[Intel-gfx] [PATCH i-g-t] Revert "lib/i915: request CPU_ACCESS for fb objects"

This reverts commit 3cf110f8dcd1f4f02cf84339664b413abdaebf7d. This is too big of a hammer it seems, since we can't really support flat-CCS with lmem + smem objects, and here adding the flag means we also attach the smem placement, which seems to break kms_ccs. Signed-off-by: Matthew Aul

Re: [Intel-gfx] [PATCH] drm/i915/selftests: Grab the runtime pm in shrink_thp

On Wed, 6 Jul 2022 at 16:48, Matthew Auld wrote: > > From: Chris Wilson > > Since we are not holding a wakeref, shrinking a bound object is not > guaranteed. > > Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/6370 > Signed-off-by: Chris Wilson Reviewed-by: Matthew Auld

[Intel-gfx] [PATCH] drm/i915/selftests: Grab the runtime pm in shrink_thp

From: Chris Wilson Since we are not holding a wakeref, shrinking a bound object is not guaranteed. Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/6370 Signed-off-by: Chris Wilson Signed-off-by: Matthew Auld --- drivers/gpu/drm/i915/gem/selftests/huge_pages.c | 7 ++- 1 file

[Intel-gfx] [PATCH i-g-t v2] tests/i915_query: tweak the unallocated tracking test

Make sure we always print the seed. Also make sure we use the correct helpers for the igt_assert when comparing values of type uint64. v2:(Nirmoy) - Fix broken conversion with s/lt/lte/ in a couple places. Signed-off-by: Matthew Auld Cc: Nirmoy Das --- tests/i915/i915_query.c | 36

[Intel-gfx] [PATCH i-g-t] tests/i915_query: tweak the unallocated tracking test

Make sure we always print the seed. Also make sure we use the correct helpers for the igt_assert when comparing values of type uint64. Signed-off-by: Matthew Auld Cc: Nirmoy Das --- tests/i915/i915_query.c | 36 +++- 1 file changed, 19 insertions(+), 17

[Intel-gfx] [PATCH i-g-t] tests/gem_exec_capture: adjust the pi subtest

This was broken by the kernel change: 71b1669ea9bd ("drm/i915/uapi: tweak error capture on recoverable contexts"). Update the test to use non-recoverable context if needed. Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/6350 Signed-off-by: Matthew Auld Cc: Nirmoy Das ---

Re: [Intel-gfx] [PATCH v6 3/3] drm/doc/rfc: VM_BIND uapi definition

On 30/06/2022 17:23, Matthew Auld wrote: On 30/06/2022 16:34, Jason Ekstrand wrote: On Thu, Jun 30, 2022 at 10:14 AM Matthew Auld <mailto:matthew.a...@intel.com>> wrote:     On 30/06/2022 06:11, Jason Ekstrand wrote: > On Sat, Jun 25, 2022 at 8:49 PM Niranjana Vis

Re: [Intel-gfx] [PATCH v2] drm/i915: Fix vm use-after-free in vma destruction

org/drm/intel/-/issues/5944 > Fixes: e1a7ab4fca ("drm/i915: Remove the vm open count") > > Cc: Niranjana Vishwanathapura > Cc: Matthew Auld > Signed-off-by: Thomas Hellström Reviewed-by: Matthew Auld

Re: [Intel-gfx] [PATCH v6 3/3] drm/doc/rfc: VM_BIND uapi definition

On 30/06/2022 16:34, Jason Ekstrand wrote: On Thu, Jun 30, 2022 at 10:14 AM Matthew Auld <mailto:matthew.a...@intel.com>> wrote: On 30/06/2022 06:11, Jason Ekstrand wrote: > On Sat, Jun 25, 2022 at 8:49 PM Niranjana Vishwanathapura > mailto:niranjana.vishwanath

Re: [Intel-gfx] [PATCH v6 3/3] drm/doc/rfc: VM_BIND uapi definition

On 30/06/2022 06:11, Jason Ekstrand wrote: On Sat, Jun 25, 2022 at 8:49 PM Niranjana Vishwanathapura > wrote: VM_BIND and related uapi definitions v2: Reduce the scope to simple Mesa use case. v3: Expand VM_UNBIND documentation and add

Re: [Intel-gfx] [PATCH 2/3] drm/i915/ttm: don't overwrite cache_dirty after setting coherency

On Tue, 28 Jun 2022 at 22:11, Robert Beckett wrote: > > > > On 14/06/2022 18:55, Matthew Auld wrote: > > On Tue, 14 Jun 2022 at 02:14, Adrian Larumbe > > wrote: > >> > >> When i915_gem_object_set_cache_level sets the GEM object's cache_dirty to &g

Re: [Intel-gfx] ✗ Fi.CI.IGT: failure for series starting with [CI,v4,01/13] drm/doc: add rfc section for small BAR uapi

On 30/06/2022 10:42, Patchwork wrote: *Patch Details* *Series:* series starting with [CI,v4,01/13] drm/doc: add rfc section for small BAR uapi *URL:* https://patchwork.freedesktop.org/series/105787/ *State:*failure *Details:* https://

[Intel-gfx] [PATCH i-g-t 9/9] lib/i915: request CPU_ACCESS for fb objects

e the mappable portion, if possible. Signed-off-by: Matthew Auld Cc: Thomas Hellström Reviewed-by: Nirmoy Das --- lib/ioctl_wrappers.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/lib/ioctl_wrappers.c b/lib/ioctl_wrappers.c index 09eb3ce7..7713e78b 100644 --- a/lib/ioctl_wrapp

[Intel-gfx] [PATCH i-g-t 8/9] tests/i915/capture: handle uapi changes

skipped, for now at least. v2: try to make it backwards compat Signed-off-by: Matthew Auld Cc: Thomas Hellström Reviewed-by: Nirmoy Das --- tests/i915/gem_exec_capture.c | 176 -- 1 file changed, 169 insertions(+), 7 deletions(-) diff --git a/tests/i915

[Intel-gfx] [PATCH i-g-t 7/9] lib/i915/intel_memory_region: plumb through the cpu_size

Will be useful later. Signed-off-by: Matthew Auld Cc: Thomas Hellström Reviewed-by: Nirmoy Das --- lib/i915/intel_memory_region.c | 2 ++ lib/i915/intel_memory_region.h | 1 + 2 files changed, 3 insertions(+) diff --git a/lib/i915/intel_memory_region.c b/lib/i915/intel_memory_region.c index

[Intel-gfx] [PATCH i-g-t 6/9] tests/i915/query: sanity check the unallocated tracking

Sanity both the unallocated_size & unallocated_cpu_visible_size tracking. v2(Petri): always use from_user_pointer() Signed-off-by: Matthew Auld Cc: Thomas Hellström Reviewed-by: Nirmoy Das --- tests/i915/i915_query.c | 274 +++- 1 file changed,

[Intel-gfx] [PATCH i-g-t 5/9] tests/i915/query: sanity check the probed_cpu_visible_size

Add some basic sanity checks for this, like checking if this falls within the probed_size. On older kernels the value reported here should be zero. Signed-off-by: Matthew Auld Cc: Thomas Hellström Reviewed-by: Nirmoy Das --- tests/i915/i915_query.c | 19 --- 1 file changed

[Intel-gfx] [PATCH i-g-t 4/9] lib/i915: add gem_create_with_cpu_access_in_memory_regions

r. Signed-off-by: Matthew Auld Cc: Thomas Hellström Reviewed-by: Nirmoy Das --- lib/i915/intel_memory_region.c | 10 +++-- lib/i915/intel_memory_region.h | 68 -- tests/i915/gem_eio.c | 1 + tests/i915/gem_lmem_swapping.c | 2 +- tests/i915/i91

[Intel-gfx] [PATCH i-g-t 3/9] tests/i915/gem_create: exercise NEEDS_CPU_ACCESS

Add some basic tests for this new flag. Signed-off-by: Matthew Auld Cc: Thomas Hellström Reviewed-by: Nirmoy Das --- tests/i915/gem_create.c | 309 +++- 1 file changed, 308 insertions(+), 1 deletion(-) diff --git a/tests/i915/gem_create.c b/tests/i915

[Intel-gfx] [PATCH i-g-t 1/9] lib/i915_drm_local: Add I915_GEM_CREATE_EXT_FLAG_NEEDS_CPU_ACCESS

For now dump into i915_drm_local.h. Once the uapi on the kernel side is merged, and is part of drm-next, we can sync the kernel headers and remove this. Signed-off-by: Matthew Auld Cc: Thomas Hellström Reviewed-by: Nirmoy Das --- lib/i915/i915_drm_local.h | 21 + 1 file

[Intel-gfx] [PATCH i-g-t 2/9] lib/i915: wire up optional flags for gem_create_ext

For now limit to direct callers. Signed-off-by: Matthew Auld Cc: Thomas Hellström Reviewed-by: Nirmoy Das --- lib/i915/gem_create.c | 9 ++--- lib/i915/gem_create.h | 5 +++-- lib/i915/intel_memory_region.c | 2 +- tests/i915/gem_create.c| 24

[Intel-gfx] [CI v4 12/13] drm/i915/ttm: disallow CPU fallback mode for ccs pages

s objects") Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Lionel Landwerlin Cc: Tvrtko Ursulin Cc: Jon Bloomfield Cc: Daniel Vetter Cc: Jordan Justen Cc: Kenneth Graunke Cc: Akeem G Abodunrin Cc: Ramalingam C --- drivers/gpu/drm/i915/gem/i915_gem_

[Intel-gfx] [CI v4 08/13] drm/i915/uapi: tweak error capture on recoverable contexts

integrated platforms, for capture buffer memory allocation purposes. v3 (Reported-by: kernel test robot ): - Fix build on !CONFIG_DRM_I915_CAPTURE_ERROR Testcase: igt@gem_exec_capture@capture-recoverable Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Lionel Landwerlin Cc: Tvrtko Ursulin Cc

[Intel-gfx] [CI v4 03/13] drm/i915/uapi: expose the avail tracking

Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Lionel Landwerlin Cc: Tvrtko Ursulin Cc: Jon Bloomfield Cc: Daniel Vetter Cc: Jordan Justen Cc: Kenneth Graunke Cc: Akeem G Abodunrin Reviewed-by: Thomas Hellström --- drivers/gpu/drm/i915/i915_query.c | 10 +- drivers/g

