Merge branch 'misc2' into devel

9 files changed, 343 insertions, 93 deletions

diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index baf638487a2..c4ed9f93f64 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -399,7 +399,7 @@ config CPU_V6
 config CPU_32v6K
 	bool "Support ARM V6K processor extensions" if !SMP
 	depends on CPU_V6
-	default y if SMP && !ARCH_MX3
+	default y if SMP && !(ARCH_MX3 || ARCH_OMAP2)
 	help
 	  Say Y here if your ARMv6 processor supports the 'K' extension.
 	  This enables the kernel to use some instructions not present
@@ -410,7 +410,7 @@ config CPU_32v6K
 # ARMv7
 config CPU_V7
 	bool "Support ARM V7 processor" if ARCH_INTEGRATOR || MACH_REALVIEW_EB || MACH_REALVIEW_PBX
-	select CPU_32v6K
+	select CPU_32v6K if !ARCH_OMAP2
 	select CPU_32v7
 	select CPU_ABRT_EV7
 	select CPU_PABRT_V7
@@ -754,7 +754,7 @@ config CACHE_FEROCEON_L2_WRITETHROUGH
 config CACHE_L2X0
 	bool "Enable the L2x0 outer cache controller"
 	depends on REALVIEW_EB_ARM11MP || MACH_REALVIEW_PB11MP || MACH_REALVIEW_PB1176 || \
-		   REALVIEW_EB_A9MP || ARCH_MX35 || ARCH_MX31 || MACH_REALVIEW_PBX || ARCH_NOMADIK
+		   REALVIEW_EB_A9MP || ARCH_MX35 || ARCH_MX31 || MACH_REALVIEW_PBX || ARCH_NOMADIK || ARCH_OMAP4
 	default y
 	select OUTER_CACHE
 	help
@@ -779,5 +779,5 @@ config CACHE_XSC3L2
 
 config ARM_L1_CACHE_SHIFT
 	int
-	default 6 if ARCH_OMAP3 || ARCH_S5PC1XX
+	default 6 if ARM_L1_CACHE_SHIFT_6
 	default 5
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index b270d6228fe..0c5eb6983ce 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -898,11 +898,7 @@ static int __init alignment_init(void)
 #ifdef CONFIG_PROC_FS
 	struct proc_dir_entry *res;
 
-	res = proc_mkdir("cpu", NULL);
-	if (!res)
-		return -ENOMEM;
-
-	res = create_proc_entry("alignment", S_IWUSR | S_IRUGO, res);
+	res = create_proc_entry("cpu/alignment", S_IWUSR | S_IRUGO, NULL);
 	if (!res)
 		return -ENOMEM;
 
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index cb8fc6573b1..07334632d3e 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -42,6 +42,57 @@ static inline void cache_sync(void)
 	cache_wait(base + L2X0_CACHE_SYNC, 1);
 }
 
+static inline void l2x0_clean_line(unsigned long addr)
+{
+	void __iomem *base = l2x0_base;
+	cache_wait(base + L2X0_CLEAN_LINE_PA, 1);
+	writel(addr, base + L2X0_CLEAN_LINE_PA);
+}
+
+static inline void l2x0_inv_line(unsigned long addr)
+{
+	void __iomem *base = l2x0_base;
+	cache_wait(base + L2X0_INV_LINE_PA, 1);
+	writel(addr, base + L2X0_INV_LINE_PA);
+}
+
+#ifdef CONFIG_PL310_ERRATA_588369
+static void debug_writel(unsigned long val)
+{
+	extern void omap_smc1(u32 fn, u32 arg);
+
+	/*
+	 * Texas Instrument secure monitor api to modify the
+	 * PL310 Debug Control Register.
+	 */
+	omap_smc1(0x100, val);
+}
+
+static inline void l2x0_flush_line(unsigned long addr)
+{
+	void __iomem *base = l2x0_base;
+
+	/* Clean by PA followed by Invalidate by PA */
+	cache_wait(base + L2X0_CLEAN_LINE_PA, 1);
+	writel(addr, base + L2X0_CLEAN_LINE_PA);
+	cache_wait(base + L2X0_INV_LINE_PA, 1);
+	writel(addr, base + L2X0_INV_LINE_PA);
+}
+#else
+
+/* Optimised out for non-errata case */
+static inline void debug_writel(unsigned long val)
+{
+}
+
+static inline void l2x0_flush_line(unsigned long addr)
+{
+	void __iomem *base = l2x0_base;
+	cache_wait(base + L2X0_CLEAN_INV_LINE_PA, 1);
+	writel(addr, base + L2X0_CLEAN_INV_LINE_PA);
+}
+#endif
+
 static inline void l2x0_inv_all(void)
 {
 	unsigned long flags;
@@ -62,23 +113,24 @@ static void l2x0_inv_range(unsigned long start, unsigned long end)
 	spin_lock_irqsave(&l2x0_lock, flags);
 	if (start & (CACHE_LINE_SIZE - 1)) {
 		start &= ~(CACHE_LINE_SIZE - 1);
-		cache_wait(base + L2X0_CLEAN_INV_LINE_PA, 1);
-		writel(start, base + L2X0_CLEAN_INV_LINE_PA);
+		debug_writel(0x03);
+		l2x0_flush_line(start);
+		debug_writel(0x00);
 		start += CACHE_LINE_SIZE;
 	}
 
