[SCSI] libcxgbi: common library for cxgb3i and cxgb4i

[PATCH v5 1/3] libcxgbi: common library for cxgb3i and cxgb4i

From: Karen Xie <kxie@chelsio.com>

Extracts common functions to libcxgbi.

Signed-off-by: Karen Xie <kxie@chelsio.com>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Signed-off-by: James Bottomley <James.Bottomley@suse.de>

2 files changed, 3363 insertions, 0 deletions

diff --git a/drivers/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c
new file mode 100644
index 00000000000..db9d08a831d
--- /dev/null
+++ b/drivers/scsi/cxgbi/libcxgbi.c
@@ -0,0 +1,2610 @@
+/*
+ * libcxgbi.c: Chelsio common library for T3/T4 iSCSI driver.
+ *
+ * Copyright (c) 2010 Chelsio Communications, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.
+ *
+ * Written by: Karen Xie (kxie@chelsio.com)
+ * Written by: Rakesh Ranjan (rranjan@chelsio.com)
+ */
+
+#define pr_fmt(fmt)	KBUILD_MODNAME ":%s: " fmt, __func__
+
+#include <linux/skbuff.h>
+#include <linux/crypto.h>
+#include <linux/scatterlist.h>
+#include <linux/pci.h>
+#include <scsi/scsi.h>
+#include <scsi/scsi_cmnd.h>
+#include <scsi/scsi_host.h>
+#include <linux/if_vlan.h>
+#include <linux/inet.h>
+#include <net/dst.h>
+#include <net/route.h>
+#include <linux/inetdevice.h>	/* ip_dev_find */
+#include <net/tcp.h>
+
+static unsigned int dbg_level;
+
+#include "libcxgbi.h"
+
+#define DRV_MODULE_NAME		"libcxgbi"
+#define DRV_MODULE_DESC		"Chelsio iSCSI driver library"
+#define DRV_MODULE_VERSION	"0.9.0"
+#define DRV_MODULE_RELDATE	"Jun. 2010"
+
+MODULE_AUTHOR("Chelsio Communications, Inc.");
+MODULE_DESCRIPTION(DRV_MODULE_DESC);
+MODULE_VERSION(DRV_MODULE_VERSION);
+MODULE_LICENSE("GPL");
+
+module_param(dbg_level, uint, 0644);
+MODULE_PARM_DESC(dbg_level, "libiscsi debug level (default=0)");
+
+
+/*
+ * cxgbi device management
+ * maintains a list of the cxgbi devices
+ */
+static LIST_HEAD(cdev_list);
+static DEFINE_MUTEX(cdev_mutex);
+
+int cxgbi_device_portmap_create(struct cxgbi_device *cdev, unsigned int base,
+				unsigned int max_conn)
+{
+	struct cxgbi_ports_map *pmap = &cdev->pmap;
+
+	pmap->port_csk = cxgbi_alloc_big_mem(max_conn *
+					     sizeof(struct cxgbi_sock *),
+					     GFP_KERNEL);
+	if (!pmap->port_csk) {
+		pr_warn("cdev 0x%p, portmap OOM %u.\n", cdev, max_conn);
+		return -ENOMEM;
+	}
+
+	pmap->max_connect = max_conn;
+	pmap->sport_base = base;
+	spin_lock_init(&pmap->lock);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(cxgbi_device_portmap_create);
+
+void cxgbi_device_portmap_cleanup(struct cxgbi_device *cdev)
+{
+	struct cxgbi_ports_map *pmap = &cdev->pmap;
+	struct cxgbi_sock *csk;
+	int i;
+
+	for (i = 0; i < pmap->max_connect; i++) {
+		if (pmap->port_csk[i]) {
+			csk = pmap->port_csk[i];
+			pmap->port_csk[i] = NULL;
+			log_debug(1 << CXGBI_DBG_SOCK,
+				"csk 0x%p, cdev 0x%p, offload down.\n",
+				csk, cdev);
+			spin_lock_bh(&csk->lock);
+			cxgbi_sock_set_flag(csk, CTPF_OFFLOAD_DOWN);
+			cxgbi_sock_closed(csk);
+			spin_unlock_bh(&csk->lock);
+			cxgbi_sock_put(csk);
+		}
+	}
+}
+EXPORT_SYMBOL_GPL(cxgbi_device_portmap_cleanup);
+
+static inline void cxgbi_device_destroy(struct cxgbi_device *cdev)
+{
+	log_debug(1 << CXGBI_DBG_DEV,
+		"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);
+	if (cdev->pmap.max_connect)
+		cxgbi_free_big_mem(cdev->pmap.port_csk);
+	kfree(cdev);
+}
+
+struct cxgbi_device *cxgbi_device_register(unsigned int extra,
+					   unsigned int nports)
+{
+	struct cxgbi_device *cdev;
+
+	cdev = kzalloc(sizeof(*cdev) + extra + nports *
+			(sizeof(struct cxgbi_hba *) +
+			 sizeof(struct net_device *)),
+			GFP_KERNEL);
+	if (!cdev) {
+		pr_warn("nport %d, OOM.\n", nports);
+		return NULL;
+	}
+	cdev->ports = (struct net_device **)(cdev + 1);
+	cdev->hbas = (struct cxgbi_hba **)(((char*)cdev->ports) + nports *
+						sizeof(struct net_device *));
+	if (extra)
+		cdev->dd_data = ((char *)cdev->hbas) +
+				nports * sizeof(struct cxgbi_hba *);
+	spin_lock_init(&cdev->pmap.lock);
+
+	mutex_lock(&cdev_mutex);
+	list_add_tail(&cdev->list_head, &cdev_list);
+	mutex_unlock(&cdev_mutex);
+
+	log_debug(1 << CXGBI_DBG_DEV,
+		"cdev 0x%p, p# %u.\n", cdev, nports);
+	return cdev;
+}
+EXPORT_SYMBOL_GPL(cxgbi_device_register);
+
+void cxgbi_device_unregister(struct cxgbi_device *cdev)
+{
+	log_debug(1 << CXGBI_DBG_DEV,
+		"cdev 0x%p, p# %u,%s.\n",
+		cdev, cdev->nports, cdev->nports ? cdev->ports[0]->name : "");
+	mutex_lock(&cdev_mutex);
+	list_del(&cdev->list_head);
+	mutex_unlock(&cdev_mutex);
+	cxgbi_device_destroy(cdev);
+}
+EXPORT_SYMBOL_GPL(cxgbi_device_unregister);
+
+void cxgbi_device_unregister_all(unsigned int flag)
+{
+	struct cxgbi_device *cdev, *tmp;
+
+	mutex_lock(&cdev_mutex);
+	list_for_each_entry_safe(cdev, tmp, &cdev_list, list_head) {
+		if ((cdev->flags & flag) == flag) {
+			log_debug(1 << CXGBI_DBG_DEV,
+				"cdev 0x%p, p# %u,%s.\n",
+				cdev, cdev->nports, cdev->nports ?
+				 cdev->ports[0]->name : "");
+			list_del(&cdev->list_head);
+			cxgbi_device_destroy(cdev);
+		}
+	}
+	mutex_unlock(&cdev_mutex);
+}
+EXPORT_SYMBOL_GPL(cxgbi_device_unregister_all);
+
+struct cxgbi_device *cxgbi_device_find_by_lldev(void *lldev)
+{
+	struct cxgbi_device *cdev, *tmp;
+
+	mutex_lock(&cdev_mutex);
+	list_for_each_entry_safe(cdev, tmp, &cdev_list, list_head) {
+		if (cdev->lldev == lldev) {
+			mutex_unlock(&cdev_mutex);
+			return cdev;
+		}
+	}
+	mutex_unlock(&cdev_mutex);
+	log_debug(1 << CXGBI_DBG_DEV,
+		"lldev 0x%p, NO match found.\n", lldev);
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(cxgbi_device_find_by_lldev);
+
+static struct cxgbi_device *cxgbi_device_find_by_netdev(struct net_device *ndev,
+							int *port)
+{
+	struct cxgbi_device *cdev, *tmp;
+	int i;
+
+	if (ndev->priv_flags & IFF_802_1Q_VLAN)
+		ndev = vlan_dev_real_dev(ndev);
+
+	mutex_lock(&cdev_mutex);
+	list_for_each_entry_safe(cdev, tmp, &cdev_list, list_head) {
+		for (i = 0; i < cdev->nports; i++) {
+			if (ndev == cdev->ports[i]) {
+				mutex_unlock(&cdev_mutex);
+				if (port)
+					*port = i;
+				return cdev;
+			}
+		}
+	}
+	mutex_unlock(&cdev_mutex);
+	log_debug(1 << CXGBI_DBG_DEV,
+		"ndev 0x%p, %s, NO match found.\n", ndev, ndev->name);
+	return NULL;
+}
+
+struct cxgbi_hba *cxgbi_hba_find_by_netdev(struct net_device *dev,
+					struct cxgbi_device *cdev)
+{
+	int i;
+
+	if (dev->priv_flags & IFF_802_1Q_VLAN)
+		dev = vlan_dev_real_dev(dev);
+
+	for (i = 0; i < cdev->nports; i++) {
+		if (cdev->hbas[i]->ndev == dev)
+			return cdev->hbas[i];
+	}
+	log_debug(1 << CXGBI_DBG_DEV,
+		"ndev 0x%p, %s, cdev 0x%p, NO match found.\n",
+		dev, dev->name, cdev);
+	return NULL;
+}
+
+void cxgbi_hbas_remove(struct cxgbi_device *cdev)
+{
+	int i;
+	struct cxgbi_hba *chba;
+
+	log_debug(1 << CXGBI_DBG_DEV,
+		"cdev 0x%p, p#%u.\n", cdev, cdev->nports);
+
+	for (i = 0; i < cdev->nports; i++) {
+		chba = cdev->hbas[i];
+		if (chba) {
+			cdev->hbas[i] = NULL;
+			iscsi_host_remove(chba->shost);
+			pci_dev_put(cdev->pdev);
+			iscsi_host_free(chba->shost);
+		}
+	}
+}
+EXPORT_SYMBOL_GPL(cxgbi_hbas_remove);
+
+int cxgbi_hbas_add(struct cxgbi_device *cdev, unsigned int max_lun,
+		unsigned int max_id, struct scsi_host_template *sht,
+		struct scsi_transport_template *stt)
+{
+	struct cxgbi_hba *chba;
+	struct Scsi_Host *shost;
+	int i, err;
+
+	log_debug(1 << CXGBI_DBG_DEV, "cdev 0x%p, p#%u.\n", cdev, cdev->nports);
+
+	for (i = 0; i < cdev->nports; i++) {
+		shost = iscsi_host_alloc(sht, sizeof(*chba), 1);
+		if (!shost) {
+			pr_info("0x%p, p%d, %s, host alloc failed.\n",
+				cdev, i, cdev->ports[i]->name);
+			err = -ENOMEM;
+			goto err_out;
+		}
+
+		shost->transportt = stt;
+		shost->max_lun = max_lun;
+		shost->max_id = max_id;
+		shost->max_channel = 0;
+		shost->max_cmd_len = 16;
+
+		chba = iscsi_host_priv(shost);
+		chba->cdev = cdev;
+		chba->ndev = cdev->ports[i];
+		chba->shost = shost;
+
+		log_debug(1 << CXGBI_DBG_DEV,
+			"cdev 0x%p, p#%d %s: chba 0x%p.\n",
+			cdev, i, cdev->ports[i]->name, chba);
+
+		pci_dev_get(cdev->pdev);
+		err = iscsi_host_add(shost, &cdev->pdev->dev);
+		if (err) {
+			pr_info("cdev 0x%p, p#%d %s, host add failed.\n",
+				cdev, i, cdev->ports[i]->name);
+			pci_dev_put(cdev->pdev);
+			scsi_host_put(shost);
+			goto  err_out;
+		}
+
+		cdev->hbas[i] = chba;
+	}
+
+	return 0;
+
+err_out:
+	cxgbi_hbas_remove(cdev);
+	return err;
+}
+EXPORT_SYMBOL_GPL(cxgbi_hbas_add);
+
+/*
+ * iSCSI offload
+ *
+ * - source port management
+ *   To find a free source port in the port allocation map we use a very simple
+ *   rotor scheme to look for the next free port.
+ *
+ *   If a source port has been specified make sure that it doesn't collide with
+ *   our normal source port allocation map.  If it's outside the range of our
+ *   allocation/deallocation scheme just let them use it.
+ *
+ *   If the source port is outside our allocation range, the caller is
+ *   responsible for keeping track of their port usage.
+ */
+static int sock_get_port(struct cxgbi_sock *csk)
+{
+	struct cxgbi_device *cdev = csk->cdev;
+	struct cxgbi_ports_map *pmap = &cdev->pmap;
+	unsigned int start;
+	int idx;
+
+	if (!pmap->max_connect) {
+		pr_err("cdev 0x%p, p#%u %s, NO port map.\n",
+			   cdev, csk->port_id, cdev->ports[csk->port_id]->name);
+		return -EADDRNOTAVAIL;
+	}
+
+	if (csk->saddr.sin_port) {
+		pr_err("source port NON-ZERO %u.\n",
+			ntohs(csk->saddr.sin_port));
+		return -EADDRINUSE;
+	}
+
+	spin_lock_bh(&pmap->lock);
+	if (pmap->used >= pmap->max_connect) {
+		spin_unlock_bh(&pmap->lock);
+		pr_info("cdev 0x%p, p#%u %s, ALL ports used.\n",
+			cdev, csk->port_id, cdev->ports[csk->port_id]->name);
+		return -EADDRNOTAVAIL;
+	}
+
+	start = idx = pmap->next;
+	do {
+		if (++idx >= pmap->max_connect)
+			idx = 0;
+		if (!pmap->port_csk[idx]) {
+			pmap->used++;
+			csk->saddr.sin_port =
+				htons(pmap->sport_base + idx);
+			pmap->next = idx;
+			pmap->port_csk[idx] = csk;
+			spin_unlock_bh(&pmap->lock);
+			cxgbi_sock_get(csk);
+			log_debug(1 << CXGBI_DBG_SOCK,
+				"cdev 0x%p, p#%u %s, p %u, %u.\n",
+				cdev, csk->port_id,
+				cdev->ports[csk->port_id]->name,
+				pmap->sport_base + idx, pmap->next);
+			return 0;
+		}
+	} while (idx != start);
+	spin_unlock_bh(&pmap->lock);
+
+	/* should not happen */
+	pr_warn("cdev 0x%p, p#%u %s, next %u?\n",
+		cdev, csk->port_id, cdev->ports[csk->port_id]->name,
+		pmap->next);
+	return -EADDRNOTAVAIL;
+}
+
+static void sock_put_port(struct cxgbi_sock *csk)
+{
+	struct cxgbi_device *cdev = csk->cdev;
+	struct cxgbi_ports_map *pmap = &cdev->pmap;
+
+	if (csk->saddr.sin_port) {
+		int idx = ntohs(csk->saddr.sin_port) - pmap->sport_base;
+
+		csk->saddr.sin_port = 0;
+		if (idx < 0 || idx >= pmap->max_connect) {
+			pr_err("cdev 0x%p, p#%u %s, port %u OOR.\n",
+				cdev, csk->port_id,
+				cdev->ports[csk->port_id]->name,
+				ntohs(csk->saddr.sin_port));
+			return;
+		}
+
+		spin_lock_bh(&pmap->lock);
+		pmap->port_csk[idx] = NULL;
+		pmap->used--;
+		spin_unlock_bh(&pmap->lock);
+
+		log_debug(1 << CXGBI_DBG_SOCK,
+			"cdev 0x%p, p#%u %s, release %u.\n",
+			cdev, csk->port_id, cdev->ports[csk->port_id]->name,
+			pmap->sport_base + idx);
+
+		cxgbi_sock_put(csk);
+	}
+}
+
+/*
+ * iscsi tcp connection
+ */
+void cxgbi_sock_free_cpl_skbs(struct cxgbi_sock *csk)
+{
+	if (csk->cpl_close) {
+		kfree_skb(csk->cpl_close);
+		csk->cpl_close = NULL;
+	}
+	if (csk->cpl_abort_req) {
+		kfree_skb(csk->cpl_abort_req);
+		csk->cpl_abort_req = NULL;
+	}
+	if (csk->cpl_abort_rpl) {
+		kfree_skb(csk->cpl_abort_rpl);
+		csk->cpl_abort_rpl = NULL;
+	}
+}
+EXPORT_SYMBOL_GPL(cxgbi_sock_free_cpl_skbs);
+
+static struct cxgbi_sock *cxgbi_sock_create(struct cxgbi_device *cdev)
+{
+	struct cxgbi_sock *csk = kzalloc(sizeof(*csk), GFP_NOIO);
+
+	if (!csk) {
+		pr_info("alloc csk %zu failed.\n", sizeof(*csk));
+		return NULL;
+	}
+
+	if (cdev->csk_alloc_cpls(csk) < 0) {
+		pr_info("csk 0x%p, alloc cpls failed.\n", csk);
+		kfree(csk);
+		return NULL;
+	}
+
+	spin_lock_init(&csk->lock);
+	kref_init(&csk->refcnt);
+	skb_queue_head_init(&csk->receive_queue);
+	skb_queue_head_init(&csk->write_queue);
+	setup_timer(&csk->retry_timer, NULL, (unsigned long)csk);
+	rwlock_init(&csk->callback_lock);
+	csk->cdev = cdev;
+	csk->flags = 0;
+	cxgbi_sock_set_state(csk, CTP_CLOSED);
+
+	log_debug(1 << CXGBI_DBG_SOCK, "cdev 0x%p, new csk 0x%p.\n", cdev, csk);
+
+	return csk;
+}
+
+static struct rtable *find_route_ipv4(__be32 saddr, __be32 daddr,
+					__be16 sport, __be16 dport, u8 tos)
+{
+	struct rtable *rt;
+	struct flowi fl = {
+		.oif = 0,
+		.nl_u = {
+			.ip4_u = {
+				.daddr = daddr,
+				.saddr = saddr,
+				.tos = tos }
+			},
+		.proto = IPPROTO_TCP,
+		.uli_u = {
+			.ports = {
+				.sport = sport,
+				.dport = dport }
+			}
+	};
+
+	if (ip_route_output_flow(&init_net, &rt, &fl, NULL, 0))
+		return NULL;
+
+	return rt;
+}
+
+static struct cxgbi_sock *cxgbi_check_route(struct sockaddr *dst_addr)
+{
+	struct sockaddr_in *daddr = (struct sockaddr_in *)dst_addr;
+	struct dst_entry *dst;
+	struct net_device *ndev;
+	struct cxgbi_device *cdev;
+	struct rtable *rt = NULL;
+	struct cxgbi_sock *csk = NULL;
+	unsigned int mtu = 0;
+	int port = 0xFFFF;
+	int err = 0;
+
+	if (daddr->sin_family != AF_INET) {
+		pr_info("address family 0x%x NOT supported.\n",
+			daddr->sin_family);
+		err = -EAFNOSUPPORT;
+		goto err_out;
+	}
+
+	rt = find_route_ipv4(0, daddr->sin_addr.s_addr, 0, daddr->sin_port, 0);
+	if (!rt) {
+		pr_info("no route to ipv4 0x%x, port %u.\n",
+			daddr->sin_addr.s_addr, daddr->sin_port);
+		err = -ENETUNREACH;
+		goto err_out;
+	}
+	dst = &rt->dst;
+	ndev = dst->neighbour->dev;
+
+	if (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST)) {
+		pr_info("multi-cast route %pI4, port %u, dev %s.\n",
+			&daddr->sin_addr.s_addr, ntohs(daddr->sin_port),
+			ndev->name);
+		err = -ENETUNREACH;
+		goto rel_rt;
+	}
+
+	if (ndev->flags & IFF_LOOPBACK) {
+		ndev = ip_dev_find(&init_net, daddr->sin_addr.s_addr);
+		mtu = ndev->mtu;
+		pr_info("rt dev %s, loopback -> %s, mtu %u.\n",
+			dst->neighbour->dev->name, ndev->name, mtu);
+	}
+
+	if (ndev->priv_flags & IFF_802_1Q_VLAN) {
+		ndev = vlan_dev_real_dev(ndev);
+		pr_info("rt dev %s, vlan -> %s.\n",
+			dst->neighbour->dev->name, ndev->name);
+	}
+
+	cdev = cxgbi_device_find_by_netdev(ndev, &port);
+	if (!cdev) {
+		pr_info("dst %pI4, %s, NOT cxgbi device.\n",
+			&daddr->sin_addr.s_addr, ndev->name);
+		err = -ENETUNREACH;
+		goto rel_rt;
+	}
+	log_debug(1 << CXGBI_DBG_SOCK,
+		"route to %pI4 :%u, ndev p#%d,%s, cdev 0x%p.\n",
+		&daddr->sin_addr.s_addr, ntohs(daddr->sin_port),
+			   port, ndev->name, cdev);
+
+	csk = cxgbi_sock_create(cdev);
+	if (!csk) {
+		err = -ENOMEM;
+		goto rel_rt;
+	}
+	csk->cdev = cdev;
+	csk->port_id = port;
+	csk->mtu = mtu;
+	csk->dst = dst;
+	csk->daddr.sin_addr.s_addr = daddr->sin_addr.s_addr;
+	csk->daddr.sin_port = daddr->sin_port;
+	if (cdev->hbas[port]->ipv4addr)
+		csk->saddr.sin_addr.s_addr = cdev->hbas[port]->ipv4addr;
+	else
+		csk->saddr.sin_addr.s_addr = rt->rt_src;
+
+	return csk;
+
+rel_rt:
+	ip_rt_put(rt);
+	if (csk)
+		cxgbi_sock_closed(csk);
+err_out:
+	return ERR_PTR(err);
+}
+
+void cxgbi_sock_established(struct cxgbi_sock *csk, unsigned int snd_isn,
+			unsigned int opt)
+{
+	csk->write_seq = csk->snd_nxt = csk->snd_una = snd_isn;
+	dst_confirm(csk->dst);
+	smp_mb();
+	cxgbi_sock_set_state(csk, CTP_ESTABLISHED);
+}
+EXPORT_SYMBOL_GPL(cxgbi_sock_established);
+
+static void cxgbi_inform_iscsi_conn_closing(struct cxgbi_sock *csk)
+{
+	log_debug(1 << CXGBI_DBG_SOCK,
+		"csk 0x%p, state %u, flags 0x%lx, conn 0x%p.\n",
+		csk, csk->state, csk->flags, csk->user_data);
+
+	if (csk->state != CTP_ESTABLISHED) {
+		read_lock(&csk->callback_lock);
+		if (csk->user_data)
+			iscsi_conn_failure(csk->user_data,
+					ISCSI_ERR_CONN_FAILED);
+		read_unlock(&csk->callback_lock);
+	}
+}
+
+void cxgbi_sock_closed(struct cxgbi_sock *csk)
+{
+	log_debug(1 << CXGBI_DBG_SOCK, "csk 0x%p,%u,0x%lx,%u.\n",
+		csk, (csk)->state, (csk)->flags, (csk)->tid);
+	cxgbi_sock_set_flag(csk, CTPF_ACTIVE_CLOSE_NEEDED);
+	if (csk->state == CTP_ACTIVE_OPEN || csk->state == CTP_CLOSED)
+		return;
+	if (csk->saddr.sin_port)
+		sock_put_port(csk);
+	if (csk->dst)
+		dst_release(csk->dst);
+	csk->cdev->csk_release_offload_resources(csk);
+	cxgbi_sock_set_state(csk, CTP_CLOSED);
+	cxgbi_inform_iscsi_conn_closing(csk);
+	cxgbi_sock_put(csk);
+}
+EXPORT_SYMBOL_GPL(cxgbi_sock_closed);
+
+static void need_active_close(struct cxgbi_sock *csk)
+{
+	int data_lost;
+	int close_req = 0;
+
+	log_debug(1 << CXGBI_DBG_SOCK, "csk 0x%p,%u,0x%lx,%u.\n",
+		csk, (csk)->state, (csk)->flags, (csk)->tid);
+	spin_lock_bh(&csk->lock);
+	dst_confirm(csk->dst);
+	data_lost = skb_queue_len(&csk->receive_queue);
+	__skb_queue_purge(&csk->receive_queue);
+
+	if (csk->state == CTP_ACTIVE_OPEN)
+		cxgbi_sock_set_flag(csk, CTPF_ACTIVE_CLOSE_NEEDED);
+	else if (csk->state == CTP_ESTABLISHED) {
+		close_req = 1;
+		cxgbi_sock_set_state(csk, CTP_ACTIVE_CLOSE);
+	} else if (csk->state == CTP_PASSIVE_CLOSE) {
+		close_req = 1;
+		cxgbi_sock_set_state(csk, CTP_CLOSE_WAIT_2);
+	}
+
+	if (close_req) {
+		if (data_lost)
+			csk->cdev->csk_send_abort_req(csk);
+		else
+			csk->cdev->csk_send_close_req(csk);
+	}
+
+	spin_unlock_bh(&csk->lock);
+}
+
+void cxgbi_sock_fail_act_open(struct cxgbi_sock *csk, int errno)
+{
+	pr_info("csk 0x%p,%u,%lx, %pI4:%u-%pI4:%u, err %d.\n",
+			csk, csk->state, csk->flags,
+			&csk->saddr.sin_addr.s_addr, csk->saddr.sin_port,
+			&csk->daddr.sin_addr.s_addr, csk->daddr.sin_port,
+			errno);
+
+	cxgbi_sock_set_state(csk, CTP_CONNECTING);
+	csk->err = errno;
+	cxgbi_sock_closed(csk);
+}
+EXPORT_SYMBOL_GPL(cxgbi_sock_fail_act_open);
+
+void cxgbi_sock_act_open_req_arp_failure(void *handle, struct sk_buff *skb)
+{
+	struct cxgbi_sock *csk = (struct cxgbi_sock *)skb->sk;
+
+	log_debug(1 << CXGBI_DBG_SOCK, "csk 0x%p,%u,0x%lx,%u.\n",
+		csk, (csk)->state, (csk)->flags, (csk)->tid);
+	cxgbi_sock_get(csk);
+	spin_lock_bh(&csk->lock);
+	if (csk->state == CTP_ACTIVE_OPEN)
+		cxgbi_sock_fail_act_open(csk, -EHOSTUNREACH);
+	spin_unlock_bh(&csk->lock);
+	cxgbi_sock_put(csk);
+	__kfree_skb(skb);
+}
+EXPORT_SYMBOL_GPL(cxgbi_sock_act_open_req_arp_failure);
+
+void cxgbi_sock_rcv_abort_rpl(struct cxgbi_sock *csk)
+{
+	cxgbi_sock_get(csk);
+	spin_lock_bh(&csk->lock);
+	if (cxgbi_sock_flag(csk, CTPF_ABORT_RPL_PENDING)) {
+		if (!cxgbi_sock_flag(csk, CTPF_ABORT_RPL_RCVD))
+			cxgbi_sock_set_flag(csk, CTPF_ABORT_RPL_RCVD);
+		else {
+			cxgbi_sock_clear_flag(csk, CTPF_ABORT_RPL_RCVD);
+			cxgbi_sock_clear_flag(csk, CTPF_ABORT_RPL_PENDING);
+			if (cxgbi_sock_flag(csk, CTPF_ABORT_REQ_RCVD))
+				pr_err("csk 0x%p,%u,0x%lx,%u,ABT_RPL_RSS.\n",
+					csk, csk->state, csk->flags, csk->tid);
+			cxgbi_sock_closed(csk);
+		}
+	}
+	spin_unlock_bh(&csk->lock);
+	cxgbi_sock_put(csk);
+}
+EXPORT_SYMBOL_GPL(cxgbi_sock_rcv_abort_rpl);
+
+void cxgbi_sock_rcv_peer_close(struct cxgbi_sock *csk)
+{
+	log_debug(1 << CXGBI_DBG_SOCK, "csk 0x%p,%u,0x%lx,%u.\n",
+		csk, (csk)->state, (csk)->flags, (csk)->tid);
+	cxgbi_sock_get(csk);
+	spin_lock_bh(&csk->lock);
+
+	if (cxgbi_sock_flag(csk, CTPF_ABORT_RPL_PENDING))
+		goto done;
+
+	switch (csk->state) {
+	case CTP_ESTABLISHED:
+		cxgbi_sock_set_state(csk, CTP_PASSIVE_CLOSE);
+		break;
+	case CTP_ACTIVE_CLOSE:
+		cxgbi_sock_set_state(csk, CTP_CLOSE_WAIT_2);
+		break;
+	case CTP_CLOSE_WAIT_1:
+		cxgbi_sock_closed(csk);
+		break;
+	case CTP_ABORTING:
+		break;
+	default:
+		pr_err("csk 0x%p,%u,0x%lx,%u, bad state.\n",
+			csk, csk->state, csk->flags, csk->tid);
+	}
+	cxgbi_inform_iscsi_conn_closing(csk);
+done:
+	spin_unlock_bh(&csk->lock);
+	cxgbi_sock_put(csk);
+}
+EXPORT_SYMBOL_GPL(cxgbi_sock_rcv_peer_close);
+
+void cxgbi_sock_rcv_close_conn_rpl(struct cxgbi_sock *csk, u32 snd_nxt)
+{
+	log_debug(1 << CXGBI_DBG_SOCK, "csk 0x%p,%u,0x%lx,%u.\n",
+		csk, (csk)->state, (csk)->flags, (csk)->tid);
+	cxgbi_sock_get(csk);
+	spin_lock_bh(&csk->lock);
+
+	csk->snd_una = snd_nxt - 1;
+	if (cxgbi_sock_flag(csk, CTPF_ABORT_RPL_PENDING))
+		goto done;
+
+	switch (csk->state) {
+	case CTP_ACTIVE_CLOSE:
+		cxgbi_sock_set_state(csk, CTP_CLOSE_WAIT_1);
+		break;
+	case CTP_CLOSE_WAIT_1:
+	case CTP_CLOSE_WAIT_2:
+		cxgbi_sock_closed(csk);
+		break;
+	case CTP_ABORTING:
+		break;
+	default:
+		pr_err("csk 0x%p,%u,0x%lx,%u, bad state.\n",
+			csk, csk->state, csk->flags, csk->tid);
+	}
+done:
+	spin_unlock_bh(&csk->lock);
+	cxgbi_sock_put(csk);
+}
+EXPORT_SYMBOL_GPL(cxgbi_sock_rcv_close_conn_rpl);
+
+void cxgbi_sock_rcv_wr_ack(struct cxgbi_sock *csk, unsigned int credits,
+			   unsigned int snd_una, int seq_chk)
+{
+	log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK,
+			"csk 0x%p,%u,0x%lx,%u, cr %u,%u+%u, snd_una %u,%d.\n",
+			csk, csk->state, csk->flags, csk->tid, credits,
+			csk->wr_cred, csk->wr_una_cred, snd_una, seq_chk);
+
+	spin_lock_bh(&csk->lock);
+
+	csk->wr_cred += credits;
+	if (csk->wr_una_cred > csk->wr_max_cred - csk->wr_cred)
+		csk->wr_una_cred = csk->wr_max_cred - csk->wr_cred;
+
+	while (credits) {
+		struct sk_buff *p = cxgbi_sock_peek_wr(csk);
+
+		if (unlikely(!p)) {
+			pr_err("csk 0x%p,%u,0x%lx,%u, cr %u,%u+%u, empty.\n",
+				csk, csk->state, csk->flags, csk->tid, credits,
+				csk->wr_cred, csk->wr_una_cred);
+			break;
+		}
+
+		if (unlikely(credits < p->csum)) {
+			pr_warn("csk 0x%p,%u,0x%lx,%u, cr %u,%u+%u, < %u.\n",
+				csk, csk->state, csk->flags, csk->tid,
+				credits, csk->wr_cred, csk->wr_una_cred,
+				p->csum);
+			p->csum -= credits;
+			break;
+		} else {
+			cxgbi_sock_dequeue_wr(csk);
+			credits -= p->csum;
+			kfree_skb(p);
+		}
+	}
+
+	cxgbi_sock_check_wr_invariants(csk);
+
+	if (seq_chk) {
+		if (unlikely(before(snd_una, csk->snd_una))) {
+			pr_warn("csk 0x%p,%u,0x%lx,%u, snd_una %u/%u.",
+				csk, csk->state, csk->flags, csk->tid, snd_una,
+				csk->snd_una);
+			goto done;
+		}
+
+		if (csk->snd_una != snd_una) {
+			csk->snd_una = snd_una;
+			dst_confirm(csk->dst);
+		}
+	}
+
+	if (skb_queue_len(&csk->write_queue)) {
+		if (csk->cdev->csk_push_tx_frames(csk, 0))
+			cxgbi_conn_tx_open(csk);
+	} else
+		cxgbi_conn_tx_open(csk);
+done:
+	spin_unlock_bh(&csk->lock);
+}
+EXPORT_SYMBOL_GPL(cxgbi_sock_rcv_wr_ack);
+
+static unsigned int cxgbi_sock_find_best_mtu(struct cxgbi_sock *csk,
+					     unsigned short mtu)
+{
+	int i = 0;
+
+	while (i < csk->cdev->nmtus - 1 && csk->cdev->mtus[i + 1] <= mtu)
+		++i;
+
+	return i;
+}
+
+unsigned int cxgbi_sock_select_mss(struct cxgbi_sock *csk, unsigned int pmtu)
+{
+	unsigned int idx;
+	struct dst_entry *dst = csk->dst;
+
+	csk->advmss = dst_metric(dst, RTAX_ADVMSS);
+
+	if (csk->advmss > pmtu - 40)
+		csk->advmss = pmtu - 40;
+	if (csk->advmss < csk->cdev->mtus[0] - 40)
+		csk->advmss = csk->cdev->mtus[0] - 40;
+	idx = cxgbi_sock_find_best_mtu(csk, csk->advmss + 40);
+
+	return idx;
+}
+EXPORT_SYMBOL_GPL(cxgbi_sock_select_mss);
+
+void cxgbi_sock_skb_entail(struct cxgbi_sock *csk, struct sk_buff *skb)
+{
+	cxgbi_skcb_tcp_seq(skb) = csk->write_seq;
+	__skb_queue_tail(&csk->write_queue, skb);
+}
+EXPORT_SYMBOL_GPL(cxgbi_sock_skb_entail);
+
+void cxgbi_sock_purge_wr_queue(struct cxgbi_sock *csk)
+{
+	struct sk_buff *skb;
+
+	while ((skb = cxgbi_sock_dequeue_wr(csk)) != NULL)
+		kfree_skb(skb);
+}
+EXPORT_SYMBOL_GPL(cxgbi_sock_purge_wr_queue);
+
+void cxgbi_sock_check_wr_invariants(const struct cxgbi_sock *csk)
+{
+	int pending = cxgbi_sock_count_pending_wrs(csk);
+
+	if (unlikely(csk->wr_cred + pending != csk->wr_max_cred))
+		pr_err("csk 0x%p, tid %u, credit %u + %u != %u.\n",
+			csk, csk->tid, csk->wr_cred, pending, csk->wr_max_cred);
+}
+EXPORT_SYMBOL_GPL(cxgbi_sock_check_wr_invariants);
+
+static int cxgbi_sock_send_pdus(struct cxgbi_sock *csk, struct sk_buff *skb)
+{
