11 files changed, 294 insertions, 50 deletions

diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h
index d0daeab2234..e8ddec2cb15 100644
--- a/arch/arm/include/asm/atomic.h
+++ b/arch/arm/include/asm/atomic.h
@@ -235,6 +235,234 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u)
 #define smp_mb__before_atomic_inc()	smp_mb()
 #define smp_mb__after_atomic_inc()	smp_mb()
 
+#ifndef CONFIG_GENERIC_ATOMIC64
+typedef struct {
+	u64 __aligned(8) counter;
+} atomic64_t;
+
+#define ATOMIC64_INIT(i) { (i) }
+
+static inline u64 atomic64_read(atomic64_t *v)
+{
+	u64 result;
+
+	__asm__ __volatile__("@ atomic64_read\n"
+"	ldrexd	%0, %H0, [%1]"
+	: "=&r" (result)
+	: "r" (&v->counter)
+	);
+
+	return result;
+}
+
+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"
+"	teq	%0, #0\n"
+"	bne	1b"
+	: "=&r" (tmp)
+	: "r" (&v->counter), "r" (i)
+	: "cc");
+}
+
+static inline void atomic64_add(u64 i, atomic64_t *v)
+{
+	u64 result;
+	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"
+"	teq	%1, #0\n"
+"	bne	1b"
+	: "=&r" (result), "=&r" (tmp)
+	: "r" (&v->counter), "r" (i)
+	: "cc");
+}
+
+static inline u64 atomic64_add_return(u64 i, atomic64_t *v)
+{
+	u64 result;
+	unsigned long tmp;
+
+	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"
+"	teq	%1, #0\n"
+"	bne	1b"
+	: "=&r" (result), "=&r" (tmp)
+	: "r" (&v->counter), "r" (i)
+	: "cc");
+
+	smp_mb();
+
+	return result;
+}
+
+static inline void atomic64_sub(u64 i, atomic64_t *v)
+{
+	u64 result;
+	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"
+"	teq	%1, #0\n"
+"	bne	1b"
+	: "=&r" (result), "=&r" (tmp)
+	: "r" (&v->counter), "r" (i)
+	: "cc");
+}
+
+static inline u64 atomic64_sub_return(u64 i, atomic64_t *v)
+{
+	u64 result;
+	unsigned long tmp;
+
+	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"
+"	teq	%1, #0\n"
+"	bne	1b"
+	: "=&r" (result), "=&r" (tmp)
+	: "r" (&v->counter), "r" (i)
+	: "cc");
+
+	smp_mb();
+
+	return result;
+}
+
+static inline u64 atomic64_cmpxchg(atomic64_t *ptr, u64 old, u64 new)
+{
+	u64 oldval;
+	unsigned long res;
+
+	smp_mb();
+
+	do {
+		__asm__ __volatile__("@ atomic64_cmpxchg\n"
+		"ldrexd		%1, %H1, [%2]\n"
+		"mov		%0, #0\n"
+		"teq		%1, %3\n"
+		"teqeq		%H1, %H3\n"
+		"strexdeq	%0, %4, %H4, [%2]"
+		: "=&r" (res), "=&r" (oldval)
+		: "r" (&ptr->counter), "r" (old), "r" (new)
+		: "cc");
+	} while (res);
+
+	smp_mb();
+
+	return oldval;
+}
+
+static inline u64 atomic64_xchg(atomic64_t *ptr, u64 new)
+{
+	u64 result;
+	unsigned long tmp;
+
+	smp_mb();
+
+	__asm__ __volatile__("@ atomic64_xchg\n"
+"1:	ldrexd	%0, %H0, [%2]\n"
+"	strexd	%1, %3, %H3, [%2]\n"
+"	teq	%1, #0\n"
+"	bne	1b"
+	: "=&r" (result), "=&r" (tmp)
+	: "r" (&ptr->counter), "r" (new)
+	: "cc");
+
+	smp_mb();
+
+	return result;
+}
+
+static inline u64 atomic64_dec_if_positive(atomic64_t *v)
