get_od_clk_volt_info assumed the size of the file instead of checking
the length. This caused out-of-bounds array element access.
Change-Id: Ibda8f0c3a6d1623d48964641ae5ef610d2072e94
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
[ROCm/rocm_smi_lib commit: 8eb9f892d3]
* Updates:
- rocm_smi_logger:
General cleanup &
Aligned to cpplint rules for usage
- rocm_smi_monitor:
Fixed MonitorTypes
from not displaying properly in logs
& Added socket power label + current
socket power MonitorTypes
- rocm_smi API:
Added rsmi_dev_current_socket_power_get API
- rocm_smi CLI:
General cleanup,
Concise info now displays device data
in variable width (see printLogSpacer's
new field),
printLogSpacer now as an adjustable
variable that overrides appWidth,
Added Socket Power to base rocm-smi +
--showpower CLI calls,
--showpower & base rocm-smi CLI defaults
to printing socket power (if not available,
displays average power)
- Cleaned up temp label references
- power_read gtests:
Added current socket power to testing
Change-Id: Ica57e6f98ad96e2584e7c7955e188f68d2dab89d
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
[ROCm/rocm_smi_lib commit: f078375350]
The purpose of this patch is to add the following missing firmware
blocks to the SMI LIB:
-RSMI_FW_BLOCK_MES
-RSMI_FW_BLOCK_MES_KIQ
Signed-off-by: Ori Messinger <Ori.Messinger@amd.com>
Change-Id: I5d4d37d883878dd02ef8533d4eb8891d54d70630
[ROCm/rocm_smi_lib commit: d44a6ef523]
Change the code to handle the memory frequency if it is only one line.
Change-Id: I09e6ee78a2b9c12c861243dc89296e4e7862da49
[ROCm/rocm_smi_lib commit: 85df5676d4]
For operations related to:
--resetfans
--setfan
We report 'Not supported' for these cases instead of 'Permission denied'
Code changes related to the following:
* rocm_smi_properties
* rocm_smi related APIs
Change-Id: I144646efc3804fabd45cc5a46351803950b4feb7
Signed-off-by: Oliveira, Daniel <daniel.oliveira@amd.com>
[ROCm/rocm_smi_lib commit: 12f395e592]
* Updates:
- Fixed infinit loop on systems
which did not have VRAM files
- Fixed concise info from throwing exception
with no amdgpu driver loaded
- Fix for ability to see all nodes when
after switching partitions (mirrors
original card display/settings)
- Added to logs build type, lib path,
and set env. variables
Change-Id: Ic0333df355144ce2242cecea93fe4ce51caf311c
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
[ROCm/rocm_smi_lib commit: ed6777a8e7]
Code changes related to the following:
* Reverts earlier fix for the same issue
* Check for existence of files before reading
Change-Id: I175b20c3343c414b12b79dc3fc404f53fbaabf3a
Signed-off-by: Oliveira, Daniel <daniel.oliveira@amd.com>
[ROCm/rocm_smi_lib commit: 328ce0150b]
Change the affinity from unsigned int to integer to represent -1.
Change-Id: I82dc6f476b45fa4ec03a3c686fe8e6e2b7761b56
[ROCm/rocm_smi_lib commit: 471fbfddc1]
Sending RSMI_STATUS_UNEXPECTED_DATA for drivers
which do not set some clock freqs
Change-Id: I43a9515c2757dddd412bb25cfd54095e63367030
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
[ROCm/rocm_smi_lib commit: f191c2753c]
The driver may not expose VRAM sysfs in certain system. Add a
fallback to it.
