bee/audit/internal/platform/error_patterns.go

package platform

import "regexp"

// ErrorPattern describes a kernel log pattern that indicates a hardware error.
// Add new patterns by appending to HardwareErrorPatterns — no other code changes needed.
type ErrorPattern struct {
	// Name is a short machine-readable label for logging and deduplication.
	Name string
	// Re is the compiled regular expression matched against a single kmsg line.
	Re *regexp.Regexp
	// Category groups related errors: "gpu", "pcie", "storage", "mce", "memory", "cpu".
	Category string
	// Severity is "warning" for recoverable/uncertain faults, "critical" for definitive failures.
	Severity string
	// BDFGroup is the capture group index (1-based) that contains a PCIe BDF address
	// (e.g. "0000:c8:00.0"). 0 means no BDF is captured by this pattern.
	BDFGroup int
	// DevGroup is the capture group index (1-based) that contains a device name
	// (e.g. "sda", "nvme0"). 0 means no device name is captured by this pattern.
	DevGroup int
}

// HardwareErrorPatterns is the global list of kernel log patterns that indicate hardware faults.
// To add a new pattern: append a new ErrorPattern struct to this slice.
var HardwareErrorPatterns = []ErrorPattern{
	// ── GPU / NVIDIA ────────────────────────────────────────────────────────────
	{
		Name:     "nvidia-rminitadapter",
		Re:       mustPat(`(?i)NVRM:.*GPU\s+([\da-f]{4}:[\da-f]{2}:[\da-f]{2}\.\d)`),
		Category: "gpu",
		Severity: "warning",
		BDFGroup: 1,
	},
	{
		Name:     "nvidia-msi-fail",
		Re:       mustPat(`(?i)NVRM:.*Failed to enable MSI`),
		Category: "gpu",
		Severity: "warning",
	},
	{
		Name:     "nvidia-aer",
		Re:       mustPat(`(?i)nvidia\s+([\da-f]{4}:[\da-f]{2}:[\da-f]{2}\.\d).*AER`),
		Category: "gpu",
		Severity: "warning",
		BDFGroup: 1,
	},
	{
		Name:     "nvidia-xid",
		Re:       mustPat(`(?i)NVRM:.*Xid.*\b([\da-f]{4}:[\da-f]{2}:[\da-f]{2}\.\d)`),
		Category: "gpu",
		Severity: "warning",
		BDFGroup: 1,
	},

	// ── PCIe AER (generic) ──────────────────────────────────────────────────────
	{
		Name:     "pcie-aer",
		Re:       mustPat(`(?i)pcieport\s+([\da-f]{4}:[\da-f]{2}:[\da-f]{2}\.\d).*AER`),
		Category: "pcie",
		Severity: "warning",
		BDFGroup: 1,
	},
	{
		Name:     "pcie-uncorrectable",
		Re:       mustPat(`(?i)([\da-f]{4}:[\da-f]{2}:[\da-f]{2}\.\d).*[Uu]ncorrectable`),
		Category: "pcie",
		Severity: "warning",
		BDFGroup: 1,
	},
	{
		Name:     "pcie-link-down",
		Re:       mustPat(`(?i)pcieport\s+([\da-f]{4}:[\da-f]{2}:[\da-f]{2}\.\d).*[Ll]ink.*[Dd]own`),
		Category: "pcie",
		Severity: "warning",
		BDFGroup: 1,
	},

	// ── Storage ─────────────────────────────────────────────────────────────────
	{
		Name:     "blk-io-error",
		Re:       mustPat(`(?i)blk_update_request.*I/O error.*dev\s+(\w+)`),
		Category: "storage",
		Severity: "warning",
		DevGroup: 1,
	},
	{
		Name:     "nvme-timeout",
		Re:       mustPat(`(?i)nvme\s+(\w+):.*timeout`),
		Category: "storage",
		Severity: "warning",
		DevGroup: 1,
	},
	{
		Name:     "scsi-failed",
		Re:       mustPat(`(?i)sd\s+[\da-f:]+:.*FAILED`),
		Category: "storage",
		Severity: "warning",
	},
	{
		Name:     "nvme-reset",
		Re:       mustPat(`(?i)nvme\s+(\w+):.*reset`),
		Category: "storage",
		Severity: "warning",
		DevGroup: 1,
	},

	// ── Machine Check Exceptions ────────────────────────────────────────────────
	{
		Name:     "mce-hardware-error",
		Re:       mustPat(`(?i)mce:.*[Hh]ardware [Ee]rror`),
		Category: "mce",
		Severity: "warning",
	},
	{
		Name:     "mce-corrected",
		Re:       mustPat(`(?i)mce:.*[Cc]orrected`),
		Category: "mce",
		Severity: "warning",
	},

	// ── Memory ─────────────────────────────────────────────────────────────────
	{
		Name:     "edac-ue",
		Re:       mustPat(`(?i)EDAC.*[Uu]ncorrectable`),
		Category: "memory",
		Severity: "warning",
	},
	{
		Name:     "edac-ce",
		Re:       mustPat(`(?i)EDAC.*[Cc]orrectable`),
		Category: "memory",
		Severity: "warning",
	},
}

func mustPat(s string) *regexp.Regexp {
	return regexp.MustCompile(s)
}