From dbe01350fa8ce0c11948ab7d6be71a4d901be151 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 10 Nov 2009 13:37:19 -0800 Subject: rcu: Remove inline from forward-referenced functions Some variants of gcc are reputed to dislike forward references to functions declared "inline". Remove the "inline" keyword from such functions. Signed-off-by: Paul E. McKenney Cc: laijs@cn.fujitsu.com Cc: dipankar@in.ibm.com Cc: mathieu.desnoyers@polymtl.ca Cc: josh@joshtriplett.org Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org Cc: Valdis.Kletnieks@vt.edu Cc: dhowells@redhat.com LKML-Reference: <12578890422402-git-send-email-> Signed-off-by: Ingo Molnar --- kernel/rcutree_plugin.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/rcutree_plugin.h') diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index ef2a58c2b9d..c03edf76635 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -33,7 +33,7 @@ DEFINE_PER_CPU(struct rcu_data, rcu_preempt_data); /* * Tell them what RCU they are running. */ -static inline void rcu_bootup_announce(void) +static void rcu_bootup_announce(void) { printk(KERN_INFO "Experimental preemptable hierarchical RCU implementation.\n"); @@ -481,7 +481,7 @@ void exit_rcu(void) /* * Tell them what RCU they are running. */ -static inline void rcu_bootup_announce(void) +static void rcu_bootup_announce(void) { printk(KERN_INFO "Hierarchical RCU implementation.\n"); } -- cgit v1.2.3-70-g09d2 From c64ac3ce06558e534aec62b1fadeb0a3f111dac1 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 10 Nov 2009 13:37:22 -0800 Subject: rcu: Simplify association of quiescent states with grace periods The rdp->passed_quiesc_completed fields are used to properly associate the recorded quiescent state with a grace period. It is OK to wrongly associate a given quiescent state with a preceding grace period, but it is fatal to associate a given quiescent state with a grace period that begins after the quiescent state occurred. Grace periods are numbered, and the following fields track them: o ->gpnum is the number of the grace period currently in progress, or the number of the last grace period to complete if no grace period is currently in progress. o ->completed is the number of the last grace period to have completed. These two fields are equal if there is no grace period in progress, otherwise ->gpnum is one greater than ->completed. But the rdp->passed_quiesc_completed field compared against ->completed, and if equal, the quiescent state is presumed to count against the current grace period. The earlier code copied rdp->completed to rdp->passed_quiesc_completed, which has been made to work, but is error-prone. In contrast, copying one less than rdp->gpnum is guaranteed safe, because rdp->gpnum is not incremented until after the start of the corresponding grace period. At the end of the grace period, when ->completed has incremented, then any quiescent periods recorded previously will be discarded. Signed-off-by: Paul E. McKenney Cc: laijs@cn.fujitsu.com Cc: dipankar@in.ibm.com Cc: mathieu.desnoyers@polymtl.ca Cc: josh@joshtriplett.org Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org Cc: Valdis.Kletnieks@vt.edu Cc: dhowells@redhat.com LKML-Reference: <12578890421011-git-send-email-> Signed-off-by: Ingo Molnar --- kernel/rcutree.c | 4 ++-- kernel/rcutree_plugin.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel/rcutree_plugin.h') diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 26fc7807761..d8024192c73 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -100,7 +100,7 @@ void rcu_sched_qs(int cpu) struct rcu_data *rdp; rdp = &per_cpu(rcu_sched_data, cpu); - rdp->passed_quiesc_completed = rdp->completed; + rdp->passed_quiesc_completed = rdp->gpnum - 1; barrier(); rdp->passed_quiesc = 1; rcu_preempt_note_context_switch(cpu); @@ -111,7 +111,7 @@ void rcu_bh_qs(int cpu) struct rcu_data *rdp; rdp = &per_cpu(rcu_bh_data, cpu); - rdp->passed_quiesc_completed = rdp->completed; + rdp->passed_quiesc_completed = rdp->gpnum - 1; barrier(); rdp->passed_quiesc = 1; } diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index c03edf76635..52075da7054 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -67,7 +67,7 @@ EXPORT_SYMBOL_GPL(rcu_batches_completed); static void rcu_preempt_qs(int cpu) { struct rcu_data *rdp = &per_cpu(rcu_preempt_data, cpu); - rdp->passed_quiesc_completed = rdp->completed; + rdp->passed_quiesc_completed = rdp->gpnum - 1; barrier(); rdp->passed_quiesc = 1; } -- cgit v1.2.3-70-g09d2 From 0e0fc1c23e04c15e814763f2b366e92d87d8b95d Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 11 Nov 2009 11:28:06 -0800 Subject: rcu: Mark init-time-only rcu_bootup_announce() as __init Because rcu_bootup_announce() is used only at boot time, mark it as __init, presumably so that its memory can be reclaimed. Suggested-by: Joe Perches Signed-off-by: Paul E. McKenney Cc: laijs@cn.fujitsu.com Cc: dipankar@in.ibm.com Cc: mathieu.desnoyers@polymtl.ca Cc: josh@joshtriplett.org Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org Cc: Valdis.Kletnieks@vt.edu Cc: dhowells@redhat.com LKML-Reference: <20091111192806.GA10073@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar --- kernel/rcutree_plugin.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/rcutree_plugin.h') diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index 52075da7054..5ca2d26c597 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -33,7 +33,7 @@ DEFINE_PER_CPU(struct rcu_data, rcu_preempt_data); /* * Tell them what RCU they are running. */ -static void rcu_bootup_announce(void) +static void __init rcu_bootup_announce(void) { printk(KERN_INFO "Experimental preemptable hierarchical RCU implementation.\n"); @@ -481,7 +481,7 @@ void exit_rcu(void) /* * Tell them what RCU they are running. */ -static void rcu_bootup_announce(void) +static void __init rcu_bootup_announce(void) { printk(KERN_INFO "Hierarchical RCU implementation.\n"); } -- cgit v1.2.3-70-g09d2 From b668c9cf3e58739dac54a1d6f42f2b4bdd980b3e Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sun, 22 Nov 2009 08:53:48 -0800 Subject: rcu: Fix grace-period-stall bug on large systems with CPU hotplug When the last CPU of a given leaf rcu_node structure goes offline, all of the tasks queued on that leaf rcu_node structure (due to having blocked in their current RCU read-side critical sections) are requeued onto the root rcu_node structure. This requeuing is carried out by rcu_preempt_offline_tasks(). However, it is possible that these queued tasks are the only thing preventing the leaf rcu_node structure from reporting a quiescent state up the rcu_node hierarchy. Unfortunately, the old code would fail to do this reporting, resulting in a grace-period stall given the following sequence of events: 1. Kernel built for more than 32 CPUs on 32-bit systems or for more than 64 CPUs on 64-bit systems, so that there is more than one rcu_node structure. (Or CONFIG_RCU_FANOUT is artificially set to a number smaller than CONFIG_NR_CPUS.) 2. The kernel is built with CONFIG_TREE_PREEMPT_RCU. 3. A task running on a CPU associated with a given leaf rcu_node structure blocks while in an RCU read-side critical section -and- that CPU has not yet passed through a quiescent state for the current RCU grace period. This will cause the task to be queued on the leaf rcu_node's blocked_tasks[] array, in particular, on the element of this array corresponding to the current grace period. 4. Each of the remaining CPUs corresponding to this same leaf rcu_node structure pass through a quiescent state. However, the task is still in its RCU read-side critical section, so these quiescent states cannot be reported further up the rcu_node hierarchy. Nevertheless, all bits in the leaf rcu_node structure's ->qsmask field are now zero. 5. Each of the remaining CPUs go offline. (The events in step #4 and #5 can happen in any order as long as each CPU passes through a quiescent state before going offline.) 6. When the last CPU goes offline, __rcu_offline_cpu() will invoke rcu_preempt_offline_tasks(), which will move the task to the root rcu_node structure, but without reporting a quiescent state up the rcu_node hierarchy (and this failure to report a quiescent state is the bug). But because this leaf rcu_node structure's ->qsmask field is already zero and its ->block_tasks[] entries are all empty, force_quiescent_state() will skip this rcu_node structure. Therefore, grace periods are now hung. This patch abstracts some code out of rcu_read_unlock_special(), calling the result task_quiet() by analogy with cpu_quiet(), and invokes task_quiet() from both rcu_read_lock_special() and __rcu_offline_cpu(). Invoking task_quiet() from __rcu_offline_cpu() reports the quiescent state up the rcu_node hierarchy, fixing the bug. This ends up requiring a separate lock_class_key per level of the rcu_node hierarchy, which this patch also provides. Signed-off-by: Paul E. McKenney Cc: laijs@cn.fujitsu.com Cc: dipankar@in.ibm.com Cc: mathieu.desnoyers@polymtl.ca Cc: josh@joshtriplett.org Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org Cc: Valdis.Kletnieks@vt.edu Cc: dhowells@redhat.com LKML-Reference: <12589088301770-git-send-email-> Signed-off-by: Ingo Molnar --- kernel/rcutree.c | 40 ++++++++++++----------- kernel/rcutree.h | 3 ++ kernel/rcutree_plugin.h | 85 +++++++++++++++++++++++++++++++++++-------------- 3 files changed, 85 insertions(+), 43 deletions(-) (limited to 'kernel/rcutree_plugin.h') diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 9b36d6d7fb9..b79bfcd28e9 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -51,7 +51,7 @@ /* Data structures. */ -static struct lock_class_key rcu_root_class; +static struct lock_class_key rcu_node_class[NUM_RCU_LVLS]; #define RCU_STATE_INITIALIZER(name) { \ .level = { &name.node[0] }, \ @@ -936,6 +936,7 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp) { unsigned long flags; unsigned long mask; + int need_quiet = 0; struct rcu_data *rdp = rsp->rda[cpu]; struct rcu_node *rnp; @@ -949,29 +950,30 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp) spin_lock(&rnp->lock); /* irqs already disabled. */ rnp->qsmaskinit &= ~mask; if (rnp->qsmaskinit != 0) { - spin_unlock(&rnp->lock); /* irqs remain disabled. */ + if (rnp != rdp->mynode) + spin_unlock(&rnp->lock); /* irqs remain disabled. */ break; } - - /* - * If there was a task blocking the current grace period, - * and if all CPUs have checked in, we need to propagate - * the quiescent state up the rcu_node hierarchy. But that - * is inconvenient at the moment due to deadlock issues if - * this should end the current grace period. So set the - * offlined CPU's bit in ->qsmask in order to force the - * next force_quiescent_state() invocation to clean up this - * mess in a deadlock-free manner. - */ - if (rcu_preempt_offline_tasks(rsp, rnp, rdp) && !rnp->qsmask) - rnp->qsmask |= mask; - + if (rnp == rdp->mynode) + need_quiet = rcu_preempt_offline_tasks(rsp, rnp, rdp); + else + spin_unlock(&rnp->lock); /* irqs remain disabled. */ mask = rnp->grpmask; - spin_unlock(&rnp->lock); /* irqs remain disabled. */ rnp = rnp->parent; } while (rnp != NULL); - spin_unlock_irqrestore(&rsp->onofflock, flags); + /* + * We still hold the leaf rcu_node structure lock here, and + * irqs are still disabled. The reason for this subterfuge is + * because invoking task_quiet() with ->onofflock held leads + * to deadlock. + */ + spin_unlock(&rsp->onofflock); /* irqs remain disabled. */ + rnp = rdp->mynode; + if (need_quiet) + task_quiet(rnp, flags); + else + spin_unlock_irqrestore(&rnp->lock, flags); rcu_adopt_orphan_cbs(rsp); } @@ -1731,6 +1733,7 @@ static void __init rcu_init_one(struct rcu_state *rsp) rnp = rsp->level[i]; for (j = 0; j < rsp->levelcnt[i]; j++, rnp++) { spin_lock_init(&rnp->lock); + lockdep_set_class(&rnp->lock, &rcu_node_class[i]); rnp->gpnum = 0; rnp->qsmask = 0; rnp->qsmaskinit = 0; @@ -1753,7 +1756,6 @@ static void __init rcu_init_one(struct rcu_state *rsp) INIT_LIST_HEAD(&rnp->blocked_tasks[1]); } } - lockdep_set_class(&rcu_get_root(rsp)->lock, &rcu_root_class); } /* diff --git a/kernel/rcutree.h b/kernel/rcutree.h index 17a28a08b55..a81188c4292 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -305,6 +305,9 @@ static void rcu_bootup_announce(void); long rcu_batches_completed(void); static void rcu_preempt_note_context_switch(int cpu); static int rcu_preempted_readers(struct rcu_node *rnp); +#ifdef CONFIG_HOTPLUG_CPU +static void task_quiet(struct rcu_node *rnp, unsigned long flags); +#endif /* #ifdef CONFIG_HOTPLUG_CPU */ #ifdef CONFIG_RCU_CPU_STALL_DETECTOR static void rcu_print_task_stall(struct rcu_node *rnp); #endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */ diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index 5ca2d26c597..0bdb592eee6 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -160,11 +160,51 @@ static int rcu_preempted_readers(struct rcu_node *rnp) return !list_empty(&rnp->blocked_tasks[rnp->gpnum & 0x1]); } +/* + * Record a quiescent state for all tasks that were previously queued + * on the specified rcu_node structure and that were blocking the current + * RCU grace period. The caller must hold the specified rnp->lock with + * irqs disabled, and this lock is released upon return, but irqs remain + * disabled. + */ +static void task_quiet(struct rcu_node *rnp, unsigned long flags) + __releases(rnp->lock) +{ + unsigned long mask; + struct rcu_node *rnp_p; + + if (rnp->qsmask != 0 || rcu_preempted_readers(rnp)) { + spin_unlock_irqrestore(&rnp->lock, flags); + return; /* Still need more quiescent states! */ + } + + rnp_p = rnp->parent; + if (rnp_p == NULL) { + /* + * Either there is only one rcu_node in the tree, + * or tasks were kicked up to root rcu_node due to + * CPUs going offline. + */ + cpu_quiet_msk_finish(&rcu_preempt_state, flags); + return; + } + + /* Report up the rest of the hierarchy. */ + mask = rnp->grpmask; + spin_unlock(&rnp->lock); /* irqs remain disabled. */ + spin_lock(&rnp_p->lock); /* irqs already disabled. */ + cpu_quiet_msk(mask, &rcu_preempt_state, rnp_p, flags); +} + +/* + * Handle special cases during rcu_read_unlock(), such as needing to + * notify RCU core processing or task having blocked during the RCU + * read-side critical section. + */ static void rcu_read_unlock_special(struct task_struct *t) { int empty; unsigned long flags; - unsigned long mask; struct rcu_node *rnp; int special; @@ -213,30 +253,15 @@ static void rcu_read_unlock_special(struct task_struct *t) /* * If this was the last task on the current list, and if * we aren't waiting on any CPUs, report the quiescent state. - * Note that both cpu_quiet_msk_finish() and cpu_quiet_msk() - * drop rnp->lock and restore irq. + * Note that task_quiet() releases rnp->lock. */ - if (!empty && rnp->qsmask == 0 && - !rcu_preempted_readers(rnp)) { - struct rcu_node *rnp_p; - - if (rnp->parent == NULL) { - /* Only one rcu_node in the tree. */ - cpu_quiet_msk_finish(&rcu_preempt_state, flags); - return; - } - /* Report up the rest of the hierarchy. */ - mask = rnp->grpmask; + if (empty) spin_unlock_irqrestore(&rnp->lock, flags); - rnp_p = rnp->parent; - spin_lock_irqsave(&rnp_p->lock, flags); - WARN_ON_ONCE(rnp->qsmask); - cpu_quiet_msk(mask, &rcu_preempt_state, rnp_p, flags); - return; - } - spin_unlock(&rnp->lock); + else + task_quiet(rnp, flags); + } else { + local_irq_restore(flags); } - local_irq_restore(flags); } /* @@ -303,6 +328,8 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp) * rcu_node. The reason for not just moving them to the immediate * parent is to remove the need for rcu_read_unlock_special() to * make more than two attempts to acquire the target rcu_node's lock. + * Returns true if there were tasks blocking the current RCU grace + * period. * * Returns 1 if there was previously a task blocking the current grace * period on the specified rcu_node structure. @@ -316,7 +343,7 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp, int i; struct list_head *lp; struct list_head *lp_root; - int retval = rcu_preempted_readers(rnp); + int retval; struct rcu_node *rnp_root = rcu_get_root(rsp); struct task_struct *tp; @@ -334,6 +361,7 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp, * rcu_nodes in terms of gp_num value. This fact allows us to * move the blocked_tasks[] array directly, element by element. */ + retval = rcu_preempted_readers(rnp); for (i = 0; i < 2; i++) { lp = &rnp->blocked_tasks[i]; lp_root = &rnp_root->blocked_tasks[i]; @@ -346,7 +374,6 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp, spin_unlock(&rnp_root->lock); /* irqs remain disabled */ } } - return retval; } @@ -512,6 +539,16 @@ static int rcu_preempted_readers(struct rcu_node *rnp) return 0; } +#ifdef CONFIG_HOTPLUG_CPU + +/* Because preemptible RCU does not exist, no quieting of tasks. */ +static void task_quiet(struct rcu_node *rnp, unsigned long flags) +{ + spin_unlock_irqrestore(&rnp->lock, flags); +} + +#endif /* #ifdef CONFIG_HOTPLUG_CPU */ + #ifdef CONFIG_RCU_CPU_STALL_DETECTOR /* -- cgit v1.2.3-70-g09d2 From 6ebb237bece23275d1da149b61a342f0d4d06a08 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sun, 22 Nov 2009 08:53:50 -0800 Subject: rcu: Re-arrange code to reduce #ifdef pain Remove #ifdefs from kernel/rcupdate.c and include/linux/rcupdate.h by moving code to include/linux/rcutiny.h, include/linux/rcutree.h, and kernel/rcutree.c. Also remove some definitions that are no longer used. Signed-off-by: Paul E. McKenney Cc: laijs@cn.fujitsu.com Cc: dipankar@in.ibm.com Cc: mathieu.desnoyers@polymtl.ca Cc: josh@joshtriplett.org Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org Cc: Valdis.Kletnieks@vt.edu Cc: dhowells@redhat.com LKML-Reference: <1258908830885-git-send-email-> Signed-off-by: Ingo Molnar --- include/linux/rcupdate.h | 12 ------ include/linux/rcutiny.h | 11 +++++ include/linux/rcutree.h | 4 +- kernel/rcupdate.c | 104 ----------------------------------------------- kernel/rcutree.c | 80 ++++++++++++++++++++++++++++++++++++ kernel/rcutree_plugin.h | 24 +++++++++++ 6 files changed, 118 insertions(+), 117 deletions(-) (limited to 'kernel/rcutree_plugin.h') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 2f1bc42a3b8..24440f4bf47 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -52,11 +52,6 @@ struct rcu_head { }; /* Exported common interfaces */ -#ifdef CONFIG_TREE_PREEMPT_RCU -extern void synchronize_rcu(void); -#else /* #ifdef CONFIG_TREE_PREEMPT_RCU */ -#define synchronize_rcu synchronize_sched -#endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */ extern void synchronize_rcu_bh(void); extern void synchronize_sched(void); extern void rcu_barrier(void); @@ -67,13 +62,6 @@ extern int sched_expedited_torture_stats(char *page); /* Internal to kernel */ extern void rcu_init(void); -extern void rcu_scheduler_starting(void); -#ifndef CONFIG_TINY_RCU -extern int rcu_needs_cpu(int cpu); -#else -static inline int rcu_needs_cpu(int cpu) { return 0; } -#endif -extern int rcu_scheduler_active; #if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU) #include diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index a3b6272af2d..c4ba9a78721 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -39,6 +39,11 @@ void rcu_bh_qs(int cpu); #define rcu_init_sched() do { } while (0) extern void rcu_check_callbacks(int cpu, int user); +static inline int rcu_needs_cpu(int cpu) +{ + return 0; +} + /* * Return the number of grace periods. */ @@ -57,6 +62,8 @@ static inline long rcu_batches_completed_bh(void) extern int rcu_expedited_torture_stats(char *page); +#define synchronize_rcu synchronize_sched + static inline void synchronize_rcu_expedited(void) { synchronize_sched(); @@ -86,6 +93,10 @@ static inline void rcu_exit_nohz(void) #endif /* #else #ifdef CONFIG_NO_HZ */ +static inline void rcu_scheduler_starting(void) +{ +} + static inline void exit_rcu(void) { } diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 111a6525735..c93eee5911b 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -35,12 +35,14 @@ struct notifier_block; extern void rcu_sched_qs(int cpu); extern void rcu_bh_qs(int cpu); extern int rcu_needs_cpu(int cpu); +extern void rcu_scheduler_starting(void); extern int rcu_expedited_torture_stats(char *page); #ifdef CONFIG_TREE_PREEMPT_RCU extern void __rcu_read_lock(void); extern void __rcu_read_unlock(void); +extern void synchronize_rcu(void); extern void exit_rcu(void); #else /* #ifdef CONFIG_TREE_PREEMPT_RCU */ @@ -55,7 +57,7 @@ static inline void __rcu_read_unlock(void) preempt_enable(); } -#define __synchronize_sched() synchronize_rcu() +#define synchronize_rcu synchronize_sched static inline void exit_rcu(void) { diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index eb6b534db31..9b7fd472387 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -44,7 +44,6 @@ #include #include #include -#include #ifdef CONFIG_DEBUG_LOCK_ALLOC static struct lock_class_key rcu_lock_key; @@ -53,8 +52,6 @@ struct lockdep_map rcu_lock_map = EXPORT_SYMBOL_GPL(rcu_lock_map); #endif -int rcu_scheduler_active __read_mostly; - /* * Awaken the corresponding synchronize_rcu() instance now that a * grace period has elapsed. @@ -66,104 +63,3 @@ void wakeme_after_rcu(struct rcu_head *head) rcu = container_of(head, struct rcu_synchronize, head); complete(&rcu->completion); } - -#ifndef CONFIG_TINY_RCU - -#ifdef