diff --git a/arch/arc/include/asm/spinlock.h b/arch/arc/include/asm/spinlock.h
index f158197ac5b0..b6a8c2dfbe6e 100644
--- a/arch/arc/include/asm/spinlock.h
+++ b/arch/arc/include/asm/spinlock.h
@@ -45,7 +45,14 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock)
 
 static inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
-	lock->slock = __ARCH_SPIN_LOCK_UNLOCKED__;
+	unsigned int tmp = __ARCH_SPIN_LOCK_UNLOCKED__;
+
+	__asm__ __volatile__(
+	"	ex  %0, [%1]		\n"
+	: "+r" (tmp)
+	: "r"(&(lock->slock))
+	: "memory");
+
 	smp_mb();
 }
 
diff --git a/arch/arc/include/asm/uaccess.h b/arch/arc/include/asm/uaccess.h
index 32420824375b..30c9baffa96f 100644
--- a/arch/arc/include/asm/uaccess.h
+++ b/arch/arc/include/asm/uaccess.h
@@ -43,7 +43,7 @@
  * Because it essentially checks if buffer end is within limit and @len is
  * non-ngeative, which implies that buffer start will be within limit too.
  *
- * The reason for rewriting being, for majorit yof cases, @len is generally
+ * The reason for rewriting being, for majority of cases, @len is generally
  * compile time constant, causing first sub-expression to be compile time
  * subsumed.
  *
@@ -53,7 +53,7 @@
  *
  */
 #define __user_ok(addr, sz)	(((sz) <= TASK_SIZE) && \
-				 (((addr)+(sz)) <= get_fs()))
+				 ((addr) <= (get_fs() - (sz))))
 #define __access_ok(addr, sz)	(unlikely(__kernel_ok) || \
 				 likely(__user_ok((addr), (sz))))
 
diff --git a/arch/arc/kernel/time.c b/arch/arc/kernel/time.c
index 0e51e69cf30d..3fde7de3ea67 100644
--- a/arch/arc/kernel/time.c
+++ b/arch/arc/kernel/time.c
@@ -227,12 +227,9 @@ void __attribute__((weak)) arc_local_timer_setup(unsigned int cpu)
 {
 	struct clock_event_device *clk = &per_cpu(arc_clockevent_device, cpu);
 
-	clockevents_calc_mult_shift(clk, arc_get_core_freq(), 5);
-
-	clk->max_delta_ns = clockevent_delta2ns(ARC_TIMER_MAX, clk);
 	clk->cpumask = cpumask_of(cpu);
-
-	clockevents_register_device(clk);
+	clockevents_config_and_register(clk, arc_get_core_freq(),
+					0, ARC_TIMER_MAX);
 
 	/*
 	 * setup the per-cpu timer IRQ handler - for all cpus
diff --git a/arch/arc/kernel/unaligned.c b/arch/arc/kernel/unaligned.c
index 28d170060747..7ff5b5c183bb 100644
--- a/arch/arc/kernel/unaligned.c
+++ b/arch/arc/kernel/unaligned.c
@@ -245,6 +245,12 @@ int misaligned_fixup(unsigned long address, struct pt_regs *regs,
 		regs->status32 &= ~STATUS_DE_MASK;
 	} else {
 		regs->ret += state.instr_len;
+
+		/* handle zero-overhead-loop */
+		if ((regs->ret == regs->lp_end) && (regs->lp_count)) {
+			regs->ret = regs->lp_start;
+			regs->lp_count--;
+		}
 	}
 
 	return 0;