Merge tag 'mlx5-fixes-2022-02-01' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5 fixes 2022-02-01

This series provides bug fixes to mlx5 driver.
Please pull and let me know if there is any problem.

Sorry about the long series, but I had to move the top two patches from
net-next to net to help avoiding a build break when kspp branch is merged
into linus-next on next merge window.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/mellanox/mlx5/core/en.h

@@ -224,7 +224,7 @@ static inline int mlx5e_get_max_num_channels(struct mlx5_core_dev *mdev)
 struct mlx5e_tx_wqe {
 	struct mlx5_wqe_ctrl_seg ctrl;
 	struct mlx5_wqe_eth_seg  eth;
-	struct mlx5_wqe_data_seg data[0];
+	struct mlx5_wqe_data_seg data[];
 };
 
 struct mlx5e_rx_wqe_ll {
@@ -241,8 +241,8 @@ struct mlx5e_umr_wqe {
 	struct mlx5_wqe_umr_ctrl_seg   uctrl;
 	struct mlx5_mkey_seg           mkc;
 	union {
-		struct mlx5_mtt inline_mtts[0];
-		struct mlx5_klm inline_klms[0];
+		DECLARE_FLEX_ARRAY(struct mlx5_mtt, inline_mtts);
+		DECLARE_FLEX_ARRAY(struct mlx5_klm, inline_klms);
 	};
 };
 

drivers/net/ethernet/mellanox/mlx5/core/en/qos.c

@@ -570,7 +570,8 @@ static int mlx5e_htb_convert_rate(struct mlx5e_priv *priv, u64 rate,
 
 static void mlx5e_htb_convert_ceil(struct mlx5e_priv *priv, u64 ceil, u32 *max_average_bw)
 {
-	*max_average_bw = div_u64(ceil, BYTES_IN_MBIT);
+	/* Hardware treats 0 as "unlimited", set at least 1. */
+	*max_average_bw = max_t(u32, div_u64(ceil, BYTES_IN_MBIT), 1);
 
 	qos_dbg(priv->mdev, "Convert: ceil %llu -> max_average_bw %u\n",
 		ceil, *max_average_bw);

drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c

@@ -183,18 +183,7 @@ void mlx5e_rep_bond_unslave(struct mlx5_eswitch *esw,
 
 static bool mlx5e_rep_is_lag_netdev(struct net_device *netdev)
 {
-	struct mlx5e_rep_priv *rpriv;
-	struct mlx5e_priv *priv;
-
-	/* A given netdev is not a representor or not a slave of LAG configuration */
-	if (!mlx5e_eswitch_rep(netdev) || !netif_is_lag_port(netdev))
-		return false;
-
-	priv = netdev_priv(netdev);
-	rpriv = priv->ppriv;
-
-	/* Egress acl forward to vport is supported only non-uplink representor */
-	return rpriv->rep->vport != MLX5_VPORT_UPLINK;
+	return netif_is_lag_port(netdev) && mlx5e_eswitch_vf_rep(netdev);
 }
 
 static void mlx5e_rep_changelowerstate_event(struct net_device *netdev, void *ptr)
@@ -210,9 +199,6 @@ static void mlx5e_rep_changelowerstate_event(struct net_device *netdev, void *pt
 	u16 fwd_vport_num;
 	int err;
 
-	if (!mlx5e_rep_is_lag_netdev(netdev))
-		return;
-
 	info = ptr;
 	lag_info = info->lower_state_info;
 	/* This is not an event of a representor becoming active slave */
@@ -266,9 +252,6 @@ static void mlx5e_rep_changeupper_event(struct net_device *netdev, void *ptr)
 	struct net_device *lag_dev;
 	struct mlx5e_priv *priv;
 
-	if (!mlx5e_rep_is_lag_netdev(netdev))
-		return;
-
 	priv = netdev_priv(netdev);
 	rpriv = priv->ppriv;
 	lag_dev = info->upper_dev;
@@ -293,6 +276,19 @@ static int mlx5e_rep_esw_bond_netevent(struct notifier_block *nb,
 				       unsigned long event, void *ptr)
 {
 	struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
+	struct mlx5e_rep_priv *rpriv;
+	struct mlx5e_rep_bond *bond;
+	struct mlx5e_priv *priv;
+
+	if (!mlx5e_rep_is_lag_netdev(netdev))
+		return NOTIFY_DONE;
+
+	bond = container_of(nb, struct mlx5e_rep_bond, nb);
+	priv = netdev_priv(netdev);
+	rpriv = mlx5_eswitch_get_uplink_priv(priv->mdev->priv.eswitch, REP_ETH);
+	/* Verify VF representor is on the same device of the bond handling the netevent. */
+	if (rpriv->uplink_priv.bond != bond)
+		return NOTIFY_DONE;
 
 	switch (event) {
 	case NETDEV_CHANGELOWERSTATE:

drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c

@@ -491,7 +491,7 @@ void mlx5e_rep_bridge_init(struct mlx5e_priv *priv)
 	}
 
 	br_offloads->netdev_nb.notifier_call = mlx5_esw_bridge_switchdev_port_event;
-	err = register_netdevice_notifier(&br_offloads->netdev_nb);
+	err = register_netdevice_notifier_net(&init_net, &br_offloads->netdev_nb);
 	if (err) {
 		esw_warn(mdev, "Failed to register bridge offloads netdevice notifier (err=%d)\n",
 			 err);
@@ -509,7 +509,9 @@ void mlx5e_rep_bridge_init(struct mlx5e_priv *priv)
 err_register_swdev:
 	destroy_workqueue(br_offloads->wq);
 err_alloc_wq:
+	rtnl_lock();
 	mlx5_esw_bridge_cleanup(esw);
+	rtnl_unlock();
 }
 
 void mlx5e_rep_bridge_cleanup(struct mlx5e_priv *priv)
@@ -524,7 +526,7 @@ void mlx5e_rep_bridge_cleanup(struct mlx5e_priv *priv)
 		return;
 
 	cancel_delayed_work_sync(&br_offloads->update_work);
-	unregister_netdevice_notifier(&br_offloads->netdev_nb);
+	unregister_netdevice_notifier_net(&init_net, &br_offloads->netdev_nb);
 	unregister_switchdev_blocking_notifier(&br_offloads->nb_blk);
 	unregister_switchdev_notifier(&br_offloads->nb);
 	destroy_workqueue(br_offloads->wq);

drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h

@@ -167,6 +167,11 @@ static inline u16 mlx5e_txqsq_get_next_pi(struct mlx5e_txqsq *sq, u16 size)
 	return pi;
 }
 
+static inline u16 mlx5e_shampo_get_cqe_header_index(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
+{
+	return be16_to_cpu(cqe->shampo.header_entry_index) & (rq->mpwqe.shampo->hd_per_wq - 1);
+}
+
 struct mlx5e_shampo_umr {
 	u16 len;
 };

drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c

@@ -341,8 +341,10 @@ mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd,
 
 	/* copy the inline part if required */
 	if (sq->min_inline_mode != MLX5_INLINE_MODE_NONE) {
-		memcpy(eseg->inline_hdr.start, xdptxd->data, MLX5E_XDP_MIN_INLINE);
+		memcpy(eseg->inline_hdr.start, xdptxd->data, sizeof(eseg->inline_hdr.start));
 		eseg->inline_hdr.sz = cpu_to_be16(MLX5E_XDP_MIN_INLINE);
+		memcpy(dseg, xdptxd->data + sizeof(eseg->inline_hdr.start),
+		       MLX5E_XDP_MIN_INLINE - sizeof(eseg->inline_hdr.start));
 		dma_len  -= MLX5E_XDP_MIN_INLINE;
 		dma_addr += MLX5E_XDP_MIN_INLINE;
 		dseg++;

drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c

@@ -157,11 +157,20 @@ static void mlx5e_ipsec_set_swp(struct sk_buff *skb,
 	/* Tunnel mode */
 	if (mode == XFRM_MODE_TUNNEL) {
 		eseg->swp_inner_l3_offset = skb_inner_network_offset(skb) / 2;
-		eseg->swp_inner_l4_offset = skb_inner_transport_offset(skb) / 2;
 		if (xo->proto == IPPROTO_IPV6)
 			eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L3_IPV6;
-		if (inner_ip_hdr(skb)->protocol == IPPROTO_UDP)
+
+		switch (xo->inner_ipproto) {
+		case IPPROTO_UDP:
 			eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L4_UDP;
+			fallthrough;
+		case IPPROTO_TCP:
+			/* IP | ESP | IP | [TCP | UDP] */
+			eseg->swp_inner_l4_offset = skb_inner_transport_offset(skb) / 2;
+			break;
+		default:
+			break;
+		}
 		return;
 	}
 

drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h

@@ -131,14 +131,17 @@ static inline bool
 mlx5e_ipsec_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 				  struct mlx5_wqe_eth_seg *eseg)
 {
-	struct xfrm_offload *xo = xfrm_offload(skb);
+	u8 inner_ipproto;
 
 	if (!mlx5e_ipsec_eseg_meta(eseg))
 		return false;
 
 	eseg->cs_flags = MLX5_ETH_WQE_L3_CSUM;
-	if (xo->inner_ipproto) {
-		eseg->cs_flags |= MLX5_ETH_WQE_L4_INNER_CSUM | MLX5_ETH_WQE_L3_INNER_CSUM;
+	inner_ipproto = xfrm_offload(skb)->inner_ipproto;
+	if (inner_ipproto) {
+		eseg->cs_flags |= MLX5_ETH_WQE_L3_INNER_CSUM;
+		if (inner_ipproto == IPPROTO_TCP || inner_ipproto == IPPROTO_UDP)
+			eseg->cs_flags |= MLX5_ETH_WQE_L4_INNER_CSUM;
 	} else if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) {
 		eseg->cs_flags |= MLX5_ETH_WQE_L4_CSUM;
 		sq->stats->csum_partial_inner++;

drivers/net/ethernet/mellanox/mlx5/core/en_rx.c

@@ -1117,7 +1117,7 @@ static void mlx5e_shampo_update_ipv6_udp_hdr(struct mlx5e_rq *rq, struct ipv6hdr
 static void mlx5e_shampo_update_fin_psh_flags(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
 					      struct tcphdr *skb_tcp_hd)
 {
-	u16 header_index = be16_to_cpu(cqe->shampo.header_entry_index);
+	u16 header_index = mlx5e_shampo_get_cqe_header_index(rq, cqe);
 	struct tcphdr *last_tcp_hd;
 	void *last_hd_addr;
 
@@ -1871,7 +1871,7 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 	return skb;
 }
 
-static void
+static struct sk_buff *
 mlx5e_skb_from_cqe_shampo(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 			  struct mlx5_cqe64 *cqe, u16 header_index)
 {
@@ -1895,7 +1895,7 @@ mlx5e_skb_from_cqe_shampo(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 		skb = mlx5e_build_linear_skb(rq, hdr, frag_size, rx_headroom, head_size);
 
 		if (unlikely(!skb))
-			return;
+			return NULL;
 
 		/* queue up for recycling/reuse */
 		page_ref_inc(head->page);
@@ -1907,7 +1907,7 @@ mlx5e_skb_from_cqe_shampo(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 				     ALIGN(head_size, sizeof(long)));
 		if (unlikely(!skb)) {
 			rq->stats->buff_alloc_err++;
-			return;
+			return NULL;
 		}
 
 		prefetchw(skb->data);
@@ -1918,9 +1918,7 @@ mlx5e_skb_from_cqe_shampo(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 		skb->tail += head_size;
 		skb->len  += head_size;
 	}
-	rq->hw_gro_data->skb = skb;
-	NAPI_GRO_CB(skb)->count = 1;
-	skb_shinfo(skb)->gso_size = mpwrq_get_cqe_byte_cnt(cqe) - head_size;
+	return skb;
 }
 
 static void
@@ -1973,13 +1971,14 @@ mlx5e_free_rx_shampo_hd_entry(struct mlx5e_rq *rq, u16 header_index)
 static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 {
 	u16 data_bcnt		= mpwrq_get_cqe_byte_cnt(cqe) - cqe->shampo.header_size;
-	u16 header_index	= be16_to_cpu(cqe->shampo.header_entry_index);
+	u16 header_index	= mlx5e_shampo_get_cqe_header_index(rq, cqe);
 	u32 wqe_offset		= be32_to_cpu(cqe->shampo.data_offset);
 	u16 cstrides		= mpwrq_get_cqe_consumed_strides(cqe);
 	u32 data_offset		= wqe_offset & (PAGE_SIZE - 1);
 	u32 cqe_bcnt		= mpwrq_get_cqe_byte_cnt(cqe);
 	u16 wqe_id		= be16_to_cpu(cqe->wqe_id);
 	u32 page_idx		= wqe_offset >> PAGE_SHIFT;
+	u16 head_size		= cqe->shampo.header_size;
 	struct sk_buff **skb	= &rq->hw_gro_data->skb;
 	bool flush		= cqe->shampo.flush;
 	bool match		= cqe->shampo.match;
@@ -2011,9 +2010,16 @@ static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cq
 	}
 
 	if (!*skb) {
-		mlx5e_skb_from_cqe_shampo(rq, wi, cqe, header_index);
+		if (likely(head_size))
+			*skb = mlx5e_skb_from_cqe_shampo(rq, wi, cqe, header_index);
+		else
+			*skb = mlx5e_skb_from_cqe_mpwrq_nonlinear(rq, wi, cqe_bcnt, data_offset,
+								  page_idx);
 		if (unlikely(!*skb))
 			goto free_hd_entry;
+
+		NAPI_GRO_CB(*skb)->count = 1;
+		skb_shinfo(*skb)->gso_size = cqe_bcnt - head_size;
 	} else {
 		NAPI_GRO_CB(*skb)->count++;
 		if (NAPI_GRO_CB(*skb)->count == 2 &&
@@ -2027,8 +2033,10 @@ static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cq
 		}
 	}
 
+	if (likely(head_size)) {
 		di = &wi->umr.dma_info[page_idx];
 		mlx5e_fill_skb_data(*skb, rq, di, data_bcnt, data_offset);
+	}
 
 	mlx5e_shampo_complete_rx_cqe(rq, cqe, cqe_bcnt, *skb);
 	if (flush)

drivers/net/ethernet/mellanox/mlx5/core/en_tc.c

@@ -1414,7 +1414,8 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 		if (err)
 			goto err_out;
 
-		if (!attr->chain && esw_attr->int_port) {
+		if (!attr->chain && esw_attr->int_port &&
+		    attr->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) {
 			/* If decap route device is internal port, change the
 			 * source vport value in reg_c0 back to uplink just in
 			 * case the rule performs goto chain > 0. If we have a miss
@@ -3191,6 +3192,18 @@ actions_match_supported(struct mlx5e_priv *priv,
 		return false;
 	}
 
+	if (!(~actions &
+	      (MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_DROP))) {
+		NL_SET_ERR_MSG_MOD(extack, "Rule cannot support forward+drop action");
+		return false;
+	}
+
+	if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR &&
+	    actions & MLX5_FLOW_CONTEXT_ACTION_DROP) {
+		NL_SET_ERR_MSG_MOD(extack, "Drop with modify header action is not supported");
+		return false;
+	}
+
 	if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR &&
 	    !modify_header_match_supported(priv, &parse_attr->spec, flow_action,
 					   actions, ct_flow, ct_clear, extack))

drivers/net/ethernet/mellanox/mlx5/core/en_tx.c

@@ -208,7 +208,7 @@ static inline void mlx5e_insert_vlan(void *start, struct sk_buff *skb, u16 ihs)
 	int cpy1_sz = 2 * ETH_ALEN;
 	int cpy2_sz = ihs - cpy1_sz;
 
-	memcpy(vhdr, skb->data, cpy1_sz);
+	memcpy(&vhdr->addrs, skb->data, cpy1_sz);
 	vhdr->h_vlan_proto = skb->vlan_proto;
 	vhdr->h_vlan_TCI = cpu_to_be16(skb_vlan_tag_get(skb));
 	memcpy(&vhdr->h_vlan_encapsulated_proto, skb->data + cpy1_sz, cpy2_sz);

drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c

@@ -1574,6 +1574,8 @@ struct mlx5_esw_bridge_offloads *mlx5_esw_bridge_init(struct mlx5_eswitch *esw)
 {
 	struct mlx5_esw_bridge_offloads *br_offloads;
 
+	ASSERT_RTNL();
+
 	br_offloads = kvzalloc(sizeof(*br_offloads), GFP_KERNEL);
 	if (!br_offloads)
 		return ERR_PTR(-ENOMEM);
@@ -1590,6 +1592,8 @@ void mlx5_esw_bridge_cleanup(struct mlx5_eswitch *esw)
 {
 	struct mlx5_esw_bridge_offloads *br_offloads = esw->br_offloads;
 
