Commit Graph

875 Commits

Author SHA1 Message Date
Bellekallu Rajkiran
84cdf47abf fix: Update handles upon device reset
Outdated info that is present in several modules
because of reset result in crash when module info
is retrieved after reset.

Release and re-create module handles during reset
to avoid crash.

Related-To: NEO-9100

Signed-off-by: Bellekallu Rajkiran <bellekallu.rajkiran@intel.com>
2023-10-24 00:27:19 +02:00
Jablonski, Mateusz
d724627098 fix: fix compilation error in clang on Windows (1/n)
Signed-off-by: Jablonski, Mateusz <mateusz.jablonski@intel.com>
2023-10-23 10:36:23 +02:00
Brandon Yates
85d35d5239 feature(debugger): use linux driver type to create correct debug session imp
Related-to: NEO-8403

Signed-off-by: Brandon Yates <brandon.yates@intel.com>
2023-10-23 10:25:28 +02:00
Bellekallu Rajkiran
75537b3463 feature: Add support for fabric multi port throughput
Update iaf uapi header sync to:
https://github.com/intel-gpu/drm-uapi-helper/releases/tag/v2.0-rc19

Add netlink calls to support fabric multi port throughput.

Related-To: LOCI-4301

Signed-off-by: Bellekallu Rajkiran <bellekallu.rajkiran@intel.com>
2023-10-20 07:34:40 +02:00
Joshua Santosh Ranjan
994fb1110f fix(sysman): handle memory info creation failure
Related-To: NEO-8452

Signed-off-by: Joshua Santosh Ranjan <joshua.santosh.ranjan@intel.com>
2023-10-18 07:55:48 +02:00
Joshua Santosh Ranjan
5c8cbc80eb feature: initial support for programmable metrics
Related-To: NEO-8779

Signed-off-by: Joshua Santosh Ranjan <joshua.santosh.ranjan@intel.com>
2023-10-16 18:11:38 +02:00
Mateusz Jablonski
19aba581d4 fix: remove potential memory leak from OaMetricSourceImp class
Related-To: NEO-9038
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-12 10:59:25 +02:00
Mateusz Jablonski
4be1a8f615 fix: ignore read error when getting bandwidth for DG2
Related-To: NEO-9038
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-12 10:37:15 +02:00
Mateusz Jablonski
a420e34b10 fix: explicitly remove assign operators when not needed
when class defines copy/move ctor then corresponding assign operator(s)
should be defined or deleted

Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-12 10:25:15 +02:00
Mateusz Jablonski
a7e86f40bf fix: use FileDescriptor class to handle open/close file descriptor in PCI/PMT
Related-To: NEO-9038
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-11 14:04:07 +02:00
Compute-Runtime-Validation
52cc796886 Revert "fix: use FileDescriptor class to handle open/close file descriptor in...
This reverts commit 174ec38b52.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2023-10-11 03:07:04 +02:00
Mateusz Jablonski
420f273a6c fix: don't wait on condition in unit tests
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-10 15:14:30 +02:00
Mateusz Jablonski
174ec38b52 fix: use FileDescriptor class to handle open/close file descriptor in PCI/PMT
Related-To: NEO-9038
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-10 12:42:14 +02:00
Mateusz Jablonski
099a3f30e3 fix: add FileDescriptor class to ensure file descriptor is closed
Related-To: NEO-9038
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-09 16:23:28 +02:00
Brandon Yates
3fbce47182 refactor(debugger): Rename DebugSessionLinux
Rename to DebugSessionLinuxi915 in preparation
for implementation of Xe debugger

