kata-deploy: Add qemu-nvidia-gpu-runtime-rs shim

Register the Rust NVIDIA GPU runtime as a kata-deploy shim so it gets
installed and configured alongside the existing Go-based
qemu-nvidia-gpu shim.

Add qemu-nvidia-gpu-runtime-rs to the RUST_SHIMS list and the default
enabled shims, create its RuntimeClass entry in the Helm chart, and
include it in the try-kata-nvidia-gpu values overlay. The kata-deploy
installer will now copy the runtime-rs configuration and create the
containerd runtime entry for it.

Signed-off-by: Fabiano Fidêncio <ffidencio@nvidia.com>
Signed-off-by: Alex Lyn <alex.lyn@antgroup.com>

tools/packaging/kata-deploy/binary/src/artifacts/install.rs

@@ -30,6 +30,7 @@ const ALL_SHIMS: &[&str] = &[
     "qemu-coco-dev",
     "qemu-coco-dev-runtime-rs",
     "qemu-nvidia-gpu",
+    "qemu-nvidia-gpu-runtime-rs",
     "qemu-nvidia-gpu-snp",
     "qemu-nvidia-gpu-tdx",
     "qemu-runtime-rs",
@@ -1055,6 +1056,7 @@ mod tests {
     #[case("qemu-coco-dev", "qemu")]
     #[case("qemu-cca", "qemu")]
     #[case("qemu-nvidia-gpu", "qemu")]
+    #[case("qemu-nvidia-gpu-runtime-rs", "qemu")]
     #[case("qemu-nvidia-gpu-tdx", "qemu")]
     #[case("qemu-nvidia-gpu-snp", "qemu")]
     #[case("qemu-runtime-rs", "qemu")]

tools/packaging/kata-deploy/binary/src/config.rs

@@ -718,8 +718,8 @@ fn parse_custom_runtimes() -> Result<Vec<CustomRuntime>> {
 /// Returns only shims that are supported for that architecture
 fn get_default_shims_for_arch(arch: &str) -> &'static str {
     match arch {
-        "x86_64" => "clh cloud-hypervisor dragonball fc qemu qemu-coco-dev qemu-coco-dev-runtime-rs qemu-runtime-rs qemu-nvidia-gpu qemu-nvidia-gpu-snp qemu-nvidia-gpu-tdx qemu-snp qemu-snp-runtime-rs qemu-tdx qemu-tdx-runtime-rs",
-        "aarch64" => "clh cloud-hypervisor dragonball fc qemu qemu-runtime-rs qemu-nvidia-gpu qemu-cca",
+        "x86_64" => "clh cloud-hypervisor dragonball fc qemu qemu-coco-dev qemu-coco-dev-runtime-rs qemu-runtime-rs qemu-nvidia-gpu qemu-nvidia-gpu-runtime-rs qemu-nvidia-gpu-snp qemu-nvidia-gpu-tdx qemu-snp qemu-snp-runtime-rs qemu-tdx qemu-tdx-runtime-rs",
+        "aarch64" => "clh cloud-hypervisor dragonball fc qemu qemu-runtime-rs qemu-nvidia-gpu qemu-nvidia-gpu-runtime-rs qemu-cca",
         "s390x" => "qemu qemu-runtime-rs qemu-se qemu-se-runtime-rs qemu-coco-dev qemu-coco-dev-runtime-rs",
         "ppc64le" => "qemu",
         _ => "qemu", // Fallback to qemu for unknown architectures

tools/packaging/kata-deploy/binary/src/utils/system.rs

@@ -10,6 +10,7 @@ pub const RUST_SHIMS: &[&str] = &[
     "cloud-hypervisor",
     "dragonball",
     "qemu-runtime-rs",
+    "qemu-nvidia-gpu-runtime-rs",
     "qemu-coco-dev-runtime-rs",
     "qemu-se-runtime-rs",
     "qemu-snp-runtime-rs",

tools/packaging/kata-deploy/helm-chart/kata-deploy/templates/runtimeclasses.yaml

@@ -109,6 +109,7 @@ scheduling:
   "qemu-tdx" (dict "memory" "2048Mi" "cpu" "1.0")
   "qemu-tdx-runtime-rs" (dict "memory" "2048Mi" "cpu" "1.0")
   "qemu-nvidia-gpu" (dict "memory" "10240Mi" "cpu" "1.0")
+  "qemu-nvidia-gpu-runtime-rs" (dict "memory" "10240Mi" "cpu" "1.0")
   "qemu-nvidia-gpu-snp" (dict "memory" "10240Mi" "cpu" "1.0")
   "qemu-nvidia-gpu-tdx" (dict "memory" "10240Mi" "cpu" "1.0")
   "qemu-cca" (dict "memory" "2048Mi" "cpu" "1.0")

tools/packaging/kata-deploy/helm-chart/kata-deploy/try-kata-nvidia-gpu.values.yaml

@@ -1,5 +1,5 @@
 # Example values file to enable NVIDIA GPU shims
-# This includes all NVIDIA GPU-enabled shims: qemu-nvidia-gpu, qemu-nvidia-gpu-snp, qemu-nvidia-gpu-tdx
+# This includes all NVIDIA GPU-enabled shims: qemu-nvidia-gpu, qemu-nvidia-gpu-runtime-rs, qemu-nvidia-gpu-snp, qemu-nvidia-gpu-tdx
 #
 # Usage:
 #   helm install kata-deploy oci://ghcr.io/kata-containers/kata-deploy-charts/kata-deploy \
@@ -31,6 +31,20 @@ shims:
       nodeSelector:
         nvidia.com/cc.ready.state: "false"
 
+  qemu-nvidia-gpu-runtime-rs:
+    enabled: true
+    supportedArches:
+      - amd64
+      - arm64
+    allowedHypervisorAnnotations: []
+    containerd:
+      snapshotter: ""
+    runtimeClass:
+      # This label is automatically added by gpu-operator. Override it
+      # if you want to use a different label.
+      nodeSelector:
+        nvidia.com/cc.ready.state: "false"
+
   qemu-nvidia-gpu-snp:
     enabled: true
     supportedArches:

tools/packaging/kata-deploy/helm-chart/kata-deploy/values.yaml

@@ -147,6 +147,20 @@ shims:
       nodeSelector:
         nvidia.com/cc.ready.state: "false"
 
+  qemu-nvidia-gpu-runtime-rs:
+    enabled: ~
+    supportedArches:
+      - amd64
+      - arm64
+    allowedHypervisorAnnotations: []
+    containerd:
+      snapshotter: ""
+    runtimeClass:
+      # This label is automatically added by gpu-operator. Override it
+      # if you want to use a different label.
+      nodeSelector:
+        nvidia.com/cc.ready.state: "false"
+
   qemu-nvidia-gpu-snp:
     enabled: ~
     supportedArches: