1 files changed, 741 insertions, 210 deletions

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 97f90edbc068..9cbce1faab26 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -66,6 +66,9 @@
 #include <linux/crash_dump.h>
 #include <net/udp_tunnel.h>
 #include <net/xfrm.h>
+#if IS_ENABLED(CONFIG_CHELSIO_TLS_DEVICE)
+#include <net/tls.h>
+#endif
 
 #include "cxgb4.h"
 #include "cxgb4_filter.h"
@@ -90,11 +93,6 @@
 
 char cxgb4_driver_name[] = KBUILD_MODNAME;
 
-#ifdef DRV_VERSION
-#undef DRV_VERSION
-#endif
-#define DRV_VERSION "2.0.0-ko"
-const char cxgb4_driver_version[] = DRV_VERSION;
 #define DRV_DESC "Chelsio T4/T5/T6 Network Driver"
 
 #define DFLT_MSG_ENABLE (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK | \
@@ -137,7 +135,6 @@ const char cxgb4_driver_version[] = DRV_VERSION;
 MODULE_DESCRIPTION(DRV_DESC);
 MODULE_AUTHOR("Chelsio Communications");
 MODULE_LICENSE("Dual BSD/GPL");
-MODULE_VERSION(DRV_VERSION);
 MODULE_DEVICE_TABLE(pci, cxgb4_pci_tbl);
 MODULE_FIRMWARE(FW4_FNAME);
 MODULE_FIRMWARE(FW5_FNAME);
@@ -186,6 +183,7 @@ static struct dentry *cxgb4_debugfs_root;
 
 LIST_HEAD(adapter_list);
 DEFINE_MUTEX(uld_mutex);
+LIST_HEAD(uld_list);
 
 static int cfg_queues(struct adapter *adap);
 
@@ -437,8 +435,8 @@ static int set_rxmode(struct net_device *dev, int mtu, bool sleep_ok)
 	__dev_uc_sync(dev, cxgb4_mac_sync, cxgb4_mac_unsync);
 	__dev_mc_sync(dev, cxgb4_mac_sync, cxgb4_mac_unsync);
 
-	return t4_set_rxmode(adapter, adapter->mbox, pi->viid, mtu,
-			     (dev->flags & IFF_PROMISC) ? 1 : 0,
+	return t4_set_rxmode(adapter, adapter->mbox, pi->viid, pi->viid_mirror,
+			     mtu, (dev->flags & IFF_PROMISC) ? 1 : 0,
 			     (dev->flags & IFF_ALLMULTI) ? 1 : 0, 1, -1,
 			     sleep_ok);
 }
@@ -451,7 +449,7 @@ static int set_rxmode(struct net_device *dev, int mtu, bool sleep_ok)
  *		   or -1
  *	@addr: the new MAC address value
  *	@persist: whether a new MAC allocation should be persistent
- *	@add_smt: if true also add the address to the HW SMT
+ *	@smt_idx: the destination to store the new SMT index.
  *
  *	Modifies an MPS filter and sets it to the new MAC address if
  *	@tcam_idx >= 0, or adds the MAC address to a new filter if
@@ -505,15 +503,16 @@ set_hash:
  */
 static int link_start(struct net_device *dev)
 {
-	int ret;
 	struct port_info *pi = netdev_priv(dev);
-	unsigned int mb = pi->adapter->pf;
+	unsigned int mb = pi->adapter->mbox;
+	int ret;
 
 	/*
 	 * We do not set address filters and promiscuity here, the stack does
 	 * that step explicitly.
 	 */
-	ret = t4_set_rxmode(pi->adapter, mb, pi->viid, dev->mtu, -1, -1, -1,
+	ret = t4_set_rxmode(pi->adapter, mb, pi->viid, pi->viid_mirror,
+			    dev->mtu, -1, -1, -1,
 			    !!(dev->features & NETIF_F_HW_VLAN_CTAG_RX), true);
 	if (ret == 0)
 		ret = cxgb4_update_mac_filt(pi, pi->viid, &pi->xact_addr_filt,
@@ -824,6 +823,31 @@ static void adap_config_hpfilter(struct adapter *adapter)
 			"HP filter region isn't supported by FW\n");
 }
 
+static int cxgb4_config_rss(const struct port_info *pi, u16 *rss,
+			    u16 rss_size, u16 viid)
+{
+	struct adapter *adap = pi->adapter;
+	int ret;
+
+	ret = t4_config_rss_range(adap, adap->mbox, viid, 0, rss_size, rss,
+				  rss_size);
+	if (ret)
+		return ret;
+
+	/* If Tunnel All Lookup isn't specified in the global RSS
+	 * Configuration, then we need to specify a default Ingress
+	 * Queue for any ingress packets which aren't hashed.  We'll
+	 * use our first ingress queue ...
+	 */
+	return t4_config_vi_rss(adap, adap->mbox, viid,
+				FW_RSS_VI_CONFIG_CMD_IP6FOURTUPEN_F |
+				FW_RSS_VI_CONFIG_CMD_IP6TWOTUPEN_F |
+				FW_RSS_VI_CONFIG_CMD_IP4FOURTUPEN_F |
+				FW_RSS_VI_CONFIG_CMD_IP4TWOTUPEN_F |
+				FW_RSS_VI_CONFIG_CMD_UDPEN_F,
+				rss[0]);
+}
+
 /**
  *	cxgb4_write_rss - write the RSS table for a given port
  *	@pi: the port
@@ -835,10 +859,10 @@ static void adap_config_hpfilter(struct adapter *adapter)
  */
 int cxgb4_write_rss(const struct port_info *pi, const u16 *queues)
 {
-	u16 *rss;
-	int i, err;
 	struct adapter *adapter = pi->adapter;
 	const struct sge_eth_rxq *rxq;
+	int i, err;
+	u16 *rss;
 
 	rxq = &adapter->sge.ethrxq[pi->first_qset];
 	rss = kmalloc_array(pi->rss_size, sizeof(u16), GFP_KERNEL);
@@ -849,21 +873,7 @@ int cxgb4_write_rss(const struct port_info *pi, const u16 *queues)
 	for (i = 0; i < pi->rss_size; i++, queues++)
 		rss[i] = rxq[*queues].rspq.abs_id;
 
-	err = t4_config_rss_range(adapter, adapter->pf, pi->viid, 0,
-				  pi->rss_size, rss, pi->rss_size);
-	/* If Tunnel All Lookup isn't specified in the global RSS
-	 * Configuration, then we need to specify a default Ingress
-	 * Queue for any ingress packets which aren't hashed.  We'll
-	 * use our first ingress queue ...
-	 */
-	if (!err)
-		err = t4_config_vi_rss(adapter, adapter->mbox, pi->viid,
-				       FW_RSS_VI_CONFIG_CMD_IP6FOURTUPEN_F |
-				       FW_RSS_VI_CONFIG_CMD_IP6TWOTUPEN_F |
-				       FW_RSS_VI_CONFIG_CMD_IP4FOURTUPEN_F |
-				       FW_RSS_VI_CONFIG_CMD_IP4TWOTUPEN_F |
-				       FW_RSS_VI_CONFIG_CMD_UDPEN_F,
-				       rss[0]);
+	err = cxgb4_config_rss(pi, rss, pi->rss_size, pi->viid);
 	kfree(rss);
 	return err;
 }
@@ -1166,6 +1176,7 @@ static u16 cxgb_select_queue(struct net_device *dev, struct sk_buff *skb,
 		txq = netdev_pick_tx(dev, skb, sb_dev);
 		if (xfrm_offload(skb) || is_ptp_enabled(skb, dev) ||
 		    skb->encapsulation ||
+		    cxgb4_is_ktls_skb(skb) ||
 		    (proto != IPPROTO_TCP && proto != IPPROTO_UDP))
 			txq = txq % pi->nqsets;
 
@@ -1261,15 +1272,15 @@ int cxgb4_set_rspq_intr_params(struct sge_rspq *q,
 
 static int cxgb_set_features(struct net_device *dev, netdev_features_t features)
 {
-	const struct port_info *pi = netdev_priv(dev);
 	netdev_features_t changed = dev->features ^ features;
+	const struct port_info *pi = netdev_priv(dev);
 	int err;
 
 	if (!(changed & NETIF_F_HW_VLAN_CTAG_RX))
 		return 0;
 
-	err = t4_set_rxmode(pi->adapter, pi->adapter->pf, pi->viid, -1,
-			    -1, -1, -1,
+	err = t4_set_rxmode(pi->adapter, pi->adapter->mbox, pi->viid,
+			    pi->viid_mirror, -1, -1, -1, -1,
 			    !!(features & NETIF_F_HW_VLAN_CTAG_RX), true);
 	if (unlikely(err))
 		dev->features = features ^ NETIF_F_HW_VLAN_CTAG_RX;
@@ -1287,6 +1298,292 @@ static int setup_debugfs(struct adapter *adap)
 	return 0;
 }
 
+static void cxgb4_port_mirror_free_rxq(struct adapter *adap,
+				       struct sge_eth_rxq *mirror_rxq)
+{
+	if ((adap->flags & CXGB4_FULL_INIT_DONE) &&
+	    !(adap->flags & CXGB4_SHUTTING_DOWN))
+		cxgb4_quiesce_rx(&mirror_rxq->rspq);
+
+	if (adap->flags & CXGB4_USING_MSIX) {
+		cxgb4_clear_msix_aff(mirror_rxq->msix->vec,
+				     mirror_rxq->msix->aff_mask);
+		free_irq(mirror_rxq->msix->vec, &mirror_rxq->rspq);
+		cxgb4_free_msix_idx_in_bmap(adap, mirror_rxq->msix->idx);
+	}
+
+	free_rspq_fl(adap, &mirror_rxq->rspq, &mirror_rxq->fl);
+}
+
+static int cxgb4_port_mirror_alloc_queues(struct net_device *dev)
+{
+	struct port_info *pi = netdev2pinfo(dev);
+	struct adapter *adap = netdev2adap(dev);
+	struct sge_eth_rxq *mirror_rxq;
+	struct sge *s = &adap->sge;
+	int ret = 0, msix = 0;
+	u16 i, rxqid;
+	u16 *rss;
+
+	if (!pi->vi_mirror_count)
+		return 0;
+
+	if (s->mirror_rxq[pi->port_id])
+		return 0;
+
+	mirror_rxq = kcalloc(pi->nmirrorqsets, sizeof(*mirror_rxq), GFP_KERNEL);
+	if (!mirror_rxq)
+		return -ENOMEM;
+
+	s->mirror_rxq[pi->port_id] = mirror_rxq;
+
+	if (!(adap->flags & CXGB4_USING_MSIX))
+		msix = -((int)adap->sge.intrq.abs_id + 1);
+
+	for (i = 0, rxqid = 0; i < pi->nmirrorqsets; i++, rxqid++) {
+		mirror_rxq = &s->mirror_rxq[pi->port_id][i];
+
+		/* Allocate Mirror Rxqs */
+		if (msix >= 0) {
+			msix = cxgb4_get_msix_idx_from_bmap(adap);
+			if (msix < 0) {
+				ret = msix;
+				goto out_free_queues;
+			}
+
+			mirror_rxq->msix = &adap->msix_info[msix];
+			snprintf(mirror_rxq->msix->desc,
+				 sizeof(mirror_rxq->msix->desc),
+				 "%s-mirrorrxq%d", dev->name, i);
+		}
+
+		init_rspq(adap, &mirror_rxq->rspq,
+			  CXGB4_MIRROR_RXQ_DEFAULT_INTR_USEC,
+			  CXGB4_MIRROR_RXQ_DEFAULT_PKT_CNT,
+			  CXGB4_MIRROR_RXQ_DEFAULT_DESC_NUM,
+			  CXGB4_MIRROR_RXQ_DEFAULT_DESC_SIZE);
+
+		mirror_rxq->fl.size = CXGB4_MIRROR_FLQ_DEFAULT_DESC_NUM;
+
+		ret = t4_sge_alloc_rxq(adap, &mirror_rxq->rspq, false,
+				       dev, msix, &mirror_rxq->fl,
+				       t4_ethrx_handler, NULL, 0);
+		if (ret)
+			goto out_free_msix_idx;
+
+		/* Setup MSI-X vectors for Mirror Rxqs */
+		if (adap->flags & CXGB4_USING_MSIX) {
+			ret = request_irq(mirror_rxq->msix->vec,
+					  t4_sge_intr_msix, 0,
+					  mirror_rxq->msix->desc,
+					  &mirror_rxq->rspq);
+			if (ret)
+				goto out_free_rxq;
+
+			cxgb4_set_msix_aff(adap, mirror_rxq->msix->vec,
+					   &mirror_rxq->msix->aff_mask, i);
+		}
+
+		/* Start NAPI for Mirror Rxqs */
+		cxgb4_enable_rx(adap, &mirror_rxq->rspq);
+	}
+
+	/* Setup RSS for Mirror Rxqs */
+	rss = kcalloc(pi->rss_size, sizeof(u16), GFP_KERNEL);
+	if (!rss) {
+		ret = -ENOMEM;
+		goto out_free_queues;
+	}
+
+	mirror_rxq = &s->mirror_rxq[pi->port_id][0];
+	for (i = 0; i < pi->rss_size; i++)
+		rss[i] = mirror_rxq[i % pi->nmirrorqsets].rspq.abs_id;
+
+	ret = cxgb4_config_rss(pi, rss, pi->rss_size, pi->viid_mirror);
+	kfree(rss);
+	if (ret)
+		goto out_free_queues;
+
+	return 0;
+
+out_free_rxq:
+	free_rspq_fl(adap, &mirror_rxq->rspq, &mirror_rxq->fl);
+
+out_free_msix_idx:
+	cxgb4_free_msix_idx_in_bmap(adap, mirror_rxq->msix->idx);
+
+out_free_queues:
+	while (rxqid-- > 0)
+		cxgb4_port_mirror_free_rxq(adap,
+					   &s->mirror_rxq[pi->port_id][rxqid]);
+
+	kfree(s->mirror_rxq[pi->port_id]);
+	s->mirror_rxq[pi->port_id] = NULL;
+	return ret;
+}
+
+static void cxgb4_port_mirror_free_queues(struct net_device *dev)
+{
+	struct port_info *pi = netdev2pinfo(dev);
+	struct adapter *adap = netdev2adap(dev);
+	struct sge *s = &adap->sge;
+	u16 i;
+
+	if (!pi->vi_mirror_count)
+		return;
+
+	if (!s->mirror_rxq[pi->port_id])
+		return;
+
+	for (i = 0; i < pi->nmirrorqsets; i++)
+		cxgb4_port_mirror_free_rxq(adap,
+					   &s->mirror_rxq[pi->port_id][i]);
+
+	kfree(s->mirror_rxq[pi->port_id]);
+	s->mirror_rxq[pi->port_id] = NULL;
+}
+
+static int cxgb4_port_mirror_start(struct net_device *dev)
+{
+	struct port_info *pi = netdev2pinfo(dev);
+	struct adapter *adap = netdev2adap(dev);
+	int ret, idx = -1;
+
+	if (!pi->vi_mirror_count)
+		return 0;
+
+	/* Mirror VIs can be created dynamically after stack had
+	 * already setup Rx modes like MTU, promisc, allmulti, etc.
+	 * on main VI. So, parse what the stack had setup on the
+	 * main VI and update the same on the mirror VI.
+	 */
+	ret = t4_set_rxmode(adap, adap->mbox, pi->viid, pi->viid_mirror,
+			    dev->mtu, (dev->flags & IFF_PROMISC) ? 1 : 0,
+			    (dev->flags & IFF_ALLMULTI) ? 1 : 0, 1,
+			    !!(dev->features & NETIF_F_HW_VLAN_CTAG_RX), true);
+	if (ret) {
+		dev_err(adap->pdev_dev,
+			"Failed start up Rx mode for Mirror VI 0x%x, ret: %d\n",
+			pi->viid_mirror, ret);
+		return ret;
+	}
+
+	/* Enable replication bit for the device's MAC address
+	 * in MPS TCAM, so that the packets for the main VI are
+	 * replicated to mirror VI.
+	 */
+	ret = cxgb4_update_mac_filt(pi, pi->viid_mirror, &idx,
+				    dev->dev_addr, true, NULL);
+	if (ret) {
+		dev_err(adap->pdev_dev,
+			"Failed updating MAC filter for Mirror VI 0x%x, ret: %d\n",
+			pi->viid_mirror, ret);
+		return ret;
+	}
+
+	/* Enabling a Virtual Interface can result in an interrupt
+	 * during the processing of the VI Enable command and, in some
+	 * paths, result in an attempt to issue another command in the
+	 * interrupt context. Thus, we disable interrupts during the
+	 * course of the VI Enable command ...
+	 */
+	local_bh_disable();
+	ret = t4_enable_vi_params(adap, adap->mbox, pi->viid_mirror, true, true,
+				  false);
+	local_bh_enable();
+	if (ret)
+		dev_err(adap->pdev_dev,
+			"Failed starting Mirror VI 0x%x, ret: %d\n",
+			pi->viid_mirror, ret);
+
+	return ret;
+}
+
+static void cxgb4_port_mirror_stop(struct net_device *dev)
+{
+	struct port_info *pi = netdev2pinfo(dev);
+	struct adapter *adap = netdev2adap(dev);
+
+	if (!pi->vi_mirror_count)
+		return;
+
+	t4_enable_vi_params(adap, adap->mbox, pi->viid_mirror, false, false,
+			    false);
+}
+
+int cxgb4_port_mirror_alloc(struct net_device *dev)
+{
+	struct port_info *pi = netdev2pinfo(dev);
+	struct adapter *adap = netdev2adap(dev);
+	int ret = 0;
+
+	if (!pi->nmirrorqsets)
+		return -EOPNOTSUPP;
+
+	mutex_lock(&pi->vi_mirror_mutex);
+	if (pi->viid_mirror) {
+		pi->vi_mirror_count++;
+		goto out_unlock;
+	}
+
+	ret = t4_init_port_mirror(pi, adap->mbox, pi->port_id, adap->pf, 0,
+				  &pi->viid_mirror);
+	if (ret)
+		goto out_unlock;
+
+	pi->vi_mirror_count = 1;
+
+	if (adap->flags & CXGB4_FULL_INIT_DONE) {
+		ret = cxgb4_port_mirror_alloc_queues(dev);
+		if (ret)
+			goto out_free_vi;
+
+		ret = cxgb4_port_mirror_start(dev);
+		if (ret)
+			goto out_free_queues;
+	}
+
+	mutex_unlock(&pi->vi_mirror_mutex);
+	return 0;
+
+out_free_queues:
+	cxgb4_port_mirror_free_queues(dev);
+
+out_free_vi:
+	pi->vi_mirror_count = 0;
+	t4_free_vi(adap, adap->mbox, adap->pf, 0, pi->viid_mirror);
+	pi->viid_mirror = 0;
+
+out_unlock:
+	mutex_unlock(&pi->vi_mirror_mutex);
+	return ret;
+}
+
+void cxgb4_port_mirror_free(struct net_device *dev)
+{
+	struct port_info *pi = netdev2pinfo(dev);
+	struct adapter *adap = netdev2adap(dev);
+
+	mutex_lock(&pi->vi_mirror_mutex);
+	if (!pi->viid_mirror)
+		goto out_unlock;
+
+	if (pi->vi_mirror_count > 1) {
+		pi->vi_mirror_count--;
+		goto out_unlock;
+	}
+
+	cxgb4_port_mirror_stop(dev);
+	cxgb4_port_mirror_free_queues(dev);
+
+	pi->vi_mirror_count = 0;
+	t4_free_vi(adap, adap->mbox, adap->pf, 0, pi->viid_mirror);
+	pi->viid_mirror = 0;
+
+out_unlock:
+	mutex_unlock(&pi->vi_mirror_mutex);
+}
+
 /*
  * upper-layer driver support
  */
@@ -1585,6 +1882,7 @@ static int tid_init(struct tid_info *t)
 	atomic_set(&t->tids_in_use, 0);
 	atomic_set(&t->conns_in_use, 0);
 	atomic_set(&t->hash_tids_in_use, 0);
+	atomic_set(&t->eotids_in_use, 0);
 
 	/* Setup the free list for atid_tab and clear the stid bitmap. */
 	if (natids) {
@@ -1616,6 +1914,7 @@ static int tid_init(struct tid_info *t)
  *	@stid: the server TID
  *	@sip: local IP address to bind server to
  *	@sport: the server's TCP port
+ *	@vlan: the VLAN header information
  *	@queue: queue to direct messages from this server to
  *
  *	Create an IP server for the given port and address.
@@ -2344,6 +2643,9 @@ static void detach_ulds(struct adapter *adap)
 {
 	unsigned int i;
 
+	if (!is_uld(adap))
+		return;
+
 	mutex_lock(&uld_mutex);
 	list_del(&adap->list_node);
 
@@ -2535,7 +2837,7 @@ static void cxgb_down(struct adapter *adapter)
 /*
  * net_device operations
  */
-int cxgb_open(struct net_device *dev)
+static int cxgb_open(struct net_device *dev)
 {
 	struct port_info *pi = netdev_priv(dev);
 	struct adapter *adapter = pi->adapter;
@@ -2557,12 +2859,33 @@ int cxgb_open(struct net_device *dev)
 		return err;
 
 	err = link_start(dev);
-	if (!err)
-		netif_tx_start_all_queues(dev);
+	if (err)
+		return err;
+
+	if (pi->nmirrorqsets) {
+		mutex_lock(&pi->vi_mirror_mutex);
+		err = cxgb4_port_mirror_alloc_queues(dev);
+		if (err)
+			goto out_unlock;
+
+		err = cxgb4_port_mirror_start(dev);
+		if (err)
+			goto out_free_queues;
+		mutex_unlock(&pi->vi_mirror_mutex);
+	}
+
+	netif_tx_start_all_queues(dev);
+	return 0;
+
+out_free_queues:
+	cxgb4_port_mirror_free_queues(dev);
+
+out_unlock:
+	mutex_unlock(&pi->vi_mirror_mutex);
 	return err;
 }
 
-int cxgb_close(struct net_device *dev)
+static int cxgb_close(struct net_device *dev)
 {
 	struct port_info *pi = netdev_priv(dev);
 	struct adapter *adapter = pi->adapter;
@@ -2576,7 +2899,17 @@ int cxgb_close(struct net_device *dev)
 	cxgb4_dcb_reset(dev);
 	dcb_tx_queue_prio_enable(dev, false);
 #endif
-	return ret;
+	if (ret)
+		return ret;
+
+	if (pi->nmirrorqsets) {
+		mutex_lock(&pi->vi_mirror_mutex);
+		cxgb4_port_mirror_stop(dev);
+		cxgb4_port_mirror_free_queues(dev);
+		mutex_unlock(&pi->vi_mirror_mutex);
+	}
+
+	return 0;
 }
 
 int cxgb4_create_server_filter(const struct net_device *dev, unsigned int stid,
@@ -2610,7 +2943,7 @@ int cxgb4_create_server_filter(const struct net_device *dev, unsigned int stid,
 
 	/* Clear out filter specifications */
 	memset(&f->fs, 0, sizeof(struct ch_filter_specification));
-	f->fs.val.lport = cpu_to_be16(sport);
+	f->fs.val.lport = be16_to_cpu(sport);
 	f->fs.mask.lport  = ~0;
 	val = (u8 *)&sip;
 	if ((val[0] | val[1] | val[2] | val[3]) != 0) {
@@ -2842,11 +3175,11 @@ static void cxgb_set_rxmode(struct net_device *dev)
 
 static int cxgb_change_mtu(struct net_device *dev, int new_mtu)
 {
-	int ret;
 	struct port_info *pi = netdev_priv(dev);
+	int ret;
 
-	ret = t4_set_rxmode(pi->adapter, pi->adapter->pf, pi->viid, new_mtu, -1,
-			    -1, -1, -1, true);
+	ret = t4_set_rxmode(pi->adapter, pi->adapter->mbox, pi->viid,
+			    pi->viid_mirror, new_mtu, -1, -1, -1, -1, true);
 	if (!ret)
 		dev->mtu = new_mtu;
 	return ret;
@@ -2871,8 +3204,6 @@ static void cxgb4_mgmt_fill_vf_station_mac_addr(struct adapter *adap)
 	int err;
 	u8 *na;
 
-	adap->params.pci.vpd_cap_addr = pci_find_capability(adap->pdev,
-							    PCI_CAP_ID_VPD);
 	err = t4_get_raw_vpd_params(adap, &adap->params.vpd);
 	if (err)
 		return;
@@ -3027,7 +3358,7 @@ static int cxgb4_mgmt_set_vf_rate(struct net_device *dev, int vf,
 			      SCHED_CLASS_RATEUNIT_BITS,
 			      SCHED_CLASS_RATEMODE_ABS,
 			      pi->tx_chan, class_id, 0,
-			      max_tx_rate * 1000, 0, pktsize);
+			      max_tx_rate * 1000, 0, pktsize, 0);
 	if (ret) {
 		dev_err(adap->pdev_dev, "Err %d for Traffic Class config\n",
 			ret);
@@ -3137,8 +3468,7 @@ static int cxgb_set_mac_addr(struct net_device *dev, void *p)
 	if (ret < 0)
 		return ret;
 
-	memcpy(dev->dev_addr, addr->sa_data, dev->addr_len);
-	pi->xact_addr_filt = ret;
+	eth_hw_addr_set(dev, addr->sa_data);
 	return 0;
 }
 
@@ -3404,129 +3734,71 @@ static int cxgb_setup_tc(struct net_device *dev, enum tc_setup_type type,
 	}
 }
 
-static void cxgb_del_udp_tunnel(struct net_device *netdev,
-				struct udp_tunnel_info *ti)
+static int cxgb_udp_tunnel_unset_port(struct net_device *netdev,
+				      unsigned int table, unsigned int entry,
+				      struct udp_tunnel_info *ti)
 {
 	struct port_info *pi = netdev_priv(netdev);
 	struct adapter *adapter = pi->adapter;
-	unsigned int chip_ver = CHELSIO_CHIP_VERSION(adapter->params.chip);
 	u8 match_all_mac[] = { 0, 0, 0, 0, 0, 0 };
 	int ret = 0, i;
 
-	if (chip_ver < CHELSIO_T6)
-		return;
-
 	switch (ti->type) {
 	case UDP_TUNNEL_TYPE_VXLAN:
-		if (!adapter->vxlan_port_cnt ||
-		    adapter->vxlan_port != ti->port)
-			return; /* Invalid VxLAN destination port */
-
-		adapter->vxlan_port_cnt--;
-		if (adapter->vxlan_port_cnt)
-			return;
-
 		adapter->vxlan_port = 0;
 		t4_write_reg(adapter, MPS_RX_VXLAN_TYPE_A, 0);
 		break;
 	case UDP_TUNNEL_TYPE_GENEVE:
-		if (!adapter->geneve_port_cnt ||
-		    adapter->geneve_port != ti->port)
-			return; /* Invalid GENEVE destination port */
-
-		adapter->geneve_port_cnt--;
-		if (adapter->geneve_port_cnt)
-			return;
-
 		adapter->geneve_port = 0;
 		t4_write_reg(adapter, MPS_RX_GENEVE_TYPE_A, 0);
 		break;
 	default:
-		return;
+		return -EINVAL;
 	}
 
 	/* Matchall mac entries can be deleted only after all tunnel ports
 	 * are brought down or removed.
 	 */
 	if (!adapter->rawf_cnt)
-		return;
+		return 0;
 	for_each_port(adapter, i) {
 		pi = adap2pinfo(adapter, i);
 		ret = t4_free_raw_mac_filt(adapter, pi->viid,
 					   match_all_mac, match_all_mac,
-					   adapter->rawf_start +
-					    pi->port_id,
+					   adapter->rawf_start + pi->port_id,
 					   1, pi->port_id, false);
 		if (ret < 0) {
 			netdev_info(netdev, "Failed to free mac filter entry, for port %d\n",
 				    i);
-			return;
+			return ret;
 		}
 	}
+
+	return 0;
 }
 
-static void cxgb_add_udp_tunnel(struct net_device *netdev,
-				struct udp_tunnel_info *ti)
+static int cxgb_udp_tunnel_set_port(struct net_device *netdev,
+				    unsigned int table, unsigned int entry,
+				    struct udp_tunnel_info *ti)
 {
 	struct port_info *pi = netdev_priv(netdev);
 	struct adapter *adapter = pi->adapter;
-	unsigned int chip_ver = CHELSIO_CHIP_VERSION(adapter->params.chip);
 	u8 match_all_mac[] = { 0, 0, 0, 0, 0, 0 };
 	int i, ret;
 
-	if (chip_ver < CHELSIO_T6 || !adapter->rawf_cnt)
-		return;
-
 	switch (ti->type) {
 	case UDP_TUNNEL_TYPE_VXLAN:
-		/* Callback for adding vxlan port can be called with the same
-		 * port for both IPv4 and IPv6. We should not disable the
-		 * offloading when the same port for both protocols is added
-		 * and later one of them is removed.
-		 */
-		if (adapter->vxlan_port_cnt &&
-		    adapter->vxlan_port == ti->port) {
-			adapter->vxlan_port_cnt++;
-			return;
-		}
-
-		/* We will support only one VxLAN port */
-		if (adapter->vxlan_port_cnt) {
-			netdev_info(netdev, "UDP port %d already offloaded, not adding port %d\n",
-				    be16_to_cpu(adapter->vxlan_port),
-				    be16_to_cpu(ti->port));
-			return;
-		}
-
 		adapter->vxlan_port = ti->port;
-		adapter->vxlan_port_cnt = 1;
-
 		t4_write_reg(adapter, MPS_RX_VXLAN_TYPE_A,
 			     VXLAN_V(be16_to_cpu(ti->port)) | VXLAN_EN_F);
 		break;
 	case UDP_TUNNEL_TYPE_GENEVE:
-		if (adapter->geneve_port_cnt &&
-		    adapter->geneve_port == ti->port) {
-			adapter->geneve_port_cnt++;
-			return;
-		}
-
-		/* We will support only one GENEVE port */
-		if (adapter->geneve_port_cnt) {
-			netdev_info(netdev, "UDP port %d already offloaded, not adding port %d\n",
-				    be16_to_cpu(adapter->geneve_port),
-				    be16_to_cpu(ti->port));
-			return;
-		}
-
 		adapter->geneve_port = ti->port;
-		adapter->geneve_port_cnt = 1;
-
 		t4_write_reg(adapter, MPS_RX_GENEVE_TYPE_A,
 			     GENEVE_V(be16_to_cpu(ti->port)) | GENEVE_EN_F);
 		break;
 	default:
-		return;
+		return -EINVAL;
 	}
 
 	/* Create a 'match all' mac filter entry for inner mac,
@@ -3541,18 +3813,27 @@ static void cxgb_add_udp_tunnel(struct net_device *netdev,
 		ret = t4_alloc_raw_mac_filt(adapter, pi->viid,
 					    match_all_mac,
 					    match_all_mac,
-					    adapter->rawf_start +
-					    pi->port_id,
+					    adapter->rawf_start + pi->port_id,
 					    1, pi->port_id, false);
 		if (ret < 0) {
 			netdev_info(netdev, "Failed to allocate a mac filter entry, not adding port %d\n",
 				    be16_to_cpu(ti->port));
-			cxgb_del_udp_tunnel(netdev, ti);
-			return;
+			return ret;
 		}
 	}
+
+	return 0;
 }
 
