#include <linux/interrupt.h>
#include <linux/init.h>
#include <linux/compiler.h>
+#include <linux/cpuset.h>
#include <linux/seq_file.h>
#include <linux/notifier.h>
#include <linux/kallsyms.h>
SLAB_CACHE_DMA | \
SLAB_MUST_HWCACHE_ALIGN | SLAB_STORE_USER | \
SLAB_RECLAIM_ACCOUNT | SLAB_PANIC | \
- SLAB_DESTROY_BY_RCU)
+ SLAB_DESTROY_BY_RCU | SLAB_MEM_SPREAD)
#else
# define CREATE_MASK (SLAB_HWCACHE_ALIGN | \
SLAB_CACHE_DMA | SLAB_MUST_HWCACHE_ALIGN | \
SLAB_RECLAIM_ACCOUNT | SLAB_PANIC | \
- SLAB_DESTROY_BY_RCU)
+ SLAB_DESTROY_BY_RCU | SLAB_MEM_SPREAD)
#endif
/*
typedef unsigned int kmem_bufctl_t;
#define BUFCTL_END (((kmem_bufctl_t)(~0U))-0)
#define BUFCTL_FREE (((kmem_bufctl_t)(~0U))-1)
-#define SLAB_LIMIT (((kmem_bufctl_t)(~0U))-2)
+#define BUFCTL_ACTIVE (((kmem_bufctl_t)(~0U))-2)
+#define SLAB_LIMIT (((kmem_bufctl_t)(~0U))-3)
/* Max number of objs-per-slab for caches which use off-slab slabs.
* Needed to avoid a possible looping condition in cache_grow().
node = next_node(cpu_to_node(cpu), node_online_map);
if (node == MAX_NUMNODES)
- node = 0;
+ node = first_node(node_online_map);
__get_cpu_var(reap_node) = node;
}
return nc;
}
+/*
+ * Transfer objects in one arraycache to another.
+ * Locking must be handled by the caller.
+ *
+ * Return the number of entries transferred.
+ */
+static int transfer_objects(struct array_cache *to,
+ struct array_cache *from, unsigned int max)
+{
+ /* Figure out how many entries to transfer */
+ int nr = min(min(from->avail, max), to->limit - to->avail);
+
+ if (!nr)
+ return 0;
+
+ memcpy(to->entry + to->avail, from->entry + from->avail -nr,
+ sizeof(void *) *nr);
+
+ from->avail -= nr;
+ to->avail += nr;
+ to->touched = 1;
+ return nr;
+}
+
#ifdef CONFIG_NUMA
static void *__cache_alloc_node(struct kmem_cache *, gfp_t, int);
+static void *alternate_node_alloc(struct kmem_cache *, gfp_t);
static struct array_cache **alloc_alien_cache(int node, int limit)
{
if (ac->avail) {
spin_lock(&rl3->list_lock);
+ /*
+ * Stuff objects into the remote nodes shared array first.
+ * That way we could avoid the overhead of putting the objects
+ * into the free lists and getting them back later.
+ */
+ transfer_objects(rl3->shared, ac, ac->limit);
+
free_block(cachep, ac->entry, ac->avail, node);
ac->avail = 0;
spin_unlock(&rl3->list_lock);
if (l3->alien) {
struct array_cache *ac = l3->alien[node];
- if (ac && ac->avail) {
- spin_lock_irq(&ac->lock);
+
+ if (ac && ac->avail && spin_trylock_irq(&ac->lock)) {
__drain_alien_cache(cachep, ac, node);
spin_unlock_irq(&ac->lock);
}
if (cache_cache.num)
break;
}
- if (!cache_cache.num)
- BUG();
+ BUG_ON(!cache_cache.num);
cache_cache.gfporder = order;
cache_cache.colour = left_over / cache_cache.colour_off;
cache_cache.slab_size = ALIGN(cache_cache.num * sizeof(kmem_bufctl_t) +
* Always checks flags, a caller might be expecting debug support which
* isn't available.
