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

kernel/bpf/local_storage.c

@@ -1,6 +1,7 @@
 //SPDX-License-Identifier: GPL-2.0
 #include <linux/bpf-cgroup.h>
 #include <linux/bpf.h>
+#include <linux/bpf_local_storage.h>
 #include <linux/btf.h>
 #include <linux/bug.h>
 #include <linux/filter.h>
@@ -283,9 +284,17 @@ enoent:
 
 static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr)
 {
+	__u32 max_value_size = BPF_LOCAL_STORAGE_MAX_VALUE_SIZE;
 	int numa_node = bpf_map_attr_numa_node(attr);
 	struct bpf_cgroup_storage_map *map;
 
+	/* percpu is bound by PCPU_MIN_UNIT_SIZE, non-percu
+	 * is the same as other local storages.
+	 */
+	if (attr->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE)
+		max_value_size = min_t(__u32, max_value_size,
+				       PCPU_MIN_UNIT_SIZE);
+
 	if (attr->key_size != sizeof(struct bpf_cgroup_storage_key) &&
 	    attr->key_size != sizeof(__u64))
 		return ERR_PTR(-EINVAL);
@@ -293,7 +302,7 @@ static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr)
 	if (attr->value_size == 0)
 		return ERR_PTR(-EINVAL);
 
-	if (attr->value_size > PAGE_SIZE)
+	if (attr->value_size > max_value_size)
 		return ERR_PTR(-E2BIG);
 
 	if (attr->map_flags & ~LOCAL_STORAGE_CREATE_FLAG_MASK ||

tools/testing/selftests/bpf/netcnt_common.h

@@ -6,7 +6,22 @@
 
 #define MAX_PERCPU_PACKETS 32
 
-struct percpu_net_cnt {
+/* 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
+
+/* Try to estimate kernel's BPF_LOCAL_STORAGE_MAX_VALUE_SIZE: */
+#define BPF_LOCAL_STORAGE_MAX_VALUE_SIZE	(0xFFFF - \
+						 SIZEOF_BPF_LOCAL_STORAGE_ELEM)
+
+#define PCPU_MIN_UNIT_SIZE			32768
+
+union percpu_net_cnt {
+	struct {
 		__u64 packets;
 		__u64 bytes;
 
@@ -14,11 +29,16 @@ struct percpu_net_cnt {
 
 		__u64 prev_packets;
 		__u64 prev_bytes;
+	};
+	__u8 data[PCPU_MIN_UNIT_SIZE];
 };
 
-struct net_cnt {
+union net_cnt {
+	struct {
 		__u64 packets;
 		__u64 bytes;
+	};
+	__u8 data[BPF_LOCAL_STORAGE_MAX_VALUE_SIZE];
 };
 
 #endif

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;
 

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;