Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:

 1) Unified UDP encapsulation offload methods for drivers, from
    Alexander Duyck.

 2) Make DSA binding more sane, from Andrew Lunn.

 3) Support QCA9888 chips in ath10k, from Anilkumar Kolli.

 4) Several workqueue usage cleanups, from Bhaktipriya Shridhar.

 5) Add XDP (eXpress Data Path), essentially running BPF programs on RX
    packets as soon as the device sees them, with the option to mirror
    the packet on TX via the same interface.  From Brenden Blanco and
    others.

 6) Allow qdisc/class stats dumps to run lockless, from Eric Dumazet.

 7) Add VLAN support to b53 and bcm_sf2, from Florian Fainelli.

 8) Simplify netlink conntrack entry layout, from Florian Westphal.

 9) Add ipv4 forwarding support to mlxsw spectrum driver, from Ido
    Schimmel, Yotam Gigi, and Jiri Pirko.

10) Add SKB array infrastructure and convert tun and macvtap over to it.
    From Michael S Tsirkin and Jason Wang.

11) Support qdisc packet injection in pktgen, from John Fastabend.

12) Add neighbour monitoring framework to TIPC, from Jon Paul Maloy.

13) Add NV congestion control support to TCP, from Lawrence Brakmo.

14) Add GSO support to SCTP, from Marcelo Ricardo Leitner.

15) Allow GRO and RPS to function on macsec devices, from Paolo Abeni.

16) Support MPLS over IPV4, from Simon Horman.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1622 commits)
  xgene: Fix build warning with ACPI disabled.
  be2net: perform temperature query in adapter regardless of its interface state
  l2tp: Correctly return -EBADF from pppol2tp_getname.
  net/mlx5_core/health: Remove deprecated create_singlethread_workqueue
  net: ipmr/ip6mr: update lastuse on entry change
  macsec: ensure rx_sa is set when validation is disabled
  tipc: dump monitor attributes
  tipc: add a function to get the bearer name
  tipc: get monitor threshold for the cluster
  tipc: make cluster size threshold for monitoring configurable
  tipc: introduce constants for tipc address validation
  net: neigh: disallow transition to NUD_STALE if lladdr is unchanged in neigh_update()
  MAINTAINERS: xgene: Add driver and documentation path
  Documentation: dtb: xgene: Add MDIO node
  dtb: xgene: Add MDIO node
  drivers: net: xgene: ethtool: Use phy_ethtool_gset and sset
  drivers: net: xgene: Use exported functions
  drivers: net: xgene: Enable MDIO driver
  drivers: net: xgene: Add backward compatibility
  drivers: net: phy: xgene: Add MDIO driver
  ...

9 files changed, 455 insertions, 840 deletions

diff --git a/drivers/scsi/cxgbi/Makefile b/drivers/scsi/cxgbi/Makefile
index 86007e344955..a73781ac1800 100644
--- a/drivers/scsi/cxgbi/Makefile
+++ b/drivers/scsi/cxgbi/Makefile
@@ -1,2 +1,4 @@
+ccflags-y += -Idrivers/net/ethernet/chelsio/libcxgb
+
 obj-$(CONFIG_SCSI_CXGB3_ISCSI)	+= libcxgbi.o cxgb3i/
 obj-$(CONFIG_SCSI_CXGB4_ISCSI)	+= libcxgbi.o cxgb4i/
diff --git a/drivers/scsi/cxgbi/cxgb3i/Kbuild b/drivers/scsi/cxgbi/cxgb3i/Kbuild
index 961a12f6d318..663c52e05d81 100644
--- a/drivers/scsi/cxgbi/cxgb3i/Kbuild
+++ b/drivers/scsi/cxgbi/cxgb3i/Kbuild
@@ -1,3 +1,4 @@
 ccflags-y += -I$(srctree)/drivers/net/ethernet/chelsio/cxgb3
+ccflags-y += -I$(srctree)/drivers/net/ethernet/chelsio/libcxgb
 
 obj-$(CONFIG_SCSI_CXGB3_ISCSI) += cxgb3i.o
diff --git a/drivers/scsi/cxgbi/cxgb3i/Kconfig b/drivers/scsi/cxgbi/cxgb3i/Kconfig
index e4603985dce3..f68c871b16ca 100644
--- a/drivers/scsi/cxgbi/cxgb3i/Kconfig
+++ b/drivers/scsi/cxgbi/cxgb3i/Kconfig
@@ -5,6 +5,7 @@ config SCSI_CXGB3_ISCSI
 	select ETHERNET
 	select NET_VENDOR_CHELSIO
 	select CHELSIO_T3
+	select CHELSIO_LIB
 	select SCSI_ISCSI_ATTRS
 	---help---
 	  This driver supports iSCSI offload for the Chelsio T3 devices.
diff --git a/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c b/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c
index e22a268fd311..33e83464e091 100644
--- a/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c
+++ b/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c
@@ -1028,7 +1028,7 @@ cxgb3_cpl_handler_func cxgb3i_cpl_handlers[NUM_CPL_CMDS] = {
  * cxgb3i_ofld_init - allocate and initialize resources for each adapter found
  * @cdev:	cxgbi adapter
  */
-int cxgb3i_ofld_init(struct cxgbi_device *cdev)
+static int cxgb3i_ofld_init(struct cxgbi_device *cdev)
 {
 	struct t3cdev *t3dev = (struct t3cdev *)cdev->lldev;
 	struct adap_ports port;
@@ -1076,64 +1076,69 @@ static inline void ulp_mem_io_set_hdr(struct sk_buff *skb, unsigned int addr)
 	req->wr.wr_hi = htonl(V_WR_OP(FW_WROPCODE_BYPASS));
 	req->cmd_lock_addr = htonl(V_ULP_MEMIO_ADDR(addr >> 5) |
 				   V_ULPTX_CMD(ULP_MEM_WRITE));
-	req->len = htonl(V_ULP_MEMIO_DATA_LEN(PPOD_SIZE >> 5) |
-			 V_ULPTX_NFLITS((PPOD_SIZE >> 3) + 1));
+	req->len = htonl(V_ULP_MEMIO_DATA_LEN(IPPOD_SIZE >> 5) |
+			 V_ULPTX_NFLITS((IPPOD_SIZE >> 3) + 1));
 }
 
-static int ddp_set_map(struct cxgbi_sock *csk, struct cxgbi_pagepod_hdr *hdr,
-			unsigned int idx, unsigned int npods,
-				struct cxgbi_gather_list *gl)
+static struct cxgbi_ppm *cdev2ppm(struct cxgbi_device *cdev)
 {
-	struct cxgbi_device *cdev = csk->cdev;
-	struct cxgbi_ddp_info *ddp = cdev->ddp;
-	unsigned int pm_addr = (idx << PPOD_SIZE_SHIFT) + ddp->llimit;
-	int i;
+	return ((struct t3cdev *)cdev->lldev)->ulp_iscsi;
+}
 
-	log_debug(1 << CXGBI_DBG_DDP,
-		"csk 0x%p, idx %u, npods %u, gl 0x%p.\n",
-		csk, idx, npods, gl);
+static int ddp_set_map(struct cxgbi_ppm *ppm, struct cxgbi_sock *csk,
+		       struct cxgbi_task_tag_info *ttinfo)
+{
+	unsigned int idx = ttinfo->idx;
+	unsigned int npods = ttinfo->npods;
+	struct scatterlist *sg = ttinfo->sgl;
+	struct cxgbi_pagepod *ppod;
+	struct ulp_mem_io *req;
+	unsigned int sg_off;
+	unsigned int pm_addr = (idx << PPOD_SIZE_SHIFT) + ppm->llimit;
+	int i;
 
-	for (i = 0; i < npods; i++, idx++, pm_addr += PPOD_SIZE) {
+	for (i = 0; i < npods; i++, idx++, pm_addr += IPPOD_SIZE) {
 		struct sk_buff *skb = alloc_wr(sizeof(struct ulp_mem_io) +
-						PPOD_SIZE, 0, GFP_ATOMIC);
+					       IPPOD_SIZE, 0, GFP_ATOMIC);
 
 		if (!skb)
 			return -ENOMEM;
-
 		ulp_mem_io_set_hdr(skb, pm_addr);
-		cxgbi_ddp_ppod_set((struct cxgbi_pagepod *)(skb->head +
-					sizeof(struct ulp_mem_io)),
-				   hdr, gl, i * PPOD_PAGES_MAX);
+		req = (struct ulp_mem_io *)skb->head;
+		ppod = (struct cxgbi_pagepod *)(req + 1);
+		sg_off = i * PPOD_PAGES_MAX;
+		cxgbi_ddp_set_one_ppod(ppod, ttinfo, &sg,
+				       &sg_off);
 		skb->priority = CPL_PRIORITY_CONTROL;
-		cxgb3_ofld_send(cdev->lldev, skb);
+		cxgb3_ofld_send(ppm->lldev, skb);
 	}
 	return 0;
 }
 
-static void ddp_clear_map(struct cxgbi_hba *chba, unsigned int tag,
-			  unsigned int idx, unsigned int npods)
+static void ddp_clear_map(struct cxgbi_device *cdev, struct cxgbi_ppm *ppm,
+			  struct cxgbi_task_tag_info *ttinfo)
 {
-	struct cxgbi_device *cdev = chba->cdev;
-	struct cxgbi_ddp_info *ddp = cdev->ddp;
-	unsigned int pm_addr = (idx << PPOD_SIZE_SHIFT) + ddp->llimit;
+	unsigned int idx = ttinfo->idx;
+	unsigned int pm_addr = (idx << PPOD_SIZE_SHIFT) + ppm->llimit;
+	unsigned int npods = ttinfo->npods;
 	int i;
 
 	log_debug(1 << CXGBI_DBG_DDP,
-		"cdev 0x%p, idx %u, npods %u, tag 0x%x.\n",
-		cdev, idx, npods, tag);
+		  "cdev 0x%p, clear idx %u, npods %u.\n",
+		  cdev, idx, npods);
 
-	for (i = 0; i < npods; i++, idx++, pm_addr += PPOD_SIZE) {
+	for (i = 0; i < npods; i++, idx++, pm_addr += IPPOD_SIZE) {
 		struct sk_buff *skb = alloc_wr(sizeof(struct ulp_mem_io) +
-						PPOD_SIZE, 0, GFP_ATOMIC);
+					       IPPOD_SIZE, 0, GFP_ATOMIC);
 
 		if (!skb) {
-			pr_err("tag 0x%x, 0x%x, %d/%u, skb OOM.\n",
-				tag, idx, i, npods);
+			pr_err("cdev 0x%p, clear ddp, %u,%d/%u, skb OOM.\n",
+			       cdev, idx, i, npods);
 			continue;
 		}
 		ulp_mem_io_set_hdr(skb, pm_addr);
 		skb->priority = CPL_PRIORITY_CONTROL;
-		cxgb3_ofld_send(cdev->lldev, skb);
+		cxgb3_ofld_send(ppm->lldev, skb);
 	}
 }
 
@@ -1203,82 +1208,68 @@ static int ddp_setup_conn_digest(struct cxgbi_sock *csk, unsigned int tid,
 }
 
 /**
- * t3_ddp_cleanup - release the cxgb3 adapter's ddp resource
- * @cdev: cxgb3i adapter
- * release all the resource held by the ddp pagepod manager for a given
- * adapter if needed
- */
-
-static void t3_ddp_cleanup(struct cxgbi_device *cdev)
-{
-	struct t3cdev *tdev = (struct t3cdev *)cdev->lldev;
-
-	if (cxgbi_ddp_cleanup(cdev)) {
-		pr_info("t3dev 0x%p, ulp_iscsi no more user.\n", tdev);
-		tdev->ulp_iscsi = NULL;
-	}
-}
-
-/**
- * ddp_init - initialize the cxgb3 adapter's ddp resource
+ * cxgb3i_ddp_init - initialize the cxgb3 adapter's ddp resource
  * @cdev: cxgb3i adapter
  * initialize the ddp pagepod manager for a given adapter
  */
 static int cxgb3i_ddp_init(struct cxgbi_device *cdev)
 {
 	struct t3cdev *tdev = (struct t3cdev *)cdev->lldev;
-	struct cxgbi_ddp_info *ddp = tdev->ulp_iscsi;
+	struct net_device *ndev = cdev->ports[0];
+	struct cxgbi_tag_format tformat;
+	unsigned int ppmax, tagmask = 0;
 	struct ulp_iscsi_info uinfo;
-	unsigned int pgsz_factor[4];
 	int i, err;
 
-	if (ddp) {
-		kref_get(&ddp->refcnt);
-		pr_warn("t3dev 0x%p, ddp 0x%p already set up.\n",
-			tdev, tdev->ulp_iscsi);
-		cdev->ddp = ddp;
-		return -EALREADY;
-	}
-
 	err = tdev->ctl(tdev, ULP_ISCSI_GET_PARAMS, &uinfo);
 	if (err < 0) {
-		pr_err("%s, failed to get iscsi param err=%d.\n",
-			 tdev->name, err);
+		pr_err("%s, failed to get iscsi param %d.\n",
+		       ndev->name, err);
 		return err;
 	}
+	if (uinfo.llimit >= uinfo.ulimit) {
+		pr_warn("T3 %s, iscsi NOT enabled %u ~ %u!\n",
+			ndev->name, uinfo.llimit, uinfo.ulimit);
+		return -EACCES;
+	}
 
-	err = cxgbi_ddp_init(cdev, uinfo.llimit, uinfo.ulimit,
-			uinfo.max_txsz, uinfo.max_rxsz);
-	if (err < 0)
-		return err;
+	ppmax = (uinfo.ulimit - uinfo.llimit + 1) >> PPOD_SIZE_SHIFT;
+	tagmask = cxgbi_tagmask_set(ppmax);
 
-	ddp = cdev->ddp;
+	pr_info("T3 %s: 0x%x~0x%x, 0x%x, tagmask 0x%x -> 0x%x.\n",
+		ndev->name, uinfo.llimit, uinfo.ulimit, ppmax, uinfo.tagmask,
+		tagmask);
 
-	uinfo.tagmask = ddp->idx_mask << PPOD_IDX_SHIFT;
-	cxgbi_ddp_page_size_factor(pgsz_factor);
+	memset(&tformat, 0, sizeof(struct cxgbi_tag_format));
 	for (i = 0; i < 4; i++)
-		uinfo.pgsz_factor[i] = pgsz_factor[i];
-	uinfo.ulimit = uinfo.llimit + (ddp->nppods << PPOD_SIZE_SHIFT);
+		tformat.pgsz_order[i] = uinfo.pgsz_factor[i];
+	cxgbi_tagmask_check(tagmask, &tformat);
 
-	err = tdev->ctl(tdev, ULP_ISCSI_SET_PARAMS, &uinfo);
-	if (err < 0) {
-		pr_warn("%s unable to set iscsi param err=%d, ddp disabled.\n",
-			tdev->name, err);
-		cxgbi_ddp_cleanup(cdev);
-		return err;
+	cxgbi_ddp_ppm_setup(&tdev->ulp_iscsi, cdev, &tformat, ppmax,
+			    uinfo.llimit, uinfo.llimit, 0);
+	if (!(cdev->flags & CXGBI_FLAG_DDP_OFF)) {
+		uinfo.tagmask = tagmask;
+		uinfo.ulimit = uinfo.llimit + (ppmax << PPOD_SIZE_SHIFT);
+
+		err = tdev->ctl(tdev, ULP_ISCSI_SET_PARAMS, &uinfo);
+		if (err < 0) {
+			pr_err("T3 %s fail to set iscsi param %d.\n",
+			       ndev->name, err);
+			cdev->flags |= CXGBI_FLAG_DDP_OFF;
+		}
+		err = 0;
 	}
-	tdev->ulp_iscsi = ddp;
 
 	cdev->csk_ddp_setup_digest = ddp_setup_conn_digest;
 	cdev->csk_ddp_setup_pgidx = ddp_setup_conn_pgidx;
-	cdev->csk_ddp_set = ddp_set_map;
-	cdev->csk_ddp_clear = ddp_clear_map;
-
-	pr_info("tdev 0x%p, nppods %u, bits %u, mask 0x%x,0x%x pkt %u/%u, "
-		"%u/%u.\n",
-		tdev, ddp->nppods, ddp->idx_bits, ddp->idx_mask,
-		ddp->rsvd_tag_mask, ddp->max_txsz, uinfo.max_txsz,
-		ddp->max_rxsz, uinfo.max_rxsz);
+	cdev->csk_ddp_set_map = ddp_set_map;
+	cdev->csk_ddp_clear_map = ddp_clear_map;
+	cdev->cdev2ppm = cdev2ppm;
+	cdev->tx_max_size = min_t(unsigned int, ULP2_MAX_PDU_PAYLOAD,
+				  uinfo.max_txsz - ISCSI_PDU_NONPAYLOAD_LEN);
+	cdev->rx_max_size = min_t(unsigned int, ULP2_MAX_PDU_PAYLOAD,
+				  uinfo.max_rxsz - ISCSI_PDU_NONPAYLOAD_LEN);
+
 	return 0;
 }
 
@@ -1325,7 +1316,6 @@ static void cxgb3i_dev_open(struct t3cdev *t3dev)
 	cdev->rx_credit_thres = cxgb3i_rx_credit_thres;
 	cdev->skb_tx_rsvd = CXGB3I_TX_HEADER_LEN;
 	cdev->skb_rx_extra = sizeof(struct cpl_iscsi_hdr_norss);
-	cdev->dev_ddp_cleanup = t3_ddp_cleanup;
 	cdev->itp = &cxgb3i_iscsi_transport;
 
 	err = cxgb3i_ddp_init(cdev);
diff --git a/drivers/scsi/cxgbi/cxgb4i/Kbuild b/drivers/scsi/cxgbi/cxgb4i/Kbuild
index 37458643749b..38e03c280417 100644
--- a/drivers/scsi/cxgbi/cxgb4i/Kbuild
+++ b/drivers/scsi/cxgbi/cxgb4i/Kbuild
@@ -1,3 +1,4 @@
 ccflags-y += -I$(srctree)/drivers/net/ethernet/chelsio/cxgb4
+ccflags-y += -I$(srctree)/drivers/net/ethernet/chelsio/libcxgb
 
 obj-$(CONFIG_SCSI_CXGB4_ISCSI) += cxgb4i.o
diff --git a/drivers/scsi/cxgbi/cxgb4i/Kconfig b/drivers/scsi/cxgbi/cxgb4i/Kconfig
index 8c4e423037b6..594f593c8821 100644
--- a/drivers/scsi/cxgbi/cxgb4i/Kconfig
+++ b/drivers/scsi/cxgbi/cxgb4i/Kconfig
@@ -5,6 +5,7 @@ config SCSI_CXGB4_ISCSI
 	select ETHERNET
 	select NET_VENDOR_CHELSIO
 	select CHELSIO_T4
+	select CHELSIO_LIB
 	select SCSI_ISCSI_ATTRS
 	---help---
 	  This driver supports iSCSI offload for the Chelsio T4 devices.
diff --git a/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c
index 339f6b7f4803..e4ba2d2616cd 100644
--- a/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c
+++ b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c
@@ -1503,7 +1503,7 @@ rel_resource_without_clip:
 	return -EINVAL;
 }
 
-cxgb4i_cplhandler_func cxgb4i_cplhandlers[NUM_CPL_CMDS] = {
+static cxgb4i_cplhandler_func cxgb4i_cplhandlers[NUM_CPL_CMDS] = {
 	[CPL_ACT_ESTABLISH] = do_act_establish,
 	[CPL_ACT_OPEN_RPL] = do_act_open_rpl,
 	[CPL_PEER_CLOSE] = do_peer_close,
@@ -1519,7 +1519,7 @@ cxgb4i_cplhandler_func cxgb4i_cplhandlers[NUM_CPL_CMDS] = {
 	[CPL_RX_DATA] = do_rx_data,
 };
 
-int cxgb4i_ofld_init(struct cxgbi_device *cdev)
+static int cxgb4i_ofld_init(struct cxgbi_device *cdev)
 {
 	int rc;
 
@@ -1543,24 +1543,22 @@ int cxgb4i_ofld_init(struct cxgbi_device *cdev)
 	return 0;
 }
 
-/*
- * functions to program the pagepod in h/w
- */
-#define ULPMEM_IDATA_MAX_NPPODS	4 /* 256/PPOD_SIZE */
-static inline void ulp_mem_io_set_hdr(struct cxgb4_lld_info *lldi,
-				struct ulp_mem_io *req,
-				unsigned int wr_len, unsigned int dlen,
-				unsigned int pm_addr)
+static inline void
+ulp_mem_io_set_hdr(struct cxgbi_device *cdev,
+		   struct ulp_mem_io *req,
+		   unsigned int wr_len, unsigned int dlen,
+		   unsigned int pm_addr,
+		   int tid)
 {
+	struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(cdev);
 	struct ulptx_idata *idata = (struct ulptx_idata *)(req + 1);
 
-	INIT_ULPTX_WR(req, wr_len, 0, 0);
-	if (is_t4(lldi->adapter_type))
-		req->cmd = htonl(ULPTX_CMD_V(ULP_TX_MEM_WRITE) |
-					(ULP_MEMIO_ORDER_F));
-	else
-		req->cmd = htonl(ULPTX_CMD_V(ULP_TX_MEM_WRITE) |
-					(T5_ULP_MEMIO_IMM_F));
+	INIT_ULPTX_WR(req, wr_len, 0, tid);
+	req->wr.wr_hi = htonl(FW_WR_OP_V(FW_ULPTX_WR) |
+		FW_WR_ATOMIC_V(0));
+	req->cmd = htonl(ULPTX_CMD_V(ULP_TX_MEM_WRITE) |
+		ULP_MEMIO_ORDER_V(is_t4(lldi->adapter_type)) |
+		T5_ULP_MEMIO_IMM_V(!is_t4(lldi->adapter_type)));
 	req->dlen = htonl(ULP_MEMIO_DATA_LEN_V(dlen >> 5));
 	req->lock_addr = htonl(ULP_MEMIO_ADDR_V(pm_addr >> 5));
 	req->len16 = htonl(DIV_ROUND_UP(wr_len - sizeof(req->wr), 16));
@@ -1569,82 +1567,89 @@ static inline void ulp_mem_io_set_hdr(struct cxgb4_lld_info *lldi,
 	idata->len = htonl(dlen);
 }
 
-static int ddp_ppod_write_idata(struct cxgbi_device *cdev, unsigned int port_id,
-				struct cxgbi_pagepod_hdr *hdr, unsigned int idx,
-				unsigned int npods,
-				struct cxgbi_gather_list *gl,
-				unsigned int gl_pidx)
+static struct sk_buff *
+ddp_ppod_init_idata(struct cxgbi_device *cdev,
+		    struct cxgbi_ppm *ppm,
+		    unsigned int idx, unsigned int npods,
+		    unsigned int tid)
 {
-	struct cxgbi_ddp_info *ddp = cdev->ddp;
-	struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(cdev);
-	struct sk_buff *skb;
-	struct ulp_mem_io *req;
-	struct ulptx_idata *idata;
-	struct cxgbi_pagepod *ppod;
-	unsigned int pm_addr = idx * PPOD_SIZE + ddp->llimit;
-	unsigned int dlen = PPOD_SIZE * npods;
+	unsigned int pm_addr = (idx << PPOD_SIZE_SHIFT) + ppm->llimit;
+	unsigned int dlen = npods << PPOD_SIZE_SHIFT;
 	unsigned int wr_len = roundup(sizeof(struct ulp_mem_io) +
 				sizeof(struct ulptx_idata) + dlen, 16);
-	unsigned int i;
+	struct sk_buff *skb = alloc_wr(wr_len, 0, GFP_ATOMIC);
 
