summaryrefslogtreecommitdiff
path: root/net/sched
diff options
context:
space:
mode:
Diffstat (limited to 'net/sched')
-rw-r--r--net/sched/Kconfig13
-rw-r--r--net/sched/Makefile1
-rw-r--r--net/sched/act_api.c61
-rw-r--r--net/sched/act_bpf.c5
-rw-r--r--net/sched/act_csum.c30
-rw-r--r--net/sched/act_ife.c7
-rw-r--r--net/sched/act_mirred.c21
-rw-r--r--net/sched/act_sample.c274
-rw-r--r--net/sched/cls_api.c4
-rw-r--r--net/sched/cls_bpf.c4
-rw-r--r--net/sched/cls_flower.c95
-rw-r--r--net/sched/cls_matchall.c22
-rw-r--r--net/sched/cls_u32.c1
-rw-r--r--net/sched/sch_api.c3
-rw-r--r--net/sched/sch_fq_codel.c6
-rw-r--r--net/sched/sch_generic.c2
-rw-r--r--net/sched/sch_netem.c2
-rw-r--r--net/sched/sch_teql.c5
18 files changed, 499 insertions, 57 deletions
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index 87956a768d1b..72cfa3a6bac0 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -650,6 +650,18 @@ config NET_ACT_MIRRED
To compile this code as a module, choose M here: the
module will be called act_mirred.
+config NET_ACT_SAMPLE
+ tristate "Traffic Sampling"
+ depends on NET_CLS_ACT
+ select PSAMPLE
+ ---help---
+ Say Y here to allow packet sampling tc action. The packet sample
+ action consists of statistically choosing packets and sampling
+ them using the psample module.
+
+ To compile this code as a module, choose M here: the
+ module will be called act_sample.
+
config NET_ACT_IPT
tristate "IPtables targets"
depends on NET_CLS_ACT && NETFILTER && IP_NF_IPTABLES
@@ -707,6 +719,7 @@ config NET_ACT_SKBEDIT
config NET_ACT_CSUM
tristate "Checksum Updating"
depends on NET_CLS_ACT && INET
+ select LIBCRC32C
---help---
Say Y here to update some common checksum after some direct
packet alterations.
diff --git a/net/sched/Makefile b/net/sched/Makefile
index 4bdda3634e0b..7b915d226de7 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -10,6 +10,7 @@ obj-$(CONFIG_NET_CLS_ACT) += act_api.o
obj-$(CONFIG_NET_ACT_POLICE) += act_police.o
obj-$(CONFIG_NET_ACT_GACT) += act_gact.o
obj-$(CONFIG_NET_ACT_MIRRED) += act_mirred.o
+obj-$(CONFIG_NET_ACT_SAMPLE) += act_sample.o
obj-$(CONFIG_NET_ACT_IPT) += act_ipt.o
obj-$(CONFIG_NET_ACT_NAT) += act_nat.o
obj-$(CONFIG_NET_ACT_PEDIT) += act_pedit.o
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 2095c83ce773..3c5e29ba6594 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -24,6 +24,7 @@
#include <net/net_namespace.h>
#include <net/sock.h>
#include <net/sch_generic.h>
+#include <net/pkt_cls.h>
#include <net/act_api.h>
#include <net/netlink.h>
@@ -33,6 +34,12 @@ static void free_tcf(struct rcu_head *head)
free_percpu(p->cpu_bstats);
free_percpu(p->cpu_qstats);
+
+ if (p->act_cookie) {
+ kfree(p->act_cookie->data);
+ kfree(p->act_cookie);
+ }
+
kfree(p);
}
@@ -426,11 +433,9 @@ int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions,
{
int ret = -1, i;
- if (skb->tc_verd & TC_NCLS) {
- skb->tc_verd = CLR_TC_NCLS(skb->tc_verd);
- ret = TC_ACT_OK;
- goto exec_done;
- }
+ if (skb_skip_tc_classify(skb))
+ return TC_ACT_OK;
+
for (i = 0; i < nr_actions; i++) {
const struct tc_action *a = actions[i];
@@ -439,9 +444,8 @@ repeat:
if (ret == TC_ACT_REPEAT)
goto repeat; /* we need a ttl - JHS */
if (ret != TC_ACT_PIPE)
- goto exec_done;
+ break;
}
-exec_done:
return ret;
}
EXPORT_SYMBOL(tcf_action_exec);
@@ -478,6 +482,12 @@ tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
goto nla_put_failure;
if (tcf_action_copy_stats(skb, a, 0))
goto nla_put_failure;
+ if (a->act_cookie) {
+ if (nla_put(skb, TCA_ACT_COOKIE, a->act_cookie->len,
+ a->act_cookie->data))
+ goto nla_put_failure;
+ }
+
nest = nla_nest_start(skb, TCA_OPTIONS);
if (nest == NULL)
goto nla_put_failure;
@@ -519,6 +529,22 @@ errout:
return err;
}
+int nla_memdup_cookie(struct tc_action *a, struct nlattr **tb)
