From ba9f207c9f82115aba4ce04b22e0081af0ae300f Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 20 May 2011 02:09:54 +0200 Subject: rcu: Fix unpaired rcu_irq_enter() from locking selftests HARDIRQ_ENTER() maps to irq_enter() which calls rcu_irq_enter(). But HARDIRQ_EXIT() maps to __irq_exit() which doesn't call rcu_irq_exit(). So for every locking selftest that simulates hardirq disabled, we create an imbalance in the rcu extended quiescent state internal state. As a result, after the first missing rcu_irq_exit(), subsequent irqs won't exit dyntick-idle mode after leaving the interrupt handler. This means that RCU won't see the affected CPU as being in an extended quiescent state, resulting in long grace-period delays (as in grace periods extending for hours). To fix this, just use __irq_enter() to simulate the hardirq context. This is sufficient for the locking selftests as we don't need to exit any extended quiescent state or perform any check that irqs normally do when they wake up from idle. As a side effect, this patch makes it possible to restore "rcu: Decrease memory-barrier usage based on semi-formal proof", which eventually helped finding this bug. Reported-and-tested-by: Yinghai Lu Signed-off-by: Frederic Weisbecker Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Stable Signed-off-by: Paul E. McKenney --- lib/locking-selftest.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/locking-selftest.c b/lib/locking-selftest.c index 619313e..507a22f 100644 --- a/lib/locking-selftest.c +++ b/lib/locking-selftest.c @@ -144,7 +144,7 @@ static void init_shared_classes(void) #define HARDIRQ_ENTER() \ local_irq_disable(); \ - irq_enter(); \ + __irq_enter(); \ WARN_ON(!in_irq()); #define HARDIRQ_EXIT() \ -- cgit v1.1 From 0bbcc529fcea9c7de5e2e7243f9913b8f7302a8c Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 16 May 2011 02:24:04 -0700 Subject: rcu: Add memory barriers Add the memory barriers added by e59fb3120b. Signed-off-by: Paul E. McKenney --- kernel/rcutree.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/kernel/rcutree.c b/kernel/rcutree.c index e486f7c..3731141 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -907,6 +907,12 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags) unsigned long gp_duration; WARN_ON_ONCE(!rcu_gp_in_progress(rsp)); + + /* + * Ensure that all grace-period and pre-grace-period activity + * is seen before the assignment to rsp->completed. + */ + smp_mb(); /* See above block comment. */ gp_duration = jiffies - rsp->gp_start; if (gp_duration > rsp->gp_max) rsp->gp_max = gp_duration; -- cgit v1.1 From 1135633bddcf7a819a1490c18d04965c490bcc1e Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 16 May 2011 02:44:06 -0700 Subject: rcu: Remove old memory barriers from rcu_process_callbacks() Second step of partitioning of commit e59fb3120b. Signed-off-by: Paul E. McKenney --- kernel/rcutree.c | 14 -------------- 1 file changed, 14 deletions(-) diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 3731141..011bf6f 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -1460,25 +1460,11 @@ __rcu_process_callbacks(struct rcu_state *rsp, struct rcu_data *rdp) */ static void rcu_process_callbacks(void) { - /* - * Memory references from any prior RCU read-side critical sections - * executed by the interrupted code must be seen before any RCU - * grace-period manipulations below. - */ - smp_mb(); /* See above block comment. */ - __rcu_process_callbacks(&rcu_sched_state, &__get_cpu_var(rcu_sched_data)); __rcu_process_callbacks(&rcu_bh_state, &__get_cpu_var(rcu_bh_data)); rcu_preempt_process_callbacks(); - /* - * Memory references from any later RCU read-side critical sections - * executed by the interrupted code must be seen after any RCU - * grace-period manipulations above. - */ - smp_mb(); /* See above block comment. */ - /* If we are last CPU on way to dyntick-idle mode, accelerate it. */ rcu_needs_cpu_flush(); } -- cgit v1.1 From b5904090c754327ed6c2ecaefed4f7d473df393f Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 16 May 2011 02:52:04 -0700 Subject: rcu: Don't do reschedule unless in irq Condition the set_need_resched() in rcu_irq_exit() on in_irq(). This should be a no-op, because rcu_irq_exit() should only be called from irq. Signed-off-by: Paul E. McKenney --- kernel/rcutree.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 011bf6f..195b3a3 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -421,8 +421,9 @@ void rcu_irq_exit(void) WARN_ON_ONCE(rdtp->dynticks & 0x1); /* If the interrupt queued a callback, get out of dyntick mode. */ - if (__this_cpu_read(rcu_sched_data.nxtlist) || - __this_cpu_read(rcu_bh_data.nxtlist)) + if (in_irq() && + (__this_cpu_read(rcu_sched_data.nxtlist) || + __this_cpu_read(rcu_bh_data.nxtlist))) set_need_resched(); } -- cgit v1.1 From 4305ce7894dd38b0633bfc8978437320119223bd Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 16 May 2011 14:27:31 -0700 Subject: rcu: Make rcu_enter_nohz() pay attention to nesting The old version of rcu_enter_nohz() forced RCU into nohz mode even if the nesting count was non-zero. This change causes rcu_enter_nohz() to hold off for non-zero nesting counts. Signed-off-by: Paul E. McKenney --- kernel/rcutree.