From: "Ville Syrjälä" <ville.syrjala@linux.intel.com>
To: Mahesh Kumar <mahesh1.sh.kumar@gmail.com>
Cc: intel-gfx@lists.freedesktop.org
Subject: Re: [PATCH v2] drm/i915: Don't apply the 16Gb DIMM wm latency w/a to BXT/GLK
Date: Wed, 24 Oct 2018 15:26:43 +0300 [thread overview]
Message-ID: <20181024122643.GA9144@intel.com> (raw)
In-Reply-To: <CAGrStEqrbcaaSE+YAt4-0fCF2Nm+OTZkS9NPYZfUNarVXbjZ4w@mail.gmail.com>
On Wed, Oct 24, 2018 at 12:05:40PM +0530, Mahesh Kumar wrote:
> LGTM..
> Reviewed-by: Mahesh Kumar <mahesh1.sh.kumar@gmail.com>
Thanks for the reviews. Pushed to dinq.
>
> -Mahesh
> On Tue, Oct 23, 2018 at 11:52 PM Ville Syrjala
> <ville.syrjala@linux.intel.com> wrote:
> >
> > From: Ville Syrjälä <ville.syrjala@linux.intel.com>
> >
> > The 16Gb DIMM w/a is not applicable to BXT or GLK. Limit it to
> > the appropriate platforms.
> >
> > This was especially harsh on GLK since we don't even try to read
> > the DIMM information on that platforms, hence valid_dimm was
> > always false and thus we always tried to apply the w/a.
> > Furthermore the w/a pushed the level 0 latency above the
> > level 1 latency, which doesn't really make sense.
> >
> > v2: Do the check when populating is_16gb_dimm (Mahesh)
> >
> > Cc: Mahesh Kumar <mahesh1.kumar@intel.com>
> > Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
> > Fixes: 86b592876cb6 ("drm/i915: Implement 16GB dimm wa for latency level-0")
> > Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
> > ---
> > drivers/gpu/drm/i915/i915_drv.c | 15 ++++++++-------
> > drivers/gpu/drm/i915/i915_drv.h | 1 -
> > drivers/gpu/drm/i915/intel_pm.c | 3 +--
> > 3 files changed, 9 insertions(+), 10 deletions(-)
> >
> > diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
> > index baac35f698f9..6571044c9286 100644
> > --- a/drivers/gpu/drm/i915/i915_drv.c
> > +++ b/drivers/gpu/drm/i915/i915_drv.c
> > @@ -1165,8 +1165,6 @@ skl_dram_get_channels_info(struct drm_i915_private *dev_priv)
> > return -EINVAL;
> > }
> >
> > - dram_info->valid_dimm = true;
> > -
> > /*
> > * If any of the channel is single rank channel, worst case output
> > * will be same as if single rank memory, so consider single rank
> > @@ -1183,8 +1181,7 @@ skl_dram_get_channels_info(struct drm_i915_private *dev_priv)
> > return -EINVAL;
> > }
> >
> > - if (ch0.is_16gb_dimm || ch1.is_16gb_dimm)
> > - dram_info->is_16gb_dimm = true;
> > + dram_info->is_16gb_dimm = ch0.is_16gb_dimm || ch1.is_16gb_dimm;
> >
> > dev_priv->dram_info.symmetric_memory = intel_is_dram_symmetric(val_ch0,
> > val_ch1,
> > @@ -1304,7 +1301,6 @@ bxt_get_dram_info(struct drm_i915_private *dev_priv)
> > return -EINVAL;
> > }
> >
> > - dram_info->valid_dimm = true;
> > dram_info->valid = true;
> > return 0;
> > }
> > @@ -1317,12 +1313,17 @@ intel_get_dram_info(struct drm_i915_private *dev_priv)
> > int ret;
> >
> > dram_info->valid = false;
> > - dram_info->valid_dimm = false;
> > - dram_info->is_16gb_dimm = false;
> > dram_info->rank = I915_DRAM_RANK_INVALID;
> > dram_info->bandwidth_kbps = 0;
> > dram_info->num_channels = 0;
> >
> > + /*
> > + * Assume 16Gb DIMMs are present until proven otherwise.
> > + * This is only used for the level 0 watermark latency
> > + * w/a which does not apply to bxt/glk.
> > + */
> > + dram_info->is_16gb_dimm = !IS_GEN9_LP(dev_priv);
> > +
> > if (INTEL_GEN(dev_priv) < 9 || IS_GEMINILAKE(dev_priv))
> > return;
> >
> > diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> > index 22cf3c75558c..2d7761b8ac07 100644
> > --- a/drivers/gpu/drm/i915/i915_drv.h
> > +++ b/drivers/gpu/drm/i915/i915_drv.h
> > @@ -1933,7 +1933,6 @@ struct drm_i915_private {
> >
> > struct dram_info {
> > bool valid;
> > - bool valid_dimm;
> > bool is_16gb_dimm;
> > u8 num_channels;
> > enum dram_rank {
> > diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
> > index 67a4d0735291..faef7f528269 100644
> > --- a/drivers/gpu/drm/i915/intel_pm.c
> > +++ b/drivers/gpu/drm/i915/intel_pm.c
> > @@ -2881,8 +2881,7 @@ static void intel_read_wm_latency(struct drm_i915_private *dev_priv,
> > * any underrun. If not able to get Dimm info assume 16GB dimm
> > * to avoid any underrun.
> > */
> > - if (!dev_priv->dram_info.valid_dimm ||
> > - dev_priv->dram_info.is_16gb_dimm)
> > + if (dev_priv->dram_info.is_16gb_dimm)
> > wm[0] += 1;
> >
> > } else if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) {
> > --
> > 2.18.1
> >
> > _______________________________________________
> > Intel-gfx mailing list
> > Intel-gfx@lists.freedesktop.org
> > https://lists.freedesktop.org/mailman/listinfo/intel-gfx
--
Ville Syrjälä
Intel
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
next prev parent reply other threads:[~2018-10-24 12:26 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-10-10 17:53 [PATCH] drm/i915: Don't apply the 16Gb DIMM wm latency w/a to BXT/GLK Ville Syrjala
2018-10-10 18:35 ` ✓ Fi.CI.BAT: success for " Patchwork
2018-10-10 20:49 ` [PATCH] " Mahesh Kumar
2018-10-10 21:00 ` Mahesh Kumar
2018-10-11 16:05 ` Ville Syrjälä
2018-10-11 2:03 ` ✓ Fi.CI.IGT: success for " Patchwork
2018-10-23 18:21 ` [PATCH v2] " Ville Syrjala
2018-10-23 18:58 ` Rodrigo Vivi
2018-10-24 6:35 ` Mahesh Kumar
2018-10-24 12:26 ` Ville Syrjälä [this message]
2018-10-23 18:44 ` ✗ Fi.CI.SPARSE: warning for drm/i915: Don't apply the 16Gb DIMM wm latency w/a to BXT/GLK (rev2) Patchwork
2018-10-23 19:03 ` ✓ Fi.CI.BAT: success " Patchwork
2018-10-23 21:27 ` ✓ Fi.CI.IGT: " 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=20181024122643.GA9144@intel.com \
--to=ville.syrjala@linux.intel.com \
--cc=intel-gfx@lists.freedesktop.org \
--cc=mahesh1.sh.kumar@gmail.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