summaryrefslogtreecommitdiff
path: root/net/sched
diff options
context:
space:
mode:
Diffstat (limited to 'net/sched')
-rw-r--r--net/sched/Kconfig11
-rw-r--r--net/sched/Makefile1
-rw-r--r--net/sched/act_api.c5
-rw-r--r--net/sched/act_bpf.c9
-rw-r--r--net/sched/act_mirred.c2
-rw-r--r--net/sched/act_pedit.c5
-rw-r--r--net/sched/cls_api.c12
-rw-r--r--net/sched/cls_bpf.c16
-rw-r--r--net/sched/cls_flow.c28
-rw-r--r--net/sched/cls_flower.c691
-rw-r--r--net/sched/em_ipset.c4
-rw-r--r--net/sched/sch_api.c27
-rw-r--r--net/sched/sch_choke.c20
-rw-r--r--net/sched/sch_codel.c17
-rw-r--r--net/sched/sch_fq_codel.c28
-rw-r--r--net/sched/sch_gred.c32
-rw-r--r--net/sched/sch_hhf.c19
-rw-r--r--net/sched/sch_ingress.c59
-rw-r--r--net/sched/sch_netem.c4
-rw-r--r--net/sched/sch_qfq.c3
-rw-r--r--net/sched/sch_sfb.c24
-rw-r--r--net/sched/sch_sfq.c27
22 files changed, 853 insertions, 191 deletions
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index 2274e723a3df..daa33432b716 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -312,6 +312,7 @@ config NET_SCH_PIE
config NET_SCH_INGRESS
tristate "Ingress Qdisc"
depends on NET_CLS_ACT
+ select NET_INGRESS
---help---
Say Y here if you want to use classifiers for incoming packets.
If unsure, say Y.
@@ -477,6 +478,16 @@ config NET_CLS_BPF
To compile this code as a module, choose M here: the module will
be called cls_bpf.
+config NET_CLS_FLOWER
+ tristate "Flower classifier"
+ select NET_CLS
+ ---help---
+ If you say Y here, you will be able to classify packets based on
+ a configurable combination of packet keys and masks.
+
+ To compile this code as a module, choose M here: the module will
+ be called cls_flower.
+
config NET_EMATCH
bool "Extended Matches"
select NET_CLS
diff --git a/net/sched/Makefile b/net/sched/Makefile
index 7ca7f4c1b8c2..690c1689e090 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -56,6 +56,7 @@ obj-$(CONFIG_NET_CLS_BASIC) += cls_basic.o
obj-$(CONFIG_NET_CLS_FLOW) += cls_flow.o
obj-$(CONFIG_NET_CLS_CGROUP) += cls_cgroup.o
obj-$(CONFIG_NET_CLS_BPF) += cls_bpf.o
+obj-$(CONFIG_NET_CLS_FLOWER) += cls_flower.o
obj-$(CONFIG_NET_EMATCH) += ematch.o
obj-$(CONFIG_NET_EMATCH_CMP) += em_cmp.o
obj-$(CONFIG_NET_EMATCH_NBYTE) += em_nbyte.o
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 3d43e4979f27..af427a3dbcba 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -392,11 +392,6 @@ int tcf_action_exec(struct sk_buff *skb, const struct list_head *actions,
list_for_each_entry(a, actions, list) {
repeat:
ret = a->ops->act(skb, a, res);
- if (TC_MUNGED & skb->tc_verd) {
- /* copied already, allow trampling */
- skb->tc_verd = SET_TC_OK2MUNGE(skb->tc_verd);
- skb->tc_verd = CLR_TC_MUNGED(skb->tc_verd);
- }
if (ret == TC_ACT_REPEAT)
goto repeat; /* we need a ttl - JHS */
if (ret != TC_ACT_PIPE)
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index dc6a2d324bd8..1d56903fd4c7 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -37,6 +37,7 @@ static int tcf_bpf(struct sk_buff *skb, const struct tc_action *act,
{
struct tcf_bpf *prog = act->priv;
int action, filter_res;
+ bool at_ingress = G_TC_AT(skb->tc_verd) & AT_INGRESS;
if (unlikely(!skb_mac_header_was_set(skb)))
return TC_ACT_UNSPEC;
@@ -48,7 +49,13 @@ static int tcf_bpf(struct sk_buff *skb, const struct tc_action *act,
/* Needed here for accessing maps. */
rcu_read_lock();
- filter_res = BPF_PROG_RUN(prog->filter, skb);
+ if (at_ingress) {
+ __skb_push(skb, skb->mac_len);
+ filter_res = BPF_PROG_RUN(prog->filter, skb);
+ __skb_pull(skb, skb->mac_len);
+ } else {
+ filter_res = BPF_PROG_RUN(prog->filter, skb);
+ }
rcu_read_unlock();
/* A BPF program may overwrite the default action opcode.
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 3f63ceac8e01..a42a3b257226 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -151,7 +151,7 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a,
}
at = G_TC_AT(skb->tc_verd);
- skb2 = skb_act_clone(skb, GFP_ATOMIC, m->tcf_action);
+ skb2 = skb_clone(skb, GFP_ATOMIC);
if (skb2 == NULL)
goto out;
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 59649d588d79..17e6d6669c7f 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -108,7 +108,7 @@ static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a,
struct tcf_result *res)
{
struct tcf_pedit *p = a->priv;
- int i, munged = 0;
+ int i;
unsigned int off;
if (skb_unclone(skb, GFP_ATOMIC))
@@ -156,11 +156,8 @@ static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a,
*ptr = ((*ptr & tkey->mask) ^ tkey->val);
if (ptr == &_data)
skb_store_bits(skb, off + offset, ptr, 4);
- munged++;
}
- if (munged)
- skb->tc_verd = SET_TC_MUNGED(skb->tc_verd);
goto done;
} else
WARN(1, "pedit BUG: index %d\n", p->tcf_index);
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 8b0470e418dc..a75864d93142 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -81,6 +81,11 @@ int unregister_tcf_proto_ops(struct tcf_proto_ops *ops)
struct tcf_proto_ops *t;
int rc = -ENOENT;
+ /* Wait for outstanding call_rcu()s, if any, from a
+ * tcf_proto_ops's destroy() handler.
