public inbox for intel-gfx@lists.freedesktop.org
 help / color / mirror / Atom feed
From: Matt Roper <matthew.d.roper@intel.com>
To: Radhakrishna Sripada <radhakrishna.sripada@intel.com>
Cc: intel-gfx@lists.freedesktop.org
Subject: Re: [Intel-gfx] [PATCH 16/23] drm/i915/mtl: Update memory bandwidth parameters
Date: Tue, 2 Aug 2022 09:52:07 -0700	[thread overview]
Message-ID: <YulWNwSyGlk/SB3A@mdroper-desk1.amr.corp.intel.com> (raw)
In-Reply-To: <20220728013420.3750388-17-radhakrishna.sripada@intel.com>

On Wed, Jul 27, 2022 at 06:34:13PM -0700, Radhakrishna Sripada wrote:
> Like ADL_P, Meteorlake has different memory characteristics from
> past platforms. Update the values used by our memory bandwidth
> calculations accordingly.
> 
> Bspec: 64631
> 
> Cc: Matt Roper <matthew.d.roper@intel.com>
> Cc: Caz Yokoyama <caz.yokoyama@intel.com>
> Signed-off-by: Radhakrishna Sripada <radhakrishna.sripada@intel.com>
> Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
> ---
>  drivers/gpu/drm/i915/display/intel_bw.c | 42 ++++++++++++++++++++++---
>  1 file changed, 38 insertions(+), 4 deletions(-)
> 
> diff --git a/drivers/gpu/drm/i915/display/intel_bw.c b/drivers/gpu/drm/i915/display/intel_bw.c
> index 8bbf47da1716..447a15f2c18a 100644
> --- a/drivers/gpu/drm/i915/display/intel_bw.c
> +++ b/drivers/gpu/drm/i915/display/intel_bw.c
> @@ -178,7 +178,32 @@ static int icl_get_qgv_points(struct drm_i915_private *dev_priv,
>  	qi->num_points = dram_info->num_qgv_points;
>  	qi->num_psf_points = dram_info->num_psf_gv_points;
>  
> -	if (DISPLAY_VER(dev_priv) >= 12)
> +	if (DISPLAY_VER(dev_priv) >= 14) {
> +		switch (dram_info->type) {
> +		case INTEL_DRAM_DDR4:
> +			qi->t_bl = 4;
> +			qi->max_numchannels = 2;
> +			qi->channel_width = 64;
> +			qi->deinterleave = 2;
> +			break;
> +		case INTEL_DRAM_DDR5:
> +			qi->t_bl = 8;
> +			qi->max_numchannels = 4;
> +			qi->channel_width = 32;
> +			qi->deinterleave = 2;
> +			break;
> +		case INTEL_DRAM_LPDDR4:
> +		case INTEL_DRAM_LPDDR5:
> +			qi->t_bl = 16;
> +			qi->max_numchannels = 8;
> +			qi->channel_width = 16;
> +			qi->deinterleave = 4;
> +			break;
> +		default:
> +			MISSING_CASE(dram_info->type);
> +			return -EINVAL;
> +		}
> +	} else if (DISPLAY_VER(dev_priv) >= 12) {
>  		switch (dram_info->type) {
>  		case INTEL_DRAM_DDR4:
>  			qi->t_bl = is_y_tile ? 8 : 4;
> @@ -212,7 +237,7 @@ static int icl_get_qgv_points(struct drm_i915_private *dev_priv,
>  			qi->max_numchannels = 1;
>  			break;
>  		}
> -	else if (DISPLAY_VER(dev_priv) == 11) {
> +	} else if (DISPLAY_VER(dev_priv) == 11) {
>  		qi->t_bl = dev_priv->dram_info.type == INTEL_DRAM_DDR4 ? 4 : 8;
>  		qi->max_numchannels = 1;
>  	}
> @@ -311,6 +336,13 @@ static const struct intel_sa_info adlp_sa_info = {
>  	.derating = 20,
>  };
>  
> +static const struct intel_sa_info mtl_sa_info = {
> +	.deburst = 32,
> +	.deprogbwlimit = 38, /* GB/s */
> +	.displayrtids = 256,
> +	.derating = 20,
> +};
> +
>  static int icl_get_bw_info(struct drm_i915_private *dev_priv, const struct intel_sa_info *sa)
>  {
>  	struct intel_qgv_info qi = {};
> @@ -585,9 +617,11 @@ void intel_bw_init_hw(struct drm_i915_private *dev_priv)
>  	if (!HAS_DISPLAY(dev_priv))
>  		return;
>  
> -	if (IS_DG2(dev_priv))
> +	if (DISPLAY_VER(dev_priv) >= 14)
> +		tgl_get_bw_info(dev_priv, &mtl_sa_info);
> +	else if (IS_DG2(dev_priv))
>  		dg2_get_bw_info(dev_priv);
> -	else if (DISPLAY_VER(dev_priv) >= 13 || IS_ALDERLAKE_P(dev_priv))
> +	else if (IS_ALDERLAKE_P(dev_priv))

Here you're undoing the change from the previous patch.  If you drop the
unwanted change from the previous patch and rebase the real changes here
accordingly,

Reviewed-by: Matt Roper <matthew.d.roper@intel.com>

>  		tgl_get_bw_info(dev_priv, &adlp_sa_info);
>  	else if (IS_ALDERLAKE_S(dev_priv))
>  		tgl_get_bw_info(dev_priv, &adls_sa_info);
> -- 
> 2.25.1
> 

-- 
Matt Roper
Graphics Software Engineer
VTT-OSGC Platform Enablement
Intel Corporation

  reply	other threads:[~2022-08-02 16:53 UTC|newest]

Thread overview: 56+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-07-28  1:33 [Intel-gfx] [PATCH 00/23] Initial Meteorlake Support Radhakrishna Sripada
2022-07-28  1:33 ` [Intel-gfx] [PATCH 01/23] drm/i915: Read graphics/media/display arch version from hw Radhakrishna Sripada
2022-07-28  3:46   ` [Intel-gfx] [v1.1 " Radhakrishna Sripada
2022-08-10 11:02     ` Jani Nikula
2022-08-10 13:23       ` Jani Nikula
2022-08-18 14:58     ` Balasubramani Vivekanandan
2022-07-28  1:33 ` [Intel-gfx] [PATCH 02/23] drm/i915: Parse and set stepping for platforms with GMD Radhakrishna Sripada
2022-07-28  1:34 ` [Intel-gfx] [PATCH 03/23] drm/i915/mtl: MMIO range is now 4MB Radhakrishna Sripada
2022-07-28  1:34 ` [Intel-gfx] [PATCH 04/23] drm/i915/mtl: Don't mask off CCS according to DSS fusing Radhakrishna Sripada
2022-07-28  1:34 ` [Intel-gfx] [PATCH 05/23] drm/i915/mtl: Define engine context layouts Radhakrishna Sripada
2022-07-28  1:34 ` [Intel-gfx] [PATCH 06/23] drm/i915/mtl: Add PCH support Radhakrishna Sripada
2022-07-28 21:28   ` Srivatsa, Anusha
2022-07-28  1:34 ` [Intel-gfx] [PATCH 07/23] drm/i915/mtl: Add gmbus and gpio support Radhakrishna Sripada
2022-08-01 21:33   ` Matt Roper
2022-07-28  1:34 ` [Intel-gfx] [PATCH 08/23] drm/i915/mtl: Add VBT port and AUX_CH mapping Radhakrishna Sripada
2022-08-01 21:45   ` Matt Roper
2022-07-28  1:34 ` [Intel-gfx] [PATCH 09/23] drm/i915/mtl: Add support for MTL in Display Init sequences Radhakrishna Sripada
2022-08-01 21:49   ` Matt Roper
2022-07-28  1:34 ` [Intel-gfx] [PATCH 10/23] drm/i915/mtl: Add display power wells Radhakrishna Sripada
2022-08-02  1:23   ` Matt Roper
2022-08-02 15:40     ` Matt Roper
2022-07-28  1:34 ` [Intel-gfx] [PATCH 11/23] drm/i915/mtl: Add DP AUX support on TypeC ports Radhakrishna Sripada
2022-08-02 15:41   ` Matt Roper
2022-07-28  1:34 ` [Intel-gfx] [PATCH 12/23] drm/i915/mtl: Fix rawclk for Meteorlake PCH Radhakrishna Sripada
2022-08-02  3:28   ` Matt Roper
2022-08-02  3:36     ` Caz Yokoyama
2022-07-28  1:34 ` [Intel-gfx] [PATCH 13/23] drm/i915/mtl: memory latency data from LATENCY_LPX_LPY for WM Radhakrishna Sripada
2022-08-02 16:12   ` Matt Roper
2022-08-10 11:09     ` Jani Nikula
2022-08-10 11:10       ` Jani Nikula
2022-07-28  1:34 ` [Intel-gfx] [PATCH 14/23] drm/i915/mtl: Add CDCLK Support Radhakrishna Sripada
2022-07-28  1:34 ` [Intel-gfx] [PATCH 15/23] drm/i915/mtl: Obtain SAGV values from MMIO instead of GT pcode mailbox Radhakrishna Sripada
2022-08-02 16:43   ` Matt Roper
2022-08-02 16:53   ` Caz Yokoyama
2022-08-10 11:14   ` Jani Nikula
2022-07-28  1:34 ` [Intel-gfx] [PATCH 16/23] drm/i915/mtl: Update memory bandwidth parameters Radhakrishna Sripada
2022-08-02 16:52   ` Matt Roper [this message]
2022-07-28  1:34 ` [Intel-gfx] [PATCH 17/23] drm/i915/mtl: Update MBUS_DBOX credits Radhakrishna Sripada
2022-08-02 17:14   ` Matt Roper
2022-08-03 13:55   ` Balasubramani Vivekanandan
2022-07-28  1:34 ` [Intel-gfx] [PATCH 18/23] drm/i915/mtl: DBUF handling is same as adlp Radhakrishna Sripada
2022-08-02 17:35   ` Matt Roper
2022-07-28  1:34 ` [Intel-gfx] [PATCH 19/23] drm/i915/display/mtl: Extend MBUS programming Radhakrishna Sripada
2022-08-02 17:39   ` Matt Roper
2022-07-28  1:34 ` [Intel-gfx] [PATCH 20/23] drm/i915/dmc: Load DMC on MTL Radhakrishna Sripada
2022-08-02 18:00   ` Matt Roper
2022-07-28  1:34 ` [Intel-gfx] [PATCH 21/23] drm/i915/dmc: MTL DMC debugfs entries Radhakrishna Sripada
2022-08-02 18:22   ` Matt Roper
2022-08-09 18:06     ` Srivatsa, Anusha
2022-07-28  1:34 ` [Intel-gfx] [PATCH 22/23] drm/i915/mtl: Update CHICKEN_TRANS* register addresses Radhakrishna Sripada
2022-08-10 11:21   ` Jani Nikula
2022-07-28  1:34 ` [Intel-gfx] [PATCH 23/23] drm/i915/mtl: Do not update GV point, mask value Radhakrishna Sripada
2022-07-28  1:54 ` [Intel-gfx] ✗ Fi.CI.BUILD: failure for Initial Meteorlake Support Patchwork
2022-08-02  3:26 ` [Intel-gfx] [PATCH 00/23] " Matt Roper
2022-08-04  9:08 ` Jani Nikula
2022-08-04 13:10   ` Jani Nikula

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=YulWNwSyGlk/SB3A@mdroper-desk1.amr.corp.intel.com \
    --to=matthew.d.roper@intel.com \
    --cc=intel-gfx@lists.freedesktop.org \
    --cc=radhakrishna.sripada@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