+{
+	u64 result;
+	unsigned long tmp;
+
+	smp_mb();
+
+	__asm__ __volatile__("@ atomic64_dec_if_positive\n"
+"1:	ldrexd	%0, %H0, [%2]\n"
+"	subs	%0, %0, #1\n"
+"	sbc	%H0, %H0, #0\n"
+"	teq	%H0, #0\n"
+"	bmi	2f\n"
+"	strexd	%1, %0, %H0, [%2]\n"
+"	teq	%1, #0\n"
+"	bne	1b\n"
+"2:"
+	: "=&r" (result), "=&r" (tmp)
+	: "r" (&v->counter)
+	: "cc");
+
+	smp_mb();
+
+	return result;
+}
+
+static inline int atomic64_add_unless(atomic64_t *v, u64 a, u64 u)
+{
+	u64 val;
+	unsigned long tmp;
+	int ret = 1;
+
+	smp_mb();
+
+	__asm__ __volatile__("@ atomic64_add_unless\n"
+"1:	ldrexd	%0, %H0, [%3]\n"
+"	teq	%0, %4\n"
+"	teqeq	%H0, %H4\n"
+"	moveq	%1, #0\n"
+"	beq	2f\n"
+"	adds	%0, %0, %5\n"
+"	adc	%H0, %H0, %H5\n"
+"	strexd	%2, %0, %H0, [%3]\n"
+"	teq	%2, #0\n"
+"	bne	1b\n"
+"2:"
+	: "=&r" (val), "=&r" (ret), "=&r" (tmp)
+	: "r" (&v->counter), "r" (u), "r" (a)
+	: "cc");
+
+	if (ret)
+		smp_mb();
+
+	return ret;
+}
+
+#define atomic64_add_negative(a, v)	(atomic64_add_return((a), (v)) < 0)
+#define atomic64_inc(v)			atomic64_add(1LL, (v))
+#define atomic64_inc_return(v)		atomic64_add_return(1LL, (v))
+#define atomic64_inc_and_test(v)	(atomic64_inc_return(v) == 0)
+#define atomic64_sub_and_test(a, v)	(atomic64_sub_return((a), (v)) == 0)
+#define atomic64_dec(v)			atomic64_sub(1LL, (v))
+#define atomic64_dec_return(v)		atomic64_sub_return(1LL, (v))
+#define atomic64_dec_and_test(v)	(atomic64_dec_return((v)) == 0)
+#define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1LL, 0LL)
+
+#else /* !CONFIG_GENERIC_ATOMIC64 */
+#include <asm-generic/atomic64.h>
+#endif
 #include <asm-generic/atomic-long.h>
 #endif
 #endif
diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h
index d2a59cfc30c..c980156f326 100644
--- a/arch/arm/include/asm/io.h
+++ b/arch/arm/include/asm/io.h
@@ -69,9 +69,16 @@ extern void __raw_readsl(const void __iomem *addr, void *data, int longlen);
 /*
  * __arm_ioremap takes CPU physical address.
  * __arm_ioremap_pfn takes a Page Frame Number and an offset into that page
+ * The _caller variety takes a __builtin_return_address(0) value for
+ * /proc/vmalloc to use - and should only be used in non-inline functions.
  */
-extern void __iomem * __arm_ioremap_pfn(unsigned long, unsigned long, size_t, unsigned int);
-extern void __iomem * __arm_ioremap(unsigned long, size_t, unsigned int);
+extern void __iomem *__arm_ioremap_pfn_caller(unsigned long, unsigned long,
+	size_t, unsigned int, void *);
+extern void __iomem *__arm_ioremap_caller(unsigned long, size_t, unsigned int,
+	void *);
+
+extern void __iomem *__arm_ioremap_pfn(unsigned long, unsigned long, size_t, unsigned int);
+extern void __iomem *__arm_ioremap(unsigned long, size_t, unsigned int);
 extern void __iounmap(volatile void __iomem *addr);
 
 /*
diff --git a/arch/arm/include/asm/mach/time.h b/arch/arm/include/asm/mach/time.h
index b2cc1fcd040..8bffc3ff3ac 100644
--- a/arch/arm/include/asm/mach/time.h
+++ b/arch/arm/include/asm/mach/time.h
@@ -46,12 +46,4 @@ struct sys_timer {
 extern struct sys_timer *system_timer;
 extern void timer_tick(void);
 
-/*
- * Kernel time keeping support.
- */
-struct timespec;
-extern int (*set_rtc)(void);
-extern void save_time_delta(struct timespec *delta, struct timespec *rtc);
-extern void restore_time_delta(struct timespec *delta, struct timespec *rtc);
-
 #endif
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index 5421d82a257..4312ee5e3d0 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -76,6 +76,17 @@
  */
 #define IOREMAP_MAX_ORDER	24
 
+/*
+ * Size of DMA-consistent memory region.  Must be multiple of 2M,
+ * between 2MB and 14MB inclusive.
+ */
+#ifndef CONSISTENT_DMA_SIZE
+#define CONSISTENT_DMA_SIZE 	SZ_2M
+#endif
+
+#define CONSISTENT_END		(0xffe00000UL)
+#define CONSISTENT_BASE		(CONSISTENT_END - CONSISTENT_DMA_SIZE)
+
 #else /* CONFIG_MMU */
 
 /*
@@ -93,11 +104,11 @@
 #endif
 
 #ifndef PHYS_OFFSET
-#define PHYS_OFFSET 		(CONFIG_DRAM_BASE)
+#define PHYS_OFFSET 		UL(CONFIG_DRAM_BASE)
 #endif
 
 #ifndef END_MEM
-#define END_MEM     		(CONFIG_DRAM_BASE + CONFIG_DRAM_SIZE)
+#define END_MEM     		(UL(CONFIG_DRAM_BASE) + CONFIG_DRAM_SIZE)
 #endif
 
 #ifndef PAGE_OFFSET
@@ -113,14 +124,6 @@
 #endif /* !CONFIG_MMU */
 
 /*
- * Size of DMA-consistent memory region.  Must be multiple of 2M,
- * between 2MB and 14MB inclusive.
- */
-#ifndef CONSISTENT_DMA_SIZE
-#define CONSISTENT_DMA_SIZE SZ_2M
-#endif
-
-/*
  * Physical vs virtual RAM address space conversion.  These are
  * private definitions which should NOT be used outside memory.h
  * files.  Use virt_to_phys/phys_to_virt/__pa/__va instead.
diff --git a/arch/arm/include/asm/mmu.h b/arch/arm/include/asm/mmu.h
index b561584d04a..68870c77667 100644
--- a/arch/arm/include/asm/mmu.h
+++ b/arch/arm/include/asm/mmu.h
@@ -6,6 +6,7 @@
 typedef struct {
 #ifdef CONFIG_CPU_HAS_ASID
 	unsigned int id;
+	spinlock_t id_lock;
 #endif
 	unsigned int kvm_seq;
 } mm_context_t;
diff --git a/arch/arm/include/asm/mmu_context.h b/arch/arm/include/asm/mmu_context.h
index de6cefb329d..a0b3cac0547 100644
--- a/arch/arm/include/asm/mmu_context.h
+++ b/arch/arm/include/asm/mmu_context.h
@@ -43,12 +43,23 @@ void __check_kvm_seq(struct mm_struct *mm);
 #define ASID_FIRST_VERSION	(1 << ASID_BITS)
 
 extern unsigned int cpu_last_asid;
+#ifdef CONFIG_SMP
+DECLARE_PER_CPU(struct mm_struct *, current_mm);
+#endif
 
 void __init_new_context(struct task_struct *tsk, struct mm_struct *mm);
 void __new_context(struct mm_struct *mm);
 
 static inline void check_context(struct mm_struct *mm)
 {
+	/*
+	 * This code is executed with interrupts enabled. Therefore,
+	 * mm->context.id cannot be updated to the latest ASID version
+	 * on a different CPU (and condition below not triggered)
+	 * without first getting an IPI to reset the context. The
+	 * alternative is to take a read_lock on mm->context.id_lock
+	 * (after changing its type to rwlock_t).
+	 */
 	if (unlikely((mm->context.id ^ cpu_last_asid) >> ASID_BITS))
 		__new_context(mm);
 
@@ -108,6 +119,10 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next,
 		__flush_icache_all();
 #endif
 	if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next)) || prev != next) {
+#ifdef CONFIG_SMP
+		struct mm_struct **crt_mm = &per_cpu(current_mm, cpu);
+		*crt_mm = next;
+#endif
 		check_context(next);
 		cpu_switch_mm(next->pgd, next);
 		if (cache_is_vivt())
diff --git a/arch/arm/include/asm/pgtable-nommu.h b/arch/arm/include/asm/pgtable-nommu.h
index b011f2e939a..013cfcdc483 100644
--- a/arch/arm/include/asm/pgtable-nommu.h
+++ b/arch/arm/include/asm/pgtable-nommu.h
@@ -86,8 +86,8 @@ extern unsigned int kobjsize(const void *objp);
  * All 32bit addresses are effectively valid for vmalloc...
  * Sort of meaningless for non-VM targets.
  */
-#define	VMALLOC_START	0
-#define	VMALLOC_END	0xffffffff
+#define	VMALLOC_START	0UL
+#define	VMALLOC_END	0xffffffffUL
 
 #define FIRST_USER_ADDRESS      (0)
 
diff --git a/arch/arm/include/asm/setup.h b/arch/arm/include/asm/setup.h
index 5ccce0a9b03..f392fb4437a 100644
--- a/arch/arm/include/asm/setup.h
+++ b/arch/arm/include/asm/setup.h
@@ -223,18 +223,6 @@ extern struct meminfo meminfo;
 #define bank_phys_end(bank)	((bank)->start + (bank)->size)
 #define bank_phys_size(bank)	(bank)->size
 
-/*
- * Early command line parameters.
- */
-struct early_params {
-	const char *arg;
-	void (*fn)(char **p);
-};
-
-#define __early_param(name,fn)					\
-static struct early_params __early_##fn __used			\
-__attribute__((__section__(".early_param.init"))) = { name, fn }
-
 #endif  /*  __KERNEL__  */
 
 #endif
diff --git a/arch/arm/include/asm/spinlock.h b/arch/arm/include/asm/spinlock.h
index c91c64cab92..17eb355707d 100644
--- a/arch/arm/include/asm/spinlock.h
+++ b/arch/arm/include/asm/spinlock.h
@@ -5,6 +5,22 @@
 #error SMP not supported on pre-ARMv6 CPUs
 #endif
 
+static inline void dsb_sev(void)
+{
+#if __LINUX_ARM_ARCH__ >= 7
+	__asm__ __volatile__ (
+		"dsb\n"
+		"sev"
+	);
+#elif defined(CONFIG_CPU_32v6K)
+	__asm__ __volatile__ (
+		"mcr p15, 0, %0, c7, c10, 4\n"
+		"sev"
+		: : "r" (0)
+	);
+#endif
+}
+
 /*
  * ARMv6 Spin-locking.
  *
@@ -69,13 +85,11 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 
 	__asm__ __volatile__(
 "	str	%1, [%0]\n"
-#ifdef CONFIG_CPU_32v6K
-"	mcr	p15, 0, %1, c7, c10, 4\n" /* DSB */
-"	sev"
-#endif
 	:
 	: "r" (&lock->lock), "r" (0)
 	: "cc");
+
+	dsb_sev();
 }
 
 /*
@@ -132,13 +146,11 @@ static inline void arch_write_unlock(arch_rwlock_t *rw)
 
 	__asm__ __volatile__(
 	"str	%1, [%0]\n"
-#ifdef CONFIG_CPU_32v6K
-"	mcr	p15, 0, %1, c7, c10, 4\n" /* DSB */
-"	sev\n"
-#endif
 	:
 	: "r" (&rw->lock), "r" (0)
 	: "cc");
+
+	dsb_sev();
 }
 
 /* write_can_lock - would write_trylock() succeed? */
@@ -188,14 +200,12 @@ static inline void arch_read_unlock(arch_rwlock_t *rw)
 "	strex	%1, %0, [%2]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
-#ifdef CONFIG_CPU_32v6K
-"\n	cmp	%0, #0\n"
-"	mcreq   p15, 0, %0, c7, c10, 4\n"
-"	seveq"
-#endif
 	: "=&r" (tmp), "=&r" (tmp2)
 	: "r" (&rw->lock)
 	: "cc");
+
+	if (tmp == 0)
+		dsb_sev();
 }
 
 static inline int arch_read_trylock(arch_rwlock_t *rw)
diff --git a/arch/arm/include/asm/system.h b/arch/arm/include/asm/system.h
index 058e7e90881..ca88e6a8470 100644
--- a/arch/arm/include/asm/system.h
+++ b/arch/arm/include/asm/system.h
@@ -73,8 +73,7 @@ extern unsigned int mem_fclk_21285;
 
 struct pt_regs;
 
-void die(const char *msg, struct pt_regs *regs, int err)
-		__attribute__((noreturn));
+void die(const char *msg, struct pt_regs *regs, int err);
 
 struct siginfo;
 void arm_notify_die(const char *str, struct pt_regs *regs, struct siginfo *info,
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index 2dfb7d7a66e..b74970ec02c 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -115,7 +115,8 @@ extern void iwmmxt_task_restore(struct thread_info *, void *);
 extern void iwmmxt_task_release(struct thread_info *);
 extern void iwmmxt_task_switch(struct thread_info *);
 
-extern void vfp_sync_state(struct thread_info *thread);
+extern void vfp_sync_hwstate(struct thread_info *);
+extern void vfp_flush_hwstate(struct thread_info *);
 
 #endif