* Further notes from the original documentation:
*
* 11 April '97. Started multi-threading - markhe
- * The global cache-chain is protected by the mutex 'cache_chain_mutex'.
+ * The global cache-chain is protected by the mutex 'slab_mutex'.
* The sem is only needed when accessing/extending the cache-chain, which
* can never happen inside an interrupt (kmem_cache_create(),
* kmem_cache_shrink() and kmem_cache_reap()).
#include <linux/memory.h>
#include <linux/prefetch.h>
+#include <net/sock.h>
+
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
#include <asm/page.h>
#include <trace/events/kmem.h>
+#include "internal.h"
+
/*
* DEBUG - 1 for kmem_cache_create() to honour; SLAB_RED_ZONE & SLAB_POISON.
* 0 for faster, smaller code (especially in the critical paths).
#define ARCH_KMALLOC_FLAGS SLAB_HWCACHE_ALIGN
#endif
+/*
+ * true if a page was allocated from pfmemalloc reserves for network-based
+ * swap
+ */
+static bool pfmemalloc_active __read_mostly;
+
/* Legal flag mask for kmem_cache_create(). */
#if DEBUG
# define CREATE_MASK (SLAB_RED_ZONE | \
* Must have this definition in here for the proper
* alignment of array_cache. Also simplifies accessing
* the entries.
+ *
+ * Entries should not be directly dereferenced as
+ * entries belonging to slabs marked pfmemalloc will
+ * have the lower bits set SLAB_OBJ_PFMEMALLOC
*/
};
+#define SLAB_OBJ_PFMEMALLOC 1
+static inline bool is_obj_pfmemalloc(void *objp)
+{
+ return (unsigned long)objp & SLAB_OBJ_PFMEMALLOC;
+}
+
+static inline void set_obj_pfmemalloc(void **objp)
+{
+ *objp = (void *)((unsigned long)*objp | SLAB_OBJ_PFMEMALLOC);
+ return;
+}
+
+static inline void clear_obj_pfmemalloc(void **objp)
+{
+ *objp = (void *)((unsigned long)*objp & ~SLAB_OBJ_PFMEMALLOC);
+}
+
/*
* bootstrap: The caches do not work without cpuarrays anymore, but the
* cpuarrays are allocated from the generic caches...
}
#endif
-/*
- * Guard access to the cache-chain.
- */
-static DEFINE_MUTEX(cache_chain_mutex);
-static struct list_head cache_chain;
-
static DEFINE_PER_CPU(struct delayed_work, slab_reap_work);
static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep)
return nc;
}
+static inline bool is_slab_pfmemalloc(struct slab *slabp)
+{
+ struct page *page = virt_to_page(slabp->s_mem);
+
+ return PageSlabPfmemalloc(page);
+}
+
+/* Clears pfmemalloc_active if no slabs have pfmalloc set */
+static void recheck_pfmemalloc_active(struct kmem_cache *cachep,
+ struct array_cache *ac)
+{
+ struct kmem_list3 *l3 = cachep->nodelists[numa_mem_id()];
+ struct slab *slabp;
+ unsigned long flags;
+
+ if (!pfmemalloc_active)
+ return;
+
+ spin_lock_irqsave(&l3->list_lock, flags);
+ list_for_each_entry(slabp, &l3->slabs_full, list)
+ if (is_slab_pfmemalloc(slabp))
+ goto out;
+
+ list_for_each_entry(slabp, &l3->slabs_partial, list)
+ if (is_slab_pfmemalloc(slabp))
+ goto out;
+
+ list_for_each_entry(slabp, &l3->slabs_free, list)
+ if (is_slab_pfmemalloc(slabp))
+ goto out;
+
+ pfmemalloc_active = false;
+out:
+ spin_unlock_irqrestore(&l3->list_lock, flags);
+}
+
+static void *__ac_get_obj(struct kmem_cache *cachep, struct array_cache *ac,
+ gfp_t flags, bool force_refill)
+{
+ int i;
+ void *objp = ac->entry[--ac->avail];
+
+ /* Ensure the caller is allowed to use objects from PFMEMALLOC slab */
+ if (unlikely(is_obj_pfmemalloc(objp))) {
+ struct kmem_list3 *l3;
+
+ if (gfp_pfmemalloc_allowed(flags)) {
+ clear_obj_pfmemalloc(&objp);
+ return objp;
+ }
+
+ /* The caller cannot use PFMEMALLOC objects, find another one */
+ for (i = 0; i < ac->avail; i++) {
+ /* If a !PFMEMALLOC object is found, swap them */
+ if (!is_obj_pfmemalloc(ac->entry[i])) {
+ objp = ac->entry[i];
+ ac->entry[i] = ac->entry[ac->avail];
+ ac->entry[ac->avail] = objp;
+ return objp;
+ }
+ }
+
+ /*
+ * If there are empty slabs on the slabs_free list and we are
+ * being forced to refill the cache, mark this one !pfmemalloc.
+ */
+ l3 = cachep->nodelists[numa_mem_id()];
+ if (!list_empty(&l3->slabs_free) && force_refill) {
+ struct slab *slabp = virt_to_slab(objp);
+ ClearPageSlabPfmemalloc(virt_to_head_page(slabp->s_mem));
+ clear_obj_pfmemalloc(&objp);
+ recheck_pfmemalloc_active(cachep, ac);
+ return objp;
+ }
+
+ /* No !PFMEMALLOC objects available */
+ ac->avail++;
+ objp = NULL;
+ }
+
+ return objp;
+}
+
+static inline void *ac_get_obj(struct kmem_cache *cachep,
+ struct array_cache *ac, gfp_t flags, bool force_refill)
+{
+ void *objp;
+
+ if (unlikely(sk_memalloc_socks()))
+ objp = __ac_get_obj(cachep, ac, flags, force_refill);
+ else
+ objp = ac->entry[--ac->avail];
+
+ return objp;
+}
+
+static void *__ac_put_obj(struct kmem_cache *cachep, struct array_cache *ac,
+ void *objp)
+{
+ if (unlikely(pfmemalloc_active)) {
+ /* Some pfmemalloc slabs exist, check if this is one */
+ struct page *page = virt_to_head_page(objp);
+ if (PageSlabPfmemalloc(page))
+ set_obj_pfmemalloc(&objp);
+ }
+
+ return objp;
+}
+
+static inline void ac_put_obj(struct kmem_cache *cachep, struct array_cache *ac,
+ void *objp)
+{
+ if (unlikely(sk_memalloc_socks()))
+ objp = __ac_put_obj(cachep, ac, objp);
+
+ ac->entry[ac->avail++] = objp;
+}
+
/*
* Transfer objects in one arraycache to another.
* Locking must be handled by the caller.
STATS_INC_ACOVERFLOW(cachep);
__drain_alien_cache(cachep, alien, nodeid);
}
- alien->entry[alien->avail++] = objp;
+ ac_put_obj(cachep, alien, objp);
spin_unlock(&alien->lock);
} else {
spin_lock(&(cachep->nodelists[nodeid])->list_lock);
* When hotplugging memory or a cpu, existing nodelists are not replaced if
* already in use.
*
- * Must hold cache_chain_mutex.
+ * Must hold slab_mutex.
*/
static int init_cache_nodelists_node(int node)
{
struct kmem_list3 *l3;
const int memsize = sizeof(struct kmem_list3);
- list_for_each_entry(cachep, &cache_chain, list) {
+ list_for_each_entry(cachep, &slab_caches, list) {
/*
* Set up the size64 kmemlist for cpu before we can
* begin anything. Make sure some other cpu on this
/*
* The l3s don't come and go as CPUs come and
- * go. cache_chain_mutex is sufficient
+ * go. slab_mutex is sufficient
* protection here.
*/
cachep->nodelists[node] = l3;
int node = cpu_to_mem(cpu);
const struct cpumask *mask = cpumask_of_node(node);
- list_for_each_entry(cachep, &cache_chain, list) {
+ list_for_each_entry(cachep, &slab_caches, list) {
struct array_cache *nc;
struct array_cache *shared;
struct array_cache **alien;
* the respective cache's slabs, now we can go ahead and
* shrink each nodelist to its limit.
*/
- list_for_each_entry(cachep, &cache_chain, list) {
+ list_for_each_entry(cachep, &slab_caches, list) {
l3 = cachep->nodelists[node];
if (!l3)
continue;
* Now we can go ahead with allocating the shared arrays and
* array caches
*/
- list_for_each_entry(cachep, &cache_chain, list) {
+ list_for_each_entry(cachep, &slab_caches, list) {
struct array_cache *nc;
struct array_cache *shared = NULL;
struct array_cache **alien = NULL;
switch (action) {
case CPU_UP_PREPARE:
case CPU_UP_PREPARE_FROZEN:
- mutex_lock(&cache_chain_mutex);
+ mutex_lock(&slab_mutex);
err = cpuup_prepare(cpu);
- mutex_unlock(&cache_chain_mutex);
+ mutex_unlock(&slab_mutex);
break;
case CPU_ONLINE:
case CPU_ONLINE_FROZEN:
case CPU_DOWN_PREPARE:
case CPU_DOWN_PREPARE_FROZEN:
/*
- * Shutdown cache reaper. Note that the cache_chain_mutex is
+ * Shutdown cache reaper. Note that the slab_mutex is
* held so that if cache_reap() is invoked it cannot do
* anything expensive but will only modify reap_work
* and reschedule the timer.
#endif
case CPU_UP_CANCELED:
case CPU_UP_CANCELED_FROZEN:
- mutex_lock(&cache_chain_mutex);
+ mutex_lock(&slab_mutex);
cpuup_canceled(cpu);
- mutex_unlock(&cache_chain_mutex);
+ mutex_unlock(&slab_mutex);
break;
}
return notifier_from_errno(err);
* Returns -EBUSY if all objects cannot be drained so that the node is not
* removed.
*
- * Must hold cache_chain_mutex.
+ * Must hold slab_mutex.
*/
static int __meminit drain_cache_nodelists_node(int node)
{
struct kmem_cache *cachep;
int ret = 0;
- list_for_each_entry(cachep, &cache_chain, list) {
+ list_for_each_entry(cachep, &slab_caches, list) {
struct kmem_list3 *l3;
l3 = cachep->nodelists[node];
switch (action) {
case MEM_GOING_ONLINE:
- mutex_lock(&cache_chain_mutex);
+ mutex_lock(&slab_mutex);
ret = init_cache_nodelists_node(nid);
- mutex_unlock(&cache_chain_mutex);
+ mutex_unlock(&slab_mutex);
break;
case MEM_GOING_OFFLINE:
- mutex_lock(&cache_chain_mutex);
+ mutex_lock(&slab_mutex);
ret = drain_cache_nodelists_node(nid);
- mutex_unlock(&cache_chain_mutex);
+ mutex_unlock(&slab_mutex);
break;
case MEM_ONLINE:
case MEM_OFFLINE:
node = numa_mem_id();
/* 1) create the cache_cache */
- INIT_LIST_HEAD(&cache_chain);
- list_add(&cache_cache.list, &cache_chain);
+ INIT_LIST_HEAD(&slab_caches);
+ list_add(&cache_cache.list, &slab_caches);
cache_cache.colour_off = cache_line_size();
cache_cache.array[smp_processor_id()] = &initarray_cache.cache;
cache_cache.nodelists[node] = &initkmem_list3[CACHE_CACHE + node];
init_lock_keys();
/* 6) resize the head arrays to their final sizes */
- mutex_lock(&cache_chain_mutex);
- list_for_each_entry(cachep, &cache_chain, list)
+ mutex_lock(&slab_mutex);
+ list_for_each_entry(cachep, &slab_caches, list)
if (enable_cpucache(cachep, GFP_NOWAIT))
BUG();
- mutex_unlock(&cache_chain_mutex);
+ mutex_unlock(&slab_mutex);
/* Done! */
slab_state = FULL;
return NULL;
}
+ /* Record if ALLOC_NO_WATERMARKS was set when allocating the slab */
+ if (unlikely(page->pfmemalloc))
+ pfmemalloc_active = true;
+
nr_pages = (1 << cachep->gfporder);
if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
add_zone_page_state(page_zone(page),
else
add_zone_page_state(page_zone(page),
NR_SLAB_UNRECLAIMABLE, nr_pages);
- for (i = 0; i < nr_pages; i++)
+ for (i = 0; i < nr_pages; i++) {
__SetPageSlab(page + i);
+ if (page->pfmemalloc)
+ SetPageSlabPfmemalloc(page + i);
+ }
+
if (kmemcheck_enabled && !(cachep->flags & SLAB_NOTRACK)) {
kmemcheck_alloc_shadow(page, cachep->gfporder, flags, nodeid);
NR_SLAB_UNRECLAIMABLE, nr_freed);
while (i--) {
BUG_ON(!PageSlab(page));
+ __ClearPageSlabPfmemalloc(page);
__ClearPageSlab(page);
page++;
}
unsigned long flags, void (*ctor)(void *))
{
size_t left_over, slab_size, ralign;
- struct kmem_cache *cachep = NULL, *pc;
+ struct kmem_cache *cachep = NULL;
gfp_t gfp;
- /*
- * Sanity checks... these are all serious usage bugs.
- */
- if (!name || in_interrupt() || (size < BYTES_PER_WORD) ||
- size > KMALLOC_MAX_SIZE) {
- printk(KERN_ERR "%s: Early error in slab %s\n", __func__,
- name);
- BUG();
- }
-
- /*
- * We use cache_chain_mutex to ensure a consistent view of
- * cpu_online_mask as well. Please see cpuup_callback
- */
- if (slab_is_available()) {
- get_online_cpus();
- mutex_lock(&cache_chain_mutex);
- }
-
- list_for_each_entry(pc, &cache_chain, list) {
- char tmp;
- int res;
-
- /*
- * This happens when the module gets unloaded and doesn't
- * destroy its slab cache and no-one else reuses the vmalloc
- * area of the module. Print a warning.
- */
- res = probe_kernel_address(pc->name, tmp);
- if (res) {
- printk(KERN_ERR
- "SLAB: cache with size %d has lost its name\n",
- pc->size);
- continue;
- }
-
- if (!strcmp(pc->name, name)) {
- printk(KERN_ERR
- "kmem_cache_create: duplicate cache %s\n", name);
- dump_stack();
- goto oops;
- }
- }
-
#if DEBUG
- WARN_ON(strchr(name, ' ')); /* It confuses parsers */
#if FORCED_DEBUG
/*
* Enable redzoning and last user accounting, except for caches with
}
/* cache setup completed, link it into the list */
- list_add(&cachep->list, &cache_chain);
-oops:
- if (slab_is_available()) {
- mutex_unlock(&cache_chain_mutex);
- put_online_cpus();
- }
+ list_add(&cachep->list, &slab_caches);
return cachep;
}
return nr_freed;
}
-/* Called with cache_chain_mutex held to protect against cpu hotplug */
+/* Called with slab_mutex held to protect against cpu hotplug */
static int __cache_shrink(struct kmem_cache *cachep)
{
int ret = 0, i = 0;
BUG_ON(!cachep || in_interrupt());
get_online_cpus();
- mutex_lock(&cache_chain_mutex);
+ mutex_lock(&slab_mutex);
