diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2014-08-04 15:55:08 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2014-08-04 15:55:08 -0700 |
commit | 5bda4f638f36ef4c4e3b1397b02affc3db94356e (patch) | |
tree | d1bde148cde9981c31941382b2076084c7f5796c | |
parent | a45c657f28f82b056173d1afc2e7ed1f1f68829f (diff) | |
parent | 01c9db827146ce321562a992a5dbc1a49b1a99ce (diff) |
Merge branch 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull RCU changes from Ingo Molar:
"The main changes:
- torture-test updates
- callback-offloading changes
- maintainership changes
- update RCU documentation
- miscellaneous fixes"
* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (32 commits)
rcu: Allow for NULL tick_nohz_full_mask when nohz_full= missing
rcu: Fix a sparse warning in rcu_report_unblock_qs_rnp()
rcu: Fix a sparse warning in rcu_initiate_boost()
rcu: Fix __rcu_reclaim() to use true/false for bool
rcu: Remove CONFIG_PROVE_RCU_DELAY
rcu: Use __this_cpu_read() instead of per_cpu_ptr()
rcu: Don't use NMIs to dump other CPUs' stacks
rcu: Bind grace-period kthreads to non-NO_HZ_FULL CPUs
rcu: Simplify priority boosting by putting rt_mutex in rcu_node
rcu: Check both root and current rcu_node when setting up future grace period
rcu: Allow post-unlock reference for rt_mutex
rcu: Loosen __call_rcu()'s rcu_head alignment constraint
rcu: Eliminate read-modify-write ACCESS_ONCE() calls
rcu: Remove redundant ACCESS_ONCE() from tick_do_timer_cpu
rcu: Make rcu node arrays static const char * const
signal: Explain local_irq_save() call
rcu: Handle obsolete references to TINY_PREEMPT_RCU
rcu: Document deadlock-avoidance information for rcu_read_unlock()
scripts: Teach get_maintainer.pl about the new "R:" tag
rcu: Update rcu torture maintainership filename patterns
...
40 files changed, 492 insertions, 177 deletions
diff --git a/Documentation/RCU/RTFP.txt b/Documentation/RCU/RTFP.txt index 2f0fcb2112d2..f29bcbc463e7 100644 --- a/Documentation/RCU/RTFP.txt +++ b/Documentation/RCU/RTFP.txt @@ -2451,8 +2451,8 @@ lot of {Linux} into your technology!!!" ,month="February" ,year="2010" ,note="Available: -\url{http://kerneltrap.com/mailarchive/linux-netdev/2010/2/26/6270589} -[Viewed March 20, 2011]" +\url{http://thread.gmane.org/gmane.linux.network/153338} +[Viewed June 9, 2014]" ,annotation={ Use a pair of list_head structures to support RCU-protected resizable hash tables. diff --git a/Documentation/RCU/rcuref.txt b/Documentation/RCU/rcuref.txt index 141d531aa14b..613033ff2b9b 100644 --- a/Documentation/RCU/rcuref.txt +++ b/Documentation/RCU/rcuref.txt @@ -1,5 +1,14 @@ Reference-count design for elements of lists/arrays protected by RCU. + +Please note that the percpu-ref feature is likely your first +stop if you need to combine reference counts and RCU. Please see +include/linux/percpu-refcount.h for more information. However, in +those unusual cases where percpu-ref would consume too much memory, +please read on. + +------------------------------------------------------------------------ + Reference counting on elements of lists which are protected by traditional reader/writer spinlocks or semaphores are straightforward: diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 45fbea7c329b..90f6139608ff 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -2813,6 +2813,13 @@ bytes respectively. Such letter suffixes can also be entirely omitted. quiescent states. Units are jiffies, minimum value is one, and maximum value is HZ. + rcutree.rcu_nocb_leader_stride= [KNL] + Set the number of NOCB kthread groups, which + defaults to the square root of the number of + CPUs. Larger numbers reduces the wakeup overhead + on the per-CPU grace-period kthreads, but increases + that same overhead on each group's leader. + rcutree.qhimark= [KNL] Set threshold of queued RCU callbacks beyond which batch limiting is disabled. diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt index f1dc4a215593..a4de88fb55f0 100644 --- a/Documentation/memory-barriers.txt +++ b/Documentation/memory-barriers.txt @@ -757,10 +757,14 @@ SMP BARRIER PAIRING When dealing with CPU-CPU interactions, certain types of memory barrier should always be paired. A lack of appropriate pairing is almost certainly an error. -A write barrier should always be paired with a data dependency barrier or read -barrier, though a general barrier would also be viable. Similarly a read -barrier or a data dependency barrier should always be paired with at least an -write barrier, though, again, a general barrier is viable: +General barriers pair with each other, though they also pair with +most other types of barriers, albeit without transitivity. An acquire +barrier pairs with a release barrier, but both may also pair with other +barriers, including of course general barriers. A write barrier pairs +with a data dependency barrier, an acquire barrier, a release barrier, +a read barrier, or a general barrier. Similarly a read barrier or a +data dependency barrier pairs with a write barrier, an acquire barrier, +a release barrier, or a general barrier: CPU 1 CPU 2 =============== =============== @@ -1893,6 +1897,21 @@ between the STORE to indicate the event and the STORE to set TASK_RUNNING: <general barrier> STORE current->state LOAD event_indicated +To repeat, this write memory barrier is present if and only if something +is actually awakened. To see this, consider the following sequence of +events, where X and Y are both initially zero: + + CPU 1 CPU 2 + =============================== =============================== + X = 1; STORE event_indicated + smp_mb(); wake_up(); + Y = 1; wait_event(wq, Y == 1); + wake_up(); load from Y sees 1, no memory barrier + load from X might see 0 + +In contrast, if a wakeup does occur, CPU 2's load from X would be guaranteed +to see 1. + The available waker functions include: complete(); diff --git a/MAINTAINERS b/MAINTAINERS index e4cf1f63f487..1acc624ecfd7 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -70,6 +70,8 @@ Descriptions of section entries: P: Person (obsolete) M: Mail patches to: FullName <address@domain> + R: Designated reviewer: FullName <address@domain> + These reviewers should be CCed on patches. L: Mailing list that is relevant to this area W: Web-page with status/info Q: Patchwork web based patch tracking system site @@ -7443,10 +7445,14 @@ L: linux-kernel@vger.kernel.org S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git F: Documentation/RCU/torture.txt -F: kernel/rcu/torture.c +F: kernel/rcu/rcutorture.c RCUTORTURE TEST FRAMEWORK M: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> +M: Josh Triplett <josh@joshtriplett.org> +R: Steven Rostedt <rostedt@goodmis.org> +R: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> +R: Lai Jiangshan <laijs@cn.fujitsu.com> L: linux-kernel@vger.kernel.org S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git @@ -7469,8 +7475,11 @@ S: Supported F: net/rds/ READ-COPY UPDATE (RCU) -M: Dipankar Sarma <dipankar@in.ibm.com> M: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> +M: Josh Triplett <josh@joshtriplett.org> +R: Steven Rostedt <rostedt@goodmis.org> +R: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> +R: Lai Jiangshan <laijs@cn.fujitsu.com> L: linux-kernel@vger.kernel.org W: http://www.rdrop.com/users/paulmck/RCU/ S: Supported @@ -7480,7 +7489,7 @@ X: Documentation/RCU/torture.txt F: include/linux/rcu* X: include/linux/srcu.h F: kernel/rcu/ -X: kernel/rcu/torture.c +X: kernel/torture.c REAL TIME CLOCK (RTC) SUBSYSTEM M: Alessandro Zummo <a.zummo@towertech.it> @@ -8263,6 +8272,9 @@ F: mm/sl?b* SLEEPABLE READ-COPY UPDATE (SRCU) M: Lai Jiangshan <laijs@cn.fujitsu.com> M: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> +M: Josh Triplett <josh@joshtriplett.org> +R: Steven Rostedt <rostedt@goodmis.org> +R: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> L: linux-kernel@vger.kernel.org W: http://www.rdrop.com/users/paulmck/RCU/ S: Supported diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 6df7f9fe0d01..2bb4c4f3531a 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -102,12 +102,6 @@ extern struct group_info init_groups; #define INIT_IDS #endif -#ifdef CONFIG_RCU_BOOST -#define INIT_TASK_RCU_BOOST() \ - .rcu_boost_mutex = NULL, -#else -#define INIT_TASK_RCU_BOOST() -#endif #ifdef CONFIG_TREE_PREEMPT_RCU #define INIT_TASK_RCU_TREE_PREEMPT() \ .rcu_blocked_node = NULL, @@ -119,8 +113,7 @@ extern struct group_info init_groups; .rcu_read_lock_nesting = 0, \ .rcu_read_unlock_special = 0, \ .rcu_node_entry = LIST_HEAD_INIT(tsk.rcu_node_entry), \ - INIT_TASK_RCU_TREE_PREEMPT() \ - INIT_TASK_RCU_BOOST() + INIT_TASK_RCU_TREE_PREEMPT() #else #define INIT_TASK_RCU_PREEMPT(tsk) #endif diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 6a94cc8b1ca0..d231aa17b1d7 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -826,15 +826,14 @@ static inline void rcu_preempt_sleep_check(void) * read-side critical section that would block in a !PREEMPT kernel. * But if you want the full story, read on! * - * In non-preemptible RCU implementations (TREE_RCU and TINY_RCU), it - * is illegal to block while in an RCU read-side critical section. In - * preemptible RCU implementations (TREE_PREEMPT_RCU and TINY_PREEMPT_RCU) - * in CONFIG_PREEMPT kernel builds, RCU read-side critical sections may - * be preempted, but explicit blocking is illegal. Finally, in preemptible - * RCU implementations in real-time (with -rt patchset) kernel builds, - * RCU read-side critical sections may be preempted and they may also - * block, but only when acquiring spinlocks that are subject to priority - * inheritance. + * In non-preemptible RCU implementations (TREE_RCU and TINY_RCU), + * it is illegal to block while in an RCU read-side critical section. + * In preemptible RCU implementations (TREE_PREEMPT_RCU) in CONFIG_PREEMPT + * kernel builds, RCU read-side critical sections may be preempted, + * but explicit blocking is illegal. Finally, in preemptible RCU + * implementations in real-time (with -rt patchset) kernel builds, RCU + * read-side critical sections may be preempted and they may also block, but + * only when acquiring spinlocks that are subject to priority inheritance. */ static inline void rcu_read_lock(void) { @@ -858,6 +857,34 @@ static inline void rcu_read_lock(void) /** * rcu_read_unlock() - marks the end of an RCU read-side critical section. * + * In most situations, rcu_read_unlock() is immune from deadlock. + * However, in kernels built with CONFIG_RCU_BOOST, rcu_read_unlock() + * is responsible for deboosting, which it does via rt_mutex_unlock(). + * Unfortunately, this function acquires the scheduler's runqueue and + * priority-inheritance spinlocks. This means that deadlock could result + * if the caller of rcu_read_unlock() already holds one of these locks or + * any lock that is ever acquired while holding them. + * + * That said, RCU readers are never priority boosted unless they were + * preempted. Therefore, one way to avoid deadlock is to make sure + * that preemption never happens within any RCU read-side critical + * section whose outermost rcu_read_unlock() is called with one of + * rt_mutex_unlock()'s locks held. Such preemption can be avoided in + * a number of ways, for example, by invoking preempt_disable() before + * critical section's outermost rcu_read_lock(). + * + * Given that the set of locks acquired by rt_mutex_unlock() might change + * at any time, a somewhat more future-proofed approach is to make sure + * that that preemption never happens within any RCU read-side critical + * section whose outermost rcu_read_unlock() is called with irqs disabled. + * This approach relies on the fact that rt_mutex_unlock() currently only + * acquires irq-disabled locks. + * + * The second of these two approaches is best in most situations, + * however, the first approach can also be useful, at least to those + * developers willing to keep abreast of the set of locks acquired by + * rt_mutex_unlock(). + * * See rcu_read_lock() for more information. */ static inline void rcu_read_unlock(void) diff --git a/include/linux/sched.h b/include/linux/sched.h index 0376b054a0d0..b39a671cfd59 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1270,9 +1270,6 @@ struct task_struct { #ifdef CONFIG_TREE_PREEMPT_RCU struct rcu_node *rcu_blocked_node; #endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ -#ifdef CONFIG_RCU_BOOST - struct rt_mutex *rcu_boost_mutex; -#endif /* #ifdef CONFIG_RCU_BOOST */ #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) struct sched_info sched_info; @@ -2009,9 +2006,6 @@ static inline void rcu_copy_process(struct task_struct *p) #ifdef CONFIG_TREE_PREEMPT_RCU p->rcu_blocked_node = NULL; #endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ -#ifdef CONFIG_RCU_BOOST - p->rcu_boost_mutex = NULL; -#endif /* #ifdef CONFIG_RCU_BOOST */ INIT_LIST_HEAD(&p->rcu_node_entry); } diff --git a/include/linux/tick.h b/include/linux/tick.h index b84773cb9f4c..06cc093ab7ad 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -12,6 +12,7 @@ #include <linux/hrtimer.h> #include <linux/context_tracking_state.h> #include <linux/cpumask.h> +#include <linux/sched.h> #ifdef CONFIG_GENERIC_CLOCKEVENTS @@ -162,6 +163,7 @@ static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; } #ifdef CONFIG_NO_HZ_FULL extern bool tick_nohz_full_running; extern cpumask_var_t tick_nohz_full_mask; +extern cpumask_var_t housekeeping_mask; static inline bool tick_nohz_full_enabled(void) { @@ -194,6 +196,24 @@ static inline void tick_nohz_full_kick_all(void) { } static inline void __tick_nohz_task_switch(struct task_struct *tsk) { } #endif +static inline bool is_housekeeping_cpu(int cpu) +{ +#ifdef CONFIG_NO_HZ_FULL + if (tick_nohz_full_enabled()) + return cpumask_test_cpu(cpu, housekeeping_mask); +#endif + return true; +} + +static inline void housekeeping_affine(struct task_struct *t) +{ +#ifdef CONFIG_NO_HZ_FULL + if (tick_nohz_full_enabled()) + set_cpus_allowed_ptr(t, housekeeping_mask); + +#endif +} + static inline void tick_nohz_full_check(void) { if (tick_nohz_full_enabled()) diff --git a/init/Kconfig b/init/Kconfig index 9d76b99af1b9..41066e49e880 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -505,7 +505,7 @@ config PREEMPT_RCU def_bool TREE_PREEMPT_RCU help This option enables preemptible-RCU code that is common between - the TREE_PREEMPT_RCU and TINY_PREEMPT_RCU implementations. + TREE_PREEMPT_RCU and, in the old days, TINY_PREEMPT_RCU. config RCU_STALL_COMMON def_bool ( TREE_RCU || TREE_PREEMPT_RCU || RCU_TRACE ) @@ -737,7 +737,7 @@ choice config RCU_NOCB_CPU_NONE bool "No build_forced no-CBs CPUs" - depends on RCU_NOCB_CPU && !NO_HZ_FULL + depends on RCU_NOCB_CPU && !NO_HZ_FULL_ALL help This option does not force any of the CPUs to be no-CBs CPUs. Only CPUs designated by the rcu_nocbs= boot parameter will be @@ -751,7 +751,7 @@ config RCU_NOCB_CPU_NONE config RCU_NOCB_CPU_ZERO bool "CPU 0 is a build_forced no-CBs CPU" - depends on RCU_NOCB_CPU && !NO_HZ_FULL + depends on RCU_NOCB_CPU && !NO_HZ_FULL_ALL help This option forces CPU 0 to be a no-CBs CPU, so that its RCU callbacks are invoked by a per-CPU kthread whose name begins diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h index bfda2726ca45..ff1a6de62f17 100644 --- a/kernel/rcu/rcu.h +++ b/kernel/rcu/rcu.h @@ -99,6 +99,10 @@ static inline void debug_rcu_head_unqueue(struct rcu_head *head) void kfree(const void *); +/* + * Reclaim the specified callback, either by invoking it (non-lazy case) + * or freeing it directly (lazy case). Return true if lazy, false otherwise. + */ static inline bool __rcu_reclaim(const char *rn, struct rcu_head *head) { unsigned long offset = (unsigned long)head->func; @@ -108,12 +112,12 @@ static inline bool __rcu_reclaim(const char *rn, struct rcu_head *head) RCU_TRACE(trace_rcu_invoke_kfree_callback(rn, head, offset)); kfree((void *)head - offset); rcu_lock_release(&rcu_callback_map); - return 1; + return true; } else { RCU_TRACE(trace_rcu_invoke_callback(rn, head)); head->func(head); rcu_lock_release(&rcu_callback_map); - return 0; + return false; } } diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c index c639556f3fa0..e037f3eb2f7b 100644 --- a/kernel/rcu/srcu.c +++ b/kernel/rcu/srcu.c @@ -298,9 +298,9 @@ int __srcu_read_lock(struct srcu_struct *sp) idx = ACCESS_ONCE(sp->completed) & 0x1; preempt_disable(); - ACCESS_ONCE(this_cpu_ptr(sp->per_cpu_ref)->c[idx]) += 1; + __this_cpu_inc(sp->per_cpu_ref->c[idx]); smp_mb(); /* B */ /* Avoid leaking the critical section. */ - ACCESS_ONCE(this_cpu_ptr(sp->per_cpu_ref)->seq[idx]) += 1; + __this_cpu_inc(sp->per_cpu_ref->seq[idx]); preempt_enable(); return idx; } diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 625d0b0cd75a..1b70cb6fbe3c 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -1013,10 +1013,7 @@ static void record_gp_stall_check_time(struct rcu_state *rsp) } /* - * Dump stacks of all tasks running on stalled CPUs. This is a fallback - * for architectures that do not implement trigger_all_cpu_backtrace(). - * The NMI-triggered stack traces are more accurate because they are - * printed by the target CPU. + * Dump stacks of all tasks running on stalled CPUs. */ static void rcu_dump_cpu_stacks(struct rcu_state *rsp) { @@ -1094,7 +1091,7 @@ static void print_other_cpu_stall(struct rcu_state *rsp) (long)rsp->gpnum, (long)rsp->completed, totqlen); if (ndetected == 0) pr_err("INFO: Stall ended before state dump start\n"); - else if (!trigger_all_cpu_backtrace()) + else rcu_dump_cpu_stacks(rsp); /* Complain about tasks blocking the grace period. */ @@ -1125,8 +1122,7 @@ static void print_cpu_stall(struct rcu_state *rsp) pr_cont(" (t=%lu jiffies g=%ld c=%ld q=%lu)\n", jiffies - rsp->gp_start, (long)rsp->gpnum, (long)rsp->completed, totqlen); - if (!trigger_all_cpu_backtrace()) - dump_stack(); + rcu_dump_cpu_stacks(rsp); raw_spin_lock_irqsave(&rnp->lock, flags); if (ULONG_CMP_GE(jiffies, ACCESS_ONCE(rsp->jiffies_stall))) @@ -1305,10 +1301,16 @@ rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp, * believe that a grace period is in progress, then we must wait * for the one following, which is in "c". Because our request * will be noticed at the end of the current grace period, we don't - * need to explicitly start one. + * need to explicitly start one. We only do the lockless check + * of rnp_root's fields if the current rcu_node structure thinks + * there is no grace period in flight, and because we hold rnp->lock, + * the only possible change is when rnp_root's two fields are + * equal, in which case rnp_root->gpnum might be concurrently + * incremented. But that is OK, as it will just result in our + * doing some extra useless work. */ if (rnp->gpnum != rnp->completed || - ACCESS_ONCE(rnp->gpnum) != ACCESS_ONCE(rnp->completed)) { + ACCESS_ONCE(rnp_root->gpnum) != ACCESS_ONCE(rnp_root->completed)) { rnp->need_future_gp[c & 0x1]++; trace_rcu_future_gp(rnp, rdp, c, TPS("Startedleaf")); goto out; @@ -1645,11 +1647,6 @@ static int rcu_gp_init(struct rcu_state *rsp) rnp->level, rnp->grplo, rnp->grphi, rnp->qsmask); raw_spin_unlock_irq(&rnp->lock); -#ifdef CONFIG_PROVE_RCU_DELAY - if ((prandom_u32() % (rcu_num_nodes + 1)) == 0 && - system_state == SYSTEM_RUNNING) - udelay(200); -#endif /* #ifdef CONFIG_PROVE_RCU_DELAY */ cond_resched(); } @@ -2347,7 +2344,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) } smp_mb(); /* List handling before counting for rcu_barrier(). */ rdp->qlen_lazy -= count_lazy; - ACCESS_ONCE(rdp->qlen) -= count; + ACCESS_ONCE(rdp->qlen) = rdp->qlen - count; rdp->n_cbs_invoked += count; /* Reinstate batch limit if we have worked down the excess. */ @@ -2485,14 +2482,14 @@ static void force_quiescent_state(struct rcu_state *rsp) struct rcu_node *rnp_old = NULL; /* Funnel through hierarchy to reduce memory contention. */ - rnp = per_cpu_ptr(rsp->rda, raw_smp_processor_id())->mynode; + rnp = __this_cpu_read(rsp->rda->mynode); for (; rnp != NULL; rnp = rnp->parent) { ret = (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) || !raw_spin_trylock(&rnp->fqslock); if (rnp_old != NULL) raw_spin_unlock(&rnp_old->fqslock); if (ret) { - ACCESS_ONCE(rsp->n_force_qs_lh)++; + rsp->n_force_qs_lh++; return; } rnp_old = rnp; @@ -2504,7 +2501,7 @@ static void force_quiescent_state(struct rcu_state *rsp) smp_mb__after_unlock_lock(); raw_spin_unlock(&rnp_old->fqslock); if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) { - ACCESS_ONCE(rsp->n_force_qs_lh)++; + rsp->n_force_qs_lh++; raw_spin_unlock_irqrestore(&rnp_old->lock, flags); return; /* Someone beat us to it. */ } @@ -2662,7 +2659,7 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), unsigned long flags; struct rcu_data *rdp; - WARN_ON_ONCE((unsigned long)head & 0x3); /* Misaligned rcu_head! */ + WARN_ON_ONCE((unsigned long)head & 0x1); /* Misaligned rcu_head! */ if (debug_rcu_head_queue(head)) { /* Probable double call_rcu(), so leak the callback. */ ACCESS_ONCE(head->func) = rcu_leak_callback; @@ -2693,7 +2690,7 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), local_irq_restore(flags); return; } - ACCESS_ONCE(rdp->qlen)++; + ACCESS_ONCE(rdp->qlen) = rdp->qlen + 1; if (lazy) rdp->qlen_lazy++; else @@ -3257,7 +3254,7 @@ static void _rcu_barrier(struct rcu_state *rsp) * ACCESS_ONCE() to prevent the compiler from speculating * the increment to precede the early-exit check. */ - ACCESS_ONCE(rsp->n_barrier_done)++; + ACCESS_ONCE(rsp->n_barrier_done) = rsp->n_barrier_done + 1; WARN_ON_ONCE((rsp->n_barrier_done & 0x1) != 1); _rcu_barrier_trace(rsp, "Inc1", -1, rsp->n_barrier_done); smp_mb(); /* Order ->n_barrier_done increment with below mechanism. */ @@ -3307,7 +3304,7 @@ static void _rcu_barrier(struct rcu_state *rsp) /* Increment ->n_barrier_done to prevent duplicate work. */ smp_mb(); /* Keep increment after above mechanism. */ - ACCESS_ONCE(rsp->n_barrier_done)++; + ACCESS_ONCE(rsp->n_barrier_done) = rsp->n_barrier_done + 1; WARN_ON_ONCE((rsp->n_barrier_done & 0x1) != 0); _rcu_barrier_trace(rsp, "Inc2", -1, rsp->n_barrier_done); smp_mb(); /* Keep increment before caller's subsequent code. */ @@ -3564,14 +3561,16 @@ static void __init rcu_init_levelspread(struct rcu_state *rsp) static void __init rcu_init_one(struct rcu_state *rsp, struct rcu_data __percpu *rda) { - static char *buf[] = { "rcu_node_0", - "rcu_node_1", - "rcu_node_2", - "rcu_node_3" }; /* Match MAX_RCU_LVLS */ - static char *fqs[] = { "rcu_node_fqs_0", - "rcu_node_fqs_1", - "rcu_node_fqs_2", - "rcu_node_fqs_3" }; /* Match MAX_RCU_LVLS */ + static const char * const buf[] = { + "rcu_node_0", + "rcu_node_1", + "rcu_node_2", + "rcu_node_3" }; /* Match MAX_RCU_LVLS */ + static const char * const fqs[] = { + "rcu_node_fqs_0", + "rcu_node_fqs_1", + "rcu_node_fqs_2", + "rcu_node_fqs_3" }; /* Match MAX_RCU_LVLS */ static u8 fl_mask = 0x1; int cpustride = 1; int i; diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 0f69a79c5b7d..71e64c718f75 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -172,6 +172,14 @@ struct rcu_node { /* queued on this rcu_node structure that */ /* are blocking the current grace period, */ /* there can be no such task. */ + struct completion boost_completion; + /* Used to ensure that the rt_mutex used */ + /* to carry out the boosting is fully */ + /* released with no future boostee accesses */ + /* before that rt_mutex is re-initialized. */ + struct rt_mutex boost_mtx; + /* Used only for the priority-boosting */ + /* side effect, not as a lock. */ unsigned long boost_time; /* When to start boosting (jiffies). */ struct task_struct *boost_kthread_task; @@ -334,11 +342,29 @@ struct rcu_data { struct rcu_head **nocb_tail; atomic_long_t nocb_q_count; /* # CBs waiting for kthread */ atomic_long_t nocb_q_count_lazy; /* (approximate). */ + struct rcu_head *nocb_follower_head; /* CBs ready to invoke. */ + struct rcu_head **nocb_follower_tail; + atomic_long_t nocb_follower_count; /* # CBs ready to invoke. */ + atomic_long_t nocb_follower_count_lazy; /* (approximate). */ int nocb_p_count; /* # CBs being invoked by kthread */ int nocb_p_count_lazy; /* (approximate). */ wait_queue_head_t nocb_wq; /* For nocb kthreads to sleep on. */ struct task_struct *nocb_kthread; bool nocb_defer_wakeup; /* Defer wakeup of nocb_kthread. */ + + /* The following fields are used by the leader, hence own cacheline. */ + struct rcu_head *nocb_gp_head ____cacheline_internodealigned_in_smp; + /* CBs waiting for GP. */ + struct rcu_head **nocb_gp_tail; + long nocb_gp_count; + long nocb_gp_count_lazy; + bool nocb_leader_wake; /* Is the nocb leader thread awake? */ + struct rcu_data *nocb_next_follower; + /* Next follower in wakeup chain. */ + + /* The following fields are used by the follower, hence new cachline. */ + struct rcu_data *nocb_leader ____cacheline_internodealigned_in_smp; + /* Leader CPU takes GP-end wakeups. */ #endif /* #ifdef CONFIG_RCU_NOCB_CPU */ /* 8) RCU CPU stall data. */ @@ -587,8 +613,14 @@ static bool rcu_nohz_full_cpu(struct rcu_state *rsp); /* Sum up queue lengths for tracing. */ static inline void rcu_nocb_q_lengths(struct rcu_data *rdp, long *ql, long *qll) { - *ql = atomic_long_read(&rdp->nocb_q_count) + rdp->nocb_p_count; - *qll = atomic_long_read(&rdp->nocb_q_count_lazy) + rdp->nocb_p_count_lazy; + *ql = atomic_long_read(&rdp->nocb_q_count) + + rdp->nocb_p_count + + atomic_long_read(&rdp->nocb_follower_count) + + rdp->nocb_p_count + rdp->nocb_gp_count; + *qll = atomic_long_read(&rdp->nocb_q_count_lazy) + + rdp->nocb_p_count_lazy + + atomic_long_read(&rdp->nocb_follower_count_lazy) + + rdp->nocb_p_count_lazy + rdp->nocb_gp_count_lazy; } #else /* #ifdef CONFIG_RCU_NOCB_CPU */ static inline void rcu_ |