From: Deepak S <deepak.s@linux.intel.com>
To: Chris Wilson <chris@chris-wilson.co.uk>, intel-gfx@lists.freedesktop.org
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>,
Rodrigo Vivi <rodrigo.vivi@intel.com>
Subject: Re: [PATCH 5/7] drm/i915: Agressive downclocking on Baytrail
Date: Wed, 18 Mar 2015 13:42:58 +0530 [thread overview]
Message-ID: <5509338A.9060309@linux.intel.com> (raw)
In-Reply-To: <1425654391-2126-5-git-send-email-chris@chris-wilson.co.uk>
On Friday 06 March 2015 08:36 PM, Chris Wilson wrote:
> Reuse the same reclocking strategy for Baytail as on its bigger brethren,
> Sandybridge and Ivybridge. In particular, this makes the device quicker
> to reclock (both up and down) though the tendency now is to downclock
> more aggressively to compensate for the RPS boosts.
>
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> Cc: Deepak S <deepak.s@linux.intel.com>
> Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
> Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
>
> Conflicts:
> drivers/gpu/drm/i915/intel_pm.c
> ---
> drivers/gpu/drm/i915/i915_drv.h | 3 +++
> drivers/gpu/drm/i915/i915_irq.c | 4 ++--
> drivers/gpu/drm/i915/i915_reg.h | 2 --
> drivers/gpu/drm/i915/intel_pm.c | 11 ++++++++++-
> 4 files changed, 15 insertions(+), 5 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> index efa98c9e5777..bfa6e11f802e 100644
> --- a/drivers/gpu/drm/i915/i915_drv.h
> +++ b/drivers/gpu/drm/i915/i915_drv.h
> @@ -1028,6 +1028,9 @@ struct intel_gen6_power_mgmt {
> u8 rp0_freq; /* Non-overclocked max frequency. */
> u32 cz_freq;
>
> + u8 up_threshold; /* Current %busy required to uplock */
> + u8 down_threshold; /* Current %busy required to downclock */
> +
> int last_adj;
> enum { LOW_POWER, BETWEEN, HIGH_POWER } power;
>
> diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
> index 8892dbdfb629..483079d96957 100644
> --- a/drivers/gpu/drm/i915/i915_irq.c
> +++ b/drivers/gpu/drm/i915/i915_irq.c
> @@ -1050,7 +1050,7 @@ static u32 vlv_wa_c0_ei(struct drm_i915_private *dev_priv, u32 pm_iir)
> if (pm_iir & GEN6_PM_RP_DOWN_EI_EXPIRED) {
> if (!vlv_c0_above(dev_priv,
> &dev_priv->rps.down_ei, &now,
> - VLV_RP_DOWN_EI_THRESHOLD))
> + dev_priv->rps.down_threshold))
> events |= GEN6_PM_RP_DOWN_THRESHOLD;
> dev_priv->rps.down_ei = now;
> }
> @@ -1058,7 +1058,7 @@ static u32 vlv_wa_c0_ei(struct drm_i915_private *dev_priv, u32 pm_iir)
> if (pm_iir & GEN6_PM_RP_UP_EI_EXPIRED) {
> if (vlv_c0_above(dev_priv,
> &dev_priv->rps.up_ei, &now,
> - VLV_RP_UP_EI_THRESHOLD))
> + dev_priv->rps.up_threshold))
> events |= GEN6_PM_RP_UP_THRESHOLD;
> dev_priv->rps.up_ei = now;
> }
> diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
> index ca24a2d4a823..13ec6c2b1fcf 100644
> --- a/drivers/gpu/drm/i915/i915_reg.h
> +++ b/drivers/gpu/drm/i915/i915_reg.h
> @@ -663,8 +663,6 @@ enum skl_disp_power_wells {
> #define FB_FMAX_VMIN_FREQ_LO_MASK 0xf8000000
>
> #define VLV_CZ_CLOCK_TO_MILLI_SEC 100000
> -#define VLV_RP_UP_EI_THRESHOLD 90
> -#define VLV_RP_DOWN_EI_THRESHOLD 70
>
> /* vlv2 north clock has */
> #define CCK_FUSE_REG 0x8
> diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
> index 55dc406cd195..972333d2211d 100644
> --- a/drivers/gpu/drm/i915/intel_pm.c
> +++ b/drivers/gpu/drm/i915/intel_pm.c
> @@ -3722,10 +3722,12 @@ static void gen6_set_rps_thresholds(struct drm_i915_private *dev_priv, u8 val)
> switch (new_power) {
> case LOW_POWER:
> /* Upclock if more than 95% busy over 16ms */
> + dev_priv->rps.up_threshold = 95;
> I915_WRITE(GEN6_RP_UP_EI, 12500);
> I915_WRITE(GEN6_RP_UP_THRESHOLD, 11800);
>
> /* Downclock if less than 85% busy over 32ms */
> + dev_priv->rps.down_threshold = 85;
