netdev - Re: [PATCH v2 bpf-next 2/5] bpf: Add support to attach bpf program to a devmap entry

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: <87imgg1lty.fsf@toke.dk>
Date:   Thu, 28 May 2020 10:54:17 +0200
From:   Toke Høiland-Jørgensen <toke@...hat.com>
To:     David Ahern <dsahern@...nel.org>, netdev@...r.kernel.org
Cc:     davem@...emloft.net, kuba@...nel.org, brouer@...hat.com,
        daniel@...earbox.net, john.fastabend@...il.com, ast@...nel.org,
        kafai@...com, songliubraving@...com, yhs@...com, andriin@...com,
        dsahern@...il.com
Subject: Re: [PATCH v2 bpf-next 2/5] bpf: Add support to attach bpf program to a devmap entry

David Ahern <dsahern@...nel.org> writes:

> From: David Ahern <dsahern@...il.com>
>
> Add BPF_XDP_DEVMAP attach type for use with programs associated with a
> DEVMAP entry.
>
> Allow DEVMAPs to associate a program with a device entry by adding
> a bpf_prog_fd to 'struct devmap_val'. Values read show the program
> id, so the fd and id are a union.
>
> The program associated with the fd must have type XDP with expected
> attach type BPF_XDP_DEVMAP. When a program is associated with a device
> index, the program is run on an XDP_REDIRECT and before the buffer is
> added to the per-cpu queue. At this point rxq data is still valid; the
> next patch adds tx device information allowing the prorgam to see both
> ingress and egress device indices.
>
> XDP generic is skb based and XDP programs do not work with skb's. Block
> the use case by walking maps used by a program that is to be attached
> via xdpgeneric and fail if any of them are DEVMAP / DEVMAP_HASH with
>  > 4-byte values.
>
> Block attach of BPF_XDP_DEVMAP programs to devices.
>
> Signed-off-by: David Ahern <dsahern@...il.com>
> ---
>  include/linux/bpf.h            |  5 +++
>  include/uapi/linux/bpf.h       |  5 +++
>  kernel/bpf/devmap.c            | 79 +++++++++++++++++++++++++++++++++-
>  net/core/dev.c                 | 18 ++++++++
>  tools/include/uapi/linux/bpf.h |  5 +++
>  5 files changed, 110 insertions(+), 2 deletions(-)
>
> diff --git a/include/linux/bpf.h b/include/linux/bpf.h
> index efe8836b5c48..088751bc09aa 100644
> --- a/include/linux/bpf.h
> +++ b/include/linux/bpf.h
> @@ -1242,6 +1242,7 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
>  		    struct net_device *dev_rx);
>  int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
>  			     struct bpf_prog *xdp_prog);
> +bool dev_map_can_have_prog(struct bpf_map *map);
>  
>  struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key);
>  void __cpu_map_flush(void);
> @@ -1355,6 +1356,10 @@ static inline struct net_device  *__dev_map_hash_lookup_elem(struct bpf_map *map
>  {
>  	return NULL;
>  }
> +static inline bool dev_map_can_have_prog(struct bpf_map *map)
> +{
> +	return false;
> +}
>  
>  static inline void __dev_flush(void)
>  {
> diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
> index d27302ecaa9c..2d9927b7a922 100644
> --- a/include/uapi/linux/bpf.h
> +++ b/include/uapi/linux/bpf.h
> @@ -224,6 +224,7 @@ enum bpf_attach_type {
>  	BPF_CGROUP_INET6_GETPEERNAME,
>  	BPF_CGROUP_INET4_GETSOCKNAME,
>  	BPF_CGROUP_INET6_GETSOCKNAME,
> +	BPF_XDP_DEVMAP,
>  	__MAX_BPF_ATTACH_TYPE
>  };
>  
> @@ -3628,6 +3629,10 @@ struct xdp_md {
>  /* DEVMAP values */
>  struct devmap_val {
>  	__u32 ifindex;   /* device index */
> +	union {
> +		int   bpf_prog_fd;  /* prog fd on map write */
> +		__u32 bpf_prog_id;  /* prog id on map read */
> +	};
>  };
>  
>  enum sk_action {
> diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
> index 069a50113e26..a628585a31e1 100644
> --- a/kernel/bpf/devmap.c
> +++ b/kernel/bpf/devmap.c
> @@ -64,6 +64,7 @@ struct bpf_dtab_netdev {
>  	struct net_device *dev; /* must be first member, due to tracepoint */
>  	struct hlist_node index_hlist;
>  	struct bpf_dtab *dtab;
> +	struct bpf_prog *xdp_prog;
>  	struct rcu_head rcu;
>  	unsigned int idx;
>  	struct devmap_val val;
> @@ -219,6 +220,8 @@ static void dev_map_free(struct bpf_map *map)
>  
>  			hlist_for_each_entry_safe(dev, next, head, index_hlist) {
>  				hlist_del_rcu(&dev->index_hlist);
> +				if (dev->xdp_prog)
> +					bpf_prog_put(dev->xdp_prog);
>  				dev_put(dev->dev);
>  				kfree(dev);
>  			}
> @@ -233,6 +236,8 @@ static void dev_map_free(struct bpf_map *map)
>  			if (!dev)
>  				continue;
>  
> +			if (dev->xdp_prog)
> +				bpf_prog_put(dev->xdp_prog);
>  			dev_put(dev->dev);
>  			kfree(dev);
>  		}
> @@ -319,6 +324,16 @@ static int dev_map_hash_get_next_key(struct bpf_map *map, void *key,
>  	return -ENOENT;
>  }
>  
> +bool dev_map_can_have_prog(struct bpf_map *map)
> +{
> +	if ((map->map_type == BPF_MAP_TYPE_DEVMAP ||
> +	     map->map_type == BPF_MAP_TYPE_DEVMAP_HASH) &&
> +	    map->value_size != 4)

nit (since you've gotten rid of the magic sizes everywhere else) how about:

map->value_size != sizeof_field(struct devmap_val, ifindex)