: https://gitlab.freedesktop.org/drm/intel/-/issues/4932
Signed-off-by: Daniele Ceraolo Spurio
Cc: Matthew Brost
Cc: John Harrison
Reviewed-by: John Harrison
---
.../gpu/drm/i915/gt/uc/intel_guc_submission.c | 27 ++-
1 file changed, 14 insertions(+), 13 deletions(-)
diff
On 2/8/2022 01:39, Tvrtko Ursulin wrote:
On 08/02/2022 02:07, john.c.harri...@intel.com wrote:
From: John Harrison
A flag query helper was actually writing to the flags word rather than
just reading. Fix that. Also update the function's comment as it was
out of date.
Fixes: 0f7976506de61
Hmm, this is actually v1 not v3! Had something stale when posting.
John.
On 2/7/2022 12:36, john.c.harri...@intel.com wrote:
From: John Harrison
First release of GuC for DG2.
Signed-off-by: John Harrison
CC: Tomasz Mistat
CC: Ramalingam C
CC: Daniele Ceraolo Spurio
---
drivers/gpu
FFF, 0x, 0xFF00,
};
The attribute ids are defined in a hardware spec.
Cc: Tvrtko Ursulin
Cc: Kenneth Graunke
Cc: Michal Wajdeczko
Cc: Slawomir Milczarek
Signed-off-by: Rodrigo Vivi
Signed-off-by: John Harrison
Reviewed-by: Matthew Brost
---
drivers/gpu/drm/i915/i915_quer
On 1/28/2022 01:34, Tvrtko Ursulin wrote:
John,
What CI results were used to merge this particular single patch?
Unless I am not seeing it, it was always set in pair with something else.
First with "drm/i915/pmu: Use PM timestamp instead of RING TIMESTAMP
for reference", which was merged
mean that it doesn't exist.
John.
Cc: Tvrtko Ursulin
Cc: Kenneth Graunke
Cc: Michal Wajdeczko
Cc: Slawomir Milczarek
Signed-off-by: Rodrigo Vivi
Signed-off-by: John Harrison
Reviewed-by: Matthew Brost
---
drivers/gpu/drm/i915/i915_query.c | 23 +++
include/uapi/dr
On 1/24/2022 07:01, Matthew Brost wrote:
More than 1 request can be submitted to a single ELSP at a time if
multiple requests are ready run to on the same context. When a request
is canceled it is marked bad, an idle pulse is triggered to the engine
(high priority kernel request), the execlists
On 1/24/2022 07:01, Matthew Brost wrote:
Change the preemption timeout to the smallest possible value (1 us) when
disabling scheduling to cancel a request and restore it after
cancellation. This not only cancels the request as fast as possible, it
fixes a bug where the preemption timeout is 0
On 1/25/2022 01:13, Colin Ian King wrote:
There is a spelling mistake in a drm_err error message. Fix it.
Signed-off-by: Colin Ian King
Reviewed-by: John Harrison
However, note that this message is going to be deleted anyway. Or at
least dropped down to an informational. Partly
On 1/20/2022 20:31, Matthew Brost wrote:
The G2H handler needs to be flushed during a GT reset but a G2H
indicating engine reset failure can trigger a GT reset. Add a worker to
trigger the GT rest when an engine reset failure is received to break
this circular dependency.
v2:
(John Harrison
GuC generated G2H (e.g. engine resets) race with a GT
reset.
v2:
(John Harrison)
- Fix typo in commit message (s/is/in)
Signed-off-by: Matthew Brost
Reviewed-by: John Harrison
---
.../gpu/drm/i915/gt/uc/intel_guc_submission.c | 18 +-
1 file changed, 1 insertion(+), 17
:
(John Harrison)
- Store engine reset mask
- Fix typo in commit message
Signed-off-by: Matthew Brost
---
drivers/gpu/drm/i915/gt/uc/intel_guc.h| 9 +
.../gpu/drm/i915/gt/uc/intel_guc_submission.c | 37 +--
2 files changed, 42 insertions(+), 4 deletions
On 1/11/2022 08:39, Matthew Brost wrote:
Don't use the interruptable version of the timeline mutex lock in the
error path of eb_pin_timeline as the cleanup must always happen.
v2:
(John Harrison)
- Don't check for interrupt during mutex lock
v3:
(Tvrtko)
- A comment explaining why
On 1/19/2022 16:42, Patchwork wrote:
Project List - Patchwork *Patch Details*
*Series:* Add support for querying hw info that UMDs need
*URL:* https://patchwork.freedesktop.org/series/99060/
*State:*failure
*Details:*
On 1/19/2022 12:47, Matthew Brost wrote:
On Tue, Jan 18, 2022 at 05:29:54PM -0800, John Harrison wrote:
On 1/18/2022 13:43, Matthew Brost wrote:
Allocate intel_engine_coredump_alloc with ALLOW_FAIL rather than
GFP_KERNEL do fully decouple the error capture from fence signalling.
s/do
On 1/18/2022 13:43, Matthew Brost wrote:
Now that the error capture is fully decoupled from fence signalling
(request retirement to free memory, which is turn depends on resets) we
s/is/in/
With that fixed:
Reviewed-by: John Harrison
John.
can safely flush the G2H handler during a GT reset
On 1/18/2022 13:43, Matthew Brost wrote:
The G2H handler needs to be flushed during a GT reset but a G2H
indicating engine reset failure can trigger a GT reset. Add a worker to
trigger the GT when a engine reset failure is received to break this
s/a/an/
circular dependency.
Signed-off-by:
On 1/18/2022 13:43, Matthew Brost wrote:
Allocate intel_engine_coredump_alloc with ALLOW_FAIL rather than
GFP_KERNEL do fully decouple the error capture from fence signalling.
s/do/to/
Fixes: 8b91cdd4f8649 ("drm/i915: Use __GFP_KSWAPD_RECLAIM in the capture code")
Does this really count as a
good. There was a checkpatch warning about blank lines. With that
fixed:
Reviewed-by: John Harrison
---
.../gpu/drm/i915/gt/uc/intel_guc_submission.c | 32 +++
1 file changed, 26 insertions(+), 6 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
b
On 1/13/2022 13:06, Matthew Brost wrote:
On Thu, Jan 13, 2022 at 11:59:44AM -0800, john.c.harri...@intel.com wrote:
From: John Harrison
The update to use intel_ctx_t missed a line that configures the
context to allow hanging. Fix that.
Fixes: 09c36188b23f83ef9a7b5414e2a10100adc4291f
On 1/13/2022 13:01, Matthew Brost wrote:
On Thu, Jan 13, 2022 at 11:59:43AM -0800, john.c.harri...@intel.com wrote:
From: John Harrison
The global context used by all the subtests for causing hangs is
marked as unbannable. However, some of the subtests set background
spinners running on all
On 1/13/2022 12:30, Matthew Brost wrote:
On Thu, Jan 13, 2022 at 11:59:41AM -0800, john.c.harri...@intel.com wrote:
From: John Harrison
The hang test was relying on context persitence for no particular
reason. That is, it would set a bunch of background spinners running
then immediately
On 1/13/2022 12:23, Matthew Brost wrote:
On Thu, Jan 13, 2022 at 12:27:00PM -0800, John Harrison wrote:
On 1/13/2022 12:10, Matthew Brost wrote:
On Thu, Jan 13, 2022 at 11:59:39AM -0800, john.c.harri...@intel.com wrote:
From: John Harrison
A lot of tests use almost identical code
On 1/13/2022 12:10, Matthew Brost wrote:
On Thu, Jan 13, 2022 at 11:59:39AM -0800, john.c.harri...@intel.com wrote:
From: John Harrison
A lot of tests use almost identical code for creating a batch buffer
which does a single write to memory and another is about to be added.
Instead, move
timeout compiled out
- Skip test if engine reset isn't supported
- Update debug prints to be more descriptive
v3:
- Add comment explaining test
v4:
(John Harrison)
- Fix typos in comment explaining test
- goto out_rq is NOP creation fails
Signed-off-by: Matthew Brost
---
drivers
On 1/13/2022 09:34, Matthew Brost wrote:
On Thu, Jan 13, 2022 at 09:33:12AM -0800, John Harrison wrote:
On 1/11/2022 15:11, Matthew Brost wrote:
Add a cancel request selftest that results in an engine reset to cancel
the request as it is non-preemptable. Also insert a NOP request after
On 1/11/2022 15:11, Matthew Brost wrote:
Add a cancel request selftest that results in an engine reset to cancel
the request as it is non-preemptable. Also insert a NOP request after
the cancelled request and confirm that it completes successfully.
v2:
(Tvrtko)
- Skip test if preemption
these hacks.
Signed-off-by: Matthew Brost
Reviewed-by: John Harrison
---
.../gpu/drm/i915/gt/uc/intel_guc_submission.c | 30 ++-
1 file changed, 2 insertions(+), 28 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
b/drivers/gpu/drm/i915/gt/uc
On 12/26/2021 22:02, Zbigniew Kempczyński wrote:
On Tue, Dec 21, 2021 at 06:22:22PM -0800, John Harrison wrote:
On 12/20/2021 10:13, Zbigniew Kempczyński wrote:
On Thu, Dec 16, 2021 at 02:40:21PM -0800, John Harrison wrote:
On 12/15/2021 23:46, Zbigniew Kempczyński wrote:
On Mon, Dec 13
On 1/6/2022 16:31, john.c.harri...@intel.com wrote:
From: John Harrison
There is a race (already documented in the code) whereby a context can
be (re-)queued for submission at the same time as it is being banned
due to a hang and reset. That leads to a hang/reset report from GuC
for a context
On 1/4/2022 09:31, Matthew Brost wrote:
intel_context_timeline_lock can return can error if interrupted by a
user when trying to lock the timeline mutex. Check the return value of
intel_context_timeline_lock in eb_pin_timeline (execbuf IOCTL).
Fixes: 544460c33821 ("drm/i915: Multi-BB execbuf")
eb->context->parallel.seqno,
+eb->context->parallel.seqno++,
As is, this change looks good. So:
Reviewed-by: John Harrison
However, just spotted that dma_fence_array_create() takes the seqno
value as an 'unsigned' even though it pas
On 12/23/2021 02:23, Tvrtko Ursulin wrote:
On 22/12/2021 21:58, John Harrison wrote:
On 12/22/2021 08:21, Tvrtko Ursulin wrote:
On 21/12/2021 22:14, John Harrison wrote:
On 12/21/2021 05:37, Tvrtko Ursulin wrote:
On 20/12/2021 18:34, John Harrison wrote:
On 12/20/2021 07:00, Tvrtko Ursulin
are not allowed. This is on par with what
is there for the existing (hopefully soon deprecated) bonding interface.
We perma-pin these execlists contexts to align with GuC implementation.
v2:
(John Harrison)
- Drop siblings array as num_siblings must be 1
v3:
(John Harrison)
- Drop single submission
On 12/22/2021 15:29, Matthew Brost wrote:
Use a lockless list structure for destroyed contexts to avoid hammering
on global submission spin lock.
I thought the guidance was that lockless anything without an explanation
longer than War And Peace comes with an automatic termination penalty?
On 12/22/2021 08:21, Tvrtko Ursulin wrote:
On 21/12/2021 22:14, John Harrison wrote:
On 12/21/2021 05:37, Tvrtko Ursulin wrote:
On 20/12/2021 18:34, John Harrison wrote:
On 12/20/2021 07:00, Tvrtko Ursulin wrote:
On 17/12/2021 16:22, Matthew Brost wrote:
On Fri, Dec 17, 2021 at 12:15:53PM
On 12/20/2021 10:13, Zbigniew Kempczyński wrote:
On Thu, Dec 16, 2021 at 02:40:21PM -0800, John Harrison wrote:
On 12/15/2021 23:46, Zbigniew Kempczyński wrote:
On Mon, Dec 13, 2021 at 03:29:11PM -0800, john.c.harri...@intel.com wrote:
From: John Harrison
A lot of tests use almost identical
On 12/21/2021 03:28, Dandamudi, Priyanka wrote:
Does this test series cover to prove that it can survive killing one without
killing all the others except RCS+CCS combination(killing one affects other and
shows with the help of reset stats)?
