On Sat, Jan 09, 2021 at 03:05:33AM +0100, Frederic Weisbecker wrote:
> Following the idle loop model, cleanly check for pending rcuog wakeup
> before the last rescheduling point on resuming to user mode. This
> way we can avoid to do it from rcu_user_enter() with the last resort
> self-IPI hack that enforces rescheduling.
>
> Signed-off-by: Frederic Weisbecker <frederic@xxxxxxxxxx>
> Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
> Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
> Cc: Ingo Molnar<mingo@xxxxxxxxxx>
> Cc: Paul E. McKenney <paulmck@xxxxxxxxxx>
> Cc: Rafael J. Wysocki <rafael.j.wysocki@xxxxxxxxx>
> ---
> kernel/entry/common.c | 6 ++++++
> kernel/rcu/tree.c | 12 +++++++-----
> 2 files changed, 13 insertions(+), 5 deletions(-)
>
> diff --git a/kernel/entry/common.c b/kernel/entry/common.c
> index 378341642f94..8f3292b5f9b7 100644
> --- a/kernel/entry/common.c
> +++ b/kernel/entry/common.c
> @@ -178,6 +178,9 @@ static unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
> /* Architecture specific TIF work */
> arch_exit_to_user_mode_work(regs, ti_work);
>
> + /* Check if any of the above work has queued a deferred wakeup */
> + rcu_nocb_flush_deferred_wakeup();
> +
> /*
> * Disable interrupts and reevaluate the work flags as they
> * might have changed while interrupts and preemption was
> @@ -197,6 +200,9 @@ static void exit_to_user_mode_prepare(struct pt_regs *regs)
>
> lockdep_assert_irqs_disabled();
>
> + /* Flush pending rcuog wakeup before the last need_resched() check */
> + rcu_nocb_flush_deferred_wakeup();
> +
> if (unlikely(ti_work & EXIT_TO_USER_MODE_WORK))
> ti_work = exit_to_user_mode_loop(regs, ti_work);
>
> diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
> index 2920dfc9f58c..3c4c0d5cea65 100644
> --- a/kernel/rcu/tree.c
> +++ b/kernel/rcu/tree.c
> @@ -705,12 +705,14 @@ noinstr void rcu_user_enter(void)
>
> lockdep_assert_irqs_disabled();
> /*
> - * We may be past the last rescheduling opportunity in the entry code.
> - * Trigger a self IPI that will fire and reschedule once we resume to
> - * user/guest mode.
> + * Other than generic entry implementation, we may be past the last
> + * rescheduling opportunity in the entry code. Trigger a self IPI
> + * that will fire and reschedule once we resume in user/guest mode.
> */
> - if (do_nocb_deferred_wakeup(rdp) && need_resched())
> - irq_work_queue(this_cpu_ptr(&late_wakeup_work));
> + if (!IS_ENABLED(CONFIG_GENERIC_ENTRY) || (current->flags & PF_VCPU)) {
We have xfer_to_guest_mode_work() for that PF_VCPU case.
> + if (do_nocb_deferred_wakeup(rdp) && need_resched())
> + irq_work_queue(this_cpu_ptr(&late_wakeup_work));
> + }
