bpf: Add basic bpf_rb_{root,node} support

This patch adds special BPF_RB_{ROOT,NODE} btf_field_types similar to
BPF_LIST_{HEAD,NODE}, adds the necessary plumbing to detect the new
types, and adds bpf_rb_root_free function for freeing bpf_rb_root in
map_values.

structs bpf_rb_root and bpf_rb_node are opaque types meant to
obscure structs rb_root_cached rb_node, respectively.

btf_struct_access will prevent BPF programs from touching these special
fields automatically now that they're recognized.

btf_check_and_fixup_fields now groups list_head and rb_root together as
"graph root" fields and {list,rb}_node as "graph node", and does same
ownership cycle checking as before. Note that this function does _not_
prevent ownership type mixups (e.g. rb_root owning list_node) - that's
handled by btf_parse_graph_root.

After this patch, a bpf program can have a struct bpf_rb_root in a
map_value, but not add anything to nor do anything useful with it.
Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com>
Link: https://lore.kernel.org/r/20230214004017.2534011-2-davemarchevsky@fb.comSigned-off-by: Alexei Starovoitov <ast@kernel.org>

include/linux/bpf.h

@@ -181,7 +181,10 @@ enum btf_field_type {
 	BPF_KPTR       = BPF_KPTR_UNREF | BPF_KPTR_REF,
 	BPF_LIST_HEAD  = (1 << 4),
 	BPF_LIST_NODE  = (1 << 5),
-	BPF_GRAPH_NODE_OR_ROOT = BPF_LIST_NODE | BPF_LIST_HEAD,
+	BPF_RB_ROOT    = (1 << 6),
+	BPF_RB_NODE    = (1 << 7),
+	BPF_GRAPH_NODE_OR_ROOT = BPF_LIST_NODE | BPF_LIST_HEAD |
+				 BPF_RB_NODE | BPF_RB_ROOT,
 };
 
 struct btf_field_kptr {
@@ -285,6 +288,10 @@ static inline const char *btf_field_type_name(enum btf_field_type type)
 		return "bpf_list_head";
 	case BPF_LIST_NODE:
 		return "bpf_list_node";
+	case BPF_RB_ROOT:
+		return "bpf_rb_root";
+	case BPF_RB_NODE:
+		return "bpf_rb_node";
 	default:
 		WARN_ON_ONCE(1);
 		return "unknown";
@@ -305,6 +312,10 @@ static inline u32 btf_field_type_size(enum btf_field_type type)
 		return sizeof(struct bpf_list_head);
 	case BPF_LIST_NODE:
 		return sizeof(struct bpf_list_node);
+	case BPF_RB_ROOT:
+		return sizeof(struct bpf_rb_root);
+	case BPF_RB_NODE:
+		return sizeof(struct bpf_rb_node);
 	default:
 		WARN_ON_ONCE(1);
 		return 0;
@@ -325,6 +336,10 @@ static inline u32 btf_field_type_align(enum btf_field_type type)
 		return __alignof__(struct bpf_list_head);
 	case BPF_LIST_NODE:
 		return __alignof__(struct bpf_list_node);
+	case BPF_RB_ROOT:
+		return __alignof__(struct bpf_rb_root);
+	case BPF_RB_NODE:
+		return __alignof__(struct bpf_rb_node);
 	default:
 		WARN_ON_ONCE(1);
 		return 0;
@@ -435,6 +450,9 @@ void copy_map_value_locked(struct bpf_map *map, void *dst, void *src,
 void bpf_timer_cancel_and_free(void *timer);
 void bpf_list_head_free(const struct btf_field *field, void *list_head,
 			struct bpf_spin_lock *spin_lock);
+void bpf_rb_root_free(const struct btf_field *field, void *rb_root,
+		      struct bpf_spin_lock *spin_lock);
+
 
 int bpf_obj_name_cpy(char *dst, const char *src, unsigned int size);
 

include/uapi/linux/bpf.h

@@ -6917,6 +6917,17 @@ struct bpf_list_node {
 	__u64 :64;
 } __attribute__((aligned(8)));
 
+struct bpf_rb_root {
+	__u64 :64;
+	__u64 :64;
+} __attribute__((aligned(8)));
+
+struct bpf_rb_node {
+	__u64 :64;
+	__u64 :64;
+	__u64 :64;
+} __attribute__((aligned(8)));
+
 struct bpf_sysctl {
 	__u32	write;		/* Sysctl is being read (= 0) or written (= 1).
 				 * Allows 1,2,4-byte read, but no write.

