Tidy up pxe flow

serving/dnsmasq/entrypoint.sh

@@ -23,8 +23,12 @@
 set -eu
 
 mkdir -p /srv/tftp
-# User-supplied iPXE binary (ipxe.efi) from the read-only source mount.
+# User-supplied iPXE binary (snponly.efi) from the read-only source mount.
 cp -f /tftp-src/*.efi /srv/tftp/ 2>/dev/null || true
+# autoexec.ipxe was an STP-era workaround (ifopen+retry before autoboot); it's no
+# longer rendered — PortFast on the switch port is the real fix. Remove any stale
+# copy left in a long-lived container's writable layer.
+rm -f /srv/tftp/autoexec.ipxe
 
 extract_cmdline() {  # $1 = UKI path; echoes the cleaned cmdline (empty on failure)
   uki="$1"
@@ -47,49 +51,28 @@ render_boot_ipxe() {
     echo "      hit a dracut shell under Secure Boot OFF (no embedded cmdline)." >&2
     echo "      Check the /artifacts mount + binutils, or enable Secure Boot." >&2
   fi
-  # Render the SAME boot logic to two files:
-  #   autoexec.ipxe — iPXE fetches + runs this at STARTUP (before autoboot). The
-  #     leading `ifopen net0` brings the link UP on NICs whose NII/UNDI link iPXE
-  #     can't establish during autoboot — e.g. EliteBook 820 G4 / Intel I219-LM,
-  #     which sits at link:down ("No configurable methods") until ifopen. Without
-  #     this, autoboot fails before it can even DHCP for boot.ipxe.
-  #   boot.ipxe — the DHCP-bootfile fallback (tag:ipxe) for firmware that DOES
-  #     autoboot-DHCP fine; harmless to carry the same ifopen.
-  # Both feed iPXE the UKI's REAL cmdline via imgargs (Secure Boot OFF; see top).
-  for f in /srv/tftp/autoexec.ipxe /srv/tftp/boot.ipxe; do
-    cat > "$f" <<EOF
+  # boot.ipxe is fetched as the DHCP bootfile (dnsmasq tag:ipxe) AFTER iPXE's
+  # normal autoboot DHCP has already configured the link, so it just fetches and
+  # boots the UKI. `imgargs` feeds the UKI's REAL cmdline (Secure Boot OFF — see
+  # top); without it iPXE would pass the image name as the cmdline and dracut
+  # would drop to an emergency shell. (every fallible step is '||'-guarded — a
+  # bare failure aborts the iPXE script.)
+  #
+  # REQUIRES PortFast/edge on the switch port: iPXE's autoboot opens the NIC,
+  # which bounces the PHY; without PortFast the switch's STP forwarding delay
+  # (~30s) drops the DHCP and the boot fails. (We removed the old ifopen+retry
+  # workaround now that PortFast is the documented requirement — serving/tftp/README.)
+  cat > /srv/tftp/boot.ipxe <<EOF
 #!ipxe
-# NOTE: in iPXE a bare failing command aborts the script (-> iPXE exits -> the
-# firmware restarts PXE), so EVERY step that can fail is guarded with '||'.
-#
-# The link is already up + forwarding here (the TFTP fetch of this script just
-# succeeded), so try DHCP FIRST without touching the PHY — on a PortFast/edge
-# port this succeeds immediately with no delay.
-dhcp net0 && goto have_ip || echo initial DHCP failed; will reset link and retry
-# Fallback: reset the link, then retry DHCP long enough to outlast the switch's
-# STP forwarding delay (~30s) that the ifopen bounce triggers. A single ifopen
-# (held open across the loop) means the PHY bounces ONCE; STP then converges and
-# a later DHCP gets through. PROPER fix is PortFast/edge on the switch port so
-# there's no delay at all — see serving/tftp/README.md.
-ifopen net0 || goto err
-set tries 0
-:dhcp_retry
-dhcp net0 && goto have_ip || echo DHCP retry \${tries}
-inc tries || goto err
-iseq \${tries} 30 && goto no_ip || sleep 3
-goto dhcp_retry
-:have_ip
+dhcp net0 || goto err
 imgfetch http://${SERVER_IP}/${uki} || goto err
 imgargs ${uki} ${cmdline}
 boot ${uki} || goto err
-:no_ip
-echo No DHCP after ~90s on net0 - enable PortFast/edge on the switch port (STP delay).
 :err
 echo Fleet iPXE chain failed (\${errno}) - dropping to iPXE shell
 shell
 EOF
-  done
-  echo "rendered autoexec.ipxe + boot.ipxe -> ${uki} (cmdline: ${cmdline:-<MISSING>})"
+  echo "rendered /srv/tftp/boot.ipxe -> ${uki} (cmdline: ${cmdline:-<MISSING>})"
 }
 
 if [ -n "${SERVER_IP:-}" ] && [ -n "${IMAGE_VERSION:-}" ]; then