On 14.1.2022 19.59, Andi Shyti wrote:
Hi Matt,
[...]
-int intel_uncore_setup_mmio(struct intel_uncore *uncore)
+int intel_uncore_setup_mmio(struct intel_uncore *uncore, phys_addr_t phys_addr)
{
struct drm_i915_private *i915 = uncore->i915;
- struct pci_dev *pdev = to_pci_dev(i9
the drm_vma_node itself to manage the file
> association (allow/revoke) dropping our need to keep an mmo per-file.
> Then if we keep a small rbtree of per-type mmap_offsets, we can lookup
> duplicate requests quickly.
As discussed, rbtree does do away with the limitation of the linear list
Re
On 17/01/2020 23.11, Chris Wilson wrote:
> Just keep on generating a new mmap_offset for the same old buffer, but
> for different handles and so exercise the scaling of the obj->mmo lists.
>
Reviewed-by: Abdiel Janulgue
> Signed-off-by: Chris Wilson
> C
Instead of testing individually our new fault handlers, iterate over all
memory regions and test all from one interface.
Signed-off-by: Abdiel Janulgue
Cc: Matthew Auld
Cc: Chris Wilson
Cc: Joonas Lahtinen
---
.../drm/i915/gem/selftests/i915_gem_mman.c| 233 --
1 file
Fault handler to handle missing pages for lmem objects.
v6: Use new remap_io_sg interface for noncontiguous fault handling
Signed-off-by: Abdiel Janulgue
Signed-off-by: Matthew Auld
Cc: Chris Wilson
Cc: Joonas Lahtinen
---
drivers/gpu/drm/i915/gem/i915_gem_lmem.c | 1 +
drivers/gpu/drm
Provide a way to set the PTE within apply_page_range for discontiguous
objects in addition to the existing method of just incrementing the pfn
for a page range.
Signed-off-by: Abdiel Janulgue
Cc: Chris Wilson
---
drivers/gpu/drm/i915/i915_drv.h | 3 ++
drivers/gpu/drm/i915/i915_mm.c | 67
Instead of testing individually our new fault handlers, iterate over all
memory regions and test all from one interface.
Signed-off-by: Abdiel Janulgue
Cc: Matthew Auld
Cc: Chris Wilson
Cc: Joonas Lahtinen
---
.../drm/i915/gem/selftests/i915_gem_mman.c| 233 --
1 file
Fault handler to handle missing pages for lmem objects.
v5: Use new remap_io_mapping interface for noncontiguous fault handling
Signed-off-by: Abdiel Janulgue
Signed-off-by: Matthew Auld
Cc: Chris Wilson
Cc: Joonas Lahtinen
---
drivers/gpu/drm/i915/gem/i915_gem_lmem.c | 13 ++
drivers
Provide a way to set the PTE of the physical address of kernel memory in
addition to just incrementing the pfn for a page range.
Signed-off-by: Abdiel Janulgue
Cc: Chris Wilson
---
drivers/gpu/drm/i915/gem/i915_gem_mman.c | 1 +
drivers/gpu/drm/i915/i915_drv.h | 4 +++-
drivers/gpu
On 17/12/2019 15.00, Patchwork wrote:
> == Series Details ==
>
> Series: series starting with [1/2] drm/i915: Add lmem fault handler
> URL : https://patchwork.freedesktop.org/series/71051/
> State : failure
>
> == Summary ==
>
> CI Bug Log - changes from CI_DRM_7580 -> Patchwork_15810
> ===
On 17/12/2019 14.14, Chris Wilson wrote:
> Quoting Abdiel Janulgue (2019-12-17 11:57:49)
>> Fault handler to handle missing pages for lmem objects.
>>
>> v4: Restore non-contigous fault handling in addition to remap_io_mapping
>>
>> Signed-off-by: Abdiel Janulgu
Fault handler to handle missing pages for lmem objects.
v4: Restore non-contigous fault handling in addition to remap_io_mapping
Signed-off-by: Abdiel Janulgue
Signed-off-by: Matthew Auld
Cc: Chris Wilson
Cc: Joonas Lahtinen
---
drivers/gpu/drm/i915/gem/i915_gem_lmem.c | 13 +
drivers
Instead of testing individually our new fault handlers, iterate over all
memory regions and test all from one interface.
