drm/i915: Use mul_u32_u32() for 32b x 32b -> 64b result

As realised by commit 9e3d622 ("math64, timers: Fix 32bit
mul_u64_u32_shr() and friends"), GCC does not always generate ideal code
for performing a 32b x 32b multiply returning a 64b result (i.e. where
we idiomatically use u64 result = (u64)x * (u32)x). This catches a
couple of instances in the display code using (u64)x * (u32)y.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20170913105154.2910-1-chris@chris-wilson.co.uk
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>

drivers/gpu/drm/i915/intel_display.c

@@ -10224,7 +10224,7 @@ int intel_dotclock_calculate(int link_freq,
 	if (!m_n->link_n)
 		return 0;
 
-	return div_u64((u64)m_n->link_m * link_freq, m_n->link_n);
+	return div_u64(mul_u32_u32(m_n->link_m, link_freq), m_n->link_n);
 }
 
 static void ironlake_pch_clock_get(struct intel_crtc *crtc,

drivers/gpu/drm/i915/intel_tv.c

@@ -1385,7 +1385,7 @@ intel_tv_get_modes(struct drm_connector *connector)
 			mode_ptr->vsync_end = mode_ptr->vsync_start  + 1;
 		mode_ptr->vtotal = vactive_s + 33;
 
-		tmp = (u64) tv_mode->refresh * mode_ptr->vtotal;
+		tmp = mul_u32_u32(tv_mode->refresh, mode_ptr->vtotal);
 		tmp *= mode_ptr->htotal;
 		tmp = div_u64(tmp, 1000000);
 		mode_ptr->clock = (int) tmp;