1 files changed, 45 insertions, 10 deletions

diff --git a/net/core/flow.c b/net/core/flow.c
index 43f7495..7102f16 100644
--- a/net/core/flow.c
+++ b/net/core/flow.c
@@ -132,14 +132,14 @@ static void __flow_cache_shrink(struct flow_cache *fc,
 				int shrink_to)
 {
 	struct flow_cache_entry *fle;
-	struct hlist_node *entry, *tmp;
+	struct hlist_node *tmp;
 	LIST_HEAD(gc_list);
 	int i, deleted = 0;
 
 	for (i = 0; i < flow_cache_hash_size(fc); i++) {
 		int saved = 0;
 
-		hlist_for_each_entry_safe(fle, entry, tmp,
+		hlist_for_each_entry_safe(fle, tmp,
 					  &fcp->hash_table[i], u.hlist) {
 			if (saved < shrink_to &&
 			    flow_entry_valid(fle)) {
@@ -211,7 +211,6 @@ flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir,
 	struct flow_cache *fc = &flow_cache_global;
 	struct flow_cache_percpu *fcp;
 	struct flow_cache_entry *fle, *tfle;
-	struct hlist_node *entry;
 	struct flow_cache_object *flo;
 	size_t keysize;
 	unsigned int hash;
@@ -235,7 +234,7 @@ flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir,
 		flow_new_hash_rnd(fc, fcp);
 
 	hash = flow_hash_code(fc, fcp, key, keysize);
-	hlist_for_each_entry(tfle, entry, &fcp->hash_table[hash], u.hlist) {
+	hlist_for_each_entry(tfle, &fcp->hash_table[hash], u.hlist) {
 		if (tfle->net == net &&
 		    tfle->family == family &&
 		    tfle->dir == dir &&
@@ -301,13 +300,13 @@ static void flow_cache_flush_tasklet(unsigned long data)
 	struct flow_cache *fc = info->cache;
 	struct flow_cache_percpu *fcp;
 	struct flow_cache_entry *fle;
-	struct hlist_node *entry, *tmp;
+	struct hlist_node *tmp;
 	LIST_HEAD(gc_list);
 	int i, deleted = 0;
 
 	fcp = this_cpu_ptr(fc->percpu);
 	for (i = 0; i < flow_cache_hash_size(fc); i++) {
-		hlist_for_each_entry_safe(fle, entry, tmp,
+		hlist_for_each_entry_safe(fle, tmp,
 					  &fcp->hash_table[i], u.hlist) {
 			if (flow_entry_valid(fle))
 				continue;
@@ -324,12 +323,30 @@ static void flow_cache_flush_tasklet(unsigned long data)
 		complete(&info->completion);
 }
 
+/*
+ * Return whether a cpu needs flushing.  Conservatively, we assume
+ * the presence of any entries means the core may require flushing,
+ * since the flow_cache_ops.check() function may assume it's running
+ * on the same core as the per-cpu cache component.
+ */
+static int flow_cache_percpu_empty(struct flow_cache *fc, int cpu)
+{
+	struct flow_cache_percpu *fcp;
+	int i;
+
+	fcp = per_cpu_ptr(fc->percpu, cpu);
+	for (i = 0; i < flow_cache_hash_size(fc); i++)
+		if (!hlist_empty(&fcp->hash_table[i]))
+			return 0;
+	return 1;
+}
+
 static void flow_cache_flush_per_cpu(void *data)
 {
 	struct flow_flush_info *info = data;
 	struct tasklet_struct *tasklet;
 
-	tasklet = this_cpu_ptr(&info->cache->percpu->flush_tasklet);
+	tasklet = &this_cpu_ptr(info->cache->percpu)->flush_tasklet;
 	tasklet->data = (unsigned long)info;
 	tasklet_schedule(tasklet);
 }
@@ -338,22 +355,40 @@ void flow_cache_flush(void)
 {
 	struct flow_flush_info info;
 	static DEFINE_MUTEX(flow_flush_sem);
+	cpumask_var_t mask;
+	int i, self;
+
+	/* Track which cpus need flushing to avoid disturbing all cores. */
+	if (!alloc_cpumask_var(&mask, GFP_KERNEL))
+		return;
+	cpumask_clear(mask);
 
 	/* Don't want cpus going down or up during this. */
 	get_online_cpus();
 	mutex_lock(&flow_flush_sem);
 	info.cache = &flow_cache_global;
-	atomic_set(&info.cpuleft, num_online_cpus());
+	for_each_online_cpu(i)
+		if (!flow_cache_percpu_empty(info.cache, i))
+			cpumask_set_cpu(i, mask);
+	atomic_set(&info.cpuleft, cpumask_weight(mask));
+	if (atomic_read(&info.cpuleft) == 0)
+		goto done;
+
 	init_completion(&info.completion);
 
 	local_bh_disable();
-	smp_call_function(flow_cache_flush_per_cpu, &info, 0);
-	flow_cache_flush_tasklet((unsigned long)&info);
+	self = cpumask_test_and_clear_cpu(smp_processor_id(), mask);
+	on_each_cpu_mask(mask, flow_cache_flush_per_cpu, &info, 0);
+	if (self)
+		flow_cache_flush_tasklet((unsigned long)&info);
 	local_bh_enable();
 
 	wait_for_completion(&info.completion);
+
+done:
 	mutex_unlock(&flow_flush_sem);
 	put_online_cpus();
+	free_cpumask_var(mask);
 }
 
 static void flow_cache_flush_task(struct work_struct *work)