Merge master.kernel.org:/pub/scm/linux/kernel/git/lethal/sh-2.6

* master.kernel.org:/pub/scm/linux/kernel/git/lethal/sh-2.6: (29 commits)
  sh: Fixup SH-2 BUG() trap handling.
  sh: Use early_param() for earlyprintk parsing.
  sh: Fix .empty_zero_page alignment for PAGE_SIZE > 4096.
  sh: Fixup .data.page_aligned.
  sh: Hook up SH7722 scif ipr interrupts.
  sh: Fixup sh_bios() trap handling.
  sh: SH-MobileR SH7722 CPU support.
  sh: Fixup dma_cache_sync() callers.
  sh: Convert remaining remap_area_pages() users to ioremap_page_range().
  sh: Fixup kernel_execve() for syscall cleanups.
  sh: Fix get_wchan().
  sh: BUG() handling through trapa vector.
  rtc: rtc-sh: alarm support.
  rtc: rtc-sh: fix rtc for out-by-one for the month.
  sh: Kill off unused SE7619 I/O ops.
  serial: sh-sci: Shut up various sci_rxd_in() gcc4 warnings.
  sh: Split out atomic ops logically.
  sh: Fix Solution Engine 7619 build.
  sh: Trivial build fixes for SH-2 support.
  sh: IPR IRQ updates for SH7619/SH7206.
  ...

13 files changed, 329 insertions, 213 deletions

diff --git a/include/asm-sh/atomic-irq.h b/include/asm-sh/atomic-irq.h
new file mode 100644
index 000000000000..74f7943cff6f
--- /dev/null
+++ b/include/asm-sh/atomic-irq.h
@@ -0,0 +1,71 @@
+#ifndef __ASM_SH_ATOMIC_IRQ_H
+#define __ASM_SH_ATOMIC_IRQ_H
+
+/*
+ * To get proper branch prediction for the main line, we must branch
+ * forward to code at the end of this object's .text section, then
+ * branch back to restart the operation.
+ */
+static inline void atomic_add(int i, atomic_t *v)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	*(long *)v += i;
+	local_irq_restore(flags);
+}
+
+static inline void atomic_sub(int i, atomic_t *v)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	*(long *)v -= i;
+	local_irq_restore(flags);
+}
+
+static inline int atomic_add_return(int i, atomic_t *v)
+{
+	unsigned long temp, flags;
+
+	local_irq_save(flags);
+	temp = *(long *)v;
+	temp += i;
+	*(long *)v = temp;
+	local_irq_restore(flags);
+
+	return temp;
+}
+
+static inline int atomic_sub_return(int i, atomic_t *v)
+{
+	unsigned long temp, flags;
+
+	local_irq_save(flags);
+	temp = *(long *)v;
+	temp -= i;
+	*(long *)v = temp;
+	local_irq_restore(flags);
+
+	return temp;
+}
+
+static inline void atomic_clear_mask(unsigned int mask, atomic_t *v)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	*(long *)v &= ~mask;
+	local_irq_restore(flags);
+}
+
+static inline void atomic_set_mask(unsigned int mask, atomic_t *v)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	*(long *)v |= mask;
+	local_irq_restore(flags);
+}
+
+#endif /* __ASM_SH_ATOMIC_IRQ_H */
diff --git a/include/asm-sh/atomic-llsc.h b/include/asm-sh/atomic-llsc.h
new file mode 100644
index 000000000000..4b00b78e3f4f
--- /dev/null
+++ b/include/asm-sh/atomic-llsc.h
@@ -0,0 +1,107 @@
+#ifndef __ASM_SH_ATOMIC_LLSC_H
+#define __ASM_SH_ATOMIC_LLSC_H
+
+/*
+ * To get proper branch prediction for the main line, we must branch
+ * forward to code at the end of this object's .text section, then
+ * branch back to restart the operation.
+ */
+static inline void atomic_add(int i, atomic_t *v)
+{
+	unsigned long tmp;
+
+	__asm__ __volatile__ (
+"1:	movli.l @%2, %0		! atomic_add	\n"
+"	add	%1, %0				\n"
+"	movco.l	%0, @%2				\n"
+"	bf	1b				\n"
+	: "=&z" (tmp)
+	: "r" (i), "r" (&v->counter)
+	: "t");
+}
+
+static inline void atomic_sub(int i, atomic_t *v)
+{
+	unsigned long tmp;
+
+	__asm__ __volatile__ (
+"1:	movli.l @%2, %0		! atomic_sub	\n"
+"	sub	%1, %0				\n"
+"	movco.l	%0, @%2				\n"
+"	bf	1b				\n"
+	: "=&z" (tmp)
+	: "r" (i), "r" (&v->counter)
+	: "t");
+}
+
+/*
+ * SH-4A note:
+ *
+ * We basically get atomic_xxx_return() for free compared with
+ * atomic_xxx(). movli.l/movco.l require r0 due to the instruction
+ * encoding, so the retval is automatically set without having to
+ * do any special work.
+ */
+static inline int atomic_add_return(int i, atomic_t *v)
+{
+	unsigned long temp;
+
+	__asm__ __volatile__ (
+"1:	movli.l @%2, %0		! atomic_add_return	\n"
+"	add	%1, %0					\n"
+"	movco.l	%0, @%2					\n"
+"	bf	1b					\n"
+"	synco						\n"
+	: "=&z" (temp)
+	: "r" (i), "r" (&v->counter)
+	: "t");
+
+	return temp;
+}
+
+static inline int atomic_sub_return(int i, atomic_t *v)
+{
+	unsigned long temp;
+
+	__asm__ __volatile__ (
+"1:	movli.l @%2, %0		! atomic_sub_return	\n"
+"	sub	%1, %0					\n"
+"	movco.l	%0, @%2					\n"
+"	bf	1b					\n"
+"	synco						\n"
+	: "=&z" (temp)
+	: "r" (i), "r" (&v->counter)
+	: "t");
+
+	return temp;
+}
+
+static inline void atomic_clear_mask(unsigned int mask, atomic_t *v)
+{
+	unsigned long tmp;
+
+	__asm__ __volatile__ (
+"1:	movli.l @%2, %0		! atomic_clear_mask	\n"
+"	and	%1, %0					\n"
+"	movco.l	%0, @%2					\n"
+"	bf	1b					\n"
+	: "=&z" (tmp)
+	: "r" (~mask), "r" (&v->counter)
+	: "t");
+}
+
+static inline void atomic_set_mask(unsigned int mask, atomic_t *v)
+{
+	unsigned long tmp;
+
+	__asm__ __volatile__ (
+"1:	movli.l @%2, %0		! atomic_set_mask	\n"
+"	or	%1, %0					\n"
+"	movco.l	%0, @%2					\n"
+"	bf	1b					\n"
+	: "=&z" (tmp)
+	: "r" (mask), "r" (&v->counter)
+	: "t");
+}
+
+#endif /* __ASM_SH_ATOMIC_LLSC_H */
diff --git a/include/asm-sh/atomic.h b/include/asm-sh/atomic.h
index 28305c3cbddf..e12570b9339d 100644
--- a/include/asm-sh/atomic.h
+++ b/include/asm-sh/atomic.h
@@ -17,119 +17,14 @@ typedef struct { volatile int counter; } atomic_t;
 #include <linux/compiler.h>
 #include <asm/system.h>
 
