Merge branch 'devel-misc' into omap-for-linus

4 files changed, 104 insertions, 86 deletions

diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h
index a0162fa94564..7e79503ab89b 100644
--- a/arch/arm/include/asm/atomic.h
+++ b/arch/arm/include/asm/atomic.h
@@ -40,12 +40,12 @@ static inline void atomic_add(int i, atomic_t *v)
 	int result;
 
 	__asm__ __volatile__("@ atomic_add\n"
-"1:	ldrex	%0, [%2]\n"
-"	add	%0, %0, %3\n"
-"	strex	%1, %0, [%2]\n"
+"1:	ldrex	%0, [%3]\n"
+"	add	%0, %0, %4\n"
+"	strex	%1, %0, [%3]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
-	: "=&r" (result), "=&r" (tmp)
+	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
 	: "r" (&v->counter), "Ir" (i)
 	: "cc");
 }
@@ -58,12 +58,12 @@ static inline int atomic_add_return(int i, atomic_t *v)
 	smp_mb();
 
 	__asm__ __volatile__("@ atomic_add_return\n"
-"1:	ldrex	%0, [%2]\n"
-"	add	%0, %0, %3\n"
-"	strex	%1, %0, [%2]\n"
+"1:	ldrex	%0, [%3]\n"
+"	add	%0, %0, %4\n"
+"	strex	%1, %0, [%3]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
-	: "=&r" (result), "=&r" (tmp)
+	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
 	: "r" (&v->counter), "Ir" (i)
 	: "cc");
 
@@ -78,12 +78,12 @@ static inline void atomic_sub(int i, atomic_t *v)
 	int result;
 
 	__asm__ __volatile__("@ atomic_sub\n"
-"1:	ldrex	%0, [%2]\n"
-"	sub	%0, %0, %3\n"
-"	strex	%1, %0, [%2]\n"
+"1:	ldrex	%0, [%3]\n"
+"	sub	%0, %0, %4\n"
+"	strex	%1, %0, [%3]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
-	: "=&r" (result), "=&r" (tmp)
+	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
 	: "r" (&v->counter), "Ir" (i)
 	: "cc");
 }
@@ -96,12 +96,12 @@ static inline int atomic_sub_return(int i, atomic_t *v)
 	smp_mb();
 
 	__asm__ __volatile__("@ atomic_sub_return\n"
-"1:	ldrex	%0, [%2]\n"
-"	sub	%0, %0, %3\n"
-"	strex	%1, %0, [%2]\n"
+"1:	ldrex	%0, [%3]\n"
+"	sub	%0, %0, %4\n"
+"	strex	%1, %0, [%3]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
-	: "=&r" (result), "=&r" (tmp)
+	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
 	: "r" (&v->counter), "Ir" (i)
 	: "cc");
 
@@ -118,11 +118,11 @@ static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
 
 	do {
 		__asm__ __volatile__("@ atomic_cmpxchg\n"
-		"ldrex	%1, [%2]\n"
+		"ldrex	%1, [%3]\n"
 		"mov	%0, #0\n"
-		"teq	%1, %3\n"
-		"strexeq %0, %4, [%2]\n"
-		    : "=&r" (res), "=&r" (oldval)
+		"teq	%1, %4\n"
+		"strexeq %0, %5, [%3]\n"
+		    : "=&r" (res), "=&r" (oldval), "+Qo" (ptr->counter)
 		    : "r" (&ptr->counter), "Ir" (old), "r" (new)
 		    : "cc");
 	} while (res);
@@ -137,12 +137,12 @@ static inline void atomic_clear_mask(unsigned long mask, unsigned long *addr)
 	unsigned long tmp, tmp2;
 
 	__asm__ __volatile__("@ atomic_clear_mask\n"
-"1:	ldrex	%0, [%2]\n"
-"	bic	%0, %0, %3\n"
-"	strex	%1, %0, [%2]\n"
+"1:	ldrex	%0, [%3]\n"
+"	bic	%0, %0, %4\n"
+"	strex	%1, %0, [%3]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
-	: "=&r" (tmp), "=&r" (tmp2)
+	: "=&r" (tmp), "=&r" (tmp2), "+Qo" (*addr)
 	: "r" (addr), "Ir" (mask)
 	: "cc");
 }
@@ -249,7 +249,7 @@ static inline u64 atomic64_read(atomic64_t *v)
 	__asm__ __volatile__("@ atomic64_read\n"
 "	ldrexd	%0, %H0, [%1]"
 	: "=&r" (result)
-	: "r" (&v->counter)
+	: "r" (&v->counter), "Qo" (v->counter)
 	);
 
 	return result;
@@ -260,11 +260,11 @@ static inline void atomic64_set(atomic64_t *v, u64 i)
 	u64 tmp;
 
 	__asm__ __volatile__("@ atomic64_set\n"
-"1:	ldrexd	%0, %H0, [%1]\n"
-"	strexd	%0, %2, %H2, [%1]\n"
+"1:	ldrexd	%0, %H0, [%2]\n"
+"	strexd	%0, %3, %H3, [%2]\n"
 "	teq	%0, #0\n"
 "	bne	1b"
-	: "=&r" (tmp)
+	: "=&r" (tmp), "=Qo" (v->counter)
 	: "r" (&v->counter), "r" (i)
 	: "cc");
 }
@@ -275,13 +275,13 @@ static inline void atomic64_add(u64 i, atomic64_t *v)
 	unsigned long tmp;
 
 	__asm__ __volatile__("@ atomic64_add\n"
-"1:	ldrexd	%0, %H0, [%2]\n"
-"	adds	%0, %0, %3\n"
-"	adc	%H0, %H0, %H3\n"
-"	strexd	%1, %0, %H0, [%2]\n"
+"1:	ldrexd	%0, %H0, [%3]\n"
+"	adds	%0, %0, %4\n"
+"	adc	%H0, %H0, %H4\n"
+"	strexd	%1, %0, %H0, [%3]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
-	: "=&r" (result), "=&r" (tmp)
+	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
 	: "r" (&v->counter), "r" (i)
 	: "cc");
 }
@@ -294,13 +294,13 @@ static inline u64 atomic64_add_return(u64 i, atomic64_t *v)
 	smp_mb();
 
 	__asm__ __volatile__("@ atomic64_add_return\n"
-"1:	ldrexd	%0, %H0, [%2]\n"
-"	adds	%0, %0, %3\n"
-"	adc	%H0, %H0, %H3\n"
-"	strexd	%1, %0, %H0, [%2]\n"
+"1:	ldrexd	%0, %H0, [%3]\n"
+"	adds	%0, %0, %4\n"
+"	adc	%H0, %H0, %H4\n"
+"	strexd	%1, %0, %H0, [%3]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
-	: "=&r" (result), "=&r" (tmp)
+	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
 	: "r" (&v->counter), "r" (i)
 	: "cc");
 
@@ -315,13 +315,13 @@ static inline void atomic64_sub(u64 i, atomic64_t *v)
 	unsigned long tmp;
 
 	__asm__ __volatile__("@ atomic64_sub\n"
-"1:	ldrexd	%0, %H0, [%2]\n"
-"	subs	%0, %0, %3\n"
-"	sbc	%H0, %H0, %H3\n"
-"	strexd	%1, %0, %H0, [%2]\n"
+"1:	ldrexd	%0, %H0, [%3]\n"
+"	subs	%0, %0, %4\n"
+"	sbc	%H0, %H0, %H4\n"
+"	strexd	%1, %0, %H0, [%3]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
-	: "=&r" (result), "=&r" (tmp)
+	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
 	: "r" (&v->counter), "r" (i)
 	: "cc");
 }
@@ -334,13 +334,13 @@ static inline u64 atomic64_sub_return(u64 i, atomic64_t *v)
 	smp_mb();
 
 	__asm__ __volatile__("@ atomic64_sub_return\n"
-"1:	ldrexd	%0, %H0, [%2]\n"
-"	subs	%0, %0, %3\n"
-"	sbc	%H0, %H0, %H3\n"
-"	strexd	%1, %0, %H0, [%2]\n"
+"1:	ldrexd	%0, %H0, [%3]\n"
+"	subs	%0, %0, %4\n"
+"	sbc	%H0, %H0, %H4\n"
+"	strexd	%1, %0, %H0, [%3]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
-	: "=&r" (result), "=&r" (tmp)
+	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
 	: "r" (&v->counter), "r" (i)
 	: "cc");
 
@@ -358,12 +358,12 @@ static inline u64 atomic64_cmpxchg(atomic64_t *ptr, u64 old, u64 new)
 
 	do {
 		__asm__ __volatile__("@ atomic64_cmpxchg\n"
-		"ldrexd		%1, %H1, [%2]\n"
+		"ldrexd		%1, %H1, [%3]\n"
 		"mov		%0, #0\n"
-		"teq		%1, %3\n"
-		"teqeq		%H1, %H3\n"
-		"strexdeq	%0, %4, %H4, [%2]"
-		: "=&r" (res), "=&r" (oldval)
+		"teq		%1, %4\n"
+		"teqeq		%H1, %H4\n"
+		"strexdeq	%0, %5, %H5, [%3]"
+		: "=&r" (res), "=&r" (oldval), "+Qo" (ptr->counter)
 		: "r" (&ptr->counter), "r" (old), "r" (new)
 		: "cc");
 	} while (res);
@@ -381,11 +381,11 @@ static inline u64 atomic64_xchg(atomic64_t *ptr, u64 new)
 	smp_mb();
 