+static const struct udp_tunnel_nic_info cxgb_udp_tunnels = {
+	.set_port	= cxgb_udp_tunnel_set_port,
+	.unset_port	= cxgb_udp_tunnel_unset_port,
+	.tables		= {
+		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN,  },
+		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_GENEVE, },
+	},
+};
+
 static netdev_features_t cxgb_features_check(struct sk_buff *skb,
 					     struct net_device *dev,
 					     netdev_features_t features)
@@ -3591,7 +3872,7 @@ static const struct net_device_ops cxgb4_netdev_ops = {
 	.ndo_set_mac_address  = cxgb_set_mac_addr,
 	.ndo_set_features     = cxgb_set_features,
 	.ndo_validate_addr    = eth_validate_addr,
-	.ndo_do_ioctl         = cxgb_ioctl,
+	.ndo_eth_ioctl         = cxgb_ioctl,
 	.ndo_change_mtu       = cxgb_change_mtu,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller  = cxgb_netpoll,
@@ -3602,8 +3883,6 @@ static const struct net_device_ops cxgb4_netdev_ops = {
 #endif /* CONFIG_CHELSIO_T4_FCOE */
 	.ndo_set_tx_maxrate   = cxgb_set_tx_maxrate,
 	.ndo_setup_tc         = cxgb_setup_tc,
-	.ndo_udp_tunnel_add   = cxgb_add_udp_tunnel,
-	.ndo_udp_tunnel_del   = cxgb_del_udp_tunnel,
 	.ndo_features_check   = cxgb_features_check,
 	.ndo_fix_features     = cxgb_fix_features,
 };
@@ -3618,23 +3897,21 @@ static const struct net_device_ops cxgb4_mgmt_netdev_ops = {
 	.ndo_set_vf_vlan        = cxgb4_mgmt_set_vf_vlan,
 	.ndo_set_vf_link_state	= cxgb4_mgmt_set_vf_link_state,
 };
-#endif
 
 static void cxgb4_mgmt_get_drvinfo(struct net_device *dev,
 				   struct ethtool_drvinfo *info)
 {
 	struct adapter *adapter = netdev2adap(dev);
 
-	strlcpy(info->driver, cxgb4_driver_name, sizeof(info->driver));
-	strlcpy(info->version, cxgb4_driver_version,
-		sizeof(info->version));
-	strlcpy(info->bus_info, pci_name(adapter->pdev),
+	strscpy(info->driver, cxgb4_driver_name, sizeof(info->driver));
+	strscpy(info->bus_info, pci_name(adapter->pdev),
 		sizeof(info->bus_info));
 }
 
 static const struct ethtool_ops cxgb4_mgmt_ethtool_ops = {
 	.get_drvinfo       = cxgb4_mgmt_get_drvinfo,
 };
+#endif
 
 static void notify_fatal_err(struct work_struct *work)
 {
@@ -3731,7 +4008,7 @@ static void adap_free_hma_mem(struct adapter *adapter)
 
 	if (adapter->hma.flags & HMA_DMA_MAPPED_FLAG) {
 		dma_unmap_sg(adapter->pdev_dev, adapter->hma.sgt->sgl,
-			     adapter->hma.sgt->nents, PCI_DMA_BIDIRECTIONAL);
+			     adapter->hma.sgt->nents, DMA_BIDIRECTIONAL);
 		adapter->hma.flags &= ~HMA_DMA_MAPPED_FLAG;
 	}
 
@@ -4150,8 +4427,7 @@ static int adap_init0_phy(struct adapter *adap)
 
 	/* Load PHY Firmware onto adapter.
 	 */
-	ret = t4_load_phy_fw(adap, MEMWIN_NIC, &adap->win0_lock,
-			     phy_info->phy_fw_version,
+	ret = t4_load_phy_fw(adap, MEMWIN_NIC, phy_info->phy_fw_version,
 			     (u8 *)phyf->data, phyf->size);
 	if (ret < 0)
 		dev_err(adap->pdev_dev, "PHY Firmware transfer error %d\n",
@@ -4771,23 +5047,20 @@ static int adap_init0(struct adapter *adap, int vpd_skip)
 	/* Allocate the memory for the vaious egress queue bitmaps
 	 * ie starving_fl, txq_maperr and blocked_fl.
 	 */
-	adap->sge.starving_fl =	kcalloc(BITS_TO_LONGS(adap->sge.egr_sz),
-					sizeof(long), GFP_KERNEL);
+	adap->sge.starving_fl = bitmap_zalloc(adap->sge.egr_sz, GFP_KERNEL);
 	if (!adap->sge.starving_fl) {
 		ret = -ENOMEM;
 		goto bye;
 	}
 
-	adap->sge.txq_maperr = kcalloc(BITS_TO_LONGS(adap->sge.egr_sz),
-				       sizeof(long), GFP_KERNEL);
+	adap->sge.txq_maperr = bitmap_zalloc(adap->sge.egr_sz, GFP_KERNEL);
 	if (!adap->sge.txq_maperr) {
 		ret = -ENOMEM;
 		goto bye;
 	}
 
 #ifdef CONFIG_DEBUG_FS
-	adap->sge.blocked_fl = kcalloc(BITS_TO_LONGS(adap->sge.egr_sz),
-				       sizeof(long), GFP_KERNEL);
+	adap->sge.blocked_fl = bitmap_zalloc(adap->sge.egr_sz, GFP_KERNEL);
 	if (!adap->sge.blocked_fl) {
 		ret = -ENOMEM;
 		goto bye;
@@ -4860,7 +5133,7 @@ static int adap_init0(struct adapter *adap, int vpd_skip)
 
 	/* See if FW supports FW_FILTER2 work request */
 	if (is_t4(adap->params.chip)) {
-		adap->params.filter2_wr_support = 0;
+		adap->params.filter2_wr_support = false;
 	} else {
 		params[0] = FW_PARAM_DEV(FILTER2_WR);
 		ret = t4_query_params(adap, adap->mbox, adap->pf, 0,
@@ -5140,10 +5413,10 @@ bye:
 	adap_free_hma_mem(adap);
 	kfree(adap->sge.egr_map);
 	kfree(adap->sge.ingr_map);
-	kfree(adap->sge.starving_fl);
-	kfree(adap->sge.txq_maperr);
+	bitmap_free(adap->sge.starving_fl);
+	bitmap_free(adap->sge.txq_maperr);
 #ifdef CONFIG_DEBUG_FS
-	kfree(adap->sge.blocked_fl);
+	bitmap_free(adap->sge.blocked_fl);
 #endif
 	if (ret != -ETIMEDOUT && ret != -EIO)
 		t4_fw_bye(adap, adap->mbox);
@@ -5381,10 +5654,10 @@ static inline bool is_x_10g_port(const struct link_config *lc)
 static int cfg_queues(struct adapter *adap)
 {
 	u32 avail_qsets, avail_eth_qsets, avail_uld_qsets;
-	u32 i, n10g = 0, qidx = 0, n1g = 0;
 	u32 ncpus = num_online_cpus();
 	u32 niqflint, neq, num_ulds;
 	struct sge *s = &adap->sge;
+	u32 i, n10g = 0, qidx = 0;
 	u32 q10g = 0, q1g;
 
 	/* Reduce memory usage in kdump environment, disable all offload. */
@@ -5430,7 +5703,6 @@ static int cfg_queues(struct adapter *adap)
 	if (n10g)
 		q10g = (avail_eth_qsets - (adap->params.nports - n10g)) / n10g;
 
-	n1g = adap->params.nports - n10g;
 #ifdef CONFIG_CHELSIO_T4_DCB
 	/* For Data Center Bridging support we need to be able to support up
 	 * to 8 Traffic Priorities; each of which will be assigned to its
@@ -5448,7 +5720,8 @@ static int cfg_queues(struct adapter *adap)
 	else
 		q10g = max(8U, q10g);
 
-	while ((q10g * n10g) > (avail_eth_qsets - n1g * q1g))
+	while ((q10g * n10g) >
+	       (avail_eth_qsets - (adap->params.nports - n10g) * q1g))
 		q10g--;
 
