#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
#include <asm/page.h>
+#include <linux/memcontrol.h>
#include "slab.h"
struct kmem_cache *kmem_cache;
#ifdef CONFIG_DEBUG_VM
-static int kmem_cache_sanity_check(const char *name, size_t size)
+static int kmem_cache_sanity_check(struct mem_cgroup *memcg, const char *name,
+ size_t size)
{
struct kmem_cache *s = NULL;
continue;
}
- if (!strcmp(s->name, name)) {
+ /*
+ * For simplicity, we won't check this in the list of memcg
+ * caches. We have control over memcg naming, and if there
+ * aren't duplicates in the global list, there won't be any
+ * duplicates in the memcg lists as well.
+ */
+ if (!memcg && !strcmp(s->name, name)) {
pr_err("%s (%s): Cache name already exists.\n",
__func__, name);
dump_stack();
return 0;
}
#else
-static inline int kmem_cache_sanity_check(const char *name, size_t size)
+static inline int kmem_cache_sanity_check(struct mem_cgroup *memcg,
+ const char *name, size_t size)
{
return 0;
}
#endif
+#ifdef CONFIG_MEMCG_KMEM
+int memcg_update_all_caches(int num_memcgs)
+{
+ struct kmem_cache *s;
+ int ret = 0;
+ mutex_lock(&slab_mutex);
+
+ list_for_each_entry(s, &slab_caches, list) {
+ if (!is_root_cache(s))
+ continue;
+
+ ret = memcg_update_cache_size(s, num_memcgs);
+ /*
+ * See comment in memcontrol.c, memcg_update_cache_size:
+ * Instead of freeing the memory, we'll just leave the caches
+ * up to this point in an updated state.
+ */
+ if (ret)
+ goto out;
+ }
+
+ memcg_update_array_size(num_memcgs);
+out:
+ mutex_unlock(&slab_mutex);
+ return ret;
+}
+#endif
+
/*
* Figure out what the alignment of the objects will be given a set of
* flags, a user specified alignment and the size of the objects.
* as davem.
*/
-struct kmem_cache *kmem_cache_create(const char *name, size_t size, size_t align,
- unsigned long flags, void (*ctor)(void *))
+struct kmem_cache *
+kmem_cache_create_memcg(struct mem_cgroup *memcg, const char *name, size_t size,
+ size_t align, unsigned long flags, void (*ctor)(void *),
+ struct kmem_cache *parent_cache)
{
struct kmem_cache *s = NULL;
int err = 0;
get_online_cpus();
mutex_lock(&slab_mutex);
- if (!kmem_cache_sanity_check(name, size) == 0)
+ if (!kmem_cache_sanity_check(memcg, name, size) == 0)
goto out_locked;
/*
*/
flags &= CACHE_CREATE_MASK;
- s = __kmem_cache_alias(name, size, align, flags, ctor);
+ s = __kmem_cache_alias(memcg, name, size, align, flags, ctor);
if (s)
goto out_locked;
s->object_size = s->size = size;
s->align = calculate_alignment(flags, align, size);
s->ctor = ctor;
+
+ if (memcg_register_cache(memcg, s, parent_cache)) {
+ kmem_cache_free(kmem_cache, s);
+ err = -ENOMEM;
+ goto out_locked;
+ }
+
s->name = kstrdup(name, GFP_KERNEL);
if (!s->name) {
kmem_cache_free(kmem_cache, s);
err = __kmem_cache_create(s, flags);
if (!err) {
-
s->refcount = 1;
list_add(&s->list, &slab_caches);
-
+ memcg_cache_list_add(memcg, s);
} else {
kfree(s->name);
kmem_cache_free(kmem_cache, s);
return s;
}
+
+struct kmem_cache *
+kmem_cache_create(const char *name, size_t size, size_t align,
+ unsigned long flags, void (*ctor)(void *))
+{
+ return kmem_cache_create_memcg(NULL, name, size, align, flags, ctor, NULL);
+}
EXPORT_SYMBOL(kmem_cache_create);
void kmem_cache_destroy(struct kmem_cache *s)
{
+ /* Destroy all the children caches if we aren't a memcg cache */
+ kmem_cache_destroy_memcg_children(s);
+
get_online_cpus();
mutex_lock(&slab_mutex);
s->refcount--;
if (s->flags & SLAB_DESTROY_BY_RCU)
rcu_barrier();
+ memcg_release_cache(s);
kfree(s->name);
kmem_cache_free(kmem_cache, s);
} else {
err = __kmem_cache_create(s, flags);
if (err)
- panic("Creation of kmalloc slab %s size=%zd failed. Reason %d\n",
+ panic("Creation of kmalloc slab %s size=%zu failed. Reason %d\n",
name, size, err);
s->refcount = -1; /* Exempt from merging for now */
return s;
}
+struct kmem_cache *kmalloc_caches[KMALLOC_SHIFT_HIGH + 1];
+EXPORT_SYMBOL(kmalloc_caches);
+
+#ifdef CONFIG_ZONE_DMA
+struct kmem_cache *kmalloc_dma_caches[KMALLOC_SHIFT_HIGH + 1];
+EXPORT_SYMBOL(kmalloc_dma_caches);
+#endif
+
+/*
+ * Conversion table for small slabs sizes / 8 to the index in the
+ * kmalloc array. This is necessary for slabs < 192 since we have non power
+ * of two cache sizes there. The size of larger slabs can be determined using
+ * fls.
+ */
+static s8 size_index[24] = {
+ 3, /* 8 */
+ 4, /* 16 */
+ 5, /* 24 */
+ 5, /* 32 */
+ 6, /* 40 */
+ 6, /* 48 */
+ 6, /* 56 */
+ 6, /* 64 */
+ 1, /* 72 */
+ 1, /* 80 */
+ 1, /* 88 */
+ 1, /* 96 */
+ 7, /* 104 */
+ 7, /* 112 */
+ 7, /* 120 */
+ 7, /* 128 */
+ 2, /* 136 */
+ 2, /* 144 */
+ 2, /* 152 */
+ 2, /* 160 */
+ 2, /* 168 */
+ 2, /* 176 */
+ 2, /* 184 */
+ 2 /* 192 */
+};
+
+static inline int size_index_elem(size_t bytes)
+{
+ return (bytes - 1) / 8;
+}
+
+/*
+ * Find the kmem_cache structure that serves a given size of
+ * allocation
+ */
+struct kmem_cache *kmalloc_slab(size_t size, gfp_t flags)
+{
+ int index;
+
+ if (WARN_ON_ONCE(size > KMALLOC_MAX_SIZE))
+ return NULL;
+
+ if (size <= 192) {
+ if (!size)
+ return ZERO_SIZE_PTR;
+
+ index = size_index[size_index_elem(size)];
+ } else
+ index = fls(size - 1);
+
+#ifdef CONFIG_ZONE_DMA
+ if (unlikely((flags & GFP_DMA)))
+ return kmalloc_dma_caches[index];
+
+#endif
+ return kmalloc_caches[index];
+}
+
+/*
+ * Create the kmalloc array. Some of the regular kmalloc arrays
+ * may already have been created because they were needed to
+ * enable allocations for slab creation.
+ */
+void __init create_kmalloc_caches(unsigned long flags)
+{
+ int i;
+
+ /*
+ * Patch up the size_index table if we have strange large alignment
+ * requirements for the kmalloc array. This is only the case for
+ * MIPS it seems. The standard arches will not generate any code here.
+ *
+ * Largest permitted alignment is 256 bytes due to the way we
+ * handle the index determination for the smaller caches.
+ *
+ * Make sure that nothing crazy happens if someone starts tinkering
+ * around with ARCH_KMALLOC_MINALIGN
+ */
+ BUILD_BUG_ON(KMALLOC_MIN_SIZE > 256 ||
+ (KMALLOC_MIN_SIZE & (KMALLOC_MIN_SIZE - 1)));
+
+ for (i = 8; i < KMALLOC_MIN_SIZE; i += 8) {
+ int elem = size_index_elem(i);
+
+ if (elem >= ARRAY_SIZE(size_index))
+ break;
+ size_index[elem] = KMALLOC_SHIFT_LOW;
+ }
+
+ if (KMALLOC_MIN_SIZE >= 64) {
+ /*
+ * The 96 byte size cache is not used if the alignment
+ * is 64 byte.
+ */
+ for (i = 64 + 8; i <= 96; i += 8)
+ size_index[size_index_elem(i)] = 7;
+
+ }
+
+ if (KMALLOC_MIN_SIZE >= 128) {
+ /*
+ * The 192 byte sized cache is not used if the alignment
+ * is 128 byte. Redirect kmalloc to use the 256 byte cache
+ * instead.
+ */
+ for (i = 128 + 8; i <= 192; i += 8)
+ size_index[size_index_elem(i)] = 8;
+ }
+ /* Caches that are not of the two-to-the-power-of size */
+ if (KMALLOC_MIN_SIZE <= 32 && !kmalloc_caches[1])
+ kmalloc_caches[1] = create_kmalloc_cache(NULL, 96, flags);
+
+ if (KMALLOC_MIN_SIZE <= 64 && !kmalloc_caches[2])
+ kmalloc_caches[2] = create_kmalloc_cache(NULL, 192, flags);
+
+ for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++)
+ if (!kmalloc_caches[i])
+ kmalloc_caches[i] = create_kmalloc_cache(NULL,
+ 1 << i, flags);
+
+ /* Kmalloc array is now usable */
+ slab_state = UP;
+
+ for (i = 0; i <= KMALLOC_SHIFT_HIGH; i++) {
+ struct kmem_cache *s = kmalloc_caches[i];
+ char *n;
+
+ if (s) {
+ n = kasprintf(GFP_NOWAIT, "kmalloc-%d", kmalloc_size(i));
+
+ BUG_ON(!n);
+ s->name = n;
+ }
+ }
+
+#ifdef CONFIG_ZONE_DMA
+ for (i = 0; i <= KMALLOC_SHIFT_HIGH; i++) {
+ struct kmem_cache *s = kmalloc_caches[i];
+
+ if (s) {
+ int size = kmalloc_size(i);
+ char *n = kasprintf(GFP_NOWAIT,
+ "dma-kmalloc-%d", size);
+
+ BUG_ON(!n);
+ kmalloc_dma_caches[i] = create_kmalloc_cache(n,
+ size, SLAB_CACHE_DMA | flags);
+ }
+ }
+#endif
+}
#endif /* !CONFIG_SLOB */
#ifdef CONFIG_SLABINFO
-static void print_slabinfo_header(struct seq_file *m)
+void print_slabinfo_header(struct seq_file *m)
{
/*
* Output format version, so at least we can change it
mutex_unlock(&slab_mutex);
}
-static int s_show(struct seq_file *m, void *p)
+static void
+memcg_accumulate_slabinfo(struct kmem_cache *s, struct slabinfo *info)
+{
+ struct kmem_cache *c;
+ struct slabinfo sinfo;
+ int i;
+
+ if (!is_root_cache(s))
+ return;
+
+ for_each_memcg_cache_index(i) {
+ c = cache_from_memcg(s, i);
+ if (!c)
+ continue;
+
+ memset(&sinfo, 0, sizeof(sinfo));
+ get_slabinfo(c, &sinfo);
+
+ info->active_slabs += sinfo.active_slabs;
+ info->num_slabs += sinfo.num_slabs;
+ info->shared_avail += sinfo.shared_avail;
+ info->active_objs += sinfo.active_objs;
+ info->num_objs += sinfo.num_objs;
+ }
+}
+
+int cache_show(struct kmem_cache *s, struct seq_file *m)
{
- struct kmem_cache *s = list_entry(p, struct kmem_cache, list);
struct slabinfo sinfo;
memset(&sinfo, 0, sizeof(sinfo));
get_slabinfo(s, &sinfo);
+ memcg_accumulate_slabinfo(s, &sinfo);
+
seq_printf(m, "%-17s %6lu %6lu %6u %4u %4d",
- s->name, sinfo.active_objs, sinfo.num_objs, s->size,
+ cache_name(s), sinfo.active_objs, sinfo.num_objs, s->size,
sinfo.objects_per_slab, (1 << sinfo.cache_order));
seq_printf(m, " : tunables %4u %4u %4u",
return 0;
}
+static int s_show(struct seq_file *m, void *p)
+{
+ struct kmem_cache *s = list_entry(p, struct kmem_cache, list);
+
+ if (!is_root_cache(s))
+ return 0;
+ return cache_show(s, m);
+}
+
/*
* slabinfo_op - iterator that generates /proc/slabinfo
*