+ */
+ rcu_barrier();
+
write_lock(&cls_mod_lock);
list_for_each_entry(t, &tcf_proto_base, head) {
if (t == ops) {
@@ -308,12 +313,11 @@ replay:
case RTM_DELTFILTER:
err = tp->ops->delete(tp, fh);
if (err == 0) {
- tfilter_notify(net, skb, n, tp, fh, RTM_DELTFILTER);
- if (tcf_destroy(tp, false)) {
- struct tcf_proto *next = rtnl_dereference(tp->next);
+ struct tcf_proto *next = rtnl_dereference(tp->next);
+ tfilter_notify(net, skb, n, tp, fh, RTM_DELTFILTER);
+ if (tcf_destroy(tp, false))
RCU_INIT_POINTER(*back, next);
- }
}
goto errout;
case RTM_GETTFILTER:
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index 91bd9c19471d..c79ecfd36e0f 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -64,6 +64,11 @@ static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
{
struct cls_bpf_head *head = rcu_dereference_bh(tp->root);
struct cls_bpf_prog *prog;
+#ifdef CONFIG_NET_CLS_ACT
+ bool at_ingress = G_TC_AT(skb->tc_verd) & AT_INGRESS;
+#else
+ bool at_ingress = false;
+#endif
int ret = -1;
if (unlikely(!skb_mac_header_was_set(skb)))
@@ -72,7 +77,16 @@ static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
/* Needed here for accessing maps. */
rcu_read_lock();
list_for_each_entry_rcu(prog, &head->plist, link) {
- int filter_res = BPF_PROG_RUN(prog->filter, skb);
+ int filter_res;
+
+ if (at_ingress) {
+ /* It is safe to push/pull even if skb_shared() */
+ __skb_push(skb, skb->mac_len);
+ filter_res = BPF_PROG_RUN(prog->filter, skb);
+ __skb_pull(skb, skb->mac_len);
+ } else {
+ filter_res = BPF_PROG_RUN(prog->filter, skb);
+ }
if (filter_res == 0)
continue;
diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index a620c4e288a5..76bc3a20ffdb 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -26,7 +26,7 @@
#include <net/pkt_cls.h>
#include <net/ip.h>
#include <net/route.h>
-#include <net/flow_keys.h>
+#include <net/flow_dissector.h>
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
#include <net/netfilter/nf_conntrack.h>
@@ -68,35 +68,41 @@ static inline u32 addr_fold(void *addr)
static u32 flow_get_src(const struct sk_buff *skb, const struct flow_keys *flow)
{
- if (flow->src)
- return ntohl(flow->src);
+ __be32 src = flow_get_u32_src(flow);
+
+ if (src)
+ return ntohl(src);
+
return addr_fold(skb->sk);
}
static u32 flow_get_dst(const struct sk_buff *skb, const struct flow_keys *flow)
{
- if (flow->dst)
- return ntohl(flow->dst);
+ __be32 dst = flow_get_u32_dst(flow);
+
+ if (dst)
+ return ntohl(dst);
+
return addr_fold(skb_dst(skb)) ^ (__force u16) tc_skb_protocol(skb);
}
static u32 flow_get_proto(const struct sk_buff *skb, const struct flow_keys *flow)
{
- return flow->ip_proto;
+ return flow->basic.ip_proto;
}
static u32 flow_get_proto_src(const struct sk_buff *skb, const struct flow_keys *flow)
{
- if (flow->ports)
- return ntohs(flow->port16[0]);
+ if (flow->ports.ports)
+ return ntohs(flow->ports.src);
return addr_fold(skb->sk);
}
static u32 flow_get_proto_dst(const struct sk_buff *skb, const struct flow_keys *flow)
{
- if (flow->ports)
- return ntohs(flow->port16[1]);
+ if (flow->ports.ports)
+ return ntohs(flow->ports.dst);
return addr_fold(skb_dst(skb)) ^ (__force u16) tc_skb_protocol(skb);
}
@@ -295,7 +301,7 @@ static int flow_classify(struct sk_buff *skb, const struct tcf_proto *tp,
keymask = f->keymask;
if (keymask & FLOW_KEYS_NEEDED)
- skb_flow_dissect(skb, &flow_keys);
+ skb_flow_dissect_flow_keys(skb, &flow_keys);
for (n = 0; n < f->nkeys; n++) {
key = ffs(keymask) - 1;
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
new file mode 100644
index 000000000000..b92d3f49c23e
--- /dev/null
+++ b/net/sched/cls_flower.c
@@ -0,0 +1,691 @@
+/*
+ * net/sched/cls_flower.c Flower classifier
+ *
+ * Copyright (c) 2015 Jiri Pirko <jiri@resnulli.us>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/rhashtable.h>
+
+#include <linux/if_ether.h>
+#include <linux/in6.h>
+#include <linux/ip.h>
+
+#include <net/sch_generic.h>
+#include <net/pkt_cls.h>
+#include <net/ip.h>
+#include <net/flow_dissector.h>
+
+struct fl_flow_key {
+ int indev_ifindex;
+ struct flow_dissector_key_control control;
+ struct flow_dissector_key_basic basic;
+ struct flow_dissector_key_eth_addrs eth;
+ struct flow_dissector_key_addrs ipaddrs;
+ union {
+ struct flow_dissector_key_ipv4_addrs ipv4;
+ struct flow_dissector_key_ipv6_addrs ipv6;
+ };
+ struct flow_dissector_key_ports tp;
+} __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */
+
+struct fl_flow_mask_range {
+ unsigned short int start;
+ unsigned short int end;
+};
+
+struct fl_flow_mask {
+ struct fl_flow_key key;
+ struct fl_flow_mask_range range;
+ struct rcu_head rcu;
+};
+
+struct cls_fl_head {
+ struct rhashtable ht;
+ struct fl_flow_mask mask;
+ struct flow_dissector dissector;
+ u32 hgen;
+ bool mask_assigned;
+ struct list_head filters;
+ struct rhashtable_params ht_params;
+ struct rcu_head rcu;
+};
+
+struct cls_fl_filter {
+ struct rhash_head ht_node;
+ struct fl_flow_key mkey;
+ struct tcf_exts exts;
+ struct tcf_result res;
+ struct fl_flow_key key;
+ struct list_head list;
+ u32 handle;
+ struct rcu_head rcu;
+};
+
+static unsigned short int fl_mask_range(const struct fl_flow_mask *mask)
+{
+ return mask->range.end - mask->range.start;
+}
+
+static void fl_mask_update_range(struct fl_flow_mask *mask)
+{
+ const u8 *bytes = (const u8 *) &mask->key;
+ size_t size = sizeof(mask->key);
+ size_t i, first = 0, last = size - 1;
+
+ for (i = 0; i < sizeof(mask->key); i++) {
+ if (bytes[i]) {
+ if (!first && i)
+ first = i;
+ last = i;
+ }
+ }
+ mask->range.start = rounddown(first, sizeof(long));
+ mask->range.end = roundup(last + 1, sizeof(long));
+}
+
+static void *fl_key_get_start(struct fl_flow_key *key,
+ const struct fl_flow_mask *mask)
+{
+ return (u8 *) key + mask->range.start;
+}
+
+static void fl_set_masked_key(struct fl_flow_key *mkey, struct fl_flow_key *key,
+ struct fl_flow_mask *mask)
+{
+ const long *lkey = fl_key_get_start(key, mask);
+ const long *lmask = fl_key_get_start(&mask->key, mask);
+ long *lmkey = fl_key_get_start(mkey, mask);
+ int i;
+
+ for (i = 0; i < fl_mask_range(mask); i += sizeof(long))
+ *lmkey++ = *lkey++ & *lmask++;
+}
+
+static void fl_clear_masked_range(struct fl_flow_key *key,
+ struct fl_flow_mask *mask)
+{
+ memset(fl_key_get_start(key, mask), 0, fl_mask_range(mask));
+}
+
+static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp,
+ struct tcf_result *res)
+{
+ struct cls_fl_head *head = rcu_dereference_bh(tp->root);
+ struct cls_fl_filter *f;
+ struct fl_flow_key skb_key;
+ struct fl_flow_key skb_mkey;
+
+ fl_clear_masked_range(&skb_key, &head->mask);
+ skb_key.indev_ifindex = skb->skb_iif;
+ /* skb_flow_dissect() does not set n_proto in case an unknown protocol,
+ * so do it rather here.
