On 04/10/2016 16:46, Praveen Paneri wrote:
Decoupled MMIO is an alternative way to access forcewake domain
registers, which requires less cycles for a single read/write and
avoids frequent software forcewake.
This certainly gives advantage over the forcewake as this new
mechanism “decouples” CPU
Hi Chris,
On Wednesday 05 October 2016 01:26 AM, Chris Wilson wrote:
On Tue, Oct 04, 2016 at 09:16:06PM +0530, Praveen Paneri wrote:
+#define HAS_DECOUPLED_MMIO(dev) (INTEL_INFO(dev)->has_decoupled_mmio \
+ && IS_BXT_REVID(dev, BXT_REVID_C0, REVID_FOREVER))
Edit dev_priv->info.h
Thanks Chris for the review. Will fix these and resend.
~Praveen
On Wednesday 05 October 2016 01:26 AM, Chris Wilson wrote:
On Tue, Oct 04, 2016 at 09:16:06PM +0530, Praveen Paneri wrote:
+#define HAS_DECOUPLED_MMIO(dev) (INTEL_INFO(dev)->has_decoupled_mmio \
+ && IS_BXT_REVID(de
On Tue, Oct 04, 2016 at 09:16:06PM +0530, Praveen Paneri wrote:
> +#define HAS_DECOUPLED_MMIO(dev) (INTEL_INFO(dev)->has_decoupled_mmio \
> + && IS_BXT_REVID(dev, BXT_REVID_C0, REVID_FOREVER))
Edit dev_priv->info.has_decoupled_mmio on init.
> +static void __gen9_decoupled_mmio_access(
Is this still an embargoed feature? why?
With Apollolake out there we need to work to get permission to upstream
this feature already and post it to intel-gfx@lists.freedesktop.org in
order to get this merged upstream.
A decoupled version for BXT stayed in the internal for so long time and
caused
Decoupled MMIO is an alternative way to access forcewake domain
registers, which requires less cycles for a single read/write and
avoids frequent software forcewake.
This certainly gives advantage over the forcewake as this new
mechanism “decouples” CPU cycles and allow them to complete even
when G
