Merge branch 'master' into next

24 files changed, 400 insertions, 136 deletions

diff --git a/arch/sh/include/asm/addrspace.h b/arch/sh/include/asm/addrspace.h
index 36736c7e93db..80d40813e057 100644
--- a/arch/sh/include/asm/addrspace.h
+++ b/arch/sh/include/asm/addrspace.h
@@ -31,7 +31,7 @@
 /* Returns the physical address of a PnSEG (n=1,2) address   */
 #define PHYSADDR(a)	(((unsigned long)(a)) & 0x1fffffff)
 
-#ifdef CONFIG_29BIT
+#if defined(CONFIG_29BIT) || defined(CONFIG_PMB_FIXED)
 /*
  * Map an address to a certain privileged segment
  */
@@ -43,7 +43,7 @@
 	((__typeof__(a))(((unsigned long)(a) & 0x1fffffff) | P3SEG))
 #define P4SEGADDR(a)	\
 	((__typeof__(a))(((unsigned long)(a) & 0x1fffffff) | P4SEG))
-#endif /* 29BIT */
+#endif /* 29BIT || PMB_FIXED */
 #endif /* P1SEG */
 
 /* Check if an address can be reached in 29 bits */
diff --git a/arch/sh/include/asm/atomic-irq.h b/arch/sh/include/asm/atomic-irq.h
index 74f7943cff6f..a0b348068cae 100644
--- a/arch/sh/include/asm/atomic-irq.h
+++ b/arch/sh/include/asm/atomic-irq.h
@@ -11,7 +11,7 @@ static inline void atomic_add(int i, atomic_t *v)
 	unsigned long flags;
 
 	local_irq_save(flags);
-	*(long *)v += i;
+	v->counter += i;
 	local_irq_restore(flags);
 }
 
@@ -20,7 +20,7 @@ static inline void atomic_sub(int i, atomic_t *v)
 	unsigned long flags;
 
 	local_irq_save(flags);
-	*(long *)v -= i;
+	v->counter -= i;
 	local_irq_restore(flags);
 }
 
@@ -29,9 +29,9 @@ static inline int atomic_add_return(int i, atomic_t *v)
 	unsigned long temp, flags;
 
 	local_irq_save(flags);
-	temp = *(long *)v;
+	temp = v->counter;
 	temp += i;
-	*(long *)v = temp;
+	v->counter = temp;
 	local_irq_restore(flags);
 
 	return temp;
@@ -42,9 +42,9 @@ static inline int atomic_sub_return(int i, atomic_t *v)
 	unsigned long temp, flags;
 
 	local_irq_save(flags);
-	temp = *(long *)v;
+	temp = v->counter;
 	temp -= i;
-	*(long *)v = temp;
+	v->counter = temp;
 	local_irq_restore(flags);
 
 	return temp;
@@ -55,7 +55,7 @@ static inline void atomic_clear_mask(unsigned int mask, atomic_t *v)
 	unsigned long flags;
 
 	local_irq_save(flags);
-	*(long *)v &= ~mask;
+	v->counter &= ~mask;
 	local_irq_restore(flags);
 }
 
@@ -64,7 +64,7 @@ static inline void atomic_set_mask(unsigned int mask, atomic_t *v)
 	unsigned long flags;
 
 	local_irq_save(flags);
-	*(long *)v |= mask;
+	v->counter |= mask;
 	local_irq_restore(flags);
 }
 
diff --git a/arch/sh/include/asm/bitops-llsc.h b/arch/sh/include/asm/bitops-llsc.h
index 1d2fc0b010ad..d8328be06191 100644
--- a/arch/sh/include/asm/bitops-llsc.h
+++ b/arch/sh/include/asm/bitops-llsc.h
@@ -1,7 +1,7 @@
 #ifndef __ASM_SH_BITOPS_LLSC_H
 #define __ASM_SH_BITOPS_LLSC_H
 
-static inline void set_bit(int nr, volatile void * addr)
+static inline void set_bit(int nr, volatile void *addr)
 {
 	int	mask;
 	volatile unsigned int *a = addr;
@@ -13,16 +13,16 @@ static inline void set_bit(int nr, volatile void * addr)
 	__asm__ __volatile__ (
 		"1:						\n\t"
 		"movli.l	@%1, %0	! set_bit		\n\t"
-		"or		%3, %0				\n\t"
+		"or		%2, %0				\n\t"
 		"movco.l	%0, @%1				\n\t"
 		"bf		1b				\n\t"
-		: "=&z" (tmp), "=r" (a)
-		: "1" (a), "r" (mask)
+		: "=&z" (tmp)
+		: "r" (a), "r" (mask)
 		: "t", "memory"
 	);
 }
 
-static inline void clear_bit(int nr, volatile void * addr)
+static inline void clear_bit(int nr, volatile void *addr)
 {
 	int	mask;
 	volatile unsigned int *a = addr;
@@ -34,16 +34,16 @@ static inline void clear_bit(int nr, volatile void * addr)
 	__asm__ __volatile__ (
 		"1:						\n\t"
 		"movli.l	@%1, %0	! clear_bit		\n\t"
-		"and		%3, %0				\n\t"
+		"and		%2, %0				\n\t"
 		"movco.l	%0, @%1				\n\t"
 		"bf		1b				\n\t"
-		: "=&z" (tmp), "=r" (a)
-		: "1" (a), "r" (~mask)
+		: "=&z" (tmp)
+		: "r" (a), "r" (~mask)
 		: "t", "memory"
 	);
 }
 
