summaryrefslogtreecommitdiffstats
path: root/net/sched
diff options
context:
space:
mode:
Diffstat (limited to 'net/sched')
-rw-r--r--net/sched/Kconfig2
-rw-r--r--net/sched/act_api.c43
-rw-r--r--net/sched/act_bpf.c3
-rw-r--r--net/sched/act_ct.c569
-rw-r--r--net/sched/act_pedit.c11
-rw-r--r--net/sched/act_sample.c2
-rw-r--r--net/sched/act_skbedit.c11
-rw-r--r--net/sched/cls_api.c168
-rw-r--r--net/sched/cls_flower.c70
-rw-r--r--net/sched/cls_matchall.c8
-rw-r--r--net/sched/em_ipt.c2
-rw-r--r--net/sched/em_nbyte.c2
-rw-r--r--net/sched/sch_api.c21
-rw-r--r--net/sched/sch_atm.c2
-rw-r--r--net/sched/sch_fifo.c97
-rw-r--r--net/sched/sch_fq.c21
-rw-r--r--net/sched/sch_fq_pie.c1
-rw-r--r--net/sched/sch_generic.c8
-rw-r--r--net/sched/sch_ingress.c11
-rw-r--r--net/sched/sch_netem.c2
-rw-r--r--net/sched/sch_pie.c49
-rw-r--r--net/sched/sch_red.c69
22 files changed, 1045 insertions, 127 deletions
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index edde0e519438..bfbefb7bff9d 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -972,7 +972,7 @@ config NET_ACT_TUNNEL_KEY
config NET_ACT_CT
tristate "connection tracking tc action"
- depends on NET_CLS_ACT && NF_CONNTRACK && NF_NAT
+ depends on NET_CLS_ACT && NF_CONNTRACK && NF_NAT && NF_FLOW_TABLE
help
Say Y here to allow sending the packets to conntrack module.
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 8c466a712cda..df4560909157 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -185,6 +185,7 @@ static size_t tcf_action_shared_attrs_size(const struct tc_action *act)
return nla_total_size(0) /* action number nested */
+ nla_total_size(IFNAMSIZ) /* TCA_ACT_KIND */
+ cookie_len /* TCA_ACT_COOKIE */
+ + nla_total_size(sizeof(struct nla_bitfield32)) /* TCA_ACT_HW_STATS */
+ nla_total_size(0) /* TCA_ACT_STATS nested */
+ nla_total_size(sizeof(struct nla_bitfield32)) /* TCA_ACT_FLAGS */
/* TCA_STATS_BASIC */
@@ -788,13 +789,20 @@ tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
}
rcu_read_unlock();
- if (a->tcfa_flags) {
- struct nla_bitfield32 flags = { a->tcfa_flags,
- a->tcfa_flags, };
+ if (a->hw_stats != TCA_ACT_HW_STATS_ANY &&
+ nla_put_bitfield32(skb, TCA_ACT_HW_STATS,
+ a->hw_stats, TCA_ACT_HW_STATS_ANY))
+ goto nla_put_failure;
- if (nla_put(skb, TCA_ACT_FLAGS, sizeof(flags), &flags))
- goto nla_put_failure;
- }
+ if (a->used_hw_stats_valid &&
+ nla_put_bitfield32(skb, TCA_ACT_USED_HW_STATS,
+ a->used_hw_stats, TCA_ACT_HW_STATS_ANY))
+ goto nla_put_failure;
+
+ if (a->tcfa_flags &&
+ nla_put_bitfield32(skb, TCA_ACT_FLAGS,
+ a->tcfa_flags, a->tcfa_flags))
+ goto nla_put_failure;
nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
if (nest == NULL)
@@ -854,7 +862,23 @@ static struct tc_cookie *nla_memdup_cookie(struct nlattr **tb)
return c;
}
+static u8 tcf_action_hw_stats_get(struct nlattr *hw_stats_attr)
+{
+ struct nla_bitfield32 hw_stats_bf;
+
+ /* If the user did not pass the attr, that means he does
+ * not care about the type. Return "any" in that case
+ * which is setting on all supported types.
+ */
+ if (!hw_stats_attr)
+ return TCA_ACT_HW_STATS_ANY;
+ hw_stats_bf = nla_get_bitfield32(hw_stats_attr);
+ return hw_stats_bf.value;
+}
+
static const u32 tca_act_flags_allowed = TCA_ACT_FLAGS_NO_PERCPU_STATS;
+static const u32 tca_act_hw_stats_allowed = TCA_ACT_HW_STATS_ANY;
+
static const struct nla_policy tcf_action_policy[TCA_ACT_MAX + 1] = {
[TCA_ACT_KIND] = { .type = NLA_STRING },
[TCA_ACT_INDEX] = { .type = NLA_U32 },
@@ -863,6 +887,8 @@ static const struct nla_policy tcf_action_policy[TCA_ACT_MAX + 1] = {
[TCA_ACT_OPTIONS] = { .type = NLA_NESTED },
[TCA_ACT_FLAGS] = { .type = NLA_BITFIELD32,
.validation_data = &tca_act_flags_allowed },
+ [TCA_ACT_HW_STATS] = { .type = NLA_BITFIELD32,
+ .validation_data = &tca_act_hw_stats_allowed },
};
struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
@@ -872,6 +898,7 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
struct netlink_ext_ack *extack)
{
struct nla_bitfield32 flags = { 0, 0 };
+ u8 hw_stats = TCA_ACT_HW_STATS_ANY;
struct tc_action *a;
struct tc_action_ops *a_o;
struct tc_cookie *cookie = NULL;
@@ -903,6 +930,7 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
goto err_out;
}
}
+ hw_stats = tcf_action_hw_stats_get(tb[TCA_ACT_HW_STATS]);
if (tb[TCA_ACT_FLAGS])
flags = nla_get_bitfield32(tb[TCA_ACT_FLAGS]);
} else {
@@ -953,6 +981,9 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
if (!name && tb[TCA_ACT_COOKIE])
tcf_set_action_cookie(&a->act_cookie, cookie);
+ if (!name)
+ a->hw_stats = hw_stats;
+
/* 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).
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index 46f47e58b3be..54d5652cfe6c 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -12,6 +12,7 @@
#include <linux/bpf.h>
#include <net/netlink.h>
+#include <net/sock.h>
#include <net/pkt_sched.h>
#include <net/pkt_cls.h>
@@ -53,6 +54,8 @@ static int tcf_bpf_act(struct sk_buff *skb, const struct tc_action *act,
bpf_compute_data_pointers(skb);
filter_res = BPF_PROG_RUN(filter, skb);
}
+ if (skb_sk_is_prefetched(skb) && filter_res != TC_ACT_OK)
+ skb_orphan(skb);
rcu_read_unlock();
/* A BPF program may overwrite the default action opcode.
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index 41114b463161..1a766393be62 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -15,6 +15,7 @@
#include <linux/pkt_cls.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
+#include <linux/rhashtable.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
#include <net/pkt_cls.h>
@@ -24,6 +25,7 @@
#include <uapi/linux/tc_act/tc_ct.h>
#include <net/tc_act/tc_ct.h>
+#include <net/netfilter/nf_flow_table.h>
#include <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_conntrack_core.h>
#include <net/netfilter/nf_conntrack_zones.h>
@@ -31,6 +33,523 @@
#include <net/netfilter/ipv6/nf_defrag_ipv6.h>
#include <uapi/linux/netfilter/nf_nat.h>
+static struct workqueue_struct *act_ct_wq;
+static struct rhashtable zones_ht;
+static DEFINE_MUTEX(zones_mutex);
+
+struct tcf_ct_flow_table {
+ struct rhash_head node; /* In zones tables */
+
+ struct rcu_work rwork;
+ struct nf_flowtable nf_ft;
+ refcount_t ref;
+ u16 zone;
+
+ bool dying;
+};
+
+static const struct rhashtable_params zones_params = {
+ .head_offset = offsetof(struct tcf_ct_flow_table, node),
+ .key_offset = offsetof(struct tcf_ct_flow_table, zone),
+ .key_len = sizeof_field(struct tcf_ct_flow_table, zone),
+ .automatic_shrinking = true,
+};
+
+static struct flow_action_entry *
+tcf_ct_flow_table_flow_action_get_next(struct flow_action *flow_action)
+{
+ int i = flow_action->num_entries++;
+
+ return &flow_action->entries[i];
+}
+
+static void tcf_ct_add_mangle_action(struct flow_action *action,
+ enum flow_action_mangle_base htype,
+ u32 offset,
+ u32 mask,
+ u32 val)
+{
+ struct flow_action_entry *entry;
+
+ entry = tcf_ct_flow_table_flow_action_get_next(action);
+ entry->id = FLOW_ACTION_MANGLE;
+ entry->mangle.htype = htype;
+ entry->mangle.mask = ~mask;
+ entry->mangle.offset = offset;
+ entry->mangle.val = val;
+}
+
+/* The following nat helper functions check if the inverted reverse tuple
+ * (target) is different then the current dir tuple - meaning nat for ports
+ * and/or ip is needed, and add the relevant mangle actions.
