summaryrefslogtreecommitdiffstats
path: root/kernel/rcutree.c
diff options
context:
space:
mode:
authorPaul E. McKenney <paul.mckenney@linaro.org>2011-06-27 09:17:43 +0200
committerPaul E. McKenney <paulmck@linux.vnet.ibm.com>2011-09-29 06:38:22 +0200
commite4cc1f22b2f4e9b0207a8cdb63e56dcf99e82d35 (patch)
treeec3fad6587f0a83e764a571394bdfb85a84edf30 /kernel/rcutree.c
parentrcu: Add grace-period, quiescent-state, and call_rcu trace events (diff)
downloadlinux-e4cc1f22b2f4e9b0207a8cdb63e56dcf99e82d35.tar.xz
linux-e4cc1f22b2f4e9b0207a8cdb63e56dcf99e82d35.zip
rcu: Simplify quiescent-state accounting
There is often a delay between the time that a CPU passes through a quiescent state and the time that this quiescent state is reported to the RCU core. It is quite possible that the grace period ended before the quiescent state could be reported, for example, some other CPU might have deduced that this CPU passed through dyntick-idle mode. It is critically important that quiescent state be counted only against the grace period that was in effect at the time that the quiescent state was detected. Previously, this was handled by recording the number of the last grace period to complete when passing through a quiescent state. The RCU core then checks this number against the current value, and rejects the quiescent state if there is a mismatch. However, one additional possibility must be accounted for, namely that the quiescent state was recorded after the prior grace period completed but before the current grace period started. In this case, the RCU core must reject the quiescent state, but the recorded number will match. This is handled when the CPU becomes aware of a new grace period -- at that point, it invalidates any prior quiescent state. This works, but is a bit indirect. The new approach records the current grace period, and the RCU core checks to see (1) that this is still the current grace period and (2) that this grace period has not yet ended. This approach simplifies reasoning about correctness, and this commit changes over to this new approach. Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Diffstat (limited to 'kernel/rcutree.c')
-rw-r--r--kernel/rcutree.c44
1 files changed, 22 insertions, 22 deletions
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 7e0282949f8a..7e2f297aeec8 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -159,32 +159,34 @@ static int rcu_gp_in_progress(struct rcu_state *rsp)
* Note a quiescent state. Because we do not need to know
* how many quiescent states passed, just if there was at least
* one since the start of the grace period, this just sets a flag.
+ * The caller must have disabled preemption.
*/
void rcu_sched_qs(int cpu)
{
struct rcu_data *rdp = &per_cpu(rcu_sched_data, cpu);
- rdp->passed_quiesc_completed = rdp->gpnum - 1;
+ rdp->passed_quiesce_gpnum = rdp->gpnum;
barrier();
- if (rdp->passed_quiesc == 0)
+ if (rdp->passed_quiesce == 0)
trace_rcu_grace_period("rcu_sched", rdp->gpnum, "cpuqs");
- rdp->passed_quiesc = 1;
+ rdp->passed_quiesce = 1;
}
void rcu_bh_qs(int cpu)
{
struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu);
- rdp->passed_quiesc_completed = rdp->gpnum - 1;
+ rdp->passed_quiesce_gpnum = rdp->gpnum;
barrier();
- if (rdp->passed_quiesc == 0)
+ if (rdp->passed_quiesce == 0)
trace_rcu_grace_period("rcu_bh", rdp->gpnum, "cpuqs");
- rdp->passed_quiesc = 1;
+ rdp->passed_quiesce = 1;
}
/*
* Note a context switch. This is a quiescent state for RCU-sched,
* and requires special handling for preemptible RCU.
+ * The caller must have disabled preemption.
*/
void rcu_note_context_switch(int cpu)
{
@@ -694,7 +696,7 @@ static void __note_new_gpnum(struct rcu_state *rsp, struct rcu_node *rnp, struct
trace_rcu_grace_period(rsp->name, rdp->gpnum, "cpustart");
if (rnp->qsmask & rdp->grpmask) {
rdp->qs_pending = 1;
- rdp->passed_quiesc = 0;
+ rdp->passed_quiesce = 0;
} else
rdp->qs_pending = 0;
}
@@ -1027,7 +1029,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
* based on quiescent states detected in an earlier grace period!
*/
static void
-rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp, long lastcomp)
+rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp, long lastgp)
{
unsigned long flags;
unsigned long mask;
@@ -1035,17 +1037,15 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp, long las
rnp = rdp->mynode;
raw_spin_lock_irqsave(&rnp->lock, flags);
- if (lastcomp != rnp->completed) {
+ if (lastgp != rnp->gpnum || rnp->completed == rnp->gpnum) {
/*
- * Someone beat us to it for this grace period, so leave.
- * The race with GP start is resolved by the fact that we
- * hold the leaf rcu_node lock, so that the per-CPU bits
- * cannot yet be initialized -- so we would simply find our
- * CPU's bit already cleared in rcu_report_qs_rnp() if this
- * race occurred.
+ * The grace period in which this quiescent state was
+ * recorded has ended, so don't report it upwards.
+ * We will instead need a new quiescent state that lies
+ * within the current grace period.
*/
- rdp->passed_quiesc = 0; /* try again later! */
+ rdp->passed_quiesce = 0; /* need qs for new gp. */
raw_spin_unlock_irqrestore(&rnp->lock, flags);
return;
}
@@ -1089,14 +1089,14 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp)
* Was there a quiescent state since the beginning of the grace
* period? If no, then exit and wait for the next call.
*/
- if (!rdp->passed_quiesc)
+ if (!rdp->passed_quiesce)
return;
/*
* Tell RCU we are done (but rcu_report_qs_rdp() will be the
* judge of that).
*/
- rcu_report_qs_rdp(rdp->cpu, rsp, rdp, rdp->passed_quiesc_completed);
+ rcu_report_qs_rdp(rdp->cpu, rsp, rdp, rdp->passed_quiesce_gpnum);
}
#ifdef CONFIG_HOTPLUG_CPU
@@ -1712,7 +1712,7 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
check_cpu_stall(rsp, rdp);
/* Is the RCU core waiting for a quiescent state from this CPU? */
- if (rdp->qs_pending && !rdp->passed_quiesc) {
+ if (rdp->qs_pending && !rdp->passed_quiesce) {
/*
* If force_quiescent_state() coming soon and this CPU
@@ -1724,7 +1724,7 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
ULONG_CMP_LT(ACCESS_ONCE(rsp->jiffies_force_qs) - 1,
jiffies))
set_need_resched();
- } else if (rdp->qs_pending && rdp->passed_quiesc) {
+ } else if (rdp->qs_pending && rdp->passed_quiesce) {
rdp->n_rp_report_qs++;
return 1;
}
@@ -1907,7 +1907,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptible)
/* Set up local state, ensuring consistent view of global state. */
raw_spin_lock_irqsave(&rnp->lock, flags);
- rdp->passed_quiesc = 0; /* We could be racing with new GP, */
+ rdp->passed_quiesce = 0; /* We could be racing with new GP, */
rdp->qs_pending = 1; /* so set up to respond to current GP. */
rdp->beenonline = 1; /* We have now been online. */
rdp->preemptible = preemptible;
@@ -1935,7 +1935,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptible)
if (rnp == rdp->mynode) {
rdp->gpnum = rnp->completed; /* if GP in progress... */
rdp->completed = rnp->completed;
- rdp->passed_quiesc_completed = rnp->completed - 1;
+ rdp->passed_quiesce_gpnum = rnp->gpnum - 1;
trace_rcu_grace_period(rsp->name, rdp->gpnum, "cpuonl");
}
raw_spin_unlock(&rnp->lock); /* irqs already disabled. */