Merge amd-master into release/rocm-rel-6.2 20240710

Signed-off-by: Maisam Arif <[email protected]>
Change-Id: I67885b9df87d2300c53c576f7b36369154b835a7

CHANGELOG.md

@@ -8,6 +8,8 @@ Full documentation for amd_smi_lib is available at [https://rocm.docs.amd.com/pr
 
 ### Additions
 
+- **`amd-smi dmon` is now available as an alias to `amd-smi monitor`**.  
+
 - **Added optional process table under `amd-smi monitor -q`**.  
 The monitor subcommand within the CLI Tool now has the `-q` option to enable an optional process table underneath the original monitored output.
 
@@ -40,6 +42,48 @@ Added `AMDSMI_EVT_NOTIF_RING_HANG` to the possible events in the `amdsmi_evt_not
 
 ### Optimizations
 
+- **Updated CLI error strings to specify invalid device type queried**  
+
+```shell
+$ amd-smi static --asic --gpu 123123
+Can not find a device: GPU '123123' Error code: -3
+```
+
+- **Removed elevated permission requirements for `amdsmi_get_gpu_process_list()`**.  
+Previously if a processes with elevated permissions was running amd-smi would required sudo to display all output. Now amd-smi will populate all process data and return N/A for elevated process names instead. However if ran with sudo you will be able to see the name like so:
+
+```shell
+$ amd-smi process
+GPU: 0
+    PROCESS_INFO:
+        NAME: N/A
+        PID: 1693982
+        MEMORY_USAGE:
+            GTT_MEM: 0.0 B
+            CPU_MEM: 0.0 B
+            VRAM_MEM: 10.1 GB
+        MEM_USAGE: 0.0 B
+        USAGE:
+            GFX: 0 ns
+            ENC: 0 ns
+```
+
+```shell
+$ sudo amd-smi process
+GPU: 0
+    PROCESS_INFO:
+        NAME: TransferBench
+        PID: 1693982
+        MEMORY_USAGE:
+            GTT_MEM: 0.0 B
+            CPU_MEM: 0.0 B
+            VRAM_MEM: 10.1 GB
+        MEM_USAGE: 0.0 B
+        USAGE:
+            GFX: 0 ns
+            ENC: 0 ns
+```
+
 - **Updated naming for `amdsmi_set_gpu_clear_sram_data()` to `amdsmi_clean_gpu_local_data()`**.  
 Changed the naming to be more accurate to what the function was doing. This change also extends to the CLI where we changed the `clear-sram-data` command to `clean_local_data`.
 

CMakeLists.txt

@@ -28,7 +28,7 @@ find_program(GIT NAMES git)
 
 ## Setup the package version based on git tags.
 set(PKG_VERSION_GIT_TAG_PREFIX "amdsmi_pkg_ver")
-get_package_version_number("24.6.1" ${PKG_VERSION_GIT_TAG_PREFIX} GIT)
+get_package_version_number("24.6.2" ${PKG_VERSION_GIT_TAG_PREFIX} GIT)
 message("Package version: ${PKG_VERSION_STR}")
 set(${AMD_SMI_LIBS_TARGET}_VERSION_MAJOR "${CPACK_PACKAGE_VERSION_MAJOR}")
 set(${AMD_SMI_LIBS_TARGET}_VERSION_MINOR "${CPACK_PACKAGE_VERSION_MINOR}")

amdsmi_cli/README.md

@@ -73,13 +73,13 @@ Type "help", "copyright", "credits" or "license" for more information.
 
 ## Usage
 
-amd-smi will report the version and current platform detected when running the command without arguments:
+AMD-SMI reports the version and current platform detected when running the command line interface (CLI) without arguments:
 
 ``` bash
 ~$ amd-smi
 usage: amd-smi [-h]  ...
 
-AMD System Management Interface | Version: 24.6.1.0 | ROCm version: 6.2.0 | Platform: Linux Baremetal
+AMD System Management Interface | Version: 24.6.2.0 | ROCm version: 6.2.0 | Platform: Linux Baremetal
 
 options:
   -h, --help          show this help message and exit
@@ -97,7 +97,7 @@ AMD-SMI Commands:
     topology          Displays topology information of the devices
     set               Set options for devices
     reset             Reset options for devices
-    monitor           Monitor metrics for target devices
+    monitor (dmon)    Monitor metrics for target devices
     xgmi              Displays xgmi information of the devices
 ```
 
