summaryrefslogtreecommitdiff
path: root/include/linux/bpf.h
diff options
context:
space:
mode:
authorMartin KaFai Lau <kafai@fb.com>2017-08-18 11:28:00 -0700
committerDavid S. Miller <davem@davemloft.net>2017-08-19 21:35:43 -0700
commit96eabe7a40aa17e613cf3db2c742ee8b1fc764d0 (patch)
tree6364b3b63eeb2707e74c3bd770b01342016d936a /include/linux/bpf.h
parentbd76b87962833f6e55264030a227be0f090b1286 (diff)
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>
Diffstat (limited to 'include/linux/bpf.h')
-rw-r--r--include/linux/bpf.h10
1 files changed, 9 insertions, 1 deletions
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 1cc6c5ff61ec..55b88e329804 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -51,6 +51,7 @@ struct bpf_map {
u32 map_flags;
u32 pages;
u32 id;
+ int numa_node;
struct user_struct *user;
const struct bpf_map_ops *ops;
struct work_struct work;
@@ -264,7 +265,7 @@ struct bpf_map * __must_check bpf_map_inc(struct bpf_map *map, bool uref);
void bpf_map_put_with_uref(struct bpf_map *map);
void bpf_map_put(struct bpf_map *map);
int bpf_map_precharge_memlock(u32 pages);
-void *bpf_map_area_alloc(size_t size);
+void *bpf_map_area_alloc(size_t size, int numa_node);
void bpf_map_area_free(void *base);
extern int sysctl_unprivileged_bpf_disabled;
@@ -316,6 +317,13 @@ struct net_device *__dev_map_lookup_elem(struct bpf_map *map, u32 key);
void __dev_map_insert_ctx(struct bpf_map *map, u32 index);
void __dev_map_flush(struct bpf_map *map);
+/* Return map's numa specified by userspace */
+static inline int bpf_map_attr_numa_node(const union bpf_attr *attr)
+{
+ return (attr->map_flags & BPF_F_NUMA_NODE) ?
+ attr->numa_node : NUMA_NO_NODE;
+}
+
#else
static inline struct bpf_prog *bpf_prog_get(u32 ufd)
{