Re: Use case for TASKS_RCU

o Molnar wrote: > > > > > > * Paul E. McKenney <paul...@linux.vnet.ibm.com> wrote: > > > > > > > Hello! > > > > > > > > The question of the use case for TASKS_RCU came up, and here is my > > > > understanding. Steve

Re: Use case for TASKS_RCU

E. McKenney wrote: > > > > > > > Hello! > > > > > > > > The question of the use case for TASKS_RCU came up, and here is my > > > > understanding. Steve will not be shy about correcting any > > > > misconceptions > > >

Re: Use case for TASKS_RCU

On Tue, May 23, 2017 at 04:38:53PM -0400, Steven Rostedt wrote: > On Tue, 23 May 2017 13:00:35 -0700 > "Paul E. McKenney" wrote: > > > > > > Unfortunately, it does not work, as I should have known ahead of > > > > time from the dyntick-idle experience. Not all

Re: Use case for TASKS_RCU

On Tue, May 23, 2017 at 04:38:53PM -0400, Steven Rostedt wrote: > On Tue, 23 May 2017 13:00:35 -0700 > "Paul E. McKenney" wrote: > > > > > > Unfortunately, it does not work, as I should have known ahead of > > > > time from the dyntick-idle experience. Not all context switches > > > > go

Re: Use case for TASKS_RCU

On Tue, 23 May 2017 13:00:35 -0700 "Paul E. McKenney" wrote: > > > Unfortunately, it does not work, as I should have known ahead of > > > time from the dyntick-idle experience. Not all context switches > > > go through context_switch(). :-/ > > > > Wait. What

Re: Use case for TASKS_RCU

On Tue, 23 May 2017 13:00:35 -0700 "Paul E. McKenney" wrote: > > > Unfortunately, it does not work, as I should have known ahead of > > > time from the dyntick-idle experience. Not all context switches > > > go through context_switch(). :-/ > > > > Wait. What context switch doesn't go

Re: Use case for TASKS_RCU

On Tue, May 23, 2017 at 03:39:39PM -0400, Steven Rostedt wrote: > On Mon, 22 May 2017 17:00:36 -0700 > "Paul E. McKenney" wrote: > > > > > > > Hmmm... The goal is to make sure that any task that was preempted > > > or running at a given point in time passes through

Re: Use case for TASKS_RCU

On Tue, May 23, 2017 at 03:39:39PM -0400, Steven Rostedt wrote: > On Mon, 22 May 2017 17:00:36 -0700 > "Paul E. McKenney" wrote: > > > > > > > Hmmm... The goal is to make sure that any task that was preempted > > > or running at a given point in time passes through a voluntary > > > context

Re: Use case for TASKS_RCU

On Mon, 22 May 2017 17:00:36 -0700 "Paul E. McKenney" wrote: > > > > Hmmm... The goal is to make sure that any task that was preempted > > or running at a given point in time passes through a voluntary > > context switch (or userspace execution, or, ...). > > > >

Re: Use case for TASKS_RCU

On Mon, 22 May 2017 17:00:36 -0700 "Paul E. McKenney" wrote: > > > > Hmmm... The goal is to make sure that any task that was preempted > > or running at a given point in time passes through a voluntary > > context switch (or userspace execution, or, ...). > > > > What is the simplest way to

Re: Use case for TASKS_RCU

On Tue, May 23, 2017 at 01:19:58AM -0400, Steven Rostedt wrote: > On Mon, 22 May 2017 17:00:36 -0700 > "Paul E. McKenney" wrote: > > > On Fri, May 19, 2017 at 12:06:09PM -0700, Paul E. McKenney wrote: > > > On Fri, May 19, 2017 at 10:23:31AM -0400, Steven Rostedt

Re: Use case for TASKS_RCU

On Tue, May 23, 2017 at 01:19:58AM -0400, Steven Rostedt wrote: > On Mon, 22 May 2017 17:00:36 -0700 > "Paul E. McKenney" wrote: > > > On Fri, May 19, 2017 at 12:06:09PM -0700, Paul E. McKenney wrote: > > > On Fri, May 19, 2017 at 10:23:31AM -0400, Steven Rostedt wrote: > > > > On Fri, 19 May

Re: Use case for TASKS_RCU

On Mon, 22 May 2017 17:00:36 -0700 "Paul E. McKenney" wrote: > On Fri, May 19, 2017 at 12:06:09PM -0700, Paul E. McKenney wrote: > > On Fri, May 19, 2017 at 10:23:31AM -0400, Steven Rostedt wrote: > > > On Fri, 19 May 2017 10:04:21 -0400 > > > Steven Rostedt

Re: Use case for TASKS_RCU

On Mon, 22 May 2017 17:00:36 -0700 "Paul E. McKenney" wrote: > On Fri, May 19, 2017 at 12:06:09PM -0700, Paul E. McKenney wrote: > > On Fri, May 19, 2017 at 10:23:31AM -0400, Steven Rostedt wrote: > > > On Fri, 19 May 2017 10:04:21 -0400 > > > Steven Rostedt wrote: > > > > > > > On Fri, 19

Re: Use case for TASKS_RCU

On Fri, May 19, 2017 at 12:06:09PM -0700, Paul E. McKenney wrote: > On Fri, May 19, 2017 at 10:23:31AM -0400, Steven Rostedt wrote: > > On Fri, 19 May 2017 10:04:21 -0400 > > Steven Rostedt wrote: > > > > > On Fri, 19 May 2017 06:35:50 -0700 > > > "Paul E. McKenney"

Re: Use case for TASKS_RCU

On Fri, May 19, 2017 at 12:06:09PM -0700, Paul E. McKenney wrote: > On Fri, May 19, 2017 at 10:23:31AM -0400, Steven Rostedt wrote: > > On Fri, 19 May 2017 10:04:21 -0400 > > Steven Rostedt wrote: > > > > > On Fri, 19 May 2017 06:35:50 -0700 > > > "Paul E. McKenney" wrote: > > > > > > >

Re: Use case for TASKS_RCU

On Fri, May 19, 2017 at 10:23:31AM -0400, Steven Rostedt wrote: > On Fri, 19 May 2017 10:04:21 -0400 > Steven Rostedt wrote: > > > On Fri, 19 May 2017 06:35:50 -0700 > > "Paul E. McKenney" wrote: > > > > > Simpler would be better! > > > > > >

Re: Use case for TASKS_RCU

On Fri, May 19, 2017 at 10:23:31AM -0400, Steven Rostedt wrote: > On Fri, 19 May 2017 10:04:21 -0400 > Steven Rostedt wrote: > > > On Fri, 19 May 2017 06:35:50 -0700 > > "Paul E. McKenney" wrote: > > > > > Simpler would be better! > > > > > > However, is it really guaranteed that one

Re: Use case for TASKS_RCU

On Fri, 19 May 2017 10:04:21 -0400 Steven Rostedt wrote: > On Fri, 19 May 2017 06:35:50 -0700 > "Paul E. McKenney" wrote: > > > Simpler would be better! > > > > However, is it really guaranteed that one SCHED_IDLE thread cannot > > preempt

Re: Use case for TASKS_RCU

On Fri, 19 May 2017 10:04:21 -0400 Steven Rostedt wrote: > On Fri, 19 May 2017 06:35:50 -0700 > "Paul E. McKenney" wrote: > > > Simpler would be better! > > > > However, is it really guaranteed that one SCHED_IDLE thread cannot > > preempt another? If not, then the trampoline-freeing

Re: Use case for TASKS_RCU

On Fri, 19 May 2017 06:35:50 -0700 "Paul E. McKenney" wrote: > Simpler would be better! > > However, is it really guaranteed that one SCHED_IDLE thread cannot > preempt another? If not, then the trampoline-freeing SCHED_IDLE thread > might preempt some other

Re: Use case for TASKS_RCU

On Fri, 19 May 2017 06:35:50 -0700 "Paul E. McKenney" wrote: > Simpler would be better! > > However, is it really guaranteed that one SCHED_IDLE thread cannot > preempt another? If not, then the trampoline-freeing SCHED_IDLE thread > might preempt some other SCHED_IDLE thread in the middle of

Re: Use case for TASKS_RCU

.vnet.ibm.com> wrote: > > > > > > > Hello! > > > > > > > > The question of the use case for TASKS_RCU came up, and here is my > > > > understanding. Steve will not be shy about correcting any > > > > misconceptions > > &g

Re: Use case for TASKS_RCU

On Fri, May 19, 2017 at 08:23:31AM +0200, Ingo Molnar wrote: > > * Paul E. McKenney wrote: > > > On Tue, May 16, 2017 at 08:22:33AM +0200, Ingo Molnar wrote: > > > > > > * Paul E. McKenney wrote: > > > > > > > Hello! > > >

Re: Use case for TASKS_RCU

* Paul E. McKenney <paul...@linux.vnet.ibm.com> wrote: > On Tue, May 16, 2017 at 08:22:33AM +0200, Ingo Molnar wrote: > > > > * Paul E. McKenney <paul...@linux.vnet.ibm.com> wrote: > > > > > Hello! > > > > > > The qu

Re: Use case for TASKS_RCU

* Paul E. McKenney wrote: > On Tue, May 16, 2017 at 08:22:33AM +0200, Ingo Molnar wrote: > > > > * Paul E. McKenney wrote: > > > > > Hello! > > > > > > The question of the use case for TASKS_RCU came up, and here is my > > > u

Re: Use case for TASKS_RCU

On Tue, 16 May 2017 05:23:54 -0700 "Paul E. McKenney" <paul...@linux.vnet.ibm.com> wrote: > On Tue, May 16, 2017 at 08:22:33AM +0200, Ingo Molnar wrote: > > > > * Paul E. McKenney <paul...@linux.vnet.ibm.com> wrote: > > > > > Hello! > >

Re: Use case for TASKS_RCU

On Tue, 16 May 2017 05:23:54 -0700 "Paul E. McKenney" wrote: > On Tue, May 16, 2017 at 08:22:33AM +0200, Ingo Molnar wrote: > > > > * Paul E. McKenney wrote: > > > > > Hello! > > > > > > The question of the use case for TAS

Re: Use case for TASKS_RCU

On Tue, May 16, 2017 at 08:22:33AM +0200, Ingo Molnar wrote: > > * Paul E. McKenney <paul...@linux.vnet.ibm.com> wrote: > > > Hello! > > > > The question of the use case for TASKS_RCU came up, and here is my > > understanding. Steve will not be shy ab

Re: Use case for TASKS_RCU

On Tue, May 16, 2017 at 08:22:33AM +0200, Ingo Molnar wrote: > > * Paul E. McKenney wrote: > > > Hello! > > > > The question of the use case for TASKS_RCU came up, and here is my > > understanding. Steve will not be shy about correcting an

Re: Use case for TASKS_RCU

* Paul E. McKenney <paul...@linux.vnet.ibm.com> wrote: > Hello! > > The question of the use case for TASKS_RCU came up, and here is my > understanding. Steve will not be shy about correcting any misconceptions > I might have. ;-) > > The use case is to support

Re: Use case for TASKS_RCU

* Paul E. McKenney wrote: > Hello! > > The question of the use case for TASKS_RCU came up, and here is my > understanding. Steve will not be shy about correcting any misconceptions > I might have. ;-) > > The use case is to support freeing of trampolines us

Re: Use case for TASKS_RCU

On Mon, May 15, 2017 at 02:48:10PM -0400, Steven Rostedt wrote: > On Mon, 15 May 2017 11:23:54 -0700 > "Paul E. McKenney" <paul...@linux.vnet.ibm.com> wrote: > > > Hello! > > > > The question of the use case for TASKS_RCU came up, and here is my >

Re: Use case for TASKS_RCU

On Mon, May 15, 2017 at 02:48:10PM -0400, Steven Rostedt wrote: > On Mon, 15 May 2017 11:23:54 -0700 > "Paul E. McKenney" wrote: > > > Hello! > > > > The question of the use case for TASKS_RCU came up, and here is my > > understanding. Steve will not

Re: Use case for TASKS_RCU

On Mon, 15 May 2017 11:23:54 -0700 "Paul E. McKenney" <paul...@linux.vnet.ibm.com> wrote: > Hello! > > The question of the use case for TASKS_RCU came up, and here is my > understanding. Steve will not be shy about correcting any misconceptions > I mig

Re: Use case for TASKS_RCU

On Mon, 15 May 2017 11:23:54 -0700 "Paul E. McKenney" wrote: > Hello! > > The question of the use case for TASKS_RCU came up, and here is my > understanding. Steve will not be shy about correcting any misconceptions > I might have. ;-) > > The use case is to

Use case for TASKS_RCU

Hello! The question of the use case for TASKS_RCU came up, and here is my understanding. Steve will not be shy about correcting any misconceptions I might have. ;-) The use case is to support freeing of trampolines used in tracing/probing in CONFIG_PREEMPT=y kernels. It is necessary to wait

Use case for TASKS_RCU

Hello! The question of the use case for TASKS_RCU came up, and here is my understanding. Steve will not be shy about correcting any misconceptions I might have. ;-) The use case is to support freeing of trampolines used in tracing/probing in CONFIG_PREEMPT=y kernels. It is necessary to wait