From: "Nautiyal, Ankit K" <ankit.k.nautiyal@intel.com>
To: "Golani,
Mitulkumar Ajitkumar" <mitulkumar.ajitkumar.golani@intel.com>,
"intel-gfx@lists.freedesktop.org"
<intel-gfx@lists.freedesktop.org>,
"intel-xe@lists.freedesktop.org" <intel-xe@lists.freedesktop.org>
Cc: "ville.syrjala@linux.intel.com" <ville.syrjala@linux.intel.com>,
"jani.nikula@linux.intel.com" <jani.nikula@linux.intel.com>
Subject: Re: [PATCH 04/12] drm/i915/display: Extract helpers to set dsc/scaler prefill latencies
Date: Mon, 18 Aug 2025 11:39:09 +0530 [thread overview]
Message-ID: <5bf4ef6e-cafe-4f7f-aa9b-5deb80fab6ba@intel.com> (raw)
In-Reply-To: <IA1PR11MB63482583ED9773132E155F73B228A@IA1PR11MB6348.namprd11.prod.outlook.com>
On 8/11/2025 11:46 AM, Golani, Mitulkumar Ajitkumar wrote:
>
>> -----Original Message-----
>> From: Nautiyal, Ankit K <ankit.k.nautiyal@intel.com>
>> Sent: 07 August 2025 16:46
>> To: intel-gfx@lists.freedesktop.org; intel-xe@lists.freedesktop.org
>> Cc: ville.syrjala@linux.intel.com; jani.nikula@linux.intel.com; Golani,
>> Mitulkumar Ajitkumar <mitulkumar.ajitkumar.golani@intel.com>; Nautiyal,
>> Ankit K <ankit.k.nautiyal@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@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
next prev parent reply other threads:[~2025-08-18 6:09 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-08-07 11:15 [PATCH 00/12] Optimize vrr.guardband and fix LRR Ankit Nautiyal
2025-08-07 11:15 ` [PATCH 01/12] drm/i915/skl_watermark: Fix the scaling factor for chroma subsampling Ankit Nautiyal
2025-08-07 15:26 ` Golani, Mitulkumar Ajitkumar
2025-08-07 11:15 ` [PATCH 02/12] drm/i915/skl_watermark: Pass linetime as argument to latency helpers Ankit Nautiyal
2025-08-07 16:19 ` Golani, Mitulkumar Ajitkumar
2025-08-07 11:15 ` [PATCH 03/12] drm/i915/skl_scaler: Introduce helper for chroma downscale factor Ankit Nautiyal
2025-08-07 16:29 ` Golani, Mitulkumar Ajitkumar
2025-08-07 11:15 ` [PATCH 04/12] drm/i915/display: Extract helpers to set dsc/scaler prefill latencies Ankit Nautiyal
2025-08-11 6:16 ` Golani, Mitulkumar Ajitkumar
2025-08-18 6:09 ` Nautiyal, Ankit K [this message]
2025-08-07 11:15 ` [PATCH 05/12] drm/i915/dp: Add SDP latency computation helper Ankit Nautiyal
2025-08-07 11:15 ` [PATCH 06/12] drm/i915/alpm: Add function to compute max link-wake latency Ankit Nautiyal
2025-08-07 11:15 ` [PATCH 07/12] drm/i915/vrr: Use vrr.sync_start for getting vtotal Ankit Nautiyal
2025-08-07 17:01 ` Golani, Mitulkumar Ajitkumar
2025-08-07 11:15 ` [PATCH 08/12] drm/i915/display: Add guardband check for feature latencies Ankit Nautiyal
2025-08-11 9:11 ` Golani, Mitulkumar Ajitkumar
2025-08-18 6:01 ` Nautiyal, Ankit K
2025-08-11 9:59 ` Golani, Mitulkumar Ajitkumar
2025-08-18 6:00 ` Nautiyal, Ankit K
2025-08-11 15:14 ` Jani Nikula
2025-08-18 6:02 ` Nautiyal, Ankit K
2025-08-07 11:15 ` [PATCH 09/12] drm/i915/skl_watermark: Remove redundant latency checks from vblank validation Ankit Nautiyal
2025-08-07 17:03 ` Golani, Mitulkumar Ajitkumar
2025-08-07 11:15 ` [PATCH 10/12] drm/i915/vrr: Use static guardband to support seamless LRR switching Ankit Nautiyal
2025-08-07 11:15 ` [PATCH 11/12] drm/i915/panel: Add helper to get highest fixed mode Ankit Nautiyal
2025-08-11 15:22 ` Jani Nikula
2025-08-18 6:15 ` Nautiyal, Ankit K
2025-08-07 11:15 ` [PATCH 12/12] drm/i915/vrr: Fix seamless_mn drrs for PTL Ankit Nautiyal
2025-08-07 12:22 ` ✓ i915.CI.BAT: success for Optimize vrr.guardband and fix LRR (rev4) Patchwork
2025-08-07 16:31 ` ✓ i915.CI.Full: " Patchwork
-- strict thread matches above, loose matches on Subject: below --
2025-08-18 7:31 [PATCH 00/12] Optimize vrr.guardband and fix LRR Ankit Nautiyal
2025-08-18 7:31 ` [PATCH 04/12] drm/i915/display: Extract helpers to set dsc/scaler prefill latencies Ankit Nautiyal
2025-08-18 10:37 ` Golani, Mitulkumar Ajitkumar
2025-08-20 8:04 [PATCH 00/12] Optimize vrr.guardband and fix LRR Ankit Nautiyal
2025-08-20 8:04 ` [PATCH 04/12] drm/i915/display: Extract helpers to set dsc/scaler prefill latencies Ankit Nautiyal
2025-08-22 11:23 ` Jani Nikula
2025-08-24 4:36 ` Nautiyal, Ankit K
2025-08-25 12:55 ` Nautiyal, Ankit K
2025-08-25 12:35 [PATCH 00/12] Optimize vrr.guardband and fix LRR Ankit Nautiyal
2025-08-25 12:35 ` [PATCH 04/12] drm/i915/display: Extract helpers to set dsc/scaler prefill latencies Ankit Nautiyal
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=5bf4ef6e-cafe-4f7f-aa9b-5deb80fab6ba@intel.com \
--to=ankit.k.nautiyal@intel.com \
--cc=intel-gfx@lists.freedesktop.org \
--cc=intel-xe@lists.freedesktop.org \
--cc=jani.nikula@linux.intel.com \
--cc=mitulkumar.ajitkumar.golani@intel.com \
--cc=ville.syrjala@linux.intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).