-	skb = alloc_wr(wr_len, 0, GFP_ATOMIC);
 	if (!skb) {
-		pr_err("cdev 0x%p, idx %u, npods %u, OOM.\n",
-			cdev, idx, npods);
-		return -ENOMEM;
+		pr_err("%s: %s idx %u, npods %u, OOM.\n",
+		       __func__, ppm->ndev->name, idx, npods);
+		return NULL;
 	}
-	req = (struct ulp_mem_io *)skb->head;
-	set_wr_txq(skb, CPL_PRIORITY_CONTROL, 0);
 
-	ulp_mem_io_set_hdr(lldi, req, wr_len, dlen, pm_addr);
+	ulp_mem_io_set_hdr(cdev, (struct ulp_mem_io *)skb->head, wr_len, dlen,
+			   pm_addr, tid);
+
+	return skb;
+}
+
+static int ddp_ppod_write_idata(struct cxgbi_ppm *ppm, struct cxgbi_sock *csk,
+				struct cxgbi_task_tag_info *ttinfo,
+				unsigned int idx, unsigned int npods,
+				struct scatterlist **sg_pp,
+				unsigned int *sg_off)
+{
+	struct cxgbi_device *cdev = csk->cdev;
+	struct sk_buff *skb = ddp_ppod_init_idata(cdev, ppm, idx, npods,
+						  csk->tid);
+	struct ulp_mem_io *req;
+	struct ulptx_idata *idata;
+	struct cxgbi_pagepod *ppod;
+	int i;
+
+	if (!skb)
+		return -ENOMEM;
+
+	req = (struct ulp_mem_io *)skb->head;
 	idata = (struct ulptx_idata *)(req + 1);
 	ppod = (struct cxgbi_pagepod *)(idata + 1);
 
-	for (i = 0; i < npods; i++, ppod++, gl_pidx += PPOD_PAGES_MAX) {
-		if (!hdr && !gl)
-			cxgbi_ddp_ppod_clear(ppod);
-		else
-			cxgbi_ddp_ppod_set(ppod, hdr, gl, gl_pidx);
-	}
+	for (i = 0; i < npods; i++, ppod++)
+		cxgbi_ddp_set_one_ppod(ppod, ttinfo, sg_pp, sg_off);
+
+	cxgbi_skcb_set_flag(skb, SKCBF_TX_MEM_WRITE);
+	cxgbi_skcb_set_flag(skb, SKCBF_TX_FLAG_COMPL);
+	set_wr_txq(skb, CPL_PRIORITY_DATA, csk->port_id);
+
+	spin_lock_bh(&csk->lock);
+	cxgbi_sock_skb_entail(csk, skb);
+	spin_unlock_bh(&csk->lock);
 
-	cxgb4_ofld_send(cdev->ports[port_id], skb);
 	return 0;
 }
 
-static int ddp_set_map(struct cxgbi_sock *csk, struct cxgbi_pagepod_hdr *hdr,
-			unsigned int idx, unsigned int npods,
-			struct cxgbi_gather_list *gl)
+static int ddp_set_map(struct cxgbi_ppm *ppm, struct cxgbi_sock *csk,
+		       struct cxgbi_task_tag_info *ttinfo)
 {
+	unsigned int pidx = ttinfo->idx;
+	unsigned int npods = ttinfo->npods;
 	unsigned int i, cnt;
 	int err = 0;
+	struct scatterlist *sg = ttinfo->sgl;
+	unsigned int offset = 0;
 
-	for (i = 0; i < npods; i += cnt, idx += cnt) {
-		cnt = npods - i;
-		if (cnt > ULPMEM_IDATA_MAX_NPPODS)
-			cnt = ULPMEM_IDATA_MAX_NPPODS;
-		err = ddp_ppod_write_idata(csk->cdev, csk->port_id, hdr,
-					idx, cnt, gl, 4 * i);
-		if (err < 0)
-			break;
-	}
-	return err;
-}
-
-static void ddp_clear_map(struct cxgbi_hba *chba, unsigned int tag,
-			  unsigned int idx, unsigned int npods)
-{
-	unsigned int i, cnt;
-	int err;
+	ttinfo->cid = csk->port_id;
 
-	for (i = 0; i < npods; i += cnt, idx += cnt) {
+	for (i = 0; i < npods; i += cnt, pidx += cnt) {
 		cnt = npods - i;
+
 		if (cnt > ULPMEM_IDATA_MAX_NPPODS)
 			cnt = ULPMEM_IDATA_MAX_NPPODS;
-		err = ddp_ppod_write_idata(chba->cdev, chba->port_id, NULL,
-					idx, cnt, NULL, 0);
+		err = ddp_ppod_write_idata(ppm, csk, ttinfo, pidx, cnt,
+					   &sg, &offset);
 		if (err < 0)
 			break;
 	}
+
+	return err;
 }
 
 static int ddp_setup_conn_pgidx(struct cxgbi_sock *csk, unsigned int tid,
@@ -1710,48 +1715,46 @@ static int ddp_setup_conn_digest(struct cxgbi_sock *csk, unsigned int tid,
 	return 0;
 }
 
+static struct cxgbi_ppm *cdev2ppm(struct cxgbi_device *cdev)
+{
+	return (struct cxgbi_ppm *)(*((struct cxgb4_lld_info *)
+				       (cxgbi_cdev_priv(cdev)))->iscsi_ppm);
+}
+
 static int cxgb4i_ddp_init(struct cxgbi_device *cdev)
 {
 	struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(cdev);
-	struct cxgbi_ddp_info *ddp = cdev->ddp;
-	unsigned int tagmask, pgsz_factor[4];
-	int err;
-
-	if (ddp) {
-		kref_get(&ddp->refcnt);
-		pr_warn("cdev 0x%p, ddp 0x%p already set up.\n",
-			cdev, cdev->ddp);
-		return -EALREADY;
+	struct net_device *ndev = cdev->ports[0];
+	struct cxgbi_tag_format tformat;
+	unsigned int ppmax;
+	int i;
+
+	if (!lldi->vr->iscsi.size) {
+		pr_warn("%s, iscsi NOT enabled, check config!\n", ndev->name);
+		return -EACCES;
 	}
 
