* [PATCH net-next 1/2] net/mlx4_core: Add basic support for TCP/IP offloads under tunneling
2013-12-18 14:05 [PATCH net-next 0/2] net/mlx4: Add support for TCP/IP offloads of vxlan tunneling Or Gerlitz
@ 2013-12-18 14:05 ` Or Gerlitz
2013-12-18 14:05 ` [PATCH net-next 2/2] net/mlx4_en: Add netdev support for TCP/IP offloads of vxlan tunneling Or Gerlitz
2013-12-19 1:16 ` [PATCH net-next 0/2] net/mlx4: Add " Wei-Chun Chao
2 siblings, 0 replies; 4+ messages in thread
From: Or Gerlitz @ 2013-12-18 14:05 UTC (permalink / raw)
To: davem; +Cc: netdev, amirv, yanb, ast, Or Gerlitz
Add the low-level device commands and definitions used for TCP/IP HW offloads
of tunneled/vxlan traffic which are supported by the ConnectX3-pro NIC.
This is done through the following elements:
- read tunneling device caps in QUERY_DEV_CAP
- add helper function to do SET_PORT for tunneling
- add DMFS VXLAN steering rule definitions
- add CQE and WQE checksum offload field definitions
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx4/fw.c | 19 ++++++++++++-
drivers/net/ethernet/mellanox/mlx4/main.c | 14 ++++++++++
drivers/net/ethernet/mellanox/mlx4/mcg.c | 14 ++++++++-
drivers/net/ethernet/mellanox/mlx4/port.c | 41 +++++++++++++++++++++++++++++
include/linux/mlx4/cmd.h | 1 +
include/linux/mlx4/cq.h | 5 +++
include/linux/mlx4/device.h | 37 +++++++++++++++++++++++++-
include/linux/mlx4/qp.h | 6 ++++
8 files changed, 133 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 27a8434..55c4ea7 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -134,7 +134,8 @@ static void dump_dev_cap_flags2(struct mlx4_dev *dev, u64 flags)
[5] = "Time stamping support",
[6] = "VST (control vlan insertion/stripping) support",
[7] = "FSM (MAC anti-spoofing) support",
- [8] = "Dynamic QP updates support"
+ [8] = "Dynamic QP updates support",
+ [9] = "TCP/IP offloads/flow-steering for VXLAN support"
};
int i;
@@ -536,6 +537,7 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
#define QUERY_DEV_CAP_RSVD_LKEY_OFFSET 0x98
#define QUERY_DEV_CAP_MAX_ICM_SZ_OFFSET 0xa0
#define QUERY_DEV_CAP_FW_REASSIGN_MAC 0x9d
+#define QUERY_DEV_CAP_VXLAN 0x9e
dev_cap->flags2 = 0;
mailbox = mlx4_alloc_cmd_mailbox(dev);
@@ -701,6 +703,9 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
MLX4_GET(field, outbox, QUERY_DEV_CAP_FW_REASSIGN_MAC);
if (field & 1<<6)
dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_REASSIGN_MAC_EN;
+ MLX4_GET(field, outbox, QUERY_DEV_CAP_VXLAN);
+ if (field & 1<<3)
+ dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_VXLAN_OFFLOADS;
MLX4_GET(dev_cap->max_icm_sz, outbox,
QUERY_DEV_CAP_MAX_ICM_SZ_OFFSET);