 	if (end & (CACHE_LINE_SIZE - 1)) {
 		end &= ~(CACHE_LINE_SIZE - 1);
-		cache_wait(base + L2X0_CLEAN_INV_LINE_PA, 1);
-		writel(end, base + L2X0_CLEAN_INV_LINE_PA);
+		debug_writel(0x03);
+		l2x0_flush_line(end);
+		debug_writel(0x00);
 	}
 
 	while (start < end) {
 		unsigned long blk_end = start + min(end - start, 4096UL);
 
 		while (start < blk_end) {
-			cache_wait(base + L2X0_INV_LINE_PA, 1);
-			writel(start, base + L2X0_INV_LINE_PA);
+			l2x0_inv_line(start);
 			start += CACHE_LINE_SIZE;
 		}
 
@@ -103,8 +155,7 @@ static void l2x0_clean_range(unsigned long start, unsigned long end)
 		unsigned long blk_end = start + min(end - start, 4096UL);
 
 		while (start < blk_end) {
-			cache_wait(base + L2X0_CLEAN_LINE_PA, 1);
-			writel(start, base + L2X0_CLEAN_LINE_PA);
+			l2x0_clean_line(start);
 			start += CACHE_LINE_SIZE;
 		}
 
@@ -128,11 +179,12 @@ static void l2x0_flush_range(unsigned long start, unsigned long end)
 	while (start < end) {
 		unsigned long blk_end = start + min(end - start, 4096UL);
 
+		debug_writel(0x03);
 		while (start < blk_end) {
-			cache_wait(base + L2X0_CLEAN_INV_LINE_PA, 1);
-			writel(start, base + L2X0_CLEAN_INV_LINE_PA);
+			l2x0_flush_line(start);
 			start += CACHE_LINE_SIZE;
 		}
+		debug_writel(0x00);
 
 		if (blk_end < end) {
 			spin_unlock_irqrestore(&l2x0_lock, flags);
diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c
index a9e22e31eaa..b0ee9ba3cfa 100644
--- a/arch/arm/mm/context.c
+++ b/arch/arm/mm/context.c
@@ -10,12 +10,17 @@
 #include <linux/init.h>
 #include <linux/sched.h>
 #include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/percpu.h>
 
 #include <asm/mmu_context.h>
 #include <asm/tlbflush.h>
 
 static DEFINE_SPINLOCK(cpu_asid_lock);
 unsigned int cpu_last_asid = ASID_FIRST_VERSION;
+#ifdef CONFIG_SMP
+DEFINE_PER_CPU(struct mm_struct *, current_mm);
+#endif
 
 /*
  * We fork()ed a process, and we need a new context for the child
@@ -26,13 +31,109 @@ unsigned int cpu_last_asid = ASID_FIRST_VERSION;
 void __init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 {
 	mm->context.id = 0;
+	spin_lock_init(&mm->context.id_lock);
 }
 
