From 6ea0c8b524a98ff5d94217e1dd404773b037dede Mon Sep 17 00:00:00 2001
From: Ori Messinger <Ori.Messinger@amd.com>
Date: Wed, 23 Sep 2020 16:33:01 -0400
Subject: [PATCH] ROCm SMI Python CLI: Check for amdgpu Driver Initialization

The purpose of this patch is to check for amdgpu driver initialization
before attempting to initialize rocmsmi in the CLI.

Additionally, since the '--help' functionality does not rely on anything
external to the CLI, it can now be called without the driver initialized.

Change-Id: I2fcce60ca6d9f77835549e3558c4bb1747499c5c
Signed-off-by: Ori Messinger <Ori.Messinger@amd.com>


[ROCm/amdsmi commit: e3c9aec71443e608369dc00b808b53fe61b8715c]
---
 projects/amdsmi/python_smi_tools/rocm_smi.py | 34 +++++++++++++++++---
 1 file changed, 29 insertions(+), 5 deletions(-)

diff --git a/projects/amdsmi/python_smi_tools/rocm_smi.py b/projects/amdsmi/python_smi_tools/rocm_smi.py
index 555f92f1c6..ed79d966e7 100755
--- a/projects/amdsmi/python_smi_tools/rocm_smi.py
+++ b/projects/amdsmi/python_smi_tools/rocm_smi.py
@@ -57,11 +57,18 @@ validClockNames = clk_type_names[1:-2]
 validClockNames.append('pcie')
 validClockNames.sort()
 
-# Check for correct initialization value
-ret_init = rocmsmi.rsmi_init(0)
-if ret_init != 0:
-    logging.error('ROCm SMI returned %s (the expected value is 0)', ret_init)
-    exit(ret_init)
+def driverInitialized():
+    """ Returns true if amdgpu is found in the list of initialized modules
+    """
+    driverInitialized = ''
+    try:
+        driverInitialized = str(subprocess.check_output("cat /proc/modules|grep amdgpu", shell=True))
+    except subprocess.CalledProcessError:
+        pass
+    if len(driverInitialized) > 0:
+        return True
+    return False
+
 
 def formatJson(device, log):
     """ Print out in JSON format
@@ -2132,6 +2139,20 @@ def doesDeviceExist(device):
     return False
 
 
+def initializeRsmi():
+    """ initializes rocmsmi if the amdgpu driver is initialized
+    """
+    # Check if amdgpu is initialized before initializing rsmi
+    if driverInitialized() is True:
+        ret_init = rocmsmi.rsmi_init(0)
+        if ret_init != 0:
+            logging.error('ROCm SMI returned %s (the expected value is 0)', ret_init)
+            exit(ret_init)
+    else:
+        logging.error('Driver not initialized (amdgpu not found in modules)')
+        exit(0)
+
+
 def isAmdDevice(device):
     """ Return whether the specified device is an AMD device or not
 
@@ -2444,6 +2465,9 @@ if __name__ == '__main__':
 
     args = parser.parse_args()
 
+    # Initialize the rocm SMI library
+    initializeRsmi()
+
     logging.basicConfig(format='%(levelname)s: %(message)s', level=logging.WARNING)
     if args.loglevel is not None:
         numericLogLevel = getattr(logging, args.loglevel.upper(), logging.WARNING)