From: Rodrigo Vivi <rodrigo.vivi@intel.com>
To: Lucas De Marchi <lucas.de.marchi@gmail.com>
Cc: intel-gfx@lists.freedesktop.org, x86@kernel.org,
Paulo Zanoni <paulo.r.zanoni@intel.com>
Subject: Re: [PATCH 2/2] drm/i915: use the ICL stolen memory
Date: Mon, 9 Jul 2018 12:13:21 -0700 [thread overview]
Message-ID: <20180709191321.GE28253@intel.com> (raw)
In-Reply-To: <CAKi4VALiW0bvvhZj7upDp-EwXkUNYUQe83hhMXnX97wjjNjcKA@mail.gmail.com>
On Fri, Jul 06, 2018 at 07:09:15PM -0700, Lucas De Marchi wrote:
> On Fri, May 4, 2018 at 1:33 PM Paulo Zanoni <paulo.r.zanoni@intel.com> wrote:
> >
> > Now that our stolen memory is already reserved by the x86 subsystem
> > (since commit "x86/gpu: reserve ICL's graphics stolen memory"), make
> > use of it.
> >
> > Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
> > Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
> > Cc: x86@kernel.org
> > Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
> > ---
> > drivers/gpu/drm/i915/i915_gem_stolen.c | 38 +++++++++++++++++++++++++++++++++-
> > drivers/gpu/drm/i915/i915_reg.h | 1 +
> > 2 files changed, 38 insertions(+), 1 deletion(-)
> >
> > diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c
> > index ad949cc30928..99556f0dbedc 100644
> > --- a/drivers/gpu/drm/i915/i915_gem_stolen.c
> > +++ b/drivers/gpu/drm/i915/i915_gem_stolen.c
> > @@ -343,6 +343,35 @@ static void bdw_get_stolen_reserved(struct drm_i915_private *dev_priv,
> > *size = stolen_top - *base;
> > }
> >
> > +static void icl_get_stolen_reserved(struct drm_i915_private *dev_priv,
> > + resource_size_t *base,
> > + resource_size_t *size)
> > +{
> > + u64 reg_val = I915_READ64(GEN6_STOLEN_RESERVED);
>
> are you sure it's still the same address? Either I'm looking to the
> wrong place or this needs to be changed.
The only thing that changed was the size s/32/64
and the reg name s/MPAVPC/PAVPC_REG
BSpec: 19481
So, since this question made me look to the spec:
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
>
> Lucas De Marchi
>
> > +
> > + DRM_DEBUG_DRIVER("GEN6_STOLEN_RESERVED = 0x%016llx\n", reg_val);
> > +
> > + *base = reg_val & GEN11_STOLEN_RESERVED_ADDR_MASK;
> > +
> > + switch (reg_val & GEN8_STOLEN_RESERVED_SIZE_MASK) {
> > + case GEN8_STOLEN_RESERVED_1M:
> > + *size = 1024 * 1024;
> > + break;
> > + case GEN8_STOLEN_RESERVED_2M:
> > + *size = 2 * 1024 * 1024;
> > + break;
> > + case GEN8_STOLEN_RESERVED_4M:
> > + *size = 4 * 1024 * 1024;
> > + break;
> > + case GEN8_STOLEN_RESERVED_8M:
> > + *size = 8 * 1024 * 1024;
> > + break;
> > + default:
> > + *size = 8 * 1024 * 1024;
> > + MISSING_CASE(reg_val & GEN8_STOLEN_RESERVED_SIZE_MASK);
> > + }
> > +}
> > +
> > int i915_gem_init_stolen(struct drm_i915_private *dev_priv)
> > {
> > resource_size_t reserved_base, stolen_top;
> > @@ -399,7 +428,9 @@ int i915_gem_init_stolen(struct drm_i915_private *dev_priv)
> > gen7_get_stolen_reserved(dev_priv,
> > &reserved_base, &reserved_size);
> > break;
> > - default:
> > + case 8:
> > + case 9:
> > + case 10:
> > if (IS_LP(dev_priv))
> > chv_get_stolen_reserved(dev_priv,
> > &reserved_base, &reserved_size);
> > @@ -407,6 +438,11 @@ int i915_gem_init_stolen(struct drm_i915_private *dev_priv)
> > bdw_get_stolen_reserved(dev_priv,
> > &reserved_base, &reserved_size);
> > break;
> > + case 11:
> > + default:
> > + icl_get_stolen_reserved(dev_priv, &reserved_base,
> > + &reserved_size);
> > + break;
> > }
> >
> > /*
> > diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
> > index 15daf3553d40..c5bc7c808e31 100644
> > --- a/drivers/gpu/drm/i915/i915_reg.h
> > +++ b/drivers/gpu/drm/i915/i915_reg.h
> > @@ -398,6 +398,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
> > #define GEN8_STOLEN_RESERVED_4M (2 << 7)
> > #define GEN8_STOLEN_RESERVED_8M (3 << 7)
> > #define GEN6_STOLEN_RESERVED_ENABLE (1 << 0)
> > +#define GEN11_STOLEN_RESERVED_ADDR_MASK (0xFFFFFFFFFFFULL << 20)
> >
> > /* VGA stuff */
> >
> > --
> > 2.14.3
> >
> > _______________________________________________
> > Intel-gfx mailing list
> > Intel-gfx@lists.freedesktop.org
> > https://lists.freedesktop.org/mailman/listinfo/intel-gfx
>
>
>
> --
> Lucas De Marchi
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/intel-gfx
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
next prev parent reply other threads:[~2018-07-09 19:13 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-05-03 0:23 [PATCH] drm/i915/icl, x86/gpu: implement ICL stolen memory support Paulo Zanoni
2018-05-03 0:52 ` ✗ Fi.CI.CHECKPATCH: warning for " Patchwork
2018-05-03 1:06 ` ✓ Fi.CI.BAT: success " Patchwork
2018-05-03 9:59 ` [PATCH] " Joonas Lahtinen
2018-05-03 15:24 ` Paulo Zanoni
2018-05-03 15:35 ` Chris Wilson
2018-05-03 16:28 ` Joonas Lahtinen
2018-05-03 10:18 ` ✓ Fi.CI.IGT: success for " Patchwork
2018-05-04 20:32 ` [PATCH 1/2] x86/gpu: reserve ICL's graphics stolen memory Paulo Zanoni
2018-05-04 20:32 ` [PATCH 2/2] drm/i915: use the ICL " Paulo Zanoni
2018-07-07 2:09 ` Lucas De Marchi
2018-07-09 19:13 ` Rodrigo Vivi [this message]
2018-07-09 23:44 ` Paulo Zanoni
2018-05-07 8:46 ` [PATCH 1/2] x86/gpu: reserve ICL's graphics " Joonas Lahtinen
2018-05-07 8:46 ` Joonas Lahtinen
2018-06-01 21:44 ` Paulo Zanoni
2018-06-18 17:47 ` Rodrigo Vivi
2018-06-18 17:47 ` [Intel-gfx] " Rodrigo Vivi
2018-07-03 19:11 ` Rodrigo Vivi
2018-07-03 19:11 ` [Intel-gfx] " Rodrigo Vivi
2018-07-04 5:50 ` Ingo Molnar
2018-07-04 5:50 ` [Intel-gfx] " Ingo Molnar
2018-07-05 14:52 ` Rodrigo Vivi
2018-07-05 14:52 ` [Intel-gfx] " Rodrigo Vivi
2018-07-10 23:40 ` Rodrigo Vivi
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=20180709191321.GE28253@intel.com \
--to=rodrigo.vivi@intel.com \
--cc=intel-gfx@lists.freedesktop.org \
--cc=lucas.de.marchi@gmail.com \
--cc=paulo.r.zanoni@intel.com \
--cc=x86@kernel.org \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.