bpf: Support bpf_list_head in map values

Add the support on the map side to parse, recognize, verify, and build
metadata table for a new special field of the type struct bpf_list_head.
To parameterize the bpf_list_head for a certain value type and the
list_node member it will accept in that value type, we use BTF
declaration tags.

The definition of bpf_list_head in a map value will be done as follows:

struct foo {
	struct bpf_list_node node;
	int data;
};

struct map_value {
	struct bpf_list_head head __contains(foo, node);
};

Then, the bpf_list_head only allows adding to the list 'head' using the
bpf_list_node 'node' for the type struct foo.

The 'contains' annotation is a BTF declaration tag composed of four
parts, "contains:name:node" where the name is then used to look up the
type in the map BTF, with its kind hardcoded to BTF_KIND_STRUCT during
the lookup. The node defines name of the member in this type that has
the type struct bpf_list_node, which is actually used for linking into
the linked list. For now, 'kind' part is hardcoded as struct.

This allows building intrusive linked lists in BPF, using container_of
to obtain pointer to entry, while being completely type safe from the
perspective of the verifier. The verifier knows exactly the type of the
nodes, and knows that list helpers return that type at some fixed offset
where the bpf_list_node member used for this list exists. The verifier
also uses this information to disallow adding types that are not
accepted by a certain list.

For now, no elements can be added to such lists. Support for that is
coming in future patches, hence draining and freeing items is done with
a TODO that will be resolved in a future patch.

Note that the bpf_list_head_free function moves the list out to a local
variable under the lock and releases it, doing the actual draining of
the list items outside the lock. While this helps with not holding the
lock for too long pessimizing other concurrent list operations, it is
also necessary for deadlock prevention: unless every function called in
the critical section would be notrace, a fentry/fexit program could
attach and call bpf_map_update_elem again on the map, leading to the
same lock being acquired if the key matches and lead to a deadlock.
While this requires some special effort on part of the BPF programmer to
trigger and is highly unlikely to occur in practice, it is always better
if we can avoid such a condition.

While notrace would prevent this, doing the draining outside the lock
has advantages of its own, hence it is used to also fix the deadlock
related problem.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20221114191547.1694267-5-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

2 files changed, 27 insertions, 0 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index f08eb2d27de0..05f98e9e5c48 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -175,6 +175,7 @@ enum btf_field_type {
 	BPF_KPTR_UNREF = (1 << 2),
 	BPF_KPTR_REF   = (1 << 3),
 	BPF_KPTR       = BPF_KPTR_UNREF | BPF_KPTR_REF,
+	BPF_LIST_HEAD  = (1 << 4),
 };
 
 struct btf_field_kptr {
@@ -184,11 +185,18 @@ struct btf_field_kptr {
 	u32 btf_id;
 };
 
+struct btf_field_list_head {
+	struct btf *btf;
+	u32 value_btf_id;
+	u32 node_offset;
+};
+
 struct btf_field {
 	u32 offset;
 	enum btf_field_type type;
 	union {
 		struct btf_field_kptr kptr;
+		struct btf_field_list_head list_head;
 	};
 };
 
@@ -266,6 +274,8 @@ static inline const char *btf_field_type_name(enum btf_field_type type)
 	case BPF_KPTR_UNREF:
 	case BPF_KPTR_REF:
 		return "kptr";
+	case BPF_LIST_HEAD:
+		return "bpf_list_head";
 	default:
 		WARN_ON_ONCE(1);
 		return "unknown";
@@ -282,6 +292,8 @@ static inline u32 btf_field_type_size(enum btf_field_type type)
 	case BPF_KPTR_UNREF:
 	case BPF_KPTR_REF:
 		return sizeof(u64);
+	case BPF_LIST_HEAD:
+		return sizeof(struct bpf_list_head);
 	default:
 		WARN_ON_ONCE(1);
 		return 0;
@@ -298,6 +310,8 @@ static inline u32 btf_field_type_align(enum btf_field_type type)
 	case BPF_KPTR_UNREF:
 	case BPF_KPTR_REF:
 		return __alignof__(u64);
+	case BPF_LIST_HEAD:
+		return __alignof__(struct bpf_list_head);
 	default:
 		WARN_ON_ONCE(1);
 		return 0;
@@ -403,6 +417,9 @@ static inline void zero_map_value(struct bpf_map *map, void *dst)
 void copy_map_value_locked(struct bpf_map *map, void *dst, void *src,
 			   bool lock_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);
+
 int bpf_obj_name_cpy(char *dst, const char *src, unsigned int size);
 
 struct bpf_offload_dev;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index fb4c911d2a03..6580448e9f77 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -6888,6 +6888,16 @@ struct bpf_dynptr {
 	__u64 :64;
 } __attribute__((aligned(8)));
 
+struct bpf_list_head {
+	__u64 :64;
+	__u64 :64;
+} __attribute__((aligned(8)));
+
+struct bpf_list_node {
+	__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.