-	err = cxgbi_ddp_init(cdev, lldi->vr->iscsi.start,
-			lldi->vr->iscsi.start + lldi->vr->iscsi.size - 1,
-			lldi->iscsi_iolen, lldi->iscsi_iolen);
-	if (err < 0)
-		return err;
+	cdev->flags |= CXGBI_FLAG_USE_PPOD_OFLDQ;
+	ppmax = lldi->vr->iscsi.size >> PPOD_SIZE_SHIFT;
 
-	ddp = cdev->ddp;
+	memset(&tformat, 0, sizeof(struct cxgbi_tag_format));
+	for (i = 0; i < 4; i++)
+		tformat.pgsz_order[i] = (lldi->iscsi_pgsz_order >> (i << 3))
+					 & 0xF;
+	cxgbi_tagmask_check(lldi->iscsi_tagmask, &tformat);
 
-	tagmask = ddp->idx_mask << PPOD_IDX_SHIFT;
-	cxgbi_ddp_page_size_factor(pgsz_factor);
-	cxgb4_iscsi_init(lldi->ports[0], tagmask, pgsz_factor);
+	cxgbi_ddp_ppm_setup(lldi->iscsi_ppm, cdev, &tformat, ppmax,
+			    lldi->iscsi_llimit, lldi->vr->iscsi.start, 2);
 
 	cdev->csk_ddp_setup_digest = ddp_setup_conn_digest;
 	cdev->csk_ddp_setup_pgidx = ddp_setup_conn_pgidx;
-	cdev->csk_ddp_set = ddp_set_map;
-	cdev->csk_ddp_clear = ddp_clear_map;
-
-	pr_info("cxgb4i 0x%p tag: sw %u, rsvd %u,%u, mask 0x%x.\n",
-		cdev, cdev->tag_format.sw_bits, cdev->tag_format.rsvd_bits,
-		cdev->tag_format.rsvd_shift, cdev->tag_format.rsvd_mask);
-	pr_info("cxgb4i 0x%p, nppods %u, bits %u, mask 0x%x,0x%x pkt %u/%u, "
-		" %u/%u.\n",
-		cdev, ddp->nppods, ddp->idx_bits, ddp->idx_mask,
-		ddp->rsvd_tag_mask, ddp->max_txsz, lldi->iscsi_iolen,
-		ddp->max_rxsz, lldi->iscsi_iolen);
-	pr_info("cxgb4i 0x%p max payload size: %u/%u, %u/%u.\n",
-		cdev, cdev->tx_max_size, ddp->max_txsz, cdev->rx_max_size,
-		ddp->max_rxsz);
+	cdev->csk_ddp_set_map = ddp_set_map;
+	cdev->tx_max_size = min_t(unsigned int, ULP2_MAX_PDU_PAYLOAD,
+				  lldi->iscsi_iolen - ISCSI_PDU_NONPAYLOAD_LEN);
+	cdev->rx_max_size = min_t(unsigned int, ULP2_MAX_PDU_PAYLOAD,
+				  lldi->iscsi_iolen - ISCSI_PDU_NONPAYLOAD_LEN);
+	cdev->cdev2ppm = cdev2ppm;
+
 	return 0;
 }
 
diff --git a/drivers/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c
index ead83a24bcd1..d1421139e6ea 100644
--- a/drivers/scsi/cxgbi/libcxgbi.c
+++ b/drivers/scsi/cxgbi/libcxgbi.c
@@ -64,6 +64,14 @@ static DEFINE_MUTEX(cdev_mutex);
 static LIST_HEAD(cdev_rcu_list);
 static DEFINE_SPINLOCK(cdev_rcu_lock);
 
+static inline void cxgbi_decode_sw_tag(u32 sw_tag, int *idx, int *age)
+{
+	if (age)
+		*age = sw_tag & 0x7FFF;
+	if (idx)
+		*idx = (sw_tag >> 16) & 0x7FFF;
+}
+
 int cxgbi_device_portmap_create(struct cxgbi_device *cdev, unsigned int base,
 				unsigned int max_conn)
 {
@@ -113,12 +121,7 @@ static inline void cxgbi_device_destroy(struct cxgbi_device *cdev)
 		"cdev 0x%p, p# %u.\n", cdev, cdev->nports);
 	cxgbi_hbas_remove(cdev);
 	cxgbi_device_portmap_cleanup(cdev);
-	if (cdev->dev_ddp_cleanup)
-		cdev->dev_ddp_cleanup(cdev);
-	else
-		cxgbi_ddp_cleanup(cdev);
-	if (cdev->ddp)
-		cxgbi_ddp_cleanup(cdev);
+	cxgbi_ppm_release(cdev->cdev2ppm(cdev));
 	if (cdev->pmap.max_connect)
 		cxgbi_free_big_mem(cdev->pmap.port_csk);
 	kfree(cdev);
@@ -1182,525 +1185,245 @@ out_err:
 	goto done;
 }
 
-/*
- * 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.
- */
-
-static unsigned char ddp_page_order[DDP_PGIDX_MAX] = {0, 1, 2, 4};
-static unsigned char ddp_page_shift[DDP_PGIDX_MAX] = {12, 13, 14, 16};
-static unsigned char page_idx = DDP_PGIDX_MAX;
-
-static unsigned char sw_tag_idx_bits;
-static unsigned char sw_tag_age_bits;
-
-/*
- * Direct-Data Placement page size adjustment
- */
-static int ddp_adjust_page_table(void)
+static inline void
+scmd_get_params(struct scsi_cmnd *sc, struct scatterlist **sgl,
+		unsigned int *sgcnt, unsigned int *dlen,
+		unsigned int prot)
 {
-	int i;
-	unsigned int base_order, order;
-
-	if (PAGE_SIZE < (1UL << ddp_page_shift[0])) {
-		pr_info("PAGE_SIZE 0x%lx too small, min 0x%lx\n",
-			PAGE_SIZE, 1UL << ddp_page_shift[0]);
-		return -EINVAL;
-	}
-
-	base_order = get_order(1UL << ddp_page_shift[0]);
-	order = get_order(1UL << PAGE_SHIFT);
+	struct scsi_data_buffer *sdb = prot ? scsi_prot(sc) : scsi_out(sc);
 
