5 files changed, 163 insertions, 61 deletions

diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index ca8ecdee47d8..f5ad9ee70426 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -264,7 +264,7 @@ config CPU_ARM1026
 
 # SA110
 config CPU_SA110
-	bool "Support StrongARM(R) SA-110 processor" if ARCH_RPC
+	bool
 	select CPU_32v3 if ARCH_RPC
 	select CPU_32v4 if !ARCH_RPC
 	select CPU_ABRT_EV4
@@ -854,7 +854,7 @@ config OUTER_CACHE_SYNC
 
 config CACHE_FEROCEON_L2
 	bool "Enable the Feroceon L2 cache controller"
-	depends on ARCH_KIRKWOOD || ARCH_MV78XX0
+	depends on ARCH_KIRKWOOD || ARCH_MV78XX0 || ARCH_MVEBU
 	default y
 	select OUTER_CACHE
 	help
diff --git a/arch/arm/mm/cache-feroceon-l2.c b/arch/arm/mm/cache-feroceon-l2.c
index aae891820f8f..dc814a548056 100644
--- a/arch/arm/mm/cache-feroceon-l2.c
+++ b/arch/arm/mm/cache-feroceon-l2.c
@@ -13,10 +13,15 @@
  */
 
 #include <linux/init.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
 #include <linux/highmem.h>
+#include <linux/io.h>
 #include <asm/cacheflush.h>
 #include <asm/cp15.h>
-#include <plat/cache-feroceon-l2.h>
+#include <asm/hardware/cache-feroceon-l2.h>
+
+#define L2_WRITETHROUGH_KIRKWOOD	BIT(4)
 
 /*
  * Low-level cache maintenance operations.
@@ -352,3 +357,41 @@ void __init feroceon_l2_init(int __l2_wt_override)
 	printk(KERN_INFO "Feroceon L2: Cache support initialised%s.\n",
 			 l2_wt_override ? ", in WT override mode" : "");
 }
+#ifdef CONFIG_OF
+static const struct of_device_id feroceon_ids[] __initconst = {
+	{ .compatible = "marvell,kirkwood-cache"},
+	{ .compatible = "marvell,feroceon-cache"},
+	{}
+};
+
+int __init feroceon_of_init(void)
+{
+	struct device_node *node;
+	void __iomem *base;
+	bool l2_wt_override = false;
+	struct resource res;
+
+#if defined(CONFIG_CACHE_FEROCEON_L2_WRITETHROUGH)
+	l2_wt_override = true;
+#endif
+
+	node = of_find_matching_node(NULL, feroceon_ids);
+	if (node && of_device_is_compatible(node, "marvell,kirkwood-cache")) {
+		if (of_address_to_resource(node, 0, &res))
+			return -ENODEV;
+
+		base = ioremap(res.start, resource_size(&res));
+		if (!base)
+			return -ENOMEM;
+
+		if (l2_wt_override)
+			writel(readl(base) | L2_WRITETHROUGH_KIRKWOOD, base);
+		else
+			writel(readl(base) & ~L2_WRITETHROUGH_KIRKWOOD, base);
+	}
+
+	feroceon_l2_init(l2_wt_override);
+
+	return 0;
+}
+#endif
diff --git a/arch/arm/mm/cache-tauros2.c b/arch/arm/mm/cache-tauros2.c
index 1be0f4e5e6eb..b273739e6359 100644
--- a/arch/arm/mm/cache-tauros2.c
+++ b/arch/arm/mm/cache-tauros2.c
@@ -33,7 +33,7 @@
  * outer cache operations into the kernel image if the kernel has been
  * configured to support a pre-v7 CPU.
  */
-#if __LINUX_ARM_ARCH__ < 7
+#ifdef CONFIG_CPU_32v5
 /*
  * Low-level cache maintenance operations.
  */
@@ -229,33 +229,6 @@ static void __init tauros2_internal_init(unsigned int features)
 	}
 #endif
 
-#ifdef CONFIG_CPU_32v6
-	/*
-	 * Check whether this CPU lacks support for the v7 hierarchical
-	 * cache ops.  (PJ4 is in its v6 personality mode if the MMFR3
-	 * register indicates no support for the v7 hierarchical cache
-	 * ops.)
-	 */
-	if (cpuid_scheme() && (read_mmfr3() & 0xf) == 0) {
-		/*
-		 * When Tauros2 is used in an ARMv6 system, the L2
-		 * enable bit is in the ARMv6 ARM-mandated position
-		 * (bit [26] of the System Control Register).
-		 */
-		if (!(get_cr() & 0x04000000)) {
-			printk(KERN_INFO "Tauros2: Enabling L2 cache.\n");
-			adjust_cr(0x04000000, 0x04000000);
-		}
-
-		mode = "ARMv6";
-		outer_cache.inv_range = tauros2_inv_range;
-		outer_cache.clean_range = tauros2_clean_range;
-		outer_cache.flush_range = tauros2_flush_range;
-		outer_cache.disable = tauros2_disable;
-		outer_cache.resume = tauros2_resume;
-	}
-#endif
-
 #ifdef CONFIG_CPU_32v7
 	/*
 	 * Check whether this CPU has support for the v7 hierarchical
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index c9c6acdf90cc..f62aa0677e5c 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -1066,6 +1066,8 @@ fs_initcall(dma_debug_do_init);
 