Related-to: NEO-8404

Signed-off-by: Brandon Yates <brandon.yates@intel.com>
2023-10-09 10:12:47 +02:00
Mateusz Jablonski
2ab4aeda85 fix: add static casts to destination type to avoid overflows in multiplication
Related-To: NEO-9038
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-06 14:55:24 +02:00
Mateusz Jablonski
a583213eef fix: add unrecoverable to avoid division by zero
Related-To: NEO-9038
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-06 08:43:11 +02:00
Mateusz Jablonski
382fc952f2 refactor: add NonAssignableClass to define classes without assign operator
Related-To: NEO-9038
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-05 15:16:58 +02:00
Mateusz Jablonski
72182c28e9 refactor: add NonCopyableOrMovableClass to classes that don't need copy ctors
Related-To: NEO-9038
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-05 13:11:01 +02:00
Mateusz Jablonski
95eb5df978 refactor: use reference in for-range loops
Related-To: NEO-9038
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-04 15:32:26 +02:00
Mateusz Jablonski
895a586083 refactor: use reference in for-range loops
Related-To: NEO-9038
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-03 18:56:53 +02:00
Mateusz Jablonski
094724e0b3 refactor: remove not needed condition
Related-To: NEO-9038
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-03 10:19:28 +02:00
Mateusz Jablonski
1963ea69e5 fix: add missing member initializations
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-03 08:41:46 +02:00
Mateusz Jablonski
9337911742 fix: add self-assign check in operator=
Related-To: NEO-9038
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-10-03 08:09:16 +02:00
Mateusz Jablonski
4a80380aaf refactor: remove redundant comparing array address to zero
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-09-29 15:36:22 +02:00
Brandon Yates
253e1df43b feature(debugger): Filter page fault threads by start IP
When a thread is stopped due to potential page fault
we must check AIP against start IP to ensure it is not
a newly started thread accidentally caught by PF algorithm

Related-to: NEO-8617

Signed-off-by: Brandon Yates <brandon.yates@intel.com>
2023-09-29 12:45:32 +02:00
Brandon Yates
9c56a11c2e refactor(debugger): Move PF exception check into bitmask
Related-to: NEO-8617
Signed-off-by: Brandon Yates <brandon.yates@intel.com>
2023-09-28 08:28:00 +02:00
Mateusz Jablonski
3a21b3b228 refactor: remove not needed code
Related-To: NEO-7527

Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-09-28 07:52:39 +02:00
Brandon Yates
b3464a2621 feature(debugger): Expose DBG regset
Related-To: NEO-8383

Signed-off-by: Brandon Yates <brandon.yates@intel.com>
2023-09-26 11:50:29 +02:00
Jitendra Sharma
8f7b3e6699 feature: Report 128 GRF count with zetDebugGetRegisterSetProperties
Related-to: NEO-6788

Signed-off-by: Jitendra Sharma <jitendra.sharma@intel.com>
2023-09-18 11:03:59 +02:00
Brandon Yates
7c1f5585d7 feature(debugger): online page fault event handling
Sync to
https://github.com/intel-gpu/drm-uapi-helper/releases/tag/v2.0-rc20

Related-to: LOCI-2052

Signed-off-by: Brandon Yates <brandon.yates@intel.com>
2023-09-18 00:15:45 +02:00
Brandon Yates
513045bd90 fix(debugger): auto-ack vmbind on tile for module from other tiles
Related-to: NEO-8371

Signed-off-by: Brandon Yates <brandon.yates@intel.com>
2023-09-14 15:33:58 +02:00
Compute-Runtime-Validation
e489c16529 Revert "feature: Report 128 GRF count with zetDebugGetRegisterSetProperties"
This reverts commit 6596ce5097.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2023-09-14 14:34:55 +02:00
Jitendra Sharma
6596ce5097 feature: Report 128 GRF count with zetDebugGetRegisterSetProperties
Related-to: NEO-6788

Signed-off-by: Jitendra Sharma <jitendra.sharma@intel.com>
2023-09-13 14:12:38 +02:00
Jitendra Sharma
9818ef61a5 feature: Report correct GRF register count
Based on Large GRF enabled or not, report correct GRF
register.

Related-To: NEO-6788
Signed-off-by: Jitendra Sharma <jitendra.sharma@intel.com>
2023-09-04 11:42:48 +02:00
Compute-Runtime-Validation
154530ad23 Revert "feature: Report correct GRF register count"
This reverts commit 8eb3fe222e.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2023-09-01 15:12:57 +02:00
Jitendra Sharma
8eb3fe222e feature: Report correct GRF register count
Based on Large GRF enabled or not, report correct GRF
register.

