From: Zbigniew Kempczyński
As with new memory region era we will have to cover different sets
of memory regions inside the tests this patch adds support for
generating subtest names according to passed memory region collection.
Signed-off-by: Zbigniew Kempczyński
Signed-off-by: José Roberto de
From: Andrzej Turko
Added stubs for memory regions to make upstreaming of tests which are
using this interface possible.
The memory region uapi implementation in the driver is not stable yet.
Thus, the full memory region interface cannot be used in lib. This
commit adds stubs for this uapi to be
, Lukasz (1):
tests/i915/gem_exec_basic/dg1: Iterate over all memory regions
Lukasz Kalamarz (1):
lib/i915/intel_memory_region/dg1: Add new lib to query memory region
Matthew Auld (2):
i915_drm.h sync
tests/i915/gem_create: exercise placements extension
Zbigniew Kempczyński (1):
lib/i915
y: Dominik Grzegorzek
Signed-off-by: Lukasz Kalamarz
Signed-off-by: Vinay Belgaumkar
Cc: Janulgue Abdiel
Cc: Matthew Auld
Cc: Katarzyna Dec
Cc: Vanshidhar Konda
Cc: Stuart Summers
Cc: Zbigniew Kempczyński
---
tests/i915/gem_exec_basic.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
di
From: Dominik Grzegorzek
As we need to add new test variants, convert the code to standard
igt_main format so those variants can be easily accommodated.
Signed-off-by: Janusz Krzysztofik
Signed-off-by: Zbigniew Kempczyński
---
tests/i915/gem_gpgpu_fill.c | 25 -
1 file
The proper headers have now landed in include/uapi/drm/i915_drm.h, so we
can drop i915_gem_lmem.h and instead just reference the real headers for
pulling in the kernel doc.
Suggested-by: Daniel Vetter
Signed-off-by: Matthew Auld
---
Documentation/gpu/rfc/i915_gem_lmem.h | 237
On 11/05/2021 18:29, Daniel Vetter wrote:
On Tue, May 11, 2021 at 07:28:08PM +0200, Daniel Vetter wrote:
On Tue, May 11, 2021 at 06:03:56PM +0100, Matthew Auld wrote:
The proper headers have now landed in include/uapi/drm/i915_drm.h, so we
can drop i915_gem_lmem.h and instead just reference
On Tue, 11 May 2021 at 14:26, Thomas Hellström
wrote:
>
> Since objects can be migrated or evicted when not pinned or locked,
> update the checks for lmem residency or future residency so that
> the value returned is not immediately stale.
>
> Signed-off-by: Thomas Hellström
> ---
> drivers/gpu/
On Tue, 11 May 2021 at 14:26, Thomas Hellström
wrote:
>
> Temporarily remove the buddy allocator and related selftests
> and hook up the TTM range manager for i915 regions.
>
> In order to support some of the mock region-related selftests, we need to
> be able to initialize the TTM range-manager s
ces: https://gitlab.freedesktop.org/drm/intel/-/issues/3293
Reported-by: Ville Syrjälä
Signed-off-by: Chris Wilson
Signed-off-by: Matthew Auld
---
drivers/gpu/drm/i915/gem/i915_gem_pages.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c
b/drivers/gpu/dr
On Tue, 11 May 2021 at 14:26, Thomas Hellström
wrote:
>
> Most logical place to introduce TTM buffer objects is as an i915
> gem object backend. We need to add some ops to account for added
> functionality like delayed delete and LRU list manipulation.
>
> Initially we support only LMEM and SYSTEM
shrinking
Fixes: 0175969e489a ("drm/i915/gem: Use shrinkable status for unknown swizzle
quirks")
References: https://gitlab.freedesktop.org/drm/intel/-/issues/3293
Reported-by: Ville Syrjälä
Signed-off-by: Chris Wilson
Signed-off-by: Matthew Auld
---
drivers/gpu/drm/i915/gem/i915_g
Signed-off-by: Chris Wilson
Reviewed-by: Matthew Auld
Signed-off-by: Matthew Auld
Cc: # v5.12+
---
drivers/gpu/drm/i915/gem/i915_gem_pages.c | 2 ++
drivers/gpu/drm/i915/i915_gem.c | 11 +--
2 files changed, 7 insertions(+), 6 deletions(-)
diff --git a/drivers/gpu/dr
On Mon, 17 May 2021 at 14:11, Christoph Hellwig wrote:
>
> On Mon, May 17, 2021 at 04:09:42PM +0300, Serge Belyshev wrote:
> > Christoph Hellwig writes:
> >
> > > As an ad-hoc experiment: can you replace the call to remap_pfn_range
> > > with remap_pfn_range_notrack (and export it if you build i
by: Thomas Hellström
Reviewed-by: Matthew Auld
___
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
t; Signed-off-by: Thomas Hellström
> ---
> v2:
> - Fix an error unwind in lmem_get_pages() (Reported by Matthew Auld)
> - Break out and modify usage of i915_sg_dma_sizes() (Reported by Mattew Auld)
> - Break out TTM changes to a separate patch (Reported by Christian König)
> ---
>
t; Signed-off-by: Thomas Hellström
> ---
> v2:
> - Fix an error unwind in lmem_get_pages() (Reported by Matthew Auld)
> - Break out and modify usage of i915_sg_dma_sizes() (Reported by Mattew Auld)
> - Break out TTM changes to a separate patch (Reported by Christian König)
> ---
>
On Tue, 18 May 2021 at 14:21, Christoph Hellwig wrote:
>
> On Mon, May 17, 2021 at 06:06:44PM +0100, Matthew Auld wrote:
> > > Looks like it is caused by the validation failure then. Which means the
> > > existing code is doing something wrong in its choice of the page
On Tue, 11 May 2021 at 17:52, Matthew Auld wrote:
>
> Just the really basic stuff, which unlocks adding more interesting testcases
> later, like gem_lmem_swapping.
>
> On the kernel side we landed the uAPI bits[1] behind CONFIG_BROKEN, which is
> already enabled in CI build
a separate patch (Reported by
> Christian König).
> - Fix an unhandled error (Reported by Matthew Auld and Maarten Lankhorst)
> - Remove a stray leftover sg_table allocation (Reported by Matthew Auld)
> - Use ttm_tt_unpopulate() rather than ttm_tt_destroy() in the purge path
>
On Tue, 18 May 2021 at 09:28, Thomas Hellström
wrote:
>
> Since objects can be migrated or evicted when not pinned or locked,
> update the checks for lmem residency or future residency so that
> the value returned is not immediately stale.
>
> Signed-off-by: Thomas Hellström
Re
On Wed, 19 May 2021 at 09:49, Petri Latvala wrote:
>
> On Wed, May 19, 2021 at 09:13:37AM +0100, Matthew Auld wrote:
> > On Tue, 11 May 2021 at 17:52, Matthew Auld wrote:
> > >
> > > Just the really basic stuff, which unlocks adding more interesting
>
On Wed, 19 May 2021 at 12:00, Petri Latvala wrote:
>
> On Wed, May 19, 2021 at 11:45:17AM +0100, Matthew Auld wrote:
> > On Wed, 19 May 2021 at 09:49, Petri Latvala wrote:
> > >
> > > On Wed, May 19, 2021 at 09:13:37AM +0100, Matthew Auld wrote:
> > > >
: Use memory region interface
tests/i915/gem_media_fill: Use memory region interface
Dominik Grzegorzek (1):
tests/gem_gpgpu_fill: Convert from simple to standard igt_main
Kalamarz, Lukasz (1):
tests/i915/gem_exec_basic: Iterate over all memory regions
Matthew Auld (2):
i915_drm.h sync
Sync to get gem_create_ext and the regions query stuff.
Generated from kernel commit: 2459e56fd8af ("drm/i915/uapi: implement
object placement extension")
Signed-off-by: Matthew Auld
---
include/drm-uapi/i915_drm.h | 394
1 file changed, 360
-authored-by: Lukasz Kalamarz
Co-authored-by: Zbigniew Kempczynski
Signed-off-by: Andrzej Turko
Signed-off-by: Lukasz Kalamarz
Signed-off-by: Zbigniew Kempczynski
Cc: Zbigniew Kempczynski
Cc: Dominik Grzegorzek
Cc: Petri Latvala
Signed-off-by: Matthew Auld
---
lib/i915/intel_memory_region.c | 441
-off-by: Matthew Auld
---
benchmarks/gem_blt.c| 2 +-
benchmarks/gem_busy.c | 2 +-
benchmarks/gem_create.c | 2 +-
benchmarks/gem_exec_ctx.c | 2 +-
benchmarks/gem_exec_fault.c | 2 +-
benchmarks/gem_exec_nop.c
From: Dominik Grzegorzek
As we need to add new test variants, convert the code to standard
igt_main format so those variants can be easily accommodated.
Signed-off-by: Janusz Krzysztofik
Signed-off-by: Zbigniew Kempczyński
Signed-off-by: Matthew Auld
---
tests/i915/gem_gpgpu_fill.c | 25
From: Andrzej Turko
Converted the test gem_gpgpu_fill to use memory region uapi.
Signed-off-by: Andrzej Turko
Cc: Zbigniew Kempczynski
Cc: Dominik Grzegorzek
Cc: Petri Latvala
Signed-off-by: Matthew Auld
---
tests/i915/gem_gpgpu_fill.c | 42 ++---
1 file
From: Andrzej Turko
Converted the test gem_exec_basic to use the memory region uapi.
Signed-off-by: Andrzej Turko
Cc: Zbigniew Kempczynski
Cc: Dominik Grzegorzek
Cc: Petri Latvala
Signed-off-by: Matthew Auld
---
tests/i915/gem_exec_basic.c | 50 +
1
From: Andrzej Turko
Converted the test gem_media_fill to use memory region uapi.
Signed-off-by: Andrzej Turko
Cc: Zbigniew Kempczynski
Cc: Dominik Grzegorzek
Cc: Petri Latvala
Signed-off-by: Matthew Auld
---
tests/i915/gem_media_fill.c | 57 -
1 file
Add some explicit testcases for the create_ext placements extension.
Signed-off-by: Matthew Auld
Cc: Dominik Grzegorzek
Cc: Joonas Lahtinen
Signed-off-by: Matthew Auld
---
tests/i915/gem_create.c | 188
1 file changed, 188 insertions(+)
diff --git a
y: Dominik Grzegorzek
Signed-off-by: Lukasz Kalamarz
Signed-off-by: Vinay Belgaumkar
Cc: Janulgue Abdiel
Cc: Matthew Auld
Cc: Katarzyna Dec
Cc: Vanshidhar Konda
Cc: Stuart Summers
Cc: Zbigniew Kempczyński
Signed-off-by: Matthew Auld
---
tests/i915/gem_exec_basic.c | 3 ++-
1 file changed, 2 insert
o")
Signed-off-by: Chris Wilson
Cc: Tvrtko Ursulin
Cc: Chintan M Patel
Cc: Andi Shyti
Cc: # v5.7+
Signed-off-by: Matthew Auld
---
.../drm/i915/gt/intel_execlists_submission.c | 20 ++-
drivers/gpu/drm/i915/i915_request.c | 7 ++-
2 files changed, 21 inserti
On Thu, 20 May 2021 at 09:23, samirweng1979 wrote:
>
> From: wengjianfeng
>
> change 'freqency' to 'frequency'.
>
> Signed-off-by: wengjianfeng
Pushed to intel-gt-next. Thanks.
___
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.f
On Mon, 24 May 2021 at 13:05, Hillf Danton wrote:
>
> On Sun, 23 May 2021 12:47:34 -0700 Philippe Troin wrote:
> > Found the following bug on a FUJITSU LIFEBOOK S6520.
> >
> > The kernel crash happens when selecting a user from the gdm login
> > screen right after boot.
> > The same hardware has n
mcpy_from_wc(_dst, _src, _len) (false)
> +#define drm_has_memcpy_from_wc() (false)
Does the compiler not complain for these on !x86, if called without
checking the result of the statement? Maybe just make these function
stubs?
Otherwise,
Reviewed-by: Matthew Auld
> +#define drm_una
On Fri, 21 May 2021 at 16:33, Thomas Hellström
wrote:
>
> Use fast wc memcpy for reading out of wc memory for TTM bo moves.
>
> Cc: Dave Airlie
> Cc: Christian König
> Cc: Daniel Vetter
> Signed-off-by: Thomas Hellström
> ---
> drivers/gpu/drm/ttm/ttm_bo_util.c | 9 -
> 1 file changed
On Fri, 21 May 2021 at 16:33, Thomas Hellström
wrote:
>
> The internal ttm_bo_util memcpy uses ioremap functionality, and while it
> probably might be possible to use it for copying in- and out of
> sglist represented io memory, using io_mem_reserve() / io_mem_free()
> callbacks, that would cause
On Tue, 25 May 2021 at 10:32, Thomas Hellström
wrote:
>
>
> On 5/25/21 11:18 AM, Matthew Auld wrote:
> > On Fri, 21 May 2021 at 16:33, Thomas Hellström
> > wrote:
> >> The internal ttm_bo_util memcpy uses ioremap functionality, and while it
> >> probably
On Fri, 21 May 2021 at 16:33, Thomas Hellström
wrote:
>
> If the bo is idle when calling ttm_bo_pipeline_gutting(), we unnecessarily
> create a ghost object and push it out to delayed destroy.
> Fix this by adding a path for idle, and document the function.
>
> Also avoid having the bo end up in a
On Fri, 7 May 2021 at 10:12, Matthew Auld wrote:
>
> From: Chris Wilson
>
> The kernel prefers enabling fbc over the initial fb, since this leads to
> actual runtime power savings, so if the initial fb is deemed too big
> using some heuristic, then we simply skip alloca
NSOLE/CONFIG_FRAMEBUFFER_CONSOLE
Signed-off-by: Chris Wilson
Signed-off-by: Matthew Auld
Cc: Lee Shawn C
Cc: Ville Syrjälä
Cc: Daniel Vetter
Reviewed-by: Imre Deak
---
drivers/gpu/drm/i915/display/intel_display.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/driver
-off-by: Matthew Auld
Acked-by: Petri Latvala
---
benchmarks/gem_blt.c| 2 +-
benchmarks/gem_busy.c | 2 +-
benchmarks/gem_create.c | 2 +-
benchmarks/gem_exec_ctx.c | 2 +-
benchmarks/gem_exec_fault.c | 2
-authored-by: Lukasz Kalamarz
Co-authored-by: Zbigniew Kempczynski
Signed-off-by: Andrzej Turko
Signed-off-by: Lukasz Kalamarz
Signed-off-by: Zbigniew Kempczynski
Cc: Zbigniew Kempczynski
Cc: Dominik Grzegorzek
Cc: Petri Latvala
Signed-off-by: Matthew Auld
Acked-by: Petri Latvala
---
lib/i915
From: Andrzej Turko
Converted the test gem_exec_basic to use the memory region uapi.
Signed-off-by: Andrzej Turko
Cc: Zbigniew Kempczynski
Cc: Dominik Grzegorzek
Cc: Petri Latvala
Signed-off-by: Matthew Auld
Acked-by: Petri Latvala
---
tests/i915/gem_exec_basic.c | 50
From: Andrzej Turko
Converted the test gem_media_fill to use memory region uapi.
Signed-off-by: Andrzej Turko
Cc: Zbigniew Kempczynski
Cc: Dominik Grzegorzek
Cc: Petri Latvala
Signed-off-by: Matthew Auld
Acked-by: Petri Latvala
Reviewed-by: Zbigniew Kempczyński
---
tests/i915
y: Dominik Grzegorzek
Signed-off-by: Lukasz Kalamarz
Signed-off-by: Vinay Belgaumkar
Cc: Janulgue Abdiel
Cc: Matthew Auld
Cc: Katarzyna Dec
Cc: Vanshidhar Konda
Cc: Stuart Summers
Cc: Zbigniew Kempczyński
Signed-off-by: Matthew Auld
Acked-by: Petri Latvala
---
tests/i915/gem_exec_basic.c | 3 +
Sync to get gem_create_ext and the regions query stuff.
Generated from kernel commit: 2459e56fd8af ("drm/i915/uapi: implement
object placement extension")
Signed-off-by: Matthew Auld
Acked-by: Petri Latvala
---
include/drm-uapi/i915_drm.h | 394 --
From: Dominik Grzegorzek
As we need to add new test variants, convert the code to standard
igt_main format so those variants can be easily accommodated.
Signed-off-by: Janusz Krzysztofik
Signed-off-by: Matthew Auld
Reviewed-by: Zbigniew Kempczyński
Acked-by: Petri Latvala
---
tests/i915
From: Andrzej Turko
Converted the test gem_gpgpu_fill to use memory region uapi.
Signed-off-by: Andrzej Turko
Cc: Zbigniew Kempczynski
Cc: Dominik Grzegorzek
Cc: Petri Latvala
Signed-off-by: Matthew Auld
Acked-by: Petri Latvala
Reviewed-by: Zbigniew Kempczyński
---
tests/i915
Add some explicit testcases for the create_ext placements extension.