That is part of the purpose of i915_hangman - to
On 12/21/2021 05:37, Tvrtko Ursulin wrote:
On 20/12/2021 18:34, John Harrison wrote:
On 12/20/2021 07:00, Tvrtko Ursulin wrote:
On 17/12/2021 16:22, Matthew Brost wrote:
On Fri, Dec 17, 2021 at 12:15:53PM +, Tvrtko Ursulin wrote:
On 14/12/2021 15:07, Tvrtko Ursulin wrote:
From: Tvrtko
ion itself could be triggered but basically,
if GuC resets an active context then it is because it did not pre-empt
quickly enough when requested.
Regards,
Tvrtko
Signed-off-by: Tvrtko Ursulin
Cc: Matthew Brost
Cc: John Harrison
---
drivers/gpu/drm/i915/gt/uc/intel_guc_submiss
On 12/15/2021 23:46, Zbigniew Kempczyński wrote:
On Mon, Dec 13, 2021 at 03:29:11PM -0800, john.c.harri...@intel.com wrote:
From: John Harrison
A lot of tests use almost identical code for creating a batch buffer
which does a single write to memory. This patch collects two such
instances
On 12/15/2021 23:23, Zbigniew Kempczyński wrote:
On Mon, Dec 13, 2021 at 03:29:10PM -0800, john.c.harri...@intel.com wrote:
From: John Harrison
Added a an extra step to the i915_hangman tests to check that the
system is still alive after the hang and recovery. This submits a
simple batch
On 12/16/2021 00:47, Tvrtko Ursulin wrote:
On 15/12/2021 22:45, john.c.harri...@intel.com wrote:
From: John Harrison
A fault injection probe test hit a BUG_ON in a GuC error path. It
showed that the GuC code could potentially attempt to do many things
when the device is actually wedged. So
request which should successfully steal
a guc_id. Wait on last request to complete, idle GPU, verify a guc_id
was stolen via a counter, and exit the test. Test also artificially
reduces the number of guc_ids so the test runs in a timely manner.
v2:
(John Harrison)
- s/stole/stolen
- Fix some
On 12/14/2021 01:47, Petri Latvala wrote:
On Mon, Dec 13, 2021 at 03:29:04PM -0800, john.c.harri...@intel.com wrote:
From: John Harrison
Added descriptions of the various sub-tests and the test as a whole.
Signed-off-by: John Harrison
---
tests/i915/i915_hangman.c | 11 +--
1
On 12/11/2021 09:35, Matthew Brost wrote:
Let's be paranoid and kick the G2H tasklet, which dequeues messages, if
G2H credits are exhausted.
Signed-off-by: Matthew Brost
Reviewed-by: John Harrison
---
drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c | 9 -
1 file changed, 8 insertions
manner.
v2:
(John Harrison)
- s/stole/stolen
- Fix some wording in test description
- Rework indexing into context array
- Add test description to commit message
- Fix typo in commit message
(Checkpatch)
- s/guc/(guc) in NUMBER_MULTI_LRC_GUC_ID
Signed-off-by: Matthew Brost
On 12/11/2021 18:43, Patchwork wrote:
Project List - Patchwork *Patch Details*
*Series:* More fixes/tweaks to GuC support
*URL:* https://patchwork.freedesktop.org/series/97898/
*State:*failure
*Details:*
https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21832/index.html
CI
On 12/10/2021 21:30, Lucas De Marchi wrote:
On Fri, Dec 10, 2021 at 05:41:46PM -0800, John Harrison wrote:
On 12/10/2021 17:22, Matt Roper wrote:
On Thu, Dec 09, 2021 at 09:21:39AM -0800, Lucas De Marchi wrote:
On Fri, Dec 03, 2021 at 08:26:03PM +0530,
ravitejax.goud.ta...@intel.com wrote
On 12/10/2021 17:43, John Harrison wrote:
On 12/10/2021 16:56, Matthew Brost wrote:
Print CT state (H2G + G2H head / tail pointers, credits) on CT
deadlock.
Signed-off-by: Matthew Brost
Reviewed-by: John Harrison
---
drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c | 9 +
1 file
On 12/10/2021 16:56, Matthew Brost wrote:
Print CT state (H2G + G2H head / tail pointers, credits) on CT
deadlock.
Signed-off-by: Matthew Brost
Reviewed-by: John Harrison
---
drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c | 9 +
1 file changed, 9 insertions(+)
diff --git a/drivers
1407352427,Wa_1406680159 to proper function icl_gt_workarounds_init()
Which will resolve guc enabling error
v2:
- Previous patch rev2 was created by email client which caused the
Build failure, This v2 is to resolve the previous broken series
Reviewed-by: John Harrison
Signed-off-by: Raviteja
On 12/10/2021 16:56, Matthew Brost wrote:
Testing the stealing of guc ids is hard from user spaec as we have 64k
spaec -> space
guc_ids. Add a selftest, which artificially reduces the number of guc
ids, and forces a steal. Details of test has comment in code so will not
has -> are
But would
On 12/10/2021 16:56, Matthew Brost wrote:
Previously assigned whole guc_id structure (list, spin lock) which is
incorrect, only assign the guc_id.id.
Fixes: 0f7976506de61 ("drm/i915/guc: Rework and simplify locking")
Signed-off-by: Matthew Brost
Reviewed-by: John Harrison
---
d
On 12/10/2021 16:56, Matthew Brost wrote:
From: John Harrison
While attempting to debug a CT deadlock issue in various CI failures
(most easily reproduced with gem_ctx_create/basic-files), I was seeing
CPU deadlock errors being reported. This were because the context
destroy loop was blocking
On 12/8/2021 20:03, Patchwork wrote:
Project List - Patchwork *Patch Details*
*Series:* Assorted fixes/tweaks to GuC support (rev5)
*URL:* https://patchwork.freedesktop.org/series/97514/
*State:*failure
*Details:*
On 12/9/2021 06:41, Robert Beckett wrote:
On 09/12/2021 00:24, John Harrison wrote:
On 12/8/2021 09:58, Robert Beckett wrote:
On 07/12/2021 23:15, John Harrison wrote:
On 12/7/2021 09:53, Adrian Larumbe wrote:
Beginning with DG2, all successive devices will require GuC FW to be
present
On 12/7/2021 09:53, Adrian Larumbe wrote:
Beginning with DG2, all successive devices will require GuC FW to be
present and loaded at probe() time. This change alters error handling in
the FW init and load functions so that the driver's probe() function will
fail if GuC could not be loaded.
We
On 11/29/2021 12:22, Thomas Hellström wrote:
With asynchronous migrations, the vma state may be several migrations
ahead of the state that matches the request we're capturing.
Address that by introducing an i915_vma_snapshot structure that
can be used to snapshot relevant state at request
are not allowed. This is on par with what
is there for the existing (hopefully soon deprecated) bonding interface.
We perma-pin these execlists contexts to align with GuC implementation.
v2:
(John Harrison)
- Drop siblings array as num_siblings must be 1
v3:
(John Harrison)
- Drop single submission
Michal, do you know what this is complaining about?
John.
On 12/3/2021 14:27, Patchwork wrote:
== Series Details ==
Series: Update to GuC version 69.0.0
URL : https://patchwork.freedesktop.org/series/97564/
State : warning
== Summary ==
$ make htmldocs 2>&1 > /dev/null | grep i915
On 11/23/2021 06:45, ravitejax.goud.ta...@intel.com wrote:
From: raviteja goud talla
Bspec page says "Reset: BUS", Accordingly moving w/a's:
Wa_1407352427,Wa_1406680159 to proper function icl_gt_workarounds_init()
Which will resolve guc enabling error
Cc: John Harrison
On 11/3/2021 14:38, Jordan Justen wrote:
John Harrison writes:
On 11/1/2021 08:39, Jordan Justen wrote:
writes:
From: Rodrigo Vivi
GuC contains a consolidated table with a bunch of information about the
current device.
