* kfdtest: Enable GPU selection via CLI for multi-GPU tests
Replaced environment variable-based GPU selection with
GPU selection via command-line parameter --concurrentnodes (-c)
Modified g_TestGPUsNum to be passed in via command-line
parameter --testnodenum (t)
Signed-off-by: Alysa Liu <Alysa.Liu@amd.com>
* kfdtest: Enable GPU selection via CLI for multi-GPU tests
Replaced environment variable-based GPU selection with
GPU selection via command-line parameter --concurrentnodes (-c)
Modified g_TestGPUsNum to be passed in via command-line
parameter --testnodenum (t)
---------
Signed-off-by: Alysa Liu <Alysa.Liu@amd.com>
Co-authored-by: Alysa Liu <Alysa.Liu@amd.com>
Workaround for rare issue on gfx90x asics when SDMA_OP_POLLREGMEM
returns before polled memory has value of 0.
Removing previous SW workaround to double-poll as it was not reliable.
* rocr: hsa_amd_pointer_info return err on shutdown
Decrement ref count before starting to unload to make sure API
calls during shutdown return error.
Delete blit objects during agent destructor.
* Add support for HSA_AMD_SYSTEM_SHUTDOWN_EVENT
Add support for new event to indicate shut down within the
hsa_amd_register_system_event_handler API.
* SWDEV-555347 - Remove lock contention in async events loop
* SWDEV-555347 - Introduce Pool of AsyncEventItems
* create generic mempool for AsyncEventItem
* Use BaseShared allocate and free for async event pool
---------
Co-authored-by: Rahul Manocha <rmanocha@amd.com>
* Check emulator mode at runtime
* Reduce emu mode function call to one time and use result
* Move function to main.cc
* Address feedback
* EmuMode check improvement; convert to AoS
* replace g_isEmuMode with func call
* Add mode check func for every sample
* rocr: fix nullptr dereference
Return early in the case that malloc fails to avoid dereferencing of a
null pointer on eventDescrp.
Signed-off-by: Sunday Clement <Sunday.Clement@amd.com>
* rocr: Fix potential nullptr dereference
returns early if sym->section() fails to properly acquire the object.
Signed-off-by: Sunday Clement <Sunday.Clement@amd.com>
---------
Signed-off-by: Sunday Clement <Sunday.Clement@amd.com>
Co-authored-by: Sunday Clement <Sunday.Clement@amd.com>
* rocr: Add support for VMM and RDMA
Add extra CPU mapping so that kernel-mode drivers can look up the memory
mapping by virtual address.
* Update projects/rocr-runtime/runtime/hsa-runtime/core/runtime/runtime.cpp
Co-authored-by: Yiannis Papadopoulos <102817138+ypapadop-amd@users.noreply.github.com>
* Update projects/rocr-runtime/runtime/hsa-runtime/core/inc/runtime.h
Co-authored-by: Yiannis Papadopoulos <102817138+ypapadop-amd@users.noreply.github.com>
* rocr: Honor uncache flag in memory_lock_to_pool()
Also, combined several flag options used in apis into a
single integer.
Signed-off-by: Chris Freehill <cfreehil@amd.com>
* rocr: Fix hsa_amd_pointer_info on CPU agents
Fix hsa_amd_pointer_info query returning allowd on VMM pointers for CPU
agents when CPU mapping was mapped with PROT_NONE.
---------
Signed-off-by: Chris Freehill <cfreehil@amd.com>
Co-authored-by: Yiannis Papadopoulos <102817138+ypapadop-amd@users.noreply.github.com>
Co-authored-by: Chris Freehill <cfreehil@amd.com>
Co-authored-by: cfreeamd <166262151+cfreeamd@users.noreply.github.com>
Modify the code that computes the adjusted CU mask array to take
into account of additional cases for inactive CUs.
Signed-off-by: David Belanger <david.belanger@amd.com>
this test will prefetch SVM memory, and then verify the memory is sourced
from the expected numa node.
Signed-off-by: Sunday Clement <Sunday.Clement@amd.com>
Query IPC handles on shared memory export/import for any metadata as a
means to uniquely identify handles that happen to be backed by buffers
that point to the same memory.
* rocr: Don't assert in hsa_shut_down when no agents
Instead, print error message and return an error. Prior to
this patch, the assertion would occur when hsa_shut_down() is
called more than once.
* rocr: Reorder Unload ASAN clean-up on shut down
* rocrtst: Reduce host memory limit to 70%
Reducing the upper bound for rocrtstFunc.Memory_Max_Mem to 70% from
90% to help reduce test execution time.
Signed-off-by: Sunday Clement <Sunday.Clement@amd.com>
* rocrtst: Add ROCRTST_LIMIT_POOL_SIZE env var
Add environment variable to override the memory pool sizes when running
tests.
Co-authored-by: David Yat Sin <David.YatSin@amd.com>
---------
Signed-off-by: Sunday Clement <Sunday.Clement@amd.com>
Co-authored-by: David Yat Sin <David.YatSin@amd.com>
* libhsakmt: Update hsakmt_fmm_get_handle to support address range
Currently, hsakmt_fmm_get_handle works only if the address is allocated
(staring) value. Update it so it can find the handle if address falls in
the valid allocated range. This is useful for AMD infinity storage
feature where data needs to be transferred to any memory within in the
allocated range
Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
* libhsakmt: Introduce AMD Infinity Storage (AIS) API
Add hsaKmtAisReadWriteFile() API to support AMD Infinity Storage. The
API moves data directly from GPU VRAM to a file.
v2: Add in/out ioctl arguments to provide more status information to
user space. Modify hsaKmt API also accordingly.
Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
* rocr: Initial implementation of AMD Infinity Storage (AIS)
Implement first two API: hsa_amd_ais_file_write and hsa_amd_ais_file_read
v2: Change API from hsa_amd_ to hsa_amd_ais_
Change API to take in handle instead of fd for compatibility accross
different platforms
Original Author: Chris Freehill <Chris.Freehill@amd.com>
Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
---------
Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Because the base QueueWrapper class copies the wrapped queue's
amd_queue_v2_t queue descriptor struct the QueueProxy seems
superfluous as it will have the same effect as calling the
underlying methods on the wrapped queue itself.
Additionally, because the QueueProxy needs to access the wrapped
queue's queue descriptor it breaks the Queue API which is meant
to abstract the underlying agent's queue implementation.
This makes it easier to generalize the core::Queue as well as
the InterceptQueue.
Signed-off-by: Tony Gutierrez <anthony.gutierrez@amd.com>
Make sure ROCR can be compiled under windows. Extra setup for the windows build environment is required. The change should not have any functional changes under Linux.
* libhsakmt: fix UB due to signed integer literal in 1 << 31
Bit shift operations on signed numbers should not shift into or beyond
the signed bit as this results in Undefined Behaviour.
Signed-off-by: Sunday Clement <Sunday.Clement@amd.com>
* libhsakmt: Fix UB due to signed integer literal in 1 << x
Bit Shifting an unsigned integer is undefined behavior.
BUG: SWDEV-532853
Signed-off-by: Sunday Clement <Sunday.Clement@amd.com>
* rocr: Fix UB in various places due signed integer in bit shift
Bit shifting signed integers into or beyond the sign bit is undefined.
Signed-off-by: Sunday Clement <Sunday.Clement@amd.com>
* rocr: Change signed integer literals to unsigned
Changing the signed integers in the macro expressions throughout the file
to avoid overflow.
Signed-off-by: Sunday Clement <Sunday.Clement@amd.com>
---------
Signed-off-by: Sunday Clement <Sunday.Clement@amd.com>
Co-authored-by: Flora Cui <flora.cui@amd.com>
* rocr: Fix Incorrect Assertion Check
The wrong variable is used in the assertion statement, should be error
checking for the value of paramEndLoc after it is modified by the call
to find().
Signed-off-by: Sunday Clement <Sunday.Clement@amd.com>
* rocr: Fix Potential Undefined Behaviour
In the event that the SvmProfileControl destructor is called and
event == -1 is true then the call to close(event) is effectively
close(-1) which is undefined behaviour. This has been changed to only
call close() on valid file descriptors.
Signed-off-by: Sunday Clement <Sunday.Clement@amd.com>
* rocr: Add Error Check on Bytes Read
In the case that there is an incomplete read the call to copyTo() will
now return an error.
Signed-off-by: Sunday Clement <Sunday.Clement@amd.com>
* rocr: Fix Exception Error
Destructors are implicitly marked with noexcept being true by default
so if its not explicitly marked false in the destructor or the
functions it calls, any thrown exceptions will cause the program to
crash.
Signed-off-by: Sunday Clement <Sunday.Clement@amd.com>
---------
Signed-off-by: Sunday Clement <Sunday.Clement@amd.com>
Co-authored-by: Sunday Clement <Sunday.Clement@amd.com>
InterceptQueue::Submit had an "all-or-nothing" packet submission policy that
could cause infinite retry loops when the number of packets to submit exceeded
the available queue slots. When 504+ packets needed submission to a ~500-slot
queue, the system would:
1. Set submitted_count=0 (submit nothing)
2. Add retry barrier packet
3. Trigger async handler via StoreRelaxed
4. Attempt to submit overflow packets
5. Fail again due to same space constraints
6. Repeat
Solution:
Added partial packet submission capability during overflow processing while
preserving the original "all-or-nothing" behavior for normal operations.
When processing overflow packets and insufficient space exists for all packets,
the system now submits as many packets as possible rather than none.
The fix:
- Detects overflow processing via !overflow_.empty()
- Allows partial submission: submitted_count = free_slots - barrier_reservation
- Maintains atomicity guarantees for normal packet rewrites
- Prevents infinite retry loops by ensuring forward progress
This resolves deadlocks in high-throughput scenarios while maintaining
backward compatibility and the original design intent for packet rewrite
atomicity.
New test that does a memory_copy, and right after has the shader access
the data. This verifies that the memory is coherent and that all the
probes and flushes were done correctly by the memory_copy.
Signed-off-by: Sunday Clement <Sunday.Clement@amd.com>
* libhsakmt: Update ioctl version to 1.18
Sync with kernel ioctl version.
Also explicitly set the ioctl flag to KFD_PROC_FLAG_MFMA_HIGH_PRECISION
Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
* libhsakmt: Sync ioctl header by adding kfd_ioctl_profiler
Sync with kernel ioctl version. Add kfd_ioctl_profiler.
Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
---------
Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
When stochastic sampling is not active, the trap handler is incorrectly
branching to .check_exceptions, bypassing the software trap ID checks
and inturn not advancing the PC. Fixed the issue to always check software
traps regardless of PC sampling state.
Co-authored-by: Shweta Khatri <shweta.khatri@amd.com>
This commit reverts the following related commits which cause
test failures:
6d15779b3e rocr/driver: add PC sampling support to driver interface
56cb9390ff rocr/driver: add PC sampling support to driver interface
76bf829f09 rocr/driver: add ASAN header page management to Driver class
a47c060d6a rocr/driver: add ASAN header page management to Driver class
02d7eaf3b7 rocr: add memory sharing call to Driver interface
9312468655 rocr: add memory sharing call to Driver interface
Fix regression when hsa_amd_pointer_info is called on a pointer that was
allocated using non-VMM APIs. The helper function VMemoryPtrInfo should
return error when the address is not found so that PtrInfo does the
lookup via Thunk.
Also advice parameter of madvise() system call is not a bitmask. So fix
that also
v2: Use MAP_SHARED instead of MAP_PRIVATE. This avoids MMU notifiers and
evictions.
Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
German Andryeyev
systems-assistant[bot]
arvindcheru
Yiannis Papadopoulos
David Yat Sin
Rahul Manocha
pghoshamd
randyh62
cfreeamd
David Bélanger
Sunday Clement
Alysa Liu
axie_amdeng
hkasivis
Tony G
Benjamin Welton
Flora Cui
estewart08
SaleelK
jonatluu
shwetakhatri-amd