Re: [Intel-gfx] [RFC PATCH 36/97] drm/i915/guc: Add non blocking CTB send function

2021-06-24 Thread Daniel Vetter
On Thu, Jun 24, 2021 at 09:38:33AM -0700, Matthew Brost wrote: > On Thu, Jun 10, 2021 at 05:27:48PM +0200, Daniel Vetter wrote: > > On Wed, Jun 09, 2021 at 04:10:23PM -0700, Matthew Brost wrote: > > > On Tue, Jun 08, 2021 at 10:46:15AM +0200, Daniel Vetter wrote: > > > > On Tue, Jun 8, 2021 at

Re: [Intel-gfx] [RFC PATCH 36/97] drm/i915/guc: Add non blocking CTB send function

2021-06-24 Thread Matthew Brost
On Thu, Jun 10, 2021 at 05:27:48PM +0200, Daniel Vetter wrote: > On Wed, Jun 09, 2021 at 04:10:23PM -0700, Matthew Brost wrote: > > On Tue, Jun 08, 2021 at 10:46:15AM +0200, Daniel Vetter wrote: > > > On Tue, Jun 8, 2021 at 10:39 AM Tvrtko Ursulin > > > wrote: > > > > > > > > > > > > On

Re: [Intel-gfx] [RFC PATCH 36/97] drm/i915/guc: Add non blocking CTB send function

2021-06-10 Thread Daniel Vetter
On Wed, Jun 09, 2021 at 04:10:23PM -0700, Matthew Brost wrote: > On Tue, Jun 08, 2021 at 10:46:15AM +0200, Daniel Vetter wrote: > > On Tue, Jun 8, 2021 at 10:39 AM Tvrtko Ursulin > > wrote: > > > > > > > > > On 07/06/2021 18:31, Matthew Brost wrote: > > > > On Thu, May 27, 2021 at 04:11:50PM

Re: [Intel-gfx] [RFC PATCH 36/97] drm/i915/guc: Add non blocking CTB send function

2021-06-09 Thread Matthew Brost
On Wed, Jun 09, 2021 at 04:14:05PM +0200, Michal Wajdeczko wrote: > > > On 07.06.2021 19:31, Matthew Brost wrote: > > On Thu, May 27, 2021 at 04:11:50PM +0100, Tvrtko Ursulin wrote: > >> > >> On 27/05/2021 15:35, Matthew Brost wrote: > >>> On Thu, May 27, 2021 at 11:02:24AM +0100, Tvrtko Ursulin

Re: [Intel-gfx] [RFC PATCH 36/97] drm/i915/guc: Add non blocking CTB send function

2021-06-09 Thread Matthew Brost
On Tue, Jun 08, 2021 at 10:46:15AM +0200, Daniel Vetter wrote: > On Tue, Jun 8, 2021 at 10:39 AM Tvrtko Ursulin > wrote: > > > > > > On 07/06/2021 18:31, Matthew Brost wrote: > > > On Thu, May 27, 2021 at 04:11:50PM +0100, Tvrtko Ursulin wrote: > > >> > > >> On 27/05/2021 15:35, Matthew Brost

Re: [Intel-gfx] [RFC PATCH 36/97] drm/i915/guc: Add non blocking CTB send function

2021-06-09 Thread Matthew Brost
On Wed, Jun 09, 2021 at 03:58:38PM +0200, Michal Wajdeczko wrote: > > > On 08.06.2021 10:39, Tvrtko Ursulin wrote: > > > > On 07/06/2021 18:31, Matthew Brost wrote: > >> On Thu, May 27, 2021 at 04:11:50PM +0100, Tvrtko Ursulin wrote: > >>> > >>> On 27/05/2021 15:35, Matthew Brost wrote: >

Re: [Intel-gfx] [RFC PATCH 36/97] drm/i915/guc: Add non blocking CTB send function

2021-06-09 Thread Michal Wajdeczko
On 07.06.2021 19:31, Matthew Brost wrote: > On Thu, May 27, 2021 at 04:11:50PM +0100, Tvrtko Ursulin wrote: >> >> On 27/05/2021 15:35, Matthew Brost wrote: >>> On Thu, May 27, 2021 at 11:02:24AM +0100, Tvrtko Ursulin wrote: On 26/05/2021 19:10, Matthew Brost wrote: [snip]

Re: [Intel-gfx] [RFC PATCH 36/97] drm/i915/guc: Add non blocking CTB send function

2021-06-09 Thread Michal Wajdeczko
On 08.06.2021 10:39, Tvrtko Ursulin wrote: > > On 07/06/2021 18:31, Matthew Brost wrote: >> On Thu, May 27, 2021 at 04:11:50PM +0100, Tvrtko Ursulin wrote: >>> >>> On 27/05/2021 15:35, Matthew Brost wrote: On Thu, May 27, 2021 at 11:02:24AM +0100, Tvrtko Ursulin wrote: > > On

Re: [Intel-gfx] [RFC PATCH 36/97] drm/i915/guc: Add non blocking CTB send function

2021-06-08 Thread Daniel Vetter
On Tue, Jun 8, 2021 at 10:39 AM Tvrtko Ursulin wrote: > > > On 07/06/2021 18:31, Matthew Brost wrote: > > On Thu, May 27, 2021 at 04:11:50PM +0100, Tvrtko Ursulin wrote: > >> > >> On 27/05/2021 15:35, Matthew Brost wrote: > >>> On Thu, May 27, 2021 at 11:02:24AM +0100, Tvrtko Ursulin wrote: >

Re: [Intel-gfx] [RFC PATCH 36/97] drm/i915/guc: Add non blocking CTB send function

2021-06-08 Thread Tvrtko Ursulin
On 07/06/2021 18:31, Matthew Brost wrote: On Thu, May 27, 2021 at 04:11:50PM +0100, Tvrtko Ursulin wrote: On 27/05/2021 15:35, Matthew Brost wrote: On Thu, May 27, 2021 at 11:02:24AM +0100, Tvrtko Ursulin wrote: On 26/05/2021 19:10, Matthew Brost wrote: [snip] +static int

Re: [Intel-gfx] [RFC PATCH 36/97] drm/i915/guc: Add non blocking CTB send function

2021-06-07 Thread Matthew Brost
On Thu, May 27, 2021 at 04:11:50PM +0100, Tvrtko Ursulin wrote: > > On 27/05/2021 15:35, Matthew Brost wrote: > > On Thu, May 27, 2021 at 11:02:24AM +0100, Tvrtko Ursulin wrote: > > > > > > On 26/05/2021 19:10, Matthew Brost wrote: > > > > > > [snip] > > > > > > > > > > > +static int

Re: [Intel-gfx] [RFC PATCH 36/97] drm/i915/guc: Add non blocking CTB send function

2021-05-27 Thread Tvrtko Ursulin
On 27/05/2021 15:35, Matthew Brost wrote: On Thu, May 27, 2021 at 11:02:24AM +0100, Tvrtko Ursulin wrote: On 26/05/2021 19:10, Matthew Brost wrote: [snip] +static int ct_send_nb(struct intel_guc_ct *ct, + const u32 *action, + u32 len, +

Re: [Intel-gfx] [RFC PATCH 36/97] drm/i915/guc: Add non blocking CTB send function

2021-05-27 Thread Matthew Brost
On Thu, May 27, 2021 at 11:02:24AM +0100, Tvrtko Ursulin wrote: > > On 26/05/2021 19:10, Matthew Brost wrote: > > [snip] > > > > > > > +static int ct_send_nb(struct intel_guc_ct *ct, > > > > > > + const u32 *action, > > > > > > + u32 len, > > > > > > +

Re: [Intel-gfx] [RFC PATCH 36/97] drm/i915/guc: Add non blocking CTB send function

2021-05-27 Thread Tvrtko Ursulin
On 26/05/2021 19:10, Matthew Brost wrote: [snip] +static int ct_send_nb(struct intel_guc_ct *ct, + const u32 *action, + u32 len, + u32 flags) +{ + struct intel_guc_ct_buffer *ctb = >ctbs.send; + unsigned long spin_flags;

Re: [Intel-gfx] [RFC PATCH 36/97] drm/i915/guc: Add non blocking CTB send function

2021-05-26 Thread Matthew Brost
On Wed, May 26, 2021 at 09:57:10AM +0100, Tvrtko Ursulin wrote: > > On 25/05/2021 18:21, Matthew Brost wrote: > > On Tue, May 25, 2021 at 10:21:00AM +0100, Tvrtko Ursulin wrote: > > > > > > On 06/05/2021 20:13, Matthew Brost wrote: > > > > Add non blocking CTB send function, intel_guc_send_nb.

Re: [Intel-gfx] [RFC PATCH 36/97] drm/i915/guc: Add non blocking CTB send function

2021-05-26 Thread Tvrtko Ursulin
On 25/05/2021 18:21, Matthew Brost wrote: On Tue, May 25, 2021 at 10:21:00AM +0100, Tvrtko Ursulin wrote: On 06/05/2021 20:13, Matthew Brost wrote: Add non blocking CTB send function, intel_guc_send_nb. In order to support a non blocking CTB send function a spin lock is needed to protect the

Re: [Intel-gfx] [RFC PATCH 36/97] drm/i915/guc: Add non blocking CTB send function

2021-05-25 Thread Matthew Brost
On Mon, May 24, 2021 at 02:21:42PM +0200, Michal Wajdeczko wrote: > > > On 06.05.2021 21:13, Matthew Brost wrote: > > Add non blocking CTB send function, intel_guc_send_nb. In order to > > support a non blocking CTB send function a spin lock is needed to > > spin lock was added in 16/97 > > >

Re: [Intel-gfx] [RFC PATCH 36/97] drm/i915/guc: Add non blocking CTB send function

2021-05-25 Thread Matthew Brost
On Tue, May 25, 2021 at 10:21:00AM +0100, Tvrtko Ursulin wrote: > > On 06/05/2021 20:13, Matthew Brost wrote: > > Add non blocking CTB send function, intel_guc_send_nb. In order to > > support a non blocking CTB send function a spin lock is needed to > > protect the CTB descriptors fields. Also

Re: [Intel-gfx] [RFC PATCH 36/97] drm/i915/guc: Add non blocking CTB send function

2021-05-25 Thread Tvrtko Ursulin
On 06/05/2021 20:13, Matthew Brost wrote: Add non blocking CTB send function, intel_guc_send_nb. In order to support a non blocking CTB send function a spin lock is needed to protect the CTB descriptors fields. Also the non blocking call must not update the fence value as this value is owned by

Re: [Intel-gfx] [RFC PATCH 36/97] drm/i915/guc: Add non blocking CTB send function

2021-05-24 Thread Michal Wajdeczko
On 06.05.2021 21:13, Matthew Brost wrote: > Add non blocking CTB send function, intel_guc_send_nb. In order to > support a non blocking CTB send function a spin lock is needed to spin lock was added in 16/97 > protect the CTB descriptors fields. Also the non blocking call must not > update the

[Intel-gfx] [RFC PATCH 36/97] drm/i915/guc: Add non blocking CTB send function

2021-05-06 Thread Matthew Brost
Add non blocking CTB send function, intel_guc_send_nb. In order to support a non blocking CTB send function a spin lock is needed to protect the CTB descriptors fields. Also the non blocking call must not update the fence value as this value is owned by the blocking call (intel_guc_send). The