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, 10 insertions, 4 deletions

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index b8cb1b3c9bfb..9378f3ba2cbf 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -105,7 +105,7 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
         return map;
 }
 
-void *bpf_map_area_alloc(size_t size)
+void *bpf_map_area_alloc(size_t size, int numa_node)
 {
         /* We definitely need __GFP_NORETRY, so OOM killer doesn't
          * trigger under memory pressure as we really just want to
@@ -115,12 +115,13 @@ void *bpf_map_area_alloc(size_t size)
         void *area;
 
         if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
-                area = kmalloc(size, GFP_USER | flags);
+                area = kmalloc_node(size, GFP_USER | flags, numa_node);
                 if (area != NULL)
                         return area;
         }
 
-        return __vmalloc(size, GFP_KERNEL | flags, PAGE_KERNEL);
+        return __vmalloc_node_flags_caller(size, numa_node, GFP_KERNEL | flags,
+                                           __builtin_return_address(0));
 }
 
 void bpf_map_area_free(void *area)
@@ -309,10 +310,11 @@ int bpf_map_new_fd(struct bpf_map *map)
                    offsetof(union bpf_attr, CMD##_LAST_FIELD) - \
                    sizeof(attr->CMD##_LAST_FIELD)) != NULL
 
-#define BPF_MAP_CREATE_LAST_FIELD inner_map_fd
+#define BPF_MAP_CREATE_LAST_FIELD numa_node
 /* called via syscall */
 static int map_create(union bpf_attr *attr)
 {
+        int numa_node = bpf_map_attr_numa_node(attr);
         struct bpf_map *map;
         int err;
 
@@ -320,6 +322,10 @@ static int map_create(union bpf_attr *attr)
         if (err)
                 return -EINVAL;
 
+        if (numa_node != NUMA_NO_NODE &&
+            (numa_node >= nr_node_ids || !node_online(numa_node)))
+                return -EINVAL;
+
         /* find map type and init map: hashtable vs rbtree vs bloom vs ... */
         map = find_and_alloc_map(attr);
         if (IS_ERR(map))