diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2020-03-31 17:29:33 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2020-03-31 17:29:33 -0700 |
commit | 29d9f30d4ce6c7a38745a54a8cddface10013490 (patch) | |
tree | 85649ba6a7b39203584d8db9365e03f64e62c136 /net/sched/sch_red.c | |
parent | 56a451b780676bc1cdac011735fe2869fa2e9abf (diff) | |
parent | 7f80ccfe996871ca69648efee74a60ae7ad0dcd9 (diff) | |
download | linux-29d9f30d4ce6c7a38745a54a8cddface10013490.tar.bz2 |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from David Miller:
"Highlights:
1) Fix the iwlwifi regression, from Johannes Berg.
2) Support BSS coloring and 802.11 encapsulation offloading in
hardware, from John Crispin.
3) Fix some potential Spectre issues in qtnfmac, from Sergey
Matyukevich.
4) Add TTL decrement action to openvswitch, from Matteo Croce.
5) Allow paralleization through flow_action setup by not taking the
RTNL mutex, from Vlad Buslov.
6) A lot of zero-length array to flexible-array conversions, from
Gustavo A. R. Silva.
7) Align XDP statistics names across several drivers for consistency,
from Lorenzo Bianconi.
8) Add various pieces of infrastructure for offloading conntrack, and
make use of it in mlx5 driver, from Paul Blakey.
9) Allow using listening sockets in BPF sockmap, from Jakub Sitnicki.
10) Lots of parallelization improvements during configuration changes
in mlxsw driver, from Ido Schimmel.
11) Add support to devlink for generic packet traps, which report
packets dropped during ACL processing. And use them in mlxsw
driver. From Jiri Pirko.
12) Support bcmgenet on ACPI, from Jeremy Linton.
13) Make BPF compatible with RT, from Thomas Gleixnet, Alexei
Starovoitov, and your's truly.
14) Support XDP meta-data in virtio_net, from Yuya Kusakabe.
15) Fix sysfs permissions when network devices change namespaces, from
Christian Brauner.
16) Add a flags element to ethtool_ops so that drivers can more simply
indicate which coalescing parameters they actually support, and
therefore the generic layer can validate the user's ethtool
request. Use this in all drivers, from Jakub Kicinski.
17) Offload FIFO qdisc in mlxsw, from Petr Machata.
18) Support UDP sockets in sockmap, from Lorenz Bauer.
19) Fix stretch ACK bugs in several TCP congestion control modules,
from Pengcheng Yang.
20) Support virtual functiosn in octeontx2 driver, from Tomasz
Duszynski.
21) Add region operations for devlink and use it in ice driver to dump
NVM contents, from Jacob Keller.
22) Add support for hw offload of MACSEC, from Antoine Tenart.
23) Add support for BPF programs that can be attached to LSM hooks,
from KP Singh.
24) Support for multiple paths, path managers, and counters in MPTCP.
From Peter Krystad, Paolo Abeni, Florian Westphal, Davide Caratti,
and others.
25) More progress on adding the netlink interface to ethtool, from
Michal Kubecek"
* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2121 commits)
net: ipv6: rpl_iptunnel: Fix potential memory leak in rpl_do_srh_inline
cxgb4/chcr: nic-tls stats in ethtool
net: dsa: fix oops while probing Marvell DSA switches
net/bpfilter: remove superfluous testing message
net: macb: Fix handling of fixed-link node
net: dsa: ksz: Select KSZ protocol tag
netdevsim: dev: Fix memory leak in nsim_dev_take_snapshot_write
net: stmmac: add EHL 2.5Gbps PCI info and PCI ID
net: stmmac: add EHL PSE0 & PSE1 1Gbps PCI info and PCI ID
net: stmmac: create dwmac-intel.c to contain all Intel platform
net: dsa: bcm_sf2: Support specifying VLAN tag egress rule
net: dsa: bcm_sf2: Add support for matching VLAN TCI
net: dsa: bcm_sf2: Move writing of CFP_DATA(5) into slicing functions
net: dsa: bcm_sf2: Check earlier for FLOW_EXT and FLOW_MAC_EXT
net: dsa: bcm_sf2: Disable learning for ASP port
net: dsa: b53: Deny enslaving port 7 for 7278 into a bridge
net: dsa: b53: Prevent tagged VLAN on port 7 for 7278
net: dsa: b53: Restore VLAN entries upon (re)configuration
net: dsa: bcm_sf2: Fix overflow checks
hv_netvsc: Remove unnecessary round_up for recv_completion_cnt
...
