Compare commits

..

5 Commits

Author SHA1 Message Date
bcmmbaga
6d9543661f fix sonar 2026-08-14 19:39:54 +03:00
bcmmbaga
fab720db5f quote and escape the DSN written to .env 2026-08-14 19:35:19 +03:00
bcmmbaga
2f5d224150 reject a DSN the flow enricher cannot reach 2026-08-14 19:24:15 +03:00
bcmmbaga
1313bf7298 fix sonar lint 2026-08-14 19:16:57 +03:00
bcmmbaga
b56b82a069 detect existing Postgres during enterprise migration 2026-08-14 19:03:04 +03:00
15 changed files with 359 additions and 296 deletions

View File

@@ -204,9 +204,8 @@ func (a *Auth) foregroundGetTokenInfo(authClient *auth.Auth, urlOpener URLOpener
return nil, fmt.Errorf("failed to get OAuth flow: %v", err)
}
// An empty hint is deliberate, not a fallback: a fresh profile leaves the
// choice to the IdP. Switching accounts is done by switching or removing
// profiles, not by logging out — logout keeps the email.
// An empty hint is deliberate, not a fallback: a fresh or logged-out profile
// leaves the choice to the IdP, which is how accounts get switched.
if a.cfgPath != "" {
if hint := readProfileEmail(a.cfgPath); hint != "" {
if setter, ok := oAuthFlow.(loginHintSetter); ok {

View File

@@ -22,8 +22,7 @@ type Profile struct {
ID string
Name string
// Email is the account this profile last logged in with, "" if it never
// completed an SSO login. Kept across logouts; cleared when the profile is
// removed. See profile_state.go.
// completed an SSO login or was logged out. See profile_state.go.
Email string
IsActive bool
}
@@ -201,9 +200,11 @@ func (pm *ProfileManager) LogoutProfile(id string) error {
return fmt.Errorf("failed to save config: %w", err)
}
// The stored account email is kept on purpose, matching the desktop and CLI
// logout semantics: the next login passes it as the login_hint so the IdP
// preselects the account. Removing the profile is what deletes it.
// Not fatal: a stale hint costs an account switch, not the logout itself.
if err := removeProfileEmail(configPath); err != nil {
log.Warnf("failed to clear stored account email for profile %s: %v", id, err)
}
log.Infof("logged out from profile: %s", id)
return nil
}
@@ -223,24 +224,11 @@ func (pm *ProfileManager) RenameProfile(id string, newName string) error {
// RemoveProfile deletes a profile
func (pm *ProfileManager) RemoveProfile(id string) error {
configPath, err := pm.getProfileConfigPath(id)
if err != nil {
return err
}
// Use ServiceManager (removes profile from profiles/ directory)
if err := pm.serviceMgr.RemoveProfile(profilemanager.ID(id), androidUsername); err != nil {
return fmt.Errorf("failed to remove profile: %w", err)
}
// The account file is this package's, not the ServiceManager's, so it must
// go here. The default profile has a fixed filename, so a recreated one
// would otherwise inherit the deleted profile's email as its login_hint.
// Not fatal: the profile itself is gone.
if err := removeProfileEmail(configPath); err != nil {
log.Warnf("failed to remove stored account email for profile %s: %v", id, err)
}
log.Infof("removed profile: %s", id)
return nil
}

View File

@@ -90,10 +90,10 @@ func writeProfileEmail(configPath string, email string) error {
return nil
}
// removeProfileEmail drops the stored account email. Called on profile removal,
// not on logout: a logged-out profile keeps its email so the next login passes
// it as the login_hint, matching the desktop and CLI semantics. Mirrors the
// desktop UI's RemoveProfileState call.
// removeProfileEmail drops the stored account email. Called on logout: while the
// email is on disk it goes out as a login_hint, which would steer the next login
// straight back into the account just logged out of. Mirrors the desktop UI's
// RemoveProfileState call.
func removeProfileEmail(configPath string) error {
accountPath, err := profileAccountPathFor(configPath)
if err != nil {

View File

@@ -127,10 +127,10 @@ func TestWriteThenReadProfileEmail(t *testing.T) {
t.Fatalf("remove: %v", err)
}
if got := readProfileEmail(configPath); got != "" {
t.Errorf("expected no email after removal, got %q", got)
t.Errorf("expected no email after logout, got %q", got)
}
// Removal may run on a never-logged-in profile, so a second remove must pass.
// Logout may run on a never-logged-in profile, so a second remove must pass.
if err := removeProfileEmail(configPath); err != nil {
t.Fatalf("second remove should be a no-op: %v", err)
}

View File

@@ -87,10 +87,9 @@ func (pm *ProfileManager) SetActiveProfileState(state *ProfileState) error {
// RemoveProfileState deletes the per-profile state file (which holds the
// account email used for the SSO login hint and the UI display). Called after
// profile removal; logout keeps the file so the next login can pass the email
// as the login_hint. The state file only stores the email, so deleting it is
// equivalent to clearing it; the next SSO login recreates it. A missing file
// is not an error.
// a successful logout so a logged-out profile no longer shows a stale account
// email. The state file only stores the email, so deleting it is equivalent to
// clearing it; the next SSO login recreates it. A missing file is not an error.
func (pm *ProfileManager) RemoveProfileState(profileName string) error {
configDir, err := getConfigDir()
if err != nil {

View File

@@ -1,82 +0,0 @@
//go:build windows
package systemops
import (
"math"
"testing"
"github.com/stretchr/testify/assert"
)
func TestSortRouteCandidates(t *testing.T) {
tests := []struct {
name string
candidates []candidateRoute
wantOrder []uint32
}{
{
name: "longest prefix wins over metrics",
candidates: []candidateRoute{
{interfaceIndex: 1, prefixLength: 0, routeMetric: 0, interfaceMetric: 5},
{interfaceIndex: 2, prefixLength: 24, routeMetric: 100, interfaceMetric: 50},
},
wantOrder: []uint32{2, 1},
},
{
// Windows ranks equal-length prefixes by route metric + interface metric,
// so a higher route metric on a low metric interface can still win.
name: "combined metric beats route metric alone",
candidates: []candidateRoute{
{interfaceIndex: 8, prefixLength: 0, routeMetric: 0, interfaceMetric: 100},
{interfaceIndex: 5, prefixLength: 0, routeMetric: 10, interfaceMetric: 5},
},
wantOrder: []uint32{5, 8},
},
{
name: "lower combined metric wins",
candidates: []candidateRoute{
{interfaceIndex: 5, prefixLength: 0, routeMetric: 300, interfaceMetric: 5},
{interfaceIndex: 8, prefixLength: 0, routeMetric: 0, interfaceMetric: 100},
},
wantOrder: []uint32{8, 5},
},
{
name: "equal combined metric falls back to route metric",
candidates: []candidateRoute{
{interfaceIndex: 1, prefixLength: 0, routeMetric: 20, interfaceMetric: 10},
{interfaceIndex: 2, prefixLength: 0, routeMetric: 5, interfaceMetric: 25},
},
wantOrder: []uint32{2, 1},
},
{
// The metrics are uint32 on the Windows side, so the sum must not wrap.
name: "combined metric beyond the uint32 range",
candidates: []candidateRoute{
{interfaceIndex: 1, prefixLength: 0, routeMetric: math.MaxUint32, interfaceMetric: 5},
{interfaceIndex: 2, prefixLength: 0, routeMetric: math.MaxUint32 - 10, interfaceMetric: 5},
},
wantOrder: []uint32{2, 1},
},
{
name: "unknown interface metric ranks on route metric only",
candidates: []candidateRoute{
{interfaceIndex: 1, prefixLength: 0, routeMetric: 30, interfaceMetric: -1},
{interfaceIndex: 2, prefixLength: 0, routeMetric: 5, interfaceMetric: 10},
},
wantOrder: []uint32{2, 1},
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
sortRouteCandidates(tt.candidates)
got := make([]uint32, 0, len(tt.candidates))
for _, c := range tt.candidates {
got = append(got, c.interfaceIndex)
}
assert.Equal(t, tt.wantOrder, got)
})
}
}

View File

@@ -882,40 +882,26 @@ func getInterfaceMetric(interfaceIndex uint32, family int16) int {
return int(ipInterfaceRow.Metric)
}
// sortRouteCandidates sorts route candidates by priority: prefix length -> combined metric -> route metric.
// Windows prefers the longest matching prefix and, among prefixes of the same length, the lowest metric, see
// https://learn.microsoft.com/en-us/windows-hardware/customize/desktop/unattend/microsoft-windows-tcpip-interfaces-interface-routes-route-metric
// sortRouteCandidates sorts route candidates by priority: prefix length -> route metric -> interface metric
func sortRouteCandidates(candidates []candidateRoute) {
sort.Slice(candidates, func(i, j int) bool {
if candidates[i].prefixLength != candidates[j].prefixLength {
return candidates[i].prefixLength > candidates[j].prefixLength
}
mi, mj := combinedMetric(candidates[i]), combinedMetric(candidates[j])
if mi != mj {
return mi < mj
if candidates[i].routeMetric != candidates[j].routeMetric {
return candidates[i].routeMetric < candidates[j].routeMetric
}
return candidates[i].routeMetric < candidates[j].routeMetric
return candidates[i].interfaceMetric < candidates[j].interfaceMetric
})
}
// combinedMetric returns the effective metric Windows uses to rank routes with an equal prefix length:
// the sum of the route metric and the metric of the interface the route is on, see
// https://learn.microsoft.com/en-us/windows-server/networking/technologies/network-subsystem/net-sub-interface-metric
// An unknown interface metric contributes nothing.
func combinedMetric(candidate candidateRoute) uint64 {
if candidate.interfaceMetric < 0 {
return uint64(candidate.routeMetric)
}
return uint64(candidate.routeMetric) + uint64(candidate.interfaceMetric)
}
// GetBestInterface finds the best interface for reaching a destination,
// excluding the VPN interface to avoid routing loops.
//
// Route selection priority:
// 1. Longest prefix match (most specific route)
// 2. Lowest combined metric (route metric + interface metric)
// 3. Lowest route metric.
// 2. Lowest route metric
// 3. Lowest interface metric
func GetBestInterface(dest netip.Addr, vpnIntf string) (*net.Interface, error) {
var skipInterfaceIndex int
if vpnIntf != "" {
@@ -939,6 +925,7 @@ func GetBestInterface(dest netip.Addr, vpnIntf string) (*net.Interface, error) {
return nil, fmt.Errorf("no route to %s", dest)
}
// Sort routes: prefix length -> route metric -> interface metric
sortRouteCandidates(candidates)
for _, candidate := range candidates {

