Re: [GIT PULL rcu/next] rcu commits for 2.6.40
From: Yinghai Lu
Date: Thu May 12 2011 - 03:27:55 EST
On 05/11/2011 11:03 PM, Ingo Molnar wrote:
>
> * Yinghai Lu <yinghai@xxxxxxxxxx> wrote:
>
>> e59fb3120becfb36b22ddb8bd27d065d3cdca499 is the first bad commit
>> commit e59fb3120becfb36b22ddb8bd27d065d3cdca499
>> Author: Paul E. McKenney <paulmck@xxxxxxxxxxxxxxxxxx>
>> Date: Tue Sep 7 10:38:22 2010 -0700
>>
>> rcu: Decrease memory-barrier usage based on semi-formal proof
>
> Find below an (untested!) attempt at reverting it for debugging purposes: could
> you please try it, does your system now boot up fine?
>
> Thanks,
>
> Ingo
>
yes, reverted manually that commit fix the problem.
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 5616b17..ed59987 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 = ATOMIC_INIT(1),
+ .dynticks = 1,
};
#endif /* #ifdef CONFIG_NO_HZ */
@@ -321,25 +321,13 @@ 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) {
- 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);
+ rdtp->dynticks++;
+ rdtp->dynticks_nesting--;
+ WARN_ON_ONCE(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();
}
/*
@@ -355,16 +343,11 @@ void rcu_exit_nohz(void)
local_irq_save(flags);
rdtp = &__get_cpu_var(rcu_dynticks);
- 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));
+ rdtp->dynticks++;
+ rdtp->dynticks_nesting++;
+ WARN_ON_ONCE(!(rdtp->dynticks & 0x1));
local_irq_restore(flags);
+ smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */
}
/**
@@ -378,15 +361,11 @@ void rcu_nmi_enter(void)
{
struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
- if (rdtp->dynticks_nmi_nesting == 0 &&
- (atomic_read(&rdtp->dynticks) & 0x1))
+ if (rdtp->dynticks & 0x1)
return;
- 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));
+ rdtp->dynticks_nmi++;
+ WARN_ON_ONCE(!(rdtp->dynticks_nmi & 0x1));
+ smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */
}
/**
@@ -400,14 +379,11 @@ void rcu_nmi_exit(void)
{
struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
- if (rdtp->dynticks_nmi_nesting == 0 ||
- --rdtp->dynticks_nmi_nesting != 0)
+ if (rdtp->dynticks & 0x1)
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 delay to next write. */
- WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);
+ smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */
+ rdtp->dynticks_nmi++;
+ WARN_ON_ONCE(rdtp->dynticks_nmi & 0x1);
}
/**
@@ -418,7 +394,13 @@ void rcu_nmi_exit(void)
*/
void rcu_irq_enter(void)
{
- rcu_exit_nohz();
+ 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 */
}
/**
@@ -430,7 +412,18 @@ void rcu_irq_enter(void)
*/
void rcu_irq_exit(void)
{
- rcu_enter_nohz();
+ 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 (__this_cpu_read(rcu_sched_data.nxtlist) ||
+ __this_cpu_read(rcu_bh_data.nxtlist))
+ set_need_resched();
}
#ifdef CONFIG_SMP
@@ -442,8 +435,19 @@ void rcu_irq_exit(void)
*/
static int dyntick_save_progress_counter(struct rcu_data *rdp)
{
- rdp->dynticks_snap = atomic_add_return(0, &rdp->dynticks->dynticks);
- return 0;
+ 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;
}
/*
@@ -454,11 +458,16 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp)
*/
static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
{
- unsigned long curr;
- unsigned long snap;
+ long curr;
+ long curr_nmi;
+ long snap;
+ long snap_nmi;
- curr = (unsigned long)atomic_add_return(0, &rdp->dynticks->dynticks);
- snap = (unsigned long)rdp->dynticks_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. */
/*
* If the CPU passed through or entered a dynticks idle phase with
@@ -468,7 +477,8 @@ 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 & 0x1) == 0 || ULONG_CMP_GE(curr, snap + 2)) {
+ if ((curr != snap || (curr & 0x1) == 0) &&
+ (curr_nmi != snap_nmi || (curr_nmi & 0x1) == 0)) {
rdp->dynticks_fqs++;
return 1;
}
@@ -898,11 +908,6 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags)
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;
@@ -1450,11 +1455,25 @@ __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();
}
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index 93d4a1c..2576648 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -84,9 +84,11 @@
* Dynticks per-CPU state.
*/
struct rcu_dynticks {
- 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. */
+ 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. */
};
/* RCU's kthread states for tracing. */
@@ -282,6 +284,7 @@ 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 ed33970..3f6559a 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -1520,6 +1520,7 @@ int rcu_needs_cpu(int cpu)
{
int c = 0;
int snap;
+ int snap_nmi;
int thatcpu;
/* Check for being in the holdoff period. */
@@ -1530,10 +1531,10 @@ int rcu_needs_cpu(int cpu)
for_each_online_cpu(thatcpu) {
if (thatcpu == cpu)
continue;
- snap = atomic_add_return(0, &per_cpu(rcu_dynticks,
- thatcpu).dynticks);
+ snap = per_cpu(rcu_dynticks, thatcpu).dynticks;
+ snap_nmi = per_cpu(rcu_dynticks, thatcpu).dynticks_nmi;
smp_mb(); /* Order sampling of snap with end of grace period. */
- if ((snap & 0x1) != 0) {
+ if (((snap & 0x1) != 0) || ((snap_nmi & 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 9678cc3..aa0fd72 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/%d df=%lu",
- atomic_read(&rdp->dynticks->dynticks),
+ seq_printf(m, " dt=%d/%d dn=%d df=%lu",
+ rdp->dynticks->dynticks,
rdp->dynticks->dynticks_nesting,
- rdp->dynticks->dynticks_nmi_nesting,
+ rdp->dynticks->dynticks_nmi,
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",
- atomic_read(&rdp->dynticks->dynticks),
+ rdp->dynticks->dynticks,
rdp->dynticks->dynticks_nesting,
- rdp->dynticks->dynticks_nmi_nesting,
+ rdp->dynticks->dynticks_nmi,
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\",\"dt NMI nesting\",\"df\",");
+ seq_puts(m, "\"dt\",\"dt nesting\",\"dn\",\"df\",");
#endif /* #ifdef CONFIG_NO_HZ */
seq_puts(m, "\"of\",\"ri\",\"ql\",\"b\",\"ci\",\"co\",\"ca\"\n");
#ifdef CONFIG_TREE_PREEMPT_RCU
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/