netdev - Re: [PATCH bpf-next,v3 2/4] xfrm: interface: Add unstable helpers for setting/getting XFRM metadata from TC-BPF

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <55c5d250-f3c4-84e0-c56f-cd554ee05482@linux.dev>
Date:   Thu, 1 Dec 2022 23:25:22 -0800
From:   Martin KaFai Lau <martin.lau@...ux.dev>
To:     Eyal Birger <eyal.birger@...il.com>
Cc:     netdev@...r.kernel.org, bpf@...r.kernel.org,
        linux-kselftest@...r.kernel.org, davem@...emloft.net,
        edumazet@...gle.com, kuba@...nel.org, pabeni@...hat.com,
        steffen.klassert@...unet.com, herbert@...dor.apana.org.au,
        andrii@...nel.org, daniel@...earbox.net, nicolas.dichtel@...nd.com,
        razor@...ckwall.org, mykolal@...com, ast@...nel.org,
        song@...nel.org, yhs@...com, john.fastabend@...il.com,
        kpsingh@...nel.org, sdf@...gle.com, haoluo@...gle.com,
        jolsa@...nel.org, shuah@...nel.org, liuhangbin@...il.com,
        lixiaoyan@...gle.com
Subject: Re: [PATCH bpf-next,v3 2/4] xfrm: interface: Add unstable helpers for
 setting/getting XFRM metadata from TC-BPF

On 12/1/22 1:14 PM, Eyal Birger wrote:
> This change adds xfrm metadata helpers using the unstable kfunc call
> interface for the TC-BPF hooks. This allows steering traffic towards
> different IPsec connections based on logic implemented in bpf programs.
> 
> This object is built based on the availabilty of BTF debug info.

s/availabilty/availability/

> 
> The metadata percpu dsts used on TX take ownership of the original skb
> dsts so that they may be used as part of the xfrm transmittion logic -

s/transmittion/transmission/

[ ... ]

> diff --git a/net/xfrm/Makefile b/net/xfrm/Makefile
> index 08a2870fdd36..cd47f88921f5 100644
> --- a/net/xfrm/Makefile
> +++ b/net/xfrm/Makefile
> @@ -5,6 +5,12 @@
>   
>   xfrm_interface-$(CONFIG_XFRM_INTERFACE) += xfrm_interface_core.o
>   
> +ifeq ($(CONFIG_XFRM_INTERFACE),m)
> +xfrm_interface-$(CONFIG_DEBUG_INFO_BTF_MODULES) += xfrm_interface_bpf.o
> +else ifeq ($(CONFIG_XFRM_INTERFACE),y)
> +xfrm_interface-$(CONFIG_DEBUG_INFO_BTF) += xfrm_interface_bpf.o
> +endif
> +
>   obj-$(CONFIG_XFRM) := xfrm_policy.o xfrm_state.o xfrm_hash.o \
>   		      xfrm_input.o xfrm_output.o \
>   		      xfrm_sysctl.o xfrm_replay.o xfrm_device.o
> diff --git a/net/xfrm/xfrm_interface_bpf.c b/net/xfrm/xfrm_interface_bpf.c
> new file mode 100644
> index 000000000000..7938bf6cbb32
> --- /dev/null
> +++ b/net/xfrm/xfrm_interface_bpf.c
> @@ -0,0 +1,99 @@
> +// SPDX-License-Identifier: GPL-2.0-only
> +/* Unstable XFRM Helpers for TC-BPF hook
> + *
> + * These are called from SCHED_CLS BPF programs. 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/dst_metadata.h>
> +#include <net/xfrm.h>
> +
> +struct bpf_xfrm_info {

Documentation is needed here and...

> +	u32 if_id;
> +	int link;
> +};
> +
> +static struct metadata_dst __percpu *xfrm_md_dst;
> +__diag_push();
> +__diag_ignore_all("-Wmissing-prototypes",
> +		  "Global functions as their definitions will be in xfrm_interface BTF");
> +
> +__used noinline
> +int bpf_skb_get_xfrm_info(struct __sk_buff *skb_ctx, struct bpf_xfrm_info *to)

... also this get and the following set kfunc.

> +{
> +	struct sk_buff *skb = (struct sk_buff *)skb_ctx;
> +	struct xfrm_md_info *info;
> +
> +	memset(to, 0, sizeof(*to));
> +
> +	info = skb_xfrm_md_info(skb);
> +	if (!info)
> +		return -EINVAL;
> +
> +	to->if_id = info->if_id;
> +	to->link = info->link;
> +	return 0;
> +}
> +
> +__used noinline
> +int bpf_skb_set_xfrm_info(struct __sk_buff *skb_ctx,
> +			  const struct bpf_xfrm_info *from)
> +{
> +	struct sk_buff *skb = (struct sk_buff *)skb_ctx;
> +	struct metadata_dst *md_dst;
> +	struct xfrm_md_info *info;
> +
> +	if (unlikely(skb_metadata_dst(skb)))
> +		return -EINVAL;
> +
> +	md_dst = this_cpu_ptr(xfrm_md_dst);
> +
> +	info = &md_dst->u.xfrm_info;
> +
> +	info->if_id = from->if_id;
> +	info->link = from->link;
> +	skb_dst_force(skb);
> +	info->dst_orig = skb_dst(skb);
> +
> +	dst_hold((struct dst_entry *)md_dst);
> +	skb_dst_set(skb, (struct dst_entry *)md_dst);
> +	return 0;
> +}
> +
> +__diag_pop()
> +
> +BTF_SET8_START(xfrm_ifc_kfunc_set)
> +BTF_ID_FLAGS(func, bpf_skb_get_xfrm_info)
> +BTF_ID_FLAGS(func, bpf_skb_set_xfrm_info)
> +BTF_SET8_END(xfrm_ifc_kfunc_set)
> +
> +static const struct btf_kfunc_id_set xfrm_interface_kfunc_set = {
> +	.owner = THIS_MODULE,
> +	.set   = &xfrm_ifc_kfunc_set,
> +};
> +
> +int __init register_xfrm_interface_bpf(void)
> +{
> +	int err;
> +
> +	xfrm_md_dst = metadata_dst_alloc_percpu(0, METADATA_XFRM,
> +						GFP_KERNEL);
> +	if (!xfrm_md_dst)
> +		return -ENOMEM;
> +	err = register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS,
> +					&xfrm_interface_kfunc_set);
> +	if (err < 0) {
> +		cleanup_xfrm_interface_bpf();


nit. Directly call metadata_dst_free_percpu(xfrm_md_dst), easier to read.
> +		return err;
> +	}
> +	return 0;
> +}
> +
> +void cleanup_xfrm_interface_bpf(void)
> +{
> +	metadata_dst_free_percpu(xfrm_md_dst);
> +}