Doc updates + commits from merge conflict resolution

api/v1alpha1/deviceconfig_types.go

@@ -94,7 +94,9 @@ type DriverSpec struct {
 	// +kubebuilder:default=true
 	Enable *bool `json:"enable,omitempty"`
 
-	// blacklist amdgpu drivers on the host
+	// blacklist amdgpu drivers on the host. Node reboot is required to apply the baclklist on the worker nodes.
+	// Not working for OpenShift cluster. OpenShift users please use the Machine Config Operator (MCO) resource to configure amdgpu blacklist.
+	// Example MCO resource is available at https://instinct.docs.amd.com/projects/gpu-operator/en/latest/installation/openshift-olm.html#create-blacklist-for-installing-out-of-tree-kernel-module
 	//+operator-sdk:csv:customresourcedefinitions:type=spec,displayName="BlacklistDrivers",xDescriptors={"urn:alm:descriptor:com.amd.deviceconfigs:blacklistDrivers"}
 	Blacklist *bool `json:"blacklist,omitempty"`
 
@@ -117,7 +119,7 @@ type DriverSpec struct {
 	// example tag is coreos-416.94-5.14.0-427.28.1.el9_4.x86_64-6.2.2 and ubuntu-22.04-5.15.0-94-generic-6.1.3
 	//+operator-sdk:csv:customresourcedefinitions:type=spec,displayName="Image",xDescriptors={"urn:alm:descriptor:com.amd.deviceconfigs:image"}
 	// +optional
-	// +kubebuilder:validation:Pattern=`^([a-z0-9]+(?:[._-][a-z0-9]+)*(:[0-9]+)?)(/[a-z0-9]+(?:[._-][a-z0-9]+)*)*(?::[a-z0-9._-]+)?(?:@[a-zA-Z0-9]+:[a-f0-9]+)?$`
+	// +kubebuilder:validation:Pattern=`^([a-z0-9]+(?:[._-][a-z0-9]+)*(:[0-9]+)?)(/[$a-zA-Z0-9_]+(?:[._-][$a-zA-Z0-9_]+)*)*(?::[a-z0-9._-]+)?(?:@[a-zA-Z0-9]+:[a-f0-9]+)?$`
 	Image string `json:"image,omitempty"`
 
 	// driver image registry TLS setting for the container image
@@ -251,12 +253,11 @@ type DevicePluginSpec struct {
 	// +optional
 	DevicePluginTolerations []v1.Toleration `json:"devicePluginTolerations,omitempty"`
 
-	// resource naming strategy for device plugin
-	//+operator-sdk:csv:customresourcedefinitions:type=spec,displayName="ResourceNamingStrategy",xDescriptors={"urn:alm:descriptor:com.amd.deviceconfigs:ResourceNamingStrategy"}
-	// +kubebuilder:validation:Enum=single;mixed
-	// +kubebuilder:default:="single"
+	// device plugin arguments is used to pass supported flags and their values while starting device plugin daemonset
+	// supported flag values: {"resource_naming_strategy": {"single", "mixed"}}
+	//+operator-sdk:csv:customresourcedefinitions:type=spec,displayName="DevicePluginArguments",xDescriptors={"urn:alm:descriptor:com.amd.deviceconfigs:devicePluginArguments"}
 	// +optional
-	ResourceNamingStrategy string `json:"resourceNamingStrategy,omitempty"`
+	DevicePluginArguments map[string]string `json:"devicePluginArguments,omitempty"`
 
 	// node labeller image
 	//+operator-sdk:csv:customresourcedefinitions:type=spec,displayName="NodeLabellerImage",xDescriptors={"urn:alm:descriptor:com.amd.deviceconfigs:nodeLabellerImage"}

