[PATCH 04/12] drm/i915/display: Extract helpers to set dsc/scaler prefill latencies
Nautiyal, Ankit K
ankit.k.nautiyal at intel.com
Mon Aug 18 06:09:09 UTC 2025
On 8/11/2025 11:46 AM, Golani, Mitulkumar Ajitkumar wrote:
>
>> -----Original Message-----
>> From: Nautiyal, Ankit K <ankit.k.nautiyal at intel.com>
>> Sent: 07 August 2025 16:46
>> To: intel-gfx at lists.freedesktop.org; intel-xe at lists.freedesktop.org
>> Cc: ville.syrjala at linux.intel.com; jani.nikula at linux.intel.com; Golani,
>> Mitulkumar Ajitkumar <mitulkumar.ajitkumar.golani at intel.com>; Nautiyal,
>> Ankit K <ankit.k.nautiyal at intel.com>
>> Subject: [PATCH 04/12] drm/i915/display: Extract helpers to set dsc/scaler
>> prefill latencies
>>
>> Currently dsc/scaler prefill latencies are handled during watermark
>> calculations. With the optimized guardband, we need to compute the latencies
>> to find the minimum guardband that works for most cases.
>> Extract the helpers to compute these latencies, so that they can be used while
>> computing vrr guardband.
>>
>> While at it, put declarations in reverse xmas tree order for better redability.
>>
>> Signed-off-by: Ankit Nautiyal <ankit.k.nautiyal at intel.com>
>> ---
>> drivers/gpu/drm/i915/display/intel_display.c | 34 +++++++++++++++
>> drivers/gpu/drm/i915/display/intel_display.h | 8 ++++
>> drivers/gpu/drm/i915/display/skl_watermark.c | 46 +++++++++-----------
>> 3 files changed, 63 insertions(+), 25 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/i915/display/intel_display.c
>> b/drivers/gpu/drm/i915/display/intel_display.c
>> index c1a3a95c65f0..af4d54672d0d 100644
>> --- a/drivers/gpu/drm/i915/display/intel_display.c
>> +++ b/drivers/gpu/drm/i915/display/intel_display.c
>> @@ -8328,3 +8328,37 @@ bool intel_scanout_needs_vtd_wa(struct
>> intel_display *display)
>>
>> return IS_DISPLAY_VER(display, 6, 11) && i915_vtd_active(i915); }
>> +
>> +int intel_display_scaler_prefill_latency(int num_scaler_users, u64 hscale, u64
>> vscale,
>> + int chroma_downscaling_factor,
>> + int cdclk_prefill_adjustment,
>> + int linetime)
>> +{
>> + int scaler_prefill_latency;
>> +
>> + scaler_prefill_latency = 4 * linetime;
>> + if (num_scaler_users > 1)
>> + scaler_prefill_latency += DIV_ROUND_UP_ULL((4 * linetime *
>> hscale * vscale *
>> +
>> chroma_downscaling_factor), 1000000);
>> +
>> + scaler_prefill_latency *= cdclk_prefill_adjustment;
>> +
>> + return scaler_prefill_latency;
>> +}
>> +
>> +int intel_display_dsc_prefill_latency(int num_scaler_users, u64 *hscale, u64
>> *vscale,
>> + int chroma_downscaling_factor,
>> + int cdclk_prefill_adjustment,
>> + int linetime)
>> +{
>> + int dsc_prefill_latency;
>> +
>> + dsc_prefill_latency = DIV_ROUND_UP(15 * linetime *
>> +chroma_downscaling_factor, 10);
>> +
>> + for (int i = 0; i < num_scaler_users; i++)
>> + dsc_prefill_latency = DIV_ROUND_UP_ULL(dsc_prefill_latency
>> * hscale[i] * vscale[i],
>> + 1000000);
>> + dsc_prefill_latency *= cdclk_prefill_adjustment;
>> +
>> + return dsc_prefill_latency;
>> +}
>> diff --git a/drivers/gpu/drm/i915/display/intel_display.h
>> b/drivers/gpu/drm/i915/display/intel_display.h
>> index 37e2ab301a80..8d094b0a8c6b 100644
>> --- a/drivers/gpu/drm/i915/display/intel_display.h
>> +++ b/drivers/gpu/drm/i915/display/intel_display.h
>> @@ -559,5 +559,13 @@ bool assert_port_valid(struct intel_display *display,
>> enum port port);
>>
>> bool intel_scanout_needs_vtd_wa(struct intel_display *display); int
>> intel_crtc_num_joined_pipes(const struct intel_crtc_state *crtc_state);
>> +int intel_display_scaler_prefill_latency(int num_scaler_users, u64 hscale, u64
>> vscale,
>> + int chroma_downscaling_factor,
>> + int cdclk_prefill_adjustment,
>> + int linetime);
>> +int intel_display_dsc_prefill_latency(int num_scaler_users, u64 *hscale, u64
>> *vscale,
>> + int chroma_downscaling_factor,
>> + int cdclk_prefill_adjustment,
>> + int linetime);
>>
>> #endif
>> diff --git a/drivers/gpu/drm/i915/display/skl_watermark.c
>> b/drivers/gpu/drm/i915/display/skl_watermark.c
>> index 97b42bbf5642..4474f987de06 100644
>> --- a/drivers/gpu/drm/i915/display/skl_watermark.c
>> +++ b/drivers/gpu/drm/i915/display/skl_watermark.c
>> @@ -2179,11 +2179,12 @@ cdclk_prefill_adjustment(const struct
>> intel_crtc_state *crtc_state) static int dsc_prefill_latency(const struct
>> intel_crtc_state *crtc_state, int linetime) {
>> + const struct intel_crtc_scaler_state *scaler_state = &crtc_state-
>>> scaler_state;
>> + int chroma_downscaling_factor =
>> +skl_scaler_chroma_downscale_factor(crtc_state);
>> struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
>> - const struct intel_crtc_scaler_state *scaler_state =
>> - &crtc_state->scaler_state;
>> int num_scaler_users = hweight32(scaler_state->scaler_users);
>> - int chroma_downscaling_factor =
>> skl_scaler_chroma_downscale_factor(crtc_state);
>> + u64 hscale_k[ARRAY_SIZE(scaler_state->scalers)];
>> + u64 vscale_k[ARRAY_SIZE(scaler_state->scalers)];
>> u32 dsc_prefill_latency = 0;
>>
>> if (!crtc_state->dsc.compression_enable || @@ -2191,18 +2192,16
>> @@ dsc_prefill_latency(const struct intel_crtc_state *crtc_state, int linetime)
>> num_scaler_users > crtc->num_scalers)
>> return dsc_prefill_latency;
>>
>> - dsc_prefill_latency = DIV_ROUND_UP(15 * linetime *
>> chroma_downscaling_factor, 10);
>> -
>> for (int i = 0; i < num_scaler_users; i++) {
>> - u64 hscale_k, vscale_k;
>> -
>> - hscale_k = max(1000, mul_u32_u32(scaler_state-
>>> scalers[i].hscale, 1000) >> 16);
>> - vscale_k = max(1000, mul_u32_u32(scaler_state-
>>> scalers[i].vscale, 1000) >> 16);
>> - dsc_prefill_latency = DIV_ROUND_UP_ULL(dsc_prefill_latency
>> * hscale_k * vscale_k,
>> - 1000000);
>> + hscale_k[i] = max(1000, mul_u32_u32(scaler_state-
>>> scalers[i].hscale, 1000) >> 16);
>> + vscale_k[i] = max(1000, mul_u32_u32(scaler_state-
>>> scalers[i].vscale,
>> +1000) >> 16);
>> }
>>
>> - dsc_prefill_latency *= cdclk_prefill_adjustment(crtc_state);
>> + dsc_prefill_latency =
>> + intel_display_dsc_prefill_latency(num_scaler_users, hscale_k,
>> vscale_k,
>> + chroma_downscaling_factor,
>> +
>> cdclk_prefill_adjustment(crtc_state),
>> + linetime);
>>
>> return dsc_prefill_latency;
>> }
>> @@ -2210,28 +2209,25 @@ dsc_prefill_latency(const struct intel_crtc_state
>> *crtc_state, int linetime) static int scaler_prefill_latency(const struct
>> intel_crtc_state *crtc_state, int linetime) {
>> - const struct intel_crtc_scaler_state *scaler_state =
>> - &crtc_state->scaler_state;
>> + const struct intel_crtc_scaler_state *scaler_state = &crtc_state-
>>> scaler_state;
>> + int chroma_downscaling_factor =
>> +skl_scaler_chroma_downscale_factor(crtc_state);
>> int num_scaler_users = hweight32(scaler_state->scaler_users);
>> + u64 hscale_k = 1000, vscale_k = 1000;
> This could be initialized to 0 ?
>
> As further going, you are already assigning to max 1000 when even 1 scaler is being used, also intel_display_scaler_prefill_latency we are again redundantly check for number scaler presence
>
> this could be avoided if initialised to 0 and assigning to max when scaler users presence is found ?
Makes sense. Will change this in the next version.
Regards,
Ankit
>
> also in
>> int scaler_prefill_latency = 0;
>>
>> 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 =
>> skl_scaler_chroma_downscale_factor(crtc_state);
>> - int latency;
>> -
>> - latency = DIV_ROUND_UP_ULL((4 * linetime * hscale_k *
>> vscale_k *
>> - chroma_downscaling_factor),
>> 1000000);
>> - scaler_prefill_latency += latency;
>> + hscale_k = max(1000, mul_u32_u32(scaler_state-
>>> scalers[0].hscale, 1000) >> 16);
>> + vscale_k = max(1000, mul_u32_u32(scaler_state-
>>> scalers[0].vscale,
>> +1000) >> 16);
>> }
>>
>> - scaler_prefill_latency *= cdclk_prefill_adjustment(crtc_state);
>> + scaler_prefill_latency =
>> + intel_display_scaler_prefill_latency(num_scaler_users,
>> hscale_k, vscale_k,
>> +
>> chroma_downscaling_factor,
>> +
>> cdclk_prefill_adjustment(crtc_state),
>> + linetime);
>>
>> return scaler_prefill_latency;
>> }
>> --
>> 2.45.2
More information about the Intel-xe
mailing list