On Sat, Aug 31, 2024 at 09:13:52AM +0200, Boris Brezillon wrote:
> Hi Matthew,
>
> On Fri, 30 Aug 2024 22:28:19 +
> Matthew Brost wrote:
>
> > On Fri, Aug 30, 2024 at 12:40:57PM +0200, Boris Brezillon wrote:
> > > dma_fence objects created by drm_sched might hit other subsystems, which
> > >
On Mon, Sep 02, 2024 at 12:58:54PM +0200, Christian König wrote:
> Am 31.08.24 um 00:28 schrieb Matthew Brost:
> > On Fri, Aug 30, 2024 at 12:40:57PM +0200, Boris Brezillon wrote:
> > > dma_fence objects created by drm_sched might hit other subsystems, which
> > > means the fence object might poten
Am 31.08.24 um 00:28 schrieb Matthew Brost:
On Fri, Aug 30, 2024 at 12:40:57PM +0200, Boris Brezillon wrote:
dma_fence objects created by drm_sched might hit other subsystems, which
means the fence object might potentially outlive the drm_sched module
lifetime, and at this point the dma_fence::o
Hi Matthew,
On Fri, 30 Aug 2024 22:28:19 +
Matthew Brost wrote:
> On Fri, Aug 30, 2024 at 12:40:57PM +0200, Boris Brezillon wrote:
> > dma_fence objects created by drm_sched might hit other subsystems, which
> > means the fence object might potentially outlive the drm_sched module
> > lifeti
On Fri, Aug 30, 2024 at 12:40:57PM +0200, Boris Brezillon wrote:
> dma_fence objects created by drm_sched might hit other subsystems, which
> means the fence object might potentially outlive the drm_sched module
> lifetime, and at this point the dma_fence::ops points to a memory region
> that no lo
dma_fence objects created by drm_sched might hit other subsystems, which
means the fence object might potentially outlive the drm_sched module
lifetime, and at this point the dma_fence::ops points to a memory region
that no longer exists.
In order to fix that, let's make sure the drm_sched_fence c