 	__asm__ __volatile__("@ atomic64_xchg\n"
-"1:	ldrexd	%0, %H0, [%2]\n"
-"	strexd	%1, %3, %H3, [%2]\n"
+"1:	ldrexd	%0, %H0, [%3]\n"
+"	strexd	%1, %4, %H4, [%3]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
-	: "=&r" (result), "=&r" (tmp)
+	: "=&r" (result), "=&r" (tmp), "+Qo" (ptr->counter)
 	: "r" (&ptr->counter), "r" (new)
 	: "cc");
 
@@ -402,16 +402,16 @@ static inline u64 atomic64_dec_if_positive(atomic64_t *v)
 	smp_mb();
 
 	__asm__ __volatile__("@ atomic64_dec_if_positive\n"
-"1:	ldrexd	%0, %H0, [%2]\n"
+"1:	ldrexd	%0, %H0, [%3]\n"
 "	subs	%0, %0, #1\n"
 "	sbc	%H0, %H0, #0\n"
 "	teq	%H0, #0\n"
 "	bmi	2f\n"
-"	strexd	%1, %0, %H0, [%2]\n"
+"	strexd	%1, %0, %H0, [%3]\n"
 "	teq	%1, #0\n"
 "	bne	1b\n"
 "2:"
-	: "=&r" (result), "=&r" (tmp)
+	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
 	: "r" (&v->counter)
 	: "cc");
 
@@ -429,18 +429,18 @@ static inline int atomic64_add_unless(atomic64_t *v, u64 a, u64 u)
 	smp_mb();
 
 	__asm__ __volatile__("@ atomic64_add_unless\n"
-"1:	ldrexd	%0, %H0, [%3]\n"
-"	teq	%0, %4\n"
-"	teqeq	%H0, %H4\n"
+"1:	ldrexd	%0, %H0, [%4]\n"
+"	teq	%0, %5\n"
+"	teqeq	%H0, %H5\n"
 "	moveq	%1, #0\n"
 "	beq	2f\n"
-"	adds	%0, %0, %5\n"
-"	adc	%H0, %H0, %H5\n"
-"	strexd	%2, %0, %H0, [%3]\n"
+"	adds	%0, %0, %6\n"
+"	adc	%H0, %H0, %H6\n"
+"	strexd	%2, %0, %H0, [%4]\n"
 "	teq	%2, #0\n"
 "	bne	1b\n"
 "2:"
-	: "=&r" (val), "=&r" (ret), "=&r" (tmp)
+	: "=&r" (val), "+r" (ret), "=&r" (tmp), "+Qo" (v->counter)
 	: "r" (&v->counter), "r" (u), "r" (a)
 	: "cc");
 
diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h
index c980156f3263..1261b1f928d9 100644
--- a/arch/arm/include/asm/io.h
+++ b/arch/arm/include/asm/io.h
@@ -26,6 +26,7 @@
 #include <linux/types.h>
 #include <asm/byteorder.h>
 #include <asm/memory.h>
+#include <asm/system.h>
 
 /*
  * ISA I/O bus memory addresses are 1:1 with the physical address.
@@ -179,25 +180,38 @@ extern void _memset_io(volatile void __iomem *, int, size_t);
  * IO port primitives for more information.
  */
 #ifdef __mem_pci
-#define readb(c) ({ __u8  __v = __raw_readb(__mem_pci(c)); __v; })
-#define readw(c) ({ __u16 __v = le16_to_cpu((__force __le16) \
+#define readb_relaxed(c) ({ u8  __v = __raw_readb(__mem_pci(c)); __v; })
+#define readw_relaxed(c) ({ u16 __v = le16_to_cpu((__force __le16) \
 					__raw_readw(__mem_pci(c))); __v; })
-#define readl(c) ({ __u32 __v = le32_to_cpu((__force __le32) \
+#define readl_relaxed(c) ({ u32 __v = le32_to_cpu((__force __le32) \
 					__raw_readl(__mem_pci(c))); __v; })
-#define readb_relaxed(addr) readb(addr)
-#define readw_relaxed(addr) readw(addr)
-#define readl_relaxed(addr) readl(addr)
+
+#define writeb_relaxed(v,c)	((void)__raw_writeb(v,__mem_pci(c)))
+#define writew_relaxed(v,c)	((void)__raw_writew((__force u16) \
+					cpu_to_le16(v),__mem_pci(c)))
+#define writel_relaxed(v,c)	((void)__raw_writel((__force u32) \
+					cpu_to_le32(v),__mem_pci(c)))
+
+#ifdef CONFIG_ARM_DMA_MEM_BUFFERABLE
+#define __iormb()		rmb()
+#define __iowmb()		wmb()
+#else
+#define __iormb()		do { } while (0)
+#define __iowmb()		do { } while (0)
+#endif
+
+#define readb(c)		({ u8  __v = readb_relaxed(c); __iormb(); __v; })
+#define readw(c)		({ u16 __v = readw_relaxed(c); __iormb(); __v; })
+#define readl(c)		({ u32 __v = readl_relaxed(c); __iormb(); __v; })
+
+#define writeb(v,c)		({ __iowmb(); writeb_relaxed(v,c); })
+#define writew(v,c)		({ __iowmb(); writew_relaxed(v,c); })
+#define writel(v,c)		({ __iowmb(); writel_relaxed(v,c); })
 