-	for (i = 0; i < DDP_PGIDX_MAX; i++) {
-		/* first is the kernel page size, then just doubling */
-		ddp_page_order[i] = order - base_order + i;
-		ddp_page_shift[i] = PAGE_SHIFT + i;
-	}
-	return 0;
+	*sgl = sdb->table.sgl;
+	*sgcnt = sdb->table.nents;
+	*dlen = sdb->length;
+	/* Caution: for protection sdb, sdb->length is invalid */
 }
 
-static int ddp_find_page_index(unsigned long pgsz)
+void cxgbi_ddp_set_one_ppod(struct cxgbi_pagepod *ppod,
+			    struct cxgbi_task_tag_info *ttinfo,
+			    struct scatterlist **sg_pp, unsigned int *sg_off)
 {
+	struct scatterlist *sg = sg_pp ? *sg_pp : NULL;
+	unsigned int offset = sg_off ? *sg_off : 0;
+	dma_addr_t addr = 0UL;
+	unsigned int len = 0;
 	int i;
 
-	for (i = 0; i < DDP_PGIDX_MAX; i++) {
-		if (pgsz == (1UL << ddp_page_shift[i]))
-			return i;
-	}
-	pr_info("ddp page size %lu not supported.\n", pgsz);
-	return DDP_PGIDX_MAX;
-}
+	memcpy(ppod, &ttinfo->hdr, sizeof(struct cxgbi_pagepod_hdr));
 
-static void ddp_setup_host_page_size(void)
-{
-	if (page_idx == DDP_PGIDX_MAX) {
-		page_idx = ddp_find_page_index(PAGE_SIZE);
+	if (sg) {
+		addr = sg_dma_address(sg);
+		len = sg_dma_len(sg);
+	}
 
-		if (page_idx == DDP_PGIDX_MAX) {
-			pr_info("system PAGE %lu, update hw.\n", PAGE_SIZE);
-			if (ddp_adjust_page_table() < 0) {
-				pr_info("PAGE %lu, disable ddp.\n", PAGE_SIZE);
-				return;
+	for (i = 0; i < PPOD_PAGES_MAX; i++) {
+		if (sg) {
+			ppod->addr[i] = cpu_to_be64(addr + offset);
+			offset += PAGE_SIZE;
+			if (offset == (len + sg->offset)) {
+				offset = 0;
+				sg = sg_next(sg);
+				if (sg) {
+					addr = sg_dma_address(sg);
+					len = sg_dma_len(sg);
+				}
 			}
-			page_idx = ddp_find_page_index(PAGE_SIZE);
+		} else {
+			ppod->addr[i] = 0ULL;
 		}
-		pr_info("system PAGE %lu, ddp idx %u.\n", PAGE_SIZE, page_idx);
 	}
-}
-
-void cxgbi_ddp_page_size_factor(int *pgsz_factor)
-{
-	int i;
-
-	for (i = 0; i < DDP_PGIDX_MAX; i++)
-		pgsz_factor[i] = ddp_page_order[i];
-}
-EXPORT_SYMBOL_GPL(cxgbi_ddp_page_size_factor);
-
-/*
- * DDP setup & teardown
- */
-
-void cxgbi_ddp_ppod_set(struct cxgbi_pagepod *ppod,
-			struct cxgbi_pagepod_hdr *hdr,
-			struct cxgbi_gather_list *gl, unsigned int gidx)
-{
-	int i;
-
-	memcpy(ppod, hdr, sizeof(*hdr));
-	for (i = 0; i < (PPOD_PAGES_MAX + 1); i++, gidx++) {
-		ppod->addr[i] = gidx < gl->nelem ?
-				cpu_to_be64(gl->phys_addr[gidx]) : 0ULL;
-	}
-}
-EXPORT_SYMBOL_GPL(cxgbi_ddp_ppod_set);
-
-void cxgbi_ddp_ppod_clear(struct cxgbi_pagepod *ppod)
-{
-	memset(ppod, 0, sizeof(*ppod));
-}
-EXPORT_SYMBOL_GPL(cxgbi_ddp_ppod_clear);
-
-static inline int ddp_find_unused_entries(struct cxgbi_ddp_info *ddp,
-					unsigned int start, unsigned int max,
-					unsigned int count,
-					struct cxgbi_gather_list *gl)
-{
-	unsigned int i, j, k;
 
-	/*  not enough entries */
-	if ((max - start) < count) {
-		log_debug(1 << CXGBI_DBG_DDP,
-			"NOT enough entries %u+%u < %u.\n", start, count, max);
-		return -EBUSY;
+	/*
+	 * the fifth address needs to be repeated in the next ppod, so do
+	 * not move sg
+	 */
+	if (sg_pp) {
+		*sg_pp = sg;
+		*sg_off = offset;
 	}
 
-	max -= count;
-	spin_lock(&ddp->map_lock);
-	for (i = start; i < max;) {
-		for (j = 0, k = i; j < count; j++, k++) {
-			if (ddp->gl_map[k])
-				break;
-		}
-		if (j == count) {
-			for (j = 0, k = i; j < count; j++, k++)
-				ddp->gl_map[k] = gl;
-			spin_unlock(&ddp->map_lock);
-			return i;
+	if (offset == len) {
+		offset = 0;
+		sg = sg_next(sg);
+		if (sg) {
+			addr = sg_dma_address(sg);
+			len = sg_dma_len(sg);
 		}
-		i += j + 1;
 	}
-	spin_unlock(&ddp->map_lock);
-	log_debug(1 << CXGBI_DBG_DDP,
-		"NO suitable entries %u available.\n", count);
-	return -EBUSY;
-}
-
-static inline void ddp_unmark_entries(struct cxgbi_ddp_info *ddp,
-						int start, int count)
-{
-	spin_lock(&ddp->map_lock);
-	memset(&ddp->gl_map[start], 0,
-		count * sizeof(struct cxgbi_gather_list *));
-	spin_unlock(&ddp->map_lock);
+	ppod->addr[i] = sg ? cpu_to_be64(addr + offset) : 0ULL;
 }
+EXPORT_SYMBOL_GPL(cxgbi_ddp_set_one_ppod);
 
