Re: [PATCH 4/4] rcu: Fix dyntick-idle tracing

From: Paul E. McKenney
Date: Thu Apr 06 2017 - 14:02:01 EST


On Thu, Apr 06, 2017 at 12:42:41PM -0400, Steven Rostedt wrote:
> From: "Paul E. McKenney" <paulmck@xxxxxxxxxxxxxxxxxx>
>
> The tracing subsystem started using rcu_irq_entry() and rcu_irq_exit()
> (with my blessing) to allow the current _rcuidle alternative tracepoint
> name to be dispensed with while still maintaining good performance.
> Unfortunately, this causes RCU's dyntick-idle entry code's tracing to
> appear to RCU like an interrupt that occurs where RCU is not designed
> to handle interrupts.
>
> This commit fixes this problem by moving the zeroing of ->dynticks_nesting
> after the offending trace_rcu_dyntick() statement, which narrows the
> window of vulnerability to a pair of adjacent statements that are now
> marked with comments to that effect.
>
> Link: http://lkml.kernel.org/r/20170405193928.GM1600@xxxxxxxxxxxxxxxxxx
>
> Reported-by: Steven Rostedt <rostedt@xxxxxxxxxxx>
> Signed-off-by: Paul E. McKenney <paulmck@xxxxxxxxxxxxxxxxxx>
> Signed-off-by: Steven Rostedt (VMware) <rostedt@xxxxxxxxxxx>

Acked-by: Paul E. McKenney <paulmck@xxxxxxxxxxxxxxxxxx>

Really confirming my Signed-off-by given Steven's changes, but whatever. ;-)

Thanx, Paul

> ---
> kernel/rcu/tree.c | 48 +++++++++++++++++++++++-------------------------
> 1 file changed, 23 insertions(+), 25 deletions(-)
>
> diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
> index 50fee7689e71..8b4d273331e4 100644
> --- a/kernel/rcu/tree.c
> +++ b/kernel/rcu/tree.c
> @@ -57,6 +57,7 @@
> #include <linux/random.h>
> #include <linux/trace_events.h>
> #include <linux/suspend.h>
> +#include <linux/ftrace.h>
>
> #include "tree.h"
> #include "rcu.h"
> @@ -771,25 +772,24 @@ cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp)
> }
>
> /*
> - * rcu_eqs_enter_common - current CPU is moving towards extended quiescent state
> + * rcu_eqs_enter_common - current CPU is entering an extended quiescent state
> *
> - * If the new value of the ->dynticks_nesting counter now is zero,
> - * we really have entered idle, and must do the appropriate accounting.
> - * The caller must have disabled interrupts.
> + * Enter idle, doing appropriate accounting. The caller must have
> + * disabled interrupts.
> */
> -static void rcu_eqs_enter_common(long long oldval, bool user)
> +static void rcu_eqs_enter_common(bool user)
> {
> struct rcu_state *rsp;
> struct rcu_data *rdp;
> - RCU_TRACE(struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);)
> + struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
>
> - trace_rcu_dyntick(TPS("Start"), oldval, rdtp->dynticks_nesting);
> + trace_rcu_dyntick(TPS("Start"), rdtp->dynticks_nesting, 0);
> if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
> !user && !is_idle_task(current)) {
> struct task_struct *idle __maybe_unused =
> idle_task(smp_processor_id());
>
> - trace_rcu_dyntick(TPS("Error on entry: not idle task"), oldval, 0);
> + trace_rcu_dyntick(TPS("Error on entry: not idle task"), rdtp->dynticks_nesting, 0);
> rcu_ftrace_dump(DUMP_ORIG);
> WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s",
> current->pid, current->comm,
> @@ -800,7 +800,10 @@ static void rcu_eqs_enter_common(long long oldval, bool user)
> do_nocb_deferred_wakeup(rdp);
> }
> rcu_prepare_for_idle();
> - rcu_dynticks_eqs_enter();
> + stack_tracer_disable();
> + rdtp->dynticks_nesting = 0; /* Breaks tracing momentarily. */
> + rcu_dynticks_eqs_enter(); /* After this, tracing works again. */
> + stack_tracer_enable();
> rcu_dynticks_task_enter();
>
> /*
> @@ -821,19 +824,15 @@ static void rcu_eqs_enter_common(long long oldval, bool user)
> */
> static void rcu_eqs_enter(bool user)
> {
> - long long oldval;
> struct rcu_dynticks *rdtp;
>
> rdtp = this_cpu_ptr(&rcu_dynticks);
> - oldval = rdtp->dynticks_nesting;
> WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
> - (oldval & DYNTICK_TASK_NEST_MASK) == 0);
> - if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE) {
> - rdtp->dynticks_nesting = 0;
> - rcu_eqs_enter_common(oldval, user);
> - } else {
> + (rdtp->dynticks_nesting & DYNTICK_TASK_NEST_MASK) == 0);
> + if ((rdtp->dynticks_nesting & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE)
> + rcu_eqs_enter_common(user);
> + else
> rdtp->dynticks_nesting -= DYNTICK_TASK_NEST_VALUE;
> - }
> }
>
> /**
> @@ -892,19 +891,18 @@ void rcu_user_enter(void)
> */
> void rcu_irq_exit(void)
> {
> - long long oldval;
> struct rcu_dynticks *rdtp;
>
> RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_exit() invoked with irqs enabled!!!");
> rdtp = this_cpu_ptr(&rcu_dynticks);
> - oldval = rdtp->dynticks_nesting;
> - rdtp->dynticks_nesting--;
> WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
> - rdtp->dynticks_nesting < 0);
> - if (rdtp->dynticks_nesting)
> - trace_rcu_dyntick(TPS("--="), oldval, rdtp->dynticks_nesting);
> - else
> - rcu_eqs_enter_common(oldval, true);
> + rdtp->dynticks_nesting < 1);
> + if (rdtp->dynticks_nesting <= 1) {
> + rcu_eqs_enter_common(true);
> + } else {
> + trace_rcu_dyntick(TPS("--="), rdtp->dynticks_nesting, rdtp->dynticks_nesting - 1);
> + rdtp->dynticks_nesting--;
> + }
> rcu_sysidle_enter(1);
> }
>
> --
> 2.10.2
>
>