Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/netHEADmaster

Pull networking fixes from David Miller:

 1) Fix rtnl deadlock in ipvs, from Julian Anastasov.

 2) s390 qeth fixes from Julian Wiedmann (control IO completion stalls,
    bad MAC address update sequence, request side races on command IO
    timeouts).

 3) Handle seq_file overflow properly in l2tp, from Guillaume Nault.

 4) Fix VLAN priority mappings in cpsw driver, from Ivan Khoronzhuk.

 5) Packet scheduler ife action fixes (malformed TLV lengths, etc.) from
    Alexander Aring.

 6) Fix out of bounds access in tcp md5 option parser, from Jann Horn.

 7) Missing netlink attribute policies in rtm_ipv6_policy table, from
    Eric Dumazet.

 8) Missing socket address length checks in l2tp and pppoe connect, from
    Guillaume Nault.

 9) Fix netconsole over team and bonding, from Xin Long.

10) Fix race with AF_PACKET socket state bitfields, from Willem de
    Bruijn.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (51 commits)
  ice: Fix insufficient memory issue in ice_aq_manage_mac_read
  sfc: ARFS filter IDs
  net: ethtool: Add missing kernel doc for FEC parameters
  packet: fix bitfield update race
  ice: Do not check INTEVENT bit for OICR interrupts
  ice: Fix incorrect comment for action type
  ice: Fix initialization for num_nodes_added
  igb: Fix the transmission mode of queue 0 for Qav mode
  ixgbevf: ensure xdp_ring resources are free'd on error exit
  team: fix netconsole setup over team
  amd-xgbe: Only use the SFP supported transceiver signals
  amd-xgbe: Improve KR auto-negotiation and training
  amd-xgbe: Add pre/post auto-negotiation phy hooks
  pppoe: check sockaddr length in pppoe_connect()
  l2tp: check sockaddr length in pppol2tp_connect()
  net: phy: marvell: clear wol event before setting it
  ipv6: add RTA_TABLE and RTA_PREFSRC to rtm_ipv6_policy
  bonding: do not set slave_dev npinfo before slave_enable_netpoll in bond_enslave
  tcp: don't read out-of-bounds opsize
  ibmvnic: Clean actual number of RX or TX pools
  ...

1 files changed, 46 insertions, 34 deletions

diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index 83ce229f4eb7..63036d9bf3e6 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -3999,29 +3999,6 @@ static void efx_ef10_prepare_flr(struct efx_nic *efx)
 	atomic_set(&efx->active_queues, 0);
 }
 
-static bool efx_ef10_filter_equal(const struct efx_filter_spec *left,
-				  const struct efx_filter_spec *right)
-{
-	if ((left->match_flags ^ right->match_flags) |
-	    ((left->flags ^ right->flags) &
-	     (EFX_FILTER_FLAG_RX | EFX_FILTER_FLAG_TX)))
-		return false;
-
-	return memcmp(&left->outer_vid, &right->outer_vid,
-		      sizeof(struct efx_filter_spec) -
-		      offsetof(struct efx_filter_spec, outer_vid)) == 0;
-}
-
-static unsigned int efx_ef10_filter_hash(const struct efx_filter_spec *spec)
-{
-	BUILD_BUG_ON(offsetof(struct efx_filter_spec, outer_vid) & 3);
-	return jhash2((const u32 *)&spec->outer_vid,
-		      (sizeof(struct efx_filter_spec) -
-		       offsetof(struct efx_filter_spec, outer_vid)) / 4,
-		      0);
-	/* XXX should we randomise the initval? */
-}
-
 /* Decide whether a filter should be exclusive or else should allow
  * delivery to additional recipients.  Currently we decide that
  * filters for specific local unicast MAC and IP addresses are
@@ -4346,7 +4323,7 @@ static s32 efx_ef10_filter_insert(struct efx_nic *efx,
 		goto out_unlock;
 	match_pri = rc;
 
-	hash = efx_ef10_filter_hash(spec);
+	hash = efx_filter_spec_hash(spec);
 	is_mc_recip = efx_filter_is_mc_recipient(spec);
 	if (is_mc_recip)
 		bitmap_zero(mc_rem_map, EFX_EF10_FILTER_SEARCH_LIMIT);
@@ -4378,7 +4355,7 @@ static s32 efx_ef10_filter_insert(struct efx_nic *efx,
 		if (!saved_spec) {
 			if (ins_index < 0)
 				ins_index = i;
-		} else if (efx_ef10_filter_equal(spec, saved_spec)) {
+		} else if (efx_filter_spec_equal(spec, saved_spec)) {
 			if (spec->priority < saved_spec->priority &&
 			    spec->priority != EFX_FILTER_PRI_AUTO) {
 				rc = -EPERM;
@@ -4762,27 +4739,62 @@ static s32 efx_ef10_filter_get_rx_ids(struct efx_nic *efx,
 static bool efx_ef10_filter_rfs_expire_one(struct efx_nic *efx, u32 flow_id,
 					   unsigned int filter_idx)
 {
+	struct efx_filter_spec *spec, saved_spec;
 	struct efx_ef10_filter_table *table;
-	struct efx_filter_spec *spec;
-	bool ret;
+	struct efx_arfs_rule *rule = NULL;
+	bool ret = true, force = false;
+	u16 arfs_id;
 
 	down_read(&efx->filter_sem);
 	table = efx->filter_state;
 	down_write(&table->lock);
 	spec = efx_ef10_filter_entry_spec(table, filter_idx);
 
-	if (!spec || spec->priority != EFX_FILTER_PRI_HINT) {
-		ret = true;
+	if (!spec || spec->priority != EFX_FILTER_PRI_HINT)
 		goto out_unlock;
-	}
 
-	if (!rps_may_expire_flow(efx->net_dev, spec->dmaq_id, flow_id, 0)) {
-		ret = false;
-		goto out_unlock;
+	spin_lock_bh(&efx->rps_hash_lock);
+	if (!efx->rps_hash_table) {
+		/* In the absence of the table, we always return 0 to ARFS. */
+		arfs_id = 0;
+	} else {
+		rule = efx_rps_hash_find(efx, spec);
+		if (!rule)
+			/* ARFS table doesn't know of this filter, so remove it */
+			goto expire;
+		arfs_id = rule->arfs_id;
+		ret = efx_rps_check_rule(rule, filter_idx, &force);
+		if (force)
+			goto expire;
+		if (!ret) {
+			spin_unlock_bh(&efx->rps_hash_lock);
+			goto out_unlock;
+		}
 	}
-
+	if (!rps_may_expire_flow(efx->net_dev, spec->dmaq_id, flow_id, arfs_id))
+		ret = false;
+	else if (rule)
+		rule->filter_id = EFX_ARFS_FILTER_ID_REMOVING;
+expire:
+	saved_spec = *spec; /* remove operation will kfree spec */
+	spin_unlock_bh(&efx->rps_hash_lock);
+	/* At this point (since we dropped the lock), another thread might queue
+	 * up a fresh insertion request (but the actual insertion will be held
+	 * up by our possession of the filter table lock).  In that case, it
+	 * will set rule->filter_id to EFX_ARFS_FILTER_ID_PENDING, meaning that
+	 * the rule is not removed by efx_rps_hash_del() below.
+	 */
 	ret = efx_ef10_filter_remove_internal(efx, 1U << spec->priority,
 					      filter_idx, true) == 0;
+	/* While we can't safely dereference rule (we dropped the lock), we can
+	 * still test it for NULL.
+	 */
+	if (ret && rule) {
+		/* Expiring, so remove entry from ARFS table */
+		spin_lock_bh(&efx->rps_hash_lock);
+		efx_rps_hash_del(efx, &saved_spec);
+		spin_unlock_bh(&efx->rps_hash_lock);
+	}
 out_unlock:
 	up_write(&table->lock);
 	up_read(&efx->filter_sem);