 #define readsb(p,d,l)		__raw_readsb(__mem_pci(p),d,l)
 #define readsw(p,d,l)		__raw_readsw(__mem_pci(p),d,l)
 #define readsl(p,d,l)		__raw_readsl(__mem_pci(p),d,l)
 
-#define writeb(v,c)		__raw_writeb(v,__mem_pci(c))
-#define writew(v,c)		__raw_writew((__force __u16) \
-					cpu_to_le16(v),__mem_pci(c))
-#define writel(v,c)		__raw_writel((__force __u32) \
-					cpu_to_le32(v),__mem_pci(c))
-
 #define writesb(p,d,l)		__raw_writesb(__mem_pci(p),d,l)
 #define writesw(p,d,l)		__raw_writesw(__mem_pci(p),d,l)
 #define writesl(p,d,l)		__raw_writesl(__mem_pci(p),d,l)
@@ -244,13 +258,13 @@ extern void _memset_io(volatile void __iomem *, int, size_t);
  * io{read,write}{8,16,32} macros
  */
 #ifndef ioread8
-#define ioread8(p)	({ unsigned int __v = __raw_readb(p); __v; })
-#define ioread16(p)	({ unsigned int __v = le16_to_cpu((__force __le16)__raw_readw(p)); __v; })
-#define ioread32(p)	({ unsigned int __v = le32_to_cpu((__force __le32)__raw_readl(p)); __v; })
+#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 iowrite8(v,p)	__raw_writeb(v, p)
-#define iowrite16(v,p)	__raw_writew((__force __u16)cpu_to_le16(v), p)
-#define iowrite32(v,p)	__raw_writel((__force __u32)cpu_to_le32(v), p)
+#define iowrite8(v,p)	({ __iowmb(); (void)__raw_writeb(v, p); })
+#define iowrite16(v,p)	({ __iowmb(); (void)__raw_writew((__force __u16)cpu_to_le16(v), p); })
+#define iowrite32(v,p)	({ __iowmb(); (void)__raw_writel((__force __u32)cpu_to_le32(v), p); })
 
 #define ioread8_rep(p,d,c)	__raw_readsb(p,d,c)
 #define ioread16_rep(p,d,c)	__raw_readsw(p,d,c)
diff --git a/arch/arm/include/asm/mach/udc_pxa2xx.h b/arch/arm/include/asm/mach/udc_pxa2xx.h
index f3eabf1ecec3..833306ee9e7f 100644
--- a/arch/arm/include/asm/mach/udc_pxa2xx.h
+++ b/arch/arm/include/asm/mach/udc_pxa2xx.h
@@ -21,8 +21,8 @@ struct pxa2xx_udc_mach_info {
 	 * here.  Note that sometimes the signals go through inverters...
 	 */
 	bool	gpio_vbus_inverted;
-	u16	gpio_vbus;			/* high == vbus present */
+	int	gpio_vbus;			/* high == vbus present */
 	bool	gpio_pullup_inverted;
-	u16	gpio_pullup;			/* high == pullup activated */
+	int	gpio_pullup;			/* high == pullup activated */
 };
 
diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h
index 6a89567ffc5b..7bed3daf83b8 100644
--- a/arch/arm/include/asm/processor.h
+++ b/arch/arm/include/asm/processor.h
@@ -91,7 +91,11 @@ extern void release_thread(struct task_struct *);
 
 unsigned long get_wchan(struct task_struct *p);
 
+#if __LINUX_ARM_ARCH__ == 6
+#define cpu_relax()			smp_mb()
+#else
 #define cpu_relax()			barrier()
+#endif
 
 /*
  * Create a new kernel thread