bundle/manifests/amd-gpu-operator.clusterserviceversion.yaml

@@ -29,12 +29,30 @@ metadata:
           }
         }
       ]
-    capabilities: Basic Install
-    createdAt: "2025-03-20T06:06:57Z"
+    capabilities: Seamless Upgrades
+    categories: AI/Machine Learning,Monitoring
+    containerImage: docker.io/rocm/gpu-operator:v1.2.0
+    createdAt: "2025-04-02T23:22:18Z"
+    description: |-
+      Operator responsible for deploying AMD GPU kernel drivers, device plugin, device test runner and device metrics exporter
+      For more information, visit [documentation](https://instinct.docs.amd.com/projects/gpu-operator/en/latest/)
+    devicePluginImage: docker.io/rocm/k8s-device-plugin:rhubi-latest
+    features.operators.openshift.io/disconnected: "true"
+    features.operators.openshift.io/fips-compliant: "false"
+    features.operators.openshift.io/proxy-aware: "true"
+    features.operators.openshift.io/tls-profiles: "false"
+    features.operators.openshift.io/token-auth-aws: "false"
+    features.operators.openshift.io/token-auth-azure: "false"
+    features.operators.openshift.io/token-auth-gcp: "false"
+    metricsExporterImage: docker.io/rocm/device-metrics-exporter:v1.2.0
+    nodelabellerImage: docker.io/rocm/k8s-device-plugin:labeller-rhubi-latest
+    operatorframework.io/cluster-monitoring: "true"
     operatorframework.io/suggested-namespace: openshift-amd-gpu
+    operators.openshift.io/valid-subscription: '[]'
     operators.operatorframework.io/builder: operator-sdk-v1.32.0
     operators.operatorframework.io/project_layout: go.kubebuilder.io/v3
     repository: https://github.com/ROCm/gpu-operator
+    support: Advanced Micro Devices, Inc.
   name: amd-gpu-operator.v1.2.0
   namespace: placeholder
 spec:
@@ -152,6 +170,13 @@ spec:
         path: devicePlugin
         x-descriptors:
         - urn:alm:descriptor:com.amd.deviceconfigs:devicePlugin
+      - description: 'device plugin arguments is used to pass supported flags and
+          their values while starting device plugin daemonset supported flag values:
+          {"resource_naming_strategy": {"single", "mixed"}}'
+        displayName: DevicePluginArguments
+        path: devicePlugin.devicePluginArguments
+        x-descriptors:
+        - urn:alm:descriptor:com.amd.deviceconfigs:devicePluginArguments
       - description: device plugin image
         displayName: DevicePluginImage
         path: devicePlugin.devicePluginImage
@@ -192,11 +217,6 @@ spec:
         path: devicePlugin.nodeLabellerTolerations
         x-descriptors:
         - urn:alm:descriptor:com.amd.deviceconfigs:nodeLabellerTolerations
-      - description: resource naming strategy for device plugin
-        displayName: ResourceNamingStrategy
-        path: devicePlugin.resourceNamingStrategy
-        x-descriptors:
-        - urn:alm:descriptor:com.amd.deviceconfigs:ResourceNamingStrategy
       - description: upgrade policy for device plugin and node labeller daemons
         displayName: UpgradePolicy
         path: devicePlugin.upgradePolicy
@@ -227,7 +247,10 @@ spec:
         path: driver.amdgpuInstallerRepoURL
         x-descriptors:
         - urn:alm:descriptor:com.amd.deviceconfigs:amdgpuInstallerRepoURL
-      - description: blacklist amdgpu drivers on the host
+      - description: blacklist amdgpu drivers on the host. Node reboot is required
+          to apply the baclklist on the worker nodes. Not working for OpenShift cluster.
+          OpenShift users please use the Machine Config Operator (MCO) resource to
+          configure amdgpu blacklist. Example MCO resource is available at https://instinct.docs.amd.com/projects/gpu-operator/en/latest/installation/openshift-olm.html#create-blacklist-for-installing-out-of-tree-kernel-module
         displayName: BlacklistDrivers
         path: driver.blacklist
         x-descriptors:
@@ -606,7 +629,7 @@ spec:
         - urn:alm:descriptor:com.amd.deviceconfigs:nodeModuleStatus
       version: v1alpha1
   description: |-
-    Operator responsible for deploying AMD GPU kernel drivers and device plugin
+    Operator responsible for deploying AMD GPU kernel drivers, device plugin, device test runner and device metrics exporter
     For more information, visit [documentation](https://instinct.docs.amd.com/projects/gpu-operator/en/latest/)
   displayName: amd-gpu-operator
   icon:
@@ -1110,11 +1133,24 @@ spec:
   - supported: true
     type: AllNamespaces
   keywords:
-  - amd-gpu-operator
+  - AMD
+  - GPU
+  - AI
+  - Deep Learning
+  - Hardware
+  - Driver
+  - Monitoring
   links:
-  - name: Amd Gpu Operator
-    url: https://amd-gpu-operator.domain
-  maturity: alpha
+  - name: AMD GPU Operator
+    url: https://github.com/ROCm/gpu-operator
+  maintainers:
+  - email: [email protected]
+    name: Yan Sun
+  - email: [email protected]
+    name: Farshad Ghodsian
+  - email: [email protected]
+    name: Shrey Ajmera
+  maturity: stable
   provider:
-    name: amd-gpu-operator
+    name: Advanced Micro Devices, Inc.
   version: 1.2.0

bundle/manifests/amd.com_deviceconfigs.yaml

@@ -190,6 +190,13 @@ spec:
               devicePlugin:
                 description: device plugin
                 properties:
+                  devicePluginArguments:
+                    additionalProperties:
+                      type: string
+                    description: |-
+                      device plugin arguments is used to pass supported flags and their values while starting device plugin daemonset
+                      supported flag values: {"resource_naming_strategy": {"single", "mixed"}}
+                    type: object
                   devicePluginImage:
                     description: device plugin image
                     pattern: ^([a-z0-9]+(?:[._-][a-z0-9]+)*(:[0-9]+)?)(/[a-z0-9]+(?:[._-][a-z0-9]+)*)*(?::[a-z0-9._-]+)?(?:@[a-zA-Z0-9]+:[a-f0-9]+)?$
@@ -306,13 +313,6 @@ spec:
                           type: string
                       type: object
                     type: array
-                  resourceNamingStrategy:
-                    default: single
-                    description: resource naming strategy for device plugin
-                    enum:
-                    - single
-                    - mixed
-                    type: string
                   upgradePolicy:
                     description: upgrade policy for device plugin and node labeller
                       daemons
@@ -342,7 +342,10 @@ spec:
                       installer URL is https://repo.radeon.com/amdgpu-install by default
                     type: string
                   blacklist:
-                    description: blacklist amdgpu drivers on the host
+                    description: |-
+                      blacklist amdgpu drivers on the host. Node reboot is required to apply the baclklist on the worker nodes.
+                      Not working for OpenShift cluster. OpenShift users please use the Machine Config Operator (MCO) resource to configure amdgpu blacklist.
+                      Example MCO resource is available at https://instinct.docs.amd.com/projects/gpu-operator/en/latest/installation/openshift-olm.html#create-blacklist-for-installing-out-of-tree-kernel-module
                     type: boolean
                   enable:
                     default: true
@@ -357,7 +360,7 @@ spec:
                       for OpenShift the default value is image-registry.openshift-image-registry.svc:5000/$MOD_NAMESPACE/amdgpu_kmod
                       image tag will be in the format of <linux distro>-<release version>-<kernel version>-<driver version>
                       example tag is coreos-416.94-5.14.0-427.28.1.el9_4.x86_64-6.2.2 and ubuntu-22.04-5.15.0-94-generic-6.1.3
-                    pattern: ^([a-z0-9]+(?:[._-][a-z0-9]+)*(:[0-9]+)?)(/[a-z0-9]+(?:[._-][a-z0-9]+)*)*(?::[a-z0-9._-]+)?(?:@[a-zA-Z0-9]+:[a-f0-9]+)?$
+                    pattern: ^([a-z0-9]+(?:[._-][a-z0-9]+)*(:[0-9]+)?)(/[$a-zA-Z0-9_]+(?:[._-][$a-zA-Z0-9_]+)*)*(?::[a-z0-9._-]+)?(?:@[a-zA-Z0-9]+:[a-f0-9]+)?$
                     type: string
                   imageRegistrySecret:
                     description: secrets used for pull/push images from/to private

cmd/main.go

@@ -35,9 +35,6 @@ package main
 import (
 	"flag"
 
-	"github.com/ROCm/gpu-operator/internal/configmanager"
-	"github.com/ROCm/gpu-operator/internal/metricsexporter"
-	"github.com/ROCm/gpu-operator/internal/testrunner"
 	kmmv1beta1 "github.com/rh-ecosystem-edge/kernel-module-management/api/v1beta1"
 	"k8s.io/apimachinery/pkg/runtime"
 	utilruntime "k8s.io/apimachinery/pkg/util/runtime"
@@ -51,11 +48,15 @@ import (
 	_ "k8s.io/client-go/plugin/pkg/client/auth"
 
 	gpuev1alpha1 "github.com/ROCm/gpu-operator/api/v1alpha1"
+	utils "github.com/ROCm/gpu-operator/internal"
 	"github.com/ROCm/gpu-operator/internal/cmd"
 	"github.com/ROCm/gpu-operator/internal/config"
+	"github.com/ROCm/gpu-operator/internal/configmanager"
 	"github.com/ROCm/gpu-operator/internal/controllers"
 	"github.com/ROCm/gpu-operator/internal/kmmmodule"
+	"github.com/ROCm/gpu-operator/internal/metricsexporter"
 	"github.com/ROCm/gpu-operator/internal/nodelabeller"
+	"github.com/ROCm/gpu-operator/internal/testrunner"
 	//+kubebuilder:scaffold:imports
 )
 
@@ -107,8 +108,9 @@ func main() {
 	}
 
 	client := mgr.GetClient()
-	kmmHandler := kmmmodule.NewKMMModule(client, scheme)
-	nlHandler := nodelabeller.NewNodeLabeller(scheme)
+	isOpenShift := utils.IsOpenShift(setupLogger)
+	kmmHandler := kmmmodule.NewKMMModule(client, scheme, isOpenShift)
+	nlHandler := nodelabeller.NewNodeLabeller(scheme, isOpenShift)
 	metricsHandler := metricsexporter.NewMetricsExporter(scheme)
 	testrunnerHandler := testrunner.NewTestRunner(scheme)
 	configmanagerHandler := configmanager.NewConfigManager(scheme)

config/crd/bases/amd.com_deviceconfigs.yaml

@@ -186,6 +186,13 @@ spec:
               devicePlugin:
                 description: device plugin
                 properties:
+                  devicePluginArguments:
+                    additionalProperties:
+                      type: string
+                    description: |-
+                      device plugin arguments is used to pass supported flags and their values while starting device plugin daemonset
+                      supported flag values: {"resource_naming_strategy": {"single", "mixed"}}
+                    type: object
                   devicePluginImage:
                     description: device plugin image
                     pattern: ^([a-z0-9]+(?:[._-][a-z0-9]+)*(:[0-9]+)?)(/[a-z0-9]+(?:[._-][a-z0-9]+)*)*(?::[a-z0-9._-]+)?(?:@[a-zA-Z0-9]+:[a-f0-9]+)?$
@@ -302,13 +309,6 @@ spec:
                           type: string
                       type: object
                     type: array
-                  resourceNamingStrategy:
-                    default: single
-                    description: resource naming strategy for device plugin
-                    enum:
-                    - single
-                    - mixed
-                    type: string
                   upgradePolicy:
                     description: upgrade policy for device plugin and node labeller
                       daemons
@@ -338,7 +338,10 @@ spec:
                       installer URL is https://repo.radeon.com/amdgpu-install by default
                     type: string
                   blacklist:
-                    description: blacklist amdgpu drivers on the host
+                    description: |-
+                      blacklist amdgpu drivers on the host. Node reboot is required to apply the baclklist on the worker nodes.
+                      Not working for OpenShift cluster. OpenShift users please use the Machine Config Operator (MCO) resource to configure amdgpu blacklist.
+                      Example MCO resource is available at https://instinct.docs.amd.com/projects/gpu-operator/en/latest/installation/openshift-olm.html#create-blacklist-for-installing-out-of-tree-kernel-module
                     type: boolean
                   enable:
                     default: true
@@ -353,7 +356,7 @@ spec:
                       for OpenShift the default value is image-registry.openshift-image-registry.svc:5000/$MOD_NAMESPACE/amdgpu_kmod
                       image tag will be in the format of <linux distro>-<release version>-<kernel version>-<driver version>
                       example tag is coreos-416.94-5.14.0-427.28.1.el9_4.x86_64-6.2.2 and ubuntu-22.04-5.15.0-94-generic-6.1.3
-                    pattern: ^([a-z0-9]+(?:[._-][a-z0-9]+)*(:[0-9]+)?)(/[a-z0-9]+(?:[._-][a-z0-9]+)*)*(?::[a-z0-9._-]+)?(?:@[a-zA-Z0-9]+:[a-f0-9]+)?$
+                    pattern: ^([a-z0-9]+(?:[._-][a-z0-9]+)*(:[0-9]+)?)(/[$a-zA-Z0-9_]+(?:[._-][$a-zA-Z0-9_]+)*)*(?::[a-z0-9._-]+)?(?:@[a-zA-Z0-9]+:[a-f0-9]+)?$
                     type: string
                   imageRegistrySecret:
                     description: secrets used for pull/push images from/to private