Unverified Commit f20ae83d authored by openeuler-ci-bot's avatar openeuler-ci-bot Committed by Gitee
Browse files

!9241 v2 Bugfix backport for rcu 

Merge Pull Request from: @ci-robot 
 
PR sync from: Wei Li <liwei391@huawei.com>
https://mailweb.openeuler.org/hyperkitty/list/kernel@openeuler.org/message/VW2YPQE5JBKCW7MSZRNA4S2YCCCYVHE2/ 
Backport 3 bugfix patches for rcu from mainline.

v1 -> v2:
 - Fix conflict in patch 2

Frederic Weisbecker (3):
  rcu: Defer RCU kthreads wakeup when CPU is dying
  entry/rcu: Check TIF_RESCHED _after_ delayed RCU wake-up
  srcu: Fix callbacks acceleration mishandling


-- 
2.25.1
 
https://gitee.com/openeuler/kernel/issues/I9NZ3E 
 
Link:https://gitee.com/openeuler/kernel/pulls/9241

 

Reviewed-by: default avatarXiongfeng Wang <wangxiongfeng2@huawei.com>
Signed-off-by: default avatarJialin Zhang <zhangjialin11@huawei.com>
parents 651a5774 2afe3ba0

kernel/entry/common.c

+2 −1
Original line number Diff line number Diff line
@@ -195,13 +195,14 @@ static unsigned long exit_to_user_mode_loop(struct pt_regs *regs, 


static void exit_to_user_mode_prepare(struct pt_regs *regs)

{

	unsigned long ti_work = read_thread_flags();

	unsigned long ti_work;



	lockdep_assert_irqs_disabled();



	/* Flush pending rcuog wakeup before the last need_resched() check */

	rcu_nocb_flush_deferred_wakeup();



	ti_work = read_thread_flags();

	if (unlikely(ti_work & EXIT_TO_USER_MODE_WORK))

		ti_work = exit_to_user_mode_loop(regs, ti_work);

kernel/rcu/srcutree.c

+29 −2
Original line number Diff line number Diff line
@@ -829,10 +829,37 @@ static unsigned long srcu_gp_start_if_needed(struct srcu_struct *ssp, 
	spin_lock_irqsave_rcu_node(sdp, flags);

	if (rhp)

		rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp);

	/*

	 * The snapshot for acceleration must be taken _before_ the read of the

	 * current gp sequence used for advancing, otherwise advancing may fail

	 * and acceleration may then fail too.

	 *

	 * This could happen if:

	 *

	 *  1) The RCU_WAIT_TAIL segment has callbacks (gp_num = X + 4) and the

	 *     RCU_NEXT_READY_TAIL also has callbacks (gp_num = X + 8).

	 *

	 *  2) The grace period for RCU_WAIT_TAIL is seen as started but not

	 *     completed so rcu_seq_current() returns X + SRCU_STATE_SCAN1.

	 *

	 *  3) This value is passed to rcu_segcblist_advance() which can't move

	 *     any segment forward and fails.

	 *

	 *  4) srcu_gp_start_if_needed() still proceeds with callback acceleration.

	 *     But then the call to rcu_seq_snap() observes the grace period for the

	 *     RCU_WAIT_TAIL segment as completed and the subsequent one for the

	 *     RCU_NEXT_READY_TAIL segment as started (ie: X + 4 + SRCU_STATE_SCAN1)

	 *     so it returns a snapshot of the next grace period, which is X + 12.

	 *

	 *  5) The value of X + 12 is passed to rcu_segcblist_accelerate() but the

	 *     freshly enqueued callback in RCU_NEXT_TAIL can't move to

	 *     RCU_NEXT_READY_TAIL which already has callbacks for a previous grace

	 *     period (gp_num = X + 8). So acceleration fails.

	 */

	s = rcu_seq_snap(&ssp->srcu_gp_seq);

	rcu_segcblist_advance(&sdp->srcu_cblist,

			      rcu_seq_current(&ssp->srcu_gp_seq));

	s = rcu_seq_snap(&ssp->srcu_gp_seq);

	(void)rcu_segcblist_accelerate(&sdp->srcu_cblist, s);

	WARN_ON_ONCE(!rcu_segcblist_accelerate(&sdp->srcu_cblist, s) && rhp);

	if (ULONG_CMP_LT(sdp->srcu_gp_seq_needed, s)) {

		sdp->srcu_gp_seq_needed = s;

		needgp = true;

kernel/rcu/tree.c

+33 −1
Original line number Diff line number Diff line
@@ -1483,6 +1483,38 @@ static bool rcu_future_gp_cleanup(struct rcu_node *rnp) 
	return needmore;

}



static void swake_up_one_online_ipi(void *arg)

{

	struct swait_queue_head *wqh = arg;



	swake_up_one(wqh);

}



static void swake_up_one_online(struct swait_queue_head *wqh)

{

	int cpu = get_cpu();



	/*

	 * If called from rcutree_report_cpu_starting(), wake up

	 * is dangerous that late in the CPU-down hotplug process. The

	 * scheduler might queue an ignored hrtimer. Defer the wake up

	 * to an online CPU instead.

	 */

	if (unlikely(cpu_is_offline(cpu))) {

		int target;



		target = cpumask_any_and(housekeeping_cpumask(HK_FLAG_RCU),

					 cpu_online_mask);



		smp_call_function_single(target, swake_up_one_online_ipi,

					 wqh, 0);

		put_cpu();

	} else {

		put_cpu();

		swake_up_one(wqh);

	}

}



/*

 * Awaken the grace-period kthread.  Don't do a self-awaken (unless in an

 * interrupt or softirq handler, in which case we just might immediately
@@ -1507,7 +1539,7 @@ static void rcu_gp_kthread_wake(void) 
		return;

	WRITE_ONCE(rcu_state.gp_wake_time, jiffies);

	WRITE_ONCE(rcu_state.gp_wake_seq, READ_ONCE(rcu_state.gp_seq));

	swake_up_one(&rcu_state.gp_wq);

	swake_up_one_online(&rcu_state.gp_wq);

}



/*

kernel/rcu/tree_exp.h

+1 −2
Original line number Diff line number Diff line
@@ -170,7 +170,6 @@ static bool sync_rcu_exp_done_unlocked(struct rcu_node *rnp) 
	return ret;

}





/*

 * Report the exit from RCU read-side critical section for the last task

 * that queued itself during or before the current expedited preemptible-RCU
@@ -198,7 +197,7 @@ static void __rcu_report_exp_rnp(struct rcu_node *rnp, 
			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);

			if (wake) {

				smp_mb(); /* EGP done before wake_up(). */

				swake_up_one(&rcu_state.expedited_wq);

				swake_up_one_online(&rcu_state.expedited_wq);

			}

			break;

		}