mesh-catalog/modules/pacman/cmd/pacman-tools/rollback.go

package main

// A rollback (novox/hq ADR 0508 §7; acceptance 1841/AC8): a node is returned to the record a run took, and says
// first what that would change. The plan compares the record's packages with the node's `installed` now: each
// package whose version differs, or that is gone since, is brought back to the record's version, from the node's
// package cache when it holds that file, else from the Arch Linux Archive's copy of that exact version, else from
// the archive's repository as it stood on the record's date. The packages installed since are listed, and are
// removed only when asked. A foreign package, in the record or now, is never in the plan (ADR 0507 §7).
//
// The archive keeps every version its repositories published, so a version is taken from it by its file's name,
// which needs the package's architecture: the architecture of any of the package's files in the cache, else of
// its installed version (the local database). A package whose architecture is not known on this machine is
// taken from the dated repository, where pacman finds it by name. Nothing is fetched to make the plan; a file
// the archive does not hold fails the transaction, which the run then says.
//
// With apply, pacman_rollback writes an ask; the node's keeper takes it (TakeAsk), makes the plan again on the
// node itself (its cache is the one that counts), and runs it as a run of kind rollback: one transaction started
// by the root helper with the plan in the request (RootActs.Rollback), `rollback.started` and
// `rollback.finished`, then the after-upgrade check against the record (Follow, checkAfter).

import (
	"encoding/json"
	"errors"
	"fmt"
	"path"
	"regexp"
	"sort"
	"strings"
	"time"

	stdio "git.novox.be/novox/mesh-sdk/go"
)

// ArchiveURL is the Arch Linux Archive.
const ArchiveURL = "https://archive.archlinux.org"

// SourceRemoved marks a plan item that removes a package installed since the record (to "" and no location):
// only when the rollback was asked to remove what the upgrade added.
const SourceRemoved = "removed"

// RollbackPlan is what a rollback to a run's record would change.
type RollbackPlan struct {
	Node string `json:"node"`
	Of   string `json:"of"`
	// RecordAt is when the record was taken; the dated repository is that day's.
	RecordAt time.Time `json:"record_at"`
	// Items brings each package back, or removes one installed since when RemoveAdded.
	Items []RollbackItem `json:"items"`
	// Added is the packages installed since the record, not foreign.
	Added       []PackageVersion `json:"added"`
	RemoveAdded bool             `json:"remove_added"`
	// Foreign is how many foreign packages the plan leaves untouched.
	Foreign int `json:"foreign_untouched"`
	// CacheRead says whether the node's package cache was read: only on the node itself.
	CacheRead bool `json:"cache_read"`
}

// cacheFile is `<name>-<version>-<arch>.pkg.tar.<ext>`; a name may hold dashes, a version and an arch none.
var cacheFile = regexp.MustCompile(`^(.+)-([^-]+-[^-]+)-([^-]+)\.pkg\.tar\.(zst|xz)$`)

// packageCache is the node's cache: by package name, by version, the file's path; and each name's arch.
type packageCache struct {
	files map[string]map[string]string
	arch  map[string]string
}

// readCache lists the cache's package files.
func (m *Machine) readCache() (packageCache, error) {
	c := packageCache{files: map[string]map[string]string{}, arch: map[string]string{}}
	out, err := m.Out("find", CacheDir, "-mindepth", "1", "-maxdepth", "1", "-name", "*.pkg.tar.*", "-printf", "%f\n")
	if err != nil {
		return c, err
	}
	for _, l := range lines(out) {
		f := cacheFile.FindStringSubmatch(strings.TrimSpace(l))
		if f == nil || !packageName.MatchString(f[1]) || !packageVersion.MatchString(f[2]) {
			continue
		}
		if c.files[f[1]] == nil {
			c.files[f[1]] = map[string]string{}
		}
		if _, ok := c.files[f[1]][f[2]]; !ok || f[4] == "zst" {
			c.files[f[1]][f[2]] = path.Join(CacheDir, f[0])
		}
		c.arch[f[1]] = f[3]
	}
	return c, nil
}

// installedArch is an installed package's architecture from the local database, or "".
func (m *Machine) installedArch(name, version string) string {
	desc, err := m.ReadFile(path.Join(PacmanDBDir, "local", name+"-"+version, "desc"))
	if err != nil {
		return ""
	}
	ls := strings.Split(string(desc), "\n")
	for i, l := range ls {
		if strings.TrimSpace(l) == "%ARCH%" && i+1 < len(ls) {
			if a := strings.TrimSpace(ls[i+1]); repoName.MatchString(a) {
				return a
			}
		}
	}
	return ""
}

