From: Martin KaFai Lau <kafai@fb.com>
Date: Fri, 18 Aug 2017 11:28:01 -0700
Subject: bpf: Allow numa selection in INNER_LRU_HASH_PREALLOC test of
map_perf_test
Patch-mainline: v4.14-rc1
Git-commit: ad17d0e6c708805bf9e6686eb747cc528b702e67
References: bsc#1109837
This patch makes the needed changes to allow each process of
the INNER_LRU_HASH_PREALLOC test to provide its numa node id
when creating the lru map.
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>
Acked-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
---
samples/bpf/bpf_load.c | 21 ++++++++++++-------
samples/bpf/bpf_load.h | 1
samples/bpf/map_perf_test_kern.c | 2 +
samples/bpf/map_perf_test_user.c | 12 ++++++++---
tools/include/uapi/linux/bpf.h | 10 ++++++++-
tools/lib/bpf/bpf.c | 32 ++++++++++++++++++++++++++----
tools/lib/bpf/bpf.h | 6 +++++
tools/testing/selftests/bpf/bpf_helpers.h | 1
8 files changed, 69 insertions(+), 16 deletions(-)
--- a/samples/bpf/bpf_load.c
+++ b/samples/bpf/bpf_load.c
@@ -201,7 +201,7 @@ static int load_and_attach(const char *e
static int load_maps(struct bpf_map_data *maps, int nr_maps,
fixup_map_cb fixup_map)
{
- int i;
+ int i, numa_node;
for (i = 0; i < nr_maps; i++) {
if (fixup_map) {
@@ -213,21 +213,26 @@ static int load_maps(struct bpf_map_data
}
}
+ numa_node = maps[i].def.map_flags & BPF_F_NUMA_NODE ?
+ maps[i].def.numa_node : -1;
+
if (maps[i].def.type == BPF_MAP_TYPE_ARRAY_OF_MAPS ||
maps[i].def.type == BPF_MAP_TYPE_HASH_OF_MAPS) {
int inner_map_fd = map_fd[maps[i].def.inner_map_idx];
- map_fd[i] = bpf_create_map_in_map(maps[i].def.type,
+ map_fd[i] = bpf_create_map_in_map_node(maps[i].def.type,
maps[i].def.key_size,
inner_map_fd,
maps[i].def.max_entries,
- maps[i].def.map_flags);
+ maps[i].def.map_flags,
+ numa_node);
} else {
- map_fd[i] = bpf_create_map(maps[i].def.type,
- maps[i].def.key_size,
- maps[i].def.value_size,
- maps[i].def.max_entries,
- maps[i].def.map_flags);
+ map_fd[i] = bpf_create_map_node(maps[i].def.type,
+ maps[i].def.key_size,
+ maps[i].def.value_size,
+ maps[i].def.max_entries,
+ maps[i].def.map_flags,
+ numa_node);
}
if (map_fd[i] < 0) {
printf("failed to create a map: %d %s\n",
--- a/samples/bpf/bpf_load.h
+++ b/samples/bpf/bpf_load.h
@@ -13,6 +13,7 @@ struct bpf_map_def {
unsigned int max_entries;
unsigned int map_flags;
unsigned int inner_map_idx;
+ unsigned int numa_node;
};
struct bpf_map_data {
--- a/samples/bpf/map_perf_test_kern.c
+++ b/samples/bpf/map_perf_test_kern.c
@@ -40,6 +40,8 @@ struct bpf_map_def SEC("maps") inner_lru
.key_size = sizeof(u32),
.value_size = sizeof(long),
.max_entries = MAX_ENTRIES,
+ .map_flags = BPF_F_NUMA_NODE,
+ .numa_node = 0,
};
struct bpf_map_def SEC("maps") array_of_lru_hashs = {
--- a/samples/bpf/map_perf_test_user.c
+++ b/samples/bpf/map_perf_test_user.c
@@ -97,14 +97,20 @@ static void do_test_lru(enum test_type t
if (test == INNER_LRU_HASH_PREALLOC) {
int outer_fd = map_fd[array_of_lru_hashs_idx];
+ unsigned int mycpu, mynode;
assert(cpu < MAX_NR_CPUS);
if (cpu) {
+ ret = syscall(__NR_getcpu, &mycpu, &mynode, NULL);
+ assert(!ret);
+
inner_lru_map_fds[cpu] =
- bpf_create_map(BPF_MAP_TYPE_LRU_HASH,
- sizeof(uint32_t), sizeof(long),
- inner_lru_hash_size, 0);
+ bpf_create_map_node(BPF_MAP_TYPE_LRU_HASH,
+ sizeof(uint32_t),
+ sizeof(long),
+ inner_lru_hash_size, 0,
+ mynode);
if (inner_lru_map_fds[cpu] == -1) {
printf("cannot create BPF_MAP_TYPE_LRU_HASH %s(%d)\n",
strerror(errno), errno);
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -168,6 +168,7 @@ enum bpf_sockmap_flags {
#define BPF_NOEXIST 1 /* create new element if it didn't exist */
#define BPF_EXIST 2 /* update existing element */
+/* flags for BPF_MAP_CREATE command */
#define BPF_F_NO_PREALLOC (1U << 0)
/* Instead of having one common LRU list in the
* BPF_MAP_TYPE_LRU_[PERCPU_]HASH map, use a percpu LRU list
@@ -176,6 +177,8 @@ enum bpf_sockmap_flags {
* across different LRU lists.
*/
#define BPF_F_NO_COMMON_LRU (1U << 1)
+/* Specify numa node during map creation */
+#define BPF_F_NUMA_NODE (1U << 2)
union bpf_attr {
struct { /* anonymous struct used by BPF_MAP_CREATE command */
@@ -183,8 +186,13 @@ union bpf_attr {
__u32 key_size; /* size of key in bytes */
__u32 value_size; /* size of value in bytes */
__u32 max_entries; /* max number of entries in a map */
- __u32 map_flags; /* prealloc or not */
+ __u32 map_flags; /* BPF_MAP_CREATE related
+ * flags defined above.
+ */
__u32 inner_map_fd; /* fd pointing to the inner map */
+ __u32 numa_node; /* numa node (effective only if
+ * BPF_F_NUMA_NODE is set).
+ */
};
struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -55,8 +55,9 @@ static inline int sys_bpf(enum bpf_cmd c
return syscall(__NR_bpf, cmd, attr, size);
}
-int bpf_create_map(enum bpf_map_type map_type, int key_size,
- int value_size, int max_entries, __u32 map_flags)
+int bpf_create_map_node(enum bpf_map_type map_type, int key_size,
+ int value_size, int max_entries, __u32 map_flags,
+ int node)
{
union bpf_attr attr;
@@ -67,12 +68,24 @@ int bpf_create_map(enum bpf_map_type map
attr.value_size = value_size;
attr.max_entries = max_entries;
attr.map_flags = map_flags;
+ if (node >= 0) {
+ attr.map_flags |= BPF_F_NUMA_NODE;
+ attr.numa_node = node;
+ }
return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
}
-int bpf_create_map_in_map(enum bpf_map_type map_type, int key_size,
- int inner_map_fd, int max_entries, __u32 map_flags)
+int bpf_create_map(enum bpf_map_type map_type, int key_size,
+ int value_size, int max_entries, __u32 map_flags)
+{
+ return bpf_create_map_node(map_type, key_size, value_size,
+ max_entries, map_flags, -1);
+}
+
+int bpf_create_map_in_map_node(enum bpf_map_type map_type, int key_size,
+ int inner_map_fd, int max_entries,
+ __u32 map_flags, int node)
{
union bpf_attr attr;
@@ -84,10 +97,21 @@ int bpf_create_map_in_map(enum bpf_map_t
attr.inner_map_fd = inner_map_fd;
attr.max_entries = max_entries;
attr.map_flags = map_flags;
+ if (node >= 0) {
+ attr.map_flags |= BPF_F_NUMA_NODE;
+ attr.numa_node = node;
+ }
return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
}
+int bpf_create_map_in_map(enum bpf_map_type map_type, int key_size,
+ int inner_map_fd, int max_entries, __u32 map_flags)
+{
+ return bpf_create_map_in_map_node(map_type, key_size, inner_map_fd,
+ max_entries, map_flags, -1);
+}
+
int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
size_t insns_cnt, const char *license,
__u32 kern_version, char *log_buf, size_t log_buf_sz)
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -24,8 +24,14 @@
#include <linux/bpf.h>
#include <stddef.h>
+int bpf_create_map_node(enum bpf_map_type map_type, int key_size,
+ int value_size, int max_entries, __u32 map_flags,
+ int node);
int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size,
int max_entries, __u32 map_flags);
+int bpf_create_map_in_map_node(enum bpf_map_type map_type, int key_size,
+ int inner_map_fd, int max_entries,
+ __u32 map_flags, int node);
int bpf_create_map_in_map(enum bpf_map_type map_type, int key_size,
int inner_map_fd, int max_entries, __u32 map_flags);
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -94,6 +94,7 @@ struct bpf_map_def {
unsigned int max_entries;
unsigned int map_flags;
unsigned int inner_map_idx;
+ unsigned int numa_node;
};
static int (*bpf_skb_load_bytes)(void *ctx, int off, void *to, int len) =