From f4ecea309d3e17ba5e90082308125ad23bd5701b Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 29 Jul 2015 17:28:11 -0700 Subject: rcu: Use rsp->expedited_wq instead of sync_rcu_preempt_exp_wq Now that there is an ->expedited_wq waitqueue in each rcu_state structure, there is no need for the sync_rcu_preempt_exp_wq global variable. This commit therefore substitutes ->expedited_wq for sync_rcu_preempt_exp_wq. It also initializes ->expedited_wq only once at boot instead of at the start of each expedited grace period. Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 2 +- kernel/rcu/tree_plugin.h | 6 ++---- 2 files changed, 3 insertions(+), 5 deletions(-) (limited to 'kernel/rcu') diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 775d36cc0050..53d66ebb4811 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -3556,7 +3556,6 @@ void synchronize_sched_expedited(void) rcu_exp_gp_seq_start(rsp); /* Stop each CPU that is online, non-idle, and not us. */ - init_waitqueue_head(&rsp->expedited_wq); atomic_set(&rsp->expedited_need_qs, 1); /* Extra count avoids race. */ for_each_online_cpu(cpu) { struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); @@ -4179,6 +4178,7 @@ static void __init rcu_init_one(struct rcu_state *rsp, } init_waitqueue_head(&rsp->gp_wq); + init_waitqueue_head(&rsp->expedited_wq); rnp = rsp->level[rcu_num_lvls - 1]; for_each_possible_cpu(i) { while (i > rnp->grphi) diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index b2bf3963a0ae..72df006de798 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -535,8 +535,6 @@ void synchronize_rcu(void) } EXPORT_SYMBOL_GPL(synchronize_rcu); -static DECLARE_WAIT_QUEUE_HEAD(sync_rcu_preempt_exp_wq); - /* * Return non-zero if there are any tasks in RCU read-side critical * sections blocking the current preemptible-RCU expedited grace period. @@ -590,7 +588,7 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, raw_spin_unlock_irqrestore(&rnp->lock, flags); if (wake) { smp_mb(); /* EGP done before wake_up(). */ - wake_up(&sync_rcu_preempt_exp_wq); + wake_up(&rsp->expedited_wq); } break; } @@ -729,7 +727,7 @@ void synchronize_rcu_expedited(void) /* Wait for snapshotted ->blkd_tasks lists to drain. */ rnp = rcu_get_root(rsp); - wait_event(sync_rcu_preempt_exp_wq, + wait_event(rsp->expedited_wq, sync_rcu_preempt_exp_done(rnp)); /* Clean up and exit. */ -- cgit v1.2.3 From 7922cd0e562cb2b8da2c8a0afda2e1c9bb4a94e2 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 31 Jul 2015 13:34:32 -0700 Subject: rcu: Move rcu_report_exp_rnp() to allow consolidation This is a nearly pure code-movement commit, moving rcu_report_exp_rnp(), sync_rcu_preempt_exp_done(), and rcu_preempted_readers_exp() so that later commits can make synchronize_sched_expedited() use them. The non-code-movement portion of this commit tags rcu_report_exp_rnp() as __maybe_unused to avoid build errors when CONFIG_PREEMPT=n. Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 66 ++++++++++++++++++++++++++++++++++++++++++++++++ kernel/rcu/tree_plugin.h | 66 ------------------------------------------------ 2 files changed, 66 insertions(+), 66 deletions(-) (limited to 'kernel/rcu') diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 53d66ebb4811..59af27d8bc6a 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -3379,6 +3379,72 @@ static bool rcu_exp_gp_seq_done(struct rcu_state *rsp, unsigned long s) return rcu_seq_done(&rsp->expedited_sequence, s); } +/* + * Return non-zero if there are any tasks in RCU read-side critical + * sections blocking the current preemptible-RCU expedited grace period. + * If there is no preemptible-RCU expedited grace period currently in + * progress, returns zero unconditionally. + */ +static int rcu_preempted_readers_exp(struct rcu_node *rnp) +{ + return rnp->exp_tasks != NULL; +} + +/* + * return non-zero if there is no RCU expedited grace period in progress + * for the specified rcu_node structure, in other words, if all CPUs and + * tasks covered by the specified rcu_node structure have done their bit + * for the current expedited grace period. Works only for preemptible + * RCU -- other RCU implementation use other means. + * + * Caller must hold the root rcu_node's exp_funnel_mutex. + */ +static int sync_rcu_preempt_exp_done(struct rcu_node *rnp) +{ + return !rcu_preempted_readers_exp(rnp) && + READ_ONCE(rnp->expmask) == 0; +} + +/* + * Report the exit from RCU read-side critical section for the last task + * that queued itself during or before the current expedited preemptible-RCU + * grace period. This event is reported either to the rcu_node structure on + * which the task was queued or to one of that rcu_node structure's ancestors, + * recursively up the tree. (Calm down, calm down, we do the recursion + * iteratively!) + * + * Caller must hold the root rcu_node's exp_funnel_mutex. + */ +static void __maybe_unused rcu_report_exp_rnp(struct rcu_state *rsp, + struct rcu_node *rnp, bool wake) +{ + unsigned long flags; + unsigned long mask; + + raw_spin_lock_irqsave(&rnp->lock, flags); + smp_mb__after_unlock_lock(); + for (;;) { + if (!sync_rcu_preempt_exp_done(rnp)) { + raw_spin_unlock_irqrestore(&rnp->lock, flags); + break; + } + if (rnp->parent == NULL) { + raw_spin_unlock_irqrestore(&rnp->lock, flags); + if (wake) { + smp_mb(); /* EGP done before wake_up(). */ + wake_up(&rsp->expedited_wq); + } + break; + } + mask = rnp->grpmask; + raw_spin_unlock(&rnp->lock); /* irqs remain disabled */ + rnp = rnp->parent; + raw_spin_lock(&rnp->lock); /* irqs already disabled */ + smp_mb__after_unlock_lock(); + rnp->expmask &= ~mask; + } +} + /* Common code for synchronize_{rcu,sched}_expedited() work-done checking. */ static bool sync_exp_work_done(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp, diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 72df006de798..e73be8539978 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -535,72 +535,6 @@ void synchronize_rcu(void) } EXPORT_SYMBOL_GPL(synchronize_rcu); -/* - * Return non-zero if there are any tasks in RCU read-side critical - * sections blocking the current preemptible-RCU expedited grace period. - * If there is no preemptible-RCU expedited grace period currently in - * progress, returns zero unconditionally. - */ -static int rcu_preempted_readers_exp(struct rcu_node *rnp) -{ - return rnp->exp_tasks != NULL; -} - -/* - * return non-zero if there is no RCU expedited grace period in progress - * for the specified rcu_node structure, in other words, if all CPUs and - * tasks covered by the specified rcu_node structure have done their bit - * for the current expedited grace period. Works only for preemptible - * RCU -- other RCU implementation use other means. - * - * Caller must hold the root rcu_node's exp_funnel_mutex. - */ -static int sync_rcu_preempt_exp_done(struct rcu_node *rnp) -{ - return !rcu_preempted_readers_exp(rnp) && - READ_ONCE(rnp->expmask) == 0; -} - -/* - * Report the exit from RCU read-side critical section for the last task - * that queued itself during or before the current expedited preemptible-RCU - * grace period. This event is reported either to the rcu_node structure on - * which the task was queued or to one of that rcu_node structure's ancestors, - * recursively up the tree. (Calm down, calm down, we do the recursion - * iteratively!) - * - * Caller must hold the root rcu_node's exp_funnel_mutex. - */ -static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, - bool wake) -{ - unsigned long flags; - unsigned long mask; - - raw_spin_lock_irqsave(&rnp->lock, flags); - smp_mb__after_unlock_lock(); - for (;;) { - if (!sync_rcu_preempt_exp_done(rnp)) { - raw_spin_unlock_irqrestore(&rnp->lock, flags); - break; - } - if (rnp->parent == NULL) { - raw_spin_unlock_irqrestore(&rnp->lock, flags); - if (wake) { - smp_mb(); /* EGP done before wake_up(). */ - wake_up(&rsp->expedited_wq); - } - break; - } - mask = rnp->grpmask; - raw_spin_unlock(&rnp->lock); /* irqs remain disabled */ - rnp = rnp->parent; - raw_spin_lock(&rnp->lock); /* irqs already disabled */ - smp_mb__after_unlock_lock(); - rnp->expmask &= ~mask; - } -} - /* * Snapshot the tasks blocking the newly started preemptible-RCU expedited * grace period for the specified rcu_node structure, phase 1. If there -- cgit v1.2.3 From b9585e940a0d78770cda8f9aebf81b17b4d19e6d Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 31 Jul 2015 16:04:45 -0700 Subject: rcu: Consolidate tree setup for synchronize_rcu_expedited() This commit replaces sync_rcu_preempt_exp_init1(() and sync_rcu_preempt_exp_init2() with sync_exp_reset_tree_hotplug() and sync_exp_reset_tree(), which will also be used by synchronize_sched_expedited(), and sync_rcu_exp_select_nodes(), which contains code specific to synchronize_rcu_expedited(). Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 86 ++++++++++++++++++++++++++++++++++++++- kernel/rcu/tree.h | 17 +++++--- kernel/rcu/tree_plugin.h | 102 +++++++++-------------------------------------- 3 files changed, 115 insertions(+), 90 deletions(-) (limited to 'kernel/rcu') diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 59af27d8bc6a..8526896afea7 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -3379,6 +3379,87 @@ static bool rcu_exp_gp_seq_done(struct rcu_state *rsp, unsigned long s) return rcu_seq_done(&rsp->expedited_sequence, s); } +/* + * Reset the ->expmaskinit values in the rcu_node tree to reflect any + * recent CPU-online activity. Note that these masks are not cleared + * when CPUs go offline, so they reflect the union of all CPUs that have + * ever been online. This means that this function normally takes its + * no-work-to-do fastpath. + */ +static void sync_exp_reset_tree_hotplug(struct rcu_state *rsp) +{ + bool done; + unsigned long flags; + unsigned long mask; + unsigned long oldmask; + int ncpus = READ_ONCE(rsp->ncpus); + struct rcu_node *rnp; + struct rcu_node *rnp_up; + + /* If no new CPUs onlined since last time, nothing to do. */ + if (likely(ncpus == rsp->ncpus_snap)) + return; + rsp->ncpus_snap = ncpus; + + /* + * Each pass through the following loop propagates newly onlined + * CPUs for the current rcu_node structure up the rcu_node tree. + */ + rcu_for_each_leaf_node(rsp, rnp) { + raw_spin_lock_irqsave(&rnp->lock, flags); + smp_mb__after_unlock_lock(); + if (rnp->expmaskinit == rnp->expmaskinitnext) { + raw_spin_unlock_irqrestore(&rnp->lock, flags); + continue; /* No new CPUs, nothing to do. */ + } + + /* Update this node's mask, track old value for propagation. */ + oldmask = rnp->expmaskinit; + rnp->expmaskinit = rnp->expmaskinitnext; + raw_spin_unlock_irqrestore(&rnp->lock, flags); + + /* If was already nonzero, nothing to propagate. */ + if (oldmask) + continue; + + /* Propagate the new CPU up the tree. */ + mask = rnp->grpmask; + rnp_up = rnp->parent; + done = false; + while (rnp_up) { + raw_spin_lock_irqsave(&rnp_up->lock, flags); + smp_mb__after_unlock_lock(); + if (rnp_up->expmaskinit) + done = true; + rnp_up->expmaskinit |= mask; + raw_spin_unlock_irqrestore(&rnp_up->lock, flags); + if (done) + break; + mask = rnp_up->grpmask; + rnp_up = rnp_up->parent; + } + } +} + +/* + * Reset the ->expmask values in the rcu_node tree in preparation for + * a new expedited grace period. + */ +static void __maybe_unused sync_exp_reset_tree(struct rcu_state *rsp) +{ + unsigned long flags; + struct rcu_node *rnp; + + sync_exp_reset_tree_hotplug(rsp); + rcu_for_each_node_breadth_first(rsp, rnp) { + raw_spin_lock_irqsave(&rnp->lock, flags); + smp_mb__after_unlock_lock(); + WARN_ON_ONCE(rnp->expmask); + rnp->expmask = rnp->expmaskinit; + raw_spin_unlock_irqrestore(&rnp->lock, flags); + } +} + /* * Return non-zero if there are any tasks in RCU read-side critical * sections blocking the current preemptible-RCU expedited grace period. @@ -3971,7 +4052,6 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp) /* 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->qlen_last_fqs_check = 0; rdp->n_force_qs_snap = rsp->n_force_qs; rdp->blimit = blimit; @@ -3993,6 +4073,10 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp) raw_spin_lock(&rnp->lock); /* irqs already disabled. */ smp_mb__after_unlock_lock(); rnp->qsmaskinitnext |= mask; + rnp->expmaskinitnext |= mask; + if (!rdp->beenonline) + WRITE_ONCE(rsp->ncpus, READ_ONCE(rsp->ncpus) + 1); + rdp->beenonline = true; /* We have now been online. */ rdp->gpnum = rnp->completed; /* Make CPU later note any new GP. */ rdp->completed = rnp->completed; rdp->passed_quiesce = false; diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 2e991f8361e4..a57f25ecca58 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -171,16 +171,21 @@ struct rcu_node { /* an rcu_data structure, otherwise, each */ /* bit corresponds to a child rcu_node */ /* structure. */ - unsigned long expmask; /* Groups that have ->blkd_tasks */ - /* elements that need to drain to allow the */ - /* current expedited grace period to */ - /* complete (only for PREEMPT_RCU). */ unsigned long qsmaskinit; - /* Per-GP initial value for qsmask & expmask. */ + /* Per-GP initial value for qsmask. */ /* Initialized from ->qsmaskinitnext at the */ /* beginning of each grace period. */ unsigned long qsmaskinitnext; /* Online CPUs for next grace period. */ + unsigned long expmask; /* CPUs or groups that need to check in */ + /* to allow the current expedited GP */ + /* to complete. */ + unsigned long expmaskinit; + /* Per-GP initial values for expmask. */ + /* Initialized from ->expmaskinitnext at the */ + /* beginning of each expedited GP. */ + unsigned long expmaskinitnext; + /* Online CPUs for next expedited GP. */ 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. */ @@ -466,6 +471,7 @@ struct rcu_state { struct rcu_data __percpu *rda; /* pointer of percu rcu_data. */ void (*call)(struct rcu_head *head, /* call_rcu() flavor. */ void (*func)(struct rcu_head *head)); + int ncpus; /* # CPUs seen so far. */ /* The following fields are guarded by the root rcu_node's lock. */ @@ -508,6 +514,7 @@ struct rcu_state { atomic_long_t expedited_normal; /* # fallbacks to normal. */ atomic_t expedited_need_qs; /* # CPUs left to check in. */ wait_queue_head_t expedited_wq; /* Wait for check-ins. */ + int ncpus_snap; /* # CPUs seen last time. */ unsigned long jiffies_force_qs; /* Time at which to invoke */ /* force_quiescent_state(). */ diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index e73be8539978..62d05413b7ba 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -536,86 +536,28 @@ void synchronize_rcu(void) EXPORT_SYMBOL_GPL(synchronize_rcu); /* - * Snapshot the tasks blocking the newly started preemptible-RCU expedited - * grace period for the specified rcu_node structure, phase 1. If there - * are such tasks, set the ->expmask bits up the rcu_node tree and also - * set the ->expmask bits on the leaf rcu_node structures to tell phase 2 - * that work is needed here. - * - * Caller must hold the root rcu_node's exp_funnel_mutex. + * Select the nodes that the upcoming expedited grace period needs + * to wait for. */ -static void -sync_rcu_preempt_exp_init1(struct rcu_state *rsp, struct rcu_node *rnp) +static void sync_rcu_exp_select_nodes(struct rcu_state *rsp) { unsigned long flags; - unsigned long mask; - struct rcu_node *rnp_up; + struct rcu_node *rnp; - raw_spin_lock_irqsave(&rnp->lock, flags); - smp_mb__after_unlock_lock(); - WARN_ON_ONCE(rnp->expmask); - WARN_ON_ONCE(rnp->exp_tasks); - if (!rcu_preempt_has_tasks(rnp)) { - /* No blocked tasks, nothing to do. */ - raw_spin_unlock_irqrestore(&rnp->lock, flags); - return; - } - /* Call for Phase 2 and propagate ->expmask bits up the tree. */ - rnp->expmask = 1; - rnp_up = rnp; - while (rnp_up->parent) { - mask = rnp_up->grpmask; - rnp_up = rnp_up->parent; - if (rnp_up->expmask & mask) - break; - raw_spin_lock(&rnp_up->lock); /* irqs already off */ + sync_exp_reset_tree(rsp); + rcu_for_each_leaf_node(rsp, rnp) { + raw_spin_lock_irqsave(&rnp->lock, flags); smp_mb__after_unlock_lock(); - rnp_up->expmask |= mask; - raw_spin_unlock(&rnp_up->lock); /* irqs still off */ - } - raw_spin_unlock_irqrestore(&rnp->lock, flags); -} - -/* - * Snapshot the tasks blocking the newly started preemptible-RCU expedited - * grace period for the specified rcu_node structure, phase 2. If the - * leaf rcu_node structure has its ->expmask field set, check for tasks. - * If there are some, clear ->expmask and set ->exp_tasks accordingly, - * then initiate RCU priority boosting. Otherwise, clear ->expmask and - * invoke rcu_report_exp_rnp() to clear out the upper-level ->expmask bits, - * enabling rcu_read_unlock_special() to do the bit-clearing. - * - * Caller must hold the root rcu_node's exp_funnel_mutex. - */ -static void -sync_rcu_preempt_exp_init2(struct rcu_state *rsp, struct rcu_node *rnp) -{ - unsigned long flags; - - raw_spin_lock_irqsave(&rnp->lock, flags); - smp_mb__after_unlock_lock(); - if (!rnp->expmask) { - /* Phase 1 didn't do anything, so Phase 2 doesn't either. */ - raw_spin_unlock_irqrestore(&rnp->lock, flags); - return; - } - - /* Phase 1 is over. */ - rnp->expmask = 0; - - /* - * If there are still blocked tasks, set up ->exp_tasks so that - * rcu_read_unlock_special() will wake us and then boost them. - */ - if (rcu_preempt_has_tasks(rnp)) { - rnp->exp_tasks = rnp->blkd_tasks.next; - rcu_initiate_boost(rnp, flags); /* releases rnp->lock */ - return; + rnp->expmask = 0; /* No per-CPU component yet. */ + if (!rcu_preempt_has_tasks(rnp)) { + /* FIXME: Want __rcu_report_exp_rnp() here. */ + raw_spin_unlock_irqrestore(&rnp->lock, flags); + } else { + rnp->exp_tasks = rnp->blkd_tasks.next; + rcu_initiate_boost(rnp, flags); + } + rcu_report_exp_rnp(rsp, rnp, false); } - - /* No longer any blocked tasks, so undo bit setting. */ - raw_spin_unlock_irqrestore(&rnp->lock, flags); - rcu_report_exp_rnp(rsp, rnp, false); } /** @@ -648,16 +590,8 @@ void synchronize_rcu_expedited(void) /* force all RCU readers onto ->blkd_tasks lists. */ synchronize_sched_expedited(); - /* - * Snapshot current state of ->blkd_tasks lists into ->expmask. - * Phase 1 sets bits and phase 2 permits rcu_read_unlock_special() - * to start clearing them. Doing this in one phase leads to - * strange races between setting and clearing bits, so just say "no"! - */ - rcu_for_each_leaf_node(rsp, rnp) - sync_rcu_preempt_exp_init1(rsp, rnp); - rcu_for_each_leaf_node(rsp, rnp) - sync_rcu_preempt_exp_init2(rsp, rnp); + /* Initialize the rcu_node tree in preparation for the wait. */ + sync_rcu_exp_select_nodes(rsp); /* Wait for snapshotted ->blkd_tasks lists to drain. */ rnp = rcu_get_root(rsp); -- cgit v1.2.3 From 8203d6d0ee784cfb2ebf89053f7fe399abc867d7 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sun, 2 Aug 2015 13:53:17 -0700 Subject: rcu: Use single-stage IPI algorithm for RCU expedited grace period The current preemptible-RCU expedited grace-period algorithm invokes synchronize_sched_expedited() to enqueue all tasks currently running in a preemptible-RCU read-side critical section, then waits for all the ->blkd_tasks lists to drain. This works, but results in both an IPI and a double context switch even on CPUs that do not happen to be running in a preemptible RCU read-side critical section. This commit implements a new algorithm that causes less OS jitter. This new algorithm IPIs all online CPUs that are not idle (from an RCU perspective), but refrains from self-IPIs. If a CPU receiving this IPI is not in a preemptible RCU read-side critical section (or is just now exiting one), it pushes quiescence up the rcu_node tree, otherwise, it sets a flag that will be handled by the upcoming outermost rcu_read_unlock(), which will then push quiescence up the tree. The expedited grace period must of course wait on any pre-existing blocked readers, and newly blocked readers must be queued carefully based on the state of both the normal and the expedited grace periods. This new queueing approach also avoids the need to update boost state, courtesy of the fact that blocked tasks are no longer ever migrated to the root rcu_node structure. Signed-off-by: Paul E. McKenney --- include/linux/sched.h | 10 +- kernel/rcu/tree.c | 75 ++++++++---- kernel/rcu/tree_plugin.h | 296 +++++++++++++++++++++++++++++++++++++++-------- 3 files changed, 311 insertions(+), 70 deletions(-) (limited to 'kernel/rcu') diff --git a/include/linux/sched.h b/include/linux/sched.h index a4ab9daa387c..7fa8c4d372e7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1330,10 +1330,12 @@ struct sched_dl_entity { union rcu_special { struct { - bool blocked; - bool need_qs; - } b; - short s; + u8 blocked; + u8 need_qs; + u8 exp_need_qs; + u8 pad; /* Otherwise the compiler can store garbage here. */ + } b; /* Bits. */ + u32 s; /* Set of bits. */ }; struct rcu_node; diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 8526896afea7..6e92bf4337bd 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -3461,18 +3461,7 @@ static void __maybe_unused sync_exp_reset_tree(struct rcu_state *rsp) } /* - * Return non-zero if there are any tasks in RCU read-side critical - * sections blocking the current preemptible-RCU expedited grace period. - * If there is no preemptible-RCU expedited grace period currently in - * progress, returns zero unconditionally. - */ -static int rcu_preempted_readers_exp(struct rcu_node *rnp) -{ - return rnp->exp_tasks != NULL; -} - -/* - * return non-zero if there is no RCU expedited grace period in progress + * Return non-zero if there is no RCU expedited grace period in progress * for the specified rcu_node structure, in other words, if all CPUs and * tasks covered by the specified rcu_node structure have done their bit * for the current expedited grace period. Works only for preemptible @@ -3482,7 +3471,7 @@ static int rcu_preempted_readers_exp(struct rcu_node *rnp) */ static int sync_rcu_preempt_exp_done(struct rcu_node *rnp) { - return !rcu_preempted_readers_exp(rnp) && + return rnp->exp_tasks == NULL && READ_ONCE(rnp->expmask) == 0; } @@ -3494,19 +3483,21 @@ static int sync_rcu_preempt_exp_done(struct rcu_node *rnp) * recursively up the tree. (Calm down, calm down, we do the recursion * iteratively!) * - * Caller must hold the root rcu_node's exp_funnel_mutex. + * Caller must hold the root rcu_node's exp_funnel_mutex and the + * specified rcu_node structure's ->lock. */ -static void __maybe_unused rcu_report_exp_rnp(struct rcu_state *rsp, - struct rcu_node *rnp, bool wake) +static void __rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, + bool wake, unsigned long flags) + __releases(rnp->lock) { - unsigned long flags; unsigned long mask; - raw_spin_lock_irqsave(&rnp->lock, flags); - smp_mb__after_unlock_lock(); for (;;) { if (!sync_rcu_preempt_exp_done(rnp)) { - raw_spin_unlock_irqrestore(&rnp->lock, flags); + if (!rnp->expmask) + rcu_initiate_boost(rnp, flags); + else + raw_spin_unlock_irqrestore(&rnp->lock, flags); break; } if (rnp->parent == NULL) { @@ -3522,10 +3513,54 @@ static void __maybe_unused rcu_report_exp_rnp(struct rcu_state *rsp, rnp = rnp->parent; raw_spin_lock(&rnp->lock); /* irqs already disabled */ smp_mb__after_unlock_lock(); + WARN_ON_ONCE(!(rnp->expmask & mask)); rnp->expmask &= ~mask; } } +/* + * Report expedited quiescent state for specified node. This is a + * lock-acquisition wrapper function for __rcu_report_exp_rnp(). + * + * Caller must hold the root rcu_node's exp_funnel_mutex. + */ +static void __maybe_unused rcu_report_exp_rnp(struct rcu_state *rsp, + struct rcu_node *rnp, bool wake) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&rnp->lock, flags); + smp_mb__after_unlock_lock(); + __rcu_report_exp_rnp(rsp, rnp, wake, flags); +} + +/* + * Report expedited quiescent state for multiple CPUs, all covered by the + * specified leaf rcu_node structure. Caller must hold the root + * rcu_node's exp_funnel_mutex. + */ +static void rcu_report_exp_cpu_mult(struct rcu_state *rsp, struct rcu_node *rnp, + unsigned long mask, bool wake) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&rnp->lock, flags); + smp_mb__after_unlock_lock(); + WARN_ON_ONCE((rnp->expmask & mask) != mask); + rnp->expmask &= ~mask; + __rcu_report_exp_rnp(rsp, rnp, wake, flags); /* Releases rnp->lock. */ +} + +/* + * Report expedited quiescent state for specified rcu_data (CPU). + * Caller must hold the root rcu_node's exp_funnel_mutex. + */ +static void __maybe_unused rcu_report_exp_rdp(struct rcu_state *rsp, + struct rcu_data *rdp, bool wake) +{ + rcu_report_exp_cpu_mult(rsp, rdp->mynode, rdp->grpmask, wake); +} + /* Common code for synchronize_{rcu,sched}_expedited() work-done checking. */ static bool sync_exp_work_done(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp, diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 62d05413b7ba..6f7500f9387c 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -101,7 +101,6 @@ RCU_STATE_INITIALIZER(rcu_preempt, 'p', call_rcu); static struct rcu_state *const rcu_state_p = &rcu_preempt_state; static struct rcu_data __percpu *const rcu_data_p = &rcu_preempt_data; -static int rcu_preempted_readers_exp(struct rcu_node *rnp); static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, bool wake); @@ -114,6 +113,147 @@ static void __init rcu_bootup_announce(void) rcu_bootup_announce_oddness(); } +/* Flags for rcu_preempt_ctxt_queue() decision table. */ +#define RCU_GP_TASKS 0x8 +#define RCU_EXP_TASKS 0x4 +#define RCU_GP_BLKD 0x2 +#define RCU_EXP_BLKD 0x1 + +/* + * Queues a task preempted within an RCU-preempt read-side critical + * section into the appropriate location within the ->blkd_tasks list, + * depending on the states of any ongoing normal and expedited grace + * periods. The ->gp_tasks pointer indicates which element the normal + * grace period is waiting on (NULL if none), and the ->exp_tasks pointer + * indicates which element the expedited grace period is waiting on (again, + * NULL if none). If a grace period is waiting on a given element in the + * ->blkd_tasks list, it also waits on all subsequent elements. Thus, + * adding a task to the tail of the list blocks any grace period that is + * already waiting on one of the elements. In contrast, adding a task + * to the head of the list won't block any grace period that is already + * waiting on one of the elements. + * + * This queuing is imprecise, and can sometimes make an ongoing grace + * period wait for a task that is not strictly speaking blocking it. + * Given the choice, we needlessly block a normal grace period rather than + * blocking an expedited grace period. + * + * Note that an endless sequence of expedited grace periods still cannot + * indefinitely postpone a normal grace period. Eventually, all of the + * fixed number of preempted tasks blocking the normal grace period that are + * not also blocking the expedited grace period will resume and complete + * their RCU read-side critical sections. At that point, the ->gp_tasks + * pointer will equal the ->exp_tasks pointer, at which point the end of + * the corresponding expedited grace period will also be the end of the + * normal grace period. + */ +static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp, + unsigned long flags) __releases(rnp->lock) +{ + int blkd_state = (rnp->gp_tasks ? RCU_GP_TASKS : 0) + + (rnp->exp_tasks ? RCU_EXP_TASKS : 0) + + (rnp->qsmask & rdp->grpmask ? RCU_GP_BLKD : 0) + + (rnp->expmask & rdp->grpmask ? RCU_EXP_BLKD : 0); + struct task_struct *t = current; + + /* + * Decide where to queue the newly blocked task. In theory, + * this could be an if-statement. In practice, when I tried + * that, it was quite messy. + */ + switch (blkd_state) { + case 0: + case RCU_EXP_TASKS: + case RCU_EXP_TASKS + RCU_GP_BLKD: + case RCU_GP_TASKS: + case RCU_GP_TASKS + RCU_EXP_TASKS: + + /* + * Blocking neither GP, or first task blocking the normal + * GP but not blocking the already-waiting expedited GP. + * Queue at the head of the list to avoid unnecessarily + * blocking the already-waiting GPs. + */ + list_add(&t->rcu_node_entry, &rnp->blkd_tasks); + break; + + case RCU_EXP_BLKD: + case RCU_GP_BLKD: + case RCU_GP_BLKD + RCU_EXP_BLKD: + case RCU_GP_TASKS + RCU_EXP_BLKD: + case RCU_GP_TASKS + RCU_GP_BLKD + RCU_EXP_BLKD: + case RCU_GP_TASKS + RCU_EXP_TASKS + RCU_GP_BLKD + RCU_EXP_BLKD: + + /* + * First task arriving that blocks either GP, or first task + * arriving that blocks the expedited GP (with the normal + * GP already waiting), or a task arriving that blocks + * both GPs with both GPs already waiting. Queue at the + * tail of the list to avoid any GP waiting on any of the + * already queued tasks that are not blocking it. + */ + list_add_tail(&t->rcu_node_entry, &rnp->blkd_tasks); + break; + + case RCU_EXP_TASKS + RCU_EXP_BLKD: + case RCU_EXP_TASKS + RCU_GP_BLKD + RCU_EXP_BLKD: + case RCU_GP_TASKS + RCU_EXP_TASKS + RCU_EXP_BLKD: + + /* + * Second or subsequent task blocking the expedited GP. + * The task either does not block the normal GP, or is the + * first task blocking the normal GP. Queue just after + * the first task blocking the expedited GP. + */ + list_add(&t->rcu_node_entry, rnp->exp_tasks); + break; + + case RCU_GP_TASKS + RCU_GP_BLKD: + case RCU_GP_TASKS + RCU_EXP_TASKS + RCU_GP_BLKD: + + /* + * Second or subsequent task blocking the normal GP. + * The task does not block the expedited GP. Queue just + * after the first task blocking the normal GP. + */ + list_add(&t->rcu_node_entry, rnp->gp_tasks); + break; + + default: + + /* Yet another exercise in excessive paranoia. */ + WARN_ON_ONCE(1); + break; + } + + /* + * We have now queued the task. If it was the first one to + * block either grace period, update the ->gp_tasks and/or + * ->exp_tasks pointers, respectively, to reference the newly + * blocked tasks. + */ + if (!rnp->gp_tasks && (blkd_state & RCU_GP_BLKD)) + rnp->gp_tasks = &t->rcu_node_entry; + if (!rnp->exp_tasks && (blkd_state & RCU_EXP_BLKD)) + rnp->exp_tasks = &t->rcu_node_entry; + raw_spin_unlock(&rnp->lock); + + /* + * Report the quiescent state for the expedited GP. This expedited + * GP should not be able to end until we report, so there should be + * no need to check for a subsequent expedited GP. (Though we are + * still in a quiescent state in any case.) + */ + if (blkd_state & RCU_EXP_BLKD && + t->rcu_read_unlock_special.b.exp_need_qs) { + t->rcu_read_unlock_special.b.exp_need_qs = false; + rcu_report_exp_rdp(rdp->rsp, rdp, true); + } else { + WARN_ON_ONCE(t->rcu_read_unlock_special.b.exp_need_qs); + } + local_irq_restore(flags); +} + /* * Record a preemptible-RCU quiescent state for the specified CPU. Note * that this just means that the task currently running on the CPU is @@ -167,42 +307,18 @@ static void rcu_preempt_note_context_switch(void) t->rcu_blocked_node = rnp; /* - * If this CPU has already checked in, then this task - * will hold up the next grace period rather than the - * current grace period. Queue the task accordingly. - * If the task is queued for the current grace period - * (i.e., this CPU has not yet passed through a quiescent - * state for the current grace period), then as long - * as that task remains queued, the current grace period - * cannot end. Note that there is some uncertainty as - * to exactly when the current grace period started. - * We take a conservative approach, which can result - * in unnecessarily waiting on tasks that started very - * slightly after the current grace period began. C'est - * la vie!!! - * - * But first, note that the current CPU must still be - * on line! + * Verify the CPU's sanity, trace the preemption, and + * then queue the task as required based on the states + * of any ongoing and expedited grace periods. */ WARN_ON_ONCE((rdp->grpmask & rcu_rnp_online_cpus(rnp)) == 0); WARN_ON_ONCE(!list_empty(&t->rcu_node_entry)); - if ((rnp->qsmask & rdp->grpmask) && rnp->gp_tasks != NULL) { - list_add(&t->rcu_node_entry, rnp->gp_tasks->prev); - rnp->gp_tasks = &t->rcu_node_entry; - if (IS_ENABLED(CONFIG_RCU_BOOST) && - rnp->boost_tasks != NULL) - rnp->boost_tasks = rnp->gp_tasks; - } else { - list_add(&t->rcu_node_entry, &rnp->blkd_tasks); - if (rnp->qsmask & rdp->grpmask) - rnp->gp_tasks = &t->rcu_node_entry; - } trace_rcu_preempt_task(rdp->rsp->name, t->pid, (rnp->qsmask & rdp->grpmask) ? rnp->gpnum : rnp->gpnum + 1); - raw_spin_unlock_irqrestore(&rnp->lock, flags); + rcu_preempt_ctxt_queue(rnp, rdp, flags); } else if (t->rcu_read_lock_nesting < 0 && t->rcu_read_unlock_special.s) { @@ -272,6 +388,7 @@ void rcu_read_unlock_special(struct task_struct *t) unsigned long flags; struct list_head *np; bool drop_boost_mutex = false; + struct rcu_data *rdp; struct rcu_node *rnp; union rcu_special special; @@ -282,8 +399,8 @@ void rcu_read_unlock_special(struct task_struct *t) local_irq_save(flags); /* - * If RCU core is waiting for this CPU to exit critical section, - * let it know that we have done so. Because irqs are disabled, + * If RCU core is waiting for this CPU to exit its critical section, + * report the fact that it has exited. Because irqs are disabled, * t->rcu_read_unlock_special cannot change. */ special = t->rcu_read_unlock_special; @@ -296,13 +413,32 @@ void rcu_read_unlock_special(struct task_struct *t) } } + /* + * Respond to a request for an expedited grace period, but only if + * we were not preempted, meaning that we were running on the same + * CPU throughout. If we were preempted, the exp_need_qs flag + * would have been cleared at the time of the first preemption, + * and the quiescent state would be reported when we were dequeued. + */ + if (special.b.exp_need_qs) { + WARN_ON_ONCE(special.b.blocked); + t->rcu_read_unlock_special.b.exp_need_qs = false; + rdp = this_cpu_ptr(rcu_state_p->rda); + rcu_report_exp_rdp(rcu_state_p, rdp, true); + if (!t->rcu_read_unlock_special.s) { + local_irq_restore(flags); + return; + } + } + /* Hardware IRQ handlers cannot block, complain if they get here. */ if (in_irq() || in_serving_softirq()) { lockdep_rcu_suspicious(__FILE__, __LINE__, "rcu_read_unlock() from irq or softirq with blocking in critical section!!!\n"); - pr_alert("->rcu_read_unlock_special: %#x (b: %d, nq: %d)\n", + pr_alert("->rcu_read_unlock_special: %#x (b: %d, enq: %d nq: %d)\n", t->rcu_read_unlock_special.s, t->rcu_read_unlock_special.b.blocked, + t->rcu_read_unlock_special.b.exp_need_qs, t->rcu_read_unlock_special.b.need_qs); local_irq_restore(flags); return; @@ -329,7 +465,7 @@ void rcu_read_unlock_special(struct task_struct *t) raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ } empty_norm = !rcu_preempt_blocked_readers_cgp(rnp); - empty_exp = !rcu_preempted_readers_exp(rnp); + empty_exp = sync_rcu_preempt_exp_done(rnp); smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */ np = rcu_next_node_entry(t, rnp); list_del_init(&t->rcu_node_entry); @@ -353,7 +489,7 @@ void rcu_read_unlock_special(struct task_struct *t) * Note that rcu_report_unblock_qs_rnp() releases rnp->lock, * so we must take a snapshot of the expedited state. */ - empty_exp_now = !rcu_preempted_readers_exp(rnp); + empty_exp_now = sync_rcu_preempt_exp_done(rnp); if (!empty_norm && !rcu_preempt_blocked_readers_cgp(rnp)) { trace_rcu_quiescent_state_report(TPS("preempt_rcu"), rnp->gpnum, @@ -535,28 +671,99 @@ void synchronize_rcu(void) } EXPORT_SYMBOL_GPL(synchronize_rcu); +/* + * Remote handler for smp_call_function_single(). If there is an + * RCU read-side critical section in effect, request that the + * next rcu_read_unlock() record the quiescent state up the + * ->expmask fields in the rcu_node tree. Otherwise, immediately + * report the quiescent state. + */ +static void sync_rcu_exp_handler(void *info) +{ + struct rcu_data *rdp; + struct rcu_state *rsp = info; + struct task_struct *t = current; + + /* + * Within an RCU read-side critical section, request that the next + * rcu_read_unlock() report. Unless this RCU read-side critical + * section has already blocked, in which case it is already set + * up for the expedited grace period to wait on it. + */ + if (t->rcu_read_lock_nesting > 0 && + !t->rcu_read_unlock_special.b.blocked) { + t->rcu_read_unlock_special.b.exp_need_qs = true; + return; + } + + /* + * We are either exiting an RCU read-side critical section (negative + * values of t->rcu_read_lock_nesting) or are not in one at all + * (zero value of t->rcu_read_lock_nesting). Or we are in an RCU + * read-side critical section that blocked before this expedited + * grace period started. Either way, we can immediately report + * the quiescent state. + */ + rdp = this_cpu_ptr(rsp->rda); + rcu_report_exp_rdp(rsp, rdp, true); +} + /* * Select the nodes that the upcoming expedited grace period needs * to wait for. */ -static void sync_rcu_exp_select_nodes(struct rcu_state *rsp) +static void sync_rcu_exp_select_cpus(struct rcu_state *rsp) { + int cpu; unsigned long flags; + unsigned long mask; + unsigned long mask_ofl_test; + unsigned long mask_ofl_ipi; + int ret; struct rcu_node *rnp; sync_exp_reset_tree(rsp); rcu_for_each_leaf_node(rsp, rnp) { raw_spin_lock_irqsave(&rnp->lock, flags); smp_mb__after_unlock_lock(); - rnp->expmask = 0; /* No per-CPU component yet. */ - if (!rcu_preempt_has_tasks(rnp)) { - /* FIXME: Want __rcu_report_exp_rnp() here. */ - raw_spin_unlock_irqrestore(&rnp->lock, flags); - } else { + + /* Each pass checks a CPU for identity, offline, and idle. */ + mask_ofl_test = 0; + for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++) { + struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); + struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu); + + if (raw_smp_processor_id() == cpu || + cpu_is_offline(cpu) || + !(atomic_add_return(0, &rdtp->dynticks) & 0x1)) + mask_ofl_test |= rdp->grpmask; + } + mask_ofl_ipi = rnp->expmask & ~mask_ofl_test; + + /* + * Need to wait for any blocked tasks as well. Note that + * additional blocking tasks will also block the expedited + * GP until such time as the ->expmask bits are cleared. + */ + if (rcu_preempt_has_tasks(rnp)) rnp->exp_tasks = rnp->blkd_tasks.next; - rcu_initiate_boost(rnp, flags); + raw_spin_unlock_irqrestore(&rnp->lock, flags); + + /* IPI the remaining CPUs for expedited quiescent state. */ + mask = 1; + for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask <<= 1) { + if (!(mask_ofl_ipi & mask)) + continue; + ret = smp_call_function_single(cpu, + sync_rcu_exp_handler, + rsp, 0); + if (!ret) + mask_ofl_ipi &= ~mask; } - rcu_report_exp_rnp(rsp, rnp, false); + /* Report quiescent states for those that went offline. */ + mask_ofl_test |= mask_ofl_ipi; + if (mask_ofl_test) + rcu_report_exp_cpu_mult(rsp, rnp, mask_ofl_test, false); } } @@ -587,11 +794,8 @@ void synchronize_rcu_expedited(void) rcu_exp_gp_seq_start(rsp); - /* force all RCU readers onto ->blkd_tasks lists. */ - synchronize_sched_expedited(); - /* Initialize the rcu_node tree in preparation for the wait. */ - sync_rcu_exp_select_nodes(rsp); + sync_rcu_exp_select_cpus(rsp); /* Wait for snapshotted ->blkd_tasks lists to drain. */ rnp = rcu_get_root(rsp); -- cgit v1.2.3 From bce5fa12aad148e15efd9bc0015dc4898b6e723b Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 5 Aug 2015 16:03:54 -0700 Subject: rcu: Move synchronize_sched_expedited() to combining tree Currently, synchronize_sched_expedited() uses a single global counter to track the number of remaining context switches that the current expedited grace period must wait on. This is problematic on large systems, where the resulting memory contention can be pathological. This commit therefore makes synchronize_sched_expedited() instead use the combining tree in the same manner as synchronize_rcu_expedited(), keeping memory contention down to a dull roar. This commit creates a temporary function sync_sched_exp_select_cpus() that is very similar to sync_rcu_exp_select_cpus(). A later commit will consolidate these two functions, which becomes possible when synchronize_sched_expedited() switches from stop_one_cpu_nowait() to smp_call_function_single(). Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 123 ++++++++++++++++++++++++++++++++++++------------------ kernel/rcu/tree.h | 1 - 2 files changed, 82 insertions(+), 42 deletions(-) (limited to 'kernel/rcu') diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 6e92bf4337bd..d2cdcada6fe0 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -3642,19 +3642,77 @@ static int synchronize_sched_expedited_cpu_stop(void *data) struct rcu_data *rdp = data; struct rcu_state *rsp = rdp->rsp; - /* We are here: If we are last, do the wakeup. */ - rdp->exp_done = true; - if (atomic_dec_and_test(&rsp->expedited_need_qs)) - wake_up(&rsp->expedited_wq); + /* Report the quiescent state. */ + rcu_report_exp_rdp(rsp, rdp, true); return 0; } +/* + * Select the nodes that the upcoming expedited grace period needs + * to wait for. + */ +static void sync_sched_exp_select_cpus(struct rcu_state *rsp) +{ + int cpu; + unsigned long flags; + unsigned long mask; + unsigned long mask_ofl_test; + unsigned long mask_ofl_ipi; + struct rcu_data *rdp; + struct rcu_node *rnp; + + sync_exp_reset_tree(rsp); + rcu_for_each_leaf_node(rsp, rnp) { + raw_spin_lock_irqsave(&rnp->lock, flags); + smp_mb__after_unlock_lock(); + + /* Each pass checks a CPU for identity, offline, and idle. */ + mask_ofl_test = 0; + for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++) { + struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); + struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu); + + if (raw_smp_processor_id() == cpu || + cpu_is_offline(cpu) || + !(atomic_add_return(0, &rdtp->dynticks) & 0x1)) + mask_ofl_test |= rdp->grpmask; + } + mask_ofl_ipi = rnp->expmask & ~mask_ofl_test; + + /* + * Need to wait for any blocked tasks as well. Note that + * additional blocking tasks will also block the expedited + * GP until such time as the ->expmask bits are cleared. + */ + if (rcu_preempt_has_tasks(rnp)) + rnp->exp_tasks = rnp->blkd_tasks.next; + raw_spin_unlock_irqrestore(&rnp->lock, flags); + + /* IPI the remaining CPUs for expedited quiescent state. */ + mask = 1; + for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask <<= 1) { + if (!(mask_ofl_ipi & mask)) + continue; + rdp = per_cpu_ptr(rsp->rda, cpu); + stop_one_cpu_nowait(cpu, synchronize_sched_expedited_cpu_stop, + rdp, &rdp->exp_stop_work); + mask_ofl_ipi &= ~mask; + } + /* Report quiescent states for those that went offline. */ + mask_ofl_test |= mask_ofl_ipi; + if (mask_ofl_test) + rcu_report_exp_cpu_mult(rsp, rnp, mask_ofl_test, false); + } +} + static void synchronize_sched_expedited_wait(struct rcu_state *rsp) { int cpu; unsigned long jiffies_stall; unsigned long jiffies_start; - struct rcu_data *rdp; + unsigned long mask; + struct rcu_node *rnp; + struct rcu_node *rnp_root = rcu_get_root(rsp); int ret; jiffies_stall = rcu_jiffies_till_stall_check(); @@ -3663,33 +3721,36 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp) for (;;) { ret = wait_event_interruptible_timeout( rsp->expedited_wq, - !atomic_read(&rsp->expedited_need_qs), + sync_rcu_preempt_exp_done(rnp_root), jiffies_stall); if (ret > 0) return; if (ret < 0) { /* Hit a signal, disable CPU stall warnings. */ wait_event(rsp->expedited_wq, - !atomic_read(&rsp->expedited_need_qs)); + sync_rcu_preempt_exp_done(rnp_root)); return; } pr_err("INFO: %s detected expedited stalls on CPUs: {", rsp->name); - for_each_online_cpu(cpu) { - rdp = per_cpu_ptr(rsp->rda, cpu); - - if (rdp->exp_done) - continue; - pr_cont(" %d", cpu); + rcu_for_each_leaf_node(rsp, rnp) { + mask = 1; + for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask <<= 1) { + if (!(rnp->expmask & mask)) + continue; + pr_cont(" %d", cpu); + } + mask <<= 1; } pr_cont(" } %lu jiffies s: %lu\n", jiffies - jiffies_start, rsp->expedited_sequence); - for_each_online_cpu(cpu) { - rdp = per_cpu_ptr(rsp->rda, cpu); - - if (rdp->exp_done) - continue; - dump_cpu_task(cpu); + rcu_for_each_leaf_node(rsp, rnp) { + mask = 1; + for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask <<= 1) { + if (!(rnp->expmask & mask)) + continue; + dump_cpu_task(cpu); + } } jiffies_stall = 3 * rcu_jiffies_till_stall_check() + 3; } @@ -3713,7 +3774,6 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp) */ void synchronize_sched_expedited(void) { - int cpu; unsigned long s; struct rcu_node *rnp; struct rcu_state *rsp = &rcu_sched_state; @@ -3736,27 +3796,8 @@ void synchronize_sched_expedited(void) } rcu_exp_gp_seq_start(rsp); - - /* Stop each CPU that is online, non-idle, and not us. */ - atomic_set(&rsp->expedited_need_qs, 1); /* Extra count avoids race. */ - for_each_online_cpu(cpu) { - struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); - struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu); - - rdp->exp_done = false; - - /* Skip our CPU and any idle CPUs. */ - if (raw_smp_processor_id() == cpu || - !(atomic_add_return(0, &rdtp->dynticks) & 0x1)) - continue; - atomic_inc(&rsp->expedited_need_qs); - stop_one_cpu_nowait(cpu, synchronize_sched_expedited_cpu_stop, - rdp, &rdp->exp_stop_work); - } - - /* Remove extra count and, if necessary, wait for CPUs to stop. */ - if (!atomic_dec_and_test(&rsp->expedited_need_qs)) - synchronize_sched_expedited_wait(rsp); + sync_sched_exp_select_cpus(rsp); + synchronize_sched_expedited_wait(rsp); rcu_exp_gp_seq_end(rsp); mutex_unlock(&rnp->exp_funnel_mutex); diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index a57f25ecca58..efe361c764ab 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -383,7 +383,6 @@ struct rcu_data { struct rcu_head oom_head; #endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */ struct mutex exp_funnel_mutex; - bool exp_done; /* Expedited QS for this CPU? */ /* 7) Callback offloading. */ #ifdef CONFIG_RCU_NOCB_CPU -- cgit v1.2.3 From 97c668b8e983b722e2ed765b98b05f644aff1b13 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 6 Aug 2015 11:31:51 -0700 Subject: rcu: Rename qs_pending to core_needs_qs An upcoming commit needs to invert the sense of the ->passed_quiesce rcu_data structure field, so this commit is taking this opportunity to clarify things a bit by renaming ->qs_pending to ->core_needs_qs. So if !rdp->core_needs_qs, then this CPU need not concern itself with quiescent states, in particular, it need not acquire its leaf rcu_node structure's ->lock to check. Otherwise, it needs to report the next quiescent state. Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 14 +++++++------- kernel/rcu/tree.h | 4 ++-- kernel/rcu/tree_plugin.h | 2 +- kernel/rcu/tree_trace.c | 4 ++-- 4 files changed, 12 insertions(+), 12 deletions(-) (limited to 'kernel/rcu') diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index d2cdcada6fe0..7c158ffc7769 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -1746,7 +1746,7 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp, trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpustart")); rdp->passed_quiesce = 0; rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr); - rdp->qs_pending = !!(rnp->qsmask & rdp->grpmask); + rdp->core_needs_qs = !!(rnp->qsmask & rdp->grpmask); zero_cpu_stall_ticks(rdp); WRITE_ONCE(rdp->gpwrap, false); } @@ -2357,7 +2357,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp) if ((rnp->qsmask & mask) == 0) { raw_spin_unlock_irqrestore(&rnp->lock, flags); } else { - rdp->qs_pending = 0; + rdp->core_needs_qs = 0; /* * This GP can't end until cpu checks in, so all of our @@ -2388,7 +2388,7 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp) * Does this CPU still need to do its part for current grace period? * If no, return and let the other CPUs do their part as well. */ - if (!rdp->qs_pending) + if (!rdp->core_needs_qs) return; /* @@ -3828,10 +3828,10 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp) /* Is the RCU core waiting for a quiescent state from this CPU? */ if (rcu_scheduler_fully_active && - rdp->qs_pending && !rdp->passed_quiesce && + rdp->core_needs_qs && !rdp->passed_quiesce && rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) { - rdp->n_rp_qs_pending++; - } else if (rdp->qs_pending && + rdp->n_rp_core_needs_qs++; + } else if (rdp->core_needs_qs && (rdp->passed_quiesce || rdp->rcu_qs_ctr_snap != __this_cpu_read(rcu_qs_ctr))) { rdp->n_rp_report_qs++; @@ -4157,7 +4157,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp) rdp->completed = rnp->completed; rdp->passed_quiesce = false; rdp->rcu_qs_ctr_snap = per_cpu(rcu_qs_ctr, cpu); - rdp->qs_pending = false; + rdp->core_needs_qs = false; trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl")); raw_spin_unlock_irqrestore(&rnp->lock, flags); } diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index efe361c764ab..4a0f30676ba8 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -303,7 +303,7 @@ struct rcu_data { unsigned long rcu_qs_ctr_snap;/* Snapshot of rcu_qs_ctr to check */ /* for rcu_all_qs() invocations. */ bool passed_quiesce; /* User-mode/idle loop etc. */ - bool qs_pending; /* Core waits for quiesc state. */ + bool core_needs_qs; /* Core waits for quiesc state. */ bool beenonline; /* CPU online at least once. */ bool gpwrap; /* Possible gpnum/completed wrap. */ struct rcu_node *mynode; /* This CPU's leaf of hierarchy */ @@ -368,7 +368,7 @@ struct rcu_data { /* 5) __rcu_pending() statistics. */ unsigned long n_rcu_pending; /* rcu_pending() calls since boot. */ - unsigned long n_rp_qs_pending; + unsigned long n_rp_core_needs_qs; unsigned long n_rp_report_qs; unsigned long n_rp_cb_ready; unsigned long n_rp_cpu_needs_gp; diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 6f7500f9387c..e33b4f3b8e0a 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -619,7 +619,7 @@ static void rcu_preempt_check_callbacks(void) return; } if (t->rcu_read_lock_nesting > 0 && - __this_cpu_read(rcu_data_p->qs_pending) && + __this_cpu_read(rcu_data_p->core_needs_qs) && !__this_cpu_read(rcu_data_p->passed_quiesce)) t->rcu_read_unlock_special.b.need_qs = true; } diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c index 6fc4c5ff3bb5..4ac25f8520d6 100644 --- a/kernel/rcu/tree_trace.c +++ b/kernel/rcu/tree_trace.c @@ -123,7 +123,7 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp) ulong2long(rdp->completed), ulong2long(rdp->gpnum), rdp->passed_quiesce, rdp->rcu_qs_ctr_snap == per_cpu(rcu_qs_ctr, rdp->cpu), - rdp->qs_pending); + rdp->core_needs_qs); seq_printf(m, " dt=%d/%llx/%d df=%lu", atomic_read(&rdp->dynticks->dynticks), rdp->dynticks->dynticks_nesting, @@ -361,7 +361,7 @@ static void print_one_rcu_pending(struct seq_file *m, struct rcu_data *rdp) cpu_is_offline(rdp->cpu) ? '!' : ' ', rdp->n_rcu_pending); seq_printf(m, "qsp=%ld rpq=%ld cbr=%ld cng=%ld ", - rdp->n_rp_qs_pending, + rdp->n_rp_core_needs_qs, rdp->n_rp_report_qs, rdp->n_rp_cb_ready, rdp->n_rp_cpu_needs_gp); -- cgit v1.2.3 From 0d43eb34f9aabcddf41c99b7af2d0ced33e9a3cc Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 6 Aug 2015 14:17:29 -0700 Subject: rcu: Invert passed_quiesce and rename to cpu_no_qs This commit inverts the sense of the rcu_data structure's ->passed_quiesce field and renames it to ->cpu_no_qs. This will allow a later commit to use an "aggregate OR" operation to test expedited as well as normal grace periods without added overhead. Signed-off-by: Paul E. McKenney --- Documentation/RCU/trace.txt | 32 ++++++++++++++++---------------- kernel/rcu/tree.c | 22 +++++++++++----------- kernel/rcu/tree.h | 2 +- kernel/rcu/tree_plugin.h | 6 +++--- kernel/rcu/tree_trace.c | 4 ++-- 5 files changed, 33 insertions(+), 33 deletions(-) (limited to 'kernel/rcu') diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt index 97f17e9decda..ec6998b1b6d0 100644 --- a/Documentation/RCU/trace.txt +++ b/Documentation/RCU/trace.txt @@ -56,14 +56,14 @@ rcuboost: The output of "cat rcu/rcu_preempt/rcudata" looks as follows: - 0!c=30455 g=30456 pq=1/0 qp=1 dt=126535/140000000000000/0 df=2002 of=4 ql=0/0 qs=N... b=10 ci=74572 nci=0 co=1131 ca=716 - 1!c=30719 g=30720 pq=1/0 qp=0 dt=132007/140000000000000/0 df=1874 of=10 ql=0/0 qs=N... b=10 ci=123209 nci=0 co=685 ca=982 - 2!c=30150 g=30151 pq=1/1 qp=1 dt=138537/140000000000000/0 df=1707 of=8 ql=0/0 qs=N... b=10 ci=80132 nci=0 co=1328 ca=1458 - 3 c=31249 g=31250 pq=1/1 qp=0 dt=107255/140000000000000/0 df=1749 of=6 ql=0/450 qs=NRW. b=10 ci=151700 nci=0 co=509 ca=622 - 4!c=29502 g=29503 pq=1/0 qp=1 dt=83647/140000000000000/0 df=965 of=5 ql=0/0 qs=N... b=10 ci=65643 nci=0 co=1373 ca=1521 - 5 c=31201 g=31202 pq=1/0 qp=1 dt=70422/0/0 df=535 of=7 ql=0/0 qs=.... b=10 ci=58500 nci=0 co=764 ca=698 - 6!c=30253 g=30254 pq=1/0 qp=1 dt=95363/140000000000000/0 df=780 of=5 ql=0/0 qs=N... b=10 ci=100607 nci=0 co=1414 ca=1353 - 7 c=31178 g=31178 pq=1/0 qp=0 dt=91536/0/0 df=547 of=4 ql=0/0 qs=.... b=10 ci=109819 nci=0 co=1115 ca=969 + 0!c=30455 g=30456 cnq=1/0:1 dt=126535/140000000000000/0 df=2002 of=4 ql=0/0 qs=N... b=10 ci=74572 nci=0 co=1131 ca=716 + 1!c=30719 g=30720 cnq=1/0:0 dt=132007/140000000000000/0 df=1874 of=10 ql=0/0 qs=N... b=10 ci=123209 nci=0 co=685 ca=982 + 2!c=30150 g=30151 cnq=1/1:1 dt=138537/140000000000000/0 df=1707 of=8 ql=0/0 qs=N... b=10 ci=80132 nci=0 co=1328 ca=1458 + 3 c=31249 g=31250 cnq=1/1:0 dt=107255/140000000000000/0 df=1749 of=6 ql=0/450 qs=NRW. b=10 ci=151700 nci=0 co=509 ca=622 + 4!c=29502 g=29503 cnq=1/0:1 dt=83647/140000000000000/0 df=965 of=5 ql=0/0 qs=N... b=10 ci=65643 nci=0 co=1373 ca=1521 + 5 c=31201 g=31202 cnq=1/0:1 dt=70422/0/0 df=535 of=7 ql=0/0 qs=.... b=10 ci=58500 nci=0 co=764 ca=698 + 6!c=30253 g=30254 cnq=1/0:1 dt=95363/140000000000000/0 df=780 of=5 ql=0/0 qs=N... b=10 ci=100607 nci=0 co=1414 ca=1353 + 7 c=31178 g=31178 cnq=1/0:0 dt=91536/0/0 df=547 of=4 ql=0/0 qs=.... b=10 ci=109819 nci=0 co=1115 ca=969 This file has one line per CPU, or eight for this 8-CPU system. The fields are as follows: @@ -188,14 +188,14 @@ o "ca" is the number of RCU callbacks that have been adopted by this Kernels compiled with CONFIG_RCU_BOOST=y display the following from /debug/rcu/rcu_preempt/rcudata: - 0!c=12865 g=12866 pq=1/0 qp=1 dt=83113/140000000000000/0 df=288 of=11 ql=0/0 qs=N... kt=0/O ktl=944 b=10 ci=60709 nci=0 co=748 ca=871 - 1 c=14407 g=14408 pq=1/0 qp=0 dt=100679/140000000000000/0 df=378 of=7 ql=0/119 qs=NRW. kt=0/W ktl=9b6 b=10 ci=109740 nci=0 co=589 ca=485 - 2 c=14407 g=14408 pq=1/0 qp=0 dt=105486/0/0 df=90 of=9 ql=0/89 qs=NRW. kt=0/W ktl=c0c b=10 ci=83113 nci=0 co=533 ca=490 - 3 c=14407 g=14408 pq=1/0 qp=0 dt=107138/0/0 df=142 of=8 ql=0/188 qs=NRW. kt=0/W ktl=b96 b=10 ci=121114 nci=0 co=426 ca=290 - 4 c=14405 g=14406 pq=1/0 qp=1 dt=50238/0/0 df=706 of=7 ql=0/0 qs=.... kt=0/W ktl=812 b=10 ci=34929 nci=0 co=643 ca=114 - 5!c=14168 g=14169 pq=1/0 qp=0 dt=45465/140000000000000/0 df=161 of=11 ql=0/0 qs=N... kt=0/O ktl=b4d b=10 ci=47712 nci=0 co=677 ca=722 - 6 c=14404 g=14405 pq=1/0 qp=0 dt=59454/0/0 df=94 of=6 ql=0/0 qs=.... kt=0/W ktl=e57 b=10 ci=55597 nci=0 co=701 ca=811 - 7 c=14407 g=14408 pq=1/0 qp=1 dt=68850/0/0 df=31 of=8 ql=0/0 qs=.... kt=0/W ktl=14bd b=10 ci=77475 nci=0 co=508 ca=1042 + 0!c=12865 g=12866 cnq=1/0:1 dt=83113/140000000000000/0 df=288 of=11 ql=0/0 qs=N... kt=0/O ktl=944 b=10 ci=60709 nci=0 co=748 ca=871 + 1 c=14407 g=14408 cnq=1/0:0 dt=100679/140000000000000/0 df=378 of=7 ql=0/119 qs=NRW. kt=0/W ktl=9b6 b=10 ci=109740 nci=0 co=589 ca=485 + 2 c=14407 g=14408 cnq=1/0:0 dt=105486/0/0 df=90 of=9 ql=0/89 qs=NRW. kt=0/W ktl=c0c b=10 ci=83113 nci=0 co=533 ca=490 + 3 c=14407 g=14408 cnq=1/0:0 dt=107138/0/0 df=142 of=8 ql=0/188 qs=NRW. kt=0/W ktl=b96 b=10 ci=121114 nci=0 co=426 ca=290 + 4 c=14405 g=14406 cnq=1/0:1 dt=50238/0/0 df=706 of=7 ql=0/0 qs=.... kt=0/W ktl=812 b=10 ci=34929 nci=0 co=643 ca=114 + 5!c=14168 g=14169 cnq=1/0:0 dt=45465/140000000000000/0 df=161 of=11 ql=0/0 qs=N... kt=0/O ktl=b4d b=10 ci=47712 nci=0 co=677 ca=722 + 6 c=14404 g=14405 cnq=1/0:0 dt=59454/0/0 df=94 of=6 ql=0/0 qs=.... kt=0/W ktl=e57 b=10 ci=55597 nci=0 co=701 ca=811 + 7 c=14407 g=14408 cnq=1/0:1 dt=68850/0/0 df=31 of=8 ql=0/0 qs=.... kt=0/W ktl=14bd b=10 ci=77475 nci=0 co=508 ca=1042 This is similar to the output discussed above, but contains the following additional fields: diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 7c158ffc7769..31e7021ced4d 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -245,21 +245,21 @@ static int rcu_gp_in_progress(struct rcu_state *rsp) */ void rcu_sched_qs(void) { - if (!__this_cpu_read(rcu_sched_data.passed_quiesce)) { + if (__this_cpu_read(rcu_sched_data.cpu_no_qs)) { trace_rcu_grace_period(TPS("rcu_sched"), __this_cpu_read(rcu_sched_data.gpnum), TPS("cpuqs")); - __this_cpu_write(rcu_sched_data.passed_quiesce, 1); + __this_cpu_write(rcu_sched_data.cpu_no_qs, false); } } void rcu_bh_qs(void) { - if (!__this_cpu_read(rcu_bh_data.passed_quiesce)) { + if (__this_cpu_read(rcu_bh_data.cpu_no_qs)) { trace_rcu_grace_period(TPS("rcu_bh"), __this_cpu_read(rcu_bh_data.gpnum), TPS("cpuqs")); - __this_cpu_write(rcu_bh_data.passed_quiesce, 1); + __this_cpu_write(rcu_bh_data.cpu_no_qs, false); } } @@ -1744,7 +1744,7 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp, */ rdp->gpnum = rnp->gpnum; trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpustart")); - rdp->passed_quiesce = 0; + rdp->cpu_no_qs = true; rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr); rdp->core_needs_qs = !!(rnp->qsmask & rdp->grpmask); zero_cpu_stall_ticks(rdp); @@ -2337,7 +2337,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp) rnp = rdp->mynode; raw_spin_lock_irqsave(&rnp->lock, flags); smp_mb__after_unlock_lock(); - if ((rdp->passed_quiesce == 0 && + if ((rdp->cpu_no_qs && rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) || rdp->gpnum != rnp->gpnum || rnp->completed == rnp->gpnum || rdp->gpwrap) { @@ -2348,7 +2348,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp) * We will instead need a new quiescent state that lies * within the current grace period. */ - rdp->passed_quiesce = 0; /* need qs for new gp. */ + rdp->cpu_no_qs = true; /* need qs for new gp. */ rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr); raw_spin_unlock_irqrestore(&rnp->lock, flags); return; @@ -2395,7 +2395,7 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp) * Was there a quiescent state since the beginning of the grace * period? If no, then exit and wait for the next call. */ - if (!rdp->passed_quiesce && + if (rdp->cpu_no_qs && rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) return; @@ -3828,11 +3828,11 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp) /* Is the RCU core waiting for a quiescent state from this CPU? */ if (rcu_scheduler_fully_active && - rdp->core_needs_qs && !rdp->passed_quiesce && + rdp->core_needs_qs && rdp->cpu_no_qs && rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) { rdp->n_rp_core_needs_qs++; } else if (rdp->core_needs_qs && - (rdp->passed_quiesce || + (!rdp->cpu_no_qs || rdp->rcu_qs_ctr_snap != __this_cpu_read(rcu_qs_ctr))) { rdp->n_rp_report_qs++; return 1; @@ -4155,7 +4155,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp) rdp->beenonline = true; /* We have now been online. */ rdp->gpnum = rnp->completed; /* Make CPU later note any new GP. */ rdp->completed = rnp->completed; - rdp->passed_quiesce = false; + rdp->cpu_no_qs = true; rdp->rcu_qs_ctr_snap = per_cpu(rcu_qs_ctr, cpu); rdp->core_needs_qs = false; trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl")); diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 4a0f30676ba8..ded4ceebed76 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -302,7 +302,7 @@ struct rcu_data { /* is aware of having started. */ unsigned long rcu_qs_ctr_snap;/* Snapshot of rcu_qs_ctr to check */ /* for rcu_all_qs() invocations. */ - bool passed_quiesce; /* User-mode/idle loop etc. */ + bool cpu_no_qs; /* No QS yet for this CPU. */ bool core_needs_qs; /* Core waits for quiesc state. */ bool beenonline; /* CPU online at least once. */ bool gpwrap; /* Possible gpnum/completed wrap. */ diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index e33b4f3b8e0a..6977ff0dccb9 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -265,11 +265,11 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp, */ static void rcu_preempt_qs(void) { - if (!__this_cpu_read(rcu_data_p->passed_quiesce)) { + if (__this_cpu_read(rcu_data_p->cpu_no_qs)) { trace_rcu_grace_period(TPS("rcu_preempt"), __this_cpu_read(rcu_data_p->gpnum), TPS("cpuqs")); - __this_cpu_write(rcu_data_p->passed_quiesce, 1); + __this_cpu_write(rcu_data_p->cpu_no_qs, false); barrier(); /* Coordinate with rcu_preempt_check_callbacks(). */ current->rcu_read_unlock_special.b.need_qs = false; } @@ -620,7 +620,7 @@ static void rcu_preempt_check_callbacks(void) } if (t->rcu_read_lock_nesting > 0 && __this_cpu_read(rcu_data_p->core_needs_qs) && - !__this_cpu_read(rcu_data_p->passed_quiesce)) + __this_cpu_read(rcu_data_p->cpu_no_qs)) t->rcu_read_unlock_special.b.need_qs = true; } diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c index 4ac25f8520d6..d373e57109b8 100644 --- a/kernel/rcu/tree_trace.c +++ b/kernel/rcu/tree_trace.c @@ -117,11 +117,11 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp) if (!rdp->beenonline) return; - seq_printf(m, "%3d%cc=%ld g=%ld pq=%d/%d qp=%d", + seq_printf(m, "%3d%cc=%ld g=%ld cnq=%d/%d:%d", rdp->cpu, cpu_is_offline(rdp->cpu) ? '!' : ' ', ulong2long(rdp->completed), ulong2long(rdp->gpnum), - rdp->passed_quiesce, + rdp->cpu_no_qs, rdp->rcu_qs_ctr_snap == per_cpu(rcu_qs_ctr, rdp->cpu), rdp->core_needs_qs); seq_printf(m, " dt=%d/%llx/%d df=%lu", -- cgit v1.2.3 From 5b74c458906fc4a62f932ee8bb801d29baf15fec Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 6 Aug 2015 15:16:57 -0700 Subject: rcu: Make ->cpu_no_qs be a union for aggregate OR This commit converts the rcu_data structure's ->cpu_no_qs field to a union. The bytewise side of this union allows individual access to indications as to whether this CPU needs to find a quiescent state for a normal (.norm) and/or expedited (.exp) grace period. The setwise side of the union allows testing whether or not a quiescent state is needed at all, for either type of grace period. For now, only .norm is used. A later commit will introduce the expedited usage. Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 22 +++++++++++----------- kernel/rcu/tree.h | 14 +++++++++++++- kernel/rcu/tree_plugin.h | 6 +++--- kernel/rcu/tree_trace.c | 2 +- 4 files changed, 28 insertions(+), 16 deletions(-) (limited to 'kernel/rcu') diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 31e7021ced4d..3e2875b38eae 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -245,21 +245,21 @@ static int rcu_gp_in_progress(struct rcu_state *rsp) */ void rcu_sched_qs(void) { - if (__this_cpu_read(rcu_sched_data.cpu_no_qs)) { + if (__this_cpu_read(rcu_sched_data.cpu_no_qs.s)) { trace_rcu_grace_period(TPS("rcu_sched"), __this_cpu_read(rcu_sched_data.gpnum), TPS("cpuqs")); - __this_cpu_write(rcu_sched_data.cpu_no_qs, false); + __this_cpu_write(rcu_sched_data.cpu_no_qs.b.norm, false); } } void rcu_bh_qs(void) { - if (__this_cpu_read(rcu_bh_data.cpu_no_qs)) { + if (__this_cpu_read(rcu_bh_data.cpu_no_qs.s)) { trace_rcu_grace_period(TPS("rcu_bh"), __this_cpu_read(rcu_bh_data.gpnum), TPS("cpuqs")); - __this_cpu_write(rcu_bh_data.cpu_no_qs, false); + __this_cpu_write(rcu_bh_data.cpu_no_qs.b.norm, false); } } @@ -1744,7 +1744,7 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp, */ rdp->gpnum = rnp->gpnum; trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpustart")); - rdp->cpu_no_qs = true; + rdp->cpu_no_qs.b.norm = true; rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr); rdp->core_needs_qs = !!(rnp->qsmask & rdp->grpmask); zero_cpu_stall_ticks(rdp); @@ -2337,7 +2337,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp) rnp = rdp->mynode; raw_spin_lock_irqsave(&rnp->lock, flags); smp_mb__after_unlock_lock(); - if ((rdp->cpu_no_qs && + if ((rdp->cpu_no_qs.b.norm && rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) || rdp->gpnum != rnp->gpnum || rnp->completed == rnp->gpnum || rdp->gpwrap) { @@ -2348,7 +2348,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp) * We will instead need a new quiescent state that lies * within the current grace period. */ - rdp->cpu_no_qs = true; /* need qs for new gp. */ + rdp->cpu_no_qs.b.norm = true; /* need qs for new gp. */ rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr); raw_spin_unlock_irqrestore(&rnp->lock, flags); return; @@ -2395,7 +2395,7 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp) * Was there a quiescent state since the beginning of the grace * period? If no, then exit and wait for the next call. */ - if (rdp->cpu_no_qs && + if (rdp->cpu_no_qs.b.norm && rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) return; @@ -3828,11 +3828,11 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp) /* Is the RCU core waiting for a quiescent state from this CPU? */ if (rcu_scheduler_fully_active && - rdp->core_needs_qs && rdp->cpu_no_qs && + rdp->core_needs_qs && rdp->cpu_no_qs.b.norm && rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) { rdp->n_rp_core_needs_qs++; } else if (rdp->core_needs_qs && - (!rdp->cpu_no_qs || + (!rdp->cpu_no_qs.b.norm || rdp->rcu_qs_ctr_snap != __this_cpu_read(rcu_qs_ctr))) { rdp->n_rp_report_qs++; return 1; @@ -4155,7 +4155,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp) rdp->beenonline = true; /* We have now been online. */ rdp->gpnum = rnp->completed; /* Make CPU later note any new GP. */ rdp->completed = rnp->completed; - rdp->cpu_no_qs = true; + rdp->cpu_no_qs.b.norm = true; rdp->rcu_qs_ctr_snap = per_cpu(rcu_qs_ctr, cpu); rdp->core_needs_qs = false; trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl")); diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index ded4ceebed76..3eee48bcf52b 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -286,6 +286,18 @@ struct rcu_node { for ((rnp) = (rsp)->level[rcu_num_lvls - 1]; \ (rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++) +/* + * Union to allow "aggregate OR" operation on the need for a quiescent + * state by the normal and expedited grace periods. + */ +union rcu_noqs { + struct { + u8 norm; + u8 exp; + } b; /* Bits. */ + u16 s; /* Set of bits, aggregate OR here. */ +}; + /* Index values for nxttail array in struct rcu_data. */ #define RCU_DONE_TAIL 0 /* Also RCU_WAIT head. */ #define RCU_WAIT_TAIL 1 /* Also RCU_NEXT_READY head. */ @@ -302,7 +314,7 @@ struct rcu_data { /* is aware of having started. */ unsigned long rcu_qs_ctr_snap;/* Snapshot of rcu_qs_ctr to check */ /* for rcu_all_qs() invocations. */ - bool cpu_no_qs; /* No QS yet for this CPU. */ + union rcu_noqs cpu_no_qs; /* No QSes yet for this CPU. */ bool core_needs_qs; /* Core waits for quiesc state. */ bool beenonline; /* CPU online at least once. */ bool gpwrap; /* Possible gpnum/completed wrap. */ diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 6977ff0dccb9..7880202f1e38 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -265,11 +265,11 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp, */ static void rcu_preempt_qs(void) { - if (__this_cpu_read(rcu_data_p->cpu_no_qs)) { + if (__this_cpu_read(rcu_data_p->cpu_no_qs.s)) { trace_rcu_grace_period(TPS("rcu_preempt"), __this_cpu_read(rcu_data_p->gpnum), TPS("cpuqs")); - __this_cpu_write(rcu_data_p->cpu_no_qs, false); + __this_cpu_write(rcu_data_p->cpu_no_qs.b.norm, false); barrier(); /* Coordinate with rcu_preempt_check_callbacks(). */ current->rcu_read_unlock_special.b.need_qs = false; } @@ -620,7 +620,7 @@ static void rcu_preempt_check_callbacks(void) } if (t->rcu_read_lock_nesting > 0 && __this_cpu_read(rcu_data_p->core_needs_qs) && - __this_cpu_read(rcu_data_p->cpu_no_qs)) + __this_cpu_read(rcu_data_p->cpu_no_qs.b.norm)) t->rcu_read_unlock_special.b.need_qs = true; } diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c index d373e57109b8..999c3672f990 100644 --- a/kernel/rcu/tree_trace.c +++ b/kernel/rcu/tree_trace.c @@ -121,7 +121,7 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp) rdp->cpu, cpu_is_offline(rdp->cpu) ? '!' : ' ', ulong2long(rdp->completed), ulong2long(rdp->gpnum), - rdp->cpu_no_qs, + rdp->cpu_no_qs.b.norm, rdp->rcu_qs_ctr_snap == per_cpu(rcu_qs_ctr, rdp->cpu), rdp->core_needs_qs); seq_printf(m, " dt=%d/%llx/%d df=%lu", -- cgit v1.2.3 From 6587a23b6b9bdb47205ec96c703e5bf8a2d39701 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 6 Aug 2015 16:50:39 -0700 Subject: rcu: Switch synchronize_sched_expedited() to IPI This commit switches synchronize_sched_expedited() from stop_one_cpu_nowait() to smp_call_function_single(), thus moving from an IPI and a pair of context switches to an IPI and a single pass through the scheduler. Of course, if the scheduler actually does decide to switch to a different task, there will still be a pair of context switches, but there would likely have been a pair of context switches anyway, just a bit later. Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 32 ++++++++++++++++++++------------ kernel/rcu/tree.h | 3 --- 2 files changed, 20 insertions(+), 15 deletions(-) (limited to 'kernel/rcu') diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 3e2875b38eae..a42168911941 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -161,6 +161,8 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf); static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu); static void invoke_rcu_core(void); static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp); +static void rcu_report_exp_rdp(struct rcu_state *rsp, + struct rcu_data *rdp, bool wake); /* rcuc/rcub kthread realtime priority */ #ifdef CONFIG_RCU_KTHREAD_PRIO @@ -250,6 +252,12 @@ void rcu_sched_qs(void) __this_cpu_read(rcu_sched_data.gpnum), TPS("cpuqs")); __this_cpu_write(rcu_sched_data.cpu_no_qs.b.norm, false); + if (__this_cpu_read(rcu_sched_data.cpu_no_qs.b.exp)) { + __this_cpu_write(rcu_sched_data.cpu_no_qs.b.exp, false); + rcu_report_exp_rdp(&rcu_sched_state, + this_cpu_ptr(&rcu_sched_data), + true); + } } } @@ -3555,8 +3563,8 @@ static void rcu_report_exp_cpu_mult(struct rcu_state *rsp, struct rcu_node *rnp, * Report expedited quiescent state for specified rcu_data (CPU). * Caller must hold the root rcu_node's exp_funnel_mutex. */ -static void __maybe_unused rcu_report_exp_rdp(struct rcu_state *rsp, - struct rcu_data *rdp, bool wake) +static void rcu_report_exp_rdp(struct rcu_state *rsp, struct rcu_data *rdp, + bool wake) { rcu_report_exp_cpu_mult(rsp, rdp->mynode, rdp->grpmask, wake); } @@ -3637,14 +3645,10 @@ static struct rcu_node *exp_funnel_lock(struct rcu_state *rsp, unsigned long s) } /* Invoked on each online non-idle CPU for expedited quiescent state. */ -static int synchronize_sched_expedited_cpu_stop(void *data) +static void synchronize_sched_expedited_cpu_stop(void *data) { - struct rcu_data *rdp = data; - struct rcu_state *rsp = rdp->rsp; - - /* Report the quiescent state. */ - rcu_report_exp_rdp(rsp, rdp, true); - return 0; + __this_cpu_write(rcu_sched_data.cpu_no_qs.b.exp, true); + resched_cpu(smp_processor_id()); } /* @@ -3659,6 +3663,7 @@ static void sync_sched_exp_select_cpus(struct rcu_state *rsp) unsigned long mask_ofl_test; unsigned long mask_ofl_ipi; struct rcu_data *rdp; + int ret; struct rcu_node *rnp; sync_exp_reset_tree(rsp); @@ -3694,9 +3699,9 @@ static void sync_sched_exp_select_cpus(struct rcu_state *rsp) if (!(mask_ofl_ipi & mask)) continue; rdp = per_cpu_ptr(rsp->rda, cpu); - stop_one_cpu_nowait(cpu, synchronize_sched_expedited_cpu_stop, - rdp, &rdp->exp_stop_work); - mask_ofl_ipi &= ~mask; + ret = smp_call_function_single(cpu, synchronize_sched_expedited_cpu_stop, NULL, 0); + if (!ret) + mask_ofl_ipi &= ~mask; } /* Report quiescent states for those that went offline. */ mask_ofl_test |= mask_ofl_ipi; @@ -4201,6 +4206,9 @@ int rcu_cpu_notify(struct notifier_block *self, rcu_cleanup_dying_cpu(rsp); break; case CPU_DYING_IDLE: + /* QS for any half-done expedited RCU-sched GP. */ + rcu_sched_qs(); + for_each_rcu_flavor(rsp) { rcu_cleanup_dying_idle_cpu(cpu, rsp); } diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 3eee48bcf52b..1b969cef8fe4 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -324,9 +324,6 @@ struct rcu_data { /* ticks this CPU has handled */ /* during and after the last grace */ /* period it is aware of. */ - struct cpu_stop_work exp_stop_work; - /* Expedited grace-period control */ - /* for CPU stopping. */ /* 2) batch handling */ /* -- cgit v1.2.3 From 83c2c735e78da1a0d994911f730f6e1d36c88d7a Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 6 Aug 2015 20:43:02 -0700 Subject: rcu: Stop silencing lockdep false positive for expedited grace periods This reverts commit af859beaaba4 (rcu: Silence lockdep false positive for expedited grace periods). Because synchronize_rcu_expedited() no longer invokes synchronize_sched_expedited(), ->exp_funnel_mutex acquisition is no longer nested, so the false positive no longer happens. This commit therefore removes the extra lockdep data structures, as they are no longer needed. --- kernel/rcu/tree.c | 17 ++--------------- kernel/rcu/tree.h | 8 -------- 2 files changed, 2 insertions(+), 23 deletions(-) (limited to 'kernel/rcu') diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index a42168911941..15b19baaade5 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -71,7 +71,6 @@ MODULE_ALIAS("rcutree"); static struct lock_class_key rcu_node_class[RCU_NUM_LVLS]; static struct lock_class_key rcu_fqs_class[RCU_NUM_LVLS]; static struct lock_class_key rcu_exp_class[RCU_NUM_LVLS]; -static struct lock_class_key rcu_exp_sched_class[RCU_NUM_LVLS]; /* * In order to export the rcu_state name to the tracing tools, it @@ -4095,7 +4094,6 @@ static void rcu_init_new_rnp(struct rcu_node *rnp_leaf) static void __init rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp) { - static struct lock_class_key rcu_exp_sched_rdp_class; unsigned long flags; struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); struct rcu_node *rnp = rcu_get_root(rsp); @@ -4111,10 +4109,6 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp) mutex_init(&rdp->exp_funnel_mutex); rcu_boot_init_nocb_percpu_data(rdp); raw_spin_unlock_irqrestore(&rnp->lock, flags); - if (rsp == &rcu_sched_state) - lockdep_set_class_and_name(&rdp->exp_funnel_mutex, - &rcu_exp_sched_rdp_class, - "rcu_data_exp_sched"); } /* @@ -4340,7 +4334,6 @@ static void __init rcu_init_one(struct rcu_state *rsp, static const char * const buf[] = RCU_NODE_NAME_INIT; static const char * const fqs[] = RCU_FQS_NAME_INIT; static const char * const exp[] = RCU_EXP_NAME_INIT; - static const char * const exp_sched[] = RCU_EXP_SCHED_NAME_INIT; static u8 fl_mask = 0x1; int levelcnt[RCU_NUM_LVLS]; /* # nodes in each level. */ @@ -4400,14 +4393,8 @@ static void __init rcu_init_one(struct rcu_state *rsp, INIT_LIST_HEAD(&rnp->blkd_tasks); rcu_init_one_nocb(rnp); mutex_init(&rnp->exp_funnel_mutex); - if (rsp == &rcu_sched_state) - lockdep_set_class_and_name( - &rnp->exp_funnel_mutex, - &rcu_exp_sched_class[i], exp_sched[i]); - else - lockdep_set_class_and_name( - &rnp->exp_funnel_mutex, - &rcu_exp_class[i], exp[i]); + lockdep_set_class_and_name(&rnp->exp_funnel_mutex, + &rcu_exp_class[i], exp[i]); } } diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 1b969cef8fe4..6f3b63b68886 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -70,8 +70,6 @@ # define RCU_NODE_NAME_INIT { "rcu_node_0" } # define RCU_FQS_NAME_INIT { "rcu_node_fqs_0" } # define RCU_EXP_NAME_INIT { "rcu_node_exp_0" } -# define RCU_EXP_SCHED_NAME_INIT \ - { "rcu_node_exp_sched_0" } #elif NR_CPUS <= RCU_FANOUT_2 # define RCU_NUM_LVLS 2 # define NUM_RCU_LVL_0 1 @@ -81,8 +79,6 @@ # define RCU_NODE_NAME_INIT { "rcu_node_0", "rcu_node_1" } # define RCU_FQS_NAME_INIT { "rcu_node_fqs_0", "rcu_node_fqs_1" } # define RCU_EXP_NAME_INIT { "rcu_node_exp_0", "rcu_node_exp_1" } -# define RCU_EXP_SCHED_NAME_INIT \ - { "rcu_node_exp_sched_0", "rcu_node_exp_sched_1" } #elif NR_CPUS <= RCU_FANOUT_3 # define RCU_NUM_LVLS 3 # define NUM_RCU_LVL_0 1 @@ -93,8 +89,6 @@ # define RCU_NODE_NAME_INIT { "rcu_node_0", "rcu_node_1", "rcu_node_2" } # define RCU_FQS_NAME_INIT { "rcu_node_fqs_0", "rcu_node_fqs_1", "rcu_node_fqs_2" } # define RCU_EXP_NAME_INIT { "rcu_node_exp_0", "rcu_node_exp_1", "rcu_node_exp_2" } -# define RCU_EXP_SCHED_NAME_INIT \ - { "rcu_node_exp_sched_0", "rcu_node_exp_sched_1", "rcu_node_exp_sched_2" } #elif NR_CPUS <= RCU_FANOUT_4 # define RCU_NUM_LVLS 4 # define NUM_RCU_LVL_0 1 @@ -106,8 +100,6 @@ # define RCU_NODE_NAME_INIT { "rcu_node_0", "rcu_node_1", "rcu_node_2", "rcu_node_3" } # define RCU_FQS_NAME_INIT { "rcu_node_fqs_0", "rcu_node_fqs_1", "rcu_node_fqs_2", "rcu_node_fqs_3" } # define RCU_EXP_NAME_INIT { "rcu_node_exp_0", "rcu_node_exp_1", "rcu_node_exp_2", "rcu_node_exp_3" } -# define RCU_EXP_SCHED_NAME_INIT \ - { "rcu_node_exp_sched_0", "rcu_node_exp_sched_1", "rcu_node_exp_sched_2", "rcu_node_exp_sched_3" } #else # error "CONFIG_RCU_FANOUT insufficient for NR_CPUS" #endif /* #if (NR_CPUS) <= RCU_FANOUT_1 */ -- cgit v1.2.3 From 807226e2fbb504d82cd504b7b6114896db41ef63 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 7 Aug 2015 12:03:45 -0700 Subject: rcu: Stop excluding CPU hotplug in synchronize_sched_expedited() Now that synchronize_sched_expedited() uses IPIs, a hook in rcu_sched_qs(), and the ->expmask field in the rcu_node combining tree, it is no longer necessary to exclude CPU hotplug. Any races with CPU hotplug will be detected when attempting to send the IPI. This commit therefore removes the code excluding CPU hotplug operations. Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 14 +------------- 1 file changed, 1 insertion(+), 13 deletions(-) (limited to 'kernel/rcu') diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 15b19baaade5..7e7df5deadf9 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -3785,19 +3785,9 @@ void synchronize_sched_expedited(void) /* Take a snapshot of the sequence number. */ s = rcu_exp_gp_seq_snap(rsp); - if (!try_get_online_cpus()) { - /* CPU hotplug operation in flight, fall back to normal GP. */ - wait_rcu_gp(call_rcu_sched); - atomic_long_inc(&rsp->expedited_normal); - return; - } - WARN_ON_ONCE(cpu_is_offline(raw_smp_processor_id())); - rnp = exp_funnel_lock(rsp, s); - if (rnp == NULL) { - put_online_cpus(); + if (rnp == NULL) return; /* Someone else did our work for us. */ - } rcu_exp_gp_seq_start(rsp); sync_sched_exp_select_cpus(rsp); @@ -3805,8 +3795,6 @@ void synchronize_sched_expedited(void) rcu_exp_gp_seq_end(rsp); mutex_unlock(&rnp->exp_funnel_mutex); - - put_online_cpus(); } EXPORT_SYMBOL_GPL(synchronize_sched_expedited); -- cgit v1.2.3 From 66fe6cbee44e3f78d05882195a6a38e30b97b936 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sat, 15 Aug 2015 17:20:58 -0700 Subject: rcu: Prepare for consolidating expedited CPU selection This commit brings sync_sched_exp_select_cpus() into alignment with sync_rcu_exp_select_cpus(), as a first step towards consolidating them into one function. Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'kernel/rcu') diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 7e7df5deadf9..ae582e3d4136 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -3661,7 +3661,6 @@ static void sync_sched_exp_select_cpus(struct rcu_state *rsp) unsigned long mask; unsigned long mask_ofl_test; unsigned long mask_ofl_ipi; - struct rcu_data *rdp; int ret; struct rcu_node *rnp; @@ -3697,7 +3696,6 @@ static void sync_sched_exp_select_cpus(struct rcu_state *rsp) for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask <<= 1) { if (!(mask_ofl_ipi & mask)) continue; - rdp = per_cpu_ptr(rsp->rda, cpu); ret = smp_call_function_single(cpu, synchronize_sched_expedited_cpu_stop, NULL, 0); if (!ret) mask_ofl_ipi &= ~mask; -- cgit v1.2.3 From dcdb8807ba0f5127d4dc67daeeb154edf50a93d1 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sat, 15 Aug 2015 19:00:31 -0700 Subject: rcu: Consolidate expedited CPU selection Now that sync_sched_exp_select_cpus() and sync_rcu_exp_select_cpus() are identical aside from the the argument to smp_call_function_single(), this commit consolidates them with a functional argument. Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 7 +++--- kernel/rcu/tree_plugin.h | 61 +----------------------------------------------- 2 files changed, 5 insertions(+), 63 deletions(-) (limited to 'kernel/rcu') diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index ae582e3d4136..f44f4b30c68a 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -3654,7 +3654,8 @@ static void synchronize_sched_expedited_cpu_stop(void *data) * Select the nodes that the upcoming expedited grace period needs * to wait for. */ -static void sync_sched_exp_select_cpus(struct rcu_state *rsp) +static void sync_rcu_exp_select_cpus(struct rcu_state *rsp, + smp_call_func_t func) { int cpu; unsigned long flags; @@ -3696,7 +3697,7 @@ static void sync_sched_exp_select_cpus(struct rcu_state *rsp) for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask <<= 1) { if (!(mask_ofl_ipi & mask)) continue; - ret = smp_call_function_single(cpu, synchronize_sched_expedited_cpu_stop, NULL, 0); + ret = smp_call_function_single(cpu, func, rsp, 0); if (!ret) mask_ofl_ipi &= ~mask; } @@ -3788,7 +3789,7 @@ void synchronize_sched_expedited(void) return; /* Someone else did our work for us. */ rcu_exp_gp_seq_start(rsp); - sync_sched_exp_select_cpus(rsp); + sync_rcu_exp_select_cpus(rsp, synchronize_sched_expedited_cpu_stop); synchronize_sched_expedited_wait(rsp); rcu_exp_gp_seq_end(rsp); diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 7880202f1e38..6cbfbfc58656 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -708,65 +708,6 @@ static void sync_rcu_exp_handler(void *info) rcu_report_exp_rdp(rsp, rdp, true); } -/* - * Select the nodes that the upcoming expedited grace period needs - * to wait for. - */ -static void sync_rcu_exp_select_cpus(struct rcu_state *rsp) -{ - int cpu; - unsigned long flags; - unsigned long mask; - unsigned long mask_ofl_test; - unsigned long mask_ofl_ipi; - int ret; - struct rcu_node *rnp; - - sync_exp_reset_tree(rsp); - rcu_for_each_leaf_node(rsp, rnp) { - raw_spin_lock_irqsave(&rnp->lock, flags); - smp_mb__after_unlock_lock(); - - /* Each pass checks a CPU for identity, offline, and idle. */ - mask_ofl_test = 0; - for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++) { - struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); - struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu); - - if (raw_smp_processor_id() == cpu || - cpu_is_offline(cpu) || - !(atomic_add_return(0, &rdtp->dynticks) & 0x1)) - mask_ofl_test |= rdp->grpmask; - } - mask_ofl_ipi = rnp->expmask & ~mask_ofl_test; - - /* - * Need to wait for any blocked tasks as well. Note that - * additional blocking tasks will also block the expedited - * GP until such time as the ->expmask bits are cleared. - */ - if (rcu_preempt_has_tasks(rnp)) - rnp->exp_tasks = rnp->blkd_tasks.next; - raw_spin_unlock_irqrestore(&rnp->lock, flags); - - /* IPI the remaining CPUs for expedited quiescent state. */ - mask = 1; - for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask <<= 1) { - if (!(mask_ofl_ipi & mask)) - continue; - ret = smp_call_function_single(cpu, - sync_rcu_exp_handler, - rsp, 0); - if (!ret) - mask_ofl_ipi &= ~mask; - } - /* Report quiescent states for those that went offline. */ - mask_ofl_test |= mask_ofl_ipi; - if (mask_ofl_test) - rcu_report_exp_cpu_mult(rsp, rnp, mask_ofl_test, false); - } -} - /** * synchronize_rcu_expedited - Brute-force RCU grace period * @@ -795,7 +736,7 @@ void synchronize_rcu_expedited(void) rcu_exp_gp_seq_start(rsp); /* Initialize the rcu_node tree in preparation for the wait. */ - sync_rcu_exp_select_cpus(rsp); + sync_rcu_exp_select_cpus(rsp, sync_rcu_exp_handler); /* Wait for snapshotted ->blkd_tasks lists to drain. */ rnp = rcu_get_root(rsp); -- cgit v1.2.3 From 74611ecb0fc4c850a8f89a744ce99cbf0dd43cb2 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 18 Aug 2015 10:20:43 -0700 Subject: rcu: Add online/offline info to expedited stall warning message This commit makes the RCU CPU stall warning message print online/offline indications immediately after the CPU number. A "O" indicates global offline, a "." global online, and a "o" indicates RCU believes that the CPU is offline for the current grace period and "." otherwise, and an "N" indicates that RCU believes that the CPU will be offline for the next grace period, and "." otherwise, all right after the CPU number. So for CPU 10, you would normally see "10-...:" indicating that everything believes that the CPU is online. Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 9 ++++++++- kernel/rcu/tree.h | 1 + kernel/rcu/tree_plugin.h | 31 +++++++++++++++++++++++++++++++ 3 files changed, 40 insertions(+), 1 deletion(-) (limited to 'kernel/rcu') diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index f44f4b30c68a..3d033fee0dcb 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -3737,11 +3737,18 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp) pr_err("INFO: %s detected expedited stalls on CPUs: {", rsp->name); rcu_for_each_leaf_node(rsp, rnp) { + (void)rcu_print_task_exp_stall(rnp); mask = 1; for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask <<= 1) { + struct rcu_data *rdp; + if (!(rnp->expmask & mask)) continue; - pr_cont(" %d", cpu); + rdp = per_cpu_ptr(rsp->rda, cpu); + pr_cont(" %d-%c%c%c", cpu, + "O."[cpu_online(cpu)], + "o."[!!(rdp->grpmask & rnp->expmaskinit)], + "N."[!!(rdp->grpmask & rnp->expmaskinitnext)]); } mask <<= 1; } diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 6f3b63b68886..191aa3678575 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -589,6 +589,7 @@ static bool rcu_preempt_has_tasks(struct rcu_node *rnp); #endif /* #ifdef CONFIG_HOTPLUG_CPU */ static void rcu_print_detail_task_stall(struct rcu_state *rsp); static int rcu_print_task_stall(struct rcu_node *rnp); +static int rcu_print_task_exp_stall(struct rcu_node *rnp); static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp); static void rcu_preempt_check_callbacks(void); void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu)); diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 6cbfbfc58656..7b61cece80c0 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -585,6 +585,27 @@ static int rcu_print_task_stall(struct rcu_node *rnp) return ndetected; } +/* + * Scan the current list of tasks blocked within RCU read-side critical + * sections, printing out the tid of each that is blocking the current + * expedited grace period. + */ +static int rcu_print_task_exp_stall(struct rcu_node *rnp) +{ + struct task_struct *t; + int ndetected = 0; + + if (!rnp->exp_tasks) + return 0; + t = list_entry(rnp->exp_tasks->prev, + struct task_struct, rcu_node_entry); + list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) { + pr_cont(" P%d", t->pid); + ndetected++; + } + return ndetected; +} + /* * Check that the list of blocked tasks for the newly completed grace * period is in fact empty. It is a serious bug to complete a grace @@ -845,6 +866,16 @@ static int rcu_print_task_stall(struct rcu_node *rnp) return 0; } +/* + * Because preemptible RCU does not exist, we never have to check for + * tasks blocked within RCU read-side critical sections that are + * blocking the current expedited grace period. + */ +static int rcu_print_task_exp_stall(struct rcu_node *rnp) +{ + return 0; +} + /* * Because there is no preemptible RCU, there can be no readers blocked, * so there is no need to check for blocked tasks. So check only for -- cgit v1.2.3 From c58656382e5f2919b05913584f2c54b4f841bc9f Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 18 Aug 2015 11:25:48 -0700 Subject: rcu: Add tasks to expedited stall-warning messages This commit adds task-print ability to the expedited RCU CPU stall warning messages in preparation for adding stall warnings to synchornize_rcu_expedited(). Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/rcu') diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 3d033fee0dcb..b4f71ffa299c 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -3734,7 +3734,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp) sync_rcu_preempt_exp_done(rnp_root)); return; } - pr_err("INFO: %s detected expedited stalls on CPUs: {", + pr_err("INFO: %s detected expedited stalls on CPUs/tasks: {", rsp->name); rcu_for_each_leaf_node(rsp, rnp) { (void)rcu_print_task_exp_stall(rnp); -- cgit v1.2.3 From b08517c76d764c373c232cd309ed058c98705219 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 18 Aug 2015 12:17:29 -0700 Subject: rcu: Enable stall warnings for synchronize_rcu_expedited() This commit redirects synchronize_rcu_expedited()'s wait to synchronize_sched_expedited_wait(), thus enabling RCU CPU stall warnings. Signed-off-by: Paul E. McKenney --- kernel/rcu/tree_plugin.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'kernel/rcu') diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 7b61cece80c0..ffeb99e550e8 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -761,8 +761,7 @@ void synchronize_rcu_expedited(void) /* Wait for snapshotted ->blkd_tasks lists to drain. */ rnp = rcu_get_root(rsp); - wait_event(rsp->expedited_wq, - sync_rcu_preempt_exp_done(rnp)); + synchronize_sched_expedited_wait(rsp); /* Clean up and exit. */ rcu_exp_gp_seq_end(rsp); -- cgit v1.2.3 From 338b0f760e84676130c6e4d8268cb8c923b38c8c Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 3 Sep 2015 00:45:02 -0700 Subject: rcu: Better hotplug handling for synchronize_sched_expedited() Earlier versions of synchronize_sched_expedited() can prematurely end grace periods due to the fact that a CPU marked as cpu_is_offline() can still be using RCU read-side critical sections during the time that CPU makes its last pass through the scheduler and into the idle loop and during the time that a given CPU is in the process of coming online. This commit therefore eliminates this window by adding additional interaction with the CPU-hotplug operations. Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 68 ++++++++++++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 62 insertions(+), 6 deletions(-) (limited to 'kernel/rcu') diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index b4f71ffa299c..42b317e13776 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -246,17 +246,23 @@ static int rcu_gp_in_progress(struct rcu_state *rsp) */ void rcu_sched_qs(void) { + unsigned long flags; + if (__this_cpu_read(rcu_sched_data.cpu_no_qs.s)) { trace_rcu_grace_period(TPS("rcu_sched"), __this_cpu_read(rcu_sched_data.gpnum), TPS("cpuqs")); __this_cpu_write(rcu_sched_data.cpu_no_qs.b.norm, false); + if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.b.exp)) + return; + local_irq_save(flags); if (__this_cpu_read(rcu_sched_data.cpu_no_qs.b.exp)) { __this_cpu_write(rcu_sched_data.cpu_no_qs.b.exp, false); rcu_report_exp_rdp(&rcu_sched_state, this_cpu_ptr(&rcu_sched_data), true); } + local_irq_restore(flags); } } @@ -3553,7 +3559,10 @@ static void rcu_report_exp_cpu_mult(struct rcu_state *rsp, struct rcu_node *rnp, raw_spin_lock_irqsave(&rnp->lock, flags); smp_mb__after_unlock_lock(); - WARN_ON_ONCE((rnp->expmask & mask) != mask); + if (!(rnp->expmask & mask)) { + raw_spin_unlock_irqrestore(&rnp->lock, flags); + return; + } rnp->expmask &= ~mask; __rcu_report_exp_rnp(rsp, rnp, wake, flags); /* Releases rnp->lock. */ } @@ -3644,12 +3653,37 @@ static struct rcu_node *exp_funnel_lock(struct rcu_state *rsp, unsigned long s) } /* Invoked on each online non-idle CPU for expedited quiescent state. */ -static void synchronize_sched_expedited_cpu_stop(void *data) +static void sync_sched_exp_handler(void *data) { + struct rcu_data *rdp; + struct rcu_node *rnp; + struct rcu_state *rsp = data; + + rdp = this_cpu_ptr(rsp->rda); + rnp = rdp->mynode; + if (!(READ_ONCE(rnp->expmask) & rdp->grpmask) || + __this_cpu_read(rcu_sched_data.cpu_no_qs.b.exp)) + return; __this_cpu_write(rcu_sched_data.cpu_no_qs.b.exp, true); resched_cpu(smp_processor_id()); } +/* Send IPI for expedited cleanup if needed at end of CPU-hotplug operation. */ +static void sync_sched_exp_online_cleanup(int cpu) +{ + struct rcu_data *rdp; + int ret; + struct rcu_node *rnp; + struct rcu_state *rsp = &rcu_sched_state; + + rdp = per_cpu_ptr(rsp->rda, cpu); + rnp = rdp->mynode; + if (!(READ_ONCE(rnp->expmask) & rdp->grpmask)) + return; + ret = smp_call_function_single(cpu, sync_sched_exp_handler, rsp, 0); + WARN_ON_ONCE(ret); +} + /* * Select the nodes that the upcoming expedited grace period needs * to wait for. @@ -3677,7 +3711,6 @@ static void sync_rcu_exp_select_cpus(struct rcu_state *rsp, struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu); if (raw_smp_processor_id() == cpu || - cpu_is_offline(cpu) || !(atomic_add_return(0, &rdtp->dynticks) & 0x1)) mask_ofl_test |= rdp->grpmask; } @@ -3697,9 +3730,28 @@ static void sync_rcu_exp_select_cpus(struct rcu_state *rsp, for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask <<= 1) { if (!(mask_ofl_ipi & mask)) continue; +retry_ipi: ret = smp_call_function_single(cpu, func, rsp, 0); - if (!ret) + if (!ret) { mask_ofl_ipi &= ~mask; + } else { + /* Failed, raced with offline. */ + raw_spin_lock_irqsave(&rnp->lock, flags); + if (cpu_online(cpu) && + (rnp->expmask & mask)) { + raw_spin_unlock_irqrestore(&rnp->lock, + flags); + schedule_timeout_uninterruptible(1); + if (cpu_online(cpu) && + (rnp->expmask & mask)) + goto retry_ipi; + raw_spin_lock_irqsave(&rnp->lock, + flags); + } + if (!(rnp->expmask & mask)) + mask_ofl_ipi &= ~mask; + raw_spin_unlock_irqrestore(&rnp->lock, flags); + } } /* Report quiescent states for those that went offline. */ mask_ofl_test |= mask_ofl_ipi; @@ -3796,7 +3848,7 @@ void synchronize_sched_expedited(void) return; /* Someone else did our work for us. */ rcu_exp_gp_seq_start(rsp); - sync_rcu_exp_select_cpus(rsp, synchronize_sched_expedited_cpu_stop); + sync_rcu_exp_select_cpus(rsp, sync_sched_exp_handler); synchronize_sched_expedited_wait(rsp); rcu_exp_gp_seq_end(rsp); @@ -4183,6 +4235,7 @@ int rcu_cpu_notify(struct notifier_block *self, break; case CPU_ONLINE: case CPU_DOWN_FAILED: + sync_sched_exp_online_cleanup(cpu); rcu_boost_kthread_setaffinity(rnp, -1); break; case CPU_DOWN_PREPARE: @@ -4195,7 +4248,10 @@ int rcu_cpu_notify(struct notifier_block *self, break; case CPU_DYING_IDLE: /* QS for any half-done expedited RCU-sched GP. */ - rcu_sched_qs(); + preempt_disable(); + rcu_report_exp_rdp(&rcu_sched_state, + this_cpu_ptr(rcu_sched_state.rda), true); + preempt_enable(); for_each_rcu_flavor(rsp) { rcu_cleanup_dying_idle_cpu(cpu, rsp); -- cgit v1.2.3