When is hsaKmtCreateQueue called first time for node
doorbells[NodeId].size is initialized to zero in init_process_doorbells
but used to calculate the doorbell offset. It works just by accident
because doorbells[NodeId].size is uint32_t so -1 will be 0xFFFFFFFF which
is zero extended into 0x00000000FFFFFFFF and it will work as long as mmap
offset bits are not within lower 32 bits.
Bug: https://github.com/RadeonOpenCompute/ROCT-Thunk-Interface/issues/78
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Change-Id: Ia791adfc51363d4704cb50fa4f01137b7dd48a75
Modifier scc is disabled from gfx90a's asm, so remove the
shader for gfx90a A+A and keep it for newer asics with scc
support.
Signed-off-by: Eric Huang <jinhuieric.huang@amd.com>
Change-Id: Iec3c7ccd5156a855adb2b02feb3db0761876aa2f
File reorganization feature was implemented with backward compatibility
The backward compatibility support will be deprecated in future release.
Changed the #pragma message to #warning for a smooth transition
Change-Id: I21025f4cefb40721f095130263b4247877979d36
Simplified the callback method. Also fixed the way, loaded shared object were getting appended into a string vector,
which was not being passed to this callback method.
Change-Id: I68661dd73f61a11c42fa92f670e8e7b6ffcb5711
File reorganization feature was implemented with backward compatibility
The backward compatibility support will be deprecated in future release.
Changed the #pragma message to #warning for a smooth transition
Change-Id: Ibaedc1873bc764d25f74d9ca9416077d084e332d
When hsa is closed, it would close open fds for /dev/kfd but
not for /dev/dri/renderD*. This caused issues with CRIU
checkpoint, which expects that /dev/kfd will be open if
/dev/dri/renderD* is.
As a workaround for the CRIU behaviour, leave /dev/kfd open
when closing hsa.
Signed-off-by: David Francis <David.Francis@amd.com>
Change-Id: Ie1b2d5b1d8986750b0e560ae2934b7c73cff942e
Previous versions of HIP will call hsa_amd_ipc_memory_create with then
len aligned to granularity. Temporarily allow this so that we go not
break backward compability. Will remove this after 2 releaes
Change-Id: I6b5ac2cad5d32d62c803637cf1a2c6deebc03169
To avoid confusion since this shader has changed to be persistent
(original IterateIsa may be re-used for debugger tests).
Signed-off-by: Graham Sider <Graham.Sider@amd.com>
Change-Id: I4643692765fc7665933257e89d5b922e779ad2e5
Don't use the full path to link against libc, but rather let
cmake find it.
Regarding gcc_s, it doesn't seem like this is still needed, so I've
removed it instead.
Change-Id: I1dc594f10c647b2abfdab7c5e0de90c331c6eeaf
Signed-off-by: Jeremy Newton <Jeremy.Newton@amd.com>
To be more alligned with ROCr, libdrm dev package appears to be
required, but we don't care if it's ours or the distro's. So require
either but recommend our package to get the latest version.
Change-Id: I744ce4861644a83ba94c39e0bf4230eab58cc68a
Signed-off-by: Jeremy Newton <Jeremy.Newton@amd.com>
MES devices need GART mappings and therefore need non-paged memory. But
using non-paged memory introduces performance regression where it can
take over 80 ms to see the signal changes if the memory is in the wrong
NUMA node. Currently, we cannot control NUMA affinity when allocating
non-paged memory. Using non-paged memory allocation only on devices that
have MES scheduler
Change-Id: Ib27fb01d75247aa4f2bb2aa4503c6af5a98afda0
Using previous method of std::thread for SVM profiler task was causing
segfaults on thread launch on RHEL 8 if libhsa-runtime library is loaded
using dlopen.
Change-Id: Ic010cd6ae9bc6e6ed0605de02b93f6aae8ed3e97
Transient exec usage is not required for GFX11 and will result in a NULL
return of s_sendmsg_rtn if directly returned to exec_lo.
Directly fetch and mask the doorbell ID to ttmp3 for GFX11 instead.
Change-Id: Ie17ed69d68d84ab18869b1c7871a0ed0482cd661
Update rocrtst packaging to add dependency on rocm-core so that rocrtst
gets uninstalled when rocm-core package is removed
Depends-On : I1e7ed52d7eed2c190d0b5651e7ded7192d7634b5
Change-Id: I7243dd29950b93a2665720a0062816c574f0f640
If hsa_amd_agents_allow_access is called for an imported IPC handle,
ignore the request as this pointer will already have these pointers
mapped to other GPUs during IPCAttach()
Change-Id: I4bf33ed57e93b5a3ead749d4f87ab6f2750bed58
Get more debug information about user pointers that were registered
through SVM API, and triggered by memory exception events.
A new kfdtest with this use case was also included inside
KFDExceptionTest.
Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Change-Id: I8e9df3c1c6c3f42d7b9235d12406d80d31746443
Register and map userptrs through Shared Virtual Memory(SVM) API at
the Kernel level when available. Using this approach, performance
will be improve as register/unregister memory will not trigger any
system call to KFD driver.
Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Change-Id: I20723cbeb340bf48b95e1115f0102c031397bc14
If a user queries the pointer info on an invalid pointer,
hsaKmtQueryPointerInfo will return error or unknown pointer. The other
fields in HsaPointerInfo are invalid, so we do not return them to the
user.
Also removing the assert and returning unknown pointer instead. As the
assert will not trigger in release builds.
hsaKmtQueryPointerInfo may also return unknown pointer for userptrs as
they are not always tracked by thunk. Adjusting code to still treat
these pointers as valid in this case.
Change-Id: Idf5cd8b61cd532d31b072f449839d223369bb138
:Since all public interface libraries are present in
same folder RUNPATH/RPATH is not required in the library itself.
Application shall provide the required RPATH/RUNPATH to load all
libraries.
Change-Id: I1d1ba920bf291eb89bd1f4c0fd0cfd80c7d739bd
Amount of memory requested by user may be aligned-up internally to
the memory pool granularity. The extra padded memory should not be
considered when validating pointers from the user. Also return the
user requested size when user queries pointer information.
Change-Id: I28b25448ea03c836b44fafdb34b7330cf6887424
For APU asics, the default configuration size of video memory is
relatively small, while the reserved region becomes larger in recent
generation asics, ratio of max alloc size to the pool size may below
the expected value, so adjust it.
Signed-off-by: Yifan Zhang <yifan1.zhang@amd.com>
Change-Id: I0e847c4c13e957cf6e811d3f379842619cf53370
What we want for libdrm-amdgpu is for it to be a recommended package.
Either libdrm or libdrm-amdgpu can be used, but we recommend the latter.
Using "SUGGESTS" does not seem like a strong enough requirement, but
CPACK does not support RPM recommends. Although, it does allow
customizing the RPM SPEC file template. By generating a template, which
is done by setting:
-DCPACK_RPM_GENERATE_USER_BINARY_SPECFILE_TEMPLATE=1
This template file can be trivially modified to allow adding a line to
implement CPACK_RPM_PACKAGE_RECOMMENDS.
Fixes
Signed-off-by: Jeremy Newton <Jeremy.Newton@amd.com>
Change-Id: I34467b1ba878827ced9b8db74977967815732552
KFDCWSRTest.BasicTest is parameterized to allow an easy method of
tweaking the number of work-items (and save/restores). The input/output
buffers were previously hardcoded to a single page, which would cause a
segmentation fault if the number of work-items specified is greater than
1024 for wave32.
Signed-off-by: Graham Sider <Graham.Sider@amd.com>
Change-Id: Ieefc819a5d81c77cee88081a287fd383e6378e74
For software trap in GFX11, COMPUTE_PGM_RSRC1 must have PRIV = 1.
Signed-off-by: Graham Sider <Graham.Sider@amd.com>
Change-Id: Id504889c3ca2588b6c8cefdebaec00dcfc217995
On error mmap returns value MAP_FAILED, which is (void *)-1, not NULL
pointer.
Change-Id: I81b187266c943fa0aa4fab21b529d4c2989b12ad
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Prior to launch some ASICs may re-use PCI DIDs from older generations.
This can cause issues during topology initialization as hsa_gfxip_table
lookups will override sysfs-provided gfx versions, causing incorrect
gfxip selection. Since no new entries will be added to hsa_gfxip_table,
limit its search only to pre-GFX11 ASICs.
Signed-off-by: Graham Sider <Graham.Sider@amd.com>
Change-Id: I53eaefac5db2650a36a6ce9f21daf750f50cfd26
IterateIsa had some leftover instructions from when the shader was
getting updated for KFDCWSRTest.BasicTest.
Signed-off-by: Graham Sider <Graham.Sider@amd.com>
Change-Id: I41ae7b7948cbe2aff8bf61b170b9a7d498b836a3
fork process copy-on-write MMU nitifier on CWSR range will evict user
queues, and then update GPU mapping and resume queues, use MADV_DONTFORK
to avoid COW MMU notifier callback on CWSR SVM range.
Use mmap to alloc SVM range for CWSR because posix_memalign don't alloc
new range in child process, this fails to register svm range as range is
invalid address in forked child process.
Change-Id: Ibaea56a691dd6f577ed2e1f2d43f4a3500b8316f
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
To remove duplicate mmap aligned allocation code.
Change-Id: Ibc05cc4aaf6d190bd2382e33bdeca1496960c5f2
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
mmap alloc larger address range with align padding page plus guard
pages, then unmap the padding and guard pages at beginning and end
of the range, return aligned address range.
Change-Id: Iaf3c711a079c744289efbafee9b5e63aaf724765
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
GFX1036(ISA version) is not included in the previous range.
This patch can really include all gfx10 series ASICs.
Signed-off-by: Aaron Liu <aaron.liu@amd.com>
Change-Id: I0e28dbfc031c216166b306b9fb39f644f75a330f
Avoiding the segfault, runtime debugger enable is not supported
if the firmware of gpu doesn't support debug exceptions.
Signed-off-by: jie1zhan <jesse.zhang@amd.com>
Change-Id: Ifad57a6e78cb1c92b1f8927355ece8c64e89c51b
Remove potential double free condition when free_queue() is called
after hsaKmtDestroyQueue() if mapping doorbell fails during queue
creation.
Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Change-Id: If2aa19c455b30d2940b232dbafb9cc1eaad721a5
Felix Kuehling
Eric Huang
David Yat Sin
Ranjith Ramakrishnan
Shweta Khatri
David Francis
Nirmal Unnikrishnan
Graham Sider
Jeremy Newton
Ramesh Errabolu
Jonathan Kim
Alex Sierra
Freddy Paul
David Belanger
Yifan Zhang
Sean Keely
Philip Yang
Daniel Phillips
Aaron Liu
jie1zhan
Mukul Joshi