#!/usr/bin/env bash
## entrypoint-shared-ols.sh — PID 1 for the shared-ols tier.
##
## One OpenLiteSpeed container fronting MANY tenants' detached cac-lsphp
## sidecars (the OLS analogue of the shared-httpd container). Webserver ONLY —
## it runs NO PHP locally (render-shared-ols-config.sh strips the stock local
## lsphp; every site's PHP goes to its own sidecar over LSAPI). HAProxy stays
## the TLS/WAF/SNI edge and routes OLS-type hostnames here on :443.
##
## Reuses cac-litespeed's hard-won DAEMON-MODE supervision (NOT `openlitespeed
## -n` + wait): OLS self-restarts on QUIC.cloud IP refresh would otherwise exit
## PID 1 cleanly and tear the container down. See entrypoint-litespeed.sh and
## feedback_ols_quiccloud_restart_kills_container.
set -euo pipefail

: "${environment:=PROD}"
export CONTAINER_ROLE="shared_ols"

LSWS_CONF=/usr/local/lsws/conf
CERT_DIR="$LSWS_CONF/cert"
HEALTH_DIR=/usr/local/lsws/shared-ols-health
export SITES_ROOT="${SITES_ROOT:-$LSWS_CONF/shared-sites}"
export LSCACHE_ROOT="${LSCACHE_ROOT:-/var/lscache}"
export CERT_FILE="$CERT_DIR/shared-ols.crt"
export KEY_FILE="$CERT_DIR/shared-ols.key"

mkdir -p "$SITES_ROOT" "$LSCACHE_ROOT" "$CERT_DIR" "$HEALTH_DIR/html"

## ---- self-signed cert for the :443 listener (HAProxy verifies none) ----
if [ ! -f "$CERT_FILE" ]; then
  openssl req -x509 -newkey rsa:2048 -nodes -days 3650 \
    -keyout "$KEY_FILE" -out "$CERT_FILE" -subj "/CN=shared-ols" 2>/dev/null
fi

## ---- health vhost (catch-all) ----
## This vhost is mapped `map _health *` by render-shared-ols-config.sh, so it
## answers EVERY Host that no customer vhost claims. It exists so the server is
## valid with zero customer sites and so local/edge health probes get a 200.
##
## IT MUST NOT ANSWER 200 FOR AN UNMAPPED CUSTOMER HOST.
## It used to serve html/index.html ("shared-ols", 11 bytes) with HTTP 200 to
## anything that fell through. Measured 2026-08: three live customer sites
## (their vhost had silently stopped being rendered) served that 200 for ~2
## months and no monitor noticed, because every uptime check asks "is it 200?"
## and the answer was yes. A hostname this server cannot serve now gets
## 421 Misdirected Request -- semantically exact (RFC 7540 s9.1.2: the server is
## not able to produce a response for the combination of scheme and authority in
## the request URI) and unambiguous to monitoring in a way 404 is not, since a
## 404 is a perfectly normal answer from a real, working site.
##
## THE DISCRIMINATOR: request path /healthz AND an INTERNAL client address.
##   * Path alone is not enough -- anyone can request /healthz.
##   * REMOTE_ADDR is the half an outside caller cannot choose, BECAUSE of
##     `useIpInProxyHeader 1` in httpd_config_base.tpl: OLS resolves the client
##     IP from X-Forwarded-For, and HAProxy -- the only thing that can reach
##     this tier, which has no host-published ports and sits on client-net --
##     SETS (not appends) that header:
##     `http-request set-header X-Forwarded-For %[var(txn.real_ip)]` in
##     haproxy-manager-base/templates/hap_backend.tpl, which DISCARDS whatever
##     the client sent. So a request arriving from outside carries the real
##     public client IP. Verified on the lab: `-H 'X-Forwarded-For: 8.8.8.8'`
##     on /healthz returns 421.
##   * MEASURED LIMIT OF THE IP GATE, stated plainly rather than assumed away:
##     OLS takes the FIRST element of a multi-value X-Forwarded-For as
##     REMOTE_ADDR. `X-Forwarded-For: 10.0.0.1, 8.8.8.8` returns 200 on /healthz
##     here, and anchoring the pattern ^...$ does NOT change that (tested both
##     ways) -- because by the time the rule sees REMOTE_ADDR it is already the
##     single token `10.0.0.1`. The anchors are kept because they are correct
##     and free, not because they close that hole. What closes it is HAProxy:
##     `http-request set-header X-Forwarded-For %[var(txn.real_ip)]` REPLACES
##     whatever the client sent with one value.
##   * AND THE GATE IS NOT LOAD-BEARING ANYWAY. It only guards /healthz. `/`,
##     and every other path, is 421 UNCONDITIONALLY -- no header, source
##     address or Host can talk this vhost into a 200 there. So even a total
##     bypass of the IP gate buys an attacker a 3-byte `ok` on /healthz, never
##     a "the site is up" answer on the URL a monitor actually requests. That
##     is the property this change exists to guarantee, and it does not rest on
##     anything spoofable.
##   * The probes that MUST keep passing all originate inside: the Docker
##     HEALTHCHECK (`curl -sfk https://127.0.0.1/healthz` in Dockerfile.shared-ols,
##     overridden by WHP's setup-shared-ols.sh to `https://localhost/healthz`)
##     connects over loopback and sends no X-Forwarded-For, so REMOTE_ADDR falls
##     back to the peer, 127.0.0.1. An edge/host probe of the container IP comes
##     from the docker gateway (172.16/12), also allowed.
##
## `/` is 421 for EVERY client, internal ones included -- there is deliberately
## no "internal clients still get the old 200 page" escape hatch, because that
## is exactly the response that hid the outage. Anything probing this tier for
## liveness must ask for /healthz.
##
## WHY REWRITE AND NOT A REDIRECT CONTEXT: `context / { type redirect
## statusCode 421 }` was measured on this image (OLS 1.8.4) and does NOT work --
## 421 is not in OLS's accepted status-code list, so it silently degrades to a
## 302 with a literal, unexpanded `Location: $DOC_ROOT/?`. A rewrite `[R=421,L]`
## does emit a real 421.
##
## WHY THE THE_REQUEST GUARD ON THE ERROR PAGE: a bare [R=421] has no body, and
## a bare 421 with no explanation is a support ticket. `errorpage 421` supplies
## the body, but OLS fetches that URL as a fresh internal request that runs
## through these same rules -- without an exception it is itself 421'd and the
## body comes back empty (measured: content-length 0). %{IS_SUBREQ} and
## %{ENV:REDIRECT_STATUS} are NOT populated by OLS's rewrite engine (both
## measured, both no-ops), but %{THE_REQUEST} keeps the ORIGINAL request line
## across the internal fetch. So: serve misdirected.html when the client did not
## itself ask for it, which lets the error page render while a direct external
## GET /misdirected.html still gets 421 -- no path on this catch-all answers 200
## to an outside caller.
##
## The body is deliberately generic: no branding, no customer names, nothing
## that reveals which hostnames this server does serve. Every unmapped Host and
## every path gets the byte-identical 421, so the response cannot be used to
## enumerate configured vs unconfigured hostnames.
cat > "$HEALTH_DIR/vhconf.conf" <<'EOF'
docRoot                   $VH_ROOT/html
enableScript              0

errorpage 421 {
  url                     /misdirected.html
}

rewrite {
  enable                  1
  rules                   <<<END_rules
  RewriteCond %{THE_REQUEST} !\s/+misdirected\.html
  RewriteRule ^/?misdirected\.html$ - [L]
  RewriteCond %{REMOTE_ADDR} ^(127\.0\.0\.1|::1|10\.[0-9.]+|192\.168\.[0-9.]+|172\.(1[6-9]|2[0-9]|3[01])\.[0-9.]+)$
  RewriteRule ^/?healthz$ - [L]
  RewriteRule .* - [R=421,L]
  END_rules
}

context / {
  allowBrowse             1
  location                $DOC_ROOT/
}
EOF
printf 'ok\n' > "$HEALTH_DIR/html/healthz"
cat > "$HEALTH_DIR/html/misdirected.html" <<'EOF'
<!DOCTYPE html>
<html lang="en">
<head><meta charset="utf-8"><title>421 Misdirected Request</title></head>
<body>
<h1>421 Misdirected Request</h1>
<p>This hostname is not configured on this server.</p>
<p>If you own this domain, check that its DNS points to the correct server and
that the site is active in your hosting control panel.</p>
</body>
</html>
EOF
## The old catch-all index.html ("shared-ols") is gone on purpose, and actively
## removed so an in-place upgrade of a long-lived container cannot leave it
## behind. If these rewrite rules were ever to stop applying, `context /` would
## fall back to serving the docRoot index -- with no index.html that is a 403,
## which is wrong-but-loud, instead of a 200 that is wrong-and-silent.
rm -f "$HEALTH_DIR/html/index.html"

## ---- ownership: OLS reads conf/ as lsadm. chown the base conf dir + health dir
## NON-recursively (the per-site files under conf/shared-sites are written by the
## panel and are world-readable; a recursive chown here would be O(N-sites) on
## every container (re)start, delaying first-listen after a crash). The render
## script chowns the httpd_config.conf it produces. ----
chown lsadm:nogroup "$LSWS_CONF" "$HEALTH_DIR" "$HEALTH_DIR/html" 2>/dev/null || true
chown lsadm:nogroup "$HEALTH_DIR/vhconf.conf" "$HEALTH_DIR/html/healthz" "$HEALTH_DIR/html/misdirected.html" 2>/dev/null || true

## ---- assemble httpd_config.conf from the panel's per-site files ----
/scripts/render-shared-ols-config.sh

## ---- stream OLS logs to PID-1 stdout (follows across restarts) ----
mkdir -p /usr/local/lsws/logs
touch /usr/local/lsws/logs/error.log /usr/local/lsws/logs/access.log
tail -F /usr/local/lsws/logs/error.log /usr/local/lsws/logs/access.log 2>/dev/null &

## ---- .htaccess watcher (required; spec 5.3). Background; the panel monitors
## that it stays alive (its death silently stops rewrite changes applying). ----
/scripts/ols-htaccess-watcher.sh &
WATCHER_PID=$!

## ---- supervise OLS in DAEMON mode (verbatim model from entrypoint-litespeed.sh) ----
STOP_REQUESTED=0
term_handler() {
  STOP_REQUESTED=1
  kill "$WATCHER_PID" 2>/dev/null || true
  /usr/local/lsws/bin/lswsctrl stop >/dev/null 2>&1 || true
}
trap term_handler TERM INT

## NOT `lswsctrl status` (unlike the otherwise-identical function in
## entrypoint-litespeed.sh). `lswsctrl` appends a timestamped line to
## logs/lsrestart.log on EVERY invocation it makes, including `status` — and
## this loop polls every 3s forever. Measured on whp01: lsrestart.log is 96 MB,
## holding 1,819,286 `status` lines against 2,429 real `restart` lines; at one
## poll per 3s that's ~63 days of continuous polling, which is exactly the
## file's age, and it isn't rotated on any host (whp01/whp02/sdbees all growing
## at ~1.5 MB/day). So: check liveness directly instead of shelling out to a
## tool whose logging is a side effect we don't want on a fixed timer.
##
## Verified (docker run litespeedtech/openlitespeed:1.8.4-lsphp83, the exact
## base this image is built FROM — see Dockerfile.shared-ols): the running main
## process shows in `ps` as `openlitespeed (lshttpd - main)`, one PID, always
## present while OLS is up and absent the instant it is killed (checked via
## `ps aux` immediately after `kill -9` on the main PID). `pgrep -f` matches
## against the full command line, and no other process on this image's `ps`
## output contains that string, so this cannot cross-match an unrelated
## process. It also cannot self-match: pgrep excludes its own PID by default,
## and the invoking process here is bash executing this script file, whose own
## argv never contains the pattern text (only the *source lines* of this script
## do, which `pgrep -f` never sees).
##
## Deliberately NOT the pidfile (/tmp/lshttpd/lshttpd.pid, confirmed present in
## the same probe): pidfiles are known to go stale across a crash (verified —
## after `kill -9` the file still held the dead PID), and treating a stale PID
## as "alive" if the kernel ever reuses that number is a false positive this
## supervisor cannot afford (see below). `pgrep -f` reads the live process
## table, so there is no staleness window to reason about.
##
## Conservative on both failure directions, which matters because this is a
## supervisor predicate, not a metric: a false negative makes start_ols() run
## `lswsctrl start` against an already-running OLS — verified against the same
## probe base image, that is NOT a no-op, it sends SIGUSR1 to the live main
## process, i.e. the same graceful self-restart QUIC.cloud IP refreshes trigger
## (see entrypoint-litespeed.sh's note on that handoff) — a brief, zero-
## downtime blip at worst. A false positive is worse: it leaves a genuinely
## dead OLS un-revived until some later poll happens to notice. So if this
## predicate is ever in doubt it should err toward reporting "not running", not
## "running".
ols_running() {
  pgrep -f 'lshttpd - main' >/dev/null 2>&1
}

MAX_STARTS=5
WINDOW=60
starts=""

start_ols() {
  /usr/local/lsws/bin/lswsctrl start >/dev/null 2>&1 || true
  for _ in $(seq 1 20); do
    ols_running && return 0
    sleep 0.5
  done
  return 1
}

if ! start_ols; then
  echo "entrypoint-shared-ols: OLS failed to start (not running after 10s)." >&2
  exit 1
fi
echo "entrypoint-shared-ols: OLS started in daemon mode — $(/usr/local/lsws/bin/lswsctrl status 2>/dev/null || true)"

while true; do
  if ols_running; then
    sleep 3
    continue
  fi
  sleep 2
  if [ "$STOP_REQUESTED" -eq 0 ] && ols_running; then
    continue
  fi
  if [ "$STOP_REQUESTED" -eq 1 ]; then
    echo "entrypoint-shared-ols: SIGTERM received, OLS stopped — exiting."
    exit 0
  fi
  now=$(date +%s)
  starts="$starts $now"
  pruned=""
  for t in $starts; do
    [ $((now - t)) -lt "$WINDOW" ] && pruned="$pruned $t"
  done
  starts="$pruned"
  n=$(echo $starts | wc -w)
  echo "entrypoint-shared-ols: OLS not running — relaunching (attempt $n/$MAX_STARTS within ${WINDOW}s)." >&2
  if [ "$n" -ge "$MAX_STARTS" ]; then
    echo "entrypoint-shared-ols: OLS crash-looping — bailing for Docker restart policy / monitor." >&2
    exit 1
  fi
  start_ols || true
done