blob: 5710788c58e72cb7b943f7ab8c9dd4a3b520f2f3 [file] [log] [blame]
/*
* 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 operatios
* 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/bitops.h>
#include <linux/slab.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/kmemcheck.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/memory.h>
#include <linux/math64.h>
#include <linux/fault-inject.h>
#include <linux/stacktrace.h>
#include <trace/events/kmem.h>
/*
* Lock order:
* 1. slub_lock (Global Semaphore)
* 2. node->list_lock
* 3. slab_lock(page) (Only on some arches and for debugging)
*
* slub_lock
*
* The role of the slub_lock is to protect the list of all the slabs
* and to synchronize major metadata changes to slab cache structures.
*
* 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 the second
* double word in the page struct. Meaning
* A. page->freelist -> List of object free in a page
* B. page->counters -> Counters of objects
* C. page->frozen -> frozen state
*
* If a slab is frozen then it is exempt from list management. It is not
* on any 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.
*
* 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.
* Interrupts are disabled during allocation and deallocation in order to
* make the slab allocator safe to use in the context of an irq. In addition
* interrupts are disabled to ensure that the processor does not change
* while handling per_cpu slabs, due to kernel preemption.
*
* 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.
*
* Overloading of page flags that are otherwise used for LRU management.
*
* PageActive 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.
*
* PageError Slab requires special handling due to debug
* options set. This moves slab handling out of
* the fast path and disables lockless freelists.
*/
#define SLAB_DEBUG_FLAGS (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER | \
SLAB_TRACE | SLAB_DEBUG_FREE)
static inline int kmem_cache_debug(struct kmem_cache *s)
{
#ifdef CONFIG_SLUB_DEBUG
return unlikely(s->flags & SLAB_DEBUG_FLAGS);
#else
return 0;
#endif
}
/*
* Issues still to be resolved:
*
* - Support PAGE_ALLOC_DEBUG. Should be easy to do.
*
* - Variable sizing of the per node arrays
*/
/* Enable to test recovery from slab corruption on boot */
#undef SLUB_RESILIENCY_TEST
/* Enable to log cmpxchg failures */
#undef SLUB_DEBUG_CMPXCHG
/*
* Mininum 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 the.
*/
#define MAX_PARTIAL 10
#define DEBUG_DEFAULT_FLAGS (SLAB_DEBUG_FREE | SLAB_RED_ZONE | \
SLAB_POISON | SLAB_STORE_USER)
/*
* 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)
/*
* Set of flags that will prevent slab merging
*/
#define SLUB_NEVER_MERGE (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER | \
SLAB_TRACE | SLAB_DESTROY_BY_RCU | SLAB_NOLEAKTRACE | \
SLAB_FAILSLAB)
#define SLUB_MERGE_SAME (SLAB_DEBUG_FREE | SLAB_RECLAIM_ACCOUNT | \
SLAB_CACHE_DMA | SLAB_NOTRACK)
#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 */
#define __OBJECT_POISON 0x80000000UL /* Poison object */
#define __CMPXCHG_DOUBLE 0x40000000UL /* Use cmpxchg_double */
static int kmem_size = sizeof(struct kmem_cache);
#ifdef CONFIG_SMP
static struct notifier_block slab_notifier;
#endif
static enum {
DOWN, /* No slab functionality available */
PARTIAL, /* Kmem_cache_node works */
UP, /* Everything works but does not show up in sysfs */
SYSFS /* Sysfs up */
} slab_state = DOWN;
/* A list of all slab caches on the system */
static DECLARE_RWSEM(slub_lock);
static LIST_HEAD(slab_caches);
/*
* 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 *);
static void sysfs_slab_remove(struct kmem_cache *);
#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; }
static inline void sysfs_slab_remove(struct kmem_cache *s)
{
kfree(s->name);
kfree(s);
}
#endif
static inline void stat(const struct kmem_cache *s, enum stat_item si)
{
#ifdef CONFIG_SLUB_STATS
__this_cpu_inc(s->cpu_slab->stat[si]);
#endif
}
/********************************************************************
* Core slab cache functions
*******************************************************************/
int slab_is_available(void)
{
return slab_state >= UP;
}
static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node)
{
return s->node[node];
}
/* 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, const void *object)
{
void *base;
if (!object)
return 1;
base = page_address(page);
if (object < base || object >= base + page->objects * s->size ||
(object - base) % s->size) {
return 0;
}
return 1;
}
static inline void *get_freepointer(struct kmem_cache *s, void *object)
{
return *(void **)(object + s->offset);
}
static inline void *get_freepointer_safe(struct kmem_cache *s, void *object)
{
void *p;
#ifdef CONFIG_DEBUG_PAGEALLOC
probe_kernel_read(&p, (void **)(object + s->offset), sizeof(p));
#else
p = get_freepointer(s, object);
#endif
return p;
}
static inline void set_freepointer(struct kmem_cache *s, void *object, void *fp)
{
*(void **)(object + s->offset) = fp;
}
/* Loop over all objects in a slab */
#define for_each_object(__p, __s, __addr, __objects) \
for (__p = (__addr); __p < (__addr) + (__objects) * (__s)->size;\
__p += (__s)->size)
/* Determine object index from a given position */
static inline int slab_index(void *p, struct kmem_cache *s, void *addr)
{
return (p - addr) / s->size;
}
static inline size_t slab_ksize(const struct kmem_cache *s)
{
#ifdef CONFIG_SLUB_DEBUG
/*
* Debugging requires use of the padding between object
* and whatever may come after it.
*/
if (s->flags & (SLAB_RED_ZONE | SLAB_POISON))
return s->objsize;
#endif
/*
* If we have the need to store the freelist pointer
* back there or track user information then we can
* only use the space before that information.
*/
if (s->flags & (SLAB_DESTROY_BY_RCU | SLAB_STORE_USER))
return s->inuse;
/*
* Else we can use all the padding etc for the allocation
*/
return s->size;
}
static inline int order_objects(int order, unsigned long size, int reserved)
{
return ((PAGE_SIZE << order) - reserved) / size;
}
static inline struct kmem_cache_order_objects oo_make(int order,
unsigned long size, int reserved)
{
struct kmem_cache_order_objects x = {
(order << OO_SHIFT) + order_objects(order, size, reserved)
};
return x;
}
static inline int oo_order(struct kmem_cache_order_objects x)
{
return x.x >> OO_SHIFT;
}
static inline int oo_objects(struct kmem_cache_order_objects x)
{
return x.x & OO_MASK;
}
/*
* Per slab locking using the pagelock
*/
static __always_inline void slab_lock(struct page *page)
{
bit_spin_lock(PG_locked, &page->flags);
}
static __always_inline void slab_unlock(struct page *page)
{
__bit_spin_unlock(PG_locked, &page->flags);
}
/* Interrupts must be disabled (for the fallback code to work right) */
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)
{
VM_BUG_ON(!irqs_disabled());
#ifdef CONFIG_CMPXCHG_DOUBLE
if (s->flags & __CMPXCHG_DOUBLE) {
if (cmpxchg_double(&page->freelist,
freelist_old, counters_old,
freelist_new, counters_new))
return 1;
} else
#endif
{
slab_lock(page);
if (page->freelist == freelist_old && page->counters == counters_old) {
page->freelist = freelist_new;
page->counters = counters_new;
slab_unlock(page);
return 1;
}
slab_unlock(page);
}
cpu_relax();
stat(s, CMPXCHG_DOUBLE_FAIL);
#ifdef SLUB_DEBUG_CMPXCHG
printk(KERN_INFO "%s %s: cmpxchg double redo ", n, s->name);
#endif
return 0;
}
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)
{
#ifdef CONFIG_CMPXCHG_DOUBLE
if (s->flags & __CMPXCHG_DOUBLE) {
if (cmpxchg_double(&page->freelist,
freelist_old, counters_old,
freelist_new, counters_new))
return 1;
} 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 1;
}
slab_unlock(page);
local_irq_restore(flags);
}
cpu_relax();
stat(s, CMPXCHG_DOUBLE_FAIL);
#ifdef SLUB_DEBUG_CMPXCHG
printk(KERN_INFO "%s %s: cmpxchg double redo ", n, s->name);
#endif
return 0;
}
#ifdef CONFIG_SLUB_DEBUG
/*
* 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 void get_map(struct kmem_cache *s, struct page *page, unsigned long *map)
{
void *p;
void *addr = page_address(page);
for (p = page->freelist; p; p = get_freepointer(s, p))
set_bit(slab_index(p, s, addr), map);
}
/*
* Debug settings:
*/
#ifdef CONFIG_SLUB_DEBUG_ON
static int slub_debug = DEBUG_DEFAULT_FLAGS;
#else
static int slub_debug;
#endif
static char *slub_debug_slabs;
static int disable_higher_order_debug;
/*
* Object debugging
*/
static void print_section(char *text, u8 *addr, unsigned int length)
{
print_hex_dump(KERN_ERR, text, DUMP_PREFIX_ADDRESS, 16, 1, addr,
length, 1);
}
static struct track *get_track(struct kmem_cache *s, void *object,
enum track_item alloc)
{
struct track *p;
if (s->offset)
p = object + s->offset + sizeof(void *);
else
p = object + s->inuse;
return 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
struct stack_trace trace;
int i;
trace.nr_entries = 0;
trace.max_entries = TRACK_ADDRS_COUNT;
trace.entries = p->addrs;
trace.skip = 3;
save_stack_trace(&trace);
/* See rant in lockdep.c */
if (trace.nr_entries != 0 &&
trace.entries[trace.nr_entries - 1] == ULONG_MAX)
trace.nr_entries--;
for (i = trace.nr_entries; i < TRACK_ADDRS_COUNT; i++)
p->addrs[i] = 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)
{
if (!t->addr)
return;
printk(KERN_ERR "INFO: %s in %pS age=%lu cpu=%u pid=%d\n",
s, (void *)t->addr, jiffies - t->when, t->cpu, t->pid);
#ifdef CONFIG_STACKTRACE
{
int i;
for (i = 0; i < TRACK_ADDRS_COUNT; i++)
if (t->addrs[i])
printk(KERN_ERR "\t%pS\n", (void *)t->addrs[i]);
else
break;
}
#endif
}
static void print_tracking(struct kmem_cache *s, void *object)
{
if (!(s->flags & SLAB_STORE_USER))
return;
print_track("Allocated", get_track(s, object, TRACK_ALLOC));
print_track("Freed", get_track(s, object, TRACK_FREE));
}
static void print_page_info(struct page *page)
{
printk(KERN_ERR "INFO: Slab 0x%p objects=%u used=%u fp=0x%p flags=0x%04lx\n",
page, page->objects, page->inuse, page->freelist, page->flags);
}
static void slab_bug(struct kmem_cache *s, char *fmt, ...)
{
va_list args;
char buf[100];
va_start(args, fmt);
vsnprintf(buf, sizeof(buf), fmt, args);
va_end(args);
printk(KERN_ERR "========================================"
"=====================================\n");
printk(KERN_ERR "BUG %s: %s\n", s->name, buf);
printk(KERN_ERR "----------------------------------------"
"-------------------------------------\n\n");
}
static void slab_fix(struct kmem_cache *s, char *fmt, ...)
{
va_list args;
char buf[100];
va_start(args, fmt);
vsnprintf(buf, sizeof(buf), fmt, args);
va_end(args);
printk(KERN_ERR "FIX %s: %s\n", s->name, buf);
}
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);
printk(KERN_ERR "INFO: Object 0x%p @offset=%tu fp=0x%p\n\n",
p, p - addr, get_freepointer(s, p));
if (p > addr + 16)
print_section("Bytes b4 ", p - 16, 16);
print_section("Object ", p, min_t(unsigned long, s->objsize,
PAGE_SIZE));
if (s->flags & SLAB_RED_ZONE)
print_section("Redzone ", p + s->objsize,
s->inuse - s->objsize);
if (s->offset)
off = s->offset + sizeof(void *);
else
off = s->inuse;
if (s->flags & SLAB_STORE_USER)
off += 2 * sizeof(struct track);
if (off != s->size)
/* Beginning of the filler is the free pointer */
print_section("Padding ", p + off, s->size - off);
dump_stack();
}
static void object_err(struct kmem_cache *s, struct page *page,
u8 *object, char *reason)
{
slab_bug(s, "%s", reason);
print_trailer(s, page, object);
}
static void slab_err(struct kmem_cache *s, struct page *page, char *fmt, ...)
{
va_list args;
char buf[100];
va_start(args, fmt);
vsnprintf(buf, sizeof(buf), fmt, args);
va_end(args);
slab_bug(s, "%s", buf);
print_page_info(page);
dump_stack();
}
static void init_object(struct kmem_cache *s, void *object, u8 val)
{
u8 *p = object;
if (s->flags & __OBJECT_POISON) {
memset(p, POISON_FREE, s->objsize - 1);
p[s->objsize - 1] = POISON_END;
}
if (s->flags & SLAB_RED_ZONE)
memset(p + s->objsize, val, s->inuse - s->objsize);
}
static void restore_bytes(struct kmem_cache *s, char *message, u8 data,
void *from, void *to)
{
slab_fix(s, "Restoring 0x%p-0x%p=0x%x\n", 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;
fault = memchr_inv(start, value, bytes);
if (!fault)
return 1;
end = start + bytes;
while (end > fault && end[-1] == value)
end--;
slab_bug(s, "%s overwritten", what);
printk(KERN_ERR "INFO: 0x%p-0x%p. First byte 0x%x instead of 0x%x\n",
fault, end - 1, fault[0], value);
print_trailer(s, page, object);
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 the first word of the object.
*
* Poisoning uses 0x6b (POISON_FREE) and the last byte is
* 0xa5 (POISON_END)
*
* object + s->objsize
* Padding to reach word boundary. This is also used for Redzoning.
* Padding is extended by another word if Redzoning is enabled and
* objsize == 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 mininum
* 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 objsize 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 = s->inuse; /* The end of info */
if (s->offset)
/* Freepointer is placed after the object. */
off += sizeof(void *);
if (s->flags & SLAB_STORE_USER)
/* We also have user information there */
off += 2 * sizeof(struct track);
if (s->size == off)
return 1;
return check_bytes_and_report(s, page, p, "Object padding",
p + off, POISON_INUSE, s->size - 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;
int length;
int remainder;
if (!(s->flags & SLAB_POISON))
return 1;
start = page_address(page);
length = (PAGE_SIZE << compound_order(page)) - s->reserved;
end = start + length;
remainder = length % s->size;
if (!remainder)
return 1;
fault = memchr_inv(end - remainder, POISON_INUSE, remainder);
if (!fault)
return 1;
while (end > fault && end[-1] == POISON_INUSE)
end--;
slab_err(s, page, "Padding overwritten. 0x%p-0x%p", fault, end - 1);
print_section("Padding ", end - remainder, remainder);
restore_bytes(s, "slab padding", POISON_INUSE, end - remainder, 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->objsize;
if (s->flags & SLAB_RED_ZONE) {
if (!check_bytes_and_report(s, page, object, "Redzone",
endobject, val, s->inuse - s->objsize))
return 0;
} else {
if ((s->flags & SLAB_POISON) && s->objsize < s->inuse) {
check_bytes_and_report(s, page, p, "Alignment padding",
endobject, POISON_INUSE, s->inuse - s->objsize);
}
}
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->objsize - 1) ||
!check_bytes_and_report(s, page, p, "Poison",
p + s->objsize - 1, POISON_END, 1)))
return 0;
/*
* check_pad_bytes cleans up on its own.
*/
check_pad_bytes(s, page, p);
}
if (!s->offset && 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;
VM_BUG_ON(!irqs_disabled());
if (!PageSlab(page)) {
slab_err(s, page, "Not a valid slab page");
return 0;
}
maxobj = order_objects(compound_order(page), s->size, s->reserved);
if (page->objects > maxobj) {
slab_err(s, page, "objects %u > max %u",
s->name, page->objects, maxobj);
return 0;
}
if (page->inuse > page->objects) {
slab_err(s, page, "inuse %u > max %u",
s->name, 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;
unsigned long 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);
break;
} 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, s->reserved);
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) {
printk(KERN_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("Object ", (void *)object, s->objsize);
dump_stack();
}
}
/*
* Hooks for other subsystems that check memory allocations. In a typical
* production configuration these hooks all should produce no code at all.
*/
static inline int slab_pre_alloc_hook(struct kmem_cache *s, gfp_t flags)
{
flags &= gfp_allowed_mask;
lockdep_trace_alloc(flags);
might_sleep_if(flags & __GFP_WAIT);
return should_failslab(s->objsize, flags, s->flags);
}
static inline void slab_post_alloc_hook(struct kmem_cache *s, gfp_t flags, void *object)
{
flags &= gfp_allowed_mask;
kmemcheck_slab_alloc(s, flags, object, slab_ksize(s));
kmemleak_alloc_recursive(object, s->objsize, 1, s->flags, flags);
}
static inline void slab_free_hook(struct kmem_cache *s, void *x)
{
kmemleak_free_recursive(x, s->flags);
/*
* Trouble is that we may no longer disable interupts in the fast path
* So in order to make the debug calls that expect irqs to be
* disabled we need to disable interrupts temporarily.
*/
#if defined(CONFIG_KMEMCHECK) || defined(CONFIG_LOCKDEP)
{
unsigned long flags;
local_irq_save(flags);
kmemcheck_slab_free(s, x, s->objsize);
debug_check_no_locks_freed(x, s->objsize);
local_irq_restore(flags);
}
#endif
if (!(s->flags & SLAB_DEBUG_OBJECTS))
debug_check_no_obj_freed(x, s->objsize);
}
/*
* Tracking of fully allocated slabs for debugging purposes.
*
* list_lock must be held.
*/
static void add_full(struct kmem_cache *s,
struct kmem_cache_node *n, struct page *page)
{
if (!(s->flags & SLAB_STORE_USER))
return;
list_add(&page->lru, &n->full);
}
/*
* list_lock must be held.
*/
static void remove_full(struct kmem_cache *s, struct page *page)
{
if (!(s->flags & SLAB_STORE_USER))
return;
list_del(&page->lru);
}
/* 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 (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 (!(s->flags & (SLAB_STORE_USER|SLAB_RED_ZONE|__OBJECT_POISON)))
return;
init_object(s, object, SLUB_RED_INACTIVE);
init_tracking(s, object);
}
static noinline int alloc_debug_processing(struct kmem_cache *s, struct page *page,
void *object, unsigned long addr)
{
if (!check_slab(s, page))
goto bad;
if (!check_valid_pointer(s, page, object)) {
object_err(s, page, object, "Freelist Pointer check fails");
goto bad;
}
if (!check_object(s, page, object, SLUB_RED_INACTIVE))
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 noinline int free_debug_processing(struct kmem_cache *s,
struct page *page, void *object, unsigned long addr)
{
unsigned long flags;
int rc = 0;
local_irq_save(flags);
slab_lock(page);
if (!check_slab(s, page))
goto fail;
if (!check_valid_pointer(s, page, object)) {
slab_err(s, page, "Invalid object pointer 0x%p", object);
goto fail;
}
if (on_freelist(s, page, object)) {
object_err(s, page, object, "Object already free");
goto fail;
}
if (!check_object(s, page, object, SLUB_RED_ACTIVE))
goto out;
if (unlikely(s != page->slab)) {
if (!PageSlab(page)) {
slab_err(s, page, "Attempt to free object(0x%p) "
"outside of slab", object);
} else if (!page->slab) {
printk(KERN_ERR
"SLUB <none>: no slab for object 0x%p.\n",
object);
dump_stack();
} else
object_err(s, page, object,
"page slab pointer corrupt.");
goto fail;
}
if (s->flags & SLAB_STORE_USER)
set_track(s, object, TRACK_FREE, addr);
trace(s, page, object, 0);
init_object(s, object, SLUB_RED_INACTIVE);
rc = 1;
out:
slab_unlock(page);
local_irq_restore(flags);
return rc;
fail:
slab_fix(s, "Object at 0x%p not freed", object);
goto out;
}
static int __init setup_slub_debug(char *str)
{
slub_debug = DEBUG_DEFAULT_FLAGS;
if (*str++ != '=' || !*str)
/*
* No options specified. Switch on full debugging.
*/
goto out;
if (*str == ',')
/*
* No options but restriction on slabs. This means full
* debugging for slabs matching a pattern.
*/
goto check_slabs;
if (tolower(*str) == 'o') {
/*
* Avoid enabling debugging on caches if its minimum order
* would increase as a result.
*/
disable_higher_order_debug = 1;
goto out;
}
slub_debug = 0;
if (*str == '-')
/*
* Switch off all debugging measures.
*/
goto out;
/*
* Determine which debug features should be switched on
*/
for (; *str && *str != ','; str++) {
switch (tolower(*str)) {
case 'f':
slub_debug |= SLAB_DEBUG_FREE;
break;
case 'z':
slub_debug |= SLAB_RED_ZONE;
break;
case 'p':
slub_debug |= SLAB_POISON;
break;
case 'u':
slub_debug |= SLAB_STORE_USER;
break;
case 't':
slub_debug |= SLAB_TRACE;
break;
case 'a':
slub_debug |= SLAB_FAILSLAB;
break;
default:
printk(KERN_ERR "slub_debug option '%c' "
"unknown. skipped\n", *str);
}
}
check_slabs:
if (*str == ',')
slub_debug_slabs = str + 1;
out:
return 1;
}
__setup("slub_debug", setup_slub_debug);
static unsigned long kmem_cache_flags(unsigned long objsize,
unsigned long flags, const char *name,
void (*ctor)(void *))
{
/*
* Enable debugging if selected on the kernel commandline.
*/
if (slub_debug && (!slub_debug_slabs ||
!strncmp(slub_debug_slabs, name, strlen(slub_debug_slabs))))
flags |= slub_debug;
return flags;
}
#else
static inline void setup_object_debug(struct kmem_cache *s,
struct page *page, void *object) {}
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 *object, 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 page *page) {}
static inline unsigned long kmem_cache_flags(unsigned long objsize,
unsigned long flags, const char *name,
void (*ctor)(void *))
{
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 inline int slab_pre_alloc_hook(struct kmem_cache *s, gfp_t flags)
{ return 0; }
static inline void slab_post_alloc_hook(struct kmem_cache *s, gfp_t flags,
void *object) {}
static inline void slab_free_hook(struct kmem_cache *s, void *x) {}
#endif /* CONFIG_SLUB_DEBUG */
/*
* Slab allocation and freeing
*/
static inline struct page *alloc_slab_page(gfp_t flags, int node,
struct kmem_cache_order_objects oo)
{
int order = oo_order(oo);
flags |= __GFP_NOTRACK;
if (node == NUMA_NO_NODE)
return alloc_pages(flags, order);
else
return alloc_pages_exact_node(node, flags, order);
}
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;
flags &= gfp_allowed_mask;
if (flags & __GFP_WAIT)
local_irq_enable();
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;
page = alloc_slab_page(alloc_gfp, node, oo);
if (unlikely(!page)) {
oo = s->min;
/*
* Allocation may have failed due to fragmentation.
* Try a lower order alloc if possible
*/
page = alloc_slab_page(flags, node, oo);
if (page)
stat(s, ORDER_FALLBACK);
}
if (flags & __GFP_WAIT)
local_irq_disable();
if (!page)
return NULL;
if (kmemcheck_enabled
&& !(s->flags & (SLAB_NOTRACK | DEBUG_DEFAULT_FLAGS))) {
int pages = 1 << oo_order(oo);
kmemcheck_alloc_shadow(page, oo_order(oo), flags, node);
/*
* Objects from caches that have a constructor don't get
* cleared when they're allocated, so we need to do it here.
*/
if (s->ctor)
kmemcheck_mark_uninitialized_pages(page, pages);
else
kmemcheck_mark_unallocated_pages(page, pages);
}
page->objects = oo_objects(oo);
mod_zone_page_state(page_zone(page),
(s->flags & SLAB_RECLAIM_ACCOUNT) ?
NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE,
1 << oo_order(oo));
return page;
}
static void setup_object(struct kmem_cache *s, struct page *page,
void *object)
{
setup_object_debug(s, page, object);
if (unlikely(s->ctor))
s->ctor(object);
}
static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
{
struct page *page;
void *start;
void *last;
void *p;
BUG_ON(flags & GFP_SLAB_BUG_MASK);
page = allocate_slab(s,
flags & (GFP_RECLAIM_MASK | GFP_CONSTRAINT_MASK), node);
if (!page)
goto out;
inc_slabs_node(s, page_to_nid(page), page->objects);
page->slab = s;
page->flags |= 1 << PG_slab;
start = page_address(page);
if (unlikely(s->flags & SLAB_POISON))
memset(start, POISON_INUSE, PAGE_SIZE << compound_order(page));
last = start;
for_each_object(p, s, start, page->objects) {
setup_object(s, page, last);
set_freepointer(s, last, p);
last = p;
}
setup_object(s, page, last);
set_freepointer(s, last, NULL);
page->freelist = start;
page->inuse = page->objects;
page->frozen = 1;
out:
return page;
}
static void __free_slab(struct kmem_cache *s, struct page *page)
{
int order = compound_order(page);
int pages = 1 << order;
if (kmem_cache_debug(s)) {
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);
}
kmemcheck_free_shadow(page, compound_order(page));
mod_zone_page_state(page_zone(page),
(s->flags & SLAB_RECLAIM_ACCOUNT) ?
NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE,
-pages);
__ClearPageSlab(page);
reset_page_mapcount(page);
if (current->reclaim_state)
current->reclaim_state->reclaimed_slab += pages;
__free_pages(page, order);
}
#define need_reserve_slab_rcu \
(sizeof(((struct page *)NULL)->lru) < sizeof(struct rcu_head))
static void rcu_free_slab(struct rcu_head *h)
{
struct page *page;
if (need_reserve_slab_rcu)
page = virt_to_head_page(h);
else
page = container_of((struct list_head *)h, struct page, lru);
__free_slab(page->slab, page);
}
static void free_slab(struct kmem_cache *s, struct page *page)
{
if (unlikely(s->flags & SLAB_DESTROY_BY_RCU)) {
struct rcu_head *head;
if (need_reserve_slab_rcu) {
int order = compound_order(page);
int offset = (PAGE_SIZE << order) - s->reserved;
VM_BUG_ON(s->reserved != sizeof(*head));
head = page_address(page) + offset;
} else {
/*
* RCU free overloads the RCU head over the LRU
*/
head = (void *)&page->lru;
}
call_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.
*
* list_lock must be held.
*/
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->lru, &n->partial);
else
list_add(&page->lru, &n->partial);
}
/*
* list_lock must be held.
*/
static inline void remove_partial(struct kmem_cache_node *n,
struct page *page)
{
list_del(&page->lru);
n->nr_partial--;
}
/*
* Lock slab, remove from the partial list and put the object into the
* per cpu freelist.
*
* Returns a list of objects or NULL if it fails.
*
* Must hold list_lock.
*/
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;
/*
* Zap the freelist and set the frozen bit.
* The old freelist is the list of objects for the
* per cpu allocation list.
*/
do {
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;
} while (!__cmpxchg_double_slab(s, page,
freelist, counters,
new.freelist, new.counters,
"lock and freeze"));
remove_partial(n, page);
return freelist;
}
static int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain);
/*
* 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 kmem_cache_cpu *c)
{
struct page *page, *page2;
void *object = NULL;
/*
* 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_partials()
* will return NULL.
*/
if (!n || !n->nr_partial)
return NULL;
spin_lock(&n->list_lock);
list_for_each_entry_safe(page, page2, &n->partial, lru) {
void *t = acquire_slab(s, n, page, object == NULL);
int available;
if (!t)
break;
if (!object) {
c->page = page;
c->node = page_to_nid(page);
stat(s, ALLOC_FROM_PARTIAL);
object = t;
available = page->objects - page->inuse;
} else {
available = put_cpu_partial(s, page, 0);
}
if (kmem_cache_debug(s) || available > s->cpu_partial / 2)
break;
}
spin_unlock(&n->list_lock);
return object;
}
/*
* Get a page from somewhere. Search in increasing NUMA distances.
*/
static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags,
struct kmem_cache_cpu *c)
{
#ifdef CONFIG_NUMA
struct zonelist *zonelist;
struct zoneref *z;
struct zone *zone;
enum zone_type high_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/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 = get_mems_allowed();
zonelist = node_zonelist(slab_node(current->mempolicy), flags);
for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
struct kmem_cache_node *n;
n = get_node(s, zone_to_nid(zone));
if (n && cpuset_zone_allowed_hardwall(zone, flags) &&
n->nr_partial > s->min_partial) {
object = get_partial_node(s, n, c);
if (object) {
/*
* Return the object even if
* put_mems_allowed indicated that
* the cpuset mems_allowed was
* updated in parallel. It's a
* harmless race between the alloc
* and the cpuset update.
*/
put_mems_allowed(cpuset_mems_cookie);
return object;
}
}
}
} while (!put_mems_allowed(cpuset_mems_cookie));
#endif
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 kmem_cache_cpu *c)
{
void *object;
int searchnode = (node == NUMA_NO_NODE) ? numa_node_id() : node;
object = get_partial_node(s, get_node(s, searchnode), c);
if (object || node != NUMA_NO_NODE)
return object;
return get_any_partial(s, flags, c);
}
#ifdef CONFIG_PREEMPT
/*
* Calculate the next globally unique transaction for disambiguiation
* 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;
}
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;
}
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);
printk(KERN_INFO "%s %s: cmpxchg redo ", n, s->name);
#ifdef CONFIG_PREEMPT
if (tid_to_cpu(tid) != tid_to_cpu(actual_tid))
printk("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))
printk("due to cpu running other code. Event %ld->%ld\n",
tid_to_event(tid), tid_to_event(actual_tid));
else
printk("for unknown reason: actual=%lx was=%lx target=%lx\n",
actual_tid, tid, next_tid(tid));
#endif
stat(s, CMPXCHG_DOUBLE_CPU_FAIL);
}
void init_kmem_cache_cpus(struct kmem_cache *s)
{
int cpu;
for_each_possible_cpu(cpu)
per_cpu_ptr(s->cpu_slab, cpu)->tid = init_tid(cpu);
}
/*
* Remove the cpu slab
*/
static void deactivate_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)
{
enum slab_modes { M_NONE, M_PARTIAL, M_FULL, M_FREE };
struct page *page = c->page;
struct kmem_cache_node *n = get_node(s, page_to_nid(page));
int lock = 0;
enum slab_modes l = M_NONE, m = M_NONE;
void *freelist;
void *nextfree;
int tail = DEACTIVATE_TO_HEAD;
struct page new;
struct page old;
if (page->freelist) {
stat(s, DEACTIVATE_REMOTE_FREES);
tail = DEACTIVATE_TO_TAIL;
}
c->tid = next_tid(c->tid);
c->page = NULL;
freelist = c->freelist;
c->freelist = NULL;
/*
* Stage one: Free all available per cpu objects back
* to the page freelist while it is still frozen. Leave the
* last one.
*
* There is no need to take the list->lock because the page
* is still frozen.
*/
while (freelist && (nextfree = get_freepointer(s, freelist))) {
void *prior;
unsigned long counters;
do {
prior = page->freelist;
counters = page->counters;
set_freepointer(s, freelist, prior);
new.counters = counters;
new.inuse--;
VM_BUG_ON(!new.frozen);
} while (!__cmpxchg_double_slab(s, page,
prior, counters,
freelist, new.counters,
"drain percpu freelist"));
freelist = nextfree;
}
/*
* Stage two: 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 = page->freelist;
old.counters = page->counters;
VM_BUG_ON(!old.frozen);
/* Determine target state of the slab */
new.counters = old.counters;
if (freelist) {
new.inuse--;
set_freepointer(s, freelist, 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 possiblity
* that acquire_slab() will see a slab page that
* is frozen
*/
spin_lock(&n->list_lock);
}
} else {
m = M_FULL;
if (kmem_cache_debug(s) && !lock) {
lock = 1;
/*
* This also ensures that the scanning of full
* slabs from diagnostic functions will not see
* any frozen slabs.
*/
spin_lock(&n->list_lock);
}
}
if (l != m) {
if (l == M_PARTIAL)
remove_partial(n, page);
else if (l == M_FULL)
remove_full(s, page);
if (m == M_PARTIAL) {
add_partial(n, page, tail);
stat(s, tail);
} else if (m == M_FULL) {
stat(s, DEACTIVATE_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(&n->list_lock);
if (m == M_FREE) {
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 kmem_cache_node *n = NULL;
struct kmem_cache_cpu *c = this_cpu_ptr(s->cpu_slab);
struct page *page, *discard_page = NULL;
while ((page = c->partial)) {
enum slab_modes { M_PARTIAL, M_FREE };
enum slab_modes l, m;
struct page new;
struct page old;
c->partial = page->next;
l = M_FREE;
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;
if (!new.inuse && (!n || n->nr_partial > s->min_partial))
m = M_FREE;
else {
struct kmem_cache_node *n2 = get_node(s,
page_to_nid(page));
m = M_PARTIAL;
if (n != n2) {
if (n)
spin_unlock(&n->list_lock);
n = n2;
spin_lock(&n->list_lock);
}
}
if (l != m) {
if (l == M_PARTIAL)
remove_partial(n, page);
else
add_partial(n, page,
DEACTIVATE_TO_TAIL);
l = m;
}
} while (!cmpxchg_double_slab(s, page,
old.freelist, old.counters,
new.freelist, new.counters,
"unfreezing slab"));
if (m == M_FREE) {
page->next = discard_page;
discard_page = page;
}
}
if (n)
spin_unlock(&n->list_lock);
while (discard_page) {
page = discard_page;
discard_page = discard_page->next;
stat(s, DEACTIVATE_EMPTY);
discard_slab(s, page);
stat(s, FREE_SLAB);
}
}
/*
* Put a page that was just frozen (in __slab_free) into a partial page
* slot if available. This is done without interrupts disabled and without
* preemption disabled. The cmpxchg is racy and may put the partial page
* onto a random cpus partial slot.
*
* If we did not find a slot then simply move all the partials to the
* per node partial list.
*/
int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
{
struct page *oldpage;
int pages;
int pobjects;
do {
pages = 0;
pobjects = 0;
oldpage = this_cpu_read(s->cpu_slab->partial);
if (oldpage) {
pobjects = oldpage->pobjects;
pages = oldpage->pages;
if (drain && pobjects > s->cpu_partial) {
unsigned long flags;
/*
* partial array is full. Move the existing
* set to the per node partial list.
*/
local_irq_save(flags);
unfreeze_partials(s);
local_irq_restore(flags);
pobjects = 0;
pages = 0;
}
}
pages++;
pobjects += page->objects - page->inuse;
page->pages = pages;
page->pobjects = pobjects;
page->next = oldpage;
} while (irqsafe_cpu_cmpxchg(s->cpu_slab->partial, oldpage, page) != oldpage);
stat(s, CPU_PARTIAL_FREE);
return pobjects;
}
static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)
{
stat(s, CPUSLAB_FLUSH);
deactivate_slab(s, c);
}
/*
* Flush cpu slab.
*
* Called from IPI handler with interrupts disabled.
*/
static inline void __flush_cpu_slab(struct kmem_cache *s, int cpu)
{
struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu);
if (likely(c)) {
if (c->page)
flush_slab(s, c);
unfreeze_partials(s);
}
}
static void flush_cpu_slab(void *d)
{
struct kmem_cache *s = d;
__flush_cpu_slab(s, smp_processor_id());
}
static void flush_all(struct kmem_cache *s)
{
on_each_cpu(flush_cpu_slab, s, 1);
}
/*
* Check if the objects in a per cpu structure fit numa
* locality expectations.
*/
static inline int node_match(struct kmem_cache_cpu *c, int node)
{
#ifdef CONFIG_NUMA
if (node != NUMA_NO_NODE && c->node != node)
return 0;
#endif
return 1;
}
static int count_free(struct page *page)
{
return page->objects - page->inuse;
}
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, lru)
x += get_count(page);
spin_unlock_irqrestore(&n->list_lock, flags);
return x;
}
static inline unsigned long node_nr_objs(struct kmem_cache_node *n)
{
#ifdef CONFIG_SLUB_DEBUG
return atomic_long_read(&n->total_objects);
#else
return 0;
#endif
}
static noinline void
slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid)
{
int node;
printk(KERN_WARNING
"SLUB: Unable to allocate memory on node %d (gfp=0x%x)\n",
nid, gfpflags);
printk(KERN_WARNING " cache: %s, object size: %d, buffer size: %d, "
"default order: %d, min order: %d\n", s->name, s->objsize,
s->size, oo_order(s->oo), oo_order(s->min));
if (oo_order(s->min) > get_order(s->objsize))
printk(KERN_WARNING " %s debugging increased min order, use "
"slub_debug=O to disable.\n", s->name);
for_each_online_node(node) {
struct kmem_cache_node *n = get_node(s, node);
unsigned long nr_slabs;
unsigned long nr_objs;
unsigned long nr_free;
if (!n)
continue;
nr_free = count_partial(n, count_free);
nr_slabs = node_nr_slabs(n);
nr_objs = node_nr_objs(n);
printk(KERN_WARNING
" node %d: slabs: %ld, objs: %ld, free: %ld\n",
node, nr_slabs, nr_objs, nr_free);
}
}
static inline void *new_slab_objects(struct kmem_cache *s, gfp_t flags,
int node, struct kmem_cache_cpu **pc)
{
void *object;
struct kmem_cache_cpu *c;
struct page *page = new_slab(s, flags, node);
if (page) {
c = __this_cpu_ptr(s->cpu_slab);
if (c->page)
flush_slab(s, c);
/*
* No other reference to the page yet so we can
* muck around with it freely without cmpxchg
*/
object = page->freelist;
page->freelist = NULL;
stat(s, ALLOC_SLAB);
c->node = page_to_nid(page);
c->page = page;
*pc = c;
} else
object = NULL;
return object;
}
/*
* 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.
*/
static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
unsigned long addr, struct kmem_cache_cpu *c)
{
void **object;
unsigned long flags;
struct page new;
unsigned long counters;
local_irq_save(flags);
#ifdef CONFIG_PREEMPT
/*
* We may have been preempted and rescheduled on a different
* cpu before disabling interrupts. Need to reload cpu area
* pointer.
*/
c = this_cpu_ptr(s->cpu_slab);
#endif
if (!c->page)
goto new_slab;
redo:
if (unlikely(!node_match(c, node))) {
stat(s, ALLOC_NODE_MISMATCH);
deactivate_slab(s, c);
goto new_slab;
}
/* must check again c->freelist in case of cpu migration or IRQ */
object = c->freelist;
if (object)
goto load_freelist;
stat(s, ALLOC_SLOWPATH);
do {
object = c->page->freelist;
counters = c->page->counters;
new.counters = counters;
VM_BUG_ON(!new.frozen);
/*
* If there is no object left then we use this loop to
* deactivate the slab which is simple since no objects
* are left in the slab and therefore we do not need to
* put the page back onto the partial list.
*
* If there are objects left then we retrieve them
* and use them to refill the per cpu queue.
*/
new.inuse = c->page->objects;
new.frozen = object != NULL;
} while (!__cmpxchg_double_slab(s, c->page,
object, counters,
NULL, new.counters,
"__slab_alloc"));
if (!object) {
c->page = NULL;
stat(s, DEACTIVATE_BYPASS);
goto new_slab;
}
stat(s, ALLOC_REFILL);
load_freelist:
c->freelist = get_freepointer(s, object);
c->tid = next_tid(c->tid);
local_irq_restore(flags);
return object;
new_slab:
if (c->partial) {
c->page = c->partial;
c->partial = c->page->next;
c->node = page_to_nid(c->page);
stat(s, CPU_PARTIAL_ALLOC);
c->freelist = NULL;
goto redo;
}
/* Then do expensive stuff like retrieving pages from the partial lists */
object = get_partial(s, gfpflags, node, c);
if (unlikely(!object)) {
object = new_slab_objects(s, gfpflags, node, &c);
if (unlikely(!object)) {
if (!(gfpflags & __GFP_NOWARN) && printk_ratelimit())
slab_out_of_memory(s, gfpflags, node);
local_irq_restore(flags);
return NULL;
}
}
if (likely(!kmem_cache_debug(s)))
goto load_freelist;
/* Only entered in the debug case */
if (!alloc_debug_processing(s, c->page, object, addr))
goto new_slab; /* Slab failed checks. Next slab needed */
c->freelist = get_freepointer(s, object);
deactivate_slab(s, c);
c->node = NUMA_NO_NODE;
local_irq_restore(flags);
return object;
}
/*
* 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(struct kmem_cache *s,
gfp_t gfpflags, int node, unsigned long addr)
{
void **object;
struct kmem_cache_cpu *c;
unsigned long tid;
if (slab_pre_alloc_hook(s, gfpflags))
return NULL;
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.
*/
c = __this_cpu_ptr(s->cpu_slab);
/*
* 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.
*/
tid = c->tid;
barrier();
object = c->freelist;
if (unlikely(!object || !node_match(c, node)))
object = __slab_alloc(s, gfpflags, node, addr, c);
else {
/*
* 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(!irqsafe_cpu_cmpxchg_double(
s->cpu_slab->freelist, s->cpu_slab->tid,
object, tid,
get_freepointer_safe(s, object), next_tid(tid)))) {
note_cmpxchg_failure("slab_alloc", s, tid);
goto redo;
}
stat(s, ALLOC_FASTPATH);
}
if (unlikely(gfpflags & __GFP_ZERO) && object)
memset(object, 0, s->objsize);
slab_post_alloc_hook(s, gfpflags, object);
return object;
}
void *kmem_cache_alloc(struct kmem_cache *s, gfp_t gfpflags)
{
void *ret = slab_alloc(s, gfpflags, NUMA_NO_NODE, _RET_IP_);
trace_kmem_cache_alloc(_RET_IP_, ret, s->objsize, s->size, gfpflags);
return ret;
}
EXPORT_SYMBOL(kmem_cache_alloc);
#ifdef CONFIG_TRACING
void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t gfpflags, size_t size)
{
void *ret = slab_alloc(s, gfpflags, NUMA_NO_NODE, _RET_IP_);
trace_kmalloc(_RET_IP_, ret, size, s->size, gfpflags);
return ret;
}
EXPORT_SYMBOL(kmem_cache_alloc_trace);
void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order)
{
void *ret = kmalloc_order(size, flags, order);
trace_kmalloc(_RET_IP_, ret, size, PAGE_SIZE << order, flags);
return ret;
}
EXPORT_SYMBOL(kmalloc_order_trace);
#endif
#ifdef CONFIG_NUMA
void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t gfpflags, int node)
{
void *ret = slab_alloc(s, gfpflags, node, _RET_IP_);
trace_kmem_cache_alloc_node(_RET_IP_, ret,
s->objsize, s->size, gfpflags, node);
return ret;
}
EXPORT_SYMBOL(kmem_cache_alloc_node);
#ifdef CONFIG_TRACING
void *kmem_cache_alloc_node_trace(struct kmem_cache *s,
gfp_t gfpflags,
int node, size_t size)
{
void *ret = slab_alloc(s, gfpflags, node, _RET_IP_);
trace_kmalloc_node(_RET_IP_, ret,
size, s->size, gfpflags, node);
return ret;
}
EXPORT_SYMBOL(kmem_cache_alloc_node_trace);
#endif
#endif
/*
* Slow patch 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 page
* handling required then we can return immediately.
*/
static void __slab_free(struct kmem_cache *s, struct page *page,
void *x, unsigned long addr)
{
void *prior;
void **object = (void *)x;
int was_frozen;
int inuse;
struct page new;
unsigned long counters;
struct kmem_cache_node *n = NULL;
unsigned long uninitialized_var(flags);
stat(s, FREE_SLOWPATH);
if (kmem_cache_debug(s) && !free_debug_processing(s, page, x, addr))
return;
do {
prior = page->freelist;
counters = page->counters;
set_freepointer(s, object, prior);
new.counters = counters;
was_frozen = new.frozen;
new.inuse--;
if ((!new.inuse || !prior) && !was_frozen && !n) {
if (!kmem_cache_debug(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, page_to_nid(page));
/*
* 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);
}
}
inuse = new.inuse;
} while (!cmpxchg_double_slab(s, page,
prior, counters,
object, new.counters,
"__slab_free"));
if (likely(!n)) {
/*
* If we just froze the page then put it onto the
* per cpu partial list.
*/
if (new.frozen && !was_frozen)
put_cpu_partial(s, page, 1);
/*
* The list lock was not taken therefore no list
* activity can be necessary.
*/
if (was_frozen)
stat(s, FREE_FROZEN);
return;
}
/*
* was_frozen may have been set after we acquired the list_lock in
* an earlier loop. So we need to check it here again.
*/
if (was_frozen)
stat(s, FREE_FROZEN);
else {
if (unlikely(!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 (unlikely(!prior)) {
remove_full(s, page);
add_partial(n, page, 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, page);
stat(s, FREE_REMOVE_PARTIAL);
} else
/* Slab must be on the full list */
remove_full(s, page);
spin_unlock_irqrestore(&n->list_lock, flags);
stat(s, FREE_SLAB);
discard_slab(s, page);
}
/*
* 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.
*/
static __always_inline void slab_free(struct kmem_cache *s,
struct page *page, void *x, unsigned long addr)
{
void **object = (void *)x;
struct kmem_cache_cpu *c;
unsigned long tid;
slab_free_hook(s, x);
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 succedd.
*/
c = __this_cpu_ptr(s->cpu_slab);
tid = c->tid;
barrier();
if (likely(page == c->page)) {
set_freepointer(s, object, c->freelist);
if (unlikely(!irqsafe_cpu_cmpxchg_double(
s->cpu_slab->freelist, s->cpu_slab->tid,
c->freelist, tid,
object, next_tid(tid)))) {
note_cmpxchg_failure("slab_free", s, tid);
goto redo;
}
stat(s, FREE_FASTPATH);
} else
__slab_free(s, page, x, addr);
}
void kmem_cache_free(struct kmem_cache *s, void *x)
{
struct page *page;
page = virt_to_head_page(x);
slab_free(s, page, x, _RET_IP_);
trace_kmem_cache_free(_RET_IP_, x);
}
EXPORT_SYMBOL(kmem_cache_free);
/*
* Object placement in a slab is made very easy because we always start at
* offset 0. If we tune the size of the object to the alignment then we can
* get the required alignment by putting one properly sized object after
* another.
*
* Notice that the allocation order determines the sizes of the per cpu
* caches. Each processor has always one slab available for allocations.
* Increasing the allocation order reduces the number of times that slabs
* must be moved on and off the partial lists and is therefore a factor in
* locking overhead.
*/
/*
* Mininum / Maximum order of slab pages. This influences locking overhead
* and slab fragmentation. A higher order reduces the number of partial slabs
* and increases the number of allocations possible without having to
* take the list_lock.
*/
static int slub_min_order;
static int slub_max_order = PAGE_ALLOC_COSTLY_ORDER;
static int slub_min_objects;
/*
* Merge control. If this is set then no merging of slab caches will occur.
* (Could be removed. This was introduced to pacify the merge skeptics.)
*/
static int slub_nomerge;
/*
* Calculate the order of allocation given an slab object size.
*
* The order of allocation has significant impact on performance and other
* system components. Generally order 0 allocations should be preferred since
* order 0 does not cause fragmentation in the page allocator. Larger objects
* be problematic to put into order 0 slabs because there may be too much
* unused space left. We go to a higher order if more than 1/16th of the slab
* would be wasted.
