From 0aa04b055e71bd3b8040dd71a126126c66b6f01e Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 23 Jan 2015 21:52:37 -0800 Subject: rcu: Process offlining and onlining only at grace-period start Races between CPU hotplug and grace periods can be difficult to resolve, so the ->onoff_mutex is used to exclude the two events. Unfortunately, this means that it is impossible for an outgoing CPU to perform the last bits of its offlining from its last pass through the idle loop, because sleeplocks cannot be acquired in that context. This commit avoids these problems by buffering online and offline events in a new ->qsmaskinitnext field in the leaf rcu_node structures. When a grace period starts, the events accumulated in this mask are applied to the ->qsmaskinit field, and, if needed, up the rcu_node tree. The special case of all CPUs corresponding to a given leaf rcu_node structure being offline while there are still elements in that structure's ->blkd_tasks list is handled using a new ->wait_blkd_tasks field. In this case, propagating the offline bits up the tree is deferred until the beginning of the grace period after all of the tasks have exited their RCU read-side critical sections and removed themselves from the list, at which point the ->wait_blkd_tasks flag is cleared. If one of that leaf rcu_node structure's CPUs comes back online before the list empties, then the ->wait_blkd_tasks flag is simply cleared. This of course means that RCU's notion of which CPUs are offline can be out of date. This is OK because RCU need only wait on CPUs that were online at the time that the grace period started. In addition, RCU's force-quiescent-state actions will handle the case where a CPU goes offline after the grace period starts. Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'kernel/rcu/tree.h') diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 119de399eb2f..aa42562ff5b2 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -141,12 +141,20 @@ struct rcu_node { /* complete (only for PREEMPT_RCU). */ unsigned long qsmaskinit; /* Per-GP initial value for qsmask & expmask. */ + /* Initialized from ->qsmaskinitnext at the */ + /* beginning of each grace period. */ + unsigned long qsmaskinitnext; + /* Online CPUs for next grace period. */ 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. */ int grphi; /* highest-numbered CPU or group here. */ u8 grpnum; /* CPU/group number for next level up. */ u8 level; /* root is at level 0. */ + bool wait_blkd_tasks;/* Necessary to wait for blocked tasks to */ + /* exit RCU read-side critical sections */ + /* before propagating offline up the */ + /* rcu_node tree? */ struct rcu_node *parent; struct list_head blkd_tasks; /* Tasks blocked in RCU read-side critical */ @@ -559,6 +567,7 @@ static void rcu_prepare_kthreads(int cpu); static void rcu_cleanup_after_idle(void); static void rcu_prepare_for_idle(void); static void rcu_idle_count_callbacks_posted(void); +static bool rcu_preempt_has_tasks(struct rcu_node *rnp); static void print_cpu_stall_info_begin(void); static void print_cpu_stall_info(struct rcu_state *rsp, int cpu); static void print_cpu_stall_info_end(void); -- cgit v1.2.3 From c199068913c9c5cbb5498e289bb387703e087ea8 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 23 Jan 2015 22:29:37 -0800 Subject: rcu: Eliminate ->onoff_mutex from rcu_node structure Because that RCU grace-period initialization need no longer exclude CPU-hotplug operations, this commit eliminates the ->onoff_mutex and its uses. Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 15 --------------- kernel/rcu/tree.h | 2 -- 2 files changed, 17 deletions(-) (limited to 'kernel/rcu/tree.h') diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index f0f4d3510d24..79d53399247e 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -101,7 +101,6 @@ struct rcu_state sname##_state = { \ .orphan_nxttail = &sname##_state.orphan_nxtlist, \ .orphan_donetail = &sname##_state.orphan_donelist, \ .barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \ - .onoff_mutex = __MUTEX_INITIALIZER(sname##_state.onoff_mutex), \ .name = RCU_STATE_NAME(sname), \ .abbr = sabbr, \ }; \ @@ -1754,10 +1753,6 @@ static int rcu_gp_init(struct rcu_state *rsp) trace_rcu_grace_period(rsp->name, rsp->gpnum, TPS("start")); raw_spin_unlock_irq(&rnp->lock); - /* Exclude any concurrent CPU-hotplug operations. */ - mutex_lock(&rsp->onoff_mutex); - smp_mb__after_unlock_lock(); /* ->gpnum increment before GP! */ - /* * Apply per-leaf buffered online and offline operations to the * rcu_node tree. Note that this new grace period need not wait @@ -1844,7 +1839,6 @@ static int rcu_gp_init(struct rcu_state *rsp) schedule_timeout_uninterruptible(gp_init_delay); } - mutex_unlock(&rsp->onoff_mutex); return 1; } @@ -2498,9 +2492,6 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp) /* Adjust any no-longer-needed kthreads. */ rcu_boost_kthread_setaffinity(rnp, -1); - /* Exclude any attempts to start a new grace period. */ - mutex_lock(&rsp->onoff_mutex); - /* Orphan the dead CPU's callbacks, and adopt them if appropriate. */ raw_spin_lock_irqsave(&rsp->orphan_lock, flags); rcu_send_cbs_to_orphanage(cpu, rsp, rnp, rdp); @@ -2517,7 +2508,6 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp) WARN_ONCE(rdp->qlen != 0 || rdp->nxtlist != NULL, "rcu_cleanup_dead_cpu: Callbacks on offline CPU %d: qlen=%lu, nxtlist=%p\n", cpu, rdp->qlen, rdp->nxtlist); - mutex_unlock(&rsp->onoff_mutex); } #else /* #ifdef CONFIG_HOTPLUG_CPU */ @@ -3700,9 +3690,6 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp) struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); struct rcu_node *rnp = rcu_get_root(rsp); - /* Exclude new grace periods. */ - mutex_lock(&rsp->onoff_mutex); - /* 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. */ @@ -3733,8 +3720,6 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp) rdp->qs_pending = false; trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl")); raw_spin_unlock_irqrestore(&rnp->lock, flags); - - mutex_unlock(&rsp->onoff_mutex); } static void rcu_prepare_cpu(int cpu) diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index aa42562ff5b2..a69d3dab2ec4 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -456,8 +456,6 @@ struct rcu_state { long qlen; /* Total number of callbacks. */ /* End of fields guarded by orphan_lock. */ - struct mutex onoff_mutex; /* Coordinate hotplug & GPs. */ - struct mutex barrier_mutex; /* Guards barrier fields. */ atomic_t barrier_cpu_count; /* # CPUs waiting on. */ struct completion barrier_completion; /* Wake at barrier end. */ -- cgit v1.2.3