Diffstat (limited to 'net/sched/sch_red.c')
-rw-r--r-- | net/sched/sch_red.c | 69 |
1 files changed, 61 insertions, 8 deletions
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 1695421333e3..c7de47c942e3 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -35,7 +35,11 @@ struct red_sched_data { u32 limit; /* HARD maximal queue length */ + unsigned char flags; + /* Non-flags in tc_red_qopt.flags. */ + unsigned char userbits; + struct timer_list adapt_timer; struct Qdisc *sch; struct red_parms parms; @@ -44,6 +48,8 @@ struct red_sched_data { struct Qdisc *qdisc; }; +static const u32 red_supported_flags = TC_RED_HISTORIC_FLAGS | TC_RED_NODROP; + static inline int red_use_ecn(struct red_sched_data *q) { return q->flags & TC_RED_ECN; @@ -54,6 +60,11 @@ static inline int red_use_harddrop(struct red_sched_data *q) return q->flags & TC_RED_HARDDROP; } +static int red_use_nodrop(struct red_sched_data *q) +{ + return q->flags & TC_RED_NODROP; +} + static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { @@ -74,23 +85,36 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch, case RED_PROB_MARK: qdisc_qstats_overlimit(sch); - if (!red_use_ecn(q) || !INET_ECN_set_ce(skb)) { + if (!red_use_ecn(q)) { q->stats.prob_drop++; goto congestion_drop; } - q->stats.prob_mark++; + if (INET_ECN_set_ce(skb)) { + q->stats.prob_mark++; + } else if (!red_use_nodrop(q)) { + q->stats.prob_drop++; + goto congestion_drop; + } + + /* Non-ECT packet in ECN nodrop mode: queue it. */ break; case RED_HARD_MARK: qdisc_qstats_overlimit(sch); - if (red_use_harddrop(q) || !red_use_ecn(q) || - !INET_ECN_set_ce(skb)) { + if (red_use_harddrop(q) || !red_use_ecn(q)) { + q->stats.forced_drop++; + goto congestion_drop; + } + + if (INET_ECN_set_ce(skb)) { + q->stats.forced_mark++; + } else if (!red_use_nodrop(q)) { q->stats.forced_drop++; goto congestion_drop; } - q->stats.forced_mark++; + /* Non-ECT packet in ECN nodrop mode: queue it. */ break; } @@ -165,6 +189,7 @@ static int red_offload(struct Qdisc *sch, bool enable) opt.set.limit = q->limit; opt.set.is_ecn = red_use_ecn(q); opt.set.is_harddrop = red_use_harddrop(q); + opt.set.is_nodrop = red_use_nodrop(q); opt.set.qstats = &sch->qstats; } else { opt.command = TC_RED_DESTROY; @@ -183,9 +208,12 @@ static void red_destroy(struct Qdisc *sch) } static const struct nla_policy red_policy[TCA_RED_MAX + 1] = { + [TCA_RED_UNSPEC] = { .strict_start_type = TCA_RED_FLAGS }, [TCA_RED_PARMS] = { .len = sizeof(struct tc_red_qopt) }, [TCA_RED_STAB] = { .len = RED_STAB_SIZE }, [TCA_RED_MAX_P] = { .type = NLA_U32 }, + [TCA_RED_FLAGS] = { .type = NLA_BITFIELD32, + .validation_data = &red_supported_flags }, }; static int red_change(struct Qdisc *sch, struct nlattr *opt, @@ -194,7 +222,10 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt, struct Qdisc *old_child = NULL, *child = NULL; struct red_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_RED_MAX + 1]; + struct nla_bitfield32 flags_bf; struct tc_red_qopt *ctl; + unsigned char userbits; + unsigned char flags; int err; u32 max_P; @@ -216,6 +247,12 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt, if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog)) return -EINVAL; + err = red_get_flags(ctl->flags, TC_RED_HISTORIC_FLAGS, + tb[TCA_RED_FLAGS], red_supported_flags, + &flags_bf, &userbits, extack); + if (err) + return err; + if (ctl->limit > 0) { child = fifo_create_dflt(sch, &bfifo_qdisc_ops, ctl->limit, extack); @@ -227,7 +264,14 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt, } sch_tree_lock(sch); - q->flags = ctl->flags; + + flags = (q->flags & ~flags_bf.selector) | flags_bf.value; + err = red_validate_flags(flags, extack); + if (err) + goto unlock_out; + + q->flags = flags; + q->userbits = userbits; q->limit = ctl->limit; if (child) { qdisc_tree_flush_backlog(q->qdisc); @@ -256,6 +300,12 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt, if (old_child) qdisc_put(old_child); return 0; + +unlock_out: + sch_tree_unlock(sch); + if (child) + qdisc_put(child); + return err; } static inline void red_adaptative_timer(struct timer_list *t) @@ -302,7 +352,8 @@ static int red_dump(struct Qdisc *sch, struct sk_buff *skb) struct nlattr *opts = NULL; struct tc_red_qopt opt = { .limit = q->limit, - .flags = q->flags, + .flags = (q->flags & TC_RED_HISTORIC_FLAGS) | + q->userbits, .qth_min = q->parms.qth_min >> q->parms.Wlog, .qth_max = q->parms.qth_max >> q->parms.Wlog, .Wlog = q->parms.Wlog, @@ -319,7 +370,9 @@ static int red_dump(struct Qdisc *sch, struct sk_buff *skb) if (opts == NULL) goto nla_put_failure; if (nla_put(skb, TCA_RED_PARMS, sizeof(opt), &opt) || - nla_put_u32(skb, TCA_RED_MAX_P, q->parms.max_P)) + nla_put_u32(skb, TCA_RED_MAX_P, q->parms.max_P) || + nla_put_bitfield32(skb, TCA_RED_FLAGS, + q->flags, red_supported_flags)) goto nla_put_failure; return nla_nest_end(skb, opts); |