-/*
- * To get proper branch prediction for the main line, we must branch
- * forward to code at the end of this object's .text section, then
- * branch back to restart the operation.
- */
-static inline void atomic_add(int i, atomic_t *v)
-{
 #ifdef CONFIG_CPU_SH4A
-	unsigned long tmp;
-
-	__asm__ __volatile__ (
-"1:	movli.l @%2, %0		! atomic_add	\n"
-"	add	%1, %0				\n"
-"	movco.l	%0, @%2				\n"
-"	bf	1b				\n"
-	: "=&z" (tmp)
-	: "r" (i), "r" (&v->counter)
-	: "t");
+#include <asm/atomic-llsc.h>
 #else
-	unsigned long flags;
-
-	local_irq_save(flags);
-	*(long *)v += i;
-	local_irq_restore(flags);
-#endif
-}
-
-static inline void atomic_sub(int i, atomic_t *v)
-{
-#ifdef CONFIG_CPU_SH4A
-	unsigned long tmp;
-
-	__asm__ __volatile__ (
-"1:	movli.l @%2, %0		! atomic_sub	\n"
-"	sub	%1, %0				\n"
-"	movco.l	%0, @%2				\n"
-"	bf	1b				\n"
-	: "=&z" (tmp)
-	: "r" (i), "r" (&v->counter)
-	: "t");
-#else
-	unsigned long flags;
-
-	local_irq_save(flags);
-	*(long *)v -= i;
-	local_irq_restore(flags);
+#include <asm/atomic-irq.h>
 #endif
-}
-
-/*
- * SH-4A note:
- *
- * We basically get atomic_xxx_return() for free compared with
- * atomic_xxx(). movli.l/movco.l require r0 due to the instruction
- * encoding, so the retval is automatically set without having to
- * do any special work.
- */
-static inline int atomic_add_return(int i, atomic_t *v)
-{
-	unsigned long temp;
-
-#ifdef CONFIG_CPU_SH4A
-	__asm__ __volatile__ (
-"1:	movli.l @%2, %0		! atomic_add_return	\n"
-"	add	%1, %0					\n"
-"	movco.l	%0, @%2					\n"
-"	bf	1b					\n"
-"	synco						\n"
-	: "=&z" (temp)
-	: "r" (i), "r" (&v->counter)
-	: "t");
-#else
-	unsigned long flags;
-
-	local_irq_save(flags);
-	temp = *(long *)v;
-	temp += i;
-	*(long *)v = temp;
-	local_irq_restore(flags);
-#endif
-
-	return temp;
-}
 
 #define atomic_add_negative(a, v)	(atomic_add_return((a), (v)) < 0)
 
-static inline int atomic_sub_return(int i, atomic_t *v)
-{
-	unsigned long temp;
-
-#ifdef CONFIG_CPU_SH4A
-	__asm__ __volatile__ (
-"1:	movli.l @%2, %0		! atomic_sub_return	\n"
-"	sub	%1, %0					\n"
-"	movco.l	%0, @%2					\n"
-"	bf	1b					\n"
-"	synco						\n"
-	: "=&z" (temp)
-	: "r" (i), "r" (&v->counter)
-	: "t");
-#else
-	unsigned long flags;
-
-	local_irq_save(flags);
-	temp = *(long *)v;
-	temp -= i;
-	*(long *)v = temp;
-	local_irq_restore(flags);
-#endif
-
-	return temp;
-}
-
 #define atomic_dec_return(v) atomic_sub_return(1,(v))
 #define atomic_inc_return(v) atomic_add_return(1,(v))
 
@@ -180,50 +75,6 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u)
 }
 #define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
 
-static inline void atomic_clear_mask(unsigned int mask, atomic_t *v)
-{
-#ifdef CONFIG_CPU_SH4A
-	unsigned long tmp;
-
-	__asm__ __volatile__ (
-"1:	movli.l @%2, %0		! atomic_clear_mask	\n"
-"	and	%1, %0					\n"
-"	movco.l	%0, @%2					\n"
-"	bf	1b					\n"
-	: "=&z" (tmp)
-	: "r" (~mask), "r" (&v->counter)
-	: "t");
-#else
-	unsigned long flags;
-
-	local_irq_save(flags);
-	*(long *)v &= ~mask;
-	local_irq_restore(flags);
-#endif
-}
-
-static inline void atomic_set_mask(unsigned int mask, atomic_t *v)
-{
-#ifdef CONFIG_CPU_SH4A
-	unsigned long tmp;
-
-	__asm__ __volatile__ (
-"1:	movli.l @%2, %0		! atomic_set_mask	\n"
-"	or	%1, %0					\n"
-"	movco.l	%0, @%2					\n"
-"	bf	1b					\n"
-	: "=&z" (tmp)
-	: "r" (mask), "r" (&v->counter)
-	: "t");
-#else
-	unsigned long flags;
-
-	local_irq_save(flags);
-	*(long *)v |= mask;
-	local_irq_restore(flags);
-#endif
-}
-
 /* Atomic operations are already serializing on SH */
 #define smp_mb__before_atomic_dec()	barrier()
 #define smp_mb__after_atomic_dec()	barrier()
diff --git a/include/asm-sh/bug.h b/include/asm-sh/bug.h
index 1b4fc52a59e8..2f89dd06d0cd 100644
--- a/include/asm-sh/bug.h
+++ b/include/asm-sh/bug.h
@@ -1,19 +1,54 @@
 #ifndef __ASM_SH_BUG_H
 #define __ASM_SH_BUG_H
 
