Re: [PATCH bpf-next v3 3/7] bpf: minimize number of allocated lsm slots per program

[Martin KaFai Lau <kafai@fb.com>]

On Thu, Apr 07, 2022 at 03:31:08PM -0700, Stanislav Fomichev wrote:
> Previous patch adds 1:1 mapping between all 211 LSM hooks
> and bpf_cgroup program array. Instead of reserving a slot per
> possible hook, reserve 10 slots per cgroup for lsm programs.
> Those slots are dynamically allocated on demand and reclaimed.
> This still adds some bloat to the cgroup and brings us back to
> roughly pre-cgroup_bpf_attach_type times.
> 
> It should be possible to eventually extend this idea to all hooks if
> the memory consumption is unacceptable and shrink overall effective
> programs array.
> 
> Signed-off-by: Stanislav Fomichev <sdf@google.com>
> ---
>  include/linux/bpf-cgroup-defs.h |  4 +-
>  include/linux/bpf_lsm.h         |  6 ---
>  kernel/bpf/bpf_lsm.c            |  9 ++--
>  kernel/bpf/cgroup.c             | 96 ++++++++++++++++++++++++++++-----
>  4 files changed, 90 insertions(+), 25 deletions(-)
> 
> diff --git a/include/linux/bpf-cgroup-defs.h b/include/linux/bpf-cgroup-defs.h
> index 6c661b4df9fa..d42516e86b3a 100644
> --- a/include/linux/bpf-cgroup-defs.h
> +++ b/include/linux/bpf-cgroup-defs.h
> @@ -10,7 +10,9 @@
>  
>  struct bpf_prog_array;
>  
> -#define CGROUP_LSM_NUM 211 /* will be addressed in the next patch */
> +/* Maximum number of concurrently attachable per-cgroup LSM hooks.
> + */
> +#define CGROUP_LSM_NUM 10
hmm...only 10 different lsm hooks (or 10 different attach_btf_ids) can
have BPF_LSM_CGROUP programs attached.  This feels quite limited but having
a static 211 (and potentially growing in the future) is not good either.
I currently do not have a better idea also. :/

Have you thought about other dynamic schemes or they would be too slow ?

>  enum cgroup_bpf_attach_type {
>  	CGROUP_BPF_ATTACH_TYPE_INVALID = -1,
> diff --git a/include/linux/bpf_lsm.h b/include/linux/bpf_lsm.h
> index 7f0e59f5f9be..613de44aa429 100644
> --- a/include/linux/bpf_lsm.h
> +++ b/include/linux/bpf_lsm.h
> @@ -43,7 +43,6 @@ extern const struct bpf_func_proto bpf_inode_storage_delete_proto;
>  void bpf_inode_storage_free(struct inode *inode);
>  
>  int bpf_lsm_find_cgroup_shim(const struct bpf_prog *prog, bpf_func_t *bpf_func);
> -int bpf_lsm_hook_idx(u32 btf_id);
>  
>  #else /* !CONFIG_BPF_LSM */
>  
> @@ -74,11 +73,6 @@ static inline int bpf_lsm_find_cgroup_shim(const struct bpf_prog *prog,
>  	return -ENOENT;
>  }
>  
> -static inline int bpf_lsm_hook_idx(u32 btf_id)
> -{
> -	return -EINVAL;
> -}
> -
>  #endif /* CONFIG_BPF_LSM */
>  
>  #endif /* _LINUX_BPF_LSM_H */
> diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c
> index eca258ba71d8..8b948ec9ab73 100644
> --- a/kernel/bpf/bpf_lsm.c
> +++ b/kernel/bpf/bpf_lsm.c
> @@ -57,10 +57,12 @@ static unsigned int __cgroup_bpf_run_lsm_socket(const void *ctx,
>  	if (unlikely(!sk))
>  		return 0;
>  
> +	rcu_read_lock(); /* See bpf_lsm_attach_type_get(). */
>  	cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
>  	if (likely(cgrp))
>  		ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[prog->aux->cgroup_atype],
>  					    ctx, bpf_prog_run, 0);
> +	rcu_read_unlock();
>  	return ret;
>  }
>  
> @@ -77,7 +79,7 @@ static unsigned int __cgroup_bpf_run_lsm_current(const void *ctx,
>  	/*prog = container_of(insn, struct bpf_prog, insnsi);*/
>  	prog = (const struct bpf_prog *)((void *)insn - offsetof(struct bpf_prog, insnsi));
>  
> -	rcu_read_lock();
> +	rcu_read_lock(); /* See bpf_lsm_attach_type_get(). */
I think this is also needed for task_dfl_cgroup().  If yes,
will be a good idea to adjust the comment if it ends up
using the 'CGROUP_LSM_NUM 10' scheme.

While at rcu_read_lock(), have you thought about what major things are
needed to make BPF_LSM_CGROUP sleepable ?

The cgroup local storage could be one that require changes but it seems
the cgroup local storage is not available to BPF_LSM_GROUP in this change set.
The current use case doesn't need it?  

>  	cgrp = task_dfl_cgroup(current);
>  	if (likely(cgrp))
>  		ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[prog->aux->cgroup_atype],
> @@ -122,11 +124,6 @@ int bpf_lsm_find_cgroup_shim(const struct bpf_prog *prog,
>  	return 0;
>  }
>  
> -int bpf_lsm_hook_idx(u32 btf_id)
> -{
> -	return btf_id_set_index(&bpf_lsm_hooks, btf_id);
> -}
> -
>  int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog,
>  			const struct bpf_prog *prog)
>  {