Merge branch 'irq/numa' into x86/mce3

Merge reason: arch/x86/kernel/irqinit_{32,64}.c unified in irq/numa
and modified in x86/mce3; this merge resolves the conflict.

Conflicts:
	arch/x86/kernel/irqinit.c

Signed-off-by: H. Peter Anvin <hpa@zytor.com>

95 files changed, 1521 insertions, 1218 deletions

diff --git a/arch/alpha/kernel/sys_dp264.c b/arch/alpha/kernel/sys_dp264.c
index 9c9d1fd4155..5bd5259324b 100644
--- a/arch/alpha/kernel/sys_dp264.c
+++ b/arch/alpha/kernel/sys_dp264.c
@@ -176,22 +176,26 @@ cpu_set_irq_affinity(unsigned int irq, cpumask_t affinity)
 	}
 }
 
-static void
+static int
 dp264_set_affinity(unsigned int irq, const struct cpumask *affinity)
 { 
 	spin_lock(&dp264_irq_lock);
 	cpu_set_irq_affinity(irq, *affinity);
 	tsunami_update_irq_hw(cached_irq_mask);
 	spin_unlock(&dp264_irq_lock);
+
+	return 0;
 }
 
-static void
+static int
 clipper_set_affinity(unsigned int irq, const struct cpumask *affinity)
 { 
 	spin_lock(&dp264_irq_lock);
 	cpu_set_irq_affinity(irq - 16, *affinity);
 	tsunami_update_irq_hw(cached_irq_mask);
 	spin_unlock(&dp264_irq_lock);
+
+	return 0;
 }
 
 static struct hw_interrupt_type dp264_irq_type = {
diff --git a/arch/alpha/kernel/sys_titan.c b/arch/alpha/kernel/sys_titan.c
index 27f840a4ad3..8dd239ebdb9 100644
--- a/arch/alpha/kernel/sys_titan.c
+++ b/arch/alpha/kernel/sys_titan.c
@@ -157,13 +157,15 @@ titan_cpu_set_irq_affinity(unsigned int irq, cpumask_t affinity)
 
 }
 
-static void
+static int
 titan_set_irq_affinity(unsigned int irq, const struct cpumask *affinity)
 { 
 	spin_lock(&titan_irq_lock);
 	titan_cpu_set_irq_affinity(irq - 16, *affinity);
 	titan_update_irq_hw(titan_cached_irq_mask);
 	spin_unlock(&titan_irq_lock);
+
+	return 0;
 }
 
 static void
diff --git a/arch/arm/common/gic.c b/arch/arm/common/gic.c
index 3e1714c6523..664c7b8b1ba 100644
--- a/arch/arm/common/gic.c
+++ b/arch/arm/common/gic.c
@@ -109,7 +109,7 @@ static void gic_unmask_irq(unsigned int irq)
 }
 
 #ifdef CONFIG_SMP
-static void gic_set_cpu(unsigned int irq, const struct cpumask *mask_val)
+static int gic_set_cpu(unsigned int irq, const struct cpumask *mask_val)
 {
 	void __iomem *reg = gic_dist_base(irq) + GIC_DIST_TARGET + (gic_irq(irq) & ~3);
 	unsigned int shift = (irq % 4) * 8;
@@ -122,6 +122,8 @@ static void gic_set_cpu(unsigned int irq, const struct cpumask *mask_val)
 	val |= 1 << (cpu + shift);
 	writel(val, reg);
 	spin_unlock(&irq_controller_lock);
+
+	return 0;
 }
 #endif
 
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 6116e4893c0..15f8a092b70 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -114,3 +114,16 @@
 	.align	3;				\
 	.long	9999b,9001f;			\
 	.previous
+
+/*
+ * SMP data memory barrier
+ */
+	.macro	smp_dmb
+#ifdef CONFIG_SMP
+#if __LINUX_ARM_ARCH__ >= 7
+	dmb
+#elif __LINUX_ARM_ARCH__ == 6
+	mcr	p15, 0, r0, c7, c10, 5	@ dmb
+#endif
+#endif
+	.endm
diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h
index ee99723b3a6..16b52f39798 100644
--- a/arch/arm/include/asm/atomic.h
+++ b/arch/arm/include/asm/atomic.h
@@ -44,11 +44,29 @@ static inline void atomic_set(atomic_t *v, int i)
 	: "cc");
 }
 
+static inline void atomic_add(int i, atomic_t *v)
+{
+	unsigned long tmp;
+	int result;
+
+	__asm__ __volatile__("@ atomic_add\n"
+"1:	ldrex	%0, [%2]\n"
+"	add	%0, %0, %3\n"
+"	strex	%1, %0, [%2]\n"
+"	teq	%1, #0\n"
+"	bne	1b"
+	: "=&r" (result), "=&r" (tmp)
+	: "r" (&v->counter), "Ir" (i)
+	: "cc");
+}
+
 static inline int atomic_add_return(int i, atomic_t *v)
 {
 	unsigned long tmp;
 	int result;
 
+	smp_mb();
+
 	__asm__ __volatile__("@ atomic_add_return\n"
 "1:	ldrex	%0, [%2]\n"
 "	add	%0, %0, %3\n"
@@ -59,14 +77,34 @@ static inline int atomic_add_return(int i, atomic_t *v)
 	: "r" (&v->counter), "Ir" (i)
 	: "cc");
 
+	smp_mb();
+
 	return result;
 }
 
+static inline void atomic_sub(int i, atomic_t *v)
+{
+	unsigned long tmp;
+	int result;
+
+	__asm__ __volatile__("@ atomic_sub\n"
+"1:	ldrex	%0, [%2]\n"
+"	sub	%0, %0, %3\n"
+"	strex	%1, %0, [%2]\n"
+"	teq	%1, #0\n"
+"	bne	1b"
+	: "=&r" (result), "=&r" (tmp)
+	: "r" (&v->counter), "Ir" (i)
+	: "cc");
+}
+
 static inline int atomic_sub_return(int i, atomic_t *v)
 {
 	unsigned long tmp;
 	int result;
 
+	smp_mb();
+
 	__asm__ __volatile__("@ atomic_sub_return\n"
 "1:	ldrex	%0, [%2]\n"
 "	sub	%0, %0, %3\n"
@@ -77,6 +115,8 @@ static inline int atomic_sub_return(int i, atomic_t *v)
 	: "r" (&v->counter), "Ir" (i)
 	: "cc");
 
+	smp_mb();
+
 	return result;
 }
 
@@ -84,6 +124,8 @@ static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
 {
 	unsigned long oldval, res;
 
+	smp_mb();
+
 	do {
 		__asm__ __volatile__("@ atomic_cmpxchg\n"
 		"ldrex	%1, [%2]\n"
@@ -95,6 +137,8 @@ static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
 		    : "cc");
 	} while (res);
 
+	smp_mb();
+
 	return oldval;
 }
 
@@ -135,6 +179,7 @@ static inline int atomic_add_return(int i, atomic_t *v)
 
 	return val;
 }
+#define atomic_add(i, v)	(void) atomic_add_return(i, v)
 
 static inline int atomic_sub_return(int i, atomic_t *v)
 {
@@ -148,6 +193,7 @@ static inline int atomic_sub_return(int i, atomic_t *v)
 
 	return val;
 }
+#define atomic_sub(i, v)	(void) atomic_sub_return(i, v)
 
 static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 {
@@ -187,10 +233,8 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u)
 }
 #define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
 
-#define atomic_add(i, v)	(void) atomic_add_return(i, v)
-#define atomic_inc(v)		(void) atomic_add_return(1, v)
-#define atomic_sub(i, v)	(void) atomic_sub_return(i, v)
-#define atomic_dec(v)		(void) atomic_sub_return(1, v)
+#define atomic_inc(v)		atomic_add(1, v)
+#define atomic_dec(v)		atomic_sub(1, v)
 
 #define atomic_inc_and_test(v)	(atomic_add_return(1, v) == 0)
 #define atomic_dec_and_test(v)	(atomic_sub_return(1, v) == 0)
@@ -200,11 +244,10 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u)
 
 #define atomic_add_negative(i,v) (atomic_add_return(i, v) < 0)
 
-/* Atomic operations are already serializing on ARM */
-#define smp_mb__before_atomic_dec()	barrier()
-#define smp_mb__after_atomic_dec()	barrier()
-#define smp_mb__before_atomic_inc()	barrier()
-#define smp_mb__after_atomic_inc()	barrier()
+#define smp_mb__before_atomic_dec()	smp_mb()
+#define smp_mb__after_atomic_dec()	smp_mb()
+#define smp_mb__before_atomic_inc()	smp_mb()
+#define smp_mb__after_atomic_inc()	smp_mb()
 
 #include <asm-generic/atomic.h>
 #endif
diff --git a/arch/arm/include/asm/flat.h b/arch/arm/include/asm/flat.h
index 1d77e51907f..59426a4595c 100644
--- a/arch/arm/include/asm/flat.h
+++ b/arch/arm/include/asm/flat.h
@@ -5,9 +5,6 @@
 #ifndef __ARM_FLAT_H__
 #define __ARM_FLAT_H__
 
-/* An odd number of words will be pushed after this alignment, so
-   deliberately misalign the value.  */
-#define	flat_stack_align(sp)	sp = (void *)(((unsigned long)(sp) - 4) | 4)
 #define	flat_argvp_envp_on_stack()		1
 #define	flat_old_ram_flag(flags)		(flags)
 #define	flat_reloc_valid(reloc, size)		((reloc) <= (size))
diff --git a/arch/arm/include/asm/system.h b/arch/arm/include/asm/system.h
index bd4dc8ed53d..d65b2f5bf41 100644
--- a/arch/arm/include/asm/system.h
+++ b/arch/arm/include/asm/system.h
@@ -248,6 +248,8 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
 	unsigned int tmp;
 #endif
 
+	smp_mb();
+
 	switch (size) {
 #if __LINUX_ARM_ARCH__ >= 6
 	case 1:
@@ -307,6 +309,7 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
 		__bad_xchg(ptr, size), ret = 0;
 		break;
 	}
+	smp_mb();
 
 	return ret;
 }
@@ -316,6 +319,12 @@ extern void enable_hlt(void);
 
 #include <asm-generic/cmpxchg-local.h>
 
+#if __LINUX_ARM_ARCH__ < 6
+
+#ifdef CONFIG_SMP
+#error "SMP is not supported on this platform"
+#endif
+
 /*
  * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make
  * them available.
@@ -329,6 +338,173 @@ extern void enable_hlt(void);
 #include <asm-generic/cmpxchg.h>
 #endif
 
+#else	/* __LINUX_ARM_ARCH__ >= 6 */
+
+extern void __bad_cmpxchg(volatile void *ptr, int size);
+
+/*
+ * cmpxchg only support 32-bits operands on ARMv6.
+ */
+
+static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
+				      unsigned long new, int size)
+{
+	unsigned long oldval, res;
+
+	switch (size) {
+#ifdef CONFIG_CPU_32v6K
+	case 1:
+		do {
+			asm volatile("@ __cmpxchg1\n"
+			"	ldrexb	%1, [%2]\n"
+			"	mov	%0, #0\n"
+			"	teq	%1, %3\n"
+			"	strexbeq %0, %4, [%2]\n"
+				: "=&r" (res), "=&r" (oldval)
+				: "r" (ptr), "Ir" (old), "r" (new)
+				: "memory", "cc");
+		} while (res);
+		break;
+	case 2:
+		do {
+			asm volatile("@ __cmpxchg1\n"
+			"	ldrexh	%1, [%2]\n"
+			"	mov	%0, #0\n"
+			"	teq	%1, %3\n"
+			"	strexheq %0, %4, [%2]\n"
+				: "=&r" (res), "=&r" (oldval)
+				: "r" (ptr), "Ir" (old), "r" (new)
+				: "memory", "cc");
+		} while (res);
+		break;
+#endif /* CONFIG_CPU_32v6K */
+	case 4:
+		do {
+			asm volatile("@ __cmpxchg4\n"
+			"	ldrex	%1, [%2]\n"
+			"	mov	%0, #0\n"
+			"	teq	%1, %3\n"
+			"	strexeq %0, %4, [%2]\n"
+				: "=&r" (res), "=&r" (oldval)
+				: "r" (ptr), "Ir" (old), "r" (new)
+				: "memory", "cc");
+		} while (res);
+		break;
+	default:
+		__bad_cmpxchg(ptr, size);
+		oldval = 0;
+	}
+
+	return oldval;
+}
+
+static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old,
+					 unsigned long new, int size)
+{
+	unsigned long ret;
+
+	smp_mb();
+	ret