summaryrefslogtreecommitdiff
path: root/net/sched
diff options
context:
space:
mode:
Diffstat (limited to 'net/sched')
-rw-r--r--net/sched/act_api.c9
-rw-r--r--net/sched/act_bpf.c20
-rw-r--r--net/sched/act_connmark.c2
-rw-r--r--net/sched/act_csum.c2
-rw-r--r--net/sched/act_gact.c2
-rw-r--r--net/sched/act_ife.c2
-rw-r--r--net/sched/act_ipt.c16
-rw-r--r--net/sched/act_mirred.c85
-rw-r--r--net/sched/act_nat.c2
-rw-r--r--net/sched/act_pedit.c2
-rw-r--r--net/sched/act_police.c23
-rw-r--r--net/sched/act_simple.c2
-rw-r--r--net/sched/act_skbedit.c23
-rw-r--r--net/sched/act_skbmod.c2
-rw-r--r--net/sched/act_tunnel_key.c17
-rw-r--r--net/sched/act_vlan.c2
-rw-r--r--net/sched/cls_api.c24
-rw-r--r--net/sched/cls_bpf.c49
-rw-r--r--net/sched/cls_flower.c296
-rw-r--r--net/sched/em_ipset.c17
-rw-r--r--net/sched/em_meta.c9
-rw-r--r--net/sched/sch_api.c13
-rw-r--r--net/sched/sch_cbq.c6
-rw-r--r--net/sched/sch_drr.c6
-rw-r--r--net/sched/sch_fq.c4
-rw-r--r--net/sched/sch_generic.c2
-rw-r--r--net/sched/sch_hfsc.c6
-rw-r--r--net/sched/sch_htb.c6
-rw-r--r--net/sched/sch_qfq.c8
-rw-r--r--net/sched/sch_teql.c5
30 files changed, 478 insertions, 184 deletions
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index f893d180da1c..2095c83ce773 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -41,8 +41,7 @@ static void tcf_hash_destroy(struct tcf_hashinfo *hinfo, struct tc_action *p)
spin_lock_bh(&hinfo->lock);
hlist_del(&p->tcfa_head);
spin_unlock_bh(&hinfo->lock);
- gen_kill_estimator(&p->tcfa_bstats,
- &p->tcfa_rate_est);
+ gen_kill_estimator(&p->tcfa_rate_est);
/*
* gen_estimator est_timer() might access p->tcfa_lock
* or bstats, wait a RCU grace period before freeing p
@@ -237,8 +236,7 @@ EXPORT_SYMBOL(tcf_hash_check);
void tcf_hash_cleanup(struct tc_action *a, struct nlattr *est)
{
if (est)
- gen_kill_estimator(&a->tcfa_bstats,
- &a->tcfa_rate_est);
+ gen_kill_estimator(&a->tcfa_rate_est);
call_rcu(&a->tcfa_rcu, free_tcf);
}
EXPORT_SYMBOL(tcf_hash_cleanup);
@@ -670,8 +668,7 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *p,
goto errout;
if (gnet_stats_copy_basic(NULL, &d, p->cpu_bstats, &p->tcfa_bstats) < 0 ||
- gnet_stats_copy_rate_est(&d, &p->tcfa_bstats,
- &p->tcfa_rate_est) < 0 ||
+ gnet_stats_copy_rate_est(&d, &p->tcfa_rate_est) < 0 ||
gnet_stats_copy_queue(&d, p->cpu_qstats,
&p->tcfa_qstats,
p->tcfa_qstats.qlen) < 0)
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index 1d3960033f61..1c60317f0121 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -28,12 +28,11 @@ struct tcf_bpf_cfg {
struct bpf_prog *filter;
struct sock_filter *bpf_ops;
const char *bpf_name;
- u32 bpf_fd;
u16 bpf_num_ops;
bool is_ebpf;
};
-static int bpf_net_id;
+static unsigned int bpf_net_id;
static struct tc_action_ops act_bpf_ops;
static int tcf_bpf(struct sk_buff *skb, const struct tc_action *act,
@@ -118,13 +117,19 @@ static int tcf_bpf_dump_bpf_info(const struct tcf_bpf *prog,
static int tcf_bpf_dump_ebpf_info(const struct tcf_bpf *prog,
struct sk_buff *skb)
{
- if (nla_put_u32(skb, TCA_ACT_BPF_FD, prog->bpf_fd))
- return -EMSGSIZE;
+ struct nlattr *nla;
if (prog->bpf_name &&
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));
+ if (nla == NULL)
+ return -EMSGSIZE;
+
+ memcpy(nla_data(nla), prog->filter->digest, nla_len(nla));
+
return 0;
}
@@ -226,16 +231,13 @@ static int tcf_bpf_init_from_efd(struct nlattr **tb, struct tcf_bpf_cfg *cfg)
return PTR_ERR(fp);
if (tb[TCA_ACT_BPF_NAME]) {
- name = kmemdup(nla_data(tb[TCA_ACT_BPF_NAME]),
- nla_len(tb[TCA_ACT_BPF_NAME]),
- GFP_KERNEL);
+ name = nla_memdup(tb[TCA_ACT_BPF_NAME], GFP_KERNEL);
if (!name) {
bpf_prog_put(fp);
return -ENOMEM;
}
}
- cfg->bpf_fd = bpf_fd;
cfg->bpf_name = name;
cfg->filter = fp;
cfg->is_ebpf = true;
@@ -334,8 +336,6 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
if (cfg.bpf_num_ops)
prog->bpf_num_ops = cfg.bpf_num_ops;
- if (cfg.bpf_fd)
- prog->bpf_fd = cfg.bpf_fd;
prog->tcf_action = parm->action;
rcu_assign_pointer(prog->filter, cfg.filter);
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index eae07a2e774d..ab8062909962 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -30,7 +30,7 @@
#define CONNMARK_TAB_MASK 3
-static int connmark_net_id;
+static unsigned int connmark_net_id;
static struct tc_action_ops act_connmark_ops;
static int tcf_connmark(struct sk_buff *skb, const struct tc_action *a,
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index e0defcef376d..a0edd80a44db 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -42,7 +42,7 @@ static const struct nla_policy csum_policy[TCA_CSUM_MAX + 1] = {
[TCA_CSUM_PARMS] = { .len = sizeof(struct tc_csum), },
};
-static int csum_net_id;
+static unsigned int csum_net_id;
static struct tc_action_ops act_csum_ops;
static int tcf_csum_init(struct net *net, struct nlattr *nla,
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index e0aa30f83c6c..e6c874a2b283 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -25,7 +25,7 @@
#define GACT_TAB_MASK 15
-static int gact_net_id;
+static unsigned int gact_net_id;
static struct tc_action_ops act_gact_ops;
#ifdef CONFIG_GACT_PROB
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 95c463cbb9a6..80b848d3f096 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -35,7 +35,7 @@
#define IFE_TAB_MASK 15
-static int ife_net_id;
+static unsigned int ife_net_id;
static int max_metacnt = IFE_META_MAX + 1;
static struct tc_action_ops act_ife_ops;
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 378c1c976058..992ef8d624f1 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -30,10 +30,10 @@
#define IPT_TAB_MASK 15
-static int ipt_net_id;
+static unsigned int ipt_net_id;
static struct tc_action_ops act_ipt_ops;
-static int xt_net_id;
+static unsigned int xt_net_id;
static struct tc_action_ops act_xt_ops;
static int ipt_init_target(struct xt_entry_target *t, char *table,
