slab.c

ARM 嵌入式 系统 设计与实例开发 实验教材 二源码

 */
void * kmalloc (size_t size, int flags)
{
	cache_sizes_t *csizep = cache_sizes;

	for (; csizep->cs_size; csizep++) {
		if (size > csizep->cs_size)
			continue;
		return __kmem_cache_alloc(flags & GFP_DMA ?
			 csizep->cs_dmacachep : csizep->cs_cachep, flags);
	}
	return NULL;
}

/**
 * kmem_cache_free - Deallocate an object
 * @cachep: The cache the allocation was from.
 * @objp: The previously allocated object.
 *
 * Free an object which was previously allocated from this
 * cache.
 */
void kmem_cache_free (kmem_cache_t *cachep, void *objp)
{
	unsigned long flags;
#if DEBUG
	CHECK_PAGE(virt_to_page(objp));
	if (cachep != GET_PAGE_CACHE(virt_to_page(objp)))
		BUG();
#endif

	local_irq_save(flags);
	__kmem_cache_free(cachep, objp);
	local_irq_restore(flags);
}

/**
 * kfree - free previously allocated memory
 * @objp: pointer returned by kmalloc.
 *
 * Don't free memory not originally allocated by kmalloc()
 * or you will run into trouble.
 */
void kfree (const void *objp)
{
	kmem_cache_t *c;
	unsigned long flags;

	if (!objp)
		return;
	local_irq_save(flags);
	CHECK_PAGE(virt_to_page(objp));
	c = GET_PAGE_CACHE(virt_to_page(objp));
	__kmem_cache_free(c, (void*)objp);
	local_irq_restore(flags);
}

kmem_cache_t * kmem_find_general_cachep (size_t size, int gfpflags)
{
	cache_sizes_t *csizep = cache_sizes;

	/* This function could be moved to the header file, and
	 * made inline so consumers can quickly determine what
	 * cache pointer they require.
	 */
	for ( ; csizep->cs_size; csizep++) {
		if (size > csizep->cs_size)
			continue;
		break;
	}
	return (gfpflags & GFP_DMA) ? csizep->cs_dmacachep : csizep->cs_cachep;
}

#ifdef CONFIG_SMP

/* called with cache_chain_sem acquired.  */
static int kmem_tune_cpucache (kmem_cache_t* cachep, int limit, int batchcount)
{
	ccupdate_struct_t new;
	int i;

	/*
	 * These are admin-provided, so we are more graceful.
	 */
	if (limit < 0)
		return -EINVAL;
	if (batchcount < 0)
		return -EINVAL;
	if (batchcount > limit)
		return -EINVAL;
	if (limit != 0 && !batchcount)
		return -EINVAL;

	memset(&new.new,0,sizeof(new.new));
	if (limit) {
		for (i = 0; i< smp_num_cpus; i++) {
			cpucache_t* ccnew;

			ccnew = kmalloc(sizeof(void*)*limit+
					sizeof(cpucache_t), GFP_KERNEL);
			if (!ccnew)
				goto oom;
			ccnew->limit = limit;
			ccnew->avail = 0;
			new.new[cpu_logical_map(i)] = ccnew;
		}
	}
	new.cachep = cachep;
	spin_lock_irq(&cachep->spinlock);
	cachep->batchcount = batchcount;
	spin_unlock_irq(&cachep->spinlock);

	smp_call_function_all_cpus(do_ccupdate_local, (void *)&new);

	for (i = 0; i < smp_num_cpus; i++) {
		cpucache_t* ccold = new.new[cpu_logical_map(i)];
		if (!ccold)
			continue;
		local_irq_disable();
		free_block(cachep, cc_entry(ccold), ccold->avail);
		local_irq_enable();
		kfree(ccold);
	}
	return 0;
oom:
	for (i--; i >= 0; i--)
		kfree(new.new[cpu_logical_map(i)]);
	return -ENOMEM;
}

static void enable_cpucache (kmem_cache_t *cachep)
{
	int err;
	int limit;

	/* FIXME: optimize */
	if (cachep->objsize > PAGE_SIZE)
		return;
	if (cachep->objsize > 1024)
		limit = 60;
	else if (cachep->objsize > 256)
		limit = 124;
	else
		limit = 252;

	err = kmem_tune_cpucache(cachep, limit, limit/2);
	if (err)
		printk(KERN_ERR "enable_cpucache failed for %s, error %d.\n",
					cachep->name, -err);
}

static void enable_all_cpucaches (void)
{
	struct list_head* p;

	down(&cache_chain_sem);

	p = &cache_cache.next;
	do {
		kmem_cache_t* cachep = list_entry(p, kmem_cache_t, next);

		enable_cpucache(cachep);
		p = cachep->next.next;
	} while (p != &cache_cache.next);

	up(&cache_chain_sem);
}
#endif

/**
 * kmem_cache_reap - Reclaim memory from caches.
 * @gfp_mask: the type of memory required.
 *
 * Called from do_try_to_free_pages() and __alloc_pages()
 */
int kmem_cache_reap (int gfp_mask)
{
	slab_t *slabp;
	kmem_cache_t *searchp;
	kmem_cache_t *best_cachep;
	unsigned int best_pages;
	unsigned int best_len;
	unsigned int scan;
	int ret = 0;

	if (gfp_mask & __GFP_WAIT)
		down(&cache_chain_sem);
	else
		if (down_trylock(&cache_chain_sem))
			return 0;

	scan = REAP_SCANLEN;
	best_len = 0;
	best_pages = 0;
	best_cachep = NULL;
	searchp = clock_searchp;
	do {
		unsigned int pages;
		struct list_head* p;
		unsigned int full_free;

		/* It's safe to test this without holding the cache-lock. */
		if (searchp->flags & SLAB_NO_REAP)
			goto next;
		spin_lock_irq(&searchp->spinlock);
		if (searchp->growing)
			goto next_unlock;
		if (searchp->dflags & DFLGS_GROWN) {
			searchp->dflags &= ~DFLGS_GROWN;
			goto next_unlock;
		}
#ifdef CONFIG_SMP
		{
			cpucache_t *cc = cc_data(searchp);
			if (cc && cc->avail) {
				__free_block(searchp, cc_entry(cc), cc->avail);
				cc->avail = 0;
			}
		}
#endif

		full_free = 0;
		p = searchp->slabs_free.next;
		while (p != &searchp->slabs_free) {
			slabp = list_entry(p, slab_t, list);
#if DEBUG
			if (slabp->inuse)
				BUG();
#endif
			full_free++;
			p = p->next;
		}

		/*
		 * Try to avoid slabs with constructors and/or
		 * more than one page per slab (as it can be difficult
		 * to get high orders from gfp()).
		 */
		pages = full_free * (1<<searchp->gfporder);
		if (searchp->ctor)
			pages = (pages*4+1)/5;
		if (searchp->gfporder)
			pages = (pages*4+1)/5;
		if (pages > best_pages) {
			best_cachep = searchp;
			best_len = full_free;
			best_pages = pages;
			if (pages >= REAP_PERFECT) {
				clock_searchp = list_entry(searchp->next.next,
							kmem_cache_t,next);
				goto perfect;
			}
		}
next_unlock:
		spin_unlock_irq(&searchp->spinlock);
next:
		searchp = list_entry(searchp->next.next,kmem_cache_t,next);
	} while (--scan && searchp != clock_searchp);

	clock_searchp = searchp;

	if (!best_cachep)
		/* couldn't find anything to reap */
		goto out;

	spin_lock_irq(&best_cachep->spinlock);
perfect:
	/* free only 50% of the free slabs */
	best_len = (best_len + 1)/2;
	for (scan = 0; scan < best_len; scan++) {
		struct list_head *p;

		if (best_cachep->growing)
			break;
		p = best_cachep->slabs_free.prev;
		if (p == &best_cachep->slabs_free)
			break;
		slabp = list_entry(p,slab_t,list);
#if DEBUG
		if (slabp->inuse)
			BUG();
#endif
		list_del(&slabp->list);
		STATS_INC_REAPED(best_cachep);

		/* Safe to drop the lock. The slab is no longer linked to the
		 * cache.
		 */
		spin_unlock_irq(&best_cachep->spinlock);
		kmem_slab_destroy(best_cachep, slabp);
		spin_lock_irq(&best_cachep->spinlock);
	}
	spin_unlock_irq(&best_cachep->spinlock);
	ret = scan * (1 << best_cachep->gfporder);
out:
	up(&cache_chain_sem);
	return ret;
}

#ifdef CONFIG_PROC_FS
/* /proc/slabinfo
 *	cache-name num-active-objs total-objs
 *	obj-size num-active-slabs total-slabs
 *	num-pages-per-slab
 */
#define FIXUP(t)				\
	do {					\
		if (len <= off) {		\
			off -= len;		\
			len = 0;		\
		} else {			\
			if (len-off > count)	\
				goto t;		\
		}				\
	} while (0)

static int proc_getdata (char*page, char**start, off_t off, int count)
{
	struct list_head *p;
	int len = 0;

	/* Output format version, so at least we can change it without _too_
	 * many complaints.
	 */
	len += sprintf(page+len, "slabinfo - version: 1.1"
#if STATS
				" (statistics)"
#endif
#ifdef CONFIG_SMP
				" (SMP)"
#endif
				"\n");
	FIXUP(got_data);

	down(&cache_chain_sem);
	p = &cache_cache.next;
	do {
		kmem_cache_t	*cachep;
		struct list_head *q;
		slab_t		*slabp;
		unsigned long	active_objs;
		unsigned long	num_objs;
		unsigned long	active_slabs = 0;
		unsigned long	num_slabs;
		cachep = list_entry(p, kmem_cache_t, next);

