From 365187fbc04fd55766bf6a94e37e558505bf480a Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 10 Mar 2014 10:55:52 -0700 Subject: rcu: Update cpu_needs_another_gp() for futures from non-NOCB CPUs In the old days, the only source of requests for future grace periods was NOCB CPUs. This has changed: CPUs routinely post requests for future grace periods in order to promote power efficiency and reduce OS jitter with minimal impact on grace-period latency. This commit therefore updates cpu_needs_another_gp() to invoke rcu_future_needs_gp() instead of rcu_nocb_needs_gp(). The latter is no longer used, so is now removed. This commit also adds tracing for the irq_work_queue() wakeup case. Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- kernel/rcu/tree.h | 1 - 1 file changed, 1 deletion(-) (limited to 'kernel/rcu/tree.h') diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 75dc3c39a02a..7b572c5c65e1 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -547,7 +547,6 @@ static void print_cpu_stall_info(struct rcu_state *rsp, int cpu); static void print_cpu_stall_info_end(void); static void zero_cpu_stall_ticks(struct rcu_data *rdp); static void increment_cpu_stall_ticks(void); -static int rcu_nocb_needs_gp(struct rcu_state *rsp); static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq); static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp); static void rcu_init_one_nocb(struct rcu_node *rnp); -- cgit v1.2.3 From 9b67122ae3da3018c966148233739116ed89502a Mon Sep 17 00:00:00 2001 From: Iulia Manda Date: Tue, 11 Mar 2014 13:18:22 +0200 Subject: rcu: Remove unused rcu_data structure field The ->preemptible field in rcu_data is only initialized in the function rcu_init_percpu_data(), and never used. This commit therefore removes this field. Signed-off-by: Iulia Manda Reviewed-by: Josh Triplett Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- kernel/rcu/tree.c | 6 ++---- kernel/rcu/tree.h | 1 - 2 files changed, 2 insertions(+), 5 deletions(-) (limited to 'kernel/rcu/tree.h') diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index b4688993e956..2cc39c781085 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -3180,7 +3180,7 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp) * that this CPU cannot possibly have any RCU callbacks in flight yet. */ static void -rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptible) +rcu_init_percpu_data(int cpu, struct rcu_state *rsp) { unsigned long flags; unsigned long mask; @@ -3193,7 +3193,6 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptible) /* Set up local state, ensuring consistent view of global state. */ raw_spin_lock_irqsave(&rnp->lock, flags); rdp->beenonline = 1; /* We have now been online. */ - rdp->preemptible = preemptible; rdp->qlen_last_fqs_check = 0; rdp->n_force_qs_snap = rsp->n_force_qs; rdp->blimit = blimit; @@ -3237,8 +3236,7 @@ static void rcu_prepare_cpu(int cpu) struct rcu_state *rsp; for_each_rcu_flavor(rsp) - rcu_init_percpu_data(cpu, rsp, - strcmp(rsp->name, "rcu_preempt") == 0); + rcu_init_percpu_data(cpu, rsp); } /* diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 7b572c5c65e1..13766ad2f4ee 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -252,7 +252,6 @@ struct rcu_data { bool passed_quiesce; /* User-mode/idle loop etc. */ bool qs_pending; /* Core waits for quiesc state. */ bool beenonline; /* CPU online at least once. */ - bool preemptible; /* Preemptible RCU? */ struct rcu_node *mynode; /* This CPU's leaf of hierarchy */ unsigned long grpmask; /* Mask to apply to leaf qsmask. */ #ifdef CONFIG_RCU_CPU_STALL_INFO -- cgit v1.2.3 From 48a7639ce80cf279834d0d44865e49ecd714f37d Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 11 Mar 2014 13:02:16 -0700 Subject: rcu: Make callers awaken grace-period kthread The rcu_start_gp_advanced() function currently uses irq_work_queue() to defer wakeups of the RCU grace-period kthread. This deferring is necessary to avoid RCU-scheduler deadlocks involving the rcu_node structure's lock, meaning that RCU cannot call any of the scheduler's wake-up functions while holding one of these locks. Unfortunately, the second and subsequent calls to irq_work_queue() are ignored, and the first call will be ignored (aside from queuing the work item) if the scheduler-clock tick is turned off. This is OK for many uses, especially those where irq_work_queue() is called from an interrupt or softirq handler, because in those cases the scheduler-clock-tick state will be re-evaluated, which will turn the scheduler-clock tick back on. On the next tick, any deferred work will then be processed. However, this strategy does not always work for RCU, which can be invoked at process level from idle CPUs. In this case, the tick might never be turned back on, indefinitely defering a grace-period start request. Note that the RCU CPU stall detector cannot see this condition, because there is no RCU grace period in progress. Therefore, we can (and do!) see long tens-of-seconds stalls in grace-period handling. In theory, we could see a full grace-period hang, but rcutorture testing to date has seen only the tens-of-seconds stalls. Event tracing demonstrates that irq_work_queue() is being called repeatedly to no effect during these stalls: The "newreq" event appears repeatedly from a task that is not one of the grace-period kthreads. In theory, irq_work_queue() might be fixed to avoid this sort of issue, but RCU's requirements are unusual and it is quite straightforward to pass wake-up responsibility up through RCU's call chain, so that the wakeup happens when the offending locks are released. This commit therefore makes this change. The rcu_start_gp_advanced(), rcu_start_future_gp(), rcu_accelerate_cbs(), rcu_advance_cbs(), __note_gp_changes(), and rcu_start_gp() functions now return a boolean which indicates when a wake-up is needed. A new rcu_gp_kthread_wake() does the wakeup when it is necessary and safe to do so: No self-wakes, no wake-ups if the ->gp_flags field indicates there is no need (as in someone else did the wake-up before we got around to it), and no wake-ups before the grace-period kthread has been created. Signed-off-by: Paul E. McKenney Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Frederic Weisbecker Reviewed-by: Josh Triplett --- kernel/rcu/tree.c | 137 +++++++++++++++++++++++++++++------------------ kernel/rcu/tree.h | 1 - kernel/rcu/tree_plugin.h | 10 +++- 3 files changed, 94 insertions(+), 54 deletions(-) (limited to 'kernel/rcu/tree.h') diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index c624415f8386..fca911b6b29c 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -243,7 +243,7 @@ static ulong jiffies_till_next_fqs = ULONG_MAX; module_param(jiffies_till_first_fqs, ulong, 0644); module_param(jiffies_till_next_fqs, ulong, 0644); -static void rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp, +static bool rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp); static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *rsp, bool *isidle, @@ -1138,15 +1138,18 @@ static void trace_rcu_future_gp(struct rcu_node *rnp, struct rcu_data *rdp, /* * Start some future grace period, as needed to handle newly arrived * callbacks. The required future grace periods are recorded in each - * rcu_node structure's ->need_future_gp field. + * rcu_node structure's ->need_future_gp field. Returns true if there + * is reason to awaken the grace-period kthread. * * The caller must hold the specified rcu_node structure's ->lock. */ -static unsigned long __maybe_unused -rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp) +static bool __maybe_unused +rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp, + unsigned long *c_out) { unsigned long c; int i; + bool ret = false; struct rcu_node *rnp_root = rcu_get_root(rdp->rsp); /* @@ -1157,7 +1160,7 @@ rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp) trace_rcu_future_gp(rnp, rdp, c, TPS("Startleaf")); if (rnp->need_future_gp[c & 0x1]) { trace_rcu_future_gp(rnp, rdp, c, TPS("Prestartleaf")); - return c; + goto out; } /* @@ -1171,7 +1174,7 @@ rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp) ACCESS_ONCE(rnp->gpnum) != ACCESS_ONCE(rnp->completed)) { rnp->need_future_gp[c & 0x1]++; trace_rcu_future_gp(rnp, rdp, c, TPS("Startedleaf")); - return c; + goto out; } /* @@ -1212,12 +1215,15 @@ rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp) trace_rcu_future_gp(rnp, rdp, c, TPS("Startedleafroot")); } else { trace_rcu_future_gp(rnp, rdp, c, TPS("Startedroot")); - rcu_start_gp_advanced(rdp->rsp, rnp_root, rdp); + ret = rcu_start_gp_advanced(rdp->rsp, rnp_root, rdp); } unlock_out: if (rnp != rnp_root) raw_spin_unlock(&rnp_root->lock); - return c; +out: + if (c_out != NULL) + *c_out = c; + return ret; } /* @@ -1240,6 +1246,22 @@ static int rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) return needmore; } +/* + * Awaken the grace-period kthread for the specified flavor of RCU. + * Don't do a self-awaken, and don't bother awakening when there is + * nothing for the grace-period kthread to do (as in several CPUs + * raced to awaken, and we lost), and finally don't try to awaken + * a kthread that has not yet been created. + */ +static void rcu_gp_kthread_wake(struct rcu_state *rsp) +{ + if (current == rsp->gp_kthread || + !ACCESS_ONCE(rsp->gp_flags) || + !rsp->gp_kthread) + return; + wake_up(&rsp->gp_wq); +} + /* * If there is room, assign a ->completed number to any callbacks on * this CPU that have not already been assigned. Also accelerate any @@ -1247,19 +1269,21 @@ static int rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) * since proven to be too conservative, which can happen if callbacks get * assigned a ->completed number while RCU is idle, but with reference to * a non-root rcu_node structure. This function is idempotent, so it does - * not hurt to call it repeatedly. + * not hurt to call it repeatedly. Returns an flag saying that we should + * awaken the RCU grace-period kthread. * * The caller must hold rnp->lock with interrupts disabled. */ -static void rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp, +static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp) { unsigned long c; int i; + bool ret; /* If the CPU has no callbacks, nothing to do. */ if (!rdp->nxttail[RCU_NEXT_TAIL] || !*rdp->nxttail[RCU_DONE_TAIL]) - return; + return false; /* * Starting from the sublist containing the callbacks most @@ -1288,7 +1312,7 @@ static void rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp, * be grouped into. */ if (++i >= RCU_NEXT_TAIL) - return; + return false; /* * Assign all subsequent callbacks' ->completed number to the next @@ -1300,13 +1324,14 @@ static void rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp, rdp->nxtcompleted[i] = c; } /* Record any needed additional grace periods. */ - rcu_start_future_gp(rnp, rdp); + ret = rcu_start_future_gp(rnp, rdp, NULL); /* Trace depending on how much we were able to accelerate. */ if (!*rdp->nxttail[RCU_WAIT_TAIL]) trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("AccWaitCB")); else trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("AccReadyCB")); + return ret; } /* @@ -1315,17 +1340,18 @@ static void rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp, * assign ->completed numbers to any callbacks in the RCU_NEXT_TAIL * sublist. This function is idempotent, so it does not hurt to * invoke it repeatedly. As long as it is not invoked -too- often... + * Returns true if the RCU grace-period kthread needs to be awakened. * * The caller must hold rnp->lock with interrupts disabled. */ -static void rcu_advance_cbs(struct rcu_state *rsp, struct rcu_node *rnp, +static bool rcu_advance_cbs(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp) { int i, j; /* If the CPU has no callbacks, nothing to do. */ if (!rdp->nxttail[RCU_NEXT_TAIL] || !*rdp->nxttail[RCU_DONE_TAIL]) - return; + return false; /* * Find all callbacks whose ->completed numbers indicate that they @@ -1349,26 +1375,30 @@ static void rcu_advance_cbs(struct rcu_state *rsp, struct rcu_node *rnp, } /* Classify any remaining callbacks. */ - rcu_accelerate_cbs(rsp, rnp, rdp); + return rcu_accelerate_cbs(rsp, rnp, rdp); } /* * Update CPU-local rcu_data state to record the beginnings and ends of * grace periods. The caller must hold the ->lock of the leaf rcu_node * structure corresponding to the current CPU, and must have irqs disabled. + * Returns true if the grace-period kthread needs to be awakened. */ -static void __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp) +static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp, + struct rcu_data *rdp) { + bool ret; + /* Handle the ends of any preceding grace periods first. */ if (rdp->completed == rnp->completed) { /* No grace period end, so just accelerate recent callbacks. */ - rcu_accelerate_cbs(rsp, rnp, rdp); + ret = rcu_accelerate_cbs(rsp, rnp, rdp); } else { /* Advance callbacks. */ - rcu_advance_cbs(rsp, rnp, rdp); + ret = rcu_advance_cbs(rsp, rnp, rdp); /* Remember that we saw this grace-period completion. */ rdp->completed = rnp->completed; @@ -1387,11 +1417,13 @@ static void __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp, struc rdp->qs_pending = !!(rnp->qsmask & rdp->grpmask); zero_cpu_stall_ticks(rdp); } + return ret; } static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp) { unsigned long flags; + bool needwake; struct rcu_node *rnp; local_irq_save(flags); @@ -1403,8 +1435,10 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp) return; } smp_mb__after_unlock_lock(); - __note_gp_changes(rsp, rnp, rdp); + needwake = __note_gp_changes(rsp, rnp, rdp); raw_spin_unlock_irqrestore(&rnp->lock, flags); + if (needwake) + rcu_gp_kthread_wake(rsp); } /* @@ -1468,7 +1502,7 @@ static int rcu_gp_init(struct rcu_state *rsp) WARN_ON_ONCE(rnp->completed != rsp->completed); ACCESS_ONCE(rnp->completed) = rsp->completed; if (rnp == rdp->mynode) - __note_gp_changes(rsp, rnp, rdp); + (void)__note_gp_changes(rsp, rnp, rdp); rcu_preempt_boost_start_gp(rnp); trace_rcu_grace_period_init(rsp->name, rnp->gpnum, rnp->level, rnp->grplo, @@ -1528,6 +1562,7 @@ static int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in) static void rcu_gp_cleanup(struct rcu_state *rsp) { unsigned long gp_duration; + bool needgp = false; int nocb = 0; struct rcu_data *rdp; struct rcu_node *rnp = rcu_get_root(rsp); @@ -1563,7 +1598,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) ACCESS_ONCE(rnp->completed) = rsp->gpnum; rdp = this_cpu_ptr(rsp->rda); if (rnp == rdp->mynode) - __note_gp_changes(rsp, rnp, rdp); + needgp = __note_gp_changes(rsp, rnp, rdp) || needgp; /* smp_mb() provided by prior unlock-lock pair. */ nocb += rcu_future_gp_cleanup(rsp, rnp); raw_spin_unlock_irq(&rnp->lock); @@ -1579,8 +1614,9 