On Thu, 21 Oct 2021 at 13:54, Matthew Auld wrote:
>
> wbinvd_on_all_cpus() is only defined on x86 it seems, plus we need to
> include asm/smp.h here.
>
> Reported-by: kernel test robot
> Signed-off-by: Matthew Auld
> Cc: Thomas Hellström
Jani, would it make sense to cherr
On Wed, 27 Oct 2021 at 09:58, Jani Nikula wrote:
>
> On Wed, 27 Oct 2021, Matthew Auld wrote:
> > On Thu, 21 Oct 2021 at 13:54, Matthew Auld wrote:
> >>
> >> wbinvd_on_all_cpus() is only defined on x86 it seems, plus we need to
> >> include asm/smp.h h
On Wed, 27 Oct 2021 at 09:36, Thomas Hellström
wrote:
>
> GPU relocs are gone. There should be no need for this workaround anymore.
> Remove it.
>
> Signed-off-by: Thomas Hellström
I was completely wrong here, sorry. Digging through the git history it
looks like this came from:
Commit 149c84077
On Wed, 27 Oct 2021 at 10:44, Jani Nikula wrote:
>
> On Wed, 27 Oct 2021, Matthew Auld wrote:
> > On Wed, 27 Oct 2021 at 09:58, Jani Nikula
> > wrote:
> >>
> >> On Wed, 27 Oct 2021, Matthew Auld wrote:
> >> > On Thu, 2
efore the
pages are populated.
v2(Thomas):
- Move setting cache_dirty out of the async portion, also add a
comment for why that should still be safe.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
---
drivers/gpu/drm/i915/gem/i915_gem_clflush.c | 10 +-
1 file changed, 9 inser
Should not be needed. Even with non-coherent display, we should be using
device local-memory there, and not system memory.
v2: also add a warning in i915_gem_clflush_object
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Reviewed-by: Thomas Hellström #v1
---
drivers/gpu/drm/i915/gem
, so there should in theory be no
conceivable reason to ever call i915_gem_clflush_object() on discrete.
References: https://gitlab.freedesktop.org/drm/intel/-/issues/4320
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Reviewed-by: Thomas Hellström
---
drivers/gpu/drm/i915/gem/i915_gem_clflush.c
Move it next to its partner in crime; gpu_write_needs_clflush. For
better readability lets keep gpu vs cpu at least in the same file.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Reviewed-by: Thomas Hellström
---
drivers/gpu/drm/i915/gem/i915_gem_domain.c | 12
drivers/gpu
On Wed, 27 Oct 2021 at 15:54, Lucas De Marchi wrote:
>
> On Wed, Oct 27, 2021 at 08:57:48AM +0100, Matthew Auld wrote:
> >On Thu, 21 Oct 2021 at 13:54, Matthew Auld wrote:
> >>
> >> wbinvd_on_all_cpus() is only defined on x86 it seems, plus we need
On 27/10/2021 11:52, Thomas Hellström wrote:
As we start to introduce asynchronous failsafe object migration,
where we update the object state and then submit asynchronous
commands we need to record what memory resources are actually used
by various part of the command stream. Initially for three
contexts, like is already done
for the kernel context.
v2:
- Don't reset the contexts on each __engine_unpark() but rather at
resume time (Chris Wilson).
v3:
- Reset contexts in the engine sanitize callback. (Chris Wilson)
Cc: Tvrtko Ursulin
Cc: Matthew Auld
Cc: Maarten Lankhorst
Cc:
allowed to lose its content on suspend.
v3:
- Slight documentation clarification (Matthew Auld)
Signed-off-by: Thomas Hellström
Reviewed-by: Matthew Auld
submission.
v2:
- Major refactor to make sure gem_exec_suspend@hang-SX subtests work, and
suspend / resume works with a slightly modified GuC submission enabling
patch series.
v3:
- Fix a potential use-after-free (Matthew Auld)
- Use i915_gem_object_create_shmem() instead of
44,7 +644,7 @@ static int init_aliasing_ppgtt(struct i915_ggtt *ggtt)
struct i915_ppgtt *ppgtt;
int err;
- ppgtt = i915_ppgtt_create(ggtt->vm.gt);
+ ppgtt = i915_ppgtt_create(ggtt->vm.gt, I915_BO_ALLOC_PM_EARLY);
I guess could leave as flags=0, since appgtt is not relevant o
es
array is never actually cleared in unpopulate this might lead to a nasty
uaf.
