Merge: ovs: backports P1 for 9.2

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9/-/merge_requests/1489

Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2134560

Signed-off-by: Antoine Tenart <atenart@redhat.com>

Approved-by: Jarod Wilson <jarod@redhat.com>
Approved-by: Eelco Chaudron <echaudro@redhat.com>
Approved-by: Marcelo Ricardo Leitner <mleitner@redhat.com>

Signed-off-by: Herton R. Krzesinski <herton@redhat.com>

Author: Herton R. Krzesinski

include/uapi/linux/openvswitch.h

@@ -76,6 +76,8 @@ enum ovs_datapath_cmd {
  * datapath.  Always present in notifications.
  * @OVS_DP_ATTR_MEGAFLOW_STATS: Statistics about mega flow masks usage for the
  * datapath. Always present in notifications.
+ * @OVS_DP_ATTR_IFINDEX: Interface index for a new datapath netdev. Only
+ * valid for %OVS_DP_CMD_NEW requests.
  *
  * These attributes follow the &struct ovs_header within the Generic Netlink
  * payload for %OVS_DP_* commands.
@@ -92,6 +94,7 @@ enum ovs_datapath_attr {
 	OVS_DP_ATTR_PER_CPU_PIDS,   /* Netlink PIDS to receive upcalls in
 				     * per-cpu dispatch mode
 				     */
+	OVS_DP_ATTR_IFINDEX,
 	__OVS_DP_ATTR_MAX
 };
 

net/openvswitch/conntrack.c

@@ -1015,7 +1015,8 @@ static int __ovs_ct_lookup(struct net *net, struct sw_flow_key *key,
 		 * connections which we will commit, we may need to attach
 		 * the helper here.
 		 */
-		if (info->commit && info->helper && !nfct_help(ct)) {
+		if (!nf_ct_is_confirmed(ct) && info->commit &&
+		    info->helper && !nfct_help(ct)) {
 			int err = __nf_ct_try_assign_helper(ct, info->ct,
 							    GFP_ATOMIC);
 			if (err)
@@ -1982,7 +1983,8 @@ static int ovs_ct_limit_set_zone_limit(struct nlattr *nla_zone_limit,
 		} else {
 			struct ovs_ct_limit *ct_limit;
 
-			ct_limit = kmalloc(sizeof(*ct_limit), GFP_KERNEL);
+			ct_limit = kmalloc(sizeof(*ct_limit),
+					   GFP_KERNEL_ACCOUNT);
 			if (!ct_limit)
 				return -ENOMEM;
 
@@ -2252,14 +2254,16 @@ static int ovs_ct_limit_cmd_get(struct sk_buff *skb, struct genl_info *info)
 static const struct genl_small_ops ct_limit_genl_ops[] = {
 	{ .cmd = OVS_CT_LIMIT_CMD_SET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN
-					   * privilege. */
+		.flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN
+					       * privilege.
+					       */
 		.doit = ovs_ct_limit_cmd_set,
 	},
 	{ .cmd = OVS_CT_LIMIT_CMD_DEL,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN
-					   * privilege. */
+		.flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN
+					       * privilege.
+					       */
 		.doit = ovs_ct_limit_cmd_del,
 	},
 	{ .cmd = OVS_CT_LIMIT_CMD_GET,

net/openvswitch/datapath.c

@@ -252,10 +252,17 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key)
 
 		upcall.mru = OVS_CB(skb)->mru;
 		error = ovs_dp_upcall(dp, skb, key, &upcall, 0);
-		if (unlikely(error))
-			kfree_skb(skb);
-		else
+		switch (error) {
+		case 0:
+		case -EAGAIN:
+		case -ERESTARTSYS:
+		case -EINTR:
 			consume_skb(skb);
+			break;
+		default:
+			kfree_skb(skb);
+			break;
+		}
 		stats_counter = &stats->n_missed;
 		goto out;
 	}
@@ -551,8 +558,9 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
 out:
 	if (err)
 		skb_tx_error(skb);
-	kfree_skb(user_skb);
-	kfree_skb(nskb);
+	consume_skb(user_skb);
+	consume_skb(nskb);
+
 	return err;
 }
 
@@ -1515,6 +1523,7 @@ static size_t ovs_dp_cmd_msg_size(void)
 	msgsize += nla_total_size_64bit(sizeof(struct ovs_dp_megaflow_stats));
 	msgsize += nla_total_size(sizeof(u32)); /* OVS_DP_ATTR_USER_FEATURES */
 	msgsize += nla_total_size(sizeof(u32)); /* OVS_DP_ATTR_MASKS_CACHE_SIZE */
+	msgsize += nla_total_size(sizeof(u32) * nr_cpu_ids); /* OVS_DP_ATTR_PER_CPU_PIDS */
 
 	return msgsize;
 }
@@ -1526,7 +1535,8 @@ static int ovs_dp_cmd_fill_info(struct datapath *dp, struct sk_buff *skb,
 	struct ovs_header *ovs_header;
 	struct ovs_dp_stats dp_stats;
 	struct ovs_dp_megaflow_stats dp_megaflow_stats;
-	int err;
+	struct dp_nlsk_pids *pids = ovsl_dereference(dp->upcall_portids);
+	int err, pids_len;
 
 	ovs_header = genlmsg_put(skb, portid, seq, &dp_datapath_genl_family,
 				 flags, cmd);
@@ -1556,6 +1566,12 @@ static int ovs_dp_cmd_fill_info(struct datapath *dp, struct sk_buff *skb,
 			ovs_flow_tbl_masks_cache_size(&dp->table)))
 		goto nla_put_failure;
 
+	if (dp->user_features & OVS_DP_F_DISPATCH_UPCALL_PER_CPU && pids) {
+		pids_len = min(pids->n_pids, nr_cpu_ids) * sizeof(u32);
+		if (nla_put(skb, OVS_DP_ATTR_PER_CPU_PIDS, pids_len, &pids->pids))
+			goto nla_put_failure;
+	}
+
 	genlmsg_end(skb, ovs_header);
 	return 0;
 
@@ -1779,6 +1795,8 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	parms.dp = dp;
 	parms.port_no = OVSP_LOCAL;
 	parms.upcall_portids = a[OVS_DP_ATTR_UPCALL_PID];
+	parms.desired_ifindex = a[OVS_DP_ATTR_IFINDEX]
+		? nla_get_u32(a[OVS_DP_ATTR_IFINDEX]) : 0;
 
 	/* So far only local changes have been made, now need the lock. */
 	ovs_lock();
@@ -1802,7 +1820,7 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
 				ovs_dp_reset_user_features(skb, info);
 		}
 
-		goto err_unlock_and_destroy_meters;
+		goto err_destroy_portids;
 	}
 
 	err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid,
@@ -1817,6 +1835,8 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	ovs_notify(&dp_datapath_genl_family, reply, info);
 	return 0;
 
+err_destroy_portids:
+	kfree(rcu_dereference_raw(dp->upcall_portids));
 err_unlock_and_destroy_meters:
 	ovs_unlock();
 	ovs_meters_exit(dp);
@@ -1996,6 +2016,7 @@ static const struct nla_policy datapath_policy[OVS_DP_ATTR_MAX + 1] = {
 	[OVS_DP_ATTR_USER_FEATURES] = { .type = NLA_U32 },
 	[OVS_DP_ATTR_MASKS_CACHE_SIZE] =  NLA_POLICY_RANGE(NLA_U32, 0,
 		PCPU_MIN_UNIT_SIZE / sizeof(struct mask_cache_entry)),
+	[OVS_DP_ATTR_IFINDEX] = {.type = NLA_U32 },
 };
 
 static const struct genl_small_ops dp_datapath_genl_ops[] = {
@@ -2199,7 +2220,10 @@ static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	if (!a[OVS_VPORT_ATTR_NAME] || !a[OVS_VPORT_ATTR_TYPE] ||
 	    !a[OVS_VPORT_ATTR_UPCALL_PID])
 		return -EINVAL;
-	if (a[OVS_VPORT_ATTR_IFINDEX])
+
+	parms.type = nla_get_u32(a[OVS_VPORT_ATTR_TYPE]);
+
+	if (a[OVS_VPORT_ATTR_IFINDEX] && parms.type != OVS_VPORT_TYPE_INTERNAL)
 		return -EOPNOTSUPP;
 
 	port_no = a[OVS_VPORT_ATTR_PORT_NO]
@@ -2236,11 +2260,12 @@ static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	parms.name = nla_data(a[OVS_VPORT_ATTR_NAME]);
-	parms.type = nla_get_u32(a[OVS_VPORT_ATTR_TYPE]);
 	parms.options = a[OVS_VPORT_ATTR_OPTIONS];
 	parms.dp = dp;
 	parms.port_no = port_no;
 	parms.upcall_portids = a[OVS_VPORT_ATTR_UPCALL_PID];
+	parms.desired_ifindex = a[OVS_VPORT_ATTR_IFINDEX]
+		? nla_get_u32(a[OVS_VPORT_ATTR_IFINDEX]) : 0;
 
 	vport = new_vport(&parms);
 	err = PTR_ERR(vport);

net/openvswitch/flow_netlink.c

@@ -3275,7 +3275,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 
 			/* Disallow subsequent L2.5+ set actions and mpls_pop
 			 * actions once the last MPLS label in the packet is
-			 * is popped as there is no check here to ensure that
+			 * popped as there is no check here to ensure that
 			 * the new eth type is valid and thus set actions could
 			 * write off the end of the packet or otherwise corrupt
 			 * it.

net/openvswitch/meter.c

@@ -343,7 +343,7 @@ static struct dp_meter *dp_meter_create(struct nlattr **a)
 			return ERR_PTR(-EINVAL);
 
 	/* Allocate and set up the meter before locking anything. */
-	meter = kzalloc(struct_size(meter, bands, n_bands), GFP_KERNEL);
+	meter = kzalloc(struct_size(meter, bands, n_bands), GFP_KERNEL_ACCOUNT);
 	if (!meter)
 		return ERR_PTR(-ENOMEM);
 
@@ -687,9 +687,9 @@ static const struct genl_small_ops dp_meter_genl_ops[] = {
 	},
 	{ .cmd = OVS_METER_CMD_SET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN
-					   *  privilege.
-					   */
+		.flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN
+					       *  privilege.
+					       */
 		.doit = ovs_meter_cmd_set,
 	},
 	{ .cmd = OVS_METER_CMD_GET,
@@ -699,9 +699,9 @@ static const struct genl_small_ops dp_meter_genl_ops[] = {
 	},
 	{ .cmd = OVS_METER_CMD_DEL,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN
-					   *  privilege.
-					   */
+		.flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN
+					       *  privilege.
+					       */
 		.doit = ovs_meter_cmd_del
 	},
 };

net/openvswitch/vport-internal_dev.c

@@ -65,7 +65,7 @@ static int internal_dev_stop(struct net_device *netdev)
 static void internal_dev_getinfo(struct net_device *netdev,
 				 struct ethtool_drvinfo *info)
 {
-	strlcpy(info->driver, "openvswitch", sizeof(info->driver));
+	strscpy(info->driver, "openvswitch", sizeof(info->driver));
 }
 
 static const struct ethtool_ops internal_dev_ethtool_ops = {
@@ -147,6 +147,7 @@ static struct vport *internal_dev_create(const struct vport_parms *parms)
 	}
 
 	dev_net_set(vport->dev, ovs_dp_get_net(vport->dp));
+	dev->ifindex = parms->desired_ifindex;
 	internal_dev = internal_dev_priv(vport->dev);
 	internal_dev->vport = vport;
 
@@ -189,7 +190,7 @@ static void internal_dev_destroy(struct vport *vport)
 	rtnl_unlock();
 }
 
-static netdev_tx_t internal_dev_recv(struct sk_buff *skb)
+static int internal_dev_recv(struct sk_buff *skb)
 {
 	struct net_device *netdev = skb->dev;
 

net/openvswitch/vport.h

@@ -90,12 +90,14 @@ struct vport {
  * @type: New vport's type.
  * @options: %OVS_VPORT_ATTR_OPTIONS attribute from Netlink message, %NULL if
  * none was supplied.
+ * @desired_ifindex: New vport's ifindex.
  * @dp: New vport's datapath.
  * @port_no: New vport's port number.
  */
 struct vport_parms {
 	const char *name;
 	enum ovs_vport_type type;
+	int desired_ifindex;
 	struct nlattr *options;
 
 	/* For ovs_vport_alloc(). */
@@ -130,7 +132,7 @@ struct vport_ops {
 	int (*set_options)(struct vport *, struct nlattr *);
 	int (*get_options)(const struct vport *, struct sk_buff *);
 
-	netdev_tx_t (*send) (struct sk_buff *skb);
+	int (*send)(struct sk_buff *skb);
 	struct module *owner;
 	struct list_head list;
 };