From 426216970e0458c1f507860f4837cbde66a72263 Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Wed, 3 Jun 2015 08:18:31 +0200 Subject: rcu: Simplify arithmetic to calculate number of RCU nodes This update makes arithmetic to calculate number of RCU nodes more straight and easy to read. Cc: "Paul E. McKenney" Cc: Steven Rostedt Signed-off-by: Alexander Gordeev Signed-off-by: Paul E. McKenney --- kernel/rcu/tree_plugin.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/rcu/tree_plugin.h') diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 013485fb2b06..5dac0a10a985 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -84,8 +84,8 @@ static void __init rcu_bootup_announce_oddness(void) pr_info("\tRCU torture testing starts during boot.\n"); if (IS_ENABLED(CONFIG_RCU_CPU_STALL_INFO)) pr_info("\tAdditional per-CPU info printed with stalls.\n"); - if (NUM_RCU_LVL_4 != 0) - pr_info("\tFour-level hierarchy is enabled.\n"); + if (RCU_NUM_LVLS >= 4) + pr_info("\tFour(or more)-level hierarchy is enabled.\n"); if (RCU_FANOUT_LEAF != 16) pr_info("\tBuild-time adjustment of leaf fanout to %d.\n", RCU_FANOUT_LEAF); -- cgit v1.2.3 From 9b683874504a57cfa97558d403c75e286e20c9ce Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 11 Jun 2015 14:50:22 -0700 Subject: rcu: Stop disabling CPU hotplug in synchronize_rcu_expedited() The fact that tasks could be migrated from leaf to root rcu_node structures meant that synchronize_rcu_expedited() had to disable CPU hotplug. However, tasks now stay put, so this commit removes the CPU-hotplug disabling from synchronize_rcu_expedited(). Signed-off-by: Paul E. McKenney --- kernel/rcu/tree_plugin.h | 25 ++----------------------- 1 file changed, 2 insertions(+), 23 deletions(-) (limited to 'kernel/rcu/tree_plugin.h') diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 5dac0a10a985..7234f03e0aa2 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -727,20 +727,6 @@ void synchronize_rcu_expedited(void) snap = READ_ONCE(sync_rcu_preempt_exp_count) + 1; smp_mb(); /* Above access cannot bleed into critical section. */ - /* - * Block CPU-hotplug operations. This means that any CPU-hotplug - * operation that finds an rcu_node structure with tasks in the - * process of being boosted will know that all tasks blocking - * this expedited grace period will already be in the process of - * being boosted. This simplifies the process of moving tasks - * from leaf to root rcu_node structures. - */ - if (!try_get_online_cpus()) { - /* CPU-hotplug operation in flight, fall back to normal GP. */ - wait_rcu_gp(call_rcu); - return; - } - /* * Acquire lock, falling back to synchronize_rcu() if too many * lock-acquisition failures. Of course, if someone does the @@ -748,22 +734,17 @@ void synchronize_rcu_expedited(void) */ while (!mutex_trylock(&sync_rcu_preempt_exp_mutex)) { if (ULONG_CMP_LT(snap, - READ_ONCE(sync_rcu_preempt_exp_count))) { - put_online_cpus(); + READ_ONCE(sync_rcu_preempt_exp_count))) goto mb_ret; /* Others did our work for us. */ - } if (trycount++ < 10) { udelay(trycount * num_online_cpus()); } else { - put_online_cpus(); wait_rcu_gp(call_rcu); return; } } - if (ULONG_CMP_LT(snap, READ_ONCE(sync_rcu_preempt_exp_count))) { - put_online_cpus(); + if (ULONG_CMP_LT(snap, READ_ONCE(sync_rcu_preempt_exp_count))) goto unlock_mb_ret; /* Others did our work for us. */ - } /* force all RCU readers onto ->blkd_tasks lists. */ synchronize_sched_expedited(); @@ -779,8 +760,6 @@ void synchronize_rcu_expedited(void) rcu_for_each_leaf_node(rsp, rnp) sync_rcu_preempt_exp_init2(rsp, rnp); - put_online_cpus(); - /* Wait