Re: [PATCH 5/6] drm/vc4: Fix overflow mem unreferencing when the binner runs dry.

On Wed, Jul 27, 2016 at 1:37 AM, Eric Anholt wrote: > Rob Clark writes: > >> On Tue, Jul 26, 2016 at 7:11 PM, Eric Anholt wrote: >>> Rob Clark writes: >>> On Tue, Jul 26, 2016 at 4:47 PM, Eric Anholt

Re: [PATCH 5/6] drm/vc4: Fix overflow mem unreferencing when the binner runs dry.

On Wed, Jul 27, 2016 at 1:37 AM, Eric Anholt wrote: > Rob Clark writes: > >> On Tue, Jul 26, 2016 at 7:11 PM, Eric Anholt wrote: >>> Rob Clark writes: >>> On Tue, Jul 26, 2016 at 4:47 PM, Eric Anholt wrote: > Overflow memory handling is tricky: While it's still referenced by the

Re: [PATCH 5/6] drm/vc4: Fix overflow mem unreferencing when the binner runs dry.

Rob Clark writes: > On Tue, Jul 26, 2016 at 7:11 PM, Eric Anholt wrote: >> Rob Clark writes: >> >>> On Tue, Jul 26, 2016 at 4:47 PM, Eric Anholt wrote: Overflow memory handling is tricky: While it's still

Re: [PATCH 5/6] drm/vc4: Fix overflow mem unreferencing when the binner runs dry.

Rob Clark writes: > On Tue, Jul 26, 2016 at 7:11 PM, Eric Anholt wrote: >> Rob Clark writes: >> >>> On Tue, Jul 26, 2016 at 4:47 PM, Eric Anholt wrote: Overflow memory handling is tricky: While it's still referenced by the BPO registers, we want to keep it from being freed. When we

Re: [PATCH 5/6] drm/vc4: Fix overflow mem unreferencing when the binner runs dry.

On Tue, Jul 26, 2016 at 7:11 PM, Eric Anholt wrote: > Rob Clark writes: > >> On Tue, Jul 26, 2016 at 4:47 PM, Eric Anholt wrote: >>> Overflow memory handling is tricky: While it's still referenced by the >>> BPO registers, we want to keep

Re: [PATCH 5/6] drm/vc4: Fix overflow mem unreferencing when the binner runs dry.

On Tue, Jul 26, 2016 at 7:11 PM, Eric Anholt wrote: > Rob Clark writes: > >> On Tue, Jul 26, 2016 at 4:47 PM, Eric Anholt wrote: >>> Overflow memory handling is tricky: While it's still referenced by the >>> BPO registers, we want to keep it from being freed. When we are >>> putting a new set

Re: [PATCH 5/6] drm/vc4: Fix overflow mem unreferencing when the binner runs dry.

Rob Clark writes: > On Tue, Jul 26, 2016 at 4:47 PM, Eric Anholt wrote: >> Overflow memory handling is tricky: While it's still referenced by the >> BPO registers, we want to keep it from being freed. When we are >> putting a new set of overflow memory in

Re: [PATCH 5/6] drm/vc4: Fix overflow mem unreferencing when the binner runs dry.

Rob Clark writes: > On Tue, Jul 26, 2016 at 4:47 PM, Eric Anholt wrote: >> Overflow memory handling is tricky: While it's still referenced by the >> BPO registers, we want to keep it from being freed. When we are >> putting a new set of overflow memory in the registers, we need to >> assign

Re: [PATCH 5/6] drm/vc4: Fix overflow mem unreferencing when the binner runs dry.

On Tue, Jul 26, 2016 at 4:47 PM, Eric Anholt wrote: > Overflow memory handling is tricky: While it's still referenced by the > BPO registers, we want to keep it from being freed. When we are > putting a new set of overflow memory in the registers, we need to > assign the old one

Re: [PATCH 5/6] drm/vc4: Fix overflow mem unreferencing when the binner runs dry.

On Tue, Jul 26, 2016 at 4:47 PM, Eric Anholt wrote: > Overflow memory handling is tricky: While it's still referenced by the > BPO registers, we want to keep it from being freed. When we are > putting a new set of overflow memory in the registers, we need to > assign the old one to the last

[PATCH 5/6] drm/vc4: Fix overflow mem unreferencing when the binner runs dry.

Overflow memory handling is tricky: While it's still referenced by the BPO registers, we want to keep it from being freed. When we are putting a new set of overflow memory in the registers, we need to assign the old one to the last rendering job using it. We were looking at "what's currently

[PATCH 5/6] drm/vc4: Fix overflow mem unreferencing when the binner runs dry.

Overflow memory handling is tricky: While it's still referenced by the BPO registers, we want to keep it from being freed. When we are putting a new set of overflow memory in the registers, we need to assign the old one to the last rendering job using it. We were looking at "what's currently