[Intel-gfx] [CI v4 11/13] drm/i915/ttm: handle blitter failure on DG2

e ordering of the set_wedged, also add FIXME. Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Lionel Landwerlin Cc: Tvrtko Ursulin Cc: Jon Bloomfield Cc: Daniel Vetter Cc: Jordan Justen Cc: Kenneth Graunke Cc: Akeem G Abodunrin Reviewed-by: Thomas Hellström --- drivers/gpu/dr

[Intel-gfx] [CI v4 09/13] drm/i915/selftests: skip the mman tests for stolen

It's not supported, and just skips later anyway. With small-BAR things get more complicated since all of stolen is likely not even CPU accessible, hence not passing I915_BO_ALLOC_GPU_ONLY just results in the object create failing. Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: L

[Intel-gfx] [CI v4 10/13] drm/i915/selftests: ensure we reserve a fence slot

We should always be explicit and allocate a fence slot before adding a new fence. Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Lionel Landwerlin Cc: Tvrtko Ursulin Cc: Jon Bloomfield Cc: Daniel Vetter Cc: Jordan Justen Cc: Kenneth Graunke Cc: Akeem G Abodunrin Reviewed-by: Thomas

[Intel-gfx] [CI v4 13/13] drm/i915: turn on small BAR support

With the uAPI in place we should now have enough in place to ensure a working system on small BAR configurations. v2: (Nirmoy & Thomas): - s/full BAR/Resizable BAR/ which is hopefully more easily understood by users. Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Lionel Landwe

[Intel-gfx] [CI v4 02/13] drm/i915/uapi: add probed_cpu_visible_size

through to the region query. v2: Drop the ( -1 = unknown ) stuff, which is confusing since nothing can currently ever return such a value. Testcase: igt@i915_query@query-regions-sanity-check Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Lionel Landwerlin Cc: Tvrtko Ursulin Cc: Jon

[Intel-gfx] [CI v4 07/13] drm/i915/error: skip non-mappable pages

Skip capturing any lmem pages that can't be copied using the CPU. This in now only best effort on platforms that have small BAR. Testcase: igt@gem-exec-capture@capture-invisible Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Lionel Landwerlin Cc: Tvrtko Ursulin Cc: Jon Bloomfiel

[Intel-gfx] [CI v4 06/13] drm/i915/uapi: add NEEDS_CPU_ACCESS hint

x27;t make space. Testcase: igt@gem-create@create-ext-cpu-access-sanity-check Testcase: igt@gem-create@create-ext-cpu-access-big Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Lionel Landwerlin Cc: Jon Bloomfield Cc: Daniel Vetter Cc: Jordan Justen Cc: Kenneth Graunke Cc: Akeem G Abod

[Intel-gfx] [CI v4 05/13] drm/i915/uapi: apply ALLOC_GPU_ONLY by default

eate@create-ext-cpu-access-big Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Lionel Landwerlin Cc: Tvrtko Ursulin Cc: Jon Bloomfield Cc: Daniel Vetter Cc: Jordan Justen Cc: Kenneth Graunke Cc: Akeem G Abodunrin Reviewed-by: Thomas Hellström --- drivers/gpu/drm/i915/gem/i915_g

[Intel-gfx] [CI v4 04/13] drm/i915: remove intel_memory_region avail

No longer used. Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Lionel Landwerlin Cc: Tvrtko Ursulin Cc: Jon Bloomfield Cc: Daniel Vetter Cc: Jordan Justen Cc: Kenneth Graunke Cc: Akeem G Abodunrin Reviewed-by: Thomas Hellström --- drivers/gpu/drm/i915/intel_memory_region.c | 4

[Intel-gfx] [CI v4 01/13] drm/doc: add rfc section for small BAR uapi

over. (Tvrtko) v5: - Include newer integrated platforms when applying the non-recoverable context and error capture restriction. (Thomas) Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Lionel Landwerlin Cc: Tvrtko Ursulin Cc: Jon Bloomfield Cc: Daniel Vetter Cc: Jordan Justen Cc: Ken

Re: [Intel-gfx] [PATCH v3 09/13] drm/i915/selftests: skip the mman tests for stolen

On 29/06/2022 17:22, Thomas Hellström wrote: On 6/29/22 14:14, Matthew Auld wrote: It's not supported, and just skips later anyway. With small-BAR things get more complicated since all of stolen is likely not even CPU accessible, hence not passing I915_BO_ALLOC_GPU_ONLY just results i

Re: [Intel-gfx] [PATCH v3 11/13] drm/i915/ttm: handle blitter failure on DG2

On 29/06/2022 17:11, Thomas Hellström wrote: Hi, Matthew, On 6/29/22 14:14, Matthew Auld wrote: If the move or clear operation somehow fails, and the memory underneath is not cleared, like when moving to lmem, then we currently fallback to memcpy or memset. However with small-BAR systems this

[Intel-gfx] [PATCH v3 13/13] drm/i915: turn on small BAR support

With the uAPI in place we should now have enough in place to ensure a working system on small BAR configurations. v2: (Nirmoy & Thomas): - s/full BAR/Resizable BAR/ which is hopefully more easily understood by users. Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Lionel Landwe

[Intel-gfx] [PATCH v3 12/13] drm/i915/ttm: disallow CPU fallback mode for ccs pages

s objects") Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Lionel Landwerlin Cc: Tvrtko Ursulin Cc: Jon Bloomfield Cc: Daniel Vetter Cc: Jordan Justen Cc: Kenneth Graunke Cc: Akeem G Abodunrin Cc: Ramalingam C --- drivers/gpu/drm/i915/gem/i915_gem_

[Intel-gfx] [PATCH v3 11/13] drm/i915/ttm: handle blitter failure on DG2

here. - Make sure we wedge each gt. (Thomas) - Peek at the unknown_state in io_reserve, that way we don't have to export or hand roll the fault_wait_for_idle. (Thomas) - Add the missing read-side barriers for the unknown_state. (Thomas) - Some kernel-doc fixes. (Thomas) Signed-off-by: Ma

[Intel-gfx] [PATCH v3 10/13] drm/i915/selftests: ensure we reserve a fence slot

We should always be explicit and allocate a fence slot before adding a new fence. Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Lionel Landwerlin Cc: Tvrtko Ursulin Cc: Jon Bloomfield Cc: Daniel Vetter Cc: Jordan Justen Cc: Kenneth Graunke Cc: Akeem G Abodunrin Reviewed-by: Thomas

[Intel-gfx] [PATCH v3 09/13] drm/i915/selftests: skip the mman tests for stolen

It's not supported, and just skips later anyway. With small-BAR things get more complicated since all of stolen is likely not even CPU accessible, hence not passing I915_BO_ALLOC_GPU_ONLY just results in the object create failing. Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: L

[Intel-gfx] [PATCH v3 07/13] drm/i915/error: skip non-mappable pages

Skip capturing any lmem pages that can't be copied using the CPU. This in now only best effort on platforms that have small BAR. Testcase: igt@gem-exec-capture@capture-invisible Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Lionel Landwerlin Cc: Tvrtko Ursulin Cc: Jon Bloomfiel

[Intel-gfx] [PATCH v3 05/13] drm/i915/uapi: apply ALLOC_GPU_ONLY by default

eate@create-ext-cpu-access-big Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Lionel Landwerlin Cc: Tvrtko Ursulin Cc: Jon Bloomfield Cc: Daniel Vetter Cc: Jordan Justen Cc: Kenneth Graunke Cc: Akeem G Abodunrin Reviewed-by: Thomas Hellström --- drivers/gpu/drm/i915/gem/i915_g

[Intel-gfx] [PATCH v3 04/13] drm/i915: remove intel_memory_region avail

No longer used. Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Lionel Landwerlin Cc: Tvrtko Ursulin Cc: Jon Bloomfield Cc: Daniel Vetter Cc: Jordan Justen Cc: Kenneth Graunke Cc: Akeem G Abodunrin Reviewed-by: Thomas Hellström --- drivers/gpu/drm/i915/intel_memory_region.c | 4

[Intel-gfx] [PATCH v3 06/13] drm/i915/uapi: add NEEDS_CPU_ACCESS hint

x27;t make space. Testcase: igt@gem-create@create-ext-cpu-access-sanity-check Testcase: igt@gem-create@create-ext-cpu-access-big Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Lionel Landwerlin Cc: Jon Bloomfield Cc: Daniel Vetter Cc: Jordan Justen Cc: Kenneth Graunke Cc: Akeem G Abod

[Intel-gfx] [PATCH v3 08/13] drm/i915/uapi: tweak error capture on recoverable contexts

integrated platforms, for capture buffer memory allocation purposes. v3 (Reported-by: kernel test robot ): - Fix build on !CONFIG_DRM_I915_CAPTURE_ERROR Testcase: igt@gem_exec_capture@capture-recoverable Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Lionel Landwerlin Cc: Tvrtko Ursulin Cc

[Intel-gfx] [PATCH v3 02/13] drm/i915/uapi: add probed_cpu_visible_size

through to the region query. v2: Drop the ( -1 = unknown ) stuff, which is confusing since nothing can currently ever return such a value. Testcase: igt@i915_query@query-regions-sanity-check Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Lionel Landwerlin Cc: Tvrtko Ursulin Cc: Jon

[Intel-gfx] [PATCH v3 03/13] drm/i915/uapi: expose the avail tracking

Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Lionel Landwerlin Cc: Tvrtko Ursulin Cc: Jon Bloomfield Cc: Daniel Vetter Cc: Jordan Justen Cc: Kenneth Graunke Cc: Akeem G Abodunrin Reviewed-by: Thomas Hellström --- drivers/gpu/drm/i915/i915_query.c | 10 +- drivers/g

[Intel-gfx] [PATCH v3 00/13] small BAR uapi bits

IGT: https://patchwork.freedesktop.org/series/104368/#rev2 Mesa: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/16739 -- 2.36.1

[Intel-gfx] [PATCH v3 01/13] drm/doc: add rfc section for small BAR uapi

over. (Tvrtko) v5: - Include newer integrated platforms when applying the non-recoverable context and error capture restriction. (Thomas) Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Lionel Landwerlin Cc: Tvrtko Ursulin Cc: Jon Bloomfield Cc: Daniel Vetter Cc: Jordan Justen Cc: Ken

[Intel-gfx] [PATCH i-g-t 3/3] tests/amdgpu/amdgpu_command_submission: fix uaf

dle); | ^~~~ ../lib/amdgpu/amd_command_submission.c:199:9: note: call to ‘free’ here 199 | free(ring_context); | ^~ Signed-off-by: Matthew Auld Cc: Petri Latvala --- lib/amdgpu/amd_command_submission.c

[Intel-gfx] [PATCH i-g-t 2/3] tests/kms_cursor_crc: fix truncated warning

73 |__va_arg_pack ()); |~~~~~ Signed-off-by: Matthew Auld Cc: Petri Latvala --- tests/kms_cursor_crc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tests/kms_cursor_crc.c b/tests/kms_cursor_crc.c index 5

[Intel-gfx] [PATCH i-g-t 1/3] lib/igt_device_scan: fix dangling pointer

p(v)); | ^ ../lib/igt_device_scan.c:351:22: note: ‘linkto’ declared here 351 | char linkto[PATH_MAX]; Signed-off-by: Matthew Auld Cc: Petri Latvala --- lib/igt_device_scan.c | 2 +- 1 file changed, 1 insertion(+)

Re: [Intel-gfx] [PATCH i-g-t 1/3] tests/i915/gem_eio: fix uaf

assume it's just a difference in compiler version or so. I have: gcc (GCC) 12.1.1 20220507 (Red Hat 12.1.1-1). Br, G.G. On 6/27/22 7:10 PM, Matthew Auld wrote: ../tests/i915/gem_eio.c:277:20: warning: pointer ‘ctx’ used after ‘free’ [-Wuse-after-free]    277 | igt_assert(igt_sy

Re: [Intel-gfx] [PATCH] drm/i915/gt: handle null ptr at sg traversing

On 27/06/2022 18:35, Ramalingam C wrote: When calculating the starting address for ccs data in smem scatterlist, handle the NULL pointer returned from sg_next, incase of scatterlist less than required size.. Do we have some more information on how we can hit this? Is this a programmer error? D

[Intel-gfx] [PATCH i-g-t 2/3] tests/i915/kms_mmap_write_crc: handle missing gem_get_caching()

from lmem, which can only be mapped as WC and so should always be coherent for scanout. Adjust the test and ensure it still passes as expected. Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/5303 Signed-off-by: Matthew Auld Cc: Gwan-gyeong Mun --- tests/i915/kms_mmap_write_crc.c

[Intel-gfx] [PATCH i-g-t 3/3] tests/i915: adapt __copy_ccs for discrete

We can't explicitly control the mmap caching type for discrete, but using mmap_device_coherent should be good enough here on such devices. Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/4842 Signed-off-by: Matthew Auld Cc: Gwan-gyeong Mun --- lib/intel_bufops.c

[Intel-gfx] [PATCH i-g-t 1/3] tests/i915/gem_eio: fix uaf

{ if (!(expr)) \ |^~~~ ../tests/i915/gem_eio.c:274:9: note: call to ‘free’ here 274 | free(ctx); Signed-off-by: Matthew Auld Cc: Gwan-gyeong Mun --- tests/i915/gem_eio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tests/i915/gem_eio.c b/tests/i915/gem_eio.c i

Re: [Intel-gfx] ✗ Fi.CI.IGT: failure for drm/i915: tweak the ordering in cpu_write_needs_clflush

On Mon, 27 Jun 2022 at 12:49, Patchwork wrote: > > Patch Details > Series:drm/i915: tweak the ordering in cpu_write_needs_clflush > URL:https://patchwork.freedesktop.org/series/105503/ > State:failure > Details:https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_105503v1/index.html > > CI Bug Log -

Re: [Intel-gfx] [PATCH v2 10/12] drm/i915/ttm: handle blitter failure on DG2

On Thu, 23 Jun 2022 at 16:31, Matthew Auld wrote: > > On 23/06/2022 15:52, Christian König wrote: > > Am 23.06.22 um 16:13 schrieb Matthew Auld: > >> [SNIP] > >>>> TTM_BO_VM_NUM_PREFAULT); > >>>> + /* > >>>> +

Re: [Intel-gfx] [PATCH v2 10/12] drm/i915/ttm: handle blitter failure on DG2

On 23/06/2022 15:52, Christian König wrote: Am 23.06.22 um 16:13 schrieb Matthew Auld: [SNIP] TTM_BO_VM_NUM_PREFAULT); +   /* +    * Ensure we check for any fatal errors if we had to move/clear +    * the object. The device should already be wedged if we hit

Re: [Intel-gfx] [PATCH v2 10/12] drm/i915/ttm: handle blitter failure on DG2

On 23/06/2022 08:00, Thomas Hellström wrote: On Tue, 2022-06-21 at 11:44 +0100, Matthew Auld wrote: If the move or clear operation somehow fails, and the memory underneath is not cleared, like when moving to lmem, then we currently fallback to memcpy or memset. However with small-BAR systems

[Intel-gfx] [PATCH] drm/i915: tweak the ordering in cpu_write_needs_clflush

: Fix prime_mmap to work when using LMEM") Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/5266 Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Gwan-gyeong Mun --- drivers/gpu/drm/i915/gem/i915_gem_domain.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/d

Re: [Intel-gfx] [PATCH] drm/i915/selftests: Increase timeout for live_parallel_switch

On Wed, 22 Jun 2022 at 15:11, Matthew Auld wrote: > > From: Akeem G Abodunrin > > With GuC submission, it takes a little bit longer switching contexts > among all available engines simultaneously, when running > live_parallel_switch subtest. Increase the timeout.

[Intel-gfx] [PATCH] drm/i915/selftests: Increase timeout for live_parallel_switch

Abodunrin Cc: Matthew Brost Signed-off-by: Matthew Auld --- drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c index

Re: [Intel-gfx] [PATCH 2/3] drm/i915: Fix i915_vma_pin_iomap()

On Tue, 21 Jun 2022 at 19:38, Juha-Pekka Heikkila wrote: > > On 21.6.2022 13.53, Matthew Auld wrote: > > On Mon, 20 Jun 2022 at 10:38, Juha-Pekka Heikkila > > wrote: > >> > >> On 10.6.2022 20.43, Matthew Auld wrote: > >>> On Fri, 10 Jun 2022 at 15

Re: [Intel-gfx] [PATCH i-g-t 1/2] drm/i915: Add support for LMEM PCIe resizable bar

gt; > Cc: Michael J Ruhl > > Cc: Prathap Kumar Valsan > > Signed-off-by: Priyanka Dandamudi > > Reviewed-by: Matthew Auld > > --- > > drivers/gpu/drm/i915/i915_driver.c | 92 ++ > > 1 file changed, 92 insertions(+) > >

Re: [Intel-gfx] [igt-dev] [PATCH i-g-t v2 6/9] tests/i915/query: sanity check the unallocated tracking

On 21/06/2022 13:41, Petri Latvala wrote: On Tue, Jun 21, 2022 at 11:29:58AM +0100, Matthew Auld wrote: Sanity both the unallocated_size & unallocated_cpu_visible_size tracking. Signed-off-by: Matthew Auld Cc: Thomas Hellström Reviewed-by: Nirmoy Das --- tests/i915/i915_query.c |

Re: [Intel-gfx] [PATCH 2/3] drm/i915: Fix i915_vma_pin_iomap()

On Mon, 20 Jun 2022 at 10:38, Juha-Pekka Heikkila wrote: > > On 10.6.2022 20.43, Matthew Auld wrote: > > On Fri, 10 Jun 2022 at 15:53, Matthew Auld > > wrote: > >> > >> On Fri, 10 Jun 2022 at 13:12, Juha-Pekka Heikkila > >> wrote: > >>>

[Intel-gfx] [PATCH v2 12/12] HAX: force small BAR on dg2

Just for CI. Signed-off-by: Matthew Auld --- drivers/gpu/drm/i915/gt/intel_region_lmem.c | 5 + 1 file changed, 5 insertions(+) diff --git a/drivers/gpu/drm/i915/gt/intel_region_lmem.c b/drivers/gpu/drm/i915/gt/intel_region_lmem.c index 82c3d2d0f0e0..62c3f8185852 100644 --- a/drivers/gpu

[Intel-gfx] [PATCH v2 11/12] drm/i915: turn on small BAR support

With the uAPI in place we should now have enough in place to ensure a working system on small BAR configurations. v2: (Nirmoy & Thomas): - s/full BAR/Resizable BAR/ which is hopefully more easily understood by users. Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Lionel Landwe

[Intel-gfx] [PATCH v2 09/12] drm/i915/selftests: ensure we reserve a fence slot

We should always be explicit and allocate a fence slot before adding a new fence. Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Lionel Landwerlin Cc: Tvrtko Ursulin Cc: Jon Bloomfield Cc: Daniel Vetter Cc: Jordan Justen Cc: Kenneth Graunke Cc: Akeem G Abodunrin --- drivers/gpu

[Intel-gfx] [PATCH v2 10/12] drm/i915/ttm: handle blitter failure on DG2

encounter such a scenario, and mark the object as borked to plug any holes where access to the memory underneath can happen. Add some basic selftests to exercise this. Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Lionel Landwerlin Cc: Tvrtko Ursulin Cc: Jon Bloomfield Cc: Daniel Vetter Cc

[Intel-gfx] [PATCH v2 08/12] drm/i915/uapi: tweak error capture on recoverable contexts

platforms, for capture buffer memory allocation purposes. Testcase: igt@gem_exec_capture@capture-recoverable Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Lionel Landwerlin Cc: Tvrtko Ursulin Cc: Jon Bloomfield Cc: Daniel Vetter Cc: Jordan Justen Cc: Kenneth Graunke Cc: Akeem G

[Intel-gfx] [PATCH v2 07/12] drm/i915/error: skip non-mappable pages

Skip capturing any lmem pages that can't be copied using the CPU. This in now only best effort on platforms that have small BAR. Testcase: igt@gem-exec-capture@capture-invisible Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Lionel Landwerlin Cc: Tvrtko Ursulin Cc: Jon Bloomfiel

[Intel-gfx] [PATCH v2 06/12] drm/i915/uapi: add NEEDS_CPU_ACCESS hint

x27;t make space. Testcase: igt@gem-create@create-ext-cpu-access-sanity-check Testcase: igt@gem-create@create-ext-cpu-access-big Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Lionel Landwerlin Cc: Jon Bloomfield Cc: Daniel Vetter Cc: Jordan Justen Cc: Kenneth Graunke Cc: Akeem G Abod

[Intel-gfx] [PATCH v2 05/12] drm/i915/uapi: apply ALLOC_GPU_ONLY by default

eate@create-ext-cpu-access-big Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Lionel Landwerlin Cc: Tvrtko Ursulin Cc: Jon Bloomfield Cc: Daniel Vetter Cc: Jordan Justen Cc: Kenneth Graunke Cc: Akeem G Abodunrin Reviewed-by: Thomas Hellström --- drivers/gpu/drm/i915/gem/i915_g

[Intel-gfx] [PATCH v2 04/12] drm/i915: remove intel_memory_region avail

No longer used. Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Lionel Landwerlin Cc: Tvrtko Ursulin Cc: Jon Bloomfield Cc: Daniel Vetter Cc: Jordan Justen Cc: Kenneth Graunke Cc: Akeem G Abodunrin Reviewed-by: Thomas Hellström --- drivers/gpu/drm/i915/intel_memory_region.c | 4

[Intel-gfx] [PATCH v2 03/12] drm/i915/uapi: expose the avail tracking

Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Lionel Landwerlin Cc: Tvrtko Ursulin Cc: Jon Bloomfield Cc: Daniel Vetter Cc: Jordan Justen Cc: Kenneth Graunke Cc: Akeem G Abodunrin --- drivers/gpu/drm/i915/i915_query.c | 10 +- drivers/gpu/drm/i915/i915_ttm_buddy_man

[Intel-gfx] [PATCH v2 02/12] drm/i915/uapi: add probed_cpu_visible_size

through to the region query. v2: Drop the ( -1 = unknown ) stuff, which is confusing since nothing can currently ever return such a value. Testcase: igt@i915_query@query-regions-sanity-check Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Lionel Landwerlin Cc: Tvrtko Ursulin Cc: Jon

[Intel-gfx] [PATCH v2 01/12] drm/doc: add rfc section for small BAR uapi

over. (Tvrtko) v5: - Include newer integrated platforms when applying the non-recoverable context and error capture restriction. (Thomas) Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Lionel Landwerlin Cc: Tvrtko Ursulin Cc: Jon Bloomfield Cc: Daniel Vetter Cc: Jordan Justen Cc: Ken

[Intel-gfx] [PATCH v2 00/12] small BAR uapi bits

Test-with: 20220621103001.184373-1-matthew.a...@intel.com IGT: https://patchwork.freedesktop.org/series/104368/#rev2 Mesa: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/16739 (WIP) -- 2.36.1

[Intel-gfx] [PATCH i-g-t v2 9/9] lib/i915: request CPU_ACCESS for fb objects

e the mappable portion, if possible. Signed-off-by: Matthew Auld Cc: Thomas Hellström Reviewed-by: Nirmoy Das --- lib/ioctl_wrappers.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/lib/ioctl_wrappers.c b/lib/ioctl_wrappers.c index 09eb3ce7..7713e78b 100644 --- a/lib/ioctl_wrapp

[Intel-gfx] [PATCH i-g-t v2 7/9] lib/i915/intel_memory_region: plumb through the cpu_size

Will be useful later. Signed-off-by: Matthew Auld Cc: Thomas Hellström Reviewed-by: Nirmoy Das --- lib/i915/intel_memory_region.c | 2 ++ lib/i915/intel_memory_region.h | 1 + 2 files changed, 3 insertions(+) diff --git a/lib/i915/intel_memory_region.c b/lib/i915/intel_memory_region.c index

[Intel-gfx] [PATCH i-g-t v2 5/9] tests/i915/query: sanity check the probed_cpu_visible_size

Add some basic sanity checks for this, like checking if this falls within the probed_size. On older kernels the value reported here should be zero. Signed-off-by: Matthew Auld Cc: Thomas Hellström Reviewed-by: Nirmoy Das --- tests/i915/i915_query.c | 19 --- 1 file changed

[Intel-gfx] [PATCH i-g-t v2 8/9] tests/i915/capture: handle uapi changes

skipped, for now at least. Signed-off-by: Matthew Auld Cc: Thomas Hellström Reviewed-by: Nirmoy Das --- tests/i915/gem_exec_capture.c | 145 -- 1 file changed, 138 insertions(+), 7 deletions(-) diff --git a/tests/i915/gem_exec_capture.c b/tests/i915

[Intel-gfx] [PATCH i-g-t v2 6/9] tests/i915/query: sanity check the unallocated tracking

Sanity both the unallocated_size & unallocated_cpu_visible_size tracking. Signed-off-by: Matthew Auld Cc: Thomas Hellström Reviewed-by: Nirmoy Das --- tests/i915/i915_query.c | 274 +++- 1 file changed, 273 insertions(+), 1 deletion(-) diff --git a/t

[Intel-gfx] [PATCH i-g-t v2 4/9] lib/i915: add gem_create_with_cpu_access_in_memory_regions

r. Signed-off-by: Matthew Auld Cc: Thomas Hellström Reviewed-by: Nirmoy Das --- lib/i915/intel_memory_region.c | 10 +++-- lib/i915/intel_memory_region.h | 68 -- tests/i915/gem_eio.c | 1 + tests/i915/gem_lmem_swapping.c | 2 +- tests/i915/i91

[Intel-gfx] [PATCH i-g-t v2 2/9] lib/i915: wire up optional flags for gem_create_ext

For now limit to direct callers. Signed-off-by: Matthew Auld Cc: Thomas Hellström Reviewed-by: Nirmoy Das --- lib/i915/gem_create.c | 9 ++--- lib/i915/gem_create.h | 5 +++-- lib/i915/intel_memory_region.c | 2 +- tests/i915/gem_create.c| 24

[Intel-gfx] [PATCH i-g-t v2 3/9] tests/i915/gem_create: exercise NEEDS_CPU_ACCESS

Add some basic tests for this new flag. Signed-off-by: Matthew Auld Cc: Thomas Hellström Reviewed-by: Nirmoy Das --- tests/i915/gem_create.c | 309 +++- 1 file changed, 308 insertions(+), 1 deletion(-) diff --git a/tests/i915/gem_create.c b/tests/i915

[Intel-gfx] [PATCH i-g-t v2 1/9] lib/i915_drm_local: Add I915_GEM_CREATE_EXT_FLAG_NEEDS_CPU_ACCESS

For now dump into i915_drm_local.h. Once the uapi on the kernel side is merged, and is part of drm-next, we can sync the kernel headers and remove this. Signed-off-by: Matthew Auld Cc: Thomas Hellström Reviewed-by: Nirmoy Das --- lib/i915/i915_drm_local.h | 21 + 1 file

[Intel-gfx] [PATCH i-g-t v2 0/9] small BAR uapi bits

-- 2.36.1

Re: [Intel-gfx] [PATCH 09/10] drm/i915: turn on small BAR support

On 17/06/2022 13:33, Thomas Hellström wrote: On 5/25/22 20:43, Matthew Auld wrote: With the uAPI in place we should now have enough in place to ensure a working system on small BAR configurations. Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Lionel Landwerlin Cc: Tvrtko Ursulin Cc

Re: [Intel-gfx] Access to Intel-gfx

On Fri, 17 Jun 2022 at 11:15, Golani, Mitulkumar Ajitkumar wrote: > > Hi Team, > > This is Mitul Golani from OSGC bangalore team. Please add me to intel-gfx > mailing list to see/post message to all the list members. You should be able to subscribe here: https://lists.freedesktop.org/mailman/lis

Re: [Intel-gfx] [PATCH] drm/i915: Improve on suspend / resume time with VT-d enabled

_lost = val; +} diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.h b/drivers/gpu/drm/i915/gt/intel_gtt.h index 4529b5e9f6e6..7561672c4f17 100644 --- a/drivers/gpu/drm/i915/gt/intel_gtt.h +++ b/drivers/gpu/drm/i915/gt/intel_gtt.h @@ -345,6 +345,15 @@ struct i915_ggtt { bool do_idle_maps; + /*

Re: [Intel-gfx] [PATCH 1/2] drm/i915: Add support for LMEM PCIe resizable bar

t amdgpu is already doing with their bar resizing stuff, Reviewed-by: Matthew Auld + * + * This function will attempt to resize LMEM bar to make all memory accessible. + * Whether it will be successful depends on both device and platform + * capabilities. Any errors are non-critical, even if resi

Re: [Intel-gfx] [PATCH 2/2] drm/i915: Add lmem_bar_size modparam

e etc) with all the potential lmem_bar sizes that we might expect see in the wild." ? Cc: Matthew Auld Signed-off-by: Priyanka Dandamudi --- drivers/gpu/drm/i915/gt/intel_region_lmem.c | 3 +++ drivers/gpu/drm/i915/i915_driver.c | 25 - drivers/gp

Re: [Intel-gfx] [PATCH 2/3] drm/i915/ttm: don't overwrite cache_dirty after setting coherency

On Tue, 14 Jun 2022 at 02:14, Adrian Larumbe wrote: > > When i915_gem_object_set_cache_level sets the GEM object's cache_dirty to > true, in the case of TTM that will sometimes be overwritten when getting > the object's pages, more specifically for shmem-placed objects for which > its ttm structur

Re: [Intel-gfx] [PATCH 2/3] drm/i915: Fix i915_vma_pin_iomap()

On Fri, 10 Jun 2022 at 15:53, Matthew Auld wrote: > > On Fri, 10 Jun 2022 at 13:12, Juha-Pekka Heikkila > wrote: > > > > From: CQ Tang > > > > Display might allocate a smem object and call > > i915_vma_pin_iomap(), the existing code will fail. > >

Re: [Intel-gfx] [PATCH 2/3] drm/i915: Fix i915_vma_pin_iomap()

n_map_unlocked(). > > v2 (jheikkil): Change i915_gem_object_pin_map_unlocked to >i915_gem_object_pin_map > > Signed-off-by: CQ Tang > Signed-off-by: Juha-Pekka Heikkila > Cc: Chris Wilson > Cc: Jari Tahvanainen Reviewed-by: Matthew Auld

<    1   2   3   4   5   6   7   8   9   10   >