diff --git a/arch/arm/include/asm/smp_plat.h b/arch/arm/include/asm/smp_plat.h
index 6462a721ebd4..a252c0bfacf5 100644
--- a/arch/arm/include/asm/smp_plat.h
+++ b/arch/arm/include/asm/smp_plat.h
@@ -88,4 +88,7 @@ static inline u32 mpidr_hash_size(void)
 {
 	return 1 << mpidr_hash.bits;
 }
+
+extern int platform_can_cpu_hotplug(void);
+
 #endif
diff --git a/arch/arm/include/asm/spinlock.h b/arch/arm/include/asm/spinlock.h
index f8b8965666e9..b07c09e5a0ac 100644
--- a/arch/arm/include/asm/spinlock.h
+++ b/arch/arm/include/asm/spinlock.h
@@ -107,7 +107,7 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock)
 		"	subs	%1, %0, %0, ror #16\n"
 		"	addeq	%0, %0, %4\n"
 		"	strexeq	%2, %0, [%3]"
-		: "=&r" (slock), "=&r" (contended), "=r" (res)
+		: "=&r" (slock), "=&r" (contended), "=&r" (res)
 		: "r" (&lock->slock), "I" (1 << TICKET_SHIFT)
 		: "cc");
 	} while (res);
@@ -168,17 +168,20 @@ static inline void arch_write_lock(arch_rwlock_t *rw)
 
 static inline int arch_write_trylock(arch_rwlock_t *rw)
 {
-	unsigned long tmp;
+	unsigned long contended, res;
 
-	__asm__ __volatile__(
-"	ldrex	%0, [%1]\n"
-"	teq	%0, #0\n"
-"	strexeq	%0, %2, [%1]"
-	: "=&r" (tmp)
-	: "r" (&rw->lock), "r" (0x80000000)
-	: "cc");
+	do {
+		__asm__ __volatile__(
+		"	ldrex	%0, [%2]\n"
+		"	mov	%1, #0\n"
+		"	teq	%0, #0\n"
+		"	strexeq	%1, %3, [%2]"
+		: "=&r" (contended), "=&r" (res)
+		: "r" (&rw->lock), "r" (0x80000000)
+		: "cc");
+	} while (res);
 
-	if (tmp == 0) {
+	if (!contended) {
 		smp_mb();
 		return 1;
 	} else {
@@ -254,18 +257,26 @@ static inline void arch_read_unlock(arch_rwlock_t *rw)
 
 static inline int arch_read_trylock(arch_rwlock_t *rw)
 {
-	unsigned long tmp, tmp2 = 1;
+	unsigned long contended, res;
 
-	__asm__ __volatile__(
-"	ldrex	%0, [%2]\n"
-"	adds	%0, %0, #1\n"
-"	strexpl	%1, %0, [%2]\n"
-	: "=&r" (tmp), "+r" (tmp2)
-	: "r" (&rw->lock)
-	: "cc");
+	do {
+		__asm__ __volatile__(
+		"	ldrex	%0, [%2]\n"
+		"	mov	%1, #0\n"
+		"	adds	%0, %0, #1\n"
+		"	strexpl	%1, %0, [%2]"
+		: "=&r" (contended), "=&r" (res)
+		: "r" (&rw->lock)
+		: "cc");
+	} while (res);
 
-	smp_mb();
-	return tmp2 == 0;
+	/* If the lock is negative, then it is already held for write. */
+	if (contended < 0x80000000) {
+		smp_mb();
+		return 1;
+	} else {
+		return 0;
+	}
 }
 
 /* read_can_lock - would read_trylock() succeed? */
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index d40d0ef389db..9cbe70c8b0ef 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -357,7 +357,8 @@ ENDPROC(__pabt_svc)
 	.endm
 
 	.macro	kuser_cmpxchg_check
-#if !defined(CONFIG_CPU_32v6K) && !defined(CONFIG_NEEDS_SYSCALL_FOR_CMPXCHG)
+#if !defined(CONFIG_CPU_32v6K) && defined(CONFIG_KUSER_HELPERS) && \
+    !defined(CONFIG_NEEDS_SYSCALL_FOR_CMPXCHG)
 #ifndef CONFIG_MMU
 #warning "NPTL on non MMU needs fixing"
 #else
diff --git a/arch/arm/kernel/fiq.c b/arch/arm/kernel/fiq.c
index 25442f451148..fc7920288a3d 100644
--- a/arch/arm/kernel/fiq.c
+++ b/arch/arm/kernel/fiq.c
@@ -84,17 +84,13 @@ int show_fiq_list(struct seq_file *p, int prec)
 
 void set_fiq_handler(void *start, unsigned int length)
 {
-#if defined(CONFIG_CPU_USE_DOMAINS)
-	void *base = (void *)0xffff0000;
-#else
 	void *base = vectors_page;
-#endif
 	unsigned offset = FIQ_OFFSET;
 
 	memcpy(base + offset, start, length);
+	if (!cache_is_vipt_nonaliasing())
+		flush_icache_range(base + offset, offset + length);
 	flush_icache_range(0xffff0000 + offset, 0xffff0000 + offset + length);
-	if (!vectors_high())
-		flush_icache_range(offset, offset + length);
 }
 
 int claim_fiq(struct fiq_handler *f)
diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c
index 4fb074c446bf..d7c82df69243 100644
--- a/arch/arm/kernel/machine_kexec.c
+++ b/arch/arm/kernel/machine_kexec.c
@@ -15,6 +15,7 @@
 #include <asm/mmu_context.h>
 #include <asm/cacheflush.h>
 #include <asm/mach-types.h>
+#include <asm/smp_plat.h>
 #include <asm/system_misc.h>
 
 extern const unsigned char relocate_new_kernel[];
@@ -38,6 +39,14 @@ int machine_kexec_prepare(struct kimage *image)
 	__be32 header;
 	int i, err;
 
+	/*
+	 * Validate that if the current HW supports SMP, then the SW supports
+	 * and implements CPU hotplug for the current HW. If not, we won't be
+	 * able to kexec reliably, so fail the prepare operation.
+	 */
+	if (num_possible_cpus() > 1 && !platform_can_cpu_hotplug())
+		return -EINVAL;
+
 	/*
 	 * No segment at default ATAGs address. try to locate
 	 * a dtb using magic.
@@ -134,10 +143,13 @@ void machine_kexec(struct kimage *image)
 	unsigned long reboot_code_buffer_phys;
 	void *reboot_code_buffer;
 
-	if (num_online_cpus() > 1) {
-		pr_err("kexec: error: multiple CPUs still online\n");
-		return;
-	}
+	/*
+	 * This can only happen if machine_shutdown() failed to disable some
+	 * CPU, and that can only happen if the checks in
+	 * machine_kexec_prepare() were not correct. If this fails, we can't
+	 * reliably kexec anyway, so BUG_ON is appropriate.
+	 */
+	BUG_ON(num_online_cpus() > 1);
 
 	page_list = image->head & PAGE_MASK;
 
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 21f77906602c..e186ee1e63f6 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -56,7 +56,7 @@ armpmu_map_hw_event(const unsigned (*event_map)[PERF_COUNT_HW_MAX], u64 config)
 	int mapping;
 
 	if (config >= PERF_COUNT_HW_MAX)
-		return -ENOENT;
+		return -EINVAL;
 
 	mapping = (*event_map)[config];
 	return mapping == HW_OP_UNSUPPORTED ? -ENOENT : mapping;
@@ -258,6 +258,9 @@ validate_event(struct pmu_hw_events *hw_events,
 	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	struct pmu *leader_pmu = event->group_leader->pmu;
 
+	if (is_software_event(event))
+		return 1;
+
 	if (event->pmu != leader_pmu || event->state < PERF_EVENT_STATE_OFF)
 		return 1;
 
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 536c85fe72a8..94f6b05f9e24 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -462,7 +462,7 @@ int in_gate_area_no_mm(unsigned long addr)
 {
 	return in_gate_area(NULL, addr);
 }
-#define is_gate_vma(vma)	((vma) = &gate_vma)
+#define is_gate_vma(vma)	((vma) == &gate_vma)
 #else
 #define is_gate_vma(vma)	0
 #endif
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index c2b4f8f0be9a..2dc19349eb19 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -145,6 +145,16 @@ int boot_secondary(unsigned int cpu, struct task_struct *idle)
 	return -ENOSYS;
 }
 
+int platform_can_cpu_hotplug(void)
+{
+#ifdef CONFIG_HOTPLUG_CPU
+	if (smp_ops.cpu_kill)
+		return 1;
+#endif
+
+	return 0;
+}
+
 #ifdef CONFIG_HOTPLUG_CPU
 static void percpu_timer_stop(void);