* [net-next 04/12] net/mlx5e: Tx, Strict the room needed for SQ edge NOPs
From: Saeed Mahameed @ 2019-08-01 19:56 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev@vger.kernel.org, Tariq Toukan, Saeed Mahameed
In-Reply-To: <20190801195620.26180-1-saeedm@mellanox.com>
From: Tariq Toukan <tariqt@mellanox.com>
We use NOPs to populate the WQ fragment edge if the WQE does not fit
in frag, to avoid WQEs crossing a page boundary (or wrap-around the WQ).
The upper bound on the needed number of NOPs is one WQEBB less than
the largest possible WQE, for otherwise the WQE would certainly fit.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
index ddfe19adb3d9..7da22b413a48 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
@@ -6,7 +6,7 @@
#include "en.h"
-#define MLX5E_SQ_NOPS_ROOM MLX5_SEND_WQE_MAX_WQEBBS
+#define MLX5E_SQ_NOPS_ROOM (MLX5_SEND_WQE_MAX_WQEBBS - 1)
#define MLX5E_SQ_STOP_ROOM (MLX5_SEND_WQE_MAX_WQEBBS +\
MLX5E_SQ_NOPS_ROOM)
--
2.21.0
^ permalink raw reply related
* [net-next 01/12] net/mlx5: E-Switch, add ingress rate support
From: Saeed Mahameed @ 2019-08-01 19:56 UTC (permalink / raw)
To: David S. Miller
Cc: netdev@vger.kernel.org, Eli Cohen, Paul Blakey, Saeed Mahameed
In-Reply-To: <20190801195620.26180-1-saeedm@mellanox.com>
From: Eli Cohen <eli@mellanox.com>
Use the scheduling elements to implement ingress rate limiter on an
eswitch ports ingress traffic. Since the ingress of eswitch port is the
egress of VF port, we control eswitch ingress by controlling VF egress.
Configuration is done using the ports' representor net devices.
Please note that burst size configuration is not supported by devices
ConnectX-5 and earlier generations.
Configuration examples:
tc:
tc filter add dev enp59s0f0_0 root protocol ip matchall action police rate 1mbit burst 20k
ovs:
ovs-vsctl set interface eth0 ingress_policing_rate=1000
Signed-off-by: Eli Cohen <eli@mellanox.com>
Reviewed-by: Paul Blakey <paulb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../net/ethernet/mellanox/mlx5/core/en_rep.c | 19 ++++
.../net/ethernet/mellanox/mlx5/core/en_rep.h | 1 +
.../net/ethernet/mellanox/mlx5/core/en_tc.c | 100 ++++++++++++++++++
.../net/ethernet/mellanox/mlx5/core/en_tc.h | 7 ++
.../net/ethernet/mellanox/mlx5/core/eswitch.c | 16 +++
.../net/ethernet/mellanox/mlx5/core/eswitch.h | 2 +
6 files changed, 145 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 6edf0aeb1e26..bf6f4835457e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -1156,6 +1156,23 @@ mlx5e_rep_setup_tc_cls_flower(struct mlx5e_priv *priv,
}
}
+static
+int mlx5e_rep_setup_tc_cls_matchall(struct mlx5e_priv *priv,
+ struct tc_cls_matchall_offload *ma)
+{
+ switch (ma->command) {
+ case TC_CLSMATCHALL_REPLACE:
+ return mlx5e_tc_configure_matchall(priv, ma);
+ case TC_CLSMATCHALL_DESTROY:
+ return mlx5e_tc_delete_matchall(priv, ma);
+ case TC_CLSMATCHALL_STATS:
+ mlx5e_tc_stats_matchall(priv, ma);
+ return 0;
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
static int mlx5e_rep_setup_tc_cb(enum tc_setup_type type, void *type_data,
void *cb_priv)
{
@@ -1165,6 +1182,8 @@ static int mlx5e_rep_setup_tc_cb(enum tc_setup_type type, void *type_data,
switch (type) {
case TC_SETUP_CLSFLOWER:
return mlx5e_rep_setup_tc_cls_flower(priv, type_data, flags);
+ case TC_SETUP_CLSMATCHALL:
+ return mlx5e_rep_setup_tc_cls_matchall(priv, type_data);
default:
return -EOPNOTSUPP;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
index 10fafd5fa17b..43eeebe9c8d2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
@@ -88,6 +88,7 @@ struct mlx5e_rep_priv {
struct mlx5_flow_handle *vport_rx_rule;
struct list_head vport_sqs_list;
struct mlx5_rep_uplink_priv uplink_priv; /* valid for uplink rep */
+ struct rtnl_link_stats64 prev_vf_vport_stats;
struct devlink_port dl_port;
};
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index f3ed028d5017..dc5fc3350b65 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -3638,6 +3638,106 @@ int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv,
return err;
}
+static int apply_police_params(struct mlx5e_priv *priv, u32 rate,
+ struct netlink_ext_ack *extack)
+{
+ struct mlx5e_rep_priv *rpriv = priv->ppriv;
+ struct mlx5_eswitch *esw;
+ u16 vport_num;
+ u32 rate_mbps;
+ int err;
+
+ esw = priv->mdev->priv.eswitch;
+ /* rate is given in bytes/sec.
+ * First convert to bits/sec and then round to the nearest mbit/secs.
+ * mbit means million bits.
+ * Moreover, if rate is non zero we choose to configure to a minimum of
+ * 1 mbit/sec.
+ */
+ rate_mbps = rate ? max_t(u32, (rate * 8 + 500000) / 1000000, 1) : 0;
+ vport_num = rpriv->rep->vport;
+
+ err = mlx5_esw_modify_vport_rate(esw, vport_num, rate_mbps);
+ if (err)
+ NL_SET_ERR_MSG_MOD(extack, "failed applying action to hardware");
+
+ return err;
+}
+
+static int scan_tc_matchall_fdb_actions(struct mlx5e_priv *priv,
+ struct flow_action *flow_action,
+ struct netlink_ext_ack *extack)
+{
+ struct mlx5e_rep_priv *rpriv = priv->ppriv;
+ const struct flow_action_entry *act;
+ int err;
+ int i;
+
+ if (!flow_action_has_entries(flow_action)) {
+ NL_SET_ERR_MSG_MOD(extack, "matchall called with no action");
+ return -EINVAL;
+ }
+
+ if (!flow_offload_has_one_action(flow_action)) {
+ NL_SET_ERR_MSG_MOD(extack, "matchall policing support only a single action");
+ return -EOPNOTSUPP;
+ }
+
+ flow_action_for_each(i, act, flow_action) {
+ switch (act->id) {
+ case FLOW_ACTION_POLICE:
+ err = apply_police_params(priv, act->police.rate_bytes_ps, extack);
+ if (err)
+ return err;
+
+ rpriv->prev_vf_vport_stats = priv->stats.vf_vport;
+ break;
+ default:
+ NL_SET_ERR_MSG_MOD(extack, "mlx5 supports only police action for matchall");
+ return -EOPNOTSUPP;
+ }
+ }
+
+ return 0;
+}
+
+int mlx5e_tc_configure_matchall(struct mlx5e_priv *priv,
+ struct tc_cls_matchall_offload *ma)
+{
+ struct netlink_ext_ack *extack = ma->common.extack;
+ int prio = TC_H_MAJ(ma->common.prio) >> 16;
+
+ if (prio != 1) {
+ NL_SET_ERR_MSG_MOD(extack, "only priority 1 is supported");
+ return -EINVAL;
+ }
+
+ return scan_tc_matchall_fdb_actions(priv, &ma->rule->action, extack);
+}
+
+int mlx5e_tc_delete_matchall(struct mlx5e_priv *priv,
+ struct tc_cls_matchall_offload *ma)
+{
+ struct netlink_ext_ack *extack = ma->common.extack;
+
+ return apply_police_params(priv, 0, extack);
+}
+
+void mlx5e_tc_stats_matchall(struct mlx5e_priv *priv,
+ struct tc_cls_matchall_offload *ma)
+{
+ struct mlx5e_rep_priv *rpriv = priv->ppriv;
+ struct rtnl_link_stats64 cur_stats;
+ u64 dbytes;
+ u64 dpkts;
+
+ cur_stats = priv->stats.vf_vport;
+ dpkts = cur_stats.rx_packets - rpriv->prev_vf_vport_stats.rx_packets;
+ dbytes = cur_stats.rx_bytes - rpriv->prev_vf_vport_stats.rx_bytes;
+ rpriv->prev_vf_vport_stats = cur_stats;
+ flow_stats_update(&ma->stats, dpkts, dbytes, jiffies);
+}
+
static void mlx5e_tc_hairpin_update_dead_peer(struct mlx5e_priv *priv,
struct mlx5e_priv *peer_priv)
{
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
index 1cb66bf76997..20f045e96c92 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
@@ -63,6 +63,13 @@ int mlx5e_delete_flower(struct net_device *dev, struct mlx5e_priv *priv,
int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv,
struct flow_cls_offload *f, unsigned long flags);
+int mlx5e_tc_configure_matchall(struct mlx5e_priv *priv,
+ struct tc_cls_matchall_offload *f);
+int mlx5e_tc_delete_matchall(struct mlx5e_priv *priv,
+ struct tc_cls_matchall_offload *f);
+void mlx5e_tc_stats_matchall(struct mlx5e_priv *priv,
+ struct tc_cls_matchall_offload *ma);
+
struct mlx5e_encap_entry;
void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv,
struct mlx5e_encap_entry *e);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index f4ace5f8e884..5fbebee7254d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1585,6 +1585,22 @@ static int esw_vport_qos_config(struct mlx5_eswitch *esw,
return 0;
}
+int mlx5_esw_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num,
+ u32 rate_mbps)
+{
+ u32 ctx[MLX5_ST_SZ_DW(scheduling_context)] = {};
+ struct mlx5_vport *vport;
+
+ vport = mlx5_eswitch_get_vport(esw, vport_num);
+ MLX5_SET(scheduling_context, ctx, max_average_bw, rate_mbps);
+
+ return mlx5_modify_scheduling_element_cmd(esw->dev,
+ SCHEDULING_HIERARCHY_E_SWITCH,
+ ctx,
+ vport->qos.esw_tsar_ix,
+ MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_MAX_AVERAGE_BW);
+}
+
static void node_guid_gen_from_mac(u64 *node_guid, u8 mac[ETH_ALEN])
{
((u8 *)node_guid)[7] = mac[0];
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 4a03fdadb47e..804912e38dee 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -261,6 +261,8 @@ void esw_vport_disable_ingress_acl(struct mlx5_eswitch *esw,
struct mlx5_vport *vport);
void esw_vport_del_ingress_acl_modify_metadata(struct mlx5_eswitch *esw,
struct mlx5_vport *vport);
+int mlx5_esw_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num,
+ u32 rate_mbps);
/* E-Switch API */
int mlx5_eswitch_init(struct mlx5_core_dev *dev);
--
2.21.0
^ permalink raw reply related
* [net-next 05/12] net/mlx5e: XDP, Close TX MPWQE session when no room for inline packet left
From: Saeed Mahameed @ 2019-08-01 19:56 UTC (permalink / raw)
To: David S. Miller
Cc: netdev@vger.kernel.org, Shay Agroskin, Tariq Toukan,
Saeed Mahameed
In-Reply-To: <20190801195620.26180-1-saeedm@mellanox.com>
From: Shay Agroskin <shayag@mellanox.com>
In MPWQE mode, when transmitting packets with XDP, a packet that is smaller
than a certain size (set to 256 bytes) would be sent inline within its WQE
TX descriptor (mem-copied), in case the hardware tx queue is congested
beyond a pre-defined water-mark.
If a MPWQE cannot contain an additional inline packet, we close this
MPWQE session, and send the packet inlined within the next MPWQE.
To save some MPWQE session close+open operations, we don't open MPWQE
sessions that are contiguously smaller than certain size (set to the
HW MPWQE maximum size). If there isn't enough contiguous room in the
send queue, we fill it with NOPs and wrap the send queue index around.
This way, qualified packets are always sent inline.
Perf tests:
Tested packet rate for UDP 64Byte multi-stream
over two dual port ConnectX-5 100Gbps NICs.
CPU: Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz
XDP_TX:
With 24 channels:
| ------ | bounced packets | inlined packets | inline ratio |
| before | 113.6Mpps | 96.3Mpps | 84% |
| after | 115Mpps | 99.5Mpps | 86% |
With one channel:
| ------ | bounced packets | inlined packets | inline ratio |
| before | 6.7Mpps | 0pps | 0% |
| after | 6.8Mpps | 0pps | 0% |
As we can see, there is improvement in both inline ratio and overall
packet rate for 24 channels. Also, we see no degradation for the
one-channel case.
Signed-off-by: Shay Agroskin <shayag@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en.h | 2 -
.../net/ethernet/mellanox/mlx5/core/en/xdp.c | 32 ++++-------
.../net/ethernet/mellanox/mlx5/core/en/xdp.h | 53 +++++++++++++++----
.../ethernet/mellanox/mlx5/core/en_stats.c | 6 +++
.../ethernet/mellanox/mlx5/core/en_stats.h | 3 ++
5 files changed, 63 insertions(+), 33 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 79d93d6c7d7a..745bcc25c6f8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -483,8 +483,6 @@ struct mlx5e_xdp_mpwqe {
struct mlx5e_tx_wqe *wqe;
u8 ds_count;
u8 pkt_count;
- u8 max_ds_count;
- u8 complete;
u8 inline_on;
};
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index b0b982cf69bb..8cb98326531f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -179,34 +179,22 @@ static void mlx5e_xdp_mpwqe_session_start(struct mlx5e_xdpsq *sq)
struct mlx5e_xdp_mpwqe *session = &sq->mpwqe;
struct mlx5e_xdpsq_stats *stats = sq->stats;
struct mlx5_wq_cyc *wq = &sq->wq;
- u8 wqebbs;
- u16 pi;
+ u16 pi, contig_wqebbs;
+
+ pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
+ contig_wqebbs = mlx5_wq_cyc_get_contig_wqebbs(wq, pi);
+
+ if (unlikely(contig_wqebbs < MLX5_SEND_WQE_MAX_WQEBBS))
+ mlx5e_fill_xdpsq_frag_edge(sq, wq, pi, contig_wqebbs);
mlx5e_xdpsq_fetch_wqe(sq, &session->wqe);
prefetchw(session->wqe->data);
session->ds_count = MLX5E_XDP_TX_EMPTY_DS_COUNT;
session->pkt_count = 0;
- session->complete = 0;
pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
-/* The mult of MLX5_SEND_WQE_MAX_WQEBBS * MLX5_SEND_WQEBB_NUM_DS
- * (16 * 4 == 64) does not fit in the 6-bit DS field of Ctrl Segment.
- * We use a bound lower that MLX5_SEND_WQE_MAX_WQEBBS to let a
- * full-session WQE be cache-aligned.
- */
-#if L1_CACHE_BYTES < 128
-#define MLX5E_XDP_MPW_MAX_WQEBBS (MLX5_SEND_WQE_MAX_WQEBBS - 1)
-#else
-#define MLX5E_XDP_MPW_MAX_WQEBBS (MLX5_SEND_WQE_MAX_WQEBBS - 2)
-#endif
-
- wqebbs = min_t(u16, mlx5_wq_cyc_get_contig_wqebbs(wq, pi),
- MLX5E_XDP_MPW_MAX_WQEBBS);
-
- session->max_ds_count = MLX5_SEND_WQEBB_NUM_DS * wqebbs;
-
mlx5e_xdp_update_inline_state(sq);
stats->mpwqe++;
@@ -244,7 +232,7 @@ static int mlx5e_xmit_xdp_frame_check_mpwqe(struct mlx5e_xdpsq *sq)
{
if (unlikely(!sq->mpwqe.wqe)) {
if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc,
- MLX5_SEND_WQE_MAX_WQEBBS))) {
+ MLX5E_XDPSQ_STOP_ROOM))) {
/* SQ is full, ring doorbell */
mlx5e_xmit_xdp_doorbell(sq);
sq->stats->full++;
@@ -285,8 +273,8 @@ static bool mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq,
mlx5e_xdp_mpwqe_add_dseg(sq, xdptxd, stats);
- if (unlikely(session->complete ||
- session->ds_count == session->max_ds_count))
+ if (unlikely(mlx5e_xdp_no_room_for_inline_pkt(session) ||
+ session->ds_count == MLX5E_XDP_MPW_MAX_NUM_DS))
mlx5e_xdp_mpwqe_complete(sq);
mlx5e_xdpi_fifo_push(&sq->db.xdpi_fifo, xdpi);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
index b90923932668..e0ed7710f5f1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
@@ -40,6 +40,26 @@
(sizeof(struct mlx5e_tx_wqe) / MLX5_SEND_WQE_DS)
#define MLX5E_XDP_TX_DS_COUNT (MLX5E_XDP_TX_EMPTY_DS_COUNT + 1 /* SG DS */)
+#define MLX5E_XDPSQ_STOP_ROOM (MLX5E_SQ_STOP_ROOM)
+
+#define MLX5E_XDP_INLINE_WQE_SZ_THRSD (256 - sizeof(struct mlx5_wqe_inline_seg))
+#define MLX5E_XDP_INLINE_WQE_MAX_DS_CNT \
+ DIV_ROUND_UP(MLX5E_XDP_INLINE_WQE_SZ_THRSD, MLX5_SEND_WQE_DS)
+
+/* The mult of MLX5_SEND_WQE_MAX_WQEBBS * MLX5_SEND_WQEBB_NUM_DS
+ * (16 * 4 == 64) does not fit in the 6-bit DS field of Ctrl Segment.
+ * We use a bound lower that MLX5_SEND_WQE_MAX_WQEBBS to let a
+ * full-session WQE be cache-aligned.
+ */
+#if L1_CACHE_BYTES < 128
+#define MLX5E_XDP_MPW_MAX_WQEBBS (MLX5_SEND_WQE_MAX_WQEBBS - 1)
+#else
+#define MLX5E_XDP_MPW_MAX_WQEBBS (MLX5_SEND_WQE_MAX_WQEBBS - 2)
+#endif
+
+#define MLX5E_XDP_MPW_MAX_NUM_DS \
+ (MLX5E_XDP_MPW_MAX_WQEBBS * MLX5_SEND_WQEBB_NUM_DS)
+
struct mlx5e_xsk_param;
int mlx5e_xdp_max_mtu(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk);
bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
@@ -114,6 +134,30 @@ static inline void mlx5e_xdp_update_inline_state(struct mlx5e_xdpsq *sq)
session->inline_on = 1;
}
+static inline bool
+mlx5e_xdp_no_room_for_inline_pkt(struct mlx5e_xdp_mpwqe *session)
+{
+ return session->inline_on &&
+ session->ds_count + MLX5E_XDP_INLINE_WQE_MAX_DS_CNT > MLX5E_XDP_MPW_MAX_NUM_DS;
+}
+
+static inline void
+mlx5e_fill_xdpsq_frag_edge(struct mlx5e_xdpsq *sq, struct mlx5_wq_cyc *wq,
+ u16 pi, u16 nnops)
+{
+ struct mlx5e_xdp_wqe_info *edge_wi, *wi = &sq->db.wqe_info[pi];
+
+ edge_wi = wi + nnops;
+ /* fill sq frag edge with nops to avoid wqe wrapping two pages */
+ for (; wi < edge_wi; wi++) {
+ wi->num_wqebbs = 1;
+ wi->num_pkts = 0;
+ mlx5e_post_nop(wq, sq->sqn, &sq->pc);
+ }
+
+ sq->stats->nops += nnops;
+}
+
static inline void
mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq,
struct mlx5e_xdp_xmit_data *xdptxd,
@@ -126,20 +170,12 @@ mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq,
session->pkt_count++;
-#define MLX5E_XDP_INLINE_WQE_SZ_THRSD (256 - sizeof(struct mlx5_wqe_inline_seg))
-
if (session->inline_on && dma_len <= MLX5E_XDP_INLINE_WQE_SZ_THRSD) {
struct mlx5_wqe_inline_seg *inline_dseg =
(struct mlx5_wqe_inline_seg *)dseg;
u16 ds_len = sizeof(*inline_dseg) + dma_len;
u16 ds_cnt = DIV_ROUND_UP(ds_len, MLX5_SEND_WQE_DS);
- if (unlikely(session->ds_count + ds_cnt > session->max_ds_count)) {
- /* Not enough space for inline wqe, send with memory pointer */
- session->complete = true;
- goto no_inline;
- }
-
inline_dseg->byte_count = cpu_to_be32(dma_len | MLX5_INLINE_SEG);
memcpy(inline_dseg->data, xdptxd->data, dma_len);
@@ -148,7 +184,6 @@ mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq,
return;
}
-no_inline:
dseg->addr = cpu_to_be64(xdptxd->dma_addr);
dseg->byte_count = cpu_to_be32(dma_len);
dseg->lkey = sq->mkey_be;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 539b4d3656da..6eee3c7d4b06 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -74,6 +74,7 @@ static const struct counter_desc sw_stats_desc[] = {
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_xmit) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_mpwqe) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_inlnw) },
+ { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_nops) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_full) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_err) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_cqe) },
@@ -90,6 +91,7 @@ static const struct counter_desc sw_stats_desc[] = {
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_xmit) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_mpwqe) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_inlnw) },
+ { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_nops) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_full) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_err) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_cqes) },
@@ -200,6 +202,7 @@ static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
s->rx_xdp_tx_xmit += xdpsq_stats->xmit;
s->rx_xdp_tx_mpwqe += xdpsq_stats->mpwqe;
s->rx_xdp_tx_inlnw += xdpsq_stats->inlnw;
+ s->rx_xdp_tx_nops += xdpsq_stats->nops;
s->rx_xdp_tx_full += xdpsq_stats->full;
s->rx_xdp_tx_err += xdpsq_stats->err;
s->rx_xdp_tx_cqe += xdpsq_stats->cqes;
@@ -227,6 +230,7 @@ static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
s->tx_xdp_xmit += xdpsq_red_stats->xmit;
s->tx_xdp_mpwqe += xdpsq_red_stats->mpwqe;
s->tx_xdp_inlnw += xdpsq_red_stats->inlnw;
+ s->tx_xdp_nops += xdpsq_red_stats->nops;
s->tx_xdp_full += xdpsq_red_stats->full;
s->tx_xdp_err += xdpsq_red_stats->err;
s->tx_xdp_cqes += xdpsq_red_stats->cqes;
@@ -1331,6 +1335,7 @@ static const struct counter_desc rq_xdpsq_stats_desc[] = {
{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, xmit) },
{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, mpwqe) },
{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, inlnw) },
+ { MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, nops) },
{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, full) },
{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, err) },
{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, cqes) },
@@ -1340,6 +1345,7 @@ static const struct counter_desc xdpsq_stats_desc[] = {
{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, xmit) },
{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, mpwqe) },
{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, inlnw) },
+ { MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, nops) },
{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, full) },
{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, err) },
{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, cqes) },
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 76ac111e14d0..bf645d42c833 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -81,6 +81,7 @@ struct mlx5e_sw_stats {
u64 rx_xdp_tx_xmit;
u64 rx_xdp_tx_mpwqe;
u64 rx_xdp_tx_inlnw;
+ u64 rx_xdp_tx_nops;
u64 rx_xdp_tx_full;
u64 rx_xdp_tx_err;
u64 rx_xdp_tx_cqe;
@@ -97,6 +98,7 @@ struct mlx5e_sw_stats {
u64 tx_xdp_xmit;
u64 tx_xdp_mpwqe;
u64 tx_xdp_inlnw;
+ u64 tx_xdp_nops;
u64 tx_xdp_full;
u64 tx_xdp_err;
u64 tx_xdp_cqes;
@@ -288,6 +290,7 @@ struct mlx5e_xdpsq_stats {
u64 xmit;
u64 mpwqe;
u64 inlnw;
+ u64 nops;
u64 full;
u64 err;
/* dirtied @completion */
--
2.21.0
^ permalink raw reply related
* [net-next 07/12] net/mlx5e: Tx, Soften inline mode VLAN dependencies
From: Saeed Mahameed @ 2019-08-01 19:57 UTC (permalink / raw)
To: David S. Miller
Cc: netdev@vger.kernel.org, Tariq Toukan, Noam Stolero,
Saeed Mahameed
In-Reply-To: <20190801195620.26180-1-saeedm@mellanox.com>
From: Tariq Toukan <tariqt@mellanox.com>
If capable, use zero inline mode in TX WQE for non-VLAN packets.
For VLAN ones, keep the enforcement of at least L2 inline mode,
unless the WQE VLAN insertion offload cap is on.
Performance:
Tested single core packet rate of 64Bytes.
NIC: ConnectX-5
CPU: Intel(R) Xeon(R) Gold 6154 CPU @ 3.00GHz
pktgen:
Before: 12.46 Mpps
After: 14.65 Mpps (+17.5%)
XDP_TX:
The MPWQE flow is not affected, as it already has this optimization.
So we test with priv-flag xdp_tx_mpwqe: off.
Before: 9.90 Mpps
After: 10.20 Mpps (+3%)
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Tested-by: Noam Stolero <noams@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en.h | 2 +-
.../net/ethernet/mellanox/mlx5/core/en/txrx.h | 22 +++++++++++++++++--
.../ethernet/mellanox/mlx5/core/en_common.c | 12 ----------
.../ethernet/mellanox/mlx5/core/en_dcbnl.c | 2 +-
.../net/ethernet/mellanox/mlx5/core/en_main.c | 4 +++-
.../net/ethernet/mellanox/mlx5/core/en_tx.c | 7 +++---
.../net/ethernet/mellanox/mlx5/core/vport.c | 7 +++---
7 files changed, 33 insertions(+), 23 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 745bcc25c6f8..30f13f81c965 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -359,6 +359,7 @@ enum {
MLX5E_SQ_STATE_IPSEC,
MLX5E_SQ_STATE_AM,
MLX5E_SQ_STATE_TLS,
+ MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE,
};
struct mlx5e_sq_wqe_info {
@@ -1132,7 +1133,6 @@ void mlx5e_build_rq_params(struct mlx5_core_dev *mdev,
struct mlx5e_params *params);
void mlx5e_build_rss_params(struct mlx5e_rss_params *rss_params,
u16 num_channels);
-u8 mlx5e_params_calculate_tx_min_inline(struct mlx5_core_dev *mdev);
void mlx5e_rx_dim_work(struct work_struct *work);
void mlx5e_tx_dim_work(struct work_struct *work);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
index 7da22b413a48..87be96747902 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
@@ -117,9 +117,27 @@ mlx5e_notify_hw(struct mlx5_wq_cyc *wq, u16 pc, void __iomem *uar_map,
mlx5_write64((__be32 *)ctrl, uar_map);
}
-static inline bool mlx5e_transport_inline_tx_wqe(struct mlx5e_tx_wqe *wqe)
+static inline bool mlx5e_transport_inline_tx_wqe(struct mlx5_wqe_ctrl_seg *cseg)
{
- return !!wqe->ctrl.tisn;
+ return cseg && !!cseg->tisn;
+}
+
+static inline u8
+mlx5e_tx_wqe_inline_mode(struct mlx5e_txqsq *sq, struct mlx5_wqe_ctrl_seg *cseg,
+ struct sk_buff *skb)
+{
+ u8 mode;
+
+ if (mlx5e_transport_inline_tx_wqe(cseg))
+ return MLX5_INLINE_MODE_TCP_UDP;
+
+ mode = sq->min_inline_mode;
+
+ if (skb_vlan_tag_present(skb) &&
+ test_bit(MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE, &sq->state))
+ mode = max_t(u8, MLX5_INLINE_MODE_L2, mode);
+
+ return mode;
}
static inline void mlx5e_cq_arm(struct mlx5e_cq *cq)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
index 1539cf3de5dc..f7890e0ce96c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
@@ -180,15 +180,3 @@ int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb)
return err;
}
-
-u8 mlx5e_params_calculate_tx_min_inline(struct mlx5_core_dev *mdev)
-{
- u8 min_inline_mode;
-
- mlx5_query_min_inline(mdev, &min_inline_mode);
- if (min_inline_mode == MLX5_INLINE_MODE_NONE &&
- !MLX5_CAP_ETH(mdev, wqe_vlan_insert))
- min_inline_mode = MLX5_INLINE_MODE_L2;
-
- return min_inline_mode;
-}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
index 8dd31b5c740c..01f2918063af 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
@@ -1101,7 +1101,7 @@ void mlx5e_dcbnl_delete_app(struct mlx5e_priv *priv)
static void mlx5e_trust_update_tx_min_inline_mode(struct mlx5e_priv *priv,
struct mlx5e_params *params)
{
- params->tx_min_inline_mode = mlx5e_params_calculate_tx_min_inline(priv->mdev);
+ mlx5_query_min_inline(priv->mdev, ¶ms->tx_min_inline_mode);
if (priv->dcbx_dp.trust_state == MLX5_QPTS_TRUST_DSCP &&
params->tx_min_inline_mode == MLX5_INLINE_MODE_L2)
params->tx_min_inline_mode = MLX5_INLINE_MODE_IP;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index b2618dd6dd10..e75cb18c2256 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1131,6 +1131,8 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
sq->stats = &c->priv->channel_stats[c->ix].sq[tc];
sq->stop_room = MLX5E_SQ_STOP_ROOM;
INIT_WORK(&sq->recover_work, mlx5e_tx_err_cqe_work);
+ if (!MLX5_CAP_ETH(mdev, wqe_vlan_insert))
+ set_bit(MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE, &sq->state);
if (MLX5_IPSEC_DEV(c->priv->mdev))
set_bit(MLX5E_SQ_STATE_IPSEC, &sq->state);
if (mlx5_accel_is_tls_device(c->priv->mdev)) {
@@ -4777,7 +4779,7 @@ void mlx5e_build_nic_params(struct mlx5_core_dev *mdev,
mlx5e_set_tx_cq_mode_params(params, MLX5_CQ_PERIOD_MODE_START_FROM_EQE);
/* TX inline */
- params->tx_min_inline_mode = mlx5e_params_calculate_tx_min_inline(mdev);
+ mlx5_query_min_inline(mdev, ¶ms->tx_min_inline_mode);
/* RSS */
mlx5e_build_rss_params(rss_params, params->num_channels);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index acf25cc38fa1..d3a67a9b4eba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -292,8 +292,7 @@ netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
num_bytes = skb->len + (skb_shinfo(skb)->gso_segs - 1) * ihs;
stats->packets += skb_shinfo(skb)->gso_segs;
} else {
- u8 mode = mlx5e_transport_inline_tx_wqe(wqe) ?