Fixes: 09ac4fcb3f25 ("drm/ttm: Implement vm_operations_struct.access v2")
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Cc: Christian König
---
drivers/gpu/drm/ttm/ttm_bo_vm.c | 5 -
1 file changed,
at in the next patch.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Cc: Christian König
Reviewed-by: Christian König
---
drivers/gpu/drm/ttm/ttm_bo_vm.c | 2 --
drivers/gpu/drm/ttm/ttm_tt.c| 4 +---
2 files changed, 1 insertion(+), 5 deletions(-)
diff --git a/drivers/gpu/drm/ttm/ttm_bo_
later tries to touch them.
v2(Christian):
- Drop the functions altogether and just inline modifying
the page->mapping
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Cc: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 15 ++-
drivers/gpu/drm/ttm/ttm_tt.
No longer used it seems.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Cc: Christian König
Reviewed-by: Christian König
---
include/drm/ttm/ttm_tt.h | 1 -
1 file changed, 1 deletion(-)
diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h
index 89b15d673b22..842ce756213c
Suggested-by: Christian König
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Cc: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 10 +-
drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 6 +++---
drivers/gpu/drm/nouveau/nouveau_bo.c| 4 ++--
drivers/gpu/drm/radeon
Move it to inline kernel-doc, otherwise we can't add empty lines it
seems. Also drop the kernel-doc for pages_list, which doesn't seem to
exist.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Cc: Christian König
---
include/drm/ttm/ttm_tt.h | 57 ++---
handle objects which don't even have mm.pages, so bundling this into
put_pages() would require somehow handling that edge case, hence
just letting the ttm backend handle everything in try_to_writeback
doesn't seem too bad.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
PABLE in the definition
of EXTERNAL_MAPPABLE, just leave it the caller to handle this
correctly, otherwise we might encounter subtle issues.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Cc: Christian König
---
drivers/gpu/drm/ttm/ttm_bo_vm.c | 6 --
drivers/gpu/drm/ttm/ttm
compute the page sizes using
the dma segments rather than using the physical page address segments.
v2(Reported-by: kernel test robot )
- Make sure we initialise the mapping on the error path in
shmem_get_pages()
Signed-off-by: Thomas Hellström
Reviewed-by: Matthew Auld
Signed-off-by
This should let us do an accelerated copy directly to the shmem pages
when temporarily moving lmem-only objects, where the i915-gem shrinker
can later kick in to swap out the pages, if needed.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
---
drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 8
able to do the bo_unpin() from the unpopulate hook,
but since that can be called from the BO destroy path we will likely go
down in flames.
An alternative is to maybe just add EXTERNAL objects to some
bdev->external LRU in TTM, or just don't add them at all?
Signed-off-by: Matthew
on nesting calls to shrink_pin.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
---
drivers/gpu/drm/i915/gem/i915_gem_object.c| 9
.../gpu/drm/i915/gem/i915_gem_object_types.h | 3 +-
drivers/gpu/drm/i915/gem/i915_gem_pages.c | 16 +-
drivers/gpu/drm/i915/gem/i915_gem_shrin
just gets migrated back to lmem when touched again. For such
cases we can make the object visible as soon as we populate the TT with
shmem pages, and then hide it again when doing the unpopulate.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
---
drivers/gpu/drm/i915/gem/i915_gem_object.h | 1 +
d
Enable shmem tt backend, and enable shrinking.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
---
drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
index f68481b852ff
gine as NULL, but this
does require adding some extra handling in get_driver_name etc.
v2(Daniel):
- Try to make the commit message less confusing
Fixes: 855e39e65cfc ("drm/i915: Initialise basic fence before acquiring seqno")
Signed-off-by: Matthew Auld
Cc: Michael Mason
Cc: Daniel
is now fixed.
While the IGTs did eventually hit this(although not during pre-merge it
seems), it's likely worthwhile adding some explicit coverage for this
scenario in the shrink_thp selftest.
References: https://gitlab.freedesktop.org/drm/intel/-/issues/4166
Signed-off-by: Matthew Aul
> not protected from eviction by fences.
>
> Cc: Matthew Brost
> Fixes: 91160c839824 ("drm/i915: Take pinning into account in
> __i915_gem_object_is_lmem")
>
> Signed-off-by: Thomas Hellström
Reviewed-by: Matthew Auld
On Wed, 22 Sept 2021 at 09:38, Thomas Hellström
wrote:
>
> In the mman selftest, some tests make the ttm_bo_init_reserved() fail,
> which may trigger a call to the i915_ttm_bo_destroy() function.
> However, at this point the gem object refcount is set to 1, which
> triggers a lockdep warning in __
On 21/09/2021 12:48, Christian König wrote:
Am 21.09.21 um 13:01 schrieb Matthew Auld:
This is probably a NAK. But ideally we need to somehow prevent TTM from
seeing shmem objects when doing its LRU swap walk. Since these are
EXTERNAL they are ignored anyway, but keeping them in the LRU seems
), increase the timeout before we mark the gt wedged and proceed.
Signed-off-by: Thomas Hellström
Acked-by: Matthew Auld
---
drivers/gpu/drm/i915/gt/intel_gt_pm.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c
b/drivers/gpu/drm/i915
k the aliasing ppgtt page table flags for early resume, but
rather the ggtt page table flags as intended. (Matthew Auld)
- The check for user buffer objects during early resume is pointless, since
they are never marked I915_BO_ALLOC_PM_EARLY. (Matthew Auld)
v5:
- Mark GuC LMEM objects
Seems to fix some object-debug splat which appeared while debugging
something unrelated.
v2: s/guc_blocked/guc_state.blocked/
Signed-off-by: Matthew Auld
Cc: Ville Syrjälä
Cc: Matthew Brost
---
drivers/gpu/drm/i915/gt/intel_context.c | 1 +
1 file changed, 1 insertion(+)
diff --git a
at in the next patch.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Cc: Christian König
Reviewed-by: Christian König
---
drivers/gpu/drm/ttm/ttm_bo_vm.c | 2 --
drivers/gpu/drm/ttm/ttm_tt.c| 4 +---
2 files changed, 1 insertion(+), 5 deletions(-)
diff --git a/drivers/gpu/drm/ttm/ttm_bo_
es
array is never actually cleared in unpopulate this might lead to a nasty
uaf.
Fixes: 09ac4fcb3f25 ("drm/ttm: Implement vm_operations_struct.access v2")
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Cc: Christian König
Reviewed-by: Thomas Hellström
Reviewed-by: Christian König
---
Move it to inline kernel-doc, otherwise we can't add empty lines it
seems. Also drop the kernel-doc for pages_list, which doesn't seem to
exist.
v2(Christian):
- Add a note that FLAG_SWAPPED shouldn't need to be touched by drivers.
- Mention what FLAG_POPULATED does.
Signed-
later tries to touch them.
v2(Christian):
- Drop the functions altogether and just inline modifying
the page->mapping
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Cc: Christian König
Reviewed-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 15 ++-
dr
Suggested-by: Christian König
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Cc: Christian König
Acked-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 10 +-
drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 6 +++---
drivers/gpu/drm/nouveau/nouveau_bo.c| 4
No longer used it seems.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Cc: Christian König
Reviewed-by: Christian König
---
include/drm/ttm/ttm_tt.h | 1 -
1 file changed, 1 deletion(-)
diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h
index 89b15d673b22..842ce756213c
compute the page sizes using
the dma segments rather than using the physical page address segments.
