17 files changed, 276 insertions, 355 deletions

diff --git a/arch/sh/include/asm/cacheflush.h b/arch/sh/include/asm/cacheflush.h
index 1f4e562c5e8c..82e1eabeac98 100644
--- a/arch/sh/include/asm/cacheflush.h
+++ b/arch/sh/include/asm/cacheflush.h
@@ -96,7 +96,7 @@ void kmap_coherent_init(void);
 void *kmap_coherent(struct page *page, unsigned long addr);
 void kunmap_coherent(void *kvaddr);
 
-#define PG_dcache_dirty	PG_arch_1
+#define PG_dcache_clean	PG_arch_1
 
 void cpu_cache_init(void);
 
diff --git a/arch/sh/include/asm/clkdev.h b/arch/sh/include/asm/clkdev.h
index 5645f358128b..6ba91868201c 100644
--- a/arch/sh/include/asm/clkdev.h
+++ b/arch/sh/include/asm/clkdev.h
@@ -1,9 +1,5 @@
 /*
- *  arch/sh/include/asm/clkdev.h
- *
- * Cloned from arch/arm/include/asm/clkdev.h:
- *
- *  Copyright (C) 2008 Russell King.
+ *  Copyright (C) 2010 Paul Mundt <lethal@linux-sh.org>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -11,25 +7,25 @@
  *
  * Helper for the clk API to assist looking up a struct clk.
  */
-#ifndef __ASM_CLKDEV_H
-#define __ASM_CLKDEV_H
 
-struct clk;
+#ifndef __CLKDEV__H_
+#define __CLKDEV__H_
 
-struct clk_lookup {
-	struct list_head	node;
-	const char		*dev_id;
-	const char		*con_id;
-	struct clk		*clk;
-};
+#include <linux/bootmem.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
 
-struct clk_lookup *clkdev_alloc(struct clk *clk, const char *con_id,
-	const char *dev_fmt, ...);
+#include <asm/clock.h>
 
-void clkdev_add(struct clk_lookup *cl);
-void clkdev_drop(struct clk_lookup *cl);
+static inline struct clk_lookup_alloc *__clkdev_alloc(size_t size)
+{
+	if (!slab_is_available())
+		return alloc_bootmem_low_pages(size);
+	else
+		return kzalloc(size, GFP_KERNEL);
+}
 
-void clkdev_add_table(struct clk_lookup *, size_t);
-int clk_add_alias(const char *, const char *, char *, struct device *);
+#define __clk_put(clk)
+#define __clk_get(clk) ({ 1; })
 
-#endif
+#endif /* __CLKDEV_H__ */
diff --git a/arch/sh/include/asm/io.h b/arch/sh/include/asm/io.h
index b237d525d592..89ab2c57a4c2 100644
--- a/arch/sh/include/asm/io.h
+++ b/arch/sh/include/asm/io.h
@@ -1,5 +1,6 @@
 #ifndef __ASM_SH_IO_H
 #define __ASM_SH_IO_H
+
 /*
  * Convention:
  *    read{b,w,l,q}/write{b,w,l,q} are for PCI,
@@ -15,12 +16,6 @@
  * SuperH specific I/O (raw I/O to on-chip CPU peripherals). In practice
  * these have the same semantics as the __raw variants, and as such, all
  * new code should be using the __raw versions.
- *
- * All ISA I/O routines are wrapped through the machine vector. If a
- * board does not provide overrides, a generic set that are copied in
- * from the default machine vector are used instead. These are largely
- * for old compat code for I/O offseting to SuperIOs, all of which are
- * better handled through the machvec ioport mapping routines these days.
  */
 #include <linux/errno.h>
 #include <asm/cache.h>
@@ -31,39 +26,10 @@
 #include <asm-generic/iomap.h>
 
 #ifdef __KERNEL__
-/*
- * Depending on which platform we are running on, we need different
- * I/O functions.
- */
-#define __IO_PREFIX	generic
+#define __IO_PREFIX     generic
 #include <asm/io_generic.h>
 #include <asm/io_trapped.h>
 
-#ifdef CONFIG_HAS_IOPORT
-
-#define inb(p)			sh_mv.mv_inb((p))
-#define inw(p)			sh_mv.mv_inw((p))
-#define inl(p)			sh_mv.mv_inl((p))
-#define outb(x,p)		sh_mv.mv_outb((x),(p))
-#define outw(x,p)		sh_mv.mv_outw((x),(p))
-#define outl(x,p)		sh_mv.mv_outl((x),(p))
-
-#define inb_p(p)		sh_mv.mv_inb_p((p))
-#define inw_p(p)		sh_mv.mv_inw_p((p))
-#define inl_p(p)		sh_mv.mv_inl_p((p))
-#define outb_p(x,p)		sh_mv.mv_outb_p((x),(p))
-#define outw_p(x,p)		sh_mv.mv_outw_p((x),(p))
-#define outl_p(x,p)		sh_mv.mv_outl_p((x),(p))
-
-#define insb(p,b,c)		sh_mv.mv_insb((p), (b), (c))
-#define insw(p,b,c)		sh_mv.mv_insw((p), (b), (c))
-#define insl(p,b,c)		sh_mv.mv_insl((p), (b), (c))
-#define outsb(p,b,c)		sh_mv.mv_outsb((p), (b), (c))
-#define outsw(p,b,c)		sh_mv.mv_outsw((p), (b), (c))
-#define outsl(p,b,c)		sh_mv.mv_outsl((p), (b), (c))
-
-#endif
-
 #define __raw_writeb(v,a)	(__chk_io_ptr(a), *(volatile u8  __force *)(a) = (v))
 #define __raw_writew(v,a)	(__chk_io_ptr(a), *(volatile u16 __force *)(a) = (v))
 #define __raw_writel(v,a)	(__chk_io_ptr(a), *(volatile u32 __force *)(a) = (v))
@@ -74,68 +40,39 @@
 #define __raw_readl(a)		(__chk_io_ptr(a), *(volatile u32 __force *)(a))
 #define __raw_readq(a)		(__chk_io_ptr(a), *(volatile u64 __force *)(a))
 
-#define readb(a)		({ u8  r_ = __raw_readb(a); mb(); r_; })
-#define readw(a)		({ u16 r_ = __raw_readw(a); mb(); r_; })
-#define readl(a)		({ u32 r_ = __raw_readl(a); mb(); r_; })
-#define readq(a)		({ u64 r_ = __raw_readq(a); mb(); r_; })
-
-#define writeb(v,a)		({ __raw_writeb((v),(a)); mb(); })
-#define writew(v,a)		({ __raw_writew((v),(a)); mb(); })
-#define writel(v,a)		({ __raw_writel((v),(a)); mb(); })
-#define writeq(v,a)		({ __raw_writeq((v),(a)); mb(); })
-
-/*
- * Legacy SuperH on-chip I/O functions
- *
- * These are all deprecated, all new (and especially cross-platform) code
- * should be using the __raw_xxx() routines directly.
- */
-static inline u8 __deprecated ctrl_inb(unsigned long addr)
-{
-	return __raw_readb(addr);
-}
-
-static inline u16 __deprecated ctrl_inw(unsigned long addr)
-{
-	return __raw_readw(addr);
-}
-
-static inline u32 __deprecated ctrl_inl(unsigned long addr)
-{
-	return __raw_readl(addr);
-}
-
-static inline u64 __deprecated ctrl_inq(unsigned long addr)
-{
-	return __raw_readq(addr);
-}
-
-static inline void __deprecated ctrl_outb(u8 v, unsigned long addr)
-{
-	__raw_writeb(v, addr);
-}
-
-static inline void __deprecated ctrl_outw(u16 v, unsigned long addr)
-{
-	__raw_writew(v, addr);
-}
-
-static inline void __deprecated ctrl_outl(u32 v, unsigned long addr)
-{
-	__raw_writel(v, addr);
-}
-
-static inline void __deprecated ctrl_outq(u64 v, unsigned long addr)
-{
-	__raw_writeq(v, addr);
-}
-
-extern unsigned long generic_io_base;
-
-static inline void ctrl_delay(void)
-{
-	__raw_readw(generic_io_base);
-}
+#define readb_relaxed(c)	({ u8  __v = __raw_readb(c); __v; })
+#define readw_relaxed(c)	({ u16 __v = le16_to_cpu((__force __le16) \
+					__raw_readw(c)); __v; })
+#define readl_relaxed(c)	({ u32 __v = le32_to_cpu((__force __le32) \
+					__raw_readl(c)); __v; })
+#define readq_relaxed(c)	({ u64 __v = le64_to_cpu((__force __le64) \
+					__raw_readq(c)); __v; })
+
+#define writeb_relaxed(v,c)	((void)__raw_writeb(v,c))
+#define writew_relaxed(v,c)	((void)__raw_writew((__force u16) \
+					cpu_to_le16(v),c))
+#define writel_relaxed(v,c)	((void)__raw_writel((__force u32) \
+					cpu_to_le32(v),c))
+#define writeq_relaxed(v,c)	((void)__raw_writeq((__force u64) \
+					cpu_to_le64(v),c))
+
+#define readb(a)		({ u8  r_ = readb_relaxed(a); rmb(); r_; })
+#define readw(a)		({ u16 r_ = readw_relaxed(a); rmb(); r_; })
+#define readl(a)		({ u32 r_ = readl_relaxed(a); rmb(); r_; })
+#define readq(a)		({ u64 r_ = readq_relaxed(a); rmb(); r_; })
+
+#define writeb(v,a)		({ wmb(); writeb_relaxed((v),(a)); })
+#define writew(v,a)		({ wmb(); writew_relaxed((v),(a)); })
+#define writel(v,a)		({ wmb(); writel_relaxed((v),(a)); })
+#define writeq(v,a)		({ wmb(); writeq_relaxed((v),(a)); })
+
+#define readsb(p,d,l)		__raw_readsb(p,d,l)
+#define readsw(p,d,l)		__raw_readsw(p,d,l)
+#define readsl(p,d,l)		__raw_readsl(p,d,l)
+
+#define writesb(p,d,l)		__raw_writesb(p,d,l)
+#define writesw(p,d,l)		__raw_writesw(p,d,l)
+#define writesl(p,d,l)		__raw_writesl(p,d,l)
 
 #define __BUILD_UNCACHED_IO(bwlq, type)					\
 static inline type read##bwlq##_uncached(unsigned long addr)		\
@@ -159,10 +96,11 @@ __BUILD_UNCACHED_IO(w, u16)
 __BUILD_UNCACHED_IO(l, u32)
 __BUILD_UNCACHED_IO(q, u64)
 
-#define __BUILD_MEMORY_STRING(bwlq, type)				\
+#define __BUILD_MEMORY_STRING(pfx, bwlq, type)				\
 									\
-static inline void __raw_writes##bwlq(volatile void __iomem *mem,	\
-				const void *addr, unsigned int count)	\
+static inline void							\
+pfx##writes##bwlq(volatile void __iomem *mem, const void *addr,		\
+		  unsigned int count)					\
 {									\
 	const volatile type *__addr = addr;				\
 									\
@@ -172,8 +110,8 @@ static inline void __raw_writes##bwlq(volatile void __iomem *mem,	\
 	}								\
 }									\
 									\
-static inline void __raw_reads##bwlq(volatile void __iomem *mem,	\
-			       void *addr, unsigned int count)		\
+static inline void pfx##reads##bwlq(volatile void __iomem *mem,		\
+				    void *addr, unsigned int count)	\
 {									\
 	volatile type *__addr = addr;					\
 									\
@@ -183,85 +121,166 @@ static inline void __raw_reads##bwlq(volatile void __iomem *mem,	\
 	}								\
 }
 
-__BUILD_MEMORY_STRING(b, u8)
-__BUILD_MEMORY_STRING(w, u16)
+__BUILD_MEMORY_STRING(__raw_, b, u8)
+__BUILD_MEMORY_STRING(__raw_, w, u16)
 
 #ifdef CONFIG_SUPERH32
 void __raw_writesl(void __iomem *addr, const void *data, int longlen);
 void __raw_readsl(const void __iomem *addr, void *data, int longlen);
 #else
-__BUILD_MEMORY_STRING(l, u32)
+__BUILD_MEMORY_STRING(__raw_, l, u32)
 #endif
 
-__BUILD_MEMORY_STRING(q, u64)
-
-#define writesb			__raw_writesb
-#define writesw			__raw_writesw
-#define writesl			__raw_writesl
-
-#define readsb			__raw_readsb
-#define readsw			__raw_readsw
-#define readsl			__raw_readsl
-
-#define readb_relaxed(a)	readb(a)
-#define readw_relaxed(a)	readw(a)
-#define readl_relaxed(a)	readl(a)
-#define readq_relaxed(a)	readq(a)
-
-#ifndef CONFIG_GENERIC_IOMAP
-/* Simple MMIO */
-#define ioread8(a)		__raw_readb(a)
-#define ioread16(a)		__raw_readw(a)
-#define ioread16be(a)		be16_to_cpu(__raw_readw((a)))
-#define ioread32(a)		__raw_readl(a)
-#define ioread32be(a)		be32_to_cpu(__raw_readl((a)))
-
-#define iowrite8(v,a)		__raw_writeb((v),(a))
-#define iowrite16(v,a)		__raw_writew((v),(a))
-#define iowrite16be(v,a)	__raw_writew(cpu_to_be16((v)),(a))
-#define iowrite32(v,a)		__raw_writel((v),(a))
-#define iowrite32be(v,a)	__raw_writel(cpu_to_be32((v)),(a))
-
-#define ioread8_rep(a, d, c)	__raw_readsb((a), (d), (c))
-#define ioread16_rep(a, d, c)	__raw_readsw((a), (d), (c))
-#define ioread32_rep(a, d, c)	__raw_readsl((a), (d), (c))
-
-#define iowrite8_rep(a, s, c)	__raw_writesb((a), (s), (c))
-#define iowrite16_rep(a, s, c)	__raw_writesw((a), (s), (c))
-#define iowrite32_rep(a, s, c)	__raw_writesl((a), (s), (c))
+__BUILD_MEMORY_STRING(__raw_, q, u64)
+
+#ifdef CONFIG_HAS_IOPORT
+
+/*
+ * Slowdown I/O port space accesses for antique hardware.
+ */
+#undef CONF_SLOWDOWN_IO
+
+/*
+ * On SuperH I/O ports are memory mapped, so we access them using normal
+ * load/store instructions. sh_io_port_base is the virtual address to
+ * which all ports are being mapped.
+ */
+extern const unsigned long sh_io_port_base;
+
+static inline void __set_io_port_base(unsigned long pbase)
+{
+	*(unsigned long *)&sh_io_port_base = pbase;
+	barrier();
+}
+
+#ifdef CONFIG_GENERIC_IOMAP
+#define __ioport_map ioport_map
+#else
+extern void __iomem *__ioport_map(unsigned long addr, unsigned int size);
 #endif
 
-#define mmio_insb(p,d,c)	__raw_readsb(p,d,c)
-#define mmio_insw(p,d,c)	__raw_readsw(p,d,c)
-#define mmio_insl(p,d,c)	__raw_readsl(p,d,c)
+#ifdef CONF_SLOWDOWN_IO
+#define SLOW_DOWN_IO __raw_readw(sh_io_port_base)
+#else
+#define SLOW_DOWN_IO
+#endif
 
-#define mmio_outsb(p,s,c)	__raw_writesb(p,s,c)
-#define mmio_outsw(p,s,c)	__raw_writesw(p,s,c)
-#define mmio_outsl(p,s,c)	__raw_writesl(p,s,c)
+#define __BUILD_IOPORT_SINGLE(pfx, bwlq, type, p, slow)			\
+									\
+static inline void pfx##out##bwlq##p(type val, unsigned long port)	\
+{									\
+	volatile type *__addr;						\
+									\
+	__addr = __ioport_map(port, sizeof(type));			\
+	*__addr = val;							\
+	slow;								\
+}									\
+									\
+static inline type pfx##in##bwlq##p(unsigned long port)			\
+{									\
+	volatile type *__addr;						\
+	type __val;							\
+									\
+	__addr = __ioport_map(port, sizeof(type));			\
+	__val = *__addr;						\
+	slow;								\
+									\
+	return __val;							\
+}
 
-/* synco on SH-4A, otherwise a nop */
-#define mmiowb()		wmb()
+#define __BUILD_IOPORT_PFX(bus, bwlq, type)				\
+	__BUILD_IOPORT_SINGLE(bus, bwlq, type, ,)			\
+	__BUILD_IOPORT_SINGLE(bus, bwlq, type, _p, SLOW_DOWN_IO)
 
