fix(pcie): account for downstream link capability

2026-08-28 09:12:02 +03:00
parent af95216c6f
commit 2354599889
2 changed files with 205 additions and 15 deletions
@@ -1,6 +1,8 @@
 package platform

 import (
+	"os"
+	"path/filepath"
 	"strings"
 	"testing"
 )
@@ -30,6 +32,82 @@ func TestClassifyGPUFromVendorClass(t *testing.T) {
 	}
 }

+func TestPCIeBridgeUsesDownstreamCapability(t *testing.T) {
+	cases := []struct {
+		name          string
+		portSpeed     string
+		portWidth     int
+		endpointSpeed string
+		endpointWidth int
+		wantSpeed     string
+		wantWidth     int
+	}{
+		{"ConnectX-5 behind Gen4 root port", "Gen4", 16, "Gen3", 8, "Gen3", 8},
+		{"Adaptec SAS behind Gen4 root port", "Gen4", 16, "Gen3", 8, "Gen3", 8},
+		{"I350 behind Gen4 root port", "Gen4", 16, "Gen2", 4, "Gen2", 4},
+		{"faster endpoint remains port-limited", "Gen3", 8, "Gen4", 16, "Gen3", 8},
+	}
+
+	for _, tc := range cases {
+		t.Run(tc.name, func(t *testing.T) {
+			gotSpeed := minPCIeLinkSpeed(tc.portSpeed, tc.endpointSpeed)
+			gotWidth := minPositiveInt(tc.portWidth, tc.endpointWidth)
+			if gotSpeed != tc.wantSpeed || gotWidth != tc.wantWidth {
+				t.Fatalf("effective capability = %s x%d, want %s x%d", gotSpeed, gotWidth, tc.wantSpeed, tc.wantWidth)
+			}
+		})
+	}
+}
+
+func TestPCIeBridgeAtEndpointMaximumPasses(t *testing.T) {
+	maxSpeed := minPCIeLinkSpeed("Gen4", "Gen3")
+	maxWidth := minPositiveInt(16, 8)
+	finding := pcieLinkFinding{
+		BDF:          "0000:4a:02.0",
+		Description:  "Intel root port to ConnectX-5",
+		BeforeSpeed:  "Gen3",
+		AfterSpeed:   "Gen3",
+		MaxSpeed:     maxSpeed,
+		PortMaxSpeed: "Gen4",
+		Width:        8,
+		MaxWidth:     maxWidth,
+		PortMaxWidth: 16,
+		Degraded:     "Gen3" != maxSpeed,
+	}
+
+	summary := renderPCIeLinkCheckSummary([]pcieLinkFinding{finding})
+	if !strings.Contains(summary, "overall_status=OK") {
+		t.Fatalf("endpoint-limited bridge should pass, got:\n%s", summary)
+	}
+	report := renderPCIeLinkCheckReport([]pcieLinkFinding{finding})
+	if !strings.Contains(report, "limited by downstream device") {
+		t.Fatalf("report should explain the effective maximum, got:\n%s", report)
+	}
+}
+
+func TestDownstreamPCIeLinkCapabilityFromSysfsTopology(t *testing.T) {
+	bridgeDir := t.TempDir()
+	childDir := filepath.Join(bridgeDir, "0000:4b:00.0")
+	if err := os.Mkdir(childDir, 0755); err != nil {
+		t.Fatal(err)
+	}
+	if err := os.WriteFile(filepath.Join(childDir, "max_link_speed"), []byte("8.0 GT/s PCIe\n"), 0644); err != nil {
+		t.Fatal(err)
+	}
+	if err := os.WriteFile(filepath.Join(childDir, "max_link_width"), []byte("8\n"), 0644); err != nil {
+		t.Fatal(err)
+	}
+	// A non-BDF sysfs entry must not influence peer discovery.
+	if err := os.WriteFile(filepath.Join(bridgeDir, "max_link_speed"), []byte("16.0 GT/s PCIe\n"), 0644); err != nil {
+		t.Fatal(err)
+	}
+
+	speed, width, ok := downstreamPCIeLinkCapabilityAt(bridgeDir)
+	if !ok || speed != "Gen3" || width != 8 {
+		t.Fatalf("downstream capability = (%q, %d, %v), want (Gen3, 8, true)", speed, width, ok)
+	}
+}
+
 func TestRenderPCIeLinkCheckSummaryDegradedGPU(t *testing.T) {
 	findings := []pcieLinkFinding{
 		{BDF: "0000:0d:00.0", Description: "NVIDIA GPU", IsGPU: true, GPUVendor: "nvidia",