Merge branch 'bpf-libbpf-int-btf-map'

Andrii Nakryiko says:

====================
This patch set implements an update to how BTF-defined maps are specified. The
change is in how integer attributes, e.g., type, max_entries, map_flags, are
specified: now they are captured as part of map definition struct's BTF type
information (using array dimension), eliminating the need for compile-time
data initialization and keeping all the metadata in one place.

All existing selftests that were using BTF-defined maps are updated, along
with some other selftests, that were switched to new syntax.

v4->v5:
- revert sample_map_ret0.c, which is loaded with iproute2 (kernel test robot);
v3->v4:
- add acks;
- fix int -> uint type in commit message;
v2->v3:
- rename __int into __uint (Yonghong);
v1->v2:
- split bpf_helpers.h change from libbpf change (Song).
====================

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

tools/lib/bpf/libbpf.c

@@ -1029,40 +1029,40 @@ static const struct btf_type *skip_mods_and_typedefs(const struct btf *btf,
 	}
 }
 
-static bool get_map_field_int(const char *map_name,
-			      const struct btf *btf,
+/*
+ * Fetch integer attribute of BTF map definition. Such attributes are
+ * represented using a pointer to an array, in which dimensionality of array
+ * encodes specified integer value. E.g., int (*type)[BPF_MAP_TYPE_ARRAY];
+ * encodes `type => BPF_MAP_TYPE_ARRAY` key/value pair completely using BTF
+ * type definition, while using only sizeof(void *) space in ELF data section.
+ */
+static bool get_map_field_int(const char *map_name, const struct btf *btf,
 			      const struct btf_type *def,
-			      const struct btf_member *m,
-			      const void *data, __u32 *res) {
+			      const struct btf_member *m, __u32 *res) {
 	const struct btf_type *t = skip_mods_and_typedefs(btf, m->type);
 	const char *name = btf__name_by_offset(btf, m->name_off);
-	__u32 int_info = *(const __u32 *)(const void *)(t + 1);
+	const struct btf_array *arr_info;
+	const struct btf_type *arr_t;
 
-	if (BTF_INFO_KIND(t->info) != BTF_KIND_INT) {
-		pr_warning("map '%s': attr '%s': expected INT, got %u.\n",
+	if (BTF_INFO_KIND(t->info) != BTF_KIND_PTR) {
+		pr_warning("map '%s': attr '%s': expected PTR, got %u.\n",
 			   map_name, name, BTF_INFO_KIND(t->info));
 		return false;
 	}
-	if (t->size != 4 || BTF_INT_BITS(int_info) != 32 ||
-	    BTF_INT_OFFSET(int_info)) {
-		pr_warning("map '%s': attr '%s': expected 32-bit non-bitfield integer, "
-			   "got %u-byte (%d-bit) one with bit offset %d.\n",
-			   map_name, name, t->size, BTF_INT_BITS(int_info),
-			   BTF_INT_OFFSET(int_info));
-		return false;
-	}
-	if (BTF_INFO_KFLAG(def->info) && BTF_MEMBER_BITFIELD_SIZE(m->offset)) {
-		pr_warning("map '%s': attr '%s': bitfield is not supported.\n",
-			   map_name, name);
+
+	arr_t = btf__type_by_id(btf, t->type);
+	if (!arr_t) {
+		pr_warning("map '%s': attr '%s': type [%u] not found.\n",
+			   map_name, name, t->type);
 		return false;
 	}
-	if (m->offset % 32) {
-		pr_warning("map '%s': attr '%s': unaligned fields are not supported.\n",
-			   map_name, name);
+	if (BTF_INFO_KIND(arr_t->info) != BTF_KIND_ARRAY) {
+		pr_warning("map '%s': attr '%s': expected ARRAY, got %u.\n",
+			   map_name, name, BTF_INFO_KIND(arr_t->info));
 		return false;
 	}
-
-	*res = *(const __u32 *)(data + m->offset / 8);
+	arr_info = (const void *)(arr_t + 1);
+	*res = arr_info->nelems;
 	return true;
 }
 
@@ -1075,7 +1075,6 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
 	const struct btf_var_secinfo *vi;
 	const struct btf_var *var_extra;
 	const struct btf_member *m;
-	const void *def_data;
 	const char *map_name;
 	struct bpf_map *map;
 	int vlen, i;
@@ -1132,7 +1131,6 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
 	pr_debug("map '%s': at sec_idx %d, offset %zu.\n",
 		 map_name, map->sec_idx, map->sec_offset);
 
-	def_data = data->d_buf + vi->offset;
 	vlen = BTF_INFO_VLEN(def->info);
 	m = (const void *)(def + 1);
 	for (i = 0; i < vlen; i++, m++) {
@@ -1145,27 +1143,27 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
 		}
 		if (strcmp(name, "type") == 0) {
 			if (!get_map_field_int(map_name, obj->btf, def, m,
-					       def_data, &map->def.type))
+					       &map->def.type))
 				return -EINVAL;
 			pr_debug("map '%s': found type = %u.\n",
 				 map_name, map->def.type);
 		} else if (strcmp(name, "max_entries") == 0) {
 			if (!get_map_field_int(map_name, obj->btf, def, m,
-					       def_data, &map->def.max_entries))
+					       &map->def.max_entries))
 				return -EINVAL;
 			pr_debug("map '%s': found max_entries = %u.\n",
 				 map_name, map->def.max_entries);
 		} else if (strcmp(name, "map_flags") == 0) {
 			if (!get_map_field_int(map_name, obj->btf, def, m,
-					       def_data, &map->def.map_flags))
+					       &map->def.map_flags))
 				return -EINVAL;
 			pr_debug("map '%s': found map_flags = %u.\n",
 				 map_name, map->def.map_flags);
 		} else if (strcmp(name, "key_size") == 0) {
 			__u32 sz;
 
 			if (!get_map_field_int(map_name, obj->btf, def, m,
-					       def_data, &sz))
+					       &sz))
 				return -EINVAL;
 			pr_debug("map '%s': found key_size = %u.\n",
 				 map_name, sz);
@@ -1208,7 +1206,7 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
 			__u32 sz;
 
 			if (!get_map_field_int(map_name, obj->btf, def, m,
-					       def_data, &sz))
+					       &sz))
 				return -EINVAL;
 			pr_debug("map '%s': found value_size = %u.\n",
 				 map_name, sz);

tools/testing/selftests/bpf/bpf_helpers.h

@@ -8,6 +8,9 @@
  */
 #define SEC(NAME) __attribute__((section(NAME), used))
 
+#define __uint(name, val) int (*name)[val]
+#define __type(name, val) val *name
+
 /* helper macro to print out debug messages */
 #define bpf_printk(fmt, ...)				\
 ({							\

tools/testing/selftests/bpf/progs/bpf_flow.c

@@ -58,26 +58,18 @@ struct frag_hdr {
 };
 
 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 key_size;
-	__u32 value_size;
-} jmp_table SEC(".maps") = {
-	.type = BPF_MAP_TYPE_PROG_ARRAY,
-	.max_entries = 8,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(__u32),
-};
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 8);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u32));
+} jmp_table SEC(".maps");
 
 struct {
-	__u32 type;
-	__u32 max_entries;
-	__u32 *key;
-	struct bpf_flow_keys *value;
-} last_dissection SEC(".maps") = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.max_entries = 1,
-};
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, struct bpf_flow_keys);
+} last_dissection SEC(".maps");
 
 static __always_inline int export_flow_keys(struct bpf_flow_keys *keys,
 					    int ret)

tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c

@@ -4,19 +4,19 @@
 #include <linux/bpf.h>
 #include "bpf_helpers.h"
 
-struct bpf_map_def SEC("maps") cg_ids = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(__u64),
-	.max_entries = 1,
-};
-
-struct bpf_map_def SEC("maps") pidmap = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(__u32),
-	.max_entries = 1,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, __u64);
+} cg_ids SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, __u32);
+} pidmap SEC(".maps");
 
 SEC("tracepoint/syscalls/sys_enter_nanosleep")
 int trace(void *ctx)

tools/testing/selftests/bpf/progs/netcnt_prog.c

@@ -11,20 +11,16 @@
 #define NS_PER_SEC	1000000000
 
 struct {
-	__u32 type;
-	struct bpf_cgroup_storage_key *key;
-	struct percpu_net_cnt *value;
-} percpu_netcnt SEC(".maps") = {
-	.type = BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
-};
+	__uint(type, BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE);
+	__type(key, struct bpf_cgroup_storage_key);
+	__type(value, struct percpu_net_cnt);
+} percpu_netcnt SEC(".maps");
 
 struct {
-	__u32 type;
-	struct bpf_cgroup_storage_key *key;
-	struct net_cnt *value;
-} netcnt SEC(".maps") = {
-	.type = BPF_MAP_TYPE_CGROUP_STORAGE,
-};
+	__uint(type, BPF_MAP_TYPE_CGROUP_STORAGE);
+	__type(key, struct bpf_cgroup_storage_key);
+	__type(value, struct net_cnt);
+} netcnt SEC(".maps");
 
 SEC("cgroup/skb")
 int bpf_nextcnt(struct __sk_buff *skb)

tools/testing/selftests/bpf/progs/pyperf.h

@@ -58,14 +58,6 @@ typedef struct {
 } Event;
 
 
-struct bpf_elf_map {
-	__u32 type;
-	__u32 size_key;
-	__u32 size_value;
-	__u32 max_elem;
-	__u32 flags;
-};
-
 typedef int pid_t;
 
 typedef struct {
@@ -118,47 +110,47 @@ static __always_inline bool get_frame_data(void *frame_ptr, PidData *pidData,
 	return true;
 }
 
-struct bpf_elf_map SEC("maps") pidmap = {
-	.type = BPF_MAP_TYPE_HASH,
-	.size_key = sizeof(int),
-	.size_value = sizeof(PidData),
-	.max_elem = 1,
-};
-
-struct bpf_elf_map SEC("maps") eventmap = {
-	.type = BPF_MAP_TYPE_HASH,
-	.size_key = sizeof(int),
-	.size_value = sizeof(Event),
-	.max_elem = 1,
-};
-
-struct bpf_elf_map SEC("maps") symbolmap = {
-	.type = BPF_MAP_TYPE_HASH,
-	.size_key = sizeof(Symbol),
-	.size_value = sizeof(int),
-	.max_elem = 1,
-};
-
-struct bpf_elf_map SEC("maps") statsmap = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.size_key = sizeof(Stats),
-	.size_value = sizeof(int),
-	.max_elem = 1,
-};
-
-struct bpf_elf_map SEC("maps") perfmap = {
-	.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
-	.size_key = sizeof(int),
-	.size_value = sizeof(int),
-	.max_elem = 32,
-};
-
-struct bpf_elf_map SEC("maps") stackmap = {
-	.type = BPF_MAP_TYPE_STACK_TRACE,
-	.size_key = sizeof(int),
-	.size_value = sizeof(long long) * 127,
-	.max_elem = 1000,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, PidData);
+} pidmap SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, Event);
+} eventmap SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, Symbol);
+	__type(value, int);
+} symbolmap SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, Stats);
+} statsmap SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
+	__uint(max_entries, 32);
+	__uint(key_size, sizeof(int));
+	__uint(value_size, sizeof(int));
+} perfmap SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_STACK_TRACE);
+	__uint(max_entries, 1000);
+	__uint(key_size, sizeof(int));
+	__uint(value_size, sizeof(long long) * 127);
+} stackmap SEC(".maps");
 
 static __always_inline int __on_event(struct pt_regs *ctx)
 {

tools/testing/selftests/bpf/progs/socket_cookie_prog.c

@@ -13,14 +13,11 @@ struct socket_cookie {
 };
 
 struct {
-	__u32 type;
-	__u32 map_flags;
-	int *key;
-	struct socket_cookie *value;
-} socket_cookies SEC(".maps") = {
-	.type = BPF_MAP_TYPE_SK_STORAGE,
-	.map_flags = BPF_F_NO_PREALLOC,
-};
+	__uint(type, BPF_MAP_TYPE_SK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct socket_cookie);
+} socket_cookies SEC(".maps");
 
 SEC("cgroup/connect6")
 int set_cookie(struct bpf_sock_addr *ctx)