1 files changed, 426 insertions, 34 deletions

diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index 2bac6be8f6a0..550843e2164b 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -10,6 +10,7 @@
 #include <linux/filter.h>
 #include <linux/mm.h>
 #include <linux/pci.h>
+#include <linux/export.h>
 
 #include <net/checksum.h>
 #include <net/ip6_checksum.h>
@@ -47,6 +48,15 @@ static const struct file_operations mana_dbg_q_fops = {
 	.read   = mana_dbg_q_read,
 };
 
+static bool mana_en_need_log(struct mana_port_context *apc, int err)
+{
+	if (apc && apc->ac && apc->ac->gdma_dev &&
+	    apc->ac->gdma_dev->gdma_context)
+		return mana_need_log(apc->ac->gdma_dev->gdma_context, err);
+	else
+		return true;
+}
+
 /* Microsoft Azure Network Adapter (MANA) functions */
 
 static int mana_open(struct net_device *ndev)
@@ -251,10 +261,10 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	struct netdev_queue *net_txq;
 	struct mana_stats_tx *tx_stats;
 	struct gdma_queue *gdma_sq;
+	int err, len, num_gso_seg;
 	unsigned int csum_type;
 	struct mana_txq *txq;
 	struct mana_cq *cq;
-	int err, len;
 
 	if (unlikely(!apc->port_is_up))
 		goto tx_drop;
@@ -407,6 +417,7 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	skb_queue_tail(&txq->pending_skbs, skb);
 
 	len = skb->len;
+	num_gso_seg = skb_is_gso(skb) ? skb_shinfo(skb)->gso_segs : 1;
 	net_txq = netdev_get_tx_queue(ndev, txq_idx);
 
 	err = mana_gd_post_work_request(gdma_sq, &pkg.wqe_req,
@@ -431,10 +442,13 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	/* skb may be freed after mana_gd_post_work_request. Do not use it. */
 	skb = NULL;
 
+	/* Populated the packet and bytes counters based on post GSO packet
+	 * calculations
+	 */
 	tx_stats = &txq->stats;
 	u64_stats_update_begin(&tx_stats->syncp);
-	tx_stats->packets++;
-	tx_stats->bytes += len;
+	tx_stats->packets += num_gso_seg;
+	tx_stats->bytes += len + ((num_gso_seg - 1) * gso_hs);
 	u64_stats_update_end(&tx_stats->syncp);
 
 tx_busy:
@@ -719,6 +733,78 @@ out:
 	return err;
 }
 
+static int mana_shaper_set(struct net_shaper_binding *binding,
+			   const struct net_shaper *shaper,
+			   struct netlink_ext_ack *extack)
+{
+	struct mana_port_context *apc = netdev_priv(binding->netdev);
+	u32 old_speed, rate;
+	int err;
+
+	if (shaper->handle.scope != NET_SHAPER_SCOPE_NETDEV) {
+		NL_SET_ERR_MSG_MOD(extack, "net shaper scope should be netdev");
+		return -EINVAL;
+	}
+
+	if (apc->handle.id && shaper->handle.id != apc->handle.id) {
+		NL_SET_ERR_MSG_MOD(extack, "Cannot create multiple shapers");
+		return -EOPNOTSUPP;
+	}
+
+	if (!shaper->bw_max || (shaper->bw_max % 100000000)) {
+		NL_SET_ERR_MSG_MOD(extack, "Please use multiples of 100Mbps for bandwidth");
+		return -EINVAL;
+	}
+
+	rate = div_u64(shaper->bw_max, 1000); /* Convert bps to Kbps */
+	rate = div_u64(rate, 1000);	      /* Convert Kbps to Mbps */
+
+	/* Get current speed */
+	err = mana_query_link_cfg(apc);
+	old_speed = (err) ? SPEED_UNKNOWN : apc->speed;
+
+	if (!err) {
+		err = mana_set_bw_clamp(apc, rate, TRI_STATE_TRUE);
+		apc->speed = (err) ? old_speed : rate;
+		apc->handle = (err) ? apc->handle : shaper->handle;
+	}
+
+	return err;
+}
+
+static int mana_shaper_del(struct net_shaper_binding *binding,
+			   const struct net_shaper_handle *handle,
+			   struct netlink_ext_ack *extack)
+{
+	struct mana_port_context *apc = netdev_priv(binding->netdev);
+	int err;
+
+	err = mana_set_bw_clamp(apc, 0, TRI_STATE_FALSE);
+
+	if (!err) {
+		/* Reset mana port context parameters */
+		apc->handle.id = 0;
+		apc->handle.scope = NET_SHAPER_SCOPE_UNSPEC;
+		apc->speed = 0;
+	}
+
+	return err;
+}
+
+static void mana_shaper_cap(struct net_shaper_binding *binding,
+			    enum net_shaper_scope scope,
+			    unsigned long *flags)
+{
+	*flags = BIT(NET_SHAPER_A_CAPS_SUPPORT_BW_MAX) |
+		 BIT(NET_SHAPER_A_CAPS_SUPPORT_METRIC_BPS);
+}
+
+static const struct net_shaper_ops mana_shaper_ops = {
+	.set = mana_shaper_set,
+	.delete = mana_shaper_del,
+	.capabilities = mana_shaper_cap,
+};
+
 static const struct net_device_ops mana_devops = {
 	.ndo_open		= mana_open,
 	.ndo_stop		= mana_close,
@@ -729,6 +815,7 @@ static const struct net_device_ops mana_devops = {
 	.ndo_bpf		= mana_bpf,
 	.ndo_xdp_xmit		= mana_xdp_xmit,
 	.ndo_change_mtu		= mana_change_mtu,
+	.net_shaper_ops         = &mana_shaper_ops,
 };
 
 static void mana_cleanup_port_context(struct mana_port_context *apc)
@@ -774,8 +861,13 @@ static int mana_send_request(struct mana_context *ac, void *in_buf,
 	err = mana_gd_send_request(gc, in_len, in_buf, out_len,
 				   out_buf);
 	if (err || resp->status) {
-		dev_err(dev, "Failed to send mana message: %d, 0x%x\n",
-			err, resp->status);
+		if (err == -EOPNOTSUPP)
+			return err;
+
+		if (req->req.msg_type != MANA_QUERY_PHY_STAT &&
+		    mana_need_log(gc, err))
+			dev_err(dev, "Failed to send mana message: %d, 0x%x\n",
+				err, resp->status);
 		return err ? err : -EPROTO;
 	}
 
@@ -850,8 +942,10 @@ static void mana_pf_deregister_hw_vport(struct mana_port_context *apc)
 	err = mana_send_request(apc->ac, &req, sizeof(req), &resp,
 				sizeof(resp));
 	if (err) {
-		netdev_err(apc->ndev, "Failed to unregister hw vPort: %d\n",
-			   err);
+		if (mana_en_need_log(apc, err))
+			netdev_err(apc->ndev, "Failed to unregister hw vPort: %d\n",
+				   err);
+
 		return;
 	}
 
@@ -906,8 +1000,10 @@ static void mana_pf_deregister_filter(struct mana_port_context *apc)
 	err = mana_send_request(apc->ac, &req, sizeof(req), &resp,
 				sizeof(resp));
 	if (err) {
-		netdev_err(apc->ndev, "Failed to unregister filter: %d\n",
-			   err);
+		if (mana_en_need_log(apc, err))
+			netdev_err(apc->ndev, "Failed to unregister filter: %d\n",
+				   err);
+
 		return;
 	}
 