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 195b3a3..99c6038 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -324,8 +324,8 @@ void rcu_enter_nohz(void) smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */ local_irq_save(flags); rdtp = &__get_cpu_var(rcu_dynticks); - rdtp->dynticks++; - rdtp->dynticks_nesting--; + if (--rdtp->dynticks_nesting == 0) + rdtp->dynticks++; WARN_ON_ONCE(rdtp->dynticks & 0x1); local_irq_restore(flags); } -- cgit v1.1 From 23b5c8fa01b723c70a20d6e4ef4ff54c7656d6e1 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 7 Sep 2010 10:38:22 -0700 Subject: rcu: Decrease memory-barrier usage based on semi-formal proof (Note: this was reverted, and is now being re-applied in pieces, with this being the fifth and final piece. See below for the reason that it is now felt to be safe to re-apply this.) Commit d09b62d fixed grace-period synchronization, but left some smp_mb() invocations in rcu_process_callbacks() that are no longer needed, but sheer paranoia prevented them from being removed. This commit removes them and provides a proof of correctness in their absence. It also adds a memory barrier to rcu_report_qs_rsp() immediately before the update to rsp->completed in order to handle the theoretical possibility that the compiler or CPU might move massive quantities of code into a lock-based critical section. This also proves that the sheer paranoia was not entirely unjustified, at least from a theoretical point of view. In addition, the old dyntick-idle synchronization depended on the fact that grace periods were many milliseconds in duration, so that it could be assumed that no dyntick-idle CPU could reorder a memory reference across an entire grace period. Unfortunately for this design, the addition of expedited grace periods breaks this assumption, which has the unfortunate side-effect of requiring atomic operations in the functions that track dyntick-idle state for RCU. (There is some hope that the algorithms used in user-level RCU might be applied here, but some work is required to handle the NMIs that user-space applications can happily ignore. For the short term, better safe than sorry.) This proof assumes that neither compiler nor CPU will allow a lock acquisition and release to be reordered, as doing so can result in deadlock. The proof is as follows: 1. A given CPU declares a quiescent state under the protection of its leaf rcu_node's lock. 2. If there is more than one level of rcu_node hierarchy, the last CPU to declare a quiescent state will also acquire the ->lock of the next rcu_node up in the hierarchy, but only after releasing the lower level's lock. The acquisition of this lock clearly cannot occur prior to the acquisition of the leaf node's lock. 3. Step 2 repeats until we reach the root rcu_node structure. Please note again that only one lock is held at a time through this process. The acquisition of the root rcu_node's ->lock must occur after the release of that of the leaf rcu_node. 4. At this point, we set the ->completed field in the rcu_state structure in rcu_report_qs_rsp(). However, if the rcu_node hierarchy contains only one rcu_node, then in theory the code preceding the quiescent state could leak into the critical section. We therefore precede the update of ->completed with a memory barrier. All CPUs will therefore agree that any updates preceding any report of a quiescent state will have happened before the update of ->completed. 5. Regardless of whether a new grace period is needed, rcu_start_gp() will propagate the new value of ->completed to all of the leaf rcu_node structures, under the protection of each rcu_node's ->lock. If a new grace period is needed immediately, this propagation will occur in the same critical section that ->completed was set in, but courtesy of the memory barrier in #4 above, is still seen to follow any pre-quiescent-state activity. 6. When a given CPU invokes __rcu_process_gp_end(), it becomes aware of the end of the old grace period and therefore makes any RCU callbacks that were waiting on that grace period eligible for invocation. If this CPU is the same one that detected the end of the grace period, and if there is but a single rcu_node in the hierarchy, we will still be in the single critical section. In this case, the memory barrier in step #4 guarantees that all callbacks will be seen to execute after each CPU's quiescent state. On the other hand, if this is a different CPU, it will acquire the leaf rcu_node's ->lock, and will again be serialized after each CPU's quiescent state for the old grace period. On the strength of this proof, this commit therefore removes the memory barriers from rcu_process_callbacks() and adds one to rcu_report_qs_rsp(). The effect is to reduce the number of memory barriers by one and to reduce the frequency of execution from about once per scheduling tick per CPU to once per grace period. This was reverted do to hangs found during testing by Yinghai Lu and Ingo Molnar. Frederic Weisbecker supplied Yinghai with tracing that located the underlying problem, and Frederic also provided the fix. The underlying problem was that the HARDIRQ_ENTER() macro from lib/locking-selftest.c invoked irq_enter(), which in turn invokes rcu_irq_enter(), but HARDIRQ_EXIT() invoked __irq_exit(), which does not invoke rcu_irq_exit(). This situation resulted in calls to rcu_irq_enter() that were not balanced by the required calls to rcu_irq_exit(). Therefore, after these locking selftests completed, RCU's dyntick-idle nesting count was a large number (for example, 72), which caused RCU to to conclude that the affected CPU was not in dyntick-idle mode when in fact it was. RCU would therefore incorrectly wait for this dyntick-idle CPU, resulting in hangs. In contrast, with Frederic's patch, which replaces the irq_enter() in HARDIRQ_ENTER() with an __irq_enter(), these tests don't ever call either rcu_irq_enter() or rcu_irq_exit(), which works because the CPU running the test is already marked as not being in dyntick-idle mode. This means that the rcu_irq_enter() and rcu_irq_exit() calls and RCU then has no problem working out which CPUs are in dyntick-idle mode and which are not. The reason that the imbalance was not noticed before the barrier patch was applied is that the old implementation of rcu_enter_nohz() ignored the nesting depth. This could still result in delays, but much shorter ones. Whenever there was a delay, RCU would IPI the CPU with the unbalanced nesting level, which would eventually result in rcu_enter_nohz() being called, which in turn would force RCU to see that the CPU was in dyntick-idle mode. The reason that very few people noticed the problem is that the mismatched irq_enter() vs. __irq_exit() occured only when the kernel was built with CONFIG_DEBUG_LOCKING_API_SELFTESTS. Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- Documentation/RCU/trace.txt | 17 ++----- kernel/rcutree.c | 111 ++++++++++++++++++++------------------------ kernel/rcutree.h | 9 ++-- kernel/rcutree_plugin.h | 7 ++- kernel/rcutree_trace.c | 12 ++--- 5 files changed, 67 insertions(+), 89 deletions(-) diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt index c078ad4..8173cec 100644 --- a/Documentation/RCU/trace.txt +++ b/Documentation/RCU/trace.txt @@ -99,18 +99,11 @@ o "qp" indicates that RCU still expects a quiescent state from o "dt" is the current value of the dyntick counter that is incremented when entering or leaving dynticks idle state, either by the - scheduler or by irq. The number after the "/" is the interrupt - nesting depth when in dyntick-idle state, or one greater than - the interrupt-nesting depth otherwise. - - This field is displayed only for CONFIG_NO_HZ kernels. - -o "dn" is the current value of the dyntick counter that is incremented - when entering or leaving dynticks idle state via NMI. If both - the "dt" and "dn" values are even, then this CPU is in dynticks - idle mode and may be ignored by RCU. If either of these two - counters is odd, then RCU must be alert to the possibility of - an RCU read-side critical section running on this CPU. + scheduler or by irq. This number is even if the CPU is in + dyntick idle mode and odd otherwise. The number after the first + "/" is the interrupt nesting depth when in dyntick-idle state, + or one greater than the interrupt-nesting depth otherwise. + The number after the second "/" is the NMI nesting depth. This field is displayed only for CONFIG_NO_HZ kernels. diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 99c6038..5616b17 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -162,7 +162,7 @@ EXPORT_SYMBOL_GPL(rcu_note_context_switch); #ifdef CONFIG_NO_HZ DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = { .dynticks_nesting = 1, - .dynticks = 1, + .dynticks = ATOMIC_INIT(1), }; #endif /* #ifdef CONFIG_NO_HZ */ @@ -321,13 +321,25 @@ void rcu_enter_nohz(void) unsigned long flags; struct rcu_dynticks *rdtp; - smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */ local_irq_save(flags); rdtp = &__get_cpu_var(rcu_dynticks); - if (--rdtp->dynticks_nesting == 0) - rdtp->dynticks++; - WARN_ON_ONCE(rdtp->dynticks & 0x1); + if (--rdtp->dynticks_nesting) { + local_irq_restore(flags); + return; + } + /* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */ + smp_mb__before_atomic_inc(); /* See above. */ + atomic_inc(&rdtp->dynticks); + smp_mb__after_atomic_inc(); /* Force ordering with next sojourn. */ + WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1); local_irq_restore(flags); + + /* If the interrupt queued a callback, get out of dyntick mode. */ + if (in_irq() && + (__get_cpu_var(rcu_sched_data).nxtlist || + __get_cpu_var(rcu_bh_data).nxtlist || + rcu_preempt_needs_cpu(smp_processor_id()))) + set_need_resched(); } /* @@ -343,11 +355,16 @@ void rcu_exit_nohz(void) local_irq_save(flags); rdtp = &__get_cpu_var(rcu_dynticks); - rdtp->dynticks++; - rdtp->dynticks_nesting++; - WARN_ON_ONCE(!(rdtp->dynticks & 0x1)); + if (rdtp->dynticks_nesting++) { + local_irq_restore(flags); + return; + } + smp_mb__before_atomic_inc(); /* Force ordering w/previous sojourn. */ + atomic_inc(&rdtp->dynticks); + /* CPUs seeing atomic_inc() must see later RCU read-side crit sects */ + smp_mb__after_atomic_inc(); /* See above. */ + WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1)); local_irq_restore(flags); - smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */ } /** @@ -361,11 +378,15 @@ void rcu_nmi_enter(void) { struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks); - if (rdtp->dynticks & 0x1) + if (rdtp->dynticks_nmi_nesting == 0 && + (atomic_read(&rdtp->dynticks) & 0x1)) return; - rdtp->dynticks_nmi++; - WARN_ON_ONCE(!(rdtp->dynticks_nmi & 0x1)); - smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */ + rdtp->dynticks_nmi_nesting++; + smp_mb__before_atomic_inc(); /* Force delay from prior write. */ + atomic_inc(&rdtp->dynticks); + /* CPUs seeing atomic_inc() must see later RCU read-side crit sects */ + smp_mb__after_atomic_inc(); /* See above. */ + WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1)); } /** @@ -379,11 +400,14 @@ void rcu_nmi_exit(void) { struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks); - if (rdtp->dynticks & 0x1) + if (rdtp->dynticks_nmi_nesting == 0 || + --rdtp->dynticks_nmi_nesting != 0) return; - smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */ - rdtp->dynticks_nmi++; - WARN_ON_ONCE(rdtp->dynticks_nmi & 0x1); + /* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */ + smp_mb__before_atomic_inc(); /* See above. */ + atomic_inc(&rdtp->dynticks); + smp_mb__after_atomic_inc(); /* Force delay to next write. */ + WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1); } /** @@ -394,13 +418,7 @@ void rcu_nmi_exit(void) */ void rcu_irq_enter(void) { - struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks); - - if (rdtp->dynticks_nesting++) - return; - rdtp->dynticks++; - WARN_ON_ONCE(!(rdtp->dynticks & 0x1)); - smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */ + rcu_exit_nohz(); } /** @@ -412,19 +430,7 @@ void rcu_irq_enter(void) */ void rcu_irq_exit(void) { - struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks); - - if (--rdtp->dynticks_nesting) - return; - smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */ - rdtp->dynticks++; - WARN_ON_ONCE(rdtp->dynticks & 0x1); - - /* If the interrupt queued a callback, get out of dyntick mode. */ - if (in_irq() && - (__this_cpu_read(rcu_sched_data.nxtlist) || - __this_cpu_read(rcu_bh_data.nxtlist))) - set_need_resched(); + rcu_enter_nohz(); } #ifdef CONFIG_SMP @@ -436,19 +442,8 @@ void rcu_irq_exit(void) */ static int dyntick_save_progress_counter(struct rcu_data *rdp) { - int ret; - int snap; - int snap_nmi; - - snap = rdp->dynticks->dynticks; - snap_nmi = rdp->dynticks->dynticks_nmi; - smp_mb(); /* Order sampling of snap with end of grace period. */ - rdp->dynticks_snap = snap; - rdp->dynticks_nmi_snap = snap_nmi; - ret = ((snap & 0x1) == 0) && ((snap_nmi & 0x1) == 0); - if (ret) - rdp->dynticks_fqs++; - return ret; + rdp->dynticks_snap = atomic_add_return(0, &rdp->dynticks->dynticks); + return 0; } /* @@ -459,16 +454,11 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp) */ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) { - long curr; - long curr_nmi; - long snap; - long snap_nmi; + unsigned long curr; + unsigned long snap; - curr = rdp->dynticks->dynticks; - snap = rdp->dynticks_snap; - curr_nmi = rdp->dynticks->dynticks_nmi; - snap_nmi = rdp->dynticks_nmi_snap; - smp_mb(); /* force ordering with cpu entering/leaving dynticks. */ + curr = (unsigned long)atomic_add_return(0, &rdp->dynticks->dynticks); + snap = (unsigned long)rdp->dynticks_snap; /* * If the CPU passed through or entered a dynticks idle phase with @@ -478,8 +468,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) * read-side critical section that started before the beginning * of the current RCU grace period. */ - if ((curr != snap || (curr & 0x1) == 0) && - (curr_nmi != snap_nmi || (curr_nmi & 0x1) == 0)) { + if ((curr & 0x1) == 0 || ULONG_CMP_GE(curr, snap + 2)) { rdp->dynticks_fqs++; return 1; } diff --git a/kernel/rcutree.h b/kernel/rcutree.h index 2576648..93d4a1c 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -84,11 +84,9 @@ * Dynticks per-CPU state. */ struct rcu_dynticks { - int dynticks_nesting; /* Track nesting level, sort of. */ - int dynticks; /* Even value for dynticks-idle, else odd. */ - int dynticks_nmi; /* Even value for either dynticks-idle or */ - /* not in nmi handler, else odd. So this */ - /* remains even for nmi from irq handler. */ + int dynticks_nesting; /* Track irq/process nesting level. */ + int dynticks_nmi_nesting; /* Track NMI nesting level. */ + atomic_t dynticks; /* Even value for dynticks-idle, else odd. */ }; /* RCU's kthread states for tracing. */ @@ -284,7 +282,6 @@ struct rcu_data { /* 3) dynticks interface. */ struct rcu_dynticks *dynticks; /* Shared per-CPU dynticks state. */ int dynticks_snap; /* Per-GP tracking for dynticks. */ - int dynticks_nmi_snap; /* Per-GP tracking for dynticks_nmi. */ #endif /* #ifdef CONFIG_NO_HZ */ /* 4) reasons this CPU needed to be kicked by force_quiescent_state */ diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index 3f6559a..ed339702 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -1520,7 +1520,6 @@ int rcu_needs_cpu(int cpu) { int c = 0; int snap; - int snap_nmi; int thatcpu; /* Check for being in the holdoff period. */ @@ -1531,10 +1530,10 @@ int rcu_needs_cpu(int cpu) for_each_online_cpu(thatcpu) { if (thatcpu == cpu) continue; - snap = per_cpu(rcu_dynticks, thatcpu).dynticks; - snap_nmi = per_cpu(rcu_dynticks, thatcpu).dynticks_nmi; + snap = atomic_add_return(0, &per_cpu(rcu_dynticks, + thatcpu).dynticks); smp_mb(); /* Order sampling of snap with end of grace period. */ - if (((snap & 0x1) != 0) || ((snap_nmi & 0x1) != 0)) { + if ((snap & 0x1) != 0) { per_cpu(rcu_dyntick_drain, cpu) = 0; per_cpu(rcu_dyntick_holdoff, cpu) = jiffies - 1; return rcu_needs_cpu_quick_check(cpu); diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c index aa0fd72..9678cc3 100644 --- a/kernel/rcutree_trace.c +++ b/kernel/rcutree_trace.c @@ -69,10 +69,10 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp) rdp->passed_quiesc, rdp->passed_quiesc_completed, rdp->qs_pending); #ifdef CONFIG_NO_HZ - seq_printf(m, " dt=%d/%d dn=%d df=%lu", - rdp->dynticks->dynticks, + seq_printf(m, " dt=%d/%d/%d df=%lu", + atomic_read(&rdp->dynticks->dynticks), rdp->dynticks->dynticks_nesting, - rdp->dynticks->dynticks_nmi, + rdp->dynticks->dynticks_nmi_nesting, rdp->dynticks_fqs); #endif /* #ifdef CONFIG_NO_HZ */ seq_printf(m, " of=%lu ri=%lu", rdp->offline_fqs, rdp->resched_ipi); @@ -141,9 +141,9 @@ static void print_one_rcu_data_csv(struct seq_file *m, struct rcu_data *rdp) rdp->qs_pending); #ifdef CONFIG_NO_HZ seq_printf(m, ",%d,%d,%d,%lu", - rdp->dynticks->dynticks, + atomic_read(&rdp->dynticks->dynticks), rdp->dynticks->dynticks_nesting, - rdp->dynticks->dynticks_nmi, + rdp->dynticks->dynticks_nmi_nesting, rdp->dynticks_fqs); #endif /* #ifdef CONFIG_NO_HZ */ seq_printf(m, ",%lu,%lu", rdp->offline_fqs, rdp->resched_ipi); @@ -167,7 +167,7 @@ static int show_rcudata_csv(struct seq_file *m, void *unused) { seq_puts(m, "\"CPU\",\"Online?\",\"c\",\"g\",\"pq\",\"pqc\",\"pq\","); #ifdef CONFIG_NO_HZ - seq_puts(m, "\"dt\",\"dt nesting\",\"dn\",\"df\","); + seq_puts(m, "\"dt\",\"dt nesting\",\"dt NMI nesting\",\"df\","); #endif /* #ifdef CONFIG_NO_HZ */ seq_puts(m, "\"of\",\"ri\",\"ql\",\"b\",\"ci\",\"co\",\"ca\"\n"); #ifdef CONFIG_TREE_PREEMPT_RCU -- cgit v1.1 From f62508f68d04adefc4cf9b0177ba02c8818b3eec Mon Sep 17 00:00:00 2001 From: Juri Lelli Date: Thu, 19 May 2011 12:53:53 +0200 Subject: Documentation: Add statistics about nested locks Explain what the trailing "/1" on some lock class names of lock_stat output means. Reviewed-by: Yong Zhang Signed-off-by: Juri Lelli Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/4DD4F6C1.5090701@gmail.com Signed-off-by: Ingo Molnar --- Documentation/lockstat.txt | 36 ++++++++++++++++++++++++++++++++++-- 1 file changed, 34 insertions(+), 2 deletions(-) diff --git a/Documentation/lockstat.txt b/Documentation/lockstat.txt index 9c0a80d..cef00d4 100644 --- a/Documentation/lockstat.txt +++ b/Documentation/lockstat.txt @@ -12,8 +12,9 @@ Because things like lock contention can severely impact performance. - HOW Lockdep already has hooks in the lock functions and maps lock instances to -lock classes. We build on that. The graph below shows the relation between -the lock functions and the various hooks therein. +lock classes. We build on that (see Documentation/lockdep-design.txt). +The graph below shows the relation between the lock functions and the various +hooks therein. __acquire | @@ -128,6 +129,37 @@ points are the points we're contending with. The integer part of the time values is in us. +Dealing with nested locks, subclasses may appear: + +32............................................................................................................................................................................................... +33 +34 &rq->lock: 13128 13128 0.43 190.53 103881.26 97454 3453404 0.00 401.11 13224683.11 +35 --------- +36 &rq->lock 645 [] task_rq_lock+0x43/0x75 +37 &rq->lock 297 [] try_to_wake_up+0x127/0x25a +38 &rq->lock 360 [] select_task_rq_fair+0x1f0/0x74a +39 &rq->lock 428 [] scheduler_tick+0x46/0x1fb +40 --------- +41 &rq->lock 77 [] task_rq_lock+0x43/0x75 +42 &rq->lock 174 [] try_to_wake_up+0x127/0x25a +43 &rq->lock 4715 [] double_rq_lock+0x42/0x54 +44 &rq->lock 893 [] schedule+0x157/0x7b8 +45 +46............................................................................................................................................................................................... +47 +48 &rq->lock/1: 11526 11488 0.33 388.73 136294.31 21461 38404 0.00 37.93 109388.53 +49 ----------- +50 &rq->lock/1 11526 [] double_rq_lock+0x4f/0x54 +51 ----------- +52 &rq->lock/1 5645 [] double_rq_lock+0x42/0x54 +53 &rq->lock/1 1224 [] schedule+0x157/0x7b8 +54 &rq->lock/1 4336 [] double_rq_lock+0x4f/0x54 +55 &rq->lock/1 181 [] try_to_wake_up+0x127/0x25a + +Line 48 shows statistics for the second subclass (/1) of &rq->lock class +(subclass starts from 0), since in this case, as line 50 suggests, +double_rq_lock actually acquires a nested lock of two spinlocks. + View the top contending locks: # grep : /proc/lock_stat | head -- cgit v1.1 From 55c2945aa9d4d907ec5ca4f6a4e30ae908d8d30d Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 11 May 2011 05:33:33 -0700 Subject: atomic: Add atomic_or() An atomic_or() function is needed by TREE_RCU to avoid deadlock, so add a generic version. Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney Signed-off-by: Ingo Molnar --- include/linux/atomic.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 96c038e..ee456c7 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -34,4 +34,17 @@ static inline int atomic_inc_not_zero_hint(atomic_t *v, int hint) } #endif +#ifndef CONFIG_ARCH_HAS_ATOMIC_OR +static inline void atomic_or(int i, atomic_t *v) +{ + int old; + int new; + + do { + old = atomic_read(v); + new = old | i; + } while (atomic_cmpxchg(v, old, new) != old); +} +#endif /* #ifndef CONFIG_ARCH_HAS_ATOMIC_OR */ + #endif /* _LINUX_ATOMIC_H */ -- cgit v1.1 From 8826f3b0397562eee6f8785d548be9dfdb169100 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 11 May 2011 05:41:41 -0700 Subject: rcu: Avoid acquiring rcu_node locks in timer functions This commit switches manipulations of the rcu_node ->wakemask field to atomic operations, which allows rcu_cpu_kthread_timer() to avoid acquiring the rcu_node lock. This should avoid the following lockdep splat reported by Valdis Kletnieks: [ 12.872150] usb 1-4: new high speed USB device number 3 using ehci_hcd [ 12.986667] usb 1-4: New USB device found, idVendor=413c, idProduct=2513 [ 12.986679] usb 1-4: New USB device strings: Mfr=0, Product=0, SerialNumber=0 [ 12.987691] hub 1-4:1.0: USB hub found [ 12.987877] hub 1-4:1.0: 3 ports detected [ 12.996372] input: PS/2 Generic Mouse as /devices/platform/i8042/serio1/input/input10 [ 13.071471] udevadm used greatest stack depth: 3984 bytes left [ 13.172129] [ 13.172130] ======================================================= [ 13.172425] [ INFO: possible circular locking dependency detected ] [ 13.172650] 2.6.39-rc6-mmotm0506 #1 [ 13.172773] ------------------------------------------------------- [ 13.172997] blkid/267 is trying to acquire lock: [ 13.173009] (&p->pi_lock){-.-.-.}, at: [] try_to_wake_up+0x29/0x1aa [ 13.173009] [ 13.173009] but task is already holding lock: [ 13.173009] (rcu_node_level_0){..-...}, at: [] rcu_cpu_kthread_timer+0x27/0x58 [ 13.173009] [ 13.173009] which lock already depends on the new lock. [ 13.173009] [ 13.173009] [ 13.173009] the existing dependency chain (in reverse order) is: [ 13.173009] [ 13.173009] -> #2 (rcu_node_level_0){..-...