+static void flush_context(void)
+{
+	/* set the reserved ASID before flushing the TLB */
+	asm("mcr	p15, 0, %0, c13, c0, 1\n" : : "r" (0));
+	isb();
+	local_flush_tlb_all();
+	if (icache_is_vivt_asid_tagged()) {
+		__flush_icache_all();
+		dsb();
+	}
+}
+
+#ifdef CONFIG_SMP
+
+static void set_mm_context(struct mm_struct *mm, unsigned int asid)
+{
+	unsigned long flags;
+
+	/*
+	 * Locking needed for multi-threaded applications where the
+	 * same mm->context.id could be set from different CPUs during
+	 * the broadcast. This function is also called via IPI so the
+	 * mm->context.id_lock has to be IRQ-safe.
+	 */
+	spin_lock_irqsave(&mm->context.id_lock, flags);
+	if (likely((mm->context.id ^ cpu_last_asid) >> ASID_BITS)) {
+		/*
+		 * Old version of ASID found. Set the new one and
+		 * reset mm_cpumask(mm).
+		 */
+		mm->context.id = asid;
+		cpumask_clear(mm_cpumask(mm));
+	}
+	spin_unlock_irqrestore(&mm->context.id_lock, flags);
+
+	/*
+	 * Set the mm_cpumask(mm) bit for the current CPU.
+	 */
+	cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm));
+}
+
+/*
+ * Reset the ASID on the current CPU. This function call is broadcast
+ * from the CPU handling the ASID rollover and holding cpu_asid_lock.
+ */
+static void reset_context(void *info)
+{
+	unsigned int asid;
+	unsigned int cpu = smp_processor_id();
+	struct mm_struct *mm = per_cpu(current_mm, cpu);
+
+	/*
+	 * Check if a current_mm was set on this CPU as it might still
+	 * be in the early booting stages and using the reserved ASID.
+	 */
+	if (!mm)
+		return;
+
+	smp_rmb();
+	asid = cpu_last_asid + cpu + 1;
+
+	flush_context();
+	set_mm_context(mm, asid);
+
+	/* set the new ASID */
+	asm("mcr	p15, 0, %0, c13, c0, 1\n" : : "r" (mm->context.id));
+	isb();
+}
+
+#else
+
+static inline void set_mm_context(struct mm_struct *mm, unsigned int asid)
+{
+	mm->context.id = asid;
+	cpumask_copy(mm_cpumask(mm), cpumask_of(smp_processor_id()));
+}
+
+#endif
+
 void __new_context(struct mm_struct *mm)
 {
 	unsigned int asid;
 
 	spin_lock(&cpu_asid_lock);
+#ifdef CONFIG_SMP
+	/*
+	 * Check the ASID again, in case the change was broadcast from
+	 * another CPU before we acquired the lock.
+	 */
+	if (unlikely(((mm->context.id ^ cpu_last_asid) >> ASID_BITS) == 0)) {
+		cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm));
+		spin_unlock(&cpu_asid_lock);
+		return;
+	}
+#endif
+	/*
+	 * At this point, it is guaranteed that the current mm (with
+	 * an old ASID) isn't active on any other CPU since the ASIDs
+	 * are changed simultaneously via IPI.
+	 */
 	asid = ++cpu_last_asid;
 	if (asid == 0)
 		asid = cpu_last_asid = ASID_FIRST_VERSION;
@@ -42,20 +143,15 @@ void __new_context(struct mm_struct *mm)
 	 * to start a new version and flush the TLB.
 	 */
 	if (unlikely((asid & ~ASID_MASK) == 0)) {
-		asid = ++cpu_last_asid;
-		/* set the reserved ASID before flushing the TLB */
-		asm("mcr	p15, 0, %0, c13, c0, 1	@ set reserved context ID\n"
-		    :
-		    : "r" (0));
-		isb();
-		flush_tlb_all();
-		if (icache_is_vivt_asid_tagged()) {
-			__flush_icache_all();
-			dsb();
-		}
+		asid = cpu_last_asid + smp_processor_id() + 1;
+		flush_context();
+#ifdef CONFIG_SMP
+		smp_wmb();
+		smp_call_function(reset_context, NULL, 1);
+#endif
+		cpu_last_asid += NR_CPUS;
 	}
-	spin_unlock(&cpu_asid_lock);
 
-	cpumask_copy(mm_cpumask(mm), cpumask_of(smp_processor_id()));
-	mm->context.id = asid;
+	set_mm_context(mm, asid);
+	spin_unlock(&cpu_asid_lock);
 }
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 64daef2173b..0da7eccf774 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -29,9 +29,6 @@
 #error "CONSISTENT_DMA_SIZE must be multiple of 2MiB"
 #endif
 
-#define CONSISTENT_END	(0xffe00000)
-#define CONSISTENT_BASE	(CONSISTENT_END - CONSISTENT_DMA_SIZE)
-
 #define CONSISTENT_OFFSET(x)	(((unsigned long)(x) - CONSISTENT_BASE) >> PAGE_SHIFT)
 #define CONSISTENT_PTE_INDEX(x) (((unsigned long)(x) - CONSISTENT_BASE) >> PGDIR_SHIFT)
 #define NUM_CONSISTENT_PTES (CONSISTENT_DMA_SIZE >> PGDIR_SHIFT)
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index a04ffbbbe25..7829cb5425f 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -23,6 +23,7 @@
 #include <asm/setup.h>
 #include <asm/sizes.h>
 #include <asm/tlb.h>
+#include <asm/fixmap.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
@@ -32,19 +33,21 @@
 static unsigned long phys_initrd_start __initdata = 0;
 static unsigned long phys_initrd_size __initdata = 0;
 
-static void __init early_initrd(char **p)
+static int __init early_initrd(char *p)
 {
 	unsigned long start, size;
+	char *endp;
 
-	start = memparse(*p, p);
-	if (**p == ',') {
-		size = memparse((*p) + 1, p);
+	start = memparse(p, &endp);
+	if (*endp == ',') {
+		size = memparse(endp + 1, NULL);
 
 		phys_initrd_start = start;
 		phys_initrd_size = size;
 	}
+	return 0;
 }
-__early_param("initrd=", early_initrd);
+early_param("initrd", early_initrd);
 
 static int __init parse_tag_initrd(const struct tag *tag)
 {
@@ -560,7 +563,7 @@ static void __init free_unused_memmap_node(int node, struct meminfo *mi)
  */
 void __init mem_init(void)
 {
-	unsigned int codesize, datasize, initsize;
+	unsigned long reserved_pages, free_pages;
 	int i, node;
 
 #ifndef CONFIG_DISCONTIGMEM
@@ -596,6 +599,33 @@ void __init mem_init(void)
 	totalram_pages += totalhigh_pages;
 #endif
 
+	reserved_pages = free_pages = 0;
+
+	for_each_online_node(node) {
+		pg_data_t *n = NODE_DATA(node);
+		struct page *map = pgdat_page_nr(n, 0) - n->node_start_pfn;
+
+		for_each_nodebank(i, &meminfo, node) {
+			struct membank *bank = &meminfo.bank[i];
+			unsigned int pfn1, pfn2;
+			struct page *page, *end;
+
+			pfn1 = bank_pfn_start(bank);
+			pfn2 = bank_pfn_end(bank);
+
+			page = map + pfn1;
+			end  = map + pfn2;
+
+			do {
+				if (PageReserved(page))
+					reserved_pages++;
+				else if (!page_count(page))
+					free_pages++;
+				page++;
+			} while (page < end);
+		}
+	}
+
 	/*
 	 * Since our memory may not be contiguous, calculate the
 	 * real number of pages we have in this system
@@ -608,16 +638,71 @@ void __init mem_init(void)
 	}
 	printk(" = %luMB total\n", num_physpages >> (20 - PAGE_SHIFT));
 
-	codesize = _etext - _text;
-	datasize = _end - _data;
-	initsize = __init_end - __init_begin;
-
-	printk(KERN_NOTICE "Memory: %luKB available (%dK code, "
-		"%dK data, %dK init, %luK highmem)\n",
-		nr_free_pages() << (PAGE_SHIFT-10), codesize >> 10,
-		datasize >> 10, initsize >> 10,
+	printk(KERN_NOTICE "Memory: %luk/%luk available, %luk reserved, %luK highmem\n",
+		nr_free_pages() << (PAGE_SHIFT-10),
+		free_pages << (PAGE_SHIFT-10),
+		reserved_pages << (PAGE_SHIFT-10),
 		totalhigh_pages << (PAGE_SHIFT-10));
 
