Update Linux to v5.10.109
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz
Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 8f12824..ec83290 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -26,6 +26,8 @@
#define CREATE_TRACE_POINTS
#include <trace/events/kmem.h>
+#include "internal.h"
+
#include "slab.h"
enum slab_state slab_state;
@@ -127,152 +129,6 @@
return i;
}
-#ifdef CONFIG_MEMCG_KMEM
-
-LIST_HEAD(slab_root_caches);
-static DEFINE_SPINLOCK(memcg_kmem_wq_lock);
-
-static void kmemcg_cache_shutdown(struct percpu_ref *percpu_ref);
-
-void slab_init_memcg_params(struct kmem_cache *s)
-{
- s->memcg_params.root_cache = NULL;
- RCU_INIT_POINTER(s->memcg_params.memcg_caches, NULL);
- INIT_LIST_HEAD(&s->memcg_params.children);
- s->memcg_params.dying = false;
-}
-
-static int init_memcg_params(struct kmem_cache *s,
- struct kmem_cache *root_cache)
-{
- struct memcg_cache_array *arr;
-
- if (root_cache) {
- int ret = percpu_ref_init(&s->memcg_params.refcnt,
- kmemcg_cache_shutdown,
- 0, GFP_KERNEL);
- if (ret)
- return ret;
-
- s->memcg_params.root_cache = root_cache;
- INIT_LIST_HEAD(&s->memcg_params.children_node);
- INIT_LIST_HEAD(&s->memcg_params.kmem_caches_node);
- return 0;
- }
-
- slab_init_memcg_params(s);
-
- if (!memcg_nr_cache_ids)
- return 0;
-
- arr = kvzalloc(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)) {
- kvfree(rcu_access_pointer(s->memcg_params.memcg_caches));
- } else {
- mem_cgroup_put(s->memcg_params.memcg);
- WRITE_ONCE(s->memcg_params.memcg, NULL);
- percpu_ref_exit(&s->memcg_params.refcnt);
- }
-}
-
-static void free_memcg_params(struct rcu_head *rcu)
-{
- struct memcg_cache_array *old;
-
- old = container_of(rcu, struct memcg_cache_array, rcu);
- kvfree(old);
-}
-
-static int update_memcg_params(struct kmem_cache *s, int new_array_size)
-{
- struct memcg_cache_array *old, *new;
-
- new = kvzalloc(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)
- call_rcu(&old->rcu, free_memcg_params);
- 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_root_caches, root_caches_node) {
- 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;
-}
-
-void memcg_link_cache(struct kmem_cache *s, struct mem_cgroup *memcg)
-{
- if (is_root_cache(s)) {
- list_add(&s->root_caches_node, &slab_root_caches);
- } else {
- css_get(&memcg->css);
- s->memcg_params.memcg = memcg;
- list_add(&s->memcg_params.children_node,
- &s->memcg_params.root_cache->memcg_params.children);
- list_add(&s->memcg_params.kmem_caches_node,
- &s->memcg_params.memcg->kmem_caches);
- }
-}
-
-static void memcg_unlink_cache(struct kmem_cache *s)
-{
- if (is_root_cache(s)) {
- list_del(&s->root_caches_node);
- } else {
- list_del(&s->memcg_params.children_node);
- list_del(&s->memcg_params.kmem_caches_node);
- }
-}
-#else
-static inline int init_memcg_params(struct kmem_cache *s,
- struct kmem_cache *root_cache)
-{
- return 0;
-}
-
-static inline void destroy_memcg_params(struct kmem_cache *s)
-{
-}
-
-static inline void memcg_unlink_cache(struct kmem_cache *s)
-{
-}
-#endif /* CONFIG_MEMCG_KMEM */
-
/*
* 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.
@@ -310,9 +166,6 @@
if (slab_nomerge || (s->flags & SLAB_NEVER_MERGE))
return 1;
- if (!is_root_cache(s))
- return 1;
-
if (s->ctor)
return 1;
@@ -342,12 +195,12 @@
size = ALIGN(size, sizeof(void *));
align = calculate_alignment(flags, align, size);
size = ALIGN(size, align);
- flags = kmem_cache_flags(size, flags, name, NULL);
+ flags = kmem_cache_flags(size, flags, name);
if (flags & SLAB_NEVER_MERGE)
return NULL;
- list_for_each_entry_reverse(s, &slab_root_caches, root_caches_node) {
+ list_for_each_entry_reverse(s, &slab_caches, list) {
if (slab_unmergeable(s))
continue;
@@ -379,7 +232,7 @@
unsigned int object_size, unsigned int align,
slab_flags_t flags, unsigned int useroffset,
unsigned int usersize, void (*ctor)(void *),
- struct mem_cgroup *memcg, struct kmem_cache *root_cache)
+ struct kmem_cache *root_cache)
{
struct kmem_cache *s;
int err;
@@ -399,24 +252,18 @@
s->useroffset = useroffset;
s->usersize = usersize;
- err = init_memcg_params(s, 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);
- memcg_link_cache(s, memcg);
out:
if (err)
return ERR_PTR(err);
return s;
out_free_cache:
- destroy_memcg_params(s);
kmem_cache_free(kmem_cache, s);
goto out;
}
@@ -462,7 +309,6 @@
get_online_cpus();
get_online_mems();
- memcg_get_cache_ids();
mutex_lock(&slab_mutex);
@@ -503,7 +349,7 @@
s = create_cache(cache_name, size,
calculate_alignment(flags, align, size),
- flags, useroffset, usersize, ctor, NULL, NULL);
+ flags, useroffset, usersize, ctor, NULL);
if (IS_ERR(s)) {
err = PTR_ERR(s);
kfree_const(cache_name);
@@ -512,7 +358,6 @@
out_unlock:
mutex_unlock(&slab_mutex);
- memcg_put_cache_ids();
put_online_mems();
put_online_cpus();
@@ -573,7 +418,7 @@
/*
* On destruction, SLAB_TYPESAFE_BY_RCU kmem_caches are put on the
* @slab_caches_to_rcu_destroy list. The slab pages are freed
- * through RCU and and the associated kmem_cache are dereferenced
+ * through RCU and the associated kmem_cache are dereferenced
* while freeing the pages, so the kmem_caches should be freed only
* after the pending RCU operations are finished. As rcu_barrier()
* is a pretty slow operation, we batch all pending destructions
@@ -605,7 +450,6 @@
if (__kmem_cache_shutdown(s) != 0)
return -EBUSY;
- memcg_unlink_cache(s);
list_del(&s->list);
if (s->flags & SLAB_TYPESAFE_BY_RCU) {
@@ -626,311 +470,9 @@
return 0;
}
-#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 = &memcg->css;
- 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 offlined while the cache
- * creation work was pending.
- */
- if (memcg->kmem_state != KMEM_ONLINE)
- 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(%llu:%s)", root_cache->name,
- css->serial_nr, memcg_name_buf);
- if (!cache_name)
- goto out_unlock;
-
- s = create_cache(cache_name, root_cache->object_size,
- root_cache->align,
- root_cache->flags & CACHE_CREATE_MASK,
- root_cache->useroffset, root_cache->usersize,
- 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;
- }
-
- /*
- * Since readers won't lock (see memcg_kmem_get_cache()), 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();
-}
-
-static void kmemcg_workfn(struct work_struct *work)
-{
- struct kmem_cache *s = container_of(work, struct kmem_cache,
- memcg_params.work);
-
- get_online_cpus();
- get_online_mems();
-
- mutex_lock(&slab_mutex);
- s->memcg_params.work_fn(s);
- mutex_unlock(&slab_mutex);
-
- put_online_mems();
- put_online_cpus();
-}
-
-static void kmemcg_rcufn(struct rcu_head *head)
-{
- struct kmem_cache *s = container_of(head, struct kmem_cache,
- memcg_params.rcu_head);
-
- /*
- * We need to grab blocking locks. Bounce to ->work. The
- * work item shares the space with the RCU head and can't be
- * initialized eariler.
- */
- INIT_WORK(&s->memcg_params.work, kmemcg_workfn);
- queue_work(memcg_kmem_cache_wq, &s->memcg_params.work);
-}
-
-static void kmemcg_cache_shutdown_fn(struct kmem_cache *s)
-{
- WARN_ON(shutdown_cache(s));
-}
-
-static void kmemcg_cache_shutdown(struct percpu_ref *percpu_ref)
-{
- struct kmem_cache *s = container_of(percpu_ref, struct kmem_cache,
- memcg_params.refcnt);
- unsigned long flags;
-
- spin_lock_irqsave(&memcg_kmem_wq_lock, flags);
- if (s->memcg_params.root_cache->memcg_params.dying)
- goto unlock;
-
- s->memcg_params.work_fn = kmemcg_cache_shutdown_fn;
- INIT_WORK(&s->memcg_params.work, kmemcg_workfn);
- queue_work(memcg_kmem_cache_wq, &s->memcg_params.work);
-
-unlock:
- spin_unlock_irqrestore(&memcg_kmem_wq_lock, flags);
-}
-
-static void kmemcg_cache_deactivate_after_rcu(struct kmem_cache *s)
-{
- __kmemcg_cache_deactivate_after_rcu(s);
- percpu_ref_kill(&s->memcg_params.refcnt);
-}
-
-static void kmemcg_cache_deactivate(struct kmem_cache *s)
-{
- if (WARN_ON_ONCE(is_root_cache(s)))
- return;
-
- __kmemcg_cache_deactivate(s);
- s->flags |= SLAB_DEACTIVATED;
-
- /*
- * memcg_kmem_wq_lock is used to synchronize memcg_params.dying
- * flag and make sure that no new kmem_cache deactivation tasks
- * are queued (see flush_memcg_workqueue() ).
- */
- spin_lock_irq(&memcg_kmem_wq_lock);
- if (s->memcg_params.root_cache->memcg_params.dying)
- goto unlock;
-
- s->memcg_params.work_fn = kmemcg_cache_deactivate_after_rcu;
- call_rcu(&s->memcg_params.rcu_head, kmemcg_rcufn);
-unlock:
- spin_unlock_irq(&memcg_kmem_wq_lock);
-}
-
-void memcg_deactivate_kmem_caches(struct mem_cgroup *memcg,
- struct mem_cgroup *parent)
-{
- int idx;
- struct memcg_cache_array *arr;
- struct kmem_cache *s, *c;
- unsigned int nr_reparented;
-
- idx = memcg_cache_id(memcg);
-
- get_online_cpus();
- get_online_mems();
-
- mutex_lock(&slab_mutex);
- list_for_each_entry(s, &slab_root_caches, root_caches_node) {
- arr = rcu_dereference_protected(s->memcg_params.memcg_caches,
- lockdep_is_held(&slab_mutex));
- c = arr->entries[idx];
- if (!c)
- continue;
-
- kmemcg_cache_deactivate(c);
- arr->entries[idx] = NULL;
- }
- nr_reparented = 0;
- list_for_each_entry(s, &memcg->kmem_caches,
- memcg_params.kmem_caches_node) {
- WRITE_ONCE(s->memcg_params.memcg, parent);
- css_put(&memcg->css);
- nr_reparented++;
- }
- if (nr_reparented) {
- list_splice_init(&memcg->kmem_caches,
- &parent->kmem_caches);
- css_get_many(&parent->css, nr_reparented);
- }
- mutex_unlock(&slab_mutex);
-
- put_online_mems();
- put_online_cpus();
-}
-
-static int shutdown_memcg_caches(struct kmem_cache *s)
-{
- struct memcg_cache_array *arr;
- struct kmem_cache *c, *c2;
- LIST_HEAD(busy);
- int i;
-
- BUG_ON(!is_root_cache(s));
-
- /*
- * First, shutdown active caches, i.e. caches that belong to online
- * memory cgroups.
- */
- arr = rcu_dereference_protected(s->memcg_params.memcg_caches,
- lockdep_is_held(&slab_mutex));
- for_each_memcg_cache_index(i) {
- c = arr->entries[i];
- if (!c)
- continue;
- if (shutdown_cache(c))
- /*
- * The cache still has objects. Move it to a temporary
- * list so as not to try to destroy it for a second
- * time while iterating over inactive caches below.
- */
- list_move(&c->memcg_params.children_node, &busy);
- else
- /*
- * The cache is empty and will be destroyed soon. Clear
- * the pointer to it in the memcg_caches array so that
- * it will never be accessed even if the root cache
- * stays alive.
- */
- arr->entries[i] = NULL;
- }
-
- /*
- * Second, shutdown all caches left from memory cgroups that are now
- * offline.
- */
- list_for_each_entry_safe(c, c2, &s->memcg_params.children,
- memcg_params.children_node)
- shutdown_cache(c);
-
- list_splice(&busy, &s->memcg_params.children);
-
- /*
- * A cache being destroyed must be empty. In particular, this means
- * that all per memcg caches attached to it must be empty too.
- */
- if (!list_empty(&s->memcg_params.children))
- return -EBUSY;
- return 0;
-}
-
-static void memcg_set_kmem_cache_dying(struct kmem_cache *s)
-{
- spin_lock_irq(&memcg_kmem_wq_lock);
- s->memcg_params.dying = true;
- spin_unlock_irq(&memcg_kmem_wq_lock);
-}
-
-static void flush_memcg_workqueue(struct kmem_cache *s)
-{
- /*
- * SLAB and SLUB deactivate the kmem_caches through call_rcu. Make
- * sure all registered rcu callbacks have been invoked.
- */
- rcu_barrier();
-
- /*
- * SLAB and SLUB create memcg kmem_caches through workqueue and SLUB
- * deactivates the memcg kmem_caches through workqueue. Make sure all
- * previous workitems on workqueue are processed.
- */
- if (likely(memcg_kmem_cache_wq))
- flush_workqueue(memcg_kmem_cache_wq);
-
- /*
- * If we're racing with children kmem_cache deactivation, it might
- * take another rcu grace period to complete their destruction.
- * At this moment the corresponding percpu_ref_kill() call should be
- * done, but it might take another rcu grace period to complete
- * switching to the atomic mode.
- * Please, note that we check without grabbing the slab_mutex. It's safe
- * because at this moment the children list can't grow.
- */
- if (!list_empty(&s->memcg_params.children))
- rcu_barrier();
-}
-#else
-static inline int shutdown_memcg_caches(struct kmem_cache *s)
-{
- return 0;
-}
-#endif /* CONFIG_MEMCG_KMEM */
-
void slab_kmem_cache_release(struct kmem_cache *s)
{
__kmem_cache_release(s);
- destroy_memcg_params(s);
kfree_const(s->name);
kmem_cache_free(kmem_cache, s);
}
@@ -951,36 +493,7 @@
if (s->refcount)
goto out_unlock;
-#ifdef CONFIG_MEMCG_KMEM
- memcg_set_kmem_cache_dying(s);
-
- mutex_unlock(&slab_mutex);
-
- put_online_mems();
- put_online_cpus();
-
- flush_memcg_workqueue(s);
-
- get_online_cpus();
- get_online_mems();
-
- mutex_lock(&slab_mutex);
-
- /*
- * Another thread referenced it again
- */
- if (READ_ONCE(s->refcount)) {
- spin_lock_irq(&memcg_kmem_wq_lock);
- s->memcg_params.dying = false;
- spin_unlock_irq(&memcg_kmem_wq_lock);
- goto out_unlock;
- }
-#endif
-
- err = shutdown_memcg_caches(s);
- if (!err)
- err = shutdown_cache(s);
-
+ err = shutdown_cache(s);
if (err) {
pr_err("kmem_cache_destroy %s: Slab cache still has objects\n",
s->name);
@@ -1017,43 +530,6 @@
}
EXPORT_SYMBOL(kmem_cache_shrink);
-/**
- * kmem_cache_shrink_all - shrink a cache and all memcg caches for root cache
- * @s: The cache pointer
- */
-void kmem_cache_shrink_all(struct kmem_cache *s)
-{
- struct kmem_cache *c;
-
- if (!IS_ENABLED(CONFIG_MEMCG_KMEM) || !is_root_cache(s)) {
- kmem_cache_shrink(s);
- return;
- }
-
- get_online_cpus();
- get_online_mems();
- kasan_cache_shrink(s);
- __kmem_cache_shrink(s);
-
- /*
- * We have to take the slab_mutex to protect from the memcg list
- * modification.
- */
- mutex_lock(&slab_mutex);
- for_each_memcg_cache(c, s) {
- /*
- * Don't need to shrink deactivated memcg caches.
- */
- if (s->flags & SLAB_DEACTIVATED)
- continue;
- kasan_cache_shrink(c);
- __kmem_cache_shrink(c);
- }
- mutex_unlock(&slab_mutex);
- put_online_mems();
- put_online_cpus();
-}
-
bool slab_is_available(void)
{
return slab_state >= UP;
@@ -1082,8 +558,6 @@
s->useroffset = useroffset;
s->usersize = usersize;
- slab_init_memcg_params(s);
-
err = __kmem_cache_create(s, flags);
if (err)
@@ -1104,7 +578,6 @@
create_boot_cache(s, name, size, flags, useroffset, usersize);
list_add(&s->list, &slab_caches);
- memcg_link_cache(s, NULL);
s->refcount = 1;
return s;
}
@@ -1174,26 +647,56 @@
return kmalloc_caches[kmalloc_type(flags)][index];
}
+#ifdef CONFIG_ZONE_DMA
+#define INIT_KMALLOC_INFO(__size, __short_size) \
+{ \
+ .name[KMALLOC_NORMAL] = "kmalloc-" #__short_size, \
+ .name[KMALLOC_RECLAIM] = "kmalloc-rcl-" #__short_size, \
+ .name[KMALLOC_DMA] = "dma-kmalloc-" #__short_size, \
+ .size = __size, \
+}
+#else
+#define INIT_KMALLOC_INFO(__size, __short_size) \
+{ \
+ .name[KMALLOC_NORMAL] = "kmalloc-" #__short_size, \
+ .name[KMALLOC_RECLAIM] = "kmalloc-rcl-" #__short_size, \
+ .size = __size, \
+}
+#endif
+
/*
* 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.
*/
const struct kmalloc_info_struct 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-1k", 1024}, {"kmalloc-2k", 2048},
- {"kmalloc-4k", 4096}, {"kmalloc-8k", 8192},
- {"kmalloc-16k", 16384}, {"kmalloc-32k", 32768},
- {"kmalloc-64k", 65536}, {"kmalloc-128k", 131072},
- {"kmalloc-256k", 262144}, {"kmalloc-512k", 524288},
- {"kmalloc-1M", 1048576}, {"kmalloc-2M", 2097152},
- {"kmalloc-4M", 4194304}, {"kmalloc-8M", 8388608},
- {"kmalloc-16M", 16777216}, {"kmalloc-32M", 33554432},
- {"kmalloc-64M", 67108864}
+ INIT_KMALLOC_INFO(0, 0),
+ INIT_KMALLOC_INFO(96, 96),
+ INIT_KMALLOC_INFO(192, 192),
+ INIT_KMALLOC_INFO(8, 8),
+ INIT_KMALLOC_INFO(16, 16),
+ INIT_KMALLOC_INFO(32, 32),
+ INIT_KMALLOC_INFO(64, 64),
+ INIT_KMALLOC_INFO(128, 128),
+ INIT_KMALLOC_INFO(256, 256),
+ INIT_KMALLOC_INFO(512, 512),
+ INIT_KMALLOC_INFO(1024, 1k),
+ INIT_KMALLOC_INFO(2048, 2k),
+ INIT_KMALLOC_INFO(4096, 4k),
+ INIT_KMALLOC_INFO(8192, 8k),
+ INIT_KMALLOC_INFO(16384, 16k),
+ INIT_KMALLOC_INFO(32768, 32k),
+ INIT_KMALLOC_INFO(65536, 64k),
+ INIT_KMALLOC_INFO(131072, 128k),
+ INIT_KMALLOC_INFO(262144, 256k),
+ INIT_KMALLOC_INFO(524288, 512k),
+ INIT_KMALLOC_INFO(1048576, 1M),
+ INIT_KMALLOC_INFO(2097152, 2M),
+ INIT_KMALLOC_INFO(4194304, 4M),
+ INIT_KMALLOC_INFO(8388608, 8M),
+ INIT_KMALLOC_INFO(16777216, 16M),
+ INIT_KMALLOC_INFO(33554432, 32M),
+ INIT_KMALLOC_INFO(67108864, 64M)
};
/*
@@ -1243,36 +746,14 @@
}
}
-static const char *
-kmalloc_cache_name(const char *prefix, unsigned int size)
-{
-
- static const char units[3] = "\0kM";
- int idx = 0;
-
- while (size >= 1024 && (size % 1024 == 0)) {
- size /= 1024;
- idx++;
- }
-
- return kasprintf(GFP_NOWAIT, "%s-%u%c", prefix, size, units[idx]);
-}
-
static void __init
-new_kmalloc_cache(int idx, int type, slab_flags_t flags)
+new_kmalloc_cache(int idx, enum kmalloc_cache_type type, slab_flags_t flags)
{
- const char *name;
-
- if (type == KMALLOC_RECLAIM) {
+ if (type == KMALLOC_RECLAIM)
flags |= SLAB_RECLAIM_ACCOUNT;
- name = kmalloc_cache_name("kmalloc-rcl",
- kmalloc_info[idx].size);
- BUG_ON(!name);
- } else {
- name = kmalloc_info[idx].name;
- }
- kmalloc_caches[type][idx] = create_kmalloc_cache(name,
+ kmalloc_caches[type][idx] = create_kmalloc_cache(
+ kmalloc_info[idx].name[type],
kmalloc_info[idx].size, flags, 0,
kmalloc_info[idx].size);
}
@@ -1284,7 +765,8 @@
*/
void __init create_kmalloc_caches(slab_flags_t flags)
{
- int i, type;
+ int i;
+ enum kmalloc_cache_type type;
for (type = KMALLOC_NORMAL; type <= KMALLOC_RECLAIM; type++) {
for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++) {
@@ -1313,18 +795,29 @@
struct kmem_cache *s = kmalloc_caches[KMALLOC_NORMAL][i];
if (s) {
- unsigned int size = kmalloc_size(i);
- const char *n = kmalloc_cache_name("dma-kmalloc", size);
-
- BUG_ON(!n);
kmalloc_caches[KMALLOC_DMA][i] = create_kmalloc_cache(
- n, size, SLAB_CACHE_DMA | flags, 0, 0);
+ kmalloc_info[i].name[KMALLOC_DMA],
+ kmalloc_info[i].size,
+ SLAB_CACHE_DMA | flags, 0,
+ kmalloc_info[i].size);
}
}
#endif
}
#endif /* !CONFIG_SLOB */
+gfp_t kmalloc_fix_flags(gfp_t flags)
+{
+ gfp_t invalid_mask = flags & GFP_SLAB_BUG_MASK;
+
+ flags &= ~GFP_SLAB_BUG_MASK;
+ pr_warn("Unexpected gfp: %#x (%pGg). Fixing up to gfp: %#x (%pGg). Fix your code!\n",
+ invalid_mask, &invalid_mask, flags, &flags);
+ dump_stack();
+
+ return flags;
+}
+
/*
* To avoid unnecessary overhead, we pass through large allocation requests
* directly to the page allocator. We use __GFP_COMP, because we will need to
@@ -1335,12 +828,15 @@
void *ret = NULL;
struct page *page;
+ if (unlikely(flags & GFP_SLAB_BUG_MASK))
+ flags = kmalloc_fix_flags(flags);
+
flags |= __GFP_COMP;
page = alloc_pages(flags, order);
if (likely(page)) {
ret = page_address(page);
- mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE,
- 1 << order);
+ mod_lruvec_page_state(page, NR_SLAB_UNRECLAIMABLE_B,
+ PAGE_SIZE << order);
}
ret = kasan_kmalloc_large(ret, size, flags);
/* As ret might get tagged, call kmemleak hook after KASAN. */
@@ -1437,12 +933,12 @@
void *slab_start(struct seq_file *m, loff_t *pos)
{
mutex_lock(&slab_mutex);
- return seq_list_start(&slab_root_caches, *pos);
+ 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_root_caches, pos);
+ return seq_list_next(p, &slab_caches, pos);
}
void slab_stop(struct seq_file *m, void *p)
@@ -1450,27 +946,6 @@
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;
@@ -1478,10 +953,8 @@
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,
+ s->name, sinfo.active_objs, sinfo.num_objs, s->size,
sinfo.objects_per_slab, (1 << sinfo.cache_order));
seq_printf(m, " : tunables %4u %4u %4u",
@@ -1494,9 +967,9 @@
static int slab_show(struct seq_file *m, void *p)
{
- struct kmem_cache *s = list_entry(p, struct kmem_cache, root_caches_node);
+ struct kmem_cache *s = list_entry(p, struct kmem_cache, list);
- if (p == slab_root_caches.next)
+ if (p == slab_caches.next)
print_slabinfo_header(m);
cache_show(s, m);
return 0;
@@ -1523,49 +996,26 @@
pr_info("Name Used Total\n");
list_for_each_entry_safe(s, s2, &slab_caches, list) {
- if (!is_root_cache(s) || (s->flags & SLAB_RECLAIM_ACCOUNT))
+ if (s->flags & SLAB_RECLAIM_ACCOUNT)
continue;
get_slabinfo(s, &sinfo);
if (sinfo.num_objs > 0)
- pr_info("%-17s %10luKB %10luKB\n", cache_name(s),
+ pr_info("%-17s %10luKB %10luKB\n", s->name,
(sinfo.active_objs * s->size) / 1024,
(sinfo.num_objs * s->size) / 1024);
}
mutex_unlock(&slab_mutex);
}
-#if defined(CONFIG_MEMCG)
-void *memcg_slab_start(struct seq_file *m, loff_t *pos)
-{
- struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
-
- mutex_lock(&slab_mutex);
- return seq_list_start(&memcg->kmem_caches, *pos);
-}
-
-void *memcg_slab_next(struct seq_file *m, void *p, loff_t *pos)
-{
- struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
-
- return seq_list_next(p, &memcg->kmem_caches, pos);
-}
-
-void memcg_slab_stop(struct seq_file *m, void *p)
-{
- mutex_unlock(&slab_mutex);
-}
-
+#if defined(CONFIG_MEMCG_KMEM)
int memcg_slab_show(struct seq_file *m, void *p)
{
- struct kmem_cache *s = list_entry(p, struct kmem_cache,
- memcg_params.kmem_caches_node);
- struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
-
- if (p == memcg->kmem_caches.next)
- print_slabinfo_header(m);
- cache_show(s, m);
+ /*
+ * Deprecated.
+ * Please, take a look at tools/cgroup/slabinfo.py .
+ */
return 0;
}
#endif
@@ -1595,89 +1045,31 @@
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 const struct proc_ops slabinfo_proc_ops = {
+ .proc_flags = PROC_ENTRY_PERMANENT,
+ .proc_open = slabinfo_open,
+ .proc_read = seq_read,
+ .proc_write = slabinfo_write,
+ .proc_lseek = seq_lseek,
+ .proc_release = seq_release,
};
static int __init slab_proc_init(void)
{
- proc_create("slabinfo", SLABINFO_RIGHTS, NULL,
- &proc_slabinfo_operations);
+ proc_create("slabinfo", SLABINFO_RIGHTS, NULL, &slabinfo_proc_ops);
return 0;
}
module_init(slab_proc_init);
-#if defined(CONFIG_DEBUG_FS) && defined(CONFIG_MEMCG_KMEM)
-/*
- * Display information about kmem caches that have child memcg caches.
