*
* - Support PAGE_ALLOC_DEBUG. Should be easy to do.
*
- * - SLAB_DEBUG_INITIAL is not supported but I have never seen a use of
- * it.
- *
* - Variable sizing of the per node arrays
*/
#endif
/*
- * Flags from the regular SLAB that SLUB does not support:
+ * 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 SLUB_UNIMPLEMENTED (SLAB_DEBUG_INITIAL)
-
-/* Mininum number of partial slabs */
#define MIN_PARTIAL 2
+/*
+ * 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)
/*
static void restore_bytes(struct kmem_cache *s, char *message, u8 data,
void *from, void *to)
{
- printk(KERN_ERR "@@@ SLUB: %s Restoring %s (0x%x) from 0x%p-0x%p\n",
+ printk(KERN_ERR "@@@ SLUB %s: Restoring %s (0x%x) from 0x%p-0x%p\n",
s->name, message, data, from, to - 1);
memset(from, data, to - from);
}
return 1;
if (!check_bytes(p + length, POISON_INUSE, remainder)) {
- printk(KERN_ERR "SLUB: %s slab 0x%p: Padding fails check\n",
- s->name, p);
- dump_stack();
+ slab_err(s, page, "Padding check failed");
restore_bytes(s, "slab padding", POISON_INUSE, p + length,
p + length + remainder);
return 0;
VM_BUG_ON(!irqs_disabled());
if (!PageSlab(page)) {
- printk(KERN_ERR "SLUB: %s Not a valid slab page @0x%p "
- "flags=%lx mapping=0x%p count=%d \n",
- s->name, page, page->flags, page->mapping,
+ slab_err(s, page, "Not a valid slab page flags=%lx "
+ "mapping=0x%p count=%d", page->flags, page->mapping,
page_count(page));
return 0;
}
if (page->offset * sizeof(void *) != s->offset) {
- printk(KERN_ERR "SLUB: %s Corrupted offset %lu in slab @0x%p"
- " flags=0x%lx mapping=0x%p count=%d\n",
- s->name,
+ slab_err(s, page, "Corrupted offset %lu flags=0x%lx "
+ "mapping=0x%p count=%d",
(unsigned long)(page->offset * sizeof(void *)),
- page,
page->flags,
page->mapping,
page_count(page));
- dump_stack();
return 0;
}
if (page->inuse > s->objects) {
- printk(KERN_ERR "SLUB: %s Inuse %u > max %u in slab "
- "page @0x%p flags=%lx mapping=0x%p count=%d\n",
- s->name, page->inuse, s->objects, page, page->flags,
+ slab_err(s, page, "inuse %u > max %u @0x%p flags=%lx "
+ "mapping=0x%p count=%d",
+ s->name, page->inuse, s->objects, page->flags,
page->mapping, page_count(page));
- dump_stack();
return 0;
}
/* Slab_pad_check fixes things up after itself */
set_freepointer(s, object, NULL);
break;
} else {
- printk(KERN_ERR "SLUB: %s slab 0x%p "
- "freepointer 0x%p corrupted.\n",
- s->name, page, fp);
- dump_stack();
+ slab_err(s, page, "Freepointer 0x%p corrupt",
+ fp);
page->freelist = NULL;
page->inuse = s->objects;
+ printk(KERN_ERR "@@@ SLUB %s: Freelist "
+ "cleared. Slab 0x%p\n",
+ s->name, page);
return 0;
}
break;
}
if (page->inuse != s->objects - nr) {
- printk(KERN_ERR "slab %s: page 0x%p wrong object count."
- " counter is %d but counted were %d\n",
- s->name, page, page->inuse,
- s->objects - nr);
+ slab_err(s, page, "Wrong object count. Counter is %d but "
+ "counted were %d", s, page, page->inuse,
+ s->objects - nr);
page->inuse = s->objects - nr;
+ printk(KERN_ERR "@@@ SLUB %s: Object count adjusted. "
+ "Slab @0x%p\n", s->name, page);
}
return search == NULL;
}
goto bad;
if (object && !on_freelist(s, page, object)) {
- printk(KERN_ERR "SLUB: %s Object 0x%p@0x%p "
- "already allocated.\n",
- s->name, object, page);
- goto dump;
+ slab_err(s, page, "Object 0x%p already allocated", object);
+ goto bad;
}
if (!check_valid_pointer(s, page, object)) {
object_err(s, page, object, "Freelist Pointer check fails");
- goto dump;
+ goto bad;
}
if (!object)
if (!check_object(s, page, object, 0))
goto bad;
- init_object(s, object, 1);
- if (s->flags & SLAB_TRACE) {
- printk(KERN_INFO "TRACE %s alloc 0x%p inuse=%d fp=0x%p\n",
- s->name, object, page->inuse,
- page->freelist);
- dump_stack();
- }
return 1;
-dump:
- dump_stack();
bad:
if (PageSlab(page)) {
/*
goto fail;
if (!check_valid_pointer(s, page, object)) {
- printk(KERN_ERR "SLUB: %s slab 0x%p invalid "
- "object pointer 0x%p\n",
- s->name, page, object);
+ slab_err(s, page, "Invalid object pointer 0x%p", object);
goto fail;
}
if (on_freelist(s, page, object)) {
- printk(KERN_ERR "SLUB: %s slab 0x%p object "
- "0x%p already free.\n", s->name, page, object);
+ slab_err(s, page, "Object 0x%p already free", object);
goto fail;
}
if (unlikely(s != page->slab)) {
if (!PageSlab(page))
- printk(KERN_ERR "slab_free %s size %d: attempt to"
- "free object(0x%p) outside of slab.\n",
- s->name, s->size, object);
+ slab_err(s, page, "Attempt to free object(0x%p) "
+ "outside of slab", object);
else
- if (!page->slab)
+ if (!page->slab) {
printk(KERN_ERR
- "slab_free : no slab(NULL) for object 0x%p.\n",
+ "SLUB <none>: no slab for object 0x%p.\n",
object);
+ dump_stack();
+ }
else
- printk(KERN_ERR "slab_free %s(%d): object at 0x%p"
- " belongs to slab %s(%d)\n",
- s->name, s->size, object,
- page->slab->name, page->slab->size);
+ slab_err(s, page, "object at 0x%p belongs "
+ "to slab %s", object, page->slab->name);
goto fail;
}
- if (s->flags & SLAB_TRACE) {
- printk(KERN_INFO "TRACE %s free 0x%p inuse=%d fp=0x%p\n",
- s->name, object, page->inuse,
- page->freelist);
- print_section("Object", object, s->objsize);
- dump_stack();
- }
- init_object(s, object, 0);
return 1;
fail:
- dump_stack();
printk(KERN_ERR "@@@ SLUB: %s slab 0x%p object at 0x%p not freed.\n",
s->name, page, object);
return 0;
init_tracking(s, object);
}
- if (unlikely(s->ctor)) {
- int mode = SLAB_CTOR_CONSTRUCTOR;
-
- if (!(s->flags & __GFP_WAIT))
- mode |= SLAB_CTOR_ATOMIC;
-
- s->ctor(object, s, mode);
- }
+ if (unlikely(s->ctor))
+ s->ctor(object, s, SLAB_CTOR_CONSTRUCTOR);
}
static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
goto another_slab;
if (s->flags & SLAB_STORE_USER)
set_track(s, object, TRACK_ALLOC, addr);
+ if (s->flags & SLAB_TRACE) {
+ printk(KERN_INFO "TRACE %s alloc 0x%p inuse=%d fp=0x%p\n",
+ s->name, object, page->inuse,
+ page->freelist);
+ dump_stack();
+ }
+ init_object(s, object, 1);
goto have_object;
}
remove_full(s, page);
if (s->flags & SLAB_STORE_USER)
set_track(s, x, TRACK_FREE, addr);
+ if (s->flags & SLAB_TRACE) {
+ printk(KERN_INFO "TRACE %s free 0x%p inuse=%d fp=0x%p\n",
+ s->name, object, page->inuse,
+ page->freelist);
+ print_section("Object", (void *)object, s->objsize);
+ dump_stack();
+ }
+ init_object(s, object, 0);
goto checks_ok;
}
* specified alignment though. If that is greater
* then use it.
*/
- if ((flags & (SLAB_MUST_HWCACHE_ALIGN | SLAB_HWCACHE_ALIGN)) &&
+ if ((flags & SLAB_HWCACHE_ALIGN) &&
size > L1_CACHE_BYTES / 2)
return max_t(unsigned long, align, L1_CACHE_BYTES);
s->flags = flags;
s->align = align;
- BUG_ON(flags & SLUB_UNIMPLEMENTED);
-
/*
* The page->offset field is only 16 bit wide. This is an offset
* in units of words from the beginning of an object. If the slab
for_each_online_node(node) {
struct kmem_cache_node *n = get_node(s, node);
- free_list(s, n, &n->partial);
+ n->nr_partial -= free_list(s, n, &n->partial);
if (atomic_long_read(&n->nr_slabs))
return 1;
}
}
EXPORT_SYMBOL(kfree);
+/*
+ * kmem_cache_shrink removes empty slabs from the partial lists
+ * and then sorts the partially allocated slabs by the number
+ * of items in use. The slabs with the most items in use
+ * come first. New allocations will remove these from the
+ * partial list because they are full. The slabs with the
+ * least items are placed last. If it happens that the objects
+ * are freed then the page can be returned to the page allocator.
+ */
+int kmem_cache_shrink(struct kmem_cache *s)
+{
+ int node;
+ int i;
+ struct kmem_cache_node *n;
+ struct page *page;
+ struct page *t;
+ struct list_head *slabs_by_inuse =
+ kmalloc(sizeof(struct list_head) * s->objects, GFP_KERNEL);
+ unsigned long flags;
+
+ if (!slabs_by_inuse)
+ return -ENOMEM;
+
+ flush_all(s);
+ for_each_online_node(node) {
+ n = get_node(s, node);
+
+ if (!n->nr_partial)
+ continue;
+
+ for (i = 0; i < s->objects; i++)
+ INIT_LIST_HEAD(slabs_by_inuse + i);
+
+ spin_lock_irqsave(&n->list_lock, flags);
+
+ /*
+ * Build lists indexed by the items in use in
+ * each slab or free slabs if empty.
+ *
+ * Note that concurrent frees may occur while
+ * we hold the list_lock. page->inuse here is
+ * the upper limit.
+ */
+ list_for_each_entry_safe(page, t, &n->partial, lru) {
+ if (!page->inuse && slab_trylock(page)) {
+ /*
+ * Must hold slab lock here because slab_free
+ * may have freed the last object and be
+ * waiting to release the slab.
+ */
+ list_del(&page->lru);
+ n->nr_partial--;
+ slab_unlock(page);
+ discard_slab(s, page);
+ } else {
+ if (n->nr_partial > MAX_PARTIAL)
+ list_move(&page->lru,
+ slabs_by_inuse + page->inuse);
+ }
+ }
+
+ if (n->nr_partial <= MAX_PARTIAL)
+ goto out;
+
+ /*
+ * Rebuild the partial list with the slabs filled up
+ * most first and the least used slabs at the end.
+ */
+ for (i = s->objects - 1; i >= 0; i--)
+ list_splice(slabs_by_inuse + i, n->partial.prev);
+
+ out:
+ spin_unlock_irqrestore(&n->list_lock, flags);
+ }
+
+ kfree(slabs_by_inuse);
+ return 0;
+}
+EXPORT_SYMBOL(kmem_cache_shrink);
+
/**
* krealloc - reallocate memory. The contents will remain unchanged.
*
#endif
-/***************************************************************
- * Compatiblility definitions
- **************************************************************/
-
-int kmem_cache_shrink(struct kmem_cache *s)
-{
- flush_all(s);
- return 0;
-}
-EXPORT_SYMBOL(kmem_cache_shrink);
-
#ifdef CONFIG_NUMA
/*****************************************************************
static ssize_t hwcache_align_show(struct kmem_cache *s, char *buf)
{
- return sprintf(buf, "%d\n", !!(s->flags &
- (SLAB_HWCACHE_ALIGN|SLAB_MUST_HWCACHE_ALIGN)));
+ return sprintf(buf, "%d\n", !!(s->flags & SLAB_HWCACHE_ALIGN));
}
SLAB_ATTR_RO(hwcache_align);
}
SLAB_ATTR(validate);
+static ssize_t shrink_show(struct kmem_cache *s, char *buf)
+{
+ return 0;
+}
+
+static ssize_t shrink_store(struct kmem_cache *s,
+ const char *buf, size_t length)
+{
+ if (buf[0] == '1') {
+ int rc = kmem_cache_shrink(s);
+
+ if (rc)
+ return rc;
+ } else
+ return -EINVAL;
+ return length;
+}
+SLAB_ATTR(shrink);
+
static ssize_t alloc_calls_show(struct kmem_cache *s, char *buf)
{
if (!(s->flags & SLAB_STORE_USER))
&poison_attr.attr,
&store_user_attr.attr,
&validate_attr.attr,
+ &shrink_attr.attr,
&alloc_calls_attr.attr,
&free_calls_attr.attr,
#ifdef CONFIG_ZONE_DMA
projects / firefly-linux-kernel-4.4.55.git / blobdiff