From e8c8b53ccaff568fef4c13a6ccaf08bf241aa01a Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Mon, 3 Dec 2018 22:14:04 -0800 Subject: [PATCH 1/4] net/mlx5e: Force CHECKSUM_UNNECESSARY for short ethernet frames When an ethernet frame is padded to meet the minimum ethernet frame size, the padding octets are not covered by the hardware checksum. Fortunately the padding octets are usually zero's, which don't affect checksum. However, we have a switch which pads non-zero octets, this causes kernel hardware checksum fault repeatedly. Prior to: commit '88078d98d1bb ("net: pskb_trim_rcsum() and CHECKSUM_COMPLETE ...")' skb checksum was forced to be CHECKSUM_NONE when padding is detected. After it, we need to keep skb->csum updated, like what we do for RXFCS. However, fixing up CHECKSUM_COMPLETE requires to verify and parse IP headers, it is not worthy the effort as the packets are so small that CHECKSUM_COMPLETE can't save anything. Fixes: 88078d98d1bb ("net: pskb_trim_rcsum() and CHECKSUM_COMPLETE are friends"), Cc: Eric Dumazet Cc: Tariq Toukan Cc: Nikola Ciprich Signed-off-by: Cong Wang Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 1d0bb5ff8c26..f86e4804e83e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -732,6 +732,8 @@ static u8 get_ip_proto(struct sk_buff *skb, int network_depth, __be16 proto) ((struct ipv6hdr *)ip_p)->nexthdr; } +#define short_frame(size) ((size) <= ETH_ZLEN + ETH_FCS_LEN) + static inline void mlx5e_handle_csum(struct net_device *netdev, struct mlx5_cqe64 *cqe, struct mlx5e_rq *rq, @@ -754,6 +756,17 @@ static inline void mlx5e_handle_csum(struct net_device *netdev, if (unlikely(test_bit(MLX5E_RQ_STATE_NO_CSUM_COMPLETE, &rq->state))) goto csum_unnecessary; + /* CQE csum doesn't cover padding octets in short ethernet + * frames. And the pad field is appended prior to calculating + * and appending the FCS field. + * + * Detecting these padded frames requires to verify and parse + * IP headers, so we simply force all those small frames to be + * CHECKSUM_UNNECESSARY even if they are not padded. + */ + if (short_frame(skb->len)) + goto csum_unnecessary; + if (likely(is_last_ethertype_ip(skb, &network_depth, &proto))) { if (unlikely(get_ip_proto(skb, network_depth, proto) == IPPROTO_SCTP)) goto csum_unnecessary; From 2eb1e42551a8128d9182480dfaea52fa861e26e8 Mon Sep 17 00:00:00 2001 From: Shay Agroskin Date: Sun, 9 Dec 2018 12:00:13 +0200 Subject: [PATCH 2/4] net/mlx5e: Fix wrong error code return on FEC query failure Advertised and configured FEC query failure resulted in printing wrong error code. Fixes: 6cfa94605091 ("net/mlx5e: Ethtool driver callback for query/set FEC policy") Signed-off-by: Shay Agroskin Reported-by: Or Gerlitz Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index c9df08133718..3bbccead2f63 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -844,9 +844,12 @@ int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv, ethtool_link_ksettings_add_link_mode(link_ksettings, supported, Autoneg); - if (get_fec_supported_advertised(mdev, link_ksettings)) + err = get_fec_supported_advertised(mdev, link_ksettings); + if (err) { netdev_dbg(priv->netdev, "%s: FEC caps query failed: %d\n", __func__, err); + err = 0; /* don't fail caps query because of FEC error */ + } if (!an_disable_admin) ethtool_link_ksettings_add_link_mode(link_ksettings, From 7fdc1adc52d3975740547a78c2df329bb207f15d Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Thu, 8 Nov 2018 12:06:53 +0200 Subject: [PATCH 3/4] net/mlx5e: Fix wrong (zero) TX drop counter indication for representor For representors, the TX dropped counter is not folded from the per-ring counters. Fix it. Signed-off-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 96cc0c6a4014..c9a7081a5329 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -179,6 +179,7 @@ static void mlx5e_rep_update_sw_counters(struct mlx5e_priv *priv) s->tx_packets += sq_stats->packets; s->tx_bytes += sq_stats->bytes; + s->tx_queue_dropped += sq_stats->dropped; } } } From 