*/
- if (flags & ~CREATE_MASK)
- BUG();
+ BUG_ON(flags & ~CREATE_MASK);
/*
* Check that size is in terms of words. This is needed to avoid
align = ralign;
/* Get cache's description obj. */
- cachep = kmem_cache_alloc(&cache_cache, SLAB_KERNEL);
+ cachep = kmem_cache_zalloc(&cache_cache, SLAB_KERNEL);
if (!cachep)
goto oops;
- memset(cachep, 0, sizeof(struct kmem_cache));
#if DEBUG
cachep->obj_size = size;
#define check_spinlock_acquired_node(x, y) do { } while(0)
#endif
-static void drain_array_locked(struct kmem_cache *cachep,
- struct array_cache *ac, int force, int node);
-
static void drain_array(struct kmem_cache *cachep, struct kmem_list3 *l3,
struct array_cache *ac,
int force, int node);
slabp = list_entry(l3->slabs_free.prev, struct slab, list);
#if DEBUG
- if (slabp->inuse)
- BUG();
+ BUG_ON(slabp->inuse);
#endif
list_del(&slabp->list);
*/
int kmem_cache_shrink(struct kmem_cache *cachep)
{
- if (!cachep || in_interrupt())
- BUG();
+ BUG_ON(!cachep || in_interrupt());
return __cache_shrink(cachep);
}
int i;
struct kmem_list3 *l3;
- if (!cachep || in_interrupt())
- BUG();
+ BUG_ON(!cachep || in_interrupt());
/* Don't let CPUs to come and go */
lock_cpu_hotplug();
/* Verify that the slab belongs to the intended node */
WARN_ON(slabp->nodeid != nodeid);
- if (slab_bufctl(slabp)[objnr] != BUFCTL_FREE) {
+ if (slab_bufctl(slabp)[objnr] + 1 <= SLAB_LIMIT + 1) {
printk(KERN_ERR "slab: double free detected in cache "
"'%s', objp %p\n", cachep->name, objp);
BUG();
* Be lazy and only check for valid flags here, keeping it out of the
* critical path in kmem_cache_alloc().
*/
- if (flags & ~(SLAB_DMA | SLAB_LEVEL_MASK | SLAB_NO_GROW))
- BUG();
+ BUG_ON(flags & ~(SLAB_DMA | SLAB_LEVEL_MASK | SLAB_NO_GROW));
if (flags & SLAB_NO_GROW)
return 0;
*/
cachep->dtor(objp + obj_offset(cachep), cachep, 0);
}
+#ifdef CONFIG_DEBUG_SLAB_LEAK
+ slab_bufctl(slabp)[objnr] = BUFCTL_FREE;
+#endif
if (cachep->flags & SLAB_POISON) {
#ifdef CONFIG_DEBUG_PAGEALLOC
if ((cachep->buffer_size % PAGE_SIZE)==0 && OFF_SLAB(cachep)) {
BUG_ON(ac->avail > 0 || !l3);
spin_lock(&l3->list_lock);
- if (l3->shared) {
- struct array_cache *shared_array = l3->shared;
- if (shared_array->avail) {
- if (batchcount > shared_array->avail)
- batchcount = shared_array->avail;
- shared_array->avail -= batchcount;
- ac->avail = batchcount;
- memcpy(ac->entry,
- &(shared_array->entry[shared_array->avail]),
- sizeof(void *) * batchcount);
- shared_array->touched = 1;
- goto alloc_done;
- }
- }
+ /* See if we can refill from the shared array */
+ if (l3->shared && transfer_objects(ac, l3->shared, batchcount))
+ goto alloc_done;
+
while (batchcount > 0) {
struct list_head *entry;
struct slab *slabp;
*dbg_redzone1(cachep, objp) = RED_ACTIVE;
*dbg_redzone2(cachep, objp) = RED_ACTIVE;
}
+#ifdef CONFIG_DEBUG_SLAB_LEAK
+ {
+ struct slab *slabp;
+ unsigned objnr;
+
+ slabp = page_get_slab(virt_to_page(objp));
+ objnr = (unsigned)(objp - slabp->s_mem) / cachep->buffer_size;
+ slab_bufctl(slabp)[objnr] = BUFCTL_ACTIVE;
+ }
+#endif
objp += obj_offset(cachep);
if (cachep->ctor && cachep->flags & SLAB_POISON) {
unsigned long ctor_flags = SLAB_CTOR_CONSTRUCTOR;
struct array_cache *ac;
#ifdef CONFIG_NUMA
- if (unlikely(current->mempolicy && !in_interrupt())) {
- int nid = slab_node(current->mempolicy);
-
- if (nid != numa_node_id())
- return __cache_alloc_node(cachep, flags, nid);
+ if (unlikely(current->flags & (PF_SPREAD_SLAB | PF_MEMPOLICY))) {
+ objp = alternate_node_alloc(cachep, flags);
+ if (objp != NULL)
+ return objp;
}
#endif
}
#ifdef CONFIG_NUMA
+/*
+ * Try allocating on another node if PF_SPREAD_SLAB|PF_MEMPOLICY.
+ *
+ * If we are in_interrupt, then process context, including cpusets and
+ * mempolicy, may not apply and should not be used for allocation policy.
+ */
+static void *alternate_node_alloc(struct kmem_cache *cachep, gfp_t flags)
+{
+ int nid_alloc, nid_here;
+
+ if (in_interrupt())
+ return NULL;
+ nid_alloc = nid_here = numa_node_id();
+ if (cpuset_do_slab_mem_spread() && (cachep->flags & SLAB_MEM_SPREAD))
+ nid_alloc = cpuset_mem_spread_node();
+ else if (current->mempolicy)
+ nid_alloc = slab_node(current->mempolicy);
+ if (nid_alloc != nid_here)
+ return __cache_alloc_node(cachep, flags, nid_alloc);
+ return NULL;
+}
+
/*
* A interface to enable slab creation on nodeid
*/
}
EXPORT_SYMBOL(kmem_cache_alloc);
+/**
+ * kmem_cache_alloc - Allocate an object. The memory is set to zero.
+ * @cache: The cache to allocate from.
+ * @flags: See kmalloc().
+ *
+ * Allocate an object from this cache and set the allocated memory to zero.
+ * The flags are only relevant if the cache has no available objects.
+ */
+void *kmem_cache_zalloc(struct kmem_cache *cache, gfp_t flags)
+{
+ void *ret = __cache_alloc(cache, flags, __builtin_return_address(0));
+ if (ret)
+ memset(ret, 0, obj_size(cache));
+ return ret;
+}
+EXPORT_SYMBOL(kmem_cache_zalloc);
+
/**
* kmem_ptr_validate - check if an untrusted pointer might
* be a slab entry.
return __cache_alloc(cachep, flags, caller);
}
-#ifndef CONFIG_DEBUG_SLAB
void *__kmalloc(size_t size, gfp_t flags)
{
+#ifndef CONFIG_DEBUG_SLAB
return __do_kmalloc(size, flags, NULL);
+#else
+ return __do_kmalloc(size, flags, __builtin_return_address(0));
+#endif
}
EXPORT_SYMBOL(__kmalloc);
-#else
-
+#ifdef CONFIG_DEBUG_SLAB
void *__kmalloc_track_caller(size_t size, gfp_t flags, void *caller)
{
return __do_kmalloc(size, flags, caller);
}
EXPORT_SYMBOL(__kmalloc_track_caller);
-
#endif
#ifdef CONFIG_SMP
* and we have no way of figuring out how to fix the array
* that we have allocated then....
*/
- for_each_cpu(i) {
+ for_each_possible_cpu(i) {
int node = cpu_to_node(i);
if (node_online(node))
/*
* We allocate for all cpus so we cannot use for online cpu here.
*/
- for_each_cpu(i)
+ for_each_possible_cpu(i)
kfree(p->ptrs[i]);
kfree(p);
}
EXPORT_SYMBOL_GPL(kmem_cache_name);
/*
- * This initializes kmem_list3 for all nodes.
+ * This initializes kmem_list3 or resizes varioius caches for all nodes.