}: [ 13.173009] [] check_prevs_add+0x8b/0x104 [ 13.173009] [] validate_chain+0x36f/0x3ab [ 13.173009] [] __lock_acquire+0x369/0x3e2 [ 13.173009] [] lock_acquire+0xfc/0x14c [ 13.173009] [] _raw_spin_lock+0x36/0x45 [ 13.173009] [] rcu_read_unlock_special+0x8c/0x1d5 [ 13.173009] [] __rcu_read_unlock+0x4f/0xd7 [ 13.173009] [] rcu_read_unlock+0x21/0x23 [ 13.173009] [] cpuacct_charge+0x6c/0x75 [ 13.173009] [] update_curr+0x101/0x12e [ 13.173009] [] check_preempt_wakeup+0xf7/0x23b [ 13.173009] [] check_preempt_curr+0x2b/0x68 [ 13.173009] [] ttwu_do_wakeup+0x76/0x128 [ 13.173009] [] ttwu_do_activate.constprop.63+0x57/0x5c [ 13.173009] [] scheduler_ipi+0x48/0x5d [ 13.173009] [] smp_reschedule_interrupt+0x16/0x18 [ 13.173009] [] reschedule_interrupt+0x13/0x20 [ 13.173009] [] rcu_read_unlock+0x21/0x23 [ 13.173009] [] find_get_page+0xa9/0xb9 [ 13.173009] [] filemap_fault+0x6a/0x34d [ 13.173009] [] __do_fault+0x54/0x3e6 [ 13.173009] [] handle_pte_fault+0x12c/0x1ed [ 13.173009] [] handle_mm_fault+0x1cd/0x1e0 [ 13.173009] [] do_page_fault+0x42d/0x5de [ 13.173009] [] page_fault+0x1f/0x30 [ 13.173009] [ 13.173009] -> #1 (&rq->lock){-.-.-.}: [ 13.173009] [] check_prevs_add+0x8b/0x104 [ 13.173009] [] validate_chain+0x36f/0x3ab [ 13.173009] [] __lock_acquire+0x369/0x3e2 [ 13.173009] [] lock_acquire+0xfc/0x14c [ 13.173009] [] _raw_spin_lock+0x36/0x45 [ 13.173009] [] __task_rq_lock+0x8b/0xd3 [ 13.173009] [] wake_up_new_task+0x41/0x108 [ 13.173009] [] do_fork+0x265/0x33f [ 13.173009] [] kernel_thread+0x6b/0x6d [ 13.173009] [] rest_init+0x21/0xd2 [ 13.173009] [] start_kernel+0x3bb/0x3c6 [ 13.173009] [] x86_64_start_reservations+0xaf/0xb3 [ 13.173009] [] x86_64_start_kernel+0xf0/0xf7 [ 13.173009] [ 13.173009] -> #0 (&p->pi_lock){-.-.-.}: [ 13.173009] [] check_prev_add+0x68/0x20e [ 13.173009] [] check_prevs_add+0x8b/0x104 [ 13.173009] [] validate_chain+0x36f/0x3ab [ 13.173009] [] __lock_acquire+0x369/0x3e2 [ 13.173009] [] lock_acquire+0xfc/0x14c [ 13.173009] [] _raw_spin_lock_irqsave+0x44/0x57 [ 13.173009] [] try_to_wake_up+0x29/0x1aa [ 13.173009] [] wake_up_process+0x10/0x12 [ 13.173009] [] rcu_cpu_kthread_timer+0x44/0x58 [ 13.173009] [] call_timer_fn+0xac/0x1e9 [ 13.173009] [] run_timer_softirq+0x1aa/0x1f2 [ 13.173009] [] __do_softirq+0x109/0x26a [ 13.173009] [] call_softirq+0x1c/0x30 [ 13.173009] [] do_softirq+0x44/0xf1 [ 13.173009] [] irq_exit+0x58/0xc8 [ 13.173009] [] smp_apic_timer_interrupt+0x79/0x87 [ 13.173009] [] apic_timer_interrupt+0x13/0x20 [ 13.173009] [] get_page_from_freelist+0x2aa/0x310 [ 13.173009] [] __alloc_pages_nodemask+0x178/0x243 [ 13.173009] [] pte_alloc_one+0x1e/0x3a [ 13.173009] [] __pte_alloc+0x22/0x14b [ 13.173009] [] handle_mm_fault+0x17e/0x1e0 [ 13.173009] [] do_page_fault+0x42d/0x5de [ 13.173009] [] page_fault+0x1f/0x30 [ 13.173009] [ 13.173009] other info that might help us debug this: [ 13.173009] [ 13.173009] Chain exists of: [ 13.173009] &p->pi_lock --> &rq->lock --> rcu_node_level_0 [ 13.173009] [ 13.173009] Possible unsafe locking scenario: [ 13.173009] [ 13.173009] CPU0 CPU1 [ 13.173009] ---- ---- [ 13.173009] lock(rcu_node_level_0); [ 13.173009] lock(&rq->lock); [ 13.173009] lock(rcu_node_level_0); [ 13.173009] lock(&p->pi_lock); [ 13.173009] [ 13.173009] *** DEADLOCK *** [ 13.173009] [ 13.173009] 3 locks held by blkid/267: [ 13.173009] #0: (&mm->mmap_sem){++++++}, at: [] do_page_fault+0x1f3/0x5de [ 13.173009] #1: (&yield_timer){+.-...}, at: [] call_timer_fn+0x0/0x1e9 [ 13.173009] #2: (rcu_node_level_0){..-...}, at: [] rcu_cpu_kthread_timer+0x27/0x58 [ 13.173009] [ 13.173009] stack backtrace: [ 13.173009] Pid: 267, comm: blkid Not tainted 2.6.39-rc6-mmotm0506 #1 [ 13.173009] Call Trace: [ 13.173009] [] print_circular_bug+0xc8/0xd9 [ 13.173009] [] check_prev_add+0x68/0x20e [ 13.173009] [] ? save_stack_trace+0x28/0x46 [ 13.173009] [] check_prevs_add+0x8b/0x104 [ 13.173009] [] validate_chain+0x36f/0x3ab [ 13.173009] [] __lock_acquire+0x369/0x3e2 [ 13.173009] [] ? try_to_wake_up+0x29/0x1aa [ 13.173009] [] lock_acquire+0xfc/0x14c [ 13.173009] [] ? try_to_wake_up+0x29/0x1aa [ 13.173009] [] ? rcu_check_quiescent_state+0x82/0x82 [ 13.173009] [] _raw_spin_lock_irqsave+0x44/0x57 [ 13.173009] [] ? try_to_wake_up+0x29/0x1aa [ 13.173009] [] try_to_wake_up+0x29/0x1aa [ 13.173009] [] ? rcu_check_quiescent_state+0x82/0x82 [ 13.173009] [] wake_up_process+0x10/0x12 [ 13.173009] [] rcu_cpu_kthread_timer+0x44/0x58 [ 13.173009] [] ? rcu_check_quiescent_state+0x82/0x82 [ 13.173009] [] call_timer_fn+0xac/0x1e9 [ 13.173009] [] ? del_timer+0x75/0x75 [ 13.173009] [] ? rcu_check_quiescent_state+0x82/0x82 [ 13.173009] [] run_timer_softirq+0x1aa/0x1f2 [ 13.173009] [] __do_softirq+0x109/0x26a [ 13.173009] [] ? tick_dev_program_event+0x37/0xf6 [ 13.173009] [] ? time_hardirqs_off+0x1b/0x2f [ 13.173009] [] call_softirq+0x1c/0x30 [ 13.173009] [] do_softirq+0x44/0xf1 [ 13.173009] [] irq_exit+0x58/0xc8 [ 13.173009] [] smp_apic_timer_interrupt+0x79/0x87 [ 13.173009] [] apic_timer_interrupt+0x13/0x20 [ 13.173009] [] ? get_page_from_freelist+0x114/0x310 [ 13.173009] [] ? get_page_from_freelist+0x2aa/0x310 [ 13.173009] [] ? clear_page_c+0x7/0x10 [ 13.173009] [] ? prep_new_page+0x14c/0x1cd [ 13.173009] [] get_page_from_freelist+0x2aa/0x310 [ 13.173009] [] __alloc_pages_nodemask+0x178/0x243 [ 13.173009] [] ? __pmd_alloc+0x87/0x99 [ 13.173009] [] pte_alloc_one+0x1e/0x3a [ 13.173009] [] ? __pmd_alloc+0x87/0x99 [ 13.173009] [] __pte_alloc+0x22/0x14b [ 13.173009] [] handle_mm_fault+0x17e/0x1e0 [ 13.173009] [] do_page_fault+0x42d/0x5de [ 13.173009] [] ? sys_brk+0x32/0x10c [ 13.173009] [] ? time_hardirqs_off+0x1b/0x2f [ 13.173009] [] ? trace_hardirqs_off_caller+0x3f/0x9c [ 13.173009] [] ? trace_hardirqs_off_thunk+0x3a/0x3c [ 13.173009] [] page_fault+0x1f/0x30 [ 14.010075] usb 5-1: new full speed USB device number 2 using uhci_hcd Reported-by: Valdis Kletnieks Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney Signed-off-by: Ingo Molnar --- kernel/rcutree.c | 13 +++++-------- kernel/rcutree.h | 4 +++- 2 files changed, 8 insertions(+), 9 deletions(-) diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 8154a4a..5d96d68 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -36,7 +36,7 @@ #include #include #include -#include +#include #include #include #include @@ -1526,13 +1526,10 @@ static void rcu_cpu_kthread_setrt(int cpu, int to_rt) */ static void rcu_cpu_kthread_timer(unsigned long arg) { - unsigned long flags; struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, arg); struct rcu_node *rnp = rdp->mynode; - raw_spin_lock_irqsave(&rnp->lock, flags); - rnp->wakemask |= rdp->grpmask; - raw_spin_unlock_irqrestore(&rnp->lock, flags); + atomic_or(rdp->grpmask, &rnp->wakemask); invoke_rcu_node_kthread(rnp); } @@ -1680,11 +1677,11 @@ static int rcu_node_kthread(void *arg) for (;;) { rnp->node_kthread_status = RCU_KTHREAD_WAITING; - wait_event_interruptible(rnp->node_wq, rnp->wakemask != 0); + wait_event_interruptible(rnp->node_wq, + atomic_read(&rnp->wakemask) != 0); rnp->node_kthread_status = RCU_KTHREAD_RUNNING; raw_spin_lock_irqsave(&rnp->lock, flags); - mask = rnp->wakemask; - rnp->wakemask = 0; + mask = atomic_xchg(&rnp->wakemask, 0); rcu_initiate_boost(rnp, flags); /* releases rnp->lock. */ for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask >>= 1) { if ((mask & 0x1) == 0) diff --git a/kernel/rcutree.h b/kernel/rcutree.h index 93d4a1c..561dcb9 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -119,7 +119,9 @@ struct rcu_node { /* elements that need to drain to allow the */ /* current expedited grace period to */ /* complete (only for TREE_PREEMPT_RCU). */ - unsigned long wakemask; /* CPUs whose kthread needs to be awakened. */ + atomic_t wakemask; /* CPUs whose kthread needs to be awakened. */ + /* Since this has meaning only for leaf */ + /* rcu_node structures, 32 bits suffices. */ unsigned long qsmaskinit; /* Per-GP initial value for qsmask & expmask. */ unsigned long grpmask; /* Mask to apply to parent qsmask. */ -- cgit v1.1 From 08bca60a6912ad225254250c0a9c3a05b4152cfa Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 20 May 2011 16:06:29 -0700 Subject: rcu: Remove waitqueue usage for cpu, node, and boost kthreads It is not necessary to use waitqueues for the RCU kthreads because we always know exactly which thread is to be awakened. In addition, wake_up() only issues an actual wakeup when there is a thread waiting on the queue, which was why there was an extra explicit wake_up_process() to get the RCU kthreads started. Eliminating the waitqueues (and wake_up()) in favor of wake_up_process() eliminates the need for the initial wake_up_process() and also shrinks the data structure size a bit. The wakeup logic is placed in a new rcu_wait() macro. Signed-off-by: Peter Zijlstra Signed-off-by: Paul E. McKenney Signed-off-by: Ingo Molnar --- kernel/rcutree.c | 23 ++++++----------------- kernel/rcutree.h | 17 ++++++++++------- kernel/rcutree_plugin.h | 16 +--------------- 3 files changed, 17 insertions(+), 39 deletions(-) diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 5d96d68..05e254e 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -95,7 +95,6 @@ static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task); DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status); DEFINE_PER_CPU(int, rcu_cpu_kthread_cpu); DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops); -static DEFINE_PER_CPU(wait_queue_head_t, rcu_cpu_wq); DEFINE_PER_CPU(char, rcu_cpu_has_work); static char rcu_kthreads_spawnable; @@ -1476,7 +1475,7 @@ static void invoke_rcu_cpu_kthread(void) local_irq_restore(flags); return; } - wake_up(&__get_cpu_var(rcu_cpu_wq)); + wake_up_process(__this_cpu_read(rcu_cpu_kthread_task)); local_irq_restore(flags); } @@ -1596,14 +1595,12 @@ static int rcu_cpu_kthread(void *arg) unsigned long flags; int spincnt = 0; unsigned int *statusp = &per_cpu(rcu_cpu_kthread_status, cpu); - wait_queue_head_t *wqp = &per_cpu(rcu_cpu_wq, cpu); char work; char *workp = &per_cpu(rcu_cpu_has_work, cpu); for (;;) { *statusp = RCU_KTHREAD_WAITING; - wait_event_interruptible(*wqp, - *workp != 0 || kthread_should_stop()); + rcu_wait(*workp != 0 || kthread_should_stop()); local_bh_disable(); if (rcu_cpu_kthread_should_stop(cpu)) { local_bh_enable(); @@ -1654,7 +1651,6 @@ static int __cpuinit rcu_spawn_one_cpu_kthread(int cpu) per_cpu(rcu_cpu_kthread_cpu, cpu) = cpu; WARN_ON_ONCE(per_cpu(rcu_cpu_kthread_task, cpu) != NULL); per_cpu(rcu_cpu_kthread_task, cpu) = t; - wake_up_process(t); sp.sched_priority = RCU_KTHREAD_PRIO; sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); return 0; @@ -1677,8 +1673,7 @@ static int rcu_node_kthread(void *arg) for (;;) { rnp->node_kthread_status = RCU_KTHREAD_WAITING; - wait_event_interruptible(rnp->node_wq, - atomic_read(&rnp->wakemask) != 0); + rcu_wait(atomic_read(&rnp->wakemask) != 0); rnp->node_kthread_status = RCU_KTHREAD_RUNNING; raw_spin_lock_irqsave(&rnp->lock, flags); mask = atomic_xchg(&rnp->wakemask, 0); @@ -1762,7 +1757,6 @@ static int __cpuinit rcu_spawn_one_node_kthread(struct rcu_state *rsp, raw_spin_lock_irqsave(&rnp->lock, flags); rnp->node_kthread_task = t; raw_spin_unlock_irqrestore(&rnp->lock, flags); - wake_up_process(t); sp.sched_priority = 99; sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); } @@ -1779,21 +1773,16 @@ static int __init rcu_spawn_kthreads(void) rcu_kthreads_spawnable = 1; for_each_possible_cpu(cpu) { - init_waitqueue_head(&per_cpu(rcu_cpu_wq, cpu)); per_cpu(rcu_cpu_has_work, cpu) = 0; if (cpu_online(cpu)) (void)rcu_spawn_one_cpu_kthread(cpu); } rnp = rcu_get_root(rcu_state); - init_waitqueue_head(&rnp->node_wq); - rcu_init_boost_waitqueue(rnp); (void)rcu_spawn_one_node_kthread(rcu_state, rnp); - if (NUM_RCU_NODES > 1) - rcu_for_each_leaf_node(rcu_state, rnp) { - init_waitqueue_head(&rnp->node_wq); - rcu_init_boost_waitqueue(rnp); + if (NUM_RCU_NODES > 1) { + rcu_for_each_leaf_node(rcu_state, rnp) (void)rcu_spawn_one_node_kthread(rcu_state, rnp); - } + } return 0; } early_initcall(rcu_spawn_kthreads); diff --git a/kernel/rcutree.h b/kernel/rcutree.h index 561dcb9..7b9a08b 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -159,9 +159,6 @@ struct rcu_node { struct task_struct *boost_kthread_task; /* kthread that takes care of priority */ /* boosting for this rcu_node structure. */ - wait_queue_head_t boost_wq; - /* Wait queue on which to park the boost */ - /* kthread. */ unsigned int boost_kthread_status; /* State of boost_kthread_task for tracing. */ unsigned long n_tasks_boosted; @@ -188,9 +185,6 @@ struct rcu_node { /* kthread that takes care of this rcu_node */ /* structure, for example, awakening the */ /* per-CPU kthreads as needed. */ - wait_queue_head_t node_wq; - /* Wait queue on which to park the per-node */ - /* kthread. */ unsigned int node_kthread_status; /* State of node_kthread_task for tracing. */ } ____cacheline_internodealigned_in_smp; @@ -336,6 +330,16 @@ struct rcu_data { /* scheduling clock irq */ /* before ratting on them. */ +#define rcu_wait(cond) \ +do { \ + for (;;) { \ + set_current_state(TASK_INTERRUPTIBLE); \ + if (cond) \ + break; \ + schedule(); \ + } \ + __set_current_state(TASK_RUNNING); \ +} while (0) /* * RCU global state, including node hierarchy. This hierarchy is @@ -445,7 +449,6 @@ static void __cpuinit rcu_preempt_init_percpu_data(int cpu); static void rcu_preempt_send_cbs_to_online(void); static void __init __rcu_init_preempt(void); static void rcu_needs_cpu_flush(void); -static void __init rcu_init_boost_waitqueue(struct rcu_node *rnp); static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags); static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, cpumask_var_t cm); diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index ed339702..049f278 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -1196,8 +1196,7 @@ static int rcu_boost_kthread(void *arg) for (;;) { rnp->boost_kthread_status = RCU_KTHREAD_WAITING; - wait_event_interruptible(rnp->boost_wq, rnp->boost_tasks || - rnp->exp_tasks); + rcu_wait(rnp->boost_tasks || rnp->exp_tasks); rnp->boost_kthread_status = RCU_KTHREAD_RUNNING; more2boost = rcu_boost(rnp); if (more2boost) @@ -1275,14 +1274,6 @@ static void rcu_preempt_boost_start_gp(struct rcu_node *rnp) } /* - * Initialize the RCU-boost waitqueue. - */ -static void __init rcu_init_boost_waitqueue(struct rcu_node *rnp) -{ - init_waitqueue_head(&rnp->boost_wq); -} - -/* * Create an RCU-boost kthread for the specified node if one does not * already exist. We only create this kthread for preemptible RCU. * Returns zero if all is well, a negated errno otherwise. @@ -1306,7 +1297,6 @@ static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp, raw_spin_lock_irqsave(&rnp->lock, flags); rnp->boost_kthread_task = t; raw_spin_unlock_irqrestore(&rnp->lock, flags); - wake_up_process(t); sp.sched_priority = RCU_KTHREAD_PRIO; sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); return 0; @@ -1328,10 +1318,6 @@ static void rcu_preempt_boost_start_gp(struct rcu_node *rnp) { } -static void __init rcu_init_boost_waitqueue(struct rcu_node *rnp) -{ -} - static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp, struct rcu_node *rnp, int rnp_index) -- cgit v1.1 From cc3ce5176d83cd8ae1134f86e208ea758d6cb78e Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 25 May 2011 13:42:06 -0700 Subject: rcu: Start RCU kthreads in TASK_INTERRUPTIBLE state Upon creation, kthreads are in TASK_UNINTERRUPTIBLE state, which can result in softlockup warnings. Because some of RCU's kthreads can legitimately be idle indefinitely, start them in TASK_INTERRUPTIBLE state in order to avoid those warnings. Suggested-by: Peter Zijlstra Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney Tested-by: Yinghai Lu Signed-off-by: Ingo Molnar --- kernel/rcutree.c | 2 ++ kernel/rcutree_plugin.h | 1 + 2 files changed, 3 insertions(+) diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 05e254e..77a7671 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -1648,6 +1648,7 @@ static int __cpuinit rcu_spawn_one_cpu_kthread(int cpu) if (IS_ERR(t)) return PTR_ERR(t); kthread_bind(t, cpu); + set_task_state(t, TASK_INTERRUPTIBLE); per_cpu(rcu_cpu_kthread_cpu, cpu) = cpu; WARN_ON_ONCE(per_cpu(rcu_cpu_kthread_task, cpu) != NULL); per_cpu(rcu_cpu_kthread_task, cpu) = t; @@ -1755,6 +1756,7 @@ static int __cpuinit rcu_spawn_one_node_kthread(struct rcu_state *rsp, if (IS_ERR(t)) return PTR_ERR(t); raw_spin_lock_irqsave(&rnp->lock, flags); + set_task_state(t, TASK_INTERRUPTIBLE); rnp->node_kthread_task = t; raw_spin_unlock_irqrestore(&rnp->lock, flags); sp.sched_priority = 99; diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index 049f278..a767b7d 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -1295,6 +1295,7 @@ static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp, if (IS_ERR(t)) return PTR_ERR(t); raw_spin_lock_irqsave(&rnp->lock, flags); + set_task_state(t, TASK_INTERRUPTIBLE); rnp->boost_kthread_task = t; raw_spin_unlock_irqrestore(&rnp->lock, flags); sp.sched_priority = RCU_KTHREAD_PRIO; -- cgit v1.1