Signed-off-by: Matthew Auld
Cc: Dominik Grzegorzek
Cc: Joonas Lahtinen
Acked-by: Petri Latvala
---
tests/i915/gem_create.c | 188
1 file changed, 188 insertions(+)
diff --git a
On 26/05/2021 15:14, Tvrtko Ursulin wrote:
From: Chris Wilson
Only perform the domain transition under the object lock, and push the
required waits to outside the lock.
v2 (Tvrtko):
* Rebase.
Signed-off-by: Chris Wilson
Reviewed-by: Matthew Auld # v1
Signed-off-by: Tvrtko Ursulin
apping_map_user")
Cc: Christoph Hellwig
Cc: Daniel Vetter
Signed-off-by: Matthew Auld
---
drivers/gpu/drm/i915/Kconfig | 1 -
drivers/gpu/drm/i915/gem/i915_gem_mman.c | 9 ++---
drivers/gpu/drm/i915/i915_drv.h | 3 ++
drivers/gpu/drm/i915/i915_mm.c | 44 +
On Mon, 16 Aug 2021 at 09:49, Thomas Hellström
wrote:
>
> It's only used by the for_i915_gem_ww() macro and we can use
> the (typically) on-stack _err variable in its place.
>
> While initially setting the _err variable to -EDEADLK to enter the
> loop, we clear it before actually entering using fe
On Mon, 16 Aug 2021 at 18:14, Thomas Hellström
wrote:
>
> It's only used by the for_i915_gem_ww() macro and we can use
> the (typically) on-stack _err variable in its place.
>
> v2:
> - Don't clear the _err variable when entering the loop
> (Matthew Auld, Maarten
This should give a more complete view of the various bits of internal
resource manager state, for device local-memory.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
---
drivers/gpu/drm/i915/i915_debugfs.c | 12 +---
1 file changed, 9 insertions(+), 3 deletions(-)
diff --git a
.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
---
drivers/gpu/drm/i915/i915_buddy.c | 45 +++
drivers/gpu/drm/i915/i915_buddy.h | 8
drivers/gpu/drm/i915/i915_ttm_buddy_manager.c | 20 -
3 files changed, 72 insertions(+), 1 deletion
If the ttm_bo_init_reserved() call fails ensure we also release the
region, otherwise we leak the reference, or worse hit some uaf, when we
start using the objects.list. Also remove the make_unshrinkable call
here, which doesn't do anything.
Signed-off-by: Matthew Auld
Cc: Thomas Hell
On Thu, 19 Aug 2021 at 08:25, Thomas Hellström
wrote:
>
> On Wed, 2021-08-18 at 18:12 +0100, Matthew Auld wrote:
> > If the ttm_bo_init_reserved() call fails ensure we also release the
> > region, otherwise we leak the reference, or worse hit some uaf, when
> > we
> >
.
v2(Thomas):
- s/MB/MiB
- s/KB/KiB
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Reviewed-by: Thomas Hellström
---
drivers/gpu/drm/i915/i915_buddy.c | 45 +++
drivers/gpu/drm/i915/i915_buddy.h | 8
drivers/gpu/drm/i915
This should give a more complete view of the various bits of internal
resource manager state, for device local-memory.
v2(Thomas):
- Move the region printing into a nice helper
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
---
drivers/gpu/drm/i915/i915_debugfs.c| 4
On Thu, 19 Aug 2021 at 14:04, Patchwork
wrote:
>
> Patch Details
> Series:series starting with [v2,1/2] drm/i915/buddy: add some pretty printing
> URL:https://patchwork.freedesktop.org/series/93819/
> State:failure
> Details:https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_20853/index.html
>
> C
On Tue, 17 Aug 2021 at 18:28, Patchwork
wrote:
>
> Patch Details
> Series:drm/i915: Ditch the i915_gem_ww_ctx loop member (rev2)
> URL:https://patchwork.freedesktop.org/series/93711/
> State:failure
> Details:https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_20834/index.html
>
> CI Bug Log - chan
On Sun, 22 Aug 2021 at 17:30, Ayaz A Siddiqui 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
> Cc: Joonas L
On Sun, 22 Aug 2021 at 17:30, Ayaz A Siddiqui wrote:
>
> Removing extern declaration of i915_gem_lmem_obj_ops
> from i915_gem_lmem.h.
>
> Signed-off-by: Ayaz A Siddiqui
Reviewed-by: Matthew Auld
because all objects are
> allocated during driver load and if we have issues with lmem at that point
> something is seriously wrong with the system, so no point in trying to
> handle it.
>
> Cc: Matthew Auld
> Cc: Abdiel Janulgue
> Cc: Michal Wajdeczko
> Cc: Vinay Belgaum
, and will therefore already
hold the same value, it shouldn't matter. We still leave the
spin_lock_init() in the ctor, since we can't re-init the rq->lock in
case it is already held.
Fixes: 855e39e65cfc ("drm/i915: Initialise basic fence before acquiring seqno")
Signed-off-by:
If we need to mark the PDE as operating in 64K GTT mode, we should be
paranoid and flush the extra writes, like we already do for the PTEs. On
some platforms the clflush can apparently add the just the right amount
of magical delay to force the GPU to see the updated entry.
Signed-off-by: Matthew
forcing I915_SHRINK_ACTIVE.
v2: Some machine in the shard runs doesn't seem to have any available
swap when running this test. Try to handle this.
Signed-off-by: Matthew Auld
Cc: Tvrtko Ursulin
Cc: Thomas Hellström
Reviewed-by: Tvrtko Ursulin #v1
---
.../gpu/drm/i915/gem/selftests/huge_pa
On 06/09/2021 13:19, Tvrtko Ursulin wrote:
On 06/09/2021 10:17, Matthew Auld wrote:
Since the object might still be active here, the shrink_all will simply
ignore it, which blows up in the test, since the pages will still be
there. Currently THP is disabled which should result in the test
On 06/09/2021 13:53, Tvrtko Ursulin wrote:
On 06/09/2021 13:30, Matthew Auld wrote:
On 06/09/2021 13:19, Tvrtko Ursulin wrote:
On 06/09/2021 10:17, Matthew Auld wrote:
Since the object might still be active here, the shrink_all will simply
ignore it, which blows up in the test, since the
On 06/09/2021 17:55, Thomas Hellström wrote:
When backing up or restoring contents of pinned objects at suspend /
resume time we need to allocate a new object as the backup. Add a function
to facilitate copies between the two. Some data needs to be copied before
the migration context is ready for
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 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
> flags and caching before anyone else gets hold of the object.
>
> Signed-off-by: Thomas Hellström
> Reviewed-by: Matthew Auld
> ---
> v6:
> - Rebase on accelerated ttm moves.
> ---
> @@ -775,14 +845,13 @@ int __i915_gem_ttm_object_init(struct
> int
Just checking the current region is not enough, if we later migrate the
object somewhere else. For example if the placements are {SMEM, LMEM},
then we might get this wrong. Another idea might be to make the
page_alignment part of the ttm_place, instead of the BO.
Signed-off-by: Matthew Auld
Cc
mented from our ttm_tt_populate callback. We can then also reuse our
> own very elaborate shrinker for that memory.
>
> Signed-off-by: Thomas Hellström
> Reviewed-by: Matthew Auld
> ---
> v2:
> - Fix IS_ERR_OR_NULL() check to IS_ERR() (Reported by Matthew Auld)
> v3:
&g
On Tue, 22 Jun 2021 at 11:11, Thomas Hellström
wrote:
>
>
> On 6/22/21 11:58 AM, Matthew Auld wrote:
> > Just checking the current region is not enough, if we later migrate the
> > object somewhere else. For example if the placements are {SMEM, LMEM},
> > then we mi
On 22/06/2021 13:29, Thomas Hellström wrote:
On 6/22/21 2:15 PM, Matthew Auld wrote:
On Tue, 22 Jun 2021 at 11:11, Thomas Hellström
wrote:
On 6/22/21 11:58 AM, Matthew Auld wrote:
Just checking the current region is not enough, if we later migrate the
object somewhere else. For example if
Just checking the current region is not enough, if we later migrate the
object somewhere else. For example if the placements are {SMEM, LMEM},
then we might get this wrong. Another idea might be to make the
page_alignment part of the ttm_place, instead of the BO.
Signed-off-by: Matthew Auld
Cc
The min_page_size is only needed for pages inserted into the GTT, and
for our paging structures we only need at most 4K bytes, so simply
ignore the min_page_size restrictions here, otherwise we might see some
severe overallocation on some devices.
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
-off-by: Matthew Auld
Cc: Thomas Hellström
---
drivers/gpu/drm/i915/gem/i915_gem_create.c| 2 +-
drivers/gpu/drm/i915/gem/i915_gem_lmem.c | 33 +-
drivers/gpu/drm/i915/gem/i915_gem_lmem.h | 5 ++
drivers/gpu/drm/i915/gem/i915_gem_region.c| 10 ++-
drivers/gpu/drm/i915
On 23/06/2021 12:51, Thomas Hellström wrote:
On 6/23/21 1:26 PM, Matthew Auld wrote:
The min_page_size is only needed for pages inserted into the GTT, and
for our paging structures we only need at most 4K bytes, so simply
ignore the min_page_size restrictions here, otherwise we might see some
On 23/06/2021 14:32, Thomas Hellström wrote:
On 6/23/21 1:26 PM, Matthew Auld wrote:
The min_page_size is only needed for pages inserted into the GTT, and
for our paging structures we only need at most 4K bytes, so simply
ignore the min_page_size restrictions here, otherwise we might see some
buddy_man, and let
the user override it with the page-alignment, which looks cleaner
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
---
drivers/gpu/drm/i915/gem/i915_gem_create.c| 2 +-
drivers/gpu/drm/i915/gem/i915_gem_lmem.c | 33 +-
drivers/gpu/drm/i915/gem/i915_gem_lmem.h
: Matthew Auld
Cc: Thomas Hellström
Reviewed-by: Thomas Hellström
---
drivers/gpu/drm/i915/gt/intel_gtt.c | 14 +-
1 file changed, 13 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.c
b/drivers/gpu/drm/i915/gt/intel_gtt.c
index 084ea65d59c0..f7e0352edb62
warning: symbol 'i915_gem_ttm_obj_ops' was not declared. Should it be static?
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
---
drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
b/d
ernal fragmentation,
or having to remember to track things for all possible interfaces that
might want to allocate or reserve pages.
v2(Thomas): add some more kernel doc
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Reviewed-by: Thomas Hellström
---
drivers/gpu/drm/i915/i915_buddy.c
On Wed, 23 Jun 2021 at 20:15, Daniel Vetter wrote:
>
> On Wed, Jun 23, 2021 at 06:27:06PM +0100, Matthew Auld wrote:
> > Looks like it got lost along the way, so add it back. This is needed for
> > the region query uAPI where we want to report a snapshot of how much
>
: Ville Syrjälä
Cc: Matt Roper
Cc: Jani Saarinen
Signed-off-by: Clint Taylor
Signed-off-by: Jani Nikula
Signed-off-by: Matthew Auld
---
drivers/gpu/drm/i915/display/intel_bw.c | 52 +
1 file changed, 52 insertions(+)
diff --git a/drivers/gpu/drm/i915/display/intel_bw.c
From: Clint Taylor
Use MCHBAR Gear_type information to compute memory bandwidth available
during MCHBAR calculations.
Tested-by: Swati Sharma
Cc: Lucas De Marchi
Cc: Swati Sharma
Cc: Ville Syrjälä
Signed-off-by: Clint Taylor
Signed-off-by: Jani Nikula
Signed-off-by: Matthew Auld
le mmap ioctl for gen12+")
> Signed-off-by: Thomas Hellström
Reviewed-by: Matthew Auld
___
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
buddy_man, and let
the user override it with the page-alignment, which looks cleaner
v3: rebase on ttm sys changes
Signed-off-by: Matthew Auld
Cc: Thomas Hellström
Reviewed-by: Thomas Hellström
---
drivers/gpu/drm/i915/gem/i915_gem_create.c| 2 +-
drivers/gpu/drm/i915/gem/i915_gem_lmem.c
: Matthew Auld
Cc: Thomas Hellström
Reviewed-by: Thomas Hellström
---
drivers/gpu/drm/i915/gt/intel_gtt.c | 14 +-
1 file changed, 13 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.c
b/drivers/gpu/drm/i915/gt/intel_gtt.c
index 084ea65d59c0..f7e0352edb62
On 24/06/2021 19:31, Thomas Hellström wrote:
Introduce an interface to migrate objects between regions.
This is primarily intended to migrate objects to LMEM for display and
to SYSTEM for dma-buf, but might be reused in one form or another for
performande-based migration.
Signed-off-by: Thomas H
401 - 500 of 3792 matches
Mail list logo