+#define MLK(b, t) b, t, ((t) - (b)) >> 10
+#define MLM(b, t) b, t, ((t) - (b)) >> 20
+#define MLK_ROUNDUP(b, t) b, t, DIV_ROUND_UP(((t) - (b)), SZ_1K)
+
+	printk(KERN_NOTICE "Virtual kernel memory layout:\n"
+			"    vector  : 0x%08lx - 0x%08lx   (%4ld kB)\n"
+			"    fixmap  : 0x%08lx - 0x%08lx   (%4ld kB)\n"
+#ifdef CONFIG_MMU
+			"    DMA     : 0x%08lx - 0x%08lx   (%4ld MB)\n"
+#endif
+			"    vmalloc : 0x%08lx - 0x%08lx   (%4ld MB)\n"
+			"    lowmem  : 0x%08lx - 0x%08lx   (%4ld MB)\n"
+#ifdef CONFIG_HIGHMEM
+			"    pkmap   : 0x%08lx - 0x%08lx   (%4ld MB)\n"
+#endif
+			"    modules : 0x%08lx - 0x%08lx   (%4ld MB)\n"
+			"      .init : 0x%p" " - 0x%p" "   (%4d kB)\n"
+			"      .text : 0x%p" " - 0x%p" "   (%4d kB)\n"
+			"      .data : 0x%p" " - 0x%p" "   (%4d kB)\n",
+
+			MLK(UL(CONFIG_VECTORS_BASE), UL(CONFIG_VECTORS_BASE) +
+				(PAGE_SIZE)),
+			MLK(FIXADDR_START, FIXADDR_TOP),
+#ifdef CONFIG_MMU
+			MLM(CONSISTENT_BASE, CONSISTENT_END),
+#endif
+			MLM(VMALLOC_START, VMALLOC_END),
+			MLM(PAGE_OFFSET, (unsigned long)high_memory),
+#ifdef CONFIG_HIGHMEM
+			MLM(PKMAP_BASE, (PKMAP_BASE) + (LAST_PKMAP) *
+				(PAGE_SIZE)),
+#endif
+			MLM(MODULES_VADDR, MODULES_END),
+
+			MLK_ROUNDUP(__init_begin, __init_end),
+			MLK_ROUNDUP(_text, _etext),
+			MLK_ROUNDUP(_data, _edata));
+
+#undef MLK
+#undef MLM
+#undef MLK_ROUNDUP
+
+	/*
+	 * Check boundaries twice: Some fundamental inconsistencies can
+	 * be detected at build time already.
+	 */
+#ifdef CONFIG_MMU
+	BUILD_BUG_ON(VMALLOC_END			> CONSISTENT_BASE);
+	BUG_ON(VMALLOC_END				> CONSISTENT_BASE);
+
+	BUILD_BUG_ON(TASK_SIZE				> MODULES_VADDR);
+	BUG_ON(TASK_SIZE 				> MODULES_VADDR);
+#endif
+
+#ifdef CONFIG_HIGHMEM
+	BUILD_BUG_ON(PKMAP_BASE + LAST_PKMAP * PAGE_SIZE > PAGE_OFFSET);
+	BUG_ON(PKMAP_BASE + LAST_PKMAP * PAGE_SIZE	> PAGE_OFFSET);
+#endif
+
 	if (PAGE_SIZE >= 16384 && num_physpages <= 128) {
 		extern int sysctl_overcommit_memory;
 		/*
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index 0ab75c60f7c..28c8b950ef0 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -139,8 +139,8 @@ void __check_kvm_seq(struct mm_struct *mm)
  * which requires the new ioremap'd region to be referenced, the CPU will
  * reference the _old_ region.
  *
- * Note that get_vm_area() allocates a guard 4K page, so we need to mask
- * the size back to 1MB aligned or we will overflow in the loop below.
+ * Note that get_vm_area_caller() allocates a guard 4K page, so we need to
+ * mask the size back to 1MB aligned or we will overflow in the loop below.
  */
 static void unmap_area_sections(unsigned long virt, unsigned long size)
 {
@@ -254,22 +254,8 @@ remap_area_supersections(unsigned long virt, unsigned long pfn,
 }
 #endif
 
