* [PATCH net-next 1/9] net_sched: act_vlan: add helper inlines to access tcf_vlan info
2016-09-22 17:01 [PATCH net-next 0/9] Mellanox 100G SRIOV offloads vlan push/pop Saeed Mahameed
@ 2016-09-22 17:01 ` Saeed Mahameed
2016-09-22 17:01 ` [PATCH net-next 2/9] net/mlx5: E-Switch, Set the vport when registering the uplink rep Saeed Mahameed
` (8 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: Saeed Mahameed @ 2016-09-22 17:01 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Or Gerlitz, Hadar Hen-Zion, Jiri Pirko, Andy Gospodarek,
Jesse Brandeburg, John Fastabend, Amir Vadai, Saeed Mahameed
From: Or Gerlitz <ogerlitz@mellanox.com>
Needed e.g for offloading drivers to pick the relevant attributes.
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
include/net/tc_act/tc_vlan.h | 25 +++++++++++++++++++++++++
1 file changed, 25 insertions(+)
diff --git a/include/net/tc_act/tc_vlan.h b/include/net/tc_act/tc_vlan.h
index 6b83588..48cca32 100644
--- a/include/net/tc_act/tc_vlan.h
+++ b/include/net/tc_act/tc_vlan.h
@@ -11,6 +11,7 @@
#define __NET_TC_VLAN_H
#include <net/act_api.h>
+#include <linux/tc_act/tc_vlan.h>
#define VLAN_F_POP 0x1
#define VLAN_F_PUSH 0x2
@@ -24,4 +25,28 @@ struct tcf_vlan {
};
#define to_vlan(a) ((struct tcf_vlan *)a)
+static inline bool is_tcf_vlan(const struct tc_action *a)
+{
+#ifdef CONFIG_NET_CLS_ACT
+ if (a->ops && a->ops->type == TCA_ACT_VLAN)
+ return true;
+#endif
+ return false;
+}
+
+static inline u32 tcf_vlan_action(const struct tc_action *a)
+{
+ return to_vlan(a)->tcfv_action;
+}
+
+static inline u16 tcf_vlan_push_vid(const struct tc_action *a)
+{
+ return to_vlan(a)->tcfv_push_vid;
+}
+
+static inline __be16 tcf_vlan_push_proto(const struct tc_action *a)
+{
+ return to_vlan(a)->tcfv_push_proto;
+}
+
#endif /* __NET_TC_VLAN_H */
--
2.7.4
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH net-next 2/9] net/mlx5: E-Switch, Set the vport when registering the uplink rep
2016-09-22 17:01 [PATCH net-next 0/9] Mellanox 100G SRIOV offloads vlan push/pop Saeed Mahameed
2016-09-22 17:01 ` [PATCH net-next 1/9] net_sched: act_vlan: add helper inlines to access tcf_vlan info Saeed Mahameed
@ 2016-09-22 17:01 ` Saeed Mahameed
2016-09-22 17:01 ` [PATCH net-next 3/9] net/mlx5: E-Switch, Set vport representor fields explicitly on registration Saeed Mahameed
` (7 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: Saeed Mahameed @ 2016-09-22 17:01 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Or Gerlitz, Hadar Hen-Zion, Jiri Pirko, Andy Gospodarek,
Jesse Brandeburg, John Fastabend, Amir Vadai, Saeed Mahameed
From: Or Gerlitz <ogerlitz@mellanox.com>
Set the vport value in the PF entry to be that of the uplink so
we can use it blindly over the tc / eswitch offload code without
translating it each time we deal with the uplink representor.
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 6 ++---
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 10 ++------
drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 3 ++-
.../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 27 +++++++++++-----------
4 files changed, 20 insertions(+), 26 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index a9fc9d4..b309e7c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3726,9 +3726,9 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv)
mlx5_query_nic_vport_mac_address(mdev, 0, rep.hw_id);
rep.load = mlx5e_nic_rep_load;
rep.unload = mlx5e_nic_rep_unload;
- rep.vport = 0;
+ rep.vport = FDB_UPLINK_VPORT;
rep.priv_data = priv;
- mlx5_eswitch_register_vport_rep(esw, &rep);
+ mlx5_eswitch_register_vport_rep(esw, 0, &rep);
}
}
@@ -3867,7 +3867,7 @@ static void mlx5e_register_vport_rep(struct mlx5_core_dev *mdev)
rep.unload = mlx5e_vport_rep_unload;
rep.vport = vport;
ether_addr_copy(rep.hw_id, mac);
- mlx5_eswitch_register_vport_rep(esw, &rep);
+ mlx5_eswitch_register_vport_rep(esw, vport, &rep);
}
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 22cfc4a..783e122 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -120,10 +120,7 @@ static struct mlx5_flow_rule *mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
struct mlx5_eswitch_rep *rep = priv->ppriv;
u32 src_vport;
- if (rep->vport) /* set source vport for the flow */
- src_vport = rep->vport;
- else
- src_vport = FDB_UPLINK_VPORT;
+ src_vport = rep->vport;
return mlx5_eswitch_add_offloaded_rule(esw, spec, action, src_vport, dst_vport);
}
@@ -399,10 +396,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
out_priv = netdev_priv(out_dev);
out_rep = out_priv->ppriv;
- if (out_rep->vport == 0)
- *dest_vport = FDB_UPLINK_VPORT;
- else
- *dest_vport = out_rep->vport;
+ *dest_vport = out_rep->vport;
*action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
continue;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index b96e8c9..6d8c5a2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -254,9 +254,10 @@ void mlx5_eswitch_sqs2vport_stop(struct mlx5_eswitch *esw,
int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode);
int mlx5_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode);
void mlx5_eswitch_register_vport_rep(struct mlx5_eswitch *esw,
+ int vport_index,
struct mlx5_eswitch_rep *rep);
void mlx5_eswitch_unregister_vport_rep(struct mlx5_eswitch *esw,
- int vport);
+ int vport_index);
#define MLX5_DEBUG_ESWITCH_MASK BIT(3)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 3dc83a9..a73721b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -144,16 +144,12 @@ int mlx5_eswitch_sqs2vport_start(struct mlx5_eswitch *esw,
{
struct mlx5_flow_rule *flow_rule;
struct mlx5_esw_sq *esw_sq;
- int vport;
int err;
int i;
if (esw->mode != SRIOV_OFFLOADS)
return 0;
- vport = rep->vport == 0 ?
- FDB_UPLINK_VPORT : rep->vport;
-
for (i = 0; i < sqns_num; i++) {
esw_sq = kzalloc(sizeof(*esw_sq), GFP_KERNEL);
if (!esw_sq) {
@@ -163,7 +159,7 @@ int mlx5_eswitch_sqs2vport_start(struct mlx5_eswitch *esw,
/* Add re-inject rule to the PF/representor sqs */
flow_rule = mlx5_eswitch_add_send_to_vport_rule(esw,
- vport,
+ rep->vport,
sqns_array[i]);
if (IS_ERR(flow_rule)) {
err = PTR_ERR(flow_rule);
@@ -612,27 +608,30 @@ int mlx5_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode)
}
void mlx5_eswitch_register_vport_rep(struct mlx5_eswitch *esw,
- struct mlx5_eswitch_rep *rep)
+ int vport_index,
+ struct mlx5_eswitch_rep *__rep)
{
struct mlx5_esw_offload *offloads = &esw->offloads;
+ struct mlx5_eswitch_rep *rep;
+
+ rep = &offloads->vport_reps[vport_index];
- memcpy(&offloads->vport_reps[rep->vport], rep,
- sizeof(struct mlx5_eswitch_rep));
+ memcpy(rep, __rep, sizeof(struct mlx5_eswitch_rep));
- INIT_LIST_HEAD(&offloads->vport_reps[rep->vport].vport_sqs_list);
- offloads->vport_reps[rep->vport].valid = true;
+ INIT_LIST_HEAD(&rep->vport_sqs_list);
+ rep->valid = true;
}
void mlx5_eswitch_unregister_vport_rep(struct mlx5_eswitch *esw,
- int vport)
+ int vport_index)
{
struct mlx5_esw_offload *offloads = &esw->offloads;
struct mlx5_eswitch_rep *rep;
- rep = &offloads->vport_reps[vport];
+ rep = &offloads->vport_reps[vport_index];
- if (esw->mode == SRIOV_OFFLOADS && esw->vports[vport].enabled)
+ if (esw->mode == SRIOV_OFFLOADS && esw->vports[vport_index].enabled)
rep->unload(esw, rep);
- offloads->vport_reps[vport].valid = false;
+ rep->valid = false;
}
--
2.7.4
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH net-next 3/9] net/mlx5: E-Switch, Set vport representor fields explicitly on registration
2016-09-22 17:01 [PATCH net-next 0/9] Mellanox 100G SRIOV offloads vlan push/pop Saeed Mahameed
2016-09-22 17:01 ` [PATCH net-next 1/9] net_sched: act_vlan: add helper inlines to access tcf_vlan info Saeed Mahameed
2016-09-22 17:01 ` [PATCH net-next 2/9] net/mlx5: E-Switch, Set the vport when registering the uplink rep Saeed Mahameed
@ 2016-09-22 17:01 ` Saeed Mahameed
2016-09-22 17:01 ` [PATCH net-next 4/9] net/mlx5: E-Switch, Allow fine tuning of eswitch vport push/pop vlan Saeed Mahameed
` (6 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: Saeed Mahameed @ 2016-09-22 17:01 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Or Gerlitz, Hadar Hen-Zion, Jiri Pirko, Andy Gospodarek,
Jesse Brandeburg, John Fastabend, Amir Vadai, Saeed Mahameed
From: Or Gerlitz <ogerlitz@mellanox.com>
The structure we use for the eswitch vport representor (mlx5_eswitch_rep)
has some fields which are set from upper layers in the driver when they
register the rep. Use explicit setting on registration time for them and
avoid global memcpy. This patch doesn't add new functionality.
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 5 +++--
drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 8 +++++++-
2 files changed, 10 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 6d8c5a2..ebfcde0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -178,11 +178,12 @@ struct mlx5_eswitch_rep {
void (*unload)(struct mlx5_eswitch *esw,
struct mlx5_eswitch_rep *rep);
u16 vport;
- struct mlx5_flow_rule *vport_rx_rule;
+ u8 hw_id[ETH_ALEN];
void *priv_data;
+
+ struct mlx5_flow_rule *vport_rx_rule;
struct list_head vport_sqs_list;
bool valid;
- u8 hw_id[ETH_ALEN];
};
struct mlx5_esw_offload {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index a73721b..b901cd4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -616,7 +616,13 @@ void mlx5_eswitch_register_vport_rep(struct mlx5_eswitch *esw,
rep = &offloads->vport_reps[vport_index];
- memcpy(rep, __rep, sizeof(struct mlx5_eswitch_rep));
+ memset(rep, 0, sizeof(*rep));
+
+ rep->load = __rep->load;
+ rep->unload = __rep->unload;
+ rep->vport = __rep->vport;
+ rep->priv_data = __rep->priv_data;
+ ether_addr_copy(rep->hw_id, __rep->hw_id);
INIT_LIST_HEAD(&rep->vport_sqs_list);
rep->valid = true;
--
2.7.4
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH net-next 4/9] net/mlx5: E-Switch, Allow fine tuning of eswitch vport push/pop vlan
2016-09-22 17:01 [PATCH net-next 0/9] Mellanox 100G SRIOV offloads vlan push/pop Saeed Mahameed
` (2 preceding siblings ...)
2016-09-22 17:01 ` [PATCH net-next 3/9] net/mlx5: E-Switch, Set vport representor fields explicitly on registration Saeed Mahameed
@ 2016-09-22 17:01 ` Saeed Mahameed
2016-09-22 17:01 ` [PATCH net-next 5/9] net/mlx5: Put elements related to offloaded TC rule in one struct Saeed Mahameed
` (5 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: Saeed Mahameed @ 2016-09-22 17:01 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Or Gerlitz, Hadar Hen-Zion, Jiri Pirko, Andy Gospodarek,
Jesse Brandeburg, John Fastabend, Amir Vadai, Saeed Mahameed
From: Or Gerlitz <ogerlitz@mellanox.com>
The HW can be programmed to push vlan, pop vlan or both.
A factorization step towards using the push/pop capabilties in the
eswitch offloads mode. This patch doesn't add new functionality.
