#include <linux/reciprocal_div.h>
#include <linux/debugobjects.h>
#include <linux/kmemcheck.h>
++++ +#include <linux/memory.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
#define BYTES_PER_WORD sizeof(void *)
#define REDZONE_ALIGN max(BYTES_PER_WORD, __alignof__(unsigned long long))
- ----#ifndef ARCH_KMALLOC_MINALIGN
- ----/*
- ---- * Enforce a minimum alignment for the kmalloc caches.
- ---- * Usually, the kmalloc caches are cache_line_size() aligned, except when
- ---- * DEBUG and FORCED_DEBUG are enabled, then they are BYTES_PER_WORD aligned.
- ---- * Some archs want to perform DMA into kmalloc caches and need a guaranteed
- ---- * alignment larger than the alignment of a 64-bit integer.
- ---- * ARCH_KMALLOC_MINALIGN allows that.
- ---- * Note that increasing this value may disable some debug features.
- ---- */
- ----#define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long)
- ----#endif
- ----
- ----#ifndef ARCH_SLAB_MINALIGN
- ----/*
- ---- * Enforce a minimum alignment for all caches.
- ---- * Intended for archs that get misalignment faults even for BYTES_PER_WORD
- ---- * aligned buffers. Includes ARCH_KMALLOC_MINALIGN.
- ---- * If possible: Do not enable this flag for CONFIG_DEBUG_SLAB, it disables
- ---- * some debug features.
- ---- */
- ----#define ARCH_SLAB_MINALIGN 0
- ----#endif
- ----
#ifndef ARCH_KMALLOC_FLAGS
#define ARCH_KMALLOC_FLAGS SLAB_HWCACHE_ALIGN
#endif
}
#endif
++++ +/*
++++ + * Allocates and initializes nodelists for a node on each slab cache, used for
++++ + * either memory or cpu hotplug. If memory is being hot-added, the kmem_list3
++++ + * will be allocated off-node since memory is not yet online for the new node.
++++ + * When hotplugging memory or a cpu, existing nodelists are not replaced if
++++ + * already in use.
++++ + *
++++ + * Must hold cache_chain_mutex.
++++ + */
++++ +static int init_cache_nodelists_node(int node)
++++ +{
++++ + struct kmem_cache *cachep;
++++ + struct kmem_list3 *l3;
++++ + const int memsize = sizeof(struct kmem_list3);
++++ +
++++ + list_for_each_entry(cachep, &cache_chain, next) {
++++ + /*
++++ + * Set up the size64 kmemlist for cpu before we can
++++ + * begin anything. Make sure some other cpu on this
++++ + * node has not already allocated this
++++ + */
++++ + if (!cachep->nodelists[node]) {
++++ + l3 = kmalloc_node(memsize, GFP_KERNEL, node);
++++ + if (!l3)
++++ + return -ENOMEM;
++++ + kmem_list3_init(l3);
++++ + l3->next_reap = jiffies + REAPTIMEOUT_LIST3 +
++++ + ((unsigned long)cachep) % REAPTIMEOUT_LIST3;
++++ +
++++ + /*
++++ + * The l3s don't come and go as CPUs come and
++++ + * go. cache_chain_mutex is sufficient
++++ + * protection here.
++++ + */
++++ + cachep->nodelists[node] = l3;
++++ + }
++++ +
++++ + spin_lock_irq(&cachep->nodelists[node]->list_lock);
++++ + cachep->nodelists[node]->free_limit =
++++ + (1 + nr_cpus_node(node)) *
++++ + cachep->batchcount + cachep->num;
++++ + spin_unlock_irq(&cachep->nodelists[node]->list_lock);
++++ + }
++++ + return 0;
++++ +}
++++ +
static void __cpuinit cpuup_canceled(long cpu)
{
struct kmem_cache *cachep;
struct kmem_cache *cachep;
struct kmem_list3 *l3 = NULL;
int node = cpu_to_node(cpu);
---- - const int memsize = sizeof(struct kmem_list3);
++++ + int err;
/*
* We need to do this right in the beginning since
* kmalloc_node allows us to add the slab to the right
* kmem_list3 and not this cpu's kmem_list3
*/
---- -
---- - list_for_each_entry(cachep, &cache_chain, next) {
---- - /*
---- - * Set up the size64 kmemlist for cpu before we can
---- - * begin anything. Make sure some other cpu on this
---- - * node has not already allocated this
---- - */
---- - if (!cachep->nodelists[node]) {
---- - l3 = kmalloc_node(memsize, GFP_KERNEL, node);
---- - if (!l3)
---- - goto bad;
---- - kmem_list3_init(l3);
---- - l3->next_reap = jiffies + REAPTIMEOUT_LIST3 +
---- - ((unsigned long)cachep) % REAPTIMEOUT_LIST3;
---- -
---- - /*
---- - * The l3s don't come and go as CPUs come and
---- - * go. cache_chain_mutex is sufficient
---- - * protection here.
---- - */
---- - cachep->nodelists[node] = l3;
---- - }
---- -
---- - spin_lock_irq(&cachep->nodelists[node]->list_lock);
---- - cachep->nodelists[node]->free_limit =
---- - (1 + nr_cpus_node(node)) *
---- - cachep->batchcount + cachep->num;
---- - spin_unlock_irq(&cachep->nodelists[node]->list_lock);
---- - }
++++ + err = init_cache_nodelists_node(node);
++++ + if (err < 0)
++++ + goto bad;
/*
* Now we can go ahead with allocating the shared arrays and
&cpuup_callback, NULL, 0
};
++++ +#if defined(CONFIG_NUMA) && defined(CONFIG_MEMORY_HOTPLUG)
++++ +/*
++++ + * Drains freelist for a node on each slab cache, used for memory hot-remove.
++++ + * Returns -EBUSY if all objects cannot be drained so that the node is not
++++ + * removed.
++++ + *
++++ + * Must hold cache_chain_mutex.
++++ + */
++++ +static int __meminit drain_cache_nodelists_node(int node)
++++ +{
++++ + struct kmem_cache *cachep;
++++ + int ret = 0;
++++ +
++++ + list_for_each_entry(cachep, &cache_chain, next) {
++++ + struct kmem_list3 *l3;
++++ +
++++ + l3 = cachep->nodelists[node];
++++ + if (!l3)
++++ + continue;
++++ +
++++ + drain_freelist(cachep, l3, l3->free_objects);
++++ +
++++ + if (!list_empty(&l3->slabs_full) ||
++++ + !list_empty(&l3->slabs_partial)) {
++++ + ret = -EBUSY;
++++ + break;
++++ + }
++++ + }
++++ + return ret;
++++ +}
++++ +
++++ +static int __meminit slab_memory_callback(struct notifier_block *self,
++++ + unsigned long action, void *arg)
++++ +{
++++ + struct memory_notify *mnb = arg;
++++ + int ret = 0;
++++ + int nid;
++++ +
++++ + nid = mnb->status_change_nid;
++++ + if (nid < 0)
++++ + goto out;
++++ +
++++ + switch (action) {
++++ + case MEM_GOING_ONLINE:
++++ + mutex_lock(&cache_chain_mutex);
++++ + ret = init_cache_nodelists_node(nid);
++++ + mutex_unlock(&cache_chain_mutex);
++++ + break;
++++ + case MEM_GOING_OFFLINE:
++++ + mutex_lock(&cache_chain_mutex);
++++ + ret = drain_cache_nodelists_node(nid);
++++ + mutex_unlock(&cache_chain_mutex);
++++ + break;
++++ + case MEM_ONLINE:
++++ + case MEM_OFFLINE:
++++ + case MEM_CANCEL_ONLINE:
++++ + case MEM_CANCEL_OFFLINE:
++++ + break;
++++ + }
++++ +out:
++++ + return ret ? notifier_from_errno(ret) : NOTIFY_OK;
++++ +}
++++ +#endif /* CONFIG_NUMA && CONFIG_MEMORY_HOTPLUG */
++++ +
/*
* swap the static kmem_list3 with kmalloced memory
*/
---- -static void init_list(struct kmem_cache *cachep, struct kmem_list3 *list,
---- - int nodeid)
++++ +static void __init init_list(struct kmem_cache *cachep, struct kmem_list3 *list,
++++ + int nodeid)
{
struct kmem_list3 *ptr;
*/
register_cpu_notifier(&cpucache_notifier);
++++ +#ifdef CONFIG_NUMA
++++ + /*
++++ + * Register a memory hotplug callback that initializes and frees
++++ + * nodelists.
++++ + */
++++ + hotplug_memory_notifier(slab_memory_callback, SLAB_CALLBACK_PRI);
++++ +#endif
++++ +
/*
* The reap timers are started later, with a module init call: That part
* of the kernel is not yet operational.
if (ralign < align) {
ralign = align;
}
--- -- /* disable debug if necessary */
--- -- if (ralign > __alignof__(unsigned long long))
+++ ++ /* disable debug if not aligning with REDZONE_ALIGN */
+++ ++ if (ralign & (__alignof__(unsigned long long) - 1))
flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER);
/*
* 4) Store it.
*/
if (flags & SLAB_RED_ZONE) {
/* add space for red zone words */
--- -- cachep->obj_offset += sizeof(unsigned long long);
--- -- size += 2 * sizeof(unsigned long long);
+++ ++ cachep->obj_offset += align;
+++ ++ size += align + sizeof(unsigned long long);
}
if (flags & SLAB_STORE_USER) {
/* user store requires one word storage behind the end of
*/
int kmem_ptr_validate(struct kmem_cache *cachep, const void *ptr)
{
- - unsigned long addr = (unsigned long)ptr;
- - unsigned long min_addr = PAGE_OFFSET;
- - unsigned long align_mask = BYTES_PER_WORD - 1;
unsigned long size = cachep->buffer_size;
struct page *page;
- - if (unlikely(addr < min_addr))
- - goto out;
- - if (unlikely(addr > (unsigned long)high_memory - size))
- - goto out;
- - if (unlikely(addr & align_mask))
- - goto out;
- - if (unlikely(!kern_addr_valid(addr)))
- - goto out;
- - if (unlikely(!kern_addr_valid(addr + size - 1)))
+ + if (unlikely(!kern_ptr_validate(ptr, size)))
goto out;
page = virt_to_page(ptr);
if (unlikely(!PageSlab(page)))
unsigned long node_frees = cachep->node_frees;
unsigned long overflows = cachep->node_overflow;
-- --- seq_printf(m, " : globalstat %7lu %6lu %5lu %4lu \
-- --- %4lu %4lu %4lu %4lu %4lu", allocs, high, grown,
-- --- reaped, errors, max_freeable, node_allocs,
-- --- node_frees, overflows);
++ +++ seq_printf(m, " : globalstat %7lu %6lu %5lu %4lu "
++ +++ "%4lu %4lu %4lu %4lu %4lu",
++ +++ allocs, high, grown,
++ +++ reaped, errors, max_freeable, node_allocs,
++ +++ node_frees, overflows);
}
/* cpu stats */
{
#define SLUB_MERGE_SAME (SLAB_DEBUG_FREE | SLAB_RECLAIM_ACCOUNT | \
SLAB_CACHE_DMA | SLAB_NOTRACK)
- ----#ifndef ARCH_KMALLOC_MINALIGN
- ----#define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long)
- ----#endif
- ----
- ----#ifndef ARCH_SLAB_MINALIGN
- ----#define ARCH_SLAB_MINALIGN __alignof__(unsigned long long)
- ----#endif
- ----
#define OO_SHIFT 16
#define OO_MASK ((1 << OO_SHIFT) - 1)
#define MAX_OBJS_PER_PAGE 65535 /* since page.objects is u16 */
if (node == -1)
return alloc_pages(flags, order);
else
----- return alloc_pages_node(node, flags, order);
+++++ return alloc_pages_exact_node(node, flags, order);
}
static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
int local_node;
if (slab_state >= UP && (s < kmalloc_caches ||
--- s > kmalloc_caches + KMALLOC_CACHES))
+++ s >= kmalloc_caches + KMALLOC_CACHES))
local_node = page_to_nid(virt_to_page(s));
else
local_node = 0;
{
struct page *page;
+ + if (!kern_ptr_validate(object, s->size))
+ + return 0;
+ +
page = get_object_page(object);
if (!page || s != page->slab)
#ifdef CONFIG_SLUB_DEBUG
void *addr = page_address(page);
void *p;
----- DECLARE_BITMAP(map, page->objects);
+++++ long *map = kzalloc(BITS_TO_LONGS(page->objects) * sizeof(long),
+++++ GFP_ATOMIC);
----- bitmap_zero(map, page->objects);
+++++ if (!map)
+++++ return;
slab_err(s, page, "%s", text);
slab_lock(page);
for_each_free_object(p, s, page->freelist)
}
}
slab_unlock(page);
+++++ kfree(map);
#endif
}
struct kmem_cache *s;
void *ret;
----- if (unlikely(size > SLUB_MAX_SIZE))
----- return kmalloc_large_node(size, gfpflags, node);
+++++ if (unlikely(size > SLUB_MAX_SIZE)) {
+++++ ret = kmalloc_large_node(size, gfpflags, node);
+++++
+++++ trace_kmalloc_node(caller, ret,
+++++ size, PAGE_SIZE << get_order(size),
+++++ gfpflags, node);
+++++
+++++ return ret;
+++++ }
s = get_slab(size, gfpflags);
}
static void process_slab(struct loc_track *t, struct kmem_cache *s,
----- struct page *page, enum track_item alloc)
+++++ struct page *page, enum track_item alloc,
+++++ long *map)
{
void *addr = page_address(page);
----- DECLARE_BITMAP(map, page->objects);
void *p;
bitmap_zero(map, page->objects);
unsigned long i;
struct loc_track t = { 0, 0, NULL };
int node;
+++++ unsigned long *map = kmalloc(BITS_TO_LONGS(oo_objects(s->max)) *
+++++ sizeof(unsigned long), GFP_KERNEL);
----- if (!alloc_loc_track(&t, PAGE_SIZE / sizeof(struct location),
----- GFP_TEMPORARY))
+++++ if (!map || !alloc_loc_track(&t, PAGE_SIZE / sizeof(struct location),
+++++ GFP_TEMPORARY)) {
+++++ kfree(map);
return sprintf(buf, "Out of memory\n");
-----
+++++ }
/* Push back cpu slabs */
flush_all(s);
spin_lock_irqsave(&n->list_lock, flags);
list_for_each_entry(page, &n->partial, lru)
----- process_slab(&t, s, page, alloc);
+++++ process_slab(&t, s, page, alloc, map);
list_for_each_entry(page, &n->full, lru)
----- process_slab(&t, s, page, alloc);
+++++ process_slab(&t, s, page, alloc, map);
spin_unlock_irqrestore(&n->list_lock, flags);
}
}
free_loc_track(&t);
+++++ kfree(map);
if (!t.count)
len += sprintf(buf, "No data\n");
return len;