 #else /* !CONFIG_CHELSIO_T4_DCB */
@@ -5506,6 +5779,19 @@ static int cfg_queues(struct adapter *adap)
 		avail_qsets -= s->eoqsets;
 	}
 
+	/* Mirror queues must follow same scheme as normal Ethernet
+	 * Queues, when there are enough queues available. Otherwise,
+	 * allocate at least 1 queue per port. If even 1 queue is not
+	 * available, then disable mirror queues support.
+	 */
+	if (avail_qsets >= s->max_ethqsets)
+		s->mirrorqsets = s->max_ethqsets;
+	else if (avail_qsets >= adap->params.nports)
+		s->mirrorqsets = adap->params.nports;
+	else
+		s->mirrorqsets = 0;
+	avail_qsets -= s->mirrorqsets;
+
 	for (i = 0; i < ARRAY_SIZE(s->ethrxq); i++) {
 		struct sge_eth_rxq *r = &s->ethrxq[i];
 
@@ -5564,8 +5850,7 @@ static int alloc_msix_info(struct adapter *adap, u32 num_vec)
 	if (!msix_info)
 		return -ENOMEM;
 
-	adap->msix_bmap.msix_bmap = kcalloc(BITS_TO_LONGS(num_vec),
-					    sizeof(long), GFP_KERNEL);
+	adap->msix_bmap.msix_bmap = bitmap_zalloc(num_vec, GFP_KERNEL);
 	if (!adap->msix_bmap.msix_bmap) {
 		kfree(msix_info);
 		return -ENOMEM;
@@ -5580,7 +5865,7 @@ static int alloc_msix_info(struct adapter *adap, u32 num_vec)
 
 static void free_msix_info(struct adapter *adap)
 {
-	kfree(adap->msix_bmap.msix_bmap);
+	bitmap_free(adap->msix_bmap.msix_bmap);
 	kfree(adap->msix_info);
 }
 
@@ -5619,8 +5904,8 @@ void cxgb4_free_msix_idx_in_bmap(struct adapter *adap,
 
 static int enable_msix(struct adapter *adap)
 {
-	u32 eth_need, uld_need = 0, ethofld_need = 0;
-	u32 ethqsets = 0, ofldqsets = 0, eoqsets = 0;
+	u32 eth_need, uld_need = 0, ethofld_need = 0, mirror_need = 0;
+	u32 ethqsets = 0, ofldqsets = 0, eoqsets = 0, mirrorqsets = 0;
 	u8 num_uld = 0, nchan = adap->params.nports;
 	u32 i, want, need, num_vec;
 	struct sge *s = &adap->sge;
@@ -5651,6 +5936,12 @@ static int enable_msix(struct adapter *adap)
 		need += ethofld_need;
 	}
 
+	if (s->mirrorqsets) {
+		want += s->mirrorqsets;
+		mirror_need = nchan;
+		need += mirror_need;
+	}
+
 	want += EXTRA_VECS;
 	need += EXTRA_VECS;
 
@@ -5684,8 +5975,10 @@ static int enable_msix(struct adapter *adap)
 		adap->params.ethofld = 0;
 		s->ofldqsets = 0;
 		s->eoqsets = 0;
+		s->mirrorqsets = 0;
 		uld_need = 0;
 		ethofld_need = 0;
+		mirror_need = 0;
 	}
 
 	num_vec = allocated;
@@ -5699,6 +5992,8 @@ static int enable_msix(struct adapter *adap)
 			ofldqsets = nchan;
 		if (is_ethofld(adap))
 			eoqsets = ethofld_need;
+		if (s->mirrorqsets)
+			mirrorqsets = mirror_need;
 
 		num_vec -= need;
 		while (num_vec) {
@@ -5730,12 +6025,25 @@ static int enable_msix(struct adapter *adap)
 				num_vec -= uld_need;
 			}
 		}
+
+		if (s->mirrorqsets) {
+			while (num_vec) {
+				if (num_vec < mirror_need ||
+				    mirrorqsets > s->mirrorqsets)
+					break;
+
+				mirrorqsets++;
+				num_vec -= mirror_need;
+			}
+		}
 	} else {
 		ethqsets = s->max_ethqsets;
 		if (is_uld(adap))
 			ofldqsets = s->ofldqsets;
 		if (is_ethofld(adap))
 			eoqsets = s->eoqsets;
+		if (s->mirrorqsets)
+			mirrorqsets = s->mirrorqsets;
 	}
 
 	if (ethqsets < s->max_ethqsets) {
@@ -5751,6 +6059,15 @@ static int enable_msix(struct adapter *adap)
 	if (is_ethofld(adap))
 		s->eoqsets = eoqsets;
 
+	if (s->mirrorqsets) {
+		s->mirrorqsets = mirrorqsets;
+		for_each_port(adap, i) {
+			pi = adap2pinfo(adap, i);
+			pi->nmirrorqsets = s->mirrorqsets / nchan;
+			mutex_init(&pi->vi_mirror_mutex);
+		}
+	}
+
 	/* map for msix */
 	ret = alloc_msix_info(adap, allocated);
 	if (ret)
@@ -5762,8 +6079,9 @@ static int enable_msix(struct adapter *adap)
 	}
 
 	dev_info(adap->pdev_dev,
-		 "%d MSI-X vectors allocated, nic %d eoqsets %d per uld %d\n",
-		 allocated, s->max_ethqsets, s->eoqsets, s->nqs_per_uld);
+		 "%d MSI-X vectors allocated, nic %d eoqsets %d per uld %d mirrorqsets %d\n",
+		 allocated, s->max_ethqsets, s->eoqsets, s->nqs_per_uld,
+		 s->mirrorqsets);
 
 	kfree(entries);
 	return 0;
@@ -5840,8 +6158,7 @@ static void print_port_info(const struct net_device *dev)
 		--bufp;
 	sprintf(bufp, "BASE-%s", t4_get_port_type_description(pi->port_type));
 
-	netdev_info(dev, "%s: Chelsio %s (%s) %s\n",
-		    dev->name, adap->params.vpd.id, adap->name, buf);
+	netdev_info(dev, "Chelsio %s %s\n", adap->params.vpd.id, buf);
 }
 
 /*
@@ -5864,12 +6181,13 @@ static void free_some_resources(struct adapter *adapter)
 	cxgb4_cleanup_tc_mqprio(adapter);
 	cxgb4_cleanup_tc_flower(adapter);
 	cxgb4_cleanup_tc_u32(adapter);
+	cxgb4_cleanup_ethtool_filters(adapter);
 	kfree(adapter->sge.egr_map);
 	kfree(adapter->sge.ingr_map);
-	kfree(adapter->sge.starving_fl);
-	kfree(adapter->sge.txq_maperr);
+	bitmap_free(adapter->sge.starving_fl);
+	bitmap_free(adapter->sge.txq_maperr);
 #ifdef CONFIG_DEBUG_FS
-	kfree(adapter->sge.blocked_fl);
+	bitmap_free(adapter->sge.blocked_fl);
 #endif
 	disable_msi(adapter);
 
@@ -6071,6 +6389,213 @@ static int cxgb4_iov_configure(struct pci_dev *pdev, int num_vfs)
 }
 #endif /* CONFIG_PCI_IOV */
 
