Linuxメモリ管理のslabメカニズム(cacheの作成)
Linuxカーネルでcacheノードを作成する関数kmem_cache_create()実装.
この関数の実行プロセス:
1、グローバルcache_からCacheでは、グローバルcache_Cache初期化オブジェクトのサイズはkmem_ですCache構造の大きさなので、返されるポインタはちょうどcache構造に変換できます.呼び出しkmem_cache_zalloc(&cache_cache, gfp);
2,slabのフラグメントサイズを取得し、関数calculate_slab_order()実装;
3,cacheの各種属性を計算して初期化し,外付け式であればkmem_を用いる必要がある.find_general_Cachep(slab_size,0 u)指定cachep->slabp_Cache、slabオブジェクトとkmem_を格納するために使用bufctl_t[]配列;
4,各CPU上のローカルcache,setup_を設定するcpu_cache();
5、cacheの作成が完了し、グローバルslab cacheチェーンテーブルに追加します.
一、主な実現
ここで、cache_cache
二、slab断片の大きさを計算する
三、指定サイズcacheの検索
四、CPUローカルcacheの設定
この関数の実行プロセス:
1、グローバルcache_からCacheでは、グローバルcache_Cache初期化オブジェクトのサイズはkmem_ですCache構造の大きさなので、返されるポインタはちょうどcache構造に変換できます.呼び出しkmem_cache_zalloc(&cache_cache, gfp);
2,slabのフラグメントサイズを取得し、関数calculate_slab_order()実装;
3,cacheの各種属性を計算して初期化し,外付け式であればkmem_を用いる必要がある.find_general_Cachep(slab_size,0 u)指定cachep->slabp_Cache、slabオブジェクトとkmem_を格納するために使用bufctl_t[]配列;
4,各CPU上のローカルcache,setup_を設定するcpu_cache();
5、cacheの作成が完了し、グローバルslab cacheチェーンテーブルに追加します.
一、主な実現
/**
* kmem_cache_create - Create a cache.
* @name: A string which is used in /proc/slabinfo to identify this cache.
* @size: The size of objects to be created in this cache.
* @align: The required alignment for the objects.
* @flags: SLAB flags
* @ctor: A constructor for the objects.
*
* Returns a ptr to the cache on success, NULL on failure.
* Cannot be called within a int, but can be interrupted.
* The @ctor is run when new pages are allocated by the cache.
*
* @name must be valid until the cache is destroyed. This implies that
* the module calling this has to destroy the cache before getting unloaded.
* Note that kmem_cache_name() is not guaranteed to return the same pointer,
* therefore applications must manage it themselves.
*
* The flags are
*
* %SLAB_POISON - Poison the slab with a known test pattern (a5a5a5a5)
* to catch references to uninitialised memory.
*
* %SLAB_RED_ZONE - Insert `Red' zones around the allocated memory to check
* for buffer overruns.
*
* %SLAB_HWCACHE_ALIGN - Align the objects in this cache to a hardware
* cacheline. This can be beneficial if you're counting cycles as closely
* as davem.
*/
/* slab cache 。 ，cache
slab ，
， cache ， slab。*/
struct kmem_cache *
kmem_cache_create (const char *name, size_t size, size_t align,
unsigned long flags, void (*ctor)(void *))
{
size_t left_over, slab_size, ralign;
struct kmem_cache *cachep = NULL, *pc;
gfp_t gfp;
/*
* Sanity checks... these are all serious usage bugs.
*//* */
if (!name || in_interrupt() || (size < BYTES_PER_WORD) ||
size > KMALLOC_MAX_SIZE) {
printk(KERN_ERR "%s: Early error in slab %s
", __func__,
name);
BUG();
}
/*
* We use cache_chain_mutex to ensure a consistent view of
* cpu_online_mask as well. Please see cpuup_callback
*/
/* slab ，
， cpu slab ， ， */
if (slab_is_available()) {
get_online_cpus();
mutex_lock(&cache_chain_mutex);
}
/* cache ， */
list_for_each_entry(pc, &cache_chain, next) {
char tmp;
int res;
/*
* This happens when the module gets unloaded and doesn't
* destroy its slab cache and no-one else reuses the vmalloc
* area of the module. Print a warning.
