From: Paul Blakey <paulb@mellanox.com>
To: Paul Blakey <paulb@mellanox.com>,
Saeed Mahameed <saeedm@mellanox.com>,
Oz Shlomo <ozsh@mellanox.com>,
Jakub Kicinski <jakub.kicinski@netronome.com>,
Vlad Buslov <vladbu@mellanox.com>,
David Miller <davem@davemloft.net>,
"netdev@vger.kernel.org" <netdev@vger.kernel.org>,
Jiri Pirko <jiri@resnulli.us>, Roi Dayan <roid@mellanox.com>
Subject: [PATCH net-next-mlx5 v2 07/13] net/mlx5: E-Switch, Restore chain id on miss
Date: Wed, 22 Jan 2020 15:52:52 +0200 [thread overview]
Message-ID: <1579701178-24624-8-git-send-email-paulb@mellanox.com> (raw)
In-Reply-To: <1579701178-24624-1-git-send-email-paulb@mellanox.com>
Chain ids are mapped to the lower part of reg C, and after loopback
are copied to to CQE via a restore rule's flow_tag.
To let tc continue in the correct chain, we find the corresponding
chain id in the eswitch chain id <-> reg C mapping, and set the SKB's
tc extension chain to it.
That tells tc to continue processing from this set chain.
Signed-off-by: Paul Blakey <paulb@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Oz Shlomo <ozsh@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 6 ++++
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 43 +++++++++++++++++++++++++
drivers/net/ethernet/mellanox/mlx5/core/en_tc.h | 2 ++
3 files changed, 51 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index ad84a55..4402a53 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -1223,6 +1223,9 @@ void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
if (rep->vlan && skb_vlan_tag_present(skb))
skb_vlan_pop(skb);
+ if (!mlx5e_tc_rep_update_skb(cqe, skb))
+ goto free_wqe;
+
napi_gro_receive(rq->cq.napi, skb);
free_wqe:
@@ -1273,6 +1276,9 @@ void mlx5e_handle_rx_cqe_mpwrq_rep(struct mlx5e_rq *rq,
mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
+ if (!mlx5e_tc_rep_update_skb(cqe, skb))
+ goto mpwrq_cqe_out;
+
napi_gro_receive(rq->cq.napi, skb);
mpwrq_cqe_out:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 427432f..f8a3b9c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -4290,3 +4290,46 @@ void mlx5e_tc_reoffload_flows_work(struct work_struct *work)
}
mutex_unlock(&rpriv->unready_flows_lock);
}
+
+bool mlx5e_tc_rep_update_skb(struct mlx5_cqe64 *cqe,
+ struct sk_buff *skb)
+{
+#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
+ struct tc_skb_ext *tc_skb_ext;
+ struct mlx5_eswitch *esw;
+ struct mlx5e_priv *priv;
+ u32 chain = 0, reg_c0;
+ int err;
+
+ reg_c0 = (be32_to_cpu(cqe->sop_drop_qpn) & MLX5E_TC_FLOW_ID_MASK);
+ if (reg_c0 == MLX5_FS_DEFAULT_FLOW_TAG)
+ reg_c0 = 0;
+
+ if (!reg_c0)
+ return true;
+
+ priv = netdev_priv(skb->dev);
+ esw = priv->mdev->priv.eswitch;
+
+ err = mlx5_eswitch_get_chain_for_tag(esw, reg_c0, &chain);
+ if (err) {
+ netdev_dbg(priv->netdev,
+ "Couldn't find chain for chain tag: %d, err: %d\n",
+ reg_c0, err);
+ return false;
+ }
+
+ if (!chain)
+ return true;
+
+ tc_skb_ext = skb_ext_add(skb, TC_SKB_EXT);
+ if (!tc_skb_ext) {
+ WARN_ON_ONCE(1);
+ return false;
+ }
+
+ tc_skb_ext->chain = chain;
+#endif /* CONFIG_NET_TC_SKB_EXT */
+
+ return true;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
index e2dbbae..9d5fcf6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
@@ -106,6 +106,8 @@ struct mlx5e_tc_attr_to_reg_mapping {
bool mlx5e_is_valid_eswitch_fwd_dev(struct mlx5e_priv *priv,
struct net_device *out_dev);
+bool mlx5e_tc_rep_update_skb(struct mlx5_cqe64 *cqe, struct sk_buff *skb);
+
#else /* CONFIG_MLX5_ESWITCH */
static inline int mlx5e_tc_nic_init(struct mlx5e_priv *priv) { return 0; }
static inline void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv) {}
--
1.8.3.1
next prev parent reply other threads:[~2020-01-22 13:53 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-01-22 13:52 [PATCH net-next v2 00/13] Handle multi chain hardware misses Paul Blakey
2020-01-22 13:52 ` [PATCH net-next v2 01/13] net: sched: support skb chain ext in tc classification path Paul Blakey
2020-01-22 15:29 ` Jakub Kicinski
2020-01-23 7:06 ` Jiri Pirko
2020-01-24 8:46 ` Paul Blakey
2020-01-22 13:52 ` [PATCH net-next-mlx5 v2 02/13] net/mlx5: Add new driver lib for mappings unique ids to data Paul Blakey
2020-01-22 13:52 ` [PATCH net-next-mlx5 v2 03/13] net/mlx5: E-Switch, Move source port on reg_c0 to the upper 16 bits Paul Blakey
2020-01-22 13:52 ` [PATCH net-next-mlx5 v2 04/13] net/mlx5: E-Switch, Get reg_c0 value on CQE Paul Blakey
2020-01-22 13:52 ` [PATCH net-next-mlx5 v2 05/13] net/mlx5: E-Switch, Mark miss packets with new chain id mapping Paul Blakey
2020-01-22 13:52 ` [PATCH net-next-mlx5 v2 06/13] net/mlx5e: Rx, Split rep rx mpwqe handler from nic Paul Blakey
2020-01-22 13:52 ` Paul Blakey [this message]
2020-01-22 13:52 ` [PATCH net-next-mlx5 v2 08/13] net/mlx5e: Allow re-allocating mod header actions Paul Blakey
2020-01-22 13:52 ` [PATCH net-next-mlx5 v2 09/13] net/mlx5e: Move tc tunnel parsing logic with the rest at tc_tun module Paul Blakey
2020-01-22 13:52 ` [PATCH net-next-mlx5 v2 10/13] net/mlx5e: Disallow inserting vxlan/vlan egress rules without decap/pop Paul Blakey
2020-01-22 13:52 ` [PATCH net-next-mlx5 v2 11/13] net/mlx5e: Support inner header rewrite with goto action Paul Blakey
2020-01-22 13:52 ` [PATCH net-next-mlx5 v2 12/13] net/mlx5: E-Switch, Get reg_c1 value on miss Paul Blakey
2020-01-22 13:52 ` [PATCH net-next-mlx5 v2 13/13] net/mlx5e: Restore tunnel metadata " Paul Blakey
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1579701178-24624-8-git-send-email-paulb@mellanox.com \
--to=paulb@mellanox.com \
--cc=davem@davemloft.net \
--cc=jakub.kicinski@netronome.com \
--cc=jiri@resnulli.us \
--cc=netdev@vger.kernel.org \
--cc=ozsh@mellanox.com \
--cc=roid@mellanox.com \
--cc=saeedm@mellanox.com \
--cc=vladbu@mellanox.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).