if (dev_cap->flags & MLX4_DEV_CAP_FLAG_COUNTERS)
@@ -849,6 +854,11 @@ int mlx4_QUERY_DEV_CAP_wrapper(struct mlx4_dev *dev, int slave,
field &= 0x7f;
MLX4_PUT(outbox->buf, field, QUERY_DEV_CAP_CQ_TS_SUPPORT_OFFSET);
+ /* For guests, disable vxlan tunneling */
+ MLX4_GET(field, outbox, QUERY_DEV_CAP_VXLAN);
+ field &= 0xf7;
+ MLX4_PUT(outbox->buf, field, QUERY_DEV_CAP_VXLAN);
+
/* For guests, report Blueflame disabled */
MLX4_GET(field, outbox->buf, QUERY_DEV_CAP_BF_OFFSET);
field &= 0x7f;
@@ -1274,6 +1284,7 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param)
#define INIT_HCA_IN_SIZE 0x200
#define INIT_HCA_VERSION_OFFSET 0x000
#define INIT_HCA_VERSION 2
+#define INIT_HCA_VXLAN_OFFSET 0x0c
#define INIT_HCA_CACHELINE_SZ_OFFSET 0x0e
#define INIT_HCA_FLAGS_OFFSET 0x014
#define INIT_HCA_QPC_OFFSET 0x020
@@ -1432,6 +1443,12 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param)
MLX4_PUT(inbox, param->uar_page_sz, INIT_HCA_UAR_PAGE_SZ_OFFSET);
MLX4_PUT(inbox, param->log_uar_sz, INIT_HCA_LOG_UAR_SZ_OFFSET);
+ /* set parser VXLAN attributes */
+ if (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_VXLAN_OFFLOADS) {
+ u8 parser_params = 0;
+ MLX4_PUT(inbox, parser_params, INIT_HCA_VXLAN_OFFSET);
+ }
+
err = mlx4_cmd(dev, mailbox->dma, 0, 0, MLX4_CMD_INIT_HCA, 10000,
MLX4_CMD_NATIVE);
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index fbebfb0..d2b8b39 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -1444,6 +1444,19 @@ static void choose_steering_mode(struct mlx4_dev *dev,
mlx4_log_num_mgm_entry_size);
}
+static void choose_tunnel_offload_mode(struct mlx4_dev *dev,
+ struct mlx4_dev_cap *dev_cap)
+{
+ if (dev->caps.steering_mode == MLX4_STEERING_MODE_DEVICE_MANAGED &&
+ dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_VXLAN_OFFLOADS)
+ dev->caps.tunnel_offload_mode = MLX4_TUNNEL_OFFLOAD_MODE_VXLAN;
+ else
+ dev->caps.tunnel_offload_mode = MLX4_TUNNEL_OFFLOAD_MODE_NONE;
+
+ mlx4_dbg(dev, "Tunneling offload mode is: %s\n", (dev->caps.tunnel_offload_mode
+ == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) ? "vxlan" : "none");
+}
+
static int mlx4_init_hca(struct mlx4_dev *dev)
{
struct mlx4_priv *priv = mlx4_priv(dev);
@@ -1484,6 +1497,7 @@ static int mlx4_init_hca(struct mlx4_dev *dev)
}
choose_steering_mode(dev, &dev_cap);
+ choose_tunnel_offload_mode(dev, &dev_cap);
err = mlx4_get_phys_port_id(dev);
if (err)
diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c
index 7c83e6c..bfe65f7 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mcg.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c
@@ -697,7 +697,8 @@ const u16 __sw_id_hw[] = {
[MLX4_NET_TRANS_RULE_ID_IPV6] = 0xE003,
