diff options
Diffstat (limited to 'pkgs/patches-linux-5.15/645-netfilter-connmark-introduce-set-dscpmark.patch')
| -rw-r--r-- | pkgs/patches-linux-5.15/645-netfilter-connmark-introduce-set-dscpmark.patch | 212 |
1 files changed, 212 insertions, 0 deletions
diff --git a/pkgs/patches-linux-5.15/645-netfilter-connmark-introduce-set-dscpmark.patch b/pkgs/patches-linux-5.15/645-netfilter-connmark-introduce-set-dscpmark.patch new file mode 100644 index 0000000..2d3fe01 --- /dev/null +++ b/pkgs/patches-linux-5.15/645-netfilter-connmark-introduce-set-dscpmark.patch @@ -0,0 +1,212 @@ +From eda40b8c8c82e0f2789d6bc8bf63846dce2e8f32 Mon Sep 17 00:00:00 2001 +From: Kevin Darbyshire-Bryant <ldir@darbyshire-bryant.me.uk> +Date: Sat, 23 Mar 2019 09:29:49 +0000 +Subject: [PATCH] netfilter: connmark: introduce set-dscpmark + +set-dscpmark is a method of storing the DSCP of an ip packet into +conntrack mark. In combination with a suitable tc filter action +(act_ctinfo) DSCP values are able to be stored in the mark on egress and +restored on ingress across links that otherwise alter or bleach DSCP. + +This is useful for qdiscs such as CAKE which are able to shape according +to policies based on DSCP. + +Ingress classification is traditionally a challenging task since +iptables rules haven't yet run and tc filter/eBPF programs are pre-NAT +lookups, hence are unable to see internal IPv4 addresses as used on the +typical home masquerading gateway. + +x_tables CONNMARK set-dscpmark target solves the problem of storing the +DSCP to the conntrack mark in a way suitable for the new act_ctinfo tc +action to restore. + +The set-dscpmark option accepts 2 parameters, a 32bit 'dscpmask' and a +32bit 'statemask'. The dscp mask must be 6 contiguous bits and +represents the area where the DSCP will be stored in the connmark. The +state mask is a minimum 1 bit length mask that must not overlap with the +dscpmask. It represents a flag which is set when the DSCP has been +stored in the conntrack mark. This is useful to implement a 'one shot' +iptables based classification where the 'complicated' iptables rules are +only run once to classify the connection on initial (egress) packet and +subsequent packets are all marked/restored with the same DSCP. A state +mask of zero disables the setting of a status bit/s. + +example syntax with a suitably modified iptables user space application: + +iptables -A QOS_MARK_eth0 -t mangle -j CONNMARK --set-dscpmark 0xfc000000/0x01000000 + +Would store the DSCP in the top 6 bits of the 32bit mark field, and use +the LSB of the top byte as the 'DSCP has been stored' marker. + +|----0xFC----conntrack mark----000000---| +| Bits 31-26 | bit 25 | bit24 |~~~ Bit 0| +| DSCP | unused | flag |unused | +|-----------------------0x01---000000---| + ^ ^ + | | + ---| Conditional flag + | set this when dscp +|-ip diffserv-| stored in mark +| 6 bits | +|-------------| + +an identically configured tc action to restore looks like: + +tc filter show dev eth0 ingress +filter parent ffff: protocol all pref 10 u32 chain 0 +filter parent ffff: protocol all pref 10 u32 chain 0 fh 800: ht divisor 1 +filter parent ffff: protocol all pref 10 u32 chain 0 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1: not_in_hw + match 00000000/00000000 at 0 + action order 1: ctinfo zone 0 pipe + index 2 ref 1 bind 1 dscp 0xfc000000/0x1000000 + + action order 2: mirred (Egress Redirect to device ifb4eth0) stolen + index 1 ref 1 bind 1 + +|----0xFC----conntrack mark----000000---| +| Bits 31-26 | bit 25 | bit24 |~~~ Bit 0| +| DSCP | unused | flag |unused | +|-----------------------0x01---000000---| + | | + | | + ---| Conditional flag + v only restore if set +|-ip diffserv-| +| 6 bits | +|-------------| + +Signed-off-by: Kevin Darbyshire-Bryant <ldir@darbyshire-bryant.me.uk> +--- + include/uapi/linux/netfilter/xt_connmark.h | 10 ++++ + net/netfilter/xt_connmark.c | 55 ++++++++++++++++++---- + 2 files changed, 57 insertions(+), 8 deletions(-) + +--- a/include/uapi/linux/netfilter/xt_connmark.h ++++ b/include/uapi/linux/netfilter/xt_connmark.h +@@ -20,6 +20,11 @@ enum { + }; + + enum { ++ XT_CONNMARK_VALUE = (1 << 0), ++ XT_CONNMARK_DSCP = (1 << 1) ++}; ++ ++enum { + D_SHIFT_LEFT = 0, + D_SHIFT_RIGHT, + }; +@@ -34,6 +39,11 @@ struct xt_connmark_tginfo2 { + __u8 shift_dir, shift_bits, mode; + }; + ++struct xt_connmark_tginfo3 { ++ __u32 ctmark, ctmask, nfmask; ++ __u8 shift_dir, shift_bits, mode, func; ++}; ++ + struct xt_connmark_mtinfo1 { + __u32 mark, mask; + __u8 invert; +--- a/net/netfilter/xt_connmark.c ++++ b/net/netfilter/xt_connmark.c +@@ -24,12 +24,13 @@ MODULE_ALIAS("ipt_connmark"); + MODULE_ALIAS("ip6t_connmark"); + + static unsigned int +-connmark_tg_shift(struct sk_buff *skb, const struct xt_connmark_tginfo2 *info) ++connmark_tg_shift(struct sk_buff *skb, const struct xt_connmark_tginfo3 *info) + { + enum ip_conntrack_info ctinfo; + u_int32_t new_targetmark; + struct nf_conn *ct; + u_int32_t newmark; ++ u_int8_t dscp; + + ct = nf_ct_get(skb, &ctinfo); + if (ct == NULL) +@@ -37,12 +38,24 @@ connmark_tg_shift(struct sk_buff *skb, c + + switch (info->mode) { + case XT_CONNMARK_SET: +- newmark = (ct->mark & ~info->ctmask) ^ info->ctmark; +- if (info->shift_dir == D_SHIFT_RIGHT) +- newmark >>= info->shift_bits; +- else +- newmark <<= info->shift_bits; ++ newmark = ct->mark; ++ if (info->func & XT_CONNMARK_VALUE) { ++ newmark = (newmark & ~info->ctmask) ^ info->ctmark; ++ if (info->shift_dir == D_SHIFT_RIGHT) ++ newmark >>= info->shift_bits; ++ else ++ newmark <<= info->shift_bits; ++ } else if (info->func & XT_CONNMARK_DSCP) { ++ if (skb->protocol == htons(ETH_P_IP)) ++ dscp = ipv4_get_dsfield(ip_hdr(skb)) >> 2; ++ else if (skb->protocol == htons(ETH_P_IPV6)) ++ dscp = ipv6_get_dsfield(ipv6_hdr(skb)) >> 2; ++ else /* protocol doesn't have diffserv */ ++ break; + ++ newmark = (newmark & ~info->ctmark) | ++ (info->ctmask | (dscp << info->shift_bits)); ++ } + if (ct->mark != newmark) { + ct->mark = newmark; + nf_conntrack_event_cache(IPCT_MARK, ct); +@@ -81,20 +94,36 @@ static unsigned int + connmark_tg(struct sk_buff *skb, const struct xt_action_param *par) + { + const struct xt_connmark_tginfo1 *info = par->targinfo; +- const struct xt_connmark_tginfo2 info2 = { ++ const struct xt_connmark_tginfo3 info3 = { + .ctmark = info->ctmark, + .ctmask = info->ctmask, + .nfmask = info->nfmask, + .mode = info->mode, ++ .func = XT_CONNMARK_VALUE + }; + +- return connmark_tg_shift(skb, &info2); ++ return connmark_tg_shift(skb, &info3); + } + + static unsigned int + connmark_tg_v2(struct sk_buff *skb, const struct xt_action_param *par) + { + const struct xt_connmark_tginfo2 *info = par->targinfo; ++ const struct xt_connmark_tginfo3 info3 = { ++ .ctmark = info->ctmark, ++ .ctmask = info->ctmask, ++ .nfmask = info->nfmask, ++ .mode = info->mode, ++ .func = XT_CONNMARK_VALUE ++ }; ++ ++ return connmark_tg_shift(skb, &info3); ++} ++ ++static unsigned int ++connmark_tg_v3(struct sk_buff *skb, const struct xt_action_param *par) ++{ ++ const struct xt_connmark_tginfo3 *info = par->targinfo; + + return connmark_tg_shift(skb, info); + } +@@ -165,6 +194,16 @@ static struct xt_target connmark_tg_reg[ + .targetsize = sizeof(struct xt_connmark_tginfo2), + .destroy = connmark_tg_destroy, + .me = THIS_MODULE, ++ }, ++ { ++ .name = "CONNMARK", ++ .revision = 3, ++ .family = NFPROTO_UNSPEC, ++ .checkentry = connmark_tg_check, ++ .target = connmark_tg_v3, ++ .targetsize = sizeof(struct xt_connmark_tginfo3), ++ .destroy = connmark_tg_destroy, ++ .me = THIS_MODULE, + } + }; + |