-static inline void change_bit(int nr, volatile void * addr)
+static inline void change_bit(int nr, volatile void *addr)
 {
 	int	mask;
 	volatile unsigned int *a = addr;
@@ -55,16 +55,16 @@ static inline void change_bit(int nr, volatile void * addr)
 	__asm__ __volatile__ (
 		"1:						\n\t"
 		"movli.l	@%1, %0	! change_bit		\n\t"
-		"xor		%3, %0				\n\t"
+		"xor		%2, %0				\n\t"
 		"movco.l	%0, @%1				\n\t"
 		"bf		1b				\n\t"
-		: "=&z" (tmp), "=r" (a)
-		: "1" (a), "r" (mask)
+		: "=&z" (tmp)
+		: "r" (a), "r" (mask)
 		: "t", "memory"
 	);
 }
 
-static inline int test_and_set_bit(int nr, volatile void * addr)
+static inline int test_and_set_bit(int nr, volatile void *addr)
 {
 	int	mask, retval;
 	volatile unsigned int *a = addr;
@@ -75,21 +75,21 @@ static inline int test_and_set_bit(int nr, volatile void * addr)
 
 	__asm__ __volatile__ (
 		"1:						\n\t"
-		"movli.l	@%1, %0	! test_and_set_bit	\n\t"
-		"mov		%0, %2				\n\t"
-		"or		%4, %0				\n\t"
-		"movco.l	%0, @%1				\n\t"
+		"movli.l	@%2, %0	! test_and_set_bit	\n\t"
+		"mov		%0, %1				\n\t"
+		"or		%3, %0				\n\t"
+		"movco.l	%0, @%2				\n\t"
 		"bf		1b				\n\t"
-		"and		%4, %2				\n\t"
-		: "=&z" (tmp), "=r" (a), "=&r" (retval)
-		: "1" (a), "r" (mask)
+		"and		%3, %1				\n\t"
+		: "=&z" (tmp), "=&r" (retval)
+		: "r" (a), "r" (mask)
 		: "t", "memory"
 	);
 
 	return retval != 0;
 }
 
-static inline int test_and_clear_bit(int nr, volatile void * addr)
+static inline int test_and_clear_bit(int nr, volatile void *addr)
 {
 	int	mask, retval;
 	volatile unsigned int *a = addr;
@@ -100,22 +100,22 @@ static inline int test_and_clear_bit(int nr, volatile void * addr)
 
 	__asm__ __volatile__ (
 		"1:						\n\t"
-		"movli.l	@%1, %0	! test_and_clear_bit	\n\t"
-		"mov		%0, %2				\n\t"
-		"and		%5, %0				\n\t"
-		"movco.l	%0, @%1				\n\t"
+		"movli.l	@%2, %0	! test_and_clear_bit	\n\t"
+		"mov		%0, %1				\n\t"
+		"and		%4, %0				\n\t"
+		"movco.l	%0, @%2				\n\t"
 		"bf		1b				\n\t"
-		"and		%4, %2				\n\t"
+		"and		%3, %1				\n\t"
 		"synco						\n\t"
-		: "=&z" (tmp), "=r" (a), "=&r" (retval)
-		: "1" (a), "r" (mask), "r" (~mask)
+		: "=&z" (tmp), "=&r" (retval)
+		: "r" (a), "r" (mask), "r" (~mask)
 		: "t", "memory"
 	);
 
 	return retval != 0;
 }
 
-static inline int test_and_change_bit(int nr, volatile void * addr)
+static inline int test_and_change_bit(int nr, volatile void *addr)
 {
 	int	mask, retval;
 	volatile unsigned int *a = addr;
@@ -126,15 +126,15 @@ static inline int test_and_change_bit(int nr, volatile void * addr)
 
 	__asm__ __volatile__ (
 		"1:						\n\t"
-		"movli.l	@%1, %0	! test_and_change_bit	\n\t"
-		"mov		%0, %2				\n\t"
-		"xor		%4, %0				\n\t"
-		"movco.l	%0, @%1				\n\t"
+		"movli.l	@%2, %0	! test_and_change_bit	\n\t"
+		"mov		%0, %1				\n\t"
+		"xor		%3, %0				\n\t"
+		"movco.l	%0, @%2				\n\t"
 		"bf		1b				\n\t"
-		"and		%4, %2				\n\t"
+		"and		%3, %1				\n\t"
 		"synco						\n\t"
-		: "=&z" (tmp), "=r" (a), "=&r" (retval)
-		: "1" (a), "r" (mask)
+		: "=&z" (tmp), "=&r" (retval)
+		: "r" (a), "r" (mask)
 		: "t", "memory"
 	);
 
diff --git a/arch/sh/include/asm/clock.h b/arch/sh/include/asm/clock.h
index f9c88583d90a..2f6c9627bc1f 100644
--- a/arch/sh/include/asm/clock.h
+++ b/arch/sh/include/asm/clock.h
@@ -15,6 +15,7 @@ struct clk_ops {
 	void (*disable)(struct clk *clk);
 	void (*recalc)(struct clk *clk);
 	int (*set_rate)(struct clk *clk, unsigned long rate, int algo_id);
+	int (*set_parent)(struct clk *clk, struct clk *parent);
 	long (*round_rate)(struct clk *clk, unsigned long rate);
 };
 
diff --git a/arch/sh/include/asm/cmpxchg-llsc.h b/arch/sh/include/asm/cmpxchg-llsc.h
index aee3bf286581..0fac3da536ca 100644
--- a/arch/sh/include/asm/cmpxchg-llsc.h
+++ b/arch/sh/include/asm/cmpxchg-llsc.h
@@ -8,14 +8,14 @@ static inline unsigned long xchg_u32(volatile u32 *m, unsigned long val)
 
 	__asm__ __volatile__ (
 		"1:					\n\t"
-		"movli.l	@%1, %0	! xchg_u32	\n\t"
-		"mov		%0, %2			\n\t"
-		"mov		%4, %0			\n\t"
-		"movco.l	%0, @%1			\n\t"
+		"movli.l	@%2, %0	! xchg_u32	\n\t"
+		"mov		%0, %1			\n\t"
+		"mov		%3, %0			\n\t"
+		"movco.l	%0, @%2			\n\t"
 		"bf		1b			\n\t"
 		"synco					\n\t"
-		: "=&z"(tmp), "=r" (m), "=&r" (retval)
-		: "1" (m), "r" (val)
+		: "=&z"(tmp), "=&r" (retval)
+		: "r" (m), "r" (val)
 		: "t", "memory"
 	);
 
@@ -29,14 +29,14 @@ static inline unsigned long xchg_u8(volatile u8 *m, unsigned long val)
 
 	__asm__ __volatile__ (
 		"1:					\n\t"
-		"movli.l	@%1, %0	! xchg_u8	\n\t"
-		"mov		%0, %2			\n\t"
-		"mov		%4, %0			\n\t"
-		"movco.l	%0, @%1			\n\t"
+		"movli.l	@%2, %0	! xchg_u8	\n\t"
+		"mov		%0, %1			\n\t"
+		"mov		%3, %0			\n\t"
+		"movco.l	%0, @%2			\n\t"
 		"bf		1b			\n\t"
 		"synco					\n\t"
-		: "=&z"(tmp), "=r" (m), "=&r" (retval)
-		: "1" (m), "r" (val & 0xff)
+		: "=&z"(tmp), "=&r" (retval)
+		: "r" (m), "r" (val & 0xff)
 		: "t", "memory"
 	);
 
@@ -51,17 +51,17 @@ __cmpxchg_u32(volatile int *m, unsigned long old, unsigned long new)
 
 	__asm__ __volatile__ (
 		"1:						\n\t"
-		"movli.l	@%1, %0	! __cmpxchg_u32		\n\t"
-		"mov		%0, %2				\n\t"
-		"cmp/eq		%2, %4				\n\t"
+		"movli.l	@%2, %0	! __cmpxchg_u32		\n\t"
+		"mov		%0, %1				\n\t"
+		"cmp/eq		%1, %3				\n\t"
 		"bf		2f				\n\t"
-		"mov		%5, %0				\n\t"
+		"mov		%3, %0				\n\t"
 		"2:						\n\t"
-		"movco.l	%0, @%1				\n\t"
+		"movco.l	%0, @%2				\n\t"
 		"bf		1b				\n\t"
 		"synco						\n\t"
-		: "=&z" (tmp), "=r" (m), "=&r" (retval)
-		: "1" (m), "r" (old), "r" (new)
+		: "=&z" (tmp), "=&r" (retval)
+		: "r" (m), "r" (old), "r" (new)
 		: "t", "memory"
 	);
 
diff --git a/arch/sh/include/asm/cpu-features.h b/arch/sh/include/asm/cpu-features.h
index 86308aa39731..694abe490edb 100644
--- a/arch/sh/include/asm/cpu-features.h
+++ b/arch/sh/include/asm/cpu-features.h
@@ -21,5 +21,6 @@
 #define CPU_HAS_LLSC		0x0040	/* movli.l/movco.l */
 #define CPU_HAS_L2_CACHE	0x0080	/* Secondary cache / URAM */
 #define CPU_HAS_OP32		0x0100	/* 32-bit instruction support */
+#define CPU_HAS_PTEAEX		0x0200	/* PTE ASID Extension support */
 