@@ -921,7 +1017,7 @@ static void mana_pf_deregister_filter(struct mana_port_context *apc)
 
 static int mana_query_device_cfg(struct mana_context *ac, u32 proto_major_ver,
 				 u32 proto_minor_ver, u32 proto_micro_ver,
-				 u16 *max_num_vports)
+				 u16 *max_num_vports, u8 *bm_hostmode)
 {
 	struct gdma_context *gc = ac->gdma_dev->gdma_context;
 	struct mana_query_device_cfg_resp resp = {};
@@ -932,7 +1028,7 @@ static int mana_query_device_cfg(struct mana_context *ac, u32 proto_major_ver,
 	mana_gd_init_req_hdr(&req.hdr, MANA_QUERY_DEV_CONFIG,
 			     sizeof(req), sizeof(resp));
 
-	req.hdr.resp.msg_version = GDMA_MESSAGE_V2;
+	req.hdr.resp.msg_version = GDMA_MESSAGE_V3;
 
 	req.proto_major_ver = proto_major_ver;
 	req.proto_minor_ver = proto_minor_ver;
@@ -956,11 +1052,16 @@ static int mana_query_device_cfg(struct mana_context *ac, u32 proto_major_ver,
 
 	*max_num_vports = resp.max_num_vports;
 
-	if (resp.hdr.response.msg_version == GDMA_MESSAGE_V2)
+	if (resp.hdr.response.msg_version >= GDMA_MESSAGE_V2)
 		gc->adapter_mtu = resp.adapter_mtu;
 	else
 		gc->adapter_mtu = ETH_FRAME_LEN;
 
+	if (resp.hdr.response.msg_version >= GDMA_MESSAGE_V3)
+		*bm_hostmode = resp.bm_hostmode;
+	else
+		*bm_hostmode = 0;
+
 	debugfs_create_u16("adapter-MTU", 0400, gc->mana_pci_debugfs, &gc->adapter_mtu);
 
 	return 0;
@@ -1132,7 +1233,9 @@ static int mana_cfg_vport_steering(struct mana_port_context *apc,
 	err = mana_send_request(apc->ac, req, req_buf_size, &resp,
 				sizeof(resp));
 	if (err) {
-		netdev_err(ndev, "Failed to configure vPort RX: %d\n", err);
+		if (mana_en_need_log(apc, err))
+			netdev_err(ndev, "Failed to configure vPort RX: %d\n", err);
+
 		goto out;
 	}
 