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 33 +++++++++++++++--------
drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 5 ++++
2 files changed, 27 insertions(+), 11 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 4927494..6605453 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -127,7 +127,7 @@ static int modify_esw_vport_context_cmd(struct mlx5_core_dev *dev, u16 vport,
}
static int modify_esw_vport_cvlan(struct mlx5_core_dev *dev, u32 vport,
- u16 vlan, u8 qos, bool set)
+ u16 vlan, u8 qos, u8 set_flags)
{
u32 in[MLX5_ST_SZ_DW(modify_esw_vport_context_in)] = {0};
@@ -135,14 +135,18 @@ static int modify_esw_vport_cvlan(struct mlx5_core_dev *dev, u32 vport,
!MLX5_CAP_ESW(dev, vport_cvlan_insert_if_not_exist))
return -ENOTSUPP;
- esw_debug(dev, "Set Vport[%d] VLAN %d qos %d set=%d\n",
- vport, vlan, qos, set);
- if (set) {
+ esw_debug(dev, "Set Vport[%d] VLAN %d qos %d set=%x\n",
+ vport, vlan, qos, set_flags);
+
+ if (set_flags & SET_VLAN_STRIP)
MLX5_SET(modify_esw_vport_context_in, in,
esw_vport_context.vport_cvlan_strip, 1);
+
+ if (set_flags & SET_VLAN_INSERT) {
/* insert only if no vlan in packet */
MLX5_SET(modify_esw_vport_context_in, in,
esw_vport_context.vport_cvlan_insert, 1);
+
MLX5_SET(modify_esw_vport_context_in, in,
esw_vport_context.cvlan_pcp, qos);
MLX5_SET(modify_esw_vport_context_in, in,
@@ -1777,25 +1781,21 @@ int mlx5_eswitch_get_vport_config(struct mlx5_eswitch *esw,
return 0;
}
-int mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw,
- int vport, u16 vlan, u8 qos)
+int __mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw,
+ int vport, u16 vlan, u8 qos, u8 set_flags)
{
struct mlx5_vport *evport;
int err = 0;
- int set = 0;
if (!ESW_ALLOWED(esw))
return -EPERM;
if (!LEGAL_VPORT(esw, vport) || (vlan > 4095) || (qos > 7))
return -EINVAL;
- if (vlan || qos)
- set = 1;
-
mutex_lock(&esw->state_lock);
evport = &esw->vports[vport];
- err = modify_esw_vport_cvlan(esw->dev, vport, vlan, qos, set);
+ err = modify_esw_vport_cvlan(esw->dev, vport, vlan, qos, set_flags);
if (err)
goto unlock;
@@ -1813,6 +1813,17 @@ unlock:
return err;
}
+int mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw,
+ int vport, u16 vlan, u8 qos)
+{
+ u8 set_flags = 0;
+
+ if (vlan || qos)
+ set_flags = SET_VLAN_STRIP | SET_VLAN_INSERT;
+
+ return __mlx5_eswitch_set_vport_vlan(esw, vport, vlan, qos, set_flags);
+}
+
int mlx5_eswitch_set_vport_spoofchk(struct mlx5_eswitch *esw,
int vport, bool spoofchk)
{
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index ebfcde0..4f5391a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -246,6 +246,11 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
struct mlx5_flow_rule *
mlx5_eswitch_create_vport_rx_rule(struct mlx5_eswitch *esw, int vport, u32 tirn);
+enum {
+ SET_VLAN_STRIP = BIT(0),
+ SET_VLAN_INSERT = BIT(1)
+};
+
int mlx5_eswitch_sqs2vport_start(struct mlx5_eswitch *esw,
struct mlx5_eswitch_rep *rep,
u16 *sqns_array, int sqns_num);
--
2.7.4
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH net-next 5/9] net/mlx5: Put elements related to offloaded TC rule in one struct
2016-09-22 17:01 [PATCH net-next 0/9] Mellanox 100G SRIOV offloads vlan push/pop Saeed Mahameed
` (3 preceding siblings ...)
2016-09-22 17:01 ` [PATCH net-next 4/9] net/mlx5: E-Switch, Allow fine tuning of eswitch vport push/pop vlan Saeed Mahameed
@ 2016-09-22 17:01 ` Saeed Mahameed
2016-09-22 17:01 ` [PATCH net-next 6/9] net/mlx5e: Refactor retrival of skb from rx completion element (cqe) Saeed Mahameed
` (4 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: Saeed Mahameed @ 2016-09-22 17:01 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Or Gerlitz, Hadar Hen-Zion, Jiri Pirko, Andy Gospodarek,
Jesse Brandeburg, John Fastabend, Amir Vadai, Saeed Mahameed
From: Or Gerlitz <ogerlitz@mellanox.com>
Put the representors related to the source and dest vports and the
action in struct mlx5_esw_flow_attr which is used while setting the FDB rule.
This patch doesn't change any functionality.
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 51 ++++++++++++----------
drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 10 ++++-
.../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 9 ++--
3 files changed, 44 insertions(+), 26 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 783e122..3eb319b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -39,6 +39,7 @@
#include <linux/rhashtable.h>
#include <net/switchdev.h>
#include <net/tc_act/tc_mirred.h>
+#include <net/tc_act/tc_vlan.h>
#include "en.h"
#include "en_tc.h"
#include "eswitch.h"
@@ -47,6 +48,7 @@ struct mlx5e_tc_flow {
struct rhash_head node;
u64 cookie;
struct mlx5_flow_rule *rule;
+ struct mlx5_esw_flow_attr *attr;
};
#define MLX5E_TC_TABLE_NUM_ENTRIES 1024
@@ -114,15 +116,11 @@ err_create_ft:
static struct mlx5_flow_rule *mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
struct mlx5_flow_spec *spec,
- u32 action, u32 dst_vport)
+ struct mlx5_esw_flow_attr *attr)
{
struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
- struct mlx5_eswitch_rep *rep = priv->ppriv;
- u32 src_vport;
- src_vport = rep->vport;
-
- return mlx5_eswitch_add_offloaded_rule(esw, spec, action, src_vport, dst_vport);
+ return mlx5_eswitch_add_offloaded_rule(esw, spec, attr);
}
static void mlx5e_tc_del_flow(struct mlx5e_priv *priv,
@@ -358,7 +356,7 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
}
static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
- u32 *action, u32 *dest_vport)
+ struct mlx5_esw_flow_attr *attr)
{
const struct tc_action *a;
LIST_HEAD(actions);
@@ -366,17 +364,18 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
if (tc_no_actions(exts))
return -EINVAL;
- *action = 0;
+ memset(attr, 0, sizeof(*attr));
