From 2eb52fa8900e642b3b5054c4bf9776089d2a935f Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 4 Dec 2023 09:33:29 -0800 Subject: rcu-tasks: Repair RCU Tasks Trace quiescence check The context-switch-time check for RCU Tasks Trace quiescence expects current->trc_reader_special.b.need_qs to be zero, and if so, updates it to TRC_NEED_QS_CHECKED. This is backwards, because if this value is zero, there is no RCU Tasks Trace grace period in flight, an thus no need for a quiescent state. Instead, when a grace period starts, this field is set to TRC_NEED_QS. This commit therefore changes the check from zero to TRC_NEED_QS. Reported-by: Steven Rostedt Signed-off-by: Paul E. McKenney Tested-by: Steven Rostedt (Google) Signed-off-by: Boqun Feng --- include/linux/rcupdate.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux/rcupdate.h') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 0746b1b0b663..16f519914415 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -184,9 +184,9 @@ void rcu_tasks_trace_qs_blkd(struct task_struct *t); do { \ int ___rttq_nesting = READ_ONCE((t)->trc_reader_nesting); \ \ - if (likely(!READ_ONCE((t)->trc_reader_special.b.need_qs)) && \ + if (unlikely(READ_ONCE((t)->trc_reader_special.b.need_qs) == TRC_NEED_QS) && \ likely(!___rttq_nesting)) { \ - rcu_trc_cmpxchg_need_qs((t), 0, TRC_NEED_QS_CHECKED); \ + rcu_trc_cmpxchg_need_qs((t), TRC_NEED_QS, TRC_NEED_QS_CHECKED); \ } else if (___rttq_nesting && ___rttq_nesting != INT_MIN && \ !READ_ONCE((t)->trc_reader_special.b.blocked)) { \ rcu_tasks_trace_qs_blkd(t); \ -- cgit v1.2.3 From 1a77557d48cff187a169c2aec01c0dd78a5e7e50 Mon Sep 17 00:00:00 2001 From: Yan Zhai Date: Tue, 19 Mar 2024 13:44:34 -0700 Subject: rcu: add a helper to report consolidated flavor QS When under heavy load, network processing can run CPU-bound for many tens of seconds. Even in preemptible kernels (non-RT kernel), this can block RCU Tasks grace periods, which can cause trace-event removal to take more than a minute, which is unacceptably long. This commit therefore creates a new helper function that passes through both RCU and RCU-Tasks quiescent states every 100 milliseconds. This hard-coded value suffices for current workloads. Suggested-by: Paul E. McKenney Reviewed-by: Jesper Dangaard Brouer Signed-off-by: Yan Zhai Reviewed-by: Paul E. McKenney Acked-by: Jesper Dangaard Brouer Link: https://lore.kernel.org/r/90431d46ee112d2b0af04dbfe936faaca11810a5.1710877680.git.yan@cloudflare.com Signed-off-by: Jakub Kicinski --- include/linux/rcupdate.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include/linux/rcupdate.h') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 16f519914415..17d7ed5f3ae6 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -247,6 +247,37 @@ do { \ cond_resched(); \ } while (0) +/** + * rcu_softirq_qs_periodic - Report RCU and RCU-Tasks quiescent states + * @old_ts: jiffies at start of processing. + * + * This helper is for long-running softirq handlers, such as NAPI threads in + * networking. The caller should initialize the variable passed in as @old_ts + * at the beginning of the softirq handler. When invoked frequently, this macro + * will invoke rcu_softirq_qs() every 100 milliseconds thereafter, which will + * provide both RCU and RCU-Tasks quiescent states. Note that this macro + * modifies its old_ts argument. + * + * Because regions of code that have disabled softirq act as RCU read-side + * critical sections, this macro should be invoked with softirq (and + * preemption) enabled. + * + * The macro is not needed when CONFIG_PREEMPT_RT is defined. RT kernels would + * have more chance to invoke schedule() calls and provide necessary quiescent + * states. As a contrast, calling cond_resched() only won't achieve the same + * effect because cond_resched() does not provide RCU-Tasks quiescent states. + */ +#define rcu_softirq_qs_periodic(old_ts) \ +do { \ + if (!IS_ENABLED(CONFIG_PREEMPT_RT) && \ + time_after(jiffies, (old_ts) + HZ / 10)) { \ + preempt_disable(); \ + rcu_softirq_qs(); \ + preempt_enable(); \ + (old_ts) = jiffies; \ + } \ +} while (0) + /* * Infrastructure to implement the synchronize_() primitives in * TREE_RCU and rcu_barrier_() primitives in TINY_RCU. -- cgit v1.2.3