-
 #ifdef CONFIG_BUG
-/*
- * Tell the user there is some problem.
- */
-#define BUG() do { \
-	printk("kernel BUG at %s:%d!\n", __FILE__, __LINE__); \
-	*(volatile int *)0 = 0; \
+
+struct bug_frame {
+	unsigned short	opcode;
+	unsigned short	line;
+	const char	*file;
+	const char	*func;
+};
+
+struct pt_regs;
+
+extern void handle_BUG(struct pt_regs *);
+
+#define TRAPA_BUG_OPCODE	0xc33e	/* trapa #0x3e */
+
+#ifdef CONFIG_DEBUG_BUGVERBOSE
+
+#define BUG()						\
+do {							\
+	__asm__ __volatile__ (				\
+		".align	2\n\t"				\
+		".short	%O0\n\t"			\
+		".short	%O1\n\t"			\
+		".long	%O2\n\t"			\
+		".long	%O3\n\t"			\
+		:					\
+		: "n" (TRAPA_BUG_OPCODE),		\
+		  "i" (__LINE__), "X" (__FILE__),	\
+		  "X" (__FUNCTION__));			\
+} while (0)
+
+#else
+
+#define BUG()					\
+do {						\
+	__asm__ __volatile__ (			\
+		".align	2\n\t"			\
+		".short	%O0\n\t"		\
+		:				\
+		: "n" (TRAPA_BUG_OPCODE));	\
 } while (0)
 
+#endif /* CONFIG_DEBUG_BUGVERBOSE */
+
 #define HAVE_ARCH_BUG
-#endif
+
+#endif /* CONFIG_BUG */
 
 #include <asm-generic/bug.h>
 
-#endif
+#endif /* __ASM_SH_BUG_H */
diff --git a/include/asm-sh/bugs.h b/include/asm-sh/bugs.h
index 795047da5e17..a294997a8412 100644
--- a/include/asm-sh/bugs.h
+++ b/include/asm-sh/bugs.h
@@ -16,9 +16,8 @@
 
 static void __init check_bugs(void)
 {
-	extern char *get_cpu_subtype(void);
 	extern unsigned long loops_per_jiffy;
-	char *p= &init_utsname()->machine[2]; /* "sh" */
+	char *p = &init_utsname()->machine[2]; /* "sh" */
 
 	cpu_data->loops_per_jiffy = loops_per_jiffy;
 
@@ -40,6 +39,15 @@ static void __init check_bugs(void)
 		*p++ = '4';
 		*p++ = 'a';
 		break;
+	case CPU_SH73180 ... CPU_SH7722:
+		*p++ = '4';
+		*p++ = 'a';
+		*p++ = 'l';
+		*p++ = '-';
+		*p++ = 'd';
+		*p++ = 's';
+		*p++ = 'p';
+		break;
 	default:
 		*p++ = '?';
 		*p++ = '!';
diff --git a/include/asm-sh/checksum.h b/include/asm-sh/checksum.h
index d44344c88e73..4bc8357e8892 100644
--- a/include/asm-sh/checksum.h
+++ b/include/asm-sh/checksum.h
@@ -34,25 +34,26 @@ asmlinkage __wsum csum_partial(const void *buff, int len, __wsum sum);
  */
 
 asmlinkage __wsum csum_partial_copy_generic(const void *src, void *dst,
-					  int len, __wsum sum, int *src_err_ptr, int *dst_err_ptr);
+					    int len, __wsum sum,
+					    int *src_err_ptr, int *dst_err_ptr);
 
 /*
  *	Note: when you get a NULL pointer exception here this means someone
- *	passed in an incorrect kernel address to one of these functions. 
- *	
- *	If you use these functions directly please don't forget the 
+ *	passed in an incorrect kernel address to one of these functions.
+ *
+ *	If you use these functions directly please don't forget the
  *	access_ok().
  */
-static __inline__
+static inline
 __wsum csum_partial_copy_nocheck(const void *src, void *dst,
-					int len, __wsum sum)
+				 int len, __wsum sum)
 {
-	return csum_partial_copy_generic ( src, dst, len, sum, NULL, NULL);
+	return csum_partial_copy_generic(src, dst, len, sum, NULL, NULL);
 }
 
-static __inline__
+static inline
 __wsum csum_partial_copy_from_user(const void __user *src, void *dst,
-						int len, __wsum sum, int *err_ptr)
+				   int len, __wsum sum, int *err_ptr)
 {
 	return csum_partial_copy_generic((__force const void *)src, dst,
 					len, sum, err_ptr, NULL);
@@ -62,7 +63,7 @@ __wsum csum_partial_copy_from_user(const void __user *src, void *dst,
  *	Fold a partial checksum
  */
 
-static __inline__ __sum16 csum_fold(__wsum sum)
+static inline __sum16 csum_fold(__wsum sum)
 {
 	unsigned int __dummy;
 	__asm__("swap.w %0, %1\n\t"
@@ -85,7 +86,7 @@ static __inline__ __sum16 csum_fold(__wsum sum)
  *      i386 version by Jorge Cwik <jorge@laser.satlink.net>, adapted
  *      for linux by * Arnt Gulbrandsen.
  */
-static __inline__ __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
+static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
 {
 	unsigned int sum, __dummy0, __dummy1;
 
@@ -113,10 +114,10 @@ static __inline__ __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
 	return	csum_fold(sum);
 }
 
-static __inline__ __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
-						   unsigned short len,
-						   unsigned short proto,
-						   __wsum sum)
+static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
+					unsigned short len,
+					unsigned short proto,
+					__wsum sum)
 {
 #ifdef __LITTLE_ENDIAN__
 	unsigned long len_proto = (proto + len) << 8;
@@ -132,6 +133,7 @@ static __inline__ __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
 		: "=r" (sum), "=r" (len_proto)
 		: "r" (daddr), "r" (saddr), "1" (len_proto), "0" (sum)
 		: "t");
+
 	return sum;
 }
 
@@ -139,30 +141,28 @@ static __inline__ __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
  * computes the checksum of the TCP/UDP pseudo-header
  * returns a 16-bit checksum, already complemented
  */
-static __inline__ __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
-						       unsigned short len,
-						       unsigned short proto,
-						       __wsum sum)
+static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
+					unsigned short len,
+					unsigned short proto,
+					__wsum sum)
 {
-	return csum_fold(csum_tcpudp_nofold(saddr,daddr,len,proto,sum));
+	return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum));
 }
 
 /*
  * this routine is used for miscellaneous IP-like checksums, mainly
  * in icmp.c
  */
-
-static __inline__ __sum16 ip_compute_csum(const void *buff, int len)
+static inline __sum16 ip_compute_csum(const void *buff, int len)
 {
-    return csum_fold (csum_partial(buff, len, 0));
+    return csum_fold(csum_partial(buff, len, 0));
 }
 