+ attr->in_rep = priv->ppriv;
tcf_exts_to_list(exts, &actions);
list_for_each_entry(a, &actions, list) {
/* Only support a single action per rule */
- if (*action)
+ if (attr->action)
return -EINVAL;
if (is_tcf_gact_shot(a)) {
- *action = MLX5_FLOW_CONTEXT_ACTION_DROP |
- MLX5_FLOW_CONTEXT_ACTION_COUNT;
+ attr->action = MLX5_FLOW_CONTEXT_ACTION_DROP |
+ MLX5_FLOW_CONTEXT_ACTION_COUNT;
continue;
}
@@ -384,7 +383,6 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
int ifindex = tcf_mirred_ifindex(a);
struct net_device *out_dev;
struct mlx5e_priv *out_priv;
- struct mlx5_eswitch_rep *out_rep;
out_dev = __dev_get_by_index(dev_net(priv->netdev), ifindex);
@@ -394,10 +392,9 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
return -EINVAL;
}
+ attr->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
out_priv = netdev_priv(out_dev);
- out_rep = out_priv->ppriv;
- *dest_vport = out_rep->vport;
- *action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+ attr->out_rep = out_priv->ppriv;
continue;
}
@@ -411,18 +408,27 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv, __be16 protocol,
{
struct mlx5e_tc_table *tc = &priv->fs.tc;
int err = 0;
- u32 flow_tag, action, dest_vport = 0;
+ bool fdb_flow = false;
+ u32 flow_tag, action;
struct mlx5e_tc_flow *flow;
struct mlx5_flow_spec *spec;
struct mlx5_flow_rule *old = NULL;
struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+ if (esw && esw->mode == SRIOV_OFFLOADS)
+ fdb_flow = true;
+
flow = rhashtable_lookup_fast(&tc->ht, &f->cookie,
tc->ht_params);
- if (flow)
+ if (flow) {
old = flow->rule;
- else
- flow = kzalloc(sizeof(*flow), GFP_KERNEL);
+ } else {
+ if (fdb_flow)
+ flow = kzalloc(sizeof(*flow) + sizeof(struct mlx5_esw_flow_attr),
+ GFP_KERNEL);
+ else
+ flow = kzalloc(sizeof(*flow), GFP_KERNEL);
+ }
spec = mlx5_vzalloc(sizeof(*spec));
if (!spec || !flow) {
@@ -436,11 +442,12 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv, __be16 protocol,
if (err < 0)
goto err_free;
- if (esw && esw->mode == SRIOV_OFFLOADS) {
- err = parse_tc_fdb_actions(priv, f->exts, &action, &dest_vport);
+ if (fdb_flow) {
+ flow->attr = (struct mlx5_esw_flow_attr *)(flow + 1);
+ err = parse_tc_fdb_actions(priv, f->exts, flow->attr);
if (err < 0)
goto err_free;
- flow->rule = mlx5e_tc_add_fdb_flow(priv, spec, action, dest_vport);
+ flow->rule = mlx5e_tc_add_fdb_flow(priv, spec, flow->attr);
} else {
err = parse_tc_nic_actions(priv, f->exts, &action, &flow_tag);
if (err < 0)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 4f5391a..eeeeadc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -238,11 +238,12 @@ int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw,
struct ifla_vf_stats *vf_stats);
struct mlx5_flow_spec;
+struct mlx5_esw_flow_attr;
struct mlx5_flow_rule *
mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
struct mlx5_flow_spec *spec,
- u32 action, u32 src_vport, u32 dst_vport);
+ struct mlx5_esw_flow_attr *attr);
struct mlx5_flow_rule *
mlx5_eswitch_create_vport_rx_rule(struct mlx5_eswitch *esw, int vport, u32 tirn);
@@ -251,6 +252,13 @@ enum {
SET_VLAN_INSERT = BIT(1)
};
+struct mlx5_esw_flow_attr {
+ struct mlx5_eswitch_rep *in_rep;
+ struct mlx5_eswitch_rep *out_rep;
+
+ int action;
+};
+
int mlx5_eswitch_sqs2vport_start(struct mlx5_eswitch *esw,
struct mlx5_eswitch_rep *rep,
u16 *sqns_array, int sqns_num);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index b901cd4..c0d9d1a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -46,19 +46,22 @@ enum {
struct mlx5_flow_rule *
mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
struct mlx5_flow_spec *spec,
- u32 action, u32 src_vport, u32 dst_vport)
+ struct mlx5_esw_flow_attr *attr)
{
struct mlx5_flow_destination dest = { 0 };
struct mlx5_fc *counter = NULL;
struct mlx5_flow_rule *rule;
void *misc;
+ int action;
if (esw->mode != SRIOV_OFFLOADS)
return ERR_PTR(-EOPNOTSUPP);
+ action = attr->action;
+
if (action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) {
dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
- dest.vport_num = dst_vport;
+ dest.vport_num = attr->out_rep->vport;
action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
} else if (action & MLX5_FLOW_CONTEXT_ACTION_COUNT) {
counter = mlx5_fc_create(esw->dev, true);
@@ -69,7 +72,7 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
}
misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
- MLX5_SET(fte_match_set_misc, misc, source_port, src_vport);
+ MLX5_SET(fte_match_set_misc, misc, source_port, attr->in_rep->vport);
misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
--
2.7.4
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH net-next 6/9] net/mlx5e: Refactor retrival of skb from rx completion element (cqe)
2016-09-22 17:01 [PATCH net-next 0/9] Mellanox 100G SRIOV offloads vlan push/pop Saeed Mahameed
` (4 preceding siblings ...)
2016-09-22 17:01 ` [PATCH net-next 5/9] net/mlx5: Put elements related to offloaded TC rule in one struct Saeed Mahameed
@ 2016-09-22 17:01 ` Saeed Mahameed
2016-09-22 17:01 ` [PATCH net-next 7/9] net/mlx5: E-Switch, Support VLAN actions in the offloads mode Saeed Mahameed
` (3 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: Saeed Mahameed @ 2016-09-22 17:01 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Or Gerlitz, Hadar Hen-Zion, Jiri Pirko, Andy Gospodarek,
Jesse Brandeburg, John Fastabend, Amir Vadai, Saeed Mahameed
From: Or Gerlitz <ogerlitz@mellanox.com>
Factor the relevant code into a static inline helper (skb_from_cqe)
doing that.
Move the call to napi_gro_receive to be carried out just
after mlx5e_complete_rx_cqe returns.
Both changes are to be used for the VF representor as well
in the next commit.
This patch doesn't change any functionality.
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 41 +++++++++++++++++--------
1 file changed, 28 insertions(+), 13 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 0a81bd3..e836e47 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -629,7 +629,6 @@ static inline void mlx5e_complete_rx_cqe(struct mlx5e_rq *rq,
rq->stats.packets++;
rq->stats.bytes += cqe_bcnt;
mlx5e_build_rx_skb(cqe, cqe_bcnt, rq, skb);
- napi_gro_receive(rq->cq.napi, skb);
}
static inline void mlx5e_xmit_xdp_doorbell(struct mlx5e_sq *sq)
@@ -733,20 +732,15 @@ static inline bool mlx5e_xdp_handle(struct mlx5e_rq *rq,
}
}
-void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
+static inline
+struct sk_buff *skb_from_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
+ u16 wqe_counter, u32 cqe_bcnt)
{
struct bpf_prog *xdp_prog = READ_ONCE(rq->xdp_prog);
struct mlx5e_dma_info *di;
- struct mlx5e_rx_wqe *wqe;
- __be16 wqe_counter_be;
struct sk_buff *skb;
- u16 wqe_counter;
void *va, *data;
- u32 cqe_bcnt;
- wqe_counter_be = cqe->wqe_counter;
- wqe_counter = be16_to_cpu(wqe_counter_be);
- wqe = mlx5_wq_ll_get_wqe(&rq->wq, wqe_counter);
di = &rq->dma_info[wqe_counter];
va = page_address(di->page);
data = va + MLX5_RX_HEADROOM;
@@ -757,22 +751,21 @@ void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
rq->buff.wqe_sz,
DMA_FROM_DEVICE);
prefetch(data);
- cqe_bcnt = be32_to_cpu(cqe->byte_cnt);
if (unlikely((cqe->op_own >> 4) != MLX5_CQE_RESP_SEND)) {
rq->stats.wqe_err++;
mlx5e_page_release(rq, di, true);
- goto wq_ll_pop;
+ return NULL;
}
if (mlx5e_xdp_handle(rq, xdp_prog, di, data, cqe_bcnt))
- goto wq_ll_pop; /* page/packet was consumed by XDP */
+ return NULL; /* page/packet was consumed by XDP */
skb = build_skb(va, RQ_PAGE_SIZE(rq));
if (unlikely(!skb)) {
rq->stats.buff_alloc_err++;
mlx5e_page_release(rq, di, true);
- goto wq_ll_pop;
+ return NULL;
}
/* queue up for recycling ..*/
@@ -782,7 +775,28 @@ void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
skb_reserve(skb, MLX5_RX_HEADROOM);
skb_put(skb, cqe_bcnt);
+ return skb;
+}
+
+void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
+{
+ struct mlx5e_rx_wqe *wqe;
+ __be16 wqe_counter_be;
+ struct sk_buff *skb;
+ u16 wqe_counter;
+ u32 cqe_bcnt;
+
+ wqe_counter_be = cqe->wqe_counter;
+ wqe_counter = be16_to_cpu(wqe_counter_be);
+ wqe = mlx5_wq_ll_get_wqe(&rq->wq, wqe_counter);
+ cqe_bcnt = be32_to_cpu(cqe->byte_cnt);
+
+ skb = skb_from_cqe(rq, cqe, wqe_counter, cqe_bcnt);
+ if (!skb)
+ goto wq_ll_pop;
+
mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
+ napi_gro_receive(rq->cq.napi, skb);
wq_ll_pop:
mlx5_wq_ll_pop(&rq->wq, wqe_counter_be,
@@ -861,6 +875,7 @@ void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
mlx5e_mpwqe_fill_rx_skb(rq, cqe, wi, cqe_bcnt, skb);
mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
+ napi_gro_receive(rq->cq.napi, skb);
mpwrq_cqe_out:
if (likely(wi->consumed_strides < rq->mpwqe_num_strides))
--
2.7.4
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH net-next 7/9] net/mlx5: E-Switch, Support VLAN actions in the offloads mode
2016-09-22 17:01 [PATCH net-next 0/9] Mellanox 100G SRIOV offloads vlan push/pop Saeed Mahameed
` (5 preceding siblings ...)
2016-09-22 17:01 ` [PATCH net-next 6/9] net/mlx5e: Refactor retrival of skb from rx completion element (cqe) Saeed Mahameed
@ 2016-09-22 17:01 ` Saeed Mahameed
2016-09-22 17:01 ` [PATCH net-next 8/9] net/mlx5e: Add TC vlan action for SRIOV offloads Saeed Mahameed
` (2 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: Saeed Mahameed @ 2016-09-22 17:01 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Or Gerlitz, Hadar Hen-Zion, Jiri Pirko, Andy Gospodarek,
Jesse Brandeburg, John Fastabend, Amir Vadai, Saeed Mahameed
From: Or Gerlitz <ogerlitz@mellanox.com>
Many virtualization systems use a policy under which a vlan tag is
pushed to packets sent by guests, and popped before the packet is
forwarded to the VM.
The current generation of the mlx5 HW doesn't fully support that on
a per flow level. As such, we are addressing the above common use
case with the SRIOV e-Switch abilities to push vlan into packets
sent by VFs and pop vlan from packets forwarded to VFs.
The HW can match on the correct vlan being present in packets
forwarded to VFs (eSwitch steering is done before stripping
the tag), so this part is offloaded as is.
A common practice for vlans is to avoid both push vlan and pop vlan
for inter-host VM/VM (east-west) communication because in this case,
push on egress cancels out with pop on ingress.
For supporting that, we use a global eswitch vlan pop policy, hence
allowing guest A to communicate with both remote VM B and local VM C.
This works since the HW pops the vlan only if it exists (e.g for
C --> A packets but not for B --> A packets).
On the slow path, when a VF vport has an offloaded flow which involves
pushing vlans, wheres another flow is not currently offloaded, the
packets from the 2nd flow seen by the VF representor on the host have
vlan. The VF rep driver removes such vlan before calling into the host
networking stack.
