[Intel-gfx] [PATCH] drm/i915: Rewrite vlv_find_best_dpll()

[ville.syrjala at linux.intel.com]

From: Ville Syrjälä <ville.syrjala at linux.intel.com>

vlv_find_best_dpll() has several integer over/underflow issues,
includes a hand rolled DIV_ROUND_CLOSEST(), has a boat load of
variables, some slightly weird math, and it doesn't look very
nice either.

Rather than try to deal with each issue separately I just decided
to rewrite the function a bit.

WARNING: Entirely untested

Signed-off-by: Ville Syrjälä <ville.syrjala at linux.intel.com>
---
 drivers/gpu/drm/i915/intel_display.c | 94 +++++++++++++++---------------------
 1 file changed, 40 insertions(+), 54 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 3b06250..f89fb12 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -670,65 +670,51 @@ vlv_find_best_dpll(const intel_limit_t *limit, struct drm_crtc *crtc,
 		   int target, int refclk, intel_clock_t *match_clock,
 		   intel_clock_t *best_clock)
 {
-	u32 p1, p2, m1, m2, vco, bestn, bestm1, bestm2, bestp1, bestp2;
-	u32 m, n, fastclk;
-	u32 updrate, minupdate, p;
-	unsigned long bestppm, ppm, absppm;
-	int dotclk, flag;
-
-	flag = 0;
-	dotclk = target * 1000;
-	bestppm = 1000000;
-	ppm = absppm = 0;
-	fastclk = dotclk / (2*100);
-	updrate = 0;
-	minupdate = 19200;
-	n = p = p1 = p2 = m = m1 = m2 = vco = bestn = 0;
-	bestm1 = bestm2 = bestp1 = bestp2 = 0;
+	intel_clock_t clock = {
+		.dot = target * 5, /* fast clock */
+	};
+	unsigned int bestppm = 1000000;
+	/* min update 19.2 MHz */
+	int max_n = min(limit->n.max, refclk / 19200);
 
 	/* based on hardware requirement, prefer smaller n to precision */
-	for (n = limit->n.min; n <= ((refclk) / minupdate); n++) {
-		updrate = refclk / n;
-		for (p1 = limit->p1.max; p1 > limit->p1.min; p1--) {
-			for (p2 = limit->p2.p2_fast+1; p2 > 0; p2--) {
-				if (p2 > 10)
-					p2 = p2 - 1;
-				p = p1 * p2;
-				/* based on hardware requirement, prefer bigger m1,m2 values */
-				for (m1 = limit->m1.min; m1 <= limit->m1.max; m1++) {
-					m2 = (((2*(fastclk * p * n / m1 )) +
-					       refclk) / (2*refclk));
-					m = m1 * m2;
-					vco = updrate * m;
-					if (vco >= limit->vco.min && vco < limit->vco.max) {
-						ppm = 1000000 * ((vco / p) - fastclk) / fastclk;
-						absppm = (ppm > 0) ? ppm : (-ppm);
-						if (absppm < 100 && ((p1 * p2) > (bestp1 * bestp2))) {
-							bestppm = 0;
-							flag = 1;
-						}
-						if (absppm < bestppm - 10) {
-							bestppm = absppm;
-							flag = 1;
-						}
-						if (flag) {
-							bestn = n;
-							bestm1 = m1;
-							bestm2 = m2;
-							bestp1 = p1;
-							bestp2 = p2;
-							flag = 0;
-						}
-					}
-				}
+	for (clock.n = limit->n.min; clock.n <= max_n; clock.n++) {
+	for (clock.p1 = limit->p1.max; clock.p1 > limit->p1.min; clock.p1--) {
+	for (clock.p2 = limit->p2.p2_fast+1; clock.p2 > 0; clock.p2--) {
+		if (clock.p2 > 10)
+			clock.p2--;
+		clock.p = clock.p1 * clock.p2;
+
+		/* based on hardware requirement, prefer bigger m1,m2 values */
+		for (clock.m1 = limit->m1.min; clock.m1 <= limit->m1.max; clock.m1++) {
+			unsigned int ppm, diff;
+
+			clock.m2 = DIV_ROUND_CLOSEST(clock.dot * clock.p * clock.n,
+						     clock.m1 * refclk);
+			clock.m = clock.m1 * clock.m2;
+
+			clock.vco = refclk * clock.m / clock.n;
+
+			if (clock.vco < limit->vco.min ||
+			    clock.vco >= limit->vco.max)
+				continue;
+
+			diff = abs(clock.vco / clock.p - clock.dot);
+			ppm = div_u64(1000000ULL * diff, clock.dot);
+
+			if (ppm < 100 && clock.p > best_clock->p) {
+				bestppm = 0;
+				*best_clock = clock;
+			}
+
+			if (ppm + 10 < bestppm) {
+				bestppm = ppm;
+				*best_clock = clock;
 			}
 		}
 	}
-	best_clock->n = bestn;
-	best_clock->m1 = bestm1;
-	best_clock->m2 = bestm2;
-	best_clock->p1 = bestp1;
-	best_clock->p2 = bestp2;
+	}
+	}
 
 	return true;
 }
-- 
1.8.1.5