+	struct cxgbi_device *cdev = csk->cdev;
+	struct sk_buff *next;
+	int err, copied = 0;
+
+	spin_lock_bh(&csk->lock);
+
+	if (csk->state != CTP_ESTABLISHED) {
+		log_debug(1 << CXGBI_DBG_PDU_TX,
+			"csk 0x%p,%u,0x%lx,%u, EAGAIN.\n",
+			csk, csk->state, csk->flags, csk->tid);
+		err = -EAGAIN;
+		goto out_err;
+	}
+
+	if (csk->err) {
+		log_debug(1 << CXGBI_DBG_PDU_TX,
+			"csk 0x%p,%u,0x%lx,%u, EPIPE %d.\n",
+			csk, csk->state, csk->flags, csk->tid, csk->err);
+		err = -EPIPE;
+		goto out_err;
+	}
+
+	if (csk->write_seq - csk->snd_una >= cdev->snd_win) {
+		log_debug(1 << CXGBI_DBG_PDU_TX,
+			"csk 0x%p,%u,0x%lx,%u, FULL %u-%u >= %u.\n",
+			csk, csk->state, csk->flags, csk->tid, csk->write_seq,
+			csk->snd_una, cdev->snd_win);
+		err = -ENOBUFS;
+		goto out_err;
+	}
+
+	while (skb) {
+		int frags = skb_shinfo(skb)->nr_frags +
+				(skb->len != skb->data_len);
+
+		if (unlikely(skb_headroom(skb) < cdev->skb_tx_rsvd)) {
+			pr_err("csk 0x%p, skb head %u < %u.\n",
+				csk, skb_headroom(skb), cdev->skb_tx_rsvd);
+			err = -EINVAL;
+			goto out_err;
+		}
+
+		if (frags >= SKB_WR_LIST_SIZE) {
+			pr_err("csk 0x%p, frags %d, %u,%u >%u.\n",
+				csk, skb_shinfo(skb)->nr_frags, skb->len,
+				skb->data_len, (uint)(SKB_WR_LIST_SIZE));
+			err = -EINVAL;
+			goto out_err;
+		}
+
+		next = skb->next;
+		skb->next = NULL;
+		cxgbi_skcb_set_flag(skb, SKCBF_TX_NEED_HDR);
+		cxgbi_sock_skb_entail(csk, skb);
+		copied += skb->len;
+		csk->write_seq += skb->len +
+				cxgbi_ulp_extra_len(cxgbi_skcb_ulp_mode(skb));
+		skb = next;
+	}
+done:
+	if (likely(skb_queue_len(&csk->write_queue)))
+		cdev->csk_push_tx_frames(csk, 1);
+	spin_unlock_bh(&csk->lock);
+	return copied;
+
+out_err:
+	if (copied == 0 && err == -EPIPE)
+		copied = csk->err ? csk->err : -EPIPE;
+	else
+		copied = 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)
+{
+	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);
+
+	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;
+}
+
+static int ddp_find_page_index(unsigned long pgsz)
+{
+	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;
+}
+
+static void ddp_setup_host_page_size(void)
+{
+	if (page_idx == DDP_PGIDX_MAX) {
+		page_idx = ddp_find_page_index(PAGE_SIZE);
+
+		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;
+			}
+			page_idx = ddp_find_page_index(PAGE_SIZE);
+		}
+		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;
+	}
+
+	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;
+		}
+		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);
+}
+
+static inline void ddp_gl_unmap(struct pci_dev *pdev,
+					struct cxgbi_gather_list *gl)
+{
+	int i;
+
+	for (i = 0; i < gl->nelem; i++)
+		dma_unmap_page(&pdev->dev, gl->phys_addr[i], PAGE_SIZE,
+				PCI_DMA_FROMDEVICE);
+}
+
+static inline int ddp_gl_map(struct pci_dev *pdev,
+				    struct cxgbi_gather_list *gl)
+{
+	int i;
+
+	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;
+
+		gl->nelem = i;
+		ddp_gl_unmap(pdev, gl);
+		gl->nelem = nelem;
+	}
+	return -EINVAL;
+}
+
+static void ddp_release_gl(struct cxgbi_gather_list *gl,
+				  struct pci_dev *pdev)
+{
+	ddp_gl_unmap(pdev, gl);
+	kfree(gl);
+}
+
+static struct cxgbi_gather_list *ddp_make_gl(unsigned int xferlen,
+						    struct scatterlist *sgl,
+						    unsigned int sgcnt,
+						    struct pci_dev *pdev,
+						    gfp_t gfp)
+{
+	struct cxgbi_gather_list *gl;
+	struct scatterlist *sg = sgl;