*/
static int alloc_kmemlist(struct kmem_cache *cachep)
{
int node;
struct kmem_list3 *l3;
- int err = 0;
+ struct array_cache *new_shared;
+ struct array_cache **new_alien;
for_each_online_node(node) {
- struct array_cache *nc = NULL, *new;
- struct array_cache **new_alien = NULL;
-#ifdef CONFIG_NUMA
+
new_alien = alloc_alien_cache(node, cachep->limit);
if (!new_alien)
goto fail;
-#endif
- new = alloc_arraycache(node, cachep->shared*cachep->batchcount,
+
+ new_shared = alloc_arraycache(node,
+ cachep->shared*cachep->batchcount,
0xbaadf00d);
- if (!new)
+ if (!new_shared) {
+ free_alien_cache(new_alien);
goto fail;
+ }
+
l3 = cachep->nodelists[node];
if (l3) {
+ struct array_cache *shared = l3->shared;
+
spin_lock_irq(&l3->list_lock);
- nc = cachep->nodelists[node]->shared;
- if (nc)
- free_block(cachep, nc->entry, nc->avail, node);
+ if (shared)
+ free_block(cachep, shared->entry,
+ shared->avail, node);
- l3->shared = new;
- if (!cachep->nodelists[node]->alien) {
+ l3->shared = new_shared;
+ if (!l3->alien) {
l3->alien = new_alien;
new_alien = NULL;
}
l3->free_limit = (1 + nr_cpus_node(node)) *
cachep->batchcount + cachep->num;
spin_unlock_irq(&l3->list_lock);
- kfree(nc);
+ kfree(shared);
free_alien_cache(new_alien);
continue;
}
l3 = kmalloc_node(sizeof(struct kmem_list3), GFP_KERNEL, node);
- if (!l3)
+ if (!l3) {
+ free_alien_cache(new_alien);
+ kfree(new_shared);
goto fail;
+ }
kmem_list3_init(l3);
l3->next_reap = jiffies + REAPTIMEOUT_LIST3 +
((unsigned long)cachep) % REAPTIMEOUT_LIST3;
- l3->shared = new;
+ l3->shared = new_shared;
l3->alien = new_alien;
l3->free_limit = (1 + nr_cpus_node(node)) *
cachep->batchcount + cachep->num;
cachep->nodelists[node] = l3;
}
- return err;
+ return 0;
+
fail:
- err = -ENOMEM;
- return err;
+ if (!cachep->next.next) {
+ /* Cache is not active yet. Roll back what we did */
+ node--;
+ while (node >= 0) {
+ if (cachep->nodelists[node]) {
+ l3 = cachep->nodelists[node];
+
+ kfree(l3->shared);
+ free_alien_cache(l3->alien);
+ kfree(l3);
+ cachep->nodelists[node] = NULL;
+ }
+ node--;
+ }
+ }
+ return -ENOMEM;
}
struct ccupdate_struct {
cachep->name, -err);
}
-static void drain_array_locked(struct kmem_cache *cachep,
- struct array_cache *ac, int force, int node)
-{
- int tofree;
-
- check_spinlock_acquired_node(cachep, node);
- if (ac->touched && !force) {
- ac->touched = 0;
- } else if (ac->avail) {
- tofree = force ? ac->avail : (ac->limit + 4) / 5;
- if (tofree > ac->avail)
- tofree = (ac->avail + 1) / 2;
- free_block(cachep, ac->entry, tofree, node);
- ac->avail -= tofree;
- memmove(ac->entry, &(ac->entry[tofree]),
- sizeof(void *) * ac->avail);
- }
-}
-
-
/*
* Drain an array if it contains any elements taking the l3 lock only if
- * necessary.
+ * necessary. Note that the l3 listlock also protects the array_cache
+ * if drain_array() is used on the shared array.
*/
-static void drain_array(struct kmem_cache *searchp, struct kmem_list3 *l3,
+void drain_array(struct kmem_cache *cachep, struct kmem_list3 *l3,
struct array_cache *ac, int force, int node)
{
- if (ac && ac->avail) {
+ int tofree;
+
+ if (!ac || !ac->avail)
+ return;
+ if (ac->touched && !force) {
+ ac->touched = 0;
+ } else {
spin_lock_irq(&l3->list_lock);
- drain_array_locked(searchp, ac, force, node);
+ if (ac->avail) {
+ tofree = force ? ac->avail : (ac->limit + 4) / 5;
+ if (tofree > ac->avail)
+ tofree = (ac->avail + 1) / 2;