View File

@@ -5,7 +5,6 @@ package systemops
import (
"errors"
"net"
"net/netip"
"syscall"
"testing"
@@ -30,7 +29,6 @@ func ensureIPv6DefaultRoute(t *testing.T) {
}
if err := netlink.RouteAdd(route); err != nil {
if errors.Is(err, syscall.EEXIST) {
requireUsableIPv6Nexthop(t)
return
}
t.Skipf("install IPv6 fallback default route: %v", err)
@@ -40,36 +38,4 @@ func ensureIPv6DefaultRoute(t *testing.T) {
t.Logf("delete IPv6 fallback default route: %v", err)
}
})
requireUsableIPv6Nexthop(t)
}
// requireUsableIPv6Nexthop skips the test unless the resolved IPv6 default
// nexthop can actually carry a route. Installing the default route succeeding
// does not imply the kernel accepts it as a nexthop for a concrete prefix.
func requireUsableIPv6Nexthop(t *testing.T) {
t.Helper()
nexthop, err := GetNextHop(netip.IPv6Unspecified())
if err != nil {
t.Skipf("resolve IPv6 default nexthop: %v", err)
}
probe := &netlink.Route{
Scope: netlink.SCOPE_UNIVERSE,
Table: syscall.RT_TABLE_MAIN,
Family: netlink.FAMILY_V6,
Dst: &net.IPNet{IP: net.ParseIP("100::64"), Mask: net.CIDRMask(128, 128)},
}
require.NoError(t, addNextHop(nexthop, probe), "build IPv6 probe route")
switch err := netlink.RouteAdd(probe); {
case err == nil:
if err := netlink.RouteDel(probe); err != nil && !errors.Is(err, syscall.ESRCH) {
t.Logf("delete IPv6 probe route: %v", err)
}
case errors.Is(err, syscall.EEXIST):
default:
t.Skipf("IPv6 nexthop %s unusable for route installation: %v", nexthop, err)
}
}

View File

@@ -6,11 +6,9 @@ import (
"context"
"time"
log "github.com/sirupsen/logrus"
"google.golang.org/grpc/codes"
gstatus "google.golang.org/grpc/status"
"github.com/netbirdio/netbird/client/internal/profilemanager"
"github.com/netbirdio/netbird/client/proto"
)
@@ -62,19 +60,9 @@ func (s *Session) RequestExtend(ctx context.Context, p ExtendStartParams) (Exten
// a request from the UI implies a graphical session, which the daemon cannot detect itself
req := &proto.RequestExtendAuthSessionRequest{HasGraphicalSession: true}
hint := p.Hint
if hint == "" {
pm := profilemanager.NewProfileManager()
if active, perr := pm.GetActiveProfile(); perr != nil {
log.Debugf("failed to get active profile for login hint: %v", perr)
} else if state, serr := pm.GetProfileState(active.ID); serr != nil {
log.Debugf("failed to get profile state for login hint: %v", serr)
} else {
hint = state.Email
}
}
if hint != "" {
req.Hint = &hint
if p.Hint != "" {
h := p.Hint
req.Hint = &h
}
resp, err := cli.RequestExtendAuthSession(ctx, req)

View File

@@ -123,16 +123,8 @@ func (s *Connection) Login(ctx context.Context, p LoginParams) (LoginResult, err
if p.PreSharedKey != "" {
req.OptionalPreSharedKey = ptrStr(p.PreSharedKey)
}
hint := p.Hint
if hint == "" && profileID != "" {
if state, serr := profilemanager.NewProfileManager().GetProfileState(profilemanager.ID(profileID)); serr == nil {
hint = state.Email
} else {
log.Debugf("failed to get profile state for login hint: %v", serr)
}
}
if hint != "" {
req.Hint = ptrStr(hint)
if p.Hint != "" {
req.Hint = ptrStr(p.Hint)
}
resp, err := cli.Login(ctx, req)
@@ -236,6 +228,16 @@ func (s *Connection) Logout(ctx context.Context, p LogoutParams) error {
return s.classifyDaemonError(err)
}
// The daemon runs as root and can't reach the user-owned per-profile state
// file holding the account email (see Profiles.List), so clear the stale
// email here; the next SSO login recreates it.
if p.ProfileName != "" {
if err := profilemanager.NewProfileManager().RemoveProfileState(p.ProfileName); err != nil {
// Non-fatal: the logout itself succeeded.
log.Warnf("failed to remove profile state for %s: %v", p.ProfileName, err)
}
}
return nil
}
@@ -259,7 +261,7 @@ func (s *Connection) waitSSOLogin(ctx context.Context, p WaitSSOParams) (string,
// Persist the account email the same way the CLI does after its own
// WaitSSOLogin: the daemon returns it but cannot store it, since it runs as
// root and the per-profile state file is user-owned (see Profiles.List).
// root and the per-profile state file is user-owned (see Logout below).
// Without this the profile has no email, so Profiles.List shows no account
// and later logins and session extends go out without a login_hint —
// leaving the IdP to guess which account was meant.

View File

@@ -162,9 +162,8 @@ func (s *Profiles) Remove(ctx context.Context, p ProfileRef) error {
}
// The daemon deletes what it owns but runs as root, so it leaves the
// user-owned state file holding the account email behind. Logout keeps the
// email on purpose so later logins can pass it as the login_hint; profile
// removal is what deletes it. Legacy profiles are keyed by name rather than by a
// user-owned state file holding the account email behind (same split as
// Connection.Logout). Legacy profiles are keyed by name rather than by a
// generated ID, so a recreated profile of the same name would inherit the
// deleted one's email and offer it as the login_hint.
//

View File

@@ -15,6 +15,12 @@ set -o pipefail
# 2. Postgres migration — add Postgres, migrate SQLite data via migrate-store.
# 3. Traffic flow — add NATS + flow-enricher + flow-receiver.
#
# Step 2 is skipped when the deployment already runs on Postgres
# (server.store.engine: postgres in config.yaml). Nothing is provisioned or
# migrated in that case and the store config is left exactly as the operator
# wrote it — the enterprise image reads the same Postgres the community image
# did. Such a deployment gets the image swap, and can still opt into step 3.
#
# If any step fails once the stack has been touched, the script rolls itself
# back automatically: generated files are removed, the Postgres volume this run
# created is dropped, and the original deployment is started again.
@@ -38,6 +44,18 @@ ENV_BACKUP=""
PG_VOLUME_NAME=""
BACKUP_DIR=""
# Store state. STORE_ENGINE is what the deployment runs on today; when it is
# already postgres, MIGRATE_POSTGRES stays "no" and nothing is provisioned.
# POSTGRES_SERVICE is empty when Postgres lives outside this compose project.
STORE_ENGINE=""
EXISTING_POSTGRES="no"
POSTGRES_DSN=""
POSTGRES_SERVICE=""
POSTGRES_DEPENDS_CONDITION="service_healthy"
# Whether this run needs to generate config.yaml.enterprise at all. A pure
# image swap does not.
ENTERPRISE_CONFIG="no"
NETBIRD_EULA_URL="https://netbird.io/self-hosted-EULA"
check_docker_compose() {
@@ -192,6 +210,85 @@ detect_exposed_address() {
yq eval '.server.exposedAddress // ""' "$CONFIG_YAML_HOST"
}
# The engine is a config.yaml-only setting — there is no env override for it
# (combined/cmd/root.go reads it from YAML and derives the env vars), so
# config.yaml is authoritative. Absent means the sqlite default.
detect_store_engine() {
local engine
engine=$(yq eval '.server.store.engine // ""' "$CONFIG_YAML_HOST")
if [[ -z "$engine" ]] || [[ "$engine" == "null" ]]; then
engine="sqlite"
fi
echo "$engine" | tr '[:upper:]' '[:lower:]'
}
detect_store_dsn() {
yq eval '.server.store.dsn // ""' "$CONFIG_YAML_HOST"
}
# config.yaml is where a combined deployment carries its DSN; this only covers
# hand-rolled installs that keep it in the environment instead.
detect_store_dsn_from_compose() {
# `compose config` re-escapes a literal $ as $$ on the way out, so undo that
# to get the value the container actually receives.
$DOCKER_COMPOSE_COMMAND config 2>/dev/null | yq eval "
.services[\"$COMBINED_SERVICE\"].environment.NB_STORE_ENGINE_POSTGRES_DSN //
.services[\"$COMBINED_SERVICE\"].environment.NETBIRD_STORE_ENGINE_POSTGRES_DSN // \"\"
" - 2>/dev/null | sed 's/\$\$/$/g'
}
# Reads either DSN form: "host=db ..." or "postgres://user:pass@db:5432/name".
dsn_host() {
local dsn="$1"
case "$dsn" in
*://*) printf '%s' "$dsn" | sed -n 's,^[a-zA-Z+]*://\([^/?]*\).*,\1,p' | sed -e 's,.*@,,' -e 's,:.*,,' ;;
*) printf '%s' "$dsn" | sed -n 's/.*[[:space:]]*host=\([^[:space:]]*\).*/\1/p' ;;
esac
}
# flow-enricher is its own container, so a loopback host or a socket path would
# reach the enricher rather than Postgres. Only flag hosts we can positively
# identify — an unparseable DSN must not leave the operator with no way forward.
dsn_host_reachable() {
local dsn="$1"
case "$(dsn_host "$dsn")" in
localhost | 127.* | ::1 | 0.0.0.0 | /*) return 1 ;;
*) return 0 ;;
esac
}
# Names the compose service running this deployment's Postgres, for depends_on.
# Empty means external — the DSN host matched no service. A DSN with no readable
# host falls back to matching on image.
detect_postgres_service() {
local host
host=$(dsn_host "$POSTGRES_DSN")
if [[ -n "$host" ]]; then
if [[ "$(host="$host" yq eval '.services | has(env(host))' "$COMPOSE_FILE" 2>/dev/null)" == "true" ]]; then
echo "$host"
fi
return
fi
yq eval '.services | to_entries | map(select(.value.image // "" | test("(^|/)(postgres|postgis|pgvector|timescaledb)(:|@|$)"))) | .[0].key // ""' "$COMPOSE_FILE"
}
# depends_on: service_healthy is only legal if the service defines a healthcheck.
detect_postgres_depends_condition() {
local tag
