Re: [RFC bpf-next 1/6] bpf: xfrm: Add bpf_xdp_get_xfrm_state() kfunc

[Alexei Starovoitov]

On Fri, Oct 27, 2023 at 11:46 AM Daniel Xu <dxu@xxxxxxxxx> wrote:
>
> This commit adds an unstable kfunc helper to access internal xfrm_state
> associated with an SA. This is intended to be used for the upcoming
> IPsec pcpu work to assign special pcpu SAs to a particular CPU. In other
> words: for custom software RSS.
>
> That being said, the function that this kfunc wraps is fairly generic
> and used for a lot of xfrm tasks. I'm sure people will find uses
> elsewhere over time.
>
> Signed-off-by: Daniel Xu <dxu@xxxxxxxxx>
> ---
>  include/net/xfrm.h        |   9 ++++
>  net/xfrm/Makefile         |   1 +
>  net/xfrm/xfrm_policy.c    |   2 +
>  net/xfrm/xfrm_state_bpf.c | 105 ++++++++++++++++++++++++++++++++++++++
>  4 files changed, 117 insertions(+)
>  create mode 100644 net/xfrm/xfrm_state_bpf.c
>
> diff --git a/include/net/xfrm.h b/include/net/xfrm.h
> index 98d7aa78adda..ab4cf66480f3 100644
> --- a/include/net/xfrm.h
> +++ b/include/net/xfrm.h
> @@ -2188,4 +2188,13 @@ static inline int register_xfrm_interface_bpf(void)
>
>  #endif
>
> +#if IS_ENABLED(CONFIG_DEBUG_INFO_BTF)
> +int register_xfrm_state_bpf(void);
> +#else
> +static inline int register_xfrm_state_bpf(void)
> +{
> +       return 0;
> +}
> +#endif
> +
>  #endif /* _NET_XFRM_H */
> diff --git a/net/xfrm/Makefile b/net/xfrm/Makefile
> index cd47f88921f5..547cec77ba03 100644
> --- a/net/xfrm/Makefile
> +++ b/net/xfrm/Makefile
> @@ -21,3 +21,4 @@ obj-$(CONFIG_XFRM_USER_COMPAT) += xfrm_compat.o
>  obj-$(CONFIG_XFRM_IPCOMP) += xfrm_ipcomp.o
>  obj-$(CONFIG_XFRM_INTERFACE) += xfrm_interface.o
>  obj-$(CONFIG_XFRM_ESPINTCP) += espintcp.o
> +obj-$(CONFIG_DEBUG_INFO_BTF) += xfrm_state_bpf.o
> diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
> index 5cdd3bca3637..62e64fa7ae5c 100644
> --- a/net/xfrm/xfrm_policy.c
> +++ b/net/xfrm/xfrm_policy.c
> @@ -4267,6 +4267,8 @@ void __init xfrm_init(void)
>  #ifdef CONFIG_XFRM_ESPINTCP
>         espintcp_init();
>  #endif
> +
> +       register_xfrm_state_bpf();
>  }
>
>  #ifdef CONFIG_AUDITSYSCALL
> diff --git a/net/xfrm/xfrm_state_bpf.c b/net/xfrm/xfrm_state_bpf.c
> new file mode 100644
> index 000000000000..a73a17a6497b
> --- /dev/null
> +++ b/net/xfrm/xfrm_state_bpf.c
> @@ -0,0 +1,105 @@
> +// SPDX-License-Identifier: GPL-2.0-only
> +/* Unstable XFRM state BPF helpers.
> + *
> + * Note that it is allowed to break compatibility for these functions since the
> + * interface they are exposed through to BPF programs is explicitly unstable.
> + */
> +
> +#include <linux/bpf.h>
> +#include <linux/btf_ids.h>
> +#include <net/xdp.h>
> +#include <net/xfrm.h>
> +
> +/* bpf_xfrm_state_opts - Options for XFRM state lookup helpers
> + *
> + * Members:
> + * @error      - Out parameter, set for any errors encountered
> + *              Values:
> + *                -EINVAL - netns_id is less than -1
> + *                -EINVAL - Passed NULL for opts
> + *                -EINVAL - opts__sz isn't BPF_XFRM_STATE_OPTS_SZ
> + *                -ENONET - No network namespace found for netns_id
> + * @netns_id   - Specify the network namespace for lookup
> + *              Values:
> + *                BPF_F_CURRENT_NETNS (-1)
> + *                  Use namespace associated with ctx
> + *                [0, S32_MAX]
> + *                  Network Namespace ID
> + * @mark       - XFRM mark to match on
> + * @daddr      - Destination address to match on
> + * @spi                - Security parameter index to match on
> + * @proto      - L3 protocol to match on
> + * @family     - L3 protocol family to match on
> + */
> +struct bpf_xfrm_state_opts {
> +       s32 error;
> +       s32 netns_id;
> +       u32 mark;
> +       xfrm_address_t daddr;
> +       __be32 spi;
> +       u8 proto;
> +       u16 family;
> +};
> +
> +enum {
> +       BPF_XFRM_STATE_OPTS_SZ = sizeof(struct bpf_xfrm_state_opts),
> +};
> +
> +__diag_push();
> +__diag_ignore_all("-Wmissing-prototypes",
> +                 "Global functions as their definitions will be in xfrm_state BTF");
> +
> +/* bpf_xdp_get_xfrm_state - Get XFRM state
> + *
> + * Parameters:
> + * @ctx        - Pointer to ctx (xdp_md) in XDP program
> + *                 Cannot be NULL
> + * @opts       - Options for lookup (documented above)
> + *                 Cannot be NULL
> + * @opts__sz   - Length of the bpf_xfrm_state_opts structure
> + *                 Must be BPF_XFRM_STATE_OPTS_SZ
> + */
> +__bpf_kfunc struct xfrm_state *
> +bpf_xdp_get_xfrm_state(struct xdp_md *ctx, struct bpf_xfrm_state_opts *opts, u32 opts__sz)
> +{
> +       struct xdp_buff *xdp = (struct xdp_buff *)ctx;
> +       struct net *net = dev_net(xdp->rxq->dev);
> +
> +       if (!opts || opts__sz != BPF_XFRM_STATE_OPTS_SZ) {
> +               opts->error = -EINVAL;
> +               return NULL;
> +       }
> +
> +       if (unlikely(opts->netns_id < BPF_F_CURRENT_NETNS)) {
> +               opts->error = -EINVAL;
> +               return NULL;
> +       }
> +
> +       if (opts->netns_id >= 0) {
> +               net = get_net_ns_by_id(net, opts->netns_id);
> +               if (unlikely(!net)) {
> +                       opts->error = -ENONET;
> +                       return NULL;
> +               }
> +       }
> +
> +       return xfrm_state_lookup(net, opts->mark, &opts->daddr, opts->spi,
> +                                opts->proto, opts->family);
> +}

Patch 6 example does little to explain how this kfunc can be used.
Cover letter sounds promising, but no code to demonstrate the result.
The main issue is that this kfunc has to be KF_ACQUIRE,
otherwise bpf prog will keep leaking xfrm_state.
Plenty of red flags in this RFC.