bpf: Increase supported cgroup storage value size

Current max cgroup storage value size is 4k (PAGE_SIZE). The other local
storages accept up to 64k (BPF_LOCAL_STORAGE_MAX_VALUE_SIZE). Let's align
max cgroup value size with the other storages.

For percpu, the max is 32k (PCPU_MIN_UNIT_SIZE) because percpu
allocator is not happy about larger values.

netcnt test is extended to exercise those maximum values
(non-percpu max size is close to, but not real max).

v4:
* remove inner union (Andrii Nakryiko)
* keep net_cnt on the stack (Andrii Nakryiko)

v3:
* refine SIZEOF_BPF_LOCAL_STORAGE_ELEM comment (Yonghong Song)
* anonymous struct in percpu_net_cnt & net_cnt (Yonghong Song)
* reorder free (Yonghong Song)

v2:
* cap max_value_size instead of BUILD_BUG_ON (Martin KaFai Lau)

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20210727222335.4029096-1-sdf@google.com

3 files changed, 35 insertions, 15 deletions

diff --git a/tools/testing/selftests/bpf/netcnt_common.h b/tools/testing/selftests/bpf/netcnt_common.h
index 81084c1c2c23..0ab1c88041cd 100644
--- a/tools/testing/selftests/bpf/netcnt_common.h
+++ b/tools/testing/selftests/bpf/netcnt_common.h
@@ -6,19 +6,39 @@
 
 #define MAX_PERCPU_PACKETS 32
 
-struct percpu_net_cnt {
-	__u64 packets;
-	__u64 bytes;
+/* sizeof(struct bpf_local_storage_elem):
+ *
+ * It really is about 128 bytes on x86_64, but allocate more to account for
+ * possible layout changes, different architectures, etc.
+ * The kernel will wrap up to PAGE_SIZE internally anyway.
+ */
+#define SIZEOF_BPF_LOCAL_STORAGE_ELEM		256
 
-	__u64 prev_ts;
+/* Try to estimate kernel's BPF_LOCAL_STORAGE_MAX_VALUE_SIZE: */
+#define BPF_LOCAL_STORAGE_MAX_VALUE_SIZE	(0xFFFF - \
+						 SIZEOF_BPF_LOCAL_STORAGE_ELEM)
 
-	__u64 prev_packets;
-	__u64 prev_bytes;
+#define PCPU_MIN_UNIT_SIZE			32768
+
+union percpu_net_cnt {
+	struct {
+		__u64 packets;
+		__u64 bytes;
+
+		__u64 prev_ts;
+
+		__u64 prev_packets;
+		__u64 prev_bytes;
+	};
+	__u8 data[PCPU_MIN_UNIT_SIZE];
 };
 
-struct net_cnt {
-	__u64 packets;
-	__u64 bytes;
+union net_cnt {
+	struct {
+		__u64 packets;
+		__u64 bytes;
+	};
+	__u8 data[BPF_LOCAL_STORAGE_MAX_VALUE_SIZE];
 };
 
 #endif
diff --git a/tools/testing/selftests/bpf/progs/netcnt_prog.c b/tools/testing/selftests/bpf/progs/netcnt_prog.c
index d071adf178bd..43649bce4c54 100644
--- a/tools/testing/selftests/bpf/progs/netcnt_prog.c
+++ b/tools/testing/selftests/bpf/progs/netcnt_prog.c
@@ -13,21 +13,21 @@
 struct {
 	__uint(type, BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE);
 	__type(key, struct bpf_cgroup_storage_key);
-	__type(value, struct percpu_net_cnt);
+	__type(value, union percpu_net_cnt);
 } percpu_netcnt SEC(".maps");
 
 struct {
 	__uint(type, BPF_MAP_TYPE_CGROUP_STORAGE);
 	__type(key, struct bpf_cgroup_storage_key);
-	__type(value, struct net_cnt);
+	__type(value, union net_cnt);
 } netcnt SEC(".maps");
 
 SEC("cgroup/skb")
 int bpf_nextcnt(struct __sk_buff *skb)
 {
-	struct percpu_net_cnt *percpu_cnt;
+	union percpu_net_cnt *percpu_cnt;
 	char fmt[] = "%d %llu %llu\n";
-	struct net_cnt *cnt;
+	union net_cnt *cnt;
 	__u64 ts, dt;
 	int ret;
 
diff --git a/tools/testing/selftests/bpf/test_netcnt.c b/tools/testing/selftests/bpf/test_netcnt.c
index a7b9a69f4fd5..4990a99e7381 100644
--- a/tools/testing/selftests/bpf/test_netcnt.c
+++ b/tools/testing/selftests/bpf/test_netcnt.c
@@ -33,14 +33,14 @@ static int bpf_find_map(const char *test, struct bpf_object *obj,
 
 int main(int argc, char **argv)
 {
-	struct percpu_net_cnt *percpu_netcnt;
+	union percpu_net_cnt *percpu_netcnt;
 	struct bpf_cgroup_storage_key key;
 	int map_fd, percpu_map_fd;
 	int error = EXIT_FAILURE;
-	struct net_cnt netcnt;
 	struct bpf_object *obj;
 	int prog_fd, cgroup_fd;
 	unsigned long packets;
+	union net_cnt netcnt;
 	unsigned long bytes;
 	int cpu, nproc;
 	__u32 prog_cnt;