diff --git a/Documentation/devicetree/bindings/arm/l2cc.txt b/Documentation/devicetree/bindings/arm/l2cc.txt
index 0dbabe9a6b0a..2251dccb141e 100644
--- a/Documentation/devicetree/bindings/arm/l2cc.txt
+++ b/Documentation/devicetree/bindings/arm/l2cc.txt
@@ -67,6 +67,11 @@ Optional properties:
   disable if zero.
 - arm,prefetch-offset : Override prefetch offset value. Valid values are
   0-7, 15, 23, and 31.
+- prefetch-data : Data prefetch. Value: <0> (forcibly disable), <1>
+  (forcibly enable), property absent (retain settings set by firmware)
+- prefetch-instr : Instruction prefetch. Value: <0> (forcibly disable),
+  <1> (forcibly enable), property absent (retain settings set by
+  firmware)
 
 Example:
 
diff --git a/Documentation/devicetree/booting-without-of.txt b/Documentation/devicetree/booting-without-of.txt
index e49e423268c0..04d34f6a58f3 100644
--- a/Documentation/devicetree/booting-without-of.txt
+++ b/Documentation/devicetree/booting-without-of.txt
@@ -856,6 +856,10 @@ address which can extend beyond that limit.
   name may clash with standard defined ones, you prefix them with your
   vendor name and a comma.
 
+  Additional properties for the root node:
+
+    - serial-number : a string representing the device's serial number
+
   b) The /cpus node
 
   This node is the parent of all individual CPU nodes. It doesn't
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 0536e8d3cda3..b47457d9387c 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -60,7 +60,7 @@ config ARM
 	select HAVE_KPROBES if !XIP_KERNEL && !CPU_ENDIAN_BE32 && !CPU_V7M
 	select HAVE_KRETPROBES if (HAVE_KPROBES)
 	select HAVE_MEMBLOCK
-	select HAVE_MOD_ARCH_SPECIFIC if ARM_UNWIND
+	select HAVE_MOD_ARCH_SPECIFIC
 	select HAVE_OPROFILE if (HAVE_PERF_EVENTS)
 	select HAVE_OPTPROBES if !THUMB2_KERNEL
 	select HAVE_PERF_EVENTS
@@ -975,11 +975,6 @@ config PLAT_PXA
 config PLAT_VERSATILE
 	bool
 
-config ARM_TIMER_SP804
-	bool
-	select CLKSRC_MMIO
-	select CLKSRC_OF if OF
-
 source "arch/arm/firmware/Kconfig"
 
 source arch/arm/mm/Kconfig
@@ -1682,6 +1677,21 @@ config HAVE_ARCH_TRANSPARENT_HUGEPAGE
 config ARCH_WANT_GENERAL_HUGETLB
 	def_bool y
 
+config ARM_MODULE_PLTS
+	bool "Use PLTs to allow module memory to spill over into vmalloc area"
+	depends on MODULES
+	help
+	  Allocate PLTs when loading modules so that jumps and calls whose
+	  targets are too far away for their relative offsets to be encoded
+	  in the instructions themselves can be bounced via veneers in the
+	  module's PLT. This allows modules to be allocated in the generic
+	  vmalloc area after the dedicated module memory area has been
+	  exhausted. The modules will use slightly more memory, but after
+	  rounding up to page size, the actual memory footprint is usually
+	  the same.
+
+	  Say y if you are getting out of memory errors while loading modules
+
 source "mm/Kconfig"
 
 config FORCE_MAX_ZONEORDER
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 985227cbbd1b..ffb53e86599e 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -19,6 +19,10 @@ LDFLAGS_vmlinux	+= --be8
 LDFLAGS_MODULE	+= --be8
 endif
 
+ifeq ($(CONFIG_ARM_MODULE_PLTS),y)
+LDFLAGS_MODULE	+= -T $(srctree)/arch/arm/kernel/module.lds
+endif
+
 OBJCOPYFLAGS	:=-O binary -R .comment -S
 GZFLAGS		:=-9
 #KBUILD_CFLAGS	+=-pipe
diff --git a/arch/arm/common/Makefile b/arch/arm/common/Makefile
index 70b1eff477b3..6ee5959a813b 100644
--- a/arch/arm/common/Makefile
+++ b/arch/arm/common/Makefile
@@ -11,7 +11,6 @@ obj-$(CONFIG_SHARP_LOCOMO)	+= locomo.o
 obj-$(CONFIG_SHARP_PARAM)	+= sharpsl_param.o
 obj-$(CONFIG_SHARP_SCOOP)	+= scoop.o
 obj-$(CONFIG_PCI_HOST_ITE8152)  += it8152.o
-obj-$(CONFIG_ARM_TIMER_SP804)	+= timer-sp.o
 obj-$(CONFIG_MCPM)		+= mcpm_head.o mcpm_entry.o mcpm_platsmp.o vlock.o
 CFLAGS_REMOVE_mcpm_entry.o	= -pg
 AFLAGS_mcpm_head.o		:= -march=armv7-a
diff --git a/arch/arm/include/asm/cmpxchg.h b/arch/arm/include/asm/cmpxchg.h
index abb2c3769b01..1692a05d3207 100644
--- a/arch/arm/include/asm/cmpxchg.h
+++ b/arch/arm/include/asm/cmpxchg.h
@@ -94,6 +94,7 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
 		break;
 #endif
 	default:
+		/* Cause a link-time error, the xchg() size is not supported */
 		__bad_xchg(ptr, size), ret = 0;
 		break;
 	}
@@ -102,8 +103,10 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
 	return ret;
 }
 
-#define xchg(ptr,x) \
-	((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))
+#define xchg(ptr, x) ({							\
+	(__typeof__(*(ptr)))__xchg((unsigned long)(x), (ptr),		\
+				   sizeof(*(ptr)));			\
+})
 
 #include <asm-generic/cmpxchg-local.h>
 
@@ -118,14 +121,16 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
  * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make
  * them available.
  */
-#define cmpxchg_local(ptr, o, n)				  	       \
-	((__typeof__(*(ptr)))__cmpxchg_local_generic((ptr), (unsigned long)(o),\
-			(unsigned long)(n), sizeof(*(ptr))))
+#define cmpxchg_local(ptr, o, n) ({					\
+	(__typeof(*ptr))__cmpxchg_local_generic((ptr),			\
+					        (unsigned long)(o),	\
+					        (unsigned long)(n),	\
+					        sizeof(*(ptr)));	\
+})
+
 #define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
 
-#ifndef CONFIG_SMP
 #include <asm-generic/cmpxchg.h>
-#endif
 
 #else	/* min ARCH >= ARMv6 */
 
@@ -201,11 +206,12 @@ static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old,
 	return ret;
 }
 
-#define cmpxchg(ptr,o,n)						\
-	((__typeof__(*(ptr)))__cmpxchg_mb((ptr),			\
-					  (unsigned long)(o),		\
-					  (unsigned long)(n),		\
-					  sizeof(*(ptr))))
+#define cmpxchg(ptr,o,n) ({						\
+	(__typeof__(*(ptr)))__cmpxchg_mb((ptr),				\
+					 (unsigned long)(o),		\
+					 (unsigned long)(n),		\
+					 sizeof(*(ptr)));		\
+})
 
 static inline unsigned long __cmpxchg_local(volatile void *ptr,
 					    unsigned long old,
@@ -227,6 +233,13 @@ static inline unsigned long __cmpxchg_local(volatile void *ptr,
 	return ret;
 }
 
+#define cmpxchg_local(ptr, o, n) ({					\
+	(__typeof(*ptr))__cmpxchg_local((ptr),				\
+				        (unsigned long)(o),		\
+				        (unsigned long)(n),		\
+				        sizeof(*(ptr)));		\
+})
+
 static inline unsigned long long __cmpxchg64(unsigned long long *ptr,
 					     unsigned long long old,
 					     unsigned long long new)
@@ -252,6 +265,14 @@ static inline unsigned long long __cmpxchg64(unsigned long long *ptr,
 	return oldval;
 }
 
+#define cmpxchg64_relaxed(ptr, o, n) ({					\
+	(__typeof__(*(ptr)))__cmpxchg64((ptr),				\
+					(unsigned long long)(o),	\
+					(unsigned long long)(n));	\
+})
+
+#define cmpxchg64_local(ptr, o, n) cmpxchg64_relaxed((ptr), (o), (n))
+
 static inline unsigned long long __cmpxchg64_mb(unsigned long long *ptr,
 						unsigned long long old,
 						unsigned long long new)
@@ -265,23 +286,11 @@ static inline unsigned long long __cmpxchg64_mb(unsigned long long *ptr,
 	return ret;
 }
 
-#define cmpxchg_local(ptr,o,n)						\
-	((__typeof__(*(ptr)))__cmpxchg_local((ptr),			\
-				       (unsigned long)(o),		\
-				       (unsigned long)(n),		\
-				       sizeof(*(ptr))))
-
-#define cmpxchg64(ptr, o, n)						\
-	((__typeof__(*(ptr)))__cmpxchg64_mb((ptr),			\
-					(unsigned long long)(o),	\
-					(unsigned long long)(n)))
-
-#define cmpxchg64_relaxed(ptr, o, n)					\
-	((__typeof__(*(ptr)))__cmpxchg64((ptr),				\
-					(unsigned long long)(o),	\
-					(unsigned long long)(n)))
-
-#define cmpxchg64_local(ptr, o, n)	cmpxchg64_relaxed((ptr), (o), (n))
+#define cmpxchg64(ptr, o, n) ({						\
+	(__typeof__(*(ptr)))__cmpxchg64_mb((ptr),			\
+					   (unsigned long long)(o),	\
+					   (unsigned long long)(n));	\
+})
 
 #endif	/* __LINUX_ARM_ARCH__ >= 6 */
 
diff --git a/arch/arm/include/asm/dma-iommu.h b/arch/arm/include/asm/dma-iommu.h
index 8e3fcb924db6..2ef282f96651 100644
--- a/arch/arm/include/asm/dma-iommu.h
+++ b/arch/arm/include/asm/dma-iommu.h
@@ -25,7 +25,7 @@ struct dma_iommu_mapping {
 };
 
 struct dma_iommu_mapping *
-arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, size_t size);
+arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, u64 size);
 
 void arm_iommu_release_mapping(struct dma_iommu_mapping *mapping);
 
diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h
index db58deb00aa7..addfb3dd095f 100644
--- a/arch/arm/include/asm/io.h
+++ b/arch/arm/include/asm/io.h
@@ -23,6 +23,7 @@
 
 #ifdef __KERNEL__
 
+#include <linux/string.h>
 #include <linux/types.h>
 #include <linux/blk_types.h>
 #include <asm/byteorder.h>
@@ -73,17 +74,16 @@ void __raw_readsl(const volatile void __iomem *addr, void *data, int longlen);
 static inline void __raw_writew(u16 val, volatile void __iomem *addr)
 {
 	asm volatile("strh %1, %0"
-		     : "+Q" (*(volatile u16 __force *)addr)
-		     : "r" (val));
+		     : : "Q" (*(volatile u16 __force *)addr), "r" (val));
 }
 
 #define __raw_readw __raw_readw
 static inline u16 __raw_readw(const volatile void __iomem *addr)
 {
 	u16 val;
-	asm volatile("ldrh %1, %0"
-		     : "+Q" (*(volatile u16 __force *)addr),
-		       "=r" (val));
+	asm volatile("ldrh %0, %1"
+		     : "=r" (val)
+		     : "Q" (*(volatile u16 __force *)addr));
 	return val;
 }
 #endif
@@ -92,25 +92,23 @@ static inline u16 __raw_readw(const volatile void __iomem *addr)
 static inline void __raw_writeb(u8 val, volatile void __iomem *addr)
 {
 	asm volatile("strb %1, %0"
-		     : "+Qo" (*(volatile u8 __force *)addr)
-		     : "r" (val));
+		     : : "Qo" (*(volatile u8 __force *)addr), "r" (val));
 }
 
 #define __raw_writel __raw_writel
 static inline void __raw_writel(u32 val, volatile void __iomem *addr)
 {
 	asm volatile("str %1, %0"
-		     : "+Qo" (*(volatile u32 __force *)addr)
-		     : "r" (val));
+		     : : "Qo" (*(volatile u32 __force *)addr), "r" (val));
 }
 
 #define __raw_readb __raw_readb
 static inline u8 __raw_readb(const volatile void __iomem *addr)
 {
 	u8 val;
-	asm volatile("ldrb %1, %0"
-		     : "+Qo" (*(volatile u8 __force *)addr),
-		       "=r" (val));
+	asm volatile("ldrb %0, %1"
+		     : "=r" (val)
+		     : "Qo" (*(volatile u8 __force *)addr));
 	return val;
 }
 
@@ -118,9 +116,9 @@ static inline u8 __raw_readb(const volatile void __iomem *addr)
 static inline u32 __raw_readl(const volatile void __iomem *addr)
 {
 	u32 val;
-	asm volatile("ldr %1, %0"
-		     : "+Qo" (*(volatile u32 __force *)addr),
-		       "=r" (val));
+	asm volatile("ldr %0, %1"
+		     : "=r" (val)
+		     : "Qo" (*(volatile u32 __force *)addr));
 	return val;
 }
 
@@ -319,9 +317,33 @@ extern void _memset_io(volatile void __iomem *, int, size_t);
 #define writesw(p,d,l)		__raw_writesw(p,d,l)
 #define writesl(p,d,l)		__raw_writesl(p,d,l)
 
+#ifndef __ARMBE__
+static inline void memset_io(volatile void __iomem *dst, unsigned c,
+	size_t count)
+{
+	memset((void __force *)dst, c, count);
+}
+#define memset_io(dst,c,count) memset_io(dst,c,count)
+
+static inline void memcpy_fromio(void *to, const volatile void __iomem *from,
+	size_t count)
+{
+	memcpy(to, (const void __force *)from, count);
+}
+#define memcpy_fromio(to,from,count) memcpy_fromio(to,from,count)
+
+static inline void memcpy_toio(volatile void __iomem *to, const void *from,
+	size_t count)
+{
+	memcpy((void __force *)to, from, count);
+}
+#define memcpy_toio(to,from,count) memcpy_toio(to,from,count)
+
+#else
 #define memset_io(c,v,l)	_memset_io(c,(v),(l))
 #define memcpy_fromio(a,c,l)	_memcpy_fromio((a),c,(l))
 #define memcpy_toio(c,a,l)	_memcpy_toio(c,(a),(l))
+#endif
 
 #endif	/* readl */
 
diff --git a/arch/arm/include/asm/mach/arch.h b/arch/arm/include/asm/mach/arch.h
index 0406cb3f1af7..cb3a40717edd 100644
--- a/arch/arm/include/asm/mach/arch.h
+++ b/arch/arm/include/asm/mach/arch.h
@@ -51,7 +51,7 @@ struct machine_desc {
 	bool			(*smp_init)(void);
 	void			(*fixup)(struct tag *, char **);
 	void			(*dt_fixup)(void);
-	void			(*init_meminfo)(void);
+	long long		(*pv_fixup)(void);
 	void			(*reserve)(void);/* reserve mem blocks	*/
 	void			(*map_io)(void);/* IO mapping function	*/
 	void			(*init_early)(void);
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index 184def0e1652..3a72d69b3255 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -18,8 +18,6 @@
 #include <linux/types.h>
 #include <linux/sizes.h>
 
-#include <asm/cache.h>
-
 #ifdef CONFIG_NEED_MACH_MEMORY_H
 #include <mach/memory.h>
 #endif
@@ -132,20 +130,6 @@
 #define page_to_phys(page)	(__pfn_to_phys(page_to_pfn(page)))
 #define phys_to_page(phys)	(pfn_to_page(__phys_to_pfn(phys)))
 
-/*
- * Minimum guaranted alignment in pgd_alloc().  The page table pointers passed
- * around in head.S and proc-*.S are shifted by this amount, in order to
- * leave spare high bits for systems with physical address extension.  This
- * does not fully accomodate the 40-bit addressing capability of ARM LPAE, but
- * gives us about 38-bits or so.
- */
-#ifdef CONFIG_ARM_LPAE
-#define ARCH_PGD_SHIFT		L1_CACHE_SHIFT
-#else
-#define ARCH_PGD_SHIFT		0
-#endif
-#define ARCH_PGD_MASK		((1 << ARCH_PGD_SHIFT) - 1)
-
 /*
  * PLAT_PHYS_OFFSET is the offset (from zero) of the start of physical
  * memory.  This is used for XIP and NoMMU kernels, and on platforms that don't
diff --git a/arch/arm/include/asm/module.h b/arch/arm/include/asm/module.h
index ed690c49ef93..e358b7966c06 100644
--- a/arch/arm/include/asm/module.h
+++ b/arch/arm/include/asm/module.h
@@ -16,11 +16,21 @@ enum {
 	ARM_SEC_UNLIKELY,
 	ARM_SEC_MAX,
 };
+#endif
 
 struct mod_arch_specific {
+#ifdef CONFIG_ARM_UNWIND
 	struct unwind_table *unwind[ARM_SEC_MAX];
-};
 #endif
+#ifdef CONFIG_ARM_MODULE_PLTS
+	struct elf32_shdr   *core_plt;
+	struct elf32_shdr   *init_plt;
+	int		    core_plt_count;
+	int		    init_plt_count;
+#endif
+};
+
+u32 get_module_plt(struct module *mod, unsigned long loc, Elf32_Addr val);
 
 /*
  * Add the ARM architecture version to the version magic string
diff --git a/arch/arm/include/asm/proc-fns.h b/arch/arm/include/asm/proc-fns.h
index 5324c1112f3a..8877ad5ffe10 100644
--- a/arch/arm/include/asm/proc-fns.h
+++ b/arch/arm/include/asm/proc-fns.h
@@ -125,13 +125,6 @@ extern void cpu_resume(void);
 		ttbr;						\
 	})
 
-#define cpu_set_ttbr(nr, val)					\
-	do {							\
-		u64 ttbr = val;					\
-		__asm__("mcrr	p15, " #nr ", %Q0, %R0, c2"	\
-			: : "r" (ttbr));			\
-	} while (0)
-
 #define cpu_get_pgd()	\
 	({						\
 		u64 pg = cpu_get_ttbr(0);		\
diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h
index 18f5a554134f..2f3ac1ba6fb4 100644
--- a/arch/arm/include/asm/smp.h
+++ b/arch/arm/include/asm/smp.h
@@ -61,7 +61,7 @@ asmlinkage void secondary_start_kernel(void);
 struct secondary_data {
 	union {
 		unsigned long mpu_rgn_szr;
-		unsigned long pgdir;
+		u64 pgdir;
 	};
 	unsigned long swapper_pg_dir;
 	void *stack;
@@ -69,6 +69,7 @@ struct secondary_data {
 extern struct secondary_data secondary_data;
 extern volatile int pen_release;
 extern void secondary_startup(void);
+extern void secondary_startup_arm(void);
 
 extern int __cpu_disable(void);
 
diff --git a/arch/arm/include/asm/system_info.h b/arch/arm/include/asm/system_info.h
index 720ea0320a6d..3860cbd401ec 100644
--- a/arch/arm/include/asm/system_info.h
+++ b/arch/arm/include/asm/system_info.h
@@ -17,6 +17,7 @@
 
 /* information about the system we're running on */
 extern unsigned int system_rev;
+extern const char *system_serial;
 extern unsigned int system_serial_low;
 extern unsigned int system_serial_high;
 extern unsigned int mem_fclk_21285;
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index 752725dcbf42..32c0990d1968 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -34,6 +34,7 @@ obj-$(CONFIG_CPU_IDLE)		+= cpuidle.o
 obj-$(CONFIG_ISA_DMA_API)	+= dma.o
 obj-$(CONFIG_FIQ)		+= fiq.o fiqasm.o
 obj-$(CONFIG_MODULES)		+= armksyms.o module.o
+obj-$(CONFIG_ARM_MODULE_PLTS)	+= module-plts.o
 obj-$(CONFIG_ISA_DMA)		+= dma-isa.o
 obj-$(CONFIG_PCI)		+= bios32.o isa.o
 obj-$(CONFIG_ARM_CPU_SUSPEND)	+= sleep.o suspend.o
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index f8ccc21fa032..4e7f40c577e6 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -33,7 +33,9 @@ ret_fast_syscall:
  UNWIND(.fnstart	)
  UNWIND(.cantunwind	)
 	disable_irq				@ disable interrupts
-	ldr	r1, [tsk, #TI_FLAGS]
+	ldr	r1, [tsk, #TI_FLAGS]		@ re-check for syscall tracing
+	tst	r1, #_TIF_SYSCALL_WORK
+	bne	__sys_trace_return
 	tst	r1, #_TIF_WORK_MASK
 	bne	fast_work_pending
 	asm_trace_hardirqs_on
diff --git a/arch/arm/kernel/entry-v7m.S b/arch/arm/kernel/entry-v7m.S
index 8944f4991c3c..b6c8bb9315e7 100644
--- a/arch/arm/kernel/entry-v7m.S
+++ b/arch/arm/kernel/entry-v7m.S
@@ -117,9 +117,14 @@ ENTRY(__switch_to)
 ENDPROC(__switch_to)
 
 	.data
-	.align	8
+#if CONFIG_CPU_V7M_NUM_IRQ <= 112
+	.align	9
+#else
+	.align	10
+#endif
+
 /*
- * Vector table (64 words => 256 bytes natural alignment)
+ * Vector table (Natural alignment need to be ensured)
  */
 ENTRY(vector_table)
 	.long	0			@ 0 - Reset stack pointer
@@ -138,6 +143,6 @@ ENTRY(vector_table)
 	.long	__invalid_entry		@ 13 - Reserved
 	.long	__pendsv_entry		@ 14 - PendSV
 	.long	__invalid_entry		@ 15 - SysTick
-	.rept	64 - 16
-	.long	__irq_entry		@ 16..64 - External Interrupts
+	.rept	CONFIG_CPU_V7M_NUM_IRQ
+	.long	__irq_entry		@ External Interrupts
 	.endr
diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S
index aebfbf79a1a3..84da14b7cd04 100644
--- a/arch/arm/kernel/head-nommu.S
+++ b/arch/arm/kernel/head-nommu.S
@@ -123,7 +123,7 @@ ENTRY(secondary_startup)
 ENDPROC(secondary_startup)
 
 ENTRY(__secondary_switched)
-	ldr	sp, [r7, #8]			@ set up the stack pointer
+	ldr	sp, [r7, #12]			@ set up the stack pointer
 	mov	fp, #0
 	b	secondary_start_kernel
 ENDPROC(__secondary_switched)
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 3637973a9708..e13c9cb2e99f 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -131,13 +131,30 @@ ENTRY(stext)
 	 * The following calls CPU specific code in a position independent
 	 * manner.  See arch/arm/mm/proc-*.S for details.  r10 = base of
 	 * xxx_proc_info structure selected by __lookup_processor_type
-	 * above.  On return, the CPU will be ready for the MMU to be
-	 * turned on, and r0 will hold the CPU control register value.
+	 * above.
+	 *
+	 * The processor init function will be called with:
+	 *  r1 - machine type
+	 *  r2 - boot data (atags/dt) pointer
+	 *  r4 - translation table base (low word)
+	 *  r5 - translation table base (high word, if LPAE)
+	 *  r8 - translation table base 1 (pfn if LPAE)
+	 *  r9 - cpuid
+	 *  r13 - virtual address for __enable_mmu -> __turn_mmu_on
+	 *
+	 * On return, the CPU will be ready for the MMU to be turned on,
+	 * r0 will hold the CPU control register value, r1, r2, r4, and
+	 * r9 will be preserved.  r5 will also be preserved if LPAE.
 	 */
 	ldr	r13, =__mmap_switched		@ address to jump to after
 						@ mmu has been enabled
 	adr	lr, BSYM(1f)			@ return (PIC) address
+#ifdef CONFIG_ARM_LPAE
+	mov	r5, #0				@ high TTBR0
+	mov	r8, r4, lsr #12			@ TTBR1 is swapper_pg_dir pfn
+#else
 	mov	r8, r4				@ set TTBR1 to swapper_pg_dir
+#endif
 	ldr	r12, [r10, #PROCINFO_INITFUNC]
 	add	r12, r12, r10
 	ret	r12
@@ -158,7 +175,7 @@ ENDPROC(stext)
  *
  * Returns:
  *  r0, r3, r5-r7 corrupted
- *  r4 = page table (see ARCH_PGD_SHIFT in asm/memory.h)
+ *  r4 = physical page table address
  */
 __create_page_tables:
 	pgtbl	r4, r8				@ page table address
@@ -333,7 +350,6 @@ __create_page_tables:
 #endif
 #ifdef CONFIG_ARM_LPAE
 	sub	r4, r4, #0x1000		@ point to the PGD table
-	mov	r4, r4, lsr #ARCH_PGD_SHIFT
 #endif
 	ret	lr
 ENDPROC(__create_page_tables)
@@ -346,8 +362,8 @@ __turn_mmu_on_loc:
 
 #if defined(CONFIG_SMP)
 	.text
-ENTRY(secondary_startup_arm)
 	.arm
+ENTRY(secondary_startup_arm)
  THUMB(	adr	r9, BSYM(1f)	)	@ Kernel is entered in ARM.
  THUMB(	bx	r9		)	@ If this is a Thumb-2 kernel,
  THUMB(	.thumb			)	@ switch to Thumb now.
@@ -381,9 +397,9 @@ ENTRY(secondary_startup)
 	adr	r4, __secondary_data
 	ldmia	r4, {r5, r7, r12}		@ address to jump to after
 	sub	lr, r4, r5			@ mmu has been enabled
-	ldr	r4, [r7, lr]			@ get secondary_data.pgdir
-	add	r7, r7, #4
-	ldr	r8, [r7, lr]			@ get secondary_data.swapper_pg_dir
+	add	r3, r7, lr
+	ldrd	r4, [r3, #0]			@ get secondary_data.pgdir
+	ldr	r8, [r3, #8]			@ get secondary_data.swapper_pg_dir
 	adr	lr, BSYM(__enable_mmu)		@ return address
 	mov	r13, r12			@ __secondary_switched address
 	ldr	r12, [r10, #PROCINFO_INITFUNC]
@@ -397,7 +413,7 @@ ENDPROC(secondary_startup_arm)
 	 * r6  = &secondary_data
 	 */
 ENTRY(__secondary_switched)
-	ldr	sp, [r7, #4]			@ get secondary_data.stack
+	ldr	sp, [r7, #12]			@ get secondary_data.stack
 	mov	fp, #0
 	b	secondary_start_kernel
 ENDPROC(__secondary_switched)
@@ -416,12 +432,14 @@ __secondary_data:
 /*
  * Setup common bits before finally enabling the MMU.  Essentially
  * this is just loading the page table pointer and domain access
- * registers.
+ * registers.  All these registers need to be preserved by the
+ * processor setup function (or set in the case of r0)
  *
  *  r0  = cp#15 control register
  *  r1  = machine ID
  *  r2  = atags or dtb pointer
- *  r4  = page table (see ARCH_PGD_SHIFT in asm/memory.h)
+ *  r4  = TTBR pointer (low word)
+ *  r5  = TTBR pointer (high word if LPAE)
  *  r9  = processor ID
  *  r13 = *virtual* address to jump to upon completion
  */
@@ -440,7 +458,9 @@ __enable_mmu:
 #ifdef CONFIG_CPU_ICACHE_DISABLE
 	bic	r0, r0, #CR_I
 #endif
-#ifndef CONFIG_ARM_LPAE
+#ifdef CONFIG_ARM_LPAE
+	mcrr	p15, 0, r4, r5, c2		@ load TTBR0
+#else
 	mov	r5, #(domain_val(DOMAIN_USER, DOMAIN_MANAGER) | \
 		      domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) | \
 		      domain_val(DOMAIN_TABLE, DOMAIN_MANAGER) | \
diff --git a/arch/arm/kernel/module-plts.c b/arch/arm/kernel/module-plts.c
new file mode 100644
index 000000000000..097e2e201b9f
--- /dev/null
+++ b/arch/arm/kernel/module-plts.c
@@ -0,0 +1,183 @@
+/*
+ * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/elf.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include <asm/cache.h>
+#include <asm/opcodes.h>
+
+#define PLT_ENT_STRIDE		L1_CACHE_BYTES
+#define PLT_ENT_COUNT		(PLT_ENT_STRIDE / sizeof(u32))
+#define PLT_ENT_SIZE		(sizeof(struct plt_entries) / PLT_ENT_COUNT)
+
+#ifdef CONFIG_THUMB2_KERNEL
+#define PLT_ENT_LDR		__opcode_to_mem_thumb32(0xf8dff000 | \
+							(PLT_ENT_STRIDE - 4))
+#else
+#define PLT_ENT_LDR		__opcode_to_mem_arm(0xe59ff000 | \
+						    (PLT_ENT_STRIDE - 8))
+#endif
+
+struct plt_entries {
+	u32	ldr[PLT_ENT_COUNT];
+	u32	lit[PLT_ENT_COUNT];
+};
+
+static bool in_init(const struct module *mod, u32 addr)
+{
+	return addr - (u32)mod->module_init < mod->init_size;
+}
+
+u32 get_module_plt(struct module *mod, unsigned long loc, Elf32_Addr val)
+{
+	struct plt_entries *plt, *plt_end;
+	int c, *count;
+
+	if (in_init(mod, loc)) {
+		plt = (void *)mod->arch.init_plt->sh_addr;
+		plt_end = (void *)plt + mod->arch.init_plt->sh_size;
+		count = &mod->arch.init_plt_count;
+	} else {
+		plt = (void *)mod->arch.core_plt->sh_addr;
+		plt_end = (void *)plt + mod->arch.core_plt->sh_size;
+		count = &mod->arch.core_plt_count;
+	}
+
+	/* Look for an existing entry pointing to 'val' */
+	for (c = *count; plt < plt_end; c -= PLT_ENT_COUNT, plt++) {
+		int i;
+
+		if (!c) {
+			/* Populate a new set of entries */
+			*plt = (struct plt_entries){
+				{ [0 ... PLT_ENT_COUNT - 1] = PLT_ENT_LDR, },
+				{ val, }
+			};
+			++*count;
+			return (u32)plt->ldr;
+		}
+		for (i = 0; i < PLT_ENT_COUNT; i++) {
+			if (!plt->lit[i]) {
+				plt->lit[i] = val;
+				++*count;
+			}
+			if (plt->lit[i] == val)
+				return (u32)&plt->ldr[i];
+		}
+	}
+	BUG();
+}
+
+static int duplicate_rel(Elf32_Addr base, const Elf32_Rel *rel, int num,
+			   u32 mask)
+{
+	u32 *loc1, *loc2;
+	int i;
+
+	for (i = 0; i < num; i++) {
+		if (rel[i].r_info != rel[num].r_info)
+			continue;
+
+		/*
+		 * Identical relocation types against identical symbols can
+		 * still result in different PLT entries if the addend in the
+		 * place is different. So resolve the target of the relocation
+		 * to compare the values.
+		 */
+		loc1 = (u32 *)(base + rel[i].r_offset);
+		loc2 = (u32 *)(base + rel[num].r_offset);
+		if (((*loc1 ^ *loc2) & mask) == 0)
+			return 1;
+	}
+	return 0;
+}
+
+/* Count how many PLT entries we may need */
+static unsigned int count_plts(Elf32_Addr base, const Elf32_Rel *rel, int num)
+{
+	unsigned int ret = 0;
+	int i;
+
+	/*
+	 * Sure, this is order(n^2), but it's usually short, and not
+	 * time critical
+	 */
+	for (i = 0; i < num; i++)
+		switch (ELF32_R_TYPE(rel[i].r_info)) {
+		case R_ARM_CALL:
+		case R_ARM_PC24:
+		case R_ARM_JUMP24:
+			if (!duplicate_rel(base, rel, i,
+					   __opcode_to_mem_arm(0x00ffffff)))
+				ret++;
+			break;
+#ifdef CONFIG_THUMB2_KERNEL
+		case R_ARM_THM_CALL:
+		case R_ARM_THM_JUMP24:
+			if (!duplicate_rel(base, rel, i,
+					   __opcode_to_mem_thumb32(0x07ff2fff)))
+				ret++;
+#endif
+		}
+	return ret;
+}
+
+int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
+			      char *secstrings, struct module *mod)
+{
+	unsigned long core_plts = 0, init_plts = 0;
+	Elf32_Shdr *s, *sechdrs_end = sechdrs + ehdr->e_shnum;
+
+	/*
+	 * To store the PLTs, we expand the .text section for core module code
+	 * and the .init.text section for initialization code.
+	 */
+	for (s = sechdrs; s < sechdrs_end; ++s)
+		if (strcmp(".core.plt", secstrings + s->sh_name) == 0)
+			mod->arch.core_plt = s;
+		else if (strcmp(".init.plt", secstrings + s->sh_name) == 0)
+			mod->arch.init_plt = s;
+
+	if (!mod->arch.core_plt || !mod->arch.init_plt) {
+		pr_err("%s: sections missing\n", mod->name);
+		return -ENOEXEC;
+	}
+
+	for (s = sechdrs + 1; s < sechdrs_end; ++s) {
+		const Elf32_Rel *rels = (void *)ehdr + s->sh_offset;
+		int numrels = s->sh_size / sizeof(Elf32_Rel);
+		Elf32_Shdr *dstsec = sechdrs + s->sh_info;
+
+		if (s->sh_type != SHT_REL)
+			continue;
+
+		if (strstr(secstrings + s->sh_name, ".init"))
+			init_plts += count_plts(dstsec->sh_addr, rels, numrels);
+		else
+			core_plts += count_plts(dstsec->sh_addr, rels, numrels);
+	}
+
+	mod->arch.core_plt->sh_type = SHT_NOBITS;
+	mod->arch.core_plt->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
+	mod->arch.core_plt->sh_addralign = L1_CACHE_BYTES;
+	mod->arch.core_plt->sh_size = round_up(core_plts * PLT_ENT_SIZE,
+					       sizeof(struct plt_entries));
+	mod->arch.core_plt_count = 0;
+
+	mod->arch.init_plt->sh_type = SHT_NOBITS;
+	mod->arch.init_plt->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
+	mod->arch.init_plt->sh_addralign = L1_CACHE_BYTES;
+	mod->arch.init_plt->sh_size = round_up(init_plts * PLT_ENT_SIZE,
+					       sizeof(struct plt_entries));
+	mod->arch.init_plt_count = 0;
+	pr_debug("%s: core.plt=%x, init.plt=%x\n", __func__,
+		 mod->arch.core_plt->sh_size, mod->arch.init_plt->sh_size);
+	return 0;
+}
diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c
index af791f4a6205..efdddcb97dd1 100644
--- a/arch/arm/kernel/module.c
+++ b/arch/arm/kernel/module.c
@@ -40,7 +40,12 @@
 #ifdef CONFIG_MMU
 void *module_alloc(unsigned long size)
 {
-	return __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END,
+	void *p = __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END,
+				GFP_KERNEL, PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE,
+				__builtin_return_address(0));
+	if (!IS_ENABLED(CONFIG_ARM_MODULE_PLTS) || p)
+		return p;
+	return __vmalloc_node_range(size, 1,  VMALLOC_START, VMALLOC_END,
 				GFP_KERNEL, PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE,
 				__builtin_return_address(0));
 }
@@ -110,6 +115,20 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
 				offset -= 0x04000000;
 
 			offset += sym->st_value - loc;
+
+			/*
+			 * Route through a PLT entry if 'offset' exceeds the
+			 * supported range. Note that 'offset + loc + 8'
+			 * contains the absolute jump target, i.e.,
+			 * @sym + addend, corrected for the +8 PC bias.
+			 */
+			if (IS_ENABLED(CONFIG_ARM_MODULE_PLTS) &&
+			    (offset <= (s32)0xfe000000 ||
+			     offset >= (s32)0x02000000))
+				offset = get_module_plt(module, loc,
+							offset + loc + 8)
+					 - loc - 8;
+
 			if (offset <= (s32)0xfe000000 ||
 			    offset >= (s32)0x02000000) {
 				pr_err("%s: section %u reloc %u sym '%s': relocation %u out of range (%#lx -> %#x)\n",
@@ -203,6 +222,17 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
 				offset -= 0x02000000;
 			offset += sym->st_value - loc;
 
+			/*
+			 * Route through a PLT entry if 'offset' exceeds the
+			 * supported range.
+			 */
+			if (IS_ENABLED(CONFIG_ARM_MODULE_PLTS) &&
+			    (offset <= (s32)0xff000000 ||
+			     offset >= (s32)0x01000000))
+				offset = get_module_plt(module, loc,
+							offset + loc + 4)
+					 - loc - 4;
+
 			if (offset <= (s32)0xff000000 ||
 			    offset >= (s32)0x01000000) {
 				pr_err("%s: section %u reloc %u sym '%s': relocation %u out of range (%#lx -> %#x)\n",
diff --git a/arch/arm/kernel/module.lds b/arch/arm/kernel/module.lds
new file mode 100644
index 000000000000..3682fa107918
--- /dev/null
+++ b/arch/arm/kernel/module.lds
@@ -0,0 +1,4 @@
+SECTIONS {
+        .core.plt : { BYTE(0) }
+        .init.plt : { BYTE(0) }
+}
diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c
index 91c7ba182dcd..3b8c2833c537 100644
--- a/arch/arm/kernel/perf_event_cpu.c
+++ b/arch/arm/kernel/perf_event_cpu.c
@@ -303,9 +303,15 @@ static int probe_current_pmu(struct arm_pmu *pmu)
 
 static int of_pmu_irq_cfg(struct platform_device *pdev)
 {
-	int i;
-	int *irqs = kcalloc(pdev->num_resources, sizeof(*irqs), GFP_KERNEL);
+	int i, irq;
+	int *irqs;
 
+	/* Don't bother with PPIs; they're already affine */
+	irq = platform_get_irq(pdev, 0);
+	if (irq >= 0 && irq_is_percpu(irq))
+		return 0;
+
+	irqs = kcalloc(pdev->num_resources, sizeof(*irqs), GFP_KERNEL);
 	if (!irqs)
 		return -ENOMEM;
 
@@ -317,7 +323,7 @@ static int of_pmu_irq_cfg(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/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 6c777e908a24..e6d8c7658ffd 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -75,8 +75,7 @@ __setup("fpe=", fpe_setup);
 
 extern void init_default_cache_policy(unsigned long);
 extern void paging_init(const struct machine_desc *desc);
-extern void early_paging_init(const struct machine_desc *,
-			      struct proc_info_list *);
+extern void early_paging_init(const struct machine_desc *);
 extern void sanity_check_meminfo(void);
 extern enum reboot_mode reboot_mode;
 extern void setup_dma_zone(const struct machine_desc *desc);
@@ -93,6 +92,9 @@ unsigned int __atags_pointer __initdata;
 unsigned int system_rev;
 EXPORT_SYMBOL(system_rev);
 
+const char *system_serial;
+EXPORT_SYMBOL(system_serial);
+
 unsigned int system_serial_low;
 EXPORT_SYMBOL(system_serial_low);
 
@@ -839,8 +841,25 @@ arch_initcall(customize_machine);
 
 static int __init init_machine_late(void)
 {
+	struct device_node *root;
+	int ret;
+
 	if (machine_desc->init_late)
 		machine_desc->init_late();
+
+	root = of_find_node_by_path("/");
+	if (root) {
+		ret = of_property_read_string(root, "serial-number",
+					      &system_serial);
+		if (ret)
+			system_serial = NULL;
+	}
+
+	if (!system_serial)
+		system_serial = kasprintf(GFP_KERNEL, "%08x%08x",
+					  system_serial_high,
+					  system_serial_low);
+
 	return 0;
 }
 late_initcall(init_machine_late);
@@ -936,7 +955,9 @@ void __init setup_arch(char **cmdline_p)
 
 	parse_early_param();
 
-	early_paging_init(mdesc, lookup_processor_type(read_cpuid_id()));
+#ifdef CONFIG_MMU
+	early_paging_init(mdesc);
+#endif
 	setup_dma_zone(mdesc);
 	sanity_check_meminfo();
 	arm_memblock_init(mdesc);
@@ -1109,8 +1130,7 @@ static int c_show(struct seq_file *m, void *v)
 
 	seq_printf(m, "Hardware\t: %s\n", machine_name);
 	seq_printf(m, "Revision\t: %04x\n", system_rev);
-	seq_printf(m, "Serial\t\t: %08x%08x\n",
-		   system_serial_high, system_serial_low);
+	seq_printf(m, "Serial\t\t: %s\n", system_serial);
 
 	return 0;
 }
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index cca5b8758185..90dfbedfbfb8 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -86,9 +86,11 @@ void __init smp_set_ops(struct smp_operations *ops)
 
 static unsigned long get_arch_pgd(pgd_t *pgd)
 {
-	phys_addr_t pgdir = virt_to_idmap(pgd);
-	BUG_ON(pgdir & ARCH_PGD_MASK);
-	return pgdir >> ARCH_PGD_SHIFT;
+#ifdef CONFIG_ARM_LPAE
+	return __phys_to_pfn(virt_to_phys(pgd));
+#else
+	return virt_to_phys(pgd);
+#endif
 }
 
 int __cpu_up(unsigned int cpu, struct task_struct *idle)
@@ -108,7 +110,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 #endif
 
 #ifdef CONFIG_MMU
-	secondary_data.pgdir = get_arch_pgd(idmap_pgd);
+	secondary_data.pgdir = virt_to_phys(idmap_pgd);
 	secondary_data.swapper_pg_dir = get_arch_pgd(swapper_pg_dir);
 #endif
 	sync_cache_w(&secondary_data);
diff --git a/arch/arm/kernel/tcm.c b/arch/arm/kernel/tcm.c
index 7a3be1d4d0b1..b10e1360762e 100644
--- a/arch/arm/kernel/tcm.c
+++ b/arch/arm/kernel/tcm.c
@@ -17,6 +17,9 @@
 #include <asm/mach/map.h>
 #include <asm/memory.h>
 #include <asm/system_info.h>
+#include <asm/traps.h>
+
+#define TCMTR_FORMAT_MASK	0xe0000000U
 
 static struct gen_pool *tcm_pool;
 static bool dtcm_present;
@@ -175,6 +178,77 @@ static int __init setup_tcm_bank(u8 type, u8 bank, u8 banks,
 	return 0;
 }
 
+/*
+ * When we are running in the non-secure world and the secure world
+ * has not explicitly given us access to the TCM we will get an
+ * undefined error when reading the TCM region register in the
+ * setup_tcm_bank function (above).
+ *
+ * There are two variants of this register read that we need to trap,
+ * the read for the data TCM and the read for the instruction TCM:
+ *  c0370628:       ee196f11        mrc     15, 0, r6, cr9, cr1, {0}
+ *  c0370674:       ee196f31        mrc     15, 0, r6, cr9, cr1, {1}
+ *
+ * Our undef hook mask explicitly matches all fields of the encoded
+ * instruction other than the destination register.  The mask also
+ * only allows operand 2 to have the values 0 or 1.
+ *
+ * The undefined hook is defined as __init and __initdata, and therefore
+ * must be removed before tcm_init returns.
+ *
+ * In this particular case (MRC with ARM condition code ALways) the
+ * Thumb-2 and ARM instruction encoding are identical, so this hook
+ * will work on a Thumb-2 kernel.
+ *
+ * See A8.8.107, DDI0406C_C ARM Architecture Reference Manual, Encoding
+ * T1/A1 for the bit-by-bit details.
+ *
+ *  mrc   p15, 0, XX, c9, c1, 0
+ *  mrc   p15, 0, XX, c9, c1, 1
+ *   |  |  |   |   |   |   |  +---- opc2           0|1 = 000|001
+ *   |  |  |   |   |   |   +------- CRm              0 = 0001
+ *   |  |  |   |   |   +----------- CRn              0 = 1001
+ *   |  |  |   |   +--------------- Rt               ? = ????
+ *   |  |  |   +------------------- opc1             0 =  000
+ *   |  |  +----------------------- coproc          15 = 1111
+ *   |  +-------------------------- condition   ALways = 1110
+ *   +----------------------------- instruction    MRC = 1110
+ *
+ * Encoding this as per A8.8.107 of DDI0406C, Encoding T1/A1, yields:
+ *  1111 1111 1111 1111 0000 1111 1101 1111 Required Mask
+ *  1110 1110 0001 1001 ???? 1111 0001 0001 mrc p15, 0, XX, c9, c1, 0
+ *  1110 1110 0001 1001 ???? 1111 0011 0001 mrc p15, 0, XX, c9, c1, 1
+ *  [  ] [  ] [ ]| [  ] [  ] [  ] [ ]| +--- CRm
+ *    |    |   | |   |    |    |   | +----- SBO
+ *    |    |   | |   |    |    |   +------- opc2
+ *    |    |   | |   |    |    +----------- coproc
+ *    |    |   | |   |    +---------------- Rt
+ *    |    |   | |   +--------------------- CRn
+ *    |    |   | +------------------------- SBO
+ *    |    |   +--------------------------- opc1
+ *    |    +------------------------------- instruction
+ *    +------------------------------------ condition
+ */
+#define TCM_REGION_READ_MASK		0xffff0fdf
+#define TCM_REGION_READ_INSTR		0xee190f11
+#define DEST_REG_SHIFT			12
+#define DEST_REG_MASK			0xf
+
+static int __init tcm_handler(struct pt_regs *regs, unsigned int instr)
+{
+	regs->uregs[(instr >> DEST_REG_SHIFT) & DEST_REG_MASK] = 0;
+	regs->ARM_pc += 4;
+	return 0;
+}
+
+static struct undef_hook tcm_hook __initdata = {
+	.instr_mask	= TCM_REGION_READ_MASK,
+	.instr_val	= TCM_REGION_READ_INSTR,
+	.cpsr_mask	= MODE_MASK,
+	.cpsr_val	= SVC_MODE,
+	.fn		= tcm_handler
+};
+
 /*
  * This initializes the TCM memory
  */
@@ -204,9 +278,18 @@ void __init tcm_init(void)
 	}
 
 	tcm_status = read_cpuid_tcmstatus();
+
+	/*
+	 * This code only supports v6-compatible TCMTR implementations.
+	 */
+	if (tcm_status & TCMTR_FORMAT_MASK)
+		return;
+
 	dtcm_banks = (tcm_status >> 16) & 0x03;
 	itcm_banks = (tcm_status & 0x03);
 
+	register_undef_hook(&tcm_hook);
+
 	/* Values greater than 2 for D/ITCM banks are "reserved" */
 	if (dtcm_banks > 2)
 		dtcm_banks = 0;
@@ -218,7 +301,7 @@ void __init tcm_init(void)
 		for (i = 0; i < dtcm_banks; i++) {
 			ret = setup_tcm_bank(0, i, dtcm_banks, &dtcm_end);
 			if (ret)
-				return;
+				goto unregister;
 		}
 		/* This means you compiled more code than fits into DTCM */
 		if (dtcm_code_sz > (dtcm_end - DTCM_OFFSET)) {
@@ -227,6 +310,12 @@ void __init tcm_init(void)
 				dtcm_code_sz, (dtcm_end - DTCM_OFFSET));
 			goto no_dtcm;
 		}
+		/*
+		 * This means that the DTCM sizes were 0 or the DTCM banks
+		 * were inaccessible due to TrustZone configuration.
+		 */
+		if (!(dtcm_end - DTCM_OFFSET))
+			goto no_dtcm;
 		dtcm_res.end = dtcm_end - 1;
 		request_resource(&iomem_resource, &dtcm_res);
 		dtcm_iomap[0].length = dtcm_end - DTCM_OFFSET;
@@ -250,15 +339,21 @@ no_dtcm:
 		for (i = 0; i < itcm_banks; i++) {
 			ret = setup_tcm_bank(1, i, itcm_banks, &itcm_end);
 			if (ret)
-				return;
+				goto unregister;
 		}
 		/* This means you compiled more code than fits into ITCM */
 		if (itcm_code_sz > (itcm_end - ITCM_OFFSET)) {
 			pr_info("CPU ITCM: %u bytes of code compiled to "
 				"ITCM but only %lu bytes of ITCM present\n",
 				itcm_code_sz, (itcm_end - ITCM_OFFSET));
-			return;
+			goto unregister;
 		}
+		/*
+		 * This means that the ITCM sizes were 0 or the ITCM banks
+		 * were inaccessible due to TrustZone configuration.
+		 */
+		if (!(itcm_end - ITCM_OFFSET))
+			goto unregister;
 		itcm_res.end = itcm_end - 1;
 		request_resource(&iomem_resource, &itcm_res);
 		itcm_iomap[0].length = itcm_end - ITCM_OFFSET;
@@ -275,6 +370,9 @@ no_dtcm:
 		pr_info("CPU ITCM: %u bytes of code compiled to ITCM but no "
 			"ITCM banks present in CPU\n", itcm_code_sz);
 	}
+
+unregister:
+	unregister_undef_hook(&tcm_hook);
 }
 
 /*
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 3dce1a342030..d358226236f2 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -749,14 +749,6 @@ late_initcall(arm_mrc_hook_init);
 
 #endif
 
-void __bad_xchg(volatile void *ptr, int size)
-{
-	pr_err("xchg: bad data size: pc 0x%p, ptr 0x%p, size %d\n",
-	       __builtin_return_address(0), ptr, size);
-	BUG();
-}
-EXPORT_SYMBOL(__bad_xchg);
-
 /*
  * A data abort trap was taken, but we did not handle the instruction.
  * Try to abort the user program, or panic if it was the kernel.
diff --git a/arch/arm/mach-davinci/da850.c b/arch/arm/mach-davinci/da850.c
index 45ce065e7170..3b8740c083c4 100644
--- a/arch/arm/mach-davinci/da850.c
+++ b/arch/arm/mach-davinci/da850.c
@@ -11,6 +11,7 @@
  * is licensed "as is" without any warranty of any kind, whether express
  * or implied.
  */
+#include <linux/clkdev.h>
 #include <linux/gpio.h>
 #include <linux/init.h>
 #include <linux/clk.h>
diff --git a/arch/arm/mach-integrator/integrator_ap.c b/arch/arm/mach-integrator/integrator_ap.c
index 30003ba447a5..5b0e363fe5ba 100644
--- a/arch/arm/mach-integrator/integrator_ap.c
+++ b/arch/arm/mach-integrator/integrator_ap.c
@@ -37,7 +37,6 @@
 #include <linux/stat.h>
 #include <linux/termios.h>
 
-#include <asm/hardware/arm_timer.h>
 #include <asm/setup.h>
 #include <asm/param.h>		/* HZ */
 #include <asm/mach-types.h>
diff --git a/arch/arm/mach-keystone/keystone.c b/arch/arm/mach-keystone/keystone.c
index 06620875813a..e288010522f9 100644
--- a/arch/arm/mach-keystone/keystone.c
+++ b/arch/arm/mach-keystone/keystone.c
@@ -27,7 +27,6 @@
 
 #include "keystone.h"
 
-static struct notifier_block platform_nb;
 static unsigned long keystone_dma_pfn_offset __read_mostly;
 
 static int keystone_platform_notifier(struct notifier_block *nb,
@@ -49,11 +48,18 @@ static int keystone_platform_notifier(struct notifier_block *nb,
 	return NOTIFY_OK;
 }
 
+static struct notifier_block platform_nb = {
+	.notifier_call = keystone_platform_notifier,
+};
+
 static void __init keystone_init(void)
 {
-	keystone_pm_runtime_init();
-	if (platform_nb.notifier_call)
+	if (PHYS_OFFSET >= KEYSTONE_HIGH_PHYS_START) {
+		keystone_dma_pfn_offset = PFN_DOWN(KEYSTONE_HIGH_PHYS_START -
+						   KEYSTONE_LOW_PHYS_START);
 		bus_register_notifier(&platform_bus_type, &platform_nb);
+	}
+	keystone_pm_runtime_init();
 	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 }
 
@@ -62,11 +68,9 @@ static phys_addr_t keystone_virt_to_idmap(unsigned long x)
 	return (phys_addr_t)(x) - CONFIG_PAGE_OFFSET + KEYSTONE_LOW_PHYS_START;
 }
 
-static void __init keystone_init_meminfo(void)
+static long long __init keystone_pv_fixup(void)
 {
-	bool lpae = IS_ENABLED(CONFIG_ARM_LPAE);
-	bool pvpatch = IS_ENABLED(CONFIG_ARM_PATCH_PHYS_VIRT);
-	phys_addr_t offset = PHYS_OFFSET - KEYSTONE_LOW_PHYS_START;
+	long long offset;
 	phys_addr_t mem_start, mem_end;
 
 	mem_start = memblock_start_of_DRAM();
@@ -75,32 +79,21 @@ static void __init keystone_init_meminfo(void)
 	/* nothing to do if we are running out of the <32-bit space */
 	if (mem_start >= KEYSTONE_LOW_PHYS_START &&
 	    mem_end   <= KEYSTONE_LOW_PHYS_END)
-		return;
-
-	if (!lpae || !pvpatch) {
-		pr_crit("Enable %s%s%s to run outside 32-bit space\n",
-		      !lpae ? __stringify(CONFIG_ARM_LPAE) : "",
-		      (!lpae && !pvpatch) ? " and " : "",
-		      !pvpatch ? __stringify(CONFIG_ARM_PATCH_PHYS_VIRT) : "");
-	}
+		return 0;
 
 	if (mem_start < KEYSTONE_HIGH_PHYS_START ||
 	    mem_end   > KEYSTONE_HIGH_PHYS_END) {
 		pr_crit("Invalid address space for memory (%08llx-%08llx)\n",
-		      (u64)mem_start, (u64)mem_end);
+		        (u64)mem_start, (u64)mem_end);
+		return 0;
 	}
 
-	offset += KEYSTONE_HIGH_PHYS_START;
-	__pv_phys_pfn_offset = PFN_DOWN(offset);
-	__pv_offset = (offset - PAGE_OFFSET);
+	offset = KEYSTONE_HIGH_PHYS_START - KEYSTONE_LOW_PHYS_START;
 
 	/* Populate the arch idmap hook */
 	arch_virt_to_idmap = keystone_virt_to_idmap;
-	platform_nb.notifier_call = keystone_platform_notifier;
-	keystone_dma_pfn_offset = PFN_DOWN(KEYSTONE_HIGH_PHYS_START -
-						KEYSTONE_LOW_PHYS_START);
 
-	pr_info("Switching to high address space at 0x%llx\n", (u64)offset);
+	return offset;
 }
 
 static const char *const keystone_match[] __initconst = {
@@ -115,5 +108,5 @@ DT_MACHINE_START(KEYSTONE, "Keystone")
 	.smp		= smp_ops(keystone_smp_ops),
 	.init_machine	= keystone_init,
 	.dt_compat	= keystone_match,
-	.init_meminfo   = keystone_init_meminfo,
+	.pv_fixup	= keystone_pv_fixup,
 MACHINE_END
diff --git a/arch/arm/mach-keystone/platsmp.c b/arch/arm/mach-keystone/platsmp.c
index 5f46a7cf907b..4bbb18463bfd 100644
--- a/arch/arm/mach-keystone/platsmp.c
+++ b/arch/arm/mach-keystone/platsmp.c
@@ -39,19 +39,6 @@ static int keystone_smp_boot_secondary(unsigned int cpu,
 	return error;
 }
 
-#ifdef CONFIG_ARM_LPAE
-static void __cpuinit keystone_smp_secondary_initmem(unsigned int cpu)
-{
-	pgd_t *pgd0 = pgd_offset_k(0);
-	cpu_set_ttbr(1, __pa(pgd0) + TTBR1_OFFSET);
-	local_flush_tlb_all();
-}
-#else
-static inline void __cpuinit keystone_smp_secondary_initmem(unsigned int cpu)
-{}
-#endif
-
 struct smp_operations keystone_smp_ops __initdata = {
 	.smp_boot_secondary	= keystone_smp_boot_secondary,
-	.smp_secondary_init     = keystone_smp_secondary_initmem,
 };
diff --git a/arch/arm/mach-lpc32xx/clock.c b/arch/arm/mach-lpc32xx/clock.c
index dd5d6f532e8c..661c8f4b2310 100644
--- a/arch/arm/mach-lpc32xx/clock.c
+++ b/arch/arm/mach-lpc32xx/clock.c
@@ -1238,10 +1238,7 @@ static struct clk_lookup lookups[] = {
 
 static int __init clk_init(void)
 {
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(lookups); i++)
-		clkdev_add(&lookups[i]);
+	clkdev_add_table(lookups, ARRAY_SIZE(lookups));
 
 	/*
 	 * Setup muxed SYSCLK for HCLK PLL base -this selects the
diff --git a/arch/arm/mach-nspire/nspire.c b/arch/arm/mach-nspire/nspire.c
index 3445a5686805..34c2a1b32e7d 100644
--- a/arch/arm/mach-nspire/nspire.c
+++ b/arch/arm/mach-nspire/nspire.c
@@ -22,8 +22,6 @@
 #include <asm/mach-types.h>
 #include <asm/mach/map.h>
 
-#include <asm/hardware/timer-sp.h>
-
 #include "mmio.h"
 #include "clcd.h"
 
diff --git a/arch/arm/mach-omap1/board-nokia770.c b/arch/arm/mach-omap1/board-nokia770.c
index 85089d821982..3bc59390a943 100644
--- a/arch/arm/mach-omap1/board-nokia770.c
+++ b/arch/arm/mach-omap1/board-nokia770.c
@@ -7,6 +7,7 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
+#include <linux/clkdev.h>
 #include <linux/irq.h>
 #include <linux/gpio.h>
 #include <linux/kernel.h>
@@ -14,7 +15,6 @@
 #include <linux/mutex.h>
 #include <linux/platform_device.h>
 #include <linux/input.h>
-#include <linux/clk.h>
 #include <linux/omapfb.h>
 
 #include <linux/spi/spi.h>
diff --git a/arch/arm/mach-omap2/clkt2xxx_virt_prcm_set.c b/arch/arm/mach-omap2/clkt2xxx_virt_prcm_set.c
index 85e0b0c06718..b64d717bfab6 100644
--- a/arch/arm/mach-omap2/clkt2xxx_virt_prcm_set.c
+++ b/arch/arm/mach-omap2/clkt2xxx_virt_prcm_set.c
@@ -232,14 +232,12 @@ void omap2xxx_clkt_vps_init(void)
 	struct clk_hw_omap *hw = NULL;
 	struct clk *clk;
 	const char *parent_name = "mpu_ck";
-	struct clk_lookup *lookup = NULL;
 
 	omap2xxx_clkt_vps_late_init();
 	omap2xxx_clkt_vps_check_bootloader_rates();
 
 	hw = kzalloc(sizeof(*hw), GFP_KERNEL);
-	lookup = kzalloc(sizeof(*lookup), GFP_KERNEL);
-	if (!hw || !lookup)
+	if (!hw)
 		goto cleanup;
 	init.name = "virt_prcm_set";
 	init.ops = &virt_prcm_set_ops;
@@ -249,15 +247,9 @@ void omap2xxx_clkt_vps_init(void)
 	hw->hw.init = &init;
 
 	clk = clk_register(NULL, &hw->hw);
-
-	lookup->dev_id = NULL;
-	lookup->con_id = "cpufreq_ck";
-	lookup->clk = clk;
-
-	clkdev_add(lookup);
+	clkdev_create(clk, "cpufreq_ck", NULL);
 	return;
 cleanup:
 	kfree(hw);
-	kfree(lookup);
 }
 #endif
diff --git a/arch/arm/mach-omap2/omap_device.c b/arch/arm/mach-omap2/omap_device.c
index 166b18f515a2..02da3655d288 100644
--- a/arch/arm/mach-omap2/omap_device.c
+++ b/arch/arm/mach-omap2/omap_device.c
@@ -47,7 +47,7 @@ static void _add_clkdev(struct omap_device *od, const char *clk_alias,
 		       const char *clk_name)
 {
 	struct clk *r;
-	struct clk_lookup *l;
+	int rc;
 
 	if (!clk_alias || !clk_name)
 		return;
@@ -62,21 +62,15 @@ static void _add_clkdev(struct omap_device *od, const char *clk_alias,
 		return;
 	}
 
-	r = clk_get(NULL, clk_name);
-	if (IS_ERR(r)) {
-		dev_err(&od->pdev->dev,
-			"clk_get for %s failed\n", clk_name);
-		return;
+	rc = clk_add_alias(clk_alias, dev_name(&od->pdev->dev), clk_name, NULL);
+	if (rc) {
+		if (rc == -ENODEV || rc == -ENOMEM)
+			dev_err(&od->pdev->dev,
+				"clkdev_alloc for %s failed\n", clk_alias);
+		else
+			dev_err(&od->pdev->dev,
+				"clk_get for %s failed\n", clk_name);
 	}
-
-	l = clkdev_alloc(r, clk_alias, dev_name(&od->pdev->dev));
-	if (!l) {
-		dev_err(&od->pdev->dev,
-			"clkdev_alloc for %s failed\n", clk_alias);
-		return;
-	}
-
-	clkdev_add(l);
 }
 
 /**
diff --git a/arch/arm/mach-pxa/eseries.c b/arch/arm/mach-pxa/eseries.c
index cfb864173ce3..4427bf26ea47 100644
--- a/arch/arm/mach-pxa/eseries.c
+++ b/arch/arm/mach-pxa/eseries.c
@@ -10,6 +10,7 @@
  *
  */
 
+#include <linux/clkdev.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/gpio.h>
diff --git a/arch/arm/mach-pxa/lubbock.c b/arch/arm/mach-pxa/lubbock.c
index d8a1be619f21..235f2d9318c1 100644
--- a/arch/arm/mach-pxa/lubbock.c
+++ b/arch/arm/mach-pxa/lubbock.c
@@ -11,6 +11,7 @@
  *  it under the terms of the GNU General Public License version 2 as
  *  published by the Free Software Foundation.
  */
+#include <linux/clkdev.h>
 #include <linux/gpio.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
diff --git a/arch/arm/mach-pxa/tosa.c b/arch/arm/mach-pxa/tosa.c
index 7780d1faa06f..92e56d8a24d8 100644
--- a/arch/arm/mach-pxa/tosa.c
+++ b/arch/arm/mach-pxa/tosa.c
@@ -12,6 +12,7 @@
  *
  */
 
+#include <linux/clkdev.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/platform_device.h>
diff --git a/arch/arm/mach-realview/core.c b/arch/arm/mach-realview/core.c
index c309593abdb2..44575edc44b1 100644
--- a/arch/arm/mach-realview/core.c
+++ b/arch/arm/mach-realview/core.c
@@ -35,20 +35,19 @@
 #include <linux/mtd/physmap.h>
 #include <linux/memblock.h>
 
+#include <clocksource/timer-sp804.h>
+
 #include <mach/hardware.h>
 #include <asm/irq.h>
 #include <asm/mach-types.h>
-#include <asm/hardware/arm_timer.h>
 #include <asm/hardware/icst.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/irq.h>
 #include <asm/mach/map.h>
 
-
 #include <mach/platform.h>
 #include <mach/irqs.h>
-#include <asm/hardware/timer-sp.h>
 
 #include <plat/sched_clock.h>
 
@@ -381,10 +380,10 @@ void __init realview_timer_init(unsigned int timer_irq)
 	/*
 	 * Initialise to a known state (all timers off)
 	 */
-	writel(0, timer0_va_base + TIMER_CTRL);
-	writel(0, timer1_va_base + TIMER_CTRL);
-	writel(0, timer2_va_base + TIMER_CTRL);
-	writel(0, timer3_va_base + TIMER_CTRL);
+	sp804_timer_disable(timer0_va_base);
+	sp804_timer_disable(timer1_va_base);
+	sp804_timer_disable(timer2_va_base);
+	sp804_timer_disable(timer3_va_base);
 
 	sp804_clocksource_init(timer3_va_base, "timer3");
 	sp804_clockevents_init(timer0_va_base, timer_irq, "timer0");
diff --git a/arch/arm/mach-sa1100/irq.c b/arch/arm/mach-sa1100/irq.c
index 65aebfa66fe5..ea3eb4144b66 100644
--- a/arch/arm/mach-sa1100/irq.c
+++ b/arch/arm/mach-sa1100/irq.c
@@ -73,7 +73,7 @@ static int sa1100_normal_irqdomain_map(struct irq_domain *d,
 	return 0;
 }
 
-static struct irq_domain_ops sa1100_normal_irqdomain_ops = {
+static const struct irq_domain_ops sa1100_normal_irqdomain_ops = {
 	.map = sa1100_normal_irqdomain_map,
 	.xlate = irq_domain_xlate_onetwocell,
 };
diff --git a/arch/arm/mach-versatile/core.c b/arch/arm/mach-versatile/core.c
index 6ea09fe53426..23a04fe5d2ad 100644
--- a/arch/arm/mach-versatile/core.c
+++ b/arch/arm/mach-versatile/core.c
@@ -41,8 +41,9 @@
 #include <linux/bitops.h>
 #include <linux/reboot.h>
 
+#include <clocksource/timer-sp804.h>
+
 #include <asm/irq.h>
-#include <asm/hardware/arm_timer.h>
 #include <asm/hardware/icst.h>
 #include <asm/mach-types.h>
 
@@ -52,7 +53,6 @@
 #include <asm/mach/map.h>
 #include <mach/hardware.h>
 #include <mach/platform.h>
-#include <asm/hardware/timer-sp.h>
 
 #include <plat/sched_clock.h>
 
@@ -798,10 +798,10 @@ void __init versatile_timer_init(void)
 	/*
 	 * Initialise to a known state (all timers off)
 	 */
-	writel(0, TIMER0_VA_BASE + TIMER_CTRL);
-	writel(0, TIMER1_VA_BASE + TIMER_CTRL);
-	writel(0, TIMER2_VA_BASE + TIMER_CTRL);
-	writel(0, TIMER3_VA_BASE + TIMER_CTRL);
+	sp804_timer_disable(TIMER0_VA_BASE);
+	sp804_timer_disable(TIMER1_VA_BASE);
+	sp804_timer_disable(TIMER2_VA_BASE);
+	sp804_timer_disable(TIMER3_VA_BASE);
 
 	sp804_clocksource_init(TIMER3_VA_BASE, "timer3");
 	sp804_clockevents_init(TIMER0_VA_BASE, IRQ_TIMERINT0_1, "timer0");
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 7188d6359797..7c6b976ab8d3 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -604,6 +604,22 @@ config CPU_USE_DOMAINS
 	  This option enables or disables the use of domain switching
 	  via the set_fs() function.
 
+config CPU_V7M_NUM_IRQ
+	int "Number of external interrupts connected to the NVIC"
+	depends on CPU_V7M
+	default 90 if ARCH_STM32
+	default 38 if ARCH_EFM32
+	default 112 if SOC_VF610
+	default 240
+	help
+	  This option indicates the number of interrupts connected to the NVIC.
+	  The value can be larger than the real number of interrupts supported
+	  by the system, but must not be lower.
+	  The default value is 240, corresponding to the maximum number of
+	  interrupts supported by the NVIC on Cortex-M family.
+
+	  If unsure, keep default value.
+
 #
 # CPU supports 36-bit I/O
 #
@@ -624,6 +640,10 @@ config ARM_LPAE
 
 	  If unsure, say N.
 
+config ARM_PV_FIXUP
+	def_bool y
+	depends on ARM_LPAE && ARM_PATCH_PHYS_VIRT && ARCH_KEYSTONE
+
 config ARCH_PHYS_ADDR_T_64BIT
 	def_bool ARM_LPAE
 
diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile
index 39a44bb84edf..57c8df500e8c 100644
--- a/arch/arm/mm/Makefile
+++ b/arch/arm/mm/Makefile
@@ -18,6 +18,7 @@ obj-$(CONFIG_MODULES)		+= proc-syms.o
 obj-$(CONFIG_ALIGNMENT_TRAP)	+= alignment.o
 obj-$(CONFIG_HIGHMEM)		+= highmem.o
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
+obj-$(CONFIG_ARM_PV_FIXUP)	+= pv-fixup-asm.o
 
 obj-$(CONFIG_CPU_ABRT_NOMMU)	+= abort-nommu.o
 obj-$(CONFIG_CPU_ABRT_EV4)	+= abort-ev4.o
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index e309c8f35af5..71b3d3309024 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -38,10 +38,11 @@ struct l2c_init_data {
 	unsigned way_size_0;
 	unsigned num_lock;
 	void (*of_parse)(const struct device_node *, u32 *, u32 *);
-	void (*enable)(void __iomem *, u32, unsigned);
+	void (*enable)(void __iomem *, unsigned);
 	void (*fixup)(void __iomem *, u32, struct outer_cache_fns *);
 	void (*save)(void __iomem *);
 	void (*configure)(void __iomem *);
+	void (*unlock)(void __iomem *, unsigned);
 	struct outer_cache_fns outer_cache;
 };
 
@@ -110,14 +111,6 @@ static inline void l2c_unlock(void __iomem *base, unsigned num)
 
 static void l2c_configure(void __iomem *base)
 {
-	if (outer_cache.configure) {
-		outer_cache.configure(&l2x0_saved_regs);
-		return;
-	}
-
-	if (l2x0_data->configure)
-		l2x0_data->configure(base);
-
 	l2c_write_sec(l2x0_saved_regs.aux_ctrl, base, L2X0_AUX_CTRL);
 }
 
@@ -125,18 +118,16 @@ static void l2c_configure(void __iomem *base)
  * Enable the L2 cache controller.  This function must only be
  * called when the cache controller is known to be disabled.
  */
-static void l2c_enable(void __iomem *base, u32 aux, unsigned num_lock)
+static void l2c_enable(void __iomem *base, unsigned num_lock)
 {
 	unsigned long flags;
 
-	/* Do not touch the controller if already enabled. */
-	if (readl_relaxed(base + L2X0_CTRL) & L2X0_CTRL_EN)
-		return;
+	if (outer_cache.configure)
+		outer_cache.configure(&l2x0_saved_regs);
+	else
+		l2x0_data->configure(base);
 
-	l2x0_saved_regs.aux_ctrl = aux;
-	l2c_configure(base);
-
-	l2c_unlock(base, num_lock);
+	l2x0_data->unlock(base, num_lock);
 
 	local_irq_save(flags);
 	__l2c_op_way(base + L2X0_INV_WAY);
@@ -163,7 +154,11 @@ static void l2c_save(void __iomem *base)
 
 static void l2c_resume(void)
 {
-	l2c_enable(l2x0_base, l2x0_saved_regs.aux_ctrl, l2x0_data->num_lock);
+	void __iomem *base = l2x0_base;
+
+	/* Do not touch the controller if already enabled. */
+	if (!(readl_relaxed(base + L2X0_CTRL) & L2X0_CTRL_EN))
+		l2c_enable(base, l2x0_data->num_lock);
 }
 
 /*
@@ -252,6 +247,8 @@ static const struct l2c_init_data l2c210_data __initconst = {
 	.num_lock = 1,
 	.enable = l2c_enable,
 	.save = l2c_save,
+	.configure = l2c_configure,
+	.unlock = l2c_unlock,
 	.outer_cache = {
 		.inv_range = l2c210_inv_range,
 		.clean_range = l2c210_clean_range,
@@ -391,16 +388,22 @@ static void l2c220_sync(void)
 	raw_spin_unlock_irqrestore(&l2x0_lock, flags);
 }
 
-static void l2c220_enable(void __iomem *base, u32 aux, unsigned num_lock)
+static void l2c220_enable(void __iomem *base, unsigned num_lock)
 {
 	/*
 	 * Always enable non-secure access to the lockdown registers -
 	 * we write to them as part of the L2C enable sequence so they
 	 * need to be accessible.
 	 */
-	aux |= L220_AUX_CTRL_NS_LOCKDOWN;
+	l2x0_saved_regs.aux_ctrl |= L220_AUX_CTRL_NS_LOCKDOWN;
 
-	l2c_enable(base, aux, num_lock);
+	l2c_enable(base, num_lock);
+}
+
+static void l2c220_unlock(void __iomem *base, unsigned num_lock)
+{
+	if (readl_relaxed(base + L2X0_AUX_CTRL) & L220_AUX_CTRL_NS_LOCKDOWN)
+		l2c_unlock(base, num_lock);
 }
 
 static const struct l2c_init_data l2c220_data = {
@@ -409,6 +412,8 @@ static const struct l2c_init_data l2c220_data = {
 	.num_lock = 1,
 	.enable = l2c220_enable,
 	.save = l2c_save,
+	.configure = l2c_configure,
+	.unlock = l2c220_unlock,
 	.outer_cache = {
 		.inv_range = l2c220_inv_range,
 		.clean_range = l2c220_clean_range,
@@ -569,6 +574,8 @@ static void l2c310_configure(void __iomem *base)
 {
 	unsigned revision;
 
+	l2c_configure(base);
+
 	/* restore pl310 setup */
 	l2c_write_sec(l2x0_saved_regs.tag_latency, base,
 		      L310_TAG_LATENCY_CTRL);
@@ -603,10 +610,11 @@ static int l2c310_cpu_enable_flz(struct notifier_block *nb, unsigned long act, v
 	return NOTIFY_OK;
 }
 
-static void __init l2c310_enable(void __iomem *base, u32 aux, unsigned num_lock)
+static void __init l2c310_enable(void __iomem *base, unsigned num_lock)
 {
 	unsigned rev = readl_relaxed(base + L2X0_CACHE_ID) & L2X0_CACHE_ID_RTL_MASK;
 	bool cortex_a9 = read_cpuid_part() == ARM_CPU_PART_CORTEX_A9;
+	u32 aux = l2x0_saved_regs.aux_ctrl;
 
 	if (rev >= L310_CACHE_ID_RTL_R2P0) {
 		if (cortex_a9) {
@@ -649,9 +657,9 @@ static void __init l2c310_enable(void __iomem *base, u32 aux, unsigned num_lock)
 	 * we write to them as part of the L2C enable sequence so they
 	 * need to be accessible.
 	 */
-	aux |= L310_AUX_CTRL_NS_LOCKDOWN;
+	l2x0_saved_regs.aux_ctrl = aux | L310_AUX_CTRL_NS_LOCKDOWN;
 
-	l2c_enable(base, aux, num_lock);
+	l2c_enable(base, num_lock);
 
 	/* Read back resulting AUX_CTRL value as it could have been altered. */
 	aux = readl_relaxed(base + L2X0_AUX_CTRL);
@@ -755,6 +763,12 @@ static void l2c310_resume(void)
 		set_auxcr(get_auxcr() | BIT(3) | BIT(2) | BIT(1));
 }
 
+static void l2c310_unlock(void __iomem *base, unsigned num_lock)
+{
+	if (readl_relaxed(base + L2X0_AUX_CTRL) & L310_AUX_CTRL_NS_LOCKDOWN)
+		l2c_unlock(base, num_lock);
+}
+
 static const struct l2c_init_data l2c310_init_fns __initconst = {
 	.type = "L2C-310",
 	.way_size_0 = SZ_8K,
@@ -763,6 +777,7 @@ static const struct l2c_init_data l2c310_init_fns __initconst = {
 	.fixup = l2c310_fixup,
 	.save = l2c310_save,
 	.configure = l2c310_configure,
+	.unlock = l2c310_unlock,
 	.outer_cache = {
 		.inv_range = l2c210_inv_range,
 		.clean_range = l2c210_clean_range,
@@ -856,8 +871,11 @@ static int __init __l2c_init(const struct l2c_init_data *data,
 	 * Check if l2x0 controller is already enabled.  If we are booting
 	 * in non-secure mode accessing the below registers will fault.
 	 */
-	if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN))
-		data->enable(l2x0_base, aux, data->num_lock);
+	if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN)) {
+		l2x0_saved_regs.aux_ctrl = aux;
+
+		data->enable(l2x0_base, data->num_lock);
+	}
 
 	outer_cache = fns;
 
@@ -1066,6 +1084,8 @@ static const struct l2c_init_data of_l2c210_data __initconst = {
 	.of_parse = l2x0_of_parse,
 	.enable = l2c_enable,
 	.save = l2c_save,
+	.configure = l2c_configure,
+	.unlock = l2c_unlock,
 	.outer_cache = {
 		.inv_range   = l2c210_inv_range,
 		.clean_range = l2c210_clean_range,
@@ -1084,6 +1104,8 @@ static const struct l2c_init_data of_l2c220_data __initconst = {
 	.of_parse = l2x0_of_parse,
 	.enable = l2c220_enable,
 	.save = l2c_save,
+	.configure = l2c_configure,
+	.unlock = l2c220_unlock,
 	.outer_cache = {
 		.inv_range   = l2c220_inv_range,
 		.clean_range = l2c220_clean_range,
@@ -1199,6 +1221,26 @@ static void __init l2c310_of_parse(const struct device_node *np,
 		pr_err("L2C-310 OF arm,prefetch-offset property value is missing\n");
 	}
 
+	ret = of_property_read_u32(np, "prefetch-data", &val);
+	if (ret == 0) {
+		if (val)
+			prefetch |= L310_PREFETCH_CTRL_DATA_PREFETCH;
+		else
+			prefetch &= ~L310_PREFETCH_CTRL_DATA_PREFETCH;
+	} else if (ret != -EINVAL) {
+		pr_err("L2C-310 OF prefetch-data property value is missing\n");
+	}
+
+	ret = of_property_read_u32(np, "prefetch-instr", &val);
+	if (ret == 0) {
+		if (val)
+			prefetch |= L310_PREFETCH_CTRL_INSTR_PREFETCH;
+		else
+			prefetch &= ~L310_PREFETCH_CTRL_INSTR_PREFETCH;
+	} else if (ret != -EINVAL) {
+		pr_err("L2C-310 OF prefetch-instr property value is missing\n");
+	}
+
 	l2x0_saved_regs.prefetch_ctrl = prefetch;
 }
 
@@ -1211,6 +1253,7 @@ static const struct l2c_init_data of_l2c310_data __initconst = {
 	.fixup = l2c310_fixup,
 	.save  = l2c310_save,
 	.configure = l2c310_configure,
+	.unlock = l2c310_unlock,
 	.outer_cache = {
 		.inv_range   = l2c210_inv_range,
 		.clean_range = l2c210_clean_range,
@@ -1240,6 +1283,7 @@ static const struct l2c_init_data of_l2c310_coherent_data __initconst = {
 	.fixup = l2c310_fixup,
 	.save  = l2c310_save,
 	.configure = l2c310_configure,
+	.unlock = l2c310_unlock,
 	.outer_cache = {
 		.inv_range   = l2c210_inv_range,
 		.clean_range = l2c210_clean_range,
@@ -1366,7 +1410,7 @@ static void aurora_save(void __iomem *base)
  * For Aurora cache in no outer mode, enable via the CP15 coprocessor
  * broadcasting of cache commands to L2.
  */
-static void __init aurora_enable_no_outer(void __iomem *base, u32 aux,
+static void __init aurora_enable_no_outer(void __iomem *base,
 	unsigned num_lock)
 {
 	u32 u;
@@ -1377,7 +1421,7 @@ static void __init aurora_enable_no_outer(void __iomem *base, u32 aux,
 
 	isb();
 
-	l2c_enable(base, aux, num_lock);
+	l2c_enable(base, num_lock);
 }
 
 static void __init aurora_fixup(void __iomem *base, u32 cache_id,
@@ -1416,6 +1460,8 @@ static const struct l2c_init_data of_aurora_with_outer_data __initconst = {
 	.enable = l2c_enable,
 	.fixup = aurora_fixup,
 	.save  = aurora_save,
+	.configure = l2c_configure,
+	.unlock = l2c_unlock,
 	.outer_cache = {
 		.inv_range   = aurora_inv_range,
 		.clean_range = aurora_clean_range,
@@ -1435,6 +1481,8 @@ static const struct l2c_init_data of_aurora_no_outer_data __initconst = {
 	.enable = aurora_enable_no_outer,
 	.fixup = aurora_fixup,
 	.save  = aurora_save,
+	.configure = l2c_configure,
+	.unlock = l2c_unlock,
 	.outer_cache = {
 		.resume      = l2c_resume,
 	},
@@ -1585,6 +1633,7 @@ static const struct l2c_init_data of_bcm_l2x0_data __initconst = {
 	.enable = l2c310_enable,
 	.save  = l2c310_save,
 	.configure = l2c310_configure,
+	.unlock = l2c310_unlock,
 	.outer_cache = {
 		.inv_range   = bcm_inv_range,
 		.clean_range = bcm_clean_range,
@@ -1608,6 +1657,7 @@ static void __init tauros3_save(void __iomem *base)
 
 static void tauros3_configure(void __iomem *base)
 {
+	l2c_configure(base);
 	writel_relaxed(l2x0_saved_regs.aux2_ctrl,
 		       base + TAUROS3_AUX2_CTRL);
 	writel_relaxed(l2x0_saved_regs.prefetch_ctrl,
@@ -1621,6 +1671,7 @@ static const struct l2c_init_data of_tauros3_data __initconst = {
 	.enable = l2c_enable,
 	.save  = tauros3_save,
 	.configure = tauros3_configure,
+	.unlock = l2c_unlock,
 	/* Tauros3 broadcasts L1 cache operations to L2 */
 	.outer_cache = {
 		.resume      = l2c_resume,
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 09c5fe3d30c2..1ced8a0f7a52 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -148,11 +148,14 @@ static void *arm_coherent_dma_alloc(struct device *dev, size_t size,
 	dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs);
 static void arm_coherent_dma_free(struct device *dev, size_t size, void *cpu_addr,
 				  dma_addr_t handle, struct dma_attrs *attrs);
+static int arm_coherent_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+		 void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		 struct dma_attrs *attrs);
 
 struct dma_map_ops arm_coherent_dma_ops = {
 	.alloc			= arm_coherent_dma_alloc,
 	.free			= arm_coherent_dma_free,
-	.mmap			= arm_dma_mmap,
+	.mmap			= arm_coherent_dma_mmap,
 	.get_sgtable		= arm_dma_get_sgtable,
 	.map_page		= arm_coherent_dma_map_page,
 	.map_sg			= arm_dma_map_sg,
@@ -690,10 +693,7 @@ static void *arm_coherent_dma_alloc(struct device *dev, size_t size,
 			   attrs, __builtin_return_address(0));
 }
 
-/*
- * Create userspace mapping for the DMA-coherent memory.
- */
-int arm_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+static int __arm_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 		 void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		 struct dma_attrs *attrs)
 {
@@ -704,8 +704,6 @@ int arm_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 	unsigned long pfn = dma_to_pfn(dev, dma_addr);
 	unsigned long off = vma->vm_pgoff;
 
-	vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot);
-
 	if (dma_mmap_from_coherent(dev, vma, cpu_addr, size, &ret))
 		return ret;
 
@@ -720,6 +718,26 @@ int arm_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 	return ret;
 }
 
+/*
+ * Create userspace mapping for the DMA-coherent memory.
+ */
+static int arm_coherent_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+		 void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		 struct dma_attrs *attrs)
+{
+	return __arm_dma_mmap(dev, vma, cpu_addr, dma_addr, size, attrs);
+}
+
+int arm_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+		 void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		 struct dma_attrs *attrs)
+{
+#ifdef CONFIG_MMU
+	vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot);
+#endif	/* CONFIG_MMU */
+	return __arm_dma_mmap(dev, vma, cpu_addr, dma_addr, size, attrs);
+}
+
 /*
  * Free a buffer as defined by the above mapping.
  */
@@ -1878,7 +1896,7 @@ 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)
+arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, u64 size)
 {
 	unsigned int bits = size >> PAGE_SHIFT;
 	unsigned int bitmap_size = BITS_TO_LONGS(bits) * sizeof(long);
@@ -1886,6 +1904,10 @@ arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, size_t size)
 	int extensions = 1;
 	int err = -ENOMEM;
 
+	/* currently only 32-bit DMA address space is supported */
+	if (size > DMA_BIT_MASK(32) + 1)
+		return ERR_PTR(-ERANGE);
+
 	if (!bitmap_size)
 		return ERR_PTR(-EINVAL);
 
@@ -2057,13 +2079,6 @@ static bool arm_setup_iommu_dma_ops(struct device *dev, u64 dma_base, u64 size,
 	if (!iommu)
 		return false;
 
-	/*
-	 * currently arm_iommu_create_mapping() takes a max of size_t
-	 * for size param. So check this limit for now.
-	 */
-	if (size > SIZE_MAX)
-		return false;
-
 	mapping = arm_iommu_create_mapping(dev->bus, dma_base, size);
 	if (IS_ERR(mapping)) {
 		pr_warn("Failed to create %llu-byte IOMMU mapping for device %s\n",
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 4e6ef896c619..6ca7d9aa896f 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -1112,22 +1112,22 @@ void __init sanity_check_meminfo(void)
 			}
 
 			/*
-			 * Find the first non-section-aligned page, and point
+			 * Find the first non-pmd-aligned page, and point
 			 * memblock_limit at it. This relies on rounding the
-			 * limit down to be section-aligned, which happens at
-			 * the end of this function.
+			 * limit down to be pmd-aligned, which happens at the
+			 * end of this function.
 			 *
 			 * With this algorithm, the start or end of almost any
-			 * bank can be non-section-aligned. The only exception
-			 * is that the start of the bank 0 must be section-
+			 * bank can be non-pmd-aligned. The only exception is
+			 * that the start of the bank 0 must be section-
 			 * aligned, since otherwise memory would need to be
 			 * allocated when mapping the start of bank 0, which
 			 * occurs before any free memory is mapped.
 			 */
 			if (!memblock_limit) {
-				if (!IS_ALIGNED(block_start, SECTION_SIZE))
+				if (!IS_ALIGNED(block_start, PMD_SIZE))
 					memblock_limit = block_start;
-				else if (!IS_ALIGNED(block_end, SECTION_SIZE))
+				else if (!IS_ALIGNED(block_end, PMD_SIZE))
 					memblock_limit = arm_lowmem_limit;
 			}
 
@@ -1137,12 +1137,12 @@ void __init sanity_check_meminfo(void)
 	high_memory = __va(arm_lowmem_limit - 1) + 1;
 
 	/*
-	 * Round the memblock limit down to a section size.  This
+	 * Round the memblock limit down to a pmd size.  This
 	 * helps to ensure that we will allocate memory from the
-	 * last full section, which should be mapped.
+	 * last full pmd, which should be mapped.
 	 */
 	if (memblock_limit)
-		memblock_limit = round_down(memblock_limit, SECTION_SIZE);
+		memblock_limit = round_down(memblock_limit, PMD_SIZE);
 	if (!memblock_limit)
 		memblock_limit = arm_lowmem_limit;
 
@@ -1387,123 +1387,98 @@ static void __init map_lowmem(void)
 	}
 }
 
-#ifdef CONFIG_ARM_LPAE
+#ifdef CONFIG_ARM_PV_FIXUP
+extern unsigned long __atags_pointer;
+typedef void pgtables_remap(long long offset, unsigned long pgd, void *bdata);
+pgtables_remap lpae_pgtables_remap_asm;
+
 /*
  * early_paging_init() recreates boot time page table setup, allowing machines
  * to switch over to a high (>4G) address space on LPAE systems
  */
-void __init early_paging_init(const struct machine_desc *mdesc,
-			      struct proc_info_list *procinfo)
+void __init early_paging_init(const struct machine_desc *mdesc)
 {
-	pmdval_t pmdprot = procinfo->__cpu_mm_mmu_flags;
-	unsigned long map_start, map_end;
-	pgd_t *pgd0, *pgdk;
-	pud_t *pud0, *pudk, *pud_start;
-	pmd_t *pmd0, *pmdk;
-	phys_addr_t phys;
-	int i;
+	pgtables_remap *lpae_pgtables_remap;
+	unsigned long pa_pgd;
+	unsigned int cr, ttbcr;
+	long long offset;
+	void *boot_data;
 
-	if (!(mdesc->init_meminfo))
+	if (!mdesc->pv_fixup)
 		return;
 
-	/* remap kernel code and data */
-	map_start = init_mm.start_code & PMD_MASK;
-	map_end   = ALIGN(init_mm.brk, PMD_SIZE);
+	offset = mdesc->pv_fixup();
+	if (offset == 0)
+		return;
 
-	/* get a handle on things... */
-	pgd0 = pgd_offset_k(0);
-	pud_start = pud0 = pud_offset(pgd0, 0);
-	pmd0 = pmd_offset(pud0, 0);
+	/*
+	 * Get the address of the remap function in the 1:1 identity
+	 * mapping setup by the early page table assembly code.  We
+	 * must get this prior to the pv update.  The following barrier
+	 * ensures that this is complete before we fixup any P:V offsets.
+	 */
+	lpae_pgtables_remap = (pgtables_remap *)(unsigned long)__pa(lpae_pgtables_remap_asm);
+	pa_pgd = __pa(swapper_pg_dir);
+	boot_data = __va(__atags_pointer);
+	barrier();
 
-	pgdk = pgd_offset_k(map_start);
-	pudk = pud_offset(pgdk, map_start);
-	pmdk = pmd_offset(pudk, map_start);
+	pr_info("Switching physical address space to 0x%08llx\n",
+		(u64)PHYS_OFFSET + offset);
 
-	mdesc->init_meminfo();
+	/* Re-set the phys pfn offset, and the pv offset */
+	__pv_offset += offset;
+	__pv_phys_pfn_offset += PFN_DOWN(offset);
 
 	/* Run the patch stub to update the constants */
 	fixup_pv_table(&__pv_table_begin,
 		(&__pv_table_end - &__pv_table_begin) << 2);
 
 	/*
-	 * Cache cleaning operations for self-modifying code
-	 * We should clean the entries by MVA but running a
-	 * for loop over every pv_table entry pointer would
-	 * just complicate the code.
-	 */
-	flush_cache_louis();
-	dsb(ishst);
-	isb();
-
-	/*
-	 * FIXME: This code is not architecturally compliant: we modify
-	 * the mappings in-place, indeed while they are in use by this
-	 * very same code.  This may lead to unpredictable behaviour of
-	 * the CPU.
-	 *
-	 * Even modifying the mappings in a separate page table does
-	 * not resolve this.
-	 *
-	 * The architecture strongly recommends that when a mapping is
-	 * changed, that it is changed by first going via an invalid
-	 * mapping and back to the new mapping.  This is to ensure that
-	 * no TLB conflicts (caused by the TLB having more than one TLB
-	 * entry match a translation) can occur.  However, doing that
-	 * here will result in unmapping the code we are running.
-	 */
-	pr_warn("WARNING: unsafe modification of in-place page tables - tainting kernel\n");
-	add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK);
-
-	/*
-	 * Remap level 1 table.  This changes the physical addresses
-	 * used to refer to the level 2 page tables to the high
-	 * physical address alias, leaving everything else the same.
-	 */
-	for (i = 0; i < PTRS_PER_PGD; pud0++, i++) {
-		set_pud(pud0,
-			__pud(__pa(pmd0) | PMD_TYPE_TABLE | L_PGD_SWAPPER));
-		pmd0 += PTRS_PER_PMD;
-	}
-
-	/*
-	 * Remap the level 2 table, pointing the mappings at the high
-	 * physical address alias of these pages.
-	 */
-	phys = __pa(map_start);
-	do {
-		*pmdk++ = __pmd(phys | pmdprot);
-		phys += PMD_SIZE;
-	} while (phys < map_end);
-
-	/*
-	 * Ensure that the above updates are flushed out of the cache.
-	 * This is not strictly correct; on a system where the caches
-	 * are coherent with each other, but the MMU page table walks
-	 * may not be coherent, flush_cache_all() may be a no-op, and
-	 * this will fail.
+	 * We changing not only the virtual to physical mapping, but also
+	 * the physical addresses used to access memory.  We need to flush
+	 * all levels of cache in the system with caching disabled to
+	 * ensure that all data is written back, and nothing is prefetched
+	 * into the caches.  We also need to prevent the TLB walkers
+	 * allocating into the caches too.  Note that this is ARMv7 LPAE
+	 * specific.
 	 */
+	cr = get_cr();
+	set_cr(cr & ~(CR_I | CR_C));
+	asm("mrc p15, 0, %0, c2, c0, 2" : "=r" (ttbcr));
+	asm volatile("mcr p15, 0, %0, c2, c0, 2"
+		: : "r" (ttbcr & ~(3 << 8 | 3 << 10)));
 	flush_cache_all();
 
 	/*
-	 * Re-write the TTBR values to point them at the high physical
-	 * alias of the page tables.  We expect __va() will work on
-	 * cpu_get_pgd(), which returns the value of TTBR0.
+	 * Fixup the page tables - this must be in the idmap region as
+	 * we need to disable the MMU to do this safely, and hence it
+	 * needs to be assembly.  It's fairly simple, as we're using the
+	 * temporary tables setup by the initial assembly code.
 	 */
-	cpu_switch_mm(pgd0, &init_mm);
-	cpu_set_ttbr(1, __pa(pgd0) + TTBR1_OFFSET);
+	lpae_pgtables_remap(offset, pa_pgd, boot_data);
 
-	/* Finally flush any stale TLB values. */
-	local_flush_bp_all();
-	local_flush_tlb_all();
+	/* Re-enable the caches and cacheable TLB walks */
+	asm volatile("mcr p15, 0, %0, c2, c0, 2" : : "r" (ttbcr));
+	set_cr(cr);
 }
 
 #else
 
-void __init early_paging_init(const struct machine_desc *mdesc,
-			      struct proc_info_list *procinfo)
+void __init early_paging_init(const struct machine_desc *mdesc)
 {
-	if (mdesc->init_meminfo)
-		mdesc->init_meminfo();
+	long long offset;
+
+	if (!mdesc->pv_fixup)
+		return;
+
+	offset = mdesc->pv_fixup();
+	if (offset == 0)
+		return;
+
+	pr_crit("Physical address space modification is only to support Keystone2.\n");
+	pr_crit("Please enable ARM_LPAE and ARM_PATCH_PHYS_VIRT support to use this\n");
+	pr_crit("feature. Your kernel may crash now, have a good day.\n");
+	add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK);
 }
 
 #endif
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index a014dfacd5ca..afd7e05d95f1 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -303,15 +303,6 @@ void __init sanity_check_meminfo(void)
 	memblock_set_current_limit(end);
 }
 
-/*
- * early_paging_init() recreates boot time page table setup, allowing machines
- * to switch over to a high (>4G) address space on LPAE systems
- */
-void __init early_paging_init(const struct machine_desc *mdesc,
-			      struct proc_info_list *procinfo)
-{
-}
-
 /*
  * paging_init() sets up the page tables, initialises the zone memory
  * maps, and sets up the zero page, bad page and bad page tables.
diff --git a/arch/arm/mm/proc-arm1020.S b/arch/arm/mm/proc-arm1020.S
index aa0519eed698..774ef1323554 100644
--- a/arch/arm/mm/proc-arm1020.S
+++ b/arch/arm/mm/proc-arm1020.S
@@ -22,8 +22,6 @@
  *
  * These are the low level assembler for performing cache and TLB
  * functions on the arm1020.
- *
- *  CONFIG_CPU_ARM1020_CPU_IDLE -> nohlt
  */
 #include <linux/linkage.h>
 #include <linux/init.h>
diff --git a/arch/arm/mm/proc-arm1020e.S b/arch/arm/mm/proc-arm1020e.S
index bff4c7f70fd6..ae3c27b71594 100644
--- a/arch/arm/mm/proc-arm1020e.S
+++ b/arch/arm/mm/proc-arm1020e.S
@@ -22,8 +22,6 @@
  *
  * These are the low level assembler for performing cache and TLB
  * functions on the arm1020e.
- *
- *  CONFIG_CPU_ARM1020_CPU_IDLE -> nohlt
  */
 #include <linux/linkage.h>
 #include <linux/init.h>
diff --git a/arch/arm/mm/proc-arm925.S b/arch/arm/mm/proc-arm925.S
index ede8c54ab4aa..32a47cc19076 100644
--- a/arch/arm/mm/proc-arm925.S
+++ b/arch/arm/mm/proc-arm925.S
@@ -441,9 +441,6 @@ ENTRY(cpu_arm925_set_pte_ext)
 	.type	__arm925_setup, #function
 __arm925_setup:
 	mov	r0, #0
-#if defined(CONFIG_CPU_ICACHE_STREAMING_DISABLE)
-        orr     r0,r0,#1 << 7
-#endif
 
 	/* Transparent on, D-cache clean & flush mode. See  NOTE2 above */
         orr     r0,r0,#1 << 1			@ transparent mode on
diff --git a/arch/arm/mm/proc-feroceon.S b/arch/arm/mm/proc-feroceon.S
index e494d6d6acbe..92e08bf37aad 100644
--- a/arch/arm/mm/proc-feroceon.S
+++ b/arch/arm/mm/proc-feroceon.S
@@ -602,7 +602,6 @@ __\name\()_proc_info:
 		PMD_SECT_AP_WRITE | \
 		PMD_SECT_AP_READ
 	initfn	__feroceon_setup, __\name\()_proc_info
-	.long __feroceon_setup
 	.long	cpu_arch_name
 	.long	cpu_elf_name
 	.long	HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP
diff --git a/arch/arm/mm/proc-v7-2level.S b/arch/arm/mm/proc-v7-2level.S
index 10405b8d31af..c6141a5435c3 100644
--- a/arch/arm/mm/proc-v7-2level.S
+++ b/arch/arm/mm/proc-v7-2level.S
@@ -36,14 +36,16 @@
  *
  *	It is assumed that:
  *	- we are not using split page tables
+ *
+ *	Note that we always need to flush BTAC/BTB if IBE is set
+ *	even on Cortex-A8 revisions not affected by 430973.
+ *	If IBE is not set, the flush BTAC/BTB won't do anything.
  */
 ENTRY(cpu_ca8_switch_mm)
 #ifdef CONFIG_MMU
 	mov	r2, #0
-#ifdef CONFIG_ARM_ERRATA_430973
 	mcr	p15, 0, r2, c7, c5, 6		@ flush BTAC/BTB
 #endif
-#endif
 ENTRY(cpu_v7_switch_mm)
 #ifdef CONFIG_MMU
 	mmid	r1, r1				@ get mm->context.id
@@ -148,10 +150,10 @@ ENDPROC(cpu_v7_set_pte_ext)
 	 * Macro for setting up the TTBRx and TTBCR registers.
 	 * - \ttb0 and \ttb1 updated with the corresponding flags.
 	 */
-	.macro	v7_ttb_setup, zero, ttbr0, ttbr1, tmp
+	.macro	v7_ttb_setup, zero, ttbr0l, ttbr0h, ttbr1, tmp
 	mcr	p15, 0, \zero, c2, c0, 2	@ TTB control register
-	ALT_SMP(orr	\ttbr0, \ttbr0, #TTB_FLAGS_SMP)
-	ALT_UP(orr	\ttbr0, \ttbr0, #TTB_FLAGS_UP)
+	ALT_SMP(orr	\ttbr0l, \ttbr0l, #TTB_FLAGS_SMP)
+	ALT_UP(orr	\ttbr0l, \ttbr0l, #TTB_FLAGS_UP)
 	ALT_SMP(orr	\ttbr1, \ttbr1, #TTB_FLAGS_SMP)
 	ALT_UP(orr	\ttbr1, \ttbr1, #TTB_FLAGS_UP)
 	mcr	p15, 0, \ttbr1, c2, c0, 1	@ load TTB1
diff --git a/arch/arm/mm/proc-v7-3level.S b/arch/arm/mm/proc-v7-3level.S
index d3daed0ae0ad..5e5720e8bc5f 100644
--- a/arch/arm/mm/proc-v7-3level.S
+++ b/arch/arm/mm/proc-v7-3level.S
@@ -126,11 +126,10 @@ ENDPROC(cpu_v7_set_pte_ext)
 	 * Macro for setting up the TTBRx and TTBCR registers.
 	 * - \ttbr1 updated.
 	 */
-	.macro	v7_ttb_setup, zero, ttbr0, ttbr1, tmp
+	.macro	v7_ttb_setup, zero, ttbr0l, ttbr0h, ttbr1, tmp
 	ldr	\tmp, =swapper_pg_dir		@ swapper_pg_dir virtual address
-	mov	\tmp, \tmp, lsr #ARCH_PGD_SHIFT
-	cmp	\ttbr1, \tmp			@ PHYS_OFFSET > PAGE_OFFSET?
-	mrc	p15, 0, \tmp, c2, c0, 2		@ TTB control register
+	cmp	\ttbr1, \tmp, lsr #12		@ PHYS_OFFSET > PAGE_OFFSET?
+	mrc	p15, 0, \tmp, c2, c0, 2		@ TTB control egister
 	orr	\tmp, \tmp, #TTB_EAE
 	ALT_SMP(orr	\tmp, \tmp, #TTB_FLAGS_SMP)
 	ALT_UP(orr	\tmp, \tmp, #TTB_FLAGS_UP)
@@ -143,13 +142,10 @@ ENDPROC(cpu_v7_set_pte_ext)
 	 */
 	orrls	\tmp, \tmp, #TTBR1_SIZE				@ TTBCR.T1SZ
 	mcr	p15, 0, \tmp, c2, c0, 2				@ TTBCR
-	mov	\tmp, \ttbr1, lsr #(32 - ARCH_PGD_SHIFT)	@ upper bits
-	mov	\ttbr1, \ttbr1, lsl #ARCH_PGD_SHIFT		@ lower bits
+	mov	\tmp, \ttbr1, lsr #20
+	mov	\ttbr1, \ttbr1, lsl #12
 	addls	\ttbr1, \ttbr1, #TTBR1_OFFSET
 	mcrr	p15, 1, \ttbr1, \tmp, c2			@ load TTBR1
-	mov	\tmp, \ttbr0, lsr #(32 - ARCH_PGD_SHIFT)	@ upper bits
-	mov	\ttbr0, \ttbr0, lsl #ARCH_PGD_SHIFT		@ lower bits
-	mcrr	p15, 0, \ttbr0, \tmp, c2			@ load TTBR0
 	.endm
 
 	/*
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 3d1054f11a8a..003190ae9cd8 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -252,6 +252,12 @@ ENDPROC(cpu_pj4b_do_resume)
  *	Initialise TLB, Caches, and MMU state ready to switch the MMU
  *	on.  Return in r0 the new CP15 C1 control register setting.
  *
+ *	r1, r2, r4, r5, r9, r13 must be preserved - r13 is not a stack
+ *	r4: TTBR0 (low word)
+ *	r5: TTBR0 (high word if LPAE)
+ *	r8: TTBR1
+ *	r9: Main ID register
+ *
  *	This should be able to cover all ARMv7 cores.
  *
  *	It is assumed that:
@@ -279,6 +285,78 @@ __v7_ca17mp_setup:
 #endif
 	b	__v7_setup
 
+/*
+ * Errata:
+ *  r0, r10 available for use
+ *  r1, r2, r4, r5, r9, r13: must be preserved
+ *  r3: contains MIDR rX number in bits 23-20
+ *  r6: contains MIDR rXpY as 8-bit XY number
+ *  r9: MIDR
+ */
+__ca8_errata:
+#if defined(CONFIG_ARM_ERRATA_430973) && !defined(CONFIG_ARCH_MULTIPLATFORM)
+	teq	r3, #0x00100000			@ only present in r1p*
+	mrceq	p15, 0, r0, c1, c0, 1		@ read aux control register
+	orreq	r0, r0, #(1 << 6)		@ set IBE to 1
+	mcreq	p15, 0, r0, c1, c0, 1		@ write aux control register
+#endif
+#ifdef CONFIG_ARM_ERRATA_458693
+	teq	r6, #0x20			@ only present in r2p0
+	mrceq	p15, 0, r0, c1, c0, 1		@ read aux control register
+	orreq	r0, r0, #(1 << 5)		@ set L1NEON to 1
+	orreq	r0, r0, #(1 << 9)		@ set PLDNOP to 1
+	mcreq	p15, 0, r0, c1, c0, 1		@ write aux control register
+#endif
+#ifdef CONFIG_ARM_ERRATA_460075
+	teq	r6, #0x20			@ only present in r2p0
+	mrceq	p15, 1, r0, c9, c0, 2		@ read L2 cache aux ctrl register
+	tsteq	r0, #1 << 22
+	orreq	r0, r0, #(1 << 22)		@ set the Write Allocate disable bit
+	mcreq	p15, 1, r0, c9, c0, 2		@ write the L2 cache aux ctrl register
+#endif
+	b	__errata_finish
+
+__ca9_errata:
+#ifdef CONFIG_ARM_ERRATA_742230
+	cmp	r6, #0x22			@ only present up to r2p2
+	mrcle	p15, 0, r0, c15, c0, 1		@ read diagnostic register
+	orrle	r0, r0, #1 << 4			@ set bit #4
+	mcrle	p15, 0, r0, c15, c0, 1		@ write diagnostic register
+#endif
+#ifdef CONFIG_ARM_ERRATA_742231
+	teq	r6, #0x20			@ present in r2p0
+	teqne	r6, #0x21			@ present in r2p1
+	teqne	r6, #0x22			@ present in r2p2
+	mrceq	p15, 0, r0, c15, c0, 1		@ read diagnostic register
+	orreq	r0, r0, #1 << 12		@ set bit #12
+	orreq	r0, r0, #1 << 22		@ set bit #22
+	mcreq	p15, 0, r0, c15, c0, 1		@ write diagnostic register
+#endif
+#ifdef CONFIG_ARM_ERRATA_743622
+	teq	r3, #0x00200000			@ only present in r2p*
+	mrceq	p15, 0, r0, c15, c0, 1		@ read diagnostic register
+	orreq	r0, r0, #1 << 6			@ set bit #6
+	mcreq	p15, 0, r0, c15, c0, 1		@ write diagnostic register
+#endif
+#if defined(CONFIG_ARM_ERRATA_751472) && defined(CONFIG_SMP)
+	ALT_SMP(cmp r6, #0x30)			@ present prior to r3p0
+	ALT_UP_B(1f)
+	mrclt	p15, 0, r0, c15, c0, 1		@ read diagnostic register
+	orrlt	r0, r0, #1 << 11		@ set bit #11
+	mcrlt	p15, 0, r0, c15, c0, 1		@ write diagnostic register
+1:
+#endif
+	b	__errata_finish
+
+__ca15_errata:
+#ifdef CONFIG_ARM_ERRATA_773022
+	cmp	r6, #0x4			@ only present up to r0p4
+	mrcle	p15, 0, r0, c1, c0, 1		@ read aux control register
+	orrle	r0, r0, #1 << 1			@ disable loop buffer
+	mcrle	p15, 0, r0, c1, c0, 1		@ write aux control register
+#endif
+	b	__errata_finish
+
 __v7_pj4b_setup:
 #ifdef CONFIG_CPU_PJ4B
 
@@ -339,96 +417,38 @@ __v7_setup:
 	bl      v7_flush_dcache_louis
 	ldmia	r12, {r0-r5, r7, r9, r11, lr}
 
-	mrc	p15, 0, r0, c0, c0, 0		@ read main ID register
-	and	r10, r0, #0xff000000		@ ARM?
-	teq	r10, #0x41000000
-	bne	3f
-	and	r5, r0, #0x00f00000		@ variant
-	and	r6, r0, #0x0000000f		@ revision
-	orr	r6, r6, r5, lsr #20-4		@ combine variant and revision
-	ubfx	r0, r0, #4, #12			@ primary part number
+	and	r0, r9, #0xff000000		@ ARM?
+	teq	r0, #0x41000000
+	bne	__errata_finish
+	and	r3, r9, #0x00f00000		@ variant
+	and	r6, r9, #0x0000000f		@ revision
+	orr	r6, r6, r3, lsr #20-4		@ combine variant and revision
+	ubfx	r0, r9, #4, #12			@ primary part number
 
 	/* Cortex-A8 Errata */
 	ldr	r10, =0x00000c08		@ Cortex-A8 primary part number
 	teq	r0, r10
-	bne	2f
-#if defined(CONFIG_ARM_ERRATA_430973) && !defined(CONFIG_ARCH_MULTIPLATFORM)
-
-	teq	r5, #0x00100000			@ only present in r1p*
-	mrceq	p15, 0, r10, c1, c0, 1		@ read aux control register
-	orreq	r10, r10, #(1 << 6)		@ set IBE to 1
-	mcreq	p15, 0, r10, c1, c0, 1		@ write aux control register
-#endif
-#ifdef CONFIG_ARM_ERRATA_458693
-	teq	r6, #0x20			@ only present in r2p0
-	mrceq	p15, 0, r10, c1, c0, 1		@ read aux control register
-	orreq	r10, r10, #(1 << 5)		@ set L1NEON to 1
-	orreq	r10, r10, #(1 << 9)		@ set PLDNOP to 1
-	mcreq	p15, 0, r10, c1, c0, 1		@ write aux control register
-#endif
-#ifdef CONFIG_ARM_ERRATA_460075
-	teq	r6, #0x20			@ only present in r2p0
-	mrceq	p15, 1, r10, c9, c0, 2		@ read L2 cache aux ctrl register
-	tsteq	r10, #1 << 22
-	orreq	r10, r10, #(1 << 22)		@ set the Write Allocate disable bit
-	mcreq	p15, 1, r10, c9, c0, 2		@ write the L2 cache aux ctrl register
-#endif
-	b	3f
+	beq	__ca8_errata
 
 	/* Cortex-A9 Errata */
-2:	ldr	r10, =0x00000c09		@ Cortex-A9 primary part number
+	ldr	r10, =0x00000c09		@ Cortex-A9 primary part number
 	teq	r0, r10
-	bne	3f
-#ifdef CONFIG_ARM_ERRATA_742230
-	cmp	r6, #0x22			@ only present up to r2p2
-	mrcle	p15, 0, r10, c15, c0, 1		@ read diagnostic register
-	orrle	r10, r10, #1 << 4		@ set bit #4
-	mcrle	p15, 0, r10, c15, c0, 1		@ write diagnostic register
-#endif
-#ifdef CONFIG_ARM_ERRATA_742231
-	teq	r6, #0x20			@ present in r2p0
-	teqne	r6, #0x21			@ present in r2p1
-	teqne	r6, #0x22			@ present in r2p2
-	mrceq	p15, 0, r10, c15, c0, 1		@ read diagnostic register
-	orreq	r10, r10, #1 << 12		@ set bit #12
-	orreq	r10, r10, #1 << 22		@ set bit #22
-	mcreq	p15, 0, r10, c15, c0, 1		@ write diagnostic register
-#endif
-#ifdef CONFIG_ARM_ERRATA_743622
-	teq	r5, #0x00200000			@ only present in r2p*
-	mrceq	p15, 0, r10, c15, c0, 1		@ read diagnostic register
-	orreq	r10, r10, #1 << 6		@ set bit #6
-	mcreq	p15, 0, r10, c15, c0, 1		@ write diagnostic register
-#endif
-#if defined(CONFIG_ARM_ERRATA_751472) && defined(CONFIG_SMP)
-	ALT_SMP(cmp r6, #0x30)			@ present prior to r3p0
-	ALT_UP_B(1f)
-	mrclt	p15, 0, r10, c15, c0, 1		@ read diagnostic register
-	orrlt	r10, r10, #1 << 11		@ set bit #11
-	mcrlt	p15, 0, r10, c15, c0, 1		@ write diagnostic register
-1:
-#endif
+	beq	__ca9_errata
 
 	/* Cortex-A15 Errata */
-3:	ldr	r10, =0x00000c0f		@ Cortex-A15 primary part number
+	ldr	r10, =0x00000c0f		@ Cortex-A15 primary part number
 	teq	r0, r10
-	bne	4f
+	beq	__ca15_errata
 
-#ifdef CONFIG_ARM_ERRATA_773022
-	cmp	r6, #0x4			@ only present up to r0p4
-	mrcle	p15, 0, r10, c1, c0, 1		@ read aux control register
-	orrle	r10, r10, #1 << 1		@ disable loop buffer
-	mcrle	p15, 0, r10, c1, c0, 1		@ write aux control register
-#endif
-
-4:	mov	r10, #0
+__errata_finish:
+	mov	r10, #0
 	mcr	p15, 0, r10, c7, c5, 0		@ I+BTB cache invalidate
 #ifdef CONFIG_MMU
 	mcr	p15, 0, r10, c8, c7, 0		@ invalidate I + D TLBs
-	v7_ttb_setup r10, r4, r8, r5		@ TTBCR, TTBRx setup
-	ldr	r5, =PRRR			@ PRRR
+	v7_ttb_setup r10, r4, r5, r8, r3	@ TTBCR, TTBRx setup
+	ldr	r3, =PRRR			@ PRRR
 	ldr	r6, =NMRR			@ NMRR
-	mcr	p15, 0, r5, c10, c2, 0		@ write PRRR
+	mcr	p15, 0, r3, c10, c2, 0		@ write PRRR
 	mcr	p15, 0, r6, c10, c2, 1		@ write NMRR
 #endif
 	dsb					@ Complete invalidations
@@ -437,22 +457,22 @@ __v7_setup:
 	and	r0, r0, #(0xf << 12)		@ ThumbEE enabled field
 	teq	r0, #(1 << 12)			@ check if ThumbEE is present
 	bne	1f
-	mov	r5, #0
-	mcr	p14, 6, r5, c1, c0, 0		@ Initialize TEEHBR to 0
+	mov	r3, #0
+	mcr	p14, 6, r3, c1, c0, 0		@ Initialize TEEHBR to 0
 	mrc	p14, 6, r0, c0, c0, 0		@ load TEECR
 	orr	r0, r0, #1			@ set the 1st bit in order to
 	mcr	p14, 6, r0, c0, c0, 0		@ stop userspace TEEHBR access
 1:
 #endif
-	adr	r5, v7_crval
-	ldmia	r5, {r5, r6}
+	adr	r3, v7_crval
+	ldmia	r3, {r3, r6}
  ARM_BE8(orr	r6, r6, #1 << 25)		@ big-endian page tables
 #ifdef CONFIG_SWP_EMULATE
-	orr     r5, r5, #(1 << 10)              @ set SW bit in "clear"
+	orr     r3, r3, #(1 << 10)              @ set SW bit in "clear"
 	bic     r6, r6, #(1 << 10)              @ clear it in "mmuset"
 #endif
    	mrc	p15, 0, r0, c1, c0, 0		@ read control register
-	bic	r0, r0, r5			@ clear bits them
+	bic	r0, r0, r3			@ clear bits them
 	orr	r0, r0, r6			@ set them
  THUMB(	orr	r0, r0, #1 << 30	)	@ Thumb exceptions
 	ret	lr				@ return to head.S:__ret
diff --git a/arch/arm/mm/pv-fixup-asm.S b/arch/arm/mm/pv-fixup-asm.S
new file mode 100644
index 000000000000..1867f3e43016
--- /dev/null
+++ b/arch/arm/mm/pv-fixup-asm.S
@@ -0,0 +1,88 @@
+/*
+ *  Copyright (C) 2015 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This assembly is required to safely remap the physical address space
+ * for Keystone 2
+ */
+#include <linux/linkage.h>
+#include <asm/asm-offsets.h>
+#include <asm/cp15.h>
+#include <asm/memory.h>
+#include <asm/pgtable.h>
+
+	.section ".idmap.text", "ax"
+
+#define L1_ORDER 3
+#define L2_ORDER 3
+
+ENTRY(lpae_pgtables_remap_asm)
+	stmfd	sp!, {r4-r8, lr}
+
+	mrc	p15, 0, r8, c1, c0, 0		@ read control reg
+	bic	ip, r8, #CR_M			@ disable caches and MMU
+	mcr	p15, 0, ip, c1, c0, 0
+	dsb
+	isb
+
+	/* Update level 2 entries covering the kernel */
+	ldr	r6, =(_end - 1)
+	add	r7, r2, #0x1000
+	add	r6, r7, r6, lsr #SECTION_SHIFT - L2_ORDER
+	add	r7, r7, #PAGE_OFFSET >> (SECTION_SHIFT - L2_ORDER)
+1:	ldrd	r4, [r7]
+	adds	r4, r4, r0
+	adc	r5, r5, r1
+	strd	r4, [r7], #1 << L2_ORDER
+	cmp	r7, r6
+	bls	1b
+
+	/* Update level 2 entries for the boot data */
+	add	r7, r2, #0x1000
+	add	r7, r7, r3, lsr #SECTION_SHIFT - L2_ORDER
+	bic	r7, r7, #(1 << L2_ORDER) - 1
+	ldrd	r4, [r7]
+	adds	r4, r4, r0
+	adc	r5, r5, r1
+	strd	r4, [r7], #1 << L2_ORDER
+	ldrd	r4, [r7]
+	adds	r4, r4, r0
+	adc	r5, r5, r1
+	strd	r4, [r7]
+
+	/* Update level 1 entries */
+	mov	r6, #4
+	mov	r7, r2
+2:	ldrd	r4, [r7]
+	adds	r4, r4, r0
+	adc	r5, r5, r1
+	strd	r4, [r7], #1 << L1_ORDER
+	subs	r6, r6, #1
+	bne	2b
+
+	mrrc	p15, 0, r4, r5, c2		@ read TTBR0
+	adds	r4, r4, r0			@ update physical address
+	adc	r5, r5, r1
+	mcrr	p15, 0, r4, r5, c2		@ write back TTBR0
+	mrrc	p15, 1, r4, r5, c2		@ read TTBR1
+	adds	r4, r4, r0			@ update physical address
+	adc	r5, r5, r1
+	mcrr	p15, 1, r4, r5, c2		@ write back TTBR1
+
+	dsb
+
+	mov	ip, #0
+	mcr	p15, 0, ip, c7, c5, 0		@ I+BTB cache invalidate
+	mcr	p15, 0, ip, c8, c7, 0		@ local_flush_tlb_all()
+	dsb
+	isb
+
+	mcr	p15, 0, r8, c1, c0, 0		@ re-enable MMU
+	dsb
+	isb
+
+	ldmfd	sp!, {r4-r8, pc}
+ENDPROC(lpae_pgtables_remap_asm)
diff --git a/arch/arm/plat-orion/common.c b/arch/arm/plat-orion/common.c
index f5b00f41c4f6..2235081a04ee 100644
--- a/arch/arm/plat-orion/common.c
+++ b/arch/arm/plat-orion/common.c
@@ -28,11 +28,7 @@
 void __init orion_clkdev_add(const char *con_id, const char *dev_id,
 			     struct clk *clk)
 {
-	struct clk_lookup *cl;
-
-	cl = clkdev_alloc(clk, con_id, dev_id);
-	if (cl)
-		clkdev_add(cl);
+	clkdev_create(clk, con_id, "%s", dev_id);
 }
 
 /* Create clkdev entries for all orion platforms except kirkwood.
diff --git a/arch/arm/vdso/Makefile b/arch/arm/vdso/Makefile
index 8aa791051029..9d259d94e429 100644
--- a/arch/arm/vdso/Makefile
+++ b/arch/arm/vdso/Makefile
@@ -6,9 +6,15 @@ obj-vdso := vgettimeofday.o datapage.o
 targets := $(obj-vdso) vdso.so vdso.so.dbg vdso.so.raw vdso.lds
 obj-vdso := $(addprefix $(obj)/, $(obj-vdso))
 
-ccflags-y := -shared -fPIC -fno-common -fno-builtin -fno-stack-protector
-ccflags-y += -nostdlib -Wl,-soname=linux-vdso.so.1 -DDISABLE_BRANCH_PROFILING
-ccflags-y += -Wl,--no-undefined $(call cc-ldoption, -Wl$(comma)--hash-style=sysv)
+ccflags-y := -fPIC -fno-common -fno-builtin -fno-stack-protector
+ccflags-y += -DDISABLE_BRANCH_PROFILING
+
+VDSO_LDFLAGS := -Wl,-Bsymbolic -Wl,--no-undefined -Wl,-soname=linux-vdso.so.1
+VDSO_LDFLAGS += -Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096
+VDSO_LDFLAGS += -nostdlib -shared
+VDSO_LDFLAGS += $(call cc-ldoption, -Wl$(comma)--hash-style=sysv)
+VDSO_LDFLAGS += $(call cc-ldoption, -Wl$(comma)--build-id)
+VDSO_LDFLAGS += $(call cc-option, -fuse-ld=bfd)
 
 obj-$(CONFIG_VDSO) += vdso.o
 extra-$(CONFIG_VDSO) += vdso.lds
@@ -40,10 +46,8 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE
 
 # Actual build commands
 quiet_cmd_vdsold = VDSO    $@
-      cmd_vdsold = $(CC) $(c_flags) -Wl,-T $(filter %.lds,$^) $(filter %.o,$^) \
-                   $(call cc-ldoption, -Wl$(comma)--build-id) \
-                   -Wl,-Bsymbolic -Wl,-z,max-page-size=4096 \
-                   -Wl,-z,common-page-size=4096 -o $@
+      cmd_vdsold = $(CC) $(c_flags) $(VDSO_LDFLAGS) \
+                   -Wl,-T $(filter %.lds,$^) $(filter %.o,$^) -o $@
 
 quiet_cmd_vdsomunge = MUNGE   $@
       cmd_vdsomunge = $(objtree)/$(obj)/vdsomunge $< $@
diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7734.c b/arch/sh/kernel/cpu/sh4a/clock-sh7734.c
index 1fdf1ee672de..7f54bf2f453d 100644
--- a/arch/sh/kernel/cpu/sh4a/clock-sh7734.c
+++ b/arch/sh/kernel/cpu/sh4a/clock-sh7734.c
@@ -246,8 +246,7 @@ int __init arch_clk_init(void)
 	for (i = 0; i < ARRAY_SIZE(main_clks); i++)
 		ret |= clk_register(main_clks[i]);
 
-	for (i = 0; i < ARRAY_SIZE(lookups); i++)
-		clkdev_add(&lookups[i]);
+	clkdev_add_table(lookups, ARRAY_SIZE(lookups));
 
 	if (!ret)
 		ret = sh_clk_div4_register(div4_clks, ARRAY_SIZE(div4_clks),
diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7757.c b/arch/sh/kernel/cpu/sh4a/clock-sh7757.c
index 9a28fdb36387..e40ec2c97ad1 100644
--- a/arch/sh/kernel/cpu/sh4a/clock-sh7757.c
+++ b/arch/sh/kernel/cpu/sh4a/clock-sh7757.c
@@ -141,8 +141,8 @@ int __init arch_clk_init(void)
 
 	for (i = 0; i < ARRAY_SIZE(clks); i++)
 		ret |= clk_register(clks[i]);
-	for (i = 0; i < ARRAY_SIZE(lookups); i++)
-		clkdev_add(&lookups[i]);
+
+	clkdev_add_table(lookups, ARRAY_SIZE(lookups));
 
 	if (!ret)
 		ret = sh_clk_div4_register(div4_clks, ARRAY_SIZE(div4_clks),
diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7785.c b/arch/sh/kernel/cpu/sh4a/clock-sh7785.c
index 17d0ea55a5a2..8eb6e62340c9 100644
--- a/arch/sh/kernel/cpu/sh4a/clock-sh7785.c
+++ b/arch/sh/kernel/cpu/sh4a/clock-sh7785.c
@@ -164,8 +164,8 @@ int __init arch_clk_init(void)
 
 	for (i = 0; i < ARRAY_SIZE(clks); i++)
 		ret |= clk_register(clks[i]);
-	for (i = 0; i < ARRAY_SIZE(lookups); i++)
-		clkdev_add(&lookups[i]);
+
+	clkdev_add_table(lookups, ARRAY_SIZE(lookups));
 
 	if (!ret)
 		ret = sh_clk_div4_register(div4_clks, ARRAY_SIZE(div4_clks),
diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7786.c b/arch/sh/kernel/cpu/sh4a/clock-sh7786.c
index bec2a83f1ba5..5e50e7ebeff0 100644
--- a/arch/sh/kernel/cpu/sh4a/clock-sh7786.c
+++ b/arch/sh/kernel/cpu/sh4a/clock-sh7786.c
@@ -179,8 +179,8 @@ int __init arch_clk_init(void)
 
 	for (i = 0; i < ARRAY_SIZE(clks); i++)
 		ret |= clk_register(clks[i]);
-	for (i = 0; i < ARRAY_SIZE(lookups); i++)
-		clkdev_add(&lookups[i]);
+
+	clkdev_add_table(lookups, ARRAY_SIZE(lookups));
 
 	if (!ret)
 		ret = sh_clk_div4_register(div4_clks, ARRAY_SIZE(div4_clks),
diff --git a/arch/sh/kernel/cpu/sh4a/clock-shx3.c b/arch/sh/kernel/cpu/sh4a/clock-shx3.c
index 9a49a44f6f94..605221d1448a 100644
--- a/arch/sh/kernel/cpu/sh4a/clock-shx3.c
+++ b/arch/sh/kernel/cpu/sh4a/clock-shx3.c
@@ -138,8 +138,8 @@ int __init arch_clk_init(void)
 
 	for (i = 0; i < ARRAY_SIZE(clks); i++)
 		ret |= clk_register(clks[i]);
-	for (i = 0; i < ARRAY_SIZE(lookups); i++)
-		clkdev_add(&lookups[i]);
+
+	clkdev_add_table(lookups, ARRAY_SIZE(lookups));
 
 	if (!ret)
 		ret = sh_clk_div4_register(div4_clks, ARRAY_SIZE(div4_clks),
diff --git a/drivers/clk/clk-s2mps11.c b/drivers/clk/clk-s2mps11.c
index bfa1e64e267d..9b13a303d3f8 100644
--- a/drivers/clk/clk-s2mps11.c
+++ b/drivers/clk/clk-s2mps11.c
@@ -242,14 +242,12 @@ static int s2mps11_clk_probe(struct platform_device *pdev)
 			goto err_reg;
 		}
 
-		s2mps11_clk->lookup = clkdev_alloc(s2mps11_clk->clk,
+		s2mps11_clk->lookup = clkdev_create(s2mps11_clk->clk,
 					s2mps11_name(s2mps11_clk), NULL);
 		if (!s2mps11_clk->lookup) {
 			ret = -ENOMEM;
 			goto err_lup;
 		}
-
-		clkdev_add(s2mps11_clk->lookup);
 	}
 
 	for (i = 0; i < S2MPS11_CLKS_NUM; i++) {
diff --git a/drivers/clk/clkdev.c b/drivers/clk/clkdev.c
index 1fcb6ef2cdac..c0eaf0973bd2 100644
--- a/drivers/clk/clkdev.c
+++ b/drivers/clk/clkdev.c
@@ -177,7 +177,7 @@ struct clk *clk_get_sys(const char *dev_id, const char *con_id)
 	if (!cl)
 		goto out;
 
-	clk = __clk_create_clk(__clk_get_hw(cl->clk), dev_id, con_id);
+	clk = __clk_create_clk(cl->clk_hw, dev_id, con_id);
 	if (IS_ERR(clk))
 		goto out;
 
@@ -215,18 +215,26 @@ void clk_put(struct clk *clk)
 }
 EXPORT_SYMBOL(clk_put);
 
-void clkdev_add(struct clk_lookup *cl)
+static void __clkdev_add(struct clk_lookup *cl)
 {
 	mutex_lock(&clocks_mutex);
 	list_add_tail(&cl->node, &clocks);
 	mutex_unlock(&clocks_mutex);
 }
+
+void clkdev_add(struct clk_lookup *cl)
+{
+	if (!cl->clk_hw)
+		cl->clk_hw = __clk_get_hw(cl->clk);
+	__clkdev_add(cl);
+}
 EXPORT_SYMBOL(clkdev_add);
 
-void __init clkdev_add_table(struct clk_lookup *cl, size_t num)
+void clkdev_add_table(struct clk_lookup *cl, size_t num)
 {
 	mutex_lock(&clocks_mutex);
 	while (num--) {
+		cl->clk_hw = __clk_get_hw(cl->clk);
 		list_add_tail(&cl->node, &clocks);
 		cl++;
 	}
@@ -243,7 +251,7 @@ struct clk_lookup_alloc {
 };
 
 static struct clk_lookup * __init_refok
-vclkdev_alloc(struct clk *clk, const char *con_id, const char *dev_fmt,
+vclkdev_alloc(struct clk_hw *hw, const char *con_id, const char *dev_fmt,
 	va_list ap)
 {
 	struct clk_lookup_alloc *cla;
@@ -252,7 +260,7 @@ vclkdev_alloc(struct clk *clk, const char *con_id, const char *dev_fmt,
 	if (!cla)
 		return NULL;
 
-	cla->cl.clk = clk;
+	cla->cl.clk_hw = hw;
 	if (con_id) {
 		strlcpy(cla->con_id, con_id, sizeof(cla->con_id));
 		cla->cl.con_id = cla->con_id;
@@ -266,6 +274,19 @@ vclkdev_alloc(struct clk *clk, const char *con_id, const char *dev_fmt,
 	return &cla->cl;
 }
 
+static struct clk_lookup *
+vclkdev_create(struct clk_hw *hw, const char *con_id, const char *dev_fmt,
+	va_list ap)
+{
+	struct clk_lookup *cl;
+
+	cl = vclkdev_alloc(hw, con_id, dev_fmt, ap);
+	if (cl)
+		__clkdev_add(cl);
+
+	return cl;
+}
+
 struct clk_lookup * __init_refok
 clkdev_alloc(struct clk *clk, const char *con_id, const char *dev_fmt, ...)
 {
@@ -273,28 +294,49 @@ clkdev_alloc(struct clk *clk, const char *con_id, const char *dev_fmt, ...)
 	va_list ap;
 
 	va_start(ap, dev_fmt);
-	cl = vclkdev_alloc(clk, con_id, dev_fmt, ap);
+	cl = vclkdev_alloc(__clk_get_hw(clk), con_id, dev_fmt, ap);
 	va_end(ap);
 
 	return cl;
 }
 EXPORT_SYMBOL(clkdev_alloc);
 
-int clk_add_alias(const char *alias, const char *alias_dev_name, char *id,
-	struct device *dev)
+/**
+ * clkdev_create - allocate and add a clkdev lookup structure
+ * @clk: struct clk to associate with all clk_lookups
+ * @con_id: connection ID string on device
+ * @dev_fmt: format string describing device name
+ *
+ * Returns a clk_lookup structure, which can be later unregistered and
+ * freed.
+ */
+struct clk_lookup *clkdev_create(struct clk *clk, const char *con_id,
+	const char *dev_fmt, ...)
 {
-	struct clk *r = clk_get(dev, id);
+	struct clk_lookup *cl;
+	va_list ap;
+
+	va_start(ap, dev_fmt);
+	cl = vclkdev_create(__clk_get_hw(clk), con_id, dev_fmt, ap);
+	va_end(ap);
+
+	return cl;
+}
+EXPORT_SYMBOL_GPL(clkdev_create);
+
+int clk_add_alias(const char *alias, const char *alias_dev_name,
+	const char *con_id, struct device *dev)
+{
+	struct clk *r = clk_get(dev, con_id);
 	struct clk_lookup *l;
 
 	if (IS_ERR(r))
 		return PTR_ERR(r);
 
-	l = clkdev_alloc(r, alias, alias_dev_name);
+	l = clkdev_create(r, alias, "%s", alias_dev_name);
 	clk_put(r);
-	if (!l)
-		return -ENODEV;
-	clkdev_add(l);
-	return 0;
+
+	return l ? 0 : -ENODEV;
 }
 EXPORT_SYMBOL(clk_add_alias);
 
@@ -334,15 +376,10 @@ int clk_register_clkdev(struct clk *clk, const char *con_id,
 		return PTR_ERR(clk);
 
 	va_start(ap, dev_fmt);
-	cl = vclkdev_alloc(clk, con_id, dev_fmt, ap);
+	cl = vclkdev_create(__clk_get_hw(clk), con_id, dev_fmt, ap);
 	va_end(ap);
 
-	if (!cl)
-		return -ENOMEM;
-
-	clkdev_add(cl);
-
-	return 0;
+	return cl ? 0 : -ENOMEM;
 }
 EXPORT_SYMBOL(clk_register_clkdev);
 
@@ -365,8 +402,8 @@ int clk_register_clkdevs(struct clk *clk, struct clk_lookup *cl, size_t num)
 		return PTR_ERR(clk);
 
 	for (i = 0; i < num; i++, cl++) {
-		cl->clk = clk;
-		clkdev_add(cl);
+		cl->clk_hw = __clk_get_hw(clk);
+		__clkdev_add(cl);
 	}
 
 	return 0;
diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index 51d7865fdddb..50534704486a 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -132,6 +132,12 @@ config ARM_GLOBAL_TIMER
 	help
 	  This options enables support for the ARM global timer unit
 
+config ARM_TIMER_SP804
+	bool "Support for Dual Timer SP804 module"
+	depends on GENERIC_SCHED_CLOCK
+	select CLKSRC_MMIO
+	select CLKSRC_OF if OF
+
 config CLKSRC_ARM_GLOBAL_TIMER_SCHED_CLOCK
 	bool
 	depends on ARM_GLOBAL_TIMER
diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile
index 5b85f6adb258..5ca59f9b377f 100644
--- a/drivers/clocksource/Makefile
+++ b/drivers/clocksource/Makefile
@@ -45,6 +45,7 @@ obj-$(CONFIG_MTK_TIMER)		+= mtk_timer.o
 
 obj-$(CONFIG_ARM_ARCH_TIMER)		+= arm_arch_timer.o
 obj-$(CONFIG_ARM_GLOBAL_TIMER)		+= arm_global_timer.o
+obj-$(CONFIG_ARM_TIMER_SP804)		+= timer-sp804.o
 obj-$(CONFIG_CLKSRC_METAG_GENERIC)	+= metag_generic.o
 obj-$(CONFIG_ARCH_HAS_TICK_BROADCAST)	+= dummy_timer.o
 obj-$(CONFIG_ARCH_KEYSTONE)		+= timer-keystone.o
diff --git a/drivers/clocksource/timer-integrator-ap.c b/drivers/clocksource/timer-integrator-ap.c
index b9efd30513d5..d7d21e4dcef0 100644
--- a/drivers/clocksource/timer-integrator-ap.c
+++ b/drivers/clocksource/timer-integrator-ap.c
@@ -26,7 +26,8 @@
 #include <linux/clockchips.h>
 #include <linux/interrupt.h>
 #include <linux/sched_clock.h>
-#include <asm/hardware/arm_timer.h>
+
+#include "timer-sp.h"
 
 static void __iomem * sched_clk_base;
 
diff --git a/arch/arm/include/asm/hardware/arm_timer.h b/drivers/clocksource/timer-sp.h
similarity index 93%
rename from arch/arm/include/asm/hardware/arm_timer.h
rename to drivers/clocksource/timer-sp.h
index d6030ff599db..050d88561e9c 100644
--- a/arch/arm/include/asm/hardware/arm_timer.h
+++ b/drivers/clocksource/timer-sp.h
@@ -1,6 +1,3 @@
-#ifndef __ASM_ARM_HARDWARE_ARM_TIMER_H
-#define __ASM_ARM_HARDWARE_ARM_TIMER_H
-
 /*
  * ARM timer implementation, found in Integrator, Versatile and Realview
  * platforms.  Not all platforms support all registers and bits in these
@@ -31,5 +28,3 @@
 #define TIMER_RIS	0x10			/*  CVR ro */
 #define TIMER_MIS	0x14			/*  CVR ro */
 #define TIMER_BGLOAD	0x18			/*  CVR rw */
-
-#endif
diff --git a/arch/arm/common/timer-sp.c b/drivers/clocksource/timer-sp804.c
similarity index 97%
rename from arch/arm/common/timer-sp.c
rename to drivers/clocksource/timer-sp804.c
index 19211324772f..ca02503f17d1 100644
--- a/arch/arm/common/timer-sp.c
+++ b/drivers/clocksource/timer-sp804.c
@@ -1,5 +1,5 @@
 /*
- *  linux/arch/arm/common/timer-sp.c
+ *  linux/drivers/clocksource/timer-sp.c
  *
  *  Copyright (C) 1999 - 2003 ARM Limited
  *  Copyright (C) 2000 Deep Blue Solutions Ltd
@@ -30,8 +30,9 @@
 #include <linux/of_irq.h>
 #include <linux/sched_clock.h>
 
-#include <asm/hardware/arm_timer.h>
-#include <asm/hardware/timer-sp.h>
+#include <clocksource/timer-sp804.h>
+
+#include "timer-sp.h"
 
 static long __init sp804_get_clock_rate(struct clk *clk)
 {
@@ -71,6 +72,11 @@ static u64 notrace sp804_read(void)
 	return ~readl_relaxed(sched_clock_base + TIMER_VALUE);
 }
 
+void __init sp804_timer_disable(void __iomem *base)
+{
+	writel(0, base + TIMER_CTRL);
+}
+
 void __init __sp804_clocksource_and_sched_clock_init(void __iomem *base,
 						     const char *name,
 						     struct clk *clk,
diff --git a/arch/arm/include/asm/hardware/timer-sp.h b/include/clocksource/timer-sp804.h
similarity index 85%
rename from arch/arm/include/asm/hardware/timer-sp.h
rename to include/clocksource/timer-sp804.h
index bb28af7c32de..1f8a1caa7cb4 100644
--- a/arch/arm/include/asm/hardware/timer-sp.h
+++ b/include/clocksource/timer-sp804.h
@@ -1,9 +1,13 @@
+#ifndef __CLKSOURCE_TIMER_SP804_H
+#define __CLKSOURCE_TIMER_SP804_H
+
 struct clk;
 
 void __sp804_clocksource_and_sched_clock_init(void __iomem *,
 					      const char *, struct clk *, int);
 void __sp804_clockevents_init(void __iomem *, unsigned int,
 			      struct clk *, const char *);
+void sp804_timer_disable(void __iomem *);
 
 static inline void sp804_clocksource_init(void __iomem *base, const char *name)
 {
@@ -21,3 +25,4 @@ static inline void sp804_clockevents_init(void __iomem *base, unsigned int irq,
 	__sp804_clockevents_init(base, irq, NULL, name);
 
 }
+#endif
diff --git a/include/linux/clk.h b/include/linux/clk.h
index 68c16a6bedb3..0df4a51e1a78 100644
--- a/include/linux/clk.h
+++ b/include/linux/clk.h
@@ -306,6 +306,20 @@ void devm_clk_put(struct device *dev, struct clk *clk);
  * @clk: clock source
  * @rate: desired clock rate in Hz
  *
+ * This answers the question "if I were to pass @rate to clk_set_rate(),
+ * what clock rate would I end up with?" without changing the hardware
+ * in any way.  In other words:
+ *
+ *   rate = clk_round_rate(clk, r);
+ *
+ * and:
+ *
+ *   clk_set_rate(clk, r);
+ *   rate = clk_get_rate(clk);
+ *
+ * are equivalent except the former does not modify the clock hardware
+ * in any way.
+ *
  * Returns rounded clock rate in Hz, or negative errno.
  */
 long clk_round_rate(struct clk *clk, unsigned long rate);
@@ -471,19 +485,6 @@ static inline void clk_disable_unprepare(struct clk *clk)
 	clk_unprepare(clk);
 }
 
-/**
- * clk_add_alias - add a new clock alias
- * @alias: name for clock alias
- * @alias_dev_name: device name
- * @id: platform specific clock name
- * @dev: device
- *
- * Allows using generic clock names for drivers by adding a new alias.
- * Assumes clkdev, see clkdev.h for more info.
- */
-int clk_add_alias(const char *alias, const char *alias_dev_name, char *id,
-			struct device *dev);
-
 struct device_node;
 struct of_phandle_args;
 
diff --git a/include/linux/clkdev.h b/include/linux/clkdev.h
index 94bad77eeb4a..a240b18e86fa 100644
--- a/include/linux/clkdev.h
+++ b/include/linux/clkdev.h
@@ -22,6 +22,7 @@ struct clk_lookup {
 	const char		*dev_id;
 	const char		*con_id;
 	struct clk		*clk;
+	struct clk_hw		*clk_hw;
 };
 
 #define CLKDEV_INIT(d, n, c)	\
@@ -37,8 +38,11 @@ struct clk_lookup *clkdev_alloc(struct clk *clk, const char *con_id,
 void clkdev_add(struct clk_lookup *cl);
 void clkdev_drop(struct clk_lookup *cl);
 
+struct clk_lookup *clkdev_create(struct clk *clk, const char *con_id,
+	const char *dev_fmt, ...);
+
 void clkdev_add_table(struct clk_lookup *, size_t);
-int clk_add_alias(const char *, const char *, char *, struct device *);
+int clk_add_alias(const char *, const char *, const char *, struct device *);
 
 int clk_register_clkdev(struct clk *, const char *, const char *, ...);
 int clk_register_clkdevs(struct clk *, struct clk_lookup *, size_t);
diff --git a/sound/soc/sh/migor.c b/sound/soc/sh/migor.c
index 82f582344fe7..672bcd4c252b 100644
--- a/sound/soc/sh/migor.c
+++ b/sound/soc/sh/migor.c
@@ -162,12 +162,11 @@ static int __init migor_init(void)
 	if (ret < 0)
 		return ret;
 
-	siumckb_lookup = clkdev_alloc(&siumckb_clk, "siumckb_clk", NULL);
+	siumckb_lookup = clkdev_create(&siumckb_clk, "siumckb_clk", NULL);
 	if (!siumckb_lookup) {
 		ret = -ENOMEM;
 		goto eclkdevalloc;
 	}
-	clkdev_add(siumckb_lookup);
 
 	/* Port number used on this machine: port B */
 	migor_snd_device = platform_device_alloc("soc-audio", 1);