 #endif /* __ASM_SH_CPU_FEATURES_H */
diff --git a/arch/sh/include/asm/dma-sh.h b/arch/sh/include/asm/dma-sh.h
new file mode 100644
index 000000000000..0c8f8e14622a
--- /dev/null
+++ b/arch/sh/include/asm/dma-sh.h
@@ -0,0 +1,118 @@
+/*
+ * arch/sh/include/asm/dma-sh.h
+ *
+ * Copyright (C) 2000  Takashi YOSHII
+ * Copyright (C) 2003  Paul Mundt
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#ifndef __DMA_SH_H
+#define __DMA_SH_H
+
+#include <asm/dma.h>
+#include <cpu/dma.h>
+
+/* DMAOR contorl: The DMAOR access size is different by CPU.*/
+#if defined(CONFIG_CPU_SUBTYPE_SH7723)	|| \
+    defined(CONFIG_CPU_SUBTYPE_SH7780)	|| \
+    defined(CONFIG_CPU_SUBTYPE_SH7785)
+#define dmaor_read_reg(n) \
+    (n ? ctrl_inw(SH_DMAC_BASE1 + DMAOR) \
+	: ctrl_inw(SH_DMAC_BASE0 + DMAOR))
+#define dmaor_write_reg(n, data) \
+    (n ? ctrl_outw(data, SH_DMAC_BASE1 + DMAOR) \
+    : ctrl_outw(data, SH_DMAC_BASE0 + DMAOR))
+#else /* Other CPU */
+#define dmaor_read_reg(n) ctrl_inw(SH_DMAC_BASE0 + DMAOR)
+#define dmaor_write_reg(n, data) ctrl_outw(data, SH_DMAC_BASE0 + DMAOR)
+#endif
+
+static int dmte_irq_map[] __maybe_unused = {
+#if (MAX_DMA_CHANNELS >= 4)
+    DMTE0_IRQ,
+    DMTE0_IRQ + 1,
+    DMTE0_IRQ + 2,
+    DMTE0_IRQ + 3,
+#endif
+#if (MAX_DMA_CHANNELS >= 6)
+    DMTE4_IRQ,
+    DMTE4_IRQ + 1,
+#endif
+#if (MAX_DMA_CHANNELS >= 8)
+    DMTE6_IRQ,
+    DMTE6_IRQ + 1,
+#endif
+#if (MAX_DMA_CHANNELS >= 12)
+    DMTE8_IRQ,
+    DMTE9_IRQ,
+    DMTE10_IRQ,
+    DMTE11_IRQ,
+#endif
+};
+
+/* Definitions for the SuperH DMAC */
+#define REQ_L	0x00000000
+#define REQ_E	0x00080000
+#define RACK_H	0x00000000
+#define RACK_L	0x00040000
+#define ACK_R	0x00000000
+#define ACK_W	0x00020000
+#define ACK_H	0x00000000
+#define ACK_L	0x00010000
+#define DM_INC	0x00004000
+#define DM_DEC	0x00008000
+#define SM_INC	0x00001000
+#define SM_DEC	0x00002000
+#define RS_IN	0x00000200
+#define RS_OUT	0x00000300
+#define TS_BLK	0x00000040
+#define TM_BUR	0x00000020
+#define CHCR_DE 0x00000001
+#define CHCR_TE 0x00000002
+#define CHCR_IE 0x00000004
+
+/* DMAOR definitions */
+#define DMAOR_AE	0x00000004
+#define DMAOR_NMIF	0x00000002
+#define DMAOR_DME	0x00000001
+
+/*
+ * Define the default configuration for dual address memory-memory transfer.
+ * The 0x400 value represents auto-request, external->external.
+ */
+#define RS_DUAL	(DM_INC | SM_INC | 0x400 | TS_32)
+
+/* DMA base address */
+static u32 dma_base_addr[] __maybe_unused = {
+#if (MAX_DMA_CHANNELS >= 4)
+	SH_DMAC_BASE0 + 0x00,	/* channel 0 */
+	SH_DMAC_BASE0 + 0x10,
+	SH_DMAC_BASE0 + 0x20,
+	SH_DMAC_BASE0 + 0x30,
+#endif
+#if (MAX_DMA_CHANNELS >= 6)
+	SH_DMAC_BASE0 + 0x50,
+	SH_DMAC_BASE0 + 0x60,
+#endif
+#if (MAX_DMA_CHANNELS >= 8)
+	SH_DMAC_BASE1 + 0x00,
+	SH_DMAC_BASE1 + 0x10,
+#endif
+#if (MAX_DMA_CHANNELS >= 12)
+	SH_DMAC_BASE1 + 0x20,
+	SH_DMAC_BASE1 + 0x30,
+	SH_DMAC_BASE1 + 0x50,
+	SH_DMAC_BASE1 + 0x60, /* channel 11 */
+#endif
+};
+
+/* DMA register */
+#define SAR     0x00
+#define DAR     0x04
+#define TCR     0x08
+#define CHCR    0x0C
+#define DMAOR	0x40
+
+#endif /* __DMA_SH_H */
diff --git a/arch/sh/include/asm/dma.h b/arch/sh/include/asm/dma.h
index beca7128e2ab..6bd178473878 100644
--- a/arch/sh/include/asm/dma.h
+++ b/arch/sh/include/asm/dma.h
@@ -25,9 +25,9 @@
 #define MAX_DMA_ADDRESS		(PAGE_OFFSET+0x10000000)
 
 #ifdef CONFIG_NR_DMA_CHANNELS
-#  define MAX_DMA_CHANNELS	(CONFIG_NR_DMA_CHANNELS)
+#  define MAX_DMA_CHANNELS   (CONFIG_NR_DMA_CHANNELS)
 #else
-#  define MAX_DMA_CHANNELS	(CONFIG_NR_ONCHIP_DMA_CHANNELS)
+#  define MAX_DMA_CHANNELS   (CONFIG_NR_ONCHIP_DMA_CHANNELS)
 #endif
 
 /*
diff --git a/arch/sh/include/asm/entry-macros.S b/arch/sh/include/asm/entry-macros.S
index 2dab0b8d9454..3a4752a65722 100644
--- a/arch/sh/include/asm/entry-macros.S
+++ b/arch/sh/include/asm/entry-macros.S
@@ -31,3 +31,8 @@
 #endif	
 	.endm
 
+#if defined(CONFIG_CPU_SH2A) || defined(CONFIG_CPU_SH4)
+# define PREF(x)	pref	@x
+#else
+# define PREF(x)	nop
+#endif
diff --git a/arch/sh/include/asm/gpio.h b/arch/sh/include/asm/gpio.h
index 90673658eb14..61f93da2c62e 100644
--- a/arch/sh/include/asm/gpio.h
+++ b/arch/sh/include/asm/gpio.h
@@ -19,8 +19,42 @@
 #include <cpu/gpio.h>
 #endif
 
+#define ARCH_NR_GPIOS 512
+#include <asm-generic/gpio.h>
+
+#ifdef CONFIG_GPIOLIB
+
+static inline int gpio_get_value(unsigned gpio)
+{
+	return __gpio_get_value(gpio);
+}
+
+static inline void gpio_set_value(unsigned gpio, int value)
+{
+	__gpio_set_value(gpio, value);
+}
+
+static inline int gpio_cansleep(unsigned gpio)
+{
+	return __gpio_cansleep(gpio);
+}
+
+static inline int gpio_to_irq(unsigned gpio)
+{
+	WARN_ON(1);
+	return -ENOSYS;
+}
+
+static inline int irq_to_gpio(unsigned int irq)
+{
+	WARN_ON(1);
+	return -EINVAL;
+}
+
+#endif /* CONFIG_GPIOLIB */
+
 typedef unsigned short pinmux_enum_t;
-typedef unsigned char pinmux_flag_t;
+typedef unsigned short pinmux_flag_t;
 
 #define PINMUX_TYPE_NONE            0
 #define PINMUX_TYPE_FUNCTION        1
@@ -34,6 +68,11 @@ typedef unsigned char pinmux_flag_t;
 #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;
@@ -54,7 +93,7 @@ struct pinmux_cfg_reg {
 	.enum_ids = (pinmux_enum_t [(r_width / f_width) * (1 << f_width)]) \
 
 struct pinmux_data_reg {
-	unsigned long reg, reg_width;
+	unsigned long reg, reg_width, reg_shadow;
 	pinmux_enum_t *enum_ids;
 };
 
@@ -89,34 +128,9 @@ struct pinmux_info {
 	unsigned int gpio_data_size;
 
 	unsigned long *gpio_in_use;
+	struct gpio_chip chip;
 };
 
 int register_pinmux(struct pinmux_info *pip);
 
-int __gpio_request(unsigned gpio);
-static inline int gpio_request(unsigned gpio, const char *label)
-{
-	return __gpio_request(gpio);
-}
-void gpio_free(unsigned gpio);
-int gpio_direction_input(unsigned gpio);
-int gpio_direction_output(unsigned gpio, int value);
-int gpio_get_value(unsigned gpio);
-void gpio_set_value(unsigned gpio, int value);
-
-/* IRQ modes are unspported */
-static inline int gpio_to_irq(unsigned gpio)
-{
-	WARN_ON(1);
-	return -EINVAL;
-}
-
-static inline int irq_to_gpio(unsigned irq)
-{
-	WARN_ON(1);
-	return -EINVAL;
-}
-
-#include <asm-generic/gpio.h>
-
 #endif /* __ASM_SH_GPIO_H */
diff --git a/arch/sh/include/asm/hd64461.h b/arch/sh/include/asm/hd64461.h
index 8c1353baf00f..52b4b6238277 100644
--- a/arch/sh/include/asm/hd64461.h
+++ b/arch/sh/include/asm/hd64461.h
@@ -242,7 +242,6 @@
 #include <asm/io_generic.h>
 
 /* arch/sh/cchips/hd6446x/hd64461/setup.c */
-int hd64461_irq_demux(int irq);
 void hd64461_register_irq_demux(int irq,
 				int (*demux) (int irq, void *dev), void *dev);
 void hd64461_unregister_irq_demux(int irq);
diff --git a/arch/sh/include/asm/io.h b/arch/sh/include/asm/io.h
index 61f6dae40534..0454f8d68059 100644
--- a/arch/sh/include/asm/io.h
+++ b/arch/sh/include/asm/io.h
@@ -238,7 +238,7 @@ extern void onchip_unmap(unsigned long vaddr);
 static inline void __iomem *
 __ioremap_mode(unsigned long offset, unsigned long size, unsigned long flags)
 {
-#ifdef CONFIG_SUPERH32
+#if defined(CONFIG_SUPERH32) && !defined(CONFIG_PMB_FIXED)
 	unsigned long last_addr = offset + size - 1;
 #endif
 	void __iomem *ret;
@@ -247,7 +247,7 @@ __ioremap_mode(unsigned long offset, unsigned long size, unsigned long flags)
 	if (ret)
 		return ret;
 
-#ifdef CONFIG_SUPERH32
+#if defined(CONFIG_SUPERH32) && !defined(CONFIG_PMB_FIXED)
 	/*
 	 * For P1 and P2 space this is trivial, as everything is already
 	 * mapped. Uncached access for P1 addresses are done through P2.
diff --git a/arch/sh/include/asm/kprobes.h b/arch/sh/include/asm/kprobes.h
index 6078d8e551d4..613644a758e8 100644
--- a/arch/sh/include/asm/kprobes.h
+++ b/arch/sh/include/asm/kprobes.h
@@ -16,7 +16,7 @@ typedef u16 kprobe_opcode_t;
 	? (MAX_STACK_SIZE) \
 	: (((unsigned long)current_thread_info()) + THREAD_SIZE - (ADDR)))
 