-
-/*
- * Remap an arbitrary physical address space into the kernel virtual
- * address space. Needed when the kernel wants to access high addresses
- * directly.
- *
- * NOTE! We need to allow non-page-aligned mappings too: we will obviously
- * have to convert them into an offset in a page-aligned mapping, but the
- * caller shouldn't need to know that small detail.
- *
- * 'flags' are the extra L_PTE_ flags that you want to specify for this
- * mapping.  See <asm/pgtable.h> for more information.
- */
-void __iomem *
-__arm_ioremap_pfn(unsigned long pfn, unsigned long offset, size_t size,
-		  unsigned int mtype)
+void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
+	unsigned long offset, size_t size, unsigned int mtype, void *caller)
 {
 	const struct mem_type *type;
 	int err;
@@ -291,7 +277,7 @@ __arm_ioremap_pfn(unsigned long pfn, unsigned long offset, size_t size,
 	 */
 	size = PAGE_ALIGN(offset + size);
 
- 	area = get_vm_area(size, VM_IOREMAP);
+	area = get_vm_area_caller(size, VM_IOREMAP, caller);
  	if (!area)
  		return NULL;
  	addr = (unsigned long)area->addr;
@@ -318,10 +304,9 @@ __arm_ioremap_pfn(unsigned long pfn, unsigned long offset, size_t size,
 	flush_cache_vmap(addr, addr + size);
 	return (void __iomem *) (offset + addr);
 }
-EXPORT_SYMBOL(__arm_ioremap_pfn);
 
-void __iomem *
-__arm_ioremap(unsigned long phys_addr, size_t size, unsigned int mtype)
+void __iomem *__arm_ioremap_caller(unsigned long phys_addr, size_t size,
+	unsigned int mtype, void *caller)
 {
 	unsigned long last_addr;
  	unsigned long offset = phys_addr & ~PAGE_MASK;
@@ -334,7 +319,33 @@ __arm_ioremap(unsigned long phys_addr, size_t size, unsigned int mtype)
 	if (!size || last_addr < phys_addr)
 		return NULL;
 
- 	return __arm_ioremap_pfn(pfn, offset, size, mtype);
+	return __arm_ioremap_pfn_caller(pfn, offset, size, mtype,
+			caller);
+}
+
+/*
+ * Remap an arbitrary physical address space into the kernel virtual
+ * address space. Needed when the kernel wants to access high addresses
+ * directly.
+ *
+ * NOTE! We need to allow non-page-aligned mappings too: we will obviously
+ * have to convert them into an offset in a page-aligned mapping, but the
+ * caller shouldn't need to know that small detail.
+ */
+void __iomem *
+__arm_ioremap_pfn(unsigned long pfn, unsigned long offset, size_t size,
+		  unsigned int mtype)
+{
+	return __arm_ioremap_pfn_caller(pfn, offset, size, mtype,
+			__builtin_return_address(0));
+}
+EXPORT_SYMBOL(__arm_ioremap_pfn);
+
+void __iomem *
+__arm_ioremap(unsigned long phys_addr, size_t size, unsigned int mtype)
+{
+	return __arm_ioremap_caller(phys_addr, size, mtype,
+			__builtin_return_address(0));
 }
 EXPORT_SYMBOL(__arm_ioremap);
 
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 1708da82da9..88f5d71248d 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -100,18 +100,17 @@ static struct cachepolicy cache_policies[] __initdata = {
  * writebuffer to be turned off.  (Note: the write
  * buffer should not be on and the cache off).
  */
-static void __init early_cachepolicy(char **p)
+static int __init early_cachepolicy(char *p)
 {
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(cache_policies); i++) {
 		int len = strlen(cache_policies[i].policy);
 
-		if (memcmp(*p, cache_policies[i].policy, len) == 0) {
+		if (memcmp(p, cache_policies[i].policy, len) == 0) {
 			cachepolicy = i;
 			cr_alignment &= ~cache_policies[i].cr_mask;
 			cr_no_alignment &= ~cache_policies[i].cr_mask;
-			*p += len;
 			break;
 		}
 	}
@@ -130,36 +129,37 @@ static void __init early_cachepolicy(char **p)
 	}
 	flush_cache_all();
 	set_cr(cr_alignment);
+	return 0;
 }
-__early_param("cachepolicy=", early_cachepolicy);
+early_param("cachepolicy", early_cachepolicy);
 
-static void __init early_nocache(char **__unused)
+static int __init early_nocache(char *__unused)
 {
 	char *p = "buffered";
 	printk(KERN_WARNING "nocache is deprecated; use cachepolicy=%s\n", p);
-	early_cachepolicy(&p);
+	early_cachepolicy(p);
+	return 0;
 }
-__early_param("nocache", early_nocache);
+early_param("nocache", early_nocache);
 
-static void __init early_nowrite(char **__unused)
+static int __init early_nowrite(char *__unused)
 {
 	char *p = "uncached";
 	printk(KERN_WARNING "nowb is deprecated; use cachepolicy=%s\n", p);
-	early_cachepolicy(&p);
+	early_cachepolicy(p);
+	return 0;
 }
-__early_param("nowb", early_nowrite);
+early_param("nowb", early_nowrite);
 
-static void __init early_ecc(char **p)
+static int __init early_ecc(char *p)
 {
-	if (memcmp(*p, "on", 2) == 0) {
+	if (memcmp(p, "on", 2) == 0)
 		ecc_mask = PMD_PROTECTION;
-		*p += 2;
-	} else if (memcmp(*p, "off", 3) == 0) {
+	else if (memcmp(p, "off", 3) == 0)
 		ecc_mask = 0;
-		*p += 3;
-	}
+	return 0;
 }
-__early_param("ecc=", early_ecc);
+early_param("ecc", early_ecc);
 
 static int __init noalign_setup(char *__unused)
 {
@@ -670,9 +670,9 @@ static unsigned long __initdata vmalloc_reserve = SZ_128M;
  * bytes. This can be used to increase (or decrease) the vmalloc
  * area - the default is 128m.
  */
-static void __init early_vmalloc(char **arg)
+static int __init early_vmalloc(char *arg)
 {
-	vmalloc_reserve = memparse(*arg, arg);
+	vmalloc_reserve = memparse(arg, NULL);
 
 	if (vmalloc_reserve < SZ_16M) {
 		vmalloc_reserve = SZ_16M;
@@ -687,8 +687,9 @@ static void __init early_vmalloc(char **arg)
 			"vmalloc area is too big, limiting to %luMB\n",
 			vmalloc_reserve >> 20);
 	}
+	return 0;
 }
-__early_param("vmalloc=", early_vmalloc);
+early_param("vmalloc", early_vmalloc);
 
 #define VMALLOC_MIN	(void *)(VMALLOC_END - vmalloc_reserve)
 
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index 374a8311bc8..9bfeb6b9509 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -74,6 +74,12 @@ void __iomem *__arm_ioremap_pfn(unsigned long pfn, unsigned long offset,
 }
 EXPORT_SYMBOL(__arm_ioremap_pfn);
 
+void __iomem *__arm_ioremap_pfn_caller(unsigned long pfn, unsigned long offset,
+			   size_t size, unsigned int mtype, void *caller)
+{
+	return __arm_ioremap_pfn(pfn, offset, size, mtype);
+}
+
 void __iomem *__arm_ioremap(unsigned long phys_addr, size_t size,
 			    unsigned int mtype)
 {
@@ -81,6 +87,12 @@ void __iomem *__arm_ioremap(unsigned long phys_addr, size_t size,
 }
 EXPORT_SYMBOL(__arm_ioremap);
 
+void __iomem *__arm_ioremap(unsigned long phys_addr, size_t size,
+			    unsigned int mtype, void *caller)
+{
+	return __arm_ioremap(phys_addr, size, mtype);
+}
+
 void __iounmap(volatile void __iomem *addr)
 {
 }