mesh-controller/internal/inventory/secrets.go

package inventory

import (
	"context"
	"errors"
	"fmt"

	"github.com/jackc/pgx/v5"

	"github.com/novox/mesh-control/internal/secrets"
)

// Where sealed secrets live.
//
// The table holds nothing usable — see the migration and internal/secrets for why that is the
// design rather than an inconvenience.

// Secret is one provision's credential, sealed to each end.
type Secret struct {
	Name     string
	Consumer string
	// ConsumerModule is which module on that machine it is for.
	//
	// **Part of the key, not a label** (novox/hq 04-ISSUES/022). Two modules on one node wanting
	// the same provision are two consumers, and were one credential until this.
	ConsumerModule string
	Provider       string
	ForConsumer    string
	ForProvider    string
	ConsumerKey    string
	ProviderKey    string
}

// SecretFor is the credential one module uses for one provision, making it the first time.
//
// **Made once and kept**, rather than regenerated whenever it is asked for. A secret that changed
// on every declaration would restart both ends on every push and would mean the password a
// provider was told to create never matches the one a consumer was given — which is a mesh that
// reports success and cannot connect.
//
// **Remade when either end's sealing key changes.** A node that rejoined generated a new key and
// can no longer open what was sealed to the old one, so keeping the blob would deliver something
// unreadable for ever. The new secret reaches both ends in the same push, which is the only
// moment they can be changed together.
func (i *Inventory) SecretFor(ctx context.Context, name, consumer, consumerModule, provider string) (
	Secret, error) {
	consumerKey, err := i.SealingKeyOf(ctx, consumer)
	if err != nil {
		return Secret{}, err
	}
	providerKey, err := i.SealingKeyOf(ctx, provider)
	if err != nil {
		return Secret{}, err
	}

	consumerNode, err := i.NodeByName(ctx, consumer)
	if err != nil {
		return Secret{}, err
	}
	providerNode, err := i.NodeByName(ctx, provider)
	if err != nil {
		return Secret{}, err
	}

	var held Secret
	err = i.store.Pool().QueryRow(ctx,
		`select for_consumer, for_provider, consumer_key, provider_key from secret
		 where name = $1 and consumer = $2 and consumer_module = $3 and provider = $4`,
		name, consumerNode.ID, consumerModule, providerNode.ID).
		Scan(&held.ForConsumer, &held.ForProvider, &held.ConsumerKey, &held.ProviderKey)
	if err == nil && held.ConsumerKey == consumerKey && held.ProviderKey == providerKey {
		held.Name, held.Consumer, held.Provider = name, consumer, provider
		held.ConsumerModule = consumerModule
		return held, nil
	}

	made, err := secrets.Make(consumerKey, providerKey)
	if err != nil {
		return Secret{}, err
	}
	_, err = i.store.Pool().Exec(ctx,
		`insert into secret (name, consumer, consumer_module, provider, for_consumer, for_provider,
		                     consumer_key, provider_key)
		 values ($1, $2, $3, $4, $5, $6, $7, $8)
		 on conflict (name, consumer, consumer_module, provider) do update set
		   for_consumer = excluded.for_consumer, for_provider = excluded.for_provider,
		   consumer_key = excluded.consumer_key, provider_key = excluded.provider_key,
		   created_at = now()`,
		name, consumerNode.ID, consumerModule, providerNode.ID,
		made.ForConsumer, made.ForProvider, made.ConsumerKey, made.ProviderKey)
	if err != nil {
		return Secret{}, err
	}
	return Secret{Name: name, Consumer: consumer, ConsumerModule: consumerModule,
		Provider:    provider,
		ForConsumer: made.ForConsumer, ForProvider: made.ForProvider,
		ConsumerKey: made.ConsumerKey, ProviderKey: made.ProviderKey}, nil
}

// RotateSecret discards what was there, so the next declaration carries a new one.
//
// Only a delete. Nothing reads the old value first, because nothing can — and making the
// replacement here rather than on the next read would be a second path to the same act, which is
// how two ends come to hold different passwords.
//
// The new secret then reaches both ends on the same push, together, which is what makes rotation
// a single event rather than a fanout with a window where half the mesh holds a dead credential.
func (i *Inventory) RotateSecret(ctx context.Context, name, consumer, consumerModule, provider string) error {
	consumerNode, err := i.NodeByName(ctx, consumer)
	if err != nil {
		return err
	}
	providerNode, err := i.NodeByName(ctx, provider)
	if err != nil {
		return err
	}
	_, err = i.store.Pool().Exec(ctx,
		`delete from secret where name = $1 and consumer = $2 and consumer_module = $3
		   and provider = $4`,
		name, consumerNode.ID, consumerModule, providerNode.ID)
	return err
}

// SecretsFrom is every credential a provider node was issued, so it can be told what to create.
func (i *Inventory) SecretsFrom(ctx context.Context, provider string) ([]Secret, error) {
	providerNode, err := i.NodeByName(ctx, provider)
	if err != nil {
		return nil, err
	}
	rows, err := i.store.Pool().Query(ctx,
		`select s.name, c.name, s.consumer_module, s.for_provider from secret s
		 join node c on c.id = s.consumer
		 where s.provider = $1 order by s.name, c.name, s.consumer_module`, providerNode.ID)
	if err != nil {
		return nil, err
	}
	defer rows.Close()

	var out []Secret
	for rows.Next() {
		s := Secret{Provider: provider}
		if err := rows.Scan(&s.Name, &s.Consumer, &s.ConsumerModule, &s.ForProvider); err != nil {
			return nil, err
		}
		out = append(out, s)
	}
	return out, rows.Err()
}

// SecretForModule is a secret a module needs in order to be itself, on one machine.
//
// Not the credential a consumer is given: a superuser password is not *for* anybody. Made once
// and kept, because regenerating it on every declaration would change the password a running
// database has already been started with — and remade when the node's sealing key changes, for
// the same reason as everything else sealed here.
// ModuleSecretIfIssued is what a module already holds on a node, and nothing if it holds nothing.
//
// **The read half of SecretForModule**, which mints one when there is none — an insert, and a row
// lock, on a path that also serves questions. Composing a declaration to answer *is this machine
// running what I would send it* went through the minting version for every module on every node,
// so asking wrote to the database and blocked against the machine it was asking about.
//
// A module with no secret yet has never been sent one, which is the same answer the caller wanted
// anyway: this machine is not running what the mesh would send it.
func (i *Inventory) ModuleSecretIfIssued(
	ctx context.Context, node, module, name string,
) (string, bool, error) {
	key, err := i.SealingKeyOf(ctx, node)
	if err != nil || key == "" {
		return "", false, err
	}
	record, err := i.NodeByName(ctx, node)
	if err != nil {
		return "", false, err
	}
	var sealed, against, origin string
	err = i.store.Pool().QueryRow(ctx,
		`select sealed, node_key, origin from module_secret
		  where node = $1 and module = $2 and name = $3`,
		record.ID, module, name).Scan(&sealed, &against, &origin)
	if errors.Is(err, pgx.ErrNoRows) {
		return "", false, nil
	}
	if err != nil {
		return "", false, err
	}
	// Sealed to a key the node no longer has is not something it holds. Reported as absent rather
	// than as an error: this is the read, and refusing here would make a question fail for a
	// condition its writing counterpart is the right place to explain.
	if against != key {
		return "", false, nil
	}
	return sealed, true, nil
}

func (i *Inventory) SecretForModule(ctx context.Context, node, module, name string) (string, error) {
	key, err := i.SealingKeyOf(ctx, node)
	if err != nil {
		return "", err
	}
	if key == "" {
		return "", fmt.Errorf(
			"%s needs a secret and %s has no sealing key, so nothing can be sealed to it",
			module, node)
	}
	record, err := i.NodeByName(ctx, node)
	if err != nil {
		return "", err
	}

	var sealed, against, origin string
	err = i.store.Pool().QueryRow(ctx,
		`select sealed, node_key, origin from module_secret
		  where node = $1 and module = $2 and name = $3`,
		record.ID, module, name).Scan(&sealed, &against, &origin)
	if err == nil && against == key {
		return sealed, nil
	}
	if err == nil && origin == "accepted" {
		// Sealed to a key this node no longer has, and not the mesh's to invent again. Making one
		// would put 32 random bytes where a working credential was: the machine would apply it,
		// report success, and whatever reads it would fail to authenticate somewhere else
		// entirely — with the mesh insisting the secret was delivered, which it was.
		return "", fmt.Errorf(
			"%s on %s holds %q, which was given to the mesh rather than made by it, and %s has "+
				"since generated a new sealing key. The mesh cannot make another; issue it again",
			module, node, name, node)
	}

	made, err := secrets.Make(key, key)
	if err != nil {
		return "", err
	}
	// Sealed once, to one recipient. Make seals to two ends because a provision has two; here
	// both are the same machine, and only one copy is kept.
	if _, err := i.store.Pool().Exec(ctx,
		`insert into module_secret (node, module, name, sealed, node_key, origin)
		 values ($1, $2, $3, $4, $5, 'made')
		 on conflict (node, module, name) do update set
		   sealed = excluded.sealed, node_key = excluded.node_key,
		   origin = excluded.origin, made_at = now()`,
		record.ID, module, name, made.ForConsumer, key); err != nil {
		return "", err
	}
	return made.ForConsumer, nil
}

// AcceptSecretForModule keeps a value somebody supplied as a module's own secret.
//
// The counterpart to SecretForModule, which generates one. Some of what a module needs the mesh
// cannot invent: a broker account exists because the broker was told about it, and the password is
// whatever was agreed with the broker at that moment. The mesh's job is to carry it to the machine
// that will use it without being able to read it afterwards.
//
// Sealed on the way in and the plaintext discarded, exactly as a generated one is — so the only
// difference between the two is where the value came from.
func (i *Inventory) AcceptSecretForModule(ctx context.Context, node, module, name, value string) error {
	key, err := i.SealingKeyOf(ctx, node)
	if err != nil {
		return err
	}
	if key == "" {
		return fmt.Errorf(
			"%s has no sealing key, so nothing can be sealed to it — it joins again to get one",
			node)
	}
	record, err := i.NodeByName(ctx, node)
	if err != nil {
		return err
	}

	sealed, err := secrets.Accept(value, key, key)
	if err != nil {
		return err
	}
	_, err = i.store.Pool().Exec(ctx,
		`insert into module_secret (node, module, name, sealed, node_key, origin)
		 values ($1, $2, $3, $4, $5, 'accepted')
		 on conflict (node, module, name) do update set
		   sealed = excluded.sealed, node_key = excluded.node_key,
		   origin = excluded.origin, made_at = now()`,
		record.ID, module, name, sealed.ForConsumer, key)
	return err
}

// Holder is one end-to-end credential: who gets it and who must create it.
type Holder struct {
	Provision string
	Consumer  string
	// ConsumerModule is which module on that machine holds it. Part of what identifies a
	// credential (novox/hq 04-ISSUES/022), so rotating one consumer's does not touch another's.
	ConsumerModule string
	Provider       string
}

// HoldersOf is every pair sharing a credential for one provision.
//
// **The question rotation has to ask, and the one HAL could not.** There, a provision had a single
// shared credential and rotating it updated the provider's row; nothing enumerated who else held
// the old one, so three nodes carried dead credentials for two days and the mesh reported success
// (novox/hq ADR 0001). Here each pair has its own credential, and this is the list that makes
// "every consumer" a set the mesh can name rather than a hope.
//
// Empty consumer means all of them.
func (i *Inventory) HoldersOf(ctx context.Context, provision, consumer string) ([]Holder, error) {
	rows, err := i.store.Pool().Query(ctx,
		`select s.name, c.name, s.consumer_module, p.name from secret s
		   join node c on c.id = s.consumer
		   join node p on p.id = s.provider
		  where s.name = $1 and ($2 = '' or c.name = $2)
		  order by c.name, s.consumer_module, p.name`, provision, consumer)
	if err != nil {
		return nil, err
	}
	defer rows.Close()

	var out []Holder
	for rows.Next() {
		var h Holder
		if err := rows.Scan(&h.Provision, &h.Consumer, &h.ConsumerModule, &h.Provider); err != nil {
			return nil, err
		}
		out = append(out, h)
	}
	return out, rows.Err()
}