_objexts_empty(obj_exts);
kfree(obj_exts);
slab->obj_exts = 0;
}
static inline bool need_slab_obj_ext(void)
{
if (mem_alloc_profiling_enabled())
return true;
/*
* CONFIG_MEMCG creates vector of obj_cgroup objects conditionally
* inside memcg_slab_post_alloc_hook. No other users for now.
*/
return false;
}
#else /* CONFIG_SLAB_OBJ_EXT */
static int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s,
gfp_t gfp, bool new_slab)
{
return 0;
}
static inline void free_slab_obj_exts(struct slab *slab)
{
}
static inline bool need_slab_obj_ext(void)
{
return false;
}
#endif /* CONFIG_SLAB_OBJ_EXT */
#ifdef CONFIG_MEM_ALLOC_PROFILING
static inline struct slabobj_ext *
prepare_slab_obj_exts_hook(struct kmem_cache *s, gfp_t flags, void *p)
{
struct slab *slab;
if (!p)
return NULL;
if (s->flags & (SLAB_NO_OBJ_EXT | SLAB_NOLEAKTRACE))
return NULL;
if (flags & __GFP_NO_OBJ_EXT)
return NULL;
slab = virt_to_slab(p);
if (!slab_obj_exts(slab) &&
WARN(alloc_slab_obj_exts(slab, s, flags, false),
"%s, %s: Failed to create slab extension vector!\n",
__func__, s->name))
return NULL;
return slab_obj_exts(slab) + obj_to_index(s, slab, p);
}
static inline void
alloc_tagging_slab_alloc_hook(struct kmem_cache *s, void *object, gfp_t flags)
{
if (need_slab_obj_ext()) {
struct slabobj_ext *obj_exts;
obj_exts = prepare_slab_obj_exts_hook(s, flags, object);
/*
* Currently obj_exts is used only for allocation profiling.
* If other users appear then mem_alloc_profiling_enabled()
* check should be added before alloc_tag_add().
*/
if (likely(obj_exts))
alloc_tag_add(&obj_exts->ref, current->alloc_tag, s->size);
}
}
static inline void
alloc_tagging_slab_free_hook(struct kmem_cache *s, struct slab *slab, void **p,
int objects)
{
struct slabobj_ext *obj_exts;
int i;
if (!mem_alloc_profiling_enabled())
return;
/* slab->obj_exts might not be NULL if it was created for MEMCG accounting. */
if (s->flags & (SLAB_NO_OBJ_EXT | SLAB_NOLEAKTRACE))
return;
obj_exts = slab_obj_exts(slab);
if (!obj_exts)
return;
for (i = 0; i < objects; i++) {
unsigned int off = obj_to_index(s, slab, p[i]);
alloc_tag_sub(&obj_exts[off].ref, s->size);
}
}
#else /* CONFIG_MEM_ALLOC_PROFILING */
static inline void
alloc_tagging_slab_alloc_hook(struct kmem_cache *s, void *object, gfp_t flags)
{
}
static inline void
alloc_tagging_slab_free_hook(struct kmem_cache *s, struct slab *slab, void **p,
int objects)
{
}
#endif /* CONFIG_MEM_ALLOC_PROFILING */
#ifdef CONFIG_MEMCG
static void memcg_alloc_abort_single(struct kmem_cache *s, void *object);
static __fastpath_inline
bool memcg_slab_post_alloc_hook(struct kmem_cache *s, struct list_lru *lru,
gfp_t flags, size_t size, void **p)
{
if (likely(!memcg_kmem_online()))
return true;
if (likely(!(flags & __GFP_ACCOUNT) && !(s->flags & SLAB_ACCOUNT)))
return true;
if (likely(__memcg_slab_post_alloc_hook(s, lru, flags, size, p)))
return true;
if (likely(size == 1)) {
memcg_alloc_abort_single(s, *p);
*p = NULL;
} else {
kmem_cache_free_bulk(s, size, p);
}
return false;
}
static __fastpath_inline
void memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab, void **p,
int objects)
{
struct slabobj_ext *obj_exts;
if (!memcg_kmem_online())
return;
obj_exts = slab_obj_exts(slab);
if (likely(!obj_exts))
return;
__memcg_slab_free_hook(s, slab, p, objects, obj_exts);
}
static __fastpath_inline
bool memcg_slab_post_charge(void *p, gfp_t flags)
{
struct slabobj_ext *slab_exts;
struct kmem_cache *s;
struct folio *folio;
struct slab *slab;
unsigned long off;
folio = virt_to_folio(p);
if (!folio_test_slab(folio)) {
return folio_memcg_kmem(folio) ||
(__memcg_kmem_charge_page(folio_page(folio, 0), flags,
folio_order(folio)) == 0);
}
slab = folio_slab(folio);
s = slab->slab_cache;
/*
* Ignore KMALLOC_NORMAL cache to avoid possible circular dependency
* of slab_obj_exts being allocated from the same slab and thus the slab
* becoming effectively unfreeable.
*/
if (is_kmalloc_normal(s))
return true;
/* Ignore already charged objects. */
slab_exts = slab_obj_exts(slab);
if (slab_exts) {
off = obj_to_index(s, slab, p);
if (unlikely(slab_exts[off].objcg))
return true;
}
return __memcg_slab_post_alloc_hook(s, NULL, flags, 1, &p);
}
#else /* CONFIG_MEMCG */
static inline bool memcg_slab_post_alloc_hook(struct kmem_cache *s,
struct list_lru *lru,
gfp_t flags, size_t size,
void **p)
{
return true;
}
static inline void memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab,
void **p, int objects)
{
}
static inline bool memcg_slab_post_charge(void *p, gfp_t flags)
{
return true;
}
#endif /* CONFIG_MEMCG */
#ifdef CONFIG_SLUB_RCU_DEBUG
static void slab_free_after_rcu_debug(struct rcu_head *rcu_head);
struct rcu_delayed_free {
struct rcu_head head;
void *object;
};
#endif
/*
* Hooks for other subsystems that check memory allocations. In a typical
* production configuration these hooks all should produce no code at all.
*
* Returns true if freeing of the object can proceed, false if its reuse
* was delayed by CONFIG_SLUB_RCU_DEBUG or KASAN quarantine, or it was returned
* to KFENCE.
*/
static __always_inline
bool slab_free_hook(struct kmem_cache *s, void *x, bool init,
bool after_rcu_delay)
{
/* Are the object contents still accessible? */
bool still_accessible = (s->flags & SLAB_TYPESAFE_BY_RCU) && !after_rcu_delay;
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 (!still_accessible)
__kcsan_check_access(x, s->object_size,
KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ASSERT);
if (kfence_free(x))
return false;
/*
* Give KASAN a chance to notice an invalid free operation before we
* modify the object.
*/
if (kasan_slab_pre_free(s, x))
return false;
#ifdef CONFIG_SLUB_RCU_DEBUG
if (still_accessible) {
struct rcu_delayed_free *delayed_free;
delayed_free = kmalloc(sizeof(*delayed_free), GFP_NOWAIT);
if (delayed_free) {
/*
* Let KASAN track our call stack as a "related work
* creation", just like if the object had been freed
* normally via kfree_rcu().
* We have to do this manually because the rcu_head is
* not located inside the object.
*/
kasan_record_aux_stack_noalloc(x);
delayed_free->object = x;
call_rcu(&delayed_free->head, slab_free_after_rcu_debug);
return false;
}
}
#endif /* CONFIG_SLUB_RCU_DEBUG */
/*
* 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.
*
* The object's freepointer is also avoided if stored outside the
* object.
*/
if (unlikely(init)) {
int rsize;
unsigned int inuse, orig_size;
inuse = get_info_end(s);
orig_size = get_orig_size(s, x);
if (!kasan_has_integrated_init())
memset(kasan_reset_tag(x), 0, orig_size);
rsize = (s->flags & SLAB_RED_ZONE) ? s->red_left_pad : 0;
memset((char *)kasan_reset_tag(x) + inuse, 0,
s->size - inuse - rsize);
/*
* Restore orig_size, otherwize kmalloc redzone overwritten
* would be reported
*/
set_orig_size(s, x, orig_size);
}
/* KASAN might put x into memory quarantine, delaying its reuse. */
return !kasan_slab_free(s, x, init, still_accessible);
}
static __fastpath_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;
bool init;
if (is_kfence_address(next)) {
slab_free_hook(s, next, false, false);
return false;
}
/* Head and tail of the reconstructed freelist */
*head = NULL;
*tail = NULL;
init = slab_want_init_on_free(s);
do {
object = next;
next = get_freepointer(s, object);
/* If object's reuse doesn't have to be delayed */
if (likely(slab_free_hook(s, object, init, false))) {
/* 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);
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_new_object(s, object);
s->ctor(object);
kasan_poison_new_object(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,
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
* page might be smaller than the usual size defined by the cache.
*/
do {
idx = s->random_seq[*pos];
*pos += 1;
if (*pos >= freelist_count)
*pos = 0;
} while (unlikely(idx >= page_limit));
return (char *)start + idx;
}
/* Shuffle the single linked freelist based on a random pre-computed sequence */
static bool shuffle_freelist(struct kmem_cache *s, struct slab *slab)
{
void *start;
void *cur;
void *next;
unsigned long idx, pos, page_limit, freelist_count;
if (slab->objects < 2 || !s->random_seq)
return false;
freelist_count = oo_objects(s->oo);
pos = get_random_u32_below(freelist_count);
page_limit = slab->objects * s->size;
start = fixup_red_left(s, slab_address(slab));
/* First entry is used as the base of the freelist */
cur = next_freelist_entry(s, &pos, start, page_limit, freelist_count);
cur = setup_object(s, cur);
slab->freelist = cur;
for (idx = 1; idx < slab->objects; idx++) {
next = next_freelist_entry(s, &pos, start, page_limit,
freelist_count);
next = setup_object(s, next);
set_freepointer(s, cur, next);
cur = next;
}
set_freepointer(s, cur, NULL);
return true;
}
#else
static inline int init_cache_random_seq(struct kmem_cache *s)
{
return 0;
}
static inline void init_freelist_randomization(void) { }
static inline bool shuffle_freelist(struct kmem_cache *s, struct slab *slab)
{
return false;
}
#endif /* CONFIG_SLAB_FREELIST_RANDOM */
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))
alloc_slab_obj_exts(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() || need_slab_obj_ext())
free_slab_obj_exts(slab);
mod_node_page_state(slab_pgdat(slab), cache_vmstat_idx(s),
-(PAGE_SIZE << order));
}
static struct slab *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
{
struct slab *slab;
struct kmem_cache_order_objects oo = s->oo;
gfp_t alloc_gfp;
void *start, *p, *next;
int idx;
bool shuffle;
flags &= gfp_allowed_mask;
flags |= s->allocflags;
/*
* Let the initial higher-order allocation fail under memory pressure
* so we fall-back to the minimum order allocation.
*/
alloc_gfp = (flags | __GFP_NOWARN | __GFP_NORETRY) & ~__GFP_NOFAIL;
if ((alloc_gfp & __GFP_DIRECT_RECLAIM) && oo_order(oo) > oo_order(s->min))
alloc_gfp = (alloc_gfp | __GFP_NOMEMALLOC) & ~__GFP_RECLAIM;
slab = alloc_slab_page(alloc_gfp, node, oo);
if (unlikely(!slab)) {
oo = s->min;
alloc_gfp = flags;
/*
* Allocation may have failed due to fragmentation.
