linux-kernel - [RFC PATCH 05/12] rcu: De-offloading GP kthread

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Mon, 21 Sep 2020 14:43:44 +0200
From:   Frederic Weisbecker <frederic@...nel.org>
To:     "Paul E . McKenney" <paulmck@...nel.org>
Cc:     LKML <linux-kernel@...r.kernel.org>,
        Frederic Weisbecker <frederic@...nel.org>,
        Steven Rostedt <rostedt@...dmis.org>,
        Mathieu Desnoyers <mathieu.desnoyers@...icios.com>,
        Lai Jiangshan <jiangshanlai@...il.com>,
        Joel Fernandes <joel@...lfernandes.org>,
        Josh Triplett <josh@...htriplett.org>
Subject: [RFC PATCH 05/12] rcu: De-offloading GP kthread

In order to de-offload the callbacks processing of an rdp, we must clear
SEGCBLIST_OFFLOAD and notify the GP kthread so that it clears its own
bit flag and ignore the target rdp from its loop. The CB kthread
is also notified the same way. Whoever acknowledges and clears its
own bit last must notify the de-offloading worker so that it can resume
the de-offloading while being sure that callbacks won't be handled
remotely anymore.

Inspired-by: Paul E. McKenney <paulmck@...nel.org>
Signed-off-by: Frederic Weisbecker <frederic@...nel.org>
Cc: Paul E. McKenney <paulmck@...nel.org>
Cc: Josh Triplett <josh@...htriplett.org>
Cc: Steven Rostedt <rostedt@...dmis.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@...icios.com>
Cc: Lai Jiangshan <jiangshanlai@...il.com>
Cc: Joel Fernandes <joel@...lfernandes.org>
---
 kernel/rcu/tree_plugin.h | 53 ++++++++++++++++++++++++++++++++++++++--
 1 file changed, 51 insertions(+), 2 deletions(-)

diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 3ea43c75c7a3..e4e7e7c4bfb6 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -1900,6 +1900,33 @@ static void do_nocb_bypass_wakeup_timer(struct timer_list *t)
 	__call_rcu_nocb_wake(rdp, true, flags);
 }
 
+static inline bool nocb_gp_enabled_cb(struct rcu_data *rdp)
+{
+	u8 flags = SEGCBLIST_OFFLOADED | SEGCBLIST_KTHREAD_GP;
+
+	return rcu_segcblist_test_flags(&rdp->cblist, flags);
+}
+
+static inline bool nocb_gp_update_state(struct rcu_data *rdp, bool *needwake_state)
+{
+	struct rcu_segcblist *cblist = &rdp->cblist;
+
+	if (rcu_segcblist_test_flags(cblist, SEGCBLIST_OFFLOADED)) {
+		return true;
+	} else {
+		/*
+		 * De-offloading. Clear our flag and notify the de-offload worker.
+		 * We will ignore this rdp until it ever gets re-offloaded.
+		 */
+		WARN_ON_ONCE(!rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_GP));
+		rcu_segcblist_clear_flags(cblist, SEGCBLIST_KTHREAD_GP);
+		if (!rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_CB))
+			*needwake_state = true;
+		return false;
+	}
+}
+
+
 /*
  * No-CBs GP kthreads come here to wait for additional callbacks to show up
  * or for grace periods to end.
@@ -1927,8 +1954,17 @@ static void nocb_gp_wait(struct rcu_data *my_rdp)
 	 * and the global grace-period kthread are awakened if needed.
 	 */
 	for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_cb_rdp) {
+		bool needwake_state = false;
+		if (!nocb_gp_enabled_cb(rdp))
+			continue;
 		trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("Check"));
 		rcu_nocb_lock_irqsave(rdp, flags);
+		if (!nocb_gp_update_state(rdp, &needwake_state)) {
+			rcu_nocb_unlock_irqrestore(rdp, flags);
+			if (needwake_state)
+				swake_up_one(&rdp->nocb_state_wq);
+			continue;
+		}
 		bypass_ncbs = rcu_cblist_n_cbs(&rdp->nocb_bypass);
 		if (bypass_ncbs &&
 		    (time_after(j, READ_ONCE(rdp->nocb_bypass_first) + 1) ||
@@ -2194,7 +2230,8 @@ static void __rcu_nocb_rdp_deoffload(struct rcu_data *rdp)
 	unsigned long flags;
 	struct rcu_node *rnp = rdp->mynode;
 	struct rcu_segcblist *cblist = &rdp->cblist;
-	bool wake_cb = false;
+	struct rcu_data *rdp_gp = rdp->nocb_gp_rdp;
+	bool wake_cb = false, wake_gp = false;
 
 	printk("De-offloading %d\n", rdp->cpu);
 
@@ -2212,8 +2249,19 @@ static void __rcu_nocb_rdp_deoffload(struct rcu_data *rdp)
 	if (wake_cb)
 		swake_up_one(&rdp->nocb_cb_wq);
 
+	raw_spin_lock_irqsave(&rdp_gp->nocb_gp_lock, flags);
+	if (rdp_gp->nocb_gp_sleep) {
+		rdp_gp->nocb_gp_sleep = false;
+		wake_gp = true;
+	}
+	raw_spin_unlock_irqrestore(&rdp_gp->nocb_gp_lock, flags);
+
+	if (wake_gp)
+		wake_up_process(rdp_gp->nocb_gp_kthread);
+
 	swait_event_exclusive(rdp->nocb_state_wq,
-			      !rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_CB));
+			      !rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_CB |
+							SEGCBLIST_KTHREAD_GP));
 }
 
 static long rcu_nocb_rdp_deoffload(void *arg)
@@ -2292,6 +2340,7 @@ void __init rcu_init_nohz(void)
 			rcu_segcblist_init(&rdp->cblist);
 		rcu_segcblist_offload(&rdp->cblist, true);
 		rcu_segcblist_set_flags(&rdp->cblist, SEGCBLIST_KTHREAD_CB);
+		rcu_segcblist_set_flags(&rdp->cblist, SEGCBLIST_KTHREAD_GP);
 	}
 	rcu_organize_nocb_kthreads();
 }
-- 
2.28.0