CONFIG_TREE_PREEMPT_RCU - -/** - * synchronize_rcu - wait until a grace period has elapsed. - * - * Control will return to the caller some time after a full grace - * period has elapsed, in other words after all currently executing RCU - * read-side critical sections have completed. RCU read-side critical - * sections are delimited by rcu_read_lock() and rcu_read_unlock(), - * and may be nested. - */ -void synchronize_rcu(void) -{ - struct rcu_synchronize rcu; - - if (!rcu_scheduler_active) - return; - - init_completion(&rcu.completion); - /* Will wake me after RCU finished. */ - call_rcu(&rcu.head, wakeme_after_rcu); - /* Wait for it. */ - wait_for_completion(&rcu.completion); -} -EXPORT_SYMBOL_GPL(synchronize_rcu); - -#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ - -/** - * synchronize_sched - wait until an rcu-sched grace period has elapsed. - * - * Control will return to the caller some time after a full rcu-sched - * grace period has elapsed, in other words after all currently executing - * rcu-sched read-side critical sections have completed. These read-side - * critical sections are delimited by rcu_read_lock_sched() and - * rcu_read_unlock_sched(), and may be nested. Note that preempt_disable(), - * local_irq_disable(), and so on may be used in place of - * rcu_read_lock_sched(). - * - * This means that all preempt_disable code sequences, including NMI and - * hardware-interrupt handlers, in progress on entry will have completed - * before this primitive returns. However, this does not guarantee that - * softirq handlers will have completed, since in some kernels, these - * handlers can run in process context, and can block. - * - * This primitive provides the guarantees made by the (now removed) - * synchronize_kernel() API. In contrast, synchronize_rcu() only - * guarantees that rcu_read_lock() sections will have completed. - * In "classic RCU", these two guarantees happen to be one and - * the same, but can differ in realtime RCU implementations. - */ -void synchronize_sched(void) -{ - struct rcu_synchronize rcu; - - if (rcu_blocking_is_gp()) - return; - - init_completion(&rcu.completion); - /* Will wake me after RCU finished. */ - call_rcu_sched(&rcu.head, wakeme_after_rcu); - /* Wait for it. */ - wait_for_completion(&rcu.completion); -} -EXPORT_SYMBOL_GPL(synchronize_sched); - -/** - * synchronize_rcu_bh - wait until an rcu_bh grace period has elapsed. - * - * Control will return to the caller some time after a full rcu_bh grace - * period has elapsed, in other words after all currently executing rcu_bh - * read-side critical sections have completed. RCU read-side critical - * sections are delimited by rcu_read_lock_bh() and rcu_read_unlock_bh(), - * and may be nested. - */ -void synchronize_rcu_bh(void) -{ - struct rcu_synchronize rcu; - - if (rcu_blocking_is_gp()) - return; - - init_completion(&rcu.completion); - /* Will wake me after RCU finished. */ - call_rcu_bh(&rcu.head, wakeme_after_rcu); - /* Wait for it. */ - wait_for_completion(&rcu.completion); -} -EXPORT_SYMBOL_GPL(synchronize_rcu_bh); - -#endif /* #ifndef CONFIG_TINY_RCU */ - -void rcu_scheduler_starting(void) -{ - WARN_ON(num_online_cpus() != 1); - WARN_ON(nr_context_switches() > 0); - rcu_scheduler_active = 1; -} diff --git a/kernel/rcutree.c b/kernel/rcutree.c index e3d3bbddbcd..4ca7e0292fd 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -46,6 +46,7 @@ #include #include #include +#include #include "rcutree.h" @@ -79,6 +80,8 @@ DEFINE_PER_CPU(struct rcu_data, rcu_sched_data); struct rcu_state rcu_bh_state = RCU_STATE_INITIALIZER(rcu_bh_state); DEFINE_PER_CPU(struct rcu_data, rcu_bh_data); +static int rcu_scheduler_active __read_mostly; + /* * Return true if an RCU grace period is in progress. The ACCESS_ONCE()s @@ -1396,6 +1399,68 @@ void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) } EXPORT_SYMBOL_GPL(call_rcu_bh); +/** + * synchronize_sched - wait until an rcu-sched grace period has elapsed. + * + * Control will return to the caller some time after a full rcu-sched + * grace period has elapsed, in other words after all currently executing + * rcu-sched read-side critical sections have completed. These read-side + * critical sections are delimited by rcu_read_lock_sched() and + * rcu_read_unlock_sched(), and may be nested. Note that preempt_disable(), + * local_irq_disable(), and so on may be used in place of + * rcu_read_lock_sched(). + * + * This means that all preempt_disable code sequences, including NMI and + * hardware-interrupt handlers, in progress on entry will have completed + * before this primitive returns. However, this does not guarantee that + * softirq handlers will have completed, since in some kernels, these + * handlers can run in process context, and can block. + * + * This primitive provides the guarantees made by the (now removed) + * synchronize_kernel() API. In contrast, synchronize_rcu() only + * guarantees that rcu_read_lock() sections will have completed. + * In "classic RCU", these two guarantees happen to be one and + * the same, but can differ in realtime RCU implementations. + */ +void synchronize_sched(void) +{ + struct rcu_synchronize rcu; + + if (rcu_blocking_is_gp()) + return; + + init_completion(&rcu.completion); + /* Will wake me after RCU finished. */ + call_rcu_sched(&rcu.head, wakeme_after_rcu); + /* Wait for it. */ + wait_for_completion(&rcu.completion); +} +EXPORT_SYMBOL_GPL(synchronize_sched); + +/** + * synchronize_rcu_bh - wait until an rcu_bh grace period has elapsed. + * + * Control will return to the caller some time after a full rcu_bh grace + * period has elapsed, in other words after all currently executing rcu_bh + * read-side critical sections have completed. RCU read-side critical + * sections are delimited by rcu_read_lock_bh() and rcu_read_unlock_bh(), + * and may be nested. + */ +void synchronize_rcu_bh(void) +{ + struct rcu_synchronize rcu; + + if (rcu_blocking_is_gp()) + return; + + init_completion(&rcu.completion); + /* Will wake me after RCU finished. */ + call_rcu_bh(&rcu.head, wakeme_after_rcu); + /* Wait for it. */ + wait_for_completion(&rcu.completion); +} +EXPORT_SYMBOL_GPL(synchronize_rcu_bh); + /* * Check to see if there is any immediate RCU-related work to be done * by the current CPU, for the specified type of RCU, returning 1 if so. @@ -1480,6 +1545,21 @@ int rcu_needs_cpu(int cpu) rcu_preempt_needs_cpu(cpu); } +/* + * This function is invoked towards the end of the scheduler's initialization + * process. Before this is called, the idle task might contain + * RCU read-side critical sections (during which time, this idle + * task is booting the system). After this function is called, the + * idle tasks are prohibited from containing RCU read-side critical + * sections. + */ +void rcu_scheduler_starting(void) +{ + WARN_ON(num_online_cpus() != 1); + WARN_ON(nr_context_switches() > 0); + rcu_scheduler_active = 1; +} + static DEFINE_PER_CPU(struct rcu_head, rcu_barrier_head) = {NULL}; static atomic_t rcu_barrier_cpu_count; static DEFINE_MUTEX(rcu_barrier_mutex); diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index 