*/
/* cache cache */
res = probe_kernel_address(pc->name, tmp);
if (res) {/* ， */
printk(KERN_ERR
"SLAB: cache with size %d has lost its name
",
pc->buffer_size);
continue;
}
/* cache cache */
if (!strcmp(pc->name, name)) {
printk(KERN_ERR
"kmem_cache_create: duplicate cache %s
", name);
dump_stack();
goto oops;
}
}
#if DEBUG
WARN_ON(strchr(name, ' ')); /* It confuses parsers */
#if FORCED_DEBUG
/*
* Enable redzoning and last user accounting, except for caches with
* large objects, if the increased size would increase the object size
* above the next power of two: caches with object sizes just above a
* power of two have a significant amount of internal fragmentation.
*/
if (size < 4096 || fls(size - 1) == fls(size-1 + REDZONE_ALIGN +
2 * sizeof(unsigned long long)))
flags |= SLAB_RED_ZONE | SLAB_STORE_USER;
if (!(flags & SLAB_DESTROY_BY_RCU))
flags |= SLAB_POISON;
#endif
if (flags & SLAB_DESTROY_BY_RCU)
BUG_ON(flags & SLAB_POISON);
#endif
/*
* Always checks flags, a caller might be expecting debug support which
* isn't available.
*/
BUG_ON(flags & ~CREATE_MASK);
/*
* Check that size is in terms of words. This is needed to avoid
* unaligned accesses for some archs when redzoning is used, and makes
* sure any on-slab bufctl's are also correctly aligned.
*/
if (size & (BYTES_PER_WORD - 1)) {
size += (BYTES_PER_WORD - 1);
size &= ~(BYTES_PER_WORD - 1);
}
/* calculate the final buffer alignment: */
/* 1) arch recommendation: can be overridden for debug */
if (flags & SLAB_HWCACHE_ALIGN) {
/*
* Default alignment: as specified by the arch code. Except if
* an object is really small, then squeeze multiple objects into
* one cacheline.
*/
ralign = cache_line_size();
while (size <= ralign / 2)
ralign /= 2;
} else {
ralign = BYTES_PER_WORD;
}
/*
* Redzoning and user store require word alignment or possibly larger.
* Note this will be overridden by architecture or caller mandated
* alignment if either is greater than BYTES_PER_WORD.
*/
if (flags & SLAB_STORE_USER)
ralign = BYTES_PER_WORD;
if (flags & SLAB_RED_ZONE) {
ralign = REDZONE_ALIGN;
/* If redzoning, ensure that the second redzone is suitably
* aligned, by adjusting the object size accordingly. */
size += REDZONE_ALIGN - 1;
size &= ~(REDZONE_ALIGN - 1);
}
/* 2) arch mandated alignment */
if (ralign < ARCH_SLAB_MINALIGN) {
ralign = ARCH_SLAB_MINALIGN;
}
/* 3) caller mandated alignment */
if (ralign < align) {
ralign = align;
}
/* disable debug if necessary */
if (ralign > __alignof__(unsigned long long))
flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER);
/*
* 4) Store it.
*/
align = ralign;
/* slab */
if (slab_is_available())
gfp = GFP_KERNEL;
else
/* slab ， ， */
gfp = GFP_NOWAIT;
/* Get cache's description obj. */
/* struct kmem_cache , cache
kmem_cache ， cache_cache
kmem_cache */
cachep = kmem_cache_zalloc(&cache_cache, gfp);
if (!cachep)
goto oops;
#if DEBUG
cachep->obj_size = size;
/*
* Both debugging options require word-alignment which is calculated
* into align above.
*/
if (flags & SLAB_RED_ZONE) {
/* add space for red zone words */
cachep->obj_offset += sizeof(unsigned long long);
size += 2 * sizeof(unsigned long long);
}
if (flags & SLAB_STORE_USER) {
/* user store requires one word storage behind the end of
* the real object. But if the second red zone needs to be
* aligned to 64 bits, we must allow that much space.
*/
if (flags & SLAB_RED_ZONE)
size += REDZONE_ALIGN;
else
size += BYTES_PER_WORD;
}
#if FORCED_DEBUG && defined(CONFIG_DEBUG_PAGEALLOC)
if (size >= malloc_sizes[INDEX_L3 + 1].cs_size
&& cachep->obj_size > cache_line_size() && size < PAGE_SIZE) {
cachep->obj_offset += PAGE_SIZE - size;
size = PAGE_SIZE;
}
#endif
#endif
/*
* Determine if the slab management is 'on' or 'off' slab.
* (bootstrapping cannot cope with offslab caches so don't do
* it too early on.)
*/
/* slab ：
。 ， 512 ，
。 。
slab_early_init kmem_cache_init */
if ((size >= (PAGE_SIZE >> 3)) && !slab_early_init)
/*
* Size is large, assume best to place the slab management obj
* off-slab (should allow better packing of objs).
*/
flags |= CFLGS_OFF_SLAB;
size = ALIGN(size, align);
/* slab */
left_over = calculate_slab_order(cachep, size, align, flags);
/* cachep->num cache slab ， 0， cache */
if (!cachep->num) {
printk(KERN_ERR
"kmem_cache_create: couldn't create cache %s.
", name);
kmem_cache_free(&cache_cache, cachep);
cachep = NULL;
goto oops;
}
/* slab ， struct slab kmem_bufctl_t */
slab_size = ALIGN(cachep->num * sizeof(kmem_bufctl_t)
+ sizeof(struct slab), align);
/*
* If the slab has been placed off-slab, and we have enough space then
* move it on-slab. This is at the expense of any extra colouring.
*/
/* slab， slab
， slab slab ， slab */
if (flags & CFLGS_OFF_SLAB && left_over >= slab_size) {
/* off-slab */
flags &= ~CFLGS_OFF_SLAB;
/* */
left_over -= slab_size;
}
if (flags & CFLGS_OFF_SLAB) {
/* really off slab. No need for manual alignment */
/* align slab ， slab
， slab
， */
slab_size =
cachep->num * sizeof(kmem_bufctl_t) + sizeof(struct slab);
#ifdef CONFIG_PAGE_POISONING
/* If we're going to use the generic kernel_map_pages()
* poisoning, then it's going to smash the contents of
* the redzone and userword anyhow, so switch them off.
*/
if (size % PAGE_SIZE == 0 && flags & SLAB_POISON)
flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER);
#endif
}
/* cache */
cachep->colour_off = cache_line_size();
/* Offset must be a multiple of the alignment. */
/* */
if (cachep->colour_off < align)
cachep->colour_off = align;
/* */
cachep->colour = left_over / cachep->colour_off;
/* slab */
cachep->slab_size = slab_size;
cachep->flags = flags;
cachep->gfpflags = 0;
if (CONFIG_ZONE_DMA_FLAG && (flags & SLAB_CACHE_DMA))
cachep->gfpflags |= GFP_DMA;
/* slab */
cachep->buffer_size = size;
/* slab ， obj_to_index */
cachep->reciprocal_buffer_size = reciprocal_value(size);
if (flags & CFLGS_OFF_SLAB) {
/* slab ， slabp_cache ，
slab_size, slab_size cache
, slab ，
slab ， kmem_bufctl_t[] ，
slab， */
cachep->slabp_cache = kmem_find_general_cachep(slab_size, 0u);
/*
* This is a possibility for one of the malloc_sizes caches.
* But since we go off slab only for object size greater than
* PAGE_SIZE/8, and malloc_sizes gets created in ascending order,
* this should not happen at all.
* But leave a BUG_ON for some lucky dude.
