On Fri, Sep 13, 2013 at 2:59 AM, Rob Clark wrote:
> I guess in i915 (and ttm) case, the issue arises due to need for CPU
> access to buffer via GTT? In which case I should be safe to drop the
> set_need_resched() as well? (Since CPU always has direct access to the
> pages.) Or am I missing
On Fri, Sep 13, 2013 at 2:59 AM, Rob Clark robdcl...@gmail.com wrote:
I guess in i915 (and ttm) case, the issue arises due to need for CPU
access to buffer via GTT? In which case I should be safe to drop the
set_need_resched() as well? (Since CPU always has direct access to the
pages.) Or am
hmm, looks like I cargo-cult'd the same into msm.
I guess in i915 (and ttm) case, the issue arises due to need for CPU
access to buffer via GTT? In which case I should be safe to drop the
set_need_resched() as well? (Since CPU always has direct access to the
pages.) Or am I missing something
On Thu, Sep 12, 2013 at 05:59:51PM +0200, Peter Zijlstra wrote:
> On Thu, Sep 12, 2013 at 05:57:28PM +0200, Daniel Vetter wrote:
> > This is just a remnant from the old days when our reset handling was
> > horribly racy, suffered from terribly locking issues and often happily
> > live-locked.
This is just a remnant from the old days when our reset handling was
horribly racy, suffered from terribly locking issues and often happily
live-locked. Those days are now gone so we can drop the hacks and just
rip the reschedule-point out.
Reported-by: Peter Zijlstra
Cc: Peter Zijlstra
Cc:
On Thu, Sep 12, 2013 at 05:57:28PM +0200, Daniel Vetter wrote:
> This is just a remnant from the old days when our reset handling was
> horribly racy, suffered from terribly locking issues and often happily
> live-locked. Those days are now gone so we can drop the hacks and just
> rip the
On Thu, Sep 12, 2013 at 05:57:28PM +0200, Daniel Vetter wrote:
This is just a remnant from the old days when our reset handling was
horribly racy, suffered from terribly locking issues and often happily
live-locked. Those days are now gone so we can drop the hacks and just
rip the
This is just a remnant from the old days when our reset handling was
horribly racy, suffered from terribly locking issues and often happily
live-locked. Those days are now gone so we can drop the hacks and just
rip the reschedule-point out.
Reported-by: Peter Zijlstra pet...@infradead.org
Cc:
On Thu, Sep 12, 2013 at 05:59:51PM +0200, Peter Zijlstra wrote:
On Thu, Sep 12, 2013 at 05:57:28PM +0200, Daniel Vetter wrote:
This is just a remnant from the old days when our reset handling was
horribly racy, suffered from terribly locking issues and often happily
live-locked. Those days
hmm, looks like I cargo-cult'd the same into msm.
I guess in i915 (and ttm) case, the issue arises due to need for CPU
access to buffer via GTT? In which case I should be safe to drop the
set_need_resched() as well? (Since CPU always has direct access to the
pages.) Or am I missing something
10 matches
Mail list logo