summaryrefslogtreecommitdiffstats
path: root/kernel/rcutree_plugin.h
diff options
context:
space:
mode:
authorPaul E. McKenney <paulmck@linux.vnet.ibm.com>2009-08-27 14:58:16 -0700
committerIngo Molnar <mingo@elte.hu>2009-08-29 15:34:39 +0200
commitdd5d19bafd90d33043a4a14b2e2d98612caa293c (patch)
treec21d547124d277f00332bdb01c75f2f4f321de8c /kernel/rcutree_plugin.h
parent06e799764eb7c2e4640888d438c3524d756613e1 (diff)
downloadop-kernel-dev-dd5d19bafd90d33043a4a14b2e2d98612caa293c.zip
op-kernel-dev-dd5d19bafd90d33043a4a14b2e2d98612caa293c.tar.gz
rcu: Create rcutree plugins to handle hotplug CPU for multi-level trees
When offlining CPUs from a multi-level tree, there is the possibility of offlining the last CPU from a given node when there are preempted RCU read-side critical sections that started life on one of the CPUs on that node. In this case, the corresponding tasks will be enqueued via the task_struct's rcu_node_entry list_head onto one of the rcu_node's blocked_tasks[] lists. These tasks need to be moved somewhere else so that they will prevent the current grace period from ending. That somewhere is the root rcu_node. Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: laijs@cn.fujitsu.com Cc: dipankar@in.ibm.com Cc: akpm@linux-foundation.org Cc: mathieu.desnoyers@polymtl.ca Cc: josht@linux.vnet.ibm.com Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org LKML-Reference: <20090827215816.GA30472@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Diffstat (limited to 'kernel/rcutree_plugin.h')
-rw-r--r--kernel/rcutree_plugin.h69
1 files changed, 64 insertions, 5 deletions
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 201334c..04343be 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -92,7 +92,7 @@ static void rcu_preempt_qs(int cpu)
rnp = rdp->mynode;
spin_lock(&rnp->lock);
t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED;
- t->rcu_blocked_cpu = cpu;
+ t->rcu_blocked_node = (void *)rnp;
/*
* If this CPU has already checked in, then this task
@@ -170,12 +170,21 @@ static void rcu_read_unlock_special(struct task_struct *t)
if (special & RCU_READ_UNLOCK_BLOCKED) {
t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_BLOCKED;
- /* Remove this task from the list it blocked on. */
- rnp = rcu_preempt_state.rda[t->rcu_blocked_cpu]->mynode;
- spin_lock(&rnp->lock);
+ /*
+ * Remove this task from the list it blocked on. The
+ * task can migrate while we acquire the lock, but at
+ * most one time. So at most two passes through loop.
+ */
+ for (;;) {
+ rnp = (struct rcu_node *)t->rcu_blocked_node;
+ spin_lock(&rnp->lock);
+ if (rnp == (struct rcu_node *)t->rcu_blocked_node)
+ break;
+ spin_unlock(&rnp->lock);
+ }
empty = list_empty(&rnp->blocked_tasks[rnp->gpnum & 0x1]);
list_del_init(&t->rcu_node_entry);
- t->rcu_blocked_cpu = -1;
+ t->rcu_blocked_node = NULL;
/*
* If this was the last task on the current list, and if
@@ -262,6 +271,47 @@ static int rcu_preempted_readers(struct rcu_node *rnp)
#ifdef CONFIG_HOTPLUG_CPU
/*
+ * Handle tasklist migration for case in which all CPUs covered by the
+ * specified rcu_node have gone offline. Move them up to the root
+ * rcu_node. The reason for not just moving them to the immediate
+ * parent is to remove the need for rcu_read_unlock_special() to
+ * make more than two attempts to acquire the target rcu_node's lock.
+ *
+ * The caller must hold rnp->lock with irqs disabled.
+ */
+static void rcu_preempt_offline_tasks(struct rcu_state *rsp,
+ struct rcu_node *rnp)
+{
+ int i;
+ struct list_head *lp;
+ struct list_head *lp_root;
+ struct rcu_node *rnp_root = rcu_get_root(rsp);
+ struct task_struct *tp;
+
+ if (rnp == rnp_root)
+ return; /* Shouldn't happen: at least one CPU online. */
+
+ /*
+ * Move tasks up to root rcu_node. Rely on the fact that the
+ * root rcu_node can be at most one ahead of the rest of the
+ * rcu_nodes in terms of gp_num value. This fact allows us to
+ * move the blocked_tasks[] array directly, element by element.
+ */
+ for (i = 0; i < 2; i++) {
+ lp = &rnp->blocked_tasks[i];
+ lp_root = &rnp_root->blocked_tasks[i];
+ while (!list_empty(lp)) {
+ tp = list_entry(lp->next, typeof(*tp), rcu_node_entry);
+ spin_lock(&rnp_root->lock); /* irqs already disabled */
+ list_del(&tp->rcu_node_entry);
+ tp->rcu_blocked_node = rnp_root;
+ list_add(&tp->rcu_node_entry, lp_root);
+ spin_unlock(&rnp_root->lock); /* irqs remain disabled */
+ }
+ }
+}
+
+/*
* Do CPU-offline processing for preemptable RCU.
*/
static void rcu_preempt_offline_cpu(int cpu)
@@ -410,6 +460,15 @@ static int rcu_preempted_readers(struct rcu_node *rnp)
#ifdef CONFIG_HOTPLUG_CPU
/*
+ * Because preemptable RCU does not exist, it never needs to migrate
+ * tasks that were blocked within RCU read-side critical sections.
+ */
+static void rcu_preempt_offline_tasks(struct rcu_state *rsp,
+ struct rcu_node *rnp)
+{
+}
+
+/*
* Because preemptable RCU does not exist, it never needs CPU-offline
* processing.
*/
OpenPOWER on IntegriCloud