Merge amd-dev into amd-master 20240813

Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: Ic744285e2203fad663a2f4a9f722c2bad1e623c8

amdsmi_cli/README.md

@@ -1,5 +1,7 @@
 # AMD SMI CLI Tool
 
+**Disclaimer: CLI Tool is provided as an example code to aid the development of telemetry tools. Python or C++ Library is recommended as a reliable data source.**  
+
 This tool acts as a command line interface for manipulating
 and monitoring the amdgpu kernel, and is intended to replace
 and deprecate the existing rocm_smi CLI tool & gpuv-smi tool.

amdsmi_cli/amdsmi_commands.py

@@ -293,6 +293,8 @@ class AMDSMICommands():
             args.board = board
         if driver:
             args.driver = driver
+        if ras:
+            args.ras = ras
         if vram:
             args.vram = vram
         if cache:
@@ -301,14 +303,12 @@ class AMDSMICommands():
             args.process_isolation = process_isolation
 
         # Store args that are applicable to the current platform
-        current_platform_args = ["asic", "bus", "vbios", "driver", "vram", "cache",
-                                 "board", "process_isolation"]
-        current_platform_values = [args.asic, args.bus, args.vbios, args.driver, args.vram, args.cache,
-                                   args.board, args.process_isolation]
+        current_platform_args = ["asic", "bus", "vbios", "driver", "ras",
+                                 "vram", "cache", "board", "process_isolation"]
+        current_platform_values = [args.asic, args.bus, args.vbios, args.driver, args.ras,
+                                   args.vram, args.cache, args.board, args.process_isolation]
 
         if self.helpers.is_linux() and self.helpers.is_baremetal():
-            if ras:
-                args.ras = ras
             if partition:
                 args.partition = partition
             if limit:
@@ -1191,14 +1191,19 @@ class AMDSMICommands():
                 args.clock = clock
             if temperature:
                 args.temperature = temperature
+            if pcie:
+                args.pcie = pcie
+            current_platform_args += ["usage", "power", "clock", "temperature", "pcie"]
+            current_platform_values += [args.usage, args.power, args.clock, args.temperature, args.pcie]
+
+        # Only args that are applicable to Hypervisors and BM Linux
+        if self.helpers.is_hypervisor() and (self.helpers.is_baremetal() and self.helpers.is_linux()):
             if ecc:
                 args.ecc = ecc
             if ecc_blocks:
                 args.ecc_blocks = ecc_blocks
-            if pcie:
-                args.pcie = pcie
-            current_platform_args += ["usage", "power", "clock", "temperature", "ecc", "ecc_blocks", "pcie"]
-            current_platform_values += [args.usage, args.power, args.clock, args.temperature, args.ecc, args.ecc_blocks, args.pcie]
+            current_platform_args += ["ecc", "ecc_blocks"]
+            current_platform_values += [args.ecc, args.ecc_blocks]
 
         if self.helpers.is_baremetal() and self.helpers.is_linux():
             if fan:

amdsmi_cli/amdsmi_helpers.py

@@ -807,12 +807,11 @@ class AMDSMIHelpers():
         pci_devices_path = "/sys/bus/pci/devices"
         pci_devices: set[str] = set()
         for device in os.listdir(pci_devices_path):
-            subsystem_device_path = os.path.join(pci_devices_path, device, "subsystem_device")
+            device_path = os.path.join(pci_devices_path, device, "device")
             try:
-                with open(subsystem_device_path, 'r') as f:
-                    subsystem_device = f.read().strip()
-                    pci_devices.add(subsystem_device)
+                with open(device_path, 'r') as f:
+                    device = f.read().strip()
+                    pci_devices.add(device)
             except Exception as _:
                 continue
         return pci_devices
-

amdsmi_cli/amdsmi_parser.py

@@ -620,10 +620,10 @@ class AMDSMIParser(argparse.ArgumentParser):
             static_parser.add_argument('-c', '--cache', action='store_true', required=False, help=cache_help)
             static_parser.add_argument('-B', '--board', action='store_true', required=False, help=board_help)
             static_parser.add_argument('-R', '--process-isolation', action='store_true', required=False, help=process_isolation_help)
+            static_parser.add_argument('-r', '--ras', action='store_true', required=False, help=ras_help)
 
             # Options to display on Hypervisors and Baremetal
             if self.helpers.is_hypervisor() or self.helpers.is_baremetal():
-                static_parser.add_argument('-r', '--ras', action='store_true', required=False, help=ras_help)
                 static_parser.add_argument('-p', '--partition', action='store_true', required=False, help=partition_help)
                 static_parser.add_argument('-l', '--limit', action='store_true', required=False, help=limit_help)
                 static_parser.add_argument('-P', '--soc-pstate', action='store_true', required=False, help=soc_pstate_help)
@@ -804,6 +804,9 @@ class AMDSMIParser(argparse.ArgumentParser):
                 metric_parser.add_argument('-c', '--clock', action='store_true', required=False, help=clock_help)
                 metric_parser.add_argument('-t', '--temperature', action='store_true', required=False, help=temperature_help)
                 metric_parser.add_argument('-P', '--pcie', action='store_true', required=False, help=pcie_help)
+
+            # Options that only apply to Hypervisors and Baremetal Linux
+            if self.helpers.is_hypervisor() or (self.helpers.is_baremetal() and self.helpers.is_linux()):
                 metric_parser.add_argument('-e', '--ecc', action='store_true', required=False, help=ecc_help)
                 metric_parser.add_argument('-k', '--ecc-blocks', action='store_true', required=False, help=ecc_blocks_help)
 

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

@@ -1,5 +1,7 @@
 # Using AMD SMI Command Line Interface tool
 
+**Disclaimer: CLI Tool is provided as an example code to aid the development of telemetry tools. Python or C++ Library is recommended as a reliable data source.**  
+
 AMD-SMI reports the version and current platform detected when running the command line interface (CLI) without arguments:
 
 ``` bash