Previously, this information was spread and hardcoded to all
On 11/3/2021 02:36, Petri Latvala wrote:
On Tue, Nov 02, 2021 at 06:45:38PM -0700, John Harrison wrote:
On 11/2/2021 16:34, Matthew Brost wrote:
On Thu, Oct 21, 2021 at 04:40:40PM -0700, john.c.harri...@intel.com wrote:
From: John Harrison
Some of the capture tests were using explicit
On 11/3/2021 07:00, Tvrtko Ursulin wrote:
On 22/10/2021 00:40, john.c.harri...@intel.com wrote:
From: John Harrison
The sysfs file read helper does not actually report any errors if a
realloc fails. It just silently returns a 'valid' but truncated
buffer. This then leads to the decode
On 11/3/2021 06:50, Tvrtko Ursulin wrote:
On 22/10/2021 00:40, john.c.harri...@intel.com wrote:
From: John Harrison
The 'many' test ended with an 'assert(count)', presumably meaning to
ensure that some objects were actually captured. However, 'count' is
the number of objects created not how
On 11/2/2021 16:34, Matthew Brost wrote:
On Thu, Oct 21, 2021 at 04:40:40PM -0700, john.c.harri...@intel.com wrote:
From: John Harrison
Some of the capture tests were using explicit contexts, some not. Some
were poking the per engine pre-emption timeout, some not. This would
lead to sporadic
On 11/1/2021 08:39, Jordan Justen wrote:
writes:
From: Rodrigo Vivi
GuC contains a consolidated table with a bunch of information about the
current device.
Previously, this information was spread and hardcoded to all the components
including GuC, i915 and various UMDs. The goal here is to
On 10/29/2021 10:39, Matthew Brost wrote:
On Thu, Oct 21, 2021 at 04:40:38PM -0700, john.c.harri...@intel.com wrote:
From: John Harrison
At some point, larger than 4KB page sizes were added to the i915
driver. This included adding an informational line to the buffer
entries in error capture
these bits, rip the use
of these bits out from the reset code.
To be clear, there are other tests poking these bits in addition to
hangcheck. Not sure if they would suffer from the same problems but I
don't see why they wouldn't.
Reviewed-by: John Harrison
Signed-off-by: Matthew Brost
On 10/26/2021 23:36, Thomas Hellström wrote:
Hi, John,
On 10/26/21 21:55, John Harrison wrote:
On 10/21/2021 23:23, Thomas Hellström wrote:
On 10/21/21 22:37, Matthew Brost wrote:
On Thu, Oct 21, 2021 at 08:15:49AM +0200, Thomas Hellström wrote:
Hi, Matthew,
On Mon, 2021-10-11 at 16:47
On 10/27/2021 12:17, Matthew Brost wrote:
On Tue, Oct 26, 2021 at 02:58:00PM -0700, John Harrison wrote:
On 10/20/2021 14:47, Matthew Brost wrote:
A weak implementation of parallel submission (multi-bb execbuf IOCTL) for
execlists. Doing as little as possible to support this interface
are not allowed. This is on par with what
is there for the existing (hopefully soon deprecated) bonding interface.
We perma-pin these execlists contexts to align with GuC implementation.
v2:
(John Harrison)
- Drop siblings array as num_siblings must be 1
Signed-off-by: Matthew Brost
---
drivers/gpu
On 10/21/2021 23:23, Thomas Hellström wrote:
On 10/21/21 22:37, Matthew Brost wrote:
On Thu, Oct 21, 2021 at 08:15:49AM +0200, Thomas Hellström wrote:
Hi, Matthew,
On Mon, 2021-10-11 at 16:47 -0700, Matthew Brost wrote:
The hangcheck selftest blocks per engine resets by setting magic bits
in
On 10/11/2021 16:47, Matthew Brost wrote:
The hangcheck selftest blocks per engine resets by setting magic bits in
the reset flags. This is incorrect for GuC submission because if the GuC
fails to reset an engine we would like to do a full GT reset. Do no set
these magic bits when using GuC
On 10/25/2021 09:34, Matthew Brost wrote:
Hide the guc_id and tail fields, for request trace points, behind
CONFIG_DRM_I915_LOW_LEVEL_TRACEPOINTS Kconfig option. Trace points
are ABI (maybe?) so don't change them without kernel developers Kconfig
options.
The i915 sw arch team have previously
On 10/23/2021 11:36, Thomas Hellström wrote:
On 10/23/21 20:18, Matthew Brost wrote:
On Sat, Oct 23, 2021 at 07:46:48PM +0200, Thomas Hellström wrote:
On 10/22/21 20:09, John Harrison wrote:
And to be clear, the engine reset is not supposed to fail. Whether
issued by GuC or i915, the GDRST
st
[1] https://patchwork.freedesktop.org/series/89844/
[2] https://patchwork.freedesktop.org/series/91417/
Daniele Ceraolo Spurio (1):
drm/i915/guc: Unblock GuC submission on Gen11+
John Harrison (10):
drm/i915/guc: Module load failure test for CT buffer creation
drm/i915: Track '
On 10/22/2021 10:03, Matthew Brost wrote:
On Fri, Oct 22, 2021 at 08:23:55AM +0200, Thomas Hellström wrote:
On 10/21/21 22:37, Matthew Brost wrote:
On Thu, Oct 21, 2021 at 08:15:49AM +0200, Thomas Hellström wrote:
Hi, Matthew,
On Mon, 2021-10-11 at 16:47 -0700, Matthew Brost wrote:
The
understand that is ok for contexts to get starved in this
scenario.
A future patch / cleanup may just delete these micro benchmark tests as
they basically mean nothing. We care about real workloads not made up
ones.
Signed-off-by: Matthew Brost
Reviewed-by: John Harrison
---
drivers/gpu/drm/i915
On 10/15/2021 07:52, Dixit, Ashutosh wrote:
On Thu, 14 Oct 2021 12:42:38 -0700, wrote:
+ /*
+* These tests are for a specific scheduling model which is
+* not currently implemented by GuC. So skip on GuC platforms.
+*/
+
d after all?
John.
commit b0179f0d18dd7e6fb6b1c52c49ac21365257e97e
Author: Hugh Dickins
AuthorDate: Tue Sep 21 18:50:39 2021 -0700
Commit: John Harrison
CommitDate: Thu Oct 14 18:29:01 2021 -0700
drm/i915: fix blank screen booting crashes
commit cdc1e6e225e3256d56dc6648411630e71d7c776b
Author: Hugh Dickins
On 10/14/2021 10:20, Matthew Brost wrote:
A weak implementation of parallel submission (multi-bb execbuf IOCTL) for
execlists. Doing as little as possible to support this interface for
execlists - basically just passing submit fences between each request
generated and virtual engines are not
On 10/14/2021 10:20, Matthew Brost wrote:
Enable multi-bb execbuf by enabling the set_parallel extension.
Signed-off-by: Matthew Brost
Reviewed-by: John Harrison
---
drivers/gpu/drm/i915/gem/i915_gem_context.c | 3 ---
1 file changed, 3 deletions(-)
diff --git a/drivers/gpu/drm/i915
media UMD: https://github.com/intel/media-driver/pull/1252
v2:
(Matthew Brost)
- Return proper error value if i915_request_create fails
v3:
(John Harrison)
- Add comment explaining create / add order loops + locking
- Update commit message explaining different in IOCTL behavior
/1252
v2:
(Daniel Vetter)
- Add IGT link and placeholder for media UMD link
v3:
(Kernel test robot)
- Fix warning in unpin engines call
(John Harrison)
- Reword a bunch of the kernel doc
v4:
(John Harrison)
- Add comment why perma-pin is done after setting gem context
On 10/14/2021 10:19, Matthew Brost wrote:
Add multi-lrc context registration H2G. In addition a workqueue and
process descriptor are setup during multi-lrc context registration as
these data structures are needed for multi-lrc submission.
