Merge branch 'for-next-merge' of git://git.kernel.org/pub/scm/linux/kernel/git/nab/target-pending

Pull more SCSI target updates from Nicholas Bellinger:
 "This series contains cxgb4 driver prerequisites for supporting iscsi
  segmentation offload (ISO), that will be utilized for a number of
  future v4.7 developments in iscsi-target for supporting generic hw
  offloads"

* 'for-next-merge' of git://git.kernel.org/pub/scm/linux/kernel/git/nab/target-pending:
  cxgb4: update Kconfig and Makefile
  cxgb4: add iSCSI DDP page pod manager
  cxgb4, iw_cxgb4: move delayed ack macro definitions
  cxgb4: move VLAN_NONE macro definition
  cxgb4: update struct cxgb4_lld_info definition
  cxgb4: add definitions for iSCSI target ULD
  cxgb4, cxgb4i: move struct cpl_rx_data_ddp definition
  cxgb4, iw_cxgb4, cxgb4i: remove duplicate definitions
  cxgb4, iw_cxgb4: move definitions to common header file
  cxgb4: large receive offload support
  cxgb4: allocate resources for CXGB4_ULD_ISCSIT
  cxgb4: add new ULD type CXGB4_ULD_ISCSIT

13 files changed, 1174 insertions, 23 deletions

diff --git a/drivers/net/ethernet/chelsio/Kconfig b/drivers/net/ethernet/chelsio/Kconfig
index 4d187f22c48b..4686a85a8a22 100644
--- a/drivers/net/ethernet/chelsio/Kconfig
+++ b/drivers/net/ethernet/chelsio/Kconfig
@@ -96,6 +96,17 @@ config CHELSIO_T4_DCB
 
 	  If unsure, say N.
 
+config CHELSIO_T4_UWIRE
+	bool "Unified Wire Support for Chelsio T5 cards"
+	default n
+	depends on CHELSIO_T4
+	---help---
+	  Enable unified-wire offload features.
+	  Say Y here if you want to enable unified-wire over Ethernet
+	  in the driver.
+
+	  If unsure, say N.
+
 config CHELSIO_T4_FCOE
 	bool "Fibre Channel over Ethernet (FCoE) Support for Chelsio T5 cards"
 	default n
diff --git a/drivers/net/ethernet/chelsio/cxgb4/Makefile b/drivers/net/ethernet/chelsio/cxgb4/Makefile
index ace0ab98d0f1..85c92821b239 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/Makefile
+++ b/drivers/net/ethernet/chelsio/cxgb4/Makefile
@@ -7,4 +7,5 @@ obj-$(CONFIG_CHELSIO_T4) += cxgb4.o
 cxgb4-objs := cxgb4_main.o l2t.o t4_hw.o sge.o clip_tbl.o cxgb4_ethtool.o
 cxgb4-$(CONFIG_CHELSIO_T4_DCB) +=  cxgb4_dcb.o
 cxgb4-$(CONFIG_CHELSIO_T4_FCOE) +=  cxgb4_fcoe.o
+cxgb4-$(CONFIG_CHELSIO_T4_UWIRE) +=  cxgb4_ppm.o
 cxgb4-$(CONFIG_DEBUG_FS) += cxgb4_debugfs.o
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index 1dac6c6111bf..984a3cc26f86 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -404,6 +404,9 @@ enum {
 	MAX_CTRL_QUEUES = NCHAN,      /* # of control Tx queues */
 	MAX_RDMA_QUEUES = NCHAN,      /* # of streaming RDMA Rx queues */
 	MAX_RDMA_CIQS = 32,        /* # of  RDMA concentrator IQs */
+
+	/* # of streaming iSCSIT Rx queues */
+	MAX_ISCSIT_QUEUES = MAX_OFLD_QSETS,
 };
 
 enum {
@@ -420,8 +423,8 @@ enum {
 enum {
 	INGQ_EXTRAS = 2,        /* firmware event queue and */
 				/*   forwarded interrupts */
-	MAX_INGQ = MAX_ETH_QSETS + MAX_OFLD_QSETS + MAX_RDMA_QUEUES
-		   + MAX_RDMA_CIQS + INGQ_EXTRAS,
+	MAX_INGQ = MAX_ETH_QSETS + MAX_OFLD_QSETS + MAX_RDMA_QUEUES +
+		   MAX_RDMA_CIQS + MAX_ISCSIT_QUEUES + INGQ_EXTRAS,
 };
 
 struct adapter;
@@ -508,6 +511,15 @@ struct pkt_gl {
 
 typedef int (*rspq_handler_t)(struct sge_rspq *q, const __be64 *rsp,
 			      const struct pkt_gl *gl);
+typedef void (*rspq_flush_handler_t)(struct sge_rspq *q);
+/* LRO related declarations for ULD */
+struct t4_lro_mgr {
+#define MAX_LRO_SESSIONS		64
+	u8 lro_session_cnt;         /* # of sessions to aggregate */
+	unsigned long lro_pkts;     /* # of LRO super packets */
+	unsigned long lro_merged;   /* # of wire packets merged by LRO */
+	struct sk_buff_head lroq;   /* list of aggregated sessions */
+};
 
 struct sge_rspq {                   /* state for an SGE response queue */
 	struct napi_struct napi;
@@ -532,6 +544,8 @@ struct sge_rspq {                   /* state for an SGE response queue */
 	struct adapter *adap;
 	struct net_device *netdev;  /* associated net device */
 	rspq_handler_t handler;
+	rspq_flush_handler_t flush_handler;
+	struct t4_lro_mgr lro_mgr;
 #ifdef CONFIG_NET_RX_BUSY_POLL
 #define CXGB_POLL_STATE_IDLE		0
 #define CXGB_POLL_STATE_NAPI		BIT(0) /* NAPI owns this poll */
@@ -641,6 +655,7 @@ struct sge {
 
 	struct sge_eth_rxq ethrxq[MAX_ETH_QSETS];
 	struct sge_ofld_rxq iscsirxq[MAX_OFLD_QSETS];
+	struct sge_ofld_rxq iscsitrxq[MAX_ISCSIT_QUEUES];
 	struct sge_ofld_rxq rdmarxq[MAX_RDMA_QUEUES];
 	struct sge_ofld_rxq rdmaciq[MAX_RDMA_CIQS];
 	struct sge_rspq fw_evtq ____cacheline_aligned_in_smp;
@@ -652,9 +667,11 @@ struct sge {
 	u16 ethqsets;               /* # of active Ethernet queue sets */
 	u16 ethtxq_rover;           /* Tx queue to clean up next */
 	u16 iscsiqsets;              /* # of active iSCSI queue sets */
+	u16 niscsitq;               /* # of available iSCST Rx queues */
 	u16 rdmaqs;                 /* # of available RDMA Rx queues */
 	u16 rdmaciqs;               /* # of available RDMA concentrator IQs */
 	u16 iscsi_rxq[MAX_OFLD_QSETS];
+	u16 iscsit_rxq[MAX_ISCSIT_QUEUES];
 	u16 rdma_rxq[MAX_RDMA_QUEUES];
 	u16 rdma_ciq[MAX_RDMA_CIQS];
 	u16 timer_val[SGE_NTIMERS];
@@ -681,6 +698,7 @@ struct sge {
 
 #define for_each_ethrxq(sge, i) for (i = 0; i < (sge)->ethqsets; i++)
 #define for_each_iscsirxq(sge, i) for (i = 0; i < (sge)->iscsiqsets; i++)
+#define for_each_iscsitrxq(sge, i) for (i = 0; i < (sge)->niscsitq; i++)
 #define for_each_rdmarxq(sge, i) for (i = 0; i < (sge)->rdmaqs; i++)
 #define for_each_rdmaciq(sge, i) for (i = 0; i < (sge)->rdmaciqs; i++)
 
@@ -747,6 +765,8 @@ struct adapter {
 	struct list_head rcu_node;
 	struct list_head mac_hlist; /* list of MAC addresses in MPS Hash */
 
+	void *iscsi_ppm;
+
 	struct tid_info tids;
 	void **tid_release_head;
 	spinlock_t tid_release_lock;
@@ -1113,7 +1133,8 @@ int t4_mgmt_tx(struct adapter *adap, struct sk_buff *skb);
 int t4_ofld_send(struct adapter *adap, struct sk_buff *skb);
 int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq,
 		     struct net_device *dev, int intr_idx,
-		     struct sge_fl *fl, rspq_handler_t hnd, int cong);
+		     struct sge_fl *fl, rspq_handler_t hnd,
+		     rspq_flush_handler_t flush_handler, int cong);
 int t4_sge_alloc_eth_txq(struct adapter *adap, struct sge_eth_txq *txq,
 			 struct net_device *dev, struct netdev_queue *netdevq,
 			 unsigned int iqid);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
index e6a4072b494b..0bb41e9b9b1c 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
@@ -2334,12 +2334,14 @@ static int sge_qinfo_show(struct seq_file *seq, void *v)
 	struct adapter *adap = seq->private;
 	int eth_entries = DIV_ROUND_UP(adap->sge.ethqsets, 4);
 	int iscsi_entries = DIV_ROUND_UP(adap->sge.iscsiqsets, 4);
+	int iscsit_entries = DIV_ROUND_UP(adap->sge.niscsitq, 4);
 	int rdma_entries = DIV_ROUND_UP(adap->sge.rdmaqs, 4);
 	int ciq_entries = DIV_ROUND_UP(adap->sge.rdmaciqs, 4);
 	int ctrl_entries = DIV_ROUND_UP(MAX_CTRL_QUEUES, 4);
 	int i, r = (uintptr_t)v - 1;
 	int iscsi_idx = r - eth_entries;
-	int rdma_idx = iscsi_idx - iscsi_entries;
+	int iscsit_idx = iscsi_idx - iscsi_entries;
+	int rdma_idx = iscsit_idx - iscsit_entries;
 	int ciq_idx = rdma_idx - rdma_entries;
 	int ctrl_idx =  ciq_idx - ciq_entries;
 	int fq_idx =  ctrl_idx - ctrl_entries;
@@ -2453,6 +2455,35 @@ do { \
 		RL("FLLow:", fl.low);
 		RL("FLStarving:", fl.starving);
 