v2(Reported-by: kernel test robot )
- Make sure we initialise the mapping on the error path in
shmem_get_pages()
Signed-off-by: Thomas Hellström
Reviewed-by: Matthew Auld
Signed-off-by
to come up with something
better later.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Cc: Christian König
---
drivers/gpu/drm/i915/gem/i915_gem_object.h| 8 +
.../gpu/drm/i915/gem/i915_gem_object_types.h | 2 +
drivers/gpu/drm/i915/gem/i915_gem_shmem.c | 14 +-
drivers/gpu/drm/i91
PABLE in the definition
of EXTERNAL_MAPPABLE, just leave it the caller to handle this
correctly, otherwise we might encounter subtle issues.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Cc: Christian König
---
drivers/gpu/drm/ttm/ttm_bo_vm.c | 6 --
drivers/gpu/drm/ttm/ttm
This should let us do an accelerated copy directly to the shmem pages
when temporarily moving lmem-only objects, where the i915-gem shrinker
can later kick in to swap out the pages, if needed.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
---
drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 8
on nesting calls to shrink_pin.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
---
drivers/gpu/drm/i915/gem/i915_gem_object.c| 9
.../gpu/drm/i915/gem/i915_gem_object_types.h | 3 +-
drivers/gpu/drm/i915/gem/i915_gem_pages.c | 16 +-
drivers/gpu/drm/i915/gem/i915_gem_shrin
don't touch
the shrinker LRU more than needed.
v2(Thomas)
- Handle managing the shrinker LRU in adjust_lru, where it is always
safe to touch the object.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
---
drivers/gpu/drm/i915/gem/i915_gem_object.h | 1 +
drivers/gpu/drm/i915/gem/i91
Turn on the shmem tt backend, and enable shrinking.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
---
drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
index
On Mon, 27 Sept 2021 at 12:47, Christian König wrote:
>
> Any objections that I just push patches 1-7 to drm-misc-next?
Please go ahead Christian. Thanks.
>
> Christian.
>
> Am 27.09.21 um 13:41 schrieb Matthew Auld:
> > In commit:
> >
> > commit 09ac
obj_link))) {
GEM_BUG_ON(vma->obj != obj);
spin_unlock(&obj->vma.lock);
-
__i915_vma_put(vma);
Unrelated change?
Not seeing any DG1 machines in CI currently, so assuming this was tested
locally,
Reviewed-by: Matthew Auld
Suggested-by: Christian König
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Cc: Christian König
Acked-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 10 +-
drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 6 +++---
drivers/gpu/drm/nouveau/nouveau_bo.c| 4
Move it to inline kernel-doc, otherwise we can't add empty lines it
seems. Also drop the kernel-doc for pages_list, which doesn't seem to
exist.
v2(Christian):
- Add a note that FLAG_SWAPPED shouldn't need to be touched by drivers.
- Mention what FLAG_POPULATED does.
Signed-
PABLE in the definition
of EXTERNAL_MAPPABLE, just leave it the caller to handle this
correctly, otherwise we might encounter subtle issues.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Cc: Christian König
---
drivers/gpu/drm/ttm/ttm_bo_vm.c | 6 --
drivers/gpu/drm/ttm/ttm
On Wed, 29 Sept 2021 at 13:01, Christian König wrote:
>
> Am 27.09.21 um 18:14 schrieb Matthew Auld:
> > On Mon, 27 Sept 2021 at 12:47, Christian König
> > wrote:
> >> Any objections that I just push patches 1-7 to drm-misc-next?
> > Please go ahead Christ
!(clear && ttm && !(ttm->page_flags & TTM_PAGE_FLAG_ZERO_ALLOC)))
| ^~~~
| TTM_TT_FLAG_ZERO_ALLOC
Do we just need to revert the bad commit in drm-rerere, rebuild tip,
and try again? If so I can try to attempt this.
>
> Christian.
>
> Am 29.09.21 um 15:26 schrieb
On Thu, 30 Sept 2021 at 08:45, Christian König wrote:
>
> Am 30.09.21 um 09:42 schrieb Matthew Auld:
> > On Thu, 30 Sept 2021 at 08:28, Christian König
> > wrote:
> >> I pushed those to drm-misc-next and fixed the i915 merge fallout in
> >> drm-tip.
>
On 30/09/2021 11:04, Michel Dänzer wrote:
On 2021-09-29 13:54, Thomas Hellström wrote:
On Mon, 2021-09-27 at 12:41 +0100, Matthew Auld wrote:
This should let us do an accelerated copy directly to the shmem pages
when temporarily moving lmem-only objects, where the i915-gem
shrinker
can later
ject_free_mmaps() in __i915_gem_object_pages_fini()
to make sure we don't inadvertedly introduce a race.
Signed-off-by: Thomas Hellström
Reviewed-by: Matthew Auld #v1
R-b still stands.
---
drivers/gpu/drm/i915/gem/i915_gem_object.c | 43 +++---
drivers/gpu/drm/i915/g
] drm/i915/ttm: add tt shmem
backend
On 10/5/21 04:05, Zeng, Oak wrote:
Hi Matthew/Thomas,
See one question inline
Regards,
Oak
-Original Message-
From: Intel-gfx On Behalf Of
Matthew Auld
Sent: September 27, 2021 7:41 AM
To: intel-...@lists.freedesktop.org
Cc: dri-devel
compute the page sizes using
the dma segments rather than using the physical page address segments.
v2(Reported-by: kernel test robot )
- Make sure we initialise the mapping on the error path in
shmem_get_pages()
Signed-off-by: Thomas Hellström
Reviewed-by: Matthew Auld
Signed-off-by
The comment here is no longer accurate, since the current shrinker code
requires a full ref before touching any objects. Also unset_pages()
should already do the required make_unshrinkable() for us, if needed,
which is also nicely balanced with set_pages().
Signed-off-by: Matthew Auld
Cc: Thomas
to come up with something
better later.
v4(Thomas):
- s/PCI_DMA/DMA/. Also drop NO_KERNEL_MAPPING and NO_WARN, which
apparently doesn't do anything with streaming mappings.
- Just pass along the error for ->truncate, and assume nothing.
Signed-off-by: Matthew Auld
Cc: Thomas Hellst
We already do this when mapping the pages.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
---
drivers/gpu/drm/i915/gt/gen6_ppgtt.c | 1 -
drivers/gpu/drm/i915/gt/gen8_ppgtt.c | 1 -
2 files changed, 2 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/gen6_ppgtt.c
b/drivers/gpu/drm/i915/gt
Attempt to document shrink_pin and the other relevant interfaces that
interact with it, before we start messing with it.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
---
.../gpu/drm/i915/gem/i915_gem_object_types.h | 24 +-
drivers/gpu/drm/i915/gem/i915_gem_shrinker.c | 31
This should let us do an accelerated copy directly to the shmem pages
when temporarily moving lmem-only objects, where the i915-gem shrinker
can later kick in to swap out the pages, if needed.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Reviewed-by: Thomas Hellström
---
drivers/gpu/drm
, which actually seems to fit quite well for what we want here.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
---
drivers/gpu/drm/i915/gem/i915_gem_object.h| 8 +++
.../gpu/drm/i915/gem/i915_gem_object_types.h | 25 ++-
drivers/gpu/drm/i915/gem/i915_gem_pages.c | 5 +-
drivers/
Turn on the shmem tt backend, and enable shrinking.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Reviewed-by: Thomas Hellström
---
drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
b
compute the page sizes using
the dma segments rather than using the physical page address segments.
v2(Reported-by: kernel test robot )
- Make sure we initialise the mapping on the error path in
shmem_get_pages()
Signed-off-by: Thomas Hellström
Reviewed-by: Matthew Auld
Signed-off-by
We already do this when mapping the pages.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Reviewed-by: Thomas Hellström
---
drivers/gpu/drm/i915/gt/gen6_ppgtt.c | 1 -
drivers/gpu/drm/i915/gt/gen8_ppgtt.c | 1 -
2 files changed, 2 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt
The comment here is no longer accurate, since the current shrinker code
requires a full ref before touching any objects. Also unset_pages()
should already do the required make_unshrinkable() for us, if needed,
which is also nicely balanced with set_pages().
Signed-off-by: Matthew Auld
Cc: Thomas
to come up with something
better later.
v4(Thomas):
- s/PCI_DMA/DMA/. Also drop NO_KERNEL_MAPPING and NO_WARN, which
apparently doesn't do anything with streaming mappings.
- Just pass along the error for ->truncate, and assume nothing.
Signed-off-by: Matthew Auld
Cc: Thomas Hellst
Attempt to document shrink_pin and the other relevant interfaces that
interact with it, before we start messing with it.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Reviewed-by: Thomas Hellström
---
.../gpu/drm/i915/gem/i915_gem_object_types.h | 24 +-
drivers/gpu/drm/i915
, which actually seems to fit quite well for what we want here.
v4(Thomas):
- Just use a simple boolean for tracking ttm_shrinkable.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Reviewed-by: Thomas Hellström
---
drivers/gpu/drm/i915/gem/i915_gem_object.h| 8 +++
.../
This should let us do an accelerated copy directly to the shmem pages
when temporarily moving lmem-only objects, where the i915-gem shrinker
can later kick in to swap out the pages, if needed.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Reviewed-by: Thomas Hellström
---
drivers/gpu/drm
Turn on the shmem tt backend, and enable shrinking.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Reviewed-by: Thomas Hellström
---
drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
b
("drm/i915: buddy allocator")
Signed-off-by: Matthew Auld
Cc: Arunpravin
Cc: Christian König
---
drivers/gpu/drm/i915/i915_buddy.c | 8 ++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_buddy.c
b/drivers/gpu/drm/i915/i915_buddy.c
ind
On 19/01/2022 17:47, Thomas Hellström wrote:
In some cases we use leftover kfree() instead of i915_vma_resource_free().
Fix this.
Fixes: Fixes: 2f6b90da9192 ("drm/i915: Use vma resources for async unbinding")
Reported-by: Robert Beckett
Cc: Matthew Auld
Signed-off-by: Thomas
On 20/01/2022 13:15, Robert Beckett wrote:
On 20/01/2022 11:46, Ramalingam C wrote:
On 2022-01-18 at 17:50:34 +, Robert Beckett wrote:
From: Matthew Auld
For local-memory objects we need to align the GTT addresses
to 64K, both for the ppgtt and ggtt.
We need to support vm
On 20/01/2022 15:44, Robert Beckett wrote:
On 20/01/2022 14:59, Matthew Auld wrote:
On 20/01/2022 13:15, Robert Beckett wrote:
On 20/01/2022 11:46, Ramalingam C wrote:
On 2022-01-18 at 17:50:34 +, Robert Beckett wrote:
From: Matthew Auld
For local-memory objects we need to align
On 20/01/2022 16:09, Robert Beckett wrote:
On 20/01/2022 15:58, Matthew Auld wrote:
On 20/01/2022 15:44, Robert Beckett wrote:
On 20/01/2022 14:59, Matthew Auld wrote:
On 20/01/2022 13:15, Robert Beckett wrote:
On 20/01/2022 11:46, Ramalingam C wrote:
On 2022-01-18 at 17:50:34 +
On 19/01/2022 11:37, Arunpravin wrote:
On contiguous allocation, we round up the size
to the *next* power of 2, implement a function
to free the unused pages after the newly allocate block.
v2(Matthew Auld):
- replace function name 'drm_buddy_free_unused_pages' with
drm_buddy_
to i915 driver
v3(Matthew Auld):
- Fix alignment issues and remove unnecessary list_empty check
- add more validation checks for input arguments
- make alloc_range() block allocations as bottom-up
- optimize order computation logic
- replace uint64_t with u64, which is preferred in
drm_buddy_free()
request and split up of larger blocks for a single page
request.
v2:
- Fix alignment issues(Matthew Auld)
- Remove unnecessary list_empty check(Matthew Auld)
- merged the below patch to see the feature in action
- add top-down alloc support to i915 driver
Signed-off-by
ake the test pass on systems with a small LMEM
BAR(256M), where before it was just running out of memory,
Reviewed-by: Matthew Auld
> ---
> drivers/gpu/drm/i915/gt/uc/selftest_guc.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/i915/gt
Ensure we drop the reference to the last rq, otherwise we are leaking
the context etc. Also don't zero the previous valid context.