+ */
+ skb_key.basic.n_proto = skb->protocol;
+ skb_flow_dissect(skb, &head->dissector, &skb_key);
+
+ fl_set_masked_key(&skb_mkey, &skb_key, &head->mask);
+
+ f = rhashtable_lookup_fast(&head->ht,
+ fl_key_get_start(&skb_mkey, &head->mask),
+ head->ht_params);
+ if (f) {
+ *res = f->res;
+ return tcf_exts_exec(skb, &f->exts, res);
+ }
+ return -1;
+}
+
+static int fl_init(struct tcf_proto *tp)
+{
+ struct cls_fl_head *head;
+
+ head = kzalloc(sizeof(*head), GFP_KERNEL);
+ if (!head)
+ return -ENOBUFS;
+
+ INIT_LIST_HEAD_RCU(&head->filters);
+ rcu_assign_pointer(tp->root, head);
+
+ return 0;
+}
+
+static void fl_destroy_filter(struct rcu_head *head)
+{
+ struct cls_fl_filter *f = container_of(head, struct cls_fl_filter, rcu);
+
+ tcf_exts_destroy(&f->exts);
+ kfree(f);
+}
+
+static bool fl_destroy(struct tcf_proto *tp, bool force)
+{
+ struct cls_fl_head *head = rtnl_dereference(tp->root);
+ struct cls_fl_filter *f, *next;
+
+ if (!force && !list_empty(&head->filters))
+ return false;
+
+ list_for_each_entry_safe(f, next, &head->filters, list) {
+ list_del_rcu(&f->list);
+ call_rcu(&f->rcu, fl_destroy_filter);
+ }
+ RCU_INIT_POINTER(tp->root, NULL);
+ if (head->mask_assigned)
+ rhashtable_destroy(&head->ht);
+ kfree_rcu(head, rcu);
+ return true;
+}
+
+static unsigned long fl_get(struct tcf_proto *tp, u32 handle)
+{
+ struct cls_fl_head *head = rtnl_dereference(tp->root);
+ struct cls_fl_filter *f;
+
+ list_for_each_entry(f, &head->filters, list)
+ if (f->handle == handle)
+ return (unsigned long) f;
+ return 0;
+}
+
+static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = {
+ [TCA_FLOWER_UNSPEC] = { .type = NLA_UNSPEC },
+ [TCA_FLOWER_CLASSID] = { .type = NLA_U32 },
+ [TCA_FLOWER_INDEV] = { .type = NLA_STRING,
+ .len = IFNAMSIZ },
+ [TCA_FLOWER_KEY_ETH_DST] = { .len = ETH_ALEN },
+ [TCA_FLOWER_KEY_ETH_DST_MASK] = { .len = ETH_ALEN },
+ [TCA_FLOWER_KEY_ETH_SRC] = { .len = ETH_ALEN },
+ [TCA_FLOWER_KEY_ETH_SRC_MASK] = { .len = ETH_ALEN },
+ [TCA_FLOWER_KEY_ETH_TYPE] = { .type = NLA_U16 },
+ [TCA_FLOWER_KEY_IP_PROTO] = { .type = NLA_U8 },
+ [TCA_FLOWER_KEY_IPV4_SRC] = { .type = NLA_U32 },
+ [TCA_FLOWER_KEY_IPV4_SRC_MASK] = { .type = NLA_U32 },
+ [TCA_FLOWER_KEY_IPV4_DST] = { .type = NLA_U32 },
+ [TCA_FLOWER_KEY_IPV4_DST_MASK] = { .type = NLA_U32 },
+ [TCA_FLOWER_KEY_IPV6_SRC] = { .len = sizeof(struct in6_addr) },
+ [TCA_FLOWER_KEY_IPV6_SRC_MASK] = { .len = sizeof(struct in6_addr) },
+ [TCA_FLOWER_KEY_IPV6_DST] = { .len = sizeof(struct in6_addr) },
+ [TCA_FLOWER_KEY_IPV6_DST_MASK] = { .len = sizeof(struct in6_addr) },
+ [TCA_FLOWER_KEY_TCP_SRC] = { .type = NLA_U16 },
+ [TCA_FLOWER_KEY_TCP_DST] = { .type = NLA_U16 },
+ [TCA_FLOWER_KEY_TCP_SRC] = { .type = NLA_U16 },
+ [TCA_FLOWER_KEY_TCP_DST] = { .type = NLA_U16 },
+};
+
+static void fl_set_key_val(struct nlattr **tb,
+ void *val, int val_type,
+ void *mask, int mask_type, int len)
+{
+ if (!tb[val_type])
+ return;
+ memcpy(val, nla_data(tb[val_type]), len);
+ if (mask_type == TCA_FLOWER_UNSPEC || !tb[mask_type])
+ memset(mask, 0xff, len);
+ else
+ memcpy(mask, nla_data(tb[mask_type]), len);
+}
+
+static int fl_set_key(struct net *net, struct nlattr **tb,
+ struct fl_flow_key *key, struct fl_flow_key *mask)
+{
+#ifdef CONFIG_NET_CLS_IND
+ if (tb[TCA_FLOWER_INDEV]) {
+ int err = tcf_change_indev(net, tb[TCA_FLOWER_INDEV]);
+ if (err < 0)
+ return err;
+ key->indev_ifindex = err;
+ mask->indev_ifindex = 0xffffffff;
+ }
+#endif
+
+ fl_set_key_val(tb, key->eth.dst, TCA_FLOWER_KEY_ETH_DST,
+ mask->eth.dst, TCA_FLOWER_KEY_ETH_DST_MASK,
+ sizeof(key->eth.dst));
+ fl_set_key_val(tb, key->eth.src, TCA_FLOWER_KEY_ETH_SRC,
+ mask->eth.src, TCA_FLOWER_KEY_ETH_SRC_MASK,
+ sizeof(key->eth.src));
+ fl_set_key_val(tb, &key->basic.n_proto, TCA_FLOWER_KEY_ETH_TYPE,
+ &mask->basic.n_proto, TCA_FLOWER_UNSPEC,
+ sizeof(key->basic.n_proto));
+ if (key->basic.n_proto == htons(ETH_P_IP) ||
+ key->basic.n_proto == htons(ETH_P_IPV6)) {
+ fl_set_key_val(tb, &key->basic.ip_proto, TCA_FLOWER_KEY_IP_PROTO,
+ &mask->basic.ip_proto, TCA_FLOWER_UNSPEC,
+ sizeof(key->basic.ip_proto));
+ }
+ if (key->control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
+ fl_set_key_val(tb, &key->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC,
+ &mask->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC_MASK,
+ sizeof(key->ipv4.src));
+ fl_set_key_val(tb, &key->ipv4.dst, TCA_FLOWER_KEY_IPV4_DST,
+ &mask->ipv4.dst, TCA_FLOWER_KEY_IPV4_DST_MASK,
+ sizeof(key->ipv4.dst));
+ } else if (key->control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
+ fl_set_key_val(tb, &key->ipv6.src, TCA_FLOWER_KEY_IPV6_SRC,
+ &mask->ipv6.src, TCA_FLOWER_KEY_IPV6_SRC_MASK,
+ sizeof(key->ipv6.src));
+ fl_set_key_val(tb, &key->ipv6.dst, TCA_FLOWER_KEY_IPV6_DST,
+ &mask->ipv6.dst, TCA_FLOWER_KEY_IPV6_DST_MASK,
+ sizeof(key->ipv6.dst));
+ }
+ if (key->basic.ip_proto == IPPROTO_TCP) {
+ fl_set_key_val(tb, &key->tp.src, TCA_FLOWER_KEY_TCP_SRC,
+ &mask->tp.src, TCA_FLOWER_UNSPEC,
+ sizeof(key->tp.src));
+ fl_set_key_val(tb, &key->tp.dst, TCA_FLOWER_KEY_TCP_DST,
+ &mask->tp.dst, TCA_FLOWER_UNSPEC,
+ sizeof(key->tp.dst));
+ } else if (key->basic.ip_proto == IPPROTO_UDP) {
+ fl_set_key_val(tb, &key->tp.src, TCA_FLOWER_KEY_UDP_SRC,
+ &mask->tp.src, TCA_FLOWER_UNSPEC,
+ sizeof(key->tp.src));
+ fl_set_key_val(tb, &key->tp.dst, TCA_FLOWER_KEY_UDP_DST,
+ &mask->tp.dst, TCA_FLOWER_UNSPEC,
+ sizeof(key->tp.dst));
+ }
+
+ return 0;
+}
+
+static bool fl_mask_eq(struct fl_flow_mask *mask1,
+ struct fl_flow_mask *mask2)
+{
+ const long *lmask1 = fl_key_get_start(&mask1->key, mask1);
+ const long *lmask2 = fl_key_get_start(&mask2->key, mask2);
+
+ return !memcmp(&mask1->range, &mask2->range, sizeof(mask1->range)) &&
+ !memcmp(lmask1, lmask2, fl_mask_range(mask1));
+}
+
+static const struct rhashtable_params fl_ht_params = {
+ .key_offset = offsetof(struct cls_fl_filter, mkey), /* base offset */
+ .head_offset = offsetof(struct cls_fl_filter, ht_node),
+ .automatic_shrinking = true,
+};
+
+static int fl_init_hashtable(struct cls_fl_head *head,
+ struct fl_flow_mask *mask)
+{
+ head->ht_params = fl_ht_params;
+ head->ht_params.key_len = fl_mask_range(mask);
+ head->ht_params.key_offset += mask->range.start;
+
+ return rhashtable_init(&head->ht, &head->ht_params);
+}
+
+#define FL_KEY_MEMBER_OFFSET(member) offsetof(struct fl_flow_key, member)
+#define FL_KEY_MEMBER_SIZE(member) (sizeof(((struct fl_flow_key *) 0)->member))
+#define FL_KEY_MEMBER_END_OFFSET(member) \
+ (FL_KEY_MEMBER_OFFSET(member) + FL_KEY_MEMBER_SIZE(member))
+
+#define FL_KEY_IN_RANGE(mask, member) \
+ (FL_KEY_MEMBER_OFFSET(member) <= (mask)->range.end && \
+ FL_KEY_MEMBER_END_OFFSET(member) >= (mask)->range.start)
+
+#define FL_KEY_SET(keys, cnt, id, member) \
+ do { \
+ keys[cnt].key_id = id; \
+ keys[cnt].offset = FL_KEY_MEMBER_OFFSET(member); \
+ cnt++; \
+ } while(0);
+
+#define FL_KEY_SET_IF_IN_RANGE(mask, keys, cnt, id, member) \
+ do { \
+ if (FL_KEY_IN_RANGE(mask, member)) \
+ FL_KEY_SET(keys, cnt, id, member); \
+ } while(0);
+
+static void fl_init_dissector(struct cls_fl_head *head,
+ struct fl_flow_mask *mask)
+{
+ struct flow_dissector_key keys[FLOW_DISSECTOR_KEY_MAX];
+ size_t cnt = 0;
+
+ FL_KEY_SET(keys, cnt, FLOW_DISSECTOR_KEY_CONTROL, control);
+ FL_KEY_SET(keys, cnt, FLOW_DISSECTOR_KEY_BASIC, basic);
+ FL_KEY_SET_IF_IN_RANGE(mask, keys, cnt,
+ FLOW_DISSECTOR_KEY_ETH_ADDRS, eth);
+ FL_KEY_SET_IF_IN_RANGE(mask, keys, cnt,
+ FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4);
+ FL_KEY_SET_IF_IN_RANGE(mask, keys, cnt,
+ FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6);
+ FL_KEY_SET_IF_IN_RANGE(mask, keys, cnt,
+ FLOW_DISSECTOR_KEY_PORTS, tp);
+
+ skb_flow_dissector_init(&head->dissector, keys, cnt);
+}
+
+static int fl_check_assign_mask(struct cls_fl_head *head,
+ struct fl_flow_mask *mask)
+{
+ int err;
+
+ if (head->mask_assigned) {
+ if (!fl_mask_eq(&head->mask, mask))
+ return -EINVAL;
+ else
+ return 0;
+ }
+
+ /* Mask is not assigned yet. So assign it and init hashtable
+ * according to that.
+ */
+ err = fl_init_hashtable(head, mask);
+ if (err)
+ return err;
+ memcpy(&head->mask, mask, sizeof(head->mask));
+ head->mask_assigned = true;
+
+ fl_init_dissector(head, mask);
+
+ return 0;
+}
+
+static int fl_set_parms(struct net *net, struct tcf_proto *tp,
+ struct cls_fl_filter *f, struct fl_flow_mask *mask,
+ unsigned long base, struct nlattr **tb,
+ struct nlattr *est, bool ovr)
+{
+ struct tcf_exts e;
+ int err;
+
+ tcf_exts_init(&e, TCA_FLOWER_ACT, 0);
+ err = tcf_exts_validate(net, tp, tb, est, &e, ovr);
+ if (err < 0)
+ return err;
+
+ if (tb[TCA_FLOWER_CLASSID]) {
+ f->res.classid = nla_get_u32(tb[TCA_FLOWER_CLASSID]);
+ tcf_bind_filter(tp, &f->res, base);
+ }
+
+ err = fl_set_key(net, tb, &f->key, &mask->key);
+ if (err)
+ goto errout;
+
+ fl_mask_update_range(mask);
+ fl_set_masked_key(&f->mkey, &f->key, mask);
+
+ tcf_exts_change(tp, &f->exts, &e);
+
+ return 0;
+errout:
+ tcf_exts_destroy(&e);
+ return err;
+}
+
+static u32 fl_grab_new_handle(struct tcf_proto *tp,
+ struct cls_fl_head *head)
+{
+ unsigned int i = 0x80000000;
+ u32 handle;
+
+ do {
+ if (++head->hgen == 0x7FFFFFFF)
+ head->hgen = 1;
+ } while (--i > 0 && fl_get(tp, head->hgen));
+
+ if (unlikely(i == 0)) {
+ pr_err("Insufficient number of handles\n");
+ handle = 0;
+ } else {
+ handle = head->hgen;
+ }
+
+ return handle;
+}
+
+static int fl_change(struct net *net, struct sk_buff *in_skb,
+ struct tcf_proto *tp, unsigned long base,
+ u32 handle, struct nlattr **tca,
+ unsigned long *arg, bool ovr)
+{
+ struct cls_fl_head *head = rtnl_dereference(tp->root);
+ struct cls_fl_filter *fold = (struct cls_fl_filter *) *arg;
+ struct cls_fl_filter *fnew;
+ struct nlattr *tb[TCA_FLOWER_MAX + 1];
+ struct fl_flow_mask mask = {};
+ int err;
+
+ if (!tca[TCA_OPTIONS])
+ return -EINVAL;
+
+ err = nla_parse_nested(tb, TCA_FLOWER_MAX, tca[TCA_OPTIONS], fl_policy);
+ if (err < 0)
+ return err;
+
+ if (fold && handle && fold->handle != handle)
+ return -EINVAL;
+
+ fnew = kzalloc(sizeof(*fnew), GFP_KERNEL);
+ if (!fnew)
+ return -ENOBUFS;
+
+ tcf_exts_init(&fnew->exts, TCA_FLOWER_ACT, 0);
+
+ if (!handle) {
+ handle = fl_grab_new_handle(tp, head);
+ if (!handle) {
+ err = -EINVAL;
+ goto errout;
+ }
+ }
+ fnew->handle = handle;
+
+ err = fl_set_parms(net, tp, fnew, &mask, base, tb, tca[TCA_RATE], ovr);
+ if (err)
+ goto errout;
+
+ err = fl_check_assign_mask(head, &mask);
+ if (err)
+ goto errout;
+
+ err = rhashtable_insert_fast(&head->ht, &fnew->ht_node,
+ head->ht_params);
+ if (err)
+ goto errout;
+ if (fold)
+ rhashtable_remove_fast(&head->ht, &fold->ht_node,
+ head->ht_params);
+
+ *arg = (unsigned long) fnew;
+
+ if (fold) {
+ list_replace_rcu(&fnew->list, &fold->list);
+ tcf_unbind_filter(tp, &fold->res);
+ call_rcu(&fold->rcu, fl_destroy_filter);
+ } else {
+ list_add_tail_rcu(&fnew->list, &head->filters);
+ }
+
+ return 0;
+
+errout:
+ kfree(fnew);
+ return err;
+}
+
+static int fl_delete(struct tcf_proto *tp, unsigned long arg)
+{
+ struct cls_fl_head *head = rtnl_dereference(tp->root);
+ struct cls_fl_filter *f = (struct cls_fl_filter *) arg;
+
+ rhashtable_remove_fast(&head->ht, &f->ht_node,
+ head->ht_params);
+ list_del_rcu(&f->list);
+ tcf_unbind_filter(tp, &f->res);
+ call_rcu(&f->rcu, fl_destroy_filter);
+ return 0;
+}
+
+static void fl_walk(struct tcf_proto *tp, struct tcf_walker *arg)
+{
+ struct cls_fl_head *head = rtnl_dereference(tp->root);
+ struct cls_fl_filter *f;
+
+ list_for_each_entry_rcu(f, &head->filters, list) {
+ if (arg->count < arg->skip)
+ goto skip;
+ if (arg->fn(tp, (unsigned long) f, arg) < 0) {
+ arg->stop = 1;
+ break;
+ }
+skip:
+ arg->count++;
+ }
+}
+
+static int fl_dump_key_val(struct sk_buff *skb,
+ void *val, int val_type,
+ void *mask, int mask_type, int len)
+{
+ int err;
+
+ if (!memchr_inv(mask, 0, len))
+ return 0;
+ err = nla_put(skb, val_type, len, val);
+ if (err)
+ return err;
+ if (mask_type != TCA_FLOWER_UNSPEC) {
+ err = nla_put(skb, mask_type, len, mask);
+ if (err)
+ return err;
+ }
+ return 0;
+}
+
+static int fl_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
+ struct sk_buff *skb, struct tcmsg *t)
+{
+ struct cls_fl_head *head = rtnl_dereference(tp->root);
+ struct cls_fl_filter *f = (struct cls_fl_filter *) fh;
+ struct nlattr *nest;
+ struct fl_flow_key *key, *mask;
+
+ if (!f)
+ return skb->len;
+
+ t->tcm_handle = f->handle;
+
+ nest = nla_nest_start(skb, TCA_OPTIONS);
+ if (!nest)
+ goto nla_put_failure;
+
+ if (f->res.classid &&
+ nla_put_u32(skb, TCA_FLOWER_CLASSID, f->res.classid))
+ goto nla_put_failure;
+
+ key = &f->key;
+ mask = &head->mask.key;
+
+ if (mask->indev_ifindex) {
+ struct net_device *dev;
+
+ dev = __dev_get_by_index(net, key->indev_ifindex);
+ if (dev && nla_put_string(skb, TCA_FLOWER_INDEV, dev->name))
+ goto nla_put_failure;
+ }
+
+ if (fl_dump_key_val(skb, key->eth.dst, TCA_FLOWER_KEY_ETH_DST,
+ mask->eth.dst, TCA_FLOWER_KEY_ETH_DST_MASK,
+ sizeof(key->eth.dst)) ||
+ fl_dump_key_val(skb, key->eth.src, TCA_FLOWER_KEY_ETH_SRC,
+ mask->eth.src, TCA_FLOWER_KEY_ETH_SRC_MASK,
+ sizeof(key->eth.src)) ||
+ fl_dump_key_val(skb, &key->basic.n_proto, TCA_FLOWER_KEY_ETH_TYPE,
+ &mask->basic.n_proto, TCA_FLOWER_UNSPEC,
+ sizeof(key->basic.n_proto)))
+ goto nla_put_failure;
+ if ((key->basic.n_proto == htons(ETH_P_IP) ||
+ key->basic.n_proto == htons(ETH_P_IPV6)) &&
+ fl_dump_key_val(skb, &key->basic.ip_proto, TCA_FLOWER_KEY_IP_PROTO,
+ &mask->basic.ip_proto, TCA_FLOWER_UNSPEC,
+ sizeof(key->basic.ip_proto)))
+ goto nla_put_failure;
+
+ if (key->control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS &&
+ (fl_dump_key_val(skb, &key->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC,
+ &mask->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC_MASK,
+ sizeof(key->ipv4.src)) ||
+ fl_dump_key_val(skb, &key->ipv4.dst, TCA_FLOWER_KEY_IPV4_DST,
+ &mask->ipv4.dst, TCA_FLOWER_KEY_IPV4_DST_MASK,
+ sizeof(key->ipv4.dst))))
+ goto nla_put_failure;
+ else if (key->control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS &&
+ (fl_dump_key_val(skb, &key->ipv6.src, TCA_FLOWER_KEY_IPV6_SRC,
+ &mask->ipv6.src, TCA_FLOWER_KEY_IPV6_SRC_MASK,
+ sizeof(key->ipv6.src)) ||
+ fl_dump_key_val(skb, &key->ipv6.dst, TCA_FLOWER_KEY_IPV6_DST,
+ &mask->ipv6.dst, TCA_FLOWER_KEY_IPV6_DST_MASK,
+ sizeof(key->ipv6.dst))))
+ goto nla_put_failure;
+
+ if (key->basic.ip_proto == IPPROTO_TCP &&
+ (fl_dump_key_val(skb, &key->tp.src, TCA_FLOWER_KEY_TCP_SRC,
+ &mask->tp.src, TCA_FLOWER_UNSPEC,
+ sizeof(key->tp.src)) ||
+ fl_dump_key_val(skb, &key->tp.dst, TCA_FLOWER_KEY_TCP_DST,
+ &mask->tp.dst, TCA_FLOWER_UNSPEC,
+ sizeof(key->tp.dst))))
+ goto nla_put_failure;
+ else if (key->basic.ip_proto == IPPROTO_UDP &&
+ (fl_dump_key_val(skb, &key->tp.src, TCA_FLOWER_KEY_UDP_SRC,
+ &mask->tp.src, TCA_FLOWER_UNSPEC,
+ sizeof(key->tp.src)) ||
+ fl_dump_key_val(skb, &key->tp.dst, TCA_FLOWER_KEY_UDP_DST,
+ &mask->tp.dst, TCA_FLOWER_UNSPEC,
+ sizeof(key->tp.dst))))
+ goto nla_put_failure;
+
+ if (tcf_exts_dump(skb, &f->exts))
+ goto nla_put_failure;
+
+ nla_nest_end(skb, nest);
+
+ if (tcf_exts_dump_stats(skb, &f->exts) < 0)
+ goto nla_put_failure;
+
+ return skb->len;
+
+nla_put_failure:
+ nla_nest_cancel(skb, nest);
+ return -1;
+}
+
+static struct tcf_proto_ops cls_fl_ops __read_mostly = {
+ .kind = "flower",
+ .classify = fl_classify,
+ .init = fl_init,
+ .destroy = fl_destroy,
+ .get = fl_get,
+ .change = fl_change,
+ .delete = fl_delete,
+ .walk = fl_walk,
+ .dump = fl_dump,
+ .owner = THIS_MODULE,
+};
+
+static int __init cls_fl_init(void)
+{
+ return register_tcf_proto_ops(&cls_fl_ops);
+}
+
+static void __exit cls_fl_exit(void)
+{
+ unregister_tcf_proto_ops(&cls_fl_ops);
+}
+
+module_init(cls_fl_init);
+module_exit(cls_fl_exit);
+
+MODULE_AUTHOR("Jiri Pirko <jiri@resnulli.us>");
+MODULE_DESCRIPTION("Flower classifier");
+MODULE_LICENSE("GPL v2");
diff --git a/net/sched/em_ipset.c b/net/sched/em_ipset.c
index a3d79c8bf3b8..df0328ba6a48 100644
--- a/net/sched/em_ipset.c
+++ b/net/sched/em_ipset.c
@@ -92,8 +92,8 @@ static int em_ipset_match(struct sk_buff *skb, struct tcf_ematch *em,
rcu_read_lock();
- if (dev && skb->skb_iif)
- indev = dev_get_by_index_rcu(dev_net(dev), skb->skb_iif);
+ if (skb->skb_iif)
+ indev = dev_get_by_index_rcu(em->net, skb->skb_iif);
acpar.in = indev ? indev : dev;
acpar.out = dev;
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index ad9eed70bc8f..f06aa01d60fd 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -815,10 +815,8 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent,
if (dev->flags & IFF_UP)
dev_deactivate(dev);
- if (new && new->ops->attach) {
- new->ops->attach(new);
- num_q = 0;
- }
+ if (new && new->ops->attach)
+ goto skip;
for (i = 0; i < num_q; i++) {
struct netdev_queue *dev_queue = dev_ingress_queue(dev);
@@ -834,12 +832,16 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent,
qdisc_destroy(old);
}
+skip:
if (!ingress) {
notify_and_destroy(net, skb, n, classid,
dev->qdisc, new);
if (new && !new->ops->attach)
atomic_inc(&new->refcnt);
dev->qdisc = new ? : &noop_qdisc;
+
+ if (new && new->ops->attach)
+ new->ops->attach(new);
} else {
notify_and_destroy(net, skb, n, classid, old, new);
}
@@ -1816,13 +1818,8 @@ int tc_classify_compat(struct sk_buff *skb, const struct tcf_proto *tp,
continue;
err = tp->classify(skb, tp, res);
- if (err >= 0) {
-#ifdef CONFIG_NET_CLS_ACT
- if (err != TC_ACT_RECLASSIFY && skb->tc_verd)
- skb->tc_verd = SET_TC_VERD(skb->tc_verd, 0);
-#endif
+ if (err >= 0)
return err;
- }
}
return -1;
}
@@ -1834,23 +1831,22 @@ int tc_classify(struct sk_buff *skb, const struct tcf_proto *tp,
int err = 0;
#ifdef CONFIG_NET_CLS_ACT
const struct tcf_proto *otp = tp;
+ int limit = 0;
reclassify:
#endif
err = tc_classify_compat(skb, tp, res);
#ifdef CONFIG_NET_CLS_ACT
if (err == TC_ACT_RECLASSIFY) {
- u32 verd = G_TC_VERD(skb->tc_verd);
tp = otp;
- if (verd++ >= MAX_REC_LOOP) {
+ if (unlikely(limit++ >= MAX_REC_LOOP)) {
net_notice_ratelimited("%s: packet reclassify loop rule prio %u protocol %02x\n",
tp->q->ops->id,
tp->prio & 0xffff,
ntohs(tp->protocol));
return TC_ACT_SHOT;
}
- skb->tc_verd = SET_TC_VERD(skb->tc_verd, verd);
goto reclassify;
}
#endif
@@ -1883,13 +1879,10 @@ EXPORT_SYMBOL(tcf_destroy_chain);
#ifdef CONFIG_PROC_FS
static int psched_show(struct seq_file *seq, void *v)
{
- struct timespec ts;
-
- hrtimer_get_res(CLOCK_MONOTONIC, &ts);
seq_printf(seq, "%08x %08x %08x %08x\n",
(u32)NSEC_PER_USEC, (u32)PSCHED_TICKS2NS(1),
1000000,
- (u32)NSEC_PER_SEC/(u32)ktime_to_ns(timespec_to_ktime(ts)));
+ (u32)NSEC_PER_SEC / hrtimer_resolution);
return 0;
}
diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c
index c009eb9045ce..93d5742dc7e0 100644
--- a/net/sched/sch_choke.c
+++ b/net/sched/sch_choke.c
@@ -18,7 +18,7 @@
#include <net/pkt_sched.h>
#include <net/inet_ecn.h>
#include <net/red.h>
-#include <net/flow_keys.h>
+#include <net/flow_dissector.h>
/*
CHOKe stateless AQM for fair bandwidth allocation
@@ -133,16 +133,10 @@ static void choke_drop_by_idx(struct Qdisc *sch, unsigned int idx)
--sch->q.qlen;
}
-/* private part of skb->cb[] that a qdisc is allowed to use
- * is limited to QDISC_CB_PRIV_LEN bytes.