Change-Id: Ib3be71b4f4d2c79318d5026b0a97f3657d8a97b6
[ROCm/rocm_smi_lib commit: a10f00bf57]
* Updates:
- Fix for devices which do not have edge sensors, but junction
- Added partitioning (memory and dynamic) displays for
base rocm-smi CLI calls
- Added subheading for base rocm-smi call output
- Added better hwmon and device detection logging
Change-Id: I8219884b2e532d6ed379527cacdc1f2b232a5451
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
[ROCm/rocm_smi_lib commit: 755e14dbad]
Code changes related to the following:
* All reinforcement work moved to their own files
* Self contained changes only to support them
* New files added to CMakeLists.txt
Change-Id: I761e91f54392824df9145eaed8b9805986861285
Signed-off-by: Oliveira, Daniel <daniel.oliveira@amd.com>
[ROCm/rocm_smi_lib commit: cc5ab079df]
* Updates:
- Env variable RSMI_LOGGING=0 or any other value
-> all logging off
- Env variable RSMI_LOGGING=1 -> logs only
- Env variable RSMI_LOGGING=2 -> console only
- Env variable RSMI_LOGGING=3 -> both logs + console
- Metrics output includes hexdump of current file
and decoded metrics (functions: logHexDump
and log_gpu_metrics)
- System info gathered, now includes if system's
perceived endianness - little or big endian
helpful for viewing decoded hexdump or any
binary translation
- Added templates for printing unsigned hex
(print_unsigned_hex_and_int), unsigned integers
(print_unsigned_int), and printing both unsigned
hex and int with an optional header
(print_unsigned_hex_and_int)
- Fixed some build compile warnings/errors -
ex. doing strncpys for sku or board names
this operation is expected and needed
and for temp file writes if unsuccessful
we now properly send RSMI_STATUS_FILE_ERROR
- Fixed on RHEL 8.8/9.x logrotate does not properly
initialize
Change-Id: Ifa0f0218c9cafd0a8cd6aa8e7f94d61e9107200f
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
[ROCm/rocm_smi_lib commit: 9c7eed7edc]
Code changes related to the following:
* Added 'rsmi_dev_revision_get()' related code
* Test code
* Functional tests
Change-Id: I8c2097c65384a028c8c8437b717d05d52fe45250
Signed-off-by: Oliveira, Daniel <daniel.oliveira@amd.com>
[ROCm/rocm_smi_lib commit: 573620f586]
The following read tests were failing:
*.TestIdInfoRead
*.TestSysInfoRead
1. *.TestIdInfoRead failed because rsmi_dev_brand_get did not specify
dependency on vbios_version.
2. *.TestSysInfoRead failed because the test didn't expect vbios_version to
be missing. Which is a new behavior in Aqua Vanjaram.
Change-Id: I9ee88a12fcf6cff2032049e2ecdfb2957efb03ab
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
[ROCm/rocm_smi_lib commit: 8fe848d10e]
Building on this package on Fedora reports this warning
In file included from rpmbuild/BUILD/rocm_smi_lib-rocm-5.5.1/src/rocm_smi_main.cc:62:
In member function 'amd::smi::Device::set_bdfid(unsigned long)',
inlined from 'amd::smi::RocmSMI::Initialize(unsigned long)' at rpmbuild/BUILD/rocm_smi_lib-rocm-5.5.1/src/rocm_smi_main.cc:330:27:
rpmbuild/BUILD/rocm_smi_lib-rocm-5.5.1/include/rocm_smi/rocm_smi_device.h:199:42: warning: 'bdfid' may be used uninitialized [-Wmaybe-uninitialized]
199 | void set_bdfid(uint64_t val) {bdfid_ = val;}
| ~~~~~~~^~~~~
rpmbuild/BUILD/rocm_smi_lib-rocm-5.5.1/src/rocm_smi_main.cc: In member function 'amd::smi::RocmSMI::Initialize(unsigned long)':
rpmbuild/BUILD/rocm_smi_lib-rocm-5.5.1/src/rocm_smi_main.cc:324:12: note: 'bdfid' was declared here
324 | uint64_t bdfid;
| ^~~~~
Only set the bdfid when it is know to be valid.
Signed-off-by: Tom Rix <trix@redhat.com>
Change-Id: I839b4d2d2d4e3b25469cf5972245b9630da00c87
[ROCm/rocm_smi_lib commit: 19c3e2aff9]
The gpu_metrics may have required PCI link width and speed.
Change-Id: I939d733f5f6a71088545ba042345eb1b6ad20ee5
[ROCm/rocm_smi_lib commit: a6467c4083]
Updates:
* [rocm-smi] Provide a thread-safe logging feature
* [rocm-smi] Adding logrotation into install/upgrade/remove
scripts
* [rocm-smi] Updated cmake lists to include rocm_smi_logger
* [rocm-smi] Updated DEB/RPM install/remove logging file &
folder with all users having r/w privledges for
/var/log/rocm_smi_lib/ROCm-SMI-lib.log
* [rocm-smi] Added ability to do a glob search for multiple files
(globFileExists), assists doing file searches with * strings
* [rocm-smi] Added ability to log system details when RSMI_LOGGING
is turned on (getSystemDetails())
* [rocm-smi] Added logging to provide which ROCm API is being called
when RSMI_LOGGING is on
* [rocm-smi] Added logging to provide SYSFS path and read value,
when RSMI_LOGGING is on. Provides error reponse on failure.
* [rocm-smi] Added logging to provide SYSFS path and read value,
when RSMI_LOGGING is on. Provides error reponse on failure.
* [rocm-smi] Added environment variable RSMI_LOGGING to control
when logging is enabled or disabled. By default, by not
setting this env. variable, logging is turned off. When
setting RSMI_LOGGING=<any value>, logging is enabled
which is placed in /var/log/rocm_smi_lib/ROCm-SMI-lib.log file.
Setting RSMI_LOGGING is allowed in both debug and release builds.
* [rocm-smi] Removed an initialize procedure which keeps
debug_inf_loop. Seems this feature is not being used.
Change-Id: I79b48387609c6233c6f05b04fb8bba66b68c2399
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
[ROCm/rocm_smi_lib commit: c3a095a180]
Updates:
* [rocm-smi] Added larger app width size, which helps
display missing device info
* [rocm-smi] Added better context when rsmi_ret_ok
does not return with RSMI_STATUS_SUCCESS
* [rocm-smi] Removed all references to an
undefined function (printLogNoDev())
* [rocm-smi] Fixed not detecting non-int
values when setting the voltage curve
* [rocm-smi] Added better context on missing
sysfs file when setting clock overdrive
values
* [rocm-smi] Fixed getMemInfo() calls not
referencing tuple values (making it easier
to read)
* [rocm-smi] Silenced concise info spitting
out errors for missing VRAM files, instead
display which metric is "unsupported" if
the files are missing
* [rocm-smi] Updated function descriptions for
rsmi_ret_ok & getMemInfo
* [rocm-smi] Updated getMemInfo to provide a
quiet call, to silence for concise info calls.
This provides a way to keep the output clean.
* [rocm-smi-lib] Added when using debug sysfs
files, to state, which enums are enabled
for debug
Change-Id: I0e9e0c97ccf71467ced0e1a1f71803327a8be2b7
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
[ROCm/rocm_smi_lib commit: 6be92b9e26]
Updates:
* VoltRead - needed to properly send out RSMI_STATUS_NOT_SUPPORTED
when device does not have voltage hwmon files
* ComputePart. - test failure was likely caused due to EvtNotif
causing conflicts (unknown exactly why). Test passes when
moving it ahead of the event notifier. Both API calls may have
a system resource issue, TBD.
* rocm_smi_example - now indicates when an API call
returns RSMI_STATUS_NOT_SUPPORTED or
RSMI_STATUS_NOT_YET_IMPLEMENTED. Allows example to fully complete
on systems which may not provide support for all API calls.
Change-Id: I520b8584e078d412414e8e5797c664220a7e823a
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
[ROCm/rocm_smi_lib commit: 78a0812f7f]
The rsmi_dev_subsystem_name_get() only matches subvendor id and
subdevice id for a vendor. The change will also match device id.
Change-Id: Ife3aedaf6fc7390ed7fa62edbde40c2340689b23
[ROCm/rocm_smi_lib commit: 0c82a9d577]
Fix was needed due to hwmon updates.
Several voltage sensors (ex. vddgfx/vddnb)
are unsupported or not applicable
to upcoming hardware. This was not the case
for previous hardware sensors, resulting in
the rocm-smi crash observed.
Change-Id: Ib8593e10811638def26fc7a1eda29309e328db09
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
[ROCm/rocm_smi_lib commit: f44d1ea8bc]
The process ids of other container are still visible in the sysfs file,
filter it out to prevent crash.
Change-Id: I665912cd09c606804186aff8cba5c24f5e58ded7
[ROCm/rocm_smi_lib commit: 710649ab66]
Updates:
* Fixed rsmi_dev_compute_partition_get
& rsmi_dev_nps_mode_get to properly check
for invalid arguments
* Updated compute partition & NPS mode tests
- Now properly confirms the invalid
argument is seen
- Spacing for multiple devices is added
to better see distinction between
separate device's tests (for verbose output)
- Changed expect to assert calls, so errors
are observed faster for test failures
- Fixed multiple device testing where a
variable should have been unset, but
having multiple devices caused it to
set
- Updated multiple device testing to iterate
accross all devices (previously returned,
instead of continuing checking support
after RSMI_STATUS_NOT_SUPPORTED detected)
- Fixed a few spelling errors & verbose output
Change-Id: Ieba9e5b46763c6cd880fbf27fcdf58be8ecbc683
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
[ROCm/rocm_smi_lib commit: c252ecccd1]
Updates:
* Added RSMI_STATUS_SETTING_UNAVAILABLE for
rsmi_dev_compute_partition_set - gives users
better error output when attempting to set
compute partition to values not listed in
available_compute_partition SYSFS
* Updated python --setcomputepartition to
provide better output when receiving
RSMI_STATUS_SETTING_UNAVAILABLE
* Updated all test & example files to check for
RSMI_STATUS_SETTING_UNAVAILABLE when doing
rsmi_dev_compute_partition_set
Change-Id: Ida5d54880d9b9b6e4a0468cdb962fdc0c18d6257
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
[ROCm/rocm_smi_lib commit: 0d3558945b]
Updates:
* Added rsmi_dev_compute_partition_reset & rsmi_dev_nps_mode_reset
* Added --resetcomputepartition and --resetnpsmode python smi calls
* Added temp data files rocmsmi_boot_compute_partition_<device num>
& rocmsmi_boot_nps_mode_partition_<device num>, writes UNKNOWN
if data cannot be read or device does not support
* Cleaned up NPS & compute API documentation
* Added creation and reading of API temp files (used in reset
functionality)
* Cleaned up output of rocm_smi_example
* Updated rocm_smi_example to check if running with sudo permission
before executing write API calls (cleans up erroneous output)
* Added template specialization for storing temp data, requires
specific rsmi_type_t enums (restrics what data can be stored)
* Added storage of temp data, if temp files do not exist
* Updated google tests for NPS & compute to include reset API calls
Change-Id: I69895a466b97107617e6dbb355737b84499a76c9
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
[ROCm/rocm_smi_lib commit: 77c950a4bf]
Updates:
* Added rsmi_dev_nps_mode_set and rsmi_dev_nps_mode_get
* Added ability to set multiple SYSFS files in debug build
* Added ability to see user's env variables set for debug build
* Added tests for rsmi_dev_nps_mode_set and rsmi_dev_nps_mode_get
* Added ability to restart AMD GPU driver, used in nps_mode_set
* Updated ROCm_SMI_Manual.pdf to include new APIs
* Added progress bar for long running python_smi_tools, used
in setting nps_mode if runs longer than .1 seconds
Change-Id: I6d61bedd28d7cba6aff432ad2d127ba741b7d15a
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
[ROCm/rocm_smi_lib commit: 9ef376cd61]
Fallback to other methods if the device name in sysfs is not printable.
Change-Id: I20b22950399d4a515d2688b955248a3de3c61d05
[ROCm/rocm_smi_lib commit: 00a6c78a51]
On APU's vbios_version string might not be exposed. Relying on vendor ID
to detect AMDGPU is sufficient
Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Change-Id: I08ef4b4bc7491a40f318791803aeaf261f7fac25
[ROCm/rocm_smi_lib commit: 142dcfa8f4]
Original updates:
* Added .gitignore to help with future commits
* Updated/added copyrights on modified or added files
* Updated rocm_smi.h/.cc
- Added 3 new SMI API functions:
rsmi_dev_compute_partition_set &
rsmi_dev_compute_partition_get
- Added helpful maps/enums used in
new get/set compute_partition API calls
* Updated rocm_smi.py
- Added --showcomputepartition
- Added --setcomputepartition
- Fixed a few mistypes
* Updated rsmiBindings.py - added helpful class/dict/list
* Updated rocm_smi_example.cc
- Added helpful MACRO to detect if api is not supported.
- Added current_compute_partition set/get rocm lib calls
- Added helpful macro to discover future RSMI errors
- Commented out test_set_freq, was having permission issues
on a Navi21
* Updated rocm_smi_main.cc
- Added helpful map to debug API calls, left in for future use
- Added comment to better understand a non-class function returns
* Added computepartition_read_write.cc/.h
- Added get/set compute partition API test calls
- Confirmed on devices that do not support the API calls, tests pass
* Updated rocm_smi_test/main.cc
- Calls new compute partition gtests
Added following updates from review feedback:
* Updated rocm_smi.h/cc
- Removed C++ API calls, adding support for both C/C++
API calls could cause confusion and adds extra work for us
- rsmi_dev_compute_partition_get -> Fixed an edge case where
user gives a small buffer length size (smaller than data
received), but does not receive the partial buffer back.
google Tests are updated to reflect this find.
* Updated rocm_smi_example.cc
- Fixed test_set_freq, issue was that file was not writable.
We now indicate this warning, so prior errors make sense.
- General test code cleanup. Removed extra code,
by creating loops for tests.
* Updated rocm_smi_main.cc
- Moved and got rid of an external reference to a map used
for debugging RSMI enums, now is a const public reference.
* Updated rocm_smi.py
- Updated python code to identify NOT_SUPPORTED due to
(currently) only a few GPU support the feature
Change-Id: I4a567acbb59d6771fb64df08d19175fe3604fd1b
[ROCm/rocm_smi_lib commit: 4d7f3f2bc7]
If the code is crashed and the mutex may be in bad status. The user
has to mannually remove it. The fix will remove the shared mutex
if no process is using it.
Change-Id: I18bf562f2e0a7de8b3f0cccf72d60950b0d9bb2d
[ROCm/rocm_smi_lib commit: 76b5528feb]
Return value from ReadSysfsStr function that reads cu_occupancy file
was not handled correctly. Modified the script to handle any fail conditions.
Change-Id: I3c71e0f6f288f196ed1f833e8709255c2b6e78ee
[ROCm/rocm_smi_lib commit: e9e3ba541e]
Devices with CPU XGMI iolink do not support PCIe peer access. Therefore,
they should not be reported as accessible links in the topology.
Signed-off-by: Alex Sierra <Alex.Sierra@amd.com>
Change-Id: I3ee51796945dc0966200dee03886510e8f1846b7
[ROCm/rocm_smi_lib commit: 4658630d8d]
1. Memory allocated for handle was not deleted
when no variant, subvariant or supported function
was found
2. handle->func_id_iter address was set to 0
before delete[]
Signed-off-by: Divya Shikre <DivyaUday.Shikre@amd.com>
Change-Id: Iab50fdfbe03eec8e6fd0e84e03bd2c47e645b3d8
[ROCm/rocm_smi_lib commit: b23cfc0e82]
Show an optional debug log (RSMI_DEBUG_BITFIELD=2) to
the user in the following scenarios:
1. If more than one current frequency is found
2. If frequencies are not read in increasing order of
their value
If current frequency is not available, index for it is
set to -1, values will not have * next to it in the
output. This will also be handled in rocm_smi.py.
Signed-off-by: Divya Shikre <DivyaUday.Shikre@amd.com>
Change-Id: I477ec065f7513c8045d6392f12ef6cb835a6b8f6
[ROCm/rocm_smi_lib commit: afe996c2ed]
Add DEBUG_LOG that will optionally print error
message when RSMI_DEBUG_BITFIELD is set to 2.
Signed-off-by: Divya Shikre <DivyaUday.Shikre@amd.com>
Change-Id: I6017e92d8a9e5f9861ae29ece0488d4bc198f996
[ROCm/rocm_smi_lib commit: 99be3451d7]
showclocks/showclkfrq does not display pp_dpm_pcie values
in sriov. This fix adds pcie clocks to rsmi_clk_type_t
where rest of the clocks are present.
Signed-off-by: Divya Shikre <DivyaUday.Shikre@amd.com>
Change-Id: I6d129ae412623b369c14456ae9781b2dbceb2139
[ROCm/rocm_smi_lib commit: c9b42bff57]
This patch adds the following 4 missing GPU blocks to the SMI LIB:
-RSMI_GPU_BLOCK_MMHUB
-RSMI_GPU_BLOCK_PCIE_BIF
-RSMI_GPU_BLOCK_HDP
-RSMI_GPU_BLOCK_XGMI_WAFL
Signed-off-by: Ori Messinger <Ori.Messinger@amd.com>
Change-Id: Ia1ec6f53e195f4bf7b8f073d6bed4fdb6572e546
[ROCm/rocm_smi_lib commit: 9d6403bb17]
Galantsev, Dmitrii
Charis Poag
Ori Messinger
Bill(Shuzhou) Liu
Oliveira, Daniel
Tom Rix
Harish Kasiviswanathan
Sreekant Somasekharan
Alex Sierra
Divya Shikre