diff --git a/arch/arm/mach-omap2/timer-gp.c b/arch/arm/mach-omap2/timer-gp.c
index 78d05f203fff..557603f99313 100644
--- a/arch/arm/mach-omap2/timer-gp.c
+++ b/arch/arm/mach-omap2/timer-gp.c
@@ -59,8 +59,7 @@ static struct irqaction omap2_gp_timer_irq = {
 static int omap2_gp_timer_set_next_event(unsigned long cycles,
 					 struct clock_event_device *evt)
 {
-	omap_dm_timer_set_load(gptimer, 0, 0xffffffff - cycles);
-	omap_dm_timer_start(gptimer);
+	omap_dm_timer_set_load_start(gptimer, 0, 0xffffffff - cycles);
 
 	return 0;
 }
@@ -77,8 +76,7 @@ static void omap2_gp_timer_set_mode(enum clock_event_mode mode,
 		period = clk_get_rate(omap_dm_timer_get_fclk(gptimer)) / HZ;
 		period -= 1;
 
-		omap_dm_timer_set_load(gptimer, 1, 0xffffffff - period);
-		omap_dm_timer_start(gptimer);
+		omap_dm_timer_set_load_start(gptimer, 1, 0xffffffff - period);
 		break;
 	case CLOCK_EVT_MODE_ONESHOT:
 		break;
@@ -172,8 +170,7 @@ static void __init omap2_gp_clocksource_init(void)
 	tick_rate = clk_get_rate(omap_dm_timer_get_fclk(gpt));
 	tick_period = (tick_rate / HZ) - 1;
 
-	omap_dm_timer_set_load(gpt, 1, 0);
-	omap_dm_timer_start(gpt);
+	omap_dm_timer_set_load_start(gpt, 1, 0);
 
 	clocksource_gpt.mult =
 		clocksource_khz2mult(tick_rate/1000, clocksource_gpt.shift);
diff --git a/arch/arm/plat-omap/dmtimer.c b/arch/arm/plat-omap/dmtimer.c
index 822b6bb5c74c..f22506af0e67 100644
--- a/arch/arm/plat-omap/dmtimer.c
+++ b/arch/arm/plat-omap/dmtimer.c
@@ -546,6 +546,24 @@ void omap_dm_timer_set_load(struct omap_dm_timer *timer, int autoreload,
 	omap_dm_timer_write_reg(timer, OMAP_TIMER_TRIGGER_REG, 0);
 }
 
+/* Optimized set_load which removes costly spin wait in timer_start */
+void omap_dm_timer_set_load_start(struct omap_dm_timer *timer, int autoreload,
+                            unsigned int load)
+{
+	u32 l;
+
+	l = omap_dm_timer_read_reg(timer, OMAP_TIMER_CTRL_REG);
+	if (autoreload)
+		l |= OMAP_TIMER_CTRL_AR;
+	else
+		l &= ~OMAP_TIMER_CTRL_AR;
+	l |= OMAP_TIMER_CTRL_ST;
+
+	omap_dm_timer_write_reg(timer, OMAP_TIMER_COUNTER_REG, load);
+	omap_dm_timer_write_reg(timer, OMAP_TIMER_LOAD_REG, load);
+	omap_dm_timer_write_reg(timer, OMAP_TIMER_CTRL_REG, l);
+}
+
 void omap_dm_timer_set_match(struct omap_dm_timer *timer, int enable,
 			     unsigned int match)
 {
@@ -560,7 +578,6 @@ void omap_dm_timer_set_match(struct omap_dm_timer *timer, int enable,
 	omap_dm_timer_write_reg(timer, OMAP_TIMER_MATCH_REG, match);
 }
 
-
 void omap_dm_timer_set_pwm(struct omap_dm_timer *timer, int def_on,
 			   int toggle, int trigger)
 {
diff --git a/include/asm-arm/arch-omap/dmtimer.h b/include/asm-arm/arch-omap/dmtimer.h
index fefb276ed402..02b29e8437ae 100644
--- a/include/asm-arm/arch-omap/dmtimer.h
+++ b/include/asm-arm/arch-omap/dmtimer.h
@@ -66,6 +66,7 @@ void omap_dm_timer_stop(struct omap_dm_timer *timer);
 
 void omap_dm_timer_set_source(struct omap_dm_timer *timer, int source);
 void omap_dm_timer_set_load(struct omap_dm_timer *timer, int autoreload, unsigned int value);
+void omap_dm_timer_set_load_start(struct omap_dm_timer *timer, int autoreload, unsigned int value);
 void omap_dm_timer_set_match(struct omap_dm_timer *timer, int enable, unsigned int match);
 void omap_dm_timer_set_pwm(struct omap_dm_timer *timer, int def_on, int toggle, int trigger);
 void omap_dm_timer_set_prescaler(struct omap_dm_timer *timer, int prescaler);