diff options
-rw-r--r-- | Documentation/RCU/stallwarn.txt | 18 | ||||
-rw-r--r-- | Documentation/RCU/trace.txt | 13 | ||||
-rw-r--r-- | include/linux/rcupdate.h | 14 | ||||
-rw-r--r-- | kernel/rcutiny_plugin.h | 12 | ||||
-rw-r--r-- | kernel/rcutorture.c | 11 | ||||
-rw-r--r-- | kernel/rcutree.c | 3 | ||||
-rw-r--r-- | kernel/rcutree.h | 3 | ||||
-rw-r--r-- | kernel/rcutree_plugin.h | 2 | ||||
-rw-r--r-- | kernel/rcutree_trace.c | 10 | ||||
-rw-r--r-- | kernel/srcu.c | 2 | ||||
-rw-r--r-- | lib/Kconfig.debug | 4 |
11 files changed, 74 insertions, 18 deletions
diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt index 44c6dcc93d6d..862c08ef1fde 100644 --- a/Documentation/RCU/stallwarn.txt +++ b/Documentation/RCU/stallwarn.txt @@ -80,6 +80,24 @@ o A CPU looping with bottom halves disabled. This condition can o For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the kernel without invoking schedule(). +o A CPU-bound real-time task in a CONFIG_PREEMPT kernel, which might + happen to preempt a low-priority task in the middle of an RCU + read-side critical section. This is especially damaging if + that low-priority task is not permitted to run on any other CPU, + in which case the next RCU grace period can never complete, which + will eventually cause the system to run out of memory and hang. + While the system is in the process of running itself out of + memory, you might see stall-warning messages. + +o A CPU-bound real-time task in a CONFIG_PREEMPT_RT kernel that + is running at a higher priority than the RCU softirq threads. + This will prevent RCU callbacks from ever being invoked, + and in a CONFIG_TREE_PREEMPT_RCU kernel will further prevent + RCU grace periods from ever completing. Either way, the + system will eventually run out of memory and hang. In the + CONFIG_TREE_PREEMPT_RCU case, you might see stall-warning + messages. + o A bug in the RCU implementation. o A hardware failure. This is quite unlikely, but has occurred diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt index efd8cc95c06b..a851118775d8 100644 --- a/Documentation/RCU/trace.txt +++ b/Documentation/RCU/trace.txt @@ -125,6 +125,17 @@ o "b" is the batch limit for this CPU. If more than this number of RCU callbacks is ready to invoke, then the remainder will be deferred. +o "ci" is the number of RCU callbacks that have been invoked for + this CPU. Note that ci+ql is the number of callbacks that have + been registered in absence of CPU-hotplug activity. + +o "co" is the number of RCU callbacks that have been orphaned due to + this CPU going offline. + +o "ca" is the number of RCU callbacks that have been adopted due to + other CPUs going offline. Note that ci+co-ca+ql is the number of + RCU callbacks registered on this CPU. + There is also an rcu/rcudata.csv file with the same information in comma-separated-variable spreadsheet format. @@ -180,7 +191,7 @@ o "s" is the "signaled" state that drives force_quiescent_state()'s o "jfq" is the number of jiffies remaining for this grace period before force_quiescent_state() is invoked to help push things - along. Note that CPUs in dyntick-idle mode thoughout the grace + along. Note that CPUs in dyntick-idle mode throughout the grace period will not report on their own, but rather must be check by some other CPU via force_quiescent_state(). diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 89414d67d961..03cda7bed985 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -310,24 +310,32 @@ extern int rcu_my_thread_group_empty(void); * (e.g., __rcu_bh, * __rcu_sched, and __srcu), should this make sense in * the future. */ + +#ifdef __CHECKER__ +#define rcu_dereference_sparse(p, space) \ + ((void)(((typeof(*p) space *)p) == p)) +#else /* #ifdef __CHECKER__ */ +#define rcu_dereference_sparse(p, space) +#endif /* #else #ifdef __CHECKER__ */ + #define __rcu_access_pointer(p, space) \ ({ \ typeof(*p) *_________p1 = (typeof(*p)*__force )ACCESS_ONCE(p); \ - (void) (((typeof (*p) space *)p) == p); \ + rcu_dereference_sparse(p, space); \ ((typeof(*p) __force __kernel *)(_________p1)); \ }) #define __rcu_dereference_check(p, c, space) \ ({ \ typeof(*p) *_________p1 = (typeof(*p)*__force )ACCESS_ONCE(p); \ rcu_lockdep_assert(c); \ - (void) (((typeof (*p) space *)p) == p); \ + rcu_dereference_sparse(p, space); \ smp_read_barrier_depends(); \ ((typeof(*p) __force __kernel *)(_________p1)); \ }) #define __rcu_dereference_protected(p, c, space) \ ({ \ rcu_lockdep_assert(c); \ - (void) (((typeof (*p) space *)p) == p); \ + rcu_dereference_sparse(p, space); \ ((typeof(*p) __force __kernel *)(p)); \ }) diff --git a/kernel/rcutiny_plugin.h b/kernel/rcutiny_plugin.h index c5bea1137dcb..6ceca4f745ff 100644 --- a/kernel/rcutiny_plugin.h +++ b/kernel/rcutiny_plugin.h @@ -72,7 +72,7 @@ static void rcu_report_exp_done(void); /* * Return true if the CPU has not yet responded to the current grace period. */ -static int rcu_cpu_cur_gp(void) +static int rcu_cpu_blocking_cur_gp(void) { return rcu_preempt_ctrlblk.gpcpu != rcu_preempt_ctrlblk.gpnum; } @@ -229,7 +229,7 @@ void rcu_preempt_note_context_switch(void) * cannot end. */ list_add(&t->rcu_node_entry, &rcu_preempt_ctrlblk.blkd_tasks); - if (rcu_cpu_cur_gp()) + if (rcu_cpu_blocking_cur_gp()) rcu_preempt_ctrlblk.gp_tasks = &t->rcu_node_entry; } @@ -368,12 +368,16 @@ static void rcu_preempt_check_callbacks(void) { struct task_struct *t = current; - if (!rcu_preempt_running_reader() && rcu_preempt_gp_in_progress()) + if (rcu_preempt_gp_in_progress() && + (!rcu_preempt_running_reader() || + !rcu_cpu_blocking_cur_gp())) rcu_preempt_cpu_qs(); if (&rcu_preempt_ctrlblk.rcb.rcucblist != rcu_preempt_ctrlblk.rcb.donetail) raise_softirq(RCU_SOFTIRQ); - if (rcu_preempt_gp_in_progress() && rcu_preempt_running_reader()) + if (rcu_preempt_gp_in_progress() && + rcu_cpu_blocking_cur_gp() && + rcu_preempt_running_reader()) t->rcu_read_unlock_special |= RCU_READ_UNLOCK_NEED_QS; } diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index 729710273dcb..9d8e8fb2515f 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -120,7 +120,7 @@ struct rcu_torture { }; static LIST_HEAD(rcu_torture_freelist); -static struct rcu_torture *rcu_torture_current; +static struct rcu_torture __rcu *rcu_torture_current; static long rcu_torture_current_version; static struct rcu_torture rcu_tortures[10 * RCU_TORTURE_PIPE_LEN]; static DEFINE_SPINLOCK(rcu_torture_lock); @@ -153,8 +153,10 @@ int rcutorture_runnable = RCUTORTURE_RUNNABLE_INIT; #define FULLSTOP_SHUTDOWN 1 /* System shutdown with rcutorture running. */ #define FULLSTOP_RMMOD 2 /* Normal rmmod of rcutorture. */ static int fullstop = FULLSTOP_RMMOD; -DEFINE_MUTEX(fullstop_mutex); /* Protect fullstop transitions and spawning */ - /* of kthreads. */ +/* + * Protect fullstop transitions and spawning of kthreads. + */ +static DEFINE_MUTEX(fullstop_mutex); /* * Detect and respond to a system shutdown. @@ -737,7 +739,8 @@ rcu_torture_writer(void *arg) continue; rp->rtort_pipe_count = 0; udelay(rcu_random(&rand) & 0x3ff); - old_rp = rcu_torture_current; + old_rp = rcu_dereference_check(rcu_torture_current, + current == writer_task); rp->rtort_mbtest = 1; rcu_assign_pointer(rcu_torture_current, rp); smp_wmb(); /* Mods to old_rp must follow rcu_assign_pointer() */ diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 42140a860bb9..e75073504a31 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -1004,6 +1004,7 @@ static void rcu_send_cbs_to_orphanage(struct rcu_state *rsp) for (i = 0; i < RCU_NEXT_SIZE; i++) rdp->nxttail[i] = &rdp->nxtlist; rsp->orphan_qlen += rdp->qlen; + rdp->n_cbs_orphaned += rdp->qlen; rdp->qlen = 0; raw_spin_unlock(&rsp->onofflock); /* irqs remain disabled. */ } @@ -1025,6 +1026,7 @@ static void rcu_adopt_orphan_cbs(struct rcu_state *rsp) *rdp->nxttail[RCU_NEXT_TAIL] = rsp->orphan_cbs_list; rdp->nxttail[RCU_NEXT_TAIL] = rsp->orphan_cbs_tail; rdp->qlen += rsp->orphan_qlen; + rdp->n_cbs_adopted += rsp->orphan_qlen; rsp->orphan_cbs_list = NULL; rsp->orphan_cbs_tail = &rsp->orphan_cbs_list; rsp->orphan_qlen = 0; @@ -1156,6 +1158,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) /* Update count, and requeue any remaining callbacks. */ rdp->qlen -= count; + rdp->n_cbs_invoked += count; if (list != NULL) { *tail = rdp->nxtlist; rdp->nxtlist = list; diff --git a/kernel/rcutree.h b/kernel/rcutree.h index 7918ba61873f..91d4170c5c13 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -202,6 +202,9 @@ struct rcu_data { long qlen; /* # of queued callbacks */ long qlen_last_fqs_check; /* qlen at last check for QS forcing */ + unsigned long n_cbs_invoked; /* count of RCU cbs invoked. */ + unsigned long n_cbs_orphaned; /* RCU cbs sent to orphanage. */ + unsigned long n_cbs_adopted; /* RCU cbs adopted from orphanage. */ unsigned long n_force_qs_snap; /* did other CPU force QS recently? */ long blimit; /* Upper limit on a processed batch */ diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index e9e0bc74ff37..71a4147473f9 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -57,7 +57,7 @@ static void __init rcu_bootup_announce_oddness(void) printk(KERN_INFO "\tRCU-based detection of stalled CPUs is disabled.\n"); #endif -#ifndef CONFIG_RCU_CPU_STALL_VERBOSE +#if defined(CONFIG_TREE_PREEMPT_RCU) && !defined(CONFIG_RCU_CPU_STALL_VERBOSE) printk(KERN_INFO "\tVerbose stalled-CPUs detection is disabled.\n"); #endif #if NUM_RCU_LVL_4 != 0 diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c index 458e032a3a30..d15430b9d122 100644 --- a/kernel/rcutree_trace.c +++ b/kernel/rcutree_trace.c @@ -64,7 +64,9 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp) rdp->dynticks_fqs); #endif /* #ifdef CONFIG_NO_HZ */ seq_printf(m, " of=%lu ri=%lu", rdp->offline_fqs, rdp->resched_ipi); - seq_printf(m, " ql=%ld b=%ld\n", rdp->qlen, rdp->blimit); + seq_printf(m, " ql=%ld b=%ld", rdp->qlen, rdp->blimit); + seq_printf(m, " ci=%lu co=%lu ca=%lu\n", + rdp->n_cbs_invoked, rdp->n_cbs_orphaned, rdp->n_cbs_adopted); } #define PRINT_RCU_DATA(name, func, m) \ @@ -119,7 +121,9 @@ static void print_one_rcu_data_csv(struct seq_file *m, struct rcu_data *rdp) rdp->dynticks_fqs); #endif /* #ifdef CONFIG_NO_HZ */ seq_printf(m, ",%lu,%lu", rdp->offline_fqs, rdp->resched_ipi); - seq_printf(m, ",%ld,%ld\n", rdp->qlen, rdp->blimit); + seq_printf(m, ",%ld,%ld", rdp->qlen, rdp->blimit); + seq_printf(m, ",%lu,%lu,%lu\n", + rdp->n_cbs_invoked, rdp->n_cbs_orphaned, rdp->n_cbs_adopted); } static int show_rcudata_csv(struct seq_file *m, void *unused) @@ -128,7 +132,7 @@ static int show_rcudata_csv(struct seq_file *m, void *unused) #ifdef CONFIG_NO_HZ seq_puts(m, "\"dt\",\"dt nesting\",\"dn\",\"df\","); #endif /* #ifdef CONFIG_NO_HZ */ - seq_puts(m, "\"of\",\"ri\",\"ql\",\"b\"\n"); + seq_puts(m, "\"of\",\"ri\",\"ql\",\"b\",\"ci\",\"co\",\"ca\"\n"); #ifdef CONFIG_TREE_PREEMPT_RCU seq_puts(m, "\"rcu_preempt:\"\n"); PRINT_RCU_DATA(rcu_preempt_data, print_one_rcu_data_csv, m); diff --git a/kernel/srcu.c b/kernel/srcu.c index 2980da3fd509..c71e07500536 100644 --- a/kernel/srcu.c +++ b/kernel/srcu.c @@ -46,11 +46,9 @@ static int init_srcu_struct_fields(struct srcu_struct *sp) int __init_srcu_struct(struct srcu_struct *sp, const char *name, struct lock_class_key *key) { -#ifdef CONFIG_DEBUG_LOCK_ALLOC /* Don't re-initialize a lock while it is held. */ debug_check_no_locks_freed((void *)sp, sizeof(*sp)); lockdep_init_map(&sp->dep_map, name, key, 0); -#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ return init_srcu_struct_fields(sp); } EXPORT_SYMBOL_GPL(__init_srcu_struct); diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index cba079370f7f..21ac83070a80 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -540,6 +540,10 @@ config PROVE_RCU_REPEATEDLY disabling, allowing multiple RCU-lockdep warnings to be printed on a single reboot. + Say Y to allow multiple RCU-lockdep warnings per boot. + + Say N if you are unsure. + config SPARSE_RCU_POINTER bool "RCU debugging: sparse-based checks for pointer usage" default n |