Signed-off-by: Matthew Auld
Cc: Matthew Brost
---
drivers/gpu/drm/i915/gt/uc/selftest_guc.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --
Starting from DG2 we will have resizable BAR support for device local-memory,
but in some cases the final BAR size might still be smaller than the total
local-memory size. In such cases only part of local-memory will be CPU
accessible, while the remainder is only accessible via the GPU. This series
With small LMEM-BAR we need to be able to differentiate between the
total size of LMEM, and how much of it is CPU mappable. The end goal is
to be able to utilize the entire range, even if part of is it not CPU
accessible.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
---
drivers/gpu/drm
split up of larger blocks for a single page
request.
v2:
- Fix alignment issues(Matthew Auld)
- Remove unnecessary list_empty check(Matthew Auld)
- merged the below patch to see the feature in action
- add top-down alloc support to i915 driver
Signed-off-by: Arunpravin
---
drivers/gpu
From: Arunpravin
On contiguous allocation, we round up the size
to the *next* power of 2, implement a function
to free the unused pages after the newly allocate block.
v2(Matthew Auld):
- replace function name 'drm_buddy_free_unused_pages' with
drm_buddy_block_trim
- rep
Auld):
- Fix alignment issues and remove unnecessary list_empty check
- add more validation checks for input arguments
- make alloc_range() block allocations as bottom-up
- optimize order computation logic
- replace uint64_t with u64, which is preferred in the kernel
v4(Matthew Auld
this behaviour.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
---
drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 4
drivers/gpu/drm/i915/intel_region_ttm.c | 5 +
2 files changed, 9 insertions(+)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
b/drivers/gpu/drm/i915/gem
If the user doesn't require CPU access for the buffer, then
ALLOC_TOPDOWN should be used, in order to prioritise allocating in the
non-mappable portion of LMEM.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
---
drivers/gpu/drm/i915/gem/i915_gem_object_types.h | 15 +++
dr
in an actual move, instead of being turned into a noop.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
---
drivers/gpu/drm/i915/i915_ttm_buddy_manager.c | 7 +++
1 file changed, 7 insertions(+)
diff --git a/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c
b/drivers/gpu/dr
Otherwise we get -EINVAL, instead of the more useful -E2BIG if the
allocation doesn't fit within the pfn range, like with mappable lmem.
The hugepages selftest, for example, needs this to know if a smaller
size is needed.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
---
drivers/gp
for when deciding if we should attempt to evict certain
buffers.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
---
drivers/gpu/drm/i915/i915_ttm_buddy_manager.c | 55 ++-
drivers/gpu/drm/i915/i915_ttm_buddy_manager.h | 8 ++-
drivers/gpu/drm/i915/intel_region_ttm.c | 1
For some reason we are selecting PRIO_HAS_PAGES when we don't have
mm.pages, and vice versa. Perhaps something else is going on here.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
---
drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 6 ++
1 file changed, 2 insertions(+), 4 deletions(-)
placements permit it.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
---
drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 58 ++---
1 file changed, 52 insertions(+), 6 deletions(-)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
index
ce will be able to provide a hint if CPU access
to the buffer is needed.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
---
drivers/gpu/drm/i915/gem/i915_gem_create.c | 9 +
1 file changed, 9 insertions(+)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_create.c
b/drivers/gpu/dr
t way we hopefully victimize these last.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
---
drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 65 -
1 file changed, 63 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
b/drivers/gpu/drm/i91
601 - 700 of 1645 matches
Mail list logo
