drm/i915/gen10: implement gen 10 watermarks calculations

They're slightly different than the gen 9 calculations.

v2: Remove TODO comment. Code matches recent spec.
v3: Rebase on top of latest skl code using new fp16.16 and
    fixing a logic issue. Auto rebase bot has apparently
    made some bad decisions that changed the logic of the
    code. (Noticed by Manesh, updated by Rodrigo).

Cc: Mahesh Kumar <mahesh1.kumar@intel.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Mahesh Kumar <mahesh1.kumar@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170811233825.32083-1-rodrigo.vivi@intel.com

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 66495ad36973d8e52f5fcad8e52b049e32a43828..ed662937ec3c85685b7fed049f381c6d1cb5654c 100644 (file)
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -4290,8 +4290,9 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *cstate,
  * should allow pixel_rate up to ~2 GHz which seems sufficient since max
  * 2xcdclk is 1350 MHz and the pixel rate should never exceed that.
 */
-static uint_fixed_16_16_t skl_wm_method1(uint32_t pixel_rate, uint8_t cpp,
-                                        uint32_t latency)
+static uint_fixed_16_16_t
+skl_wm_method1(const struct drm_i915_private *dev_priv, uint32_t pixel_rate,
+              uint8_t cpp, uint32_t latency)
 {
        uint32_t wm_intermediate_val;
        uint_fixed_16_16_t ret;
@@ -4301,6 +4302,10 @@ static uint_fixed_16_16_t skl_wm_method1(uint32_t pixel_rate, uint8_t cpp,
 
        wm_intermediate_val = latency * pixel_rate * cpp;
        ret = div_fixed16(wm_intermediate_val, 1000 * 512);
+
+       if (INTEL_GEN(dev_priv) >= 10)
+               ret = add_fixed16_u32(ret, 1);
+
        return ret;
 }
 
@@ -4456,9 +4461,13 @@ static int skl_compute_plane_wm(const struct drm_i915_private *dev_priv,
        if (y_tiled) {
                interm_pbpl = DIV_ROUND_UP(plane_bytes_per_line *
                                           y_min_scanlines, 512);
+
+               if (INTEL_GEN(dev_priv) >= 10)
+                       interm_pbpl++;
+
                plane_blocks_per_line = div_fixed16(interm_pbpl,
                                                        y_min_scanlines);
-       } else if (x_tiled) {
+       } else if (x_tiled && INTEL_GEN(dev_priv) == 9) {
                interm_pbpl = DIV_ROUND_UP(plane_bytes_per_line, 512);
                plane_blocks_per_line = u32_to_fixed16(interm_pbpl);
        } else {
@@ -4466,7 +4475,7 @@ static int skl_compute_plane_wm(const struct drm_i915_private *dev_priv,
                plane_blocks_per_line = u32_to_fixed16(interm_pbpl);
        }
 
-       method1 = skl_wm_method1(plane_pixel_rate, cpp, latency);
+       method1 = skl_wm_method1(dev_priv, plane_pixel_rate, cpp, latency);
        method2 = skl_wm_method2(plane_pixel_rate,
                                 cstate->base.adjusted_mode.crtc_htotal,
                                 latency,