- MLX5_INLINE_MODE_TCP_UDP : sq->min_inline_mode;
+ u8 mode = mlx5e_tx_wqe_inline_mode(sq, &wqe->ctrl, skb);
opcode = MLX5_OPCODE_SEND;
mss = 0;
@@ -608,9 +607,11 @@ netdev_tx_t mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
num_bytes = skb->len + (skb_shinfo(skb)->gso_segs - 1) * ihs;
stats->packets += skb_shinfo(skb)->gso_segs;
} else {
+ u8 mode = mlx5e_tx_wqe_inline_mode(sq, NULL, skb);
+
opcode = MLX5_OPCODE_SEND;
mss = 0;
- ihs = mlx5e_calc_min_inline(sq->min_inline_mode, skb);
+ ihs = mlx5e_calc_min_inline(mode, skb);
num_bytes = max_t(unsigned int, skb->len, ETH_ZLEN);
stats->packets++;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index c912d82ca64b..30f7848a6f88 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -122,12 +122,13 @@ void mlx5_query_min_inline(struct mlx5_core_dev *mdev,
u8 *min_inline_mode)
{
switch (MLX5_CAP_ETH(mdev, wqe_inline_mode)) {
+ case MLX5_CAP_INLINE_MODE_VPORT_CONTEXT:
+ if (!mlx5_query_nic_vport_min_inline(mdev, 0, min_inline_mode))
+ break;
+ /* fall through */
case MLX5_CAP_INLINE_MODE_L2:
*min_inline_mode = MLX5_INLINE_MODE_L2;
break;
- case MLX5_CAP_INLINE_MODE_VPORT_CONTEXT:
- mlx5_query_nic_vport_min_inline(mdev, 0, min_inline_mode);
- break;
case MLX5_CAP_INLINE_MODE_NOT_REQUIRED:
*min_inline_mode = MLX5_INLINE_MODE_NONE;
break;
--
2.21.0
^ permalink raw reply related
* [net-next 08/12] net/mlx5e: Rx, checksum handling refactoring
From: Saeed Mahameed @ 2019-08-01 19:57 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev@vger.kernel.org, Saeed Mahameed
In-Reply-To: <20190801195620.26180-1-saeedm@mellanox.com>
Move vlan checksum fixup flow into mlx5e_skb_padding_csum(), which is
supposed to fixup SKB checksum if needed. And rename
mlx5e_skb_padding_csum() to mlx5e_skb_csum_fixup().
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../net/ethernet/mellanox/mlx5/core/en_rx.c | 26 ++++++++++---------
1 file changed, 14 insertions(+), 12 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index ac6e586d403d..60570b442fff 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -859,13 +859,24 @@ tail_padding_csum(struct sk_buff *skb, int offset,
}
static void
-mlx5e_skb_padding_csum(struct sk_buff *skb, int network_depth, __be16 proto,
- struct mlx5e_rq_stats *stats)
+mlx5e_skb_csum_fixup(struct sk_buff *skb, int network_depth, __be16 proto,
+ struct mlx5e_rq_stats *stats)
{
struct ipv6hdr *ip6;
struct iphdr *ip4;
int pkt_len;
+ /* Fixup vlan headers, if any */
+ if (network_depth > ETH_HLEN)
+ /* CQE csum is calculated from the IP header and does
+ * not cover VLAN headers (if present). This will add
+ * the checksum manually.
+ */
+ skb->csum = csum_partial(skb->data + ETH_HLEN,
+ network_depth - ETH_HLEN,
+ skb->csum);
+
+ /* Fixup tail padding, if any */
switch (proto) {
case htons(ETH_P_IP):
ip4 = (struct iphdr *)(skb->data + network_depth);
@@ -931,16 +942,7 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
return; /* CQE csum covers all received bytes */
/* csum might need some fixups ...*/
- if (network_depth > ETH_HLEN)
- /* CQE csum is calculated from the IP header and does
- * not cover VLAN headers (if present). This will add
- * the checksum manually.
- */
- skb->csum = csum_partial(skb->data + ETH_HLEN,
- network_depth - ETH_HLEN,
- skb->csum);
-
- mlx5e_skb_padding_csum(skb, network_depth, proto, stats);
+ mlx5e_skb_csum_fixup(skb, network_depth, proto, stats);
return;
}
--
2.21.0
^ permalink raw reply related
* [net-next 09/12] net/mlx5e: Fix mlx5e_tx_reporter_create return value
From: Saeed Mahameed @ 2019-08-01 19:57 UTC (permalink / raw)
To: David S. Miller
Cc: netdev@vger.kernel.org, Aya Levin, Tariq Toukan, Jiri Pirko,
Saeed Mahameed
In-Reply-To: <20190801195620.26180-1-saeedm@mellanox.com>
From: Aya Levin <ayal@mellanox.com>
Return error when failing to create a reporter in devlink. Since
NET_DEVLINK mandatory to MLX5_CORE in Kconfig, returned pointer
can't be NULL and can only hold an error in bad path.
Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
index f3d98748b211..383ecfd85d8a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -296,11 +296,13 @@ int mlx5e_tx_reporter_create(struct mlx5e_priv *priv)
devlink_health_reporter_create(devlink, &mlx5_tx_reporter_ops,
MLX5_REPORTER_TX_GRACEFUL_PERIOD,
true, priv);
- if (IS_ERR(priv->tx_reporter))
+ if (IS_ERR(priv->tx_reporter)) {
netdev_warn(priv->netdev,
"Failed to create tx reporter, err = %ld\n",
PTR_ERR(priv->tx_reporter));
- return IS_ERR_OR_NULL(priv->tx_reporter);
+ return PTR_ERR(priv->tx_reporter);
+ }
+ return 0;
}
void mlx5e_tx_reporter_destroy(struct mlx5e_priv *priv)
--
2.21.0
^ permalink raw reply related
* [net-next 06/12] net/mlx5e: XDP, Slight enhancement for WQE fetch function
From: Saeed Mahameed @ 2019-08-01 19:57 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev@vger.kernel.org, Tariq Toukan, Saeed Mahameed
In-Reply-To: <20190801195620.26180-1-saeedm@mellanox.com>
From: Tariq Toukan <tariqt@mellanox.com>
Instead of passing an output param, let function return the
WQE pointer.
In addition, pass &pi so it gets its value in the function,
and save the redundant assignment that comes after it.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c | 4 +---
drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h | 13 ++++++++-----
2 files changed, 9 insertions(+), 8 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 8cb98326531f..1ed5c33e022f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -187,14 +187,12 @@ static void mlx5e_xdp_mpwqe_session_start(struct mlx5e_xdpsq *sq)
if (unlikely(contig_wqebbs < MLX5_SEND_WQE_MAX_WQEBBS))
mlx5e_fill_xdpsq_frag_edge(sq, wq, pi, contig_wqebbs);
- mlx5e_xdpsq_fetch_wqe(sq, &session->wqe);
+ session->wqe = mlx5e_xdpsq_fetch_wqe(sq, &pi);
prefetchw(session->wqe->data);
session->ds_count = MLX5E_XDP_TX_EMPTY_DS_COUNT;
session->pkt_count = 0;
- pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
-
mlx5e_xdp_update_inline_state(sq);
stats->mpwqe++;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
index e0ed7710f5f1..36ac1e3816b9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
@@ -190,14 +190,17 @@ mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq,
session->ds_count++;
}
-static inline void mlx5e_xdpsq_fetch_wqe(struct mlx5e_xdpsq *sq,
- struct mlx5e_tx_wqe **wqe)
+static inline struct mlx5e_tx_wqe *
+mlx5e_xdpsq_fetch_wqe(struct mlx5e_xdpsq *sq, u16 *pi)
{
struct mlx5_wq_cyc *wq = &sq->wq;
- u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
+ struct mlx5e_tx_wqe *wqe;
- *wqe = mlx5_wq_cyc_get_wqe(wq, pi);
- memset(*wqe, 0, sizeof(**wqe));
+ *pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
+ wqe = mlx5_wq_cyc_get_wqe(wq, *pi);
+ memset(wqe, 0, sizeof(*wqe));
+
+ return wqe;
}
static inline void
--
2.21.0
^ permalink raw reply related
* [net-next 10/12] net/mlx5e: Set tx reporter only on successful creation
From: Saeed Mahameed @ 2019-08-01 19:57 UTC (permalink / raw)
To: David S. Miller
Cc: netdev@vger.kernel.org, Aya Levin, Tariq Toukan, Jiri Pirko,
Saeed Mahameed
In-Reply-To: <20190801195620.26180-1-saeedm@mellanox.com>
From: Aya Levin <ayal@mellanox.com>
When failing to create tx reporter, don't set the reporter's pointer.
Creating a reporter is not mandatory for driver load, avoid
garbage/error pointer.
Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../ethernet/mellanox/mlx5/core/en/reporter_tx.c | 14 ++++++++------
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 2 +-
2 files changed, 9 insertions(+), 7 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
index 383ecfd85d8a..f1c652f75718 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -117,7 +117,7 @@ static int mlx5_tx_health_report(struct devlink_health_reporter *tx_reporter,
char *err_str,
struct mlx5e_tx_err_ctx *err_ctx)
{
- if (IS_ERR_OR_NULL(tx_reporter)) {
+ if (!tx_reporter) {
netdev_err(err_ctx->sq->channel->netdev, err_str);
return err_ctx->recover(err_ctx->sq);
}
@@ -289,25 +289,27 @@ static const struct devlink_health_reporter_ops mlx5_tx_reporter_ops = {
int mlx5e_tx_reporter_create(struct mlx5e_priv *priv)
{
+ struct devlink_health_reporter *reporter;
struct mlx5_core_dev *mdev = priv->mdev;
struct devlink *devlink = priv_to_devlink(mdev);
- priv->tx_reporter =
+ reporter =
devlink_health_reporter_create(devlink, &mlx5_tx_reporter_ops,
MLX5_REPORTER_TX_GRACEFUL_PERIOD,
true, priv);
- if (IS_ERR(priv->tx_reporter)) {
+ if (IS_ERR(reporter)) {
netdev_warn(priv->netdev,
"Failed to create tx reporter, err = %ld\n",
- PTR_ERR(priv->tx_reporter));
- return PTR_ERR(priv->tx_reporter);
+ PTR_ERR(reporter));
+ return PTR_ERR(reporter);
}
+ priv->tx_reporter = reporter;
return 0;
}
void mlx5e_tx_reporter_destroy(struct mlx5e_priv *priv)
{
- if (IS_ERR_OR_NULL(priv->tx_reporter))
+ if (!priv->tx_reporter)
return;
devlink_health_reporter_destroy(priv->tx_reporter);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index e75cb18c2256..4db595a7eb03 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2325,7 +2325,7 @@ int mlx5e_open_channels(struct mlx5e_priv *priv,
goto err_close_channels;
}
- if (!IS_ERR_OR_NULL(priv->tx_reporter))
+ if (priv->tx_reporter)
devlink_health_reporter_state_update(priv->tx_reporter,
DEVLINK_HEALTH_REPORTER_STATE_HEALTHY);
--
2.21.0
^ permalink raw reply related
* [net-next 11/12] net/mlx5e: TX reporter cleanup
From: Saeed Mahameed @ 2019-08-01 19:57 UTC (permalink / raw)
To: David S. Miller
Cc: netdev@vger.kernel.org, Aya Levin, Tariq Toukan, Jiri Pirko,
Saeed Mahameed
In-Reply-To: <20190801195620.26180-1-saeedm@mellanox.com>
From: Aya Levin <ayal@mellanox.com>
Remove redundant include files.
Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h | 1 -
drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c | 1 -
2 files changed, 2 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h
index e78e92753d73..ed7a3881d2c5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h
@@ -4,7 +4,6 @@
#ifndef __MLX5E_EN_REPORTER_H
#define __MLX5E_EN_REPORTER_H
-#include <linux/mlx5/driver.h>
#include "en.h"
int mlx5e_tx_reporter_create(struct mlx5e_priv *priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
index f1c652f75718..6e54fefea410 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -1,7 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0 */
/* Copyright (c) 2019 Mellanox Technologies. */
-#include <net/devlink.h>
#include "reporter.h"
#include "lib/eq.h"
--
2.21.0
^ permalink raw reply related
* [net-next 12/12] net/mlx5e: Allow dropping specific tunnel packets
From: Saeed Mahameed @ 2019-08-01 19:57 UTC (permalink / raw)
To: David S. Miller
Cc: netdev@vger.kernel.org, Tonghao Zhang, Roi Dayan, Saeed Mahameed
In-Reply-To: <20190801195620.26180-1-saeedm@mellanox.com>
From: Tonghao Zhang <xiangxia.m.yue@gmail.com>
In some case, we don't want to allow specific tunnel packets
to host that can avoid to take up high CPU (e.g network attacks).
But other tunnel packets which not matched in hardware will be
sent to host too.
$ tc filter add dev vxlan_sys_4789 \
protocol ip chain 0 parent ffff: prio 1 handle 1 \
flower dst_ip 1.1.1.100 ip_proto tcp dst_port 80 \
enc_dst_ip 2.2.2.100 enc_key_id 100 enc_dst_port 4789 \
action tunnel_key unset pipe action drop
Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index dc5fc3350b65..c5d75e2ecf54 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -2485,7 +2485,8 @@ static bool actions_match_supported(struct mlx5e_priv *priv,
if (flow_flag_test(flow, EGRESS) &&
!((actions & MLX5_FLOW_CONTEXT_ACTION_DECAP) ||
- (actions & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP)))
+ (actions & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP) ||
+ (actions & MLX5_FLOW_CONTEXT_ACTION_DROP)))
return false;
if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
--
2.21.0
^ permalink raw reply related
* Re: [PATCH] net: bridge: Allow bridge to joing multicast groups
From: Vivien Didelot @ 2019-08-01 20:08 UTC (permalink / raw)
To: Horatiu Vultur
Cc: roopa, nikolay, davem, bridge, netdev, linux-kernel,
allan.nielsen
In-Reply-To: <20190801194801.rqv5jvb5vxjo2dor@soft-dev3.microsemi.net>
Hi Horatiu,
On Thu, 1 Aug 2019 21:48:02 +0200, Horatiu Vultur <horatiu.vultur@microchip.com> wrote:
> > I'm a bit late in the conversation. Isn't this what you want?
> >
> > ip address add <multicast IPv4 address> dev br0 autojoin
> >
>
> Not really, I was looking in a way to register the ports to link layer
> multicast address. Sorry for the confusion, my description of the patch
> was totally missleaning.
>
> If you follow this thread you will get a better idea what we wanted to
> achive. We got some really good comments and based on these we send a
> RFC[1].
OK great! Keep me in the loop, I enjoy bridge and multicast very much ;-)
Thanks,
Vivien
^ permalink raw reply
* Re: [PATCH net-next 0/5] net: dsa: mv88e6xxx: avoid some redundant VTU operations
From: David Miller @ 2019-08-01 20:43 UTC (permalink / raw)
To: vivien.didelot; +Cc: linux-kernel, rasmus.villemoes, f.fainelli, andrew, netdev
In-Reply-To: <20190801183637.24841-1-vivien.didelot@gmail.com>
From: Vivien Didelot <vivien.didelot@gmail.com>
Date: Thu, 1 Aug 2019 14:36:32 -0400
> The mv88e6xxx driver currently uses a mv88e6xxx_vtu_get wrapper to get a
> single entry and uses a boolean to eventually initialize a fresh one.
>
> However the fresh entry is only needed in one place and mv88e6xxx_vtu_getnext
> is simple enough to call it directly. Doing so makes the code easier to read,
> especially for the return code expected by switchdev to honor software VLANs.
>
> In addition to not loading the VTU again when an entry is already correctly
> programmed, this also allows to avoid programming the broadcast entries
> again when updating a port's membership, from e.g. tagged to untagged.
>
> This patch series removes the mv88e6xxx_vtu_get wrapper in favor of direct
> calls to mv88e6xxx_vtu_getnext, and also renames the _mv88e6xxx_port_vlan_add
> and _mv88e6xxx_port_vlan_del helpers using an old underscore prefix convention.
>
> In case the port's membership is already correctly programmed in hardware,
> the following debug message may be printed:
>
> [ 745.989884] mv88e6085 2188000.ethernet-1:00: p4: already a member of VLAN 42
Series applied, thanks Vivien.
^ permalink raw reply
* Re: [PATCH bpf 1/2] bpf: fix x64 JIT code generation for jmp to 1st insn
From: Alexei Starovoitov @ 2019-08-01 20:44 UTC (permalink / raw)
To: Song Liu
Cc: Alexei Starovoitov, David S. Miller, Daniel Borkmann,
netdev@vger.kernel.org, bpf@vger.kernel.org, Kernel Team
In-Reply-To: <CAADnVQJu9s4a=tc0+C5hgSPX4KnpYDzKu0AxxU4nCoU1QaWVEg@mail.gmail.com>
On Wed, Jul 31, 2019 at 8:43 PM Alexei Starovoitov
<alexei.starovoitov@gmail.com> wrote:
>
> On Wed, Jul 31, 2019 at 12:36 PM Song Liu <songliubraving@fb.com> wrote:
> >
> >
> >
> > > On Jul 30, 2019, at 6:38 PM, Alexei Starovoitov <ast@kernel.org> wrote:
> > >
> > > Introduction of bounded loops exposed old bug in x64 JIT.
> > > JIT maintains the array of offsets to the end of all instructions to
> > > compute jmp offsets.
> > > addrs[0] - offset of the end of the 1st insn (that includes prologue).
> > > addrs[1] - offset of the end of the 2nd insn.
> > > JIT didn't keep the offset of the beginning of the 1st insn,
> > > since classic BPF didn't have backward jumps and valid extended BPF
> > > couldn't have a branch to 1st insn, because it didn't allow loops.
> > > With bounded loops it's possible to construct a valid program that
> > > jumps backwards to the 1st insn.
> > > Fix JIT by computing:
> > > addrs[0] - offset of the end of prologue == start of the 1st insn.
> > > addrs[1] - offset of the end of 1st insn.
> > >
> > > Reported-by: syzbot+35101610ff3e83119b1b@syzkaller.appspotmail.com
> > > Fixes: 2589726d12a1 ("bpf: introduce bounded loops")
> > > Fixes: 0a14842f5a3c ("net: filter: Just In Time compiler for x86-64")
> > > Signed-off-by: Alexei Starovoitov <ast@kernel.org>
> >
> > Acked-by: Song Liu <songliubraving@fb.com>
> >
> > Do we need similar fix for x86_32?
>
> Right. x86_32 would need similar fix.
>
> Applied to bpf tree.
Yonghong noticed that it subtly changes jited linfo.
Surprisingly perf annotated output for source code in jited bpf progs
looks exactly the same for several large bpf progs that I've looked at.
This to be investigated later.
I've applied the fix:
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index a56c95805732..991549a1c5f3 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1181,7 +1181,7 @@ struct bpf_prog *bpf_int_jit_compile(struct
bpf_prog *prog)
if (!image || !prog->is_func || extra_pass) {
if (image)
- bpf_prog_fill_jited_linfo(prog, addrs);
+ bpf_prog_fill_jited_linfo(prog, addrs + 1);
out_addrs:
kfree(addrs);
kfree(jit_data);
and re-pushed bpf tree.
The new commit is here:
https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf.git/commit/?id=7c2e988f400e83501e0a3568250780609b7c8263
Thanks Yonghong!
For bpf-next we need to figure out how to make test_btf more robust.
We can probably check first few insns for specific jited offsets,
but I don't yet see how to make it work for all archs.
And it will be annoying to keep it working with every change to jit.
^ permalink raw reply related
* [PATCH] net: mvpp2: Implement RXAUI Support
From: Matt Pelland @ 2019-08-01 20:45 UTC (permalink / raw)
To: netdev; +Cc: davem, maxime.chevallier, antoine.tenart
This patch set implements support for configuring Marvell's mvpp2 hardware for
RXAUI operation. There are two other patches necessary for this to work
correctly that concern Marvell's cp110 comphy that were emailed to the general
linux-kernel mailing list earlier on. I can post them here if need be. This
patch set was successfully tested on a Marvell Armada 7040 based platform.
Cheers,
Matt
^ permalink raw reply
* [PATCH 1/2] net: mvpp2: implement RXAUI support
From: Matt Pelland @ 2019-08-01 20:45 UTC (permalink / raw)
To: netdev; +Cc: davem, maxime.chevallier, antoine.tenart, Matt Pelland
In-Reply-To: <20190801204523.26454-1-mpelland@starry.com>
Marvell's mvpp2 packet processor supports RXAUI on port zero in a
similar manner to the existing 10G protocols that have already been
implemented. This patch implements the miscellaneous extra configuration
steps required for RXAUI operation.