Signed-off-by: Abdiel Janulgue
Cc: Matthew Auld
Cc: Chris Wilson
Cc: Joonas Lahtinen
---
.../drm/i915/gem/selftests/i915_gem_mman.c| 226 --
1 file
On 12/12/2019 17.19, Chris Wilson wrote:
> Quoting Matthew Auld (2019-12-12 15:11:02)
>> On Thu, 12 Dec 2019 at 14:20, Chris Wilson wrote:
>>>
>>> Quoting Abdiel Janulgue (2019-12-12 11:34:38)
>>>> Fault handler to handle missing pages for lmem ob
Fault handler to handle missing pages for lmem objects.
v3: Add get_vm_cpu_ops, iterate over all memory regions in the
lmem selftest, use remap_io_mapping.
Signed-off-by: Abdiel Janulgue
Signed-off-by: Matthew Auld
Cc: Chris Wilson
Cc: Joonas Lahtinen
---
drivers/gpu/drm/i915/gem
Fault handler to handle missing pages for lmem objects.
v2: Handle ENXIO in fault error, account for offset in region start
for fake lmem (Matt).
Add selftest (Chris).
Signed-off-by: Abdiel Janulgue
Signed-off-by: Matthew Auld
Cc: Chris Wilson
Cc: Joonas Lahtinen
---
drivers/gpu/drm
Fault handler to handle missing pages for lmem objects.
Signed-off-by: Abdiel Janulgue
Signed-off-by: Matthew Auld
Cc: Chris Wilson
Cc: Joonas Lahtinen
---
drivers/gpu/drm/i915/gem/i915_gem_lmem.c | 43
drivers/gpu/drm/i915/gem/i915_gem_lmem.h | 6
drivers/gpu
On 19/11/2019 13.37, Abdiel Janulgue wrote:
> +struct drm_i915_gem_mmap_offset {
> + /** Handle for the object being mapped. */
> + __u32 handle;
> + __u32 pad;
> + /**
> + * Fake offset to use for subsequent mmap call
> + *
> + * This is
DONLY instead of obj->readonly.
Signed-off-by: Abdiel Janulgue
Cc: Matthew Auld
Cc: Joonas Lahtinen
Cc: Chris Wilson
---
drivers/gpu/drm/i915/gem/i915_gem_domain.c| 3 +-
drivers/gpu/drm/i915/gem/i915_gem_mman.c | 241 +++---
drivers/gpu/drm/i915/gem/i915_ge
PTEs are revoked (Chris)
Signed-off-by: Abdiel Janulgue
Signed-off-by: Matthew Auld
Cc: Joonas Lahtinen
Reviewed-by: Chris Wilson
---
drivers/gpu/drm/i915/gem/i915_gem_mman.c | 129 ++
.../drm/i915/gem/selftests/i915_gem_mman.c| 48 ++-
2 files changed, 145
Prefer CPU WC mmaps via our new mmap offset plumbing otherwise fall-
back to GTT mmaps when hw doesn't support PAT
Signed-off-by: Abdiel Janulgue
Cc: Matthew Auld
Acked-by: Chris Wilson
---
drivers/gpu/drm/i915/gem/i915_gem_mman.c | 18 ++
drivers/gpu/drm/i91
s)
- Don't bail out on no PAT when doing WB mmaps
- Prepare uAPI for further extensions
v3:
- drop MMAP_OFFSET_FLAGS
v4:
- Tweaks, header re-org
Signed-off-by: Abdiel Janulgue
Signed-off-by: Matthew Auld
Cc: Joonas Lahtinen
---
drivers/gpu/drm/i915/gem/i915_gem_ioctls.h| 4 +-
driv
Fault handler to handle missing pages for shmem-backed objects.
v2: bail out of inserting PTEs when failing to insert the
fault address
v3: has struct page check
v4: Add self-test for validating CPU fault handler to ensure PTEs
are revoked when an object is unbound.
Signed-off-by: Abdiel
Prefer CPU WC mmaps via our new mmap offset plumbing otherwise fall-
back to GTT mmaps when hw doesn't support PAT
Signed-off-by: Abdiel Janulgue
Cc: Matthew Auld
---
drivers/gpu/drm/i915/gem/i915_gem_mman.c | 18 ++
drivers/gpu/drm/i915/gem/i915_gem_mman.h | 2 ++
driver
s)
- Don't bail out on no PAT when doing WB mmaps
- Prepare uAPI for further extensions
v3:
- drop MMAP_OFFSET_FLAGS
v4:
- Tweaks, header re-org
Signed-off-by: Abdiel Janulgue
Signed-off-by: Matthew Auld
Cc: Joonas Lahtinen
---
drivers/gpu/drm/i915/gem/i915_gem_ioctls.h| 4 +-
driv
aps on i915_gem_object_unbind() since unlike GTT
mmaps, they don't have bound i915_vmas objects. Rebase.
v6: Minor tweaks, header re-org (Chris)
Signed-off-by: Abdiel Janulgue
Cc: Matthew Auld
Cc: Joonas Lahtinen
Cc: Chris Wilson
---
drivers/gpu/drm/i915/gem/i915_gem_domain.c| 3 +-
driv
Fault handler to handle missing pages for shmem-backed objects.
v2: bail out of inserting PTEs when failing to insert the
fault address
v3: has struct page check
v4: Add self-test for validating CPU fault handler to ensure PTEs
are revoked when an object is unbound.
Signed-off-by: Abdiel
Prefer CPU WC mmaps via our new mmap offset plumbing otherwise fall-
back to GTT mmaps when hw doesn't support PAT
Signed-off-by: Abdiel Janulgue
Cc: Matthew Auld
---
drivers/gpu/drm/i915/gem/i915_gem_mman.c | 13 +
drivers/gpu/drm/i915/i915_drv.c | 1 +
drivers/gp
aps on i915_gem_object_unbind() since unlike GTT
mmaps, they don't have bound i915_vmas objects. Rebase.
Signed-off-by: Abdiel Janulgue
Cc: Matthew Auld
Cc: Joonas Lahtinen
Cc: Chris Wilson
---
drivers/gpu/drm/i915/gem/i915_gem_domain.c| 2 +-
drivers/gpu/drm/i915/gem/i915_gem_mman.c
s)
- Don't bail out on no PAT when doing WB mmaps
- Prepare uAPI for further extensions
v3:
- drop MMAP_OFFSET_FLAGS
Signed-off-by: Abdiel Janulgue
Signed-off-by: Matthew Auld
Cc: Joonas Lahtinen
---
drivers/gpu/drm/i915/gem/i915_gem_mman.c | 44 ++-
On 06/11/2019 10.26, Chris Wilson wrote:
> Provide a utility function to create a vma corresponding to an mmap() of
> our device. And use it to exercise the equivalent of userspace
> performing a GTT mmap of our objects.
>
> Signed-off-by: Chris Wilson
> Cc: Abdiel Janu
d explicitly control the mmap type (viz
> MMAP_OFFSET_IOCTL).
Reviewed-by: Abdiel Janulgue
>
> Signed-off-by: Chris Wilson
> Cc: Abdiel Janulgue
> Cc: Matthew Auld
> Cc: Joonas Lahtinen
> ---
> drivers/gpu/drm/i915/gem/i915_gem_mman.c | 3 +++
> 1 file changed, 3 inse
Prefer CPU WC mmaps via our new mmap offset plumbing otherwise fall-
back to GTT mmaps when hw doesn't support PAT
Signed-off-by: Abdiel Janulgue
Cc: Matthew Auld
---
drivers/gpu/drm/i915/gem/i915_gem_mman.c | 13 +
drivers/gpu/drm/i915/i915_drv.c | 1 +
drivers/gp
Fault handler to handle missing pages for shmem-backed objects.
v2: bail out of inserting PTEs when failing to insert the
fault address
v3: has struct page check
Signed-off-by: Abdiel Janulgue
Signed-off-by: Matthew Auld
Cc: Joonas Lahtinen
---
drivers/gpu/drm/i915/gem/i915_gem_mman.c
cts be ensuring it is
owned by the parent gem object instead of refcounting.
- Track mmo used by fencing to Avoid locking when revoking mmaps
during GPU reset.
- Rebase.
v3:
- Simplify mmo tracking
v4:
- use vma->mmo in __i915_gem_object_release_mmap_gtt
Signed-off-by: Abdiel Janulg
From: Daniele Ceraolo Spurio
The following patches in the series will use it to avoid certain
operations when the mappable aperture is not available in HW.
Signed-off-by: Daniele Ceraolo Spurio
Signed-off-by: Matthew Auld
---
drivers/gpu/drm/i915/i915_gem_gtt.h | 5 +
1 file changed, 5 in
s)
- Don't bail out on no PAT when doing WB mmaps
- Prepare uAPI for further extensions
v3:
- drop MMAP_OFFSET_FLAGS
Signed-off-by: Abdiel Janulgue
Signed-off-by: Matthew Auld
Cc: Joonas Lahtinen
---
drivers/gpu/drm/i915/gem/i915_gem_mman.c | 44 ++-
> i915_gem_mmap_gtt_ioctl(struct drm_device *dev, void *data,
> struct drm_file *file)
> {
> - struct drm_i915_gem_mmap_gtt *args = data;
> + struct drm_i915_gem_mmap_offset *args = data;
> + struct drm_i915_private *i915 = to_i915(dev);
> +
> + if (args->fl
From: Daniele Ceraolo Spurio
The following patches in the series will use it to avoid certain
operations when the mappable aperture is not available in HW.
Signed-off-by: Daniele Ceraolo Spurio
Signed-off-by: Matthew Auld
---
drivers/gpu/drm/i915/i915_gem_gtt.h | 5 +
1 file changed, 5 in
cts be ensuring it is
owned by the parent gem object instead of refcounting.
- Track mmo used by fencing to avoid locking when revoking mmaps
during GPU reset.
- Rebase.
v3:
- Simplify mmo tracking
v4:
- use vma->mmo in __i915_gem_object_release_mmap_gtt
Signed-off-by: Abdiel Janulg
Fault handler to handle missing pages for shmem-backed objects.
v2: bail out of inserting PTEs when failing to insert the
fault address
v3: has struct page check
Signed-off-by: Abdiel Janulgue
Signed-off-by: Matthew Auld
Cc: Joonas Lahtinen
---
drivers/gpu/drm/i915/gem/i915_gem_mman.c
s)
- Don't bail out on no PAT when doing WB mmaps
- Prepare uAPI for further extensions
v3:
- drop MMAP_OFFSET_FLAGS
Signed-off-by: Abdiel Janulgue
Signed-off-by: Matthew Auld
Cc: Joonas Lahtinen
---
drivers/gpu/drm/i915/gem/i915_gem_mman.c | 44 ++-
Prefer CPU WC mmaps via our new mmap offset plumbing otherwise fall-
back to GTT mmaps when hw doesn't support PAT
Signed-off-by: Abdiel Janulgue
Cc: Matthew Auld
---
drivers/gpu/drm/i915/gem/i915_gem_mman.c | 13 +
drivers/gpu/drm/i915/i915_drv.c | 1 +
drivers/gp
On 21/10/2019 16.35, Chris Wilson wrote:
> Quoting Abdiel Janulgue (2019-10-21 11:48:10)
>> +int
>> +i915_gem_mmap_dumb(struct drm_file *file,
>> + struct drm_device *dev,
>> + u32 handle,
>> + u64
From: Daniele Ceraolo Spurio
The following patches in the series will use it to avoid certain
operations when aperture is not available in HW.
Signed-off-by: Daniele Ceraolo Spurio
Cc: Matthew Auld
---
drivers/gpu/drm/i915/i915_drv.h | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drive
Fault handler to handle missing pages for shmem-backed objects.
v2: bail out of inserting PTEs when failing to insert the
fault address
v3: has struct page check
Signed-off-by: Abdiel Janulgue
Signed-off-by: Matthew Auld
Cc: Joonas Lahtinen
---
drivers/gpu/drm/i915/gem/i915_gem_mman.c
No reason for sticking to GTT mmaps now we have CPU WC mmaps via
our new mmap offset plumbing.
Signed-off-by: Abdiel Janulgue
Cc: Matthew Auld
---
drivers/gpu/drm/i915/gem/i915_gem_mman.c | 10 ++
drivers/gpu/drm/i915/i915_drv.c | 1 +
drivers/gpu/drm/i915/i915_drv.h
s)
- Don't bail out on no PAT when doing WB mmaps
- Prepare uAPI for further extensions
v3:
- drop MMAP_OFFSET_FLAGS
Signed-off-by: Abdiel Janulgue
Signed-off-by: Matthew Auld
Cc: Joonas Lahtinen
---
drivers/gpu/drm/i915/gem/i915_gem_mman.c | 44 ++-
cts be ensuring it is
owned by the parent gem object instead of refcounting.
- Track mmo used by fencing to Avoid locking when revoking mmaps
during GPU reset.
- Rebase.
v3:
- Simplify mmo tracking
v4:
- use vma->mmo in __i915_gem_object_release_mmap_gtt
Signed-off-by: Abdiel Janulg
On 15/10/2019 14.15, Chris Wilson wrote:
> Quoting Abdiel Janulgue (2019-10-15 09:37:23)
>> +int
>> +i915_gem_mmap_dumb(struct drm_file *file,
>> + struct drm_device *dev,
>> + u32 handle,
>> + u64 *offset)
>>
Don't bail out on no PAT when doing WB mmaps
- Prepare uAPI for further extensions
Signed-off-by: Abdiel Janulgue
Signed-off-by: Matthew Auld
Cc: Joonas Lahtinen
---
drivers/gpu/drm/i915/gem/i915_gem_mman.c | 36 +--
.../gpu/drm/i915/gem/i915_gem_object_types.h | 3
Fault handler to handle missing pages for shmem-backed objects.
v2: bail out of inserting PTEs when failing to insert the
fault address
Signed-off-by: Abdiel Janulgue
Signed-off-by: Matthew Auld
Cc: Joonas Lahtinen
---
drivers/gpu/drm/i915/gem/i915_gem_mman.c | 125
If there is no aperture we can't use map_gtt to map dumb buffers, so we
need a cpu-map based path to do it. We prefer map_gtt on platforms that
do have aperture.
Signed-off-by: Abdiel Janulgue
Cc: Daniele Ceraolo Spurio
Cc: Tvrtko Ursulin
Cc: Matthew Auld
---
drivers/gpu/drm/i91
From: Daniele Ceraolo Spurio
The following patches in the series will use it to avoid certain
operations when aperture is not available in HW.
Signed-off-by: Daniele Ceraolo Spurio
Cc: Matthew Auld
---
drivers/gpu/drm/i915/i915_drv.h | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drive
cts be ensuring it is
owned by the parent gem object instead of refcounting.
- Track mmo used by fencing to Avoid locking when revoking mmaps
during GPU reset.
- Rebase.
v3:
- Simplify mmo tracking
Signed-off-by: Abdiel Janulgue
Cc: Matthew Auld
Cc: Joonas Lahtinen
Cc: Chris Wil
cts be ensuring it is
owned by the parent gem object instead of refcounting.
- Track mmo used by fencing to Avoid locking when revoking mmaps
during GPU reset.
- Rebase
Signed-off-by: Abdiel Janulgue
Cc: Matthew Auld
Cc: Joonas Lahtinen
Cc: Chris Wilson
---
drivers/gpu/drm/i915/
If there is no aperture we can't use map_gtt to map dumb buffers, so we
need a cpu-map based path to do it. We prefer map_gtt on platforms that
do have aperture.
Signed-off-by: Abdiel Janulgue
Cc: Daniele Ceraolo Spurio
Cc: Tvrtko Ursulin
Cc: Matthew Auld
---
drivers/gpu/drm/i91
tween
them, when we inspect the flags.
Signed-off-by: Abdiel Janulgue
Signed-off-by: Matthew Auld
Cc: Joonas Lahtinen
---
drivers/gpu/drm/i915/gem/i915_gem_mman.c | 36 +--
.../gpu/drm/i915/gem/i915_gem_object_types.h | 3 ++
drivers/gpu/drm/i915/i915_drv.c
From: Daniele Ceraolo Spurio
The following patches in the series will use it to avoid certain
operations when aperture is not available in HW.
Signed-off-by: Daniele Ceraolo Spurio
Cc: Matthew Auld
---
drivers/gpu/drm/i915/i915_drv.h | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drive
Fault handler to handle missing pages for shmem-backed objects.
Signed-off-by: Abdiel Janulgue
Signed-off-by: Matthew Auld
Cc: Joonas Lahtinen
---
drivers/gpu/drm/i915/gem/i915_gem_mman.c | 125 ++-
1 file changed, 100 insertions(+), 25 deletions(-)
diff --git a/drivers
If there is no aperture we can't use map_gtt to map dumb buffers, so we
need a cpu-map based path to do it. We prefer map_gtt on platforms that
do have aperture.
Signed-off-by: Abdiel Janulgue
Cc: Daniele Ceraolo Spurio
Cc: Tvrtko Ursulin
Cc: Matthew Auld
---
drivers/gpu/drm/i91
From: Daniele Ceraolo Spurio
The following patches in the series will use it to avoid certain
operations when aperture is not available in HW.
Signed-off-by: Daniele Ceraolo Spurio
Cc: Matthew Auld
---
drivers/gpu/drm/i915/i915_drv.h | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drive
cts be ensuring it is
owned by the parent gem object instead of refcounting.
- Track mmo used by fencing to Avoid locking when revoking mmaps
during GPU reset.
- Rebase
Signed-off-by: Abdiel Janulgue
Cc: Matthew Auld
Cc: Joonas Lahtinen
Cc: Chris Wilson
---
drivers/gpu/drm/i915/
Fault handler to handle missing pages for shmem-backed objects.
Signed-off-by: Abdiel Janulgue
Signed-off-by: Matthew Auld
Cc: Joonas Lahtinen
---
drivers/gpu/drm/i915/gem/i915_gem_mman.c | 125 ++-
1 file changed, 100 insertions(+), 25 deletions(-)
diff --git a/drivers
tween
them, when we inspect the flags.
Signed-off-by: Abdiel Janulgue
Signed-off-by: Matthew Auld
Cc: Joonas Lahtinen
---
drivers/gpu/drm/i915/gem/i915_gem_mman.c | 36 +--
.../gpu/drm/i915/gem/i915_gem_object_types.h | 3 ++
drivers/gpu/drm/i915/i915_drv.c
On 02/09/2019 7.02, Chris Wilson wrote:
> It's been a long time since we accidentally reported -EIO upon wedging,
> it can now only be generated by failure to swap in a page.
>
Reviewed-by: Abdiel Janulgue
> Signed-off-by: Chris Wilson
> Cc: Abdiel Janulgue
> ---
>
Yup, this is a valid issue.
Reviewed-by: Abdiel Janulgue
On 26/08/2019 18.20, Chris Wilson wrote:
> Signed-off-by: Chris Wilson
> Cc: Abdiel Janulgue
> ---
> tests/i915/gem_mmap_gtt.c | 98 +++
> 1 file changed, 98 insertions(+)
>
&g
On 26/08/2019 15.48, Chris Wilson wrote:
> Quoting Abdiel Janulgue (2019-08-26 13:21:02)
>> +int
>> +i915_gem_mmap_dumb(struct drm_file *file,
>> + struct drm_device *dev,
>> + u32 handle,
>> + u64 *offset)
>>
If there is no aperture we can't use map_gtt to map dumb buffers, so we
need a cpu-map based path to do it. We prefer map_gtt on platforms that
do have aperture.
Signed-off-by: Abdiel Janulgue
Cc: Daniele Ceraolo Spurio
Cc: Tvrtko Ursulin
Cc: Matthew Auld
---
drivers/gpu/drm/i91
tween
them, when we inspect the flags.
Signed-off-by: Abdiel Janulgue
Signed-off-by: Matthew Auld
Cc: Joonas Lahtinen
---
drivers/gpu/drm/i915/gem/i915_gem_mman.c | 34 ++-
.../gpu/drm/i915/gem/i915_gem_object_types.h | 3 ++
drivers/gpu/drm/i915/i915_drv.c
Fault handler to handle missing pages for shmem-backed objects. Handle also
logic needed to refault pages depending on fault handler usage.
Signed-off-by: Abdiel Janulgue
Signed-off-by: Matthew Auld
Cc: Joonas Lahtinen
---
drivers/gpu/drm/i915/gem/i915_gem_domain.c | 2 +-
drivers/gpu/drm
From: Daniele Ceraolo Spurio
The following patches in the series will use it to avoid certain
operations when aperture is not available in HW.
Signed-off-by: Daniele Ceraolo Spurio
Cc: Matthew Auld
---
drivers/gpu/drm/i915/i915_drv.h | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drive
store extra data within vma->vm_private_data and assign
the pagefault ops for each mmap instance allowing objects to use multiple
fault handlers depending on its backing storage.
Signed-off-by: Abdiel Janulgue
Cc: Joonas Lahtinen
Cc: Chris Wilson
---
drivers/gpu/drm/i915/gem/i915_gem_mma
On 10/08/2019 15.38, Chris Wilson wrote:
> Closing the object on another file should not affect the local
> mmap_offset.
>
Thanks for this! It helped squeezed the bug out of mmap_offset.
Reviewed-by: Abdiel Janulgue
> Signed-off-by: Chris Wilson
> Cc: Abdiel Janulgue
>
the vma.
Reviewed-by: Abdiel Janulgue
>
> Signed-off-by: Chris Wilson
> Cc: Joonas Lahtinen
> Cc: Abdiel Janulgue
> ---
> drivers/gpu/drm/i915/i915_mm.c | 5 ++---
> 1 file changed, 2 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_mm.c b/dr
On 19/07/2019 16.07, Chris Wilson wrote:
> The top-level page directory for 36b is a single entry, not multiple
> like 32b. Fix up the rounding on the calculation of the size of the top
> level so that we populate the 4th level correctly for 36b.
>
Reviewed-by: Abdiel Janulgue
&
On 12/07/2019 14.27, Chris Wilson wrote:
> Apply the new radix shift helpers to extract the multi-level indices
> cleanly when inserting pte into the gtt tree.
>
Reviewed-by: Abdiel Janulgue
> Signed-off-by: Chris Wilson
> ---
> drivers/gpu/drm/i915/i9
On 12/07/2019 14.27, Chris Wilson wrote:
> Refactor the separate allocation routines into a single recursive
> function.
>
Reviewed-by: Abdiel Janulgue
> Signed-off-by: Chris Wilson
> ---
> drivers/gpu/drm/i915/i915_gem_gtt.c | 272 ++--
>
On 12/07/2019 14.27, Chris Wilson wrote:
> Refactor the separate allocation routines into a single recursive
> function.
>
Reviewed-by: Abdiel Janulgue
> Signed-off-by: Chris Wilson
> ---
> drivers/gpu/drm/i915/i915_gem_gtt.c | 272 ++--
>
y: Chris Wilson
> ---
Reviewed-by: Abdiel Janulgue
> drivers/gpu/drm/i915/Kconfig.debug | 15 +++
> drivers/gpu/drm/i915/i915_gem_gtt.c | 154
> 2 files changed, 105 insertions(+), 64 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/Kconfig.debug
>
r allocating for 32/36-bit vm.
>
> Signed-off-by: Chris Wilson
> ---
Reviewed-by: Abdiel Janulgue
Regards,
Abdiel
> drivers/gpu/drm/i915/i915_gem_gtt.c | 93 ++---
> drivers/gpu/drm/i915/i915_gem_gtt.h | 2 +-
> 2 files changed, 33 insertions(+), 62
On 06/04/2019 02:00 PM, Chris Wilson wrote:
>> +
>> + /* Access to snoopable pages through the GTT is incoherent. */
>> + if (obj->cache_level != I915_CACHE_NONE && !HAS_LLC(dev_priv)) {
>
> And that is very, very specific to one path.
>
Oops, yep that should be gtt-fault specific
Allow reuse of the fault-handling code in preparation for having
multiple fault handlers depending on the mmaping type and backing
storage.
Cc: Matthew Auld
Cc: Chris Wilson
Cc: Joonas Lahtinen
Signed-off-by: Abdiel Janulgue
---
drivers/gpu/drm/i915/gem/i915_gem_mman.c | 208
This simplifies adding new query item objects.
v2: Use query_hdr (Tvrtko, Chris).
int instead of u32 in return (Tvrtko)
v3: More naming fixes (Tvrtko)
Signed-off-by: Abdiel Janulgue
Cc: Joonas Lahtinen
---
drivers/gpu/drm/i915/i915_query.c | 39 ---
1 file
This simplifies adding new query item objects.
v2: Use query_hdr (Tvrtko, Chris).
int instead of u32 in return (Tvrtko)
Signed-off-by: Abdiel Janulgue
Cc: Joonas Lahtinen
---
drivers/gpu/drm/i915/i915_query.c | 39 ---
1 file changed, 26 insertions(+), 13
This simplifies adding new query item objects.
Signed-off-by: Abdiel Janulgue
Cc: Joonas Lahtinen
---
drivers/gpu/drm/i915/i915_query.c | 40 ---
1 file changed, 26 insertions(+), 14 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_query.c
b/drivers/gpu/drm
From: Chris Wilson
One important use of partial vma is to provide mappable access to the
object while it is being used elsewhere (pinned entirely into the
unmappable portion of the Global GTT, i.e. for use as a display scanout).
Signed-off-by: Chris Wilson
Cc: Joonas Lahtinen
---
drivers/gpu/
Add an additional comparison to check the entire vma created in the mappable
region of the global GTT against the one in the unmappable range.
Further test with an assert_partial as well to ensure the VMA corresponds
to the original object's backing store.
Signed-off-by: Abdiel Janulgu
quent series.
Reviewed-by: Abdiel Janulgue
___
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
eset by another client writing to i915_wedged.
>
> Signed-off-by: Chris Wilson
Reviewed-by: Abdiel Janulgue
> ---
> lib/igt_dummyload.c | 17 ++---
> tests/pm_rps.c | 4 +++-
> 2 files changed, 17 insertions(+), 4 deletions(-)
>
> diff --git a/li
or the override condition after
respecting the value of drm_dp_dual_mode_detect (Jani Nikula).
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=101649
Cc: Ville Syrjälä
Cc: Jani Nikula
Cc: Daniel Vetter
Signed-off-by: Abdiel Janulgue
---
drivers/gpu/drm/i915/intel_hdmi.c | 5 -
1
ow_bug.cgi?id=101649
Cc: Ville Syrjälä
Cc: Jani Nikula
Cc: Daniel Vetter
Signed-off-by: Abdiel Janulgue
---
drivers/gpu/drm/i915/intel_hdmi.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c
b/drivers/gpu/drm/i915/intel_hdmi.c
index bced7b
gem_hangcheck_forcewake has been superseded by drv_hangman, and a lot of
other very extensive hangchecking that is not run by CI (Chris).
v2: Split into multiple patches (Antonio Argenziano)
Signed-off-by: Abdiel Janulgue
Reviewed-by: Joonas Lahtinen
---
tests/Makefile.sources | 1
gem_pin ABI is going away (Chris).
Signed-off-by: Abdiel Janulgue
Reviewed-by: Joonas Lahtinen
---
tests/Makefile.sources | 1 -
tests/gem_pin.c| 248 -
tests/meson.build | 1 -
3 files changed, 250 deletions(-)
delete mode
gem_seqno_wrap is defunct as the debug API withered away. The
handling of wraparound under many different workloads is tested by
gem_exec_whisper (Chris).
Signed-off-by: Abdiel Janulgue
Reviewed-by: Joonas Lahtinen
---
tests/Makefile.sources | 1 -
tests/gem_seqno_wrap.c | 483
This improves the GEM tests section of I-G-T to make it more
suitable for CI testing
Cc: Joonas Lahtinen
Signed-off-by: Abdiel Janulgue
---
tests/Makefile.sources | 3 -
tests/gem_hangcheck_forcewake.c | 123 --
tests/gem_pin.c | 248
of intel_l3_parity prepended by [cmd], but that ended up
> being printed again prepended by [cmd] because output was redirected,
> causing outputs to appear multiple times. This patch fixes that.
>
> CC: Abdiel Janulgue
> Signed-off-by: Petri Latvala
Thanks for fixing this. Serie
lla: https://bugs.freedesktop.org/show_bug.cgi?id=101650
> CC: Abdiel Janulgue
> Signed-off-by: Petri Latvala
Reviewed-by: Abdiel Janulgue
> ---
> tests/tools_test.c | 83
> ++
> 1 file changed, 46 insertions(+), 37 dele
On 09/13/2017 01:10 PM, Petri Latvala wrote:
> On Wed, Sep 13, 2017 at 12:24:18PM +0300, Abdiel Janulgue wrote:
>> v3: Don't pipe the output of intel_l3_parity, parse it's output
>> directly. (Petri)
>>
>> v2: Check support before executing test.
>>
ned-off-by: Abdiel Janulgue
---
tests/tools_test.c | 64 ++
1 file changed, 36 insertions(+), 28 deletions(-)
diff --git a/tests/tools_test.c b/tests/tools_test.c
index 1baf60b..572d5f4 100644
--- a/tests/tools_test.c
+++ b/tests/tools_test.c
@@ -27
1 - 100 of 283 matches
Mail list logo
