[patch 0/6 v2] network fixes for link waiting

[patch 0/6 v2] network fixes for link waiting

[dyoung-H+wXaHxf7aLQT0dZR+AlfA]

Hi,

This is the v2 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.
V2 patch updated 05 and 06 to fix some issues with bonding device.

--
Thanks a lot
Dave

[patch 1/6 v2] Move wait for if functions to net lib

[dyoung-H+wXaHxf7aLQT0dZR+AlfA]

[-- Attachment #1: patch1 --]
[-- Type: text/plain, Size: 2586 bytes --]

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

Signed-off-by: Dave Young <dyoung-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
---
 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(-)

--- dracut.orig/modules.d/99base/dracut-lib.sh
+++ dracut/modules.d/99base/dracut-lib.sh
@@ -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() {
--- dracut.orig/modules.d/40network/net-lib.sh
+++ dracut/modules.d/40network/net-lib.sh
@@ -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##*$1*}" ] && return 0
+        sleep 0.1
+        cnt=$(($cnt+1))
+    done
+    return 1
+}
--- dracut.orig/modules.d/40network/dhclient-script.sh
+++ dracut/modules.d/40network/dhclient-script.sh
@@ -51,6 +51,7 @@ PATH=/usr/sbin:/usr/bin:/sbin:/bin
 export PS4="dhclient.$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
--- dracut.orig/modules.d/95fcoe/fcoe-up.sh
+++ dracut/modules.d/95fcoe/fcoe-up.sh
@@ -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

[patch 2/6 v2] Add function linkup

[dyoung-H+wXaHxf7aLQT0dZR+AlfA]

[-- Attachment #1: patch2 --]
[-- Type: text/plain, Size: 579 bytes --]

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.

Signed-off-by: Dave Young <dyoung-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
---
 modules.d/40network/net-lib.sh |    5 +++++
 1 file changed, 5 insertions(+)

--- dracut.orig/modules.d/40network/net-lib.sh
+++ dracut/modules.d/40network/net-lib.sh
@@ -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
+}
+

[patch 3/6 v2] Change to use linkup function in network scripts

[dyoung-H+wXaHxf7aLQT0dZR+AlfA]

[-- Attachment #1: patch3 --]
[-- Type: text/plain, Size: 2614 bytes --]

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

Signed-off-by: Dave Young <dyoung-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
---
 modules.d/40network/ifup.sh |   17 ++++++-----------
 modules.d/95fcoe/fcoe-up.sh |    3 +--
 2 files changed, 7 insertions(+), 13 deletions(-)

--- dracut.orig/modules.d/40network/ifup.sh
+++ dracut/modules.d/40network/ifup.sh
@@ -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
 
--- dracut.orig/modules.d/95fcoe/fcoe-up.sh
+++ dracut/modules.d/95fcoe/fcoe-up.sh
@@ -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##*/}

[patch 4/6 v2] Wait for link ready before use the interface

[dyoung-H+wXaHxf7aLQT0dZR+AlfA]

[-- Attachment #1: patch4 --]
[-- Type: text/plain, Size: 1259 bytes --]

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.

Signed-off-by: Dave Young <dyoung-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
---
 modules.d/40network/net-lib.sh |   17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

--- dracut.orig/modules.d/40network/net-lib.sh
+++ dracut/modules.d/40network/net-lib.sh
@@ -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
 }
 

[patch 5/6 v2] Get failsafe ifaces for udev rule use

[dyoung-H+wXaHxf7aLQT0dZR+AlfA]

[-- Attachment #1: patch5 --]
[-- Type: text/plain, Size: 802 bytes --]

In case BOOTIF is not set and IFACES are not set in bonding/vlan/bridge code,
net-genrule.sh will fall to bring up all net interfaces.

Here add a failsafe option to read IFACES from /tmp/net.ifaces

[v1->v2]: move IFACES reading from net.ifaces after bonding/vlan/bridge info
code chunks.

Signed-off-by: Dave Young <dyoung-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
---
 modules.d/40network/net-genrules.sh |    2 ++
 1 file changed, 2 insertions(+)

--- dracut.orig/modules.d/40network/net-genrules.sh
+++ dracut/modules.d/40network/net-genrules.sh
@@ -39,6 +39,10 @@ fi
         IFACES+=" $phydevice"
     fi
 
+    if [ -n "$IFACES" ]; then
+        [ -e /tmp/net.ifaces ] && read IFACES < /tmp/net.ifaces
+    fi
+
     ifup='/sbin/ifup $env{INTERFACE}'
     [ -z "$netroot" ] && ifup="$ifup -m"
 

[patch 6/6 v2] Wait for interface up at the early stage

[dyoung-H+wXaHxf7aLQT0dZR+AlfA]

[-- Attachment #1: patch6 --]
[-- Type: text/plain, Size: 2457 bytes --]

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.

[v1->v2]: only wait for bootdev or it's possible to cause boot fail for 
waiting for non-bootdev. For example bond0->eth0, set bond0 as bootdev and
dhcp, we only need to wait bond0 setup ok.

Signed-off-by: Dave Young <dyoung-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
---
 modules.d/40network/ifup.sh         |    1 +
 modules.d/40network/net-genrules.sh |    9 +++++++++
 2 files changed, 10 insertions(+)

--- dracut.orig/modules.d/40network/net-genrules.sh
+++ dracut/modules.d/40network/net-genrules.sh
@@ -43,6 +43,10 @@ fi
         [ -e /tmp/net.ifaces ] && read IFACES < /tmp/net.ifaces
     fi
 
+    if [ -e /tmp/net.bootdev ]; then
+        bootdev=$(cat /tmp/net.bootdev)
+    fi
+
     ifup='/sbin/ifup $env{INTERFACE}'
     [ -z "$netroot" ] && ifup="$ifup -m"
 
@@ -51,14 +55,19 @@ 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 $ifup"
+            if [ "$bootdev" = "$iface" ]; then
+                echo "[ -f /tmp/setup_net_${iface}.ok ]" >$hookdir/initqueue/finished/wait-$iface.sh
+            fi
         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 $ifup" > /etc/udev/rules.d/91-default-net.rules
     fi
--- dracut.orig/modules.d/40network/ifup.sh
+++ dracut/modules.d/40network/ifup.sh
@@ -109,6 +109,7 @@ do_static() {
     [ -n "$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
 }