9 files changed, 491 insertions, 224 deletions

diff --git a/arch/arm/common/Kconfig b/arch/arm/common/Kconfig
index 4b71766fb21d..74df9ca2be31 100644
--- a/arch/arm/common/Kconfig
+++ b/arch/arm/common/Kconfig
@@ -1,4 +1,5 @@
 config ARM_GIC
+	select IRQ_DOMAIN
 	bool
 
 config ARM_VIC
diff --git a/arch/arm/common/dmabounce.c b/arch/arm/common/dmabounce.c
index 841df7d21c2f..595ecd290ebf 100644
--- a/arch/arm/common/dmabounce.c
+++ b/arch/arm/common/dmabounce.c
@@ -79,6 +79,8 @@ struct dmabounce_device_info {
 	struct dmabounce_pool	large;
 
 	rwlock_t lock;
+
+	int (*needs_bounce)(struct device *, dma_addr_t, size_t);
 };
 
 #ifdef STATS
@@ -210,114 +212,91 @@ static struct safe_buffer *find_safe_buffer_dev(struct device *dev,
 	if (!dev || !dev->archdata.dmabounce)
 		return NULL;
 	if (dma_mapping_error(dev, dma_addr)) {
-		if (dev)
-			dev_err(dev, "Trying to %s invalid mapping\n", where);
-		else
-			pr_err("unknown device: Trying to %s invalid mapping\n", where);
+		dev_err(dev, "Trying to %s invalid mapping\n", where);
 		return NULL;
 	}
 	return find_safe_buffer(dev->archdata.dmabounce, dma_addr);
 }
 
-static inline dma_addr_t map_single(struct device *dev, void *ptr, size_t size,
-		enum dma_data_direction dir)
+static int needs_bounce(struct device *dev, dma_addr_t dma_addr, size_t size)
 {
-	struct dmabounce_device_info *device_info = dev->archdata.dmabounce;
-	dma_addr_t dma_addr;
-	int needs_bounce = 0;
-
-	if (device_info)
-		DO_STATS ( device_info->map_op_count++ );
-
-	dma_addr = virt_to_dma(dev, ptr);
+	if (!dev || !dev->archdata.dmabounce)
+		return 0;
 
 	if (dev->dma_mask) {
-		unsigned long mask = *dev->dma_mask;
-		unsigned long limit;
+		unsigned long limit, mask = *dev->dma_mask;
 
 		limit = (mask + 1) & ~mask;
 		if (limit && size > limit) {
 			dev_err(dev, "DMA mapping too big (requested %#x "
 				"mask %#Lx)\n", size, *dev->dma_mask);
-			return ~0;
+			return -E2BIG;
 		}
 
-		/*
-		 * Figure out if we need to bounce from the DMA mask.
-		 */
-		needs_bounce = (dma_addr | (dma_addr + size - 1)) & ~mask;
+		/* Figure out if we need to bounce from the DMA mask. */
+		if ((dma_addr | (dma_addr + size - 1)) & ~mask)
+			return 1;
 	}
 
-	if (device_info && (needs_bounce || dma_needs_bounce(dev, dma_addr, size))) {
-		struct safe_buffer *buf;
+	return !!dev->archdata.dmabounce->needs_bounce(dev, dma_addr, size);
+}
 
-		buf = alloc_safe_buffer(device_info, ptr, size, dir);
-		if (buf == 0) {
-			dev_err(dev, "%s: unable to map unsafe buffer %p!\n",
-			       __func__, ptr);
-			return ~0;
-		}
+static inline dma_addr_t map_single(struct device *dev, void *ptr, size_t size,
+		enum dma_data_direction dir)
+{
+	struct dmabounce_device_info *device_info = dev->archdata.dmabounce;
+	struct safe_buffer *buf;
 
-		dev_dbg(dev,
-			"%s: unsafe buffer %p (dma=%#x) mapped to %p (dma=%#x)\n",
-			__func__, buf->ptr, virt_to_dma(dev, buf->ptr),
-			buf->safe, buf->safe_dma_addr);
+	if (device_info)
+		DO_STATS ( device_info->map_op_count++ );
 
-		if ((dir == DMA_TO_DEVICE) ||
-		    (dir == DMA_BIDIRECTIONAL)) {
-			dev_dbg(dev, "%s: copy unsafe %p to safe %p, size %d\n",
-				__func__, ptr, buf->safe, size);
-			memcpy(buf->safe, ptr, size);
-		}
-		ptr = buf->safe;
+	buf = alloc_safe_buffer(device_info, ptr, size, dir);
+	if (buf == NULL) {
+		dev_err(dev, "%s: unable to map unsafe buffer %p!\n",
+		       __func__, ptr);
+		return ~0;
+	}
 
-		dma_addr = buf->safe_dma_addr;
-	} else {
-		/*
-		 * We don't need to sync the DMA buffer since
-		 * it was allocated via the coherent allocators.
-		 */
-		__dma_single_cpu_to_dev(ptr, size, dir);
+	dev_dbg(dev, "%s: unsafe buffer %p (dma=%#x) mapped to %p (dma=%#x)\n",
+		__func__, buf->ptr, virt_to_dma(dev, buf->ptr),
+		buf->safe, buf->safe_dma_addr);
+
+	if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL) {
+		dev_dbg(dev, "%s: copy unsafe %p to safe %p, size %d\n",
+			__func__, ptr, buf->safe, size);
+		memcpy(buf->safe, ptr, size);
 	}
 
-	return dma_addr;
+	return buf->safe_dma_addr;
 }
 
-static inline void unmap_single(struct device *dev, dma_addr_t dma_addr,
+static inline void unmap_single(struct device *dev, struct safe_buffer *buf,
 		size_t size, enum dma_data_direction dir)
 {
-	struct safe_buffer *buf = find_safe_buffer_dev(dev, dma_addr, "unmap");
-
-	if (buf) {
-		BUG_ON(buf->size != size);
-		BUG_ON(buf->direction != dir);
+	BUG_ON(buf->size != size);
+	BUG_ON(buf->direction != dir);
 