		spin_lock_irq(&cachep->spinlock);
		active_objs = 0;
		num_slabs = 0;
		list_for_each(q,&cachep->slabs_full) {
			slabp = list_entry(q, slab_t, list);
			if (slabp->inuse != cachep->num)
				BUG();
			active_objs += cachep->num;
			active_slabs++;
		}
		list_for_each(q,&cachep->slabs_partial) {
			slabp = list_entry(q, slab_t, list);
			if (slabp->inuse == cachep->num || !slabp->inuse)
				BUG();
			active_objs += slabp->inuse;
			active_slabs++;
		}
		list_for_each(q,&cachep->slabs_free) {
			slabp = list_entry(q, slab_t, list);
			if (slabp->inuse)
				BUG();
			num_slabs++;
		}
		num_slabs+=active_slabs;
		num_objs = num_slabs*cachep->num;

		len += sprintf(page+len, "%-17s %6lu %6lu %6u %4lu %4lu %4u",
			cachep->name, active_objs, num_objs, cachep->objsize,
			active_slabs, num_slabs, (1<<cachep->gfporder));

#if STATS
		{
			unsigned long errors = cachep->errors;
			unsigned long high = cachep->high_mark;
			unsigned long grown = cachep->grown;
			unsigned long reaped = cachep->reaped;
			unsigned long allocs = cachep->num_allocations;

			len += sprintf(page+len, " : %6lu %7lu %5lu %4lu %4lu",
					high, allocs, grown, reaped, errors);
		}
#endif
#ifdef CONFIG_SMP
		{
			cpucache_t *cc = cc_data(cachep);
			unsigned int batchcount = cachep->batchcount;
			unsigned int limit;

			if (cc)
				limit = cc->limit;
			else
				limit = 0;
			len += sprintf(page+len, " : %4u %4u",
					limit, batchcount);
		}
#endif
#if STATS && defined(CONFIG_SMP)
		{
			unsigned long allochit = atomic_read(&cachep->allochit);
			unsigned long allocmiss = atomic_read(&cachep->allocmiss);
			unsigned long freehit = atomic_read(&cachep->freehit);
			unsigned long freemiss = atomic_read(&cachep->freemiss);
			len += sprintf(page+len, " : %6lu %6lu %6lu %6lu",
					allochit, allocmiss, freehit, freemiss);
		}
#endif
		len += sprintf(page+len,"\n");
		spin_unlock_irq(&cachep->spinlock);
		FIXUP(got_data_up);
		p = cachep->next.next;
	} while (p != &cache_cache.next);
got_data_up:
	up(&cache_chain_sem);

got_data:
	*start = page+off;
	return len;
}

/**
 * slabinfo_read_proc - generates /proc/slabinfo
 * @page: scratch area, one page long
 * @start: pointer to the pointer to the output buffer
 * @off: offset within /proc/slabinfo the caller is interested in
 * @count: requested len in bytes
 * @eof: eof marker
 * @data: unused
 *
 * The contents of the buffer are
 * cache-name
 * num-active-objs
 * total-objs
 * object size
 * num-active-slabs
 * total-slabs
 * num-pages-per-slab
 * + further values on SMP and with statistics enabled
 */
int slabinfo_read_proc (char *page, char **start, off_t off,
				 int count, int *eof, void *data)
{
	int len = proc_getdata(page, start, off, count);
	len -= (*start-page);
	if (len <= count)
		*eof = 1;
	if (len>count) len = count;
	if (len<0) len = 0;
	return len;
}

#define MAX_SLABINFO_WRITE 128
/**
 * slabinfo_write_proc - SMP tuning for the slab allocator
 * @file: unused
 * @buffer: user buffer
 * @count: data len
 * @data: unused
 */
int slabinfo_write_proc (struct file *file, const char *buffer,
				unsigned long count, void *data)
{
#ifdef CONFIG_SMP
	char kbuf[MAX_SLABINFO_WRITE+1], *tmp;
	int limit, batchcount, res;
	struct list_head *p;
	
	if (count > MAX_SLABINFO_WRITE)
		return -EINVAL;
	if (copy_from_user(&kbuf, buffer, count))
		return -EFAULT;
	kbuf[MAX_SLABINFO_WRITE] = '\0'; 

	tmp = strchr(kbuf, ' ');
	if (!tmp)
		return -EINVAL;
	*tmp = '\0';
	tmp++;
	limit = simple_strtol(tmp, &tmp, 10);
	while (*tmp == ' ')
		tmp++;
	batchcount = simple_strtol(tmp, &tmp, 10);

	/* Find the cache in the chain of caches. */
	down(&cache_chain_sem);
	res = -EINVAL;
	list_for_each(p,&cache_chain) {
		kmem_cache_t *cachep = list_entry(p, kmem_cache_t, next);

		if (!strcmp(cachep->name, kbuf)) {
			res = kmem_tune_cpucache(cachep, limit, batchcount);
			break;
		}
	}
	up(&cache_chain_sem);
	if (res >= 0)
		res = count;
	return res;
#else
	return -EINVAL;
#endif
}
#endif