Related-To: NEO-6788
Signed-off-by: Jitendra Sharma <jitendra.sharma@intel.com>
2023-08-31 18:48:29 +02:00
Compute-Runtime-Validation
e61c5af7ec Revert "feature(debugger): online page fault event handling"
This reverts commit 0c6444aab7.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2023-08-24 08:16:45 +02:00
Brandon Yates
0c6444aab7 feature(debugger): online page fault event handling
Related-to: LOCI-2052

Signed-off-by: Brandon Yates <brandon.yates@intel.com>
2023-08-23 18:29:58 +02:00
Brandon Yates
9db08001c4 fix(debugger): Set flags for MME regset
Related-to: NEO-8286

Signed-off-by: Brandon Yates <brandon.yates@intel.com>
2023-08-23 16:38:35 +02:00
Bari, Pratik
f9e4381c1e feature: Add FsAccess and Derived class in Sysman Kmd Interface
- The FsAccess, ProcFsAccess and SysfsAccess classes have been added in
a file in the Sysman Shared directory. The instances of these classes
are maintained in the Sysman Kmd Interface classes.
- Added functions for opendir, readdir and closedir in the shared code.
- Added a ULT in the sysman directory to cover these new functions from
the shared code.

Related-To: LOCI-4689

Signed-off-by: Bari, Pratik <pratik.bari@intel.com>
2023-08-23 11:38:57 +02:00
Spruit, Neil R
5c75449508 fix: Track Sub Device Hierarchy for use by Metrics Library
Related-To: LOCI-4819

- When communicating with the Metrics Libraries, if one is using a
specific sub device, then the correct physical sub device index and
number of sub devices must be used.

- When Affinity Mask is set, this hierarchy information is lost,
therefore the sub device hierarchy data is stored in a map to each
"device" to be returned to the user allowing for the correct sub device
information to be passed to the metrics library.

Signed-off-by: Spruit, Neil R <neil.r.spruit@intel.com>
2023-08-22 21:37:25 +02:00
Mateusz Jablonski
8b09bb855e fix: add missing includes
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2023-08-22 16:31:11 +02:00
Bellekallu Rajkiran
81d037f59b feature(sysman): Add support for fabric error counters
Related-To: LOCI-4620

Signed-off-by: Bellekallu Rajkiran <bellekallu.rajkiran@intel.com>
2023-08-16 15:05:32 +02:00
Kacper Nowak
1afaf37f78 refactor: Unify GTPin initialization logic between APIs
Add support for new GTPin loading logic in OCL path, similar to existing
in L0 - invoking exposed, dedicated API call (OpenGTPinOCL).
- Move logic to shared, including unit tests
- Check whether instrumentation is required on
  context creation and if yes,
  make a call to OpenGTPinOCL function.
  Handle potential errors gracefully without exiting.
Signed-off-by: Kacper Nowak <kacper.nowak@intel.com>
2023-08-09 17:15:24 +02:00
Compute-Runtime-Validation
65df34bbc7 Revert "refactor: Unify GTPin initialization logic between APIs"
This reverts commit 68a5108e05.

Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com>
2023-08-07 04:31:52 +02:00
Kacper Nowak
68a5108e05 refactor: Unify GTPin initialization logic between APIs
Add support for new GTPin loading logic in OCL path, similar to existing
in L0 - invoking exposed, dedicated API call (OpenGTPinOCL).
- Move logic to shared, including unit tests
- Check whether instrumentation is required on
  clGetPlatformIDs API call, and if yes,
  make a call to OpenGTPinOCL function.
Signed-off-by: Kacper Nowak <kacper.nowak@intel.com>
2023-08-05 18:22:08 +02:00
Kulkarni, Ashwin Kumar
5cd39dd155 fix(sysman): supports return of correct temperature domains on igfx
Related-To: LOCI-4741

Signed-off-by: Kulkarni, Ashwin Kumar <ashwin.kumar.kulkarni@intel.com>
2023-08-04 12:28:50 +02:00
Bellekallu Rajkiran
63fa05e776 fix: Proper update of device count that generated events
numDeviceEvents out param is not being updated in case
there are no events and device events map is not overridden
on multiple register calls result in failure.

Related-To: LOCI-4751

Signed-off-by: Bellekallu Rajkiran <bellekallu.rajkiran@intel.com>
2023-08-04 11:58:56 +02:00
Bari, Pratik
3f083360a2 feature(sysman): Added sysfs filenames for the memory module
- The sysfs filenames have been added in the sysfsNameToFileMap of the
SysmanKmdInterface classes.
- The functions returning the sysfs filenames have been removed from the
shared directory.
- The ULTs have been added to return the sysfs filenames.

Related-To: LOCI-4699

Signed-off-by: Bari, Pratik <pratik.bari@intel.com>
2023-08-03 22:36:17 +02:00