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en.h | 1 +
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 21 ++-
drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 33 ++++
drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 15 ++
.../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 180 +++++++++++++++++++++
5 files changed, 249 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 3460154..460363b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -869,6 +869,7 @@ void mlx5e_nic_rep_unload(struct mlx5_eswitch *esw,
int mlx5e_add_sqs_fwd_rules(struct mlx5e_priv *priv);
void mlx5e_remove_sqs_fwd_rules(struct mlx5e_priv *priv);
int mlx5e_attr_get(struct net_device *dev, struct switchdev_attr *attr);
+void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
int mlx5e_create_direct_rqts(struct mlx5e_priv *priv);
void mlx5e_destroy_rqt(struct mlx5e_priv *priv, struct mlx5e_rqt *rqt);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index b309e7c..c127923 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -446,6 +446,16 @@ static void mlx5e_rq_free_mpwqe_info(struct mlx5e_rq *rq)
kfree(rq->mpwqe.info);
}
+static bool mlx5e_is_vf_vport_rep(struct mlx5e_priv *priv)
+{
+ struct mlx5_eswitch_rep *rep = (struct mlx5_eswitch_rep *)priv->ppriv;
+
+ if (rep && rep->vport != FDB_UPLINK_VPORT)
+ return true;
+
+ return false;
+}
+
static int mlx5e_create_rq(struct mlx5e_channel *c,
struct mlx5e_rq_param *param,
struct mlx5e_rq *rq)
@@ -487,6 +497,11 @@ static int mlx5e_create_rq(struct mlx5e_channel *c,
switch (priv->params.rq_wq_type) {
case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
+ if (mlx5e_is_vf_vport_rep(priv)) {
+ err = -EINVAL;
+ goto err_rq_wq_destroy;
+ }
+
rq->handle_rx_cqe = mlx5e_handle_rx_cqe_mpwrq;
rq->alloc_wqe = mlx5e_alloc_rx_mpwqe;
rq->dealloc_wqe = mlx5e_dealloc_rx_mpwqe;
@@ -512,7 +527,11 @@ static int mlx5e_create_rq(struct mlx5e_channel *c,
goto err_rq_wq_destroy;
}
- rq->handle_rx_cqe = mlx5e_handle_rx_cqe;
+ if (mlx5e_is_vf_vport_rep(priv))
+ rq->handle_rx_cqe = mlx5e_handle_rx_cqe_rep;
+ else
+ rq->handle_rx_cqe = mlx5e_handle_rx_cqe;
+
rq->alloc_wqe = mlx5e_alloc_rx_wqe;
rq->dealloc_wqe = mlx5e_dealloc_rx_wqe;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index e836e47..c6de6fb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -36,6 +36,7 @@
#include <net/busy_poll.h>
#include "en.h"
#include "en_tc.h"
+#include "eswitch.h"
static inline bool mlx5e_rx_hw_stamp(struct mlx5e_tstamp *tstamp)
{
@@ -803,6 +804,38 @@ wq_ll_pop:
&wqe->next.next_wqe_index);
}
+void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
+{
+ struct net_device *netdev = rq->netdev;
+ struct mlx5e_priv *priv = netdev_priv(netdev);
+ struct mlx5_eswitch_rep *rep = priv->ppriv;
+ struct mlx5e_rx_wqe *wqe;
+ struct sk_buff *skb;
+ __be16 wqe_counter_be;
+ u16 wqe_counter;
+ u32 cqe_bcnt;
+
+ wqe_counter_be = cqe->wqe_counter;
+ wqe_counter = be16_to_cpu(wqe_counter_be);
+ wqe = mlx5_wq_ll_get_wqe(&rq->wq, wqe_counter);
+ cqe_bcnt = be32_to_cpu(cqe->byte_cnt);
+
+ skb = skb_from_cqe(rq, cqe, wqe_counter, cqe_bcnt);
+ if (!skb)
+ goto wq_ll_pop;
+
+ mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
+
+ if (rep->vlan && skb_vlan_tag_present(skb))
+ skb_vlan_pop(skb);
+
+ napi_gro_receive(rq->cq.napi, skb);
+
+wq_ll_pop:
+ mlx5_wq_ll_pop(&rq->wq, wqe_counter_be,
+ &wqe->next.next_wqe_index);
+}
+
static inline void mlx5e_mpwqe_fill_rx_skb(struct mlx5e_rq *rq,
struct mlx5_cqe64 *cqe,
struct mlx5e_mpw_info *wi,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index eeeeadc..2e2938e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -157,6 +157,7 @@ struct mlx5_eswitch_fdb {
struct mlx5_flow_group *send_to_vport_grp;
struct mlx5_flow_group *miss_grp;
struct mlx5_flow_rule *miss_rule;
+ int vlan_push_pop_refcount;
} offloads;
};
};
@@ -183,6 +184,8 @@ struct mlx5_eswitch_rep {
struct mlx5_flow_rule *vport_rx_rule;
struct list_head vport_sqs_list;
+ u16 vlan;
+ u32 vlan_refcount;
bool valid;
};
@@ -252,11 +255,16 @@ enum {
SET_VLAN_INSERT = BIT(1)
};
+#define MLX5_FLOW_CONTEXT_ACTION_VLAN_POP 0x40
+#define MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH 0x80
+
struct mlx5_esw_flow_attr {
struct mlx5_eswitch_rep *in_rep;
struct mlx5_eswitch_rep *out_rep;
int action;
+ u16 vlan;
+ bool vlan_handled;
};
int mlx5_eswitch_sqs2vport_start(struct mlx5_eswitch *esw,
@@ -273,6 +281,13 @@ void mlx5_eswitch_register_vport_rep(struct mlx5_eswitch *esw,
void mlx5_eswitch_unregister_vport_rep(struct mlx5_eswitch *esw,
int vport_index);
+int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw,
+ struct mlx5_esw_flow_attr *attr);
+int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw,
+ struct mlx5_esw_flow_attr *attr);
+int __mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw,
+ int vport, u16 vlan, u8 qos, u8 set_flags);
+
#define MLX5_DEBUG_ESWITCH_MASK BIT(3)
#define esw_info(dev, format, ...) \
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index c0d9d1a..c910858 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -89,6 +89,186 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
return rule;
}
+static int esw_set_global_vlan_pop(struct mlx5_eswitch *esw, u8 val)
+{
+ struct mlx5_eswitch_rep *rep;
+ int vf_vport, err = 0;
