diff options
Diffstat (limited to 'target')
4 files changed, 487 insertions, 0 deletions
diff --git a/target/linux/generic/backport-4.19/391-v5.1-sch_cake-Correctly-update-parent-qlen-when-splitting.patch b/target/linux/generic/backport-4.19/391-v5.1-sch_cake-Correctly-update-parent-qlen-when-splitting.patch new file mode 100644 index 0000000000..f6de44568a --- /dev/null +++ b/target/linux/generic/backport-4.19/391-v5.1-sch_cake-Correctly-update-parent-qlen-when-splitting.patch @@ -0,0 +1,50 @@ +From 8c6c37fdc20ec9ffaa342f827a8e20afe736fb0c Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@redhat.com> +Date: Wed, 9 Jan 2019 17:09:44 +0100 +Subject: [PATCH] sch_cake: Correctly update parent qlen when splitting GSO + packets +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +To ensure parent qdiscs have the same notion of the number of enqueued +packets even after splitting a GSO packet, update the qdisc tree with the +number of packets that was added due to the split. + +Reported-by: Pete Heist <pete@heistp.net> +Tested-by: Pete Heist <pete@heistp.net> +Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> +Signed-off-by: David S. Miller <davem@davemloft.net> +Signed-off-by: Kevin Darbyshire-Bryant <ldir@darbyshire-bryant.me.uk> +--- + net/sched/sch_cake.c | 5 +++-- + 1 file changed, 3 insertions(+), 2 deletions(-) + +--- a/net/sched/sch_cake.c ++++ b/net/sched/sch_cake.c +@@ -1666,7 +1666,7 @@ static s32 cake_enqueue(struct sk_buff * + if (skb_is_gso(skb) && q->rate_flags & CAKE_FLAG_SPLIT_GSO) { + struct sk_buff *segs, *nskb; + netdev_features_t features = netif_skb_features(skb); +- unsigned int slen = 0; ++ unsigned int slen = 0, numsegs = 0; + + segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); + if (IS_ERR_OR_NULL(segs)) +@@ -1682,6 +1682,7 @@ static s32 cake_enqueue(struct sk_buff * + flow_queue_add(flow, segs); + + sch->q.qlen++; ++ numsegs++; + slen += segs->len; + q->buffer_used += segs->truesize; + b->packets++; +@@ -1695,7 +1696,7 @@ static s32 cake_enqueue(struct sk_buff * + sch->qstats.backlog += slen; + q->avg_window_bytes += slen; + +- qdisc_tree_reduce_backlog(sch, 1, len); ++ qdisc_tree_reduce_backlog(sch, 1-numsegs, len-slen); + consume_skb(skb); + } else { + /* not splitting */ diff --git a/target/linux/generic/backport-4.19/392-v5.1-sch_cake-Make-the-dual-modes-fairer.patch b/target/linux/generic/backport-4.19/392-v5.1-sch_cake-Make-the-dual-modes-fairer.patch new file mode 100644 index 0000000000..cd94600152 --- /dev/null +++ b/target/linux/generic/backport-4.19/392-v5.1-sch_cake-Make-the-dual-modes-fairer.patch @@ -0,0 +1,217 @@ +From 712639929912c5eefb09facccb48d55b3f72c9f8 Mon Sep 17 00:00:00 2001 +From: George Amanakis <gamanakis@gmail.com> +Date: Fri, 1 Mar 2019 16:04:05 +0100 +Subject: [PATCH] sch_cake: Make the dual modes fairer +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +CAKE host fairness does not work well with TCP flows in dual-srchost and +dual-dsthost setup. The reason is that ACKs generated by TCP flows are +classified as sparse flows, and affect flow isolation from other hosts. Fix +this by calculating host_load based only on the bulk flows a host +generates. In a hash collision the host_bulk_flow_count values must be +decremented on the old hosts and incremented on the new ones *if* the queue +is in the bulk set. + +Reported-by: Pete Heist <peteheist@gmail.com> +Signed-off-by: George Amanakis <gamanakis@gmail.com> +Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> +Signed-off-by: David S. Miller <davem@davemloft.net> +Signed-off-by: Kevin Darbyshire-Bryant <ldir@darbyshire-bryant.me.uk> +--- + net/sched/sch_cake.c | 92 ++++++++++++++++++++++++++++++-------------- + 1 file changed, 63 insertions(+), 29 deletions(-) + +--- a/net/sched/sch_cake.c ++++ b/net/sched/sch_cake.c +@@ -138,8 +138,8 @@ struct cake_flow { + struct cake_host { + u32 srchost_tag; + u32 dsthost_tag; +- u16 srchost_refcnt; +- u16 dsthost_refcnt; ++ u16 srchost_bulk_flow_count; ++ u16 dsthost_bulk_flow_count; + }; + + struct cake_heap_entry { +@@ -746,8 +746,10 @@ skip_hash: + * queue, accept the collision, update the host tags. + */ + q->way_collisions++; +- q->hosts[q->flows[reduced_hash].srchost].srchost_refcnt--; +- q->hosts[q->flows[reduced_hash].dsthost].dsthost_refcnt--; ++ if (q->flows[outer_hash + k].set == CAKE_SET_BULK) { ++ q->hosts[q->flows[reduced_hash].srchost].srchost_bulk_flow_count--; ++ q->hosts[q->flows[reduced_hash].dsthost].dsthost_bulk_flow_count--; ++ } + allocate_src = cake_dsrc(flow_mode); + allocate_dst = cake_ddst(flow_mode); + found: +@@ -767,13 +769,14 @@ found: + } + for (i = 0; i < CAKE_SET_WAYS; + i++, k = (k + 1) % CAKE_SET_WAYS) { +- if (!q->hosts[outer_hash + k].srchost_refcnt) ++ if (!q->hosts[outer_hash + k].srchost_bulk_flow_count) + break; + } + q->hosts[outer_hash + k].srchost_tag = srchost_hash; + found_src: + srchost_idx = outer_hash + k; +- q->hosts[srchost_idx].srchost_refcnt++; ++ if (q->flows[reduced_hash].set == CAKE_SET_BULK) ++ q->hosts[srchost_idx].srchost_bulk_flow_count++; + q->flows[reduced_hash].srchost = srchost_idx; + } + +@@ -789,13 +792,14 @@ found_src: + } + for (i = 0; i < CAKE_SET_WAYS; + i++, k = (k + 1) % CAKE_SET_WAYS) { +- if (!q->hosts[outer_hash + k].dsthost_refcnt) ++ if (!q->hosts[outer_hash + k].dsthost_bulk_flow_count) + break; + } + q->hosts[outer_hash + k].dsthost_tag = dsthost_hash; + found_dst: + dsthost_idx = outer_hash + k; +- q->hosts[dsthost_idx].dsthost_refcnt++; ++ if (q->flows[reduced_hash].set == CAKE_SET_BULK) ++ q->hosts[dsthost_idx].dsthost_bulk_flow_count++; + q->flows[reduced_hash].dsthost = dsthost_idx; + } + } +@@ -1793,20 +1797,30 @@ static s32 cake_enqueue(struct sk_buff * + b->sparse_flow_count++; + + if (cake_dsrc(q->flow_mode)) +- host_load = max(host_load, srchost->srchost_refcnt); ++ host_load = max(host_load, srchost->srchost_bulk_flow_count); + + if (cake_ddst(q->flow_mode)) +- host_load = max(host_load, dsthost->dsthost_refcnt); ++ host_load = max(host_load, dsthost->dsthost_bulk_flow_count); + + flow->deficit = (b->flow_quantum * + quantum_div[host_load]) >> 16; + } else if (flow->set == CAKE_SET_SPARSE_WAIT) { ++ struct cake_host *srchost = &b->hosts[flow->srchost]; ++ struct cake_host *dsthost = &b->hosts[flow->dsthost]; ++ + /* this flow was empty, accounted as a sparse flow, but actually + * in the bulk rotation. + */ + flow->set = CAKE_SET_BULK; + b->sparse_flow_count--; + b->bulk_flow_count++; ++ ++ if (cake_dsrc(q->flow_mode)) ++ srchost->srchost_bulk_flow_count++; ++ ++ if (cake_ddst(q->flow_mode)) ++ dsthost->dsthost_bulk_flow_count++; ++ + } + + if (q->buffer_used > q->buffer_max_used) +@@ -1974,23 +1988,8 @@ retry: + dsthost = &b->hosts[flow->dsthost]; + host_load = 1; + +- if (cake_dsrc(q->flow_mode)) +- host_load = max(host_load, srchost->srchost_refcnt); +- +- if (cake_ddst(q->flow_mode)) +- host_load = max(host_load, dsthost->dsthost_refcnt); +- +- WARN_ON(host_load > CAKE_QUEUES); +- + /* flow isolation (DRR++) */ + if (flow->deficit <= 0) { +- /* The shifted prandom_u32() is a way to apply dithering to +- * avoid accumulating roundoff errors +- */ +- flow->deficit += (b->flow_quantum * quantum_div[host_load] + +- (prandom_u32() >> 16)) >> 16; +- list_move_tail(&flow->flowchain, &b->old_flows); +- + /* Keep all flows with deficits out of the sparse and decaying + * rotations. No non-empty flow can go into the decaying + * rotation, so they can't get deficits +@@ -1999,6 +1998,13 @@ retry: + if (flow->head) { + b->sparse_flow_count--; + b->bulk_flow_count++; ++ ++ if (cake_dsrc(q->flow_mode)) ++ srchost->srchost_bulk_flow_count++; ++ ++ if (cake_ddst(q->flow_mode)) ++ dsthost->dsthost_bulk_flow_count++; ++ + flow->set = CAKE_SET_BULK; + } else { + /* we've moved it to the bulk rotation for +@@ -2008,6 +2014,22 @@ retry: + flow->set = CAKE_SET_SPARSE_WAIT; + } + } ++ ++ if (cake_dsrc(q->flow_mode)) ++ host_load = max(host_load, srchost->srchost_bulk_flow_count); ++ ++ if (cake_ddst(q->flow_mode)) ++ host_load = max(host_load, dsthost->dsthost_bulk_flow_count); ++ ++ WARN_ON(host_load > CAKE_QUEUES); ++ ++ /* The shifted prandom_u32() is a way to apply dithering to ++ * avoid accumulating roundoff errors ++ */ ++ flow->deficit += (b->flow_quantum * quantum_div[host_load] + ++ (prandom_u32() >> 16)) >> 16; ++ list_move_tail(&flow->flowchain, &b->old_flows); ++ + goto retry; + } + +@@ -2028,6 +2050,13 @@ retry: + &b->decaying_flows); + if (flow->set == CAKE_SET_BULK) { + b->bulk_flow_count--; ++ ++ if (cake_dsrc(q->flow_mode)) ++ srchost->srchost_bulk_flow_count--; ++ ++ if (cake_ddst(q->flow_mode)) ++ dsthost->dsthost_bulk_flow_count--; ++ + b->decaying_flow_count++; + } else if (flow->set == CAKE_SET_SPARSE || + flow->set == CAKE_SET_SPARSE_WAIT) { +@@ -2041,14 +2070,19 @@ retry: + if (flow->set == CAKE_SET_SPARSE || + flow->set == CAKE_SET_SPARSE_WAIT) + b->sparse_flow_count--; +- else if (flow->set == CAKE_SET_BULK) ++ else if (flow->set == CAKE_SET_BULK) { + b->bulk_flow_count--; +- else ++ ++ if (cake_dsrc(q->flow_mode)) ++ srchost->srchost_bulk_flow_count--; ++ ++ if (cake_ddst(q->flow_mode)) ++ dsthost->dsthost_bulk_flow_count--; ++ ++ } else + b->decaying_flow_count--; + + flow->set = CAKE_SET_NONE; +- srchost->srchost_refcnt--; +- dsthost->dsthost_refcnt--; + } + goto begin; + } diff --git a/target/linux/generic/backport-4.19/393-v5.1-sch_cake-Permit-use-of-connmarks-as-tin-classifiers.patch b/target/linux/generic/backport-4.19/393-v5.1-sch_cake-Permit-use-of-connmarks-as-tin-classifiers.patch new file mode 100644 index 0000000000..9ac1388c98 --- /dev/null +++ b/target/linux/generic/backport-4.19/393-v5.1-sch_cake-Permit-use-of-connmarks-as-tin-classifiers.patch @@ -0,0 +1,118 @@ +From 0b5c7efdfc6e389ec6840579fe90bdb6f42b08dc Mon Sep 17 00:00:00 2001 +From: Kevin Darbyshire-Bryant <ldir@darbyshire-bryant.me.uk> +Date: Fri, 1 Mar 2019 16:04:05 +0100 +Subject: [PATCH] sch_cake: Permit use of connmarks as tin classifiers +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +Add flag 'FWMARK' to enable use of firewall connmarks as tin selector. +The connmark (skbuff->mark) needs to be in the range 1->tin_cnt ie. +for diffserv3 the mark needs to be 1->3. + +Background + +Typically CAKE uses DSCP as the basis for tin selection. DSCP values +are relatively easily changed as part of the egress path, usually with +iptables & the mangle table, ingress is more challenging. CAKE is often +used on the WAN interface of a residential gateway where passthrough of +DSCP from the ISP is either missing or set to unhelpful values thus use +of ingress DSCP values for tin selection isn't helpful in that +environment. + +An approach to solving the ingress tin selection problem is to use +CAKE's understanding of tc filters. Naive tc filters could match on +source/destination port numbers and force tin selection that way, but +multiple filters don't scale particularly well as each filter must be +traversed whether it matches or not. e.g. a simple example to map 3 +firewall marks to tins: + +MAJOR=$( tc qdisc show dev $DEV | head -1 | awk '{print $3}' ) +tc filter add dev $DEV parent $MAJOR protocol all handle 0x01 fw action skbedit priority ${MAJOR}1 +tc filter add dev $DEV parent $MAJOR protocol all handle 0x02 fw action skbedit priority ${MAJOR}2 +tc filter add dev $DEV parent $MAJOR protocol all handle 0x03 fw action skbedit priority ${MAJOR}3 + +Another option is to use eBPF cls_act with tc filters e.g. + +MAJOR=$( tc qdisc show dev $DEV | head -1 | awk '{print $3}' ) +tc filter add dev $DEV parent $MAJOR bpf da obj my-bpf-fwmark-to-class.o + +This has the disadvantages of a) needing someone to write & maintain +the bpf program, b) a bpf toolchain to compile it and c) needing to +hardcode the major number in the bpf program so it matches the cake +instance (or forcing the cake instance to a particular major number) +since the major number cannot be passed to the bpf program via tc +command line. + +As already hinted at by the previous examples, it would be helpful +to associate tins with something that survives the Internet path and +ideally allows tin selection on both egress and ingress. Netfilter's +conntrack permits setting an identifying mark on a connection which +can also be restored to an ingress packet with tc action connmark e.g. + +tc filter add dev eth0 parent ffff: protocol all prio 10 u32 \ + match u32 0 0 flowid 1:1 action connmark action mirred egress redirect dev ifb1 + +Since tc's connmark action has restored any connmark into skb->mark, +any of the previous solutions are based upon it and in one form or +another copy that mark to the skb->priority field where again CAKE +picks this up. + +This change cuts out at least one of the (less intuitive & +non-scalable) middlemen and permit direct access to skb->mark. + +Signed-off-by: Kevin Darbyshire-Bryant <ldir@darbyshire-bryant.me.uk> +Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> +Signed-off-by: David S. Miller <davem@davemloft.net> +--- + include/uapi/linux/pkt_sched.h | 1 + + net/sched/sch_cake.c | 34 +++++++++++++++++++++++++++------- + 2 files changed, 28 insertions(+), 7 deletions(-) + +--- a/include/uapi/linux/pkt_sched.h ++++ b/include/uapi/linux/pkt_sched.h +@@ -991,6 +991,7 @@ enum { + TCA_CAKE_INGRESS, + TCA_CAKE_ACK_FILTER, + TCA_CAKE_SPLIT_GSO, ++ TCA_CAKE_FWMARK, + __TCA_CAKE_MAX + }; + #define TCA_CAKE_MAX (__TCA_CAKE_MAX - 1) +--- a/net/sched/sch_cake.c ++++ b/net/sched/sch_cake.c +@@ -258,7 +258,8 @@ enum { + CAKE_FLAG_AUTORATE_INGRESS = BIT(1), + CAKE_FLAG_INGRESS = BIT(2), + CAKE_FLAG_WASH = BIT(3), +- CAKE_FLAG_SPLIT_GSO = BIT(4) ++ CAKE_FLAG_SPLIT_GSO = BIT(4), ++ CAKE_FLAG_FWMARK = BIT(5) + }; + + /* COBALT operates the Codel and BLUE algorithms in parallel, in order to +@@ -2623,6 +2624,13 @@ static int cake_change(struct Qdisc *sch + q->rate_flags &= ~CAKE_FLAG_SPLIT_GSO; + } + ++ if (tb[TCA_CAKE_FWMARK]) { ++ if (!!nla_get_u32(tb[TCA_CAKE_FWMARK])) ++ q->rate_flags |= CAKE_FLAG_FWMARK; ++ else ++ q->rate_flags &= ~CAKE_FLAG_FWMARK; ++ } ++ + if (q->tins) { + sch_tree_lock(sch); + cake_reconfigure(sch); +@@ -2782,6 +2790,10 @@ static int cake_dump(struct Qdisc *sch, + !!(q->rate_flags & CAKE_FLAG_SPLIT_GSO))) + goto nla_put_failure; + ++ if (nla_put_u32(skb, TCA_CAKE_FWMARK, ++ !!(q->rate_flags & CAKE_FLAG_FWMARK))) ++ goto nla_put_failure; ++ + return nla_nest_end(skb, opts); + + nla_put_failure: diff --git a/target/linux/generic/backport-4.19/394-v5.1-sch_cake-Interpret-fwmark-parameter-as-a-bitmask.patch b/target/linux/generic/backport-4.19/394-v5.1-sch_cake-Interpret-fwmark-parameter-as-a-bitmask.patch new file mode 100644 index 0000000000..325f5719d7 --- /dev/null +++ b/target/linux/generic/backport-4.19/394-v5.1-sch_cake-Interpret-fwmark-parameter-as-a-bitmask.patch @@ -0,0 +1,102 @@ +From eab2fc822af38f31fd5f4e731b5d10b94904d919 Mon Sep 17 00:00:00 2001 +From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@redhat.com> +Date: Thu, 14 Mar 2019 23:08:22 +0100 +Subject: [PATCH] sch_cake: Interpret fwmark parameter as a bitmask +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +We initially interpreted the fwmark parameter as a flag that simply turned +on the feature, using the whole skb->mark field as the index into the CAKE +tin_order array. However, it is quite common for different applications to +use different parts of the mask field for their own purposes, each using a +different mask. + +Support this use of subsets of the mark by interpreting the TCA_CAKE_FWMARK +parameter as a bitmask to apply to the fwmark field when reading it. The +result will be right-shifted by the number of unset lower bits of the mask +before looking up the tin. + +In the original commit message we also failed to credit Felix Resch with +originally suggesting the fwmark feature back in 2017; so the Suggested-By +in this commit covers the whole fwmark feature. + +Fixes: 0b5c7efdfc6e ("sch_cake: Permit use of connmarks as tin classifiers") +Suggested-by: Felix Resch <fuller@beif.de> +Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> +Signed-off-by: David S. Miller <davem@davemloft.net> +Signed-off-by: Kevin Darbyshire-Bryant <ldir@darbyshire-bryant.me.uk> +--- + net/sched/sch_cake.c | 25 ++++++++++++------------- + 1 file changed, 12 insertions(+), 13 deletions(-) + +--- a/net/sched/sch_cake.c ++++ b/net/sched/sch_cake.c +@@ -211,6 +211,9 @@ struct cake_sched_data { + u8 ack_filter; + u8 atm_mode; + ++ u32 fwmark_mask; ++ u16 fwmark_shft; ++ + /* time_next = time_this + ((len * rate_ns) >> rate_shft) */ + u16 rate_shft; + ktime_t time_next_packet; +@@ -258,8 +261,7 @@ enum { + CAKE_FLAG_AUTORATE_INGRESS = BIT(1), + CAKE_FLAG_INGRESS = BIT(2), + CAKE_FLAG_WASH = BIT(3), +- CAKE_FLAG_SPLIT_GSO = BIT(4), +- CAKE_FLAG_FWMARK = BIT(5) ++ CAKE_FLAG_SPLIT_GSO = BIT(4) + }; + + /* COBALT operates the Codel and BLUE algorithms in parallel, in order to +@@ -1554,7 +1556,7 @@ static struct cake_tin_data *cake_select + struct sk_buff *skb) + { + struct cake_sched_data *q = qdisc_priv(sch); +- u32 tin; ++ u32 tin, mark; + u8 dscp; + + /* Tin selection: Default to diffserv-based selection, allow overriding +@@ -1562,6 +1564,7 @@ static struct cake_tin_data *cake_select + */ + dscp = cake_handle_diffserv(skb, + q->rate_flags & CAKE_FLAG_WASH); ++ mark = (skb->mark & q->fwmark_mask) >> q->fwmark_shft; + + if (q->tin_mode == CAKE_DIFFSERV_BESTEFFORT) + tin = 0; +@@ -2178,6 +2181,7 @@ static const struct nla_policy cake_poli + [TCA_CAKE_MPU] = { .type = NLA_U32 }, + [TCA_CAKE_INGRESS] = { .type = NLA_U32 }, + [TCA_CAKE_ACK_FILTER] = { .type = NLA_U32 }, ++ [TCA_CAKE_FWMARK] = { .type = NLA_U32 }, + }; + + static void cake_set_rate(struct cake_tin_data *b, u64 rate, u32 mtu, +@@ -2625,10 +2629,8 @@ static int cake_change(struct Qdisc *sch + } + + if (tb[TCA_CAKE_FWMARK]) { +- if (!!nla_get_u32(tb[TCA_CAKE_FWMARK])) +- q->rate_flags |= CAKE_FLAG_FWMARK; +- else +- q->rate_flags &= ~CAKE_FLAG_FWMARK; ++ q->fwmark_mask = nla_get_u32(tb[TCA_CAKE_FWMARK]); ++ q->fwmark_shft = q->fwmark_mask ? __ffs(q->fwmark_mask) : 0; + } + + if (q->tins) { +@@ -2790,8 +2792,7 @@ static int cake_dump(struct Qdisc *sch, + !!(q->rate_flags & CAKE_FLAG_SPLIT_GSO))) + goto nla_put_failure; + +- if (nla_put_u32(skb, TCA_CAKE_FWMARK, +- !!(q->rate_flags & CAKE_FLAG_FWMARK))) ++ if (nla_put_u32(skb, TCA_CAKE_FWMARK, q->fwmark_mask)) + goto nla_put_failure; + + return nla_nest_end(skb, opts); |