| Message ID | 20250315195910.17659-3-ericwouds@gmail.com (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | Add nf_flow_encap_push() for xmit direct | expand |
On Sat, Mar 15, 2025 at 08:59:09PM +0100, Eric Woudstra wrote: > Loosely based on wenxu's patches: > > "nf_flow_table_offload: offload the vlan/PPPoE encap in the flowtable". I remember that patch. > Fixed double vlan and pppoe packets, almost entirely rewriting the patch. > > After this patch, it is possible to transmit packets in the fastpath with > outgoing encaps, without using vlan- and/or pppoe-devices. > > This makes it possible to use more different kinds of network setups. > For example, when bridge tagging is used to egress vlan tagged > packets using the forward fastpath. Another example is passing 802.1q > tagged packets through a bridge using the bridge fastpath. > > This also makes the software fastpath process more similar to the > hardware offloaded fastpath process, where encaps are also pushed. I am not convinced that making the software flowtable more similar hardware is the way the go, we already have to deal with issues with flow teardown mechanism (races) to make it more suitable for hardware offload. I think the benefit for pppoe is that packets do not go to userspace anymore, but probably pppoe driver can be modified push the header itself? As for vlan, this is saving an indirection? Going in this direction means the flowtable datapath will get more headers to be pushed in this path in the future, eg. mpls. Is this also possibly breaking existing setups? eg. xfrm + vlan devices, but maybe I'm wrong. > After applying this patch, always info->outdev = info->hw_outdev, > so the netfilter code can be further cleaned up by removing: > * hw_outdev from struct nft_forward_info > * out.hw_ifindex from struct nf_flow_route > * out.hw_ifidx from struct flow_offload_tuple > > Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org> > Signed-off-by: Eric Woudstra <ericwouds@gmail.com> > --- > net/netfilter/nf_flow_table_ip.c | 96 +++++++++++++++++++++++++++++++- > net/netfilter/nft_flow_offload.c | 6 +- > 2 files changed, 96 insertions(+), 6 deletions(-) > > diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c > index 8cd4cf7ae211..d0c3c459c4d2 100644 > --- a/net/netfilter/nf_flow_table_ip.c > +++ b/net/netfilter/nf_flow_table_ip.c > @@ -306,6 +306,92 @@ static bool nf_flow_skb_encap_protocol(struct sk_buff *skb, __be16 proto, > return false; > } > > +static int nf_flow_vlan_inner_push(struct sk_buff *skb, __be16 proto, u16 id) > +{ > + struct vlan_hdr *vhdr; > + > + if (skb_cow_head(skb, VLAN_HLEN)) > + return -1; > + > + __skb_push(skb, VLAN_HLEN); > + skb_reset_network_header(skb); > + > + vhdr = (struct vlan_hdr *)(skb->data); > + vhdr->h_vlan_TCI = htons(id); > + vhdr->h_vlan_encapsulated_proto = skb->protocol; > + skb->protocol = proto; > + > + return 0; > +} > + > +static int nf_flow_ppoe_push(struct sk_buff *skb, u16 id) > +{ > + struct ppp_hdr { > + struct pppoe_hdr hdr; > + __be16 proto; > + } *ph; > + int data_len = skb->len + 2; > + __be16 proto; > + > + if (skb_cow_head(skb, PPPOE_SES_HLEN)) > + return -1; > + > + if (skb->protocol == htons(ETH_P_IP)) > + proto = htons(PPP_IP); > + else if (skb->protocol == htons(ETH_P_IPV6)) > + proto = htons(PPP_IPV6); > + else > + return -1; > + > + __skb_push(skb, PPPOE_SES_HLEN); > + skb_reset_network_header(skb); > + > + ph = (struct ppp_hdr *)(skb->data); > + ph->hdr.ver = 1; > + ph->hdr.type = 1; > + ph->hdr.code = 0; > + ph->hdr.sid = htons(id); > + ph->hdr.length = htons(data_len); > + ph->proto = proto; > + skb->protocol = htons(ETH_P_PPP_SES); > + > + return 0; > +} > + > +static int nf_flow_encap_push(struct sk_buff *skb, > + struct flow_offload_tuple_rhash *tuplehash, > + unsigned short *type) > +{ > + int i = 0, ret = 0; > + > + if (!tuplehash->tuple.encap_num) > + return 0; > + > + if (tuplehash->tuple.encap[i].proto == htons(ETH_P_8021Q) || > + tuplehash->tuple.encap[i].proto == htons(ETH_P_8021AD)) { > + __vlan_hwaccel_put_tag(skb, tuplehash->tuple.encap[i].proto, > + tuplehash->tuple.encap[i].id); > + i++; > + if (i >= tuplehash->tuple.encap_num) > + return 0; > + } > + > + switch (tuplehash->tuple.encap[i].proto) { > + case htons(ETH_P_8021Q): > + *type = ETH_P_8021Q; > + ret = nf_flow_vlan_inner_push(skb, > + tuplehash->tuple.encap[i].proto, > + tuplehash->tuple.encap[i].id); > + break; > + case htons(ETH_P_PPP_SES): > + *type = ETH_P_PPP_SES; > + ret = nf_flow_ppoe_push(skb, > + tuplehash->tuple.encap[i].id); > + break; > + } > + return ret; > +} > + > static void nf_flow_encap_pop(struct sk_buff *skb, > struct flow_offload_tuple_rhash *tuplehash) > { > @@ -335,6 +421,7 @@ static void nf_flow_encap_pop(struct sk_buff *skb, > > static unsigned int nf_flow_queue_xmit(struct net *net, struct sk_buff *skb, > const struct flow_offload_tuple_rhash *tuplehash, > + struct flow_offload_tuple_rhash *other_tuplehash, > unsigned short type) > { > struct net_device *outdev; > @@ -343,6 +430,9 @@ static unsigned int nf_flow_queue_xmit(struct net *net, struct sk_buff *skb, > if (!outdev) > return NF_DROP; > > + if (nf_flow_encap_push(skb, other_tuplehash, &type) < 0) > + return NF_DROP; > + > skb->dev = outdev; > dev_hard_header(skb, skb->dev, type, tuplehash->tuple.out.h_dest, > tuplehash->tuple.out.h_source, skb->len); > @@ -462,7 +552,8 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, > ret = NF_STOLEN; > break; > case FLOW_OFFLOAD_XMIT_DIRECT: > - ret = nf_flow_queue_xmit(state->net, skb, tuplehash, ETH_P_IP); > + ret = nf_flow_queue_xmit(state->net, skb, tuplehash, > + &flow->tuplehash[!dir], ETH_P_IP); > if (ret == NF_DROP) > flow_offload_teardown(flow); > break; > @@ -757,7 +848,8 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, > ret = NF_STOLEN; > break; > case FLOW_OFFLOAD_XMIT_DIRECT: > - ret = nf_flow_queue_xmit(state->net, skb, tuplehash, ETH_P_IPV6); > + ret = nf_flow_queue_xmit(state->net, skb, tuplehash, > + &flow->tuplehash[!dir], ETH_P_IPV6); > if (ret == NF_DROP) > flow_offload_teardown(flow); > break; > diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c > index 221d50223018..d320b7f5282e 100644 > --- a/net/netfilter/nft_flow_offload.c > +++ b/net/netfilter/nft_flow_offload.c > @@ -124,13 +124,12 @@ static void nft_dev_path_info(const struct net_device_path_stack *stack, > info->indev = NULL; > break; > } > - if (!info->outdev) > - info->outdev = path->dev; > info->encap[info->num_encaps].id = path->encap.id; > info->encap[info->num_encaps].proto = path->encap.proto; > info->num_encaps++; > if (path->type == DEV_PATH_PPPOE) > memcpy(info->h_dest, path->encap.h_dest, ETH_ALEN); > + info->xmit_type = FLOW_OFFLOAD_XMIT_DIRECT; > break; > case DEV_PATH_BRIDGE: > if (is_zero_ether_addr(info->h_source)) > @@ -158,8 +157,7 @@ static void nft_dev_path_info(const struct net_device_path_stack *stack, > break; > } > } > - if (!info->outdev) > - info->outdev = info->indev; > + info->outdev = info->indev; > > info->hw_outdev = info->indev; > > -- > 2.47.1 >
On 3/19/25 12:23 AM, Pablo Neira Ayuso wrote: > On Sat, Mar 15, 2025 at 08:59:09PM +0100, Eric Woudstra wrote: >> Loosely based on wenxu's patches: >> >> "nf_flow_table_offload: offload the vlan/PPPoE encap in the flowtable". > > I remember that patch. > >> Fixed double vlan and pppoe packets, almost entirely rewriting the patch. >> >> After this patch, it is possible to transmit packets in the fastpath with >> outgoing encaps, without using vlan- and/or pppoe-devices. >> >> This makes it possible to use more different kinds of network setups. >> For example, when bridge tagging is used to egress vlan tagged >> packets using the forward fastpath. Another example is passing 802.1q >> tagged packets through a bridge using the bridge fastpath. >> >> This also makes the software fastpath process more similar to the >> hardware offloaded fastpath process, where encaps are also pushed. > > I am not convinced that making the software flowtable more similar > hardware is the way the go, we already have to deal with issues with > flow teardown mechanism (races) to make it more suitable for hardware > offload. > > I think the benefit for pppoe is that packets do not go to userspace > anymore, but probably pppoe driver can be modified push the header > itself? > > As for vlan, this is saving an indirection? > > Going in this direction means the flowtable datapath will get more > headers to be pushed in this path in the future, eg. mpls. > > Is this also possibly breaking existing setups? eg. xfrm + vlan > devices, but maybe I'm wrong. > If you do not want to touch the software fastpath, It should be possible to do it without. For bridged interfaces, only use the hardware fastpath, not installing a hook for the software fastpath at all. Another option is installing the hook (matching the hash, updating counter and perhaps calling flow_offload_refresh() and so), but then letting traffic continue the normal path. That is, until the hardware offload takes over. In both cases only allow to add the flowtable if the offload flag is set. What do you think? But in all cases (including existing cases in existing code), I think we need the patches from "[PATCH v10 nf-next 0/3] netfilter: fastpath fixes". Could you look at these?
diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index 8cd4cf7ae211..d0c3c459c4d2 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -306,6 +306,92 @@ static bool nf_flow_skb_encap_protocol(struct sk_buff *skb, __be16 proto, return false; } +static int nf_flow_vlan_inner_push(struct sk_buff *skb, __be16 proto, u16 id) +{ + struct vlan_hdr *vhdr; + + if (skb_cow_head(skb, VLAN_HLEN)) + return -1; + + __skb_push(skb, VLAN_HLEN); + skb_reset_network_header(skb); + + vhdr = (struct vlan_hdr *)(skb->data); + vhdr->h_vlan_TCI = htons(id); + vhdr->h_vlan_encapsulated_proto = skb->protocol; + skb->protocol = proto; + + return 0; +} + +static int nf_flow_ppoe_push(struct sk_buff *skb, u16 id) +{ + struct ppp_hdr { + struct pppoe_hdr hdr; + __be16 proto; + } *ph; + int data_len = skb->len + 2; + __be16 proto; + + if (skb_cow_head(skb, PPPOE_SES_HLEN)) + return -1; + + if (skb->protocol == htons(ETH_P_IP)) + proto = htons(PPP_IP); + else if (skb->protocol == htons(ETH_P_IPV6)) + proto = htons(PPP_IPV6); + else + return -1; + + __skb_push(skb, PPPOE_SES_HLEN); + skb_reset_network_header(skb); + + ph = (struct ppp_hdr *)(skb->data); + ph->hdr.ver = 1; + ph->hdr.type = 1; + ph->hdr.code = 0; + ph->hdr.sid = htons(id); + ph->hdr.length = htons(data_len); + ph->proto = proto; + skb->protocol = htons(ETH_P_PPP_SES); + + return 0; +} + +static int nf_flow_encap_push(struct sk_buff *skb, + struct flow_offload_tuple_rhash *tuplehash, + unsigned short *type) +{ + int i = 0, ret = 0; + + if (!tuplehash->tuple.encap_num) + return 0; + + if (tuplehash->tuple.encap[i].proto == htons(ETH_P_8021Q) || + tuplehash->tuple.encap[i].proto == htons(ETH_P_8021AD)) { + __vlan_hwaccel_put_tag(skb, tuplehash->tuple.encap[i].proto, + tuplehash->tuple.encap[i].id); + i++; + if (i >= tuplehash->tuple.encap_num) + return 0; + } + + switch (tuplehash->tuple.encap[i].proto) { + case htons(ETH_P_8021Q): + *type = ETH_P_8021Q; + ret = nf_flow_vlan_inner_push(skb, + tuplehash->tuple.encap[i].proto, + tuplehash->tuple.encap[i].id); + break; + case htons(ETH_P_PPP_SES): + *type = ETH_P_PPP_SES; + ret = nf_flow_ppoe_push(skb, + tuplehash->tuple.encap[i].id); + break; + } + return ret; +} + static void nf_flow_encap_pop(struct sk_buff *skb, struct flow_offload_tuple_rhash *tuplehash) { @@ -335,6 +421,7 @@ static void nf_flow_encap_pop(struct sk_buff *skb, static unsigned int nf_flow_queue_xmit(struct net *net, struct sk_buff *skb, const struct flow_offload_tuple_rhash *tuplehash, + struct flow_offload_tuple_rhash *other_tuplehash, unsigned short type) { struct net_device *outdev; @@ -343,6 +430,9 @@ static unsigned int nf_flow_queue_xmit(struct net *net, struct sk_buff *skb, if (!outdev) return NF_DROP; + if (nf_flow_encap_push(skb, other_tuplehash, &type) < 0) + return NF_DROP; + skb->dev = outdev; dev_hard_header(skb, skb->dev, type, tuplehash->tuple.out.h_dest, tuplehash->tuple.out.h_source, skb->len); @@ -462,7 +552,8 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, ret = NF_STOLEN; break; case FLOW_OFFLOAD_XMIT_DIRECT: - ret = nf_flow_queue_xmit(state->net, skb, tuplehash, ETH_P_IP); + ret = nf_flow_queue_xmit(state->net, skb, tuplehash, + &flow->tuplehash[!dir], ETH_P_IP); if (ret == NF_DROP) flow_offload_teardown(flow); break; @@ -757,7 +848,8 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, ret = NF_STOLEN; break; case FLOW_OFFLOAD_XMIT_DIRECT: - ret = nf_flow_queue_xmit(state->net, skb, tuplehash, ETH_P_IPV6); + ret = nf_flow_queue_xmit(state->net, skb, tuplehash, + &flow->tuplehash[!dir], ETH_P_IPV6); if (ret == NF_DROP) flow_offload_teardown(flow); break; diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index 221d50223018..d320b7f5282e 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -124,13 +124,12 @@ static void nft_dev_path_info(const struct net_device_path_stack *stack, info->indev = NULL; break; } - if (!info->outdev) - info->outdev = path->dev; info->encap[info->num_encaps].id = path->encap.id; info->encap[info->num_encaps].proto = path->encap.proto; info->num_encaps++; if (path->type == DEV_PATH_PPPOE) memcpy(info->h_dest, path->encap.h_dest, ETH_ALEN); + info->xmit_type = FLOW_OFFLOAD_XMIT_DIRECT; break; case DEV_PATH_BRIDGE: if (is_zero_ether_addr(info->h_source)) @@ -158,8 +157,7 @@ static void nft_dev_path_info(const struct net_device_path_stack *stack, break; } } - if (!info->outdev) - info->outdev = info->indev; + info->outdev = info->indev; info->hw_outdev = info->indev;