From 4de376a1b14e32f550931274f06b571abc0f3d4b Mon Sep 17 00:00:00 2001 From: Pranith Kumar Date: Tue, 8 Jul 2014 17:46:50 -0400 Subject: rcu: Remove remaining read-modify-write ACCESS_ONCE() calls Change the remaining uses of ACCESS_ONCE() so that each ACCESS_ONCE() either does a load or a store, but not both. Signed-off-by: Pranith Kumar Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 6 ++++-- kernel/rcu/tree_plugin.h | 8 +++++--- 2 files changed, 9 insertions(+), 5 deletions(-) (limited to 'kernel/rcu') diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 1b70cb6..4b526ca4 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -1684,7 +1684,8 @@ static int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in) if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) { raw_spin_lock_irq(&rnp->lock); smp_mb__after_unlock_lock(); - ACCESS_ONCE(rsp->gp_flags) &= ~RCU_GP_FLAG_FQS; + ACCESS_ONCE(rsp->gp_flags) = + ACCESS_ONCE(rsp->gp_flags) & ~RCU_GP_FLAG_FQS; raw_spin_unlock_irq(&rnp->lock); } return fqs_state; @@ -2505,7 +2506,8 @@ static void force_quiescent_state(struct rcu_state *rsp) raw_spin_unlock_irqrestore(&rnp_old->lock, flags); return; /* Someone beat us to it. */ } - ACCESS_ONCE(rsp->gp_flags) |= RCU_GP_FLAG_FQS; + ACCESS_ONCE(rsp->gp_flags) = + ACCESS_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS; raw_spin_unlock_irqrestore(&rnp_old->lock, flags); wake_up(&rsp->gp_wq); /* Memory barrier implied by wake_up() path. */ } diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index a7997e2..218fae3 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -897,7 +897,8 @@ void synchronize_rcu_expedited(void) /* Clean up and exit. */ smp_mb(); /* ensure expedited GP seen before counter increment. */ - ACCESS_ONCE(sync_rcu_preempt_exp_count)++; + ACCESS_ONCE(sync_rcu_preempt_exp_count) = + sync_rcu_preempt_exp_count + 1; unlock_mb_ret: mutex_unlock(&sync_rcu_preempt_exp_mutex); mb_ret: @@ -2428,8 +2429,9 @@ static int rcu_nocb_kthread(void *arg) list = next; } trace_rcu_batch_end(rdp->rsp->name, c, !!list, 0, 0, 1); - ACCESS_ONCE(rdp->nocb_p_count) -= c; - ACCESS_ONCE(rdp->nocb_p_count_lazy) -= cl; + ACCESS_ONCE(rdp->nocb_p_count) = rdp->nocb_p_count - c; + ACCESS_ONCE(rdp->nocb_p_count_lazy) = + rdp->nocb_p_count_lazy - cl; rdp->n_nocbs_invoked += c; } return 0; -- cgit v1.1 From bf33eb1aef23e8049cd222471d35b0988c420b18 Mon Sep 17 00:00:00 2001 From: Pranith Kumar Date: Tue, 8 Jul 2014 18:26:10 -0400 Subject: rcu: Fix sparse warning about rcu_batches_completed_preempt() being non-static fix sparse warning about rcu_batches_completed_preempt() being non-static by marking it as static Signed-off-by: Pranith Kumar Signed-off-by: Paul E. McKenney --- kernel/rcu/tree_plugin.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/rcu') diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 218fae3..5defa2f 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -134,7 +134,7 @@ static void __init rcu_bootup_announce(void) * Return the number of RCU-preempt batches processed thus far * for debug and statistics. */ -long rcu_batches_completed_preempt(void) +static long rcu_batches_completed_preempt(void) { return rcu_preempt_state.completed; } -- cgit v1.1 From f534ed1fd71cea885a59255d9b44c3b17df03eb1 Mon Sep 17 00:00:00 2001 From: Pranith Kumar Date: Tue, 8 Jul 2014 18:26:11 -0400 Subject: rcu: Use bool type for return value in rcu_is_watching() Use a bool type for return in rcu_is_watching(). Signed-off-by: Pranith Kumar Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/rcu') diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 4b526ca4..253ea55 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -819,7 +819,7 @@ bool notrace __rcu_is_watching(void) */ bool notrace rcu_is_watching(void) { - int ret; + bool ret; preempt_disable(); ret = __rcu_is_watching(); -- cgit v1.1 From d0bc90fd37e50e4ea22c51c26947fd78c2a7a6c2 Mon Sep 17 00:00:00 2001 From: Pranith Kumar Date: Tue, 8 Jul 2014 18:26:13 -0400 Subject: rcu: Return bool type for rcu_try_advance_all_cbs() Return a bool type instead of 0 in rcu_try_advance_all_cbs(). Signed-off-by: Pranith Kumar Signed-off-by: Paul E. McKenney --- kernel/rcu/tree_plugin.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/rcu') diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 5defa2f..bb56456 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -1626,7 +1626,7 @@ static bool __maybe_unused rcu_try_advance_all_cbs(void) /* Exit early if we advanced recently. */ if (jiffies == rdtp->last_advance_all) - return 0; + return false; rdtp->last_advance_all = jiffies; for_each_rcu_flavor(rsp) { -- cgit v1.1 From e02b2edfa13878c6671d31d5c736f56f89d99bf1 Mon Sep 17 00:00:00 2001 From: Pranith Kumar Date: Wed, 9 Jul 2014 00:08:17 -0400 Subject: rcu: Use true/false instead of 1/0 for a bool type This commit uses true/false instead of 1/0 for bool types in rcu_gp_fqs() and force_qs_rnp(). Signed-off-by: Pranith Kumar Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel/rcu') diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 253ea55..2719978 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -1668,7 +1668,7 @@ static int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in) if (fqs_state == RCU_SAVE_DYNTICK) { /* Collect dyntick-idle snapshots. */ if (is_sysidle_rcu_state(rsp)) { - isidle = 1; + isidle = true; maxj = jiffies - ULONG_MAX / 4; } force_qs_rnp(rsp, dyntick_save_progress_counter, @@ -1677,7 +1677,7 @@ static int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in) fqs_state = RCU_FORCE_QS; } else { /* Handle dyntick-idle and offline CPUs. */ - isidle = 0; + isidle = false; force_qs_rnp(rsp, rcu_implicit_dynticks_qs, &isidle, &maxj); } /* Clear flag to prevent immediate re-entry. */ @@ -2450,7 +2450,7 @@ static void force_qs_rnp(struct rcu_state *rsp, for (; cpu <= rnp->grphi; cpu++, bit <<= 1) { if ((rnp->qsmask & bit) != 0) { if ((rnp->qsmaskinit & bit) != 0) - *isidle = 0; + *isidle = false; if (f(per_cpu_ptr(rsp->rda, cpu), isidle, maxj)) mask |= bit; } -- cgit v1.1 From 85b39d305bfe809a11ff2770d380be3e2465beec Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 8 Jul 2014 15:17:59 -0700 Subject: rcu: Uninline rcu_read_lock_held() This commit uninlines rcu_read_lock_held(). According to "size vmlinux" this saves 28549 in .text: - 5541731 3014560 14757888 23314179 + 5513182 3026848 14757888 23297918 Note: it looks as if the data grows by 12288 bytes but this is not true, it does not actually grow. But .data starts with ALIGN(THREAD_SIZE) and since .text shrinks the padding grows, and thus .data grows too as it seen by /bin/size. diff System.map: - ffffffff81510000 D _sdata - ffffffff81510000 D init_thread_union + ffffffff81509000 D _sdata + ffffffff8150c000 D init_thread_union Perhaps we can change vmlinux.lds.S to .data itself, so that /bin/size can't "wrongly" report that .data grows if .text shinks. Signed-off-by: Oleg Nesterov Signed-off-by: Paul E. McKenney --- kernel/rcu/update.c | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) (limited to 'kernel/rcu') diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 4056d79..ea8ea7b 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -137,6 +137,38 @@ int notrace debug_lockdep_rcu_enabled(void) EXPORT_SYMBOL_GPL(debug_lockdep_rcu_enabled); /** + * rcu_read_lock_held() - might we be in RCU read-side critical section? + * + * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an RCU + * read-side critical section. In absence of CONFIG_DEBUG_LOCK_ALLOC, + * this assumes we are in an RCU read-side critical section unless it can + * prove otherwise. This is useful for debug checks in functions that + * require that they be called within an RCU read-side critical section. + * + * Checks debug_lockdep_rcu_enabled() to prevent false positives during boot + * and while lockdep is disabled. + * + * Note that rcu_read_lock() and the matching rcu_read_unlock() must + * occur in the same context, for example, it is illegal to invoke + * rcu_read_unlock() in process context if the matching rcu_read_lock() + * was invoked from within an irq handler. + * + * Note that rcu_read_lock() is disallowed if the CPU is either idle or + * offline from an RCU perspective, so check for those as well. + */ +int rcu_read_lock_held(void) +{ + if (!debug_lockdep_rcu_enabled()) + return 1; + if (!rcu_is_watching()) + return 0; + if (!rcu_lockdep_current_cpu_online()) + return 0; + return lock_is_held(&rcu_lock_map); +} +EXPORT_SYMBOL_GPL(rcu_read_lock_held); + +/** * rcu_read_lock_bh_held() - might we be in RCU-bh read-side critical section? * * Check for bottom half being disabled, which covers both the -- cgit v1.1 From a8a29b3b7b18251c4e3ffce501f25ae868302a75 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Sat, 12 Jul 2014 19:01:49 +0200 Subject: rcu: Define tracepoint strings only if CONFIG_TRACING is set Commit f7f7bac9cb1c ("rcu: Have the RCU tracepoints use the tracepoint_string infrastructure") unconditionally populates the __tracepoint_str input section, but this section is not assigned an output section if CONFIG_TRACING is not set. This results in the __tracepoint_str turning up in unexpected places, i.e., after _edata. Signed-off-by: Ard Biesheuvel Reviewed-by: Steven Rostedt Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) (limited to 'kernel/rcu') diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 2719978..dc52dc3 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -79,9 +79,18 @@ static struct lock_class_key rcu_fqs_class[RCU_NUM_LVLS]; * the tracing userspace tools to be able to decipher the string * address to the matching string. */ -#define RCU_STATE_INITIALIZER(sname, sabbr, cr) \ +#ifdef CONFIG_TRACING +# define DEFINE_RCU_TPS(sname) \ static char sname##_varname[] = #sname; \ -static const char *tp_##sname##_varname __used __tracepoint_string = sname##_varname; \ +static const char *tp_##sname##_varname __used __tracepoint_string = sname##_varname; +# define RCU_STATE_NAME(sname) sname##_varname +#else +# define DEFINE_RCU_TPS(sname) +# define RCU_STATE_NAME(sname) __stringify(sname) +#endif + +#define RCU_STATE_INITIALIZER(sname, sabbr, cr) \ +DEFINE_RCU_TPS(sname) \ struct rcu_state sname##_state = { \ .level = { &sname##_state.node[0] }, \ .call = cr, \ @@ -93,7 +102,7 @@ struct rcu_state sname##_state = { \ .orphan_donetail = &sname##_state.orphan_donelist, \ .barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \ .onoff_mutex = __MUTEX_INITIALIZER(sname##_state.onoff_mutex), \ - .name = sname##_varname, \ + .name = RCU_STATE_NAME(sname), \ .abbr = sabbr, \ }; \ DEFINE_PER_CPU(struct rcu_data, sname##_data) -- cgit v1.1 From fafb6e843f229a6e842a22773f16d93194ca06e4 Mon Sep 17 00:00:00 2001 From: Pranith Kumar Date: Tue, 15 Jul 2014 18:31:47 -0400 Subject: rcu: Update tiny.c references to tree.c This commit updates the references to rcutree.c which is now rcu/tree.c Signed-off-by: Pranith Kumar Signed-off-by: Paul E. McKenney --- kernel/rcu/tiny.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/rcu') diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c index d9efcc13..6bd785c 100644 --- a/kernel/rcu/tiny.c +++ b/kernel/rcu/tiny.c @@ -51,7 +51,7 @@ static long long rcu_dynticks_nesting = DYNTICK_TASK_EXIT_IDLE; #include "tiny_plugin.h" -/* Common code for rcu_idle_enter() and rcu_irq_exit(), see kernel/rcutree.c. */ +/* Common code for rcu_idle_enter() and rcu_irq_exit(), see kernel/rcu/tree.c. */ static void rcu_idle_enter_common(long long newval) { if (newval) { @@ -114,7 +114,7 @@ void rcu_irq_exit(void) } EXPORT_SYMBOL_GPL(rcu_irq_exit); -/* Common code for rcu_idle_exit() and rcu_irq_enter(), see kernel/rcutree.c. */ +/* Common code for rcu_idle_exit() and rcu_irq_enter(), see kernel/rcu/tree.c. */ static void rcu_idle_exit_common(long long oldval) { if (oldval) { -- cgit v1.1 From 66d701ea7e148f8ed8b1497c9159fbf6175d462f Mon Sep 17 00:00:00 2001 From: Pranith Kumar Date: Wed, 16 Jul 2014 22:20:33 -0400 Subject: rcu: Remove stale comment in tree.c This commit removes a stale comment in rcu/tree.c which was left out when some code was moved around previously in commit 2036d94a7b61 ("rcu: Rework detection of use of RCU by offline CPUs") For reference, the following updated comment exists a few lines below this which means the same: /* Remove the outgoing CPU from the masks in the rcu_node hierarchy. */ Signed-off-by: Pranith Kumar Reviewed-by: Josh Triplett Reviewed-by: Lai Jiangshan Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'kernel/rcu') diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index dc52dc3..dd6c8b5 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -2220,8 +2220,6 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp) /* Adjust any no-longer-needed kthreads. */ rcu_boost_kthread_setaffinity(rnp, -1); - /* Remove the dead CPU from the bitmasks in the rcu_node hierarchy. */ - /* Exclude any attempts to start a new grace period. */ mutex_lock(&rsp->onoff_mutex); raw_spin_lock_irqsave(&rsp->orphan_lock, flags); -- cgit v1.1 From 9fdd3bc9005824704f9802bec7b3e06f5edae434 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 29 Jul 2014 14:50:47 -0700 Subject: rcu: Break more call_rcu() deadlock involving scheduler and perf Commit 96d3fd0d315a9 (rcu: Break call_rcu() deadlock involving scheduler and perf) covered the case where __call_rcu_nocb_enqueue() needs to wake the rcuo kthread due to the queue being initially empty, but did not do anything for the case where the queue was overflowing. This commit therefore also defers wakeup for the overflow case. Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.h | 9 +++++++-- kernel/rcu/tree_plugin.h | 26 ++++++++++++++++++-------- 2 files changed, 25 insertions(+), 10 deletions(-) (limited to 'kernel/rcu') diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 6a86eb7..e33562f 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -350,7 +350,7 @@ struct rcu_data { 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. */ + int 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; @@ -383,6 +383,11 @@ struct rcu_data { #define RCU_FORCE_QS 3 /* Need to force quiescent state. */ #define RCU_SIGNAL_INIT RCU_SAVE_DYNTICK +/* Values for nocb_defer_wakeup field in struct rcu_data. */ +#define RCU_NOGP_WAKE_NOT 0 +#define RCU_NOGP_WAKE 1 +#define RCU_NOGP_WAKE_FORCE 2 + #define RCU_JIFFIES_TILL_FORCE_QS (1 + (HZ > 250) + (HZ > 500)) /* For jiffies_till_first_fqs and */ /* and jiffies_till_next_fqs. */ @@ -589,7 +594,7 @@ static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp, static bool rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp, struct rcu_data *rdp, unsigned long flags); -static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp); +static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp); static void do_nocb_deferred_wakeup(struct rcu_data *rdp); static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp); static void rcu_spawn_nocb_kthreads(struct rcu_state *rsp); diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index bb56456..d67cc5c 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -2121,16 +2121,23 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp, trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WakeEmpty")); } else { - rdp->nocb_defer_wakeup = true; + rdp->nocb_defer_wakeup = RCU_NOGP_WAKE; trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WakeEmptyIsDeferred")); } rdp->qlen_last_fqs_check = 0; } else if (len > rdp->qlen_last_fqs_check + qhimark) { /* ... or if many callbacks queued. */ - wake_nocb_leader(rdp, true); + if (!irqs_disabled_flags(flags)) { + wake_nocb_leader(rdp, true); + trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, + TPS("WakeOvf")); + } else { + rdp->nocb_defer_wakeup = RCU_NOGP_WAKE_FORCE; + trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, + TPS("WakeOvfIsDeferred")); + } rdp->qlen_last_fqs_check = LONG_MAX / 2; - trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WakeOvf")); } else { trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WakeNot")); } @@ -2438,7 +2445,7 @@ static int rcu_nocb_kthread(void *arg) } /* Is a deferred wakeup of rcu_nocb_kthread() required? */ -static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp) +static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp) { return ACCESS_ONCE(rdp->nocb_defer_wakeup); } @@ -2446,11 +2453,14 @@ static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp) /* Do a deferred wakeup of rcu_nocb_kthread(). */ static void do_nocb_deferred_wakeup(struct rcu_data *rdp) { + int ndw; + if (!rcu_nocb_need_deferred_wakeup(rdp)) return; - ACCESS_ONCE(rdp->nocb_defer_wakeup) = false; - wake_nocb_leader(rdp, false); - trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("DeferredWakeEmpty")); + ndw = ACCESS_ONCE(rdp->nocb_defer_wakeup); + ACCESS_ONCE(rdp->nocb_defer_wakeup) = RCU_NOGP_WAKE_NOT; + wake_nocb_leader(rdp, ndw == RCU_NOGP_WAKE_FORCE); + trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("DeferredWake")); } /* Initialize per-rcu_data variables for no-CBs CPUs. */ @@ -2557,7 +2567,7 @@ static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp) { } -static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp) +static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp) { return false; } -- cgit v1.1 From ade9862470dd0595d8e292ecea8445ed90b98df5 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 31 Jul 2014 16:02:33 -0700 Subject: rcu: Make TINY_RCU tinier by putting error checks under #ifdef The rcu_idle_enter_common() and rcu_idle_exit_common() functions contain error checks that have to the best of my knowledge have never triggered over the past several years. These are nevertheless valuable when creating new architectures or doing other low-level changes, so the checks should not be deleted. This commit instead places these checks under #ifdef CONFIG_RCU_TRACE so that they are executed only when specifically requested. The savings are significant: Before: text data bss dec hex filename 1749 39 0 1788 6fc /tmp/b/kernel/rcu/tiny.o 632 152 0 784 310 /tmp/b/kernel/rcu/update.o ---- 2572 After: text data bss dec hex filename 1281 37 0 1318 526 /tmp/b/kernel/rcu/tiny.o 632 152 0 784 310 /tmp/b/kernel/rcu/update.o ---- 2102 This amounts to 470 bytes, or 18% of the original. Switched from #ifdef to IS_ENABLED() on Josh Triplett's advice. Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- kernel/rcu/tiny.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/rcu') diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c index 6bd785c..4a55a24 100644 --- a/kernel/rcu/tiny.c +++ b/kernel/rcu/tiny.c @@ -62,7 +62,7 @@ static void rcu_idle_enter_common(long long newval) } RCU_TRACE(trace_rcu_dyntick(TPS("Start"), rcu_dynticks_nesting, newval)); - if (!is_idle_task(current)) { + if (IS_ENABLED(CONFIG_RCU_TRACE) && !is_idle_task(current)) { struct task_struct *idle __maybe_unused = idle_task(smp_processor_id()); RCU_TRACE(trace_rcu_dyntick(TPS("Entry error: not idle task"), @@ -123,7 +123,7 @@ static void rcu_idle_exit_common(long long oldval) return; } RCU_TRACE(trace_rcu_dyntick(TPS("End"), oldval, rcu_dynticks_nesting)); - if (!is_idle_task(current)) { + if (IS_ENABLED(CONFIG_RCU_TRACE) && !is_idle_task(current)) { struct task_struct *idle __maybe_unused = idle_task(smp_processor_id()); RCU_TRACE(trace_rcu_dyntick(TPS("Exit error: not idle task"), -- cgit v1.1 From 2aa792e6faf1a00f5accf1f69e87e11a390ba2cd Mon Sep 17 00:00:00 2001 From: Pranith Kumar Date: Tue, 12 Aug 2014 13:07:47 -0400 Subject: rcu: Use rcu_gp_kthread_wake() to wake up grace period kthreads The rcu_gp_kthread_wake() function checks for three conditions before waking up grace period kthreads: * Is the thread we are trying to wake up the current thread? * Are the gp_flags zero? (all threads wait on non-zero gp_flags condition) * Is there no thread created for this flavour, hence nothing to wake up? If any one of these condition is true, we do not call wake_up(). It was found that there are quite a few avoidable wake ups both during idle time and under stress induced by rcutorture. Idle: Total:66000, unnecessary:66000, case1:61827, case2:66000, case3:0 Total:68000, unnecessary:68000, case1:63696, case2:68000, case3:0 rcutorture: Total:254000, unnecessary:254000, case1:199913, case2:254000, case3:0 Total:256000, unnecessary:256000, case1:201784, case2:256000, case3:0 Here case{1-3} are the cases listed above. We can avoid these wake ups by using rcu_gp_kthread_wake() to conditionally wake up the grace period kthreads. There is a comment about an implied barrier supplied by the wake_up() logic. This barrier is necessary for the awakened thread to see the updated ->gp_flags. This flag is always being updated with the root node lock held. Also, the awakened thread tries to acquire the root node lock before reading ->gp_flags because of which there is proper ordering. Hence this commit tries to avoid calling wake_up() whenever we can by using rcu_gp_kthread_wake() function. Signed-off-by: Pranith Kumar CC: Mathieu Desnoyers Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/rcu') diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index dd6c8b5..9e83cd9 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -1938,7 +1938,7 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags) { WARN_ON_ONCE(!rcu_gp_in_progress(rsp)); raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags); - wake_up(&rsp->gp_wq); /* Memory barrier implied by wake_up() path. */ + rcu_gp_kthread_wake(rsp); } /* @@ -2516,7 +2516,7 @@ static void force_quiescent_state(struct rcu_state *rsp) ACCESS_ONCE(rsp->gp_flags) = ACCESS_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS; raw_spin_unlock_irqrestore(&rnp_old->lock, flags); - wake_up(&rsp->gp_wq); /* Memory barrier implied by wake_up() path. */ + rcu_gp_kthread_wake(rsp); } /* -- cgit v1.1 From 73a860cd58a1eb258e889b615cebf738ab33aa23 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 14 Aug 2014 10:28:23 -0700 Subject: rcu: Replace flush_signals() with WARN_ON(signal_pending()) Currently, when RCU awakens from a wait_event_interruptible() that might have awakened prematurely, it does a flush_signals(). This is done on the off-chance that someone figured out how to deliver a signal to a kthread, which is supposed to be impossible. Given that this is supposed to be impossible, this commit changes the flush_signals() calls into WARN_ON(signal_pending()). Reported-by: Oleg Nesterov Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.c | 4 ++-- kernel/rcu/tree_plugin.h | 6 +++--- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'kernel/rcu') diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 9e83cd9..3e002c1 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -1796,7 +1796,7 @@ static int __noreturn rcu_gp_kthread(void *arg) if (rcu_gp_init(rsp)) break; cond_resched(); - flush_signals(current); + WARN_ON(signal_pending(current)); trace_rcu_grace_period(rsp->name, ACCESS_ONCE(rsp->gpnum), TPS("reqwaitsig")); @@ -1842,7 +1842,7 @@ static int __noreturn rcu_gp_kthread(void *arg) } else { /* Deal with stray signal. */ cond_resched(); - flush_signals(current); + WARN_ON(signal_pending(current)); trace_rcu_grace_period(rsp->name, ACCESS_ONCE(rsp->gpnum), TPS("fqswaitsig")); diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index d67cc5c..bbb0a0c 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -2237,7 +2237,7 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp) (d = ULONG_CMP_GE(ACCESS_ONCE(rnp->completed), c))); if (likely(d)) break; - flush_signals(current); + WARN_ON(signal_pending(current)); trace_rcu_future_gp(rnp, rdp, c, TPS("ResumeWait")); } trace_rcu_future_gp(rnp, rdp, c, TPS("EndWait")); @@ -2296,7 +2296,7 @@ wait_again: if (!rcu_nocb_poll) trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, "WokeEmpty"); - flush_signals(current); + WARN_ON(signal_pending(current)); schedule_timeout_interruptible(1); /* Rescan in case we were a victim of memory ordering. */ @@ -2375,7 +2375,7 @@ static void nocb_follower_wait(struct rcu_data *rdp) if (!rcu_nocb_poll) trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, "WokeEmpty"); - flush_signals(current); + WARN_ON(signal_pending(current)); schedule_timeout_interruptible(1); } } -- cgit v1.1 From 58ade2dbe9a253635e0835adedfaa822849aa3a3 Mon Sep 17 00:00:00 2001 From: Pranith Kumar Date: Wed, 11 Jun 2014 16:39:43 -0400 Subject: rcutorture: Fix a sparse warning by marking boost_mutex static This commit fixes the following sparse warning by marking boost_mutex static: kernel/rcu/rcutorture.c:185:1: warning: symbol 'boost_mutex' was not declared. Should it be static? Signed-off-by: Pranith Kumar Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- kernel/rcu/rcutorture.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/rcu') diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index 948a769..7e67711 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -182,7 +182,7 @@ static u64 notrace rcu_trace_clock_local(void) #endif /* #else #ifdef CONFIG_RCU_TRACE */ static unsigned long boost_starttime; /* jiffies of next boost test start. */ -DEFINE_MUTEX(boost_mutex); /* protect setting boost_starttime */ +static DEFINE_MUTEX(boost_mutex); /* protect setting boost_starttime */ /* and boost task create/destroy. */ static atomic_t barrier_cbs_count; /* Barrier callbacks registered. */ static bool barrier_phase; /* Test phase. */ -- cgit v1.1 From eea203fea3484598280a07fe503e025e886297fb Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Mon, 14 Jul 2014 09:16:15 -0400 Subject: rcu: Use pr_alert/pr_cont for printing logs User pr_alert/pr_cont for printing the logs from rcutorture module directly instead of writing it to a buffer and then printing it. This allows us from not having to allocate such buffers. Also remove a resulting empty function. I tested this using the parse-torture.sh script as follows: $ dmesg | grep torture > log.txt $ bash parse-torture.sh log.txt test $ There were no warnings which means that parsing went fine. Signed-off-by: Joe Perches Signed-off-by: Pranith Kumar Signed-off-by: Paul