drm/i915: Streamline the artihmetic

All these ROUNDING_FACTORs and whatnot are making this thing hard to
read. Get rid of them. And let's massage some of the fractions to
give us less questionable intermediate results and perhaps less
divisions.

Also looks like a good helping of 64bit math stuff is needed to
avoid some of overflows present in the current code. There
might still be a few overflows, namely when calculating
link_clks_available/samples_room (would require a huge hblank
though), and potentially when calculating hblank_rise (not sure
how large link_clks_active can get).

It looks like we're still not calculating exactly what the spec says
since we truncate tu_data and tu_line early. But I'm too lazy to
figure out if we could avoid that.

v2: Fix typo in commit msg (Uma)
    Remove ROUNDING_FACTOR define (Uma)
    s/5*link_clk+5*cdclk/5*(link_clk+cdclk)/ (Chris)

Cc: Anshuman Gupta <anshuman.gupta@intel.com>
Cc: Uma Shankar <uma.shankar@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200429185457.26235-3-ville.syrjala@linux.intel.com
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Uma Shankar <uma.shankar@intel.com>

diff --git a/drivers/gpu/drm/i915/display/intel_audio.c b/drivers/gpu/drm/i915/display/intel_audio.c
index 00f7a3cf9a0468a71595cc4a281705c8e58602f3..ad4aa66fd676743b897753492eda3cb73e2cbab7 100644 (file)
--- a/drivers/gpu/drm/i915/display/intel_audio.c
+++ b/drivers/gpu/drm/i915/display/intel_audio.c
@@ -514,19 +514,16 @@ static void hsw_audio_codec_disable(struct intel_encoder *encoder,
        mutex_unlock(&dev_priv->av_mutex);
 }
 
-/* Add a factor to take care of rounding and truncations */
-#define ROUNDING_FACTOR 10000
-
-static unsigned int get_hblank_early_enable_config(struct intel_encoder *encoder,
-                                                  const struct intel_crtc_state *crtc_state)
+static unsigned int calc_hblank_early_prog(struct intel_encoder *encoder,
+                                          const struct intel_crtc_state *crtc_state)
 {
        struct drm_i915_private *i915 = to_i915(encoder->base.dev);
        unsigned int link_clks_available, link_clks_required;
        unsigned int tu_data, tu_line, link_clks_active;
-       unsigned int hblank_rise, hblank_early_prog;
        unsigned int h_active, h_total, hblank_delta, pixel_clk;
        unsigned int fec_coeff, cdclk, vdsc_bpp;
        unsigned int link_clk, lanes;
+       unsigned int hblank_rise;
 
        h_active = crtc_state->hw.adjusted_mode.crtc_hdisplay;
        h_total = crtc_state->hw.adjusted_mode.crtc_htotal;
@@ -542,44 +539,33 @@ static unsigned int get_hblank_early_enable_config(struct intel_encoder *encoder
                    "lanes = %u vdsc_bpp = %u cdclk = %u\n",
                    h_active, link_clk, lanes, vdsc_bpp, cdclk);
 
-       if (WARN_ON(!link_clk || !lanes || !vdsc_bpp || !cdclk))
+       if (WARN_ON(!link_clk || !pixel_clk || !lanes || !vdsc_bpp || !cdclk))
                return 0;
 
-       link_clks_available = ((((h_total - h_active) *
-                              ((link_clk * ROUNDING_FACTOR) /
-                               pixel_clk)) / ROUNDING_FACTOR) - 28);
-       link_clks_required = DIV_ROUND_UP(192000, (1000 * pixel_clk / h_total)) * ((48 /
-                                         lanes) + 2);
+       link_clks_available = (h_total - h_active) * link_clk / pixel_clk - 28;
+       link_clks_required = DIV_ROUND_UP(192000 * h_total, 1000 * pixel_clk) * (48 / lanes + 2);
 
        if (link_clks_available > link_clks_required)
                hblank_delta = 32;
        else
-               hblank_delta = DIV_ROUND_UP(((((5 * ROUNDING_FACTOR) /
-                                           link_clk) + ((5 *
-                                           ROUNDING_FACTOR) /
-                                           cdclk)) * pixel_clk),
-                                           ROUNDING_FACTOR);
-
-       tu_data = (pixel_clk * vdsc_bpp * 8) / ((link_clk *
-                  lanes * fec_coeff) / 1000000);
-       tu_line = (((h_active * link_clk * fec_coeff) /
-                  1000000) / (64 * pixel_clk));
-       link_clks_active  = (tu_line - 1) * 64 + tu_data;
+               hblank_delta = DIV64_U64_ROUND_UP(mul_u32_u32(5 * (link_clk + cdclk), pixel_clk),
+                                                 mul_u32_u32(link_clk, cdclk));
 
-       hblank_rise = ((link_clks_active + 6 * DIV_ROUND_UP(link_clks_active,
-                       250) + 4) * ((pixel_clk * ROUNDING_FACTOR) /
-                       link_clk)) / ROUNDING_FACTOR;
+       tu_data = div64_u64(mul_u32_u32(pixel_clk * vdsc_bpp * 8, 1000000),
+                           mul_u32_u32(link_clk * lanes, fec_coeff));
+       tu_line = div64_u64(h_active * mul_u32_u32(link_clk, fec_coeff),
+                           mul_u32_u32(64 * pixel_clk, 1000000));
+       link_clks_active  = (tu_line - 1) * 64 + tu_data;
 
-       hblank_early_prog = h_active - hblank_rise + hblank_delta;
+       hblank_rise = (link_clks_active + 6 * DIV_ROUND_UP(link_clks_active, 250) + 4) * pixel_clk / link_clk;
 
-       return hblank_early_prog;
+       return h_active - hblank_rise + hblank_delta;
 }
 
-static unsigned int get_sample_room_req_config(const struct intel_crtc_state *crtc_state)
+static unsigned int calc_samples_room(const struct intel_crtc_state *crtc_state)
 {
        unsigned int h_active, h_total, pixel_clk;
        unsigned int link_clk, lanes;
-       unsigned int samples_room;
 
        h_active = crtc_state->hw.adjusted_mode.hdisplay;
        h_total = crtc_state->hw.adjusted_mode.htotal;
@@ -587,12 +573,8 @@ static unsigned int get_sample_room_req_config(const struct intel_crtc_state *cr
        link_clk = crtc_state->port_clock;
        lanes = crtc_state->lane_count;
 
-       samples_room = ((((h_total - h_active) * ((link_clk *
-                       ROUNDING_FACTOR) / pixel_clk)) /
-                       ROUNDING_FACTOR) - 12) / ((48 /
-                       lanes) + 2);
-
-       return samples_room;
+       return ((h_total - h_active) * link_clk - 12 * pixel_clk) /
+               (pixel_clk * (48 / lanes + 2));
 }
 
 static void enable_audio_dsc_wa(struct intel_encoder *encoder,
@@ -618,8 +600,7 @@ static void enable_audio_dsc_wa(struct intel_encoder *encoder,
            (crtc_state->hw.adjusted_mode.hdisplay >= 3840 &&
            crtc_state->hw.adjusted_mode.vdisplay >= 2160)) {
                /* Get hblank early enable value required */
-               hblank_early_prog = get_hblank_early_enable_config(encoder,
-                                                                  crtc_state);
+               hblank_early_prog = calc_hblank_early_prog(encoder, crtc_state);
                if (hblank_early_prog < 32) {
                        val &= ~HBLANK_START_COUNT_MASK(pipe);
                        val |= HBLANK_START_COUNT(pipe, HBLANK_START_COUNT_32);
@@ -635,7 +616,7 @@ static void enable_audio_dsc_wa(struct intel_encoder *encoder,
                }
 
                /* Get samples room value required */
-               samples_room = get_sample_room_req_config(crtc_state);
+               samples_room = calc_samples_room(crtc_state);
                if (samples_room < 3) {
                        val &= ~NUMBER_SAMPLES_PER_LINE_MASK(pipe);
                        val |= NUMBER_SAMPLES_PER_LINE(pipe, samples_room);