// source is where a package's record version comes from.
func source(name, version, repo string, arch string, cache *packageCache, recordAt time.Time) (string, string) {
	if cache != nil {
		if p, ok := cache.files[name][version]; ok {
			return SourceCache, p
		}
	}
	if arch != "" {
		file := name + "-" + version + "-" + arch + ".pkg.tar.zst"
		return SourceArchive, ArchiveURL + "/packages/" + name[:1] + "/" + name + "/" + file
	}
	day := recordAt.UTC().Format("2006/01/02")
	return SourceRepository, ArchiveURL + "/repos/" + day + "/" + repo + "/os/$arch"
}

// keyGetter reads one key: a Bucket the keeper writes, or a StateReader a verb reads.
type keyGetter interface {
	Get(key string) (*stdio.StateEntry, error)
}

// PlanRollback is the plan for returning node to the record of run, from the states: `records.<node>.<run>` and
// `installed.<node>`, which must be current. local says this is the node itself, whose cache and local database
// are read.
func PlanRollback(m *Machine, installed, records keyGetter, node, run string, removeAdded, local bool) (RollbackPlan, error) {
	p := RollbackPlan{Node: node, Of: run, Items: []RollbackItem{}, Added: []PackageVersion{}, RemoveAdded: removeAdded}
	if e, err := installed.Get(NotCurrentKey(node)); err != nil {
		return p, err
	} else if e != nil {
		return p, fmt.Errorf("the packages of %s on the bus are not current: a plan from them would not be what is installed", node)
	}
	var rec Record
	if e, err := records.Get(NodeKey(node, run)); err != nil {
		return p, err
	} else if e == nil {
		return p, fmt.Errorf("%s has no record of run %s: it was never taken, or is older than record-days", node, run)
	} else if err := json.Unmarshal(e.Value, &rec); err != nil {
		return p, fmt.Errorf("the record of run %s is not readable: %w", run, err)
	}
	var now InstalledValue
	if e, err := installed.Get(node); err != nil {
		return p, err
	} else if e == nil {
		return p, fmt.Errorf("no packages of %s are on the bus", node)
	} else if err := json.Unmarshal(e.Value, &now); err != nil {
		return p, fmt.Errorf("installed.%s is not readable: %w", node, err)
	}
	p.RecordAt = rec.At
	var cache *packageCache
	if local {
		c, err := m.readCache()
		if err != nil {
			return p, fmt.Errorf("reading the package cache: %w", err)
		}
		cache, p.CacheRead = &c, true
	}
	foreign := map[string]bool{}
	nowBy := map[string]InstalledPackage{}
	for _, ip := range now.Packages {
		nowBy[ip.Name] = ip
		if ip.Repo == RepoForeign {
			foreign[ip.Name] = true
		}
	}
	recBy := map[string]InstalledPackage{}
	for _, ip := range rec.Installed.Packages {
		recBy[ip.Name] = ip
		if ip.Repo == RepoForeign {
			foreign[ip.Name] = true
		}
	}
	p.Foreign = len(foreign)
	for _, want := range rec.Installed.Packages {
		if foreign[want.Name] {
			continue
		}
		have, installedNow := nowBy[want.Name]
		if installedNow && have.Version == want.Version {
			continue
		}
		arch := ""
		if cache != nil {
			arch = cache.arch[want.Name]
		}
		if arch == "" && local && installedNow {
			arch = m.installedArch(have.Name, have.Version)
		}
		src, loc := source(want.Name, want.Version, want.Repo, arch, cache, rec.At)
		p.Items = append(p.Items, RollbackItem{Name: want.Name, From: have.Version, To: want.Version, Source: src, Location: loc})
	}
	for _, have := range now.Packages {
		if _, inRecord := recBy[have.Name]; inRecord || foreign[have.Name] {
			continue
		}
		p.Added = append(p.Added, PackageVersion{have.Name, have.Version})
		if removeAdded {
			p.Items = append(p.Items, RollbackItem{Name: have.Name, From: have.Version, Source: SourceRemoved})
		}
	}
	sort.Slice(p.Items, func(i, j int) bool { return p.Items[i].Name < p.Items[j].Name })
	return p, nil
}

// AskRollback writes an ask for a rollback of node to the record of run, for that node's keeper to take.
func AskRollback(asks Bucket, node, run string, removeAdded bool, now time.Time) (Ask, error) {
	a := Ask{ID: AskID(now), Node: node, Act: ActRollback, At: now.UTC(), Of: run, RemoveAdded: removeAdded}
	if _, err := asks.Create(NodeKey(node, a.ID), a); err != nil {
		return Ask{}, fmt.Errorf("writing the ask: %w", err)
	}
	return a, nil
}

// StartRollback runs a rollback's steps up to its transaction's start: the plan made again on the node, and the
// transaction started by the root helper with it. The end and the check follow as for an upgrade (Follow).
func (u *Upgrades) StartRollback(of string, removeAdded bool, ask string) (Run, error) {
	now := u.Machine.Now().UTC()
	r := &openRun{Run: Run{Node: u.Node, Run: RunID(now), Kind: RunRollback, From: FromAsk, Ask: ask, Of: of}}
	runs, err := u.ownRuns()
	if err != nil {
		return r.Run, err
	}
	for _, o := range runs {
		if o.Run.Run == r.Run.Run {
			return r.Run, fmt.Errorf("run %s of %s is there already: one run a second", o.Run.Run, u.Node)
		}
		if holdsTheDatabase(o.Run) {
			return r.Run, u.refuse(r, fmt.Sprintf("run %s is still going (its last step is %s): one run at a time", o.Run.Run, lastStep(o.Run)))
		}
	}
	if u.Machine.locked() {
		return r.Run, u.refuse(r, "another pacman holds "+DBLock+": a transaction is running, or one was killed and left its lock")
	}
	plan, err := PlanRollback(u.Machine, u.Installed, u.Records, u.Node, of, removeAdded, true)
	if err != nil {
		return r.Run, u.refuse(r, err.Error())
	}
	if len(plan.Items) == 0 {
		return r.Run, u.refuse(r, "the node's packages are those of the record already: there is nothing to bring back")
	}
	unit := TransactionUnit(RunRollback, r.Run.Run)
	if err := u.Root.Rollback(r.Run.Run, plan.Items); err != nil {
		return r.Run, u.end(r, Step{Step: StepFailed, At: u.Machine.Now().UTC(), Error: "the transaction could not be started: " + err.Error()})
	}
	if err := u.step(r, Step{Step: StepStarted, At: now, Unit: unit, Plan: plan.Items}); err != nil {
		return r.Run, err
	}
	return r.Run, u.emit(EventRollbackStarted, RollbackStarted{Node: u.Node, Run: r.Run.Run, Of: of, Unit: unit})
}

// takeRollback carries out an ask for a rollback; the ask is deleted once a run names it.
func (u *Upgrades) takeRollback(key string, a Ask) error {
	if a.Of == "" {
		return errors.Join(fmt.Errorf("ask %s names no run to return to", key), u.Asks.Delete(key))
	}
	r, err := u.StartRollback(a.Of, a.RemoveAdded, a.ID)
	if len(r.Steps) == 0 {
		return err
	}
	if derr := u.Asks.Delete(key); derr != nil {
		err = errors.Join(err, fmt.Errorf("deleting the ask %s: %w", key, derr))
	}
	return err
}

// Rollback is pacman_rollback: the plan, read from the bus (and on the node itself its cache), and with apply
// the ask that has the node's keeper carry it out.
func (m *Machine) Rollback(node, run string, removeAdded, apply bool) (map[string]any, error) {
	if node == "" {
		node = m.Node
	}
	if node == "" {
		return nil, errors.New("node is required: this bundle does not know its own")
	}
	if err := m.states(); err != nil {
		return nil, err
	}
	plan, err := PlanRollback(m, m.States(StateInstalled), m.States(StateRecords), node, run, removeAdded, node == m.Node)
	if err != nil {
		return nil, err
	}
	out := map[string]any{"plan": plan}
	if !apply {
		return out, nil
	}
	if len(plan.Items) == 0 {
		return nil, fmt.Errorf("the packages of %s are those of the record already: there is nothing to bring back", node)
	}
	a, err := AskRollback(upgradeState(StateAsks), node, run, removeAdded, m.Now())
	if err != nil {
		return nil, err
	}
	out["asked"] = a
	out["follow"] = "pacman_upgrades with node " + node + " lists the rollback run that names this ask; its keeper makes the plan again from its own cache"
	return out, nil
}