summaryrefslogtreecommitdiff
path: root/mm/percpu-internal.h
diff options
context:
space:
mode:
Diffstat (limited to 'mm/percpu-internal.h')
-rw-r--r--mm/percpu-internal.h45
1 files changed, 38 insertions, 7 deletions
diff --git a/mm/percpu-internal.h b/mm/percpu-internal.h
index 70b1ea23f4d2..4b3d6ec43703 100644
--- a/mm/percpu-internal.h
+++ b/mm/percpu-internal.h
@@ -4,6 +4,7 @@
#include <linux/types.h>
#include <linux/percpu.h>
+#include <linux/memcontrol.h>
/*
* pcpu_block_md is the metadata block struct.
@@ -31,6 +32,19 @@ struct pcpu_block_md {
int nr_bits; /* total bits responsible for */
};
+struct pcpuobj_ext {
+#ifdef CONFIG_MEMCG
+ struct obj_cgroup *cgroup;
+#endif
+#ifdef CONFIG_MEM_ALLOC_PROFILING
+ union codetag_ref tag;
+#endif
+};
+
+#if defined(CONFIG_MEMCG) || defined(CONFIG_MEM_ALLOC_PROFILING)
+#define NEED_PCPUOBJ_EXT
+#endif
+
struct pcpu_chunk {
#ifdef CONFIG_PERCPU_STATS
int nr_alloc; /* # of allocations */
@@ -40,10 +54,17 @@ struct pcpu_chunk {
struct list_head list; /* linked to pcpu_slot lists */
int free_bytes; /* free bytes in the chunk */
struct pcpu_block_md chunk_md;
- void *base_addr; /* base address of this chunk */
+ unsigned long *bound_map; /* boundary map */
+
+ /*
+ * base_addr is the base address of this chunk.
+ * To reduce false sharing, current layout is optimized to make sure
+ * base_addr locate in the different cacheline with free_bytes and
+ * chunk_md.
+ */
+ void *base_addr ____cacheline_aligned_in_smp;
unsigned long *alloc_map; /* allocation map */
- unsigned long *bound_map; /* boundary map */
struct pcpu_block_md *md_blocks; /* metadata blocks */
void *data; /* chunk data */
@@ -56,8 +77,8 @@ struct pcpu_chunk {
int end_offset; /* additional area required to
have the region end page
aligned */
-#ifdef CONFIG_MEMCG_KMEM
- struct obj_cgroup **obj_cgroups; /* vector of object cgroups */
+#ifdef NEED_PCPUOBJ_EXT
+ struct pcpuobj_ext *obj_exts; /* vector of object cgroups */
#endif
int nr_pages; /* # of pages served by this chunk */
@@ -66,6 +87,15 @@ struct pcpu_chunk {
unsigned long populated[]; /* populated bitmap */
};
+static inline bool need_pcpuobj_ext(void)
+{
+ if (IS_ENABLED(CONFIG_MEM_ALLOC_PROFILING))
+ return true;
+ if (!mem_cgroup_kmem_disabled())
+ return true;
+ return false;
+}
+
extern spinlock_t pcpu_lock;
extern struct list_head *pcpu_chunk_lists;
@@ -118,14 +148,15 @@ static inline int pcpu_chunk_map_bits(struct pcpu_chunk *chunk)
* @size: size of area to allocate in bytes
*
* For each accounted object there is an extra space which is used to store
- * obj_cgroup membership. Charge it too.
+ * obj_cgroup membership if kmemcg is not disabled. Charge it too.
*/
static inline size_t pcpu_obj_full_size(size_t size)
{
size_t extra_size = 0;
-#ifdef CONFIG_MEMCG_KMEM
- extra_size += size / PCPU_MIN_ALLOC_SIZE * sizeof(struct obj_cgroup *);
+#ifdef CONFIG_MEMCG
+ if (!mem_cgroup_kmem_disabled())
+ extra_size += size / PCPU_MIN_ALLOC_SIZE * sizeof(struct obj_cgroup *);
#endif
return size * num_possible_cpus() + extra_size;