On 04/10/2019 07:40, Juergen Gross wrote: > sched_tick_suspend() and sched_tick_resume() should not call the > scheduler specific timer handlers in case the cpu they are running on > is just being moved to or from a cpupool. > > Use a new percpu lock for that purpose. > > Reported-by: Sergey Dyasli <sergey.dya...@citrix.com> > Signed-off-by: Juergen Gross <jgr...@suse.com> > --- > To be applied on top of my core scheduling series.
There is a somewhat interesting stack trace to go with this (XEN) Testing NMI watchdog on all CPUs: ok (XEN) ----[ Xen-4.13.0-8.0.12-d x86_64 debug=y Not tainted ]---- (XEN) CPU: 79 (XEN) RIP: e008:[<ffff82d0802467dc>] set_timer+0x39/0x1f7 (XEN) RFLAGS: 0000000000010002 CONTEXT: hypervisor <snip> (XEN) Xen call trace: (XEN) [<ffff82d0802467dc>] set_timer+0x39/0x1f7 (XEN) [<ffff82d08022c1f4>] sched_credit.c#csched_tick_resume+0x54/0x59 (XEN) [<ffff82d080241dfe>] sched_tick_resume+0x67/0x86 (XEN) [<ffff82d0802eda52>] mwait-idle.c#mwait_idle+0x32b/0x357 (XEN) [<ffff82d08027939e>] domain.c#idle_loop+0xa6/0xc2 (XEN) (XEN) Running stub recovery selftests... (XEN) Pagetable walk from 0000000000000048: (XEN) traps.c:1564: GPF (0000): ffff82d0bffff041 [ffff82d0bffff041] -> ffff82d0803893f2 (XEN) L4[0x000] = 00000082cfb9c063 ffffffffffffffff (XEN) traps.c:759: Trap 12: ffff82d0bffff040 [ffff82d0bffff040] -> ffff82d0803893f2 (XEN) L3[0x000] = 00000082cfb9b063 ffffffffffffffff (XEN) traps.c:1098: Trap 3: ffff82d0bffff041 [ffff82d0bffff041] -> ffff82d0803893f2 (XEN) L2[0x000] = 00000082cfb9a063 ffffffffffffffff (XEN) L1[0x000] = 0000000000000000 ffffffffffffffff (XEN) (XEN) **************************************** (XEN) Panic on CPU 79: (XEN) FATAL PAGE FAULT (XEN) [error_code=0000] (XEN) Faulting linear address: 0000000000000048 (XEN) **************************************** which demonstrates CPU 79 exploding straight out of idle, while the BSP is continuing to boot. ~Andrew _______________________________________________ Xen-devel mailing list Xen-devel@lists.xenproject.org https://lists.xenproject.org/mailman/listinfo/xen-devel
