Both workarounds require the same implementation and apply to MTL P and
M from stepping A0 to B0 (exclusive).
v2:
- Remove unrelated brace removal. (Matt)
Signed-off-by: Radhakrishna Sripada <radhakrishna.sripada@intel.com>
Signed-off-by: Gustavo Sousa <gustavo.sousa@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230329212336.106161-2-gustavo.sousa@intel.com
Userspace can guess the id value and try to race oa_config object creation
with config remove, resulting in a use-after-free if we dereference the
object after unlocking the metrics_lock. For that reason, unlocking the
metrics_lock must be done after we are done dereferencing the object.
Signed-off-by: Min Li <lm0963hack@gmail.com>
Fixes: f89823c212 ("drm/i915/perf: Implement I915_PERF_ADD/REMOVE_CONFIG interface")
Cc: <stable@vger.kernel.org> # v4.14+
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Reviewed-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230328093627.5067-1-lm0963hack@gmail.com
[tursulin: Manually added stable tag.]
The WA states that we need to alert the GSC FW before doing a GSC engine
reset and then wait for 200ms. The GuC owns engine reset, so on the i915
side we only need to apply this for full GT reset.
Given that we do full GT resets in the resume paths to cleanup the HW
state and that a long wait in those scenarios would not be acceptable,
a faster path has been introduced where, if the GSC is idle, we try first
to individually reset the GuC and all engines except the GSC and only fall
back to full reset if that fails.
Note: according to the WA specs, if the GSC is idle it should be possible
to only wait for the uC wakeup time (~15ms) instead of the whole 200ms.
However, the GSC FW team have mentioned that the wakeup time can change
based on other things going on in the HW and pcode, so a good security
margin would be required. Given that when the GSC is idle we already
skip the wait & reset entirely and that this reduced wait would still
likely be too long to use in resume paths, it's not worth adding support
for this reduced wait.
v2: add comment to explain why it is safe to skip the GSC reset (John)
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: John Harrison <john.c.harrison@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230323231857.2194435-2-daniele.ceraolospurio@intel.com
Commit 3db9d59055 ("drm/i915/gt: Reset twice") modified the code to
always hit the GDRST register twice when doing a reset, with the
reported aim to fix invalid post-reset engine state on some platforms
(Jasperlake being the only one actually mentioned).
This is a problem on MTL, due to the fact that we have to apply a time
consuming WA (coming in the next patch) every time we hit the GDRST
register in a way that can include the GSC engine. Even post MTL, the
expectation is that we'll have some work to do before and after hitting
the GDRST if the GSC is involved.
Since the issue requiring the double reset seems to be limited to older
platforms, instead of trying to handle the double-reset on MTL and
future platforms it is just easier to turn it off. The default on MTL is
also for GuC to own engine reset, with i915 only covering full-GT reset.
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Andi Shyti <andi.shyti@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Gwan-gyeong Mun <gwan-gyeong.mun@intel.com>
Cc: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230323231857.2194435-1-daniele.ceraolospurio@intel.com
In the rare case where we do a full GT reset after starting the HuC
load and before it completes (which basically boils down to i915 hanging
during init), we need to cancel the delayed load fence, as it will be
re-initialized in the post-reset recovery.
Fixes: 27536e0327 ("drm/i915/huc: track delayed HuC load with a fence")
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Alan Previn <alan.previn.teres.alexis@intel.com>
Reviewed-by: Alan Previn <alan.previn.teres.alexis@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230313205556.1174503-1-daniele.ceraolospurio@intel.com
Although we now sanitycheck MMIO access during driver load to make sure
the MMIO BAR isn't returning all 0xFFFFFFFF, there have been a few cases
where (temporarily?) unreliable MMIO access has happened after GPU
resets or power events. We'll often notice this on our next GT register
access since forcewake handling will fail; let's change our handling
slightly so that when this happens we print a more meaningful message
clarifying that the problem is the MMIO access, not forcewake
specifically.
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Reviewed-by: Andrzej Hajda <andrzej.hajda@intel.com>
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230327195547.356584-3-andi.shyti@linux.intel.com
We occasionally see the PCI device in a non-accessible state at the
point the driver is loaded. When this happens, all BAR accesses will
read back as 0xFFFFFFFF. Rather than reading registers and
misinterpreting their (invalid) values, let's specifically check for
0xFFFFFFFF in a register that cannot have that value to see if the
device is accessible.
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230327195547.356584-2-andi.shyti@linux.intel.com
Earlier merge dropped an if block when applying the patch -
"drm/i915/mtl: Synchronize i915/BIOS on C6 enabling". Bring back the
if block as the check is required by - "drm/i915/mtl: Disable MC6 for MTL
A step" to disable C6 on media for A0 stepping.
Fixes: 3735040978 ("drm/i915/mtl: Synchronize i915/BIOS on C6 enabling")
Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Reviewed-by: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230324213918.75212-1-umesh.nerlige.ramappa@intel.com
OAM does not work with media C6 enabled on some steppings of MTL.
Disable OAM if we detect that media C6 was enabled in bios.
v2: (Ashutosh)
- Remove drm_notice from the driver load path
- Log a drm_err when opening an OAM stream on affected steppings
v3:
- Initialize the engine group even if mc6 is enabled (Ashutosh)
- Checkpatch fix
Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230323225901.3743681-12-umesh.nerlige.ramappa@intel.com
Some of the newer OA formats are not powers of 2. For those formats,
adjust the hw_tail accordingly when checking for new reports.
v2: (Ashutosh)
- Switch to OA_TAKEN for diff calculation
- Use OA_BUFFER_SIZE instead of the vma size
- Update comments
Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230323225901.3743681-8-umesh.nerlige.ramappa@intel.com
Now that OA formats come in flavor of 64 bit reports, the report header
has 64 bit report-id, timestamp, context-id and gpu-ticks fields. When
filtering these reports, use the right width for these fields.
Note that upper dword of context id is reserved, so squash lower dword
only.
v2: (Ashutosh)
- Drop inline
- Update comment with dword definitions - report id and timestamp
Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230323225901.3743681-7-umesh.nerlige.ramappa@intel.com
Now that we may have multiple OA units in a single GT as well as on
separate GTs, create an engine group that maps to a single OA unit.
v2: (Jani)
- Drop warning on ENOMEM
- Reorder patch in the series
v3: (Ashutosh)
- Remove unused members from perf structs
- Update comments
- Update engine_supports_oa check
- Just return 1 in num_perf_groups_per_gt for now
- Set engine->oa_group to NULL to begin with
v4: Use engine_supports_oa() check in oa_init_reg_state (Ashutosh)
v5: Rebase after dropping engine_supports_oa helper
Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230323225901.3743681-5-umesh.nerlige.ramappa@intel.com
Once OA supports media engine class:instance, the engine can only be
validated outside the switch since class and instance parameters are
separate entities. Since OA sseu config depends on engine
class:instance, validate OA sseu config outside the switch.
v2: (Ashutosh)
- Clarify commit message
- Use drm_dbg instead of DRM_DEBUG
- Reorder stack variables
Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230323225901.3743681-4-umesh.nerlige.ramappa@intel.com
If BIOS enables/disables C6, i915 should do the same. Also, retain
this value across driver reloads. This is needed only for MTL as
of now due to an existing bug in OA which needs C6 disabled for
it to function. BIOS behavior is also different across platforms
in terms of how C6 is enabled.
Signed-off-by: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230323225901.3743681-3-umesh.nerlige.ramappa@intel.com
If we fail to adjust the GuC run-control on opening the perf stream,
make sure we unwind the wakeref just taken.
v2: Retain old goto label names (Ashutosh)
v3: Drop bitfield boolean
Fixes: 01e7427467 ("drm/i915/guc: Support OA when Wa_16011777198 is enabled")
Signed-off-by: Chris Wilson <chris.p.wilson@linux.intel.com>
Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230323225901.3743681-2-umesh.nerlige.ramappa@intel.com
There are multiple ways in which the GuC load can fail. The driver was
reporting the status register as is, but not everyone can read the
matrix unfiltered. So add decoding of the common error cases.
Also, remove the comment about interrupt based load completion
checking being not recommended. The interrupt was removed from the GuC
firmware some time ago so it is no longer an option anyway. While at
it, also abort the timeout if a known error code is reported. No need
to keep waiting if the GuC has already given up the load.
v2: Fix mis-matched case and confusing 'success' variable (Daniele).
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230316220632.3312218-2-John.C.Harrison@Intel.com
The gt_tlb live selftest has the same code coverage as the
igt_cs_tlb subtest of gtt, except it is better at detecting
TLB bugs. Furthermore, while igt_cs_tlb is hitting some
unforeseen issues, these issues are either false positives
due to the test being poorly formatted, or are true
positives that can be more easily diagnosed with smaller
tests. As such, igt_cs_tlb is superceded by and obsoleted
by gt_tlb, meaning it can be removed.
Signed-off-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Reviewed-by: Andrzej Hajda <andrzej.hajda@intel.com>
Acked-by: Nirmoy Das <nirmoy.das@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230320192117.287374-1-andi.shyti@linux.intel.com
i915_gem_object_create_lmem_from_data() lacks the flush of the data
written to lmem to ensure the object is marked as dirty and the writes
flushed to the backing store. Once created, we can immediately release
the obj->mm.mapping caching of the vmap.
Fixes: 7acbbc7cf4 ("drm/i915/guc: put all guc objects in lmem when available")
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Andi Shyti <andi.shyti@linux.intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: John Harrison <John.C.Harrison@Intel.com>
Signed-off-by: Chris Wilson <chris.p.wilson@linux.intel.com>
Cc: <stable@vger.kernel.org> # v5.16+
Signed-off-by: Nirmoy Das <nirmoy.das@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Reviewed-by: Nirmoy Das <nirmoy.das@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230316165918.13074-1-nirmoy.das@intel.com
The commit 82a149a62b ("drm/i915/gt: move remaining debugfs
interfaces into gt") moved gt-related debugfs files in the gtX/
directories to operate on individual gt's.
However, the original files were only functioning on the root
GT (GT 0) and have been left in the same location to maintain
compatibility with userspace users.
Add multiplexing functionality to the higher directories' files.
This enables the operations to be performed on all the GTs with
a single write. In the case of reads, the files provide an or'ed
value across all the tiles.
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Cc: Maciej Patelczyk <maciej.patelczyk@intel.com>
Reviewed-by: Nirmoy Das <nirmoy.das@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230318203616.183765-4-andi.shyti@linux.intel.com
To support multi-GT configurations, we need to generate
independent debug files for each GT.
To achieve this create a separate directory for each GT under the
debugfs directory. For instance, in a system with two GTs, the
debugfs structure would look like this:
/sys/kernel/debug/dri
└── 0
├── gt0
│ ├── drpc
│ ├── engines
│ ├── forcewake
│ ├── frequency
│ └── rps_boost
└── gt1
: ├── drpc
: ├── engines
: ├── forcewake
├── frequency
└── rps_boost
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Radhakrishna Sripada <radhakrishna.sripada@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230318203616.183765-2-andi.shyti@linux.intel.com
Zero-length arrays as fake flexible arrays are deprecated and we are
moving towards adopting C99 flexible-array members instead.
Address the following warning found with GCC-13 and
-fstrict-flex-arrays=3 enabled:
drivers/gpu/drm/i915/gem/i915_gem_context.c: In function ‘set_proto_ctx_engines.isra’:
drivers/gpu/drm/i915/gem/i915_gem_context.c:769:41: warning: array subscript n is outside array bounds of ‘struct i915_engine_class_instance[0]’ [-Warray-bounds=]
769 | if (copy_from_user(&ci, &user->engines[n], sizeof(ci))) {
| ^~~~~~~~~~~~~~~~~
./include/uapi/drm/i915_drm.h:2494:43: note: while referencing ‘engines’
2494 | struct i915_engine_class_instance engines[0];
This helps with the ongoing efforts to tighten the FORTIFY_SOURCE
routines on memcpy() and help us make progress towards globally
enabling -fstrict-flex-arrays=3 [1].
Link: https://github.com/KSPP/linux/issues/21
Link: https://github.com/KSPP/linux/issues/271
Link: https://gcc.gnu.org/pipermail/gcc-patches/2022-October/602902.html [1]
Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/ZBSu2QsUJy31kjSE@work
Expose intel_rps_read_actual_frequency_fw to read the actual freq without
taking forcewake for use by PMU. The code is refactored to use a common set
of functions across sysfs and PMU. Using common functions with sysfs in PMU
solves the issues of missing support for MTL and missing support for older
generations (prior to Gen6). It also future proofs the PMU where sometimes
code has been updated for sysfs and PMU has been missed.
v2: Remove runtime_pm_if_in_use from read_actual_frequency_fw (Tvrtko)
v3: (Tvrtko)
- Remove goto in __read_cagf
- Unexport intel_rps_get_cagf and intel_rps_read_punit_req
Fixes: 22009b6dad ("drm/i915/mtl: Modify CAGF functions for MTL")
Link: https://gitlab.freedesktop.org/drm/intel/-/issues/8280
Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230316004800.2539753-1-ashutosh.dixit@intel.com
On MTL, objects allocated through i915_gem_object_create_internal() are
mapped as uncached in GPU by default because HAS_LLC is false. However
in the live_hwsp_read selftest these watcher objects are mapped as WB
on CPU side. The conseqence is that the updates done by the GPU are not
immediately visible to CPU, thus the selftest is randomly failing due to
the stale data in CPU cache. Solution can be either setting WC for CPU +
UC for GPU, or WB for CPU + 1-way coherent WB for GPU.
To keep the consistency, let's simply inherit the same cache settings
from the timeline, which is WB for CPU + 1-way coherent WB for GPU,
because this test is supposed to emulate the behavior of the timeline
anyway.
Signed-off-by: Fei Yang <fei.yang@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230315180800.2632766-1-fei.yang@intel.com
Probe pseudo errors should be injected only in places where real errors
can be encountered, otherwise unwinding code can be broken.
Placing intel_uc_init_late before i915_inject_probe_error violated
this rule, resulting in following bug:
__intel_gt_disable:655 GEM_BUG_ON(intel_gt_pm_is_awake(gt))
Fixes: 481d458cae ("drm/i915/guc: Add golden context to GuC ADS")
Acked-by: Nirmoy Das <nirmoy.das@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Signed-off-by: Andrzej Hajda <andrzej.hajda@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230314151920.1065847-1-andrzej.hajda@intel.com
No need to look at the mask of present engines when we already have a
count stored ever since e2d0ff3525 ("drm/i915: Count engine instances
per uabi class").
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Jonathan Cavitt <jonathan.cavitt@intel.com>
Reviewed-by: Nirmoy Das <nirmoy.das@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230316142728.1335239-1-tvrtko.ursulin@linux.intel.com
[tursulin: fixup typo in patch title]
Write-combining memory allows speculative reads by CPU.
ggtt->error_capture is WC mapped to CPU, so CPU/MMU can try
to prefetch memory beyond the error_capture, ie it tries
to read memory pointed by next PTE in GGTT.
If this PTE points to invalid address DMAR errors will occur.
This behaviour was observed on ADL and RPL platforms.
To avoid it, guard scratch page should be added after error_capture.
The patch fixes the most annoying issue with error capture but
since WC reads are used also in other places there is a risk similar
problem can affect them as well.
v2:
- modified commit message (I hope the diagnosis is correct),
- added bug checks to ensure scratch is initialized on gen3 platforms.