kernel/bpf/helpers.c

@@ -1772,6 +1772,46 @@ void bpf_list_head_free(const struct btf_field *field, void *list_head,
 	}
 }
 
+/* Like rbtree_postorder_for_each_entry_safe, but 'pos' and 'n' are
+ * 'rb_node *', so field name of rb_node within containing struct is not
+ * needed.
+ *
+ * Since bpf_rb_tree's node type has a corresponding struct btf_field with
+ * graph_root.node_offset, it's not necessary to know field name
+ * or type of node struct
+ */
+#define bpf_rbtree_postorder_for_each_entry_safe(pos, n, root) \
+	for (pos = rb_first_postorder(root); \
+	    pos && ({ n = rb_next_postorder(pos); 1; }); \
+	    pos = n)
+
+void bpf_rb_root_free(const struct btf_field *field, void *rb_root,
+		      struct bpf_spin_lock *spin_lock)
+{
+	struct rb_root_cached orig_root, *root = rb_root;
+	struct rb_node *pos, *n;
+	void *obj;
+
+	BUILD_BUG_ON(sizeof(struct rb_root_cached) > sizeof(struct bpf_rb_root));
+	BUILD_BUG_ON(__alignof__(struct rb_root_cached) > __alignof__(struct bpf_rb_root));
+
+	__bpf_spin_lock_irqsave(spin_lock);
+	orig_root = *root;
+	*root = RB_ROOT_CACHED;
+	__bpf_spin_unlock_irqrestore(spin_lock);
+
+	bpf_rbtree_postorder_for_each_entry_safe(pos, n, &orig_root.rb_root) {
+		obj = pos;
+		obj -= field->graph_root.node_offset;
+
+		bpf_obj_free_fields(field->graph_root.value_rec, obj);
+
+		migrate_disable();
+		bpf_mem_free(&bpf_global_ma, obj);
+		migrate_enable();
+	}
+}
+
 __diag_push();
 __diag_ignore_all("-Wmissing-prototypes",
 		  "Global functions as their definitions will be in vmlinux BTF");

kernel/bpf/syscall.c

@@ -537,9 +537,6 @@ void btf_record_free(struct btf_record *rec)
 		return;
 	for (i = 0; i < rec->cnt; i++) {
 		switch (rec->fields[i].type) {
-		case BPF_SPIN_LOCK:
-		case BPF_TIMER:
-			break;
 		case BPF_KPTR_UNREF:
 		case BPF_KPTR_REF:
 			if (rec->fields[i].kptr.module)
@@ -548,7 +545,11 @@ void btf_record_free(struct btf_record *rec)
 			break;
 		case BPF_LIST_HEAD:
 		case BPF_LIST_NODE:
-			/* Nothing to release for bpf_list_head */
+		case BPF_RB_ROOT:
+		case BPF_RB_NODE:
+		case BPF_SPIN_LOCK:
+		case BPF_TIMER:
+			/* Nothing to release */
 			break;
 		default:
 			WARN_ON_ONCE(1);
@@ -581,9 +582,6 @@ struct btf_record *btf_record_dup(const struct btf_record *rec)
 	new_rec->cnt = 0;
 	for (i = 0; i < rec->cnt; i++) {
 		switch (fields[i].type) {
-		case BPF_SPIN_LOCK:
-		case BPF_TIMER:
-			break;
 		case BPF_KPTR_UNREF:
 		case BPF_KPTR_REF:
 			btf_get(fields[i].kptr.btf);
@@ -594,7 +592,11 @@ struct btf_record *btf_record_dup(const struct btf_record *rec)
 			break;
 		case BPF_LIST_HEAD:
 		case BPF_LIST_NODE:
-			/* Nothing to acquire for bpf_list_head */
+		case BPF_RB_ROOT:
+		case BPF_RB_NODE:
+		case BPF_SPIN_LOCK:
+		case BPF_TIMER:
+			/* Nothing to acquire */
 			break;
 		default:
 			ret = -EFAULT;
@@ -674,7 +676,13 @@ void bpf_obj_free_fields(const struct btf_record *rec, void *obj)
 				continue;
 			bpf_list_head_free(field, field_ptr, obj + rec->spin_lock_off);
 			break;
+		case BPF_RB_ROOT:
+			if (WARN_ON_ONCE(rec->spin_lock_off < 0))
+				continue;
+			bpf_rb_root_free(field, field_ptr, obj + rec->spin_lock_off);
+			break;
 		case BPF_LIST_NODE:
+		case BPF_RB_NODE:
 			break;
 		default:
 			WARN_ON_ONCE(1);
@@ -1010,7 +1018,8 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf,
 		return -EINVAL;
 
 	map->record = btf_parse_fields(btf, value_type,
-				       BPF_SPIN_LOCK | BPF_TIMER | BPF_KPTR | BPF_LIST_HEAD,
+				       BPF_SPIN_LOCK | BPF_TIMER | BPF_KPTR | BPF_LIST_HEAD |
+				       BPF_RB_ROOT,
 				       map->value_size);
 	if (!IS_ERR_OR_NULL(map->record)) {
 		int i;
@@ -1058,6 +1067,7 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf,
 				}
 				break;
 			case BPF_LIST_HEAD:
+			case BPF_RB_ROOT:
 				if (map->map_type != BPF_MAP_TYPE_HASH &&
 				    map->map_type != BPF_MAP_TYPE_LRU_HASH &&
 				    map->map_type != BPF_MAP_TYPE_ARRAY) {

kernel/bpf/verifier.c

@@ -14703,9 +14703,10 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env,
 {
 	enum bpf_prog_type prog_type = resolve_prog_type(prog);
 
-	if (btf_record_has_field(map->record, BPF_LIST_HEAD)) {
+	if (btf_record_has_field(map->record, BPF_LIST_HEAD) ||
+	    btf_record_has_field(map->record, BPF_RB_ROOT)) {
 		if (is_tracing_prog_type(prog_type)) {
-			verbose(env, "tracing progs cannot use bpf_list_head yet\n");
+			verbose(env, "tracing progs cannot use bpf_{list_head,rb_root} yet\n");
 			return -EINVAL;
 		}
 	}

tools/include/uapi/linux/bpf.h

@@ -6917,6 +6917,17 @@ struct bpf_list_node {
 	__u64 :64;
 } __attribute__((aligned(8)));
 
+struct bpf_rb_root {
+	__u64 :64;
+	__u64 :64;
+} __attribute__((aligned(8)));
+
+struct bpf_rb_node {
+	__u64 :64;
+	__u64 :64;
+	__u64 :64;
+} __attribute__((aligned(8)));
+
 struct bpf_sysctl {
 	__u32	write;		/* Sysctl is being read (= 0) or written (= 1).
 				 * Allows 1,2,4-byte read, but no write.

tools/testing/selftests/bpf/prog_tests/linked_list.c

@@ -58,12 +58,12 @@ static struct {
 	TEST(inner_map, pop_front)
 	TEST(inner_map, pop_back)
 #undef TEST
-	{ "map_compat_kprobe", "tracing progs cannot use bpf_list_head yet" },
-	{ "map_compat_kretprobe", "tracing progs cannot use bpf_list_head yet" },
-	{ "map_compat_tp", "tracing progs cannot use bpf_list_head yet" },
-	{ "map_compat_perf", "tracing progs cannot use bpf_list_head yet" },
-	{ "map_compat_raw_tp", "tracing progs cannot use bpf_list_head yet" },
-	{ "map_compat_raw_tp_w", "tracing progs cannot use bpf_list_head yet" },
+	{ "map_compat_kprobe", "tracing progs cannot use bpf_{list_head,rb_root} yet" },
+	{ "map_compat_kretprobe", "tracing progs cannot use bpf_{list_head,rb_root} yet" },
+	{ "map_compat_tp", "tracing progs cannot use bpf_{list_head,rb_root} yet" },
+	{ "map_compat_perf", "tracing progs cannot use bpf_{list_head,rb_root} yet" },
+	{ "map_compat_raw_tp", "tracing progs cannot use bpf_{list_head,rb_root} yet" },
+	{ "map_compat_raw_tp_w", "tracing progs cannot use bpf_{list_head,rb_root} yet" },
 	{ "obj_type_id_oor", "local type ID argument must be in range [0, U32_MAX]" },
 	{ "obj_new_no_composite", "bpf_obj_new type ID argument must be of a struct" },
 	{ "obj_new_no_struct", "bpf_obj_new type ID argument must be of a struct" },