diff options
| author | Paul E. McKenney <paulmck@linux.vnet.ibm.com> | 2018-02-02 09:05:38 +0300 |
|---|---|---|
| committer | Paul E. McKenney <paulmck@linux.vnet.ibm.com> | 2018-05-15 20:25:44 +0300 |
| commit | 25f3d7effab632eb10d145f1a5aebf6515a04b98 (patch) | |
| tree | 8f088c805ed43c898543f1e74d21e808605143fc /kernel/rcu/rcu.h | |
| parent | 60cc43fc888428bb2f18f08997432d426a243338 (diff) | |
| download | linux-25f3d7effab632eb10d145f1a5aebf6515a04b98.tar.xz | |
rcu: Parallelize expedited grace-period initialization
The latency of RCU expedited grace periods grows with increasing numbers
of CPUs, eventually failing to be all that expedited. Much of the growth
in latency is in the initialization phase, so this commit uses workqueues
to carry out this initialization concurrently on a rcu_node-by-rcu_node
basis.
This change makes use of a new rcu_par_gp_wq because flushing a work
item from another work item running from the same workqueue can result
in deadlock.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Tested-by: Nicholas Piggin <npiggin@gmail.com>
Diffstat (limited to 'kernel/rcu/rcu.h')
| -rw-r--r-- | kernel/rcu/rcu.h | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h index 7a693e31184a..976019d6fa06 100644 --- a/kernel/rcu/rcu.h +++ b/kernel/rcu/rcu.h @@ -486,6 +486,7 @@ void rcu_force_quiescent_state(void); void rcu_bh_force_quiescent_state(void); void rcu_sched_force_quiescent_state(void); extern struct workqueue_struct *rcu_gp_wq; +extern struct workqueue_struct *rcu_par_gp_wq; #endif /* #else #ifdef CONFIG_TINY_RCU */ #ifdef CONFIG_RCU_NOCB_CPU |