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, 15 insertions, 4 deletions

diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 4fb463172aa8..47ae748c3a49 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -18,6 +18,9 @@
 #include "bpf_lru_list.h"
 #include "map_in_map.h"
 
+#define HTAB_CREATE_FLAG_MASK \
+        (BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE)
+
 struct bucket {
         struct hlist_nulls_head head;
         raw_spinlock_t lock;
@@ -138,7 +141,8 @@ static int prealloc_init(struct bpf_htab *htab)
         if (!htab_is_percpu(htab) && !htab_is_lru(htab))
                 num_entries += num_possible_cpus();
 
-        htab->elems = bpf_map_area_alloc(htab->elem_size * num_entries);
+        htab->elems = bpf_map_area_alloc(htab->elem_size * num_entries,
+                                         htab->map.numa_node);
         if (!htab->elems)
                 return -ENOMEM;
 
@@ -233,6 +237,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
          */
         bool percpu_lru = (attr->map_flags & BPF_F_NO_COMMON_LRU);
         bool prealloc = !(attr->map_flags & BPF_F_NO_PREALLOC);
+        int numa_node = bpf_map_attr_numa_node(attr);
         struct bpf_htab *htab;
         int err, i;
         u64 cost;
@@ -248,7 +253,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
                  */
                 return ERR_PTR(-EPERM);
 
-        if (attr->map_flags & ~(BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU))
+        if (attr->map_flags & ~HTAB_CREATE_FLAG_MASK)
                 /* reserved bits should not be used */
                 return ERR_PTR(-EINVAL);
 
@@ -258,6 +263,9 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
         if (lru && !prealloc)
                 return ERR_PTR(-ENOTSUPP);
 
+        if (numa_node != NUMA_NO_NODE && (percpu || percpu_lru))
+                return ERR_PTR(-EINVAL);
+
         htab = kzalloc(sizeof(*htab), GFP_USER);
         if (!htab)
                 return ERR_PTR(-ENOMEM);
@@ -268,6 +276,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
         htab->map.value_size = attr->value_size;
         htab->map.max_entries = attr->max_entries;
         htab->map.map_flags = attr->map_flags;
+        htab->map.numa_node = numa_node;
 
         /* check sanity of attributes.
          * value_size == 0 may be allowed in the future to use map as a set
@@ -346,7 +355,8 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 
         err = -ENOMEM;
         htab->buckets = bpf_map_area_alloc(htab->n_buckets *
-                                           sizeof(struct bucket));
+                                           sizeof(struct bucket),
+                                           htab->map.numa_node);
         if (!htab->buckets)
                 goto free_htab;
 
@@ -689,7 +699,8 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
                                 atomic_dec(&htab->count);
                                 return ERR_PTR(-E2BIG);
                         }
-                l_new = kmalloc(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN);
+                l_new = kmalloc_node(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN,
+                                     htab->map.numa_node);
                 if (!l_new)
                         return ERR_PTR(-ENOMEM);
         }