ret = __cache_shrink(cachep);
- mutex_unlock(&cache_chain_mutex);
+ mutex_unlock(&slab_mutex);
put_online_cpus();
return ret;
}
/* Find the cache in the chain of caches. */
get_online_cpus();
- mutex_lock(&cache_chain_mutex);
+ mutex_lock(&slab_mutex);
/*
* the chain is never empty, cache_cache is never destroyed
*/
list_del(&cachep->list);
if (__cache_shrink(cachep)) {
slab_error(cachep, "Can't free all objects");
- list_add(&cachep->list, &cache_chain);
- mutex_unlock(&cache_chain_mutex);
+ list_add(&cachep->list, &slab_caches);
+ mutex_unlock(&slab_mutex);
put_online_cpus();
return;
}
rcu_barrier();
__kmem_cache_destroy(cachep);
- mutex_unlock(&cache_chain_mutex);
+ mutex_unlock(&slab_mutex);
put_online_cpus();
}
EXPORT_SYMBOL(kmem_cache_destroy);
#define check_slabp(x,y) do { } while(0)
#endif
-static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags)
+static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags,
+ bool force_refill)
{
int batchcount;
struct kmem_list3 *l3;
struct array_cache *ac;
int node;
-retry:
check_irq_off();
node = numa_mem_id();
+ if (unlikely(force_refill))
+ goto force_grow;
+retry:
ac = cpu_cache_get(cachep);
batchcount = ac->batchcount;
if (!ac->touched && batchcount > BATCHREFILL_LIMIT) {
STATS_INC_ACTIVE(cachep);
STATS_SET_HIGH(cachep);
- ac->entry[ac->avail++] = slab_get_obj(cachep, slabp,
- node);
+ ac_put_obj(cachep, ac, slab_get_obj(cachep, slabp,
+ node));
}
check_slabp(cachep, slabp);
if (unlikely(!ac->avail)) {
int x;
+force_grow:
x = cache_grow(cachep, flags | GFP_THISNODE, node, NULL);
/* cache_grow can reenable interrupts, then ac could change. */
ac = cpu_cache_get(cachep);
- if (!x && ac->avail == 0) /* no objects in sight? abort */
+ node = numa_mem_id();
+
+ /* no objects in sight? abort */
+ if (!x && (ac->avail == 0 || force_refill))
return NULL;
if (!ac->avail) /* objects refilled by interrupt? */
goto retry;
}
ac->touched = 1;
- return ac->entry[--ac->avail];
+
+ return ac_get_obj(cachep, ac, flags, force_refill);
}
static inline void cache_alloc_debugcheck_before(struct kmem_cache *cachep,
{
void *objp;
struct array_cache *ac;
+ bool force_refill = false;
check_irq_off();
ac = cpu_cache_get(cachep);
if (likely(ac->avail)) {
- STATS_INC_ALLOCHIT(cachep);
ac->touched = 1;
- objp = ac->entry[--ac->avail];
- } else {
- STATS_INC_ALLOCMISS(cachep);
- objp = cache_alloc_refill(cachep, flags);
+ objp = ac_get_obj(cachep, ac, flags, false);
+
/*
- * the 'ac' may be updated by cache_alloc_refill(),
- * and kmemleak_erase() requires its correct value.
+ * Allow for the possibility all avail objects are not allowed
+ * by the current flags
*/
- ac = cpu_cache_get(cachep);
+ if (objp) {
+ STATS_INC_ALLOCHIT(cachep);
+ goto out;
+ }
+ force_refill = true;
}
+
+ STATS_INC_ALLOCMISS(cachep);
+ objp = cache_alloc_refill(cachep, flags, force_refill);
+ /*
+ * the 'ac' may be updated by cache_alloc_refill(),
+ * and kmemleak_erase() requires its correct value.
+ */
+ ac = cpu_cache_get(cachep);
+
+out:
/*
* To avoid a false negative, if an object that is in one of the
* per-CPU caches is leaked, we need to make sure kmemleak doesn't
struct kmem_list3 *l3;
for (i = 0; i < nr_objects; i++) {
- void *objp = objpp[i];
+ void *objp;
struct slab *slabp;
+ clear_obj_pfmemalloc(&objpp[i]);
+ objp = objpp[i];
+
slabp = virt_to_slab(objp);
l3 = cachep->nodelists[node];
list_del(&slabp->list);
cache_flusharray(cachep, ac);
}
- ac->entry[ac->avail++] = objp;
+ ac_put_obj(cachep, ac, objp);
}
/**
new->new[smp_processor_id()] = old;
}
-/* Always called with the cache_chain_mutex held */
+/* Always called with the slab_mutex held */
static int do_tune_cpucache(struct kmem_cache *cachep, int limit,
int batchcount, int shared, gfp_t gfp)
{
return alloc_kmemlist(cachep, gfp);
}
-/* Called with cache_chain_mutex held always */
+/* Called with slab_mutex held always */
static int enable_cpucache(struct kmem_cache *cachep, gfp_t gfp)
{
int err;
int node = numa_mem_id();
struct delayed_work *work = to_delayed_work(w);
- if (!mutex_trylock(&cache_chain_mutex))
+ if (!mutex_trylock(&slab_mutex))
/* Give up. Setup the next iteration. */
goto out;
- list_for_each_entry(searchp, &cache_chain, list) {
+ list_for_each_entry(searchp, &slab_caches, list) {
check_irq_on();
/*
cond_resched();
}
check_irq_on();
- mutex_unlock(&cache_chain_mutex);
+ mutex_unlock(&slab_mutex);
next_reap_node();
out:
/* Set up the next iteration */
{
loff_t n = *pos;
- mutex_lock(&cache_chain_mutex);
+ mutex_lock(&slab_mutex);
if (!n)
print_slabinfo_header(m);
- return seq_list_start(&cache_chain, *pos);
+ return seq_list_start(&slab_caches, *pos);
}
static void *s_next(struct seq_file *m, void *p, loff_t *pos)
{
- return seq_list_next(p, &cache_chain, pos);
+ return seq_list_next(p, &slab_caches, pos);
}
static void s_stop(struct seq_file *m, void *p)
{
- mutex_unlock(&cache_chain_mutex);
+ mutex_unlock(&slab_mutex);
}
static int s_show(struct seq_file *m, void *p)
return -EINVAL;
/* Find the cache in the chain of caches. */
- mutex_lock(&cache_chain_mutex);
+ mutex_lock(&slab_mutex);
res = -EINVAL;
- list_for_each_entry(cachep, &cache_chain, list) {
+ list_for_each_entry(cachep, &slab_caches, list) {
if (!strcmp(cachep->name, kbuf)) {
if (limit < 1 || batchcount < 1 ||
batchcount > limit || shared < 0) {
break;
}
}
- mutex_unlock(&cache_chain_mutex);
+ mutex_unlock(&slab_mutex);
if (res >= 0)
res = count;
return res;
static void *leaks_start(struct seq_file *m, loff_t *pos)
{
- mutex_lock(&cache_chain_mutex);
- return seq_list_start(&cache_chain, *pos);
+ mutex_lock(&slab_mutex);
+ return seq_list_start(&slab_caches, *pos);
}
static inline int add_caller(unsigned long *n, unsigned long v)
name = cachep->name;
if (n[0] == n[1]) {
/* Increase the buffer size */
- mutex_unlock(&cache_chain_mutex);
+ mutex_unlock(&slab_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);
+ mutex_lock(&slab_mutex);
return -ENOMEM;
}
*(unsigned long *)m->private = n[0] * 2;
kfree(n);
- mutex_lock(&cache_chain_mutex);
+ mutex_lock(&slab_mutex);
/* Now make sure this entry will be retried */
m->count = m->size;
return 0;