1 files changed, 279 insertions, 91 deletions

diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index 6b3e65d7de0c..8c1d1554f657 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -1,18 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (c) 2008, Intel Corporation.
  *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, see <http://www.gnu.org/licenses/>.
- *
  * Author: Alexander Duyck <alexander.h.duyck@intel.com>
  */
 
@@ -23,38 +12,93 @@
 #include <linux/rtnetlink.h>
 #include <net/netlink.h>
 #include <net/pkt_sched.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+#include <net/dsfield.h>
+#include <net/pkt_cls.h>
+#include <net/tc_wrapper.h>
 
 #include <linux/tc_act/tc_skbedit.h>
 #include <net/tc_act/tc_skbedit.h>
 
-#define SKBEDIT_TAB_MASK     15
-
-static unsigned int skbedit_net_id;
 static struct tc_action_ops act_skbedit_ops;
 
-static int tcf_skbedit(struct sk_buff *skb, const struct tc_action *a,
-		       struct tcf_result *res)
+static u16 tcf_skbedit_hash(struct tcf_skbedit_params *params,
+			    struct sk_buff *skb)
+{
+	u16 queue_mapping = params->queue_mapping;
+
+	if (params->flags & SKBEDIT_F_TXQ_SKBHASH) {
+		u32 hash = skb_get_hash(skb);
+
+		queue_mapping += hash % params->mapping_mod;
+	}
+
+	return netdev_cap_txqueue(skb->dev, queue_mapping);
+}
+
+TC_INDIRECT_SCOPE int tcf_skbedit_act(struct sk_buff *skb,
+				      const struct tc_action *a,
+				      struct tcf_result *res)
 {
 	struct tcf_skbedit *d = to_skbedit(a);
+	struct tcf_skbedit_params *params;
 
-	spin_lock(&d->tcf_lock);
 	tcf_lastuse_update(&d->tcf_tm);
-	bstats_update(&d->tcf_bstats, skb);
-
-	if (d->flags & SKBEDIT_F_PRIORITY)
-		skb->priority = d->priority;
-	if (d->flags & SKBEDIT_F_QUEUE_MAPPING &&
-	    skb->dev->real_num_tx_queues > d->queue_mapping)
-		skb_set_queue_mapping(skb, d->queue_mapping);
-	if (d->flags & SKBEDIT_F_MARK) {
-		skb->mark &= ~d->mask;
-		skb->mark |= d->mark & d->mask;
+	bstats_update(this_cpu_ptr(d->common.cpu_bstats), skb);
+
+	params = rcu_dereference_bh(d->params);
+
+	if (params->flags & SKBEDIT_F_PRIORITY)
+		skb->priority = params->priority;
+	if (params->flags & SKBEDIT_F_INHERITDSFIELD) {
+		int wlen = skb_network_offset(skb);
+
+		switch (skb_protocol(skb, true)) {
+		case htons(ETH_P_IP):
+			wlen += sizeof(struct iphdr);
+			if (!pskb_may_pull(skb, wlen))
+				goto err;
+			skb->priority = ipv4_get_dsfield(ip_hdr(skb)) >> 2;
+			break;
+
+		case htons(ETH_P_IPV6):
+			wlen += sizeof(struct ipv6hdr);
+			if (!pskb_may_pull(skb, wlen))
+				goto err;
+			skb->priority = ipv6_get_dsfield(ipv6_hdr(skb)) >> 2;
+			break;
+		}
 	}
-	if (d->flags & SKBEDIT_F_PTYPE)
-		skb->pkt_type = d->ptype;
+	if (params->flags & SKBEDIT_F_QUEUE_MAPPING &&
+	    skb->dev->real_num_tx_queues > params->queue_mapping) {
+#ifdef CONFIG_NET_EGRESS
+		netdev_xmit_skip_txqueue(true);
+#endif
+		skb_set_queue_mapping(skb, tcf_skbedit_hash(params, skb));
+	}
+	if (params->flags & SKBEDIT_F_MARK) {
+		skb->mark &= ~params->mask;
+		skb->mark |= params->mark & params->mask;
+	}
+	if (params->flags & SKBEDIT_F_PTYPE)
+		skb->pkt_type = params->ptype;
+	return params->action;
+
+err:
+	qstats_drop_inc(this_cpu_ptr(d->common.cpu_qstats));
+	return TC_ACT_SHOT;
+}
+
+static void tcf_skbedit_stats_update(struct tc_action *a, u64 bytes,
+				     u64 packets, u64 drops,
+				     u64 lastuse, bool hw)
+{
+	struct tcf_skbedit *d = to_skbedit(a);
+	struct tcf_t *tm = &d->tcf_tm;
 
-	spin_unlock(&d->tcf_lock);
-	return d->tcf_action;
+	tcf_action_update_stats(a, bytes, packets, drops, hw);
+	tm->lastuse = max_t(u64, tm->lastuse, lastuse);
 }
 
 static const struct nla_policy skbedit_policy[TCA_SKBEDIT_MAX + 1] = {
@@ -64,25 +108,34 @@ static const struct nla_policy skbedit_policy[TCA_SKBEDIT_MAX + 1] = {
 	[TCA_SKBEDIT_MARK]		= { .len = sizeof(u32) },
 	[TCA_SKBEDIT_PTYPE]		= { .len = sizeof(u16) },
 	[TCA_SKBEDIT_MASK]		= { .len = sizeof(u32) },
+	[TCA_SKBEDIT_FLAGS]		= { .len = sizeof(u64) },
+	[TCA_SKBEDIT_QUEUE_MAPPING_MAX]	= { .len = sizeof(u16) },
 };
 
 static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 			    struct nlattr *est, struct tc_action **a,
-			    int ovr, int bind)
+			    struct tcf_proto *tp, u32 act_flags,
+			    struct netlink_ext_ack *extack)
 {
-	struct tc_action_net *tn = net_generic(net, skbedit_net_id);
+	struct tc_action_net *tn = net_generic(net, act_skbedit_ops.net_id);
+	bool bind = act_flags & TCA_ACT_FLAGS_BIND;
+	struct tcf_skbedit_params *params_new;
 	struct nlattr *tb[TCA_SKBEDIT_MAX + 1];
+	struct tcf_chain *goto_ch = NULL;
 	struct tc_skbedit *parm;
 	struct tcf_skbedit *d;
 	u32 flags = 0, *priority = NULL, *mark = NULL, *mask = NULL;
 	u16 *queue_mapping = NULL, *ptype = NULL;
+	u16 mapping_mod = 1;
 	bool exists = false;
 	int ret = 0, err;
+	u32 index;
 
 	if (nla == NULL)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_SKBEDIT_MAX, nla, skbedit_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, TCA_SKBEDIT_MAX, nla,
+					  skbedit_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -95,6 +148,11 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 	}
 
 	if (tb[TCA_SKBEDIT_QUEUE_MAPPING] != NULL) {
+		if (is_tcf_skbedit_ingress(act_flags) &&
+		    !(act_flags & TCA_ACT_FLAGS_SKIP_SW)) {
+			NL_SET_ERR_MSG_MOD(extack, "\"queue_mapping\" option on receive side is hardware only, use skip_sw");
+			return -EOPNOTSUPP;
+		}
 		flags |= SKBEDIT_F_QUEUE_MAPPING;
 		queue_mapping = nla_data(tb[TCA_SKBEDIT_QUEUE_MAPPING]);
 	}
@@ -116,144 +174,274 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 		mask = nla_data(tb[TCA_SKBEDIT_MASK]);
 	}
 
-	parm = nla_data(tb[TCA_SKBEDIT_PARMS]);
+	if (tb[TCA_SKBEDIT_FLAGS] != NULL) {
+		u64 *pure_flags = nla_data(tb[TCA_SKBEDIT_FLAGS]);
+
+		if (*pure_flags & SKBEDIT_F_TXQ_SKBHASH) {
+			u16 *queue_mapping_max;
+
+			if (!tb[TCA_SKBEDIT_QUEUE_MAPPING] ||
+			    !tb[TCA_SKBEDIT_QUEUE_MAPPING_MAX]) {
+				NL_SET_ERR_MSG_MOD(extack, "Missing required range of queue_mapping.");
+				return -EINVAL;
+			}
+
+			queue_mapping_max =
+				nla_data(tb[TCA_SKBEDIT_QUEUE_MAPPING_MAX]);
+			if (*queue_mapping_max < *queue_mapping) {
+				NL_SET_ERR_MSG_MOD(extack, "The range of queue_mapping is invalid, max < min.");
+				return -EINVAL;
+			}
+
+			mapping_mod = *queue_mapping_max - *queue_mapping + 1;
+			flags |= SKBEDIT_F_TXQ_SKBHASH;
+		}
+		if (*pure_flags & SKBEDIT_F_INHERITDSFIELD)
+			flags |= SKBEDIT_F_INHERITDSFIELD;
+	}
 
-	exists = tcf_hash_check(tn, parm->index, a, bind);
+	parm = nla_data(tb[TCA_SKBEDIT_PARMS]);
+	index = parm->index;
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
+	if (err < 0)
+		return err;
+	exists = err;
 	if (exists && bind)
-		return 0;
+		return ACT_P_BOUND;
 
 	if (!flags) {
-		tcf_hash_release(*a, bind);
+		if (exists)
+			tcf_idr_release(*a, bind);
+		else
+			tcf_idr_cleanup(tn, index);
 		return -EINVAL;
 	}
 
 	if (!exists) {
-		ret = tcf_hash_create(tn, parm->index, est, a,
-				      &act_skbedit_ops, bind, false);
-		if (ret)
+		ret = tcf_idr_create(tn, index, est, a,
+				     &act_skbedit_ops, bind, true, act_flags);
+		if (ret) {
+			tcf_idr_cleanup(tn, index);
 			return ret;
+		}
 
 		d = to_skbedit(*a);
 		ret = ACT_P_CREATED;
 	} else {
 		d = to_skbedit(*a);
-		tcf_hash_release(*a, bind);
-		if (!ovr)
+		if (!(act_flags & TCA_ACT_FLAGS_REPLACE)) {
+			tcf_idr_release(*a, bind);
 			return -EEXIST;
+		}
 	}
+	err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
+	if (err < 0)
+		goto release_idr;
 
-	spin_lock_bh(&d->tcf_lock);
+	params_new = kzalloc(sizeof(*params_new), GFP_KERNEL);
+	if (unlikely(!params_new)) {
+		err = -ENOMEM;
+		goto put_chain;
+	}
 
-	d->flags = flags;
+	params_new->flags = flags;
 	if (flags & SKBEDIT_F_PRIORITY)
-		d->priority = *priority;
-	if (flags & SKBEDIT_F_QUEUE_MAPPING)
-		d->queue_mapping = *queue_mapping;
+		params_new->priority = *priority;
+	if (flags & SKBEDIT_F_QUEUE_MAPPING) {
+		params_new->queue_mapping = *queue_mapping;
+		params_new->mapping_mod = mapping_mod;
+	}
 	if (flags & SKBEDIT_F_MARK)
-		d->mark = *mark;
+		params_new->mark = *mark;
 	if (flags & SKBEDIT_F_PTYPE)
-		d->ptype = *ptype;
+		params_new->ptype = *ptype;
 	/* default behaviour is to use all the bits */
-	d->mask = 0xffffffff;
+	params_new->mask = 0xffffffff;
 	if (flags & SKBEDIT_F_MASK)
-		d->mask = *mask;
-
-	d->tcf_action = parm->action;
+		params_new->mask = *mask;
 
+	params_new->action = parm->action;
+	spin_lock_bh(&d->tcf_lock);
+	goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
+	params_new = rcu_replace_pointer(d->params, params_new,
+					 lockdep_is_held(&d->tcf_lock));
 	spin_unlock_bh(&d->tcf_lock);
+	if (params_new)
+		kfree_rcu(params_new, rcu);
+	if (goto_ch)
+		tcf_chain_put_by_act(goto_ch);
 
-	if (ret == ACT_P_CREATED)
-		tcf_hash_insert(tn, *a);
 	return ret;
+put_chain:
+	if (goto_ch)
+		tcf_chain_put_by_act(goto_ch);
+release_idr:
+	tcf_idr_release(*a, bind);
+	return err;
 }
 
 static int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a,
 			    int bind, int ref)
 {
+	const struct tcf_skbedit *d = to_skbedit(a);
 	unsigned char *b = skb_tail_pointer(skb);
-	struct tcf_skbedit *d = to_skbedit(a);
+	const struct tcf_skbedit_params *params;
 	struct tc_skbedit opt = {
 		.index   = d->tcf_index,
-		.refcnt  = d->tcf_refcnt - ref,
-		.bindcnt = d->tcf_bindcnt - bind,
-		.action  = d->tcf_action,
+		.refcnt  = refcount_read(&d->tcf_refcnt) - ref,
+		.bindcnt = atomic_read(&d->tcf_bindcnt) - bind,
 	};
+	u64 pure_flags = 0;
 	struct tcf_t t;
 
+	rcu_read_lock();
+	params = rcu_dereference(d->params);
+	opt.action = params->action;
+
 	if (nla_put(skb, TCA_SKBEDIT_PARMS, sizeof(opt), &opt))
 		goto nla_put_failure;
-	if ((d->flags & SKBEDIT_F_PRIORITY) &&
-	    nla_put_u32(skb, TCA_SKBEDIT_PRIORITY, d->priority))
+	if ((params->flags & SKBEDIT_F_PRIORITY) &&
+	    nla_put_u32(skb, TCA_SKBEDIT_PRIORITY, params->priority))
 		goto nla_put_failure;
-	if ((d->flags & SKBEDIT_F_QUEUE_MAPPING) &&
-	    nla_put_u16(skb, TCA_SKBEDIT_QUEUE_MAPPING, d->queue_mapping))
+	if ((params->flags & SKBEDIT_F_QUEUE_MAPPING) &&
+	    nla_put_u16(skb, TCA_SKBEDIT_QUEUE_MAPPING, params->queue_mapping))
 		goto nla_put_failure;
-	if ((d->flags & SKBEDIT_F_MARK) &&
-	    nla_put_u32(skb, TCA_SKBEDIT_MARK, d->mark))
+	if ((params->flags & SKBEDIT_F_MARK) &&
+	    nla_put_u32(skb, TCA_SKBEDIT_MARK, params->mark))
 		goto nla_put_failure;
-	if ((d->flags & SKBEDIT_F_PTYPE) &&
-	    nla_put_u16(skb, TCA_SKBEDIT_PTYPE, d->ptype))
+	if ((params->flags & SKBEDIT_F_PTYPE) &&
+	    nla_put_u16(skb, TCA_SKBEDIT_PTYPE, params->ptype))
 		goto nla_put_failure;
-	if ((d->flags & SKBEDIT_F_MASK) &&
-	    nla_put_u32(skb, TCA_SKBEDIT_MASK, d->mask))
+	if ((params->flags & SKBEDIT_F_MASK) &&
+	    nla_put_u32(skb, TCA_SKBEDIT_MASK, params->mask))
+		goto nla_put_failure;
+	if (params->flags & SKBEDIT_F_INHERITDSFIELD)
+		pure_flags |= SKBEDIT_F_INHERITDSFIELD;
+	if (params->flags & SKBEDIT_F_TXQ_SKBHASH) {
+		if (nla_put_u16(skb, TCA_SKBEDIT_QUEUE_MAPPING_MAX,
+				params->queue_mapping + params->mapping_mod - 1))
+			goto nla_put_failure;
+
+		pure_flags |= SKBEDIT_F_TXQ_SKBHASH;
+	}
+	if (pure_flags != 0 &&
+	    nla_put(skb, TCA_SKBEDIT_FLAGS, sizeof(pure_flags), &pure_flags))
 		goto nla_put_failure;
 
 	tcf_tm_dump(&t, &d->tcf_tm);
 	if (nla_put_64bit(skb, TCA_SKBEDIT_TM, sizeof(t), &t, TCA_SKBEDIT_PAD))
 		goto nla_put_failure;
+	rcu_read_unlock();
+
 	return skb->len;
 
 nla_put_failure:
+	rcu_read_unlock();
 	nlmsg_trim(skb, b);
 	return -1;
 }
 
-static int tcf_skbedit_walker(struct net *net, struct sk_buff *skb,
-			      struct netlink_callback *cb, int type,
-			      const struct tc_action_ops *ops)
+static void tcf_skbedit_cleanup(struct tc_action *a)
 {
-	struct tc_action_net *tn = net_generic(net, skbedit_net_id);
+	struct tcf_skbedit *d = to_skbedit(a);
+	struct tcf_skbedit_params *params;
+
+	params = rcu_dereference_protected(d->params, 1);
+	if (params)
+		kfree_rcu(params, rcu);
+}
 
-	return tcf_generic_walker(tn, skb, cb, type, ops);
+static size_t tcf_skbedit_get_fill_size(const struct tc_action *act)
+{
+	return nla_total_size(sizeof(struct tc_skbedit))
+		+ nla_total_size(sizeof(u32)) /* TCA_SKBEDIT_PRIORITY */
+		+ nla_total_size(sizeof(u16)) /* TCA_SKBEDIT_QUEUE_MAPPING */
+		+ nla_total_size(sizeof(u16)) /* TCA_SKBEDIT_QUEUE_MAPPING_MAX */
+		+ nla_total_size(sizeof(u32)) /* TCA_SKBEDIT_MARK */
+		+ nla_total_size(sizeof(u16)) /* TCA_SKBEDIT_PTYPE */
+		+ nla_total_size(sizeof(u32)) /* TCA_SKBEDIT_MASK */
+		+ nla_total_size_64bit(sizeof(u64)); /* TCA_SKBEDIT_FLAGS */
 }
 
-static int tcf_skbedit_search(struct net *net, struct tc_action **a, u32 index)
+static int tcf_skbedit_offload_act_setup(struct tc_action *act, void *entry_data,
+					 u32 *index_inc, bool bind,
+					 struct netlink_ext_ack *extack)
 {
-	struct tc_action_net *tn = net_generic(net, skbedit_net_id);
+	if (bind) {
+		struct flow_action_entry *entry = entry_data;
+
+		if (is_tcf_skbedit_mark(act)) {
+			entry->id = FLOW_ACTION_MARK;
+			entry->mark = tcf_skbedit_mark(act);
+		} 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_skbedit_tx_queue_mapping(act)) {
+			NL_SET_ERR_MSG_MOD(extack, "Offload not supported when \"queue_mapping\" option is used on transmit side");
+			return -EOPNOTSUPP;
+		} else if (is_tcf_skbedit_rx_queue_mapping(act)) {
+			entry->id = FLOW_ACTION_RX_QUEUE_MAPPING;
+			entry->rx_queue = tcf_skbedit_rx_queue_mapping(act);
+		} else if (is_tcf_skbedit_inheritdsfield(act)) {
+			NL_SET_ERR_MSG_MOD(extack, "Offload not supported when \"inheritdsfield\" option is used");
+			return -EOPNOTSUPP;
+		} else {
+			NL_SET_ERR_MSG_MOD(extack, "Unsupported skbedit option offload");
+			return -EOPNOTSUPP;
+		}
+		*index_inc = 1;
+	} else {
+		struct flow_offload_action *fl_action = entry_data;
+
+		if (is_tcf_skbedit_mark(act))
+			fl_action->id = FLOW_ACTION_MARK;
+		else if (is_tcf_skbedit_ptype(act))
+			fl_action->id = FLOW_ACTION_PTYPE;
+		else if (is_tcf_skbedit_priority(act))
+			fl_action->id = FLOW_ACTION_PRIORITY;
+		else if (is_tcf_skbedit_rx_queue_mapping(act))
+			fl_action->id = FLOW_ACTION_RX_QUEUE_MAPPING;
+		else
+			return -EOPNOTSUPP;
+	}
 
-	return tcf_hash_search(tn, a, index);
+	return 0;
 }
 
 static struct tc_action_ops act_skbedit_ops = {
 	.kind		=	"skbedit",
-	.type		=	TCA_ACT_SKBEDIT,
+	.id		=	TCA_ID_SKBEDIT,
 	.owner		=	THIS_MODULE,
-	.act		=	tcf_skbedit,
+	.act		=	tcf_skbedit_act,
+	.stats_update	=	tcf_skbedit_stats_update,
 	.dump		=	tcf_skbedit_dump,
 	.init		=	tcf_skbedit_init,
-	.walk		=	tcf_skbedit_walker,
-	.lookup		=	tcf_skbedit_search,
+	.cleanup	=	tcf_skbedit_cleanup,
+	.get_fill_size	=	tcf_skbedit_get_fill_size,
+	.offload_act_setup =	tcf_skbedit_offload_act_setup,
 	.size		=	sizeof(struct tcf_skbedit),
 };
+MODULE_ALIAS_NET_ACT("skbedit");
 
 static __net_init int skbedit_init_net(struct net *net)
 {
-	struct tc_action_net *tn = net_generic(net, skbedit_net_id);
+	struct tc_action_net *tn = net_generic(net, act_skbedit_ops.net_id);
 
-	return tc_action_net_init(tn, &act_skbedit_ops, SKBEDIT_TAB_MASK);
+	return tc_action_net_init(net, tn, &act_skbedit_ops);
 }
 
-static void __net_exit skbedit_exit_net(struct net *net)
+static void __net_exit skbedit_exit_net(struct list_head *net_list)
 {
-	struct tc_action_net *tn = net_generic(net, skbedit_net_id);
-
-	tc_action_net_exit(tn);
+	tc_action_net_exit(net_list, act_skbedit_ops.net_id);
 }
 
 static struct pernet_operations skbedit_net_ops = {
 	.init = skbedit_init_net,
-	.exit = skbedit_exit_net,
-	.id   = &skbedit_net_id,
+	.exit_batch = skbedit_exit_net,
+	.id   = &act_skbedit_ops.net_id,
 	.size = sizeof(struct tc_action_net),
 };