+	} else if (iscsit_idx < iscsit_entries) {
+		const struct sge_ofld_rxq *rx =
+			&adap->sge.iscsitrxq[iscsit_idx * 4];
+		int n = min(4, adap->sge.niscsitq - 4 * iscsit_idx);
+
+		S("QType:", "iSCSIT");
+		R("RspQ ID:", rspq.abs_id);
+		R("RspQ size:", rspq.size);
+		R("RspQE size:", rspq.iqe_len);
+		R("RspQ CIDX:", rspq.cidx);
+		R("RspQ Gen:", rspq.gen);
+		S3("u", "Intr delay:", qtimer_val(adap, &rx[i].rspq));
+		S3("u", "Intr pktcnt:",
+		   adap->sge.counter_val[rx[i].rspq.pktcnt_idx]);
+		R("FL ID:", fl.cntxt_id);
+		R("FL size:", fl.size - 8);
+		R("FL pend:", fl.pend_cred);
+		R("FL avail:", fl.avail);
+		R("FL PIDX:", fl.pidx);
+		R("FL CIDX:", fl.cidx);
+		RL("RxPackets:", stats.pkts);
+		RL("RxImmPkts:", stats.imm);
+		RL("RxNoMem:", stats.nomem);
+		RL("FLAllocErr:", fl.alloc_failed);
+		RL("FLLrgAlcErr:", fl.large_alloc_failed);
+		RL("FLMapErr:", fl.mapping_err);
+		RL("FLLow:", fl.low);
+		RL("FLStarving:", fl.starving);
+
 	} else if (rdma_idx < rdma_entries) {
 		const struct sge_ofld_rxq *rx =
 				&adap->sge.rdmarxq[rdma_idx * 4];
@@ -2543,6 +2574,7 @@ static int sge_queue_entries(const struct adapter *adap)
 {
 	return DIV_ROUND_UP(adap->sge.ethqsets, 4) +
 	       DIV_ROUND_UP(adap->sge.iscsiqsets, 4) +
+	       DIV_ROUND_UP(adap->sge.niscsitq, 4) +
 	       DIV_ROUND_UP(adap->sge.rdmaqs, 4) +
 	       DIV_ROUND_UP(adap->sge.rdmaciqs, 4) +
 	       DIV_ROUND_UP(MAX_CTRL_QUEUES, 4) + 1;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index adad73f7c8cd..d1e3f0997d6b 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -227,7 +227,7 @@ static DEFINE_MUTEX(uld_mutex);
 static LIST_HEAD(adap_rcu_list);
 static DEFINE_SPINLOCK(adap_rcu_lock);
 static struct cxgb4_uld_info ulds[CXGB4_ULD_MAX];
-static const char *uld_str[] = { "RDMA", "iSCSI" };
+static const char *const uld_str[] = { "RDMA", "iSCSI", "iSCSIT" };
 
 static void link_report(struct net_device *dev)
 {
@@ -664,6 +664,13 @@ out:
 	return 0;
 }
 
+/* Flush the aggregated lro sessions */
+static void uldrx_flush_handler(struct sge_rspq *q)
+{
+	if (ulds[q->uld].lro_flush)
+		ulds[q->uld].lro_flush(&q->lro_mgr);
+}
+
 /**
  *	uldrx_handler - response queue handler for ULD queues
  *	@q: the response queue that received the packet
@@ -677,6 +684,7 @@ static int uldrx_handler(struct sge_rspq *q, const __be64 *rsp,
 			 const struct pkt_gl *gl)
 {
 	struct sge_ofld_rxq *rxq = container_of(q, struct sge_ofld_rxq, rspq);
+	int ret;
 
 	/* FW can send CPLs encapsulated in a CPL_FW4_MSG.
 	 */
@@ -684,10 +692,19 @@ static int uldrx_handler(struct sge_rspq *q, const __be64 *rsp,
 	    ((const struct cpl_fw4_msg *)(rsp + 1))->type == FW_TYPE_RSSCPL)
 		rsp += 2;
 
-	if (ulds[q->uld].rx_handler(q->adap->uld_handle[q->uld], rsp, gl)) {
+	if (q->flush_handler)
+		ret = ulds[q->uld].lro_rx_handler(q->adap->uld_handle[q->uld],
+						  rsp, gl, &q->lro_mgr,
+						  &q->napi);
+	else
+		ret = ulds[q->uld].rx_handler(q->adap->uld_handle[q->uld],
+					      rsp, gl);
+
+	if (ret) {
 		rxq->stats.nomem++;
 		return -1;
 	}
+
 	if (gl == NULL)
 		rxq->stats.imm++;
 	else if (gl == CXGB4_MSG_AN)
@@ -754,6 +771,10 @@ static void name_msix_vecs(struct adapter *adap)
 		snprintf(adap->msix_info[msi_idx++].desc, n, "%s-iscsi%d",
 			 adap->port[0]->name, i);
 
+	for_each_iscsitrxq(&adap->sge, i)
+		snprintf(adap->msix_info[msi_idx++].desc, n, "%s-iSCSIT%d",
+			 adap->port[0]->name, i);
+
 	for_each_rdmarxq(&adap->sge, i)
 		snprintf(adap->msix_info[msi_idx++].desc, n, "%s-rdma%d",
 			 adap->port[0]->name, i);
@@ -767,6 +788,7 @@ static int request_msix_queue_irqs(struct adapter *adap)
 {
 	struct sge *s = &adap->sge;
 	int err, ethqidx, iscsiqidx = 0, rdmaqidx = 0, rdmaciqqidx = 0;
+	int iscsitqidx = 0;
 	int msi_index = 2;
 
 	err = request_irq(adap->msix_info[1].vec, t4_sge_intr_msix, 0,
@@ -792,6 +814,15 @@ static int request_msix_queue_irqs(struct adapter *adap)
 			goto unwind;
 		msi_index++;
 	}
+	for_each_iscsitrxq(s, iscsitqidx) {
+		err = request_irq(adap->msix_info[msi_index].vec,
+				  t4_sge_intr_msix, 0,
+				  adap->msix_info[msi_index].desc,
+				  &s->iscsitrxq[iscsitqidx].rspq);
+		if (err)
+			goto unwind;
+		msi_index++;
+	}
 	for_each_rdmarxq(s, rdmaqidx) {
 		err = request_irq(adap->msix_info[msi_index].vec,
 				  t4_sge_intr_msix, 0,
@@ -819,6 +850,9 @@ unwind:
 	while (--rdmaqidx >= 0)
 		free_irq(adap->msix_info[--msi_index].vec,
 			 &s->rdmarxq[rdmaqidx].rspq);
+	while (--iscsitqidx >= 0)
+		free_irq(adap->msix_info[--msi_index].vec,
+			 &s->iscsitrxq[iscsitqidx].rspq);
 	while (--iscsiqidx >= 0)
 		free_irq(adap->msix_info[--msi_index].vec,
 			 &s->iscsirxq[iscsiqidx].rspq);
@@ -840,6 +874,9 @@ static void free_msix_queue_irqs(struct adapter *adap)
 	for_each_iscsirxq(s, i)
 		free_irq(adap->msix_info[msi_index++].vec,
 			 &s->iscsirxq[i].rspq);
+	for_each_iscsitrxq(s, i)
+		free_irq(adap->msix_info[msi_index++].vec,
+			 &s->iscsitrxq[i].rspq);
 	for_each_rdmarxq(s, i)
 		free_irq(adap->msix_info[msi_index++].vec, &s->rdmarxq[i].rspq);
 	for_each_rdmaciq(s, i)
@@ -984,7 +1021,7 @@ static void enable_rx(struct adapter *adap)
 
 static int alloc_ofld_rxqs(struct adapter *adap, struct sge_ofld_rxq *q,
 			   unsigned int nq, unsigned int per_chan, int msi_idx,
-			   u16 *ids)
+			   u16 *ids, bool lro)
 {
 	int i, err;
 
@@ -994,7 +1031,9 @@ static int alloc_ofld_rxqs(struct adapter *adap, struct sge_ofld_rxq *q,
 		err = t4_sge_alloc_rxq(adap, &q->rspq, false,
 				       adap->port[i / per_chan],
 				       msi_idx, q->fl.size ? &q->fl : NULL,
-				       uldrx_handler, 0);
+				       uldrx_handler,
+				       lro ? uldrx_flush_handler : NULL,
+				       0);
 		if (err)
 			return err;
 		memset(&q->stats, 0, sizeof(q->stats));
@@ -1024,7 +1063,7 @@ static int setup_sge_queues(struct adapter *adap)
 		msi_idx = 1;         /* vector 0 is for non-queue interrupts */
 	else {
 		err = t4_sge_alloc_rxq(adap, &s->intrq, false, adap->port[0], 0,
-				       NULL, NULL, -1);
+				       NULL, NULL, NULL, -1);
 		if (err)
 			return err;
 		msi_idx = -((int)s->intrq.abs_id + 1);
@@ -1044,7 +1083,7 @@ static int setup_sge_queues(struct adapter *adap)
 	 *    new/deleted queues.
 	 */
 	err = t4_sge_alloc_rxq(adap, &s->fw_evtq, true, adap->port[0],
-			       msi_idx, NULL, fwevtq_handler, -1);
+			       msi_idx, NULL, fwevtq_handler, NULL, -1);
 	if (err) {
 freeout:	t4_free_sge_resources(adap);
 		return err;
@@ -1062,6 +1101,7 @@ freeout:	t4_free_sge_resources(adap);
 			err = t4_sge_alloc_rxq(adap, &q->rspq, false, dev,
 					       msi_idx, &q->fl,
 					       t4_ethrx_handler,
+					       NULL,
 					       t4_get_mps_bg_map(adap,
 								 pi->tx_chan));
 			if (err)
@@ -1087,18 +1127,19 @@ freeout:	t4_free_sge_resources(adap);
 			goto freeout;
 	}
 
-#define ALLOC_OFLD_RXQS(firstq, nq, per_chan, ids) do { \
-	err = alloc_ofld_rxqs(adap, firstq, nq, per_chan, msi_idx, ids); \
+#define ALLOC_OFLD_RXQS(firstq, nq, per_chan, ids, lro) do { \
+	err = alloc_ofld_rxqs(adap, firstq, nq, per_chan, msi_idx, ids, lro); \
 	if (err) \
 		goto freeout; \
 	if (msi_idx > 0) \
 		msi_idx += nq; \
 } while (0)
 
-	ALLOC_OFLD_RXQS(s->iscsirxq, s->iscsiqsets, j, s->iscsi_rxq);
-	ALLOC_OFLD_RXQS(s->rdmarxq, s->rdmaqs, 1, s->rdma_rxq);
+	ALLOC_OFLD_RXQS(s->iscsirxq, s->iscsiqsets, j, s->iscsi_rxq, false);
+	ALLOC_OFLD_RXQS(s->iscsitrxq, s->niscsitq, j, s->iscsit_rxq, true);
+	ALLOC_OFLD_RXQS(s->rdmarxq, s->rdmaqs, 1, s->rdma_rxq, false);
 	j = s->rdmaciqs / adap->params.nports; /* rdmaq queues per channel */
-	ALLOC_OFLD_RXQS(s->rdmaciq, s->rdmaciqs, j, s->rdma_ciq);
+	ALLOC_OFLD_RXQS(s->rdmaciq, s->rdmaciqs, j, s->rdma_ciq, false);
 
 #undef ALLOC_OFLD_RXQS
 
@@ -2430,6 +2471,9 @@ static void uld_attach(struct adapter *adap, unsigned int uld)
 	} else if (uld == CXGB4_ULD_ISCSI) {
 		lli.rxq_ids = adap->sge.iscsi_rxq;
 		lli.nrxq = adap->sge.iscsiqsets;
+	} else if (uld == CXGB4_ULD_ISCSIT) {
+		lli.rxq_ids = adap->sge.iscsit_rxq;
+		lli.nrxq = adap->sge.niscsitq;
 	}
 	lli.ntxq = adap->sge.iscsiqsets;
 	lli.nchan = adap->params.nports;
@@ -2437,6 +2481,10 @@ static void uld_attach(struct adapter *adap, unsigned int uld)
 	lli.wr_cred = adap->params.ofldq_wr_cred;
 	lli.adapter_type = adap->params.chip;
 	lli.iscsi_iolen = MAXRXDATA_G(t4_read_reg(adap, TP_PARA_REG2_A));
+	lli.iscsi_tagmask = t4_read_reg(adap, ULP_RX_ISCSI_TAGMASK_A);
+	lli.iscsi_pgsz_order = t4_read_reg(adap, ULP_RX_ISCSI_PSZ_A);
+	lli.iscsi_llimit = t4_read_reg(adap, ULP_RX_ISCSI_LLIMIT_A);
+	lli.iscsi_ppm = &adap->iscsi_ppm;
 	lli.cclk_ps = 1000000000 / adap->params.vpd.cclk;
 	lli.udb_density = 1 << adap->params.sge.eq_qpp;
 	lli.ucq_density = 1 << adap->params.sge.iq_qpp;
@@ -4336,6 +4384,9 @@ static void cfg_queues(struct adapter *adap)
 		s->rdmaciqs = (s->rdmaciqs / adap->params.nports) *
 				adap->params.nports;
 		s->rdmaciqs = max_t(int, s->rdmaciqs, adap->params.nports);
+
+		if (!is_t4(adap->params.chip))
+			s->niscsitq = s->iscsiqsets;
 	}
 
 	for (i = 0; i < ARRAY_SIZE(s->ethrxq); i++) {
@@ -4362,6 +4413,16 @@ static void cfg_queues(struct adapter *adap)
 		r->fl.size = 72;
 	}
 
+	if (!is_t4(adap->params.chip)) {
+		for (i = 0; i < ARRAY_SIZE(s->iscsitrxq); i++) {
+			struct sge_ofld_rxq *r = &s->iscsitrxq[i];
+
+			init_rspq(adap, &r->rspq, 5, 1, 1024, 64);
+			r->rspq.uld = CXGB4_ULD_ISCSIT;
+			r->fl.size = 72;
+		}
+	}
+
 	for (i = 0; i < ARRAY_SIZE(s->rdmarxq); i++) {
 		struct sge_ofld_rxq *r = &s->rdmarxq[i];
 
@@ -4436,9 +4497,13 @@ static int enable_msix(struct adapter *adap)
 
 	want = s->max_ethqsets + EXTRA_VECS;
 	if (is_offload(adap)) {
-		want += s->rdmaqs + s->rdmaciqs + s->iscsiqsets;
+		want += s->rdmaqs + s->rdmaciqs + s->iscsiqsets	+
+			s->niscsitq;
 		/* need nchan for each possible ULD */
-		ofld_need = 3 * nchan;
+		if (is_t4(adap->params.chip))
+			ofld_need = 3 * nchan;
+		else
+			ofld_need = 4 * nchan;
 	}
 #ifdef CONFIG_CHELSIO_T4_DCB
 	/* For Data Center Bridging we need 8 Ethernet TX Priority Queues for
@@ -4470,12 +4535,16 @@ static int enable_msix(struct adapter *adap)
 		if (allocated < want) {
 			s->rdmaqs = nchan;
 			s->rdmaciqs = nchan;
+
+			if (!is_t4(adap->params.chip))
+				s->niscsitq = nchan;
 		}
 
 		/* leftovers go to OFLD */
 		i = allocated - EXTRA_VECS - s->max_ethqsets -
-		    s->rdmaqs - s->rdmaciqs;
+		    s->rdmaqs - s->rdmaciqs - s->niscsitq;
 		s->iscsiqsets = (i / nchan) * nchan;  /* round down */
+
 	}
 	for (i = 0; i < allocated; ++i)
 		adap->msix_info[i].vec = entries[i].vector;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ppm.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ppm.c
new file mode 100644
index 000000000000..d88a7a7b2400
--- /dev/null
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ppm.c
@@ -0,0 +1,464 @@
+/*
+ * cxgb4_ppm.c: Chelsio common library for T4/T5 iSCSI PagePod Manager
+ *
+ * Copyright (c) 2016 Chelsio Communications, Inc. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Written by: Karen Xie (kxie@chelsio.com)
+ */
+
+#include <linux/kernel.h>
+#include <linux/version.h>
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/debugfs.h>
+#include <linux/export.h>
+#include <linux/list.h>
+#include <linux/skbuff.h>
+#include <linux/pci.h>
+#include <linux/scatterlist.h>
+
+#include "cxgb4_ppm.h"
+
+/* Direct Data Placement -
+ * Directly place the iSCSI Data-In or Data-Out PDU's payload into
+ * pre-posted final destination host-memory buffers based on the
+ * Initiator Task Tag (ITT) in Data-In or Target Task Tag (TTT)
+ * in Data-Out PDUs. The host memory address is programmed into
+ * h/w in the format of pagepod entries. The location of the
+ * pagepod entry is encoded into ddp tag which is used as the base
+ * for ITT/TTT.
+ */
+
+/* Direct-Data Placement page size adjustment
+ */
+int cxgbi_ppm_find_page_index(struct cxgbi_ppm *ppm, unsigned long pgsz)
+{
+	struct cxgbi_tag_format *tformat = &ppm->tformat;
+	int i;
+
+	for (i = 0; i < DDP_PGIDX_MAX; i++) {
+		if (pgsz == 1UL << (DDP_PGSZ_BASE_SHIFT +
+					 tformat->pgsz_order[i])) {
+			pr_debug("%s: %s ppm, pgsz %lu -> idx %d.\n",
+				 __func__, ppm->ndev->name, pgsz, i);
+			return i;
+		}
+	}
+	pr_info("ippm: ddp page size %lu not supported.\n", pgsz);
+	return DDP_PGIDX_MAX;
+}
+
+/* DDP setup & teardown
+ */
+static int ppm_find_unused_entries(unsigned long *bmap,
+				   unsigned int max_ppods,
+				   unsigned int start,
+				   unsigned int nr,
+				   unsigned int align_mask)
+{
+	unsigned long i;
+
+	i = bitmap_find_next_zero_area(bmap, max_ppods, start, nr, align_mask);
+
+	if (unlikely(i >= max_ppods) && (start > nr))
+		i = bitmap_find_next_zero_area(bmap, max_ppods, 0, start - 1,
+					       align_mask);
+	if (unlikely(i >= max_ppods))
+		return -ENOSPC;
+
+	bitmap_set(bmap, i, nr);
+	return (int)i;
+}
+
+static void ppm_mark_entries(struct cxgbi_ppm *ppm, int i, int count,
+			     unsigned long caller_data)
+{
+	struct cxgbi_ppod_data *pdata = ppm->ppod_data + i;
+
+	pdata->caller_data = caller_data;
+	pdata->npods = count;
+
+	if (pdata->color == ((1 << PPOD_IDX_SHIFT) - 1))
+		pdata->color = 0;
+	else
+		pdata->color++;
+}
+
+static int ppm_get_cpu_entries(struct cxgbi_ppm *ppm, unsigned int count,
+			       unsigned long caller_data)
+{
+	struct cxgbi_ppm_pool *pool;
+	unsigned int cpu;
+	int i;
+
+	cpu = get_cpu();
+	pool = per_cpu_ptr(ppm->pool, cpu);
+	spin_lock_bh(&pool->lock);
+	put_cpu();
+
+	i = ppm_find_unused_entries(pool->bmap, ppm->pool_index_max,
+				    pool->next, count, 0);
+	if (i < 0) {
+		pool->next = 0;
+		spin_unlock_bh(&pool->lock);
+		return -ENOSPC;
+	}
+
+	pool->next = i + count;
+	if (pool->next >= ppm->pool_index_max)
+		pool->next = 0;
+
+	spin_unlock_bh(&pool->lock);
+
+	pr_debug("%s: cpu %u, idx %d + %d (%d), next %u.\n",
+		 __func__, cpu, i, count, i + cpu * ppm->pool_index_max,
+		pool->next);
+
+	i += cpu * ppm->pool_index_max;
+	ppm_mark_entries(ppm, i, count, caller_data);
+
+	return i;
+}
+
+static int ppm_get_entries(struct cxgbi_ppm *ppm, unsigned int count,
+			   unsigned long caller_data)
+{
+	int i;
+
+	spin_lock_bh(&ppm->map_lock);
+	i = ppm_find_unused_entries(ppm->ppod_bmap, ppm->bmap_index_max,
+				    ppm->next, count, 0);
+	if (i < 0) {
+		ppm->next = 0;
+		spin_unlock_bh(&ppm->map_lock);
+		pr_debug("ippm: NO suitable entries %u available.\n",
+			 count);
+		return -ENOSPC;
+	}
+
+	ppm->next = i + count;
+	if (ppm->next >= ppm->bmap_index_max)
+		ppm->next = 0;
+
+	spin_unlock_bh(&ppm->map_lock);
+
+	pr_debug("%s: idx %d + %d (%d), next %u, caller_data 0x%lx.\n",
+		 __func__, i, count, i + ppm->pool_rsvd, ppm->next,
+		 caller_data);
+
+	i += ppm->pool_rsvd;
+	ppm_mark_entries(ppm, i, count, caller_data);
+
+	return i;
+}
+
+static void ppm_unmark_entries(struct cxgbi_ppm *ppm, int i, int count)
+{
+	pr_debug("%s: idx %d + %d.\n", __func__, i, count);
+
+	if (i < ppm->pool_rsvd) {
+		unsigned int cpu;
+		struct cxgbi_ppm_pool *pool;
+
+		cpu = i / ppm->pool_index_max;
+		i %= ppm->pool_index_max;
+
+		pool = per_cpu_ptr(ppm->pool, cpu);
+		spin_lock_bh(&pool->lock);
+		bitmap_clear(pool->bmap, i, count);
+
+		if (i < pool->next)
+			pool->next = i;
+		spin_unlock_bh(&pool->lock);
+
+		pr_debug("%s: cpu %u, idx %d, next %u.\n",
+			 __func__, cpu, i, pool->next);
+	} else {
+		spin_lock_bh(&ppm->map_lock);
+
+		i -= ppm->pool_rsvd;
+		bitmap_clear(ppm->ppod_bmap, i, count);
+
+		if (i < ppm->next)
+			ppm->next = i;
+		spin_unlock_bh(&ppm->map_lock);
+
+		pr_debug("%s: idx %d, next %u.\n", __func__, i, ppm->next);
+	}
+}
+
+void cxgbi_ppm_ppod_release(struct cxgbi_ppm *ppm, u32 idx)
+{
+	struct cxgbi_ppod_data *pdata;
+
+	if (idx >= ppm->ppmax) {
+		pr_warn("ippm: idx too big %u > %u.\n", idx, ppm->ppmax);
+		return;
+	}
+
+	pdata = ppm->ppod_data + idx;
+	if (!pdata->npods) {
+		pr_warn("ippm: idx %u, npods 0.\n", idx);
+		return;
+	}
+
+	pr_debug("release idx %u, npods %u.\n", idx, pdata->npods);
+	ppm_unmark_entries(ppm, idx, pdata->npods);
+}
+EXPORT_SYMBOL(cxgbi_ppm_ppod_release);
+
+int cxgbi_ppm_ppods_reserve(struct cxgbi_ppm *ppm, unsigned short nr_pages,
+			    u32 per_tag_pg_idx, u32 *ppod_idx,
+			    u32 *ddp_tag, unsigned long caller_data)
+{
+	struct cxgbi_ppod_data *pdata;
+	unsigned int npods;
+	int idx = -1;
+	unsigned int hwidx;
+	u32 tag;
+
+	npods = (nr_pages + PPOD_PAGES_MAX - 1) >> PPOD_PAGES_SHIFT;
+	if (!npods) {
+		pr_warn("%s: pages %u -> npods %u, full.\n",
+			__func__, nr_pages, npods);
+		return -EINVAL;
+	}
+
+	/* grab from cpu pool first */
+	idx = ppm_get_cpu_entries(ppm, npods, caller_data);
+	/* try the general pool */
+	if (idx < 0)
+		idx = ppm_get_entries(ppm, npods, caller_data);
+	if (idx < 0) {
+		pr_debug("ippm: pages %u, nospc %u, nxt %u, 0x%lx.\n",
+			 nr_pages, npods, ppm->next, caller_data);
+		return idx;
+	}
+
+	pdata = ppm->ppod_data + idx;
+	hwidx = ppm->base_idx + idx;
+
+	tag = cxgbi_ppm_make_ddp_tag(hwidx, pdata->color);
+
+	if (per_tag_pg_idx)
+		tag |= (per_tag_pg_idx << 30) & 0xC0000000;
+
+	*ppod_idx = idx;
+	*ddp_tag = tag;
+
+	pr_debug("ippm: sg %u, tag 0x%x(%u,%u), data 0x%lx.\n",
+		 nr_pages, tag, idx, npods, caller_data);
+
+	return npods;
+}
+EXPORT_SYMBOL(cxgbi_ppm_ppods_reserve);
+
+void cxgbi_ppm_make_ppod_hdr(struct cxgbi_ppm *ppm, u32 tag,
+			     unsigned int tid, unsigned int offset,
+			     unsigned int length,
+			     struct cxgbi_pagepod_hdr *hdr)
+{
