#!/usr/bin/env bash
# Configure SPDK nvmf_tgt to serve the diskless root filesystem as a single
# READ-ONLY NVMe/TCP namespace (design doc §5, §7).
#
# rootfs.erofs is the erofs image with the dm-verity hash tree appended in-file;
# we expose the WHOLE file as one namespace, and the host splits data/hash with
# systemd.verity_root_options=hash-offset= from the kernel cmdline. Integrity is
# enforced end-to-end by dm-verity on the host; the target serves it read-only.
set -euo pipefail

ROOTFS="/artifacts/rootfs.erofs"
SUBNQN="${SUBNQN:-nqn.2026-06.org.example.fleet:rootfs}"
# Fixed, fleet-generic namespace UUID. The host references the root device as
# /dev/disk/by-id/nvme-uuid.$ROOT_NS_UUID on the kernel cmdline, which is stable
# regardless of NVMe controller enumeration order (the I/O controller can land
# on nvme0/nvme1/... depending on whether a transient discovery controller took
# a slot first — so a hardcoded /dev/nvme0n1 is unsafe). MUST match
# ROOT_NS_UUID in scripts/extract-artifacts.sh, which bakes it into the UKI
# cmdline. NOTE: for multi-version serving (TODO #6) make this version-specific
# alongside the per-version NQN, so a host can't connect the wrong rootfs.
ROOT_NS_UUID="${ROOT_NS_UUID:-f1ee7000-0000-4000-8000-000000000001}"
TADDR="${TARGET_ADDR:-0.0.0.0}"
TPORT="${TARGET_PORT:-4420}"
CPUMASK="${SPDK_CPUMASK:-0x1}"

[ -s "$ROOTFS" ] || { echo "ERROR: $ROOTFS not found/empty — is ARTIFACT_SRC populated?" >&2; exit 1; }

# Binary locations differ across SPDK images; fall back to the common path.
TGT=$(command -v nvmf_tgt || echo /usr/libexec/spdk/spdk/build/bin/nvmf_tgt)
RPC=$(command -v rpc.py   || echo /usr/libexec/spdk/scripts/rpc.py)

# Ensure hugepages exist — DPDK needs them. vm.nr_hugepages isn't namespaced,
# so a privileged container writes the host value; this re-applies after a host
# reboot (the container restarts). Best-effort: allocation can fail on a
# fragmented host, in which case set vm.nr_hugepages on the host (persistently
# via /etc/sysctl.d). Override the count with HUGEPAGES.
HUGEPAGES="${HUGEPAGES:-1024}"
if [ -w /proc/sys/vm/nr_hugepages ]; then
    cur=$(cat /proc/sys/vm/nr_hugepages 2>/dev/null || echo 0)
    if [ "${cur:-0}" -lt "$HUGEPAGES" ]; then
        echo "==> allocating $HUGEPAGES hugepages (was ${cur:-0})"
        echo "$HUGEPAGES" > /proc/sys/vm/nr_hugepages 2>/dev/null || true
    fi
fi
free=$(awk '/HugePages_Free/{print $2}' /proc/meminfo 2>/dev/null || echo 0)
[ "${free:-0}" -gt 0 ] || echo "WARNING: no free hugepages — SPDK will fail; allocate vm.nr_hugepages on the host." >&2

echo "==> starting nvmf_tgt (cpumask ${CPUMASK})"
"$TGT" -m "$CPUMASK" &
TGT_PID=$!
trap 'kill "$TGT_PID" 2>/dev/null || true' EXIT

# Wait for the RPC socket to come up.
for _ in $(seq 1 30); do
    "$RPC" framework_get_config >/dev/null 2>&1 && break
    sleep 1
done

echo "==> creating TCP transport"
"$RPC" nvmf_create_transport -t TCP -u 16384 -m 8 -c 8192

echo "==> exposing $ROOTFS as bdev 'rootfs' (4 KiB blocks)"
# -r opens the backing file read-only where supported; harmless if ignored.
"$RPC" bdev_aio_create "$ROOTFS" rootfs 4096 -r \
    || "$RPC" bdev_aio_create "$ROOTFS" rootfs 4096

echo "==> creating subsystem $SUBNQN (allow any host — lab/no-auth)"
"$RPC" nvmf_create_subsystem "$SUBNQN" -a -s SPDKLAB0000000001 -d FleetRootfs

echo "==> adding namespace 1 (uuid $ROOT_NS_UUID)"
# Read-only is enforced by the bdev_aio '-r' open above (this SPDK's add_ns has
# no --read-only flag), plus the :ro image-volume mount and the client's erofs
# ro + dm-verity.
# -u pins the namespace UUID so the host can reference it as
# /dev/disk/by-id/nvme-uuid.$ROOT_NS_UUID (stable across controller indices).
"$RPC" nvmf_subsystem_add_ns "$SUBNQN" rootfs -u "$ROOT_NS_UUID"

echo "==> adding TCP listener ${TADDR}:${TPORT} to $SUBNQN"
"$RPC" nvmf_subsystem_add_listener "$SUBNQN" -t tcp -a "$TADDR" -s "$TPORT"

# Also add the listener to the well-known discovery subsystem. Without this,
# SPDK still answers discovery on this listener but logs a deprecation warning
# ("listener was not added to the discovery subsystem") and the implicit
# behaviour is slated for removal. Explicitly registering it is the supported
# way and future-proofs `nvme discover` against an SPDK bump. Best-effort:
# tolerate older SPDK builds where the discovery NQN can't take a listener.
echo "==> adding TCP listener ${TADDR}:${TPORT} to the discovery subsystem"
"$RPC" nvmf_subsystem_add_listener nqn.2014-08.org.nvmexpress.discovery \
    -t tcp -a "$TADDR" -s "$TPORT" \
    || echo "WARNING: could not add listener to discovery subsystem (older SPDK?) — discovery still works via the deprecated implicit path." >&2

echo "==> SPDK serving $SUBNQN over tcp/${TPORT}; rd.nvmf.discover=tcp,${TADDR},${TPORT}"
wait "$TGT_PID"