On 11/26/23 03:56, Christophe JAILLET wrote:
Based on pahole, 2 holes can be combined in the 'struct lock_class'. This
saves 8 bytes in the structure on my x86_64.
On a x86_64 configured with allmodconfig, this saves 64kb of memory in
'kernel/locking/lockdep.o', certainly because of:
struct lock_class lock_classes[MAX_LOCKDEP_KEYS];
Before:
text data bss dec hex filename
102501 1912490 11531636 13546627 ceb483 kernel/locking/lockdep.o
After:
102181 1912490 11466100 13480771 cdb343 kernel/locking/lockdep.o
Signed-off-by: Christophe JAILLET <christophe.jaillet@xxxxxxxxxx>
---
After the reorder, pahole gives:
struct lock_class {
struct hlist_node hash_entry; /* 0 16 */
struct list_head lock_entry; /* 16 16 */
struct list_head locks_after; /* 32 16 */
struct list_head locks_before; /* 48 16 */
/* --- cacheline 1 boundary (64 bytes) --- */
const struct lockdep_subclass_key * key; /* 64 8 */
lock_cmp_fn cmp_fn; /* 72 8 */
lock_print_fn print_fn; /* 80 8 */
unsigned int subclass; /* 88 4 */
unsigned int dep_gen_id; /* 92 4 */
long unsigned int usage_mask; /* 96 8 */
const struct lock_trace * usage_traces[10]; /* 104 80 */
/* --- cacheline 2 boundary (128 bytes) was 56 bytes ago --- */
const char * name; /* 184 8 */
/* --- cacheline 3 boundary (192 bytes) --- */
int name_version; /* 192 4 */
u8 wait_type_inner; /* 196 1 */
u8 wait_type_outer; /* 197 1 */
u8 lock_type; /* 198 1 */
/* XXX 1 byte hole, try to pack */
long unsigned int contention_point[4]; /* 200 32 */
long unsigned int contending_point[4]; /* 232 32 */
/* size: 264, cachelines: 5, members: 18 */
/* sum members: 263, holes: 1, sum holes: 1 */
/* last cacheline: 8 bytes */
};
---
include/linux/lockdep_types.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/include/linux/lockdep_types.h b/include/linux/lockdep_types.h
index 2ebc323d345a..857d785e89e6 100644
--- a/include/linux/lockdep_types.h
+++ b/include/linux/lockdep_types.h
@@ -127,12 +127,12 @@ struct lock_class {
unsigned long usage_mask;
const struct lock_trace *usage_traces[LOCK_TRACE_STATES];
+ const char *name;
/*
* Generation counter, when doing certain classes of graph walking,
* to ensure that we check one node only once:
*/
int name_version;
- const char *name;
u8 wait_type_inner;
u8 wait_type_outer;
LGTM
Acked-by: Waiman Long <longman@xxxxxxxxxx>