> I915_WRITE(GEN6_RP_DOWN_EI, 25000);
> I915_WRITE(GEN6_RP_DOWN_THRESHOLD, 21250);
>
> @@ -3740,10 +3742,12 @@ static void gen6_set_rps_thresholds(struct drm_i915_private *dev_priv, u8 val)
>
> case BETWEEN:
> /* Upclock if more than 90% busy over 13ms */
> + dev_priv->rps.up_threshold = 90;
> I915_WRITE(GEN6_RP_UP_EI, 10250);
> I915_WRITE(GEN6_RP_UP_THRESHOLD, 9225);
>
> /* Downclock if less than 75% busy over 32ms */
> + dev_priv->rps.down_threshold = 75;
> I915_WRITE(GEN6_RP_DOWN_EI, 25000);
> I915_WRITE(GEN6_RP_DOWN_THRESHOLD, 18750);
>
> @@ -3758,10 +3762,12 @@ static void gen6_set_rps_thresholds(struct drm_i915_private *dev_priv, u8 val)
>
> case HIGH_POWER:
> /* Upclock if more than 85% busy over 10ms */
> + dev_priv->rps.up_threshold = 85;
> I915_WRITE(GEN6_RP_UP_EI, 8000);
> I915_WRITE(GEN6_RP_UP_THRESHOLD, 6800);
>
> /* Downclock if less than 60% busy over 32ms */
> + dev_priv->rps.down_threshold = 60;
> I915_WRITE(GEN6_RP_DOWN_EI, 25000);
> I915_WRITE(GEN6_RP_DOWN_THRESHOLD, 15000);
>
> @@ -3842,8 +3848,10 @@ static void valleyview_set_rps(struct drm_device *dev, u8 val)
> "Odd GPU freq value\n"))
> val &= ~1;
>
> - if (val != dev_priv->rps.cur_freq)
> + if (val != dev_priv->rps.cur_freq) {
> vlv_punit_write(dev_priv, PUNIT_REG_GPU_FREQ_REQ, val);
> + gen6_set_rps_thresholds(dev_priv, val);
> If only for BYT, we might want to add a platform check before "gen6_set_rps_thresholds"
> + }
>
> I915_WRITE(GEN6_PMINTRMSK, gen6_rps_pm_mask(dev_priv, val));
>
> @@ -3892,6 +3900,7 @@ static void vlv_set_rps_idle(struct drm_i915_private *dev_priv)
> & GENFREQSTATUS) == 0, 100))
> DRM_ERROR("timed out waiting for Punit\n");
>
> + gen6_set_rps_thresholds(dev_priv, val);
> vlv_force_gfx_clock(dev_priv, false);
>
> I915_WRITE(GEN6_PMINTRMSK, gen6_rps_pm_mask(dev_priv, val));
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
next prev parent reply other threads:[~2015-03-18 8:17 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-03-06 15:06 [PATCH 1/7] drm/i915: Relax RPS contraints to allows setting minfreq on idle Chris Wilson
2015-03-06 15:06 ` [PATCH 2/7] drm/i915: Fix computation of last_adjustment for RPS autotuning Chris Wilson
2015-03-06 17:32 ` Daniel Vetter
2015-03-06 21:44 ` Chris Wilson
2015-03-18 6:56 ` Deepak S
2015-03-18 9:05 ` Chris Wilson
2015-03-18 9:20 ` Chris Wilson
2015-03-18 11:09 ` Deepak S
2015-03-06 15:06 ` [PATCH 3/7] drm/i915: Improved w/a for rps on Baytrail Chris Wilson
2015-03-18 7:56 ` Deepak S
2015-03-06 15:06 ` [PATCH 4/7] drm/i915: Use down ei for manual Baytrail RPS calculations Chris Wilson
2015-03-18 8:04 ` Deepak S
2015-03-06 15:06 ` [PATCH 5/7] drm/i915: Agressive downclocking on Baytrail Chris Wilson
2015-03-18 8:12 ` Deepak S [this message]
2015-03-18 9:48 ` Daniel Vetter
2015-03-18 9:49 ` Chris Wilson
2015-03-18 11:06 ` Deepak S
2015-03-06 15:06 ` [PATCH 6/7] drm/i915: Boost GPU frequency if we detect outstanding pageflips Chris Wilson
2015-03-18 8:18 ` Deepak S
2015-03-18 8:20 ` Deepak S
2015-03-06 15:06 ` [PATCH 7/7] drm/i915: Deminish contribution of wait-boosting from clients Chris Wilson
2015-03-06 17:58 ` shuang.he
2015-03-18 9:00 ` Deepak S
2015-03-09 15:38 ` [PATCH 1/7] drm/i915: Relax RPS contraints to allows setting minfreq on idle Jesse Barnes
2015-03-18 5:44 ` Deepak S
2015-03-18 9:07 ` Chris Wilson
2015-03-18 5:52 ` Deepak S
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=5509338A.9060309@linux.intel.com \
--to=deepak.s@linux.intel.com \
--cc=chris@chris-wilson.co.uk \
--cc=daniel.vetter@ffwll.ch \
--cc=intel-gfx@lists.freedesktop.org \
--cc=rodrigo.vivi@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