On Thu, 2017-06-08 at 17:41 +0200, Rouven Spreckels wrote: > Package: src:linux > Version: 4.9.30-1 > Severity: critical > Tags: patch upstream > Justification: causes serious data loss > > Hello, > > the igb/e1000e driver causes a soft lockup when doing stats updates. > For instance, when using the ledtrig-netdev kernel module to > visualize network activity via LEDs. The lockup mostly happens within > the first 3 days of uptime, probably depending on network activity: > > [168313.275259] NMI watchdog: BUG: soft lockup - CPU#2 stuck for 22s! > [kworker/2:1:46] > [168323.276973] INFO: rcu_sched self-detected stall on CPU > [168323.282239] 2-...: (1 GPs behind) > idle=337/140000000000002/0 softirq=359087/359089 fqs=14081745 > [168323.291202] (t=28187367 jiffies g=247240 c=247239 > q=1072734) > > The attached patch fixes the problem and originates from: > http://git.ipfire.org/?p=people/arne_f/ipfire- > 2.x.git;a=commit;h=fcffac1340f61923786af8a860c12056a9ef3706
I'm not sure this patch is correct. Has anyone submitted it upstream (netdev or intel-wired-lan list)? Ben. -- Ben Hutchings Unix is many things to many people, but it's never been everything to anybody.
signature.asc
Description: This is a digitally signed message part