Update Linux to v5.10.109
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz
Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 7f20fd3..9a789a0 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -20,8 +20,8 @@
#include <linux/kmod.h>
#include <linux/slab.h>
#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>
@@ -38,6 +38,7 @@
#include <net/tc_act/tc_skbedit.h>
#include <net/tc_act/tc_ct.h>
#include <net/tc_act/tc_mpls.h>
+#include <net/tc_act/tc_gate.h>
#include <net/flow_offload.h>
extern const struct nla_policy rtm_tca_policy[TCA_MAX + 1];
@@ -354,7 +355,7 @@
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 @@
ASSERT_BLOCK_LOCKED(block);
- list_del(&chain->list);
+ list_del_rcu(&chain->list);
if (!chain->index)
block->chain0.chain = NULL;
@@ -453,6 +454,20 @@
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);
@@ -605,96 +620,46 @@
static int tcf_block_setup(struct tcf_block *block,
struct flow_block_offload *bo);
-static void tc_indr_block_cmd(struct net_device *dev, struct tcf_block *block,
- flow_indr_block_bind_cb_t *cb, void *cb_priv,
- enum flow_block_command command, bool ingress)
+static void tcf_block_offload_init(struct flow_block_offload *bo,
+ struct net_device *dev, struct Qdisc *sch,
+ enum flow_block_command command,
+ enum flow_block_binder_type binder_type,
+ struct flow_block *flow_block,
+ bool shared, struct netlink_ext_ack *extack)
{
- struct flow_block_offload bo = {
- .command = command,
- .binder_type = ingress ?
- FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS :
- FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS,
- .net = dev_net(dev),
- .block_shared = tcf_block_non_null_shared(block),
- };
- INIT_LIST_HEAD(&bo.cb_list);
+ bo->net = dev_net(dev);
+ bo->command = command;
+ bo->binder_type = binder_type;
+ bo->block = flow_block;
+ bo->block_shared = shared;
+ bo->extack = extack;
+ bo->sch = sch;
+ bo->cb_list_head = &flow_block->cb_list;
+ INIT_LIST_HEAD(&bo->cb_list);
+}
- if (!block)
- return;
+static void tcf_block_unbind(struct tcf_block *block,
+ struct flow_block_offload *bo);
- bo.block = &block->flow_block;
+static void tc_block_indr_cleanup(struct flow_block_cb *block_cb)
+{
+ struct tcf_block *block = block_cb->indr.data;
+ struct net_device *dev = block_cb->indr.dev;
+ struct Qdisc *sch = block_cb->indr.sch;
+ struct netlink_ext_ack extack = {};
+ struct flow_block_offload bo = {};
+ tcf_block_offload_init(&bo, dev, sch, FLOW_BLOCK_UNBIND,
+ block_cb->indr.binder_type,
+ &block->flow_block, tcf_block_shared(block),
+ &extack);
+ rtnl_lock();
down_write(&block->cb_lock);
- cb(dev, cb_priv, TC_SETUP_BLOCK, &bo);
-
- tcf_block_setup(block, &bo);
+ list_del(&block_cb->driver_list);
+ list_move(&block_cb->list, &bo.cb_list);
+ tcf_block_unbind(block, &bo);
up_write(&block->cb_lock);
-}
-
-static struct tcf_block *tc_dev_block(struct net_device *dev, bool ingress)
-{
- const struct Qdisc_class_ops *cops;
- const struct Qdisc_ops *ops;
- struct Qdisc *qdisc;
-
- if (!dev_ingress_queue(dev))
- return NULL;
-
- qdisc = dev_ingress_queue(dev)->qdisc_sleeping;
- if (!qdisc)
- return NULL;
-
- ops = qdisc->ops;
- if (!ops)
- return NULL;
-
- if (!ingress && !strcmp("ingress", ops->id))
- return NULL;
-
- cops = ops->cl_ops;
- if (!cops)
- return NULL;
-
- if (!cops->tcf_block)
- return NULL;
-
- return cops->tcf_block(qdisc,
- ingress ? TC_H_MIN_INGRESS : TC_H_MIN_EGRESS,
- NULL);
-}
-
-static void tc_indr_block_get_and_cmd(struct net_device *dev,
- flow_indr_block_bind_cb_t *cb,
- void *cb_priv,
- enum flow_block_command command)
-{
- struct tcf_block *block;
-
- block = tc_dev_block(dev, true);
- tc_indr_block_cmd(dev, block, cb, cb_priv, command, true);
-
- block = tc_dev_block(dev, false);
- tc_indr_block_cmd(dev, block, cb, cb_priv, command, false);
-}
-
-static void tc_indr_block_call(struct tcf_block *block,
- struct net_device *dev,
- struct tcf_block_ext_info *ei,
- enum flow_block_command command,
- struct netlink_ext_ack *extack)
-{
- struct flow_block_offload bo = {
- .command = command,
- .binder_type = ei->binder_type,
- .net = dev_net(dev),
- .block = &block->flow_block,
- .block_shared = tcf_block_shared(block),
- .extack = extack,
- };
- INIT_LIST_HEAD(&bo.cb_list);
-
- flow_indr_block_call(dev, &bo, command);
- tcf_block_setup(block, &bo);
+ rtnl_unlock();
}
static bool tcf_block_offload_in_use(struct tcf_block *block)
@@ -703,27 +668,35 @@
}
static int tcf_block_offload_cmd(struct tcf_block *block,
- struct net_device *dev,
+ struct net_device *dev, struct Qdisc *sch,
struct tcf_block_ext_info *ei,
enum flow_block_command command,
struct netlink_ext_ack *extack)
{
struct flow_block_offload bo = {};
- int err;
- bo.net = dev_net(dev);
- bo.command = command;
- bo.binder_type = ei->binder_type;
- bo.block = &block->flow_block;
- bo.block_shared = tcf_block_shared(block);
- bo.extack = extack;
- INIT_LIST_HEAD(&bo.cb_list);
+ tcf_block_offload_init(&bo, dev, sch, command, ei->binder_type,
+ &block->flow_block, tcf_block_shared(block),
+ extack);
- err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo);
- if (err < 0)
- return err;
+ if (dev->netdev_ops->ndo_setup_tc) {
+ int err;
- return tcf_block_setup(block, &bo);
+ err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo);
+ if (err < 0) {
+ if (err != -EOPNOTSUPP)
+ NL_SET_ERR_MSG(extack, "Driver ndo_setup_tc failed");
+ return err;
+ }
+
+ return tcf_block_setup(block, &bo);
+ }
+
+ flow_indr_dev_setup_offload(dev, sch, TC_SETUP_BLOCK, block, &bo,
+ tc_block_indr_cleanup);
+ tcf_block_setup(block, &bo);
+
+ return -EOPNOTSUPP;
}
static int tcf_block_offload_bind(struct tcf_block *block, struct Qdisc *q,
@@ -734,36 +707,33 @@
int err;
down_write(&block->cb_lock);
- if (!dev->netdev_ops->ndo_setup_tc)
- goto no_offload_dev_inc;
/* If tc offload feature is disabled and the block we try to bind
* to already has some offloaded filters, forbid to bind.
