diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 4269dba63cf1..7796af4b1d6f 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -31,6 +31,7 @@ config ARM64
 	select GENERIC_EARLY_IOREMAP
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
+	select GENERIC_IRQ_SHOW_LEVEL
 	select GENERIC_PCI_IOMAP
 	select GENERIC_SCHED_CLOCK
 	select GENERIC_SMP_IDLE_THREAD
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index a5abb0062d6e..71f19c4dc0de 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -65,6 +65,14 @@ do {									\
 do {									\
 	compiletime_assert_atomic_type(*p);				\
 	switch (sizeof(*p)) {						\
+	case 1:								\
+		asm volatile ("stlrb %w1, %0"				\
+				: "=Q" (*p) : "r" (v) : "memory");	\
+		break;							\
+	case 2:								\
+		asm volatile ("stlrh %w1, %0"				\
+				: "=Q" (*p) : "r" (v) : "memory");	\
+		break;							\
 	case 4:								\
 		asm volatile ("stlr %w1, %0"				\
 				: "=Q" (*p) : "r" (v) : "memory");	\
@@ -81,6 +89,14 @@ do {									\
 	typeof(*p) ___p1;						\
 	compiletime_assert_atomic_type(*p);				\
 	switch (sizeof(*p)) {						\
+	case 1:								\
+		asm volatile ("ldarb %w0, %1"				\
+			: "=r" (___p1) : "Q" (*p) : "memory");		\
+		break;							\
+	case 2:								\
+		asm volatile ("ldarh %w0, %1"				\
+			: "=r" (___p1) : "Q" (*p) : "memory");		\
+		break;							\
 	case 4:								\
 		asm volatile ("ldar %w0, %1"				\
 			: "=r" (___p1) : "Q" (*p) : "memory");		\
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 195991dadc37..23f25acf43a9 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -1310,7 +1310,7 @@ static const struct of_device_id armpmu_of_device_ids[] = {
 
 static int armpmu_device_probe(struct platform_device *pdev)
 {
-	int i, *irqs;
+	int i, irq, *irqs;
 
 	if (!cpu_pmu)
 		return -ENODEV;
@@ -1319,6 +1319,11 @@ static int armpmu_device_probe(struct platform_device *pdev)
 	if (!irqs)
 		return -ENOMEM;
 
+	/* Don't bother with PPIs; they're already affine */
+	irq = platform_get_irq(pdev, 0);
+	if (irq >= 0 && irq_is_percpu(irq))
+		return 0;
+
 	for (i = 0; i < pdev->num_resources; ++i) {
 		struct device_node *dn;
 		int cpu;
@@ -1327,7 +1332,7 @@ static int armpmu_device_probe(struct platform_device *pdev)
 				      i);
 		if (!dn) {
 			pr_warn("Failed to parse %s/interrupt-affinity[%d]\n",
-				of_node_full_name(dn), i);
+				of_node_full_name(pdev->dev.of_node), i);
 			break;
 		}
 
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index ef7d112f5ce0..b0bd4e5fd5cf 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -67,8 +67,7 @@ static void *__alloc_from_pool(size_t size, struct page **ret_page, gfp_t flags)
 
 		*ret_page = phys_to_page(phys);
 		ptr = (void *)val;
-		if (flags & __GFP_ZERO)
-			memset(ptr, 0, size);
+		memset(ptr, 0, size);
 	}
 
 	return ptr;
@@ -105,7 +104,6 @@ static void *__dma_alloc_coherent(struct device *dev, size_t size,
 		struct page *page;
 		void *addr;
 
-		size = PAGE_ALIGN(size);
 		page = dma_alloc_from_contiguous(dev, size >> PAGE_SHIFT,
 							get_order(size));
 		if (!page)
@@ -113,8 +111,7 @@ static void *__dma_alloc_coherent(struct device *dev, size_t size,
 
 		*dma_handle = phys_to_dma(dev, page_to_phys(page));
 		addr = page_address(page);
-		if (flags & __GFP_ZERO)
-			memset(addr, 0, size);
+		memset(addr, 0, size);
 		return addr;
 	} else {
 		return swiotlb_alloc_coherent(dev, size, dma_handle, flags);
@@ -195,6 +192,8 @@ static void __dma_free(struct device *dev, size_t size,
 {
 	void *swiotlb_addr = phys_to_virt(dma_to_phys(dev, dma_handle));
 
+	size = PAGE_ALIGN(size);
+
 	if (!is_device_dma_coherent(dev)) {
 		if (__free_from_pool(vaddr, size))
 			return;