On Mon, Apr 27, 2020 at 01:12:36PM -0700, Yonghong Song wrote:
> The target can call bpf_iter_reg_target() to register itself.
> The needed information:
> target: target name, reprsented as a directory hierarchy
> target_func_name: the kernel func name used by verifier to
> verify bpf programs
> seq_ops: the seq_file operations for the target
> seq_priv_size: the private_data size needed by the seq_file
> operations
> target_feature: certain feature requested by the target for
> bpf_iter to prepare for seq_file operations.
>
> A little bit more explanations on the target name and target_feature.
> For example, the target name can be "bpf_map", "task", "task/file",
> which represents iterating all bpf_map's, all tasks, or all files
> of all tasks.
>
> The target feature is mostly for reusing existing seq_file operations.
> For example, /proc/net/{tcp6, ipv6_route, netlink, ...} seq_file private
> data contains a reference to net namespace. When bpf_iter tries to
> reuse the same seq_ops, its seq_file private data need the net namespace
> setup properly too. In this case, the bpf_iter infrastructure can help
> set up properly before doing seq_file operations.
>
> Signed-off-by: Yonghong Song <yhs@xxxxxx>
> ---
> include/linux/bpf.h | 11 ++++++++++
> kernel/bpf/Makefile | 2 +-
> kernel/bpf/bpf_iter.c | 50 +++++++++++++++++++++++++++++++++++++++++++
> 3 files changed, 62 insertions(+), 1 deletion(-)
> create mode 100644 kernel/bpf/bpf_iter.c
>
> diff --git a/include/linux/bpf.h b/include/linux/bpf.h
> index 10960cfabea4..5e56abc1e2f1 100644
> --- a/include/linux/bpf.h
> +++ b/include/linux/bpf.h
> @@ -31,6 +31,7 @@ struct seq_file;
> struct btf;
> struct btf_type;
> struct exception_table_entry;
> +struct seq_operations;
>
> extern struct idr btf_idr;
> extern spinlock_t btf_idr_lock;
> @@ -1109,6 +1110,16 @@ struct bpf_link *bpf_link_get_from_fd(u32 ufd);
> int bpf_obj_pin_user(u32 ufd, const char __user *pathname);
> int bpf_obj_get_user(const char __user *pathname, int flags);
>
> +struct bpf_iter_reg {
> + const char *target;
> + const char *target_func_name;
> + const struct seq_operations *seq_ops;
> + u32 seq_priv_size;
> + u32 target_feature;
> +};
> +
> +int bpf_iter_reg_target(struct bpf_iter_reg *reg_info);
> +
> int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value);
> int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value);
> int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value,
> diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
> index f2d7be596966..6a8b0febd3f6 100644
> --- a/kernel/bpf/Makefile
> +++ b/kernel/bpf/Makefile
> @@ -2,7 +2,7 @@
> obj-y := core.o
> CFLAGS_core.o += $(call cc-disable-warning, override-init)
>
> -obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o
> +obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_iter.o
> obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o
> obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o
> obj-$(CONFIG_BPF_SYSCALL) += disasm.o
> diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c
> new file mode 100644
> index 000000000000..1115b978607a
> --- /dev/null
> +++ b/kernel/bpf/bpf_iter.c
> @@ -0,0 +1,50 @@
> +// SPDX-License-Identifier: GPL-2.0-only
> +/* Copyright (c) 2020 Facebook */
> +
> +#include <linux/fs.h>
> +#include <linux/filter.h>
> +#include <linux/bpf.h>
> +
> +struct bpf_iter_target_info {
> + struct list_head list;
> + const char *target;
> + const char *target_func_name;
> + const struct seq_operations *seq_ops;
> + u32 seq_priv_size;
> + u32 target_feature;
> +};
> +
> +static struct list_head targets;
> +static struct mutex targets_mutex;
> +static bool bpf_iter_inited = false;
The "!bpf_iter_inited" test below is racy.
LIST_HEAD_INIT and DEFINE_MUTEX can be used instead.
> +
> +int bpf_iter_reg_target(struct bpf_iter_reg *reg_info)
> +{
> + struct bpf_iter_target_info *tinfo;
> +
> + /* The earliest bpf_iter_reg_target() is called at init time
> + * where the bpf_iter registration is serialized.
> + */
> + if (!bpf_iter_inited) {
> + INIT_LIST_HEAD(&targets);
> + mutex_init(&targets_mutex);
> + bpf_iter_inited = true;
> + }
