mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
To: linux-kernel@vger.kernel.org
Cc: mingo@kernel.org, jiangshanlai@gmail.com, dipankar@in.ibm.com,
	akpm@linux-foundation.org, mathieu.desnoyers@efficios.com,
	josh@joshtriplett.org, tglx@linutronix.de, peterz@infradead.org,
	rostedt@goodmis.org, dhowells@redhat.com, edumazet@google.com,
	fweisbec@gmail.com, oleg@redhat.com, joel@joelfernandes.org,
	"Paul E . McKenney" <paulmck@linux.vnet.ibm.com>
Subject: [PATCH tip/core/rcu 40/40] rcu: Identify grace period is in progress as we advance up the tree
Date: Mon, 25 Jun 2018 17:08:59 -0700	[thread overview]
Message-ID: <20180626000859.23572-40-paulmck@linux.vnet.ibm.com> (raw)
In-Reply-To: <20180626000841.GA15696@linux.vnet.ibm.com>

From: "Joel Fernandes (Google)" <joel@joelfernandes.org>

There's no need to keep checking the same starting node for whether a
grace period is in progress as we advance up the funnel lock loop. Its
sufficient if we just checked it in the start, and then subsequently
checked the internal nodes as we advanced up the combining tree. This
also makes sense because the grace-period updates propogate from the
root to the leaf, so there's a chance we may find a grace period has
started as we advance up, lets check for the same.

Reported-by: Paul McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 0dac8c716c48..73298a27620f 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1598,11 +1598,12 @@ static bool rcu_start_this_gp(struct rcu_node *rnp_start, struct rcu_data *rdp,
 			goto unlock_out;
 		}
 		rnp->gp_seq_needed = gp_seq_req;
-		if (rcu_seq_state(rcu_seq_current(&rnp_start->gp_seq))) {
+		if (rcu_seq_state(rcu_seq_current(&rnp->gp_seq))) {
 			/*
-			 * We just marked the leaf, and a grace period
-			 * is in progress, which means that rcu_gp_cleanup()
-			 * will see the marking.  Bail to reduce contention.
+			 * We just marked the leaf or internal node, and a
+			 * grace period is in progress, which means that
+			 * rcu_gp_cleanup() will see the marking.  Bail to
+			 * reduce contention.
 			 */
 			trace_rcu_this_gp(rnp_start, rdp, gp_seq_req,
 					  TPS("Startedleaf"));
-- 
2.17.1


      parent reply	other threads:[~2018-06-26  0:12 UTC|newest]

Thread overview: 41+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-06-26  0:08 [PATCH tip/core/rcu 0/40] RCU ->gp_seq conversion for v4.19 Paul E. McKenney
2018-06-26  0:08 ` [PATCH tip/core/rcu 01/40] rcu: Introduce grace-period sequence numbers Paul E. McKenney
2018-06-26  0:08 ` [PATCH tip/core/rcu 02/40] rcu: Move rcu_gp_slow() to ->gp_seq Paul E. McKenney
2018-06-26  0:08 ` [PATCH tip/core/rcu 03/40] rcu: Make rcutorture's batches-completed API use ->gp_seq Paul E. McKenney
2018-06-26  0:08 ` [PATCH tip/core/rcu 04/40] rcu: Convert rcu_check_gp_kthread_starvation() to GP sequence number Paul E. McKenney
2018-06-26  0:08 ` [PATCH tip/core/rcu 05/40] rcu: Make quiescent-state reporting use ->gp_seq Paul E. McKenney
2018-06-26  0:08 ` [PATCH tip/core/rcu 06/40] rcu: Convert conditional grace-period primitives to ->gp_seq Paul E. McKenney
2018-06-26  0:08 ` [PATCH tip/core/rcu 07/40] rcu: Move RCU's grace-period-change code " Paul E. McKenney
2018-06-26  0:08 ` [PATCH tip/core/rcu 08/40] rcu: Convert rcu_gpnum_ovf() " Paul E. McKenney
2018-06-26  0:08 ` [PATCH tip/core/rcu 09/40] rcu: Move rcu_implicit_dynticks_qs() " Paul E. McKenney
2018-06-26  0:08 ` [PATCH tip/core/rcu 10/40] rcu: Move rcu_try_advance_all_cbs() " Paul E. McKenney
2018-06-26  0:08 ` [PATCH tip/core/rcu 11/40] rcu: Move rcu_nocb_gp_get() " Paul E. McKenney
2018-06-26  0:08 ` [PATCH tip/core/rcu 12/40] rcu: Move rcu_gp_in_progress() " Paul E. McKenney
2018-06-26  0:08 ` [PATCH tip/core/rcu 13/40] rcu: Convert ->rcu_iw_gpnum " Paul E. McKenney
2018-06-26  0:08 ` [PATCH tip/core/rcu 14/40] rcu: Convert ->completedqs " Paul E. McKenney
2018-06-26  0:08 ` [PATCH tip/core/rcu 15/40] rcu: Convert grace-period requests " Paul E. McKenney
2018-06-26  0:08 ` [PATCH tip/core/rcu 16/40] rcu: Make RCU CPU stall warnings use ->gp_seq Paul E. McKenney
2018-06-26  0:08 ` [PATCH tip/core/rcu 17/40] rcutorture: Convert rcutorture_get_gp_data() to ->gp_seq Paul E. McKenney
2018-06-26  0:08 ` [PATCH tip/core/rcu 18/40] rcu: Move from ->need_future_gp[] to ->gp_seq_needed Paul E. McKenney
2018-06-26  0:08 ` [PATCH tip/core/rcu 19/40] rcu: Make rcu_nocb_wait_gp() check if GP already requested Paul E. McKenney
2018-06-26  0:08 ` [PATCH tip/core/rcu 20/40] rcu: Convert rcu_grace_period tracepoint to gp_seq Paul E. McKenney
2018-06-26  0:08 ` [PATCH tip/core/rcu 21/40] rcu: Convert rcu_future_grace_period " Paul E. McKenney
2018-06-26  0:08 ` [PATCH tip/core/rcu 22/40] rcu: Convert rcu_grace_period_init " Paul E. McKenney
2018-06-26  0:08 ` [PATCH tip/core/rcu 23/40] rcu: Convert rcu_preempt_task tracepoint to ->gp_seq Paul E. McKenney
2018-06-26  0:08 ` [PATCH tip/core/rcu 24/40] rcu: Convert rcu_unlock_preempted_task " Paul E. McKenney
2018-06-26  0:08 ` [PATCH tip/core/rcu 25/40] rcu: Convert rcu_quiescent_state_report " Paul E. McKenney
2018-06-26  0:08 ` [PATCH tip/core/rcu 26/40] rcu: Convert rcu_fqs " Paul E. McKenney
2018-06-26  0:08 ` [PATCH tip/core/rcu 27/40] rcu: Remove ->gpnum and ->completed Paul E. McKenney
2018-06-26  0:08 ` [PATCH tip/core/rcu 28/40] rcu: Make simple callback acceleration refer to rdp->gp_seq_needed Paul E. McKenney
2018-06-26  0:08 ` [PATCH tip/core/rcu 29/40] doc: Update data-structure documentation for ->gp_seq Paul E. McKenney
2018-06-26  0:08 ` [PATCH tip/core/rcu 30/40] doc: Update memory-ordering documentation for ->gp-seq Paul E. McKenney
2018-06-26  0:08 ` [PATCH tip/core/rcu 31/40] doc: Update RCU CPU stall-warning documentation Paul E. McKenney
2018-06-26  0:08 ` [PATCH tip/core/rcu 32/40] rcu: Don't funnel-lock above leaf node if GP in progress Paul E. McKenney
2018-06-26  0:08 ` [PATCH tip/core/rcu 33/40] rcu: Produce last "CleanupMore" trace only if late-breaking request Paul E. McKenney
2018-06-26  0:08 ` [PATCH tip/core/rcu 34/40] rcu: Fix cpustart tracepoint gp_seq number Paul E. McKenney
2018-06-26  0:08 ` [PATCH tip/core/rcu 35/40] rcu: Make rcu_start_this_gp() check for grace period already started Paul E. McKenney
2018-06-26  0:08 ` [PATCH tip/core/rcu 36/40] rcutorture: Correctly handle grace-period sequence wrap Paul E. McKenney
2018-06-26  0:08 ` [PATCH tip/core/rcu 37/40] rcu: Regularize resetting of rcu_data wrap indicator Paul E. McKenney
2018-06-26  0:08 ` [PATCH tip/core/rcu 38/40] rcu: Rename the grace-period-request variables and parameters Paul E. McKenney
2018-06-26  0:08 ` [PATCH tip/core/rcu 39/40] rcu: Use better variable names in funnel locking loop Paul E. McKenney
2018-06-26  0:08 ` Paul E. McKenney [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20180626000859.23572-40-paulmck@linux.vnet.ibm.com \
    --to=paulmck@linux.vnet.ibm.com \
    --cc=akpm@linux-foundation.org \
    --cc=dhowells@redhat.com \
    --cc=dipankar@in.ibm.com \
    --cc=edumazet@google.com \
    --cc=fweisbec@gmail.com \
    --cc=jiangshanlai@gmail.com \
    --cc=joel@joelfernandes.org \
    --cc=josh@joshtriplett.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mathieu.desnoyers@efficios.com \
    --cc=mingo@kernel.org \
    --cc=oleg@redhat.com \
    --cc=peterz@infradead.org \
    --cc=rostedt@goodmis.org \
    --cc=tglx@linutronix.de \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®