drm/radeon: Avoid overflows/divide-by-zero in latency_watermark calculations.

At dot clocks > approx. 250 Mhz, some of these calcs will overflow and
cause miscalculation of latency watermarks, and for some overflows also
divide-by-zero driver crash. Make calcs more overflow resistant.

This is a direct port of the corresponding patch from amdgpu-kms,
copy-paste for cik from dce-8 and si from dce-6, with a slightly
simpler variant for evergreen dce-4/5.

Only tested on DCE-4 evergreen with a Radeon HD-5770.
Signed-off-by: Mario Kleiner <mario.kleiner.de@gmail.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/radeon/cik.c

@@ -9150,23 +9150,10 @@ static u32 dce8_latency_watermark(struct dce8_wm_params *wm)
 	a.full = dfixed_const(available_bandwidth);
 	b.full = dfixed_const(wm->num_heads);
 	a.full = dfixed_div(a, b);
+	tmp = div_u64((u64) dmif_size * (u64) wm->disp_clk, mc_latency + 512);
+	tmp = min(dfixed_trunc(a), tmp);
 
-	b.full = dfixed_const(mc_latency + 512);
-	c.full = dfixed_const(wm->disp_clk);
-	b.full = dfixed_div(b, c);
-
-	c.full = dfixed_const(dmif_size);
-	b.full = dfixed_div(c, b);
-
-	tmp = min(dfixed_trunc(a), dfixed_trunc(b));
-
-	b.full = dfixed_const(1000);
-	c.full = dfixed_const(wm->disp_clk);
-	b.full = dfixed_div(c, b);
-	c.full = dfixed_const(wm->bytes_per_pixel);
-	b.full = dfixed_mul(b, c);
-
-	lb_fill_bw = min(tmp, dfixed_trunc(b));
+	lb_fill_bw = min(tmp, wm->disp_clk * wm->bytes_per_pixel / 1000);
 
 	a.full = dfixed_const(max_src_lines_per_dst_line * wm->src_width * wm->bytes_per_pixel);
 	b.full = dfixed_const(1000);

drivers/gpu/drm/radeon/evergreen.c

@@ -2188,13 +2188,7 @@ static u32 evergreen_latency_watermark(struct evergreen_wm_params *wm)
 	b.full = dfixed_const(wm->num_heads);
 	a.full = dfixed_div(a, b);
 
-	b.full = dfixed_const(1000);
-	c.full = dfixed_const(wm->disp_clk);
-	b.full = dfixed_div(c, b);
-	c.full = dfixed_const(wm->bytes_per_pixel);
-	b.full = dfixed_mul(b, c);
-
-	lb_fill_bw = min(dfixed_trunc(a), dfixed_trunc(b));
+	lb_fill_bw = min(dfixed_trunc(a), wm->disp_clk * wm->bytes_per_pixel / 1000);
 
 	a.full = dfixed_const(max_src_lines_per_dst_line * wm->src_width * wm->bytes_per_pixel);
 	b.full = dfixed_const(1000);

drivers/gpu/drm/radeon/si.c

@@ -2204,23 +2204,10 @@ static u32 dce6_latency_watermark(struct dce6_wm_params *wm)
 	a.full = dfixed_const(available_bandwidth);
 	b.full = dfixed_const(wm->num_heads);
 	a.full = dfixed_div(a, b);
+	tmp = div_u64((u64) dmif_size * (u64) wm->disp_clk, mc_latency + 512);
+	tmp = min(dfixed_trunc(a), tmp);
 
-	b.full = dfixed_const(mc_latency + 512);
-	c.full = dfixed_const(wm->disp_clk);
-	b.full = dfixed_div(b, c);
-
-	c.full = dfixed_const(dmif_size);
-	b.full = dfixed_div(c, b);
-
-	tmp = min(dfixed_trunc(a), dfixed_trunc(b));
-
-	b.full = dfixed_const(1000);
-	c.full = dfixed_const(wm->disp_clk);
-	b.full = dfixed_div(c, b);
-	c.full = dfixed_const(wm->bytes_per_pixel);
-	b.full = dfixed_mul(b, c);
-
-	lb_fill_bw = min(tmp, dfixed_trunc(b));
+	lb_fill_bw = min(tmp, wm->disp_clk * wm->bytes_per_pixel / 1000);
 
 	a.full = dfixed_const(max_src_lines_per_dst_line * wm->src_width * wm->bytes_per_pixel);
 	b.full = dfixed_const(1000);