 #define _HAVE_ARCH_IPV6_CSUM
-#ifdef CONFIG_IPV6
-static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
-					  const struct in6_addr *daddr,
-					  __u32 len, unsigned short proto,
-					  __wsum sum)
+static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
+				      const struct in6_addr *daddr,
+				      __u32 len, unsigned short proto,
+				      __wsum sum)
 {
 	unsigned int __dummy;
 	__asm__("clrt\n\t"
@@ -187,22 +187,21 @@ static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
 		"movt	%1\n\t"
 		"add	%1, %0\n"
 		: "=r" (sum), "=&r" (__dummy)
-		: "r" (saddr), "r" (daddr), 
+		: "r" (saddr), "r" (daddr),
 		  "r" (htonl(len)), "r" (htonl(proto)), "0" (sum)
 		: "t");
 
 	return csum_fold(sum);
 }
-#endif
 
-/* 
+/*
  *	Copy and checksum to user
  */
 #define HAVE_CSUM_COPY_USER
-static __inline__ __wsum csum_and_copy_to_user (const void *src,
-						      void __user *dst,
-						      int len, __wsum sum,
-						      int *err_ptr)
+static inline __wsum csum_and_copy_to_user(const void *src,
+					   void __user *dst,
+					   int len, __wsum sum,
+					   int *err_ptr)
 {
 	if (access_ok(VERIFY_WRITE, dst, len))
 		return csum_partial_copy_generic((__force const void *)src,
diff --git a/include/asm-sh/cpu-sh4/cache.h b/include/asm-sh/cpu-sh4/cache.h
index 6e9c7e6ee8e4..f92b20a0983d 100644
--- a/include/asm-sh/cpu-sh4/cache.h
+++ b/include/asm-sh/cpu-sh4/cache.h
@@ -22,7 +22,7 @@
 #define CCR_CACHE_ICE	0x0100	/* Instruction Cache Enable */
 #define CCR_CACHE_ICI	0x0800	/* IC Invalidate */
 #define CCR_CACHE_IIX	0x8000	/* IC Index Enable */
-#ifndef CONFIG_CPU_SUBTYPE_SH7780
+#ifndef CONFIG_CPU_SH4A
 #define CCR_CACHE_EMODE	0x80000000	/* EMODE Enable */
 #endif
 
diff --git a/include/asm-sh/cpu-sh4/freq.h b/include/asm-sh/cpu-sh4/freq.h
index ef2b9b1ae41f..602d061ca2dc 100644
--- a/include/asm-sh/cpu-sh4/freq.h
+++ b/include/asm-sh/cpu-sh4/freq.h
@@ -10,7 +10,7 @@
 #ifndef __ASM_CPU_SH4_FREQ_H
 #define __ASM_CPU_SH4_FREQ_H
 
-#if defined(CONFIG_CPU_SUBTYPE_SH73180)
+#if defined(CONFIG_CPU_SUBTYPE_SH73180) || defined(CONFIG_CPU_SUBTYPE_SH7722)
 #define FRQCR		        0xa4150000
 #elif defined(CONFIG_CPU_SUBTYPE_SH7780)
 #define	FRQCR			0xffc80000
diff --git a/include/asm-sh/dma-mapping.h b/include/asm-sh/dma-mapping.h
index 37ab0c131a4d..8d0867b98e05 100644
--- a/include/asm-sh/dma-mapping.h
+++ b/include/asm-sh/dma-mapping.h
@@ -67,7 +67,7 @@ static inline dma_addr_t dma_map_single(struct device *dev,
 	if (dev->bus == &pci_bus_type)
 		return virt_to_bus(ptr);
 #endif
-	dma_cache_sync(ptr, size, dir);
+	dma_cache_sync(dev, ptr, size, dir);
 
 	return virt_to_bus(ptr);
 }
@@ -81,7 +81,7 @@ static inline int dma_map_sg(struct device *dev, struct scatterlist *sg,
 
 	for (i = 0; i < nents; i++) {
 #if !defined(CONFIG_PCI) || defined(CONFIG_SH_PCIDMA_NONCOHERENT)
-		dma_cache_sync(page_address(sg[i].page) + sg[i].offset,
+		dma_cache_sync(dev, page_address(sg[i].page) + sg[i].offset,
 			       sg[i].length, dir);
 #endif
 		sg[i].dma_address = page_to_phys(sg[i].page) + sg[i].offset;
@@ -112,7 +112,7 @@ static inline void dma_sync_single(struct device *dev, dma_addr_t dma_handle,
 	if (dev->bus == &pci_bus_type)
 		return;
 #endif
-	dma_cache_sync(bus_to_virt(dma_handle), size, dir);
+	dma_cache_sync(dev, bus_to_virt(dma_handle), size, dir);
 }
 