+{
+ a->act_cookie = kzalloc(sizeof(*a->act_cookie), GFP_KERNEL);
+ if (!a->act_cookie)
+ return -ENOMEM;
+
+ a->act_cookie->data = nla_memdup(tb[TCA_ACT_COOKIE], GFP_KERNEL);
+ if (!a->act_cookie->data) {
+ kfree(a->act_cookie);
+ return -ENOMEM;
+ }
+ a->act_cookie->len = nla_len(tb[TCA_ACT_COOKIE]);
+
+ return 0;
+}
+
struct tc_action *tcf_action_init_1(struct net *net, struct nlattr *nla,
struct nlattr *est, char *name, int ovr,
int bind)
@@ -578,6 +604,22 @@ struct tc_action *tcf_action_init_1(struct net *net, struct nlattr *nla,
if (err < 0)
goto err_mod;
+ if (tb[TCA_ACT_COOKIE]) {
+ int cklen = nla_len(tb[TCA_ACT_COOKIE]);
+
+ if (cklen > TC_COOKIE_MAX_SIZE) {
+ err = -EINVAL;
+ tcf_hash_release(a, bind);
+ goto err_mod;
+ }
+
+ err = nla_memdup_cookie(a, tb);
+ if (err < 0) {
+ tcf_hash_release(a, bind);
+ goto err_mod;
+ }
+ }
+
/* module count goes up only when brand new policy is created
* if it exists and is only bound to in a_o->init() then
* ACT_P_CREATED is not returned (a zero is).
@@ -900,8 +942,6 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n,
goto err;
}
act->order = i;
- if (event == RTM_GETACTION)
- act->tcfa_refcnt++;
list_add_tail(&act->list, &actions);
}
@@ -914,7 +954,8 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n,
return ret;
}
err:
- tcf_action_destroy(&actions, 0);
+ if (event != RTM_GETACTION)
+ tcf_action_destroy(&actions, 0);
return ret;
}
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index 1c60317f0121..520baa41cba3 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -123,12 +123,11 @@ static int tcf_bpf_dump_ebpf_info(const struct tcf_bpf *prog,
nla_put_string(skb, TCA_ACT_BPF_NAME, prog->bpf_name))
return -EMSGSIZE;
- nla = nla_reserve(skb, TCA_ACT_BPF_DIGEST,
- sizeof(prog->filter->digest));
+ nla = nla_reserve(skb, TCA_ACT_BPF_TAG, sizeof(prog->filter->tag));
if (nla == NULL)
return -EMSGSIZE;
- memcpy(nla_data(nla), prog->filter->digest, nla_len(nla));
+ memcpy(nla_data(nla), prog->filter->tag, nla_len(nla));
return 0;
}
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index a0edd80a44db..e978ccd4402c 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -30,6 +30,7 @@
#include <net/tcp.h>
#include <net/udp.h>
#include <net/ip6_checksum.h>
+#include <net/sctp/checksum.h>
#include <net/act_api.h>
@@ -322,6 +323,25 @@ ignore_obscure_skb:
return 1;
}
+static int tcf_csum_sctp(struct sk_buff *skb, unsigned int ihl,
+ unsigned int ipl)
+{
+ struct sctphdr *sctph;
+
+ if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_SCTP)
+ return 1;
+
+ sctph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*sctph));
+ if (!sctph)
+ return 0;
+
+ sctph->checksum = sctp_compute_cksum(skb,
+ skb_network_offset(skb) + ihl);
+ skb->ip_summed = CHECKSUM_NONE;
+
+ return 1;
+}
+
static int tcf_csum_ipv4(struct sk_buff *skb, u32 update_flags)
{
const struct iphdr *iph;
@@ -365,6 +385,11 @@ static int tcf_csum_ipv4(struct sk_buff *skb, u32 update_flags)
ntohs(iph->tot_len), 1))
goto fail;
break;
+ case IPPROTO_SCTP:
+ if ((update_flags & TCA_CSUM_UPDATE_FLAG_SCTP) &&
+ !tcf_csum_sctp(skb, iph->ihl * 4, ntohs(iph->tot_len)))
+ goto fail;
+ break;
}
if (update_flags & TCA_CSUM_UPDATE_FLAG_IPV4HDR) {
@@ -481,6 +506,11 @@ static int tcf_csum_ipv6(struct sk_buff *skb, u32 update_flags)
pl + sizeof(*ip6h), 1))
goto fail;
goto done;
+ case IPPROTO_SCTP:
+ if ((update_flags & TCA_CSUM_UPDATE_FLAG_SCTP) &&
+ !tcf_csum_sctp(skb, hl, pl + sizeof(*ip6h)))
+ goto fail;
+ goto done;
default:
goto ignore_skb;
}
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 80b848d3f096..921fb20eaa7c 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -736,12 +736,11 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a,
u16 metalen = ife_get_sz(skb, ife);
int hdrm = metalen + skb->dev->hard_header_len + IFE_METAHDRLEN;
unsigned int skboff = skb->dev->hard_header_len;
- u32 at = G_TC_AT(skb->tc_verd);
int new_len = skb->len + hdrm;
bool exceed_mtu = false;
int err;
- if (at & AT_EGRESS) {
+ if (!skb_at_tc_ingress(skb)) {
if (new_len > skb->dev->mtu)
exceed_mtu = true;
}
@@ -773,7 +772,7 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a,
return TC_ACT_SHOT;
}
- if (!(at & AT_EGRESS))
+ if (skb_at_tc_ingress(skb))
skb_push(skb, skb->dev->hard_header_len);
iethh = (struct ethhdr *)skb->data;
@@ -816,7 +815,7 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a,
ether_addr_copy(oethh->h_dest, iethh->h_dest);
oethh->h_proto = htons(ife->eth_type);
- if (!(at & AT_EGRESS))
+ if (skb_at_tc_ingress(skb))
skb_pull(skb, skb->dev->hard_header_len);
spin_unlock(&ife->tcf_lock);
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 2d9fa6e0a1b4..84682f02b611 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -39,15 +39,15 @@ static bool tcf_mirred_is_act_redirect(int action)
return action == TCA_EGRESS_REDIR || action == TCA_INGRESS_REDIR;
}
-static u32 tcf_mirred_act_direction(int action)
+static bool tcf_mirred_act_wants_ingress(int action)
{
switch (action) {
case TCA_EGRESS_REDIR:
case TCA_EGRESS_MIRROR:
- return AT_EGRESS;
+ return false;
case TCA_INGRESS_REDIR:
case TCA_INGRESS_MIRROR:
- return AT_INGRESS;
+ return true;
default:
BUG();
}
@@ -170,7 +170,6 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a,
int retval, err = 0;
int m_eaction;
int mac_len;
- u32 at;
tcf_lastuse_update(&m->tcf_tm);
bstats_cpu_update(this_cpu_ptr(m->common.cpu_bstats), skb);
@@ -191,7 +190,6 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a,
goto out;
}
- at = G_TC_AT(skb->tc_verd);
skb2 = skb_clone(skb, GFP_ATOMIC);
if (!skb2)
goto out;
@@ -200,8 +198,9 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a,
* and devices expect a mac header on xmit, then mac push/pull is
* needed.
*/
- if (at != tcf_mirred_act_direction(m_eaction) && m_mac_header_xmit) {
- if (at & AT_EGRESS) {
+ if (skb_at_tc_ingress(skb) != tcf_mirred_act_wants_ingress(m_eaction) &&
+ m_mac_header_xmit) {
+ if (!skb_at_tc_ingress(skb)) {
/* caught at egress, act ingress: pull mac */
mac_len = skb_network_header(skb) - skb_mac_header(skb);
skb_pull_rcsum(skb2, mac_len);
@@ -212,12 +211,14 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a,
}
/* mirror is always swallowed */
- if (tcf_mirred_is_act_redirect(m_eaction))
- skb2->tc_verd = SET_TC_FROM(skb2->tc_verd, at);
+ if (tcf_mirred_is_act_redirect(m_eaction)) {
+ skb2->tc_redirected = 1;
+ skb2->tc_from_ingress = skb2->tc_at_ingress;
+ }
skb2->skb_iif = skb->dev->ifindex;
skb2->dev = dev;
- if (tcf_mirred_act_direction(m_eaction) & AT_EGRESS)
+ if (!tcf_mirred_act_wants_ingress(m_eaction))
err = dev_queue_xmit(skb2);
else
err = netif_receive_skb(skb2);
diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
new file mode 100644
index 000000000000..39229756de07
--- /dev/null
+++ b/net/sched/act_sample.c
@@ -0,0 +1,274 @@
+/*
+ * net/sched/act_sample.c - Packet sampling tc action
+ * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/skbuff.h>
+#include <linux/rtnetlink.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/gfp.h>
+#include <net/net_namespace.h>
+#include <net/netlink.h>
+#include <net/pkt_sched.h>
+#include <linux/tc_act/tc_sample.h>
+#include <net/tc_act/tc_sample.h>
+#include <net/psample.h>
+
+#include <linux/if_arp.h>
+
+#define SAMPLE_TAB_MASK 7
+static unsigned int sample_net_id;
+static struct tc_action_ops act_sample_ops;
+
+static const struct nla_policy sample_policy[TCA_SAMPLE_MAX + 1] = {
+ [TCA_SAMPLE_PARMS] = { .len = sizeof(struct tc_sample) },
+ [TCA_SAMPLE_RATE] = { .type = NLA_U32 },
+ [TCA_SAMPLE_TRUNC_SIZE] = { .type = NLA_U32 },
+ [TCA_SAMPLE_PSAMPLE_GROUP] = { .type = NLA_U32 },
+};
+
+static int tcf_sample_init(struct net *net, struct nlattr *nla,
+ struct nlattr *est, struct tc_action **a, int ovr,
+ int bind)
+{
+ struct tc_action_net *tn = net_generic(net, sample_net_id);
+ struct nlattr *tb[TCA_SAMPLE_MAX + 1];
+ struct psample_group *psample_group;
+ struct tc_sample *parm;
+ struct tcf_sample *s;
+ bool exists = false;
+ int ret;
+
+ if (!nla)
+ return -EINVAL;
+ ret = nla_parse_nested(tb, TCA_SAMPLE_MAX, nla, sample_policy);
+ if (ret < 0)
+ return ret;
+ if (!tb[TCA_SAMPLE_PARMS] || !tb[TCA_SAMPLE_RATE] ||
+ !tb[TCA_SAMPLE_PSAMPLE_GROUP])
+ return -EINVAL;
+
+ parm = nla_data(tb[TCA_SAMPLE_PARMS]);
+
+ exists = tcf_hash_check(tn, parm->index, a, bind);
+ if (exists && bind)
+ return 0;
+
+ if (!exists) {
+ ret = tcf_hash_create(tn, parm->index, est, a,
+ &act_sample_ops, bind, false);
+ if (ret)
+ return ret;
+ ret = ACT_P_CREATED;
+ } else {
+ tcf_hash_release(*a, bind);
+ if (!ovr)
+ return -EEXIST;
+ }
+ s = to_sample(*a);
+
+ ASSERT_RTNL();
+ s->tcf_action = parm->action;
+ s->rate = nla_get_u32(tb[TCA_SAMPLE_RATE]);
+ s->psample_group_num = nla_get_u32(tb[TCA_SAMPLE_PSAMPLE_GROUP]);
+ psample_group = psample_group_get(net, s->psample_group_num);
+ if (!psample_group)
+ return -ENOMEM;
+ RCU_INIT_POINTER(s->psample_group, psample_group);
+
+ if (tb[TCA_SAMPLE_TRUNC_SIZE]) {
+ s->truncate = true;
+ s->trunc_size = nla_get_u32(tb[TCA_SAMPLE_TRUNC_SIZE]);
+ }
+
+ if (ret == ACT_P_CREATED)
+ tcf_hash_insert(tn, *a);
+ return ret;
+}
+
+static void tcf_sample_cleanup_rcu(struct rcu_head *rcu)
+{
+ struct tcf_sample *s = container_of(rcu, struct tcf_sample, rcu);
+ struct psample_group *psample_group;
+
+ psample_group = rcu_dereference_protected(s->psample_group, 1);
+ RCU_INIT_POINTER(s->psample_group, NULL);
+ psample_group_put(psample_group);
+}
+
+static void tcf_sample_cleanup(struct tc_action *a, int bind)
+{
+ struct tcf_sample *s = to_sample(a);
+
+ call_rcu(&s->rcu, tcf_sample_cleanup_rcu);
+}
+
+static bool tcf_sample_dev_ok_push(struct net_device *dev)
+{
+ switch (dev->type) {
+ case ARPHRD_TUNNEL:
+ case ARPHRD_TUNNEL6:
+ case ARPHRD_SIT:
+ case ARPHRD_IPGRE:
+ case ARPHRD_VOID:
+ case ARPHRD_NONE:
+ return false;
+ default:
+ return true;
+ }
+}
+
+static int tcf_sample_act(struct sk_buff *skb, const struct tc_action *a,
+ struct tcf_result *res)
+{
+ struct tcf_sample *s = to_sample(a);
+ struct psample_group *psample_group;
+ int retval;
+ int size;
+ int iif;
+ int oif;
+
+ tcf_lastuse_update(&s->tcf_tm);
+ bstats_cpu_update(this_cpu_ptr(s->common.cpu_bstats), skb);
+ retval = READ_ONCE(s->tcf_action);
+
+ rcu_read_lock();
+ psample_group = rcu_dereference(s->psample_group);
+
+ /* randomly sample packets according to rate */
+ if (psample_group && (prandom_u32() % s->rate == 0)) {
+ if (!skb_at_tc_ingress(skb)) {
+ iif = skb->skb_iif;
+ oif = skb->dev->ifindex;
+ } else {
+ iif = skb->dev->ifindex;
+ oif = 0;
+ }
+
+ /* on ingress, the mac header gets popped, so push it back */
+ if (skb_at_tc_ingress(skb) && tcf_sample_dev_ok_push(skb->dev))
+ skb_push(skb, skb->mac_len);
+
+ size = s->truncate ? s->trunc_size : skb->len;
+ psample_sample_packet(psample_group, skb, size, iif, oif,
+ s->rate);
+
+ if (skb_at_tc_ingress(skb) && tcf_sample_dev_ok_push(skb->dev))
+ skb_pull(skb, skb->mac_len);
+ }
+
+ rcu_read_unlock();
+ return retval;
+}
+
+static int tcf_sample_dump(struct sk_buff *skb, struct tc_action *a,
+ int bind, int ref)
+{
+ unsigned char *b = skb_tail_pointer(skb);
+ struct tcf_sample *s = to_sample(a);
+ struct tc_sample opt = {
+ .index = s->tcf_index,
+ .action = s->tcf_action,
+ .refcnt = s->tcf_refcnt - ref,
+ .bindcnt = s->tcf_bindcnt - bind,
+ };
+ struct tcf_t t;
+
+ if (nla_put(skb, TCA_SAMPLE_PARMS, sizeof(opt), &opt))
+ goto nla_put_failure;
+
+ tcf_tm_dump(&t, &s->tcf_tm);
+ if (nla_put_64bit(skb, TCA_SAMPLE_TM, sizeof(t), &t, TCA_SAMPLE_PAD))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, TCA_SAMPLE_RATE, s->rate))
+ goto nla_put_failure;
+
+ if (s->truncate)
+ if (nla_put_u32(skb, TCA_SAMPLE_TRUNC_SIZE, s->trunc_size))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, TCA_SAMPLE_PSAMPLE_GROUP, s->psample_group_num))
+ goto nla_put_failure;
+ return skb->len;
+
+nla_put_failure:
+ nlmsg_trim(skb, b);
+ return -1;
+}
+
+static int tcf_sample_walker(struct net *net, struct sk_buff *skb,
+ struct netlink_callback *cb, int type,
+ const struct tc_action_ops *ops)
+{
+ struct tc_action_net *tn = net_generic(net, sample_net_id);
+
+ return tcf_generic_walker(tn, skb, cb, type, ops);
+}
+
+static int tcf_sample_search(struct net *net, struct tc_action **a, u32 index)
+{
+ struct tc_action_net *tn = net_generic(net, sample_net_id);
+
+ return tcf_hash_search(tn, a, index);
+}
+
+static struct tc_action_ops act_sample_ops = {
+ .kind = "sample",
+ .type = TCA_ACT_SAMPLE,
+ .owner = THIS_MODULE,
+ .act = tcf_sample_act,
+ .dump = tcf_sample_dump,
+ .init = tcf_sample_init,
+ .cleanup = tcf_sample_cleanup,
+ .walk = tcf_sample_walker,
+ .lookup = tcf_sample_search,
+ .size = sizeof(struct tcf_sample),
+};
+
+static __net_init int sample_init_net(struct net *net)
+{
+ struct tc_action_net *tn = net_generic(net, sample_net_id);
+
+ return tc_action_net_init(tn, &act_sample_ops, SAMPLE_TAB_MASK);
+}
+
+static void __net_exit sample_exit_net(struct net *net)
+{
+ struct tc_action_net *tn = net_generic(net, sample_net_id);
+
+ tc_action_net_exit(tn);
+}
+
+static struct pernet_operations sample_net_ops = {
+ .init = sample_init_net,
+ .exit = sample_exit_net,
+ .id = &sample_net_id,
+ .size = sizeof(struct tc_action_net),
+};
+
+static int __init sample_init_module(void)
+{
+ return tcf_register_action(&act_sample_ops, &sample_net_ops);
+}
+
+static void __exit sample_cleanup_module(void)
+{
+ tcf_unregister_action(&act_sample_ops, &sample_net_ops);
+}
+
+module_init(sample_init_module);
+module_exit(sample_cleanup_module);
+
+MODULE_AUTHOR("Yotam Gigi <yotamg@mellanox.com>");
+MODULE_DESCRIPTION("Packet sampling action");
+MODULE_LICENSE("GPL v2");
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 3fbba79a4ef0..1ecdf809b5fa 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -148,13 +148,15 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n)
unsigned long cl;
unsigned long fh;
int err;
- int tp_created = 0;
+ int tp_created;
if ((n->nlmsg_type != RTM_GETTFILTER) &&
!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
return -EPERM;
replay:
+ tp_created = 0;
+
err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, NULL);
if (err < 0)
return err;
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index adc776048d1a..d9c97018317d 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -555,11 +555,11 @@ static int cls_bpf_dump_ebpf_info(const struct cls_bpf_prog *prog,
nla_put_string(skb, TCA_BPF_NAME, prog->bpf_name))
return -EMSGSIZE;
- nla = nla_reserve(skb, TCA_BPF_DIGEST, sizeof(prog->filter->digest));
+ nla = nla_reserve(skb, TCA_BPF_TAG, sizeof(prog->filter->tag));
if (nla == NULL)
return -EMSGSIZE;
- memcpy(nla_data(nla), prog->filter->digest, nla_len(nla));
+ memcpy(nla_data(nla), prog->filter->tag, nla_len(nla));
return 0;
}
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 333f8e268431..9e74b0fa4b89 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -40,6 +40,7 @@ struct fl_flow_key {
};
struct flow_dissector_key_ports tp;
struct flow_dissector_key_icmp icmp;
+ struct flow_dissector_key_arp arp;
struct flow_dissector_key_keyid enc_key_id;
union {
struct flow_dissector_key_ipv4_addrs enc_ipv4;
@@ -133,6 +134,14 @@ static void fl_clear_masked_range(struct fl_flow_key *key,
memset(fl_key_get_start(key, mask), 0, fl_mask_range(mask));
}
+static struct cls_fl_filter *fl_lookup(struct cls_fl_head *head,
+ struct fl_flow_key *mkey)
+{
+ return rhashtable_lookup_fast(&head->ht,
+ fl_key_get_start(mkey, &head->mask),
+ head->ht_params);
+}
+
static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp,
struct tcf_result *res)
{
@@ -153,10 +162,14 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp,
switch (ip_tunnel_info_af(info)) {
case AF_INET:
+ skb_key.enc_control.addr_type =
+ FLOW_DISSECTOR_KEY_IPV4_ADDRS;
skb_key.enc_ipv4.src = key->u.ipv4.src;
skb_key.enc_ipv4.dst = key->u.ipv4.dst;
break;
case AF_INET6:
+ skb_key.enc_control.addr_type =
+ FLOW_DISSECTOR_KEY_IPV6_ADDRS;
skb_key.enc_ipv6.src = key->u.ipv6.src;
skb_key.enc_ipv6.dst = key->u.ipv6.dst;
break;
@@ -176,9 +189,7 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp,
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);
+ f = fl_lookup(head, &skb_mkey);
if (f && !tc_skip_sw(f->flags)) {
*res = f->res;
return tcf_exts_exec(skb, &f->exts, res);
@@ -397,6 +408,16 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = {
[TCA_FLOWER_KEY_ICMPV6_TYPE_MASK] = { .type = NLA_U8 },
[TCA_FLOWER_KEY_ICMPV6_CODE] = { .type = NLA_U8 },
[TCA_FLOWER_KEY_ICMPV6_CODE_MASK] = { .type = NLA_U8 },
+ [TCA_FLOWER_KEY_ARP_SIP] = { .type = NLA_U32 },
+ [TCA_FLOWER_KEY_ARP_SIP_MASK] = { .type = NLA_U32 },
+ [TCA_FLOWER_KEY_ARP_TIP] = { .type = NLA_U32 },
+ [TCA_FLOWER_KEY_ARP_TIP_MASK] = { .type = NLA_U32 },
+ [TCA_FLOWER_KEY_ARP_OP] = { .type = NLA_U8 },
+ [TCA_FLOWER_KEY_ARP_OP_MASK] = { .type = NLA_U8 },
+ [TCA_FLOWER_KEY_ARP_SHA] = { .len = ETH_ALEN },
+ [TCA_FLOWER_KEY_ARP_SHA_MASK] = { .len = ETH_ALEN },
+ [TCA_FLOWER_KEY_ARP_THA] = { .len = ETH_ALEN },
+ [TCA_FLOWER_KEY_ARP_THA_MASK] = { .len = ETH_ALEN },
};
static void fl_set_key_val(struct nlattr **tb,
@@ -568,6 +589,23 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
&mask->icmp.code,
TCA_FLOWER_KEY_ICMPV4_CODE_MASK,
sizeof(key->icmp.code));
+ } else if (key->basic.n_proto == htons(ETH_P_ARP) ||
+ key->basic.n_proto == htons(ETH_P_RARP)) {
+ fl_set_key_val(tb, &key->arp.sip, TCA_FLOWER_KEY_ARP_SIP,
+ &mask->arp.sip, TCA_FLOWER_KEY_ARP_SIP_MASK,
+ sizeof(key->arp.sip));
+ fl_set_key_val(tb, &key->arp.tip, TCA_FLOWER_KEY_ARP_TIP,
+ &mask->arp.tip, TCA_FLOWER_KEY_ARP_TIP_MASK,
+ sizeof(key->arp.tip));
+ fl_set_key_val(tb, &key->arp.op, TCA_FLOWER_KEY_ARP_OP,
+ &mask->arp.op, TCA_FLOWER_KEY_ARP_OP_MASK,
+ sizeof(key->arp.op));
+ fl_set_key_val(tb, key->arp.sha, TCA_FLOWER_KEY_ARP_SHA,
+ mask->arp.sha, TCA_FLOWER_KEY_ARP_SHA_MASK,
+ sizeof(key->arp.sha));
+ fl_set_key_val(tb, key->arp.tha, TCA_FLOWER_KEY_ARP_THA,
+ mask->arp.tha, TCA_FLOWER_KEY_ARP_THA_MASK,
+ sizeof(key->arp.tha));
}
if (tb[TCA_FLOWER_KEY_ENC_IPV4_SRC] ||
@@ -685,6 +723,8 @@ static void fl_init_dissector(struct cls_fl_head *head,
FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
FLOW_DISSECTOR_KEY_ICMP, icmp);
FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+ FLOW_DISSECTOR_KEY_ARP, arp);
+ FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
FLOW_DISSECTOR_KEY_VLAN, vlan);
FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
FLOW_DISSECTOR_KEY_ENC_KEYID, enc_key_id);
@@ -792,23 +832,31 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
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 nlattr **tb;
struct fl_flow_mask mask = {};
int err;
if (!tca[TCA_OPTIONS])
return -EINVAL;
+ tb = kcalloc(TCA_FLOWER_MAX + 1, sizeof(struct nlattr *), GFP_KERNEL);
+ if (!tb)
+ return -ENOBUFS;
+
err = nla_parse_nested(tb, TCA_FLOWER_MAX, tca[TCA_OPTIONS], fl_policy);
if (err < 0)
- return err;
+ goto errout_tb;
- if (fold && handle && fold->handle != handle)
- return -EINVAL;
+ if (fold && handle && fold->handle != handle) {
+ err = -EINVAL;
+ goto errout_tb;
+ }
fnew = kzalloc(sizeof(*fnew), GFP_KERNEL);
- if (!fnew)
- return -ENOBUFS;
+ if (!fnew) {
+ err = -ENOBUFS;
+ goto errout_tb;
+ }
err = tcf_exts_init(&fnew->exts, TCA_FLOWER_ACT, 0);
if (err < 0)
@@ -841,6 +889,11 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
goto errout;
if (!tc_skip_sw(fnew->flags)) {
+ if (!fold && fl_lookup(head, &fnew->mkey)) {
+ err = -EEXIST;
+ goto errout;
+ }
+
err = rhashtable_insert_fast(&head->ht, &fnew->ht_node,
head->ht_params);
if (err)
@@ -874,11 +927,14 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
list_add_tail_rcu(&fnew->list, &head->filters);
}
+ kfree(tb);
return 0;
errout:
tcf_exts_destroy(&fnew->exts);
kfree(fnew);
+errout_tb:
+ kfree(tb);
return err;
}
@@ -1108,6 +1164,27 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
TCA_FLOWER_KEY_ICMPV6_CODE_MASK,
sizeof(key->icmp.code))))
goto nla_put_failure;
+ else if ((key->basic.n_proto == htons(ETH_P_ARP) ||
+ key->basic.n_proto == htons(ETH_P_RARP)) &&
+ (fl_dump_key_val(skb, &key->arp.sip,
+ TCA_FLOWER_KEY_ARP_SIP, &mask->arp.sip,
+ TCA_FLOWER_KEY_ARP_SIP_MASK,
+ sizeof(key->arp.sip)) ||
+ fl_dump_key_val(skb, &key->arp.tip,
+ TCA_FLOWER_KEY_ARP_TIP, &mask->arp.tip,
+ TCA_FLOWER_KEY_ARP_TIP_MASK,
+ sizeof(key->arp.tip)) ||
+ fl_dump_key_val(skb, &key->arp.op,
+ TCA_FLOWER_KEY_ARP_OP, &mask->arp.op,
+ TCA_FLOWER_KEY_ARP_OP_MASK,
+ sizeof(key->arp.op)) ||
+ fl_dump_key_val(skb, key->arp.sha, TCA_FLOWER_KEY_ARP_SHA,
+ mask->arp.sha, TCA_FLOWER_KEY_ARP_SHA_MASK,
+ sizeof(key->arp.sha)) ||
+ fl_dump_key_val(skb, key->arp.tha, TCA_FLOWER_KEY_ARP_THA,
+ mask->arp.tha, TCA_FLOWER_KEY_ARP_THA_MASK,
+ sizeof(key->arp.tha))))
+ goto nla_put_failure;
if (key->enc_control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS &&
(fl_dump_key_val(skb, &key->enc_ipv4.src,
diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index f935429bd5ef..fcecf5aac666 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -141,10 +141,12 @@ static int mall_set_parms(struct net *net, struct tcf_proto *tp,
struct tcf_exts e;
int err;
- tcf_exts_init(&e, TCA_MATCHALL_ACT, 0);
+ err = tcf_exts_init(&e, TCA_MATCHALL_ACT, 0);
+ if (err)
+ return err;
err = tcf_exts_validate(net, tp, tb, est, &e, ovr);
if (err < 0)
- return err;
+ goto errout;
if (tb[TCA_MATCHALL_CLASSID]) {
f->res.classid = nla_get_u32(tb[TCA_MATCHALL_CLASSID]);
@@ -154,6 +156,9 @@ static int mall_set_parms(struct net *net, struct tcf_proto *tp,
tcf_exts_change(tp, &f->exts, &e);
return 0;
+errout:
+ tcf_exts_destroy(&e);
+ return err;
}
static int mall_change(struct net *net, struct sk_buff *in_skb,
@@ -193,7 +198,9 @@ static int mall_change(struct net *net, struct sk_buff *in_skb,
if (!f)
return -ENOBUFS;
- tcf_exts_init(&f->exts, TCA_MATCHALL_ACT, 0);
+ err = tcf_exts_init(&f->exts, TCA_MATCHALL_ACT, 0);
+ if (err)
+ goto err_exts_init;
if (!handle)
handle = 1;
@@ -202,13 +209,13 @@ static int mall_change(struct net *net, struct sk_buff *in_skb,
err = mall_set_parms(net, tp, f, base, tb, tca[TCA_RATE], ovr);
if (err)
- goto errout;
+ goto err_set_parms;
if (tc_should_offload(dev, tp, flags)) {
err = mall_replace_hw_filter(tp, f, (unsigned long) f);
if (err) {
if (tc_skip_sw(flags))
- goto errout;
+ goto err_replace_hw_filter;
else
err = 0;
}
@@ -219,7 +226,10 @@ static int mall_change(struct net *net, struct sk_buff *in_skb,
return 0;
-errout:
+err_replace_hw_filter:
+err_set_parms:
+ tcf_exts_destroy(&f->exts);
+err_exts_init:
kfree(f);
return err;
}
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index ae83c3aec308..a6ec3e4b57ab 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -334,7 +334,6 @@ static int u32_init(struct tcf_proto *tp)
if (root_ht == NULL)
return -ENOBUFS;
- root_ht->divisor = 0;
root_ht->refcnt++;
root_ht->handle = tp_c ? gen_new_htid(tp_c) : 0x80000000;
root_ht->prio = tp->prio;
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index d7b93429f0cc..ef53ede11590 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1861,6 +1861,7 @@ int tc_classify(struct sk_buff *skb, const struct tcf_proto *tp,
{
__be16 protocol = tc_skb_protocol(skb);
#ifdef CONFIG_NET_CLS_ACT
+ const int max_reclassify_loop = 4;
const struct tcf_proto *old_tp = tp;
int limit = 0;
@@ -1885,7 +1886,7 @@ reclassify:
return TC_ACT_UNSPEC; /* signal: continue lookup */
#ifdef CONFIG_NET_CLS_ACT
reset:
- if (unlikely(limit++ >= MAX_REC_LOOP)) {
+ if (unlikely(limit++ >= max_reclassify_loop)) {
net_notice_ratelimited("%s: reclassify loop, rule prio %u, protocol %02x\n",
tp->q->ops->id, tp->prio & 0xffff,
ntohs(tp->protocol));
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index a5ea0e9b6be4..2f50e4c72fb4 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -57,7 +57,6 @@ struct fq_codel_sched_data {
struct fq_codel_flow *flows; /* Flows table [flows_cnt] */
u32 *backlogs; /* backlog table [flows_cnt] */
u32 flows_cnt; /* number of flows */
- u32 perturbation; /* hash perturbation */
u32 quantum; /* psched_mtu(qdisc_dev(sch)); */
u32 drop_batch_size;
u32 memory_limit;
@@ -75,9 +74,7 @@ struct fq_codel_sched_data {
static unsigned int fq_codel_hash(const struct fq_codel_sched_data *q,
struct sk_buff *skb)
{
- u32 hash = skb_get_hash_perturb(skb, q->perturbation);
-
- return reciprocal_scale(hash, q->flows_cnt);
+ return reciprocal_scale(skb_get_hash(skb), q->flows_cnt);
}
static unsigned int fq_codel_classify(struct sk_buff *skb, struct Qdisc *sch,
@@ -482,7 +479,6 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt)
q->memory_limit = 32 << 20; /* 32 MBytes */
q->drop_batch_size = 64;
q->quantum = psched_mtu(qdisc_dev(sch));
- q->perturbation = prandom_u32();
INIT_LIST_HEAD(&q->new_flows);
INIT_LIST_HEAD(&q->old_flows);
codel_params_init(&q->cparams);
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 6eb9c8e88519..b052b27a984e 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -247,7 +247,7 @@ static inline int qdisc_restart(struct Qdisc *q, int *packets)
void __qdisc_run(struct Qdisc *q)
{
- int quota = weight_p;
+ int quota = dev_tx_weight;
int packets;
while (qdisc_restart(q, &packets)) {
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index bcfadfdea8e0..c8bb62a1e744 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -626,7 +626,7 @@ deliver:
* If it's at ingress let's pretend the delay is
* from the network (tstamp will be updated).
*/
- if (G_TC_FROM(skb->tc_verd) & AT_INGRESS)
+ if (skb->tc_redirected && skb->tc_from_ingress)
skb->tstamp = 0;
#endif
diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c
index b0196366d58d..9fe6b427afed 100644
--- a/net/sched/sch_teql.c
+++ b/net/sched/sch_teql.c
@@ -401,8 +401,8 @@ static int teql_master_close(struct net_device *dev)
return 0;
}
-static struct rtnl_link_stats64 *teql_master_stats64(struct net_device *dev,
- struct rtnl_link_stats64 *stats)
+static void teql_master_stats64(struct net_device *dev,
+ struct rtnl_link_stats64 *stats)
{
struct teql_master *m = netdev_priv(dev);
@@ -410,7 +410,6 @@ static struct rtnl_link_stats64 *teql_master_stats64(struct net_device *dev,
stats->tx_bytes = m->tx_bytes;
stats->tx_errors = m->tx_errors;
stats->tx_dropped = m->tx_dropped;
- return stats;
}
static int teql_master_mtu(struct net_device *dev, int new_mtu)
generated by cgit v1.2.3 (git 2.39.0) at 2025-03-05 17:26:06 +0300