Messages in this thread | | | Date | Mon, 9 Jan 2006 09:20:47 -0800 | From | "Paul E. McKenney" <> | Subject | Re: [PATCH 1/5] rcu: uninline __rcu_pending() |
| |
On Sun, Jan 08, 2006 at 10:19:16PM +0300, Oleg Nesterov wrote: > __rcu_pending() is rather fat and called twice from rcu_pending(). > > rcu_pending() has multiple callers, and not that small too. > > This patch uninlines both of them.
Looks good -- I must defer to Dipankar on any performance problems, but I would not expect any this far off of the fastpaths. Also makes handling multiple different RCU implementations a bit easier on the eyes.
Thanx, Paul
Acked-by: Paul E. McKenney <paulmck@us.ibm.com> > Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> > > --- 2.6.15/include/linux/rcupdate.h~1_OUTL 2006-01-03 21:15:58.000000000 +0300 > +++ 2.6.15/include/linux/rcupdate.h 2006-01-08 21:36:07.000000000 +0300 > @@ -125,36 +125,7 @@ static inline void rcu_bh_qsctr_inc(int > rdp->passed_quiesc = 1; > } > > -static inline int __rcu_pending(struct rcu_ctrlblk *rcp, > - struct rcu_data *rdp) > -{ > - /* This cpu has pending rcu entries and the grace period > - * for them has completed. > - */ > - if (rdp->curlist && !rcu_batch_before(rcp->completed, rdp->batch)) > - return 1; > - > - /* This cpu has no pending entries, but there are new entries */ > - if (!rdp->curlist && rdp->nxtlist) > - return 1; > - > - /* This cpu has finished callbacks to invoke */ > - if (rdp->donelist) > - return 1; > - > - /* The rcu core waits for a quiescent state from the cpu */ > - if (rdp->quiescbatch != rcp->cur || rdp->qs_pending) > - return 1; > - > - /* nothing to do */ > - return 0; > -} > - > -static inline int rcu_pending(int cpu) > -{ > - return __rcu_pending(&rcu_ctrlblk, &per_cpu(rcu_data, cpu)) || > - __rcu_pending(&rcu_bh_ctrlblk, &per_cpu(rcu_bh_data, cpu)); > -} > +extern int rcu_pending(int cpu); > > /** > * rcu_read_lock - mark the beginning of an RCU read-side critical section. > --- 2.6.15/kernel/rcupdate.c~1_OUTL 2006-01-03 21:15:58.000000000 +0300 > +++ 2.6.15/kernel/rcupdate.c 2006-01-08 21:35:21.000000000 +0300 > @@ -442,6 +442,36 @@ static void rcu_process_callbacks(unsign > &__get_cpu_var(rcu_bh_data)); > } > > +static int __rcu_pending(struct rcu_ctrlblk *rcp, struct rcu_data *rdp) > +{ > + /* This cpu has pending rcu entries and the grace period > + * for them has completed. > + */ > + if (rdp->curlist && !rcu_batch_before(rcp->completed, rdp->batch)) > + return 1; > + > + /* This cpu has no pending entries, but there are new entries */ > + if (!rdp->curlist && rdp->nxtlist) > + return 1; > + > + /* This cpu has finished callbacks to invoke */ > + if (rdp->donelist) > + return 1; > + > + /* The rcu core waits for a quiescent state from the cpu */ > + if (rdp->quiescbatch != rcp->cur || rdp->qs_pending) > + return 1; > + > + /* nothing to do */ > + return 0; > +} > + > +int rcu_pending(int cpu) > +{ > + return __rcu_pending(&rcu_ctrlblk, &per_cpu(rcu_data, cpu)) || > + __rcu_pending(&rcu_bh_ctrlblk, &per_cpu(rcu_bh_data, cpu)); > +} > + > void rcu_check_callbacks(int cpu, int user) > { > if (user || > - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |