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

commit e190ed1ea7458e446230de4113cc5d53b8dc4ec8 upstream.

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: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Mario Kleiner <mario.kleiner.de@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
index 5b261adb4b6936cdcb8d7e154151d2ae1ffd3dbf..ffe83b648ec22d59d66a70de51271e5050cde614 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
@@ -1126,23 +1126,10 @@ 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);

diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
index 267749a94c5aacd055e8ea31e43b85cbff2f7935..2944a8fa6b745b37b21073e1d9a86a4c25433e24 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
@@ -1114,23 +1114,10 @@ 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);

diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
index 9b4dcf76ce6c4b14ef727230fb13fd373be340c4..e378a70f1b61485249057fd3ab14eeb3b177e1e2 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
@@ -1096,23 +1096,10 @@ 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);