+
+ esw_debug(esw->dev, "%s applying global %s policy\n", __func__, val ? "pop" : "none");
+ for (vf_vport = 1; vf_vport < esw->enabled_vports; vf_vport++) {
+ rep = &esw->offloads.vport_reps[vf_vport];
+ if (!rep->valid)
+ continue;
+
+ err = __mlx5_eswitch_set_vport_vlan(esw, rep->vport, 0, 0, val);
+ if (err)
+ goto out;
+ }
+
+out:
+ return err;
+}
+
+static struct mlx5_eswitch_rep *
+esw_vlan_action_get_vport(struct mlx5_esw_flow_attr *attr, bool push, bool pop)
+{
+ struct mlx5_eswitch_rep *in_rep, *out_rep, *vport = NULL;
+
+ in_rep = attr->in_rep;
+ out_rep = attr->out_rep;
+
+ if (push)
+ vport = in_rep;
+ else if (pop)
+ vport = out_rep;
+ else
+ vport = in_rep;
+
+ return vport;
+}
+
+static int esw_add_vlan_action_check(struct mlx5_esw_flow_attr *attr,
+ bool push, bool pop, bool fwd)
+{
+ struct mlx5_eswitch_rep *in_rep, *out_rep;
+
+ if ((push || pop) && !fwd)
+ goto out_notsupp;
+
+ in_rep = attr->in_rep;
+ out_rep = attr->out_rep;
+
+ if (push && in_rep->vport == FDB_UPLINK_VPORT)
+ goto out_notsupp;
+
+ if (pop && out_rep->vport == FDB_UPLINK_VPORT)
+ goto out_notsupp;
+
+ /* vport has vlan push configured, can't offload VF --> wire rules w.o it */
+ if (!push && !pop && fwd)
+ if (in_rep->vlan && out_rep->vport == FDB_UPLINK_VPORT)
+ goto out_notsupp;
+
+ /* protects against (1) setting rules with different vlans to push and
+ * (2) setting rules w.o vlans (attr->vlan = 0) && w. vlans to push (!= 0)
+ */
+ if (push && in_rep->vlan_refcount && (in_rep->vlan != attr->vlan))
+ goto out_notsupp;
+
+ return 0;
+
+out_notsupp:
+ return -ENOTSUPP;
+}
+
+int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw,
+ struct mlx5_esw_flow_attr *attr)
+{
+ struct offloads_fdb *offloads = &esw->fdb_table.offloads;
+ struct mlx5_eswitch_rep *vport = NULL;
+ bool push, pop, fwd;
+ int err = 0;
+
+ push = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH);
+ pop = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP);
+ fwd = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST);
+
+ err = esw_add_vlan_action_check(attr, push, pop, fwd);
+ if (err)
+ return err;
+
+ attr->vlan_handled = false;
+
+ vport = esw_vlan_action_get_vport(attr, push, pop);
+
+ if (!push && !pop && fwd) {
+ /* tracks VF --> wire rules without vlan push action */
+ if (attr->out_rep->vport == FDB_UPLINK_VPORT) {
+ vport->vlan_refcount++;
+ attr->vlan_handled = true;
+ }
+
+ return 0;
+ }
+
+ if (!push && !pop)
+ return 0;
+
+ if (!(offloads->vlan_push_pop_refcount)) {
+ /* it's the 1st vlan rule, apply global vlan pop policy */
+ err = esw_set_global_vlan_pop(esw, SET_VLAN_STRIP);
+ if (err)
+ goto out;
+ }
+ offloads->vlan_push_pop_refcount++;
+
+ if (push) {
+ if (vport->vlan_refcount)
+ goto skip_set_push;
+
+ err = __mlx5_eswitch_set_vport_vlan(esw, vport->vport, attr->vlan, 0,
+ SET_VLAN_INSERT | SET_VLAN_STRIP);
+ if (err)
+ goto out;
+ vport->vlan = attr->vlan;
+skip_set_push:
+ vport->vlan_refcount++;
+ }
+out:
+ if (!err)
+ attr->vlan_handled = true;
+ return err;
+}
+
+int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw,
+ struct mlx5_esw_flow_attr *attr)
+{
+ struct offloads_fdb *offloads = &esw->fdb_table.offloads;
+ struct mlx5_eswitch_rep *vport = NULL;
+ bool push, pop, fwd;
+ int err = 0;
+
+ if (!attr->vlan_handled)
+ return 0;
+
+ push = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH);
+ pop = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP);
+ fwd = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST);
+
+ vport = esw_vlan_action_get_vport(attr, push, pop);
+
+ if (!push && !pop && fwd) {
+ /* tracks VF --> wire rules without vlan push action */
+ if (attr->out_rep->vport == FDB_UPLINK_VPORT)
+ vport->vlan_refcount--;
+
+ return 0;
+ }
+
+ if (push) {
+ vport->vlan_refcount--;
+ if (vport->vlan_refcount)
+ goto skip_unset_push;
+
+ vport->vlan = 0;
+ err = __mlx5_eswitch_set_vport_vlan(esw, vport->vport,
+ 0, 0, SET_VLAN_STRIP);
+ if (err)
+ goto out;
+ }
+
+skip_unset_push:
+ offloads->vlan_push_pop_refcount--;
+ if (offloads->vlan_push_pop_refcount)
+ return 0;
+
+ /* no more vlan rules, stop global vlan pop policy */
+ err = esw_set_global_vlan_pop(esw, 0);
+
+out:
+ return err;
+}
+
static struct mlx5_flow_rule *
mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *esw, int vport, u32 sqn)
{
--
2.7.4
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH net-next 8/9] net/mlx5e: Add TC vlan action for SRIOV offloads
2016-09-22 17:01 [PATCH net-next 0/9] Mellanox 100G SRIOV offloads vlan push/pop Saeed Mahameed
` (6 preceding siblings ...)
2016-09-22 17:01 ` [PATCH net-next 7/9] net/mlx5: E-Switch, Support VLAN actions in the offloads mode Saeed Mahameed
@ 2016-09-22 17:01 ` Saeed Mahameed
2016-09-22 17:01 ` [PATCH net-next 9/9] net/mlx5e: Add TC vlan match parsing Saeed Mahameed
2016-09-23 11:22 ` [PATCH net-next 0/9] Mellanox 100G SRIOV offloads vlan push/pop David Miller
9 siblings, 0 replies; 11+ messages in thread
From: Saeed Mahameed @ 2016-09-22 17:01 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Or Gerlitz, Hadar Hen-Zion, Jiri Pirko, Andy Gospodarek,
Jesse Brandeburg, John Fastabend, Amir Vadai, Saeed Mahameed
From: Or Gerlitz <ogerlitz@mellanox.com>
Parse TC vlan actions and set the required elements to allow offloading.
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 43 ++++++++++++++++++-------
1 file changed, 32 insertions(+), 11 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 3eb319b..e61bd52 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -119,17 +119,27 @@ static struct mlx5_flow_rule *mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
struct mlx5_esw_flow_attr *attr)
{
struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+ int err;
+
+ err = mlx5_eswitch_add_vlan_action(esw, attr);
+ if (err)
+ return ERR_PTR(err);
return mlx5_eswitch_add_offloaded_rule(esw, spec, attr);
}
static void mlx5e_tc_del_flow(struct mlx5e_priv *priv,
- struct mlx5_flow_rule *rule)
+ struct mlx5_flow_rule *rule,
+ struct mlx5_esw_flow_attr *attr)
{
+ struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
struct mlx5_fc *counter = NULL;
counter = mlx5_flow_rule_counter(rule);
+ if (esw && esw->mode == SRIOV_OFFLOADS)
+ mlx5_eswitch_del_vlan_action(esw, attr);
+
mlx5_del_flow_rule(rule);
mlx5_fc_destroy(priv->mdev, counter);
@@ -369,13 +379,9 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
tcf_exts_to_list(exts, &actions);
list_for_each_entry(a, &actions, list) {
- /* Only support a single action per rule */
- if (attr->action)
- return -EINVAL;
-
if (is_tcf_gact_shot(a)) {
- attr->action = MLX5_FLOW_CONTEXT_ACTION_DROP |
- MLX5_FLOW_CONTEXT_ACTION_COUNT;
+ attr->action |= MLX5_FLOW_CONTEXT_ACTION_DROP |
+ MLX5_FLOW_CONTEXT_ACTION_COUNT;
continue;
}
@@ -392,12 +398,25 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
return -EINVAL;
}
- attr->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+ attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
out_priv = netdev_priv(out_dev);
attr->out_rep = out_priv->ppriv;
continue;
}
+ if (is_tcf_vlan(a)) {
+ if (tcf_vlan_action(a) == VLAN_F_POP) {
+ attr->action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP;
+ } else if (tcf_vlan_action(a) == VLAN_F_PUSH) {
+ if (tcf_vlan_push_proto(a) != htons(ETH_P_8021Q))
+ return -EOPNOTSUPP;
+
+ attr->action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH;
+ attr->vlan = tcf_vlan_push_vid(a);
+ }
+ continue;
+ }
+
return -EINVAL;
}
return 0;
@@ -413,6 +432,7 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv, __be16 protocol,
struct mlx5e_tc_flow *flow;
struct mlx5_flow_spec *spec;
struct mlx5_flow_rule *old = NULL;
+ struct mlx5_esw_flow_attr *old_attr;
struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
if (esw && esw->mode == SRIOV_OFFLOADS)
@@ -422,6 +442,7 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv, __be16 protocol,
tc->ht_params);
if (flow) {
old = flow->rule;
+ old_attr = flow->attr;
} else {
if (fdb_flow)
flow = kzalloc(sizeof(*flow) + sizeof(struct mlx5_esw_flow_attr),
@@ -466,7 +487,7 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv, __be16 protocol,
goto err_del_rule;
if (old)
- mlx5e_tc_del_flow(priv, old);
+ mlx5e_tc_del_flow(priv, old, old_attr);
goto out;
@@ -494,7 +515,7 @@ int mlx5e_delete_flower(struct mlx5e_priv *priv,
rhashtable_remove_fast(&tc->ht, &flow->node, tc->ht_params);
- mlx5e_tc_del_flow(priv, flow->rule);
+ mlx5e_tc_del_flow(priv, flow->rule, flow->attr);
kfree(flow);
@@ -551,7 +572,7 @@ static void _mlx5e_tc_del_flow(void *ptr, void *arg)
struct mlx5e_tc_flow *flow = ptr;
struct mlx5e_priv *priv = arg;
- mlx5e_tc_del_flow(priv, flow->rule);
+ mlx5e_tc_del_flow(priv, flow->rule, flow->attr);
kfree(flow);
}
--
2.7.4
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH net-next 9/9] net/mlx5e: Add TC vlan match parsing
2016-09-22 17:01 [PATCH net-next 0/9] Mellanox 100G SRIOV offloads vlan push/pop Saeed Mahameed
` (7 preceding siblings ...)
2016-09-22 17:01 ` [PATCH net-next 8/9] net/mlx5e: Add TC vlan action for SRIOV offloads Saeed Mahameed
@ 2016-09-22 17:01 ` Saeed Mahameed
2016-09-23 11:22 ` [PATCH net-next 0/9] Mellanox 100G SRIOV offloads vlan push/pop David Miller
9 siblings, 0 replies; 11+ messages in thread
From: Saeed Mahameed @ 2016-09-22 17:01 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Or Gerlitz, Hadar Hen-Zion, Jiri Pirko, Andy Gospodarek,
Jesse Brandeburg, John Fastabend, Amir Vadai, Saeed Mahameed
From: Or Gerlitz <ogerlitz@mellanox.com>
Enhance the parsing of offloaded TC rules matches to handle vlans.
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 19 +++++++++++++++++++
1 file changed, 19 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index e61bd52..a350b71 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -164,6 +164,7 @@ static int parse_cls_flower(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec
~(BIT(FLOW_DISSECTOR_KEY_CONTROL) |
BIT(FLOW_DISSECTOR_KEY_BASIC) |
BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
+ BIT(FLOW_DISSECTOR_KEY_VLAN) |
BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
BIT(FLOW_DISSECTOR_KEY_PORTS))) {
@@ -227,6 +228,24 @@ static int parse_cls_flower(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec
key->src);
}
+ if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) {
+ struct flow_dissector_key_vlan *key =
+ skb_flow_dissector_target(f->dissector,
+ FLOW_DISSECTOR_KEY_VLAN,
+ f->key);
+ struct flow_dissector_key_vlan *mask =
+ skb_flow_dissector_target(f->dissector,
+ FLOW_DISSECTOR_KEY_VLAN,
+ f->mask);
+ if (mask->vlan_id) {
+ MLX5_SET(fte_match_set_lyr_2_4, headers_c, vlan_tag, 1);
+ MLX5_SET(fte_match_set_lyr_2_4, headers_v, vlan_tag, 1);
+
+ MLX5_SET(fte_match_set_lyr_2_4, headers_c, first_vid, mask->vlan_id);
+ MLX5_SET(fte_match_set_lyr_2_4, headers_v, first_vid, key->vlan_id);
+ }
+ }
+
if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
struct flow_dissector_key_ipv4_addrs *key =
skb_flow_dissector_target(f->dissector,
--
2.7.4
^ permalink raw reply related [flat|nested] 11+ messages in thread* Re: [PATCH net-next 0/9] Mellanox 100G SRIOV offloads vlan push/pop
2016-09-22 17:01 [PATCH net-next 0/9] Mellanox 100G SRIOV offloads vlan push/pop Saeed Mahameed
` (8 preceding siblings ...)
2016-09-22 17:01 ` [PATCH net-next 9/9] net/mlx5e: Add TC vlan match parsing Saeed Mahameed
@ 2016-09-23 11:22 ` David Miller
9 siblings, 0 replies; 11+ messages in thread
From: David Miller @ 2016-09-23 11:22 UTC (permalink / raw)
To: saeedm
Cc: netdev, ogerlitz, hadarh, jiri, gospo, jesse.brandeburg,
john.r.fastabend, amirv
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Thu, 22 Sep 2016 20:01:40 +0300
> From Or Gerlitz:
>
> This series further enhances the SRIOV TC offloads of mlx5 to handle
> the TC vlan push and pop actions. This serves a common use-case in
> virtualization systems where the virtual switch add (push) vlan tags
> to packets sent from VMs and removes (pop) vlan tags before the packet
> is received by the VM. We use the new E-Switch switchdev mode and the
> TC vlan action to achieve that also in SW defined SRIOV environments by
> offloading TC rules that contain this action along with forwarding
> (TC mirred/redirect action) the packet.
>
> In the first patch we add some helpers to access the TC vlan action info
> by offloading drivers. The next five patches don't add any new functionality,
> they do some refactoring and cleanups in the current code to be used next.
>
> The seventh patch deals with supporting vlans by the mlx5 e-switch in switchdev
> mode. The eighth patch does the vlan action offload from TC and the last patch
> adds matching for vlans as typically required by TC flows that involve vlan
> pop action.
>
> The series was applied on top of commit 524605e "cxgb4: Convert to use simple_open()"
Series applied, thanks.
^ permalink raw reply [flat|nested] 11+ messages in thread