From 96eabe7a40aa17e613cf3db2c742ee8b1fc764d0 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Fri, 18 Aug 2017 11:28:00 -0700 Subject: bpf: Allow selecting numa node during map creation The current map creation API does not allow to provide the numa-node preference. The memory usually comes from where the map-creation-process is running. The performance is not ideal if the bpf_prog is known to always run in a numa node different from the map-creation-process. One of the use case is sharding on CPU to different LRU maps (i.e. an array of LRU maps). Here is the test result of map_perf_test on the INNER_LRU_HASH_PREALLOC test if we force the lru map used by CPU0 to be allocated from a remote numa node: [ The machine has 20 cores. CPU0-9 at node 0. CPU10-19 at node 1 ] ># taskset -c 10 ./map_perf_test 512 8 1260000 8000000 5:inner_lru_hash_map_perf pre-alloc 1628380 events per sec 4:inner_lru_hash_map_perf pre-alloc 1626396 events per sec 3:inner_lru_hash_map_perf pre-alloc 1626144 events per sec 6:inner_lru_hash_map_perf pre-alloc 1621657 events per sec 2:inner_lru_hash_map_perf pre-alloc 1621534 events per sec 1:inner_lru_hash_map_perf pre-alloc 1620292 events per sec 7:inner_lru_hash_map_perf pre-alloc 1613305 events per sec 0:inner_lru_hash_map_perf pre-alloc 1239150 events per sec #<<< After specifying numa node: ># taskset -c 10 ./map_perf_test 512 8 1260000 8000000 5:inner_lru_hash_map_perf pre-alloc 1629627 events per sec 3:inner_lru_hash_map_perf pre-alloc 1628057 events per sec 1:inner_lru_hash_map_perf pre-alloc 1623054 events per sec 6:inner_lru_hash_map_perf pre-alloc 1616033 events per sec 2:inner_lru_hash_map_perf pre-alloc 1614630 events per sec 4:inner_lru_hash_map_perf pre-alloc 1612651 events per sec 7:inner_lru_hash_map_perf pre-alloc 1609337 events per sec 0:inner_lru_hash_map_perf pre-alloc 1619340 events per sec #<<< This patch adds one field, numa_node, to the bpf_attr. Since numa node 0 is a valid node, a new flag BPF_F_NUMA_NODE is also added. The numa_node field is honored if and only if the BPF_F_NUMA_NODE flag is set. Numa node selection is not supported for percpu map. This patch does not change all the kmalloc. F.e. 'htab = kzalloc()' is not changed since the object is small enough to stay in the cache. Signed-off-by: Martin KaFai Lau Acked-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- kernel/bpf/devmap.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'kernel/bpf/devmap.c') diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 18a72a8add43..67f4f00ce33a 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -80,7 +80,7 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || - attr->value_size != 4 || attr->map_flags) + attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE) return ERR_PTR(-EINVAL); dtab = kzalloc(sizeof(*dtab), GFP_USER); @@ -93,6 +93,7 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) dtab->map.value_size = attr->value_size; dtab->map.max_entries = attr->max_entries; dtab->map.map_flags = attr->map_flags; + dtab->map.numa_node = bpf_map_attr_numa_node(attr); err = -ENOMEM; @@ -119,7 +120,8 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) goto free_dtab; dtab->netdev_map = bpf_map_area_alloc(dtab->map.max_entries * - sizeof(struct bpf_dtab_netdev *)); + sizeof(struct bpf_dtab_netdev *), + dtab->map.numa_node); if (!dtab->netdev_map) goto free_dtab; @@ -344,7 +346,8 @@ static int dev_map_update_elem(struct bpf_map *map, void *key, void *value, if (!ifindex) { dev = NULL; } else { - dev = kmalloc(sizeof(*dev), GFP_ATOMIC | __GFP_NOWARN); + dev = kmalloc_node(sizeof(*dev), GFP_ATOMIC | __GFP_NOWARN, + map->numa_node); if (!dev) return -ENOMEM; -- cgit