Merge tag 'mlx5-updates-2017-04-22' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5-updates-2017-04-22

Sparse and compiler warnings fixes from Stephen Hemminger.

From Roi Dayan and Or Gerlitz, Add devlink and mlx5 support for controlling
E-Switch encapsulation mode, this knob will enable HW support for applying
encapsulation/decapsulation to VF traffic as part of SRIOV e-switch offloading.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

10 files changed, 167 insertions, 36 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 43308243f519..ae66fad98244 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -39,6 +39,7 @@
 #include "en.h"
 #include "en_tc.h"
 #include "eswitch.h"
+#include "ipoib.h"
 
 static inline bool mlx5e_rx_hw_stamp(struct mlx5e_tstamp *tstamp)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index dda7db503043..ab3bb026ff9e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -33,6 +33,7 @@
 #include <linux/tcp.h>
 #include <linux/if_vlan.h>
 #include "en.h"
+#include "ipoib.h"
 
 #define MLX5E_SQ_NOPS_ROOM  MLX5_SEND_WQE_MAX_WQEBBS
 #define MLX5E_SQ_STOP_ROOM (MLX5_SEND_WQE_MAX_WQEBBS +\
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index b3281d1118b3..21bed3c3334d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1806,6 +1806,11 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 	esw->enabled_vports = 0;
 	esw->mode = SRIOV_NONE;
 	esw->offloads.inline_mode = MLX5_INLINE_MODE_NONE;
+	if (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, encap) &&
+	    MLX5_CAP_ESW_FLOWTABLE_FDB(dev, decap))
+		esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_BASIC;
+	else
+		esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE;
 
 	dev->priv.eswitch = esw;
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 1f56ed9f5a6f..1e7f21be1233 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -210,6 +210,7 @@ struct mlx5_esw_offload {
 	DECLARE_HASHTABLE(encap_tbl, 8);
 	u8 inline_mode;
 	u64 num_flows;
+	u8 encap;
 };
 
 struct mlx5_eswitch {
@@ -322,6 +323,8 @@ int mlx5_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode);
 int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode);
 int mlx5_devlink_eswitch_inline_mode_get(struct devlink *devlink, u8 *mode);
 int mlx5_eswitch_inline_mode_get(struct mlx5_eswitch *esw, int nvfs, u8 *mode);
+int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink, u8 encap);
+int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink, u8 *encap);
 void mlx5_eswitch_register_vport_rep(struct mlx5_eswitch *esw,
 				     int vport_index,
 				     struct mlx5_eswitch_rep *rep);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 992b380d36be..189d24dbd3e3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -426,31 +426,21 @@ out:
 	return err;
 }
 
-#define MAX_PF_SQ 256
 #define ESW_OFFLOADS_NUM_GROUPS  4
 
-static int esw_create_offloads_fdb_table(struct mlx5_eswitch *esw, int nvports)
+static int esw_create_offloads_fast_fdb_table(struct mlx5_eswitch *esw)
 {
-	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
-	struct mlx5_flow_table_attr ft_attr = {};
-	int table_size, ix, esw_size, err = 0;
 	struct mlx5_core_dev *dev = esw->dev;
 	struct mlx5_flow_namespace *root_ns;
 	struct mlx5_flow_table *fdb = NULL;
-	struct mlx5_flow_group *g;
-	u32 *flow_group_in;
-	void *match_criteria;
+	int esw_size, err = 0;
 	u32 flags = 0;
 
-	flow_group_in = mlx5_vzalloc(inlen);
-	if (!flow_group_in)
-		return -ENOMEM;
-
 	root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_FDB);
 	if (!root_ns) {
 		esw_warn(dev, "Failed to get FDB flow namespace\n");
 		err = -EOPNOTSUPP;
-		goto ns_err;
+		goto out;
 	}
 
 	esw_debug(dev, "Create offloads FDB table, min (max esw size(2^%d), max counters(%d)*groups(%d))\n",
@@ -460,8 +450,7 @@ static int esw_create_offloads_fdb_table(struct mlx5_eswitch *esw, int nvports)
 	esw_size = min_t(int, MLX5_CAP_GEN(dev, max_flow_counter) * ESW_OFFLOADS_NUM_GROUPS,
 			 1 << MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size));
 
-	if (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, encap) &&
-	    MLX5_CAP_ESW_FLOWTABLE_FDB(dev, decap))
+	if (esw->offloads.encap != DEVLINK_ESWITCH_ENCAP_MODE_NONE)
 		flags |= MLX5_FLOW_TABLE_TUNNEL_EN;
 
 	fdb = mlx5_create_auto_grouped_flow_table(root_ns, FDB_FAST_PATH,
@@ -471,10 +460,49 @@ static int esw_create_offloads_fdb_table(struct mlx5_eswitch *esw, int nvports)
 	if (IS_ERR(fdb)) {
 		err = PTR_ERR(fdb);
 		esw_warn(dev, "Failed to create Fast path FDB Table err %d\n", err);
-		goto fast_fdb_err;
+		goto out;
 	}
 	esw->fdb_table.fdb = fdb;
 
+out:
+	return err;
+}
+
+static void esw_destroy_offloads_fast_fdb_table(struct mlx5_eswitch *esw)
+{
+	mlx5_destroy_flow_table(esw->fdb_table.fdb);
+}
+
+#define MAX_PF_SQ 256
+
+static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
+{
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	struct mlx5_flow_table_attr ft_attr = {};
+	struct mlx5_core_dev *dev = esw->dev;
+	struct mlx5_flow_namespace *root_ns;
+	struct mlx5_flow_table *fdb = NULL;
+	int table_size, ix, err = 0;
+	struct mlx5_flow_group *g;
+	void *match_criteria;
+	u32 *flow_group_in;
+
+	esw_debug(esw->dev, "Create offloads FDB Tables\n");
+	flow_group_in = mlx5_vzalloc(inlen);
+	if (!flow_group_in)
+		return -ENOMEM;
+
+	root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_FDB);
+	if (!root_ns) {
+		esw_warn(dev, "Failed to get FDB flow namespace\n");
+		err = -EOPNOTSUPP;
+		goto ns_err;
+	}
+
+	err = esw_create_offloads_fast_fdb_table(esw);
+	if (err)
+		goto fast_fdb_err;
+
 	table_size = nvports + MAX_PF_SQ + 1;
 
 	ft_attr.max_fte = table_size;
@@ -545,18 +573,18 @@ ns_err:
 	return err;
 }
 
-static void esw_destroy_offloads_fdb_table(struct mlx5_eswitch *esw)
+static void esw_destroy_offloads_fdb_tables(struct mlx5_eswitch *esw)
 {
 	if (!esw->fdb_table.fdb)
 		return;
 
-	esw_debug(esw->dev, "Destroy offloads FDB Table\n");
+	esw_debug(esw->dev, "Destroy offloads FDB Tables\n");
 	mlx5_del_flow_rules(esw->fdb_table.offloads.miss_rule);
 	mlx5_destroy_flow_group(esw->fdb_table.offloads.send_to_vport_grp);
 	mlx5_destroy_flow_group(esw->fdb_table.offloads.miss_grp);
 
 	mlx5_destroy_flow_table(esw->fdb_table.offloads.fdb);
-	mlx5_destroy_flow_table(esw->fdb_table.fdb);
+	esw_destroy_offloads_fast_fdb_table(esw);
 }
 
 static int esw_create_offloads_table(struct mlx5_eswitch *esw)
@@ -716,7 +744,7 @@ int esw_offloads_init(struct mlx5_eswitch *esw, int nvports)
 	mlx5_remove_dev_by_protocol(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
 	mlx5_dev_list_unlock();
 
-	err = esw_create_offloads_fdb_table(esw, nvports);
+	err = esw_create_offloads_fdb_tables(esw, nvports);
 	if (err)
 		goto create_fdb_err;
 
@@ -753,7 +781,7 @@ create_fg_err:
 	esw_destroy_offloads_table(esw);
 
 create_ft_err:
-	esw_destroy_offloads_fdb_table(esw);
+	esw_destroy_offloads_fdb_tables(esw);
 
 create_fdb_err:
 	/* enable back PF RoCE */
@@ -799,7 +827,7 @@ void esw_offloads_cleanup(struct mlx5_eswitch *esw, int nvports)
 
 	esw_destroy_vport_rx_group(esw);
 	esw_destroy_offloads_table(esw);
-	esw_destroy_offloads_fdb_table(esw);
+	esw_destroy_offloads_fdb_tables(esw);
 }
 
 static int esw_mode_from_devlink(u16 mode, u16 *mlx5_mode)
@@ -1016,6 +1044,66 @@ int mlx5_eswitch_inline_mode_get(struct mlx5_eswitch *esw, int nvfs, u8 *mode)
 	return 0;
 }
 
+int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink, u8 encap)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+	struct mlx5_eswitch *esw = dev->priv.eswitch;
+	int err;
+
+	if (!MLX5_CAP_GEN(dev, vport_group_manager))
+		return -EOPNOTSUPP;
+
+	if (esw->mode == SRIOV_NONE)
+		return -EOPNOTSUPP;
+
+	if (encap != DEVLINK_ESWITCH_ENCAP_MODE_NONE &&
+	    (!MLX5_CAP_ESW_FLOWTABLE_FDB(dev, encap) ||
+	     !MLX5_CAP_ESW_FLOWTABLE_FDB(dev, decap)))
+		return -EOPNOTSUPP;
+
+	if (encap && encap != DEVLINK_ESWITCH_ENCAP_MODE_BASIC)
+		return -EOPNOTSUPP;
+
+	if (esw->mode == SRIOV_LEGACY) {
+		esw->offloads.encap = encap;
+		return 0;
+	}
+
+	if (esw->offloads.encap == encap)
+		return 0;
+
+	if (esw->offloads.num_flows > 0) {
+		esw_warn(dev, "Can't set encapsulation when flows are configured\n");
+		return -EOPNOTSUPP;
+	}
+
+	esw_destroy_offloads_fast_fdb_table(esw);
+
+	esw->offloads.encap = encap;
+	err = esw_create_offloads_fast_fdb_table(esw);
+	if (err) {
+		esw_warn(esw->dev, "Failed re-creating fast FDB table, err %d\n", err);
+		esw->offloads.encap = !encap;
+		(void) esw_create_offloads_fast_fdb_table(esw);
+	}
+	return err;
+}
+
+int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink, u8 *encap)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+	struct mlx5_eswitch *esw = dev->priv.eswitch;
+
+	if (!MLX5_CAP_GEN(dev, vport_group_manager))
+		return -EOPNOTSUPP;
+
+	if (esw->mode == SRIOV_NONE)
+		return -EOPNOTSUPP;
+
+	*encap = esw->offloads.encap;
+	return 0;
+}
+
 void mlx5_eswitch_register_vport_rep(struct mlx5_eswitch *esw,
 				     int vport_index,
 				     struct mlx5_eswitch_rep *__rep)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib.c
index ec78e637840f..3c84e36af018 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib.c
@@ -178,7 +178,7 @@ static int mlx5i_init_tx(struct mlx5e_priv *priv)
 	return 0;
 }
 
-void mlx5i_cleanup_tx(struct mlx5e_priv *priv)
+static void mlx5i_cleanup_tx(struct mlx5e_priv *priv)
 {
 	struct mlx5i_priv *ipriv = priv->ppriv;
 
@@ -359,9 +359,10 @@ unlock:
 	return 0;
 }
 
+#ifdef notusedyet
 /* IPoIB RDMA netdev callbacks */
-int mlx5i_attach_mcast(struct net_device *netdev, struct ib_device *hca,
-		       union ib_gid *gid, u16 lid, int set_qkey)
+static int mlx5i_attach_mcast(struct net_device *netdev, struct ib_device *hca,
+			      union ib_gid *gid, u16 lid, int set_qkey)
 {
 	struct mlx5e_priv    *epriv = mlx5i_epriv(netdev);
 	struct mlx5_core_dev *mdev  = epriv->mdev;
@@ -377,8 +378,8 @@ int mlx5i_attach_mcast(struct net_device *netdev, struct ib_device *hca,
 	return err;
 }
 
-int mlx5i_detach_mcast(struct net_device *netdev, struct ib_device *hca,
-		       union ib_gid *gid, u16 lid)
+static int mlx5i_detach_mcast(struct net_device *netdev, struct ib_device *hca,
+			      union ib_gid *gid, u16 lid)
 {
 	struct mlx5e_priv    *epriv = mlx5i_epriv(netdev);
 	struct mlx5_core_dev *mdev  = epriv->mdev;
@@ -395,7 +396,7 @@ int mlx5i_detach_mcast(struct net_device *netdev, struct ib_device *hca,
 	return err;
 }
 
-int mlx5i_xmit(struct net_device *dev, struct sk_buff *skb,
+static int mlx5i_xmit(struct net_device *dev, struct sk_buff *skb,
 	       struct ib_ah *address, u32 dqpn, u32 dqkey)
 {
 	struct mlx5e_priv *epriv = mlx5i_epriv(dev);
@@ -404,6 +405,7 @@ int mlx5i_xmit(struct net_device *dev, struct sk_buff *skb,
 
 	return mlx5i_sq_xmit(sq, skb, &mah->av, dqpn, dqkey);
 }
+#endif
 
 static int mlx5i_check_required_hca_cap(struct mlx5_core_dev *mdev)
 {
@@ -418,10 +420,10 @@ static int mlx5i_check_required_hca_cap(struct mlx5_core_dev *mdev)
 	return 0;
 }
 
-struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev,
-					  struct ib_device *ibdev,
-					  const char *name,
-					  void (*setup)(struct net_device *))
+static struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev,
+						 struct ib_device *ibdev,
+						 const char *name,
+						 void (*setup)(struct net_device *))
 {
 	const struct mlx5e_profile *profile = &mlx5i_nic_profile;
 	int nch = profile->max_nch(mdev);
@@ -480,7 +482,7 @@ free_mdev_resources:
 }
 EXPORT_SYMBOL(mlx5_rdma_netdev_alloc);
 
-void mlx5_rdma_netdev_free(struct net_device *netdev)
+static void mlx5_rdma_netdev_free(struct net_device *netdev)
 {
 	struct mlx5e_priv          *priv    = mlx5i_epriv(netdev);
 	const struct mlx5e_profile *profile = priv->profile;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 9c2bec732af9..bde91a8bec73 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1280,6 +1280,8 @@ static const struct devlink_ops mlx5_devlink_ops = {
 	.eswitch_mode_get = mlx5_devlink_eswitch_mode_get,
 	.eswitch_inline_mode_set = mlx5_devlink_eswitch_inline_mode_set,
 	.eswitch_inline_mode_get = mlx5_devlink_eswitch_inline_mode_get,
+	.eswitch_encap_mode_set = mlx5_devlink_eswitch_encap_mode_set,
+	.eswitch_encap_mode_get = mlx5_devlink_eswitch_encap_mode_get,
 #endif
 };
 
diff --git a/include/net/devlink.h b/include/net/devlink.h
index 24de13f8c94f..ed7687bbf5d0 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -268,6 +268,8 @@ struct devlink_ops {
 	int (*eswitch_mode_set)(struct devlink *devlink, u16 mode);
 	int (*eswitch_inline_mode_get)(struct devlink *devlink, u8 *p_inline_mode);
 	int (*eswitch_inline_mode_set)(struct devlink *devlink, u8 inline_mode);
+	int (*eswitch_encap_mode_get)(struct devlink *devlink, u8 *p_encap_mode);
+	int (*eswitch_encap_mode_set)(struct devlink *devlink, u8 encap_mode);
 };
 
 static inline void *devlink_priv(struct devlink *devlink)
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index b47bee277347..b0e807ac53bb 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -119,6 +119,11 @@ enum devlink_eswitch_inline_mode {
 	DEVLINK_ESWITCH_INLINE_MODE_TRANSPORT,
 };
 
