Merge tag 'asm-generic-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/arnd/asm-generic

Pull asm-generic asm/io.h rewrite from Arnd Bergmann:
 "While there normally is no reason to have a pull request for
  asm-generic but have all changes get merged through whichever tree
  needs them, I do have a series for 3.19.

  There are two sets of patches that change significant portions of
  asm/io.h, and this branch contains both in order to resolve the
  conflicts:

   - Will Deacon has done a set of patches to ensure that all
     architectures define {read,write}{b,w,l,q}_relaxed() functions or
     get them by including asm-generic/io.h.

     These functions are commonly used on ARM specific drivers to avoid
     expensive L2 cache synchronization implied by the normal
     {read,write}{b,w,l,q}, but we need to define them on all
     architectures in order to share the drivers across architectures
     and to enable CONFIG_COMPILE_TEST configurations for them

   - Thierry Reding has done an unrelated set of patches that extends
     the asm-generic/io.h file to the degree necessary to make it useful
     on ARM64 and potentially other architectures"

* tag 'asm-generic-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/arnd/asm-generic: (29 commits)
  ARM64: use GENERIC_PCI_IOMAP
  sparc: io: remove duplicate relaxed accessors on sparc32
  ARM: sa11x0: Use void __iomem * in MMIO accessors
  arm64: Use include/asm-generic/io.h
  ARM: Use include/asm-generic/io.h
  asm-generic/io.h: Implement generic {read,write}s*()
  asm-generic/io.h: Reconcile I/O accessor overrides
  /dev/mem: Use more consistent data types
  Change xlate_dev_{kmem,mem}_ptr() prototypes
  ARM: ixp4xx: Properly override I/O accessors
  ARM: ixp4xx: Fix build with IXP4XX_INDIRECT_PCI
  ARM: ebsa110: Properly override I/O accessors
  ARC: Remove redundant PCI_IOBASE declaration
  documentation: memory-barriers: clarify relaxed io accessor semantics
  x86: io: implement dummy relaxed accessor macros for writes
  tile: io: implement dummy relaxed accessor macros for writes
  sparc: io: implement dummy relaxed accessor macros for writes
  powerpc: io: implement dummy relaxed accessor macros for writes
  parisc: io: implement dummy relaxed accessor macros for writes
  mn10300: io: implement dummy relaxed accessor macros for writes
  ...

33 files changed, 835 insertions, 368 deletions

diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index 22a969cdd476..4af4cea8cff0 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -2465,10 +2465,15 @@ functions:
      Please refer to the PCI specification for more information on interactions
      between PCI transactions.
 
- (*) readX_relaxed()
-
-     These are similar to readX(), but are not guaranteed to be ordered in any
-     way. Be aware that there is no I/O read barrier available.
+ (*) readX_relaxed(), writeX_relaxed()
+
+     These are similar to readX() and writeX(), but provide weaker memory
+     ordering guarantees. Specifically, they do not guarantee ordering with
+     respect to normal memory accesses (e.g. DMA buffers) nor do they guarantee
+     ordering with respect to LOCK or UNLOCK operations. If the latter is
+     required, an mmiowb() barrier can be used. Note that relaxed accesses to
+     the same peripheral are guaranteed to be ordered with respect to each
+     other.
 
  (*) ioreadX(), iowriteX()
 
diff --git a/arch/arc/include/asm/io.h b/arch/arc/include/asm/io.h
index 334ce7017a18..cabd518cb253 100644
--- a/arch/arc/include/asm/io.h
+++ b/arch/arc/include/asm/io.h
@@ -13,8 +13,6 @@
 #include <asm/byteorder.h>
 #include <asm/page.h>
 
-#define PCI_IOBASE ((void __iomem *)0)
-
 extern void __iomem *ioremap(unsigned long physaddr, unsigned long size);
 extern void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size,
 				  unsigned long flags);
diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h
index 180567408ee8..db58deb00aa7 100644
--- a/arch/arm/include/asm/io.h
+++ b/arch/arm/include/asm/io.h
@@ -47,13 +47,13 @@ extern void atomic_io_modify_relaxed(void __iomem *reg, u32 mask, u32 set);
  * Generic IO read/write.  These perform native-endian accesses.  Note
  * that some architectures will want to re-define __raw_{read,write}w.
  */
-extern void __raw_writesb(void __iomem *addr, const void *data, int bytelen);
-extern void __raw_writesw(void __iomem *addr, const void *data, int wordlen);
-extern void __raw_writesl(void __iomem *addr, const void *data, int longlen);
+void __raw_writesb(volatile void __iomem *addr, const void *data, int bytelen);
+void __raw_writesw(volatile void __iomem *addr, const void *data, int wordlen);
+void __raw_writesl(volatile void __iomem *addr, const void *data, int longlen);
 
-extern void __raw_readsb(const void __iomem *addr, void *data, int bytelen);
-extern void __raw_readsw(const void __iomem *addr, void *data, int wordlen);
-extern void __raw_readsl(const void __iomem *addr, void *data, int longlen);
+void __raw_readsb(const volatile void __iomem *addr, void *data, int bytelen);
+void __raw_readsw(const volatile void __iomem *addr, void *data, int wordlen);
+void __raw_readsl(const volatile void __iomem *addr, void *data, int longlen);
 
 #if __LINUX_ARM_ARCH__ < 6
 /*
@@ -69,6 +69,7 @@ extern void __raw_readsl(const void __iomem *addr, void *data, int longlen);
  * writeback addressing modes as these incur a significant performance
  * overhead (the address generation must be emulated in software).
  */
+#define __raw_writew __raw_writew
 static inline void __raw_writew(u16 val, volatile void __iomem *addr)
 {
 	asm volatile("strh %1, %0"
@@ -76,6 +77,7 @@ static inline void __raw_writew(u16 val, volatile void __iomem *addr)
 		     : "r" (val));
 }
 
+#define __raw_readw __raw_readw
 static inline u16 __raw_readw(const volatile void __iomem *addr)
 {
 	u16 val;
@@ -86,6 +88,7 @@ static inline u16 __raw_readw(const volatile void __iomem *addr)
 }
 #endif
 
+#define __raw_writeb __raw_writeb
 static inline void __raw_writeb(u8 val, volatile void __iomem *addr)
 {
 	asm volatile("strb %1, %0"
@@ -93,6 +96,7 @@ static inline void __raw_writeb(u8 val, volatile void __iomem *addr)
 		     : "r" (val));
 }
 
+#define __raw_writel __raw_writel
 static inline void __raw_writel(u32 val, volatile void __iomem *addr)
 {
 	asm volatile("str %1, %0"
@@ -100,6 +104,7 @@ static inline void __raw_writel(u32 val, volatile void __iomem *addr)
 		     : "r" (val));
 }
 
+#define __raw_readb __raw_readb
 static inline u8 __raw_readb(const volatile void __iomem *addr)
 {
 	u8 val;
@@ -109,6 +114,7 @@ static inline u8 __raw_readb(const volatile void __iomem *addr)
 	return val;
 }
 
+#define __raw_readl __raw_readl
 static inline u32 __raw_readl(const volatile void __iomem *addr)
 {
 	u32 val;
@@ -267,20 +273,6 @@ extern int pci_ioremap_io(unsigned int offset, phys_addr_t phys_addr);
 #define insl(p,d,l)		__raw_readsl(__io(p),d,l)
 #endif
 
-#define outb_p(val,port)	outb((val),(port))
-#define outw_p(val,port)	outw((val),(port))
-#define outl_p(val,port)	outl((val),(port))
-#define inb_p(port)		inb((port))
-#define inw_p(port)		inw((port))
-#define inl_p(port)		inl((port))
-
-#define outsb_p(port,from,len)	outsb(port,from,len)
-#define outsw_p(port,from,len)	outsw(port,from,len)
-#define outsl_p(port,from,len)	outsl(port,from,len)
-#define insb_p(port,to,len)	insb(port,to,len)
-#define insw_p(port,to,len)	insw(port,to,len)
-#define insl_p(port,to,len)	insl(port,to,len)
-
 /*
  * String version of IO memory access ops:
  */
@@ -347,40 +339,42 @@ extern void _memset_io(volatile void __iomem *, int, size_t);
 #define iounmap				__arm_iounmap
 
 /*
- * io{read,write}{8,16,32} macros
+ * io{read,write}{16,32}be() macros
  */
-#ifndef ioread8
-#define ioread8(p)	({ unsigned int __v = __raw_readb(p); __iormb(); __v; })
-#define ioread16(p)	({ unsigned int __v = le16_to_cpu((__force __le16)__raw_readw(p)); __iormb(); __v; })
-#define ioread32(p)	({ unsigned int __v = le32_to_cpu((__force __le32)__raw_readl(p)); __iormb(); __v; })
-
-#define ioread16be(p)	({ unsigned int __v = be16_to_cpu((__force __be16)__raw_readw(p)); __iormb(); __v; })
-#define ioread32be(p)	({ unsigned int __v = be32_to_cpu((__force __be32)__raw_readl(p)); __iormb(); __v; })
-
-#define iowrite8(v,p)	({ __iowmb(); __raw_writeb(v, p); })
-#define iowrite16(v,p)	({ __iowmb(); __raw_writew((__force __u16)cpu_to_le16(v), p); })
-#define iowrite32(v,p)	({ __iowmb(); __raw_writel((__force __u32)cpu_to_le32(v), p); })
+#define ioread16be(p)		({ __u16 __v = be16_to_cpu((__force __be16)__raw_readw(p)); __iormb(); __v; })
+#define ioread32be(p)		({ __u32 __v = be32_to_cpu((__force __be32)__raw_readl(p)); __iormb(); __v; })
 
-#define iowrite16be(v,p) ({ __iowmb(); __raw_writew((__force __u16)cpu_to_be16(v), p); })
-#define iowrite32be(v,p) ({ __iowmb(); __raw_writel((__force __u32)cpu_to_be32(v), p); })
-
-#define ioread8_rep(p,d,c)	__raw_readsb(p,d,c)
-#define ioread16_rep(p,d,c)	__raw_readsw(p,d,c)
-#define ioread32_rep(p,d,c)	__raw_readsl(p,d,c)
-
-#define iowrite8_rep(p,s,c)	__raw_writesb(p,s,c)
-#define iowrite16_rep(p,s,c)	__raw_writesw(p,s,c)
-#define iowrite32_rep(p,s,c)	__raw_writesl(p,s,c)
+#define iowrite16be(v,p)	({ __iowmb(); __raw_writew((__force __u16)cpu_to_be16(v), p); })
+#define iowrite32be(v,p)	({ __iowmb(); __raw_writel((__force __u32)cpu_to_be32(v), p); })
 
+#ifndef ioport_map
+#define ioport_map ioport_map
 extern void __iomem *ioport_map(unsigned long port, unsigned int nr);
+#endif
+#ifndef ioport_unmap
+#define ioport_unmap ioport_unmap
 extern void ioport_unmap(void __iomem *addr);
 #endif
 
 struct pci_dev;
 
+#define pci_iounmap pci_iounmap
 extern void pci_iounmap(struct pci_dev *dev, void __iomem *addr);
 
 /*
+ * Convert a physical pointer to a virtual kernel pointer for /dev/mem
+ * access
+ */
+#define xlate_dev_mem_ptr(p)	__va(p)
+
+/*
+ * Convert a virtual cached pointer to an uncached pointer
+ */
+#define xlate_dev_kmem_ptr(p)	p
+
+#include <asm-generic/io.h>
+
+/*
  * can the hardware map this into one segment or not, given no other
  * constraints.
  */
@@ -402,17 +396,6 @@ extern int devmem_is_allowed(unsigned long pfn);
 #endif
 
 /*
- * Convert a physical pointer to a virtual kernel pointer for /dev/mem
- * access
- */
-#define xlate_dev_mem_ptr(p)	__va(p)
-
-/*
- * Convert a virtual cached pointer to an uncached pointer
- */
-#define xlate_dev_kmem_ptr(p)	p
-
-/*
  * Register ISA memory and port locations for glibc iopl/inb/outb
  * emulation.
  */
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index e731018869a7..184def0e1652 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -274,11 +274,13 @@ static inline unsigned long __phys_to_virt(phys_addr_t x)
  * translation for translating DMA addresses.  Use the driver
  * DMA support - see dma-mapping.h.
  */
+#define virt_to_phys virt_to_phys
 static inline phys_addr_t virt_to_phys(const volatile void *x)
 {
 	return __virt_to_phys((unsigned long)(x));
 }
 
+#define phys_to_virt phys_to_virt
 static inline void *phys_to_virt(phys_addr_t x)
 {
 	return (void *)__phys_to_virt(x);
@@ -322,11 +324,13 @@ static inline phys_addr_t __virt_to_idmap(unsigned long x)
 #endif
 
 #ifdef CONFIG_VIRT_TO_BUS
+#define virt_to_bus virt_to_bus
 static inline __deprecated unsigned long virt_to_bus(void *x)
 {
 	return __virt_to_bus((unsigned long)x);
 }
 
+#define bus_to_virt bus_to_virt
 static inline __deprecated void *bus_to_virt(unsigned long x)
 {
 	return (void *)__bus_to_virt(x);
diff --git a/arch/arm/mach-ebsa110/include/mach/io.h b/arch/arm/mach-ebsa110/include/mach/io.h
index 11bb0799424b..69975784acfa 100644
--- a/arch/arm/mach-ebsa110/include/mach/io.h
+++ b/arch/arm/mach-ebsa110/include/mach/io.h
@@ -29,9 +29,9 @@ u8  __readb(const volatile void __iomem *addr);
 u16 __readw(const volatile void __iomem *addr);
 u32 __readl(const volatile void __iomem *addr);
 
-void __writeb(u8  val, void __iomem *addr);
-void __writew(u16 val, void __iomem *addr);
-void __writel(u32 val, void __iomem *addr);
+void __writeb(u8  val, volatile void __iomem *addr);
+void __writew(u16 val, volatile void __iomem *addr);
+void __writel(u32 val, volatile void __iomem *addr);
 
 /*
  * Argh, someone forgot the IOCS16 line.  We therefore have to handle
@@ -62,20 +62,31 @@ void __writel(u32 val, void __iomem *addr);
 #define writew(v,b)		__writew(v,b)
 #define writel(v,b)		__writel(v,b)
 
+#define insb insb
 extern void insb(unsigned int port, void *buf, int sz);
+#define insw insw
 extern void insw(unsigned int port, void *buf, int sz);
+#define insl insl
 extern void insl(unsigned int port, void *buf, int sz);
 
+#define outsb outsb
 extern void outsb(unsigned int port, const void *buf, int sz);
+#define outsw outsw
 extern void outsw(unsigned int port, const void *buf, int sz);
+#define outsl outsl
 extern void outsl(unsigned int port, const void *buf, int sz);
 
 /* can't support writesb atm */
-extern void writesw(void __iomem *addr, const void *data, int wordlen);
-extern void writesl(void __iomem *addr, const void *data, int longlen);
+#define writesw writesw
+extern void writesw(volatile void __iomem *addr, const void *data, int wordlen);
+#define writesl writesl
+extern void writesl(volatile void __iomem *addr, const void *data, int longlen);
 
 /* can't support readsb atm */
-extern void readsw(const void __iomem *addr, void *data, int wordlen);
-extern void readsl(const void __iomem *addr, void *data, int longlen);
+#define readsw readsw
+extern void readsw(const volatile void __iomem *addr, void *data, int wordlen);
+
+#define readsl readsl
+extern void readsl(const volatile void __iomem *addr, void *data, int longlen);
 
 #endif
diff --git a/arch/arm/mach-ebsa110/io.c b/arch/arm/mach-ebsa110/io.c
index 756cc377a73d..b57980b435fd 100644
--- a/arch/arm/mach-ebsa110/io.c
+++ b/arch/arm/mach-ebsa110/io.c
@@ -102,7 +102,7 @@ EXPORT_SYMBOL(__readb);
 EXPORT_SYMBOL(__readw);
 EXPORT_SYMBOL(__readl);
 
-void readsw(const void __iomem *addr, void *data, int len)
+void readsw(const volatile void __iomem *addr, void *data, int len)
 {
 	void __iomem *a = __isamem_convert_addr(addr);
 
@@ -112,7 +112,7 @@ void readsw(const void __iomem *addr, void *data, int len)
 }
 EXPORT_SYMBOL(readsw);
 
-void readsl(const void __iomem *addr, void *data, int len)
+void readsl(const volatile void __iomem *addr, void *data, int len)
 {
 	void __iomem *a = __isamem_convert_addr(addr);
 
@@ -122,7 +122,7 @@ void readsl(const void __iomem *addr, void *data, int len)
 }
 EXPORT_SYMBOL(readsl);
 
-void __writeb(u8 val, void __iomem *addr)
+void __writeb(u8 val, volatile void __iomem *addr)
 {
 	void __iomem *a = __isamem_convert_addr(addr);
 
@@ -132,7 +132,7 @@ void __writeb(u8 val, void __iomem *addr)
 		__raw_writeb(val, a);
 }
 
-void __writew(u16 val, void __iomem *addr)
+void __writew(u16 val, volatile void __iomem *addr)
 {
 	void __iomem *a = __isamem_convert_addr(addr);
 
@@ -142,7 +142,7 @@ void __writew(u16 val, void __iomem *addr)
 	__raw_writew(val, a);
 }
 
-void __writel(u32 val, void __iomem *addr)
+void __writel(u32 val, volatile void __iomem *addr)
 {
 	void __iomem *a = __isamem_convert_addr(addr);
 
@@ -157,7 +157,7 @@ EXPORT_SYMBOL(__writeb);
 EXPORT_SYMBOL(__writew);
 EXPORT_SYMBOL(__writel);
 
-void writesw(void __iomem *addr, const void *data, int len)
+void writesw(volatile void __iomem *addr, const void *data, int len)
 {
 	void __iomem *a = __isamem_convert_addr(addr);
 
@@ -167,7 +167,7 @@ void writesw(void __iomem *addr, const void *data, int len)
 }
 EXPORT_SYMBOL(writesw);
 
-void writesl(void __iomem *addr, const void *data, int len)
+void writesl(volatile void __iomem *addr, const void *data, int len)
 {
 	void __iomem *a = __isamem_convert_addr(addr);
 
diff --git a/arch/arm/mach-ixp4xx/common.c b/arch/arm/mach-ixp4xx/common.c
index fc4b7b24265e..8537d4c41e34 100644
--- a/arch/arm/mach-ixp4xx/common.c
+++ b/arch/arm/mach-ixp4xx/common.c
@@ -652,7 +652,7 @@ static void __iomem *ixp4xx_ioremap_caller(phys_addr_t addr, size_t size,
 	return (void __iomem *)addr;
 }
 
-static void ixp4xx_iounmap(void __iomem *addr)
+static void ixp4xx_iounmap(volatile void __iomem *addr)
 {
 	if (!is_pci_memory((__force u32)addr))
 		__iounmap(addr);
diff --git a/arch/arm/mach-ixp4xx/include/mach/io.h b/arch/arm/mach-ixp4xx/include/mach/io.h
index 7d11979da030..6a722860e34d 100644
--- a/arch/arm/mach-ixp4xx/include/mach/io.h
+++ b/arch/arm/mach-ixp4xx/include/mach/io.h
@@ -58,6 +58,10 @@ static inline int is_pci_memory(u32 addr)
 #define writew(v, p)			__indirect_writew(v, p)
 #define writel(v, p)			__indirect_writel(v, p)
 
+#define writeb_relaxed(v, p)		__indirect_writeb(v, p)
+#define writew_relaxed(v, p)		__indirect_writew(v, p)
+#define writel_relaxed(v, p)		__indirect_writel(v, p)
+
 #define writesb(p, v, l)		__indirect_writesb(p, v, l)
 #define writesw(p, v, l)		__indirect_writesw(p, v, l)
 #define writesl(p, v, l)		__indirect_writesl(p, v, l)
@@ -66,6 +70,10 @@ static inline int is_pci_memory(u32 addr)
 #define readw(p)			__indirect_readw(p)
 #define readl(p)			__indirect_readl(p)
 
+#define readb_relaxed(p)		__indirect_readb(p)
+#define readw_relaxed(p)		__indirect_readw(p)
+#define readl_relaxed(p)		__indirect_readl(p)
+
 #define readsb(p, v, l)			__indirect_readsb(p, v, l)
 #define readsw(p, v, l)			__indirect_readsw(p, v, l)
 #define readsl(p, v, l)			__indirect_readsl(p, v, l)
@@ -99,7 +107,7 @@ static inline void __indirect_writew(u16 value, volatile void __iomem *p)
 	u32 n, byte_enables, data;
 
 	if (!is_pci_memory(addr)) {
-		__raw_writew(value, addr);
+		__raw_writew(value, p);
 		return;
 	}
 
@@ -164,7 +172,7 @@ static inline unsigned short __indirect_readw(const volatile void __iomem *p)
 	u32 n, byte_enables, data;
 
 	if (!is_pci_memory(addr))
-		return __raw_readw(addr);
+		return __raw_readw(p);
 
 	n = addr % 4;
 	byte_enables = (0xf & ~(BIT(n) | BIT(n+1))) << IXP4XX_PCI_NP_CBE_BESL;
@@ -226,6 +234,7 @@ static inline void __indirect_readsl(const volatile void __iomem *bus_addr,
  * I/O functions.
  */
 
+#define outb outb
 static inline void outb(u8 value, u32 addr)
 {
 	u32 n, byte_enables, data;
@@ -235,12 +244,14 @@ static inline void outb(u8 value, u32 addr)
 	ixp4xx_pci_write(addr, byte_enables | NP_CMD_IOWRITE, data);
 }
 
+#define outsb outsb
 static inline void outsb(u32 io_addr, const u8 *vaddr, u32 count)
 {
 	while (count--)
 		outb(*vaddr++, io_addr);
 }
 
+#define outw outw
 static inline void outw(u16 value, u32 addr)
 {
 	u32 n, byte_enables, data;
@@ -250,23 +261,27 @@ static inline void outw(u16 value, u32 addr)
 	ixp4xx_pci_write(addr, byte_enables | NP_CMD_IOWRITE, data);
 }
 
+#define outsw outsw
 static inline void outsw(u32 io_addr, const u16 *vaddr, u32 count)
 {
 	while (count--)
 		outw(cpu_to_le16(*vaddr++), io_addr);
 }
 
+#define outl outl
 static inline void outl(u32 value, u32 addr)
 {
 	ixp4xx_pci_write(addr, NP_CMD_IOWRITE, value);
 }
 
+#define outsl outsl
 static inline void outsl(u32 io_addr, const u32 *vaddr, u32 count)
 {
 	while (count--)
 		outl(cpu_to_le32(*vaddr++), io_addr);
 }
 
+#define inb inb
 static inline u8 inb(u32 addr)
 {
 	u32 n, byte_enables, data;
@@ -278,12 +293,14 @@ static inline u8 inb(u32 addr)
 	return data >> (8*n);
 }
 
+#define insb insb
 static inline void insb(u32 io_addr, u8 *vaddr, u32 count)
 {
 	while (count--)
 		*vaddr++ = inb(io_addr);
 }
 
+#define inw inw
 static inline u16 inw(u32 addr)
 {
 	u32 n, byte_enables, data;
@@ -295,12 +312,14 @@ static inline u16 inw(u32 addr)
 	return data>>(8*n);
 }
 
+#define insw insw
 static inline void insw(u32 io_addr, u16 *vaddr, u32 count)
 {
 	while (count--)
 		*vaddr++ = le16_to_cpu(inw(io_addr));
 }
 
+#define inl inl
 static inline u32 inl(u32 addr)
 {
 	u32 data;
@@ -310,6 +329,7 @@ static inline u32 inl(u32 addr)
 	return data;
 }
 
+#define insl insl
 static inline void insl(u32 io_addr, u32 *vaddr, u32 count)
 {
 	while (count--)
diff --git a/arch/arm/mach-sa1100/pci-nanoengine.c b/arch/arm/mach-sa1100/pci-nanoengine.c
index ff02e2da99f2..b704433c529c 100644
--- a/arch/arm/mach-sa1100/pci-nanoengine.c
+++ b/arch/arm/mach-sa1100/pci-nanoengine.c
@@ -33,12 +33,12 @@
 static DEFINE_SPINLOCK(nano_lock);
 
 static int nanoengine_get_pci_address(struct pci_bus *bus,
-	unsigned int devfn, int where, unsigned long *address)
+	unsigned int devfn, int where, void __iomem **address)
 {
 	int ret = PCIBIOS_DEVICE_NOT_FOUND;
 	unsigned int busnr = bus->number;
 
-	*address = NANO_PCI_CONFIG_SPACE_VIRT +
+	*address = (void __iomem *)NANO_PCI_CONFIG_SPACE_VIRT +
 		((bus->number << 16) | (devfn << 8) | (where & ~3));
 
 	ret = (busnr > 255 || devfn > 255 || where > 255) ?
@@ -51,7 +51,7 @@ static int nanoengine_read_config(struct pci_bus *bus, unsigned int devfn, int w
 	int size, u32 *val)
 {
 	int ret;
-	unsigned long address;
+	void __iomem *address;
 	unsigned long flags;
 	u32 v;
 
@@ -85,7 +85,7 @@ static int nanoengine_write_config(struct pci_bus *bus, unsigned int devfn, int
 	int size, u32 val)
 {
 	int ret;
-	unsigned long address;
+	void __iomem *address;
 	unsigned long flags;
 	unsigned shift;
 	u32 v;
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index f385273f4b24..6b1ebd964c10 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -24,9 +24,9 @@ config ARM64
 	select GENERIC_CLOCKEVENTS_BROADCAST if SMP
 	select GENERIC_CPU_AUTOPROBE
 	select GENERIC_EARLY_IOREMAP
-	select GENERIC_IOMAP
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
+	select GENERIC_PCI_IOMAP
 	select GENERIC_SCHED_CLOCK
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_STRNCPY_FROM_USER
diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index 75825b63464d..949c406d4df4 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -36,26 +36,31 @@
 /*
  * Generic IO read/write.  These perform native-endian accesses.
  */
+#define __raw_writeb __raw_writeb
 static inline void __raw_writeb(u8 val, volatile void __iomem *addr)
 {
 	asm volatile("strb %w0, [%1]" : : "r" (val), "r" (addr));
 }
 
+#define __raw_writew __raw_writew
 static inline void __raw_writew(u16 val, volatile void __iomem *addr)
 {
 	asm volatile("strh %w0, [%1]" : : "r" (val), "r" (addr));
 }
 
+#define __raw_writel __raw_writel
 static inline void __raw_writel(u32 val, volatile void __iomem *addr)
 {
 	asm volatile("str %w0, [%1]" : : "r" (val), "r" (addr));
 }
 
+#define __raw_writeq __raw_writeq
 static inline void __raw_writeq(u64 val, volatile void __iomem *addr)
 {
 	asm volatile("str %0, [%1]" : : "r" (val), "r" (addr));
 }
 
+#define __raw_readb __raw_readb
 static inline u8 __raw_readb(const volatile void __iomem *addr)
 {
 	u8 val;
@@ -66,6 +71,7 @@ static inline u8 __raw_readb(const volatile void __iomem *addr)
 	return val;
 }
 
+#define __raw_readw __raw_readw
 static inline u16 __raw_readw(const volatile void __iomem *addr)
 {
 	u16 val;
@@ -77,6 +83,7 @@ static inline u16 __raw_readw(const volatile void __iomem *addr)
 	return val;
 }
 
+#define __raw_readl __raw_readl
 static inline u32 __raw_readl(const volatile void __iomem *addr)
 {
 	u32 val;
@@ -87,6 +94,7 @@ static inline u32 __raw_readl(const volatile void __iomem *addr)
 	return val;
 }
 
+#define __raw_readq __raw_readq
 static inline u64 __raw_readq(const volatile void __iomem *addr)
 {
 	u64 val;
@@ -140,94 +148,6 @@ static inline u64 __raw_readq(const volatile void __iomem *addr)
 #define IO_SPACE_LIMIT		(SZ_32M - 1)
 #define PCI_IOBASE		((void __iomem *)(MODULES_VADDR - SZ_32M))
 
-static inline u8 inb(unsigned long addr)
-{
-	return readb(addr + PCI_IOBASE);
-}
-
-static inline u16 inw(unsigned long addr)
-{
-	return readw(addr + PCI_IOBASE);
-}
-
-static inline u32 inl(unsigned long addr)
-{
-	return readl(addr + PCI_IOBASE);
-}
-
-static inline void outb(u8 b, unsigned long addr)
-{
-	writeb(b, addr + PCI_IOBASE);
-}
-
-static inline void outw(u16 b, unsigned long addr)
-{
-	writew(b, addr + PCI_IOBASE);
-}
-
-static inline void outl(u32 b, unsigned long addr)
-{
-	writel(b, addr + PCI_IOBASE);
-}
-
-#define inb_p(addr)	inb(addr)
-#define inw_p(addr)	inw(addr)
-#define inl_p(addr)	inl(addr)
-
-#define outb_p(x, addr)	outb((x), (addr))
-#define outw_p(x, addr)	outw((x), (addr))
-#define outl_p(x, addr)	outl((x), (addr))
-
-static inline void insb(unsigned long addr, void *buffer, int count)
-{
-	u8 *buf = buffer;
-	while (count--)
-		*buf++ = __raw_readb(addr + PCI_IOBASE);
-}
-
-static inline void insw(unsigned long addr, void *buffer, int count)
-{
-	u16 *buf = buffer;
-	while (count--)
-		*buf++ = __raw_readw(addr + PCI_IOBASE);
-}
-
-static inline void insl(unsigned long addr, void *buffer, int count)
-{
-	u32 *buf = buffer;
-	while (count--)
-		*buf++ = __raw_readl(addr + PCI_IOBASE);
-}
-
-static inline void outsb(unsigned long addr, const void *buffer, int count)
-{
-	const u8 *buf = buffer;
-	while (count--)
-		__raw_writeb(*buf++, addr + PCI_IOBASE);
-}
-
-static inline void outsw(unsigned long addr, const void *buffer, int count)
-{
-	const u16 *buf = buffer;
-	while (count--)
-		__raw_writew(*buf++, addr + PCI_IOBASE);
-}
-
-static inline void outsl(unsigned long addr, const void *buffer, int count)
-{
-	const u32 *buf = buffer;
-	while (count--)
-		__raw_writel(*buf++, addr + PCI_IOBASE);
-}
-
-#define insb_p(port,to,len)	insb(port,to,len)
-#define insw_p(port,to,len)	insw(port,to,len)
-#define insl_p(port,to,len)	insl(port,to,len)
-
-#define outsb_p(port,from,len)	outsb(port,from,len)
-#define outsw_p(port,from,len)	outsw(port,from,len)
-#define outsl_p(port,from,len)	outsl(port,from,len)
-
 /*
  * String version of I/O memory access operations.
  */
@@ -251,18 +171,14 @@ extern void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size);
 #define ioremap_wc(addr, size)		__ioremap((addr), (size), __pgprot(PROT_NORMAL_NC))
 #define iounmap				__iounmap
 
-#define ARCH_HAS_IOREMAP_WC
-#include <asm-generic/iomap.h>
-
 /*
- * More restrictive address range checking than the default implementation
- * (PHYS_OFFSET and PHYS_MASK taken into account).
+ * io{read,write}{16,32}be() macros
  */
-#define ARCH_HAS_VALID_PHYS_ADDR_RANGE
-extern int valid_phys_addr_range(phys_addr_t addr, size_t size);
-extern int valid_mmap_phys_addr_range(unsigned long pfn, size_t size);
+#define ioread16be(p)		({ __u16 __v = be16_to_cpu((__force __be16)__raw_readw(p)); __iormb(); __v; })
+#define ioread32be(p)		({ __u32 __v = be32_to_cpu((__force __be32)__raw_readl(p)); __iormb(); __v; })
 
-extern int devmem_is_allowed(unsigned long pfn);
+#define iowrite16be(v,p)	({ __iowmb(); __raw_writew((__force __u16)cpu_to_be16(v), p); })
+#define iowrite32be(v,p)	({ __iowmb(); __raw_writel((__force __u32)cpu_to_be32(v), p); })
 
 /*
  * Convert a physical pointer to a virtual kernel pointer for /dev/mem
@@ -275,6 +191,18 @@ extern int devmem_is_allowed(unsigned long pfn);
  */
 #define xlate_dev_kmem_ptr(p)	p
 
+#include <asm-generic/io.h>
+
+/*
+ * More restrictive address range checking than the default implementation
+ * (PHYS_OFFSET and PHYS_MASK taken into account).
+ */
+#define ARCH_HAS_VALID_PHYS_ADDR_RANGE
+extern int valid_phys_addr_range(phys_addr_t addr, size_t size);
+extern int valid_mmap_phys_addr_range(unsigned long pfn, size_t size);
+
+extern int devmem_is_allowed(unsigned long pfn);
+
 struct bio_vec;
 extern bool xen_biovec_phys_mergeable(const struct bio_vec *vec1,
 				      const struct bio_vec *vec2);
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index a62cd077457b..6486b2bfd562 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -120,11 +120,13 @@ extern phys_addr_t		memstart_addr;
  * translation for translating DMA addresses.  Use the driver
  * DMA support - see dma-mapping.h.
  */
+#define virt_to_phys virt_to_phys
 static inline phys_addr_t virt_to_phys(const volatile void *x)
 {
 	return __virt_to_phys((unsigned long)(x));
 }
 
+#define phys_to_virt phys_to_virt
 static inline void *phys_to_virt(phys_addr_t x)
 {
 	return (void *)(__phys_to_virt(x));
diff --git a/arch/cris/include/asm/io.h b/arch/cris/include/asm/io.h
index e59dba12ce94..752a3f45df60 100644
--- a/arch/cris/include/asm/io.h
+++ b/arch/cris/include/asm/io.h
@@ -112,6 +112,9 @@ static inline void writel(unsigned int b, volatile void __iomem *addr)
 	else
 		*(volatile unsigned int __force *) addr = b;
 }
+#define writeb_relaxed(b, addr) writeb(b, addr)
+#define writew_relaxed(b, addr) writew(b, addr)
+#define writel_relaxed(b, addr) writel(b, addr)
 #define __raw_writeb writeb
 #define __raw_writew writew
 #define __raw_writel writel
diff --git a/arch/frv/include/asm/io.h b/arch/frv/include/asm/io.h
index 8cb50a2fbcb2..99bb7efaf9b7 100644
--- a/arch/frv/include/asm/io.h
+++ b/arch/frv/include/asm/io.h
@@ -243,6 +243,9 @@ static inline void writel(uint32_t datum, volatile void __iomem *addr)
 		__flush_PCI_writes();
 }
 
+#define writeb_relaxed writeb
+#define writew_relaxed writew
+#define writel_relaxed writel
 
 /* Values for nocacheflag and cmode */
 #define IOMAP_FULL_CACHING		0
diff --git a/arch/ia64/include/asm/io.h b/arch/ia64/include/asm/io.h
index bee0acd52f7e..80a7e34be009 100644
--- a/arch/ia64/include/asm/io.h
+++ b/arch/ia64/include/asm/io.h
@@ -393,6 +393,10 @@ __writeq (unsigned long val, volatile void __iomem *addr)
 #define writew(v,a)	__writew((v), (a))
 #define writel(v,a)	__writel((v), (a))
 #define writeq(v,a)	__writeq((v), (a))
+#define writeb_relaxed(v,a)	__writeb((v), (a))
+#define writew_relaxed(v,a)	__writew((v), (a))
+#define writel_relaxed(v,a)	__writel((v), (a))
+#define writeq_relaxed(v,a)	__writeq((v), (a))
 #define __raw_writeb	writeb
 #define __raw_writew	writew
 #define __raw_writel	writel
diff --git a/arch/ia64/include/asm/uaccess.h b/arch/ia64/include/asm/uaccess.h
index 449c8c0fa2bd..103bedc59644 100644
--- a/arch/ia64/include/asm/uaccess.h
+++ b/arch/ia64/include/asm/uaccess.h
@@ -365,15 +365,15 @@ ia64_done_with_exception (struct pt_regs *regs)
 }
 
 #define ARCH_HAS_TRANSLATE_MEM_PTR	1
-static __inline__ char *
-xlate_dev_mem_ptr (unsigned long p)
+static __inline__ void *
+xlate_dev_mem_ptr(phys_addr_t p)
 {
 	struct page *page;
-	char * ptr;
+	void *ptr;
 
 	page = pfn_to_page(p >> PAGE_SHIFT);
 	if (PageUncached(page))
-		ptr = (char *)p + __IA64_UNCACHED_OFFSET;
+		ptr = (void *)p + __IA64_UNCACHED_OFFSET;
 	else
 		ptr = __va(p);
 
@@ -383,15 +383,15 @@ xlate_dev_mem_ptr (unsigned long p)
 /*
  * Convert a virtual cached kernel memory pointer to an uncached pointer
  */
-static __inline__ char *
-xlate_dev_kmem_ptr (char * p)
+static __inline__ void *
+xlate_dev_kmem_ptr(void *p)
 {
 	struct page *page;
-	char * ptr;
+	void *ptr;
 
 	page = virt_to_page((unsigned long)p);
 	if (PageUncached(page))
-		ptr = (char *)__pa(p) + __IA64_UNCACHED_OFFSET;
+		ptr = (void *)__pa(p) + __IA64_UNCACHED_OFFSET;
 	else
 		ptr = p;
 
diff --git a/arch/m32r/include/asm/io.h b/arch/m32r/include/asm/io.h
index 4010f1fc5b65..6e7787f3dac7 100644
--- a/arch/m32r/include/asm/io.h
+++ b/arch/m32r/include/asm/io.h
@@ -161,6 +161,9 @@ static inline void _writel(unsigned long l, unsigned long addr)
 #define __raw_writeb writeb
 #define __raw_writew writew
 #define __raw_writel writel
+#define writeb_relaxed writeb
+#define writew_relaxed writew
+#define writel_relaxed writel
 
 #define ioread8 read
 #define ioread16 readw
diff --git a/arch/m68k/include/asm/io.h b/arch/m68k/include/asm/io.h
index c70cc9155003..bccd5a914eb6 100644
--- a/arch/m68k/include/asm/io.h
+++ b/arch/m68k/include/asm/io.h
@@ -3,3 +3,11 @@
 #else
 #include <asm/io_mm.h>
 #endif
+
+#define readb_relaxed(addr)	readb(addr)
+#define readw_relaxed(addr)	readw(addr)
+#define readl_relaxed(addr)	readl(addr)
+
+#define writeb_relaxed(b, addr)	writeb(b, addr)
+#define writew_relaxed(b, addr)	writew(b, addr)
+#define writel_relaxed(b, addr)	writel(b, addr)
diff --git a/arch/m68k/include/asm/io_no.h b/arch/m68k/include/asm/io_no.h
index be4b5a813ad4..a93c8cde4d38 100644
--- a/arch/m68k/include/asm/io_no.h
+++ b/arch/m68k/include/asm/io_no.h
@@ -40,10 +40,6 @@ static inline unsigned int _swapl(volatile unsigned long v)
 #define readl(addr) \
     ({ unsigned int __v = (*(volatile unsigned int *) (addr)); __v; })
 
-#define readb_relaxed(addr) readb(addr)
-#define readw_relaxed(addr) readw(addr)
-#define readl_relaxed(addr) readl(addr)
-
 #define writeb(b,addr) (void)((*(volatile unsigned char *) (addr)) = (b))
 #define writew(b,addr) (void)((*(volatile unsigned short *) (addr)) = (b))
 #define writel(b,addr) (void)((*(volatile unsigned int *) (addr)) = (b))
diff --git a/arch/microblaze/include/asm/io.h b/arch/microblaze/include/asm/io.h
index 433751b2a003..940f5fc1d1da 100644
--- a/arch/microblaze/include/asm/io.h
+++ b/arch/microblaze/include/asm/io.h
@@ -69,12 +69,4 @@ extern void __iomem *ioremap(phys_addr_t address, unsigned long size);
 
 #include <asm-generic/io.h>
 
-#define readb_relaxed	readb
-#define readw_relaxed	readw
-#define readl_relaxed	readl
-
-#define writeb_relaxed	writeb
-#define writew_relaxed	writew
-#define writel_relaxed	writel
-
 #endif /* _ASM_MICROBLAZE_IO_H */
diff --git a/arch/mn10300/include/asm/io.h b/arch/mn10300/include/asm/io.h
index e6ed0d897ccc..897ba3c12b32 100644
--- a/arch/mn10300/include/asm/io.h
+++ b/arch/mn10300/include/asm/io.h
@@ -67,6 +67,10 @@ static inline void writel(u32 b, volatile void __iomem *addr)
 #define __raw_writew writew
 #define __raw_writel writel
 
+#define writeb_relaxed writeb
+#define writew_relaxed writew
+#define writel_relaxed writel
+
 /*****************************************************************************/
 /*
  * traditional input/output functions
diff --git a/arch/parisc/include/asm/io.h b/arch/parisc/include/asm/io.h
index 1f6d2ae7aba5..8cd0abf28ffb 100644
--- a/arch/parisc/include/asm/io.h
+++ b/arch/parisc/include/asm/io.h
@@ -217,10 +217,14 @@ static inline void writeq(unsigned long long q, volatile void __iomem *addr)
 #define writel	writel
 #define writeq	writeq
 
-#define readb_relaxed(addr) readb(addr)
-#define readw_relaxed(addr) readw(addr)
-#define readl_relaxed(addr) readl(addr)
-#define readq_relaxed(addr) readq(addr)
+#define readb_relaxed(addr)	readb(addr)
+#define readw_relaxed(addr)	readw(addr)
+#define readl_relaxed(addr)	readl(addr)
+#define readq_relaxed(addr)	readq(addr)
+#define writeb_relaxed(b, addr)	writeb(b, addr)
+#define writew_relaxed(w, addr)	writew(w, addr)
+#define writel_relaxed(l, addr)	writel(l, addr)
+#define writeq_relaxed(q, addr)	writeq(q, addr)
 
 #define mmiowb() do { } while (0)
 
diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h
index 97d3869991ca..9eaf301ac952 100644
--- a/arch/powerpc/include/asm/io.h
+++ b/arch/powerpc/include/asm/io.h
@@ -617,10 +617,14 @@ static inline void name at					\
 /*
  * We don't do relaxed operations yet, at least not with this semantic
  */
-#define readb_relaxed(addr) readb(addr)
-#define readw_relaxed(addr) readw(addr)
-#define readl_relaxed(addr) readl(addr)
-#define readq_relaxed(addr) readq(addr)
+#define readb_relaxed(addr)	readb(addr)
+#define readw_relaxed(addr)	readw(addr)
+#define readl_relaxed(addr)	readl(addr)
+#define readq_relaxed(addr)	readq(addr)
+#define writeb_relaxed(v, addr)	writeb(v, addr)
+#define writew_relaxed(v, addr)	writew(v, addr)
+#define writel_relaxed(v, addr)	writel(v, addr)
+#define writeq_relaxed(v, addr)	writeq(v, addr)
 
 #ifdef CONFIG_PPC32
 #define mmiowb()
diff --git a/arch/s390/include/asm/io.h b/arch/s390/include/asm/io.h
index cd6b9ee7b69c..6ad9013c67e7 100644
--- a/arch/s390/include/asm/io.h
+++ b/arch/s390/include/asm/io.h
@@ -13,9 +13,10 @@
 #include <asm/page.h>
 #include <asm/pci_io.h>
 
-void *xlate_dev_mem_ptr(unsigned long phys);
 #define xlate_dev_mem_ptr xlate_dev_mem_ptr
-void unxlate_dev_mem_ptr(unsigned long phys, void *addr);
+void *xlate_dev_mem_ptr(phys_addr_t phys);
+#define unxlate_dev_mem_ptr unxlate_dev_mem_ptr
+void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr);
 
 /*
  * Convert a virtual cached pointer to an uncached pointer
@@ -60,11 +61,6 @@ static inline void iounmap(volatile void __iomem *addr)
 #define __raw_writel	zpci_write_u32
 #define __raw_writeq	zpci_write_u64
 
-#define readb_relaxed	readb
-#define readw_relaxed	readw
-#define readl_relaxed	readl
-#define readq_relaxed	readq
-
 #endif /* CONFIG_PCI */
 
 #include <asm-generic/io.h>
diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c
index 2a2e35416d2f..2eb34bdfc613 100644
--- a/arch/s390/mm/maccess.c
+++ b/arch/s390/mm/maccess.c
@@ -176,7 +176,7 @@ static int is_swapped(unsigned long addr)
  * For swapped prefix pages a new buffer is returned that contains a copy of
  * the absolute memory. The buffer size is maximum one page large.
  */
-void *xlate_dev_mem_ptr(unsigned long addr)
+void *xlate_dev_mem_ptr(phys_addr_t addr)
 {
 	void *bounce = (void *) addr;
 	unsigned long size;
@@ -197,7 +197,7 @@ void *xlate_dev_mem_ptr(unsigned long addr)
 /*
  * Free converted buffer for /dev/mem access (if necessary)
  */
-void unxlate_dev_mem_ptr(unsigned long addr, void *buf)
+void unxlate_dev_mem_ptr(phys_addr_t addr, void *buf)
 {
 	if ((void *) addr != buf)
 		free_page((unsigned long) buf);
diff --git a/arch/sparc/include/asm/io_32.h b/arch/sparc/include/asm/io_32.h
index 9f532902627c..407ac14295f4 100644
--- a/arch/sparc/include/asm/io_32.h
+++ b/arch/sparc/include/asm/io_32.h
@@ -4,10 +4,6 @@
 #include <linux/kernel.h>
 #include <linux/ioport.h>  /* struct resource */
 
-#define readb_relaxed(__addr)	readb(__addr)
-#define readw_relaxed(__addr)	readw(__addr)
-#define readl_relaxed(__addr)	readl(__addr)
-
 #define IO_SPACE_LIMIT 0xffffffff
 
 #define memset_io(d,c,sz)     _memset_io(d,c,sz)
diff --git a/arch/sparc/include/asm/io_64.h b/arch/sparc/include/asm/io_64.h
index 80b54b326d49..9b672be70dda 100644
--- a/arch/sparc/include/asm/io_64.h
+++ b/arch/sparc/include/asm/io_64.h
@@ -101,6 +101,7 @@ static inline void __raw_writeq(u64 q, const volatile void __iomem *addr)
  * the cache by using ASI_PHYS_BYPASS_EC_E_L
  */
 #define readb readb
+#define readb_relaxed readb
 static inline u8 readb(const volatile void __iomem *addr)
 {	u8 ret;
 
@@ -112,6 +113,7 @@ static inline u8 readb(const volatile void __iomem *addr)
 }
 
 #define readw readw
+#define readw_relaxed readw
 static inline u16 readw(const volatile void __iomem *addr)
 {	u16 ret;
 
@@ -124,6 +126,7 @@ static inline u16 readw(const volatile void __iomem *addr)
 }
 
 #define readl readl
+#define readl_relaxed readl
 static inline u32 readl(const volatile void __iomem *addr)
 {	u32 ret;
 
@@ -136,6 +139,7 @@ static inline u32 readl(const volatile void __iomem *addr)
 }
 
 #define readq readq
+#define readq_relaxed readq
 static inline u64 readq(const volatile void __iomem *addr)
 {	u64 ret;
 
@@ -148,6 +152,7 @@ static inline u64 readq(const volatile void __iomem *addr)
 }
 
 #define writeb writeb
+#define writeb_relaxed writeb
 static inline void writeb(u8 b, volatile void __iomem *addr)
 {
 	__asm__ __volatile__("stba\t%r0, [%1] %2\t/* pci_writeb */"
@@ -157,6 +162,7 @@ static inline void writeb(u8 b, volatile void __iomem *addr)
 }
 
 #define writew writew
+#define writew_relaxed writew
 static inline void writew(u16 w, volatile void __iomem *addr)
 {
 	__asm__ __volatile__("stha\t%r0, [%1] %2\t/* pci_writew */"
@@ -166,6 +172,7 @@ static inline void writew(u16 w, volatile void __iomem *addr)
 }
 
 #define writel writel
+#define writel_relaxed writel
 static inline void writel(u32 l, volatile void __iomem *addr)
 {
 	__asm__ __volatile__("stwa\t%r0, [%1] %2\t/* pci_writel */"
@@ -175,6 +182,7 @@ static inline void writel(u32 l, volatile void __iomem *addr)
 }
 
 #define writeq writeq
+#define writeq_relaxed writeq
 static inline void writeq(u64 q, volatile void __iomem *addr)
 {
 	__asm__ __volatile__("stxa\t%r0, [%1] %2\t/* pci_writeq */"
@@ -183,7 +191,6 @@ static inline void writeq(u64 q, volatile void __iomem *addr)
 			     : "memory");
 }
 
-
 #define inb inb
 static inline u8 inb(unsigned long addr)
 {
@@ -264,11 +271,6 @@ static inline void iowrite32_rep(void __iomem *port, const void *buf, unsigned l
 	outsl((unsigned long __force)port, buf, count);
 }
 
-#define readb_relaxed(__addr)	readb(__addr)
-#define readw_relaxed(__addr)	readw(__addr)
-#define readl_relaxed(__addr)	readl(__addr)
-#define readq_relaxed(__addr)	readq(__addr)
-
 /* Valid I/O Space regions are anywhere, because each PCI bus supported
  * can live in an arbitrary area of the physical address range.
  */
diff --git a/arch/tile/include/asm/io.h b/arch/tile/include/asm/io.h
index 9fe434969fab..d372641054d9 100644
--- a/arch/tile/include/asm/io.h
+++ b/arch/tile/include/asm/io.h
@@ -241,6 +241,10 @@ static inline void writeq(u64 val, unsigned long addr)
 #define readw_relaxed readw
 #define readl_relaxed readl
 #define readq_relaxed readq
+#define writeb_relaxed writeb
+#define writew_relaxed writew
+#define writel_relaxed writel
+#define writeq_relaxed writeq
 
 #define ioread8 readb
 #define ioread16 readw
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index b8237d8a1e0c..0cdbe6e81b45 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -74,6 +74,9 @@ build_mmio_write(__writel, "l", unsigned int, "r", )
 #define __raw_readw __readw
 #define __raw_readl __readl
 
+#define writeb_relaxed(v, a) __writeb(v, a)
+#define writew_relaxed(v, a) __writew(v, a)
+#define writel_relaxed(v, a) __writel(v, a)
 #define __raw_writeb __writeb
 #define __raw_writew __writew
 #define __raw_writel __writel
@@ -86,6 +89,7 @@ build_mmio_read(readq, "q", unsigned long, "=r", :"memory")
 build_mmio_write(writeq, "q", unsigned long, "r", :"memory")
 
 #define readq_relaxed(a)	readq(a)
+#define writeq_relaxed(v, a)	writeq(v, a)
 
 #define __raw_readq(a)		readq(a)
 #define __raw_writeq(val, addr)	writeq(val, addr)
@@ -310,8 +314,8 @@ BUILDIO(b, b, char)
 BUILDIO(w, w, short)
 BUILDIO(l, , int)
 
-extern void *xlate_dev_mem_ptr(unsigned long phys);
-extern void unxlate_dev_mem_ptr(unsigned long phys, void *addr);
+extern void *xlate_dev_mem_ptr(phys_addr_t phys);
+extern void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr);
 
 extern int ioremap_change_attr(unsigned long vaddr, unsigned long size,
 				unsigned long prot_val);
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index af78e50ca6ce..b12f43c192cf 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -327,7 +327,7 @@ EXPORT_SYMBOL(iounmap);
  * Convert a physical pointer to a virtual kernel pointer for /dev/mem
  * access
  */
-void *xlate_dev_mem_ptr(unsigned long phys)
+void *xlate_dev_mem_ptr(phys_addr_t phys)
 {
 	void *addr;
 	unsigned long start = phys & PAGE_MASK;
@@ -343,7 +343,7 @@ void *xlate_dev_mem_ptr(unsigned long phys)
 	return addr;
 }
 
-void unxlate_dev_mem_ptr(unsigned long phys, void *addr)
+void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr)
 {
 	if (page_is_ram(phys >> PAGE_SHIFT))
 		return;
diff --git a/arch/xtensa/include/asm/io.h b/arch/xtensa/include/asm/io.h
index 74944207167e..fe1600a09438 100644
--- a/arch/xtensa/include/asm/io.h
+++ b/arch/xtensa/include/asm/io.h
@@ -74,13 +74,6 @@ static inline void iounmap(volatile void __iomem *addr)
 
 #endif /* CONFIG_MMU */
 
-/*
- * Generic I/O
- */
-#define readb_relaxed readb
-#define readw_relaxed readw
-#define readl_relaxed readl
-
 #endif	/* __KERNEL__ */
 
 #include <asm-generic/io.h>
diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index 524b707894ef..4c58333b4257 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -84,9 +84,12 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size)
 }
 #endif
 
-void __weak unxlate_dev_mem_ptr(unsigned long phys, void *addr)
+#ifndef unxlate_dev_mem_ptr
+#define unxlate_dev_mem_ptr unxlate_dev_mem_ptr
+void __weak unxlate_dev_mem_ptr(phys_addr_t phys, void *addr)
 {
 }
+#endif
 
 /*
  * This funcion reads the *physical* memory. The f_pos points directly to the
@@ -97,7 +100,7 @@ static ssize_t read_mem(struct file *file, char __user *buf,
 {
 	phys_addr_t p = *ppos;
 	ssize_t read, sz;
-	char *ptr;
+	void *ptr;
 
 	if (p != *ppos)
 		return 0;
@@ -400,7 +403,7 @@ static ssize_t read_kmem(struct file *file, char __user *buf,
 			 * uncached, then it must also be accessed uncached
 			 * by the kernel or data corruption may occur
 			 */
-			kbuf = xlate_dev_kmem_ptr((char *)p);
+			kbuf = xlate_dev_kmem_ptr((void *)p);
 
 			if (copy_to_user(buf, kbuf, sz))
 				return -EFAULT;
@@ -461,7 +464,7 @@ static ssize_t do_write_kmem(unsigned long p, const char __user *buf,
 #endif
 
 	while (count > 0) {
-		char *ptr;
+		void *ptr;
 
 		sz = size_inside_page(p, count);
 
@@ -470,7 +473,7 @@ static ssize_t do_write_kmem(unsigned long p, const char __user *buf,
 		 * it must also be accessed uncached by the kernel or data
 		 * corruption may occur.
 		 */
-		ptr = xlate_dev_kmem_ptr((char *)p);
+		ptr = xlate_dev_kmem_ptr((void *)p);
 
 		copied = copy_from_user(ptr, buf, sz);
 		if (copied) {
diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h
index b8fdc57a7335..9db042304df3 100644
--- a/include/asm-generic/io.h
+++ b/include/asm-generic/io.h
@@ -12,6 +12,7 @@
 #define __ASM_GENERIC_IO_H
 
 #include <asm/page.h> /* I/O is all done through memory accesses */
+#include <linux/string.h> /* for memset() and memcpy() */
 #include <linux/types.h>
 
 #ifdef CONFIG_GENERIC_IOMAP
@@ -24,260 +25,691 @@
 #define mmiowb() do {} while (0)
 #endif
 
-/*****************************************************************************/
 /*
- * readX/writeX() are used to access memory mapped devices. On some
- * architectures the memory mapped IO stuff needs to be accessed
- * differently. On the simple architectures, we just read/write the
- * memory location directly.
+ * __raw_{read,write}{b,w,l,q}() access memory in native endianness.
+ *
+ * On some architectures memory mapped IO needs to be accessed differently.
+ * On the simple architectures, we just read/write the memory location
+ * directly.
  */
+
 #ifndef __raw_readb
+#define __raw_readb __raw_readb
 static inline u8 __raw_readb(const volatile void __iomem *addr)
 {
-	return *(const volatile u8 __force *) addr;
+	return *(const volatile u8 __force *)addr;
 }
 #endif
 
 #ifndef __raw_readw
+#define __raw_readw __raw_readw
 static inline u16 __raw_readw(const volatile void __iomem *addr)
 {
-	return *(const volatile u16 __force *) addr;
+	return *(const volatile u16 __force *)addr;
 }
 #endif
 
 #ifndef __raw_readl
+#define __raw_readl __raw_readl
 static inline u32 __raw_readl(const volatile void __iomem *addr)
 {
-	return *(const volatile u32 __force *) addr;
+	return *(const volatile u32 __force *)addr;
 }
 #endif
 
-#define readb __raw_readb
-
-#define readw readw
-static inline u16 readw(const volatile void __iomem *addr)
-{
-	return __le16_to_cpu(__raw_readw(addr));
-}
-
-#define readl readl
-static inline u32 readl(const volatile void __iomem *addr)
+#ifdef CONFIG_64BIT
+#ifndef __raw_readq
+#define __raw_readq __raw_readq
+static inline u64 __raw_readq(const volatile void __iomem *addr)
 {
-	return __le32_to_cpu(__raw_readl(addr));
+	return *(const volatile u64 __force *)addr;
 }
+#endif
+#endif /* CONFIG_64BIT */
 
 #ifndef __raw_writeb
-static inline void __raw_writeb(u8 b, volatile void __iomem *addr)
+#define __raw_writeb __raw_writeb
+static inline void __raw_writeb(u8 value, volatile void __iomem *addr)
 {
-	*(volatile u8 __force *) addr = b;
+	*(volatile u8 __force *)addr = value;
 }
 #endif
 
 #ifndef __raw_writew
-static inline void __raw_writew(u16 b, volatile void __iomem *addr)
+#define __raw_writew __raw_writew
+static inline void __raw_writew(u16 value, volatile void __iomem *addr)
 {
-	*(volatile u16 __force *) addr = b;
+	*(volatile u16 __force *)addr = value;
 }
 #endif
 
 #ifndef __raw_writel
-static inline void __raw_writel(u32 b, volatile void __iomem *addr)
+#define __raw_writel __raw_writel
+static inline void __raw_writel(u32 value, volatile void __iomem *addr)
 {
-	*(volatile u32 __force *) addr = b;
+	*(volatile u32 __force *)addr = value;
 }
 #endif
 
-#define writeb __raw_writeb
-#define writew(b,addr) __raw_writew(__cpu_to_le16(b),addr)
-#define writel(b,addr) __raw_writel(__cpu_to_le32(b),addr)
-
 #ifdef CONFIG_64BIT
-#ifndef __raw_readq
-static inline u64 __raw_readq(const volatile void __iomem *addr)
+#ifndef __raw_writeq
+#define __raw_writeq __raw_writeq
+static inline void __raw_writeq(u64 value, volatile void __iomem *addr)
 {
-	return *(const volatile u64 __force *) addr;
+	*(volatile u64 __force *)addr = value;
 }
 #endif
+#endif /* CONFIG_64BIT */
 
-#define readq readq
-static inline u64 readq(const volatile void __iomem *addr)
-{
-	return __le64_to_cpu(__raw_readq(addr));
-}
+/*
+ * {read,write}{b,w,l,q}() access little endian memory and return result in
+ * native endianness.
+ */
 
-#ifndef __raw_writeq
-static inline void __raw_writeq(u64 b, volatile void __iomem *addr)
+#ifndef readb
+#define readb readb
+static inline u8 readb(const volatile void __iomem *addr)
 {
-	*(volatile u64 __force *) addr = b;
+	return __raw_readb(addr);
 }
 #endif
 
-#define writeq(b, addr) __raw_writeq(__cpu_to_le64(b), addr)
-#endif /* CONFIG_64BIT */
-
-#ifndef PCI_IOBASE
-#define PCI_IOBASE ((void __iomem *) 0)
+#ifndef readw
+#define readw readw
+static inline u16 readw(const volatile void __iomem *addr)
+{
+	return __le16_to_cpu(__raw_readw(addr));
+}
 #endif
 
-/*****************************************************************************/
-/*
- * traditional input/output functions
- */
-
-static inline u8 inb(unsigned long addr)
+#ifndef readl
+#define readl readl
+static inline u32 readl(const volatile void __iomem *addr)
 {
-	return readb(addr + PCI_IOBASE);
+	return __le32_to_cpu(__raw_readl(addr));
 }
+#endif
 
-static inline u16 inw(unsigned long addr)
+#ifdef CONFIG_64BIT
+#ifndef readq
+#define readq readq
+static inline u64 readq(const volatile void __iomem *addr)
 {
-	return readw(addr + PCI_IOBASE);
+	return __le64_to_cpu(__raw_readq(addr));
 }
+#endif
+#endif /* CONFIG_64BIT */
 
-static inline u32 inl(unsigned long addr)
+#ifndef writeb
+#define writeb writeb
+static inline void writeb(u8 value, volatile void __iomem *addr)
 {
-	return readl(addr + PCI_IOBASE);
+	__raw_writeb(value, addr);
 }
+#endif
 
-static inline void outb(u8 b, unsigned long addr)
+#ifndef writew
+#define writew writew
+static inline void writew(u16 value, volatile void __iomem *addr)
 {
-	writeb(b, addr + PCI_IOBASE);
+	__raw_writew(cpu_to_le16(value), addr);
 }
+#endif
 
-static inline void outw(u16 b, unsigned long addr)
+#ifndef writel
+#define writel writel
+static inline void writel(u32 value, volatile void __iomem *addr)
 {
-	writew(b, addr + PCI_IOBASE);
+	__raw_writel(__cpu_to_le32(value), addr);
 }
+#endif
 
-static inline void outl(u32 b, unsigned long addr)
+#ifdef CONFIG_64BIT
+#ifndef writeq
+#define writeq writeq
+static inline void writeq(u64 value, volatile void __iomem *addr)
 {
-	writel(b, addr + PCI_IOBASE);
+	__raw_writeq(__cpu_to_le64(value), addr);
 }
+#endif
+#endif /* CONFIG_64BIT */
+
+/*
+ * {read,write}{b,w,l,q}_relaxed() are like the regular version, but
+ * are not guaranteed to provide ordering against spinlocks or memory
+ * accesses.
+ */
+#ifndef readb_relaxed
+#define readb_relaxed readb
+#endif
 
-#define inb_p(addr)	inb(addr)
-#define inw_p(addr)	inw(addr)
-#define inl_p(addr)	inl(addr)
-#define outb_p(x, addr)	outb((x), (addr))
-#define outw_p(x, addr)	outw((x), (addr))
-#define outl_p(x, addr)	outl((x), (addr))
+#ifndef readw_relaxed
+#define readw_relaxed readw
+#endif
 
-#ifndef insb
-static inline void insb(unsigned long addr, void *buffer, int count)
+#ifndef readl_relaxed
+#define readl_relaxed readl
+#endif
+
+#ifndef readq_relaxed
+#define readq_relaxed readq
+#endif
+
+#ifndef writeb_relaxed
+#define writeb_relaxed writeb
+#endif
+
+#ifndef writew_relaxed
+#define writew_relaxed writew
+#endif
+
+#ifndef writel_relaxed
+#define writel_relaxed writel
+#endif
+
+#ifndef writeq_relaxed
+#define writeq_relaxed writeq
+#endif
+
+/*
+ * {read,write}s{b,w,l,q}() repeatedly access the same memory address in
+ * native endianness in 8-, 16-, 32- or 64-bit chunks (@count times).
+ */
+#ifndef readsb
+#define readsb readsb
+static inline void readsb(const volatile void __iomem *addr, void *buffer,
+			  unsigned int count)
 {
 	if (count) {
 		u8 *buf = buffer;
+
 		do {
-			u8 x = __raw_readb(addr + PCI_IOBASE);
+			u8 x = __raw_readb(addr);
 			*buf++ = x;
 		} while (--count);
 	}
 }
 #endif
 
-#ifndef insw
-static inline void insw(unsigned long addr, void *buffer, int count)
+#ifndef readsw
+#define readsw readsw
+static inline void readsw(const volatile void __iomem *addr, void *buffer,
+			  unsigned int count)
 {
 	if (count) {
 		u16 *buf = buffer;
+
 		do {
-			u16 x = __raw_readw(addr + PCI_IOBASE);
+			u16 x = __raw_readw(addr);
 			*buf++ = x;
 		} while (--count);
 	}
 }
 #endif
 
-#ifndef insl
-static inline void insl(unsigned long addr, void *buffer, int count)
+#ifndef readsl
+#define readsl readsl
+static inline void readsl(const volatile void __iomem *addr, void *buffer,
+			  unsigned int count)
 {
 	if (count) {
 		u32 *buf = buffer;
+
 		do {
-			u32 x = __raw_readl(addr + PCI_IOBASE);
+			u32 x = __raw_readl(addr);
 			*buf++ = x;
 		} while (--count);
 	}
 }
 #endif
 
-#ifndef outsb
-static inline void outsb(unsigned long addr, const void *buffer, int count)
+#ifdef CONFIG_64BIT
+#ifndef readsq
+#define readsq readsq
+static inline void readsq(const volatile void __iomem *addr, void *buffer,
+			  unsigned int count)
+{
+	if (count) {
+		u64 *buf = buffer;
+
+		do {
+			u64 x = __raw_readq(addr);
+			*buf++ = x;
+		} while (--count);
+	}
+}
+#endif
+#endif /* CONFIG_64BIT */
+
+#ifndef writesb
+#define writesb writesb
+static inline void writesb(volatile void __iomem *addr, const void *buffer,
+			   unsigned int count)
 {
 	if (count) {
 		const u8 *buf = buffer;
+
 		do {
-			__raw_writeb(*buf++, addr + PCI_IOBASE);
+			__raw_writeb(*buf++, addr);
 		} while (--count);
 	}
 }
 #endif
 
-#ifndef outsw
-static inline void outsw(unsigned long addr, const void *buffer, int count)
+#ifndef writesw
+#define writesw writesw
+static inline void writesw(volatile void __iomem *addr, const void *buffer,
+			   unsigned int count)
 {
 	if (count) {
 		const u16 *buf = buffer;
+
 		do {
-			__raw_writew(*buf++, addr + PCI_IOBASE);
+			__raw_writew(*buf++, addr);
 		} while (--count);
 	}
 }
 #endif
 
-#ifndef outsl
-static inline void outsl(unsigned long addr, const void *buffer, int count)
+#ifndef writesl
+#define writesl writesl
+static inline void writesl(volatile void __iomem *addr, const void *buffer,
+			   unsigned int count)
 {
 	if (count) {
 		const u32 *buf = buffer;
+
 		do {
-			__raw_writel(*buf++, addr + PCI_IOBASE);
+			__raw_writel(*buf++, addr);
 		} while (--count);
 	}
 }
 #endif
 
-#ifndef CONFIG_GENERIC_IOMAP
-#define ioread8(addr)		readb(addr)
-#define ioread16(addr)		readw(addr)
-#define ioread16be(addr)	__be16_to_cpu(__raw_readw(addr))
-#define ioread32(addr)		readl(addr)
-#define ioread32be(addr)	__be32_to_cpu(__raw_readl(addr))
-
-#define iowrite8(v, addr)	writeb((v), (addr))
-#define iowrite16(v, addr)	writew((v), (addr))
-#define iowrite16be(v, addr)	__raw_writew(__cpu_to_be16(v), addr)
-#define iowrite32(v, addr)	writel((v), (addr))
-#define iowrite32be(v, addr)	__raw_writel(__cpu_to_be32(v), addr)
-
-#define ioread8_rep(p, dst, count) \
-	insb((unsigned long) (p), (dst), (count))
-#define ioread16_rep(p, dst, count) \
-	insw((unsigned long) (p), (dst), (count))
-#define ioread32_rep(p, dst, count) \
-	insl((unsigned long) (p), (dst), (count))
-
-#define iowrite8_rep(p, src, count) \
-	outsb((unsigned long) (p), (src), (count))
-#define iowrite16_rep(p, src, count) \
-	outsw((unsigned long) (p), (src), (count))
-#define iowrite32_rep(p, src, count) \
-	outsl((unsigned long) (p), (src), (count))
-#endif /* CONFIG_GENERIC_IOMAP */
+#ifdef CONFIG_64BIT
+#ifndef writesq
+#define writesq writesq
+static inline void writesq(volatile void __iomem *addr, const void *buffer,
+			   unsigned int count)
+{
+	if (count) {
+		const u64 *buf = buffer;
+
+		do {
+			__raw_writeq(*buf++, addr);
+		} while (--count);
+	}
+}
+#endif
+#endif /* CONFIG_64BIT */
+
+#ifndef PCI_IOBASE
+#define PCI_IOBASE ((void __iomem *)0)
+#endif
 
 #ifndef IO_SPACE_LIMIT
 #define IO_SPACE_LIMIT 0xffff
 #endif
 
+/*
+ * {in,out}{b,w,l}() access little endian I/O. {in,out}{b,w,l}_p() can be
+ * implemented on hardware that needs an additional delay for I/O accesses to
+ * take effect.
+ */
+
+#ifndef inb
+#define inb inb
+static inline u8 inb(unsigned long addr)
+{
+	return readb(PCI_IOBASE + addr);
+}
+#endif
+
+#ifndef inw
+#define inw inw
+static inline u16 inw(unsigned long addr)
+{
+	return readw(PCI_IOBASE + addr);
+}
+#endif
+
+#ifndef inl
+#define inl inl
+static inline u32 inl(unsigned long addr)
+{
+	return readl(PCI_IOBASE + addr);
+}
+#endif
+
+#ifndef outb
+#define outb outb
+static inline void outb(u8 value, unsigned long addr)
+{
+	writeb(value, PCI_IOBASE + addr);
+}
+#endif
+
+#ifndef outw
+#define outw outw
+static inline void outw(u16 value, unsigned long addr)
+{
+	writew(value, PCI_IOBASE + addr);
+}
+#endif
+
+#ifndef outl
+#define outl outl
+static inline void outl(u32 value, unsigned long addr)
+{
+	writel(value, PCI_IOBASE + addr);
+}
+#endif
+
+#ifndef inb_p
+#define inb_p inb_p
+static inline u8 inb_p(unsigned long addr)
+{
+	return inb(addr);
+}
+#endif
+
+#ifndef inw_p
+#define inw_p inw_p
+static inline u16 inw_p(unsigned long addr)
+{
+	return inw(addr);
+}
+#endif
+
+#ifndef inl_p
+#define inl_p inl_p
+static inline u32 inl_p(unsigned long addr)
+{
+	return inl(addr);
+}
+#endif
+
+#ifndef outb_p
+#define outb_p outb_p
+static inline void outb_p(u8 value, unsigned long addr)
+{
+	outb(value, addr);
+}
+#endif
+
+#ifndef outw_p
+#define outw_p outw_p
+static inline void outw_p(u16 value, unsigned long addr)
+{
+	outw(value, addr);
+}
+#endif
+
+#ifndef outl_p
+#define outl_p outl_p
+static inline void outl_p(u32 value, unsigned long addr)
+{
+	outl(value, addr);
+}
+#endif
+
+/*
+ * {in,out}s{b,w,l}{,_p}() are variants of the above that repeatedly access a
+ * single I/O port multiple times.
+ */
+
+#ifndef insb
+#define insb insb
+static inline void insb(unsigned long addr, void *buffer, unsigned int count)
+{
+	readsb(PCI_IOBASE + addr, buffer, count);
+}
+#endif
+
+#ifndef insw
+#define insw insw
+static inline void insw(unsigned long addr, void *buffer, unsigned int count)
+{
+	readsw(PCI_IOBASE + addr, buffer, count);
+}
+#endif
+
+#ifndef insl
+#define insl insl
+static inline void insl(unsigned long addr, void *buffer, unsigned int count)
+{
+	readsl(PCI_IOBASE + addr, buffer, count);
+}
+#endif
+
+#ifndef outsb
+#define outsb outsb
+static inline void outsb(unsigned long addr, const void *buffer,
+			 unsigned int count)
+{
+	writesb(PCI_IOBASE + addr, buffer, count);
+}
+#endif
+
+#ifndef outsw
+#define outsw outsw
+static inline void outsw(unsigned long addr, const void *buffer,
+			 unsigned int count)
+{
+	writesw(PCI_IOBASE + addr, buffer, count);
+}
+#endif
+
+#ifndef outsl
+#define outsl outsl
+static inline void outsl(unsigned long addr, const void *buffer,
+			 unsigned int count)
+{
+	writesl(PCI_IOBASE + addr, buffer, count);
+}
+#endif
+
+#ifndef insb_p
+#define insb_p insb_p
+static inline void insb_p(unsigned long addr, void *buffer, unsigned int count)
+{
+	insb(addr, buffer, count);
+}
+#endif
+
+#ifndef insw_p
+#define insw_p insw_p
+static inline void insw_p(unsigned long addr, void *buffer, unsigned int count)
+{
+	insw(addr, buffer, count);
+}
+#endif
+
+#ifndef insl_p
+#define insl_p insl_p
+static inline void insl_p(unsigned long addr, void *buffer, unsigned int count)
+{
+	insl(addr, buffer, count);
+}
+#endif
+
+#ifndef outsb_p
+#define outsb_p outsb_p
+static inline void outsb_p(unsigned long addr, const void *buffer,
+			   unsigned int count)
+{
+	outsb(addr, buffer, count);
+}
+#endif
+
+#ifndef outsw_p
+#define outsw_p outsw_p
+static inline void outsw_p(unsigned long addr, const void *buffer,
+			   unsigned int count)
+{
+	outsw(addr, buffer, count);
+}
+#endif
+
+#ifndef outsl_p
+#define outsl_p outsl_p
+static inline void outsl_p(unsigned long addr, const void *buffer,
+			   unsigned int count)
+{
+	outsl(addr, buffer, count);
+}
+#endif
+
+#ifndef CONFIG_GENERIC_IOMAP
+#ifndef ioread8
+#define ioread8 ioread8
+static inline u8 ioread8(const volatile void __iomem *addr)
+{
+	return readb(addr);
+}
+#endif
+
+#ifndef ioread16
+#define ioread16 ioread16
+static inline u16 ioread16(const volatile void __iomem *addr)
+{
+	return readw(addr);
+}
+#endif
+
+#ifndef ioread32
+#define ioread32 ioread32
+static inline u32 ioread32(const volatile void __iomem *addr)
+{
+	return readl(addr);
+}
+#endif
+
+#ifndef iowrite8
+#define iowrite8 iowrite8
+static inline void iowrite8(u8 value, volatile void __iomem *addr)
+{
+	writeb(value, addr);
+}
+#endif
+
+#ifndef iowrite16
+#define iowrite16 iowrite16
+static inline void iowrite16(u16 value, volatile void __iomem *addr)
+{
+	writew(value, addr);
+}
+#endif
+
+#ifndef iowrite32
+#define iowrite32 iowrite32
+static inline void iowrite32(u32 value, volatile void __iomem *addr)
+{
+	writel(value, addr);
+}
+#endif
+
+#ifndef ioread16be
+#define ioread16be ioread16be
+static inline u16 ioread16be(const volatile void __iomem *addr)
+{
+	return __be16_to_cpu(__raw_readw(addr));
+}
+#endif
+
+#ifndef ioread32be
+#define ioread32be ioread32be
+static inline u32 ioread32be(const volatile void __iomem *addr)
+{
+	return __be32_to_cpu(__raw_readl(addr));
+}
+#endif
+
+#ifndef iowrite16be
+#define iowrite16be iowrite16be
+static inline void iowrite16be(u16 value, void volatile __iomem *addr)
+{
+	__raw_writew(__cpu_to_be16(value), addr);
+}
+#endif
+
+#ifndef iowrite32be
+#define iowrite32be iowrite32be
+static inline void iowrite32be(u32 value, volatile void __iomem *addr)
+{
+	__raw_writel(__cpu_to_be32(value), addr);
+}
+#endif
+
+#ifndef ioread8_rep
+#define ioread8_rep ioread8_rep
+static inline void ioread8_rep(const volatile void __iomem *addr, void *buffer,
+			       unsigned int count)
+{
+	readsb(addr, buffer, count);
+}
+#endif
+
+#ifndef ioread16_rep
+#define ioread16_rep ioread16_rep
+static inline void ioread16_rep(const volatile void __iomem *addr,
+				void *buffer, unsigned int count)
+{
+	readsw(addr, buffer, count);
+}
+#endif
+
+#ifndef ioread32_rep
+#define ioread32_rep ioread32_rep
+static inline void ioread32_rep(const volatile void __iomem *addr,
+				void *buffer, unsigned int count)
+{
+	readsl(addr, buffer, count);
+}
+#endif
+
+#ifndef iowrite8_rep
+#define iowrite8_rep iowrite8_rep
+static inline void iowrite8_rep(volatile void __iomem *addr,
+				const void *buffer,
+				unsigned int count)
+{
+	writesb(addr, buffer, count);
+}
+#endif
+
+#ifndef iowrite16_rep
+#define iowrite16_rep iowrite16_rep
+static inline void iowrite16_rep(volatile void __iomem *addr,
+				 const void *buffer,
+				 unsigned int count)
+{
+	writesw(addr, buffer, count);
+}
+#endif
+
+#ifndef iowrite32_rep
+#define iowrite32_rep iowrite32_rep
+static inline void iowrite32_rep(volatile void __iomem *addr,
+				 const void *buffer,
+				 unsigned int count)
+{
+	writesl(addr, buffer, count);
+}
+#endif
+#endif /* CONFIG_GENERIC_IOMAP */
+
 #ifdef __KERNEL__
 
 #include <linux/vmalloc.h>
-#define __io_virt(x) ((void __force *) (x))
+#define __io_virt(x) ((void __force *)(x))
 
 #ifndef CONFIG_GENERIC_IOMAP
 struct pci_dev;
 extern void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long max);
 
 #ifndef pci_iounmap
+#define pci_iounmap pci_iounmap
 static inline void pci_iounmap(struct pci_dev *dev, void __iomem *p)
 {
 }
@@ -289,11 +721,15 @@ static inline void pci_iounmap(struct pci_dev *dev, void __iomem *p)
  * These are pretty trivial
  */
 #ifndef virt_to_phys
+#define virt_to_phys virt_to_phys
 static inline unsigned long virt_to_phys(volatile void *address)
 {
 	return __pa((unsigned long)address);
 }
+#endif
 
+#ifndef phys_to_virt
+#define phys_to_virt phys_to_virt
 static inline void *phys_to_virt(unsigned long address)
 {
 	return __va(address);
@@ -306,37 +742,65 @@ static inline void *phys_to_virt(unsigned long address)
  * This implementation is for the no-MMU case only... if you have an MMU
  * you'll need to provide your own definitions.
  */
+
 #ifndef CONFIG_MMU
-static inline void __iomem *ioremap(phys_addr_t offset, unsigned long size)
+#ifndef ioremap
+#define ioremap ioremap
+static inline void __iomem *ioremap(phys_addr_t offset, size_t size)
 {
-	return (void __iomem*) (unsigned long)offset;
+	return (void __iomem *)(unsigned long)offset;
 }
+#endif
 
-#define __ioremap(offset, size, flags)	ioremap(offset, size)
+#ifndef __ioremap
+#define __ioremap __ioremap
+static inline void __iomem *__ioremap(phys_addr_t offset, size_t size,
+				      unsigned long flags)
+{
+	return ioremap(offset, size);
+}
+#endif
 
 #ifndef ioremap_nocache
-#define ioremap_nocache ioremap
+#define ioremap_nocache ioremap_nocache
+static inline void __iomem *ioremap_nocache(phys_addr_t offset, size_t size)
+{
+	return ioremap(offset, size);
+}
 #endif
 
 #ifndef ioremap_wc
-#define ioremap_wc ioremap_nocache
+#define ioremap_wc ioremap_wc
+static inline void __iomem *ioremap_wc(phys_addr_t offset, size_t size)
+{
+	return ioremap_nocache(offset, size);
+}
 #endif
 
+#ifndef iounmap
+#define iounmap iounmap
 static inline void iounmap(void __iomem *addr)
 {
 }
+#endif
 #endif /* CONFIG_MMU */
 
 #ifdef CONFIG_HAS_IOPORT_MAP
 #ifndef CONFIG_GENERIC_IOMAP
+#ifndef ioport_map
+#define ioport_map ioport_map
 static inline void __iomem *ioport_map(unsigned long port, unsigned int nr)
 {
 	return PCI_IOBASE + (port & IO_SPACE_LIMIT);
 }
+#endif
 
+#ifndef ioport_unmap
+#define ioport_unmap ioport_unmap
 static inline void ioport_unmap(void __iomem *p)
 {
 }
+#endif
 #else /* CONFIG_GENERIC_IOMAP */
 extern void __iomem *ioport_map(unsigned long port, unsigned int nr);
 extern void ioport_unmap(void __iomem *p);
@@ -344,35 +808,68 @@ extern void ioport_unmap(void __iomem *p);
 #endif /* CONFIG_HAS_IOPORT_MAP */
 
 #ifndef xlate_dev_kmem_ptr
-#define xlate_dev_kmem_ptr(p)	p
+#define xlate_dev_kmem_ptr xlate_dev_kmem_ptr
+static inline void *xlate_dev_kmem_ptr(void *addr)
+{
+	return addr;
+}
 #endif
+
 #ifndef xlate_dev_mem_ptr
-#define xlate_dev_mem_ptr(p)	__va(p)
+#define xlate_dev_mem_ptr xlate_dev_mem_ptr
+static inline void *xlate_dev_mem_ptr(phys_addr_t addr)
+{
+	return __va(addr);
+}
+#endif
+
+#ifndef unxlate_dev_mem_ptr
+#define unxlate_dev_mem_ptr unxlate_dev_mem_ptr
+static inline void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr)
+{
+}
 #endif
 
 #ifdef CONFIG_VIRT_TO_BUS
 #ifndef virt_to_bus
-static inline unsigned long virt_to_bus(volatile void *address)
+static inline unsigned long virt_to_bus(void *address)
 {
-	return ((unsigned long) address);
+	return (unsigned long)address;
 }
 
 static inline void *bus_to_virt(unsigned long address)
 {
-	return (void *) address;
+	return (void *)address;
 }
 #endif
 #endif
 
 #ifndef memset_io
-#define memset_io(a, b, c)	memset(__io_virt(a), (b), (c))
+#define memset_io memset_io
+static inline void memset_io(volatile void __iomem *addr, int value,
+			     size_t size)
+{
+	memset(__io_virt(addr), value, size);
+}
 #endif
 
 #ifndef memcpy_fromio
-#define memcpy_fromio(a, b, c)	memcpy((a), __io_virt(b), (c))
+#define memcpy_fromio memcpy_fromio
+static inline void memcpy_fromio(void *buffer,
+				 const volatile void __iomem *addr,
+				 size_t size)
+{
+	memcpy(buffer, __io_virt(addr), size);
+}
 #endif
+
 #ifndef memcpy_toio
-#define memcpy_toio(a, b, c)	memcpy(__io_virt(a), (b), (c))
+#define memcpy_toio memcpy_toio
+static inline void memcpy_toio(volatile void __iomem *addr, const void *buffer,
+			       size_t size)
+{
+	memcpy(__io_virt(addr), buffer, size);
+}
 #endif
 
 #endif /* __KERNEL__ */