Re: [PATCH bpf-next 2/3] bpf: add bpffs pretty print for cgroup local storage maps

[Martin Lau]

On Fri, Dec 07, 2018 at 04:53:14PM -0800, Roman Gushchin wrote:
> Implement bpffs pretty printing for cgroup local storage maps
> (both shared and per-cpu).
> Output example (captured for tools/testing/selftests/bpf/netcnt_prog.c):
> 
> Shared:
>   $ cat /sys/fs/bpf/map_2
>   # WARNING!! The output is for debug purpose only
>   # WARNING!! The output format will change
>   {4294968594,1}: {9999,1039896}
> 
> Per-cpu:
>   $ cat /sys/fs/bpf/map_1
>   # WARNING!! The output is for debug purpose only
>   # WARNING!! The output format will change
>   {4294968594,1}: {
>   	cpu0: {0,0,0,0,0}
>   	cpu1: {0,0,0,0,0}
>   	cpu2: {1,104,0,0,0}
>   	cpu3: {0,0,0,0,0}
>   }
> 
> Signed-off-by: Roman Gushchin <guro@xxxxxx>
> Cc: Alexei Starovoitov <ast@xxxxxxxxxx>
> Cc: Daniel Borkmann <daniel@xxxxxxxxxxxxx>
> ---
>  include/linux/btf.h        | 10 +++++
>  kernel/bpf/local_storage.c | 90 +++++++++++++++++++++++++++++++++++++-
>  2 files changed, 99 insertions(+), 1 deletion(-)
> 
> diff --git a/include/linux/btf.h b/include/linux/btf.h
> index 8c2199b5d250..ac67bc4cbfd9 100644
> --- a/include/linux/btf.h
> +++ b/include/linux/btf.h
> @@ -5,6 +5,7 @@
>  #define _LINUX_BTF_H 1
>  
>  #include <linux/types.h>
> +#include <uapi/linux/btf.h>
>  
>  struct btf;
>  struct btf_type;
> @@ -63,4 +64,13 @@ static inline const char *btf_name_by_offset(const struct btf *btf,
>  }
>  #endif
>  
> +static inline const struct btf_type *btf_orig_type(const struct btf *btf,
> +						   const struct btf_type *t)
> +{
> +	while (t && BTF_INFO_KIND(t->info) == BTF_KIND_TYPEDEF)
> +		t = btf_type_by_id(btf, t->type);
Only typedef is allowed?  Not even const?
If that is not the case, can btf_type_id_size() be reused?
The "type following" has already been done once and then remembered
in the verification time.

If cgroup_storage_check_btf() can only allow typedef, please
move "btf_orig_type()" to the local_storage.c.

> +
> +	return t;
> +}
> +
>  #endif
> diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
> index b65017dead44..7b51fe1aba3c 100644
> --- a/kernel/bpf/local_storage.c
> +++ b/kernel/bpf/local_storage.c
> @@ -1,11 +1,13 @@
>  //SPDX-License-Identifier: GPL-2.0
>  #include <linux/bpf-cgroup.h>
>  #include <linux/bpf.h>
> +#include <linux/btf.h>
>  #include <linux/bug.h>
>  #include <linux/filter.h>
>  #include <linux/mm.h>
>  #include <linux/rbtree.h>
>  #include <linux/slab.h>
> +#include <uapi/linux/btf.h>
>  
>  DEFINE_PER_CPU(struct bpf_cgroup_storage*, bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]);
>  
> @@ -308,6 +310,91 @@ static int cgroup_storage_delete_elem(struct bpf_map *map, void *key)
>  	return -EINVAL;
>  }
>  
> +static int cgroup_storage_check_btf(const struct bpf_map *map,
> +				    const struct btf *btf,
> +				    const struct btf_type *key_type,
Actually, in "map_check_btf()" (just before cgroup_storage_check_btf()
is called), btf_type_id_size() has already been called
to get the true size and the resolved type (i.e. BTF_INFO_KIND_STRUCT here)
in order to reject "key_size != map->key_size".  Hence, the key_type
passed to cgroup_storage_check_btf() here will not be KIND_TYPEDEF or
KIND_CONST.

> +				    const struct btf_type *value_type)
> +{
> +	const struct btf_type *st, *t;
> +	struct btf_member *m;
> +
> +	/* Key is expected to be of struct bpf_cgroup_storage_key type,
> +	 * which is:
> +	 * struct bpf_cgroup_storage_key {
> +	 *	__u64	cgroup_inode_id;
> +	 *	__u32	attach_type;
> +	 * };
> +	 */
> +
> +	/*
> +	 * Key_type must be a structure (or a typedef of a structure) with
> +	 * two members.
> +	 */
> +	st = btf_orig_type(btf, key_type);
> +	if (BTF_INFO_KIND(st->info) != BTF_KIND_STRUCT ||
> +	    BTF_INFO_VLEN(st->info) != 2)
> +		return -EINVAL;
> +
> +	/*
> +	 * The first field must be a 64 bit integer at 0 offset.
> +	 */
> +	m = (struct btf_member *)(st + 1);
> +	t = btf_orig_type(btf, btf_type_by_id(btf, m->type));
> +	if (!t || BTF_INFO_KIND(t->info) != BTF_KIND_INT || m->offset ||
> +	    t->size !=
> +	    FIELD_SIZEOF(struct bpf_cgroup_storage_key, cgroup_inode_id))
Instead of t->size,
BTF_INT_BITS() and BTF_INT_OFFSET() need to be checked (please refer to the
key_type check in array_map_check_btf()).

I think exposing "btf_type_int_is_regular()" from btf.c will be easier here.
Actually, add "btf_type_is_reg_int(t, expected_size)" to btf.h and btf.c,
like (uncompiled and untested code):

/*
 * Not a bit field and it must be the expected size.
 */
bool btf_type_is_reg_int(const struct btf_type *t, u32 expected_size)
{
 	u8 nr_bits, nr_bytes;
        u32 int_data;

	if (!btf_type_is_int(t))
		return false;

	int_data = btf_type_int(t);
	nr_bits = BTF_INT_BITS(int_data);
	nr_bytes = BITS_ROUNDUP_BYTES(nr_bits);
	if (BITS_PER_BYTE_MASKED(nr_bits) ||
	    BTF_INT_OFFSET(int_data) ||
	    nr_bytes != expected_size)
                return false;

	return true;
}


> +		return -EINVAL;
> +
> +	/*
> +	 * The second field must be a 32 bit integer at 0 offset.
> +	 */
> +	m = m + 1;
> +	t = btf_orig_type(btf, btf_type_by_id(btf, m->type));
> +	if (!t || BTF_INFO_KIND(t->info) != BTF_KIND_INT ||
> +	    m->offset != offsetof(struct bpf_cgroup_storage_key, attach_type) *
> +	    BITS_PER_BYTE || t->size !=
> +	    FIELD_SIZEOF(struct bpf_cgroup_storage_key, attach_type))
> +		return -EINVAL;
> +
> +	return 0;
> +}
> +
> +static void cgroup_storage_seq_show_elem(struct bpf_map *map, void *_key,
> +					 struct seq_file *m)
> +{
> +	enum bpf_cgroup_storage_type stype = cgroup_storage_type(map);
> +	struct bpf_cgroup_storage_key *key = _key;
> +	struct bpf_cgroup_storage *storage;
> +	int cpu;
> +
> +	rcu_read_lock();
> +	storage = cgroup_storage_lookup(map_to_storage(map), key, false);
> +	if (!storage) {
> +		rcu_read_unlock();
> +		return;
> +	}
> +
> +	btf_type_seq_show(map->btf, map->btf_key_type_id, key, m);
> +	stype = cgroup_storage_type(map);
> +	if (stype == BPF_CGROUP_STORAGE_SHARED) {
> +		seq_puts(m, ": ");
> +		btf_type_seq_show(map->btf, map->btf_value_type_id,
> +				  &READ_ONCE(storage->buf)->data[0], m);
> +		seq_puts(m, "\n");
> +	} else {
> +		seq_puts(m, ": {\n");
> +		for_each_possible_cpu(cpu) {
> +			seq_printf(m, "\tcpu%d: ", cpu);
> +			btf_type_seq_show(map->btf, map->btf_value_type_id,
> +					  per_cpu_ptr(storage->percpu_buf, cpu),
> +					  m);
> +			seq_puts(m, "\n");
> +		}
> +		seq_puts(m, "}\n");
> +	}
> +	rcu_read_unlock();
> +}
> +
>  const struct bpf_map_ops cgroup_storage_map_ops = {
>  	.map_alloc = cgroup_storage_map_alloc,
>  	.map_free = cgroup_storage_map_free,
> @@ -315,7 +402,8 @@ const struct bpf_map_ops cgroup_storage_map_ops = {
>  	.map_lookup_elem = cgroup_storage_lookup_elem,
>  	.map_update_elem = cgroup_storage_update_elem,
>  	.map_delete_elem = cgroup_storage_delete_elem,
> -	.map_check_btf = map_check_no_btf,
> +	.map_check_btf = cgroup_storage_check_btf,
> +	.map_seq_show_elem = cgroup_storage_seq_show_elem,
>  };
>  
>  int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *_map)
> -- 
> 2.19.2
>