+enum devlink_eswitch_encap_mode {
+	DEVLINK_ESWITCH_ENCAP_MODE_NONE,
+	DEVLINK_ESWITCH_ENCAP_MODE_BASIC,
+};
+
 enum devlink_attr {
 	/* don't change the order or add anything between, this is ABI! */
 	DEVLINK_ATTR_UNSPEC,
@@ -195,6 +200,8 @@ enum devlink_attr {
 
 	DEVLINK_ATTR_PAD,
 
+	DEVLINK_ATTR_ESWITCH_ENCAP_MODE,	/* u8 */
+
 	/* add new attributes above here, update the policy in devlink.c */
 
 	__DEVLINK_ATTR_MAX,
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 0afac5800b57..b0b87a292e7c 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -1397,10 +1397,10 @@ static int devlink_nl_eswitch_fill(struct sk_buff *msg, struct devlink *devlink,
 				   u32 seq, int flags)
 {
 	const struct devlink_ops *ops = devlink->ops;
+	u8 inline_mode, encap_mode;
 	void *hdr;
 	int err = 0;
 	u16 mode;
-	u8 inline_mode;
 
 	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
 	if (!hdr)
@@ -1429,6 +1429,15 @@ static int devlink_nl_eswitch_fill(struct sk_buff *msg, struct devlink *devlink,
 			goto nla_put_failure;
 	}
 
+	if (ops->eswitch_encap_mode_get) {
+		err = ops->eswitch_encap_mode_get(devlink, &encap_mode);
+		if (err)
+			goto nla_put_failure;
+		err = nla_put_u8(msg, DEVLINK_ATTR_ESWITCH_ENCAP_MODE, encap_mode);
+		if (err)
+			goto nla_put_failure;
+	}
+
 	genlmsg_end(msg, hdr);
 	return 0;
 
@@ -1468,9 +1477,9 @@ static int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb,
 {
 	struct devlink *devlink = info->user_ptr[0];
 	const struct devlink_ops *ops = devlink->ops;
-	u16 mode;
-	u8 inline_mode;
+	u8 inline_mode, encap_mode;
 	int err = 0;
+	u16 mode;
 
 	if (!ops)
 		return -EOPNOTSUPP;
@@ -1493,6 +1502,16 @@ static int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb,
 		if (err)
 			return err;
 	}
+
+	if (info->attrs[DEVLINK_ATTR_ESWITCH_ENCAP_MODE]) {
+		if (!ops->eswitch_encap_mode_set)
+			return -EOPNOTSUPP;
+		encap_mode = nla_get_u8(info->attrs[DEVLINK_ATTR_ESWITCH_ENCAP_MODE]);
+		err = ops->eswitch_encap_mode_set(devlink, encap_mode);
+		if (err)
+			return err;
+	}
+
 	return 0;
 }
 
@@ -2190,6 +2209,7 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_SB_TC_INDEX] = { .type = NLA_U16 },
 	[DEVLINK_ATTR_ESWITCH_MODE] = { .type = NLA_U16 },
 	[DEVLINK_ATTR_ESWITCH_INLINE_MODE] = { .type = NLA_U8 },
+	[DEVLINK_ATTR_ESWITCH_ENCAP_MODE] = { .type = NLA_U8 },
 	[DEVLINK_ATTR_DPIPE_TABLE_NAME] = { .type = NLA_NUL_STRING },
 	[DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED] = { .type = NLA_U8 },
 };