*/
BUG_ON(ZERO_OR_NULL_PTR(cachep->slabp_cache));
}
cachep->ctor = ctor;
cachep->name = name;
/* cpu local cache */
if (setup_cpu_cache(cachep, gfp)) {
__kmem_cache_destroy(cachep);
cachep = NULL;
goto oops;
}
/* cache setup completed, link it into the list */
/* cache ， slab cache */
list_add(&cachep->next, &cache_chain);
oops:
if (!cachep && (flags & SLAB_PANIC))
panic("kmem_cache_create(): failed to create slab `%s'
",
name);
if (slab_is_available()) {
mutex_unlock(&cache_chain_mutex);
put_online_cpus();
}
return cachep;
}ここで、cache_cache
/* internal cache of cache description objs */
static struct kmem_cache cache_cache = {
.batchcount = 1,
.limit = BOOT_CPUCACHE_ENTRIES,
.shared = 1,
.buffer_size = sizeof(struct kmem_cache),/* cache ， cache_cache*/
.name = "kmem_cache",
};二、slab断片の大きさを計算する
/**
* calculate_slab_order - calculate size (page order) of slabs
* @cachep: pointer to the cache that is being created
* @size: size of objects to be created in this cache.
* @align: required alignment for the objects.
* @flags: slab allocation flags
*
* Also calculates the number of objects per slab.
*
* This could be made much more intelligent. For now, try to avoid using
* high order pages for slabs. When the gfp() functions are more friendly
* towards high-order requests, this should be changed.
*/
/* slab ， slab */
static size_t calculate_slab_order(struct kmem_cache *cachep,
size_t size, size_t align, unsigned long flags)
{
unsigned long offslab_limit;
size_t left_over = 0;
int gfporder;
for (gfporder = 0; gfporder <= KMALLOC_MAX_ORDER; gfporder++) {
unsigned int num;
size_t remainder;
/* slab */
cache_estimate(gfporder, size, align, flags, &remainder, &num);
/* 0， order ， ， order */
if (!num)
continue;
if (flags & CFLGS_OFF_SLAB) {
/*
* Max number of objs-per-slab for caches which
* use off-slab slabs. Needed to avoid a possible
* looping condition in cache_grow().
*/
/* slab ， slab
， struct slab kmem_bufctl_t ，
， ：
kmem_cache_alloc->__cache_alloc-> __do_cache_alloc-> ____cache_alloc-> cache_alloc_refill-> cache_grow-> alloc_slabmgmt-> kmem_cache_alloc_node-> kmem_cache_alloc
， alloc_slabmgmt
， slab off-slab ，
。 slab slab ？ slab
， kmem_bufctl_t ， ，
。 kmem_bufctl_t ， ， size
， slab， size， kmem_bufctl_t
， kmem_bufctl_t slab。
， ， slab。
， slab_break_gfp_order slab ， 1， slab
， slab 512 ，
slab ，kmem_bufctl_t ， 。
*/
offslab_limit = size - sizeof(struct slab);
offslab_limit /= sizeof(kmem_bufctl_t);
/* ， ， order
， slab
， ， */
if (num > offslab_limit)
break;
}
/* Found something acceptable - save it away */
/* slab */
cachep->num = num;
/* slab order， */
cachep->gfporder = gfporder;
/* slab （ ） */
left_over = remainder;
/*
* A VFS-reclaimable slab tends to have most allocations
* as GFP_NOFS and we really don't want to have to be allocating
* higher-order pages when we are unable to shrink dcache.
*/
/* SLAB_RECLAIM_ACCOUNT slab
，
， ，
kmem_freepages() slab 。
， */
if (flags & SLAB_RECLAIM_ACCOUNT)
break;
/*
* Large number of objects is good, but very large slabs are
* currently bad for the gfp()s.
*/
/* slab_break_gfp_order slab ，
， ， order */
if (gfporder >= slab_break_gfp_order)
break;
/*
* Acceptable internal fragmentation?
*/
/* slab 8
， ， order */
if (left_over * 8 <= (PAGE_SIZE << gfporder))
break;
}
/* */
return left_over;
}三、指定サイズcacheの検索
/* general cache struct kmem_cache 。 __find_general_cachep。*/
static struct kmem_cache *kmem_find_general_cachep(size_t size, gfp_t gfpflags)
{
return __find_general_cachep(size, gfpflags);
}static inline struct kmem_cache *__find_general_cachep(size_t size,
gfp_t gfpflags)
{
struct cache_sizes *csizep = malloc_sizes;
#if DEBUG
/* This happens if someone tries to call
* kmem_cache_create(), or __kmalloc(), before
* the generic caches are initialized.
*/
BUG_ON(malloc_sizes[INDEX_AC].cs_cachep == NULL);
#endif
if (!size)
return ZERO_SIZE_PTR;
/* malloc size */
while (size > csizep->cs_size)
csizep++;
/*
* Really subtle: The last entry with cs->cs_size==ULONG_MAX
* has cs_{dma,}cachep==NULL. Thus no special case
* for large kmalloc calls required.
*/
#ifdef CONFIG_ZONE_DMA
if (unlikely(gfpflags & GFP_DMA))
return csizep->cs_dmacachep;
#endif
/* cache */
return csizep->cs_cachep;
}四、CPUローカルcacheの設定
/* local cache slab 。*/
static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp)
{
/* general cache ， cpu local cache */
if (g_cpucache_up == FULL)
return enable_cpucache(cachep, gfp);
/* ，g_cpucache_up general cache
， PARTIAL_AC struct array_cache cache ，
PARTIAL_L3 struct kmem_list3 cache
， cache
。 cpu local cache slab */
if (g_cpucache_up == NONE) {
/*
* Note: the first kmem_cache_create must create the cache
* that's used by kmalloc(24), otherwise the creation of
* further caches will BUG().
*/
/* struct array_cache cache
， struct array_cache general cache
， initarray_generic local cache */
cachep->array[smp_processor_id()] = &initarray_generic.cache;
/*
* If the cache that's used by kmalloc(sizeof(kmem_list3)) is
* the first cache, then we need to set up all its list3s,
* otherwise the creation of further caches will BUG().
*/
/* struct kmem_list3 cache struct array_cache cache
， struct kmem_list3
cache ， */
set_up_list3s(cachep, SIZE_AC);
/* struct array_cache cache
， struct kmem_list3 struct array_cache general cache
，
，g_cpucache_up */
if (INDEX_AC == INDEX_L3)
g_cpucache_up = PARTIAL_L3;
else
g_cpucache_up = PARTIAL_AC;
} else {
/* g_cpucache_up PARTIAL_AC ，struct array_cache
general cache ， kmalloc */
cachep->array[smp_processor_id()] =
kmalloc(sizeof(struct arraycache_init), gfp);
if (g_cpucache_up == PARTIAL_AC) {
/* struct kmem_list3 cache ， slab */
set_up_list3s(cachep, SIZE_L3);
/* kmem_cache_init ， struct kmem_list3
cache ， ，struct kmem_list3
cache ， g_cpucache_up */
g_cpucache_up = PARTIAL_L3;
} else {
int node;
for_each_online_node(node) {
cachep->nodelists[node] =/* kmalloc struct kmem_list3 */
kmalloc_node(sizeof(struct kmem_list3),
gfp, node);
BUG_ON(!cachep->nodelists[node]);
/* slab */
kmem_list3_init(cachep->nodelists[node]);
}
}
}
/* */
cachep->nodelists[numa_node_id()]->next_reap =
jiffies + REAPTIMEOUT_LIST3 +
((unsigned long)cachep) % REAPTIMEOUT_LIST3;
cpu_cache_get(cachep)->avail = 0;
cpu_cache_get(cachep)->limit = BOOT_CPUCACHE_ENTRIES;
cpu_cache_get(cachep)->batchcount = 1;
cpu_cache_get(cachep)->touched = 0;
cachep->batchcount = 1;
cachep->limit = BOOT_CPUCACHE_ENTRIES;
return 0;
}