On 06/09/2021 17:55, Thomas Hellström wrote:
An upcoming common pattern is to traverse the region object list and
perform certain actions on all objects in a region. It's a little tricky
to get the list locking right, in particular since a gem object may
change region unless it's pinned or the ob
On 06/09/2021 17:55, Thomas Hellström wrote:
Just evict unpinned objects to system. For pinned LMEM objects,
make a backup system object and blit the contents to that.
Backup is performed in three steps,
1: Opportunistically evict evictable objects using the gpu blitter.
2: After gt idle, evict
On 06/09/2021 17:55, Thomas Hellström wrote:
Pinned context images are now reset during resume. Don't back them up,
and assuming that rings can be assumed empty at suspend, don't back them
up either.
Introduce a new object flag, I915_BO_ALLOC_PM_VOLATILE meaning that an
object is allowed to lose
On 06/09/2021 17:55, Thomas Hellström wrote:
Pinned context images are now reset during resume. Don't back them up,
and assuming that rings can be assumed empty at suspend, don't back them
up either.
Introduce a new object flag, I915_BO_ALLOC_PM_VOLATILE meaning that an
object is allowed to lose
On 08/09/2021 13:26, Thomas Hellström wrote:
On Wed, 2021-09-08 at 12:07 +0100, Matthew Auld wrote:
On 06/09/2021 17:55, Thomas Hellström wrote:
Pinned context images are now reset during resume. Don't back them
up,
and assuming that rings can be assumed empty at suspend, don't ba
On Wed, 8 Sept 2021 at 14:29, Christian König
wrote:
>
> For now just a brief description of what TTM is all about.
>
> Signed-off-by: Christian König
Reviewed-by: Matthew Auld
Hi Christian,
We are looking into using shmem as a ttm_tt backend in i915 for cached
system memory objects. We would also like to make such objects visible
to the i915-gem shrinker, so that they may be swapped out or discarded
when under memory pressure.
One idea for handling this is roughly some
On 08/09/2021 18:38, Daniel Vetter wrote:
On Fri, Sep 03, 2021 at 12:24:05PM +0100, Matthew Auld wrote:
Currently we blow up in trace_dma_fence_init, when calling into
get_driver_name or get_timeline_name, since both the engine and context
might be NULL(or contain some garbage address) in the
to work with pages from a shmem file.
Hmm, what do you mean by reverse lookup functionality? Could you
please point out where that is in the TTM code?
>
> Regards,
> Christian.
>
> ____
> Von: Matthew Auld
> Gesendet: Donnerstag, 9. September 2021
pping/index behaviour for their
own purposes, so directly using shmem tt likely won't be usable there
as-is.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Cc: Christian König
---
drivers/gpu/drm/ttm/ttm_bo_vm.c | 4 ++--
drivers/gpu/drm/ttm/ttm_tt.c| 10 +-
include/drm/ttm
compute the page sizes using
the dma segments rather than using the physical page address segments.
Signed-off-by: Thomas Hellström
Reviewed-by: Matthew Auld
Signed-off-by: Matthew Auld
---
drivers/gpu/drm/i915/gem/i915_gem_shmem.c | 182 +-
1 file changed, 107 insertions(+), 75
Fixes some object-debug splat which appeared while debugging something
unrelated.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
---
drivers/gpu/drm/i915/gt/intel_context.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/gpu/drm/i915/gt/intel_context.c
b/drivers/gpu/drm/i915/gt
For cached objects we can allocate our pages directly in shmem. This
should make it possible(in a later patch) to utilise the existing
i915-gem shrinker code for such objects. For now this is still disabled.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Cc: Christian König
---
drivers/gpu
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
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
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 dbf06a2af8bf
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
pping/index behaviour for their
own purposes, so directly using shmem tt likely won't be usable there
as-is.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Cc: Christian König
---
drivers/gpu/drm/ttm/ttm_bo_vm.c | 4 ++--
drivers/gpu/drm/ttm/ttm_tt.c| 10 +-
include/drm/ttm
For cached objects we can allocate our pages directly in shmem. This
should make it possible(in a later patch) to utilise the existing
i915-gem shrinker code for such objects. For now this is still disabled.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Cc: Christian König
---
drivers/gpu
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 f02037a8cebd
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
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
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
On Tue, 14 Sept 2021 at 10:03, Christian König wrote:
>
> Am 14.09.21 um 10:50 schrieb Matthew Auld:
> > Add new flag to indicate special shmem based tt, which can directly
> > handle swapping itself, and should be visible to some shrinker.
> >
> > As p
perf_selftests+0x20/0x20 [i915]
> ? __i915_nop_setup+0x10/0x10 [i915]
> __run_selftests.part.3+0x10d/0x172 [i915]
> i915_live_selftests.cold.5+0x1f/0x47 [i915]
> i915_pci_probe+0x93/0x1d0 [i915]
>
> Signed-off-by: Maarten Lankhorst
> Closes: https://gitlab.freedesktop.org/drm/intel/issues/4129
Reviewed-by: Matthew Auld
at in the next patch.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Cc: 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_vm.c b/drivers/gpu/drm/ttm/ttm
later tries to touch them.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Cc: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 27 -
drivers/gpu/drm/ttm/ttm_tt.c| 25 ---
2 files changed, 26 insertions(+), 26 deletions(-)
No longer used it seems.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Cc: 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 100644
--- a/include/drm/ttm
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, and get rid of all the strange holes.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Cc: Christian König
---
include/drm/ttm/ttm
It covers more than just ttm_bo_type_sg usage, like with say dma-buf,
since one other user is userptr in amdgpu, and in the future we might
have some more. Hence EXTERNAL is likely a more suitable name.
Suggested-by: Christian König
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Cc
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
userptr). In the next patch we
want to introduce a shmem_tt backend, which should follow all the
existing rules with TTM_PAGE_FLAG_EXTERNAL, since it will need to handle
swapping itself, but with the above mapping restriction lifted.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Cc: Christian
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
For cached objects we can allocate our pages directly in shmem. This
should make it possible(in a later patch) to utilise the existing
i915-gem shrinker code for such objects. For now this is still disabled.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Cc: Christian König
---
drivers/gpu
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 e758de336b96
On 16/09/2021 10:03, Thomas Hellström wrote:
On Thu, 2021-09-16 at 08:55 +0200, Christian König wrote:
Am 15.09.21 um 20:59 schrieb Matthew Auld:
In commit:
commit 667a50db0477d47fdff01c666f5ee1ce26b5264c
Author: Thomas Hellstrom
Date: Fri Jan 3 11:17:18 2014 +0100
drm/ttm: Refuse
for operation, so make sure we can
disable accelerated copies.
v2:
- Fix a missing return value check (Matthew Auld)
Signed-off-by: Thomas Hellström
Reviewed-by: Matthew Auld
ned or the object lock is held.
Define a function that does this for us and that takes an argument that
defines the action to be performed on each object.
v3:
- Improve structure documentation a bit (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
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
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
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
ttm_move (Thomas)
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Reviewed-by: Thomas Hellström #v4
---
drivers/gpu/drm/i915/gem/i915_gem_object.h| 8 ++
.../gpu/drm/i915/gem/i915_gem_object_types.h | 14 +++-
drivers/gpu/drm/i915/gem/i915_gem_pages.c | 5 +-
drivers/
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
On 13/10/2021 14:38, Daniel Vetter wrote:
On Mon, Oct 11, 2021 at 09:41:44PM +0530, Ramalingam C wrote:
From: Matthew Auld
For local-memory objects we need to align the GTT addresses to 64K, both
for the ppgtt and ggtt.