+#if IS_ENABLED(CONFIG_CHELSIO_TLS_DEVICE) || IS_ENABLED(CONFIG_CHELSIO_IPSEC_INLINE)
+
+static int chcr_offload_state(struct adapter *adap,
+			      enum cxgb4_netdev_tls_ops op_val)
+{
+	switch (op_val) {
+#if IS_ENABLED(CONFIG_CHELSIO_TLS_DEVICE)
+	case CXGB4_TLSDEV_OPS:
+		if (!adap->uld[CXGB4_ULD_KTLS].handle) {
+			dev_dbg(adap->pdev_dev, "ch_ktls driver is not loaded\n");
+			return -EOPNOTSUPP;
+		}
+		if (!adap->uld[CXGB4_ULD_KTLS].tlsdev_ops) {
+			dev_dbg(adap->pdev_dev,
+				"ch_ktls driver has no registered tlsdev_ops\n");
+			return -EOPNOTSUPP;
+		}
+		break;
+#endif /* CONFIG_CHELSIO_TLS_DEVICE */
+#if IS_ENABLED(CONFIG_CHELSIO_IPSEC_INLINE)
+	case CXGB4_XFRMDEV_OPS:
+		if (!adap->uld[CXGB4_ULD_IPSEC].handle) {
+			dev_dbg(adap->pdev_dev, "chipsec driver is not loaded\n");
+			return -EOPNOTSUPP;
+		}
+		if (!adap->uld[CXGB4_ULD_IPSEC].xfrmdev_ops) {
+			dev_dbg(adap->pdev_dev,
+				"chipsec driver has no registered xfrmdev_ops\n");
+			return -EOPNOTSUPP;
+		}
+		break;
+#endif /* CONFIG_CHELSIO_IPSEC_INLINE */
+	default:
+		dev_dbg(adap->pdev_dev,
+			"driver has no support for offload %d\n", op_val);
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+#endif /* CONFIG_CHELSIO_TLS_DEVICE || CONFIG_CHELSIO_IPSEC_INLINE */
+
+#if IS_ENABLED(CONFIG_CHELSIO_TLS_DEVICE)
+
+static int cxgb4_ktls_dev_add(struct net_device *netdev, struct sock *sk,
+			      enum tls_offload_ctx_dir direction,
+			      struct tls_crypto_info *crypto_info,
+			      u32 tcp_sn)
+{
+	struct adapter *adap = netdev2adap(netdev);
+	int ret;
+
+	mutex_lock(&uld_mutex);
+	ret = chcr_offload_state(adap, CXGB4_TLSDEV_OPS);
+	if (ret)
+		goto out_unlock;
+
+	ret = cxgb4_set_ktls_feature(adap, FW_PARAMS_PARAM_DEV_KTLS_HW_ENABLE);
+	if (ret)
+		goto out_unlock;
+
+	ret = adap->uld[CXGB4_ULD_KTLS].tlsdev_ops->tls_dev_add(netdev, sk,
+								direction,
+								crypto_info,
+								tcp_sn);
+	/* if there is a failure, clear the refcount */
+	if (ret)
+		cxgb4_set_ktls_feature(adap,
+				       FW_PARAMS_PARAM_DEV_KTLS_HW_DISABLE);
+out_unlock:
+	mutex_unlock(&uld_mutex);
+	return ret;
+}
+
+static void cxgb4_ktls_dev_del(struct net_device *netdev,
+			       struct tls_context *tls_ctx,
+			       enum tls_offload_ctx_dir direction)
+{
+	struct adapter *adap = netdev2adap(netdev);
+
+	mutex_lock(&uld_mutex);
+	if (chcr_offload_state(adap, CXGB4_TLSDEV_OPS))
+		goto out_unlock;
+
+	adap->uld[CXGB4_ULD_KTLS].tlsdev_ops->tls_dev_del(netdev, tls_ctx,
+							  direction);
+
+out_unlock:
+	cxgb4_set_ktls_feature(adap, FW_PARAMS_PARAM_DEV_KTLS_HW_DISABLE);
+	mutex_unlock(&uld_mutex);
+}
+
+static const struct tlsdev_ops cxgb4_ktls_ops = {
+	.tls_dev_add = cxgb4_ktls_dev_add,
+	.tls_dev_del = cxgb4_ktls_dev_del,
+};
+#endif /* CONFIG_CHELSIO_TLS_DEVICE */
+
+#if IS_ENABLED(CONFIG_CHELSIO_IPSEC_INLINE)
+
+static int cxgb4_xfrm_add_state(struct xfrm_state *x)
+{
+	struct adapter *adap = netdev2adap(x->xso.dev);
+	int ret;
+
+	if (!mutex_trylock(&uld_mutex)) {
+		dev_dbg(adap->pdev_dev,
+			"crypto uld critical resource is under use\n");
+		return -EBUSY;
+	}
+	ret = chcr_offload_state(adap, CXGB4_XFRMDEV_OPS);
+	if (ret)
+		goto out_unlock;
+
+	ret = adap->uld[CXGB4_ULD_IPSEC].xfrmdev_ops->xdo_dev_state_add(x);
+
+out_unlock:
+	mutex_unlock(&uld_mutex);
+
+	return ret;
+}
+
+static void cxgb4_xfrm_del_state(struct xfrm_state *x)
+{
+	struct adapter *adap = netdev2adap(x->xso.dev);
+
+	if (!mutex_trylock(&uld_mutex)) {
+		dev_dbg(adap->pdev_dev,
+			"crypto uld critical resource is under use\n");
+		return;
+	}
+	if (chcr_offload_state(adap, CXGB4_XFRMDEV_OPS))
+		goto out_unlock;
+
+	adap->uld[CXGB4_ULD_IPSEC].xfrmdev_ops->xdo_dev_state_delete(x);
+
+out_unlock:
+	mutex_unlock(&uld_mutex);
+}
+
+static void cxgb4_xfrm_free_state(struct xfrm_state *x)
+{
+	struct adapter *adap = netdev2adap(x->xso.dev);
+
+	if (!mutex_trylock(&uld_mutex)) {
+		dev_dbg(adap->pdev_dev,
+			"crypto uld critical resource is under use\n");
+		return;
+	}
+	if (chcr_offload_state(adap, CXGB4_XFRMDEV_OPS))
+		goto out_unlock;
+
+	adap->uld[CXGB4_ULD_IPSEC].xfrmdev_ops->xdo_dev_state_free(x);
+
+out_unlock:
+	mutex_unlock(&uld_mutex);
+}
+
+static bool cxgb4_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *x)
+{
+	struct adapter *adap = netdev2adap(x->xso.dev);
+	bool ret = false;
+
+	if (!mutex_trylock(&uld_mutex)) {
+		dev_dbg(adap->pdev_dev,
+			"crypto uld critical resource is under use\n");
+		return ret;
+	}
+	if (chcr_offload_state(adap, CXGB4_XFRMDEV_OPS))
+		goto out_unlock;
+
+	ret = adap->uld[CXGB4_ULD_IPSEC].xfrmdev_ops->xdo_dev_offload_ok(skb, x);
+
+out_unlock:
+	mutex_unlock(&uld_mutex);
+	return ret;
+}
+
+static void cxgb4_advance_esn_state(struct xfrm_state *x)
+{
+	struct adapter *adap = netdev2adap(x->xso.dev);
+
+	if (!mutex_trylock(&uld_mutex)) {
+		dev_dbg(adap->pdev_dev,
+			"crypto uld critical resource is under use\n");
+		return;
+	}
+	if (chcr_offload_state(adap, CXGB4_XFRMDEV_OPS))
+		goto out_unlock;
+
+	adap->uld[CXGB4_ULD_IPSEC].xfrmdev_ops->xdo_dev_state_advance_esn(x);
+
+out_unlock:
+	mutex_unlock(&uld_mutex);
+}
+
+static const struct xfrmdev_ops cxgb4_xfrmdev_ops = {
+	.xdo_dev_state_add      = cxgb4_xfrm_add_state,
+	.xdo_dev_state_delete   = cxgb4_xfrm_del_state,
+	.xdo_dev_state_free     = cxgb4_xfrm_free_state,
+	.xdo_dev_offload_ok     = cxgb4_ipsec_offload_ok,
+	.xdo_dev_state_advance_esn = cxgb4_advance_esn_state,
+};
+
+#endif /* CONFIG_CHELSIO_IPSEC_INLINE */
+
 static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	struct net_device *netdev;
@@ -6078,7 +6603,6 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	static int adap_idx = 1;
 	int s_qpp, qpp, num_seg;
 	struct port_info *pi;
-	bool highdma = false;
 	enum chip_type chip;
 	void __iomem *regs;
 	int func, chip_ver;
@@ -6086,8 +6610,6 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	int i, err;
 	u32 whoami;
 
-	printk_once(KERN_INFO "%s - version %s\n", DRV_DESC, DRV_VERSION);
-
 	err = pci_request_regions(pdev, KBUILD_MODNAME);
 	if (err) {
 		/* Just info, some other driver may have claimed the device. */
@@ -6159,20 +6681,10 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		return 0;
 	}
 
-	if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) {
-		highdma = true;
-		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
-		if (err) {
-			dev_err(&pdev->dev, "unable to obtain 64-bit DMA for "
-				"coherent allocations\n");
-			goto out_free_adapter;
-		}
-	} else {
-		err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
-		if (err) {
-			dev_err(&pdev->dev, "no usable DMA configuration\n");
-			goto out_free_adapter;
-		}
+	err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
+	if (err) {
+		dev_err(&pdev->dev, "no usable DMA configuration\n");
+		goto out_free_adapter;
 	}
 
 	pci_enable_pcie_error_reporting(pdev);
@@ -6260,13 +6772,11 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	setup_memwin(adapter);
 	err = adap_init0(adapter, 0);
-#ifdef CONFIG_DEBUG_FS
-	bitmap_zero(adapter->sge.blocked_fl, adapter->sge.egr_sz);
-#endif
-	setup_memwin_rdma(adapter);
 	if (err)
 		goto out_unmap_bar;
 
+	setup_memwin_rdma(adapter);
+
 	/* configure SGE_STAT_CFG_A to read WC stats */
 	if (!is_t4(adapter->params.chip))
 		t4_write_reg(adapter, SGE_STAT_CFG_A, STATSOURCE_T5_V(7) |
@@ -6303,7 +6813,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 			NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
 			NETIF_F_RXCSUM | NETIF_F_RXHASH | NETIF_F_GRO |
 			NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX |
-			NETIF_F_HW_TC;
+			NETIF_F_HW_TC | NETIF_F_NTUPLE | NETIF_F_HIGHDMA;
 
 		if (chip_ver > CHELSIO_T5) {
 			netdev->hw_enc_features |= NETIF_F_IP_CSUM |
@@ -6316,12 +6826,28 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 			netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL |
 					       NETIF_F_GSO_UDP_TUNNEL_CSUM |
 					       NETIF_F_HW_TLS_RECORD;
+
+			if (adapter->rawf_cnt)
+				netdev->udp_tunnel_nic_info = &cxgb_udp_tunnels;
 		}
 
-		if (highdma)
-			netdev->hw_features |= NETIF_F_HIGHDMA;
 		netdev->features |= netdev->hw_features;
 		netdev->vlan_features = netdev->features & VLAN_FEAT;
+#if IS_ENABLED(CONFIG_CHELSIO_TLS_DEVICE)
+		if (pi->adapter->params.crypto & FW_CAPS_CONFIG_TLS_HW) {
+			netdev->hw_features |= NETIF_F_HW_TLS_TX;
+			netdev->tlsdev_ops = &cxgb4_ktls_ops;
+			/* initialize the refcount */
+			refcount_set(&pi->adapter->chcr_ktls.ktls_refcount, 0);
+		}
+#endif /* CONFIG_CHELSIO_TLS_DEVICE */
+#if IS_ENABLED(CONFIG_CHELSIO_IPSEC_INLINE)
+		if (pi->adapter->params.crypto & FW_CAPS_CONFIG_IPSEC_INLINE) {
+			netdev->hw_enc_features |= NETIF_F_HW_ESP;
+			netdev->features |= NETIF_F_HW_ESP;
+			netdev->xfrmdev_ops = &cxgb4_xfrmdev_ops;
+		}
+#endif /* CONFIG_CHELSIO_IPSEC_INLINE */
 
 		netdev->priv_flags |= IFF_UNICAST_FLT;
 
@@ -6419,6 +6945,24 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 				 i);
 	}
 
+	if (is_offload(adapter) || is_hashfilter(adapter)) {
+		if (t4_read_reg(adapter, LE_DB_CONFIG_A) & HASHEN_F) {
+			u32 v;
+
+			v = t4_read_reg(adapter, LE_DB_HASH_CONFIG_A);
+			if (chip_ver <= CHELSIO_T5) {
+				adapter->tids.nhash = 1 << HASHTIDSIZE_G(v);
+				v = t4_read_reg(adapter, LE_DB_TID_HASHBASE_A);
+				adapter->tids.hash_base = v / 4;
+			} else {
+				adapter->tids.nhash = HASHTBLSIZE_G(v) << 3;
+				v = t4_read_reg(adapter,
+						T6_LE_DB_HASH_TID_BASE_A);
+				adapter->tids.hash_base = v;
+			}
+		}
+	}
+
 	if (tid_init(&adapter->tids) < 0) {
 		dev_warn(&pdev->dev, "could not allocate TID table, "
 			 "continuing\n");
@@ -6440,22 +6984,9 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		if (cxgb4_init_tc_matchall(adapter))
 			dev_warn(&pdev->dev,
 				 "could not offload tc matchall, continuing\n");
-	}
-
-	if (is_offload(adapter) || is_hashfilter(adapter)) {
-		if (t4_read_reg(adapter, LE_DB_CONFIG_A) & HASHEN_F) {
-			u32 hash_base, hash_reg;
-
-			if (chip_ver <= CHELSIO_T5) {
-				hash_reg = LE_DB_TID_HASHBASE_A;
-				hash_base = t4_read_reg(adapter, hash_reg);
-				adapter->tids.hash_base = hash_base / 4;
-			} else {
-				hash_reg = T6_LE_DB_HASH_TID_BASE_A;
-				hash_base = t4_read_reg(adapter, hash_reg);
-				adapter->tids.hash_base = hash_base;
-			}
-		}
+		if (cxgb4_init_ethtool_filters(adapter))
+			dev_warn(&pdev->dev,
+				 "could not initialize ethtool filters, continuing\n");
 	}
 
 	/* See what interrupts we'll be using */
@@ -6529,11 +7060,8 @@ fw_attach_fail:
 	/* PCIe EEH recovery on powerpc platforms needs fundamental reset */
 	pdev->needs_freset = 1;
 
-	if (is_uld(adapter)) {
-		mutex_lock(&uld_mutex);
-		list_add_tail(&adapter->list_node, &adapter_list);
-		mutex_unlock(&uld_mutex);
-	}
+	if (is_uld(adapter))
+		cxgb4_uld_enable(adapter);
 
 	if (!is_t4(adapter->params.chip))
 		cxgb4_ptp_init(adapter);
@@ -6596,10 +7124,13 @@ static void remove_one(struct pci_dev *pdev)
 		 */
 		destroy_workqueue(adapter->workq);
 
-		if (is_uld(adapter)) {
-			detach_ulds(adapter);
-			t4_uld_clean_up(adapter);
-		}
+		detach_ulds(adapter);
+
+		for_each_port(adapter, i)
+			if (adapter->port[i]->reg_state == NETREG_REGISTERED)
+				unregister_netdev(adapter->port[i]);
+
+		t4_uld_clean_up(adapter);
 
 		adap_free_hma_mem(adapter);
 
@@ -6607,10 +7138,6 @@ static void remove_one(struct pci_dev *pdev)
 
 		cxgb4_free_mps_ref_entries(adapter);
 
-		for_each_port(adapter, i)
-			if (adapter->port[i]->reg_state == NETREG_REGISTERED)
-				unregister_netdev(adapter->port[i]);
-
 		debugfs_remove_recursive(adapter->debugfs_root);
 
 		if (!is_t4(adapter->params.chip))
@@ -6682,6 +7209,10 @@ static void shutdown_one(struct pci_dev *pdev)
 			if (adapter->port[i]->reg_state == NETREG_REGISTERED)
 				cxgb_close(adapter->port[i]);
 
+		rtnl_lock();
+		cxgb4_mqprio_stop_offload(adapter);
+		rtnl_unlock();
+
 		if (is_uld(adapter)) {
 			detach_ulds(adapter);
 			t4_uld_clean_up(adapter);