Merge tag 'net-6.8.0-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni:
 "Including fixes from bpf and netfilter.

  Current release - regressions:

   - af_unix: fix another unix GC hangup

  Previous releases - regressions:

   - core: fix a possible AF_UNIX deadlock

   - bpf: fix NULL pointer dereference in sk_psock_verdict_data_ready()

   - netfilter: nft_flow_offload: release dst in case direct xmit path
     is used

   - bridge: switchdev: ensure MDB events are delivered exactly once

   - l2tp: pass correct message length to ip6_append_data

   - dccp/tcp: unhash sk from ehash for tb2 alloc failure after
     check_estalblished()

   - tls: fixes for record type handling with PEEK

   - devlink: fix possible use-after-free and memory leaks in
     devlink_init()

  Previous releases - always broken:

   - bpf: fix an oops when attempting to read the vsyscall page through
     bpf_probe_read_kernel

   - sched: act_mirred: use the backlog for mirred ingress

   - netfilter: nft_flow_offload: fix dst refcount underflow

   - ipv6: sr: fix possible use-after-free and null-ptr-deref

   - mptcp: fix several data races

   - phonet: take correct lock to peek at the RX queue

  Misc:

   - handful of fixes and reliability improvements for selftests"

* tag 'net-6.8.0-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (72 commits)
  l2tp: pass correct message length to ip6_append_data
  net: phy: realtek: Fix rtl8211f_config_init() for RTL8211F(D)(I)-VD-CG PHY
  selftests: ioam: refactoring to align with the fix
  Fix write to cloned skb in ipv6_hop_ioam()
  phonet/pep: fix racy skb_queue_empty() use
  phonet: take correct lock to peek at the RX queue
  net: sparx5: Add spinlock for frame transmission from CPU
  net/sched: flower: Add lock protection when remove filter handle
  devlink: fix port dump cmd type
  net: stmmac: Fix EST offset for dwmac 5.10
  tools: ynl: don't leak mcast_groups on init error
  tools: ynl: make sure we always pass yarg to mnl_cb_run
  net: mctp: put sock on tag allocation failure
  netfilter: nf_tables: use kzalloc for hook allocation
  netfilter: nf_tables: register hooks last when adding new chain/flowtable
  netfilter: nft_flow_offload: release dst in case direct xmit path is used
  netfilter: nft_flow_offload: reset dst in route object after setting up flow
  netfilter: nf_tables: set dormant flag on hook register failure
  selftests: tls: add test for peeking past a record of a different type
  selftests: tls: add test for merging of same-type control messages
  ...

1 files changed, 43 insertions, 26 deletions

diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 287a60381eae..58d17d9604e7 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -396,19 +396,6 @@ void mptcp_pm_free_anno_list(struct mptcp_sock *msk)
 	}
 }
 
-static bool lookup_address_in_vec(const struct mptcp_addr_info *addrs, unsigned int nr,
-				  const struct mptcp_addr_info *addr)
-{
-	int i;
-
-	for (i = 0; i < nr; i++) {
-		if (addrs[i].id == addr->id)
-			return true;
-	}
-
-	return false;
-}
-
 /* Fill all the remote addresses into the array addrs[],
  * and return the array size.
  */
@@ -440,18 +427,34 @@ static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk,
 		msk->pm.subflows++;
 		addrs[i++] = remote;
 	} else {
+		DECLARE_BITMAP(unavail_id, MPTCP_PM_MAX_ADDR_ID + 1);
+
+		/* Forbid creation of new subflows matching existing
+		 * ones, possibly already created by incoming ADD_ADDR
+		 */
+		bitmap_zero(unavail_id, MPTCP_PM_MAX_ADDR_ID + 1);
+		mptcp_for_each_subflow(msk, subflow)
+			if (READ_ONCE(subflow->local_id) == local->id)
+				__set_bit(subflow->remote_id, unavail_id);
+
 		mptcp_for_each_subflow(msk, subflow) {
 			ssk = mptcp_subflow_tcp_sock(subflow);
 			remote_address((struct sock_common *)ssk, &addrs[i]);
-			addrs[i].id = subflow->remote_id;
+			addrs[i].id = READ_ONCE(subflow->remote_id);
 			if (deny_id0 && !addrs[i].id)
 				continue;
 
+			if (test_bit(addrs[i].id, unavail_id))
+				continue;
+
 			if (!mptcp_pm_addr_families_match(sk, local, &addrs[i]))
 				continue;
 