*
* In order to reach satisfactory performance we must ensure that a minimum
* number of objects is in one slab. Otherwise we may generate too much
* activity on the partial lists which requires taking the list_lock. This is
* less a concern for large slabs though which are rarely used.
*
* slub_max_order specifies the order where we begin to stop considering the
* number of objects in a slab as critical. If we reach slub_max_order then
* we try to keep the page order as low as possible. So we accept more waste
* of space in favor of a small page order.
*
* Higher order allocations also allow the placement of more objects in a
* slab and thereby reduce object handling overhead. If the user has
* requested a higher mininum order then we start with that one instead of
* the smallest order which will fit the object.
*/
static inline int slab_order(int size, int min_objects,
int max_order, int fract_leftover, int reserved)
{
int order;
int rem;
int min_order = slub_min_order;
if (order_objects(min_order, size, reserved) > MAX_OBJS_PER_PAGE)
return get_order(size * MAX_OBJS_PER_PAGE) - 1;
for (order = max(min_order,
fls(min_objects * size - 1) - PAGE_SHIFT);
order <= max_order; order++) {
unsigned long slab_size = PAGE_SIZE << order;
if (slab_size < min_objects * size + reserved)
continue;
rem = (slab_size - reserved) % size;
if (rem <= slab_size / fract_leftover)
break;
}
return order;
}
static inline int calculate_order(int size, int reserved)
{
int order;
int min_objects;
int fraction;
int max_objects;
/*
* Attempt to find best configuration for a slab. This
* works by first attempting to generate a layout with
* the best configuration and backing off gradually.
*
* First we reduce the acceptable waste in a slab. Then
* we reduce the minimum objects required in a slab.
*/
min_objects = slub_min_objects;
if (!min_objects)
min_objects = 4 * (fls(nr_cpu_ids) + 1);
max_objects = order_objects(slub_max_order, size, reserved);
min_objects = min(min_objects, max_objects);
while (min_objects > 1) {
fraction = 16;
while (fraction >= 4) {
order = slab_order(size, min_objects,
slub_max_order, fraction, reserved);
if (order <= slub_max_order)
return order;
fraction /= 2;
}
min_objects--;
}
/*
* We were unable to place multiple objects in a slab. Now
* lets see if we can place a single object there.
*/
order = slab_order(size, 1, slub_max_order, 1, reserved);
if (order <= slub_max_order)
return order;
/*
* Doh this slab cannot be placed using slub_max_order.
*/
order = slab_order(size, 1, MAX_ORDER, 1, reserved);
if (order < MAX_ORDER)
return order;
return -ENOSYS;
}
/*
* Figure out what the alignment of the objects will be.
*/
static unsigned long calculate_alignment(unsigned long flags,
unsigned long align, unsigned long size)
{
/*
* If the user wants hardware cache aligned objects then follow that
* suggestion if the object is sufficiently large.
*
* The hardware cache alignment cannot override the specified
* alignment though. If that is greater then use it.
*/
if (flags & SLAB_HWCACHE_ALIGN) {
unsigned long ralign = cache_line_size();
while (size <= ralign / 2)
ralign /= 2;
align = max(align, ralign);
}
if (align < ARCH_SLAB_MINALIGN)
align = ARCH_SLAB_MINALIGN;
return ALIGN(align, sizeof(void *));
}
static void
init_kmem_cache_node(struct kmem_cache_node *n, struct kmem_cache *s)
{
n->nr_partial = 0;
spin_lock_init(&n->list_lock);
INIT_LIST_HEAD(&n->partial);
#ifdef CONFIG_SLUB_DEBUG
atomic_long_set(&n->nr_slabs, 0);
atomic_long_set(&n->total_objects, 0);
INIT_LIST_HEAD(&n->full);
#endif
}
static inline int alloc_kmem_cache_cpus(struct kmem_cache *s)
{
BUILD_BUG_ON(PERCPU_DYNAMIC_EARLY_SIZE <
SLUB_PAGE_SHIFT * sizeof(struct kmem_cache_cpu));
/*
* Must align to double word boundary for the double cmpxchg
* instructions to work; see __pcpu_double_call_return_bool().
*/
s->cpu_slab = __alloc_percpu(sizeof(struct kmem_cache_cpu),
2 * sizeof(void *));
if (!s->cpu_slab)
return 0;
init_kmem_cache_cpus(s);
return 1;
}
static struct kmem_cache *kmem_cache_node;
/*
* No kmalloc_node yet so do it by hand. We know that this is the first
* slab on the node for this slabcache. There are no concurrent accesses
* possible.
*
* Note that this function only works on the kmalloc_node_cache
* when allocating for the kmalloc_node_cache. This is used for bootstrapping
* memory on a fresh node that has no slab structures yet.
*/
static void early_kmem_cache_node_alloc(int node)
{
struct page *page;
struct kmem_cache_node *n;
BUG_ON(kmem_cache_node->size < sizeof(struct kmem_cache_node));
page = new_slab(kmem_cache_node, GFP_NOWAIT, node);
BUG_ON(!page);
if (page_to_nid(page) != node) {
printk(KERN_ERR "SLUB: Unable to allocate memory from "
"node %d\n", node);
printk(KERN_ERR "SLUB: Allocating a useless per node structure "
"in order to be able to continue\n");
}
n = page->freelist;
BUG_ON(!n);
page->freelist = get_freepointer(kmem_cache_node, n);
page->inuse = 1;
page->frozen = 0;
kmem_cache_node->node[node] = n;
#ifdef CONFIG_SLUB_DEBUG
init_object(kmem_cache_node, n, SLUB_RED_ACTIVE);
init_tracking(kmem_cache_node, n);
#endif
init_kmem_cache_node(n, kmem_cache_node);
inc_slabs_node(kmem_cache_node, node, page->objects);
add_partial(n, page, DEACTIVATE_TO_HEAD);
}
static void free_kmem_cache_nodes(struct kmem_cache *s)
{
int node;
for_each_node_state(node, N_NORMAL_MEMORY) {
struct kmem_cache_node *n = s->node[node];
if (n)
kmem_cache_free(kmem_cache_node, n);
s->node[node] = NULL;
}
}
static int init_kmem_cache_nodes(struct kmem_cache *s)
{
int node;
for_each_node_state(node, N_NORMAL_MEMORY) {
struct kmem_cache_node *n;
if (slab_state == DOWN) {
early_kmem_cache_node_alloc(node);
continue;
}
n = kmem_cache_alloc_node(kmem_cache_node,
GFP_KERNEL, node);
if (!n) {
free_kmem_cache_nodes(s);
return 0;
}
s->node[node] = n;
init_kmem_cache_node(n, s);
}
return 1;
}
static void set_min_partial(struct kmem_cache *s, unsigned long min)
{
if (min < MIN_PARTIAL)
min = MIN_PARTIAL;
else if (min > MAX_PARTIAL)
min = MAX_PARTIAL;
s->min_partial = min;
}
/*
* calculate_sizes() determines the order and the distribution of data within
* a slab object.
*/
static int calculate_sizes(struct kmem_cache *s, int forced_order)
{
unsigned long flags = s->flags;
unsigned long size = s->objsize;
unsigned long align = s->align;
int order;
/*
* Round up object size to the next word boundary. We can only
* place the free pointer at word boundaries and this determines
* the possible location of the free pointer.
*/
size = ALIGN(size, sizeof(void *));
#ifdef CONFIG_SLUB_DEBUG
/*
* Determine if we can poison the object itself. If the user of
* the slab may touch the object after free or before allocation
* then we should never poison the object itself.
*/
if ((flags & SLAB_POISON) && !(flags & SLAB_DESTROY_BY_RCU) &&
!s->ctor)
s->flags |= __OBJECT_POISON;
else
s->flags &= ~__OBJECT_POISON;
/*
* If we are Redzoning then check if there is some space between the
* end of the object and the free pointer. If not then add an
* additional word to have some bytes to store Redzone information.
*/
if ((flags & SLAB_RED_ZONE) && size == s->objsize)
size += sizeof(void *);
#endif
/*
* With that we have determined the number of bytes in actual use
* by the object. This is the potential offset to the free pointer.
*/
s->inuse = size;
if (((flags & (SLAB_DESTROY_BY_RCU | SLAB_POISON)) ||
s->ctor)) {
/*
* Relocate free pointer after the object if it is not
* permitted to overwrite the first word of the object on
* kmem_cache_free.
*
* This is the case if we do RCU, have a constructor or
* destructor or are poisoning the objects.
*/
s->offset = size;
size += sizeof(void *);
}
#ifdef CONFIG_SLUB_DEBUG
if (flags & SLAB_STORE_USER)
/*
* Need to store information about allocs and frees after
* the object.
*/
size += 2 * sizeof(struct track);
if (flags & SLAB_RED_ZONE)
/*
* Add some empty padding so that we can catch
* overwrites from earlier objects rather than let
* tracking information or the free pointer be
* corrupted if a user writes before the start
* of the object.
*/
size += sizeof(void *);
#endif
/*
* Determine the alignment based on various parameters that the
* user specified and the dynamic determination of cache line size
* on bootup.
*/
align = calculate_alignment(flags, align, s->objsize);
s->align = align;
/*
* SLUB stores one object immediately after another beginning from
* offset 0. In order to align the objects we have to simply size
* each object to conform to the alignment.
*/
size = ALIGN(size, align);
s->size = size;
if (forced_order >= 0)
order = forced_order;
else
order = calculate_order(size, s->reserved);
if (order < 0)
return 0;
s->allocflags = 0;
if (order)
s->allocflags |= __GFP_COMP;
if (s->flags & SLAB_CACHE_DMA)
s->allocflags |= SLUB_DMA;
if (s->flags & SLAB_RECLAIM_ACCOUNT)
s->allocflags |= __GFP_RECLAIMABLE;
/*
* Determine the number of objects per slab
*/
s->oo = oo_make(order, size, s->reserved);
s->min = oo_make(get_order(size), size, s->reserved);
if (oo_objects(s->oo) > oo_objects(s->max))
s->max = s->oo;
return !!oo_objects(s->oo);
}
static int kmem_cache_open(struct kmem_cache *s,
const char *name, size_t size,
size_t align, unsigned long flags,
void (*ctor)(void *))
{
memset(s, 0, kmem_size);
s->name = name;
s->ctor = ctor;
s->objsize = size;
s->align = align;
s->flags = kmem_cache_flags(size, flags, name, ctor);
s->reserved = 0;
if (need_reserve_slab_rcu && (s->flags & SLAB_DESTROY_BY_RCU))
s->reserved = sizeof(struct rcu_head);
if (!calculate_sizes(s, -1))
goto error;
if (disable_higher_order_debug) {
/*
* Disable debugging flags that store metadata if the min slab
* order increased.
*/
if (get_order(s->size) > get_order(s->objsize)) {
s->flags &= ~DEBUG_METADATA_FLAGS;
s->offset = 0;
if (!calculate_sizes(s, -1))
goto error;
}
}
#ifdef CONFIG_CMPXCHG_DOUBLE
if (system_has_cmpxchg_double() && (s->flags & SLAB_DEBUG_FLAGS) == 0)
/* Enable fast mode */
s->flags |= __CMPXCHG_DOUBLE;
#endif
/*
* The larger the object size is, the more pages we want on the partial
* list to avoid pounding the page allocator excessively.
*/
set_min_partial(s, ilog2(s->size) / 2);
/*
* cpu_partial determined the maximum number of objects kept in the
* per cpu partial lists of a processor.
*
* Per cpu partial lists mainly contain slabs that just have one
* object freed. If they are used for allocation then they can be
* filled up again with minimal effort. The slab will never hit the
* per node partial lists and therefore no locking will be required.
*
* This setting also determines
*
* A) The number of objects from per cpu partial slabs dumped to the
* per node list when we reach the limit.
* B) The number of objects in cpu partial slabs to extract from the
* per node list when we run out of per cpu objects. We only fetch 50%
* to keep some capacity around for frees.
*/
if (s->size >= PAGE_SIZE)
s->cpu_partial = 2;
else if (s->size >= 1024)
s->cpu_partial = 6;
else if (s->size >= 256)
s->cpu_partial = 13;
else
s->cpu_partial = 30;
s->refcount = 1;
#ifdef CONFIG_NUMA
s->remote_node_defrag_ratio = 1000;
#endif
if (!init_kmem_cache_nodes(s))
goto error;
if (alloc_kmem_cache_cpus(s))
return 1;
free_kmem_cache_nodes(s);
error:
if (flags & SLAB_PANIC)
panic("Cannot create slab %s size=%lu realsize=%u "
"order=%u offset=%u flags=%lx\n",
s->name, (unsigned long)size, s->size, oo_order(s->oo),
s->offset, flags);
return 0;
}
/*
* Determine the size of a slab object
*/
unsigned int kmem_cache_size(struct kmem_cache *s)
{
return s->objsize;
}
EXPORT_SYMBOL(kmem_cache_size);
static void list_slab_objects(struct kmem_cache *s, struct page *page,
const char *text)
{
#ifdef CONFIG_SLUB_DEBUG
void *addr = page_address(page);
void *p;
unsigned long *map = kzalloc(BITS_TO_LONGS(page->objects) *
sizeof(long), GFP_ATOMIC);
if (!map)
return;
slab_err(s, page, "%s", text);
slab_lock(page);
get_map(s, page, map);
for_each_object(p, s, addr, page->objects) {
if (!test_bit(slab_index(p, s, addr), map)) {
printk(KERN_ERR "INFO: Object 0x%p @offset=%tu\n",
p, p - addr);
print_tracking(s, p);
}
}
slab_unlock(page);
kfree(map);
#endif
}
/*
* Attempt to free all partial slabs on a node.
* This is called from kmem_cache_close(). We must be the last thread
* using the cache and therefore we do not need to lock anymore.
*/
static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n)
{
struct page *page, *h;
list_for_each_entry_safe(page, h, &n->partial, lru) {
if (!page->inuse) {
remove_partial(n, page);
discard_slab(s, page);
} else {
list_slab_objects(s, page,
"Objects remaining on kmem_cache_close()");
}
}
}
/*
* Release all resources used by a slab cache.
*/
static inline int kmem_cache_close(struct kmem_cache *s)
{
int node;
flush_all(s);
free_percpu(s->cpu_slab);
/* Attempt to free all objects */
for_each_node_state(node, N_NORMAL_MEMORY) {
struct kmem_cache_node *n = get_node(s, node);
free_partial(s, n);
if (n->nr_partial || slabs_node(s, node))
return 1;
}
free_kmem_cache_nodes(s);
return 0;
}
/*
* Close a cache and release the kmem_cache structure
* (must be used for caches created using kmem_cache_create)
*/
void kmem_cache_destroy(struct kmem_cache *s)
{
down_write(&slub_lock);
s->refcount--;
if (!s->refcount) {
list_del(&s->list);
up_write(&slub_lock);
if (kmem_cache_close(s)) {
printk(KERN_ERR "SLUB %s: %s called for cache that "
"still has objects.\n", s->name, __func__);
dump_stack();
}
if (s->flags & SLAB_DESTROY_BY_RCU)
rcu_barrier();
sysfs_slab_remove(s);
} else
up_write(&slub_lock);
}
EXPORT_SYMBOL(kmem_cache_destroy);
/********************************************************************
* Kmalloc subsystem
*******************************************************************/
struct kmem_cache *kmalloc_caches[SLUB_PAGE_SHIFT];
EXPORT_SYMBOL(kmalloc_caches);
static struct kmem_cache *kmem_cache;
#ifdef CONFIG_ZONE_DMA
static struct kmem_cache *kmalloc_dma_caches[SLUB_PAGE_SHIFT];
#endif
static int __init setup_slub_min_order(char *str)
{
get_option(&str, &slub_min_order);
return 1;
}
__setup("slub_min_order=", setup_slub_min_order);
static int __init setup_slub_max_order(char *str)
{
get_option(&str, &slub_max_order);
slub_max_order = min(slub_max_order, MAX_ORDER - 1);
return 1;
}
__setup("slub_max_order=", setup_slub_max_order);
static int __init setup_slub_min_objects(char *str)
{
get_option(&str, &slub_min_objects<