From 135bd1a230bb69a68c9808a7d25467318900b80a Mon Sep 17 00:00:00 2001 From: Neeraj Upadhyay Date: Mon, 7 Aug 2017 11:20:10 +0530 Subject: [PATCH 01/15] rcu: Fix up pending cbs check in rcu_prepare_for_idle The pending-callbacks check in rcu_prepare_for_idle() is backwards. It should accelerate if there are pending callbacks, but the check rather uselessly accelerates only if there are no callbacks. This commit therefore inverts this check. Fixes: 15fecf89e46a ("srcu: Abstract multi-tail callback list handling") Signed-off-by: Neeraj Upadhyay Signed-off-by: Paul E. McKenney Cc: # 4.12.x --- kernel/rcu/tree_plugin.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index e012b9be777e..fed95fa941e6 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -1507,7 +1507,7 @@ static void rcu_prepare_for_idle(void) rdtp->last_accelerate = jiffies; for_each_rcu_flavor(rsp) { rdp = this_cpu_ptr(rsp->rda); - if (rcu_segcblist_pend_cbs(&rdp->cblist)) + if (!rcu_segcblist_pend_cbs(&rdp->cblist)) continue; rnp = rdp->mynode; raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */ From c63eb17ff06dbcf73e771b9b425c531cc0a9c17b Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 11 Aug 2017 12:37:07 -0700 Subject: [PATCH 02/15] rcu: Create call_rcu_tasks() kthread at boot time Currently the call_rcu_tasks() kthread is created upon first invocation of call_rcu_tasks(). This has the advantage of avoiding creation if there are never any invocations of call_rcu_tasks() and of synchronize_rcu_tasks(), but it requires an unreliable heuristic to determine when it is safe to create the kthread. For example, it is not safe to create the kthread when call_rcu_tasks() is invoked with a spinlock held, but there is no good way to detect this in !PREEMPT kernels. This commit therefore creates this kthread unconditionally at core_initcall() time. If you don't want this kthread created, then build with CONFIG_TASKS_RCU=n. Signed-off-by: Paul E. McKenney --- kernel/rcu/update.c | 24 +++++------------------- 1 file changed, 5 insertions(+), 19 deletions(-) diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 5033b66d2753..e9bbedbb8745 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -575,7 +575,6 @@ DEFINE_STATIC_SRCU(tasks_rcu_exit_srcu); static int rcu_task_stall_timeout __read_mostly = RCU_TASK_STALL_TIMEOUT; module_param(rcu_task_stall_timeout, int, 0644); -static void rcu_spawn_tasks_kthread(void); static struct task_struct *rcu_tasks_kthread_ptr; /** @@ -600,7 +599,6 @@ void call_rcu_tasks(struct rcu_head *rhp, rcu_callback_t func) { unsigned long flags; bool needwake; - bool havetask = READ_ONCE(rcu_tasks_kthread_ptr); rhp->next = NULL; rhp->func = func; @@ -610,11 +608,8 @@ void call_rcu_tasks(struct rcu_head *rhp, rcu_callback_t func) rcu_tasks_cbs_tail = &rhp->next; raw_spin_unlock_irqrestore(&rcu_tasks_cbs_lock, flags); /* We can't create the thread unless interrupts are enabled. */ - if ((needwake && havetask) || - (!havetask && !irqs_disabled_flags(flags))) { - rcu_spawn_tasks_kthread(); + if (needwake && READ_ONCE(rcu_tasks_kthread_ptr)) wake_up(&rcu_tasks_cbs_wq); - } } EXPORT_SYMBOL_GPL(call_rcu_tasks); @@ -853,27 +848,18 @@ static int __noreturn rcu_tasks_kthread(void *arg) } } -/* Spawn rcu_tasks_kthread() at first call to call_rcu_tasks(). */ -static void rcu_spawn_tasks_kthread(void) +/* Spawn rcu_tasks_kthread() at core_initcall() time. */ +static int __init rcu_spawn_tasks_kthread(void) { - static DEFINE_MUTEX(rcu_tasks_kthread_mutex); struct task_struct *t; - if (READ_ONCE(rcu_tasks_kthread_ptr)) { - smp_mb(); /* Ensure caller sees full kthread. */ - return; - } - mutex_lock(&rcu_tasks_kthread_mutex); - if (rcu_tasks_kthread_ptr) { - mutex_unlock(&rcu_tasks_kthread_mutex); - return; - } t = kthread_run(rcu_tasks_kthread, NULL, "rcu_tasks_kthread"); BUG_ON(IS_ERR(t)); smp_mb(); /* Ensure others see full kthread. */ WRITE_ONCE(rcu_tasks_kthread_ptr, t); - mutex_unlock(&rcu_tasks_kthread_mutex); + return 0; } +core_initcall(rcu_spawn_tasks_kthread); /* Do the srcu_read_lock() for the above synchronize_srcu(). */ void exit_tasks_rcu_start(void) From 6733bab7bc09b67668028dab562caea1b4ff3c69 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 18 Aug 2017 10:59:16 -0700 Subject: [PATCH 03/15] irq_work: Map irq_work_on_queue() to irq_work_on() in !SMP Commit 478850160636 ("irq_work: Implement remote queueing") provides irq_work_on_queue() only for SMP builds. However, providing it simplifies code that submits irq_work to lists of CPUs, eliminating the !SMP special cases. This commit therefore maps irq_work_on_queue() to irq_work_on() in !SMP builds, but validating the specified CPU. Signed-off-by: Paul E. McKenney --- include/linux/irq_work.h | 3 --- kernel/irq_work.c | 9 ++++++--- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h index 47b9ebd4a74f..d8c9876d5da4 100644 --- a/include/linux/irq_work.h +++ b/include/linux/irq_work.h @@ -33,10 +33,7 @@ void init_irq_work(struct irq_work *work, void (*func)(struct irq_work *)) #define DEFINE_IRQ_WORK(name, _f) struct irq_work name = { .func = (_f), } bool irq_work_queue(struct irq_work *work); - -#ifdef CONFIG_SMP bool irq_work_queue_on(struct irq_work *work, int cpu); -#endif void irq_work_tick(void); void irq_work_sync(struct irq_work *work); diff --git a/kernel/irq_work.c b/kernel/irq_work.c index bcf107ce0854..9f20f6c72579 100644 --- a/kernel/irq_work.c +++ b/kernel/irq_work.c @@ -56,7 +56,6 @@ void __weak arch_irq_work_raise(void) */ } -#ifdef CONFIG_SMP /* * Enqueue the irq_work @work on @cpu unless it's already pending * somewhere. @@ -68,6 +67,8 @@ bool irq_work_queue_on(struct irq_work *work, int cpu) /* All work should have been flushed before going offline */ WARN_ON_ONCE(cpu_is_offline(cpu)); +#ifdef CONFIG_SMP + /* Arch remote IPI send/receive backend aren't NMI safe */ WARN_ON_ONCE(in_nmi()); @@ -78,10 +79,12 @@ bool irq_work_queue_on(struct irq_work *work, int cpu) if (llist_add(&work->llnode, &per_cpu(raised_list, cpu))) arch_send_call_function_single_ipi(cpu); +#else /* #ifdef CONFIG_SMP */ + irq_work_queue(work); +#endif /* #else #ifdef CONFIG_SMP */ + return true; } -EXPORT_SYMBOL_GPL(irq_work_queue_on); -#endif /* Enqueue the irq work @work on the current CPU */ bool irq_work_queue(struct irq_work *work) From 7c2102e56a3f7d85b5d8f33efbd7aecc1f36fdd8 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 18 Sep 2017 08:54:40 -0700 Subject: [PATCH 04/15] sched: Make resched_cpu() unconditional The current implementation of synchronize_sched_expedited() incorrectly assumes that resched_cpu() is unconditional, which it is not. This means that synchronize_sched_expedited() can hang when resched_cpu()'s trylock fails as follows (analysis by Neeraj Upadhyay): o CPU1 is waiting for expedited wait to complete: sync_rcu_exp_select_cpus rdp->exp_dynticks_snap & 0x1 // returns 1 for CPU5 IPI sent to CPU5 synchronize_sched_expedited_wait ret = swait_event_timeout(rsp->expedited_wq, sync_rcu_preempt_exp_done(rnp_root), jiffies_stall); expmask = 0x20, CPU 5 in idle path (in cpuidle_enter()) o CPU5 handles IPI and fails to acquire rq lock. Handles IPI sync_sched_exp_handler resched_cpu returns while failing to try lock acquire rq->lock need_resched is not set o CPU5 calls rcu_idle_enter() and as need_resched is not set, goes to idle (schedule() is not called). o CPU 1 reports RCU stall. Given that resched_cpu() is now used only by RCU, this commit fixes the assumption by making resched_cpu() unconditional. Reported-by: Neeraj Upadhyay Suggested-by: Neeraj Upadhyay Signed-off-by: Paul E. McKenney Acked-by: Steven Rostedt (VMware) Acked-by: Peter Zijlstra (Intel) Cc: stable@vger.kernel.org --- kernel/sched/core.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index d17c5da523a0..8fa7b6f9e19b 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -505,8 +505,7 @@ void resched_cpu(int cpu) struct rq *rq = cpu_rq(cpu); unsigned long flags; - if (!raw_spin_trylock_irqsave(&rq->lock, flags)) - return; + raw_spin_lock_irqsave(&rq->lock, flags); resched_curr(rq); raw_spin_unlock_irqrestore(&rq->lock, flags); } From f79c3ad6189624c3de0ad5521610c9e22a1c33cf Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 30 Nov 2016 06:24:30 -0800 Subject: [PATCH 05/15] sched,rcu: Make cond_resched() provide RCU quiescent state There is some confusion as to which of cond_resched() or cond_resched_rcu_qs() should be added to long in-kernel loops. This commit therefore eliminates the decision by adding RCU quiescent states to cond_resched(). This commit also simplifies the code that used to interact with cond_resched_rcu_qs(), and that now interacts with cond_resched(), to reduce its overhead. This reduction is necessary to allow the heavier-weight cond_resched_rcu_qs() mechanism to be invoked everywhere that cond_resched() is invoked. Part of that reduction in overhead converts the jiffies_till_sched_qs kernel parameter to read-only at runtime, thus eliminating the need for bounds checking. Reported-by: Michal Hocko Signed-off-by: Paul E. McKenney Cc: Peter Zijlstra [ paulmck: Keep PREEMPT=n cond_resched a no-op, per Peter Zijlstra. ] --- kernel/rcu/tree.c | 25 +++++-------------------- kernel/sched/core.c | 1 + 2 files changed, 6 insertions(+), 20 deletions(-) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index b0ad62b0e7b8..0dda57a28276 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -534,8 +534,8 @@ module_param(rcu_kick_kthreads, bool, 0644); * How long the grace period must be before we start recruiting * quiescent-state help from rcu_note_context_switch(). */ -static ulong jiffies_till_sched_qs = HZ / 20; -module_param(jiffies_till_sched_qs, ulong, 0644); +static ulong jiffies_till_sched_qs = HZ / 10; +module_param(jiffies_till_sched_qs, ulong, 0444); static bool rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp); @@ -1235,7 +1235,6 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) unsigned long jtsq; bool *rnhqp; bool *ruqp; - unsigned long rjtsc; struct rcu_node *rnp; /* @@ -1252,23 +1251,13 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) return 1; } - /* Compute and saturate jiffies_till_sched_qs. */ - jtsq = jiffies_till_sched_qs; - rjtsc = rcu_jiffies_till_stall_check(); - if (jtsq > rjtsc / 2) { - WRITE_ONCE(jiffies_till_sched_qs, rjtsc); - jtsq = rjtsc / 2; - } else if (jtsq < 1) { - WRITE_ONCE(jiffies_till_sched_qs, 1); - jtsq = 1; - } - /* * Has this CPU encountered a cond_resched_rcu_qs() since the * beginning of the grace period? For this to be the case, * the CPU has to have noticed the current grace period. This * might not be the case for nohz_full CPUs looping in the kernel. */ + jtsq = jiffies_till_sched_qs; rnp = rdp->mynode; ruqp = per_cpu_ptr(&rcu_dynticks.rcu_urgent_qs, rdp->cpu); if (time_after(jiffies, rdp->rsp->gp_start + jtsq) && @@ -1276,7 +1265,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) READ_ONCE(rdp->gpnum) == rnp->gpnum && !rdp->gpwrap) { trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("rqc")); return 1; - } else { + } else if (time_after(jiffies, rdp->rsp->gp_start + jtsq)) { /* Load rcu_qs_ctr before store to rcu_urgent_qs. */ smp_store_release(ruqp, true); } @@ -1304,10 +1293,6 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) * updates are only once every few jiffies, the probability of * lossage (and thus of slight grace-period extension) is * quite low. - * - * Note that if the jiffies_till_sched_qs boot/sysfs parameter - * is set too high, we override with half of the RCU CPU stall - * warning delay. */ rnhqp = &per_cpu(rcu_dynticks.rcu_need_heavy_qs, rdp->cpu); if (!READ_ONCE(*rnhqp) && @@ -1316,7 +1301,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) WRITE_ONCE(*rnhqp, true); /* Store rcu_need_heavy_qs before rcu_urgent_qs. */ smp_store_release(ruqp, true); - rdp->rsp->jiffies_resched += 5; /* Re-enable beating. */ + rdp->rsp->jiffies_resched += jtsq; /* Re-enable beating. */ } /* diff --git a/kernel/sched/core.c b/kernel/sched/core.c index d17c5da523a0..904d3ab35c83 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4842,6 +4842,7 @@ int __sched _cond_resched(void) preempt_schedule_common(); return 1; } + rcu_all_qs(); return 0; } EXPORT_SYMBOL(_cond_resched); From 9b9500da81502738efa1b485a8835f174ff7be6d Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 17 Aug 2017 17:05:59 -0700 Subject: [PATCH 06/15] rcu: Make RCU CPU stall warnings check for irq-disabled CPUs One common question upon seeing an RCU CPU stall warning is "did the stalled CPUs have interrupts disabled?" However, the current stall warnings are silent on this point. This commit therefore uses irq_work to check whether stalled CPUs still respond to IPIs, and flags this state in the RCU CPU stall warning console messages. Reported-by: Steven Rostedt Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 104 ++++++++++++++++++++++++++++++++++----- kernel/rcu/tree.h | 5 ++ kernel/rcu/tree_plugin.h | 7 ++- 3 files changed, 103 insertions(+), 13 deletions(-) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 0dda57a28276..12838a9a128e 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -1206,6 +1206,22 @@ static int rcu_is_cpu_rrupt_from_idle(void) return __this_cpu_read(rcu_dynticks.dynticks_nesting) <= 1; } +/* + * We are reporting a quiescent state on behalf of some other CPU, so + * it is our responsibility to check for and handle potential overflow + * of the rcu_node ->gpnum counter with respect to the rcu_data counters. + * After all, the CPU might be in deep idle state, and thus executing no + * code whatsoever. + */ +static void rcu_gpnum_ovf(struct rcu_node *rnp, struct rcu_data *rdp) +{ + lockdep_assert_held(&rnp->lock); + if (ULONG_CMP_LT(READ_ONCE(rdp->gpnum) + ULONG_MAX / 4, rnp->gpnum)) + WRITE_ONCE(rdp->gpwrap, true); + if (ULONG_CMP_LT(rdp->rcu_iw_gpnum + ULONG_MAX / 4, rnp->gpnum)) + rdp->rcu_iw_gpnum = rnp->gpnum + ULONG_MAX / 4; +} + /* * Snapshot the specified CPU's dynticks counter so that we can later * credit them with an implicit quiescent state. Return 1 if this CPU @@ -1216,14 +1232,33 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp) rdp->dynticks_snap = rcu_dynticks_snap(rdp->dynticks); if (rcu_dynticks_in_eqs(rdp->dynticks_snap)) { trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti")); - if (ULONG_CMP_LT(READ_ONCE(rdp->gpnum) + ULONG_MAX / 4, - rdp->mynode->gpnum)) - WRITE_ONCE(rdp->gpwrap, true); + rcu_gpnum_ovf(rdp->mynode, rdp); return 1; } return 0; } +/* + * Handler for the irq_work request posted when a grace period has + * gone on for too long, but not yet long enough for an RCU CPU + * stall warning. Set state appropriately, but just complain if + * there is unexpected state on entry. + */ +static void rcu_iw_handler(struct irq_work *iwp) +{ + struct rcu_data *rdp; + struct rcu_node *rnp; + + rdp = container_of(iwp, struct rcu_data, rcu_iw); + rnp = rdp->mynode; + raw_spin_lock_rcu_node(rnp); + if (!WARN_ON_ONCE(!rdp->rcu_iw_pending)) { + rdp->rcu_iw_gpnum = rnp->gpnum; + rdp->rcu_iw_pending = false; + } + raw_spin_unlock_rcu_node(rnp); +} + /* * Return true if the specified CPU has passed through a quiescent * state by virtue of being in or having passed through an dynticks @@ -1235,7 +1270,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) unsigned long jtsq; bool *rnhqp; bool *ruqp; - struct rcu_node *rnp; + struct rcu_node *rnp = rdp->mynode; /* * If the CPU passed through or entered a dynticks idle phase with @@ -1248,6 +1283,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) if (rcu_dynticks_in_eqs_since(rdp->dynticks, rdp->dynticks_snap)) { trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti")); rdp->dynticks_fqs++; + rcu_gpnum_ovf(rnp, rdp); return 1; } @@ -1258,12 +1294,12 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) * might not be the case for nohz_full CPUs looping in the kernel. */ jtsq = jiffies_till_sched_qs; - rnp = rdp->mynode; ruqp = per_cpu_ptr(&rcu_dynticks.rcu_urgent_qs, rdp->cpu); if (time_after(jiffies, rdp->rsp->gp_start + jtsq) && READ_ONCE(rdp->rcu_qs_ctr_snap) != per_cpu(rcu_dynticks.rcu_qs_ctr, rdp->cpu) && READ_ONCE(rdp->gpnum) == rnp->gpnum && !rdp->gpwrap) { trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("rqc")); + rcu_gpnum_ovf(rnp, rdp); return 1; } else if (time_after(jiffies, rdp->rsp->gp_start + jtsq)) { /* Load rcu_qs_ctr before store to rcu_urgent_qs. */ @@ -1274,6 +1310,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) if (!(rdp->grpmask & rcu_rnp_online_cpus(rnp))) { trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("ofl")); rdp->offline_fqs++; + rcu_gpnum_ovf(rnp, rdp); return 1; } @@ -1305,11 +1342,22 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) } /* - * If more than halfway to RCU CPU stall-warning time, do - * a resched_cpu() to try to loosen things up a bit. + * If more than halfway to RCU CPU stall-warning time, do a + * resched_cpu() to try to loosen things up a bit. Also check to + * see if the CPU is getting hammered with interrupts, but only + * once per grace period, just to keep the IPIs down to a dull roar. */ - if (jiffies - rdp->rsp->gp_start > rcu_jiffies_till_stall_check() / 2) + if (jiffies - rdp->rsp->gp_start > rcu_jiffies_till_stall_check() / 2) { resched_cpu(rdp->cpu); + if (IS_ENABLED(CONFIG_IRQ_WORK) && + !rdp->rcu_iw_pending && rdp->rcu_iw_gpnum != rnp->gpnum && + (rnp->ffmask & rdp->grpmask)) { + init_irq_work(&rdp->rcu_iw, rcu_iw_handler); + rdp->rcu_iw_pending = true; + rdp->rcu_iw_gpnum = rnp->gpnum; + irq_work_queue_on(&rdp->rcu_iw, rdp->cpu); + } + } return 0; } @@ -1498,6 +1546,7 @@ static void print_cpu_stall(struct rcu_state *rsp) { int cpu; unsigned long flags; + struct rcu_data *rdp = this_cpu_ptr(rsp->rda); struct rcu_node *rnp = rcu_get_root(rsp); long totqlen = 0; @@ -1513,7 +1562,9 @@ static void print_cpu_stall(struct rcu_state *rsp) */ pr_err("INFO: %s self-detected stall on CPU", rsp->name); print_cpu_stall_info_begin(); + raw_spin_lock_irqsave_rcu_node(rdp->mynode, flags); print_cpu_stall_info(rsp, smp_processor_id()); + raw_spin_unlock_irqrestore_rcu_node(rdp->mynode, flags); print_cpu_stall_info_end(); for_each_possible_cpu(cpu) totqlen += rcu_segcblist_n_cbs(&per_cpu_ptr(rsp->rda, @@ -1907,6 +1958,7 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp, rdp->core_needs_qs = need_gp; zero_cpu_stall_ticks(rdp); WRITE_ONCE(rdp->gpwrap, false); + rcu_gpnum_ovf(rnp, rdp); } return ret; } @@ -3685,6 +3737,8 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp) rdp->cpu_no_qs.b.norm = true; rdp->rcu_qs_ctr_snap = per_cpu(rcu_dynticks.rcu_qs_ctr, cpu); rdp->core_needs_qs = false; + rdp->rcu_iw_pending = false; + rdp->rcu_iw_gpnum = rnp->gpnum - 1; trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl")); raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } @@ -3722,10 +3776,24 @@ static void rcutree_affinity_setting(unsigned int cpu, int outgoing) */ int rcutree_online_cpu(unsigned int cpu) { - sync_sched_exp_online_cleanup(cpu); - rcutree_affinity_setting(cpu, -1); + unsigned long flags; + struct rcu_data *rdp; + struct rcu_node *rnp; + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) { + rdp = per_cpu_ptr(rsp->rda, cpu); + rnp = rdp->mynode; + raw_spin_lock_irqsave_rcu_node(rnp, flags); + rnp->ffmask |= rdp->grpmask; + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + } if (IS_ENABLED(CONFIG_TREE_SRCU)) srcu_online_cpu(cpu); + if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE) + return 0; /* Too early in boot for scheduler work. */ + sync_sched_exp_online_cleanup(cpu); + rcutree_affinity_setting(cpu, -1); return 0; } @@ -3735,6 +3803,19 @@ int rcutree_online_cpu(unsigned int cpu) */ int rcutree_offline_cpu(unsigned int cpu) { + unsigned long flags; + struct rcu_data *rdp; + struct rcu_node *rnp; + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) { + rdp = per_cpu_ptr(rsp->rda, cpu); + rnp = rdp->mynode; + raw_spin_lock_irqsave_rcu_node(rnp, flags); + rnp->ffmask &= ~rdp->grpmask; + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + } + rcutree_affinity_setting(cpu, cpu); if (IS_ENABLED(CONFIG_TREE_SRCU)) srcu_offline_cpu(cpu); @@ -4183,8 +4264,7 @@ void __init rcu_init(void) for_each_online_cpu(cpu) { rcutree_prepare_cpu(cpu); rcu_cpu_starting(cpu); - if (IS_ENABLED(CONFIG_TREE_SRCU)) - srcu_online_cpu(cpu); + rcutree_online_cpu(cpu); } } diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 8e1f285f0a70..46a5d1991450 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -103,6 +103,7 @@ struct rcu_node { /* Online CPUs for next expedited GP. */ /* Any CPU that has ever been online will */ /* have its bit set. */ + unsigned long ffmask; /* Fully functional CPUs. */ unsigned long grpmask; /* Mask to apply to parent qsmask. */ /* Only one bit will be set in this mask. */ int grplo; /* lowest-numbered CPU or group here. */ @@ -285,6 +286,10 @@ struct rcu_data { /* 8) RCU CPU stall data. */ unsigned int softirq_snap; /* Snapshot of softirq activity. */ + /* ->rcu_iw* fields protected by leaf rcu_node ->lock. */ + struct irq_work rcu_iw; /* Check for non-irq activity. */ + bool rcu_iw_pending; /* Is ->rcu_iw pending? */ + unsigned long rcu_iw_gpnum; /* ->gpnum associated with ->rcu_iw. */ int cpu; struct rcu_state *rsp; diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index e012b9be777e..14977d0470d1 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -1671,6 +1671,7 @@ static void print_cpu_stall_info_begin(void) */ static void print_cpu_stall_info(struct rcu_state *rsp, int cpu) { + unsigned long delta; char fast_no_hz[72]; struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); struct rcu_dynticks *rdtp = rdp->dynticks; @@ -1685,11 +1686,15 @@ static void print_cpu_stall_info(struct rcu_state *rsp, int cpu) ticks_value = rsp->gpnum - rdp->gpnum; } print_cpu_stall_fast_no_hz(fast_no_hz, cpu); - pr_err("\t%d-%c%c%c: (%lu %s) idle=%03x/%llx/%d softirq=%u/%u fqs=%ld %s\n", + delta = rdp->mynode->gpnum - rdp->rcu_iw_gpnum; + pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%03x/%llx/%d softirq=%u/%u fqs=%ld %s\n", cpu, "O."[!!cpu_online(cpu)], "o."[!!(rdp->grpmask & rdp->mynode->qsmaskinit)], "N."[!!(rdp->grpmask & rdp->mynode->qsmaskinitnext)], + !IS_ENABLED(CONFIG_IRQ_WORK) ? '?' : + rdp->rcu_iw_pending ? (int)min(delta, 9UL) + '0' : + "!."[!delta], ticks_value, ticks_title, rcu_dynticks_snap(rdtp) & 0xfff, rdtp->dynticks_nesting, rdtp->dynticks_nmi_nesting, From 83b6ca1fede773eebcdfb44f5a94eb410d48b886 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 31 Aug 2017 16:47:08 -0700 Subject: [PATCH 07/15] rcu: Turn off tracing before dumping trace Currently, RCU allows tracing to continue when it automatically does ftrace_dump() after detecting an error condition, which can result in excessively large traces and lost trace events. This commit therefore does a tracing_off() before any of these ftrace_dump() calls. Signed-off-by: Paul E. McKenney --- kernel/rcu/rcu.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h index e4b43fef89f5..b8729eb09a5d 100644 --- a/kernel/rcu/rcu.h +++ b/kernel/rcu/rcu.h @@ -220,8 +220,10 @@ do { \ static atomic_t ___rfd_beenhere = ATOMIC_INIT(0); \ \ if (!atomic_read(&___rfd_beenhere) && \ - !atomic_xchg(&___rfd_beenhere, 1)) \ + !atomic_xchg(&___rfd_beenhere, 1)) { \ + tracing_off(); \ ftrace_dump(oops_dump_mode); \ + } \ } while (0) void rcu_early_boot_tests(void); From f22ce09157239aab08eae99c678ef664f71a9097 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 1 Sep 2017 14:40:54 -0700 Subject: [PATCH 08/15] rcu: Suppress RCU CPU stall warnings while dumping trace Currently, RCU emits Suppress RCU CPU stall warnings during its automatically initiated ftrace_dump() calls after detecting an error condition, which can result in excessively excessive console output and lost trace events. This commit therefore suppresses RCU CPU stall warnings across any of these ftrace_dump() calls. Signed-off-by: Paul E. McKenney --- kernel/rcu/rcu.h | 17 +++++++++++++++++ kernel/rcu/update.c | 1 + 2 files changed, 18 insertions(+) diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h index b8729eb09a5d..59c471de342a 100644 --- a/kernel/rcu/rcu.h +++ b/kernel/rcu/rcu.h @@ -203,6 +203,21 @@ static inline bool __rcu_reclaim(const char *rn, struct rcu_head *head) extern int rcu_cpu_stall_suppress; int rcu_jiffies_till_stall_check(void); +#define rcu_ftrace_dump_stall_suppress() \ +do { \ + if (!rcu_cpu_stall_suppress) \ + rcu_cpu_stall_suppress = 3; \ +} while (0) + +#define rcu_ftrace_dump_stall_unsuppress() \ +do { \ + if (rcu_cpu_stall_suppress == 3) \ + rcu_cpu_stall_suppress = 0; \ +} while (0) + +#else /* #endif #ifdef CONFIG_RCU_STALL_COMMON */ +#define rcu_ftrace_dump_stall_suppress() +#define rcu_ftrace_dump_stall_unsuppress() #endif /* #ifdef CONFIG_RCU_STALL_COMMON */ /* @@ -222,7 +237,9 @@ do { \ if (!atomic_read(&___rfd_beenhere) && \ !atomic_xchg(&___rfd_beenhere, 1)) { \ tracing_off(); \ + rcu_ftrace_dump_stall_suppress(); \ ftrace_dump(oops_dump_mode); \ + rcu_ftrace_dump_stall_unsuppress(); \ } \ } while (0) diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 5033b66d2753..3dc8efb16dc7 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -494,6 +494,7 @@ EXPORT_SYMBOL_GPL(do_trace_rcu_torture_read); #endif int rcu_cpu_stall_suppress __read_mostly; /* 1 = suppress stall warnings. */ +EXPORT_SYMBOL_GPL(rcu_cpu_stall_suppress); static int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT; module_param(rcu_cpu_stall_suppress, int, 0644); From 2b1516e55f8416acfb48d5f43d41222d180fb5a3 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 18 Aug 2017 16:11:37 -0700 Subject: [PATCH 09/15] rcutorture: Add interrupt-disable capability to stall-warning tests When rcutorture sees the rcutorture.stall_cpu kernel boot parameter, it loops with preemption disabled, which does in fact normally generate an RCU CPU stall warning message. However, there are test scenarios that need the stalling CPU to have interrupts disabled. This commit therefore adds an rcutorture.stall_cpu_irqsoff kernel boot parameter that causes the stalling CPU to disable interrupts. Signed-off-by: Paul E. McKenney --- .../admin-guide/kernel-parameters.txt | 3 +++ kernel/rcu/rcutorture.c | 18 +++++++++++++----- 2 files changed, 16 insertions(+), 5 deletions(-) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 05496622b4ef..bc94c47085a5 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3539,6 +3539,9 @@ rcutorture.stall_cpu_holdoff= [KNL] Time to wait (s) after boot before inducing stall. + rcutorture.stall_cpu_irqsoff= [KNL] + Disable interrupts while stalling if set. + rcutorture.stat_interval= [KNL] Time (s) between statistics printk()s. diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index 45f2ffbc1e78..0273bc0a8586 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -89,6 +89,7 @@ torture_param(int, shutdown_secs, 0, "Shutdown time (s), <= zero to disable."); torture_param(int, stall_cpu, 0, "Stall duration (s), zero to disable."); torture_param(int, stall_cpu_holdoff, 10, "Time to wait before starting stall (s)."); +torture_param(int, stall_cpu_irqsoff, 0, "Disable interrupts while stalling."); torture_param(int, stat_interval, 60, "Number of seconds between stats printk()s"); torture_param(int, stutter, 5, "Number of seconds to run/halt test"); @@ -1357,7 +1358,7 @@ rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag) "fqs_duration=%d fqs_holdoff=%d fqs_stutter=%d " "test_boost=%d/%d test_boost_interval=%d " "test_boost_duration=%d shutdown_secs=%d " - "stall_cpu=%d stall_cpu_holdoff=%d " + "stall_cpu=%d stall_cpu_holdoff=%d stall_cpu_irqsoff=%d " "n_barrier_cbs=%d " "onoff_interval=%d onoff_holdoff=%d\n", torture_type, tag, nrealreaders, nfakewriters, @@ -1365,7 +1366,7 @@ rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag) stutter, irqreader, fqs_duration, fqs_holdoff, fqs_stutter, test_boost, cur_ops->can_boost, test_boost_interval, test_boost_duration, shutdown_secs, - stall_cpu, stall_cpu_holdoff, + stall_cpu, stall_cpu_holdoff, stall_cpu_irqsoff, n_barrier_cbs, onoff_interval, onoff_holdoff); } @@ -1430,12 +1431,19 @@ static int rcu_torture_stall(void *args) if (!kthread_should_stop()) { stop_at = get_seconds() + stall_cpu; /* RCU CPU stall is expected behavior in following code. */ - pr_alert("rcu_torture_stall start.\n"); rcu_read_lock(); - preempt_disable(); + if (stall_cpu_irqsoff) + local_irq_disable(); + else + preempt_disable(); + pr_alert("rcu_torture_stall start on CPU %d.\n", + smp_processor_id()); while (ULONG_CMP_LT(get_seconds(), stop_at)) continue; /* Induce RCU CPU stall warning. */ - preempt_enable(); + if (stall_cpu_irqsoff) + local_irq_enable(); + else + preempt_enable(); rcu_read_unlock(); pr_alert("rcu_torture_stall end.\n"); } From 0032f4e889764d22ccccb6a15742071d6f0d1f5a Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 30 Aug 2017 10:40:17 -0700 Subject: [PATCH 10/15] rcutorture: Dump writer stack if stalled Right now, rcutorture warns if an rcu_torture_writer() kthread stalls, but this warning is not always all that helpful. This commit therefore makes the first such warning include a stack dump. This in turn requires that sched_show_task() be exported to GPL modules, so this commit makes that change as well. Signed-off-by: Paul E. McKenney --- kernel/rcu/rcutorture.c | 6 ++++++ kernel/sched/core.c | 1 + 2 files changed, 7 insertions(+) diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index 0273bc0a8586..362eb2f78b3c 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -51,6 +51,7 @@ #include #include #include +#include #include "rcu.h" @@ -1240,6 +1241,7 @@ rcu_torture_stats_print(void) long pipesummary[RCU_TORTURE_PIPE_LEN + 1] = { 0 }; long batchsummary[RCU_TORTURE_PIPE_LEN + 1] = { 0 }; static unsigned long rtcv_snap = ULONG_MAX; + static bool splatted; struct task_struct *wtp; for_each_possible_cpu(cpu) { @@ -1325,6 +1327,10 @@ rcu_torture_stats_print(void) gpnum, completed, flags, wtp == NULL ? ~0UL : wtp->state, wtp == NULL ? -1 : (int)task_cpu(wtp)); + if (!splatted && wtp) { + sched_show_task(wtp); + splatted = true; + } show_rcu_gp_kthreads(); rcu_ftrace_dump(DUMP_ALL); } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index d17c5da523a0..7ae0151dcc1d 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5165,6 +5165,7 @@ void sched_show_task(struct task_struct *p) show_stack(p, NULL); put_task_stack(p); } +EXPORT_SYMBOL_GPL(sched_show_task); static inline bool state_filter_match(unsigned long state_filter, struct task_struct *p) From b038c58bd258522d9cde6619d730ebdb1f7be198 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 30 Aug 2017 15:33:49 -0700 Subject: [PATCH 11/15] torture: Provide TMPDIR environment variable to specify tmpdir Both rcutorture and locktorture currently place temporary files in /tmp, in keeping with decades-long tradition. However, sometimes it is useful to specify an alternative temporary directory, for example, for space or performance reasons. This commit therefore causes the torture-test scripting to use the path specified in the TMPDIR environment variable, or to fall back to traditional /tmp if this variable is not set. Signed-off-by: Paul E. McKenney --- tools/testing/selftests/rcutorture/bin/config_override.sh | 2 +- tools/testing/selftests/rcutorture/bin/configcheck.sh | 2 +- tools/testing/selftests/rcutorture/bin/configinit.sh | 2 +- tools/testing/selftests/rcutorture/bin/kvm-build.sh | 2 +- tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh | 2 +- tools/testing/selftests/rcutorture/bin/kvm.sh | 4 ++-- tools/testing/selftests/rcutorture/bin/parse-build.sh | 2 +- tools/testing/selftests/rcutorture/bin/parse-torture.sh | 2 +- 8 files changed, 9 insertions(+), 9 deletions(-) diff --git a/tools/testing/selftests/rcutorture/bin/config_override.sh b/tools/testing/selftests/rcutorture/bin/config_override.sh index 49fa51726ce3..ef7fcbac3d42 100755 --- a/tools/testing/selftests/rcutorture/bin/config_override.sh +++ b/tools/testing/selftests/rcutorture/bin/config_override.sh @@ -42,7 +42,7 @@ else exit 1 fi -T=/tmp/config_override.sh.$$ +T=${TMPDIR-/tmp}/config_override.sh.$$ trap 'rm -rf $T' 0 mkdir $T diff --git a/tools/testing/selftests/rcutorture/bin/configcheck.sh b/tools/testing/selftests/rcutorture/bin/configcheck.sh index 70fca318a82b..197deece7c7c 100755 --- a/tools/testing/selftests/rcutorture/bin/configcheck.sh +++ b/tools/testing/selftests/rcutorture/bin/configcheck.sh @@ -19,7 +19,7 @@ # # Authors: Paul E. McKenney -T=/tmp/abat-chk-config.sh.$$ +T=${TMPDIR-/tmp}/abat-chk-config.sh.$$ trap 'rm -rf $T' 0 mkdir $T diff --git a/tools/testing/selftests/rcutorture/bin/configinit.sh b/tools/testing/selftests/rcutorture/bin/configinit.sh index 3f81a1095206..51f66a7ce876 100755 --- a/tools/testing/selftests/rcutorture/bin/configinit.sh +++ b/tools/testing/selftests/rcutorture/bin/configinit.sh @@ -32,7 +32,7 @@ # # Authors: Paul E. McKenney -T=/tmp/configinit.sh.$$ +T=${TMPDIR-/tmp}/configinit.sh.$$ trap 'rm -rf $T' 0 mkdir $T diff --git a/tools/testing/selftests/rcutorture/bin/kvm-build.sh b/tools/testing/selftests/rcutorture/bin/kvm-build.sh index 46752c164676..fb66d0173638 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-build.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-build.sh @@ -35,7 +35,7 @@ then exit 1 fi -T=/tmp/test-linux.sh.$$ +T=${TMPDIR-/tmp}/test-linux.sh.$$ trap 'rm -rf $T' 0 mkdir $T diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh index 0af36a721b9c..ab14b97c942c 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh @@ -38,7 +38,7 @@ # # Authors: Paul E. McKenney -T=/tmp/kvm-test-1-run.sh.$$ +T=${TMPDIR-/tmp}/kvm-test-1-run.sh.$$ trap 'rm -rf $T' 0 mkdir $T diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh index b55895fb10ed..ccd49e958fd2 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm.sh @@ -30,7 +30,7 @@ scriptname=$0 args="$*" -T=/tmp/kvm.sh.$$ +T=${TMPDIR-/tmp}/kvm.sh.$$ trap 'rm -rf $T' 0 mkdir $T @@ -222,7 +222,7 @@ do exit 1 fi done -sort -k2nr $T/cfgcpu > $T/cfgcpu.sort +sort -k2nr $T/cfgcpu -T="$T" > $T/cfgcpu.sort # Use a greedy bin-packing algorithm, sorting the list accordingly. awk < $T/cfgcpu.sort > $T/cfgcpu.pack -v ncpus=$cpus ' diff --git a/tools/testing/selftests/rcutorture/bin/parse-build.sh b/tools/testing/selftests/rcutorture/bin/parse-build.sh index a6b57622c2e5..24fe5f822b28 100755 --- a/tools/testing/selftests/rcutorture/bin/parse-build.sh +++ b/tools/testing/selftests/rcutorture/bin/parse-build.sh @@ -28,7 +28,7 @@ F=$1 title=$2 -T=/tmp/parse-build.sh.$$ +T=${TMPDIR-/tmp}/parse-build.sh.$$ trap 'rm -rf $T' 0 mkdir $T diff --git a/tools/testing/selftests/rcutorture/bin/parse-torture.sh b/tools/testing/selftests/rcutorture/bin/parse-torture.sh index e3c5f0705696..f12c38909b00 100755 --- a/tools/testing/selftests/rcutorture/bin/parse-torture.sh +++ b/tools/testing/selftests/rcutorture/bin/parse-torture.sh @@ -27,7 +27,7 @@ # # Authors: Paul E. McKenney -T=/tmp/parse-torture.sh.$$ +T=${TMPDIR-/tmp}/parse-torture.sh.$$ file="$1" title="$2" From b88697810d7c1d102a529990f9071b0f14cfe6df Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 18 Oct 2017 08:33:44 -0700 Subject: [PATCH 12/15] rcu: Do not include rtmutex_common.h unconditionally This commit adjusts include files and provides definitions in preparation for suppressing lockdep false-positive ->boost_mtx complaints. Without this preparation, architectures not supporting rt_mutex will get build failures. Reported-by: kbuild test robot Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Paul E. McKenney --- kernel/rcu/tree_plugin.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index fed95fa941e6..969eae45f05d 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -54,6 +54,7 @@ DEFINE_PER_CPU(char, rcu_cpu_has_work); * This probably needs to be excluded from -rt builds. */ #define rt_mutex_owner(a) ({ WARN_ON_ONCE(1); NULL; }) +#define rt_mutex_futex_unlock(x) WARN_ON_ONCE(1) #endif /* #else #ifdef CONFIG_RCU_BOOST */ @@ -911,8 +912,6 @@ void exit_rcu(void) #ifdef CONFIG_RCU_BOOST -#include "../locking/rtmutex_common.h" - static void rcu_wake_cond(struct task_struct *t, int status) { /* From 02a7c234e54052101164368ff981bd72f7acdd65 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 19 Sep 2017 15:36:42 -0700 Subject: [PATCH 13/15] rcu: Suppress lockdep false-positive ->boost_mtx complaints RCU priority boosting uses rt_mutex_init_proxy_locked() to initialize an rt_mutex structure in locked state held by some other task. When that other task releases it, lockdep complains (quite accurately, but a bit uselessly) that the other task never acquired it. This complaint can suppress other, more helpful, lockdep complaints, and in any case it is a false positive. This commit therefore switches from rt_mutex_unlock() to rt_mutex_futex_unlock(), thereby avoiding the lockdep annotations. Of course, if lockdep ever learns about rt_mutex_init_proxy_locked(), addtional adjustments will be required. Suggested-by: Peter Zijlstra Signed-off-by: Paul E. McKenney --- kernel/rcu/tree_plugin.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 969eae45f05d..1eaab96d1a3c 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -531,7 +531,7 @@ void rcu_read_unlock_special(struct task_struct *t) /* Unboost if we were boosted. */ if (IS_ENABLED(CONFIG_RCU_BOOST) && drop_boost_mutex) - rt_mutex_unlock(&rnp->boost_mtx); + rt_mutex_futex_unlock(&rnp->boost_mtx); /* * If this was the last task on the expedited lists, From c0da313e090d6e7130d0c3005245176296c24e4a Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 22 Sep 2017 09:58:47 -0700 Subject: [PATCH 14/15] rcu: Add extended-quiescent-state testing advice If you add or remove calls to rcu_idle_enter(), rcu_user_enter(), rcu_irq_exit(), rcu_irq_exit_irqson(), rcu_idle_exit(), rcu_user_exit(), rcu_irq_enter(), rcu_irq_enter_irqson(), rcu_nmi_enter(), or rcu_nmi_exit(), you should run a full set of tests on a kernel built with CONFIG_RCU_EQS_DEBUG=y. Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index b0ad62b0e7b8..d234356d7afc 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -837,6 +837,9 @@ static void rcu_eqs_enter(bool user) * We crowbar the ->dynticks_nesting field to zero to allow for * the possibility of usermode upcalls having messed up our count * of interrupt nesting level during the prior busy period. + * + * If you add or remove a call to rcu_idle_enter(), be sure to test with + * CONFIG_RCU_EQS_DEBUG=y. */ void rcu_idle_enter(void) { @@ -852,6 +855,9 @@ void rcu_idle_enter(void) * is permitted between this call and rcu_user_exit(). This way the * CPU doesn't need to maintain the tick for RCU maintenance purposes * when the CPU runs in userspace. + * + * If you add or remove a call to rcu_user_enter(), be sure to test with + * CONFIG_RCU_EQS_DEBUG=y. */ void rcu_user_enter(void) { @@ -875,6 +881,9 @@ void rcu_user_enter(void) * Use things like work queues to work around this limitation. * * You have been warned. + * + * If you add or remove a call to rcu_irq_exit(), be sure to test with + * CONFIG_RCU_EQS_DEBUG=y. */ void rcu_irq_exit(void) { @@ -899,6 +908,9 @@ void rcu_irq_exit(void) /* * Wrapper for rcu_irq_exit() where interrupts are enabled. + * + * If you add or remove a call to rcu_irq_exit_irqson(), be sure to test + * with CONFIG_RCU_EQS_DEBUG=y. */ void rcu_irq_exit_irqson(void) { @@ -971,6 +983,9 @@ static void rcu_eqs_exit(bool user) * allow for the possibility of usermode upcalls messing up our count * of interrupt nesting level during the busy period that is just * now starting. + * + * If you add or remove a call to rcu_idle_exit(), be sure to test with + * CONFIG_RCU_EQS_DEBUG=y. */ void rcu_idle_exit(void) { @@ -987,6 +1002,9 @@ void rcu_idle_exit(void) * * Exit RCU idle mode while entering the kernel because it can * run a RCU read side critical section anytime. + * + * If you add or remove a call to rcu_user_exit(), be sure to test with + * CONFIG_RCU_EQS_DEBUG=y. */ void rcu_user_exit(void) { @@ -1012,6 +1030,9 @@ void rcu_user_exit(void) * Use things like work queues to work around this limitation. * * You have been warned. + * + * If you add or remove a call to rcu_irq_enter(), be sure to test with + * CONFIG_RCU_EQS_DEBUG=y. */ void rcu_irq_enter(void) { @@ -1037,6 +1058,9 @@ void rcu_irq_enter(void) /* * Wrapper for rcu_irq_enter() where interrupts are enabled. + * + * If you add or remove a call to rcu_irq_enter_irqson(), be sure to test + * with CONFIG_RCU_EQS_DEBUG=y. */ void rcu_irq_enter_irqson(void) { @@ -1055,6 +1079,9 @@ void rcu_irq_enter_irqson(void) * that the CPU is active. This implementation permits nested NMIs, as * long as the nesting level does not overflow an int. (You will probably * run out of stack space first.) + * + * If you add or remove a call to rcu_nmi_enter(), be sure to test + * with CONFIG_RCU_EQS_DEBUG=y. */ void rcu_nmi_enter(void) { @@ -1087,6 +1114,9 @@ void rcu_nmi_enter(void) * RCU-idle period, update rdtp->dynticks and rdtp->dynticks_nmi_nesting * to let the RCU grace-period handling know that the CPU is back to * being RCU-idle. + * + * If you add or remove a call to rcu_nmi_exit(), be sure to test + * with CONFIG_RCU_EQS_DEBUG=y. */ void rcu_nmi_exit(void) { From 56628a7fc84a6e3c4c84886d70ec26da3d7f2ce4 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Fri, 22 Sep 2017 17:28:06 +0200 Subject: [PATCH 15/15] rcu/segcblist: Include rcupdate.h The RT build on ARM complains about non-existing ULONG_CMP_LT. This commit therefore includes rcupdate.h into rcu_segcblist.c. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Paul E. McKenney --- kernel/rcu/rcu_segcblist.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/rcu/rcu_segcblist.c b/kernel/rcu/rcu_segcblist.c index 7649fcd2c4c7..88cba7c2956c 100644 --- a/kernel/rcu/rcu_segcblist.c +++ b/kernel/rcu/rcu_segcblist.c @@ -23,6 +23,7 @@ #include #include #include +#include #include "rcu_segcblist.h"