 static inline void dma_sync_single_range(struct device *dev,
@@ -124,7 +124,7 @@ static inline void dma_sync_single_range(struct device *dev,
 	if (dev->bus == &pci_bus_type)
 		return;
 #endif
-	dma_cache_sync(bus_to_virt(dma_handle) + offset, size, dir);
+	dma_cache_sync(dev, bus_to_virt(dma_handle) + offset, size, dir);
 }
 
 static inline void dma_sync_sg(struct device *dev, struct scatterlist *sg,
@@ -134,7 +134,7 @@ static inline void dma_sync_sg(struct device *dev, struct scatterlist *sg,
 
 	for (i = 0; i < nelems; i++) {
 #if !defined(CONFIG_PCI) || defined(CONFIG_SH_PCIDMA_NONCOHERENT)
-		dma_cache_sync(page_address(sg[i].page) + sg[i].offset,
+		dma_cache_sync(dev, page_address(sg[i].page) + sg[i].offset,
 			       sg[i].length, dir);
 #endif
 		sg[i].dma_address = page_to_phys(sg[i].page) + sg[i].offset;
diff --git a/include/asm-sh/irq.h b/include/asm-sh/irq.h
index fd576088e47e..bff965ef4b95 100644
--- a/include/asm-sh/irq.h
+++ b/include/asm-sh/irq.h
@@ -37,7 +37,8 @@
 # define ONCHIP_NR_IRQS 144
 #elif defined(CONFIG_CPU_SUBTYPE_SH7300) || \
       defined(CONFIG_CPU_SUBTYPE_SH73180) || \
-      defined(CONFIG_CPU_SUBTYPE_SH7343)
+      defined(CONFIG_CPU_SUBTYPE_SH7343) || \
+      defined(CONFIG_CPU_SUBTYPE_SH7722)
 # define ONCHIP_NR_IRQS 109
 #elif defined(CONFIG_CPU_SUBTYPE_SH7780)
 # define ONCHIP_NR_IRQS 111
@@ -79,6 +80,8 @@
 # define OFFCHIP_NR_IRQS 16
 #elif defined(CONFIG_SH_7343_SOLUTION_ENGINE)
 # define OFFCHIP_NR_IRQS 12
+#elif defined(CONFIG_SH_7722_SOLUTION_ENGINE)
+# define OFFCHIP_NR_IRQS 14
 #elif defined(CONFIG_SH_UNKNOWN)
 # define OFFCHIP_NR_IRQS 16	/* Must also be last */
 #else
diff --git a/include/asm-sh/pgtable.h b/include/asm-sh/pgtable.h
index c84901dbd8e5..036ca2843866 100644
--- a/include/asm-sh/pgtable.h
+++ b/include/asm-sh/pgtable.h
@@ -508,16 +508,50 @@ struct vm_area_struct;
 extern void update_mmu_cache(struct vm_area_struct * vma,
 			     unsigned long address, pte_t pte);
 
-/* Encode and de-code a swap entry */
 /*
+ * Encode and de-code a swap entry
+ *
+ * Constraints:
+ *	_PAGE_FILE at bit 0
+ *	_PAGE_PRESENT at bit 8
+ *	_PAGE_PROTNONE at bit 9
+ *
+ * For the normal case, we encode the swap type into bits 0:7 and the
+ * swap offset into bits 10:30. For the 64-bit PTE case, we keep the
+ * preserved bits in the low 32-bits and use the upper 32 as the swap
+ * offset (along with a 5-bit type), following the same approach as x86
+ * PAE. This keeps the logic quite simple, and allows for a full 32
+ * PTE_FILE_MAX_BITS, as opposed to the 29-bits we're constrained with
+ * in the pte_low case.
+ *
+ * As is evident by the Alpha code, if we ever get a 64-bit unsigned
+ * long (swp_entry_t) to match up with the 64-bit PTEs, this all becomes
+ * much cleaner..
+ *
  * NOTE: We should set ZEROs at the position of _PAGE_PRESENT
  *       and _PAGE_PROTNONE bits
  */
-#define __swp_type(x)		((x).val & 0xff)
-#define __swp_offset(x)		((x).val >> 10)
-#define __swp_entry(type, offset) ((swp_entry_t) { (type) | ((offset) << 10) })
-#define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val(pte) >> 1 })
-#define __swp_entry_to_pte(x)	((pte_t) { (x).val << 1 })
+#ifdef CONFIG_X2TLB
+#define __swp_type(x)			((x).val & 0x1f)
+#define __swp_offset(x)			((x).val >> 5)
+#define __swp_entry(type, offset)	((swp_entry_t){ (type) | (offset) << 5})
+#define __pte_to_swp_entry(pte)		((swp_entry_t){ (pte).pte_high })
+#define __swp_entry_to_pte(x)		((pte_t){ 0, (x).val })
+
+/*
+ * Encode and decode a nonlinear file mapping entry
+ */
+#define pte_to_pgoff(pte)		((pte).pte_high)
+#define pgoff_to_pte(off)		((pte_t) { _PAGE_FILE, (off) })
+
+#define PTE_FILE_MAX_BITS		32
+#else
+#define __swp_type(x)			((x).val & 0xff)
+#define __swp_offset(x)			((x).val >> 10)
+#define __swp_entry(type, offset)	((swp_entry_t){(type) | (offset) <<10})
+
+#define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val(pte) >> 1 })
+#define __swp_entry_to_pte(x)		((pte_t) { (x).val << 1 })
 
 /*
  * Encode and decode a nonlinear file mapping entry
@@ -525,6 +559,7 @@ extern void update_mmu_cache(struct vm_area_struct * vma,
 #define PTE_FILE_MAX_BITS	29
 #define pte_to_pgoff(pte)	(pte_val(pte) >> 1)
 #define pgoff_to_pte(off)	((pte_t) { ((off) << 1) | _PAGE_FILE })
+#endif
 
 typedef pte_t *pte_addr_t;
 
diff --git a/include/asm-sh/processor.h b/include/asm-sh/processor.h
index 6f1dd7ca1b1d..e29f2abb92de 100644
--- a/include/asm-sh/processor.h
+++ b/include/asm-sh/processor.h
@@ -27,6 +27,8 @@
 #define CCN_CVR		0xff000040
 #define CCN_PRR		0xff000044
 
+const char *get_cpu_subtype(void);
+
 /*
  *  CPU type and hardware bug flags. Kept separately for each CPU.
  *
@@ -52,8 +54,10 @@ enum cpu_type {
 	CPU_SH7760, CPU_ST40RA, CPU_ST40GX1, CPU_SH4_202, CPU_SH4_501,
 
 	/* SH-4A types */
-	CPU_SH73180, CPU_SH7343, CPU_SH7770, CPU_SH7780, CPU_SH7781,
-	CPU_SH7785,
+	CPU_SH7770, CPU_SH7780, CPU_SH7781, CPU_SH7785,
+
+	/* SH4AL-DSP types */
+	CPU_SH73180, CPU_SH7343, CPU_SH7722,
 
 	/* Unknown subtype */
 	CPU_SH_NONE
diff --git a/include/asm-sh/push-switch.h b/include/asm-sh/push-switch.h
index dfc6bad567f0..4903f9e52dd8 100644
--- a/include/asm-sh/push-switch.h
+++ b/include/asm-sh/push-switch.h
@@ -4,6 +4,7 @@
 #include <linux/timer.h>
 #include <linux/interrupt.h>
 #include <linux/workqueue.h>
+#include <linux/platform_device.h>
 
 struct push_switch {
 	/* switch state */
@@ -12,6 +13,8 @@ struct push_switch {
 	struct timer_list	debounce;
 	/* workqueue */
 	struct work_struct	work;
+	/* platform device, for workqueue handler */
+	struct platform_device	*pdev;
 };
 
 struct push_switch_platform_info {