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 <kafai@fb.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 7 insertions, 2 deletions

diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c
index b09185f0f17d..1b767844a76f 100644
--- a/kernel/bpf/lpm_trie.c
+++ b/kernel/bpf/lpm_trie.c
@@ -244,7 +244,8 @@ static struct lpm_trie_node *lpm_trie_node_alloc(const struct lpm_trie *trie,
 	if (value)
 		size += trie->map.value_size;
 
-	node = kmalloc(size, GFP_ATOMIC | __GFP_NOWARN);
+	node = kmalloc_node(size, GFP_ATOMIC | __GFP_NOWARN,
+			    trie->map.numa_node);
 	if (!node)
 		return NULL;
 
@@ -405,6 +406,8 @@ static int trie_delete_elem(struct bpf_map *map, void *key)
 #define LPM_KEY_SIZE_MAX	LPM_KEY_SIZE(LPM_DATA_SIZE_MAX)
 #define LPM_KEY_SIZE_MIN	LPM_KEY_SIZE(LPM_DATA_SIZE_MIN)
 
+#define LPM_CREATE_FLAG_MASK	(BPF_F_NO_PREALLOC | BPF_F_NUMA_NODE)
+
 static struct bpf_map *trie_alloc(union bpf_attr *attr)
 {
 	struct lpm_trie *trie;
@@ -416,7 +419,8 @@ static struct bpf_map *trie_alloc(union bpf_attr *attr)
 
 	/* check sanity of attributes */
 	if (attr->max_entries == 0 ||
-	    attr->map_flags != BPF_F_NO_PREALLOC ||
+	    !(attr->map_flags & BPF_F_NO_PREALLOC) ||
+	    attr->map_flags & ~LPM_CREATE_FLAG_MASK ||
 	    attr->key_size < LPM_KEY_SIZE_MIN ||
 	    attr->key_size > LPM_KEY_SIZE_MAX ||
 	    attr->value_size < LPM_VAL_SIZE_MIN ||
@@ -433,6 +437,7 @@ static struct bpf_map *trie_alloc(union bpf_attr *attr)
 	trie->map.value_size = attr->value_size;
 	trie->map.max_entries = attr->max_entries;
 	trie->map.map_flags = attr->map_flags;
+	trie->map.numa_node = bpf_map_attr_numa_node(attr);
 	trie->data_size = attr->key_size -
 			  offsetof(struct bpf_lpm_trie_key, data);
 	trie->max_prefixlen = trie->data_size * 8;