[bpf-next,v9,04/12] bpf: add struct_ops_tab to btf.

Commit Message

Kui-Feng Lee Nov. 1, 2023, 8:45 p.m. UTC

From: Kui-Feng Lee <[e-mail]>

Maintain a registry of registered struct_ops types in the per-btf (module)
struct_ops_tab. This registry allows for easy lookup of struct_ops types
that are registered by a specific module.

It is a preparation work for supporting kernel module struct_ops in a
latter patch. Each struct_ops will be registered under its own kernel
module btf and will be stored in the newly added btf->struct_ops_tab. The
bpf verifier and bpf syscall (e.g. prog and map cmd) can find the
struct_ops and its btf type/size/id... information from
btf->struct_ops_tab.

Signed-off-by: Kui-Feng Lee <[e-mail]>
---
 include/linux/btf.h         |  5 +++
 kernel/bpf/bpf_struct_ops.c | 24 +++++++-----
 kernel/bpf/btf.c            | 74 +++++++++++++++++++++++++++++++++++++
 3 files changed, 94 insertions(+), 9 deletions(-)

Patch

diff --git a/include/linux/btf.h b/include/linux/btf.h
index c2231c64d60b..e613b6b45dc4 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -572,4 +572,9 @@  static inline bool btf_type_is_struct_ptr(struct btf *btf, const struct btf_type
 	return btf_type_is_struct(t);
 }
 
+struct bpf_struct_ops_desc;
+
+const struct bpf_struct_ops_desc *
+btf_get_struct_ops(struct btf *btf, u32 *ret_cnt);
+
 #endif
diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index d804801c7864..a0291877a792 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -46,6 +46,8 @@  struct bpf_struct_ops_map {
 	 * "links[]".
 	 */
 	void *image;
+	/* The owner moduler's btf. */
+	struct btf *btf;
 	/* uvalue->data stores the kernel struct
 	 * (e.g. tcp_congestion_ops) that is more useful
 	 * to userspace than the kvalue.  For example,
@@ -314,7 +316,7 @@  static void bpf_struct_ops_map_put_progs(struct bpf_struct_ops_map *st_map)
 	}
 }
 
-static int check_zero_holes(const struct btf_type *t, void *data)
+static int check_zero_holes(const struct btf *btf, const struct btf_type *t, void *data)
 {
 	const struct btf_member *member;
 	u32 i, moff, msize, prev_mend = 0;
@@ -326,8 +328,8 @@  static int check_zero_holes(const struct btf_type *t, void *data)
 		    memchr_inv(data + prev_mend, 0, moff - prev_mend))
 			return -EINVAL;
 
-		mtype = btf_type_by_id(btf_vmlinux, member->type);
-		mtype = btf_resolve_size(btf_vmlinux, mtype, &msize);
+		mtype = btf_type_by_id(btf, member->type);
+		mtype = btf_resolve_size(btf, mtype, &msize);
 		if (IS_ERR(mtype))
 			return PTR_ERR(mtype);
 		prev_mend = moff + msize;
@@ -395,12 +397,12 @@  static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 	if (*(u32 *)key != 0)
 		return -E2BIG;
 
-	err = check_zero_holes(st_ops_desc->value_type, value);
+	err = check_zero_holes(st_map->btf, st_ops_desc->value_type, value);
 	if (err)
 		return err;
 
 	uvalue = value;
-	err = check_zero_holes(t, uvalue->data);
+	err = check_zero_holes(st_map->btf, t, uvalue->data);
 	if (err)
 		return err;
 
@@ -436,7 +438,7 @@  static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 		u32 moff;
 
 		moff = __btf_member_bit_offset(t, member) / 8;
-		ptype = btf_type_resolve_ptr(btf_vmlinux, member->type, NULL);
+		ptype = btf_type_resolve_ptr(st_map->btf, member->type, NULL);
 		if (ptype == module_type) {
 			if (*(void **)(udata + moff))
 				goto reset_unlock;
@@ -461,8 +463,8 @@  static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 		if (!ptype || !btf_type_is_func_proto(ptype)) {
 			u32 msize;
 
-			mtype = btf_type_by_id(btf_vmlinux, member->type);
-			mtype = btf_resolve_size(btf_vmlinux, mtype, &msize);
+			mtype = btf_type_by_id(st_map->btf, member->type);
+			mtype = btf_resolve_size(st_map->btf, mtype, &msize);
 			if (IS_ERR(mtype)) {
 				err = PTR_ERR(mtype);
 				goto reset_unlock;
@@ -601,6 +603,7 @@  static long bpf_struct_ops_map_delete_elem(struct bpf_map *map, void *key)
 static void bpf_struct_ops_map_seq_show_elem(struct bpf_map *map, void *key,
 					     struct seq_file *m)
 {
+	struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map;
 	void *value;
 	int err;
 
@@ -610,7 +613,8 @@  static void bpf_struct_ops_map_seq_show_elem(struct bpf_map *map, void *key,
 
 	err = bpf_struct_ops_map_sys_lookup_elem(map, key, value);
 	if (!err) {
-		btf_type_seq_show(btf_vmlinux, map->btf_vmlinux_value_type_id,
+		btf_type_seq_show(st_map->btf,
+				  map->btf_vmlinux_value_type_id,
 				  value, m);
 		seq_puts(m, "\n");
 	}
@@ -720,6 +724,8 @@  static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
 		return ERR_PTR(-ENOMEM);
 	}
 
+	st_map->btf = btf_vmlinux;
+
 	mutex_init(&st_map->lock);
 	set_vm_flush_reset_perms(st_map->image);
 	bpf_map_init_from_attr(map, attr);
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 15d71d2986d3..2fd6fa0ea1f4 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -241,6 +241,12 @@  struct btf_id_dtor_kfunc_tab {
 	struct btf_id_dtor_kfunc dtors[];
 };
 
+struct btf_struct_ops_tab {
+	u32 cnt;
+	u32 capacity;
+	struct bpf_struct_ops_desc ops[];
+};
+
 struct btf {
 	void *data;
 	struct btf_type **types;
@@ -258,6 +264,7 @@  struct btf {
 	struct btf_kfunc_set_tab *kfunc_set_tab;
 	struct btf_id_dtor_kfunc_tab *dtor_kfunc_tab;
 	struct btf_struct_metas *struct_meta_tab;
+	struct btf_struct_ops_tab *struct_ops_tab;
 
 	/* split BTF support */
 	struct btf *base_btf;
@@ -1688,11 +1695,20 @@  static void btf_free_struct_meta_tab(struct btf *btf)
 	btf->struct_meta_tab = NULL;
 }
 
+static void btf_free_struct_ops_tab(struct btf *btf)
+{
+	struct btf_struct_ops_tab *tab = btf->struct_ops_tab;
+
+	kfree(tab);
+	btf->struct_ops_tab = NULL;
+}
+
 static void btf_free(struct btf *btf)
 {
 	btf_free_struct_meta_tab(btf);
 	btf_free_dtor_kfunc_tab(btf);
 	btf_free_kfunc_set_tab(btf);
+	btf_free_struct_ops_tab(btf);
 	kvfree(btf->types);
 	kvfree(btf->resolved_sizes);
 	kvfree(btf->resolved_ids);
@@ -8602,3 +8618,61 @@  bool btf_type_ids_nocast_alias(struct bpf_verifier_log *log,
 
 	return !strncmp(reg_name, arg_name, cmp_len);
 }
+
+static int
+btf_add_struct_ops(struct btf *btf, struct bpf_struct_ops *st_ops)
+{
+	struct btf_struct_ops_tab *tab, *new_tab;
+	int i;
+
+	if (!btf)
+		return -ENOENT;
+
+	/* Assume this function is called for a module when the module is
+	 * loading.
+	 */
+
+	tab = btf->struct_ops_tab;
+	if (!tab) {
+		tab = kzalloc(offsetof(struct btf_struct_ops_tab, ops[4]),
+			      GFP_KERNEL);
+		if (!tab)
+			return -ENOMEM;
+		tab->capacity = 4;
+		btf->struct_ops_tab = tab;
+	}
+
+	for (i = 0; i < tab->cnt; i++)
+		if (tab->ops[i].st_ops == st_ops)
+			return -EEXIST;
+
+	if (tab->cnt == tab->capacity) {
+		new_tab = krealloc(tab,
+				   offsetof(struct btf_struct_ops_tab,
+					    ops[tab->capacity * 2]),
+				   GFP_KERNEL);
+		if (!new_tab)
+			return -ENOMEM;
+		tab = new_tab;
+		tab->capacity *= 2;
+		btf->struct_ops_tab = tab;
+	}
+
+	tab->ops[btf->struct_ops_tab->cnt].st_ops = st_ops;
+
+	btf->struct_ops_tab->cnt++;
+
+	return 0;
+}
+
+const struct bpf_struct_ops_desc *btf_get_struct_ops(struct btf *btf, u32 *ret_cnt)
+{
+	if (!btf)
+		return NULL;
+	if (!btf->struct_ops_tab)
+		return NULL;
+
+	*ret_cnt = btf->struct_ops_tab->cnt;
+	return (const struct bpf_struct_ops_desc *)btf->struct_ops_tab->ops;
+}
+