hamlab/internal/hardware/hardware.go

// Package hardware is what is physically in the machine: the board it is, its processor,
// the memory modules in its slots, the drives attached to it and the graphics in it.
//
// None of this changes while the machine is running, so it is read once and remembered.
// Everything here is read from what Debian and its kin already have — dmidecode for the
// parts only the firmware knows, lscpu, lspci, sysfs — and every reader is allowed to
// come back empty: a machine with no dmidecode, no PCI bus or no root still gets a page,
// with a note saying what could not be read and why.
package hardware

import (
	"bufio"
	"context"
	"os"
	"os/exec"
	"path/filepath"
	"regexp"
	"sort"
	"strconv"
	"strings"
	"sync"
	"time"

	"hamlab/internal/priv"
	"hamlab/internal/storage"
)

type System struct {
	Model  string `json:"model,omitempty"` // "GMKtec NucBox G3"
	Serial string `json:"serial,omitempty"`
	Family string `json:"family,omitempty"`
	Kernel string `json:"kernel,omitempty"`
	Arch   string `json:"arch,omitempty"`
	Virt   string `json:"virt,omitempty"` // "kvm", "lxc", … when this is not real hardware
}

// Slot is an expansion slot as the firmware describes it. Worth treating with suspicion on
// a mini PC, where the table is often copied from a reference design and lists slots the
// case has no room for.
type Slot struct {
	Designation string `json:"designation"`
	Type        string `json:"type,omitempty"`
	Usage       string `json:"usage,omitempty"` // Available | In Use | Unknown
	Length      string `json:"length,omitempty"`
	Width       string `json:"width,omitempty"`
	Bus         string `json:"bus,omitempty"`    // PCI address of what is in it
	Device      string `json:"device,omitempty"` // and what that turns out to be
}

// Board is the motherboard and the firmware on it.
type Board struct {
	Maker        string `json:"maker,omitempty"`
	Product      string `json:"product,omitempty"`
	Version      string `json:"version,omitempty"`
	Serial       string `json:"serial,omitempty"`
	AssetTag     string `json:"asset_tag,omitempty"`
	Type         string `json:"type,omitempty"`     // "Motherboard", "Processor Module", …
	Location     string `json:"location,omitempty"` // where it sits in the chassis
	Chassis      string `json:"chassis,omitempty"`
	ChassisMaker string `json:"chassis_maker,omitempty"`
	BIOS         string `json:"bios,omitempty"` // vendor and version
	BIOSDate     string `json:"bios_date,omitempty"`
	BIOSRevision string `json:"bios_revision,omitempty"`
	ROMSize      string `json:"rom_size,omitempty"`
	UEFI         bool   `json:"uefi,omitempty"`
	Slots        []Slot `json:"slots,omitempty"`
}

type Cache struct {
	Level string `json:"level"` // L1d, L1i, L2, L3
	Size  string `json:"size"`  // as lscpu puts it: "6 MiB (1 instance)"
}

type CPU struct {
	Model          string   `json:"model,omitempty"`
	Vendor         string   `json:"vendor,omitempty"`
	Arch           string   `json:"arch,omitempty"`
	Sockets        int      `json:"sockets,omitempty"`
	SocketNames    []string `json:"socket_names,omitempty"` // what the firmware calls each socket
	Cores          int      `json:"cores,omitempty"`
	Threads        int      `json:"threads,omitempty"`
	ThreadsPerCore int      `json:"threads_per_core,omitempty"`
	MinMHz         float64  `json:"min_mhz,omitempty"`
	MaxMHz         float64  `json:"max_mhz,omitempty"`
	Family         string   `json:"family,omitempty"`
	ModelID        string   `json:"model_id,omitempty"`
	Stepping       string   `json:"stepping,omitempty"`
	Microcode      string   `json:"microcode,omitempty"`
	Virtualization string   `json:"virtualization,omitempty"`
	Caches         []Cache  `json:"caches,omitempty"`
	Flags          []string `json:"flags,omitempty"` // the handful anyone looks for
}

type Module struct {
	Locator    string `json:"locator"` // the slot, as the board labels it
	Bank       string `json:"bank,omitempty"`
	Empty      bool   `json:"empty,omitempty"`
	Size       uint64 `json:"size,omitempty"`
	Type       string `json:"type,omitempty"`        // DDR4
	FormFactor string `json:"form_factor,omitempty"` // SODIMM
	SpeedMTs   int    `json:"speed_mts,omitempty"`   // what the module can do
	RunningMTs int    `json:"running_mts,omitempty"` // what the board is running it at
	Maker      string `json:"maker,omitempty"`
	Part       string `json:"part,omitempty"`
	Serial     string `json:"serial,omitempty"`
	Rank       int    `json:"rank,omitempty"`
	Voltage    string `json:"voltage,omitempty"`
}

type Memory struct {
	Total       uint64   `json:"total"`                  // what the kernel can use
	Installed   uint64   `json:"installed,omitempty"`    // what the modules add up to
	MaxCapacity uint64   `json:"max_capacity,omitempty"` // what the board will take
	Slots       int      `json:"slots,omitempty"`
	Filled      int      `json:"filled,omitempty"`
	ECC         string   `json:"ecc,omitempty"`
	Modules     []Module `json:"modules,omitempty"`
}

type Drive struct {
	Name       string `json:"name"`
	Kind       string `json:"kind"` // nvme | ssd | hdd | usb | emmc | sd | other
	Model      string `json:"model,omitempty"`
	Vendor     string `json:"vendor,omitempty"`
	Serial     string `json:"serial,omitempty"`
	Firmware   string `json:"firmware,omitempty"`
	Tran       string `json:"tran,omitempty"`
	Size       uint64 `json:"size"`
	Rotational bool   `json:"rotational,omitempty"`
	Removable  bool   `json:"removable,omitempty"`
}

type GPU struct {
	Model  string `json:"model,omitempty"`
	Vendor string `json:"vendor,omitempty"`
	Slot   string `json:"slot,omitempty"` // PCI address, when it is on a bus
	Driver string `json:"driver,omitempty"`
	Node   string `json:"node,omitempty"` // card0
	Memory uint64 `json:"memory,omitempty"`
	Class  string `json:"class,omitempty"` // VGA | 3D | Display
}

type Report struct {
	At     time.Time `json:"at"`
	System System    `json:"system"`
	Board  Board     `json:"board"`
	CPU    CPU       `json:"cpu"`
	Memory Memory    `json:"memory"`
	Drives []Drive   `json:"drives"`
	GPUs   []GPU     `json:"gpus"`
	Notes  []string  `json:"notes,omitempty"` // what could not be read, and why
}

// Manager remembers the last report. Hardware does not change under a running kernel —
// the one thing that would, a drive plugged in, is what Refresh is for.
type Manager struct {
	mu   sync.Mutex
	last *Report
	at   time.Time
}

func New() *Manager { return &Manager{} }

const keepFor = 10 * time.Minute

func (m *Manager) Report(ctx context.Context, refresh bool) *Report {
	m.mu.Lock()
	if !refresh && m.last != nil && time.Since(m.at) < keepFor {
		r := m.last
		m.mu.Unlock()
		return r
	}
	m.mu.Unlock()

	r := collect(ctx)

	m.mu.Lock()
	m.last, m.at = r, time.Now()
	m.mu.Unlock()
	return r
}

func collect(ctx context.Context) *Report {
	ctx, cancel := context.WithTimeout(ctx, 25*time.Second)
	defer cancel()
	r := &Report{At: time.Now()}
	dmi, note := readDMI(ctx)
	if note != "" {
		r.Notes = append(r.Notes, note)
	}
	r.System = system(ctx, dmi)
	r.Board = board(dmi, pciNames(ctx))
	r.CPU = cpu(ctx, dmi)
	r.Memory = memory(dmi)
	if len(r.Memory.Modules) == 0 && note == "" {
		r.Notes = append(r.Notes, "memory modules: the firmware's table says nothing about this machine's slots")
	}
	r.Drives = drives(ctx)
	r.GPUs = gpus(ctx)
	if len(r.GPUs) == 0 {
		r.Notes = append(r.Notes, "graphics: nothing on the PCI bus and no kernel display device")
	}
	return r
}

// ---- dmidecode ----

// record is one entry of the firmware's table: its DMI type and its key/value lines.
type record struct {
	Type int
	V    map[string]string
}

// listKey holds every doubly-indented line of a record — dmidecode's lists, which have no
// key of their own: BIOS characteristics, board features, slot characteristics.
const listKey = "\x00list"

var handleRe = regexp.MustCompile(`^Handle 0x[0-9A-Fa-f]+, DMI type (\d+)`)

// readDMI runs dmidecode once for every type the page wants and parses the lot. It needs
// root; without it the page loses the board, the memory modules and the socket names, and
// says so rather than pretending the machine has none.
func readDMI(ctx context.Context) ([]record, string) {
	tool, err := exec.LookPath("dmidecode")
	if err != nil {
		if _, e := os.Stat("/usr/sbin/dmidecode"); e != nil {
			return nil, "the board and the memory modules need dmidecode, which isn't installed here"
		}
		tool = "/usr/sbin/dmidecode"
	}
	args := []string{tool, "-t", "bios", "-t", "system", "-t", "baseboard", "-t", "chassis", "-t", "slot", "-t", "processor", "-t", "memory"}
	if os.Geteuid() != 0 {
		if !priv.Available() {
			return nil, "the board and the memory modules come from the firmware's table, which only root may read"
		}
		args = priv.Wrap(args...)
	}
	out, err := exec.CommandContext(ctx, args[0], args[1:]...).Output()
	if err != nil {
		return nil, "the firmware's table could not be read: " + strings.TrimSpace(err.Error())
	}
	return parse(string(out)), ""
}

// parse turns dmidecode's output into records: a handle line starts one, and the single
// indented "Key: Value" lines under it are its fields. Doubly-indented lines are the
// continuation of a list (a processor's flags), which nothing here reads.
func parse(text string) []record {
	var recs []record
	var cur *record
	sc := bufio.NewScanner(strings.NewReader(text))
	sc.Buffer(make([]byte, 0, 64<<10), 2<<20)
	for sc.Scan() {
		line := sc.Text()
		if m := handleRe.FindStringSubmatch(line); m != nil {
			t, _ := strconv.Atoi(m[1])
			recs = append(recs, record{Type: t, V: map[string]string{}})
			cur = &recs[len(recs)-1]
			continue
		}
		if cur == nil || !strings.HasPrefix(line, "\t") {
			if strings.TrimSpace(line) == "" {
				cur = nil
			}
			continue
		}
		if strings.HasPrefix(line, "\t\t") { // a list under the field above it, e.g. BIOS characteristics
			cur.V[listKey] += strings.TrimSpace(line) + "\n"
			continue
		}
		k, v, ok := strings.Cut(strings.TrimSpace(line), ":")
		if !ok {
			continue
		}
		cur.V[k] = strings.TrimSpace(v)
	}
	return recs
}

func (r record) get(keys ...string) string {
	for _, k := range keys {
		if v := r.V[k]; v != "" && !unset(v) {
			return v
		}
	}
	return ""
}

// unset is every way the firmware has of saying "nobody filled this in".
func unset(v string) bool {
	switch strings.ToLower(v) {
	case "", "unknown", "not specified", "not provided", "none", "default string", "to be filled by o.e.m.",
		"system manufacturer", "system product name", "to be filled by oem", "n/a", "empty", "no module installed",
		"<out of spec>", "other", "not applicable":
		return true
	}
	return false
}

func first(recs []record, t int) record {
	for _, r := range recs {
		if r.Type == t {
			return r
		}
	}
	return record{Type: t, V: map[string]string{}}
}

func all(recs []record, t int) []record {
	var out []record
	for _, r := range recs {
		if r.Type == t {
			out = append(out, r)
		}
	}
	return out
}

// ---- system ----

func system(ctx context.Context, dmi []record) System {
	sys := first(dmi, 1)
	s := System{
		Model:  join(sys.get("Manufacturer"), sys.get("Product Name")),
		Serial: sys.get("Serial Number"),
		Family: sys.get("Family"),
		Arch:   runtimeArch(),
	}
	s.Kernel = readFile("/proc/sys/kernel/osrelease")
	if s.Model == "" { // no SMBIOS: a Pi, a Mac, anything with a device tree
		s.Model = strings.TrimRight(readFile("/sys/firmware/devicetree/base/model"), "\x00")
	}
	if out, err := exec.CommandContext(ctx, "systemd-detect-virt").Output(); err == nil {
		if v := strings.TrimSpace(string(out)); v != "" && v != "none" {
			s.Virt = v
		}
	}
	return s
}

// board reads the motherboard, the chassis it sits in, the firmware on it and the
// expansion slots the firmware claims. All of it is SMBIOS, so a machine without one — a
// Mac, a Pi — gets an empty board, and the page says so rather than inventing one.
func board(dmi []record, pci map[string]string) Board {
	b, ch, bios := first(dmi, 2), first(dmi, 3), first(dmi, 0)
	out := Board{
		Maker:        b.get("Manufacturer"),
		Product:      b.get("Product Name"),
		Version:      b.get("Version"),
		Serial:       b.get("Serial Number"),
		AssetTag:     b.get("Asset Tag"),
		Type:         b.get("Type"),
		Location:     b.get("Location In Chassis"),
		Chassis:      ch.get("Type"),
		ChassisMaker: ch.get("Manufacturer"),
		BIOS:         join(bios.get("Vendor"), bios.get("Version")),
		BIOSDate:     bios.get("Release Date"),
		BIOSRevision: bios.get("BIOS Revision"),
	}
	// "ROM Size: 0 MB" is a board that never filled the field in, not a board with no ROM
	if rom := bios.get("ROM Size"); rom != "" && !strings.HasPrefix(rom, "0 ") {
		out.ROMSize = rom
	}
	if out.Product == out.Maker {
		out.Product = "" // a board named after its maker says nothing twice
	}
	out.UEFI = strings.Contains(bios.V[listKey], "UEFI") // a characteristics line, not a field
	for _, sl := range all(dmi, 9) {
		s := Slot{
			Designation: sl.get("Designation"),
			Type:        sl.get("Type"),
			Usage:       sl.get("Current Usage"),
			Length:      sl.get("Length"),
			Width:       sl.get("Data Bus Width"),
		}
		// every slot on some boards claims 0000:00:00.0, which is the host bridge and
		// certainly not what is plugged into that slot
		if bus := sl.get("Bus Address"); bus != "" && bus != "0000:00:00.0" {
			s.Bus, s.Device = bus, pci[bus]
		}
		if s.Designation != "" {
			out.Slots = append(out.Slots, s)
		}
	}
	return out
}

func join(parts ...string) string {
	var keep []string
	for _, p := range parts {
		if p = strings.TrimSpace(p); p != "" && !unset(p) {
			keep = append(keep, p)
		}
	}
	// "GMKtec GMKtec" reads badly: drop a maker the product already names
	if len(keep) == 2 && strings.HasPrefix(strings.ToLower(keep[1]), strings.ToLower(keep[0])) {
		return keep[1]
	}
	return strings.Join(keep, " ")
}

func readFile(p string) string {
	b, err := os.ReadFile(p)
	if err != nil {
		return ""
	}
	return strings.TrimSpace(string(b))
}

func runtimeArch() string {
	if out, err := exec.Command("uname", "-m").Output(); err == nil {
		return strings.TrimSpace(string(out))
	}
	return ""
}

// ---- processor ----

// worthShowing is the short list of processor features anyone actually asks about; the
// full flag list runs to hundreds and belongs in a terminal.
var worthShowing = []string{"aes", "avx", "avx2", "avx512f", "sha_ni", "vmx", "svm", "sse4_2", "rdrand", "hypervisor"}

func cpu(ctx context.Context, dmi []record) CPU {
	c := CPU{}
	f := lscpu(ctx)
	c.Model = f["Model name"]
	c.Vendor = f["Vendor ID"]
	c.Arch = f["Architecture"]
	c.Sockets = atoi(f["Socket(s)"])
	c.ThreadsPerCore = atoi(f["Thread(s) per core"])
	c.Threads = atoi(f["CPU(s)"])
	c.Cores = atoi(f["Core(s) per socket"]) * maxInt(1, c.Sockets)
	c.MinMHz = atof(f["CPU min MHz"])
	c.MaxMHz = atof(f["CPU max MHz"])
	c.Family, c.ModelID, c.Stepping = f["CPU family"], f["Model"], f["Stepping"]
	c.Virtualization = f["Virtualization"]
	for _, l := range []string{"L1d", "L1i", "L2", "L3"} {
		if v := f[l+" cache"]; v != "" {
			c.Caches = append(c.Caches, Cache{Level: l, Size: v})
		}
	}
	have := map[string]bool{}
	for _, fl := range strings.Fields(f["Flags"]) {
		have[fl] = true
	}
	for _, fl := range worthShowing {
		if have[fl] {
			c.Flags = append(c.Flags, fl)
		}
	}
	for _, p := range all(dmi, 4) {
		if s := p.get("Socket Designation"); s != "" {
			c.SocketNames = append(c.SocketNames, s)
		}
		if c.Model == "" {
			c.Model = p.get("Version", "Family")
		}
		if c.MaxMHz == 0 {
			if mhz := atof(strings.TrimSuffix(p.get("Max Speed"), " MHz")); mhz > 0 {
				c.MaxMHz = mhz
			}
		}
	}
	if c.Sockets == 0 {
		c.Sockets = len(c.SocketNames)
	}
	// A processor whose cores are not all alike — Apple's, Intel's P and E cores — is
	// reported by lscpu as several groups, and "core(s) per socket" then counts one group
	// rather than the chip. Without SMT every thread is a core, so the thread count is the
	// honest answer.
	if c.ThreadsPerCore == 1 && c.Threads > c.Cores {
		c.Cores = c.Threads
	}
	// /proc/cpuinfo is the only place the running microcode revision is written down
	if b, err := os.ReadFile("/proc/cpuinfo"); err == nil {
		for _, line := range strings.Split(string(b), "\n") {
			if k, v, ok := strings.Cut(line, ":"); ok && strings.TrimSpace(k) == "microcode" {
				c.Microcode = strings.TrimSpace(v)
				break
			}
		}
	}
	if c.Model == "" {
		c.Model = "unknown processor"
	}
	return c
}

func lscpu(ctx context.Context) map[string]string {
	f := map[string]string{}
	out, err := exec.CommandContext(ctx, "lscpu").Output()
	if err != nil {
		// no util-linux: /proc/cpuinfo still names the thing and counts it
		if b, err := os.ReadFile("/proc/cpuinfo"); err == nil {
			n := 0
			for _, line := range strings.Split(string(b), "\n") {
				k, v, ok := strings.Cut(line, ":")
				k, v = strings.TrimSpace(k), strings.TrimSpace(v)
				switch {
				case ok && strings.EqualFold(k, "model name"):
					f["Model name"] = v
				case ok && k == "processor":
					n++
				}
			}
			f["CPU(s)"] = strconv.Itoa(n)
		}
		return f
	}
	for _, line := range strings.Split(string(out), "\n") {
		k, v, ok := strings.Cut(line, ":")
		if !ok || strings.HasPrefix(line, " ") {
			continue
		}
		f[strings.TrimSpace(k)] = strings.TrimSpace(v)
	}
	return f
}

func atoi(s string) int { n, _ := strconv.Atoi(strings.TrimSpace(s)); return n }

func atof(s string) float64 {
	v, _ := strconv.ParseFloat(strings.TrimSpace(s), 64)
	return v
}

func maxInt(a, b int) int {
	if a > b {
		return a
	}
	return b
}

// leadingInt reads the number off the front of "3200 MT/s".
func leadingInt(s string) int {
	f := strings.Fields(s)
	if len(f) == 0 {
		return 0
	}
	return atoi(f[0])
}

// ---- memory ----

var sizeRe = regexp.MustCompile(`^(\d+)\s*(kB|KB|MB|GB|TB)$`)

// dmiSize turns dmidecode's "8 GB" / "16384 MB" into bytes.
func dmiSize(s string) uint64 {
	m := sizeRe.FindStringSubmatch(strings.TrimSpace(s))
	if m == nil {
		return 0
	}
	n, _ := strconv.ParseUint(m[1], 10, 64)
	switch strings.ToUpper(m[2]) {
	case "KB":
		return n << 10
	case "MB":
		return n << 20
	case "GB":
		return n << 30
	case "TB":
		return n << 40
	}
	return 0
}

func memory(dmi []record) Memory {
	m := Memory{}
	if b, err := os.ReadFile("/proc/meminfo"); err == nil {
		for _, line := range strings.Split(string(b), "\n") {
			if k, v, ok := strings.Cut(line, ":"); ok && k == "MemTotal" {
				m.Total = uint64(atoi(strings.TrimSuffix(strings.TrimSpace(v), " kB"))) << 10
				break
			}
		}
	}
	for _, a := range all(dmi, 16) {
		m.MaxCapacity += dmiSize(a.get("Maximum Capacity"))
		switch e := a.V["Error Correction Type"]; {
		case e == "None":
			m.ECC = "non-ECC" // the array says so outright; worth knowing, not worth hiding
		case e != "" && !unset(e):
			m.ECC = e
		}
	}
	for _, d := range all(dmi, 17) {
		mod := Module{
			Locator: d.get("Locator"),
			Bank:    d.get("Bank Locator"),
			Size:    dmiSize(d.get("Size")),
		}
		m.Slots++
		if mod.Locator == "" {
			mod.Locator = "slot " + strconv.Itoa(m.Slots)
		}
		if mod.Size == 0 {
			mod.Empty = true
			m.Modules = append(m.Modules, mod)
			continue
		}
		m.Filled++
		mod.Type = d.get("Type")
		mod.FormFactor = d.get("Form Factor")
		mod.SpeedMTs = leadingInt(d.get("Speed"))
		mod.RunningMTs = leadingInt(d.get("Configured Memory Speed", "Configured Clock Speed"))
		mod.Maker = makerName(d.get("Manufacturer"), d.V["Module Manufacturer ID"])
		mod.Part = d.get("Part Number")
		mod.Serial = d.get("Serial Number")
		mod.Rank = atoi(d.get("Rank"))
		mod.Voltage = d.get("Configured Voltage")
		m.Installed += mod.Size
		m.Modules = append(m.Modules, mod)
	}
	return m
}

// jedec maps the memory makers who turn up in a homelab to their names: SPD carries a
// JEDEC id, and dmidecode prints the raw code when the module's string field is empty.
var jedec = map[string]string{
	"0X2C00": "Micron", "0X802C": "Micron",
	"0XCE00": "Samsung", "0X80CE": "Samsung", "0X00CE": "Samsung",
	"0XAD00": "SK hynix", "0X80AD": "SK hynix",
	"0X9801": "Kingston", "0X7F98": "Kingston", "0X0198": "Kingston",
	"0X859B": "Crucial", "0X04CB": "A-DATA", "0X04CD": "G.Skill",
	"0X029E": "Corsair", "0X0B45": "Wilk Elektronik", "0X830B": "Wilk Elektronik",
	"0X0443": "Ramaxel", "0X0194": "Smart Modular",
}