-		dev_dbg(dev,
-			"%s: unsafe buffer %p (dma=%#x) mapped to %p (dma=%#x)\n",
-			__func__, buf->ptr, virt_to_dma(dev, buf->ptr),
-			buf->safe, buf->safe_dma_addr);
+	dev_dbg(dev, "%s: unsafe buffer %p (dma=%#x) mapped to %p (dma=%#x)\n",
+		__func__, buf->ptr, virt_to_dma(dev, buf->ptr),
+		buf->safe, buf->safe_dma_addr);
 
-		DO_STATS(dev->archdata.dmabounce->bounce_count++);
+	DO_STATS(dev->archdata.dmabounce->bounce_count++);
 
-		if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL) {
-			void *ptr = buf->ptr;
+	if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL) {
+		void *ptr = buf->ptr;
 
-			dev_dbg(dev,
-				"%s: copy back safe %p to unsafe %p size %d\n",
-				__func__, buf->safe, ptr, size);
-			memcpy(ptr, buf->safe, size);
+		dev_dbg(dev, "%s: copy back safe %p to unsafe %p size %d\n",
+			__func__, buf->safe, ptr, size);
+		memcpy(ptr, buf->safe, size);
 
-			/*
-			 * Since we may have written to a page cache page,
-			 * we need to ensure that the data will be coherent
-			 * with user mappings.
-			 */
-			__cpuc_flush_dcache_area(ptr, size);
-		}
-		free_safe_buffer(dev->archdata.dmabounce, buf);
-	} else {
-		__dma_single_dev_to_cpu(dma_to_virt(dev, dma_addr), size, dir);
+		/*
+		 * Since we may have written to a page cache page,
+		 * we need to ensure that the data will be coherent
+		 * with user mappings.
+		 */
+		__cpuc_flush_dcache_area(ptr, size);
 	}
+	free_safe_buffer(dev->archdata.dmabounce, buf);
 }
 
 /* ************************************************** */
@@ -328,45 +307,28 @@ static inline void unmap_single(struct device *dev, dma_addr_t dma_addr,
  * substitute the safe buffer for the unsafe one.
  * (basically move the buffer from an unsafe area to a safe one)
  */
-dma_addr_t __dma_map_single(struct device *dev, void *ptr, size_t size,
-		enum dma_data_direction dir)
-{
-	dev_dbg(dev, "%s(ptr=%p,size=%d,dir=%x)\n",
-		__func__, ptr, size, dir);
-
-	BUG_ON(!valid_dma_direction(dir));
-
-	return map_single(dev, ptr, size, dir);
-}
-EXPORT_SYMBOL(__dma_map_single);
-
-/*
- * see if a mapped address was really a "safe" buffer and if so, copy
- * the data from the safe buffer back to the unsafe buffer and free up
- * the safe buffer.  (basically return things back to the way they
- * should be)
- */
-void __dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
-		enum dma_data_direction dir)
-{
-	dev_dbg(dev, "%s(ptr=%p,size=%d,dir=%x)\n",
-		__func__, (void *) dma_addr, size, dir);
-
-	unmap_single(dev, dma_addr, size, dir);
-}
-EXPORT_SYMBOL(__dma_unmap_single);
-
 dma_addr_t __dma_map_page(struct device *dev, struct page *page,
 		unsigned long offset, size_t size, enum dma_data_direction dir)
 {
+	dma_addr_t dma_addr;
+	int ret;
+
 	dev_dbg(dev, "%s(page=%p,off=%#lx,size=%zx,dir=%x)\n",
 		__func__, page, offset, size, dir);
 
-	BUG_ON(!valid_dma_direction(dir));
+	dma_addr = pfn_to_dma(dev, page_to_pfn(page)) + offset;
+
+	ret = needs_bounce(dev, dma_addr, size);
+	if (ret < 0)
+		return ~0;
+
+	if (ret == 0) {
+		__dma_page_cpu_to_dev(page, offset, size, dir);
+		return dma_addr;
+	}
 
 	if (PageHighMem(page)) {
-		dev_err(dev, "DMA buffer bouncing of HIGHMEM pages "
-			     "is not supported\n");
+		dev_err(dev, "DMA buffer bouncing of HIGHMEM pages is not supported\n");
 		return ~0;
 	}
 
@@ -383,10 +345,19 @@ EXPORT_SYMBOL(__dma_map_page);
 void __dma_unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size,
 		enum dma_data_direction dir)
 {
-	dev_dbg(dev, "%s(ptr=%p,size=%d,dir=%x)\n",
-		__func__, (void *) dma_addr, size, dir);
+	struct safe_buffer *buf;
+
+	dev_dbg(dev, "%s(dma=%#x,size=%d,dir=%x)\n",
+		__func__, dma_addr, size, dir);
+
+	buf = find_safe_buffer_dev(dev, dma_addr, __func__);
+	if (!buf) {
+		__dma_page_dev_to_cpu(pfn_to_page(dma_to_pfn(dev, dma_addr)),
+			dma_addr & ~PAGE_MASK, size, dir);
+		return;
+	}
 
-	unmap_single(dev, dma_addr, size, dir);
+	unmap_single(dev, buf, size, dir);
 }
 EXPORT_SYMBOL(__dma_unmap_page);
 
