diff --git a/drivers/infiniband/hw/ehca/ehca_irq.c b/drivers/infiniband/hw/ehca/ehca_irq.c
index 4b89b791be6a3cf5fdb7947638778ddd4451f8ab..42be0b15084bb2445e6024eea21033d765bf7438 100644
--- a/drivers/infiniband/hw/ehca/ehca_irq.c
+++ b/drivers/infiniband/hw/ehca/ehca_irq.c
@@ -826,8 +826,7 @@ static void __cpuinit take_over_work(struct ehca_comp_pool *pool, int cpu)
 		cq = list_entry(cct->cq_list.next, struct ehca_cq, entry);
 
 		list_del(&cq->entry);
-		__queue_comp_task(cq, per_cpu_ptr(pool->cpu_comp_tasks,
-						  smp_processor_id()));
+		__queue_comp_task(cq, this_cpu_ptr(pool->cpu_comp_tasks));
 	}
 
 	spin_unlock_irqrestore(&cct->task_lock, flags_cct);
diff --git a/drivers/net/chelsio/sge.c b/drivers/net/chelsio/sge.c
index 8c658cf6f62f3066d84c3b7e45ce79d6d0979dd4..109d2783e4d88fc6823b57d36dd8138a30e5d68b 100644
--- a/drivers/net/chelsio/sge.c
+++ b/drivers/net/chelsio/sge.c
@@ -1378,7 +1378,7 @@ static void sge_rx(struct sge *sge, struct freelQ *fl, unsigned int len)
 	}
 	__skb_pull(skb, sizeof(*p));
 
-	st = per_cpu_ptr(sge->port_stats[p->iff], smp_processor_id());
+	st = this_cpu_ptr(sge->port_stats[p->iff]);
 
 	skb->protocol = eth_type_trans(skb, adapter->port[p->iff].dev);
 	if ((adapter->flags & RX_CSUM_ENABLED) && p->csum == 0xffff &&
@@ -1780,8 +1780,7 @@ netdev_tx_t t1_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct adapter *adapter = dev->ml_priv;
 	struct sge *sge = adapter->sge;
-	struct sge_port_stats *st = per_cpu_ptr(sge->port_stats[dev->if_port],
-						smp_processor_id());
+	struct sge_port_stats *st = this_cpu_ptr(sge->port_stats[dev->if_port]);
 	struct cpl_tx_pkt *cpl;
 	struct sk_buff *orig_skb = skb;
 	int ret;
diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c
index 1bc654a73c4758262e8e07e72ccd0b62c915813a..8ebeb76a373d862c8d157017917990bf626e11dd 100644
--- a/drivers/net/loopback.c
+++ b/drivers/net/loopback.c
@@ -81,7 +81,7 @@ static netdev_tx_t loopback_xmit(struct sk_buff *skb,
 
 	/* it's OK to use per_cpu_ptr() because BHs are off */
 	pcpu_lstats = dev->ml_priv;
-	lb_stats = per_cpu_ptr(pcpu_lstats, smp_processor_id());
+	lb_stats = this_cpu_ptr(pcpu_lstats);
 
 	len = skb->len;
 	if (likely(netif_rx(skb) == NET_RX_SUCCESS)) {
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index bba12824defad2c8d5cee1baaff488576beda8d7..d527fd384582e75f872ad40ba001353bdef3aab3 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -3932,7 +3932,7 @@ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac)
 	 * per cpu locality group is to reduce the contention between block
 	 * request from multiple CPUs.
 	 */
-	ac->ac_lg = per_cpu_ptr(sbi->s_locality_groups, raw_smp_processor_id());
+	ac->ac_lg = __this_cpu_ptr(sbi->s_locality_groups);
 
 	/* we're going to use group allocation */
 	ac->ac_flags |= EXT4_MB_HINT_GROUP_ALLOC;