network fixes for link waiting

Here is a patch set for some network cleanup and fixes:
01-network-move-wait-for-if-function-to-net-lib.patch 02-network-add-function-linkup.patch 03-network-use-linkup-function.patch 04-network-wait-for-link-ready-before-use.patch 05-network-get-ifaces-for-udev-rule-use.patch 06-network-wait-interface-up-at-early-stage.patch

Tested kdump with a nic which delay abouth 60s while initializing.

Please help to review especially for the patch 3/6 which replace some ip link up with a function linkup.

--
Thanks a lot
Dave

net-lib.sh are created for net related functions, move the wait_for_if* to net-lib.sh naturally.

---
 modules.d/40network/dhclient-script.sh |    1 +
 modules.d/40network/net-lib.sh         |   23 +++++++++++++++++++++++
 modules.d/95fcoe/fcoe-up.sh            |    1 +
 modules.d/99base/dracut-lib.sh         |   23 -----------------------
 4 files changed, 25 insertions(+), 23 deletions(-)

@@ -481,29 +481,6 @@ else
     }
 fi
 
-wait_for_if_up() {
-    local cnt=0
-    local li
-    while [ $cnt -lt 200 ]; do
-        li=$(ip -o link show up dev $1)
-        [ -n "$li" ] && return 0
-        sleep 0.1
-        cnt=$(($cnt+1))
-    done
-    return 1
-}
-
-wait_for_route_ok() {
-    local cnt=0
-    while [ $cnt -lt 200 ]; do
-        li=$(ip route show)
-        [ -n "$li" ] && [ -z "${li##*$1*}" ] && return 0
-        sleep 0.1
-        cnt=$(($cnt+1))
-    done
-    return 1
-}
-
 # root=nfs:[<server-ip>:]<root-dir>[:<nfs-options>]
 # root=nfs4:[<server-ip>:]<root-dir>[:<nfs-options>]
 nfsroot_to_var() {

@@ -315,3 +315,26 @@ parse_ifname_opts() {
     esac
 
 }
+
+wait_for_if_up() {
+    local cnt=0
+    local li
+    while [ $cnt -lt 200 ]; do
+        li=$(ip -o link show up dev $1)
+        [ -n "$li" ] && return 0
+        sleep 0.1
+        cnt=$(($cnt+1))
+    done
+    return 1
+}
+
+wait_for_route_ok() {
+    local cnt=0
+    while [ $cnt -lt 200 ]; do
+        li=$(ip route show)
+        [ -n "$li" ] && [ -z "${li##*$1*}" ] && return 0
+        sleep 0.1
+        cnt=$(($cnt+1))
+    done
+    return 1
+}

@@ -51,6 +51,7 @@ PATH=/usr/sbin:/usr/bin:/sbin:/bin
 export PS4="dhclient.$interface.$$ + "
 exec >>/run/initramfs/loginit.pipe 2>>/run/initramfs/loginit.pipe
 type getarg >/dev/null 2>&1 || . /lib/dracut-lib.sh
+type ip_to_var >/dev/null 2>&1 || . /lib/net-lib.sh
 
 # We already need a set netif here
 netif=$interface

@@ -16,6 +16,7 @@ PATH=/usr/sbin:/usr/bin:/sbin:/bin
 export PS4="fcoe-up.$1.$$ + "
 exec >>/run/initramfs/loginit.pipe 2>>/run/initramfs/loginit.pipe
 type getarg >/dev/null 2>&1 || . /lib/dracut-lib.sh
+type ip_to_var >/dev/null 2>&1 || . /lib/net-lib.sh
 
 netif=$1
 dcb=$2

There's some problem with my mta and smtp server.
Looks like 0/6 and 5/6 are lost.

Will resend this series.

Thanks
Dave

set link up usually include two steps, ip link set <dev> up and wait_for_if_up <dev>. Now do these two steps in one function linkup. Later patch will add other code into it.

---
 modules.d/40network/net-lib.sh |    5 +++++
 1 file changed, 5 insertions(+)

@@ -338,3 +338,8 @@ wait_for_route_ok() {
     done
     return 1
 }
+
+linkup() {
+    ip link set $1 up 2>/dev/null && wait_for_if_up $1 2>/dev/null
+}
+

Update ifup.sh and fcoe-up.sh, use linkup function instead of directly call ip command.

---
 modules.d/40network/ifup.sh |   17 ++++++-----------
 modules.d/95fcoe/fcoe-up.sh |    3 +--
 2 files changed, 7 insertions(+), 13 deletions(-)

@@ -84,8 +84,7 @@ do_ipv6auto() {
     echo 0 > /proc/sys/net/ipv6/conf/$netif/forwarding
     echo 1 > /proc/sys/net/ipv6/conf/$netif/accept_ra
     echo 1 > /proc/sys/net/ipv6/conf/$netif/accept_redirects
-    ip link set $netif up
-    wait_for_if_up $netif
+    linkup $netif
 
     [ -n "$hostname" ] && echo "echo $hostname > /proc/sys/kernel/hostname" > /tmp/net.$netif.hostname
 

@@ -96,8 +95,7 @@ do_ipv6auto() {
 do_static() {
     strstr $ip '*:*:*' && load_ipv6
 
-    ip link set $netif up
-    wait_for_if_up $netif
+    linkup $netif
     [ -n "$macaddr" ] && ip link set address $macaddr
     [ -n "$mtu" ] && ip link set mtu $mtu
     if strstr $ip '*:*:*'; then

@@ -147,13 +145,12 @@ if [ -e /tmp/bond.info ]; then
             fi
         done
 
-        ip link set $netif up
+        linkup $netif
 
         for slave in $bondslaves ; do
             ip link set $slave down
             echo "+$slave" > /sys/class/net/$bondname/bonding/slaves
-            ip link set $slave up
-            wait_for_if_up $slave
+            linkup $slave
         done
 
         # add the bits to setup the needed post enslavement parameters

@@ -180,9 +177,8 @@ if [ -e /tmp/bridge.info ]; then
             if [ "$ethname" = "$bondname" ] ; then
                 DO_BOND_SETUP=yes ifup $bondname -m
             else
-                ip link set $ethname up
+                linkup $ethname
             fi
-            wait_for_if_up $ethname
             brctl addif $bridgename $ethname
         done
     fi

@@ -204,9 +200,8 @@ if [ "$netif" = "$vlanname" ] && [ ! -e 
     if [ "$phydevice" = "$bondname" ] ; then
         DO_BOND_SETUP=yes ifup $phydevice -m
     else
-        ip link set "$phydevice" up
+        linkup "$phydevice"
     fi
-    wait_for_if_up "$phydevice"
     ip link add dev "$vlanname" link "$phydevice" type vlan id "$(get_vid $vlanname; echo $?)"
 fi
 

@@ -21,8 +21,7 @@ type ip_to_var >/dev/null 2>&1 || . /lib
 netif=$1
 dcb=$2
 
-ip link set "$netif" up
-wait_for_if_up "$netif"
+linkup "$netif"
 
 netdriver=$(readlink -f /sys/class/net/$netif/device/driver)
 netdriver=${netdriver##*/}

Some network driver will take long time to initialize. We have an example in a HP machine which take about one minute for this. The callback such as "ip link set <dev> up" will fail, afterwards setup for network will also fail.

Fix this by add a new function wait_for_if_link, wait the link ready before use it.

---
 modules.d/40network/net-lib.sh |   17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

@@ -316,6 +316,19 @@ parse_ifname_opts() {
 
 }
 
+# some network driver need long time to initialize, wait before it's ready.
+wait_for_if_link() {
+    local cnt=0
+    local li
+    while [ $cnt -lt 600 ]; do
+        li=$(ip -o link show dev $1 2>/dev/null)
+        [ -n "$li" ] && return 0
+        sleep 0.1
+        cnt=$(($cnt+1))
+    done
+    return 1
+}
+
 wait_for_if_up() {
     local cnt=0
     local li

@@ -340,6 +353,8 @@ wait_for_route_ok() {
 }
 
 linkup() {
-    ip link set $1 up 2>/dev/null && wait_for_if_up $1 2>/dev/null
+    wait_for_if_link $1 2>/dev/null\
+     && ip link set $1 up 2>/dev/null\
+     && wait_for_if_up $1 2>/dev/null
 }
 

In case without BOOTIF, but /tmp/ifaces are already created. net-genrule.sh will fall to bring up all net interfaces.

Fix by reading from /tmp/ifaces before generating rules instead.

---
 modules.d/40network/net-genrules.sh |    2 ++
 1 file changed, 2 insertions(+)

@@ -19,6 +19,8 @@ if [ -z "$netroot" ] && [ ! -e "/tmp/net
     return
 fi
 
+[ -e /tmp/net.ifaces ] && read IFACES < /tmp/net.ifaces
+
 # Write udev rules
 {
     # bridge: attempt only the defined interface

In case long delay of network driver initqueue will exit before net dev is ready. We have no chance to setup it then.
For dhcp, when we finish the setup there will be a setup_net_<dev>.ok. Doing same for static ip case. Also add a check to initqueue when we generate udev rules to ensure it's early enough.

---
 modules.d/40network/ifup.sh         |    1 +
 modules.d/40network/net-genrules.sh |    3 +++
 2 files changed, 4 insertions(+)

@@ -49,14 +49,17 @@ fi
     if [ -n "$BOOTIF" ] ; then
         BOOTIF=$(fix_bootif "$BOOTIF")
         printf 'ACTION=="add", SUBSYSTEM=="net", ATTR{address}=="%s", RUN+="%s"\n' "$BOOTIF" "/sbin/initqueue --onetime $ifup"
+        echo "[ -f /tmp/setup_net_${BOOTIF}.ok ]" >$hookdir/initqueue/finished/wait-${BOOTIF}.sh
 
     # If we have to handle multiple interfaces, handle only them.
     elif [ -n "$IFACES" ] ; then
         for iface in $IFACES ; do
             printf 'SUBSYSTEM=="net", ENV{INTERFACE}=="%s", RUN+="%s"\n' "$iface" "/sbin/initqueue --onetime $ifup"
+            echo "[ -f /tmp/setup_net_${iface}.ok ]" >$hookdir/initqueue/finished/wait-$iface.sh
         done
 
     # Default: We don't know the interface to use, handle all
+    # Fixme: waiting for the interface as well.
     else
         printf 'SUBSYSTEM=="net", RUN+="%s"\n' "/sbin/initqueue --onetime $ifup" > /etc/udev/rules.d/91-default-net.rules
     fi

@@ -109,6 +109,7 @@ do_static() {
     [ -n "$gw" ] && echo ip route add default via $gw dev $netif > /tmp/net.$netif.gw
     [ -n "$hostname" ] && echo "echo $hostname > /proc/sys/kernel/hostname" > /tmp/net.$netif.hostname
 
+    > /tmp/setup_net_${netif}.ok
     return 0
 }
 

Even with this series we still need add rd.retry=90 to make it work. How about increase the default rd.retry value in dracut?

Thanks
Dave

Am 14.11.2012 09:49, schrieb Dave Young:

wow, which HW is recognized only after 40 seconds?

Hi, It's a Qlogic nic, seel below log, looks like it detected a wrong firmware, then released it and loaded firmware from flash:

Ethernet using netxen_nic driver for exp., suppressed irrelevant info.

[    6.666842] QLogic/NetXen Network Driver v4.0.80
[    6.727424] netxen_nic 0000:04:00.0: 2MB memory map
[   38.484866] netxen_nic 0000:04:00.0: Incompatibility detected between

driver and firmware version on flash. This configuration is not recommended. Please update the firmware on flash immediately dracut-pre-pivot[581]: device node not found dracut-pre-pivot[581]: cat: /sys/class/net/em1/address: No such file or directory
dracut-pre-pivot[581]: cat: /sys/class/net/em1/address: No such file or directory
dracut-pre-pivot[581]: ++ KDUMP_PATH=/var/crash dracut-pre-pivot[581]: ++ CORE_COLLECTOR= dracut-pre-pivot[581]: ++ DEFAULT_CORE_COLLECTOR='makedumpfile -c --message-level 1 -d 31'
dracut-pre-pivot[581]: ++ DEFAULT_ACTION=dump_rootfs dracut-pre-pivot[581]: +++ date +%d.%m.%y-%T dracut-pre-pivot[581]: ++ DATEDIR=05.11.12-00:32:36 dracut-pre-pivot[581]: ++ DUMP_INSTRUCTION= dracut-pre-pivot[581]: ++ SSH_KEY_LOCATION=/root/.ssh/kdump_id_rsa dracut-pre-pivot[581]: ++ KDUMP_SCRIPT_DIR=/kdumpscripts dracut-pre-pivot[581]: ++ DD_BLKSIZE=512 dracut-pre-pivot[581]: ++ FINAL_ACTION='reboot -f' dracut-pre-pivot[581]: ++ DUMP_RETVAL=0 dracut-pre-pivot[581]: ++ conf_file=/etc/kdump.conf dracut-pre-pivot[581]: ++ KDUMP_PRE=

Entering emergency mode. Exit the shell to continue. Type "journalctl" to view system logs.

kdump:/# dracut-pre-pivot[581]: ++ KDUMP_POST=
dracut-pre-pivot[581]: ++ export
PATH=/usr/sbin:/usr/bin:/sbin:/bin:/kdumpscripts
dracut-pre-pivot[581]: ++ PATH=/usr/sbin:/usr/bin:/sbin:/bin:/kdumpscripts
dracut-pre-pivot[581]: ++ read_kdump_conf
dracut-pre-pivot[581]: ++ '[' '!' -f /etc/kdump.conf ']'
dracut-pre-pivot[581]: ++ read config_opt config_val
dracut-pre-pivot[581]: ++ case "$config_opt" in
dracut-pre-pivot[581]: ++ read config_opt config_val
dracut-pre-pivot[581]: ++ case "$config_opt" in
dracut-pre-pivot[581]: ++ KDUMP_PATH=/
dracut-pre-pivot[581]: ++ read config_opt config_val
dracut-pre-pivot[581]: ++ case "$config_opt" in
dracut-pre-pivot[581]: ++ read config_opt config_val
dracut-pre-pivot[581]: ++ case "$config_opt" in
dracut-pre-pivot[581]: ++ case $config_val in
dracut-pre-pivot[581]: ++ DEFAULT_ACTION='_emergency_shell kdump'
dracut-pre-pivot[581]: ++ read config_opt config_val
dracut-pre-pivot[581]: ++ read config_opt config_val
dracut-pre-pivot[581]: ++ case "$config_opt" in
dracut-pre-pivot[581]: ++ read config_opt config_val
dracut-pre-pivot[581]: ++ case "$config_opt" in
dracut-pre-pivot[581]: ++ read config_opt config_val
dracut-pre-pivot[581]: ++ case "$config_opt" in
dracut-pre-pivot[581]: ++ add_dump_code 'dump_fs
ibm-x3250m4-01.rhts.eng.nay.redhat.com:/mnt/testarea/nfs'
dracut-pre-pivot[581]: ++ DUMP_INSTRUCTION='dump_fs
ibm-x3250m4-01.rhts.eng.nay.redhat.com:/mnt/testarea/nfs'
dracut-pre-pivot[581]: ++ read config_opt config_val
dracut-pre-pivot[581]: ++ case "$config_opt" in
dracut-pre-pivot[581]: ++ read config_opt config_val
dracut-pre-pivot[581]: ++ '[' -z '' ']'
dracut-pre-pivot[581]: ++ CORE_COLLECTOR='makedumpfile -c
--message-level 1 -d 31'
dracut-pre-pivot[581]: ++ is_ssh_dump_target
dracut-pre-pivot[581]: ++ grep -q '^ssh.*@' /etc/kdump.conf
dracut-pre-pivot[581]: ++ is_raw_dump_target
dracut-pre-pivot[581]: ++ grep -q '^raw' /etc/kdump.conf
dracut-pre-pivot[581]: ++ '[' -z 'dump_fs
ibm-x3250m4-01.rhts.eng.nay.redhat.com:/mnt/testarea/nfs' ']'
dracut-pre-pivot[581]: ++ do_kdump_pre
dracut-pre-pivot[581]: ++ '[' -n '' ']'
dracut-pre-pivot[581]: ++ '[' 0 -ne 0 ']'
dracut-pre-pivot[581]: ++ dump_fs
ibm-x3250m4-01.rhts.eng.nay.redhat.com:/mnt/testarea/nfs
dracut-pre-pivot[581]: +++ findmnt -k -f -n -r -o TARGET
ibm-x3250m4-01.rhts.eng.nay.redhat.com:/mnt/testarea/nfs
dracut-pre-pivot[581]: ++ local _mp=
dracut-pre-pivot[581]: ++ '[' -z '' ']'
dracut-pre-pivot[581]: ++ echo 'kdump: error: Dump target
ibm-x3250m4-01.rhts.eng.nay.redhat.com:/mnt/testarea/nfs is not mounted.'
dracut-pre-pivot[581]: ++ return 1
dracut-pre-pivot[581]: ++ DUMP_RETVAL=1
dracut-pre-pivot[581]: ++ do_kdump_post 1
dracut-pre-pivot[581]: ++ '[' -n '' ']'
dracut-pre-pivot[581]: ++ '[' 0 -ne 0 ']'
dracut-pre-pivot[581]: ++ '[' 1 -ne 0 ']'
dracut-pre-pivot[581]: ++ do_default_action
dracut-pre-pivot[581]: ++ wait_for_loginit
dracut-pre-pivot[581]: ++ '[' no = yes ']'
dracut-pre-pivot[581]: ++ return
dracut-pre-pivot[581]: ++ _emergency_shell kdump
dracut-pre-pivot[581]: ++ local _name=kdump
dracut-pre-pivot[581]: ++ '[' -n 1 ']'
dracut-pre-pivot[581]: ++ echo 'PS1="kdump:${PWD}# "'
dracut-pre-pivot[581]: ++ systemctl start dracut-emergency.service
[  101.732446] netxen_nic 0000:04:00.0: loading firmware from flash
[  103.873799] netxen_nic 0000:04:00.0: Gen2 strapping detected
[  106.880731] netxen_nic 0000:04:00.0: using 64-bit dma mask
[  106.888721] netxen_nic: failed card response code:0x10
[  106.894405] netxen_nic 0000:04:00.0: Can't get template size 16843009
[  106.901481] netxen_nic 0000:04:00.0: Failed to setup minidump rcode = -5
[  106.908839] netxen_nic: NX3031 Gigabit Ethernet Board S/N
���������������������������������▒��  Chip rev 0x42
[  106.919726] netxen_nic 0000:04:00.0: firmware v4.0.527 [legacy]
[  106.926689] netxen_nic 0000:04:00.0: using msi-x interrupts
[  106.933163] netxen_nic 0000:04:00.0: eth0: GbE port initialized
[  106.939902] netxen_nic 0000:04:00.1: 2MB memory map
[  106.949661] netxen_nic 0000:04:00.1: using 64-bit dma mask
[  106.965572] systemd-udevd[629]: renamed network interface eth0 to em1
[  106.982471] netxen_nic: failed card response code:0x10
[  106.988124] netxen_nic 0000:04:00.1: Can't get template size 16843009
[  106.995196] netxen_nic 0000:04:00.1: Failed to setup minidump rcode = -5
[  107.002555] netxen_nic 0000:04:00.1: firmware v4.0.527 [legacy]
[  107.009440] netxen_nic 0000:04:00.1: using msi-x interrupts
[  107.015687] netxen_nic 0000:04:00.1: eth0: GbE port initialized
[  107.022569] netxen_nic 0000:04:00.2: 2MB memory map
[  107.030819] netxen_nic 0000:04:00.2: using 64-bit dma mask
[  107.062359] systemd-udevd[633]: renamed network interface eth0 to em2
[  107.075314] netxen_nic: failed card response code:0x10
[  107.081043] netxen_nic 0000:04:00.2: Can't get template size 16843009
[  107.088117] netxen_nic 0000:04:00.2: Failed to setup minidump rcode = -5
[  107.095476] netxen_nic 0000:04:00.2: firmware v4.0.527 [legacy]
[  107.102316] netxen_nic 0000:04:00.2: using msi-x interrupts
[  107.108574] netxen_nic 0000:04:00.2: eth0: GbE port initialized
[  107.115596] netxen_nic 0000:04:00.3: 2MB memory map
[  107.124339] netxen_nic 0000:04:00.3: using 64-bit dma mask
[  107.157705] systemd-udevd[629]: renamed network interface eth0 to em3
[  107.184131] netxen_nic: failed card response code:0x10
[  107.189786] netxen_nic 0000:04:00.3: Can't get template size 16843009
[  107.196853] netxen_nic 0000:04:00.3: Failed to setup minidump rcode = -5
[  107.204205] netxen_nic 0000:04:00.3: firmware v4.0.527 [legacy]
[  107.211062] netxen_nic 0000:04:00.3: using msi-x interrupts
[  107.217311] netxen_nic 0000:04:00.3: eth0: GbE port initialized
[  107.244557] systemd-udevd[629]: renamed network interface eth0 to em4

Thanks
Dave