summaryrefslogtreecommitdiff
path: root/net/sched
diff options
context:
space:
mode:
Diffstat (limited to 'net/sched')
-rw-r--r--net/sched/Kconfig4
-rw-r--r--net/sched/act_api.c2
-rw-r--r--net/sched/act_ct.c3
-rw-r--r--net/sched/cls_bpf.c99
-rw-r--r--net/sched/cls_flower.c149
-rw-r--r--net/sched/cls_fw.c11
-rw-r--r--net/sched/cls_matchall.c35
-rw-r--r--net/sched/cls_route.c1
-rw-r--r--net/sched/cls_u32.c105
-rw-r--r--net/sched/em_meta.c6
-rw-r--r--net/sched/sch_api.c53
-rw-r--r--net/sched/sch_drr.c11
-rw-r--r--net/sched/sch_hfsc.c14
-rw-r--r--net/sched/sch_htb.c17
-rw-r--r--net/sched/sch_ingress.c61
-rw-r--r--net/sched/sch_mqprio.c14
-rw-r--r--net/sched/sch_netem.c49
-rw-r--r--net/sched/sch_qfq.c30
-rw-r--r--net/sched/sch_taprio.c83
19 files changed, 498 insertions, 249 deletions
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index 4b95cb1ac435..470c70deffe2 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -347,8 +347,7 @@ config NET_SCH_FQ_PIE
config NET_SCH_INGRESS
tristate "Ingress/classifier-action Qdisc"
depends on NET_CLS_ACT
- select NET_INGRESS
- select NET_EGRESS
+ select NET_XGRESS
help
Say Y here if you want to use classifiers for incoming and/or outgoing
packets. This qdisc doesn't do anything else besides running classifiers,
@@ -679,6 +678,7 @@ config NET_EMATCH_IPT
config NET_CLS_ACT
bool "Actions"
select NET_CLS
+ select NET_XGRESS
help
Say Y here if you want to use traffic control actions. Actions
get attached to classifiers and are invoked after a successful
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index f7887f42d542..9d3f26bf0440 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -1320,7 +1320,7 @@ struct tc_action_ops *tc_action_load_ops(struct nlattr *nla, bool police,
return ERR_PTR(err);
}
} else {
- if (strlcpy(act_name, "police", IFNAMSIZ) >= IFNAMSIZ) {
+ if (strscpy(act_name, "police", IFNAMSIZ) < 0) {
NL_SET_ERR_MSG(extack, "TC action name too long");
return ERR_PTR(-EINVAL);
}
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index abc71a06d634..7c652d14528b 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -1238,7 +1238,8 @@ static int tcf_ct_fill_params(struct net *net,
}
}
- __set_bit(IPS_CONFIRMED_BIT, &tmpl->status);
+ if (p->ct_action & TCA_CT_ACT_COMMIT)
+ __set_bit(IPS_CONFIRMED_BIT, &tmpl->status);
return 0;
err:
nf_ct_put(p->tmpl);
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index 466c26df853a..382c7a71f81f 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -406,56 +406,6 @@ static int cls_bpf_prog_from_efd(struct nlattr **tb, struct cls_bpf_prog *prog,
return 0;
}
-static int cls_bpf_set_parms(struct net *net, struct tcf_proto *tp,
- struct cls_bpf_prog *prog, unsigned long base,
- struct nlattr **tb, struct nlattr *est, u32 flags,
- struct netlink_ext_ack *extack)
-{
- bool is_bpf, is_ebpf, have_exts = false;
- u32 gen_flags = 0;
- int ret;
-
- is_bpf = tb[TCA_BPF_OPS_LEN] && tb[TCA_BPF_OPS];
- is_ebpf = tb[TCA_BPF_FD];
- if ((!is_bpf && !is_ebpf) || (is_bpf && is_ebpf))
- return -EINVAL;
-
- ret = tcf_exts_validate(net, tp, tb, est, &prog->exts, flags,
- extack);
- if (ret < 0)
- return ret;
-
- if (tb[TCA_BPF_FLAGS]) {
- u32 bpf_flags = nla_get_u32(tb[TCA_BPF_FLAGS]);
-
- if (bpf_flags & ~TCA_BPF_FLAG_ACT_DIRECT)
- return -EINVAL;
-
- have_exts = bpf_flags & TCA_BPF_FLAG_ACT_DIRECT;
- }
- if (tb[TCA_BPF_FLAGS_GEN]) {
- gen_flags = nla_get_u32(tb[TCA_BPF_FLAGS_GEN]);
- if (gen_flags & ~CLS_BPF_SUPPORTED_GEN_FLAGS ||
- !tc_flags_valid(gen_flags))
- return -EINVAL;
- }
-
- prog->exts_integrated = have_exts;
- prog->gen_flags = gen_flags;
-
- ret = is_bpf ? cls_bpf_prog_from_ops(tb, prog) :
- cls_bpf_prog_from_efd(tb, prog, gen_flags, tp);
- if (ret < 0)
- return ret;
-
- if (tb[TCA_BPF_CLASSID]) {
- prog->res.classid = nla_get_u32(tb[TCA_BPF_CLASSID]);
- tcf_bind_filter(tp, &prog->res, base);
- }
-
- return 0;
-}
-
static int cls_bpf_change(struct net *net, struct sk_buff *in_skb,
struct tcf_proto *tp, unsigned long base,
u32 handle, struct nlattr **tca,
@@ -463,9 +413,12 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb,
struct netlink_ext_ack *extack)
{
struct cls_bpf_head *head = rtnl_dereference(tp->root);
+ bool is_bpf, is_ebpf, have_exts = false;
struct cls_bpf_prog *oldprog = *arg;
struct nlattr *tb[TCA_BPF_MAX + 1];
+ bool bound_to_filter = false;
struct cls_bpf_prog *prog;
+ u32 gen_flags = 0;
int ret;
if (tca[TCA_OPTIONS] == NULL)
@@ -504,11 +457,51 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb,
goto errout;
prog->handle = handle;
- ret = cls_bpf_set_parms(net, tp, prog, base, tb, tca[TCA_RATE], flags,
- extack);
+ is_bpf = tb[TCA_BPF_OPS_LEN] && tb[TCA_BPF_OPS];
+ is_ebpf = tb[TCA_BPF_FD];
+ if ((!is_bpf && !is_ebpf) || (is_bpf && is_ebpf)) {
+ ret = -EINVAL;
+ goto errout_idr;
+ }
+
+ ret = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &prog->exts,
+ flags, extack);
+ if (ret < 0)
+ goto errout_idr;
+
+ if (tb[TCA_BPF_FLAGS]) {
+ u32 bpf_flags = nla_get_u32(tb[TCA_BPF_FLAGS]);
+
+ if (bpf_flags & ~TCA_BPF_FLAG_ACT_DIRECT) {
+ ret = -EINVAL;
+ goto errout_idr;
+ }
+
+ have_exts = bpf_flags & TCA_BPF_FLAG_ACT_DIRECT;
+ }
+ if (tb[TCA_BPF_FLAGS_GEN]) {
+ gen_flags = nla_get_u32(tb[TCA_BPF_FLAGS_GEN]);
+ if (gen_flags & ~CLS_BPF_SUPPORTED_GEN_FLAGS ||
+ !tc_flags_valid(gen_flags)) {
+ ret = -EINVAL;
+ goto errout_idr;
+ }
+ }
+
+ prog->exts_integrated = have_exts;
+ prog->gen_flags = gen_flags;
+
+ ret = is_bpf ? cls_bpf_prog_from_ops(tb, prog) :
+ cls_bpf_prog_from_efd(tb, prog, gen_flags, tp);
if (ret < 0)
goto errout_idr;
+ if (tb[TCA_BPF_CLASSID]) {
+ prog->res.classid = nla_get_u32(tb[TCA_BPF_CLASSID]);
+ tcf_bind_filter(tp, &prog->res, base);
+ bound_to_filter = true;
+ }
+
ret = cls_bpf_offload(tp, prog, oldprog, extack);
if (ret)
goto errout_parms;
@@ -530,6 +523,8 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb,
return 0;
errout_parms:
+ if (bound_to_filter)
+ tcf_unbind_filter(tp, &prog->res);
cls_bpf_free_parms(prog);
errout_idr:
if (!oldprog)
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 56065cc5a661..e5314a31f75a 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -72,6 +72,7 @@ struct fl_flow_key {
struct flow_dissector_key_num_of_vlans num_of_vlans;
struct flow_dissector_key_pppoe pppoe;
struct flow_dissector_key_l2tpv3 l2tpv3;
+ struct flow_dissector_key_ipsec ipsec;
struct flow_dissector_key_cfm cfm;
} __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */
@@ -726,6 +727,8 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = {
[TCA_FLOWER_KEY_PPPOE_SID] = { .type = NLA_U16 },
[TCA_FLOWER_KEY_PPP_PROTO] = { .type = NLA_U16 },
[TCA_FLOWER_KEY_L2TPV3_SID] = { .type = NLA_U32 },
+ [TCA_FLOWER_KEY_SPI] = { .type = NLA_U32 },
+ [TCA_FLOWER_KEY_SPI_MASK] = { .type = NLA_U32 },
[TCA_FLOWER_L2_MISS] = NLA_POLICY_MAX(NLA_U8, 1),
[TCA_FLOWER_KEY_CFM] = { .type = NLA_NESTED },
};
@@ -776,7 +779,8 @@ mpls_stack_entry_policy[TCA_FLOWER_KEY_MPLS_OPT_LSE_MAX + 1] = {
[TCA_FLOWER_KEY_MPLS_OPT_LSE_LABEL] = { .type = NLA_U32 },
};
-static const struct nla_policy cfm_opt_policy[TCA_FLOWER_KEY_CFM_OPT_MAX] = {
+static const struct nla_policy
+cfm_opt_policy[TCA_FLOWER_KEY_CFM_OPT_MAX + 1] = {
[TCA_FLOWER_KEY_CFM_MD_LEVEL] = NLA_POLICY_MAX(NLA_U8,
FLOW_DIS_CFM_MDL_MAX),
[TCA_FLOWER_KEY_CFM_OPCODE] = { .type = NLA_U8 },
@@ -795,6 +799,24 @@ static void fl_set_key_val(struct nlattr **tb,
nla_memcpy(mask, tb[mask_type], len);
}
+static int fl_set_key_spi(struct nlattr **tb, struct fl_flow_key *key,
+ struct fl_flow_key *mask,
+ struct netlink_ext_ack *extack)
+{
+ if (key->basic.ip_proto != IPPROTO_ESP &&
+ key->basic.ip_proto != IPPROTO_AH) {
+ NL_SET_ERR_MSG(extack,
+ "Protocol must be either ESP or AH");
+ return -EINVAL;
+ }
+
+ fl_set_key_val(tb, &key->ipsec.spi,
+ TCA_FLOWER_KEY_SPI,
+ &mask->ipsec.spi, TCA_FLOWER_KEY_SPI_MASK,
+ sizeof(key->ipsec.spi));
+ return 0;
+}
+
static int fl_set_key_port_range(struct nlattr **tb, struct fl_flow_key *key,
struct fl_flow_key *mask,
struct netlink_ext_ack *extack)
@@ -812,6 +834,16 @@ 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) {
+ NL_SET_ERR_MSG(extack,
+ "Both min and max destination ports must be specified");
+ return -EINVAL;
+ }
+ if (mask->tp_range.tp_min.src != mask->tp_range.tp_max.src) {
+ NL_SET_ERR_MSG(extack,
+ "Both min and max source ports must be specified");
+ return -EINVAL;
+ }
if (mask->tp_range.tp_min.dst && mask->tp_range.tp_max.dst &&
ntohs(key->tp_range.tp_max.dst) <=
ntohs(key->tp_range.tp_min.dst)) {
@@ -1699,7 +1731,7 @@ static int fl_set_key_cfm(struct nlattr **tb,
struct fl_flow_key *mask,
struct netlink_ext_ack *extack)
{
- struct nlattr *nla_cfm_opt[TCA_FLOWER_KEY_CFM_OPT_MAX];
+ struct nlattr *nla_cfm_opt[TCA_FLOWER_KEY_CFM_OPT_MAX + 1];
int err;
if (!tb[TCA_FLOWER_KEY_CFM])
@@ -1884,6 +1916,12 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
return ret;
}
+ if (tb[TCA_FLOWER_KEY_SPI]) {
+ ret = fl_set_key_spi(tb, key, mask, extack);
+ if (ret)
+ return ret;
+ }
+
if (tb[TCA_FLOWER_KEY_ENC_IPV4_SRC] ||
tb[TCA_FLOWER_KEY_ENC_IPV4_DST]) {
key->enc_control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
@@ -2057,6 +2095,8 @@ static void fl_init_dissector(struct flow_dissector *dissector,
FL_KEY_SET_IF_MASKED(mask, keys, cnt,
FLOW_DISSECTOR_KEY_L2TPV3, l2tpv3);
FL_KEY_SET_IF_MASKED(mask, keys, cnt,
+ FLOW_DISSECTOR_KEY_IPSEC, ipsec);
+ FL_KEY_SET_IF_MASKED(mask, keys, cnt,
FLOW_DISSECTOR_KEY_CFM, cfm);
skb_flow_dissector_init(dissector, keys, cnt);
@@ -2163,53 +2203,6 @@ static bool fl_needs_tc_skb_ext(const struct fl_flow_key *mask)
return mask->meta.l2_miss;
}
-static int fl_set_parms(struct net *net, struct tcf_proto *tp,
- struct cls_fl_filter *f, struct fl_flow_mask *mask,
- unsigned long base, struct nlattr **tb,
- struct nlattr *est,
- struct fl_flow_tmplt *tmplt,
- u32 flags, u32 fl_flags,
- struct netlink_ext_ack *extack)
-{
- int err;
-
- err = tcf_exts_validate_ex(net, tp, tb, est, &f->exts, flags,
- fl_flags, extack);
- if (err < 0)
- return err;
-
- if (tb[TCA_FLOWER_CLASSID]) {
- f->res.classid = nla_get_u32(tb[TCA_FLOWER_CLASSID]);
- if (flags & TCA_ACT_FLAGS_NO_RTNL)
- rtnl_lock();
- tcf_bind_filter(tp, &f->res, base);
- if (flags & TCA_ACT_FLAGS_NO_RTNL)
- rtnl_unlock();
- }
-
- err = fl_set_key(net, tb, &f->key, &mask->key, extack);
- if (err)
- return err;
-
- fl_mask_update_range(mask);
- fl_set_masked_key(&f->mkey, &f->key, mask);
-
- if (!fl_mask_fits_tmplt(tmplt, mask)) {
- NL_SET_ERR_MSG_MOD(extack, "Mask does not fit the template");
- return -EINVAL;
- }
-
- /* Enable tc skb extension if filter matches on data extracted from
- * this extension.
- */
- if (fl_needs_tc_skb_ext(&mask->key)) {
- f->needs_tc_skb_ext = 1;
- tc_skb_ext_tc_enable();
- }
-
- return 0;
-}
-
static int fl_ht_insert_unique(struct cls_fl_filter *fnew,
struct cls_fl_filter *fold,
bool *in_ht)
@@ -2241,6 +2234,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
struct cls_fl_head *head = fl_head_dereference(tp);
bool rtnl_held = !(flags & TCA_ACT_FLAGS_NO_RTNL);
struct cls_fl_filter *fold = *arg;
+ bool bound_to_filter = false;
struct cls_fl_filter *fnew;
struct fl_flow_mask *mask;
struct nlattr **tb;
@@ -2325,15 +2319,46 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
if (err < 0)
goto errout_idr;
- err = fl_set_parms(net, tp, fnew, mask, base, tb, tca[TCA_RATE],
- tp->chain->tmplt_priv, flags, fnew->flags,
- extack);
- if (err)
+ err = tcf_exts_validate_ex(net, tp, tb, tca[TCA_RATE],
+ &fnew->exts, flags, fnew->flags,
+ extack);
+ if (err < 0)
goto errout_idr;
+ if (tb[TCA_FLOWER_CLASSID]) {
+ fnew->res.classid = nla_get_u32(tb[TCA_FLOWER_CLASSID]);
+ if (flags & TCA_ACT_FLAGS_NO_RTNL)
+ rtnl_lock();
+ tcf_bind_filter(tp, &fnew->res, base);
+ if (flags & TCA_ACT_FLAGS_NO_RTNL)
+ rtnl_unlock();
+ bound_to_filter = true;
+ }
+
+ err = fl_set_key(net, tb, &fnew->key, &mask->key, extack);
+ if (err)
+ goto unbind_filter;
+
+ fl_mask_update_range(mask);
+ fl_set_masked_key(&fnew->mkey, &fnew->key, mask);
+
+ if (!fl_mask_fits_tmplt(tp->chain->tmplt_priv, mask)) {
+ NL_SET_ERR_MSG_MOD(extack, "Mask does not fit the template");
+ err = -EINVAL;
+ goto unbind_filter;
+ }
+
+ /* Enable tc skb extension if filter matches on data extracted from
+ * this extension.
+ */
+ if (fl_needs_tc_skb_ext(&mask->key)) {
+ fnew->needs_tc_skb_ext = 1;
+ tc_skb_ext_tc_enable();
+ }
+
err = fl_check_assign_mask(head, fnew, fold, mask);
if (err)
- goto errout_idr;
+ goto unbind_filter;
err = fl_ht_insert_unique(fnew, fold, &in_ht);
if (err)
@@ -2424,6 +2449,16 @@ errout_hw:
fnew->mask->filter_ht_params);
errout_mask:
fl_mask_put(head, fnew->mask);
+
+unbind_filter:
+ if (bound_to_filter) {
+ if (flags & TCA_ACT_FLAGS_NO_RTNL)
+ rtnl_lock();
+ tcf_unbind_filter(tp, &fnew->res);
+ if (flags & TCA_ACT_FLAGS_NO_RTNL)
+ rtnl_unlock();
+ }
+
errout_idr:
if (!fold)
idr_remove(&head->handle_idr, fnew->handle);
@@ -3359,6 +3394,12 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net,
sizeof(key->l2tpv3.session_id)))
goto nla_put_failure;
+ if (key->ipsec.spi &&
+ fl_dump_key_val(skb, &key->ipsec.spi, TCA_FLOWER_KEY_SPI,
+ &mask->ipsec.spi, TCA_FLOWER_KEY_SPI_MASK,
+ sizeof(key->ipsec.spi)))
+ goto nla_put_failure;
+
if ((key->basic.ip_proto == IPPROTO_TCP ||
key->basic.ip_proto == IPPROTO_UDP ||
key->basic.ip_proto == IPPROTO_SCTP) &&
diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c
index ae9439a6c56c..c49d6af0e048 100644
--- a/net/sched/cls_fw.c
+++ b/net/sched/cls_fw.c
@@ -212,11 +212,6 @@ static int fw_set_parms(struct net *net, struct tcf_proto *tp,
if (err < 0)
return err;
- if (tb[TCA_FW_CLASSID]) {
- f->res.classid = nla_get_u32(tb[TCA_FW_CLASSID]);
- tcf_bind_filter(tp, &f->res, base);
- }
-
if (tb[TCA_FW_INDEV]) {
int ret;
ret = tcf_change_indev(net, tb[TCA_FW_INDEV], extack);
@@ -233,6 +228,11 @@ static int fw_set_parms(struct net *net, struct tcf_proto *tp,
} else if (head->mask != 0xFFFFFFFF)
return err;
+ if (tb[TCA_FW_CLASSID]) {
+ f->res.classid = nla_get_u32(tb[TCA_FW_CLASSID]);
+ tcf_bind_filter(tp, &f->res, base);
+ }
+
return 0;
}
@@ -267,7 +267,6 @@ static int fw_change(struct net *net, struct sk_buff *in_skb,
return -ENOBUFS;
fnew->id = f->id;
- fnew->res = f->res;
fnew->ifindex = f->ifindex;
fnew->tp = f->tp;
diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index fa3bbd187eb9..c4ed11df6254 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -159,26 +159,6 @@ static const struct nla_policy mall_policy[TCA_MATCHALL_MAX + 1] = {
[TCA_MATCHALL_FLAGS] = { .type = NLA_U32 },
};
-static int mall_set_parms(struct net *net, struct tcf_proto *tp,
- struct cls_mall_head *head,
- unsigned long base, struct nlattr **tb,
- struct nlattr *est, u32 flags, u32 fl_flags,
- struct netlink_ext_ack *extack)
-{
- int err;
-
- err = tcf_exts_validate_ex(net, tp, tb, est, &head->exts, flags,
- fl_flags, extack);
- if (err < 0)
- return err;
-
- if (tb[TCA_MATCHALL_CLASSID]) {
- head->res.classid = nla_get_u32(tb[TCA_MATCHALL_CLASSID]);
- tcf_bind_filter(tp, &head->res, base);
- }
- return 0;
-}
-
static int mall_change(struct net *net, struct sk_buff *in_skb,
struct tcf_proto *tp, unsigned long base,
u32 handle, struct nlattr **tca,
@@ -187,6 +167,7 @@ static int mall_change(struct net *net, struct sk_buff *in_skb,
{
struct cls_mall_head *head = rtnl_dereference(tp->root);
struct nlattr *tb[TCA_MATCHALL_MAX + 1];
+ bool bound_to_filter = false;
struct cls_mall_head *new;
u32 userflags = 0;
int err;
@@ -226,11 +207,17 @@ static int mall_change(struct net *net, struct sk_buff *in_skb,
goto err_alloc_percpu;
}
- err = mall_set_parms(net, tp, new, base, tb, tca[TCA_RATE],
- flags, new->flags, extack);
- if (err)
+ err = tcf_exts_validate_ex(net, tp, tb, tca[TCA_RATE],
+ &new->exts, flags, new->flags, extack);
+ if (err < 0)
goto err_set_parms;
+ if (tb[TCA_MATCHALL_CLASSID]) {
+ new->res.classid = nla_get_u32(tb[TCA_MATCHALL_CLASSID]);
+ tcf_bind_filter(tp, &new->res, base);
+ bound_to_filter = true;
+ }
+
if (!tc_skip_hw(new->flags)) {
err = mall_replace_hw_filter(tp, new, (unsigned long)new,
extack);
@@ -246,6 +233,8 @@ static int mall_change(struct net *net, struct sk_buff *in_skb,
return 0;
err_replace_hw_filter:
+ if (bound_to_filter)
+ tcf_unbind_filter(tp, &new->res);
err_set_parms:
free_percpu(new->pf);
err_alloc_percpu:
diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c
index d0c53724d3e8..1e20bbd687f1 100644
--- a/net/sched/cls_route.c
+++ b/net/sched/cls_route.c
@@ -513,7 +513,6 @@ static int route4_change(struct net *net, struct sk_buff *in_skb,
if (fold) {
f->id = fold->id;
f->iif = fold->iif;
- f->res = fold->res;
f->handle = fold->handle;
f->tp = fold->tp;
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index d15d50de7980..da4c179a4d41 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -712,8 +712,23 @@ static const struct nla_policy u32_policy[TCA_U32_MAX + 1] = {
[TCA_U32_FLAGS] = { .type = NLA_U32 },
};
+static void u32_unbind_filter(struct tcf_proto *tp, struct tc_u_knode *n,
+ struct nlattr **tb)
+{
+ if (tb[TCA_U32_CLASSID])
+ tcf_unbind_filter(tp, &n->res);
+}
+
+static void u32_bind_filter(struct tcf_proto *tp, struct tc_u_knode *n,
+ unsigned long base, struct nlattr **tb)
+{