-#define regs_return_value(regs)		((regs)->regs[0])
+#define regs_return_value(_regs)		((_regs)->regs[0])
 #define flush_insn_slot(p)		do { } while (0)
 #define kretprobe_blacklist_size	0
 
diff --git a/arch/sh/include/asm/mmu_context.h b/arch/sh/include/asm/mmu_context.h
index 5d9157bd474d..2a9c55f1a83f 100644
--- a/arch/sh/include/asm/mmu_context.h
+++ b/arch/sh/include/asm/mmu_context.h
@@ -19,13 +19,18 @@
  *    (a) TLB cache version (or round, cycle whatever expression you like)
  *    (b) ASID (Address Space IDentifier)
  */
+#ifdef CONFIG_CPU_HAS_PTEAEX
+#define MMU_CONTEXT_ASID_MASK		0x0000ffff
+#else
 #define MMU_CONTEXT_ASID_MASK		0x000000ff
-#define MMU_CONTEXT_VERSION_MASK	0xffffff00
-#define MMU_CONTEXT_FIRST_VERSION	0x00000100
-#define NO_CONTEXT			0UL
+#endif
 
-/* ASID is 8-bit value, so it can't be 0x100 */
-#define MMU_NO_ASID			0x100
+#define MMU_CONTEXT_VERSION_MASK	(~0UL & ~MMU_CONTEXT_ASID_MASK)
+#define MMU_CONTEXT_FIRST_VERSION	(MMU_CONTEXT_ASID_MASK + 1)
+
+/* Impossible ASID value, to differentiate from NO_CONTEXT. */
+#define MMU_NO_ASID			MMU_CONTEXT_FIRST_VERSION
+#define NO_CONTEXT			0UL
 
 #define asid_cache(cpu)		(cpu_data[cpu].asid_cache)
 
diff --git a/arch/sh/include/asm/mmu_context_32.h b/arch/sh/include/asm/mmu_context_32.h
index f4f9aebd68b7..8ef800c549ab 100644
--- a/arch/sh/include/asm/mmu_context_32.h
+++ b/arch/sh/include/asm/mmu_context_32.h
@@ -10,6 +10,17 @@ static inline void destroy_context(struct mm_struct *mm)
 	/* Do nothing */
 }
 
+#ifdef CONFIG_CPU_HAS_PTEAEX
+static inline void set_asid(unsigned long asid)
+{
+	__raw_writel(asid, MMU_PTEAEX);
+}
+
+static inline unsigned long get_asid(void)
+{
+	return __raw_readl(MMU_PTEAEX) & MMU_CONTEXT_ASID_MASK;
+}
+#else
 static inline void set_asid(unsigned long asid)
 {
 	unsigned long __dummy;
@@ -33,6 +44,7 @@ static inline unsigned long get_asid(void)
 	asid &= MMU_CONTEXT_ASID_MASK;
 	return asid;
 }
+#endif /* CONFIG_CPU_HAS_PTEAEX */
 
 /* MMU_TTB is used for optimizing the fault handling. */
 static inline void set_TTB(pgd_t *pgd)
diff --git a/arch/sh/include/asm/page.h b/arch/sh/include/asm/page.h
index 5871d78e47e5..9c6d21ec0240 100644
--- a/arch/sh/include/asm/page.h
+++ b/arch/sh/include/asm/page.h
@@ -129,7 +129,12 @@ typedef struct page *pgtable_t;
  * is not visible (it is part of the PMB mapping) and so needs to be
  * added or subtracted as required.
  */
-#ifdef CONFIG_32BIT
+#if defined(CONFIG_PMB_FIXED)
+/* phys = virt - PAGE_OFFSET - (__MEMORY_START & 0xe0000000) */
+#define PMB_OFFSET	(PAGE_OFFSET - PXSEG(__MEMORY_START))
+#define __pa(x)	((unsigned long)(x) - PMB_OFFSET)
+#define __va(x)	((void *)((unsigned long)(x) + PMB_OFFSET))
+#elif defined(CONFIG_32BIT)
 #define __pa(x)	((unsigned long)(x)-PAGE_OFFSET+__MEMORY_START)
 #define __va(x)	((void *)((unsigned long)(x)+PAGE_OFFSET-__MEMORY_START))
 #else
diff --git a/arch/sh/include/asm/processor.h b/arch/sh/include/asm/processor.h
index 1ef4b24d7619..1fd58b421438 100644
--- a/arch/sh/include/asm/processor.h
+++ b/arch/sh/include/asm/processor.h
@@ -31,7 +31,7 @@ enum cpu_type {
 	CPU_SH7760, CPU_SH4_202, CPU_SH4_501,
 
 	/* SH-4A types */
-	CPU_SH7763, CPU_SH7770, CPU_SH7780, CPU_SH7781, CPU_SH7785,
+	CPU_SH7763, CPU_SH7770, CPU_SH7780, CPU_SH7781, CPU_SH7785, CPU_SH7786,
 	CPU_SH7723, CPU_SHX3,
 
 	/* SH4AL-DSP types */
diff --git a/arch/sh/include/asm/processor_32.h b/arch/sh/include/asm/processor_32.h
index d79063c5eb9c..efdd78a53b11 100644
--- a/arch/sh/include/asm/processor_32.h
+++ b/arch/sh/include/asm/processor_32.h
@@ -108,12 +108,12 @@ extern int ubc_usercnt;
 /*
  * Do necessary setup to start up a newly executed thread.
  */
-#define start_thread(regs, new_pc, new_sp)	 \
+#define start_thread(_regs, new_pc, new_sp)	 \
 	set_fs(USER_DS);			 \
-	regs->pr = 0;				 \
-	regs->sr = SR_FD;	/* User mode. */ \
-	regs->pc = new_pc;			 \
-	regs->regs[15] = new_sp
+	_regs->pr = 0;				 \
+	_regs->sr = SR_FD;	/* User mode. */ \
+	_regs->pc = new_pc;			 \
+	_regs->regs[15] = new_sp
 