*/
- if (!tc_can_offload(dev) && tcf_block_offload_in_use(block)) {
+ if (dev->netdev_ops->ndo_setup_tc &&
+ !tc_can_offload(dev) &&
+ tcf_block_offload_in_use(block)) {
NL_SET_ERR_MSG(extack, "Bind to offloaded block failed as dev has offload disabled");
err = -EOPNOTSUPP;
goto err_unlock;
}
- err = tcf_block_offload_cmd(block, dev, ei, FLOW_BLOCK_BIND, extack);
+ err = tcf_block_offload_cmd(block, dev, q, ei, FLOW_BLOCK_BIND, extack);
if (err == -EOPNOTSUPP)
goto no_offload_dev_inc;
if (err)
goto err_unlock;
- tc_indr_block_call(block, dev, ei, FLOW_BLOCK_BIND, extack);
up_write(&block->cb_lock);
return 0;
no_offload_dev_inc:
- if (tcf_block_offload_in_use(block)) {
- err = -EOPNOTSUPP;
+ if (tcf_block_offload_in_use(block))
goto err_unlock;
- }
+
err = 0;
block->nooffloaddevcnt++;
- tc_indr_block_call(block, dev, ei, FLOW_BLOCK_BIND, extack);
err_unlock:
up_write(&block->cb_lock);
return err;
@@ -776,11 +746,7 @@
int err;
down_write(&block->cb_lock);
- tc_indr_block_call(block, dev, ei, FLOW_BLOCK_UNBIND, NULL);
-
- if (!dev->netdev_ops->ndo_setup_tc)
- goto no_offload_dev_dec;
- err = tcf_block_offload_cmd(block, dev, ei, FLOW_BLOCK_UNBIND, NULL);
+ err = tcf_block_offload_cmd(block, dev, q, ei, FLOW_BLOCK_UNBIND, NULL);
if (err == -EOPNOTSUPP)
goto no_offload_dev_dec;
up_write(&block->cb_lock);
@@ -1079,7 +1045,7 @@
/* Find qdisc */
if (!*parent) {
- *q = dev->qdisc;
+ *q = rcu_dereference(dev->qdisc);
*parent = (*q)->handle;
} else {
*q = qdisc_lookup_rcu(dev, TC_H_MAJ(*parent));
@@ -1559,12 +1525,15 @@
* 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 int max_reclassify_loop = 16;
const struct tcf_proto *first_tp;
int limit = 0;
@@ -1582,21 +1551,11 @@
#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 +1578,66 @@
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);
+ last_executed_chain = fchain->index;
+ }
+
+ 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 = tc_skb_ext_alloc(skb);
+ if (WARN_ON_ONCE(!ext))
+ return TC_ACT_SHOT;
+ ext->chain = last_executed_chain;
+ ext->mru = qdisc_skb_cb(skb)->mru;
+ }
+
+ return ret;
+#endif
+}
+EXPORT_SYMBOL(tcf_classify_ingress);
+
struct tcf_chain_info {
struct tcf_proto __rcu **pprev;
struct tcf_proto __rcu *next;
@@ -1782,7 +1799,7 @@
struct tcf_proto *tp, struct tcf_block *block,
struct Qdisc *q, u32 parent, void *fh,
u32 portid, u32 seq, u16 flags, int event,
- bool rtnl_held)
+ bool terse_dump, bool rtnl_held)
{
struct tcmsg *tcm;
struct nlmsghdr *nlh;
@@ -1809,6 +1826,14 @@
goto nla_put_failure;
if (!fh) {
tcm->tcm_handle = 0;
+ } else if (terse_dump) {
+ if (tp->ops->terse_dump) {
+ if (tp->ops->terse_dump(net, tp, fh, skb, tcm,
+ rtnl_held) < 0)
+ goto nla_put_failure;
+ } else {
+ goto cls_op_not_supp;
+ }
} else {
if (tp->ops->dump &&
tp->ops->dump(net, tp, fh, skb, tcm, rtnl_held) < 0)
@@ -1819,6 +1844,7 @@
out_nlmsg_trim:
nla_put_failure:
+cls_op_not_supp:
nlmsg_trim(skb, b);
return -1;
}
@@ -1839,7 +1865,7 @@
if (tcf_fill_node(net, skb, tp, block, q, parent, fh, portid,
n->nlmsg_seq, n->nlmsg_flags, event,
- rtnl_held) <= 0) {
+ false, rtnl_held) <= 0) {
kfree_skb(skb);
return -EINVAL;
}
@@ -1871,7 +1897,7 @@
if (tcf_fill_node(net, skb, tp, block, q, parent, fh, portid,
n->nlmsg_seq, n->nlmsg_flags, RTM_DELTFILTER,
- rtnl_held) <= 0) {
+ false, rtnl_held) <= 0) {
NL_SET_ERR_MSG(extack, "Failed to build del event notification");
kfree_skb(skb);
return -EINVAL;
@@ -1928,9 +1954,9 @@
bool prio_allocate;
u32 parent;
u32 chain_index;
- struct Qdisc *q = NULL;
+ struct Qdisc *q;
struct tcf_chain_info chain_info;
- struct tcf_chain *chain = NULL;
+ struct tcf_chain *chain;
struct tcf_block *block;
struct tcf_proto *tp;
unsigned long cl;
@@ -1958,6 +1984,8 @@
tp = NULL;
cl = 0;
block = NULL;
+ q = NULL;
+ chain = NULL;
if (prio == 0) {
/* If no priority is provided by the user,
@@ -2432,6 +2460,7 @@
struct tcf_block *block;
struct Qdisc *q;
u32 parent;
+ bool terse_dump;
};
static int tcf_node_dump(struct tcf_proto *tp, void *n, struct tcf_walker *arg)
@@ -2442,12 +2471,12 @@
return tcf_fill_node(net, a->skb, tp, a->block, a->q, a->parent,
n, NETLINK_CB(a->cb->skb).portid,
a->cb->nlh->nlmsg_seq, NLM_F_MULTI,
- RTM_NEWTFILTER, true);
+ RTM_NEWTFILTER, a->terse_dump, true);
}
static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent,
struct sk_buff *skb, struct netlink_callback *cb,
- long index_start, long *p_index)
+ long index_start, long *p_index, bool terse)
{
struct net *net = sock_net(skb->sk);
struct tcf_block *block = chain->block;
@@ -2476,7 +2505,7 @@
if (tcf_fill_node(net, skb, tp, block, q, parent, NULL,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, NLM_F_MULTI,
- RTM_NEWTFILTER, true) <= 0)
+ RTM_NEWTFILTER, false, true) <= 0)
goto errout;
cb->args[1] = 1;
}
@@ -2492,6 +2521,7 @@
arg.w.skip = cb->args[1] - 1;
arg.w.count = 0;
arg.w.cookie = cb->args[2];
+ arg.terse_dump = terse;
tp->ops->walk(tp, &arg.w, true);
cb->args[2] = arg.w.cookie;
cb->args[1] = arg.w.count + 1;
@@ -2505,6 +2535,10 @@
return false;
}
+static const struct nla_policy tcf_tfilter_dump_policy[TCA_MAX + 1] = {
+ [TCA_DUMP_FLAGS] = NLA_POLICY_BITFIELD32(TCA_DUMP_FLAGS_TERSE),
+};
+
/* called with RTNL */
static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
{
@@ -2514,6 +2548,7 @@
struct Qdisc *q = NULL;
struct tcf_block *block;
struct tcmsg *tcm = nlmsg_data(cb->nlh);
+ bool terse_dump = false;
long index_start;
long index;
u32 parent;
@@ -2523,10 +2558,17 @@
return skb->len;
err = nlmsg_parse_deprecated(cb->nlh, sizeof(*tcm), tca, TCA_MAX,
- NULL, cb->extack);
+ tcf_tfilter_dump_policy, cb->extack);
if (err)
return err;
+ if (tca[TCA_DUMP_FLAGS]) {
+ struct nla_bitfield32 flags =
+ nla_get_bitfield32(tca[TCA_DUMP_FLAGS]);
+
+ terse_dump = flags.value & TCA_DUMP_FLAGS_TERSE;
+ }
+
if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK) {
block = tcf_block_refcnt_get(net, tcm->tcm_block_index);
