dracut/SOURCES/0037.patch

From add394a3532b968e12bc7b9a8923cc4b85f5f724 Mon Sep 17 00:00:00 2001
From: Martin Wilck <mwilck@suse.de>
Date: Fri, 16 Sep 2022 21:36:52 +0200
Subject: [PATCH] feat(nvmf): add code for parsing the NBFT

Add code to parse the Nvme-oF Boot Firmware Table (NBFT) according
to the NVM Express Boot Specification 1.0 [1]. The implementation in
dracut follows a similar general approach as iBFT support in the
iscsi module.

NBFT support requires two steps:

(1) Setting up the network and routing according to the
    HFI ("Host Fabric Interface") records in the NBFT,
(2) Establishing the actual NVMe-oF connection.

(1) is accomplished by reading the NBFT using JSON output from
the "nvme nbft show" command, and transforming it into command
line options ("ip=", "rd.neednet", etc.) understood by dracut's
network module and its backends. The resulting network setup code
is backend-agnostic. It has been tested with the "network-legacy"
and "network-manager" network backend modules. The network setup
code supports IPv4 and IPv6 with static, RA, or DHCP configurations,
802.1q VLANs, and simple routing / gateway setup.

(2) is done using the "nvme connect-all" command [2] in the netroot handler,
which is invoked by networking backends when an interface gets fully
configured. This patch adds support for "netboot=nbft". The "nbftroot"
handler calls nvmf-autoconnect.sh, which contains the actual connect
logic. nvmf-autoconnect.sh itself is preserved, because there are
other NVMe-oF setups like NVMe over FC which don't depend on the
network.

The various ways to configure NVMe-oF are prioritized like this:

 1 FC autoconnect from kernel commandline (rd.nvmf.discover=fc,auto)
 2 NBFT, if present
 3 discovery.conf or config.json, if present, and cmdline.d parameters,
   if present (rd.nvmf.discovery=...)
 4 FC autoconnect (without kernel command line)

The reason for this priorization is that in the initial RAM fs, we try
to activate only those connections that are necessary to mount the root
file system. This avoids confusion, possible contradicting or ambiguous
configuration, and timeouts from unavailable targets.

A retry logic is implemented for enabling the NVMe-oF connections,
using the "settled" initqueue, the netroot handler, and eventually, the
"timeout" initqueue. This is similar to the retry logic of the iscsi module.
In the "timeout" case, connection to all possible NVMe-oF subsystems
is attempted.

Two new command line parameters are introduced to make it possible to
change the priorities above:

 - "rd.nvmf.nonbft" causes the NBFT to be ignored,
 - "rd.nvmf.nostatic" causes any statically configured NVMe-oF targets
   (config.json, discovery.conf, and cmdline.d) to be ignored.

These parameters may be helpful to skip attempts to set up broken
configurations.

At initramfs build time, the nvmf module is now enabled if an NBFT
table is detected in the system.

[1] https://nvmexpress.org/wp-content/uploads/NVM-Express-Boot-Specification-2022.11.15-Ratified.pdf
[2] NBFT support in nvme-cli requires the latest upstream code (> v2.4).

Signed-off-by: Martin Wilck <mwilck@suse.com>
Co-authored-by: John Meneghini <jmeneghi@redhat.com>
Co-authored-by: Charles Rose <charles.rose@dell.com>

(Cherry-picked commits:
9664e98b5db603567d42d4d0c6e6ea1bd3d5bf24
b3ff3f3fbce6878a754332cd4a05374e5e1156c8
a3cf4ec92202df43adf368c7fdd12e35d304a0e4
03921ec09e95ea49f89ae307dcca4e2e3d1bc6d6
e93e46520dd89a7357a15441ab6b141ff9ff9aeb
556ef46aa96650d72b2fd850a09fa04dff64bbb8
a93968b07567a654d18b8ef2144337d803186eca
a65fab69662d3adf52eb968411f59ebc5a173f7c
cf8986af7d9a3ce73f330de23d5312f924acea34
7c28e1148c086d8504caab6e70a1bcfda1bbf0b9
b03dc850e4630c3b727f71b853a1be588507a59e
0a4d7f9aece172f0f9a9286c94308b7e1ef8d500)