 /* IOMMU */
 
+static int extend_iommu_mapping(struct dma_iommu_mapping *mapping);
+
 static inline dma_addr_t __alloc_iova(struct dma_iommu_mapping *mapping,
 				      size_t size)
 {
@@ -1073,41 +1075,87 @@ static inline dma_addr_t __alloc_iova(struct dma_iommu_mapping *mapping,
 	unsigned int align = 0;
 	unsigned int count, start;
 	unsigned long flags;
+	dma_addr_t iova;
+	int i;
 
 	if (order > CONFIG_ARM_DMA_IOMMU_ALIGNMENT)
 		order = CONFIG_ARM_DMA_IOMMU_ALIGNMENT;
 
-	count = ((PAGE_ALIGN(size) >> PAGE_SHIFT) +
-		 (1 << mapping->order) - 1) >> mapping->order;
-
-	if (order > mapping->order)
-		align = (1 << (order - mapping->order)) - 1;
+	count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	align = (1 << order) - 1;
 
 	spin_lock_irqsave(&mapping->lock, flags);
-	start = bitmap_find_next_zero_area(mapping->bitmap, mapping->bits, 0,
-					   count, align);
-	if (start > mapping->bits) {
-		spin_unlock_irqrestore(&mapping->lock, flags);
-		return DMA_ERROR_CODE;
+	for (i = 0; i < mapping->nr_bitmaps; i++) {
+		start = bitmap_find_next_zero_area(mapping->bitmaps[i],
+				mapping->bits, 0, count, align);
+
+		if (start > mapping->bits)
+			continue;
+
+		bitmap_set(mapping->bitmaps[i], start, count);
+		break;
 	}
 
-	bitmap_set(mapping->bitmap, start, count);
+	/*
+	 * No unused range found. Try to extend the existing mapping
+	 * and perform a second attempt to reserve an IO virtual
+	 * address range of size bytes.
+	 */
+	if (i == mapping->nr_bitmaps) {
+		if (extend_iommu_mapping(mapping)) {
+			spin_unlock_irqrestore(&mapping->lock, flags);
+			return DMA_ERROR_CODE;
+		}
+
+		start = bitmap_find_next_zero_area(mapping->bitmaps[i],
+				mapping->bits, 0, count, align);
+
+		if (start > mapping->bits) {
+			spin_unlock_irqrestore(&mapping->lock, flags);
+			return DMA_ERROR_CODE;
+		}
+
+		bitmap_set(mapping->bitmaps[i], start, count);
+	}
 	spin_unlock_irqrestore(&mapping->lock, flags);
 
-	return mapping->base + (start << (mapping->order + PAGE_SHIFT));
+	iova = mapping->base + (mapping->size * i);
+	iova += start << PAGE_SHIFT;
+
+	return iova;
 }
 
 static inline void __free_iova(struct dma_iommu_mapping *mapping,
 			       dma_addr_t addr, size_t size)
 {
-	unsigned int start = (addr - mapping->base) >>
-			     (mapping->order + PAGE_SHIFT);
-	unsigned int count = ((size >> PAGE_SHIFT) +
-			      (1 << mapping->order) - 1) >> mapping->order;
+	unsigned int start, count;
 	unsigned long flags;
+	dma_addr_t bitmap_base;
+	u32 bitmap_index;
+
+	if (!size)
+		return;
+
+	bitmap_index = (u32) (addr - mapping->base) / (u32) mapping->size;
+	BUG_ON(addr < mapping->base || bitmap_index > mapping->extensions);
+
+	bitmap_base = mapping->base + mapping->size * bitmap_index;
+
+	start = (addr - bitmap_base) >>	PAGE_SHIFT;
+
+	if (addr + size > bitmap_base + mapping->size) {
+		/*
+		 * The address range to be freed reaches into the iova
+		 * range of the next bitmap. This should not happen as
+		 * we don't allow this in __alloc_iova (at the
+		 * moment).
+		 */
+		BUG();
+	} else
+		count = size >> PAGE_SHIFT;
 
 	spin_lock_irqsave(&mapping->lock, flags);
-	bitmap_clear(mapping->bitmap, start, count);
+	bitmap_clear(mapping->bitmaps[bitmap_index], start, count);
 	spin_unlock_irqrestore(&mapping->lock, flags);
 }
 
@@ -1872,8 +1920,7 @@ struct dma_map_ops iommu_coherent_ops = {
  * arm_iommu_create_mapping
  * @bus: pointer to the bus holding the client device (for IOMMU calls)
  * @base: start address of the valid IO address space
- * @size: size of the valid IO address space
- * @order: accuracy of the IO addresses allocations
+ * @size: maximum size of the valid IO address space
  *
  * Creates a mapping structure which holds information about used/unused
  * IO address ranges, which is required to perform memory allocation and
@@ -1883,38 +1930,54 @@ struct dma_map_ops iommu_coherent_ops = {
  * arm_iommu_attach_device function.
  */
 struct dma_iommu_mapping *
-arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, size_t size,
-			 int order)
+arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, size_t size)
 {
-	unsigned int count = size >> (PAGE_SHIFT + order);
-	unsigned int bitmap_size = BITS_TO_LONGS(count) * sizeof(long);
+	unsigned int bits = size >> PAGE_SHIFT;
+	unsigned int bitmap_size = BITS_TO_LONGS(bits) * sizeof(long);
 	struct dma_iommu_mapping *mapping;
+	int extensions = 1;
 	int err = -ENOMEM;
 
-	if (!count)
+	if (!bitmap_size)
 		return ERR_PTR(-EINVAL);
 
+	if (bitmap_size > PAGE_SIZE) {
+		extensions = bitmap_size / PAGE_SIZE;
+		bitmap_size = PAGE_SIZE;
+	}
+
 	mapping = kzalloc(sizeof(struct dma_iommu_mapping), GFP_KERNEL);
 	if (!mapping)
 		goto err;
 
-	mapping->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
-	if (!mapping->bitmap)
+	mapping->bitmap_size = bitmap_size;
+	mapping->bitmaps = kzalloc(extensions * sizeof(unsigned long *),
+				GFP_KERNEL);
+	if (!mapping->bitmaps)
 		goto err2;
 
+	mapping->bitmaps[0] = kzalloc(bitmap_size, GFP_KERNEL);
+	if (!mapping->bitmaps[0])
+		goto err3;
+
+	mapping->nr_bitmaps = 1;
+	mapping->extensions = extensions;
 	mapping->base = base;
+	mapping->size = bitmap_size << PAGE_SHIFT;
 	mapping->bits = BITS_PER_BYTE * bitmap_size;
-	mapping->order = order;
+
 	spin_lock_init(&mapping->lock);
 
 	mapping->domain = iommu_domain_alloc(bus);
 	if (!mapping->domain)
-		goto err3;
+		goto err4;
 
 	kref_init(&mapping->kref);
 	return mapping;
+err4:
+	kfree(mapping->bitmaps[0]);
 err3:
-	kfree(mapping->bitmap);
+	kfree(mapping->bitmaps);
 err2:
 	kfree(mapping);
 err:
@@ -1924,14 +1987,35 @@ EXPORT_SYMBOL_GPL(arm_iommu_create_mapping);
 
 static void release_iommu_mapping(struct kref *kref)
 {
+	int i;
 	struct dma_iommu_mapping *mapping =
 		container_of(kref, struct dma_iommu_mapping, kref);
 
 	iommu_domain_free(mapping->domain);
-	kfree(mapping->bitmap);
+	for (i = 0; i < mapping->nr_bitmaps; i++)
+		kfree(mapping->bitmaps[i]);
+	kfree(mapping->bitmaps);
 	kfree(mapping);
 }
 
+static int extend_iommu_mapping(struct dma_iommu_mapping *mapping)
+{
+	int next_bitmap;
+
+	if (mapping->nr_bitmaps > mapping->extensions)
+		return -EINVAL;
+
+	next_bitmap = mapping->nr_bitmaps;
+	mapping->bitmaps[next_bitmap] = kzalloc(mapping->bitmap_size,
+						GFP_ATOMIC);
+	if (!mapping->bitmaps[next_bitmap])
+		return -ENOMEM;
+
+	mapping->nr_bitmaps++;
+
+	return 0;
+}
+
 void arm_iommu_release_mapping(struct dma_iommu_mapping *mapping)
 {
 	if (mapping)
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 804d61566a53..2a77ba8796ae 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -323,6 +323,8 @@ void __init arm_memblock_init(struct meminfo *mi,
 	if (mdesc->reserve)
 		mdesc->reserve();
 
+	early_init_fdt_scan_reserved_mem();
+
 	/*
 	 * reserve memory for DMA contigouos allocations,
 	 * must come from DMA area inside low memory