if (!block)
@@ -2549,7 +2591,7 @@
parent = tcm->tcm_parent;
if (!parent)
- q = dev->qdisc;
+ q = rtnl_dereference(dev->qdisc);
else
q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent));
if (!q)
@@ -2584,7 +2626,7 @@
nla_get_u32(tca[TCA_CHAIN]) != chain->index)
continue;
if (!tcf_chain_dump(chain, q, parent, skb, cb,
- index_start, &index)) {
+ index_start, &index, terse_dump)) {
tcf_chain_put(chain);
err = -EMSGSIZE;
break;
@@ -2764,8 +2806,8 @@
struct tcmsg *t;
u32 parent;
u32 chain_index;
- struct Qdisc *q = NULL;
- struct tcf_chain *chain = NULL;
+ struct Qdisc *q;
+ struct tcf_chain *chain;
struct tcf_block *block;
unsigned long cl;
int err;
@@ -2775,6 +2817,7 @@
return -EPERM;
replay:
+ q = NULL;
err = nlmsg_parse_deprecated(n, sizeof(*t), tca, TCA_MAX,
rtm_tca_policy, extack);
if (err < 0)
@@ -2934,7 +2977,7 @@
parent = tcm->tcm_parent;
if (!parent) {
- q = dev->qdisc;
+ q = rtnl_dereference(dev->qdisc);
parent = q->handle;
} else {
q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent));
@@ -3012,14 +3055,21 @@
{
#ifdef CONFIG_NET_CLS_ACT
{
+ int init_res[TCA_ACT_MAX_PRIO] = {};
struct tc_action *act;
size_t attr_size = 0;
if (exts->police && tb[exts->police]) {
+ struct tc_action_ops *a_o;
+
+ a_o = tc_action_load_ops("police", tb[exts->police], rtnl_held, extack);
+ if (IS_ERR(a_o))
+ return PTR_ERR(a_o);
act = tcf_action_init_1(net, tp, tb[exts->police],
rate_tlv, "police", ovr,
- TCA_ACT_BIND, rtnl_held,
- extack);
+ TCA_ACT_BIND, a_o, init_res,
+ rtnl_held, extack);
+ module_put(a_o->owner);
if (IS_ERR(act))
return PTR_ERR(act);
@@ -3032,8 +3082,8 @@
err = tcf_action_init(net, tp, tb[exts->action],
rate_tlv, NULL, ovr, TCA_ACT_BIND,
- exts->actions, &attr_size,
- rtnl_held, extack);
+ exts->actions, init_res,
+ &attr_size, rtnl_held, extack);
if (err < 0)
return err;
exts->nr_actions = err;
@@ -3088,7 +3138,8 @@
if (nest == NULL)
goto nla_put_failure;
- if (tcf_action_dump(skb, exts->actions, 0, 0) < 0)
+ if (tcf_action_dump(skb, exts->actions, 0, 0, false)
+ < 0)
goto nla_put_failure;
nla_nest_end(skb, nest);
} else if (exts->police) {
@@ -3112,6 +3163,31 @@
}
EXPORT_SYMBOL(tcf_exts_dump);
+int tcf_exts_terse_dump(struct sk_buff *skb, struct tcf_exts *exts)
+{
+#ifdef CONFIG_NET_CLS_ACT
+ struct nlattr *nest;
+
+ if (!exts->action || !tcf_exts_has_actions(exts))
+ return 0;
+
+ nest = nla_nest_start_noflag(skb, exts->action);
+ if (!nest)
+ goto nla_put_failure;
+
+ if (tcf_action_dump(skb, exts->actions, 0, 0, true) < 0)
+ goto nla_put_failure;
+ nla_nest_end(skb, nest);
+ return 0;
+
+nla_put_failure:
+ nla_nest_cancel(skb, nest);
+ return -1;
+#else
+ return 0;
+#endif
+}
+EXPORT_SYMBOL(tcf_exts_terse_dump);
int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts)
{
@@ -3383,14 +3459,40 @@
}
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);
@@ -3433,23 +3535,62 @@
#endif
}
-int tc_setup_flow_action(struct flow_action *flow_action,
- const struct tcf_exts *exts, bool rtnl_held)
+static void tcf_gate_entry_destructor(void *priv)
{
- const struct tc_action *act;
+ struct action_gate_entry *oe = priv;
+
+ kfree(oe);
+}
+
+static int tcf_gate_get_entries(struct flow_action_entry *entry,
+ const struct tc_action *act)
+{
+ entry->gate.entries = tcf_gate_get_list(act);
+
+ if (!entry->gate.entries)
+ return -EINVAL;
+
+ entry->destructor = tcf_gate_entry_destructor;
+ entry->destructor_priv = entry->gate.entries;
+
+ return 0;
+}
+
+static enum flow_action_hw_stats tc_act_hw_stats(u8 hw_stats)
+{
+ if (WARN_ON_ONCE(hw_stats > TCA_ACT_HW_STATS_ANY))
+ return FLOW_ACTION_HW_STATS_DONT_CARE;
+ else if (!hw_stats)
+ return FLOW_ACTION_HW_STATS_DISABLED;
+
+ return hw_stats;
+}
+
+int tc_setup_flow_action(struct flow_action *flow_action,
+ const struct tcf_exts *exts)
+{
+ 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 = tc_act_hw_stats(act->hw_stats);
+
if (is_tcf_gact_ok(act)) {
entry->id = FLOW_ACTION_ACCEPT;
} else if (is_tcf_gact_shot(act)) {
@@ -3490,13 +3631,13 @@
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)) {
@@ -3510,12 +3651,13 @@
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 = tc_act_hw_stats(act->hw_stats);
entry = &flow_action->entries[++j];
}
} else if (is_tcf_csum(act)) {
@@ -3532,13 +3674,16 @@
tcf_sample_get_group(entry, act);
} else if (is_tcf_police(act)) {
entry->id = FLOW_ACTION_POLICE;
- entry->police.burst = tcf_police_tcfp_burst(act);
+ entry->police.burst = tcf_police_burst(act);
entry->police.rate_bytes_ps =
tcf_police_rate_bytes_ps(act);
+ entry->police.mtu = tcf_police_tcfp_mtu(act);
+ entry->police.index = act->tcfa_index;
} else if (is_tcf_ct(act)) {
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:
@@ -3561,28 +3706,44 @@
entry->mpls_mangle.ttl = tcf_mpls_ttl(act);
break;
default:
- goto err_out;
+ err = -EOPNOTSUPP;
+ 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 if (is_tcf_gate(act)) {
+ entry->id = FLOW_ACTION_GATE;
+ entry->gate.index = tcf_gate_index(act);
+ entry->gate.prio = tcf_gate_prio(act);
+ entry->gate.basetime = tcf_gate_basetime(act);
+ entry->gate.cycletime = tcf_gate_cycletime(act);
+ entry->gate.cycletimeext = tcf_gate_cycletimeext(act);
+ entry->gate.num_entries = tcf_gate_num_entries(act);
+ err = tcf_gate_get_entries(entry, act);
+ if (err)
+ goto err_out_locked;
} 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);
@@ -3602,6 +3763,119 @@
}
EXPORT_SYMBOL(tcf_exts_num_actions);
+#ifdef CONFIG_NET_CLS_ACT
+static int tcf_qevent_parse_block_index(struct nlattr *block_index_attr,
+ u32 *p_block_index,
+ struct netlink_ext_ack *extack)
+{
+ *p_block_index = nla_get_u32(block_index_attr);
+ if (!*p_block_index) {
+ NL_SET_ERR_MSG(extack, "Block number may not be zero");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+int tcf_qevent_init(struct tcf_qevent *qe, struct Qdisc *sch,
+ enum flow_block_binder_type binder_type,