- * As a flow key might be too large, we store a part of it only.
- */
-#define CHOKE_K_LEN min_t(u32, sizeof(struct flow_keys), QDISC_CB_PRIV_LEN - 3)
-
struct choke_skb_cb {
u16 classid;
u8 keys_valid;
- u8 keys[QDISC_CB_PRIV_LEN - 3];
+ struct flow_keys_digest keys;
};
static inline struct choke_skb_cb *choke_skb_cb(const struct sk_buff *skb)
@@ -176,19 +170,19 @@ static bool choke_match_flow(struct sk_buff *skb1,
if (!choke_skb_cb(skb1)->keys_valid) {
choke_skb_cb(skb1)->keys_valid = 1;
- skb_flow_dissect(skb1, &temp);
- memcpy(&choke_skb_cb(skb1)->keys, &temp, CHOKE_K_LEN);
+ skb_flow_dissect_flow_keys(skb1, &temp);
+ make_flow_keys_digest(&choke_skb_cb(skb1)->keys, &temp);
}
if (!choke_skb_cb(skb2)->keys_valid) {
choke_skb_cb(skb2)->keys_valid = 1;
- skb_flow_dissect(skb2, &temp);
- memcpy(&choke_skb_cb(skb2)->keys, &temp, CHOKE_K_LEN);
+ skb_flow_dissect_flow_keys(skb2, &temp);
+ make_flow_keys_digest(&choke_skb_cb(skb2)->keys, &temp);
}
return !memcmp(&choke_skb_cb(skb1)->keys,
&choke_skb_cb(skb2)->keys,
- CHOKE_K_LEN);
+ sizeof(choke_skb_cb(skb1)->keys));
}
/*
diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c
index de28f8e968e8..535007d5f0b5 100644
--- a/net/sched/sch_codel.c
+++ b/net/sched/sch_codel.c
@@ -6,7 +6,7 @@
*
* Implemented on linux by :
* Copyright (C) 2012 Michael D. Taht <dave.taht@bufferbloat.net>
- * Copyright (C) 2012 Eric Dumazet <edumazet@google.com>
+ * Copyright (C) 2012,2015 Eric Dumazet <edumazet@google.com>
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
@@ -109,6 +109,7 @@ static const struct nla_policy codel_policy[TCA_CODEL_MAX + 1] = {
[TCA_CODEL_LIMIT] = { .type = NLA_U32 },
[TCA_CODEL_INTERVAL] = { .type = NLA_U32 },
[TCA_CODEL_ECN] = { .type = NLA_U32 },
+ [TCA_CODEL_CE_THRESHOLD]= { .type = NLA_U32 },
};
static int codel_change(struct Qdisc *sch, struct nlattr *opt)
@@ -133,6 +134,12 @@ static int codel_change(struct Qdisc *sch, struct nlattr *opt)
q->params.target = ((u64)target * NSEC_PER_USEC) >> CODEL_SHIFT;
}
+ if (tb[TCA_CODEL_CE_THRESHOLD]) {
+ u64 val = nla_get_u32(tb[TCA_CODEL_CE_THRESHOLD]);
+
+ q->params.ce_threshold = (val * NSEC_PER_USEC) >> CODEL_SHIFT;
+ }
+
if (tb[TCA_CODEL_INTERVAL]) {
u32 interval = nla_get_u32(tb[TCA_CODEL_INTERVAL]);
@@ -164,7 +171,7 @@ static int codel_init(struct Qdisc *sch, struct nlattr *opt)
sch->limit = DEFAULT_CODEL_LIMIT;
- codel_params_init(&q->params);
+ codel_params_init(&q->params, sch);
codel_vars_init(&q->vars);
codel_stats_init(&q->stats);
@@ -201,7 +208,10 @@ static int codel_dump(struct Qdisc *sch, struct sk_buff *skb)
nla_put_u32(skb, TCA_CODEL_ECN,
q->params.ecn))
goto nla_put_failure;
-
+ if (q->params.ce_threshold != CODEL_DISABLED_THRESHOLD &&
+ nla_put_u32(skb, TCA_CODEL_CE_THRESHOLD,
+ codel_time_to_us(q->params.ce_threshold)))
+ goto nla_put_failure;
return nla_nest_end(skb, opts);
nla_put_failure:
@@ -220,6 +230,7 @@ static int codel_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
.ldelay = codel_time_to_us(q->vars.ldelay),
.dropping = q->vars.dropping,
.ecn_mark = q->stats.ecn_mark,
+ .ce_mark = q->stats.ce_mark,
};
if (q->vars.dropping) {
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index 1e52decb7b59..d75993f89fac 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -6,7 +6,7 @@
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*
- * Copyright (C) 2012 Eric Dumazet <edumazet@google.com>
+ * Copyright (C) 2012,2015 Eric Dumazet <edumazet@google.com>
*/
#include <linux/module.h>
@@ -23,7 +23,6 @@
#include <linux/vmalloc.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
-#include <net/flow_keys.h>
#include <net/codel.h>
/* Fair Queue CoDel.
