bee/audit/internal/platform/pcie_link_check_test.go

package platform

import (
	"strings"
	"testing"
)

func TestClassifyGPUFromVendorClass(t *testing.T) {
	cases := []struct {
		name       string
		vendor     string
		class      string
		wantIsGPU  bool
		wantVendor string
	}{
		{"nvidia GPU", "0x10de", "0x030200", true, "nvidia"},
		{"amd GPU", "0x1002", "0x030000", true, "amd"},
		{"nvidia NIC (same vendor, not display class)", "0x10de", "0x020000", false, ""},
		{"intel NIC", "0x8086", "0x020000", false, ""},
		{"unrelated display-class vendor", "0x1234", "0x030000", false, ""},
	}
	for _, tc := range cases {
		t.Run(tc.name, func(t *testing.T) {
			gotIsGPU, gotVendor := classifyGPUFromVendorClass(tc.vendor, tc.class)
			if gotIsGPU != tc.wantIsGPU || gotVendor != tc.wantVendor {
				t.Fatalf("classifyGPUFromVendorClass(%q,%q) = (%v,%q), want (%v,%q)",
					tc.vendor, tc.class, gotIsGPU, gotVendor, tc.wantIsGPU, tc.wantVendor)
			}
		})
	}
}

func TestRenderPCIeLinkCheckSummaryDegradedGPU(t *testing.T) {
	findings := []pcieLinkFinding{
		{BDF: "0000:0d:00.0", Description: "NVIDIA GPU", IsGPU: true, GPUVendor: "nvidia",
			BeforeSpeed: "Gen1", AfterSpeed: "Gen1", MaxSpeed: "Gen5", Degraded: true},
		{BDF: "0000:37:00.0", Description: "NVIDIA GPU", IsGPU: true, GPUVendor: "nvidia",
			BeforeSpeed: "Gen1", AfterSpeed: "Gen5", MaxSpeed: "Gen5", Degraded: false},
		{BDF: "0000:01:00.0", Description: "Mellanox NIC", IsGPU: false,
			BeforeSpeed: "Gen3", AfterSpeed: "Gen4", MaxSpeed: "Gen4", Degraded: false},
	}
	summary := renderPCIeLinkCheckSummary(findings)
	if !strings.Contains(summary, "gpu_nvidia_status=FAILED") {
		t.Fatalf("expected gpu_nvidia_status=FAILED (one degraded GPU should fail the vendor group), got:\n%s", summary)
	}
	if !strings.Contains(summary, "other_status=OK") {
		t.Fatalf("expected other_status=OK, got:\n%s", summary)
	}
	if !strings.Contains(summary, "overall_status=FAILED") {
		t.Fatalf("expected overall_status=FAILED, got:\n%s", summary)
	}
}

func TestRenderPCIeLinkCheckSummaryAllClean(t *testing.T) {
	findings := []pcieLinkFinding{
		{BDF: "0000:0d:00.0", IsGPU: true, GPUVendor: "nvidia", BeforeSpeed: "Gen1", AfterSpeed: "Gen5", MaxSpeed: "Gen5"},
		{BDF: "0000:2c:00.0", Skipped: "device disabled (no data traffic; link state has no operational impact)"},
	}
	summary := renderPCIeLinkCheckSummary(findings)
	if !strings.Contains(summary, "overall_status=OK") {
		t.Fatalf("expected overall_status=OK, got:\n%s", summary)
	}
	if strings.Contains(summary, "other_status=") {
		t.Fatalf("disabled/skipped-only device should not produce an other_status line, got:\n%s", summary)
	}
}

func TestRenderPCIeLinkCheckSummaryEmptySlotDoesNotFail(t *testing.T) {
	// An unpopulated switch downstream port (no card ever seated) is a
	// normal, common configuration — it must not fail the SAT the way a
	// genuinely degraded link does.
	findings := []pcieLinkFinding{
		{BDF: "0000:0d:00.0", IsGPU: true, GPUVendor: "nvidia", BeforeSpeed: "Gen5", AfterSpeed: "Gen5", MaxSpeed: "Gen5"},
		{BDF: "0000:2a:00.0", Description: "PEX890xx PCIe Gen 5 Switch",
			NotPresent: true, Skipped: "no device present downstream (empty slot/riser — nothing to retrain)"},
	}
	summary := renderPCIeLinkCheckSummary(findings)
	if !strings.Contains(summary, "overall_status=OK") {
		t.Fatalf("expected overall_status=OK for an empty slot, got:\n%s", summary)
	}
	if strings.Contains(summary, "other_status=") {
		t.Fatalf("empty-slot-only device should not produce an other_status line, got:\n%s", summary)
	}

	report := renderPCIeLinkCheckReport(findings)
	if !strings.Contains(report, "skipped: no device present downstream") {
		t.Fatalf("expected empty slot to be reported as skipped, not degraded, got:\n%s", report)
	}
	if strings.Contains(report, "retrained to") {
		t.Fatalf("empty slot must not be reported with a fabricated retrain speed, got:\n%s", report)
	}
}

func TestRenderPCIeLinkCheckSummaryDeviceFellOffBusStillFails(t *testing.T) {
	// A device that had a live link before the retrain and is gone right
	// after it is a real regression, distinct from a slot that was never
	// populated — this must still fail the check.
	findings := []pcieLinkFinding{
		{BDF: "0000:ab:00.0", Description: "PEX890xx PCIe Gen 5 Switch",
			BeforeSpeed: "Gen5", AfterSpeed: "Gen5", MaxSpeed: "Gen5", Width: 0, NotPresent: true, Degraded: true},
	}
	summary := renderPCIeLinkCheckSummary(findings)
	if !strings.Contains(summary, "overall_status=FAILED") {
		t.Fatalf("expected overall_status=FAILED when a device disappears after retrain, got:\n%s", summary)
	}
	if !strings.Contains(summary, "no device detected downstream") {
		t.Fatalf("expected an honest 'no device detected' reason, not a fabricated speed, got:\n%s", summary)
	}

	report := renderPCIeLinkCheckReport(findings)
	if !strings.Contains(report, "FELL OFF BUS") {
		t.Fatalf("expected FELL OFF BUS verdict in report, got:\n%s", report)
	}
}