+ */
+static void
+tcf_ct_flow_table_add_action_nat_ipv4(const struct nf_conntrack_tuple *tuple,
+ struct nf_conntrack_tuple target,
+ struct flow_action *action)
+{
+ if (memcmp(&target.src.u3, &tuple->src.u3, sizeof(target.src.u3)))
+ tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_IP4,
+ offsetof(struct iphdr, saddr),
+ 0xFFFFFFFF,
+ be32_to_cpu(target.src.u3.ip));
+ if (memcmp(&target.dst.u3, &tuple->dst.u3, sizeof(target.dst.u3)))
+ tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_IP4,
+ offsetof(struct iphdr, daddr),
+ 0xFFFFFFFF,
+ be32_to_cpu(target.dst.u3.ip));
+}
+
+static void
+tcf_ct_add_ipv6_addr_mangle_action(struct flow_action *action,
+ union nf_inet_addr *addr,
+ u32 offset)
+{
+ int i;
+
+ for (i = 0; i < sizeof(struct in6_addr) / sizeof(u32); i++)
+ tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_IP6,
+ i * sizeof(u32) + offset,
+ 0xFFFFFFFF, be32_to_cpu(addr->ip6[i]));
+}
+
+static void
+tcf_ct_flow_table_add_action_nat_ipv6(const struct nf_conntrack_tuple *tuple,
+ struct nf_conntrack_tuple target,
+ struct flow_action *action)
+{
+ if (memcmp(&target.src.u3, &tuple->src.u3, sizeof(target.src.u3)))
+ tcf_ct_add_ipv6_addr_mangle_action(action, &target.src.u3,
+ offsetof(struct ipv6hdr,
+ saddr));
+ if (memcmp(&target.dst.u3, &tuple->dst.u3, sizeof(target.dst.u3)))
+ tcf_ct_add_ipv6_addr_mangle_action(action, &target.dst.u3,
+ offsetof(struct ipv6hdr,
+ daddr));
+}
+
+static void
+tcf_ct_flow_table_add_action_nat_tcp(const struct nf_conntrack_tuple *tuple,
+ struct nf_conntrack_tuple target,
+ struct flow_action *action)
+{
+ __be16 target_src = target.src.u.tcp.port;
+ __be16 target_dst = target.dst.u.tcp.port;
+
+ if (target_src != tuple->src.u.tcp.port)
+ tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_TCP,
+ offsetof(struct tcphdr, source),
+ 0xFFFF, be16_to_cpu(target_src));
+ if (target_dst != tuple->dst.u.tcp.port)
+ tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_TCP,
+ offsetof(struct tcphdr, dest),
+ 0xFFFF, be16_to_cpu(target_dst));
+}
+
+static void
+tcf_ct_flow_table_add_action_nat_udp(const struct nf_conntrack_tuple *tuple,
+ struct nf_conntrack_tuple target,
+ struct flow_action *action)
+{
+ __be16 target_src = target.src.u.udp.port;
+ __be16 target_dst = target.dst.u.udp.port;
+
+ if (target_src != tuple->src.u.udp.port)
+ tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_TCP,
+ offsetof(struct udphdr, source),
+ 0xFFFF, be16_to_cpu(target_src));
+ if (target_dst != tuple->dst.u.udp.port)
+ tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_TCP,
+ offsetof(struct udphdr, dest),
+ 0xFFFF, be16_to_cpu(target_dst));
+}
+
+static void tcf_ct_flow_table_add_action_meta(struct nf_conn *ct,
+ enum ip_conntrack_dir dir,
+ struct flow_action *action)
+{
+ struct nf_conn_labels *ct_labels;
+ struct flow_action_entry *entry;
+ enum ip_conntrack_info ctinfo;
+ u32 *act_ct_labels;
+
+ entry = tcf_ct_flow_table_flow_action_get_next(action);
+ entry->id = FLOW_ACTION_CT_METADATA;
+#if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK)
+ entry->ct_metadata.mark = ct->mark;
+#endif
+ ctinfo = dir == IP_CT_DIR_ORIGINAL ? IP_CT_ESTABLISHED :
+ IP_CT_ESTABLISHED_REPLY;
+ /* aligns with the CT reference on the SKB nf_ct_set */
+ entry->ct_metadata.cookie = (unsigned long)ct | ctinfo;
+
+ act_ct_labels = entry->ct_metadata.labels;
+ ct_labels = nf_ct_labels_find(ct);
+ if (ct_labels)
+ memcpy(act_ct_labels, ct_labels->bits, NF_CT_LABELS_MAX_SIZE);
+ else
+ memset(act_ct_labels, 0, NF_CT_LABELS_MAX_SIZE);
+}
+
+static int tcf_ct_flow_table_add_action_nat(struct net *net,
+ struct nf_conn *ct,
+ enum ip_conntrack_dir dir,
+ struct flow_action *action)
+{
+ const struct nf_conntrack_tuple *tuple = &ct->tuplehash[dir].tuple;
+ struct nf_conntrack_tuple target;
+
+ nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple);
+
+ switch (tuple->src.l3num) {
+ case NFPROTO_IPV4:
+ tcf_ct_flow_table_add_action_nat_ipv4(tuple, target,
+ action);
+ break;
+ case NFPROTO_IPV6:
+ tcf_ct_flow_table_add_action_nat_ipv6(tuple, target,
+ action);
+ break;
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ switch (nf_ct_protonum(ct)) {
+ case IPPROTO_TCP:
+ tcf_ct_flow_table_add_action_nat_tcp(tuple, target, action);
+ break;
+ case IPPROTO_UDP:
+ tcf_ct_flow_table_add_action_nat_udp(tuple, target, action);
+ break;
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ return 0;
+}
+
+static int tcf_ct_flow_table_fill_actions(struct net *net,
+ const struct flow_offload *flow,
+ enum flow_offload_tuple_dir tdir,
+ struct nf_flow_rule *flow_rule)
+{
+ struct flow_action *action = &flow_rule->rule->action;
+ int num_entries = action->num_entries;
+ struct nf_conn *ct = flow->ct;
+ enum ip_conntrack_dir dir;
+ int i, err;
+
+ switch (tdir) {
+ case FLOW_OFFLOAD_DIR_ORIGINAL:
+ dir = IP_CT_DIR_ORIGINAL;
+ break;
+ case FLOW_OFFLOAD_DIR_REPLY:
+ dir = IP_CT_DIR_REPLY;
+ break;
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ err = tcf_ct_flow_table_add_action_nat(net, ct, dir, action);
+ if (err)
+ goto err_nat;
+
+ tcf_ct_flow_table_add_action_meta(ct, dir, action);
+ return 0;
+
+err_nat:
+ /* Clear filled actions */
+ for (i = num_entries; i < action->num_entries; i++)
+ memset(&action->entries[i], 0, sizeof(action->entries[i]));
+ action->num_entries = num_entries;
+
+ return err;
+}
+
+static struct nf_flowtable_type flowtable_ct = {
+ .action = tcf_ct_flow_table_fill_actions,
+ .owner = THIS_MODULE,
+};
+
+static int tcf_ct_flow_table_get(struct tcf_ct_params *params)
+{
+ struct tcf_ct_flow_table *ct_ft;
+ int err = -ENOMEM;
+
+ mutex_lock(&zones_mutex);
+ ct_ft = rhashtable_lookup_fast(&zones_ht, &params->zone, zones_params);
+ if (ct_ft && refcount_inc_not_zero(&ct_ft->ref))
+ goto out_unlock;
+
+ ct_ft = kzalloc(sizeof(*ct_ft), GFP_KERNEL);
+ if (!ct_ft)
+ goto err_alloc;
+ refcount_set(&ct_ft->ref, 1);
+
+ ct_ft->zone = params->zone;
+ err = rhashtable_insert_fast(&zones_ht, &ct_ft->node, zones_params);
+ if (err)
+ goto err_insert;
+
+ ct_ft->nf_ft.type = &flowtable_ct;
+ ct_ft->nf_ft.flags |= NF_FLOWTABLE_HW_OFFLOAD;
+ err = nf_flow_table_init(&ct_ft->nf_ft);
+ if (err)
+ goto err_init;
+
+ __module_get(THIS_MODULE);
+out_unlock:
+ params->ct_ft = ct_ft;
+ params->nf_ft = &ct_ft->nf_ft;
+ mutex_unlock(&zones_mutex);
+
+ return 0;
+
+err_init:
+ rhashtable_remove_fast(&zones_ht, &ct_ft->node, zones_params);
+err_insert:
+ kfree(ct_ft);
+err_alloc:
+ mutex_unlock(&zones_mutex);
+ return err;
+}
+
+static void tcf_ct_flow_table_cleanup_work(struct work_struct *work)
+{
+ struct tcf_ct_flow_table *ct_ft;
+
+ ct_ft = container_of(to_rcu_work(work), struct tcf_ct_flow_table,
+ rwork);
+ nf_flow_table_free(&ct_ft->nf_ft);
+ kfree(ct_ft);
+
+ module_put(THIS_MODULE);
+}
+
+static void tcf_ct_flow_table_put(struct tcf_ct_params *params)
+{
+ struct tcf_ct_flow_table *ct_ft = params->ct_ft;
+
+ if (refcount_dec_and_test(&params->ct_ft->ref)) {
+ rhashtable_remove_fast(&zones_ht, &ct_ft->node, zones_params);
+ INIT_RCU_WORK(&ct_ft->rwork, tcf_ct_flow_table_cleanup_work);
+ queue_rcu_work(act_ct_wq, &ct_ft->rwork);
+ }
+}
+
+static void tcf_ct_flow_table_add(struct tcf_ct_flow_table *ct_ft,
+ struct nf_conn *ct,
+ bool tcp)
+{
+ struct flow_offload *entry;
+ int err;
+
+ if (test_and_set_bit(IPS_OFFLOAD_BIT, &ct->status))
+ return;
+
+ entry = flow_offload_alloc(ct);
+ if (!entry) {
+ WARN_ON_ONCE(1);
+ goto err_alloc;
+ }
+
+ if (tcp) {
+ ct->proto.tcp.seen[0].flags |= IP_CT_TCP_FLAG_BE_LIBERAL;
+ ct->proto.tcp.seen[1].flags |= IP_CT_TCP_FLAG_BE_LIBERAL;
+ }
+
+ err = flow_offload_add(&ct_ft->nf_ft, entry);
+ if (err)
+ goto err_add;
+
+ return;
+
+err_add:
+ flow_offload_free(entry);
+err_alloc:
+ clear_bit(IPS_OFFLOAD_BIT, &ct->status);
+}
+
+static void tcf_ct_flow_table_process_conn(struct tcf_ct_flow_table *ct_ft,
+ struct nf_conn *ct,
+ enum ip_conntrack_info ctinfo)
+{
+ bool tcp = false;
+
+ if (ctinfo != IP_CT_ESTABLISHED && ctinfo != IP_CT_ESTABLISHED_REPLY)
+ return;
+
+ switch (nf_ct_protonum(ct)) {
+ case IPPROTO_TCP:
+ tcp = true;
+ if (ct->proto.tcp.state != TCP_CONNTRACK_ESTABLISHED)
+ return;
+ break;
+ case IPPROTO_UDP:
+ break;
+ default:
+ return;
+ }
+
+ if (nf_ct_ext_exist(ct, NF_CT_EXT_HELPER) ||
+ ct->status & IPS_SEQ_ADJUST)
+ return;
+
+ tcf_ct_flow_table_add(ct_ft, ct, tcp);
+}
+
+static bool
+tcf_ct_flow_table_fill_tuple_ipv4(struct sk_buff *skb,
+ struct flow_offload_tuple *tuple,
+ struct tcphdr **tcph)
+{
+ struct flow_ports *ports;
+ unsigned int thoff;
+ struct iphdr *iph;
+
+ if (!pskb_network_may_pull(skb, sizeof(*iph)))
+ return false;
+
+ iph = ip_hdr(skb);
+ thoff = iph->ihl * 4;
+
+ if (ip_is_fragment(iph) ||
+ unlikely(thoff != sizeof(struct iphdr)))
+ return false;
+
+ if (iph->protocol != IPPROTO_TCP &&
+ iph->protocol != IPPROTO_UDP)
+ return false;
+
+ if (iph->ttl <= 1)
+ return false;
+
+ if (!pskb_network_may_pull(skb, iph->protocol == IPPROTO_TCP ?