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) trace_rcu_grace_period(rsp->name, rsp->completed, TPS("end")); rsp->fqs_state = RCU_GP_IDLE; rdp = this_cpu_ptr(rsp->rda); - rcu_advance_cbs(rsp, rnp, rdp); /* Reduce false positives below. */ - if (cpu_needs_another_gp(rsp, rdp)) { + /* Advance CBs to reduce false positives below. */ + needgp = rcu_advance_cbs(rsp, rnp, rdp) || needgp; + if (needgp || cpu_needs_another_gp(rsp, rdp)) { ACCESS_ONCE(rsp->gp_flags) = RCU_GP_FLAG_INIT; trace_rcu_grace_period(rsp->name, ACCESS_ONCE(rsp->gpnum), @@ -1680,16 +1716,6 @@ static int __noreturn rcu_gp_kthread(void *arg) } } -static void rsp_wakeup(struct irq_work *work) -{ - struct rcu_state *rsp = container_of(work, struct rcu_state, wakeup_work); - - /* Wake up rcu_gp_kthread() to start the grace period. */ - wake_up(&rsp->gp_wq); - trace_rcu_grace_period(rsp->name, ACCESS_ONCE(rsp->gpnum), - "Workqueuewoken"); -} - /* * Start a new RCU grace period if warranted, re-initializing the hierarchy * in preparation for detecting the next grace period. The caller must hold @@ -1698,8 +1724,10 @@ static void rsp_wakeup(struct irq_work *work) * Note that it is legal for a dying CPU (which is marked as offline) to * invoke this function. This can happen when the dying CPU reports its * quiescent state. + * + * Returns true if the grace-period kthread must be awakened. */ -static void +static bool rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp) { @@ -1710,7 +1738,7 @@ rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp, * or a grace period is already in progress. * Either way, don't start a new grace period. */ - return; + return false; } ACCESS_ONCE(rsp->gp_flags) = RCU_GP_FLAG_INIT; trace_rcu_grace_period(rsp->name, ACCESS_ONCE(rsp->gpnum), @@ -1719,14 +1747,9 @@ rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp, /* * We can't do wakeups while holding the rnp->lock, as that * could cause possible deadlocks with the rq->lock. Defer - * the wakeup to interrupt context. And don't bother waking - * up the running kthread. + * the wakeup to our caller. */ - if (current != rsp->gp_kthread) { - trace_rcu_grace_period(rsp->name, ACCESS_ONCE(rsp->gpnum), - "Workqueuewake"); - irq_work_queue(&rsp->wakeup_work); - } + return true; } /* @@ -1735,12 +1758,14 @@ rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp, * is invoked indirectly from rcu_advance_cbs(), which would result in * endless recursion -- or would do so if it wasn't for the self-deadlock * that is encountered beforehand. + * + * Returns true if the grace-period kthread needs to be awakened. */ -static void -rcu_start_gp(struct rcu_state *rsp) +static bool rcu_start_gp(struct rcu_state *rsp) { struct rcu_data *rdp = this_cpu_ptr(rsp->rda); struct rcu_node *rnp = rcu_get_root(rsp); + bool ret = false; /* * If there is no grace period in progress right now, any @@ -1750,8 +1775,9 @@ rcu_start_gp(struct rcu_state *rsp) * resulting in pointless grace periods. So, advance callbacks * then start the grace period! */ - rcu_advance_cbs(rsp, rnp, rdp); - rcu_start_gp_advanced(rsp, rnp, rdp); + ret = rcu_advance_cbs(rsp, rnp, rdp) || ret; + ret = rcu_start_gp_advanced(rsp, rnp, rdp) || ret; + return ret; } /* @@ -1840,6 +1866,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp) { unsigned long flags; unsigned long mask; + bool needwake; struct rcu_node *rnp; rnp = rdp->mynode; @@ -1868,9 +1895,11 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp) * This GP can't end until cpu checks in, so all of our * callbacks can be processed during the next GP. */ - rcu_accelerate_cbs(rsp, rnp, rdp); + needwake = rcu_accelerate_cbs(rsp, rnp, rdp); rcu_report_qs_rnp(mask, rsp, rnp, flags); /* rlses rnp->lock */ + if (needwake) + rcu_gp_kthread_wake(rsp); } } @@ -2354,6 +2383,7 @@ static void __rcu_process_callbacks(struct rcu_state *rsp) { unsigned long flags; + bool needwake; struct rcu_data *rdp = __this_cpu_ptr(rsp->rda); WARN_ON_ONCE(rdp->beenonline == 0); @@ -2365,8 +2395,10 @@ __rcu_process_callbacks(struct rcu_state *rsp) local_irq_save(flags); if (cpu_needs_another_gp(rsp, rdp)) { raw_spin_lock(&rcu_get_root(rsp)->lock); /* irqs disabled. */ - rcu_start_gp(rsp); + needwake = rcu_start_gp(rsp); raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags); + if (needwake) + rcu_gp_kthread_wake(rsp); } else { local_irq_restore(flags); } @@ -2424,6 +2456,8 @@ static void invoke_rcu_core(void) static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp, struct rcu_head *head, unsigned long flags) { + bool needwake; + /* * If called from an extended quiescent state, invoke the RCU * core in order to force a re-evaluation of RCU's idleness. @@ -2453,8 +2487,10 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp, raw_spin_lock(&rnp_root->lock); smp_mb__after_unlock_lock(); - rcu_start_gp(rsp); + needwake = rcu_start_gp(rsp); raw_spin_unlock(&rnp_root->lock); + if (needwake) + rcu_gp_kthread_wake(rsp); } else { /* Give the grace period a kick. */ rdp->blimit = LONG_MAX; @@ -3440,7 +3476,6 @@ static void __init rcu_init_one(struct rcu_state *rsp, rsp->rda = rda; init_waitqueue_head(&rsp->gp_wq); - init_irq_work(&rsp->wakeup_work, rsp_wakeup); rnp = rsp->level[rcu_num_lvls - 1]; for_each_possible_cpu(i) { while (i > rnp->grphi) diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 13766ad2f4ee..cdbb392d5b4b 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -461,7 +461,6 @@ struct rcu_state { const char *name; /* Name of structure. */ char abbr; /* Abbreviated name. */ struct list_head flavors; /* List of RCU flavors. */ - struct irq_work wakeup_work; /* Postponed wakeups */ }; /* Values for rcu_state structure's gp_flags field. */ diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index f60dd6ea8333..0cb0816036c5 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -1744,6 +1744,7 @@ int rcu_needs_cpu(int cpu, unsigned long *dj) static void rcu_prepare_for_idle(int cpu) { #ifndef CONFIG_RCU_NOCB_CPU_ALL + bool needwake; struct rcu_data *rdp; struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu); struct rcu_node *rnp; @@ -1792,8 +1793,10 @@ static void rcu_prepare_for_idle(int cpu) rnp = rdp->mynode; raw_spin_lock(&rnp->lock); /* irqs already disabled. */ smp_mb__after_unlock_lock(); - rcu_accelerate_cbs(rsp, rnp, rdp); + needwake = rcu_accelerate_cbs(rsp, rnp, rdp); raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ + if (needwake) + rcu_gp_kthread_wake(rsp); } #endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */ } @@ -2230,12 +2233,15 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp) unsigned long c; bool d; unsigned long flags; + bool needwake; struct rcu_node *rnp = rdp->mynode; raw_spin_lock_irqsave(&rnp->lock, flags); smp_mb__after_unlock_lock(); - c = rcu_start_future_gp(rnp, rdp); + needwake = rcu_start_future_gp(rnp, rdp, &c); raw_spin_unlock_irqrestore(&rnp->lock, flags); + if (needwake) + rcu_gp_kthread_wake(rdp->rsp); /* * Wait for the grace period. Do so interruptibly to avoid messing -- cgit v1.2.3 From afea227fd4acf4f097a9e77bbc2f07d4856ebd01 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 12 Mar 2014 07:10:41 -0700 Subject: rcutorture: Export RCU grace-period kthread wait state to rcutorture This commit allows rcutorture to print additional state for the RCU grace-period kthreads in cases where RCU seems reluctant to start a new grace period. Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- include/linux/rcutiny.h | 4 ++++ include/linux/rcutree.h | 1 + kernel/rcu/rcutorture.c | 1 + kernel/rcu/tree.c | 17 +++++++++++++++++ kernel/rcu/tree.h | 8 +++++++- 5 files changed, 30 insertions(+), 1 deletion(-) (limited to 'kernel/rcu/tree.h') diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 425c659d54e5..d40a6a451330 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -119,6 +119,10 @@ static inline void rcu_sched_force_quiescent_state(void) { } +static inline void show_rcu_gp_kthreads(void) +{ +} + static inline void rcu_cpu_stall_reset(void) { } diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index a59ca05fd4e3..3e2f5d432743 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -84,6 +84,7 @@ extern unsigned long rcutorture_vernum; long rcu_batches_completed(void); long rcu_batches_completed_bh(void); long rcu_batches_completed_sched(void); +void show_rcu_gp_kthreads(void); void rcu_force_quiescent_state(void); void rcu_bh_force_quiescent_state(void); diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index 9decce0f110c..37ae5e1d4a1d 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -1034,6 +1034,7 @@ rcu_torture_printk(char *page) "??? Writer stall state %d g%lu c%lu f%#x\n", rcu_torture_writer_state, gpnum, completed, flags); + show_rcu_gp_kthreads(); rcutorture_trace_dump(); } rtcv_snap = rcu_torture_current_version; diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 3d15b5a82ae8..93e64381aa2a 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -279,6 +279,21 @@ void rcu_bh_force_quiescent_state(void) } EXPORT_SYMBOL_GPL(rcu_bh_force_quiescent_state); +/* + * Show the state of the grace-period kthreads. + */ +void show_rcu_gp_kthreads(void) +{ + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) { + pr_info("%s: wait state: %d ->state: %#lx\n", + rsp->name, rsp->gp_state, rsp->gp_kthread->state); + /* sched_show_task(rsp->gp_kthread); */ + } +} +EXPORT_SYMBOL_GPL(show_rcu_gp_kthreads); + /* * Record the number of times rcutorture tests have been initiated and * terminated. This information allows the debugfs tracing stats to be @@ -1626,6 +1641,7 @@ static int __noreturn rcu_gp_kthread(void *arg) trace_rcu_grace_period(rsp->name, ACCESS_ONCE(rsp->gpnum), TPS("reqwait")); + rsp->gp_state = RCU_GP_WAIT_GPS; wait_event_interruptible(rsp->gp_wq, ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_INIT); @@ -1653,6 +1669,7 @@ static int __noreturn rcu_gp_kthread(void *arg) trace_rcu_grace_period(rsp->name, ACCESS_ONCE(rsp->gpnum), TPS("fqswait")); + rsp->gp_state = RCU_GP_WAIT_FQS; ret = wait_event_interruptible_timeout(rsp->gp_wq, ((gf = ACCESS_ONCE(rsp->gp_flags)) & RCU_GP_FLAG_FQS) || diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 75dc3c39a02a..c2fd1e722879 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -406,7 +406,8 @@ struct rcu_state { unsigned long completed; /* # of last completed gp. */ struct task_struct *gp_kthread; /* Task for grace periods. */ wait_queue_head_t gp_wq; /* Where GP task waits. */ - int gp_flags; /* Commands for GP task. */ + short gp_flags; /* Commands for GP task. */ + short gp_state; /* GP kthread sleep state. */ /* End of fields guarded by root rcu_node's lock. */ @@ -469,6 +470,11 @@ struct rcu_state { #define RCU_GP_FLAG_INIT 0x1 /* Need grace-period initialization. */ #define RCU_GP_FLAG_FQS 0x2 /* Need grace-period quiescent-state forcing. */ +/* Values for rcu_state structure's gp_flags field. */ +#define RCU_GP_WAIT_INIT 0 /* Initial state. */ +#define RCU_GP_WAIT_GPS 1 /* Wait for grace-period start. */ +#define RCU_GP_WAIT_FQS 2 /* Wait for force-quiescent-state time. */ + extern struct list_head rcu_struct_flavors; /* Sequence through rcu_state structures for each RCU flavor. */ -- cgit v1.2.3