- */
-static int memcg_slabinfo_show(struct seq_file *m, void *unused)
-{
- struct kmem_cache *s, *c;
- struct slabinfo sinfo;
-
- mutex_lock(&slab_mutex);
- seq_puts(m, "# <name> <css_id[:dead|deact]> <active_objs> <num_objs>");
- seq_puts(m, " <active_slabs> <num_slabs>\n");
- list_for_each_entry(s, &slab_root_caches, root_caches_node) {
- /*
- * Skip kmem caches that don't have any memcg children.
- */
- if (list_empty(&s->memcg_params.children))
- continue;
-
- memset(&sinfo, 0, sizeof(sinfo));
- get_slabinfo(s, &sinfo);
- seq_printf(m, "%-17s root %6lu %6lu %6lu %6lu\n",
- cache_name(s), sinfo.active_objs, sinfo.num_objs,
- sinfo.active_slabs, sinfo.num_slabs);
-
- for_each_memcg_cache(c, s) {
- struct cgroup_subsys_state *css;
- char *status = "";
-
- css = &c->memcg_params.memcg->css;
- if (!(css->flags & CSS_ONLINE))
- status = ":dead";
- else if (c->flags & SLAB_DEACTIVATED)
- status = ":deact";
-
- memset(&sinfo, 0, sizeof(sinfo));
- get_slabinfo(c, &sinfo);
- seq_printf(m, "%-17s %4d%-6s %6lu %6lu %6lu %6lu\n",
- cache_name(c), css->id, status,
- sinfo.active_objs, sinfo.num_objs,
- sinfo.active_slabs, sinfo.num_slabs);
- }
- }
- mutex_unlock(&slab_mutex);
- return 0;
-}
-DEFINE_SHOW_ATTRIBUTE(memcg_slabinfo);
-
-static int __init memcg_slabinfo_init(void)
-{
- debugfs_create_file("memcg_slabinfo", S_IFREG | S_IRUGO,
- NULL, NULL, &memcg_slabinfo_fops);
- return 0;
-}
-
-late_initcall(memcg_slabinfo_init);
-#endif /* CONFIG_DEBUG_FS && CONFIG_MEMCG_KMEM */
#endif /* CONFIG_SLAB || CONFIG_SLUB_DEBUG */
static __always_inline void *__do_krealloc(const void *p, size_t new_size,
gfp_t flags)
{
void *ret;
- size_t ks = 0;
+ size_t ks;
- if (p)
- ks = ksize(p);
+ ks = ksize(p);
if (ks >= new_size) {
p = kasan_krealloc((void *)p, new_size, flags);
@@ -1692,28 +1084,6 @@
}
/**
- * __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.
- *
- * Return: pointer to the allocated memory or %NULL in case of error
- */
-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.
@@ -1744,28 +1114,27 @@
EXPORT_SYMBOL(krealloc);
/**
- * kzfree - like kfree but zero memory
+ * kfree_sensitive - Clear sensitive information in memory before freeing
* @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.
+ * If @p is %NULL, kfree_sensitive() 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)
+void kfree_sensitive(const void *p)
{
size_t ks;
void *mem = (void *)p;
- if (unlikely(ZERO_OR_NULL_PTR(mem)))
- return;
ks = ksize(mem);
- memzero_explicit(mem, ks);
+ if (ks)
+ memzero_explicit(mem, ks);
kfree(mem);
}
-EXPORT_SYMBOL(kzfree);
+EXPORT_SYMBOL(kfree_sensitive);
/**
* ksize - get the actual amount of memory allocated for a given object
@@ -1785,8 +1154,6 @@
{
size_t size;
- if (WARN_ON_ONCE(!objp))
- return 0;
/*
* We need to check that the pointed to object is valid, and only then
* unpoison the shadow memory below. We use __kasan_check_read(), to
@@ -1800,7 +1167,7 @@
* We want to perform the check before __ksize(), to avoid potentially
* crashing in __ksize() due to accessing invalid metadata.
*/
- if (unlikely(objp == ZERO_SIZE_PTR) || !__kasan_check_read(objp, 1))
+ if (unlikely(ZERO_OR_NULL_PTR(objp)) || !__kasan_check_read(objp, 1))
return 0;
size = __ksize(objp);