0bdb592eee6..1d295c789d3 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -425,6 +425,30 @@ void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) } EXPORT_SYMBOL_GPL(call_rcu); +/** + * synchronize_rcu - wait until a grace period has elapsed. + * + * Control will return to the caller some time after a full grace + * period has elapsed, in other words after all currently executing RCU + * read-side critical sections have completed. RCU read-side critical + * sections are delimited by rcu_read_lock() and rcu_read_unlock(), + * and may be nested. + */ +void synchronize_rcu(void) +{ + struct rcu_synchronize rcu; + + if (!rcu_scheduler_active) + return; + + init_completion(&rcu.completion); + /* Will wake me after RCU finished. */ + call_rcu(&rcu.head, wakeme_after_rcu); + /* Wait for it. */ + wait_for_completion(&rcu.completion); +} +EXPORT_SYMBOL_GPL(synchronize_rcu); + /* * Wait for an rcu-preempt grace period. We are supposed to expedite the * grace period, but this is the crude slow compatability hack, so just -- cgit v1.2.3-70-g09d2 From d3f6bad3911736e44ba11f3f3f6ac4e8c837fdfc Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 2 Dec 2009 12:10:13 -0800 Subject: rcu: Rename "quiet" functions The number of "quiet" functions has grown recently, and the names are no longer very descriptive. The point of all of these functions is to do some portion of the task of reporting a quiescent state, so rename them accordingly: o cpu_quiet() becomes rcu_report_qs_rdp(), which reports a quiescent state to the per-CPU rcu_data structure. If this turns out to be a new quiescent state for this grace period, then rcu_report_qs_rnp() will be invoked to propagate the quiescent state up the rcu_node hierarchy. o cpu_quiet_msk() becomes rcu_report_qs_rnp(), which reports a quiescent state for a given CPU (or possibly a set of CPUs) up the rcu_node hierarchy. o cpu_quiet_msk_finish() becomes rcu_report_qs_rsp(), which reports a full set of quiescent states to the global rcu_state structure. o task_quiet() becomes rcu_report_unblock_qs_rnp(), which reports a quiescent state due to a task exiting an RCU read-side critical section that had previously blocked in that same critical section. As indicated by the new name, this type of quiescent state is reported up the rcu_node hierarchy (using rcu_report_qs_rnp() to do so). Signed-off-by: Paul E. McKenney Acked-by: Josh Triplett Acked-by: Lai Jiangshan Cc: dipankar@in.ibm.com Cc: mathieu.desnoyers@polymtl.ca Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org Cc: Valdis.Kletnieks@vt.edu Cc: dhowells@redhat.com LKML-Reference: <12597846163698-git-send-email-> Signed-off-by: Ingo Molnar --- kernel/rcutree.c | 66 +++++++++++++++++++++++++++---------------------- kernel/rcutree.h | 3 ++- kernel/rcutree_plugin.h | 12 ++++----- 3 files changed, 45 insertions(+), 36 deletions(-) (limited to 'kernel/rcutree_plugin.h') diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 4ca7e0292fd..a9f51031d3e 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -740,11 +740,13 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags) } /* - * Clean up after the prior grace period and let rcu_start_gp() start up - * the next grace period if one is needed. Note that the caller must - * hold rnp->lock, as required by rcu_start_gp(), which will release it. + * Report a full set of quiescent states to the specified rcu_state + * data structure. This involves cleaning up after the prior grace + * period and letting rcu_start_gp() start up the next grace period + * if one is needed. Note that the caller must hold rnp->lock, as + * required by rcu_start_gp(), which will release it. */ -static void cpu_quiet_msk_finish(struct rcu_state *rsp, unsigned long flags) +static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags) __releases(rcu_get_root(rsp)->lock) { WARN_ON_ONCE(!rcu_gp_in_progress(rsp)); @@ -754,15 +756,16 @@ static void cpu_quiet_msk_finish(struct rcu_state *rsp, unsigned long flags) } /* - * Similar to cpu_quiet(), for which it is a helper function. Allows - * a group of CPUs to be quieted at one go, though all the CPUs in the - * group must be represented by the same leaf rcu_node structure. - * That structure's lock must be held upon entry, and it is released - * before return. + * Similar to rcu_report_qs_rdp(), for which it is a helper function. + * Allows quiescent states for a group of CPUs to be reported at one go + * to the specified rcu_node structure, though all the CPUs in the group + * must be represented by the same rcu_node structure (which need not be + * a leaf rcu_node structure, though it often will be). That structure's + * lock must be held upon entry, and it is released before return. */ static void -cpu_quiet_msk(unsigned long mask, struct rcu_state *rsp, struct rcu_node *rnp, - unsigned long flags) +rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, + struct rcu_node *rnp, unsigned long flags) __releases(rnp->lock) { struct rcu_node *rnp_c; @@ -798,21 +801,23 @@ cpu_quiet_msk(unsigned long mask, struct rcu_state *rsp, struct rcu_node *rnp, /* * Get here if we are the last CPU to pass through a quiescent - * state for this grace period. Invoke cpu_quiet_msk_finish() + * state for this grace period. Invoke rcu_report_qs_rsp() * to clean up and start the next grace period if one is needed. */ - cpu_quiet_msk_finish(rsp, flags); /* releases rnp->lock. */ + rcu_report_qs_rsp(rsp, flags); /* releases rnp->lock. */ } /* - * Record a quiescent state for the specified CPU, which must either be - * the current CPU. The lastcomp argument is used to make sure we are - * still in the grace period of interest. We don't want to end the current - * grace period based on quiescent states detected in an earlier grace - * period! + * Record a quiescent state for the specified CPU to that CPU's rcu_data + * structure. This must be either called from the specified CPU, or + * called when the specified CPU is known to be offline (and when it is + * also known that no other CPU is concurrently trying to help the offline + * CPU). The lastcomp argument is used to make sure we are still in the + * grace period of interest. We don't want to end the current grace period + * based on quiescent states detected in an earlier grace period! */ static void -cpu_quiet(int cpu, struct rcu_state *rsp, struct rcu_data *rdp, long lastcomp) +rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp, long lastcomp) { unsigned long flags; unsigned long mask; @@ -827,8 +832,8 @@ cpu_quiet(int cpu, struct rcu_state *rsp, struct rcu_data *rdp, long lastcomp) * The race with GP start is resolved by the fact that we * hold the leaf rcu_node lock, so that the per-CPU bits * cannot yet be initialized -- so we would simply find our - * CPU's bit already cleared in cpu_quiet_msk() if this race - * occurred. + * CPU's bit already cleared in rcu_report_qs_rnp() if this + * race occurred. */ rdp->passed_quiesc = 0; /* try again later! */ spin_unlock_irqrestore(&rnp->lock, flags); @@ -846,7 +851,7 @@ cpu_quiet(int cpu, struct rcu_state *rsp, struct rcu_data *rdp, long lastcomp) */ rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL]; - cpu_quiet_msk(mask, rsp, rnp, flags); /* releases rnp->lock */ + rcu_report_qs_rnp(mask, rsp, rnp, flags); /* rlses rnp->lock */ } } @@ -877,8 +882,11 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp) if (!rdp->passed_quiesc) return; - /* Tell RCU we are done (but cpu_quiet() will be the judge of that). */ - cpu_quiet(rdp->cpu, rsp, rdp, rdp->passed_quiesc_completed); + /* + * Tell RCU we are done (but rcu_report_qs_rdp() will be the + * judge of that). + */ + rcu_report_qs_rdp(rdp->cpu, rsp, rdp, rdp->passed_quiesc_completed); } #ifdef CONFIG_HOTPLUG_CPU @@ -968,13 +976,13 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp) /* * We still hold the leaf rcu_node structure lock here, and * irqs are still disabled. The reason for this subterfuge is - * because invoking task_quiet() with ->onofflock held leads - * to deadlock. + * because invoking rcu_report_unblock_qs_rnp() with ->onofflock + * held leads to deadlock. */ spin_unlock(&rsp->onofflock); /* irqs remain disabled. */ rnp = rdp->mynode; if (need_quiet) - task_quiet(rnp, flags); + rcu_report_unblock_qs_rnp(rnp, flags); else spin_unlock_irqrestore(&rnp->lock, flags); @@ -1164,8 +1172,8 @@ static int rcu_process_dyntick(struct rcu_state *rsp, long lastcomp, } if (mask != 0 && rnp->completed == lastcomp) { - /* cpu_quiet_msk() releases rnp->lock. */ - cpu_quiet_msk(mask, rsp, rnp, flags); + /* rcu_report_qs_rnp() releases rnp->lock. */ + rcu_report_qs_rnp(mask, rsp, rnp, flags); continue; } spin_unlock_irqrestore(&rnp->lock, flags); diff --git a/kernel/rcutree.h b/kernel/rcutree.h index a81188c4292..8bb03cb0744 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -306,7 +306,8 @@ long rcu_batches_completed(void); static void rcu_preempt_note_context_switch(int cpu); static int rcu_preempted_readers(struct rcu_node *rnp); #ifdef CONFIG_HOTPLUG_CPU -static void task_quiet(struct rcu_node *rnp, unsigned long flags); +static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, + unsigned long flags); #endif /* #ifdef CONFIG_HOTPLUG_CPU */ #ifdef CONFIG_RCU_CPU_STALL_DETECTOR static void rcu_print_task_stall(struct rcu_node *rnp); diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index 1d295c789d3..c9f0c975c00 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -167,7 +167,7 @@ static int rcu_preempted_readers(struct rcu_node *rnp) * irqs disabled, and this lock is released upon return, but irqs remain * disabled. */ -static void task_quiet(struct rcu_node *rnp, unsigned long flags) +static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags) __releases(rnp->lock) { unsigned long mask; @@ -185,7 +185,7 @@ static void task_quiet(struct rcu_node *rnp, unsigned long flags) * or tasks were kicked up to root rcu_node due to * CPUs going offline. */ - cpu_quiet_msk_finish(&rcu_preempt_state, flags); + rcu_report_qs_rsp(&rcu_preempt_state, flags); return; } @@ -193,7 +193,7 @@ static void task_quiet(struct rcu_node *rnp, unsigned long flags) mask = rnp->grpmask; spin_unlock(&rnp->lock); /* irqs remain disabled. */ spin_lock(&rnp_p->lock); /* irqs already disabled. */ - cpu_quiet_msk(mask, &rcu_preempt_state, rnp_p, flags); + rcu_report_qs_rnp(mask, &rcu_preempt_state, rnp_p, flags); } /* @@ -253,12 +253,12 @@ static void rcu_read_unlock_special(struct task_struct *t) /* * If this was the last task on the current list, and if * we aren't waiting on any CPUs, report the quiescent state. - * Note that task_quiet() releases rnp->lock. + * Note that rcu_report_unblock_qs_rnp() releases rnp->lock. */ if (empty) spin_unlock_irqrestore(&rnp->lock, flags); else - task_quiet(rnp, flags); + rcu_report_unblock_qs_rnp(rnp, flags); } else { local_irq_restore(flags); } @@ -566,7 +566,7 @@ static int rcu_preempted_readers(struct rcu_node *rnp) #ifdef CONFIG_HOTPLUG_CPU /* Because preemptible RCU does not exist, no quieting of tasks. */ -static void task_quiet(struct rcu_node *rnp, unsigned long flags) +static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags) { spin_unlock_irqrestore(&rnp->lock, flags); } -- cgit v1.2.3-70-g09d2 From d9a3da0699b24a589b27a61e1a5b5bd30d9db669 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 2 Dec 2009 12:10:15 -0800 Subject: rcu: Add expedited grace-period support for preemptible RCU Implement an synchronize_rcu_expedited() for preemptible RCU that actually is expedited. This uses synchronize_sched_expedited() to force all threads currently running in a preemptible-RCU read-side critical section onto the appropriate ->blocked_tasks[] list, then takes a snapshot of all of these lists and waits for them to drain. Signed-off-by: Paul E. McKenney Cc: laijs@cn.fujitsu.com Cc: dipankar@in.ibm.com Cc: mathieu.desnoyers@polymtl.ca Cc: josh@joshtriplett.org Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org Cc: Valdis.Kletnieks@vt.edu Cc: dhowells@redhat.com LKML-Reference: <1259784616158-git-send-email-> Signed-off-by: Ingo Molnar --- kernel/rcutorture.c | 34 ++++++--- kernel/rcutree.c | 10 ++- kernel/rcutree.h | 35 ++++++++- kernel/rcutree_plugin.h | 198 +++++++++++++++++++++++++++++++++++++++++++++--- kernel/rcutree_trace.c | 10 ++- 5 files changed, 260 insertions(+), 27 deletions(-) (limited to 'kernel/rcutree_plugin.h') diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index 3dd0ca23e19..a621a67ef4e 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -327,6 +327,11 @@ rcu_torture_cb(struct rcu_head *p) cur_ops->deferred_free(rp); } +static int rcu_no_completed(void) +{ + return 0; +} + static void rcu_torture_deferred_free(struct rcu_torture *p) { call_rcu(&p->rtort_rcu, rcu_torture_cb); @@ -388,6 +393,21 @@ static struct rcu_torture_ops rcu_sync_ops = { .name = "rcu_sync" }; +static struct rcu_torture_ops rcu_expedited_ops = { + .init = rcu_sync_torture_init, + .cleanup = NULL, + .readlock = rcu_torture_read_lock, + .read_delay = rcu_read_delay, /* just reuse rcu's version. */ + .readunlock = rcu_torture_read_unlock, + .completed = rcu_no_completed, + .deferred_free = rcu_sync_torture_deferred_free, + .sync = synchronize_rcu_expedited, + .cb_barrier = NULL, + .stats = NULL, + .irq_capable = 1, + .name = "rcu_expedited" +}; + /* * Definitions for rcu_bh torture testing. */ @@ -581,11 +601,6 @@ static void sched_torture_read_unlock(int idx) preempt_enable(); } -static int sched_torture_completed(void) -{ - return 0; -} - static void rcu_sched_torture_deferred_free(struct rcu_torture *p) { call_rcu_sched(&p->rtort_rcu, rcu_torture_cb); @@ -602,7 +617,7 @@ static struct rcu_torture_ops sched_ops = { .readlock = sched_torture_read_lock, .read_delay = rcu_read_delay, /* just reuse rcu's version. */ .readunlock = sched_torture_read_unlock, - .completed = sched_torture_completed, + .completed = rcu_no_completed, .deferred_free = rcu_sched_torture_deferred_free, .sync = sched_torture_synchronize, .cb_barrier = rcu_barrier_sched, @@ -617,7 +632,7 @@ static struct rcu_torture_ops sched_sync_ops = { .readlock = sched_torture_read_lock, .read_delay = rcu_read_delay, /* just reuse rcu's version. */ .readunlock = sched_torture_read_unlock, - .completed = sched_torture_completed, + .completed = rcu_no_completed, .deferred_free = rcu_sync_torture_deferred_free, .sync = sched_torture_synchronize, .cb_barrier = NULL, @@ -631,7 +646,7 @@ static struct rcu_torture_ops sched_expedited_ops = { .readlock = sched_torture_read_lock, .read_delay = rcu_read_delay, /* just reuse rcu's version. */ .readunlock = sched_torture_read_unlock, - .completed = sched_torture_completed, + .completed = rcu_no_completed, .deferred_free = rcu_sync_torture_deferred_free, .sync = synchronize_sched_expedited, .cb_barrier = NULL, @@ -1116,7 +1131,8 @@ rcu_torture_init(void) int cpu; int firsterr = 0; static struct rcu_torture_ops *torture_ops[] = - { &rcu_ops, &rcu_sync_ops, &rcu_bh_ops, &rcu_bh_sync_ops, + { &rcu_ops, &rcu_sync_ops, &rcu_expedited_ops, + &rcu_bh_ops, &rcu_bh_sync_ops, &srcu_ops, &srcu_expedited_ops, &sched_ops, &sched_sync_ops, &sched_expedited_ops, }; diff --git a/kernel/rcutree.c b/kernel/rcutree.c index d47e03e5792..53ae9598f79 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -948,7 +948,7 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp) { unsigned long flags; unsigned long mask; - int need_quiet = 0; + int need_report = 0; struct rcu_data *rdp = rsp->rda[cpu]; struct rcu_node *rnp; @@ -967,7 +967,7 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp) break; } if (rnp == rdp->mynode) - need_quiet = rcu_preempt_offline_tasks(rsp, rnp, rdp); + need_report = rcu_preempt_offline_tasks(rsp, rnp, rdp); else spin_unlock(&rnp->lock); /* irqs remain disabled. */ mask = rnp->grpmask; @@ -982,10 +982,12 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp) */ spin_unlock(&rsp->onofflock); /* irqs remain disabled. */ rnp = rdp->mynode; - if (need_quiet) + if (need_report & RCU_OFL_TASKS_NORM_GP) rcu_report_unblock_qs_rnp(rnp, flags); else spin_unlock_irqrestore(&rnp->lock, flags); + if (need_report & RCU_OFL_TASKS_EXP_GP) + rcu_report_exp_rnp(rsp, rnp); rcu_adopt_orphan_cbs(rsp); } @@ -1843,6 +1845,8 @@ static void __init rcu_init_one(struct rcu_state *rsp) rnp->level = i; INIT_LIST_HEAD(&rnp->blocked_tasks[0]); INIT_LIST_HEAD(&rnp->blocked_tasks[1]); + INIT_LIST_HEAD(&rnp->blocked_tasks[2]); + INIT_LIST_HEAD(&rnp->blocked_tasks[3]); } } } diff --git a/kernel/rcutree.h b/kernel/rcutree.h index df2e0b69474..d2a0046f63b 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -104,8 +104,12 @@ struct rcu_node { /* an rcu_data structure, otherwise, each */ /* bit corresponds to a child rcu_node */ /* structure. */ + unsigned long expmask; /* Groups that have ->blocked_tasks[] */ + /* elements that need to drain to allow the */ + /* current expedited grace period to */ + /* complete (only for TREE_PREEMPT_RCU). */ unsigned long qsmaskinit; - /* Per-GP initialization for qsmask. */ + /* Per-GP initial value for qsmask & expmask. */ 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. */ @@ -113,7 +117,7 @@ struct rcu_node { u8 grpnum; /* CPU/group number for next level up. */ u8 level; /* root is at level 0. */ struct rcu_node *parent; - struct list_head blocked_tasks[2]; + struct list_head blocked_tasks[4]; /* Tasks blocked in RCU read-side critsect. */ /* Grace period number (->gpnum) x blocked */ /* by tasks on the (x & 0x1) element of the */ @@ -128,6 +132,21 @@ struct rcu_node { for ((rnp) = &(rsp)->node[0]; \ (rnp) < &(rsp)->node[NUM_RCU_NODES]; (rnp)++) +/* + * Do a breadth-first scan of the non-leaf rcu_node structures for the + * specified rcu_state structure. Note that if there is a singleton + * rcu_node tree with but one rcu_node structure, this loop is a no-op. + */ +#define rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) \ + for ((rnp) = &(rsp)->node[0]; \ + (rnp) < (rsp)->level[NUM_RCU_LVLS - 1]; (rnp)++) + +/* + * Scan the leaves of the rcu_node hierarchy for the specified rcu_state + * structure. Note that if there is a singleton rcu_node tree with but + * one rcu_node structure, this loop -will- visit the rcu_node structure. + * It is still a leaf node, even if it is also the root node. + */ #define rcu_for_each_leaf_node(rsp, rnp) \ for ((rnp) = (rsp)->level[NUM_RCU_LVLS - 1]; \ (rnp) < &(rsp)->node[NUM_RCU_NODES]; (rnp)++) @@ -261,7 +280,7 @@ struct rcu_state { long gpnum; /* Current gp number. */ long completed; /* # of last completed gp. */ - /* End of fields guarded by root rcu_node's lock. */ + /* End of fields guarded by root rcu_node's lock. */ spinlock_t onofflock; /* exclude on/offline and */ /* starting new GP. Also */ @@ -293,6 +312,13 @@ struct rcu_state { #endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */ }; +/* Return values for rcu_preempt_offline_tasks(). */ + +#define RCU_OFL_TASKS_NORM_GP 0x1 /* Tasks blocking normal */ + /* GP were moved to root. */ +#define RCU_OFL_TASKS_EXP_GP 0x2 /* Tasks blocking expedited */ + /* GP were moved to root. */ + #ifdef RCU_TREE_NONCORE /* @@ -333,6 +359,9 @@ static void rcu_preempt_offline_cpu(int cpu); static void rcu_preempt_check_callbacks(int cpu); static void rcu_preempt_process_callbacks(void); void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu)); +#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_TREE_PREEMPT_RCU) +static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp); +#endif /* #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_TREE_PREEMPT_RCU) */ static int rcu_preempt_pending(int cpu); static int rcu_preempt_needs_cpu(int cpu); static void __cpuinit rcu_preempt_init_percpu_data(int cpu); diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index c9f0c975c00..37fbccdf41d 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -24,12 +24,15 @@ * Paul E. McKenney */ +#include #ifdef CONFIG_TREE_PREEMPT_RCU struct rcu_state rcu_preempt_state = RCU_STATE_INITIALIZER(rcu_preempt_state); DEFINE_PER_CPU(struct rcu_data, rcu_preempt_data); +static int rcu_preempted_readers_exp(struct rcu_node *rnp); + /* * Tell them what RCU they are running. */ @@ -157,7 +160,10 @@ EXPORT_SYMBOL_GPL(__rcu_read_lock); */ static int rcu_preempted_readers(struct rcu_node *rnp) { - return !list_empty(&rnp->blocked_tasks[rnp->gpnum & 0x1]); + int phase = rnp->gpnum & 0x1; + + return !list_empty(&rnp->blocked_tasks[phase]) || + !list_empty(&rnp->blocked_tasks[phase + 2]); } /* @@ -204,6 +210,7 @@ static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags) static void rcu_read_unlock_special(struct task_struct *t) { int empty; + int empty_exp; unsigned long flags; struct rcu_node *rnp; int special; @@ -247,6 +254,8 @@ static void rcu_read_unlock_special(struct task_struct *t) spin_unlock(&rnp->lock); /* irqs remain disabled. */ } empty = !rcu_preempted_readers(rnp); + empty_exp = !rcu_preempted_readers_exp(rnp); + smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */ list_del_init(&t->rcu_node_entry); t->rcu_blocked_node = NULL; @@ -259,6 +268,13 @@ static void rcu_read_unlock_special(struct task_struct *t) spin_unlock_irqrestore(&rnp->lock, flags); else rcu_report_unblock_qs_rnp(rnp, flags); + + /* + * If this was the last task on the expedited lists, + * then we need to report up the rcu_node hierarchy. + */ + if (!empty_exp && !rcu_preempted_readers_exp(rnp)) + rcu_report_exp_rnp(&rcu_preempt_state, rnp); } else { local_irq_restore(flags); } @@ -343,7 +359,7 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp, int i; struct list_head *lp; struct list_head *lp_root; - int retval; + int retval = 0; struct rcu_node *rnp_root = rcu_get_root(rsp); struct task_struct *tp; @@ -353,7 +369,9 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp, } WARN_ON_ONCE(rnp != rdp->mynode && (!list_empty(&rnp->blocked_tasks[0]) || - !list_empty(&rnp->blocked_tasks[1]))); + !list_empty(&rnp->blocked_tasks[1]) || + !list_empty(&rnp->blocked_tasks[2]) || + !list_empty(&rnp->blocked_tasks[3]))); /* * Move tasks up to root rcu_node. Rely on the fact that the @@ -361,8 +379,11 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp, * rcu_nodes in terms of gp_num value. This fact allows us to * move the blocked_tasks[] array directly, element by element. */ - retval = rcu_preempted_readers(rnp); - for (i = 0; i < 2; i++) { + if (rcu_preempted_readers(rnp)) + retval |= RCU_OFL_TASKS_NORM_GP; + if (rcu_preempted_readers_exp(rnp)) + retval |= RCU_OFL_TASKS_EXP_GP; + for (i = 0; i < 4; i++) { lp = &rnp->blocked_tasks[i]; lp_root = &rnp_root->blocked_tasks[i]; while (!list_empty(lp)) { @@ -449,14 +470,159 @@ void synchronize_rcu(void) } EXPORT_SYMBOL_GPL(synchronize_rcu); +static DECLARE_WAIT_QUEUE_HEAD(sync_rcu_preempt_exp_wq); +static long sync_rcu_preempt_exp_count; +static DEFINE_MUTEX(sync_rcu_preempt_exp_mutex); + +/* + * 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 !list_empty(&rnp->blocked_tasks[2]) || + !list_empty(&rnp->blocked_tasks[3]); +} + +/* + * 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 sync_rcu_preempt_exp_mutex. + */ +static int sync_rcu_preempt_exp_done(struct rcu_node *rnp) +{ + return !rcu_preempted_readers_exp(rnp) && + ACCESS_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 sync_rcu_preempt_exp_mutex. + */ +static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp) +{ + unsigned long flags; + unsigned long mask; + + spin_lock_irqsave(&rnp->lock, flags); + for (;;) { + if (!sync_rcu_preempt_exp_done(rnp)) + break; + if (rnp->parent == NULL) { + wake_up(&sync_rcu_preempt_exp_wq); + break; + } + mask = rnp->grpmask; + spin_unlock(&rnp->lock); /* irqs remain disabled */ + rnp = rnp->parent; + spin_lock(&rnp->lock); /* irqs already disabled */ + rnp->expmask &= ~mask; + } + spin_unlock_irqrestore(&rnp->lock, flags); +} + +/* + * Snapshot the tasks blocking the newly started preemptible-RCU expedited + * grace period for the specified rcu_node structure. If there are no such + * tasks, report it up the rcu_node hierarchy. + * + * Caller must hold sync_rcu_preempt_exp_mutex and rsp->onofflock. + */ +static void +sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp) +{ + int must_wait; + + spin_lock(&rnp->lock); /* irqs already disabled */ + list_splice_init(&rnp->blocked_tasks[0], &rnp->blocked_tasks[2]); + list_splice_init(&rnp->blocked_tasks[1], &rnp->blocked_tasks[3]); + must_wait = rcu_preempted_readers_exp(rnp); + spin_unlock(&rnp->lock); /* irqs remain disabled */ + if (!must_wait) + rcu_report_exp_rnp(rsp, rnp); +} + /* - * Wait for an rcu-preempt grace period. We are supposed to expedite the - * grace period, but this is the crude slow compatability hack, so just - * invoke synchronize_rcu(). + * Wait for an rcu-preempt grace period, but expedite it. The basic idea + * is to invoke synchronize_sched_expedited() to push all the tasks to + * the ->blocked_tasks[] lists, move all entries from the first set of + * ->blocked_tasks[] lists to the second set, and finally wait for this + * second set to drain. */ void synchronize_rcu_expedited(void) { - synchronize_rcu(); + unsigned long flags; + struct rcu_node *rnp; + struct rcu_state *rsp = &rcu_preempt_state; + long snap; + int trycount = 0; + + smp_mb(); /* Caller's modifications seen first by other CPUs. */ + snap = ACCESS_ONCE(sync_rcu_preempt_exp_count) + 1; + smp_mb(); /* Above access cannot bleed into critical section. */ + + /* + * 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 (trycount++ < 10) + udelay(trycount * num_online_cpus()); + else { + synchronize_rcu(); + return; + } + if ((ACCESS_ONCE(sync_rcu_preempt_exp_count) - snap) > 0) + goto mb_ret; /* Others did our work for us. */ + } + if ((ACCESS_ONCE(sync_rcu_preempt_exp_count) - snap) > 0) + goto unlock_mb_ret; /* Others did our work for us. */ + + /* force all RCU readers onto blocked_tasks[]. */ + synchronize_sched_expedited(); + + spin_lock_irqsave(&rsp->onofflock, flags); + + /* Initialize ->expmask for all non-leaf rcu_node structures. */ + rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) { + spin_lock(&rnp->lock); /* irqs already disabled. */ + rnp->expmask = rnp->qsmaskinit; + spin_unlock(&rnp->lock); /* irqs remain disabled. */ + } + + /* Snapshot current state of ->blocked_tasks[] lists. */ + rcu_for_each_leaf_node(rsp, rnp) + sync_rcu_preempt_exp_init(rsp, rnp); + if (NUM_RCU_NODES > 1) + sync_rcu_preempt_exp_init(rsp, rcu_get_root(rsp)); + + spin_unlock_irqrestore(&rsp->onofflock, flags); + + /* Wait for snapshotted ->blocked_tasks[] lists to drain. */ + rnp = rcu_get_root(rsp); + wait_event(sync_rcu_preempt_exp_wq, + sync_rcu_preempt_exp_done(rnp)); + + /* Clean up and exit. */ + smp_mb(); /* ensure expedited GP seen before counter increment. */ + ACCESS_ONCE(sync_rcu_preempt_exp_count)++; +unlock_mb_ret: + mutex_unlock(&sync_rcu_preempt_exp_mutex); +mb_ret: + smp_mb(); /* ensure subsequent action seen after grace period. */ } EXPORT_SYMBOL_GPL(synchronize_rcu_expedited); @@ -655,6 +821,20 @@ void synchronize_rcu_expedited(void) } EXPORT_SYMBOL_GPL(synchronize_rcu_expedited); +#ifdef CONFIG_HOTPLUG_CPU + +/* + * Because preemptable RCU does not exist, there is never any need to + * report on tasks preempted in RCU read-side critical sections during + * expedited RCU grace periods. + */ +static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp) +{ + return; +} + +#endif /* #ifdef CONFIG_HOTPLUG_CPU */ + /* * Because preemptable RCU does not exist, it never has any work to do. */ diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c index 1984cdc51e9..9d2c88423b3 100644 --- a/kernel/rcutree_trace.c +++ b/kernel/rcutree_trace.c @@ -157,6 +157,7 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp) { long gpnum; int level = 0; + int phase; struct rcu_node *rnp; gpnum = rsp->gpnum; @@ -173,10 +174,13 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp) seq_puts(m, "\n"); level = rnp->level; } - seq_printf(m, "%lx/%lx %c>%c %d:%d ^%d ", + phase = gpnum & 0x1; + seq_printf(m, "%lx/%lx %c%c>%c%c %d:%d ^%d ", rnp->qsmask, rnp->qsmaskinit, - "T."[list_empty(&rnp->blocked_tasks[gpnum & 1])], - "T."[list_empty(&rnp->blocked_tasks[!(gpnum & 1)])], + "T."[list_empty(&rnp->blocked_tasks[phase])], + "E."[list_empty(&rnp->blocked_tasks[phase + 2])], + "T."[list_empty(&rnp->blocked_tasks[!phase])], + "E."[list_empty(&rnp->blocked_tasks[!phase + 2])], rnp->grplo, rnp->grphi, rnp->grpnum); } seq_puts(m, "\n"); -- cgit v1.2.3-70-g09d2