Enabled recoverable pagefault and kmd migration support by
default for bmg and lnl, but disabled kmd migration for XeKMD
in order to disable kmd migration for all platforms using
XeKMD for now.
Related-To: NEO-13116
Signed-off-by: Young Jin Yoon <young.jin.yoon@intel.com>
This patch adds following includes to the whitelist:
<cm/cm.h>
<cm/cmtl.h>
Related-To: NEO-13641
Signed-off-by: Fabian Zwoliński <fabian.zwolinski@intel.com>
- some tests initialize sip kernel but do not free it
- this is causing memory leaks
- as a solution mock sip listener is added that will release allocated
sip kernel
Related-To: NEO-13789
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
gtId is not same as tileId. instead use gtIdToTileId
to retrieve tileId based on gtId.
Related-To: NEO-11104
Signed-off-by: Jitendra Sharma <jitendra.sharma@intel.com>
This commit addresses a bug in the previous implementation where almost all once
writable types, except `gpuTimestampBuffers`, were incorrectly enabled for TBX
faultable checks. The fix ensures that only the subset of once writable
types that are also lockable are considered TBX faultable, using the lockable
check to avoid manual exceptions and re-inventing the wheel.
Changes:
- Updated `isAllocTbxFaultable` method to check if the allocation type is
lockable in addition to being once writable.
- Refactored unit tests to include separate checks for lockable and non-lockable
allocation types.
Performance optimization:
- Removed unnecessary memory data erasure in `handlePageFault` to avoid constant
erase/insert operations, leveraging the O(1) search time of unordered maps.
Related-To: NEO-12319
Signed-off-by: Jack Myers <jack.myers@intel.com>
Patch #34223 introduced the TbxPageFaultManager for handling
uploads/downloads of host buffers to the Tbx server, ensuring
host memory is kept consistent between the host and device,
even after multiple alternating writes from the host and gpu.
This patch enable fault handling for all `isAubOnceWritable`
types.
Minor exception for gpuTimestampBuffers as enabling this type
seems to break things in real-world use cases outside of ULTs.
Related-To: NEO-12319
Signed-off-by: Jack Myers <jack.myers@intel.com>
Renames the EU_THREAD_SCHEDULING_MODE_OVERRIDE member of
STATE_COMPUTE_MODE structure to EU_THREAD_SCHEDULING_MODE.
This modification is introduced in order to align with the latest specification.
Related-To: NEO-13147
Signed-off-by: Vysochyn, Illia <illia.vysochyn@intel.com>
Addresses regressions from the reverted merge
of the tbx fault manager for host memory.
Recursive locking of mutex caused deadlock.
To fix, separate tbx fault data from base
cpu fault data, allowing separate mutexes
for each, eliminating recursive locks on
the same mutex.
By separating, we also help ensure that tbx-related
changes don't affect the original cpu fault manager code
paths.
As an added safe guard preventing critical regressions
and avoiding another auto-revert, the tbx fault manager
is hidden behind a new debug flag which is disabled by default.
Related-To: NEO-12268
Signed-off-by: Jack Myers <jack.myers@intel.com>
Renames the EU_THREAD_SCHEDULING_MODE_OVERRIDE member of
STATE_COMPUTE_MODE structure to EU_THREAD_SCHEDULING_MODE.
This modification is introduced in order to align with the latest specification.
Related-To: NEO-13147
Signed-off-by: Vysochyn, Illia <illia.vysochyn@intel.com>
Young Jin Yoon