E. McKenney --- kernel/rcu/rcutorture.c | 127 +++++++++++++++++++++--------------------------- 1 file changed, 56 insertions(+), 71 deletions(-) (limited to 'kernel/rcu') diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index 7e67711..ff4f0c7 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -242,7 +242,7 @@ struct rcu_torture_ops { void (*call)(struct rcu_head *head, void (*func)(struct rcu_head *rcu)); void (*cb_barrier)(void); void (*fqs)(void); - void (*stats)(char *page); + void (*stats)(void); int irq_capable; int can_boost; const char *name; @@ -525,21 +525,21 @@ static void srcu_torture_barrier(void) srcu_barrier(&srcu_ctl); } -static void srcu_torture_stats(char *page) +static void srcu_torture_stats(void) { int cpu; int idx = srcu_ctl.completed & 0x1; - page += sprintf(page, "%s%s per-CPU(idx=%d):", - torture_type, TORTURE_FLAG, idx); + pr_alert("%s%s per-CPU(idx=%d):", + torture_type, TORTURE_FLAG, idx); for_each_possible_cpu(cpu) { long c0, c1; c0 = (long)per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[!idx]; c1 = (long)per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[idx]; - page += sprintf(page, " %d(%ld,%ld)", cpu, c0, c1); + pr_cont(" %d(%ld,%ld)", cpu, c0, c1); } - sprintf(page, "\n"); + pr_cont("\n"); } static void srcu_torture_synchronize_expedited(void) @@ -1031,10 +1031,15 @@ rcu_torture_reader(void *arg) } /* - * Create an RCU-torture statistics message in the specified buffer. + * Print torture statistics. Caller must ensure that there is only + * one call to this function at a given time!!! This is normally + * accomplished by relying on the module system to only have one copy + * of the module loaded, and then by giving the rcu_torture_stats + * kthread full control (or the init/cleanup functions when rcu_torture_stats + * thread is not running). */ static void -rcu_torture_printk(char *page) +rcu_torture_stats_print(void) { int cpu; int i; @@ -1052,55 +1057,60 @@ rcu_torture_printk(char *page) if (pipesummary[i] != 0) break; } - page += sprintf(page, "%s%s ", torture_type, TORTURE_FLAG); - page += sprintf(page, - "rtc: %p ver: %lu tfle: %d rta: %d rtaf: %d rtf: %d ", - rcu_torture_current, - rcu_torture_current_version, - list_empty(&rcu_torture_freelist), - atomic_read(&n_rcu_torture_alloc), - atomic_read(&n_rcu_torture_alloc_fail), - atomic_read(&n_rcu_torture_free)); - page += sprintf(page, "rtmbe: %d rtbke: %ld rtbre: %ld ", - atomic_read(&n_rcu_torture_mberror), - n_rcu_torture_boost_ktrerror, - n_rcu_torture_boost_rterror); - page += sprintf(page, "rtbf: %ld rtb: %ld nt: %ld ", - n_rcu_torture_boost_failure, - n_rcu_torture_boosts, - n_rcu_torture_timers); - page = torture_onoff_stats(page); - page += sprintf(page, "barrier: %ld/%ld:%ld", - n_barrier_successes, - n_barrier_attempts, - n_rcu_torture_barrier_error); - page += sprintf(page, "\n%s%s ", torture_type, TORTURE_FLAG); + + pr_alert("%s%s ", torture_type, TORTURE_FLAG); + pr_cont("rtc: %p ver: %lu tfle: %d rta: %d rtaf: %d rtf: %d ", + rcu_torture_current, + rcu_torture_current_version, + list_empty(&rcu_torture_freelist), + atomic_read(&n_rcu_torture_alloc), + atomic_read(&n_rcu_torture_alloc_fail), + atomic_read(&n_rcu_torture_free)); + pr_cont("rtmbe: %d rtbke: %ld rtbre: %ld ", + atomic_read(&n_rcu_torture_mberror), + n_rcu_torture_boost_ktrerror, + n_rcu_torture_boost_rterror); + pr_cont("rtbf: %ld rtb: %ld nt: %ld ", + n_rcu_torture_boost_failure, + n_rcu_torture_boosts, + n_rcu_torture_timers); + torture_onoff_stats(); + pr_cont("barrier: %ld/%ld:%ld\n", + n_barrier_successes, + n_barrier_attempts, + n_rcu_torture_barrier_error); + + pr_alert("%s%s ", torture_type, TORTURE_FLAG); if (atomic_read(&n_rcu_torture_mberror) != 0 || n_rcu_torture_barrier_error != 0 || n_rcu_torture_boost_ktrerror != 0 || n_rcu_torture_boost_rterror != 0 || n_rcu_torture_boost_failure != 0 || i > 1) { - page += sprintf(page, "!!! "); + pr_cont("%s", "!!! "); atomic_inc(&n_rcu_torture_error); WARN_ON_ONCE(1); } - page += sprintf(page, "Reader Pipe: "); + pr_cont("Reader Pipe: "); for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++) - page += sprintf(page, " %ld", pipesummary[i]); - page += sprintf(page, "\n%s%s ", torture_type, TORTURE_FLAG); - page += sprintf(page, "Reader Batch: "); + pr_cont(" %ld", pipesummary[i]); + pr_cont("\n"); + + pr_alert("%s%s ", torture_type, TORTURE_FLAG); + pr_cont("Reader Batch: "); for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++) - page += sprintf(page, " %ld", batchsummary[i]); - page += sprintf(page, "\n%s%s ", torture_type, TORTURE_FLAG); - page += sprintf(page, "Free-Block Circulation: "); + pr_cont(" %ld", batchsummary[i]); + pr_cont("\n"); + + pr_alert("%s%s ", torture_type, TORTURE_FLAG); + pr_cont("Free-Block Circulation: "); for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++) { - page += sprintf(page, " %d", - atomic_read(&rcu_torture_wcount[i])); + pr_cont(" %d", atomic_read(&rcu_torture_wcount[i])); } - page += sprintf(page, "\n"); + pr_cont("\n"); + if (cur_ops->stats) - cur_ops->stats(page); + cur_ops->stats(); if (rtcv_snap == rcu_torture_current_version && rcu_torture_current != NULL) { int __maybe_unused flags; @@ -1109,10 +1119,9 @@ rcu_torture_printk(char *page) rcutorture_get_gp_data(cur_ops->ttype, &flags, &gpnum, &completed); - page += sprintf(page, - "??? Writer stall state %d g%lu c%lu f%#x\n", - rcu_torture_writer_state, - gpnum, completed, flags); + pr_alert("??? Writer stall state %d g%lu c%lu f%#x\n", + rcu_torture_writer_state, + gpnum, completed, flags); show_rcu_gp_kthreads(); rcutorture_trace_dump(); } @@ -1120,30 +1129,6 @@ rcu_torture_printk(char *page) } /* - * Print torture statistics. Caller must ensure that there is only - * one call to this function at a given time!!! This is normally - * accomplished by relying on the module system to only have one copy - * of the module loaded, and then by giving the rcu_torture_stats - * kthread full control (or the init/cleanup functions when rcu_torture_stats - * thread is not running). - */ -static void -rcu_torture_stats_print(void) -{ - int size = nr_cpu_ids * 200 + 8192; - char *buf; - - buf = kmalloc(size, GFP_KERNEL); - if (!buf) { - pr_err("rcu-torture: Out of memory, need: %d", size); - return; - } - rcu_torture_printk(buf); - pr_alert("%s", buf); - kfree(buf); -} - -/* * Periodically prints torture statistics, if periodic statistics printing * was specified via the stat_interval module parameter. */ -- cgit v1.1 From 38706bc5a29a73645e512c06ffb759fb56259d83 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 18 Aug 2014 21:12:17 -0700 Subject: rcutorture: Add callback-flood test Although RCU is designed to handle arbitrary floods of callbacks, this capability is not routinely tested. This commit therefore adds a cbflood capability in which kthreads repeatedly registers large numbers of callbacks. One such kthread is created for each four CPUs (rounding up), and the test may be controlled by several cbflood_* kernel boot parameters, which control the number of bursts per flood, the number of callbacks per burst, the time between bursts, and the time between floods. The default values are large enough to exercise RCU's emergency responses to callback flooding. Signed-off-by: Paul E. McKenney Cc: David Miller Reviewed-by: Pranith Kumar --- kernel/rcu/rcutorture.c | 86 ++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 85 insertions(+), 1 deletion(-) (limited to 'kernel/rcu') diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index ff4f0c7..0bcd53a 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -49,11 +49,19 @@ #include #include #include +#include MODULE_LICENSE("GPL"); MODULE_AUTHOR("Paul E. McKenney and Josh Triplett "); +torture_param(int, cbflood_inter_holdoff, HZ, + "Holdoff between floods (jiffies)"); +torture_param(int, cbflood_intra_holdoff, 1, + "Holdoff between bursts (jiffies)"); +torture_param(int, cbflood_n_burst, 3, "# bursts in flood, zero to disable"); +torture_param(int, cbflood_n_per_burst, 20000, + "# callbacks per burst in flood"); torture_param(int, fqs_duration, 0, "Duration of fqs bursts (us), 0 to disable"); torture_param(int, fqs_holdoff, 0, "Holdoff time within fqs bursts (us)"); @@ -96,10 +104,12 @@ module_param(torture_type, charp, 0444); MODULE_PARM_DESC(torture_type, "Type of RCU to torture (rcu, rcu_bh, ...)"); static int nrealreaders; +static int ncbflooders; static struct task_struct *writer_task; static struct task_struct **fakewriter_tasks; static struct task_struct **reader_tasks; static struct task_struct *stats_task; +static struct task_struct **cbflood_task; static struct task_struct *fqs_task; static struct task_struct *boost_tasks[NR_CPUS]; static struct task_struct *stall_task; @@ -138,6 +148,7 @@ static long n_rcu_torture_boosts; static long n_rcu_torture_timers; static long n_barrier_attempts; static long n_barrier_successes; +static atomic_long_t n_cbfloods; static struct list_head rcu_torture_removed; static int rcu_torture_writer_state; @@ -707,6 +718,58 @@ checkwait: stutter_wait("rcu_torture_boost"); return 0; } +static void rcu_torture_cbflood_cb(struct rcu_head *rhp) +{ +} + +/* + * RCU torture callback-flood kthread. Repeatedly induces bursts of calls + * to call_rcu() or analogous, increasing the probability of occurrence + * of callback-overflow corner cases. + */ +static int +rcu_torture_cbflood(void *arg) +{ + int err = 1; + int i; + int j; + struct rcu_head *rhp; + + if (cbflood_n_per_burst > 0 && + cbflood_inter_holdoff > 0 && + cbflood_intra_holdoff > 0 && + cur_ops->call && + cur_ops->cb_barrier) { + rhp = vmalloc(sizeof(*rhp) * + cbflood_n_burst * cbflood_n_per_burst); + err = !rhp; + } + if (err) { + VERBOSE_TOROUT_STRING("rcu_torture_cbflood disabled: Bad args or OOM"); + while (!torture_must_stop()) + schedule_timeout_interruptible(HZ); + return 0; + } + VERBOSE_TOROUT_STRING("rcu_torture_cbflood task started"); + do { + schedule_timeout_interruptible(cbflood_inter_holdoff); + atomic_long_inc(&n_cbfloods); + WARN_ON(signal_pending(current)); + for (i = 0; i < cbflood_n_burst; i++) { + for (j = 0; j < cbflood_n_per_burst; j++) { + cur_ops->call(&rhp[i * cbflood_n_per_burst + j], + rcu_torture_cbflood_cb); + } + schedule_timeout_interruptible(cbflood_intra_holdoff); + WARN_ON(signal_pending(current)); + } + cur_ops->cb_barrier(); + stutter_wait("rcu_torture_cbflood"); + } while (!torture_must_stop()); + torture_kthread_stopping("rcu_torture_cbflood"); + return 0; +} + /* * RCU torture force-quiescent-state kthread. Repeatedly induces * bursts of calls to force_quiescent_state(), increasing the probability @@ -1075,10 +1138,11 @@ rcu_torture_stats_print(void) n_rcu_torture_boosts, n_rcu_torture_timers); torture_onoff_stats(); - pr_cont("barrier: %ld/%ld:%ld\n", + pr_cont("barrier: %ld/%ld:%ld ", n_barrier_successes, n_barrier_attempts, n_rcu_torture_barrier_error); + pr_cont("cbflood: %ld\n", atomic_long_read(&n_cbfloods)); pr_alert("%s%s ", torture_type, TORTURE_FLAG); if (atomic_read(&n_rcu_torture_mberror) != 0 || @@ -1432,6 +1496,8 @@ rcu_torture_cleanup(void) torture_stop_kthread(rcu_torture_stats, stats_task); torture_stop_kthread(rcu_torture_fqs, fqs_task); + for (i = 0; i < ncbflooders; i++) + torture_stop_kthread(rcu_torture_cbflood, cbflood_task[i]); if ((test_boost == 1 && cur_ops->can_boost) || test_boost == 2) { unregister_cpu_notifier(&rcutorture_cpu_nb); @@ -1678,6 +1744,24 @@ rcu_torture_init(void) goto unwind; if (object_debug) rcu_test_debug_objects(); + if (cbflood_n_burst > 0) { + /* Create the cbflood threads */ + ncbflooders = (num_online_cpus() + 3) / 4; + cbflood_task = kcalloc(ncbflooders, sizeof(*cbflood_task), + GFP_KERNEL); + if (!cbflood_task) { + VERBOSE_TOROUT_ERRSTRING("out of memory"); + firsterr = -ENOMEM; + goto unwind; + } + for (i = 0; i < ncbflooders; i++) { + firsterr = torture_create_kthread(rcu_torture_cbflood, + NULL, + cbflood_task[i]); + if (firsterr) + goto unwind; + } + } rcutorture_record_test_transition(); torture_init_end(); return 0; -- cgit v1.1 From f4579fc57cf4244057b713b1f73f4dc9f0b11e97 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 25 Jul 2014 11:21:47 -0700 Subject: rcu: Fix attempt to avoid unsolicited offloading of callbacks Commit b58cc46c5f6b (rcu: Don't offload callbacks unless specifically requested) failed to adjust the callback lists of the CPUs that are known to be no-CBs CPUs only because they are also nohz_full= CPUs. This failure can result in callbacks that are posted during early boot getting stranded on nxtlist for CPUs whose no-CBs property becomes apparent late, and there can also be spurious warnings about offline CPUs posting callbacks. This commit fixes these problems by adding an early-boot rcu_init_nohz() that properly initializes the no-CBs CPUs. Note that kernels built with CONFIG_RCU_NOCB_CPU_ALL=y or with CONFIG_RCU_NOCB_CPU=n do not exhibit this bug. Neither do kernels booted without the nohz_full= boot parameter. Signed-off-by: Paul E. McKenney Reviewed-by: Pranith Kumar Tested-by: Paul Gortmaker --- kernel/rcu/tree_plugin.h | 92 ++++++++++++++++++++++++++++++++---------------- 1 file changed, 61 insertions(+), 31 deletions(-) (limited to 'kernel/rcu') diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index a7997e2..06d077c 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -85,33 +85,6 @@ static void __init rcu_bootup_announce_oddness(void) pr_info("\tBoot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf); if (nr_cpu_ids != NR_CPUS) pr_info("\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%d.\n", NR_CPUS, nr_cpu_ids); -#ifdef CONFIG_RCU_NOCB_CPU -#ifndef CONFIG_RCU_NOCB_CPU_NONE - if (!have_rcu_nocb_mask) { - zalloc_cpumask_var(&rcu_nocb_mask, GFP_KERNEL); - have_rcu_nocb_mask = true; - } -#ifdef CONFIG_RCU_NOCB_CPU_ZERO - pr_info("\tOffload RCU callbacks from CPU 0\n"); - cpumask_set_cpu(0, rcu_nocb_mask); -#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ZERO */ -#ifdef CONFIG_RCU_NOCB_CPU_ALL - pr_info("\tOffload RCU callbacks from all CPUs\n"); - cpumask_copy(rcu_nocb_mask, cpu_possible_mask); -#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ALL */ -#endif /* #ifndef CONFIG_RCU_NOCB_CPU_NONE */ - if (have_rcu_nocb_mask) { - if (!cpumask_subset(rcu_nocb_mask, cpu_possible_mask)) { - pr_info("\tNote: kernel parameter 'rcu_nocbs=' contains nonexistent CPUs.\n"); - cpumask_and(rcu_nocb_mask, cpu_possible_mask, - rcu_nocb_mask); - } - cpulist_scnprintf(nocb_buf, sizeof(nocb_buf), rcu_nocb_mask); - pr_info("\tOffload RCU callbacks from CPUs: %s.\n", nocb_buf); - if (rcu_nocb_poll) - pr_info("\tPoll for callbacks from no-CBs CPUs.\n"); - } -#endif /* #ifdef CONFIG_RCU_NOCB_CPU */ } #ifdef CONFIG_TREE_PREEMPT_RCU @@ -2451,6 +2424,67 @@ static void do_nocb_deferred_wakeup(struct rcu_data *rdp) trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("DeferredWakeEmpty")); } +void __init rcu_init_nohz(void) +{ + int cpu; + bool need_rcu_nocb_mask = true; + struct rcu_state *rsp; + +#ifdef CONFIG_RCU_NOCB_CPU_NONE + need_rcu_nocb_mask = false; +#endif /* #ifndef CONFIG_RCU_NOCB_CPU_NONE */ + +#if defined(CONFIG_NO_HZ_FULL) + if (tick_nohz_full_running && cpumask_weight(tick_nohz_full_mask)) + need_rcu_nocb_mask = true; +#endif /* #if defined(CONFIG_NO_HZ_FULL) */ + + if (!have_rcu_nocb_mask && need_rcu_nocb_mask) { + zalloc_cpumask_var(&rcu_nocb_mask, GFP_KERNEL); + have_rcu_nocb_mask = true; + } + if (!have_rcu_nocb_mask) + return; + +#ifdef CONFIG_RCU_NOCB_CPU_ZERO + pr_info("\tOffload RCU callbacks from CPU 0\n"); + cpumask_set_cpu(0, rcu_nocb_mask); +#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ZERO */ +#ifdef CONFIG_RCU_NOCB_CPU_ALL + pr_info("\tOffload RCU callbacks from all CPUs\n"); + cpumask_copy(rcu_nocb_mask, cpu_possible_mask); +#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ALL */ +#if defined(CONFIG_NO_HZ_FULL) + if (tick_nohz_full_running) + cpumask_or(rcu_nocb_mask, rcu_nocb_mask, tick_nohz_full_mask); +#endif /* #if defined(CONFIG_NO_HZ_FULL) */ + + if (!cpumask_subset(rcu_nocb_mask, cpu_possible_mask)) { + pr_info("\tNote: kernel parameter 'rcu_nocbs=' contains nonexistent CPUs.\n"); + cpumask_and(rcu_nocb_mask, cpu_possible_mask, + rcu_nocb_mask); + } + cpulist_scnprintf(nocb_buf, sizeof(nocb_buf), rcu_nocb_mask); + pr_info("\tOffload RCU callbacks from CPUs: %s.\n", nocb_buf); + if (rcu_nocb_poll) + pr_info("\tPoll for callbacks from no-CBs CPUs.\n"); + + for_each_rcu_flavor(rsp) { + for_each_cpu(cpu, rcu_nocb_mask) { + struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); + + /* + * If there are early callbacks, they will need + * to be moved to the nocb lists. + */ + WARN_ON_ONCE(rdp->nxttail[RCU_NEXT_TAIL] != + &rdp->nxtlist && + rdp->nxttail[RCU_NEXT_TAIL] != NULL); + init_nocb_callback_list(rdp); + } + } +} + /* Initialize per-rcu_data variables for no-CBs CPUs. */ static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp) { @@ -2479,10 +2513,6 @@ static void __init rcu_spawn_nocb_kthreads(struct rcu_state *rsp) if (rcu_nocb_mask == NULL) return; -#if defined(CONFIG_NO_HZ_FULL) && !defined(CONFIG_NO_HZ_FULL_ALL) - if (tick_nohz_full_running) - cpumask_or(rcu_nocb_mask, rcu_nocb_mask, tick_nohz_full_mask); -#endif /* #if defined(CONFIG_NO_HZ_FULL) && !defined(CONFIG_NO_HZ_FULL_ALL) */ if (ls == -1) { ls = int_sqrt(nr_cpu_ids); rcu_nocb_leader_stride = ls; -- cgit v1.1 From 949cccdbe6d286544ce3fe170298183eb7ada81c Mon Sep 17 00:00:00 2001 From: Pranith Kumar Date: Fri, 25 Jul 2014 16:02:07 -0700 Subject: rcu: Check the return value of zalloc_cpumask_var() This commit checks the return value of the zalloc_cpumask_var() used for allocating cpumask for rcu_nocb_mask. Signed-off-by: Pranith Kumar Signed-off-by: Paul E. McKenney Tested-by: Paul Gortmaker --- kernel/rcu/tree_plugin.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'kernel/rcu') diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 06d077c..105b0ce 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -2440,7 +2440,10 @@ void __init rcu_init_nohz(void) #endif /* #if defined(CONFIG_NO_HZ_FULL) */ if (!have_rcu_nocb_mask && need_rcu_nocb_mask) { - zalloc_cpumask_var(&rcu_nocb_mask, GFP_KERNEL); + if (!zalloc_cpumask_var(&rcu_nocb_mask, GFP_KERNEL)) { + pr_info("rcu_nocb_mask allocation failed, callback offloading disabled.\n"); + return; + } have_rcu_nocb_mask = true; } if (!have_rcu_nocb_mask) -- cgit v1.1 From c271d3a957384a162f7a6aae53455d8e8afd1f3e Mon Sep 17 00:00:00 2001 From: Pranith Kumar Date: Tue, 8 Jul 2014 18:26:14 -0400 Subject: rcu: Use true/false for return in __call_rcu_nocb() Return true/false instead of 0/1 in __call_rcu_nocb() as this returns a bool type. Signed-off-by: Pranith Kumar Signed-off-by: Paul E. McKenney Tested-by: Paul Gortmaker --- kernel/rcu/tree_plugin.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/rcu') diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 105b0ce..36c678b 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -2123,7 +2123,7 @@ static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp, { if (!rcu_is_nocb_cpu(rdp->cpu)) - return 0; + return false; __call_rcu_nocb_enqueue(rdp, rhp, &rhp->next, 1, lazy, flags); if (__is_kfree_rcu_offset((unsigned long)rhp->func)) trace_rcu_kfree_callback(rdp->rsp->name, rhp, @@ -2134,7 +2134,7 @@ static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp, trace_rcu_callback(rdp->rsp->name, rhp, -atomic_long_read(&rdp->nocb_q_count_lazy), -atomic_long_read(&rdp->nocb_q_count)); - return 1; + return true; } /* -- cgit v1.1 From 0a9e1e111b3a9e1c21d2dd27ca361cd9601d99af Mon Sep 17 00:00:00 2001 From: Pranith Kumar Date: Tue, 8 Jul 2014 18:26:15 -0400 Subject: rcu: Use true/false for return in rcu_nocb_adopt_orphan_cbs() Return true/false in rcu_nocb_adopt_orphan_cbs() instead of 0/1 as this function has return type of bool. Signed-off-by: Pranith Kumar Signed-off-by: Paul E. McKenney Tested-by: Paul Gortmaker --- kernel/rcu/tree_plugin.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/rcu') diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 36c678b..6625841 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -2150,7 +2150,7 @@ static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp, /* If this is not a no-CBs CPU, tell the caller to do it the old way. */ if (!rcu_is_nocb_cpu(smp_processor_id())) - return 0; + return false; rsp->qlen = 0; rsp->qlen_lazy = 0; @@ -2169,7 +2169,7 @@ static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp, rsp->orphan_nxtlist = NULL; rsp->orphan_nxttail = &rsp->orphan_nxtlist; } - return 1; + return true; } /* -- cgit v1.1 From 4afc7e269befc7b6e09a994e48c67e36f4a378e1 Mon Sep 17 00:00:00 2001 From: Pranith Kumar Date: Tue, 8 Jul 2014 18:26:16 -0400 Subject: rcu: Use false for return in __call_rcu_nocb() Return false instead of 0 in __call_rcu_nocb() as this has bool as return type. Signed-off-by: Pranith Kumar Signed-off-by: Paul E. McKenney Tested-by: Paul Gortmaker --- kernel/rcu/tree_plugin.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/rcu') diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 6625841..4271104 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -2574,7 +2574,7 @@ static void rcu_init_one_nocb(struct rcu_node *rnp) static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp, bool lazy, unsigned long flags) { - return 0; + return false; } static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp, -- cgit v1.1 From f4aa84ba24872e3a8e59b58bc8533cae95597f2e Mon Sep 17 00:00:00 2001 From: Pranith Kumar Date: Tue, 8 Jul 2014 18:26:17 -0400 Subject: rcu: Return false instead of 0 in rcu_nocb_adopt_orphan_cbs() Return false instead of 0 in rcu_nocb_adopt_orphan_cbs() as this has bool as return type. Signed-off-by: Pranith Kumar Signed-off-by: Paul E. McKenney Tested-by: Paul Gortmaker --- kernel/rcu/tree_plugin.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/rcu') diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 4271104..4c1af96 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -2581,7 +2581,7 @@ static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp, struct rcu_data *rdp, unsigned long flags) { - return 0; + return false; } static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp) -- cgit v1.1 From 9386c0b75dda05f535a10ea1abf1817fe292c81c Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sun, 13 Jul 2014 12:00:53 -0700 Subject: rcu: Rationalize kthread spawning Currently, RCU spawns kthreads from several different early_initcall() functions. Although this has served RCU well for quite some time, as more kthreads are added a more deterministic approach is required. This commit therefore causes all of RCU's early-boot kthreads to be spawned from a single early_initcall() function. Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett Tested-by: Paul Gortmaker --- kernel/rcu/tree.c | 4 +++- kernel/rcu/tree.h | 1 + kernel/rcu/tree_plugin.h | 12 +++--------- 3 files changed, 7 insertions(+), 10 deletions(-) (limited to 'kernel/rcu') diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 1b70cb6..9be47f4 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -3489,7 +3489,7 @@ static int rcu_pm_notify(struct notifier_block *self, } /* - * Spawn the kthread that handles this RCU flavor's grace periods. + * Spawn the kthreads that handle each RCU flavor's grace periods. */ static int __init rcu_spawn_gp_kthread(void) { @@ -3498,6 +3498,7 @@ static int __init rcu_spawn_gp_kthread(void) struct rcu_state *rsp; struct task_struct *t; + rcu_scheduler_fully_active = 1; for_each_rcu_flavor(rsp) { t = kthread_run(rcu_gp_kthread, rsp, "%s", rsp->name); BUG_ON(IS_ERR(t)); @@ -3507,6 +3508,7 @@ static int __init rcu_spawn_gp_kthread(void) raw_spin_unlock_irqrestore(&rnp->lock, flags); rcu_spawn_nocb_kthreads(rsp); } + rcu_spawn_boost_kthreads(); return 0; } early_initcall(rcu_spawn_gp_kthread); diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 6a86eb7..a966092 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -572,6 +572,7 @@ static void rcu_preempt_do_callbacks(void); static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp, struct rcu_node *rnp); #endif /* #ifdef CONFIG_RCU_BOOST */ +static void __init rcu_spawn_boost_kthreads(void); static void rcu_prepare_kthreads(int cpu); static void rcu_cleanup_after_idle(int cpu); static void rcu_prepare_for_idle(int cpu); diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 4c1af96..410c744 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -1435,14 +1435,13 @@ static struct smp_hotplug_thread rcu_cpu_thread_spec = { }; /* - * Spawn all kthreads -- called as soon as the scheduler is running. + * Spawn boost kthreads -- called as soon as the scheduler is running. */ -static int __init rcu_spawn_kthreads(void) +static void __init rcu_spawn_boost_kthreads(void) { struct rcu_node *rnp; int cpu; - rcu_scheduler_fully_active = 1; for_each_possible_cpu(cpu) per_cpu(rcu_cpu_has_work, cpu) = 0; BUG_ON(smpboot_register_percpu_thread(&rcu_cpu_thread_spec)); @@ -1452,9 +1451,7 @@ static int __init rcu_spawn_kthreads(void) rcu_for_each_leaf_node(rcu_state_p, rnp) (void)rcu_spawn_one_boost_kthread(rcu_state_p, rnp); } - return 0; } -early_initcall(rcu_spawn_kthreads); static void rcu_prepare_kthreads(int cpu) { @@ -1492,12 +1489,9 @@ static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) { } -static int __init rcu_scheduler_really_started(void) +static void __init rcu_spawn_boost_kthreads(void) { - rcu_scheduler_fully_active = 1; - return 0; } -early_initcall(rcu_scheduler_really_started); static void rcu_prepare_kthreads(int cpu) { -- cgit v1.1 From 35ce7f29a44a888c45c0a9f202f69e10613c5306 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 11 Jul 2014 11:30:24 -0700 Subject: rcu: Create rcuo kthreads only for onlined CPUs RCU currently uses for_each_possible_cpu() to spawn rcuo kthreads, which can result in more rcuo kthreads than one would expect, for example, derRichard reported 64 CPUs worth of rcuo kthreads on an 8-CPU image. This commit therefore creates rcuo kthreads only for those CPUs that actually come online. This was reported by derRichard on the OFTC IRC network. Reported-by: Richard Weinberger Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett Tested-by: Paul Gortmaker --- kernel/rcu/tree.c | 3 +- kernel/rcu/tree.h | 6 +++- kernel/rcu/tree_plugin.h | 90 ++++++++++++++++++++++++++++++++++++++++++------ 3 files changed, 86 insertions(+), 13 deletions(-) (limited to 'kernel/rcu') diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 9be47f4..b49c843 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -3442,6 +3442,7 @@ static int rcu_cpu_notify(struct notifier_block *self, case CPU_UP_PREPARE_FROZEN: rcu_prepare_cpu(cpu); rcu_prepare_kthreads(cpu); + rcu_spawn_all_nocb_kthreads(cpu); break; case CPU_ONLINE: case CPU_DOWN_FAILED: @@ -3506,8 +3507,8 @@ static int __init rcu_spawn_gp_kthread(void) raw_spin_lock_irqsave(&rnp->lock, flags); rsp->gp_kthread = t; raw_spin_unlock_irqrestore(&rnp->lock, flags); - rcu_spawn_nocb_kthreads(rsp); } + rcu_spawn_nocb_kthreads(); rcu_spawn_boost_kthreads(); return 0; } diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index a966092..a9a226d 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -593,7 +593,11 @@ static bool rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp, static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp); static void do_nocb_deferred_wakeup(struct rcu_data *rdp); static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp); -static void rcu_spawn_nocb_kthreads(struct rcu_state *rsp); +static void rcu_spawn_all_nocb_kthreads(int cpu); +static void __init rcu_spawn_nocb_kthreads(void); +#ifdef CONFIG_RCU_NOCB_CPU +static void __init rcu_organize_nocb_kthreads(struct rcu_state *rsp); +#endif /* #ifdef CONFIG_RCU_NOCB_CPU */ static void __maybe_unused rcu_kick_nohz_cpu(int cpu); static bool init_nocb_callback_list(struct rcu_data *rdp); static void rcu_sysidle_enter(struct rcu_dynticks *rdtp, int irq); diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 410c744..31c7afb 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -2479,6 +2479,7 @@ void __init rcu_init_nohz(void) rdp->nxttail[RCU_NEXT_TAIL] != NULL); init_nocb_callback_list(rdp); } + rcu_organize_nocb_kthreads(rsp); } } @@ -2490,15 +2491,85 @@ static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp) rdp->nocb_follower_tail = &rdp->nocb_follower_head; } +/* + * If the specified CPU is a no-CBs CPU that does not already have its + * rcuo kthread for the specified RCU flavor, spawn it. If the CPUs are + * brought online out of order, this can require re-organizing the + * leader-follower relationships. + */ +static void rcu_spawn_one_nocb_kthread(struct rcu_state *rsp, int cpu) +{ + struct rcu_data *rdp; + struct rcu_data *rdp_last; + struct rcu_data *rdp_old_leader; + struct rcu_data *rdp_spawn = per_cpu_ptr(rsp->rda, cpu); + struct task_struct *t; + + /* + * If this isn't a no-CBs CPU or if it already has an rcuo kthread, + * then nothing to do. + */ + if (!rcu_is_nocb_cpu(cpu) || rdp_spawn->nocb_kthread) + return; + + /* If we didn't spawn the leader first, reorganize! */ + rdp_old_leader = rdp_spawn->nocb_leader; + if (rdp_old_leader != rdp_spawn && !rdp_old_leader->nocb_kthread) { + rdp_last = NULL; + rdp = rdp_old_leader; + do { + rdp->nocb_leader = rdp_spawn; + if (rdp_last && rdp != rdp_spawn) + rdp_last->nocb_next_follower = rdp; + rdp_last = rdp; + rdp = rdp->nocb_next_follower; + rdp_last->nocb_next_follower = NULL; + } while (rdp); + rdp_spawn->nocb_next_follower = rdp_old_leader; + } + + /* Spawn the kthread for this CPU and RCU flavor. */ + t = kthread_run(rcu_nocb_kthread, rdp_spawn, + "rcuo%c/%d", rsp->abbr, cpu); + BUG_ON(IS_ERR(t)); + ACCESS_ONCE(rdp_spawn->nocb_kthread) = t; +} + +/* + * If the specified CPU is a no-CBs CPU that does not already have its + * rcuo kthreads, spawn them. + */ +static void rcu_spawn_all_nocb_kthreads(int cpu) +{ + struct rcu_state *rsp; + + if (rcu_scheduler_fully_active) + for_each_rcu_flavor(rsp) + rcu_spawn_one_nocb_kthread(rsp, cpu); +} + +/* + * Once the scheduler is running, spawn rcuo kthreads for all online + * no-CBs CPUs. This assumes that the early_initcall()s happen before + * non-boot CPUs come online -- if this changes, we will need to add + * some mutual exclusion. + */ +static void __init rcu_spawn_nocb_kthreads(void) +{ + int cpu; + + for_each_online_cpu(cpu) + rcu_spawn_all_nocb_kthreads(cpu); +} + /* How many follower CPU IDs per leader? Default of -1 for sqrt(nr_cpu_ids). */ static int rcu_nocb_leader_stride = -1; module_param(rcu_nocb_leader_stride, int, 0444); /* - * Create a kthread for each RCU flavor for each no-CBs CPU. - * Also initialize leader-follower relationships. + * Initialize leader-follower relationships for all no-CBs CPU. */ -static void __init rcu_spawn_nocb_kthreads(struct rcu_state *rsp) +static void __init rcu_organize_nocb_kthreads(struct rcu_state *rsp) { int cpu; int ls = rcu_nocb_leader_stride; @@ -2506,7 +2577,6 @@ static void __init rcu_spawn_nocb_kthreads(struct rcu_state *rsp) struct rcu_data *rdp; struct rcu_data *rdp_leader = NULL; /* Suppress misguided gcc warn. */ struct rcu_data *rdp_prev = NULL; - struct task_struct *t; if (rcu_nocb_mask == NULL) return; @@ -2532,12 +2602,6 @@ static void __init rcu_spawn_nocb_kthreads(struct rcu_state *rsp) rdp_prev->nocb_next_follower = rdp; } rdp_prev = rdp; - - /* Spawn the kthread for this CPU. */ - t = kthread_run(rcu_nocb_kthread, rdp, - "rcuo%c/%d", rsp->abbr, cpu); - BUG_ON(IS_ERR(t)); - ACCESS_ONCE(rdp->nocb_kthread) = t; } } @@ -2591,7 +2655,11 @@ static void do_nocb_deferred_wakeup(struct rcu_data *rdp) { } -static void __init rcu_spawn_nocb_kthreads(struct rcu_state *rsp) +static void rcu_spawn_all_nocb_kthreads(int cpu) +{ +} + +static void __init rcu_spawn_nocb_kthreads(void) { } -- cgit v1.1 From 22c2f669611590b428647ac9a73bc63ef3989d4b Mon Sep 17 00:00:00 2001 From: Pranith Kumar Date: Thu, 17 Jul 2014 20:11:01 -0400 Subject: rcu: Check for have_rcu_nocb_mask instead of rcu_nocb_mask If we configure a kernel with CONFIG_NOCB_CPU=y, CONFIG_RCU_NOCB_CPU_NONE=y and CONFIG_CPUMASK_OFFSTACK=n and do not pass in a rcu_nocb= boot parameter, the cpumask rcu_nocb_mask can be garbage instead of NULL. Hence this commit replaces checks for rcu_nocb_mask == NULL with a check for have_rcu_nocb_mask. Signed-off-by: Pranith Kumar Signed-off-by: Paul E. McKenney Tested-by: Paul Gortmaker --- kernel/rcu/tree_plugin.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel/rcu') diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 31c7afb..39e68bc 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -2578,7 +2578,7 @@ static void __init rcu_organize_nocb_kthreads(struct rcu_state *rsp) struct rcu_data *rdp_leader = NULL; /* Suppress misguided gcc warn. */ struct rcu_data *rdp_prev = NULL; - if (rcu_nocb_mask == NULL) + if (!have_rcu_nocb_mask) return; if (ls == -1) { ls = int_sqrt(nr_cpu_ids); @@ -2608,9 +2608,9 @@ static void __init rcu_organize_nocb_kthreads(struct rcu_state *rsp) /* Prevent __call_rcu() from enqueuing callbacks on no-CBs CPUs */ static bool init_nocb_callback_list(struct rcu_data *rdp) { - if (rcu_nocb_mask == NULL || - !cpumask_test_cpu(rdp->cpu, rcu_nocb_mask)) + if (!rcu_is_nocb_cpu(rdp->cpu)) return false; + rdp->nxttail[RCU_NEXT_TAIL] = NULL; return true; } -- cgit v1.1 From 417e8d26557c4264a484d78a7491316751afa46f Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 21 Jul 2014 11:26:54 -0700 Subject: rcu: Eliminate redundant rcu_sysidle_state variable Now that we have rcu_state_p, which references rcu_preempt_state for TREE_PREEMPT_RCU and rcu_sched_state for TREE_RCU, we don't need a separate rcu_sysidle_state variable. This commit therefore eliminates rcu_preempt_state in favor of rcu_state_p. Signed-off-by: Paul E. McKenney Reviewed-by: Pranith Kumar Acked-by: Frederic Weisbecker Tested-by: Paul Gortmaker --- kernel/rcu/tree_plugin.h | 23 ++++++----------------- 1 file changed, 6 insertions(+), 17 deletions(-) (limited to 'kernel/rcu') diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 39e68bc..3ddad4f 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -2690,16 +2690,6 @@ static void __maybe_unused rcu_kick_nohz_cpu(int cpu) #ifdef CONFIG_NO_HZ_FULL_SYSIDLE -/* - * Define RCU flavor that holds sysidle state. This needs to be the - * most active flavor of RCU. - */ -#ifdef CONFIG_PREEMPT_RCU -static struct rcu_state *rcu_sysidle_state = &rcu_preempt_state; -#else /* #ifdef CONFIG_PREEMPT_RCU */ -static struct rcu_state *rcu_sysidle_state = &rcu_sched_state; -#endif /* #else #ifdef CONFIG_PREEMPT_RCU */ - static int full_sysidle_state; /* Current system-idle state. */ #define RCU_SYSIDLE_NOT 0 /* Some CPU is not idle. */ #define RCU_SYSIDLE_SHORT 1 /* All CPUs idle for brief period. */ @@ -2841,7 +2831,7 @@ static void rcu_sysidle_check_cpu(struct rcu_data *rdp, bool *isidle, * not the flavor of RCU that tracks sysidle state, or if this * is an offline or the timekeeping CPU, nothing to do. */ - if (!*isidle || rdp->rsp != rcu_sysidle_state || + if (!*isidle || rdp->rsp != rcu_state_p || cpu_is_offline(rdp->cpu) || rdp->cpu == tick_do_timer_cpu) return; if (rcu_gp_in_progress(rdp->rsp)) @@ -2867,7 +2857,7 @@ static void rcu_sysidle_check_cpu(struct rcu_data *rdp, bool *isidle, */ static bool is_sysidle_rcu_state(struct rcu_state *rsp) { - return rsp == rcu_sysidle_state; + return rsp == rcu_state_p; } /* @@ -2945,7 +2935,7 @@ static void rcu_sysidle_cancel(void) static void rcu_sysidle_report(struct rcu_state *rsp, int isidle, unsigned long maxj, bool gpkt) { - if (rsp != rcu_sysidle_state) + if (rsp != rcu_state_p) return; /* Wrong flavor, ignore. */ if (gpkt && nr_cpu_ids <= CONFIG_NO_HZ_FULL_SYSIDLE_SMALL) return; /* Running state machine from timekeeping CPU. */ @@ -3014,13 +3004,12 @@ bool rcu_sys_is_idle(void) /* Scan all the CPUs looking for nonidle CPUs. */ for_each_possible_cpu(cpu) { - rdp = per_cpu_ptr(rcu_sysidle_state->rda, cpu); + rdp = per_cpu_ptr(rcu_state_p->rda, cpu); rcu_sysidle_check_cpu(rdp, &isidle, &maxj); if (!isidle) break; } - rcu_sysidle_report(rcu_sysidle_state, - isidle, maxj, false); + rcu_sysidle_report(rcu_state_p, isidle, maxj, false); oldrss = rss; rss = ACCESS_ONCE(full_sysidle_state); } @@ -3047,7 +3036,7 @@ bool rcu_sys_is_idle(void) * provided by the memory allocator. */ if (nr_cpu_ids > CONFIG_NO_HZ_FULL_SYSIDLE_SMALL && - !rcu_gp_in_progress(rcu_sysidle_state) && + !rcu_gp_in_progress(rcu_state_p) && !rsh.inuse && xchg(&rsh.inuse, 1) == 0) call_rcu(&rsh.rh, rcu_sysidle_cb); return false; -- cgit v1.1 From 663e131090dd10bac9dc0b4f5b624dd3211b20f6 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 21 Jul 2014 11:34:33 -0700 Subject: rcu: Don't track sysidle state if no nohz_full= CPUs If there are no nohz_full= CPUs, then there is currently no reason to track sysidle state. This commit therefore short-circuits this state tracking if !tick_nohz_full_enabled(). Note that these checks will need to be revisited if nohz_full= state can ever be changed at runtime. Signed-off-by: Paul E. McKenney Acked-by: Frederic Weisbecker Tested-by: Paul Gortmaker --- kernel/rcu/tree_plugin.h | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) (limited to 'kernel/rcu') diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 3ddad4f..d5aec54 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -2707,6 +2707,10 @@ static void rcu_sysidle_enter(struct rcu_dynticks *rdtp, int irq) { unsigned long j; + /* If there are no nohz_full= CPUs, no need to track this. */ + if (!tick_nohz_full_enabled()) + return; + /* Adjust nesting, check for fully idle. */ if (irq) { rdtp->dynticks_idle_nesting--; @@ -2772,6 +2776,10 @@ void rcu_sysidle_force_exit(void) */ static void rcu_sysidle_exit(struct rcu_dynticks *rdtp, int irq) { + /* If there are no nohz_full= CPUs, no need to track this. */ + if (!tick_nohz_full_enabled()) + return; + /* Adjust nesting, check for already non-idle. */ if (irq) { rdtp->dynticks_idle_nesting++; @@ -2826,6 +2834,10 @@ static void rcu_sysidle_check_cpu(struct rcu_data *rdp, bool *isidle, unsigned long j; struct rcu_dynticks *rdtp = rdp->dynticks; + /* If there are no nohz_full= CPUs, don't check system-wide idleness. */ + if (!tick_nohz_full_enabled()) + return; + /* * If some other CPU has already reported non-idle, if this is * not the flavor of RCU that tracks sysidle state, or if this @@ -2952,6 +2964,10 @@ static void rcu_sysidle_report(struct rcu_state *rsp, int isidle, static void rcu_sysidle_report_gp(struct rcu_state *rsp, int isidle, unsigned long maxj) { + /* If there are no nohz_full= CPUs, no need to track this. */ + if (!tick_nohz_full_enabled()) + return; + rcu_sysidle_report(rsp, isidle, maxj, true); } @@ -2978,7 +2994,8 @@ static void rcu_sysidle_cb(struct rcu_head *rhp) /* * Check to see if the system is fully idle, other than the timekeeping CPU. - * The caller must have disabled interrupts. + * The caller must have disabled interrupts. This is not intended to be + * called unless tick_nohz_full_enabled(). */ bool rcu_sys_is_idle(void) { -- cgit v1.1 From 39953dfd40077c7480b1d5deb4d617e086b1c865 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 12 Aug 2014 10:47:48 -0700 Subject: rcu: Avoid misordering in __call_rcu_nocb_enqueue() The NOCB leader wakeup ordering depends on the store to the header happening before the check for the leader already being awake. However, because atomic_long_add() does not return a value, it does not provide ordering guarantees, the incorrect comment in wake_nocb_leader() notwithstanding. This commit therefore adds a smp_mb__after_atomic() after the final atomic_long_add() to provide the needed ordering guarantee. Reported-by: Amit Shah Signed-off-by: Paul E. McKenney Tested-by: Paul Gortmaker --- kernel/rcu/tree_plugin.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel/rcu') diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index d5aec54..4ad63d8 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -2042,7 +2042,7 @@ static void wake_nocb_leader(struct rcu_data *rdp, bool force) if (!ACCESS_ONCE(rdp_leader->nocb_kthread)) return; if (ACCESS_ONCE(rdp_leader->nocb_leader_sleep) || force) { - /* Prior xchg orders against prior callback enqueue. */ + /* Prior smp_mb__after_atomic() orders against prior enqueue. */ ACCESS_ONCE(rdp_leader->nocb_leader_sleep) = false; wake_up(&rdp_leader->nocb_wq); } @@ -2071,6 +2071,7 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp, ACCESS_ONCE(*old_rhpp) = rhp; atomic_long_add(rhcount, &rdp->nocb_q_count); atomic_long_add(rhcount_lazy, &rdp->nocb_q_count_lazy); + smp_mb__after_atomic(); /* Store *old_rhpp before _wake test. */ /* If we are not being polled and there is a kthread, awaken it ... */ t = ACCESS_ONCE(rdp->nocb_kthread); -- cgit v1.1 From 1772947bd0126661866069157e95197e9c0020e9 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 12 Aug 2014 11:27:31 -0700 Subject: rcu: Handle NOCB callbacks from irq-disabled idle code If an RCU callback is queued on a no-CBs CPU from idle code with irqs disabled, and if that CPU stays idle forever after, the callback will never be invoked. This commit therefore adds a check for this situation in ____call_rcu_nocb(), invoking the RCU core solely for the purpose of the ensuing return-to-idle transition. (If the CPU doesn't return to idle, the next scheduling-clock interrupt will fix things up.) Reported-by: Amit Shah Signed-off-by: Paul E. McKenney Tested-by: Paul Gortmaker --- kernel/rcu/tree_plugin.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'kernel/rcu') diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 4ad63d8..8b73518 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -2129,6 +2129,17 @@ static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp, trace_rcu_callback(rdp->rsp->name, rhp, -atomic_long_read(&rdp->nocb_q_count_lazy), -atomic_long_read(&rdp->nocb_q_count)); + + /* + * If called from an extended quiescent state with interrupts + * disabled, invoke the RCU core in order to allow the idle-entry + * deferred-wakeup check to function. + */ + if (irqs_disabled_flags(flags) && + !rcu_is_watching() && + cpu_online(smp_processor_id())) + invoke_rcu_core(); + return true; } -- cgit v1.1 From c847f14217d5aec5336272a54a32ffcf6e06ddcb Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 12 Aug 2014 13:54:21 -0700 Subject: rcu: Avoid misordering in nocb_leader_wait() The NOCB follower wakeup ordering depends on the store to the tail pointer happening before the wakeup. However, because atomic_long_add() does not return a value, it does not provide ordering guarantees, and the locking in wake_up() only guarantees that the store will happen before the unlock, which might be too late. Even though this is only a theoretical issue, this commit adds a smp_mb__after_atomic() after the final atomic_long_add() to provide the needed ordering guarantee. Reported-by: Amit Shah Signed-off-by: Paul E. McKenney Tested-by: Paul Gortmaker --- kernel/rcu/tree_plugin.h | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel/rcu') diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 8b73518..c554acc 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -2306,6 +2306,7 @@ wait_again: atomic_long_add(rdp->nocb_gp_count, &rdp->nocb_follower_count); atomic_long_add(rdp->nocb_gp_count_lazy, &rdp->nocb_follower_count_lazy); + smp_mb__after_atomic(); /* Store *tail before wakeup. */ if (rdp != my_rdp && tail == &rdp->nocb_follower_head) { /* * List was empty, wake up the follower. -- cgit v1.1