-#define IO_SPACE_LIMIT 0xffffffff
+#define BUILDIO_IOPORT(bwlq, type)					\
+	__BUILD_IOPORT_PFX(, bwlq, type)
 
-#ifdef CONFIG_HAS_IOPORT
+BUILDIO_IOPORT(b, u8)
+BUILDIO_IOPORT(w, u16)
+BUILDIO_IOPORT(l, u32)
+BUILDIO_IOPORT(q, u64)
+
+#define __BUILD_IOPORT_STRING(bwlq, type)				\
+									\
+static inline void outs##bwlq(unsigned long port, const void *addr,	\
+			      unsigned int count)			\
+{									\
+	const volatile type *__addr = addr;				\
+									\
+	while (count--) {						\
+		out##bwlq(*__addr, port);				\
+		__addr++;						\
+	}								\
+}									\
+									\
+static inline void ins##bwlq(unsigned long port, void *addr,		\
+			     unsigned int count)			\
+{									\
+	volatile type *__addr = addr;					\
+									\
+	while (count--) {						\
+		*__addr = in##bwlq(port);				\
+		__addr++;						\
+	}								\
+}
+
+__BUILD_IOPORT_STRING(b, u8)
+__BUILD_IOPORT_STRING(w, u16)
+__BUILD_IOPORT_STRING(l, u32)
+__BUILD_IOPORT_STRING(q, u64)
+
+#endif
 
 /*
- * This function provides a method for the generic case where a
- * board-specific ioport_map simply needs to return the port + some
- * arbitrary port base.
+ * Legacy SuperH on-chip I/O functions
  *
- * We use this at board setup time to implicitly set the port base, and
- * as a result, we can use the generic ioport_map.
+ * These are all deprecated, all new (and especially cross-platform) code
+ * should be using the __raw_xxx() routines directly.
  */
-static inline void __set_io_port_base(unsigned long pbase)
+static inline u8 __deprecated ctrl_inb(unsigned long addr)
 {
-	generic_io_base = pbase;
+	return __raw_readb(addr);
 }
 
-#define __ioport_map(p, n) sh_mv.mv_ioport_map((p), (n))
+static inline u16 __deprecated ctrl_inw(unsigned long addr)
+{
+	return __raw_readw(addr);
+}
 
-#endif
+static inline u32 __deprecated ctrl_inl(unsigned long addr)
+{
+	return __raw_readl(addr);
+}
+
+static inline u64 __deprecated ctrl_inq(unsigned long addr)
+{
+	return __raw_readq(addr);
+}
+
+static inline void __deprecated ctrl_outb(u8 v, unsigned long addr)
+{
+	__raw_writeb(v, addr);
+}
+
+static inline void __deprecated ctrl_outw(u16 v, unsigned long addr)
+{
+	__raw_writew(v, addr);
+}
+
+static inline void __deprecated ctrl_outl(u32 v, unsigned long addr)
+{
+	__raw_writel(v, addr);
+}
+
+static inline void __deprecated ctrl_outq(u64 v, unsigned long addr)
+{
+	__raw_writeq(v, addr);
+}
+
+#define IO_SPACE_LIMIT 0xffffffff
+
+/* synco on SH-4A, otherwise a nop */
+#define mmiowb()		wmb()
 
 /* We really want to try and get these to memcpy etc */
 void memcpy_fromio(void *, const volatile void __iomem *, unsigned long);
@@ -395,10 +414,6 @@ static inline int iounmap_fixed(void __iomem *addr) { return -EINVAL; }
 #define ioremap_nocache	ioremap
 #define iounmap		__iounmap
 
-#define maybebadio(port) \
-	printk(KERN_ERR "bad PC-like io %s:%u for port 0x%lx at 0x%08x\n", \
-	       __func__, __LINE__, (port), (u32)__builtin_return_address(0))
-
 /*
  * Convert a physical pointer to a virtual kernel pointer for /dev/mem
  * access
diff --git a/arch/sh/include/asm/io_generic.h b/arch/sh/include/asm/io_generic.h
index 491df93cbf8e..b5f6956f19c8 100644
--- a/arch/sh/include/asm/io_generic.h
+++ b/arch/sh/include/asm/io_generic.h
@@ -11,31 +11,6 @@
 #error "Don't include this header without a valid system prefix"
 #endif
 
-u8 IO_CONCAT(__IO_PREFIX,inb)(unsigned long);
-u16 IO_CONCAT(__IO_PREFIX,inw)(unsigned long);
-u32 IO_CONCAT(__IO_PREFIX,inl)(unsigned long);
-
-void IO_CONCAT(__IO_PREFIX,outb)(u8, unsigned long);
-void IO_CONCAT(__IO_PREFIX,outw)(u16, unsigned long);
-void IO_CONCAT(__IO_PREFIX,outl)(u32, unsigned long);
-
-u8 IO_CONCAT(__IO_PREFIX,inb_p)(unsigned long);
-u16 IO_CONCAT(__IO_PREFIX,inw_p)(unsigned long);
-u32 IO_CONCAT(__IO_PREFIX,inl_p)(unsigned long);
-void IO_CONCAT(__IO_PREFIX,outb_p)(u8, unsigned long);
-void IO_CONCAT(__IO_PREFIX,outw_p)(u16, unsigned long);
-void IO_CONCAT(__IO_PREFIX,outl_p)(u32, unsigned long);
-
-void IO_CONCAT(__IO_PREFIX,insb)(unsigned long, void *dst, unsigned long count);
-void IO_CONCAT(__IO_PREFIX,insw)(unsigned long, void *dst, unsigned long count);
-void IO_CONCAT(__IO_PREFIX,insl)(unsigned long, void *dst, unsigned long count);
-void IO_CONCAT(__IO_PREFIX,outsb)(unsigned long, const void *src, unsigned long count);
-void IO_CONCAT(__IO_PREFIX,outsw)(unsigned long, const void *src, unsigned long count);
-void IO_CONCAT(__IO_PREFIX,outsl)(unsigned long, const void *src, unsigned long count);
-
-void *IO_CONCAT(__IO_PREFIX,ioremap)(unsigned long offset, unsigned long size);
-void IO_CONCAT(__IO_PREFIX,iounmap)(void *addr);
-
 void __iomem *IO_CONCAT(__IO_PREFIX,ioport_map)(unsigned long addr, unsigned int size);
 void IO_CONCAT(__IO_PREFIX,ioport_unmap)(void __iomem *addr);
 void IO_CONCAT(__IO_PREFIX,mem_init)(void);
diff --git a/arch/sh/include/asm/ioctls.h b/arch/sh/include/asm/ioctls.h
index eb6c4c687972..84e85a792638 100644
--- a/arch/sh/include/asm/ioctls.h
+++ b/arch/sh/include/asm/ioctls.h
@@ -85,6 +85,7 @@
 #define TCSETSF2	_IOW('T', 45, struct termios2)
 #define TIOCGPTN	_IOR('T',0x30, unsigned int) /* Get Pty Number (of pty-mux device) */
 #define TIOCSPTLCK	_IOW('T',0x31, int)  /* Lock/unlock Pty */
+#define TIOCGDEV	_IOR('T',0x32, unsigned int) /* Get primary device node of /dev/console */
 #define TIOCSIG		_IOW('T',0x36, int)  /* Generate signal on Pty slave */
 
 #define TIOCSERCONFIG	_IO('T', 83) /* 0x5453 */
diff --git a/arch/sh/include/asm/machvec.h b/arch/sh/include/asm/machvec.h
index a0b0cf79cf8a..dd5d6e5bf204 100644
--- a/arch/sh/include/asm/machvec.h
+++ b/arch/sh/include/asm/machvec.h
@@ -23,27 +23,6 @@ struct sh_machine_vector {
 	void (*mv_init_irq)(void);
 
 #ifdef CONFIG_HAS_IOPORT
-	u8 (*mv_inb)(unsigned long);
-	u16 (*mv_inw)(unsigned long);
-	u32 (*mv_inl)(unsigned long);
-	void (*mv_outb)(u8, unsigned long);
-	void (*mv_outw)(u16, unsigned long);
-	void (*mv_outl)(u32, unsigned long);
-
-	u8 (*mv_inb_p)(unsigned long);
-	u16 (*mv_inw_p)(unsigned long);
-	u32 (*mv_inl_p)(unsigned long);
-	void (*mv_outb_p)(u8, unsigned long);
-	void (*mv_outw_p)(u16, unsigned long);
-	void (*mv_outl_p)(u32, unsigned long);
-
-	void (*mv_insb)(unsigned long, void *dst, unsigned long count);
-	void (*mv_insw)(unsigned long, void *dst, unsigned long count);
-	void (*mv_insl)(unsigned long, void *dst, unsigned long count);
-	void (*mv_outsb)(unsigned long, const void *src, unsigned long count);
-	void (*mv_outsw)(unsigned long, const void *src, unsigned long count);
-	void (*mv_outsl)(unsigned long, const void *src, unsigned long count);
-
 	void __iomem *(*mv_ioport_map)(unsigned long port, unsigned int size);
 	void (*mv_ioport_unmap)(void __iomem *);
 #endif
diff --git a/arch/sh/include/asm/processor_32.h b/arch/sh/include/asm/processor_32.h
index 46d5179c9f49..e3c73cdd8c90 100644
--- a/arch/sh/include/asm/processor_32.h
+++ b/arch/sh/include/asm/processor_32.h
@@ -199,10 +199,13 @@ extern unsigned long get_wchan(struct task_struct *p);
 #define ARCH_HAS_PREFETCHW
 static inline void prefetch(void *x)
 {
-	__asm__ __volatile__ ("pref @%0\n\t" : : "r" (x) : "memory");
+	__builtin_prefetch(x, 0, 3);
 }
 
-#define prefetchw(x)	prefetch(x)
+static inline void prefetchw(void *x)
+{
+	__builtin_prefetch(x, 1, 3);
+}
 #endif
 
 #endif /* __KERNEL__ */
diff --git a/arch/sh/include/asm/ptrace.h b/arch/sh/include/asm/ptrace.h
index f6edc10aa0d3..de167d3a1a80 100644
--- a/arch/sh/include/asm/ptrace.h
+++ b/arch/sh/include/asm/ptrace.h
@@ -40,8 +40,8 @@
 #include <asm/system.h>
 
 #define user_mode(regs)			(((regs)->sr & 0x40000000)==0)
-#define user_stack_pointer(regs)	((unsigned long)(regs)->regs[15])
-#define kernel_stack_pointer(regs)	((unsigned long)(regs)->regs[15])
+#define user_stack_pointer(_regs)	((unsigned long)(_regs)->regs[15])
+#define kernel_stack_pointer(_regs)	((unsigned long)(_regs)->regs[15])
 #define instruction_pointer(regs)	((unsigned long)(regs)->pc)
 
 extern void show_regs(struct pt_regs *);
diff --git a/arch/sh/include/asm/ptrace_32.h b/arch/sh/include/asm/ptrace_32.h
index 35d9e257558c..6c2239cca1a2 100644
--- a/arch/sh/include/asm/ptrace_32.h
+++ b/arch/sh/include/asm/ptrace_32.h
@@ -76,7 +76,7 @@ struct pt_dspregs {
 #ifdef __KERNEL__
 