@@ -461,7 +432,8 @@ static int dmabounce_init_pool(struct dmabounce_pool *pool, struct device *dev,
 }
 
 int dmabounce_register_dev(struct device *dev, unsigned long small_buffer_size,
-		unsigned long large_buffer_size)
+		unsigned long large_buffer_size,
+		int (*needs_bounce_fn)(struct device *, dma_addr_t, size_t))
 {
 	struct dmabounce_device_info *device_info;
 	int ret;
@@ -497,6 +469,7 @@ int dmabounce_register_dev(struct device *dev, unsigned long small_buffer_size,
 	device_info->dev = dev;
 	INIT_LIST_HEAD(&device_info->safe_buffers);
 	rwlock_init(&device_info->lock);
+	device_info->needs_bounce = needs_bounce_fn;
 
 #ifdef STATS
 	device_info->total_allocs = 0;
diff --git a/arch/arm/common/gic.c b/arch/arm/common/gic.c
index 4ddd0a6ac7ff..0e6ae470c94f 100644
--- a/arch/arm/common/gic.c
+++ b/arch/arm/common/gic.c
@@ -24,26 +24,30 @@
  */
 #include <linux/init.h>
 #include <linux/kernel.h>
+#include <linux/err.h>
+#include <linux/module.h>
 #include <linux/list.h>
 #include <linux/smp.h>
+#include <linux/cpu_pm.h>
 #include <linux/cpumask.h>
 #include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/irqdomain.h>
+#include <linux/interrupt.h>
+#include <linux/percpu.h>
+#include <linux/slab.h>
 
 #include <asm/irq.h>
 #include <asm/mach/irq.h>
 #include <asm/hardware/gic.h>
 
-static DEFINE_SPINLOCK(irq_controller_lock);
+static DEFINE_RAW_SPINLOCK(irq_controller_lock);
 
 /* Address of GIC 0 CPU interface */
 void __iomem *gic_cpu_base_addr __read_mostly;
 
-struct gic_chip_data {
-	unsigned int irq_offset;
-	void __iomem *dist_base;
-	void __iomem *cpu_base;
-};
-
 /*
  * Supported arch specific GIC irq extension.
  * Default make them NULL.
@@ -77,8 +81,7 @@ static inline void __iomem *gic_cpu_base(struct irq_data *d)
 
 static inline unsigned int gic_irq(struct irq_data *d)
 {
-	struct gic_chip_data *gic_data = irq_data_get_irq_chip_data(d);
-	return d->irq - gic_data->irq_offset;
+	return d->hwirq;
 }
 
 /*
@@ -86,32 +89,32 @@ static inline unsigned int gic_irq(struct irq_data *d)
  */
 static void gic_mask_irq(struct irq_data *d)
 {
-	u32 mask = 1 << (d->irq % 32);
+	u32 mask = 1 << (gic_irq(d) % 32);
 
-	spin_lock(&irq_controller_lock);
+	raw_spin_lock(&irq_controller_lock);
 	writel_relaxed(mask, gic_dist_base(d) + GIC_DIST_ENABLE_CLEAR + (gic_irq(d) / 32) * 4);
 	if (gic_arch_extn.irq_mask)
 		gic_arch_extn.irq_mask(d);
-	spin_unlock(&irq_controller_lock);
+	raw_spin_unlock(&irq_controller_lock);
 }
 
 static void gic_unmask_irq(struct irq_data *d)
 {
-	u32 mask = 1 << (d->irq % 32);
+	u32 mask = 1 << (gic_irq(d) % 32);
 
-	spin_lock(&irq_controller_lock);
+	raw_spin_lock(&irq_controller_lock);
 	if (gic_arch_extn.irq_unmask)
 		gic_arch_extn.irq_unmask(d);
 	writel_relaxed(mask, gic_dist_base(d) + GIC_DIST_ENABLE_SET + (gic_irq(d) / 32) * 4);
-	spin_unlock(&irq_controller_lock);
+	raw_spin_unlock(&irq_controller_lock);
 }
 
 static void gic_eoi_irq(struct irq_data *d)
 {
 	if (gic_arch_extn.irq_eoi) {
-		spin_lock(&irq_controller_lock);
+		raw_spin_lock(&irq_controller_lock);
 		gic_arch_extn.irq_eoi(d);
-		spin_unlock(&irq_controller_lock);
+		raw_spin_unlock(&irq_controller_lock);
 	}
 
 	writel_relaxed(gic_irq(d), gic_cpu_base(d) + GIC_CPU_EOI);
@@ -135,7 +138,7 @@ static int gic_set_type(struct irq_data *d, unsigned int type)
 	if (type != IRQ_TYPE_LEVEL_HIGH && type != IRQ_TYPE_EDGE_RISING)
 		return -EINVAL;
 
-	spin_lock(&irq_controller_lock);
+	raw_spin_lock(&irq_controller_lock);
 
 	if (gic_arch_extn.irq_set_type)
 		gic_arch_extn.irq_set_type(d, type);
@@ -160,7 +163,7 @@ static int gic_set_type(struct irq_data *d, unsigned int type)
 	if (enabled)
 		writel_relaxed(enablemask, base + GIC_DIST_ENABLE_SET + enableoff);
 
-	spin_unlock(&irq_controller_lock);
+	raw_spin_unlock(&irq_controller_lock);
 
 	return 0;
 }
@@ -178,23 +181,22 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 			    bool force)
 {
 	void __iomem *reg = gic_dist_base(d) + GIC_DIST_TARGET + (gic_irq(d) & ~3);
-	unsigned int shift = (d->irq % 4) * 8;
-	unsigned int cpu = cpumask_first(mask_val);
+	unsigned int shift = (gic_irq(d) % 4) * 8;
+	unsigned int cpu = cpumask_any_and(mask_val, cpu_online_mask);
 	u32 val, mask, bit;
 
-	if (cpu >= 8)
+	if (cpu >= 8 || cpu >= nr_cpu_ids)
 		return -EINVAL;
 
 	mask = 0xff << shift;
-	bit = 1 << (cpu + shift);
+	bit = 1 << (cpu_logical_map(cpu) + shift);
 
-	spin_lock(&irq_controller_lock);
-	d->node = cpu;
+	raw_spin_lock(&irq_controller_lock);
 	val = readl_relaxed(reg) & ~mask;
 	writel_relaxed(val | bit, reg);
-	spin_unlock(&irq_controller_lock);
+	raw_spin_unlock(&irq_controller_lock);
 
-	return 0;
+	return IRQ_SET_MASK_OK;
 }
 #endif
 
@@ -222,15 +224,15 @@ static void gic_handle_cascade_irq(unsigned int irq, struct irq_desc *desc)
 
 	chained_irq_enter(chip, desc);
 
-	spin_lock(&irq_controller_lock);
+	raw_spin_lock(&irq_controller_lock);
 	status = readl_relaxed(chip_data->cpu_base + GIC_CPU_INTACK);
-	spin_unlock(&irq_controller_lock);
+	raw_spin_unlock(&irq_controller_lock);
 
 	gic_irq = (status & 0x3ff);
 	if (gic_irq == 1023)
 		goto out;
 
-	cascade_irq = gic_irq + chip_data->irq_offset;
+	cascade_irq = irq_domain_to_irq(&chip_data->domain, gic_irq);
 	if (unlikely(gic_irq < 32 || gic_irq > 1020 || cascade_irq >= NR_IRQS))
 		do_bad_IRQ(cascade_irq, desc);
 	else
@@ -262,28 +264,26 @@ void __init gic_cascade_irq(unsigned int gic_nr, unsigned int irq)
 	irq_set_chained_handler(irq, gic_handle_cascade_irq);
 }
 
-static void __init gic_dist_init(struct gic_chip_data *gic,
-	unsigned int irq_start)
+static void __init gic_dist_init(struct gic_chip_data *gic)
 {
-	unsigned int gic_irqs, irq_limit, i;
+	unsigned int i, irq;
+	u32 cpumask;
+	unsigned int gic_irqs = gic->gic_irqs;
+	struct irq_domain *domain = &gic->domain;
 	void __iomem *base = gic->dist_base;
-	u32 cpumask = 1 << smp_processor_id();
+	u32 cpu = 0;
+
+#ifdef CONFIG_SMP
+	cpu = cpu_logical_map(smp_processor_id());
+#endif
 
+	cpumask = 1 << cpu;
 	cpumask |= cpumask << 8;
 	cpumask |= cpumask << 16;
 
 	writel_relaxed(0, base + GIC_DIST_CTRL);
 
 	/*
-	 * Find out how many interrupts are supported.
-	 * The GIC only supports up to 1020 interrupt sources.
-	 */
-	gic_irqs = readl_relaxed(base + GIC_DIST_CTR) & 0x1f;
-	gic_irqs = (gic_irqs + 1) * 32;
-	if (gic_irqs > 1020)
-		gic_irqs = 1020;
-
-	/*
 	 * Set all global interrupts to be level triggered, active low.
 	 */
 	for (i = 32; i < gic_irqs; i += 16)
@@ -309,19 +309,20 @@ static void __init gic_dist_init(struct gic_chip_data *gic,
 		writel_relaxed(0xffffffff, base + GIC_DIST_ENABLE_CLEAR + i * 4 / 32);
 
 	/*
-	 * Limit number of interrupts registered to the platform maximum
-	 */
-	irq_limit = gic->irq_offset + gic_irqs;
-	if (WARN_ON(irq_limit > NR_IRQS))
-		irq_limit = NR_IRQS;
-
-	/*
 	 * Setup the Linux IRQ subsystem.
 	 */
-	for (i = irq_start; i < irq_limit; i++) {
-		irq_set_chip_and_handler(i, &gic_chip, handle_fasteoi_irq);
-		irq_set_chip_data(i, gic);
-		set_irq_flags(i, IRQF_VALID | IRQF_PROBE);
+	irq_domain_for_each_irq(domain, i, irq) {
+		if (i < 32) {
+			irq_set_percpu_devid(irq);
+			irq_set_chip_and_handler(irq, &gic_chip,
+						 handle_percpu_devid_irq);
+			set_irq_flags(irq, IRQF_VALID | IRQF_NOAUTOEN);
+		} else {
+			irq_set_chip_and_handler(irq, &gic_chip,
+						 handle_fasteoi_irq);
+			set_irq_flags(irq, IRQF_VALID | IRQF_PROBE);
+		}
+		irq_set_chip_data(irq, gic);
 	}
 
 	writel_relaxed(1, base + GIC_DIST_CTRL);
@@ -350,23 +351,270 @@ static void __cpuinit gic_cpu_init(struct gic_chip_data *gic)
 	writel_relaxed(1, base + GIC_CPU_CTRL);
 }
 
-void __init gic_init(unsigned int gic_nr, unsigned int irq_start,
+#ifdef CONFIG_CPU_PM
+/*
+ * Saves the GIC distributor registers during suspend or idle.  Must be called
+ * with interrupts disabled but before powering down the GIC.  After calling
+ * this function, no interrupts will be delivered by the GIC, and another
+ * platform-specific wakeup source must be enabled.
+ */
+static void gic_dist_save(unsigned int gic_nr)
+{
+	unsigned int gic_irqs;
+	void __iomem *dist_base;
+	int i;
+
+	if (gic_nr >= MAX_GIC_NR)
+		BUG();
+
+	gic_irqs = gic_data[gic_nr].gic_irqs;
+	dist_base = gic_data[gic_nr].dist_base;
+
+	if (!dist_base)
+		return;
+
+	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 16); i++)
+		gic_data[gic_nr].saved_spi_conf[i] =
+			readl_relaxed(dist_base + GIC_DIST_CONFIG + i * 4);
+
+	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 4); i++)
+		gic_data[gic_nr].saved_spi_target[i] =
+			readl_relaxed(dist_base + GIC_DIST_TARGET + i * 4);
+
+	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 32); i++)
+		gic_data[gic_nr].saved_spi_enable[i] =
+			readl_relaxed(dist_base + GIC_DIST_ENABLE_SET + i * 4);
+}
+
+/*
+ * Restores the GIC distributor registers during resume or when coming out of
+ * idle.  Must be called before enabling interrupts.  If a level interrupt
+ * that occured while the GIC was suspended is still present, it will be
+ * handled normally, but any edge interrupts that occured will not be seen by
+ * the GIC and need to be handled by the platform-specific wakeup source.
+ */
+static void gic_dist_restore(unsigned int gic_nr)
+{
+	unsigned int gic_irqs;
+	unsigned int i;
+	void __iomem *dist_base;
+
+	if (gic_nr >= MAX_GIC_NR)
+		BUG();
+
+	gic_irqs = gic_data[gic_nr].gic_irqs;
+	dist_base = gic_data[gic_nr].dist_base;
+
+	if (!dist_base)
+		return;
+
+	writel_relaxed(0, dist_base + GIC_DIST_CTRL);
+
+	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 16); i++)
+		writel_relaxed(gic_data[gic_nr].saved_spi_conf[i],
+			dist_base + GIC_DIST_CONFIG + i * 4);
+
+	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 4); i++)
+		writel_relaxed(0xa0a0a0a0,
+			dist_base + GIC_DIST_PRI + i * 4);
+
+	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 4); i++)
+		writel_relaxed(gic_data[gic_nr].saved_spi_target[i],
+			dist_base + GIC_DIST_TARGET + i * 4);
+
+	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 32); i++)
+		writel_relaxed(gic_data[gic_nr].saved_spi_enable[i],
+			dist_base + GIC_DIST_ENABLE_SET + i * 4);
+
+	writel_relaxed(1, dist_base + GIC_DIST_CTRL);
+}
+
+static void gic_cpu_save(unsigned int gic_nr)
+{
+	int i;
+	u32 *ptr;
+	void __iomem *dist_base;
+	void __iomem *cpu_base;
+
+	if (gic_nr >= MAX_GIC_NR)
+		BUG();
+
+	dist_base = gic_data[gic_nr].dist_base;
+	cpu_base = gic_data[gic_nr].cpu_base;
+
+	if (!dist_base || !cpu_base)
+		return;
+
+	ptr = __this_cpu_ptr(gic_data[gic_nr].saved_ppi_enable);
+	for (i = 0; i < DIV_ROUND_UP(32, 32); i++)
+		ptr[i] = readl_relaxed(dist_base + GIC_DIST_ENABLE_SET + i * 4);
+
+	ptr = __this_cpu_ptr(gic_data[gic_nr].saved_ppi_conf);
+	for (i = 0; i < DIV_ROUND_UP(32, 16); i++)
+		ptr[i] = readl_relaxed(dist_base + GIC_DIST_CONFIG + i * 4);
+
+}
+
+static void gic_cpu_restore(unsigned int gic_nr)
+{
+	int i;
+	u32 *ptr;
+	void __iomem *dist_base;
+	void __iomem *cpu_base;
+
+	if (gic_nr >= MAX_GIC_NR)
+		BUG();
+
+	dist_base = gic_data[gic_nr].dist_base;
+	cpu_base = gic_data[gic_nr].cpu_base;
+
+	if (!dist_base || !cpu_base)
+		return;
+
+	ptr = __this_cpu_ptr(gic_data[gic_nr].saved_ppi_enable);
+	for (i = 0; i < DIV_ROUND_UP(32, 32); i++)
+		writel_relaxed(ptr[i], dist_base + GIC_DIST_ENABLE_SET + i * 4);
+
+	ptr = __this_cpu_ptr(gic_data[gic_nr].saved_ppi_conf);
+	for (i = 0; i < DIV_ROUND_UP(32, 16); i++)
+		writel_relaxed(ptr[i], dist_base + GIC_DIST_CONFIG + i * 4);
+
+	for (i = 0; i < DIV_ROUND_UP(32, 4); i++)
+		writel_relaxed(0xa0a0a0a0, dist_base + GIC_DIST_PRI + i * 4);
+
+	writel_relaxed(0xf0, cpu_base + GIC_CPU_PRIMASK);
+	writel_relaxed(1, cpu_base + GIC_CPU_CTRL);
+}
+
+static int gic_notifier(struct notifier_block *self, unsigned long cmd,	void *v)
+{
+	int i;
+
+	for (i = 0; i < MAX_GIC_NR; i++) {
+		switch (cmd) {
+		case CPU_PM_ENTER:
+			gic_cpu_save(i);
+			break;
+		case CPU_PM_ENTER_FAILED:
+		case CPU_PM_EXIT:
+			gic_cpu_restore(i);
+			break;
+		case CPU_CLUSTER_PM_ENTER:
+			gic_dist_save(i);
+			break;
+		case CPU_CLUSTER_PM_ENTER_FAILED:
+		case CPU_CLUSTER_PM_EXIT:
+			gic_dist_restore(i);
+			break;
+		}
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block gic_notifier_block = {
+	.notifier_call = gic_notifier,
+};
+
+static void __init gic_pm_init(struct gic_chip_data *gic)
+{
+	gic->saved_ppi_enable = __alloc_percpu(DIV_ROUND_UP(32, 32) * 4,
+		sizeof(u32));
+	BUG_ON(!gic->saved_ppi_enable);
+
+	gic->saved_ppi_conf = __alloc_percpu(DIV_ROUND_UP(32, 16) * 4,
+		sizeof(u32));
+	BUG_ON(!gic->saved_ppi_conf);
+
+	cpu_pm_register_notifier(&gic_notifier_block);
+}
+#else
+static void __init gic_pm_init(struct gic_chip_data *gic)
+{
+}
+#endif
+
+#ifdef CONFIG_OF
+static int gic_irq_domain_dt_translate(struct irq_domain *d,
+				       struct device_node *controller,
+				       const u32 *intspec, unsigned int intsize,
+				       unsigned long *out_hwirq, unsigned int *out_type)
+{
+	if (d->of_node != controller)
+		return -EINVAL;
+	if (intsize < 3)
+		return -EINVAL;
+
+	/* Get the interrupt number and add 16 to skip over SGIs */
+	*out_hwirq = intspec[1] + 16;
+
+	/* For SPIs, we need to add 16 more to get the GIC irq ID number */
+	if (!intspec[0])
+		*out_hwirq += 16;
+
+	*out_type = intspec[2] & IRQ_TYPE_SENSE_MASK;
+	return 0;
+}
+#endif
+
+const struct irq_domain_ops gic_irq_domain_ops = {
+#ifdef CONFIG_OF
+	.dt_translate = gic_irq_domain_dt_translate,
+#endif
+};
+
+void __init gic_init(unsigned int gic_nr, int irq_start,
 	void __iomem *dist_base, void __iomem *cpu_base)
 {
 	struct gic_chip_data *gic;
+	struct irq_domain *domain;
+	int gic_irqs;
 
 	BUG_ON(gic_nr >= MAX_GIC_NR);
 
 	gic = &gic_data[gic_nr];
+	domain = &gic->domain;
 	gic->dist_base = dist_base;
 	gic->cpu_base = cpu_base;
-	gic->irq_offset = (irq_start - 1) & ~31;
 
-	if (gic_nr == 0)
+	/*
+	 * For primary GICs, skip over SGIs.
+	 * For secondary GICs, skip over PPIs, too.
+	 */
+	if (gic_nr == 0) {
 		gic_cpu_base_addr = cpu_base;
+		domain->hwirq_base = 16;
+		if (irq_start > 0)
+			irq_start = (irq_start & ~31) + 16;
+	} else
+		domain->hwirq_base = 32;
+
+	/*
+	 * Find out how many interrupts are supported.
+	 * The GIC only supports up to 1020 interrupt sources.
+	 */
+	gic_irqs = readl_relaxed(dist_base + GIC_DIST_CTR) & 0x1f;
+	gic_irqs = (gic_irqs + 1) * 32;
+	if (gic_irqs > 1020)
+		gic_irqs = 1020;
+	gic->gic_irqs = gic_irqs;
+
+	domain->nr_irq = gic_irqs - domain->hwirq_base;
+	domain->irq_base = irq_alloc_descs(irq_start, 16, domain->nr_irq,
+					   numa_node_id());
+	if (IS_ERR_VALUE(domain->irq_base)) {
+		WARN(1, "Cannot allocate irq_descs @ IRQ%d, assuming pre-allocated\n",
+		     irq_start);
+		domain->irq_base = irq_start;
+	}
+	domain->priv = gic;
+	domain->ops = &gic_irq_domain_ops;
+	irq_domain_add(domain);
 
-	gic_dist_init(gic, irq_start);
+	gic_chip.flags |= gic_arch_extn.flags;
+	gic_dist_init(gic);
 	gic_cpu_init(gic);
+	gic_pm_init(gic);
 }
 
 void __cpuinit gic_secondary_init(unsigned int gic_nr)
@@ -376,20 +624,15 @@ void __cpuinit gic_secondary_init(unsigned int gic_nr)
 	gic_cpu_init(&gic_data[gic_nr]);
 }
 
-void __cpuinit gic_enable_ppi(unsigned int irq)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	irq_set_status_flags(irq, IRQ_NOPROBE);
-	gic_unmask_irq(irq_get_irq_data(irq));
-	local_irq_restore(flags);
-}
-
 #ifdef CONFIG_SMP
 void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
 {
-	unsigned long map = *cpus_addr(*mask);
+	int cpu;
+	unsigned long map = 0;
+
+	/* Convert our logical CPU mask into a physical one. */
+	for_each_cpu(cpu, mask)
+		map |= 1 << cpu_logical_map(cpu);
 
 	/*
 	 * Ensure that stores to Normal memory are visible to the
@@ -401,3 +644,35 @@ void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
 	writel_relaxed(map << 16 | irq, gic_data[0].dist_base + GIC_DIST_SOFTINT);
 }
 #endif
+
+#ifdef CONFIG_OF
+static int gic_cnt __initdata = 0;
+
+int __init gic_of_init(struct device_node *node, struct device_node *parent)
+{
+	void __iomem *cpu_base;
+	void __iomem *dist_base;
+	int irq;
+	struct irq_domain *domain = &gic_data[gic_cnt].domain;
+
+	if (WARN_ON(!node))
+		return -ENODEV;
+
+	dist_base = of_iomap(node, 0);
+	WARN(!dist_base, "unable to map gic dist registers\n");
+
+	cpu_base = of_iomap(node, 1);
+	WARN(!cpu_base, "unable to map gic cpu registers\n");
+
+	domain->of_node = of_node_get(node);
+
+	gic_init(gic_cnt, -1, dist_base, cpu_base);
+
+	if (parent) {
+		irq = irq_of_parse_and_map(node, 0);
+		gic_cascade_irq(gic_cnt, irq);
+	}
+	gic_cnt++;
+	return 0;
+}
+#endif
diff --git a/arch/arm/common/it8152.c b/arch/arm/common/it8152.c
index 7a21927c52e1..b539ec855e1a 100644
--- a/arch/arm/common/it8152.c
+++ b/arch/arm/common/it8152.c
@@ -25,6 +25,7 @@
 #include <linux/ioport.h>
 #include <linux/irq.h>
 #include <linux/io.h>
+#include <linux/export.h>
 
 #include <asm/mach/pci.h>
 #include <asm/hardware/it8152.h>
@@ -144,7 +145,7 @@ void it8152_irq_demux(unsigned int irq, struct irq_desc *desc)
 }
 
 /* mapping for on-chip devices */
-int __init it8152_pci_map_irq(struct pci_dev *dev, u8 slot, u8 pin)
+int __init it8152_pci_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	if ((dev->vendor == PCI_VENDOR_ID_ITE) &&
 	    (dev->device == PCI_DEVICE_ID_ITE_8152)) {
@@ -243,6 +244,12 @@ static struct resource it8152_mem = {
  * ITE8152 chip can address up to 64MByte, so all the devices
  * connected to ITE8152 (PCI and USB) should have limited DMA window
  */
+static int it8152_needs_bounce(struct device *dev, dma_addr_t dma_addr, size_t size)
+{
+	dev_dbg(dev, "%s: dma_addr %08x, size %08x\n",
+		__func__, dma_addr, size);
+	return (dma_addr + size - PHYS_OFFSET) >= SZ_64M;
+}
 
 /*
  * Setup DMA mask to 64MB on devices connected to ITE8152. Ignore all
@@ -254,7 +261,7 @@ static int it8152_pci_platform_notify(struct device *dev)
 		if (dev->dma_mask)
 			*dev->dma_mask = (SZ_64M - 1) | PHYS_OFFSET;
 		dev->coherent_dma_mask = (SZ_64M - 1) | PHYS_OFFSET;
-		dmabounce_register_dev(dev, 2048, 4096);
+		dmabounce_register_dev(dev, 2048, 4096, it8152_needs_bounce);
 	}
 	return 0;
 }
@@ -267,14 +274,6 @@ static int it8152_pci_platform_notify_remove(struct device *dev)
 	return 0;
 }
 
-int dma_needs_bounce(struct device *dev, dma_addr_t dma_addr, size_t size)
-{
-	dev_dbg(dev, "%s: dma_addr %08x, size %08x\n",
-		__func__, dma_addr, size);
-	return (dev->bus == &pci_bus_type) &&
-		((dma_addr + size - PHYS_OFFSET) >= SZ_64M);
-}
-
 int dma_set_coherent_mask(struct device *dev, u64 mask)
 {
 	if (mask >= PHYS_OFFSET + SZ_64M - 1)
diff --git a/arch/arm/common/pl330.c b/arch/arm/common/pl330.c
index 97912fa48782..7129cfbdacd6 100644
--- a/arch/arm/common/pl330.c
+++ b/arch/arm/common/pl330.c
@@ -1546,7 +1546,7 @@ int pl330_chan_ctrl(void *ch_id, enum pl330_chan_op op)
 
 		/* Start the next */
 	case PL330_OP_START:
-		if (!_start(thrd))
+		if (!_thrd_active(thrd) && !_start(thrd))
 			ret = -EIO;
 		break;
 
diff --git a/arch/arm/common/sa1111.c b/arch/arm/common/sa1111.c
index 9c49a46a2b7a..61691cdbdcf2 100644
--- a/arch/arm/common/sa1111.c
+++ b/arch/arm/common/sa1111.c
@@ -579,7 +579,36 @@ sa1111_configure_smc(struct sa1111 *sachip, int sdram, unsigned int drac,
 
 	sachip->dev->coherent_dma_mask &= sa1111_dma_mask[drac >> 2];
 }
+#endif
 
+#ifdef CONFIG_DMABOUNCE
+/*
+ * According to the "Intel StrongARM SA-1111 Microprocessor Companion
+ * Chip Specification Update" (June 2000), erratum #7, there is a
+ * significant bug in the SA1111 SDRAM shared memory controller.  If
+ * an access to a region of memory above 1MB relative to the bank base,
+ * it is important that address bit 10 _NOT_ be asserted. Depending
+ * on the configuration of the RAM, bit 10 may correspond to one
+ * of several different (processor-relative) address bits.
+ *
+ * This routine only identifies whether or not a given DMA address
+ * is susceptible to the bug.
+ *
+ * This should only get called for sa1111_device types due to the
+ * way we configure our device dma_masks.
+ */
+static int sa1111_needs_bounce(struct device *dev, dma_addr_t addr, size_t size)
+{
+	/*
+	 * Section 4.6 of the "Intel StrongARM SA-1111 Development Module
+	 * User's Guide" mentions that jumpers R51 and R52 control the
+	 * target of SA-1111 DMA (either SDRAM bank 0 on Assabet, or
+	 * SDRAM bank 1 on Neponset). The default configuration selects
+	 * Assabet, so any address in bank 1 is necessarily invalid.
+	 */
+	return (machine_is_assabet() || machine_is_pfs168()) &&
+		(addr >= 0xc8000000 || (addr + size) >= 0xc8000000);
+}
 #endif
 
 static void sa1111_dev_release(struct device *_dev)
@@ -644,7 +673,8 @@ sa1111_init_one_child(struct sa1111 *sachip, struct resource *parent,
 		dev->dev.dma_mask = &dev->dma_mask;
 
 		if (dev->dma_mask != 0xffffffffUL) {
-			ret = dmabounce_register_dev(&dev->dev, 1024, 4096);
+			ret = dmabounce_register_dev(&dev->dev, 1024, 4096,
+					sa1111_needs_bounce);
 			if (ret) {
 				dev_err(&dev->dev, "SA1111: Failed to register"
 					" with dmabounce\n");
@@ -688,6 +718,10 @@ __sa1111_probe(struct device *me, struct resource *mem, int irq)
 		goto err_free;
 	}
 
+	ret = clk_prepare(sachip->clk);
+	if (ret)
+		goto err_clkput;
+
 	spin_lock_init(&sachip->lock);
 
 	sachip->dev = me;
@@ -703,7 +737,7 @@ __sa1111_probe(struct device *me, struct resource *mem, int irq)
 	sachip->base = ioremap(mem->start, PAGE_SIZE * 2);
 	if (!sachip->base) {
 		ret = -ENOMEM;
-		goto err_clkput;
+		goto err_clk_unprep;
 	}
 
 	/*
@@ -779,6 +813,8 @@ __sa1111_probe(struct device *me, struct resource *mem, int irq)
 
  err_unmap:
 	iounmap(sachip->base);
+ err_clk_unprep:
+	clk_unprepare(sachip->clk);
  err_clkput:
 	clk_put(sachip->clk);
  err_free:
@@ -805,6 +841,7 @@ static void __sa1111_remove(struct sa1111 *sachip)
 	sa1111_writel(0, irqbase + SA1111_WAKEEN1);
 
 	clk_disable(sachip->clk);
+	clk_unprepare(sachip->clk);
 
 	if (sachip->irq != NO_IRQ) {
 		irq_set_chained_handler(sachip->irq, NULL);
@@ -818,34 +855,6 @@ static void __sa1111_remove(struct sa1111 *sachip)
 	kfree(sachip);
 }
 
-/*
- * According to the "Intel StrongARM SA-1111 Microprocessor Companion
- * Chip Specification Update" (June 2000), erratum #7, there is a
- * significant bug in the SA1111 SDRAM shared memory controller.  If
- * an access to a region of memory above 1MB relative to the bank base,
- * it is important that address bit 10 _NOT_ be asserted. Depending
- * on the configuration of the RAM, bit 10 may correspond to one
- * of several different (processor-relative) address bits.
- *
- * This routine only identifies whether or not a given DMA address
- * is susceptible to the bug.
- *
- * This should only get called for sa1111_device types due to the
- * way we configure our device dma_masks.
- */
-int dma_needs_bounce(struct device *dev, dma_addr_t addr, size_t size)
-{
-	/*
-	 * Section 4.6 of the "Intel StrongARM SA-1111 Development Module
-	 * User's Guide" mentions that jumpers R51 and R52 control the
-	 * target of SA-1111 DMA (either SDRAM bank 0 on Assabet, or
-	 * SDRAM bank 1 on Neponset). The default configuration selects
-	 * Assabet, so any address in bank 1 is necessarily invalid.
-	 */
-	return ((machine_is_assabet() || machine_is_pfs168()) &&
-		(addr >= 0xc8000000 || (addr + size) >= 0xc8000000));
-}
-
 struct sa1111_save_data {
 	unsigned int	skcr;
 	unsigned int	skpcr;
diff --git a/arch/arm/common/scoop.c b/arch/arm/common/scoop.c
index c11af1e4bad3..0c616d5fcb0f 100644
--- a/arch/arm/common/scoop.c
+++ b/arch/arm/common/scoop.c
@@ -12,11 +12,12 @@
  */
 
 #include <linux/device.h>
+#include <linux/gpio.h>
 #include <linux/string.h>
 #include <linux/slab.h>
 #include <linux/platform_device.h>
+#include <linux/export.h>
 #include <linux/io.h>
-#include <asm/gpio.h>
 #include <asm/hardware/scoop.h>
 
 /* PCMCIA to Scoop linkage
@@ -193,7 +194,7 @@ static int __devinit scoop_probe(struct platform_device *pdev)
 	spin_lock_init(&devptr->scoop_lock);
 
 	inf = pdev->dev.platform_data;
-	devptr->base = ioremap(mem->start, mem->end - mem->start + 1);
+	devptr->base = ioremap(mem->start, resource_size(mem));
 
 	if (!devptr->base) {
 		ret = -ENOMEM;
diff --git a/arch/arm/common/timer-sp.c b/arch/arm/common/timer-sp.c
index 41df47875122..2393b5bc96fa 100644
--- a/arch/arm/common/timer-sp.c
+++ b/arch/arm/common/timer-sp.c
@@ -41,9 +41,17 @@ static long __init sp804_get_clock_rate(const char *name)
 		return PTR_ERR(clk);
 	}
 
+	err = clk_prepare(clk);
+	if (err) {
+		pr_err("sp804: %s clock failed to prepare: %d\n", name, err);
+		clk_put(clk);
+		return err;
+	}
+
 	err = clk_enable(clk);
 	if (err) {
 		pr_err("sp804: %s clock failed to enable: %d\n", name, err);
+		clk_unprepare(clk);
 		clk_put(clk);
 		return err;
 	}
@@ -52,6 +60,7 @@ static long __init sp804_get_clock_rate(const char *name)
 	if (rate < 0) {
 		pr_err("sp804: %s clock failed to get rate: %ld\n", name, rate);
 		clk_disable(clk);
+		clk_unprepare(clk);
 		clk_put(clk);
 	}
 
diff --git a/arch/arm/common/vic.c b/arch/arm/common/vic.c
index 7aa4262ada7a..01f18a421b17 100644
--- a/arch/arm/common/vic.c
+++ b/arch/arm/common/vic.c
@@ -259,7 +259,6 @@ static void __init vic_disable(void __iomem *base)
 	writel(0, base + VIC_INT_SELECT);
 	writel(0, base + VIC_INT_ENABLE);
 	writel(~0, base + VIC_INT_ENABLE_CLEAR);
-	writel(0, base + VIC_IRQ_STATUS);
 	writel(0, base + VIC_ITCR);
 	writel(~0, base + VIC_INT_SOFT_CLEAR);
 }
@@ -347,7 +346,8 @@ void __init vic_init(void __iomem *base, unsigned int irq_start,
 
 	/* Identify which VIC cell this one is, by reading the ID */
 	for (i = 0; i < 4; i++) {
-		u32 addr = ((u32)base & PAGE_MASK) + 0xfe0 + (i * 4);
+		void __iomem *addr;
+		addr = (void __iomem *)((u32)base & PAGE_MASK) + 0xfe0 + (i * 4);
 		cellid |= (readl(addr) & 0xff) << (8 * i);
 	}
 	vendor = (cellid >> 12) & 0xff;