+ free_block(cachep, ac->entry, tofree, node);
+ ac->avail -= tofree;
+ memmove(ac->entry, &(ac->entry[tofree]),
+ sizeof(void *) * ac->avail);
+ }
spin_unlock_irq(&l3->list_lock);
}
}
res = count;
return res;
}
+
+#ifdef CONFIG_DEBUG_SLAB_LEAK
+
+static void *leaks_start(struct seq_file *m, loff_t *pos)
+{
+ loff_t n = *pos;
+ struct list_head *p;
+
+ mutex_lock(&cache_chain_mutex);
+ p = cache_chain.next;
+ while (n--) {
+ p = p->next;
+ if (p == &cache_chain)
+ return NULL;
+ }
+ return list_entry(p, struct kmem_cache, next);
+}
+
+static inline int add_caller(unsigned long *n, unsigned long v)
+{
+ unsigned long *p;
+ int l;
+ if (!v)
+ return 1;
+ l = n[1];
+ p = n + 2;
+ while (l) {
+ int i = l/2;
+ unsigned long *q = p + 2 * i;
+ if (*q == v) {
+ q[1]++;
+ return 1;
+ }
+ if (*q > v) {
+ l = i;
+ } else {
+ p = q + 2;
+ l -= i + 1;
+ }
+ }
+ if (++n[1] == n[0])
+ return 0;
+ memmove(p + 2, p, n[1] * 2 * sizeof(unsigned long) - ((void *)p - (void *)n));
+ p[0] = v;
+ p[1] = 1;
+ return 1;
+}
+
+static void handle_slab(unsigned long *n, struct kmem_cache *c, struct slab *s)
+{
+ void *p;
+ int i;
+ if (n[0] == n[1])
+ return;
+ for (i = 0, p = s->s_mem; i < c->num; i++, p += c->buffer_size) {
+ if (slab_bufctl(s)[i] != BUFCTL_ACTIVE)
+ continue;
+ if (!add_caller(n, (unsigned long)*dbg_userword(c, p)))
+ return;
+ }
+}
+
+static void show_symbol(struct seq_file *m, unsigned long address)
+{
+#ifdef CONFIG_KALLSYMS
+ char *modname;
+ const char *name;
+ unsigned long offset, size;
+ char namebuf[KSYM_NAME_LEN+1];
+
+ name = kallsyms_lookup(address, &size, &offset, &modname, namebuf);
+
+ if (name) {
+ seq_printf(m, "%s+%#lx/%#lx", name, offset, size);
+ if (modname)
+ seq_printf(m, " [%s]", modname);
+ return;
+ }
+#endif
+ seq_printf(m, "%p", (void *)address);
+}
+
+static int leaks_show(struct seq_file *m, void *p)
+{
+ struct kmem_cache *cachep = p;
+ struct list_head *q;
+ struct slab *slabp;
+ struct kmem_list3 *l3;
+ const char *name;
+ unsigned long *n = m->private;
+ int node;
+ int i;
+
+ if (!(cachep->flags & SLAB_STORE_USER))
+ return 0;
+ if (!(cachep->flags & SLAB_RED_ZONE))
+ return 0;
+
+ /* OK, we can do it */
+
+ n[1] = 0;
+
+ for_each_online_node(node) {
+ l3 = cachep->nodelists[node];
+ if (!l3)
+ continue;
+
+ check_irq_on();
+ spin_lock_irq(&l3->list_lock);
+
+ list_for_each(q, &l3->slabs_full) {
+ slabp = list_entry(q, struct slab, list);
+ handle_slab(n, cachep, slabp);
+ }
+ list_for_each(q, &l3->slabs_partial) {
+ slabp = list_entry(q, struct slab, list);
+ handle_slab(n, cachep, slabp);
+ }
+ spin_unlock_irq(&l3->list_lock);
+ }
+ name = cachep->name;
+ if (n[0] == n[1]) {
+ /* Increase the buffer size */
+ mutex_unlock(&cache_chain_mutex);
+ m->private = kzalloc(n[0] * 4 * sizeof(unsigned long), GFP_KERNEL);
+ if (!m->private) {
+ /* Too bad, we are really out */
+ m->private = n;
+ mutex_lock(&cache_chain_mutex);
+ return -ENOMEM;
+ }
+ *(unsigned long *)m->private = n[0] * 2;
+ kfree(n);
+ mutex_lock(&cache_chain_mutex);
+ /* Now make sure this entry will be retried */
+ m->count = m->size;
+ return 0;
+ }
+ for (i = 0; i < n[1]; i++) {
+ seq_printf(m, "%s: %lu ", name, n[2*i+3]);
+ show_symbol(m, n[2*i+2]);
+ seq_putc(m, '\n');
+ }
+ return 0;
+}
+
+struct seq_operations slabstats_op = {
+ .start = leaks_start,
+ .next = s_next,
+ .stop = s_stop,
+ .show = leaks_show,
+};
+#endif
#endif
/**