aboutsummaryrefslogtreecommitdiff
path: root/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/net/ethernet/mellanox/mlx4/en_netdev.c')
-rw-r--r--drivers/net/ethernet/mellanox/mlx4/en_netdev.c1556
1 files changed, 1249 insertions, 307 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 75a3f467bb5..7345c43b019 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -38,6 +38,8 @@
#include <linux/slab.h>
#include <linux/hash.h>
#include <net/ip.h>
+#include <net/busy_poll.h>
+#include <net/vxlan.h>
#include <linux/mlx4/driver.h>
#include <linux/mlx4/device.h>
@@ -67,12 +69,41 @@ int mlx4_en_setup_tc(struct net_device *dev, u8 up)
return 0;
}
+#ifdef CONFIG_NET_RX_BUSY_POLL
+/* must be called with local_bh_disable()d */
+static int mlx4_en_low_latency_recv(struct napi_struct *napi)
+{
+ struct mlx4_en_cq *cq = container_of(napi, struct mlx4_en_cq, napi);
+ struct net_device *dev = cq->dev;
+ struct mlx4_en_priv *priv = netdev_priv(dev);
+ struct mlx4_en_rx_ring *rx_ring = priv->rx_ring[cq->ring];
+ int done;
+
+ if (!priv->port_up)
+ return LL_FLUSH_FAILED;
+
+ if (!mlx4_en_cq_lock_poll(cq))
+ return LL_FLUSH_BUSY;
+
+ done = mlx4_en_process_rx_cq(dev, cq, 4);
+ if (likely(done))
+ rx_ring->cleaned += done;
+ else
+ rx_ring->misses++;
+
+ mlx4_en_cq_unlock_poll(cq);
+
+ return done;
+}
+#endif /* CONFIG_NET_RX_BUSY_POLL */
+
#ifdef CONFIG_RFS_ACCEL
struct mlx4_en_filter {
struct list_head next;
struct work_struct work;
+ u8 ip_proto;
__be32 src_ip;
__be32 dst_ip;
__be16 src_port;
@@ -91,14 +122,26 @@ struct mlx4_en_filter {
static void mlx4_en_filter_rfs_expire(struct mlx4_en_priv *priv);
+static enum mlx4_net_trans_rule_id mlx4_ip_proto_to_trans_rule_id(u8 ip_proto)
+{
+ switch (ip_proto) {
+ case IPPROTO_UDP:
+ return MLX4_NET_TRANS_RULE_ID_UDP;
+ case IPPROTO_TCP:
+ return MLX4_NET_TRANS_RULE_ID_TCP;
+ default:
+ return MLX4_NET_TRANS_RULE_NUM;
+ }
+};
+
static void mlx4_en_filter_work(struct work_struct *work)
{
struct mlx4_en_filter *filter = container_of(work,
struct mlx4_en_filter,
work);
struct mlx4_en_priv *priv = filter->priv;
- struct mlx4_spec_list spec_tcp = {
- .id = MLX4_NET_TRANS_RULE_ID_TCP,
+ struct mlx4_spec_list spec_tcp_udp = {
+ .id = mlx4_ip_proto_to_trans_rule_id(filter->ip_proto),
{
.tcp_udp = {
.dst_port = filter->dst_port,
@@ -127,22 +170,24 @@ static void mlx4_en_filter_work(struct work_struct *work)
.queue_mode = MLX4_NET_TRANS_Q_LIFO,
.exclusive = 1,
.allow_loopback = 1,
- .promisc_mode = MLX4_FS_PROMISC_NONE,
+ .promisc_mode = MLX4_FS_REGULAR,
.port = priv->port,
.priority = MLX4_DOMAIN_RFS,
};
int rc;
- __be64 mac;
__be64 mac_mask = cpu_to_be64(MLX4_MAC_MASK << 16);
+ if (spec_tcp_udp.id >= MLX4_NET_TRANS_RULE_NUM) {
+ en_warn(priv, "RFS: ignoring unsupported ip protocol (%d)\n",
+ filter->ip_proto);
+ goto ignore;
+ }
list_add_tail(&spec_eth.list, &rule.list);
list_add_tail(&spec_ip.list, &rule.list);
- list_add_tail(&spec_tcp.list, &rule.list);
-
- mac = cpu_to_be64((priv->mac & MLX4_MAC_MASK) << 16);
+ list_add_tail(&spec_tcp_udp.list, &rule.list);
rule.qpn = priv->rss_map.qps[filter->rxq_index].qpn;
- memcpy(spec_eth.eth.dst_mac, &mac, ETH_ALEN);
+ memcpy(spec_eth.eth.dst_mac, priv->dev->dev_addr, ETH_ALEN);
memcpy(spec_eth.eth.dst_mac_msk, &mac_mask, ETH_ALEN);
filter->activated = 0;
@@ -157,6 +202,7 @@ static void mlx4_en_filter_work(struct work_struct *work)
if (rc)
en_err(priv, "Error attaching flow. err = %d\n", rc);
+ignore:
mlx4_en_filter_rfs_expire(priv);
filter->activated = 1;
@@ -180,8 +226,8 @@ filter_hash_bucket(struct mlx4_en_priv *priv, __be32 src_ip, __be32 dst_ip,
static struct mlx4_en_filter *
mlx4_en_filter_alloc(struct mlx4_en_priv *priv, int rxq_index, __be32 src_ip,
- __be32 dst_ip, __be16 src_port, __be16 dst_port,
- u32 flow_id)
+ __be32 dst_ip, u8 ip_proto, __be16 src_port,
+ __be16 dst_port, u32 flow_id)
{
struct mlx4_en_filter *filter = NULL;
@@ -195,6 +241,7 @@ mlx4_en_filter_alloc(struct mlx4_en_priv *priv, int rxq_index, __be32 src_ip,
filter->src_ip = src_ip;
filter->dst_ip = dst_ip;
+ filter->ip_proto = ip_proto;
filter->src_port = src_port;
filter->dst_port = dst_port;
@@ -226,18 +273,18 @@ static void mlx4_en_filter_free(struct mlx4_en_filter *filter)
static inline struct mlx4_en_filter *
mlx4_en_filter_find(struct mlx4_en_priv *priv, __be32 src_ip, __be32 dst_ip,
- __be16 src_port, __be16 dst_port)
+ u8 ip_proto, __be16 src_port, __be16 dst_port)
{
- struct hlist_node *elem;
struct mlx4_en_filter *filter;
struct mlx4_en_filter *ret = NULL;
- hlist_for_each_entry(filter, elem,
+ hlist_for_each_entry(filter,
filter_hash_bucket(priv, src_ip, dst_ip,
src_port, dst_port),
filter_chain) {
if (filter->src_ip == src_ip &&
filter->dst_ip == dst_ip &&
+ filter->ip_proto == ip_proto &&
filter->src_port == src_port &&
filter->dst_port == dst_port) {
ret = filter;
@@ -256,6 +303,7 @@ mlx4_en_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb,
struct mlx4_en_filter *filter;
const struct iphdr *ip;
const __be16 *ports;
+ u8 ip_proto;
__be32 src_ip;
__be32 dst_ip;
__be16 src_port;
@@ -270,18 +318,19 @@ mlx4_en_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb,
if (ip_is_fragment(ip))
return -EPROTONOSUPPORT;
+ if ((ip->protocol != IPPROTO_TCP) && (ip->protocol != IPPROTO_UDP))
+ return -EPROTONOSUPPORT;
ports = (const __be16 *)(skb->data + nhoff + 4 * ip->ihl);
+ ip_proto = ip->protocol;
src_ip = ip->saddr;
dst_ip = ip->daddr;
src_port = ports[0];
dst_port = ports[1];
- if (ip->protocol != IPPROTO_TCP)
- return -EPROTONOSUPPORT;
-
spin_lock_bh(&priv->filters_lock);
- filter = mlx4_en_filter_find(priv, src_ip, dst_ip, src_port, dst_port);
+ filter = mlx4_en_filter_find(priv, src_ip, dst_ip, ip_proto,
+ src_port, dst_port);
if (filter) {
if (filter->rxq_index == rxq_index)
goto out;
@@ -289,7 +338,7 @@ mlx4_en_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb,
filter->rxq_index = rxq_index;
} else {
filter = mlx4_en_filter_alloc(priv, rxq_index,
- src_ip, dst_ip,
+ src_ip, dst_ip, ip_proto,
src_port, dst_port, flow_id);
if (!filter) {
ret = -ENOMEM;
@@ -307,8 +356,7 @@ err:
return ret;
}
-void mlx4_en_cleanup_filters(struct mlx4_en_priv *priv,
- struct mlx4_en_rx_ring *rx_ring)
+void mlx4_en_cleanup_filters(struct mlx4_en_priv *priv)
{
struct mlx4_en_filter *filter, *tmp;
LIST_HEAD(del_list);
@@ -360,7 +408,8 @@ static void mlx4_en_filter_rfs_expire(struct mlx4_en_priv *priv)
}
#endif
-static int mlx4_en_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
+static int mlx4_en_vlan_rx_add_vid(struct net_device *dev,
+ __be16 proto, u16 vid)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
struct mlx4_en_dev *mdev = priv->mdev;
@@ -379,18 +428,18 @@ static int mlx4_en_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
en_err(priv, "Failed configuring VLAN filter\n");
}
if (mlx4_register_vlan(mdev->dev, priv->port, vid, &idx))
- en_err(priv, "failed adding vlan %d\n", vid);
+ en_dbg(HW, priv, "failed adding vlan %d\n", vid);
mutex_unlock(&mdev->state_lock);
return 0;
}
-static int mlx4_en_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
+static int mlx4_en_vlan_rx_kill_vid(struct net_device *dev,
+ __be16 proto, u16 vid)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
struct mlx4_en_dev *mdev = priv->mdev;
int err;
- int idx;
en_dbg(HW, priv, "Killing VID:%d\n", vid);
@@ -398,10 +447,7 @@ static int mlx4_en_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
/* Remove VID from port VLAN filter */
mutex_lock(&mdev->state_lock);
- if (!mlx4_find_cached_vlan(mdev->dev, priv->port, vid, &idx))
- mlx4_unregister_vlan(mdev->dev, priv->port, idx);
- else
- en_err(priv, "could not find vid %d in cache\n", vid);
+ mlx4_unregister_vlan(mdev->dev, priv->port, vid);
if (mdev->device_up && priv->port_up) {
err = mlx4_SET_VLAN_FLTR(mdev->dev, priv);
@@ -413,52 +459,342 @@ static int mlx4_en_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
return 0;
}
-u64 mlx4_en_mac_to_u64(u8 *addr)
+static void mlx4_en_u64_to_mac(unsigned char dst_mac[ETH_ALEN + 2], u64 src_mac)
{
- u64 mac = 0;
int i;
+ for (i = ETH_ALEN - 1; i >= 0; --i) {
+ dst_mac[i] = src_mac & 0xff;
+ src_mac >>= 8;
+ }
+ 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);
- for (i = 0; i < ETH_ALEN; i++) {
- mac <<= 8;
- mac |= addr[i];
+ 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;
}
- return mac;
+ en_dbg(DRV, priv, "added vxlan steering rule, mac %pM reg_id %llx\n", addr, *reg_id);
+ return 0;
}
-static int mlx4_en_set_mac(struct net_device *dev, void *addr)
+
+static int mlx4_en_uc_steer_add(struct mlx4_en_priv *priv,
+ unsigned char *mac, int *qpn, u64 *reg_id)
{
- struct mlx4_en_priv *priv = netdev_priv(dev);
struct mlx4_en_dev *mdev = priv->mdev;
- struct sockaddr *saddr = addr;
+ struct mlx4_dev *dev = mdev->dev;
+ int err;
- if (!is_valid_ether_addr(saddr->sa_data))
- return -EADDRNOTAVAIL;
+ switch (dev->caps.steering_mode) {
+ case MLX4_STEERING_MODE_B0: {
+ struct mlx4_qp qp;
+ u8 gid[16] = {0};
+
+ qp.qpn = *qpn;
+ memcpy(&gid[10], mac, ETH_ALEN);
+ gid[5] = priv->port;
+
+ err = mlx4_unicast_attach(dev, &qp, gid, 0, MLX4_PROT_ETH);
+ break;
+ }
+ case MLX4_STEERING_MODE_DEVICE_MANAGED: {
+ struct mlx4_spec_list spec_eth = { {NULL} };
+ __be64 mac_mask = cpu_to_be64(MLX4_MAC_MASK << 16);
+
+ 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,
+ };
+
+ rule.port = priv->port;
+ rule.qpn = *qpn;
+ INIT_LIST_HEAD(&rule.list);
+
+ spec_eth.id = MLX4_NET_TRANS_RULE_ID_ETH;
+ memcpy(spec_eth.eth.dst_mac, mac, ETH_ALEN);
+ memcpy(spec_eth.eth.dst_mac_msk, &mac_mask, ETH_ALEN);
+ list_add_tail(&spec_eth.list, &rule.list);
+
+ err = mlx4_flow_attach(dev, &rule, reg_id);
+ break;
+ }
+ default:
+ return -EINVAL;
+ }
+ if (err)
+ en_warn(priv, "Failed Attaching Unicast\n");
+
+ return err;
+}
+
+static void mlx4_en_uc_steer_release(struct mlx4_en_priv *priv,
+ unsigned char *mac, int qpn, u64 reg_id)
+{
+ struct mlx4_en_dev *mdev = priv->mdev;
+ struct mlx4_dev *dev = mdev->dev;
+
+ switch (dev->caps.steering_mode) {
+ case MLX4_STEERING_MODE_B0: {
+ struct mlx4_qp qp;
+ u8 gid[16] = {0};
+
+ qp.qpn = qpn;
+ memcpy(&gid[10], mac, ETH_ALEN);
+ gid[5] = priv->port;
+
+ mlx4_unicast_detach(dev, &qp, gid, MLX4_PROT_ETH);
+ break;
+ }
+ case MLX4_STEERING_MODE_DEVICE_MANAGED: {
+ mlx4_flow_detach(dev, reg_id);
+ break;
+ }
+ default:
+ en_err(priv, "Invalid steering mode.\n");
+ }
+}
+
+static int mlx4_en_get_qp(struct mlx4_en_priv *priv)
+{
+ struct mlx4_en_dev *mdev = priv->mdev;
+ struct mlx4_dev *dev = mdev->dev;
+ struct mlx4_mac_entry *entry;
+ int index = 0;
+ int err = 0;
+ u64 reg_id;
+ int *qpn = &priv->base_qpn;
+ u64 mac = mlx4_mac_to_u64(priv->dev->dev_addr);
+
+ en_dbg(DRV, priv, "Registering MAC: %pM for adding\n",
+ priv->dev->dev_addr);
+ index = mlx4_register_mac(dev, priv->port, mac);
+ if (index < 0) {
+ err = index;
+ en_err(priv, "Failed adding MAC: %pM\n",
+ priv->dev->dev_addr);
+ return err;
+ }
+
+ if (dev->caps.steering_mode == MLX4_STEERING_MODE_A0) {
+ int base_qpn = mlx4_get_base_qpn(dev, priv->port);
+ *qpn = base_qpn + index;
+ return 0;
+ }
+
+ err = mlx4_qp_reserve_range(dev, 1, 1, qpn);
+ en_dbg(DRV, priv, "Reserved qp %d\n", *qpn);
+ if (err) {
+ en_err(priv, "Failed to reserve qp for mac registration\n");
+ goto qp_err;
+ }
+
+ err = mlx4_en_uc_steer_add(priv, priv->dev->dev_addr, qpn, &reg_id);
+ if (err)
+ goto steer_err;
+
+ err = mlx4_en_tunnel_steer_add(priv, priv->dev->dev_addr, *qpn,
+ &priv->tunnel_reg_id);
+ if (err)
+ goto tunnel_err;
+
+ entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+ if (!entry) {
+ err = -ENOMEM;
+ goto alloc_err;
+ }
+ memcpy(entry->mac, priv->dev->dev_addr, sizeof(entry->mac));
+ entry->reg_id = reg_id;
+
+ hlist_add_head_rcu(&entry->hlist,
+ &priv->mac_hash[entry->mac[MLX4_EN_MAC_HASH_IDX]]);
- memcpy(dev->dev_addr, saddr->sa_data, ETH_ALEN);
- priv->mac = mlx4_en_mac_to_u64(dev->dev_addr);
- queue_work(mdev->workqueue, &priv->mac_task);
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:
+ mlx4_qp_release_range(dev, *qpn, 1);
+
+qp_err:
+ mlx4_unregister_mac(dev, priv->port, mac);
+ return err;
}
-static void mlx4_en_do_set_mac(struct work_struct *work)
+static void mlx4_en_put_qp(struct mlx4_en_priv *priv)
+{
+ struct mlx4_en_dev *mdev = priv->mdev;
+ struct mlx4_dev *dev = mdev->dev;
+ int qpn = priv->base_qpn;
+ u64 mac;
+
+ if (dev->caps.steering_mode == MLX4_STEERING_MODE_A0) {
+ mac = mlx4_mac_to_u64(priv->dev->dev_addr);
+ en_dbg(DRV, priv, "Registering MAC: %pM for deleting\n",
+ priv->dev->dev_addr);
+ mlx4_unregister_mac(dev, priv->port, mac);
+ } else {
+ struct mlx4_mac_entry *entry;
+ struct hlist_node *tmp;
+ struct hlist_head *bucket;
+ unsigned int i;
+
+ for (i = 0; i < MLX4_EN_MAC_HASH_SIZE; ++i) {
+ bucket = &priv->mac_hash[i];
+ hlist_for_each_entry_safe(entry, tmp, bucket, hlist) {
+ mac = mlx4_mac_to_u64(entry->mac);
+ en_dbg(DRV, priv, "Registering MAC: %pM for deleting\n",
+ entry->mac);
+ mlx4_en_uc_steer_release(priv, entry->mac,
+ qpn, entry->reg_id);
+
+ mlx4_unregister_mac(dev, priv->port, mac);
+ hlist_del_rcu(&entry->hlist);
+ kfree_rcu(entry, rcu);
+ }
+ }
+
+ 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);
+ priv->flags &= ~MLX4_EN_FLAG_FORCE_PROMISC;
+ }
+}
+
+static int mlx4_en_replace_mac(struct mlx4_en_priv *priv, int qpn,
+ unsigned char *new_mac, unsigned char *prev_mac)
{
- struct mlx4_en_priv *priv = container_of(work, struct mlx4_en_priv,
- mac_task);
struct mlx4_en_dev *mdev = priv->mdev;
+ struct mlx4_dev *dev = mdev->dev;
+ int err = 0;
+ u64 new_mac_u64 = mlx4_mac_to_u64(new_mac);
+
+ if (dev->caps.steering_mode != MLX4_STEERING_MODE_A0) {
+ struct hlist_head *bucket;
+ unsigned int mac_hash;
+ struct mlx4_mac_entry *entry;
+ struct hlist_node *tmp;
+ u64 prev_mac_u64 = mlx4_mac_to_u64(prev_mac);
+
+ bucket = &priv->mac_hash[prev_mac[MLX4_EN_MAC_HASH_IDX]];
+ hlist_for_each_entry_safe(entry, tmp, bucket, hlist) {
+ if (ether_addr_equal_64bits(entry->mac, prev_mac)) {
+ mlx4_en_uc_steer_release(priv, entry->mac,
+ qpn, entry->reg_id);
+ mlx4_unregister_mac(dev, priv->port,
+ prev_mac_u64);
+ hlist_del_rcu(&entry->hlist);
+ synchronize_rcu();
+ memcpy(entry->mac, new_mac, ETH_ALEN);
+ entry->reg_id = 0;
+ mac_hash = new_mac[MLX4_EN_MAC_HASH_IDX];
+ hlist_add_head_rcu(&entry->hlist,
+ &priv->mac_hash[mac_hash]);
+ mlx4_register_mac(dev, priv->port, new_mac_u64);
+ err = mlx4_en_uc_steer_add(priv, new_mac,
+ &qpn,
+ &entry->reg_id);
+ if (err)
+ return err;
+ if (priv->tunnel_reg_id) {
+ mlx4_flow_detach(priv->mdev->dev, priv->tunnel_reg_id);
+ priv->tunnel_reg_id = 0;
+ }
+ err = mlx4_en_tunnel_steer_add(priv, new_mac, qpn,
+ &priv->tunnel_reg_id);
+ return err;
+ }
+ }
+ return -EINVAL;
+ }
+
+ return __mlx4_replace_mac(dev, priv->port, qpn, new_mac_u64);
+}
+
+static int mlx4_en_do_set_mac(struct mlx4_en_priv *priv)
+{
int err = 0;
- mutex_lock(&mdev->state_lock);
if (priv->port_up) {
/* Remove old MAC and insert the new one */
- err = mlx4_replace_mac(mdev->dev, priv->port,
- priv->base_qpn, priv->mac);
+ err = mlx4_en_replace_mac(priv, priv->base_qpn,
+ priv->dev->dev_addr, priv->prev_mac);
if (err)
en_err(priv, "Failed changing HW MAC address\n");
} else
- en_dbg(HW, priv, "Port is down while "
- "registering mac, exiting...\n");
+ en_dbg(HW, priv, "Port is down while registering mac, exiting...\n");
+
+ memcpy(priv->prev_mac, priv->dev->dev_addr,
+ sizeof(priv->prev_mac));
+
+ return err;
+}
+static int mlx4_en_set_mac(struct net_device *dev, void *addr)
+{
+ struct mlx4_en_priv *priv = netdev_priv(dev);
+ struct mlx4_en_dev *mdev = priv->mdev;
+ struct sockaddr *saddr = addr;
+ int err;
+
+ if (!is_valid_ether_addr(saddr->sa_data))
+ return -EADDRNOTAVAIL;
+
+ mutex_lock(&mdev->state_lock);
+ memcpy(dev->dev_addr, saddr->sa_data, ETH_ALEN);
+ err = mlx4_en_do_set_mac(priv);
mutex_unlock(&mdev->state_lock);
+
+ return err;
}
static void mlx4_en_clear_list(struct net_device *dev)
@@ -482,7 +818,6 @@ static void mlx4_en_cache_mclist(struct net_device *dev)
netdev_for_each_mc_addr(ha, dev) {
tmp = kzalloc(sizeof(struct mlx4_en_mc_list), GFP_ATOMIC);
if (!tmp) {
- en_err(priv, "failed to allocate multicast list\n");
mlx4_en_clear_list(dev);
return;
}
@@ -504,7 +839,7 @@ static void update_mclist_flags(struct mlx4_en_priv *priv,
list_for_each_entry(dst_tmp, dst, list) {
found = false;
list_for_each_entry(src_tmp, src, list) {
- if (!memcmp(dst_tmp->addr, src_tmp->addr, ETH_ALEN)) {
+ if (ether_addr_equal(dst_tmp->addr, src_tmp->addr)) {
found = true;
break;
}
@@ -519,189 +854,161 @@ static void update_mclist_flags(struct mlx4_en_priv *priv,
list_for_each_entry(src_tmp, src, list) {
found = false;
list_for_each_entry(dst_tmp, dst, list) {
- if (!memcmp(dst_tmp->addr, src_tmp->addr, ETH_ALEN)) {
+ if (ether_addr_equal(dst_tmp->addr, src_tmp->addr)) {
dst_tmp->action = MCLIST_NONE;
found = true;
break;
}
}
if (!found) {
- new_mc = kmalloc(sizeof(struct mlx4_en_mc_list),
+ new_mc = kmemdup(src_tmp,
+ sizeof(struct mlx4_en_mc_list),
GFP_KERNEL);
- if (!new_mc) {
- en_err(priv, "Failed to allocate current multicast list\n");
+ if (!new_mc)
return;
- }
- memcpy(new_mc, src_tmp,
- sizeof(struct mlx4_en_mc_list));
+
new_mc->action = MCLIST_ADD;
list_add_tail(&new_mc->list, dst);
}
}
}
-static void mlx4_en_set_multicast(struct net_device *dev)
+static void mlx4_en_set_rx_mode(struct net_device *dev)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
if (!priv->port_up)
return;
- queue_work(priv->mdev->workqueue, &priv->mcast_task);
+ queue_work(priv->mdev->workqueue, &priv->rx_mode_task);
}
-static void mlx4_en_do_set_multicast(struct work_struct *work)
+static void mlx4_en_set_promisc_mode(struct mlx4_en_priv *priv,
+ struct mlx4_en_dev *mdev)
{
- struct mlx4_en_priv *priv = container_of(work, struct mlx4_en_priv,
- mcast_task);
- struct mlx4_en_dev *mdev = priv->mdev;
- struct net_device *dev = priv->dev;
- struct mlx4_en_mc_list *mclist, *tmp;
- u64 mcast_addr = 0;
- u8 mc_list[16] = {0};
int err = 0;
- mutex_lock(&mdev->state_lock);
- if (!mdev->device_up) {
- en_dbg(HW, priv, "Card is not up, "
- "ignoring multicast change.\n");
- goto out;
- }
- if (!priv->port_up) {
- en_dbg(HW, priv, "Port is down, "
- "ignoring multicast change.\n");
- goto out;
- }
-
- if (!netif_carrier_ok(dev)) {
- if (!mlx4_en_QUERY_PORT(mdev, priv->port)) {
- if (priv->port_state.link_state) {
- priv->last_link_state = MLX4_DEV_EVENT_PORT_UP;
- netif_carrier_on(dev);
- en_dbg(LINK, priv, "Link Up\n");
- }
- }
- }
-
- /*
- * Promsicuous mode: disable all filters
- */
-
- if (dev->flags & IFF_PROMISC) {
- if (!(priv->flags & MLX4_EN_FLAG_PROMISC)) {
- if (netif_msg_rx_status(priv))
- en_warn(priv, "Entering promiscuous mode\n");
- priv->flags |= MLX4_EN_FLAG_PROMISC;
-
- /* Enable promiscouos mode */
- switch (mdev->dev->caps.steering_mode) {
- case MLX4_STEERING_MODE_DEVICE_MANAGED:
- err = mlx4_flow_steer_promisc_add(mdev->dev,
- priv->port,
- priv->base_qpn,
- MLX4_FS_PROMISC_UPLINK);
- if (err)
- en_err(priv, "Failed enabling promiscuous mode\n");
- priv->flags |= MLX4_EN_FLAG_MC_PROMISC;
- break;
-
- case MLX4_STEERING_MODE_B0:
- err = mlx4_unicast_promisc_add(mdev->dev,
- priv->base_qpn,
- priv->port);
- if (err)
- en_err(priv, "Failed enabling unicast promiscuous mode\n");
-
- /* Add the default qp number as multicast
- * promisc
- */
- if (!(priv->flags & MLX4_EN_FLAG_MC_PROMISC)) {
- err = mlx4_multicast_promisc_add(mdev->dev,
- priv->base_qpn,
- priv->port);
- if (err)
- en_err(priv, "Failed enabling multicast promiscuous mode\n");
- priv->flags |= MLX4_EN_FLAG_MC_PROMISC;
- }
- break;
-
- case MLX4_STEERING_MODE_A0:
- err = mlx4_SET_PORT_qpn_calc(mdev->dev,
- priv->port,
- priv->base_qpn,
- 1);
- if (err)
- en_err(priv, "Failed enabling promiscuous mode\n");
- break;
- }
-
- /* Disable port multicast filter (unconditionally) */
- err = mlx4_SET_MCAST_FLTR(mdev->dev, priv->port, 0,
- 0, MLX4_MCAST_DISABLE);
- if (err)
- en_err(priv, "Failed disabling "
- "multicast filter\n");
-
- /* Disable port VLAN filter */
- err = mlx4_SET_VLAN_FLTR(mdev->dev, priv);
- if (err)
- en_err(priv, "Failed disabling VLAN filter\n");
- }
- goto out;
- }
-
- /*
- * Not in promiscuous mode
- */
-
- if (priv->flags & MLX4_EN_FLAG_PROMISC) {
+ if (!(priv->flags & MLX4_EN_FLAG_PROMISC)) {
if (netif_msg_rx_status(priv))
- en_warn(priv, "Leaving promiscuous mode\n");
- priv->flags &= ~MLX4_EN_FLAG_PROMISC;
+ en_warn(priv, "Entering promiscuous mode\n");
+ priv->flags |= MLX4_EN_FLAG_PROMISC;
- /* Disable promiscouos mode */
+ /* Enable promiscouos mode */
switch (mdev->dev->caps.steering_mode) {
case MLX4_STEERING_MODE_DEVICE_MANAGED:
- err = mlx4_flow_steer_promisc_remove(mdev->dev,
- priv->port,
- MLX4_FS_PROMISC_UPLINK);
+ err = mlx4_flow_steer_promisc_add(mdev->dev,
+ priv->port,
+ priv->base_qpn,
+ MLX4_FS_ALL_DEFAULT);
if (err)
- en_err(priv, "Failed disabling promiscuous mode\n");
- priv->flags &= ~MLX4_EN_FLAG_MC_PROMISC;
+ en_err(priv, "Failed enabling promiscuous mode\n");
+ priv->flags |= MLX4_EN_FLAG_MC_PROMISC;
break;
case MLX4_STEERING_MODE_B0:
- err = mlx4_unicast_promisc_remove(mdev->dev,
- priv->base_qpn,
- priv->port);
+ err = mlx4_unicast_promisc_add(mdev->dev,
+ priv->base_qpn,
+ priv->port);
if (err)
- en_err(priv, "Failed disabling unicast promiscuous mode\n");
- /* Disable Multicast promisc */
- if (priv->flags & MLX4_EN_FLAG_MC_PROMISC) {
- err = mlx4_multicast_promisc_remove(mdev->dev,
- priv->base_qpn,
- priv->port);
+ en_err(priv, "Failed enabling unicast promiscuous mode\n");
+
+ /* Add the default qp number as multicast
+ * promisc
+ */
+ if (!(priv->flags & MLX4_EN_FLAG_MC_PROMISC)) {
+ err = mlx4_multicast_promisc_add(mdev->dev,
+ priv->base_qpn,
+ priv->port);
if (err)
- en_err(priv, "Failed disabling multicast promiscuous mode\n");
- priv->flags &= ~MLX4_EN_FLAG_MC_PROMISC;
+ en_err(priv, "Failed enabling multicast promiscuous mode\n");
+ priv->flags |= MLX4_EN_FLAG_MC_PROMISC;
}
break;
case MLX4_STEERING_MODE_A0:
err = mlx4_SET_PORT_qpn_calc(mdev->dev,
priv->port,
- priv->base_qpn, 0);
+ priv->base_qpn,
+ 1);
if (err)
- en_err(priv, "Failed disabling promiscuous mode\n");
+ en_err(priv, "Failed enabling promiscuous mode\n");
break;
}
- /* Enable port VLAN filter */
+ /* Disable port multicast filter (unconditionally) */
+ err = mlx4_SET_MCAST_FLTR(mdev->dev, priv->port, 0,
+ 0, MLX4_MCAST_DISABLE);
+ if (err)
+ en_err(priv, "Failed disabling multicast filter\n");
+
+ /* Disable port VLAN filter */
err = mlx4_SET_VLAN_FLTR(mdev->dev, priv);
if (err)
- en_err(priv, "Failed enabling VLAN filter\n");
+ en_err(priv, "Failed disabling VLAN filter\n");
+ }
+}
+
+static void mlx4_en_clear_promisc_mode(struct mlx4_en_priv *priv,
+ struct mlx4_en_dev *mdev)
+{
+ int err = 0;
+
+ if (netif_msg_rx_status(priv))
+ en_warn(priv, "Leaving promiscuous mode\n");
+ priv->flags &= ~MLX4_EN_FLAG_PROMISC;
+
+ /* Disable promiscouos mode */
+ switch (mdev->dev->caps.steering_mode) {
+ case MLX4_STEERING_MODE_DEVICE_MANAGED:
+ err = mlx4_flow_steer_promisc_remove(mdev->dev,
+ priv->port,
+ MLX4_FS_ALL_DEFAULT);
+ if (err)
+ en_err(priv, "Failed disabling promiscuous mode\n");
+ priv->flags &= ~MLX4_EN_FLAG_MC_PROMISC;
+ break;
+
+ case MLX4_STEERING_MODE_B0:
+ err = mlx4_unicast_promisc_remove(mdev->dev,
+ priv->base_qpn,
+ priv->port);
+ if (err)
+ en_err(priv, "Failed disabling unicast promiscuous mode\n");
+ /* Disable Multicast promisc */
+ if (priv->flags & MLX4_EN_FLAG_MC_PROMISC) {
+ err = mlx4_multicast_promisc_remove(mdev->dev,
+ priv->base_qpn,
+ priv->port);
+ if (err)
+ en_err(priv, "Failed disabling multicast promiscuous mode\n");
+ priv->flags &= ~MLX4_EN_FLAG_MC_PROMISC;
+ }
+ break;
+
+ case MLX4_STEERING_MODE_A0:
+ err = mlx4_SET_PORT_qpn_calc(mdev->dev,
+ priv->port,
+ priv->base_qpn, 0);
+ if (err)
+ en_err(priv, "Failed disabling promiscuous mode\n");
+ break;
}
+ /* Enable port VLAN filter */
+ err = mlx4_SET_VLAN_FLTR(mdev->dev, priv);
+ if (err)
+ en_err(priv, "Failed enabling VLAN filter\n");
+}
+
+static void mlx4_en_do_multicast(struct mlx4_en_priv *priv,
+ struct net_device *dev,
+ struct mlx4_en_dev *mdev)
+{
+ struct mlx4_en_mc_list *mclist, *tmp;
+ u64 mcast_addr = 0;
+ u8 mc_list[16] = {0};
+ int err = 0;
+
/* Enable/disable the multicast filter according to IFF_ALLMULTI */
if (dev->flags & IFF_ALLMULTI) {
err = mlx4_SET_MCAST_FLTR(mdev->dev, priv->port, 0,
@@ -716,7 +1023,7 @@ static void mlx4_en_do_set_multicast(struct work_struct *work)
err = mlx4_flow_steer_promisc_add(mdev->dev,
priv->port,
priv->base_qpn,
- MLX4_FS_PROMISC_ALL_MULTI);
+ MLX4_FS_MC_DEFAULT);
break;
case MLX4_STEERING_MODE_B0:
@@ -739,7 +1046,7 @@ static void mlx4_en_do_set_multicast(struct work_struct *work)
case MLX4_STEERING_MODE_DEVICE_MANAGED:
err = mlx4_flow_steer_promisc_remove(mdev->dev,
priv->port,
- MLX4_FS_PROMISC_ALL_MULTI);
+ MLX4_FS_MC_DEFAULT);
break;
case MLX4_STEERING_MODE_B0:
@@ -767,11 +1074,11 @@ static void mlx4_en_do_set_multicast(struct work_struct *work)
/* Update multicast list - we cache all addresses so they won't
* change while HW is updated holding the command semaphor */
- netif_tx_lock_bh(dev);
+ netif_addr_lock_bh(dev);
mlx4_en_cache_mclist(dev);
- netif_tx_unlock_bh(dev);
+ netif_addr_unlock_bh(dev);
list_for_each_entry(mclist, &priv->mc_list, list) {
- mcast_addr = mlx4_en_mac_to_u64(mclist->addr);
+ mcast_addr = mlx4_mac_to_u64(mclist->addr);
mlx4_SET_MCAST_FLTR(mdev->dev, priv->port,
mcast_addr, 0, MLX4_MCAST_CONFIG);
}
@@ -794,6 +1101,12 @@ static void mlx4_en_do_set_multicast(struct work_struct *work)
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);
@@ -811,9 +1124,177 @@ static void mlx4_en_do_set_multicast(struct work_struct *work)
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");
}
}
}
+}
+
+static void mlx4_en_do_uc_filter(struct mlx4_en_priv *priv,
+ struct net_device *dev,
+ struct mlx4_en_dev *mdev)
+{
+ struct netdev_hw_addr *ha;
+ struct mlx4_mac_entry *entry;
+ struct hlist_node *tmp;
+ bool found;
+ u64 mac;
+ int err = 0;
+ struct hlist_head *bucket;
+ unsigned int i;
+ int removed = 0;
+ u32 prev_flags;
+
+ /* Note that we do not need to protect our mac_hash traversal with rcu,
+ * since all modification code is protected by mdev->state_lock
+ */
+
+ /* find what to remove */
+ for (i = 0; i < MLX4_EN_MAC_HASH_SIZE; ++i) {
+ bucket = &priv->mac_hash[i];
+ hlist_for_each_entry_safe(entry, tmp, bucket, hlist) {
+ found = false;
+ netdev_for_each_uc_addr(ha, dev) {
+ if (ether_addr_equal_64bits(entry->mac,
+ ha->addr)) {
+ found = true;
+ break;
+ }
+ }
+
+ /* MAC address of the port is not in uc list */
+ if (ether_addr_equal_64bits(entry->mac, dev->dev_addr))
+ found = true;
+
+ if (!found) {
+ mac = mlx4_mac_to_u64(entry->mac);
+ mlx4_en_uc_steer_release(priv, entry->mac,
+ priv->base_qpn,
+ entry->reg_id);
+ mlx4_unregister_mac(mdev->dev, priv->port, mac);
+
+ hlist_del_rcu(&entry->hlist);
+ kfree_rcu(entry, rcu);
+ en_dbg(DRV, priv, "Removed MAC %pM on port:%d\n",
+ entry->mac, priv->port);
+ ++removed;
+ }
+ }
+ }
+
+ /* if we didn't remove anything, there is no use in trying to add
+ * again once we are in a forced promisc mode state
+ */
+ if ((priv->flags & MLX4_EN_FLAG_FORCE_PROMISC) && 0 == removed)
+ return;
+
+ prev_flags = priv->flags;
+ priv->flags &= ~MLX4_EN_FLAG_FORCE_PROMISC;
+
+ /* find what to add */
+ netdev_for_each_uc_addr(ha, dev) {
+ found = false;
+ bucket = &priv->mac_hash[ha->addr[MLX4_EN_MAC_HASH_IDX]];
+ hlist_for_each_entry(entry, bucket, hlist) {
+ if (ether_addr_equal_64bits(entry->mac, ha->addr)) {
+ found = true;
+ break;
+ }
+ }
+
+ if (!found) {
+ entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+ if (!entry) {
+ en_err(priv, "Failed adding MAC %pM on port:%d (out of memory)\n",
+ ha->addr, priv->port);
+ priv->flags |= MLX4_EN_FLAG_FORCE_PROMISC;
+ break;
+ }
+ mac = mlx4_mac_to_u64(ha->addr);
+ memcpy(entry->mac, ha->addr, ETH_ALEN);
+ err = mlx4_register_mac(mdev->dev, priv->port, mac);
+ if (err < 0) {
+ en_err(priv, "Failed registering MAC %pM on port %d: %d\n",
+ ha->addr, priv->port, err);
+ kfree(entry);
+ priv->flags |= MLX4_EN_FLAG_FORCE_PROMISC;
+ break;
+ }
+ err = mlx4_en_uc_steer_add(priv, ha->addr,
+ &priv->base_qpn,
+ &entry->reg_id);
+ if (err) {
+ en_err(priv, "Failed adding MAC %pM on port %d: %d\n",
+ ha->addr, priv->port, err);
+ mlx4_unregister_mac(mdev->dev, priv->port, mac);
+ kfree(entry);
+ priv->flags |= MLX4_EN_FLAG_FORCE_PROMISC;
+ break;
+ } else {
+ unsigned int mac_hash;
+ en_dbg(DRV, priv, "Added MAC %pM on port:%d\n",
+ ha->addr, priv->port);
+ mac_hash = ha->addr[MLX4_EN_MAC_HASH_IDX];
+ bucket = &priv->mac_hash[mac_hash];
+ hlist_add_head_rcu(&entry->hlist, bucket);
+ }
+ }
+ }
+
+ if (priv->flags & MLX4_EN_FLAG_FORCE_PROMISC) {
+ en_warn(priv, "Forcing promiscuous mode on port:%d\n",
+ priv->port);
+ } else if (prev_flags & MLX4_EN_FLAG_FORCE_PROMISC) {
+ en_warn(priv, "Stop forcing promiscuous mode on port:%d\n",
+ priv->port);
+ }
+}
+
+static void mlx4_en_do_set_rx_mode(struct work_struct *work)
+{
+ struct mlx4_en_priv *priv = container_of(work, struct mlx4_en_priv,
+ rx_mode_task);
+ struct mlx4_en_dev *mdev = priv->mdev;
+ struct net_device *dev = priv->dev;
+
+ mutex_lock(&mdev->state_lock);
+ if (!mdev->device_up) {
+ en_dbg(HW, priv, "Card is not up, ignoring rx mode change.\n");
+ goto out;
+ }
+ if (!priv->port_up) {
+ en_dbg(HW, priv, "Port is down, ignoring rx mode change.\n");
+ goto out;
+ }
+
+ if (!netif_carrier_ok(dev)) {
+ if (!mlx4_en_QUERY_PORT(mdev, priv->port)) {
+ if (priv->port_state.link_state) {
+ priv->last_link_state = MLX4_DEV_EVENT_PORT_UP;
+ netif_carrier_on(dev);
+ en_dbg(LINK, priv, "Link Up\n");
+ }
+ }
+ }
+
+ if (dev->priv_flags & IFF_UNICAST_FLT)
+ mlx4_en_do_uc_filter(priv, dev, mdev);
+
+ /* Promsicuous mode: disable all filters */
+ if ((dev->flags & IFF_PROMISC) ||
+ (priv->flags & MLX4_EN_FLAG_FORCE_PROMISC)) {
+ mlx4_en_set_promisc_mode(priv, mdev);
+ goto out;
+ }
+
+ /* Not in promiscuous mode */
+ if (priv->flags & MLX4_EN_FLAG_PROMISC)
+ mlx4_en_clear_promisc_mode(priv, mdev);
+
+ mlx4_en_do_multicast(priv, dev, mdev);
out:
mutex_unlock(&mdev->state_lock);
}
@@ -823,15 +1304,11 @@ static void mlx4_en_netpoll(struct net_device *dev)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
struct mlx4_en_cq *cq;
- unsigned long flags;
int i;
for (i = 0; i < priv->rx_ring_num; i++) {
- cq = &priv->rx_cq[i];
- spin_lock_irqsave(&cq->lock, flags);
- napi_synchronize(&cq->napi);
- mlx4_en_process_rx_cq(dev, cq, 0);
- spin_unlock_irqrestore(&cq->lock, flags);
+ cq = priv->rx_cq[i];
+ napi_schedule(&cq->napi);
}
}
#endif
@@ -840,10 +1317,19 @@ static void mlx4_en_tx_timeout(struct net_device *dev)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
struct mlx4_en_dev *mdev = priv->mdev;
+ int i;
if (netif_msg_timer(priv))
en_warn(priv, "Tx timeout called on port:%d\n", priv->port);
+ for (i = 0; i < priv->tx_ring_num; i++) {
+ if (!netif_tx_queue_stopped(netdev_get_tx_queue(dev, i)))
+ continue;
+ en_warn(priv, "TX timeout on queue: %d, QP: 0x%x, CQ: 0x%x, Cons: 0x%x, Prod: 0x%x\n",
+ i, priv->tx_ring[i]->qpn, priv->tx_ring[i]->cqn,
+ priv->tx_ring[i]->cons, priv->tx_ring[i]->prod);
+ }
+
priv->port_stats.tx_timeout++;
en_dbg(DRV, priv, "Scheduling watchdog\n");
queue_work(mdev->workqueue, &priv->watchdog_task);
@@ -876,13 +1362,12 @@ static void mlx4_en_set_default_moderation(struct mlx4_en_priv *priv)
priv->rx_usecs = MLX4_EN_RX_COAL_TIME;
priv->tx_frames = MLX4_EN_TX_COAL_PKTS;
priv->tx_usecs = MLX4_EN_TX_COAL_TIME;
- en_dbg(INTR, priv, "Default coalesing params for mtu:%d - "
- "rx_frames:%d rx_usecs:%d\n",
- priv->dev->mtu, priv->rx_frames, priv->rx_usecs);
+ en_dbg(INTR, priv, "Default coalesing params for mtu:%d - rx_frames:%d rx_usecs:%d\n",
+ priv->dev->mtu, priv->rx_frames, priv->rx_usecs);
/* Setup cq moderation params */
for (i = 0; i < priv->rx_ring_num; i++) {
- cq = &priv->rx_cq[i];
+ cq = priv->rx_cq[i];
cq->moder_cnt = priv->rx_frames;
cq->moder_time = priv->rx_usecs;
priv->last_moder_time[i] = MLX4_EN_AUTO_CONF;
@@ -891,7 +1376,7 @@ static void mlx4_en_set_default_moderation(struct mlx4_en_priv *priv)
}
for (i = 0; i < priv->tx_ring_num; i++) {
- cq = &priv->tx_cq[i];
+ cq = priv->tx_cq[i];
cq->moder_cnt = priv->tx_frames;
cq->moder_time = priv->tx_usecs;
}
@@ -925,8 +1410,8 @@ static void mlx4_en_auto_moderation(struct mlx4_en_priv *priv)
for (ring = 0; ring < priv->rx_ring_num; ring++) {
spin_lock_bh(&priv->stats_lock);
- rx_packets = priv->rx_ring[ring].packets;
- rx_bytes = priv->rx_ring[ring].bytes;
+ rx_packets = priv->rx_ring[ring]->packets;
+ rx_bytes = priv->rx_ring[ring]->bytes;
spin_unlock_bh(&priv->stats_lock);
rx_pkt_diff = ((unsigned long) (rx_packets -
@@ -955,12 +1440,13 @@ static void mlx4_en_auto_moderation(struct mlx4_en_priv *priv)
if (moder_time != priv->last_moder_time[ring]) {
priv->last_moder_time[ring] = moder_time;
- cq = &priv->rx_cq[ring];
+ cq = priv->rx_cq[ring];
cq->moder_time = moder_time;
+ cq->moder_cnt = priv->rx_frames;
err = mlx4_en_set_cq_moder(priv, cq);
if (err)
- en_err(priv, "Failed modifying moderation "
- "for cq:%d\n", ring);
+ en_err(priv, "Failed modifying moderation for cq:%d\n",
+ ring);
}
priv->last_moder_packets[ring] = rx_packets;
priv->last_moder_bytes[ring] = rx_bytes;
@@ -977,24 +1463,46 @@ static void mlx4_en_do_get_stats(struct work_struct *work)
struct mlx4_en_dev *mdev = priv->mdev;
int err;
- err = mlx4_en_DUMP_ETH_STATS(mdev, priv->port, 0);
- if (err)
- en_dbg(HW, priv, "Could not update stats\n");
-
mutex_lock(&mdev->state_lock);
if (mdev->device_up) {
- if (priv->port_up)
+ if (priv->port_up) {
+ err = mlx4_en_DUMP_ETH_STATS(mdev, priv->port, 0);
+ if (err)
+ en_dbg(HW, priv, "Could not update stats\n");
+
mlx4_en_auto_moderation(priv);
+ }
queue_delayed_work(mdev->workqueue, &priv->stats_task, STATS_DELAY);
}
if (mdev->mac_removed[MLX4_MAX_PORTS + 1 - priv->port]) {
- queue_work(mdev->workqueue, &priv->mac_task);
+ mlx4_en_do_set_mac(priv);
mdev->mac_removed[MLX4_MAX_PORTS + 1 - priv->port] = 0;
}
mutex_unlock(&mdev->state_lock);
}
+/* mlx4_en_service_task - Run service task for tasks that needed to be done
+ * periodically
+ */
+static void mlx4_en_service_task(struct work_struct *work)
+{
+ struct delayed_work *delay = to_delayed_work(work);
+ struct mlx4_en_priv *priv = container_of(delay, struct mlx4_en_priv,
+ service_task);
+ struct mlx4_en_dev *mdev = priv->mdev;
+
+ mutex_lock(&mdev->state_lock);
+ if (mdev->device_up) {
+ if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS)
+ mlx4_en_ptp_overflow_check(mdev);
+
+ queue_delayed_work(mdev->workqueue, &priv->service_task,
+ SERVICE_TASK_DELAY);
+ }
+ mutex_unlock(&mdev->state_lock);
+}
+
static void mlx4_en_linkstate(struct work_struct *work)
{
struct mlx4_en_priv *priv = container_of(work, struct mlx4_en_priv,
@@ -1018,6 +1526,27 @@ static void mlx4_en_linkstate(struct work_struct *work)
mutex_unlock(&mdev->state_lock);
}
+static int mlx4_en_init_affinity_hint(struct mlx4_en_priv *priv, int ring_idx)
+{
+ struct mlx4_en_rx_ring *ring = priv->rx_ring[ring_idx];
+ int numa_node = priv->mdev->dev->numa_node;
+ int ret = 0;
+
+ if (!zalloc_cpumask_var(&ring->affinity_mask, GFP_KERNEL))
+ return -ENOMEM;
+
+ ret = cpumask_set_cpu_local_first(ring_idx, numa_node,
+ ring->affinity_mask);
+ if (ret)
+ free_cpumask_var(ring->affinity_mask);
+
+ return ret;
+}
+
+static void mlx4_en_free_affinity_hint(struct mlx4_en_priv *priv, int ring_idx)
+{
+ free_cpumask_var(priv->rx_ring[ring_idx]->affinity_mask);
+}
int mlx4_en_start_port(struct net_device *dev)
{
@@ -1039,6 +1568,9 @@ int mlx4_en_start_port(struct net_device *dev)
INIT_LIST_HEAD(&priv->mc_list);
INIT_LIST_HEAD(&priv->curr_list);
+ INIT_LIST_HEAD(&priv->ethtool_list);
+ memset(&priv->ethtool_rules[0], 0,
+ sizeof(struct ethtool_flow_id) * MAX_NUM_OF_FS_RULES);
/* Calculate Rx buf size */
dev->mtu = min(dev->mtu, priv->max_mtu);
@@ -1052,30 +1584,39 @@ int mlx4_en_start_port(struct net_device *dev)
return err;
}
for (i = 0; i < priv->rx_ring_num; i++) {
- cq = &priv->rx_cq[i];
+ cq = priv->rx_cq[i];
+
+ mlx4_en_cq_init_lock(cq);
+
+ err = mlx4_en_init_affinity_hint(priv, i);
+ if (err) {
+ en_err(priv, "Failed preparing IRQ affinity hint\n");
+ goto cq_err;
+ }
err = mlx4_en_activate_cq(priv, cq, i);
if (err) {
en_err(priv, "Failed activating Rx CQ\n");
+ mlx4_en_free_affinity_hint(priv, i);
goto cq_err;
}
for (j = 0; j < cq->size; j++)
cq->buf[j].owner_sr_opcode = MLX4_CQE_OWNER_MASK;
err = mlx4_en_set_cq_moder(priv, cq);
if (err) {
- en_err(priv, "Failed setting cq moderation parameters");
+ en_err(priv, "Failed setting cq moderation parameters\n");
mlx4_en_deactivate_cq(priv, cq);
+ mlx4_en_free_affinity_hint(priv, i);
goto cq_err;
}
mlx4_en_arm_cq(priv, cq);
- priv->rx_ring[i].cqn = cq->mcq.cqn;
+ priv->rx_ring[i]->cqn = cq->mcq.cqn;
++rx_index;
}
/* Set qp number */
en_dbg(DRV, priv, "Getting qp number for port %d\n", priv->port);
- err = mlx4_get_eth_qp(mdev->dev, priv->port,
- priv->mac, &priv->base_qpn);
+ err = mlx4_en_get_qp(priv);
if (err) {
en_err(priv, "Failed getting eth qp\n");
goto cq_err;
@@ -1095,7 +1636,7 @@ int mlx4_en_start_port(struct net_device *dev)
/* Configure tx cq's and rings */
for (i = 0; i < priv->tx_ring_num; i++) {
/* Configure cq */
- cq = &priv->tx_cq[i];
+ cq = priv->tx_cq[i];
err = mlx4_en_activate_cq(priv, cq, i);
if (err) {
en_err(priv, "Failed allocating Tx CQ\n");
@@ -1103,7 +1644,7 @@ int mlx4_en_start_port(struct net_device *dev)
}
err = mlx4_en_set_cq_moder(priv, cq);
if (err) {
- en_err(priv, "Failed setting cq moderation parameters");
+ en_err(priv, "Failed setting cq moderation parameters\n");
mlx4_en_deactivate_cq(priv, cq);
goto tx_err;
}
@@ -1111,7 +1652,7 @@ int mlx4_en_start_port(struct net_device *dev)
cq->buf->wqe_index = cpu_to_be16(0xffff);
/* Configure ring */
- tx_ring = &priv->tx_ring[i];
+ tx_ring = priv->tx_ring[i];
err = mlx4_en_activate_tx_ring(priv, tx_ring, cq->mcq.cqn,
i / priv->num_tx_rings_p_up);
if (err) {
@@ -1138,8 +1679,8 @@ int mlx4_en_start_port(struct net_device *dev)
priv->prof->rx_pause,
priv->prof->rx_ppp);
if (err) {
- en_err(priv, "Failed setting port general configurations "
- "for port %d, with error %d\n", priv->port, err);
+ en_err(priv, "Failed setting port general configurations for port %d, with error %d\n",
+ priv->port, err);
goto tx_err;
}
/* Set default qp number */
@@ -1149,6 +1690,15 @@ 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, 1);
+ 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);
@@ -1167,50 +1717,50 @@ int mlx4_en_start_port(struct net_device *dev)
/* Must redo promiscuous mode setup. */
priv->flags &= ~(MLX4_EN_FLAG_PROMISC | MLX4_EN_FLAG_MC_PROMISC);
- if (mdev->dev->caps.steering_mode ==
- MLX4_STEERING_MODE_DEVICE_MANAGED) {
- mlx4_flow_steer_promisc_remove(mdev->dev,
- priv->port,
- MLX4_FS_PROMISC_UPLINK);
- mlx4_flow_steer_promisc_remove(mdev->dev,
- priv->port,
- MLX4_FS_PROMISC_ALL_MULTI);
- }
/* Schedule multicast task to populate multicast list */
- queue_work(mdev->workqueue, &priv->mcast_task);
+ queue_work(mdev->workqueue, &priv->rx_mode_task);
mlx4_set_stats_bitmap(mdev->dev, &priv->stats_bitmap);
+#ifdef CONFIG_MLX4_EN_VXLAN
+ if (priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_VXLAN_OFFLOADS)
+ vxlan_get_rx_port(dev);
+#endif
priv->port_up = true;
netif_tx_start_all_queues(dev);
+ netif_device_attach(dev);
+
return 0;
tx_err:
while (tx_index--) {
- mlx4_en_deactivate_tx_ring(priv, &priv->tx_ring[tx_index]);
- mlx4_en_deactivate_cq(priv, &priv->tx_cq[tx_index]);
+ mlx4_en_deactivate_tx_ring(priv, priv->tx_ring[tx_index]);
+ mlx4_en_deactivate_cq(priv, priv->tx_cq[tx_index]);
}
mlx4_en_destroy_drop_qp(priv);
rss_err:
mlx4_en_release_rss_steer(priv);
mac_err:
- mlx4_put_eth_qp(mdev->dev, priv->port, priv->mac, priv->base_qpn);
+ mlx4_en_put_qp(priv);
cq_err:
- while (rx_index--)
- mlx4_en_deactivate_cq(priv, &priv->rx_cq[rx_index]);
+ while (rx_index--) {
+ mlx4_en_deactivate_cq(priv, priv->rx_cq[rx_index]);
+ mlx4_en_free_affinity_hint(priv, i);
+ }
for (i = 0; i < priv->rx_ring_num; i++)
- mlx4_en_deactivate_rx_ring(priv, &priv->rx_ring[i]);
+ mlx4_en_deactivate_rx_ring(priv, priv->rx_ring[i]);
return err; /* need to close devices */
}
-void mlx4_en_stop_port(struct net_device *dev)
+void mlx4_en_stop_port(struct net_device *dev, int detach)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
struct mlx4_en_dev *mdev = priv->mdev;
struct mlx4_en_mc_list *mclist, *tmp;
+ struct ethtool_flow_id *flow, *tmp_flow;
int i;
u8 mc_list[16] = {0};
@@ -1219,14 +1769,47 @@ void mlx4_en_stop_port(struct net_device *dev)
return;
}
+ /* close port*/
+ mlx4_CLOSE_PORT(mdev->dev, priv->port);
+
/* Synchronize with tx routine */
netif_tx_lock_bh(dev);
+ if (detach)
+ netif_device_detach(dev);
netif_tx_stop_all_queues(dev);
netif_tx_unlock_bh(dev);
+ netif_tx_disable(dev);
+
/* Set port as not active */
priv->port_up = false;
+ /* Promsicuous mode */
+ if (mdev->dev->caps.steering_mode ==
+ MLX4_STEERING_MODE_DEVICE_MANAGED) {
+ priv->flags &= ~(MLX4_EN_FLAG_PROMISC |
+ MLX4_EN_FLAG_MC_PROMISC);
+ mlx4_flow_steer_promisc_remove(mdev->dev,
+ priv->port,
+ MLX4_FS_ALL_DEFAULT);
+ mlx4_flow_steer_promisc_remove(mdev->dev,
+ priv->port,
+ MLX4_FS_MC_DEFAULT);
+ } else if (priv->flags & MLX4_EN_FLAG_PROMISC) {
+ priv->flags &= ~MLX4_EN_FLAG_PROMISC;
+
+ /* Disable promiscouos mode */
+ mlx4_unicast_promisc_remove(mdev->dev, priv->base_qpn,
+ priv->port);
+
+ /* Disable Multicast promisc */
+ if (priv->flags & MLX4_EN_FLAG_MC_PROMISC) {
+ mlx4_multicast_promisc_remove(mdev->dev, priv->base_qpn,
+ priv->port);
+ priv->flags &= ~MLX4_EN_FLAG_MC_PROMISC;
+ }
+ }
+
/* Detach All multicasts */
memset(&mc_list[10], 0xff, ETH_ALEN);
mc_list[5] = priv->port; /* needed for B0 steering support */
@@ -1237,6 +1820,8 @@ void mlx4_en_stop_port(struct net_device *dev)
mc_list[5] = priv->port;
mlx4_multicast_detach(mdev->dev, &priv->rss_map.indir_qp,
mc_list, MLX4_PROT_ETH, mclist->reg_id);
+ if (mclist->tunnel_reg_id)
+ mlx4_flow_detach(mdev->dev, mclist->tunnel_reg_id);
}
mlx4_en_clear_list(dev);
list_for_each_entry_safe(mclist, tmp, &priv->curr_list, list) {
@@ -1247,35 +1832,55 @@ void mlx4_en_stop_port(struct net_device *dev)
/* Flush multicast filter */
mlx4_SET_MCAST_FLTR(mdev->dev, priv->port, 0, 1, MLX4_MCAST_CONFIG);
+ /* Remove flow steering rules for the port*/
+ if (mdev->dev->caps.steering_mode ==
+ MLX4_STEERING_MODE_DEVICE_MANAGED) {
+ ASSERT_RTNL();
+ list_for_each_entry_safe(flow, tmp_flow,
+ &priv->ethtool_list, list) {
+ mlx4_flow_detach(mdev->dev, flow->id);
+ list_del(&flow->list);
+ }
+ }
+
mlx4_en_destroy_drop_qp(priv);
/* Free TX Rings */
for (i = 0; i < priv->tx_ring_num; i++) {
- mlx4_en_deactivate_tx_ring(priv, &priv->tx_ring[i]);
- mlx4_en_deactivate_cq(priv, &priv->tx_cq[i]);
+ mlx4_en_deactivate_tx_ring(priv, priv->tx_ring[i]);
+ mlx4_en_deactivate_cq(priv, priv->tx_cq[i]);
}
msleep(10);
for (i = 0; i < priv->tx_ring_num; i++)
- mlx4_en_free_tx_buf(dev, &priv->tx_ring[i]);
+ mlx4_en_free_tx_buf(dev, priv->tx_ring[i]);
/* Free RSS qps */
mlx4_en_release_rss_steer(priv);
/* Unregister Mac address for the port */
- mlx4_put_eth_qp(mdev->dev, priv->port, priv->mac, priv->base_qpn);
- mdev->mac_removed[priv->port] = 1;
+ mlx4_en_put_qp(priv);
+ if (!(mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_REASSIGN_MAC_EN))
+ mdev->mac_removed[priv->port] = 1;
/* Free RX Rings */
for (i = 0; i < priv->rx_ring_num; i++) {
- mlx4_en_deactivate_rx_ring(priv, &priv->rx_ring[i]);
- while (test_bit(NAPI_STATE_SCHED, &priv->rx_cq[i].napi.state))
+ struct mlx4_en_cq *cq = priv->rx_cq[i];
+
+ local_bh_disable();
+ while (!mlx4_en_cq_lock_napi(cq)) {
+ pr_info("CQ %d locked\n", i);
+ mdelay(1);
+ }
+ local_bh_enable();
+
+ while (test_bit(NAPI_STATE_SCHED, &cq->napi.state))
msleep(1);
- mlx4_en_deactivate_cq(priv, &priv->rx_cq[i]);
- }
+ mlx4_en_deactivate_rx_ring(priv, priv->rx_ring[i]);
+ mlx4_en_deactivate_cq(priv, cq);
- /* close port*/
- mlx4_CLOSE_PORT(mdev->dev, priv->port);
+ mlx4_en_free_affinity_hint(priv, i);
+ }
}
static void mlx4_en_restart(struct work_struct *work)
@@ -1284,15 +1889,12 @@ static void mlx4_en_restart(struct work_struct *work)
watchdog_task);
struct mlx4_en_dev *mdev = priv->mdev;
struct net_device *dev = priv->dev;
- int i;
en_dbg(DRV, priv, "Watchdog task called for port %d\n", priv->port);
mutex_lock(&mdev->state_lock);
if (priv->port_up) {
- mlx4_en_stop_port(dev);
- for (i = 0; i < priv->tx_ring_num; i++)
- netdev_tx_reset_queue(priv->tx_ring[i].tx_queue);
+ mlx4_en_stop_port(dev, 1);
if (mlx4_en_start_port(dev))
en_err(priv, "Failed restarting port %d\n", priv->port);
}
@@ -1314,15 +1916,15 @@ static void mlx4_en_clear_stats(struct net_device *dev)
memset(&priv->port_stats, 0, sizeof(priv->port_stats));
for (i = 0; i < priv->tx_ring_num; i++) {
- priv->tx_ring[i].bytes = 0;
- priv->tx_ring[i].packets = 0;
- priv->tx_ring[i].tx_csum = 0;
+ priv->tx_ring[i]->bytes = 0;
+ priv->tx_ring[i]->packets = 0;
+ priv->tx_ring[i]->tx_csum = 0;
}
for (i = 0; i < priv->rx_ring_num; i++) {
- priv->rx_ring[i].bytes = 0;
- priv->rx_ring[i].packets = 0;
- priv->rx_ring[i].csum_ok = 0;
- priv->rx_ring[i].csum_none = 0;
+ priv->rx_ring[i]->bytes = 0;
+ priv->rx_ring[i]->packets = 0;
+ priv->rx_ring[i]->csum_ok = 0;
+ priv->rx_ring[i]->csum_none = 0;
}
}
@@ -1362,7 +1964,7 @@ static int mlx4_en_close(struct net_device *dev)
mutex_lock(&mdev->state_lock);
- mlx4_en_stop_port(dev);
+ mlx4_en_stop_port(dev, 0);
netif_carrier_off(dev);
mutex_unlock(&mdev->state_lock);
@@ -1379,17 +1981,17 @@ void mlx4_en_free_resources(struct mlx4_en_priv *priv)
#endif
for (i = 0; i < priv->tx_ring_num; i++) {
- if (priv->tx_ring[i].tx_info)
+ if (priv->tx_ring && priv->tx_ring[i])
mlx4_en_destroy_tx_ring(priv, &priv->tx_ring[i]);
- if (priv->tx_cq[i].buf)
+ if (priv->tx_cq && priv->tx_cq[i])
mlx4_en_destroy_cq(priv, &priv->tx_cq[i]);
}
for (i = 0; i < priv->rx_ring_num; i++) {
- if (priv->rx_ring[i].rx_info)
+ if (priv->rx_ring[i])
mlx4_en_destroy_rx_ring(priv, &priv->rx_ring[i],
priv->prof->rx_ring_size, priv->stride);
- if (priv->rx_cq[i].buf)
+ if (priv->rx_cq[i])
mlx4_en_destroy_cq(priv, &priv->rx_cq[i]);
}
@@ -1404,6 +2006,7 @@ int mlx4_en_alloc_resources(struct mlx4_en_priv *priv)
struct mlx4_en_port_profile *prof = priv->prof;
int i;
int err;
+ int node;
err = mlx4_qp_reserve_range(priv->mdev->dev, priv->tx_ring_num, 256, &priv->base_tx_qpn);
if (err) {
@@ -1413,39 +2016,57 @@ int mlx4_en_alloc_resources(struct mlx4_en_priv *priv)
/* Create tx Rings */
for (i = 0; i < priv->tx_ring_num; i++) {
+ node = cpu_to_node(i % num_online_cpus());
if (mlx4_en_create_cq(priv, &priv->tx_cq[i],
- prof->tx_ring_size, i, TX))
+ prof->tx_ring_size, i, TX, node))
goto err;
- if (mlx4_en_create_tx_ring(priv, &priv->tx_ring[i], priv->base_tx_qpn + i,
- prof->tx_ring_size, TXBB_SIZE))
+ if (mlx4_en_create_tx_ring(priv, &priv->tx_ring[i],
+ priv->base_tx_qpn + i,
+ prof->tx_ring_size, TXBB_SIZE,
+ node, i))
goto err;
}
/* Create rx Rings */
for (i = 0; i < priv->rx_ring_num; i++) {
+ node = cpu_to_node(i % num_online_cpus());
if (mlx4_en_create_cq(priv, &priv->rx_cq[i],
- prof->rx_ring_size, i, RX))
+ prof->rx_ring_size, i, RX, node))
goto err;
if (mlx4_en_create_rx_ring(priv, &priv->rx_ring[i],
- prof->rx_ring_size, priv->stride))
+ prof->rx_ring_size, priv->stride,
+ node))
goto err;
}
#ifdef CONFIG_RFS_ACCEL
- priv->dev->rx_cpu_rmap = alloc_irq_cpu_rmap(priv->rx_ring_num);
- if (!priv->dev->rx_cpu_rmap)
- goto err;
-
- INIT_LIST_HEAD(&priv->filters);
- spin_lock_init(&priv->filters_lock);
+ if (priv->mdev->dev->caps.comp_pool) {
+ priv->dev->rx_cpu_rmap = alloc_irq_cpu_rmap(priv->mdev->dev->caps.comp_pool);
+ if (!priv->dev->rx_cpu_rmap)
+ goto err;
+ }
#endif
return 0;
err:
en_err(priv, "Failed to allocate NIC resources\n");
+ for (i = 0; i < priv->rx_ring_num; i++) {
+ if (priv->rx_ring[i])
+ mlx4_en_destroy_rx_ring(priv, &priv->rx_ring[i],
+ prof->rx_ring_size,
+ priv->stride);
+ if (priv->rx_cq[i])
+ mlx4_en_destroy_cq(priv, &priv->rx_cq[i]);
+ }
+ for (i = 0; i < priv->tx_ring_num; i++) {
+ if (priv->tx_ring[i])
+ mlx4_en_destroy_tx_ring(priv, &priv->tx_ring[i]);
+ if (priv->tx_cq[i])
+ mlx4_en_destroy_cq(priv, &priv->tx_cq[i]);
+ }
return -ENOMEM;
}
@@ -1465,6 +2086,7 @@ void mlx4_en_destroy_netdev(struct net_device *dev)
mlx4_free_hwq_res(mdev->dev, &priv->res, MLX4_EN_PAGE_SIZE);
cancel_delayed_work(&priv->stats_task);
+ cancel_delayed_work(&priv->service_task);
/* flush any pending task for this netdev */
flush_workqueue(mdev->workqueue);
@@ -1503,7 +2125,7 @@ static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu)
* the port */
en_dbg(DRV, priv, "Change MTU called with card down!?\n");
} else {
- mlx4_en_stop_port(dev);
+ mlx4_en_stop_port(dev, 1);
err = mlx4_en_start_port(dev);
if (err) {
en_err(priv, "Failed restarting port:%d\n",
@@ -1516,6 +2138,85 @@ static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu)
return 0;
}
+static int mlx4_en_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
+{
+ struct mlx4_en_priv *priv = netdev_priv(dev);
+ struct mlx4_en_dev *mdev = priv->mdev;
+ struct hwtstamp_config config;
+
+ if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
+ return -EFAULT;
+
+ /* reserved for future extensions */
+ if (config.flags)
+ return -EINVAL;
+
+ /* device doesn't support time stamping */
+ if (!(mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS))
+ return -EINVAL;
+
+ /* TX HW timestamp */
+ switch (config.tx_type) {
+ case HWTSTAMP_TX_OFF:
+ case HWTSTAMP_TX_ON:
+ break;
+ default:
+ return -ERANGE;
+ }
+
+ /* RX HW timestamp */
+ switch (config.rx_filter) {
+ case HWTSTAMP_FILTER_NONE:
+ break;
+ case HWTSTAMP_FILTER_ALL:
+ case HWTSTAMP_FILTER_SOME:
+ case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
+ case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
+ case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
+ case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
+ case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
+ case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
+ case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
+ case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
+ case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
+ case HWTSTAMP_FILTER_PTP_V2_EVENT:
+ case HWTSTAMP_FILTER_PTP_V2_SYNC:
+ case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
+ config.rx_filter = HWTSTAMP_FILTER_ALL;
+ break;
+ default:
+ return -ERANGE;
+ }
+
+ if (mlx4_en_timestamp_config(dev, config.tx_type, config.rx_filter)) {
+ config.tx_type = HWTSTAMP_TX_OFF;
+ config.rx_filter = HWTSTAMP_FILTER_NONE;
+ }
+
+ return copy_to_user(ifr->ifr_data, &config,
+ sizeof(config)) ? -EFAULT : 0;
+}
+
+static int mlx4_en_hwtstamp_get(struct net_device *dev, struct ifreq *ifr)
+{
+ struct mlx4_en_priv *priv = netdev_priv(dev);
+
+ return copy_to_user(ifr->ifr_data, &priv->hwtstamp_config,
+ sizeof(priv->hwtstamp_config)) ? -EFAULT : 0;
+}
+
+static int mlx4_en_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
+{
+ switch (cmd) {
+ case SIOCSHWTSTAMP:
+ return mlx4_en_hwtstamp_set(dev, ifr);
+ case SIOCGHWTSTAMP:
+ return mlx4_en_hwtstamp_get(dev, ifr);
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
static int mlx4_en_set_features(struct net_device *netdev,
netdev_features_t features)
{
@@ -1527,23 +2228,203 @@ static int mlx4_en_set_features(struct net_device *netdev,
priv->ctrl_flags &=
cpu_to_be32(~MLX4_WQE_CTRL_FORCE_LOOPBACK);
+ mlx4_en_update_loopback_state(netdev, features);
+
return 0;
}
+static int mlx4_en_set_vf_mac(struct net_device *dev, int queue, u8 *mac)
+{
+ struct mlx4_en_priv *en_priv = netdev_priv(dev);
+ struct mlx4_en_dev *mdev = en_priv->mdev;
+ u64 mac_u64 = mlx4_mac_to_u64(mac);
+
+ if (!is_valid_ether_addr(mac))
+ return -EINVAL;
+
+ return mlx4_set_vf_mac(mdev->dev, en_priv->port, queue, mac_u64);
+}
+
+static int mlx4_en_set_vf_vlan(struct net_device *dev, int vf, u16 vlan, u8 qos)
+{
+ struct mlx4_en_priv *en_priv = netdev_priv(dev);
+ struct mlx4_en_dev *mdev = en_priv->mdev;
+
+ return mlx4_set_vf_vlan(mdev->dev, en_priv->port, vf, vlan, qos);
+}
+
+static int mlx4_en_set_vf_spoofchk(struct net_device *dev, int vf, bool setting)
+{
+ struct mlx4_en_priv *en_priv = netdev_priv(dev);
+ struct mlx4_en_dev *mdev = en_priv->mdev;
+
+ return mlx4_set_vf_spoofchk(mdev->dev, en_priv->port, vf, setting);
+}
+
+static int mlx4_en_get_vf_config(struct net_device *dev, int vf, struct ifla_vf_info *ivf)
+{
+ struct mlx4_en_priv *en_priv = netdev_priv(dev);
+ struct mlx4_en_dev *mdev = en_priv->mdev;
+
+ return mlx4_get_vf_config(mdev->dev, en_priv->port, vf, ivf);
+}
+
+static int mlx4_en_set_vf_link_state(struct net_device *dev, int vf, int link_state)
+{
+ struct mlx4_en_priv *en_priv = netdev_priv(dev);
+ struct mlx4_en_dev *mdev = en_priv->mdev;
+
+ return mlx4_set_vf_link_state(mdev->dev, en_priv->port, vf, link_state);
+}
+
+#define PORT_ID_BYTE_LEN 8
+static int mlx4_en_get_phys_port_id(struct net_device *dev,
+ struct netdev_phys_port_id *ppid)
+{
+ struct mlx4_en_priv *priv = netdev_priv(dev);
+ struct mlx4_dev *mdev = priv->mdev->dev;
+ int i;
+ u64 phys_port_id = mdev->caps.phys_port_id[priv->port];
+
+ if (!phys_port_id)
+ return -EOPNOTSUPP;
+
+ ppid->id_len = sizeof(phys_port_id);
+ for (i = PORT_ID_BYTE_LEN - 1; i >= 0; --i) {
+ ppid->id[i] = phys_port_id & 0xff;
+ phys_port_id >>= 8;
+ }
+ return 0;
+}
+
+#ifdef CONFIG_MLX4_EN_VXLAN
+static void mlx4_en_add_vxlan_offloads(struct work_struct *work)
+{
+ int ret;
+ struct mlx4_en_priv *priv = container_of(work, struct mlx4_en_priv,
+ vxlan_add_task);
+
+ ret = mlx4_config_vxlan_port(priv->mdev->dev, priv->vxlan_port);
+ if (ret)
+ goto out;
+
+ ret = mlx4_SET_PORT_VXLAN(priv->mdev->dev, priv->port,
+ VXLAN_STEER_BY_OUTER_MAC, 1);
+out:
+ if (ret)
+ en_err(priv, "failed setting L2 tunnel configuration ret %d\n", ret);
+}
+
+static void mlx4_en_del_vxlan_offloads(struct work_struct *work)
+{
+ int ret;
+ struct mlx4_en_priv *priv = container_of(work, struct mlx4_en_priv,
+ vxlan_del_task);
+
+ ret = mlx4_SET_PORT_VXLAN(priv->mdev->dev, priv->port,
+ VXLAN_STEER_BY_OUTER_MAC, 0);
+ if (ret)
+ en_err(priv, "failed setting L2 tunnel configuration ret %d\n", ret);
+
+ priv->vxlan_port = 0;
+}
+
+static void mlx4_en_add_vxlan_port(struct net_device *dev,
+ sa_family_t sa_family, __be16 port)
+{
+ struct mlx4_en_priv *priv = netdev_priv(dev);
+ __be16 current_port;
+
+ if (priv->mdev->dev->caps.tunnel_offload_mode != MLX4_TUNNEL_OFFLOAD_MODE_VXLAN)
+ return;
+
+ if (sa_family == AF_INET6)
+ return;
+
+ current_port = priv->vxlan_port;
+ if (current_port && current_port != port) {
+ en_warn(priv, "vxlan port %d configured, can't add port %d\n",
+ ntohs(current_port), ntohs(port));
+ return;
+ }
+
+ priv->vxlan_port = port;
+ queue_work(priv->mdev->workqueue, &priv->vxlan_add_task);
+}
+
+static void mlx4_en_del_vxlan_port(struct net_device *dev,
+ sa_family_t sa_family, __be16 port)
+{
+ struct mlx4_en_priv *priv = netdev_priv(dev);
+ __be16 current_port;
+
+ if (priv->mdev->dev->caps.tunnel_offload_mode != MLX4_TUNNEL_OFFLOAD_MODE_VXLAN)
+ return;
+
+ if (sa_family == AF_INET6)
+ return;
+
+ current_port = priv->vxlan_port;
+ if (current_port != port) {
+ en_dbg(DRV, priv, "vxlan port %d isn't configured, ignoring\n", ntohs(port));
+ return;
+ }
+
+ queue_work(priv->mdev->workqueue, &priv->vxlan_del_task);
+}
+#endif
+
static const struct net_device_ops mlx4_netdev_ops = {
.ndo_open = mlx4_en_open,
.ndo_stop = mlx4_en_close,
.ndo_start_xmit = mlx4_en_xmit,
.ndo_select_queue = mlx4_en_select_queue,
.ndo_get_stats = mlx4_en_get_stats,
- .ndo_set_rx_mode = mlx4_en_set_multicast,
+ .ndo_set_rx_mode = mlx4_en_set_rx_mode,
+ .ndo_set_mac_address = mlx4_en_set_mac,
+ .ndo_validate_addr = eth_validate_addr,
+ .ndo_change_mtu = mlx4_en_change_mtu,
+ .ndo_do_ioctl = mlx4_en_ioctl,
+ .ndo_tx_timeout = mlx4_en_tx_timeout,
+ .ndo_vlan_rx_add_vid = mlx4_en_vlan_rx_add_vid,
+ .ndo_vlan_rx_kill_vid = mlx4_en_vlan_rx_kill_vid,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+ .ndo_poll_controller = mlx4_en_netpoll,
+#endif
+ .ndo_set_features = mlx4_en_set_features,
+ .ndo_setup_tc = mlx4_en_setup_tc,
+#ifdef CONFIG_RFS_ACCEL
+ .ndo_rx_flow_steer = mlx4_en_filter_rfs,
+#endif
+#ifdef CONFIG_NET_RX_BUSY_POLL
+ .ndo_busy_poll = mlx4_en_low_latency_recv,
+#endif
+ .ndo_get_phys_port_id = mlx4_en_get_phys_port_id,
+#ifdef CONFIG_MLX4_EN_VXLAN
+ .ndo_add_vxlan_port = mlx4_en_add_vxlan_port,
+ .ndo_del_vxlan_port = mlx4_en_del_vxlan_port,
+#endif
+};
+
+static const struct net_device_ops mlx4_netdev_ops_master = {
+ .ndo_open = mlx4_en_open,
+ .ndo_stop = mlx4_en_close,
+ .ndo_start_xmit = mlx4_en_xmit,
+ .ndo_select_queue = mlx4_en_select_queue,
+ .ndo_get_stats = mlx4_en_get_stats,
+ .ndo_set_rx_mode = mlx4_en_set_rx_mode,
.ndo_set_mac_address = mlx4_en_set_mac,
.ndo_validate_addr = eth_validate_addr,
.ndo_change_mtu = mlx4_en_change_mtu,
.ndo_tx_timeout = mlx4_en_tx_timeout,
.ndo_vlan_rx_add_vid = mlx4_en_vlan_rx_add_vid,
.ndo_vlan_rx_kill_vid = mlx4_en_vlan_rx_kill_vid,
+ .ndo_set_vf_mac = mlx4_en_set_vf_mac,
+ .ndo_set_vf_vlan = mlx4_en_set_vf_vlan,
+ .ndo_set_vf_spoofchk = mlx4_en_set_vf_spoofchk,
+ .ndo_set_vf_link_state = mlx4_en_set_vf_link_state,
+ .ndo_get_vf_config = mlx4_en_get_vf_config,
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_poll_controller = mlx4_en_netpoll,
#endif
@@ -1552,6 +2433,7 @@ static const struct net_device_ops mlx4_netdev_ops = {
#ifdef CONFIG_RFS_ACCEL
.ndo_rx_flow_steer = mlx4_en_filter_rfs,
#endif
+ .ndo_get_phys_port_id = mlx4_en_get_phys_port_id,
};
int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
@@ -1561,6 +2443,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
struct mlx4_en_priv *priv;
int i;
int err;
+ u64 mac_u64;
dev = alloc_etherdev_mqs(sizeof(struct mlx4_en_priv),
MAX_TX_RINGS, MAX_RX_RINGS);
@@ -1571,7 +2454,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
netif_set_real_num_rx_queues(dev, prof->rx_ring_num);
SET_NETDEV_DEV(dev, &mdev->dev->pdev->dev);
- dev->dev_id = port - 1;
+ dev->dev_port = port - 1;
/*
* Initialize driver private data
@@ -1590,14 +2473,15 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
MLX4_WQE_CTRL_SOLICITED);
priv->num_tx_rings_p_up = mdev->profile.num_tx_rings_p_up;
priv->tx_ring_num = prof->tx_ring_num;
+ priv->tx_work_limit = MLX4_EN_DEFAULT_TX_WORK;
- priv->tx_ring = kzalloc(sizeof(struct mlx4_en_tx_ring) * MAX_TX_RINGS,
+ priv->tx_ring = kzalloc(sizeof(struct mlx4_en_tx_ring *) * MAX_TX_RINGS,
GFP_KERNEL);
if (!priv->tx_ring) {
err = -ENOMEM;
goto out;
}
- priv->tx_cq = kzalloc(sizeof(struct mlx4_en_cq) * MAX_RX_RINGS,
+ priv->tx_cq = kzalloc(sizeof(struct mlx4_en_cq *) * MAX_TX_RINGS,
GFP_KERNEL);
if (!priv->tx_cq) {
err = -ENOMEM;
@@ -1608,32 +2492,67 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
priv->mac_index = -1;
priv->msg_enable = MLX4_EN_MSG_LEVEL;
spin_lock_init(&priv->stats_lock);
- INIT_WORK(&priv->mcast_task, mlx4_en_do_set_multicast);
- INIT_WORK(&priv->mac_task, mlx4_en_do_set_mac);
+ INIT_WORK(&priv->rx_mode_task, mlx4_en_do_set_rx_mode);
INIT_WORK(&priv->watchdog_task, mlx4_en_restart);
INIT_WORK(&priv->linkstate_task, mlx4_en_linkstate);
INIT_DELAYED_WORK(&priv->stats_task, mlx4_en_do_get_stats);
+ INIT_DELAYED_WORK(&priv->service_task, mlx4_en_service_task);
+#ifdef CONFIG_MLX4_EN_VXLAN
+ INIT_WORK(&priv->vxlan_add_task, mlx4_en_add_vxlan_offloads);
+ INIT_WORK(&priv->vxlan_del_task, mlx4_en_del_vxlan_offloads);
+#endif
#ifdef CONFIG_MLX4_EN_DCB
- if (!mlx4_is_slave(priv->mdev->dev))
- dev->dcbnl_ops = &mlx4_en_dcbnl_ops;
+ if (!mlx4_is_slave(priv->mdev->dev)) {
+ if (mdev->dev->caps.flags & MLX4_DEV_CAP_FLAG_SET_ETH_SCHED) {
+ dev->dcbnl_ops = &mlx4_en_dcbnl_ops;
+ } else {
+ en_info(priv, "enabling only PFC DCB ops\n");
+ dev->dcbnl_ops = &mlx4_en_dcbnl_pfc_ops;
+ }
+ }
#endif
+ for (i = 0; i < MLX4_EN_MAC_HASH_SIZE; ++i)
+ INIT_HLIST_HEAD(&priv->mac_hash[i]);
+
/* Query for default mac and max mtu */
priv->max_mtu = mdev->dev->caps.eth_mtu_cap[priv->port];
- priv->mac = mdev->dev->caps.def_mac[priv->port];
- if (ILLEGAL_MAC(priv->mac)) {
- en_err(priv, "Port: %d, invalid mac burned: 0x%llx, quiting\n",
- priv->port, priv->mac);
- err = -EINVAL;
- goto out;
+
+ /* Set default MAC */
+ dev->addr_len = ETH_ALEN;
+ mlx4_en_u64_to_mac(dev->dev_addr, mdev->dev->caps.def_mac[priv->port]);
+ if (!is_valid_ether_addr(dev->dev_addr)) {
+ if (mlx4_is_slave(priv->mdev->dev)) {
+ eth_hw_addr_random(dev);
+ en_warn(priv, "Assigned random MAC address %pM\n", dev->dev_addr);
+ mac_u64 = mlx4_mac_to_u64(dev->dev_addr);
+ mdev->dev->caps.def_mac[priv->port] = mac_u64;
+ } else {
+ en_err(priv, "Port: %d, invalid mac burned: %pM, quiting\n",
+ priv->port, dev->dev_addr);
+ err = -EINVAL;
+ goto out;
+ }
}
+ memcpy(priv->prev_mac, dev->dev_addr, sizeof(priv->prev_mac));
+
priv->stride = roundup_pow_of_two(sizeof(struct mlx4_en_rx_desc) +
DS_SIZE * MLX4_EN_MAX_RX_FRAGS);
err = mlx4_en_alloc_resources(priv);
if (err)
goto out;
+#ifdef CONFIG_RFS_ACCEL
+ INIT_LIST_HEAD(&priv->filters);
+ spin_lock_init(&priv->filters_lock);
+#endif
+
+ /* Initialize time stamping config */
+ priv->hwtstamp_config.flags = 0;
+ priv->hwtstamp_config.tx_type = HWTSTAMP_TX_OFF;
+ priv->hwtstamp_config.rx_filter = HWTSTAMP_FILTER_NONE;
+
/* Allocate page for receive rings */
err = mlx4_alloc_hwq_res(mdev->dev, &priv->res,
MLX4_EN_PAGE_SIZE, MLX4_EN_PAGE_SIZE);
@@ -1646,19 +2565,15 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
/*
* Initialize netdev entry points
*/
- dev->netdev_ops = &mlx4_netdev_ops;
+ if (mlx4_is_master(priv->mdev->dev))
+ dev->netdev_ops = &mlx4_netdev_ops_master;
+ else
+ dev->netdev_ops = &mlx4_netdev_ops;
dev->watchdog_timeo = MLX4_EN_WATCHDOG_TIMEOUT;
netif_set_real_num_tx_queues(dev, priv->tx_ring_num);
netif_set_real_num_rx_queues(dev, priv->rx_ring_num);
- SET_ETHTOOL_OPS(dev, &mlx4_en_ethtool_ops);
-
- /* Set defualt MAC */
- dev->addr_len = ETH_ALEN;
- for (i = 0; i < ETH_ALEN; i++) {
- dev->dev_addr[ETH_ALEN - 1 - i] = (u8) (priv->mac >> (8 * i));
- dev->perm_addr[ETH_ALEN - 1 - i] = (u8) (priv->mac >> (8 * i));
- }
+ dev->ethtool_ops = &mlx4_en_ethtool_ops;
/*
* Set driver features
@@ -1671,17 +2586,29 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
dev->hw_features |= NETIF_F_RXCSUM | NETIF_F_RXHASH;
dev->features = dev->hw_features | NETIF_F_HIGHDMA |
- NETIF_F_HW_VLAN_TX | NETIF_F_HW_VLAN_RX |
- NETIF_F_HW_VLAN_FILTER;
+ NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX |
+ NETIF_F_HW_VLAN_CTAG_FILTER;
dev->hw_features |= NETIF_F_LOOPBACK;
if (mdev->dev->caps.steering_mode ==
MLX4_STEERING_MODE_DEVICE_MANAGED)
dev->hw_features |= NETIF_F_NTUPLE;
+ 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_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);
+ mlx4_en_set_default_moderation(priv);
+
err = register_netdev(dev);
if (err) {
en_err(priv, "Netdev registration failed for port %d\n", port);
@@ -1692,6 +2619,8 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
en_warn(priv, "Using %d TX rings\n", prof->tx_ring_num);
en_warn(priv, "Using %d RX rings\n", prof->rx_ring_num);
+ mlx4_en_update_loopback_state(priv->dev, priv->dev->features);
+
/* Configure port */
mlx4_en_calc_rx_buf(dev);
err = mlx4_SET_PORT_general(mdev->dev, priv->port,
@@ -1699,11 +2628,20 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
prof->tx_pause, prof->tx_ppp,
prof->rx_pause, prof->rx_ppp);
if (err) {
- en_err(priv, "Failed setting port general configurations "
- "for port %d, with error %d\n", priv->port, err);
+ en_err(priv, "Failed setting port general configurations for port %d, with error %d\n",
+ priv->port, err);
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, 1);
+ 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);
@@ -1711,8 +2649,12 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
en_err(priv, "Failed Initializing port\n");
goto out;
}
- mlx4_en_set_default_moderation(priv);
queue_delayed_work(mdev->workqueue, &priv->stats_task, STATS_DELAY);
+
+ if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS)
+ queue_delayed_work(mdev->workqueue, &priv->service_task,
+ SERVICE_TASK_DELAY);
+
return 0;
out:
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-11 11:02:21 +0000