[MLX4_NET_TRANS_RULE_ID_IPV4] = 0xE002,
[MLX4_NET_TRANS_RULE_ID_TCP] = 0xE004,
- [MLX4_NET_TRANS_RULE_ID_UDP] = 0xE006
+ [MLX4_NET_TRANS_RULE_ID_UDP] = 0xE006,
+ [MLX4_NET_TRANS_RULE_ID_VXLAN] = 0xE008
};
int mlx4_map_sw_to_hw_steering_id(struct mlx4_dev *dev,
@@ -722,7 +723,9 @@ static const int __rule_hw_sz[] = {
[MLX4_NET_TRANS_RULE_ID_TCP] =
sizeof(struct mlx4_net_trans_rule_hw_tcp_udp),
[MLX4_NET_TRANS_RULE_ID_UDP] =
- sizeof(struct mlx4_net_trans_rule_hw_tcp_udp)
+ sizeof(struct mlx4_net_trans_rule_hw_tcp_udp),
+ [MLX4_NET_TRANS_RULE_ID_VXLAN] =
+ sizeof(struct mlx4_net_trans_rule_hw_vxlan)
};
int mlx4_hw_rule_sz(struct mlx4_dev *dev,
@@ -787,6 +790,13 @@ static int parse_trans_rule(struct mlx4_dev *dev, struct mlx4_spec_list *spec,
rule_hw->tcp_udp.src_port_msk = spec->tcp_udp.src_port_msk;
break;
+ case MLX4_NET_TRANS_RULE_ID_VXLAN:
+ rule_hw->vxlan.vni =
+ cpu_to_be32(be32_to_cpu(spec->vxlan.vni) << 8);
+ rule_hw->vxlan.vni_mask =
+ cpu_to_be32(be32_to_cpu(spec->vxlan.vni_mask) << 8);
+ break;
+
default:
return -EINVAL;
}
diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c
index 97d342f..93f75ec 100644
--- a/drivers/net/ethernet/mellanox/mlx4/port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/port.c
@@ -800,6 +800,47 @@ int mlx4_SET_PORT_SCHEDULER(struct mlx4_dev *dev, u8 port, u8 *tc_tx_bw,
}
EXPORT_SYMBOL(mlx4_SET_PORT_SCHEDULER);
+enum {
+ VXLAN_ENABLE_MODIFY = 1 << 7,
+ VXLAN_STEERING_MODIFY = 1 << 6,
+
+ VXLAN_ENABLE = 1 << 7,
+};
+
+struct mlx4_set_port_vxlan_context {
+ u32 reserved1;
+ u8 modify_flags;
+ u8 reserved2;
+ u8 enable_flags;
+ u8 steering;
+};
+
+int mlx4_SET_PORT_VXLAN(struct mlx4_dev *dev, u8 port, u8 steering)
+{
+ int err;
+ u32 in_mod;
+ struct mlx4_cmd_mailbox *mailbox;
+ struct mlx4_set_port_vxlan_context *context;
+
+ mailbox = mlx4_alloc_cmd_mailbox(dev);
+ if (IS_ERR(mailbox))
+ return PTR_ERR(mailbox);
+ context = mailbox->buf;
+ memset(context, 0, sizeof(*context));
+
+ context->modify_flags = VXLAN_ENABLE_MODIFY | VXLAN_STEERING_MODIFY;
+ context->enable_flags = VXLAN_ENABLE;
+ context->steering = steering;
+
+ in_mod = MLX4_SET_PORT_VXLAN << 8 | port;
+ err = mlx4_cmd(dev, mailbox->dma, in_mod, 1, MLX4_CMD_SET_PORT,
+ MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE);
+
+ mlx4_free_cmd_mailbox(dev, mailbox);
+ return err;
+}
+EXPORT_SYMBOL(mlx4_SET_PORT_VXLAN);
+
int mlx4_SET_MCAST_FLTR_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h
index 8df61bc..b0ec0fe 100644
--- a/include/linux/mlx4/cmd.h
+++ b/include/linux/mlx4/cmd.h
@@ -180,6 +180,7 @@ enum {
MLX4_SET_PORT_GID_TABLE = 0x5,
MLX4_SET_PORT_PRIO2TC = 0x8,
MLX4_SET_PORT_SCHEDULER = 0x9,
+ MLX4_SET_PORT_VXLAN = 0xB
};
enum {
diff --git a/include/linux/mlx4/cq.h b/include/linux/mlx4/cq.h
index 98fa492..5dd0d70 100644
--- a/include/linux/mlx4/cq.h
+++ b/include/linux/mlx4/cq.h
@@ -81,7 +81,12 @@ struct mlx4_ts_cqe {
} __packed;
enum {
+ MLX4_CQE_L2_TUNNEL_IPOK = 1 << 31,
MLX4_CQE_VLAN_PRESENT_MASK = 1 << 29,
+ MLX4_CQE_L2_TUNNEL = 1 << 27,
+ MLX4_CQE_L2_TUNNEL_CSUM = 1 << 26,
+ MLX4_CQE_L2_TUNNEL_IPV4 = 1 << 25,
+
MLX4_CQE_QPN_MASK = 0xffffff,
};
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 294b7c5..c99ecf6 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -119,6 +119,11 @@ static inline const char *mlx4_steering_mode_str(int steering_mode)
}
enum {
+ MLX4_TUNNEL_OFFLOAD_MODE_NONE,
+ MLX4_TUNNEL_OFFLOAD_MODE_VXLAN
+};
+
+enum {
MLX4_DEV_CAP_FLAG_RC = 1LL << 0,
MLX4_DEV_CAP_FLAG_UC = 1LL << 1,
MLX4_DEV_CAP_FLAG_UD = 1LL << 2,
@@ -160,7 +165,8 @@ enum {
MLX4_DEV_CAP_FLAG2_TS = 1LL << 5,
MLX4_DEV_CAP_FLAG2_VLAN_CONTROL = 1LL << 6,
MLX4_DEV_CAP_FLAG2_FSM = 1LL << 7,
- MLX4_DEV_CAP_FLAG2_UPDATE_QP = 1LL << 8
+ MLX4_DEV_CAP_FLAG2_UPDATE_QP = 1LL << 8,
+ MLX4_DEV_CAP_FLAG2_VXLAN_OFFLOADS = 1LL << 9
};
enum {
@@ -455,6 +461,7 @@ struct mlx4_caps {
u32 function_caps; /* VFs must be aware of these */
u16 hca_core_clock;
u64 phys_port_id[MLX4_MAX_PORTS + 1];
+ int tunnel_offload_mode;
};
struct mlx4_buf_list {
@@ -909,6 +916,7 @@ enum mlx4_net_trans_rule_id {
MLX4_NET_TRANS_RULE_ID_IPV4,
MLX4_NET_TRANS_RULE_ID_TCP,
MLX4_NET_TRANS_RULE_ID_UDP,
+ MLX4_NET_TRANS_RULE_ID_VXLAN,
MLX4_NET_TRANS_RULE_NUM, /* should be last */
};
@@ -966,6 +974,12 @@ struct mlx4_spec_ib {
u8 dst_gid_msk[16];
};
+struct mlx4_spec_vxlan {
+ __be32 vni;
+ __be32 vni_mask;
+
+};
+
struct mlx4_spec_list {
struct list_head list;
enum mlx4_net_trans_rule_id id;
@@ -974,6 +988,7 @@ struct mlx4_spec_list {
struct mlx4_spec_ib ib;
struct mlx4_spec_ipv4 ipv4;
struct mlx4_spec_tcp_udp tcp_udp;
+ struct mlx4_spec_vxlan vxlan;
};
};
@@ -1060,6 +1075,15 @@ struct mlx4_net_trans_rule_hw_ipv4 {
__be32 src_ip_msk;
} __packed;
+struct mlx4_net_trans_rule_hw_vxlan {
+ u8 size;
+ u8 rsvd;
+ __be16 id;
+ __be32 rsvd1;
+ __be32 vni;
+ __be32 vni_mask;
+} __packed;
+
struct _rule_hw {
union {
struct {
@@ -1071,9 +1095,19 @@ struct _rule_hw {
struct mlx4_net_trans_rule_hw_ib ib;
struct mlx4_net_trans_rule_hw_ipv4 ipv4;
struct mlx4_net_trans_rule_hw_tcp_udp tcp_udp;
+ struct mlx4_net_trans_rule_hw_vxlan vxlan;
};
};
+enum {
+ VXLAN_STEER_BY_OUTER_MAC = 1 << 0,
+ VXLAN_STEER_BY_OUTER_VLAN = 1 << 1,
+ VXLAN_STEER_BY_VSID_VNI = 1 << 2,
+ VXLAN_STEER_BY_INNER_MAC = 1 << 3,
+ VXLAN_STEER_BY_INNER_VLAN = 1 << 4,
+};
+
+
int mlx4_flow_steer_promisc_add(struct mlx4_dev *dev, u8 port, u32 qpn,
enum mlx4_net_trans_promisc_mode mode);
int mlx4_flow_steer_promisc_remove(struct mlx4_dev *dev, u8 port,
@@ -1096,6 +1130,7 @@ int mlx4_SET_PORT_qpn_calc(struct mlx4_dev *dev, u8 port, u32 base_qpn,
int mlx4_SET_PORT_PRIO2TC(struct mlx4_dev *dev, u8 port, u8 *prio2tc);
int mlx4_SET_PORT_SCHEDULER(struct mlx4_dev *dev, u8 port, u8 *tc_tx_bw,
u8 *pg, u16 *ratelimit);
+int mlx4_SET_PORT_VXLAN(struct mlx4_dev *dev, u8 port, u8 steering);
int mlx4_find_cached_vlan(struct mlx4_dev *dev, u8 port, u16 vid, int *idx);
int mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index);
void mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, u16 vlan);
diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h
index 6d35147..59f8ba8 100644
--- a/include/linux/mlx4/qp.h
+++ b/include/linux/mlx4/qp.h
@@ -109,6 +109,10 @@ enum {
MLX4_RSS_TCP_IPV4 = 1 << 4,
MLX4_RSS_IPV4 = 1 << 5,
+ MLX4_RSS_BY_OUTER_HEADERS = 0 << 6,
+ MLX4_RSS_BY_INNER_HEADERS = 2 << 6,
+ MLX4_RSS_BY_INNER_HEADERS_IPONLY = 3 << 6,
+
/* offset of mlx4_rss_context within mlx4_qp_context.pri_path */
MLX4_RSS_OFFSET_IN_QPC_PRI_PATH = 0x24,
/* offset of being RSS indirection QP within mlx4_qp_context.flags */
@@ -252,6 +256,8 @@ enum { /* param3 */
enum {
MLX4_WQE_CTRL_NEC = 1 << 29,
+ MLX4_WQE_CTRL_IIP = 1 << 28,
+ MLX4_WQE_CTRL_ILP = 1 << 27,
MLX4_WQE_CTRL_FENCE = 1 << 6,
MLX4_WQE_CTRL_CQ_UPDATE = 3 << 2,
MLX4_WQE_CTRL_SOLICITED = 1 << 1,
--
1.7.1
^ permalink raw reply related [flat|nested] 4+ messages in thread* [PATCH net-next 2/2] net/mlx4_en: Add netdev support for TCP/IP offloads of vxlan tunneling
2013-12-18 14:05 [PATCH net-next 0/2] net/mlx4: Add support for TCP/IP offloads of vxlan tunneling Or Gerlitz
2013-12-18 14:05 ` [PATCH net-next 1/2] net/mlx4_core: Add basic support for TCP/IP offloads under tunneling Or Gerlitz
@ 2013-12-18 14:05 ` Or Gerlitz
2013-12-19 1:16 ` [PATCH net-next 0/2] net/mlx4: Add " Wei-Chun Chao
2 siblings, 0 replies; 4+ messages in thread
From: Or Gerlitz @ 2013-12-18 14:05 UTC (permalink / raw)
To: davem; +Cc: netdev, amirv, yanb, ast, Or Gerlitz
When the device tunneling offloads mode is vxlan do the following
- call SET_PORT with the relevant setting
- add DMFS steering vxlan rule for the device self and multicast mac addresses
of the form: {<ETH, outer-mac> <VXLAN, ANY vnid> <ETH, ANY mac>} --> RSS QP
- set relevant QPC fields in RSS context and RX ring QPs
- in TX flow, set WQE fields to generate HW checksum, and handle gso skbs
which are marked for encapsulation such that the HW will segment them properly.
