Commit 5b59d467 authored by Eric Dumazet's avatar Eric Dumazet Committed by David S. Miller

rps: NUMA flow limit allocations

Given we allocate memory for each cpu, we can do this
using NUMA affinities, instead of using NUMA policies
of the process changing flow_limit_cpu_bitmap value.
Signed-off-by: default avatarEric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent c5036813
...@@ -122,7 +122,8 @@ static int flow_limit_cpu_sysctl(struct ctl_table *table, int write, ...@@ -122,7 +122,8 @@ static int flow_limit_cpu_sysctl(struct ctl_table *table, int write,
synchronize_rcu(); synchronize_rcu();
kfree(cur); kfree(cur);
} else if (!cur && cpumask_test_cpu(i, mask)) { } else if (!cur && cpumask_test_cpu(i, mask)) {
cur = kzalloc(len, GFP_KERNEL); cur = kzalloc_node(len, GFP_KERNEL,
cpu_to_node(i));
if (!cur) { if (!cur) {
/* not unwinding previous changes */ /* not unwinding previous changes */
ret = -ENOMEM; ret = -ENOMEM;
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment