Files
bee/audit/internal/collector/pcie_identity.go
T
Mikhail ChusavitinandClaude Sonnet 5 e3697c0a11 fix(pcie): stop misclassifying same-vendor non-GPU devices as GPUs
matchesGPUVendor (sat_overlay.go) matched any PCIe DeviceClass containing
the substring "Controller" instead of the actual GPU classes, so a
same-vendor non-GPU device (e.g. an NVIDIA-branded NIC/storage controller)
with a degraded PCIe link surfaced as a pcie:gpu:<vendor> alarm on the
Hardware Summary/webui.

isGPUDevice (app_format.go) had the same bug via a different path: an
"any NVIDIA-vendor device is a GPU" fallback that could inflate the
"GPU: N x <model>" audit summary line with non-GPU companion devices
(NVSwitch/NVLink bridges, etc).

Both now defer to collector.IsGPUClass (exported from the previously
unexported isGPUClass), the canonical exact-match classifier already used
by amdgpu.go — removing the duplicated/incorrect class checks instead of
reimplementing them. Also dedup two more locally-duplicated classifiers
within webui (which doesn't import collector by convention): NIC-class
matching (pages.go/page_topo.go) and GPU-class matching in
page_validate.go now share one copy per package instead of being
reimplemented per file.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-08-17 12:50:50 +03:00

124 lines
2.6 KiB
Go

package collector
import (
"bee/audit/internal/schema"
"log/slog"
"os"
"os/exec"
"path/filepath"
"strings"
)
var (
queryPCILSPCIDetail = func(bdf string) (string, error) {
out, err := exec.Command("lspci", "-vv", "-s", bdf).Output()
if err != nil {
return "", err
}
return string(out), nil
}
readPCIVPDFile = func(bdf string) ([]byte, error) {
return os.ReadFile(filepath.Join("/sys/bus/pci/devices", bdf, "vpd"))
}
)
func enrichPCIeWithPCISerials(devs []schema.HardwarePCIeDevice) []schema.HardwarePCIeDevice {
enriched := 0
for i := range devs {
if !shouldProbePCIeSerial(devs[i]) {
continue
}
bdf := normalizePCIeBDF(*devs[i].BDF)
if bdf == "" {
continue
}
if serial := queryPCIDeviceSerial(bdf); serial != "" {
devs[i].SerialNumber = &serial
enriched++
}
}
if enriched > 0 {
slog.Info("pcie: serials enriched", "count", enriched)
}
return devs
}
func shouldProbePCIeSerial(dev schema.HardwarePCIeDevice) bool {
if dev.BDF == nil || dev.SerialNumber != nil {
return false
}
if dev.DeviceClass == nil {
return false
}
class := strings.TrimSpace(*dev.DeviceClass)
return isNICClass(class) || IsGPUClass(class)
}
func queryPCIDeviceSerial(bdf string) string {
if out, err := queryPCILSPCIDetail(bdf); err == nil {
if serial := parseLSPCIDetailSerial(out); serial != "" {
return serial
}
}
if raw, err := readPCIVPDFile(bdf); err == nil {
return parsePCIVPDSerial(raw)
}
return ""
}
func parseLSPCIDetailSerial(raw string) string {
for _, line := range strings.Split(raw, "\n") {
line = strings.TrimSpace(line)
if line == "" {
continue
}
lower := strings.ToLower(line)
if !strings.Contains(lower, "serial number:") {
continue
}
idx := strings.Index(line, ":")
if idx < 0 {
continue
}
if serial := strings.TrimSpace(line[idx+1:]); serial != "" {
return serial
}
}
return ""
}
func parsePCIVPDSerial(raw []byte) string {
for i := 0; i+3 < len(raw); i++ {
if raw[i] != 'S' || raw[i+1] != 'N' {
continue
}
length := int(raw[i+2])
if length <= 0 || length > 64 || i+3+length > len(raw) {
continue
}
value := strings.TrimSpace(strings.Trim(string(raw[i+3:i+3+length]), "\x00"))
if !looksLikeSerial(value) {
continue
}
return value
}
return ""
}
func looksLikeSerial(value string) bool {
if len(value) < 4 {
return false
}
hasAlphaNum := false
for _, r := range value {
switch {
case r >= 'a' && r <= 'z', r >= 'A' && r <= 'Z', r >= '0' && r <= '9':
hasAlphaNum = true
case strings.ContainsRune(" -_./:", r):
default:
return false
}
}
return hasAlphaNum
}