+ struct nlattr *block_index_attr,
+ struct netlink_ext_ack *extack)
+{
+ u32 block_index;
+ int err;
+
+ if (!block_index_attr)
+ return 0;
+
+ err = tcf_qevent_parse_block_index(block_index_attr, &block_index, extack);
+ if (err)
+ return err;
+
+ if (!block_index)
+ return 0;
+
+ qe->info.binder_type = binder_type;
+ qe->info.chain_head_change = tcf_chain_head_change_dflt;
+ qe->info.chain_head_change_priv = &qe->filter_chain;
+ qe->info.block_index = block_index;
+
+ return tcf_block_get_ext(&qe->block, sch, &qe->info, extack);
+}
+EXPORT_SYMBOL(tcf_qevent_init);
+
+void tcf_qevent_destroy(struct tcf_qevent *qe, struct Qdisc *sch)
+{
+ if (qe->info.block_index)
+ tcf_block_put_ext(qe->block, sch, &qe->info);
+}
+EXPORT_SYMBOL(tcf_qevent_destroy);
+
+int tcf_qevent_validate_change(struct tcf_qevent *qe, struct nlattr *block_index_attr,
+ struct netlink_ext_ack *extack)
+{
+ u32 block_index;
+ int err;
+
+ if (!block_index_attr)
+ return 0;
+
+ err = tcf_qevent_parse_block_index(block_index_attr, &block_index, extack);
+ if (err)
+ return err;
+
+ /* Bounce newly-configured block or change in block. */
+ if (block_index != qe->info.block_index) {
+ NL_SET_ERR_MSG(extack, "Change of blocks is not supported");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL(tcf_qevent_validate_change);
+
+struct sk_buff *tcf_qevent_handle(struct tcf_qevent *qe, struct Qdisc *sch, struct sk_buff *skb,
+ struct sk_buff **to_free, int *ret)
+{
+ struct tcf_result cl_res;
+ struct tcf_proto *fl;
+
+ if (!qe->info.block_index)
+ return skb;
+
+ fl = rcu_dereference_bh(qe->filter_chain);
+
+ switch (tcf_classify(skb, fl, &cl_res, false)) {
+ case TC_ACT_SHOT:
+ qdisc_qstats_drop(sch);
+ __qdisc_drop(skb, to_free);
+ *ret = __NET_XMIT_BYPASS;
+ return NULL;
+ case TC_ACT_STOLEN:
+ case TC_ACT_QUEUED:
+ case TC_ACT_TRAP:
+ __qdisc_drop(skb, to_free);
+ *ret = __NET_XMIT_STOLEN;
+ return NULL;
+ case TC_ACT_REDIRECT:
+ skb_do_redirect(skb);
+ *ret = __NET_XMIT_STOLEN;
+ return NULL;
+ }
+
+ return skb;
+}
+EXPORT_SYMBOL(tcf_qevent_handle);
+
+int tcf_qevent_dump(struct sk_buff *skb, int attr_name, struct tcf_qevent *qe)
+{
+ if (!qe->info.block_index)
+ return 0;
+ return nla_put_u32(skb, attr_name, qe->info.block_index);
+}
+EXPORT_SYMBOL(tcf_qevent_dump);
+#endif
+
static __net_init int tcf_net_init(struct net *net)
{
struct tcf_net *tn = net_generic(net, tcf_net_id);
@@ -3625,11 +3899,6 @@
.size = sizeof(struct tcf_net),
};
-static struct flow_indr_block_entry block_entry = {
- .cb = tc_indr_block_get_and_cmd,
- .list = LIST_HEAD_INIT(block_entry.list),
-};
-
static int __init tc_filter_init(void)
{
int err;
@@ -3642,8 +3911,6 @@
if (err)
goto err_register_pernet_subsys;
- flow_indr_add_block_cb(&block_entry);
-
rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_new_tfilter, NULL,
RTNL_FLAG_DOIT_UNLOCKED);
rtnl_register(PF_UNSPEC, RTM_DELTFILTER, tc_del_tfilter, NULL,