diff --git a/arch/arm/common/gic.c b/arch/arm/common/gic.c
index 36ae03a3f5d1a07527145ff545ded90888ba0a7b..87dfa9026c5bdcb1ba9d57d718d00da671c8fe21 100644
--- a/arch/arm/common/gic.c
+++ b/arch/arm/common/gic.c
@@ -351,6 +351,25 @@ void __init gic_cascade_irq(unsigned int gic_nr, unsigned int irq)
 	irq_set_chained_handler(irq, gic_handle_cascade_irq);
 }
 
+static u8 gic_get_cpumask(struct gic_chip_data *gic)
+{
+	void __iomem *base = gic_data_dist_base(gic);
+	u32 mask, i;
+
+	for (i = mask = 0; i < 32; i += 4) {
+		mask = readl_relaxed(base + GIC_DIST_TARGET + i);
+		mask |= mask >> 16;
+		mask |= mask >> 8;
+		if (mask)
+			break;
+	}
+
+	if (!mask)
+		pr_crit("GIC CPU mask not found - kernel will fail to boot.\n");
+
+	return mask;
+}
+
 static void __init gic_dist_init(struct gic_chip_data *gic)
 {
 	unsigned int i;
@@ -369,7 +388,9 @@ static void __init gic_dist_init(struct gic_chip_data *gic)
 	/*
 	 * Set all global interrupts to this CPU only.
 	 */
-	cpumask = readl_relaxed(base + GIC_DIST_TARGET + 0);
+	cpumask = gic_get_cpumask(gic);
+	cpumask |= cpumask << 8;
+	cpumask |= cpumask << 16;
 	for (i = 32; i < gic_irqs; i += 4)
 		writel_relaxed(cpumask, base + GIC_DIST_TARGET + i * 4 / 4);
 
@@ -400,7 +421,7 @@ static void __cpuinit gic_cpu_init(struct gic_chip_data *gic)
 	 * Get what the GIC says our CPU mask is.
 	 */
 	BUG_ON(cpu >= NR_GIC_CPU_IF);
-	cpu_mask = readl_relaxed(dist_base + GIC_DIST_TARGET + 0);
+	cpu_mask = gic_get_cpumask(gic);
 	gic_cpu_map[cpu] = cpu_mask;
 
 	/*
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index 73cf03aa981e1b665d9a40f4f80847335ca49441..1c4df27f93322604398d70f9c585332e97374b10 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -37,7 +37,7 @@
  */
 #define PAGE_OFFSET		UL(CONFIG_PAGE_OFFSET)
 #define TASK_SIZE		(UL(CONFIG_PAGE_OFFSET) - UL(0x01000000))
-#define TASK_UNMAPPED_BASE	(UL(CONFIG_PAGE_OFFSET) / 3)
+#define TASK_UNMAPPED_BASE	ALIGN(TASK_SIZE / 3, SZ_16M)
 
 /*
  * The maximum size of a 26-bit user space task.
diff --git a/arch/arm/mach-realview/include/mach/irqs-eb.h b/arch/arm/mach-realview/include/mach/irqs-eb.h
index d6b5073692d2fdda8db2656a032f374894e57463..44754230fdcc3e23098f1cfcacee1530af508da4 100644
--- a/arch/arm/mach-realview/include/mach/irqs-eb.h
+++ b/arch/arm/mach-realview/include/mach/irqs-eb.h
@@ -115,7 +115,7 @@
 /*
  * Only define NR_IRQS if less than NR_IRQS_EB
  */
-#define NR_IRQS_EB		(IRQ_EB_GIC_START + 96)
+#define NR_IRQS_EB		(IRQ_EB_GIC_START + 128)
 
 #if defined(CONFIG_MACH_REALVIEW_EB) \
 	&& (!defined(NR_IRQS) || (NR_IRQS < NR_IRQS_EB))
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 076c26d43864f8a5b3da49ac7231a62e8edde0c2..dda3904dc64c1cb3f7681cf20998397c1e103f76 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -640,7 +640,7 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 
 	if (is_coherent || nommu())
 		addr = __alloc_simple_buffer(dev, size, gfp, &page);
-	else if (gfp & GFP_ATOMIC)
+	else if (!(gfp & __GFP_WAIT))
 		addr = __alloc_from_pool(size, &page);
 	else if (!IS_ENABLED(CONFIG_CMA))
 		addr = __alloc_remap_buffer(dev, size, gfp, prot, &page, caller);