* Try a lower order alloc if possible
*/
slab = alloc_slab_page(alloc_gfp, node, oo);
if (unlikely(!slab))
return NULL;
stat(s, ORDER_FALLBACK);
}
slab->objects = oo_objects(oo);
slab->inuse = 0;
slab->frozen = 0;
account_slab(slab, oo_order(oo), s, flags);
slab->slab_cache = s;
kasan_poison_slab(slab);
start = slab_address(slab);
setup_slab_debug(s, slab, start);
shuffle = shuffle_freelist(s, slab);
if (!shuffle) {
start = fixup_red_left(s, start);
start = setup_object(s, start);
slab->freelist = start;
for (idx = 0, p = start; idx < slab->objects - 1; idx++) {
next = p + s->size;
next = setup_object(s, next);
set_freepointer(s, p, next);
p = next;
}
set_freepointer(s, p, NULL);
}
return slab;
}
static struct slab *new_slab(struct kmem_cache *s, gfp_t flags, int node)
{
if (unlikely(flags & GFP_SLAB_BUG_MASK))
flags = kmalloc_fix_flags(flags);
WARN_ON_ONCE(s->ctor && (flags & __GFP_ZERO));
return allocate_slab(s,
flags & (GFP_RECLAIM_MASK | GFP_CONSTRAINT_MASK), node);
}
static void __free_slab(struct kmem_cache *s, struct slab *slab)
{
struct folio *folio = slab_folio(slab);
int order = folio_order(folio);
int pages = 1 << order;
__slab_clear_pfmemalloc(slab);
folio->mapping = NULL;
/* Make the mapping reset visible before clearing the flag */
smp_wmb();
__folio_clear_slab(folio);
mm_account_reclaimed_pages(pages);
unaccount_slab(slab, order, s);
__free_pages(&folio->page, order);
}
static void rcu_free_slab(struct rcu_head *h)
{
struct slab *slab = container_of(h, struct slab, rcu_head);
__free_slab(slab->slab_cache, slab);
}
static void free_slab(struct kmem_cache *s, struct slab *slab)
{
if (kmem_cache_debug_flags(s, SLAB_CONSISTENCY_CHECKS)) {
void *p;
slab_pad_check(s, slab);
for_each_object(p, s, slab_address(slab), slab->objects)
check_object(s, slab, p, SLUB_RED_INACTIVE);
}
if (unlikely(s->flags & SLAB_TYPESAFE_BY_RCU))
call_rcu(&slab->rcu_head, rcu_free_slab);
else
__free_slab(s, slab);
}
static void discard_slab(struct kmem_cache *s, struct slab *slab)
{
dec_slabs_node(s, slab_nid(slab), slab->objects);
free_slab(s, slab);
}
/*
* SLUB reuses PG_workingset bit to keep track of whether it's on
* the per-node partial list.
*/
static inline bool slab_test_node_partial(const struct slab *slab)
{
return folio_test_workingset(slab_folio(slab));
}
static inline void slab_set_node_partial(struct slab *slab)
{
set_bit(PG_workingset, folio_flags(slab_folio(slab), 0));
}
static inline void slab_clear_node_partial(struct slab *slab)
{
clear_bit(PG_workingset, folio_flags(slab_folio(slab), 0));
}
/*
* Management of partially allocated slabs.
*/
static inline void
__add_partial(struct kmem_cache_node *n, struct slab *slab, int tail)
{
n->nr_partial++;
if (tail == DEACTIVATE_TO_TAIL)
list_add_tail(&slab->slab_list, &n->partial);
else
list_add(&slab->slab_list, &n->partial);
slab_set_node_partial(slab);
}
static inline void add_partial(struct kmem_cache_node *n,
struct slab *slab, int tail)
{
lockdep_assert_held(&n->list_lock);
__add_partial(n, slab, tail);
}
static inline void remove_partial(struct kmem_cache_node *n,
struct slab *slab)
{
lockdep_assert_held(&n->list_lock);
list_del(&slab->slab_list);
slab_clear_node_partial(slab);
n->nr_partial--;
}
/*
* Called only for kmem_cache_debug() caches instead of remove_partial(), with a
* slab from the n->partial list. Remove only a single object from the slab, do
* the alloc_debug_processing() checks and leave the slab on the list, or move
* it to full list if it was the last free object.
*/
static void *alloc_single_from_partial(struct kmem_cache *s,
struct kmem_cache_node *n, struct slab *slab, int orig_size)
{
void *object;
lockdep_assert_held(&n->list_lock);
object = slab->freelist;
slab->freelist = get_freepointer(s, object);
slab->inuse++;
if (!alloc_debug_processing(s, slab, object, orig_size)) {
remove_partial(n, slab);
return NULL;
}
if (slab->inuse == slab->objects) {
remove_partial(n, slab);
add_full(s, n, slab);
}
return object;
}
/*
* Called only for kmem_cache_debug() caches to allocate from a freshly
* allocated slab. Allocate a single object instead of whole freelist
* and put the slab to the partial (or full) list.
*/
static void *alloc_single_from_new_slab(struct kmem_cache *s,
struct slab *slab, int orig_size)
{
int nid = slab_nid(slab);
struct kmem_cache_node *n = get_node(s, nid);
unsigned long flags;
void *object;
object = slab->freelist;
slab->freelist = get_freepointer(s, object);
slab->inuse = 1;
if (!alloc_debug_processing(s, slab, object, orig_size))
/*
* It's not really expected that this would fail on a
* freshly allocated slab, but a concurrent memory
* corruption in theory could cause that.
*/
return NULL;
spin_lock_irqsave(&n->list_lock, flags);
if (slab->inuse == slab->objects)
add_full(s, n, slab);
else
add_partial(n, slab, DEACTIVATE_TO_HEAD);
inc_slabs_node(s, nid, slab->objects);
spin_unlock_irqrestore(&n->list_lock, flags);
return object;
}
#ifdef CONFIG_SLUB_CPU_PARTIAL
static void put_cpu_partial(struct kmem_cache *s, struct slab *slab, int drain);
#else
static inline void put_cpu_partial(struct kmem_cache *s, struct slab *slab,
int drain) { }
#endif
static inline bool pfmemalloc_match(struct slab *slab, gfp_t gfpflags);
/*
* Try to allocate a partial slab from a specific node.
*/
static struct slab *get_partial_node(struct kmem_cache *s,
struct kmem_cache_node *n,
struct partial_context *pc)
{
struct slab *slab, *slab2, *partial = NULL;
unsigned long flags;
unsigned int partial_slabs = 0;
/*
* Racy check. If we mistakenly see no partial slabs then we
* just allocate an empty slab. If we mistakenly try to get a
* partial slab and there is none available then get_partial()
* will return NULL.
*/
if (!n || !n->nr_partial)
return NULL;
spin_lock_irqsave(&n->list_lock, flags);
list_for_each_entry_safe(slab, slab2, &n->partial, slab_list) {
if (!pfmemalloc_match(slab, pc->flags))
continue;
if (IS_ENABLED(CONFIG_SLUB_TINY) || kmem_cache_debug(s)) {
void *object = alloc_single_from_partial(s, n, slab,
pc->orig_size);
if (object) {
partial = slab;
pc->object = object;
break;
}
continue;
}
remove_partial(n, slab);
if (!partial) {
partial = slab;
stat(s, ALLOC_FROM_PARTIAL);
if ((slub_get_cpu_partial(s) == 0)) {
break;
}
} else {
put_cpu_partial(s, slab, 0);
stat(s, CPU_PARTIAL_NODE);
if (++partial_slabs > slub_get_cpu_partial(s) / 2) {
break;
}
}
}
spin_unlock_irqrestore(&n->list_lock, flags);
return partial;
}
/*
* Get a slab from somewhere. Search in increasing NUMA distances.
*/
static struct slab *get_any_partial(struct kmem_cache *s,
struct partial_context *pc)
{
#ifdef CONFIG_NUMA
struct zonelist *zonelist;
struct zoneref *z;
struct zone *zone;
enum zone_type highest_zoneidx = gfp_zone(pc->flags);
struct slab *slab;
unsigned int cpuset_mems_cookie;
/*
* The defrag ratio allows a configuration of the tradeoffs between
* inter node defragmentation and node local allocations. A lower
* defrag_ratio increases the tendency to do local allocations
* instead of attempting to obtain partial slabs from other nodes.
*
* If the defrag_ratio is set to 0 then kmalloc() always
* returns node local objects. If the ratio is higher then kmalloc()
* may return off node objects because partial slabs are obtained
* from other nodes and filled up.
*
* If /sys/kernel/slab/xx/remote_node_defrag_ratio is set to 100
* (which makes defrag_ratio = 1000) then every (well almost)
* allocation will first attempt to defrag slab caches on other nodes.
* This means scanning over all nodes to look for partial slabs which
* may be expensive if we do it every time we are trying to find a slab
* with available objects.
*/
if (!s->remote_node_defrag_ratio ||
get_cycles() % 1024 > s->remote_node_defrag_ratio)
return NULL;
do {
cpuset_mems_cookie = read_mems_allowed_begin();
zonelist = node_zonelist(mempolicy_slab_node(), pc->flags);
for_each_zone_zonelist(zone, z, zonelist, highest_zoneidx) {
struct kmem_cache_node *n;
n = get_node(s, zone_to_nid(zone));
if (n && cpuset_zone_allowed(zone, pc->flags) &&
n->nr_partial > s->min_partial) {
slab = get_partial_node(s, n, pc);
if (slab) {
/*
* Don't check read_mems_allowed_retry()
* here - if mems_allowed was updated in
* parallel, that was a harmless race
* between allocation and the cpuset
* update
*/
return slab;
}
}
}
} while (read_mems_allowed_retry(cpuset_mems_cookie));
#endif /* CONFIG_NUMA */
return NULL;
}
/*
* Get a partial slab, lock it and return it.
*/
static struct slab *get_partial(struct kmem_cache *s, int node,
struct partial_context *pc)
{
struct slab *slab;
int searchnode = node;
if (node == NUMA_NO_NODE)
searchnode = numa_mem_id();
slab = get_partial_node(s, get_node(s, searchnode), pc);
if (slab || (node != NUMA_NO_NODE && (pc->flags & __GFP_THISNODE)))
return slab;
return get_any_partial(s, pc);
}
#ifndef CONFIG_SLUB_TINY
#ifdef CONFIG_PREEMPTION
/*
* Calculate the next globally unique transaction for disambiguation
* during cmpxchg. The transactions start with the cpu number and are then
* incremented by CONFIG_NR_CPUS.
*/
#define TID_STEP roundup_pow_of_two(CONFIG_NR_CPUS)
#else
/*
* No preemption supported therefore also no need to check for
* different cpus.
*/
#define TID_STEP 1
#endif /* CONFIG_PREEMPTION */
static inline unsigned long next_tid(unsigned long tid)
{
return tid + TID_STEP;
}
#ifdef SLUB_DEBUG_CMPXCHG
static inline unsigned int tid_to_cpu(unsigned long tid)
{
return tid % TID_STEP;
}
static inline unsigned long tid_to_event(unsigned long tid)
{
return tid / TID_STEP;
}
#endif
static inline unsigned int init_tid(int cpu)
{
return cpu;
}
static inline void note_cmpxchg_failure(const char *n,
const struct kmem_cache *s, unsigned long tid)
{
#ifdef SLUB_DEBUG_CMPXCHG
unsigned long actual_tid = __this_cpu_read(s->cpu_slab->tid);
pr_info("%s %s: cmpxchg redo ", n, s->name);
#ifdef CONFIG_PREEMPTION
if (tid_to_cpu(tid) != tid_to_cpu(actual_tid))
pr_warn("due to cpu change %d -> %d\n",
tid_to_cpu(tid), tid_to_cpu(actual_tid));
else
#endif
if (tid_to_event(tid) != tid_to_event(actual_tid))
pr_warn("due to cpu running other code. Event %ld->%ld\n",
tid_to_event(tid), tid_to_event(actual_tid));
else
pr_warn("for unknown reason: actual=%lx was=%lx target=%lx\n",
actual_tid, tid, next_tid(tid));
#endif
stat(s, CMPXCHG_DOUBLE_CPU_FAIL);
}
static void init_kmem_cache_cpus(struct kmem_cache *s)
{
int cpu;
struct kmem_cache_cpu *c;
for_each_possible_cpu(cpu) {
c = per_cpu_ptr(s->cpu_slab, cpu);
local_lock_init(&c->lock);
c->tid = init_tid(cpu);
}
}
/*
* Finishes removing the cpu slab. Merges cpu's freelist with slab's freelist,
* unfreezes the slabs and puts it on the proper list.
* Assumes the slab has been already safely taken away from kmem_cache_cpu
* by the caller.
*/
static void deactivate_slab(struct kmem_cache *s, struct slab *slab,
void *freelist)
{
struct kmem_cache_node *n = get_node(s, slab_nid(slab));
int free_delta = 0;
void *nextfree, *freelist_iter, *freelist_tail;
int tail = DEACTIVATE_TO_HEAD;
unsigned long flags = 0;
struct slab new;
struct slab old;
if (READ_ONCE(slab->freelist)) {
stat(s, DEACTIVATE_REMOTE_FREES);
tail = DEACTIVATE_TO_TAIL;
}
/*
* Stage one: Count the objects on cpu's freelist as free_delta and
* remember the last object in freelist_tail for later splicing.
*/
freelist_tail = NULL;
freelist_iter = freelist;
while (freelist_iter) {
nextfree = get_freepointer(s, freelist_iter);
/*
* If 'nextfree' is invalid, it is possible that the object at
* 'freelist_iter' is already corrupted. So isolate all objects
* starting at 'freelist_iter' by skipping them.
*/
if (freelist_corrupted(s, slab, &freelist_iter, nextfree))
break;
freelist_tail = freelist_iter;
free_delta++;
freelist_iter = nextfree;
}
/*
* Stage two: Unfreeze the slab while splicing the per-cpu
* freelist to the head of slab's freelist.
*/
do {
old.freelist = READ_ONCE(slab->freelist);
old.counters = READ_ONCE(slab->counters);
VM_BUG_ON(!old.frozen);
/* Determine target state of the slab */
new.counters = old.counters;
new.frozen = 0;
if (freelist_tail) {
new.inuse -= free_delta;
set_freepointer(s, freelist_tail, old.freelist);
new.freelist = freelist;
} else {
new.freelist = old.freelist;
}
} while (!slab_update_freelist(s, slab,
old.freelist, old.counters,
new.freelist, new.counters,
"unfreezing slab"));
/*
* Stage three: Manipulate the slab list based on the updated state.
*/
if (!new.inuse && n->nr_partial >= s->min_partial) {
stat(s, DEACTIVATE_EMPTY);
discard_slab(s, slab);
stat(s, FREE_SLAB);
} else if (new.freelist) {
spin_lock_irqsave(&n->list_lock, flags);
add_partial(n, slab, tail);
spin_unlock_irqrestore(&n->list_lock, flags);
stat(s, tail);
} else {
stat(s, DEACTIVATE_FULL);
}
}
#ifdef CONFIG_SLUB_CPU_PARTIAL
static void __put_partials(struct kmem_cache *s, struct slab *partial_slab)
{
struct kmem_cache_node *n = NULL, *n2 = NULL;
struct slab *slab, *slab_to_discard = NULL;
unsigned long flags = 0;
while (partial_slab) {
slab = partial_slab;
partial_slab = slab->next;
n2 = get_node(s, slab_nid(slab));
if (n != n2) {
if (n)
spin_unlock_irqrestore(&n->list_lock, flags);
n = n2;
spin_lock_irqsave(&n->list_lock, flags);
}
if (unlikely(!slab->inuse && n->nr_partial >= s->min_partial)) {
slab->next = slab_to_discard;
slab_to_discard = slab;
} else {
add_partial(n, slab, DEACTIVATE_TO_TAIL);
stat(s, FREE_ADD_PARTIAL);
}
}
if (n)
spin_unlock_irqrestore(&n->list_lock, flags);
while (slab_to_discard) {
slab = slab_to_discard;
slab_to_discard = slab_to_discard->next;
stat(s, DEACTIVATE_EMPTY);
discard_slab(s, slab);
stat(s, FREE_SLAB);
}
}
/*
* Put all the cpu partial slabs to the node partial list.
*/
static void put_partials(struct kmem_cache *s)
{
struct slab *partial_slab;
unsigned long flags;
local_lock_irqsave(&s->cpu_slab->lock, flags);
partial_slab = this_cpu_read(s->cpu_slab->partial);
this_cpu_write(s->cpu_slab->partial, NULL);
local_unlock_irqrestore(&s->cpu_slab->lock, flags);
if (partial_slab)
__put_partials(s, partial_slab);
}
static void put_partials_cpu(struct kmem_cache *s,
struct kmem_cache_cpu *c)
{
struct slab *partial_slab;
partial_slab = slub_percpu_partial(c);
c->partial = NULL;
if (partial_slab)
__put_partials(s, partial_slab);
}
/*
* Put a slab into a partial slab slot if available.
*
* If we did not find a slot then simply move all the partials to the
* per node partial list.
*/
static void put_cpu_partial(struct kmem_cache *s, struct slab *slab, int drain)