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>
This is required for scenarios without direct submission
Otherwise, staging transfers are enqueued but not actually
flushed. If that happens, subsequent staging transfers can't
reuse previous staging buffers. It results in increased memory usage.
Signed-off-by: Szymon Morek <szymon.morek@intel.com>
getLoadedLibVersion is intended for reading version of a library that was
already loaded into the process prior to this call (i.e. new instance of
the library willnot be loaded).
Note: Currently, only windows version of this functionality is implemented.
Related-To: GSD-10248
Signed-off-by: Chodor, Jaroslaw <jaroslaw.chodor@intel.com>
Addresses regressions from the reverted merge
of the tbx fault manager for host memory.
This fixes attempts by the tbx fault manager
to protect/unprotect host buffer memory, even
if the host ptr was not driver-allocated.
In the case of the smoke test that triggered
the critical regression, clCreateBuffer was
called with the CL_MEM_USE_HOST_PTR flag.
The subsequent `mprotect` calls on the
provided host ptr then failed.
Related-To: NEO-12268
Signed-off-by: Jack Myers <jack.myers@intel.com>
restored the possibility of different writing modes in the FileLogger
mocked writeToFile in TestFileLogger
Related-To: NEO-7006
Signed-off-by: Marcel Skierkowski <marcel.skierkowski@intel.com>
Track amount of created buffer pools per device. Do not allocate extra
pools if limit is reached. New contexts will have pooling disabled if
limit is reached on device.
Related-To: NEO-13461
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
reducing the number of tests that have interactions with filesystem.
writeDataToFile() saves filename and content in std::map.
fileExistsHasSize() checks if file was previously written to virtualFileSystem
loadDataFromVirtualFile() fetches data from std::map based on filename
Related-To: NEO-7006
Signed-off-by: Marcel Skierkowski <marcel.skierkowski@intel.com>
eudebug interface is now hidden under EuDebugInterface class
shared code uses generic object and param values
layout of structs is guarded by static asserts
eudebug support is guarded by cmake flags:
- NEO_ENABLE_XE_EU_DEBUG_SUPPORT - enables eudebug in general
- NEO_USE_XE_EU_DEBUG_EXP_UPSTREAM - registers exp upstream uAPI support
- NEO_ENABLE_XE_PRELIM_DETECTION - registers prelim uAPI support
This way we can support two different xe-eudebug interfaces within
single binary.
In unit tests there is mock eudebug interface enabled (even if no
eudebug support is enabled by cmake flag).
Related-To: NEO-13472
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
bind info container is needed to distinguish between userptr and handles
with this change it stores only userptrs and their corresponding gpu va
Related-To: NEO-13501
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
In TBX mode, the host could not write to host buffers after access from device
code due to the lack of a migration mechanism post-initial TBX upload.
Migration is unnecessary with real hardware, but required for TBX.
This patch introduces a new page fault manager type that extends the original
CPU fault manager, enabling automatic migration of host buffers in TBX mode.
Refactoring was necessary to avoid diamond inheritance, achieved by using a
template parameter as the base class for OS-specific fault managers.
Related-To: NEO-12268
Signed-off-by: Jack Myers <jack.myers@intel.com>
Explicitly delete unused functions of CheckIfExitCalled
and VfManagementHandleContext. Comply with the rule of five.
Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
Refactors the STATE_BASE_ADDRESS to align with the latest specification.
Removes redundant functionality for multiple GPU partial writes and
atomics.
Related-To: NEO-13147
Signed-off-by: Vysochyn, Illia <illia.vysochyn@intel.com>