@@ -68,15 +67,9 @@ struct fq_codel_sched_data {
};
static unsigned int fq_codel_hash(const struct fq_codel_sched_data *q,
- const struct sk_buff *skb)
+ struct sk_buff *skb)
{
- struct flow_keys keys;
- unsigned int hash;
-
- skb_flow_dissect(skb, &keys);
- hash = jhash_3words((__force u32)keys.dst,
- (__force u32)keys.src ^ keys.ip_proto,
- (__force u32)keys.ports, q->perturbation);
+ u32 hash = skb_get_hash_perturb(skb, q->perturbation);
return reciprocal_scale(hash, q->flows_cnt);
}
@@ -299,6 +292,7 @@ static const struct nla_policy fq_codel_policy[TCA_FQ_CODEL_MAX + 1] = {
[TCA_FQ_CODEL_ECN] = { .type = NLA_U32 },
[TCA_FQ_CODEL_FLOWS] = { .type = NLA_U32 },
[TCA_FQ_CODEL_QUANTUM] = { .type = NLA_U32 },
+ [TCA_FQ_CODEL_CE_THRESHOLD] = { .type = NLA_U32 },
};
static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt)
@@ -329,6 +323,12 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt)
q->cparams.target = (target * NSEC_PER_USEC) >> CODEL_SHIFT;
}
+ if (tb[TCA_FQ_CODEL_CE_THRESHOLD]) {
+ u64 val = nla_get_u32(tb[TCA_FQ_CODEL_CE_THRESHOLD]);
+
+ q->cparams.ce_threshold = (val * NSEC_PER_USEC) >> CODEL_SHIFT;
+ }
+
if (tb[TCA_FQ_CODEL_INTERVAL]) {
u64 interval = nla_get_u32(tb[TCA_FQ_CODEL_INTERVAL]);
@@ -391,7 +391,7 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt)
q->perturbation = prandom_u32();
INIT_LIST_HEAD(&q->new_flows);
INIT_LIST_HEAD(&q->old_flows);
- codel_params_init(&q->cparams);
+ codel_params_init(&q->cparams, sch);
codel_stats_init(&q->cstats);
q->cparams.ecn = true;
@@ -448,6 +448,11 @@ static int fq_codel_dump(struct Qdisc *sch, struct sk_buff *skb)
q->flows_cnt))
goto nla_put_failure;
+ if (q->cparams.ce_threshold != CODEL_DISABLED_THRESHOLD &&
+ nla_put_u32(skb, TCA_FQ_CODEL_CE_THRESHOLD,
+ codel_time_to_us(q->cparams.ce_threshold)))
+ goto nla_put_failure;
+
return nla_nest_end(skb, opts);
nla_put_failure:
@@ -466,6 +471,7 @@ static int fq_codel_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
st.qdisc_stats.drop_overlimit = q->drop_overlimit;
st.qdisc_stats.ecn_mark = q->cstats.ecn_mark;
st.qdisc_stats.new_flow_count = q->new_flow_count;
+ st.qdisc_stats.ce_mark = q->cstats.ce_mark;
list_for_each(pos, &q->new_flows)
st.qdisc_stats.new_flows_len++;
diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c
index a4ca4517cdc8..abb9f2fec28f 100644
--- a/net/sched/sch_gred.c
+++ b/net/sched/sch_gred.c
@@ -165,7 +165,8 @@ static int gred_enqueue(struct sk_buff *skb, struct Qdisc *sch)
* if no default DP has been configured. This
* allows for DP flows to be left untouched.
*/
- if (skb_queue_len(&sch->q) < qdisc_dev(sch)->tx_queue_len)
+ if (likely(sch->qstats.backlog + qdisc_pkt_len(skb) <=
+ sch->limit))
return qdisc_enqueue_tail(skb, sch);
else
goto drop;
@@ -229,7 +230,7 @@ static int gred_enqueue(struct sk_buff *skb, struct Qdisc *sch)
break;
}
- if (q->backlog + qdisc_pkt_len(skb) <= q->limit) {
+ if (gred_backlog(t, q, sch) + qdisc_pkt_len(skb) <= q->limit) {
q->backlog += qdisc_pkt_len(skb);
return qdisc_enqueue_tail(skb, sch);
}
@@ -397,7 +398,10 @@ static inline int gred_change_vq(struct Qdisc *sch, int dp,
q->DP = dp;
q->prio = prio;
- q->limit = ctl->limit;
+ if (ctl->limit > sch->limit)
+ q->limit = sch->limit;
+ else
+ q->limit = ctl->limit;
if (q->backlog == 0)
red_end_of_idle_period(&q->vars);
@@ -414,6 +418,7 @@ static const struct nla_policy gred_policy[TCA_GRED_MAX + 1] = {
[TCA_GRED_STAB] = { .len = 256 },
[TCA_GRED_DPS] = { .len = sizeof(struct tc_gred_sopt) },
[TCA_GRED_MAX_P] = { .type = NLA_U32 },
+ [TCA_GRED_LIMIT] = { .type = NLA_U32 },
};
static int gred_change(struct Qdisc *sch, struct nlattr *opt)
@@ -433,11 +438,15 @@ static int gred_change(struct Qdisc *sch, struct nlattr *opt)
if (err < 0)
return err;
- if (tb[TCA_GRED_PARMS] == NULL && tb[TCA_GRED_STAB] == NULL)
+ if (tb[TCA_GRED_PARMS] == NULL && tb[TCA_GRED_STAB] == NULL) {
+ if (tb[TCA_GRED_LIMIT] != NULL)
+ sch->limit = nla_get_u32(tb[TCA_GRED_LIMIT]);
return gred_change_table_def(sch, opt);
+ }
if (tb[TCA_GRED_PARMS] == NULL ||
- tb[TCA_GRED_STAB] == NULL)
+ tb[TCA_GRED_STAB] == NULL ||
+ tb[TCA_GRED_LIMIT] != NULL)
return -EINVAL;
max_P = tb[TCA_GRED_MAX_P] ? nla_get_u32(tb[TCA_GRED_MAX_P]) : 0;
@@ -501,6 +510,14 @@ static int gred_init(struct Qdisc *sch, struct nlattr *opt)
if (tb[TCA_GRED_PARMS] || tb[TCA_GRED_STAB])
return -EINVAL;
+ if (tb[TCA_GRED_LIMIT])
+ sch->limit = nla_get_u32(tb[TCA_GRED_LIMIT]);
+ else {
+ u32 qlen = qdisc_dev(sch)->tx_queue_len ? : 1;
+
+ sch->limit = qlen * psched_mtu(qdisc_dev(sch));
+ }
+
return gred_change_table_def(sch, tb[TCA_GRED_DPS]);
}
@@ -531,6 +548,9 @@ static int gred_dump(struct Qdisc *sch, struct sk_buff *skb)
if (nla_put(skb, TCA_GRED_MAX_P, sizeof(max_p), max_p))
goto nla_put_failure;
+ if (nla_put_u32(skb, TCA_GRED_LIMIT, sch->limit))
+ goto nla_put_failure;
+
parms = nla_nest_start(skb, TCA_GRED_PARMS);
if (parms == NULL)
goto nla_put_failure;
@@ -553,7 +573,7 @@ static int gred_dump(struct Qdisc *sch, struct sk_buff *skb)
opt.limit = q->limit;
opt.DP = q->DP;
- opt.backlog = q->backlog;
+ opt.backlog = gred_backlog(table, q, sch);
opt.prio = q->prio;
opt.qth_min = q->parms.qth_min >> q->parms.Wlog;
opt.qth_max = q->parms.qth_max >> q->parms.Wlog;
diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c
index 15d3aabfe250..9d15cb6b8cb1 100644
--- a/net/sched/sch_hhf.c
+++ b/net/sched/sch_hhf.c
@@ -9,7 +9,6 @@
#include <linux/module.h>
#include <linux/skbuff.h>
#include <linux/vmalloc.h>
-#include <net/flow_keys.h>
#include <net/pkt_sched.h>
#include <net/sock.h>
@@ -176,22 +175,6 @@ static u32 hhf_time_stamp(void)
return jiffies;
}
-static unsigned int skb_hash(const struct hhf_sched_data *q,
- const struct sk_buff *skb)
-{
- struct flow_keys keys;
- unsigned int hash;
-
- if (skb->sk && skb->sk->sk_hash)
- return skb->sk->sk_hash;
-
- skb_flow_dissect(skb, &keys);
- hash = jhash_3words((__force u32)keys.dst,
- (__force u32)keys.src ^ keys.ip_proto,
- (__force u32)keys.ports, q->perturbation);
- return hash;
-}
-
/* Looks up a heavy-hitter flow in a chaining list of table T. */
static struct hh_flow_state *seek_list(const u32 hash,
struct list_head *head,
@@ -280,7 +263,7 @@ static enum wdrr_bucket_idx hhf_classify(struct sk_buff *skb, struct Qdisc *sch)
}
/* Get hashed flow-id of the skb. */
- hash = skb_hash(q, skb);
+ hash = skb_get_hash_perturb(skb, q->perturbation);
/* Check if this packet belongs to an already established HH flow. */
flow_pos = hash & HHF_BIT_MASK;
diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c
index 4cdbfb85686a..e7c648fa9dc3 100644
--- a/net/sched/sch_ingress.c
+++ b/net/sched/sch_ingress.c
@@ -12,16 +12,10 @@
#include <linux/list.h>
#include <linux/skbuff.h>
#include <linux/rtnetlink.h>
+
#include <net/netlink.h>
#include <net/pkt_sched.h>
-
-struct ingress_qdisc_data {
- struct tcf_proto __rcu *filter_list;
-};
-
-/* ------------------------- Class/flow operations ------------------------- */
