Merge branch 'master' into percpu

Conflicts:
	arch/powerpc/platforms/pseries/hvCall.S
	include/linux/percpu.h

44 files changed, 513 insertions, 621 deletions

diff --git a/arch/sh/include/asm/.gitignore b/arch/sh/include/asm/.gitignore
deleted file mode 100644
index 378db779fb6c..000000000000
--- a/arch/sh/include/asm/.gitignore
+++ /dev/null
@@ -1 +0,0 @@
-machtypes.h
diff --git a/arch/sh/include/asm/addrspace.h b/arch/sh/include/asm/addrspace.h
index 80d40813e057..99d6b3ecbe22 100644
--- a/arch/sh/include/asm/addrspace.h
+++ b/arch/sh/include/asm/addrspace.h
@@ -28,9 +28,6 @@
 /* Returns the privileged segment base of a given address  */
 #define PXSEG(a)	(((unsigned long)(a)) & 0xe0000000)
 
-/* Returns the physical address of a PnSEG (n=1,2) address   */
-#define PHYSADDR(a)	(((unsigned long)(a)) & 0x1fffffff)
-
 #if defined(CONFIG_29BIT) || defined(CONFIG_PMB_FIXED)
 /*
  * Map an address to a certain privileged segment
@@ -60,5 +57,11 @@
 #define P3_ADDR_MAX		P4SEG
 #endif
 
+#ifndef __ASSEMBLY__
+#ifdef CONFIG_PMB
+extern int __in_29bit_mode(void);
+#endif /* CONFIG_PMB */
+#endif /* __ASSEMBLY__ */
+
 #endif /* __KERNEL__ */
 #endif /* __ASM_SH_ADDRSPACE_H */
diff --git a/arch/sh/include/asm/asm-offsets.h b/arch/sh/include/asm/asm-offsets.h
new file mode 100644
index 000000000000..d370ee36a182
--- /dev/null
+++ b/arch/sh/include/asm/asm-offsets.h
@@ -0,0 +1 @@
+#include <generated/asm-offsets.h>
diff --git a/arch/sh/include/asm/atomic.h b/arch/sh/include/asm/atomic.h
index e8e78137c6f5..b16388d71954 100644
--- a/arch/sh/include/asm/atomic.h
+++ b/arch/sh/include/asm/atomic.h
@@ -78,11 +78,10 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u)
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
 #define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
 
-/* Atomic operations are already serializing on SH */
-#define smp_mb__before_atomic_dec()	barrier()
-#define smp_mb__after_atomic_dec()	barrier()
-#define smp_mb__before_atomic_inc()	barrier()
-#define smp_mb__after_atomic_inc()	barrier()
+#define smp_mb__before_atomic_dec()	smp_mb()
+#define smp_mb__after_atomic_dec()	smp_mb()
+#define smp_mb__before_atomic_inc()	smp_mb()
+#define smp_mb__after_atomic_inc()	smp_mb()
 
 #include <asm-generic/atomic-long.h>
 #include <asm-generic/atomic64.h>
diff --git a/arch/sh/include/asm/bitops.h b/arch/sh/include/asm/bitops.h
index ebe595b7ab1f..98511e4d28cb 100644
--- a/arch/sh/include/asm/bitops.h
+++ b/arch/sh/include/asm/bitops.h
@@ -26,8 +26,8 @@
 /*
  * clear_bit() doesn't provide any barrier for the compiler.
  */
-#define smp_mb__before_clear_bit()	barrier()
-#define smp_mb__after_clear_bit()	barrier()
+#define smp_mb__before_clear_bit()	smp_mb()
+#define smp_mb__after_clear_bit()	smp_mb()
 
 #ifdef CONFIG_SUPERH32
 static inline unsigned long ffz(unsigned long word)
diff --git a/arch/sh/include/asm/bugs.h b/arch/sh/include/asm/bugs.h
index 46260fcbdf4b..02a19a1c033a 100644
--- a/arch/sh/include/asm/bugs.h
+++ b/arch/sh/include/asm/bugs.h
@@ -14,11 +14,15 @@
 
 #include <asm/processor.h>
 
+extern void select_idle_routine(void);
+
 static void __init check_bugs(void)
 {
 	extern unsigned long loops_per_jiffy;
 	char *p = &init_utsname()->machine[2]; /* "sh" */
 
+	select_idle_routine();
+
 	current_cpu_data.loops_per_jiffy = loops_per_jiffy;
 
 	switch (current_cpu_data.family) {
diff --git a/arch/sh/include/asm/cacheflush.h b/arch/sh/include/asm/cacheflush.h
index c29918f3c819..dda96eb3e7c0 100644
--- a/arch/sh/include/asm/cacheflush.h
+++ b/arch/sh/include/asm/cacheflush.h
@@ -42,6 +42,7 @@ extern void flush_cache_page(struct vm_area_struct *vma,
 				unsigned long addr, unsigned long pfn);
 extern void flush_cache_range(struct vm_area_struct *vma,
 				 unsigned long start, unsigned long end);
+#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 extern void flush_dcache_page(struct page *page);
 extern void flush_icache_range(unsigned long start, unsigned long end);
 extern void flush_icache_page(struct vm_area_struct *vma,
diff --git a/arch/sh/include/asm/dma-mapping.h b/arch/sh/include/asm/dma-mapping.h
index 69d56dd4c968..87ced133a363 100644
--- a/arch/sh/include/asm/dma-mapping.h
+++ b/arch/sh/include/asm/dma-mapping.h
@@ -1,219 +1,108 @@
 #ifndef __ASM_SH_DMA_MAPPING_H
 #define __ASM_SH_DMA_MAPPING_H
 
-#include <linux/mm.h>
-#include <linux/scatterlist.h>
-#include <linux/dma-debug.h>
-#include <asm/cacheflush.h>
-#include <asm/io.h>
+extern struct dma_map_ops *dma_ops;
+extern void no_iommu_init(void);
+
+static inline struct dma_map_ops *get_dma_ops(struct device *dev)
+{
+	return dma_ops;
+}
+
 #include <asm-generic/dma-coherent.h>
+#include <asm-generic/dma-mapping-common.h>
+
+static inline int dma_supported(struct device *dev, u64 mask)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
 
-extern struct bus_type pci_bus_type;
+	if (ops->dma_supported)
+		return ops->dma_supported(dev, mask);
 
-#define dma_supported(dev, mask)	(1)
+	return 1;
+}
 
 static inline int dma_set_mask(struct device *dev, u64 mask)
 {
+	struct dma_map_ops *ops = get_dma_ops(dev);
+
 	if (!dev->dma_mask || !dma_supported(dev, mask))
 		return -EIO;
+	if (ops->set_dma_mask)
+		return ops->set_dma_mask(dev, mask);
 
 	*dev->dma_mask = mask;
 
 	return 0;
 }
 
-void *dma_alloc_coherent(struct device *dev, size_t size,
-			 dma_addr_t *dma_handle, gfp_t flag);
-
-void dma_free_coherent(struct device *dev, size_t size,
-		       void *vaddr, dma_addr_t dma_handle);
-
 void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 		    enum dma_data_direction dir);
 
 #define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
 #define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
-#define dma_is_consistent(d, h) (1)
-
-static inline dma_addr_t dma_map_single(struct device *dev,
-					void *ptr, size_t size,
-					enum dma_data_direction dir)
-{
-	dma_addr_t addr = virt_to_phys(ptr);
-
-#if defined(CONFIG_PCI) && !defined(CONFIG_SH_PCIDMA_NONCOHERENT)
-	if (dev->bus == &pci_bus_type)
-		return addr;
-#endif
-	dma_cache_sync(dev, ptr, size, dir);
-
-	debug_dma_map_page(dev, virt_to_page(ptr),
-			   (unsigned long)ptr & ~PAGE_MASK, size,
-			   dir, addr, true);
-
-	return addr;
-}
-
-static inline void dma_unmap_single(struct device *dev, dma_addr_t addr,
-				    size_t size, enum dma_data_direction dir)
-{
-	debug_dma_unmap_page(dev, addr, size, dir, true);
-}
 
-static inline int dma_map_sg(struct device *dev, struct scatterlist *sg,
-			     int nents, enum dma_data_direction dir)
-{
-	int i;
-
-	for (i = 0; i < nents; i++) {
-#if !defined(CONFIG_PCI) || defined(CONFIG_SH_PCIDMA_NONCOHERENT)
-		dma_cache_sync(dev, sg_virt(&sg[i]), sg[i].length, dir);
+#ifdef CONFIG_DMA_COHERENT
+#define dma_is_consistent(d, h) (1)
+#else
+#define dma_is_consistent(d, h) (0)
 #endif
-		sg[i].dma_address = sg_phys(&sg[i]);
-		sg[i].dma_length = sg[i].length;
-	}
 
-	debug_dma_map_sg(dev, sg, nents, i, dir);
-
-	return nents;
-}
-
-static inline void dma_unmap_sg(struct device *dev, struct scatterlist *sg,
-				int nents, enum dma_data_direction dir)
-{
-	debug_dma_unmap_sg(dev, sg, nents, dir);
-}
-
-static inline dma_addr_t dma_map_page(struct device *dev, struct page *page,
-				      unsigned long offset, size_t size,
-				      enum dma_data_direction dir)
-{
-	return dma_map_single(dev, page_address(page) + offset, size, dir);
-}
-
-static inline void dma_unmap_page(struct device *dev, dma_addr_t dma_address,
-				  size_t size, enum dma_data_direction dir)
-{
-	dma_unmap_single(dev, dma_address, size, dir);
-}
-
-static inline void __dma_sync_single(struct device *dev, dma_addr_t dma_handle,
-				   size_t size, enum dma_data_direction dir)
+static inline int dma_get_cache_alignment(void)
 {
-#if defined(CONFIG_PCI) && !defined(CONFIG_SH_PCIDMA_NONCOHERENT)
-	if (dev->bus == &pci_bus_type)
-		return;
-#endif
-	dma_cache_sync(dev, phys_to_virt(dma_handle), size, dir);
+	/*
+	 * Each processor family will define its own L1_CACHE_SHIFT,
+	 * L1_CACHE_BYTES wraps to this, so this is always safe.
+	 */
+	return L1_CACHE_BYTES;
 }
 