+	/* The ddp tag in pagepod should be with bit 31:30 set to 0.
+	 * The ddp Tag on the wire should be with non-zero 31:30 to the peer
+	 */
+	tag &= 0x3FFFFFFF;
+
+	hdr->vld_tid = htonl(PPOD_VALID_FLAG | PPOD_TID(tid));
+
+	hdr->rsvd = 0;
+	hdr->pgsz_tag_clr = htonl(tag & ppm->tformat.idx_clr_mask);
+	hdr->max_offset = htonl(length);
+	hdr->page_offset = htonl(offset);
+
+	pr_debug("ippm: tag 0x%x, tid 0x%x, xfer %u, off %u.\n",
+		 tag, tid, length, offset);
+}
+EXPORT_SYMBOL(cxgbi_ppm_make_ppod_hdr);
+
+static void ppm_free(struct cxgbi_ppm *ppm)
+{
+	vfree(ppm);
+}
+
+static void ppm_destroy(struct kref *kref)
+{
+	struct cxgbi_ppm *ppm = container_of(kref,
+					     struct cxgbi_ppm,
+					     refcnt);
+	pr_info("ippm: kref 0, destroy %s ppm 0x%p.\n",
+		ppm->ndev->name, ppm);
+
+	*ppm->ppm_pp = NULL;
+
+	free_percpu(ppm->pool);
+	ppm_free(ppm);
+}
+
+int cxgbi_ppm_release(struct cxgbi_ppm *ppm)
+{
+	if (ppm) {
+		int rv;
+
+		rv = kref_put(&ppm->refcnt, ppm_destroy);
+		return rv;
+	}
+	return 1;
+}
+
+static struct cxgbi_ppm_pool *ppm_alloc_cpu_pool(unsigned int *total,
+						 unsigned int *pcpu_ppmax)
+{
+	struct cxgbi_ppm_pool *pools;
+	unsigned int ppmax = (*total) / num_possible_cpus();
+	unsigned int max = (PCPU_MIN_UNIT_SIZE - sizeof(*pools)) << 3;
+	unsigned int bmap;
+	unsigned int alloc_sz;
+	unsigned int count = 0;
+	unsigned int cpu;
+
+	/* make sure per cpu pool fits into PCPU_MIN_UNIT_SIZE */
+	if (ppmax > max)
+		ppmax = max;
+
+	/* pool size must be multiple of unsigned long */
+	bmap = BITS_TO_LONGS(ppmax);
+	ppmax = (bmap * sizeof(unsigned long)) << 3;
+
+	alloc_sz = sizeof(*pools) + sizeof(unsigned long) * bmap;
+	pools = __alloc_percpu(alloc_sz, __alignof__(struct cxgbi_ppm_pool));
+
+	if (!pools)
+		return NULL;
+
+	for_each_possible_cpu(cpu) {
+		struct cxgbi_ppm_pool *ppool = per_cpu_ptr(pools, cpu);
+
+		memset(ppool, 0, alloc_sz);
+		spin_lock_init(&ppool->lock);
+		count += ppmax;
+	}
+
+	*total = count;
+	*pcpu_ppmax = ppmax;
+
+	return pools;
+}
+
+int cxgbi_ppm_init(void **ppm_pp, struct net_device *ndev,
+		   struct pci_dev *pdev, void *lldev,
+		   struct cxgbi_tag_format *tformat,
+		   unsigned int ppmax,
+		   unsigned int llimit,
+		   unsigned int start,
+		   unsigned int reserve_factor)
+{
+	struct cxgbi_ppm *ppm = (struct cxgbi_ppm *)(*ppm_pp);
+	struct cxgbi_ppm_pool *pool = NULL;
+	unsigned int ppmax_pool = 0;
+	unsigned int pool_index_max = 0;
+	unsigned int alloc_sz;
+	unsigned int ppod_bmap_size;
+
+	if (ppm) {
+		pr_info("ippm: %s, ppm 0x%p,0x%p already initialized, %u/%u.\n",
+			ndev->name, ppm_pp, ppm, ppm->ppmax, ppmax);
+		kref_get(&ppm->refcnt);
+		return 1;
+	}
+
+	if (reserve_factor) {
+		ppmax_pool = ppmax / reserve_factor;
+		pool = ppm_alloc_cpu_pool(&ppmax_pool, &pool_index_max);
+
+		pr_debug("%s: ppmax %u, cpu total %u, per cpu %u.\n",
+			 ndev->name, ppmax, ppmax_pool, pool_index_max);
+	}
+
+	ppod_bmap_size = BITS_TO_LONGS(ppmax - ppmax_pool);
+	alloc_sz = sizeof(struct cxgbi_ppm) +
+			ppmax * (sizeof(struct cxgbi_ppod_data)) +
+			ppod_bmap_size * sizeof(unsigned long);
+
+	ppm = vmalloc(alloc_sz);
+	if (!ppm)
+		goto release_ppm_pool;
+
+	memset(ppm, 0, alloc_sz);
+
+	ppm->ppod_bmap = (unsigned long *)(&ppm->ppod_data[ppmax]);
+
+	if ((ppod_bmap_size >> 3) > (ppmax - ppmax_pool)) {
+		unsigned int start = ppmax - ppmax_pool;
+		unsigned int end = ppod_bmap_size >> 3;
+
+		bitmap_set(ppm->ppod_bmap, ppmax, end - start);
+		pr_info("%s: %u - %u < %u * 8, mask extra bits %u, %u.\n",
+			__func__, ppmax, ppmax_pool, ppod_bmap_size, start,
+			end);
+	}
+
+	spin_lock_init(&ppm->map_lock);
+	kref_init(&ppm->refcnt);
+
+	memcpy(&ppm->tformat, tformat, sizeof(struct cxgbi_tag_format));
+
+	ppm->ppm_pp = ppm_pp;
+	ppm->ndev = ndev;
+	ppm->pdev = pdev;
+	ppm->lldev = lldev;
+	ppm->ppmax = ppmax;
+	ppm->next = 0;
+	ppm->llimit = llimit;
+	ppm->base_idx = start > llimit ?
+			(start - llimit + 1) >> PPOD_SIZE_SHIFT : 0;
+	ppm->bmap_index_max = ppmax - ppmax_pool;
+
+	ppm->pool = pool;
+	ppm->pool_rsvd = ppmax_pool;
+	ppm->pool_index_max = pool_index_max;
+
+	/* check one more time */
+	if (*ppm_pp) {
+		ppm_free(ppm);
+		ppm = (struct cxgbi_ppm *)(*ppm_pp);
+
+		pr_info("ippm: %s, ppm 0x%p,0x%p already initialized, %u/%u.\n",
+			ndev->name, ppm_pp, *ppm_pp, ppm->ppmax, ppmax);
+
+		kref_get(&ppm->refcnt);
+		return 1;
+	}
+	*ppm_pp = ppm;
+
+	ppm->tformat.pgsz_idx_dflt = cxgbi_ppm_find_page_index(ppm, PAGE_SIZE);
+
+	pr_info("ippm %s: ppm 0x%p, 0x%p, base %u/%u, pg %lu,%u, rsvd %u,%u.\n",
+		ndev->name, ppm_pp, ppm, ppm->base_idx, ppm->ppmax, PAGE_SIZE,
+		ppm->tformat.pgsz_idx_dflt, ppm->pool_rsvd,
+		ppm->pool_index_max);
+
+	return 0;
+
+release_ppm_pool:
+	free_percpu(pool);
+	return -ENOMEM;
+}
+EXPORT_SYMBOL(cxgbi_ppm_init);
+
+unsigned int cxgbi_tagmask_set(unsigned int ppmax)
+{
+	unsigned int bits = fls(ppmax);
+
+	if (bits > PPOD_IDX_MAX_SIZE)
+		bits = PPOD_IDX_MAX_SIZE;
+
+	pr_info("ippm: ppmax %u/0x%x -> bits %u, tagmask 0x%x.\n",
+		ppmax, ppmax, bits, 1 << (bits + PPOD_IDX_SHIFT));
+
+	return 1 << (bits + PPOD_IDX_SHIFT);
+}
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ppm.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ppm.h
new file mode 100644
index 000000000000..d48732673b75
--- /dev/null
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ppm.h
@@ -0,0 +1,310 @@
+/*
+ * cxgb4_ppm.h: Chelsio common library for T4/T5 iSCSI ddp operation
+ *
+ * Copyright (c) 2016 Chelsio Communications, Inc. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Written by: Karen Xie (kxie@chelsio.com)
+ */
+
+#ifndef	__CXGB4PPM_H__
+#define	__CXGB4PPM_H__
+
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/debugfs.h>
+#include <linux/list.h>
+#include <linux/netdevice.h>
+#include <linux/scatterlist.h>
+#include <linux/skbuff.h>
+#include <linux/vmalloc.h>
+#include <linux/bitmap.h>
+
+struct cxgbi_pagepod_hdr {
+	u32 vld_tid;
+	u32 pgsz_tag_clr;
+	u32 max_offset;
+	u32 page_offset;
+	u64 rsvd;
+};
+
+#define PPOD_PAGES_MAX			4
+struct cxgbi_pagepod {
+	struct cxgbi_pagepod_hdr hdr;
+	u64 addr[PPOD_PAGES_MAX + 1];
+};
+
+/* ddp tag format
+ * for a 32-bit tag:
+ * bit #
+ * 31 .....   .....  0
+ *     X   Y...Y Z...Z, where
+ *     ^   ^^^^^ ^^^^
+ *     |   |      |____ when ddp bit = 0: color bits
+ *     |   |
+ *     |   |____ when ddp bit = 0: idx into the ddp memory region
+ *     |
+ *     |____ ddp bit: 0 - ddp tag, 1 - non-ddp tag
+ *
+ *  [page selector:2] [sw/free bits] [0] [idx] [color:6]
+ */
+
+#define DDP_PGIDX_MAX		4
+#define DDP_PGSZ_BASE_SHIFT	12	/* base page 4K */
+
+struct cxgbi_task_tag_info {
+	unsigned char flags;
+#define CXGBI_PPOD_INFO_FLAG_VALID	0x1
+#define CXGBI_PPOD_INFO_FLAG_MAPPED	0x2
+	unsigned char cid;
+	unsigned short pg_shift;
+	unsigned int npods;
+	unsigned int idx;
+	unsigned int tag;
+	struct cxgbi_pagepod_hdr hdr;
+	int nents;
+	int nr_pages;
+	struct scatterlist *sgl;
+};
+
+struct cxgbi_tag_format {
+	unsigned char pgsz_order[DDP_PGIDX_MAX];
+	unsigned char pgsz_idx_dflt;
+	unsigned char free_bits:4;
+	unsigned char color_bits:4;
+	unsigned char idx_bits;
+	unsigned char rsvd_bits;
+	unsigned int  no_ddp_mask;
