From 7d0c9c50c5a109acd7a5cf589fc5563f9ef7149a Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 19 Mar 2020 15:33:12 -0700 Subject: rcu-tasks: Avoid IPIing userspace/idle tasks if kernel is so built Systems running CPU-bound real-time task do not want IPIs sent to CPUs executing nohz_full userspace tasks. Battery-powered systems don't want IPIs sent to idle CPUs in low-power mode. Unfortunately, RCU tasks trace can and will send such IPIs in some cases. Both of these situations occur only when the target CPU is in RCU dyntick-idle mode, in other words, when RCU is not watching the target CPU. This suggests that CPUs in dyntick-idle mode should use memory barriers in outermost invocations of rcu_read_lock_trace() and rcu_read_unlock_trace(), which would allow the RCU tasks trace grace period to directly read out the target CPU's read-side state. One challenge is that RCU tasks trace is not targeting a specific CPU, but rather a task. And that task could switch from one CPU to another at any time. This commit therefore uses try_invoke_on_locked_down_task() and checks for task_curr() in trc_inspect_reader_notrunning(). When this condition holds, the target task is running and cannot move. If CONFIG_TASKS_TRACE_RCU_READ_MB=y, the new rcu_dynticks_zero_in_eqs() function can be used to check if the specified integer (in this case, t->trc_reader_nesting) is zero while the target CPU remains in that same dyntick-idle sojourn. If so, the target task is in a quiescent state. If not, trc_read_check_handler() must indicate failure so that the grace-period kthread can take appropriate action or retry after an appropriate delay, as the case may be. With this change, given CONFIG_TASKS_TRACE_RCU_READ_MB=y, if a given CPU remains idle or a given task continues executing in nohz_full mode, the RCU tasks trace grace-period kthread will detect this without the need to send an IPI. Suggested-by: Mathieu Desnoyers Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'kernel/rcu/tree.c') diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 0bbcbf398169..573fd78a7bca 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -252,6 +252,7 @@ static void rcu_dynticks_eqs_enter(void) * critical sections, and we also must force ordering with the * next idle sojourn. */ + rcu_dynticks_task_trace_enter(); // Before ->dynticks update! seq = atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks); // RCU is no longer watching. Better be in extended quiescent state! WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && @@ -278,6 +279,7 @@ static void rcu_dynticks_eqs_exit(void) */ seq = atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks); // RCU is now watching. Better not be in an extended quiescent state! + rcu_dynticks_task_trace_exit(); // After ->dynticks update! WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !(seq & RCU_DYNTICK_CTRL_CTR)); if (seq & RCU_DYNTICK_CTRL_MASK) { @@ -349,6 +351,28 @@ static bool rcu_dynticks_in_eqs_since(struct rcu_data *rdp, int snap) return snap != rcu_dynticks_snap(rdp); } +/* + * Return true if the referenced integer is zero while the specified + * CPU remains within a single extended quiescent state. + */ +bool rcu_dynticks_zero_in_eqs(int cpu, int *vp) +{ + struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); + int snap; + + // If not quiescent, force back to earlier extended quiescent state. + snap = atomic_read(&rdp->dynticks) & ~(RCU_DYNTICK_CTRL_MASK | + RCU_DYNTICK_CTRL_CTR); + + smp_rmb(); // Order ->dynticks and *vp reads. + if (READ_ONCE(*vp)) + return false; // Non-zero, so report failure; + smp_rmb(); // Order *vp read and ->dynticks re-read. + + // If still in the same extended quiescent state, we are good! + return snap == (atomic_read(&rdp->dynticks) & ~RCU_DYNTICK_CTRL_MASK); +} + /* * Set the special (bottom) bit of the specified CPU so that it * will take special action (such as flushing its TLB) on the -- cgit v1.2.3-58-ga151