blob: a8626825a8299377d617219dc34ca60e34873d10 [file] [log] [blame]
// SPDX-License-Identifier: GPL-2.0
/*
* SLUB: A slab allocator that limits cache line use instead of queuing
* objects in per cpu and per node lists.
*
* The allocator synchronizes using per slab locks or atomic operations
* and only uses a centralized lock to manage a pool of partial slabs.
*
* (C) 2007 SGI, Christoph Lameter
* (C) 2011 Linux Foundation, Christoph Lameter
*/
#include <linux/mm.h>
#include <linux/swap.h> /* 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/cpu.h>
#include <linux/cpuset.h>
#include <linux/mempolicy.h>
#include <linux/ctype.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 <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(page) (Only on some arches or for debugging)
* 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 for debugging and on arches that do not
* have the ability to do a cmpxchg_double. It only protects:
* A. page->freelist -> List of object free in a page
* B. page->inuse -> Number of objects in use
* C. page->objects -> Number of objects in page
* D. page->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 page. 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
* page'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.
*
* 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 does not actually disable irqs (and thus
* prevent the lockless operations), so fastpath operations also need to take
* the lock and are no longer lockless.
*
* 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.
*
* page->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)
#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)
#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 */
static inline bool kmem_cache_debug(struct kmem_cache *s)
{
return kmem_cache_debug_flags(s, SLAB_DEBUG_FLAGS);
}
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
/*
* 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
#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 page.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_STACKTRACE
unsigned long addrs[TRACK_ADDRS_COUNT]; /* Called from address */
#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 CONFIG_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;
/********************************************************************
* 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);
}
static void prefetch_freepointer(const struct kmem_cache *s, void *object)
{
prefetchw(object + s->offset);
}
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_pages;
s->cpu_partial = nr_objects;
/*
* We take the number of objects but actually limit the number of
* pages on the per cpu partial list, in order to limit excessive
* growth of the list. For simplicity we assume that the pages will
* be half-full.
*/
nr_pages = DIV_ROUND_UP(nr_objects * 2, oo_objects(s->oo));
s->cpu_partial_pages = nr_pages;
}
#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 page *page)
{
VM_BUG_ON_PAGE(PageTail(page), page);
bit_spin_lock(PG_locked, &page->flags);
}
static __always_inline void __slab_unlock(struct page *page)
{
VM_BUG_ON_PAGE(PageTail(page), page);
__bit_spin_unlock(PG_locked, &page->flags);
}
static __always_inline void slab_lock(struct page *page, unsigned long *flags)
{
if (IS_ENABLED(CONFIG_PREEMPT_RT))
local_irq_save(*flags);
__slab_lock(page);
}
static __always_inline void slab_unlock(struct page *page, unsigned long *flags)
{
__slab_unlock(page);
if (IS_ENABLED(CONFIG_PREEMPT_RT))
local_irq_restore(*flags);
}
/*
* Interrupts must be disabled (for the fallback code to work right), typically
* by an _irqsave() lock variant. Except on PREEMPT_RT where locks are different
* so we disable interrupts as part of slab_[un]lock().
*/
static inline bool __cmpxchg_double_slab(struct kmem_cache *s, struct page *page,
void *freelist_old, unsigned long counters_old,
void *freelist_new, unsigned long counters_new,
const char *n)
{
if (!IS_ENABLED(CONFIG_PREEMPT_RT))
lockdep_assert_irqs_disabled();
#if defined(CONFIG_HAVE_CMPXCHG_DOUBLE) && \
defined(CONFIG_HAVE_ALIGNED_STRUCT_PAGE)
if (s->flags & __CMPXCHG_DOUBLE) {
if (cmpxchg_double(&page->freelist, &page->counters,
freelist_old, counters_old,
freelist_new, counters_new))
return true;
} else
#endif
{
/* init to 0 to prevent spurious warnings */
unsigned long flags = 0;
slab_lock(page, &flags);
if (page->freelist == freelist_old &&
page->counters == counters_old) {
page->freelist = freelist_new;
page->counters = counters_new;
slab_unlock(page, &flags);
return true;
}
slab_unlock(page, &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;
}
static inline bool cmpxchg_double_slab(struct kmem_cache *s, struct page *page,
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(&page->freelist, &page->counters,
freelist_old, counters_old,
freelist_new, counters_new))
return true;
} else
#endif
{
unsigned long flags;
local_irq_save(flags);
__slab_lock(page);
if (page->freelist == freelist_old &&
page->counters == counters_old) {
page->freelist = freelist_new;
page->counters = counters_new;
__slab_unlock(page);
local_irq_restore(flags);
return true;
}
__slab_unlock(page);
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_RAW_SPINLOCK(object_map_lock);
static void __fill_map(unsigned long *obj_map, struct kmem_cache *s,
struct page *page)
{
void *addr = page_address(page);
void *p;
bitmap_zero(obj_map, page->objects);
for (p = page->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 (likely(!current->kunit_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
/*
* Determine a map of object in use on a page.
*
* Node listlock must be held to guarantee that the page does
* not vanish from under us.
*/
static unsigned long *get_map(struct kmem_cache *s, struct page *page)
__acquires(&object_map_lock)
{
VM_BUG_ON(!irqs_disabled());
raw_spin_lock(&object_map_lock);
__fill_map(object_map, s, page);
return object_map;
}
static void put_map(unsigned long *map) __releases(&object_map_lock)
{
VM_BUG_ON(map != object_map);
raw_spin_unlock(&object_map_lock);
}
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 page *page, void *object)
{
void *base;
if (!object)
return 1;
base = page_address(page);
object = kasan_reset_tag(object);
object = restore_red_left(s, object);
if (object < base || object >= base + page->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);
}
static void set_track(struct kmem_cache *s, void *object,
enum track_item alloc, unsigned long addr)
{
struct track *p = get_track(s, object, alloc);
if (addr) {
#ifdef CONFIG_STACKTRACE
unsigned int nr_entries;
metadata_access_enable();
nr_entries = stack_trace_save(kasan_reset_tag(p->addrs),
TRACK_ADDRS_COUNT, 3);
metadata_access_disable();
if (nr_entries < TRACK_ADDRS_COUNT)
p->addrs[nr_entries] = 0;
#endif
p->addr = addr;
p->cpu = smp_processor_id();
p->pid = current->pid;
p->when = jiffies;
} else {
memset(p, 0, sizeof(struct track));
}
}
static void init_tracking(struct kmem_cache *s, void *object)
{
if (!(s->flags & SLAB_STORE_USER))
return;
set_track(s, object, TRACK_FREE, 0UL);
set_track(s, object, TRACK_ALLOC, 0UL);
}
static void print_track(const char *s, struct track *t, unsigned long pr_time)
{
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_STACKTRACE
{
int i;
for (i = 0; i < TRACK_ADDRS_COUNT; i++)
if (t->addrs[i])
pr_err("\t%pS\n", (void *)t->addrs[i]);
else
break;
}
#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_page_info(struct page *page)
{
pr_err("Slab 0x%p objects=%u used=%u fp=0x%p flags=%pGp\n",
page, page->objects, page->inuse, page->freelist,
&page->flags);
}
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 bool freelist_corrupted(struct kmem_cache *s, struct page *page,
void **freelist, void *nextfree)
{
if ((s->flags & SLAB_CONSISTENCY_CHECKS) &&
!check_valid_pointer(s, page, nextfree) && freelist) {
object_err(s, page, *freelist, "Freechain corrupt");
*freelist = NULL;
slab_fix(s, "Isolate corrupted freechain");
return true;
}
return false;
}
static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p)
{
unsigned int off; /* Offset of last byte */
u8 *addr = page_address(page);
print_tracking(s, p);
print_page_info(page);
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);
off += kasan_metadata_size(s);
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();
}
void object_err(struct kmem_cache *s, struct page *page,
u8 *object, char *reason)
{
if (slab_add_kunit_errors())
return;
slab_bug(s, "%s", reason);
print_trailer(s, page, object);
add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
}
static __printf(3, 4) void slab_err(struct kmem_cache *s, struct page *page,
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_page_info(page);
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);
if (s->flags & SLAB_RED_ZONE)
memset(p - s->red_left_pad, val, s->red_left_pad);
if (s->flags & __OBJECT_POISON) {
memset(p, POISON_FREE, s->object_size - 1);
p[s->object_size - 1] = POISON_END;
}
if (s->flags & SLAB_RED_ZONE)
memset(p + s->object_size, val, s->inuse - s->object_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 page *page,
u8 *object, char *what,
u8 *start, unsigned int value, unsigned int bytes)
{
u8 *fault;
u8 *end;
u8 *addr = page_address(page);
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, page, 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. 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 page *page, 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);
off += kasan_metadata_size(s);
if (size_from_object(s) == off)
return 1;
return check_bytes_and_report(s, page, p, "Object padding",
p + off, POISON_INUSE, size_from_object(s) - off);
}
/* Check the pad bytes at the end of a slab page */
static int slab_pad_check(struct kmem_cache *s, struct page *page)
{
u8 *start;
u8 *fault;
u8 *end;
u8 *pad;
int length;
int remainder;
if (!(s->flags & SLAB_POISON))
return 1;
start = page_address(page);
length = page_size(page);
end = start + length;
remainder = length % s->size;
if (!remainder)
return 1;
pad = end - remainder;
metadata_access_enable();
fault = memchr_inv(kasan_reset_tag(pad), POISON_INUSE, remainder);
metadata_access_disable();
if (!fault)
return 1;
while (end > fault && end[-1] == POISON_INUSE)
end--;
slab_err(s, page, "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);
return 0;
}
static int check_object(struct kmem_cache *s, struct page *page,
void *object, u8 val)
{
u8 *p = object;
u8 *endobject = object + s->object_size;
if (s->flags & SLAB_RED_ZONE) {
if (!check_bytes_and_report(s, page, object, "Left Redzone",
object - s->red_left_pad, val, s->red_left_pad))
return 0;
if (!check_bytes_and_report(s, page, object, "Right Redzone",
endobject, val, s->inuse - s->object_size))
return 0;
} else {
if ((s->flags & SLAB_POISON) && s->object_size < s->inuse) {
check_bytes_and_report(s, page, 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, page, p, "Poison", p,
POISON_FREE, s->object_size - 1) ||
!check_bytes_and_report(s, page, 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, page, 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, page, get_freepointer(s, p))) {
object_err(s, page, 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 page *page)
{
int maxobj;
if (!PageSlab(page)) {
slab_err(s, page, "Not a valid slab page");
return 0;
}
maxobj = order_objects(compound_order(page), s->size);
if (page->objects > maxobj) {
slab_err(s, page, "objects %u > max %u",
page->objects, maxobj);
return 0;
}
if (page->inuse > page->objects) {
slab_err(s, page, "inuse %u > max %u",
page->inuse, page->objects);
return 0;
}
/* Slab_pad_check fixes things up after itself */
slab_pad_check(s, page);
return 1;
}
/*
* Determine if a certain object on a page 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 page *page, void *search)
{
int nr = 0;
void *fp;
void *object = NULL;
int max_objects;
fp = page->freelist;
while (fp && nr <= page->objects) {
if (fp == search)
return 1;
if (!check_valid_pointer(s, page, fp)) {
if (object) {
object_err(s, page, object,
"Freechain corrupt");
set_freepointer(s, object, NULL);
} else {
slab_err(s, page, "Freepointer corrupt");
page->freelist = NULL;
page->inuse = page->objects;
slab_fix(s, "Freelist cleared");
return 0;
}
break;
}
object = fp;
fp = get_freepointer(s, object);
nr++;
}
max_objects = order_objects(compound_order(page), s->size);
if (max_objects > MAX_OBJS_PER_PAGE)
max_objects = MAX_OBJS_PER_PAGE;
if (page->objects != max_objects) {
slab_err(s, page, "Wrong number of objects. Found %d but should be %d",
page->objects, max_objects);
page->objects = max_objects;
slab_fix(s, "Number of objects adjusted");
}
if (page->inuse != page->objects - nr) {
slab_err(s, page, "Wrong object count. Counter is %d but counted were %d",
page->inuse, page->objects - nr);
page->inuse = page->objects - nr;
slab_fix(s, "Object count adjusted");
}
return search == NULL;
}
static void trace(struct kmem_cache *s, struct page *page, 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, page->inuse,
page->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 page *page)
{
if (!(s->flags & SLAB_STORE_USER))
return;
lockdep_assert_held(&n->list_lock);
list_add(&page->slab_list, &n->full);
}
static void remove_full(struct kmem_cache *s, struct kmem_cache_node *n, struct page *page)
{
if (!(s->flags & SLAB_STORE_USER))
return;
lockdep_assert_held(&n->list_lock);
list_del(&page->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, struct page *page,
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_page_debug(struct kmem_cache *s, struct page *page, void *addr)
{
if (!kmem_cache_debug_flags(s, SLAB_POISON))
return;
metadata_access_enable();
memset(kasan_reset_tag(addr), POISON_INUSE, page_size(page));
metadata_access_disable();
}
static inline int alloc_consistency_checks(struct kmem_cache *s,
struct page *page, void *object)
{
if (!check_slab(s, page))
return 0;
if (!check_valid_pointer(s, page, object)) {
object_err(s, page, object, "Freelist Pointer check fails");
return 0;
}
if (!check_object(s, page, object, SLUB_RED_INACTIVE))
return 0;
return 1;
}
static noinline int alloc_debug_processing(struct kmem_cache *s,
struct page *page,
void *object, unsigned long addr)
{
if (s->flags & SLAB_CONSISTENCY_CHECKS) {
if (!alloc_consistency_checks(s, page, object))
goto bad;
}
/* Success perform special debug activities for allocs */
if (s->flags & SLAB_STORE_USER)
set_track(s, object, TRACK_ALLOC, addr);
trace(s, page, object, 1);
init_object(s, object, SLUB_RED_ACTIVE);
return 1;
bad:
if (PageSlab(page)) {
/*
* 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");
page->inuse = page->objects;
page->freelist = NULL;
}
return 0;
}
static inline int free_consistency_checks(struct kmem_cache *s,
struct page *page, void *object, unsigned long addr)
{
if (!check_valid_pointer(s, page, object)) {
slab_err(s, page, "Invalid object pointer 0x%p", object);
return 0;
}
if (on_freelist(s, page, object)) {
object_err(s, page, object, "Object already free");
return 0;
}
if (!check_object(s, page, object, SLUB_RED_ACTIVE))
return 0;
if (unlikely(s != page->slab_cache)) {
if (!PageSlab(page)) {
slab_err(s, page, "Attempt to free object(0x%p) outside of slab",
object);
} else if (!page->slab_cache) {
pr_err("SLUB <none>: no slab for object 0x%p.\n",
object);
dump_stack();
} else
object_err(s, page, object,
"page slab pointer corrupt.");
return 0;
}
return 1;
}
/* Supports checking bulk free of a constructed freelist */
static noinline int free_debug_processing(
struct kmem_cache *s, struct page *page,
void *head, void *tail, int bulk_cnt,
unsigned long addr)
{
struct kmem_cache_node *n = get_node(s, page_to_nid(page));
void *object = head;
int cnt = 0;
unsigned long flags, flags2;
int ret = 0;
spin_lock_irqsave(&n->list_lock, flags);
slab_lock(page, &flags2);
if (s->flags & SLAB_CONSISTENCY_CHECKS) {
if (!check_slab(s, page))
goto out;
}
next_object:
cnt++;
if (s->flags & SLAB_CONSISTENCY_CHECKS) {
if (!free_consistency_checks(s, page, object, addr))
goto out;
}
if (s->flags & SLAB_STORE_USER)
set_track(s, object, TRACK_FREE, addr);
trace(s, page, 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;
}
ret = 1;
out:
if (cnt != bulk_cnt)
slab_err(s, page, "Bulk freelist count(%d) invalid(%d)\n",
bulk_cnt, cnt);
slab_unlock(page, &flags2);
spin_unlock_irqrestore(&n->list_lock, flags);
if (!ret)
slab_fix(s, "Object at 0x%p not freed", object);
return ret;
}
/*
* 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;
}
}
/*
* 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 != 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 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,
struct page *page, void *object) {}
static inline
void setup_page_debug(struct kmem_cache *s, struct page *page, void *addr) {}
static inline int alloc_debug_processing(struct kmem_cache *s,
struct page *page, void *object, unsigned long addr) { return 0; }
static inline int free_debug_processing(
struct kmem_cache *s, struct page *page,
void *head, void *tail, int bulk_cnt,
unsigned long addr) { return 0; }
static inline int slab_pad_check(struct kmem_cache *s, struct page *page)
{ return 1; }
static inline int check_object(struct kmem_cache *s, struct page *page,
void *object, u8 val) { return 1; }
static inline void add_full(struct kmem_cache *s, struct kmem_cache_node *n,
struct page *page) {}
static inline void remove_full(struct kmem_cache *s, struct kmem_cache_node *n,
struct page *page) {}
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) {}
static bool freelist_corrupted(struct kmem_cache *s, struct page *page,
void **freelist, void *nextfree)
{
return false;
}
#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 inline void *kmalloc_large_node_hook(void *ptr, size_t size, gfp_t flags)
{
ptr = kasan_kmalloc_large(ptr, size, flags);
/* As ptr might get tagged, call kmemleak hook after KASAN. */
kmemleak_alloc(ptr, size, 1, flags);
return ptr;
}
static __always_inline void kfree_hook(void *x)
{
kmemleak_free(x);
kasan_kfree_large(x);
}
static __always_inline bool slab_free_hook(struct kmem_cache *s,
void *x, bool init)
{
kmemleak_free_recursive(x, s->flags);
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, struct page *page,
void *object)
{
setup_object_debug(s, page, 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 page *alloc_slab_page(struct kmem_cache *s,
gfp_t flags, int node, struct kmem_cache_order_objects oo)
{
struct page *page;
unsigned int order = oo_order(oo);
if (node == NUMA_NO_NODE)
page = alloc_pages(flags, order);
else
page = __alloc_pages_node(node, flags, order);
return page;
}
#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 page *page,
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 page *page)
{
void *start;
void *cur;
void *next;
unsigned long idx, pos, page_limit, freelist_count;
if (page->objects < 2 || !s->random_seq)
return false;
freelist_count = oo_objects(s->oo);
pos = get_random_int() % freelist_count;
page_limit = page->objects * s->size;
start = fixup_red_left(s, page_address(page));
/* First entry is used as the base of the freelist */
cur = next_freelist_entry(s, page, &pos, start, page_limit,
freelist_count);
cur = setup_object(s, page, cur);
page->freelist = cur;
for (idx = 1; idx < page->objects; idx++) {
next = next_freelist_entry(s, page, &pos, start, page_limit,
freelist_count);
next = setup_object(s, page, 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 page *page)
{
return false;
}
#endif /* CONFIG_SLAB_FREELIST_RANDOM */
static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
{
struct page *page;
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|__GFP_NOFAIL);
page = alloc_slab_page(s, alloc_gfp, node, oo);
if (unlikely(!page)) {
oo = s->min;
alloc_gfp = flags;
/*
* Allocation may have failed due to fragmentation.
* Try a lower order alloc if possible
*/
page = alloc_slab_page(s, alloc_gfp, node, oo);
if (unlikely(!page))
goto out;
stat(s, ORDER_FALLBACK);
}
page->objects = oo_objects(oo);
account_slab_page(page, oo_order(oo), s, flags);
page->slab_cache = s;
__SetPageSlab(page);
if (page_is_pfmemalloc(page))
SetPageSlabPfmemalloc(page);
kasan_poison_slab(page);
start = page_address(page);
setup_page_debug(s, page, start);
shuffle = shuffle_freelist(s, page);
if (!shuffle) {
start = fixup_red_left(s, start);
start = setup_object(s, page, start);
page->freelist = start;
for (idx = 0, p = start; idx < page->objects - 1; idx++) {
next = p + s->size;
next = setup_object(s, page, next);
set_freepointer(s, p, next);
p = next;
}
set_freepointer(s, p, NULL);
}
page->inuse = page->objects;
page->frozen = 1;
out:
if (!page)
return NULL;
inc_slabs_node(s, page_to_nid(page), page->objects);
return page;
}
static struct page *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 page *page)
{
int order = compound_order(page);
int pages = 1 << order;
if (kmem_cache_debug_flags(s, SLAB_CONSISTENCY_CHECKS)) {
void *p;
slab_pad_check(s, page);
for_each_object(p, s, page_address(page),
page->objects)
check_object(s, page, p, SLUB_RED_INACTIVE);
}
__ClearPageSlabPfmemalloc(page);
__ClearPageSlab(page);
/* In union with page->mapping where page allocator expects NULL */
page->slab_cache = NULL;
if (current->reclaim_state)
current->reclaim_state->reclaimed_slab += pages;
unaccount_slab_page(page, order, s);
__free_pages(page, order);
}
static void rcu_free_slab(struct rcu_head *h)
{
struct page *page = container_of(h, struct page, rcu_head);
__free_slab(page->slab_cache, page);
}
static void free_slab(struct kmem_cache *s, struct page *page)
{
if (unlikely(s->flags & SLAB_TYPESAFE_BY_RCU)) {
call_rcu(&page->rcu_head, rcu_free_slab);
} else
__free_slab(s, page);
}
static void discard_slab(struct kmem_cache *s, struct page *page)
{
dec_slabs_node(s, page_to_nid(page), page->objects);
free_slab(s, page);
}
/*
* Management of partially allocated slabs.
*/
static inline void
__add_partial(struct kmem_cache_node *n, struct page *page, int tail)
{
n->nr_partial++;
if (tail == DEACTIVATE_TO_TAIL)
list_add_tail(&page->slab_list, &n->partial);
else
list_add(&page->slab_list, &n->partial);
}
static inline void add_partial(struct kmem_cache_node *n,
struct page *page, int tail)
{
lockdep_assert_held(&n->list_lock);
__add_partial(n, page, tail);
}
static inline void remove_partial(struct kmem_cache_node *n,
struct page *page)
{
lockdep_assert_held(&n->list_lock);
list_del(&page->slab_list);
n->nr_partial--;
}
/*
* 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 page *page,
int mode)
{
void *freelist;
unsigned long counters;
struct page 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 = page->freelist;
counters = page->counters;
new.counters = counters;
if (mode) {
new.inuse = page->objects;
new.freelist = NULL;
} else {
new.freelist = freelist;
}
VM_BUG_ON(new.frozen);
new.frozen = 1;
if (!__cmpxchg_double_slab(s, page,
freelist, counters,
new.freelist, new.counters,
"acquire_slab"))
return NULL;
remove_partial(n, page);
WARN_ON(!freelist);
return freelist;
}
#ifdef CONFIG_SLUB_CPU_PARTIAL
static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain);
#else
static inline void put_cpu_partial(struct kmem_cache *s, struct page *page,
int drain) { }
#endif
static inline bool pfmemalloc_match(struct page *page, 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 page **ret_page, gfp_t gfpflags)
{
struct page *page, *page2;
void *object = NULL;
unsigned long flags;
unsigned int partial_pages = 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(page, page2, &n->partial, slab_list) {
void *t;
if (!pfmemalloc_match(page, gfpflags))
continue;
t = acquire_slab(s, n, page, object == NULL);
if (!t)
break;
if (!object) {
*ret_page = page;
stat(s, ALLOC_FROM_PARTIAL);
object = t;
} else {
put_cpu_partial(s, page, 0);
stat(s, CPU_PARTIAL_NODE);
partial_pages++;
}
#ifdef CONFIG_SLUB_CPU_PARTIAL
if (!kmem_cache_has_cpu_partial(s)
|| partial_pages > s->cpu_partial_pages / 2)
break;
#else
break;
#endif
}
spin_unlock_irqrestore(&n->list_lock, flags);
return object;
}
/*
* Get a page from somewhere. Search in increasing NUMA distances.
*/
static void *get_any_partial(struct kmem_cache *s, gfp_t flags,
struct page **ret_page)
{
#ifdef CONFIG_NUMA
struct zonelist *zonelist;
struct zoneref *z;
struct zone *zone;
enum zone_type highest_zoneidx = gfp_zone(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(), 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, flags) &&
n->nr_partial > s->min_partial) {
object = get_partial_node(s, n, ret_page, flags);
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 page, lock it and return it.
*/
static void *get_partial(struct kmem_cache *s, gfp_t flags, int node,
struct page **ret_page)
{
void *object;
int searchnode = node;
if (node == NUMA_NO_NODE)
searchnode = numa_mem_id();
object = get_partial_node(s, get_node(s, searchnode), ret_page, flags);
if (object || node != NUMA_NO_NODE)
return object;
return get_any_partial(s, flags, ret_page);
}
#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
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 page'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 page *page,
void *freelist)
{
enum slab_modes { M_NONE, M_PARTIAL, M_FULL, M_FREE };
struct kmem_cache_node *n = get_node(s, page_to_nid(page));
int lock = 0, free_delta = 0;
enum slab_modes l = M_NONE, m = M_NONE;
void *nextfree, *freelist_iter, *freelist_tail;
int tail = DEACTIVATE_TO_HEAD;
unsigned long flags = 0;
struct page new;
struct page old;
if (page->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, page, &freelist_iter, nextfree))
break;
freelist_tail = freelist_iter;
free_delta++;
freelist_iter = nextfree;
}
/*
* Stage two: Unfreeze the page while splicing the per-cpu
* freelist to the head of page's freelist.
*
* Ensure that the page is unfrozen while the list presence
* reflects the actual number of objects during unfreeze.
*
* We setup the list membership and then perform a cmpxchg
* with the count. If there is a mismatch then the page
* is not unfrozen but the page is on the wrong list.
*
* Then we restart the process which may have to remove
* the page from the list that we just put it on again
* because the number of objects in the slab may have
* changed.
*/
redo:
old.freelist = READ_ONCE(page->freelist);
old.counters = READ_ONCE(page->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)
m = M_FREE;
else if (new.freelist) {
m = M_PARTIAL;
if (!lock) {
lock = 1;
/*
* Taking the spinlock removes the possibility
* that acquire_slab() will see a slab page that
* is frozen
*/
spin_lock_irqsave(&n->list_lock, flags);
}
} else {
m = M_FULL;
if (kmem_cache_debug_flags(s, SLAB_STORE_USER) && !lock) {
lock = 1;
/*
* This also ensures that the scanning of full
* slabs from diagnostic functions will not see
* any frozen slabs.
*/
spin_lock_irqsave(&n->list_lock, flags);
}
}
if (l != m) {
if (l == M_PARTIAL)
remove_partial(n, page);
else if (l == M_FULL)
remove_full(s, n, page);
if (m == M_PARTIAL)
add_partial(n, page, tail);
else if (m == M_FULL)
add_full(s, n, page);
}
l = m;
if (!cmpxchg_double_slab(s, page,
old.freelist, old.counters,
new.freelist, new.counters,
"unfreezing slab"))
goto redo;
if (lock)
spin_unlock_irqrestore(&n->list_lock, flags);
if (m == M_PARTIAL)
stat(s, tail);
else if (m == M_FULL)
stat(s, DEACTIVATE_FULL);
else if (m == M_FREE) {
stat(s, DEACTIVATE_EMPTY);
discard_slab(s, page);
stat(s, FREE_SLAB);
}
}
#ifdef CONFIG_SLUB_CPU_PARTIAL
static void __unfreeze_partials(struct kmem_cache *s, struct page *partial_page)
{
struct kmem_cache_node *n = NULL, *n2 = NULL;
struct page *page, *discard_page = NULL;
unsigned long flags = 0;
while (partial_page) {
struct page new;
struct page old;
page = partial_page;
partial_page = page->next;
n2 = get_node(s, page_to_nid(page));
if (n != n2) {
if (n)
spin_unlock_irqrestore(&n->list_lock, flags);
n = n2;
spin_lock_irqsave(&n->list_lock, flags);
}
do {
old.freelist = page->freelist;
old.counters = page->counters;
VM_BUG_ON(!old.frozen);
new.counters = old.counters;
new.freelist = old.freelist;
new.frozen = 0;
} while (!__cmpxchg_double_slab(s, page,
old.freelist, old.counters,
new.freelist, new.counters,
"unfreezing slab"));
if (unlikely(!new.inuse && n->nr_partial >= s->min_partial)) {
page->next = discard_page;
discard_page = page;
} else {
add_partial(n, page, DEACTIVATE_TO_TAIL);
stat(s, FREE_ADD_PARTIAL);
}
}
if (n)
spin_unlock_irqrestore(&n->list_lock, flags);
while (discard_page) {
page = discard_page;
discard_page = discard_page->next;
stat(s, DEACTIVATE_EMPTY);
discard_slab(s, page);
stat(s, FREE_SLAB);
}
}
/*
* Unfreeze all the cpu partial slabs.
*/
static void unfreeze_partials(struct kmem_cache *s)
{
struct page *partial_page;
unsigned long flags;
local_lock_irqsave(&s->cpu_slab->lock, flags);
partial_page = 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_page)
__unfreeze_partials(s, partial_page);
}
static void unfreeze_partials_cpu(struct kmem_cache *s,
struct kmem_cache_cpu *c)
{
struct page *partial_page;
partial_page = slub_percpu_partial(c);
c->partial = NULL;
if (partial_page)
__unfreeze_partials(s, partial_page);
}
/*
* Put a page that was just frozen (in __slab_free|get_partial_node) into a
* partial page 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 page *page, int drain)
{
struct page *oldpage;
struct page *page_to_unfreeze = NULL;
unsigned long flags;
int pages = 0;
local_lock_irqsave(&s->cpu_slab->lock, flags);
oldpage = this_cpu_read(s->cpu_slab->partial);
if (oldpage) {
if (drain && oldpage->pages >= s->cpu_partial_pages) {
/*
* Partial array is full. Move the existing set to the
* per node partial list. Postpone the actual unfreezing
* outside of the critical section.
*/
page_to_unfreeze = oldpage;
oldpage = NULL;
} else {
pages = oldpage->pages;
}
}
pages++;
page->pages = pages;
page->next = oldpage;
this_cpu_write(s->cpu_slab->partial, page);
local_unlock_irqrestore(&s->cpu_slab->lock, flags);
if (page_to_unfreeze) {
__unfreeze_partials(s, page_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 page *page;
void *freelist;
local_lock_irqsave(&s->cpu_slab->lock, flags);
page = c->page;
freelist = c->freelist;
c->page = NULL;
c->freelist = NULL;
c->tid = next_tid(c->tid);
local_unlock_irqrestore(&s->cpu_slab->lock, flags);
if (page) {
deactivate_slab(s, page, 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 page *page = c->page;
c->page = NULL;
c->freelist = NULL;
c->tid = next_tid(c->tid);
if (page) {
deactivate_slab(s, page, 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->page)
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->page || 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;
schedule_work_on(cpu, &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;
}
/*
* Check if the objects in a per cpu structure fit numa
* locality expectations.
*/
static inline int node_match(struct page *page, int node)
{
#ifdef CONFIG_NUMA
if (node != NUMA_NO_NODE && page_to_nid(page) != node)
return 0;
#endif
return 1;
}
#ifdef CONFIG_SLUB_DEBUG
static int count_free(struct page *page)
{
return page->objects - page->inuse;
}
static inline unsigned long node_nr_objs(struct kmem_cache_node *n)
{
return atomic_long_read(&n->total_objects);
}
#endif /* CONFIG_SLUB_DEBUG */
#if defined(CONFIG_SLUB_DEBUG) || defined(CONFIG_SYSFS)
static unsigned long count_partial(struct kmem_cache_node *n,
int (*get_count)(struct page *))
{
unsigned long flags;
unsigned long x = 0;
struct page *page;
spin_lock_irqsave(&n->list_lock, flags);
list_for_each_entry(page, &n->partial, slab_list)
x += get_count(page);
spin_unlock_irqrestore(&n->list_lock, flags);
return x;
}
#endif /* CONFIG_SLUB_DEBUG || CONFIG_SYSFS */
static noinline void
slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid)
{
#ifdef CONFIG_SLUB_DEBUG
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);
}
#endif
}
static inline bool pfmemalloc_match(struct page *page, gfp_t gfpflags)
{
if (unlikely(PageSlabPfmemalloc(page)))
return gfp_pfmemalloc_allowed(gfpflags);
return true;
}
/*
* A variant of pfmemalloc_match() that tests page flags without asserting
* PageSlab. Intended for opportunistic checks before taking a lock and
* rechecking that nobody else freed the page under us.
*/
static inline bool pfmemalloc_match_unsafe(struct page *page, gfp_t gfpflags)
{
if (unlikely(__PageSlabPfmemalloc(page)))
return gfp_pfmemalloc_allowed(gfpflags);
return true;
}
/*
* Check the page->freelist of a page and either transfer the freelist to the
* per cpu freelist or deactivate the page.
*
* The page is still frozen if the return value is not NULL.
*
* If this function returns NULL then the page has been unfrozen.
*/
static inline void *get_freelist(struct kmem_cache *s, struct page *page)
{
struct page new;
unsigned long counters;
void *freelist;
lockdep_assert_held(this_cpu_ptr(&s->cpu_slab->lock));
do {
freelist = page->freelist;
counters = page->counters;
new.counters = counters;
VM_BUG_ON(!new.frozen);
new.inuse = page->objects;
new.frozen = freelist != NULL;
} while (!__cmpxchg_double_slab(s, page,
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)
{
void *freelist;
struct page *page;
unsigned long flags;
stat(s, ALLOC_SLOWPATH);
reread_page:
page = READ_ONCE(c->page);
if (!page) {
/*
* 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(page, 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;
goto redo;
} 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_unsafe(page, gfpflags)))
goto deactivate_slab;
/* must check again c->page in case we got preempted and it changed */
local_lock_irqsave(&s->cpu_slab->lock, flags);
if (unlikely(page != c->page)) {
local_unlock_irqrestore(&s->cpu_slab->lock, flags);
goto reread_page;
}
freelist = c->freelist;
if (freelist)
goto load_freelist;
freelist = get_freelist(s, page);
if (!freelist) {
c->page = NULL;
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.
* page is pointing to the page from which the objects are obtained.
* That page must be frozen for per cpu allocations to work.
*/
VM_BUG_ON(!c->page->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 (page != c->page) {
local_unlock_irqrestore(&s->cpu_slab->lock, flags);
goto reread_page;
}
freelist = c->freelist;
c->page = NULL;
c->freelist = NULL;
local_unlock_irqrestore(&s->cpu_slab->lock, flags);
deactivate_slab(s, page, freelist);
new_slab:
if (slub_percpu_partial(c)) {
local_lock_irqsave(&s->cpu_slab->lock, flags);
if (unlikely(c->page)) {
local_unlock_irqrestore(&s->cpu_slab->lock, flags);
goto reread_page;
}
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;
}
page = c->page = slub_percpu_partial(c);
slub_set_percpu_partial(c, page);
local_unlock_irqrestore(&s->cpu_slab->lock, flags);
stat(s, CPU_PARTIAL_ALLOC);
goto redo;
}
new_objects:
freelist = get_partial(s, gfpflags, node, &page);
if (freelist)
goto check_new_page;
slub_put_cpu_ptr(s->cpu_slab);
page = new_slab(s, gfpflags, node);
c = slub_get_cpu_ptr(s->cpu_slab);
if (unlikely(!page)) {
slab_out_of_memory(s, gfpflags, node);
return NULL;
}
/*
* No other reference to the page yet so we can
* muck around with it freely without cmpxchg
*/
freelist = page->freelist;
page->freelist = NULL;
stat(s, ALLOC_SLAB);
check_new_page:
if (kmem_cache_debug(s)) {
if (!alloc_debug_processing(s, page, freelist, addr)) {
/* Slab failed checks. Next slab needed */
goto new_slab;
} else {
/*
* For debug case, we don't load freelist so that all
* allocations go through alloc_debug_processing()
*/
goto return_single;
}
}
if (unlikely(!pfmemalloc_match(page, gfpflags)))
/*
* For !pfmemalloc_match() case we don't load freelist so that
* we don't make further mismatched allocations easier.
*/
goto return_single;
retry_load_page:
local_lock_irqsave(&s->cpu_slab->lock, flags);
if (unlikely(c->page)) {
void *flush_freelist = c->freelist;
struct page *flush_page = c->page;
c->page = NULL;
c->freelist = NULL;
c->tid = next_tid(c->tid);
local_unlock_irqrestore(&s->cpu_slab->lock, flags);
deactivate_slab(s, flush_page, flush_freelist);
stat(s, CPUSLAB_FLUSH);
goto retry_load_page;
}
c->page = page;
goto load_freelist;
return_single:
deactivate_slab(s, page, get_freepointer(s, freelist));
return 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)
{
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);
#ifdef CONFIG_PREEMPT_COUNT
slub_put_cpu_ptr(s->cpu_slab);
#endif
return p;
}
/*
* 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 __always_inline void *slab_alloc_node(struct kmem_cache *s,
gfp_t gfpflags, int node, unsigned long addr, size_t orig_size)
{
void *object;
struct kmem_cache_cpu *c;
struct page *page;
unsigned long tid;
struct obj_cgroup *objcg = NULL;
bool init = false;
s = slab_pre_alloc_hook(s, &objcg, 1, gfpflags);
if (!s)
return NULL;
object = kfence_alloc(s, orig_size, gfpflags);
if (unlikely(object))
goto out;
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 page associated with previous tid
* won't be used with current tid. If we fetch tid first, object and
* page 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();