Messages in this thread | | | Date | Mon, 20 Dec 2010 03:14:13 +0100 | From | Frederic Weisbecker <> | Subject | Re: [PATCH RFC tip/core/rcu 15/20] rcu: Keep gpnum and completed fields synchronized |
| |
On Mon, Dec 20, 2010 at 10:13:35AM +0800, Lai Jiangshan wrote: > On 12/18/2010 04:54 AM, Paul E. McKenney wrote: > > From: Frederic Weisbecker <fweisbec@gmail.com> > > > > When a CPU that was in an extended quiescent state wakes > > up and catches up with grace periods that remote CPUs > > completed on its behalf, we update the completed field > > but not the gpnum that keeps a stale value of a backward > > grace period ID. > > > > Later, note_new_gpnum() will interpret the shift between > > the local CPU and the node grace period ID as some new grace > > period to handle and will then start to hunt quiescent state. > > > > But if every grace periods have already been completed, this > > interpretation becomes broken. And we'll be stuck in clusters > > of spurious softirqs because rcu_report_qs_rdp() will make > > this broken state run into infinite loop. > > > > The solution, as suggested by Lai Jiangshan, is to ensure that > > the gpnum and completed fields are well synchronized when we catch > > up with completed grace periods on their behalf by other cpus. > > This way we won't start noting spurious new grace periods. > > > > Suggested-by: Lai Jiangshan <laijs@cn.fujitsu.com> > > Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> > > Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> > > Cc: Ingo Molnar <mingo@elte.hu> > > Cc: Thomas Gleixner <tglx@linutronix.de> > > Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> > > Cc: Steven Rostedt <rostedt@goodmis.org > > Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> > > --- > > kernel/rcutree.c | 9 +++++++++ > > 1 files changed, 9 insertions(+), 0 deletions(-) > > > > diff --git a/kernel/rcutree.c b/kernel/rcutree.c > > index 916f42b..8105271 100644 > > --- a/kernel/rcutree.c > > +++ b/kernel/rcutree.c > > @@ -680,6 +680,15 @@ __rcu_process_gp_end(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_dat > > rdp->completed = rnp->completed; > > > > /* > > + * If we were in an extended quiescent state, we may have > > + * missed some grace periods that others CPUs took care on > > + * our behalf. Catch up with this state to avoid noting > > + * spurious new grace periods. > > + */ > > + if (rdp->completed > rdp->gpnum) > > + rdp->gpnum = rdp->completed; > > Need to use ULONG_CMP_LT(rdp->gpnum, rdp->completed) instead.
Paul fixed that in:
[PATCH RFC tip/core/rcu 16/20] rcu: fine-tune grace-period begin/end checks
| |