Merge tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband

Pull more infiniband changes from Roland Dreier:
"Second batch of InfiniBand/RDMA changes for 3.8:
- cxgb4 changes to fix lookup engine hash collisions
- mlx4 changes to make flow steering usable
- fix to IPoIB to avoid pinning dst reference for too long"

* tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband:
RDMA/cxgb4: Fix bug for active and passive LE hash collision path
RDMA/cxgb4: Fix LE hash collision bug for passive open connection
RDMA/cxgb4: Fix LE hash collision bug for active open connection
mlx4_core: Allow choosing flow steering mode
mlx4_core: Adjustments to Flow Steering activation logic for SR-IOV
mlx4_core: Fix error flow in the flow steering wrapper
mlx4_core: Add QPN enforcement for flow steering rules set by VFs
cxgb4: Add LE hash collision bug fix path in LLD driver
cxgb4: Add T4 filter support
IPoIB: Call skb_dst_drop() once skb is enqueued for sending

drivers/infiniband/hw/cxgb4/cm.c

···
 #include <linux/inetdevice.h>
 #include <linux/ip.h>
 #include <linux/tcp.h>
+#include <linux/if_vlan.h>
 
 #include <net/neighbour.h>
 #include <net/netevent.h>
 #include <net/route.h>
+#include <net/tcp.h>
 
 #include "iw_cxgb4.h"
 
···
 	"dead",
 	NULL,
 };
+
+static int nocong;
+module_param(nocong, int, 0644);
+MODULE_PARM_DESC(nocong, "Turn of congestion control (default=0)");
+
+static int enable_ecn;
+module_param(enable_ecn, int, 0644);
+MODULE_PARM_DESC(enable_ecn, "Enable ECN (default=0/disabled)");
 
 static int dack_mode = 1;
 module_param(dack_mode, int, 0644);
···
 		cxgb4_remove_tid(ep->com.dev->rdev.lldi.tids, 0, ep->hwtid);
 		dst_release(ep->dst);
 		cxgb4_l2t_release(ep->l2t);
+		remove_handle(ep->com.dev, &ep->com.dev->hwtid_idr, ep->hwtid);
 	}
 	kfree(ep);
 }
···
 	return c4iw_l2t_send(&ep->com.dev->rdev, skb, ep->l2t);
 }
 
+#define VLAN_NONE 0xfff
+#define FILTER_SEL_VLAN_NONE 0xffff
+#define FILTER_SEL_WIDTH_P_FC (3+1) /* port uses 3 bits, FCoE one bit */
+#define FILTER_SEL_WIDTH_VIN_P_FC \
+	(6 + 7 + FILTER_SEL_WIDTH_P_FC) /* 6 bits are unused, VF uses 7 bits*/
+#define FILTER_SEL_WIDTH_TAG_P_FC \
+	(3 + FILTER_SEL_WIDTH_VIN_P_FC) /* PF uses 3 bits */
+#define FILTER_SEL_WIDTH_VLD_TAG_P_FC (1 + FILTER_SEL_WIDTH_TAG_P_FC)
+
+static unsigned int select_ntuple(struct c4iw_dev *dev, struct dst_entry *dst,
+				  struct l2t_entry *l2t)
+{
+	unsigned int ntuple = 0;
+	u32 viid;
+
+	switch (dev->rdev.lldi.filt_mode) {
+
+	/* default filter mode */
+	case HW_TPL_FR_MT_PR_IV_P_FC:
+		if (l2t->vlan == VLAN_NONE)
+			ntuple |= FILTER_SEL_VLAN_NONE << FILTER_SEL_WIDTH_P_FC;
+		else {
+			ntuple |= l2t->vlan << FILTER_SEL_WIDTH_P_FC;
+			ntuple |= 1 << FILTER_SEL_WIDTH_VLD_TAG_P_FC;
+		}
+		ntuple |= l2t->lport << S_PORT | IPPROTO_TCP <<
+			  FILTER_SEL_WIDTH_VLD_TAG_P_FC;
+		break;
+	case HW_TPL_FR_MT_PR_OV_P_FC: {
+		viid = cxgb4_port_viid(l2t->neigh->dev);
+
+		ntuple |= FW_VIID_VIN_GET(viid) << FILTER_SEL_WIDTH_P_FC;
+		ntuple |= FW_VIID_PFN_GET(viid) << FILTER_SEL_WIDTH_VIN_P_FC;
+		ntuple |= FW_VIID_VIVLD_GET(viid) << FILTER_SEL_WIDTH_TAG_P_FC;
+		ntuple |= l2t->lport << S_PORT | IPPROTO_TCP <<
+			  FILTER_SEL_WIDTH_VLD_TAG_P_FC;
+		break;
+	}
+	default:
+		break;
+	}
+	return ntuple;
+}
+
 static int send_connect(struct c4iw_ep *ep)
 {
 	struct cpl_act_open_req *req;
···
 
 	cxgb4_best_mtu(ep->com.dev->rdev.lldi.mtus, ep->mtu, &mtu_idx);
 	wscale = compute_wscale(rcv_win);
-	opt0 = KEEP_ALIVE(1) |
+	opt0 = (nocong ? NO_CONG(1) : 0) |
+	       KEEP_ALIVE(1) |
 	       DELACK(1) |
 	       WND_SCALE(wscale) |
 	       MSS_IDX(mtu_idx) |
···
 	       ULP_MODE(ULP_MODE_TCPDDP) |
 	       RCV_BUFSIZ(rcv_win>>10);
 	opt2 = RX_CHANNEL(0) |
+	       CCTRL_ECN(enable_ecn) |
 	       RSS_QUEUE_VALID | RSS_QUEUE(ep->rss_qid);
 	if (enable_tcp_timestamps)
 		opt2 |= TSTAMPS_EN(1);
···
 	req->local_ip = ep->com.local_addr.sin_addr.s_addr;
 	req->peer_ip = ep->com.remote_addr.sin_addr.s_addr;
 	req->opt0 = cpu_to_be64(opt0);
-	req->params = 0;
+	req->params = cpu_to_be32(select_ntuple(ep->com.dev, ep->dst, ep->l2t));
 	req->opt2 = cpu_to_be32(opt2);
+	set_bit(ACT_OPEN_REQ, &ep->com.history);
 	return c4iw_l2t_send(&ep->com.dev->rdev, skb, ep->l2t);
 }
 
···
 	/* setup the hwtid for this connection */
 	ep->hwtid = tid;
 	cxgb4_insert_tid(t, ep, tid);
+	insert_handle(dev, &dev->hwtid_idr, ep, ep->hwtid);
 
 	ep->snd_seq = be32_to_cpu(req->snd_isn);
 	ep->rcv_seq = be32_to_cpu(req->rcv_isn);
···
 	set_emss(ep, ntohs(req->tcp_opt));
 
 	/* dealloc the atid */
+	remove_handle(ep->com.dev, &ep->com.dev->atid_idr, atid);
 	cxgb4_free_atid(t, atid);
+	set_bit(ACT_ESTAB, &ep->com.history);
 
 	/* start MPA negotiation */
 	send_flowc(ep, NULL);
···
 		ep->com.cm_id->rem_ref(ep->com.cm_id);
 		ep->com.cm_id = NULL;
 		ep->com.qp = NULL;
+		set_bit(CLOSE_UPCALL, &ep->com.history);
 	}
 }
 
···
 	PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
 	close_complete_upcall(ep);
 	state_set(&ep->com, ABORTING);
+	set_bit(ABORT_CONN, &ep->com.history);
 	return send_abort(ep, skb, gfp);
 }
 
···
 		PDBG("peer close delivered ep %p cm_id %p tid %u\n",
 		     ep, ep->com.cm_id, ep->hwtid);
 		ep->com.cm_id->event_handler(ep->com.cm_id, &event);
+		set_bit(DISCONN_UPCALL, &ep->com.history);
 	}
 }
 
···
 		ep->com.cm_id->rem_ref(ep->com.cm_id);
 		ep->com.cm_id = NULL;
 		ep->com.qp = NULL;
+		set_bit(ABORT_UPCALL, &ep->com.history);
 	}
 }
 
···
 
 	PDBG("%s ep %p tid %u status %d\n", __func__, ep,
 	     ep->hwtid, status);
+	set_bit(CONN_RPL_UPCALL, &ep->com.history);
 	ep->com.cm_id->event_handler(ep->com.cm_id, &event);
 
 	if (status < 0) {
···
 						ep->parent_ep->com.cm_id,
 						&event);
 	}
+	set_bit(CONNREQ_UPCALL, &ep->com.history);
 	c4iw_put_ep(&ep->parent_ep->com);
 	ep->parent_ep = NULL;
 }
···
 	if (ep->com.cm_id) {
 		PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
 		ep->com.cm_id->event_handler(ep->com.cm_id, &event);
+		set_bit(ESTAB_UPCALL, &ep->com.history);
 	}
 }
 
···
 	unsigned int dlen = ntohs(hdr->len);
 	unsigned int tid = GET_TID(hdr);
 	struct tid_info *t = dev->rdev.lldi.tids;
+	__u8 status = hdr->status;
 
 	ep = lookup_tid(t, tid);
 	PDBG("%s ep %p tid %u dlen %u\n", __func__, ep, ep->hwtid, dlen);
···
 	case MPA_REP_SENT:
 		break;
 	default:
-		printk(KERN_ERR MOD "%s Unexpected streaming data."
-		       " ep %p state %d tid %u\n",
-		       __func__, ep, state_read(&ep->com), ep->hwtid);
+		pr_err("%s Unexpected streaming data." \
+		       " ep %p state %d tid %u status %d\n",
+		       __func__, ep, state_read(&ep->com), ep->hwtid, status);
 
 		/*
 		 * The ep will timeout and inform the ULP of the failure.
···
 	return 0;
 }
 
+static void send_fw_act_open_req(struct c4iw_ep *ep, unsigned int atid)
+{
+	struct sk_buff *skb;
+	struct fw_ofld_connection_wr *req;
+	unsigned int mtu_idx;
+	int wscale;
+
+	skb = get_skb(NULL, sizeof(*req), GFP_KERNEL);
+	req = (struct fw_ofld_connection_wr *)__skb_put(skb, sizeof(*req));
+	memset(req, 0, sizeof(*req));
+	req->op_compl = htonl(V_WR_OP(FW_OFLD_CONNECTION_WR));
+	req->len16_pkd = htonl(FW_WR_LEN16(DIV_ROUND_UP(sizeof(*req), 16)));
+	req->le.filter = cpu_to_be32(select_ntuple(ep->com.dev, ep->dst,
+				     ep->l2t));
+	req->le.lport = ep->com.local_addr.sin_port;
+	req->le.pport = ep->com.remote_addr.sin_port;
+	req->le.u.ipv4.lip = ep->com.local_addr.sin_addr.s_addr;
+	req->le.u.ipv4.pip = ep->com.remote_addr.sin_addr.s_addr;
+	req->tcb.t_state_to_astid =
+			htonl(V_FW_OFLD_CONNECTION_WR_T_STATE(TCP_SYN_SENT) |
+			V_FW_OFLD_CONNECTION_WR_ASTID(atid));
+	req->tcb.cplrxdataack_cplpassacceptrpl =
+			htons(F_FW_OFLD_CONNECTION_WR_CPLRXDATAACK);
+	req->tcb.tx_max = jiffies;
+	req->tcb.rcv_adv = htons(1);
+	cxgb4_best_mtu(ep->com.dev->rdev.lldi.mtus, ep->mtu, &mtu_idx);
+	wscale = compute_wscale(rcv_win);
+	req->tcb.opt0 = TCAM_BYPASS(1) |
+		(nocong ? NO_CONG(1) : 0) |
+		KEEP_ALIVE(1) |
+		DELACK(1) |
+		WND_SCALE(wscale) |
+		MSS_IDX(mtu_idx) |
+		L2T_IDX(ep->l2t->idx) |
+		TX_CHAN(ep->tx_chan) |
+		SMAC_SEL(ep->smac_idx) |
+		DSCP(ep->tos) |
+		ULP_MODE(ULP_MODE_TCPDDP) |
+		RCV_BUFSIZ(rcv_win >> 10);
+	req->tcb.opt2 = PACE(1) |
+		TX_QUEUE(ep->com.dev->rdev.lldi.tx_modq[ep->tx_chan]) |
+		RX_CHANNEL(0) |
+		CCTRL_ECN(enable_ecn) |
+		RSS_QUEUE_VALID | RSS_QUEUE(ep->rss_qid);
+	if (enable_tcp_timestamps)
+		req->tcb.opt2 |= TSTAMPS_EN(1);
+	if (enable_tcp_sack)
+		req->tcb.opt2 |= SACK_EN(1);
+	if (wscale && enable_tcp_window_scaling)
+		req->tcb.opt2 |= WND_SCALE_EN(1);
+	req->tcb.opt0 = cpu_to_be64(req->tcb.opt0);
+	req->tcb.opt2 = cpu_to_be32(req->tcb.opt2);
+	set_wr_txq(skb, CPL_PRIORITY_CONTROL, ep->ctrlq_idx);
+	set_bit(ACT_OFLD_CONN, &ep->com.history);
+	c4iw_l2t_send(&ep->com.dev->rdev, skb, ep->l2t);
+}
+
 /*
  * Return whether a failed active open has allocated a TID
  */
···
 {
 	return status != CPL_ERR_TCAM_FULL && status != CPL_ERR_CONN_EXIST &&
 	       status != CPL_ERR_ARP_MISS;
+}
+
+#define ACT_OPEN_RETRY_COUNT 2
+
+static int c4iw_reconnect(struct c4iw_ep *ep)
+{
+	int err = 0;
+	struct rtable *rt;
+	struct port_info *pi;
+	struct net_device *pdev;
+	int step;
+	struct neighbour *neigh;
+
+	PDBG("%s qp %p cm_id %p\n", __func__, ep->com.qp, ep->com.cm_id);
+	init_timer(&ep->timer);
+
+	/*
+	 * Allocate an active TID to initiate a TCP connection.
+	 */
+	ep->atid = cxgb4_alloc_atid(ep->com.dev->rdev.lldi.tids, ep);
+	if (ep->atid == -1) {
+		pr_err("%s - cannot alloc atid.\n", __func__);
+		err = -ENOMEM;
+		goto fail2;
+	}
+	insert_handle(ep->com.dev, &ep->com.dev->atid_idr, ep, ep->atid);
+
+	/* find a route */
+	rt = find_route(ep->com.dev,
+			ep->com.cm_id->local_addr.sin_addr.s_addr,
+			ep->com.cm_id->remote_addr.sin_addr.s_addr,
+			ep->com.cm_id->local_addr.sin_port,
+			ep->com.cm_id->remote_addr.sin_port, 0);
+	if (!rt) {
+		pr_err("%s - cannot find route.\n", __func__);
+		err = -EHOSTUNREACH;
+		goto fail3;
+	}
+	ep->dst = &rt->dst;
+
+	neigh = dst_neigh_lookup(ep->dst,
+			&ep->com.cm_id->remote_addr.sin_addr.s_addr);
+	/* get a l2t entry */
+	if (neigh->dev->flags & IFF_LOOPBACK) {
+		PDBG("%s LOOPBACK\n", __func__);
+		pdev = ip_dev_find(&init_net,
+				ep->com.cm_id->remote_addr.sin_addr.s_addr);
+		ep->l2t = cxgb4_l2t_get(ep->com.dev->rdev.lldi.l2t,
+				neigh, pdev, 0);
+		pi = (struct port_info *)netdev_priv(pdev);
+		ep->mtu = pdev->mtu;
+		ep->tx_chan = cxgb4_port_chan(pdev);
+		ep->smac_idx = (cxgb4_port_viid(pdev) & 0x7F) << 1;
+		dev_put(pdev);
+	} else {
+		ep->l2t = cxgb4_l2t_get(ep->com.dev->rdev.lldi.l2t,
+				neigh, neigh->dev, 0);
+		pi = (struct port_info *)netdev_priv(neigh->dev);
+		ep->mtu = dst_mtu(ep->dst);
+		ep->tx_chan = cxgb4_port_chan(neigh->dev);
+		ep->smac_idx = (cxgb4_port_viid(neigh->dev) &
+				0x7F) << 1;
+	}
+
+	step = ep->com.dev->rdev.lldi.ntxq / ep->com.dev->rdev.lldi.nchan;
+	ep->txq_idx = pi->port_id * step;
+	ep->ctrlq_idx = pi->port_id;
+	step = ep->com.dev->rdev.lldi.nrxq / ep->com.dev->rdev.lldi.nchan;
+	ep->rss_qid = ep->com.dev->rdev.lldi.rxq_ids[pi->port_id * step];
+
+	if (!ep->l2t) {
+		pr_err("%s - cannot alloc l2e.\n", __func__);
+		err = -ENOMEM;
+		goto fail4;
+	}
+
+	PDBG("%s txq_idx %u tx_chan %u smac_idx %u rss_qid %u l2t_idx %u\n",
+	     __func__, ep->txq_idx, ep->tx_chan, ep->smac_idx, ep->rss_qid,
+	     ep->l2t->idx);
+
+	state_set(&ep->com, CONNECTING);
+	ep->tos = 0;
+
+	/* send connect request to rnic */
+	err = send_connect(ep);
+	if (!err)
+		goto out;
+
+	cxgb4_l2t_release(ep->l2t);
+fail4:
+	dst_release(ep->dst);
+fail3:
+	remove_handle(ep->com.dev, &ep->com.dev->atid_idr, ep->atid);
+	cxgb4_free_atid(ep->com.dev->rdev.lldi.tids, ep->atid);
+fail2:
+	/*
+	 * remember to send notification to upper layer.
+	 * We are in here so the upper layer is not aware that this is
+	 * re-connect attempt and so, upper layer is still waiting for
+	 * response of 1st connect request.
+	 */
+	connect_reply_upcall(ep, -ECONNRESET);
+	c4iw_put_ep(&ep->com);
+out:
+	return err;
 }
 
 static int act_open_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
···
 		return 0;
 	}
 
+	set_bit(ACT_OPEN_RPL, &ep->com.history);
+
 	/*
 	 * Log interesting failures.
 	 */
 	switch (status) {
 	case CPL_ERR_CONN_RESET:
 	case CPL_ERR_CONN_TIMEDOUT:
+		break;
+	case CPL_ERR_TCAM_FULL:
+		if (dev->rdev.lldi.enable_fw_ofld_conn) {
+			mutex_lock(&dev->rdev.stats.lock);
+			dev->rdev.stats.tcam_full++;
+			mutex_unlock(&dev->rdev.stats.lock);
+			send_fw_act_open_req(ep,
+					     GET_TID_TID(GET_AOPEN_ATID(
+					     ntohl(rpl->atid_status))));
+			return 0;
+		}
+		break;
+	case CPL_ERR_CONN_EXIST:
+		if (ep->retry_count++ < ACT_OPEN_RETRY_COUNT) {
+			set_bit(ACT_RETRY_INUSE, &ep->com.history);
+			remove_handle(ep->com.dev, &ep->com.dev->atid_idr,
+					atid);
+			cxgb4_free_atid(t, atid);
+			dst_release(ep->dst);
+			cxgb4_l2t_release(ep->l2t);
+			c4iw_reconnect(ep);
+			return 0;
+		}
 		break;
 	default:
 		printk(KERN_INFO MOD "Active open failure - "
···
 	if (status && act_open_has_tid(status))
 		cxgb4_remove_tid(ep->com.dev->rdev.lldi.tids, 0, GET_TID(rpl));
 
+	remove_handle(ep->com.dev, &ep->com.dev->atid_idr, atid);
 	cxgb4_free_atid(t, atid);
 	dst_release(ep->dst);
 	cxgb4_l2t_release(ep->l2t);
···
 	struct c4iw_listen_ep *ep = lookup_stid(t, stid);
 
 	if (!ep) {
-		printk(KERN_ERR MOD "stid %d lookup failure!\n", stid);
-		return 0;
+		PDBG("%s stid %d lookup failure!\n", __func__, stid);
+		goto out;
 	}
 	PDBG("%s ep %p status %d error %d\n", __func__, ep,
 	     rpl->status, status2errno(rpl->status));
 	c4iw_wake_up(&ep->com.wr_wait, status2errno(rpl->status));
 
+out:
 	return 0;
 }
 
···
 	skb_get(skb);
 	cxgb4_best_mtu(ep->com.dev->rdev.lldi.mtus, ep->mtu, &mtu_idx);
 	wscale = compute_wscale(rcv_win);
-	opt0 = KEEP_ALIVE(1) |
+	opt0 = (nocong ? NO_CONG(1) : 0) |
+	       KEEP_ALIVE(1) |
 	       DELACK(1) |
 	       WND_SCALE(wscale) |
 	       MSS_IDX(mtu_idx) |
 	       L2T_IDX(ep->l2t->idx) |
 	       TX_CHAN(ep->tx_chan) |
 	       SMAC_SEL(ep->smac_idx) |
-	       DSCP(ep->tos) |
+	       DSCP(ep->tos >> 2) |
 	       ULP_MODE(ULP_MODE_TCPDDP) |
 	       RCV_BUFSIZ(rcv_win>>10);
 	opt2 = RX_CHANNEL(0) |
···
 		opt2 |= SACK_EN(1);
 	if (wscale && enable_tcp_window_scaling)
 		opt2 |= WND_SCALE_EN(1);
+	if (enable_ecn) {
+		const struct tcphdr *tcph;
+		u32 hlen = ntohl(req->hdr_len);
+
+		tcph = (const void *)(req + 1) + G_ETH_HDR_LEN(hlen) +
+			G_IP_HDR_LEN(hlen);
+		if (tcph->ece && tcph->cwr)
+			opt2 |= CCTRL_ECN(1);
+	}
 
 	rpl = cplhdr(skb);
 	INIT_TP_WR(rpl, ep->hwtid);
···
 
 static int pass_accept_req(struct c4iw_dev *dev, struct sk_buff *skb)
 {
-	struct c4iw_ep *child_ep, *parent_ep;
+	struct c4iw_ep *child_ep = NULL, *parent_ep;
 	struct cpl_pass_accept_req *req = cplhdr(skb);
 	unsigned int stid = GET_POPEN_TID(ntohl(req->tos_stid));
 	struct tid_info *t = dev->rdev.lldi.tids;
 	unsigned int hwtid = GET_TID(req);
 	struct dst_entry *dst;
 	struct rtable *rt;
-	__be32 local_ip, peer_ip;
+	__be32 local_ip, peer_ip = 0;
 	__be16 local_port, peer_port;
 	int err;
+	u16 peer_mss = ntohs(req->tcpopt.mss);
 
 	parent_ep = lookup_stid(t, stid);
-	PDBG("%s parent ep %p tid %u\n", __func__, parent_ep, hwtid);
-
+	if (!parent_ep) {
+		PDBG("%s connect request on invalid stid %d\n", __func__, stid);
+		goto reject;
+	}
 	get_4tuple(req, &local_ip, &peer_ip, &local_port, &peer_port);
+
+	PDBG("%s parent ep %p hwtid %u laddr 0x%x raddr 0x%x lport %d " \
+	     "rport %d peer_mss %d\n", __func__, parent_ep, hwtid,
+	     ntohl(local_ip), ntohl(peer_ip), ntohs(local_port),
+	     ntohs(peer_port), peer_mss);
 
 	if (state_read(&parent_ep->com) != LISTEN) {
 		printk(KERN_ERR "%s - listening ep not in LISTEN\n",
···
 		goto reject;
 	}
 
+	if (peer_mss && child_ep->mtu > (peer_mss + 40))
+		child_ep->mtu = peer_mss + 40;
+
 	state_set(&child_ep->com, CONNECTING);
 	child_ep->com.dev = dev;
 	child_ep->com.cm_id = NULL;
···
 	init_timer(&child_ep->timer);
 	cxgb4_insert_tid(t, child_ep, hwtid);
 	accept_cr(child_ep, peer_ip, skb, req);
+	set_bit(PASS_ACCEPT_REQ, &child_ep->com.history);
 	goto out;
 reject:
 	reject_cr(dev, hwtid, peer_ip, skb);
···
 	ep->snd_seq = be32_to_cpu(req->snd_isn);
 	ep->rcv_seq = be32_to_cpu(req->rcv_isn);
 
+	PDBG("%s ep %p hwtid %u tcp_opt 0x%02x\n", __func__, ep, tid,
+	     ntohs(req->tcp_opt));
+
 	set_emss(ep, ntohs(req->tcp_opt));
+	insert_handle(dev, &dev->hwtid_idr, ep, ep->hwtid);
 
 	dst_confirm(ep->dst);
 	state_set(&ep->com, MPA_REQ_WAIT);
 	start_ep_timer(ep);
 	send_flowc(ep, skb);
+	set_bit(PASS_ESTAB, &ep->com.history);
 
 	return 0;
 }
···
 	PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
 	dst_confirm(ep->dst);
 
+	set_bit(PEER_CLOSE, &ep->com.history);
 	mutex_lock(&ep->com.mutex);
 	switch (ep->com.state) {
 	case MPA_REQ_WAIT:
···
 	       status == CPL_ERR_PERSIST_NEG_ADVICE;
 }
 
-static int c4iw_reconnect(struct c4iw_ep *ep)
-{
-	struct rtable *rt;
-	int err = 0;
-
-	PDBG("%s qp %p cm_id %p\n", __func__, ep->com.qp, ep->com.cm_id);
-	init_timer(&ep->timer);
-
-	/*
-	 * Allocate an active TID to initiate a TCP connection.
-	 */
-	ep->atid = cxgb4_alloc_atid(ep->com.dev->rdev.lldi.tids, ep);
-	if (ep->atid == -1) {
-		printk(KERN_ERR MOD "%s - cannot alloc atid.\n", __func__);
-		err = -ENOMEM;
-		goto fail2;
-	}
-
-	/* find a route */
-	rt = find_route(ep->com.dev,
-			ep->com.cm_id->local_addr.sin_addr.s_addr,
-			ep->com.cm_id->remote_addr.sin_addr.s_addr,
-			ep->com.cm_id->local_addr.sin_port,
-			ep->com.cm_id->remote_addr.sin_port, 0);
-	if (!rt) {
-		printk(KERN_ERR MOD "%s - cannot find route.\n", __func__);
-		err = -EHOSTUNREACH;
-		goto fail3;
-	}
-	ep->dst = &rt->dst;
-
-	err = import_ep(ep, ep->com.cm_id->remote_addr.sin_addr.s_addr,
-			ep->dst, ep->com.dev, false);
-	if (err) {
-		printk(KERN_ERR MOD "%s - cannot alloc l2e.\n", __func__);
-		goto fail4;
-	}
-
-	PDBG("%s txq_idx %u tx_chan %u smac_idx %u rss_qid %u l2t_idx %u\n",
-	     __func__, ep->txq_idx, ep->tx_chan, ep->smac_idx, ep->rss_qid,
-	     ep->l2t->idx);
-
-	state_set(&ep->com, CONNECTING);
-	ep->tos = 0;
-
-	/* send connect request to rnic */
-	err = send_connect(ep);
-	if (!err)
-		goto out;
-
-	cxgb4_l2t_release(ep->l2t);
-fail4:
-	dst_release(ep->dst);
-fail3:
-	cxgb4_free_atid(ep->com.dev->rdev.lldi.tids, ep->atid);
-fail2:
-	/*
-	 * remember to send notification to upper layer.
-	 * We are in here so the upper layer is not aware that this is
-	 * re-connect attempt and so, upper layer is still waiting for
-	 * response of 1st connect request.
-	 */
-	connect_reply_upcall(ep, -ECONNRESET);
-	c4iw_put_ep(&ep->com);
-out:
-	return err;
-}
-
 static int peer_abort(struct c4iw_dev *dev, struct sk_buff *skb)
 {
 	struct cpl_abort_req_rss *req = cplhdr(skb);
···
 	}
 	PDBG("%s ep %p tid %u state %u\n", __func__, ep, ep->hwtid,
 	     ep->com.state);
+	set_bit(PEER_ABORT, &ep->com.history);
 
 	/*
 	 * Wake up any threads in rdma_init() or rdma_fini().
···
 		c4iw_put_ep(&ep->com);
 		return -ECONNRESET;
 	}
+	set_bit(ULP_REJECT, &ep->com.history);
 	BUG_ON(state_read(&ep->com) != MPA_REQ_RCVD);
 	if (mpa_rev == 0)
 		abort_connection(ep, NULL, GFP_KERNEL);
···
 	BUG_ON(state_read(&ep->com) != MPA_REQ_RCVD);
 	BUG_ON(!qp);
 
+	set_bit(ULP_ACCEPT, &ep->com.history);
 	if ((conn_param->ord > c4iw_max_read_depth) ||
 	    (conn_param->ird > c4iw_max_read_depth)) {
 		abort_connection(ep, NULL, GFP_KERNEL);
···
 		err = -ENOMEM;
 		goto fail2;
 	}
+	insert_handle(dev, &dev->atid_idr, ep, ep->atid);
 
 	PDBG("%s saddr 0x%x sport 0x%x raddr 0x%x rport 0x%x\n", __func__,
 	     ntohl(cm_id->local_addr.sin_addr.s_addr),
···
 fail4:
 	dst_release(ep->dst);
 fail3:
+	remove_handle(ep->com.dev, &ep->com.dev->atid_idr, ep->atid);
 	cxgb4_free_atid(ep->com.dev->rdev.lldi.tids, ep->atid);
 fail2:
 	cm_id->rem_ref(cm_id);
···
 	int err = 0;
 	struct c4iw_dev *dev = to_c4iw_dev(cm_id->device);
 	struct c4iw_listen_ep *ep;
-
 
 	might_sleep();
 
···
 	/*
 	 * Allocate a server TID.
 	 */
-	ep->stid = cxgb4_alloc_stid(dev->rdev.lldi.tids, PF_INET, ep);
+	if (dev->rdev.lldi.enable_fw_ofld_conn)
+		ep->stid = cxgb4_alloc_sftid(dev->rdev.lldi.tids, PF_INET, ep);
+	else
+		ep->stid = cxgb4_alloc_stid(dev->rdev.lldi.tids, PF_INET, ep);
+
 	if (ep->stid == -1) {
 		printk(KERN_ERR MOD "%s - cannot alloc stid.\n", __func__);
 		err = -ENOMEM;
 		goto fail2;
 	}
-
+	insert_handle(dev, &dev->stid_idr, ep, ep->stid);
 	state_set(&ep->com, LISTEN);
-	c4iw_init_wr_wait(&ep->com.wr_wait);
-	err = cxgb4_create_server(ep->com.dev->rdev.lldi.ports[0], ep->stid,
-				  ep->com.local_addr.sin_addr.s_addr,
-				  ep->com.local_addr.sin_port,
-				  ep->com.dev->rdev.lldi.rxq_ids[0]);
-	if (err)
-		goto fail3;
-
-	/* wait for pass_open_rpl */
-	err = c4iw_wait_for_reply(&ep->com.dev->rdev, &ep->com.wr_wait, 0, 0,
-				  __func__);
+	if (dev->rdev.lldi.enable_fw_ofld_conn) {
+		do {
+			err = cxgb4_create_server_filter(
+				ep->com.dev->rdev.lldi.ports[0], ep->stid,
+				ep->com.local_addr.sin_addr.s_addr,
+				ep->com.local_addr.sin_port,
+				0,
+				ep->com.dev->rdev.lldi.rxq_ids[0],
+				0,
+				0);
+			if (err == -EBUSY) {
+				set_current_state(TASK_UNINTERRUPTIBLE);
+				schedule_timeout(usecs_to_jiffies(100));
+			}
+		} while (err == -EBUSY);
+	} else {
+		c4iw_init_wr_wait(&ep->com.wr_wait);
+		err = cxgb4_create_server(ep->com.dev->rdev.lldi.ports[0],
+				ep->stid, ep->com.local_addr.sin_addr.s_addr,
+				ep->com.local_addr.sin_port,
+				0,
+				ep->com.dev->rdev.lldi.rxq_ids[0]);
+		if (!err)
+			err = c4iw_wait_for_reply(&ep->com.dev->rdev,
+						  &ep->com.wr_wait,
+						  0, 0, __func__);
+	}
 	if (!err) {
 		cm_id->provider_data = ep;
 		goto out;
 	}
-fail3:
+	pr_err("%s cxgb4_create_server/filter failed err %d " \
+	       "stid %d laddr %08x lport %d\n", \
+	       __func__, err, ep->stid,
+	       ntohl(ep->com.local_addr.sin_addr.s_addr),
+	       ntohs(ep->com.local_addr.sin_port));
 	cxgb4_free_stid(ep->com.dev->rdev.lldi.tids, ep->stid, PF_INET);
 fail2:
 	cm_id->rem_ref(cm_id);
···
 
 	might_sleep();
 	state_set(&ep->com, DEAD);
-	c4iw_init_wr_wait(&ep->com.wr_wait);
-	err = listen_stop(ep);
-	if (err)
-		goto done;
-	err = c4iw_wait_for_reply(&ep->com.dev->rdev, &ep->com.wr_wait, 0, 0,
-				  __func__);
+	if (ep->com.dev->rdev.lldi.enable_fw_ofld_conn) {
+		err = cxgb4_remove_server_filter(
+			ep->com.dev->rdev.lldi.ports[0], ep->stid,
+			ep->com.dev->rdev.lldi.rxq_ids[0], 0);
+	} else {
+		c4iw_init_wr_wait(&ep->com.wr_wait);
+		err = listen_stop(ep);
+		if (err)
+			goto done;
+		err = c4iw_wait_for_reply(&ep->com.dev->rdev, &ep->com.wr_wait,
+					  0, 0, __func__);
+	}
+	remove_handle(ep->com.dev, &ep->com.dev->stid_idr, ep->stid);
 	cxgb4_free_stid(ep->com.dev->rdev.lldi.tids, ep->stid, PF_INET);
 done:
 	cm_id->rem_ref(cm_id);
···
 
 	if (close) {
 		if (abrupt) {
+			set_bit(EP_DISC_ABORT, &ep->com.history);
 			close_complete_upcall(ep);
 			ret = send_abort(ep, NULL, gfp);
-		} else
+		} else {
+			set_bit(EP_DISC_CLOSE, &ep->com.history);
 			ret = send_halfclose(ep, gfp);
+		}
 		if (ret)
 			fatal = 1;
 	}
···
 	return ret;
 }
 
-static int async_event(struct c4iw_dev *dev, struct sk_buff *skb)
+static void active_ofld_conn_reply(struct c4iw_dev *dev, struct sk_buff *skb,
+			struct cpl_fw6_msg_ofld_connection_wr_rpl *req)
+{
+	struct c4iw_ep *ep;
+	int atid = be32_to_cpu(req->tid);
+
+	ep = (struct c4iw_ep *)lookup_atid(dev->rdev.lldi.tids, req->tid);
+	if (!ep)
+		return;
+
+	switch (req->retval) {
+	case FW_ENOMEM:
+		set_bit(ACT_RETRY_NOMEM, &ep->com.history);
+		if (ep->retry_count++ < ACT_OPEN_RETRY_COUNT) {
+			send_fw_act_open_req(ep, atid);
+			return;
+		}
+	case FW_EADDRINUSE:
+		set_bit(ACT_RETRY_INUSE, &ep->com.history);
+		if (ep->retry_count++ < ACT_OPEN_RETRY_COUNT) {
+			send_fw_act_open_req(ep, atid);
+			return;
+		}
+		break;
+	default:
+		pr_info("%s unexpected ofld conn wr retval %d\n",
+		       __func__, req->retval);
+		break;
+	}
+	pr_err("active ofld_connect_wr failure %d atid %d\n",
+	       req->retval, atid);
+	mutex_lock(&dev->rdev.stats.lock);
+	dev->rdev.stats.act_ofld_conn_fails++;
+	mutex_unlock(&dev->rdev.stats.lock);
+	connect_reply_upcall(ep, status2errno(req->retval));
+	state_set(&ep->com, DEAD);
+	remove_handle(dev, &dev->atid_idr, atid);
+	cxgb4_free_atid(dev->rdev.lldi.tids, atid);
+	dst_release(ep->dst);
+	cxgb4_l2t_release(ep->l2t);
+	c4iw_put_ep(&ep->com);
+}
+
+static void passive_ofld_conn_reply(struct c4iw_dev *dev, struct sk_buff *skb,
+			struct cpl_fw6_msg_ofld_connection_wr_rpl *req)
+{
+	struct sk_buff *rpl_skb;
+	struct cpl_pass_accept_req *cpl;
+	int ret;
+
+	rpl_skb = (struct sk_buff *)cpu_to_be64(req->cookie);
+	BUG_ON(!rpl_skb);
+	if (req->retval) {
+		PDBG("%s passive open failure %d\n", __func__, req->retval);
+		mutex_lock(&dev->rdev.stats.lock);
+		dev->rdev.stats.pas_ofld_conn_fails++;
+		mutex_unlock(&dev->rdev.stats.lock);
+		kfree_skb(rpl_skb);
+	} else {
+		cpl = (struct cpl_pass_accept_req *)cplhdr(rpl_skb);
+		OPCODE_TID(cpl) = htonl(MK_OPCODE_TID(CPL_PASS_ACCEPT_REQ,
+						      htonl(req->tid)));
+		ret = pass_accept_req(dev, rpl_skb);
+		if (!ret)
+			kfree_skb(rpl_skb);
+	}
+	return;
+}
+
+static int deferred_fw6_msg(struct c4iw_dev *dev, struct sk_buff *skb)
 {
 	struct cpl_fw6_msg *rpl = cplhdr(skb);
-	c4iw_ev_dispatch(dev, (struct t4_cqe *)&rpl->data[0]);
+	struct cpl_fw6_msg_ofld_connection_wr_rpl *req;
+
+	switch (rpl->type) {
+	case FW6_TYPE_CQE:
+		c4iw_ev_dispatch(dev, (struct t4_cqe *)&rpl->data[0]);
+		break;
+	case FW6_TYPE_OFLD_CONNECTION_WR_RPL:
+		req = (struct cpl_fw6_msg_ofld_connection_wr_rpl *)rpl->data;
+		switch (req->t_state) {
+		case TCP_SYN_SENT:
+			active_ofld_conn_reply(dev, skb, req);
+			break;
+		case TCP_SYN_RECV:
+			passive_ofld_conn_reply(dev, skb, req);
+			break;
+		default:
+			pr_err("%s unexpected ofld conn wr state %d\n",
+			       __func__, req->t_state);
+			break;
+		}
+		break;
+	}
+	return 0;
+}
+
+static void build_cpl_pass_accept_req(struct sk_buff *skb, int stid , u8 tos)
+{
+	u32 l2info;
+	u16 vlantag, len, hdr_len;
+	u8 intf;
+	struct cpl_rx_pkt *cpl = cplhdr(skb);
+	struct cpl_pass_accept_req *req;
+	struct tcp_options_received tmp_opt;
+
+	/* Store values from cpl_rx_pkt in temporary location. */
+	vlantag = cpl->vlan;
+	len = cpl->len;
+	l2info  = cpl->l2info;
+	hdr_len = cpl->hdr_len;
+	intf = cpl->iff;
+
+	__skb_pull(skb, sizeof(*req) + sizeof(struct rss_header));
+
+	/*
+	 * We need to parse the TCP options from SYN packet.
+	 * to generate cpl_pass_accept_req.
+	 */
+	memset(&tmp_opt, 0, sizeof(tmp_opt));
+	tcp_clear_options(&tmp_opt);
+	tcp_parse_options(skb, &tmp_opt, 0, 0, NULL);
+
+	req = (struct cpl_pass_accept_req *)__skb_push(skb, sizeof(*req));
+	memset(req, 0, sizeof(*req));
+	req->l2info = cpu_to_be16(V_SYN_INTF(intf) |
+			 V_SYN_MAC_IDX(G_RX_MACIDX(htonl(l2info))) |
+			 F_SYN_XACT_MATCH);
+	req->hdr_len = cpu_to_be32(V_SYN_RX_CHAN(G_RX_CHAN(htonl(l2info))) |
+				V_TCP_HDR_LEN(G_RX_TCPHDR_LEN(htons(hdr_len))) |
+				V_IP_HDR_LEN(G_RX_IPHDR_LEN(htons(hdr_len))) |
+				V_ETH_HDR_LEN(G_RX_ETHHDR_LEN(htonl(l2info))));
+	req->vlan = vlantag;
+	req->len = len;
+	req->tos_stid = cpu_to_be32(PASS_OPEN_TID(stid) |
+				    PASS_OPEN_TOS(tos));
+	req->tcpopt.mss = htons(tmp_opt.mss_clamp);
+	if (tmp_opt.wscale_ok)
+		req->tcpopt.wsf = tmp_opt.snd_wscale;
+	req->tcpopt.tstamp = tmp_opt.saw_tstamp;
+	if (tmp_opt.sack_ok)
+		req->tcpopt.sack = 1;
+	OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_PASS_ACCEPT_REQ, 0));
+	return;
+}
+
+static void send_fw_pass_open_req(struct c4iw_dev *dev, struct sk_buff *skb,
+				  __be32 laddr, __be16 lport,
+				  __be32 raddr, __be16 rport,
+				  u32 rcv_isn, u32 filter, u16 window,
+				  u32 rss_qid, u8 port_id)
+{
+	struct sk_buff *req_skb;
+	struct fw_ofld_connection_wr *req;
+	struct cpl_pass_accept_req *cpl = cplhdr(skb);
+
+	req_skb = alloc_skb(sizeof(struct fw_ofld_connection_wr), GFP_KERNEL);
+	req = (struct fw_ofld_connection_wr *)__skb_put(req_skb, sizeof(*req));
+	memset(req, 0, sizeof(*req));
+	req->op_compl = htonl(V_WR_OP(FW_OFLD_CONNECTION_WR) | FW_WR_COMPL(1));
+	req->len16_pkd = htonl(FW_WR_LEN16(DIV_ROUND_UP(sizeof(*req), 16)));
+	req->le.version_cpl = htonl(F_FW_OFLD_CONNECTION_WR_CPL);
+	req->le.filter = filter;
+	req->le.lport = lport;
+	req->le.pport = rport;
+	req->le.u.ipv4.lip = laddr;
+	req->le.u.ipv4.pip = raddr;
+	req->tcb.rcv_nxt = htonl(rcv_isn + 1);
+	req->tcb.rcv_adv = htons(window);
+	req->tcb.t_state_to_astid =
+		 htonl(V_FW_OFLD_CONNECTION_WR_T_STATE(TCP_SYN_RECV) |
+			V_FW_OFLD_CONNECTION_WR_RCV_SCALE(cpl->tcpopt.wsf) |
+			V_FW_OFLD_CONNECTION_WR_ASTID(
+			GET_PASS_OPEN_TID(ntohl(cpl->tos_stid))));
+
+	/*
+	 * We store the qid in opt2 which will be used by the firmware
+	 * to send us the wr response.
+	 */
+	req->tcb.opt2 = htonl(V_RSS_QUEUE(rss_qid));
+
+	/*
+	 * We initialize the MSS index in TCB to 0xF.
+	 * So that when driver sends cpl_pass_accept_rpl
+	 * TCB picks up the correct value. If this was 0
+	 * TP will ignore any value > 0 for MSS index.
+	 */
+	req->tcb.opt0 = cpu_to_be64(V_MSS_IDX(0xF));
+	req->cookie = cpu_to_be64((u64)skb);
+
+	set_wr_txq(req_skb, CPL_PRIORITY_CONTROL, port_id);
+	cxgb4_ofld_send(dev->rdev.lldi.ports[0], req_skb);
+}
+
+/*
+ * Handler for CPL_RX_PKT message. Need to handle cpl_rx_pkt
+ * messages when a filter is being used instead of server to
+ * redirect a syn packet. When packets hit filter they are redirected
+ * to the offload queue and driver tries to establish the connection
+ * using firmware work request.
+ */
+static int rx_pkt(struct c4iw_dev *dev, struct sk_buff *skb)
+{
+	int stid;
+	unsigned int filter;
+	struct ethhdr *eh = NULL;
+	struct vlan_ethhdr *vlan_eh = NULL;
+	struct iphdr *iph;
+	struct tcphdr *tcph;
+	struct rss_header *rss = (void *)skb->data;
+	struct cpl_rx_pkt *cpl = (void *)skb->data;
+	struct cpl_pass_accept_req *req = (void *)(rss + 1);
+	struct l2t_entry *e;
+	struct dst_entry *dst;
+	struct rtable *rt;
+	struct c4iw_ep *lep;
+	u16 window;
+	struct port_info *pi;
+	struct net_device *pdev;
+	u16 rss_qid;
+	int step;
+	u32 tx_chan;
+	struct neighbour *neigh;
+
+	/* Drop all non-SYN packets */
+	if (!(cpl->l2info & cpu_to_be32(F_RXF_SYN)))
+		goto reject;
+
+	/*
+	 * Drop all packets which did not hit the filter.
+	 * Unlikely to happen.
+	 */
+	if (!(rss->filter_hit && rss->filter_tid))
+		goto reject;
+
+	/*
+	 * Calculate the server tid from filter hit index from cpl_rx_pkt.
+	 */
+	stid = cpu_to_be32(rss->hash_val) - dev->rdev.lldi.tids->sftid_base
+					  + dev->rdev.lldi.tids->nstids;
+
+	lep = (struct c4iw_ep *)lookup_stid(dev->rdev.lldi.tids, stid);
+	if (!lep) {
+		PDBG("%s connect request on invalid stid %d\n", __func__, stid);
+		goto reject;
+	}
+
+	if (G_RX_ETHHDR_LEN(ntohl(cpl->l2info)) == ETH_HLEN) {
+		eh = (struct ethhdr *)(req + 1);
+		iph = (struct iphdr *)(eh + 1);
+	} else {
+		vlan_eh = (struct vlan_ethhdr *)(req + 1);
+		iph = (struct iphdr *)(vlan_eh + 1);
+		skb->vlan_tci = ntohs(cpl->vlan);
+	}
+
+	if (iph->version != 0x4)
+		goto reject;
+
+	tcph = (struct tcphdr *)(iph + 1);
+	skb_set_network_header(skb, (void *)iph - (void *)rss);
+	skb_set_transport_header(skb, (void *)tcph - (void *)rss);
+	skb_get(skb);
+
+	PDBG("%s lip 0x%x lport %u pip 0x%x pport %u tos %d\n", __func__,
+	     ntohl(iph->daddr), ntohs(tcph->dest), ntohl(iph->saddr),
+	     ntohs(tcph->source), iph->tos);
+
+	rt = find_route(dev, iph->daddr, iph->saddr, tcph->dest, tcph->source,
+			iph->tos);
+	if (!rt) {
+		pr_err("%s - failed to find dst entry!\n",
+		       __func__);
+		goto reject;
+	}
+	dst = &rt->dst;
+	neigh = dst_neigh_lookup_skb(dst, skb);
+
+	if (neigh->dev->flags & IFF_LOOPBACK) {
+		pdev = ip_dev_find(&init_net, iph->daddr);
+		e = cxgb4_l2t_get(dev->rdev.lldi.l2t, neigh,
+				    pdev, 0);
+		pi = (struct port_info *)netdev_priv(pdev);
+		tx_chan = cxgb4_port_chan(pdev);
+		dev_put(pdev);
+	} else {
+		e = cxgb4_l2t_get(dev->rdev.lldi.l2t, neigh,
+					neigh->dev, 0);
+		pi = (struct port_info *)netdev_priv(neigh->dev);
+		tx_chan = cxgb4_port_chan(neigh->dev);
+	}
+	if (!e) {
+		pr_err("%s - failed to allocate l2t entry!\n",
+		       __func__);
+		goto free_dst;
+	}
+
+	step = dev->rdev.lldi.nrxq / dev->rdev.lldi.nchan;
+	rss_qid = dev->rdev.lldi.rxq_ids[pi->port_id * step];
+	window = htons(tcph->window);
+
+	/* Calcuate filter portion for LE region. */
+	filter = cpu_to_be32(select_ntuple(dev, dst, e));
+
+	/*
+	 * Synthesize the cpl_pass_accept_req. We have everything except the
+	 * TID. Once firmware sends a reply with TID we update the TID field
+	 * in cpl and pass it through the regular cpl_pass_accept_req path.
+	 */
+	build_cpl_pass_accept_req(skb, stid, iph->tos);
+	send_fw_pass_open_req(dev, skb, iph->daddr, tcph->dest, iph->saddr,
+			      tcph->source, ntohl(tcph->seq), filter, window,
+			      rss_qid, pi->port_id);
+	cxgb4_l2t_release(e);
+free_dst:
+	dst_release(dst);
+reject:
 	return 0;
 }
 
···
 	[CPL_CLOSE_CON_RPL] = close_con_rpl,
 	[CPL_RDMA_TERMINATE] = terminate,
 	[CPL_FW4_ACK] = fw4_ack,
-	[CPL_FW6_MSG] = async_event
+	[CPL_FW6_MSG] = deferred_fw6_msg,
+	[CPL_RX_PKT] = rx_pkt
 };
 
 static void process_timeout(struct c4iw_ep *ep)
···
 	mutex_lock(&ep->com.mutex);
 	PDBG("%s ep %p tid %u state %d\n", __func__, ep, ep->hwtid,
 	     ep->com.state);
+	set_bit(TIMEDOUT, &ep->com.history);
 	switch (ep->com.state) {
 	case MPA_REQ_SENT:
 		__state_set(&ep->com, ABORTING);
···
 	PDBG("%s type %u\n", __func__, rpl->type);
 
 	switch (rpl->type) {
-	case 1:
+	case FW6_TYPE_WR_RPL:
 		ret = (int)((be64_to_cpu(rpl->data[0]) >> 8) & 0xff);
 		wr_waitp = (struct c4iw_wr_wait *)(__force unsigned long) rpl->data[1];
 		PDBG("%s wr_waitp %p ret %u\n", __func__, wr_waitp, ret);
···
 			c4iw_wake_up(wr_waitp, ret ? -ret : 0);
 		kfree_skb(skb);
 		break;
-	case 2:
+	case FW6_TYPE_CQE:
+	case FW6_TYPE_OFLD_CONNECTION_WR_RPL:
 		sched(dev, skb);
 		break;
 	default:
···
 	[CPL_RDMA_TERMINATE] = sched,
 	[CPL_FW4_ACK] = sched,
 	[CPL_SET_TCB_RPL] = set_tcb_rpl,
-	[CPL_FW6_MSG] = fw6_msg
+	[CPL_FW6_MSG] = fw6_msg,
+	[CPL_RX_PKT] = sched
 };
 
 int __init c4iw_cm_init(void)

drivers/infiniband/hw/cxgb4/device.c

···
 	seq_printf(seq, " DB State: %s Transitions %llu\n",
 		   db_state_str[dev->db_state],
 		   dev->rdev.stats.db_state_transitions);
+	seq_printf(seq, "TCAM_FULL: %10llu\n", dev->rdev.stats.tcam_full);
+	seq_printf(seq, "ACT_OFLD_CONN_FAILS: %10llu\n",
+		   dev->rdev.stats.act_ofld_conn_fails);
+	seq_printf(seq, "PAS_OFLD_CONN_FAILS: %10llu\n",
+		   dev->rdev.stats.pas_ofld_conn_fails);
 	return 0;
 }
 
···
 	dev->rdev.stats.db_empty = 0;
 	dev->rdev.stats.db_drop = 0;
 	dev->rdev.stats.db_state_transitions = 0;
+	dev->rdev.stats.tcam_full = 0;
+	dev->rdev.stats.act_ofld_conn_fails = 0;
+	dev->rdev.stats.pas_ofld_conn_fails = 0;
 	mutex_unlock(&dev->rdev.stats.lock);
 	return count;
 }
···
 	.read    = seq_read,
 	.llseek  = seq_lseek,
 	.write   = stats_clear,
+};
+
+static int dump_ep(int id, void *p, void *data)
+{
+	struct c4iw_ep *ep = p;
+	struct c4iw_debugfs_data *epd = data;
+	int space;
+	int cc;
+
+	space = epd->bufsize - epd->pos - 1;
+	if (space == 0)
+		return 1;
+
+	cc = snprintf(epd->buf + epd->pos, space,
+			"ep %p cm_id %p qp %p state %d flags 0x%lx history 0x%lx "
+			"hwtid %d atid %d %pI4:%d <-> %pI4:%d\n",
+			ep, ep->com.cm_id, ep->com.qp, (int)ep->com.state,
+			ep->com.flags, ep->com.history, ep->hwtid, ep->atid,
+			&ep->com.local_addr.sin_addr.s_addr,
+			ntohs(ep->com.local_addr.sin_port),
+			&ep->com.remote_addr.sin_addr.s_addr,
+			ntohs(ep->com.remote_addr.sin_port));
+	if (cc < space)
+		epd->pos += cc;
+	return 0;
+}
+
+static int dump_listen_ep(int id, void *p, void *data)
+{
+	struct c4iw_listen_ep *ep = p;
+	struct c4iw_debugfs_data *epd = data;
+	int space;
+	int cc;
+
+	space = epd->bufsize - epd->pos - 1;
+	if (space == 0)
+		return 1;
+
+	cc = snprintf(epd->buf + epd->pos, space,
+			"ep %p cm_id %p state %d flags 0x%lx stid %d backlog %d "
+			"%pI4:%d\n", ep, ep->com.cm_id, (int)ep->com.state,
+			ep->com.flags, ep->stid, ep->backlog,
+			&ep->com.local_addr.sin_addr.s_addr,
+			ntohs(ep->com.local_addr.sin_port));
+	if (cc < space)
+		epd->pos += cc;
+	return 0;
+}
+
+static int ep_release(struct inode *inode, struct file *file)
+{
+	struct c4iw_debugfs_data *epd = file->private_data;
+	if (!epd) {
+		pr_info("%s null qpd?\n", __func__);
+		return 0;
+	}
+	vfree(epd->buf);
+	kfree(epd);
+	return 0;
+}
+
+static int ep_open(struct inode *inode, struct file *file)
+{
+	struct c4iw_debugfs_data *epd;
+	int ret = 0;
+	int count = 1;
+
+	epd = kmalloc(sizeof(*epd), GFP_KERNEL);
+	if (!epd) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	epd->devp = inode->i_private;
+	epd->pos = 0;
+
+	spin_lock_irq(&epd->devp->lock);
+	idr_for_each(&epd->devp->hwtid_idr, count_idrs, &count);
+	idr_for_each(&epd->devp->atid_idr, count_idrs, &count);
+	idr_for_each(&epd->devp->stid_idr, count_idrs, &count);
+	spin_unlock_irq(&epd->devp->lock);
+
+	epd->bufsize = count * 160;
+	epd->buf = vmalloc(epd->bufsize);
+	if (!epd->buf) {
+		ret = -ENOMEM;
+		goto err1;
+	}
+
+	spin_lock_irq(&epd->devp->lock);
+	idr_for_each(&epd->devp->hwtid_idr, dump_ep, epd);
+	idr_for_each(&epd->devp->atid_idr, dump_ep, epd);
+	idr_for_each(&epd->devp->stid_idr, dump_listen_ep, epd);
+	spin_unlock_irq(&epd->devp->lock);
+
+	file->private_data = epd;
+	goto out;
+err1:
+	kfree(epd);
+out:
+	return ret;
+}
+
+static const struct file_operations ep_debugfs_fops = {
+	.owner   = THIS_MODULE,
+	.open    = ep_open,
+	.release = ep_release,
+	.read    = debugfs_read,
 };
 
 static int setup_debugfs(struct c4iw_dev *devp)
···
 
 	de = debugfs_create_file("stats", S_IWUSR, devp->debugfs_root,
 			(void *)devp, &stats_debugfs_fops);
+	if (de && de->d_inode)
+		de->d_inode->i_size = 4096;
+
+	de = debugfs_create_file("eps", S_IWUSR, devp->debugfs_root,
+			(void *)devp, &ep_debugfs_fops);
 	if (de && de->d_inode)
 		de->d_inode->i_size = 4096;
 
···
 	idr_destroy(&ctx->dev->cqidr);
 	idr_destroy(&ctx->dev->qpidr);
 	idr_destroy(&ctx->dev->mmidr);
+	idr_destroy(&ctx->dev->hwtid_idr);
+	idr_destroy(&ctx->dev->stid_idr);
+	idr_destroy(&ctx->dev->atid_idr);
 	iounmap(ctx->dev->rdev.oc_mw_kva);
 	ib_dealloc_device(&ctx->dev->ibdev);
 	ctx->dev = NULL;
···
 	idr_init(&devp->cqidr);
 	idr_init(&devp->qpidr);
 	idr_init(&devp->mmidr);
+	idr_init(&devp->hwtid_idr);
+	idr_init(&devp->stid_idr);
+	idr_init(&devp->atid_idr);
 	spin_lock_init(&devp->lock);
 	mutex_init(&devp->rdev.stats.lock);
 	mutex_init(&devp->db_mutex);
···
 	return ctx;
 }
 
+static inline struct sk_buff *copy_gl_to_skb_pkt(const struct pkt_gl *gl,
+						 const __be64 *rsp,
+						 u32 pktshift)
+{
+	struct sk_buff *skb;
+
+	/*
+	 * Allocate space for cpl_pass_accept_req which will be synthesized by
+	 * driver. Once the driver synthesizes the request the skb will go
+	 * through the regular cpl_pass_accept_req processing.
+	 * The math here assumes sizeof cpl_pass_accept_req >= sizeof
+	 * cpl_rx_pkt.
+	 */
+	skb = alloc_skb(gl->tot_len + sizeof(struct cpl_pass_accept_req) +
+			sizeof(struct rss_header) - pktshift, GFP_ATOMIC);
+	if (unlikely(!skb))
+		return NULL;
+
+	 __skb_put(skb, gl->tot_len + sizeof(struct cpl_pass_accept_req) +
+		   sizeof(struct rss_header) - pktshift);
+
+	/*
+	 * This skb will contain:
+	 *   rss_header from the rspq descriptor (1 flit)
+	 *   cpl_rx_pkt struct from the rspq descriptor (2 flits)
+	 *   space for the difference between the size of an
+	 *      rx_pkt and pass_accept_req cpl (1 flit)
+	 *   the packet data from the gl
+	 */
+	skb_copy_to_linear_data(skb, rsp, sizeof(struct cpl_pass_accept_req) +
+				sizeof(struct rss_header));
+	skb_copy_to_linear_data_offset(skb, sizeof(struct rss_header) +
+				       sizeof(struct cpl_pass_accept_req),
+				       gl->va + pktshift,
+				       gl->tot_len - pktshift);
+	return skb;
+}
+
+static inline int recv_rx_pkt(struct c4iw_dev *dev, const struct pkt_gl *gl,
+			   const __be64 *rsp)
+{
+	unsigned int opcode = *(u8 *)rsp;
+	struct sk_buff *skb;
+
+	if (opcode != CPL_RX_PKT)
+		goto out;
+
+	skb = copy_gl_to_skb_pkt(gl , rsp, dev->rdev.lldi.sge_pktshift);
+	if (skb == NULL)
+		goto out;
+
+	if (c4iw_handlers[opcode] == NULL) {
+		pr_info("%s no handler opcode 0x%x...\n", __func__,
+		       opcode);
+		kfree_skb(skb);
+		goto out;
+	}
+	c4iw_handlers[opcode](dev, skb);
+	return 1;
+out:
+	return 0;
+}
+
 static int c4iw_uld_rx_handler(void *handle, const __be64 *rsp,
 			const struct pkt_gl *gl)
 {
 	struct uld_ctx *ctx = handle;
 	struct c4iw_dev *dev = ctx->dev;
 	struct sk_buff *skb;
-	const struct cpl_act_establish *rpl;
-	unsigned int opcode;
+	u8 opcode;
 
 	if (gl == NULL) {
 		/* omit RSS and rsp_ctrl at end of descriptor */
···
 		u32 qid = be32_to_cpu(rc->pldbuflen_qid);
 		c4iw_ev_handler(dev, qid);
 		return 0;
+	} else if (unlikely(*(u8 *)rsp != *(u8 *)gl->va)) {
+		if (recv_rx_pkt(dev, gl, rsp))
+			return 0;
+
+		pr_info("%s: unexpected FL contents at %p, " \
+		       "RSS %#llx, FL %#llx, len %u\n",
+		       pci_name(ctx->lldi.pdev), gl->va,
+		       (unsigned long long)be64_to_cpu(*rsp),
+		       (unsigned long long)be64_to_cpu(*(u64 *)gl->va),
+		       gl->tot_len);
+
+		return 0;
 	} else {
 		skb = cxgb4_pktgl_to_skb(gl, 128, 128);
 		if (unlikely(!skb))
 			goto nomem;
 	}
 
-	rpl = cplhdr(skb);
-	opcode = rpl->ot.opcode;
-
+	opcode = *(u8 *)rsp;
 	if (c4iw_handlers[opcode])
 		c4iw_handlers[opcode](dev, skb);
 	else
-		printk(KERN_INFO "%s no handler opcode 0x%x...\n", __func__,
+		pr_info("%s no handler opcode 0x%x...\n", __func__,
 		       opcode);
 
 	return 0;

drivers/infiniband/hw/cxgb4/iw_cxgb4.h

···
 	u64  db_empty;
 	u64  db_drop;
 	u64  db_state_transitions;
+	u64  tcam_full;
+	u64  act_ofld_conn_fails;
+	u64  pas_ofld_conn_fails;
 };
 
 struct c4iw_rdev {
···
 	struct dentry *debugfs_root;
 	enum db_state db_state;
 	int qpcnt;
+	struct idr hwtid_idr;
+	struct idr atid_idr;
+	struct idr stid_idr;
 };
 
 static inline struct c4iw_dev *to_c4iw_dev(struct ib_device *ibdev)
···
 	CLOSE_SENT		= 3,
 };
 
+enum c4iw_ep_history {
+	ACT_OPEN_REQ            = 0,
+	ACT_OFLD_CONN           = 1,
+	ACT_OPEN_RPL            = 2,
+	ACT_ESTAB               = 3,
+	PASS_ACCEPT_REQ         = 4,
+	PASS_ESTAB              = 5,
+	ABORT_UPCALL            = 6,
+	ESTAB_UPCALL            = 7,
+	CLOSE_UPCALL            = 8,
+	ULP_ACCEPT              = 9,
+	ULP_REJECT              = 10,
+	TIMEDOUT                = 11,
+	PEER_ABORT              = 12,
+	PEER_CLOSE              = 13,
+	CONNREQ_UPCALL          = 14,
+	ABORT_CONN              = 15,
+	DISCONN_UPCALL          = 16,
+	EP_DISC_CLOSE           = 17,
+	EP_DISC_ABORT           = 18,
+	CONN_RPL_UPCALL         = 19,
+	ACT_RETRY_NOMEM         = 20,
+	ACT_RETRY_INUSE         = 21
+};
+
 struct c4iw_ep_common {
 	struct iw_cm_id *cm_id;
 	struct c4iw_qp *qp;
···
 	struct sockaddr_in remote_addr;
 	struct c4iw_wr_wait wr_wait;
 	unsigned long flags;
+	unsigned long history;
 };
 
 struct c4iw_listen_ep {
···
 	u8 tos;
 	u8 retry_with_mpa_v1;
 	u8 tried_with_mpa_v1;
+	unsigned int retry_count;
 };
 
 static inline struct c4iw_ep *to_ep(struct iw_cm_id *cm_id)

drivers/infiniband/ulp/ipoib/ipoib_cm.c

···
 		dev->trans_start = jiffies;
 		++tx->tx_head;
 
+		skb_orphan(skb);
+		skb_dst_drop(skb);
+
 		if (++priv->tx_outstanding == ipoib_sendq_size) {
 			ipoib_dbg(priv, "TX ring 0x%x full, stopping kernel net queue\n",
 				  tx->qp->qp_num);

drivers/infiniband/ulp/ipoib/ipoib_ib.c

···
 
 		address->last_send = priv->tx_head;
 		++priv->tx_head;
-		skb_orphan(skb);
 
+		skb_orphan(skb);
+		skb_dst_drop(skb);
 	}
 
 	if (unlikely(priv->tx_outstanding > MAX_SEND_CQE))

drivers/net/ethernet/chelsio/cxgb4/cxgb4.h

···
 #ifndef __CXGB4_H__
 #define __CXGB4_H__
 
+#include "t4_hw.h"
+
 #include <linux/bitops.h>
 #include <linux/cache.h>
 #include <linux/interrupt.h>
···
 struct tp_params {
 	unsigned int ntxchan;        /* # of Tx channels */
 	unsigned int tre;            /* log2 of core clocks per TP tick */
+	unsigned short tx_modq_map;  /* TX modulation scheduler queue to */
+				     /* channel map */
 
 	uint32_t dack_re;            /* DACK timer resolution */
 	unsigned short tx_modq[NCHAN];	/* channel to modulation queue map */
···
 	struct net_device *port[MAX_NPORTS];
 	u8 chan_map[NCHAN];                   /* channel -> port map */
 
+	u32 filter_mode;
 	unsigned int l2t_start;
 	unsigned int l2t_end;
 	struct l2t_data *l2t;
···
 	struct dentry *debugfs_root;
 
 	spinlock_t stats_lock;
+};
+
+/* Defined bit width of user definable filter tuples
+ */
+#define ETHTYPE_BITWIDTH 16
+#define FRAG_BITWIDTH 1
+#define MACIDX_BITWIDTH 9
+#define FCOE_BITWIDTH 1
+#define IPORT_BITWIDTH 3
+#define MATCHTYPE_BITWIDTH 3
+#define PROTO_BITWIDTH 8
+#define TOS_BITWIDTH 8
+#define PF_BITWIDTH 8
+#define VF_BITWIDTH 8
+#define IVLAN_BITWIDTH 16
+#define OVLAN_BITWIDTH 16
+
+/* Filter matching rules.  These consist of a set of ingress packet field
+ * (value, mask) tuples.  The associated ingress packet field matches the
+ * tuple when ((field & mask) == value).  (Thus a wildcard "don't care" field
+ * rule can be constructed by specifying a tuple of (0, 0).)  A filter rule
+ * matches an ingress packet when all of the individual individual field
+ * matching rules are true.
+ *
+ * Partial field masks are always valid, however, while it may be easy to
+ * understand their meanings for some fields (e.g. IP address to match a
+ * subnet), for others making sensible partial masks is less intuitive (e.g.
+ * MPS match type) ...
+ *
+ * Most of the following data structures are modeled on T4 capabilities.
+ * Drivers for earlier chips use the subsets which make sense for those chips.
+ * We really need to come up with a hardware-independent mechanism to
+ * represent hardware filter capabilities ...
+ */
+struct ch_filter_tuple {
+	/* Compressed header matching field rules.  The TP_VLAN_PRI_MAP
+	 * register selects which of these fields will participate in the
+	 * filter match rules -- up to a maximum of 36 bits.  Because
+	 * TP_VLAN_PRI_MAP is a global register, all filters must use the same
+	 * set of fields.
+	 */
+	uint32_t ethtype:ETHTYPE_BITWIDTH;      /* Ethernet type */
+	uint32_t frag:FRAG_BITWIDTH;            /* IP fragmentation header */
+	uint32_t ivlan_vld:1;                   /* inner VLAN valid */
+	uint32_t ovlan_vld:1;                   /* outer VLAN valid */
+	uint32_t pfvf_vld:1;                    /* PF/VF valid */
+	uint32_t macidx:MACIDX_BITWIDTH;        /* exact match MAC index */
+	uint32_t fcoe:FCOE_BITWIDTH;            /* FCoE packet */
+	uint32_t iport:IPORT_BITWIDTH;          /* ingress port */
+	uint32_t matchtype:MATCHTYPE_BITWIDTH;  /* MPS match type */
+	uint32_t proto:PROTO_BITWIDTH;          /* protocol type */
+	uint32_t tos:TOS_BITWIDTH;              /* TOS/Traffic Type */
+	uint32_t pf:PF_BITWIDTH;                /* PCI-E PF ID */
+	uint32_t vf:VF_BITWIDTH;                /* PCI-E VF ID */
+	uint32_t ivlan:IVLAN_BITWIDTH;          /* inner VLAN */
+	uint32_t ovlan:OVLAN_BITWIDTH;          /* outer VLAN */
+
+	/* Uncompressed header matching field rules.  These are always
+	 * available for field rules.
+	 */
+	uint8_t lip[16];        /* local IP address (IPv4 in [3:0]) */
+	uint8_t fip[16];        /* foreign IP address (IPv4 in [3:0]) */
+	uint16_t lport;         /* local port */
+	uint16_t fport;         /* foreign port */
+};
+
+/* A filter ioctl command.
+ */
+struct ch_filter_specification {
+	/* Administrative fields for filter.
+	 */
+	uint32_t hitcnts:1;     /* count filter hits in TCB */
+	uint32_t prio:1;        /* filter has priority over active/server */
+
+	/* Fundamental filter typing.  This is the one element of filter
+	 * matching that doesn't exist as a (value, mask) tuple.
+	 */
+	uint32_t type:1;        /* 0 => IPv4, 1 => IPv6 */
+
+	/* Packet dispatch information.  Ingress packets which match the
+	 * filter rules will be dropped, passed to the host or switched back
+	 * out as egress packets.
+	 */
+	uint32_t action:2;      /* drop, pass, switch */
+
+	uint32_t rpttid:1;      /* report TID in RSS hash field */
+
+	uint32_t dirsteer:1;    /* 0 => RSS, 1 => steer to iq */
+	uint32_t iq:10;         /* ingress queue */
+
+	uint32_t maskhash:1;    /* dirsteer=0: store RSS hash in TCB */
+	uint32_t dirsteerhash:1;/* dirsteer=1: 0 => TCB contains RSS hash */
+				/*             1 => TCB contains IQ ID */
+
+	/* Switch proxy/rewrite fields.  An ingress packet which matches a
+	 * filter with "switch" set will be looped back out as an egress
+	 * packet -- potentially with some Ethernet header rewriting.
+	 */
+	uint32_t eport:2;       /* egress port to switch packet out */
+	uint32_t newdmac:1;     /* rewrite destination MAC address */
+	uint32_t newsmac:1;     /* rewrite source MAC address */
+	uint32_t newvlan:2;     /* rewrite VLAN Tag */
+	uint8_t dmac[ETH_ALEN]; /* new destination MAC address */
+	uint8_t smac[ETH_ALEN]; /* new source MAC address */
+	uint16_t vlan;          /* VLAN Tag to insert */
+
+	/* Filter rule value/mask pairs.
+	 */
+	struct ch_filter_tuple val;
+	struct ch_filter_tuple mask;
+};
+
+enum {
+	FILTER_PASS = 0,        /* default */
+	FILTER_DROP,
+	FILTER_SWITCH
+};
+
+enum {
+	VLAN_NOCHANGE = 0,      /* default */
+	VLAN_REMOVE,
+	VLAN_INSERT,
+	VLAN_REWRITE
 };
 
 static inline u32 t4_read_reg(struct adapter *adap, u32 reg_addr)
···
 void t4_write_indirect(struct adapter *adap, unsigned int addr_reg,
 		       unsigned int data_reg, const u32 *vals,
 		       unsigned int nregs, unsigned int start_idx);
+void t4_read_indirect(struct adapter *adap, unsigned int addr_reg,
+		      unsigned int data_reg, u32 *vals, unsigned int nregs,
+		      unsigned int start_idx);
+
+struct fw_filter_wr;
+
 void t4_intr_enable(struct adapter *adapter);
 void t4_intr_disable(struct adapter *adapter);
 int t4_slow_intr_handler(struct adapter *adapter);
···
 			 struct tp_tcp_stats *v6);
 void t4_load_mtus(struct adapter *adap, const unsigned short *mtus,
 		  const unsigned short *alpha, const unsigned short *beta);
+
+void t4_mk_filtdelwr(unsigned int ftid, struct fw_filter_wr *wr, int qid);
 
 void t4_wol_magic_enable(struct adapter *adap, unsigned int port,
 			 const u8 *addr);

drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c

···
 	MIN_FL_ENTRIES       = 16
 };
 
+/* Host shadow copy of ingress filter entry.  This is in host native format
+ * and doesn't match the ordering or bit order, etc. of the hardware of the
+ * firmware command.  The use of bit-field structure elements is purely to
+ * remind ourselves of the field size limitations and save memory in the case
+ * where the filter table is large.
+ */
+struct filter_entry {
+	/* Administrative fields for filter.
+	 */
+	u32 valid:1;            /* filter allocated and valid */
+	u32 locked:1;           /* filter is administratively locked */
+
+	u32 pending:1;          /* filter action is pending firmware reply */
+	u32 smtidx:8;           /* Source MAC Table index for smac */
+	struct l2t_entry *l2t;  /* Layer Two Table entry for dmac */
+
+	/* The filter itself.  Most of this is a straight copy of information
+	 * provided by the extended ioctl().  Some fields are translated to
+	 * internal forms -- for instance the Ingress Queue ID passed in from
+	 * the ioctl() is translated into the Absolute Ingress Queue ID.
+	 */
+	struct ch_filter_specification fs;
+};
+
 #define DFLT_MSG_ENABLE (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK | \
 			 NETIF_MSG_TIMER | NETIF_MSG_IFDOWN | NETIF_MSG_IFUP |\
 			 NETIF_MSG_RX_ERR | NETIF_MSG_TX_ERR)
···
 };
 
 static unsigned int tp_vlan_pri_map = TP_VLAN_PRI_MAP_DEFAULT;
+
+module_param(tp_vlan_pri_map, uint, 0644);
+MODULE_PARM_DESC(tp_vlan_pri_map, "global compressed filter configuration");
 
 static struct dentry *cxgb4_debugfs_root;
 
···
 	return ret;
 }
 
-/*
- * Response queue handler for the FW event queue.
+/* Clear a filter and release any of its resources that we own.  This also
+ * clears the filter's "pending" status.
+ */
+static void clear_filter(struct adapter *adap, struct filter_entry *f)
+{
+	/* If the new or old filter have loopback rewriteing rules then we'll
+	 * need to free any existing Layer Two Table (L2T) entries of the old
+	 * filter rule.  The firmware will handle freeing up any Source MAC
+	 * Table (SMT) entries used for rewriting Source MAC Addresses in
+	 * loopback rules.
+	 */
+	if (f->l2t)
+		cxgb4_l2t_release(f->l2t);
+
+	/* The zeroing of the filter rule below clears the filter valid,
+	 * pending, locked flags, l2t pointer, etc. so it's all we need for
+	 * this operation.
+	 */
+	memset(f, 0, sizeof(*f));
+}
+
+/* Handle a filter write/deletion reply.
+ */
+static void filter_rpl(struct adapter *adap, const struct cpl_set_tcb_rpl *rpl)
+{
+	unsigned int idx = GET_TID(rpl);
+	unsigned int nidx = idx - adap->tids.ftid_base;
+	unsigned int ret;
+	struct filter_entry *f;
+
+	if (idx >= adap->tids.ftid_base && nidx <
+	   (adap->tids.nftids + adap->tids.nsftids)) {
+		idx = nidx;
+		ret = GET_TCB_COOKIE(rpl->cookie);
+		f = &adap->tids.ftid_tab[idx];
+
+		if (ret == FW_FILTER_WR_FLT_DELETED) {
+			/* Clear the filter when we get confirmation from the
+			 * hardware that the filter has been deleted.
+			 */
+			clear_filter(adap, f);
+		} else if (ret == FW_FILTER_WR_SMT_TBL_FULL) {
+			dev_err(adap->pdev_dev, "filter %u setup failed due to full SMT\n",
+				idx);
+			clear_filter(adap, f);
+		} else if (ret == FW_FILTER_WR_FLT_ADDED) {
+			f->smtidx = (be64_to_cpu(rpl->oldval) >> 24) & 0xff;
+			f->pending = 0;  /* asynchronous setup completed */
+			f->valid = 1;
+		} else {
+			/* Something went wrong.  Issue a warning about the
+			 * problem and clear everything out.
+			 */
+			dev_err(adap->pdev_dev, "filter %u setup failed with error %u\n",
+				idx, ret);
+			clear_filter(adap, f);
+		}
+	}
+}
+
+/* Response queue handler for the FW event queue.
  */
 static int fwevtq_handler(struct sge_rspq *q, const __be64 *rsp,
 			  const struct pkt_gl *gl)
···
 		const struct cpl_l2t_write_rpl *p = (void *)rsp;
 
 		do_l2t_write_rpl(q->adap, p);
+	} else if (opcode == CPL_SET_TCB_RPL) {
+		const struct cpl_set_tcb_rpl *p = (void *)rsp;
+
+		filter_rpl(q->adap, p);
 	} else
 		dev_err(q->adap->pdev_dev,
 			"unexpected CPL %#x on FW event queue\n", opcode);
···
 		vfree(addr);
 	else
 		kfree(addr);
+}
+
+/* Send a Work Request to write the filter at a specified index.  We construct
+ * a Firmware Filter Work Request to have the work done and put the indicated
+ * filter into "pending" mode which will prevent any further actions against
+ * it till we get a reply from the firmware on the completion status of the
+ * request.
+ */
+static int set_filter_wr(struct adapter *adapter, int fidx)
+{
+	struct filter_entry *f = &adapter->tids.ftid_tab[fidx];
+	struct sk_buff *skb;
+	struct fw_filter_wr *fwr;
+	unsigned int ftid;
+
+	/* If the new filter requires loopback Destination MAC and/or VLAN
+	 * rewriting then we need to allocate a Layer 2 Table (L2T) entry for
+	 * the filter.
+	 */
+	if (f->fs.newdmac || f->fs.newvlan) {
+		/* allocate L2T entry for new filter */
+		f->l2t = t4_l2t_alloc_switching(adapter->l2t);
+		if (f->l2t == NULL)
+			return -EAGAIN;
+		if (t4_l2t_set_switching(adapter, f->l2t, f->fs.vlan,
+					f->fs.eport, f->fs.dmac)) {
+			cxgb4_l2t_release(f->l2t);
+			f->l2t = NULL;
+			return -ENOMEM;
+		}
+	}
+
+	ftid = adapter->tids.ftid_base + fidx;
+
+	skb = alloc_skb(sizeof(*fwr), GFP_KERNEL | __GFP_NOFAIL);
+	fwr = (struct fw_filter_wr *)__skb_put(skb, sizeof(*fwr));
+	memset(fwr, 0, sizeof(*fwr));
+
+	/* It would be nice to put most of the following in t4_hw.c but most
+	 * of the work is translating the cxgbtool ch_filter_specification
+	 * into the Work Request and the definition of that structure is
+	 * currently in cxgbtool.h which isn't appropriate to pull into the
+	 * common code.  We may eventually try to come up with a more neutral
+	 * filter specification structure but for now it's easiest to simply
+	 * put this fairly direct code in line ...
+	 */
+	fwr->op_pkd = htonl(FW_WR_OP(FW_FILTER_WR));
+	fwr->len16_pkd = htonl(FW_WR_LEN16(sizeof(*fwr)/16));
+	fwr->tid_to_iq =
+		htonl(V_FW_FILTER_WR_TID(ftid) |
+		      V_FW_FILTER_WR_RQTYPE(f->fs.type) |
+		      V_FW_FILTER_WR_NOREPLY(0) |
+		      V_FW_FILTER_WR_IQ(f->fs.iq));
+	fwr->del_filter_to_l2tix =
+		htonl(V_FW_FILTER_WR_RPTTID(f->fs.rpttid) |
+		      V_FW_FILTER_WR_DROP(f->fs.action == FILTER_DROP) |
+		      V_FW_FILTER_WR_DIRSTEER(f->fs.dirsteer) |
+		      V_FW_FILTER_WR_MASKHASH(f->fs.maskhash) |
+		      V_FW_FILTER_WR_DIRSTEERHASH(f->fs.dirsteerhash) |
+		      V_FW_FILTER_WR_LPBK(f->fs.action == FILTER_SWITCH) |
+		      V_FW_FILTER_WR_DMAC(f->fs.newdmac) |
+		      V_FW_FILTER_WR_SMAC(f->fs.newsmac) |
+		      V_FW_FILTER_WR_INSVLAN(f->fs.newvlan == VLAN_INSERT ||
+					     f->fs.newvlan == VLAN_REWRITE) |
+		      V_FW_FILTER_WR_RMVLAN(f->fs.newvlan == VLAN_REMOVE ||
+					    f->fs.newvlan == VLAN_REWRITE) |
+		      V_FW_FILTER_WR_HITCNTS(f->fs.hitcnts) |
+		      V_FW_FILTER_WR_TXCHAN(f->fs.eport) |
+		      V_FW_FILTER_WR_PRIO(f->fs.prio) |
+		      V_FW_FILTER_WR_L2TIX(f->l2t ? f->l2t->idx : 0));
+	fwr->ethtype = htons(f->fs.val.ethtype);
+	fwr->ethtypem = htons(f->fs.mask.ethtype);
+	fwr->frag_to_ovlan_vldm =
+		(V_FW_FILTER_WR_FRAG(f->fs.val.frag) |
+		 V_FW_FILTER_WR_FRAGM(f->fs.mask.frag) |
+		 V_FW_FILTER_WR_IVLAN_VLD(f->fs.val.ivlan_vld) |
+		 V_FW_FILTER_WR_OVLAN_VLD(f->fs.val.ovlan_vld) |
+		 V_FW_FILTER_WR_IVLAN_VLDM(f->fs.mask.ivlan_vld) |
+		 V_FW_FILTER_WR_OVLAN_VLDM(f->fs.mask.ovlan_vld));
+	fwr->smac_sel = 0;
+	fwr->rx_chan_rx_rpl_iq =
+		htons(V_FW_FILTER_WR_RX_CHAN(0) |
+		      V_FW_FILTER_WR_RX_RPL_IQ(adapter->sge.fw_evtq.abs_id));
+	fwr->maci_to_matchtypem =
+		htonl(V_FW_FILTER_WR_MACI(f->fs.val.macidx) |
+		      V_FW_FILTER_WR_MACIM(f->fs.mask.macidx) |
+		      V_FW_FILTER_WR_FCOE(f->fs.val.fcoe) |
+		      V_FW_FILTER_WR_FCOEM(f->fs.mask.fcoe) |
+		      V_FW_FILTER_WR_PORT(f->fs.val.iport) |
+		      V_FW_FILTER_WR_PORTM(f->fs.mask.iport) |
+		      V_FW_FILTER_WR_MATCHTYPE(f->fs.val.matchtype) |
+		      V_FW_FILTER_WR_MATCHTYPEM(f->fs.mask.matchtype));
+	fwr->ptcl = f->fs.val.proto;
+	fwr->ptclm = f->fs.mask.proto;
+	fwr->ttyp = f->fs.val.tos;
+	fwr->ttypm = f->fs.mask.tos;
+	fwr->ivlan = htons(f->fs.val.ivlan);
+	fwr->ivlanm = htons(f->fs.mask.ivlan);
+	fwr->ovlan = htons(f->fs.val.ovlan);
+	fwr->ovlanm = htons(f->fs.mask.ovlan);
+	memcpy(fwr->lip, f->fs.val.lip, sizeof(fwr->lip));
+	memcpy(fwr->lipm, f->fs.mask.lip, sizeof(fwr->lipm));
+	memcpy(fwr->fip, f->fs.val.fip, sizeof(fwr->fip));
+	memcpy(fwr->fipm, f->fs.mask.fip, sizeof(fwr->fipm));
+	fwr->lp = htons(f->fs.val.lport);
+	fwr->lpm = htons(f->fs.mask.lport);
+	fwr->fp = htons(f->fs.val.fport);
+	fwr->fpm = htons(f->fs.mask.fport);
+	if (f->fs.newsmac)
+		memcpy(fwr->sma, f->fs.smac, sizeof(fwr->sma));
+
+	/* Mark the filter as "pending" and ship off the Filter Work Request.
+	 * When we get the Work Request Reply we'll clear the pending status.
+	 */
+	f->pending = 1;
+	set_wr_txq(skb, CPL_PRIORITY_CONTROL, f->fs.val.iport & 0x3);
+	t4_ofld_send(adapter, skb);
+	return 0;
+}
+
+/* Delete the filter at a specified index.
+ */
+static int del_filter_wr(struct adapter *adapter, int fidx)
+{
+	struct filter_entry *f = &adapter->tids.ftid_tab[fidx];
+	struct sk_buff *skb;
+	struct fw_filter_wr *fwr;
+	unsigned int len, ftid;
+
+	len = sizeof(*fwr);
+	ftid = adapter->tids.ftid_base + fidx;
+
+	skb = alloc_skb(len, GFP_KERNEL | __GFP_NOFAIL);
+	fwr = (struct fw_filter_wr *)__skb_put(skb, len);
+	t4_mk_filtdelwr(ftid, fwr, adapter->sge.fw_evtq.abs_id);
+
+	/* Mark the filter as "pending" and ship off the Filter Work Request.
+	 * When we get the Work Request Reply we'll clear the pending status.
+	 */
+	f->pending = 1;
+	t4_mgmt_tx(adapter, skb);
+	return 0;
 }
 
 static inline int is_offload(const struct adapter *adap)
···
 	if (t->afree) {
 		union aopen_entry *p = t->afree;
 
-		atid = p - t->atid_tab;
+		atid = (p - t->atid_tab) + t->atid_base;
 		t->afree = p->next;
 		p->data = data;
 		t->atids_in_use++;
···
  */
 void cxgb4_free_atid(struct tid_info *t, unsigned int atid)
 {
-	union aopen_entry *p = &t->atid_tab[atid];
+	union aopen_entry *p = &t->atid_tab[atid - t->atid_base];
 
 	spin_lock_bh(&t->atid_lock);
 	p->next = t->afree;
···
 }
 EXPORT_SYMBOL(cxgb4_alloc_stid);
 
-/*
- * Release a server TID.
+/* Allocate a server filter TID and set it to the supplied value.
+ */
+int cxgb4_alloc_sftid(struct tid_info *t, int family, void *data)
+{
+	int stid;
+
+	spin_lock_bh(&t->stid_lock);
+	if (family == PF_INET) {
+		stid = find_next_zero_bit(t->stid_bmap,
+				t->nstids + t->nsftids, t->nstids);
+		if (stid < (t->nstids + t->nsftids))
+			__set_bit(stid, t->stid_bmap);
+		else
+			stid = -1;
+	} else {
+		stid = -1;
+	}
+	if (stid >= 0) {
+		t->stid_tab[stid].data = data;
+		stid += t->stid_base;
+		t->stids_in_use++;
+	}
+	spin_unlock_bh(&t->stid_lock);
+	return stid;
+}
+EXPORT_SYMBOL(cxgb4_alloc_sftid);
+
+/* Release a server TID.
  */
 void cxgb4_free_stid(struct tid_info *t, unsigned int stid, int family)
 {
···
 static int tid_init(struct tid_info *t)
 {
 	size_t size;
+	unsigned int stid_bmap_size;
 	unsigned int natids = t->natids;
 
-	size = t->ntids * sizeof(*t->tid_tab) + natids * sizeof(*t->atid_tab) +
+	stid_bmap_size = BITS_TO_LONGS(t->nstids + t->nsftids);
+	size = t->ntids * sizeof(*t->tid_tab) +
+	       natids * sizeof(*t->atid_tab) +
 	       t->nstids * sizeof(*t->stid_tab) +
-	       BITS_TO_LONGS(t->nstids) * sizeof(long);
+	       t->nsftids * sizeof(*t->stid_tab) +
+	       stid_bmap_size * sizeof(long) +
+	       t->nftids * sizeof(*t->ftid_tab) +
+	       t->nsftids * sizeof(*t->ftid_tab);
+
 	t->tid_tab = t4_alloc_mem(size);
 	if (!t->tid_tab)
 		return -ENOMEM;
 
 	t->atid_tab = (union aopen_entry *)&t->tid_tab[t->ntids];
 	t->stid_tab = (struct serv_entry *)&t->atid_tab[natids];
-	t->stid_bmap = (unsigned long *)&t->stid_tab[t->nstids];
+	t->stid_bmap = (unsigned long *)&t->stid_tab[t->nstids + t->nsftids];
+	t->ftid_tab = (struct filter_entry *)&t->stid_bmap[stid_bmap_size];
 	spin_lock_init(&t->stid_lock);
 	spin_lock_init(&t->atid_lock);
 
···
 			t->atid_tab[natids - 1].next = &t->atid_tab[natids];
 		t->afree = t->atid_tab;
 	}
-	bitmap_zero(t->stid_bmap, t->nstids);
+	bitmap_zero(t->stid_bmap, t->nstids + t->nsftids);
 	return 0;
 }
 
···
  *	Returns <0 on error and one of the %NET_XMIT_* values on success.
  */
 int cxgb4_create_server(const struct net_device *dev, unsigned int stid,
-			__be32 sip, __be16 sport, unsigned int queue)
+			__be32 sip, __be16 sport, __be16 vlan,
+			unsigned int queue)
 {
 	unsigned int chan;
 	struct sk_buff *skb;
···
 {
 	void *handle;
 	struct cxgb4_lld_info lli;
+	unsigned short i;
 
 	lli.pdev = adap->pdev;
 	lli.l2t = adap->l2t;
···
 	lli.ucq_density = 1 << QUEUESPERPAGEPF0_GET(
 			t4_read_reg(adap, SGE_INGRESS_QUEUES_PER_PAGE_PF) >>
 			(adap->fn * 4));
+	lli.filt_mode = adap->filter_mode;
+	/* MODQ_REQ_MAP sets queues 0-3 to chan 0-3 */
+	for (i = 0; i < NCHAN; i++)
+		lli.tx_modq[i] = i;
 	lli.gts_reg = adap->regs + MYPF_REG(SGE_PF_GTS);
 	lli.db_reg = adap->regs + MYPF_REG(SGE_PF_KDOORBELL);
 	lli.fw_vers = adap->params.fw_vers;
 	lli.dbfifo_int_thresh = dbfifo_int_thresh;
+	lli.sge_pktshift = adap->sge.pktshift;
+	lli.enable_fw_ofld_conn = adap->flags & FW_OFLD_CONN;
 
 	handle = ulds[uld].add(&lli);
 	if (IS_ERR(handle)) {
···
 	netif_carrier_off(dev);
 	return t4_enable_vi(adapter, adapter->fn, pi->viid, false, false);
 }
+
+/* Return an error number if the indicated filter isn't writable ...
+ */
+static int writable_filter(struct filter_entry *f)
+{
+	if (f->locked)
+		return -EPERM;
+	if (f->pending)
+		return -EBUSY;
+
+	return 0;
+}
+
+/* Delete the filter at the specified index (if valid).  The checks for all
+ * the common problems with doing this like the filter being locked, currently
+ * pending in another operation, etc.
+ */
+static int delete_filter(struct adapter *adapter, unsigned int fidx)
+{
+	struct filter_entry *f;
+	int ret;
+
+	if (fidx >= adapter->tids.nftids + adapter->tids.nsftids)
+		return -EINVAL;
+
+	f = &adapter->tids.ftid_tab[fidx];
+	ret = writable_filter(f);
+	if (ret)
+		return ret;
+	if (f->valid)
+		return del_filter_wr(adapter, fidx);
+
+	return 0;
+}
+
+int cxgb4_create_server_filter(const struct net_device *dev, unsigned int stid,
+		__be32 sip, __be16 sport, __be16 vlan,
+		unsigned int queue, unsigned char port, unsigned char mask)
+{
+	int ret;
+	struct filter_entry *f;
+	struct adapter *adap;
+	int i;
+	u8 *val;
+
+	adap = netdev2adap(dev);
+
+	/* Adjust stid to correct filter index */
+	stid -= adap->tids.nstids;
+	stid += adap->tids.nftids;
+
+	/* Check to make sure the filter requested is writable ...
+	 */
+	f = &adap->tids.ftid_tab[stid];
+	ret = writable_filter(f);
+	if (ret)
+		return ret;
+
+	/* Clear out any old resources being used by the filter before
+	 * we start constructing the new filter.
+	 */
+	if (f->valid)
+		clear_filter(adap, f);
+
+	/* Clear out filter specifications */
+	memset(&f->fs, 0, sizeof(struct ch_filter_specification));
+	f->fs.val.lport = cpu_to_be16(sport);
+	f->fs.mask.lport  = ~0;
+	val = (u8 *)&sip;
+	if ((val[0] | val[1] | val[2] | val[3]) != 0) {
+		for (i = 0; i < 4; i++) {
+			f->fs.val.lip[i] = val[i];
+			f->fs.mask.lip[i] = ~0;
+		}
+		if (adap->filter_mode & F_PORT) {
+			f->fs.val.iport = port;
+			f->fs.mask.iport = mask;
+		}
+	}
+
+	f->fs.dirsteer = 1;
+	f->fs.iq = queue;
+	/* Mark filter as locked */
+	f->locked = 1;
+	f->fs.rpttid = 1;
+
+	ret = set_filter_wr(adap, stid);
+	if (ret) {
+		clear_filter(adap, f);
+		return ret;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(cxgb4_create_server_filter);
+
+int cxgb4_remove_server_filter(const struct net_device *dev, unsigned int stid,
+		unsigned int queue, bool ipv6)
+{
+	int ret;
+	struct filter_entry *f;
+	struct adapter *adap;
+
+	adap = netdev2adap(dev);
+
+	/* Adjust stid to correct filter index */
+	stid -= adap->tids.nstids;
+	stid += adap->tids.nftids;
+
+	f = &adap->tids.ftid_tab[stid];
+	/* Unlock the filter */
+	f->locked = 0;
+
+	ret = delete_filter(adap, stid);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+EXPORT_SYMBOL(cxgb4_remove_server_filter);
 
 static struct rtnl_link_stats64 *cxgb_get_stats(struct net_device *dev,
 						struct rtnl_link_stats64 *ns)
···
 	t4_write_reg(adap, TP_PIO_ADDR, TP_INGRESS_CONFIG);
 	v = t4_read_reg(adap, TP_PIO_DATA);
 	t4_write_reg(adap, TP_PIO_DATA, v & ~CSUM_HAS_PSEUDO_HDR);
+
+	/* first 4 Tx modulation queues point to consecutive Tx channels */
+	adap->params.tp.tx_modq_map = 0xE4;
+	t4_write_reg(adap, A_TP_TX_MOD_QUEUE_REQ_MAP,
+		     V_TX_MOD_QUEUE_REQ_MAP(adap->params.tp.tx_modq_map));
+
+	/* associate each Tx modulation queue with consecutive Tx channels */
+	v = 0x84218421;
+	t4_write_indirect(adap, TP_PIO_ADDR, TP_PIO_DATA,
+			  &v, 1, A_TP_TX_SCHED_HDR);
+	t4_write_indirect(adap, TP_PIO_ADDR, TP_PIO_DATA,
+			  &v, 1, A_TP_TX_SCHED_FIFO);
+	t4_write_indirect(adap, TP_PIO_ADDR, TP_PIO_DATA,
+			  &v, 1, A_TP_TX_SCHED_PCMD);
+
+#define T4_TX_MODQ_10G_WEIGHT_DEFAULT 16 /* in KB units */
+	if (is_offload(adap)) {
+		t4_write_reg(adap, A_TP_TX_MOD_QUEUE_WEIGHT0,
+			     V_TX_MODQ_WEIGHT0(T4_TX_MODQ_10G_WEIGHT_DEFAULT) |
+			     V_TX_MODQ_WEIGHT1(T4_TX_MODQ_10G_WEIGHT_DEFAULT) |
+			     V_TX_MODQ_WEIGHT2(T4_TX_MODQ_10G_WEIGHT_DEFAULT) |
+			     V_TX_MODQ_WEIGHT3(T4_TX_MODQ_10G_WEIGHT_DEFAULT));
+		t4_write_reg(adap, A_TP_TX_MOD_CHANNEL_WEIGHT,
+			     V_TX_MODQ_WEIGHT0(T4_TX_MODQ_10G_WEIGHT_DEFAULT) |
+			     V_TX_MODQ_WEIGHT1(T4_TX_MODQ_10G_WEIGHT_DEFAULT) |
+			     V_TX_MODQ_WEIGHT2(T4_TX_MODQ_10G_WEIGHT_DEFAULT) |
+			     V_TX_MODQ_WEIGHT3(T4_TX_MODQ_10G_WEIGHT_DEFAULT));
+	}
 
 	/* get basic stuff going */
 	return t4_early_init(adap, adap->fn);
···
 	for (j = 0; j < NCHAN; j++)
 		adap->params.tp.tx_modq[j] = j;
 
+	t4_read_indirect(adap, TP_PIO_ADDR, TP_PIO_DATA,
+			 &adap->filter_mode, 1,
+			 TP_VLAN_PRI_MAP);
+
 	adap->flags |= FW_OK;
 	return 0;
 
···
 
 		if (adapter->debugfs_root)
 			debugfs_remove_recursive(adapter->debugfs_root);
+
+		/* If we allocated filters, free up state associated with any
+		 * valid filters ...
+		 */
+		if (adapter->tids.ftid_tab) {
+			struct filter_entry *f = &adapter->tids.ftid_tab[0];
+			for (i = 0; i < (adapter->tids.nftids +
+					adapter->tids.nsftids); i++, f++)
+				if (f->valid)
+					clear_filter(adapter, f);
+		}
 
 		if (adapter->flags & FULL_INIT_DONE)
 			cxgb_down(adapter);

drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h

···
 #include <linux/cache.h>
 #include <linux/spinlock.h>
 #include <linux/skbuff.h>
+#include <linux/inetdevice.h>
 #include <linux/atomic.h>
 
 /* CPL message priority levels */
···
 
 	union aopen_entry *atid_tab;
 	unsigned int natids;
+	unsigned int atid_base;
 
+	struct filter_entry *ftid_tab;
 	unsigned int nftids;
 	unsigned int ftid_base;
 	unsigned int aftid_base;
···
 static inline void *lookup_stid(const struct tid_info *t, unsigned int stid)
 {
 	stid -= t->stid_base;
-	return stid < t->nstids ? t->stid_tab[stid].data : NULL;
+	return stid < (t->nstids + t->nsftids) ? t->stid_tab[stid].data : NULL;
 }
 
 static inline void cxgb4_insert_tid(struct tid_info *t, void *data,
···
 
 int cxgb4_alloc_atid(struct tid_info *t, void *data);
 int cxgb4_alloc_stid(struct tid_info *t, int family, void *data);
+int cxgb4_alloc_sftid(struct tid_info *t, int family, void *data);
 void cxgb4_free_atid(struct tid_info *t, unsigned int atid);
 void cxgb4_free_stid(struct tid_info *t, unsigned int stid, int family);
 void cxgb4_remove_tid(struct tid_info *t, unsigned int qid, unsigned int tid);
···
 struct in6_addr;
 
 int cxgb4_create_server(const struct net_device *dev, unsigned int stid,
-			__be32 sip, __be16 sport, unsigned int queue);
-
+			__be32 sip, __be16 sport, __be16 vlan,
+			unsigned int queue);
+int cxgb4_create_server_filter(const struct net_device *dev, unsigned int stid,
+			       __be32 sip, __be16 sport, __be16 vlan,
+			       unsigned int queue,
+			       unsigned char port, unsigned char mask);
+int cxgb4_remove_server_filter(const struct net_device *dev, unsigned int stid,
+			       unsigned int queue, bool ipv6);
 static inline void set_wr_txq(struct sk_buff *skb, int prio, int queue)
 {
 	skb_set_queue_mapping(skb, (queue << 1) | prio);
···
 	unsigned int iscsi_iolen;            /* iSCSI max I/O length */
 	unsigned short udb_density;          /* # of user DB/page */
 	unsigned short ucq_density;          /* # of user CQs/page */
+	unsigned short filt_mode;            /* filter optional components */
+	unsigned short tx_modq[NCHAN];       /* maps each tx channel to a */
+					     /* scheduler queue */
 	void __iomem *gts_reg;               /* address of GTS register */
 	void __iomem *db_reg;                /* address of kernel doorbell */
 	int dbfifo_int_thresh;		     /* doorbell fifo int threshold */
+	unsigned int sge_pktshift;           /* Padding between CPL and */
+					     /*	packet data */
+	bool enable_fw_ofld_conn;            /* Enable connection through fw */
+					     /* WR */
 };
 
 struct cxgb4_uld_info {

drivers/net/ethernet/chelsio/cxgb4/l2t.c

···
 		handle_failed_resolution(adap, arpq);
 }
 
+/* Allocate an L2T entry for use by a switching rule.  Such need to be
+ * explicitly freed and while busy they are not on any hash chain, so normal
+ * address resolution updates do not see them.
+ */
+struct l2t_entry *t4_l2t_alloc_switching(struct l2t_data *d)
+{
+	struct l2t_entry *e;
+
+	write_lock_bh(&d->lock);
+	e = alloc_l2e(d);
+	if (e) {
+		spin_lock(&e->lock);          /* avoid race with t4_l2t_free */
+		e->state = L2T_STATE_SWITCHING;
+		atomic_set(&e->refcnt, 1);
+		spin_unlock(&e->lock);
+	}
+	write_unlock_bh(&d->lock);
+	return e;
+}
+
+/* Sets/updates the contents of a switching L2T entry that has been allocated
+ * with an earlier call to @t4_l2t_alloc_switching.
+ */
+int t4_l2t_set_switching(struct adapter *adap, struct l2t_entry *e, u16 vlan,
+		u8 port, u8 *eth_addr)
+{
+	e->vlan = vlan;
+	e->lport = port;
+	memcpy(e->dmac, eth_addr, ETH_ALEN);
+	return write_l2e(adap, e, 0);
+}
+
 struct l2t_data *t4_init_l2t(void)
 {
 	int i;

drivers/net/ethernet/chelsio/cxgb4/l2t.h

···
 				unsigned int priority);
 
 void t4_l2t_update(struct adapter *adap, struct neighbour *neigh);
+struct l2t_entry *t4_l2t_alloc_switching(struct l2t_data *d);
+int t4_l2t_set_switching(struct adapter *adap, struct l2t_entry *e, u16 vlan,
+			 u8 port, u8 *eth_addr);
 struct l2t_data *t4_init_l2t(void);
 void do_l2t_write_rpl(struct adapter *p, const struct cpl_l2t_write_rpl *rpl);
 

drivers/net/ethernet/chelsio/cxgb4/t4_hw.c

···
  *	Reads registers that are accessed indirectly through an address/data
  *	register pair.
  */
-static void t4_read_indirect(struct adapter *adap, unsigned int addr_reg,
+void t4_read_indirect(struct adapter *adap, unsigned int addr_reg,
 			     unsigned int data_reg, u32 *vals,
 			     unsigned int nregs, unsigned int start_idx)
 {
···
 
 	t4_set_reg_field(adap, PORT_REG(port, XGMAC_PORT_CFG2), 0, PATEN);
 	return 0;
+}
+
+/*     t4_mk_filtdelwr - create a delete filter WR
+ *     @ftid: the filter ID
+ *     @wr: the filter work request to populate
+ *     @qid: ingress queue to receive the delete notification
+ *
+ *     Creates a filter work request to delete the supplied filter.  If @qid is
+ *     negative the delete notification is suppressed.
+ */
+void t4_mk_filtdelwr(unsigned int ftid, struct fw_filter_wr *wr, int qid)
+{
+	memset(wr, 0, sizeof(*wr));
+	wr->op_pkd = htonl(FW_WR_OP(FW_FILTER_WR));
+	wr->len16_pkd = htonl(FW_WR_LEN16(sizeof(*wr) / 16));
+	wr->tid_to_iq = htonl(V_FW_FILTER_WR_TID(ftid) |
+			V_FW_FILTER_WR_NOREPLY(qid < 0));
+	wr->del_filter_to_l2tix = htonl(F_FW_FILTER_WR_DEL_FILTER);
+	if (qid >= 0)
+		wr->rx_chan_rx_rpl_iq = htons(V_FW_FILTER_WR_RX_RPL_IQ(qid));
 }
 
 #define INIT_CMD(var, cmd, rd_wr) do { \

drivers/net/ethernet/chelsio/cxgb4/t4_msg.h

···
 	__be64 wr_lo;
 };
 
+/* wr_hi fields */
+#define S_WR_OP    24
+#define V_WR_OP(x) ((__u64)(x) << S_WR_OP)
+
 #define WR_HDR struct work_request_hdr wr
+
+/* option 0 fields */
+#define S_MSS_IDX    60
+#define M_MSS_IDX    0xF
+#define V_MSS_IDX(x) ((__u64)(x) << S_MSS_IDX)
+#define G_MSS_IDX(x) (((x) >> S_MSS_IDX) & M_MSS_IDX)
+
+/* option 2 fields */
+#define S_RSS_QUEUE    0
+#define M_RSS_QUEUE    0x3FF
+#define V_RSS_QUEUE(x) ((x) << S_RSS_QUEUE)
+#define G_RSS_QUEUE(x) (((x) >> S_RSS_QUEUE) & M_RSS_QUEUE)
 
 struct cpl_pass_open_req {
 	WR_HDR;
···
 	__be32 peer_ip;
 	__be64 opt0;
 #define TX_CHAN(x)    ((x) << 2)
+#define NO_CONG(x)    ((x) << 4)
 #define DELACK(x)     ((x) << 5)
 #define ULP_MODE(x)   ((x) << 8)
 #define RCV_BUFSIZ(x) ((x) << 12)
 #define DSCP(x)       ((x) << 22)
 #define SMAC_SEL(x)   ((u64)(x) << 28)
 #define L2T_IDX(x)    ((u64)(x) << 36)
+#define TCAM_BYPASS(x) ((u64)(x) << 48)
 #define NAGLE(x)      ((u64)(x) << 49)
 #define WND_SCALE(x)  ((u64)(x) << 50)
 #define KEEP_ALIVE(x) ((u64)(x) << 54)
···
 #define RSS_QUEUE_VALID      (1 << 10)
 #define RX_COALESCE_VALID(x) ((x) << 11)
 #define RX_COALESCE(x)       ((x) << 12)
+#define PACE(x)	      ((x) << 16)
 #define TX_QUEUE(x)          ((x) << 23)
 #define RX_CHANNEL(x)        ((x) << 26)
+#define CCTRL_ECN(x)         ((x) << 27)
 #define WND_SCALE_EN(x)      ((x) << 28)
 #define TSTAMPS_EN(x)        ((x) << 29)
 #define SACK_EN(x)           ((x) << 30)
···
 	union opcode_tid ot;
 	__be32 rsvd;
 	__be32 tos_stid;
+#define PASS_OPEN_TID(x) ((x) << 0)
+#define PASS_OPEN_TOS(x) ((x) << 24)
+#define GET_PASS_OPEN_TID(x)	(((x) >> 0) & 0xFFFFFF)
 #define GET_POPEN_TID(x) ((x) & 0xffffff)
 #define GET_POPEN_TOS(x) (((x) >> 24) & 0xff)
 	__be16 mac_idx;
···
 	__be16 word_cookie;
 #define TCB_WORD(x)   ((x) << 0)
 #define TCB_COOKIE(x) ((x) << 5)
+#define GET_TCB_COOKIE(x) (((x) >> 5) & 7)
 	__be64 mask;
 	__be64 val;
 };
···
 	__be16 err_vec;
 };
 
+/* rx_pkt.l2info fields */
+#define S_RX_ETHHDR_LEN    0
+#define M_RX_ETHHDR_LEN    0x1F
+#define V_RX_ETHHDR_LEN(x) ((x) << S_RX_ETHHDR_LEN)
+#define G_RX_ETHHDR_LEN(x) (((x) >> S_RX_ETHHDR_LEN) & M_RX_ETHHDR_LEN)
+
+#define S_RX_MACIDX    8
+#define M_RX_MACIDX    0x1FF
+#define V_RX_MACIDX(x) ((x) << S_RX_MACIDX)
+#define G_RX_MACIDX(x) (((x) >> S_RX_MACIDX) & M_RX_MACIDX)
+
+#define S_RXF_SYN    21
+#define V_RXF_SYN(x) ((x) << S_RXF_SYN)
+#define F_RXF_SYN    V_RXF_SYN(1U)
+
+#define S_RX_CHAN    28
+#define M_RX_CHAN    0xF
+#define V_RX_CHAN(x) ((x) << S_RX_CHAN)
+#define G_RX_CHAN(x) (((x) >> S_RX_CHAN) & M_RX_CHAN)
+
+/* rx_pkt.hdr_len fields */
+#define S_RX_TCPHDR_LEN    0
+#define M_RX_TCPHDR_LEN    0x3F
+#define V_RX_TCPHDR_LEN(x) ((x) << S_RX_TCPHDR_LEN)
+#define G_RX_TCPHDR_LEN(x) (((x) >> S_RX_TCPHDR_LEN) & M_RX_TCPHDR_LEN)
+
+#define S_RX_IPHDR_LEN    6
+#define M_RX_IPHDR_LEN    0x3FF
+#define V_RX_IPHDR_LEN(x) ((x) << S_RX_IPHDR_LEN)
+#define G_RX_IPHDR_LEN(x) (((x) >> S_RX_IPHDR_LEN) & M_RX_IPHDR_LEN)
+
 struct cpl_trace_pkt {
 	u8 opcode;
 	u8 intf;
···
 /* cpl_fw6_msg.type values */
 enum {
 	FW6_TYPE_CMD_RPL = 0,
+	FW6_TYPE_WR_RPL = 1,
+	FW6_TYPE_CQE = 2,
+	FW6_TYPE_OFLD_CONNECTION_WR_RPL = 3,
+};
+
+struct cpl_fw6_msg_ofld_connection_wr_rpl {
+	__u64   cookie;
+	__be32  tid;    /* or atid in case of active failure */
+	__u8    t_state;
+	__u8    retval;
+	__u8    rsvd[2];
 };
 
 enum {

drivers/net/ethernet/chelsio/cxgb4/t4_regs.h

···
 #define  ADDRESS(x)     ((x) << ADDRESS_SHIFT)
 
 #define XGMAC_PORT_INT_CAUSE 0x10dc
+
+#define A_TP_TX_MOD_QUEUE_REQ_MAP 0x7e28
+
+#define A_TP_TX_MOD_CHANNEL_WEIGHT 0x7e34
+
+#define S_TX_MOD_QUEUE_REQ_MAP    0
+#define M_TX_MOD_QUEUE_REQ_MAP    0xffffU
+#define V_TX_MOD_QUEUE_REQ_MAP(x) ((x) << S_TX_MOD_QUEUE_REQ_MAP)
+
+#define A_TP_TX_MOD_QUEUE_WEIGHT0 0x7e30
+
+#define S_TX_MODQ_WEIGHT3    24
+#define M_TX_MODQ_WEIGHT3    0xffU
+#define V_TX_MODQ_WEIGHT3(x) ((x) << S_TX_MODQ_WEIGHT3)
+
+#define S_TX_MODQ_WEIGHT2    16
+#define M_TX_MODQ_WEIGHT2    0xffU
+#define V_TX_MODQ_WEIGHT2(x) ((x) << S_TX_MODQ_WEIGHT2)
+
+#define S_TX_MODQ_WEIGHT1    8
+#define M_TX_MODQ_WEIGHT1    0xffU
+#define V_TX_MODQ_WEIGHT1(x) ((x) << S_TX_MODQ_WEIGHT1)
+
+#define S_TX_MODQ_WEIGHT0    0
+#define M_TX_MODQ_WEIGHT0    0xffU
+#define V_TX_MODQ_WEIGHT0(x) ((x) << S_TX_MODQ_WEIGHT0)
+
+#define A_TP_TX_SCHED_HDR 0x23
+
+#define A_TP_TX_SCHED_FIFO 0x24
+
+#define A_TP_TX_SCHED_PCMD 0x25
+
+#define S_PORT    1
+#define V_PORT(x) ((x) << S_PORT)
+#define F_PORT    V_PORT(1U)
+
 #endif /* __T4_REGS_H */

drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h

···
 #ifndef _T4FW_INTERFACE_H_
 #define _T4FW_INTERFACE_H_
 
+enum fw_retval {
+	FW_SUCCESS		= 0,	/* completed sucessfully */
+	FW_EPERM		= 1,	/* operation not permitted */
+	FW_ENOENT		= 2,	/* no such file or directory */
+	FW_EIO			= 5,	/* input/output error; hw bad */
+	FW_ENOEXEC		= 8,	/* exec format error; inv microcode */
+	FW_EAGAIN		= 11,	/* try again */
+	FW_ENOMEM		= 12,	/* out of memory */
+	FW_EFAULT		= 14,	/* bad address; fw bad */
+	FW_EBUSY		= 16,	/* resource busy */
+	FW_EEXIST		= 17,	/* file exists */
+	FW_EINVAL		= 22,	/* invalid argument */
+	FW_ENOSPC		= 28,	/* no space left on device */
+	FW_ENOSYS		= 38,	/* functionality not implemented */
+	FW_EPROTO		= 71,	/* protocol error */
+	FW_EADDRINUSE		= 98,	/* address already in use */
+	FW_EADDRNOTAVAIL	= 99,	/* cannot assigned requested address */
+	FW_ENETDOWN		= 100,	/* network is down */
+	FW_ENETUNREACH		= 101,	/* network is unreachable */
+	FW_ENOBUFS		= 105,	/* no buffer space available */
+	FW_ETIMEDOUT		= 110,	/* timeout */
+	FW_EINPROGRESS		= 115,	/* fw internal */
+	FW_SCSI_ABORT_REQUESTED	= 128,	/* */
+	FW_SCSI_ABORT_TIMEDOUT	= 129,	/* */
+	FW_SCSI_ABORTED		= 130,	/* */
+	FW_SCSI_CLOSE_REQUESTED	= 131,	/* */
+	FW_ERR_LINK_DOWN	= 132,	/* */
+	FW_RDEV_NOT_READY	= 133,	/* */
+	FW_ERR_RDEV_LOST	= 134,	/* */
+	FW_ERR_RDEV_LOGO	= 135,	/* */
+	FW_FCOE_NO_XCHG		= 136,	/* */
+	FW_SCSI_RSP_ERR		= 137,	/* */
+	FW_ERR_RDEV_IMPL_LOGO	= 138,	/* */
+	FW_SCSI_UNDER_FLOW_ERR  = 139,	/* */
+	FW_SCSI_OVER_FLOW_ERR   = 140,	/* */
+	FW_SCSI_DDP_ERR		= 141,	/* DDP error*/
+	FW_SCSI_TASK_ERR	= 142,	/* No SCSI tasks available */
+};
+
 #define FW_T4VF_SGE_BASE_ADDR      0x0000
 #define FW_T4VF_MPS_BASE_ADDR      0x0100
 #define FW_T4VF_PL_BASE_ADDR       0x0200
···
 	FW_ULPTX_WR                    = 0x04,
 	FW_TP_WR                       = 0x05,
 	FW_ETH_TX_PKT_WR               = 0x08,
+	FW_OFLD_CONNECTION_WR          = 0x2f,
 	FW_FLOWC_WR                    = 0x0a,
 	FW_OFLD_TX_DATA_WR             = 0x0b,
 	FW_CMD_WR                      = 0x10,
···
 #define FW_WR_LEN16(x)	((x) << 0)
 
 #define HW_TPL_FR_MT_PR_IV_P_FC         0X32B
+#define HW_TPL_FR_MT_PR_OV_P_FC         0X327
+
+/* filter wr reply code in cookie in CPL_SET_TCB_RPL */
+enum fw_filter_wr_cookie {
+	FW_FILTER_WR_SUCCESS,
+	FW_FILTER_WR_FLT_ADDED,
+	FW_FILTER_WR_FLT_DELETED,
+	FW_FILTER_WR_SMT_TBL_FULL,
+	FW_FILTER_WR_EINVAL,
+};
+
+struct fw_filter_wr {
+	__be32 op_pkd;
+	__be32 len16_pkd;
+	__be64 r3;
+	__be32 tid_to_iq;
+	__be32 del_filter_to_l2tix;
+	__be16 ethtype;
+	__be16 ethtypem;
+	__u8   frag_to_ovlan_vldm;
+	__u8   smac_sel;
+	__be16 rx_chan_rx_rpl_iq;
+	__be32 maci_to_matchtypem;
+	__u8   ptcl;
+	__u8   ptclm;
+	__u8   ttyp;
+	__u8   ttypm;
+	__be16 ivlan;
+	__be16 ivlanm;
+	__be16 ovlan;
+	__be16 ovlanm;
+	__u8   lip[16];
+	__u8   lipm[16];
+	__u8   fip[16];
+	__u8   fipm[16];
+	__be16 lp;
+	__be16 lpm;
+	__be16 fp;
+	__be16 fpm;
+	__be16 r7;
+	__u8   sma[6];
+};
+
+#define S_FW_FILTER_WR_TID      12
+#define M_FW_FILTER_WR_TID      0xfffff
+#define V_FW_FILTER_WR_TID(x)   ((x) << S_FW_FILTER_WR_TID)
+#define G_FW_FILTER_WR_TID(x)   \
+	(((x) >> S_FW_FILTER_WR_TID) & M_FW_FILTER_WR_TID)
+
+#define S_FW_FILTER_WR_RQTYPE           11
+#define M_FW_FILTER_WR_RQTYPE           0x1
+#define V_FW_FILTER_WR_RQTYPE(x)        ((x) << S_FW_FILTER_WR_RQTYPE)
+#define G_FW_FILTER_WR_RQTYPE(x)        \
+	(((x) >> S_FW_FILTER_WR_RQTYPE) & M_FW_FILTER_WR_RQTYPE)
+#define F_FW_FILTER_WR_RQTYPE   V_FW_FILTER_WR_RQTYPE(1U)
+
+#define S_FW_FILTER_WR_NOREPLY          10
+#define M_FW_FILTER_WR_NOREPLY          0x1
+#define V_FW_FILTER_WR_NOREPLY(x)       ((x) << S_FW_FILTER_WR_NOREPLY)
+#define G_FW_FILTER_WR_NOREPLY(x)       \
+	(((x) >> S_FW_FILTER_WR_NOREPLY) & M_FW_FILTER_WR_NOREPLY)
+#define F_FW_FILTER_WR_NOREPLY  V_FW_FILTER_WR_NOREPLY(1U)
+
+#define S_FW_FILTER_WR_IQ       0
+#define M_FW_FILTER_WR_IQ       0x3ff
+#define V_FW_FILTER_WR_IQ(x)    ((x) << S_FW_FILTER_WR_IQ)
+#define G_FW_FILTER_WR_IQ(x)    \
+	(((x) >> S_FW_FILTER_WR_IQ) & M_FW_FILTER_WR_IQ)
+
+#define S_FW_FILTER_WR_DEL_FILTER       31
+#define M_FW_FILTER_WR_DEL_FILTER       0x1
+#define V_FW_FILTER_WR_DEL_FILTER(x)    ((x) << S_FW_FILTER_WR_DEL_FILTER)
+#define G_FW_FILTER_WR_DEL_FILTER(x)    \
+	(((x) >> S_FW_FILTER_WR_DEL_FILTER) & M_FW_FILTER_WR_DEL_FILTER)
+#define F_FW_FILTER_WR_DEL_FILTER       V_FW_FILTER_WR_DEL_FILTER(1U)
+
+#define S_FW_FILTER_WR_RPTTID           25
+#define M_FW_FILTER_WR_RPTTID           0x1
+#define V_FW_FILTER_WR_RPTTID(x)        ((x) << S_FW_FILTER_WR_RPTTID)
+#define G_FW_FILTER_WR_RPTTID(x)        \
+	(((x) >> S_FW_FILTER_WR_RPTTID) & M_FW_FILTER_WR_RPTTID)
+#define F_FW_FILTER_WR_RPTTID   V_FW_FILTER_WR_RPTTID(1U)
+
+#define S_FW_FILTER_WR_DROP     24
+#define M_FW_FILTER_WR_DROP     0x1
+#define V_FW_FILTER_WR_DROP(x)  ((x) << S_FW_FILTER_WR_DROP)
+#define G_FW_FILTER_WR_DROP(x)  \
+	(((x) >> S_FW_FILTER_WR_DROP) & M_FW_FILTER_WR_DROP)
+#define F_FW_FILTER_WR_DROP     V_FW_FILTER_WR_DROP(1U)
+
+#define S_FW_FILTER_WR_DIRSTEER         23
+#define M_FW_FILTER_WR_DIRSTEER         0x1
+#define V_FW_FILTER_WR_DIRSTEER(x)      ((x) << S_FW_FILTER_WR_DIRSTEER)
+#define G_FW_FILTER_WR_DIRSTEER(x)      \
+	(((x) >> S_FW_FILTER_WR_DIRSTEER) & M_FW_FILTER_WR_DIRSTEER)
+#define F_FW_FILTER_WR_DIRSTEER V_FW_FILTER_WR_DIRSTEER(1U)
+
+#define S_FW_FILTER_WR_MASKHASH         22
+#define M_FW_FILTER_WR_MASKHASH         0x1
+#define V_FW_FILTER_WR_MASKHASH(x)      ((x) << S_FW_FILTER_WR_MASKHASH)
+#define G_FW_FILTER_WR_MASKHASH(x)      \
+	(((x) >> S_FW_FILTER_WR_MASKHASH) & M_FW_FILTER_WR_MASKHASH)
+#define F_FW_FILTER_WR_MASKHASH V_FW_FILTER_WR_MASKHASH(1U)
+
+#define S_FW_FILTER_WR_DIRSTEERHASH     21
+#define M_FW_FILTER_WR_DIRSTEERHASH     0x1
+#define V_FW_FILTER_WR_DIRSTEERHASH(x)  ((x) << S_FW_FILTER_WR_DIRSTEERHASH)
+#define G_FW_FILTER_WR_DIRSTEERHASH(x)  \
+	(((x) >> S_FW_FILTER_WR_DIRSTEERHASH) & M_FW_FILTER_WR_DIRSTEERHASH)
+#define F_FW_FILTER_WR_DIRSTEERHASH     V_FW_FILTER_WR_DIRSTEERHASH(1U)
+
+#define S_FW_FILTER_WR_LPBK     20
+#define M_FW_FILTER_WR_LPBK     0x1
+#define V_FW_FILTER_WR_LPBK(x)  ((x) << S_FW_FILTER_WR_LPBK)
+#define G_FW_FILTER_WR_LPBK(x)  \
+	(((x) >> S_FW_FILTER_WR_LPBK) & M_FW_FILTER_WR_LPBK)
+#define F_FW_FILTER_WR_LPBK     V_FW_FILTER_WR_LPBK(1U)
+
+#define S_FW_FILTER_WR_DMAC     19
+#define M_FW_FILTER_WR_DMAC     0x1
+#define V_FW_FILTER_WR_DMAC(x)  ((x) << S_FW_FILTER_WR_DMAC)
+#define G_FW_FILTER_WR_DMAC(x)  \
+	(((x) >> S_FW_FILTER_WR_DMAC) & M_FW_FILTER_WR_DMAC)
+#define F_FW_FILTER_WR_DMAC     V_FW_FILTER_WR_DMAC(1U)
+
+#define S_FW_FILTER_WR_SMAC     18
+#define M_FW_FILTER_WR_SMAC     0x1
+#define V_FW_FILTER_WR_SMAC(x)  ((x) << S_FW_FILTER_WR_SMAC)
+#define G_FW_FILTER_WR_SMAC(x)  \
+	(((x) >> S_FW_FILTER_WR_SMAC) & M_FW_FILTER_WR_SMAC)
+#define F_FW_FILTER_WR_SMAC     V_FW_FILTER_WR_SMAC(1U)
+
+#define S_FW_FILTER_WR_INSVLAN          17
+#define M_FW_FILTER_WR_INSVLAN          0x1
+#define V_FW_FILTER_WR_INSVLAN(x)       ((x) << S_FW_FILTER_WR_INSVLAN)
+#define G_FW_FILTER_WR_INSVLAN(x)       \
+	(((x) >> S_FW_FILTER_WR_INSVLAN) & M_FW_FILTER_WR_INSVLAN)
+#define F_FW_FILTER_WR_INSVLAN  V_FW_FILTER_WR_INSVLAN(1U)
+
+#define S_FW_FILTER_WR_RMVLAN           16
+#define M_FW_FILTER_WR_RMVLAN           0x1
+#define V_FW_FILTER_WR_RMVLAN(x)        ((x) << S_FW_FILTER_WR_RMVLAN)
+#define G_FW_FILTER_WR_RMVLAN(x)        \
+	(((x) >> S_FW_FILTER_WR_RMVLAN) & M_FW_FILTER_WR_RMVLAN)
+#define F_FW_FILTER_WR_RMVLAN   V_FW_FILTER_WR_RMVLAN(1U)
+
+#define S_FW_FILTER_WR_HITCNTS          15
+#define M_FW_FILTER_WR_HITCNTS          0x1
+#define V_FW_FILTER_WR_HITCNTS(x)       ((x) << S_FW_FILTER_WR_HITCNTS)
+#define G_FW_FILTER_WR_HITCNTS(x)       \
+	(((x) >> S_FW_FILTER_WR_HITCNTS) & M_FW_FILTER_WR_HITCNTS)
+#define F_FW_FILTER_WR_HITCNTS  V_FW_FILTER_WR_HITCNTS(1U)
+
+#define S_FW_FILTER_WR_TXCHAN           13
+#define M_FW_FILTER_WR_TXCHAN           0x3
+#define V_FW_FILTER_WR_TXCHAN(x)        ((x) << S_FW_FILTER_WR_TXCHAN)
+#define G_FW_FILTER_WR_TXCHAN(x)        \
+	(((x) >> S_FW_FILTER_WR_TXCHAN) & M_FW_FILTER_WR_TXCHAN)
+
+#define S_FW_FILTER_WR_PRIO     12
+#define M_FW_FILTER_WR_PRIO     0x1
+#define V_FW_FILTER_WR_PRIO(x)  ((x) << S_FW_FILTER_WR_PRIO)
+#define G_FW_FILTER_WR_PRIO(x)  \
+	(((x) >> S_FW_FILTER_WR_PRIO) & M_FW_FILTER_WR_PRIO)
+#define F_FW_FILTER_WR_PRIO     V_FW_FILTER_WR_PRIO(1U)
+
+#define S_FW_FILTER_WR_L2TIX    0
+#define M_FW_FILTER_WR_L2TIX    0xfff
+#define V_FW_FILTER_WR_L2TIX(x) ((x) << S_FW_FILTER_WR_L2TIX)
+#define G_FW_FILTER_WR_L2TIX(x) \
+	(((x) >> S_FW_FILTER_WR_L2TIX) & M_FW_FILTER_WR_L2TIX)
+
+#define S_FW_FILTER_WR_FRAG     7
+#define M_FW_FILTER_WR_FRAG     0x1
+#define V_FW_FILTER_WR_FRAG(x)  ((x) << S_FW_FILTER_WR_FRAG)
+#define G_FW_FILTER_WR_FRAG(x)  \
+	(((x) >> S_FW_FILTER_WR_FRAG) & M_FW_FILTER_WR_FRAG)
+#define F_FW_FILTER_WR_FRAG     V_FW_FILTER_WR_FRAG(1U)
+
+#define S_FW_FILTER_WR_FRAGM    6
+#define M_FW_FILTER_WR_FRAGM    0x1
+#define V_FW_FILTER_WR_FRAGM(x) ((x) << S_FW_FILTER_WR_FRAGM)
+#define G_FW_FILTER_WR_FRAGM(x) \
+	(((x) >> S_FW_FILTER_WR_FRAGM) & M_FW_FILTER_WR_FRAGM)
+#define F_FW_FILTER_WR_FRAGM    V_FW_FILTER_WR_FRAGM(1U)
+
+#define S_FW_FILTER_WR_IVLAN_VLD        5
+#define M_FW_FILTER_WR_IVLAN_VLD        0x1
+#define V_FW_FILTER_WR_IVLAN_VLD(x)     ((x) << S_FW_FILTER_WR_IVLAN_VLD)
+#define G_FW_FILTER_WR_IVLAN_VLD(x)     \
+	(((x) >> S_FW_FILTER_WR_IVLAN_VLD) & M_FW_FILTER_WR_IVLAN_VLD)
+#define F_FW_FILTER_WR_IVLAN_VLD        V_FW_FILTER_WR_IVLAN_VLD(1U)
+
+#define S_FW_FILTER_WR_OVLAN_VLD        4
+#define M_FW_FILTER_WR_OVLAN_VLD        0x1
+#define V_FW_FILTER_WR_OVLAN_VLD(x)     ((x) << S_FW_FILTER_WR_OVLAN_VLD)
+#define G_FW_FILTER_WR_OVLAN_VLD(x)     \
+	(((x) >> S_FW_FILTER_WR_OVLAN_VLD) & M_FW_FILTER_WR_OVLAN_VLD)
+#define F_FW_FILTER_WR_OVLAN_VLD        V_FW_FILTER_WR_OVLAN_VLD(1U)
+
+#define S_FW_FILTER_WR_IVLAN_VLDM       3
+#define M_FW_FILTER_WR_IVLAN_VLDM       0x1
+#define V_FW_FILTER_WR_IVLAN_VLDM(x)    ((x) << S_FW_FILTER_WR_IVLAN_VLDM)
+#define G_FW_FILTER_WR_IVLAN_VLDM(x)    \
+	(((x) >> S_FW_FILTER_WR_IVLAN_VLDM) & M_FW_FILTER_WR_IVLAN_VLDM)
+#define F_FW_FILTER_WR_IVLAN_VLDM       V_FW_FILTER_WR_IVLAN_VLDM(1U)
+
+#define S_FW_FILTER_WR_OVLAN_VLDM       2
+#define M_FW_FILTER_WR_OVLAN_VLDM       0x1
+#define V_FW_FILTER_WR_OVLAN_VLDM(x)    ((x) << S_FW_FILTER_WR_OVLAN_VLDM)
+#define G_FW_FILTER_WR_OVLAN_VLDM(x)    \
+	(((x) >> S_FW_FILTER_WR_OVLAN_VLDM) & M_FW_FILTER_WR_OVLAN_VLDM)
+#define F_FW_FILTER_WR_OVLAN_VLDM       V_FW_FILTER_WR_OVLAN_VLDM(1U)
+
+#define S_FW_FILTER_WR_RX_CHAN          15
+#define M_FW_FILTER_WR_RX_CHAN          0x1
+#define V_FW_FILTER_WR_RX_CHAN(x)       ((x) << S_FW_FILTER_WR_RX_CHAN)
+#define G_FW_FILTER_WR_RX_CHAN(x)       \
+	(((x) >> S_FW_FILTER_WR_RX_CHAN) & M_FW_FILTER_WR_RX_CHAN)
+#define F_FW_FILTER_WR_RX_CHAN  V_FW_FILTER_WR_RX_CHAN(1U)
+
+#define S_FW_FILTER_WR_RX_RPL_IQ        0
+#define M_FW_FILTER_WR_RX_RPL_IQ        0x3ff
+#define V_FW_FILTER_WR_RX_RPL_IQ(x)     ((x) << S_FW_FILTER_WR_RX_RPL_IQ)
+#define G_FW_FILTER_WR_RX_RPL_IQ(x)     \
+	(((x) >> S_FW_FILTER_WR_RX_RPL_IQ) & M_FW_FILTER_WR_RX_RPL_IQ)
+
+#define S_FW_FILTER_WR_MACI     23
+#define M_FW_FILTER_WR_MACI     0x1ff
+#define V_FW_FILTER_WR_MACI(x)  ((x) << S_FW_FILTER_WR_MACI)
+#define G_FW_FILTER_WR_MACI(x)  \
+	(((x) >> S_FW_FILTER_WR_MACI) & M_FW_FILTER_WR_MACI)
+
+#define S_FW_FILTER_WR_MACIM    14
+#define M_FW_FILTER_WR_MACIM    0x1ff
+#define V_FW_FILTER_WR_MACIM(x) ((x) << S_FW_FILTER_WR_MACIM)
+#define G_FW_FILTER_WR_MACIM(x) \
+	(((x) >> S_FW_FILTER_WR_MACIM) & M_FW_FILTER_WR_MACIM)
+
+#define S_FW_FILTER_WR_FCOE     13
+#define M_FW_FILTER_WR_FCOE     0x1
+#define V_FW_FILTER_WR_FCOE(x)  ((x) << S_FW_FILTER_WR_FCOE)
+#define G_FW_FILTER_WR_FCOE(x)  \
+	(((x) >> S_FW_FILTER_WR_FCOE) & M_FW_FILTER_WR_FCOE)
+#define F_FW_FILTER_WR_FCOE     V_FW_FILTER_WR_FCOE(1U)
+
+#define S_FW_FILTER_WR_FCOEM    12
+#define M_FW_FILTER_WR_FCOEM    0x1
+#define V_FW_FILTER_WR_FCOEM(x) ((x) << S_FW_FILTER_WR_FCOEM)
+#define G_FW_FILTER_WR_FCOEM(x) \
+	(((x) >> S_FW_FILTER_WR_FCOEM) & M_FW_FILTER_WR_FCOEM)
+#define F_FW_FILTER_WR_FCOEM    V_FW_FILTER_WR_FCOEM(1U)
+
+#define S_FW_FILTER_WR_PORT     9
+#define M_FW_FILTER_WR_PORT     0x7
+#define V_FW_FILTER_WR_PORT(x)  ((x) << S_FW_FILTER_WR_PORT)
+#define G_FW_FILTER_WR_PORT(x)  \
+	(((x) >> S_FW_FILTER_WR_PORT) & M_FW_FILTER_WR_PORT)
+
+#define S_FW_FILTER_WR_PORTM    6
+#define M_FW_FILTER_WR_PORTM    0x7
+#define V_FW_FILTER_WR_PORTM(x) ((x) << S_FW_FILTER_WR_PORTM)
+#define G_FW_FILTER_WR_PORTM(x) \
+	(((x) >> S_FW_FILTER_WR_PORTM) & M_FW_FILTER_WR_PORTM)
+
+#define S_FW_FILTER_WR_MATCHTYPE        3
+#define M_FW_FILTER_WR_MATCHTYPE        0x7
+#define V_FW_FILTER_WR_MATCHTYPE(x)     ((x) << S_FW_FILTER_WR_MATCHTYPE)
+#define G_FW_FILTER_WR_MATCHTYPE(x)     \
+	(((x) >> S_FW_FILTER_WR_MATCHTYPE) & M_FW_FILTER_WR_MATCHTYPE)
+
+#define S_FW_FILTER_WR_MATCHTYPEM       0
+#define M_FW_FILTER_WR_MATCHTYPEM       0x7
+#define V_FW_FILTER_WR_MATCHTYPEM(x)    ((x) << S_FW_FILTER_WR_MATCHTYPEM)
+#define G_FW_FILTER_WR_MATCHTYPEM(x)    \
+	(((x) >> S_FW_FILTER_WR_MATCHTYPEM) & M_FW_FILTER_WR_MATCHTYPEM)
 
 struct fw_ulptx_wr {
 	__be32 op_to_compl;
···
 	__be32 equiq_to_len16;
 	__be64 r3;
 };
+
+struct fw_ofld_connection_wr {
+	__be32 op_compl;
+	__be32 len16_pkd;
+	__u64  cookie;
+	__be64 r2;
+	__be64 r3;
+	struct fw_ofld_connection_le {
+		__be32 version_cpl;
+		__be32 filter;
+		__be32 r1;
+		__be16 lport;
+		__be16 pport;
+		union fw_ofld_connection_leip {
+			struct fw_ofld_connection_le_ipv4 {
+				__be32 pip;
+				__be32 lip;
+				__be64 r0;
+				__be64 r1;
+				__be64 r2;
+			} ipv4;
+			struct fw_ofld_connection_le_ipv6 {
+				__be64 pip_hi;
+				__be64 pip_lo;
+				__be64 lip_hi;
+				__be64 lip_lo;
+			} ipv6;
+		} u;
+	} le;
+	struct fw_ofld_connection_tcb {
+		__be32 t_state_to_astid;
+		__be16 cplrxdataack_cplpassacceptrpl;
+		__be16 rcv_adv;
+		__be32 rcv_nxt;
+		__be32 tx_max;
+		__be64 opt0;
+		__be32 opt2;
+		__be32 r1;
+		__be64 r2;
+		__be64 r3;
+	} tcb;
+};
+
+#define S_FW_OFLD_CONNECTION_WR_VERSION                31
+#define M_FW_OFLD_CONNECTION_WR_VERSION                0x1
+#define V_FW_OFLD_CONNECTION_WR_VERSION(x)     \
+	((x) << S_FW_OFLD_CONNECTION_WR_VERSION)
+#define G_FW_OFLD_CONNECTION_WR_VERSION(x)     \
+	(((x) >> S_FW_OFLD_CONNECTION_WR_VERSION) & \
+	M_FW_OFLD_CONNECTION_WR_VERSION)
+#define F_FW_OFLD_CONNECTION_WR_VERSION        \
+	V_FW_OFLD_CONNECTION_WR_VERSION(1U)
+
+#define S_FW_OFLD_CONNECTION_WR_CPL    30
+#define M_FW_OFLD_CONNECTION_WR_CPL    0x1
+#define V_FW_OFLD_CONNECTION_WR_CPL(x) ((x) << S_FW_OFLD_CONNECTION_WR_CPL)
+#define G_FW_OFLD_CONNECTION_WR_CPL(x) \
+	(((x) >> S_FW_OFLD_CONNECTION_WR_CPL) & M_FW_OFLD_CONNECTION_WR_CPL)
+#define F_FW_OFLD_CONNECTION_WR_CPL    V_FW_OFLD_CONNECTION_WR_CPL(1U)
+
+#define S_FW_OFLD_CONNECTION_WR_T_STATE                28
+#define M_FW_OFLD_CONNECTION_WR_T_STATE                0xf
+#define V_FW_OFLD_CONNECTION_WR_T_STATE(x)     \
+	((x) << S_FW_OFLD_CONNECTION_WR_T_STATE)
+#define G_FW_OFLD_CONNECTION_WR_T_STATE(x)     \
+	(((x) >> S_FW_OFLD_CONNECTION_WR_T_STATE) & \
+	M_FW_OFLD_CONNECTION_WR_T_STATE)
+
+#define S_FW_OFLD_CONNECTION_WR_RCV_SCALE      24
+#define M_FW_OFLD_CONNECTION_WR_RCV_SCALE      0xf
+#define V_FW_OFLD_CONNECTION_WR_RCV_SCALE(x)   \
+	((x) << S_FW_OFLD_CONNECTION_WR_RCV_SCALE)
+#define G_FW_OFLD_CONNECTION_WR_RCV_SCALE(x)   \
+	(((x) >> S_FW_OFLD_CONNECTION_WR_RCV_SCALE) & \
+	M_FW_OFLD_CONNECTION_WR_RCV_SCALE)
+
+#define S_FW_OFLD_CONNECTION_WR_ASTID          0
+#define M_FW_OFLD_CONNECTION_WR_ASTID          0xffffff
+#define V_FW_OFLD_CONNECTION_WR_ASTID(x)       \
+	((x) << S_FW_OFLD_CONNECTION_WR_ASTID)
+#define G_FW_OFLD_CONNECTION_WR_ASTID(x)       \
+	(((x) >> S_FW_OFLD_CONNECTION_WR_ASTID) & M_FW_OFLD_CONNECTION_WR_ASTID)
+
+#define S_FW_OFLD_CONNECTION_WR_CPLRXDATAACK   15
+#define M_FW_OFLD_CONNECTION_WR_CPLRXDATAACK   0x1
+#define V_FW_OFLD_CONNECTION_WR_CPLRXDATAACK(x)        \
+	((x) << S_FW_OFLD_CONNECTION_WR_CPLRXDATAACK)
+#define G_FW_OFLD_CONNECTION_WR_CPLRXDATAACK(x)        \
+	(((x) >> S_FW_OFLD_CONNECTION_WR_CPLRXDATAACK) & \
+	M_FW_OFLD_CONNECTION_WR_CPLRXDATAACK)
+#define F_FW_OFLD_CONNECTION_WR_CPLRXDATAACK   \
+	V_FW_OFLD_CONNECTION_WR_CPLRXDATAACK(1U)
+
+#define S_FW_OFLD_CONNECTION_WR_CPLPASSACCEPTRPL       14
+#define M_FW_OFLD_CONNECTION_WR_CPLPASSACCEPTRPL       0x1
+#define V_FW_OFLD_CONNECTION_WR_CPLPASSACCEPTRPL(x)    \
+	((x) << S_FW_OFLD_CONNECTION_WR_CPLPASSACCEPTRPL)
+#define G_FW_OFLD_CONNECTION_WR_CPLPASSACCEPTRPL(x)    \
+	(((x) >> S_FW_OFLD_CONNECTION_WR_CPLPASSACCEPTRPL) & \
+	M_FW_OFLD_CONNECTION_WR_CPLPASSACCEPTRPL)
+#define F_FW_OFLD_CONNECTION_WR_CPLPASSACCEPTRPL       \
+	V_FW_OFLD_CONNECTION_WR_CPLPASSACCEPTRPL(1U)
 
 enum fw_flowc_mnem {
 	FW_FLOWC_MNEM_PFNVFN,		/* PFN [15:8] VFN [7:0] */

drivers/net/ethernet/mellanox/mlx4/fw.c

···
 {
 	struct mlx4_cmd_mailbox *mailbox;
 	__be32 *outbox;
+	u32 dword_field;
 	int err;
 	u8 byte_field;
 
···
 	MLX4_GET(param->rdmarc_base,   outbox, INIT_HCA_RDMARC_BASE_OFFSET);
 	MLX4_GET(param->log_rd_per_qp, outbox, INIT_HCA_LOG_RD_OFFSET);
 
+	MLX4_GET(dword_field, outbox, INIT_HCA_FLAGS_OFFSET);
+	if (dword_field & (1 << INIT_HCA_DEVICE_MANAGED_FLOW_STEERING_EN)) {
+		param->steering_mode = MLX4_STEERING_MODE_DEVICE_MANAGED;
+	} else {
+		MLX4_GET(byte_field, outbox, INIT_HCA_UC_STEERING_OFFSET);
+		if (byte_field & 0x8)
+			param->steering_mode = MLX4_STEERING_MODE_B0;
+		else
+			param->steering_mode = MLX4_STEERING_MODE_A0;
+	}
 	/* steering attributes */
-	if (dev->caps.steering_mode ==
-	    MLX4_STEERING_MODE_DEVICE_MANAGED) {
-
+	if (param->steering_mode == MLX4_STEERING_MODE_DEVICE_MANAGED) {
 		MLX4_GET(param->mc_base, outbox, INIT_HCA_FS_BASE_OFFSET);
 		MLX4_GET(param->log_mc_entry_sz, outbox,
 			 INIT_HCA_FS_LOG_ENTRY_SZ_OFFSET);

drivers/net/ethernet/mellanox/mlx4/fw.h

···
 	u8  log_uar_sz;
 	u8  uar_page_sz; /* log pg sz in 4k chunks */
 	u8  fs_hash_enable_bits;
+	u8  steering_mode; /* for QUERY_HCA */
 	u64 dev_cap_enabled;
 };
 

drivers/net/ethernet/mellanox/mlx4/main.c

···
 module_param(probe_vf, int, 0644);
 MODULE_PARM_DESC(probe_vf, "number of vfs to probe by pf driver (num_vfs > 0)");
 
-int mlx4_log_num_mgm_entry_size = 10;
+int mlx4_log_num_mgm_entry_size = MLX4_DEFAULT_MGM_LOG_ENTRY_SIZE;
 module_param_named(log_num_mgm_entry_size,
 			mlx4_log_num_mgm_entry_size, int, 0444);
 MODULE_PARM_DESC(log_num_mgm_entry_size, "log mgm size, that defines the num"
 					 " of qp per mcg, for example:"
-					 " 10 gives 248.range: 9<="
+					 " 10 gives 248.range: 7 <="
 					 " log_num_mgm_entry_size <= 12."
-					 " Not in use with device managed"
-					 " flow steering");
+					 " To activate device managed"
+					 " flow steering when available, set to -1");
 
 static bool enable_64b_cqe_eqe;
 module_param(enable_64b_cqe_eqe, bool, 0444);
···
 	dev->caps.stat_rate_support  = dev_cap->stat_rate_support;
 	dev->caps.max_gso_sz	     = dev_cap->max_gso_sz;
 	dev->caps.max_rss_tbl_sz     = dev_cap->max_rss_tbl_sz;
-
-	if (dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_FS_EN) {
-		dev->caps.steering_mode = MLX4_STEERING_MODE_DEVICE_MANAGED;
-		dev->caps.num_qp_per_mgm = dev_cap->fs_max_num_qp_per_entry;
-		dev->caps.fs_log_max_ucast_qp_range_size =
-			dev_cap->fs_log_max_ucast_qp_range_size;
-	} else {
-		if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER &&
-		    dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER) {
-			dev->caps.steering_mode = MLX4_STEERING_MODE_B0;
-		} else {
-			dev->caps.steering_mode = MLX4_STEERING_MODE_A0;
-
-			if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER ||
-			    dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER)
-				mlx4_warn(dev, "Must have UC_STEER and MC_STEER flags "
-						"set to use B0 steering. Falling back to A0 steering mode.\n");
-		}
-		dev->caps.num_qp_per_mgm = mlx4_get_qp_per_mgm(dev);
-	}
-	mlx4_dbg(dev, "Steering mode is: %s\n",
-		 mlx4_steering_mode_str(dev->caps.steering_mode));
 
 	/* Sense port always allowed on supported devices for ConnectX-1 and -2 */
 	if (mlx4_priv(dev)->pci_dev_data & MLX4_PCI_DEV_FORCE_SENSE_PORT)
···
 }
 EXPORT_SYMBOL(mlx4_is_slave_active);
 
+static void slave_adjust_steering_mode(struct mlx4_dev *dev,
+				       struct mlx4_dev_cap *dev_cap,
+				       struct mlx4_init_hca_param *hca_param)
+{
+	dev->caps.steering_mode = hca_param->steering_mode;
+	if (dev->caps.steering_mode == MLX4_STEERING_MODE_DEVICE_MANAGED) {
+		dev->caps.num_qp_per_mgm = dev_cap->fs_max_num_qp_per_entry;
+		dev->caps.fs_log_max_ucast_qp_range_size =
+			dev_cap->fs_log_max_ucast_qp_range_size;
+	} else
+		dev->caps.num_qp_per_mgm =
+			4 * ((1 << hca_param->log_mc_entry_sz)/16 - 2);
+
+	mlx4_dbg(dev, "Steering mode is: %s\n",
+		 mlx4_steering_mode_str(dev->caps.steering_mode));
+}
+
 static int mlx4_slave_cap(struct mlx4_dev *dev)
 {
 	int			   err;
···
 	} else {
 		dev->caps.cqe_size   = 32;
 	}
+
+	slave_adjust_steering_mode(dev, &dev_cap, &hca_param);
 
 	return 0;
 
···
 	}
 }
 
+static int choose_log_fs_mgm_entry_size(int qp_per_entry)
+{
+	int i = MLX4_MIN_MGM_LOG_ENTRY_SIZE;
+
+	for (i = MLX4_MIN_MGM_LOG_ENTRY_SIZE; i <= MLX4_MAX_MGM_LOG_ENTRY_SIZE;
+	      i++) {
+		if (qp_per_entry <= 4 * ((1 << i) / 16 - 2))
+			break;
+	}
+
+	return (i <= MLX4_MAX_MGM_LOG_ENTRY_SIZE) ? i : -1;
+}
+
+static void choose_steering_mode(struct mlx4_dev *dev,
+				 struct mlx4_dev_cap *dev_cap)
+{
+	if (mlx4_log_num_mgm_entry_size == -1 &&
+	    dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_FS_EN &&
+	    (!mlx4_is_mfunc(dev) ||
+	     (dev_cap->fs_max_num_qp_per_entry >= (num_vfs + 1))) &&
+	    choose_log_fs_mgm_entry_size(dev_cap->fs_max_num_qp_per_entry) >=
+		MLX4_MIN_MGM_LOG_ENTRY_SIZE) {
+		dev->oper_log_mgm_entry_size =
+			choose_log_fs_mgm_entry_size(dev_cap->fs_max_num_qp_per_entry);
+		dev->caps.steering_mode = MLX4_STEERING_MODE_DEVICE_MANAGED;
+		dev->caps.num_qp_per_mgm = dev_cap->fs_max_num_qp_per_entry;
+		dev->caps.fs_log_max_ucast_qp_range_size =
+			dev_cap->fs_log_max_ucast_qp_range_size;
+	} else {
+		if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER &&
+		    dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER)
+			dev->caps.steering_mode = MLX4_STEERING_MODE_B0;
+		else {
+			dev->caps.steering_mode = MLX4_STEERING_MODE_A0;
+
+			if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER ||
+			    dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER)
+				mlx4_warn(dev, "Must have both UC_STEER and MC_STEER flags "
+					  "set to use B0 steering. Falling back to A0 steering mode.\n");
+		}
+		dev->oper_log_mgm_entry_size =
+			mlx4_log_num_mgm_entry_size > 0 ?
+			mlx4_log_num_mgm_entry_size :
+			MLX4_DEFAULT_MGM_LOG_ENTRY_SIZE;
+		dev->caps.num_qp_per_mgm = mlx4_get_qp_per_mgm(dev);
+	}
+	mlx4_dbg(dev, "Steering mode is: %s, oper_log_mgm_entry_size = %d, "
+		 "modparam log_num_mgm_entry_size = %d\n",
+		 mlx4_steering_mode_str(dev->caps.steering_mode),
+		 dev->oper_log_mgm_entry_size,
+		 mlx4_log_num_mgm_entry_size);
+}
+
 static int mlx4_init_hca(struct mlx4_dev *dev)
 {
 	struct mlx4_priv	  *priv = mlx4_priv(dev);
···
 			mlx4_err(dev, "QUERY_DEV_CAP command failed, aborting.\n");
 			goto err_stop_fw;
 		}
+
+		choose_steering_mode(dev, &dev_cap);
 
 		if (mlx4_is_master(dev))
 			mlx4_parav_master_pf_caps(dev);
···
 	if (port_type_array[0] == false && port_type_array[1] == true) {
 		printk(KERN_WARNING "Module parameter configuration ETH/IB is not supported. Switching to default configuration IB/IB\n");
 		port_type_array[0] = true;
+	}
+
+	if (mlx4_log_num_mgm_entry_size != -1 &&
+	    (mlx4_log_num_mgm_entry_size < MLX4_MIN_MGM_LOG_ENTRY_SIZE ||
+	     mlx4_log_num_mgm_entry_size > MLX4_MAX_MGM_LOG_ENTRY_SIZE)) {
+		pr_warning("mlx4_core: mlx4_log_num_mgm_entry_size (%d) not "
+			   "in legal range (-1 or %d..%d)\n",
+			   mlx4_log_num_mgm_entry_size,
+			   MLX4_MIN_MGM_LOG_ENTRY_SIZE,
+			   MLX4_MAX_MGM_LOG_ENTRY_SIZE);
+		return -1;
 	}
 
 	return 0;

drivers/net/ethernet/mellanox/mlx4/mcg.c

···
 
 int mlx4_get_mgm_entry_size(struct mlx4_dev *dev)
 {
-	if (dev->caps.steering_mode ==
-	    MLX4_STEERING_MODE_DEVICE_MANAGED)
-		return 1 << MLX4_FS_MGM_LOG_ENTRY_SIZE;
-	else
-		return min((1 << mlx4_log_num_mgm_entry_size),
-			   MLX4_MAX_MGM_ENTRY_SIZE);
+	return 1 << dev->oper_log_mgm_entry_size;
 }
 
 int mlx4_get_qp_per_mgm(struct mlx4_dev *dev)

drivers/net/ethernet/mellanox/mlx4/mlx4.h

···
 };
 
 enum {
-	MLX4_MAX_MGM_ENTRY_SIZE = 0x1000,
-	MLX4_MAX_QP_PER_MGM	= 4 * (MLX4_MAX_MGM_ENTRY_SIZE / 16 - 2),
+	MLX4_DEFAULT_MGM_LOG_ENTRY_SIZE = 10,
+	MLX4_MIN_MGM_LOG_ENTRY_SIZE = 7,
+	MLX4_MAX_MGM_LOG_ENTRY_SIZE = 12,
+	MLX4_MAX_QP_PER_MGM = 4 * ((1 << MLX4_MAX_MGM_LOG_ENTRY_SIZE) / 16 - 2),
 	MLX4_MTT_ENTRY_PER_SEG	= 8,
 };
 

drivers/net/ethernet/mellanox/mlx4/resource_tracker.c

···
 	struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker;
 	struct list_head *rlist = &tracker->slave_list[slave].res_list[RES_MAC];
 	int err;
+	int qpn;
 	struct mlx4_net_trans_rule_hw_ctrl *ctrl;
 	struct _rule_hw  *rule_header;
 	int header_id;
···
 		return -EOPNOTSUPP;
 
 	ctrl = (struct mlx4_net_trans_rule_hw_ctrl *)inbox->buf;
+	qpn = be32_to_cpu(ctrl->qpn) & 0xffffff;
+	err = get_res(dev, slave, qpn, RES_QP, NULL);
+	if (err) {
+		pr_err("Steering rule with qpn 0x%x rejected.\n", qpn);
+		return err;
+	}
 	rule_header = (struct _rule_hw *)(ctrl + 1);
 	header_id = map_hw_to_sw_id(be16_to_cpu(rule_header->id));
 
 	switch (header_id) {
 	case MLX4_NET_TRANS_RULE_ID_ETH:
-		if (validate_eth_header_mac(slave, rule_header, rlist))
-			return -EINVAL;
+		if (validate_eth_header_mac(slave, rule_header, rlist)) {
+			err = -EINVAL;
+			goto err_put;
+		}
 		break;
 	case MLX4_NET_TRANS_RULE_ID_IB:
 		break;
···
 	case MLX4_NET_TRANS_RULE_ID_TCP:
 	case MLX4_NET_TRANS_RULE_ID_UDP:
 		pr_warn("Can't attach FS rule without L2 headers, adding L2 header.\n");
-		if (add_eth_header(dev, slave, inbox, rlist, header_id))
-			return -EINVAL;
+		if (add_eth_header(dev, slave, inbox, rlist, header_id)) {
+			err = -EINVAL;
+			goto err_put;
+		}
 		vhcr->in_modifier +=
 			sizeof(struct mlx4_net_trans_rule_hw_eth) >> 2;
 		break;
 	default:
 		pr_err("Corrupted mailbox.\n");
-		return -EINVAL;
+		err = -EINVAL;
+		goto err_put;
 	}
 
 	err = mlx4_cmd_imm(dev, inbox->dma, &vhcr->out_param,
···
 			   MLX4_QP_FLOW_STEERING_ATTACH, MLX4_CMD_TIME_CLASS_A,
 			   MLX4_CMD_NATIVE);
 	if (err)
-		return err;
+		goto err_put;
 
 	err = add_res_range(dev, slave, vhcr->out_param, 1, RES_FS_RULE, 0);
 	if (err) {
 		mlx4_err(dev, "Fail to add flow steering resources.\n ");
 		/* detach rule*/
 		mlx4_cmd(dev, vhcr->out_param, 0, 0,
-			 MLX4_QP_FLOW_STEERING_ATTACH, MLX4_CMD_TIME_CLASS_A,
+			 MLX4_QP_FLOW_STEERING_DETACH, MLX4_CMD_TIME_CLASS_A,
 			 MLX4_CMD_NATIVE);
 	}
+err_put:
+	put_res(dev, slave, qpn, RES_QP);
 	return err;
 }
 

drivers/scsi/csiostor/t4fw_api_stor.h

···
  *   R E T U R N   V A L U E S
  ********************************/
 
-enum fw_retval {
-	FW_SUCCESS		= 0,	/* completed sucessfully */
-	FW_EPERM		= 1,	/* operation not permitted */
-	FW_ENOENT		= 2,	/* no such file or directory */
-	FW_EIO			= 5,	/* input/output error; hw bad */
-	FW_ENOEXEC		= 8,	/* exec format error; inv microcode */
-	FW_EAGAIN		= 11,	/* try again */
-	FW_ENOMEM		= 12,	/* out of memory */
-	FW_EFAULT		= 14,	/* bad address; fw bad */
-	FW_EBUSY		= 16,	/* resource busy */
-	FW_EEXIST		= 17,	/* file exists */
-	FW_EINVAL		= 22,	/* invalid argument */
-	FW_ENOSPC		= 28,	/* no space left on device */
-	FW_ENOSYS		= 38,	/* functionality not implemented */
-	FW_EPROTO		= 71,	/* protocol error */
-	FW_EADDRINUSE		= 98,	/* address already in use */
-	FW_EADDRNOTAVAIL	= 99,	/* cannot assigned requested address */
-	FW_ENETDOWN		= 100,	/* network is down */
-	FW_ENETUNREACH		= 101,	/* network is unreachable */
-	FW_ENOBUFS		= 105,	/* no buffer space available */
-	FW_ETIMEDOUT		= 110,	/* timeout */
-	FW_EINPROGRESS		= 115,	/* fw internal */
-	FW_SCSI_ABORT_REQUESTED	= 128,	/* */
-	FW_SCSI_ABORT_TIMEDOUT	= 129,	/* */
-	FW_SCSI_ABORTED		= 130,	/* */
-	FW_SCSI_CLOSE_REQUESTED	= 131,	/* */
-	FW_ERR_LINK_DOWN	= 132,	/* */
-	FW_RDEV_NOT_READY	= 133,	/* */
-	FW_ERR_RDEV_LOST	= 134,	/* */
-	FW_ERR_RDEV_LOGO	= 135,	/* */
-	FW_FCOE_NO_XCHG		= 136,	/* */
-	FW_SCSI_RSP_ERR		= 137,	/* */
-	FW_ERR_RDEV_IMPL_LOGO	= 138,	/* */
-	FW_SCSI_UNDER_FLOW_ERR  = 139,	/* */
-	FW_SCSI_OVER_FLOW_ERR   = 140,	/* */
-	FW_SCSI_DDP_ERR		= 141,	/* DDP error*/
-	FW_SCSI_TASK_ERR	= 142,	/* No SCSI tasks available */
-};
-
 enum fw_fcoe_link_sub_op {
 	FCOE_LINK_DOWN	= 0x0,
 	FCOE_LINK_UP	= 0x1,

include/linux/mlx4/device.h

···
 	u8			rev_id;
 	char			board_id[MLX4_BOARD_ID_LEN];
 	int			num_vfs;
+	int			oper_log_mgm_entry_size;
 	u64			regid_promisc_array[MLX4_MAX_PORTS + 1];
 	u64			regid_allmulti_array[MLX4_MAX_PORTS + 1];
 };