sysv,ipc: cacheline align kern_ipc_perm

Assign 'struct kern_ipc_perm' its own cacheline to avoid false sharing
with sysv ipc calls.

While the structure itself is rather read-mostly throughout the lifespan
of ipc, the spinlock causes most of the invalidations.  One example is
commit 31a7c474 ("ipc/sem.c: cacheline align the ipc spinlock for
semaphores").  Therefore, extend this to all ipc.

The effect of cacheline alignment on sems can be seen in sembench, which
deals mostly with semtimedop wait/wakes is seen to improve raw
throughput (worker loops) between 8 to 12% on a 24-core x86 with over 4
threads.

Link: http://lkml.kernel.org/r/1486673582-6979-4-git-send-email-dave@stgolabs.netSigned-off-by: Davidlohr Bueso <dbueso@suse.de>
Cc: Manfred Spraul <manfred@colorfullife.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/linux/ipc.h

@@ -8,8 +8,7 @@
 #define IPCMNI 32768  /* <= MAX_INT limit for ipc arrays (including sysctl changes) */
 
 /* used by in-kernel data structures */
-struct kern_ipc_perm
-{
+struct kern_ipc_perm {
 	spinlock_t	lock;
 	bool		deleted;
 	int		id;
@@ -18,9 +17,9 @@ struct kern_ipc_perm
 	kgid_t		gid;
 	kuid_t		cuid;
 	kgid_t		cgid;
-	umode_t		mode; 
+	umode_t		mode;
 	unsigned long	seq;
 	void		*security;
-};
+} ____cacheline_aligned_in_smp;
 
 #endif /* _LINUX_IPC_H */

include/linux/sem.h

@@ -10,8 +10,7 @@ struct task_struct;
 
 /* One sem_array data structure for each set of semaphores in the system. */
 struct sem_array {
-	struct kern_ipc_perm	____cacheline_aligned_in_smp
-				sem_perm;	/* permissions .. see ipc.h */
+	struct kern_ipc_perm	sem_perm;	/* permissions .. see ipc.h */
 	time_t			sem_ctime;	/* last change time */
 	struct sem		*sem_base;	/* ptr to first semaphore in array */
 	struct list_head	pending_alter;	/* pending operations */