drm/i915/scaler: Check if vblank is sufficient for scaler

High refresh rate panels which may have small line times
and vblank sizes, Check if vblank size is sufficient for
enabled scaler users.

--v2:
- Use hweight* family of functions for counting bits. [Jani]
- Update precision handling for hscale and vscale. [Ankit]
- Consider chroma downscaling factor during latency
calculation. [Ankit]
- Replace function name from scaler_prefill_time to
scaler_prefill_latency.

--v3:
- hscale_k and vscale_k values are already left shifted
by 16, after multiplying by 1000, those need to be right
shifted to 16. [Ankit]
- Replace YCBCR444 to YCBCR420. [Ankit]
- Divide by 1000 * 1000 in end to get correct precision. [Ankit]
- Initialise latency to 0 to avoid any garbage.

--v4:
- Elaborate commit message and add Bspec number. [Ankit]
- Improvise latency calculation. [Ankit]
- Use ceiling value for down scaling factor when less than 1
as per bspec. [Ankit]
- Correct linetime calculation. [Ankit]
- Consider cdclk prefill adjustment while prefill
computation.[Ankit]

--v5:
- Add Bspec link in commit message trailer. [Ankit]
- Correct hscale, vscale data type.
- Use intel_crtc_compute_min_cdclk. [Ankit]

--v6:
- Update FIXME comment.
- Use cdclk_state->logical.cdclk instead of
intel_crtc_compute_min_cdclk. [Ankit]

--v7:
- Handle error return from cdclk_prefill_adjustment. [Ankit]
- Avoid incorrect round off for linetime. [Ankit]
- Correct precision. [Ankit]

--v8:
- Remove redundancy calculation added from previous patch. [Ankit]

Bspec: 70151
Signed-off-by: Mitul Golani <mitulkumar.ajitkumar.golani@intel.com>
Reviewed-by: Ankit Nautiyal <ankit.k.nautiyal@intel.com>
Signed-off-by: Ankit Nautiyal <ankit.k.nautiyal@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250120172209.188488-7-mitulkumar.ajitkumar.golani@intel.com

drivers/gpu/drm/i915/display/skl_watermark.c

@@ -2292,6 +2292,56 @@ static int icl_build_plane_wm(struct intel_crtc_state *crtc_state,
 	return 0;
 }
 
+static int
+cdclk_prefill_adjustment(const struct intel_crtc_state *crtc_state)
+{
+	struct intel_display *display = to_intel_display(crtc_state);
+	struct intel_atomic_state *state =
+		to_intel_atomic_state(crtc_state->uapi.state);
+	const struct intel_cdclk_state *cdclk_state;
+
+	cdclk_state = intel_atomic_get_cdclk_state(state);
+	if (IS_ERR(cdclk_state)) {
+		drm_WARN_ON(display->drm, PTR_ERR(cdclk_state));
+		return 1;
+	}
+
+	return min(1, DIV_ROUND_UP(crtc_state->pixel_rate,
+				   2 * cdclk_state->logical.cdclk));
+}
+
+static int
+scaler_prefill_latency(const struct intel_crtc_state *crtc_state)
+{
+	const struct intel_crtc_scaler_state *scaler_state =
+					&crtc_state->scaler_state;
+	int num_scaler_users = hweight32(scaler_state->scaler_users);
+	int scaler_prefill_latency = 0;
+	int linetime = DIV_ROUND_UP(1000 * crtc_state->hw.adjusted_mode.htotal,
+				    crtc_state->hw.adjusted_mode.clock);
+
+	if (!num_scaler_users)
+		return scaler_prefill_latency;
+
+	scaler_prefill_latency = 4 * linetime;
+
+	if (num_scaler_users > 1) {
+		u64 hscale_k = max(1000, mul_u32_u32(scaler_state->scalers[0].hscale, 1000) >> 16);
+		u64 vscale_k = max(1000, mul_u32_u32(scaler_state->scalers[0].vscale, 1000) >> 16);
+		int chroma_downscaling_factor =
+			crtc_state->output_format == INTEL_OUTPUT_FORMAT_YCBCR420 ? 2 : 1;
+		int latency;
+
+		latency = DIV_ROUND_UP_ULL((4 * linetime * hscale_k * vscale_k *
+					    chroma_downscaling_factor), 1000000);
+		scaler_prefill_latency += latency;
+	}
+
+	scaler_prefill_latency *= cdclk_prefill_adjustment(crtc_state);
+
+	return intel_usecs_to_scanlines(&crtc_state->hw.adjusted_mode, scaler_prefill_latency);
+}
+
 static bool
 skl_is_vblank_too_short(const struct intel_crtc_state *crtc_state,
 			int wm0_lines, int latency)
@@ -2299,9 +2349,10 @@ skl_is_vblank_too_short(const struct intel_crtc_state *crtc_state,
 	const struct drm_display_mode *adjusted_mode =
 		&crtc_state->hw.adjusted_mode;
 
-	/* FIXME missing scaler and DSC pre-fill time */
+	/* FIXME missing DSC pre-fill time */
 	return crtc_state->framestart_delay +
 		intel_usecs_to_scanlines(adjusted_mode, latency) +
+		scaler_prefill_latency(crtc_state) +
 		wm0_lines >
 		adjusted_mode->crtc_vtotal - adjusted_mode->crtc_vblank_start;
 }