// makerName prefers what the module says it is; a bare JEDEC id becomes a name when it is
// one we know, and stays the id when it is not — a wrong name is worse than a number.
func makerName(v, id string) string {
	if v != "" && !unset(v) && !strings.HasPrefix(v, "0x") {
		return v
	}
	code := v
	if code == "" {
		code = id
	}
	if n, ok := jedec[strings.ToUpper(code)]; ok {
		return n
	}
	if v != "" && !unset(v) {
		return v
	}
	return ""
}

// ---- drives ----

func drives(ctx context.Context) []Drive {
	devs, err := storage.Devices(ctx)
	if err != nil {
		return nil
	}
	out := make([]Drive, 0, len(devs))
	for _, d := range devs {
		out = append(out, Drive{
			Name: d.Name, Kind: d.Kind, Model: d.Model, Vendor: d.Vendor, Serial: d.Serial,
			Tran: d.Tran, Size: d.Size, Rotational: d.Rotational, Removable: d.Removable,
			Firmware: firmwareOf(d.Name),
		})
	}
	return out
}

// firmwareOf reads a drive's firmware revision. An NVMe device is folded to its
// controller ("nvme0"), which has no /sys/block entry of its own — the revision is on the
// controller in /sys/class/nvme.
func firmwareOf(name string) string {
	return firstNonEmpty(
		readFile("/sys/block/"+name+"/device/firmware_rev"),
		readFile("/sys/block/"+name+"/device/rev"),
		readFile("/sys/class/nvme/"+name+"/firmware_rev"),
	)
}

func firstNonEmpty(v ...string) string {
	for _, s := range v {
		if s != "" {
			return s
		}
	}
	return ""
}

// ---- graphics ----

// lspci -mm quotes every field, so a device name can hold the spaces and brackets it
// likes: `"VGA compatible controller [0300]" "Intel Corporation [8086]" "Alder Lake-N …"`.
var quoted = regexp.MustCompile(`"([^"]*)"`)

// stripID drops the trailing PCI id from `Alder Lake-N [UHD Graphics] [46d1]`.
func stripID(s string) string {
	if i := strings.LastIndex(s, " ["); i > 0 && strings.HasSuffix(s, "]") {
		return strings.TrimSpace(s[:i])
	}
	return s
}

func gpus(ctx context.Context) []GPU {
	var out []GPU
	seen := map[string]bool{} // PCI addresses already accounted for
	if _, err := exec.LookPath("lspci"); err == nil {
		drivers := pciDrivers(ctx)
		if b, err := exec.CommandContext(ctx, "lspci", "-D", "-mm", "-nn").Output(); err == nil {
			for _, line := range strings.Split(string(b), "\n") {
				slot, _, _ := strings.Cut(line, " ")
				fields := quoted.FindAllStringSubmatch(line, -1)
				if len(fields) < 3 {
					continue
				}
				kind := displayClass(fields[0][1])
				if kind == "" {
					continue
				}
				seen[slot] = true
				g := GPU{Slot: slot, Class: kind, Vendor: stripID(fields[1][1]), Model: stripID(fields[2][1]), Driver: drivers[slot]}
				g.Node, g.Memory = drmFor(slot)
				out = append(out, g)
			}
		}
	}
	// A GPU that is not on a PCI bus at all — an Apple Silicon Mac, a Pi, anything with a
	// device tree — is only visible as a kernel display device.
	cards, _ := filepath.Glob("/sys/class/drm/card[0-9]")
	for _, c := range cards {
		dev, err := filepath.EvalSymlinks(c + "/device")
		if err != nil || seen[filepath.Base(dev)] {
			continue
		}
		g := GPU{Node: filepath.Base(c), Class: "Display"}
		if drv, err := filepath.EvalSymlinks(dev + "/driver"); err == nil {
			g.Driver = filepath.Base(drv)
		}
		g.Model = deviceTreeName(dev)
		if g.Model == "" && g.Driver != "" {
			g.Model = g.Driver + " display"
		}
		if g.Model == "" {
			continue
		}
		g.Memory = vram(dev)
		out = append(out, g)
	}
	sort.SliceStable(out, func(i, j int) bool { return out[i].Slot < out[j].Slot })
	return out
}

// pciNames maps a PCI address to a readable name, so a slot the firmware says is in use
// can say what is in it.
func pciNames(ctx context.Context) map[string]string {
	m := map[string]string{}
	if _, err := exec.LookPath("lspci"); err != nil {
		return m
	}
	out, err := exec.CommandContext(ctx, "lspci", "-D", "-mm", "-nn").Output()
	if err != nil {
		return m
	}
	for _, line := range strings.Split(string(out), "\n") {
		slot, _, _ := strings.Cut(line, " ")
		f := quoted.FindAllStringSubmatch(line, -1)
		if slot == "" || len(f) < 3 {
			continue
		}
		m[slot] = strings.TrimSpace(stripID(f[1][1]) + " " + stripID(f[2][1]))
	}
	return m
}

func displayClass(c string) string {
	switch {
	case strings.Contains(c, "[0300]"):
		return "VGA"
	case strings.Contains(c, "[0302]"):
		return "3D"
	case strings.Contains(c, "[0301]"), strings.Contains(c, "[0380]"):
		return "Display"
	}
	return ""
}

// pciDrivers maps a PCI address to the kernel module driving it.
func pciDrivers(ctx context.Context) map[string]string {
	m := map[string]string{}
	out, err := exec.CommandContext(ctx, "lspci", "-D", "-k").Output()
	if err != nil {
		return m
	}
	slot := ""
	for _, line := range strings.Split(string(out), "\n") {
		if !strings.HasPrefix(line, "\t") && !strings.HasPrefix(line, " ") {
			slot, _, _ = strings.Cut(line, " ")
			continue
		}
		if v, ok := strings.CutPrefix(strings.TrimSpace(line), "Kernel driver in use:"); ok && slot != "" {
			m[slot] = strings.TrimSpace(v)
		}
	}
	return m
}

// drmFor finds the kernel display device for a PCI address, and its video memory when the
// driver publishes it (amdgpu does; Intel's integrated graphics have none of their own).
func drmFor(slot string) (string, uint64) {
	cards, _ := filepath.Glob("/sys/class/drm/card[0-9]")
	for _, c := range cards {
		dev, err := filepath.EvalSymlinks(c + "/device")
		if err != nil || filepath.Base(dev) != slot {
			continue
		}
		return filepath.Base(c), vram(dev)
	}
	return "", 0
}

func vram(dev string) uint64 {
	for _, f := range []string{"mem_info_vram_total", "mem_info_vis_vram_total"} {
		if v := readFile(dev + "/" + f); v != "" {
			n, _ := strconv.ParseUint(v, 10, 64)
			return n
		}
	}
	return 0
}

// deviceTreeName reads what a device-tree machine calls its graphics: the compatible
// string, tidied — "apple,agx-g13g" becomes "Apple agx-g13g".
func deviceTreeName(dev string) string {
	c := readFile(dev + "/of_node/compatible")
	if c == "" {
		return ""
	}
	c = strings.TrimRight(strings.Split(c, "\x00")[0], "\x00")
	maker, rest, ok := strings.Cut(c, ",")
	if !ok {
		return c
	}
	if maker != "" {
		maker = strings.ToUpper(maker[:1]) + maker[1:]
	}
	return strings.TrimSpace(maker + " " + rest)
}