* Re: [tip:core/rcu] sched,rcu: Make cond_resched() provide RCU quiescent state [not found] <tip-f79c3ad6189624c3de0ad5521610c9e22a1c33cf@git.kernel.org> @ 2017-10-24 10:59 ` Michal Hocko 2017-10-24 15:52 ` Paul E. McKenney 0 siblings, 1 reply; 3+ messages in thread From: Michal Hocko @ 2017-10-24 10:59 UTC (permalink / raw) To: linux-kernel, peterz, tglx, mingo, hpa, paulmck; +Cc: linux-tip-commits On Tue 24-10-17 03:02:09, tip-bot for Paul E. McKenney wrote: > Commit-ID: f79c3ad6189624c3de0ad5521610c9e22a1c33cf > Gitweb: https://git.kernel.org/tip/f79c3ad6189624c3de0ad5521610c9e22a1c33cf > Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com> > AuthorDate: Wed, 30 Nov 2016 06:24:30 -0800 > Committer: Paul E. McKenney <paulmck@linux.vnet.ibm.com> > CommitDate: Mon, 9 Oct 2017 14:25:17 -0700 > > sched,rcu: Make cond_resched() provide RCU quiescent state > > There is some confusion as to which of cond_resched() or > cond_resched_rcu_qs() should be added to long in-kernel loops. > This commit therefore eliminates the decision by adding RCU quiescent > states to cond_resched(). This commit also simplifies the code that > used to interact with cond_resched_rcu_qs(), and that now interacts with > cond_resched(), to reduce its overhead. This reduction is necessary to > allow the heavier-weight cond_resched_rcu_qs() mechanism to be invoked > everywhere that cond_resched() is invoked. > > Part of that reduction in overhead converts the jiffies_till_sched_qs > kernel parameter to read-only at runtime, thus eliminating the need for > bounds checking. Thanks a lot Paul! I have just one question. Does the above mean that we can drop cond_resched_rcu_qs? Or there are still some scenarios when this is a better option? -- Michal Hocko SUSE Labs ^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [tip:core/rcu] sched,rcu: Make cond_resched() provide RCU quiescent state 2017-10-24 10:59 ` [tip:core/rcu] sched,rcu: Make cond_resched() provide RCU quiescent state Michal Hocko @ 2017-10-24 15:52 ` Paul E. McKenney 2017-10-24 16:34 ` Michal Hocko 0 siblings, 1 reply; 3+ messages in thread From: Paul E. McKenney @ 2017-10-24 15:52 UTC (permalink / raw) To: Michal Hocko; +Cc: linux-kernel, peterz, tglx, mingo, hpa, linux-tip-commits On Tue, Oct 24, 2017 at 12:59:03PM +0200, Michal Hocko wrote: > On Tue 24-10-17 03:02:09, tip-bot for Paul E. McKenney wrote: > > Commit-ID: f79c3ad6189624c3de0ad5521610c9e22a1c33cf > > Gitweb: https://git.kernel.org/tip/f79c3ad6189624c3de0ad5521610c9e22a1c33cf > > Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com> > > AuthorDate: Wed, 30 Nov 2016 06:24:30 -0800 > > Committer: Paul E. McKenney <paulmck@linux.vnet.ibm.com> > > CommitDate: Mon, 9 Oct 2017 14:25:17 -0700 > > > > sched,rcu: Make cond_resched() provide RCU quiescent state > > > > There is some confusion as to which of cond_resched() or > > cond_resched_rcu_qs() should be added to long in-kernel loops. > > This commit therefore eliminates the decision by adding RCU quiescent > > states to cond_resched(). This commit also simplifies the code that > > used to interact with cond_resched_rcu_qs(), and that now interacts with > > cond_resched(), to reduce its overhead. This reduction is necessary to > > allow the heavier-weight cond_resched_rcu_qs() mechanism to be invoked > > everywhere that cond_resched() is invoked. > > > > Part of that reduction in overhead converts the jiffies_till_sched_qs > > kernel parameter to read-only at runtime, thus eliminating the need for > > bounds checking. > > Thanks a lot Paul! I have just one question. Does the above mean that we > can drop cond_resched_rcu_qs? Or there are still some scenarios when > this is a better option? Good point, and no time like the present! Please see commits cc1c305fff49 ("netfilter: Eliminate cond_resched_rcu_qs() in favor of cond_resched()") through cca9c4def233 ("rcu: Eliminate the cond_resched_rcu_qs() definition") in my -rcu tree: git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git Thanx, Paul ^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [tip:core/rcu] sched,rcu: Make cond_resched() provide RCU quiescent state 2017-10-24 15:52 ` Paul E. McKenney @ 2017-10-24 16:34 ` Michal Hocko 0 siblings, 0 replies; 3+ messages in thread From: Michal Hocko @ 2017-10-24 16:34 UTC (permalink / raw) To: Paul E. McKenney Cc: linux-kernel, peterz, tglx, mingo, hpa, linux-tip-commits On Tue 24-10-17 08:52:14, Paul E. McKenney wrote: > On Tue, Oct 24, 2017 at 12:59:03PM +0200, Michal Hocko wrote: > > On Tue 24-10-17 03:02:09, tip-bot for Paul E. McKenney wrote: > > > Commit-ID: f79c3ad6189624c3de0ad5521610c9e22a1c33cf > > > Gitweb: https://git.kernel.org/tip/f79c3ad6189624c3de0ad5521610c9e22a1c33cf > > > Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com> > > > AuthorDate: Wed, 30 Nov 2016 06:24:30 -0800 > > > Committer: Paul E. McKenney <paulmck@linux.vnet.ibm.com> > > > CommitDate: Mon, 9 Oct 2017 14:25:17 -0700 > > > > > > sched,rcu: Make cond_resched() provide RCU quiescent state > > > > > > There is some confusion as to which of cond_resched() or > > > cond_resched_rcu_qs() should be added to long in-kernel loops. > > > This commit therefore eliminates the decision by adding RCU quiescent > > > states to cond_resched(). This commit also simplifies the code that > > > used to interact with cond_resched_rcu_qs(), and that now interacts with > > > cond_resched(), to reduce its overhead. This reduction is necessary to > > > allow the heavier-weight cond_resched_rcu_qs() mechanism to be invoked > > > everywhere that cond_resched() is invoked. > > > > > > Part of that reduction in overhead converts the jiffies_till_sched_qs > > > kernel parameter to read-only at runtime, thus eliminating the need for > > > bounds checking. > > > > Thanks a lot Paul! I have just one question. Does the above mean that we > > can drop cond_resched_rcu_qs? Or there are still some scenarios when > > this is a better option? > > Good point, and no time like the present! Please see commits cc1c305fff49 > ("netfilter: Eliminate cond_resched_rcu_qs() in favor of cond_resched()") > through cca9c4def233 ("rcu: Eliminate the cond_resched_rcu_qs() > definition") in my -rcu tree: cool stuff. Thanks! -- Michal Hocko SUSE Labs ^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2017-10-24 16:34 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
[not found] <tip-f79c3ad6189624c3de0ad5521610c9e22a1c33cf@git.kernel.org>
2017-10-24 10:59 ` [tip:core/rcu] sched,rcu: Make cond_resched() provide RCU quiescent state Michal Hocko
2017-10-24 15:52 ` Paul E. McKenney
2017-10-24 16:34 ` Michal Hocko
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox