/*
* Release an obj back to its cache. If the obj has a constructed state, it must
* be in this state _before_ it is released. Called with disabled ints.
*/
static inline void __cache_free(struct kmem_cache *cachep, void *objp,
unsigned long caller)
{
struct array_cache *ac = cpu_cache_get(cachep);
check_irq_off();
kmemleak_free_recursive(objp, cachep->flags);
objp = cache_free_debugcheck(cachep, objp, caller);
kmemcheck_slab_free(cachep, objp, cachep->object_size);
/*
* Skip calling cache_free_alien() when the platform is not numa.
* This will avoid cache misses that happen while accessing slabp (which
* is per page memory reference) to get nodeid. Instead use a global
* variable to skip the call, which is mostly likely to be present in
* the cache.
*/
if (nr_online_nodes > 1 && cache_free_alien(cachep, objp))
return;
if (ac->avail < ac->limit) {
STATS_INC_FREEHIT(cachep);
} else {
STATS_INC_FREEMISS(cachep);
cache_flusharray(cachep, ac);
}
ac_put_obj(cachep, ac, objp);
}
/**
* kmem_cache_alloc - Allocate an object
* @cachep: The cache to allocate from.
* @flags: See kmalloc().
*
* Allocate an object from this cache. The flags are only relevant
* if the cache has no available objects.
*/
void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags)
{
void *ret = slab_alloc(cachep, flags, _RET_IP_);
trace_kmem_cache_alloc(_RET_IP_, ret,
cachep->object_size, cachep->size, flags);
return ret;
}
EXPORT_SYMBOL(kmem_cache_alloc);
#ifdef CONFIG_TRACING
void *
kmem_cache_alloc_trace(struct kmem_cache *cachep, gfp_t flags, size_t size)
{
void *ret;
ret = slab_alloc(cachep, flags, _RET_IP_);
trace_kmalloc(_RET_IP_, ret,
size, cachep->size, flags);
return ret;
}
EXPORT_SYMBOL(kmem_cache_alloc_trace);
#endif
#ifdef CONFIG_NUMA
/**
* kmem_cache_alloc_node - Allocate an object on the specified node
* @cachep: The cache to allocate from.
* @flags: See kmalloc().
* @nodeid: node number of the target node.
*
* Identical to kmem_cache_alloc but it will allocate memory on the given
* node, which can improve the performance for cpu bound structures.
*
* Fallback to other node is possible if __GFP_THISNODE is not set.
*/
void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid)
{
void *ret = slab_alloc_node(cachep, flags, nodeid, _RET_IP_);
trace_kmem_cache_alloc_node(_RET_IP_, ret,
cachep->object_size, cachep->size,
flags, nodeid);
return ret;
}
EXPORT_SYMBOL(kmem_cache_alloc_node);
#ifdef CONFIG_TRACING
void *kmem_cache_alloc_node_trace(struct kmem_cache *cachep,
gfp_t flags,
int nodeid,
size_t size)
{
void *ret;
ret = slab_alloc_node(cachep, flags, nodeid, _RET_IP_);
trace_kmalloc_node(_RET_IP_, ret,
size, cachep->size,
flags, nodeid);
return ret;
}
EXPORT_SYMBOL(kmem_cache_alloc_node_trace);
#endif
static __always_inline void *
__do_kmalloc_node(size_t size, gfp_t flags, int node, unsigned long caller)
{
struct kmem_cache *cachep;
cachep = kmalloc_slab(size, flags);
if (unlikely(ZERO_OR_NULL_PTR(cachep)))
return cachep;
return kmem_cache_alloc_node_trace(cachep, flags, node, size);
}
void *__kmalloc_node(size_t size, gfp_t flags, int node)
{
return __do_kmalloc_node(size, flags, node, _RET_IP_);
}
EXPORT_SYMBOL(__kmalloc_node);
void *__kmalloc_node_track_caller(size_t size, gfp_t flags,
int node, unsigned long caller)
{
return __do_kmalloc_node(size, flags, node, caller);
}
EXPORT_SYMBOL(__kmalloc_node_track_caller);
#endif /* CONFIG_NUMA */
/**
* __do_kmalloc - allocate memory
* @size: how many bytes of memory are required.
* @flags: the type of memory to allocate (see kmalloc).
* @caller: function caller for debug tracking of the caller
*/
static __always_inline void *__do_kmalloc(size_t size, gfp_t flags,
unsigned long caller)
{
struct kmem_cache *cachep;
void *ret;
cachep = kmalloc_slab(size, flags);
if (unlikely(ZERO_OR_NULL_PTR(cachep)))
return cachep;
ret = slab_alloc(cachep, flags, caller);
trace_kmalloc(caller, ret,
size, cachep->size, flags);
return ret;
}
void *__kmalloc(size_t size, gfp_t flags)
{
return __do_kmalloc(size, flags, _RET_IP_);
}
EXPORT_SYMBOL(__kmalloc);
void *__kmalloc_track_caller(size_t size, gfp_t flags, unsigned long caller)
{
return __do_kmalloc(size, flags, caller);
}
EXPORT_SYMBOL(__kmalloc_track_caller);
/**
* kmem_cache_free - Deallocate an object
* @cachep: The cache the allocation was from.
* @objp: The previously allocated object.
*
* Free an object which was previously allocated from this
* cache.
*/
void kmem_cache_free(struct kmem_cache *cachep, void *objp)
{
unsigned long flags;
cachep = cache_from_obj(cachep, objp);
if (!cachep)
return;
local_irq_save(flags);
debug_check_no_locks_freed(objp, cachep->object_size);
if (!(cachep->flags & SLAB_DEBUG_OBJECTS))
debug_check_no_obj_freed(objp, cachep->object_size);
__cache_free(cachep, objp, _RET_IP_);
local_irq_restore(flags);
trace_kmem_cache_free(_RET_IP_, objp);
}
EXPORT_SYMBOL(kmem_cache_free);
/**
* kfree - free previously allocated memory
* @objp: pointer returned by kmalloc.
*
* If @objp is NULL, no operation is performed.
*
* Don't free memory not originally allocated by kmalloc()
* or you will run into trouble.
*/
void kfree(const void *objp)
{
struct kmem_cache *c;
unsigned long flags;
trace_kfree(_RET_IP_, objp);
if (unlikely(ZERO_OR_NULL_PTR(objp)))
return;
local_irq_save(flags);
kfree_debugcheck(objp);
c = virt_to_cache(objp);
debug_check_no_locks_freed(objp, c->object_size);
debug_check_no_obj_freed(objp, c->object_size);
__cache_free(c, (void *)objp, _RET_IP_);
local_irq_restore(flags);
}
EXPORT_SYMBOL(kfree);
/*
* This initializes kmem_cache_node or resizes various caches for all nodes.
*/
static int alloc_kmem_cache_node(struct kmem_cache *cachep, gfp_t gfp)
{
int node;
struct kmem_cache_node *n;
struct array_cache *new_shared;
struct alien_cache **new_alien = NULL;
for_each_online_node(node) {
if (use_alien_caches) {
new_alien = alloc_alien_cache(node, cachep->limit, gfp);
if (!new_alien)
goto fail;
}
new_shared = NULL;
if (cachep->shared) {
new_shared = alloc_arraycache(node,
cachep->shared*cachep->batchcount,
0xbaadf00d, gfp);
if (!new_shared) {
free_alien_cache(new_alien);
goto fail;
}
}
n = get_node(cachep, node);
if (n) {
struct array_cache *shared = n->shared;
LIST_HEAD(list);
spin_lock_irq(&n->list_lock);
if (shared)
free_block(cachep, shared->entry,
shared->avail, node, &list);
n->shared = new_shared;
if (!n->alien) {
n->alien = new_alien;
new_alien = NULL;
}
n->free_limit = (1 + nr_cpus_node(node)) *
cachep->batchcount + cachep->num;
spin_unlock_irq(&n->list_lock);
slabs_destroy(cachep, &list);
kfree(shared);
free_alien_cache(new_alien);
continue;
}
n = kmalloc_node(sizeof(struct kmem_cache_node), gfp, node);
if (!n) {
free_alien_cache(new_alien);
kfree(new_shared);
goto fail;
}
kmem_cache_node_init(n);
n->next_reap = jiffies + REAPTIMEOUT_NODE +
((unsigned long)cachep) % REAPTIMEOUT_NODE;
n->shared = new_shared;
n->alien = new_alien;
n->free_limit = (1 + nr_cpus_node(node)) *
cachep->batchcount + cachep->num;
cachep->node[node] = n;
}
return 0;
fail:
if (!cachep->list.next) {
/* Cache is not active yet. Roll back what we did */
node--;
while (node >= 0) {
n = get_node(cachep, node);
if (n) {
kfree(n->shared);
free_alien_cache(n->alien);
kfree(n);
cachep->node[node] = NULL;
}
node--;
}
}
return -ENOMEM;
}
/* 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)
{
struct array_cache __percpu *cpu_cache, *prev;
int cpu;
cpu_cache = alloc_kmem_cache_cpus(cachep, limit, batchcount);
if (!cpu_cache)
return -ENOMEM;
prev = cachep->cpu_cache;
cachep->cpu_cache = cpu_cache;
kick_all_cpus_sync();
check_irq_on();
cachep->batchcount = batchcount;
cachep->limit = limit;
cachep->shared = shared;
if (!prev)
goto alloc_node;
for_each_online_cpu(cpu) {
LIST_HEAD(list);
int node;
struct kmem_cache_node *n;
struct array_cache *ac = per_cpu_ptr(prev, cpu);
node = cpu_to_mem(cpu);
n = get_node(cachep, node);
spin_lock_irq(&n->list_lock);
free_block(cachep, ac->entry, ac->avail, node, &list);
spin_unlock_irq(&n->list_lock);
slabs_destroy(cachep, &list);
}
free_percpu(prev);
alloc_node:
return alloc_kmem_cache_node(cachep, gfp);
}
static int do_tune_cpucache(struct kmem_cache *cachep, int limit,
int batchcount, int shared, gfp_t gfp)
{
int ret;
struct kmem_cache *c;
ret = __do_tune_cpucache(cachep, limit, batchcount, shared, gfp);
if (slab_state < FULL)
return ret;
if ((ret < 0) || !is_root_cache(cachep))
return ret;
lockdep_assert_held(&slab_mutex);
for_each_memcg_cache(c, cachep) {
/* return value determined by the root cache only */
__do_tune_cpucache(c, limit, batchcount, shared, gfp);
}
return ret;
}
/* Called with slab_mutex held always */
static int enable_cpucache(struct kmem_cache *cachep, gfp_t gfp)
{
int err;
int limit = 0;
int shared = 0;
int batchcount = 0;
if (!is_root_cache(cachep)) {
struct kmem_cache *root = memcg_root_cache(cachep);
limit = root->limit;
shared = root->shared;
batchcount = root->batchcount;
}
if (limit && shared && batchcount)
goto skip_setup;
/*
* The head array serves three purposes:
* - create a LIFO ordering, i.e. return objects that are cache-warm
* - reduce the number of spinlock operations.
* - reduce the number of linked list operations on the slab and
* bufctl chains: array operations are cheaper.
* The numbers are guessed, we should auto-tune as described by
* Bonwick.
*/
if (cachep->size > 131072)
limit = 1;
else if (cachep->size > PAGE_SIZE)
limit = 8;
else if (cachep->size > 1024)
limit = 24;
else if (cachep->size > 256)
limit = 54;
else
limit = 120;
/*
* CPU bound tasks (e.g. network routing) can exhibit cpu bound
* allocation behaviour: Most allocs on one cpu, most free operations
* on another cpu. For these cases, an efficient object passing between
* cpus is necessary. This is provided by a shared array. The array
* replaces Bonwick's magazine layer.
* On uniprocessor, it's functionally equivalent (but less efficient)
* to a larger limit. Thus disabled by default.
*/
shared = 0;
if (cachep->size <= PAGE_SIZE && num_possible_cpus() > 1)
shared = 8;
#if DEBUG
/*
* With debugging enabled, large batchcount lead to excessively long
* periods with disabled local interrupts. Limit the batchcount
*/
if (limit > 32)
limit = 32;
#endif
batchcount = (limit + 1) / 2;
skip_setup:
err = do_tune_cpucache(cachep, limit, batchcount, shared, gfp);
if (err)
printk(KERN_ERR "enable_cpucache failed for %s, error %d.\n",
cachep->name, -err);
return err;
}
/*
* Drain an array if it contains any elements taking the node lock only if
* necessary. Note that the node listlock also protects the array_cache
* if drain_array() is used on the shared array.
*/
static void drain_array(struct kmem_cache *cachep, struct kmem_cache_node *n,
struct array_cache *ac, int force, int node)
{
LIST_HEAD(list);
int tofree;
if (!ac || !ac->avail)
return;
if (ac->touched && !force) {
ac->touched = 0;
} else {
spin_lock_irq(&n->list_lock);
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, &list);
ac->avail -= tofree;
memmove(ac->entry, &(ac->entry[tofree]),
sizeof(void *) * ac->avail);
}
spin_unlock_irq(&n->list_lock);
slabs_destroy(cachep, &list);
}
}
/**
* cache_reap - Reclaim memory from caches.
* @w: work descriptor
*
* Called from workqueue/eventd every few seconds.
* Purpose:
* - clear the per-cpu caches for this CPU.
* - return freeable pages to the main free memory pool.
*
* If we cannot acquire the cache chain mutex then just give up - we'll try
* again on the next iteration.
*/
static void cache_reap(struct work_struct *w)
{
struct kmem_cache *searchp;
struct kmem_cache_node *n;
int node = numa_mem_id();
struct delayed_work *work = to_delayed_work(w);
if (!mutex_trylock(&slab_mutex))
/* Give up. Setup the next iteration. */
goto out;
list_for_each_entry(searchp, &slab_caches, list) {
check_irq_on();
/*
* We only take the node lock if absolutely necessary and we
* have established with reasonable certainty that
* we can do some work if the lock was obtained.
*/
n = get_node(searchp, node);
reap_alien(searchp, n);
drain_array(searchp, n, cpu_cache_get(searchp), 0, node);
/*
* These are racy checks but it does not matter
* if we skip one check or scan twice.
*/
if (time_after(n->next_reap, jiffies))
goto next;
n->next_reap = jiffies + REAPTIMEOUT_NODE;
drain_array(searchp, n, n->shared, 0, node);
if (n->free_touched)
n->free_touched = 0;
else {
int freed;
freed = drain_freelist(searchp, n, (n->free_limit +
5 * searchp->num - 1) / (5 * searchp->num));
STATS_ADD_REAPED(searchp, freed);
}
next:
cond_resched();
}
check_irq_on();
mutex_unlock(&slab_mutex);
next_reap_node();
out:
/* Set up the next iteration */
schedule_delayed_work(work, round_jiffies_relative(REAPTIMEOUT_AC));
}
#ifdef CONFIG_SLABINFO
void get_slabinfo(struct kmem_cache *cachep, struct slabinfo *sinfo)
{
struct page *page;
unsigned long active_objs;
unsigned long num_objs;
unsigned long active_slabs = 0;
unsigned long num_slabs, free_objects = 0, shared_avail = 0;
const char *name;
char *error = NULL;
int node;
struct kmem_cache_node *n;
active_objs = 0;
num_slabs = 0;
for_each_kmem_cache_node(cachep, node, n) {
check_irq_on();
spin_lock_irq(&n->list_lock);
list_for_each_entry(page, &n->slabs_full, lru) {
if (page->active != cachep->num && !error)
error = "slabs_full accounting error";
active_objs += cachep->num;
active_slabs++;
}
list_for_each_entry(page, &n->slabs_partial, lru) {
if (page->active == cachep->num && !error)
error = "slabs_partial accounting error";
if (!page->active && !error)
error = "slabs_partial accounting error";
active_objs += page->active;
active_slabs++;
}
list_for_each_entry(page, &n->slabs_free, lru) {
if (page->active && !error)
error = "slabs_free accounting error";
num_slabs++;
}
free_objects += n->free_objects;
if (n->shared)
shared_avail += n->shared->avail;
spin_unlock_irq(&n->list_lock);
}
num_slabs += active_slabs;
num_objs = num_slabs * cachep->num;
if (num_objs - active_objs != free_objects && !error)
error = "free_objects accounting error";
name = cachep->name;
if (error)
printk(KERN_ERR "slab: cache %s error: %s\n", name, error);
sinfo->active_objs = active_objs;
sinfo->num_objs = num_objs;
sinfo->active_slabs = active_slabs;
sinfo->num_slabs = num_slabs;
sinfo->shared_avail = shared_avail;
sinfo->limit = cachep->limit;
sinfo->batchcount = cachep->batchcount;
sinfo->shared = cachep->shared;
sinfo->objects_per_slab = cachep->num;
sinfo->cache_order = cachep->gfporder;
}
void slabinfo_show_stats(struct seq_file *m, struct kmem_cache *cachep)
{
#if STATS
{ /* node stats */
unsigned long high = cachep->high_mark;
unsigned long allocs = cachep->num_allocations;
unsigned long grown = cachep->grown;
unsigned long reaped = cachep->reaped;
unsigned long errors = cachep->errors;
unsigned long max_freeable = cachep->max_freeable;
unsigned long node_allocs = cachep->node_allocs;
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);
}
/* cpu stats */
{
unsigned long allochit = atomic_read(&cachep->allochit);
unsigned long allocmiss = atomic_read(&cachep->allocmiss);
unsigned long freehit = atomic_read(&cachep->freehit);
unsigned long freemiss = atomic_read(&cachep->freemiss);
seq_printf(m, " : cpustat %6lu %6lu %6lu %6lu",
allochit, allocmiss, freehit, freemiss);
}
#endif
}
#define MAX_SLABINFO_WRITE 128
/**
* slabinfo_write - Tuning for the slab allocator
* @file: unused
* @buffer: user buffer
* @count: data length
* @ppos: unused
*/
ssize_t slabinfo_write(struct file *file, const char __user *buffer,
size_t count, loff_t *ppos)
{
char kbuf[MAX_SLABINFO_WRITE + 1], *tmp;
int limit, batchcount, shared, res;
struct kmem_cache *cachep;
if (count > MAX_SLABINFO_WRITE)
return -EINVAL;
if (copy_from_user(&kbuf, buffer, count))
return -EFAULT;
kbuf[MAX_SLABINFO_WRITE] = '\0';
tmp = strchr(kbuf, ' ');
if (!tmp)
return -EINVAL;
*tmp = '\0';
tmp++;
if (sscanf(tmp, " %d %d %d", &limit, &batchcount, &shared) != 3)
return -EINVAL;
/* Find the cache in the chain of caches. */
mutex_lock(&slab_mutex);
res = -EINVAL;
list_for_each_entry(cachep, &slab_caches, list) {
if (!strcmp(cachep->name, kbuf)) {
if (limit < 1 || batchcount < 1 ||
batchcount > limit || shared < 0) {
res = 0;
} else {
res = do_tune_cpucache(cachep, limit,
batchcount, shared,
GFP_KERNEL);
}
break;
}
}
mutex_unlock(&slab_mutex);
if (res >= 0)
res = count;
return res;
}
#ifdef CONFIG_DEBUG_SLAB_LEAK
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 page *page)
{
void *p;
int i;
if (n[0] == n[1])
return;
for (i = 0, p = page->s_mem; i < c->num; i++, p += c->size) {
if (get_obj_status(page, i) != OBJECT_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
unsigned long offset, size;
char modname[MODULE_NAME_LEN], name[KSYM_NAME_LEN];
if (lookup_symbol_attrs(address, &size, &offset, modname, name) == 0) {
seq_printf(m, "%s+%#lx/%#lx", name, offset, size);
if (modname[0])
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 = list_entry(p, struct kmem_cache, list);
struct page *page;
struct kmem_cache_node *n;
const char *name;
unsigned long *x = 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 */
x[1] = 0;
for_each_kmem_cache_node(cachep, node, n) {
check_irq_on();
spin_lock_irq(&n->list_lock);
list_for_each_entry(page, &n->slabs_full, lru)
handle_slab(x, cachep, page);
list_for_each_entry(page, &n->slabs_partial, lru)
handle_slab(x, cachep, page);
spin_unlock_irq(&n->list_lock);
}
name = cachep->name;
if (x[0] == x[1]) {
/* Increase the buffer size */
mutex_unlock(&slab_mutex);
m->private = kzalloc(x[0] * 4 * sizeof(unsigned long), GFP_KERNEL);
if (!m->private) {
/* Too bad, we are really out */
m->private = x;
mutex_lock(&slab_mutex);
return -ENOMEM;
}
*(unsigned long *)m->private = x[0] * 2;
kfree(x);
mutex_lock(&slab_mutex);
/* Now make sure this entry will be retried */
m->count = m->size;
return 0;
}
for (i = 0; i < x[1]; i++) {
seq_printf(m, "%s: %lu ", name, x[2*i+3]);
show_symbol(m, x[2*i+2]);
seq_putc(m, '\n');
}
return 0;
}
static const struct seq_operations slabstats_op = {
.start = slab_start,
.next = slab_next,
.stop = slab_stop,
.show = leaks_show,
};
static int slabstats_open(struct inode *inode, struct file *file)
{
unsigned long *n;
n = __seq_open_private(file, &slabstats_op, PAGE_SIZE);
if (!n)
return -ENOMEM;
*n = PAGE_SIZE / (2 * sizeof(unsigned long));
return 0;
}
static const struct file_operations proc_slabstats_operations = {
.open = slabstats_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release_private,
};
#endif
static int __init slab_proc_init(void)
{
#ifdef CONFIG_DEBUG_SLAB_LEAK
proc_create("slab_allocators", 0, NULL, &proc_slabstats_operations);
#endif
return 0;
}
module_init(slab_proc_init);
#endif
/**
* ksize - get the actual amount of memory allocated for a given object
* @objp: Pointer to the object
*
* kmalloc may internally round up allocations and return more memory
* than requested. ksize() can be used to determine the actual amount of
* memory allocated. The caller may use this additional memory, even though
* a smaller amount of memory was initially specified with the kmalloc call.
* The caller must guarantee that objp points to a valid object previously
* allocated with either kmalloc() or kmem_cache_alloc(). The object
* must not be freed during the duration of the call.
*/
size_t ksize(const void *objp)
{
BUG_ON(!objp);
if (unlikely(objp == ZERO_SIZE_PTR))
return 0;
return virt_to_cache(objp)->object_size;
}
EXPORT_SYMBOL(ksize);
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\mm/slab.h
#ifndef MM_SLAB_H
#define MM_SLAB_H
/*
* Internal slab definitions
*/
#ifdef CONFIG_SLOB
/*
* Common fields provided in kmem_cache by all slab allocators
* This struct is either used directly by the allocator (SLOB)
* or the allocator must include definitions for all fields
* provided in kmem_cache_common in their definition of kmem_cache.
*
* Once we can do anonymous structs (C11 standard) we could put a
* anonymous struct definition in these allocators so that the
* separate allocations in the kmem_cache structure of SLAB and
* SLUB is no longer needed.
*/
struct kmem_cache {
unsigned int object_size;/* The original size of the object */
unsigned int size; /* The aligned/padded/added on size */
unsigned int align; /* Alignment as calculated */
unsigned long flags; /* Active flags on the slab */
const char *name; /* Slab name for sysfs */
int refcount; /* Use counter */
void (*ctor)(void *); /* Called on object slot creation */
struct list_head list; /* List of all slab caches on the system */
};
#endif /* CONFIG_SLOB */
#ifdef CONFIG_SLAB
#include <linux/slab_def.h>
#endif
#ifdef CONFIG_SLUB
#include <linux/slub_def.h>
#endif
#include <linux/memcontrol.h>
/*
* State of the slab allocator.
*
* This is used to describe the states of the allocator during bootup.
* Allocators use this to gradually bootstrap themselves. Most allocators
* have the problem that the structures used for managing slab caches are
* allocated from slab caches themselves.
*/
enum slab_state {
DOWN, /* No slab functionality yet */
PARTIAL, /* SLUB: kmem_cache_node available */
PARTIAL_NODE, /* SLAB: kmalloc size for node struct available */
UP, /* Slab caches usable but not all extras yet */
FULL /* Everything is working */
};
extern enum slab_state slab_state;
/* The slab cache mutex protects the management structures during changes */
extern struct mutex slab_mutex;
/* The list of all slab caches on the system */
extern struct list_head slab_caches;
/* The slab cache that manages slab cache information */
extern struct kmem_cache *kmem_cache;
unsigned long calculate_alignment(unsigned long flags,
unsigned long align, unsigned long size);
#ifndef CONFIG_SLOB
/* Kmalloc array related functions */
void setup_kmalloc_cache_index_table(void);
void create_kmalloc_caches(unsigned long);
/* Find the kmalloc slab corresponding for a certain size */
struct kmem_cache *kmalloc_slab(size_t, gfp_t);
#endif
/* Functions provided by the slab allocators */
extern int __kmem_cache_create(struct kmem_cache *, unsigned long flags);
extern struct kmem_cache *create_kmalloc_cache(const char *name, size_t size,
unsigned long flags);
extern void create_boot_cache(struct kmem_cache *, const char *name,
size_t size, unsigned long flags);
int slab_unmergeable(struct kmem_cache *s);
struct kmem_cache *find_mergeable(size_t size, size_t align,
unsigned long flags, const char *name, void (*ctor)(void *));
#ifndef CONFIG_SLOB
struct kmem_cache *
__kmem_cache_alias(const char *name, size_t size, size_t align,
unsigned long flags, void (*ctor)(void *));
unsigned long kmem_cache_flags(unsigned long object_size,
unsigned long flags, const char *name,
void (*ctor)(void *));
#else
static inline struct kmem_cache *
__kmem_cache_alias(const char *name, size_t size, size_t align,
unsigned long flags, void (*ctor)(void *))
{ return NULL; }
static inline unsigned long kmem_cache_flags(unsigned long object_size,
unsigned long flags, const char *name,
void (*ctor)(void *))
{
return flags;
}
#endif
/* Legal flag mask for kmem_cache_create(), for various configurations */
#define SLAB_CORE_FLAGS (SLAB_HWCACHE_ALIGN | SLAB_CACHE_DMA | SLAB_PANIC | \
SLAB_DESTROY_BY_RCU | SLAB_DEBUG_OBJECTS )
#if defined(CONFIG_DEBUG_SLAB)
#define SLAB_DEBUG_FLAGS (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER)
#elif defined(CONFIG_SLUB_DEBUG)
#define SLAB_DEBUG_FLAGS (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER | \
SLAB_TRACE | SLAB_DEBUG_FREE)
#else
#define SLAB_DEBUG_FLAGS (0)
#endif
#if defined(CONFIG_SLAB)
#define SLAB_CACHE_FLAGS (SLAB_MEM_SPREAD | SLAB_NOLEAKTRACE | \
SLAB_RECLAIM_ACCOUNT | SLAB_TEMPORARY | SLAB_NOTRACK)
#elif defined(CONFIG_SLUB)
#define SLAB_CACHE_FLAGS (SLAB_NOLEAKTRACE | SLAB_RECLAIM_ACCOUNT | \
SLAB_TEMPORARY | SLAB_NOTRACK)
#else
#define SLAB_CACHE_FLAGS (0)
#endif
#define CACHE_CREATE_MASK (SLAB_CORE_FLAGS | SLAB_DEBUG_FLAGS | SLAB_CACHE_FLAGS)
int __kmem_cache_shutdown(struct kmem_cache *);
int __kmem_cache_shrink(struct kmem_cache *, bool);
void slab_kmem_cache_release(struct kmem_cache *);
struct seq_file;
struct file;
struct slabinfo {
unsigned long active_objs;
unsigned long num_objs;
unsigned long active_slabs;
unsigned long num_slabs;
unsigned long shared_avail;
unsigned int limit;
unsigned int batchcount;
unsigned int shared;
unsigned int objects_per_slab;
unsigned int cache_order;
};
void get_slabinfo(struct kmem_cache *s, struct slabinfo *sinfo);
void slabinfo_show_stats(struct seq_file *m, struct kmem_cache *s);
ssize_t slabinfo_write(struct file *file, const char __user *buffer,
size_t count, loff_t *ppos);
#ifdef CONFIG_MEMCG_KMEM
/*
* Iterate over all memcg caches of the given root cache. The caller must hold
* slab_mutex.
*/
#define for_each_memcg_cache(iter, root) \
list_for_each_entry(iter, &(root)->memcg_params.list, \
memcg_params.list)
#define for_each_memcg_cache_safe(iter, tmp, root) \
list_for_each_entry_safe(iter, tmp, &(root)->memcg_params.list, \
memcg_params.list)
static inline bool is_root_cache(struct kmem_cache *s)
{
return s->memcg_params.is_root_cache;
}
static inline bool slab_equal_or_root(struct kmem_cache *s,
struct kmem_cache *p)
{
return p == s || p == s->memcg_params.root_cache;
}
/*
* We use suffixes to the name in memcg because we can't have caches
* created in the system with the same name. But when we print them
* locally, better refer to them with the base name
*/
static inline const char *cache_name(struct kmem_cache *s)
{
if (!is_root_cache(s))
s = s->memcg_params.root_cache;
return s->name;
}
/*
* Note, we protect with RCU only the memcg_caches array, not per-memcg caches.
* That said the caller must assure the memcg's cache won't go away by either
* taking a css reference to the owner cgroup, or holding the slab_mutex.
*/
static inline struct kmem_cache *
cache_from_memcg_idx(struct kmem_cache *s, int idx)
{
struct kmem_cache *cachep;
struct memcg_cache_array *arr;
rcu_read_lock();
arr = rcu_dereference(s->memcg_params.memcg_caches);
/*
* Make sure we will access the up-to-date value. The code updating
* memcg_caches issues a write barrier to match this (see
* memcg_create_kmem_cache()).
*/
cachep = lockless_dereference(arr->entries[idx]);
rcu_read_unlock();
return cachep;
}
static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s)
{
if (is_root_cache(s))
return s;
return s->memcg_params.root_cache;
}
static __always_inline int memcg_charge_slab(struct kmem_cache *s,
gfp_t gfp, int order)
{
if (!memcg_kmem_enabled())
return 0;
if (is_root_cache(s))
return 0;
return memcg_charge_kmem(s->memcg_params.memcg, gfp, 1 << order);
}
static __always_inline void memcg_uncharge_slab(struct kmem_cache *s, int order)
{
if (!memcg_kmem_enabled())
return;
if (is_root_cache(s))
return;
memcg_uncharge_kmem(s->memcg_params.memcg, 1 << order);
}
extern void slab_init_memcg_params(struct kmem_cache *);
#else /* !CONFIG_MEMCG_KMEM */
#define for_each_memcg_cache(iter, root) \
for ((void)(iter), (void)(root); 0; )
#define for_each_memcg_cache_safe(iter, tmp, root) \
for ((void)(iter), (void)(tmp), (void)(root); 0; )
static inline bool is_root_cache(struct kmem_cache *s)
{
return true;
}
static inline bool slab_equal_or_root(struct kmem_cache *s,
struct kmem_cache *p)
{
return true;
}
static inline const char *cache_name(struct kmem_cache *s)
{
return s->name;
}
static inline struct kmem_cache *
cache_from_memcg_idx(struct kmem_cache *s, int idx)
{
return NULL;
}
static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s)
{
return s;
}
static inline int memcg_charge_slab(struct kmem_cache *s, gfp_t gfp, int order)
{
return 0;
}
static inline void memcg_uncharge_slab(struct kmem_cache *s, int order)
{
}
static inline void slab_init_memcg_params(struct kmem_cache *s)
{
}
#endif /* CONFIG_MEMCG_KMEM */
static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x)
{
struct kmem_cache *cachep;
struct page *page;
/*
* When kmemcg is not being used, both assignments should return the
* same value. but we don't want to pay the assignment price in that
* case. If it is not compiled in, the compiler should be smart enough
* to not do even the assignment. In that case, slab_equal_or_root
* will also be a constant.
*/
if (!memcg_kmem_enabled() && !unlikely(s->flags & SLAB_DEBUG_FREE))
return s;
page = virt_to_head_page(x);
cachep = page->slab_cache;
if (slab_equal_or_root(cachep, s))
return cachep;
pr_err("%s: Wrong slab cache. %s but object is from %s\n",
__func__, cachep->name, s->name);
WARN_ON_ONCE(1);
return s;
}
#ifndef CONFIG_SLOB
/*
* The slab lists for all objects.
*/
struct kmem_cache_node {
spinlock_t list_lock;
#ifdef CONFIG_SLAB
struct list_head slabs_partial; /* partial list first, better asm code */
struct list_head slabs_full;
struct list_head slabs_free;
unsigned long free_objects;
unsigned int free_limit;
unsigned int colour_next; /* Per-node cache coloring */
struct array_cache *shared; /* shared per node */
struct alien_cache **alien; /* on other nodes */
unsigned long next_reap; /* updated without locking */
int free_touched; /* updated without locking */
#endif
#ifdef CONFIG_SLUB
unsigned long nr_partial;
struct list_head partial;
#ifdef CONFIG_SLUB_DEBUG
atomic_long_t nr_slabs;
atomic_long_t total_objects;
struct list_head full;
#endif
#endif
};
static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node)
{
return s->node[node];
}
/*
* Iterator over all nodes. The body will be executed for each node that has
* a kmem_cache_node structure allocated (which is true for all online nodes)
*/
#define for_each_kmem_cache_node(__s, __node, __n) \
for (__node = 0; __node < nr_node_ids; __node++) \
if ((__n = get_node(__s, __node)))
#endif
void *slab_start(struct seq_file *m, loff_t *pos);
void *slab_next(struct seq_file *m, void *p, loff_t *pos);
void slab_stop(struct seq_file *m, void *p);
int memcg_slab_show(struct seq_file *m, void *p);
#endif /* MM_SLAB_H */
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\mm/slab_common.c
/*
* Slab allocator functions that are independent of the allocator strategy
*
* (C) 2012 Christoph Lameter <cl@linux.com>
*/
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/poison.h>
#include <linux/interrupt.h>
#include <linux/memory.h>
#include <linux/compiler.h>
#include <linux/module.h>
#include <linux/cpu.h>
#include <linux/uaccess.h>
#include <linux/seq_file.h>
#include <linux/proc_fs.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
#include <asm/page.h>
#include <linux/memcontrol.h>
#define CREATE_TRACE_POINTS
#include <trace/events/kmem.h>
#include "slab.h"
enum slab_state slab_state;
LIST_HEAD(slab_caches);
DEFINE_MUTEX(slab_mutex);
struct kmem_cache *kmem_cache;
/*
* Set of flags that will prevent slab merging
*/
#define SLAB_NEVER_MERGE (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER | \
SLAB_TRACE | SLAB_DESTROY_BY_RCU | SLAB_NOLEAKTRACE | \
SLAB_FAILSLAB)
#define SLAB_MERGE_SAME (SLAB_RECLAIM_ACCOUNT | SLAB_CACHE_DMA | SLAB_NOTRACK)
/*
* Merge control. If this is set then no merging of slab caches will occur.
* (Could be removed. This was introduced to pacify the merge skeptics.)
*/
static int slab_nomerge;
static int __init setup_slab_nomerge(char *str)
{
slab_nomerge = 1;
return 1;
}
#ifdef CONFIG_SLUB
__setup_param("slub_nomerge", slub_nomerge, setup_slab_nomerge, 0);
#endif
__setup("slab_nomerge", setup_slab_nomerge);
/*
* Determine the size of a slab object
*/
unsigned int kmem_cache_size(struct kmem_cache *s)
{
return s->object_size;
}
EXPORT_SYMBOL(kmem_cache_size);
#ifdef CONFIG_DEBUG_VM
static int kmem_cache_sanity_check(const char *name, size_t size)
{
struct kmem_cache *s = NULL;
if (!name || in_interrupt() || size < sizeof(void *) ||
size > KMALLOC_MAX_SIZE) {
pr_err("kmem_cache_create(%s) integrity check failed\n", name);
return -EINVAL;
}
list_for_each_entry(s, &slab_caches, 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(s->name, tmp);
if (res) {
pr_err("Slab cache with size %d has lost its name\n",
s->object_size);
continue;
}
}
WARN_ON(strchr(name, ' ')); /* It confuses parsers */
return 0;
}
#else
static inline int kmem_cache_sanity_check(const char *name, size_t size)
{
return 0;
}
#endif
#ifdef CONFIG_MEMCG_KMEM
void slab_init_memcg_params(struct kmem_cache *s)
{
s->memcg_params.is_root_cache = true;
INIT_LIST_HEAD(&s->memcg_params.list);
RCU_INIT_POINTER(s->memcg_params.memcg_caches, NULL);
}
static int init_memcg_params(struct kmem_cache *s,
struct mem_cgroup *memcg, struct kmem_cache *root_cache)
{
struct memcg_cache_array *arr;
if (memcg) {
s->memcg_params.is_root_cache = false;
s->memcg_params.memcg = memcg;
s->memcg_params.root_cache = root_cache;
return 0;
}
slab_init_memcg_params(s);
if (!memcg_nr_cache_ids)
return 0;
arr = kzalloc(sizeof(struct memcg_cache_array) +
memcg_nr_cache_ids * sizeof(void *),
GFP_KERNEL);
if (!arr)
return -ENOMEM;
RCU_INIT_POINTER(s->memcg_params.memcg_caches, arr);
return 0;
}
static void destroy_memcg_params(struct kmem_cache *s)
{
if (is_root_cache(s))
kfree(rcu_access_pointer(s->memcg_params.memcg_caches));
}
static int update_memcg_params(struct kmem_cache *s, int new_array_size)
{
struct memcg_cache_array *old, *new;
if (!is_root_cache(s))
return 0;
new = kzalloc(sizeof(struct memcg_cache_array) +
new_array_size * sizeof(void *), GFP_KERNEL);
if (!new)
return -ENOMEM;
old = rcu_dereference_protected(s->memcg_params.memcg_caches,
lockdep_is_held(&slab_mutex));
if (old)
memcpy(new->entries, old->entries,
memcg_nr_cache_ids * sizeof(void *));
rcu_assign_pointer(s->memcg_params.memcg_caches, new);
if (old)
kfree_rcu(old, rcu);
return 0;
}
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) {
ret = update_memcg_params(s, num_memcgs);
/*
* Instead of freeing the memory, we'll just leave the caches
* up to this point in an updated state.
*/
if (ret)
break;
}
mutex_unlock(&slab_mutex);
return ret;
}
#else
static inline int init_memcg_params(struct kmem_cache *s,
struct mem_cgroup *memcg, struct kmem_cache *root_cache)
{
return 0;
}
static inline void destroy_memcg_params(struct kmem_cache *s)
{
}
#endif /* CONFIG_MEMCG_KMEM */
/*
* Find a mergeable slab cache
*/
int slab_unmergeable(struct kmem_cache *s)
{
if (slab_nomerge || (s->flags & SLAB_NEVER_MERGE))
return 1;
if (!is_root_cache(s))
return 1;
if (s->ctor)
return 1;
/*
* We may have set a slab to be unmergeable during bootstrap.
*/
if (s->refcount < 0)
return 1;
return 0;
}
struct kmem_cache *find_mergeable(size_t size, size_t align,
unsigned long flags, const char *name, void (*ctor)(void *))
{
struct kmem_cache *s;
if (slab_nomerge || (flags & SLAB_NEVER_MERGE))
return NULL;
if (ctor)
return NULL;
size = ALIGN(size, sizeof(void *));
align = calculate_alignment(flags, align, size);
size = ALIGN(size, align);
flags = kmem_cache_flags(size, flags, name, NULL);
list_for_each_entry_reverse(s, &slab_caches, list) {
if (slab_unmergeable(s))
continue;
if (size > s->size)
continue;
if ((flags & SLAB_MERGE_SAME) != (s->flags & SLAB_MERGE_SAME))
continue;
/*
* Check if alignment is compatible.
* Courtesy of Adrian Drzewiecki
*/
if ((s->size & ~(align - 1)) != s->size)
continue;
if (s->size - size >= sizeof(void *))
continue;
if (IS_ENABLED(CONFIG_SLAB) && align &&
(align > s->align || s->align % align))
continue;
return s;
}
return NULL;
}
/*
* 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.
*/
unsigned long calculate_alignment(unsigned long flags,
unsigned long align, unsigned long size)
{
/*
* If the user wants hardware cache aligned objects then follow that
* suggestion if the object is sufficiently large.
*
* The hardware cache alignment cannot override the specified
* alignment though. If that is greater then use it.
*/
if (flags & SLAB_HWCACHE_ALIGN) {
unsigned long ralign = cache_line_size();
while (size <= ralign / 2)
ralign /= 2;
align = max(align, ralign);
}
if (align < ARCH_SLAB_MINALIGN)
align = ARCH_SLAB_MINALIGN;
return ALIGN(align, sizeof(void *));
}
static struct kmem_cache *
do_kmem_cache_create(const char *name, size_t object_size, size_t size,
size_t align, unsigned long flags, void (*ctor)(void *),
struct mem_cgroup *memcg, struct kmem_cache *root_cache)
{
struct kmem_cache *s;
int err;
err = -ENOMEM;
s = kmem_cache_zalloc(kmem_cache, GFP_KERNEL);
if (!s)
goto out;
s->name = name;
s->object_size = object_size;
s->size = size;
s->align = align;
s->ctor = ctor;
err = init_memcg_params(s, memcg, root_cache);
if (err)
goto out_free_cache;
err = __kmem_cache_create(s, flags);
if (err)
goto out_free_cache;
s->refcount = 1;
list_add(&s->list, &slab_caches);
out:
if (err)
return ERR_PTR(err);
return s;
out_free_cache:
destroy_memcg_params(s);
kmem_cache_free(kmem_cache, s);
goto out;
}
/*
* kmem_cache_create - Create a cache.
* @name: A string which is used in /proc/slabinfo to identify this cache.
* @size: The size of objects to be created in this cache.
* @align: The required alignment for the objects.
* @flags: SLAB flags
* @ctor: A constructor for the objects.
*
* Returns a ptr to the cache on success, NULL on failure.
* Cannot be called within a interrupt, but can be interrupted.
* The @ctor is run when new pages are allocated by the cache.
*
* The flags are
*
* %SLAB_POISON - Poison the slab with a known test pattern (a5a5a5a5)
* to catch references to uninitialised memory.
*
* %SLAB_RED_ZONE - Insert `Red' zones around the allocated memory to check
* for buffer overruns.
*
* %SLAB_HWCACHE_ALIGN - Align the objects in this cache to a hardware
* cacheline. This can be beneficial if you're counting cycles as closely
* 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 *s;
const char *cache_name;
int err;
get_online_cpus();
get_online_mems();
memcg_get_cache_ids();
mutex_lock(&slab_mutex);
err = kmem_cache_sanity_check(name, size);
if (err) {
s = NULL; /* suppress uninit var warning */
goto out_unlock;
}
/*
* Some allocators will constraint the set of valid flags to a subset
* of all flags. We expect them to define CACHE_CREATE_MASK in this
* case, and we'll just provide them with a sanitized version of the
* passed flags.
*/
flags &= CACHE_CREATE_MASK;
s = __kmem_cache_alias(name, size, align, flags, ctor);
if (s)
goto out_unlock;
cache_name = kstrdup_const(name, GFP_KERNEL);
if (!cache_name) {
err = -ENOMEM;
goto out_unlock;
}
s = do_kmem_cache_create(cache_name, size, size,
calculate_alignment(flags, align, size),
flags, ctor, NULL, NULL);
if (IS_ERR(s)) {
err = PTR_ERR(s);
kfree_const(cache_name);
}
out_unlock:
mutex_unlock(&slab_mutex);
memcg_put_cache_ids();
put_online_mems();
put_online_cpus();
if (err) {
if (flags & SLAB_PANIC)
panic("kmem_cache_create: Failed to create slab '%s'. Error %d\n",
name, err);
else {
printk(KERN_WARNING "kmem_cache_create(%s) failed with error %d",
name, err);
dump_stack();
}
return NULL;
}
return s;
}
EXPORT_SYMBOL(kmem_cache_create);
static int do_kmem_cache_shutdown(struct kmem_cache *s,
struct list_head *release, bool *need_rcu_barrier)
{
if (__kmem_cache_shutdown(s) != 0) {
printk(KERN_ERR "kmem_cache_destroy %s: "
"Slab cache still has objects\n", s->name);
dump_stack();
return -EBUSY;
}
if (s->flags & SLAB_DESTROY_BY_RCU)
*need_rcu_barrier = true;
#ifdef CONFIG_MEMCG_KMEM
if (!is_root_cache(s))
list_del(&s->memcg_params.list);
#endif
list_move(&s->list, release);
return 0;
}
static void do_kmem_cache_release(struct list_head *release,
bool need_rcu_barrier)
{
struct kmem_cache *s, *s2;
if (need_rcu_barrier)
rcu_barrier();
list_for_each_entry_safe(s, s2, release, list) {
#ifdef SLAB_SUPPORTS_SYSFS
sysfs_slab_remove(s);
#else
slab_kmem_cache_release(s);
#endif
}
}
#ifdef CONFIG_MEMCG_KMEM
/*
* memcg_create_kmem_cache - Create a cache for a memory cgroup.
* @memcg: The memory cgroup the new cache is for.
* @root_cache: The parent of the new cache.
*
* This function attempts to create a kmem cache that will serve allocation
* requests going from @memcg to @root_cache. The new cache inherits properties
* from its parent.
*/
void memcg_create_kmem_cache(struct mem_cgroup *memcg,
struct kmem_cache *root_cache)
{
static char memcg_name_buf[NAME_MAX + 1]; /* protected by slab_mutex */
struct cgroup_subsys_state *css = mem_cgroup_css(memcg);
struct memcg_cache_array *arr;
struct kmem_cache *s = NULL;
char *cache_name;
int idx;
get_online_cpus();
get_online_mems();
mutex_lock(&slab_mutex);
/*
* The memory cgroup could have been deactivated while the cache
* creation work was pending.
*/
if (!memcg_kmem_is_active(memcg))
goto out_unlock;
idx = memcg_cache_id(memcg);
arr = rcu_dereference_protected(root_cache->memcg_params.memcg_caches,
lockdep_is_held(&slab_mutex));
/*
* Since per-memcg caches are created asynchronously on first
* allocation (see memcg_kmem_get_cache()), several threads can try to
* create the same cache, but only one of them may succeed.
*/
if (arr->entries[idx])
goto out_unlock;
cgroup_name(css->cgroup, memcg_name_buf, sizeof(memcg_name_buf));
cache_name = kasprintf(GFP_KERNEL, "%s(%d:%s)", root_cache->name,
css->id, memcg_name_buf);
if (!cache_name)
goto out_unlock;
s = do_kmem_cache_create(cache_name, root_cache->object_size,
root_cache->size, root_cache->align,
root_cache->flags, root_cache->ctor,
memcg, root_cache);
/*
* If we could not create a memcg cache, do not complain, because
* that's not critical at all as we can always proceed with the root
* cache.
*/
if (IS_ERR(s)) {
kfree(cache_name);
goto out_unlock;
}
list_add(&s->memcg_params.list, &root_cache->memcg_params.list);
/*
* Since readers won't lock (see cache_from_memcg_idx()), we need a
* barrier here to ensure nobody will see the kmem_cache partially
* initialized.
*/
smp_wmb();
arr->entries[idx] = s;
out_unlock:
mutex_unlock(&slab_mutex);
put_online_mems();
put_online_cpus();
}
void memcg_deactivate_kmem_caches(struct mem_cgroup *memcg)
{
int idx;
struct memcg_cache_array *arr;
struct kmem_cache *s, *c;
idx = memcg_cache_id(memcg);
get_online_cpus();
get_online_mems();
mutex_lock(&slab_mutex);
list_for_each_entry(s, &slab_caches, list) {
if (!is_root_cache(s))
continue;
arr = rcu_dereference_protected(s->memcg_params.memcg_caches,
lockdep_is_held(&slab_mutex));
c = arr->entries[idx];
if (!c)
continue;
__kmem_cache_shrink(c, true);
arr->entries[idx] = NULL;
}
mutex_unlock(&slab_mutex);
put_online_mems();
put_online_cpus();
}
void memcg_destroy_kmem_caches(struct mem_cgroup *memcg)
{
LIST_HEAD(release);
bool need_rcu_barrier = false;
struct kmem_cache *s, *s2;
get_online_cpus();
get_online_mems();
mutex_lock(&slab_mutex);
list_for_each_entry_safe(s, s2, &slab_caches, list) {
if (is_root_cache(s) || s->memcg_params.memcg != memcg)
continue;
/*
* The cgroup is about to be freed and therefore has no charges
* left. Hence, all its caches must be empty by now.
*/
BUG_ON(do_kmem_cache_shutdown(s, &release, &need_rcu_barrier));
}
mutex_unlock(&slab_mutex);
put_online_mems();
put_online_cpus();
do_kmem_cache_release(&release, need_rcu_barrier);
}
#endif /* CONFIG_MEMCG_KMEM */
void slab_kmem_cache_release(struct kmem_cache *s)
{
destroy_memcg_params(s);
kfree_const(s->name);
kmem_cache_free(kmem_cache, s);
}
void kmem_cache_destroy(struct kmem_cache *s)
{
struct kmem_cache *c, *c2;
LIST_HEAD(release);
bool need_rcu_barrier = false;
bool busy = false;
BUG_ON(!is_root_cache(s));
get_online_cpus();
get_online_mems();
mutex_lock(&slab_mutex);
s->refcount--;
if (s->refcount)
goto out_unlock;
for_each_memcg_cache_safe(c, c2, s) {
if (do_kmem_cache_shutdown(c, &release, &need_rcu_barrier))
busy = true;
}
if (!busy)
do_kmem_cache_shutdown(s, &release, &need_rcu_barrier);
out_unlock:
mutex_unlock(&slab_mutex);
put_online_mems();
put_online_cpus();
do_kmem_cache_release(&release, need_rcu_barrier);
}
EXPORT_SYMBOL(kmem_cache_destroy);
/**
* kmem_cache_shrink - Shrink a cache.
* @cachep: The cache to shrink.
*
* Releases as many slabs as possible for a cache.
* To help debugging, a zero exit status indicates all slabs were released.
*/
int kmem_cache_shrink(struct kmem_cache *cachep)
{
int ret;
get_online_cpus();
get_online_mems();
ret = __kmem_cache_shrink(cachep, false);
put_online_mems();
put_online_cpus();
return ret;
}
EXPORT_SYMBOL(kmem_cache_shrink);
int slab_is_available(void)
{
return slab_state >= UP;
}
#ifndef CONFIG_SLOB
/* Create a cache during boot when no slab services are available yet */
void __init create_boot_cache(struct kmem_cache *s, const char *name, size_t size,
unsigned long flags)
{
int err;
s->name = name;
s->size = s->object_size = size;
s->align = calculate_alignment(flags, ARCH_KMALLOC_MINALIGN, size);
slab_init_memcg_params(s);
err = __kmem_cache_create(s, flags);
if (err)
panic("Creation of kmalloc slab %s size=%zu failed. Reason %d\n",
name, size, err);
s->refcount = -1; /* Exempt from merging for now */
}
struct kmem_cache *__init create_kmalloc_cache(const char *name, size_t size,
unsigned long flags)
{
struct kmem_cache *s = kmem_cache_zalloc(kmem_cache, GFP_NOWAIT);
if (!s)
panic("Out of memory when creating slab %s\n", name);
create_boot_cache(s, name, size, flags);
list_add(&s->list, &slab_caches);
s->refcount = 1;
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 (unlikely(size > KMALLOC_MAX_SIZE)) {
WARN_ON_ONCE(!(flags & __GFP_NOWARN));
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];
}
/*
* kmalloc_info[] is to make slub_debug=,kmalloc-xx option work at boot time.
* kmalloc_index() supports up to 2^26=64MB, so the final entry of the table is
* kmalloc-67108864.
*/
static struct {
const char *name;
unsigned long size;
} const kmalloc_info[] __initconst = {
{NULL, 0}, {"kmalloc-96", 96},
{"kmalloc-192", 192}, {"kmalloc-8", 8},
{"kmalloc-16", 16}, {"kmalloc-32", 32},
{"kmalloc-64", 64}, {"kmalloc-128", 128},
{"kmalloc-256", 256}, {"kmalloc-512", 512},
{"kmalloc-1024", 1024}, {"kmalloc-2048", 2048},
{"kmalloc-4096", 4096}, {"kmalloc-8192", 8192},
{"kmalloc-16384", 16384}, {"kmalloc-32768", 32768},
{"kmalloc-65536", 65536}, {"kmalloc-131072", 131072},
{"kmalloc-262144", 262144}, {"kmalloc-524288", 524288},
{"kmalloc-1048576", 1048576}, {"kmalloc-2097152", 2097152},
{"kmalloc-4194304", 4194304}, {"kmalloc-8388608", 8388608},
{"kmalloc-16777216", 16777216}, {"kmalloc-33554432", 33554432},
{"kmalloc-67108864", 67108864}
};
/*
* 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
*/
void __init setup_kmalloc_cache_index_table(void)
{
int i;
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;
}
}
static void __init new_kmalloc_cache(int idx, unsigned long flags)
{
kmalloc_caches[idx] = create_kmalloc_cache(kmalloc_info[idx].name,
kmalloc_info[idx].size, flags);
}
/*
* 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;
for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++) {
if (!kmalloc_caches[i])
new_kmalloc_cache(i, flags);
/*
* Caches that are not of the two-to-the-power-of size.
* These have to be created immediately after the
* earlier power of two caches
*/
if (KMALLOC_MIN_SIZE <= 32 && !kmalloc_caches[1] && i == 6)
new_kmalloc_cache(1, flags);
if (KMALLOC_MIN_SIZE <= 64 && !kmalloc_caches[2] && i == 7)
new_kmalloc_cache(2, flags);
}
/* Kmalloc array is now usable */
slab_state = UP;
#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 */
/*
* To avoid unnecessary overhead, we pass through large allocation requests
* directly to the page allocator. We use __GFP_COMP, because we will need to
* know the allocation order to free the pages properly in kfree.
*/
void *kmalloc_order(size_t size, gfp_t flags, unsigned int order)
{
void *ret;
struct page *page;
flags |= __GFP_COMP;
page = alloc_kmem_pages(flags, order);
ret = page ? page_address(page) : NULL;
kmemleak_alloc(ret, size, 1, flags);
kasan_kmalloc_large(ret, size);
return ret;
}
EXPORT_SYMBOL(kmalloc_order);
#ifdef CONFIG_TRACING
void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order)
{
void *ret = kmalloc_order(size, flags, order);
trace_kmalloc(_RET_IP_, ret, size, PAGE_SIZE << order, flags);
return ret;
}
EXPORT_SYMBOL(kmalloc_order_trace);
#endif
#ifdef CONFIG_SLABINFO
#ifdef CONFIG_SLAB
#define SLABINFO_RIGHTS (S_IWUSR | S_IRUSR)
#else
#define SLABINFO_RIGHTS S_IRUSR
#endif
static void print_slabinfo_header(struct seq_file *m)
{
/*
* Output format version, so at least we can change it
* without _too_ many complaints.
*/
#ifdef CONFIG_DEBUG_SLAB
seq_puts(m, "slabinfo - version: 2.1 (statistics)\n");
#else
seq_puts(m, "slabinfo - version: 2.1\n");
#endif
seq_puts(m, "# name <active_objs> <num_objs> <objsize> "
"<objperslab> <pagesperslab>");
seq_puts(m, " : tunables <limit> <batchcount> <sharedfactor>");
seq_puts(m, " : slabdata <active_slabs> <num_slabs> <sharedavail>");
#ifdef CONFIG_DEBUG_SLAB
seq_puts(m, " : globalstat <listallocs> <maxobjs> <grown> <reaped> "
"<error> <maxfreeable> <nodeallocs> <remotefrees> <alienoverflow>");
seq_puts(m, " : cpustat <allochit> <allocmiss> <freehit> <freemiss>");
#endif
seq_putc(m, '\n');
}
void *slab_start(struct seq_file *m, loff_t *pos)
{
mutex_lock(&slab_mutex);
return seq_list_start(&slab_caches, *pos);
}
void *slab_next(struct seq_file *m, void *p, loff_t *pos)
{
return seq_list_next(p, &slab_caches, pos);
}
void slab_stop(struct seq_file *m, void *p)
{
mutex_unlock(&slab_mutex);
}
static void
memcg_accumulate_slabinfo(struct kmem_cache *s, struct slabinfo *info)
{
struct kmem_cache *c;
struct slabinfo sinfo;
if (!is_root_cache(s))
return;
for_each_memcg_cache(c, s) {
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;
}
}
static void cache_show(struct kmem_cache *s, struct seq_file *m)
{
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",
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",
sinfo.limit, sinfo.batchcount, sinfo.shared);
seq_printf(m, " : slabdata %6lu %6lu %6lu",
sinfo.active_slabs, sinfo.num_slabs, sinfo.shared_avail);
slabinfo_show_stats(m, s);
seq_putc(m, '\n');
}
static int slab_show(struct seq_file *m, void *p)
{
struct kmem_cache *s = list_entry(p, struct kmem_cache, list);
if (p == slab_caches.next)
print_slabinfo_header(m);
if (is_root_cache(s))
cache_show(s, m);
return 0;
}
#ifdef CONFIG_MEMCG_KMEM
int memcg_slab_show(struct seq_file *m, void *p)
{
struct kmem_cache *s = list_entry(p, struct kmem_cache, list);
struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
if (p == slab_caches.next)
print_slabinfo_header(m);
if (!is_root_cache(s) && s->memcg_params.memcg == memcg)
cache_show(s, m);
return 0;
}
#endif
/*
* slabinfo_op - iterator that generates /proc/slabinfo
*
* Output layout:
* cache-name
* num-active-objs
* total-objs
* object size
* num-active-slabs
* total-slabs
* num-pages-per-slab
* + further values on SMP and with statistics enabled
*/
static const struct seq_operations slabinfo_op = {
.start = slab_start,
.next = slab_next,
.stop = slab_stop,
.show = slab_show,
};
static int slabinfo_open(struct inode *inode, struct file *file)
{
return seq_open(file, &slabinfo_op);
}
static const struct file_operations proc_slabinfo_operations = {
.open = slabinfo_open,
.read = seq_read,
.write = slabinfo_write,
.llseek = seq_lseek,
.release = seq_release,
};
static int __init slab_proc_init(void)
{
proc_create("slabinfo", SLABINFO_RIGHTS, NULL,
&proc_slabinfo_operations);
return 0;
}
module_init(slab_proc_init);
#endif /* CONFIG_SLABINFO */
static __always_inline void *__do_krealloc(const void *p, size_t new_size,
gfp_t flags)
{
void *ret;
size_t ks = 0;
if (p)
ks = ksize(p);
if (ks >= new_size) {
kasan_krealloc((void *)p, new_size);
return (void *)p;
}
ret = kmalloc_track_caller(new_size, flags);
if (ret && p)
memcpy(ret, p, ks);
return ret;
}
/**
* __krealloc - like krealloc() but don't free @p.
* @p: object to reallocate memory for.
* @new_size: how many bytes of memory are required.
* @flags: the type of memory to allocate.
*
* This function is like krealloc() except it never frees the originally
* allocated buffer. Use this if you don't want to free the buffer immediately
* like, for example, with RCU.
*/
void *__krealloc(const void *p, size_t new_size, gfp_t flags)
{
if (unlikely(!new_size))
return ZERO_SIZE_PTR;
return __do_krealloc(p, new_size, flags);
}
EXPORT_SYMBOL(__krealloc);
/**
* krealloc - reallocate memory. The contents will remain unchanged.
* @p: object to reallocate memory for.
* @new_size: how many bytes of memory are required.
* @flags: the type of memory to allocate.
*
* The contents of the object pointed to are preserved up to the
* lesser of the new and old sizes. If @p is %NULL, krealloc()
* behaves exactly like kmalloc(). If @new_size is 0 and @p is not a
* %NULL pointer, the object pointed to is freed.
*/
void *krealloc(const void *p, size_t new_size, gfp_t flags)
{
void *ret;
if (unlikely(!new_size)) {
kfree(p);
return ZERO_SIZE_PTR;
}
ret = __do_krealloc(p, new_size, flags);
if (ret && p != ret)
kfree(p);
return ret;
}
EXPORT_SYMBOL(krealloc);
/**
* kzfree - like kfree but zero memory
* @p: object to free memory of
*
* The memory of the object @p points to is zeroed before freed.
* If @p is %NULL, kzfree() does nothing.
*
* Note: this function zeroes the whole allocated buffer which can be a good
* deal bigger than the requested buffer size passed to kmalloc(). So be
* careful when using this function in performance sensitive code.
*/
void kzfree(const void *p)
{
size_t ks;
void *mem = (void *)p;
if (unlikely(ZERO_OR_NULL_PTR(mem)))
return;
ks = ksize(mem);
memset(mem, 0, ks);
kfree(mem);
}
EXPORT_SYMBOL(kzfree);
/* Tracepoints definitions. */
EXPORT_TRACEPOINT_SYMBOL(kmalloc);
EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc);
EXPORT_TRACEPOINT_SYMBOL(kmalloc_node);
EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc_node);
EXPORT_TRACEPOINT_SYMBOL(kfree);
EXPORT_TRACEPOINT_SYMBOL(kmem_cache_free);
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\mm/slob.c
/*
* SLOB Allocator: Simple List Of Blocks
*
* Matt Mackall <mpm@selenic.com> 12/30/03
*
* NUMA support by Paul Mundt, 2007.
*
* How SLOB works:
*
* The core of SLOB is a traditional K&R style heap allocator, with
* support for returning aligned objects. The granularity of this
* allocator is as little as 2 bytes, however typically most architectures
* will require 4 bytes on 32-bit and 8 bytes on 64-bit.
*
* The slob heap is a set of linked list of pages from alloc_pages(),
* and within each page, there is a singly-linked list of free blocks
* (slob_t). The heap is grown on demand. To reduce fragmentation,
* heap pages are segregated into three lists, with objects less than
* 256 bytes, objects less than 1024 bytes, and all other objects.
*
* Allocation from heap involves first searching for a page with
* sufficient free blocks (using a next-fit-like approach) followed by
* a first-fit scan of the page. Deallocation inserts objects back
* into the free list in address order, so this is effectively an
* address-ordered first fit.
*
* Above this is an implementation of kmalloc/kfree. Blocks returned
* from kmalloc are prepended with a 4-byte header with the kmalloc size.
* If kmalloc is asked for objects of PAGE_SIZE or larger, it calls
* alloc_pages() directly, allocating compound pages so the page order
* does not have to be separately tracked.
* These objects are detected in kfree() because PageSlab()
* is false for them.
*
* SLAB is emulated on top of SLOB by simply calling constructors and
* destructors for every SLAB allocation. Objects are returned with the
* 4-byte alignment unless the SLAB_HWCACHE_ALIGN flag is set, in which
* case the low-level allocator will fragment blocks to create the proper
* alignment. Again, objects of page-size or greater are allocated by
* calling alloc_pages(). As SLAB objects know their size, no separate
* size bookkeeping is necessary and there is essentially no allocation
* space overhead, and compound pages aren't needed for multi-page
* allocations.
*
* NUMA support in SLOB is fairly simplistic, pushing most of the real
* logic down to the page allocator, and simply doing the node accounting
* on the upper levels. In the event that a node id is explicitly
* provided, alloc_pages_exact_node() with the specified node id is used
* instead. The common case (or when the node id isn't explicitly provided)
* will default to the current node, as per numa_node_id().
*
* Node aware pages are still inserted in to the global freelist, and
* these are scanned for by matching against the node id encoded in the
* page flags. As a result, block allocations that can be satisfied from
* the freelist will only be done so on pages residing on the same node,
* in order to prevent random node placement.
*/
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/swap.h> /* struct reclaim_state */
#include <linux/cache.h>
#include <linux/init.h>
#include <linux/export.h>
#include <linux/rcupdate.h>
#include <linux/list.h>
#include <linux/kmemleak.h>
#include <trace/events/kmem.h>
#include <linux/atomic.h>
#include "slab.h"
/*
* slob_block has a field 'units', which indicates size of block if +ve,
* or offset of next block if -ve (in SLOB_UNITs).
*
* Free blocks of size 1 unit simply contain the offset of the next block.
* Those with larger size contain their size in the first SLOB_UNIT of
* memory, and the offset of the next free block in the second SLOB_UNIT.
*/
#if PAGE_SIZE <= (32767 * 2)
typedef s16 slobidx_t;
#else
typedef s32 slobidx_t;
#endif
struct slob_block {
slobidx_t units;
};
typedef struct slob_block slob_t;
/*
* All partially free slob pages go on these lists.
*/
#define SLOB_BREAK1 256
#define SLOB_BREAK2 1024
static LIST_HEAD(free_slob_small);
static LIST_HEAD(free_slob_medium);
static LIST_HEAD(free_slob_large);
/*
* slob_page_free: true for pages on free_slob_pages list.
*/
static inline int slob_page_free(struct page *sp)
{
return PageSlobFree(sp);
}
static void set_slob_page_free(struct page *sp, struct list_head *list)
{
list_add(&sp->lru, list);
__SetPageSlobFree(sp);
}
static inline void clear_slob_page_free(struct page *sp)
{
list_del(&sp->lru);
__ClearPageSlobFree(sp);
}
#define SLOB_UNIT sizeof(slob_t)
#define SLOB_UNITS(size) DIV_ROUND_UP(size, SLOB_UNIT)
/*
* struct slob_rcu is inserted at the tail of allocated slob blocks, which
* were created with a SLAB_DESTROY_BY_RCU slab. slob_rcu is used to free
* the block using call_rcu.
*/
struct slob_rcu {
struct rcu_head head;
int size;
};
/*
* slob_lock protects all slob allocator structures.
*/
static DEFINE_SPINLOCK(slob_lock);
/*
* Encode the given size and next info into a free slob block s.
*/
static void set_slob(slob_t *s, slobidx_t size, slob_t *next)
{
slob_t *base = (slob_t *)((unsigned long)s & PAGE_MASK);
slobidx_t offset = next - base;
if (size > 1) {
s[0].units = size;
s[1].units = offset;
} else
s[0].units = -offset;
}
/*
* Return the size of a slob block.
*/
static slobidx_t slob_units(slob_t *s)
{
if (s->units > 0)
return s->units;
return 1;
}
/*
* Return the next free slob block pointer after this one.
*/
static slob_t *slob_next(slob_t *s)
{
slob_t *base = (slob_t *)((unsigned long)s & PAGE_MASK);
slobidx_t next;
if (s[0].units < 0)
next = -s[0].units;
else
next = s[1].units;
return base+next;
}
/*
* Returns true if s is the last free block in its page.
*/
static int slob_last(slob_t *s)
{
return !((unsigned long)slob_next(s) & ~PAGE_MASK);
}
static void *slob_new_pages(gfp_t gfp, int order, int node)
{
void *page;
#ifdef CONFIG_NUMA
if (node != NUMA_NO_NODE)
page = alloc_pages_exact_node(node, gfp, order);
else
#endif
page = alloc_pages(gfp, order);
if (!page)
return NULL;
return page_address(page);
}
static void slob_free_pages(void *b, int order)
{
if (current->reclaim_state)
current->reclaim_state->reclaimed_slab += 1 << order;
free_pages((unsigned long)b, order);
}
/*
* Allocate a slob block within a given slob_page sp.
*/
static void *slob_page_alloc(struct page *sp, size_t size, int align)
{
slob_t *prev, *cur, *aligned = NULL;
int delta = 0, units = SLOB_UNITS(size);
for (prev = NULL, cur = sp->freelist; ; prev = cur, cur = slob_next(cur)) {
slobidx_t avail = slob_units(cur);
if (align) {
aligned = (slob_t *)ALIGN((unsigned long)cur, align);
delta = aligned - cur;
}
if (avail >= units + delta) { /* room enough? */
slob_t *next;
if (delta) { /* need to fragment head to align? */
next = slob_next(cur);
set_slob(aligned, avail - delta, next);
set_slob(cur, delta, aligned);
prev = cur;
cur = aligned;
avail = slob_units(cur);
}
next = slob_next(cur);
if (avail == units) { /* exact fit? unlink. */
if (prev)
set_slob(prev, slob_units(prev), next);
else
sp->freelist = next;
} else { /* fragment */
if (prev)
set_slob(prev, slob_units(prev), cur + units);
else
sp->freelist = cur + units;
set_slob(cur + units, avail - units, next);
}
sp->units -= units;
if (!sp->units)
clear_slob_page_free(sp);
return cur;
}
if (slob_last(cur))
return NULL;
}
}
/*
* slob_alloc: entry point into the slob allocator.
*/
static void *slob_alloc(size_t size, gfp_t gfp, int align, int node)
{
struct page *sp;
struct list_head *prev;
struct list_head *slob_list;
slob_t *b = NULL;
unsigned long flags;
if (size < SLOB_BREAK1)
slob_list = &free_slob_small;
else if (size < SLOB_BREAK2)
slob_list = &free_slob_medium;
else
slob_list = &free_slob_large;
spin_lock_irqsave(&slob_lock, flags);
/* Iterate through each partially free page, try to find room */
list_for_each_entry(sp, slob_list, lru) {
#ifdef CONFIG_NUMA
/*
* If there's a node specification, search for a partial
* page with a matching node id in the freelist.
*/
if (node != NUMA_NO_NODE && page_to_nid(sp) != node)
continue;
#endif
/* Enough room on this page? */
if (sp->units < SLOB_UNITS(size))
continue;
/* Attempt to alloc */
prev = sp->lru.prev;
b = slob_page_alloc(sp, size, align);
if (!b)
continue;
/* Improve fragment distribution and reduce our average
* search time by starting our next search here. (see
* Knuth vol 1, sec 2.5, pg 449) */
if (prev != slob_list->prev &&
slob_list->next != prev->next)
list_move_tail(slob_list, prev->next);
break;
}
spin_unlock_irqrestore(&slob_lock, flags);
/* Not enough space: must allocate a new page */
if (!b) {
b = slob_new_pages(gfp & ~__GFP_ZERO, 0, node);
if (!b)
return NULL;
sp = virt_to_page(b);
__SetPageSlab(sp);
spin_lock_irqsave(&slob_lock, flags);
sp->units = SLOB_UNITS(PAGE_SIZE);
sp->freelist = b;
INIT_LIST_HEAD(&sp->lru);
set_slob(b, SLOB_UNITS(PAGE_SIZE), b + SLOB_UNITS(PAGE_SIZE));
set_slob_page_free(sp, slob_list);
b = slob_page_alloc(sp, size, align);
BUG_ON(!b);
spin_unlock_irqrestore(&slob_lock, flags);
}
if (unlikely((gfp & __GFP_ZERO) && b))
memset(b, 0, size);
return b;
}
/*
* slob_free: entry point into the slob allocator.
*/
static void slob_free(void *block, int size)
{
struct page *sp;
slob_t *prev, *next, *b = (slob_t *)block;
slobidx_t units;
unsigned long flags;
struct list_head *slob_list;
if (unlikely(ZERO_OR_NULL_PTR(block)))
return;
BUG_ON(!size);
sp = virt_to_page(block);
units = SLOB_UNITS(size);
spin_lock_irqsave(&slob_lock, flags);
if (sp->units + units == SLOB_UNITS(PAGE_SIZE)) {
/* Go directly to page allocator. Do not pass slob allocator */
if (slob_page_free(sp))
clear_slob_page_free(sp);
spin_unlock_irqrestore(&slob_lock, flags);
__ClearPageSlab(sp);
page_mapcount_reset(sp);
slob_free_pages(b, 0);
return;
}
if (!slob_page_free(sp)) {
/* This slob page is about to become partially free. Easy! */
sp->units = units;
sp->freelist = b;
set_slob(b, units,
(void *)((unsigned long)(b +
SLOB_UNITS(PAGE_SIZE)) & PAGE_MASK));
if (size < SLOB_BREAK1)
slob_list = &free_slob_small;
else if (size < SLOB_BREAK2)
slob_list = &free_slob_medium;
else
slob_list = &free_slob_large;
set_slob_page_free(sp, slob_list);
goto out;
}
/*
* Otherwise the page is already partially free, so find reinsertion
* point.
*/
sp->units += units;
if (b < (slob_t *)sp->freelist) {
if (b + units == sp->freelist) {
units += slob_units(sp->freelist);
sp->freelist = slob_next(sp->freelist);
}
set_slob(b, units, sp->freelist);
sp->freelist = b;
} else {
prev = sp->freelist;
next = slob_next(prev);
while (b > next) {
prev = next;
next = slob_next(prev);
}
if (!slob_last(prev) && b + units == next) {
units += slob_units(next);
set_slob(b, units, slob_next(next));
} else
set_slob(b, units, next);
if (prev + slob_units(prev) == b) {
units = slob_units(b) + slob_units(prev);
set_slob(prev, units, slob_next(b));
} else
set_slob(prev, slob_units(prev), b);
}
out:
spin_unlock_irqrestore(&slob_lock, flags);
}
/*
* End of slob allocator proper. Begin kmem_cache_alloc and kmalloc frontend.
*/
static __always_inline void *
__do_kmalloc_node(size_t size, gfp_t gfp, int node, unsigned long caller)
{
unsigned int *m;
int align = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
void *ret;
gfp &= gfp_allowed_mask;
lockdep_trace_alloc(gfp);
if (size < PAGE_SIZE - align) {
if (!size)
return ZERO_SIZE_PTR;
m = slob_alloc(size + align, gfp, align, node);
if (!m)
return NULL;
*m = size;
ret = (void *)m + align;
trace_kmalloc_node(caller, ret,
size, size + align, gfp, node);
} else {
unsigned int order = get_order(size);
if (likely(order))
gfp |= __GFP_COMP;
ret = slob_new_pages(gfp, order, node);
trace_kmalloc_node(caller, ret,
size, PAGE_SIZE << order, gfp, node);
}
kmemleak_alloc(ret, size, 1, gfp);
return ret;
}
void *__kmalloc(size_t size, gfp_t gfp)
{
return __do_kmalloc_node(size, gfp, NUMA_NO_NODE, _RET_IP_);
}
EXPORT_SYMBOL(__kmalloc);
void *__kmalloc_track_caller(size_t size, gfp_t gfp, unsigned long caller)
{
return __do_kmalloc_node(size, gfp, NUMA_NO_NODE, caller);
}
#ifdef CONFIG_NUMA
void *__kmalloc_node_track_caller(size_t size, gfp_t gfp,
int node, unsigned long caller)
{
return __do_kmalloc_node(size, gfp, node, caller);
}
#endif
void kfree(const void *block)
{
struct page *sp;
trace_kfree(_RET_IP_, block);
if (unlikely(ZERO_OR_NULL_PTR(block)))
return;
kmemleak_free(block);
sp = virt_to_page(block);
if (PageSlab(sp)) {
int align = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
unsigned int *m = (unsigned int *)(block - align);
slob_free(m, *m + align);
} else
__free_pages(sp, compound_order(sp));
}
EXPORT_SYMBOL(kfree);
/* can't use ksize for kmem_cache_alloc memory, only kmalloc */
size_t ksize(const void *block)
{
struct page *sp;
int align;
unsigned int *m;
BUG_ON(!block);
if (unlikely(block == ZERO_SIZE_PTR))
return 0;
sp = virt_to_page(block);
if (unlikely(!PageSlab(sp)))
return PAGE_SIZE << compound_order(sp);
align = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
m = (unsigned int *)(block - align);
return SLOB_UNITS(*m) * SLOB_UNIT;
}
EXPORT_SYMBOL(ksize);
int __kmem_cache_create(struct kmem_cache *c, unsigned long flags)
{
if (flags & SLAB_DESTROY_BY_RCU) {
/* leave room for rcu footer at the end of object */
c->size += sizeof(struct slob_rcu);
}
c->flags = flags;
return 0;
}
static void *slob_alloc_node(struct kmem_cache *c, gfp_t flags, int node)
{
void *b;
flags &= gfp_allowed_mask;
lockdep_trace_alloc(flags);
if (c->size < PAGE_SIZE) {
b = slob_alloc(c->size, flags, c->align, node);
trace_kmem_cache_alloc_node(_RET_IP_, b, c->object_size,
SLOB_UNITS(c->size) * SLOB_UNIT,
flags, node);
} else {
b = slob_new_pages(flags, get_order(c->size), node);
trace_kmem_cache_alloc_node(_RET_IP_, b, c->object_size,
PAGE_SIZE << get_order(c->size),
flags, node);
}
if (b && c->ctor)
c->ctor(b);
kmemleak_alloc_recursive(b, c->size, 1, c->flags, flags);
return b;
}
void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags)
{
return slob_alloc_node(cachep, flags, NUMA_NO_NODE);
}
EXPORT_SYMBOL(kmem_cache_alloc);
#ifdef CONFIG_NUMA
void *__kmalloc_node(size_t size, gfp_t gfp, int node)
{
return __do_kmalloc_node(size, gfp, node, _RET_IP_);
}
EXPORT_SYMBOL(__kmalloc_node);
void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t gfp, int node)
{
return slob_alloc_node(cachep, gfp, node);
}
EXPORT_SYMBOL(kmem_cache_alloc_node);
#endif
static void __kmem_cache_free(void *b, int size)
{
if (size < PAGE_SIZE)
slob_free(b, size);
else
slob_free_pages(b, get_order(size));
}
static void kmem_rcu_free(struct rcu_head *head)
{
struct slob_rcu *slob_rcu = (struct slob_rcu *)head;
void *b = (void *)slob_rcu - (slob_rcu->size - sizeof(struct slob_rcu));
__kmem_cache_free(b, slob_rcu->size);
}
void kmem_cache_free(struct kmem_cache *c, void *b)
{
kmemleak_free_recursive(b, c->flags);
if (unlikely(c->flags & SLAB_DESTROY_BY_RCU)) {
struct slob_rcu *slob_rcu;
slob_rcu = b + (c->size - sizeof(struct slob_rcu));
slob_rcu->size = c->size;
call_rcu(&slob_rcu->head, kmem_rcu_free);
} else {
__kmem_cache_free(b, c->size);
}
trace_kmem_cache_free(_RET_IP_, b);
}
EXPORT_SYMBOL(kmem_cache_free);
int __kmem_cache_shutdown(struct kmem_cache *c)
{
/* No way to check for remaining objects */
return 0;
}
int __kmem_cache_shrink(struct kmem_cache *d, bool deactivate)
{
return 0;
}
struct kmem_cache kmem_cache_boot = {
.name = "kmem_cache",
.size = sizeof(struct kmem_cache),
.flags = SLAB_PANIC,
.align = ARCH_KMALLOC_MINALIGN,
};
void __init kmem_cache_init(void)
{
kmem_cache = &kmem_cache_boot;
slab_state = UP;
}
void __init kmem_cache_init_late(void)
{
slab_state = FULL;
}
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\mm/slub.c
/*
* SLUB: A slab allocator that limits cache line use instead of queuing
* objects in per cpu and per node lists.
*
* The allocator synchronizes using per slab locks or atomic operatios
* and only uses a centralized lock to manage a pool of partial slabs.
*
* (C) 2007 SGI, Christoph Lameter
* (C) 2011 Linux Foundation, Christoph Lameter
*/
#include <linux/mm.h>
#include <linux/swap.h> /* struct reclaim_state */
#include <linux/module.h>
#include <linux/bit_spinlock.h>
#include <linux/interrupt.h>
#include <linux/bitops.h>
#include <linux/slab.h>
#include "slab.h"
#include <linux/proc_fs.h>
#include <linux/notifier.h>
#include <linux/seq_file.h>
#include <linux/kasan.h>
#include <linux/kmemcheck.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
#include <linux/mempolicy.h>
#include <linux/ctype.h>
#include <linux/debugobjects.h>
#include <linux/kallsyms.h>
#include <linux/memory.h>
#include <linux/math64.h>
#include <linux/fault-inject.h>
#include <linux/stacktrace.h>
#include <linux/prefetch.h>
#include <linux/memcontrol.h>
#include <trace/events/kmem.h>
#include "internal.h"
/*
* Lock order:
* 1. slab_mutex (Global Mutex)
* 2. node->list_lock
* 3. slab_lock(page) (Only on some arches and for debugging)
*
* slab_mutex
*
* The role of the slab_mutex is to protect the list of all the slabs
* and to synchronize major metadata changes to slab cache structures.
*
* The slab_lock is only used for debugging and on arches that do not
* have the ability to do a cmpxchg_double. It only protects the second
* double word in the page struct. Meaning
* A. page->freelist -> List of object free in a page
* B. page->counters -> Counters of objects
* C. page->frozen -> frozen state
*
* If a slab is frozen then it is exempt from list management. It is not
* on any list. The processor that froze the slab is the one who can
* perform list operations on the page. Other processors may put objects
* onto the freelist but the processor that froze the slab is the only
* one that can retrieve the objects from the page's freelist.
*
* The list_lock protects the partial and full list on each node and
* the partial slab counter. If taken then no new slabs may be added or
* removed from the lists nor make the number of partial slabs be modified.
* (Note that the total number of slabs is an atomic value that may be
* modified without taking the list lock).
*
* The list_lock is a centralized lock and thus we avoid taking it as
* much as possible. As long as SLUB does not have to handle partial
* slabs, operations can continue without any centralized lock. F.e.
* allocating a long series of objects that fill up slabs does not require
* the list lock.
* Interrupts are disabled during allocation and deallocation in order to
* make the slab allocator safe to use in the context of an irq. In addition
* interrupts are disabled to ensure that the processor does not change
* while handling per_cpu slabs, due to kernel preemption.
*
* SLUB assigns one slab for allocation to each processor.
* Allocations only occur from these slabs called cpu slabs.
*
* Slabs with free elements are kept on a partial list and during regular
* operations no list for full slabs is used. If an object in a full slab is
* freed then the slab will show up again on the partial lists.
* We track full slabs for debugging purposes though because otherwise we
* cannot scan all objects.
*
* Slabs are freed when they become empty. Teardown and setup is
* minimal so we rely on the page allocators per cpu caches for
* fast frees and allocs.
*
* Overloading of page flags that are otherwise used for LRU management.
*
* PageActive The slab is frozen and exempt from list processing.
* This means that the slab is dedicated to a purpose
* such as satisfying allocations for a specific
* processor. Objects may be freed in the slab while
* it is frozen but slab_free will then skip the usual
* list operations. It is up to the processor holding
* the slab to integrate the slab into the slab lists
* when the slab is no longer needed.
*
* One use of this flag is to mark slabs that are
* used for allocations. Then such a slab becomes a cpu
* slab. The cpu slab may be equipped with an additional
* freelist that allows lockless access to
* free objects in addition to the regular freelist
* that requires the slab lock.
*
* PageError Slab requires special handling due to debug
* options set. This moves slab handling out of
* the fast path and disables lockless freelists.
*/
static inline int kmem_cache_debug(struct kmem_cache *s)
{
#ifdef CONFIG_SLUB_DEBUG
return unlikely(s->flags & SLAB_DEBUG_FLAGS);
#else
return 0;
#endif
}
static inline bool kmem_cache_has_cpu_partial(struct kmem_cache *s)
{
#ifdef CONFIG_SLUB_CPU_PARTIAL
return !kmem_cache_debug(s);
#else
return false;
#endif
}
/*
* Issues still to be resolved:
*
* - Support PAGE_ALLOC_DEBUG. Should be easy to do.
*
* - Variable sizing of the per node arrays
*/
/* Enable to test recovery from slab corruption on boot */
#undef SLUB_RESILIENCY_TEST
/* Enable to log cmpxchg failures */
#undef SLUB_DEBUG_CMPXCHG
/*
* 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 MIN_PARTIAL 5
/*
* 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 use.
*/
#define MAX_PARTIAL 10
#define DEBUG_DEFAULT_FLAGS (SLAB_DEBUG_FREE | SLAB_RED_ZONE | \
SLAB_POISON | SLAB_STORE_USER)
/*
* Debugging flags that require metadata to be stored in the slab. These get
* disabled when slub_debug=O is used and a cache's min order increases with
* metadata.
*/
#define DEBUG_METADATA_FLAGS (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER)
#define OO_SHIFT 16
#define OO_MASK ((1 << OO_SHIFT) - 1)
#define MAX_OBJS_PER_PAGE 32767 /* since page.objects is u15 */
/* Internal SLUB flags */
#define __OBJECT_POISON 0x80000000UL /* Poison object */
#define __CMPXCHG_DOUBLE 0x40000000UL /* Use cmpxchg_double */
#ifdef CONFIG_SMP
static struct notifier_block slab_notifier;
#endif
/*
* Tracking user of a slab.
*/
#define TRACK_ADDRS_COUNT 16
struct track {
unsigned long addr; /* Called from address */
#ifdef CONFIG_STACKTRACE
unsigned long addrs[TRACK_ADDRS_COUNT]; /* Called from address */
#endif
int cpu; /* Was running on cpu */
int pid; /* Pid context */
unsigned long when; /* When did the operation occur */
};
enum track_item { TRACK_ALLOC, TRACK_FREE };
#ifdef CONFIG_SYSFS
static int sysfs_slab_add(struct kmem_cache *);
static int sysfs_slab_alias(struct kmem_cache *, const char *);
static void memcg_propagate_slab_attrs(struct kmem_cache *s);
#else
static inline int sysfs_slab_add(struct kmem_cache *s) { return 0; }
static inline int sysfs_slab_alias(struct kmem_cache *s, const char *p)
{ return 0; }
static inline void memcg_propagate_slab_attrs(struct kmem_cache *s) { }
#endif
static inline void stat(const struct kmem_cache *s, enum stat_item si)
{
#ifdef CONFIG_SLUB_STATS
/*
* The rmw is racy on a preemptible kernel but this is acceptable, so
* avoid this_cpu_add()'s irq-disable overhead.
*/
raw_cpu_inc(s->cpu_slab->stat[si]);
#endif
}
/********************************************************************
* Core slab cache functions
*******************************************************************/
/* Verify that a pointer has an address that is valid within a slab page */
static inline int check_valid_pointer(struct kmem_cache *s,
struct page *page, const void *object)
{
void *base;
if (!object)
return 1;
base = page_address(page);
if (object < base || object >= base + page->objects * s->size ||
(object - base) % s->size) {
return 0;
}
return 1;
}
static inline void *get_freepointer(struct kmem_cache *s, void *object)
{
return *(void **)(object + s->offset);
}
static void prefetch_freepointer(const struct kmem_cache *s, void *object)
{
prefetch(object + s->offset);
}
static inline void *get_freepointer_safe(struct kmem_cache *s, void *object)
{
void *p;
#ifdef CONFIG_DEBUG_PAGEALLOC
probe_kernel_read(&p, (void **)(object + s->offset), sizeof(p));
#else
p = get_freepointer(s, object);
#endif
return p;
}
static inline void set_freepointer(struct kmem_cache *s, void *object, void *fp)
{
*(void **)(object + s->offset) = fp;
}
/* Loop over all objects in a slab */
#define for_each_object(__p, __s, __addr, __objects) \
for (__p = (__addr); __p < (__addr) + (__objects) * (__s)->size;\
__p += (__s)->size)
#define for_each_object_idx(__p, __idx, __s, __addr, __objects) \
for (__p = (__addr), __idx = 1; __idx <= __objects;\
__p += (__s)->size, __idx++)
/* Determine object index from a given position */
static inline int slab_index(void *p, struct kmem_cache *s, void *addr)
{
return (p - addr) / s->size;
}
static inline size_t slab_ksize(const struct kmem_cache *s)
{
#ifdef CONFIG_SLUB_DEBUG
/*
* Debugging requires use of the padding between object
* and whatever may come after it.
*/
if (s->flags & (SLAB_RED_ZONE | SLAB_POISON))
return s->object_size;
#endif
/*
* If we have the need to store the freelist pointer
* back there or track user information then we can
* only use the space before that information.
*/
if (s->flags & (SLAB_DESTROY_BY_RCU | SLAB_STORE_USER))
return s->inuse;
/*
* Else we can use all the padding etc for the allocation
*/
return s->size;
}
static inline int order_objects(int order, unsigned long size, int reserved)
{
return ((PAGE_SIZE << order) - reserved) / size;
}
static inline struct kmem_cache_order_objects oo_make(int order,
unsigned long size, int reserved)
{
struct kmem_cache_order_objects x = {
(order << OO_SHIFT) + order_objects(order, size, reserved)
};
return x;
}
static inline int oo_order(struct kmem_cache_order_objects x)
{
return x.x >> OO_SHIFT;
}
static inline int oo_objects(struct kmem_cache_order_objects x)
{
return x.x & OO_MASK;
}
/*
* Per slab locking using the pagelock
*/
static __always_inline void slab_lock(struct page *page)
{
bit_spin_lock(PG_locked, &page->flags);
}
static __always_inline void slab_unlock(struct page *page)
{
__bit_spin_unlock(PG_locked, &page->flags);
}
static inline void set_page_slub_counters(struct page *page, unsigned long counters_new)
{
struct page tmp;
tmp.counters = counters_new;
/*
* page->counters can cover frozen/inuse/objects as well
* as page->_count. If we assign to ->counters directly
* we run the risk of losing updates to page->_count, so
* be careful and only assign to the fields we need.
*/
page->frozen = tmp.frozen;
page->inuse = tmp.inuse;
page->objects = tmp.objects;
}
/* Interrupts must be disabled (for the fallback code to work right) */
static inline bool __cmpxchg_double_slab(struct kmem_cache *s, struct page *page,
void *freelist_old, unsigned long counters_old,
void *freelist_new, unsigned long counters_new,
const char *n)
{
VM_BUG_ON(!irqs_disabled());
#if defined(CONFIG_HAVE_CMPXCHG_DOUBLE) && \
defined(CONFIG_HAVE_ALIGNED_STRUCT_PAGE)
if (s->flags & __CMPXCHG_DOUBLE) {
if (cmpxchg_double(&page->freelist, &page->counters,
freelist_old, counters_old,
freelist_new, counters_new))
return true;
} else
#endif
{
slab_lock(page);
if (page->freelist == freelist_old &&
page->counters == counters_old) {
page->freelist = freelist_new;
set_page_slub_counters(page, counters_new);
slab_unlock(page);
return true;
}
slab_unlock(page);
}
cpu_relax();
stat(s, CMPXCHG_DOUBLE_FAIL);
#ifdef SLUB_DEBUG_CMPXCHG
pr_info("%s %s: cmpxchg double redo ", n, s->name);
#endif
return false;
}
static inline bool cmpxchg_double_slab(struct kmem_cache *s, struct page *page,
void *freelist_old, unsigned long counters_old,
void *freelist_new, unsigned long counters_new,
const char *n)
{
#if defined(CONFIG_HAVE_CMPXCHG_DOUBLE) && \
defined(CONFIG_HAVE_ALIGNED_STRUCT_PAGE)
if (s->flags & __CMPXCHG_DOUBLE) {
if (cmpxchg_double(&page->freelist, &page->counters,
freelist_old, counters_old,
freelist_new, counters_new))
return true;
} else
#endif
{
unsigned long flags;
local_irq_save(flags);
slab_lock(page);
if (page->freelist == freelist_old &&
page->counters == counters_old) {
page->freelist = freelist_new;
set_page_slub_counters(page, counters_new);
slab_unlock(page);
local_irq_restore(flags);
return true;
}
slab_unlock(page);
local_irq_restore(flags);
}
cpu_relax();
stat(s, CMPXCHG_DOUBLE_FAIL);
#ifdef SLUB_DEBUG_CMPXCHG
pr_info("%s %s: cmpxchg double redo ", n, s->name);
#endif
return false;
}
#ifdef CONFIG_SLUB_DEBUG
/*
* Determine a map of object in use on a page.
*
* Node listlock must be held to guarantee that the page does
* not vanish from under us.
*/
static void get_map(struct kmem_cache *s, struct page *page, unsigned long *map)
{
void *p;
void *addr = page_address(page);
for (p = page->freelist; p; p = get_freepointer(s, p))
set_bit(slab_index(p, s, addr), map);
}
/*
* Debug settings:
*/
#ifdef CONFIG_SLUB_DEBUG_ON
static int slub_debug = DEBUG_DEFAULT_FLAGS;
#else
static int slub_debug;
#endif
static char *slub_debug_slabs;
static int disable_higher_order_debug;
/*
* slub is about to manipulate internal object metadata. This memory lies
* outside the range of the allocated object, so accessing it would normally
* be reported by kasan as a bounds error. metadata_access_enable() is used
* to tell kasan that these accesses are OK.
*/
static inline void metadata_access_enable(void)
{
kasan_disable_current();
}
static inline void metadata_access_disable(void)
{
kasan_enable_current();
}
/*
* Object debugging
*/
static void print_section(char *text, u8 *addr, unsigned int length)
{
metadata_access_enable();
print_hex_dump(KERN_ERR, text, DUMP_PREFIX_ADDRESS, 16, 1, addr,
length, 1);
metadata_access_disable();
}
static struct track *get_track(struct kmem_cache *s, void *object,
enum track_item alloc)
{
struct track *p;
if (s->offset)
p = object + s->offset + sizeof(void *);
else
p = object + s->inuse;
return p + alloc;
}
static void set_track(struct kmem_cache *s, void *object,
enum track_item alloc, unsigned long addr)
{
struct track *p = get_track(s, object, alloc);
if (addr) {
#ifdef CONFIG_STACKTRACE
struct stack_trace trace;
int i;
trace.nr_entries = 0;
trace.max_entries = TRACK_ADDRS_COUNT;
trace.entries = p->addrs;
trace.skip = 3;
metadata_access_enable();
save_stack_trace(&trace);
metadata_access_disable();
/* See rant in lockdep.c */
if (trace.nr_entries != 0 &&
trace.entries[trace.nr_entries - 1] == ULONG_MAX)
trace.nr_entries--;
for (i = trace.nr_entries; i < TRACK_ADDRS_COUNT; i++)
p->addrs[i] = 0;
#endif
p->addr = addr;
p->cpu = smp_processor_id();
p->pid = current->pid;
p->when = jiffies;
} else
memset(p, 0, sizeof(struct track));
}
static void init_tracking(struct kmem_cache *s, void *object)
{
if (!(s->flags & SLAB_STORE_USER))
return;
set_track(s, object, TRACK_FREE, 0UL);
set_track(s, object, TRACK_ALLOC, 0UL);
}
static void print_track(const char *s, struct track *t)
{
if (!t->addr)
return;
pr_err("INFO: %s in %pS age=%lu cpu=%u pid=%d\n",
s, (void *)t->addr, jiffies - t->when, t->cpu, t->pid);
#ifdef CONFIG_STACKTRACE
{
int i;
for (i = 0; i < TRACK_ADDRS_COUNT; i++)
if (t->addrs[i])
pr_err("\t%pS\n", (void *)t->addrs[i]);
else
break;
}
#endif
}
static void print_tracking(struct kmem_cache *s, void *object)
{
if (!(s->flags & SLAB_STORE_USER))
return;
print_track("Allocated", get_track(s, object, TRACK_ALLOC));
print_track("Freed", get_track(s, object, TRACK_FREE));
}
static void print_page_info(struct page *page)
{
pr_err("INFO: Slab 0x%p objects=%u used=%u fp=0x%p flags=0x%04lx\n",
page, page->objects, page->inuse, page->freelist, page->flags);
}
static void slab_bug(struct kmem_cache *s, char *fmt, ...)
{
struct va_format vaf;
va_list args;
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
pr_err("=============================================================================\n");
pr_err("BUG %s (%s): %pV\n", s->name, print_tainted(), &vaf);
pr_err("-----------------------------------------------------------------------------\n\n");
add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
va_end(args);
}
static void slab_fix(struct kmem_cache *s, char *fmt, ...)
{
struct va_format vaf;
va_list args;
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
pr_err("FIX %s: %pV\n", s->name, &vaf);
va_end(args);
}
static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p)
{
unsigned int off; /* Offset of last byte */
u8 *addr = page_address(page);
print_tracking(s, p);
print_page_info(page);
pr_err("INFO: Object 0x%p @offset=%tu fp=0x%p\n\n",
p, p - addr, get_freepointer(s, p));
if (p > addr + 16)
print_section("Bytes b4 ", p - 16, 16);
print_section("Object ", p, min_t(unsigned long, s->object_size,
PAGE_SIZE));
if (s->flags & SLAB_RED_ZONE)
print_section("Redzone ", p + s->object_size,
s->inuse - s->object_size);
if (s->offset)
off = s->offset + sizeof(void *);
else
off = s->inuse;
if (s->flags & SLAB_STORE_USER)
off += 2 * sizeof(struct track);
if (off != s->size)
/* Beginning of the filler is the free pointer */
print_section("Padding ", p + off, s->size - off);
dump_stack();
}
void object_err(struct kmem_cache *s, struct page *page,
u8 *object, char *reason)
{
slab_bug(s, "%s", reason);
print_trailer(s, page, object);
}
static void slab_err(struct kmem_cache *s, struct page *page,
const char *fmt, ...)
{
va_list args;
char buf[100];
va_start(args, fmt);
vsnprintf(buf, sizeof(buf), fmt, args);
va_end(args);
slab_bug(s, "%s", buf);
print_page_info(page);
dump_stack();
}
static void init_object(struct kmem_cache *s, void *object, u8 val)
{
u8 *p = object;
if (s->flags & __OBJECT_POISON) {
memset(p, POISON_FREE, s->object_size - 1);
p[s->object_size - 1] = POISON_END;
}
if (s->flags & SLAB_RED_ZONE)
memset(p + s->object_size, val, s->inuse - s->object_size);
}
static void restore_bytes(struct kmem_cache *s, char *message, u8 data,
void *from, void *to)
{
slab_fix(s, "Restoring 0x%p-0x%p=0x%x\n", from, to - 1, data);
memset(from, data, to - from);
}
static int check_bytes_and_report(struct kmem_cache *s, struct page *page,
u8 *object, char *what,
u8 *start, unsigned int value, unsigned int bytes)
{
u8 *fault;
u8 *end;
metadata_access_enable();
fault = memchr_inv(start, value, bytes);
metadata_access_disable();
if (!fault)
return 1;
end = start + bytes;
while (end > fault && end[-1] == value)
end--;
slab_bug(s, "%s overwritten", what);
pr_err("INFO: 0x%p-0x%p. First byte 0x%x instead of 0x%x\n",
fault, end - 1, fault[0], value);
print_trailer(s, page, object);
restore_bytes(s, what, value, fault, end);
return 0;
}
/*
* Object layout:
*
* object address
* Bytes of the object to be managed.
* If the freepointer may overlay the object then the free
* pointer is the first word of the object.
*
* Poisoning uses 0x6b (POISON_FREE) and the last byte is
* 0xa5 (POISON_END)
*
* object + s->object_size
* Padding to reach word boundary. This is also used for Redzoning.
* Padding is extended by another word if Redzoning is enabled and
* object_size == inuse.
*
* We fill with 0xbb (RED_INACTIVE) for inactive objects and with
* 0xcc (RED_ACTIVE) for objects in use.
*
* object + s->inuse
* Meta data starts here.
*
* A. Free pointer (if we cannot overwrite object on free)
* B. Tracking data for SLAB_STORE_USER
* C. Padding to reach required alignment boundary or at mininum
* one word if debugging is on to be able to detect writes
* before the word boundary.
*
* Padding is done using 0x5a (POISON_INUSE)
*
* object + s->size
* Nothing is used beyond s->size.
*
* If slabcaches are merged then the object_size and inuse boundaries are mostly
* ignored. And therefore no slab options that rely on these boundaries
* may be used with merged slabcaches.
*/
static int check_pad_bytes(struct kmem_cache *s, struct page *page, u8 *p)
{
unsigned long off = s->inuse; /* The end of info */
if (s->offset)
/* Freepointer is placed after the object. */
off += sizeof(void *);
if (s->flags & SLAB_STORE_USER)
/* We also have user information there */
off += 2 * sizeof(struct track);
if (s->size == off)
return 1;
return check_bytes_and_report(s, page, p, "Object padding",
p + off, POISON_INUSE, s->size - off);
}
/* Check the pad bytes at the end of a slab page */
static int slab_pad_check(struct kmem_cache *s, struct page *page)
{
u8 *start;
u8 *fault;
u8 *end;
int length;
int remainder;
if (!(s->flags & SLAB_POISON))
return 1;
start = page_address(page);
length = (PAGE_SIZE << compound_order(page)) - s->reserved;
end = start + length;
remainder = length % s->size;
if (!remainder)
return 1;
metadata_access_enable();
fault = memchr_inv(end - remainder, POISON_INUSE, remainder);
metadata_access_disable();
if (!fault)
return 1;
while (end > fault && end[-1] == POISON_INUSE)
end--;
slab_err(s, page, "Padding overwritten. 0x%p-0x%p", fault, end - 1);
print_section("Padding ", end - remainder, remainder);
restore_bytes(s, "slab padding", POISON_INUSE, end - remainder, end);
return 0;
}
static int check_object(struct kmem_cache *s, struct page *page,
void *object, u8 val)
{
u8 *p = object;
u8 *endobject = object + s->object_size;
if (s->flags & SLAB_RED_ZONE) {
if (!check_bytes_and_report(s, page, object, "Redzone",
endobject, val, s->inuse - s->object_size))
return 0;
} else {
if ((s->flags & SLAB_POISON) && s->object_size < s->inuse) {
check_bytes_and_report(s, page, p, "Alignment padding",
endobject, POISON_INUSE,
s->inuse - s->object_size);
}
}
if (s->flags & SLAB_POISON) {
if (val != SLUB_RED_ACTIVE && (s->flags & __OBJECT_POISON) &&
(!check_bytes_and_report(s, page, p, "Poison", p,
POISON_FREE, s->object_size - 1) ||
!check_bytes_and_report(s, page, p, "Poison",
p + s->object_size - 1, POISON_END, 1)))
return 0;
/*
* check_pad_bytes cleans up on its own.
*/
check_pad_bytes(s, page, p);
}
if (!s->offset && val == SLUB_RED_ACTIVE)
/*
* Object and freepointer overlap. Cannot check
* freepointer while object is allocated.
*/
return 1;
/* Check free pointer validity */
if (!check_valid_pointer(s, page, get_freepointer(s, p))) {
object_err(s, page, p, "Freepointer corrupt");
/*
* No choice but to zap it and thus lose the remainder
* of the free objects in this slab. May cause
* another error because the object count is now wrong.
*/
set_freepointer(s, p, NULL);
return 0;
}
return 1;
}
static int check_slab(struct kmem_cache *s, struct page *page)
{
int maxobj;
VM_BUG_ON(!irqs_disabled());
if (!PageSlab(page)) {
slab_err(s, page, "Not a valid slab page");
return 0;
}
maxobj = order_objects(compound_order(page), s->size, s->reserved);
if (page->objects > maxobj) {
slab_err(s, page, "objects %u > max %u",
page->objects, maxobj);
return 0;
}
if (page->inuse > page->objects) {
slab_err(s, page, "inuse %u > max %u",
page->inuse, page->objects);
return 0;
}
/* Slab_pad_check fixes things up after itself */
slab_pad_check(s, page);
return 1;
}
/*
* Determine if a certain object on a page is on the freelist. Must hold the
* slab lock to guarantee that the chains are in a consistent state.
*/
static int on_freelist(struct kmem_cache *s, struct page *page, void *search)
{
int nr = 0;
void *fp;
void *object = NULL;
int max_objects;
fp = page->freelist;
while (fp && nr <= page->objects) {
if (fp == search)
return 1;
if (!check_valid_pointer(s, page, fp)) {
if (object) {
object_err(s, page, object,
"Freechain corrupt");
set_freepointer(s, object, NULL);
} else {
slab_err(s, page, "Freepointer corrupt");
page->freelist = NULL;
page->inuse = page->objects;
slab_fix(s, "Freelist cleared");
return 0;
}
break;
}
object = fp;
fp = get_freepointer(s, object);
nr++;
}
max_objects = order_objects(compound_order(page), s->size, s->reserved);
if (max_objects > MAX_OBJS_PER_PAGE)
max_objects = MAX_OBJS_PER_PAGE;
if (page->objects != max_objects) {
slab_err(s, page, "Wrong number of objects. Found %d but "
"should be %d", page->objects, max_objects);
page->objects = max_objects;
slab_fix(s, "Number of objects adjusted.");
}
if (page->inuse != page->objects - nr) {
slab_err(s, page, "Wrong object count. Counter is %d but "
"counted were %d", page->inuse, page->objects - nr);
page->inuse = page->objects - nr;
slab_fix(s, "Object count adjusted.");
}
return search == NULL;
}
static void trace(struct kmem_cache *s, struct page *page, void *object,
int alloc)
{
if (s->flags & SLAB_TRACE) {
pr_info("TRACE %s %s 0x%p inuse=%d fp=0x%p\n",
s->name,
alloc ? "alloc" : "free",
object, page->inuse,
page->freelist);
if (!alloc)
print_section("Object ", (void *)object,
s->object_size);
dump_stack();
}
}
/*
* Tracking of fully allocated slabs for debugging purposes.
*/
static void add_full(struct kmem_cache *s,
struct kmem_cache_node *n, struct page *page)
{
if (!(s->flags & SLAB_STORE_USER))
return;
lockdep_assert_held(&n->list_lock);
list_add(&page->lru, &n->full);
}
static void remove_full(struct kmem_cache *s, struct kmem_cache_node *n, struct page *page)
{
if (!(s->flags & SLAB_STORE_USER))
return;
lockdep_assert_held(&n->list_lock);
list_del(&page->lru);
}
/* Tracking of the number of slabs for debugging purposes */
static inline unsigned long slabs_node(struct kmem_cache *s, int node)
{
struct kmem_cache_node *n = get_node(s, node);
return atomic_long_read(&n->nr_slabs);
}
static inline unsigned long node_nr_slabs(struct kmem_cache_node *n)
{
return atomic_long_read(&n->nr_slabs);
}
static inline void inc_slabs_node(struct kmem_cache *s, int node, int objects)
{
struct kmem_cache_node *n = get_node(s, node);
/*
* May be called early in order to allocate a slab for the
* kmem_cache_node structure. Solve the chicken-egg
* dilemma by deferring the increment of the count during
* bootstrap (see early_kmem_cache_node_alloc).
*/
if (likely(n)) {
atomic_long_inc(&n->nr_slabs);
atomic_long_add(objects, &n->total_objects);
}
}
static inline void dec_slabs_node(struct kmem_cache *s, int node, int objects)
{
struct kmem_cache_node *n = get_node(s, node);
atomic_long_dec(&n->nr_slabs);
atomic_long_sub(objects, &n->total_objects);
}
/* Object debug checks for alloc/free paths */
static void setup_object_debug(struct kmem_cache *s, struct page *page,
void *object)
{
if (!(s->flags & (SLAB_STORE_USER|SLAB_RED_ZONE|__OBJECT_POISON)))
return;
init_object(s, object, SLUB_RED_INACTIVE);
init_tracking(s, object);
}
static noinline int alloc_debug_processing(struct kmem_cache *s,
struct page *page,
void *object, unsigned long addr)
{
if (!check_slab(s, page))
goto bad;
if (!check_valid_pointer(s, page, object)) {
object_err(s, page, object, "Freelist Pointer check fails");
goto bad;
}
if (!check_object(s, page, object, SLUB_RED_INACTIVE))
goto bad;
/* Success perform special debug activities for allocs */
if (s->flags & SLAB_STORE_USER)
set_track(s, object, TRACK_ALLOC, addr);
trace(s, page, object, 1);
init_object(s, object, SLUB_RED_ACTIVE);
return 1;
bad:
if (PageSlab(page)) {
/*
* If this is a slab page then lets do the best we can
* to avoid issues in the future. Marking all objects
* as used avoids touching the remaining objects.
*/
slab_fix(s, "Marking all objects used");
page->inuse = page->objects;
page->freelist = NULL;
}
return 0;
}
static noinline struct kmem_cache_node *free_debug_processing(
struct kmem_cache *s, struct page *page, void *object,
unsigned long addr, unsigned long *flags)
{
struct kmem_cache_node *n = get_node(s, page_to_nid(page));
spin_lock_irqsave(&n->list_lock, *flags);
slab_lock(page);
if (!check_slab(s, page))
goto fail;
if (!check_valid_pointer(s, page, object)) {
slab_err(s, page, "Invalid object pointer 0x%p", object);
goto fail;
}
if (on_freelist(s, page, object)) {
object_err(s, page, object, "Object already free");
goto fail;
}
if (!check_object(s, page, object, SLUB_RED_ACTIVE))
goto out;
if (unlikely(s != page->slab_cache)) {
if (!PageSlab(page)) {
slab_err(s, page, "Attempt to free object(0x%p) "
"outside of slab", object);
} else if (!page->slab_cache) {
pr_err("SLUB <none>: no slab for object 0x%p.\n",
object);
dump_stack();
} else
object_err(s, page, object,
"page slab pointer corrupt.");
goto fail;
}
if (s->flags & SLAB_STORE_USER)
set_track(s, object, TRACK_FREE, addr);
trace(s, page, object, 0);
init_object(s, object, SLUB_RED_INACTIVE);
out:
slab_unlock(page);
/*
* Keep node_lock to preserve integrity
* until the object is actually freed
*/
return n;
fail:
slab_unlock(page);
spin_unlock_irqrestore(&n->list_lock, *flags);
slab_fix(s, "Object at 0x%p not freed", object);
return NULL;
}
static int __init setup_slub_debug(char *str)
{
slub_debug = DEBUG_DEFAULT_FLAGS;
if (*str++ != '=' || !*str)
/*
* No options specified. Switch on full debugging.
*/
goto out;
if (*str == ',')
/*
* No options but restriction on slabs. This means full
* debugging for slabs matching a pattern.
*/
goto check_slabs;
slub_debug = 0;
if (*str == '-')
/*
* Switch off all debugging measures.
*/
goto out;
/*
* Determine which debug features should be switched on
*/
for (; *str && *str != ','; str++) {
switch (tolower(*str)) {
case 'f':
slub_debug |= SLAB_DEBUG_FREE;
break;
case 'z':
slub_debug |= SLAB_RED_ZONE;
break;
case 'p':
slub_debug |= SLAB_POISON;
break;
case 'u':
slub_debug |= SLAB_STORE_USER;
break;
case 't':
slub_debug |= SLAB_TRACE;
break;
case 'a':
slub_debug |= SLAB_FAILSLAB;
break;
case 'o':
/*
* Avoid enabling debugging on caches if its minimum
* order would increase as a result.
*/
disable_higher_order_debug = 1;
break;
default:
pr_err("slub_debug option '%c' unknown. skipped\n",
*str);
}
}
check_slabs:
if (*str == ',')
slub_debug_slabs = str + 1;
out:
return 1;
}
__setup("slub_debug", setup_slub_debug);
unsigned long kmem_cache_flags(unsigned long object_size,
unsigned long flags, const char *name,
void (*ctor)(void *))
{
/*
* Enable debugging if selected on the kernel commandline.
