bpf: Centralize btf_field-specific initialization logic

All btf_fields in an object are 0-initialized by memset in
bpf_obj_init. This might not be a valid initial state for some field
types, in which case kfuncs that use the type will properly initialize
their input if it's been 0-initialized. Some BPF graph collection types
and kfuncs do this: bpf_list_{head,node} and bpf_rb_node.

An earlier patch in this series added the bpf_refcount field, for which
the 0 state indicates that the refcounted object should be free'd.
bpf_obj_init treats this field specially, setting refcount to 1 instead
of relying on scattered "refcount is 0? Must have just been initialized,
let's set to 1" logic in kfuncs.

This patch extends this treatment to list and rbtree field types,
allowing most scattered initialization logic in kfuncs to be removed.

Note that bpf_{list_head,rb_root} may be inside a BPF map, in which case
they'll be 0-initialized without passing through the newly-added logic,
so scattered initialization logic must remain for these collection root
types.

Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com>
Link: https://lore.kernel.org/r/20230415201811.343116-9-davemarchevsky@fb.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index b065de2cfceae13655f9885701c9d56b8c389039..18b592fde896f567424703357a344541c7449d56 100644 (file)
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -355,6 +355,34 @@ static inline u32 btf_field_type_align(enum btf_field_type type)
        }
 }
 
+static inline void bpf_obj_init_field(const struct btf_field *field, void *addr)
+{
+       memset(addr, 0, field->size);
+
+       switch (field->type) {
+       case BPF_REFCOUNT:
+               refcount_set((refcount_t *)addr, 1);
+               break;
+       case BPF_RB_NODE:
+               RB_CLEAR_NODE((struct rb_node *)addr);
+               break;
+       case BPF_LIST_HEAD:
+       case BPF_LIST_NODE:
+               INIT_LIST_HEAD((struct list_head *)addr);
+               break;
+       case BPF_RB_ROOT:
+               /* RB_ROOT_CACHED 0-inits, no need to do anything after memset */
+       case BPF_SPIN_LOCK:
+       case BPF_TIMER:
+       case BPF_KPTR_UNREF:
+       case BPF_KPTR_REF:
+               break;
+       default:
+               WARN_ON_ONCE(1);
+               return;
+       }
+}
+
 static inline bool btf_record_has_field(const struct btf_record *rec, enum btf_field_type type)
 {
        if (IS_ERR_OR_NULL(rec))
@@ -369,10 +397,7 @@ static inline void bpf_obj_init(const struct btf_record *rec, void *obj)
        if (IS_ERR_OR_NULL(rec))
                return;
        for (i = 0; i < rec->cnt; i++)
-               memset(obj + rec->fields[i].offset, 0, rec->fields[i].size);
-
-       if (rec->refcount_off >= 0)
-               refcount_set((refcount_t *)(obj + rec->refcount_off), 1);
+               bpf_obj_init_field(&rec->fields[i], obj + rec->fields[i].offset);
 }
 
 /* 'dst' must be a temporary buffer and should not point to memory that is being

diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 1835df33328719958ce3b36560c8df391e3b5d0a..00e5fb0682acc02c03f17e6434449b846ec53bd3 100644 (file)
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -1936,10 +1936,11 @@ static int __bpf_list_add(struct bpf_list_node *node, struct bpf_list_head *head
 {
        struct list_head *n = (void *)node, *h = (void *)head;
 
+       /* If list_head was 0-initialized by map, bpf_obj_init_field wasn't
+        * called on its fields, so init here
+        */
        if (unlikely(!h->next))
                INIT_LIST_HEAD(h);
-       if (unlikely(!n->next))
-               INIT_LIST_HEAD(n);
        if (!list_empty(n)) {
                /* Only called from BPF prog, no need to migrate_disable */
                __bpf_obj_drop_impl(n - off, rec);
@@ -1975,6 +1976,9 @@ static struct bpf_list_node *__bpf_list_del(struct bpf_list_head *head, bool tai
 {
        struct list_head *n, *h = (void *)head;
 
+       /* If list_head was 0-initialized by map, bpf_obj_init_field wasn't
+        * called on its fields, so init here
+        */
        if (unlikely(!h->next))
                INIT_LIST_HEAD(h);
        if (list_empty(h))
@@ -2000,9 +2004,6 @@ __bpf_kfunc struct bpf_rb_node *bpf_rbtree_remove(struct bpf_rb_root *root,
        struct rb_root_cached *r = (struct rb_root_cached *)root;
        struct rb_node *n = (struct rb_node *)node;
 
-       if (!n->__rb_parent_color)
-               RB_CLEAR_NODE(n);
-
        if (RB_EMPTY_NODE(n))
                return NULL;
 
@@ -2022,9 +2023,6 @@ static int __bpf_rbtree_add(struct bpf_rb_root *root, struct bpf_rb_node *node,
        bpf_callback_t cb = (bpf_callback_t)less;
        bool leftmost = true;
 
-       if (!n->__rb_parent_color)
-               RB_CLEAR_NODE(n);
-
        if (!RB_EMPTY_NODE(n)) {
                /* Only called from BPF prog, no need to migrate_disable */
                __bpf_obj_drop_impl(n - off, rec);