public inbox for intel-xe@lists.freedesktop.org
 help / color / mirror / Atom feed
From: "Govindapillai, Vinod" <vinod.govindapillai@intel.com>
To: "ville.syrjala@linux.intel.com" <ville.syrjala@linux.intel.com>,
	"intel-gfx@lists.freedesktop.org"
	<intel-gfx@lists.freedesktop.org>
Cc: "intel-xe@lists.freedesktop.org" <intel-xe@lists.freedesktop.org>
Subject: Re: [PATCH 9/9] drm/i915/wm: Allow SAGV with multiple pipes on pre-icl
Date: Wed, 8 Apr 2026 12:10:33 +0000	[thread overview]
Message-ID: <bc2ec020b57fc3a68dc00862aabdab6458901914.camel@intel.com> (raw)
In-Reply-To: <20260324134843.2364-10-ville.syrjala@linux.intel.com>

On Tue, 2026-03-24 at 15:48 +0200, Ville Syrjala wrote:
> From: Ville Syrjälä <ville.syrjala@linux.intel.com>
> 
> There was never any documented reason for limiting SAGV to
> single active pipe configuration on pre-icl. Allow SAGV
> with multiple active pipes.
> 
> At least my CFL NUC seems happy with this when using
> multiple displays. The machine actually has working
> SAGV because the memory clock can be observed changing
> via SA_PERF_STATUS/mchbar:0x5918.
> 
> Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
> ---
>  drivers/gpu/drm/i915/display/intel_bw.c | 40 -----------------------
> --
>  1 file changed, 40 deletions(-)
> 

Reviewed-by: Vinod Govindapillai <vinod.govindapillai@intel.com>

> diff --git a/drivers/gpu/drm/i915/display/intel_bw.c
> b/drivers/gpu/drm/i915/display/intel_bw.c
> index 07b4531a4376..bf7683ddcb67 100644
> --- a/drivers/gpu/drm/i915/display/intel_bw.c
> +++ b/drivers/gpu/drm/i915/display/intel_bw.c
> @@ -28,9 +28,6 @@ struct intel_bw_state {
>  	 */
>  	u8 pipe_sagv_reject;
>  
> -	/* bitmask of active pipes */
> -	u8 active_pipes;
> -
>  	/*
>  	 * From MTL onwards, to lock a QGV point, punit expects the
> peak BW of
>  	 * the selected QGV point as the parameter in multiples of
> 100MB/s
> @@ -1265,31 +1262,6 @@ static int intel_bw_check_data_rate(struct
> intel_atomic_state *state, bool *chan
>  	return 0;
>  }
>  
> -static int intel_bw_modeset_checks(struct intel_atomic_state *state)
> -{
> -	const struct intel_bw_state *old_bw_state;
> -	struct intel_bw_state *new_bw_state;
> -	int ret;
> -
> -	if (!intel_any_crtc_active_changed(state))
> -		return 0;
> -
> -	new_bw_state = intel_atomic_get_bw_state(state);
> -	if (IS_ERR(new_bw_state))
> -		return PTR_ERR(new_bw_state);
> -
> -	old_bw_state = intel_atomic_get_old_bw_state(state);
> -
> -	new_bw_state->active_pipes =
> -		intel_calc_active_pipes(state, old_bw_state-
> >active_pipes);
> -
> -	ret = intel_atomic_lock_global_state(&new_bw_state->base);
> -	if (ret)
> -		return ret;
> -
> -	return 0;
> -}
> -
>  static int intel_bw_check_sagv_mask(struct intel_atomic_state
> *state)
>  {
>  	struct intel_display *display = to_intel_display(state);
> @@ -1346,10 +1318,6 @@ int intel_bw_atomic_check(struct
> intel_atomic_state *state)
>  	if (DISPLAY_VER(display) < 9)
>  		return 0;
>  
> -	ret = intel_bw_modeset_checks(state);
> -	if (ret)
> -		return ret;
> -
>  	ret = intel_bw_check_sagv_mask(state);
>  	if (ret)
>  		return ret;
> @@ -1410,7 +1378,6 @@ void intel_bw_update_hw_state(struct
> intel_display *display)
>  	if (DISPLAY_VER(display) < 9)
>  		return;
>  
> -	bw_state->active_pipes = 0;
>  	bw_state->pipe_sagv_reject = 0;
>  
>  	for_each_intel_crtc(display->drm, crtc) {
> @@ -1418,9 +1385,6 @@ void intel_bw_update_hw_state(struct
> intel_display *display)
>  			to_intel_crtc_state(crtc->base.state);
>  		enum pipe pipe = crtc->pipe;
>  
> -		if (crtc_state->hw.active)
> -			bw_state->active_pipes |= BIT(pipe);
> -
>  		if (DISPLAY_VER(display) >= 11)
>  			intel_bw_crtc_update(bw_state, crtc_state);
>  
> @@ -1504,10 +1468,6 @@ bool intel_bw_pmdemand_needs_update(struct
> intel_atomic_state *state)
>  bool intel_bw_can_enable_sagv(struct intel_display *display,
>  			      const struct intel_bw_state *bw_state)
>  {
> -	if (DISPLAY_VER(display) < 11 &&
> -	    bw_state->active_pipes && !is_power_of_2(bw_state-
> >active_pipes))
> -		return false;
> -
>  	return bw_state->pipe_sagv_reject == 0;
>  }
>  


  reply	other threads:[~2026-04-08 12:10 UTC|newest]

Thread overview: 23+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-03-24 13:48 [PATCH 0/9] drm/i915/wm: Watermark/SAGV fixes/cleanups/etc Ville Syrjala
2026-03-24 13:48 ` [PATCH 1/9] drm/i915/wm: Reject SAGV consistently when block_time_us==0 Ville Syrjala
2026-04-08  9:56   ` Govindapillai, Vinod
2026-03-24 13:48 ` [PATCH 2/9] drm/i915/wm: Don't compute separate SAGV watermarks for RKL Ville Syrjala
2026-04-08 11:48   ` Govindapillai, Vinod
2026-03-24 13:48 ` [PATCH 3/9] drm/i915/wm: Consolidate SAGV pipe active/interlace checks to common code Ville Syrjala
2026-04-08 11:49   ` Govindapillai, Vinod
2026-03-24 13:48 ` [PATCH 4/9] drm/i915/wm: Verify the correct plane DDB entry Ville Syrjala
2026-04-08 11:53   ` Govindapillai, Vinod
2026-03-24 13:48 ` [PATCH 5/9] drm/i915/wm: Extract skl_wm_level_verify() Ville Syrjala
2026-04-08 11:55   ` Govindapillai, Vinod
2026-03-24 13:48 ` [PATCH 6/9] drm/i915/wm: Extract skl_ddb_entry_verify() Ville Syrjala
2026-04-08 11:57   ` Govindapillai, Vinod
2026-03-24 13:48 ` [PATCH 7/9] drm/i915/wm: Verify 'ddb_y' as well as 'ddb' Ville Syrjala
2026-04-08 11:59   ` Govindapillai, Vinod
2026-03-24 13:48 ` [PATCH 8/9] drm/i915/wm: Reduce copy-pasta in skl_print_plane_wm_changes() Ville Syrjala
2026-04-08 12:04   ` Govindapillai, Vinod
2026-03-24 13:48 ` [PATCH 9/9] drm/i915/wm: Allow SAGV with multiple pipes on pre-icl Ville Syrjala
2026-04-08 12:10   ` Govindapillai, Vinod [this message]
2026-03-24 13:58 ` ✗ CI.checkpatch: warning for drm/i915/wm: Watermark/SAGV fixes/cleanups/etc Patchwork
2026-03-24 14:00 ` ✓ CI.KUnit: success " Patchwork
2026-03-24 14:40 ` ✓ Xe.CI.BAT: " Patchwork
2026-03-25  2:08 ` ✓ Xe.CI.FULL: " Patchwork

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=bc2ec020b57fc3a68dc00862aabdab6458901914.camel@intel.com \
    --to=vinod.govindapillai@intel.com \
    --cc=intel-gfx@lists.freedesktop.org \
    --cc=intel-xe@lists.freedesktop.org \
    --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