@@ -1156,6 +1259,95 @@ out:
 	return err;
 }
 
+int mana_query_link_cfg(struct mana_port_context *apc)
+{
+	struct net_device *ndev = apc->ndev;
+	struct mana_query_link_config_resp resp = {};
+	struct mana_query_link_config_req req = {};
+	int err;
+
+	mana_gd_init_req_hdr(&req.hdr, MANA_QUERY_LINK_CONFIG,
+			     sizeof(req), sizeof(resp));
+
+	req.vport = apc->port_handle;
+	req.hdr.resp.msg_version = GDMA_MESSAGE_V2;
+
+	err = mana_send_request(apc->ac, &req, sizeof(req), &resp,
+				sizeof(resp));
+
+	if (err) {
+		if (err == -EOPNOTSUPP) {
+			netdev_info_once(ndev, "MANA_QUERY_LINK_CONFIG not supported\n");
+			return err;
+		}
+		netdev_err(ndev, "Failed to query link config: %d\n", err);
+		return err;
+	}
+
+	err = mana_verify_resp_hdr(&resp.hdr, MANA_QUERY_LINK_CONFIG,
+				   sizeof(resp));
+
+	if (err || resp.hdr.status) {
+		netdev_err(ndev, "Failed to query link config: %d, 0x%x\n", err,
+			   resp.hdr.status);
+		if (!err)
+			err = -EOPNOTSUPP;
+		return err;
+	}
+
+	if (resp.qos_unconfigured) {
+		err = -EINVAL;
+		return err;
+	}
+	apc->speed = resp.link_speed_mbps;
+	apc->max_speed = resp.qos_speed_mbps;
+	return 0;
+}
+
+int mana_set_bw_clamp(struct mana_port_context *apc, u32 speed,
+		      int enable_clamping)
+{
+	struct mana_set_bw_clamp_resp resp = {};
+	struct mana_set_bw_clamp_req req = {};
+	struct net_device *ndev = apc->ndev;
+	int err;
+
+	mana_gd_init_req_hdr(&req.hdr, MANA_SET_BW_CLAMP,
+			     sizeof(req), sizeof(resp));
+	req.vport = apc->port_handle;
+	req.link_speed_mbps = speed;
+	req.enable_clamping = enable_clamping;
+
+	err = mana_send_request(apc->ac, &req, sizeof(req), &resp,
+				sizeof(resp));
+
+	if (err) {
+		if (err == -EOPNOTSUPP) {
+			netdev_info_once(ndev, "MANA_SET_BW_CLAMP not supported\n");
+			return err;
+		}
+		netdev_err(ndev, "Failed to set bandwidth clamp for speed %u, err = %d",
+			   speed, err);
+		return err;
+	}
+
+	err = mana_verify_resp_hdr(&resp.hdr, MANA_SET_BW_CLAMP,
+				   sizeof(resp));
+
+	if (err || resp.hdr.status) {
+		netdev_err(ndev, "Failed to set bandwidth clamp: %d, 0x%x\n", err,
+			   resp.hdr.status);
+		if (!err)
+			err = -EOPNOTSUPP;
+		return err;
+	}
+
+	if (resp.qos_unconfigured)
+		netdev_info(ndev, "QoS is unconfigured\n");
+
+	return 0;
+}
+
 int mana_create_wq_obj(struct mana_port_context *apc,
 		       mana_handle_t vport,
 		       u32 wq_type, struct mana_obj_spec *wq_spec,
@@ -1227,7 +1419,9 @@ void mana_destroy_wq_obj(struct mana_port_context *apc, u32 wq_type,
 	err = mana_send_request(apc->ac, &req, sizeof(req), &resp,
 				sizeof(resp));
 	if (err) {
-		netdev_err(ndev, "Failed to destroy WQ object: %d\n", err);
+		if (mana_en_need_log(apc, err))
+			netdev_err(ndev, "Failed to destroy WQ object: %d\n", err);
+
 		return;
 	}
 
@@ -1906,8 +2100,10 @@ static void mana_destroy_txq(struct mana_port_context *apc)
 		napi = &apc->tx_qp[i].tx_cq.napi;
 		if (apc->tx_qp[i].txq.napi_initialized) {
 			napi_synchronize(napi);
-			napi_disable(napi);
-			netif_napi_del(napi);
+			netdev_lock_ops_to_full(napi->dev);
+			napi_disable_locked(napi);
+			netif_napi_del_locked(napi);
+			netdev_unlock_full_to_ops(napi->dev);
 			apc->tx_qp[i].txq.napi_initialized = false;
 		}
 		mana_destroy_wq_obj(apc, GDMA_SQ, apc->tx_qp[i].tx_object);
@@ -2059,8 +2255,11 @@ static int mana_create_txq(struct mana_port_context *apc,
 
 		mana_create_txq_debugfs(apc, i);
 
-		netif_napi_add_tx(net, &cq->napi, mana_poll);
-		napi_enable(&cq->napi);
+		set_bit(NAPI_STATE_NO_BUSY_POLL, &cq->napi.state);
+		netdev_lock_ops_to_full(net);
+		netif_napi_add_locked(net, &cq->napi, mana_poll);
+		napi_enable_locked(&cq->napi);
+		netdev_unlock_full_to_ops(net);
 		txq->napi_initialized = true;
 
 		mana_gd_ring_cq(cq->gdma_cq, SET_ARM_BIT);
@@ -2096,9 +2295,10 @@ static void mana_destroy_rxq(struct mana_port_context *apc,
 	if (napi_initialized) {
 		napi_synchronize(napi);
 
-		napi_disable(napi);
-
-		netif_napi_del(napi);
+		netdev_lock_ops_to_full(napi->dev);
+		napi_disable_locked(napi);
+		netif_napi_del_locked(napi);
+		netdev_unlock_full_to_ops(napi->dev);
 	}
 	xdp_rxq_info_unreg(&rxq->xdp_rxq);
 
@@ -2349,14 +2549,18 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc,
 
 	gc->cq_table[cq->gdma_id] = cq->gdma_cq;
 
-	netif_napi_add_weight(ndev, &cq->napi, mana_poll, 1);
+	netdev_lock_ops_to_full(ndev);
+	netif_napi_add_weight_locked(ndev, &cq->napi, mana_poll, 1);
+	netdev_unlock_full_to_ops(ndev);
 
 	WARN_ON(xdp_rxq_info_reg(&rxq->xdp_rxq, ndev, rxq_idx,
 				 cq->napi.napi_id));
 	WARN_ON(xdp_rxq_info_reg_mem_model(&rxq->xdp_rxq, MEM_TYPE_PAGE_POOL,
 					   rxq->page_pool));
 
-	napi_enable(&cq->napi);
+	netdev_lock_ops_to_full(ndev);
+	napi_enable_locked(&cq->napi);
+	netdev_unlock_full_to_ops(ndev);
 
 	mana_gd_ring_cq(cq->gdma_cq, SET_ARM_BIT);
 out:
@@ -2441,7 +2645,7 @@ static void mana_destroy_vport(struct mana_port_context *apc)
 	mana_destroy_txq(apc);
 	mana_uncfg_vport(apc);
 
-	if (gd->gdma_context->is_pf)
+	if (gd->gdma_context->is_pf && !apc->ac->bm_hostmode)
 		mana_pf_deregister_hw_vport(apc);
 }
 
@@ -2453,7 +2657,7 @@ static int mana_create_vport(struct mana_port_context *apc,
 
 	apc->default_rxobj = INVALID_MANA_HANDLE;
 
-	if (gd->gdma_context->is_pf) {
+	if (gd->gdma_context->is_pf && !apc->ac->bm_hostmode) {
 		err = mana_pf_register_hw_vport(apc);
 		if (err)
 			return err;
@@ -2606,6 +2810,88 @@ void mana_query_gf_stats(struct mana_port_context *apc)
 	apc->eth_stats.hc_tx_err_gdma = resp.tx_err_gdma;
 }
 