for snapshotted ->blkd_tasks lists to drain. */ rnp = rcu_get_root(rsp); wait_event(sync_rcu_preempt_exp_wq, -- cgit v1.2.3 From 75c27f119b6475d95374bdad872c6938b5c26196 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 11 Jun 2015 15:22:43 -0700 Subject: rcu: Remove CONFIG_RCU_CPU_STALL_INFO The CONFIG_RCU_CPU_STALL_INFO has been default-y for a couple of releases with no complaints, so it is time to eliminate this Kconfig option entirely, so that the long-form RCU CPU stall warnings cannot be disabled. This commit does just that. Signed-off-by: Paul E. McKenney --- kernel/rcu/tree_plugin.h | 45 --------------------------------------------- 1 file changed, 45 deletions(-) (limited to 'kernel/rcu/tree_plugin.h') diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 7234f03e0aa2..ef41c1b04ba6 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -82,8 +82,6 @@ static void __init rcu_bootup_announce_oddness(void) pr_info("\tRCU lockdep checking is enabled.\n"); if (IS_ENABLED(CONFIG_RCU_TORTURE_TEST_RUNNABLE)) pr_info("\tRCU torture testing starts during boot.\n"); - if (IS_ENABLED(CONFIG_RCU_CPU_STALL_INFO)) - pr_info("\tAdditional per-CPU info printed with stalls.\n"); if (RCU_NUM_LVLS >= 4) pr_info("\tFour(or more)-level hierarchy is enabled.\n"); if (RCU_FANOUT_LEAF != 16) @@ -418,8 +416,6 @@ static void rcu_print_detail_task_stall(struct rcu_state *rsp) rcu_print_detail_task_stall_rnp(rnp); } -#ifdef CONFIG_RCU_CPU_STALL_INFO - static void rcu_print_task_stall_begin(struct rcu_node *rnp) { pr_err("\tTasks blocked on level-%d rcu_node (CPUs %d-%d):", @@ -431,18 +427,6 @@ static void rcu_print_task_stall_end(void) pr_cont("\n"); } -#else /* #ifdef CONFIG_RCU_CPU_STALL_INFO */ - -static void rcu_print_task_stall_begin(struct rcu_node *rnp) -{ -} - -static void rcu_print_task_stall_end(void) -{ -} - -#endif /* #else #ifdef CONFIG_RCU_CPU_STALL_INFO */ - /* * Scan the current list of tasks blocked within RCU read-side critical * sections, printing out the tid of each. @@ -1685,8 +1669,6 @@ early_initcall(rcu_register_oom_notifier); #endif /* #else #if !defined(CONFIG_RCU_FAST_NO_HZ) */ -#ifdef CONFIG_RCU_CPU_STALL_INFO - #ifdef CONFIG_RCU_FAST_NO_HZ static void print_cpu_stall_fast_no_hz(char *cp, int cpu) @@ -1775,33 +1757,6 @@ static void increment_cpu_stall_ticks(void) raw_cpu_inc(rsp->rda->ticks_this_gp); } -#else /* #ifdef CONFIG_RCU_CPU_STALL_INFO */ - -static void print_cpu_stall_info_begin(void) -{ - pr_cont(" {"); -} - -static void print_cpu_stall_info(struct rcu_state *rsp, int cpu) -{ - pr_cont(" %d", cpu); -} - -static void print_cpu_stall_info_end(void) -{ - pr_cont("} "); -} - -static void zero_cpu_stall_ticks(struct rcu_data *rdp) -{ -} - -static void increment_cpu_stall_ticks(void) -{ -} - -#endif /* #else #ifdef CONFIG_RCU_CPU_STALL_INFO */ - #ifdef CONFIG_RCU_NOCB_CPU /* -- cgit v1.2.3 From 543c6158f6dff20a741dfa492771f18ceaa1a109 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 25 Jun 2015 15:52:50 -0700 Subject: rcu: Make synchronize_rcu_expedited() use sequence-counter scheme Although synchronize_rcu_expedited() uses a sequence-counter scheme, it is based on a single increment per grace period, which means that tasks piggybacking off of concurrent grace periods may be forced to wait longer than necessary. This commit therefore applies the new sequence-count functions developed for synchronize_sched_expedited() to speed things up a bit and to consolidate the sequence-counter implementation. Signed-off-by: Paul E. McKenney --- kernel/rcu/tree_plugin.h | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-) (limited to 'kernel/rcu/tree_plugin.h') diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index ef41c1b04ba6..759883f51de7 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -536,7 +536,6 @@ void synchronize_rcu(void) EXPORT_SYMBOL_GPL(synchronize_rcu); static DECLARE_WAIT_QUEUE_HEAD(sync_rcu_preempt_exp_wq); -static unsigned long sync_rcu_preempt_exp_count; static DEFINE_MUTEX(sync_rcu_preempt_exp_mutex); /* @@ -704,12 +703,10 @@ void synchronize_rcu_expedited(void) { struct rcu_node *rnp; struct rcu_state *rsp = rcu_state_p; - unsigned long snap; + unsigned long s; int trycount = 0; - smp_mb(); /* Caller's modifications seen first by other CPUs. */ - snap = READ_ONCE(sync_rcu_preempt_exp_count) + 1; - smp_mb(); /* Above access cannot bleed into critical section. */ + s = rcu_exp_gp_seq_snap(rsp); /* * Acquire lock, falling back to synchronize_rcu() if too many @@ -717,8 +714,7 @@ void synchronize_rcu_expedited(void) * expedited grace period for us, just leave. */ while (!mutex_trylock(&sync_rcu_preempt_exp_mutex)) { - if (ULONG_CMP_LT(snap, - READ_ONCE(sync_rcu_preempt_exp_count))) + if (rcu_exp_gp_seq_done(rsp, s)) goto mb_ret; /* Others did our work for us. */ if (trycount++ < 10) { udelay(trycount * num_online_cpus()); @@ -727,8 +723,9 @@ void synchronize_rcu_expedited(void) return; } } - if (ULONG_CMP_LT(snap, READ_ONCE(sync_rcu_preempt_exp_count))) + if (rcu_exp_gp_seq_done(rsp, s)) goto unlock_mb_ret; /* Others did our work for us. */ + rcu_exp_gp_seq_start(rsp); /* force all RCU readers onto ->blkd_tasks lists. */ synchronize_sched_expedited(); @@ -750,8 +747,7 @@ void synchronize_rcu_expedited(void) sync_rcu_preempt_exp_done(rnp)); /* Clean up and exit. */ - smp_mb(); /* ensure expedited GP seen before counter increment. */ - WRITE_ONCE(sync_rcu_preempt_exp_count, sync_rcu_preempt_exp_count + 1); + rcu_exp_gp_seq_end(rsp); unlock_mb_ret: mutex_unlock(&sync_rcu_preempt_exp_mutex); mb_ret: -- cgit v1.2.3 From 29fd930940193a9a035a75a3847457160d65559a Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 25 Jun 2015 19:03:16 -0700 Subject: rcu: Use funnel locking for synchronize_rcu_expedited()'s polling loop This commit gets rid of synchronize_rcu_expedited()'s mutex_trylock() polling loop in favor of the funnel-locking scheme that was abstracted from synchronize_sched_expedited(). Signed-off-by: Paul E. McKenney --- kernel/rcu/tree_plugin.h | 36 ++++++++++-------------------------- 1 file changed, 10 insertions(+), 26 deletions(-) (limited to 'kernel/rcu/tree_plugin.h') diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 759883f51de7..f0d71449ec0c 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -536,7 +536,6 @@ void synchronize_rcu(void) EXPORT_SYMBOL_GPL(synchronize_rcu); static DECLARE_WAIT_QUEUE_HEAD(sync_rcu_preempt_exp_wq); -static DEFINE_MUTEX(sync_rcu_preempt_exp_mutex); /* * Return non-zero if there are any tasks in RCU read-side critical @@ -556,7 +555,7 @@ static int rcu_preempted_readers_exp(struct rcu_node *rnp) * for the current expedited grace period. Works only for preemptible * RCU -- other RCU implementation use other means. * - * Caller must hold sync_rcu_preempt_exp_mutex. + * Caller must hold the root rcu_node's exp_funnel_mutex. */ static int sync_rcu_preempt_exp_done(struct rcu_node *rnp) { @@ -572,7 +571,7 @@ 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 sync_rcu_preempt_exp_mutex. + * 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) @@ -611,7 +610,7 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, * set the ->expmask bits on the leaf rcu_node structures to tell phase 2 * that work is needed here. * - * Caller must hold sync_rcu_preempt_exp_mutex. + * Caller must hold the root rcu_node's exp_funnel_mutex. */ static void sync_rcu_preempt_exp_init1(struct rcu_state *rsp, struct rcu_node *rnp) @@ -654,7 +653,7 @@ sync_rcu_preempt_exp_init1(struct rcu_state *rsp, struct rcu_node *rnp) * 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 sync_rcu_preempt_exp_mutex. + * 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) @@ -702,29 +701,16 @@ sync_rcu_preempt_exp_init2(struct rcu_state *rsp, struct rcu_node *rnp) void synchronize_rcu_expedited(void) { struct rcu_node *rnp; + struct rcu_node *rnp_unlock; struct rcu_state *rsp = rcu_state_p; unsigned long s; - int trycount = 0; s = rcu_exp_gp_seq_snap(rsp); - /* - * Acquire lock, falling back to synchronize_rcu() if too many - * lock-acquisition failures. Of course, if someone does the - * expedited grace period for us, just leave. - */ - while (!mutex_trylock(&sync_rcu_preempt_exp_mutex)) { - if (rcu_exp_gp_seq_done(rsp, s)) - goto mb_ret; /* Others did our work for us. */ - if (trycount++ < 10) { - udelay(trycount * num_online_cpus()); - } else { - wait_rcu_gp(call_rcu); - return; - } - } - if (rcu_exp_gp_seq_done(rsp, s)) - goto unlock_mb_ret; /* Others did our work for us. */ + rnp_unlock = exp_funnel_lock(rsp, s); + if (rnp_unlock == NULL) + return; /* Someone else did our work for us. */ + rcu_exp_gp_seq_start(rsp); /* force all RCU readers onto ->blkd_tasks lists. */ @@ -748,9 +734,7 @@ void synchronize_rcu_expedited(void) /* Clean up and exit. */ rcu_exp_gp_seq_end(rsp); -unlock_mb_ret: - mutex_unlock(&sync_rcu_preempt_exp_mutex); -mb_ret: + mutex_unlock(&rnp_unlock->exp_funnel_mutex); smp_mb(); /* ensure subsequent action seen after grace period. */ } EXPORT_SYMBOL_GPL(synchronize_rcu_expedited); -- cgit v1.2.3 From 704dd435ac7eaefa89fcd82fd2876b8330e00ff3 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sat, 27 Jun 2015 09:36:29 -0700 Subject: rcu: Consolidate last open-coded expedited memory barrier One of the requirements on RCU grace periods is that if there is a causal chain of operations that starts after one grace period and ends before another grace period, then the two grace periods must be serialized. There has been (and might still be) code that relies on this, for example, certain types of reference-counting code that does a call_rcu() within an RCU callback function. This requirement is why there is an smp_mb() at the end of both synchronize_sched_expedited() and synchronize_rcu_expedited(). However, this is the only smp_mb() in these functions, so it would be nicer to consolidate it into rcu_exp_gp_seq_end(). This commit does just that. Signed-off-by: Paul E. McKenney --- kernel/rcu/tree_plugin.h | 1 - 1 file changed, 1 deletion(-) (limited to 'kernel/rcu/tree_plugin.h') diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index f0d71449ec0c..27b714601c6e 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -735,7 +735,6 @@ void synchronize_rcu_expedited(void) /* Clean up and exit. */ rcu_exp_gp_seq_end(rsp); mutex_unlock(&rnp_unlock->exp_funnel_mutex); - smp_mb(); /* ensure subsequent action seen after grace period. */ } EXPORT_SYMBOL_GPL(synchronize_rcu_expedited); -- cgit v1.2.3 From bc17ea1092c48227334a311a130c1a41966333fe Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sat, 6 Jun 2015 08:11:43 -0700 Subject: rcu: Fix obsolete priority-boosting comment Tasks are no longer migrated to the root rcu_node, so there is no longer any need for a boost kthread for the root rcu_node, and there no longer is such a kthread. This commit therefore fixes the comment in rcu_boost_kthread()'s header to reflect this new reality. Signed-off-by: Paul E. McKenney --- kernel/rcu/tree_plugin.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'kernel/rcu/tree_plugin.h') diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 013485fb2b06..a983bc68a146 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -1061,8 +1061,7 @@ static int rcu_boost(struct rcu_node *rnp) } /* - * Priority-boosting kthread. One per leaf rcu_node and one for the - * root rcu_node. + * Priority-boosting kthread, one per leaf rcu_node. */ static int rcu_boost_kthread(void *arg) { -- cgit v1.2.3 From f78f5b90c4ffa559e400c3919a02236101f29f3f Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 18 Jun 2015 15:50:02 -0700 Subject: rcu: Rename rcu_lockdep_assert() to RCU_LOCKDEP_WARN() This commit renames rcu_lockdep_assert() to RCU_LOCKDEP_WARN() for consistency with the WARN() series of macros. This also requires inverting the sense of the conditional, which this commit also does. Reported-by: Ingo Molnar Signed-off-by: Paul E. McKenney Reviewed-by: Ingo Molnar --- kernel/rcu/tree_plugin.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel/rcu/tree_plugin.h') diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index a983bc68a146..9e922f111d63 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -538,10 +538,10 @@ EXPORT_SYMBOL_GPL(call_rcu); */ void synchronize_rcu(void) { - rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map) && - !lock_is_held(&rcu_lock_map) && - !lock_is_held(&rcu_sched_lock_map), - "Illegal synchronize_rcu() in RCU read-side critical section"); + RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) || + lock_is_held(&rcu_lock_map) || + lock_is_held(&rcu_sched_lock_map), + "Illegal synchronize_rcu() in RCU read-side critical section"); if (!rcu_scheduler_active) return; if (rcu_gp_is_expedited()) -- cgit v1.2.3 From 9a54f98e341d09793247a6e598012edefb5ae7cb Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 14 Jul 2015 16:24:14 -0700 Subject: rcu: Don't disable CPU hotplug during OOM notifiers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit RCU's rcu_oom_notify() disables CPU hotplug in order to stabilize the list of online CPUs, which it traverses. However, this is completely pointless because smp_call_function_single() will quietly fail if invoked on an offline CPU. Because the count of requests is incremented in the rcu_oom_notify_cpu() function that is remotely invoked, everything works nicely even in the face of concurrent CPU-hotplug operations. Furthermore, in recent kernels, invoking get_online_cpus() from an OOM notifier can result in deadlock. This commit therefore removes the call to get_online_cpus() and put_online_cpus() from rcu_oom_notify(). Reported-by: Marcin Ślusarz Reported-by: David Rientjes Signed-off-by: Paul E. McKenney Acked-by: David Rientjes Tested-by: Marcin Ślusarz --- kernel/rcu/tree_plugin.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'kernel/rcu/tree_plugin.h') diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 9e922f111d63..80a7c17907fe 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -1679,12 +1679,10 @@ static int rcu_oom_notify(struct notifier_block *self, */ atomic_set(&oom_callback_count, 1); - get_online_cpus(); for_each_online_cpu(cpu) { smp_call_function_single(cpu, rcu_oom_notify_cpu, NULL, 1); cond_resched_rcu_qs(); } - put_online_cpus(); /* Unconditionally decrement: no need to wake ourselves up. */ atomic_dec(&oom_callback_count); -- cgit v1.2.3