- in RX flow, read HW offloaded checksum for encapsulated packets from the CQE
- advertize hw_enc_features and NETIF_F_GSO_UDP_TUNNEL to the networking stack
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 95 +++++++++++++++++++++
drivers/net/ethernet/mellanox/mlx4/en_resources.c | 6 ++
drivers/net/ethernet/mellanox/mlx4/en_rx.c | 15 +++-
drivers/net/ethernet/mellanox/mlx4/en_tx.c | 14 +++-
drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 3 +-
5 files changed, 130 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 6f92090..b4b36d8 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -468,6 +468,53 @@ static void mlx4_en_u64_to_mac(unsigned char dst_mac[ETH_ALEN + 2], u64 src_mac)
memset(&dst_mac[ETH_ALEN], 0, 2);
}
+
+static int mlx4_en_tunnel_steer_add(struct mlx4_en_priv *priv, unsigned char *addr,
+ int qpn, u64 *reg_id)
+{
+ int err;
+ struct mlx4_spec_list spec_eth_outer = { {NULL} };
+ struct mlx4_spec_list spec_vxlan = { {NULL} };
+ struct mlx4_spec_list spec_eth_inner = { {NULL} };
+
+ struct mlx4_net_trans_rule rule = {
+ .queue_mode = MLX4_NET_TRANS_Q_FIFO,
+ .exclusive = 0,
+ .allow_loopback = 1,
+ .promisc_mode = MLX4_FS_REGULAR,
+ .priority = MLX4_DOMAIN_NIC,
+ };
+
+ __be64 mac_mask = cpu_to_be64(MLX4_MAC_MASK << 16);
+
+ if ((priv->mdev->dev->caps.tunnel_offload_mode != MLX4_TUNNEL_OFFLOAD_MODE_VXLAN))
+ return 0; /* do nothing */
+
+ rule.port = priv->port;
+ rule.qpn = qpn;
+ INIT_LIST_HEAD(&rule.list);
+
+ spec_eth_outer.id = MLX4_NET_TRANS_RULE_ID_ETH;
+ memcpy(spec_eth_outer.eth.dst_mac, addr, ETH_ALEN);
+ memcpy(spec_eth_outer.eth.dst_mac_msk, &mac_mask, ETH_ALEN);
+
+ spec_vxlan.id = MLX4_NET_TRANS_RULE_ID_VXLAN; /* any vxlan header */
+ spec_eth_inner.id = MLX4_NET_TRANS_RULE_ID_ETH; /* any inner eth header */
+
+ list_add_tail(&spec_eth_outer.list, &rule.list);
+ list_add_tail(&spec_vxlan.list, &rule.list);
+ list_add_tail(&spec_eth_inner.list, &rule.list);
+
+ err = mlx4_flow_attach(priv->mdev->dev, &rule, reg_id);
+ if (err) {
+ en_err(priv, "failed to add vxlan steering rule, err %d\n", err);
+ return err;
+ }
+ en_dbg(DRV, priv, "added vxlan steering rule, mac %pM reg_id %llx\n", addr, *reg_id);
+ return 0;
+}
+
+
static int mlx4_en_uc_steer_add(struct mlx4_en_priv *priv,
unsigned char *mac, int *qpn, u64 *reg_id)
{
@@ -585,6 +632,10 @@ static int mlx4_en_get_qp(struct mlx4_en_priv *priv)
if (err)
goto steer_err;
+ if (mlx4_en_tunnel_steer_add(priv, priv->dev->dev_addr, *qpn,
+ &priv->tunnel_reg_id))
+ goto tunnel_err;
+
entry = kmalloc(sizeof(*entry), GFP_KERNEL);
if (!entry) {
err = -ENOMEM;
@@ -599,6 +650,9 @@ static int mlx4_en_get_qp(struct mlx4_en_priv *priv)
return 0;
alloc_err:
+ if (priv->tunnel_reg_id)
+ mlx4_flow_detach(priv->mdev->dev, priv->tunnel_reg_id);
+tunnel_err:
mlx4_en_uc_steer_release(priv, priv->dev->dev_addr, *qpn, reg_id);
steer_err:
@@ -642,6 +696,11 @@ static void mlx4_en_put_qp(struct mlx4_en_priv *priv)
}
}
+ if (priv->tunnel_reg_id) {
+ mlx4_flow_detach(priv->mdev->dev, priv->tunnel_reg_id);
+ priv->tunnel_reg_id = 0;
+ }
+
en_dbg(DRV, priv, "Releasing qp: port %d, qpn %d\n",
priv->port, qpn);
mlx4_qp_release_range(dev, qpn, 1);
@@ -1044,6 +1103,12 @@ static void mlx4_en_do_multicast(struct mlx4_en_priv *priv,
if (err)
en_err(priv, "Fail to detach multicast address\n");
+ if (mclist->tunnel_reg_id) {
+ err = mlx4_flow_detach(priv->mdev->dev, mclist->tunnel_reg_id);
+ if (err)
+ en_err(priv, "Failed to detach multicast address\n");
+ }
+
/* remove from list */
list_del(&mclist->list);
kfree(mclist);
@@ -1061,6 +1126,10 @@ static void mlx4_en_do_multicast(struct mlx4_en_priv *priv,
if (err)
en_err(priv, "Fail to attach multicast address\n");
+ err = mlx4_en_tunnel_steer_add(priv, &mc_list[10], priv->base_qpn,
+ &mclist->tunnel_reg_id);
+ if (err)
+ en_err(priv, "Failed to attach multicast address\n");
}
}
}
@@ -1598,6 +1667,15 @@ int mlx4_en_start_port(struct net_device *dev)
goto tx_err;
}
+ if ((mdev->dev->caps.tunnel_offload_mode == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN)) {
+ err = mlx4_SET_PORT_VXLAN(mdev->dev, priv->port, VXLAN_STEER_BY_OUTER_MAC);
+ if (err) {
+ en_err(priv, "Failed setting port L2 tunnel configuration, err %d\n",
+ err);
+ goto tx_err;
+ }
+ }
+
/* Init port */
en_dbg(HW, priv, "Initializing port\n");
err = mlx4_INIT_PORT(mdev->dev, priv->port);
@@ -2400,6 +2478,14 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
if (mdev->dev->caps.steering_mode != MLX4_STEERING_MODE_A0)
dev->priv_flags |= IFF_UNICAST_FLT;
+ if ((mdev->dev->caps.tunnel_offload_mode == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN)) {
+ dev->hw_enc_features = NETIF_F_SG | NETIF_F_IP_CSUM |
+ NETIF_F_RXCSUM | NETIF_F_TSO |
+ NETIF_F_GSO_UDP_TUNNEL;
+ dev->hw_features |= NETIF_F_GSO_UDP_TUNNEL;
+ dev->features |= NETIF_F_GSO_UDP_TUNNEL;
+ }
+
mdev->pndev[port] = dev;
netif_carrier_off(dev);
@@ -2429,6 +2515,15 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
goto out;
}
+ if ((mdev->dev->caps.tunnel_offload_mode == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN)) {
+ err = mlx4_SET_PORT_VXLAN(mdev->dev, priv->port, VXLAN_STEER_BY_OUTER_MAC);
+ if (err) {
+ en_err(priv, "Failed setting port L2 tunnel configuration, err %d\n",
+ err);
+ goto out;
+ }
+ }
+
/* Init port */
en_warn(priv, "Initializing port\n");
err = mlx4_INIT_PORT(mdev->dev, priv->port);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_resources.c b/drivers/net/ethernet/mellanox/mlx4/en_resources.c
index d3f5086..365dc56 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_resources.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_resources.c
@@ -68,6 +68,12 @@ void mlx4_en_fill_qp_context(struct mlx4_en_priv *priv, int size, int stride,
context->db_rec_addr = cpu_to_be64(priv->res.db.dma << 2);
if (!(dev->features & NETIF_F_HW_VLAN_CTAG_RX))
context->param3 |= cpu_to_be32(1 << 30);
+
+ if (!is_tx && !rss &&
+ (mdev->dev->caps.tunnel_offload_mode == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN)) {
+ en_dbg(HW, priv, "Setting RX qp %x tunnel mode to RX tunneled & non-tunneled\n", qpn);
+ context->srqn |= cpu_to_be32(7 << 28); /* this fills bits 30:28 */
+ }
}
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 07a1d0f..386e931 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -628,7 +628,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
int nr;
unsigned int length;
int polled = 0;
- int ip_summed;
+ int ip_summed, l2_tunnel;
int factor = priv->cqe_factor;
u64 timestamp;
@@ -709,6 +709,8 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
length -= ring->fcs_del;
ring->bytes += length;
ring->packets++;
+ l2_tunnel = (dev->hw_enc_features & NETIF_F_RXCSUM) &&
+ (cqe->vlan_my_qpn & cpu_to_be32(MLX4_CQE_L2_TUNNEL));
if (likely(dev->features & NETIF_F_RXCSUM)) {
if ((cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPOK)) &&
@@ -738,6 +740,8 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
gro_skb->data_len = length;
gro_skb->ip_summed = CHECKSUM_UNNECESSARY;
+ if (l2_tunnel)
+ gro_skb->encapsulation = 1;
if ((cqe->vlan_my_qpn &
cpu_to_be32(MLX4_CQE_VLAN_PRESENT_MASK)) &&
(dev->features & NETIF_F_HW_VLAN_CTAG_RX)) {
@@ -788,6 +792,9 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
skb->protocol = eth_type_trans(skb, dev);
skb_record_rx_queue(skb, cq->ring);
+ if (l2_tunnel)
+ skb->encapsulation = 1;
+
if (dev->features & NETIF_F_RXHASH)
skb->rxhash = be32_to_cpu(cqe->immed_rss_invalid);
@@ -1053,6 +1060,12 @@ int mlx4_en_config_rss_steer(struct mlx4_en_priv *priv)
rss_mask |= MLX4_RSS_UDP_IPV4 | MLX4_RSS_UDP_IPV6;
rss_context->base_qpn_udp = rss_context->default_qpn;
}
+
+ if ((mdev->dev->caps.tunnel_offload_mode == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN)) {
+ en_info(priv, "Setting RSS context tunnel type to RSS on inner headers\n");
+ rss_mask |= MLX4_RSS_BY_INNER_HEADERS;
+ }
+
rss_context->flags = rss_mask;
rss_context->hash_fn = MLX4_RSS_HASH_TOP;
for (i = 0; i < 10; i++)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index e3adceb..160e86d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -39,6 +39,7 @@
#include <linux/if_vlan.h>
#include <linux/vmalloc.h>
#include <linux/tcp.h>
+#include <linux/ip.h>
#include <linux/moduleparam.h>
#include "mlx4_en.h"
@@ -560,7 +561,10 @@ static int get_real_size(struct sk_buff *skb, struct net_device *dev,
int real_size;
if (skb_is_gso(skb)) {
- *lso_header_size = skb_transport_offset(skb) + tcp_hdrlen(skb);
+ if (skb->encapsulation)
+ *lso_header_size = (skb_inner_transport_header(skb) - skb->data) + inner_tcp_hdrlen(skb);
+ else
+ *lso_header_size = skb_transport_offset(skb) + tcp_hdrlen(skb);
real_size = CTRL_SIZE + skb_shinfo(skb)->nr_frags * DS_SIZE +
ALIGN(*lso_header_size + 4, DS_SIZE);
if (unlikely(*lso_header_size != skb_headlen(skb))) {
@@ -859,6 +863,14 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
tx_info->inl = 1;
}
+ if (skb->encapsulation) {
+ struct iphdr *ipv4 = (struct iphdr *)skb_inner_network_header(skb);
+ if (ipv4->protocol == IPPROTO_TCP || ipv4->protocol == IPPROTO_UDP)
+ op_own |= cpu_to_be32(MLX4_WQE_CTRL_IIP | MLX4_WQE_CTRL_ILP);
+ else
+ op_own |= cpu_to_be32(MLX4_WQE_CTRL_IIP);
+ }
+
ring->prod += nr_txbb;
/* If we used a bounce buffer then copy descriptor back into place */
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 123714c..766691c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -436,6 +436,7 @@ struct mlx4_en_mc_list {
enum mlx4_en_mclist_act action;
u8 addr[ETH_ALEN];
u64 reg_id;
+ u64 tunnel_reg_id;
};
struct mlx4_en_frag_info {
@@ -567,7 +568,7 @@ struct mlx4_en_priv {
struct list_head filters;
struct hlist_head filter_hash[1 << MLX4_EN_FILTER_HASH_SHIFT];
#endif
-
+ u64 tunnel_reg_id;
};
enum mlx4_en_wol {
--
1.7.1
^ permalink raw reply related [flat|nested] 4+ messages in thread