Merge branch 'linus' into irq/numa

Conflicts:
	arch/mips/sibyte/bcm1480/irq.c
	arch/mips/sibyte/sb1250/irq.c

Merge reason: we gathered a few conflicts plus update to latest upstream fixes.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

60 files changed, 636 insertions, 202 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index e60ec54df33..9d02cdb15b2 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -273,6 +273,7 @@ config ARCH_EP93XX
 	select HAVE_CLK
 	select COMMON_CLKDEV
 	select ARCH_REQUIRE_GPIOLIB
+	select ARCH_HAS_HOLES_MEMORYMODEL
 	help
 	  This enables support for the Cirrus EP93xx series of CPUs.
 
@@ -976,10 +977,9 @@ config OABI_COMPAT
 	  UNPREDICTABLE (in fact it can be predicted that it won't work
 	  at all). If in doubt say Y.
 
-config ARCH_FLATMEM_HAS_HOLES
+config ARCH_HAS_HOLES_MEMORYMODEL
 	bool
-	default y
-	depends on FLATMEM
+	default n
 
 # Discontigmem is deprecated
 config ARCH_DISCONTIGMEM_ENABLE
diff --git a/arch/arm/common/gic.c b/arch/arm/common/gic.c
index 90f6b7f52d4..664c7b8b1ba 100644
--- a/arch/arm/common/gic.c
+++ b/arch/arm/common/gic.c
@@ -255,9 +255,9 @@ void __cpuinit gic_cpu_init(unsigned int gic_nr, void __iomem *base)
 }
 
 #ifdef CONFIG_SMP
-void gic_raise_softirq(cpumask_t cpumask, unsigned int irq)
+void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
 {
-	unsigned long map = *cpus_addr(cpumask);
+	unsigned long map = *cpus_addr(*mask);
 
 	/* this always happens on GIC0 */
 	writel(map << 16 | irq, gic_data[0].dist_base + GIC_DIST_SOFTINT);
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/hardware/gic.h b/arch/arm/include/asm/hardware/gic.h
index 4924914af18..7f34333bb54 100644
--- a/arch/arm/include/asm/hardware/gic.h
+++ b/arch/arm/include/asm/hardware/gic.h
@@ -36,7 +36,7 @@
 void gic_dist_init(unsigned int gic_nr, void __iomem *base, unsigned int irq_start);
 void gic_cpu_init(unsigned int gic_nr, void __iomem *base);
 void gic_cascade_irq(unsigned int gic_nr, unsigned int irq);
-void gic_raise_softirq(cpumask_t cpumask, unsigned int irq);
+void gic_raise_softirq(const struct cpumask *mask, unsigned int irq);
 #endif
 
 #endif
diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h
index fad70da5911..5995935338e 100644
--- a/arch/arm/include/asm/smp.h
+++ b/arch/arm/include/asm/smp.h
@@ -53,17 +53,12 @@ extern void smp_store_cpu_info(unsigned int cpuid);
 /*
  * Raise an IPI cross call on CPUs in callmap.
  */
-extern void smp_cross_call(cpumask_t callmap);
-
-/*
- * Broadcast a timer interrupt to the other CPUs.
- */
-extern void smp_send_timer(void);
+extern void smp_cross_call(const struct cpumask *mask);
 
 /*
  * Broadcast a clock event to other CPUs.
  */
-extern void smp_timer_broadcast(cpumask_t mask);
+extern void smp_timer_broadcast(const struct cpumask *mask);
 
 /*
  * Boot a secondary CPU, and assign it the specified idle task.
@@ -102,7 +97,8 @@ extern int platform_cpu_kill(unsigned int cpu);
 extern void platform_cpu_enable(unsigned int cpu);
 
 extern void arch_send_call_function_single_ipi(int cpu);
-extern void arch_send_call_function_ipi(cpumask_t mask);
+extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
+#define arch_send_call_function_ipi_mask arch_send_call_function_ipi_mask
 
 /*
  * Local timer interrupt handling function (can be IPI'ed).
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 = __cmpxchg(ptr, old, new, size);
+	smp_mb();
+
+	return ret;
+}
+
+#define cmpxchg(ptr,o,n)						\
+	((__typeof__(*(ptr)))__cmpxchg_mb((ptr),			\
+					  (unsigned long)(o),		\
+					  (unsigned long)(n),		\
+					  sizeof(*(ptr))))
+
+static inline unsigned long __cmpxchg_local(volatile void *ptr,
+					    unsigned long old,
+					    unsigned long new, int size)
+{
+	unsigned long ret;
+
+	switch (size) {
+#ifndef CONFIG_CPU_32v6K
+	case 1:
+	case 2:
+		ret = __cmpxchg_local_generic(ptr, old, new, size);
+		break;
+#endif	/* !CONFIG_CPU_32v6K */
+	default:
+		ret = __cmpxchg(ptr, old, new, size);
+	}
+
+	return ret;
+}
+
+#define cmpxchg_local(ptr,o,n)						\
+	((__typeof__(*(ptr)))__cmpxchg_local((ptr),			\
+				       (unsigned long)(o),		\
+				       (unsigned long)(n),		\
+				       sizeof(*(ptr))))
+
+#ifdef CONFIG_CPU_32v6K
+
+/*
+ * Note : ARMv7-M (currently unsupported by Linux) does not support
+ * ldrexd/strexd. If ARMv7-M is ever supported by the Linux kernel, it should
+ * not be allowed to use __cmpxchg64.
+ */
+static inline unsigned long long __cmpxchg64(volatile void *ptr,
+					     unsigned long long old,
+					     unsigned long long new)
+{
+	register unsigned long long oldval asm("r0");
+	register unsigned long long __old asm("r2") = old;
+	register unsigned long long __new asm("r4") = new;
+	unsigned long res;
+
+	do {
+		asm volatile(
+		"	@ __cmpxchg8\n"
+		"	ldrexd	%1, %H1, [%2]\n"
+		"	mov	%0, #0\n"
+		"	teq	%1, %3\n"
+		"	teqeq	%H1, %H3\n"
+		"	strexdeq %0, %4, %H4, [%2]\n"
+			: "=&r" (res), "=&r" (oldval)
+			: "r" (ptr), "Ir" (__old), "r" (__new)
+			: "memory", "cc");
+	} while (res);
+
+	return oldval;
+}
+
+static inline unsigned long long __cmpxchg64_mb(volatile void *ptr,
+						unsigned long long old,
+						unsigned long long new)
+{
+	unsigned long long ret;
+
+	smp_mb();
+	ret = __cmpxchg64(ptr, old, new);
+	smp_mb();
+
+	return ret;
+}
+
+#define cmpxchg64(ptr,o,n)						\
+	((__typeof__(*(ptr)))__cmpxchg64_mb((ptr),			\
+					    (unsigned long long)(o),	\
+					    (unsigned long long)(n)))
+
+#define cmpxchg64_local(ptr,o,n)					\
+	((__typeof__(*(ptr)))__cmpxchg64((ptr),				\
+					 (unsigned long long)(o),	\
+					 (unsigned long long)(n)))
+
+#else	/* !CONFIG_CPU_32v6K */
+
+#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
+
+#endif	/* CONFIG_CPU_32v6K */
+
+#endif	/* __LINUX_ARM_ARCH__ >= 6 */
+
 #endif /* __ASSEMBLY__ */
 
 #define arch_align_stack(x) (x)
diff --git a/arch/arm/kernel/elf.c b/arch/arm/kernel/elf.c
index d4a0da1e48f..950391f194c 100644
--- a/arch/arm/kernel/elf.c
+++ b/arch/arm/kernel/elf.c
@@ -78,6 +78,15 @@ int arm_elf_read_implies_exec(const struct elf32_hdr *x, int executable_stack)
 		return 1;
 	if (cpu_architecture() < CPU_ARCH_ARMv6)
 		return 1;
+#if !defined(CONFIG_AEABI) || defined(CONFIG_OABI_COMPAT)
+	/*
+	 * If we have support for OABI programs, we can never allow NX
+	 * support - our signal syscall restart mechanism relies upon
+	 * being able to execute code placed on the user stack.
+	 */
+	return 1;
+#else
 	return 0;
+#endif
 }
 EXPORT_SYMBOL(arm_elf_read_implies_exec);
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index d662a2f1fd8..83b1da6b7ba 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -815,10 +815,7 @@ __kuser_helper_start:
  */
 
 __kuser_memory_barrier:				@ 0xffff0fa0
-
-#if __LINUX_ARM_ARCH__ >= 6 && defined(CONFIG_SMP)
-	mcr	p15, 0, r0, c7, c10, 5	@ dmb
-#endif
+	smp_dmb
 	usr_ret	lr
 
 	.align	5
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 7801aac3c04..6014dfd22af 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -326,14 +326,14 @@ void __init smp_prepare_boot_cpu(void)
 	per_cpu(cpu_data, cpu).idle = current;
 }
 
-static void send_ipi_message(cpumask_t callmap, enum ipi_msg_type msg)
+static void send_ipi_message(const struct cpumask *mask, enum ipi_msg_type msg)
 {
 	unsigned long flags;
 	unsigned int cpu;
 
 	local_irq_save(flags);
 
-	for_each_cpu_mask(cpu, callmap) {
+	for_each_cpu(cpu, mask) {
 		struct ipi_data *ipi = &per_cpu(ipi_data, cpu);
 
 		spin_lock(&ipi->lock);
@@ -344,19 +344,19 @@ static void send_ipi_message(cpumask_t callmap, enum ipi_msg_type msg)
 	/*
 	 * Call the platform specific cross-CPU call function.
 	 */
-	smp_cross_call(callmap);
+	smp_cross_call(mask);
 
 	local_irq_restore(flags);
 }
 
-void arch_send_call_function_ipi(cpumask_t mask)
+void arch_send_call_function_ipi_mask(const struct cpumask *mask)
 {
 	send_ipi_message(mask, IPI_CALL_FUNC);
 }
 
 void arch_send_call_function_single_ipi(int cpu)
 {
-	send_ipi_message(cpumask_of_cpu(cpu), IPI_CALL_FUNC_SINGLE);
+	send_ipi_message(cpumask_of(cpu), IPI_CALL_FUNC_SINGLE);
 }
 
 void show_ipi_list(struct seq_file *p)
@@ -498,17 +498,10 @@ asmlinkage void __exception do_IPI(struct pt_regs *regs)
 
 void smp_send_reschedule(int cpu)
 {
-	send_ipi_message(cpumask_of_cpu(cpu), IPI_RESCHEDULE);
+	send_ipi_message(cpumask_of(cpu), IPI_RESCHEDULE);
 }
 
-void smp_send_timer(void)
-{
-	cpumask_t mask = cpu_online_map;
-	cpu_clear(smp_processor_id(), mask);
-	send_ipi_message(mask, IPI_TIMER);
-}
-
-void smp_timer_broadcast(cpumask_t mask)
+void smp_timer_broadcast(const struct cpumask *mask)
 {
 	send_ipi_message(mask, IPI_TIMER);
 }
@@ -517,7 +510,7 @@ void smp_send_stop(void)
 {
 	cpumask_t mask = cpu_online_map;
 	cpu_clear(smp_processor_id(), mask);
-	send_ipi_message(mask, IPI_CPU_STOP);
+	send_ipi_message(&mask, IPI_CPU_STOP);
 }
 
 /*
@@ -528,20 +521,17 @@ int setup_profiling_timer(unsigned int multiplier)
 	return -EINVAL;
 }
 
-static int
-on_each_cpu_mask(void (*func)(void *), void *info, int wait, cpumask_t mask)
+static void
+on_each_cpu_mask(void (*func)(void *), void *info, int wait,
+		const struct cpumask *mask)
 {
-	int ret = 0;
-
 	preempt_disable();
 
-	ret = smp_call_function_mask(mask, func, info, wait);
-	if (cpu_isset(smp_processor_id(), mask))
+	smp_call_function_many(mask, func, info, wait);
+	if (cpumask_test_cpu(smp_processor_id(), mask))
 		func(info);
 
 	preempt_enable();
-
-	return ret;
 }
 
 /**********************************************************************/
@@ -602,20 +592,17 @@ void flush_tlb_all(void)
 
 void flush_tlb_mm(struct mm_struct *mm)
 {
-	cpumask_t mask = mm->cpu_vm_mask;
-
-	on_each_cpu_mask(ipi_flush_tlb_mm, mm, 1, mask);
+	on_each_cpu_mask(ipi_flush_tlb_mm, mm, 1, &mm->cpu_vm_mask);
 }
 
 void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
 {
-	cpumask_t mask = vma->vm_mm->cpu_vm_mask;
 	struct tlb_args ta;
 
 	ta.ta_vma = vma;
 	ta.ta_start = uaddr;
 
-	on_each_cpu_mask(ipi_flush_tlb_page, &ta, 1, mask);
+	on_each_cpu_mask(ipi_flush_tlb_page, &ta, 1, &vma->vm_mm->cpu_vm_mask);
 }
 
 void flush_tlb_kernel_page(unsigned long kaddr)
@@ -630,14 +617,13 @@ void flush_tlb_kernel_page(unsigned long kaddr)
 void flu