CI produces strange stacktrace for it suggesting scratch[0] is NULL,
to be removed after resolving the issue with gen3 platforms.
v3:
- removed bug checks, replaced with gen check.
v4:
- change code for scratch page insertion to support all platforms,
- add info in commit message there could be more similar issues
v5:
- check for nop_clear_range instead of gen8 (Tvrtko),
- re-insert scratch pages on resume (Tvrtko)
v6:
- use scratch_range callback to set scratch pages (Chris)
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Acked-by: Nirmoy Das <nirmoy.das@intel.com>
Signed-off-by: Andrzej Hajda <andrzej.hajda@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230308-guard_error_capture-v6-2-1b5f31422563@intel.com
The callback will be responsible for setting scratch page PTEs for
specified range. In contrast to clear_range it cannot be optimized to nop.
It will be used by code adding guard pages.
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Reviewed-by: Nirmoy Das <nirmoy.das@intel.com>
Signed-off-by: Andrzej Hajda <andrzej.hajda@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230308-guard_error_capture-v6-1-1b5f31422563@intel.com
debug_active_activate() expected ref->count to be zero
which is not true anymore as __i915_active_activate() calls
debug_active_activate() after incrementing the count.
v2: No need to check for "ref->count == 1" as __i915_active_activate()
already make sure of that(Janusz).
References: https://gitlab.freedesktop.org/drm/intel/-/issues/6733
Fixes: 04240e30ed ("drm/i915: Skip taking acquire mutex for no ref->active callback")
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@intel.com>
Cc: Andi Shyti <andi.shyti@linux.intel.com>
Cc: intel-gfx@lists.freedesktop.org
Cc: Janusz Krzysztofik <janusz.krzysztofik@linux.intel.com>
Cc: <stable@vger.kernel.org> # v5.10+
Signed-off-by: Nirmoy Das <nirmoy.das@intel.com>
Reviewed-by: Janusz Krzysztofik <janusz.krzysztofik@linux.intel.com>
Reviewed-by: Andrzej Hajda <andrzej.hajda@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230313114613.9874-1-nirmoy.das@intel.com
The seqno value actually written out to memory is no longer in the
regular HWSP. Instead, it is now in its own private timeline buffer.
Thus, it is no longer visible in an error capture. So, explicitly read
the value and include that in the capture.
v2: %d -> %u (Alan)
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Alan Previn <alan.previn.teres.alexis@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230311063714.570389-4-John.C.Harrison@Intel.com
The comparison in the search for a matching register capture node was
not the most readable. It was also assuming that a zero GuC id means
invalid, which it does not. So remove one invalid term, one redundant
term and re-format to keep each term on a single line, and only one
term per line.
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Alan Previn <alan.previn.teres.alexis@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230311063714.570389-3-John.C.Harrison@Intel.com
Error captures are tagged with an 'ecode'. This is a pseduo-unique magic
number that is meant to distinguish similar seeming bugs with
different underlying signatures. It is a combination of two ring state
registers. Unfortunately, the register state being used is only valid
in execlist mode. In GuC mode, the register state exists in a separate
list of arbitrary register address/value pairs rather than the named
entry structure. So, search through that list to find the two exciting
registers and copy them over to the structure's named members.
v2: if else if instead of if if (Alan)
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Alan Previn <alan.previn.teres.alexis@intel.com>
Fixes: a6f0f9cf33 ("drm/i915/guc: Plumb GuC-capture into gpu_coredump")
Cc: Alan Previn <alan.previn.teres.alexis@intel.com>
Cc: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Aravind Iddamsetty <aravind.iddamsetty@intel.com>
Cc: Michael Cheng <michael.cheng@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Bruce Chang <yu.bruce.chang@intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230311063714.570389-2-John.C.Harrison@Intel.com
The Wa_14017073508 require to send Media Busy/Idle mailbox while
accessing Media tile. As of now it is getting handled while __gt_unpark,
__gt_park. But there are various corner cases where forcewakes are taken
without __gt_unpark i.e. without sending Busy Mailbox especially during
register reads. Forcewakes are taken without busy mailbox leads to
GPU HANG. So bringing mailbox calls under forcewake calls are no feasible
option as forcewake calls are atomic and mailbox calls are blocking.
The issue already fixed in B step so disabling MC6 on A step and
reverting previous commit which handles Wa_14017073508
Fixes: 8f70f1ec58 ("drm/i915/mtl: Add Wa_14017073508 for SAMedia")
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Badal Nilawar <badal.nilawar@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Anshuman Gupta <anshuman.gupta@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230310061339.2495416-2-badal.nilawar@intel.com
The CI results for the 'fast request' patch set (enables error return
codes for fire-and-forget H2G messages) hit an issue with the KMD
sending context submission requests on an invalid context. That was
caused by a fault injection probe failing the context creation of a
kernel context. However, there was no return code checking on any of
the kernel context registration paths. So the driver kept going and
tried to use the kernel context for the record defaults process.
This would not cause any actual problems. The invalid requests would
be rejected by GuC and ultimately the start up sequence would
correctly wedge due to the context creation failure. But fixing the
issue correctly rather ignoring it means we won't get CI complaining
when the fast request patch lands and enables the extra error checking.
So fix it by checking for errors and aborting as appropriate when
creating kernel contexts. While at it, clean up some other submission
init related failure cleanup paths. Also, rename guc_init_lrc_mapping
to guc_init_submission as the former name hasn't been valid in a long
time.
v2: Add another wrapper to keep the flow balanced (Daniele)
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230217223308.3449737-3-John.C.Harrison@Intel.com
The stats worker thread management was mis-matched between
enable/disable call sites. Fix those up. Also, abstract the
cancel/enable code into a helper function rather than replicating in
multiple places.
v2: Rename the helpers and wrap the enable as well as the cancel
(review feedback from Daniele).
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230217223308.3449737-2-John.C.Harrison@Intel.com
The GSC FW load is a slow process (up to 250 ms), so we defer it to a
dedicated worker to avoid stalling the init flow for that long. However,
we currently start this worker before the HW init is complete, so there
is a chance that the GSC loading code submits to the HW before the
engine initialization has completed. We can easily fix this by starting
the thread later in the gt_resume flow.
From this later spot, the GSC code can still race with the default
submission code; we functionally don't care who wins the race (the GSC
load doesn't need any state), but since the whole point of the separate
worker is to make the main thread faster, we prefer the default
submission code to run first. Therefore, make an exception for driver
probe and only and start the gsc load from uc_init_late.
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Alan Previn <alan.previn.teres.alexis@intel.com>
Reviewed-by: Alan Previn <alan.previn.teres.alexis@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230223172120.3304293-3-daniele.ceraolospurio@intel.com
If we unload the driver and wedge before the GSC worker is complete,
the worker will hit an error on its submission to the GSC engine and
then exit. This is hard to hit for a user, but it is reproducible
with skipping selftests. The error is handled gracefully by the
worker, so there are no functional issues, but we still end up with
an error message in dmesg, which is something we want to avoid as
this is a supported scenario. We could modify the worker to better
handle a wedging occurring during its execution, but that gets
complicated for a couple of reasons:
- We do want the error on runtime wedging, because there are
implications for subsystems outside of GT (i.e., PXP, HDCP), it's
only the error on driver unload that we want to silence.
- The worker is responsible for multiple submissions (GSC FW load,
HuC auth, SW proxy), so all of those will have to be adapted to
handle the wedged_on_fini scenario.
Therefore, it's much simpler to just wait for the worker to be done
before wedging on driver removal, also considering that the worker
will likely already be idle in the great majority of non-selftest
scenarios.
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Alan Previn <alan.previn.teres.alexis@intel.com>
Reviewed-by: Alan Previn <alan.previn.teres.alexis@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230223172120.3304293-2-daniele.ceraolospurio@intel.com
We can skip the assignment and i915 variable
altogether and use refernce directly. Also used at
single place only.
Signed-off-by: Tejas Upadhyay <tejas.upadhyay@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230307094643.532271-1-tejas.upadhyay@intel.com