 /* Forward declaration, a strange C thing */
 struct task_struct;
@@ -189,10 +189,9 @@ extern unsigned long get_wchan(struct task_struct *p);
 #define KSTK_EIP(tsk)  (task_pt_regs(tsk)->pc)
 #define KSTK_ESP(tsk)  (task_pt_regs(tsk)->regs[15])
 
-#define user_stack_pointer(regs)	((regs)->regs[15])
+#define user_stack_pointer(_regs)	((_regs)->regs[15])
 
-#if defined(CONFIG_CPU_SH2A) || defined(CONFIG_CPU_SH3) || \
-    defined(CONFIG_CPU_SH4)
+#if defined(CONFIG_CPU_SH2A) || defined(CONFIG_CPU_SH4)
 #define PREFETCH_STRIDE		L1_CACHE_BYTES
 #define ARCH_HAS_PREFETCH
 #define ARCH_HAS_PREFETCHW
diff --git a/arch/sh/include/asm/processor_64.h b/arch/sh/include/asm/processor_64.h
index 803177fcf086..5727d31b0ccf 100644
--- a/arch/sh/include/asm/processor_64.h
+++ b/arch/sh/include/asm/processor_64.h
@@ -145,13 +145,13 @@ struct thread_struct {
  */
 #define SR_USER (SR_MMU | SR_FD)
 
-#define start_thread(regs, new_pc, new_sp)			\
+#define start_thread(_regs, new_pc, new_sp)			\
 	set_fs(USER_DS);					\
-	regs->sr = SR_USER;	/* User mode. */		\
-	regs->pc = new_pc - 4;	/* Compensate syscall exit */	\
-	regs->pc |= 1;		/* Set SHmedia ! */		\
-	regs->regs[18] = 0;					\
-	regs->regs[15] = new_sp
+	_regs->sr = SR_USER;	/* User mode. */		\
+	_regs->pc = new_pc - 4;	/* Compensate syscall exit */	\
+	_regs->pc |= 1;		/* Set SHmedia ! */		\
+	_regs->regs[18] = 0;					\
+	_regs->regs[15] = new_sp
 
 /* Forward declaration, a strange C thing */
 struct task_struct;
@@ -226,7 +226,7 @@ extern unsigned long get_wchan(struct task_struct *p);
 #define KSTK_EIP(tsk)  ((tsk)->thread.pc)
 #define KSTK_ESP(tsk)  ((tsk)->thread.sp)
 
-#define user_stack_pointer(regs)	((regs)->regs[15])
+#define user_stack_pointer(_regs)	((_regs)->regs[15])
 
 #endif	/* __ASSEMBLY__ */
 #endif /* __ASM_SH_PROCESSOR_64_H */
diff --git a/arch/sh/include/asm/ptrace.h b/arch/sh/include/asm/ptrace.h
index 12912ab80c15..81c6568fdb3e 100644
--- a/arch/sh/include/asm/ptrace.h
+++ b/arch/sh/include/asm/ptrace.h
@@ -122,14 +122,12 @@ extern void user_disable_single_step(struct task_struct *);
 #ifdef CONFIG_SH_DSP
 #define task_pt_regs(task) \
 	((struct pt_regs *) (task_stack_page(task) + THREAD_SIZE \
-		 - sizeof(struct pt_dspregs) - sizeof(unsigned long)) - 1)
+		 - sizeof(struct pt_dspregs)) - 1)
 #define task_pt_dspregs(task) \
-	((struct pt_dspregs *) (task_stack_page(task) + THREAD_SIZE \
-		 - sizeof(unsigned long)) - 1)
+	((struct pt_dspregs *) (task_stack_page(task) + THREAD_SIZE) - 1)
 #else
 #define task_pt_regs(task) \
-	((struct pt_regs *) (task_stack_page(task) + THREAD_SIZE \
-		 - sizeof(unsigned long)) - 1)
+	((struct pt_regs *) (task_stack_page(task) + THREAD_SIZE) - 1)
 #endif
 
 static inline unsigned long profile_pc(struct pt_regs *regs)
diff --git a/arch/sh/include/asm/sections.h b/arch/sh/include/asm/sections.h
index 8f8f4ad400df..01a4076a3719 100644
--- a/arch/sh/include/asm/sections.h
+++ b/arch/sh/include/asm/sections.h
@@ -3,6 +3,7 @@
 