-
static struct Qdisc *ingress_leaf(struct Qdisc *sch, unsigned long arg)
{
return NULL;
@@ -49,57 +43,24 @@ static void ingress_walk(struct Qdisc *sch, struct qdisc_walker *walker)
static struct tcf_proto __rcu **ingress_find_tcf(struct Qdisc *sch,
unsigned long cl)
{
- struct ingress_qdisc_data *p = qdisc_priv(sch);
-
- return &p->filter_list;
-}
-
-/* --------------------------- Qdisc operations ---------------------------- */
+ struct net_device *dev = qdisc_dev(sch);
-static int ingress_enqueue(struct sk_buff *skb, struct Qdisc *sch)
-{
- struct ingress_qdisc_data *p = qdisc_priv(sch);
- struct tcf_result res;
- struct tcf_proto *fl = rcu_dereference_bh(p->filter_list);
- int result;
-
- result = tc_classify(skb, fl, &res);
-
- qdisc_bstats_update(sch, skb);
- switch (result) {
- case TC_ACT_SHOT:
- result = TC_ACT_SHOT;
- qdisc_qstats_drop(sch);
- break;
- case TC_ACT_STOLEN:
- case TC_ACT_QUEUED:
- result = TC_ACT_STOLEN;
- break;
- case TC_ACT_RECLASSIFY:
- case TC_ACT_OK:
- skb->tc_index = TC_H_MIN(res.classid);
- default:
- result = TC_ACT_OK;
- break;
- }
-
- return result;
+ return &dev->ingress_cl_list;
}
-/* ------------------------------------------------------------- */
-
static int ingress_init(struct Qdisc *sch, struct nlattr *opt)
{
net_inc_ingress_queue();
+ sch->flags |= TCQ_F_CPUSTATS;
return 0;
}
static void ingress_destroy(struct Qdisc *sch)
{
- struct ingress_qdisc_data *p = qdisc_priv(sch);
+ struct net_device *dev = qdisc_dev(sch);
- tcf_destroy_chain(&p->filter_list);
+ tcf_destroy_chain(&dev->ingress_cl_list);
net_dec_ingress_queue();
}
@@ -110,6 +71,7 @@ static int ingress_dump(struct Qdisc *sch, struct sk_buff *skb)
nest = nla_nest_start(skb, TCA_OPTIONS);
if (nest == NULL)
goto nla_put_failure;
+
return nla_nest_end(skb, nest);
nla_put_failure:
@@ -130,8 +92,6 @@ static const struct Qdisc_class_ops ingress_class_ops = {
static struct Qdisc_ops ingress_qdisc_ops __read_mostly = {
.cl_ops = &ingress_class_ops,
.id = "ingress",
- .priv_size = sizeof(struct ingress_qdisc_data),
- .enqueue = ingress_enqueue,
.init = ingress_init,
.destroy = ingress_destroy,
.dump = ingress_dump,
@@ -148,6 +108,7 @@ static void __exit ingress_module_exit(void)
unregister_qdisc(&ingress_qdisc_ops);
}
-module_init(ingress_module_init)
-module_exit(ingress_module_exit)
+module_init(ingress_module_init);
+module_exit(ingress_module_exit);
+
MODULE_LICENSE("GPL");
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 956ead2cab9a..5abd1d9de989 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -440,9 +440,9 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
if (count > 1 && (skb2 = skb_clone(skb, GFP_ATOMIC)) != NULL) {
struct Qdisc *rootq = qdisc_root(sch);
u32 dupsave = q->duplicate; /* prevent duplicating a dup... */
- q->duplicate = 0;
- qdisc_enqueue_root(skb2, rootq);
+ q->duplicate = 0;
+ rootq->enqueue(skb2, rootq);
q->duplicate = dupsave;
}
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index 3ec7e88a43ca..b8d73bca683c 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -339,8 +339,7 @@ static struct qfq_aggregate *qfq_choose_next_agg(struct qfq_sched *);
static void qfq_destroy_agg(struct qfq_sched *q, struct qfq_aggregate *agg)
{
- if (!hlist_unhashed(&agg->nonfull_next))
- hlist_del_init(&agg->nonfull_next);
+ hlist_del_init(&agg->nonfull_next);
q->wsum -= agg->class_weight;
if (q->wsum != 0)
q->iwsum = ONE_FP / q->wsum;
diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c
index 5819dd82630d..4b815193326c 100644
--- a/net/sched/sch_sfb.c
+++ b/net/sched/sch_sfb.c
@@ -26,7 +26,6 @@
#include <net/ip.h>
#include <net/pkt_sched.h>
#include <net/inet_ecn.h>
-#include <net/flow_keys.h>
/*
* SFB uses two B[l][n] : L x N arrays of bins (L levels, N bins per level)
@@ -285,9 +284,9 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch)
int i;
u32 p_min = ~0;
u32 minqlen = ~0;
- u32 r, slot, salt, sfbhash;
+ u32 r, sfbhash;
+ u32 slot = q->slot;
int ret = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
- struct flow_keys keys;
if (unlikely(sch->q.qlen >= q->limit)) {
qdisc_qstats_overlimit(sch);
@@ -309,22 +308,17 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch)
fl = rcu_dereference_bh(q->filter_list);
if (fl) {
+ u32 salt;
+
/* If using external classifiers, get result and record it. */
if (!sfb_classify(skb, fl, &ret, &salt))
goto other_drop;
- keys.src = salt;
- keys.dst = 0;
- keys.ports = 0;
+ sfbhash = jhash_1word(salt, q->bins[slot].perturbation);
} else {
- skb_flow_dissect(skb, &keys);
+ sfbhash = skb_get_hash_perturb(skb, q->bins[slot].perturbation);
}
- slot = q->slot;
- sfbhash = jhash_3words((__force u32)keys.dst,
- (__force u32)keys.src,
- (__force u32)keys.ports,
- q->bins[slot].perturbation);
if (!sfbhash)
sfbhash = 1;
sfb_skb_cb(skb)->hashes[slot] = sfbhash;
@@ -356,10 +350,8 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch)
if (unlikely(p_min >= SFB_MAX_PROB)) {
/* Inelastic flow */
if (q->double_buffering) {
- sfbhash = jhash_3words((__force u32)keys.dst,
- (__force u32)keys.src,
- (__force u32)keys.ports,
- q->bins[slot].perturbation);
+ sfbhash = skb_get_hash_perturb(skb,
+ q->bins[slot].perturbation);
if (!sfbhash)
sfbhash = 1;
sfb_skb_cb(skb)->hashes[slot] = sfbhash;
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index b877140beda5..7d1492663360 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -23,7 +23,6 @@
#include <linux/vmalloc.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
-#include <net/flow_keys.h>
#include <net/red.h>
@@ -156,30 +155,10 @@ static inline struct sfq_head *sfq_dep_head(struct sfq_sched_data *q, sfq_index
return &q->dep[val - SFQ_MAX_FLOWS];
}
-/*
- * In order to be able to quickly rehash our queue when timer changes
- * q->perturbation, we store flow_keys in skb->cb[]
- */
-struct sfq_skb_cb {
- struct flow_keys keys;
-};
-
-static inline struct sfq_skb_cb *sfq_skb_cb(const struct sk_buff *skb)
-{
- qdisc_cb_private_validate(skb, sizeof(struct sfq_skb_cb));
- return (struct sfq_skb_cb *)qdisc_skb_cb(skb)->data;
-}
-
static unsigned int sfq_hash(const struct sfq_sched_data *q,
const struct sk_buff *skb)
{
- const struct flow_keys *keys = &sfq_skb_cb(skb)->keys;
- unsigned int hash;
-
- hash = jhash_3words((__force u32)keys->dst,
- (__force u32)keys->src ^ keys->ip_proto,
- (__force u32)keys->ports, q->perturbation);
- return hash & (q->divisor - 1);
+ return skb_get_hash_perturb(skb, q->perturbation) & (q->divisor - 1);
}
static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch,
@@ -196,10 +175,8 @@ static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch,
return TC_H_MIN(skb->priority);
fl = rcu_dereference_bh(q->filter_list);
- if (!fl) {
- skb_flow_dissect(skb, &sfq_skb_cb(skb)->keys);
+ if (!fl)
return sfq_hash(q, skb) + 1;
- }
*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
result = tc_classify(skb, fl, &res);