Resolves: #1933787
---
 man/dracut.cmdline.7.asc                        |   9 +
 modules.d/95nvmf/module-setup.sh                |  25 ++-
 modules.d/95nvmf/nbftroot.sh                    |   5 +
 modules.d/95nvmf/nvmf-autoconnect.sh            |  55 +++++-
 modules.d/95nvmf/parse-nvmf-boot-connections.sh | 235 ++++++++++++++++++++++--
 5 files changed, 305 insertions(+), 24 deletions(-)

diff --git a/man/dracut.cmdline.7.asc b/man/dracut.cmdline.7.asc
index 40d13d83..abe1ec3f 100644
--- a/man/dracut.cmdline.7.asc
+++ b/man/dracut.cmdline.7.asc
@@ -898,6 +898,15 @@ NVMf
 **rd.nonvmf=0**::
     Disable NVMf
 
+**rd.nvmf.nonbft**::
+    Disable connecting to targets from the NVMe Boot Firmware Table. Without
+    this parameter, NBFT connections will take precedence over _rd.nvmf.discover_.
+
+**rd.nvmf.nostatic**::
+    Disable connecting to targets that have been statically configured when
+    the initramfs was built. Targets specified with rd.nvmf.discover on the
+    kernel command line will still be tried.
+
 **rd.nvmf.hostnqn=**__<hostNQN>__::
     NVMe host NQN to use
 
diff --git a/modules.d/95nvmf/module-setup.sh b/modules.d/95nvmf/module-setup.sh
index 46ecb38f..1dd2ca53 100755
--- a/modules.d/95nvmf/module-setup.sh
+++ b/modules.d/95nvmf/module-setup.sh
@@ -2,7 +2,7 @@
 
 # called by dracut
 check() {
-    require_binaries nvme || return 1
+    require_binaries nvme jq || return 1
     [ -f /etc/nvme/hostnqn ] || return 255
     [ -f /etc/nvme/hostid ] || return 255
 
@@ -25,17 +25,27 @@ check() {
         [[ $trtype == "fc" ]] || [[ $trtype == "tcp" ]] || [[ $trtype == "rdma" ]]
     }
 
+    has_nbft() {
+        local f found=
+        for f in /sys/firmware/acpi/tables/NBFT*; do
+            [ -f "$f" ] || continue
+            found=1
+            break
+        done
+        [[ $found ]]
+    }
+
     [[ $hostonly ]] || [[ $mount_needs ]] && {
         pushd . > /dev/null
         for_each_host_dev_and_slaves is_nvmf
         local _is_nvmf=$?
         popd > /dev/null || exit
         [[ $_is_nvmf == 0 ]] || return 255
-        if [ ! -f /sys/class/fc/fc_udev_device/nvme_discovery ]; then
-            if [ ! -f /etc/nvme/discovery.conf ]; then
-                echo "No discovery arguments present"
-                return 255
-            fi
+        if [ ! -f /sys/class/fc/fc_udev_device/nvme_discovery ] \
+            && [ ! -f /etc/nvme/discovery.conf ] \
+            && [ ! -f /etc/nvme/config.json ] && ! has_nbft; then
+            echo "No discovery arguments present"
+            return 255
         fi
     }
     return 0
@@ -126,8 +136,9 @@ install() {
     inst_multiple ip sed
 
     inst_script "${moddir}/nvmf-autoconnect.sh" /sbin/nvmf-autoconnect.sh
+    inst_script "${moddir}/nbftroot.sh" /sbin/nbftroot
 
-    inst_multiple nvme
+    inst_multiple nvme jq
     inst_hook cmdline 92 "$moddir/parse-nvmf-boot-connections.sh"
     inst_simple "/etc/nvme/discovery.conf"
     inst_simple "/etc/nvme/config.json"
diff --git a/modules.d/95nvmf/nbftroot.sh b/modules.d/95nvmf/nbftroot.sh
new file mode 100755
index 00000000..0f334995
--- /dev/null
+++ b/modules.d/95nvmf/nbftroot.sh
@@ -0,0 +1,5 @@
+#! /bin/sh
+# This script is called from /sbin/netroot
+
+/sbin/nvmf-autoconnect.sh online
+exit 0
diff --git a/modules.d/95nvmf/nvmf-autoconnect.sh b/modules.d/95nvmf/nvmf-autoconnect.sh
index c8f676a7..35ee9487 100755
--- a/modules.d/95nvmf/nvmf-autoconnect.sh
+++ b/modules.d/95nvmf/nvmf-autoconnect.sh
@@ -1,5 +1,54 @@
-#!/bin/bash
+#!/bin/sh
+# Argument $1 is "settled", "online", or "timeout", indicating
+# the queue from which the script is called.
+# In the "timeout" case, try everything.
+# Otherwise, try options according to the priorities below.
 
-[ -f /sys/class/fc/fc_udev_device/nvme_discovery ] || exit 1
-echo add > /sys/class/fc/fc_udev_device/nvme_discovery
+[ "$RD_DEBUG" != yes ] || set -x
+
+if [ "$1" = timeout ]; then
+    [ ! -f /sys/class/fc/fc_udev_device/nvme_discovery ] \
+        || echo add > /sys/class/fc/fc_udev_device/nvme_discovery
+    /usr/sbin/nvme connect-all
+    exit 0
+fi
+
+NVMF_HOSTNQN_OK=
+[ ! -f "/etc/nvme/hostnqn" ] || [ ! -f "/etc/nvme/hostid" ] || NVMF_HOSTNQN_OK=1
+
+# Only nvme-cli 2.5 or newer supports the options --nbft and --no-nbft
+# for the connect-all command.
+# Make sure we don't use unsupported options with earlier versions.
+NBFT_SUPPORTED=
+# shellcheck disable=SC2016
+/usr/sbin/nvme connect-all --help 2>&1 | sed -n '/[[:space:]]--nbft[[:space:]]/q1;$q0' \
+    || NBFT_SUPPORTED=1
+
+if [ -e /tmp/nvmf-fc-auto ] && [ "$NVMF_HOSTNQN_OK" ] \
+    && [ -f /sys/class/fc/fc_udev_device/nvme_discovery ]; then
+    # prio 1: cmdline override "rd.nvmf.discovery=fc,auto"
+    echo add > /sys/class/fc/fc_udev_device/nvme_discovery
+    exit 0
+fi
+if [ "$NBFT_SUPPORTED" ] && [ -e /tmp/valid_nbft_entry_found ]; then
+    # prio 2: NBFT
+    /usr/sbin/nvme connect-all --nbft
+    exit 0
+fi
+if [ -f /etc/nvme/discovery.conf ] || [ -f /etc/nvme/config.json ] \
+    && [ "$NVMF_HOSTNQN_OK" ]; then
+    # prio 3: configuration from initrd and/or kernel command line
+    # We can get here even if "rd.nvmf.nonbft" was given, thus use --no-nbft
+    if [ "$NBFT_SUPPORTED" ]; then
+        /usr/sbin/nvme connect-all --no-nbft
+    else
+        /usr/sbin/nvme connect-all
+    fi
+    exit 0
+fi
+if [ "$NVMF_HOSTNQN_OK" ] \
+    && [ -f /sys/class/fc/fc_udev_device/nvme_discovery ]; then
+    # prio 4: no discovery entries, try NVMeoFC autoconnect
+    echo add > /sys/class/fc/fc_udev_device/nvme_discovery
+fi
 exit 0
diff --git a/modules.d/95nvmf/parse-nvmf-boot-connections.sh b/modules.d/95nvmf/parse-nvmf-boot-connections.sh
index 6c5ef4bc..66018371 100755
--- a/modules.d/95nvmf/parse-nvmf-boot-connections.sh
+++ b/modules.d/95nvmf/parse-nvmf-boot-connections.sh
@@ -17,13 +17,225 @@
 # specify any discover parameters for FC.
 #
 
-type is_ip > /dev/null 2>&1 || . /lib/net-lib.sh
+command -v getarg > /dev/null || . /lib/dracut-lib.sh
+command -v is_ip > /dev/null || . /lib/net-lib.sh
+
+## Sample NBFT output from nvme show-nbft -H -s -d -o json
+# [
+#   {
+#     "filename":"/sys/firmware/acpi/tables/NBFT",
+#     "host":{
+#       "nqn":"nqn.2014-08.org.nvmexpress:uuid:d6f07002-7eb5-4841-a185-400e296afae4",
+#       "id":"111919da-21ea-cc4e-bafe-216d8372dd31",
+#       "host_id_configured":0,
+#       "host_nqn_configured":0,
+#       "primary_admin_host_flag":"not indicated"
+#     },
+#     "subsystem":[
+#       {
+#         "index":1,
+#         "num_hfis":1,
+#         "hfis":[
+#           1
+#         ],
+#         "transport":"tcp",
+#         "transport_address":"192.168.100.216",
+#         "transport_svcid":"4420",
+#         "subsys_port_id":0,
+#         "nsid":1,
+#         "nid_type":"uuid",
+#         "nid":"424d1c8a-8ef9-4681-b2fc-8c343bd8fa69",
+#         "subsys_nqn":"timberland-01",
+#         "controller_id":0,
+#         "asqsz":0,
+#         "pdu_header_digest_required":0,
+#         "data_digest_required":0
+#       }
+#     ],
+#     "hfi":[
+#       {
+#         "index":1,
+#         "transport":"tcp",
+#         "pcidev":"0:0:2.0",
+#         "mac_addr":"52:54:00:4f:97:e9",
+#         "vlan":0,
+#         "ip_origin":63,
+#         "ipaddr":"192.168.100.217",
+#         "subnet_mask_prefix":24,
+#         "gateway_ipaddr":"0.0.0.0",
+#         "route_metric":0,
+#         "primary_dns_ipaddr":"0.0.0.0",
+#         "secondary_dns_ipaddr":"0.0.0.0",
+#         "dhcp_server_ipaddr":"",
+#         "this_hfi_is_default_route":1
+#       }
+#     ],
+#     "discovery":[
+#     ]
+#   }
+# ]
+#
+# If the IP address is derived from DHCP, it sets the field
+# "hfi.dhcp_server_ipaddr" to a non-emtpy value.
+#
+#
+
+nbft_run_jq() {
+    local st
+    local opts="-e"
+
+    while [ $# -gt 0 ]; do
+        case $1 in
+            -*)
+                opts="$opts $1"
+                ;;
+            *)
+                break
+                ;;
+        esac
+        shift
+    done
+    # Not quoting is intentional here. We won't get glob expressions passed.
+    # shellcheck disable=SC2086
+    jq $opts "$1" << EOF
+$2
+EOF
+    st=$?
+    if [ $st -ne 0 ]; then
+        warn "NBFT: jq error while processing \"$1\""
+        return $st
+    else
+        return 0
+    fi
+}
+
+nbft_check_empty_address() {
+    # suppress meaningless or empty IP addresses
+    # "null" is returned by jq if no match found for expression
+    case $1 in
+        null | "::" | "0.0.0.0") ;;
+        *)
+            echo "$1"
+            ;;
+    esac
+}
+
+nbft_parse_hfi() {
+    # false positive of shellcheck - no expansion in variable assignments
+    # shellcheck disable=2086
+    local hfi_json=$1
+    local mac iface ipaddr prefix vlan gateway dns1 dns2 hostname adrfam dhcp
+
+    mac=$(nbft_run_jq -r .mac_addr "$hfi_json") || return 1
+    iface=$(set_ifname nbft "$mac")
+
+    vlan=$(nbft_run_jq .vlan "$hfi_json") || vlan=0
+    # treat VLAN zero as "no vlan"
+    [ "$vlan" -ne 0 ] || vlan=
+
+    [ ! -e /tmp/net."${iface}${vlan:+.$vlan}".has_ibft_config ] || return 0
+
+    dhcp=$(nbft_run_jq -r .dhcp_server_ipaddr "$hfi_json")
+    # We need to check $? here as the above is an assignment
+    # shellcheck disable=2181
+    if [ $? -eq 0 ] && [ "$dhcp" ] && [ "$dhcp" != null ]; then
+        case $dhcp in
+            *:*)
+                echo ip="$iface${vlan:+.$vlan}:dhcp6"
+                ;;
+            *.*.*.*)
+                echo ip="$iface${vlan:+.$vlan}:dhcp"
+                ;;
+            *)
+                warn "Invalid value for dhcp_server_ipaddr: $dhcp"
+                return 1
+                ;;
+        esac
+    else
+        ipaddr=$(nbft_run_jq -r .ipaddr "$hfi_json") || return 1
+
+        case $ipaddr in
+            *.*.*.*)
+                adrfam=ipv4
+                ;;
+            *:*)
+                adrfam=ipv6
+                ;;
+            *)
+                warn "invalid address: $ipaddr"
+                return 1
+                ;;
+        esac
+        prefix=$(nbft_run_jq -r .subnet_mask_prefix "$hfi_json")
+        # Need to check $? here as he above is an assignment
+        # shellcheck disable=2181
+        if [ $? -ne 0 ] && [ "$adrfam" = ipv6 ]; then
+            prefix=128
+        fi
+        # Use brackets for IPv6
+        if [ "$adrfam" = ipv6 ]; then
+            ipaddr="[$ipaddr]"
+        fi
+
+        gateway=$(nbft_check_empty_address \
+            "$(nbft_run_jq -r .gateway_ipaddr "$hfi_json")")
+        dns1=$(nbft_check_empty_address \
+            "$(nbft_run_jq -r .primary_dns_ipaddr "$hfi_json")")
+        dns2=$(nbft_check_empty_address \
+            "$(nbft_run_jq -r .secondary_dns_ipaddr "$hfi_json")")
+        hostname=$(nbft_run_jq -r .host_name "$hfi_json" 2> /dev/null) || hostname=
+
+        echo "ip=$ipaddr::$gateway:$prefix:$hostname:$iface${vlan:+.$vlan}:none${dns1:+:$dns1}${dns2:+:$dns2}"
+    fi
+
+    if [ "$vlan" ]; then
+        echo "vlan=$iface.$vlan:$iface"
+        echo "$mac" > "/tmp/net.$iface.$vlan.has_ibft_config"
+    else
+        echo "$mac" > "/tmp/net.$iface.has_ibft_config"
+    fi
+    : > /tmp/valid_nbft_entry_found
+}
+
+nbft_parse() {
+    local nbft_json n_nbft all_hfi_json n_hfi
+    local j=0 i
+
+    nbft_json=$(nvme nbft show -H -o json) || return 0
+    n_nbft=$(nbft_run_jq ". | length" "$nbft_json") || return 0
+
+    while [ "$j" -lt "$n_nbft" ]; do
+        all_hfi_json=$(nbft_run_jq ".[$j].hfi" "$nbft_json") || continue
+        n_hfi=$(nbft_run_jq ". | length" "$all_hfi_json") || continue
+        i=0
+
+        while [ "$i" -lt "$n_hfi" ]; do
+            nbft_parse_hfi "$(nbft_run_jq ".[$i]" "$all_hfi_json")"
+            i=$((i + 1))
+        done
+        j=$((j + 1))
+    done >> /etc/cmdline.d/40-nbft.conf
+}
 
 if getargbool 0 rd.nonvmf; then
     warn "rd.nonvmf=0: skipping nvmf"
     return 0
 fi
 
+if getargbool 0 rd.nvmf.nostatic; then
+    rm -f /etc/cmdline.d/95nvmf-args.conf
+    rm -f /etc/nvme/discovery.conf /etc/nvme/config.json
+fi
+
+if ! getargbool 0 rd.nvmf.nonbft; then
+    for _x in /sys/firmware/acpi/tables/NBFT*; do
+        if [ -f "$_x" ]; then
+            nbft_parse
+            break
+        fi
+    done
+fi
+
 initqueue --onetime modprobe --all -b -q nvme_tcp nvme_core nvme_fabrics
 
 parse_nvmf_discover() {
@@ -94,26 +306,21 @@ if [ -n "$nvmf_hostid" ]; then
     echo "$nvmf_hostid" > /etc/nvme/hostid
 fi
 
-NVMF_FC_AUTO=
+rm -f /tmp/nvmf-fc-auto
 for d in $(getargs rd.nvmf.discover -d nvmf.discover=); do
     parse_nvmf_discover "$d" || {
-        NVMF_FC_AUTO=1
+        : > /tmp/nvmf-fc-auto
         break
     }
 done
 
-if [ -e /tmp/nvmf_needs_network ]; then
+if [ -e /tmp/nvmf_needs_network ] || [ -e /tmp/valid_nbft_entry_found ]; then
     echo "rd.neednet=1" > /etc/cmdline.d/nvmf-neednet.conf
+    # netroot is a global variable that is present in all "sourced" scripts
+    # shellcheck disable=SC2034
+    netroot=nbft
     rm -f /tmp/nvmf_needs_network
 fi
 
-# Host NQN and host id are mandatory for NVMe-oF
-if [ -f "/etc/nvme/hostnqn" ] && [ -f "/etc/nvme/hostid" ]; then
-
-    # If no nvme command line arguments present, try autodiscovery
-    if [ $NVMF_FC_AUTO ] || [ ! -f "/etc/nvme/discovery.conf" ]; then
-        /sbin/initqueue --settled --onetime --unique --name nvme-fc-autoconnect /sbin/nvmf-autoconnect.sh
-    else
-        /sbin/initqueue --settled --onetime --unique --name nvme-discover /usr/sbin/nvme connect-all
-    fi
-fi
+/sbin/initqueue --settled --onetime --name nvmf-connect-settled /sbin/nvmf-autoconnect.sh settled
+/sbin/initqueue --timeout --onetime --name nvmf-connect-timeout /sbin/nvmf-autoconnect.sh timeout