25f2d0e7791e71cc89c58a7c2231768ad200764b Mon Sep 17 00:00:00 2001 From: Eli Britstein Date: Wed, 19 Dec 2018 07:36:51 +0200 Subject: [PATCH 4/4] net/mlx5e: Fix cb_ident duplicate in indirect block register Previously the identifier used for indirect block callback registry and for block rule cb registry (when done via indirect blocks) was the pointer to the tunnel netdev we were interested in receiving updates on. This worked fine if a single PF existed that registered one callback for the tunnel netdev of interest. However, if multiple PFs are in place then the 2nd PF tries to register with the same tunnel netdev identifier. This leads to EEXIST errors and/or incorrect cb deletions. Prevent this conflict by using the rpriv pointer as the identifier for netdev indirect block cb registry, allowing each PF to register a unique callback per tunnel netdev. For block cb registry, the same PF may register multiple cbs to the same block if using TC shared blocks. Instead of the rpriv, use the pointer to the allocated indr_priv data as the identifier here. This means that there can be a unique block callback for each PF/tunnel netdev combo. Fixes: f5bc2c5de101 ("net/mlx5e: Support TC indirect block notifications for eswitch uplink reprs") Signed-off-by: Eli Britstein Reviewed-by: Oz Shlomo Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/en_rep.c | 29 ++++++++++--------- 1 file changed, 16 insertions(+), 13 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index c9a7081a5329..04736212a21c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -58,7 +58,8 @@ struct mlx5e_rep_indr_block_priv { struct list_head list; }; -static void mlx5e_rep_indr_unregister_block(struct net_device *netdev); +static void mlx5e_rep_indr_unregister_block(struct mlx5e_rep_priv *rpriv, + struct net_device *netdev); static void mlx5e_rep_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *drvinfo) @@ -664,7 +665,7 @@ static void mlx5e_rep_indr_clean_block_privs(struct mlx5e_rep_priv *rpriv) struct list_head *head = &rpriv->uplink_priv.tc_indr_block_priv_list; list_for_each_entry_safe(cb_priv, temp, head, list) { - mlx5e_rep_indr_unregister_block(cb_priv->netdev); + mlx5e_rep_indr_unregister_block(rpriv, cb_priv->netdev); kfree(cb_priv); } } @@ -736,7 +737,7 @@ mlx5e_rep_indr_setup_tc_block(struct net_device *netdev, err = tcf_block_cb_register(f->block, mlx5e_rep_indr_setup_block_cb, - netdev, indr_priv, f->extack); + indr_priv, indr_priv, f->extack); if (err) { list_del(&indr_priv->list); kfree(indr_priv); @@ -744,14 +745,15 @@ mlx5e_rep_indr_setup_tc_block(struct net_device *netdev, return err; case TC_BLOCK_UNBIND: + indr_priv = mlx5e_rep_indr_block_priv_lookup(rpriv, netdev); + if (!indr_priv) + return -ENOENT; + tcf_block_cb_unregister(f->block, mlx5e_rep_indr_setup_block_cb, - netdev); - indr_priv = mlx5e_rep_indr_block_priv_lookup(rpriv, netdev); - if (indr_priv) { - list_del(&indr_priv->list); - kfree(indr_priv); - } + indr_priv); + list_del(&indr_priv->list); + kfree(indr_priv); return 0; default: @@ -780,7 +782,7 @@ static int mlx5e_rep_indr_register_block(struct mlx5e_rep_priv *rpriv, err = __tc_indr_block_cb_register(netdev, rpriv, mlx5e_rep_indr_setup_tc_cb, - netdev); + rpriv); if (err) { struct mlx5e_priv *priv = netdev_priv(rpriv->netdev); @@ -790,10 +792,11 @@ static int mlx5e_rep_indr_register_block(struct mlx5e_rep_priv *rpriv, return err; } -static void mlx5e_rep_indr_unregister_block(struct net_device *netdev) +static void mlx5e_rep_indr_unregister_block(struct mlx5e_rep_priv *rpriv, + struct net_device *netdev) { __tc_indr_block_cb_unregister(netdev, mlx5e_rep_indr_setup_tc_cb, - netdev); + rpriv); } static int mlx5e_nic_rep_netdevice_event(struct notifier_block *nb, @@ -812,7 +815,7 @@ static int mlx5e_nic_rep_netdevice_event(struct notifier_block *nb, mlx5e_rep_indr_register_block(rpriv, netdev); break; case NETDEV_UNREGISTER: - mlx5e_rep_indr_unregister_block(netdev); + mlx5e_rep_indr_unregister_block(rpriv, netdev); break; } return NOTIFY_OK;