Signed-off-by: Matt Pelland <mpelland@starry.com>
---
drivers/net/ethernet/marvell/mvpp2/mvpp2.h | 1 +
.../net/ethernet/marvell/mvpp2/mvpp2_main.c | 30 +++++++++++++++++++
2 files changed, 31 insertions(+)
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
index 4d9564ba68f6..256e7c796631 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
@@ -481,6 +481,7 @@
#define MVPP22_XLG_CTRL4_REG 0x184
#define MVPP22_XLG_CTRL4_FWD_FC BIT(5)
#define MVPP22_XLG_CTRL4_FWD_PFC BIT(6)
+#define MVPP22_XLG_CTRL4_USE_XPCS BIT(8)
#define MVPP22_XLG_CTRL4_MACMODSELECT_GMAC BIT(12)
#define MVPP22_XLG_CTRL4_EN_IDLE_CHECK BIT(14)
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index e9d8ffe897e9..8b633af4a684 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -968,6 +968,7 @@ mvpp2_shared_interrupt_mask_unmask(struct mvpp2_port *port, bool mask)
static bool mvpp2_is_xlg(phy_interface_t interface)
{
return interface == PHY_INTERFACE_MODE_10GKR ||
+ interface == PHY_INTERFACE_MODE_RXAUI ||
interface == PHY_INTERFACE_MODE_XAUI;
}
@@ -1008,6 +1009,27 @@ static void mvpp22_gop_init_sgmii(struct mvpp2_port *port)
}
}
+static void mvpp22_gop_init_rxaui(struct mvpp2_port *port)
+{
+ struct mvpp2 *priv = port->priv;
+ void __iomem *xpcs = priv->iface_base + MVPP22_XPCS_BASE(port->gop_id);
+ u32 val;
+
+ val = readl(xpcs + MVPP22_XPCS_CFG0);
+ val &= ~MVPP22_XPCS_CFG0_RESET_DIS;
+ writel(val, xpcs + MVPP22_XPCS_CFG0);
+
+ val = readl(xpcs + MVPP22_XPCS_CFG0);
+ val &= ~(MVPP22_XPCS_CFG0_PCS_MODE(0x3) |
+ MVPP22_XPCS_CFG0_ACTIVE_LANE(0x3));
+ val |= MVPP22_XPCS_CFG0_ACTIVE_LANE(2);
+ writel(val, xpcs + MVPP22_XPCS_CFG0);
+
+ val = readl(xpcs + MVPP22_XPCS_CFG0);
+ val |= MVPP22_XPCS_CFG0_RESET_DIS;
+ writel(val, xpcs + MVPP22_XPCS_CFG0);
+}
+
static void mvpp22_gop_init_10gkr(struct mvpp2_port *port)
{
struct mvpp2 *priv = port->priv;
@@ -1053,6 +1075,9 @@ static int mvpp22_gop_init(struct mvpp2_port *port)
case PHY_INTERFACE_MODE_2500BASEX:
mvpp22_gop_init_sgmii(port);
break;
+ case PHY_INTERFACE_MODE_RXAUI:
+ mvpp22_gop_init_rxaui(port);
+ break;
case PHY_INTERFACE_MODE_10GKR:
if (port->gop_id != 0)
goto invalid_conf;
@@ -4570,6 +4595,7 @@ static void mvpp2_phylink_validate(struct phylink_config *config,
switch (state->interface) {
case PHY_INTERFACE_MODE_10GKR:
case PHY_INTERFACE_MODE_XAUI:
+ case PHY_INTERFACE_MODE_RXAUI:
if (port->gop_id != 0)
goto empty_set;
break;
@@ -4592,6 +4618,7 @@ static void mvpp2_phylink_validate(struct phylink_config *config,
switch (state->interface) {
case PHY_INTERFACE_MODE_10GKR:
case PHY_INTERFACE_MODE_XAUI:
+ case PHY_INTERFACE_MODE_RXAUI:
case PHY_INTERFACE_MODE_NA:
if (port->gop_id == 0) {
phylink_set(mask, 10000baseT_Full);
@@ -4744,6 +4771,9 @@ static void mvpp2_xlg_config(struct mvpp2_port *port, unsigned int mode,
ctrl4 |= MVPP22_XLG_CTRL4_FWD_FC | MVPP22_XLG_CTRL4_FWD_PFC |
MVPP22_XLG_CTRL4_EN_IDLE_CHECK;
+ if (state->interface == PHY_INTERFACE_MODE_RXAUI)
+ ctrl4 |= MVPP22_XLG_CTRL4_USE_XPCS;
+
if (old_ctrl0 != ctrl0)
writel(ctrl0, port->base + MVPP22_XLG_CTRL0_REG);
if (old_ctrl4 != ctrl4)
--
2.21.0
^ permalink raw reply related
* [PATCH 2/2] net: mvpp2: support multiple comphy lanes
From: Matt Pelland @ 2019-08-01 20:45 UTC (permalink / raw)
To: netdev; +Cc: davem, maxime.chevallier, antoine.tenart, Matt Pelland
In-Reply-To: <20190801204523.26454-1-mpelland@starry.com>
mvpp 2.2 supports RXAUI which requires a pair of serdes lanes instead of
the usual single lane required by other interface modes. This patch
expands the number of lanes that can be associated to a port so that
both lanes are correctly configured at the appropriate times when RXAUI
is in use.
Signed-off-by: Matt Pelland <mpelland@starry.com>
---
drivers/net/ethernet/marvell/mvpp2/mvpp2.h | 7 +-
.../net/ethernet/marvell/mvpp2/mvpp2_main.c | 66 +++++++++++++------
2 files changed, 53 insertions(+), 20 deletions(-)
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
index 256e7c796631..9ae2b3d9d0c7 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
@@ -655,6 +655,11 @@
#define MVPP2_F_LOOPBACK BIT(0)
#define MVPP2_F_DT_COMPAT BIT(1)
+/* MVPP22 supports RXAUI which requires two comphy lanes, all other modes
+ * require one.
+ */
+#define MVPP22_MAX_COMPHYS 2
+
/* Marvell tag types */
enum mvpp2_tag_type {
MVPP2_TAG_TYPE_NONE = 0,
@@ -935,7 +940,7 @@ struct mvpp2_port {
phy_interface_t phy_interface;
struct phylink *phylink;
struct phylink_config phylink_config;
- struct phy *comphy;
+ struct phy *comphys[MVPP22_MAX_COMPHYS];
struct mvpp2_bm_pool *pool_long;
struct mvpp2_bm_pool *pool_short;
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 8b633af4a684..97dfe2e71b03 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -1186,17 +1186,40 @@ static void mvpp22_gop_setup_irq(struct mvpp2_port *port)
*/
static int mvpp22_comphy_init(struct mvpp2_port *port)
{
- int ret;
+ int i, ret;
- if (!port->comphy)
- return 0;
+ for (i = 0; i < ARRAY_SIZE(port->comphys); i++) {
+ if (!port->comphys[i])
+ return 0;
- ret = phy_set_mode_ext(port->comphy, PHY_MODE_ETHERNET,
- port->phy_interface);
- if (ret)
- return ret;
+ ret = phy_set_mode_ext(port->comphys[i],
+ PHY_MODE_ETHERNET,
+ port->phy_interface);
+ if (ret)
+ return ret;
- return phy_power_on(port->comphy);
+ ret = phy_power_on(port->comphys[i]);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
+static int mvpp22_comphy_deinit(struct mvpp2_port *port)
+{
+ int i, ret;
+
+ for (i = 0; i < ARRAY_SIZE(port->comphys); i++) {
+ if (!port->comphys[i])
+ return 0;
+
+ ret = phy_power_off(port->comphys[i]);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
}
static void mvpp2_port_enable(struct mvpp2_port *port)
@@ -3375,7 +3398,9 @@ static void mvpp2_stop_dev(struct mvpp2_port *port)
if (port->phylink)
phylink_stop(port->phylink);
- phy_power_off(port->comphy);
+
+ if (port->priv->hw_version == MVPP22)
+ mvpp22_comphy_deinit(port);
}
static int mvpp2_check_ringparam_valid(struct net_device *dev,
@@ -4947,7 +4972,7 @@ static void mvpp2_mac_config(struct phylink_config *config, unsigned int mode,
port->phy_interface = state->interface;
/* Reconfigure the serdes lanes */
- phy_power_off(port->comphy);
+ mvpp22_comphy_deinit(port);
mvpp22_mode_reconfigure(port);
}
@@ -5038,7 +5063,6 @@ static int mvpp2_port_probe(struct platform_device *pdev,
struct fwnode_handle *port_fwnode,
struct mvpp2 *priv)
{
- struct phy *comphy = NULL;
struct mvpp2_port *port;
struct mvpp2_port_pcpu *port_pcpu;
struct device_node *port_node = to_of_node(port_fwnode);
@@ -5085,14 +5109,20 @@ static int mvpp2_port_probe(struct platform_device *pdev,
goto err_free_netdev;
}
+ port = netdev_priv(dev);
+
if (port_node) {
- comphy = devm_of_phy_get(&pdev->dev, port_node, NULL);
- if (IS_ERR(comphy)) {
- if (PTR_ERR(comphy) == -EPROBE_DEFER) {
- err = -EPROBE_DEFER;
- goto err_free_netdev;
+ for (i = 0; i < ARRAY_SIZE(port->comphys); i++) {
+ port->comphys[i] = devm_of_phy_get_by_index(&pdev->dev,
+ port_node,
+ i);
+ if (IS_ERR(port->comphys[i])) {
+ err = PTR_ERR(port->comphys[i]);
+ port->comphys[i] = NULL;
+ if (err == -EPROBE_DEFER)
+ goto err_free_netdev;
+ err = 0;
}
- comphy = NULL;
}
}
@@ -5107,7 +5137,6 @@ static int mvpp2_port_probe(struct platform_device *pdev,
dev->netdev_ops = &mvpp2_netdev_ops;
dev->ethtool_ops = &mvpp2_eth_tool_ops;
- port = netdev_priv(dev);
port->dev = dev;
port->fwnode = port_fwnode;
port->has_phy = !!of_find_property(port_node, "phy", NULL);
@@ -5144,7 +5173,6 @@ static int mvpp2_port_probe(struct platform_device *pdev,
port->of_node = port_node;
port->phy_interface = phy_mode;
- port->comphy = comphy;
if (priv->hw_version == MVPP21) {
port->base = devm_platform_ioremap_resource(pdev, 2 + id);
--
2.21.0
^ permalink raw reply related
* Re: [PATCH] net: sctp: Rename fallthrough label to unhandled
From: Neil Horman @ 2019-08-01 20:48 UTC (permalink / raw)
To: Joe Perches
Cc: Vlad Yasevich, Marcelo Ricardo Leitner, David S. Miller,
linux-sctp, netdev, linux-kernel
In-Reply-To: <a9d003ddd0d59fb144db3ecda3453b3d9c0cb139.camel@perches.com>
On Thu, Aug 01, 2019 at 10:42:31AM -0700, Joe Perches wrote:
> On Thu, 2019-08-01 at 06:50 -0400, Neil Horman wrote:
> > On Wed, Jul 31, 2019 at 03:23:46PM -0700, Joe Perches wrote:
> []
> > You can say that if you want, but you made the point that your think the macro
> > as you have written is more readable. You example illustrates though that /*
> > fallthrough */ is a pretty common comment, and not prefixing it makes it look
> > like someone didn't add a comment that they meant to. The __ prefix is standard
> > practice for defining macros to attributes (212 instances of it by my count). I
> > don't mind rewriting the goto labels at all, but I think consistency is
> > valuable.
>
> Hey Neil.
>
> Perhaps you want to make this argument on the RFC patch thread
> that introduces the fallthrough pseudo-keyword.
>
> https://lore.kernel.org/patchwork/patch/1108577/
>
>
>
Sure, but it will have to wait for tomorrow at this point, as I need to run to
an appointment.
Best
Neil
^ permalink raw reply
* [net-next 6/9] i40e: Update visual effect for advertised FEC mode.
From: Jeff Kirsher @ 2019-08-01 20:51 UTC (permalink / raw)
To: davem
Cc: Czeslaw Zagorski, netdev, nhorman, sassmann, Andrew Bowers,
Jeff Kirsher
In-Reply-To: <20190801205149.4114-1-jeffrey.t.kirsher@intel.com>
From: Czeslaw Zagorski <czeslawx.zagorski@intel.com>
Updates visual effect for advertised mode after setting desired mode.
The mode appears in advertised FEC mode correctly, when ethtool
interface command is called. Without this commit advertised FEC
is displayed regardless of the settings as "None BaseR RS".
Signed-off-by: Czeslaw Zagorski <czeslawx.zagorski@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
.../net/ethernet/intel/i40e/i40e_ethtool.c | 63 ++++++++++---------
1 file changed, 35 insertions(+), 28 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 65e016f54f58..ceca57a261dc 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -710,6 +710,35 @@ static void i40e_phy_type_to_ethtool(struct i40e_pf *pf,
}
}
+/**
+ * i40e_get_settings_link_up_fec - Get the FEC mode encoding from mask
+ * @req_fec_info: mask request FEC info
+ * @ks: ethtool ksettings to fill in
+ **/
+static void i40e_get_settings_link_up_fec(u8 req_fec_info,
+ struct ethtool_link_ksettings *ks)
+{
+ ethtool_link_ksettings_add_link_mode(ks, supported, FEC_NONE);
+ ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS);
+ ethtool_link_ksettings_add_link_mode(ks, supported, FEC_BASER);
+
+ if (I40E_AQ_SET_FEC_REQUEST_RS & req_fec_info) {
+ ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_RS);
+ } else if (I40E_AQ_SET_FEC_REQUEST_KR & req_fec_info) {
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ FEC_BASER);
+ } else {
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ FEC_NONE);
+ if (I40E_AQ_SET_FEC_AUTO & req_fec_info) {
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ FEC_RS);
+ ethtool_link_ksettings_add_link_mode(ks, advertising,
+ FEC_BASER);
+ }
+ }
+}
+
/**
* i40e_get_settings_link_up - Get the Link settings for when link is up
* @hw: hw structure
@@ -769,13 +798,7 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
25000baseSR_Full);
ethtool_link_ksettings_add_link_mode(ks, advertising,
25000baseSR_Full);
- ethtool_link_ksettings_add_link_mode(ks, supported, FEC_NONE);
- ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS);
- ethtool_link_ksettings_add_link_mode(ks, supported, FEC_BASER);
- ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_NONE);
- ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_RS);
- ethtool_link_ksettings_add_link_mode(ks, advertising,
- FEC_BASER);
+ i40e_get_settings_link_up_fec(hw_link_info->req_fec_info, ks);
ethtool_link_ksettings_add_link_mode(ks, supported,
10000baseSR_Full);
ethtool_link_ksettings_add_link_mode(ks, advertising,
@@ -892,9 +915,6 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
40000baseKR4_Full);
ethtool_link_ksettings_add_link_mode(ks, supported,
25000baseKR_Full);
- ethtool_link_ksettings_add_link_mode(ks, supported, FEC_NONE);
- ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS);
- ethtool_link_ksettings_add_link_mode(ks, supported, FEC_BASER);
ethtool_link_ksettings_add_link_mode(ks, supported,
20000baseKR2_Full);
ethtool_link_ksettings_add_link_mode(ks, supported,
@@ -908,10 +928,7 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
40000baseKR4_Full);
ethtool_link_ksettings_add_link_mode(ks, advertising,
25000baseKR_Full);
- ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_NONE);
- ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_RS);
- ethtool_link_ksettings_add_link_mode(ks, advertising,
- FEC_BASER);
+ i40e_get_settings_link_up_fec(hw_link_info->req_fec_info, ks);
ethtool_link_ksettings_add_link_mode(ks, advertising,
20000baseKR2_Full);
ethtool_link_ksettings_add_link_mode(ks, advertising,
@@ -929,13 +946,8 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
25000baseCR_Full);
ethtool_link_ksettings_add_link_mode(ks, advertising,
25000baseCR_Full);
- ethtool_link_ksettings_add_link_mode(ks, supported, FEC_NONE);
- ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS);
- ethtool_link_ksettings_add_link_mode(ks, supported, FEC_BASER);
- ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_NONE);
- ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_RS);
- ethtool_link_ksettings_add_link_mode(ks, advertising,
- FEC_BASER);
+ i40e_get_settings_link_up_fec(hw_link_info->req_fec_info, ks);
+
break;
case I40E_PHY_TYPE_25GBASE_AOC:
case I40E_PHY_TYPE_25GBASE_ACC:
@@ -945,13 +957,8 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
25000baseCR_Full);
ethtool_link_ksettings_add_link_mode(ks, advertising,
25000baseCR_Full);
- ethtool_link_ksettings_add_link_mode(ks, supported, FEC_NONE);
- ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS);
- ethtool_link_ksettings_add_link_mode(ks, supported, FEC_BASER);
- ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_NONE);
- ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_RS);
- ethtool_link_ksettings_add_link_mode(ks, advertising,
- FEC_BASER);
+ i40e_get_settings_link_up_fec(hw_link_info->req_fec_info, ks);
+
ethtool_link_ksettings_add_link_mode(ks, supported,
10000baseCR_Full);
ethtool_link_ksettings_add_link_mode(ks, advertising,
--
2.21.0
^ permalink raw reply related
* [net-next 8/9] i40e: verify string count matches even on early return
From: Jeff Kirsher @ 2019-08-01 20:51 UTC (permalink / raw)
To: davem; +Cc: Jacob Keller, netdev, nhorman, sassmann, Andrew Bowers,
Jeff Kirsher
In-Reply-To: <20190801205149.4114-1-jeffrey.t.kirsher@intel.com>
From: Jacob Keller <jacob.e.keller@intel.com>
Similar to i40e_get_ethtool_stats, add a goto to verify that the data
pointer for the strings lines up with the expected stats count. This
helps ensure that bugs are not introduced when adding stats.
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index ceca57a261dc..01e4615b1b4b 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -2342,7 +2342,7 @@ static void i40e_get_stat_strings(struct net_device *netdev, u8 *data)
}
if (vsi != pf->vsi[pf->lan_vsi] || pf->hw.partition_id != 1)
- return;
+ goto check_data_pointer;
i40e_add_stat_strings(&data, i40e_gstrings_veb_stats);
@@ -2354,6 +2354,7 @@ static void i40e_get_stat_strings(struct net_device *netdev, u8 *data)
for (i = 0; i < I40E_MAX_USER_PRIORITY; i++)
i40e_add_stat_strings(&data, i40e_gstrings_pfc_stats, i);
+check_data_pointer:
WARN_ONCE(data - p != i40e_get_stats_count(netdev) * ETH_GSTRING_LEN,
"stat strings count mismatch!");
}
--
2.21.0
^ permalink raw reply related
* [net-next 1/9] i40e: fix incorrect ethtool statistics veb and veb.tc_
From: Jeff Kirsher @ 2019-08-01 20:51 UTC (permalink / raw)
To: davem
Cc: Dmitrii Golovanov, netdev, nhorman, sassmann, Andrew Bowers,
Jeff Kirsher
In-Reply-To: <20190801205149.4114-1-jeffrey.t.kirsher@intel.com>
From: Dmitrii Golovanov <dmitrii.golovanov@intel.com>
This patch fixes missing call of i40e_update_veb_stats() in function
i40e_get_ethtool_stats() to update stats data of VEB and VEB TC
counters before they are written into ethtool buffer.
Before the patch ethtool counters may fell behind interface counters.
Signed-off-by: Dmitrii Golovanov <dmitrii.golovanov@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/i40e/i40e.h | 1 +
drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 8 +++++++-
drivers/net/ethernet/intel/i40e/i40e_main.c | 2 +-
3 files changed, 9 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index 84bd06901014..3e535d3263b3 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -1021,6 +1021,7 @@ i40e_find_vsi_by_type(struct i40e_pf *pf, u16 type)
return NULL;
}
void i40e_update_stats(struct i40e_vsi *vsi);
+void i40e_update_veb_stats(struct i40e_veb *veb);
void i40e_update_eth_stats(struct i40e_vsi *vsi);
struct rtnl_link_stats64 *i40e_get_vsi_stats_struct(struct i40e_vsi *vsi);
int i40e_fetch_switch_configuration(struct i40e_pf *pf,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 527eb52c5401..65e016f54f58 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -2250,7 +2250,7 @@ static void i40e_get_ethtool_stats(struct net_device *netdev,
struct i40e_netdev_priv *np = netdev_priv(netdev);
struct i40e_vsi *vsi = np->vsi;
struct i40e_pf *pf = vsi->back;
- struct i40e_veb *veb = pf->veb[pf->lan_veb];
+ struct i40e_veb *veb = NULL;
unsigned int i;
bool veb_stats;
u64 *p = data;
@@ -2273,8 +2273,14 @@ static void i40e_get_ethtool_stats(struct net_device *netdev,
goto check_data_pointer;
veb_stats = ((pf->lan_veb != I40E_NO_VEB) &&
+ (pf->lan_veb < I40E_MAX_VEB) &&
(pf->flags & I40E_FLAG_VEB_STATS_ENABLED));
+ if (veb_stats) {
+ veb = pf->veb[pf->lan_veb];
+ i40e_update_veb_stats(veb);
+ }
+
/* If veb stats aren't enabled, pass NULL instead of the veb so that
* we initialize stats to zero and update the data pointer
* intelligently
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 44da407e0bf9..d39940b9c8b7 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -677,7 +677,7 @@ void i40e_update_eth_stats(struct i40e_vsi *vsi)
* i40e_update_veb_stats - Update Switch component statistics
* @veb: the VEB being updated
**/
-static void i40e_update_veb_stats(struct i40e_veb *veb)
+void i40e_update_veb_stats(struct i40e_veb *veb)
{
struct i40e_pf *pf = veb->pf;
struct i40e_hw *hw = &pf->hw;
--
2.21.0
^ permalink raw reply related
* [net-next 4/9] i40e: don't report link up for a VF who hasn't enabled queues
From: Jeff Kirsher @ 2019-08-01 20:51 UTC (permalink / raw)
To: davem; +Cc: Jacob Keller, netdev, nhorman, sassmann, Andrew Bowers,
Jeff Kirsher
In-Reply-To: <20190801205149.4114-1-jeffrey.t.kirsher@intel.com>
From: Jacob Keller <jacob.e.keller@intel.com>
Commit d3d657a90850 ("i40e: update VFs of link state after
GET_VF_RESOURCES") modified the PF driver to notify a VF of
its link status immediately after it requests resources.
This was intended to fix reporting on VF drivers, so that they would
properly report link status.
However, some older VF drivers do not respond well to receiving a link
up notification before queues are enabled. This can cause their state
machine to think that it is safe to send traffic. This results in a Tx
hang on the VF.
More recent versions of the old i40evf and all versions of iavf are
resilient to these early link status messages. However, if a VM happens
to run an older version of the VF driver, this can be problematic.
Record whether the PF has actually enabled queues for the VF. When
reporting link status, always report link down if the queues aren't
enabled. In this way, the VF driver will never receive a link up
notification until after its queues are enabled.
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 13 ++++++++++++-
drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h | 1 +
2 files changed, 13 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 21f7ac514d1f..bffdea629982 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -55,7 +55,12 @@ static void i40e_vc_notify_vf_link_state(struct i40e_vf *vf)
pfe.event = VIRTCHNL_EVENT_LINK_CHANGE;
pfe.severity = PF_EVENT_SEVERITY_INFO;
- if (vf->link_forced) {
+
+ /* Always report link is down if the VF queues aren't enabled */
+ if (!vf->queues_enabled) {
+ pfe.event_data.link_event.link_status = false;
+ pfe.event_data.link_event.link_speed = 0;
+ } else if (vf->link_forced) {
pfe.event_data.link_event.link_status = vf->link_up;
pfe.event_data.link_event.link_speed =
(vf->link_up ? VIRTCHNL_LINK_SPEED_40GB : 0);
@@ -65,6 +70,7 @@ static void i40e_vc_notify_vf_link_state(struct i40e_vf *vf)
pfe.event_data.link_event.link_speed =
i40e_virtchnl_link_speed(ls->link_speed);
}
+
i40e_aq_send_msg_to_vf(hw, abs_vf_id, VIRTCHNL_OP_EVENT,
0, (u8 *)&pfe, sizeof(pfe), NULL);
}
@@ -2364,6 +2370,8 @@ static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg)
}
}
+ vf->queues_enabled = true;
+
error_param:
/* send the response to the VF */
return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_ENABLE_QUEUES,
@@ -2385,6 +2393,9 @@ static int i40e_vc_disable_queues_msg(struct i40e_vf *vf, u8 *msg)
struct i40e_pf *pf = vf->pf;
i40e_status aq_ret = 0;
+ /* Immediately mark queues as disabled */
+ vf->queues_enabled = false;
+
if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
aq_ret = I40E_ERR_PARAM;
goto error_param;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
index f65cc0c16550..7164b9bb294f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
@@ -99,6 +99,7 @@ struct i40e_vf {
unsigned int tx_rate; /* Tx bandwidth limit in Mbps */
bool link_forced;
bool link_up; /* only valid if VF link is forced */
+ bool queues_enabled; /* true if the VF queues are enabled */
bool spoofchk;
u16 num_mac;
u16 num_vlan;
--
2.21.0
^ permalink raw reply related
* [net-next 9/9] i40e: Remove unicast log when VF is leaving multicast mode.
From: Jeff Kirsher @ 2019-08-01 20:51 UTC (permalink / raw)
To: davem
Cc: Czeslaw Zagorski, netdev, nhorman, sassmann, Andrew Bowers,
Jeff Kirsher
In-Reply-To: <20190801205149.4114-1-jeffrey.t.kirsher@intel.com>
From: Czeslaw Zagorski <czeslawx.zagorski@intel.com>
This patch removes unicast log when VF is leaving multicast mode.
Added check of vf->vf_states &
I40E_VF_STATE_MC_PROMISC/I40E_VF_STATE_UC_PROMISC.
Without this commit, leaving multicast mode logs "unset unicast"
in dmsg.
Signed-off-by: Czeslaw Zagorski <czeslawx.zagorski@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
.../ethernet/intel/i40e/i40e_virtchnl_pf.c | 39 ++++++++++---------
1 file changed, 21 insertions(+), 18 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 618781b3b7ac..7bc4e397d56d 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -2043,30 +2043,33 @@ static int i40e_vc_config_promiscuous_mode_msg(struct i40e_vf *vf, u8 *msg)
alluni = true;
aq_ret = i40e_config_vf_promiscuous_mode(vf, info->vsi_id, allmulti,
alluni);
- if (!aq_ret) {
- if (allmulti) {
+ if (aq_ret)
+ goto err_out;
+
+ if (allmulti) {
+ if (!test_and_set_bit(I40E_VF_STATE_MC_PROMISC,
+ &vf->vf_states))
dev_info(&pf->pdev->dev,
"VF %d successfully set multicast promiscuous mode\n",
vf->vf_id);
- set_bit(I40E_VF_STATE_MC_PROMISC, &vf->vf_states);
- } else {
- dev_info(&pf->pdev->dev,
- "VF %d successfully unset multicast promiscuous mode\n",
- vf->vf_id);
- clear_bit(I40E_VF_STATE_MC_PROMISC, &vf->vf_states);
- }
- if (alluni) {
+ } else if (test_and_clear_bit(I40E_VF_STATE_MC_PROMISC,
+ &vf->vf_states))
+ dev_info(&pf->pdev->dev,
+ "VF %d successfully unset multicast promiscuous mode\n",
+ vf->vf_id);
+
+ if (alluni) {
+ if (!test_and_set_bit(I40E_VF_STATE_UC_PROMISC,
+ &vf->vf_states))
dev_info(&pf->pdev->dev,
"VF %d successfully set unicast promiscuous mode\n",
vf->vf_id);
- set_bit(I40E_VF_STATE_UC_PROMISC, &vf->vf_states);
- } else {
- dev_info(&pf->pdev->dev,
- "VF %d successfully unset unicast promiscuous mode\n",
- vf->vf_id);
- clear_bit(I40E_VF_STATE_UC_PROMISC, &vf->vf_states);
- }
- }
+ } else if (test_and_clear_bit(I40E_VF_STATE_UC_PROMISC,
+ &vf->vf_states))
+ dev_info(&pf->pdev->dev,
+ "VF %d successfully unset unicast promiscuous mode\n",
+ vf->vf_id);
+
err_out:
/* send the response to the VF */
return i40e_vc_send_resp_to_vf(vf,
--
2.21.0
^ permalink raw reply related
* [net-next 7/9] i40e: Log info when PF is entering and leaving Allmulti mode.
From: Jeff Kirsher @ 2019-08-01 20:51 UTC (permalink / raw)
To: davem
Cc: Czeslaw Zagorski, netdev, nhorman, sassmann, Andrew Bowers,
Jeff Kirsher
In-Reply-To: <20190801205149.4114-1-jeffrey.t.kirsher@intel.com>
From: Czeslaw Zagorski <czeslawx.zagorski@intel.com>
Add log when PF is entering and leaving allmulti mode. The
change of PF state is visible in dmesg now. Without this commit,
entering and leaving allmulti mode is not logged in dmesg.
Signed-off-by: Czeslaw Zagorski <czeslawx.zagorski@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/i40e/i40e_main.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 423a4820af4c..6d456e579314 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -2530,6 +2530,10 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
vsi_name,
i40e_stat_str(hw, aq_ret),
i40e_aq_str(hw, hw->aq.asq_last_status));
+ } else {
+ dev_info(&pf->pdev->dev, "%s is %s allmulti mode.\n",
+ vsi->netdev->name,
+ cur_multipromisc ? "entering" : "leaving");
}
}
--
2.21.0
^ permalink raw reply related
* [net-next 5/9] i40e: fix code comments
From: Jeff Kirsher @ 2019-08-01 20:51 UTC (permalink / raw)
To: davem; +Cc: Jeff Kirsher, netdev, nhorman, sassmann, Andrew Bowers
In-Reply-To: <20190801205149.4114-1-jeffrey.t.kirsher@intel.com>
Found a code comment that needed TLC to correct their formatting.
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
---
drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index bffdea629982..618781b3b7ac 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -2159,7 +2159,7 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg)
* VF does not know about these additional VSIs and all
* it cares is about its own queues. PF configures these queues
* to its appropriate VSIs based on TC mapping
- **/
+ */
if (vf->adq_enabled) {
if (idx >= ARRAY_SIZE(vf->ch)) {
aq_ret = I40E_ERR_NO_AVAILABLE_VSI;
--
2.21.0
^ permalink raw reply related
* [net-next 2/9] i40e: make visible changed vf mac on host
From: Jeff Kirsher @ 2019-08-01 20:51 UTC (permalink / raw)
To: davem
Cc: Aleksandr Loktionov, netdev, nhorman, sassmann, Andrew Bowers,
Jeff Kirsher
In-Reply-To: <20190801205149.4114-1-jeffrey.t.kirsher@intel.com>
From: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
This patch makes changed VM mac address visible on host via
ip link show command. This problem is fixed by copying last
unicast mac filter to vf->default_lan_addr.addr. Without
this patch if VF MAC was not set from host side and
if you run ip link show $pf, on host side you'd always
see a zero MAC, not the real VF MAC that VF assigned to
itself.
Signed-off-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 02b09a8ad54c..21f7ac514d1f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -2629,6 +2629,9 @@ static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg)
} else {
vf->num_mac++;
}
+ if (is_valid_ether_addr(al->list[i].addr))
+ ether_addr_copy(vf->default_lan_addr.addr,
+ al->list[i].addr);
}
}
spin_unlock_bh(&vsi->mac_filter_hash_lock);
--
2.21.0
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox