--- /dev/null
+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;
+ }
--- /dev/null
+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:
--- /dev/null
+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);
+++ /dev/null
-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;
- }
+++ /dev/null
-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:
--- /dev/null
+From d7e1738f0a0b0573ac93cf570ba3df9dee61b68e Mon Sep 17 00:00:00 2001
+From: Kevin 'ldir' Darbyshire-Bryant <ldir@darbyshire-bryant.me.uk>
+Date: Wed, 18 Dec 2019 14:05:13 +0000
+Subject: [PATCH 2/2] sch_cake: drop unused variable tin_quantum_prio
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+Turns out tin_quantum_prio isn't used anymore and is a leftover from a
+previous implementation of diffserv tins. Since the variable isn't used
+in any calculations it can be eliminated.
+
+Drop variable and places where it was set. Rename remaining variable
+and consolidate naming of intermediate variables that set it.
+
+Signed-off-by: Kevin Darbyshire-Bryant <ldir@darbyshire-bryant.me.uk>
+Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+---
+ net/sched/sch_cake.c | 59 ++++++++++++++------------------------------
+ 1 file changed, 18 insertions(+), 41 deletions(-)
+
+--- a/net/sched/sch_cake.c
++++ b/net/sched/sch_cake.c
+@@ -173,8 +173,7 @@ struct cake_tin_data {
+ u64 tin_rate_bps;
+ u16 tin_rate_shft;
+
+- u16 tin_quantum_prio;
+- u16 tin_quantum_band;
++ u16 tin_quantum;
+ s32 tin_deficit;
+ u32 tin_backlog;
+ u32 tin_dropped;
+@@ -1916,7 +1915,7 @@ begin:
+ while (b->tin_deficit < 0 ||
+ !(b->sparse_flow_count + b->bulk_flow_count)) {
+ if (b->tin_deficit <= 0)
+- b->tin_deficit += b->tin_quantum_band;
++ b->tin_deficit += b->tin_quantum;
+ if (b->sparse_flow_count + b->bulk_flow_count)
+ empty = false;
+
+@@ -2237,8 +2236,7 @@ static int cake_config_besteffort(struct
+
+ cake_set_rate(b, rate, mtu,
+ us_to_ns(q->target), us_to_ns(q->interval));
+- b->tin_quantum_band = 65535;
+- b->tin_quantum_prio = 65535;
++ b->tin_quantum = 65535;
+
+ return 0;
+ }
+@@ -2249,8 +2247,7 @@ static int cake_config_precedence(struct
+ struct cake_sched_data *q = qdisc_priv(sch);
+ u32 mtu = psched_mtu(qdisc_dev(sch));
+ u64 rate = q->rate_bps;
+- u32 quantum1 = 256;
+- u32 quantum2 = 256;
++ u32 quantum = 256;
+ u32 i;
+
+ q->tin_cnt = 8;
+@@ -2263,18 +2260,14 @@ static int cake_config_precedence(struct
+ cake_set_rate(b, rate, mtu, us_to_ns(q->target),
+ us_to_ns(q->interval));
+
+- b->tin_quantum_prio = max_t(u16, 1U, quantum1);
+- b->tin_quantum_band = max_t(u16, 1U, quantum2);
++ b->tin_quantum = max_t(u16, 1U, quantum);
+
+ /* calculate next class's parameters */
+ rate *= 7;
+ rate >>= 3;
+
+- quantum1 *= 3;
+- quantum1 >>= 1;
+-
+- quantum2 *= 7;
+- quantum2 >>= 3;
++ quantum *= 7;
++ quantum >>= 3;
+ }
+
+ return 0;
+@@ -2343,8 +2336,7 @@ static int cake_config_diffserv8(struct
+ struct cake_sched_data *q = qdisc_priv(sch);
+ u32 mtu = psched_mtu(qdisc_dev(sch));
+ u64 rate = q->rate_bps;
+- u32 quantum1 = 256;
+- u32 quantum2 = 256;
++ u32 quantum = 256;
+ u32 i;
+
+ q->tin_cnt = 8;
+@@ -2360,18 +2352,14 @@ static int cake_config_diffserv8(struct
+ cake_set_rate(b, rate, mtu, us_to_ns(q->target),
+ us_to_ns(q->interval));
+
+- b->tin_quantum_prio = max_t(u16, 1U, quantum1);
+- b->tin_quantum_band = max_t(u16, 1U, quantum2);
++ b->tin_quantum = max_t(u16, 1U, quantum);
+
+ /* calculate next class's parameters */
+ rate *= 7;
+ rate >>= 3;
+
+- quantum1 *= 3;
+- quantum1 >>= 1;
+-
+- quantum2 *= 7;
+- quantum2 >>= 3;
++ quantum *= 7;
++ quantum >>= 3;
+ }
+
+ return 0;
+@@ -2410,17 +2398,11 @@ static int cake_config_diffserv4(struct
+ cake_set_rate(&q->tins[3], rate >> 2, mtu,
+ us_to_ns(q->target), us_to_ns(q->interval));
+
+- /* priority weights */
+- q->tins[0].tin_quantum_prio = quantum;
+- q->tins[1].tin_quantum_prio = quantum >> 4;
+- q->tins[2].tin_quantum_prio = quantum << 2;
+- q->tins[3].tin_quantum_prio = quantum << 4;
+-
+ /* bandwidth-sharing weights */
+- q->tins[0].tin_quantum_band = quantum;
+- q->tins[1].tin_quantum_band = quantum >> 4;
+- q->tins[2].tin_quantum_band = quantum >> 1;
+- q->tins[3].tin_quantum_band = quantum >> 2;
++ q->tins[0].tin_quantum = quantum;
++ q->tins[1].tin_quantum = quantum >> 4;
++ q->tins[2].tin_quantum = quantum >> 1;
++ q->tins[3].tin_quantum = quantum >> 2;
+
+ return 0;
+ }
+@@ -2451,15 +2433,10 @@ static int cake_config_diffserv3(struct
+ cake_set_rate(&q->tins[2], rate >> 2, mtu,
+ us_to_ns(q->target), us_to_ns(q->interval));
+
+- /* priority weights */
+- q->tins[0].tin_quantum_prio = quantum;
+- q->tins[1].tin_quantum_prio = quantum >> 4;
+- q->tins[2].tin_quantum_prio = quantum << 4;
+-
+ /* bandwidth-sharing weights */
+- q->tins[0].tin_quantum_band = quantum;
+- q->tins[1].tin_quantum_band = quantum >> 4;
+- q->tins[2].tin_quantum_band = quantum >> 2;
++ q->tins[0].tin_quantum = quantum;
++ q->tins[1].tin_quantum = quantum >> 4;
++ q->tins[2].tin_quantum = quantum >> 2;
+
+ return 0;
+ }
+++ /dev/null
-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);
--- /dev/null
+From b3c424eb6a1a3c485de64619418a471dee6ce849 Mon Sep 17 00:00:00 2001
+From: Victorien Molle <victorien.molle@wifirst.fr>
+Date: Mon, 2 Dec 2019 15:11:38 +0100
+Subject: [PATCH] sch_cake: Add missing NLA policy entry TCA_CAKE_SPLIT_GSO
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+This field has never been checked since introduction in mainline kernel
+
+Signed-off-by: Victorien Molle <victorien.molle@wifirst.fr>
+Signed-off-by: Florent Fourcot <florent.fourcot@wifirst.fr>
+Fixes: 2db6dc2662ba "sch_cake: Make gso-splitting configurable from userspace"
+Acked-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 | 1 +
+ 1 file changed, 1 insertion(+)
+
+--- a/net/sched/sch_cake.c
++++ b/net/sched/sch_cake.c
+@@ -2180,6 +2180,7 @@ 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_SPLIT_GSO] = { .type = NLA_U32 },
+ [TCA_CAKE_FWMARK] = { .type = NLA_U32 },
+ };
+
+++ /dev/null
-From d7e1738f0a0b0573ac93cf570ba3df9dee61b68e Mon Sep 17 00:00:00 2001
-From: Kevin 'ldir' Darbyshire-Bryant <ldir@darbyshire-bryant.me.uk>
-Date: Wed, 18 Dec 2019 14:05:13 +0000
-Subject: [PATCH 2/2] sch_cake: drop unused variable tin_quantum_prio
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-Turns out tin_quantum_prio isn't used anymore and is a leftover from a
-previous implementation of diffserv tins. Since the variable isn't used
-in any calculations it can be eliminated.
-
-Drop variable and places where it was set. Rename remaining variable
-and consolidate naming of intermediate variables that set it.
-
-Signed-off-by: Kevin Darbyshire-Bryant <ldir@darbyshire-bryant.me.uk>
-Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
----
- net/sched/sch_cake.c | 59 ++++++++++++++------------------------------
- 1 file changed, 18 insertions(+), 41 deletions(-)
-
---- a/net/sched/sch_cake.c
-+++ b/net/sched/sch_cake.c
-@@ -173,8 +173,7 @@ struct cake_tin_data {
- u64 tin_rate_bps;
- u16 tin_rate_shft;
-
-- u16 tin_quantum_prio;
-- u16 tin_quantum_band;
-+ u16 tin_quantum;
- s32 tin_deficit;
- u32 tin_backlog;
- u32 tin_dropped;
-@@ -1916,7 +1915,7 @@ begin:
- while (b->tin_deficit < 0 ||
- !(b->sparse_flow_count + b->bulk_flow_count)) {
- if (b->tin_deficit <= 0)
-- b->tin_deficit += b->tin_quantum_band;
-+ b->tin_deficit += b->tin_quantum;
- if (b->sparse_flow_count + b->bulk_flow_count)
- empty = false;
-
-@@ -2237,8 +2236,7 @@ static int cake_config_besteffort(struct
-
- cake_set_rate(b, rate, mtu,
- us_to_ns(q->target), us_to_ns(q->interval));
-- b->tin_quantum_band = 65535;
-- b->tin_quantum_prio = 65535;
-+ b->tin_quantum = 65535;
-
- return 0;
- }
-@@ -2249,8 +2247,7 @@ static int cake_config_precedence(struct
- struct cake_sched_data *q = qdisc_priv(sch);
- u32 mtu = psched_mtu(qdisc_dev(sch));
- u64 rate = q->rate_bps;
-- u32 quantum1 = 256;
-- u32 quantum2 = 256;
-+ u32 quantum = 256;
- u32 i;
-
- q->tin_cnt = 8;
-@@ -2263,18 +2260,14 @@ static int cake_config_precedence(struct
- cake_set_rate(b, rate, mtu, us_to_ns(q->target),
- us_to_ns(q->interval));
-
-- b->tin_quantum_prio = max_t(u16, 1U, quantum1);
-- b->tin_quantum_band = max_t(u16, 1U, quantum2);
-+ b->tin_quantum = max_t(u16, 1U, quantum);
-
- /* calculate next class's parameters */
- rate *= 7;
- rate >>= 3;
-
-- quantum1 *= 3;
-- quantum1 >>= 1;
--
-- quantum2 *= 7;
-- quantum2 >>= 3;
-+ quantum *= 7;
-+ quantum >>= 3;
- }
-
- return 0;
-@@ -2343,8 +2336,7 @@ static int cake_config_diffserv8(struct
- struct cake_sched_data *q = qdisc_priv(sch);
- u32 mtu = psched_mtu(qdisc_dev(sch));
- u64 rate = q->rate_bps;
-- u32 quantum1 = 256;
-- u32 quantum2 = 256;
-+ u32 quantum = 256;
- u32 i;
-
- q->tin_cnt = 8;
-@@ -2360,18 +2352,14 @@ static int cake_config_diffserv8(struct
- cake_set_rate(b, rate, mtu, us_to_ns(q->target),
- us_to_ns(q->interval));
-
-- b->tin_quantum_prio = max_t(u16, 1U, quantum1);
-- b->tin_quantum_band = max_t(u16, 1U, quantum2);
-+ b->tin_quantum = max_t(u16, 1U, quantum);
-
- /* calculate next class's parameters */
- rate *= 7;
- rate >>= 3;
-
-- quantum1 *= 3;
-- quantum1 >>= 1;
--
-- quantum2 *= 7;
-- quantum2 >>= 3;
-+ quantum *= 7;
-+ quantum >>= 3;
- }
-
- return 0;
-@@ -2410,17 +2398,11 @@ static int cake_config_diffserv4(struct
- cake_set_rate(&q->tins[3], rate >> 2, mtu,
- us_to_ns(q->target), us_to_ns(q->interval));
-
-- /* priority weights */
-- q->tins[0].tin_quantum_prio = quantum;
-- q->tins[1].tin_quantum_prio = quantum >> 4;
-- q->tins[2].tin_quantum_prio = quantum << 2;
-- q->tins[3].tin_quantum_prio = quantum << 4;
--
- /* bandwidth-sharing weights */
-- q->tins[0].tin_quantum_band = quantum;
-- q->tins[1].tin_quantum_band = quantum >> 4;
-- q->tins[2].tin_quantum_band = quantum >> 1;
-- q->tins[3].tin_quantum_band = quantum >> 2;
-+ q->tins[0].tin_quantum = quantum;
-+ q->tins[1].tin_quantum = quantum >> 4;
-+ q->tins[2].tin_quantum = quantum >> 1;
-+ q->tins[3].tin_quantum = quantum >> 2;
-
- return 0;
- }
-@@ -2451,15 +2433,10 @@ static int cake_config_diffserv3(struct
- cake_set_rate(&q->tins[2], rate >> 2, mtu,
- us_to_ns(q->target), us_to_ns(q->interval));
-
-- /* priority weights */
-- q->tins[0].tin_quantum_prio = quantum;
-- q->tins[1].tin_quantum_prio = quantum >> 4;
-- q->tins[2].tin_quantum_prio = quantum << 4;
--
- /* bandwidth-sharing weights */
-- q->tins[0].tin_quantum_band = quantum;
-- q->tins[1].tin_quantum_band = quantum >> 4;
-- q->tins[2].tin_quantum_band = quantum >> 2;
-+ q->tins[0].tin_quantum = quantum;
-+ q->tins[1].tin_quantum = quantum >> 4;
-+ q->tins[2].tin_quantum = quantum >> 2;
-
- return 0;
- }
+++ /dev/null
-From b3c424eb6a1a3c485de64619418a471dee6ce849 Mon Sep 17 00:00:00 2001
-From: Victorien Molle <victorien.molle@wifirst.fr>
-Date: Mon, 2 Dec 2019 15:11:38 +0100
-Subject: [PATCH] sch_cake: Add missing NLA policy entry TCA_CAKE_SPLIT_GSO
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-This field has never been checked since introduction in mainline kernel
-
-Signed-off-by: Victorien Molle <victorien.molle@wifirst.fr>
-Signed-off-by: Florent Fourcot <florent.fourcot@wifirst.fr>
-Fixes: 2db6dc2662ba "sch_cake: Make gso-splitting configurable from userspace"
-Acked-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 | 1 +
- 1 file changed, 1 insertion(+)
-
---- a/net/sched/sch_cake.c
-+++ b/net/sched/sch_cake.c
-@@ -2180,6 +2180,7 @@ 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_SPLIT_GSO] = { .type = NLA_U32 },
- [TCA_CAKE_FWMARK] = { .type = NLA_U32 },
- };
-
--- /dev/null
+From b0c19ed6088ab41dd2a727b60594b7297c15d6ce Mon Sep 17 00:00:00 2001
+From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@redhat.com>
+Date: Fri, 29 May 2020 14:43:44 +0200
+Subject: [PATCH] sch_cake: Take advantage of skb->hash where appropriate
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+While the other fq-based qdiscs take advantage of skb->hash and doesn't
+recompute it if it is already set, sch_cake does not.
+
+This was a deliberate choice because sch_cake hashes various parts of the
+packet header to support its advanced flow isolation modes. However,
+foregoing the use of skb->hash entirely loses a few important benefits:
+
+- When skb->hash is set by hardware, a few CPU cycles can be saved by not
+ hashing again in software.
+
+- Tunnel encapsulations will generally preserve the value of skb->hash from
+ before the encapsulation, which allows flow-based qdiscs to distinguish
+ between flows even though the outer packet header no longer has flow
+ information.
+
+It turns out that we can preserve these desirable properties in many cases,
+while still supporting the advanced flow isolation properties of sch_cake.
+This patch does so by reusing the skb->hash value as the flow_hash part of
+the hashing procedure in cake_hash() only in the following conditions:
+
+- If the skb->hash is marked as covering the flow headers (skb->l4_hash is
+ set)
+
+AND
+
+- NAT header rewriting is either disabled, or did not change any values
+ used for hashing. The latter is important to match local-origin packets
+ such as those of a tunnel endpoint.
+
+The immediate motivation for fixing this was the recent patch to WireGuard
+to preserve the skb->hash on encapsulation. As such, this is also what I
+tested against; with this patch, added latency under load for competing
+flows drops from ~8 ms to sub-1ms on an RRUL test over a WireGuard tunnel
+going through a virtual link shaped to 1Gbps using sch_cake. This matches
+the results we saw with a similar setup using sch_fq_codel when testing the
+WireGuard patch.
+
+Fixes: 046f6fd5daef ("sched: Add Common Applications Kept Enhanced (cake) qdisc")
+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 | 65 ++++++++++++++++++++++++++++++++++----------
+ 1 file changed, 51 insertions(+), 14 deletions(-)
+
+--- a/net/sched/sch_cake.c
++++ b/net/sched/sch_cake.c
+@@ -585,26 +585,48 @@ static bool cobalt_should_drop(struct co
+ return drop;
+ }
+
+-static void cake_update_flowkeys(struct flow_keys *keys,
++static bool cake_update_flowkeys(struct flow_keys *keys,
+ const struct sk_buff *skb)
+ {
+ #if IS_ENABLED(CONFIG_NF_CONNTRACK)
+ struct nf_conntrack_tuple tuple = {};
+- bool rev = !skb->_nfct;
++ bool rev = !skb->_nfct, upd = false;
++ __be32 ip;
+
+ if (tc_skb_protocol(skb) != htons(ETH_P_IP))
+- return;
++ return false;
+
+ if (!nf_ct_get_tuple_skb(&tuple, skb))
+- return;
++ return false;
+
+- keys->addrs.v4addrs.src = rev ? tuple.dst.u3.ip : tuple.src.u3.ip;
+- keys->addrs.v4addrs.dst = rev ? tuple.src.u3.ip : tuple.dst.u3.ip;
++ ip = rev ? tuple.dst.u3.ip : tuple.src.u3.ip;
++ if (ip != keys->addrs.v4addrs.src) {
++ keys->addrs.v4addrs.src = ip;
++ upd = true;
++ }
++ ip = rev ? tuple.src.u3.ip : tuple.dst.u3.ip;
++ if (ip != keys->addrs.v4addrs.dst) {
++ keys->addrs.v4addrs.dst = ip;
++ upd = true;
++ }
+
+ if (keys->ports.ports) {
+- keys->ports.src = rev ? tuple.dst.u.all : tuple.src.u.all;
+- keys->ports.dst = rev ? tuple.src.u.all : tuple.dst.u.all;
++ __be16 port;
++
++ port = rev ? tuple.dst.u.all : tuple.src.u.all;
++ if (port != keys->ports.src) {
++ keys->ports.src = port;
++ upd = true;
++ }
++ port = rev ? tuple.src.u.all : tuple.dst.u.all;
++ if (port != keys->ports.dst) {
++ port = keys->ports.dst;
++ upd = true;
++ }
+ }
++ return upd;
++#else
++ return false;
+ #endif
+ }
+
+@@ -625,23 +647,36 @@ static bool cake_ddst(int flow_mode)
+ static u32 cake_hash(struct cake_tin_data *q, const struct sk_buff *skb,
+ int flow_mode, u16 flow_override, u16 host_override)
+ {
++ bool hash_flows = (!flow_override && !!(flow_mode & CAKE_FLOW_FLOWS));
++ bool hash_hosts = (!host_override && !!(flow_mode & CAKE_FLOW_HOSTS));
++ bool nat_enabled = !!(flow_mode & CAKE_FLOW_NAT_FLAG);
+ u32 flow_hash = 0, srchost_hash = 0, dsthost_hash = 0;
+ u16 reduced_hash, srchost_idx, dsthost_idx;
+ struct flow_keys keys, host_keys;
++ bool use_skbhash = skb->l4_hash;
+
+ if (unlikely(flow_mode == CAKE_FLOW_NONE))
+ return 0;
+
+- /* If both overrides are set we can skip packet dissection entirely */
+- if ((flow_override || !(flow_mode & CAKE_FLOW_FLOWS)) &&
+- (host_override || !(flow_mode & CAKE_FLOW_HOSTS)))
++ /* If both overrides are set, or we can use the SKB hash and nat mode is
++ * disabled, we can skip packet dissection entirely. If nat mode is
++ * enabled there's another check below after doing the conntrack lookup.
++ */
++ if ((!hash_flows || (use_skbhash && !nat_enabled)) && !hash_hosts)
+ goto skip_hash;
+
+ skb_flow_dissect_flow_keys(skb, &keys,
+ FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL);
+
+- if (flow_mode & CAKE_FLOW_NAT_FLAG)
+- cake_update_flowkeys(&keys, skb);
++ /* Don't use the SKB hash if we change the lookup keys from conntrack */
++ if (nat_enabled && cake_update_flowkeys(&keys, skb))
++ use_skbhash = false;
++
++ /* If we can still use the SKB hash and don't need the host hash, we can
++ * skip the rest of the hashing procedure
++ */
++ if (use_skbhash && !hash_hosts)
++ goto skip_hash;
+
+ /* flow_hash_from_keys() sorts the addresses by value, so we have
+ * to preserve their order in a separate data structure to treat
+@@ -680,12 +715,14 @@ static u32 cake_hash(struct cake_tin_dat
+ /* This *must* be after the above switch, since as a
+ * side-effect it sorts the src and dst addresses.
+ */
+- if (flow_mode & CAKE_FLOW_FLOWS)
++ if (hash_flows && !use_skbhash)
+ flow_hash = flow_hash_from_keys(&keys);
+
+ skip_hash:
+ if (flow_override)
+ flow_hash = flow_override - 1;
++ else if (use_skbhash)
++ flow_hash = skb->hash;
+ if (host_override) {
+ dsthost_hash = host_override - 1;
+ srchost_hash = host_override - 1;
+++ /dev/null
-From b0c19ed6088ab41dd2a727b60594b7297c15d6ce Mon Sep 17 00:00:00 2001
-From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@redhat.com>
-Date: Fri, 29 May 2020 14:43:44 +0200
-Subject: [PATCH] sch_cake: Take advantage of skb->hash where appropriate
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-While the other fq-based qdiscs take advantage of skb->hash and doesn't
-recompute it if it is already set, sch_cake does not.
-
-This was a deliberate choice because sch_cake hashes various parts of the
-packet header to support its advanced flow isolation modes. However,
-foregoing the use of skb->hash entirely loses a few important benefits:
-
-- When skb->hash is set by hardware, a few CPU cycles can be saved by not
- hashing again in software.
-
-- Tunnel encapsulations will generally preserve the value of skb->hash from
- before the encapsulation, which allows flow-based qdiscs to distinguish
- between flows even though the outer packet header no longer has flow
- information.
-
-It turns out that we can preserve these desirable properties in many cases,
-while still supporting the advanced flow isolation properties of sch_cake.
-This patch does so by reusing the skb->hash value as the flow_hash part of
-the hashing procedure in cake_hash() only in the following conditions:
-
-- If the skb->hash is marked as covering the flow headers (skb->l4_hash is
- set)
-
-AND
-
-- NAT header rewriting is either disabled, or did not change any values
- used for hashing. The latter is important to match local-origin packets
- such as those of a tunnel endpoint.
-
-The immediate motivation for fixing this was the recent patch to WireGuard
-to preserve the skb->hash on encapsulation. As such, this is also what I
-tested against; with this patch, added latency under load for competing
-flows drops from ~8 ms to sub-1ms on an RRUL test over a WireGuard tunnel
-going through a virtual link shaped to 1Gbps using sch_cake. This matches
-the results we saw with a similar setup using sch_fq_codel when testing the
-WireGuard patch.
-
-Fixes: 046f6fd5daef ("sched: Add Common Applications Kept Enhanced (cake) qdisc")
-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 | 65 ++++++++++++++++++++++++++++++++++----------
- 1 file changed, 51 insertions(+), 14 deletions(-)
-
---- a/net/sched/sch_cake.c
-+++ b/net/sched/sch_cake.c
-@@ -585,26 +585,48 @@ static bool cobalt_should_drop(struct co
- return drop;
- }
-
--static void cake_update_flowkeys(struct flow_keys *keys,
-+static bool cake_update_flowkeys(struct flow_keys *keys,
- const struct sk_buff *skb)
- {
- #if IS_ENABLED(CONFIG_NF_CONNTRACK)
- struct nf_conntrack_tuple tuple = {};
-- bool rev = !skb->_nfct;
-+ bool rev = !skb->_nfct, upd = false;
-+ __be32 ip;
-
- if (tc_skb_protocol(skb) != htons(ETH_P_IP))
-- return;
-+ return false;
-
- if (!nf_ct_get_tuple_skb(&tuple, skb))
-- return;
-+ return false;
-
-- keys->addrs.v4addrs.src = rev ? tuple.dst.u3.ip : tuple.src.u3.ip;
-- keys->addrs.v4addrs.dst = rev ? tuple.src.u3.ip : tuple.dst.u3.ip;
-+ ip = rev ? tuple.dst.u3.ip : tuple.src.u3.ip;
-+ if (ip != keys->addrs.v4addrs.src) {
-+ keys->addrs.v4addrs.src = ip;
-+ upd = true;
-+ }
-+ ip = rev ? tuple.src.u3.ip : tuple.dst.u3.ip;
-+ if (ip != keys->addrs.v4addrs.dst) {
-+ keys->addrs.v4addrs.dst = ip;
-+ upd = true;
-+ }
-
- if (keys->ports.ports) {
-- keys->ports.src = rev ? tuple.dst.u.all : tuple.src.u.all;
-- keys->ports.dst = rev ? tuple.src.u.all : tuple.dst.u.all;
-+ __be16 port;
-+
-+ port = rev ? tuple.dst.u.all : tuple.src.u.all;
-+ if (port != keys->ports.src) {
-+ keys->ports.src = port;
-+ upd = true;
-+ }
-+ port = rev ? tuple.src.u.all : tuple.dst.u.all;
-+ if (port != keys->ports.dst) {
-+ port = keys->ports.dst;
-+ upd = true;
-+ }
- }
-+ return upd;
-+#else
-+ return false;
- #endif
- }
-
-@@ -625,23 +647,36 @@ static bool cake_ddst(int flow_mode)
- static u32 cake_hash(struct cake_tin_data *q, const struct sk_buff *skb,
- int flow_mode, u16 flow_override, u16 host_override)
- {
-+ bool hash_flows = (!flow_override && !!(flow_mode & CAKE_FLOW_FLOWS));
-+ bool hash_hosts = (!host_override && !!(flow_mode & CAKE_FLOW_HOSTS));
-+ bool nat_enabled = !!(flow_mode & CAKE_FLOW_NAT_FLAG);
- u32 flow_hash = 0, srchost_hash = 0, dsthost_hash = 0;
- u16 reduced_hash, srchost_idx, dsthost_idx;
- struct flow_keys keys, host_keys;
-+ bool use_skbhash = skb->l4_hash;
-
- if (unlikely(flow_mode == CAKE_FLOW_NONE))
- return 0;
-
-- /* If both overrides are set we can skip packet dissection entirely */
-- if ((flow_override || !(flow_mode & CAKE_FLOW_FLOWS)) &&
-- (host_override || !(flow_mode & CAKE_FLOW_HOSTS)))
-+ /* If both overrides are set, or we can use the SKB hash and nat mode is
-+ * disabled, we can skip packet dissection entirely. If nat mode is
-+ * enabled there's another check below after doing the conntrack lookup.
-+ */
-+ if ((!hash_flows || (use_skbhash && !nat_enabled)) && !hash_hosts)
- goto skip_hash;
-
- skb_flow_dissect_flow_keys(skb, &keys,
- FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL);
-
-- if (flow_mode & CAKE_FLOW_NAT_FLAG)
-- cake_update_flowkeys(&keys, skb);
-+ /* Don't use the SKB hash if we change the lookup keys from conntrack */
-+ if (nat_enabled && cake_update_flowkeys(&keys, skb))
-+ use_skbhash = false;
-+
-+ /* If we can still use the SKB hash and don't need the host hash, we can
-+ * skip the rest of the hashing procedure
-+ */
-+ if (use_skbhash && !hash_hosts)
-+ goto skip_hash;
-
- /* flow_hash_from_keys() sorts the addresses by value, so we have
- * to preserve their order in a separate data structure to treat
-@@ -680,12 +715,14 @@ static u32 cake_hash(struct cake_tin_dat
- /* This *must* be after the above switch, since as a
- * side-effect it sorts the src and dst addresses.
- */
-- if (flow_mode & CAKE_FLOW_FLOWS)
-+ if (hash_flows && !use_skbhash)
- flow_hash = flow_hash_from_keys(&keys);
-
- skip_hash:
- if (flow_override)
- flow_hash = flow_override - 1;
-+ else if (use_skbhash)
-+ flow_hash = skb->hash;
- if (host_override) {
- dsthost_hash = host_override - 1;
- srchost_hash = host_override - 1;
projects / openwrt / staging / hauke.git / commitdiff