+ if (tb[TCA_U32_CLASSID]) {
+ n->res.classid = nla_get_u32(tb[TCA_U32_CLASSID]);
+ tcf_bind_filter(tp, &n->res, base);
+ }
+}
+
static int u32_set_parms(struct net *net, struct tcf_proto *tp,
- unsigned long base,
struct tc_u_knode *n, struct nlattr **tb,
struct nlattr *est, u32 flags, u32 fl_flags,
struct netlink_ext_ack *extack)
@@ -760,10 +775,6 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp,
if (ht_old)
ht_old->refcnt--;
}
- if (tb[TCA_U32_CLASSID]) {
- n->res.classid = nla_get_u32(tb[TCA_U32_CLASSID]);
- tcf_bind_filter(tp, &n->res, base);
- }
if (ifindex >= 0)
n->ifindex = ifindex;
@@ -815,7 +826,6 @@ static struct tc_u_knode *u32_init_knode(struct net *net, struct tcf_proto *tp,
new->ifindex = n->ifindex;
new->fshift = n->fshift;
- new->res = n->res;
new->flags = n->flags;
RCU_INIT_POINTER(new->ht_down, ht);
@@ -903,17 +913,27 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
if (!new)
return -ENOMEM;
- err = u32_set_parms(net, tp, base, new, tb,
- tca[TCA_RATE], flags, new->flags,
- extack);
+ err = u32_set_parms(net, tp, new, tb, tca[TCA_RATE],
+ flags, new->flags, extack);
if (err) {
__u32_destroy_key(new);
return err;
}
+ u32_bind_filter(tp, new, base, tb);
+
err = u32_replace_hw_knode(tp, new, flags, extack);
if (err) {
+ u32_unbind_filter(tp, new, tb);
+
+ if (tb[TCA_U32_LINK]) {
+ struct tc_u_hnode *ht_old;
+
+ ht_old = rtnl_dereference(n->ht_down);
+ if (ht_old)
+ ht_old->refcnt++;
+ }
__u32_destroy_key(new);
return err;
}
@@ -1003,18 +1023,62 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
return -EINVAL;
}
+ /* At this point, we need to derive the new handle that will be used to
+ * uniquely map the identity of this table match entry. The
+ * identity of the entry that we need to construct is 32 bits made of:
+ * htid(12b):bucketid(8b):node/entryid(12b)
+ *
+ * At this point _we have the table(ht)_ in which we will insert this
+ * entry. We carry the table's id in variable "htid".
+ * Note that earlier code picked the ht selection either by a) the user
+ * providing the htid specified via TCA_U32_HASH attribute or b) when
+ * no such attribute is passed then the root ht, is default to at ID
+ * 0x[800][00][000]. Rule: the root table has a single bucket with ID 0.
+ * If OTOH the user passed us the htid, they may also pass a bucketid of
+ * choice. 0 is fine. For example a user htid is 0x[600][01][000] it is
+ * indicating hash bucketid of 1. Rule: the entry/node ID _cannot_ be
+ * passed via the htid, so even if it was non-zero it will be ignored.
+ *
+ * We may also have a handle, if the user passed one. The handle also
+ * carries the same addressing of htid(12b):bucketid(8b):node/entryid(12b).
+ * Rule: the bucketid on the handle is ignored even if one was passed;
+ * rather the value on "htid" is always assumed to be the bucketid.
+ */
if (handle) {
+ /* Rule: The htid from handle and tableid from htid must match */
if (TC_U32_HTID(handle) && TC_U32_HTID(handle ^ htid)) {
NL_SET_ERR_MSG_MOD(extack, "Handle specified hash table address mismatch");
return -EINVAL;
}
- handle = htid | TC_U32_NODE(handle);
- err = idr_alloc_u32(&ht->handle_idr, NULL, &handle, handle,
- GFP_KERNEL);
- if (err)
- return err;
- } else
+ /* Ok, so far we have a valid htid(12b):bucketid(8b) but we
+ * need to finalize the table entry identification with the last
+ * part - the node/entryid(12b)). Rule: Nodeid _cannot be 0_ for
+ * entries. Rule: nodeid of 0 is reserved only for tables(see
+ * earlier code which processes TC_U32_DIVISOR attribute).
+ * Rule: The nodeid can only be derived from the handle (and not
+ * htid).
+ * Rule: if the handle specified zero for the node id example
+ * 0x60000000, then pick a new nodeid from the pool of IDs
+ * this hash table has been allocating from.
+ * If OTOH it is specified (i.e for example the user passed a
+ * handle such as 0x60000123), then we use it generate our final
+ * handle which is used to uniquely identify the match entry.
+ */
+ if (!TC_U32_NODE(handle)) {
+ handle = gen_new_kid(ht, htid);
+ } else {
+ handle = htid | TC_U32_NODE(handle);
+ err = idr_alloc_u32(&ht->handle_idr, NULL, &handle,
+ handle, GFP_KERNEL);
+ if (err)
+ return err;
+ }
+ } else {
+ /* The user did not give us a handle; lets just generate one
+ * from the table's pool of nodeids.
+ */
handle = gen_new_kid(ht, htid);
+ }
if (tb[TCA_U32_SEL] == NULL) {
NL_SET_ERR_MSG_MOD(extack, "Selector not specified");
@@ -1074,15 +1138,18 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
}
#endif
- err = u32_set_parms(net, tp, base, n, tb, tca[TCA_RATE],
+ err = u32_set_parms(net, tp, n, tb, tca[TCA_RATE],
flags, n->flags, extack);
+
+ u32_bind_filter(tp, n, base, tb);
+
if (err == 0) {
struct tc_u_knode __rcu **ins;
struct tc_u_knode *pins;
err = u32_replace_hw_knode(tp, n, flags, extack);
if (err)
- goto errhw;
+ goto errunbind;
if (!tc_in_hw(n->flags))
n->flags |= TCA_CLS_FLAGS_NOT_IN_HW;
@@ -1100,7 +1167,9 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
return 0;
}
-errhw:
+errunbind:
+ u32_unbind_filter(tp, n, tb);
+
#ifdef CONFIG_CLS_U32_MARK
free_percpu(n->pcpu_success);
#endif
diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c
index af85a73c4c54..da34fd4c9269 100644
--- a/net/sched/em_meta.c
+++ b/net/sched/em_meta.c
@@ -502,7 +502,7 @@ META_COLLECTOR(int_sk_lingertime)
*err = -1;
return;
}
- dst->value = sk->sk_lingertime / HZ;
+ dst->value = READ_ONCE(sk->sk_lingertime) / HZ;
}
META_COLLECTOR(int_sk_err_qlen)
@@ -568,7 +568,7 @@ META_COLLECTOR(int_sk_rcvtimeo)
*err = -1;
return;
}
- dst->value = sk->sk_rcvtimeo / HZ;
+ dst->value = READ_ONCE(sk->sk_rcvtimeo) / HZ;
}
META_COLLECTOR(int_sk_sndtimeo)
@@ -579,7 +579,7 @@ META_COLLECTOR(int_sk_sndtimeo)
*err = -1;
return;
}
- dst->value = sk->sk_sndtimeo / HZ;
+ dst->value = READ_ONCE(sk->sk_sndtimeo) / HZ;
}
META_COLLECTOR(int_sk_sendmsg_off)
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index aa6b1fe65151..e9eaf637220e 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1547,10 +1547,28 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n,
return 0;
}
+static bool req_create_or_replace(struct nlmsghdr *n)
+{
+ return (n->nlmsg_flags & NLM_F_CREATE &&
+ n->nlmsg_flags & NLM_F_REPLACE);
+}
+
+static bool req_create_exclusive(struct nlmsghdr *n)
+{
+ return (n->nlmsg_flags & NLM_F_CREATE &&
+ n->nlmsg_flags & NLM_F_EXCL);
+}
+
+static bool req_change(struct nlmsghdr *n)
+{
+ return (!(n->nlmsg_flags & NLM_F_CREATE) &&
+ !(n->nlmsg_flags & NLM_F_REPLACE) &&
+ !(n->nlmsg_flags & NLM_F_EXCL));
+}
+
/*
* Create/change qdisc.
*/
-
static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n,
struct netlink_ext_ack *extack)
{
@@ -1644,27 +1662,35 @@ replay:
*
* We know, that some child q is already
* attached to this parent and have choice:
- * either to change it or to create/graft new one.
+ * 1) change it or 2) create/graft new one.
+ * If the requested qdisc kind is different
+ * than the existing one, then we choose graft.
+ * If they are the same then this is "change"
+ * operation - just let it fallthrough..
*
* 1. We are allowed to create/graft only
- * if CREATE and REPLACE flags are set.
+ * if the request is explicitly stating
+ * "please create if it doesn't exist".
*
- * 2. If EXCL is set, requestor wanted to say,
- * that qdisc tcm_handle is not expected
+ * 2. If the request is to exclusive create
+ * then the qdisc tcm_handle is not expected
* to exist, so that we choose create/graft too.
*
* 3. The last case is when no flags are set.
+ * This will happen when for example tc
+ * utility issues a "change" command.
* Alas, it is sort of hole in API, we
* cannot decide what to do unambiguously.
- * For now we select create/graft, if
- * user gave KIND, which does not match existing.
+ * For now we select create/graft.
*/
- if ((n->nlmsg_flags & NLM_F_CREATE) &&
- (n->nlmsg_flags & NLM_F_REPLACE) &&
- ((n->nlmsg_flags & NLM_F_EXCL) ||
- (tca[TCA_KIND] &&
- nla_strcmp(tca[TCA_KIND], q->ops->id))))
- goto create_n_graft;
+ if (tca[TCA_KIND] &&
+ nla_strcmp(tca[TCA_KIND], q->ops->id)) {
+ if (req_create_or_replace(n) ||
+ req_create_exclusive(n))
+ goto create_n_graft;
+ else if (req_change(n))
+ goto create_n_graft2;
+ }
}
}
} else {
@@ -1698,6 +1724,7 @@ create_n_graft:
NL_SET_ERR_MSG(extack, "Qdisc not found. To create specify NLM_F_CREATE flag");
return -ENOENT;
}
+create_n_graft2:
if (clid == TC_H_INGRESS) {
if (dev_ingress_queue(dev)) {
q = qdisc_create(dev, dev_ingress_queue(dev),
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index e35a4e90f4e6..19901e77cd3b 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -17,7 +17,6 @@
struct drr_class {
struct Qdisc_class_common common;
- unsigned int filter_cnt;
struct gnet_stats_basic_sync bstats;
struct gnet_stats_queue qstats;
@@ -150,8 +149,10 @@ static int drr_delete_class(struct Qdisc *sch, unsigned long arg,
struct drr_sched *q = qdisc_priv(sch);
struct drr_class *cl = (struct drr_class *)arg;
- if (cl->filter_cnt > 0)
+ if (qdisc_class_in_use(&cl->common)) {
+ NL_SET_ERR_MSG(extack, "DRR class is in use");
return -EBUSY;
+ }
sch_tree_lock(sch);
@@ -187,8 +188,8 @@ static unsigned long drr_bind_tcf(struct Qdisc *sch, unsigned long parent,
{
struct drr_class *cl = drr_find_class(sch, classid);
- if (cl != NULL)
- cl->filter_cnt++;
+ if (cl)
+ qdisc_class_get(&cl->common);
return (unsigned long)cl;
}
@@ -197,7 +198,7 @@ static void drr_unbind_tcf(struct Qdisc *sch, unsigned long arg)
{
struct drr_class *cl = (struct drr_class *)arg;
- cl->filter_cnt--;
+ qdisc_class_put(&cl->common);
}
static int drr_graft_class(struct Qdisc *sch, unsigned long arg,
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index 70b0c5873d32..3554085bc2be 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -116,7 +116,6 @@ struct hfsc_class {
struct net_rate_estimator __rcu *rate_est;
struct tcf_proto __rcu *filter_list; /* filter list */
struct tcf_block *block;
- unsigned int filter_cnt; /* filter count */
unsigned int level; /* class level in hierarchy */
struct hfsc_sched *sched; /* scheduler data */
@@ -1012,6 +1011,10 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
if (parent == NULL)
return -ENOENT;
}
+ if (!(parent->cl_flags & HFSC_FSC) && parent != &q->root) {
+ NL_SET_ERR_MSG(extack, "Invalid parent - parent class must have FSC");
+ return -EINVAL;
+ }
if (classid == 0 || TC_H_MAJ(classid ^ sch->handle) != 0)
return -EINVAL;
@@ -1094,8 +1097,11 @@ hfsc_delete_class(struct Qdisc *sch, unsigned long arg,
struct hfsc_sched *q = qdisc_priv(sch);
struct hfsc_class *cl = (struct hfsc_class *)arg;
- if (cl->level > 0 || cl->filter_cnt > 0 || cl == &q->root)
+ if (cl->level > 0 || qdisc_class_in_use(&cl->cl_common) ||
+ cl == &q->root) {
+ NL_SET_ERR_MSG(extack, "HFSC class in use");
return -EBUSY;
+ }
sch_tree_lock(sch);
@@ -1223,7 +1229,7 @@ hfsc_bind_tcf(struct Qdisc *sch, unsigned long parent, u32 classid)
if (cl != NULL) {
if (p != NULL && p->level <= cl->level)
return 0;
- cl->filter_cnt++;
+ qdisc_class_get(&cl->cl_common);
}
return (unsigned long)cl;
@@ -1234,7 +1240,7 @@ hfsc_unbind_tcf(struct Qdisc *sch, unsigned long arg)
{
struct hfsc_class *cl = (struct hfsc_class *)arg;
- cl->filter_cnt--;
+ qdisc_class_put(&cl->cl_common);
}
static struct tcf_block *hfsc_tcf_block(struct Qdisc *sch, unsigned long arg,
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 325c29041c7d..0d947414e616 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -102,7 +102,6 @@ struct htb_class {
struct tcf_proto __rcu *filter_list; /* class attached filters */
struct tcf_block *block;
- int filter_cnt;
int level; /* our level (see above) */
unsigned int children;
@@ -1710,8 +1709,10 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg,
* tc subsys guarantee us that in htb_destroy it holds no class
* refs so that we can remove children safely there ?
*/
- if (cl->children || cl->filter_cnt)
+ if (cl->children || qdisc_class_in_use(&cl->common)) {
+ NL_SET_ERR_MSG(extack, "HTB class in use");
return -EBUSY;
+ }
if (!cl->level && htb_parent_last_child(cl))
last_child = 1;
@@ -1810,10 +1811,6 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
NL_SET_ERR_MSG(extack, "HTB offload doesn't support the mpu parameter");
goto failure;
}
- if (hopt->quantum) {
- NL_SET_ERR_MSG(extack, "HTB offload doesn't support the quantum parameter");
- goto failure;
- }
}
/* Keeping backward compatible with rate_table based iproute2 tc */
@@ -1910,6 +1907,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
.rate = max_t(u64, hopt->rate.rate, rate64),
.ceil = max_t(u64, hopt->ceil.rate, ceil64),
.prio = hopt->prio,
+ .quantum = hopt->quantum,
.extack = extack,
};
err = htb_offload(dev, &offload_opt);
@@ -1931,6 +1929,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
.rate = max_t(u64, hopt->rate.rate, rate64),
.ceil = max_t(u64, hopt->ceil.rate, ceil64),
.prio = hopt->prio,
+ .quantum = hopt->quantum,
.extack = extack,
};
err = htb_offload(dev, &offload_opt);
@@ -2017,6 +2016,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
.rate = max_t(u64, hopt->rate.rate, rate64),
.ceil = max_t(u64, hopt->ceil.rate, ceil64),
.prio = hopt->prio,
+ .quantum = hopt->quantum,
.extack = extack,
};
err = htb_offload(dev, &offload_opt);
@@ -2108,7 +2108,7 @@ static unsigned long htb_bind_filter(struct Qdisc *sch, unsigned long parent,
* be broken by class during destroy IIUC.
*/
if (cl)
- cl->filter_cnt++;
+ qdisc_class_get(&cl->common);
return (unsigned long)cl;
}
@@ -2116,8 +2116,7 @@ static void htb_unbind_filter(struct Qdisc *sch, unsigned long arg)
{
struct htb_class *cl = (struct htb_class *)arg;
- if (cl)
- cl->filter_cnt--;
+ qdisc_class_put(&cl->common);
}
static void htb_walk(struct Qdisc *sch, struct qdisc_walker *arg)
diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c
index e43a45499372..a463a63192c3 100644
--- a/net/sched/sch_ingress.c
+++ b/net/sched/sch_ingress.c
@@ -13,6 +13,7 @@
#include <net/netlink.h>
#include <net/pkt_sched.h>
#include <net/pkt_cls.h>
+#include <net/tcx.h>
struct ingress_sched_data {
struct tcf_block *block;
@@ -78,6 +79,8 @@ 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);
+ struct bpf_mprog_entry *entry;
+ bool created;
int err;
if (sch->parent != TC_H_INGRESS)
@@ -85,7 +88,13 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt,
net_inc_ingress_queue();
- mini_qdisc_pair_init(&q->miniqp, sch, &dev->miniq_ingress);
+ entry = tcx_entry_fetch_or_create(dev, true, &created);
+ if (!entry)
+ return -ENOMEM;
+ tcx_miniq_set_active(entry, true);
+ mini_qdisc_pair_init(&q->miniqp, sch, &tcx_entry(entry)->miniq);
+ if (created)
+ tcx_entry_update(dev, entry, true);
q->block_info.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS;
q->block_info.chain_head_change = clsact_chain_head_change;
@@ -103,11 +112,22 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt,
static void ingress_destroy(struct Qdisc *sch)
{
struct ingress_sched_data *q = qdisc_priv(sch);
+ struct net_device *dev = qdisc_dev(sch);
+ struct bpf_mprog_entry *entry = rtnl_dereference(dev->tcx_ingress);
if (sch->parent != TC_H_INGRESS)
return;
tcf_block_put_ext(q->block, sch, &q->block_info);
+
+ if (entry) {
+ tcx_miniq_set_active(entry, false);
+ if (!tcx_entry_is_active(entry)) {
+ tcx_entry_update(dev, NULL, true);
+ tcx_entry_free(entry);
+ }
+ }
+
net_dec_ingress_queue();
}
@@ -223,6 +243,8 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt,
{
struct clsact_sched_data *q = qdisc_priv(sch);
struct net_device *dev = qdisc_dev(sch);
+ struct bpf_mprog_entry *entry;
+ bool created;
int err;
if (sch->parent != TC_H_CLSACT)
@@ -231,7 +253,13 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt,
net_inc_ingress_queue();
net_inc_egress_queue();
- mini_qdisc_pair_init(&q->miniqp_ingress, sch, &dev->miniq_ingress);
+ entry = tcx_entry_fetch_or_create(dev, true, &created);
+ if (!entry)
+ return -ENOMEM;
+ tcx_miniq_set_active(entry, true);
+ mini_qdisc_pair_init(&q->miniqp_ingress, sch, &tcx_entry(entry)->miniq);
+ if (created)
+ tcx_entry_update(dev, entry, true);
q->ingress_block_info.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS;
q->ingress_block_info.chain_head_change = clsact_chain_head_change;
@@ -244,7 +272,13 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt,
mini_qdisc_pair_block_init(&q->miniqp_ingress, q->ingress_block);
- mini_qdisc_pair_init(&q->miniqp_egress, sch, &dev->miniq_egress);
+ entry = tcx_entry_fetch_or_create(dev, false, &created);
+ if (!entry)
+ return -ENOMEM;
+ tcx_miniq_set_active(entry, true);
+ mini_qdisc_pair_init(&q->miniqp_egress, sch, &tcx_entry(entry)->miniq);
+ if (created)
+ tcx_entry_update(dev, entry, false);
q->egress_block_info.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS;
q->egress_block_info.chain_head_change = clsact_chain_head_change;
@@ -256,12 +290,31 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt,
static void clsact_destroy(struct Qdisc *sch)
{
struct clsact_sched_data *q = qdisc_priv(sch);
+ struct net_device *dev = qdisc_dev(sch);
+ struct bpf_mprog_entry *ingress_entry = rtnl_dereference(dev->tcx_ingress);
+ struct bpf_mprog_entry *egress_entry = rtnl_dereference(dev->tcx_egress);
if (sch->parent != TC_H_CLSACT)
return;
- tcf_block_put_ext(q->egress_block, sch, &q->egress_block_info);
tcf_block_put_ext(q->ingress_block, sch, &q->ingress_block_info);
+ tcf_block_put_ext(q->egress_block, sch, &q->egress_block_info);
+
+ if (ingress_entry) {
+ tcx_miniq_set_active(ingress_entry, false);
+ if (!tcx_entry_is_active(ingress_entry)) {
+ tcx_entry_update(dev, NULL, true);
+ tcx_entry_free(ingress_entry);
+ }
+ }
+
+ if (egress_entry) {
+ tcx_miniq_set_active(egress_entry, false);
+ if (!tcx_entry_is_active(egress_entry)) {
+ tcx_entry_update(dev, NULL, false);
+ tcx_entry_free(egress_entry);
+ }
+ }
net_dec_ingress_queue();
net_dec_egress_queue();
diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index ab69ff7577fc..793009f445c0 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -290,6 +290,13 @@ static int mqprio_parse_nlattr(struct Qdisc *sch, struct tc_mqprio_qopt *qopt,
"Attribute type expected to be TCA_MQPRIO_MIN_RATE64");
return -EINVAL;
}
+
+ if (nla_len(attr) != sizeof(u64)) {
+ NL_SET_ERR_MSG_ATTR(extack, attr,
+ "Attribute TCA_MQPRIO_MIN_RATE64 expected to have 8 bytes length");
+ return -EINVAL;
+ }
+
if (i >= qopt->num_tc)
break;
priv->min_rate[i] = nla_get_u64(attr);
@@ -312,6 +319,13 @@ static int mqprio_parse_nlattr(struct Qdisc *sch, struct tc_mqprio_qopt *qopt,
"Attribute type expected to be TCA_MQPRIO_MAX_RATE64");
return -EINVAL;
}
+
+ if (nla_len(attr) != sizeof(u64)) {
+ NL_SET_ERR_MSG_ATTR(extack, attr,
+ "Attribute TCA_MQPRIO_MAX_RATE64 expected to have 8 bytes length");
+ return -EINVAL;
+ }
+
if (i >= qopt->num_tc)
break;
priv->max_rate[i] = nla_get_u64(attr);
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 38d9aa0cd30e..4ad39a4a3cf5 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -105,6 +105,11 @@ struct netem_sched_data {
u32 rho;
} delay_cor, loss_cor, dup_cor, reorder_cor, corrupt_cor;
+ struct prng {
+ u64 seed;
+ struct rnd_state prng_state;
+ } prng;
+
struct disttable *delay_dist;
enum {
@@ -179,15 +184,16 @@ static void init_crandom(struct crndstate *state, unsigned long rho)
* Next number depends on last value.
* rho is scaled to avoid floating point.
*/
-static u32 get_crandom(struct crndstate *state)
+static u32 get_crandom(struct crndstate *state, struct prng *p)
{
u64 value, rho;
unsigned long answer;
+ struct rnd_state *s = &p->prng_state;
if (!state || state->rho == 0) /* no correlation */
- return get_random_u32();
+ return prandom_u32_state(s);
- value = get_random_u32();
+ value = prandom_u32_state(s);
rho = (u64)state->rho + 1;
answer = (value * ((1ull<<32) - rho) + state->last * rho) >> 32;
state->last = answer;
@@ -201,7 +207,7 @@ static u32 get_crandom(struct crndstate *state)
static bool loss_4state(struct netem_sched_data *q)
{
struct clgstate *clg = &q->clg;
- u32 rnd = get_random_u32();
+ u32 rnd = prandom_u32_state(&q->prng.prng_state);
/*
* Makes a comparison between rnd and the transition
@@ -266,18 +272,19 @@ static bool loss_4state(struct netem_sched_data *q)
static bool loss_gilb_ell(struct netem_sched_data *q)
{
struct clgstate *clg = &q->clg;
+ struct rnd_state *s = &q->prng.prng_state;
switch (clg->state) {
case GOOD_STATE:
- if (get_random_u32() < clg->a1)
+ if (prandom_u32_state(s) < clg->a1)
clg->state = BAD_STATE;
- if (get_random_u32() < clg->a4)
+ if (prandom_u32_state(s) < clg->a4)
return true;
break;
case BAD_STATE:
- if (get_random_u32() < clg->a2)
+ if (prandom_u32_state(s) < clg->a2)
clg->state = GOOD_STATE;
- if (get_random_u32() > clg->a3)
+ if (prandom_u32_state(s) > clg->a3)
return true;
}
@@ -289,7 +296,7 @@ static bool loss_event(struct netem_sched_data *q)
switch (q->loss_model) {
case CLG_RANDOM:
/* Random packet drop 0 => none, ~0 => all */
- return q->loss && q->loss >= get_crandom(&q->loss_cor);
+ return q->loss && q->loss >= get_crandom(&q->loss_cor, &q->prng);
case CLG_4_STATES:
/* 4state loss model algorithm (used also for GI model)
@@ -318,6 +325,7 @@ static bool loss_event(struct netem_sched_data *q)
*/
static s64 tabledist(s64 mu, s32 sigma,
struct crndstate *state,
+ struct prng *prng,
const struct disttable *dist)
{
s64 x;
@@ -327,7 +335,7 @@ static s64 tabledist(s64 mu, s32 sigma,
if (sigma == 0)
return mu;
- rnd = get_crandom(state);
+ rnd = get_crandom(state, prng);
/* default uniform distribution */
if (dist == NULL)
@@ -449,7 +457,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
skb->prev = NULL;
/* Random duplication */
- if (q->duplicate && q->duplicate >= get_crandom(&q->dup_cor))
+ if (q->duplicate && q->duplicate >= get_crandom(&q->dup_cor, &q->prng))
++count;
/* Drop packet? */
@@ -492,7 +500,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
* If packet is going to be hardware checksummed, then
* do it now in software before we mangle it.
*/
- if (q->corrupt && q->corrupt >= get_crandom(&q->corrupt_cor)) {
+ if (q->corrupt && q->corrupt >= get_crandom(&q->corrupt_cor, &q->prng)) {
if (skb_is_gso(skb)) {
skb = netem_segment(skb, sch, to_free);
if (!skb)
@@ -530,12 +538,12 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
cb = netem_skb_cb(skb);
if (q->gap == 0 || /* not doing reordering */
q->counter < q->gap - 1 || /* inside last reordering gap */
- q->reorder < get_crandom(&q->reorder_cor)) {
+ q->reorder < get_crandom(&q->reorder_cor, &q->prng)) {
u64 now;
s64 delay;
delay = tabledist(q->latency, q->jitter,
- &q->delay_cor, q->delay_dist);
+ &q->delay_cor, &q->prng, q->delay_dist);
now = ktime_get_ns();
@@ -639,7 +647,7 @@ static void get_slot_next(struct netem_sched_data *q, u64 now)
else
next_delay = tabledist(q->slot_config.dist_delay,
(s32)(q->slot_config.dist_jitter),
- NULL, q->slot_dist);
+ NULL, &q->prng, q->slot_dist);
q->slot.slot_next = now + next_delay;
q->slot.packets_left = q->slot_config.max_packets;
@@ -922,6 +930,7 @@ static const struct nla_policy netem_policy[TCA_NETEM_MAX + 1] = {
[TCA_NETEM_LATENCY64] = { .type = NLA_S64 },
[TCA_NETEM_JITTER64] = { .type = NLA_S64 },
[TCA_NETEM_SLOT] = { .len = sizeof(struct tc_netem_slot) },
+ [TCA_NETEM_PRNG_SEED] = { .type = NLA_U64 },
};
static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla,
@@ -1040,6 +1049,12 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt,
/* capping jitter to the range acceptable by tabledist() */
q->jitter = min_t(s64, abs(q->jitter), INT_MAX);
+ if (tb[TCA_NETEM_PRNG_SEED])
+ q->prng.seed = nla_get_u64(tb[TCA_NETEM_PRNG_SEED]);
+ else
+ q->prng.seed = get_random_u64();
+ prandom_seed_state(&q->prng.prng_state, q->prng.seed);
+
unlock:
sch_tree_unlock(sch);
@@ -1203,6 +1218,10 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb)
goto nla_put_failure;
}
+ if (nla_put_u64_64bit(skb, TCA_NETEM_PRNG_SEED, q->prng.seed,
+ TCA_NETEM_PAD))
+ goto nla_put_failure;
+
return nla_nest_end(skb, nla);
nla_put_failure:
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index dfd9a99e6257..1a25752f1a9a 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -130,8 +130,6 @@ struct qfq_aggregate;
struct qfq_class {
struct Qdisc_class_common common;
- unsigned int filter_cnt;
-
struct gnet_stats_basic_sync bstats;
struct gnet_stats_queue qstats;
struct net_rate_estimator __rcu *rate_est;
@@ -381,8 +379,13 @@ static int qfq_change_agg(struct Qdisc *sch, struct qfq_class *cl, u32 weight,
u32 lmax)
{
struct qfq_sched *q = qdisc_priv(sch);
- struct qfq_aggregate *new_agg = qfq_find_agg(q, lmax, weight);
+ struct qfq_aggregate *new_agg;
+
+ /* 'lmax' can range from [QFQ_MIN_LMAX, pktlen + stab overhead] */
+ if (lmax > QFQ_MAX_LMAX)
+ return -EINVAL;
+ new_agg = qfq_find_agg(q, lmax, weight);
if (new_agg == NULL) { /* create new aggregate */
new_agg = kzalloc(sizeof(*new_agg), GFP_ATOMIC);
if (new_agg == NULL)
@@ -423,10 +426,17 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
else
weight = 1;
- if (tb[TCA_QFQ_LMAX])
+ if (tb[TCA_QFQ_LMAX]) {
lmax = nla_get_u32(tb[TCA_QFQ_LMAX]);
- else
+ } else {
+ /* MTU size is user controlled */
lmax = psched_mtu(qdisc_dev(sch));
+ if (lmax < QFQ_MIN_LMAX || lmax > QFQ_MAX_LMAX) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "MTU size out of bounds for qfq");
+ return -EINVAL;
+ }
+ }
inv_w = ONE_FP / weight;
weight = ONE_FP / inv_w;
@@ -533,8 +543,10 @@ static int qfq_delete_class(struct Qdisc *sch, unsigned long arg,
struct qfq_sched *q = qdisc_priv(sch);
struct qfq_class *cl = (struct qfq_class *)arg;
- if (cl->filter_cnt > 0)
+ if (qdisc_class_in_use(&cl->common)) {
+ NL_SET_ERR_MSG_MOD(extack, "QFQ class in use");
return -EBUSY;
+ }
sch_tree_lock(sch);
@@ -568,8 +580,8 @@ static unsigned long qfq_bind_tcf(struct Qdisc *sch, unsigned long parent,
{
struct qfq_class *cl = qfq_find_class(sch, classid);
- if (cl != NULL)
- cl->filter_cnt++;
+ if (cl)
+ qdisc_class_get(&cl->common);
return (unsigned long)cl;
}
@@ -578,7 +590,7 @@ static void qfq_unbind_tcf(struct Qdisc *sch, unsigned long arg)
{
struct qfq_class *cl = (struct qfq_class *)arg;
- cl->filter_cnt--;
+ qdisc_class_put(&cl->common);
}
static int qfq_graft_class(struct Qdisc *sch, unsigned long arg,
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 717ae51d94a0..1cb5e41c0ec7 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -1015,6 +1015,11 @@ static const struct nla_policy taprio_tc_policy[TCA_TAPRIO_TC_ENTRY_MAX + 1] = {
TC_FP_PREEMPTIBLE),
};
+static struct netlink_range_validation_signed taprio_cycle_time_range = {
+ .min = 0,
+ .max = INT_MAX,
+};
+
static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = {
[TCA_TAPRIO_ATTR_PRIOMAP] = {
.len = sizeof(struct tc_mqprio_qopt)
@@ -1023,7 +1028,8 @@ static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = {
[TCA_TAPRIO_ATTR_SCHED_BASE_TIME] = { .type = NLA_S64 },
[TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY] = { .type = NLA_NESTED },
[TCA_TAPRIO_ATTR_SCHED_CLOCKID] = { .type = NLA_S32 },
- [TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME] = { .type = NLA_S64 },
+ [TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME] =
+ NLA_POLICY_FULL_RANGE_SIGNED(NLA_S64, &taprio_cycle_time_range),
[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION] = { .type = NLA_S64 },
[TCA_TAPRIO_ATTR_FLAGS] = { .type = NLA_U32 },
[TCA_TAPRIO_ATTR_TXTIME_DELAY] = { .type = NLA_U32 },
@@ -1159,6 +1165,11 @@ static int parse_taprio_schedule(struct taprio_sched *q, struct nlattr **tb,
return -EINVAL;
}
+ if (cycle < 0 || cycle > INT_MAX) {
+ NL_SET_ERR_MSG(extack, "'cycle_time' is too big");
+ return -EINVAL;
+ }
+
new->cycle_time = cycle;
}
@@ -1347,7 +1358,7 @@ static void setup_txtime(struct taprio_sched *q,
struct sched_gate_list *sched, ktime_t base)
{
struct sched_entry *entry;
- u32 interval = 0;
+ u64 interval = 0;
list_for_each_entry(entry, &sched->entries, list) {
entry->next_txtime = ktime_add_ns(base, interval);
@@ -2088,11 +2099,8 @@ static int taprio_init(struct Qdisc *sch, struct nlattr *opt,
return -EOPNOTSUPP;
}
- /* pre-allocate qdisc, attachment can't fail */
- q->qdiscs = kcalloc(dev->num_tx_queues,
- sizeof(q->qdiscs[0]),
+ q->qdiscs = kcalloc(dev->num_tx_queues, sizeof(q->qdiscs[0]),
GFP_KERNEL);
-
if (!q->qdiscs)
return -ENOMEM;
@@ -2134,25 +2142,32 @@ static void taprio_attach(struct Qdisc *sch)
/* Attach underlying qdisc */
for (ntx = 0; ntx < dev->num_tx_queues; ntx++) {
- struct Qdisc *qdisc = q->qdiscs[ntx];
- struct Qdisc *old;
+ struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, ntx);
+ struct Qdisc *old, *dev_queue_qdisc;
if (FULL_OFFLOAD_IS_ENABLED(q->flags)) {
+ struct Qdisc *qdisc = q->qdiscs[ntx];
+
+ /* In offload mode, the root taprio qdisc is bypassed
+ * and the netdev TX queues see the children directly
+ */
qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
- old = dev_graft_qdisc(qdisc->dev_queue, qdisc);
+ dev_queue_qdisc = qdisc;
} else {
- old = dev_graft_qdisc(qdisc->dev_queue, sch);
- qdisc_refcount_inc(sch);
+ /* In software mode, attach the root taprio qdisc
+ * to all netdev TX queues, so that dev_qdisc_enqueue()
+ * goes through taprio_enqueue().
+ */
+ dev_queue_qdisc = sch;
}
+ old = dev_graft_qdisc(dev_queue, dev_queue_qdisc);
+ /* The qdisc's refcount requires to be elevated once
+ * for each netdev TX queue it is grafted onto
+ */
+ qdisc_refcount_inc(dev_queue_qdisc);
if (old)
qdisc_put(old);
}
-
- /* access to the child qdiscs is not needed in offload mode */
- if (FULL_OFFLOAD_IS_ENABLED(q->flags)) {
- kfree(q->qdiscs);
- q->qdiscs = NULL;
- }
}
static struct netdev_queue *taprio_queue_get(struct Qdisc *sch,
@@ -2181,13 +2196,23 @@ static int taprio_graft(struct Qdisc *sch, unsigned long cl,
if (dev->flags & IFF_UP)
dev_deactivate(dev);
+ /* In offload mode, the child Qdisc is directly attached to the netdev
+ * TX queue, and thus, we need to keep its refcount elevated in order
+ * to counteract qdisc_graft()'s call to qdisc_put() once per TX queue.
+ * However, save the reference to the new qdisc in the private array in
+ * both software and offload cases, to have an up-to-date reference to
+ * our children.
+ */
+ *old = q->qdiscs[cl - 1];
if (FULL_OFFLOAD_IS_ENABLED(q->flags)) {
- *old = dev_graft_qdisc(dev_queue, new);
- } else {
- *old = q->qdiscs[cl - 1];
- q->qdiscs[cl - 1] = new;
+ WARN_ON_ONCE(dev_graft_qdisc(dev_queue, new) != *old);
+ if (new)
+ qdisc_refcount_inc(new);
+ if (*old)
+ qdisc_put(*old);
}
+ q->qdiscs[cl - 1] = new;
if (new)
new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
@@ -2425,12 +2450,14 @@ start_error:
static struct Qdisc *taprio_leaf(struct Qdisc *sch, unsigned long cl)
{
- struct netdev_queue *dev_queue = taprio_queue_get(sch, cl);
+ struct taprio_sched *q = qdisc_priv(sch);
+ struct net_device *dev = qdisc_dev(sch);
+ unsigned int ntx = cl - 1;
- if (!dev_queue)
+ if (ntx >= dev->num_tx_queues)
return NULL;
- return rtnl_dereference(dev_queue->qdisc_sleeping);
+ return q->qdiscs[ntx];
}
static unsigned long taprio_find(struct Qdisc *sch, u32 classid)
@@ -2445,11 +2472,11 @@ static unsigned long taprio_find(struct Qdisc *sch, u32 classid)
static int taprio_dump_class(struct Qdisc *sch, unsigned long cl,
struct sk_buff *skb, struct tcmsg *tcm)
{
- struct netdev_queue *dev_queue = taprio_queue_get(sch, cl);
+ struct Qdisc *child = taprio_leaf(sch, cl);
tcm->tcm_parent = TC_H_ROOT;
tcm->tcm_handle |= TC_H_MIN(cl);
- tcm->tcm_info = rtnl_dereference(dev_queue->qdisc_sleeping)->handle;
+ tcm->tcm_info = child->handle;
return 0;
}
@@ -2459,16 +2486,14 @@ static int taprio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
__releases(d->lock)
__acquires(d->lock)
{
- struct netdev_queue *dev_queue = taprio_queue_get(sch, cl);
+ struct Qdisc *child = taprio_leaf(sch, cl);
struct tc_taprio_qopt_offload offload = {
.cmd = TAPRIO_CMD_QUEUE_STATS,
.queue_stats = {
.queue = cl - 1,
},
};
- struct Qdisc *child;
- child = rtnl_dereference(dev_queue->qdisc_sleeping);
if (gnet_stats_copy_basic(d, NULL, &child->bstats, true) < 0 ||
qdisc_qstats_copy(d, child) < 0)
return -1;
generated by cgit v1.2.3 (git 2.39.0) at 2025-07-24 17:49:06 +0300