6507 lines
161 KiB
C
6507 lines
161 KiB
C
// 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> /* struct reclaim_state */
|
|
#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 */
|
|
#define __CMPXCHG_DOUBLE ((slab_flags_t __force)0x40000000U)
|
|
|
|
/*
|
|
* 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);
|
|
}
|
|
|
|
/*
|
|
* 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 __cmpxchg_double_slab(struct kmem_cache *s, struct slab *slab,
|
|
void *freelist_old, unsigned long counters_old,
|
|
void *freelist_new, unsigned long counters_new,
|
|
const char *n)
|
|
{
|
|
if (USE_LOCKLESS_FAST_PATH())
|
|
lockdep_assert_irqs_disabled();
|
|
#if defined(CONFIG_HAVE_CMPXCHG_DOUBLE) && \
|
|
defined(CONFIG_HAVE_ALIGNED_STRUCT_PAGE)
|
|
if (s->flags & __CMPXCHG_DOUBLE) {
|
|
if (cmpxchg_double(&slab->freelist, &slab->counters,
|
|
freelist_old, counters_old,
|
|
freelist_new, counters_new))
|
|
return true;
|
|
} else
|
|
#endif
|
|
{
|
|
slab_lock(slab);
|
|
if (slab->freelist == freelist_old &&
|
|
slab->counters == counters_old) {
|
|
slab->freelist = freelist_new;
|
|
slab->counters = counters_new;
|
|
slab_unlock(slab);
|
|
return true;
|
|
}
|
|
slab_unlock(slab);
|
|
}
|
|
|
|
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 cmpxchg_double_slab(struct kmem_cache *s, struct slab *slab,
|
|
void *freelist_old, unsigned long counters_old,
|
|
void *freelist_new, unsigned long counters_new,
|
|
const char *n)
|
|
{
|
|
#if defined(CONFIG_HAVE_CMPXCHG_DOUBLE) && \
|
|
defined(CONFIG_HAVE_ALIGNED_STRUCT_PAGE)
|
|
if (s->flags & __CMPXCHG_DOUBLE) {
|
|
if (cmpxchg_double(&slab->freelist, &slab->counters,
|
|
freelist_old, counters_old,
|
|
freelist_new, counters_new))
|
|
return true;
|
|
} else
|
|
#endif
|
|
{
|
|
unsigned long flags;
|
|
|
|
local_irq_save(flags);
|
|
slab_lock(slab);
|
|
if (slab->freelist == freelist_old &&
|
|
slab->counters == counters_old) {
|
|
slab->freelist = freelist_new;
|
|
slab->counters = counters_new;
|
|
slab_unlock(slab);
|
|
local_irq_restore(flags);
|
|
return true;
|
|
}
|
|
slab_unlock(slab);
|
|
local_irq_restore(flags);
|
|
}
|
|
|
|
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);
|
|
}
|
|
|
|
/* Tracking of the number of slabs for debugging purposes */
|
|
static inline unsigned long slabs_node(struct kmem_cache *s, int node)
|
|
{
|
|
struct kmem_cache_node *n = get_node(s, node);
|
|
|
|
return atomic_long_read(&n->nr_slabs);
|
|
}
|
|
|
|
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 slabs_node(struct kmem_cache *s, int node)
|
|
{ return 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
|
|
* 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, slab, &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, slab, &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 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);
|
|
if (current->reclaim_state)
|
|
current->reclaim_state->reclaimed_slab += 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);
|
|
}
|
|
|
|
/*
|
|
* 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);
|
|
}
|
|
|
|
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);
|
|
n->nr_partial--;
|
|
}
|
|
|
|
/*
|
|
* Called only for kmem_cache_debug() caches instead of acquire_slab(), 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;
|
|
}
|
|
|
|
/*
|
|
* Remove slab from the partial list, freeze it and
|
|
* return the pointer to the freelist.
|
|
*
|
|
* Returns a list of objects or NULL if it fails.
|
|
*/
|
|
static inline void *acquire_slab(struct kmem_cache *s,
|
|
struct kmem_cache_node *n, struct slab *slab,
|
|
int mode)
|
|
{
|
|
void *freelist;
|
|
unsigned long counters;
|
|
struct slab new;
|
|
|
|
lockdep_assert_held(&n->list_lock);
|
|
|
|
/*
|
|
* Zap the freelist and set the frozen bit.
|
|
* The old freelist is the list of objects for the
|
|
* per cpu allocation list.
|
|
*/
|
|
freelist = slab->freelist;
|
|
counters = slab->counters;
|
|
new.counters = counters;
|
|
if (mode) {
|
|
new.inuse = slab->objects;
|
|
new.freelist = NULL;
|
|
} else {
|
|
new.freelist = freelist;
|
|
}
|
|
|
|
VM_BUG_ON(new.frozen);
|
|
new.frozen = 1;
|
|
|
|
if (!__cmpxchg_double_slab(s, slab,
|
|
freelist, counters,
|
|
new.freelist, new.counters,
|
|
"acquire_slab"))
|
|
return NULL;
|
|
|
|
remove_partial(n, slab);
|
|
WARN_ON(!freelist);
|
|
return freelist;
|
|
}
|
|
|
|
#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 void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n,
|
|
struct partial_context *pc)
|
|
{
|
|
struct slab *slab, *slab2;
|
|
void *object = 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) {
|
|
void *t;
|
|
|
|
if (!pfmemalloc_match(slab, pc->flags))
|
|
continue;
|
|
|
|
if (IS_ENABLED(CONFIG_SLUB_TINY) || kmem_cache_debug(s)) {
|
|
object = alloc_single_from_partial(s, n, slab,
|
|
pc->orig_size);
|
|
if (object)
|
|
break;
|
|
continue;
|
|
}
|
|
|
|
t = acquire_slab(s, n, slab, object == NULL);
|
|
if (!t)
|
|
break;
|
|
|
|
if (!object) {
|
|
*pc->slab = slab;
|
|
stat(s, ALLOC_FROM_PARTIAL);
|
|
object = t;
|
|
} else {
|
|
put_cpu_partial(s, slab, 0);
|
|
stat(s, CPU_PARTIAL_NODE);
|
|
partial_slabs++;
|
|
}
|
|
#ifdef CONFIG_SLUB_CPU_PARTIAL
|
|
if (!kmem_cache_has_cpu_partial(s)
|
|
|| partial_slabs > s->cpu_partial_slabs / 2)
|
|
break;
|
|
#else
|
|
break;
|
|
#endif
|
|
|
|
}
|
|
spin_unlock_irqrestore(&n->list_lock, flags);
|
|
return object;
|
|
}
|
|
|
|
/*
|
|
* Get a slab from somewhere. Search in increasing NUMA distances.
|
|
*/
|
|
static void *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);
|
|
void *object;
|
|
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) {
|
|
object = get_partial_node(s, n, pc);
|
|
if (object) {
|
|
/*
|
|
* 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 object;
|
|
}
|
|
}
|
|
}
|
|
} while (read_mems_allowed_retry(cpuset_mems_cookie));
|
|
#endif /* CONFIG_NUMA */
|
|
return NULL;
|
|
}
|
|
|
|
/*
|
|
* Get a partial slab, lock it and return it.
|
|
*/
|
|
static void *get_partial(struct kmem_cache *s, int node, struct partial_context *pc)
|
|
{
|
|
void *object;
|
|
int searchnode = node;
|
|
|
|
if (node == NUMA_NO_NODE)
|
|
searchnode = numa_mem_id();
|
|
|
|
object = get_partial_node(s, get_node(s, searchnode), pc);
|
|
if (object || node != NUMA_NO_NODE)
|
|
return object;
|
|
|
|
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)
|
|
{
|
|
enum slab_modes { M_NONE, M_PARTIAL, M_FREE, M_FULL_NOLIST };
|
|
struct kmem_cache_node *n = get_node(s, slab_nid(slab));
|
|
int free_delta = 0;
|
|
enum slab_modes mode = M_NONE;
|
|
void *nextfree, *freelist_iter, *freelist_tail;
|
|
int tail = DEACTIVATE_TO_HEAD;
|
|
unsigned long flags = 0;
|
|
struct slab new;
|
|
struct slab old;
|
|
|
|
if (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.
|
|
*
|
|
* Ensure that the slab is unfrozen while the list presence
|
|
* reflects the actual number of objects during unfreeze.
|
|
*
|
|
* We first perform cmpxchg holding lock and insert to list
|
|
* when it succeed. If there is mismatch then the slab is not
|
|
* unfrozen and number of objects in the slab may have changed.
|
|
* Then release lock and retry cmpxchg again.
|
|
*/
|
|
redo:
|
|
|
|
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;
|
|
if (freelist_tail) {
|
|
new.inuse -= free_delta;
|
|
set_freepointer(s, freelist_tail, old.freelist);
|
|
new.freelist = freelist;
|
|
} else
|
|
new.freelist = old.freelist;
|
|
|
|
new.frozen = 0;
|
|
|
|
if (!new.inuse && n->nr_partial >= s->min_partial) {
|
|
mode = M_FREE;
|
|
} else if (new.freelist) {
|
|
mode = M_PARTIAL;
|
|
/*
|
|
* Taking the spinlock removes the possibility that
|
|
* acquire_slab() will see a slab that is frozen
|
|
*/
|
|
spin_lock_irqsave(&n->list_lock, flags);
|
|
} else {
|
|
mode = M_FULL_NOLIST;
|
|
}
|
|
|
|
|
|
if (!cmpxchg_double_slab(s, slab,
|
|
old.freelist, old.counters,
|
|
new.freelist, new.counters,
|
|
"unfreezing slab")) {
|
|
if (mode == M_PARTIAL)
|
|
spin_unlock_irqrestore(&n->list_lock, flags);
|
|
goto redo;
|
|
}
|
|
|
|
|
|
if (mode == M_PARTIAL) {
|
|
add_partial(n, slab, tail);
|
|
spin_unlock_irqrestore(&n->list_lock, flags);
|
|
stat(s, tail);
|
|
} else if (mode == M_FREE) {
|
|
stat(s, DEACTIVATE_EMPTY);
|
|
discard_slab(s, slab);
|
|
stat(s, FREE_SLAB);
|
|
} else if (mode == M_FULL_NOLIST) {
|
|
stat(s, DEACTIVATE_FULL);
|
|
}
|
|
}
|
|
|
|
#ifdef CONFIG_SLUB_CPU_PARTIAL
|
|
static void __unfreeze_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) {
|
|
struct slab new;
|
|
struct slab old;
|
|
|
|
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);
|
|
}
|
|
|
|
do {
|
|
|
|
old.freelist = slab->freelist;
|
|
old.counters = slab->counters;
|
|
VM_BUG_ON(!old.frozen);
|
|
|
|
new.counters = old.counters;
|
|
new.freelist = old.freelist;
|
|
|
|
new.frozen = 0;
|
|
|
|
} while (!__cmpxchg_double_slab(s, slab,
|
|
old.freelist, old.counters,
|
|
new.freelist, new.counters,
|
|
"unfreezing slab"));
|
|
|
|
if (unlikely(!new.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);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Unfreeze all the cpu partial slabs.
|
|
*/
|
|
static void unfreeze_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)
|
|
__unfreeze_partials(s, partial_slab);
|
|
}
|
|
|
|
static void unfreeze_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)
|
|
__unfreeze_partials(s, partial_slab);
|
|
}
|
|
|
|
/*
|
|
* Put a slab that was just frozen (in __slab_free|get_partial_node) 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)
|
|
{
|
|
struct slab *oldslab;
|
|
struct slab *slab_to_unfreeze = NULL;
|
|
unsigned long flags;
|
|
int slabs = 0;
|
|
|
|
local_lock_irqsave(&s->cpu_slab->lock, flags);
|
|
|
|
oldslab = this_cpu_read(s->cpu_slab->partial);
|
|
|
|
if (oldslab) {
|
|
if (drain && oldslab->slabs >= s->cpu_partial_slabs) {
|
|
/*
|
|
* Partial array is full. Move the existing set to the
|
|
* per node partial list. Postpone the actual unfreezing
|
|
* outside of the critical section.
|
|
*/
|
|
slab_to_unfreeze = oldslab;
|
|
oldslab = NULL;
|
|
} else {
|
|
slabs = oldslab->slabs;
|
|
}
|
|
}
|
|
|
|
slabs++;
|
|
|
|
slab->slabs = slabs;
|
|
slab->next = oldslab;
|
|
|
|
this_cpu_write(s->cpu_slab->partial, slab);
|
|
|
|
local_unlock_irqrestore(&s->cpu_slab->lock, flags);
|
|
|
|
if (slab_to_unfreeze) {
|
|
__unfreeze_partials(s, slab_to_unfreeze);
|
|
stat(s, CPU_PARTIAL_DRAIN);
|
|
}
|
|
}
|
|
|
|
#else /* CONFIG_SLUB_CPU_PARTIAL */
|
|
|
|
static inline void unfreeze_partials(struct kmem_cache *s) { }
|
|
static inline void unfreeze_partials_cpu(struct kmem_cache *s,
|
|
struct kmem_cache_cpu *c) { }
|
|
|
|
#endif /* CONFIG_SLUB_CPU_PARTIAL */
|
|
|
|
static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)
|
|
{
|
|
unsigned long flags;
|
|
struct slab *slab;
|
|
void *freelist;
|
|
|
|
local_lock_irqsave(&s->cpu_slab->lock, flags);
|
|
|
|
slab = c->slab;
|
|
freelist = c->freelist;
|
|
|
|
c->slab = NULL;
|
|
c->freelist = NULL;
|
|
c->tid = next_tid(c->tid);
|
|
|
|
local_unlock_irqrestore(&s->cpu_slab->lock, flags);
|
|
|
|
if (slab) {
|
|
deactivate_slab(s, slab, freelist);
|
|
stat(s, CPUSLAB_FLUSH);
|
|
}
|
|
}
|
|
|
|
static inline void __flush_cpu_slab(struct kmem_cache *s, int cpu)
|
|
{
|
|
struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu);
|
|
void *freelist = c->freelist;
|
|
struct slab *slab = c->slab;
|
|
|
|
c->slab = NULL;
|
|
c->freelist = NULL;
|
|
c->tid = next_tid(c->tid);
|
|
|
|
if (slab) {
|
|
deactivate_slab(s, slab, freelist);
|
|
stat(s, CPUSLAB_FLUSH);
|
|
}
|
|
|
|
unfreeze_partials_cpu(s, c);
|
|
}
|
|
|
|
struct slub_flush_work {
|
|
struct work_struct work;
|
|
struct kmem_cache *s;
|
|
bool skip;
|
|
};
|
|
|
|
/*
|
|
* Flush cpu slab.
|
|
*
|
|
* Called from CPU work handler with migration disabled.
|
|
*/
|
|
static void flush_cpu_slab(struct work_struct *w)
|
|
{
|
|
struct kmem_cache *s;
|
|
struct kmem_cache_cpu *c;
|
|
struct slub_flush_work *sfw;
|
|
|
|
sfw = container_of(w, struct slub_flush_work, work);
|
|
|
|
s = sfw->s;
|
|
c = this_cpu_ptr(s->cpu_slab);
|
|
|
|
if (c->slab)
|
|
flush_slab(s, c);
|
|
|
|
unfreeze_partials(s);
|
|
}
|
|
|
|
static bool has_cpu_slab(int cpu, struct kmem_cache *s)
|
|
{
|
|
struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu);
|
|
|
|
return c->slab || slub_percpu_partial(c);
|
|
}
|
|
|
|
static DEFINE_MUTEX(flush_lock);
|
|
static DEFINE_PER_CPU(struct slub_flush_work, slub_flush);
|
|
|
|
static void flush_all_cpus_locked(struct kmem_cache *s)
|
|
{
|
|
struct slub_flush_work *sfw;
|
|
unsigned int cpu;
|
|
|
|
lockdep_assert_cpus_held();
|
|
mutex_lock(&flush_lock);
|
|
|
|
for_each_online_cpu(cpu) {
|
|
sfw = &per_cpu(slub_flush, cpu);
|
|
if (!has_cpu_slab(cpu, s)) {
|
|
sfw->skip = true;
|
|
continue;
|
|
}
|
|
INIT_WORK(&sfw->work, flush_cpu_slab);
|
|
sfw->skip = false;
|
|
sfw->s = s;
|
|
queue_work_on(cpu, flushwq, &sfw->work);
|
|
}
|
|
|
|
for_each_online_cpu(cpu) {
|
|
sfw = &per_cpu(slub_flush, cpu);
|
|
if (sfw->skip)
|
|
continue;
|
|
flush_work(&sfw->work);
|
|
}
|
|
|
|
mutex_unlock(&flush_lock);
|
|
}
|
|
|
|
static void flush_all(struct kmem_cache *s)
|
|
{
|
|
cpus_read_lock();
|
|
flush_all_cpus_locked(s);
|
|
cpus_read_unlock();
|
|
}
|
|
|
|
/*
|
|
* Use the cpu notifier to insure that the cpu slabs are flushed when
|
|
* necessary.
|
|
*/
|
|
static int slub_cpu_dead(unsigned int cpu)
|
|
{
|
|
struct kmem_cache *s;
|
|
|
|
mutex_lock(&slab_mutex);
|
|
list_for_each_entry(s, &slab_caches, list)
|
|
__flush_cpu_slab(s, cpu);
|
|
mutex_unlock(&slab_mutex);
|
|
return 0;
|
|
}
|
|
|
|
#else /* CONFIG_SLUB_TINY */
|
|
static inline void flush_all_cpus_locked(struct kmem_cache *s) { }
|
|
static inline void flush_all(struct kmem_cache *s) { }
|
|
static inline void __flush_cpu_slab(struct kmem_cache *s, int cpu) { }
|
|
static inline int slub_cpu_dead(unsigned int cpu) { return 0; }
|
|
#endif /* CONFIG_SLUB_TINY */
|
|
|
|
/*
|
|
* Check if the objects in a per cpu structure fit numa
|
|
* locality expectations.
|
|
*/
|
|
static inline int node_match(struct slab *slab, int node)
|
|
{
|
|
#ifdef CONFIG_NUMA
|
|
if (node != NUMA_NO_NODE && slab_nid(slab) != node)
|
|
return 0;
|
|
#endif
|
|
return 1;
|
|
}
|
|
|
|
#ifdef CONFIG_SLUB_DEBUG
|
|
static int count_free(struct slab *slab)
|
|
{
|
|
return slab->objects - slab->inuse;
|
|
}
|
|
|
|
static inline unsigned long node_nr_objs(struct kmem_cache_node *n)
|
|
{
|
|
return atomic_long_read(&n->total_objects);
|
|
}
|
|
|
|
/* Supports checking bulk free of a constructed freelist */
|
|
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)
|
|
{
|
|
bool checks_ok = false;
|
|
void *object = head;
|
|
int cnt = 0;
|
|
|
|
if (s->flags & SLAB_CONSISTENCY_CHECKS) {
|
|
if (!check_slab(s, slab))
|
|
goto out;
|
|
}
|
|
|
|
if (slab->inuse < *bulk_cnt) {
|
|
slab_err(s, slab, "Slab has %d allocated objects but %d are to be freed\n",
|
|
slab->inuse, *bulk_cnt);
|
|
goto out;
|
|
}
|
|
|
|
next_object:
|
|
|
|
if (++cnt > *bulk_cnt)
|
|
goto out_cnt;
|
|
|
|
if (s->flags & SLAB_CONSISTENCY_CHECKS) {
|
|
if (!free_consistency_checks(s, slab, object, addr))
|
|
goto out;
|
|
}
|
|
|
|
if (s->flags & SLAB_STORE_USER)
|
|
set_track_update(s, object, TRACK_FREE, addr, handle);
|
|
trace(s, slab, object, 0);
|
|
/* Freepointer not overwritten by init_object(), SLAB_POISON moved it */
|
|
init_object(s, object, SLUB_RED_INACTIVE);
|
|
|
|
/* Reached end of constructed freelist yet? */
|
|
if (object != tail) {
|
|
object = get_freepointer(s, object);
|
|
goto next_object;
|
|
}
|
|
checks_ok = true;
|
|
|
|
out_cnt:
|
|
if (cnt != *bulk_cnt) {
|
|
slab_err(s, slab, "Bulk free expected %d objects but found %d\n",
|
|
*bulk_cnt, cnt);
|
|
*bulk_cnt = cnt;
|
|
}
|
|
|
|
out:
|
|
|
|
if (!checks_ok)
|
|
slab_fix(s, "Object at 0x%p not freed", object);
|
|
|
|
return checks_ok;
|
|
}
|
|
#endif /* CONFIG_SLUB_DEBUG */
|
|
|
|
#if defined(CONFIG_SLUB_DEBUG) || defined(SLAB_SUPPORTS_SYSFS)
|
|
static unsigned long count_partial(struct kmem_cache_node *n,
|
|
int (*get_count)(struct slab *))
|
|
{
|
|
unsigned long flags;
|
|
unsigned long x = 0;
|
|
struct slab *slab;
|
|
|
|
spin_lock_irqsave(&n->list_lock, flags);
|
|
list_for_each_entry(slab, &n->partial, slab_list)
|
|
x += get_count(slab);
|
|
spin_unlock_irqrestore(&n->list_lock, flags);
|
|
return x;
|
|
}
|
|
#endif /* CONFIG_SLUB_DEBUG || SLAB_SUPPORTS_SYSFS */
|
|
|
|
#ifdef CONFIG_SLUB_DEBUG
|
|
static noinline void
|
|
slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid)
|
|
{
|
|
static DEFINE_RATELIMIT_STATE(slub_oom_rs, DEFAULT_RATELIMIT_INTERVAL,
|
|
DEFAULT_RATELIMIT_BURST);
|
|
int node;
|
|
struct kmem_cache_node *n;
|
|
|
|
if ((gfpflags & __GFP_NOWARN) || !__ratelimit(&slub_oom_rs))
|
|
return;
|
|
|
|
pr_warn("SLUB: Unable to allocate memory on node %d, gfp=%#x(%pGg)\n",
|
|
nid, gfpflags, &gfpflags);
|
|
pr_warn(" cache: %s, object size: %u, buffer size: %u, default order: %u, min order: %u\n",
|
|
s->name, s->object_size, s->size, oo_order(s->oo),
|
|
oo_order(s->min));
|
|
|
|
if (oo_order(s->min) > get_order(s->object_size))
|
|
pr_warn(" %s debugging increased min order, use slub_debug=O to disable.\n",
|
|
s->name);
|
|
|
|
for_each_kmem_cache_node(s, node, n) {
|
|
unsigned long nr_slabs;
|
|
unsigned long nr_objs;
|
|
unsigned long nr_free;
|
|
|
|
nr_free = count_partial(n, count_free);
|
|
nr_slabs = node_nr_slabs(n);
|
|
nr_objs = node_nr_objs(n);
|
|
|
|
pr_warn(" node %d: slabs: %ld, objs: %ld, free: %ld\n",
|
|
node, nr_slabs, nr_objs, nr_free);
|
|
}
|
|
}
|
|
#else /* CONFIG_SLUB_DEBUG */
|
|
static inline void
|
|
slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid) { }
|
|
#endif
|
|
|
|
static inline bool pfmemalloc_match(struct slab *slab, gfp_t gfpflags)
|
|
{
|
|
if (unlikely(slab_test_pfmemalloc(slab)))
|
|
return gfp_pfmemalloc_allowed(gfpflags);
|
|
|
|
return true;
|
|
}
|
|
|
|
#ifndef CONFIG_SLUB_TINY
|
|
/*
|
|
* Check the slab->freelist and either transfer the freelist to the
|
|
* per cpu freelist or deactivate the slab.
|
|
*
|
|
* The slab is still frozen if the return value is not NULL.
|
|
*
|
|
* If this function returns NULL then the slab has been unfrozen.
|
|
*/
|
|
static inline void *get_freelist(struct kmem_cache *s, struct slab *slab)
|
|
{
|
|
struct slab new;
|
|
unsigned long counters;
|
|
void *freelist;
|
|
|
|
lockdep_assert_held(this_cpu_ptr(&s->cpu_slab->lock));
|
|
|
|
do {
|
|
freelist = slab->freelist;
|
|
counters = slab->counters;
|
|
|
|
new.counters = counters;
|
|
VM_BUG_ON(!new.frozen);
|
|
|
|
new.inuse = slab->objects;
|
|
new.frozen = freelist != NULL;
|
|
|
|
} while (!__cmpxchg_double_slab(s, slab,
|
|
freelist, counters,
|
|
NULL, new.counters,
|
|
"get_freelist"));
|
|
|
|
return freelist;
|
|
}
|
|
|
|
/*
|
|
* Slow path. The lockless freelist is empty or we need to perform
|
|
* debugging duties.
|
|
*
|
|
* Processing is still very fast if new objects have been freed to the
|
|
* regular freelist. In that case we simply take over the regular freelist
|
|
* as the lockless freelist and zap the regular freelist.
|
|
*
|
|
* If that is not working then we fall back to the partial lists. We take the
|
|
* first element of the freelist as the object to allocate now and move the
|
|
* rest of the freelist to the lockless freelist.
|
|
*
|
|
* And if we were unable to get a new slab from the partial slab lists then
|
|
* we need to allocate a new slab. This is the slowest path since it involves
|
|
* a call to the page allocator and the setup of a new slab.
|
|
*
|
|
* Version of __slab_alloc to use when we know that preemption is
|
|
* already disabled (which is the case for bulk allocation).
|
|
*/
|
|
static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
|
|
unsigned long addr, struct kmem_cache_cpu *c, unsigned int orig_size)
|
|
{
|
|
void *freelist;
|
|
struct slab *slab;
|
|
unsigned long flags;
|
|
struct partial_context pc;
|
|
|
|
stat(s, ALLOC_SLOWPATH);
|
|
|
|
reread_slab:
|
|
|
|
slab = READ_ONCE(c->slab);
|
|
if (!slab) {
|
|
/*
|
|
* if the node is not online or has no normal memory, just
|
|
* ignore the node constraint
|
|
*/
|
|
if (unlikely(node != NUMA_NO_NODE &&
|
|
!node_isset(node, slab_nodes)))
|
|
node = NUMA_NO_NODE;
|
|
goto new_slab;
|
|
}
|
|
redo:
|
|
|
|
if (unlikely(!node_match(slab, node))) {
|
|
/*
|
|
* same as above but node_match() being false already
|
|
* implies node != NUMA_NO_NODE
|
|
*/
|
|
if (!node_isset(node, slab_nodes)) {
|
|
node = NUMA_NO_NODE;
|
|
} else {
|
|
stat(s, ALLOC_NODE_MISMATCH);
|
|
goto deactivate_slab;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* By rights, we should be searching for a slab page that was
|
|
* PFMEMALLOC but right now, we are losing the pfmemalloc
|
|
* information when the page leaves the per-cpu allocator
|
|
*/
|
|
if (unlikely(!pfmemalloc_match(slab, gfpflags)))
|
|
goto deactivate_slab;
|
|
|
|
/* must check again c->slab in case we got preempted and it changed */
|
|
local_lock_irqsave(&s->cpu_slab->lock, flags);
|
|
if (unlikely(slab != c->slab)) {
|
|
local_unlock_irqrestore(&s->cpu_slab->lock, flags);
|
|
goto reread_slab;
|
|
}
|
|
freelist = c->freelist;
|
|
if (freelist)
|
|
goto load_freelist;
|
|
|
|
freelist = get_freelist(s, slab);
|
|
|
|
if (!freelist) {
|
|
c->slab = NULL;
|
|
c->tid = next_tid(c->tid);
|
|
local_unlock_irqrestore(&s->cpu_slab->lock, flags);
|
|
stat(s, DEACTIVATE_BYPASS);
|
|
goto new_slab;
|
|
}
|
|
|
|
stat(s, ALLOC_REFILL);
|
|
|
|
load_freelist:
|
|
|
|
lockdep_assert_held(this_cpu_ptr(&s->cpu_slab->lock));
|
|
|
|
/*
|
|
* freelist is pointing to the list of objects to be used.
|
|
* slab is pointing to the slab from which the objects are obtained.
|
|
* That slab must be frozen for per cpu allocations to work.
|
|
*/
|
|
VM_BUG_ON(!c->slab->frozen);
|
|
c->freelist = get_freepointer(s, freelist);
|
|
c->tid = next_tid(c->tid);
|
|
local_unlock_irqrestore(&s->cpu_slab->lock, flags);
|
|
return freelist;
|
|
|
|
deactivate_slab:
|
|
|
|
local_lock_irqsave(&s->cpu_slab->lock, flags);
|
|
if (slab != c->slab) {
|
|
local_unlock_irqrestore(&s->cpu_slab->lock, flags);
|
|
goto reread_slab;
|
|
}
|
|
freelist = c->freelist;
|
|
c->slab = NULL;
|
|
c->freelist = NULL;
|
|
c->tid = next_tid(c->tid);
|
|
local_unlock_irqrestore(&s->cpu_slab->lock, flags);
|
|
deactivate_slab(s, slab, freelist);
|
|
|
|
new_slab:
|
|
|
|
if (slub_percpu_partial(c)) {
|
|
local_lock_irqsave(&s->cpu_slab->lock, flags);
|
|
if (unlikely(c->slab)) {
|
|
local_unlock_irqrestore(&s->cpu_slab->lock, flags);
|
|
goto reread_slab;
|
|
}
|
|
if (unlikely(!slub_percpu_partial(c))) {
|
|
local_unlock_irqrestore(&s->cpu_slab->lock, flags);
|
|
/* we were preempted and partial list got empty */
|
|
goto new_objects;
|
|
}
|
|
|
|
slab = c->slab = slub_percpu_partial(c);
|
|
slub_set_percpu_partial(c, slab);
|
|
local_unlock_irqrestore(&s->cpu_slab->lock, flags);
|
|
stat(s, CPU_PARTIAL_ALLOC);
|
|
goto redo;
|
|
}
|
|
|
|
new_objects:
|
|
|
|
pc.flags = gfpflags;
|
|
pc.slab = &slab;
|
|
pc.orig_size = orig_size;
|
|
freelist = get_partial(s, node, &pc);
|
|
if (freelist)
|
|
goto check_new_slab;
|
|
|
|
slub_put_cpu_ptr(s->cpu_slab);
|
|
slab = new_slab(s, gfpflags, node);
|
|
c = slub_get_cpu_ptr(s->cpu_slab);
|
|
|
|
if (unlikely(!slab)) {
|
|
slab_out_of_memory(s, gfpflags, node);
|
|
return NULL;
|
|
}
|
|
|
|
stat(s, ALLOC_SLAB);
|
|
|
|
if (kmem_cache_debug(s)) {
|
|
freelist = alloc_single_from_new_slab(s, slab, orig_size);
|
|
|
|
if (unlikely(!freelist))
|
|
goto new_objects;
|
|
|
|
if (s->flags & SLAB_STORE_USER)
|
|
set_track(s, freelist, TRACK_ALLOC, addr);
|
|
|
|
return freelist;
|
|
}
|
|
|
|
/*
|
|
* No other reference to the slab yet so we can
|
|
* muck around with it freely without cmpxchg
|
|
*/
|
|
freelist = slab->freelist;
|
|
slab->freelist = NULL;
|
|
slab->inuse = slab->objects;
|
|
slab->frozen = 1;
|
|
|
|
inc_slabs_node(s, slab_nid(slab), slab->objects);
|
|
|
|
check_new_slab:
|
|
|
|
if (kmem_cache_debug(s)) {
|
|
/*
|
|
* For debug caches here we had to go through
|
|
* alloc_single_from_partial() so just store the tracking info
|
|
* and return the object
|
|
*/
|
|
if (s->flags & SLAB_STORE_USER)
|
|
set_track(s, freelist, TRACK_ALLOC, addr);
|
|
|
|
return freelist;
|
|
}
|
|
|
|
if (unlikely(!pfmemalloc_match(slab, gfpflags))) {
|
|
/*
|
|
* For !pfmemalloc_match() case we don't load freelist so that
|
|
* we don't make further mismatched allocations easier.
|
|
*/
|
|
deactivate_slab(s, slab, get_freepointer(s, freelist));
|
|
return freelist;
|
|
}
|
|
|
|
retry_load_slab:
|
|
|
|
local_lock_irqsave(&s->cpu_slab->lock, flags);
|
|
if (unlikely(c->slab)) {
|
|
void *flush_freelist = c->freelist;
|
|
struct slab *flush_slab = c->slab;
|
|
|
|
c->slab = NULL;
|
|
c->freelist = NULL;
|
|
c->tid = next_tid(c->tid);
|
|
|
|
local_unlock_irqrestore(&s->cpu_slab->lock, flags);
|
|
|
|
deactivate_slab(s, flush_slab, flush_freelist);
|
|
|
|
stat(s, CPUSLAB_FLUSH);
|
|
|
|
goto retry_load_slab;
|
|
}
|
|
c->slab = slab;
|
|
|
|
goto load_freelist;
|
|
}
|
|
|
|
/*
|
|
* A wrapper for ___slab_alloc() for contexts where preemption is not yet
|
|
* disabled. Compensates for possible cpu changes by refetching the per cpu area
|
|
* pointer.
|
|
*/
|
|
static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
|
|
unsigned long addr, struct kmem_cache_cpu *c, unsigned int orig_size)
|
|
{
|
|
void *p;
|
|
|
|
#ifdef CONFIG_PREEMPT_COUNT
|
|
/*
|
|
* We may have been preempted and rescheduled on a different
|
|
* cpu before disabling preemption. Need to reload cpu area
|
|
* pointer.
|
|
*/
|
|
c = slub_get_cpu_ptr(s->cpu_slab);
|
|
#endif
|
|
|
|
p = ___slab_alloc(s, gfpflags, node, addr, c, orig_size);
|
|
#ifdef CONFIG_PREEMPT_COUNT
|
|
slub_put_cpu_ptr(s->cpu_slab);
|
|
#endif
|
|
return p;
|
|
}
|
|
|
|
static __always_inline void *__slab_alloc_node(struct kmem_cache *s,
|
|
gfp_t gfpflags, int node, unsigned long addr, size_t orig_size)
|
|
{
|
|
struct kmem_cache_cpu *c;
|
|
struct slab *slab;
|
|
unsigned long tid;
|
|
void *object;
|
|
|
|
redo:
|
|
/*
|
|
* Must read kmem_cache cpu data via this cpu ptr. Preemption is
|
|
* enabled. We may switch back and forth between cpus while
|
|
* reading from one cpu area. That does not matter as long
|
|
* as we end up on the original cpu again when doing the cmpxchg.
|
|
*
|
|
* We must guarantee that tid and kmem_cache_cpu are retrieved on the
|
|
* same cpu. We read first the kmem_cache_cpu pointer and use it to read
|
|
* the tid. If we are preempted and switched to another cpu between the
|
|
* two reads, it's OK as the two are still associated with the same cpu
|
|
* and cmpxchg later will validate the cpu.
|
|
*/
|
|
c = raw_cpu_ptr(s->cpu_slab);
|
|
tid = READ_ONCE(c->tid);
|
|
|
|
/*
|
|
* Irqless object alloc/free algorithm used here depends on sequence
|
|
* of fetching cpu_slab's data. tid should be fetched before anything
|
|
* on c to guarantee that object and slab associated with previous tid
|
|
* won't be used with current tid. If we fetch tid first, object and
|
|
* slab could be one associated with next tid and our alloc/free
|
|
* request will be failed. In this case, we will retry. So, no problem.
|
|
*/
|
|
barrier();
|
|
|
|
/*
|
|
* The transaction ids are globally unique per cpu and per operation on
|
|
* a per cpu queue. Thus they can be guarantee that the cmpxchg_double
|
|
* occurs on the right processor and that there was no operation on the
|
|
* linked list in between.
|
|
*/
|
|
|
|
object = c->freelist;
|
|
slab = c->slab;
|
|
|
|
if (!USE_LOCKLESS_FAST_PATH() ||
|
|
unlikely(!object || !slab || !node_match(slab, node))) {
|
|
object = __slab_alloc(s, gfpflags, node, addr, c, orig_size);
|
|
} else {
|
|
void *next_object = get_freepointer_safe(s, object);
|
|
|
|
/*
|
|
* The cmpxchg will only match if there was no additional
|
|
* operation and if we are on the right processor.
|
|
*
|
|
* The cmpxchg does the following atomically (without lock
|
|
* semantics!)
|
|
* 1. Relocate first pointer to the current per cpu area.
|
|
* 2. Verify that tid and freelist have not been changed
|
|
* 3. If they were not changed replace tid and freelist
|
|
*
|
|
* Since this is without lock semantics the protection is only
|
|
* against code executing on this cpu *not* from access by
|
|
* other cpus.
|
|
*/
|
|
if (unlikely(!this_cpu_cmpxchg_double(
|
|
s->cpu_slab->freelist, s->cpu_slab->tid,
|
|
object, tid,
|
|
next_object, next_tid(tid)))) {
|
|
|
|
note_cmpxchg_failure("slab_alloc", s, tid);
|
|
goto redo;
|
|
}
|
|
prefetch_freepointer(s, next_object);
|
|
stat(s, ALLOC_FASTPATH);
|
|
}
|
|
|
|
return object;
|
|
}
|
|
#else /* CONFIG_SLUB_TINY */
|
|
static void *__slab_alloc_node(struct kmem_cache *s,
|
|
gfp_t gfpflags, int node, unsigned long addr, size_t orig_size)
|
|
{
|
|
struct partial_context pc;
|
|
struct slab *slab;
|
|
void *object;
|
|
|
|
pc.flags = gfpflags;
|
|
pc.slab = &slab;
|
|
pc.orig_size = orig_size;
|
|
object = get_partial(s, node, &pc);
|
|
|
|
if (object)
|
|
return object;
|
|
|
|
slab = new_slab(s, gfpflags, node);
|
|
if (unlikely(!slab)) {
|
|
slab_out_of_memory(s, gfpflags, node);
|
|
return NULL;
|
|
}
|
|
|
|
object = alloc_single_from_new_slab(s, slab, orig_size);
|
|
|
|
return object;
|
|
}
|
|
#endif /* CONFIG_SLUB_TINY */
|
|
|
|
/*
|
|
* If the object has been wiped upon free, make sure it's fully initialized by
|
|
* zeroing out freelist pointer.
|
|
*/
|
|
static __always_inline void maybe_wipe_obj_freeptr(struct kmem_cache *s,
|
|
void *obj)
|
|
{
|
|
if (unlikely(slab_want_init_on_free(s)) && obj)
|
|
memset((void *)((char *)kasan_reset_tag(obj) + s->offset),
|
|
0, sizeof(void *));
|
|
}
|
|
|
|
/*
|
|
* Inlined fastpath so that allocation functions (kmalloc, kmem_cache_alloc)
|
|
* have the fastpath folded into their functions. So no function call
|
|
* overhead for requests that can be satisfied on the fastpath.
|
|
*
|
|
* The fastpath works by first checking if the lockless freelist can be used.
|
|
* If not then __slab_alloc is called for slow processing.
|
|
*
|
|
* Otherwise we can simply pick the next object from the lockless free list.
|
|
*/
|
|
static __fastpath_inline void *slab_alloc_node(struct kmem_cache *s, struct list_lru *lru,
|
|
gfp_t gfpflags, int node, unsigned long addr, size_t orig_size)
|
|
{
|
|
void *object;
|
|
struct obj_cgroup *objcg = NULL;
|
|
bool init = false;
|
|
|
|
s = slab_pre_alloc_hook(s, lru, &objcg, 1, gfpflags);
|
|
if (!s)
|
|
return NULL;
|
|
|
|
object = kfence_alloc(s, orig_size, gfpflags);
|
|
if (unlikely(object))
|
|
goto out;
|
|
|
|
object = __slab_alloc_node(s, gfpflags, node, addr, orig_size);
|
|
|
|
maybe_wipe_obj_freeptr(s, object);
|
|
init = slab_want_init_on_alloc(gfpflags, s);
|
|
|
|
out:
|
|
/*
|
|
* When init equals 'true', like for kzalloc() family, only
|
|
* @orig_size bytes might be zeroed instead of s->object_size
|
|
*/
|
|
slab_post_alloc_hook(s, objcg, gfpflags, 1, &object, init, orig_size);
|
|
|
|
return object;
|
|
}
|
|
|
|
static __fastpath_inline void *slab_alloc(struct kmem_cache *s, struct list_lru *lru,
|
|
gfp_t gfpflags, unsigned long addr, size_t orig_size)
|
|
{
|
|
return slab_alloc_node(s, lru, gfpflags, NUMA_NO_NODE, addr, orig_size);
|
|
}
|
|
|
|
static __fastpath_inline
|
|
void *__kmem_cache_alloc_lru(struct kmem_cache *s, struct list_lru *lru,
|
|
gfp_t gfpflags)
|
|
{
|
|
void *ret = slab_alloc(s, lru, gfpflags, _RET_IP_, s->object_size);
|
|
|
|
trace_kmem_cache_alloc(_RET_IP_, ret, s, gfpflags, NUMA_NO_NODE);
|
|
|
|
return ret;
|
|
}
|
|
|
|
void *kmem_cache_alloc(struct kmem_cache *s, gfp_t gfpflags)
|
|
{
|
|
return __kmem_cache_alloc_lru(s, NULL, gfpflags);
|
|
}
|
|
EXPORT_SYMBOL(kmem_cache_alloc);
|
|
|
|
void *kmem_cache_alloc_lru(struct kmem_cache *s, struct list_lru *lru,
|
|
gfp_t gfpflags)
|
|
{
|
|
return __kmem_cache_alloc_lru(s, lru, gfpflags);
|
|
}
|
|
EXPORT_SYMBOL(kmem_cache_alloc_lru);
|
|
|
|
void *__kmem_cache_alloc_node(struct kmem_cache *s, gfp_t gfpflags,
|
|
int node, size_t orig_size,
|
|
unsigned long caller)
|
|
{
|
|
return slab_alloc_node(s, NULL, gfpflags, node,
|
|
caller, orig_size);
|
|
}
|
|
|
|
void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t gfpflags, int node)
|
|
{
|
|
void *ret = slab_alloc_node(s, NULL, gfpflags, node, _RET_IP_, s->object_size);
|
|
|
|
trace_kmem_cache_alloc(_RET_IP_, ret, s, gfpflags, node);
|
|
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL(kmem_cache_alloc_node);
|
|
|
|
static noinline void free_to_partial_list(
|
|
struct kmem_cache *s, struct slab *slab,
|
|
void *head, void *tail, int bulk_cnt,
|
|
unsigned long addr)
|
|
{
|
|
struct kmem_cache_node *n = get_node(s, slab_nid(slab));
|
|
struct slab *slab_free = NULL;
|
|
int cnt = bulk_cnt;
|
|
unsigned long flags;
|
|
depot_stack_handle_t handle = 0;
|
|
|
|
if (s->flags & SLAB_STORE_USER)
|
|
handle = set_track_prepare();
|
|
|
|
spin_lock_irqsave(&n->list_lock, flags);
|
|
|
|
if (free_debug_processing(s, slab, head, tail, &cnt, addr, handle)) {
|
|
void *prior = slab->freelist;
|
|
|
|
/* Perform the actual freeing while we still hold the locks */
|
|
slab->inuse -= cnt;
|
|
set_freepointer(s, tail, prior);
|
|
slab->freelist = head;
|
|
|
|
/*
|
|
* If the slab is empty, and node's partial list is full,
|
|
* it should be discarded anyway no matter it's on full or
|
|
* partial list.
|
|
*/
|
|
if (slab->inuse == 0 && n->nr_partial >= s->min_partial)
|
|
slab_free = slab;
|
|
|
|
if (!prior) {
|
|
/* was on full list */
|
|
remove_full(s, n, slab);
|
|
if (!slab_free) {
|
|
add_partial(n, slab, DEACTIVATE_TO_TAIL);
|
|
stat(s, FREE_ADD_PARTIAL);
|
|
}
|
|
} else if (slab_free) {
|
|
remove_partial(n, slab);
|
|
stat(s, FREE_REMOVE_PARTIAL);
|
|
}
|
|
}
|
|
|
|
if (slab_free) {
|
|
/*
|
|
* Update the counters while still holding n->list_lock to
|
|
* prevent spurious validation warnings
|
|
*/
|
|
dec_slabs_node(s, slab_nid(slab_free), slab_free->objects);
|
|
}
|
|
|
|
spin_unlock_irqrestore(&n->list_lock, flags);
|
|
|
|
if (slab_free) {
|
|
stat(s, FREE_SLAB);
|
|
free_slab(s, slab_free);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Slow path handling. This may still be called frequently since objects
|
|
* have a longer lifetime than the cpu slabs in most processing loads.
|
|
*
|
|
* So we still attempt to reduce cache line usage. Just take the slab
|
|
* lock and free the item. If there is no additional partial slab
|
|
* handling required then we can return immediately.
|
|
*/
|
|
static void __slab_free(struct kmem_cache *s, struct slab *slab,
|
|
void *head, void *tail, int cnt,
|
|
unsigned long addr)
|
|
|
|
{
|
|
void *prior;
|
|
int was_frozen;
|
|
struct slab new;
|
|
unsigned long counters;
|
|
struct kmem_cache_node *n = NULL;
|
|
unsigned long flags;
|
|
|
|
stat(s, FREE_SLOWPATH);
|
|
|
|
if (kfence_free(head))
|
|
return;
|
|
|
|
if (IS_ENABLED(CONFIG_SLUB_TINY) || kmem_cache_debug(s)) {
|
|
free_to_partial_list(s, slab, head, tail, cnt, addr);
|
|
return;
|
|
}
|
|
|
|
do {
|
|
if (unlikely(n)) {
|
|
spin_unlock_irqrestore(&n->list_lock, flags);
|
|
n = NULL;
|
|
}
|
|
prior = slab->freelist;
|
|
counters = slab->counters;
|
|
set_freepointer(s, tail, prior);
|
|
new.counters = counters;
|
|
was_frozen = new.frozen;
|
|
new.inuse -= cnt;
|
|
if ((!new.inuse || !prior) && !was_frozen) {
|
|
|
|
if (kmem_cache_has_cpu_partial(s) && !prior) {
|
|
|
|
/*
|
|
* Slab was on no list before and will be
|
|
* partially empty
|
|
* We can defer the list move and instead
|
|
* freeze it.
|
|
*/
|
|
new.frozen = 1;
|
|
|
|
} else { /* Needs to be taken off a list */
|
|
|
|
n = get_node(s, slab_nid(slab));
|
|
/*
|
|
* Speculatively acquire the list_lock.
|
|
* If the cmpxchg does not succeed then we may
|
|
* drop the list_lock without any processing.
|
|
*
|
|
* Otherwise the list_lock will synchronize with
|
|
* other processors updating the list of slabs.
|
|
*/
|
|
spin_lock_irqsave(&n->list_lock, flags);
|
|
|
|
}
|
|
}
|
|
|
|
} while (!cmpxchg_double_slab(s, slab,
|
|
prior, counters,
|
|
head, new.counters,
|
|
"__slab_free"));
|
|
|
|
if (likely(!n)) {
|
|
|
|
if (likely(was_frozen)) {
|
|
/*
|
|
* The list lock was not taken therefore no list
|
|
* activity can be necessary.
|
|
*/
|
|
stat(s, FREE_FROZEN);
|
|
} else if (new.frozen) {
|
|
/*
|
|
* If we just froze the slab then put it onto the
|
|
* per cpu partial list.
|
|
*/
|
|
put_cpu_partial(s, slab, 1);
|
|
stat(s, CPU_PARTIAL_FREE);
|
|
}
|
|
|
|
return;
|
|
}
|
|
|
|
if (unlikely(!new.inuse && n->nr_partial >= s->min_partial))
|
|
goto slab_empty;
|
|
|
|
/*
|
|
* Objects left in the slab. If it was not on the partial list before
|
|
* then add it.
|
|
*/
|
|
if (!kmem_cache_has_cpu_partial(s) && unlikely(!prior)) {
|
|
remove_full(s, n, slab);
|
|
add_partial(n, slab, DEACTIVATE_TO_TAIL);
|
|
stat(s, FREE_ADD_PARTIAL);
|
|
}
|
|
spin_unlock_irqrestore(&n->list_lock, flags);
|
|
return;
|
|
|
|
slab_empty:
|
|
if (prior) {
|
|
/*
|
|
* Slab on the partial list.
|
|
*/
|
|
remove_partial(n, slab);
|
|
stat(s, FREE_REMOVE_PARTIAL);
|
|
} else {
|
|
/* Slab must be on the full list */
|
|
remove_full(s, n, slab);
|
|
}
|
|
|
|
spin_unlock_irqrestore(&n->list_lock, flags);
|
|
stat(s, FREE_SLAB);
|
|
discard_slab(s, slab);
|
|
}
|
|
|
|
#ifndef CONFIG_SLUB_TINY
|
|
/*
|
|
* Fastpath with forced inlining to produce a kfree and kmem_cache_free that
|
|
* can perform fastpath freeing without additional function calls.
|
|
*
|
|
* The fastpath is only possible if we are freeing to the current cpu slab
|
|
* of this processor. This typically the case if we have just allocated
|
|
* the item before.
|
|
*
|
|
* If fastpath is not possible then fall back to __slab_free where we deal
|
|
* with all sorts of special processing.
|
|
*
|
|
* Bulk free of a freelist with several objects (all pointing to the
|
|
* same slab) possible by specifying head and tail ptr, plus objects
|
|
* count (cnt). Bulk free indicated by tail pointer being set.
|
|
*/
|
|
static __always_inline void do_slab_free(struct kmem_cache *s,
|
|
struct slab *slab, void *head, void *tail,
|
|
int cnt, unsigned long addr)
|
|
{
|
|
void *tail_obj = tail ? : head;
|
|
struct kmem_cache_cpu *c;
|
|
unsigned long tid;
|
|
void **freelist;
|
|
|
|
redo:
|
|
/*
|
|
* Determine the currently cpus per cpu slab.
|
|
* The cpu may change afterward. However that does not matter since
|
|
* data is retrieved via this pointer. If we are on the same cpu
|
|
* during the cmpxchg then the free will succeed.
|
|
*/
|
|
c = raw_cpu_ptr(s->cpu_slab);
|
|
tid = READ_ONCE(c->tid);
|
|
|
|
/* Same with comment on barrier() in slab_alloc_node() */
|
|
barrier();
|
|
|
|
if (unlikely(slab != c->slab)) {
|
|
__slab_free(s, slab, head, tail_obj, cnt, addr);
|
|
return;
|
|
}
|
|
|
|
if (USE_LOCKLESS_FAST_PATH()) {
|
|
freelist = READ_ONCE(c->freelist);
|
|
|
|
set_freepointer(s, tail_obj, freelist);
|
|
|
|
if (unlikely(!this_cpu_cmpxchg_double(
|
|
s->cpu_slab->freelist, s->cpu_slab->tid,
|
|
freelist, tid,
|
|
head, next_tid(tid)))) {
|
|
|
|
note_cmpxchg_failure("slab_free", s, tid);
|
|
goto redo;
|
|
}
|
|
} else {
|
|
/* Update the free list under the local lock */
|
|
local_lock(&s->cpu_slab->lock);
|
|
c = this_cpu_ptr(s->cpu_slab);
|
|
if (unlikely(slab != c->slab)) {
|
|
local_unlock(&s->cpu_slab->lock);
|
|
goto redo;
|
|
}
|
|
tid = c->tid;
|
|
freelist = c->freelist;
|
|
|
|
set_freepointer(s, tail_obj, freelist);
|
|
c->freelist = head;
|
|
c->tid = next_tid(tid);
|
|
|
|
local_unlock(&s->cpu_slab->lock);
|
|
}
|
|
stat(s, FREE_FASTPATH);
|
|
}
|
|
#else /* CONFIG_SLUB_TINY */
|
|
static void do_slab_free(struct kmem_cache *s,
|
|
struct slab *slab, void *head, void *tail,
|
|
int cnt, unsigned long addr)
|
|
{
|
|
void *tail_obj = tail ? : head;
|
|
|
|
__slab_free(s, slab, head, tail_obj, cnt, addr);
|
|
}
|
|
#endif /* CONFIG_SLUB_TINY */
|
|
|
|
static __fastpath_inline void slab_free(struct kmem_cache *s, struct slab *slab,
|
|
void *head, void *tail, void **p, int cnt,
|
|
unsigned long addr)
|
|
{
|
|
memcg_slab_free_hook(s, slab, p, cnt);
|
|
/*
|
|
* With KASAN enabled slab_free_freelist_hook modifies the freelist
|
|
* to remove objects, whose reuse must be delayed.
|
|
*/
|
|
if (slab_free_freelist_hook(s, &head, &tail, &cnt))
|
|
do_slab_free(s, slab, head, tail, cnt, addr);
|
|
}
|
|
|
|
#ifdef CONFIG_KASAN_GENERIC
|
|
void ___cache_free(struct kmem_cache *cache, void *x, unsigned long addr)
|
|
{
|
|
do_slab_free(cache, virt_to_slab(x), x, NULL, 1, addr);
|
|
}
|
|
#endif
|
|
|
|
void __kmem_cache_free(struct kmem_cache *s, void *x, unsigned long caller)
|
|
{
|
|
slab_free(s, virt_to_slab(x), x, NULL, &x, 1, caller);
|
|
}
|
|
|
|
void kmem_cache_free(struct kmem_cache *s, void *x)
|
|
{
|
|
s = cache_from_obj(s, x);
|
|
if (!s)
|
|
return;
|
|
trace_kmem_cache_free(_RET_IP_, x, s);
|
|
slab_free(s, virt_to_slab(x), x, NULL, &x, 1, _RET_IP_);
|
|
}
|
|
EXPORT_SYMBOL(kmem_cache_free);
|
|
|
|
struct detached_freelist {
|
|
struct slab *slab;
|
|
void *tail;
|
|
void *freelist;
|
|
int cnt;
|
|
struct kmem_cache *s;
|
|
};
|
|
|
|
/*
|
|
* This function progressively scans the array with free objects (with
|
|
* a limited look ahead) and extract objects belonging to the same
|
|
* slab. It builds a detached freelist directly within the given
|
|
* slab/objects. This can happen without any need for
|
|
* synchronization, because the objects are owned by running process.
|
|
* The freelist is build up as a single linked list in the objects.
|
|
* The idea is, that this detached freelist can then be bulk
|
|
* transferred to the real freelist(s), but only requiring a single
|
|
* synchronization primitive. Look ahead in the array is limited due
|
|
* to performance reasons.
|
|
*/
|
|
static inline
|
|
int build_detached_freelist(struct kmem_cache *s, size_t size,
|
|
void **p, struct detached_freelist *df)
|
|
{
|
|
int lookahead = 3;
|
|
void *object;
|
|
struct folio *folio;
|
|
size_t same;
|
|
|
|
object = p[--size];
|
|
folio = virt_to_folio(object);
|
|
if (!s) {
|
|
/* Handle kalloc'ed objects */
|
|
if (unlikely(!folio_test_slab(folio))) {
|
|
free_large_kmalloc(folio, object);
|
|
df->slab = NULL;
|
|
return size;
|
|
}
|
|
/* Derive kmem_cache from object */
|
|
df->slab = folio_slab(folio);
|
|
df->s = df->slab->slab_cache;
|
|
} else {
|
|
df->slab = folio_slab(folio);
|
|
df->s = cache_from_obj(s, object); /* Support for memcg */
|
|
}
|
|
|
|
/* Start new detached freelist */
|
|
df->tail = object;
|
|
df->freelist = object;
|
|
df->cnt = 1;
|
|
|
|
if (is_kfence_address(object))
|
|
return size;
|
|
|
|
set_freepointer(df->s, object, NULL);
|
|
|
|
same = size;
|
|
while (size) {
|
|
object = p[--size];
|
|
/* df->slab is always set at this point */
|
|
if (df->slab == virt_to_slab(object)) {
|
|
/* Opportunity build freelist */
|
|
set_freepointer(df->s, object, df->freelist);
|
|
df->freelist = object;
|
|
df->cnt++;
|
|
same--;
|
|
if (size != same)
|
|
swap(p[size], p[same]);
|
|
continue;
|
|
}
|
|
|
|
/* Limit look ahead search */
|
|
if (!--lookahead)
|
|
break;
|
|
}
|
|
|
|
return same;
|
|
}
|
|
|
|
/* Note that interrupts must be enabled when calling this function. */
|
|
void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void |