+	ASSERT_RTNL();
+
 	if (!br_offloads)
 		return;
 

drivers/net/ethernet/mellanox/mlx5/core/esw/diag/bridge_tracepoint.h

@@ -21,7 +21,7 @@ DECLARE_EVENT_CLASS(mlx5_esw_bridge_fdb_template,
 			    __field(unsigned int, used)
 			    ),
 		    TP_fast_assign(
-			    strncpy(__entry->dev_name,
+			    strscpy(__entry->dev_name,
 				    netdev_name(fdb->dev),
 				    IFNAMSIZ);
 			    memcpy(__entry->addr, fdb->key.addr, ETH_ALEN);

drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c

@@ -132,7 +132,7 @@ static void mlx5_stop_sync_reset_poll(struct mlx5_core_dev *dev)
 {
 	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
 
-	del_timer(&fw_reset->timer);
+	del_timer_sync(&fw_reset->timer);
 }
 
 static void mlx5_sync_reset_clear_reset_requested(struct mlx5_core_dev *dev, bool poll_health)

drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c

@@ -121,12 +121,13 @@ u32 mlx5_chains_get_nf_ft_chain(struct mlx5_fs_chains *chains)
 
 u32 mlx5_chains_get_prio_range(struct mlx5_fs_chains *chains)
 {
-	if (!mlx5_chains_prios_supported(chains))
-		return 1;
-
 	if (mlx5_chains_ignore_flow_level_supported(chains))
 		return UINT_MAX;
 
+	if (!chains->dev->priv.eswitch ||
+	    chains->dev->priv.eswitch->mode != MLX5_ESWITCH_OFFLOADS)
+		return 1;
+
 	/* We should get here only for eswitch case */
 	return FDB_TC_MAX_PRIO;
 }
@@ -211,7 +212,7 @@ static int
 create_chain_restore(struct fs_chain *chain)
 {
 	struct mlx5_eswitch *esw = chain->chains->dev->priv.eswitch;
-	char modact[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)];
+	u8 modact[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {};
 	struct mlx5_fs_chains *chains = chain->chains;
 	enum mlx5e_tc_attr_to_reg chain_to_reg;
 	struct mlx5_modify_hdr *mod_hdr;

drivers/net/ethernet/mellanox/mlx5/core/port.c

@@ -406,23 +406,24 @@ int mlx5_query_module_eeprom(struct mlx5_core_dev *dev,
 
 	switch (module_id) {
 	case MLX5_MODULE_ID_SFP:
-		mlx5_sfp_eeprom_params_set(&query.i2c_address, &query.page, &query.offset);
+		mlx5_sfp_eeprom_params_set(&query.i2c_address, &query.page, &offset);
 		break;
 	case MLX5_MODULE_ID_QSFP:
 	case MLX5_MODULE_ID_QSFP_PLUS:
 	case MLX5_MODULE_ID_QSFP28:
-		mlx5_qsfp_eeprom_params_set(&query.i2c_address, &query.page, &query.offset);
+		mlx5_qsfp_eeprom_params_set(&query.i2c_address, &query.page, &offset);
 		break;
 	default:
 		mlx5_core_err(dev, "Module ID not recognized: 0x%x\n", module_id);
 		return -EINVAL;
 	}
 
-	if (query.offset + size > MLX5_EEPROM_PAGE_LENGTH)
+	if (offset + size > MLX5_EEPROM_PAGE_LENGTH)
 		/* Cross pages read, read until offset 256 in low page */
-		size -= offset + size - MLX5_EEPROM_PAGE_LENGTH;
+		size = MLX5_EEPROM_PAGE_LENGTH - offset;
 
 	query.size = size;
+	query.offset = offset;
 
 	return mlx5_query_mcia(dev, &query, data);
 }

include/linux/if_vlan.h

@@ -46,8 +46,10 @@ struct vlan_hdr {
  *	@h_vlan_encapsulated_proto: packet type ID or len
  */
 struct vlan_ethhdr {
+	struct_group(addrs,
 		unsigned char	h_dest[ETH_ALEN];
 		unsigned char	h_source[ETH_ALEN];
+	);
 	__be16		h_vlan_proto;
 	__be16		h_vlan_TCI;
 	__be16		h_vlan_encapsulated_proto;