diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 05a2c9eefc08..acc6f64f0cb8 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -36,6 +36,7 @@
 #include <linux/crash_dump.h>
 #include <linux/memory.h>
 #include <linux/of.h>
+#include <linux/locallock.h>
 #include <asm/io.h>
 #include <asm/prom.h>
 #include <asm/rtas.h>
@@ -177,6 +178,7 @@ static int tce_build_pSeriesLP(struct iommu_table *tbl, long tcenum,
 }
 
 static DEFINE_PER_CPU(__be64 *, tce_page);
+static DEFINE_LOCAL_IRQ_LOCK(tcp_page_lock);
 
 static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 				     long npages, unsigned long uaddr,
@@ -197,7 +199,8 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 		                           direction, attrs);
 	}
 
-	local_irq_save(flags);	/* to protect tcep and the page behind it */
+	/* to protect tcep and the page behind it */
+	local_lock_irqsave(tcp_page_lock, flags);
 
 	tcep = __get_cpu_var(tce_page);
 
@@ -208,7 +211,7 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 		tcep = (__be64 *)__get_free_page(GFP_ATOMIC);
 		/* If allocation fails, fall back to the loop implementation */
 		if (!tcep) {
-			local_irq_restore(flags);
+			local_unlock_irqrestore(tcp_page_lock, flags);
 			return tce_build_pSeriesLP(tbl, tcenum, npages, uaddr,
 					    direction, attrs);
 		}
@@ -242,7 +245,7 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 		tcenum += limit;
 	} while (npages > 0 && !rc);
 
-	local_irq_restore(flags);
+	local_unlock_irqrestore(tcp_page_lock, flags);
 
 	if (unlikely(rc == H_NOT_ENOUGH_RESOURCES)) {
 		ret = (int)rc;
@@ -397,13 +400,14 @@ static int tce_setrange_multi_pSeriesLP(unsigned long start_pfn,
 	u64 rc = 0;
 	long l, limit;
 
-	local_irq_disable();	/* to protect tcep and the page behind it */
+	/* to protect tcep and the page behind it */
+	local_lock_irq(tcp_page_lock);
 	tcep = __get_cpu_var(tce_page);
 
 	if (!tcep) {
 		tcep = (__be64 *)__get_free_page(GFP_ATOMIC);
 		if (!tcep) {
-			local_irq_enable();
+			local_unlock_irq(tcp_page_lock);
 			return -ENOMEM;
 		}
 		__get_cpu_var(tce_page) = tcep;
@@ -449,7 +453,7 @@ static int tce_setrange_multi_pSeriesLP(unsigned long start_pfn,
 
 	/* error cleanup: caller will clear whole range */
 
-	local_irq_enable();
+	local_unlock_irq(tcp_page_lock);
 	return rc;
 }
 
diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c
index f97e7dac3a98..36ed02aa5575 100644
--- a/drivers/tty/sysrq.c
+++ b/drivers/tty/sysrq.c
@@ -206,7 +206,7 @@ static struct sysrq_key_op sysrq_showlocks_op = {
 #endif
 
 #ifdef CONFIG_SMP
-static DEFINE_SPINLOCK(show_lock);
+static DEFINE_RAW_SPINLOCK(show_lock);
 
 static void showacpu(void *dummy)
 {
@@ -216,10 +216,10 @@ static void showacpu(void *dummy)
 	if (idle_cpu(smp_processor_id()))
 		return;
 
-	spin_lock_irqsave(&show_lock, flags);
+	raw_spin_lock_irqsave(&show_lock, flags);
 	printk(KERN_INFO "CPU%d:\n", smp_processor_id());
 	show_stack(NULL, NULL);
-	spin_unlock_irqrestore(&show_lock, flags);
+	raw_spin_unlock_irqrestore(&show_lock, flags);
 }
 
 static void sysrq_showregs_othercpus(struct work_struct *dummy)
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 89c490b405ad..47d228982a58 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -91,6 +91,31 @@ static inline void softirq_clr_runner(unsigned int sirq)
 	sr->runner[sirq] = NULL;
 }
 
+static bool softirq_check_runner_tsk(struct task_struct *tsk,
+				     unsigned int *pending)
+{
+	bool ret = false;
+
+	if (!tsk)
+		return ret;
+
+	/*
+	 * The wakeup code in rtmutex.c wakes up the task
+	 * _before_ it sets pi_blocked_on to NULL under
+	 * tsk->pi_lock. So we need to check for both: state
+	 * and pi_blocked_on.
+	 */
+	raw_spin_lock(&tsk->pi_lock);
+	if (tsk->pi_blocked_on || tsk->state == TASK_RUNNING) {
+		/* Clear all bits pending in that task */
+		*pending &= ~(tsk->softirqs_raised);
+		ret = true;
+	}
+	raw_spin_unlock(&tsk->pi_lock);
+
+	return ret;
+}
+
 /*
  * On preempt-rt a softirq running context might be blocked on a
  * lock. There might be no other runnable task on this CPU because the
@@ -103,6 +128,7 @@ static inline void softirq_clr_runner(unsigned int sirq)
  */
 void softirq_check_pending_idle(void)
 {
+	struct task_struct *tsk;
 	static int rate_limit;
 	struct softirq_runner *sr = &__get_cpu_var(softirq_runners);
 	u32 warnpending;
@@ -112,24 +138,23 @@ void softirq_check_pending_idle(void)
 		return;
 
 	warnpending = local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK;
+	if (!warnpending)
+		return;
 	for (i = 0; i < NR_SOFTIRQS; i++) {
-		struct task_struct *tsk = sr->runner[i];
+		tsk = sr->runner[i];
 
-		/*
-		 * The wakeup code in rtmutex.c wakes up the task
-		 * _before_ it sets pi_blocked_on to NULL under
-		 * tsk->pi_lock. So we need to check for both: state
-		 * and pi_blocked_on.
-		 */
-		if (tsk) {
-			raw_spin_lock(&tsk->pi_lock);
-			if (tsk->pi_blocked_on || tsk->state == TASK_RUNNING) {
-				/* Clear all bits pending in that task */
-				warnpending &= ~(tsk->softirqs_raised);
-				warnpending &= ~(1 << i);
-			}
-			raw_spin_unlock(&tsk->pi_lock);
-		}
+		if (softirq_check_runner_tsk(tsk, &warnpending))
+			warnpending &= ~(1 << i);
+	}
+
+	if (warnpending) {
+		tsk = __this_cpu_read(ksoftirqd);
+		softirq_check_runner_tsk(tsk, &warnpending);
+	}
+
+	if (warnpending) {
+		tsk = __this_cpu_read(ktimer_softirqd);
+		softirq_check_runner_tsk(tsk, &warnpending);
 	}
 
 	if (warnpending) {
diff --git a/localversion-rt b/localversion-rt
index f2aa035883e8..34eca4e89203 100644
--- a/localversion-rt
+++ b/localversion-rt
@@ -1 +1 @@
--rt115
+-rt116