mix
7b4549a35d
Phase 13. Two new packages and one new screen. internal/health owns the shared status vocabulary (ok/warn/error/unknown) and the local checks: supervisord's process table, TLS certificate expiry and the two milter sockets. Each check reports a problem as a status rather than an error, so one broken component costs a line and not the page. internal/dnscheck does the read-only lookups: forward-confirmed reverse DNS for SELFPOST_HOSTNAME, and per-domain DKIM (compared against the key this server actually signs with), SPF and DMARC. Every check is bounded by a timeout and cached, and the resolver sits behind an interface so the tests drive every branch without touching the network. The SPF check is deliberately shallow: it looks for a mechanism literally covering the server's address and does not follow include:/redirect=, so a record that authorises us through an include is reported as "cannot tell" rather than as a failure. /status renders both, with the local checks in an HTMX-polled fragment and the DNS lookups behind a Re-check button, and becomes the panel's landing page: / now redirects there and the domain list lives at /domains. The Reload button moves onto /status, where it reads as what it is — a drift-recovery for the daemons — with text explaining what it regenerates. A template test fails on any remaining href="/" so a stale link cannot silently land on the wrong screen. Also fixes a defect this made visible: the panel could never read the mail queue in the documented deployment. postqueue relies on its setgid-postdrop bit, which the compose file's no-new-privileges disables, so the Queue screen always said "Could not read the mail queue" — including in the released 1.0.0 image. The panel user is now a real member of postdrop, which needs no setgid transition. Verified in a container on the dev server against real DNS: PTR matching (selfpost.example.com) and not matching (example.com), DKIM absent and mismatched, SPF absent and via include:, DMARC p=quarantine/p=reject/absent, and a resolver timeout degrading to "unknown" without hanging the page. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
84 lines
2.4 KiB
Go
84 lines
2.4 KiB
Go
package health
|
|
|
|
import (
|
|
"crypto/x509"
|
|
"encoding/pem"
|
|
"fmt"
|
|
"os"
|
|
"time"
|
|
)
|
|
|
|
// certWarnDays is how close to expiry the certificate has to be before the
|
|
// status page complains. Let's Encrypt renews at 30 days left, so two weeks is
|
|
// comfortably past the point where automatic renewal should have happened.
|
|
const certWarnDays = 14
|
|
|
|
// Certificate is the state of the TLS certificate Postfix serves on 465/587
|
|
// (spec 8: TLS_CERT_FILE). The panel only reads it — the file is supplied by
|
|
// the reverse proxy through a read-only mount.
|
|
type Certificate struct {
|
|
Path string
|
|
Subject string
|
|
NotAfter time.Time
|
|
DaysLeft int
|
|
Status Status
|
|
Detail string
|
|
}
|
|
|
|
// CheckCertificate parses the leaf certificate at path and reports how much
|
|
// validity is left. A missing or unparsable file is an error status rather than
|
|
// an error return: the status page reports it in place, like every other check.
|
|
func CheckCertificate(path string) Certificate {
|
|
c := Certificate{Path: path}
|
|
if path == "" {
|
|
c.Status = StatusUnknown
|
|
c.Detail = "No certificate path is configured (TLS_CERT_FILE)."
|
|
return c
|
|
}
|
|
data, err := os.ReadFile(path)
|
|
if err != nil {
|
|
c.Status = StatusError
|
|
c.Detail = fmt.Sprintf("Could not read the certificate at %s.", path)
|
|
return c
|
|
}
|
|
leaf, err := parseLeaf(data)
|
|
if err != nil {
|
|
c.Status = StatusError
|
|
c.Detail = fmt.Sprintf("%s does not contain a readable certificate.", path)
|
|
return c
|
|
}
|
|
|
|
c.Subject = leaf.Subject.CommonName
|
|
c.NotAfter = leaf.NotAfter
|
|
c.DaysLeft = int(time.Until(leaf.NotAfter).Hours() / 24)
|
|
switch {
|
|
case !time.Now().Before(leaf.NotAfter):
|
|
c.Status = StatusError
|
|
c.Detail = "The certificate has expired. Senders will refuse the TLS connection."
|
|
case c.DaysLeft < certWarnDays:
|
|
c.Status = StatusWarn
|
|
c.Detail = fmt.Sprintf("Expires in %d day(s). Check that renewal on the host still works.", c.DaysLeft)
|
|
default:
|
|
c.Status = StatusOK
|
|
c.Detail = fmt.Sprintf("Valid for another %d day(s).", c.DaysLeft)
|
|
}
|
|
return c
|
|
}
|
|
|
|
// parseLeaf returns the first certificate in a PEM chain — the leaf, which is
|
|
// the one whose validity clients see.
|
|
func parseLeaf(data []byte) (*x509.Certificate, error) {
|
|
for rest := data; len(rest) > 0; {
|
|
var block *pem.Block
|
|
block, rest = pem.Decode(rest)
|
|
if block == nil {
|
|
break
|
|
}
|
|
if block.Type != "CERTIFICATE" {
|
|
continue
|
|
}
|
|
return x509.ParseCertificate(block.Bytes)
|
|
}
|
|
return nil, fmt.Errorf("no CERTIFICATE block found")
|
|
}
|