drm/amdgpu: 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 ("divide error: 0000 [#1] PREEMPT SMP" in
"dce_v10_0_latency_watermark+0x12d/0x190").

This zero-divide happened, e.g., on AMD Tonga Pro under DCE-10,
on a Displayport panel when trying to set a video mode of 2560x1440
at 165 Hz vrefresh with a dot clock of 635.540 Mhz.

Refine calculations to avoid the overflows.

Tested for DCE-10 with R9 380 Tonga + ASUS ROG PG279 panel.
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NMario Kleiner <mario.kleiner.de@gmail.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org

drivers/gpu/drm/amd/amdgpu/dce_v10_0.c

@@ -1090,23 +1090,10 @@ static u32 dce_v10_0_latency_watermark(struct dce10_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/amd/amdgpu/dce_v11_0.c

@@ -1059,23 +1059,10 @@ static u32 dce_v11_0_latency_watermark(struct dce10_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/amd/amdgpu/dce_v6_0.c

@@ -861,23 +861,10 @@ static u32 dce_v6_0_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);

drivers/gpu/drm/amd/amdgpu/dce_v8_0.c

@@ -974,23 +974,10 @@ static u32 dce_v8_0_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);