+void mana_query_phy_stats(struct mana_port_context *apc)
+{
+	struct mana_query_phy_stat_resp resp = {};
+	struct mana_query_phy_stat_req req = {};
+	struct net_device *ndev = apc->ndev;
+	int err;
+
+	mana_gd_init_req_hdr(&req.hdr, MANA_QUERY_PHY_STAT,
+			     sizeof(req), sizeof(resp));
+	err = mana_send_request(apc->ac, &req, sizeof(req), &resp,
+				sizeof(resp));
+	if (err)
+		return;
+
+	err = mana_verify_resp_hdr(&resp.hdr, MANA_QUERY_PHY_STAT,
+				   sizeof(resp));
+	if (err || resp.hdr.status) {
+		netdev_err(ndev,
+			   "Failed to query PHY stats: %d, resp:0x%x\n",
+				err, resp.hdr.status);
+		return;
+	}
+
+	/* Aggregate drop counters */
+	apc->phy_stats.rx_pkt_drop_phy = resp.rx_pkt_drop_phy;
+	apc->phy_stats.tx_pkt_drop_phy = resp.tx_pkt_drop_phy;
+
+	/* Per TC traffic Counters */
+	apc->phy_stats.rx_pkt_tc0_phy = resp.rx_pkt_tc0_phy;
+	apc->phy_stats.tx_pkt_tc0_phy = resp.tx_pkt_tc0_phy;
+	apc->phy_stats.rx_pkt_tc1_phy = resp.rx_pkt_tc1_phy;
+	apc->phy_stats.tx_pkt_tc1_phy = resp.tx_pkt_tc1_phy;
+	apc->phy_stats.rx_pkt_tc2_phy = resp.rx_pkt_tc2_phy;
+	apc->phy_stats.tx_pkt_tc2_phy = resp.tx_pkt_tc2_phy;
+	apc->phy_stats.rx_pkt_tc3_phy = resp.rx_pkt_tc3_phy;
+	apc->phy_stats.tx_pkt_tc3_phy = resp.tx_pkt_tc3_phy;
+	apc->phy_stats.rx_pkt_tc4_phy = resp.rx_pkt_tc4_phy;
+	apc->phy_stats.tx_pkt_tc4_phy = resp.tx_pkt_tc4_phy;
+	apc->phy_stats.rx_pkt_tc5_phy = resp.rx_pkt_tc5_phy;
+	apc->phy_stats.tx_pkt_tc5_phy = resp.tx_pkt_tc5_phy;
+	apc->phy_stats.rx_pkt_tc6_phy = resp.rx_pkt_tc6_phy;
+	apc->phy_stats.tx_pkt_tc6_phy = resp.tx_pkt_tc6_phy;
+	apc->phy_stats.rx_pkt_tc7_phy = resp.rx_pkt_tc7_phy;
+	apc->phy_stats.tx_pkt_tc7_phy = resp.tx_pkt_tc7_phy;
+
+	/* Per TC byte Counters */
+	apc->phy_stats.rx_byte_tc0_phy = resp.rx_byte_tc0_phy;
+	apc->phy_stats.tx_byte_tc0_phy = resp.tx_byte_tc0_phy;
+	apc->phy_stats.rx_byte_tc1_phy = resp.rx_byte_tc1_phy;
+	apc->phy_stats.tx_byte_tc1_phy = resp.tx_byte_tc1_phy;
+	apc->phy_stats.rx_byte_tc2_phy = resp.rx_byte_tc2_phy;
+	apc->phy_stats.tx_byte_tc2_phy = resp.tx_byte_tc2_phy;
+	apc->phy_stats.rx_byte_tc3_phy = resp.rx_byte_tc3_phy;
+	apc->phy_stats.tx_byte_tc3_phy = resp.tx_byte_tc3_phy;
+	apc->phy_stats.rx_byte_tc4_phy = resp.rx_byte_tc4_phy;
+	apc->phy_stats.tx_byte_tc4_phy = resp.tx_byte_tc4_phy;
+	apc->phy_stats.rx_byte_tc5_phy = resp.rx_byte_tc5_phy;
+	apc->phy_stats.tx_byte_tc5_phy = resp.tx_byte_tc5_phy;
+	apc->phy_stats.rx_byte_tc6_phy = resp.rx_byte_tc6_phy;
+	apc->phy_stats.tx_byte_tc6_phy = resp.tx_byte_tc6_phy;
+	apc->phy_stats.rx_byte_tc7_phy = resp.rx_byte_tc7_phy;
+	apc->phy_stats.tx_byte_tc7_phy = resp.tx_byte_tc7_phy;
+
+	/* Per TC pause Counters */
+	apc->phy_stats.rx_pause_tc0_phy = resp.rx_pause_tc0_phy;
+	apc->phy_stats.tx_pause_tc0_phy = resp.tx_pause_tc0_phy;
+	apc->phy_stats.rx_pause_tc1_phy = resp.rx_pause_tc1_phy;
+	apc->phy_stats.tx_pause_tc1_phy = resp.tx_pause_tc1_phy;
+	apc->phy_stats.rx_pause_tc2_phy = resp.rx_pause_tc2_phy;
+	apc->phy_stats.tx_pause_tc2_phy = resp.tx_pause_tc2_phy;
+	apc->phy_stats.rx_pause_tc3_phy = resp.rx_pause_tc3_phy;
+	apc->phy_stats.tx_pause_tc3_phy = resp.tx_pause_tc3_phy;
+	apc->phy_stats.rx_pause_tc4_phy = resp.rx_pause_tc4_phy;
+	apc->phy_stats.tx_pause_tc4_phy = resp.tx_pause_tc4_phy;
+	apc->phy_stats.rx_pause_tc5_phy = resp.rx_pause_tc5_phy;
+	apc->phy_stats.tx_pause_tc5_phy = resp.tx_pause_tc5_phy;
+	apc->phy_stats.rx_pause_tc6_phy = resp.rx_pause_tc6_phy;
+	apc->phy_stats.tx_pause_tc6_phy = resp.tx_pause_tc6_phy;
+	apc->phy_stats.rx_pause_tc7_phy = resp.rx_pause_tc7_phy;
+	apc->phy_stats.tx_pause_tc7_phy = resp.tx_pause_tc7_phy;
+}
+
 static int mana_init_port(struct net_device *ndev)
 {
 	struct mana_port_context *apc = netdev_priv(ndev);
@@ -2689,7 +2975,7 @@ int mana_alloc_queues(struct net_device *ndev)
 		goto destroy_vport;
 	}
 
-	if (gd->gdma_context->is_pf) {
+	if (gd->gdma_context->is_pf && !apc->ac->bm_hostmode) {
 		err = mana_pf_register_filter(apc);
 		if (err)
 			goto destroy_vport;
@@ -2751,7 +3037,7 @@ static int mana_dealloc_queues(struct net_device *ndev)
 
 	mana_chn_setxdp(apc, NULL);
 
-	if (gd->gdma_context->is_pf)
+	if (gd->gdma_context->is_pf && !apc->ac->bm_hostmode)
 		mana_pf_deregister_filter(apc);
 
 	/* No packet can be transmitted now since apc->port_is_up is false.
@@ -2800,11 +3086,10 @@ static int mana_dealloc_queues(struct net_device *ndev)
 
 	apc->rss_state = TRI_STATE_FALSE;
 	err = mana_config_rss(apc, TRI_STATE_FALSE, false, false);
-	if (err) {
+	if (err && mana_en_need_log(apc, err))
 		netdev_err(ndev, "Failed to disable vPort: %d\n", err);
-		return err;
-	}
 
+	/* Even in err case, still need to cleanup the vPort */
 	mana_destroy_vport(apc);
 
 	return 0;
@@ -2913,6 +3198,8 @@ static int mana_probe_port(struct mana_context *ac, int port_idx,
 		goto free_indir;
 	}
 
+	debugfs_create_u32("current_speed", 0400, apc->mana_port_debugfs, &apc->speed);
+
 	return 0;
 
 free_indir:
@@ -2945,7 +3232,7 @@ static void remove_adev(struct gdma_dev *gd)
 	gd->adev = NULL;
 }
 
-static int add_adev(struct gdma_dev *gd)
+static int add_adev(struct gdma_dev *gd, const char *name)
 {
 	struct auxiliary_device *adev;
 	struct mana_adev *madev;
@@ -2961,7 +3248,7 @@ static int add_adev(struct gdma_dev *gd)
 		goto idx_fail;
 	adev->id = ret;
 
-	adev->name = "rdma";
+	adev->name = name;
 	adev->dev.parent = gd->gdma_context->dev;
 	adev->dev.release = adev_release;
 	madev->mdev = gd;
@@ -2993,11 +3280,76 @@ idx_fail:
 	return ret;
 }
 
+static void mana_rdma_service_handle(struct work_struct *work)
+{
+	struct mana_service_work *serv_work =
+		container_of(work, struct mana_service_work, work);
+	struct gdma_dev *gd = serv_work->gdma_dev;
+	struct device *dev = gd->gdma_context->dev;
+	int ret;
+
+	if (READ_ONCE(gd->rdma_teardown))
+		goto out;
+
+	switch (serv_work->event) {
+	case GDMA_SERVICE_TYPE_RDMA_SUSPEND:
+		if (!gd->adev || gd->is_suspended)
+			break;
+
+		remove_adev(gd);
+		gd->is_suspended = true;
+		break;
+
+	case GDMA_SERVICE_TYPE_RDMA_RESUME:
+		if (!gd->is_suspended)
+			break;
+
+		ret = add_adev(gd, "rdma");
+		if (ret)
+			dev_err(dev, "Failed to add adev on resume: %d\n", ret);
+		else
+			gd->is_suspended = false;
+		break;
+
+	default:
+		dev_warn(dev, "unknown adev service event %u\n",
+			 serv_work->event);
+		break;
+	}
+
+out:
+	kfree(serv_work);
+}
+
+int mana_rdma_service_event(struct gdma_context *gc, enum gdma_service_type event)
+{
+	struct gdma_dev *gd = &gc->mana_ib;
+	struct mana_service_work *serv_work;
+
+	if (gd->dev_id.type != GDMA_DEVICE_MANA_IB) {
+		/* RDMA device is not detected on pci */
+		return 0;
+	}
+
+	serv_work = kzalloc(sizeof(*serv_work), GFP_ATOMIC);
+	if (!serv_work)
+		return -ENOMEM;
+
+	serv_work->event = event;
+	serv_work->gdma_dev = gd;
+
+	INIT_WORK(&serv_work->work, mana_rdma_service_handle);
+	queue_work(gc->service_wq, &serv_work->work);
+
+	return 0;
+}
+
 int mana_probe(struct gdma_dev *gd, bool resuming)
 {
 	struct gdma_context *gc = gd->gdma_context;
 	struct mana_context *ac = gd->driver_data;
 	struct device *dev = gc->dev;
+	u8 bm_hostmode = 0;
 	u16 num_ports = 0;
 	int err;
 	int i;
@@ -3026,10 +3378,12 @@ int mana_probe(struct gdma_dev *gd, bool resuming)
 	}
 
 	err = mana_query_device_cfg(ac, MANA_MAJOR_VERSION, MANA_MINOR_VERSION,
-				    MANA_MICRO_VERSION, &num_ports);
+				    MANA_MICRO_VERSION, &num_ports, &bm_hostmode);
 	if (err)
 		goto out;
 
+	ac->bm_hostmode = bm_hostmode;
+
 	if (!resuming) {
 		ac->num_ports = num_ports;
 	} else {
@@ -3077,7 +3431,7 @@ int mana_probe(struct gdma_dev *gd, bool resuming)
 		}
 	}
 
-	err = add_adev(gd);
+	err = add_adev(gd, "eth");
 out:
 	if (err) {
 		mana_remove(gd, false);
@@ -3151,6 +3505,44 @@ out:
 	dev_dbg(dev, "%s succeeded\n", __func__);
 }
 
+int mana_rdma_probe(struct gdma_dev *gd)
+{
+	int err = 0;
+
+	if (gd->dev_id.type != GDMA_DEVICE_MANA_IB) {
+		/* RDMA device is not detected on pci */
+		return err;
+	}
+
+	err = mana_gd_register_device(gd);
+	if (err)
+		return err;
+
+	err = add_adev(gd, "rdma");
+	if (err)
+		mana_gd_deregister_device(gd);
+
+	return err;
+}
+
+void mana_rdma_remove(struct gdma_dev *gd)
+{
+	struct gdma_context *gc = gd->gdma_context;
+
+	if (gd->dev_id.type != GDMA_DEVICE_MANA_IB) {
+		/* RDMA device is not detected on pci */
+		return;
+	}
+
+	WRITE_ONCE(gd->rdma_teardown, true);
+	flush_workqueue(gc->service_wq);
+
+	if (gd->adev)
+		remove_adev(gd);
+
+	mana_gd_deregister_device(gd);
+}
+
 struct net_device *mana_get_primary_netdev(struct mana_context *ac,
 					   u32 port_index,
 					   netdevice_tracker *tracker)