kmem_cache_boot则是：
点击(此处)折叠或打开
/* internal cache of cache description objs */
static struct kmem_cache kmem_cache_boot = {
.batchcount = 1,
.limit = BOOT_CPUCACHE_ENTRIES, // 默认为 1
.shared = 1,
.size = sizeof(struct kmem_cache),
.name = "kmem_cache",
};
注释解释的已经很清晰了.
而setup_nodelists_pointer的作用就是把struct kmem_cache里array指针地址存放在nodelists.目的是为了便于操作指针.
对于一致性内存访问，inode只有一个.
点击(此处)折叠或打开
static struct kmem_list3 __initdata initkmem_list3[NUM_INIT_LISTS];
它是slab.c中静态全局变量
点击(此处)折叠或打开
/*
* Need this for bootstrapping a per node allocator.
*/
kmem_list3_init初始化slab的三个链表slabs_full、slabs_partial、slabs_free.为什么初始化这个和cache组成结构有关系，可以看个图：
这里CACHE_CACHE在文件的开头部分被定义为0.
点击(此处)折叠或打开
/*
* For setting up all the kmem_list3s for cache whose buffer_size is same as
* size of kmem_list3.
*/
static void __init set_up_list3s(struct kmem_cache *cachep, int index)
{
int node;
for_each_online_node(node) {
cachep->nodelists[node] = &initkmem_list3[index + node];
cachep->nodelists[node]->next_reap = jiffies +
REAPTIMEOUT_LIST3 +
((unsigned long)cachep) % REAPTIMEOUT_LIST3;
}
}
接着就要开始了真正的创建cache的工作，并且给出了初始化步骤和说明：
点击(此处)折叠或打开
/* Bootstrap is tricky, because several objects are allocated
* from caches that do not exist yet:
* 1) initialize the kmem_cache cache: it contains the struct
* kmem_cache structures of all caches, except kmem_cache itself:
* kmem_cache is statically allocated.
* Initially an __init data area is used for the head array and the
* kmem_list3 structures, it's replaced with a kmalloc allocated
* array at the end of the bootstrap.
* 2) Create the first kmalloc cache.
* The struct kmem_cache for the new cache is allocated normally.
* An __init data area is used for the head array.
* 3) Create the remaining kmalloc caches, with minimally sized
* head arrays.
* 4) Replace the __init data head arrays for kmem_cache and the first
* kmalloc cache with kmalloc allocated arrays.
* 5) Replace the __init data for kmem_list3 for kmem_cache and
* the other cache's with kmalloc allocated memory.
* 6) Resize the head arrays of the kmalloc caches to their final sizes.
*/
/* 1) create the kmem_cache */
/*
* struct kmem_cache size depends on nr_node_ids & nr_cpu_ids
*/
create_boot_cache(kmem_cache, "kmem_cache",
offsetof(struct kmem_cache, array[nr_cpu_ids]) +
nr_node_ids * sizeof(struct kmem_list3 *),
SLAB_HWCACHE_ALIGN);
list_add(&kmem_cache->list, &slab_caches);
首先创建第一个cache它名为kmem_cache，并且kmem_cache指针变量指向了kmem_cache_boot.
下面我们看看create_boot_cache函数
点击(此处)折叠或打开
#ifndef CONFIG_SLOB
/* Create a cache during boot when no slab services are available yet */
void __init create_boot_cache(struct kmem_cache *s, const char *name, size_t size,
unsigned long flags)
{
int err;
s->name = name;
s->size = s->object_size = size;
s->align = calculate_alignment(flags, ARCH_KMALLOC_MINALIGN, size);
err = __kmem_cache_create(s, flags);
if (err)
panic("Creation of kmalloc slab %s size=%zd failed. Reason %d\n",
name, size, err);
s->refcount = -1; /* Exempt from merging for now */
}
struct kmem_cache *__init create_kmalloc_cache(const char *name, size_t size,
unsigned long flags)
{
struct kmem_cache *s = kmem_cache_zalloc(kmem_cache, GFP_NOWAIT);
if (!s)
panic("Out of memory when creating slab %s\n", name);
create_boot_cache(s, name, size, flags);
list_add(&s->list, &slab_caches);
s->refcount = 1;
return s;
}
#endif /* !CONFIG_SLOB */
而它接着调用了__kmem_cache_create：这是最关键的函数
点击(此处)折叠或打开
/**
* __kmem_cache_create - Create a cache.
* @cachep: cache management descriptor
* @flags: SLAB flags
*
* 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.
*
* 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.
*/
int
__kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
{
size_t left_over, slab_size, ralign;
gfp_t gfp;
int err;
size_t size = cachep->size;
#if DEBUG
#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
/*
* 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);
} //4//四字节对齐
/*
* 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);
}
/* 3) caller mandated alignment */
if (ralign < cachep->align) {
ralign = cachep->align;
}
/* disable debug if necessary */
if (ralign > __alignof__(unsigned long long))
flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER);
/*
* 4) Store it.
*/
cachep->align = ralign;
if (slab_is_available()) // 为什么要插入这一段注释，因为它就是判断slab_state的值，默认它的值没人初始化即为DOWN.
点击(此处)折叠或打开
/*
* State of the slab allocator.
*
* This is used to describe the states of the allocator during bootup.
* Allocators use this to gradually bootstrap themselves. Most allocators
* have the problem that the structures used for managing slab caches are
* allocated from slab caches themselves.
*/
enum slab_state {
DOWN, /* No slab functionality yet */
PARTIAL, /* SLUB: kmem_cache_node available */
PARTIAL_ARRAYCACHE, /* SLAB: kmalloc size for arraycache available */
PARTIAL_L3, /* SLAB: kmalloc size for l3 struct available */
UP, /* Slab caches usable but not all extras yet */
FULL /* Everything is working */
};
gfp = GFP_KERNEL;
else
gfp = GFP_NOWAIT;
//点击(此处)折叠或打开
#define GFP_NOWAIT (GFP_ATOMIC & ~__GFP_HIGH)
setup_nodelists_pointer(cachep);
#if DEBUG
/*
* 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->object_size > cache_line_size()
&& ALIGN(size, cachep->align) < PAGE_SIZE) {
cachep->obj_offset += PAGE_SIZE - ALIGN(size, cachep->align);
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 // 判断slab管理信息是否在slab分配的内存页上，判断条件见下面：
* it too early on. Always use on-slab management when // size >= (默认page =4k/8k) 512/1024 ; slab_early_init在创建kmem_cache的时候为1；当创建通用cache
* SLAB_NOLEAKTRACE to avoid recursive calls into kmemleak) //的时才会把它初始化为0 . 而第一传递的flags为 SLAB_HWCACHE_ALIGN
*/
if ((size >= (PAGE_SIZE >> 3)) && !slab_early_init &&
!(flags & SLAB_NOLEAKTRACE))
/*
* 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, cachep->align);
left_over = calculate_slab_order(cachep, size, cachep->align, flags); // 根据obj size 计算申请page的个数即一个slab包含多少个pages，
if (!cachep->num) // 也包含了多少个obj，除去管理信息等 剩余的空间。很简单易懂.
return -E2BIG;
slab_size = ALIGN(cachep->num * sizeof(kmem_bufctl_t)
+ sizeof(struct slab), cachep->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.
*/
if (flags & CFLGS_OFF_SLAB && left_over >= slab_size) {
flags &= ~CFLGS_OFF_SLAB;
left_over -= slab_size;
}
if (flags & CFLGS_OFF_SLAB) {
/* really off slab. No need for manual alignment */
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
}
cachep->colour_off = cache_line_size(); //32B
/* Offset must be a multiple of the alignment. */
if (cachep->colour_off < cachep->align)
cachep->colour_off = cachep->align;
cachep->colour = left_over / cachep->colour_off; // slab 着色的初始化工作.
cachep->slab_size = slab_size;
cachep->flags = flags;
cachep->allocflags = 0;
if (CONFIG_ZONE_DMA_FLAG && (flags & SLAB_CACHE_DMA))
cachep->allocflags |= GFP_DMA;
cachep->size = size;
cachep->reciprocal_buffer_size = reciprocal_value(size);
if (flags & CFLGS_OFF_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));
}
err = setup_cpu_cache(cachep, gfp);
if (err) {
__kmem_cache_shutdown(cachep);
return err;
}
if (flags & SLAB_DEBUG_OBJECTS) {
/*
* Would deadlock through slab_destroy()->call_rcu()->
* debug_object_activate()->kmem_cache_alloc().
*/
WARN_ON_ONCE(flags & SLAB_DESTROY_BY_RCU);
slab_set_debugobj_lock_classes(cachep);
} else if (!OFF_SLAB(cachep) && !(flags & SLAB_DESTROY_BY_RCU))
on_slab_lock_classes(cachep);
return 0;
}
它里面有个很有趣的函数很关键的一个函数：它泄露了slab具体管理obj的布局和方法.
点击(此处)折叠或打开
/**
* 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.
*/
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;
cache_estimate(gfporder, size, align, flags, &remainder, &num); // 根据是off-slab 还是on-slab除去管理信息后多少个页面才能存下一个obj.以及其他信息，值得仔细看看.
if (!num) // 必须保证slab至少能装下一个obj
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().
*/
offslab_limit = size - sizeof(struct slab);
offslab_limit /= sizeof(kmem_bufctl_t);
if (num > offslab_limit)
break;
}
/* Found something acceptable - save it away */
cachep->num = num;
cachep->gfporder = gfporder;
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.
*/
if (flags & SLAB_RECLAIM_ACCOUNT)
break;
/*
* Large number of objects is good, but very large slabs are
* currently bad for the gfp()s.
*/
if (gfporder >= slab_max_order)
break;
/*
* Acceptable internal fragmentation?
*/
if (left_over * 8 <= (PAGE_SIZE << gfporder))
break;
}
return left_over;
}
经过上面的初始化和设置，最后调用setup_cpu_cache就完成了一个创建cache的工作.接着进行第2、3步的工作：
点击(此处)折叠或打开
/* 2+3) create the kmalloc caches */
sizes = malloc_sizes;
names = cache_names;
/*
* Initialize the caches that provide memory for the array cache and the
* kmem_list3 structures first. Without this, further allocations will
* bug.
*/
sizes[INDEX_AC].cs_cachep = create_kmalloc_cache(names[INDEX_AC].name, // create obj size 为sizeof(struct arraycache_init) 的cache
sizes[INDEX_AC].cs_size, ARCH_KMALLOC_FLAGS);
if (INDEX_AC != INDEX_L3)
sizes[INDEX_L3].cs_cachep =
create_kmalloc_cache(names[INDEX_L3].name, create obj size 为sizeof(struct kmem_list3) 的cache
sizes[INDEX_L3].cs_size, ARCH_KMALLOC_FLAGS);
slab_early_init = 0;
while (sizes->cs_size != ULONG_MAX) { //创建通用cache 根据malloc_sizes ，cache_names
/*
* For performance, all the general caches are L1 aligned.
* This should be particularly beneficial on SMP boxes, as it
* eliminates "false sharing".
* Note for systems short on memory removing the alignment will
* allow tighter packing of the smaller caches.
*/
if (!sizes->cs_cachep)
sizes->cs_cachep = create_kmalloc_cache(names->name,
sizes->cs_size, ARCH_KMALLOC_FLAGS);
#ifdef CONFIG_ZONE_DMA
sizes->cs_dmacachep = create_kmalloc_cache(
names->name_dma, sizes->cs_size,
SLAB_CACHE_DMA|ARCH_KMALLOC_FLAGS);
#endif
sizes++;
names++;
}
这里在说一下cache_names和malloc_sizes：
点击(此处)折叠或打开
/*
* These are the default caches for kmalloc. Custom caches can have other sizes.
*/
struct cache_sizes malloc_sizes[] = {
#define CACHE(x) { .cs_size = (x) },
#include
CACHE(ULONG_MAX)
#undef CACHE
};
这里就不扩展开了.
点击(此处)折叠或打开
/* Must match cache_sizes above. Out of line to keep cache footprint low. */
struct cache_names {
char *name;
char *name_dma;
};
static struct cache_names __initdata cache_names[] = {
#define CACHE(x) { .name = "size-" #x, .name_dma = "size-" #x "(DMA)" },
#include
{NULL,}
#undef CACHE
};
create_kmalloc_cache实际上是调用create_boot_cache. 把kernel预定义的通用cache创建一遍.之后我们进入第四步、第5步：
点击(此处)折叠或打开
/* 4) Replace the bootstrap head arrays */
{
struct array_cache *ptr;
ptr = kmalloc(sizeof(struct arraycache_init), GFP_NOWAIT);
memcpy(ptr, cpu_cache_get(kmem_cache),
sizeof(struct arraycache_init));
/*
* Do not assume that spinlocks can be initialized via memcpy:
*/
spin_lock_init(&ptr->lock);
kmem_cache->array[smp_processor_id()] = ptr;
ptr = kmalloc(sizeof(struct arraycache_init), GFP_NOWAIT);
BUG_ON(cpu_cache_get(malloc_sizes[INDEX_AC].cs_cachep)
!= &initarray_generic.cache);
memcpy(ptr, cpu_cache_get(malloc_sizes[INDEX_AC].cs_cachep),
sizeof(struct arraycache_init));
/*
* Do not assume that spinlocks can be initialized via memcpy:
*/
spin_lock_init(&ptr->lock);
malloc_sizes[INDEX_AC].cs_cachep->array[smp_processor_id()] =
ptr;
}
点击(此处)折叠或打开
/* 5) Replace the bootstrap kmem_list3's */
{
int nid;
for_each_online_node(nid) {
init_list(kmem_cache, &initkmem_list3[CACHE_CACHE + nid], nid);
init_list(malloc_sizes[INDEX_AC].cs_cachep,
&initkmem_list3[SIZE_AC + nid], nid);
if (INDEX_AC != INDEX_L3) {
init_list(malloc_sizes[INDEX_L3].cs_cachep,
&initkmem_list3[SIZE_L3 + nid], nid);
}
}
}
slab_state = UP;
最后把slab_state状态设置为up 即已经可以正常使用了。虽然上面大部分是代码，具体申请内存的流程前面kmalloc已经讲过了。仅仅是为了弄明白cache到底是个什么玩意，以及如何初始化的。
在kmem_cache_init后，还有一个kmem_cache_init_late函数.
它主要是调用了enable_cpucache和注册一个cpu通知连
点击(此处)折叠或打开
/*
* Register a cpu startup notifier callback that initializes
* cpu_cache_get for all new cpus
*/
register_cpu_notifier(&cpucache_notifier);
还记不记得之前我们分析batchcount的时候的矛盾点？
点击(此处)折叠或打开
/* Called with slab_mutex held always */
static int enable_cpucache(struct kmem_cache *cachep, gfp_t gfp)
{
int err;
int limit = 0;
int shared = 0;
int batchcount = 0;
if (!is_root_cache(cachep)) {
struct kmem_cache *root = memcg_root_cache(cachep);
limit = root->limit;
shared = root->shared;
batchcount = root->batchcount;
}
if (limit && shared && batchcount)
goto skip_setup;
/*
* The head array serves three purposes:
* - create a LIFO ordering, i.e. return objects that are cache-warm
* - reduce the number of spinlock operations.
* - reduce the number of linked list operations on the slab and
* bufctl chains: array operations are cheaper.
* The numbers are guessed, we should auto-tune as described by
* Bonwick.
*/
if (cachep->size > 131072)
limit = 1;
else if (cachep->size > PAGE_SIZE)
limit = 8;
else if (cachep->size > 1024)
limit = 24;
else if (cachep->size > 256)
limit = 54;
else
limit = 120;
/*
* CPU bound tasks (e.g. network routing) can exhibit cpu bound
* allocation behaviour: Most allocs on one cpu, most free operations
* on another cpu. For these cases, an efficient object passing between
* cpus is necessary. This is provided by a shared array. The array
* replaces Bonwick's magazine layer.
* On uniprocessor, it's functionally equivalent (but less efficient)
* to a larger limit. Thus disabled by default.
*/
shared = 0;
if (cachep->size <= PAGE_SIZE && num_possible_cpus() > 1)
shared = 8;
#if DEBUG
/*
* With debugging enabled, large batchcount lead to excessively long
* periods with disabled local interrupts. Limit the batchcount
*/
if (limit > 32)
limit = 32;
#endif
batchcount = (limit + 1) / 2;
skip_setup:
err = do_tune_cpucache(cachep, limit, batchcount, shared, gfp);
if (err)
printk(KERN_ERR "enable_cpucache failed for %s, error %d.\n",
cachep->name, -err);
return err;
}
它会根据obj size 计算limit值 ，再去计算batchcount的值.
这个只是一个小小的开始吧，内存管理本来就博大精深，只有遇到具体问题具体分析，来加深理解了.
2772
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