-static inline void ddp_gl_unmap(struct pci_dev *pdev,
-					struct cxgbi_gather_list *gl)
-{
-	int i;
+/*
+ * APIs interacting with open-iscsi libraries
+ */
 
-	for (i = 0; i < gl->nelem; i++)
-		dma_unmap_page(&pdev->dev, gl->phys_addr[i], PAGE_SIZE,
-				PCI_DMA_FROMDEVICE);
-}
+static unsigned char padding[4];
 
-static inline int ddp_gl_map(struct pci_dev *pdev,
-				    struct cxgbi_gather_list *gl)
+void cxgbi_ddp_ppm_setup(void **ppm_pp, struct cxgbi_device *cdev,
+			 struct cxgbi_tag_format *tformat, unsigned int ppmax,
+			 unsigned int llimit, unsigned int start,
+			 unsigned int rsvd_factor)
 {
-	int i;
+	int err = cxgbi_ppm_init(ppm_pp, cdev->ports[0], cdev->pdev,
+				cdev->lldev, tformat, ppmax, llimit, start,
+				rsvd_factor);
 
-	for (i = 0; i < gl->nelem; i++) {
-		gl->phys_addr[i] = dma_map_page(&pdev->dev, gl->pages[i], 0,
-						PAGE_SIZE,
-						PCI_DMA_FROMDEVICE);
-		if (unlikely(dma_mapping_error(&pdev->dev, gl->phys_addr[i]))) {
-			log_debug(1 << CXGBI_DBG_DDP,
-				"page %d 0x%p, 0x%p dma mapping err.\n",
-				i, gl->pages[i], pdev);
-			goto unmap;
-		}
-	}
-	return i;
-unmap:
-	if (i) {
-		unsigned int nelem = gl->nelem;
+	if (err >= 0) {
+		struct cxgbi_ppm *ppm = (struct cxgbi_ppm *)(*ppm_pp);
 
-		gl->nelem = i;
-		ddp_gl_unmap(pdev, gl);
-		gl->nelem = nelem;
+		if (ppm->ppmax < 1024 ||
+		    ppm->tformat.pgsz_idx_dflt >= DDP_PGIDX_MAX)
+			cdev->flags |= CXGBI_FLAG_DDP_OFF;
+		err = 0;
+	} else {
+		cdev->flags |= CXGBI_FLAG_DDP_OFF;
 	}
-	return -EINVAL;
-}
-
-static void ddp_release_gl(struct cxgbi_gather_list *gl,
-				  struct pci_dev *pdev)
-{
-	ddp_gl_unmap(pdev, gl);
-	kfree(gl);
 }
+EXPORT_SYMBOL_GPL(cxgbi_ddp_ppm_setup);
 
-static struct cxgbi_gather_list *ddp_make_gl(unsigned int xferlen,
-						    struct scatterlist *sgl,
-						    unsigned int sgcnt,
-						    struct pci_dev *pdev,
-						    gfp_t gfp)
+static int cxgbi_ddp_sgl_check(struct scatterlist *sgl, int nents)
 {
-	struct cxgbi_gather_list *gl;
+	int i;
+	int last_sgidx = nents - 1;
 	struct scatterlist *sg = sgl;
-	struct page *sgpage = sg_page(sg);
-	unsigned int sglen = sg->length;
-	unsigned int sgoffset = sg->offset;
-	unsigned int npages = (xferlen + sgoffset + PAGE_SIZE - 1) >>
-				PAGE_SHIFT;
-	int i = 1, j = 0;
-
-	if (xferlen < DDP_THRESHOLD) {
-		log_debug(1 << CXGBI_DBG_DDP,
-			"xfer %u < threshold %u, no ddp.\n",
-			xferlen, DDP_THRESHOLD);
-		return NULL;
-	}
-
-	gl = kzalloc(sizeof(struct cxgbi_gather_list) +
-		     npages * (sizeof(dma_addr_t) +
-		     sizeof(struct page *)), gfp);
-	if (!gl) {
-		log_debug(1 << CXGBI_DBG_DDP,
-			"xfer %u, %u pages, OOM.\n", xferlen, npages);
-		return NULL;
-	}
 
-	 log_debug(1 << CXGBI_DBG_DDP,
-		"xfer %u, sgl %u, gl max %u.\n", xferlen, sgcnt, npages);
-
-	gl->pages = (struct page **)&gl->phys_addr[npages];
-	gl->nelem = npages;
-	gl->length = xferlen;
-	gl->offset = sgoffset;
-	gl->pages[0] = sgpage;
-
-	for (i = 1, sg = sg_next(sgl), j = 0; i < sgcnt;
-		i++, sg = sg_next(sg)) {
-		struct page *page = sg_page(sg);
-
-		if (sgpage == page && sg->offset == sgoffset + sglen)
-			sglen += sg->length;
-		else {
-			/*  make sure the sgl is fit for ddp:
-			 *  each has the same page size, and
-			 *  all of the middle pages are used completely
-			 */
-			if ((j && sgoffset) || ((i != sgcnt - 1) &&
-			    ((sglen + sgoffset) & ~PAGE_MASK))) {
-				log_debug(1 << CXGBI_DBG_DDP,
-					"page %d/%u, %u + %u.\n",
-					i, sgcnt, sgoffset, sglen);
-				goto error_out;
-			}
+	for (i = 0; i < nents; i++, sg = sg_next(sg)) {
+		unsigned int len = sg->length + sg->offset;
 
-			j++;
-			if (j == gl->nelem || sg->offset) {
-				log_debug(1 << CXGBI_DBG_DDP,
-					"page %d/%u, offset %u.\n",
-					j, gl->nelem, sg->offset);
-				goto error_out;
-			}