-static inline void dma_sync_single_range(struct device *dev,
-					 dma_addr_t dma_handle,
-					 unsigned long offset, size_t size,
-					 enum dma_data_direction dir)
+static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
-#if defined(CONFIG_PCI) && !defined(CONFIG_SH_PCIDMA_NONCOHERENT)
-	if (dev->bus == &pci_bus_type)
-		return;
-#endif
-	dma_cache_sync(dev, phys_to_virt(dma_handle) + offset, size, dir);
-}
+	struct dma_map_ops *ops = get_dma_ops(dev);
 
-static inline void __dma_sync_sg(struct device *dev, struct scatterlist *sg,
-			       int nelems, enum dma_data_direction dir)
-{
-	int i;
+	if (ops->mapping_error)
+		return ops->mapping_error(dev, dma_addr);
 
-	for (i = 0; i < nelems; i++) {
-#if !defined(CONFIG_PCI) || defined(CONFIG_SH_PCIDMA_NONCOHERENT)
-		dma_cache_sync(dev, sg_virt(&sg[i]), sg[i].length, dir);
-#endif
-		sg[i].dma_address = sg_phys(&sg[i]);
-		sg[i].dma_length = sg[i].length;
-	}
+	return dma_addr == 0;
 }
 
-static inline void dma_sync_single_for_cpu(struct device *dev,
-					   dma_addr_t dma_handle, size_t size,
-					   enum dma_data_direction dir)
+static inline void *dma_alloc_coherent(struct device *dev, size_t size,
+				       dma_addr_t *dma_handle, gfp_t gfp)
 {
-	__dma_sync_single(dev, dma_handle, size, dir);
-	debug_dma_sync_single_for_cpu(dev, dma_handle, size, dir);
-}
+	struct dma_map_ops *ops = get_dma_ops(dev);
+	void *memory;
 
-static inline void dma_sync_single_for_device(struct device *dev,
-					      dma_addr_t dma_handle,
-					      size_t size,
-					      enum dma_data_direction dir)
-{
-	__dma_sync_single(dev, dma_handle, size, dir);
-	debug_dma_sync_single_for_device(dev, dma_handle, size, dir);
-}
+	if (dma_alloc_from_coherent(dev, size, dma_handle, &memory))
+		return memory;
+	if (!ops->alloc_coherent)
+		return NULL;
 
-static inline void dma_sync_single_range_for_cpu(struct device *dev,
-						 dma_addr_t dma_handle,
-						 unsigned long offset,
-						 size_t size,
-						 enum dma_data_direction direction)
-{
-	dma_sync_single_for_cpu(dev, dma_handle+offset, size, direction);
-	debug_dma_sync_single_range_for_cpu(dev, dma_handle,
-					    offset, size, direction);
-}
+	memory = ops->alloc_coherent(dev, size, dma_handle, gfp);
+	debug_dma_alloc_coherent(dev, size, *dma_handle, memory);
 
-static inline void dma_sync_single_range_for_device(struct device *dev,
-						    dma_addr_t dma_handle,
-						    unsigned long offset,
-						    size_t size,
-						    enum dma_data_direction direction)
-{
-	dma_sync_single_for_device(dev, dma_handle+offset, size, direction);
-	debug_dma_sync_single_range_for_device(dev, dma_handle,
-					       offset, size, direction);
+	return memory;
 }
 
-
-static inline void dma_sync_sg_for_cpu(struct device *dev,
-				       struct scatterlist *sg, int nelems,
-				       enum dma_data_direction dir)
+static inline void dma_free_coherent(struct device *dev, size_t size,
+				     void *vaddr, dma_addr_t dma_handle)
 {
-	__dma_sync_sg(dev, sg, nelems, dir);
-	debug_dma_sync_sg_for_cpu(dev, sg, nelems, dir);
-}
+	struct dma_map_ops *ops = get_dma_ops(dev);
 
-static inline void dma_sync_sg_for_device(struct device *dev,
-					  struct scatterlist *sg, int nelems,
-					  enum dma_data_direction dir)
-{
-	__dma_sync_sg(dev, sg, nelems, dir);
-	debug_dma_sync_sg_for_device(dev, sg, nelems, dir);
-}
+	WARN_ON(irqs_disabled());	/* for portability */
 
-static inline int dma_get_cache_alignment(void)
-{
-	/*
-	 * Each processor family will define its own L1_CACHE_SHIFT,
-	 * L1_CACHE_BYTES wraps to this, so this is always safe.
-	 */
-	return L1_CACHE_BYTES;
-}
+	if (dma_release_from_coherent(dev, get_order(size), vaddr))
+		return;
 
-static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return dma_addr == 0;
+	debug_dma_free_coherent(dev, size, vaddr, dma_handle);
+	if (ops->free_coherent)
+		ops->free_coherent(dev, size, vaddr, dma_handle);
 }
 
-#define ARCH_HAS_DMA_DECLARE_COHERENT_MEMORY
-
-extern int
-dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr,
-			    dma_addr_t device_addr, size_t size, int flags);
-
-extern void
-dma_release_declared_memory(struct device *dev);
-
-extern void *
-dma_mark_declared_memory_occupied(struct device *dev,
-				  dma_addr_t device_addr, size_t size);
+/* arch/sh/mm/consistent.c */
+extern void *dma_generic_alloc_coherent(struct device *dev, size_t size,
+					dma_addr_t *dma_addr, gfp_t flag);
+extern void dma_generic_free_coherent(struct device *dev, size_t size,
+				      void *vaddr, dma_addr_t dma_handle);
 
 #endif /* __ASM_SH_DMA_MAPPING_H */
diff --git a/arch/sh/include/asm/dma.h b/arch/sh/include/asm/dma.h
index 04ad0e1e637e..07373a074090 100644
--- a/arch/sh/include/asm/dma.h
+++ b/arch/sh/include/asm/dma.h
@@ -19,9 +19,11 @@
 #include <asm-generic/dma.h>
 
 #ifdef CONFIG_NR_DMA_CHANNELS
-#  define MAX_DMA_CHANNELS   (CONFIG_NR_DMA_CHANNELS)
+#  define MAX_DMA_CHANNELS	(CONFIG_NR_DMA_CHANNELS)
+#elif defined(CONFIG_NR_ONCHIP_DMA_CHANNELS)
+#  define MAX_DMA_CHANNELS	(CONFIG_NR_ONCHIP_DMA_CHANNELS)
 #else
-#  define MAX_DMA_CHANNELS   (CONFIG_NR_ONCHIP_DMA_CHANNELS)
+#  define MAX_DMA_CHANNELS	0
 #endif
 
 /*
diff --git a/arch/sh/include/asm/dwarf.h b/arch/sh/include/asm/dwarf.h
index ced6795891a6..bdccbbfdc0bd 100644
--- a/arch/sh/include/asm/dwarf.h
+++ b/arch/sh/include/asm/dwarf.h
@@ -194,6 +194,12 @@
 #define DWARF_ARCH_RA_REG	17
 
 #ifndef __ASSEMBLY__
+
+#include <linux/compiler.h>
+#include <linux/bug.h>
+#include <linux/list.h>
+#include <linux/module.h>
+
 /*
  * Read either the frame pointer (r14) or the stack pointer (r15).
  * NOTE: this MUST be inlined.
@@ -241,6 +247,12 @@ struct dwarf_cie {
 
 	unsigned long flags;
 #define DWARF_CIE_Z_AUGMENTATION	(1 << 0)
+
+	/*
+	 * 'mod' will be non-NULL if this CIE came from a module's
+	 * .eh_frame section.
+	 */
+	struct module *mod;
 };
 
 /**
@@ -255,6 +267,12 @@ struct dwarf_fde {
 	unsigned char *instructions;
 	unsigned char *end;
 	struct list_head link;
+
+	/*
+	 * 'mod' will be non-NULL if this FDE came from a module's
+	 * .eh_frame section.
+	 */
+	struct module *mod;
 };
 
 /**
@@ -364,6 +382,12 @@ static inline unsigned int DW_CFA_operand(unsigned long insn)
 
 extern struct dwarf_frame *dwarf_unwind_stack(unsigned long,
 					      struct dwarf_frame *);
+extern void dwarf_free_frame(struct dwarf_frame *);
+
+extern int module_dwarf_finalize(const Elf_Ehdr *, const Elf_Shdr *,
+				 struct module *);
+extern void module_dwarf_cleanup(struct module *);
+
 #endif /* !__ASSEMBLY__ */
 
 #define CFI_STARTPROC	.cfi_startproc
@@ -391,6 +415,10 @@ extern struct dwarf_frame *dwarf_unwind_stack(unsigned long,
 static inline void dwarf_unwinder_init(void)
 {
 }
+
+#define module_dwarf_finalize(hdr, sechdrs, me)	(0)
+#define module_dwarf_cleanup(mod)		do { } while (0)
+
 #endif
 
 #endif /* CONFIG_DWARF_UNWINDER */
diff --git a/arch/sh/include/asm/elf.h b/arch/sh/include/asm/elf.h
index ccb1d93bb043..ac04255022b6 100644
--- a/arch/sh/include/asm/elf.h
+++ b/arch/sh/include/asm/elf.h
@@ -114,7 +114,6 @@ typedef struct user_fpu_struct elf_fpregset_t;
  */
 #define CORE_DUMP_USE_REGSET
 
-#define USE_ELF_CORE_DUMP
 #define ELF_FDPIC_CORE_EFLAGS	EF_SH_FDPIC
 #define ELF_EXEC_PAGESIZE	PAGE_SIZE
 
diff --git a/arch/sh/include/asm/fixmap.h b/arch/sh/include/asm/fixmap.h
index 721fcc4d5e98..5ac1e40a511c 100644
--- a/arch/sh/include/asm/fixmap.h
+++ b/arch/sh/include/asm/fixmap.h
@@ -14,9 +14,9 @@
 #define _ASM_FIXMAP_H
 
 #include <linux/kernel.h>
+#include <linux/threads.h>
 #include <asm/page.h>
 #ifdef CONFIG_HIGHMEM
-#include <linux/threads.h>
 #include <asm/kmap_types.h>
 #endif
 
@@ -46,9 +46,15 @@
  * fix-mapped?
  */
 enum fixed_addresses {
-#define FIX_N_COLOURS 16
+	/*
+	 * The FIX_CMAP entries are used by kmap_coherent() to get virtual
+	 * addresses which are of a known color, and so their values are
+	 * important. __fix_to_virt(FIX_CMAP_END - n) must give an address
+	 * which is the same color as a page (n<<PAGE_SHIFT).
+	 */
+#define FIX_N_COLOURS 8
 	FIX_CMAP_BEGIN,
-	FIX_CMAP_END = FIX_CMAP_BEGIN + FIX_N_COLOURS,
+	FIX_CMAP_END = FIX_CMAP_BEGIN + (FIX_N_COLOURS * NR_CPUS) - 1,
 	FIX_UNCACHED,
 #ifdef CONFIG_HIGHMEM
 	FIX_KMAP_BEGIN,	/* reserved pte's for temporary kernel mappings */
diff --git a/arch/sh/include/asm/fpu.h b/arch/sh/include/asm/fpu.h
index 1d3aee04b5cc..fb6bbb9b1cc8 100644
--- a/arch/sh/include/asm/fpu.h
+++ b/arch/sh/include/asm/fpu.h
@@ -18,16 +18,15 @@ static inline void grab_fpu(struct pt_regs *regs)
 
 struct task_struct;
 
-extern void save_fpu(struct task_struct *__tsk, struct pt_regs *regs);
+extern void save_fpu(struct task_struct *__tsk);
+void fpu_state_restore(struct pt_regs *regs);
 #else
 
+#define save_fpu(tsk)		do { } while (0)
 #define release_fpu(regs)	do { } while (0)
 #define grab_fpu(regs)		do { } while (0)
+#define fpu_state_restore(regs)	do { } while (0)
 
-static inline void save_fpu(struct task_struct *tsk, struct pt_regs *regs)
-{
-	clear_tsk_thread_flag(tsk, TIF_USEDFPU);
-}
 #endif
 
 struct user_regset;
@@ -39,19 +38,28 @@ extern int fpregs_get(struct task_struct *target,
 		      unsigned int pos, unsigned int count,
 		      void *kbuf, void __user *ubuf);
 
+static inline void __unlazy_fpu(struct task_struct *tsk, struct pt_regs *regs)
+{
+	if (task_thread_info(tsk)->status & TS_USEDFPU) {
+		task_thread_info(tsk)->status &= ~TS_USEDFPU;
+		save_fpu(tsk);
+		release_fpu(regs);
+	} else
+		tsk->fpu_counter = 0;
+}
+
 static inline void unlazy_fpu(struct task_struct *tsk, struct pt_regs *regs)
 {
 	preempt_disable();
-	if (test_tsk_thread_flag(tsk, TIF_USEDFPU))
-		save_fpu(tsk, regs);
+	__unlazy_fpu(tsk, regs);
 	preempt_enable();
 }
 
 static inline void clear_fpu(struct task_struct *tsk, struct pt_regs *regs)
 {
 	preempt_disable();
-	if (test_tsk_thread_flag(tsk, TIF_USEDFPU)) {
-		clear_tsk_thread_flag(tsk, TIF_USEDFPU);
+	if (task_thread_info(tsk)->status & TS_USEDFPU) {
+		task_thread_info(tsk)->status &= ~TS_USEDFPU;
 		release_fpu(regs);
 	}
 	preempt_enable();
diff --git a/arch/sh/include/asm/ftrace.h b/arch/sh/include/asm/ftrace.h
index 12f3a31f20af..13e9966464c2 100644
--- a/arch/sh/include/asm/ftrace.h
+++ b/arch/sh/include/asm/ftrace.h
@@ -35,4 +35,21 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr)
 #endif /* __ASSEMBLY__ */
 #endif /* CONFIG_FUNCTION_TRACER */
 
+#ifndef __ASSEMBLY__
+
+/* arch/sh/kernel/return_address.c */
+extern void *return_address(unsigned int);
+
+#define HAVE_ARCH_CALLER_ADDR
+
+#define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
+#define CALLER_ADDR1 ((unsigned long)return_address(1))
+#define CALLER_ADDR2 ((unsigned long)return_address(2))
+#define CALLER_ADDR3 ((unsigned long)return_address(3))
+#define CALLER_ADDR4 ((unsigned long)return_address(4))
+#define CALLER_ADDR5 ((unsigned long)return_address(5))
+#define CALLER_ADDR6 ((unsigned long)return_address(6))
+
+#endif /* __ASSEMBLY__ */
+
 #endif /* __ASM_SH_FTRACE_H */
diff --git a/arch/sh/include/asm/gpio.h b/arch/sh/include/asm/gpio.h
index 61f93da2c62e..f8d9a731e903 100644
--- a/arch/sh/include/asm/gpio.h
+++ b/arch/sh/include/asm/gpio.h
@@ -20,7 +20,7 @@
 #endif
 
 #define ARCH_NR_GPIOS 512
-#include <asm-generic/gpio.h>
+#include <linux/sh_pfc.h>
 
 #ifdef CONFIG_GPIOLIB
 
@@ -53,84 +53,4 @@ static inline int irq_to_gpio(unsigned int irq)
 
 #endif /* CONFIG_GPIOLIB */
 
-typedef unsigned short pinmux_enum_t;
-typedef unsigned short pinmux_flag_t;
-
-#define PINMUX_TYPE_NONE            0
-#define PINMUX_TYPE_FUNCTION        1
-#define PINMUX_TYPE_GPIO            2
-#define PINMUX_TYPE_OUTPUT          3
-#define PINMUX_TYPE_INPUT           4
-#define PINMUX_TYPE_INPUT_PULLUP    5
-#define PINMUX_TYPE_INPUT_PULLDOWN  6
-
-#define PINMUX_FLAG_TYPE            (0x7)
-#define PINMUX_FLAG_WANT_PULLUP     (1 << 3)
-#define PINMUX_FLAG_WANT_PULLDOWN   (1 << 4)
-
-#define PINMUX_FLAG_DBIT_SHIFT      5
-#define PINMUX_FLAG_DBIT            (0x1f << PINMUX_FLAG_DBIT_SHIFT)
-#define PINMUX_FLAG_DREG_SHIFT      10
-#define PINMUX_FLAG_DREG            (0x3f << PINMUX_FLAG_DREG_SHIFT)
-
-struct pinmux_gpio {
-	pinmux_enum_t enum_id;
-	pinmux_flag_t flags;
-};
-
-#define PINMUX_GPIO(gpio, data_or_mark) [gpio] = { data_or_mark }
-#define PINMUX_DATA(data_or_mark, ids...) data_or_mark, ids, 0
-
-struct pinmux_cfg_reg {
-	unsigned long reg, reg_width, field_width;
-	unsigned long *cnt;
-	pinmux_enum_t *enum_ids;
-};
-
-#define PINMUX_CFG_REG(name, r, r_width, f_width) \
-	.reg = r, .reg_width = r_width, .field_width = f_width,		\
-	.cnt = (unsigned long [r_width / f_width]) {}, \
-	.enum_ids = (pinmux_enum_t [(r_width / f_width) * (1 << f_width)]) \
-
-struct pinmux_data_reg {
-	unsigned long reg, reg_width, reg_shadow;
-	pinmux_enum_t *enum_ids;
-};
-
-#define PINMUX_DATA_REG(name, r, r_width) \
-	.reg = r, .reg_width = r_width,	\
-	.enum_ids = (pinmux_enum_t [r_width]) \
-
-struct pinmux_range {
-	pinmux_enum_t begin;
-	pinmux_enum_t end;
-	pinmux_enum_t force;
-};
-
-struct pinmux_info {
-	char *name;
-	pinmux_enum_t reserved_id;
-	struct pinmux_range data;
-	struct pinmux_range input;
-	struct pinmux_range input_pd;
-	struct pinmux_range input_pu;
-	struct pinmux_range output;
-	struct pinmux_range mark;
-	struct pinmux_range function;
-
-	unsigned first_gpio, last_gpio;
-
-	struct pinmux_gpio *gpios;
-	struct pinmux_cfg_reg *cfg_regs;
-	struct pinmux_data_reg *data_regs;
-
-	pinmux_enum_t *gpio_data;
-	unsigned int gpio_data_size;
-
-	unsigned long *gpio_in_use;
-	struct gpio_chip chip;
-};
-
-int register_pinmux(struct pinmux_info *pip);
-
 #endif /* __ASM_SH_GPIO_H */
diff --git a/arch/sh/include/asm/hardirq.h b/arch/sh/include/asm/hardirq.h
index a5be4afa790b..48b191313a99 100644
--- a/arch/sh/include/asm/hardirq.h
+++ b/arch/sh/include/asm/hardirq.h
@@ -1,9 +1,16 @@
 #ifndef __ASM_SH_HARDIRQ_H
 #define __ASM_SH_HARDIRQ_H
 
-extern void ack_bad_irq(unsigned int irq);
-#define ack_bad_irq ack_bad_irq
+#include <linux/threads.h>
+#include <linux/irq.h>
+
+typedef struct {
+	unsigned int __softirq_pending;
+	unsigned int __nmi_count;		/* arch dependent */
+} ____cacheline_aligned irq_cpustat_t;
 
-#include <asm-generic/hardirq.h>
+#include <linux/irq_cpustat.h>	/* Standard mappings for irq_cpustat_t above */
+
+extern void ack_bad_irq(unsigned int irq);
 
 #endif /* __ASM_SH_HARDIRQ_H */
diff --git a/arch/sh/include/asm/io.h b/arch/sh/include/asm/io.h
index 5be45ea4dfec..026dd659a640 100644
--- a/arch/sh/include/asm/io.h
+++ b/arch/sh/include/asm/io.h
@@ -90,15 +90,11 @@
 #define ctrl_outl		__raw_writel
 #define ctrl_outq		__raw_writeq
 
+extern unsigned long generic_io_base;
+
 static inline void ctrl_delay(void)
 {
-#ifdef CONFIG_CPU_SH4
-	__raw_readw(CCN_PVR);
-#elif defined(P2SEG)
-	__raw_readw(P2SEG);
-#else
-#error "Need a dummy address for delay"
-#endif
+	__raw_readw(generic_io_base);
 }
 
 #define __BUILD_MEMORY_STRING(bwlq, type)				\
@@ -186,8 +182,6 @@ __BUILD_MEMORY_STRING(q, u64)
 
 #define IO_SPACE_LIMIT 0xffffffff
 
-extern unsigned long generic_io_base;
-
 /*
  * This function provides a method for the generic case where a
  * board-specific ioport_map simply needs to return the port + some
@@ -239,14 +233,20 @@ unsigned long long poke_real_address_q(unsigned long long addr,
  * doesn't exist, so everything must go through page tables.
  */
 #ifdef CONFIG_MMU
-void __iomem *__ioremap(unsigned long offset, unsigned long size,
-			unsigned long flags);
+void __iomem *__ioremap_caller(unsigned long offset, unsigned long size,
+			       unsigned long flags, void *caller);
 void __iounmap(void __iomem *addr);
 
 static inline void __iomem *
+__ioremap(unsigned long offset, unsigned long size, unsigned long flags)
+{
+	return __ioremap_caller(offset, size, flags, __builtin_return_address(0));
+}
+
+static inline void __iomem *
 __ioremap_mode(unsigned long offset, unsigned long size, unsigned long flags)
 {
-#if defined(CONFIG_SUPERH32) && !defined(CONFIG_PMB_FIXED)
+#if defined(CONFIG_SUPERH32) && !defined(CONFIG_PMB_FIXED) && !defined(CONFIG_PMB)
 	unsigned long last_addr = offset + size - 1;
 #endif
 	void __iomem *ret;
@@ -255,7 +255,7 @@ __ioremap_mode(unsigned long offset, unsigned long size, unsigned long flags)
 	if (ret)
 		return ret;
 
-#if defined(CONFIG_SUPERH32) && !defined(CONFIG_PMB_FIXED)
+#if defined(CONFIG_SUPERH32) && !defined(CONFIG_PMB_FIXED) && !defined(CONFIG_PMB)
 	/*
 	 * For P1 and P2 space this is trivial, as everything is already
 	 * mapped. Uncached access for P1 addresses are done through P2.
@@ -277,6 +277,7 @@ __ioremap_mode(unsigned long offset, unsigned long size, unsigned long flags)
 	return __ioremap(offset, size, flags);
 }
 #else
+#define __ioremap(offset, size, flags)		((void __iomem *)(offset))
 #define __ioremap_mode(offset, size, flags)	((void __iomem *)(offset))
 #define __iounmap(addr)				do { } while (0)
 #endif /* CONFIG_MMU */
diff --git a/arch/sh/include/asm/irqflags.h b/arch/sh/include/asm/irqflags.h
index 46e71da5be6b..a741153b41c2 100644
--- a/arch/sh/include/asm/irqflags.h
+++ b/arch/sh/include/asm/irqflags.h
@@ -1,34 +1,9 @@
 #ifndef __ASM_SH_IRQFLAGS_H
 #define __ASM_SH_IRQFLAGS_H
 
-#ifdef CONFIG_SUPERH32
-#include "irqflags_32.h"
-#else
-#include "irqflags_64.h"
-#endif
+#define RAW_IRQ_DISABLED	0xf0
+#define RAW_IRQ_ENABLED		0x00
 
-#define raw_local_save_flags(flags) \
-		do { (flags) = __raw_local_save_flags(); } while (0)
-
-static inline int raw_irqs_disabled_flags(unsigned long flags)
-{
-	return (flags != 0);
-}
-
-static inline int raw_irqs_disabled(void)
-{
-	unsigned long flags = __raw_local_save_flags();
-
-	return raw_irqs_disabled_flags(flags);
-}
-
-#define raw_local_irq_save(flags) \
-		do { (flags) = __raw_local_irq_save(); } while (0)
-
-static inline void raw_local_irq_restore(unsigned long flags)
-{
-	if ((flags & 0xf0) != 0xf0)
-		raw_local_irq_enable();
-}
+#include <asm-generic/irqflags.h>
 
 #endif /* __ASM_SH_IRQFLAGS_H */
diff --git a/arch/sh/include/asm/irqflags_32.h b/arch/sh/include/asm/irqflags_32.h
deleted file mode 100644
index 60218f541340..000000000000
--- a/arch/sh/include/asm/irqflags_32.h
+++ /dev/null
@@ -1,99 +0,0 @@
-#ifndef __ASM_SH_IRQFLAGS_32_H
-#define __ASM_SH_IRQFLAGS_32_H
-
-static inline void raw_local_irq_enable(void)
-{
-	unsigned long __dummy0, __dummy1;
-
-	__asm__ __volatile__ (
-		"stc	sr, %0\n\t"
-		"and	%1, %0\n\t"
-#ifdef CONFIG_CPU_HAS_SR_RB
-		"stc	r6_bank, %1\n\t"
-		"or	%1, %0\n\t"
-#endif
-		"ldc	%0, sr\n\t"
-		: "=&r" (__dummy0), "=r" (__dummy1)
-		: "1" (~0x000000f0)
-		: "memory"
-	);
-}
-
-static inline void raw_local_irq_disable(void)
-{
-	unsigned long flags;
-
-	__asm__ __volatile__ (
-		"stc	sr, %0\n\t"
-		"or	#0xf0, %0\n\t"
-		"ldc	%0, sr\n\t"
-		: "=&z" (flags)
-		: /* no inputs */
-		: "memory"
-	);
-}
-
-static inline void set_bl_bit(void)
-{
-	unsigned long __dummy0, __dummy1;
-
-	__asm__ __volatile__ (
-		"stc	sr, %0\n\t"
-		"or	%2, %0\n\t"
-		"and	%3, %0\n\t"
-		"ldc	%0, sr\n\t"
-		: "=&r" (__dummy0), "=r" (__dummy1)
-		: "r" (0x10000000), "r" (0xffffff0f)
-		: "memory"
-	);
-}
-
-static inline void clear_bl_bit(void)
-{
-	unsigned long __dummy0, __dummy1;
-
-	__asm__ __volatile__ (
-		"stc	sr, %0\n\t"
-		"and	%2, %0\n\t"
-		"ldc	%0, sr\n\t"
-		: "=&r" (__dummy0), "=r" (__dummy1)
-		: "1" (~0x10000000)
-		: "memory"
-	);
-}
-
-static inline unsigned long __raw_local_save_flags(void)
-{
-	unsigned long flags;
-
-	__asm__ __volatile__ (
-		"stc	sr, %0\n\t"
-		"and	#0xf0, %0\n\t"
-		: "=&z" (flags)
-		: /* no inputs */
-		: "memory"
-	);
-
-	return flags;
-}
-
-static inline unsigned long __raw_local_irq_save(void)
-{
-	unsigned long flags, __dummy;
-
-	__asm__ __volatile__ (
-		"stc	sr, %1\n\t"
-		"mov	%1, %0\n\t"
-		"or	#0xf0, %0\n\t"
-		"ldc	%0, sr\n\t"
-		"mov	%1, %0\n\t"
-		"and	#0xf0, %0\n\t"
-		: "=&z" (flags), "=&r" (__dummy)
-		: /* no inputs */
-		: "memory"
-	);
-
-	return flags;
-}
-
-#endif /* __ASM_SH_IRQFLAGS_32_H */
diff --git a/arch/sh/include/asm/irqflags_64.h b/arch/sh/include/asm/irqflags_64.h
deleted file mode 100644
index 88f65222c1d4..000000000000
--- a/arch/sh/include/asm/irqflags_64.h
+++ /dev/null
@@ -1,85 +0,0 @@
-#ifndef __ASM_SH_IRQFLAGS_64_H
-#define __ASM_SH_IRQFLAGS_64_H
-
-#include <cpu/registers.h>
-
-#define SR_MASK_LL	0x00000000000000f0LL
-#define SR_BL_LL	0x0000000010000000LL
-
-static inline void raw_local_irq_enable(void)
-{
-	unsigned long long __dummy0, __dummy1 = ~SR_MASK_LL;
-
-	__asm__ __volatile__("getcon	" __SR ", %0\n\t"
-			     "and	%0, %1, %0\n\t"
-			     "putcon	%0, " __SR "\n\t"
-			     : "=&r" (__dummy0)
-			     : "r" (__dummy1));
-}
-
-static inline void raw_local_irq_disable(void)
-{
-	unsigned long long __dummy0, __dummy1 = SR_MASK_LL;
-
-	__asm__ __volatile__("getcon	" __SR ", %0\n\t"
-			     "or	%0, %1, %0\n\t"
-			     "putcon	%0, " __SR "\n\t"
-			     : "=&r" (__dummy0)
-			     : "r" (__dummy1));
-}
-
-static inline void set_bl_bit(void)
-{
-	unsigned long long __dummy0, __dummy1 = SR_BL_LL;
-
-	__asm__ __volatile__("getcon	" __SR ", %0\n\t"
-			     "or	%0, %1, %0\n\t"
-			     "putcon	%0, " __SR "\n\t"
-			     : "=&r" (__dummy0)
-			     : "r" (__dummy1));
-
-}
-
-static inline void clear_bl_bit(void)
-{
-	unsigned long long __dummy0, __dummy1 = ~SR_BL_LL;
-
-	__asm__ __volatile__("getcon	" __SR ", %0\n\t"
-			     "and	%0, %1, %0\n\t"
-			     "putcon	%0, " __SR "\n\t"
-			     : "=&r" (__dummy0)
-			     : "r" (__dummy1));
-}
-
-static inline unsigned long __raw_local_save_flags(void)
-{
-	unsigned long long __dummy = SR_MASK_LL;
-	unsigned long flags;
-
-	__asm__ __volatile__ (
-		"getcon	" __SR ", %0\n\t"
-		"and	%0, %1, %0"
-		: "=&r" (flags)
-		: "r" (__dummy));
-
-	return flags;
-}
-
-static inline unsigned long __raw_local_irq_save(void)
-{
-	unsigned long long __dummy0, __dummy1 = SR_MASK_LL;
-	unsigned long flags;
-
-	__asm__ __volatile__ (
-		"getcon	" __SR ", %1\n\t"
-		"or	%1, r63, %0\n\t"
-		"or	%1, %2, %1\n\t"
-		"putcon	%1, " __SR "\n\t"
-		"and	%0, %2, %0"
-		: "=&r" (flags), "=&r" (__dummy0)
-		: "r" (__dummy1));
-
-	return flags;
-}
-
-#endif /* __ASM_SH_IRQFLAGS_64_H */
diff --git a/arch/sh/include/asm/machvec.h b/arch/sh/include/asm/machvec.h
index 84dd37761f56..9c30955630ff 100644
--- a/arch/sh/include/asm/machvec.h
+++ b/arch/sh/include/asm/machvec.h
@@ -12,7 +12,7 @@
 
 #include <linux/types.h>
 #include <linux/time.h>
-#include <asm/machtypes.h>
+#include <generated/machtypes.h>
 
 struct sh_machine_vector {
 	void (*mv_setup)(char **cmdline_p);
diff --git a/arch/sh/include/asm/mmu.h b/arch/sh/include/asm/mmu.h
index f5963037c9d6..c7426ad9926e 100644
--- a/arch/sh/include/asm/mmu.h
+++ b/arch/sh/include/asm/mmu.h
@@ -7,12 +7,16 @@
 #define PMB_PASCR		0xff000070
 #define PMB_IRMCR		0xff000078
 
+#define PASCR_SE		0x80000000
+
 #define PMB_ADDR		0xf6100000
 #define PMB_DATA		0xf7100000
 #define PMB_ENTRY_MAX		16
 #define PMB_E_MASK		0x0000000f
 #define PMB_E_SHIFT		8
 
+#define PMB_PFN_MASK		0xff000000
+
 #define PMB_SZ_16M		0x00000000
 #define PMB_SZ_64M		0x00000010
 #define PMB_SZ_128M		0x00000080
@@ -62,17 +66,10 @@ struct pmb_entry {
 };
 
 /* arch/sh/mm/pmb.c */
-int __set_pmb_entry(unsigned long vpn, unsigned long ppn,
-		    unsigned long flags, int *entry);
-int set_pmb_entry(struct pmb_entry *pmbe);
-void clear_pmb_entry(struct pmb_entry *pmbe);
-struct pmb_entry *pmb_alloc(unsigned long vpn, unsigned long ppn,
-			    unsigned long flags);
-void pmb_free(struct pmb_entry *pmbe);
 long pmb_remap(unsigned long virt, unsigned long phys,
 	       unsigned long size, unsigned long flags);
 void pmb_unmap(unsigned long addr);
+int pmb_init(void);
 #endif /* __ASSEMBLY__ */
 
 #endif /* __MMU_H */
-
diff --git a/arch/sh/include/asm/pci.h b/arch/sh/include/asm/pci.h
index 4163950cd1c6..67f3999b544e 100644
--- a/arch/sh/include/asm/pci.h
+++ b/arch/sh/include/asm/pci.h
@@ -3,8 +3,6 @@
 
 #ifdef __KERNEL__
 
-#include <linux/dma-mapping.h>
-
 /* Can be used to override the logic in pci_scan_bus for skipping
    already-configured bus numbers - to be used for buggy BIOSes
    or architectures with incomplete PCI setup by the loader */
@@ -54,30 +52,18 @@ static inline void pcibios_penalize_isa_irq(int irq, int active)
  * address space.  The networking and block device layers use
  * this boolean for bounce buffer decisions.
  */
-#define PCI_DMA_BUS_IS_PHYS	(1)
-
-#include <linux/types.h>
-#include <linux/slab.h>
-#include <asm/scatterlist.h>
-#include <linux/string.h>
-#include <asm/io.h>
+#define PCI_DMA_BUS_IS_PHYS	(dma_ops->is_phys)
 
 /* pci_unmap_{single,page} being a nop depends upon the
  * configuration.
  */
-#ifdef CONFIG_SH_PCIDMA_NONCOHERENT
-#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)	\
-	dma_addr_t ADDR_NAME;
-#define DECLARE_PCI_UNMAP_LEN(LEN_NAME)		\
-	__u32 LEN_NAME;
-#define pci_unmap_addr(PTR, ADDR_NAME)			\
-	((PTR)->ADDR_NAME)
-#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL)		\
-	(((PTR)->ADDR_NAME) = (VAL))
-#define pci_unmap_len(PTR, LEN_NAME)			\
-	((PTR)->LEN_NAME)
-#define pci_unmap_len_set(PTR, LEN_NAME, VAL)		\
-	(((PTR)->LEN_NAME) = (VAL))
+#ifdef CONFIG_DMA_NONCOHERENT
+#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)	dma_addr_t ADDR_NAME;
+#define DECLARE_PCI_UNMAP_LEN(LEN_NAME)		__u32 LEN_NAME;
+#define pci_unmap_addr(PTR, ADDR_NAME)		((PTR)->ADDR_NAME)
+#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL)	(((PTR)->ADDR_NAME) = (VAL))
+#define pci_unmap_len(PTR, LEN_NAME)		((PTR)->LEN_NAME)
+#define pci_unmap_len_set(PTR, LEN_NAME, VAL)	(((PTR)->LEN_NAME) = (VAL))
 #else
 #define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)
 #define DECLARE_PCI_UNMAP_LEN(LEN_NAME)
diff --git a/arch/sh/include/asm/perf_event.h b/arch/sh/include/asm/perf_event.h
index 11a302297ab7..3d0c9f36d150 100644
--- a/arch/sh/include/asm/perf_event.h
+++ b/arch/sh/include/asm/perf_event.h
@@ -1,8 +1,35 @@
 #ifndef __ASM_SH_PERF_EVENT_H
 #define __ASM_SH_PERF_EVENT_H
 
-/* SH only supports software events through this interface. */
-static inline void set_perf_event_pending(void) {}
+struct hw_perf_event;
+
+#define MAX_HWEVENTS	2
+
+struct sh_pmu {
+	const char	*name;
+	unsigned int	num_events;
+	void		(*disable_all)(void);
+	void		(*enable_all)(void);
+	void		(*enable)(struct hw_perf_event *, int);
+	void		(*disable)(struct hw_perf_event *, int);
+	u64		(*read)(int);
+	int		(*event_map)(int);
+	unsigned int	max_events;
+	unsigned long	raw_event_mask;
+	const int	(*cache_events)[PERF_COUNT_HW_CACHE_MAX]
+				       [PERF_COUNT_HW_CACHE_OP_MAX]
+				       [PERF_COUNT_HW_CACHE_RESULT_MAX];
+};
+
+/* arch/sh/kernel/perf_event.c */
+extern int register_sh_pmu(struct sh_pmu *);
+extern int reserve_pmc_hardware(void);
+extern void release_pmc_hardware(void);
+
+static inline void set_perf_event_pending(void)
+{
+	/* Nothing to see here, move along. */
+}
 
 #define PERF_EVENT_INDEX_OFFSET	0
 
diff --git a/arch/sh/include/asm/pgtable.h b/arch/sh/include/asm/pgtable.h
index 4f3efa7d5a64..ba3046e4f06f 100644
--- a/arch/sh/include/asm/pgtable.h
+++ b/arch/sh/include/asm/pgtable.h
@@ -75,13 +75,31 @@ static inline unsigned long long neff_sign_extend(unsigned long val)
 #define USER_PTRS_PER_PGD	(TASK_SIZE/PGDIR_SIZE)
 #define FIRST_USER_ADDRESS	0
 
-#ifdef CONFIG_32BIT
-#define PHYS_ADDR_MASK		0xffffffff
+#define PHYS_ADDR_MASK29		0x1fffffff
+#define PHYS_ADDR_MASK32		0xffffffff
+
+#ifdef CONFIG_PMB
+static inline unsigned long phys_addr_mask(void)
+{
+	/* Is the MMU in 29bit mode? */
+	if (__in_29bit_mode())
+		return PHYS_ADDR_MASK29;
+
+	return PHYS_ADDR_MASK32;
+}
+#elif defined(CONFIG_32BIT)
+static inline unsigned long phys_addr_mask(void)
+{
+	return PHYS_ADDR_MASK32;
+}
 #else
-#define PHYS_ADDR_MASK		0x1fffffff
+static inline unsigned long phys_addr_mask(void)
+{
+	return PHYS_ADDR_MASK29;
+}
 #endif
 
-#define PTE_PHYS_MASK		(PHYS_ADDR_MASK & PAGE_MASK)
+#define PTE_PHYS_MASK		(phys_addr_mask() & PAGE_MASK)
 #define PTE_FLAGS_MASK		(~(PTE_PHYS_MASK) << PAGE_SHIFT)
 
 #ifdef CONFIG_SUPERH32
diff --git a/arch/sh/include/asm/pgtable_32.h b/arch/sh/include/asm/pgtable_32.h
index c0d359ce337b..5003ee86f67b 100644
--- a/arch/sh/include/asm/pgtable_32.h
+++ b/arch/sh/include/asm/pgtable_32.h
@@ -108,7 +108,7 @@ static inline unsigned long copy_ptea_attributes(unsigned long x)
 #define _PAGE_CLEAR_FLAGS	(_PAGE_PROTNONE | _PAGE_ACCESSED | _PAGE_FILE)
 #endif
 
-#define _PAGE_FLAGS_HARDWARE_MASK	(PHYS_ADDR_MASK & ~(_PAGE_CLEAR_FLAGS))
+#define _PAGE_FLAGS_HARDWARE_MASK	(phys_addr_mask() & ~(_PAGE_CLEAR_FLAGS))
 
 /* Hardware flags, page size encoding */
 #if !defined(CONFIG_MMU)
@@ -344,7 +344,8 @@ static inline void set_pte(pte_t *ptep, pte_t pte)
 #define pte_special(pte)	((pte).pte_low & _PAGE_SPECIAL)
 
 #ifdef CONFIG_X2TLB
-#define pte_write(pte)		((pte).pte_high & _PAGE_EXT_USER_WRITE)
+#define pte_write(pte) \
+	((pte).pte_high & (_PAGE_EXT_USER_WRITE | _PAGE_EXT_KERN_WRITE))
 #else
 #define pte_write(pte)		((pte).pte_low & _PAGE_RW)
 #endif
@@ -358,7 +359,7 @@ static inline pte_t pte_##fn(pte_t pte) { pte.pte_##h op; return pte; }
  * individually toggled (and user permissions are entirely decoupled from
  * kernel permissions), we attempt to couple them a bit more sanely here.
  */
-PTE_BIT_FUNC(high, wrprotect, &= ~_PAGE_EXT_USER_WRITE);
+PTE_BIT_FUNC(high, wrprotect, &= ~(_PAGE_EXT_USER_WRITE | _PAGE_EXT_KERN_WRITE));
 PTE_BIT_FUNC(high, mkwrite, |= _PAGE_EXT_USER_WRITE | _PAGE_EXT_KERN_WRITE);
 PTE_BIT_FUNC(high, mkhuge, |= _PAGE_SZHUGE);
 #else
diff --git a/arch/sh/include/asm/processor_32.h b/arch/sh/include/asm/processor_32.h
index 9a8714945dc9..1f3d6fab660c 100644
--- a/arch/sh/include/asm/processor_32.h
+++ b/arch/sh/include/asm/processor_32.h
@@ -56,6 +56,7 @@ asmlinkage void __init sh_cpu_init(void);
 #define SR_DSP		0x00001000
 #define SR_IMASK	0x000000f0
 #define SR_FD		0x00008000
+#define SR_MD		0x40000000
 
 /*
  * DSP structure and data
@@ -136,7 +137,7 @@ struct mm_struct;
 extern void release_thread(struct task_struct *);
 
 /* Prepare to copy thread state - unlazy all lazy status */
-#define prepare_to_copy(tsk)	do { } while (0)
+void prepare_to_copy(struct task_struct *tsk);
 
 /*
  * create a kernel thread without removing it from tasklists
diff --git a/arch/sh/include/asm/rwsem.h b/arch/sh/include/asm/rwsem.h
index 1987f3ea7f1b..06e2251a5e48 100644
--- a/arch/sh/include/asm/rwsem.h
+++ b/arch/sh/include/asm/rwsem.h
@@ -41,7 +41,7 @@ struct rw_semaphore {
 #endif
 
 #define __RWSEM_INITIALIZER(name) \
-	{ RWSEM_UNLOCKED_VALUE, SPIN_LOCK_UNLOCKED, \
+	{ RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED((name).wait_lock), \
 	  LIST_HEAD_INIT((name).wait_list) \
 	  __RWSEM_DEP_MAP_INIT(name) }
 
diff --git a/arch/sh/include/asm/scatterlist.h b/arch/sh/include/asm/scatterlist.h
index 327cc2e4c97b..e38d1d4c7f6f 100644
--- a/arch/sh/include/asm/scatterlist.h
+++ b/arch/sh/include/asm/scatterlist.h
@@ -1,7 +1,7 @@
 #ifndef __ASM_SH_SCATTERLIST_H
 #define __ASM_SH_SCATTERLIST_H
 
-#define ISA_DMA_THRESHOLD	PHYS_ADDR_MASK
+#define ISA_DMA_THRESHOLD	phys_addr_mask()
 
 #include <asm-generic/scatterlist.h>
 
diff --git a/arch/sh/include/asm/sh_eth.h b/arch/sh/include/asm/sh_eth.h
index acf99700deed..f739061e2ee4 100644
--- a/arch/sh/include/asm/sh_eth.h
+++ b/arch/sh/include/asm/sh_eth.h
@@ -7,6 +7,7 @@ struct sh_eth_plat_data {
 	int phy;
 	int edmac_endian;
 
+	unsigned char mac_addr[6];
 	unsigned no_ether_link:1;
 	unsigned ether_link_active_low:1;
 };
diff --git a/arch/sh/include/asm/sh_keysc.h b/arch/sh/include/asm/sh_keysc.h
deleted file mode 100644
index 4a65b1e40eab..000000000000
--- a/arch/sh/include/asm/sh_keysc.h
+++ /dev/null
@@ -1,14 +0,0 @@
-#ifndef __ASM_KEYSC_H__
-#define __ASM_KEYSC_H__
-
-#define SH_KEYSC_MAXKEYS 30
-
-struct sh_keysc_info {
-	enum { SH_KEYSC_MODE_1, SH_KEYSC_MODE_2, SH_KEYSC_MODE_3 } mode;
-	int scan_timing; /* 0 -> 7, see KYCR1, SCN[2:0] */
-	int delay;
-	int kycr2_delay;
-	int keycodes[SH_KEYSC_MAXKEYS];
-};
-
-#endif /* __ASM_KEYSC_H__ */
diff --git a/arch/sh/include/asm/spinlock.h b/arch/sh/include/asm/spinlock.h
index a28c9f0053fd..bdc0f3b6c56a 100644
--- a/arch/sh/include/asm/spinlock.h
+++ b/arch/sh/include/asm/spinlock.h
@@ -23,10 +23,10 @@
  * Your basic SMP spinlocks, allowing only a single CPU anywhere
  */
 
-#define __raw_spin_is_locked(x)		((x)->lock <= 0)
-#define __raw_spin_lock_flags(lock, flags) __raw_spin_lock(lock)
-#define __raw_spin_unlock_wait(x) \
-	do { while (__raw_spin_is_locked(x)) cpu_relax(); } while (0)
+#define arch_spin_is_locked(x)		((x)->lock <= 0)
+#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
+#define arch_spin_unlock_wait(x) \
+	do { while (arch_spin_is_locked(x)) cpu_relax(); } while (0)
 
 /*
  * Simple spin lock operations.  There are two variants, one clears IRQ's
@@ -34,14 +34,14 @@
  *
  * We make no fairness assumptions.  They have a cost.
  */
-static inline void __raw_spin_lock(raw_spinlock_t *lock)
+static inline void arch_spin_lock(arch_spinlock_t *lock)
 {
 	unsigned long tmp;
 	unsigned long oldval;
 
 	__asm__ __volatile__ (
 		"1:						\n\t"
-		"movli.l	@%2, %0	! __raw_spin_lock	\n\t"
+		"movli.l	@%2, %0	! arch_spin_lock	\n\t"
 		"mov		%0, %1				\n\t"
 		"mov		#0, %0				\n\t"
 		"movco.l	%0, @%2				\n\t"
@@ -54,12 +54,12 @@ static inline void __raw_spin_lock(raw_spinlock_t *lock)
 	);
 }
 
-static inline void __raw_spin_unlock(raw_spinlock_t *lock)
+static inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
 	unsigned long tmp;
 
 	__asm__ __volatile__ (
-		"mov		#1, %0 ! __raw_spin_unlock	\n\t"
+		"mov		#1, %0 ! arch_spin_unlock	\n\t"
 		"mov.l		%0, @%1				\n\t"
 		: "=&z" (tmp)
 		: "r" (&lock->lock)
@@ -67,13 +67,13 @@ static inline void __raw_spin_unlock(raw_spinlock_t *lock)
 	);
 }
 
-static inline int __raw_spin_trylock(raw_spinlock_t *lock)
+static inline int arch_spin_trylock(arch_spinlock_t *lock)
 {
 	unsigned long tmp, oldval;
 
 	__asm__ __volatile__ (
 		"1:						\n\t"
-		"movli.l	@%2, %0	! __raw_spin_trylock	\n\t"
+		"movli.l	@%2, %0	! arch_spin_trylock	\n\t"
 		"mov		%0, %1				\n\t"
 		"mov		#0, %0				\n\t"
 		"movco.l	%0, @%2				\n\t"
@@ -100,21 +100,21 @@ static inline int __raw_spin_trylock(raw_spinlock_t *lock)
  * read_can_lock - would read_trylock() succeed?
  * @lock: the rwlock in question.
  */
-#define __raw_read_can_lock(x)	((x)->lock > 0)
+#define arch_read_can_lock(x)	((x)->lock > 0)
 
 /**
  * write_can_lock - would write_trylock() succeed?
  * @lock: the rwlock in question.
  */
-#define __raw_write_can_lock(x)	((x)->lock == RW_LOCK_BIAS)
+#define arch_write_can_lock(x)	((x)->lock == RW_LOCK_BIAS)
 
-static inline void __raw_read_lock(raw_rwlock_t *rw)
+static inline void arch_read_lock(arch_rwlock_t *rw)
 {
 	unsigned long tmp;
 
 	__asm__ __volatile__ (
 		"1:						\n\t"
-		"movli.l	@%1, %0	! __raw_read_lock	\n\t"
+		"movli.l	@%1, %0	! arch_read_lock	\n\t"
 		"cmp/pl		%0				\n\t"
 		"bf		1b				\n\t"
 		"add		#-1, %0				\n\t"
@@ -126,13 +126,13 @@ static inline void __raw_read_lock(raw_rwlock_t *rw)
 	);
 }
 
-static inline void __raw_read_unlock(raw_rwlock_t *rw)
+static inline void arch_read_unlock(arch_rwlock_t *rw)
 {
 	unsigned long tmp;
 
 	__asm__ __volatile__ (
 		"1:						\n\t"
-		"movli.l	@%1, %0	! __raw_read_unlock	\n\t"
+		"movli.l	@%1, %0	! arch_read_unlock	\n\t"
 		"add		#1, %0				\n\t"
 		"movco.l	%0, @%1				\n\t"
 		"bf		1b				\n\t"
@@ -142,13 +142,13 @@ static inline void __raw_read_unlock(raw_rwlock_t *rw)
 	);
 }
 
-static inline void __raw_write_lock(raw_rwlock_t *rw)
+static inline void arch_write_lock(arch_rwlock_t *rw)
 {
 	unsigned long tmp;
 
 	__asm__ __volatile__ (
 		"1:						\n\t"
-		"movli.l	@%1, %0	! __raw_write_lock	\n\t"
+		"movli.l	@%1, %0	! arch_write_lock	\n\t"
 		"cmp/hs		%2, %0				\n\t"
 		"bf		1b				\n\t"
 		"sub		%2, %0				\n\t"
@@ -160,23 +160,23 @@ static inline void __raw_write_lock(raw_rwlock_t *rw)
 	);
 }
 
-static inline void __raw_write_unlock(raw_rwlock_t *rw)
+static inline void arch_write_unlock(arch_rwlock_t *rw)
 {
 	__asm__ __volatile__ (
-		"mov.l		%1, @%0 ! __raw_write_unlock	\n\t"
+		"mov.l		%1, @%0 ! arch_write_unlock	\n\t"
 		:
 		: "r" (&rw->lock), "r" (RW_LOCK_BIAS)
 		: "t", "memory"
 	);
 }
 
-static inline int __raw_read_trylock(raw_rwlock_t *rw)
+static inline int arch_read_trylock(arch_rwlock_t *rw)
 {
 	unsigned long tmp, oldval;
 
 	__asm__ __volatile__ (
 		"1:						\n\t"
-		"movli.l	@%2, %0	! __raw_read_trylock	\n\t"
+		"movli.l	@%2, %0	! arch_read_trylock	\n\t"
 		"mov		%0, %1				\n\t"
 		"cmp/pl		%0				\n\t"
 		"bf		2f				\n\t"
@@ -193,13 +193,13 @@ static inline int __raw_read_trylock(raw_rwlock_t *rw)
 	return (oldval > 0);
 }
 
-static inline int __raw_write_trylock(raw_rwlock_t *rw)
+static inline int arch_write_trylock(arch_rwlock_t *rw)
 {
 	unsigned long tmp, oldval;
 
 	__asm__ __volatile__ (
 		"1:						\n\t"
-		"movli.l	@%2, %0	! __raw_write_trylock	\n\t"
+		"movli.l	@%2, %0	! arch_write_trylock	\n\t"
 		"mov		%0, %1				\n\t"
 		"cmp/hs		%3, %0				\n\t"
 		"bf		2f				\n\t"
@@ -216,11 +216,11 @@ static inline int __raw_write_trylock(raw_rwlock_t *rw)
 	return (oldval > (RW_LOCK_BIAS - 1));
 }
 
-#define __raw_read_lock_flags(lock, flags) __raw_read_lock(lock)
-#define __raw_write_lock_flags(lock, flags) __raw_write_lock(lock)
+#define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
+#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
 
-#define _raw_spin_relax(lock)	cpu_relax()
-#define _raw_read_relax(lock)	cpu_relax()
-#define _raw_write_relax(lock)	cpu_relax()
+#define arch_spin_relax(lock)	cpu_relax()
+#define arch_read_relax(lock)	cpu_relax()
+#define arch_write_relax(lock)	cpu_relax()
 
 #endif /* __ASM_SH_SPINLOCK_H */
diff --git a/arch/sh/include/asm/spinlock_types.h b/arch/sh/include/asm/spinlock_types.h
index b4d244e7b60c..9b7560db06ca 100644
--- a/arch/sh/include/asm/spinlock_types.h
+++ b/arch/sh/include/asm/spinlock_types.h
@@ -7,15 +7,15 @@
 
 typedef struct {
 	volatile unsigned int lock;
-} raw_spinlock_t;
+} arch_spinlock_t;
 
-#define __RAW_SPIN_LOCK_UNLOCKED		{ 1 }
+#define __ARCH_SPIN_LOCK_UNLOCKED		{ 1 }
 
 typedef struct {
 	volatile unsigned int lock;
-} raw_rwlock_t;
+} arch_rwlock_t;
 
 #define RW_LOCK_BIAS			0x01000000
-#define __RAW_RW_LOCK_UNLOCKED		{ RW_LOCK_BIAS }
+#define __ARCH_RW_LOCK_UNLOCKED		{ RW_LOCK_BIAS }
 
 #endif
diff --git a/arch/sh/include/asm/suspend.h b/arch/sh/include/asm/suspend.h
index 5c8ea28ff7a4..fe9c2a1ad047 100644
--- a/arch/sh/include/asm/suspend.h
+++ b/arch/sh/include/asm/suspend.h
@@ -2,6 +2,7 @@
 #define _ASM_SH_SUSPEND_H
 
 #ifndef __ASSEMBLY__
+#include <linux/notifier.h>
 static inline int arch_prepare_suspend(void) { return 0; }
 
 #include <asm/ptrace.h>
@@ -19,6 +20,69 @@ void sh_mobile_setup_cpuidle(void);
 static inline void sh_mobile_setup_cpuidle(void) {}
 #endif
 
+/* notifier chains for pre/post sleep hooks */
+extern struct atomic_notifier_head sh_mobile_pre_sleep_notifier_list;
+extern struct atomic_notifier_head sh_mobile_post_sleep_notifier_list;
+
+/* priority levels for notifiers */
+#define SH_MOBILE_SLEEP_BOARD	0
+#define SH_MOBILE_SLEEP_CPU	1
+#define SH_MOBILE_PRE(x)	(x)
+#define SH_MOBILE_POST(x)	(-(x))
+
+/* board code registration function for self-refresh assembly snippets */
+void sh_mobile_register_self_refresh(unsigned long flags,
+				     void *pre_start, void *pre_end,
+				     void *post_start, void *post_end);
+
+/* register structure for address/data information */
+struct sh_sleep_regs {
+	unsigned long stbcr;
+	unsigned long bar;
+
+	/* MMU */
+	unsigned long pteh;
+	unsigned long ptel;
+	unsigned long ttb;
+	unsigned long tea;
+	unsigned long mmucr;
+	unsigned long ptea;
+	unsigned long pascr;
+	unsigned long irmcr;
+
+	/* Cache */
+	unsigned long ccr;
+	unsigned long ramcr;
+};
+
+/* data area for low-level sleep code */
+struct sh_sleep_data {
+	/* current sleep mode (SUSP_SH_...) */
+	unsigned long mode;
+
+	/* addresses of board specific self-refresh snippets */
+	unsigned long sf_pre;
+	unsigned long sf_post;
+
+	/* address of resume code */
+	unsigned long resume;
+
+	/* register state saved and restored by the assembly code */
+	unsigned long vbr;
+	unsigned long spc;
+	unsigned long sr;
+	unsigned long sp;
+
+	/* structure for keeping register addresses */
+	struct sh_sleep_regs addr;
+
+	/* structure for saving/restoring register state */
+	struct sh_sleep_regs data;
+};
+
+/* a bitmap of supported sleep modes (SUSP_SH..) */
+extern unsigned long sh_mobile_sleep_supported;
+
 #endif
 
 /* flags passed to assembly suspend code */
@@ -27,5 +91,6 @@ static inline void sh_mobile_setup_cpuidle(void) {}
 #define SUSP_SH_RSTANDBY	(1 << 2) /* SH-Mobile R-standby mode */
 #define SUSP_SH_USTANDBY	(1 << 3) /* SH-Mobile U-standby mode */
 #define SUSP_SH_SF		(1 << 4) /* Enable self-refresh */
+#define SUSP_SH_MMU		(1 << 5) /* Save/restore MMU and cache */
 
 #endif /* _ASM_SH_SUSPEND_H */
diff --git a/arch/sh/include/asm/system.h b/arch/sh/include/asm/system.h
index b5c5acdc8c0e..c15415b4b169 100644
--- a/arch/sh/include/asm/system.h
+++ b/arch/sh/include/asm/system.h
@@ -171,10 +171,6 @@ BUILD_TRAP_HANDLER(fpu_error);
 BUILD_TRAP_HANDLER(fpu_state_restore);
 BUILD_TRAP_HANDLER(nmi);
 
-#ifdef CONFIG_BUG
-extern void handle_BUG(struct pt_regs *);
-#endif
-
 #define arch_align_stack(x) (x)
 
 struct mem_access {
diff --git a/arch/sh/include/asm/system_32.h b/arch/sh/include/asm/system_32.h
index 607d413f6168..06814f5b59c7 100644
--- a/arch/sh/include/asm/system_32.h
+++ b/arch/sh/include/asm/system_32.h
@@ -232,4 +232,33 @@ asmlinkage void do_exception_error(unsigned long r4, unsigned long r5,
 				   unsigned long r6, unsigned long r7,
 				   struct pt_regs __regs);
 
+static inline void set_bl_bit(void)
+{
+	unsigned long __dummy0, __dummy1;
+
+	__asm__ __volatile__ (
+		"stc	sr, %0\n\t"
+		"or	%2, %0\n\t"
+		"and	%3, %0\n\t"
+		"ldc	%0, sr\n\t"
+		: "=&r" (__dummy0), "=r" (__dummy1)
+		: "r" (0x10000000), "r" (0xffffff0f)
+		: "memory"
+	);
+}
+
+static inline void clear_bl_bit(void)
+{
+	unsigned long __dummy0, __dummy1;
+
+	__asm__ __volatile__ (
+		"stc	sr, %0\n\t"
+		"and	%2, %0\n\t"
+		"ldc	%0, sr\n\t"
+		: "=&r" (__dummy0), "=r" (__dummy1)
+		: "1" (~0x10000000)
+		: "memory"
+	);
+}
+
 #endif /* __ASM_SH_SYSTEM_32_H */
diff --git a/arch/sh/include/asm/system_64.h b/arch/sh/include/asm/system_64.h
index 8e4a03e7966c..ab1dd917ea87 100644
--- a/arch/sh/include/asm/system_64.h
+++ b/arch/sh/include/asm/system_64.h
@@ -12,6 +12,7 @@
  * License.  See the file "COPYING" in the main directory of this archive
  * for more details.
  */
+#include <cpu/registers.h>
 #include <asm/processor.h>
 
 /*
@@ -47,4 +48,29 @@ static inline reg_size_t register_align(void *val)
 	return (unsigned long long)(signed long long)(signed long)val;
 }
 
+#define SR_BL_LL	0x0000000010000000LL
+
+static inline void set_bl_bit(void)
+{
+	unsigned long long __dummy0, __dummy1 = SR_BL_LL;
+
+	__asm__ __volatile__("getcon	" __SR ", %0\n\t"
+			     "or	%0, %1, %0\n\t"
+			     "putcon	%0, " __SR "\n\t"
+			     : "=&r" (__dummy0)
+			     : "r" (__dummy1));
+
+}
+
+static inline void clear_bl_bit(void)
+{
+	unsigned long long __dummy0, __dummy1 = ~SR_BL_LL;
+
+	__asm__ __volatile__("getcon	" __SR ", %0\n\t"
+			     "and	%0, %1, %0\n\t"
+			     "putcon	%0, " __SR "\n\t"
+			     : "=&r" (__dummy0)
+			     : "r" (__dummy1));
+}
+
 #endif /* __ASM_SH_SYSTEM_64_H */
diff --git a/arch/sh/include/asm/thread_info.h b/arch/sh/include/asm/thread_info.h
index bdeb9d46d17d..1f3d927e2265 100644
--- a/arch/sh/include/asm/thread_info.h
+++ b/arch/sh/include/asm/thread_info.h
@@ -19,6 +19,7 @@ struct thread_info {
 	struct task_struct	*task;		/* main task structure */
 	struct exec_domain	*exec_domain;	/* execution domain */
 	unsigned long		flags;		/* low level flags */
+	__u32			status;		/* thread synchronous flags */
 	__u32			cpu;
 	int			preempt_count; /* 0 => preemptable, <0 => BUG */
 	mm_segment_t		addr_limit;	/* thread address space */
@@ -50,6 +51,7 @@ struct thread_info {
 	.task		= &tsk,			\
 	.exec_domain	= &default_exec_domain,	\
 	.flags		= 0,			\
+	.status		= 0,			\
 	.cpu		= 0,			\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
@@ -111,13 +113,11 @@ extern void free_thread_info(struct thread_info *ti);
 #define TIF_SYSCALL_TRACE	0	/* syscall trace active */
 #define TIF_SIGPENDING		1	/* signal pending */
 #define TIF_NEED_RESCHED	2	/* rescheduling necessary */
-#define TIF_RESTORE_SIGMASK	3	/* restore signal mask in do_signal() */
 #define TIF_SINGLESTEP		4	/* singlestepping active */
 #define TIF_SYSCALL_AUDIT	5	/* syscall auditing active */
 #define TIF_SECCOMP		6	/* secure computing */
 #define TIF_NOTIFY_RESUME	7	/* callback before returning to user */
 #define TIF_SYSCALL_TRACEPOINT	8	/* for ftrace syscall instrumentation */
-#define TIF_USEDFPU		16	/* FPU was used by this task this quantum (SMP) */
 #define TIF_POLLING_NRFLAG	17	/* true if poll_idle() is polling TIF_NEED_RESCHED */
 #define TIF_MEMDIE		18
 #define TIF_FREEZE		19	/* Freezing for suspend */
@@ -125,13 +125,11 @@ extern void free_thread_info(struct thread_info *ti);
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
-#define _TIF_RESTORE_SIGMASK	(1 << TIF_RESTORE_SIGMASK)
 #define _TIF_SINGLESTEP		(1 << TIF_SINGLESTEP)
 #define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
 #define _TIF_SECCOMP		(1 << TIF_SECCOMP)
 #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
 #define _TIF_SYSCALL_TRACEPOINT	(1 << TIF_SYSCALL_TRACEPOINT)
-#define _TIF_USEDFPU		(1 << TIF_USEDFPU)
 #define _TIF_POLLING_NRFLAG	(1 << TIF_POLLING_NRFLAG)
 #define _TIF_FREEZE		(1 << TIF_FREEZE)
 
@@ -149,13 +147,33 @@ extern void free_thread_info(struct thread_info *ti);
 /* work to do on any return to u-space */
 #define _TIF_ALLWORK_MASK	(_TIF_SYSCALL_TRACE | _TIF_SIGPENDING      | \
 				 _TIF_NEED_RESCHED  | _TIF_SYSCALL_AUDIT   | \
-				 _TIF_SINGLESTEP    | _TIF_RESTORE_SIGMASK | \
-				 _TIF_NOTIFY_RESUME | _TIF_SYSCALL_TRACEPOINT)
+				 _TIF_SINGLESTEP    | _TIF_NOTIFY_RESUME   | \
+				 _TIF_SYSCALL_TRACEPOINT)
 
 /* work to do on interrupt/exception return */
 #define _TIF_WORK_MASK		(_TIF_ALLWORK_MASK & ~(_TIF_SYSCALL_TRACE | \
 				 _TIF_SYSCALL_AUDIT | _TIF_SINGLESTEP))
 
+/*
+ * Thread-synchronous status.
+ *
+ * This is different from the flags in that nobody else
+ * ever touches our thread-synchronous status, so we don't
+ * have to worry about atomic accesses.
+ */
+#define TS_RESTORE_SIGMASK	0x0001	/* restore signal mask in do_signal() */
+#define TS_USEDFPU		0x0002	/* FPU used by this task this quantum */
+
+#ifndef __ASSEMBLY__
+#define HAVE_SET_RESTORE_SIGMASK	1
+static inline void set_restore_sigmask(void)
+{
+	struct thread_info *ti = current_thread_info();
+	ti->status |= TS_RESTORE_SIGMASK;
+	set_bit(TIF_SIGPENDING, (unsigned long *)&ti->flags);
+}
+#endif	/* !__ASSEMBLY__ */
+
 #endif /* __KERNEL__ */
 
 #endif /* __ASM_SH_THREAD_INFO_H */
diff --git a/arch/sh/include/asm/timex.h b/arch/sh/include/asm/timex.h
index b556d49e5f2b..18bf06d9c764 100644
--- a/arch/sh/include/asm/timex.h
+++ b/arch/sh/include/asm/timex.h
@@ -6,7 +6,17 @@
 #ifndef __ASM_SH_TIMEX_H
 #define __ASM_SH_TIMEX_H
 
+/*
+ * Only parts using the legacy CPG code for their clock framework
+ * implementation need to define their own Pclk value. If provided, this
+ * can be used for accurately setting CLOCK_TICK_RATE, otherwise we
+ * simply fall back on the i8253 PIT value.
+ */
+#ifdef CONFIG_SH_PCLK_FREQ
 #define CLOCK_TICK_RATE		(CONFIG_SH_PCLK_FREQ / 4) /* Underlying HZ */
+#else
+#define CLOCK_TICK_RATE		1193180
+#endif
 
 #include <asm-generic/timex.h>
 
diff --git a/arch/sh/include/asm/topology.h b/arch/sh/include/asm/topology.h
index 65e7bd2f2240..37cdadd975ac 100644
--- a/arch/sh/include/asm/topology.h
+++ b/arch/sh/include/asm/topology.h
@@ -40,6 +40,14 @@
 
 #endif
 
+#define mc_capable()    (1)
+
+const struct cpumask *cpu_coregroup_mask(unsigned int cpu);
+
+extern cpumask_t cpu_core_map[NR_CPUS];
+
+#define topology_core_cpumask(cpu)	(&cpu_core_map[cpu])
+
 #include <asm-generic/topology.h>
 
 #endif /* _ASM_SH_TOPOLOGY_H */
diff --git a/arch/sh/include/asm/ubc.h b/arch/sh/include/asm/ubc.h
index 4ca4b7717371..9bf961684431 100644
--- a/arch/sh/include/asm/ubc.h
+++ b/arch/sh/include/asm/ubc.h
@@ -60,16 +60,5 @@
 #define BRCR_UBDE		(1 << 0)
 #endif
 
-#ifndef __ASSEMBLY__
-/* arch/sh/kernel/cpu/ubc.S */
-extern void ubc_sleep(void);
-
-#ifdef CONFIG_UBC_WAKEUP
-extern void ubc_wakeup(void);
-#else
-#define ubc_wakeup()	do { } while (0)
-#endif
-#endif
-
 #endif /* __KERNEL__ */
 #endif /* __ASM_SH_UBC_H */
diff --git a/arch/sh/include/asm/unistd_32.h b/arch/sh/include/asm/unistd_32.h
index f3fd1b9eb6b1..f18c4f9baf27 100644
--- a/arch/sh/include/asm/unistd_32.h
+++ b/arch/sh/include/asm/unistd_32.h
@@ -345,8 +345,9 @@
 #define __NR_pwritev		334
 #define __NR_rt_tgsigqueueinfo	335
 #define __NR_perf_event_open	336
+#define __NR_recvmmsg		337
 
-#define NR_syscalls 337
+#define NR_syscalls 338
 
 #ifdef __KERNEL__
 
diff --git a/arch/sh/include/asm/unistd_64.h b/arch/sh/include/asm/unistd_64.h
index 343ce8f073ea..3e7645d11130 100644
--- a/arch/sh/include/asm/unistd_64.h
+++ b/arch/sh/include/asm/unistd_64.h
@@ -385,10 +385,11 @@
 #define __NR_pwritev		362
 #define __NR_rt_tgsigqueueinfo	363
 #define __NR_perf_event_open	364
+#define __NR_recvmmsg		365
 
 #ifdef __KERNEL__
 
-#define NR_syscalls 365
+#define NR_syscalls 366
 
 #define __ARCH_WANT_IPC_PARSE_VERSION
 #define __ARCH_WANT_OLD_READDIR
diff --git a/arch/sh/include/asm/watchdog.h b/arch/sh/include/asm/watchdog.h
index 2fe7cee9e43a..19dfff5c8511 100644
--- a/arch/sh/include/asm/watchdog.h
+++ b/arch/sh/include/asm/watchdog.h
@@ -2,6 +2,8 @@
  * include/asm-sh/watchdog.h
  *
  * Copyright (C) 2002, 2003 Paul Mundt
+ * Copyright (C) 2009 Siemens AG
+ * Copyright (C) 2009 Valentin Sitdikov
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License as published by the
@@ -61,6 +63,61 @@
 #define WTCSR_CKS_2048	0x06
 #define WTCSR_CKS_4096	0x07
 
+#if defined(CONFIG_CPU_SUBTYPE_SH7785) || defined(CONFIG_CPU_SUBTYPE_SH7780)
+/**
+ * 	sh_wdt_read_cnt - Read from Counter
+ * 	Reads back the WTCNT value.
+ */
+static inline __u32 sh_wdt_read_cnt(void)
+{
+	return ctrl_inl(WTCNT_R);
+}
+
+/**
+ *	sh_wdt_write_cnt - Write to Counter
+ *	@val: Value to write
+ *
+ *	Writes the given value @val to the lower byte of the timer counter.
+ *	The upper byte is set manually on each write.
+ */
+static inline void sh_wdt_write_cnt(__u32 val)
+{
+	ctrl_outl((WTCNT_HIGH << 24) | (__u32)val, WTCNT);
+}
+
+/**
+ *	sh_wdt_write_bst - Write to Counter
+ *	@val: Value to write
+ *
+ *	Writes the given value @val to the lower byte of the timer counter.
+ *	The upper byte is set manually on each write.
+ */
+static inline void sh_wdt_write_bst(__u32 val)
+{
+	ctrl_outl((WTBST_HIGH << 24) | (__u32)val, WTBST);
+}
+/**
+ * 	sh_wdt_read_csr - Read from Control/Status Register
+ *
+ *	Reads back the WTCSR value.
+ */
+static inline __u32 sh_wdt_read_csr(void)
+{
+	return ctrl_inl(WTCSR_R);
+}
+
+/**
+ * 	sh_wdt_write_csr - Write to Control/Status Register
+ * 	@val: Value to write
+ *
+ * 	Writes the given value @val to the lower byte of the control/status
+ * 	register. The upper byte is set manually on each write.
+ */
+static inline void sh_wdt_write_csr(__u32 val)
+{
+	ctrl_outl((WTCSR_HIGH << 24) | (__u32)val, WTCSR);
+}
+#else
 /**
  * 	sh_wdt_read_cnt - Read from Counter
  * 	Reads back the WTCNT value.
@@ -103,6 +160,6 @@ static inline void sh_wdt_write_csr(__u8 val)
 {
 	ctrl_outw((WTCSR_HIGH << 8) | (__u16)val, WTCSR);
 }
-
+#endif /* CONFIG_CPU_SUBTYPE_SH7785 || CONFIG_CPU_SUBTYPE_SH7780 */
 #endif /* __KERNEL__ */
 #endif /* __ASM_SH_WATCHDOG_H */