*/
if (slub_debug && (!slub_debug_slabs || (name &&
!strncmp(slub_debug_slabs, name, strlen(slub_debug_slabs)))))
flags |= slub_debug;
return flags;
}
#else
static inline void setup_object_debug(struct kmem_cache *s,
struct page *page, void *object) {}
static inline int alloc_debug_processing(struct kmem_cache *s,
struct page *page, void *object, unsigned long addr) { return 0; }
static inline struct kmem_cache_node *free_debug_processing(
struct kmem_cache *s, struct page *page, void *object,
unsigned long addr, unsigned long *flags) { return NULL; }
static inline int slab_pad_check(struct kmem_cache *s, struct page *page)
{ return 1; }
static inline int check_object(struct kmem_cache *s, struct page *page,
void *object, u8 val) { return 1; }
static inline void add_full(struct kmem_cache *s, struct kmem_cache_node *n,
struct page *page) {}
static inline void remove_full(struct kmem_cache *s, struct kmem_cache_node *n,
struct page *page) {}
unsigned long kmem_cache_flags(unsigned long object_size,
unsigned long flags, const char *name,
void (*ctor)(void *))
{
return flags;
}
#define slub_debug 0
#define disable_higher_order_debug 0
static inline unsigned long slabs_node(struct kmem_cache *s, int node)
{ return 0; }
static inline unsigned long node_nr_slabs(struct kmem_cache_node *n)
{ return 0; }
static inline void inc_slabs_node(struct kmem_cache *s, int node,
int objects) {}
static inline void dec_slabs_node(struct kmem_cache *s, int node,
int objects) {}
#endif /* CONFIG_SLUB_DEBUG */
/*
* Hooks for other subsystems that check memory allocations. In a typical
* production configuration these hooks all should produce no code at all.
*/
static inline void kmalloc_large_node_hook(void *ptr, size_t size, gfp_t flags)
{
kmemleak_alloc(ptr, size, 1, flags);
kasan_kmalloc_large(ptr, size);
}
static inline void kfree_hook(const void *x)
{
kmemleak_free(x);
kasan_kfree_large(x);
}
static inline struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s,
gfp_t flags)
{
flags &= gfp_allowed_mask;
lockdep_trace_alloc(flags);
might_sleep_if(flags & __GFP_WAIT);
if (should_failslab(s->object_size, flags, s->flags))
return NULL;
return memcg_kmem_get_cache(s, flags);
}
static inline void slab_post_alloc_hook(struct kmem_cache *s,
gfp_t flags, void *object)
{
flags &= gfp_allowed_mask;
kmemcheck_slab_alloc(s, flags, object, slab_ksize(s));
kmemleak_alloc_recursive(object, s->object_size, 1, s->flags, flags);
memcg_kmem_put_cache(s);
kasan_slab_alloc(s, object);
}
static inline void slab_free_hook(struct kmem_cache *s, void *x)
{
kmemleak_free_recursive(x, s->flags);
/*
* Trouble is that we may no longer disable interrupts in the fast path
* So in order to make the debug calls that expect irqs to be
* disabled we need to disable interrupts temporarily.
*/
#if defined(CONFIG_KMEMCHECK) || defined(CONFIG_LOCKDEP)
{
unsigned long flags;
local_irq_save(flags);
kmemcheck_slab_free(s, x, s->object_size);
debug_check_no_locks_freed(x, s->object_size);
local_irq_restore(flags);
}
#endif
if (!(s->flags & SLAB_DEBUG_OBJECTS))
debug_check_no_obj_freed(x, s->object_size);
kasan_slab_free(s, x);
}
/*
* Slab allocation and freeing
*/
static inline struct page *alloc_slab_page(struct kmem_cache *s,
gfp_t flags, int node, struct kmem_cache_order_objects oo)
{
struct page *page;
int order = oo_order(oo);
flags |= __GFP_NOTRACK;
if (memcg_charge_slab(s, flags, order))
return NULL;
if (node == NUMA_NO_NODE)
page = alloc_pages(flags, order);
else
page = alloc_pages_exact_node(node, flags, order);
if (!page)
memcg_uncharge_slab(s, order);
return page;
}
static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
{
struct page *page;
struct kmem_cache_order_objects oo = s->oo;
gfp_t alloc_gfp;
flags &= gfp_allowed_mask;
if (flags & __GFP_WAIT)
local_irq_enable();
flags |= s->allocflags;
/*
* Let the initial higher-order allocation fail under memory pressure
* so we fall-back to the minimum order allocation.
*/
alloc_gfp = (flags | __GFP_NOWARN | __GFP_NORETRY) & ~__GFP_NOFAIL;
page = alloc_slab_page(s, alloc_gfp, node, oo);
if (unlikely(!page)) {
oo = s->min;
alloc_gfp = flags;
/*
* Allocation may have failed due to fragmentation.
* Try a lower order alloc if possible
*/
page = alloc_slab_page(s, alloc_gfp, node, oo);
if (page)
stat(s, ORDER_FALLBACK);
}
if (kmemcheck_enabled && page
&& !(s->flags & (SLAB_NOTRACK | DEBUG_DEFAULT_FLAGS))) {
int pages = 1 << oo_order(oo);
kmemcheck_alloc_shadow(page, oo_order(oo), alloc_gfp, node);
/*
* Objects from caches that have a constructor don't get
* cleared when they're allocated, so we need to do it here.
*/
if (s->ctor)
kmemcheck_mark_uninitialized_pages(page, pages);
else
kmemcheck_mark_unallocated_pages(page, pages);
}
if (flags & __GFP_WAIT)
local_irq_disable();
if (!page)
return NULL;
page->objects = oo_objects(oo);
mod_zone_page_state(page_zone(page),
(s->flags & SLAB_RECLAIM_ACCOUNT) ?
NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE,
1 << oo_order(oo));
return page;
}
static void setup_object(struct kmem_cache *s, struct page *page,
void *object)
{
setup_object_debug(s, page, object);
if (unlikely(s->ctor)) {
kasan_unpoison_object_data(s, object);
s->ctor(object);
kasan_poison_object_data(s, object);
}
}
static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
{
struct page *page;
void *start;
void *p;
int order;
int idx;
if (unlikely(flags & GFP_SLAB_BUG_MASK)) {
pr_emerg("gfp: %u\n", flags & GFP_SLAB_BUG_MASK);
BUG();
}
page = allocate_slab(s,
flags & (GFP_RECLAIM_MASK | GFP_CONSTRAINT_MASK), node);
if (!page)
goto out;
order = compound_order(page);
inc_slabs_node(s, page_to_nid(page), page->objects);
page->slab_cache = s;
__SetPageSlab(page);
if (page_is_pfmemalloc(page))
SetPageSlabPfmemalloc(page);
start = page_address(page);
if (unlikely(s->flags & SLAB_POISON))
memset(start, POISON_INUSE, PAGE_SIZE << order);
kasan_poison_slab(page);
for_each_object_idx(p, idx, s, start, page->objects) {
setup_object(s, page, p);
if (likely(idx < page->objects))
set_freepointer(s, p, p + s->size);
else
set_freepointer(s, p, NULL);
}
page->freelist = start;
page->inuse = page->objects;
page->frozen = 1;
out:
return page;
}
static void __free_slab(struct kmem_cache *s, struct page *page)
{
int order = compound_order(page);
int pages = 1 << order;
if (kmem_cache_debug(s)) {
void *p;
slab_pad_check(s, page);
for_each_object(p, s, page_address(page),
page->objects)
check_object(s, page, p, SLUB_RED_INACTIVE);
}
kmemcheck_free_shadow(page, compound_order(page));
mod_zone_page_state(page_zone(page),
(s->flags & SLAB_RECLAIM_ACCOUNT) ?
NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE,
-pages);
__ClearPageSlabPfmemalloc(page);
__ClearPageSlab(page);
page_mapcount_reset(page);
if (current->reclaim_state)
current->reclaim_state->reclaimed_slab += pages;
__free_pages(page, order);
memcg_uncharge_slab(s, order);
}
#define need_reserve_slab_rcu \
(sizeof(((struct page *)NULL)->lru) < sizeof(struct rcu_head))
static void rcu_free_slab(struct rcu_head *h)
{
struct page *page;
if (need_reserve_slab_rcu)
page = virt_to_head_page(h);
else
page = container_of((struct list_head *)h, struct page, lru);
__free_slab(page->slab_cache, page);
}
static void free_slab(struct kmem_cache *s, struct page *page)
{
if (unlikely(s->flags & SLAB_DESTROY_BY_RCU)) {
struct rcu_head *head;
if (need_reserve_slab_rcu) {
int order = compound_order(page);
int offset = (PAGE_SIZE << order) - s->reserved;
VM_BUG_ON(s->reserved != sizeof(*head));
head = page_address(page) + offset;
} else {
/*
* RCU free overloads the RCU head over the LRU
*/
head = (void *)&page->lru;
}
call_rcu(head, rcu_free_slab);
} else
__free_slab(s, page);
}
static void discard_slab(struct kmem_cache *s, struct page *page)
{
dec_slabs_node(s, page_to_nid(page), page->objects);
free_slab(s, page);
}
/*
* Management of partially allocated slabs.
*/
static inline void
__add_partial(struct kmem_cache_node *n, struct page *page, int tail)
{
n->nr_partial++;
if (tail == DEACTIVATE_TO_TAIL)
list_add_tail(&page->lru, &n->partial);
else
list_add(&page->lru, &n->partial);
}
static inline void add_partial(struct kmem_cache_node *n,
struct page *page, int tail)
{
lockdep_assert_held(&n->list_lock);
__add_partial(n, page, tail);
}
static inline void
__remove_partial(struct kmem_cache_node *n, struct page *page)
{
list_del(&page->lru);
n->nr_partial--;
}
static inline void remove_partial(struct kmem_cache_node *n,
struct page *page)
{
lockdep_assert_held(&n->list_lock);
__remove_partial(n, page);
}
/*
* Remove slab from the partial list, freeze it and
* return the pointer to the freelist.
*
* Returns a list of objects or NULL if it fails.
*/
static inline void *acquire_slab(struct kmem_cache *s,
struct kmem_cache_node *n, struct page *page,
int mode, int *objects)
{
void *freelist;
unsigned long counters;
struct page new;
lockdep_assert_held(&n->list_lock);
/*
* Zap the freelist and set the frozen bit.
* The old freelist is the list of objects for the
* per cpu allocation list.
*/
freelist = page->freelist;
counters = page->counters;
new.counters = counters;
*objects = new.objects - new.inuse;
if (mode) {
new.inuse = page->objects;
new.freelist = NULL;
} else {
new.freelist = freelist;
}
VM_BUG_ON(new.frozen);
new.frozen = 1;
if (!__cmpxchg_double_slab(s, page,
freelist, counters,
new.freelist, new.counters,
"acquire_slab"))
return NULL;
remove_partial(n, page);
WARN_ON(!freelist);
return freelist;
}
static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain);
static inline bool pfmemalloc_match(struct page *page, gfp_t gfpflags);
/*
* Try to allocate a partial slab from a specific node.
*/
static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n,
struct kmem_cache_cpu *c, gfp_t flags)
{
struct page *page, *page2;
void *object = NULL;
int available = 0;
int objects;
/*
* Racy check. If we mistakenly see no partial slabs then we
* just allocate an empty slab. If we mistakenly try to get a
* partial slab and there is none available then get_partials()
* will return NULL.
*/
if (!n || !n->nr_partial)
return NULL;
spin_lock(&n->list_lock);
list_for_each_entry_safe(page, page2, &n->partial, lru) {
void *t;
if (!pfmemalloc_match(page, flags))
continue;
t = acquire_slab(s, n, page, object == NULL, &objects);
if (!t)
break;
available += objects;
if (!object) {
c->page = page;
stat(s, ALLOC_FROM_PARTIAL);
object = t;
} else {
put_cpu_partial(s, page, 0);
stat(s, CPU_PARTIAL_NODE);
}
if (!kmem_cache_has_cpu_partial(s)
|| available > s->cpu_partial / 2)
break;
}
spin_unlock(&n->list_lock);
return object;
}
/*
* Get a page from somewhere. Search in increasing NUMA distances.
*/
static void *get_any_partial(struct kmem_cache *s, gfp_t flags,
struct kmem_cache_cpu *c)
{
#ifdef CONFIG_NUMA
struct zonelist *zonelist;
struct zoneref *z;
struct zone *zone;
enum zone_type high_zoneidx = gfp_zone(flags);
void *object;
unsigned int cpuset_mems_cookie;
/*
* The defrag ratio allows a configuration of the tradeoffs between
* inter node defragmentation and node local allocations. A lower
* defrag_ratio increases the tendency to do local allocations
* instead of attempting to obtain partial slabs from other nodes.
*
* If the defrag_ratio is set to 0 then kmalloc() always
* returns node local objects. If the ratio is higher then kmalloc()
* may return off node objects because partial slabs are obtained
* from other nodes and filled up.
*
* If /sys/kernel/slab/xx/defrag_ratio is set to 100 (which makes
* defrag_ratio = 1000) then every (well almost) allocation will
* first attempt to defrag slab caches on other nodes. This means
* scanning over all nodes to look for partial slabs which may be
* expensive if we do it every time we are trying to find a slab
* with available objects.
*/
if (!s->remote_node_defrag_ratio ||
get_cycles() % 1024 > s->remote_node_defrag_ratio)
return NULL;
do {
cpuset_mems_cookie = read_mems_allowed_begin();
zonelist = node_zonelist(mempolicy_slab_node(), flags);
for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
struct kmem_cache_node *n;
n = get_node(s, zone_to_nid(zone));
if (n && cpuset_zone_allowed(zone, flags) &&
n->nr_partial > s->min_partial) {
object = get_partial_node(s, n, c, flags);
if (object) {
/*
* Don't check read_mems_allowed_retry()
* here - if mems_allowed was updated in
* parallel, that was a harmless race
* between allocation and the cpuset
* update
*/
return object;
}
}
}
} while (read_mems_allowed_retry(cpuset_mems_cookie));
#endif
return NULL;
}
/*
* Get a partial page, lock it and return it.
*/
static void *get_partial(struct kmem_cache *s, gfp_t flags, int node,
struct kmem_cache_cpu *c)
{
void *object;
int searchnode = node;
if (node == NUMA_NO_NODE)
searchnode = numa_mem_id();
else if (!node_present_pages(node))
searchnode = node_to_mem_node(node);
object = get_partial_node(s, get_node(s, searchnode), c, flags);
if (object || node != NUMA_NO_NODE)
return object;
return get_any_partial(s, flags, c);
}
#ifdef CONFIG_PREEMPT
/*
* Calculate the next globally unique transaction for disambiguiation
* during cmpxchg. The transactions start with the cpu number and are then
* incremented by CONFIG_NR_CPUS.
*/
#define TID_STEP roundup_pow_of_two(CONFIG_NR_CPUS)
#else
/*
* No preemption supported therefore also no need to check for
* different cpus.
*/
#define TID_STEP 1
#endif
static inline unsigned long next_tid(unsigned long tid)
{
return tid + TID_STEP;
}
static inline unsigned int tid_to_cpu(unsigned long tid)
{
return tid % TID_STEP;
}
static inline unsigned long tid_to_event(unsigned long tid)
{
return tid / TID_STEP;
}
static inline unsigned int init_tid(int cpu)
{
return cpu;
}
static inline void note_cmpxchg_failure(const char *n,
const struct kmem_cache *s, unsigned long tid)
{
#ifdef SLUB_DEBUG_CMPXCHG
unsigned long actual_tid = __this_cpu_read(s->cpu_slab->tid);
pr_info("%s %s: cmpxchg redo ", n, s->name);
#ifdef CONFIG_PREEMPT
if (tid_to_cpu(tid) != tid_to_cpu(actual_tid))
pr_warn("due to cpu change %d -> %d\n",
tid_to_cpu(tid), tid_to_cpu(actual_tid));
else
#endif
if (tid_to_event(tid) != tid_to_event(actual_tid))
pr_warn("due to cpu running other code. Event %ld->%ld\n",
tid_to_event(tid), tid_to_event(actual_tid));
else
pr_warn("for unknown reason: actual=%lx was=%lx target=%lx\n",
actual_tid, tid, next_tid(tid));
#endif
stat(s, CMPXCHG_DOUBLE_CPU_FAIL);
}
static void init_kmem_cache_cpus(struct kmem_cache *s)
{
int cpu;
for_each_possible_cpu(cpu)
per_cpu_ptr(s->cpu_slab, cpu)->tid = init_tid(cpu);
}
/*
* Remove the cpu slab
*/
static void deactivate_slab(struct kmem_cache *s, struct page *page,
void *freelist)
{
enum slab_modes { M_NONE, M_PARTIAL, M_FULL, M_FREE };
struct kmem_cache_node *n = get_node(s, page_to_nid(page));
int lock = 0;
enum slab_modes l = M_NONE, m = M_NONE;
void *nextfree;
int tail = DEACTIVATE_TO_HEAD;
struct page new;
struct page old;
if (page->freelist) {
stat(s, DEACTIVATE_REMOTE_FREES);
tail = DEACTIVATE_TO_TAIL;
}
/*
* Stage one: Free all available per cpu objects back
* to the page freelist while it is still frozen. Leave the
* last one.
*
* There is no need to take the list->lock because the page
* is still frozen.
*/
while (freelist && (nextfree = get_freepointer(s, freelist))) {
void *prior;
unsigned long counters;
do {
prior = page->freelist;
counters = page->counters;
set_freepointer(s, freelist, prior);
new.counters = counters;
new.inuse--;
VM_BUG_ON(!new.frozen);
} while (!__cmpxchg_double_slab(s, page,
prior, counters,
freelist, new.counters,
"drain percpu freelist"));
freelist = nextfree;
}
/*
* Stage two: Ensure that the page is unfrozen while the
* list presence reflects the actual number of objects
* during unfreeze.
*
* We setup the list membership and then perform a cmpxchg
* with the count. If there is a mismatch then the page
* is not unfrozen but the page is on the wrong list.
*
* Then we restart the process which may have to remove
* the page from the list that we just put it on again
* because the number of objects in the slab may have
* changed.
*/
redo:
old.freelist = page->freelist;
old.counters = page->counters;
VM_BUG_ON(!old.frozen);
/* Determine target state of the slab */
new.counters = old.counters;
if (freelist) {
new.inuse--;
set_freepointer(s, freelist, old.freelist);
new.freelist = freelist;
} else
new.freelist = old.freelist;
new.frozen = 0;
if (!new.inuse && n->nr_partial >= s->min_partial)
m = M_FREE;
else if (new.freelist) {
m = M_PARTIAL;
if (!lock) {
lock = 1;
/*
* Taking the spinlock removes the possiblity
* that acquire_slab() will see a slab page that
* is frozen
*/
spin_lock(&n->list_lock);
}
} else {
m = M_FULL;
if (kmem_cache_debug(s) && !lock) {
lock = 1;
/*
* This also ensures that the scanning of full
* slabs from diagnostic functions will not see
* any frozen slabs.
*/
spin_lock(&n->list_lock);
}
}
if (l != m) {
if (l == M_PARTIAL)
remove_partial(n, page);
else if (l == M_FULL)
remove_full(s, n, page);
if (m == M_PARTIAL) {
add_partial(n, page, tail);
stat(s, tail);
} else if (m == M_FULL) {
stat(s, DEACTIVATE_FULL);
add_full(s, n, page);
}
}
l = m;
if (!__cmpxchg_double_slab(s, page,
old.freelist, old.counters,
new.freelist, new.counters,
"unfreezing slab"))
goto redo;
if (lock)
spin_unlock(&n->list_lock);
if (m == M_FREE) {
stat(s, DEACTIVATE_EMPTY);
discard_slab(s, page);
stat(s, FREE_SLAB);
}
}
/*
* Unfreeze all the cpu partial slabs.
*
* This function must be called with interrupts disabled
* for the cpu using c (or some other guarantee must be there
* to guarantee no concurrent accesses).
*/
static void unfreeze_partials(struct kmem_cache *s,
struct kmem_cache_cpu *c)
{
#ifdef CONFIG_SLUB_CPU_PARTIAL
struct kmem_cache_node *n = NULL, *n2 = NULL;
struct page *page, *discard_page = NULL;
while ((page = c->partial)) {
struct page new;
struct page old;
c->partial = page->next;
n2 = get_node(s, page_to_nid(page));
if (n != n2) {
if (n)
spin_unlock(&n->list_lock);
n = n2;
spin_lock(&n->list_lock);
}
do {
old.freelist = page->freelist;
old.counters = page->counters;
VM_BUG_ON(!old.frozen);
new.counters = old.counters;
new.freelist = old.freelist;
new.frozen = 0;
} while (!__cmpxchg_double_slab(s, page,
old.freelist, old.counters,
new.freelist, new.counters,
"unfreezing slab"));
if (unlikely(!new.inuse && n->nr_partial >= s->min_partial)) {
page->next = discard_page;
discard_page = page;
} else {
add_partial(n, page, DEACTIVATE_TO_TAIL);
stat(s, FREE_ADD_PARTIAL);
}
}
if (n)
spin_unlock(&n->list_lock);
while (discard_page) {
page = discard_page;
discard_page = discard_page->next;
stat(s, DEACTIVATE_EMPTY);
discard_slab(s, page);
stat(s, FREE_SLAB);
}
#endif
}
/*
* Put a page that was just frozen (in __slab_free) into a partial page
* slot if available. This is done without interrupts disabled and without
* preemption disabled. The cmpxchg is racy and may put the partial page
* onto a random cpus partial slot.
*
* If we did not find a slot then simply move all the partials to the
* per node partial list.
*/
static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
{
#ifdef CONFIG_SLUB_CPU_PARTIAL
struct page *oldpage;
int pages;
int pobjects;
preempt_disable();
do {
pages = 0;
pobjects = 0;
oldpage = this_cpu_read(s->cpu_slab->partial);
if (oldpage) {
pobjects = oldpage->pobjects;
pages = oldpage->pages;
if (drain && pobjects > s->cpu_partial) {
unsigned long flags;
/*
* partial array is full. Move the existing
* set to the per node partial list.
*/
local_irq_save(flags);
unfreeze_partials(s, this_cpu_ptr(s->cpu_slab));
local_irq_restore(flags);
oldpage = NULL;
pobjects = 0;
pages = 0;
stat(s, CPU_PARTIAL_DRAIN);
}
}
pages++;
pobjects += page->objects - page->inuse;
page->pages = pages;
page->pobjects = pobjects;
page->next = oldpage;
} while (this_cpu_cmpxchg(s->cpu_slab->partial, oldpage, page)
!= oldpage);
if (unlikely(!s->cpu_partial)) {
unsigned long flags;
local_irq_save(flags);
unfreeze_partials(s, this_cpu_ptr(s->cpu_slab));
local_irq_restore(flags);
}
preempt_enable();
#endif
}
static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)
{
stat(s, CPUSLAB_FLUSH);
deactivate_slab(s, c->page, c->freelist);
c->tid = next_tid(c->tid);
c->page = NULL;
c->freelist = NULL;
}
/*
* Flush cpu slab.
*
* Called from IPI handler with interrupts disabled.
*/
static inline void __flush_cpu_slab(struct kmem_cache *s, int cpu)
{
struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu);
if (likely(c)) {
if (c->page)
flush_slab(s, c);
unfreeze_partials(s, c);
}
}
static void flush_cpu_slab(void *d)
{
struct kmem_cache *s = d;
__flush_cpu_slab(s, smp_processor_id());
}
static bool has_cpu_slab(int cpu, void *info)
{
struct kmem_cache *s = info;
struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu);
return c->page || c->partial;
}
static void flush_all(struct kmem_cache *s)
{
on_each_cpu_cond(has_cpu_slab, flush_cpu_slab, s, 1, GFP_ATOMIC);
}
/*
* Check if the objects in a per cpu structure fit numa
* locality expectations.
*/
static inline int node_match(struct page *page, int node)
{
#ifdef CONFIG_NUMA
if (!page || (node != NUMA_NO_NODE && page_to_nid(page) != node))
return 0;
#endif
return 1;
}
#ifdef CONFIG_SLUB_DEBUG
static int count_free(struct page *page)
{
return page->objects - page->inuse;
}
static inline unsigned long node_nr_objs(struct kmem_cache_node *n)
{
return atomic_long_read(&n->total_objects);
}
#endif /* CONFIG_SLUB_DEBUG */
#if defined(CONFIG_SLUB_DEBUG) || defined(CONFIG_SYSFS)
static unsigned long count_partial(struct kmem_cache_node *n,
int (*get_count)(struct page *))
{
unsigned long flags;
unsigned long x = 0;
struct page *page;
spin_lock_irqsave(&n->list_lock, flags);
list_for_each_entry(page, &n->partial, lru)
x += get_count(page);
spin_unlock_irqrestore(&n->list_lock, flags);
return x;
}
#endif /* CONFIG_SLUB_DEBUG || CONFIG_SYSFS */
static noinline void
slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid)
{
#ifdef CONFIG_SLUB_DEBUG
static DEFINE_RATELIMIT_STATE(slub_oom_rs, DEFAULT_RATELIMIT_INTERVAL,
DEFAULT_RATELIMIT_BURST);
int node;
struct kmem_cache_node *n;
if ((gfpflags & __GFP_NOWARN) || !__ratelimit(&slub_oom_rs))
return;
pr_warn("SLUB: Unable to allocate memory on node %d (gfp=0x%x)\n",
nid, gfpflags);
pr_warn(" cache: %s, object size: %d, buffer size: %d, default order: %d, min order: %d\n",
s->name, s->object_size, s->size, oo_order(s->oo),
oo_order(s->min));
if (oo_order(s->min) > get_order(s->object_size))
pr_warn(" %s debugging increased min order, use slub_debug=O to disable.\n",
s->name);
for_each_kmem_cache_node(s, node, n) {
unsigned long nr_slabs;
unsigned long nr_objs;
unsigned long nr_free;
nr_free = count_partial(n, count_free);
nr_slabs = node_nr_slabs(n);
nr_objs = node_nr_objs(n);
pr_warn(" node %d: slabs: %ld, objs: %ld, free: %ld\n",
node, nr_slabs, nr_objs, nr_free);
}
#endif
}
static inline void *new_slab_objects(struct kmem_cache *s, gfp_t flags,
int node, struct kmem_cache_cpu **pc)
{
void *freelist;
struct kmem_cache_cpu *c = *pc;
struct page *page;
freelist = get_partial(s, flags, node, c);
if (freelist)
return freelist;
page = new_slab(s, flags, node);
if (page) {
c = raw_cpu_ptr(s->cpu_slab);
if (c->page)
flush_slab(s, c);
/*
* No other reference to the page yet so we can
* muck around with it freely without cmpxchg
*/
freelist = page->freelist;
page->freelist = NULL;
stat(s, ALLOC_SLAB);
c->page = page;
*pc = c;
} else
freelist = NULL;
return freelist;
}
static inline bool pfmemalloc_match(struct page *page, gfp_t gfpflags)
{
if (unlikely(PageSlabPfmemalloc(page)))
return gfp_pfmemalloc_allowed(gfpflags);
return true;
}
/*
* Check the page->freelist of a page and either transfer the freelist to the
* per cpu freelist or deactivate the page.
*
* The page is still frozen if the return value is not NULL.
*
* If this function returns NULL then the page has been unfrozen.
*
* This function must be called with interrupt disabled.
*/
static inline void *get_freelist(struct kmem_cache *s, struct page *page)
{
struct page new;
unsigned long counters;
void *freelist;
do {
freelist = page->freelist;
counters = page->counters;
new.counters = counters;
VM_BUG_ON(!new.frozen);
new.inuse = page->objects;
new.frozen = freelist != NULL;
} while (!__cmpxchg_double_slab(s, page,
freelist, counters,
NULL, new.counters,
"get_freelist"));
return freelist;
}
/*
* Slow path. The lockless freelist is empty or we need to perform
* debugging duties.
*
* Processing is still very fast if new objects have been freed to the
* regular freelist. In that case we simply take over the regular freelist
* as the lockless freelist and zap the regular freelist.
*
* If that is not working then we fall back to the partial lists. We take the
* first element of the freelist as the object to allocate now and move the
* rest of the freelist to the lockless freelist.
*
* And if we were unable to get a new slab from the partial slab lists then
* we need to allocate a new slab. This is the slowest path since it involves
* a call to the page allocator and the setup of a new slab.
*/
static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
unsigned long addr, struct kmem_cache_cpu *c)
{
void *freelist;
struct page *page;
unsigned long flags;
local_irq_save(flags);
#ifdef CONFIG_PREEMPT
/*
* We may have been preempted and rescheduled on a different
* cpu before disabling interrupts. Need to reload cpu area
* pointer.
*/
c = this_cpu_ptr(s->cpu_slab);
#endif
page = c->page;
if (!page)
goto new_slab;
redo:
if (unlikely(!node_match(page, node))) {
int searchnode = node;
if (node != NUMA_NO_NODE && !node_present_pages(node))
searchnode = node_to_mem_node(node);
if (unlikely(!node_match(page, searchnode))) {
stat(s, ALLOC_NODE_MISMATCH);
deactivate_slab(s, page, c->freelist);
c->page = NULL;
c->freelist = NULL;
goto new_slab;
}
}
/*
* By rights, we should be searching for a slab page that was
* PFMEMALLOC but right now, we are losing the pfmemalloc
* information when the page leaves the per-cpu allocator
*/
if (unlikely(!pfmemalloc_match(page, gfpflags))) {
deactivate_slab(s, page, c->freelist);
c->page = NULL;
c->freelist = NULL;
goto new_slab;
}
/* must check again c->freelist in case of cpu migration or IRQ */
freelist = c->freelist;
if (freelist)
goto load_freelist;
freelist = get_freelist(s, page);
if (!freelist) {
c->page = NULL;
stat(s, DEACTIVATE_BYPASS);
goto new_slab;
}
stat(s, ALLOC_REFILL);
load_freelist:
/*
* freelist is pointing to the list of objects to be used.
* page is pointing to the page from which the objects are obtained.
* That page must be frozen for per cpu allocations to work.
*/
VM_BUG_ON(!c->page->frozen);
c->freelist = get_freepointer(s, freelist);
c->tid = next_tid(c->tid);
local_irq_restore(flags);
return freelist;
new_slab:
if (c->partial) {
page = c->page = c->partial;
c->partial = page->next;
stat(s, CPU_PARTIAL_ALLOC);
c->freelist = NULL;
goto redo;
}
freelist = new_slab_objects(s, gfpflags, node, &c);
if (unlikely(!freelist)) {
slab_out_of_memory(s, gfpflags, node);
local_irq_restore(flags);
return NULL;
}
page = c->page;
if (likely(!kmem_cache_debug(s) && pfmemalloc_match(page, gfpflags)))
goto load_freelist;
/* Only entered in the debug case */
if (kmem_cache_debug(s) &&
!alloc_debug_processing(s, page, freelist, addr))
goto new_slab; /* Slab failed checks. Next slab needed */
deactivate_slab(s, page, get_freepointer(s, freelist));
c->page = NULL;
c->freelist = NULL;
local_irq_restore(flags);
return freelist;
}
/*
* Inlined fastpath so that allocation functions (kmalloc, kmem_cache_alloc)
* have the fastpath folded into their functions. So no function call
* overhead for requests that can be satisfied on the fastpath.
*
* The fastpath works by first checking if the lockless freelist can be used.
* If not then __slab_alloc is called for slow processing.
*
* Otherwise we can simply pick the next object from the lockless free list.
*/
static __always_inline void *slab_alloc_node(struct kmem_cache *s,
gfp_t gfpflags, int node, unsigned long addr)
{
void **object;
struct kmem_cache_cpu *c;
struct page *page;
unsigned long tid;
s = slab_pre_alloc_hook(s, gfpflags);
if (!s)
return NULL;
redo:
/*
* Must read kmem_cache cpu data via this cpu ptr. Preemption is
* enabled. We may switch back and forth between cpus while
* reading from one cpu area. That does not matter as long
* as we end up on the original cpu again when doing the cmpxchg.
*
* We should guarantee that tid and kmem_cache are retrieved on
* the same cpu. It could be different if CONFIG_PREEMPT so we need
* to check if it is matched or not.
*/
do {
tid = this_cpu_read(s->cpu_slab->tid);
c = raw_cpu_ptr(s->cpu_slab);
} while (IS_ENABLED(CONFIG_PREEMPT) &&
unlikely(tid != READ_ONCE(c->tid)));
/*
* Irqless object alloc/free algorithm used here depends on sequence
* of fetching cpu_slab's data. tid should be fetched before anything
* on c to guarantee that object and page associated with previous tid
* won't be used with current tid. If we fetch tid first, object and
* page could be one associated with next tid and our alloc/free
* request will be failed. In this case, we will retry. So, no problem.
*/
barrier();
/*
* The transaction ids are globally unique per cpu and per operation on
* a per cpu queue. Thus they can be guarantee that the cmpxchg_double
* occurs on the right processor and that there was no operation on the
* linked list in between.
*/
object = c->freelist;
page = c->page;
if (unlikely(!object || !node_match(page, node))) {
object = __slab_alloc(s, gfpflags, node, addr, c);
stat(s, ALLOC_SLOWPATH);
} else {
void *next_object = get_freepointer_safe(s, object);
/*
* The cmpxchg will only match if there was no additional
* operation and if we are on the right processor.
*
* The cmpxchg does the following atomically (without lock
* semantics!)
* 1. Relocate first pointer to the current per cpu area.
* 2. Verify that tid and freelist have not been changed
* 3. If they were not changed replace tid and freelist
*
* Since this is without lock semantics the protection is only
* against code executing on this cpu *not* from access by
* other cpus.
*/
if (unlikely(!this_cpu_cmpxchg_double(
s->cpu_slab->freelist, s->cpu_slab->tid,
object, tid,
next_object, next_tid(tid)))) {
note_cmpxchg_failure("slab_alloc", s, tid);
goto redo;
}
prefetch_freepointer(s, next_object);
stat(s, ALLOC_FASTPATH);
}
if (unlikely(gfpflags & __GFP_ZERO) && object)
memset(object, 0, s->object_size);
slab_post_alloc_hook(s, gfpflags, object);
return object;
}
static __always_inline void *slab_alloc(struct kmem_cache *s,
gfp_t gfpflags, unsigned long addr)
{
return slab_alloc_node(s, gfpflags, NUMA_NO_NODE, addr);
}
void *kmem_cache_alloc(struct kmem_cache *s, gfp_t gfpflags)
{
void *ret = slab_alloc(s, gfpflags, _RET_IP_);
trace_kmem_cache_alloc(_RET_IP_, ret, s->object_size,
s->size, gfpflags);
return ret;
}
EXPORT_SYMBOL(kmem_cache_alloc);
#ifdef CONFIG_TRACING
void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t gfpflags, size_t size)
{
void *ret = slab_alloc(s, gfpflags, _RET_IP_);
trace_kmalloc(_RET_IP_, ret, size, s->size, gfpflags);
kasan_kmalloc(s, ret, size);
return ret;
}
EXPORT_SYMBOL(kmem_cache_alloc_trace);
#endif
#ifdef CONFIG_NUMA
void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t gfpflags, int node)
{
void *ret = slab_alloc_node(s, gfpflags, node, _RET_IP_);
trace_kmem_cache_alloc_node(_RET_IP_, ret,
s->object_size, s->size, gfpflags, node);
return ret;
}
EXPORT_SYMBOL(kmem_cache_alloc_node);
#ifdef CONFIG_TRACING
void *kmem_cache_alloc_node_trace(struct kmem_cache *s,
gfp_t gfpflags,
int node, size_t size)
{
void *ret = slab_alloc_node(s, gfpflags, node, _RET_IP_);
trace_kmalloc_node(_RET_IP_, ret,
size, s->size, gfpflags, node);
kasan_kmalloc(s, ret, size);
return ret;
}
EXPORT_SYMBOL(kmem_cache_alloc_node_trace);
#endif
#endif
/*
* Slow path handling. This may still be called frequently since objects
* have a longer lifetime than the cpu slabs in most processing loads.
*
* So we still attempt to reduce cache line usage. Just take the slab
* lock and free the item. If there is no additional partial page
* handling required then we can return immediately.
*/
static void __slab_free(struct kmem_cache *s, struct page *page,
void *x, unsigned long addr)
{
void *prior;
void **object = (void *)x;
int was_frozen;
struct page new;
unsigned long counters;
struct kmem_cache_node *n = NULL;
unsigned long uninitialized_var(flags);
stat(s, FREE_SLOWPATH);
if (kmem_cache_debug(s) &&
!(n = free_debug_processing(s, page, x, addr, &flags)))
return;
do {
if (unlikely(n)) {
spin_unlock_irqrestore(&n->list_lock, flags);
n = NULL;
}
prior = page->freelist;
counters = page->counters;
set_freepointer(s, object, prior);
new.counters = counters;
was_frozen = new.frozen;
new.inuse--;
if ((!new.inuse || !prior) && !was_frozen) {
if (kmem_cache_has_cpu_partial(s) && !prior) {
/*
* Slab was on no list before and will be
* partially empty
* We can defer the list move and instead
* freeze it.
*/
new.frozen = 1;
} else { /* Needs to be taken off a list */
n = get_node(s, page_to_nid(page));
/*
* Speculatively acquire the list_lock.
* If the cmpxchg does not succeed then we may
* drop the list_lock without any processing.
*
* Otherwise the list_lock will synchronize with
* other processors updating the list of slabs.
*/
spin_lock_irqsave(&n->list_lock, flags);
}
}
} while (!cmpxchg_double_slab(s, page,
prior, counters,
object, new.counters,
"__slab_free"));
if (likely(!n)) {
/*
* If we just froze the page then put it onto the
* per cpu partial list.
*/
if (new.frozen && !was_frozen) {
put_cpu_partial(s, page, 1);
stat(s, CPU_PARTIAL_FREE);
}
/*
* The list lock was not taken therefore no list
* activity can be necessary.
*/
if (was_frozen)
stat(s, FREE_FROZEN);
return;
}
if (unlikely(!new.inuse && n->nr_partial >= s->min_partial))
goto slab_empty;
/*
* Objects left in the slab. If it was not on the partial list before
* then add it.
*/
if (!kmem_cache_has_cpu_partial(s) && unlikely(!prior)) {
if (kmem_cache_debug(s))
remove_full(s, n, page);
add_partial(n, page, DEACTIVATE_TO_TAIL);
stat(s, FREE_ADD_PARTIAL);
}
spin_unlock_irqrestore(&n->list_lock, flags);
return;
slab_empty:
if (prior) {
/*
* Slab on the partial list.
*/
remove_partial(n, page);
stat(s, FREE_REMOVE_PARTIAL);
} else {
/* Slab must be on the full list */
remove_full(s, n, page);
}
spin_unlock_irqrestore(&n->list_lock, flags);
stat(s, FREE_SLAB);
discard_slab(s, page);
}
/*
* Fastpath with forced inlining to produce a kfree and kmem_cache_free that
* can perform fastpath freeing without additional function calls.
*
* The fastpath is only possible if we are freeing to the current cpu slab
* of this processor. This typically the case if we have just allocated
* the item before.
*
* If fastpath is not possible then fall back to __slab_free where we deal
* with all sorts of special processing.
*/
static __always_inline void slab_free(struct kmem_cache *s,
struct page *page, void *x, unsigned long addr)
{
void **object = (void *)x;
struct kmem_cache_cpu *c;
unsigned long tid;
slab_free_hook(s, x);
redo:
/*
* Determine the currently cpus per cpu slab.
* The cpu may change afterward. However that does not matter since
* data is retrieved via this pointer. If we are on the same cpu
* during the cmpxchg then the free will succedd.
*/
do {
tid = this_cpu_read(s->cpu_slab->tid);
c = raw_cpu_ptr(s->cpu_slab);
} while (IS_ENABLED(CONFIG_PREEMPT) &&
unlikely(tid != READ_ONCE(c->tid)));
/* Same with comment on barrier() in slab_alloc_node() */
barrier();
if (likely(page == c->page)) {
set_freepointer(s, object, c->freelist);
if (unlikely(!this_cpu_cmpxchg_double(
s->cpu_slab->freelist, s->cpu_slab->tid,
c->freelist, tid,
object, next_tid(tid)))) {
note_cmpxchg_failure("slab_free", s, tid);
goto redo;
}
stat(s, FREE_FASTPATH);
} else
__slab_free(s, page, x, addr);
}
void kmem_cache_free(struct kmem_cache *s, void *x)
{
s = cache_from_obj(s, x);
if (!s)
return;
slab_free(s, virt_to_head_page(x), x, _RET_IP_);
trace_kmem_cache_free(_RET_IP_, x);
}
EXPORT_SYMBOL(kmem_cache_free);
/*
* Object placement in a slab is made very easy because we always start at
* offset 0. If we tune the size of the object to the alignment then we can
* get the required alignment by putting one properly sized object after
* another.
*
* Notice that the allocation order determines the sizes of the per cpu
* caches. Each processor has always one slab available for allocations.
* Increasing the allocation order reduces the number of times that slabs
* must be moved on and off the partial lists and is therefore a factor in
* locking overhead.
*/
/*
* Mininum / Maximum order of slab pages. This influences locking overhead
* and slab fragmentation. A higher order reduces the number of partial slabs
* and increases the number of allocations possible without having to
* take the list_lock.
*/
static int slub_min_order;
static int slub_max_order = PAGE_ALLOC_COSTLY_ORDER;
static int slub_min_objects;
/*
* Calculate the order of allocation given an slab object size.
*
* The order of allocation has significant impact on performance and other
* system components. Generally order 0 allocations should be preferred since
* order 0 does not cause fragmentation in the page allocator. Larger objects
* be problematic to put into order 0 slabs because there may be too much
* unused space left. We go to a higher order if more than 1/16th of the slab
* would be wasted.
*
* In order to reach satisfactory performance we must ensure that a minimum
* number of objects is in one slab. Otherwise we may generate too much
* activity on the partial lists which requires taking the list_lock. This is
* less a concern for large slabs though which are rarely used.
*
* slub_max_order specifies the order where we begin to stop considering the
* number of objects in a slab as critical. If we reach slub_max_order then
* we try to keep the page order as low as possible. So we accept more waste
* of space in favor of a small page order.
*
* Higher order allocations also allow the placement of more objects in a
* slab and thereby reduce object handling overhead. If the user has
* requested a higher mininum order then we start with that one instead of
* the smallest order which will fit the object.
*/
static inline int slab_order(int size, int min_objects,
int max_order, int fract_leftover, int reserved)
{
int order;
int rem;
int min_order = slub_min_order;
if (order_objects(min_order, size, reserved) > MAX_OBJS_PER_PAGE)
return get_order(size * MAX_OBJS_PER_PAGE) - 1;
for (order = max(min_order,
fls(min_objects * size - 1) - PAGE_SHIFT);
order <= max_order; order++) {
unsigned long slab_size = PAGE_SIZE << order;
if (slab_size < min_objects * size + reserved)
continue;
rem = (slab_size - reserved) % size;
if (rem <= slab_size / fract_leftover)
break;
}
return order;
}
static inline int calculate_order(int size, int reserved)
{
int order;
int min_objects;
int fraction;
int max_objects;
/*
* Attempt to find best configuration for a slab. This
* works by first attempting to generate a layout with
* the best configuration and backing off gradually.
*
* First we reduce the acceptable waste in a slab. Then
* we reduce the minimum objects required in a slab.
*/
min_objects = slub_min_objects;
if (!min_objects)
min_objects = 4 * (fls(nr_cpu_ids) + 1);
max_objects = order_objects(slub_max_order, size, reserved);
min_objects = min(min_objects, max_objects);
while (min_objects > 1) {
fraction = 16;
while (fraction >= 4) {
order = slab_order(size, min_objects,
slub_max_order, fraction, reserved);
if (order <= slub_max_order)
return order;
fraction /= 2;
}
min_objects--;
}
/*
* We were unable to place multiple objects in a slab. Now
* lets see if we can place a single object there.
*/
order = slab_order(size, 1, slub_max_order, 1, reserved);
if (order <= slub_max_order)
return order;
/*
* Doh this slab cannot be placed using slub_max_order.
*/
order = slab_order(size, 1, MAX_ORDER, 1, reserved);
if (order < MAX_ORDER)
return order;
return -ENOSYS;
}
static void
init_kmem_cache_node(struct kmem_cache_node *n)
{
n->nr_partial = 0;
spin_lock_init(&n->list_lock);
INIT_LIST_HEAD(&n->partial);
#ifdef CONFIG_SLUB_DEBUG
atomic_long_set(&n->nr_slabs, 0);
atomic_long_set(&n->total_objects, 0);
INIT_LIST_HEAD(&n->full);
#endif
}
static inline int alloc_kmem_cache_cpus(struct kmem_cache *s)
{
BUILD_BUG_ON(PERCPU_DYNAMIC_EARLY_SIZE <
KMALLOC_SHIFT_HIGH * sizeof(struct kmem_cache_cpu));
/*
* Must align to double word boundary for the double cmpxchg
* instructions to work; see __pcpu_double_call_return_bool().
*/
s->cpu_slab = __alloc_percpu(sizeof(struct kmem_cache_cpu),
2 * sizeof(void *));
if (!s->cpu_slab)
return 0;
init_kmem_cache_cpus(s);
return 1;
}
static struct kmem_cache *kmem_cache_node;
/*
* No kmalloc_node yet so do it by hand. We know that this is the first
* slab on the node for this slabcache. There are no concurrent accesses
* possible.
*
* Note that this function only works on the kmem_cache_node
* when allocating for the kmem_cache_node. This is used for bootstrapping
* memory on a fresh node that has no slab structures yet.
*/
static void early_kmem_cache_node_alloc(int node)
{
struct page *page;
struct kmem_cache_node *n;
BUG_ON(kmem_cache_node->size < sizeof(struct kmem_cache_node));
page = new_slab(kmem_cache_node, GFP_NOWAIT, node);
BUG_ON(!page);
if (page_to_nid(page) != node) {
pr_err("SLUB: Unable to allocate memory from node %d\n", node);
pr_err("SLUB: Allocating a useless per node structure in order to be able to continue\n");
}
n = page->freelist;
BUG_ON(!n);
page->freelist = get_freepointer(kmem_cache_node, n);
page->inuse = 1;
page->frozen = 0;
kmem_cache_node->node[node] = n;
#ifdef CONFIG_SLUB_DEBUG
init_object(kmem_cache_node, n, SLUB_RED_ACTIVE);
init_tracking(kmem_cache_node, n);
#endif
kasan_kmalloc(kmem_cache_node, n, sizeof(struct kmem_cache_node));
init_kmem_cache_node(n);
inc_slabs_node(kmem_cache_node, node, page->objects);
/*
* No locks need to be taken here as it has just been
* initialized and there is no concurrent access.
*/
__add_partial(n, page, DEACTIVATE_TO_HEAD);
}
static void free_kmem_cache_nodes(struct kmem_cache *s)
{
int node;
struct kmem_cache_node *n;
for_each_kmem_cache_node(s, node, n) {
kmem_cache_free(kmem_cache_node, n);
s->node[node] = NULL;
}
}
static int init_kmem_cache_nodes(struct kmem_cache *s)
{
int node;
for_each_node_state(node, N_NORMAL_MEMORY) {
struct kmem_cache_node *n;
if (slab_state == DOWN) {
early_kmem_cache_node_alloc(node);
continue;
}
n = kmem_cache_alloc_node(kmem_cache_node,
GFP_KERNEL, node);
if (!n) {
free_kmem_cache_nodes(s);
return 0;
}
s->node[node] = n;
init_kmem_cache_node(n);
}
return 1;
}
static void set_min_partial(struct kmem_cache *s, unsigned long min)
{
if (min < MIN_PARTIAL)
min = MIN_PARTIAL;
else if (min > MAX_PARTIAL)
min = MAX_PARTIAL;
s->min_partial = min;
}
/*
* calculate_sizes() determines the order and the distribution of data within
* a slab object.
*/
static int calculate_sizes(struct kmem_cache *s, int forced_order)
{
unsigned long flags = s->flags;
unsigned long size = s->object_size;
int order;
/*
* Round up object size to the next word boundary. We can only
* place the free pointer at word boundaries and this determines
* the possible location of the free pointer.
*/
size = ALIGN(size, sizeof(void *));
#ifdef CONFIG_SLUB_DEBUG
/*
* Determine if we can poison the object itself. If the user of
* the slab may touch the object after free or before allocation
* then we should never poison the object itself.
*/
if ((flags & SLAB_POISON) && !(flags & SLAB_DESTROY_BY_RCU) &&
!s->ctor)
s->flags |= __OBJECT_POISON;
else
s->flags &= ~__OBJECT_POISON;
/*
* If we are Redzoning then check if there is some space between the
* end of the object and the free pointer. If not then add an
* additional word to have some bytes to store Redzone information.
*/
if ((flags & SLAB_RED_ZONE) && size == s->object_size)
size += sizeof(void *);
#endif
/*
* With that we have determined the number of bytes in actual use
* by the object. This is the potential offset to the free pointer.
*/
s->inuse = size;
if (((flags & (SLAB_DESTROY_BY_RCU | SLAB_POISON)) ||
s->ctor)) {
/*
* Relocate free pointer after the object if it is not
* permitted to overwrite the first word of the object on
* kmem_cache_free.
*
* This is the case if we do RCU, have a constructor or
* destructor or are poisoning the objects.
*/
s->offset = size;
size += sizeof(void *);
}
#ifdef CONFIG_SLUB_DEBUG
if (flags & SLAB_STORE_USER)
/*
* Need to store information about allocs and frees after
* the object.
*/
size += 2 * sizeof(struct track);
if (flags & SLAB_RED_ZONE)
/*
* Add some empty padding so that we can catch
* overwrites from earlier objects rather than let
* tracking information or the free pointer be
* corrupted if a user writes before the start
* of the object.
*/
size += sizeof(void *);
#endif
/*
* SLUB stores one object immediately after another beginning from
* offset 0. In order to align the objects we have to simply size
* each object to conform to the alignment.
*/
size = ALIGN(size, s->align);
s->size = size;
if (forced_order >= 0)
order = forced_order;
else
order = calculate_order(size, s->reserved);
if (order < 0)
return 0;
s->allocflags = 0;
if (order)
s->allocflags |= __GFP_COMP;
if (s->flags & SLAB_CACHE_DMA)
s->allocflags |= GFP_DMA;
if (s->flags & SLAB_RECLAIM_ACCOUNT)
s->allocflags |= __GFP_RECLAIMABLE;
/*
* Determine the number of objects per slab
*/
s->oo = oo_make(order, size, s->reserved);
s->min = oo_make(get_order(size), size, s->reserved);
if (oo_objects(s->oo) > oo_objects(s->max))
s->max = s->oo;
return !!oo_objects(s->oo);
}
static int kmem_cache_open(struct kmem_cache *s, unsigned long flags)
{
s->flags = kmem_cache_flags(s->size, flags, s->name, s->ctor);
s->reserved = 0;
if (need_reserve_slab_rcu && (s->flags & SLAB_DESTROY_BY_RCU))
s->reserved = sizeof(struct rcu_head);
if (!calculate_sizes(s, -1))
goto error;
if (disable_higher_order_debug) {
/*
* Disable debugging flags that store metadata if the min slab
* order increased.
*/
if (get_order(s->size) > get_order(s->object_size)) {
s->flags &= ~DEBUG_METADATA_FLAGS;
s->offset = 0;
if (!calculate_sizes(s, -1))
goto error;
}
}
#if defined(CONFIG_HAVE_CMPXCHG_DOUBLE) && \
defined(CONFIG_HAVE_ALIGNED_STRUCT_PAGE)
if (system_has_cmpxchg_double() && (s->flags & SLAB_DEBUG_FLAGS) == 0)
/* Enable fast mode */
s->flags |= __CMPXCHG_DOUBLE;
#endif
/*
* The larger the object size is, the more pages we want on the partial
* list to avoid pounding the page allocator excessively.
*/
set_min_partial(s, ilog2(s->size) / 2);
/*
* cpu_partial determined the maximum number of objects kept in the
* per cpu partial lists of a processor.
*
* Per cpu partial lists mainly contain slabs that just have one
* object freed. If they are used for allocation then they can be
* filled up again with minimal effort. The slab will never hit the
* per node partial lists and therefore no locking will be required.
*
* This setting also determines
*
* A) The number of objects from per cpu partial slabs dumped to the
* per node list when we reach the limit.
* B) The number of objects in cpu partial slabs to extract from the
* per node list when we run out of per cpu objects. We only fetch
* 50% to keep some capacity around for frees.
*/
if (!kmem_cache_has_cpu_partial(s))
s->cpu_partial = 0;
else if (s->size >= PAGE_SIZE)
s->cpu_partial = 2;
else if (s->size >= 1024)
s->cpu_partial = 6;
else if (s->size >= 256)
s->cpu_partial = 13;
else
s->cpu_partial = 30;
#ifdef CONFIG_NUMA
s->remote_node_defrag_ratio = 1000;
#endif
if (!init_kmem_cache_nodes(s))
goto error;
if (alloc_kmem_cache_cpus(s))
return 0;
free_kmem_cache_nodes(s);
error:
if (flags & SLAB_PANIC)
panic("Cannot create slab %s size=%lu realsize=%u "
"order=%u offset=%u flags=%lx\n",
s->name, (unsigned long)s->size, s->size,
oo_order(s->oo), s->offset, flags);
return -EINVAL;
}
static void list_slab_objects(struct kmem_cache *s, struct page *page,
const char *text)
{
#ifdef CONFIG_SLUB_DEBUG
void *addr = page_address(page);
void *p;
unsigned long *map = kzalloc(BITS_TO_LONGS(page->objects) *
sizeof(long), GFP_ATOMIC);
if (!map)
return;
slab_err(s, page, text, s->name);
slab_lock(page);
get_map(s, page, map);
for_each_object(p, s, addr, page->objects) {
if (!test_bit(slab_index(p, s, addr), map)) {
pr_err("INFO: Object 0x%p @offset=%tu\n", p, p - addr);
print_tracking(s, p);
}
}
slab_unlock(page);
kfree(map);
#endif
}
/*
* Attempt to free all partial slabs on a node.
* This is called from kmem_cache_close(). We must be the last thread
* using the cache and therefore we do not need to lock anymore.
*/
static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n)
{
struct page *page, *h;
list_for_each_entry_safe(page, h, &n->partial, lru) {
if (!page->inuse) {
__remove_partial(n, page);
discard_slab(s, page);
} else {
list_slab_objects(s, page,
"Objects remaining in %s on kmem_cache_close()");
}
}
}
/*
* Release all resources used by a slab cache.
*/
static inline int kmem_cache_close(struct kmem_cache *s)
{
int node;
struct kmem_cache_node *n;
flush_all(s);
/* Attempt to free all objects */
for_each_kmem_cache_node(s, node, n) {
free_partial(s, n);
if (n->nr_partial || slabs_node(s, node))
return 1;
}
free_percpu(s->cpu_slab);
free_kmem_cache_nodes(s);
return 0;
}
int __kmem_cache_shutdown(struct kmem_cache *s)
{
return kmem_cache_close(s);
}
/********************************************************************
* Kmalloc subsystem
*******************************************************************/
static int __init setup_slub_min_order(char *str)
{
get_option(&str, &slub_min_order);
return 1;
}
__setup("slub_min_order=", setup_slub_min_order);
static int __init setup_slub_max_order(char *str)
{
get_option(&str, &slub_max_order);
slub_max_order = min(slub_max_order, MAX_ORDER - 1);
return 1;
}
__setup("slub_max_order=", setup_slub_max_order);
static int __init setup_slub_min_objects(char *str)
{
get_option(&str, &slub_min_objects);
return 1;
}
__setup("slub_min_objects=", setup_slub_min_objects);
void *__kmalloc(size_t size, gfp_t flags)
{
struct kmem_cache *s;
void *ret;
if (unlikely(size > KMALLOC_MAX_CACHE_SIZE))
return kmalloc_large(size, flags);
s = kmalloc_slab(size, flags);
if (unlikely(ZERO_OR_NULL_PTR(s)))
return s;
ret = slab_alloc(s, flags, _RET_IP_);
trace_kmalloc(_RET_IP_, ret, size, s->size, flags);
kasan_kmalloc(s, ret, size);
return ret;
}
EXPORT_SYMBOL(__kmalloc);
#ifdef CONFIG_NUMA
static void *kmalloc_large_node(size_t size, gfp_t flags, int node)
{
struct page *page;
void *ptr = NULL;
flags |= __GFP_COMP | __GFP_NOTRACK;
page = alloc_kmem_pages_node(node, flags, get_order(size));
if (page)
ptr = page_address(page);
kmalloc_large_node_hook(ptr, size, flags);
return ptr;
}
void *__kmalloc_node(size_t size, gfp_t flags, int node)
{
struct kmem_cache *s;
void *ret;
if (unlikely(size > KMALLOC_MAX_CACHE_SIZE)) {
ret = kmalloc_large_node(size, flags, node);
trace_kmalloc_node(_RET_IP_, ret,
size, PAGE_SIZE << get_order(size),
flags, node);
return ret;
}
s = kmalloc_slab(size, flags);
if (unlikely(ZERO_OR_NULL_PTR(s)))
return s;
ret = slab_alloc_node(s, flags, node, _RET_IP_);
trace_kmalloc_node(_RET_IP_, ret, size, s->size, flags, node);
kasan_kmalloc(s, ret, size);
return ret;
}
EXPORT_SYMBOL(__kmalloc_node);
#endif
static size_t __ksize(const void *object)
{
struct page *page;
if (unlikely(object == ZERO_SIZE_PTR))
return 0;
page = virt_to_head_page(object);
if (unlikely(!PageSlab(page))) {
WARN_ON(!PageCompound(page));
return PAGE_SIZE << compound_order(page);
}
return slab_ksize(page->slab_cache);
}
size_t ksize(const void *object)
{
size_t size = __ksize(object);
/* We assume that ksize callers could use whole allocated area,
so we need unpoison this area. */
kasan_krealloc(object, size);
return size;
}
EXPORT_SYMBOL(ksize);
void kfree(const void *x)
{
struct page *page;
void *object = (void *)x;
trace_kfree(_RET_IP_, x);
if (unlikely(ZERO_OR_NULL_PTR(x)))
return;
page = virt_to_head_page(x);
if (unlikely(!PageSlab(page))) {
BUG_ON(!PageCompound(page));
kfree_hook(x);
__free_kmem_pages(page, compound_order(page));
return;
}
slab_free(page->slab_cache, page, object, _RET_IP_);
}
EXPORT_SYMBOL(kfree);
#define SHRINK_PROMOTE_MAX 32
/*
* kmem_cache_shrink discards empty slabs and promotes the slabs filled
* up most to the head of the partial lists. New allocations will then
* fill those up and thus they can be removed from the partial lists.
*
* The slabs with the least items are placed last. This results in them
* being allocated from last increasing the chance that the last objects
* are freed in them.
*/
int __kmem_cache_shrink(struct kmem_cache *s, bool deactivate)
{
int node;
int i;
struct kmem_cache_node *n;
struct page *page;
struct page *t;
struct list_head discard;
struct list_head promote[SHRINK_PROMOTE_MAX];
unsigned long flags;
int ret = 0;
if (deactivate) {
/*
* Disable empty slabs caching. Used to avoid pinning offline
* memory cgroups by kmem pages that can be freed.
*/
s->cpu_partial = 0;
s->min_partial = 0;
/*
* s->cpu_partial is checked locklessly (see put_cpu_partial),
* so we have to make sure the change is visible.
*/
kick_all_cpus_sync();
}
flush_all(s);
for_each_kmem_cache_node(s, node, n) {
INIT_LIST_HEAD(&discard);
for (i = 0; i < SHRINK_PROMOTE_MAX; i++)
INIT_LIST_HEAD(promote + i);
spin_lock_irqsave(&n->list_lock, flags);
/*
* Build lists of slabs to discard or promote.
*
* 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) {
int free = page->objects - page->inuse;
/* Do not reread page->inuse */
barrier();
/* We do not keep full slabs on the list */
BUG_ON(free <= 0);
if (free == page->objects) {
list_move(&page->lru, &discard);
n->nr_partial--;
} else if (free <= SHRINK_PROMOTE_MAX)
list_move(&page->lru, promote + free - 1);
}
/*
* Promote the slabs filled up most to the head of the
* partial list.
*/
for (i = SHRINK_PROMOTE_MAX - 1; i >= 0; i--)
list_splice(promote + i, &n->partial);
spin_unlock_irqrestore(&n->list_lock, flags);
/* Release empty slabs */
list_for_each_entry_safe(page, t, &discard, lru)
discard_slab(s, page);
if (slabs_node(s, node))
ret = 1;
}
return ret;
}
static int slab_mem_going_offline_callback(void *arg)
{
struct kmem_cache *s;
mutex_lock(&slab_mutex);
list_for_each_entry(s, &slab_caches, list)
__kmem_cache_shrink(s, false);
mutex_unlock(&slab_mutex);
return 0;
}
static void slab_mem_offline_callback(void *arg)
{
struct kmem_cache_node *n;
struct kmem_cache *s;
struct memory_notify *marg = arg;
int offline_node;
offline_node = marg->status_change_nid_normal;
/*
* If the node still has available memory. we need kmem_cache_node
* for it yet.
*/
if (offline_node < 0)
return;
mutex_lock(&slab_mutex);
list_for_each_entry(s, &slab_caches, list) {
n = get_node(s, offline_node);
if (n) {
/*
* if n->nr_slabs > 0, slabs still exist on the node
* that is going down. We were unable to free them,
* and offline_pages() function shouldn't call this
* callback. So, we must fail.
*/
BUG_ON(slabs_node(s, offline_node));
s->node[offline_node] = NULL;
kmem_cache_free(kmem_cache_node, n);
}
}
mutex_unlock(&slab_mutex);
}
static int slab_mem_going_online_callback(void *arg)
{
struct kmem_cache_node *n;
struct kmem_cache *s;
struct memory_notify *marg = arg;
int nid = marg->status_change_nid_normal;
int ret = 0;
/*
* If the node's memory is already available, then kmem_cache_node is
* already created. Nothing to do.
*/
if (nid < 0)
return 0;
/*
* We are bringing a node online. No memory is available yet. We must
* allocate a kmem_cache_node structure in order to bring the node
* online.
*/
mutex_lock(&slab_mutex);
list_for_each_entry(s, &slab_caches, list) {
/*
* XXX: kmem_cache_alloc_node will fallback to other nodes
* since memory is not yet available from the node that
* is brought up.
*/
n = kmem_cache_alloc(kmem_cache_node, GFP_KERNEL);
if (!n) {
ret = -ENOMEM;
goto out;
}
init_kmem_cache_node(n);
s->node[nid] = n;
}
out:
mutex_unlock(&slab_mutex);
return ret;
}
static int slab_memory_callback(struct notifier_block *self,
unsigned long action, void *arg)
{
int ret = 0;
switch (action) {
case MEM_GOING_ONLINE:
ret = slab_mem_going_online_callback(arg);
break;
case MEM_GOING_OFFLINE:
ret = slab_mem_going_offline_callback(arg);
break;
case MEM_OFFLINE:
case MEM_CANCEL_ONLINE:
slab_mem_offline_callback(arg);
break;
case MEM_ONLINE:
case MEM_CANCEL_OFFLINE:
break;
}
if (ret)
ret = notifier_from_errno(ret);
else
ret = NOTIFY_OK;
return ret;
}
static struct notifier_block slab_memory_callback_nb = {
.notifier_call = slab_memory_callback,
.priority = SLAB_CALLBACK_PRI,
};
/********************************************************************
* Basic setup of slabs
*******************************************************************/
/*
* Used for early kmem_cache structures that were allocated using
* the page allocator. Allocate them properly then fix up the pointers
* that may be pointing to the wrong kmem_cache structure.
*/
static struct kmem_cache * __init bootstrap(struct kmem_cache *static_cache)
{
int node;
struct kmem_cache *s = kmem_cache_zalloc(kmem_cache, GFP_NOWAIT);
struct kmem_cache_node *n;
memcpy(s, static_cache, kmem_cache->object_size);
/*
* This runs very early, and only the boot processor is supposed to be
* up. Even if it weren't true, IRQs are not up so we couldn't fire
* IPIs around.
*/
__flush_cpu_slab(s, smp_processor_id());
for_each_kmem_cache_node(s, node, n) {
struct page *p;
list_for_each_entry(p, &n->partial, lru)
p->slab_cache = s;
#ifdef CONFIG_SLUB_DEBUG
list_for_each_entry(p, &n->full, lru)
p->slab_cache = s;
#endif
}
slab_init_memcg_params(s);
list_add(&s->list, &slab_caches);
return s;
}
void __init kmem_cache_init(void)
{
static __initdata struct kmem_cache boot_kmem_cache,
boot_kmem_cache_node;
if (debug_guardpage_minorder())
slub_max_order = 0;
kmem_cache_node = &boot_kmem_cache_node;
kmem_cache = &boot_kmem_cache;
create_boot_cache(kmem_cache_node, "kmem_cache_node",
sizeof(struct kmem_cache_node), SLAB_HWCACHE_ALIGN);
register_hotmemory_notifier(&slab_memory_callback_nb);
/* Able to allocate the per node structures */
slab_state = PARTIAL;
create_boot_cache(kmem_cache, "kmem_cache",
offsetof(struct kmem_cache, node) +
nr_node_ids * sizeof(struct kmem_cache_node *),
SLAB_HWCACHE_ALIGN);
kmem_cache = bootstrap(&boot_kmem_cache);
/*
* Allocate kmem_cache_node properly from the kmem_cache slab.
* kmem_cache_node is separately allocated so no need to
* update any list pointers.
*/
kmem_cache_node = bootstrap(&boot_kmem_cache_node);
/* Now we can use the kmem_cache to allocate kmalloc slabs */
setup_kmalloc_cache_index_table();
create_kmalloc_caches(0);
#ifdef CONFIG_SMP
register_cpu_notifier(&slab_notifier);
#endif
pr_info("SLUB: HWalign=%d, Order=%d-%d, MinObjects=%d, CPUs=%d, Nodes=%d\n",
cache_line_size(),
slub_min_order, slub_max_order, slub_min_objects,
nr_cpu_ids, nr_node_ids);
}
void __init kmem_cache_init_late(void)
{
}
struct kmem_cache *
__kmem_cache_alias(const char *name, size_t size, size_t align,
unsigned long flags, void (*ctor)(void *))
{
struct kmem_cache *s, *c;
s = find_mergeable(size, align, flags, name, ctor);
if (s) {
s->refcount++;
/*
* Adjust the object sizes so that we clear
* the complete object on kzalloc.
*/
s->object_size = max(s->object_size, (int)size);
s->inuse = max_t(int, s->inuse, ALIGN(size, sizeof(void *)));
for_each_memcg_cache(c, s) {
c->object_size = s->object_size;
c->inuse = max_t(int, c->inuse,
ALIGN(size, sizeof(void *)));
}
if (sysfs_slab_alias(s, name)) {
s->refcount--;
s = NULL;
}
}
return s;
}