bpf: Implement bpf iterator for map elements

The bpf iterator for map elements are implemented.
The bpf program will receive four parameters:
  bpf_iter_meta *meta: the meta data
  bpf_map *map:        the bpf_map whose elements are traversed
  void *key:           the key of one element
  void *value:         the value of the same element

Here, meta and map pointers are always valid, and
key has register type PTR_TO_RDONLY_BUF_OR_NULL and
value has register type PTR_TO_RDWR_BUF_OR_NULL.
The kernel will track the access range of key and value
during verification time. Later, these values will be compared
against the values in the actual map to ensure all accesses
are within range.

A new field iter_seq_info is added to bpf_map_ops which
is used to add map type specific information, i.e., seq_ops,
init/fini seq_file func and seq_file private data size.
Subsequent patches will have actual implementation
for bpf_map_ops->iter_seq_info.

In user space, BPF_ITER_LINK_MAP_FD needs to be
specified in prog attr->link_create.flags, which indicates
that attr->link_create.target_fd is a map_fd.
The reason for such an explicit flag is for possible
future cases where one bpf iterator may allow more than
one possible customization, e.g., pid and cgroup id for
task_file.

Current kernel internal implementation only allows
the target to register at most one required bpf_iter_link_info.
To support the above case, optional bpf_iter_link_info's
are needed, the target can be extended to register such link
infos, and user provided link_info needs to match one of
target supported ones.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200723184112.590360-1-yhs@fb.com

1 files changed, 16 insertions, 0 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index f9c4bb08f616..4175cf1f4665 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -107,6 +107,9 @@ struct bpf_map_ops {
 	/* BTF name and id of struct allocated by map_alloc */
 	const char * const map_btf_name;
 	int *map_btf_id;
+
+	/* bpf_iter info used to open a seq_file */
+	const struct bpf_iter_seq_info *iter_seq_info;
 };
 
 struct bpf_map_memory {
@@ -1207,12 +1210,18 @@ int bpf_obj_get_user(const char __user *pathname, int flags);
 	int __init bpf_iter_ ## target(args) { return 0; }
 
 struct bpf_iter_aux_info {
+	struct bpf_map *map;
 };
 
+typedef int (*bpf_iter_check_target_t)(struct bpf_prog *prog,
+				       struct bpf_iter_aux_info *aux);
+
 #define BPF_ITER_CTX_ARG_MAX 2
 struct bpf_iter_reg {
 	const char *target;
+	bpf_iter_check_target_t check_target;
 	u32 ctx_arg_info_size;
+	enum bpf_iter_link_info req_linfo;
 	struct bpf_ctx_arg_aux ctx_arg_info[BPF_ITER_CTX_ARG_MAX];
 	const struct bpf_iter_seq_info *seq_info;
 };
@@ -1223,6 +1232,13 @@ struct bpf_iter_meta {
 	u64 seq_num;
 };
 
+struct bpf_iter__bpf_map_elem {
+	__bpf_md_ptr(struct bpf_iter_meta *, meta);
+	__bpf_md_ptr(struct bpf_map *, map);
+	__bpf_md_ptr(void *, key);
+	__bpf_md_ptr(void *, value);
+};
+
 int bpf_iter_reg_target(const struct bpf_iter_reg *reg_info);
 void bpf_iter_unreg_target(const struct bpf_iter_reg *reg_info);
 bool bpf_iter_prog_supported(struct bpf_prog *prog);