v2:
(John Harrison)
- Move GuC specific fields
On 10/14/2021 09:41, Matthew Brost wrote:
On Thu, Oct 14, 2021 at 09:43:36AM -0700, John Harrison wrote:
On 10/14/2021 08:32, Matthew Brost wrote:
On Wed, Oct 13, 2021 at 06:02:42PM -0700, John Harrison wrote:
On 10/13/2021 13:42, Matthew Brost wrote:
Introduce 'set parallel submit
scheduling with the GuC / or
deregister the context.
v2:
(Daniel Vetter)
- Perma-pin parallel contexts
Signed-off-by: Matthew Brost
Reviewed-by: John Harrison
---
.../gpu/drm/i915/gt/uc/intel_guc_submission.c | 70 +++
1 file changed, 70 insertions(+)
diff --git a/drivers
On 10/14/2021 08:32, Matthew Brost wrote:
On Wed, Oct 13, 2021 at 06:02:42PM -0700, John Harrison wrote:
On 10/13/2021 13:42, Matthew Brost wrote:
Introduce 'set parallel submit' extension to connect UAPI to GuC
multi-lrc interface. Kernel doc in new uAPI should explain it all.
IGT: https
On 10/13/2021 15:53, Dixit, Ashutosh wrote:
On Wed, 13 Oct 2021 15:43:17 -0700, wrote:
From: John Harrison
The gem_exec_fair test is specifically testing scheduler algorithm
performance. However, GuC does not implement the same algorithm as
execlist mode and this test is not applicable. So
/1252
v2:
(Daniel Vetter)
- Add IGT link and placeholder for media UMD link
v3:
(Kernel test robot)
- Fix warning in unpin engines call
(John Harrison)
- Reword a bunch of the kernel doc
v4:
(John Harrison)
- Add comment why perma-pin is done after setting gem context
the request conflict tracking
understand this by comparing a parallel submit's parent context and
skipping conflict insertion if the values match.
v2:
(John Harrison)
- Reword commit message
Signed-off-by: Matthew Brost
Reviewed-by: John Harrison
---
drivers/gpu/drm/i915/i915_request.c | 43
the parent and children to make
forward progress. If all the requests are not present this handshake
doesn't work. To work around this, if multi-lrc request has an error we
skip the handshake but still emit the breadcrumbs seqno.
v2:
(John Harrison)
- Add comment explaining the skipping
media UMD: https://github.com/intel/media-driver/pull/1252
v2:
(Matthew Brost)
- Return proper error value if i915_request_create fails
v3:
(John Harrison)
- Add comment explaining create / add order loops + locking
- Update commit message explaining different in IOCTL behavior
v2:
(John Harrison)
- Fix a few comments wording
- Add struture for parent page layout
v3:
(Jojhn Harrison)
- A structure for sync semaphore
- Use offsetof to calc address
- Update commit message
Signed-off-by: Matthew Brost
---
drivers/gpu/drm/i915/gt/intel_context.c |
On 10/13/2021 13:42, Matthew Brost wrote:
Update context and full GPU reset to work with multi-lrc. The idea is
parent context tracks all the active requests inflight for itself and
its children. The parent context owns the reset replaying / canceling
requests as needed.
v2:
(John Harrison
. As such, the tasklet and bypass path have
been updated to coalesce requests into a single submission.
v2:
(John Harrison)
- s/wqe/wqi
- Use FIELD_PREP macros
- Add GEM_BUG_ONs ensures length fits within field
- Add comment / white space to intel_guc_write_barrier
(Kernel test robot)
- Make
On 10/13/2021 13:42, Matthew Brost wrote:
Add multi-lrc context registration H2G. In addition a workqueue and
process descriptor are setup during multi-lrc context registration as
these data structures are needed for multi-lrc submission.
v2:
(John Harrison)
- Move GuC specific fields
annotations to pin / unpin function
v3:
(CI)
- Drop intel_engine_pm_might_put from unpin path as an async put is
used
v4:
(John Harrison)
- Make intel_engine_pm_might_get/put work with GuC virtual engines
- Update commit message
v5:
- Update commit message again
Signed-off
401 - 500 of 975 matches
Mail list logo