On Mon, Dec 27, 2010 at 7:58 AM, Mario Kleiner
wrote:
> On Dec 26, 2010, at 3:53 PM, Andrew Lutomirski wrote:
>
>> On Wed, Dec 22, 2010 at 4:06 PM, Mario Kleiner
>> wrote:
>>>
>>> There's a new drm module parameter for selecting the timeout: echo 50 >
>>> /sys/module/drm/parameters/vblankoffdelay
On Mon, Dec 27, 2010 at 7:58 AM, Mario Kleiner
wrote:
> On Dec 26, 2010, at 3:53 PM, Andrew Lutomirski wrote:
>
>> On Wed, Dec 22, 2010 at 4:06 PM, Mario Kleiner
>> wrote:
>>>
>>> There's a new drm module parameter for selecting the timeout: echo 50 >
>>> /sys/module/drm/parameters/vblankoffdelay
On Dec 27, 2010, at 12:16 PM, Ville Syrj?l? wrote:
> On Mon, Dec 27, 2010 at 12:58:10AM +0100, Mario Kleiner wrote:
>
>> 2. There are gpu's firing spurious vblank irq's as soon as you enable
>> irq's
>
> You're sure this isn't simply a matter of the driver forgetting to ack
> the irq just before
On Dec 27, 2010, at 12:16 PM, Ville Syrjälä wrote:
On Mon, Dec 27, 2010 at 12:58:10AM +0100, Mario Kleiner wrote:
2. There are gpu's firing spurious vblank irq's as soon as you enable
irq's
You're sure this isn't simply a matter of the driver forgetting to ack
the irq just before enabling i
On Mon, Dec 27, 2010 at 12:58:10AM +0100, Mario Kleiner wrote:
> 2. There are gpu's firing spurious vblank irq's as soon as you enable
> irq's
You're sure this isn't simply a matter of the driver forgetting to ack
the irq just before enabling it?
--
Ville Syrj?l?
syrjala at sci.fi
http://www.
On Mon, Dec 27, 2010 at 12:58:10AM +0100, Mario Kleiner wrote:
> 2. There are gpu's firing spurious vblank irq's as soon as you enable
> irq's
You're sure this isn't simply a matter of the driver forgetting to ack
the irq just before enabling it?
--
Ville Syrjälä
syrj...@sci.fi
http://www.sc
On Dec 26, 2010, at 3:53 PM, Andrew Lutomirski wrote:
> On Wed, Dec 22, 2010 at 4:06 PM, Mario Kleiner
> wrote:
>>
>> There's a new drm module parameter for selecting the timeout: echo
>> 50 >
>> /sys/module/drm/parameters/vblankoffdelay
>> would set the timeout to 50 msecs. A setting of zero w
On Dec 26, 2010, at 3:53 PM, Andrew Lutomirski wrote:
On Wed, Dec 22, 2010 at 4:06 PM, Mario Kleiner
wrote:
There's a new drm module parameter for selecting the timeout: echo
50 >
/sys/module/drm/parameters/vblankoffdelay
would set the timeout to 50 msecs. A setting of zero will disable
On Wed, Dec 22, 2010 at 4:06 PM, Mario Kleiner
wrote:
>
> There's a new drm module parameter for selecting the timeout: echo 50 >
> /sys/module/drm/parameters/vblankoffdelay
> would set the timeout to 50 msecs. A setting of zero will disable the timer,
> so vblank irq's would stay on all the time.
On Wed, Dec 22, 2010 at 4:06 PM, Mario Kleiner
wrote:
>
> There's a new drm module parameter for selecting the timeout: echo 50 >
> /sys/module/drm/parameters/vblankoffdelay
> would set the timeout to 50 msecs. A setting of zero will disable the timer,
> so vblank irq's would stay on all the time.
9:23:40 -0800
>>> From: Keith Packard
>>> Subject: Re: [Intel-gfx] [PATCH] drm: Aggressively disable vblanks
>>> To: Andy Lutomirski , Jesse Barnes
>>> , Chris Wilson >> wilson.co.uk>,
>>> David Airlie
>>> Cc: intel-gfx at lists
n, 20 Dec 2010 22:34:12 -0500
From: Andrew Lutomirski
Subject: Re: [Intel-gfx] [PATCH] drm: Aggressively disable vblanks
To: Keith Packard
Cc: intel-...@lists.freedesktop.org, dri-devel@lists.freedesktop.org
Message-ID:
Content-Type: text/plain; charset=ISO-8859-1
On Mon, Dec 20, 2010 at 10:23
On Wed, 22 Dec 2010 05:36:13 +0100
Mario Kleiner wrote:
> > --
> >
> > Message: 1
> > Date: Mon, 20 Dec 2010 19:23:40 -0800
> > From: Keith Packard
> > Subject: Re: [Intel-gfx] [PATCH] drm:
On Wed, 22 Dec 2010 05:36:13 +0100
Mario Kleiner wrote:
> > --
> >
> > Message: 1
> > Date: Mon, 20 Dec 2010 19:23:40 -0800
> > From: Keith Packard
> > Subject: Re: [Intel-gfx] [PATCH] drm:
> --
>
> Message: 1
> Date: Mon, 20 Dec 2010 19:23:40 -0800
> From: Keith Packard
> Subject: Re: [Intel-gfx] [PATCH] drm: Aggressively disable vblanks
> To: Andy Lutomirski , Jesse Barnes
>
--
Message: 1
Date: Mon, 20 Dec 2010 19:23:40 -0800
From: Keith Packard
Subject: Re: [Intel-gfx] [PATCH] drm: Aggressively disable vblanks
To: Andy Lutomirski , Jesse Barnes
, Chris Wilson
,
David Airlie
On Mon, Dec 20, 2010 at 10:47 PM, Keith Packard wrote:
> On Mon, 20 Dec 2010 22:34:12 -0500, Andrew Lutomirski wrote:
>
>> But five seconds is a *long* time, and anything short enough that the
>> interrupt actually gets turned off in normal use risks the same race.
>
> Right, so eliminating any r
On Mon, Dec 20, 2010 at 10:23 PM, Keith Packard wrote:
> On Mon, 20 Dec 2010 14:00:54 -0500, Andy Lutomirski wrote:
>
>> Enabling and disabling the vblank interrupt (on devices that
>> support it) is cheap. ?So disable it quickly after each
>> interrupt.
>
> So, the concern (and reason for the or
On Mon, 20 Dec 2010 22:55:46 -0500
Andrew Lutomirski wrote:
> On Mon, Dec 20, 2010 at 10:47 PM, Keith Packard wrote:
> > On Mon, 20 Dec 2010 22:34:12 -0500, Andrew Lutomirski wrote:
> >
> >> But five seconds is a *long* time, and anything short enough that the
> >> interrupt actually gets turne
On Mon, 20 Dec 2010 22:55:46 -0500
Andrew Lutomirski wrote:
> On Mon, Dec 20, 2010 at 10:47 PM, Keith Packard wrote:
> > On Mon, 20 Dec 2010 22:34:12 -0500, Andrew Lutomirski
> > wrote:
> >
> >> But five seconds is a *long* time, and anything short enough that the
> >> interrupt actually gets
On Mon, Dec 20, 2010 at 10:47 PM, Keith Packard wrote:
> On Mon, 20 Dec 2010 22:34:12 -0500, Andrew Lutomirski wrote:
>
>> But five seconds is a *long* time, and anything short enough that the
>> interrupt actually gets turned off in normal use risks the same race.
>
> Right, so eliminating any r
On Mon, 20 Dec 2010 22:34:12 -0500, Andrew Lutomirski wrote:
> But five seconds is a *long* time, and anything short enough that the
> interrupt actually gets turned off in normal use risks the same race.
Right, so eliminating any race seems like the basic requirement. Can
that be done?
--
kei
On Mon, 20 Dec 2010 22:34:12 -0500, Andrew Lutomirski wrote:
> But five seconds is a *long* time, and anything short enough that the
> interrupt actually gets turned off in normal use risks the same race.
Right, so eliminating any race seems like the basic requirement. Can
that be done?
--
kei
On Mon, Dec 20, 2010 at 10:23 PM, Keith Packard wrote:
> On Mon, 20 Dec 2010 14:00:54 -0500, Andy Lutomirski wrote:
>
>> Enabling and disabling the vblank interrupt (on devices that
>> support it) is cheap. So disable it quickly after each
>> interrupt.
>
> So, the concern (and reason for the or
On Mon, 20 Dec 2010 14:00:54 -0500, Andy Lutomirski wrote:
> Enabling and disabling the vblank interrupt (on devices that
> support it) is cheap. So disable it quickly after each
> interrupt.
So, the concern (and reason for the original design) was that you might
lose count of vblank interrupts
On Mon, 20 Dec 2010 14:00:54 -0500, Andy Lutomirski wrote:
> Enabling and disabling the vblank interrupt (on devices that
> support it) is cheap. So disable it quickly after each
> interrupt.
So, the concern (and reason for the original design) was that you might
lose count of vblank interrupts
26 matches
Mail list logo