+	unsigned int  idx_mask;
+	unsigned int  color_mask;
+	unsigned int  idx_clr_mask;
+	unsigned int  rsvd_mask;
+};
+
+struct cxgbi_ppod_data {
+	unsigned char pg_idx:2;
+	unsigned char color:6;
+	unsigned char chan_id;
+	unsigned short npods;
+	unsigned long caller_data;
+};
+
+/* per cpu ppm pool */
+struct cxgbi_ppm_pool {
+	unsigned int base;		/* base index */
+	unsigned int next;		/* next possible free index */
+	spinlock_t lock;		/* ppm pool lock */
+	unsigned long bmap[0];
+} ____cacheline_aligned_in_smp;
+
+struct cxgbi_ppm {
+	struct kref refcnt;
+	struct net_device *ndev;	/* net_device, 1st port */
+	struct pci_dev *pdev;
+	void *lldev;
+	void **ppm_pp;
+	struct cxgbi_tag_format tformat;
+	unsigned int ppmax;
+	unsigned int llimit;
+	unsigned int base_idx;
+
+	unsigned int pool_rsvd;
+	unsigned int pool_index_max;
+	struct cxgbi_ppm_pool __percpu *pool;
+	/* map lock */
+	spinlock_t map_lock;		/* ppm map lock */
+	unsigned int bmap_index_max;
+	unsigned int next;
+	unsigned long *ppod_bmap;
+	struct cxgbi_ppod_data ppod_data[0];
+};
+
+#define DDP_THRESHOLD		512
+
+#define PPOD_PAGES_SHIFT	2       /*  4 pages per pod */
+
+#define IPPOD_SIZE               sizeof(struct cxgbi_pagepod)  /*  64 */
+#define PPOD_SIZE_SHIFT         6
+
+/* page pods are allocated in groups of this size (must be power of 2) */
+#define PPOD_CLUSTER_SIZE	16U
+
+#define ULPMEM_DSGL_MAX_NPPODS	16	/*  1024/PPOD_SIZE */
+#define ULPMEM_IDATA_MAX_NPPODS	3	/* (PPOD_SIZE * 3 + ulptx hdr) < 256B */
+#define PCIE_MEMWIN_MAX_NPPODS	16	/*  1024/PPOD_SIZE */
+
+#define PPOD_COLOR_SHIFT	0
+#define PPOD_COLOR(x)		((x) << PPOD_COLOR_SHIFT)
+
+#define PPOD_IDX_SHIFT          6
+#define PPOD_IDX_MAX_SIZE       24
+
+#define PPOD_TID_SHIFT		0
+#define PPOD_TID(x)		((x) << PPOD_TID_SHIFT)
+
+#define PPOD_TAG_SHIFT		6
+#define PPOD_TAG(x)		((x) << PPOD_TAG_SHIFT)
+
+#define PPOD_VALID_SHIFT	24
+#define PPOD_VALID(x)		((x) << PPOD_VALID_SHIFT)
+#define PPOD_VALID_FLAG		PPOD_VALID(1U)
+
+#define PPOD_PI_EXTRACT_CTL_SHIFT	31
+#define PPOD_PI_EXTRACT_CTL(x)		((x) << PPOD_PI_EXTRACT_CTL_SHIFT)
+#define PPOD_PI_EXTRACT_CTL_FLAG	V_PPOD_PI_EXTRACT_CTL(1U)
+
+#define PPOD_PI_TYPE_SHIFT		29
+#define PPOD_PI_TYPE_MASK		0x3
+#define PPOD_PI_TYPE(x)			((x) << PPOD_PI_TYPE_SHIFT)
+
+#define PPOD_PI_CHECK_CTL_SHIFT		27
+#define PPOD_PI_CHECK_CTL_MASK		0x3
+#define PPOD_PI_CHECK_CTL(x)		((x) << PPOD_PI_CHECK_CTL_SHIFT)
+
+#define PPOD_PI_REPORT_CTL_SHIFT	25
+#define PPOD_PI_REPORT_CTL_MASK		0x3
+#define PPOD_PI_REPORT_CTL(x)		((x) << PPOD_PI_REPORT_CTL_SHIFT)
+
+static inline int cxgbi_ppm_is_ddp_tag(struct cxgbi_ppm *ppm, u32 tag)
+{
+	return !(tag & ppm->tformat.no_ddp_mask);
+}
+
+static inline int cxgbi_ppm_sw_tag_is_usable(struct cxgbi_ppm *ppm,
+					     u32 tag)
+{
+	/* the sw tag must be using <= 31 bits */
+	return !(tag & 0x80000000U);
+}
+
+static inline int cxgbi_ppm_make_non_ddp_tag(struct cxgbi_ppm *ppm,
+					     u32 sw_tag,
+					     u32 *final_tag)
+{
+	struct cxgbi_tag_format *tformat = &ppm->tformat;
+
+	if (!cxgbi_ppm_sw_tag_is_usable(ppm, sw_tag)) {
+		pr_info("sw_tag 0x%x NOT usable.\n", sw_tag);
+		return -EINVAL;
+	}
+
+	if (!sw_tag) {
+		*final_tag = tformat->no_ddp_mask;
+	} else {
+		unsigned int shift = tformat->idx_bits + tformat->color_bits;
+		u32 lower = sw_tag & tformat->idx_clr_mask;
+		u32 upper = (sw_tag >> shift) << (shift + 1);
+
+		*final_tag = upper | tformat->no_ddp_mask | lower;
+	}
+	return 0;
+}
+
+static inline u32 cxgbi_ppm_decode_non_ddp_tag(struct cxgbi_ppm *ppm,
+					       u32 tag)
+{
+	struct cxgbi_tag_format *tformat = &ppm->tformat;
+	unsigned int shift = tformat->idx_bits + tformat->color_bits;
+	u32 lower = tag & tformat->idx_clr_mask;
+	u32 upper = (tag >> tformat->rsvd_bits) << shift;
+
+	return upper | lower;
+}
+
+static inline u32 cxgbi_ppm_ddp_tag_get_idx(struct cxgbi_ppm *ppm,
+					    u32 ddp_tag)
+{
+	u32 hw_idx = (ddp_tag >> PPOD_IDX_SHIFT) &
+			ppm->tformat.idx_mask;
+
+	return hw_idx - ppm->base_idx;
+}
+
+static inline u32 cxgbi_ppm_make_ddp_tag(unsigned int hw_idx,
+					 unsigned char color)
+{
+	return (hw_idx << PPOD_IDX_SHIFT) | ((u32)color);
+}
+
+static inline unsigned long
+cxgbi_ppm_get_tag_caller_data(struct cxgbi_ppm *ppm,
+			      u32 ddp_tag)
+{
+	u32 idx = cxgbi_ppm_ddp_tag_get_idx(ppm, ddp_tag);
+
+	return ppm->ppod_data[idx].caller_data;
+}
+
+/* sw bits are the free bits */
+static inline int cxgbi_ppm_ddp_tag_update_sw_bits(struct cxgbi_ppm *ppm,
+						   u32 val, u32 orig_tag,
+						   u32 *final_tag)
+{
+	struct cxgbi_tag_format *tformat = &ppm->tformat;
+	u32 v = val >> tformat->free_bits;
+
+	if (v) {
+		pr_info("sw_bits 0x%x too large, avail bits %u.\n",
+			val, tformat->free_bits);
+		return -EINVAL;
+	}
+	if (!cxgbi_ppm_is_ddp_tag(ppm, orig_tag))
+		return -EINVAL;
+
+	*final_tag = (val << tformat->rsvd_bits) |
+		     (orig_tag & ppm->tformat.rsvd_mask);
+	return 0;
+}
+
+static inline void cxgbi_ppm_ppod_clear(struct cxgbi_pagepod *ppod)
+{
+	ppod->hdr.vld_tid = 0U;
+}
+
+static inline void cxgbi_tagmask_check(unsigned int tagmask,
+				       struct cxgbi_tag_format *tformat)
+{
+	unsigned int bits = fls(tagmask);
+
+	/* reserve top most 2 bits for page selector */
+	tformat->free_bits = 32 - 2 - bits;
+	tformat->rsvd_bits = bits;
+	tformat->color_bits = PPOD_IDX_SHIFT;
+	tformat->idx_bits = bits - 1 - PPOD_IDX_SHIFT;
+	tformat->no_ddp_mask = 1 << (bits - 1);
+	tformat->idx_mask = (1 << tformat->idx_bits) - 1;
+	tformat->color_mask = (1 << PPOD_IDX_SHIFT) - 1;
+	tformat->idx_clr_mask = (1 << (bits - 1)) - 1;
+	tformat->rsvd_mask = (1 << bits) - 1;
+
+	pr_info("ippm: tagmask 0x%x, rsvd %u=%u+%u+1, mask 0x%x,0x%x, "
+		"pg %u,%u,%u,%u.\n",
+		tagmask, tformat->rsvd_bits, tformat->idx_bits,
+		tformat->color_bits, tformat->no_ddp_mask, tformat->rsvd_mask,
+		tformat->pgsz_order[0], tformat->pgsz_order[1],
+		tformat->pgsz_order[2], tformat->pgsz_order[3]);
+}
+
+int cxgbi_ppm_find_page_index(struct cxgbi_ppm *ppm, unsigned long pgsz);
+void cxgbi_ppm_make_ppod_hdr(struct cxgbi_ppm *ppm, u32 tag,
+			     unsigned int tid, unsigned int offset,
+			     unsigned int length,
+			     struct cxgbi_pagepod_hdr *hdr);
+void cxgbi_ppm_ppod_release(struct cxgbi_ppm *, u32 idx);
+int cxgbi_ppm_ppods_reserve(struct cxgbi_ppm *, unsigned short nr_pages,
+			    u32 per_tag_pg_idx, u32 *ppod_idx, u32 *ddp_tag,
+			    unsigned long caller_data);
+int cxgbi_ppm_init(void **ppm_pp, struct net_device *, struct pci_dev *,
+		   void *lldev, struct cxgbi_tag_format *,
+		   unsigned int ppmax, unsigned int llimit,
+		   unsigned int start,
+		   unsigned int reserve_factor);
+int cxgbi_ppm_release(struct cxgbi_ppm *ppm);
+void cxgbi_tagmask_check(unsigned int tagmask, struct cxgbi_tag_format *);
+unsigned int cxgbi_tagmask_set(unsigned int ppmax);
+
+#endif	/*__CXGB4PPM_H__*/
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
index cf711d5f15be..f3c58aaa932d 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
@@ -191,6 +191,7 @@ static inline void set_wr_txq(struct sk_buff *skb, int prio, int queue)
 enum cxgb4_uld {
 	CXGB4_ULD_RDMA,
 	CXGB4_ULD_ISCSI,
+	CXGB4_ULD_ISCSIT,
 	CXGB4_ULD_MAX
 };
 
@@ -212,6 +213,7 @@ struct l2t_data;
 struct net_device;
 struct pkt_gl;
 struct tp_tcp_stats;
+struct t4_lro_mgr;
 
 struct cxgb4_range {
 	unsigned int start;
@@ -273,6 +275,10 @@ struct cxgb4_lld_info {
 	unsigned int max_ordird_qp;          /* Max ORD/IRD depth per RDMA QP */
 	unsigned int max_ird_adapter;        /* Max IRD memory per adapter */
 	bool ulptx_memwrite_dsgl;            /* use of T5 DSGL allowed */
+	unsigned int iscsi_tagmask;	     /* iscsi ddp tag mask */
+	unsigned int iscsi_pgsz_order;	     /* iscsi ddp page size orders */
+	unsigned int iscsi_llimit;	     /* chip's iscsi region llimit */
+	void **iscsi_ppm;		     /* iscsi page pod manager */
 	int nodeid;			     /* device numa node id */
 };
 
@@ -283,6 +289,11 @@ struct cxgb4_uld_info {
 			  const struct pkt_gl *gl);
 	int (*state_change)(void *handle, enum cxgb4_state new_state);
 	int (*control)(void *handle, enum cxgb4_control control, ...);
+	int (*lro_rx_handler)(void *handle, const __be64 *rsp,
+			      const struct pkt_gl *gl,
+			      struct t4_lro_mgr *lro_mgr,
+			      struct napi_struct *napi);
+	void (*lro_flush)(struct t4_lro_mgr *);
 };
 
 int cxgb4_register_uld(enum cxgb4_uld type, const struct cxgb4_uld_info *p);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/l2t.c b/drivers/net/ethernet/chelsio/cxgb4/l2t.c
index 5b0f3ef348e9..60a26037a1c6 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/l2t.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/l2t.c
@@ -48,8 +48,6 @@
 #include "t4_regs.h"
 #include "t4_values.h"
 
-#define VLAN_NONE 0xfff
-
 /* identifies sync vs async L2T_WRITE_REQs */
 #define SYNC_WR_S    12
 #define SYNC_WR_V(x) ((x) << SYNC_WR_S)
diff --git a/drivers/net/ethernet/chelsio/cxgb4/l2t.h b/drivers/net/ethernet/chelsio/cxgb4/l2t.h
index 4e2d47ac102b..79665bd8f881 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/l2t.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/l2t.h
@@ -39,6 +39,8 @@
 #include <linux/if_ether.h>
 #include <linux/atomic.h>
 
+#define VLAN_NONE 0xfff
+
 enum { L2T_SIZE = 4096 };     /* # of L2T entries */
 
 enum {
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index deca4a2956cc..13b144bcf725 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -2157,8 +2157,11 @@ static int process_responses(struct sge_rspq *q, int budget)
 
 	while (likely(budget_left)) {
 		rc = (void *)q->cur_desc + (q->iqe_len - sizeof(*rc));
-		if (!is_new_response(rc, q))
+		if (!is_new_response(rc, q)) {
+			if (q->flush_handler)
+				q->flush_handler(q);
 			break;
+		}
 
 		dma_rmb();
 		rsp_type = RSPD_TYPE_G(rc->type_gen);
@@ -2544,7 +2547,8 @@ static void __iomem *bar2_address(struct adapter *adapter,
  */
 int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq,
 		     struct net_device *dev, int intr_idx,
-		     struct sge_fl *fl, rspq_handler_t hnd, int cong)
+		     struct sge_fl *fl, rspq_handler_t hnd,
+		     rspq_flush_handler_t flush_hnd, int cong)
 {
 	int ret, flsz = 0;
 	struct fw_iq_cmd c;
@@ -2648,6 +2652,10 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq,
 	iq->size--;                           /* subtract status entry */
 	iq->netdev = dev;
 	iq->handler = hnd;
+	iq->flush_handler = flush_hnd;
+
+	memset(&iq->lro_mgr, 0, sizeof(struct t4_lro_mgr));
+	skb_queue_head_init(&iq->lro_mgr.lroq);
 
 	/* set offset to -1 to distinguish ingress queues without FL */
 	iq->offset = fl ? 0 : -1;
@@ -2992,6 +3000,7 @@ void t4_free_sge_resources(struct adapter *adap)
 
 	/* clean up RDMA and iSCSI Rx queues */
 	t4_free_ofld_rxqs(adap, adap->sge.iscsiqsets, adap->sge.iscsirxq);
+	t4_free_ofld_rxqs(adap, adap->sge.niscsitq, adap->sge.iscsitrxq);
 	t4_free_ofld_rxqs(adap, adap->sge.rdmaqs, adap->sge.rdmarxq);
 	t4_free_ofld_rxqs(adap, adap->sge.rdmaciqs, adap->sge.rdmaciq);
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
index 1d2d1da40c80..80417fc564d4 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
@@ -51,6 +51,7 @@ enum {
 	CPL_TX_PKT            = 0xE,
 	CPL_L2T_WRITE_REQ     = 0x12,
 	CPL_TID_RELEASE       = 0x1A,
+	CPL_TX_DATA_ISO	      = 0x1F,
 
 	CPL_CLOSE_LISTSRV_RPL = 0x20,
 	CPL_L2T_WRITE_RPL     = 0x23,
@@ -344,6 +345,87 @@ struct cpl_pass_open_rpl {
 	u8 status;
 };
 
+struct tcp_options {
+	__be16 mss;
+	__u8 wsf;
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+	__u8:4;
+	__u8 unknown:1;
+	__u8:1;
+	__u8 sack:1;
+	__u8 tstamp:1;
+#else
+	__u8 tstamp:1;
+	__u8 sack:1;
+	__u8:1;
+	__u8 unknown:1;
+	__u8:4;
+#endif
+};
+
+struct cpl_pass_accept_req {
+	union opcode_tid ot;
+	__be16 rsvd;
+	__be16 len;
+	__be32 hdr_len;
+	__be16 vlan;
+	__be16 l2info;
+	__be32 tos_stid;
+	struct tcp_options tcpopt;
+};
+
+/* cpl_pass_accept_req.hdr_len fields */
+#define SYN_RX_CHAN_S    0
+#define SYN_RX_CHAN_M    0xF
+#define SYN_RX_CHAN_V(x) ((x) << SYN_RX_CHAN_S)
+#define SYN_RX_CHAN_G(x) (((x) >> SYN_RX_CHAN_S) & SYN_RX_CHAN_M)
+
+#define TCP_HDR_LEN_S    10
+#define TCP_HDR_LEN_M    0x3F
+#define TCP_HDR_LEN_V(x) ((x) << TCP_HDR_LEN_S)
+#define TCP_HDR_LEN_G(x) (((x) >> TCP_HDR_LEN_S) & TCP_HDR_LEN_M)
+
+#define IP_HDR_LEN_S    16
+#define IP_HDR_LEN_M    0x3FF
+#define IP_HDR_LEN_V(x) ((x) << IP_HDR_LEN_S)
+#define IP_HDR_LEN_G(x) (((x) >> IP_HDR_LEN_S) & IP_HDR_LEN_M)
+
+#define ETH_HDR_LEN_S    26
+#define ETH_HDR_LEN_M    0x1F
+#define ETH_HDR_LEN_V(x) ((x) << ETH_HDR_LEN_S)
+#define ETH_HDR_LEN_G(x) (((x) >> ETH_HDR_LEN_S) & ETH_HDR_LEN_M)
+
+/* cpl_pass_accept_req.l2info fields */
+#define SYN_MAC_IDX_S    0
+#define SYN_MAC_IDX_M    0x1FF
+#define SYN_MAC_IDX_V(x) ((x) << SYN_MAC_IDX_S)
+#define SYN_MAC_IDX_G(x) (((x) >> SYN_MAC_IDX_S) & SYN_MAC_IDX_M)
+
+#define SYN_XACT_MATCH_S    9
+#define SYN_XACT_MATCH_V(x) ((x) << SYN_XACT_MATCH_S)
+#define SYN_XACT_MATCH_F    SYN_XACT_MATCH_V(1U)
+
+#define SYN_INTF_S    12
+#define SYN_INTF_M    0xF
+#define SYN_INTF_V(x) ((x) << SYN_INTF_S)
+#define SYN_INTF_G(x) (((x) >> SYN_INTF_S) & SYN_INTF_M)
+
+enum {                     /* TCP congestion control algorithms */
+	CONG_ALG_RENO,
+	CONG_ALG_TAHOE,
+	CONG_ALG_NEWRENO,
+	CONG_ALG_HIGHSPEED
+};
+
+#define CONG_CNTRL_S    14
+#define CONG_CNTRL_M    0x3
+#define CONG_CNTRL_V(x) ((x) << CONG_CNTRL_S)
+#define CONG_CNTRL_G(x) (((x) >> CONG_CNTRL_S) & CONG_CNTRL_M)
+
+#define T5_ISS_S    18
+#define T5_ISS_V(x) ((x) << T5_ISS_S)
+#define T5_ISS_F    T5_ISS_V(1U)
+
 struct cpl_pass_accept_rpl {
 	WR_HDR;
 	union opcode_tid ot;
@@ -818,6 +900,110 @@ struct cpl_iscsi_hdr {
 #define ISCSI_DDP_V(x) ((x) << ISCSI_DDP_S)
 #define ISCSI_DDP_F    ISCSI_DDP_V(1U)
 
+struct cpl_rx_data_ddp {
+	union opcode_tid ot;
+	__be16 urg;
+	__be16 len;
+	__be32 seq;
+	union {
+		__be32 nxt_seq;
+		__be32 ddp_report;
+	};
+	__be32 ulp_crc;
+	__be32 ddpvld;
+};
+
+#define cpl_rx_iscsi_ddp cpl_rx_data_ddp
+
+struct cpl_iscsi_data {
+	union opcode_tid ot;
+	__u8 rsvd0[2];
+	__be16 len;
+	__be32 seq;
+	__be16 urg;
+	__u8 rsvd1;
+	__u8 status;
+};
+
+struct cpl_tx_data_iso {
+	__be32 op_to_scsi;
+	__u8   reserved1;
+	__u8   ahs_len;
+	__be16 mpdu;
+	__be32 burst_size;
+	__be32 len;
+	__be32 reserved2_seglen_offset;
+	__be32 datasn_offset;
+	__be32 buffer_offset;
+	__be32 reserved3;
+
+	/* encapsulated CPL_TX_DATA follows here */
+};
+
+/* cpl_tx_data_iso.op_to_scsi fields */
+#define CPL_TX_DATA_ISO_OP_S	24
+#define CPL_TX_DATA_ISO_OP_M	0xff
+#define CPL_TX_DATA_ISO_OP_V(x)	((x) << CPL_TX_DATA_ISO_OP_S)
+#define CPL_TX_DATA_ISO_OP_G(x)	\
+	(((x) >> CPL_TX_DATA_ISO_OP_S) & CPL_TX_DATA_ISO_OP_M)
+
+#define CPL_TX_DATA_ISO_FIRST_S		23
+#define CPL_TX_DATA_ISO_FIRST_M		0x1
+#define CPL_TX_DATA_ISO_FIRST_V(x)	((x) << CPL_TX_DATA_ISO_FIRST_S)
+#define CPL_TX_DATA_ISO_FIRST_G(x)	\
+	(((x) >> CPL_TX_DATA_ISO_FIRST_S) & CPL_TX_DATA_ISO_FIRST_M)
+#define CPL_TX_DATA_ISO_FIRST_F	CPL_TX_DATA_ISO_FIRST_V(1U)
+
+#define CPL_TX_DATA_ISO_LAST_S		22
+#define CPL_TX_DATA_ISO_LAST_M		0x1
+#define CPL_TX_DATA_ISO_LAST_V(x)	((x) << CPL_TX_DATA_ISO_LAST_S)
+#define CPL_TX_DATA_ISO_LAST_G(x)	\
+	(((x) >> CPL_TX_DATA_ISO_LAST_S) & CPL_TX_DATA_ISO_LAST_M)
+#define CPL_TX_DATA_ISO_LAST_F	CPL_TX_DATA_ISO_LAST_V(1U)
+
+#define CPL_TX_DATA_ISO_CPLHDRLEN_S	21
+#define CPL_TX_DATA_ISO_CPLHDRLEN_M	0x1
+#define CPL_TX_DATA_ISO_CPLHDRLEN_V(x)	((x) << CPL_TX_DATA_ISO_CPLHDRLEN_S)
+#define CPL_TX_DATA_ISO_CPLHDRLEN_G(x)	\
+	(((x) >> CPL_TX_DATA_ISO_CPLHDRLEN_S) & CPL_TX_DATA_ISO_CPLHDRLEN_M)
+#define CPL_TX_DATA_ISO_CPLHDRLEN_F	CPL_TX_DATA_ISO_CPLHDRLEN_V(1U)
+
+#define CPL_TX_DATA_ISO_HDRCRC_S	20
+#define CPL_TX_DATA_ISO_HDRCRC_M	0x1
+#define CPL_TX_DATA_ISO_HDRCRC_V(x)	((x) << CPL_TX_DATA_ISO_HDRCRC_S)
+#define CPL_TX_DATA_ISO_HDRCRC_G(x)	\
+	(((x) >> CPL_TX_DATA_ISO_HDRCRC_S) & CPL_TX_DATA_ISO_HDRCRC_M)
+#define CPL_TX_DATA_ISO_HDRCRC_F	CPL_TX_DATA_ISO_HDRCRC_V(1U)
+
+#define CPL_TX_DATA_ISO_PLDCRC_S	19
+#define CPL_TX_DATA_ISO_PLDCRC_M	0x1
+#define CPL_TX_DATA_ISO_PLDCRC_V(x)	((x) << CPL_TX_DATA_ISO_PLDCRC_S)
+#define CPL_TX_DATA_ISO_PLDCRC_G(x)	\
+	(((x) >> CPL_TX_DATA_ISO_PLDCRC_S) & CPL_TX_DATA_ISO_PLDCRC_M)
+#define CPL_TX_DATA_ISO_PLDCRC_F	CPL_TX_DATA_ISO_PLDCRC_V(1U)
+
+#define CPL_TX_DATA_ISO_IMMEDIATE_S	18
+#define CPL_TX_DATA_ISO_IMMEDIATE_M	0x1
+#define CPL_TX_DATA_ISO_IMMEDIATE_V(x)	((x) << CPL_TX_DATA_ISO_IMMEDIATE_S)
+#define CPL_TX_DATA_ISO_IMMEDIATE_G(x)	\
+	(((x) >> CPL_TX_DATA_ISO_IMMEDIATE_S) & CPL_TX_DATA_ISO_IMMEDIATE_M)
+#define CPL_TX_DATA_ISO_IMMEDIATE_F	CPL_TX_DATA_ISO_IMMEDIATE_V(1U)
+
+#define CPL_TX_DATA_ISO_SCSI_S		16
+#define CPL_TX_DATA_ISO_SCSI_M		0x3
+#define CPL_TX_DATA_ISO_SCSI_V(x)	((x) << CPL_TX_DATA_ISO_SCSI_S)
+#define CPL_TX_DATA_ISO_SCSI_G(x)	\
+	(((x) >> CPL_TX_DATA_ISO_SCSI_S) & CPL_TX_DATA_ISO_SCSI_M)
+
+/* cpl_tx_data_iso.reserved2_seglen_offset fields */
+#define CPL_TX_DATA_ISO_SEGLEN_OFFSET_S		0
+#define CPL_TX_DATA_ISO_SEGLEN_OFFSET_M		0xffffff
+#define CPL_TX_DATA_ISO_SEGLEN_OFFSET_V(x)	\
+	((x) << CPL_TX_DATA_ISO_SEGLEN_OFFSET_S)
+#define CPL_TX_DATA_ISO_SEGLEN_OFFSET_G(x)	\
+	(((x) >> CPL_TX_DATA_ISO_SEGLEN_OFFSET_S) & \
+	 CPL_TX_DATA_ISO_SEGLEN_OFFSET_M)
+
 struct cpl_rx_data {
 	union opcode_tid ot;
 	__be16 rsvd;
@@ -854,6 +1040,15 @@ struct cpl_rx_data_ack {
 #define RX_FORCE_ACK_V(x) ((x) << RX_FORCE_ACK_S)
 #define RX_FORCE_ACK_F    RX_FORCE_ACK_V(1U)
 
+#define RX_DACK_MODE_S    29
+#define RX_DACK_MODE_M    0x3
+#define RX_DACK_MODE_V(x) ((x) << RX_DACK_MODE_S)
+#define RX_DACK_MODE_G(x) (((x) >> RX_DACK_MODE_S) & RX_DACK_MODE_M)
+
+#define RX_DACK_CHANGE_S    31
+#define RX_DACK_CHANGE_V(x) ((x) << RX_DACK_CHANGE_S)
+#define RX_DACK_CHANGE_F    RX_DACK_CHANGE_V(1U)
+
 struct cpl_rx_pkt {
 	struct rss_header rsshdr;
 	u8 opcode;
@@ -1090,6 +1285,12 @@ struct cpl_fw4_ack {
 	__be64 rsvd1;
 };
 
+enum {
+	CPL_FW4_ACK_FLAGS_SEQVAL	= 0x1,	/* seqn valid */
+	CPL_FW4_ACK_FLAGS_CH		= 0x2,	/* channel change complete */
+	CPL_FW4_ACK_FLAGS_FLOWC		= 0x4,	/* fw_flowc_wr complete */
+};
+
 struct cpl_fw6_msg {
 	u8 opcode;
 	u8 type;
@@ -1115,6 +1316,17 @@ struct cpl_fw6_msg_ofld_connection_wr_rpl {
 	__u8    rsvd[2];
 };
 
+struct cpl_tx_data {
+	union opcode_tid ot;
+	__be32 len;
+	__be32 rsvd;
+	__be32 flags;
+};
+
+/* cpl_tx_data.flags field */
+#define TX_FORCE_S	13
+#define TX_FORCE_V(x)	((x) << TX_FORCE_S)
+
 enum {
 	ULP_TX_MEM_READ = 2,
 	ULP_TX_MEM_WRITE = 3,
@@ -1143,6 +1355,11 @@ struct ulptx_sgl {
 	struct ulptx_sge_pair sge[0];
 };
 
+struct ulptx_idata {
+	__be32 cmd_more;
+	__be32 len;
+};
+
 #define ULPTX_NSGE_S    0
 #define ULPTX_NSGE_V(x) ((x) << ULPTX_NSGE_S)
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
index c8661c77b4e3..7ad6d4e75b2a 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
@@ -101,6 +101,7 @@ enum fw_wr_opcodes {
 	FW_RI_BIND_MW_WR               = 0x18,
 	FW_RI_FR_NSMR_WR               = 0x19,
 	FW_RI_INV_LSTAG_WR             = 0x1a,
+	FW_ISCSI_TX_DATA_WR	       = 0x45,
 	FW_LASTC2E_WR                  = 0x70
 };
 
@@ -561,7 +562,12 @@ enum fw_flowc_mnem {
 	FW_FLOWC_MNEM_SNDBUF,
 	FW_FLOWC_MNEM_MSS,
 	FW_FLOWC_MNEM_TXDATAPLEN_MAX,
-	FW_FLOWC_MNEM_SCHEDCLASS = 11,
+	FW_FLOWC_MNEM_TCPSTATE,
+	FW_FLOWC_MNEM_EOSTATE,
+	FW_FLOWC_MNEM_SCHEDCLASS,
+	FW_FLOWC_MNEM_DCBPRIO,
+	FW_FLOWC_MNEM_SND_SCALE,
+	FW_FLOWC_MNEM_RCV_SCALE,
 };
 
 struct fw_flowc_mnemval {