Update Linux to v5.4.2
Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 3a7ac4f..f9fb27b 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -17,6 +17,7 @@
#include <linux/uaccess.h>
#include <linux/seq_file.h>
#include <linux/proc_fs.h>
+#include <linux/debugfs.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
#include <asm/page.h>
@@ -53,7 +54,7 @@
SLAB_FAILSLAB | SLAB_KASAN)
#define SLAB_MERGE_SAME (SLAB_RECLAIM_ACCOUNT | SLAB_CACHE_DMA | \
- SLAB_ACCOUNT)
+ SLAB_CACHE_DMA32 | SLAB_ACCOUNT)
/*
* Merge control. If this is set then no merging of slab caches will occur.
@@ -130,6 +131,9 @@
#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)
{
@@ -140,13 +144,18 @@
}
static int init_memcg_params(struct kmem_cache *s,
- struct mem_cgroup *memcg, struct kmem_cache *root_cache)
+ 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;
- s->memcg_params.memcg = memcg;
INIT_LIST_HEAD(&s->memcg_params.children_node);
INIT_LIST_HEAD(&s->memcg_params.kmem_caches_node);
return 0;
@@ -169,8 +178,13 @@
static void destroy_memcg_params(struct kmem_cache *s)
{
- if (is_root_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)
@@ -221,11 +235,13 @@
return ret;
}
-void memcg_link_cache(struct kmem_cache *s)
+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,
@@ -244,7 +260,7 @@
}
#else
static inline int init_memcg_params(struct kmem_cache *s,
- struct mem_cgroup *memcg, struct kmem_cache *root_cache)
+ struct kmem_cache *root_cache)
{
return 0;
}
@@ -384,7 +400,7 @@
s->useroffset = useroffset;
s->usersize = usersize;
- err = init_memcg_params(s, memcg, root_cache);
+ err = init_memcg_params(s, root_cache);
if (err)
goto out_free_cache;
@@ -394,7 +410,7 @@
s->refcount = 1;
list_add(&s->list, &slab_caches);
- memcg_link_cache(s);
+ memcg_link_cache(s, memcg);
out:
if (err)
return ERR_PTR(err);
@@ -406,8 +422,9 @@
goto out;
}
-/*
- * kmem_cache_create_usercopy - Create a cache.
+/**
+ * kmem_cache_create_usercopy - Create a cache with a region suitable
+ * for copying to userspace
* @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.
@@ -416,7 +433,6 @@
* @usersize: Usercopy region size
* @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.
*
@@ -425,12 +441,14 @@
* %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
+ * %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.
+ *
+ * Return: a pointer to the cache on success, NULL on failure.
*/
struct kmem_cache *
kmem_cache_create_usercopy(const char *name,
@@ -514,6 +532,31 @@
}
EXPORT_SYMBOL(kmem_cache_create_usercopy);
+/**
+ * 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.
+ *
+ * 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.
+ *
+ * Return: a pointer to the cache on success, NULL on failure.
+ */
struct kmem_cache *
kmem_cache_create(const char *name, unsigned int size, unsigned int align,
slab_flags_t flags, void (*ctor)(void *))
@@ -613,7 +656,7 @@
* The memory cgroup could have been offlined while the cache
* creation work was pending.
*/
- if (memcg->kmem_state != KMEM_ONLINE || root_cache->memcg_params.dying)
+ if (memcg->kmem_state != KMEM_ONLINE)
goto out_unlock;
idx = memcg_cache_id(memcg);
@@ -650,7 +693,7 @@
}
/*
- * Since readers won't lock (see cache_from_memcg_idx()), we need a
+ * 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.
*/
@@ -664,74 +707,95 @@
put_online_cpus();
}
-static void kmemcg_deactivate_workfn(struct work_struct *work)
+static void kmemcg_workfn(struct work_struct *work)
{
struct kmem_cache *s = container_of(work, struct kmem_cache,
- memcg_params.deact_work);
+ memcg_params.work);
get_online_cpus();
get_online_mems();
mutex_lock(&slab_mutex);
-
- s->memcg_params.deact_fn(s);
-
+ s->memcg_params.work_fn(s);
mutex_unlock(&slab_mutex);
put_online_mems();
put_online_cpus();
-
- /* done, put the ref from slab_deactivate_memcg_cache_rcu_sched() */
- css_put(&s->memcg_params.memcg->css);
}
-static void kmemcg_deactivate_rcufn(struct rcu_head *head)
+static void kmemcg_rcufn(struct rcu_head *head)
{
struct kmem_cache *s = container_of(head, struct kmem_cache,
- memcg_params.deact_rcu_head);
+ memcg_params.rcu_head);
/*
- * We need to grab blocking locks. Bounce to ->deact_work. The
+ * 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.deact_work, kmemcg_deactivate_workfn);
- queue_work(memcg_kmem_cache_wq, &s->memcg_params.deact_work);
+ INIT_WORK(&s->memcg_params.work, kmemcg_workfn);
+ queue_work(memcg_kmem_cache_wq, &s->memcg_params.work);
}
-/**
- * slab_deactivate_memcg_cache_rcu_sched - schedule deactivation after a
- * sched RCU grace period
- * @s: target kmem_cache
- * @deact_fn: deactivation function to call
- *
- * Schedule @deact_fn to be invoked with online cpus, mems and slab_mutex
- * held after a sched RCU grace period. The slab is guaranteed to stay
- * alive until @deact_fn is finished. This is to be used from
- * __kmemcg_cache_deactivate().
- */
-void slab_deactivate_memcg_cache_rcu_sched(struct kmem_cache *s,
- void (*deact_fn)(struct kmem_cache *))
+static void kmemcg_cache_shutdown_fn(struct kmem_cache *s)
{
- if (WARN_ON_ONCE(is_root_cache(s)) ||
- WARN_ON_ONCE(s->memcg_params.deact_fn))
- return;
-
- if (s->memcg_params.root_cache->memcg_params.dying)
- return;
-
- /* pin memcg so that @s doesn't get destroyed in the middle */
- css_get(&s->memcg_params.memcg->css);
-
- s->memcg_params.deact_fn = deact_fn;
- call_rcu_sched(&s->memcg_params.deact_rcu_head, kmemcg_deactivate_rcufn);
+ WARN_ON(shutdown_cache(s));
}
-void memcg_deactivate_kmem_caches(struct mem_cgroup *memcg)
+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);
@@ -746,30 +810,20 @@
if (!c)
continue;
- __kmemcg_cache_deactivate(c);
+ kmemcg_cache_deactivate(c);
arr->entries[idx] = NULL;
}
- mutex_unlock(&slab_mutex);
-
- put_online_mems();
- put_online_cpus();
-}
-
-void memcg_destroy_kmem_caches(struct mem_cgroup *memcg)
-{
- struct kmem_cache *s, *s2;
-
- get_online_cpus();
- get_online_mems();
-
- mutex_lock(&slab_mutex);
- list_for_each_entry_safe(s, s2, &memcg->kmem_caches,
- memcg_params.kmem_caches_node) {
- /*
- * The cgroup is about to be freed and therefore has no charges
- * left. Hence, all its caches must be empty by now.
- */
- BUG_ON(shutdown_cache(s));
+ 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);
@@ -834,16 +888,15 @@
static void flush_memcg_workqueue(struct kmem_cache *s)
{
- mutex_lock(&slab_mutex);
+ spin_lock_irq(&memcg_kmem_wq_lock);
s->memcg_params.dying = true;
- mutex_unlock(&slab_mutex);
+ spin_unlock_irq(&memcg_kmem_wq_lock);
/*
- * SLUB deactivates the kmem_caches through call_rcu_sched. Make
+ * SLAB and SLUB deactivate the kmem_caches through call_rcu. Make
* sure all registered rcu callbacks have been invoked.
*/
- if (IS_ENABLED(CONFIG_SLUB))
- rcu_barrier_sched();
+ rcu_barrier();
/*
* SLAB and SLUB create memcg kmem_caches through workqueue and SLUB
@@ -912,6 +965,8 @@
*
* Releases as many slabs as possible for a cache.
