smp: Avoid using two cache lines for struct call_single_data

struct call_single_data is used in IPIs to transfer information between
CPUs.  Its size is bigger than sizeof(unsigned long) and less than
cache line size.  Currently it is not allocated with any explicit alignment
requirements.  This makes it possible for allocated call_single_data to
cross two cache lines, which results in double the number of the cache lines
that need to be transferred among CPUs.

This can be fixed by requiring call_single_data to be aligned with the
size of call_single_data. Currently the size of call_single_data is the
power of 2.  If we add new fields to call_single_data, we may need to
add padding to make sure the size of new definition is the power of 2
as well.

Fortunately, this is enforced by GCC, which will report bad sizes.

To set alignment requirements of call_single_data to the size of
call_single_data, a struct definition and a typedef is used.

To test the effect of the patch, I used the vm-scalability multiple
thread swap test case (swap-w-seq-mt).  The test will create multiple
threads and each thread will eat memory until all RAM and part of swap
is used, so that huge number of IPIs are triggered when unmapping
memory.  In the test, the throughput of memory writing improves ~5%
compared with misaligned call_single_data, because of faster IPIs.

Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Huang, Ying <ying.huang@intel.com>
[ Add call_single_data_t and align with size of call_single_data. ]
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Aaron Lu <aaron.lu@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/87bmnqd6lz.fsf@yhuang-mobile.sh.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

4 files changed, 8 insertions, 8 deletions

diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index 85c24cace973..81142ce781da 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -13,7 +13,7 @@
 struct nullb_cmd {
 	struct list_head list;
 	struct llist_node ll_list;
-	struct call_single_data csd;
+	call_single_data_t csd;
 	struct request *rq;
 	struct bio *bio;
 	unsigned int tag;
diff --git a/drivers/cpuidle/coupled.c b/drivers/cpuidle/coupled.c
index 71e586d7df71..147f38ea0fcd 100644
--- a/drivers/cpuidle/coupled.c
+++ b/drivers/cpuidle/coupled.c
@@ -119,13 +119,13 @@ struct cpuidle_coupled {
 
 #define CPUIDLE_COUPLED_NOT_IDLE	(-1)
 
-static DEFINE_PER_CPU(struct call_single_data, cpuidle_coupled_poke_cb);
+static DEFINE_PER_CPU(call_single_data_t, cpuidle_coupled_poke_cb);
 
 /*
  * The cpuidle_coupled_poke_pending mask is used to avoid calling
- * __smp_call_function_single with the per cpu call_single_data struct already
+ * __smp_call_function_single with the per cpu call_single_data_t struct already
  * in use.  This prevents a deadlock where two cpus are waiting for each others
- * call_single_data struct to be available
+ * call_single_data_t struct to be available
  */
 static cpumask_t cpuidle_coupled_poke_pending;
 
@@ -339,7 +339,7 @@ static void cpuidle_coupled_handle_poke(void *info)
  */
 static void cpuidle_coupled_poke(int cpu)
 {
-	struct call_single_data *csd = &per_cpu(cpuidle_coupled_poke_cb, cpu);
+	call_single_data_t *csd = &per_cpu(cpuidle_coupled_poke_cb, cpu);
 
 	if (!cpumask_test_and_set_cpu(cpu, &cpuidle_coupled_poke_pending))
 		smp_call_function_single_async(cpu, csd);
@@ -651,7 +651,7 @@ int cpuidle_coupled_register_device(struct cpuidle_device *dev)
 {
 	int cpu;
 	struct cpuidle_device *other_dev;
-	struct call_single_data *csd;
+	call_single_data_t *csd;
 	struct cpuidle_coupled *coupled;
 
 	if (cpumask_empty(&dev->coupled_cpus))
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c
index 51583ae4b1eb..120b6e537b28 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c
@@ -2468,7 +2468,7 @@ static void liquidio_napi_drv_callback(void *arg)
 	if (OCTEON_CN23XX_PF(oct) || droq->cpu_id == this_cpu) {
 		napi_schedule_irqoff(&droq->napi);
 	} else {
-		struct call_single_data *csd = &droq->csd;
+		call_single_data_t *csd = &droq->csd;
 
 		csd->func = napi_schedule_wrapper;
 		csd->info = &droq->napi;
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_droq.h b/drivers/net/ethernet/cavium/liquidio/octeon_droq.h
index 6efd139b894d..f91bc84d1719 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_droq.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_droq.h
@@ -328,7 +328,7 @@ struct octeon_droq {
 
 	u32 cpu_id;
 
-	struct call_single_data csd;
+	call_single_data_t csd;
 };
 
 #define OCT_DROQ_SIZE   (sizeof(struct octeon_droq))