Re: [Intel-gfx] [PATCH v2 06/21] drm/i915/gt: Batch TLB invalidations

2022-07-28 Thread Tvrtko Ursulin
On 28/07/2022 07:32, Mauro Carvalho Chehab wrote: On Wed, 27 Jul 2022 13:56:50 +0100 Tvrtko Ursulin wrote: Because vma_invalidate_tlb() basically stores a TLB seqno, but the actual invalidation is deferred to when the pages are unset, at __i915_gem_object_unset_pages(). So, what happens is:

Re: [Intel-gfx] [PATCH v2 06/21] drm/i915/gt: Batch TLB invalidations

2022-07-28 Thread Mauro Carvalho Chehab
On Thu, 28 Jul 2022 08:32:32 +0200 Mauro Carvalho Chehab wrote: > On Wed, 27 Jul 2022 13:56:50 +0100 > Tvrtko Ursulin wrote: > > > > Because vma_invalidate_tlb() basically stores a TLB seqno, but the > > > actual invalidation is deferred to when the pages are unset, at > > > __i915_gem_object_u

Re: [Intel-gfx] [PATCH v2 06/21] drm/i915/gt: Batch TLB invalidations

2022-07-27 Thread Mauro Carvalho Chehab
On Wed, 27 Jul 2022 13:56:50 +0100 Tvrtko Ursulin wrote: > > Because vma_invalidate_tlb() basically stores a TLB seqno, but the > > actual invalidation is deferred to when the pages are unset, at > > __i915_gem_object_unset_pages(). > > > > So, what happens is: > > > > - on VMA sync mode, the n

Re: [Intel-gfx] [PATCH v2 06/21] drm/i915/gt: Batch TLB invalidations

2022-07-27 Thread Tvrtko Ursulin
On 27/07/2022 12:48, Mauro Carvalho Chehab wrote: On Wed, 20 Jul 2022 11:49:59 +0100 Tvrtko Ursulin wrote: On 20/07/2022 08:13, Mauro Carvalho Chehab wrote: On Mon, 18 Jul 2022 14:52:05 +0100 Tvrtko Ursulin wrote: On 14/07/2022 13:06, Mauro Carvalho Chehab wrote: From: Chris Wilson

Re: [Intel-gfx] [PATCH v2 06/21] drm/i915/gt: Batch TLB invalidations

2022-07-27 Thread Mauro Carvalho Chehab
On Wed, 20 Jul 2022 11:49:59 +0100 Tvrtko Ursulin wrote: > On 20/07/2022 08:13, Mauro Carvalho Chehab wrote: > > On Mon, 18 Jul 2022 14:52:05 +0100 > > Tvrtko Ursulin wrote: > > > >> > >> On 14/07/2022 13:06, Mauro Carvalho Chehab wrote: > >>> From: Chris Wilson > >>> > >>> Invalidate TLB

Re: [Intel-gfx] [PATCH v2 06/21] drm/i915/gt: Batch TLB invalidations

2022-07-20 Thread Tvrtko Ursulin
On 14/07/2022 13:06, Mauro Carvalho Chehab wrote: From: Chris Wilson Invalidate TLB in patch, in order to reduce performance regressions. Currently, every caller performs a full barrier around a TLB invalidation, ignoring all other invalidations that may have already removed their PTEs from

Re: [Intel-gfx] [PATCH v2 06/21] drm/i915/gt: Batch TLB invalidations

2022-07-20 Thread Tvrtko Ursulin
On 20/07/2022 08:13, Mauro Carvalho Chehab wrote: On Mon, 18 Jul 2022 14:52:05 +0100 Tvrtko Ursulin wrote: On 14/07/2022 13:06, Mauro Carvalho Chehab wrote: From: Chris Wilson Invalidate TLB in patch, in order to reduce performance regressions. "in batches"? Yeah. Will fix it. diff

Re: [Intel-gfx] [PATCH v2 06/21] drm/i915/gt: Batch TLB invalidations

2022-07-20 Thread Mauro Carvalho Chehab
On Mon, 18 Jul 2022 14:52:05 +0100 Tvrtko Ursulin wrote: > > On 14/07/2022 13:06, Mauro Carvalho Chehab wrote: > > From: Chris Wilson > > > > Invalidate TLB in patch, in order to reduce performance regressions. > > "in batches"? Yeah. Will fix it. > > diff --git a/drivers/gpu/drm/i915/gt/in

Re: [Intel-gfx] [PATCH v2 06/21] drm/i915/gt: Batch TLB invalidations

2022-07-18 Thread Tvrtko Ursulin
On 14/07/2022 13:06, Mauro Carvalho Chehab wrote: From: Chris Wilson Invalidate TLB in patch, in order to reduce performance regressions. "in batches"? Currently, every caller performs a full barrier around a TLB invalidation, ignoring all other invalidations that may have already removed

[Intel-gfx] [PATCH v2 06/21] drm/i915/gt: Batch TLB invalidations

2022-07-14 Thread Mauro Carvalho Chehab
From: Chris Wilson Invalidate TLB in patch, in order to reduce performance regressions. Currently, every caller performs a full barrier around a TLB invalidation, ignoring all other invalidations that may have already removed their PTEs from the cache. As this is a synchronous operation and can