fix: P0+P1 critical bug fixes across controller (24 files)

Concurrency fixes:
- Deep-copy stacks in GetStack/GetStacks to prevent shared state mutation (C04)
- Add per-state mutex to watchdog pathProbeState (C05)
- Guard MetricsCollector.Start() with sync.Once against double-start (C06)
- Hold diskJobMu across entire raw mount operation (C07)
- Add mutex to SetEncryptionKey (C08), MigrateEncryption write lock (H03)
- Use sync.Once for sync.Stop() channel close (H08)
- Set syncing=true before releasing lock in TriggerSync (H09)
- Deep-copy lastDBDump/lastBackup in GetFullStatus (H11)
- Add WaitGroup for stderr goroutine in MigrateDrive (H19)
- Add mutex to SetBackupRunningCheck (M18)

Security fixes:
- Validate Bearer token against Hub API key in CSRF middleware (H16)
- Validate backup paths start with expected prefix in RemoveStack (M12)
- Guard uuid[:8] slice with length check (H20)
- Parse fstab fields exactly for mount target matching (H21)

Bug fixes:
- Use decrypted env vars for compose deploy (C01)
- Log decrypt failures in DecryptMap instead of swallowing (C02)
- Move Deployed=false inside lock in runComposeDeploy (C03)
- Fix activeDrives() to skip disconnected drives (H02)
- Fix Snapshot() stderr extraction from exec.ExitError (H01)
- Check unlockCmd.Run() error in restic (H01)
- Buffer template rendering via bytes.Buffer (H07)
- Thread context.Context through cloudflare client (H10)
- Fix leaf-name collision detection in cross-drive backup (H15)
- Add nil check for crossDriveRunner (H17)
- Use strings.TrimSpace instead of slice on command output (H18)
- Make SaveAppConfig atomic with write-to-tmp+rename (H04)
- Pass encKey on deploy failure SaveAppConfig (H05)
- Fix IPv6 address format in TCP health probe

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-02-25 13:39:45 +01:00
parent 2ad743b66f
commit 8b8c04a487
23 changed files with 248 additions and 83 deletions
+3 -2
View File
@@ -2,6 +2,7 @@ package cloudflare
import (
"bytes"
"context"
"encoding/json"
"fmt"
"io"
@@ -54,7 +55,7 @@ type apiMessage struct {
}
// do performs an HTTP request to the Cloudflare API and decodes the response.
func (c *Client) do(method, path string, body interface{}) (*apiResponse, error) {
func (c *Client) do(ctx context.Context, method, path string, body interface{}) (*apiResponse, error) {
var bodyReader io.Reader
if body != nil {
data, err := json.Marshal(body)
@@ -70,7 +71,7 @@ func (c *Client) do(method, path string, body interface{}) (*apiResponse, error)
}
url := apiBase + path
req, err := http.NewRequest(method, url, bodyReader)
req, err := http.NewRequestWithContext(ctx, method, url, bodyReader)
if err != nil {
return nil, fmt.Errorf("create request: %w", err)
}
+11 -11
View File
@@ -76,7 +76,7 @@ func (g *GeoSyncManager) Sync(ctx context.Context) error {
zoneID := geo.ZoneID
if zoneID == "" {
var err error
zoneID, err = g.client.GetZoneID(g.domain)
zoneID, err = g.client.GetZoneID(ctx, g.domain)
if err != nil {
g.saveError(zoneID, "", err.Error())
return fmt.Errorf("resolve zone: %w", err)
@@ -87,13 +87,13 @@ func (g *GeoSyncManager) Sync(ctx context.Context) error {
rulesetID := geo.RulesetID
if rulesetID == "" {
var err error
rulesetID, err = g.client.GetCustomRulesetID(zoneID)
rulesetID, err = g.client.GetCustomRulesetID(ctx, zoneID)
if err != nil {
g.saveError(zoneID, "", err.Error())
return fmt.Errorf("get ruleset: %w", err)
}
if rulesetID == "" {
rulesetID, err = g.client.CreateCustomRuleset(zoneID)
rulesetID, err = g.client.CreateCustomRuleset(ctx, zoneID)
if err != nil {
g.saveError(zoneID, "", err.Error())
return fmt.Errorf("create ruleset: %w", err)
@@ -102,7 +102,7 @@ func (g *GeoSyncManager) Sync(ctx context.Context) error {
}
// 3. List existing felhom-managed rules
existing, err := g.client.GetFelhomRules(zoneID, rulesetID)
existing, err := g.client.GetFelhomRules(ctx, zoneID, rulesetID)
if err != nil {
g.saveError(zoneID, rulesetID, err.Error())
return fmt.Errorf("list existing rules: %w", err)
@@ -112,7 +112,7 @@ func (g *GeoSyncManager) Sync(ctx context.Context) error {
desired := g.buildDesiredRules(geo)
// 5. Diff and apply
if err := g.applyDiff(zoneID, rulesetID, existing, desired); err != nil {
if err := g.applyDiff(ctx, zoneID, rulesetID, existing, desired); err != nil {
g.saveError(zoneID, rulesetID, err.Error())
return fmt.Errorf("apply diff: %w", err)
}
@@ -138,14 +138,14 @@ func (g *GeoSyncManager) deleteAllRules(ctx context.Context, geo *settings.GeoRe
return nil
}
existing, err := g.client.GetFelhomRules(zoneID, rulesetID)
existing, err := g.client.GetFelhomRules(ctx, zoneID, rulesetID)
if err != nil {
g.logger.Printf("[GEO] Warning: could not list rules for cleanup: %v", err)
return nil
}
for _, r := range existing {
if err := g.client.DeleteRule(zoneID, rulesetID, r.ID); err != nil {
if err := g.client.DeleteRule(ctx, zoneID, rulesetID, r.ID); err != nil {
g.logger.Printf("[GEO] Warning: could not delete rule %s: %v", r.ID, err)
}
}
@@ -202,7 +202,7 @@ func (g *GeoSyncManager) buildDesiredRules(geo *settings.GeoRestriction) []desir
}
// applyDiff applies the difference between existing and desired rules.
func (g *GeoSyncManager) applyDiff(zoneID, rulesetID string, existing []GeoRule, desired []desiredRule) error {
func (g *GeoSyncManager) applyDiff(ctx context.Context, zoneID, rulesetID string, existing []GeoRule, desired []desiredRule) error {
// Index existing by description
existingByDesc := make(map[string]GeoRule)
for _, r := range existing {
@@ -221,14 +221,14 @@ func (g *GeoSyncManager) applyDiff(zoneID, rulesetID string, existing []GeoRule,
// Rule exists — check if expression changed
if ex.Expression != d.expression {
r := newBlockRule(d.description, d.expression)
if err := g.client.UpdateRule(zoneID, rulesetID, ex.ID, r); err != nil {
if err := g.client.UpdateRule(ctx, zoneID, rulesetID, ex.ID, r); err != nil {
return fmt.Errorf("update rule %q: %w", d.description, err)
}
}
} else {
// New rule — create
r := newBlockRule(d.description, d.expression)
if _, err := g.client.CreateRule(zoneID, rulesetID, r); err != nil {
if _, err := g.client.CreateRule(ctx, zoneID, rulesetID, r); err != nil {
return fmt.Errorf("create rule %q: %w", d.description, err)
}
}
@@ -237,7 +237,7 @@ func (g *GeoSyncManager) applyDiff(zoneID, rulesetID string, existing []GeoRule,
// Delete rules that are no longer desired
for _, ex := range existing {
if _, ok := desiredByDesc[ex.Description]; !ok {
if err := g.client.DeleteRule(zoneID, rulesetID, ex.ID); err != nil {
if err := g.client.DeleteRule(ctx, zoneID, rulesetID, ex.ID); err != nil {
return fmt.Errorf("delete rule %q: %w", ex.Description, err)
}
}
+15 -14
View File
@@ -1,6 +1,7 @@
package cloudflare
import (
"context"
"encoding/json"
"fmt"
"strings"
@@ -58,9 +59,9 @@ type GeoRule struct {
// GetCustomRulesetID returns the zone's http_request_firewall_custom ruleset ID.
// Returns empty string if no such ruleset exists yet.
func (c *Client) GetCustomRulesetID(zoneID string) (string, error) {
func (c *Client) GetCustomRulesetID(ctx context.Context, zoneID string) (string, error) {
path := fmt.Sprintf("/zones/%s/rulesets", zoneID)
resp, err := c.do("GET", path, nil)
resp, err := c.do(ctx, "GET", path, nil)
if err != nil {
return "", fmt.Errorf("list rulesets: %w", err)
}
@@ -80,7 +81,7 @@ func (c *Client) GetCustomRulesetID(zoneID string) (string, error) {
}
// CreateCustomRuleset creates the http_request_firewall_custom phase entry point ruleset.
func (c *Client) CreateCustomRuleset(zoneID string) (string, error) {
func (c *Client) CreateCustomRuleset(ctx context.Context, zoneID string) (string, error) {
path := fmt.Sprintf("/zones/%s/rulesets", zoneID)
body := map[string]interface{}{
"name": "felhom custom rules",
@@ -89,7 +90,7 @@ func (c *Client) CreateCustomRuleset(zoneID string) (string, error) {
"rules": []interface{}{},
}
resp, err := c.do("POST", path, body)
resp, err := c.do(ctx, "POST", path, body)
if err != nil {
return "", fmt.Errorf("create ruleset: %w", err)
}
@@ -104,9 +105,9 @@ func (c *Client) CreateCustomRuleset(zoneID string) (string, error) {
}
// GetRules returns all rules in a ruleset.
func (c *Client) GetRules(zoneID, rulesetID string) ([]rule, error) {
func (c *Client) GetRules(ctx context.Context, zoneID, rulesetID string) ([]rule, error) {
path := fmt.Sprintf("/zones/%s/rulesets/%s", zoneID, rulesetID)
resp, err := c.do("GET", path, nil)
resp, err := c.do(ctx, "GET", path, nil)
if err != nil {
return nil, fmt.Errorf("get ruleset: %w", err)
}
@@ -122,8 +123,8 @@ func (c *Client) GetRules(zoneID, rulesetID string) ([]rule, error) {
}
// GetFelhomRules returns only rules with the [felhom-geo] prefix.
func (c *Client) GetFelhomRules(zoneID, rulesetID string) ([]GeoRule, error) {
rules, err := c.GetRules(zoneID, rulesetID)
func (c *Client) GetFelhomRules(ctx context.Context, zoneID, rulesetID string) ([]GeoRule, error) {
rules, err := c.GetRules(ctx, zoneID, rulesetID)
if err != nil {
return nil, err
}
@@ -144,9 +145,9 @@ func (c *Client) GetFelhomRules(zoneID, rulesetID string) ([]GeoRule, error) {
}
// CreateRule adds a new rule to the ruleset.
func (c *Client) CreateRule(zoneID, rulesetID string, r rule) (string, error) {
func (c *Client) CreateRule(ctx context.Context, zoneID, rulesetID string, r rule) (string, error) {
path := fmt.Sprintf("/zones/%s/rulesets/%s/rules", zoneID, rulesetID)
resp, err := c.do("POST", path, r)
resp, err := c.do(ctx, "POST", path, r)
if err != nil {
return "", fmt.Errorf("create rule: %w", err)
}
@@ -170,9 +171,9 @@ func (c *Client) CreateRule(zoneID, rulesetID string, r rule) (string, error) {
}
// UpdateRule updates an existing rule in the ruleset.
func (c *Client) UpdateRule(zoneID, rulesetID, ruleID string, r rule) error {
func (c *Client) UpdateRule(ctx context.Context, zoneID, rulesetID, ruleID string, r rule) error {
path := fmt.Sprintf("/zones/%s/rulesets/%s/rules/%s", zoneID, rulesetID, ruleID)
_, err := c.do("PATCH", path, r)
_, err := c.do(ctx, "PATCH", path, r)
if err != nil {
return fmt.Errorf("update rule %s: %w", ruleID, err)
}
@@ -181,9 +182,9 @@ func (c *Client) UpdateRule(zoneID, rulesetID, ruleID string, r rule) error {
}
// DeleteRule removes a rule from the ruleset.
func (c *Client) DeleteRule(zoneID, rulesetID, ruleID string) error {
func (c *Client) DeleteRule(ctx context.Context, zoneID, rulesetID, ruleID string) error {
path := fmt.Sprintf("/zones/%s/rulesets/%s/rules/%s", zoneID, rulesetID, ruleID)
_, err := c.do("DELETE", path, nil)
_, err := c.do(ctx, "DELETE", path, nil)
if err != nil {
return fmt.Errorf("delete rule %s: %w", ruleID, err)
}
+6 -5
View File
@@ -1,6 +1,7 @@
package cloudflare
import (
"context"
"encoding/json"
"fmt"
"net/url"
@@ -14,9 +15,9 @@ type zone struct {
// GetZoneID resolves the Cloudflare zone ID for a domain.
// It tries the exact domain first, then strips subdomains progressively.
func (c *Client) GetZoneID(domain string) (string, error) {
func (c *Client) GetZoneID(ctx context.Context, domain string) (string, error) {
// Try exact domain first (e.g., "demo-felhom.eu")
id, err := c.lookupZone(domain)
id, err := c.lookupZone(ctx, domain)
if err != nil {
return "", err
}
@@ -31,7 +32,7 @@ func (c *Client) GetZoneID(domain string) (string, error) {
if parent == "" {
break
}
id, err = c.lookupZone(parent)
id, err = c.lookupZone(ctx, parent)
if err != nil {
return "", err
}
@@ -45,9 +46,9 @@ func (c *Client) GetZoneID(domain string) (string, error) {
}
// lookupZone queries the CF API for a zone by name.
func (c *Client) lookupZone(name string) (string, error) {
func (c *Client) lookupZone(ctx context.Context, name string) (string, error) {
path := "/zones?name=" + url.QueryEscape(name) + "&status=active"
resp, err := c.do("GET", path, nil)
resp, err := c.do(ctx, "GET", path, nil)
if err != nil {
return "", fmt.Errorf("lookup zone %q: %w", name, err)
}