Re: RFC: SysRq nice-all-RT-tasks is broken

On 08/03/2017 18:46, Steven Rostedt wrote: > On Wed, 8 Mar 2017 12:40:12 -0500 > Steven Rostedt wrote: > >> I wonder if we should just have a special flag sent by that sysrq >> trigger. Since it is causing all tasks to go "nice" there's no need to >> do the pi chain walk in

Re: RFC: SysRq nice-all-RT-tasks is broken

On 08/03/2017 18:46, Steven Rostedt wrote: > On Wed, 8 Mar 2017 12:40:12 -0500 > Steven Rostedt wrote: > >> I wonder if we should just have a special flag sent by that sysrq >> trigger. Since it is causing all tasks to go "nice" there's no need to >> do the pi chain walk in

Re: RFC: SysRq nice-all-RT-tasks is broken

On 08/03/2017 17:57, Steven Rostedt wrote: > On Wed, 8 Mar 2017 11:51:14 -0500 > Steven Rostedt wrote: > > >> Hmm, that commit was added in 2.6.18, and you're right, a lot has >> changed since then. Have you tried removing it and running it under >> lockdep, and see if it

Re: RFC: SysRq nice-all-RT-tasks is broken

On 08/03/2017 17:57, Steven Rostedt wrote: > On Wed, 8 Mar 2017 11:51:14 -0500 > Steven Rostedt wrote: > > >> Hmm, that commit was added in 2.6.18, and you're right, a lot has >> changed since then. Have you tried removing it and running it under >> lockdep, and see if it triggers any warnings?

Re: RFC: SysRq nice-all-RT-tasks is broken

On Wed, 8 Mar 2017 12:40:12 -0500 Steven Rostedt wrote: > I wonder if we should just have a special flag sent by that sysrq > trigger. Since it is causing all tasks to go "nice" there's no need to > do the pi chain walk in __sched_setscheduler(). Hah, there already is a

Re: RFC: SysRq nice-all-RT-tasks is broken

On Wed, 8 Mar 2017 12:40:12 -0500 Steven Rostedt wrote: > I wonder if we should just have a special flag sent by that sysrq > trigger. Since it is causing all tasks to go "nice" there's no need to > do the pi chain walk in __sched_setscheduler(). Hah, there already is a flag! Laurent, can you

Re: RFC: SysRq nice-all-RT-tasks is broken

[ Added Peter Update: Laurent noticed that sysrq 'n' (nice-all-RT-tasks) calls __sched_setscheduler() form interrupt context. At the start of that function, there's a BUG_ON(in_interrupt()). The reason for that was due to the rt mutex pi code calling wait_lock. Which was not irq

Re: RFC: SysRq nice-all-RT-tasks is broken

[ Added Peter Update: Laurent noticed that sysrq 'n' (nice-all-RT-tasks) calls __sched_setscheduler() form interrupt context. At the start of that function, there's a BUG_ON(in_interrupt()). The reason for that was due to the rt mutex pi code calling wait_lock. Which was not irq

Re: RFC: SysRq nice-all-RT-tasks is broken

On Wed, 8 Mar 2017 11:51:14 -0500 Steven Rostedt wrote: > Hmm, that commit was added in 2.6.18, and you're right, a lot has > changed since then. Have you tried removing it and running it under > lockdep, and see if it triggers any warnings? I did a little digging, and it

Re: RFC: SysRq nice-all-RT-tasks is broken

On Wed, 8 Mar 2017 11:51:14 -0500 Steven Rostedt wrote: > Hmm, that commit was added in 2.6.18, and you're right, a lot has > changed since then. Have you tried removing it and running it under > lockdep, and see if it triggers any warnings? I did a little digging, and it appears that its the

Re: RFC: SysRq nice-all-RT-tasks is broken

On Wed, 8 Mar 2017 16:23:35 +0100 Laurent Dufour wrote: > I got it on Power and on X86_64, but I guess it should happen in all > architectures. > Here are the steps to recreate it : > 1. Create a RT task : sudo chrt -f 50 /bin/sleep 99 > 2. On the console trigger

Re: RFC: SysRq nice-all-RT-tasks is broken

On Wed, 8 Mar 2017 16:23:35 +0100 Laurent Dufour wrote: > I got it on Power and on X86_64, but I guess it should happen in all > architectures. > Here are the steps to recreate it : > 1. Create a RT task : sudo chrt -f 50 /bin/sleep 99 > 2. On the console trigger the 'nice-all-RT-tasks'

RFC: SysRq nice-all-RT-tasks is broken

Hi, It appears that triggering the SysRq nice-all-RT-tasks from the console while a real task is active is leading to panic the system like this : sysrq: SysRq : Nice All RT Tasks [ cut here ] kernel BUG at /build/linux-twbIHf/linux-4.10.0/kernel/sched/core.c:4089!

RFC: SysRq nice-all-RT-tasks is broken

Hi, It appears that triggering the SysRq nice-all-RT-tasks from the console while a real task is active is leading to panic the system like this : sysrq: SysRq : Nice All RT Tasks [ cut here ] kernel BUG at /build/linux-twbIHf/linux-4.10.0/kernel/sched/core.c:4089!