@@ -213,6 +213,12 @@ static int tcf_ipt(struct sk_buff *skb, const struct tc_action *a,
int ret = 0, result = 0;
struct tcf_ipt *ipt = to_ipt(a);
struct xt_action_param par;
+ struct nf_hook_state state = {
+ .net = dev_net(skb->dev),
+ .in = skb->dev,
+ .hook = ipt->tcfi_hook,
+ .pf = NFPROTO_IPV4,
+ };
if (skb_unclone(skb, GFP_ATOMIC))
return TC_ACT_UNSPEC;
@@ -226,13 +232,9 @@ static int tcf_ipt(struct sk_buff *skb, const struct tc_action *a,
* worry later - danger - this API seems to have changed
* from earlier kernels
*/
- par.net = dev_net(skb->dev);
- par.in = skb->dev;
- par.out = NULL;
- par.hooknum = ipt->tcfi_hook;
+ par.state = &state;
par.target = ipt->tcfi_t->u.kernel.target;
par.targinfo = ipt->tcfi_t->data;
- par.family = NFPROTO_IPV4;
ret = par.target->target(skb, &par);
switch (ret) {
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 6b07fba5770b..2d9fa6e0a1b4 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -21,6 +21,7 @@
#include <linux/module.h>
#include <linux/init.h>
#include <linux/gfp.h>
+#include <linux/if_arp.h>
#include <net/net_namespace.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
@@ -33,6 +34,25 @@
static LIST_HEAD(mirred_list);
static DEFINE_SPINLOCK(mirred_list_lock);
+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)
+{
+ switch (action) {
+ case TCA_EGRESS_REDIR:
+ case TCA_EGRESS_MIRROR:
+ return AT_EGRESS;
+ case TCA_INGRESS_REDIR:
+ case TCA_INGRESS_MIRROR:
+ return AT_INGRESS;
+ default:
+ BUG();
+ }
+}
+
static void tcf_mirred_release(struct tc_action *a, int bind)
{
struct tcf_mirred *m = to_mirred(a);
@@ -51,7 +71,7 @@ static const struct nla_policy mirred_policy[TCA_MIRRED_MAX + 1] = {
[TCA_MIRRED_PARMS] = { .len = sizeof(struct tc_mirred) },
};
-static int mirred_net_id;
+static unsigned int mirred_net_id;
static struct tc_action_ops act_mirred_ops;
static int tcf_mirred_init(struct net *net, struct nlattr *nla,
@@ -60,11 +80,12 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
{
struct tc_action_net *tn = net_generic(net, mirred_net_id);
struct nlattr *tb[TCA_MIRRED_MAX + 1];
+ bool mac_header_xmit = false;
struct tc_mirred *parm;
struct tcf_mirred *m;
struct net_device *dev;
- int ret, ok_push = 0;
bool exists = false;
+ int ret;
if (nla == NULL)
return -EINVAL;
@@ -82,6 +103,8 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
switch (parm->eaction) {
case TCA_EGRESS_MIRROR:
case TCA_EGRESS_REDIR:
+ case TCA_INGRESS_REDIR:
+ case TCA_INGRESS_MIRROR:
break;
default:
if (exists)
@@ -95,19 +118,7 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
tcf_hash_release(*a, bind);
return -ENODEV;
}
- switch (dev->type) {
- case ARPHRD_TUNNEL:
- case ARPHRD_TUNNEL6:
- case ARPHRD_SIT:
- case ARPHRD_IPGRE:
- case ARPHRD_VOID:
- case ARPHRD_NONE:
- ok_push = 0;
- break;
- default:
- ok_push = 1;
- break;
- }
+ mac_header_xmit = dev_is_mac_header_xmit(dev);
} else {
dev = NULL;
}
@@ -136,7 +147,7 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
dev_put(rcu_dereference_protected(m->tcfm_dev, 1));
dev_hold(dev);
rcu_assign_pointer(m->tcfm_dev, dev);
- m->tcfm_ok_push = ok_push;
+ m->tcfm_mac_header_xmit = mac_header_xmit;
}
if (ret == ACT_P_CREATED) {
@@ -153,15 +164,20 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a,
struct tcf_result *res)
{
struct tcf_mirred *m = to_mirred(a);
+ bool m_mac_header_xmit;
struct net_device *dev;
struct sk_buff *skb2;
- int retval, err;
+ 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);
rcu_read_lock();
+ m_mac_header_xmit = READ_ONCE(m->tcfm_mac_header_xmit);
+ m_eaction = READ_ONCE(m->tcfm_eaction);
retval = READ_ONCE(m->tcf_action);
dev = rcu_dereference(m->tcfm_dev);
if (unlikely(!dev)) {
@@ -180,23 +196,36 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a,
if (!skb2)
goto out;
- if (!(at & AT_EGRESS)) {
- if (m->tcfm_ok_push)
+ /* If action's target direction differs than filter's direction,
+ * 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) {
+ /* caught at egress, act ingress: pull mac */
+ mac_len = skb_network_header(skb) - skb_mac_header(skb);
+ skb_pull_rcsum(skb2, mac_len);
+ } else {
+ /* caught at ingress, act egress: push mac */
skb_push_rcsum(skb2, skb->mac_len);
+ }
}
/* mirror is always swallowed */
- if (m->tcfm_eaction != TCA_EGRESS_MIRROR)
+ if (tcf_mirred_is_act_redirect(m_eaction))
skb2->tc_verd = SET_TC_FROM(skb2->tc_verd, at);
skb2->skb_iif = skb->dev->ifindex;
skb2->dev = dev;
- err = dev_queue_xmit(skb2);
+ if (tcf_mirred_act_direction(m_eaction) & AT_EGRESS)
+ err = dev_queue_xmit(skb2);
+ else
+ err = netif_receive_skb(skb2);
if (err) {
out:
qstats_overlimit_inc(this_cpu_ptr(m->common.cpu_qstats));
- if (m->tcfm_eaction != TCA_EGRESS_MIRROR)
+ if (tcf_mirred_is_act_redirect(m_eaction))
retval = TC_ACT_SHOT;
}
rcu_read_unlock();
@@ -286,6 +315,17 @@ static struct notifier_block mirred_device_notifier = {
.notifier_call = mirred_device_event,
};
+static int tcf_mirred_device(const struct tc_action *a, struct net *net,
+ struct net_device **mirred_dev)
+{
+ int ifindex = tcf_mirred_ifindex(a);
+
+ *mirred_dev = __dev_get_by_index(net, ifindex);
+ if (!*mirred_dev)
+ return -EINVAL;
+ return 0;
+}
+
static struct tc_action_ops act_mirred_ops = {
.kind = "mirred",
.type = TCA_ACT_MIRRED,
@@ -298,6 +338,7 @@ static struct tc_action_ops act_mirred_ops = {
.walk = tcf_mirred_walker,
.lookup = tcf_mirred_search,
.size = sizeof(struct tcf_mirred),
+ .get_dev = tcf_mirred_device,
};
static __net_init int mirred_init_net(struct net *net)
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index 8e8b0cc30704..9b6aec665495 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -31,7 +31,7 @@
#define NAT_TAB_MASK 15
-static int nat_net_id;
+static unsigned int nat_net_id;
static struct tc_action_ops act_nat_ops;
static const struct nla_policy nat_policy[TCA_NAT_MAX + 1] = {
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index cf9b2fe8eac6..b27c4daec88f 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -25,7 +25,7 @@
#define PEDIT_TAB_MASK 15
-static int pedit_net_id;
+static unsigned int pedit_net_id;
static struct tc_action_ops act_pedit_ops;
static const struct nla_policy pedit_policy[TCA_PEDIT_MAX + 1] = {
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index d1bd248fe146..0ba91d1ce994 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -55,7 +55,7 @@ struct tc_police_compat {
/* Each policer is serialized by its individual spinlock */
-static int police_net_id;
+static unsigned int police_net_id;
static struct tc_action_ops act_police_ops;
static int tcf_act_police_walker(struct net *net, struct sk_buff *skb,
@@ -142,8 +142,7 @@ static int tcf_act_police_init(struct net *net, struct nlattr *nla,
goto failure_unlock;
} else if (tb[TCA_POLICE_AVRATE] &&
(ret == ACT_P_CREATED ||
- !gen_estimator_active(&police->tcf_bstats,
- &police->tcf_rate_est))) {
+ !gen_estimator_active(&police->tcf_rate_est))) {
err = -EINVAL;
goto failure_unlock;
}
@@ -216,13 +215,17 @@ static int tcf_act_police(struct sk_buff *skb, const struct tc_action *a,
bstats_update(&police->tcf_bstats, skb);
tcf_lastuse_update(&police->tcf_tm);
- if (police->tcfp_ewma_rate &&
- police->tcf_rate_est.bps >= police->tcfp_ewma_rate) {
- police->tcf_qstats.overlimits++;
- if (police->tcf_action == TC_ACT_SHOT)
- police->tcf_qstats.drops++;
- spin_unlock(&police->tcf_lock);
- return police->tcf_action;
+ if (police->tcfp_ewma_rate) {
+ struct gnet_stats_rate_est64 sample;
+
+ if (!gen_estimator_read(&police->tcf_rate_est, &sample) ||
+ sample.bps >= police->tcfp_ewma_rate) {
+ police->tcf_qstats.overlimits++;
+ if (police->tcf_action == TC_ACT_SHOT)
+ police->tcf_qstats.drops++;
+ spin_unlock(&police->tcf_lock);
+ return police->tcf_action;
+ }
}
if (qdisc_pkt_len(skb) <= police->tcfp_mtu) {
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index 289af6f9bb3b..823a73ad0c60 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -26,7 +26,7 @@
#define SIMP_TAB_MASK 7
-static int simp_net_id;
+static unsigned int simp_net_id;
static struct tc_action_ops act_simp_ops;
#define SIMP_MAX_DATA 32
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index a133dcb82132..06ccae3c12ee 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -29,7 +29,7 @@
#define SKBEDIT_TAB_MASK 15
-static int skbedit_net_id;
+static unsigned int skbedit_net_id;
static struct tc_action_ops act_skbedit_ops;
static int tcf_skbedit(struct sk_buff *skb, const struct tc_action *a,
@@ -46,8 +46,10 @@ static int tcf_skbedit(struct sk_buff *skb, const struct tc_action *a,
if (d->flags & SKBEDIT_F_QUEUE_MAPPING &&
skb->dev->real_num_tx_queues > d->queue_mapping)
skb_set_queue_mapping(skb, d->queue_mapping);
- if (d->flags & SKBEDIT_F_MARK)
- skb->mark = d->mark;
+ if (d->flags & SKBEDIT_F_MARK) {
+ skb->mark &= ~d->mask;
+ skb->mark |= d->mark & d->mask;
+ }
if (d->flags & SKBEDIT_F_PTYPE)
skb->pkt_type = d->ptype;
@@ -61,6 +63,7 @@ static const struct nla_policy skbedit_policy[TCA_SKBEDIT_MAX + 1] = {
[TCA_SKBEDIT_QUEUE_MAPPING] = { .len = sizeof(u16) },
[TCA_SKBEDIT_MARK] = { .len = sizeof(u32) },
[TCA_SKBEDIT_PTYPE] = { .len = sizeof(u16) },
+ [TCA_SKBEDIT_MASK] = { .len = sizeof(u32) },
};
static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
@@ -71,7 +74,7 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
struct nlattr *tb[TCA_SKBEDIT_MAX + 1];
struct tc_skbedit *parm;
struct tcf_skbedit *d;
- u32 flags = 0, *priority = NULL, *mark = NULL;
+ u32 flags = 0, *priority = NULL, *mark = NULL, *mask = NULL;
u16 *queue_mapping = NULL, *ptype = NULL;
bool exists = false;
int ret = 0, err;
@@ -108,6 +111,11 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
mark = nla_data(tb[TCA_SKBEDIT_MARK]);
}
+ if (tb[TCA_SKBEDIT_MASK] != NULL) {
+ flags |= SKBEDIT_F_MASK;
+ mask = nla_data(tb[TCA_SKBEDIT_MASK]);
+ }
+
parm = nla_data(tb[TCA_SKBEDIT_PARMS]);
exists = tcf_hash_check(tn, parm->index, a, bind);
@@ -145,6 +153,10 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
d->mark = *mark;
if (flags & SKBEDIT_F_PTYPE)
d->ptype = *ptype;
+ /* default behaviour is to use all the bits */
+ d->mask = 0xffffffff;
+ if (flags & SKBEDIT_F_MASK)
+ d->mask = *mask;
d->tcf_action = parm->action;
@@ -182,6 +194,9 @@ static int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a,
if ((d->flags & SKBEDIT_F_PTYPE) &&
nla_put_u16(skb, TCA_SKBEDIT_PTYPE, d->ptype))
goto nla_put_failure;
+ if ((d->flags & SKBEDIT_F_MASK) &&
+ nla_put_u32(skb, TCA_SKBEDIT_MASK, d->mask))
+ goto nla_put_failure;
tcf_tm_dump(&t, &d->tcf_tm);
if (nla_put_64bit(skb, TCA_SKBEDIT_TM, sizeof(t), &t, TCA_SKBEDIT_PAD))
diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index e7d96381c908..3b7074e23024 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -22,7 +22,7 @@
#define SKBMOD_TAB_MASK 15
-static int skbmod_net_id;
+static unsigned int skbmod_net_id;
static struct tc_action_ops act_skbmod_ops;
#define MAX_EDIT_LEN ETH_HLEN
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index af47bdf2f483..7af712526f01 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -16,14 +16,13 @@
#include <net/netlink.h>
#include <net/pkt_sched.h>
#include <net/dst.h>
-#include <net/dst_metadata.h>
#include <linux/tc_act/tc_tunnel_key.h>
#include <net/tc_act/tc_tunnel_key.h>
#define TUNNEL_KEY_TAB_MASK 15
-static int tunnel_key_net_id;
+static unsigned int tunnel_key_net_id;
static struct tc_action_ops act_tunnel_key_ops;
static int tunnel_key_act(struct sk_buff *skb, const struct tc_action *a,
@@ -67,6 +66,7 @@ static const struct nla_policy tunnel_key_policy[TCA_TUNNEL_KEY_MAX + 1] = {
[TCA_TUNNEL_KEY_ENC_IPV6_SRC] = { .len = sizeof(struct in6_addr) },
[TCA_TUNNEL_KEY_ENC_IPV6_DST] = { .len = sizeof(struct in6_addr) },
[TCA_TUNNEL_KEY_ENC_KEY_ID] = { .type = NLA_U32 },
+ [TCA_TUNNEL_KEY_ENC_DST_PORT] = {.type = NLA_U16},
};
static int tunnel_key_init(struct net *net, struct nlattr *nla,
@@ -81,6 +81,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
struct tc_tunnel_key *parm;
struct tcf_tunnel_key *t;
bool exists = false;
+ __be16 dst_port = 0;
__be64 key_id;
int ret = 0;
int err;
@@ -111,6 +112,9 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
key_id = key32_to_tunnel_id(nla_get_be32(tb[TCA_TUNNEL_KEY_ENC_KEY_ID]));
+ if (tb[TCA_TUNNEL_KEY_ENC_DST_PORT])
+ dst_port = nla_get_be16(tb[TCA_TUNNEL_KEY_ENC_DST_PORT]);
+
if (tb[TCA_TUNNEL_KEY_ENC_IPV4_SRC] &&
tb[TCA_TUNNEL_KEY_ENC_IPV4_DST]) {
__be32 saddr;
@@ -120,7 +124,8 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
daddr = nla_get_in_addr(tb[TCA_TUNNEL_KEY_ENC_IPV4_DST]);
metadata = __ip_tun_set_dst(saddr, daddr, 0, 0,
- TUNNEL_KEY, key_id, 0);
+ dst_port, TUNNEL_KEY,
+ key_id, 0);
} else if (tb[TCA_TUNNEL_KEY_ENC_IPV6_SRC] &&
tb[TCA_TUNNEL_KEY_ENC_IPV6_DST]) {
struct in6_addr saddr;
@@ -130,7 +135,8 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
daddr = nla_get_in6_addr(tb[TCA_TUNNEL_KEY_ENC_IPV6_DST]);
metadata = __ipv6_tun_set_dst(&saddr, &daddr, 0, 0, 0,
- TUNNEL_KEY, key_id, 0);
+ dst_port, TUNNEL_KEY,
+ key_id, 0);
}
if (!metadata) {
@@ -258,7 +264,8 @@ static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a,
if (nla_put_be32(skb, TCA_TUNNEL_KEY_ENC_KEY_ID, key_id) ||
tunnel_key_dump_addresses(skb,
- &params->tcft_enc_metadata->u.tun_info))
+ &params->tcft_enc_metadata->u.tun_info) ||
+ nla_put_be16(skb, TCA_TUNNEL_KEY_ENC_DST_PORT, key->tp_dst))
goto nla_put_failure;
}
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index b57fcbcefea1..19e0dba305ce 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -21,7 +21,7 @@
#define VLAN_TAB_MASK 15
-static int vlan_net_id;
+static unsigned int vlan_net_id;
static struct tc_action_ops act_vlan_ops;
static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a,
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index b05d4a2155b0..3fbba79a4ef0 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -682,6 +682,30 @@ int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts)
}
EXPORT_SYMBOL(tcf_exts_dump_stats);
+int tcf_exts_get_dev(struct net_device *dev, struct tcf_exts *exts,
+ struct net_device **hw_dev)
+{
+#ifdef CONFIG_NET_CLS_ACT
+ const struct tc_action *a;
+ LIST_HEAD(actions);
+
+ if (tc_no_actions(exts))
+ return -EINVAL;
+
+ tcf_exts_to_list(exts, &actions);
+ list_for_each_entry(a, &actions, list) {
+ if (a->ops->get_dev) {
+ a->ops->get_dev(a, dev_net(dev), hw_dev);
+ break;
+ }
+ }
+ if (*hw_dev)
+ return 0;
+#endif
+ return -EOPNOTSUPP;
+}
+EXPORT_SYMBOL(tcf_exts_get_dev);
+
static int __init tc_filter_init(void)
{
rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_ctl_tfilter, NULL, NULL);
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index 0a47ba5e6109..adc776048d1a 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -45,10 +45,7 @@ struct cls_bpf_prog {
u32 gen_flags;
struct tcf_exts exts;
u32 handle;
- union {
- u32 bpf_fd;
- u16 bpf_num_ops;
- };
+ u16 bpf_num_ops;
struct sock_filter *bpf_ops;
const char *bpf_name;
struct tcf_proto *tp;
@@ -244,7 +241,7 @@ static int cls_bpf_init(struct tcf_proto *tp)
return 0;
}
-static void cls_bpf_delete_prog(struct tcf_proto *tp, struct cls_bpf_prog *prog)
+static void __cls_bpf_delete_prog(struct cls_bpf_prog *prog)
{
tcf_exts_destroy(&prog->exts);
@@ -258,22 +255,22 @@ static void cls_bpf_delete_prog(struct tcf_proto *tp, struct cls_bpf_prog *prog)
kfree(prog);
}
-static void __cls_bpf_delete_prog(struct rcu_head *rcu)
+static void cls_bpf_delete_prog_rcu(struct rcu_head *rcu)
{
- struct cls_bpf_prog *prog = container_of(rcu, struct cls_bpf_prog, rcu);
-
- cls_bpf_delete_prog(prog->tp, prog);
+ __cls_bpf_delete_prog(container_of(rcu, struct cls_bpf_prog, rcu));
}
-static int cls_bpf_delete(struct tcf_proto *tp, unsigned long arg)
+static void __cls_bpf_delete(struct tcf_proto *tp, struct cls_bpf_prog *prog)
{
- struct cls_bpf_prog *prog = (struct cls_bpf_prog *) arg;
-
cls_bpf_stop_offload(tp, prog);
list_del_rcu(&prog->link);
tcf_unbind_filter(tp, &prog->res);
- call_rcu(&prog->rcu, __cls_bpf_delete_prog);
+ call_rcu(&prog->rcu, cls_bpf_delete_prog_rcu);
+}
+static int cls_bpf_delete(struct tcf_proto *tp, unsigned long arg)
+{
+ __cls_bpf_delete(tp, (struct cls_bpf_prog *) arg);
return 0;
}
@@ -285,12 +282,8 @@ static bool cls_bpf_destroy(struct tcf_proto *tp, bool force)
if (!force && !list_empty(&head->plist))
return false;
- list_for_each_entry_safe(prog, tmp, &head->plist, link) {
- cls_bpf_stop_offload(tp, prog);
- list_del_rcu(&prog->link);
- tcf_unbind_filter(tp, &prog->res);
- call_rcu(&prog->rcu, __cls_bpf_delete_prog);
- }
+ list_for_each_entry_safe(prog, tmp, &head->plist, link)
+ __cls_bpf_delete(tp, prog);
kfree_rcu(head, rcu);
return true;
@@ -365,9 +358,7 @@ static int cls_bpf_prog_from_efd(struct nlattr **tb, struct cls_bpf_prog *prog,
return PTR_ERR(fp);
if (tb[TCA_BPF_NAME]) {
- name = kmemdup(nla_data(tb[TCA_BPF_NAME]),
- nla_len(tb[TCA_BPF_NAME]),
- GFP_KERNEL);
+ name = nla_memdup(tb[TCA_BPF_NAME], GFP_KERNEL);
if (!name) {
bpf_prog_put(fp);
return -ENOMEM;
@@ -375,7 +366,6 @@ static int cls_bpf_prog_from_efd(struct nlattr **tb, struct cls_bpf_prog *prog,
}
prog->bpf_ops = NULL;
- prog->bpf_fd = bpf_fd;
prog->bpf_name = name;
prog->filter = fp;
@@ -517,14 +507,14 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb,
ret = cls_bpf_offload(tp, prog, oldprog);
if (ret) {
- cls_bpf_delete_prog(tp, prog);
+ __cls_bpf_delete_prog(prog);
return ret;
}
if (oldprog) {
list_replace_rcu(&oldprog->link, &prog->link);
tcf_unbind_filter(tp, &oldprog->res);
- call_rcu(&oldprog->rcu, __cls_bpf_delete_prog);
+ call_rcu(&oldprog->rcu, cls_bpf_delete_prog_rcu);
} else {
list_add_rcu(&prog->link, &head->plist);
}
@@ -559,13 +549,18 @@ static int cls_bpf_dump_bpf_info(const struct cls_bpf_prog *prog,
static int cls_bpf_dump_ebpf_info(const struct cls_bpf_prog *prog,
struct sk_buff *skb)
{
- if (nla_put_u32(skb, TCA_BPF_FD, prog->bpf_fd))
- return -EMSGSIZE;
+ struct nlattr *nla;
if (prog->bpf_name &&
nla_put_string(skb, TCA_BPF_NAME, prog->bpf_name))
return -EMSGSIZE;
+ nla = nla_reserve(skb, TCA_BPF_DIGEST, sizeof(prog->filter->digest));
+ if (nla == NULL)
+ return -EMSGSIZE;
+
+ memcpy(nla_data(nla), prog->filter->digest, nla_len(nla));
+
return 0;
}
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 904442421db3..e040c5140f61 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -39,11 +39,13 @@ struct fl_flow_key {
struct flow_dissector_key_ipv6_addrs ipv6;
};
struct flow_dissector_key_ports tp;
+ struct flow_dissector_key_icmp icmp;
struct flow_dissector_key_keyid enc_key_id;
union {
struct flow_dissector_key_ipv4_addrs enc_ipv4;
struct flow_dissector_key_ipv6_addrs enc_ipv6;
};
+ struct flow_dissector_key_ports enc_tp;
} __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */
struct fl_flow_mask_range {
@@ -81,6 +83,8 @@ struct cls_fl_filter {
u32 handle;
u32 flags;
struct rcu_head rcu;
+ struct tc_to_netdev tc;
+ struct net_device *hw_dev;
};
static unsigned short int fl_mask_range(const struct fl_flow_mask *mask)
@@ -159,6 +163,8 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp,
}
skb_key.enc_key_id.keyid = tunnel_id_to_key32(key->tun_id);
+ skb_key.enc_tp.src = key->tp_src;
+ skb_key.enc_tp.dst = key->tp_dst;
}
skb_key.indev_ifindex = skb->skb_iif;
@@ -202,75 +208,90 @@ static void fl_destroy_filter(struct rcu_head *head)
kfree(f);
}
-static void fl_hw_destroy_filter(struct tcf_proto *tp, unsigned long cookie)
+static void fl_hw_destroy_filter(struct tcf_proto *tp, struct cls_fl_filter *f)
{
- struct net_device *dev = tp->q->dev_queue->dev;
struct tc_cls_flower_offload offload = {0};
- struct tc_to_netdev tc;
+ struct net_device *dev = f->hw_dev;
+ struct tc_to_netdev *tc = &f->tc;
- if (!tc_should_offload(dev, tp, 0))
+ if (!tc_can_offload(dev, tp))
return;
offload.command = TC_CLSFLOWER_DESTROY;
- offload.cookie = cookie;
+ offload.cookie = (unsigned long)f;
- tc.type = TC_SETUP_CLSFLOWER;
- tc.cls_flower = &offload;
+ tc->type = TC_SETUP_CLSFLOWER;
+ tc->cls_flower = &offload;
- dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol, &tc);
+ dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol, tc);
}
static int fl_hw_replace_filter(struct tcf_proto *tp,
struct flow_dissector *dissector,
struct fl_flow_key *mask,
- struct fl_flow_key *key,
- struct tcf_exts *actions,
- unsigned long cookie, u32 flags)
+ struct cls_fl_filter *f)
{
struct net_device *dev = tp->q->dev_queue->dev;
struct tc_cls_flower_offload offload = {0};
- struct tc_to_netdev tc;
+ struct tc_to_netdev *tc = &f->tc;
int err;
- if (!tc_should_offload(dev, tp, flags))
- return tc_skip_sw(flags) ? -EINVAL : 0;
+ if (!tc_can_offload(dev, tp)) {
+ if (tcf_exts_get_dev(dev, &f->exts, &f->hw_dev) ||
+ (f->hw_dev && !tc_can_offload(f->hw_dev, tp))) {
+ f->hw_dev = dev;
+ return tc_skip_sw(f->flags) ? -EINVAL : 0;
+ }
+ dev = f->hw_dev;
+ tc->egress_dev = true;
+ } else {
+ f->hw_dev = dev;
+ }
offload.command = TC_CLSFLOWER_REPLACE;
- offload.cookie = cookie;
+ offload.cookie = (unsigned long)f;
offload.dissector = dissector;
offload.mask = mask;
- offload.key = key;
- offload.exts = actions;
+ offload.key = &f->key;
+ offload.exts = &f->exts;
- tc.type = TC_SETUP_CLSFLOWER;
- tc.cls_flower = &offload;
+ tc->type = TC_SETUP_CLSFLOWER;
+ tc->cls_flower = &offload;
err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol,
- &tc);
+ tc);
- if (tc_skip_sw(flags))
+ if (tc_skip_sw(f->flags))
return err;
-
return 0;
}
static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f)
{
- struct net_device *dev = tp->q->dev_queue->dev;
struct tc_cls_flower_offload offload = {0};
- struct tc_to_netdev tc;
+ struct net_device *dev = f->hw_dev;
+ struct tc_to_netdev *tc = &f->tc;
- if (!tc_should_offload(dev, tp, 0))
+ if (!tc_can_offload(dev, tp))
return;
offload.command = TC_CLSFLOWER_STATS;
offload.cookie = (unsigned long)f;
offload.exts = &f->exts;
- tc.type = TC_SETUP_CLSFLOWER;
- tc.cls_flower = &offload;
+ tc->type = TC_SETUP_CLSFLOWER;
+ tc->cls_flower = &offload;
+
+ dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol, tc);
+}
- dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol, &tc);
+static void __fl_delete(struct tcf_proto *tp, struct cls_fl_filter *f)
+{
+ list_del_rcu(&f->list);
+ if (!tc_skip_hw(f->flags))
+ fl_hw_destroy_filter(tp, f);
+ tcf_unbind_filter(tp, &f->res);
+ call_rcu(&f->rcu, fl_destroy_filter);
}
static void fl_destroy_sleepable(struct work_struct *work)
@@ -299,14 +320,12 @@ static bool fl_destroy(struct tcf_proto *tp, bool force)
if (!force && !list_empty(&head->filters))
return false;
- list_for_each_entry_safe(f, next, &head->filters, list) {
- fl_hw_destroy_filter(tp, (unsigned long)f);
- list_del_rcu(&f->list);
- call_rcu(&f->rcu, fl_destroy_filter);
- }
+ list_for_each_entry_safe(f, next, &head->filters, list)
+ __fl_delete(tp, f);
__module_get(THIS_MODULE);
call_rcu(&head->rcu, fl_destroy_rcu);
+
return true;
}
@@ -360,6 +379,24 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = {
[TCA_FLOWER_KEY_TCP_DST_MASK] = { .type = NLA_U16 },
[TCA_FLOWER_KEY_UDP_SRC_MASK] = { .type = NLA_U16 },
[TCA_FLOWER_KEY_UDP_DST_MASK] = { .type = NLA_U16 },
+ [TCA_FLOWER_KEY_SCTP_SRC_MASK] = { .type = NLA_U16 },
+ [TCA_FLOWER_KEY_SCTP_DST_MASK] = { .type = NLA_U16 },
+ [TCA_FLOWER_KEY_SCTP_SRC] = { .type = NLA_U16 },
+ [TCA_FLOWER_KEY_SCTP_DST] = { .type = NLA_U16 },
+ [TCA_FLOWER_KEY_ENC_UDP_SRC_PORT] = { .type = NLA_U16 },
+ [TCA_FLOWER_KEY_ENC_UDP_SRC_PORT_MASK] = { .type = NLA_U16 },
+ [TCA_FLOWER_KEY_ENC_UDP_DST_PORT] = { .type = NLA_U16 },
+ [TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK] = { .type = NLA_U16 },
+ [TCA_FLOWER_KEY_FLAGS] = { .type = NLA_U32 },
+ [TCA_FLOWER_KEY_FLAGS_MASK] = { .type = NLA_U32 },
+ [TCA_FLOWER_KEY_ICMPV4_TYPE] = { .type = NLA_U8 },
+ [TCA_FLOWER_KEY_ICMPV4_TYPE_MASK] = { .type = NLA_U8 },
+ [TCA_FLOWER_KEY_ICMPV4_CODE] = { .type = NLA_U8 },
+ [TCA_FLOWER_KEY_ICMPV4_CODE_MASK] = { .type = NLA_U8 },
+ [TCA_FLOWER_KEY_ICMPV6_TYPE] = { .type = NLA_U8 },
+ [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 },
};
static void fl_set_key_val(struct nlattr **tb,
@@ -394,6 +431,39 @@ static void fl_set_key_vlan(struct nlattr **tb,
}
}
+static void fl_set_key_flag(u32 flower_key, u32 flower_mask,
+ u32 *dissector_key, u32 *dissector_mask,
+ u32 flower_flag_bit, u32 dissector_flag_bit)
+{
+ if (flower_mask & flower_flag_bit) {
+ *dissector_mask |= dissector_flag_bit;
+ if (flower_key & flower_flag_bit)
+ *dissector_key |= dissector_flag_bit;
+ }
+}
+
+static void fl_set_key_flags(struct nlattr **tb,
+ u32 *flags_key, u32 *flags_mask)
+{
+ u32 key, mask;
+
+ if (!tb[TCA_FLOWER_KEY_FLAGS])
+ return;
+
+ key = be32_to_cpu(nla_get_u32(tb[TCA_FLOWER_KEY_FLAGS]));
+
+ if (!tb[TCA_FLOWER_KEY_FLAGS_MASK])
+ mask = ~0;
+ else
+ mask = be32_to_cpu(nla_get_u32(tb[TCA_FLOWER_KEY_FLAGS_MASK]));
+
+ *flags_key = 0;
+ *flags_mask = 0;
+
+ fl_set_key_flag(key, mask, flags_key, flags_mask,
+ TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT, FLOW_DIS_IS_FRAGMENT);
+}
+
static int fl_set_key(struct net *net, struct nlattr **tb,
struct fl_flow_key *key, struct fl_flow_key *mask)
{
@@ -469,6 +539,33 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
fl_set_key_val(tb, &key->tp.dst, TCA_FLOWER_KEY_UDP_DST,
&mask->tp.dst, TCA_FLOWER_KEY_UDP_DST_MASK,
sizeof(key->tp.dst));
+ } else if (key->basic.ip_proto == IPPROTO_SCTP) {
+ fl_set_key_val(tb, &key->tp.src, TCA_FLOWER_KEY_SCTP_SRC,
+ &mask->tp.src, TCA_FLOWER_KEY_SCTP_SRC_MASK,
+ sizeof(key->tp.src));
+ fl_set_key_val(tb, &key->tp.dst, TCA_FLOWER_KEY_SCTP_DST,
+ &mask->tp.dst, TCA_FLOWER_KEY_SCTP_DST_MASK,
+ sizeof(key->tp.dst));
+ } else if (key->basic.n_proto == htons(ETH_P_IP) &&
+ key->basic.ip_proto == IPPROTO_ICMP) {
+ fl_set_key_val(tb, &key->icmp.type, TCA_FLOWER_KEY_ICMPV4_TYPE,
+ &mask->icmp.type,
+ TCA_FLOWER_KEY_ICMPV4_TYPE_MASK,
+ sizeof(key->icmp.type));
+ fl_set_key_val(tb, &key->icmp.code, TCA_FLOWER_KEY_ICMPV4_CODE,
+ &mask->icmp.code,
+ TCA_FLOWER_KEY_ICMPV4_CODE_MASK,
+ sizeof(key->icmp.code));
+ } else if (key->basic.n_proto == htons(ETH_P_IPV6) &&
+ key->basic.ip_proto == IPPROTO_ICMPV6) {
+ fl_set_key_val(tb, &key->icmp.type, TCA_FLOWER_KEY_ICMPV6_TYPE,
+ &mask->icmp.type,
+ TCA_FLOWER_KEY_ICMPV6_TYPE_MASK,
+ sizeof(key->icmp.type));
+ fl_set_key_val(tb, &key->icmp.code, TCA_FLOWER_KEY_ICMPV4_CODE,
+ &mask->icmp.code,
+ TCA_FLOWER_KEY_ICMPV4_CODE_MASK,
+ sizeof(key->icmp.code));
}
if (tb[TCA_FLOWER_KEY_ENC_IPV4_SRC] ||
@@ -505,6 +602,16 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
&mask->enc_key_id.keyid, TCA_FLOWER_UNSPEC,
sizeof(key->enc_key_id.keyid));
+ fl_set_key_val(tb, &key->enc_tp.src, TCA_FLOWER_KEY_ENC_UDP_SRC_PORT,
+ &mask->enc_tp.src, TCA_FLOWER_KEY_ENC_UDP_SRC_PORT_MASK,
+ sizeof(key->enc_tp.src));
+
+ fl_set_key_val(tb, &key->enc_tp.dst, TCA_FLOWER_KEY_ENC_UDP_DST_PORT,
+ &mask->enc_tp.dst, TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK,
+ sizeof(key->enc_tp.dst));
+
+ fl_set_key_flags(tb, &key->control.flags, &mask->control.flags);
+
return 0;
}
@@ -571,7 +678,21 @@ static void fl_init_dissector(struct cls_fl_head *head,
FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
FLOW_DISSECTOR_KEY_PORTS, tp);
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_VLAN, vlan);
+ FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+ FLOW_DISSECTOR_KEY_ENC_KEYID, enc_key_id);
+ FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+ FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS, enc_ipv4);
+ FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+ FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS, enc_ipv6);
+ if (FL_KEY_IS_MASKED(&mask->key, enc_ipv4) ||
+ FL_KEY_IS_MASKED(&mask->key, enc_ipv6))
+ FL_KEY_SET(keys, cnt, FLOW_DISSECTOR_KEY_ENC_CONTROL,
+ enc_control);
+ FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+ FLOW_DISSECTOR_KEY_ENC_PORTS, enc_tp);
skb_flow_dissector_init(&head->dissector, keys, cnt);
}
@@ -721,21 +842,21 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
goto errout;
}
- err = fl_hw_replace_filter(tp,
- &head->dissector,
- &mask.key,
- &fnew->key,
- &fnew->exts,
- (unsigned long)fnew,
- fnew->flags);
- if (err)
- goto errout;
+ if (!tc_skip_hw(fnew->flags)) {
+ err = fl_hw_replace_filter(tp,
+ &head->dissector,
+ &mask.key,
+ fnew);
+ if (err)
+ goto errout;
+ }
if (fold) {
if (!tc_skip_sw(fold->flags))
rhashtable_remove_fast(&head->ht, &fold->ht_node,
head->ht_params);
- fl_hw_destroy_filter(tp, (unsigned long)fold);
+ if (!tc_skip_hw(fold->flags))
+ fl_hw_destroy_filter(tp, fold);
}
*arg = (unsigned long) fnew;
@@ -764,10 +885,7 @@ static int fl_delete(struct tcf_proto *tp, unsigned long arg)
if (!tc_skip_sw(f->flags))
rhashtable_remove_fast(&head->ht, &f->ht_node,
head->ht_params);
- list_del_rcu(&f->list);
- fl_hw_destroy_filter(tp, (unsigned long)f);
- tcf_unbind_filter(tp, &f->res);
- call_rcu(&f->rcu, fl_destroy_filter);
+ __fl_delete(tp, f);
return 0;
}
@@ -830,6 +948,42 @@ static int fl_dump_key_vlan(struct sk_buff *skb,
return 0;
}
+static void fl_get_key_flag(u32 dissector_key, u32 dissector_mask,
+ u32 *flower_key, u32 *flower_mask,
+ u32 flower_flag_bit, u32 dissector_flag_bit)
+{
+ if (dissector_mask & dissector_flag_bit) {
+ *flower_mask |= flower_flag_bit;
+ if (dissector_key & dissector_flag_bit)
+ *flower_key |= flower_flag_bit;
+ }
+}
+
+static int fl_dump_key_flags(struct sk_buff *skb, u32 flags_key, u32 flags_mask)
+{
+ u32 key, mask;
+ __be32 _key, _mask;
+ int err;
+
+ if (!memchr_inv(&flags_mask, 0, sizeof(flags_mask)))
+ return 0;
+
+ key = 0;
+ mask = 0;
+
+ fl_get_key_flag(flags_key, flags_mask, &key, &mask,
+ TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT, FLOW_DIS_IS_FRAGMENT);
+
+ _key = cpu_to_be32(key);
+ _mask = cpu_to_be32(mask);
+
+ err = nla_put(skb, TCA_FLOWER_KEY_FLAGS, 4, &_key);
+ if (err)
+ return err;
+
+ return nla_put(skb, TCA_FLOWER_KEY_FLAGS_MASK, 4, &_mask);
+}
+
static int fl_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
struct sk_buff *skb, struct tcmsg *t)
{
@@ -862,7 +1016,8 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
goto nla_put_failure;
}
- fl_hw_update_stats(tp, f);
+ if (!tc_skip_hw(f->flags))
+ fl_hw_update_stats(tp, f);
if (fl_dump_key_val(skb, key->eth.dst, TCA_FLOWER_KEY_ETH_DST,
mask->eth.dst, TCA_FLOWER_KEY_ETH_DST_MASK,
@@ -918,6 +1073,36 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
&mask->tp.dst, TCA_FLOWER_KEY_UDP_DST_MASK,
sizeof(key->tp.dst))))
goto nla_put_failure;
+ else if (key->basic.ip_proto == IPPROTO_SCTP &&
+ (fl_dump_key_val(skb, &key->tp.src, TCA_FLOWER_KEY_SCTP_SRC,
+ &mask->tp.src, TCA_FLOWER_KEY_SCTP_SRC_MASK,
+ sizeof(key->tp.src)) ||
+ fl_dump_key_val(skb, &key->tp.dst, TCA_FLOWER_KEY_SCTP_DST,
+ &mask->tp.dst, TCA_FLOWER_KEY_SCTP_DST_MASK,
+ sizeof(key->tp.dst))))
+ goto nla_put_failure;
+ else if (key->basic.n_proto == htons(ETH_P_IP) &&
+ key->basic.ip_proto == IPPROTO_ICMP &&
+ (fl_dump_key_val(skb, &key->icmp.type,
+ TCA_FLOWER_KEY_ICMPV4_TYPE, &mask->icmp.type,
+ TCA_FLOWER_KEY_ICMPV4_TYPE_MASK,
+ sizeof(key->icmp.type)) ||
+ fl_dump_key_val(skb, &key->icmp.code,
+ TCA_FLOWER_KEY_ICMPV4_CODE, &mask->icmp.code,
+ TCA_FLOWER_KEY_ICMPV4_CODE_MASK,
+ sizeof(key->icmp.code))))
+ goto nla_put_failure;
+ else if (key->basic.n_proto == htons(ETH_P_IPV6) &&
+ key->basic.ip_proto == IPPROTO_ICMPV6 &&
+ (fl_dump_key_val(skb, &key->icmp.type,
+ TCA_FLOWER_KEY_ICMPV6_TYPE, &mask->icmp.type,
+ TCA_FLOWER_KEY_ICMPV6_TYPE_MASK,
+ sizeof(key->icmp.type)) ||
+ fl_dump_key_val(skb, &key->icmp.code,
+ TCA_FLOWER_KEY_ICMPV6_CODE, &mask->icmp.code,
+ TCA_FLOWER_KEY_ICMPV6_CODE_MASK,
+ sizeof(key->icmp.code))))
+ goto nla_put_failure;
if (key->enc_control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS &&
(fl_dump_key_val(skb, &key->enc_ipv4.src,
@@ -943,7 +1128,20 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
if (fl_dump_key_val(skb, &key->enc_key_id, TCA_FLOWER_KEY_ENC_KEY_ID,
&mask->enc_key_id, TCA_FLOWER_UNSPEC,
- sizeof(key->enc_key_id)))
+ sizeof(key->enc_key_id)) ||
+ fl_dump_key_val(skb, &key->enc_tp.src,
+ TCA_FLOWER_KEY_ENC_UDP_SRC_PORT,
+ &mask->enc_tp.src,
+ TCA_FLOWER_KEY_ENC_UDP_SRC_PORT_MASK,
+ sizeof(key->enc_tp.src)) ||
+ fl_dump_key_val(skb, &key->enc_tp.dst,
+ TCA_FLOWER_KEY_ENC_UDP_DST_PORT,
+ &mask->enc_tp.dst,
+ TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK,
+ sizeof(key->enc_tp.dst)))
+ goto nla_put_failure;
+
+ if (fl_dump_key_flags(skb, key->control.flags, mask->control.flags))
goto nla_put_failure;
nla_put_u32(skb, TCA_FLOWER_FLAGS, f->flags);
diff --git a/net/sched/em_ipset.c b/net/sched/em_ipset.c
index c66ca9400ab4..c1b23e3060b8 100644
--- a/net/sched/em_ipset.c
+++ b/net/sched/em_ipset.c
@@ -57,17 +57,20 @@ static int em_ipset_match(struct sk_buff *skb, struct tcf_ematch *em,
struct xt_action_param acpar;
const struct xt_set_info *set = (const void *) em->data;
struct net_device *dev, *indev = NULL;
+ struct nf_hook_state state = {
+ .net = em->net,
+ };
int ret, network_offset;
switch (tc_skb_protocol(skb)) {
case htons(ETH_P_IP):
- acpar.family = NFPROTO_IPV4;
+ state.pf = NFPROTO_IPV4;
if (!pskb_network_may_pull(skb, sizeof(struct iphdr)))
return 0;
acpar.thoff = ip_hdrlen(skb);
break;
case htons(ETH_P_IPV6):
- acpar.family = NFPROTO_IPV6;
+ state.pf = NFPROTO_IPV6;
if (!pskb_network_may_pull(skb, sizeof(struct ipv6hdr)))
return 0;
/* doesn't call ipv6_find_hdr() because ipset doesn't use thoff, yet */
@@ -77,9 +80,7 @@ static int em_ipset_match(struct sk_buff *skb, struct tcf_ematch *em,
return 0;
}
- acpar.hooknum = 0;
-
- opt.family = acpar.family;
+ opt.family = state.pf;
opt.dim = set->dim;
opt.flags = set->flags;
opt.cmdflags = 0;
@@ -95,9 +96,9 @@ static int em_ipset_match(struct sk_buff *skb, struct tcf_ematch *em,
if (skb->skb_iif)
indev = dev_get_by_index_rcu(em->net, skb->skb_iif);
- acpar.net = em->net;
- acpar.in = indev ? indev : dev;
- acpar.out = dev;
+ state.in = indev ? indev : dev;
+ state.out = dev;
+ acpar.state = &state;
ret = ip_set_test(set->index, skb, &acpar, &opt);
diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c
index a309a07ccb35..41c80b6c3906 100644
--- a/net/sched/em_meta.c
+++ b/net/sched/em_meta.c
@@ -176,11 +176,12 @@ META_COLLECTOR(int_vlan_tag)
{
unsigned short tag;
- tag = skb_vlan_tag_get(skb);
- if (!tag && __vlan_get_tag(skb, &tag))
- *err = -1;
- else
+ if (skb_vlan_tag_present(skb))
+ dst->value = skb_vlan_tag_get(skb);
+ else if (!__vlan_get_tag(skb, &tag))
dst->value = tag;
+ else
+ *err = -1;
}
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 206dc24add3a..d7b93429f0cc 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -960,6 +960,17 @@ static struct Qdisc *qdisc_create(struct net_device *dev,
sch->handle = handle;
+ /* This exist to keep backward compatible with a userspace
+ * loophole, what allowed userspace to get IFF_NO_QUEUE
+ * facility on older kernels by setting tx_queue_len=0 (prior
+ * to qdisc init), and then forgot to reinit tx_queue_len
+ * before again attaching a qdisc.
+ */
+ if ((dev->priv_flags & IFF_NO_QUEUE) && (dev->tx_queue_len == 0)) {
+ dev->tx_queue_len = DEFAULT_TX_QUEUE_LEN;
+ netdev_info(dev, "Caught tx_queue_len zero misconfig\n");
+ }
+
if (!ops->init || (err = ops->init(sch, tca[TCA_OPTIONS])) == 0) {
if (qdisc_is_percpu_stats(sch)) {
sch->cpu_bstats =
@@ -1384,7 +1395,7 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid,
if (gnet_stats_copy_basic(qdisc_root_sleeping_running(q),
&d, cpu_bstats, &q->bstats) < 0 ||
- gnet_stats_copy_rate_est(&d, &q->bstats, &q->rate_est) < 0 ||
+ gnet_stats_copy_rate_est(&d, &q->rate_est) < 0 ||
gnet_stats_copy_queue(&d, cpu_qstats, &q->qstats, qlen) < 0)
goto nla_put_failure;
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index beb554aa8cfb..9ffe1c220b02 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -122,7 +122,7 @@ struct cbq_class {
psched_time_t penalized;
struct gnet_stats_basic_packed bstats;
struct gnet_stats_queue qstats;
- struct gnet_stats_rate_est64 rate_est;
+ struct net_rate_estimator __rcu *rate_est;
struct tc_cbq_xstats xstats;
struct tcf_proto __rcu *filter_list;
@@ -1346,7 +1346,7 @@ cbq_dump_class_stats(struct Qdisc *sch, unsigned long arg,
if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch),
d, NULL, &cl->bstats) < 0 ||
- gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 ||
+ gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 ||
gnet_stats_copy_queue(d, NULL, &cl->qstats, cl->q->q.qlen) < 0)
return -1;
@@ -1405,7 +1405,7 @@ static void cbq_destroy_class(struct Qdisc *sch, struct cbq_class *cl)
tcf_destroy_chain(&cl->filter_list);
qdisc_destroy(cl->q);
qdisc_put_rtab(cl->R_tab);
- gen_kill_estimator(&cl->bstats, &cl->rate_est);
+ gen_kill_estimator(&cl->rate_est);
if (cl != &q->link)
kfree(cl);
}
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index 8af5c59eef84..bb4cbdf75004 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -25,7 +25,7 @@ struct drr_class {
struct gnet_stats_basic_packed bstats;
struct gnet_stats_queue qstats;
- struct gnet_stats_rate_est64 rate_est;
+ struct net_rate_estimator __rcu *rate_est;
struct list_head alist;
struct Qdisc *qdisc;
@@ -142,7 +142,7 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
static void drr_destroy_class(struct Qdisc *sch, struct drr_class *cl)
{
- gen_kill_estimator(&cl->bstats, &cl->rate_est);
+ gen_kill_estimator(&cl->rate_est);
qdisc_destroy(cl->qdisc);
kfree(cl);
}
@@ -283,7 +283,7 @@ static int drr_dump_class_stats(struct Qdisc *sch, unsigned long arg,
if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch),
d, NULL, &cl->bstats) < 0 ||
- gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 ||
+ gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 ||
gnet_stats_copy_queue(d, NULL, &cl->qdisc->qstats, qlen) < 0)
return -1;
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 18e752439f6f..86309a3156a5 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -245,7 +245,7 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q)
skb_orphan(skb);
}
- root = &q->fq_root[hash_32((u32)(long)sk, q->fq_trees_log)];
+ root = &q->fq_root[hash_ptr(sk, q->fq_trees_log)];
if (q->flows >= (2U << q->fq_trees_log) &&
q->inactive_flows > q->flows/2)
@@ -599,7 +599,7 @@ static void fq_rehash(struct fq_sched_data *q,
kmem_cache_free(fq_flow_cachep, of);
continue;
}
- nroot = &new_array[hash_32((u32)(long)of->sk, new_log)];
+ nroot = &new_array[hash_ptr(of->sk, new_log)];
np = &nroot->rb_node;
parent = NULL;
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 6cfb6e9038c2..6eb9c8e88519 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -709,7 +709,7 @@ void qdisc_destroy(struct Qdisc *qdisc)
qdisc_put_stab(rtnl_dereference(qdisc->stab));
#endif
- gen_kill_estimator(&qdisc->bstats, &qdisc->rate_est);
+ gen_kill_estimator(&qdisc->rate_est);
if (ops->reset)
ops->reset(qdisc);
if (ops->destroy)
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index 000f1d36128e..3ffaa6fb0990 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -114,7 +114,7 @@ struct hfsc_class {
struct gnet_stats_basic_packed bstats;
struct gnet_stats_queue qstats;
- struct gnet_stats_rate_est64 rate_est;
+ struct net_rate_estimator __rcu *rate_est;
struct tcf_proto __rcu *filter_list; /* filter list */
unsigned int filter_cnt; /* filter count */
unsigned int level; /* class level in hierarchy */
@@ -1091,7 +1091,7 @@ hfsc_destroy_class(struct Qdisc *sch, struct hfsc_class *cl)
tcf_destroy_chain(&cl->filter_list);
qdisc_destroy(cl->qdisc);
- gen_kill_estimator(&cl->bstats, &cl->rate_est);
+ gen_kill_estimator(&cl->rate_est);
if (cl != &q->root)
kfree(cl);
}
@@ -1348,7 +1348,7 @@ hfsc_dump_class_stats(struct Qdisc *sch, unsigned long arg,
xstats.rtwork = cl->cl_cumul;
if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), d, NULL, &cl->bstats) < 0 ||
- gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 ||
+ gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 ||
gnet_stats_copy_queue(d, NULL, &cl->qstats, cl->qdisc->q.qlen) < 0)
return -1;
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index c798d0de8a9d..760f39e7caee 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -111,7 +111,7 @@ struct htb_class {
unsigned int children;
struct htb_class *parent; /* parent class */
- struct gnet_stats_rate_est64 rate_est;
+ struct net_rate_estimator __rcu *rate_est;
/*
* Written often fields
@@ -1145,7 +1145,7 @@ htb_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d)
if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch),
d, NULL, &cl->bstats) < 0 ||
- gnet_stats_copy_rate_est(d, NULL, &cl->rate_est) < 0 ||
+ gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 ||
gnet_stats_copy_queue(d, NULL, &qs, qlen) < 0)
return -1;
@@ -1228,7 +1228,7 @@ static void htb_destroy_class(struct Qdisc *sch, struct htb_class *cl)
WARN_ON(!cl->un.leaf.q);
qdisc_destroy(cl->un.leaf.q);
}
- gen_kill_estimator(&cl->bstats, &cl->rate_est);
+ gen_kill_estimator(&cl->rate_est);
tcf_destroy_chain(&cl->filter_list);
kfree(cl);
}
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index ca0516e6f743..f9e712ce2d15 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -137,7 +137,7 @@ struct qfq_class {
struct gnet_stats_basic_packed bstats;
struct gnet_stats_queue qstats;
- struct gnet_stats_rate_est64 rate_est;
+ struct net_rate_estimator __rcu *rate_est;
struct Qdisc *qdisc;
struct list_head alist; /* Link for active-classes list. */
struct qfq_aggregate *agg; /* Parent aggregate. */
@@ -508,7 +508,7 @@ set_change_agg:
new_agg = kzalloc(sizeof(*new_agg), GFP_KERNEL);
if (new_agg == NULL) {
err = -ENOBUFS;
- gen_kill_estimator(&cl->bstats, &cl->rate_est);
+ gen_kill_estimator(&cl->rate_est);
goto destroy_class;
}
sch_tree_lock(sch);
@@ -533,7 +533,7 @@ static void qfq_destroy_class(struct Qdisc *sch, struct qfq_class *cl)
struct qfq_sched *q = qdisc_priv(sch);
qfq_rm_from_agg(q, cl);
- gen_kill_estimator(&cl->bstats, &cl->rate_est);
+ gen_kill_estimator(&cl->rate_est);
qdisc_destroy(cl->qdisc);
kfree(cl);
}
@@ -667,7 +667,7 @@ static int qfq_dump_class_stats(struct Qdisc *sch, unsigned long arg,
if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch),
d, NULL, &cl->bstats) < 0 ||
- gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 ||
+ gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 ||
gnet_stats_copy_queue(d, NULL,
&cl->qdisc->qstats, cl->qdisc->q.qlen) < 0)
return -1;
diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c
index 2cd9b4478b92..b0196366d58d 100644
--- a/net/sched/sch_teql.c
+++ b/net/sched/sch_teql.c
@@ -418,9 +418,6 @@ static int teql_master_mtu(struct net_device *dev, int new_mtu)
struct teql_master *m = netdev_priv(dev);
struct Qdisc *q;
- if (new_mtu < 68)
- return -EINVAL;
-
q = m->slaves;
if (q) {
do {
@@ -460,6 +457,8 @@ static __init void teql_master_setup(struct net_device *dev)
dev->netdev_ops = &teql_netdev_ops;
dev->type = ARPHRD_VOID;
dev->mtu = 1500;
+ dev->min_mtu = 68;
+ dev->max_mtu = 65535;
dev->tx_queue_len = 100;
dev->flags = IFF_NOARP;
dev->hard_header_len = LL_MAX_HEADER;
generated by cgit v1.2.3 (git 2.39.0) at 2025-02-09 22:39:42 +0300