 #define MAX_REG_OFFSET		offsetof(struct pt_regs, tra)
-#define regs_return_value(regs)	((regs)->regs[0])
+#define regs_return_value(_regs)	((_regs)->regs[0])
 
 #endif /* __KERNEL__ */
 
diff --git a/arch/sh/include/asm/ptrace_64.h b/arch/sh/include/asm/ptrace_64.h
index d43c1cb0bbe7..bf9be7764d69 100644
--- a/arch/sh/include/asm/ptrace_64.h
+++ b/arch/sh/include/asm/ptrace_64.h
@@ -13,7 +13,7 @@ struct pt_regs {
 #ifdef __KERNEL__
 
 #define MAX_REG_OFFSET		offsetof(struct pt_regs, tregs[7])
-#define regs_return_value(regs)	((regs)->regs[3])
+#define regs_return_value(_regs)	((_regs)->regs[3])
 
 #endif /* __KERNEL__ */
 
diff --git a/arch/sh/include/asm/unaligned-sh4a.h b/arch/sh/include/asm/unaligned-sh4a.h
index 9f4dd252c981..c48a9c3420da 100644
--- a/arch/sh/include/asm/unaligned-sh4a.h
+++ b/arch/sh/include/asm/unaligned-sh4a.h
@@ -18,10 +18,20 @@
  * of spill registers and blowing up when building at low optimization
  * levels. See http://gcc.gnu.org/bugzilla/show_bug.cgi?id=34777.
  */
+#include <linux/unaligned/packed_struct.h>
 #include <linux/types.h>
 #include <asm/byteorder.h>
 
-static __always_inline u32 __get_unaligned_cpu32(const u8 *p)
+static inline u16 sh4a_get_unaligned_cpu16(const u8 *p)
+{
+#ifdef __LITTLE_ENDIAN
+	return p[0] | p[1] << 8;
+#else
+	return p[0] << 8 | p[1];
+#endif
+}
+
+static __always_inline u32 sh4a_get_unaligned_cpu32(const u8 *p)
 {
 	unsigned long unaligned;
 
@@ -34,218 +44,148 @@ static __always_inline u32 __get_unaligned_cpu32(const u8 *p)
 	return unaligned;
 }
 
-struct __una_u16 { u16 x __attribute__((packed)); };
-struct __una_u32 { u32 x __attribute__((packed)); };
-struct __una_u64 { u64 x __attribute__((packed)); };
-
-static inline u16 __get_unaligned_cpu16(const u8 *p)
-{
-#ifdef __LITTLE_ENDIAN
-	return p[0] | p[1] << 8;
-#else
-	return p[0] << 8 | p[1];
-#endif
-}
-
 /*
  * Even though movua.l supports auto-increment on the read side, it can
  * only store to r0 due to instruction encoding constraints, so just let
  * the compiler sort it out on its own.
  */
-static inline u64 __get_unaligned_cpu64(const u8 *p)
+static inline u64 sh4a_get_unaligned_cpu64(const u8 *p)
 {
 #ifdef __LITTLE_ENDIAN
-	return (u64)__get_unaligned_cpu32(p + 4) << 32 |
-		    __get_unaligned_cpu32(p);
+	return (u64)sh4a_get_unaligned_cpu32(p + 4) << 32 |
+		    sh4a_get_unaligned_cpu32(p);
 #else
-	return (u64)__get_unaligned_cpu32(p) << 32 |
-		    __get_unaligned_cpu32(p + 4);
+	return (u64)sh4a_get_unaligned_cpu32(p) << 32 |
+		    sh4a_get_unaligned_cpu32(p + 4);
 #endif
 }
 
 static inline u16 get_unaligned_le16(const void *p)
 {
-	return le16_to_cpu(__get_unaligned_cpu16(p));
+	return le16_to_cpu(sh4a_get_unaligned_cpu16(p));
 }
 
 static inline u32 get_unaligned_le32(const void *p)
 {
-	return le32_to_cpu(__get_unaligned_cpu32(p));
+	return le32_to_cpu(sh4a_get_unaligned_cpu32(p));
 }
 
 static inline u64 get_unaligned_le64(const void *p)
 {
-	return le64_to_cpu(__get_unaligned_cpu64(p));
+	return le64_to_cpu(sh4a_get_unaligned_cpu64(p));
 }
 
 static inline u16 get_unaligned_be16(const void *p)
 {
-	return be16_to_cpu(__get_unaligned_cpu16(p));
+	return be16_to_cpu(sh4a_get_unaligned_cpu16(p));
 }
 
 static inline u32 get_unaligned_be32(const void *p)
 {
-	return be32_to_cpu(__get_unaligned_cpu32(p));
+	return be32_to_cpu(sh4a_get_unaligned_cpu32(p));
 }
 
 static inline u64 get_unaligned_be64(const void *p)
 {
-	return be64_to_cpu(__get_unaligned_cpu64(p));
+	return be64_to_cpu(sh4a_get_unaligned_cpu64(p));
 }
 
-static inline void __put_le16_noalign(u8 *p, u16 val)
+static inline void nonnative_put_le16(u16 val, u8 *p)
 {
 	*p++ = val;
 	*p++ = val >> 8;
 }
 
-static inline void __put_le32_noalign(u8 *p, u32 val)
+static inline void nonnative_put_le32(u32 val, u8 *p)
 {
-	__put_le16_noalign(p, val);
-	__put_le16_noalign(p + 2, val >> 16);
+	nonnative_put_le16(val, p);
+	nonnative_put_le16(val >> 16, p + 2);
 }
 
-static inline void __put_le64_noalign(u8 *p, u64 val)
+static inline void nonnative_put_le64(u64 val, u8 *p)
 {
-	__put_le32_noalign(p, val);
-	__put_le32_noalign(p + 4, val >> 32);
+	nonnative_put_le32(val, p);
+	nonnative_put_le32(val >> 32, p + 4);
 }
 
-static inline void __put_be16_noalign(u8 *p, u16 val)
+static inline void nonnative_put_be16(u16 val, u8 *p)
 {
 	*p++ = val >> 8;
 	*p++ = val;
 }
 
-static inline void __put_be32_noalign(u8 *p, u32 val)
+static inline void nonnative_put_be32(u32 val, u8 *p)
 {
-	__put_be16_noalign(p, val >> 16);
-	__put_be16_noalign(p + 2, val);
+	nonnative_put_be16(val >> 16, p);
+	nonnative_put_be16(val, p + 2);
 }
 
-static inline void __put_be64_noalign(u8 *p, u64 val)
+static inline void nonnative_put_be64(u64 val, u8 *p)
 {
-	__put_be32_noalign(p, val >> 32);
-	__put_be32_noalign(p + 4, val);
+	nonnative_put_be32(val >> 32, p);
+	nonnative_put_be32(val, p + 4);
 }
 
 static inline void put_unaligned_le16(u16 val, void *p)
 {
 #ifdef __LITTLE_ENDIAN
-	((struct __una_u16 *)p)->x = val;
+	__put_unaligned_cpu16(val, p);
 #else
-	__put_le16_noalign(p, val);
+	nonnative_put_le16(val, p);
 #endif
 }
 
 static inline void put_unaligned_le32(u32 val, void *p)
 {
 #ifdef __LITTLE_ENDIAN
-	((struct __una_u32 *)p)->x = val;
+	__put_unaligned_cpu32(val, p);
 #else
-	__put_le32_noalign(p, val);
+	nonnative_put_le32(val, p);
 #endif
 }
 
 static inline void put_unaligned_le64(u64 val, void *p)
 {
 #ifdef __LITTLE_ENDIAN
-	((struct __una_u64 *)p)->x = val;
+	__put_unaligned_cpu64(val, p);
 #else
-	__put_le64_noalign(p, val);
+	nonnative_put_le64(val, p);
 #endif
 }
 
 static inline void put_unaligned_be16(u16 val, void *p)
 {
 #ifdef __BIG_ENDIAN
-	((struct __una_u16 *)p)->x = val;
+	__put_unaligned_cpu16(val, p);
 #else
-	__put_be16_noalign(p, val);
+	nonnative_put_be16(val, p);
 #endif
 }
 
 static inline void put_unaligned_be32(u32 val, void *p)
 {
 #ifdef __BIG_ENDIAN
-	((struct __una_u32 *)p)->x = val;
+	__put_unaligned_cpu32(val, p);
 #else
-	__put_be32_noalign(p, val);
+	nonnative_put_be32(val, p);
 #endif
 }
 
 static inline void put_unaligned_be64(u64 val, void *p)
 {
 #ifdef __BIG_ENDIAN
-	((struct __una_u64 *)p)->x = val;
+	__put_unaligned_cpu64(val, p);
 #else
-	__put_be64_noalign(p, val);
+	nonnative_put_be64(val, p);
 #endif
 }
 
 /*
- * Cause a link-time error if we try an unaligned access other than
- * 1,2,4 or 8 bytes long
+ * While it's a bit non-obvious, even though the generic le/be wrappers
+ * use the __get/put_xxx prefixing, they actually wrap in to the
+ * non-prefixed get/put_xxx variants as provided above.
  */
-extern void __bad_unaligned_access_size(void);
-
-#define __get_unaligned_le(ptr) ((__force typeof(*(ptr)))({			\
-	__builtin_choose_expr(sizeof(*(ptr)) == 1, *(ptr),			\
-	__builtin_choose_expr(sizeof(*(ptr)) == 2, get_unaligned_le16((ptr)),	\
-	__builtin_choose_expr(sizeof(*(ptr)) == 4, get_unaligned_le32((ptr)),	\
-	__builtin_choose_expr(sizeof(*(ptr)) == 8, get_unaligned_le64((ptr)),	\
-	__bad_unaligned_access_size()))));					\
-	}))
-
-#define __get_unaligned_be(ptr) ((__force typeof(*(ptr)))({			\
-	__builtin_choose_expr(sizeof(*(ptr)) == 1, *(ptr),			\
-	__builtin_choose_expr(sizeof(*(ptr)) == 2, get_unaligned_be16((ptr)),	\
-	__builtin_choose_expr(sizeof(*(ptr)) == 4, get_unaligned_be32((ptr)),	\
-	__builtin_choose_expr(sizeof(*(ptr)) == 8, get_unaligned_be64((ptr)),	\
-	__bad_unaligned_access_size()))));					\
-	}))
-
-#define __put_unaligned_le(val, ptr) ({					\
-	void *__gu_p = (ptr);						\
-	switch (sizeof(*(ptr))) {					\
-	case 1:								\
-		*(u8 *)__gu_p = (__force u8)(val);			\
-		break;							\
-	case 2:								\
-		put_unaligned_le16((__force u16)(val), __gu_p);		\
-		break;							\
-	case 4:								\
-		put_unaligned_le32((__force u32)(val), __gu_p);		\
-		break;							\
-	case 8:								\
-		put_unaligned_le64((__force u64)(val), __gu_p);		\
-		break;							\
-	default:							\
-		__bad_unaligned_access_size();				\
-		break;							\
-	}								\
-	(void)0; })
-
-#define __put_unaligned_be(val, ptr) ({					\
-	void *__gu_p = (ptr);						\
-	switch (sizeof(*(ptr))) {					\
-	case 1:								\
-		*(u8 *)__gu_p = (__force u8)(val);			\
-		break;							\
-	case 2:								\
-		put_unaligned_be16((__force u16)(val), __gu_p);		\
-		break;							\
-	case 4:								\
-		put_unaligned_be32((__force u32)(val), __gu_p);		\
-		break;							\
-	case 8:								\
-		put_unaligned_be64((__force u64)(val), __gu_p);		\
-		break;							\
-	default:							\
-		__bad_unaligned_access_size();				\
-		break;							\
-	}								\
-	(void)0; })
+#include <linux/unaligned/generic.h>
 
 #ifdef __LITTLE_ENDIAN
 # define get_unaligned __get_unaligned_le
diff --git a/arch/sh/include/asm/unistd_32.h b/arch/sh/include/asm/unistd_32.h
index 903cd618eb74..d6741fca89a4 100644
--- a/arch/sh/include/asm/unistd_32.h
+++ b/arch/sh/include/asm/unistd_32.h
@@ -368,8 +368,9 @@
 #define __NR_sendmsg		355
 #define __NR_recvmsg		356
 #define __NR_recvmmsg		357
+#define __NR_accept4		358
 
-#define NR_syscalls 358
+#define NR_syscalls 359
 
 #ifdef __KERNEL__
 
diff --git a/arch/sh/include/cpu-sh4/cpu/sh7724.h b/arch/sh/include/cpu-sh4/cpu/sh7724.h
index 4c27b68789b3..7eb435999426 100644
--- a/arch/sh/include/cpu-sh4/cpu/sh7724.h
+++ b/arch/sh/include/cpu-sh4/cpu/sh7724.h
@@ -303,4 +303,7 @@ enum {
 	SHDMA_SLAVE_SDHI1_RX,
 };
 
+extern struct clk sh7724_fsimcka_clk;
+extern struct clk sh7724_fsimckb_clk;
+
 #endif /* __ASM_SH7724_H__ */
diff --git a/arch/sh/include/mach-common/mach/romimage.h b/arch/sh/include/mach-common/mach/romimage.h
index 08fb42269ecd..3670455faaac 100644
--- a/arch/sh/include/mach-common/mach/romimage.h
+++ b/arch/sh/include/mach-common/mach/romimage.h
@@ -4,7 +4,7 @@
 
 #else /* __ASSEMBLY__ */
 
-extern inline void mmcif_update_progress(int nr)
+static inline void mmcif_update_progress(int nr)
 {
 }
 
diff --git a/arch/sh/include/mach-ecovec24/mach/romimage.h b/arch/sh/include/mach-ecovec24/mach/romimage.h
index 1dcf5e6c8d83..d63ef51ec186 100644
--- a/arch/sh/include/mach-ecovec24/mach/romimage.h
+++ b/arch/sh/include/mach-ecovec24/mach/romimage.h
@@ -35,7 +35,7 @@
 #define HIZCRA		0xa4050158
 #define PGDR		0xa405012c
 
-extern inline void mmcif_update_progress(int nr)
+static inline void mmcif_update_progress(int nr)
 {
 	/* disable Hi-Z for LED pins */
 	__raw_writew(__raw_readw(HIZCRA) & ~(1 << 1), HIZCRA);
diff --git a/arch/sh/include/mach-kfr2r09/mach/romimage.h b/arch/sh/include/mach-kfr2r09/mach/romimage.h
index 976256a323f2..7a883167c846 100644
--- a/arch/sh/include/mach-kfr2r09/mach/romimage.h
+++ b/arch/sh/include/mach-kfr2r09/mach/romimage.h
@@ -23,7 +23,7 @@
 
 #else /* __ASSEMBLY__ */
 
-extern inline void mmcif_update_progress(int nr)
+static inline void mmcif_update_progress(int nr)
 {
 }
 
diff --git a/arch/sh/include/mach-sdk7786/mach/fpga.h b/arch/sh/include/mach-sdk7786/mach/fpga.h
index 40f0c2d3690c..a9cdac469927 100644
--- a/arch/sh/include/mach-sdk7786/mach/fpga.h
+++ b/arch/sh/include/mach-sdk7786/mach/fpga.h
@@ -14,11 +14,16 @@
 #define INTTESTR	0x040
 #define SYSSR		0x050
 #define NRGPR		0x060
+
 #define NMISR		0x070
+#define  NMISR_MAN_NMI	BIT(0)
+#define  NMISR_AUX_NMI	BIT(1)
+#define  NMISR_MASK	(NMISR_MAN_NMI | NMISR_AUX_NMI)
 
 #define NMIMR		0x080
 #define  NMIMR_MAN_NMIM	BIT(0)	/* Manual NMI mask */
 #define  NMIMR_AUX_NMIM	BIT(1)	/* Auxiliary NMI mask */
+#define  NMIMR_MASK	(NMIMR_MAN_NMIM | NMIMR_AUX_NMIM)
 
 #define INTBSR		0x090
 #define INTBMR		0x0a0
@@ -126,6 +131,9 @@
 extern void __iomem *sdk7786_fpga_base;
 extern void sdk7786_fpga_init(void);
 
+/* arch/sh/boards/mach-sdk7786/nmi.c */
+extern void sdk7786_nmi_init(void);
+
 #define SDK7786_FPGA_REGADDR(reg)	(sdk7786_fpga_base + (reg))
 
 /*