+ thoff + sizeof(struct tcphdr) :
+ thoff + sizeof(*ports)))
+ return false;
+
+ iph = ip_hdr(skb);
+ if (iph->protocol == IPPROTO_TCP)
+ *tcph = (void *)(skb_network_header(skb) + thoff);
+
+ ports = (struct flow_ports *)(skb_network_header(skb) + thoff);
+ tuple->src_v4.s_addr = iph->saddr;
+ tuple->dst_v4.s_addr = iph->daddr;
+ tuple->src_port = ports->source;
+ tuple->dst_port = ports->dest;
+ tuple->l3proto = AF_INET;
+ tuple->l4proto = iph->protocol;
+
+ return true;
+}
+
+static bool
+tcf_ct_flow_table_fill_tuple_ipv6(struct sk_buff *skb,
+ struct flow_offload_tuple *tuple,
+ struct tcphdr **tcph)
+{
+ struct flow_ports *ports;
+ struct ipv6hdr *ip6h;
+ unsigned int thoff;
+
+ if (!pskb_network_may_pull(skb, sizeof(*ip6h)))
+ return false;
+
+ ip6h = ipv6_hdr(skb);
+
+ if (ip6h->nexthdr != IPPROTO_TCP &&
+ ip6h->nexthdr != IPPROTO_UDP)
+ return false;
+
+ if (ip6h->hop_limit <= 1)
+ return false;
+
+ thoff = sizeof(*ip6h);
+ if (!pskb_network_may_pull(skb, ip6h->nexthdr == IPPROTO_TCP ?
+ thoff + sizeof(struct tcphdr) :
+ thoff + sizeof(*ports)))
+ return false;
+
+ ip6h = ipv6_hdr(skb);
+ if (ip6h->nexthdr == IPPROTO_TCP)
+ *tcph = (void *)(skb_network_header(skb) + thoff);
+
+ ports = (struct flow_ports *)(skb_network_header(skb) + thoff);
+ tuple->src_v6 = ip6h->saddr;
+ tuple->dst_v6 = ip6h->daddr;
+ tuple->src_port = ports->source;
+ tuple->dst_port = ports->dest;
+ tuple->l3proto = AF_INET6;
+ tuple->l4proto = ip6h->nexthdr;
+
+ return true;
+}
+
+static bool tcf_ct_flow_table_lookup(struct tcf_ct_params *p,
+ struct sk_buff *skb,
+ u8 family)
+{
+ struct nf_flowtable *nf_ft = &p->ct_ft->nf_ft;
+ struct flow_offload_tuple_rhash *tuplehash;
+ struct flow_offload_tuple tuple = {};
+ enum ip_conntrack_info ctinfo;
+ struct tcphdr *tcph = NULL;
+ struct flow_offload *flow;
+ struct nf_conn *ct;
+ u8 dir;
+
+ /* Previously seen or loopback */
+ ct = nf_ct_get(skb, &ctinfo);
+ if ((ct && !nf_ct_is_template(ct)) || ctinfo == IP_CT_UNTRACKED)
+ return false;
+
+ switch (family) {
+ case NFPROTO_IPV4:
+ if (!tcf_ct_flow_table_fill_tuple_ipv4(skb, &tuple, &tcph))
+ return false;
+ break;
+ case NFPROTO_IPV6:
+ if (!tcf_ct_flow_table_fill_tuple_ipv6(skb, &tuple, &tcph))
+ return false;
+ break;
+ default:
+ return false;
+ }
+
+ tuplehash = flow_offload_lookup(nf_ft, &tuple);
+ if (!tuplehash)
+ return false;
+
+ dir = tuplehash->tuple.dir;
+ flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
+ ct = flow->ct;
+
+ if (tcph && (unlikely(tcph->fin || tcph->rst))) {
+ flow_offload_teardown(flow);
+ return false;
+ }
+
+ ctinfo = dir == FLOW_OFFLOAD_DIR_ORIGINAL ? IP_CT_ESTABLISHED :
+ IP_CT_ESTABLISHED_REPLY;
+
+ flow_offload_refresh(nf_ft, flow);
+ nf_conntrack_get(&ct->ct_general);
+ nf_ct_set(skb, ct, ctinfo);
+
+ return true;
+}
+
+static int tcf_ct_flow_tables_init(void)
+{
+ return rhashtable_init(&zones_ht, &zones_params);
+}
+
+static void tcf_ct_flow_tables_uninit(void)
+{
+ rhashtable_destroy(&zones_ht);
+}
+
static struct tc_action_ops act_ct_ops;
static unsigned int ct_net_id;
@@ -207,6 +726,8 @@ static void tcf_ct_params_free(struct rcu_head *head)
struct tcf_ct_params *params = container_of(head,
struct tcf_ct_params, rcu);
+ tcf_ct_flow_table_put(params);
+
if (params->tmpl)
nf_conntrack_put(&params->tmpl->ct_general);
kfree(params);
@@ -387,6 +908,7 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a,
struct nf_hook_state state;
int nh_ofs, err, retval;
struct tcf_ct_params *p;
+ bool skip_add = false;
struct nf_conn *ct;
u8 family;
@@ -436,6 +958,11 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a,
*/
cached = tcf_ct_skb_nfct_cached(net, skb, p->zone, force);
if (!cached) {
+ if (!commit && tcf_ct_flow_table_lookup(p, skb, family)) {
+ skip_add = true;
+ goto do_nat;
+ }
+
/* Associate skb with specified zone. */
if (tmpl) {
ct = nf_ct_get(skb, &ctinfo);
@@ -453,6 +980,7 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a,
goto out_push;
}
+do_nat:
ct = nf_ct_get(skb, &ctinfo);
if (!ct)
goto out_push;
@@ -470,6 +998,8 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a,
* even if the connection is already confirmed.
*/
nf_conntrack_confirm(skb);
+ } else if (!skip_add) {
+ tcf_ct_flow_table_process_conn(p->ct_ft, ct, ctinfo);
}
out_push:
@@ -730,6 +1260,10 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla,
if (err)
goto cleanup;
+ err = tcf_ct_flow_table_get(params);
+ if (err)
+ goto cleanup;
+
spin_lock_bh(&c->tcf_lock);
goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
params = rcu_replace_pointer(c->params, params,
@@ -974,13 +1508,46 @@ static struct pernet_operations ct_net_ops = {
static int __init ct_init_module(void)
{
- return tcf_register_action(&act_ct_ops, &ct_net_ops);
+ int err;
+
+ act_ct_wq = alloc_ordered_workqueue("act_ct_workqueue", 0);
+ if (!act_ct_wq)
+ return -ENOMEM;
+
+ err = tcf_ct_flow_tables_init();
+ if (err)
+ goto err_tbl_init;
+
+ err = tcf_register_action(&act_ct_ops, &ct_net_ops);
+ if (err)
+ goto err_register;
+
+ return 0;
+
+err_tbl_init:
+ destroy_workqueue(act_ct_wq);
+err_register:
+ tcf_ct_flow_tables_uninit();
+ return err;
}
static void __exit ct_cleanup_module(void)
{
tcf_unregister_action(&act_ct_ops, &ct_net_ops);
+ tcf_ct_flow_tables_uninit();
+ destroy_workqueue(act_ct_wq);
+}
+
+void tcf_ct_flow_table_restore_skb(struct sk_buff *skb, unsigned long cookie)
+{
+ enum ip_conntrack_info ctinfo = cookie & NFCT_INFOMASK;
+ struct nf_conn *ct;
+
+ ct = (struct nf_conn *)(cookie & NFCT_PTRMASK);
+ nf_conntrack_get(&ct->ct_general);
+ nf_ct_set(skb, ct, ctinfo);
}
+EXPORT_SYMBOL_GPL(tcf_ct_flow_table_restore_skb);
module_init(ct_init_module);
module_exit(ct_cleanup_module);
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 3ad718576304..d41d6200d9de 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -409,6 +409,16 @@ done:
return p->tcf_action;
}
+static void tcf_pedit_stats_update(struct tc_action *a, u64 bytes, u32 packets,
+ u64 lastuse, bool hw)
+{
+ struct tcf_pedit *d = to_pedit(a);
+ struct tcf_t *tm = &d->tcf_tm;
+
+ tcf_action_update_stats(a, bytes, packets, false, hw);
+ tm->lastuse = max_t(u64, tm->lastuse, lastuse);
+}
+
static int tcf_pedit_dump(struct sk_buff *skb, struct tc_action *a,
int bind, int ref)
{
@@ -485,6 +495,7 @@ static struct tc_action_ops act_pedit_ops = {
.id = TCA_ID_PEDIT,
.owner = THIS_MODULE,
.act = tcf_pedit_act,
+ .stats_update = tcf_pedit_stats_update,
.dump = tcf_pedit_dump,
.cleanup = tcf_pedit_cleanup,
.init = tcf_pedit_init,
diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index ce948c1e24dc..5e2df590bb58 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -267,14 +267,12 @@ tcf_sample_get_group(const struct tc_action *a,
struct tcf_sample *s = to_sample(a);
struct psample_group *group;
- spin_lock_bh(&s->tcf_lock);
group = rcu_dereference_protected(s->psample_group,
lockdep_is_held(&s->tcf_lock));
if (group) {
psample_group_take(group);
*destructor = tcf_psample_group_put;
}
- spin_unlock_bh(&s->tcf_lock);
return group;
}
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index e857424c387c..b125b2be4467 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -73,6 +73,16 @@ err:
return TC_ACT_SHOT;
}
+static void tcf_skbedit_stats_update(struct tc_action *a, u64 bytes,
+ u32 packets, u64 lastuse, bool hw)
+{
+ struct tcf_skbedit *d = to_skbedit(a);
+ struct tcf_t *tm = &d->tcf_tm;
+
+ tcf_action_update_stats(a, bytes, packets, false, hw);
+ tm->lastuse = max_t(u64, tm->lastuse, lastuse);
+}
+
static const struct nla_policy skbedit_policy[TCA_SKBEDIT_MAX + 1] = {
[TCA_SKBEDIT_PARMS] = { .len = sizeof(struct tc_skbedit) },
[TCA_SKBEDIT_PRIORITY] = { .len = sizeof(u32) },
@@ -323,6 +333,7 @@ static struct tc_action_ops act_skbedit_ops = {
.id = TCA_ID_SKBEDIT,
.owner = THIS_MODULE,
.act = tcf_skbedit_act,
+ .stats_update = tcf_skbedit_stats_update,
.dump = tcf_skbedit_dump,
.init = tcf_skbedit_init,
.cleanup = tcf_skbedit_cleanup,
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index c2cdd0fc2e70..f6a3b969ead0 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -22,6 +22,7 @@
#include <linux/idr.h>
#include <linux/rhashtable.h>
#include <linux/jhash.h>
+#include <linux/rculist.h>
#include <net/net_namespace.h>
#include <net/sock.h>
#include <net/netlink.h>
@@ -354,7 +355,7 @@ static struct tcf_chain *tcf_chain_create(struct tcf_block *block,
chain = kzalloc(sizeof(*chain), GFP_KERNEL);
if (!chain)
return NULL;
- list_add_tail(&chain->list, &block->chain_list);
+ list_add_tail_rcu(&chain->list, &block->chain_list);
mutex_init(&chain->filter_chain_lock);
chain->block = block;
chain->index = chain_index;
@@ -394,7 +395,7 @@ static bool tcf_chain_detach(struct tcf_chain *chain)
ASSERT_BLOCK_LOCKED(block);
- list_del(&chain->list);
+ list_del_rcu(&chain->list);
if (!chain->index)
block->chain0.chain = NULL;
@@ -453,6 +454,20 @@ static struct tcf_chain *tcf_chain_lookup(struct tcf_block *block,
return NULL;
}
+#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
+static struct tcf_chain *tcf_chain_lookup_rcu(const struct tcf_block *block,
+ u32 chain_index)
+{
+ struct tcf_chain *chain;
+
+ list_for_each_entry_rcu(chain, &block->chain_list, list) {
+ if (chain->index == chain_index)
+ return chain;
+ }
+ return NULL;
+}
+#endif
+
static int tc_chain_notify(struct tcf_chain *chain, struct sk_buff *oskb,
u32 seq, u16 flags, int event, bool unicast);
@@ -693,7 +708,7 @@ static void tc_indr_block_call(struct tcf_block *block,
};
INIT_LIST_HEAD(&bo.cb_list);
- flow_indr_block_call(dev, &bo, command);
+ flow_indr_block_call(dev, &bo, command, TC_SETUP_BLOCK);
tcf_block_setup(block, &bo);
}
@@ -1559,12 +1574,15 @@ static int tcf_block_setup(struct tcf_block *block,
* to this qdisc, (optionally) tests for protocol and asks
* specific classifiers.
*/
-int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
- struct tcf_result *res, bool compat_mode)
+static inline int __tcf_classify(struct sk_buff *skb,
+ const struct tcf_proto *tp,
+ const struct tcf_proto *orig_tp,
+ struct tcf_result *res,
+ bool compat_mode,
+ u32 *last_executed_chain)
{
#ifdef CONFIG_NET_CLS_ACT
const int max_reclassify_loop = 4;
- const struct tcf_proto *orig_tp = tp;
const struct tcf_proto *first_tp;
int limit = 0;
@@ -1582,21 +1600,11 @@ reclassify:
#ifdef CONFIG_NET_CLS_ACT
if (unlikely(err == TC_ACT_RECLASSIFY && !compat_mode)) {
first_tp = orig_tp;
+ *last_executed_chain = first_tp->chain->index;
goto reset;
} else if (unlikely(TC_ACT_EXT_CMP(err, TC_ACT_GOTO_CHAIN))) {
first_tp = res->goto_tp;
-
-#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
- {
- struct tc_skb_ext *ext;
-
- ext = skb_ext_add(skb, TC_SKB_EXT);
- if (WARN_ON_ONCE(!ext))
- return TC_ACT_SHOT;
-
- ext->chain = err & TC_ACT_EXT_VAL_MASK;
- }
-#endif
+ *last_executed_chain = err & TC_ACT_EXT_VAL_MASK;
goto reset;
}
#endif
@@ -1619,8 +1627,64 @@ reset:
goto reclassify;
#endif
}
+
+int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
+ struct tcf_result *res, bool compat_mode)
+{
+ u32 last_executed_chain = 0;
+
+ return __tcf_classify(skb, tp, tp, res, compat_mode,
+ &last_executed_chain);
+}
EXPORT_SYMBOL(tcf_classify);
+int tcf_classify_ingress(struct sk_buff *skb,
+ const struct tcf_block *ingress_block,
+ const struct tcf_proto *tp,
+ struct tcf_result *res, bool compat_mode)
+{
+#if !IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
+ u32 last_executed_chain = 0;
+
+ return __tcf_classify(skb, tp, tp, res, compat_mode,
+ &last_executed_chain);
+#else
+ u32 last_executed_chain = tp ? tp->chain->index : 0;
+ const struct tcf_proto *orig_tp = tp;
+ struct tc_skb_ext *ext;
+ int ret;
+
+ ext = skb_ext_find(skb, TC_SKB_EXT);
+
+ if (ext && ext->chain) {
+ struct tcf_chain *fchain;
+
+ fchain = tcf_chain_lookup_rcu(ingress_block, ext->chain);
+ if (!fchain)
+ return TC_ACT_SHOT;
+
+ /* Consume, so cloned/redirect skbs won't inherit ext */
+ skb_ext_del(skb, TC_SKB_EXT);
+
+ tp = rcu_dereference_bh(fchain->filter_chain);
+ }
+
+ ret = __tcf_classify(skb, tp, orig_tp, res, compat_mode,
+ &last_executed_chain);
+
+ /* If we missed on some chain */
+ if (ret == TC_ACT_UNSPEC && last_executed_chain) {
+ ext = skb_ext_add(skb, TC_SKB_EXT);
+ if (WARN_ON_ONCE(!ext))
+ return TC_ACT_SHOT;
+ ext->chain = last_executed_chain;
+ }
+
+ return ret;
+#endif
+}
+EXPORT_SYMBOL(tcf_classify_ingress);
+
struct tcf_chain_info {
struct tcf_proto __rcu **pprev;
struct tcf_proto __rcu *next;
@@ -3382,14 +3446,40 @@ int tc_setup_cb_reoffload(struct tcf_block *block, struct tcf_proto *tp,
}
EXPORT_SYMBOL(tc_setup_cb_reoffload);
+static int tcf_act_get_cookie(struct flow_action_entry *entry,
+ const struct tc_action *act)
+{
+ struct tc_cookie *cookie;
+ int err = 0;
+
+ rcu_read_lock();
+ cookie = rcu_dereference(act->act_cookie);
+ if (cookie) {
+ entry->cookie = flow_action_cookie_create(cookie->data,
+ cookie->len,
+ GFP_ATOMIC);
+ if (!entry->cookie)
+ err = -ENOMEM;
+ }
+ rcu_read_unlock();
+ return err;
+}
+
+static void tcf_act_put_cookie(struct flow_action_entry *entry)
+{
+ flow_action_cookie_destroy(entry->cookie);
+}
+
void tc_cleanup_flow_action(struct flow_action *flow_action)
{
struct flow_action_entry *entry;
int i;
- flow_action_for_each(i, entry, flow_action)
+ flow_action_for_each(i, entry, flow_action) {
+ tcf_act_put_cookie(entry);
if (entry->destructor)
entry->destructor(entry->destructor_priv);
+ }
}
EXPORT_SYMBOL(tc_cleanup_flow_action);
@@ -3433,22 +3523,30 @@ static void tcf_sample_get_group(struct flow_action_entry *entry,
}
int tc_setup_flow_action(struct flow_action *flow_action,
- const struct tcf_exts *exts, bool rtnl_held)
+ const struct tcf_exts *exts)
{
- const struct tc_action *act;
+ struct tc_action *act;
int i, j, k, err = 0;
+ BUILD_BUG_ON(TCA_ACT_HW_STATS_ANY != FLOW_ACTION_HW_STATS_ANY);
+ BUILD_BUG_ON(TCA_ACT_HW_STATS_IMMEDIATE != FLOW_ACTION_HW_STATS_IMMEDIATE);
+ BUILD_BUG_ON(TCA_ACT_HW_STATS_DELAYED != FLOW_ACTION_HW_STATS_DELAYED);
+
if (!exts)
return 0;
- if (!rtnl_held)
- rtnl_lock();
-
j = 0;
tcf_exts_for_each_action(i, act, exts) {
struct flow_action_entry *entry;
entry = &flow_action->entries[j];
+ spin_lock_bh(&act->tcfa_lock);
+ err = tcf_act_get_cookie(entry, act);
+ if (err)
+ goto err_out_locked;
+
+ entry->hw_stats = act->hw_stats;
+
if (is_tcf_gact_ok(act)) {
entry->id = FLOW_ACTION_ACCEPT;
} else if (is_tcf_gact_shot(act)) {
@@ -3489,13 +3587,13 @@ int tc_setup_flow_action(struct flow_action *flow_action,
break;
default:
err = -EOPNOTSUPP;
- goto err_out;
+ goto err_out_locked;
}
} else if (is_tcf_tunnel_set(act)) {
entry->id = FLOW_ACTION_TUNNEL_ENCAP;
err = tcf_tunnel_encap_get_tunnel(entry, act);
if (err)
- goto err_out;
+ goto err_out_locked;
} else if (is_tcf_tunnel_release(act)) {
entry->id = FLOW_ACTION_TUNNEL_DECAP;
} else if (is_tcf_pedit(act)) {
@@ -3509,12 +3607,13 @@ int tc_setup_flow_action(struct flow_action *flow_action,
break;
default:
err = -EOPNOTSUPP;
- goto err_out;
+ goto err_out_locked;
}
entry->mangle.htype = tcf_pedit_htype(act, k);
entry->mangle.mask = tcf_pedit_mask(act, k);
entry->mangle.val = tcf_pedit_val(act, k);
entry->mangle.offset = tcf_pedit_offset(act, k);
+ entry->hw_stats = act->hw_stats;
entry = &flow_action->entries[++j];
}
} else if (is_tcf_csum(act)) {
@@ -3538,6 +3637,7 @@ int tc_setup_flow_action(struct flow_action *flow_action,
entry->id = FLOW_ACTION_CT;
entry->ct.action = tcf_ct_action(act);
entry->ct.zone = tcf_ct_zone(act);
+ entry->ct.flow_table = tcf_ct_ft(act);
} else if (is_tcf_mpls(act)) {
switch (tcf_mpls_action(act)) {
case TCA_MPLS_ACT_PUSH:
@@ -3560,28 +3660,32 @@ int tc_setup_flow_action(struct flow_action *flow_action,
entry->mpls_mangle.ttl = tcf_mpls_ttl(act);
break;
default:
- goto err_out;
+ goto err_out_locked;
}
} else if (is_tcf_skbedit_ptype(act)) {
entry->id = FLOW_ACTION_PTYPE;
entry->ptype = tcf_skbedit_ptype(act);
+ } else if (is_tcf_skbedit_priority(act)) {
+ entry->id = FLOW_ACTION_PRIORITY;
+ entry->priority = tcf_skbedit_priority(act);
} else {
err = -EOPNOTSUPP;
- goto err_out;
+ goto err_out_locked;
}
+ spin_unlock_bh(&act->tcfa_lock);
if (!is_tcf_pedit(act))
j++;
}
err_out:
- if (!rtnl_held)
- rtnl_unlock();
-
if (err)
tc_cleanup_flow_action(flow_action);
return err;
+err_out_locked:
+ spin_unlock_bh(&act->tcfa_lock);
+ goto err_out;
}
EXPORT_SYMBOL(tc_setup_flow_action);
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index d32d4233d337..74a0febcafb8 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -450,8 +450,7 @@ static int fl_hw_replace_filter(struct tcf_proto *tp,
cls_flower.rule->match.key = &f->mkey;
cls_flower.classid = f->res.classid;
- err = tc_setup_flow_action(&cls_flower.rule->action, &f->exts,
- rtnl_held);
+ err = tc_setup_flow_action(&cls_flower.rule->action, &f->exts);
if (err) {
kfree(cls_flower.rule);
if (skip_sw) {
@@ -493,7 +492,9 @@ static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f,
tcf_exts_stats_update(&f->exts, cls_flower.stats.bytes,
cls_flower.stats.pkts,
- cls_flower.stats.lastused);
+ cls_flower.stats.lastused,
+ cls_flower.stats.used_hw_stats,
+ cls_flower.stats.used_hw_stats_valid);
}
static void __fl_put(struct cls_fl_filter *f)
@@ -739,7 +740,8 @@ static void fl_set_key_val(struct nlattr **tb,
}
static int fl_set_key_port_range(struct nlattr **tb, struct fl_flow_key *key,
- struct fl_flow_key *mask)
+ struct fl_flow_key *mask,
+ struct netlink_ext_ack *extack)
{
fl_set_key_val(tb, &key->tp_range.tp_min.dst,
TCA_FLOWER_KEY_PORT_DST_MIN, &mask->tp_range.tp_min.dst,
@@ -754,20 +756,30 @@ static int fl_set_key_port_range(struct nlattr **tb, struct fl_flow_key *key,
TCA_FLOWER_KEY_PORT_SRC_MAX, &mask->tp_range.tp_max.src,
TCA_FLOWER_UNSPEC, sizeof(key->tp_range.tp_max.src));
- if ((mask->tp_range.tp_min.dst && mask->tp_range.tp_max.dst &&
- htons(key->tp_range.tp_max.dst) <=
- htons(key->tp_range.tp_min.dst)) ||
- (mask->tp_range.tp_min.src && mask->tp_range.tp_max.src &&
- htons(key->tp_range.tp_max.src) <=
- htons(key->tp_range.tp_min.src)))
+ if (mask->tp_range.tp_min.dst && mask->tp_range.tp_max.dst &&
+ htons(key->tp_range.tp_max.dst) <=
+ htons(key->tp_range.tp_min.dst)) {
+ NL_SET_ERR_MSG_ATTR(extack,
+ tb[TCA_FLOWER_KEY_PORT_DST_MIN],
+ "Invalid destination port range (min must be strictly smaller than max)");
return -EINVAL;
+ }
+ if (mask->tp_range.tp_min.src && mask->tp_range.tp_max.src &&
+ htons(key->tp_range.tp_max.src) <=
+ htons(key->tp_range.tp_min.src)) {
+ NL_SET_ERR_MSG_ATTR(extack,
+ tb[TCA_FLOWER_KEY_PORT_SRC_MIN],
+ "Invalid source port range (min must be strictly smaller than max)");
+ return -EINVAL;
+ }
return 0;
}
static int fl_set_key_mpls(struct nlattr **tb,
struct flow_dissector_key_mpls *key_val,
- struct flow_dissector_key_mpls *key_mask)
+ struct flow_dissector_key_mpls *key_mask,
+ struct netlink_ext_ack *extack)
{
if (tb[TCA_FLOWER_KEY_MPLS_TTL]) {
key_val->mpls_ttl = nla_get_u8(tb[TCA_FLOWER_KEY_MPLS_TTL]);
@@ -776,24 +788,36 @@ static int fl_set_key_mpls(struct nlattr **tb,
if (tb[TCA_FLOWER_KEY_MPLS_BOS]) {
u8 bos = nla_get_u8(tb[TCA_FLOWER_KEY_MPLS_BOS]);
- if (bos & ~MPLS_BOS_MASK)
+ if (bos & ~MPLS_BOS_MASK) {
+ NL_SET_ERR_MSG_ATTR(extack,
+ tb[TCA_FLOWER_KEY_MPLS_BOS],
+ "Bottom Of Stack (BOS) must be 0 or 1");
return -EINVAL;
+ }
key_val->mpls_bos = bos;
key_mask->mpls_bos = MPLS_BOS_MASK;
}
if (tb[TCA_FLOWER_KEY_MPLS_TC]) {
u8 tc = nla_get_u8(tb[TCA_FLOWER_KEY_MPLS_TC]);
- if (tc & ~MPLS_TC_MASK)
+ if (tc & ~MPLS_TC_MASK) {
+ NL_SET_ERR_MSG_ATTR(extack,
+ tb[TCA_FLOWER_KEY_MPLS_TC],
+ "Traffic Class (TC) must be between 0 and 7");
return -EINVAL;
+ }
key_val->mpls_tc = tc;
key_mask->mpls_tc = MPLS_TC_MASK;
}
if (tb[TCA_FLOWER_KEY_MPLS_LABEL]) {
u32 label = nla_get_u32(tb[TCA_FLOWER_KEY_MPLS_LABEL]);
- if (label & ~MPLS_LABEL_MASK)
+ if (label & ~MPLS_LABEL_MASK) {
+ NL_SET_ERR_MSG_ATTR(extack,
+ tb[TCA_FLOWER_KEY_MPLS_LABEL],
+ "Label must be between 0 and 1048575");
return -EINVAL;
+ }
key_val->mpls_label = label;
key_mask->mpls_label = MPLS_LABEL_MASK;
}
@@ -834,14 +858,16 @@ static void fl_set_key_flag(u32 flower_key, u32 flower_mask,
}
}
-static int fl_set_key_flags(struct nlattr **tb,
- u32 *flags_key, u32 *flags_mask)
+static int fl_set_key_flags(struct nlattr **tb, u32 *flags_key,
+ u32 *flags_mask, struct netlink_ext_ack *extack)
{
u32 key, mask;
/* mask is mandatory for flags */
- if (!tb[TCA_FLOWER_KEY_FLAGS_MASK])
+ if (!tb[TCA_FLOWER_KEY_FLAGS_MASK]) {
+ NL_SET_ERR_MSG(extack, "Missing flags mask");
return -EINVAL;
+ }
key = be32_to_cpu(nla_get_u32(tb[TCA_FLOWER_KEY_FLAGS]));
mask = be32_to_cpu(nla_get_u32(tb[TCA_FLOWER_KEY_FLAGS_MASK]));
@@ -1365,7 +1391,7 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
sizeof(key->icmp.code));
} else if (key->basic.n_proto == htons(ETH_P_MPLS_UC) ||
key->basic.n_proto == htons(ETH_P_MPLS_MC)) {
- ret = fl_set_key_mpls(tb, &key->mpls, &mask->mpls);
+ ret = fl_set_key_mpls(tb, &key->mpls, &mask->mpls, extack);
if (ret)
return ret;
} else if (key->basic.n_proto == htons(ETH_P_ARP) ||
@@ -1390,7 +1416,7 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
if (key->basic.ip_proto == IPPROTO_TCP ||
key->basic.ip_proto == IPPROTO_UDP ||
key->basic.ip_proto == IPPROTO_SCTP) {
- ret = fl_set_key_port_range(tb, key, mask);
+ ret = fl_set_key_port_range(tb, key, mask, extack);
if (ret)
return ret;
}
@@ -1452,7 +1478,8 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
return ret;
if (tb[TCA_FLOWER_KEY_FLAGS])
- ret = fl_set_key_flags(tb, &key->control.flags, &mask->control.flags);
+ ret = fl_set_key_flags(tb, &key->control.flags,
+ &mask->control.flags, extack);
return ret;
}
@@ -2001,8 +2028,7 @@ static int fl_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb,
cls_flower.rule->match.mask = &f->mask->key;
cls_flower.rule->match.key = &f->mkey;
- err = tc_setup_flow_action(&cls_flower.rule->action, &f->exts,
- true);
+ err = tc_setup_flow_action(&cls_flower.rule->action, &f->exts);
if (err) {
kfree(cls_flower.rule);
if (tc_skip_sw(f->flags)) {
diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index 610a0b728161..8d39dbcf1746 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -97,7 +97,7 @@ static int mall_replace_hw_filter(struct tcf_proto *tp,
cls_mall.command = TC_CLSMATCHALL_REPLACE;
cls_mall.cookie = cookie;
- err = tc_setup_flow_action(&cls_mall.rule->action, &head->exts, true);
+ err = tc_setup_flow_action(&cls_mall.rule->action, &head->exts);
if (err) {
kfree(cls_mall.rule);
mall_destroy_hw_filter(tp, head, cookie, NULL);
@@ -302,7 +302,7 @@ static int mall_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb,
TC_CLSMATCHALL_REPLACE : TC_CLSMATCHALL_DESTROY;
cls_mall.cookie = (unsigned long)head;
- err = tc_setup_flow_action(&cls_mall.rule->action, &head->exts, true);
+ err = tc_setup_flow_action(&cls_mall.rule->action, &head->exts);
if (err) {
kfree(cls_mall.rule);
if (add && tc_skip_sw(head->flags)) {
@@ -338,7 +338,9 @@ static void mall_stats_hw_filter(struct tcf_proto *tp,
tc_setup_cb_call(block, TC_SETUP_CLSMATCHALL, &cls_mall, false, true);
tcf_exts_stats_update(&head->exts, cls_mall.stats.bytes,
- cls_mall.stats.pkts, cls_mall.stats.lastused);
+ cls_mall.stats.pkts, cls_mall.stats.lastused,
+ cls_mall.stats.used_hw_stats,
+ cls_mall.stats.used_hw_stats_valid);
}
static int mall_dump(struct net *net, struct tcf_proto *tp, void *fh,
diff --git a/net/sched/em_ipt.c b/net/sched/em_ipt.c
index 9fff6480acc6..eecfe072c508 100644
--- a/net/sched/em_ipt.c
+++ b/net/sched/em_ipt.c
@@ -22,7 +22,7 @@ struct em_ipt_match {
const struct xt_match *match;
u32 hook;
u8 nfproto;
- u8 match_data[0] __aligned(8);
+ u8 match_data[] __aligned(8);
};
struct em_ipt_xt_match {
diff --git a/net/sched/em_nbyte.c b/net/sched/em_nbyte.c
index 88c7ce42df7e..2c1192a2ee5e 100644
--- a/net/sched/em_nbyte.c
+++ b/net/sched/em_nbyte.c
@@ -16,7 +16,7 @@
struct nbyte_data {
struct tcf_em_nbyte hdr;
- char pattern[0];
+ char pattern[];
};
static int em_nbyte_change(struct net *net, void *data, int data_len,
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 50794125bf02..0d99df1e764d 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -618,21 +618,28 @@ void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc)
}
EXPORT_SYMBOL(qdisc_watchdog_init);
-void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd, u64 expires)
+void qdisc_watchdog_schedule_range_ns(struct qdisc_watchdog *wd, u64 expires,
+ u64 delta_ns)
{
if (test_bit(__QDISC_STATE_DEACTIVATED,
&qdisc_root_sleeping(wd->qdisc)->state))
return;
- if (wd->last_expires == expires)
- return;
+ if (hrtimer_is_queued(&wd->timer)) {
+ /* If timer is already set in [expires, expires + delta_ns],
+ * do not reprogram it.
+ */
+ if (wd->last_expires - expires <= delta_ns)
+ return;
+ }
wd->last_expires = expires;
- hrtimer_start(&wd->timer,
- ns_to_ktime(expires),
- HRTIMER_MODE_ABS_PINNED);
+ hrtimer_start_range_ns(&wd->timer,
+ ns_to_ktime(expires),
+ delta_ns,
+ HRTIMER_MODE_ABS_PINNED);
}
-EXPORT_SYMBOL(qdisc_watchdog_schedule_ns);
+EXPORT_SYMBOL(qdisc_watchdog_schedule_range_ns);
void qdisc_watchdog_cancel(struct qdisc_watchdog *wd)
{
diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c
index f4f9b8cdbffb..ee12ca9f55b4 100644
--- a/net/sched/sch_atm.c
+++ b/net/sched/sch_atm.c
@@ -58,7 +58,7 @@ struct atm_flow_data {
struct atm_flow_data *excess; /* flow for excess traffic;
NULL to set CLP instead */
int hdr_len;
- unsigned char hdr[0]; /* header data; MUST BE LAST */
+ unsigned char hdr[]; /* header data; MUST BE LAST */
};
struct atm_qdisc_data {
diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c
index 37c8aa75d70c..a579a4131d22 100644
--- a/net/sched/sch_fifo.c
+++ b/net/sched/sch_fifo.c
@@ -12,6 +12,7 @@
#include <linux/errno.h>
#include <linux/skbuff.h>
#include <net/pkt_sched.h>
+#include <net/pkt_cls.h>
/* 1 band FIFO pseudo-"scheduler" */
@@ -51,8 +52,49 @@ static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc *sch,
return NET_XMIT_CN;
}
-static int fifo_init(struct Qdisc *sch, struct nlattr *opt,
- struct netlink_ext_ack *extack)
+static void fifo_offload_init(struct Qdisc *sch)
+{
+ struct net_device *dev = qdisc_dev(sch);
+ struct tc_fifo_qopt_offload qopt;
+
+ if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc)
+ return;
+
+ qopt.command = TC_FIFO_REPLACE;
+ qopt.handle = sch->handle;
+ qopt.parent = sch->parent;
+ dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_FIFO, &qopt);
+}
+
+static void fifo_offload_destroy(struct Qdisc *sch)
+{
+ struct net_device *dev = qdisc_dev(sch);
+ struct tc_fifo_qopt_offload qopt;
+
+ if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc)
+ return;
+
+ qopt.command = TC_FIFO_DESTROY;
+ qopt.handle = sch->handle;
+ qopt.parent = sch->parent;
+ dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_FIFO, &qopt);
+}
+
+static int fifo_offload_dump(struct Qdisc *sch)
+{
+ struct tc_fifo_qopt_offload qopt;
+
+ qopt.command = TC_FIFO_STATS;
+ qopt.handle = sch->handle;
+ qopt.parent = sch->parent;
+ qopt.stats.bstats = &sch->bstats;
+ qopt.stats.qstats = &sch->qstats;
+
+ return qdisc_offload_dump_helper(sch, TC_SETUP_QDISC_FIFO, &qopt);
+}
+
+static int __fifo_init(struct Qdisc *sch, struct nlattr *opt,
+ struct netlink_ext_ack *extack)
{
bool bypass;
bool is_bfifo = sch->ops == &bfifo_qdisc_ops;
@@ -82,10 +124,35 @@ static int fifo_init(struct Qdisc *sch, struct nlattr *opt,
sch->flags |= TCQ_F_CAN_BYPASS;
else
sch->flags &= ~TCQ_F_CAN_BYPASS;
+
return 0;
}
-static int fifo_dump(struct Qdisc *sch, struct sk_buff *skb)
+static int fifo_init(struct Qdisc *sch, struct nlattr *opt,
+ struct netlink_ext_ack *extack)
+{
+ int err;
+
+ err = __fifo_init(sch, opt, extack);
+ if (err)
+ return err;
+
+ fifo_offload_init(sch);
+ return 0;
+}
+
+static int fifo_hd_init(struct Qdisc *sch, struct nlattr *opt,
+ struct netlink_ext_ack *extack)
+{
+ return __fifo_init(sch, opt, extack);
+}
+
+static void fifo_destroy(struct Qdisc *sch)
+{
+ fifo_offload_destroy(sch);
+}
+
+static int __fifo_dump(struct Qdisc *sch, struct sk_buff *skb)
{
struct tc_fifo_qopt opt = { .limit = sch->limit };
@@ -97,6 +164,22 @@ nla_put_failure:
return -1;
}
+static int fifo_dump(struct Qdisc *sch, struct sk_buff *skb)
+{
+ int err;
+
+ err = fifo_offload_dump(sch);
+ if (err)
+ return err;
+
+ return __fifo_dump(sch, skb);
+}
+
+static int fifo_hd_dump(struct Qdisc *sch, struct sk_buff *skb)
+{
+ return __fifo_dump(sch, skb);
+}
+
struct Qdisc_ops pfifo_qdisc_ops __read_mostly = {
.id = "pfifo",
.priv_size = 0,
@@ -104,6 +187,7 @@ struct Qdisc_ops pfifo_qdisc_ops __read_mostly = {
.dequeue = qdisc_dequeue_head,
.peek = qdisc_peek_head,
.init = fifo_init,
+ .destroy = fifo_destroy,
.reset = qdisc_reset_queue,
.change = fifo_init,
.dump = fifo_dump,
@@ -118,6 +202,7 @@ struct Qdisc_ops bfifo_qdisc_ops __read_mostly = {
.dequeue = qdisc_dequeue_head,
.peek = qdisc_peek_head,
.init = fifo_init,
+ .destroy = fifo_destroy,
.reset = qdisc_reset_queue,
.change = fifo_init,
.dump = fifo_dump,
@@ -131,10 +216,10 @@ struct Qdisc_ops pfifo_head_drop_qdisc_ops __read_mostly = {
.enqueue = pfifo_tail_enqueue,
.dequeue = qdisc_dequeue_head,
.peek = qdisc_peek_head,
- .init = fifo_init,
+ .init = fifo_hd_init,
.reset = qdisc_reset_queue,
- .change = fifo_init,
- .dump = fifo_dump,
+ .change = fifo_hd_init,
+ .dump = fifo_hd_dump,
.owner = THIS_MODULE,
};
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 371ad84def3b..4c060134c736 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -121,6 +121,8 @@ struct fq_sched_data {
u64 stat_flows_plimit;
u64 stat_pkts_too_long;
u64 stat_allocation_errors;
+
+ u32 timer_slack; /* hrtimer slack in ns */
struct qdisc_watchdog watchdog;
};
@@ -504,8 +506,9 @@ begin:
head = &q->old_flows;
if (!head->first) {
if (q->time_next_delayed_flow != ~0ULL)
- qdisc_watchdog_schedule_ns(&q->watchdog,
- q->time_next_delayed_flow);
+ qdisc_watchdog_schedule_range_ns(&q->watchdog,
+ q->time_next_delayed_flow,
+ q->timer_slack);
return NULL;
}
}
@@ -735,6 +738,8 @@ static int fq_resize(struct Qdisc *sch, u32 log)
}
static const struct nla_policy fq_policy[TCA_FQ_MAX + 1] = {
+ [TCA_FQ_UNSPEC] = { .strict_start_type = TCA_FQ_TIMER_SLACK },
+
[TCA_FQ_PLIMIT] = { .type = NLA_U32 },
[TCA_FQ_FLOW_PLIMIT] = { .type = NLA_U32 },
[TCA_FQ_QUANTUM] = { .type = NLA_U32 },
@@ -747,6 +752,7 @@ static const struct nla_policy fq_policy[TCA_FQ_MAX + 1] = {
[TCA_FQ_ORPHAN_MASK] = { .type = NLA_U32 },
[TCA_FQ_LOW_RATE_THRESHOLD] = { .type = NLA_U32 },
[TCA_FQ_CE_THRESHOLD] = { .type = NLA_U32 },
+ [TCA_FQ_TIMER_SLACK] = { .type = NLA_U32 },
};
static int fq_change(struct Qdisc *sch, struct nlattr *opt,
@@ -833,6 +839,9 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt,
q->ce_threshold = (u64)NSEC_PER_USEC *
nla_get_u32(tb[TCA_FQ_CE_THRESHOLD]);
+ if (tb[TCA_FQ_TIMER_SLACK])
+ q->timer_slack = nla_get_u32(tb[TCA_FQ_TIMER_SLACK]);
+
if (!err) {
sch_tree_unlock(sch);
err = fq_resize(sch, fq_log);
@@ -884,6 +893,8 @@ static int fq_init(struct Qdisc *sch, struct nlattr *opt,
q->orphan_mask = 1024 - 1;
q->low_rate_threshold = 550000 / 8;
+ q->timer_slack = 10 * NSEC_PER_USEC; /* 10 usec of hrtimer slack */
+
/* Default ce_threshold of 4294 seconds */
q->ce_threshold = (u64)NSEC_PER_USEC * ~0U;
@@ -924,7 +935,8 @@ static int fq_dump(struct Qdisc *sch, struct sk_buff *skb)
nla_put_u32(skb, TCA_FQ_LOW_RATE_THRESHOLD,
q->low_rate_threshold) ||
nla_put_u32(skb, TCA_FQ_CE_THRESHOLD, (u32)ce_threshold) ||
- nla_put_u32(skb, TCA_FQ_BUCKETS_LOG, q->fq_trees_log))
+ nla_put_u32(skb, TCA_FQ_BUCKETS_LOG, q->fq_trees_log) ||
+ nla_put_u32(skb, TCA_FQ_TIMER_SLACK, q->timer_slack))
goto nla_put_failure;
return nla_nest_end(skb, opts);
@@ -947,7 +959,8 @@ static int fq_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
st.flows_plimit = q->stat_flows_plimit;
st.pkts_too_long = q->stat_pkts_too_long;
st.allocation_errors = q->stat_allocation_errors;
- st.time_next_delayed_flow = q->time_next_delayed_flow - ktime_get_ns();
+ st.time_next_delayed_flow = q->time_next_delayed_flow + q->timer_slack -
+ ktime_get_ns();
st.flows = q->flows;
st.inactive_flows = q->inactive_flows;
st.throttled_flows = q->throttled_flows;
diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c
index 214657eb3dfd..a9da8776bf5b 100644
--- a/net/sched/sch_fq_pie.c
+++ b/net/sched/sch_fq_pie.c
@@ -189,7 +189,6 @@ static int fq_pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
out:
q->stats.dropped++;
sel_flow->vars.accu_prob = 0;
- sel_flow->vars.accu_prob_overflows = 0;
__qdisc_drop(skb, to_free);
qdisc_qstats_drop(sch);
return NET_XMIT_CN;
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 6c9595f1048a..2efd5b61acef 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -1391,6 +1391,14 @@ void mini_qdisc_pair_swap(struct mini_Qdisc_pair *miniqp,
}
EXPORT_SYMBOL(mini_qdisc_pair_swap);
+void mini_qdisc_pair_block_init(struct mini_Qdisc_pair *miniqp,
+ struct tcf_block *block)
+{
+ miniqp->miniq1.block = block;
+ miniqp->miniq2.block = block;
+}
+EXPORT_SYMBOL(mini_qdisc_pair_block_init);
+
void mini_qdisc_pair_init(struct mini_Qdisc_pair *miniqp, struct Qdisc *qdisc,
struct mini_Qdisc __rcu **p_miniq)
{
diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c
index bf56aa519797..84838128b9c5 100644
--- a/net/sched/sch_ingress.c
+++ b/net/sched/sch_ingress.c
@@ -78,6 +78,7 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt,
{
struct ingress_sched_data *q = qdisc_priv(sch);
struct net_device *dev = qdisc_dev(sch);
+ int err;
net_inc_ingress_queue();
@@ -87,7 +88,13 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt,
q->block_info.chain_head_change = clsact_chain_head_change;
q->block_info.chain_head_change_priv = &q->miniqp;
- return tcf_block_get_ext(&q->block, sch, &q->block_info, extack);
+ err = tcf_block_get_ext(&q->block, sch, &q->block_info, extack);
+ if (err)
+ return err;
+
+ mini_qdisc_pair_block_init(&q->miniqp, q->block);
+
+ return 0;
}
static void ingress_destroy(struct Qdisc *sch)
@@ -226,6 +233,8 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt,
if (err)
return err;
+ mini_qdisc_pair_block_init(&q->miniqp_ingress, q->ingress_block);
+
mini_qdisc_pair_init(&q->miniqp_egress, sch, &dev->miniq_egress);
q->egress_block_info.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS;
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 42e557d48e4e..84f82771cdf5 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -66,7 +66,7 @@
struct disttable {
u32 size;
- s16 table[0];
+ s16 table[];
};
struct netem_sched_data {
diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c
index 915bcdb59a9f..c65077f0c0f3 100644
--- a/net/sched/sch_pie.c
+++ b/net/sched/sch_pie.c
@@ -31,7 +31,7 @@ struct pie_sched_data {
};
bool pie_drop_early(struct Qdisc *sch, struct pie_params *params,
- struct pie_vars *vars, u32 qlen, u32 packet_size)
+ struct pie_vars *vars, u32 backlog, u32 packet_size)
{
u64 rnd;
u64 local_prob = vars->prob;
@@ -51,7 +51,7 @@ bool pie_drop_early(struct Qdisc *sch, struct pie_params *params,
/* If we have fewer than 2 mtu-sized packets, disable pie_drop_early,
* similar to min_th in RED
*/
- if (qlen < 2 * mtu)
+ if (backlog < 2 * mtu)
return false;
/* If bytemode is turned on, use packet size to compute new
@@ -62,27 +62,19 @@ bool pie_drop_early(struct Qdisc *sch, struct pie_params *params,
else
local_prob = vars->prob;
- if (local_prob == 0) {
+ if (local_prob == 0)
vars->accu_prob = 0;
- vars->accu_prob_overflows = 0;
- }
-
- if (local_prob > MAX_PROB - vars->accu_prob)
- vars->accu_prob_overflows++;
-
- vars->accu_prob += local_prob;
+ else
+ vars->accu_prob += local_prob;
- if (vars->accu_prob_overflows == 0 &&
- vars->accu_prob < (MAX_PROB / 100) * 85)
+ if (vars->accu_prob < (MAX_PROB / 100) * 85)
return false;
- if (vars->accu_prob_overflows == 8 &&
- vars->accu_prob >= MAX_PROB / 2)
+ if (vars->accu_prob >= (MAX_PROB / 2) * 17)
return true;
prandom_bytes(&rnd, 8);
- if (rnd < local_prob) {
+ if ((rnd >> BITS_PER_BYTE) < local_prob) {
vars->accu_prob = 0;
- vars->accu_prob_overflows = 0;
return true;
}
@@ -129,7 +121,6 @@ static int pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
out:
q->stats.dropped++;
q->vars.accu_prob = 0;
- q->vars.accu_prob_overflows = 0;
return qdisc_drop(skb, sch, to_free);
}
@@ -215,7 +206,7 @@ static int pie_change(struct Qdisc *sch, struct nlattr *opt,
}
void pie_process_dequeue(struct sk_buff *skb, struct pie_params *params,
- struct pie_vars *vars, u32 qlen)
+ struct pie_vars *vars, u32 backlog)
{
psched_time_t now = psched_get_time();
u32 dtime = 0;
@@ -231,7 +222,7 @@ void pie_process_dequeue(struct sk_buff *skb, struct pie_params *params,
vars->dq_tstamp = now;
- if (qlen == 0)
+ if (backlog == 0)
vars->qdelay = 0;
if (dtime == 0)
@@ -244,7 +235,7 @@ void pie_process_dequeue(struct sk_buff *skb, struct pie_params *params,
* we have enough packets to calculate the drain rate. Save
* current time as dq_tstamp and start measurement cycle.
*/
- if (qlen >= QUEUE_THRESHOLD && vars->dq_count == DQCOUNT_INVALID) {
+ if (backlog >= QUEUE_THRESHOLD && vars->dq_count == DQCOUNT_INVALID) {
vars->dq_tstamp = psched_get_time();
vars->dq_count = 0;
}
@@ -283,7 +274,7 @@ void pie_process_dequeue(struct sk_buff *skb, struct pie_params *params,
* dq_count to 0 to re-enter the if block when the next
* packet is dequeued
*/
- if (qlen < QUEUE_THRESHOLD) {
+ if (backlog < QUEUE_THRESHOLD) {
vars->dq_count = DQCOUNT_INVALID;
} else {
vars->dq_count = 0;
@@ -307,7 +298,7 @@ burst_allowance_reduction:
EXPORT_SYMBOL_GPL(pie_process_dequeue);
void pie_calculate_probability(struct pie_params *params, struct pie_vars *vars,
- u32 qlen)
+ u32 backlog)
{
psched_time_t qdelay = 0; /* in pschedtime */
psched_time_t qdelay_old = 0; /* in pschedtime */
@@ -322,7 +313,7 @@ void pie_calculate_probability(struct pie_params *params, struct pie_vars *vars,
vars->qdelay_old = vars->qdelay;
if (vars->avg_dq_rate > 0)
- qdelay = (qlen << PIE_SCALE) / vars->avg_dq_rate;
+ qdelay = (backlog << PIE_SCALE) / vars->avg_dq_rate;
else
qdelay = 0;
} else {
@@ -330,10 +321,10 @@ void pie_calculate_probability(struct pie_params *params, struct pie_vars *vars,
qdelay_old = vars->qdelay_old;
}
- /* If qdelay is zero and qlen is not, it means qlen is very small,
+ /* If qdelay is zero and backlog is not, it means backlog is very small,
* so we do not update probabilty in this round.
*/
- if (qdelay == 0 && qlen != 0)
+ if (qdelay == 0 && backlog != 0)
update_prob = false;
/* In the algorithm, alpha and beta are between 0 and 2 with typical
@@ -363,8 +354,8 @@ void pie_calculate_probability(struct pie_params *params, struct pie_vars *vars,
}
/* alpha and beta should be between 0 and 32, in multiples of 1/16 */
- delta += alpha * (u64)(qdelay - params->target);
- delta += beta * (u64)(qdelay - qdelay_old);
+ delta += alpha * (qdelay - params->target);
+ delta += beta * (qdelay - qdelay_old);
oldprob = vars->prob;
@@ -409,7 +400,7 @@ void pie_calculate_probability(struct pie_params *params, struct pie_vars *vars,
vars->prob -= vars->prob / 64;
vars->qdelay = qdelay;
- vars->qlen_old = qlen;
+ vars->backlog_old = backlog;
/* We restart the measurement cycle if the following conditions are met
* 1. If the delay has been low for 2 consecutive Tupdate periods
@@ -502,7 +493,7 @@ static int pie_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
{
struct pie_sched_data *q = qdisc_priv(sch);
struct tc_pie_xstats st = {
- .prob = q->vars.prob,
+ .prob = q->vars.prob << BITS_PER_BYTE,
.delay = ((u32)PSCHED_TICKS2NS(q->vars.qdelay)) /
NSEC_PER_USEC,
.packets_in = q->stats.packets_in,
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index 1695421333e3..c7de47c942e3 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -35,7 +35,11 @@
struct red_sched_data {
u32 limit; /* HARD maximal queue length */
+
unsigned char flags;
+ /* Non-flags in tc_red_qopt.flags. */
+ unsigned char userbits;
+
struct timer_list adapt_timer;
struct Qdisc *sch;
struct red_parms parms;
@@ -44,6 +48,8 @@ struct red_sched_data {
struct Qdisc *qdisc;
};
+static const u32 red_supported_flags = TC_RED_HISTORIC_FLAGS | TC_RED_NODROP;
+
static inline int red_use_ecn(struct red_sched_data *q)
{
return q->flags & TC_RED_ECN;
@@ -54,6 +60,11 @@ static inline int red_use_harddrop(struct red_sched_data *q)
return q->flags & TC_RED_HARDDROP;
}
+static int red_use_nodrop(struct red_sched_data *q)
+{
+ return q->flags & TC_RED_NODROP;
+}
+
static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch,
struct sk_buff **to_free)
{
@@ -74,23 +85,36 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch,
case RED_PROB_MARK:
qdisc_qstats_overlimit(sch);
- if (!red_use_ecn(q) || !INET_ECN_set_ce(skb)) {
+ if (!red_use_ecn(q)) {
q->stats.prob_drop++;
goto congestion_drop;
}
- q->stats.prob_mark++;
+ if (INET_ECN_set_ce(skb)) {
+ q->stats.prob_mark++;
+ } else if (!red_use_nodrop(q)) {
+ q->stats.prob_drop++;
+ goto congestion_drop;
+ }
+
+ /* Non-ECT packet in ECN nodrop mode: queue it. */
break;
case RED_HARD_MARK:
qdisc_qstats_overlimit(sch);
- if (red_use_harddrop(q) || !red_use_ecn(q) ||
- !INET_ECN_set_ce(skb)) {
+ if (red_use_harddrop(q) || !red_use_ecn(q)) {
+ q->stats.forced_drop++;
+ goto congestion_drop;
+ }
+
+ if (INET_ECN_set_ce(skb)) {
+ q->stats.forced_mark++;
+ } else if (!red_use_nodrop(q)) {
q->stats.forced_drop++;
goto congestion_drop;
}
- q->stats.forced_mark++;
+ /* Non-ECT packet in ECN nodrop mode: queue it. */
break;
}
@@ -165,6 +189,7 @@ static int red_offload(struct Qdisc *sch, bool enable)
opt.set.limit = q->limit;
opt.set.is_ecn = red_use_ecn(q);
opt.set.is_harddrop = red_use_harddrop(q);
+ opt.set.is_nodrop = red_use_nodrop(q);
opt.set.qstats = &sch->qstats;
} else {
opt.command = TC_RED_DESTROY;
@@ -183,9 +208,12 @@ static void red_destroy(struct Qdisc *sch)
}
static const struct nla_policy red_policy[TCA_RED_MAX + 1] = {
+ [TCA_RED_UNSPEC] = { .strict_start_type = TCA_RED_FLAGS },
[TCA_RED_PARMS] = { .len = sizeof(struct tc_red_qopt) },
[TCA_RED_STAB] = { .len = RED_STAB_SIZE },
[TCA_RED_MAX_P] = { .type = NLA_U32 },
+ [TCA_RED_FLAGS] = { .type = NLA_BITFIELD32,
+ .validation_data = &red_supported_flags },
};
static int red_change(struct Qdisc *sch, struct nlattr *opt,
@@ -194,7 +222,10 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt,
struct Qdisc *old_child = NULL, *child = NULL;
struct red_sched_data *q = qdisc_priv(sch);
struct nlattr *tb[TCA_RED_MAX + 1];
+ struct nla_bitfield32 flags_bf;
struct tc_red_qopt *ctl;
+ unsigned char userbits;
+ unsigned char flags;
int err;
u32 max_P;
@@ -216,6 +247,12 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt,
if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog))
return -EINVAL;
+ err = red_get_flags(ctl->flags, TC_RED_HISTORIC_FLAGS,
+ tb[TCA_RED_FLAGS], red_supported_flags,
+ &flags_bf, &userbits, extack);
+ if (err)
+ return err;
+
if (ctl->limit > 0) {
child = fifo_create_dflt(sch, &bfifo_qdisc_ops, ctl->limit,
extack);
@@ -227,7 +264,14 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt,
}
sch_tree_lock(sch);
- q->flags = ctl->flags;
+
+ flags = (q->flags & ~flags_bf.selector) | flags_bf.value;
+ err = red_validate_flags(flags, extack);
+ if (err)
+ goto unlock_out;
+
+ q->flags = flags;
+ q->userbits = userbits;
q->limit = ctl->limit;
if (child) {
qdisc_tree_flush_backlog(q->qdisc);
@@ -256,6 +300,12 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt,
if (old_child)
qdisc_put(old_child);
return 0;
+
+unlock_out:
+ sch_tree_unlock(sch);
+ if (child)
+ qdisc_put(child);
+ return err;
}
static inline void red_adaptative_timer(struct timer_list *t)
@@ -302,7 +352,8 @@ static int red_dump(struct Qdisc *sch, struct sk_buff *skb)
struct nlattr *opts = NULL;
struct tc_red_qopt opt = {
.limit = q->limit,
- .flags = q->flags,
+ .flags = (q->flags & TC_RED_HISTORIC_FLAGS) |
+ q->userbits,
.qth_min = q->parms.qth_min >> q->parms.Wlog,
.qth_max = q->parms.qth_max >> q->parms.Wlog,
.Wlog = q->parms.Wlog,
@@ -319,7 +370,9 @@ static int red_dump(struct Qdisc *sch, struct sk_buff *skb)
if (opts == NULL)
goto nla_put_failure;
if (nla_put(skb, TCA_RED_PARMS, sizeof(opt), &opt) ||
- nla_put_u32(skb, TCA_RED_MAX_P, q->parms.max_P))
+ nla_put_u32(skb, TCA_RED_MAX_P, q->parms.max_P) ||
+ nla_put_bitfield32(skb, TCA_RED_FLAGS,
+ q->flags, red_supported_flags))
goto nla_put_failure;
return nla_nest_end(skb, opts);
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-11 07:52:26 +0000