tag=$(yq eval ".services[\"$POSTGRES_SERVICE\"].healthcheck | tag" "$COMPOSE_FILE" 2>/dev/null)
if [[ "$tag" == "!!map" ]]; then
echo "service_healthy"
else
echo "service_started"
fi
}
env_value() {
local value="$1"
value=$(printf '%s' "$value" | sed -e 's/\\/\\\\/g' -e 's/"/\\"/g' -e 's/\$/$$/g')
printf '"%s"' "$value"
}
detect_compose_network() {
local tag
tag=$(yq eval ".services[\"$COMBINED_SERVICE\"].networks | tag" "$COMPOSE_FILE" 2>/dev/null)
@@ -231,16 +328,30 @@ services:
NETBIRD_LICENSE_SERVER_BASE_URL: \${NETBIRD_LICENSE_SERVER_BASE_URL}
EOF
# An existing Postgres is already wired up by the operator's own compose file,
# so only a Postgres this run creates needs a depends_on.
if [[ "$MIGRATE_POSTGRES" == "yes" ]]; then
cat <<EOF
depends_on:
postgres:
condition: service_healthy
${POSTGRES_SERVICE}:
condition: ${POSTGRES_DEPENDS_CONDITION}
EOF
fi
# The server is only pointed at a different config file when this run
# generates one. A pure image swap leaves it on its original config.yaml.
if [[ "$ENTERPRISE_CONFIG" == "yes" ]]; then
cat <<EOF
volumes:
- ./${ENTERPRISE_CONFIG_FILE}:/etc/netbird/config.yaml.enterprise:ro
command: ["--config", "/etc/netbird/config.yaml.enterprise"]
EOF
fi
postgres:
if [[ "$MIGRATE_POSTGRES" == "yes" ]]; then
cat <<EOF
${POSTGRES_SERVICE}:
image: postgres:17
container_name: netbird-postgres
restart: unless-stopped
@@ -260,6 +371,14 @@ EOF
fi
if [[ "$ENABLE_FLOW" == "yes" ]]; then
# Nothing to wait on when Postgres is managed outside this compose project.
local enricher_depends=""
if [[ -n "$POSTGRES_SERVICE" ]]; then
enricher_depends="
${POSTGRES_SERVICE}:
condition: ${POSTGRES_DEPENDS_CONDITION}"
fi
cat <<EOF
nats:
@@ -276,9 +395,7 @@ EOF
container_name: netbird-flow-enricher
restart: unless-stopped
networks: [${COMPOSE_NETWORK}]
depends_on:
postgres:
condition: service_healthy
depends_on:${enricher_depends}
nats:
condition: service_started
environment:
@@ -286,10 +403,10 @@ EOF
NETBIRD_LICENSE_SERVER_BASE_URL: \${NETBIRD_LICENSE_SERVER_BASE_URL}
NB_DATADIR: /var/lib/netbird
NB_MANAGEMENT_STORE_ENGINE: postgres
NB_MANAGEMENT_POSTGRES_DSN: "host=postgres user=netbird password=\${POSTGRES_PASSWORD} dbname=netbird port=5432 sslmode=disable"
NB_STORE_ENGINE_POSTGRES_DSN: "host=postgres user=netbird password=\${POSTGRES_PASSWORD} dbname=netbird port=5432 sslmode=disable"
NB_MANAGEMENT_POSTGRES_DSN: \${NB_ENTERPRISE_POSTGRES_DSN}
NB_STORE_ENGINE_POSTGRES_DSN: \${NB_ENTERPRISE_POSTGRES_DSN}
NB_TRAFFIC_EVENT_STORE_ENGINE: postgres
NB_TRAFFIC_EVENT_POSTGRES_DSN: "host=postgres user=netbird password=\${POSTGRES_PASSWORD} dbname=netbird port=5432 sslmode=disable"
NB_TRAFFIC_EVENT_POSTGRES_DSN: \${NB_ENTERPRISE_POSTGRES_DSN}
NB_MANAGEMENT_STORE_KEY: \${NETBIRD_ENCRYPTION_KEY}
NB_FLOW_ADAPTER_TYPE: nats
NB_FLOW_NATS_ENDPOINTS: nats://nats:4222
@@ -346,27 +463,41 @@ EOF
fi
}
# Build config.yaml.enterprise by yq-editing the operator's existing
# config.yaml. We don't touch the original file.
# Build config.yaml.enterprise from the operator's existing config.yaml. We
# don't touch the original file. Values go through strenv() so a DSN carrying
# quotes, backslashes or $ cannot break out of the expression.
render_enterprise_config() {
local pg_dsn="host=postgres user=netbird password=${POSTGRES_PASSWORD} dbname=netbird port=5432 sslmode=disable"
{
echo "# Generated by migrate-to-enterprise.sh from ${CONFIG_YAML_HOST}."
echo "# The enterprise server is started with --config pointing at this file,"
echo "# so later edits to ${CONFIG_YAML_HOST} have no effect until copied here."
cat "$CONFIG_YAML_HOST"
} > "$ENTERPRISE_CONFIG_FILE"
yq eval "
.server.store.engine = \"postgres\" |
.server.store.dsn = \"$pg_dsn\" |
.server.activityStore.engine = \"postgres\" |
.server.activityStore.dsn = \"$pg_dsn\" |
.server.authStore.engine = \"postgres\" |
.server.authStore.dsn = \"$pg_dsn\"
" "$CONFIG_YAML_HOST" > "$ENTERPRISE_CONFIG_FILE"
if [[ "$MIGRATE_POSTGRES" == "yes" ]]; then
# Fresh Postgres: point every store section at it. migrate-store carries the
# SQLite contents across.
POSTGRES_DSN="$POSTGRES_DSN" yq eval -i '
.server.store.engine = "postgres" |
.server.store.dsn = strenv(POSTGRES_DSN) |
.server.activityStore.engine = "postgres" |
.server.activityStore.dsn = strenv(POSTGRES_DSN) |
.server.authStore.engine = "postgres" |
.server.authStore.dsn = strenv(POSTGRES_DSN)
' "$ENTERPRISE_CONFIG_FILE"
fi
# Otherwise the store config is the operator's and stays untouched.
# activityStore and authStore do not inherit from server.store — each falls
# back to its own SQLite file under dataDir — so repointing them at Postgres
# here would silently strand the existing audit log and the embedded IdP's
# users, with no migrate-store run to carry them over.
if [[ "$ENABLE_FLOW" == "yes" ]]; then
local flow_addr="${NETBIRD_DOMAIN}"
yq eval -i "
NETBIRD_DOMAIN="$NETBIRD_DOMAIN" yq eval -i '
.server.trafficFlow.enabled = true |
.server.trafficFlow.address = \"$flow_addr\" |
.server.trafficFlow.interval = \"60s\"
" "$ENTERPRISE_CONFIG_FILE"
.server.trafficFlow.address = strenv(NETBIRD_DOMAIN) |
.server.trafficFlow.interval = "60s"
' "$ENTERPRISE_CONFIG_FILE"
fi
}
@@ -633,6 +764,91 @@ on_exit() {
# Main
# ---------------------------------------------------------------------------
# Already on Postgres: there is nothing to provision and nothing to migrate.
# The enterprise image reads the very same store config the community image
# did, so step 2 collapses to a no-op and the run is a plain image swap.
configure_existing_postgres() {
EXISTING_POSTGRES="yes"
MIGRATE_POSTGRES="no"
# DSN first — detect_postgres_service prefers the host it names.
POSTGRES_DSN=$(detect_store_dsn)
if [[ -z "$POSTGRES_DSN" ]] || [[ "$POSTGRES_DSN" == "null" ]]; then
POSTGRES_DSN=$(detect_store_dsn_from_compose)
fi
if [[ "$POSTGRES_DSN" == "null" ]]; then
POSTGRES_DSN=""
fi
POSTGRES_SERVICE=$(detect_postgres_service)
if [[ -n "$POSTGRES_SERVICE" ]]; then
POSTGRES_DEPENDS_CONDITION=$(detect_postgres_depends_condition)
fi
echo "Step 2: Postgres migration not needed — this deployment already runs on"
echo " Postgres. Its store configuration is reused as-is and left"
echo " untouched; no database is created and no data is moved."
if [[ -n "$POSTGRES_SERVICE" ]]; then
echo " Postgres service: $POSTGRES_SERVICE (in $COMPOSE_FILE)"
else
echo " Postgres service: managed outside $COMPOSE_FILE"
fi
}
configure_sqlite_store() {
MIGRATE_POSTGRES=$(read_yes_no "Step 2: Migrate storage from SQLite to Postgres? (recommended)" "n")
[[ "$MIGRATE_POSTGRES" == "yes" ]] || return 0
# The override would otherwise merge into a service of the same name and
# quietly rewrite its image and credentials.
local existing
existing=$(yq eval '.services | has("postgres")' "$COMPOSE_FILE")
if [[ "$existing" == "true" ]]; then
echo "" > /dev/stderr
echo "$COMPOSE_FILE already defines a service named 'postgres', but config.yaml" > /dev/stderr
echo "still has server.store.engine: sqlite. This script would add its own" > /dev/stderr
echo "'postgres' service and Compose would merge the two." > /dev/stderr
echo "" > /dev/stderr
echo "Point server.store.engine at that Postgres yourself, or rename the service," > /dev/stderr
echo "then re-run." > /dev/stderr
exit 1
fi
echo ""
echo " ⚠ Data will be migrated from SQLite to Postgres. The SQLite store"
echo " will be backed up automatically. To fully revert later, restore"
echo " that backup and delete docker-compose.override.yml +"
echo " config.yaml.enterprise."
local confirm
confirm=$(read_yes_no " Continue?" "y")
if [[ "$confirm" != "yes" ]]; then
MIGRATE_POSTGRES="no"
echo " Skipping Postgres migration."
return 0
fi
POSTGRES_PASSWORD=$(rand_password)
POSTGRES_SERVICE="postgres"
POSTGRES_DEPENDS_CONDITION="service_healthy"
POSTGRES_DSN="host=postgres user=netbird password=${POSTGRES_PASSWORD} dbname=netbird port=5432 sslmode=disable"
}
# mysql, or something this script has never seen. Swapping the images is still
# valid; touching the store is not.
configure_unsupported_store() {
MIGRATE_POSTGRES="no"
echo " ⚠ server.store.engine is '$STORE_ENGINE'. This script only migrates"
echo " SQLite to Postgres, and traffic flow requires Postgres, so both are"
echo " unavailable here. The store configuration will be left untouched."
echo ""
local proceed
proceed=$(read_yes_no "Step 2 skipped. Continue with the image swap only?" "n")
if [[ "$proceed" != "yes" ]]; then
echo "Aborted."
exit 0
fi
}
init_migration() {
DOCKER_COMPOSE_COMMAND=$(check_docker_compose)
check_yq
@@ -682,12 +898,15 @@ init_migration() {
exit 1
fi
STORE_ENGINE=$(detect_store_engine)
echo "Detected existing deployment:"
echo " Combined service: $COMBINED_SERVICE"
echo " Dashboard: $DASHBOARD_SERVICE"
echo " config.yaml: $CONFIG_YAML_HOST"
echo " Data volume: $DATA_VOLUME"
echo " Network: $COMPOSE_NETWORK"
echo " Store engine: $STORE_ENGINE"
echo ""
require_eula_acceptance
@@ -706,28 +925,17 @@ init_migration() {
echo "Step 1: Image swap (community → Enterprise). License key required."
NB_LICENSE_KEY=$(read_secret " License key")
# Step 2 — optional
# Step 2 — what this does depends on what the deployment already stores in.
echo ""
MIGRATE_POSTGRES=$(read_yes_no "Step 2: Migrate storage from SQLite to Postgres? (recommended)" "n")
if [[ "$MIGRATE_POSTGRES" == "yes" ]]; then
echo ""
echo " ⚠ Data will be migrated from SQLite to Postgres. The SQLite store"
echo " will be backed up automatically. To fully revert later, restore"
echo " that backup and delete docker-compose.override.yml +"
echo " config.yaml.enterprise."
local confirm
confirm=$(read_yes_no " Continue?" "y")
if [[ "$confirm" != "yes" ]]; then
MIGRATE_POSTGRES="no"
echo " Skipping Postgres migration."
else
POSTGRES_PASSWORD=$(rand_password)
fi
fi
case "$STORE_ENGINE" in
postgres) configure_existing_postgres ;;
sqlite) configure_sqlite_store ;;
*) configure_unsupported_store ;;
esac
# Step 3 — optional, only if Postgres is on (flow requires Postgres)
echo ""
if [[ "$MIGRATE_POSTGRES" == "yes" ]]; then
if [[ "$MIGRATE_POSTGRES" == "yes" ]] || [[ "$EXISTING_POSTGRES" == "yes" ]]; then
ENABLE_FLOW=$(read_yes_no "Step 3: Enable traffic flow? (requires Postgres)" "n")
if [[ "$ENABLE_FLOW" == "yes" ]]; then
# Auth secret MUST match server.authSecret from config.yaml
@@ -751,12 +959,43 @@ init_migration() {
echo "Could not read server.store.encryptionKey from $CONFIG_YAML_HOST." > /dev/stderr
exit 1
fi
# flow-enricher talks to Postgres directly, so this is the one place an
# existing deployment's DSN is actually needed — and the one place a host
# that only works from inside the server container shows up.
while :; do
local dsn_problem=""
if [[ -z "$POSTGRES_DSN" ]]; then
dsn_problem="No DSN could be read from $CONFIG_YAML_HOST or from the $COMBINED_SERVICE environment."
elif ! dsn_host_reachable "$POSTGRES_DSN"; then
dsn_problem="Its host '$(dsn_host "$POSTGRES_DSN")' only resolves inside the server container."
fi
[[ -n "$dsn_problem" ]] || break
echo ""
echo " The flow enricher reaches Postgres from a container of its own."
echo " $dsn_problem"
echo " Enter a DSN reachable from other containers, or press Ctrl-C to abort."
POSTGRES_DSN=$(read_required " Postgres DSN (host=… user=… password=… dbname=… port=5432 sslmode=disable)")
done
# A DSN entered above names a different host, which decides what to wait on.
POSTGRES_SERVICE=$(detect_postgres_service)
if [[ -n "$POSTGRES_SERVICE" ]]; then
POSTGRES_DEPENDS_CONDITION=$(detect_postgres_depends_condition)
fi
fi
else
ENABLE_FLOW="no"
echo "Step 3 (traffic flow) skipped — requires Postgres."
fi
# config.yaml.enterprise only exists to hold changes; without any there is
# nothing to generate and the server keeps running on its own config.yaml.
if [[ "$MIGRATE_POSTGRES" == "yes" ]] || [[ "$ENABLE_FLOW" == "yes" ]]; then
ENTERPRISE_CONFIG="yes"
fi
check_data_directory
check_stale_postgres_volume
}
@@ -774,7 +1013,7 @@ apply_changes() {
sed -i.bak '/NETBIRD_LICENSE_SERVER_BASE_URL/d' "$OVERRIDE_FILE" && rm -f "$OVERRIDE_FILE.bak"
fi
if [[ "$MIGRATE_POSTGRES" == "yes" ]]; then
if [[ "$ENTERPRISE_CONFIG" == "yes" ]]; then
echo "Writing $ENTERPRISE_CONFIG_FILE ..."
install -m 600 /dev/null "$ENTERPRISE_CONFIG_FILE"
render_enterprise_config
@@ -810,6 +1049,9 @@ apply_changes() {
echo "POSTGRES_PASSWORD=${POSTGRES_PASSWORD}"
fi
if [[ "$ENABLE_FLOW" == "yes" ]]; then
# Own variable name rather than NB_STORE_ENGINE_POSTGRES_DSN so that a
# deployment already setting that one keeps its own value.
echo "NB_ENTERPRISE_POSTGRES_DSN=$(env_value "$POSTGRES_DSN")"
echo "NB_FLOW_AUTH_SECRET=${NB_FLOW_AUTH_SECRET}"
echo "NETBIRD_ENCRYPTION_KEY=${NETBIRD_ENCRYPTION_KEY}"
fi
@@ -871,14 +1113,19 @@ print_summary() {
echo " Summary"
echo "──────────────────────────────────────────────────────────────────────"
echo " Images: swapped to enterprise"
[[ "$MIGRATE_POSTGRES" == "yes" ]] && echo " Storage: Postgres (data migrated from SQLite)"
[[ "$MIGRATE_POSTGRES" != "yes" ]] && echo " Storage: SQLite (unchanged)"
if [[ "$MIGRATE_POSTGRES" == "yes" ]]; then
echo " Storage: Postgres (data migrated from SQLite)"
elif [[ "$EXISTING_POSTGRES" == "yes" ]]; then
echo " Storage: Postgres (pre-existing, configuration unchanged)"
else
echo " Storage: $STORE_ENGINE (unchanged)"
fi
[[ "$ENABLE_FLOW" == "yes" ]] && echo " Traffic flow: enabled"
[[ "$ENABLE_FLOW" != "yes" ]] && echo " Traffic flow: disabled"
echo ""
echo " Generated files (next to your docker-compose.yml):"
echo " $OVERRIDE_FILE"
[[ "$MIGRATE_POSTGRES" == "yes" ]] && echo " $ENTERPRISE_CONFIG_FILE"
[[ "$ENTERPRISE_CONFIG" == "yes" ]] && echo " $ENTERPRISE_CONFIG_FILE"
echo " .env (license key + secrets, mode 600)"
[[ "$ENV_EXISTED" == "yes" ]] && [[ -f "$ENV_BACKUP" ]] && echo " $ENV_BACKUP (.env as it was before this run)"
[[ "$MIGRATE_POSTGRES" == "yes" ]] && echo " backups/sqlite-pre-enterprise-*/ (SQLite backup)"
@@ -902,7 +1149,11 @@ print_summary() {
else
echo " $DOCKER_COMPOSE_COMMAND down"
fi
echo " rm -f $OVERRIDE_FILE $ENTERPRISE_CONFIG_FILE"
if [[ "$ENTERPRISE_CONFIG" == "yes" ]]; then
echo " rm -f $OVERRIDE_FILE $ENTERPRISE_CONFIG_FILE"
else
echo " rm -f $OVERRIDE_FILE"
fi
if [[ "$ENV_EXISTED" == "yes" ]] && [[ -f "$ENV_BACKUP" ]]; then
echo " mv $ENV_BACKUP .env # restores .env as it was before this run"
elif [[ "$ENV_EXISTED" == "no" ]]; then

View File

@@ -64,19 +64,6 @@ func (h *handler) createSetupKey(w http.ResponseWriter, r *http.Request) {
return
}
// A one-off key can be used once, and GenerateSetupKey pins its usage limit
// at 1 whatever the request says. Silently overriding a caller that asked
// for a different number leaves them holding a key that does not do what
// they configured, and no way to find out except by using it. Only values
// above 1 are refused: usage_limit is a required field with no null, so 0
// cannot be told apart from a caller that has nothing to say about it.
if types.SetupKeyType(req.Type) == types.SetupKeyOneOff && req.UsageLimit > 1 {
util.WriteError(r.Context(), status.Errorf(status.InvalidArgument,
"usage_limit %d is not valid for a one-off setup key, which can be used once; use type reusable for a key that can be used more than once",
req.UsageLimit), w)
return
}
expiresIn := time.Duration(req.ExpiresIn) * time.Second
if expiresIn < 0 {

View File

@@ -134,40 +134,6 @@ func TestSetupKeysHandlers(t *testing.T) {
expectedBody: true,
expectedSetupKey: expectedNewKey,
},
{
// A one-off key is used once. Asking for more used to be accepted
// and then quietly reduced to 1.
name: "Create One-Off Setup Key With Conflicting Usage Limit",
requestType: http.MethodPost,
requestPath: "/api/setup-keys",
requestBody: bytes.NewBuffer(
[]byte(fmt.Sprintf("{\"name\":\"%s\",\"type\":\"one-off\",\"expires_in\":86400,\"usage_limit\":5}", newSetupKeyName))),
expectedStatus: http.StatusUnprocessableEntity,
expectedBody: false,
},
{
// 0 is what a caller sends when it has nothing to say about the
// usage limit, since the field is required and has no null, so it
// has to keep working.
name: "Create One-Off Setup Key Without Usage Limit",
requestType: http.MethodPost,
requestPath: "/api/setup-keys",
requestBody: bytes.NewBuffer(
[]byte(fmt.Sprintf("{\"name\":\"%s\",\"type\":\"one-off\",\"expires_in\":86400,\"usage_limit\":0}", newSetupKeyName))),
expectedStatus: http.StatusOK,
expectedBody: false,
},
{
// Only one-off keys are constrained; a reusable key means what it
// says.
name: "Create Reusable Setup Key With Usage Limit",
requestType: http.MethodPost,
requestPath: "/api/setup-keys",
requestBody: bytes.NewBuffer(
[]byte(fmt.Sprintf("{\"name\":\"%s\",\"type\":\"reusable\",\"expires_in\":86400,\"usage_limit\":5}", newSetupKeyName))),
expectedStatus: http.StatusOK,
expectedBody: false,
},
{
name: "Update Setup Key",
requestType: http.MethodPut,

View File

@@ -136,10 +136,7 @@ func Test_SetupKeys_Create(t *testing.T) {
},
},
{
// The key used to be created anyway, with its usage limit quietly
// reduced to 1, so the caller was told a key they had not asked for
// was what they asked for.
name: "Create Setup Key as one-off with more than one usage",
name: "Create Setup Key as on-off with more than one usage",
requestType: http.MethodPost,
requestPath: "/api/setup-keys",
requestBody: &api.CreateSetupKeyRequest{
@@ -149,7 +146,23 @@ func Test_SetupKeys_Create(t *testing.T) {
Type: "one-off",
UsageLimit: 3,
},
expectedStatus: http.StatusUnprocessableEntity,
expectedStatus: http.StatusOK,
expectedResponse: &api.SetupKey{
AutoGroups: []string{},
Ephemeral: false,
Expires: time.Time{},
Id: "",
Key: "",
LastUsed: time.Time{},
Name: testing_tools.NewKeyName,
Revoked: false,
State: "valid",
Type: "one-off",
UpdatedAt: time.Now(),
UsageLimit: 1,
UsedTimes: 0,
Valid: true,
},
},
{
name: "Create Setup Key with expiration in the past",