Signed-off-by: Matthew Auld
Signed-off-by: Stuart Summers
Signed-off
On 14/10/2021 14:33, Daniel Vetter wrote:
On Wed, Oct 13, 2021 at 03:13:33PM +0100, Matthew Auld wrote:
On 13/10/2021 14:38, Daniel Vetter wrote:
On Mon, Oct 11, 2021 at 09:41:44PM +0530, Ramalingam C wrote:
From: Matthew Auld
For local-memory objects we need to align the GTT addresses to
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
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
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
ttm_move (Thomas)
v6(Reported-by: kernel test robot ):
- Remove unused i915_tt
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Reviewed-by: Thomas Hellström #v4
---
drivers/gpu/drm/i915/gem/i915_gem_object.h| 8 ++
.../gpu/drm/i915/gem/i915_gem_object_types.h | 14 ++-
drivers/
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
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
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
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
These are userspace objects, so mark them as such. In a later patch it's
useful to determine how paranoid we need to be when managing cache
flushes. In theory no functional changes.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
---
drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c | 3 ++-
1
These are userspace objects, so mark them as such. In a later patch it's
useful to determine how paranoid we need to be when managing cache
flushes. In theory no functional changes.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
---
drivers/gpu/drm/i915/gem/i915_gem_userptr.c | 3 ++-
1
, and since execbuf binds the object before doing the
async flush, there is a potential race window.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
---
drivers/gpu/drm/i915/gem/i915_gem_shmem.c | 12
1 file changed, 12 insertions(+)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_sh
It looks like we will need this in some more places, so extract as a
helper.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
---
drivers/gpu/drm/i915/gem/i915_gem_object.c | 26 ++
drivers/gpu/drm/i915/gem/i915_gem_object.h | 1 +
drivers/gpu/drm/i915/gem/i915_gem_shmem.c
Even though userptr objects are always coherent with the GPU, with no
way for userspace to change this with the set_caching ioctl, even on
non-LLC platforms, there is still the 'Bypass LCC' mocs setting, which
might permit reading the contents of main memory directly.
Signed-off-by: Ma
As pointed out by Thomas, we likely need to flush the pages here if the
GPU can read the page contents directly from main memory. Underneath we
don't know what the sg_table is pointing to, so just add a
wbinvd_on_all_cpus() here, for now.
Reported-by: Thomas Hellström
Signed-off-by: Matthew
l volatile
objects, such that we can re-acquire new pages, if so desired, without
needing a new object. As a result we should probably be paranoid here
and put the object back into the CPU domain when discarding the pages,
and also correctly set cache_dirty, if required.
Signed-off-by: Matthew Auld
Just like we do for internal objects. Also just use
i915_gem_object_set_cache_coherency() here. No need for over-flushing on
LLC platforms.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
---
drivers/gpu/drm/i915/gem/selftests/huge_pages.c | 7 ++-
1 file changed, 6 insertions(+), 1
Add some details around non-LLC platforms and cflushing, when dealing
with the flush-on-acquire, which is potentially security sensitive.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Cc: Daniel Vetter
---
.../gpu/drm/i915/gem/i915_gem_execbuffer.c| 11
.../gpu/drm/i915/gem
le should ideally be prefixed with 'drm/i915:'.
Can fix up when pushing though. Thanks,
Reviewed-by: Matthew Auld
---
drivers/gpu/drm/i915/selftests/mock_region.c | 2 --
1 file changed, 2 deletions(-)
diff --git a/drivers/gpu/drm/i915/selftests/mock_region.c
b/drivers/gpu/drm/i915
On 20/10/2021 09:04, Ran Jianping wrote:
From: ran jianping
'drm/ttm/ttm_placement.h' included in
'drivers/gpu/drm/i915/selftests/mock_region.c' is duplicated.
It is also included on the 9 line.
Reported-by: Zeal Robot
Signed-off-by: ran jianping
Pushed to drm-intel-gt-next. Thanks.
---
efore the
pages are populated.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
---
drivers/gpu/drm/i915/gem/i915_gem_clflush.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_clflush.c
b/drivers/gpu/drm/i915/gem/i915_gem_clflush.c
, 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
---
drivers/gpu/drm/i915/gem/i915_gem_clflush.c | 6 --
1 file changed, 4
Move it next to its partner in crime; gpu_write_needs_clflush.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
---
drivers/gpu/drm/i915/gem/i915_gem_domain.c | 12
drivers/gpu/drm/i915/gem/i915_gem_object.h | 15 ++-
drivers/gpu/drm/i915/i915_gem.c| 2
Should not be needed. Even with non-coherent display, we should be using
device local-memory there, and not system memory.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
---
drivers/gpu/drm/i915/gem/i915_gem_domain.c | 10 ++
drivers/gpu/drm/i915/gem/i915_gem_object.c | 7
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
---
drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c | 7 +++
1 file changed, 7 insertions(+)
diff --git a/drivers/gpu
We were overzealous here; even though discrete is non-LLC, it should
still be always coherent.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
---
drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/i915/gem
On Thu, 21 Oct 2021 at 11:36, Maarten Lankhorst
wrote:
>
> The signaled bit is already used for quick testing if a fence is signaled.
Why do we need this change? Can you add some more details to the commit please?
>
> Signed-off-by: Maarten Lankhorst
> ---
> drivers/gpu/drm/i915/Makefile
struct sg_table *pages)
> +{
> +}
> +
> +static const struct drm_i915_gem_object_ops pd_dummy_obj_ops = {
> + .name = "pd_dummy_obj",
> + .flags = I915_GEM_OBJECT_IS_SHRINKABLE,
I would assume we don't want this dummy object to be considered for shrinking?
goto err;
> +
> + return vma;
> +
> +err:
> + i915_gem_object_put(obj);
> + return vma;
> +}
> +
> static struct intel_ring *mock_ring(struct intel_engine_cs *engine)
> {
> - const unsigned long sz = PAGE_SIZE / 2;
> +
m_cache *slab_vmas;
>
> -struct i915_vma *i915_vma_alloc(void)
> +static struct i915_vma *i915_vma_alloc(void)
> {
> return kmem_cache_zalloc(slab_vmas, GFP_KERNEL);
> }
>
> -void i915_vma_free(struct i915_vma *vma)
> +static void i915_vma_free(struct i915_vm
On Thu, 21 Oct 2021 at 11:37, Maarten Lankhorst
wrote:
>
> Call drop_pages with the gem object lock held, instead of the other
> way around. This will allow us to drop the vma bindings with the
> gem object lock held.
>
> We plan to require the object lock for unpinning in the future,
> and this i
On Thu, 21 Oct 2021 at 11:36, Maarten Lankhorst
wrote:
>
> Big delta, but boils down to moving set_pages to i915_vma.c, and removing
> the special handling, all callers use the defaults anyway. We only remap
> in ggtt, so default case will fall through.
>
> Because we still don't require locking i
On Thu, 21 Oct 2021 at 11:37, Maarten Lankhorst
wrote:
>
> i915_vma_wait_for_bind needs the vma lock held, fix the caller.
>
> Signed-off-by: Maarten Lankhorst
> ---
> drivers/gpu/drm/i915/i915_vma.c | 40 +++--
> 1 file changed, 28 insertions(+), 12 deletions(-)
>
>
On Thu, 21 Oct 2021 at 11:37, Maarten Lankhorst
wrote:
>
> Signed-off-by: Maarten Lankhorst
Needs a proper commit message.
> ---
> drivers/gpu/drm/i915/i915_gem.c | 9 -
> 1 file changed, 8 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/
est is separated, it's a lot better to use
> i915_live_selftests, so each subtest starts with a clean slate, and a
> clean address space.
>
> Signed-off-by: Maarten Lankhorst
Reviewed-by: Matthew Auld
On Thu, 21 Oct 2021 at 11:37, Maarten Lankhorst
wrote:
>
> Now that freeing objects takes the object lock when destroying the
> backing pages, we can confidently take the object lock even for dead
> objects.
>
> Use this fact to take the object lock in the shrinker, without requiring
> a reference
On Thu, 21 Oct 2021 at 11:37, Maarten Lankhorst
wrote:
>
> Signed-off-by: Maarten Lankhorst
Needs a proper commit message.
On Fri, 22 Oct 2021 at 09:22, Daniel Vetter wrote:
>
> Gone with userptr rewrite by Maarten in ed29c2691188 ("drm/i915: Fix
> userptr so we do not have to worry about obj->mm.lock, v7.")
>
> Signed-off-by: Daniel Vetter
> Cc: Maarten Lankhorst
s/i195/i
On 22/10/2021 10:26, Thomas Hellström wrote:
Hi, Matt
On 10/21/21 14:53, Matthew Auld wrote:
We were overzealous here; even though discrete is non-LLC, it should
still be always coherent.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
---
drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c | 3
On Thu, 21 Oct 2021 at 18:30, Matthew Auld
wrote:
>
> On Thu, 21 Oct 2021 at 11:36, Maarten Lankhorst
> wrote:
> >
> > Big delta, but boils down to moving set_pages to i915_vma.c, and removing
> > the special handling, all callers use the defaults anyway. We only re
On Thu, 21 Oct 2021 at 11:37, Maarten Lankhorst
wrote:
>
> TTM already requires this, and we require it for delayed destroy.
>
> Signed-off-by: Maarten Lankhorst
Reviewed-by: Matthew Auld
The scratch page is directly visible in the users address space, and
while this is forced as CACHE_LLC, by the kernel, we still have to
contend with things like "Bypass-LLC" MOCS. So just flush no matter
what.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Cc: Chris Wilson
Cc: Ra
Normal users shouldn't be hitting this, likely this would indicate a
userspace bug. So don't bother caching, which should be safe now that we
manually flush the page.
Suggested-by: Chris Wilson
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Cc: Chris Wilson
Cc: Ramalingam C
--
On 21/10/2021 15:26, Ramalingam C wrote:
From: Bommu Krishnaiah
Replace the hard coded 4K alignment value with vm->min_alignment.
Cc: Wilson Chris P
Signed-off-by: Bommu Krishnaiah
Signed-off-by: Ramalingam C
Reviewed-by: Matthew Auld
Although likely want to squash patch patches 3
On 21/10/2021 15:26, Ramalingam C wrote:
From: Matthew Auld
XEHPSDV optimises 64K GTT pages for local-memory, since everything
should be allocated at 64K granularity. We say goodbye to sparse
entries, and instead get a compact 256B page-table for 64K pages,
which should be more cache friendly
On 22/10/2021 13:06, Kai Song wrote:
Fix inconsistent IS_ERR and PTR_ERR in i915_gem_dmabuf.c
Signed-off-by: Kai Song
Pushed to drm-intel-gt-next. Thanks.
---
drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/driv
On Thu, 21 Oct 2021 at 11:37, Maarten Lankhorst
wrote:
>
> Add a flag PIN_VALIDATE, to indicate we don't need to pin and only
> protected by the object lock.
>
> This removes the need to unpin, which is done by just releasing the
> lock.
>
> eb_reserve is slightly reworked for readability, but the
On Thu, 21 Oct 2021 at 11:37, Maarten Lankhorst
wrote:
>
> Be thorough..
>
> Signed-off-by: Maarten Lankhorst
Is this strictly needed for something? Needs a proper commit message anyway.
> ---
> drivers/gpu/drm/i915/i915_drv.h | 1 +
> 1 file changed, 1 insertion(+)
>
> diff --git a/drivers/gp
On 25/10/2021 12:32, Wan Jiabing wrote:
Fix following coccicheck warning:
./drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c:3117:15-22: WARNING:
ERR_CAST can be used with eb->requests[i].
Signed-off-by: Wan Jiabing
Pushed to drm-intel-gt-next. Thanks.
---
drivers/gpu/drm/i915/gem/i915_gem_
501 - 600 of 1645 matches
Mail list logo