 #include <asm-generic/sections.h>
 
+extern void __nosave_begin, __nosave_end;
 extern long __machvec_start, __machvec_end;
 extern char __uncached_start, __uncached_end;
 extern char _ebss[];
diff --git a/arch/sh/include/asm/suspend.h b/arch/sh/include/asm/suspend.h
new file mode 100644
index 000000000000..b1b995370e79
--- /dev/null
+++ b/arch/sh/include/asm/suspend.h
@@ -0,0 +1,22 @@
+#ifndef _ASM_SH_SUSPEND_H
+#define _ASM_SH_SUSPEND_H
+
+#ifndef __ASSEMBLY__
+static inline int arch_prepare_suspend(void) { return 0; }
+
+#include <asm/ptrace.h>
+
+struct swsusp_arch_regs {
+	struct pt_regs user_regs;
+	unsigned long bank1_regs[8];
+};
+#endif
+
+/* flags passed to assembly suspend code */
+#define SUSP_SH_SLEEP		(1 << 0) /* Regular sleep mode */
+#define SUSP_SH_STANDBY		(1 << 1) /* SH-Mobile Software standby mode */
+#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 */
+
+#endif /* _ASM_SH_SUSPEND_H */
diff --git a/arch/sh/include/asm/timer.h b/arch/sh/include/asm/timer.h
index a7ca3a195bb5..4c3b66e30af2 100644
--- a/arch/sh/include/asm/timer.h
+++ b/arch/sh/include/asm/timer.h
@@ -9,7 +9,6 @@ struct sys_timer_ops {
 	int (*init)(void);
 	int (*start)(void);
 	int (*stop)(void);
-	cycle_t (*read)(void);
 #ifndef CONFIG_GENERIC_TIME
 	unsigned long (*get_offset)(void);
 #endif
@@ -39,6 +38,7 @@ struct sys_timer *get_sys_timer(void);
 
 /* arch/sh/kernel/time.c */
 void handle_timer_tick(void);
-extern unsigned long sh_hpt_frequency;
+
+extern struct clocksource clocksource_sh;
 
 #endif /* __ASM_SH_TIMER_H */
diff --git a/arch/sh/include/asm/tlb.h b/arch/sh/include/asm/tlb.h
index 88ff1ae8a6b8..9c16f737074a 100644
--- a/arch/sh/include/asm/tlb.h
+++ b/arch/sh/include/asm/tlb.h
@@ -6,22 +6,106 @@
 #endif
 
 #ifndef __ASSEMBLY__
+#include <linux/pagemap.h>
+
+#ifdef CONFIG_MMU
+#include <asm/pgalloc.h>
+#include <asm/tlbflush.h>
+
+/*
+ * TLB handling.  This allows us to remove pages from the page
+ * tables, and efficiently handle the TLB issues.
+ */
+struct mmu_gather {
+	struct mm_struct	*mm;
+	unsigned int		fullmm;
+	unsigned long		start, end;
+};
 
-#define tlb_start_vma(tlb, vma) \
-	flush_cache_range(vma, vma->vm_start, vma->vm_end)
+DECLARE_PER_CPU(struct mmu_gather, mmu_gathers);
 
-#define tlb_end_vma(tlb, vma)	\
-	flush_tlb_range(vma, vma->vm_start, vma->vm_end)
+static inline void init_tlb_gather(struct mmu_gather *tlb)
+{
+	tlb->start = TASK_SIZE;
+	tlb->end = 0;
 
-#define __tlb_remove_tlb_entry(tlb, pte, address)	do { } while (0)
+	if (tlb->fullmm) {
+		tlb->start = 0;
+		tlb->end = TASK_SIZE;
+	}
+}
+
+static inline struct mmu_gather *
+tlb_gather_mmu(struct mm_struct *mm, unsigned int full_mm_flush)
+{
+	struct mmu_gather *tlb = &get_cpu_var(mmu_gathers);
+
+	tlb->mm = mm;
+	tlb->fullmm = full_mm_flush;
+
+	init_tlb_gather(tlb);
+
+	return tlb;
+}
+
+static inline void
+tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
+{
+	if (tlb->fullmm)
+		flush_tlb_mm(tlb->mm);
+
+	/* keep the page table cache within bounds */
+	check_pgt_cache();
+
+	put_cpu_var(mmu_gathers);
+}
+
+static inline void
+tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep, unsigned long address)
+{
+	if (tlb->start > address)
+		tlb->start = address;
+	if (tlb->end < address + PAGE_SIZE)
+		tlb->end = address + PAGE_SIZE;
+}
 
 /*
- * Flush whole TLBs for MM
+ * In the case of tlb vma handling, we can optimise these away in the
+ * case where we're doing a full MM flush.  When we're doing a munmap,
+ * the vmas are adjusted to only cover the region to be torn down.
  */
-#define tlb_flush(tlb)				flush_tlb_mm((tlb)->mm)
+static inline void
+tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
+{
+	if (!tlb->fullmm)
+		flush_cache_range(vma, vma->vm_start, vma->vm_end);
+}
+
+static inline void
+tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
+{
+	if (!tlb->fullmm && tlb->end) {
+		flush_tlb_range(vma, tlb->start, tlb->end);
+		init_tlb_gather(tlb);
+	}
+}
+
+#define tlb_remove_page(tlb,page)	free_page_and_swap_cache(page)
+#define pte_free_tlb(tlb, ptep)		pte_free((tlb)->mm, ptep)
+#define pmd_free_tlb(tlb, pmdp)		pmd_free((tlb)->mm, pmdp)
+#define pud_free_tlb(tlb, pudp)		pud_free((tlb)->mm, pudp)
+
+#define tlb_migrate_finish(mm)		do { } while (0)
+
+#else /* CONFIG_MMU */
+
+#define tlb_start_vma(tlb, vma)				do { } while (0)
+#define tlb_end_vma(tlb, vma)				do { } while (0)
+#define __tlb_remove_tlb_entry(tlb, pte, address)	do { } while (0)
+#define tlb_flush(tlb)					do { } while (0)
 
-#include <linux/pagemap.h>
 #include <asm-generic/tlb.h>
 
+#endif /* CONFIG_MMU */
 #endif /* __ASSEMBLY__ */
 #endif /* __ASM_SH_TLB_H */