-			if (!lookup_address_in_vec(addrs, i, &addrs[i]) &&
-			    msk->pm.subflows < subflows_max) {
+			if (msk->pm.subflows < subflows_max) {
+				/* forbid creating multiple address towards
+				 * this id
+				 */
+				__set_bit(addrs[i].id, unavail_id);
 				msk->pm.subflows++;
 				i++;
 			}
@@ -799,18 +802,18 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
 
 		mptcp_for_each_subflow_safe(msk, subflow, tmp) {
 			struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+			u8 remote_id = READ_ONCE(subflow->remote_id);
 			int how = RCV_SHUTDOWN | SEND_SHUTDOWN;
-			u8 id = subflow->local_id;
+			u8 id = subflow_get_local_id(subflow);
 
-			if (rm_type == MPTCP_MIB_RMADDR && subflow->remote_id != rm_id)
+			if (rm_type == MPTCP_MIB_RMADDR && remote_id != rm_id)
 				continue;
 			if (rm_type == MPTCP_MIB_RMSUBFLOW && !mptcp_local_id_match(msk, id, rm_id))
 				continue;
 
 			pr_debug(" -> %s rm_list_ids[%d]=%u local_id=%u remote_id=%u mpc_id=%u",
 				 rm_type == MPTCP_MIB_RMADDR ? "address" : "subflow",
-				 i, rm_id, subflow->local_id, subflow->remote_id,
-				 msk->mpc_endpoint_id);
+				 i, rm_id, id, remote_id, msk->mpc_endpoint_id);
 			spin_unlock_bh(&msk->pm.lock);
 			mptcp_subflow_shutdown(sk, ssk, how);
 
@@ -901,7 +904,8 @@ static void __mptcp_pm_release_addr_entry(struct mptcp_pm_addr_entry *entry)
 }
 
 static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet,
-					     struct mptcp_pm_addr_entry *entry)
+					     struct mptcp_pm_addr_entry *entry,
+					     bool needs_id)
 {
 	struct mptcp_pm_addr_entry *cur, *del_entry = NULL;
 	unsigned int addr_max;
@@ -949,7 +953,7 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet,
 		}
 	}
 
-	if (!entry->addr.id) {
+	if (!entry->addr.id && needs_id) {
 find_next:
 		entry->addr.id = find_next_zero_bit(pernet->id_bitmap,
 						    MPTCP_PM_MAX_ADDR_ID + 1,
@@ -960,7 +964,7 @@ find_next:
 		}
 	}
 
-	if (!entry->addr.id)
+	if (!entry->addr.id && needs_id)
 		goto out;
 
 	__set_bit(entry->addr.id, pernet->id_bitmap);
@@ -1092,7 +1096,7 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc
 	entry->ifindex = 0;
 	entry->flags = MPTCP_PM_ADDR_FLAG_IMPLICIT;
 	entry->lsk = NULL;
-	ret = mptcp_pm_nl_append_new_local_addr(pernet, entry);
+	ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, true);
 	if (ret < 0)
 		kfree(entry);
 
@@ -1285,6 +1289,18 @@ next:
 	return 0;
 }
 
+static bool mptcp_pm_has_addr_attr_id(const struct nlattr *attr,
+				      struct genl_info *info)
+{
+	struct nlattr *tb[MPTCP_PM_ADDR_ATTR_MAX + 1];
+
+	if (!nla_parse_nested_deprecated(tb, MPTCP_PM_ADDR_ATTR_MAX, attr,
+					 mptcp_pm_address_nl_policy, info->extack) &&
+	    tb[MPTCP_PM_ADDR_ATTR_ID])
+		return true;
+	return false;
+}
+
 int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info)
 {
 	struct nlattr *attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR];
@@ -1326,7 +1342,8 @@ int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info)
 			goto out_free;
 		}
 	}
-	ret = mptcp_pm_nl_append_new_local_addr(pernet, entry);
+	ret = mptcp_pm_nl_append_new_local_addr(pernet, entry,
+						!mptcp_pm_has_addr_attr_id(attr, info));
 	if (ret < 0) {
 		GENL_SET_ERR_MSG_FMT(info, "too many addresses or duplicate one: %d", ret);
 		goto out_free;
@@ -1980,7 +1997,7 @@ static int mptcp_event_add_subflow(struct sk_buff *skb, const struct sock *ssk)
 	if (WARN_ON_ONCE(!sf))
 		return -EINVAL;
 
-	if (nla_put_u8(skb, MPTCP_ATTR_LOC_ID, sf->local_id))
+	if (nla_put_u8(skb, MPTCP_ATTR_LOC_ID, subflow_get_local_id(sf)))
 		return -EMSGSIZE;
 
 	if (nla_put_u8(skb, MPTCP_ATTR_REM_ID, sf->remote_id))