libbpf: Use .struct_ops.link section to indicate a struct_ops with a link.

Flags a struct_ops is to back a bpf_link by putting it to the
".struct_ops.link" section.  Once it is flagged, the created
struct_ops can be used to create a bpf_link or update a bpf_link that
has been backed by another struct_ops.

Signed-off-by: Kui-Feng Lee <kuifeng@meta.com>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20230323032405.3735486-8-kuifeng@meta.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 2b5ea25..f6a071d 100644 (file)
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -468,6 +468,7 @@ struct bpf_struct_ops {
 #define KCONFIG_SEC ".kconfig"
 #define KSYMS_SEC ".ksyms"
 #define STRUCT_OPS_SEC ".struct_ops"
+#define STRUCT_OPS_LINK_SEC ".struct_ops.link"
 
 enum libbpf_map_type {
        LIBBPF_MAP_UNSPEC,
@@ -597,6 +598,7 @@ struct elf_state {
        Elf64_Ehdr *ehdr;
        Elf_Data *symbols;
        Elf_Data *st_ops_data;
+       Elf_Data *st_ops_link_data;
        size_t shstrndx; /* section index for section name strings */
        size_t strtabidx;
        struct elf_sec_desc *secs;
@@ -606,6 +608,7 @@ struct elf_state {
        int text_shndx;
        int symbols_shndx;
        int st_ops_shndx;
+       int st_ops_link_shndx;
 };
 
 struct usdt_manager;
@@ -1119,7 +1122,8 @@ static int bpf_object__init_kern_struct_ops_maps(struct bpf_object *obj)
        return 0;
 }
 
-static int bpf_object__init_struct_ops_maps(struct bpf_object *obj)
+static int init_struct_ops_maps(struct bpf_object *obj, const char *sec_name,
+                               int shndx, Elf_Data *data, __u32 map_flags)
 {
        const struct btf_type *type, *datasec;
        const struct btf_var_secinfo *vsi;
@@ -1130,15 +1134,15 @@ static int bpf_object__init_struct_ops_maps(struct bpf_object *obj)
        struct bpf_map *map;
        __u32 i;
 
-       if (obj->efile.st_ops_shndx == -1)
+       if (shndx == -1)
                return 0;
 
        btf = obj->btf;
-       datasec_id = btf__find_by_name_kind(btf, STRUCT_OPS_SEC,
+       datasec_id = btf__find_by_name_kind(btf, sec_name,
                                            BTF_KIND_DATASEC);
        if (datasec_id < 0) {
                pr_warn("struct_ops init: DATASEC %s not found\n",
-                       STRUCT_OPS_SEC);
+                       sec_name);
                return -EINVAL;
        }
 
@@ -1151,7 +1155,7 @@ static int bpf_object__init_struct_ops_maps(struct bpf_object *obj)
                type_id = btf__resolve_type(obj->btf, vsi->type);
                if (type_id < 0) {
                        pr_warn("struct_ops init: Cannot resolve var type_id %u in DATASEC %s\n",
-                               vsi->type, STRUCT_OPS_SEC);
+                               vsi->type, sec_name);
                        return -EINVAL;
                }
 
@@ -1170,7 +1174,7 @@ static int bpf_object__init_struct_ops_maps(struct bpf_object *obj)
                if (IS_ERR(map))
                        return PTR_ERR(map);
 
-               map->sec_idx = obj->efile.st_ops_shndx;
+               map->sec_idx = shndx;
                map->sec_offset = vsi->offset;
                map->name = strdup(var_name);
                if (!map->name)
@@ -1180,6 +1184,7 @@ static int bpf_object__init_struct_ops_maps(struct bpf_object *obj)
                map->def.key_size = sizeof(int);
                map->def.value_size = type->size;
                map->def.max_entries = 1;
+               map->def.map_flags = map_flags;
 
                map->st_ops = calloc(1, sizeof(*map->st_ops));
                if (!map->st_ops)
@@ -1192,14 +1197,14 @@ static int bpf_object__init_struct_ops_maps(struct bpf_object *obj)
                if (!st_ops->data || !st_ops->progs || !st_ops->kern_func_off)
                        return -ENOMEM;
 
-               if (vsi->offset + type->size > obj->efile.st_ops_data->d_size) {
+               if (vsi->offset + type->size > data->d_size) {
                        pr_warn("struct_ops init: var %s is beyond the end of DATASEC %s\n",
-                               var_name, STRUCT_OPS_SEC);
+                               var_name, sec_name);
                        return -EINVAL;
                }
 
                memcpy(st_ops->data,
-                      obj->efile.st_ops_data->d_buf + vsi->offset,
+                      data->d_buf + vsi->offset,
                       type->size);
                st_ops->tname = tname;
                st_ops->type = type;
@@ -1212,6 +1217,19 @@ static int bpf_object__init_struct_ops_maps(struct bpf_object *obj)
        return 0;
 }
 
+static int bpf_object_init_struct_ops(struct bpf_object *obj)
+{
+       int err;
+
+       err = init_struct_ops_maps(obj, STRUCT_OPS_SEC, obj->efile.st_ops_shndx,
+                                  obj->efile.st_ops_data, 0);
+       err = err ?: init_struct_ops_maps(obj, STRUCT_OPS_LINK_SEC,
+                                         obj->efile.st_ops_link_shndx,
+                                         obj->efile.st_ops_link_data,
+                                         BPF_F_LINK);
+       return err;
+}
+
 static struct bpf_object *bpf_object__new(const char *path,
                                          const void *obj_buf,
                                          size_t obj_buf_sz,
@@ -1248,6 +1266,7 @@ static struct bpf_object *bpf_object__new(const char *path,
        obj->efile.obj_buf_sz = obj_buf_sz;
        obj->efile.btf_maps_shndx = -1;
        obj->efile.st_ops_shndx = -1;
+       obj->efile.st_ops_link_shndx = -1;
        obj->kconfig_map_idx = -1;
 
        obj->kern_version = get_kernel_version();
@@ -1265,6 +1284,7 @@ static void bpf_object__elf_finish(struct bpf_object *obj)
        obj->efile.elf = NULL;
        obj->efile.symbols = NULL;
        obj->efile.st_ops_data = NULL;
+       obj->efile.st_ops_link_data = NULL;
 
        zfree(&obj->efile.secs);
        obj->efile.sec_cnt = 0;
@@ -2619,7 +2639,7 @@ static int bpf_object__init_maps(struct bpf_object *obj,
        err = bpf_object__init_user_btf_maps(obj, strict, pin_root_path);
        err = err ?: bpf_object__init_global_data_maps(obj);
        err = err ?: bpf_object__init_kconfig_map(obj);
-       err = err ?: bpf_object__init_struct_ops_maps(obj);
+       err = err ?: bpf_object_init_struct_ops(obj);
 
        return err;
 }
@@ -2753,12 +2773,13 @@ static bool libbpf_needs_btf(const struct bpf_object *obj)
 {
        return obj->efile.btf_maps_shndx >= 0 ||
               obj->efile.st_ops_shndx >= 0 ||
+              obj->efile.st_ops_link_shndx >= 0 ||
               obj->nr_extern > 0;
 }
 
 static bool kernel_needs_btf(const struct bpf_object *obj)
 {
-       return obj->efile.st_ops_shndx >= 0;
+       return obj->efile.st_ops_shndx >= 0 || obj->efile.st_ops_link_shndx >= 0;
 }
 
 static int bpf_object__init_btf(struct bpf_object *obj,
@@ -3451,6 +3472,9 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
                        } else if (strcmp(name, STRUCT_OPS_SEC) == 0) {
                                obj->efile.st_ops_data = data;
                                obj->efile.st_ops_shndx = idx;
+                       } else if (strcmp(name, STRUCT_OPS_LINK_SEC) == 0) {
+                               obj->efile.st_ops_link_data = data;
+                               obj->efile.st_ops_link_shndx = idx;
                        } else {
                                pr_info("elf: skipping unrecognized data section(%d) %s\n",
                                        idx, name);
@@ -3465,6 +3489,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
                        /* Only do relo for section with exec instructions */
                        if (!section_have_execinstr(obj, targ_sec_idx) &&
                            strcmp(name, ".rel" STRUCT_OPS_SEC) &&
+                           strcmp(name, ".rel" STRUCT_OPS_LINK_SEC) &&
                            strcmp(name, ".rel" MAPS_ELF_SEC)) {
                                pr_info("elf: skipping relo section(%d) %s for section(%d) %s\n",
                                        idx, name, targ_sec_idx,
@@ -6611,7 +6636,7 @@ static int bpf_object__collect_relos(struct bpf_object *obj)
                        return -LIBBPF_ERRNO__INTERNAL;
                }
 
-               if (idx == obj->efile.st_ops_shndx)
+               if (idx == obj->efile.st_ops_shndx || idx == obj->efile.st_ops_link_shndx)
                        err = bpf_object__collect_st_ops_relos(obj, shdr, data);
                else if (idx == obj->efile.btf_maps_shndx)
                        err = bpf_object__collect_map_relos(obj, shdr, data);
@@ -8853,6 +8878,7 @@ const char *libbpf_bpf_prog_type_str(enum bpf_prog_type t)
 }
 
 static struct bpf_map *find_struct_ops_map_by_offset(struct bpf_object *obj,
+                                                    int sec_idx,
                                                     size_t offset)
 {
        struct bpf_map *map;
@@ -8862,7 +8888,8 @@ static struct bpf_map *find_struct_ops_map_by_offset(struct bpf_object *obj,
                map = &obj->maps[i];
                if (!bpf_map__is_struct_ops(map))
                        continue;
-               if (map->sec_offset <= offset &&
+               if (map->sec_idx == sec_idx &&
+                   map->sec_offset <= offset &&
                    offset - map->sec_offset < map->def.value_size)
                        return map;
        }
@@ -8904,7 +8931,7 @@ static int bpf_object__collect_st_ops_relos(struct bpf_object *obj,
                }
 
                name = elf_sym_str(obj, sym->st_name) ?: "<?>";
-               map = find_struct_ops_map_by_offset(obj, rel->r_offset);
+               map = find_struct_ops_map_by_offset(obj, shdr->sh_info, rel->r_offset);
                if (!map) {
                        pr_warn("struct_ops reloc: cannot find map at rel->r_offset %zu\n",
                                (size_t)rel->r_offset);
@@ -8971,8 +8998,9 @@ static int bpf_object__collect_st_ops_relos(struct bpf_object *obj,
                }
 
                /* struct_ops BPF prog can be re-used between multiple
-                * .struct_ops as long as it's the same struct_ops struct
-                * definition and the same function pointer field
+                * .struct_ops & .struct_ops.link as long as it's the
+                * same struct_ops struct definition and the same
+                * function pointer field
                 */
                if (prog->attach_btf_id != st_ops->type_id ||
                    prog->expected_attach_type != member_idx) {