Re: [Intel-gfx] [PATCH 4/4] dma-buf: nuke reservation_object seq number

2019-08-14 Thread Chris Wilson
Quoting Koenig, Christian (2019-08-14 18:58:32) > Am 14.08.19 um 19:48 schrieb Chris Wilson: > > Quoting Chris Wilson (2019-08-14 18:38:20) > >> Quoting Chris Wilson (2019-08-14 18:22:53) > >>> Quoting Chris Wilson (2019-08-14 18:06:18) > Quoting Chris Wilson (2019-08-14 17:42:48) > >

Re: [Intel-gfx] [PATCH 4/4] dma-buf: nuke reservation_object seq number

2019-08-14 Thread Koenig, Christian
Am 14.08.19 um 19:48 schrieb Chris Wilson: > Quoting Chris Wilson (2019-08-14 18:38:20) >> Quoting Chris Wilson (2019-08-14 18:22:53) >>> Quoting Chris Wilson (2019-08-14 18:06:18) Quoting Chris Wilson (2019-08-14 17:42:48) > Quoting Daniel Vetter (2019-08-14 16:39:08) > + }

Re: [Intel-gfx] [PATCH 4/4] dma-buf: nuke reservation_object seq number

2019-08-14 Thread Daniel Vetter
On Wed, Aug 14, 2019 at 06:20:28PM +0100, Chris Wilson wrote: > Quoting Daniel Vetter (2019-08-14 18:06:26) > > On Wed, Aug 14, 2019 at 05:42:48PM +0100, Chris Wilson wrote: > > > Quoting Daniel Vetter (2019-08-14 16:39:08) > [snip] > > > > > > > if (old) > > > > > > > -

Re: [Intel-gfx] [PATCH 4/4] dma-buf: nuke reservation_object seq number

2019-08-14 Thread Chris Wilson
Quoting Chris Wilson (2019-08-14 18:38:20) > Quoting Chris Wilson (2019-08-14 18:22:53) > > Quoting Chris Wilson (2019-08-14 18:06:18) > > > Quoting Chris Wilson (2019-08-14 17:42:48) > > > > Quoting Daniel Vetter (2019-08-14 16:39:08) > > > > > > > > + } while

Re: [Intel-gfx] [PATCH 4/4] dma-buf: nuke reservation_object seq number

2019-08-14 Thread Chris Wilson
Quoting Chris Wilson (2019-08-14 18:22:53) > Quoting Chris Wilson (2019-08-14 18:06:18) > > Quoting Chris Wilson (2019-08-14 17:42:48) > > > Quoting Daniel Vetter (2019-08-14 16:39:08) > > > > > > > + } while (rcu_access_pointer(obj->fence_excl) != *excl); > > > > > > > > What if someone is

Re: [Intel-gfx] [PATCH 4/4] dma-buf: nuke reservation_object seq number

2019-08-14 Thread Chris Wilson
Quoting Chris Wilson (2019-08-14 18:06:18) > Quoting Chris Wilson (2019-08-14 17:42:48) > > Quoting Daniel Vetter (2019-08-14 16:39:08) > > > > > > + } while (rcu_access_pointer(obj->fence_excl) != *excl); > > > > > > What if someone is real fast (like really real fast) and recycles the > >

Re: [Intel-gfx] [PATCH 4/4] dma-buf: nuke reservation_object seq number

2019-08-14 Thread Chris Wilson
Quoting Daniel Vetter (2019-08-14 18:06:26) > On Wed, Aug 14, 2019 at 05:42:48PM +0100, Chris Wilson wrote: > > Quoting Daniel Vetter (2019-08-14 16:39:08) [snip] > > > > > > if (old) > > > > > > - old->shared_count = 0; > > > > > > - write_seqcount_end(>seq); > > > >

Re: [Intel-gfx] [PATCH 4/4] dma-buf: nuke reservation_object seq number

2019-08-14 Thread Chris Wilson
Quoting Chris Wilson (2019-08-14 17:42:48) > Quoting Daniel Vetter (2019-08-14 16:39:08) > > > > > + } while (rcu_access_pointer(obj->fence_excl) != *excl); > > > > What if someone is real fast (like really real fast) and recycles the > > exclusive fence so you read the same pointer twice,

Re: [Intel-gfx] [PATCH 4/4] dma-buf: nuke reservation_object seq number

2019-08-14 Thread Daniel Vetter
On Wed, Aug 14, 2019 at 05:42:48PM +0100, Chris Wilson wrote: > Quoting Daniel Vetter (2019-08-14 16:39:08) > > Sorry I burried myself in some other stuff ... > > > > On Sat, Aug 10, 2019 at 12:51:00PM +0200, Christian König wrote: > > > Am 07.08.19 um 16:17 schrieb Chris Wilson: > > > > Quoting

Re: [Intel-gfx] [PATCH 4/4] dma-buf: nuke reservation_object seq number

2019-08-14 Thread Chris Wilson
Quoting Daniel Vetter (2019-08-14 16:39:08) > Sorry I burried myself in some other stuff ... > > On Sat, Aug 10, 2019 at 12:51:00PM +0200, Christian König wrote: > > Am 07.08.19 um 16:17 schrieb Chris Wilson: > > > Quoting Christian König (2019-08-07 14:53:12) > > > > The only remaining use for

Re: [Intel-gfx] [PATCH 4/4] dma-buf: nuke reservation_object seq number

2019-08-14 Thread Daniel Vetter
Sorry I burried myself in some other stuff ... On Sat, Aug 10, 2019 at 12:51:00PM +0200, Christian König wrote: > Am 07.08.19 um 16:17 schrieb Chris Wilson: > > Quoting Christian König (2019-08-07 14:53:12) > > > The only remaining use for this is to protect against setting a new > > > exclusive

Re: [Intel-gfx] [PATCH 4/4] dma-buf: nuke reservation_object seq number

2019-08-10 Thread Christian König
Am 07.08.19 um 16:17 schrieb Chris Wilson: Quoting Christian König (2019-08-07 14:53:12) The only remaining use for this is to protect against setting a new exclusive fence while we grab both exclusive and shared. That can also be archived by looking if the exclusive fence has changed or not

Re: [Intel-gfx] [PATCH 4/4] dma-buf: nuke reservation_object seq number

2019-08-07 Thread Chris Wilson
Quoting Christian König (2019-08-07 14:53:12) > The only remaining use for this is to protect against setting a new exclusive > fence while we grab both exclusive and shared. That can also be archived by > looking if the exclusive fence has changed or not after completing the > operation. > > v2: