On Tue, 18 Feb 2014, bradley.d.vol...@intel.com wrote:
> +static u32 gen7_render_get_cmd_length_mask(u32 cmd_header)
> +{
> + u32 client = (cmd_header & INSTR_CLIENT_MASK) >> INSTR_CLIENT_SHIFT;
> + u32 subclient =
> + (cmd_header & INSTR_SUBCLIENT_MASK) >> INSTR_SUBCLIENT_SHIFT
On Thu, Mar 06, 2014 at 03:10:50PM +0200, Jani Nikula wrote:
> On Tue, 18 Feb 2014, bradley.d.vol...@intel.com wrote:
> > From: Brad Volkin
> >
> > The command parser scans batch buffers submitted via execbuffer ioctls
> > before
> > the driver submits them to hardware. At a high level, it looks
On Tue, 18 Feb 2014, bradley.d.vol...@intel.com wrote:
> From: Brad Volkin
>
> The command parser scans batch buffers submitted via execbuffer ioctls before
> the driver submits them to hardware. At a high level, it looks for several
> things:
>
> 1) Commands which are explicitly defined as privil
From: Brad Volkin
The command parser scans batch buffers submitted via execbuffer ioctls before
the driver submits them to hardware. At a high level, it looks for several
things:
1) Commands which are explicitly defined as privileged or which should only be
used by the kernel driver. The pars
On Tue, 11 Feb 2014, "Volkin, Bradley D" wrote:
> On Fri, Feb 07, 2014 at 06:45:48AM -0800, Daniel Vetter wrote:
>> On Fri, Feb 07, 2014 at 03:58:46PM +0200, Jani Nikula wrote:
>> > On Wed, 29 Jan 2014, bradley.d.vol...@intel.com wrote:
>> > > +static int valid_reg(const u32 *table, int count, u32
On Fri, Feb 07, 2014 at 06:45:48AM -0800, Daniel Vetter wrote:
> On Fri, Feb 07, 2014 at 03:58:46PM +0200, Jani Nikula wrote:
> > On Wed, 29 Jan 2014, bradley.d.vol...@intel.com wrote:
> > > +static int valid_reg(const u32 *table, int count, u32 addr)
> > > +{
> > > + if (table && count != 0) {
> >
On Fri, Feb 07, 2014 at 03:58:46PM +0200, Jani Nikula wrote:
> On Wed, 29 Jan 2014, bradley.d.vol...@intel.com wrote:
> > +static int valid_reg(const u32 *table, int count, u32 addr)
> > +{
> > + if (table && count != 0) {
> > + int i;
> > +
> > + for (i = 0; i < count; i++) {
On Wed, 29 Jan 2014, bradley.d.vol...@intel.com wrote:
> +static int valid_reg(const u32 *table, int count, u32 addr)
> +{
> + if (table && count != 0) {
> + int i;
> +
> + for (i = 0; i < count; i++) {
> + if (table[i] == addr)
> +
On Wed, Feb 05, 2014 at 07:15:35AM -0800, Jani Nikula wrote:
> On Wed, 29 Jan 2014, bradley.d.vol...@intel.com wrote:
> > From: Brad Volkin
> >
> > The command parser scans batch buffers submitted via execbuffer ioctls
> > before
> > the driver submits them to hardware. At a high level, it looks
On Wed, 29 Jan 2014, bradley.d.vol...@intel.com wrote:
> From: Brad Volkin
>
> The command parser scans batch buffers submitted via execbuffer ioctls before
> the driver submits them to hardware. At a high level, it looks for several
> things:
>
> 1) Commands which are explicitly defined as privil
On Tue, Feb 04, 2014 at 11:33:31AM -0800, Daniel Vetter wrote:
> On Tue, Feb 04, 2014 at 10:45:45AM -0800, Volkin, Bradley D wrote:
> > The current table structure is that we have tables per-ring and per-gen
> > (plus the table
> > for common MI commands) and all tables are treated as blacklist/gr
On Tue, Feb 04, 2014 at 10:45:45AM -0800, Volkin, Bradley D wrote:
> The current table structure is that we have tables per-ring and per-gen (plus
> the table
> for common MI commands) and all tables are treated as blacklist/greylist. The
> proposed
> flow here would indicate that we need tables
On Tue, Feb 04, 2014 at 02:20:36AM -0800, Daniel Vetter wrote:
> On Mon, Feb 03, 2014 at 03:00:19PM -0800, Volkin, Bradley D wrote:
> > Ping. Daniel or Chris, can one of you clarify this request? Thanks.
>
> I've been enjoying fosdem ...
>
> > On Thu, Jan 30, 2014 at 10:05:27AM -0800, Volkin, Bra
On Mon, Feb 03, 2014 at 03:00:19PM -0800, Volkin, Bradley D wrote:
> Ping. Daniel or Chris, can one of you clarify this request? Thanks.
I've been enjoying fosdem ...
> On Thu, Jan 30, 2014 at 10:05:27AM -0800, Volkin, Bradley D wrote:
> > On Thu, Jan 30, 2014 at 03:07:15AM -0800, Daniel Vetter w
Ping. Daniel or Chris, can one of you clarify this request? Thanks.
On Thu, Jan 30, 2014 at 10:05:27AM -0800, Volkin, Bradley D wrote:
> On Thu, Jan 30, 2014 at 03:07:15AM -0800, Daniel Vetter wrote:
> > On Thu, Jan 30, 2014 at 10:12:06AM +0100, Daniel Vetter wrote:
> > > On Thu, Jan 30, 2014 at 1
On Thu, Jan 30, 2014 at 03:07:15AM -0800, Daniel Vetter wrote:
> On Thu, Jan 30, 2014 at 10:12:06AM +0100, Daniel Vetter wrote:
> > On Thu, Jan 30, 2014 at 10:05:28AM +0100, Daniel Vetter wrote:
> > > On Thu, Jan 30, 2014 at 09:53:28AM +0100, Daniel Vetter wrote:
> > > > On Wed, Jan 29, 2014 at 10:
On Thu, Jan 30, 2014 at 01:12:06AM -0800, Daniel Vetter wrote:
> On Thu, Jan 30, 2014 at 10:05:28AM +0100, Daniel Vetter wrote:
> > On Thu, Jan 30, 2014 at 09:53:28AM +0100, Daniel Vetter wrote:
> > > On Wed, Jan 29, 2014 at 10:28:36PM +, Chris Wilson wrote:
> > > > On Wed, Jan 29, 2014 at 01:5
On Thu, Jan 30, 2014 at 10:12:06AM +0100, Daniel Vetter wrote:
> On Thu, Jan 30, 2014 at 10:05:28AM +0100, Daniel Vetter wrote:
> > On Thu, Jan 30, 2014 at 09:53:28AM +0100, Daniel Vetter wrote:
> > > On Wed, Jan 29, 2014 at 10:28:36PM +, Chris Wilson wrote:
> > > > On Wed, Jan 29, 2014 at 01:5
On Thu, Jan 30, 2014 at 10:07:42AM +0100, Daniel Vetter wrote:
> On Wed, Jan 29, 2014 at 01:55:03PM -0800, bradley.d.vol...@intel.com wrote:
> > From: Brad Volkin
> >
> > The command parser scans batch buffers submitted via execbuffer ioctls
> > before
> > the driver submits them to hardware. At
On Thu, Jan 30, 2014 at 10:05:28AM +0100, Daniel Vetter wrote:
> On Thu, Jan 30, 2014 at 09:53:28AM +0100, Daniel Vetter wrote:
> > On Wed, Jan 29, 2014 at 10:28:36PM +, Chris Wilson wrote:
> > > On Wed, Jan 29, 2014 at 01:55:03PM -0800, bradley.d.vol...@intel.com
> > > wrote:
> > > > +/*
> >
On Wed, Jan 29, 2014 at 01:55:03PM -0800, bradley.d.vol...@intel.com wrote:
> From: Brad Volkin
>
> The command parser scans batch buffers submitted via execbuffer ioctls before
> the driver submits them to hardware. At a high level, it looks for several
> things:
>
> 1) Commands which are expli
On Thu, Jan 30, 2014 at 09:53:28AM +0100, Daniel Vetter wrote:
> On Wed, Jan 29, 2014 at 10:28:36PM +, Chris Wilson wrote:
> > On Wed, Jan 29, 2014 at 01:55:03PM -0800, bradley.d.vol...@intel.com wrote:
> > > +/*
> > > + * Returns a pointer to a descriptor for the command specified by
> > > cm
On Wed, Jan 29, 2014 at 10:28:36PM +, Chris Wilson wrote:
> On Wed, Jan 29, 2014 at 01:55:03PM -0800, bradley.d.vol...@intel.com wrote:
> > +/*
> > + * Returns a pointer to a descriptor for the command specified by
> > cmd_header.
> > + *
> > + * The caller must supply space for a default desc
On Wed, Jan 29, 2014 at 01:55:03PM -0800, bradley.d.vol...@intel.com wrote:
> +/*
> + * Returns a pointer to a descriptor for the command specified by cmd_header.
> + *
> + * The caller must supply space for a default descriptor via the default_desc
> + * parameter. If no descriptor for the specifi
From: Brad Volkin
The command parser scans batch buffers submitted via execbuffer ioctls before
the driver submits them to hardware. At a high level, it looks for several
things:
1) Commands which are explicitly defined as privileged or which should only be
used by the kernel driver. The pars
25 matches
Mail list logo