* To help debugging, a zero exit status indicates all slabs were released.
+ *
+ * Return: %0 if all slabs were released, non-zero otherwise
*/
int kmem_cache_shrink(struct kmem_cache *cachep)
{
@@ -927,6 +982,43 @@
}
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;
@@ -939,10 +1031,19 @@
unsigned int useroffset, unsigned int usersize)
{
int err;
+ unsigned int align = ARCH_KMALLOC_MINALIGN;
s->name = name;
s->size = s->object_size = size;
- s->align = calculate_alignment(flags, ARCH_KMALLOC_MINALIGN, size);
+
+ /*
+ * For power of two sizes, guarantee natural alignment for kmalloc
+ * caches, regardless of SL*B debugging options.
+ */
+ if (is_power_of_2(size))
+ align = max(align, size);
+ s->align = calculate_alignment(flags, align, size);
+
s->useroffset = useroffset;
s->usersize = usersize;
@@ -968,19 +1069,16 @@
create_boot_cache(s, name, size, flags, useroffset, usersize);
list_add(&s->list, &slab_caches);
- memcg_link_cache(s);
+ memcg_link_cache(s, NULL);
s->refcount = 1;
return s;
}
-struct kmem_cache *kmalloc_caches[KMALLOC_SHIFT_HIGH + 1] __ro_after_init;
+struct kmem_cache *
+kmalloc_caches[NR_KMALLOC_TYPES][KMALLOC_SHIFT_HIGH + 1] __ro_after_init =
+{ /* initialization for https://bugs.llvm.org/show_bug.cgi?id=42570 */ };
EXPORT_SYMBOL(kmalloc_caches);
-#ifdef CONFIG_ZONE_DMA
-struct kmem_cache *kmalloc_dma_caches[KMALLOC_SHIFT_HIGH + 1] __ro_after_init;
-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
@@ -1033,19 +1131,12 @@
index = size_index[size_index_elem(size)];
} else {
- if (unlikely(size > KMALLOC_MAX_CACHE_SIZE)) {
- WARN_ON(1);
+ if (WARN_ON_ONCE(size > KMALLOC_MAX_CACHE_SIZE))
return NULL;
- }
index = fls(size - 1);
}
-#ifdef CONFIG_ZONE_DMA
- if (unlikely((flags & GFP_DMA)))
- return kmalloc_dma_caches[index];
-
-#endif
- return kmalloc_caches[index];
+ return kmalloc_caches[kmalloc_type(flags)][index];
}
/*
@@ -1059,15 +1150,15 @@
{"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}
+ {"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}
};
/*
@@ -1117,9 +1208,36 @@
}
}
-static void __init new_kmalloc_cache(int idx, slab_flags_t flags)
+static const char *
+kmalloc_cache_name(const char *prefix, unsigned int size)
{
- kmalloc_caches[idx] = create_kmalloc_cache(kmalloc_info[idx].name,
+
+ 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)
+{
+ const char *name;
+
+ 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_info[idx].size, flags, 0,
kmalloc_info[idx].size);
}
@@ -1131,21 +1249,25 @@
*/
void __init create_kmalloc_caches(slab_flags_t flags)
{
- int i;
+ int i, type;
- for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++) {
- if (!kmalloc_caches[i])
- new_kmalloc_cache(i, flags);
+ for (type = KMALLOC_NORMAL; type <= KMALLOC_RECLAIM; type++) {
+ for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++) {
+ if (!kmalloc_caches[type][i])
+ new_kmalloc_cache(i, type, 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);
+ /*
+ * 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 && i == 6 &&
+ !kmalloc_caches[type][1])
+ new_kmalloc_cache(1, type, flags);
+ if (KMALLOC_MIN_SIZE <= 64 && i == 7 &&
+ !kmalloc_caches[type][2])
+ new_kmalloc_cache(2, type, flags);
+ }
}
/* Kmalloc array is now usable */
@@ -1153,16 +1275,15 @@
#ifdef CONFIG_ZONE_DMA
for (i = 0; i <= KMALLOC_SHIFT_HIGH; i++) {
- struct kmem_cache *s = kmalloc_caches[i];
+ struct kmem_cache *s = kmalloc_caches[KMALLOC_NORMAL][i];
if (s) {
unsigned int size = kmalloc_size(i);
- char *n = kasprintf(GFP_NOWAIT,
- "dma-kmalloc-%u", size);
+ const char *n = kmalloc_cache_name("dma-kmalloc", size);
BUG_ON(!n);
- kmalloc_dma_caches[i] = create_kmalloc_cache(n,
- size, SLAB_CACHE_DMA | flags, 0, 0);
+ kmalloc_caches[KMALLOC_DMA][i] = create_kmalloc_cache(
+ n, size, SLAB_CACHE_DMA | flags, 0, 0);
}
}
#endif
@@ -1176,14 +1297,19 @@
*/
void *kmalloc_order(size_t size, gfp_t flags, unsigned int order)
{
- void *ret;
+ void *ret = NULL;
struct page *page;
flags |= __GFP_COMP;
page = alloc_pages(flags, order);
- ret = page ? page_address(page) : NULL;
+ if (likely(page)) {
+ ret = page_address(page);
+ mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE,
+ 1 << order);
+ }
+ ret = kasan_kmalloc_large(ret, size, flags);
+ /* As ret might get tagged, call kmemleak hook after KASAN. */
kmemleak_alloc(ret, size, 1, flags);
- kasan_kmalloc_large(ret, size, flags);
return ret;
}
EXPORT_SYMBOL(kmalloc_order);
@@ -1378,7 +1504,7 @@
#if defined(CONFIG_MEMCG)
void *memcg_slab_start(struct seq_file *m, loff_t *pos)
{
- struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
+ struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
mutex_lock(&slab_mutex);
return seq_list_start(&memcg->kmem_caches, *pos);
@@ -1386,7 +1512,7 @@
void *memcg_slab_next(struct seq_file *m, void *p, loff_t *pos)
{
- struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
+ struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
return seq_list_next(p, &memcg->kmem_caches, pos);
}
@@ -1400,7 +1526,7 @@
{
struct kmem_cache *s = list_entry(p, struct kmem_cache,
memcg_params.kmem_caches_node);
- struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
+ struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
if (p == memcg->kmem_caches.next)
print_slabinfo_header(m);
@@ -1449,6 +1575,64 @@
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,
@@ -1461,7 +1645,7 @@
ks = ksize(p);
if (ks >= new_size) {
- kasan_krealloc((void *)p, new_size, flags);
+ p = kasan_krealloc((void *)p, new_size, flags);
return (void *)p;
}
@@ -1481,6 +1665,8 @@
* 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)
{
@@ -1502,6 +1688,8 @@
* 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.
+ *
+ * Return: pointer to the allocated memory or %NULL in case of error
*/
void *krealloc(const void *p, size_t new_size, gfp_t flags)
{
@@ -1513,7 +1701,7 @@
}
ret = __do_krealloc(p, new_size, flags);
- if (ret && p != ret)
+ if (ret && kasan_reset_tag(p) != kasan_reset_tag(ret))
kfree(p);
return ret;
@@ -1544,6 +1732,52 @@
}
EXPORT_SYMBOL(kzfree);
+/**
+ * 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.
+ *
+ * Return: size of the actual memory used by @objp in bytes
+ */
+size_t ksize(const void *objp)
+{
+ 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
+ * generate a more useful report at the time ksize() is called (rather
+ * than later where behaviour is undefined due to potential
+ * use-after-free or double-free).
+ *
+ * If the pointed to memory is invalid we return 0, to avoid users of
+ * ksize() writing to and potentially corrupting the memory region.
+ *
+ * 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))
+ return 0;
+
+ size = __ksize(objp);
+ /*
+ * We assume that ksize callers could use whole allocated area,
+ * so we need to unpoison this area.
+ */
+ kasan_unpoison_shadow(objp, size);
+ return size;
+}
+EXPORT_SYMBOL(ksize);
+
/* Tracepoints definitions. */
EXPORT_TRACEPOINT_SYMBOL(kmalloc);
EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc);