diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index 22a969cdd4766a2f4f3651d359cd81defdb3bd21..4af4cea8cff041eb1fdcd0c4d076189244d828fe 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/cris/include/asm/io.h b/arch/cris/include/asm/io.h
index e59dba12ce9476d0888e3150137274c23ea0ab0f..752a3f45df60cd475b51b21bb567b9bd48f90581 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 8cb50a2fbcb2d9b34b6bad36323cb49513f64ceb..99bb7efaf9b7ec458762cd3f5016a92949a44987 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 bee0acd52f7e3d603ec87ce87ec3843b1efe55bd..80a7e34be00984a104923d933eafa7faa0d937fc 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/m32r/include/asm/io.h b/arch/m32r/include/asm/io.h
index 4010f1fc5b65ba1fc01217f071d897af5a33c125..6e7787f3dac7bb52f87ec33378193b14f65bf70c 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 c70cc91550037c4e5e9317bd79e2d40056913b1e..bccd5a914eb6fc6c733990141f8e78f60391efda 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 be4b5a813ad401972624886802f5f69aa047e7dc..a93c8cde4d382fc171798affe7090cc59a60f46d 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 433751b2a003309bb2a449888ac5b48f6f747d3c..940f5fc1d1da13f3988fe99fd69a7d02e0825c8d 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 e6ed0d897ccc7c8b4f08b2f12fc97edee223de1b..897ba3c12b3276b9071a56e70e67e7e39d28850e 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 1f6d2ae7aba59dfe2956dd6439569aa867f5b8a1..8cd0abf28ffbbe400a4f5e1c408573085184add2 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 97d3869991ca691ebf0342b496ebe767aee7492a..9eaf301ac952fccb9270d0dc89fb293ef17b34a9 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 d22c2eeae78fc4b0f9433d4821cdd71e3d3bbb2b..6ad9013c67e72342e50fcda2c25e9b9215fe41c5 100644
--- a/arch/s390/include/asm/io.h
+++ b/arch/s390/include/asm/io.h
@@ -61,11 +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/sparc/include/asm/io.h b/arch/sparc/include/asm/io.h
index f6902cf3cbe997f5c66ec750e1ebafcfdc2e9f5b..493f22c4684f6db6cd728c1cef08ec394ad934cb 100644
--- a/arch/sparc/include/asm/io.h
+++ b/arch/sparc/include/asm/io.h
@@ -10,6 +10,15 @@
  * Defines used for both SPARC32 and SPARC64
  */
 
+/* Relaxed accessors for MMIO */
+#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(__w, __addr)	writew(__w, __addr)
+#define writel_relaxed(__l, __addr)	writel(__l, __addr)
+
 /* Big endian versions of memory read/write routines */
 #define readb_be(__addr)	__raw_readb(__addr)
 #define readw_be(__addr)	__raw_readw(__addr)
diff --git a/arch/sparc/include/asm/io_32.h b/arch/sparc/include/asm/io_32.h
index 9f532902627c4412b08968645eda5667975b104e..407ac14295f43ec01e93141e1673794d5e3f024c 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 80b54b326d4983f5c2ccdd48557276d459c5fb62..d50e6127325d099fab38a583a09c9d666a6350f4 100644
--- a/arch/sparc/include/asm/io_64.h
+++ b/arch/sparc/include/asm/io_64.h
@@ -136,6 +136,7 @@ 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;
 
@@ -175,6 +176,7 @@ 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 +185,6 @@ static inline void writeq(u64 q, volatile void __iomem *addr)
 			     : "memory");
 }
 
-
 #define inb inb
 static inline u8 inb(unsigned long addr)
 {
@@ -264,11 +265,6 @@ 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 9fe434969fab0eef3a4e28c824f6f6a415e3abb8..d372641054d910546d3426148e54ad3eac82b93a 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 ae2b593e7c6efd0b369498822b9c1adf780c46bd..0cdbe6e81b453405cbc7b39c09eb33c49043490a 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)
diff --git a/arch/xtensa/include/asm/io.h b/arch/xtensa/include/asm/io.h
index 74944207167eccfb0f6e122ad7418d5728d4a2b7..fe1600a094384e8c18a988e91862b531031984f3 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/include/asm-generic/io.h b/include/asm-generic/io.h
index 00483d769d86d0203d1ca0521764a1743956176a..9db042304df37d0c97eea09be466fa403d505603 100644
--- a/include/asm-generic/io.h
+++ b/include/asm-generic/io.h
@@ -174,6 +174,43 @@ static inline void writeq(u64 value, volatile void __iomem *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
+
+#ifndef readw_relaxed
+#define readw_relaxed readw
+#endif
+
+#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).