@@ -594,7 +594,7 @@ Command Modifiers:
 usage: amd-smi monitor [-h] [--json | --csv] [--file FILE] [--loglevel LEVEL]
                        [-g GPU [GPU ...] | -U CPU [CPU ...] | -O CORE [CORE ...]]
                        [-w INTERVAL] [-W TIME] [-i ITERATIONS] [-p] [-t] [-u] [-m] [-n]
-                       [-d] [-e] [-v] [-r]
+                       [-d] [-e] [-v] [-r] [-q]
 
 Monitor a target device for the specified arguments.
 If no arguments are provided, all arguments will be enabled.
@@ -629,6 +629,7 @@ Monitor Arguments:
   -e, --ecc                    Monitor ECC single bit, ECC double bit, and PCIe replay error counts
   -v, --vram-usage             Monitor memory usage in MB
   -r, --pcie                   Monitor PCIe bandwidth in Mb/s
+  -q, --process                Enable Process information table below monitor output
 
 Command Modifiers:
   --json                       Displays output in JSON format (human readable by default).

amdsmi_cli/amdsmi_cli_exceptions.py

@@ -69,6 +69,7 @@ def __init__(self):
         self.stdout_message = ''
         self.message = ''
         self.output_format = ''
+        self.device_type = ''
 
     def __str__(self):
         # Return message according to the current output format
@@ -83,7 +84,7 @@ def __str__(self):
 
 
 class AmdSmiInvalidCommandException(AmdSmiException):
-    def __init__(self, command, outputformat):
+    def __init__(self, command, outputformat: str):
         super().__init__()
         self.value = -1
         self.command = command
@@ -98,7 +99,7 @@ def __init__(self, command, outputformat):
 
 
 class AmdSmiInvalidParameterException(AmdSmiException):
-    def __init__(self, command, outputformat):
+    def __init__(self, command, outputformat: str):
         super().__init__()
         self.value = -2
         self.command = command
@@ -113,13 +114,22 @@ def __init__(self, command, outputformat):
 
 
 class AmdSmiDeviceNotFoundException(AmdSmiException):
-    def __init__(self, command, outputformat):
+    def __init__(self, command, outputformat: str, gpu: bool, cpu: bool, core: bool):
         super().__init__()
         self.value = -3
         self.command = command
         self.output_format = outputformat
 
-        common_message = f"Can not find a device with the corresponding identifier: '{self.command}'"
+        # Handle different devices
+        self.device_type = ""
+        if gpu:
+            self.device_type = "GPU"
+        elif cpu:
+            self.device_type = "CPU"
+        elif core:
+            self.device_type = "CPU CORE"
+
+        common_message = f"Can not find a device: {self.device_type} '{self.command}'"
 
         self.json_message["error"] = common_message
         self.json_message["code"] = self.value
@@ -128,7 +138,7 @@ def __init__(self, command, outputformat):
 
 
 class AmdSmiInvalidFilePathException(AmdSmiException):
-    def __init__(self, command, outputformat):
+    def __init__(self, command, outputformat: str):
         super().__init__()
         self.value = -4
         self.command = command
@@ -143,7 +153,7 @@ def __init__(self, command, outputformat):
 
 
 class AmdSmiInvalidParameterValueException(AmdSmiException):
-    def __init__(self, command, outputformat):
+    def __init__(self, command, outputformat: str):
         super().__init__()
         self.value = -5
         self.command = command
@@ -158,7 +168,7 @@ def __init__(self, command, outputformat):
 
 
 class AmdSmiMissingParameterValueException(AmdSmiException):
-    def __init__(self, command, outputformat):
+    def __init__(self, command, outputformat: str):
         super().__init__()
         self.value = -6
         self.command = command
@@ -172,8 +182,23 @@ def __init__(self, command, outputformat):
         self.stdout_message = f"{common_message} Error code: {self.value}"
 
 
+class AmdSmiCommandNotSupportedException(AmdSmiException):
+    def __init__(self, command, outputformat: str):
+        super().__init__()
+        self.value = -7
+        self.command = command
+        self.output_format = outputformat
+
+        common_message = f"Command '{self.command}' is not supported on the system. Run '--help' for more info."
+
+        self.json_message["error"] = common_message
+        self.json_message["code"] = self.value
+        self.csv_message = f"error,code\n{common_message}, {self.value}"
+        self.stdout_message = f"{common_message} Error code: {self.value}"
+
+
 class AmdSmiParameterNotSupportedException(AmdSmiException):
-    def __init__(self, command, outputformat):
+    def __init__(self, command, outputformat: str):
         super().__init__()
         self.value = -8
         self.command = command
@@ -188,7 +213,7 @@ def __init__(self, command, outputformat):
 
 
 class AmdSmiRequiredCommandException(AmdSmiException):
-    def __init__(self, command, outputformat):
+    def __init__(self, command, outputformat: str):
         super().__init__()
         self.value = -9
         self.command = command
@@ -203,7 +228,7 @@ def __init__(self, command, outputformat):
 
 
 class AmdSmiUnknownErrorException(AmdSmiException):
-    def __init__(self, command, outputformat):
+    def __init__(self, command, outputformat: str):
         super().__init__()
         self.value = -100
         self.command = command
@@ -218,7 +243,7 @@ def __init__(self, command, outputformat):
 
 
 class AmdSmiAMDSMIErrorException(AmdSmiException):
-    def __init__(self, outputformat, error_code):
+    def __init__(self, outputformat: str, error_code):
         super().__init__()
         self.value = -1000 - abs(error_code)
         self.smilibcode = error_code

amdsmi_cli/amdsmi_commands.py

@@ -115,9 +115,15 @@ def version(self, args):
         self.logger.output['rocm_version'] = f'{rocm_version_str}'
 
         if self.logger.is_human_readable_format():
-            print(f'AMDSMI Tool: {__version__} | '\
-                    f'AMDSMI Library version: {amdsmi_lib_version_str} | ' \
-                    f'ROCm version: {rocm_version_str}')
+            human_readable_output = f"AMDSMI Tool: {__version__} | " \
+                                    f"AMDSMI Library version: {amdsmi_lib_version_str} | " \
+                                    f"ROCm version: {rocm_version_str}"
+            # Custom human readable handling for version
+            if self.logger.destination == 'stdout':
+                print(human_readable_output)
+            else:
+                with self.logger.destination.open('a') as output_file:
+                    output_file.write(human_readable_output + '\n')
         elif self.logger.is_json_format() or self.logger.is_csv_format():
             self.logger.print_output()
 
@@ -2631,8 +2637,6 @@ def process(self, args, multiple_devices=False, watching_output=False,
         try:
             process_list = amdsmi_interface.amdsmi_get_gpu_process_list(args.gpu)
         except amdsmi_exception.AmdSmiLibraryException as e:
-            if e.get_error_code() == amdsmi_interface.amdsmi_wrapper.AMDSMI_STATUS_NO_PERM:
-                raise PermissionError('Command requires elevation') from e
             logging.debug("Failed to get process list for gpu %s | %s", gpu_id, e.get_error_info())
             raise e
 

amdsmi_cli/amdsmi_logger.py

@@ -465,7 +465,7 @@ def print_output(self, multiple_device_enabled=False, watching_output=False, tab
                 self._print_tabular_output(multiple_device_enabled=multiple_device_enabled, watching_output=watching_output)
             else:
                 self._print_human_readable_output(multiple_device_enabled=multiple_device_enabled,
-                                            watching_output=watching_output)
+                                                   watching_output=watching_output)
 
 
     def _print_json_output(self, multiple_device_enabled=False, watching_output=False):

amdsmi_cli/amdsmi_parser.py

@@ -111,6 +111,11 @@ def __init__(self, version, list, static, firmware, bad_pages, metric,
             help="Descriptions:",
             metavar='')
 
+        # Store possible subcommands & aliases for later errors
+        self.possible_commands = ['version', 'list', 'static', 'firmware', 'ucode', 'bad-pages',
+                                  'metric', 'process', 'profile', 'event', 'topology', 'set',
+                                  'reset', 'monitor', 'dmon', 'xgmi']
+
         # Add all subparsers
         self._add_version_parser(self.subparsers, version)
         self._add_list_parser(self.subparsers, list)
@@ -257,7 +262,9 @@ def __call__(self, parser, args, values, option_string=None):
                     if selected_device_handles == '':
                         raise amdsmi_cli_exceptions.AmdSmiMissingParameterValueException("--gpu", _GPUSelectAction.ouputformat)
                     else:
-                        raise amdsmi_cli_exceptions.AmdSmiDeviceNotFoundException(selected_device_handles, _GPUSelectAction.ouputformat)
+                        raise amdsmi_cli_exceptions.AmdSmiDeviceNotFoundException(selected_device_handles,
+                                                                                  _GPUSelectAction.ouputformat,
+                                                                                  True, False, False)
 
         return _GPUSelectAction
 
@@ -283,7 +290,8 @@ def __call__(self, parser, args, values, option_string=None):
                         raise amdsmi_cli_exceptions.AmdSmiMissingParameterValueException("--cpu", _CPUSelectAction.ouputformat)
                     else:
                         raise amdsmi_cli_exceptions.AmdSmiDeviceNotFoundException(selected_device_handles,
-                                                                                  _CPUSelectAction.ouputformat)
+                                                                                  _CPUSelectAction.ouputformat,
+                                                                                  False, True, False)
         return _CPUSelectAction
 
 
@@ -308,7 +316,8 @@ def __call__(self, parser, args, values, option_string=None):
                         raise amdsmi_cli_exceptions.AmdSmiMissingParameterValueException("--core", _CoreSelectAction.ouputformat)
                     else:
                         raise amdsmi_cli_exceptions.AmdSmiDeviceNotFoundException(selected_device_handles,
-                                                                                  _CoreSelectAction.ouputformat)
+                                                                                  _CoreSelectAction.ouputformat,
+                                                                                  False, False, True)
         return _CoreSelectAction
 
 
@@ -1129,7 +1138,7 @@ def _add_monitor_parser(self, subparsers, func):
         process_help = "Enable Process information table below monitor output"
 
         # Create monitor subparser
-        monitor_parser = subparsers.add_parser('monitor', help=monitor_help, description=monitor_subcommand_help)
+        monitor_parser = subparsers.add_parser('monitor', help=monitor_help, description=monitor_subcommand_help, aliases=["dmon"])
         monitor_parser._optionals.title = monitor_optionals_title
         monitor_parser.formatter_class=lambda prog: AMDSMISubparserHelpFormatter(prog)
         monitor_parser.set_defaults(func=func)
@@ -1232,6 +1241,9 @@ def error(self, message):
             l = len("argument : invalid choice: ") + 1
             message = message[l:]
             message = message.split("'")[0]
+            # Check if the command is possible in other system configurations and error accordingly
+            if message in self.possible_commands:
+                raise amdsmi_cli_exceptions.AmdSmiCommandNotSupportedException(message, outputformat)
             raise amdsmi_cli_exceptions.AmdSmiInvalidCommandException(message, outputformat)
         elif "unrecognized arguments: " in message:
             l = len("unrecognized arguments: ")

docs/doxygen/Doxyfile

@@ -48,7 +48,7 @@ PROJECT_NAME           = AMD SMI
 # could be handy for archiving the generated documentation or if some version
 # control system is used.
 
-PROJECT_NUMBER         = "24.6.1.0"
+PROJECT_NUMBER         = "24.6.2.0"
 
 # Using the PROJECT_BRIEF tag one can provide an optional one line description
 # for a project that appears at the top of each page and should give viewer a

docs/how-to/using-AMD-SMI-CLI-tool.md

@@ -6,7 +6,7 @@ AMD-SMI reports the version and current platform detected when running the comma
 ~$ amd-smi
 usage: amd-smi [-h]  ...
 
-AMD System Management Interface | Version: 24.6.1.0 | ROCm version: 6.2.0 | Platform: Linux Baremetal
+AMD System Management Interface | Version: 24.6.2.0 | ROCm version: 6.2.0 | Platform: Linux Baremetal
 
 options:
   -h, --help          show this help message and exit
@@ -521,7 +521,7 @@ Command Modifiers:
 usage: amd-smi monitor [-h] [--json | --csv] [--file FILE] [--loglevel LEVEL]
                        [-g GPU [GPU ...] | -U CPU [CPU ...] | -O CORE [CORE ...]]
                        [-w INTERVAL] [-W TIME] [-i ITERATIONS] [-p] [-t] [-u] [-m] [-n]
-                       [-d] [-e] [-v] [-r]
+                       [-d] [-e] [-v] [-r] [-q]
 
 Monitor a target device for the specified arguments.
 If no arguments are provided, all arguments will be enabled.
@@ -556,6 +556,7 @@ Monitor Arguments:
   -e, --ecc                    Monitor ECC single bit, ECC double bit, and PCIe replay error counts
   -v, --vram-usage             Monitor memory usage in MB
   -r, --pcie                   Monitor PCIe bandwidth in Mb/s
+  -q, --process                Enable Process information table below monitor output
 
 Command Modifiers:
   --json                       Displays output in JSON format (human readable by default).