cxgbit: add files for cxgbit.ko

cxgbit.h - This file contains data structure
definitions for cxgbit.ko.

cxgbit_lro.h - This file contains data structure
definitions for LRO support.

cxgbit_main.c - This file contains code for
registering with iscsi target transport and
cxgb4 driver.

cxgbit_cm.c - This file contains code for
connection management.

cxgbit_target.c - This file contains code
for processing iSCSI PDU.

cxgbit_ddp.c - This file contains code for
Direct Data Placement.

(added check for NULL sg in cxgbit_set_one_ppod)
Reported-by: NDan Carpenter <dan.carpenter@oracle.com>

(add Kconfig and Makefile v2: added dependency on INET)
Reported-by: NArnd Bergmann <arnd@arndb.de>
Signed-off-by: NVarun Prakash <varun@chelsio.com>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

drivers/target/iscsi/Kconfig

@@ -7,3 +7,5 @@ config ISCSI_TARGET
 	help
 	Say M here to enable the ConfigFS enabled Linux-iSCSI.org iSCSI
 	Target Mode Stack.
+
+source	"drivers/target/iscsi/cxgbit/Kconfig"

drivers/target/iscsi/Makefile

@@ -18,3 +18,4 @@ iscsi_target_mod-y +=		iscsi_target_parameters.o \
 				iscsi_target_transport.o
 
 obj-$(CONFIG_ISCSI_TARGET)	+= iscsi_target_mod.o
+obj-$(CONFIG_ISCSI_TARGET_CXGB4) += cxgbit/

drivers/target/iscsi/cxgbit/Kconfig

+config ISCSI_TARGET_CXGB4
+	tristate "Chelsio iSCSI target offload driver"
+	depends on ISCSI_TARGET && CHELSIO_T4 && INET
+	select CHELSIO_T4_UWIRE
+	---help---
+	To compile this driver as module, choose M here: the module
+	will be called cxgbit.

drivers/target/iscsi/cxgbit/Makefile

+ccflags-y := -Idrivers/net/ethernet/chelsio/cxgb4
+ccflags-y += -Idrivers/target/iscsi
+
+obj-$(CONFIG_ISCSI_TARGET_CXGB4)  += cxgbit.o
+
+cxgbit-y  := cxgbit_main.o cxgbit_cm.o cxgbit_target.o cxgbit_ddp.o

drivers/target/iscsi/cxgbit/cxgbit.h

+/*
+ * Copyright (c) 2016 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 version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __CXGBIT_H__
+#define __CXGBIT_H__
+
+#include <linux/mutex.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/idr.h>
+#include <linux/completion.h>
+#include <linux/netdevice.h>
+#include <linux/sched.h>
+#include <linux/pci.h>
+#include <linux/dma-mapping.h>
+#include <linux/inet.h>
+#include <linux/wait.h>
+#include <linux/kref.h>
+#include <linux/timer.h>
+#include <linux/io.h>
+
+#include <asm/byteorder.h>
+
+#include <net/net_namespace.h>
+
+#include <target/iscsi/iscsi_transport.h>
+#include <iscsi_target_parameters.h>
+#include <iscsi_target_login.h>
+
+#include "t4_regs.h"
+#include "t4_msg.h"
+#include "cxgb4.h"
+#include "cxgb4_uld.h"
+#include "l2t.h"
+#include "cxgb4_ppm.h"
+#include "cxgbit_lro.h"
+
+extern struct mutex cdev_list_lock;
+extern struct list_head cdev_list_head;
+struct cxgbit_np;
+
+struct cxgbit_sock;
+
+struct cxgbit_cmd {
+	struct scatterlist sg;
+	struct cxgbi_task_tag_info ttinfo;
+	bool setup_ddp;
+	bool release;
+};
+
+#define CXGBIT_MAX_ISO_PAYLOAD	\
+	min_t(u32, MAX_SKB_FRAGS * PAGE_SIZE, 65535)
+
+struct cxgbit_iso_info {
+	u8 flags;
+	u32 mpdu;
+	u32 len;
+	u32 burst_len;
+};
+
+enum cxgbit_skcb_flags {
+	SKCBF_TX_NEED_HDR	= (1 << 0), /* packet needs a header */
+	SKCBF_TX_FLAG_COMPL	= (1 << 1), /* wr completion flag */
+	SKCBF_TX_ISO		= (1 << 2), /* iso cpl in tx skb */
+	SKCBF_RX_LRO		= (1 << 3), /* lro skb */
+};
+
+struct cxgbit_skb_rx_cb {
+	u8 opcode;
+	void *pdu_cb;
+	void (*backlog_fn)(struct cxgbit_sock *, struct sk_buff *);
+};
+
+struct cxgbit_skb_tx_cb {
+	u8 submode;
+	u32 extra_len;
+};
+
+union cxgbit_skb_cb {
+	struct {
+		u8 flags;
+		union {
+			struct cxgbit_skb_tx_cb tx;
+			struct cxgbit_skb_rx_cb rx;
+		};
+	};
+
+	struct {
+		/* This member must be first. */
+		struct l2t_skb_cb l2t;
+		struct sk_buff *wr_next;
+	};
+};
+
+#define CXGBIT_SKB_CB(skb)	((union cxgbit_skb_cb *)&((skb)->cb[0]))
+#define cxgbit_skcb_flags(skb)		(CXGBIT_SKB_CB(skb)->flags)
+#define cxgbit_skcb_submode(skb)	(CXGBIT_SKB_CB(skb)->tx.submode)
+#define cxgbit_skcb_tx_wr_next(skb)	(CXGBIT_SKB_CB(skb)->wr_next)
+#define cxgbit_skcb_tx_extralen(skb)	(CXGBIT_SKB_CB(skb)->tx.extra_len)
+#define cxgbit_skcb_rx_opcode(skb)	(CXGBIT_SKB_CB(skb)->rx.opcode)
+#define cxgbit_skcb_rx_backlog_fn(skb)	(CXGBIT_SKB_CB(skb)->rx.backlog_fn)
+#define cxgbit_rx_pdu_cb(skb)		(CXGBIT_SKB_CB(skb)->rx.pdu_cb)
+
+static inline void *cplhdr(struct sk_buff *skb)
+{
+	return skb->data;
+}
+
+enum cxgbit_cdev_flags {
+	CDEV_STATE_UP = 0,
+	CDEV_ISO_ENABLE,
+	CDEV_DDP_ENABLE,
+};
+
+#define NP_INFO_HASH_SIZE 32
+
+struct np_info {
+	struct np_info *next;
+	struct cxgbit_np *cnp;
+	unsigned int stid;
+};
+
+struct cxgbit_list_head {
+	struct list_head list;
+	/* device lock */
+	spinlock_t lock;
+};
+
+struct cxgbit_device {
+	struct list_head list;
+	struct cxgb4_lld_info lldi;
+	struct np_info *np_hash_tab[NP_INFO_HASH_SIZE];
+	/* np lock */
+	spinlock_t np_lock;
+	u8 selectq[MAX_NPORTS][2];
+	struct cxgbit_list_head cskq;
+	u32 mdsl;
+	struct kref kref;
+	unsigned long flags;
+};
+
+struct cxgbit_wr_wait {
+	struct completion completion;
+	int ret;
+};
+
+enum cxgbit_csk_state {
+	CSK_STATE_IDLE = 0,
+	CSK_STATE_LISTEN,
+	CSK_STATE_CONNECTING,
+	CSK_STATE_ESTABLISHED,
+	CSK_STATE_ABORTING,
+	CSK_STATE_CLOSING,
+	CSK_STATE_MORIBUND,
+	CSK_STATE_DEAD,
+};
+
+enum cxgbit_csk_flags {
+	CSK_TX_DATA_SENT = 0,
+	CSK_LOGIN_PDU_DONE,
+	CSK_LOGIN_DONE,
+	CSK_DDP_ENABLE,
+};
+
+struct cxgbit_sock_common {
+	struct cxgbit_device *cdev;
+	struct sockaddr_storage local_addr;
+	struct sockaddr_storage remote_addr;
+	struct cxgbit_wr_wait wr_wait;
+	enum cxgbit_csk_state state;
+	unsigned long flags;
+};
+
+struct cxgbit_np {
+	struct cxgbit_sock_common com;
+	wait_queue_head_t accept_wait;
+	struct iscsi_np *np;
+	struct completion accept_comp;
+	struct list_head np_accept_list;
+	/* np accept lock */
+	spinlock_t np_accept_lock;
+	struct kref kref;
+	unsigned int stid;
+};
+
+struct cxgbit_sock {
+	struct cxgbit_sock_common com;
+	struct cxgbit_np *cnp;
+	struct iscsi_conn *conn;
+	struct l2t_entry *l2t;
+	struct dst_entry *dst;
+	struct list_head list;
+	struct sk_buff_head rxq;
+	struct sk_buff_head txq;
+	struct sk_buff_head ppodq;
+	struct sk_buff_head backlogq;
+	struct sk_buff_head skbq;
+	struct sk_buff *wr_pending_head;
+	struct sk_buff *wr_pending_tail;
+	struct sk_buff *skb;
+	struct sk_buff *lro_skb;
+	struct sk_buff *lro_hskb;
+	struct list_head accept_node;
+	/* socket lock */
+	spinlock_t lock;
+	wait_queue_head_t waitq;
+	wait_queue_head_t ack_waitq;
+	bool lock_owner;
+	struct kref kref;
+	u32 max_iso_npdu;
+	u32 wr_cred;
+	u32 wr_una_cred;
+	u32 wr_max_cred;
+	u32 snd_una;
+	u32 tid;
+	u32 snd_nxt;
+	u32 rcv_nxt;
+	u32 smac_idx;
+	u32 tx_chan;
+	u32 mtu;
+	u32 write_seq;
+	u32 rx_credits;
+	u32 snd_win;
+	u32 rcv_win;
+	u16 mss;
+	u16 emss;
+	u16 plen;
+	u16 rss_qid;
+	u16 txq_idx;
+	u16 ctrlq_idx;
+	u8 tos;
+	u8 port_id;
+#define CXGBIT_SUBMODE_HCRC 0x1
+#define CXGBIT_SUBMODE_DCRC 0x2
+	u8 submode;
+#ifdef CONFIG_CHELSIO_T4_DCB
+	u8 dcb_priority;
+#endif
+	u8 snd_wscale;
+};
+
+void _cxgbit_free_cdev(struct kref *kref);
+void _cxgbit_free_csk(struct kref *kref);
+void _cxgbit_free_cnp(struct kref *kref);
+
+static inline void cxgbit_get_cdev(struct cxgbit_device *cdev)
+{
+	kref_get(&cdev->kref);
+}
+
+static inline void cxgbit_put_cdev(struct cxgbit_device *cdev)
+{
+	kref_put(&cdev->kref, _cxgbit_free_cdev);
+}
+
+static inline void cxgbit_get_csk(struct cxgbit_sock *csk)
+{
+	kref_get(&csk->kref);
+}
+
+static inline void cxgbit_put_csk(struct cxgbit_sock *csk)
+{
+	kref_put(&csk->kref, _cxgbit_free_csk);
+}
+
+static inline void cxgbit_get_cnp(struct cxgbit_np *cnp)
+{
+	kref_get(&cnp->kref);
+}
+
+static inline void cxgbit_put_cnp(struct cxgbit_np *cnp)
+{
+	kref_put(&cnp->kref, _cxgbit_free_cnp);
+}
+
+static inline void cxgbit_sock_reset_wr_list(struct cxgbit_sock *csk)
+{
+	csk->wr_pending_tail = NULL;
+	csk->wr_pending_head = NULL;
+}
+
+static inline struct sk_buff *cxgbit_sock_peek_wr(const struct cxgbit_sock *csk)
+{
+	return csk->wr_pending_head;
+}
+
+static inline void
+cxgbit_sock_enqueue_wr(struct cxgbit_sock *csk, struct sk_buff *skb)
+{
+	cxgbit_skcb_tx_wr_next(skb) = NULL;
+
+	skb_get(skb);
+
+	if (!csk->wr_pending_head)
+		csk->wr_pending_head = skb;
+	else
+		cxgbit_skcb_tx_wr_next(csk->wr_pending_tail) = skb;
+	csk->wr_pending_tail = skb;
+}
+
+static inline struct sk_buff *cxgbit_sock_dequeue_wr(struct cxgbit_sock *csk)
+{
+	struct sk_buff *skb = csk->wr_pending_head;
+
+	if (likely(skb)) {
+		csk->wr_pending_head = cxgbit_skcb_tx_wr_next(skb);
+		cxgbit_skcb_tx_wr_next(skb) = NULL;
+	}
+	return skb;
+}
+
+typedef void (*cxgbit_cplhandler_func)(struct cxgbit_device *,
+				       struct sk_buff *);
+
+int cxgbit_setup_np(struct iscsi_np *, struct sockaddr_storage *);
+int cxgbit_setup_conn_digest(struct cxgbit_sock *);
+int cxgbit_accept_np(struct iscsi_np *, struct iscsi_conn *);
+void cxgbit_free_np(struct iscsi_np *);
+void cxgbit_free_conn(struct iscsi_conn *);
+extern cxgbit_cplhandler_func cxgbit_cplhandlers[NUM_CPL_CMDS];
+int cxgbit_get_login_rx(struct iscsi_conn *, struct iscsi_login *);
+int cxgbit_rx_data_ack(struct cxgbit_sock *);
+int cxgbit_l2t_send(struct cxgbit_device *, struct sk_buff *,
+		    struct l2t_entry *);
+void cxgbit_push_tx_frames(struct cxgbit_sock *);
+int cxgbit_put_login_tx(struct iscsi_conn *, struct iscsi_login *, u32);
+int cxgbit_xmit_pdu(struct iscsi_conn *, struct iscsi_cmd *,
+		    struct iscsi_datain_req *, const void *, u32);
+void cxgbit_get_r2t_ttt(struct iscsi_conn *, struct iscsi_cmd *,
+			struct iscsi_r2t *);
+u32 cxgbit_send_tx_flowc_wr(struct cxgbit_sock *);
+int cxgbit_ofld_send(struct cxgbit_device *, struct sk_buff *);
+void cxgbit_get_rx_pdu(struct iscsi_conn *);
+int cxgbit_validate_params(struct iscsi_conn *);
+struct cxgbit_device *cxgbit_find_device(struct net_device *, u8 *);
+
+/* DDP */
+int cxgbit_ddp_init(struct cxgbit_device *);
+int cxgbit_setup_conn_pgidx(struct cxgbit_sock *, u32);
+int cxgbit_reserve_ttt(struct cxgbit_sock *, struct iscsi_cmd *);
+void cxgbit_release_cmd(struct iscsi_conn *, struct iscsi_cmd *);
+
+static inline
+struct cxgbi_ppm *cdev2ppm(struct cxgbit_device *cdev)
+{
+	return (struct cxgbi_ppm *)(*cdev->lldi.iscsi_ppm);
+}
+#endif /* __CXGBIT_H__ */

drivers/target/iscsi/cxgbit/cxgbit_ddp.c

+/*
+ * Copyright (c) 2016 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 version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "cxgbit.h"
+
+static void
+cxgbit_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;
+
+	memcpy(ppod, &ttinfo->hdr, sizeof(struct cxgbi_pagepod_hdr));
+
+	if (sg) {
+		addr = sg_dma_address(sg);
+		len = sg_dma_len(sg);
+	}
+
+	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);
+				}
+			}
+		} else {
+			ppod->addr[i] = 0ULL;
+		}
+	}
+
+	/*
+	 * 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;
+	}
+
+	if (offset == len) {
+		offset = 0;
+		if (sg) {
+			sg = sg_next(sg);
+			if (sg)
+				addr = sg_dma_address(sg);
+		}
+	}
+	ppod->addr[i] = sg ? cpu_to_be64(addr + offset) : 0ULL;
+}
+
+static struct sk_buff *
+cxgbit_ppod_init_idata(struct cxgbit_device *cdev, struct cxgbi_ppm *ppm,
+		       unsigned int idx, unsigned int npods, unsigned int tid)
+{
+	struct ulp_mem_io *req;
+	struct ulptx_idata *idata;
+	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);
+	struct sk_buff *skb;
+
+	skb  = alloc_skb(wr_len, GFP_KERNEL);
+	if (!skb)
+		return NULL;
+
+	req = (struct ulp_mem_io *)__skb_put(skb, wr_len);
+	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(0) |
+		T5_ULP_MEMIO_IMM_V(1));
+	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));
+
+	idata = (struct ulptx_idata *)(req + 1);
+	idata->cmd_more = htonl(ULPTX_CMD_V(ULP_TX_SC_IMM));
+	idata->len = htonl(dlen);
+
+	return skb;
+}
+
+static int
+cxgbit_ppod_write_idata(struct cxgbi_ppm *ppm, struct cxgbit_sock *csk,
+			struct cxgbi_task_tag_info *ttinfo, unsigned int idx,
+			unsigned int npods, struct scatterlist **sg_pp,
+			unsigned int *sg_off)
+{
+	struct cxgbit_device *cdev = csk->com.cdev;
+	struct sk_buff *skb;
+	struct ulp_mem_io *req;
+	struct ulptx_idata *idata;
+	struct cxgbi_pagepod *ppod;
+	unsigned int i;
+
+	skb = cxgbit_ppod_init_idata(cdev, ppm, idx, npods, csk->tid);
+	if (!skb)
+		return -ENOMEM;
+
+	req = (struct ulp_mem_io *)skb->data;
+	idata = (struct ulptx_idata *)(req + 1);
+	ppod = (struct cxgbi_pagepod *)(idata + 1);
+
+	for (i = 0; i < npods; i++, ppod++)
+		cxgbit_set_one_ppod(ppod, ttinfo, sg_pp, sg_off);
+
+	__skb_queue_tail(&csk->ppodq, skb);
+
+	return 0;
+}
+
+static int
+cxgbit_ddp_set_map(struct cxgbi_ppm *ppm, struct cxgbit_sock *csk,
+		   struct cxgbi_task_tag_info *ttinfo)
+{
+	unsigned int pidx = ttinfo->idx;
+	unsigned int npods = ttinfo->npods;
+	unsigned int i, cnt;
+	struct scatterlist *sg = ttinfo->sgl;
+	unsigned int offset = 0;
+	int ret = 0;
+
+	for (i = 0; i < npods; i += cnt, pidx += cnt) {
+		cnt = npods - i;
+
+		if (cnt > ULPMEM_IDATA_MAX_NPPODS)
+			cnt = ULPMEM_IDATA_MAX_NPPODS;
+
+		ret = cxgbit_ppod_write_idata(ppm, csk, ttinfo, pidx, cnt,
+					      &sg, &offset);
+		if (ret < 0)
+			break;
+	}
+
+	return ret;
+}
+
+static int cxgbit_ddp_sgl_check(struct scatterlist *sg,
+				unsigned int nents)
+{
+	unsigned int last_sgidx = nents - 1;
+	unsigned int i;
+
+	for (i = 0; i < nents; i++, sg = sg_next(sg)) {
+		unsigned int len = sg->length + sg->offset;
+
+		if ((sg->offset & 0x3) || (i && sg->offset) ||
+		    ((i != last_sgidx) && (len != PAGE_SIZE))) {
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static int
+cxgbit_ddp_reserve(struct cxgbit_sock *csk, struct cxgbi_task_tag_info *ttinfo,
+		   unsigned int xferlen)
+{
+	struct cxgbit_device *cdev = csk->com.cdev;
+	struct cxgbi_ppm *ppm = cdev2ppm(cdev);
+	struct scatterlist *sgl = ttinfo->sgl;
+	unsigned int sgcnt = ttinfo->nents;
+	unsigned int sg_offset = sgl->offset;
+	int ret;
+
+	if ((xferlen < DDP_THRESHOLD) || (!sgcnt)) {
+		pr_debug("ppm 0x%p, pgidx %u, xfer %u, sgcnt %u, NO ddp.\n",
+			 ppm, ppm->tformat.pgsz_idx_dflt,
+			 xferlen, ttinfo->nents);
+		return -EINVAL;
+	}
+
+	if (cxgbit_ddp_sgl_check(sgl, sgcnt) < 0)
+		return -EINVAL;
+
+	ttinfo->nr_pages = (xferlen + sgl->offset +
+			    (1 << PAGE_SHIFT) - 1) >> PAGE_SHIFT;
+
+	/*
+	 * the ddp tag will be used for the ttt in the outgoing r2t pdu
+	 */
+	ret = cxgbi_ppm_ppods_reserve(ppm, ttinfo->nr_pages, 0, &ttinfo->idx,
+				      &ttinfo->tag, 0);
+	if (ret < 0)
+		return ret;
+	ttinfo->npods = ret;
+
+	sgl->offset = 0;
+	ret = dma_map_sg(&ppm->pdev->dev, sgl, sgcnt, DMA_FROM_DEVICE);
+	sgl->offset = sg_offset;
+	if (!ret) {
+		pr_info("%s: 0x%x, xfer %u, sgl %u dma mapping err.\n",
+			__func__, 0, xferlen, sgcnt);
+		goto rel_ppods;
+	}
+
+	cxgbi_ppm_make_ppod_hdr(ppm, ttinfo->tag, csk->tid, sgl->offset,
+				xferlen, &ttinfo->hdr);
+
+	ret = cxgbit_ddp_set_map(ppm, csk, ttinfo);
+	if (ret < 0) {
+		__skb_queue_purge(&csk->ppodq);
+		dma_unmap_sg(&ppm->pdev->dev, sgl, sgcnt, DMA_FROM_DEVICE);
+		goto rel_ppods;
+	}
+
+	return 0;
+
+rel_ppods:
+	cxgbi_ppm_ppod_release(ppm, ttinfo->idx);
+	return -EINVAL;
+}
+
+void
+cxgbit_get_r2t_ttt(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
+		   struct iscsi_r2t *r2t)
+{
+	struct cxgbit_sock *csk = conn->context;
+	struct cxgbit_device *cdev = csk->com.cdev;
+	struct cxgbit_cmd *ccmd = iscsit_priv_cmd(cmd);
+	struct cxgbi_task_tag_info *ttinfo = &ccmd->ttinfo;
+	int ret = -EINVAL;
+
+	if ((!ccmd->setup_ddp) ||
+	    (!test_bit(CSK_DDP_ENABLE, &csk->com.flags)))
+		goto out;
+
+	ccmd->setup_ddp = false;
+
+	ttinfo->sgl = cmd->se_cmd.t_data_sg;
+	ttinfo->nents = cmd->se_cmd.t_data_nents;
+
+	ret = cxgbit_ddp_reserve(csk, ttinfo, cmd->se_cmd.data_length);
+	if (ret < 0) {
+		pr_info("csk 0x%p, cmd 0x%p, xfer len %u, sgcnt %u no ddp.\n",
+			csk, cmd, cmd->se_cmd.data_length, ttinfo->nents);
+
+		ttinfo->sgl = NULL;
+		ttinfo->nents = 0;
+	} else {
+		ccmd->release = true;
+	}
+out:
+	pr_debug("cdev 0x%p, cmd 0x%p, tag 0x%x\n", cdev, cmd, ttinfo->tag);
+	r2t->targ_xfer_tag = ttinfo->tag;
+}
+
+void cxgbit_release_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd)
+{
+	struct cxgbit_cmd *ccmd = iscsit_priv_cmd(cmd);
+
+	if (ccmd->release) {
+		struct cxgbi_task_tag_info *ttinfo = &ccmd->ttinfo;
+
+		if (ttinfo->sgl) {
+			struct cxgbit_sock *csk = conn->context;
+			struct cxgbit_device *cdev = csk->com.cdev;
+			struct cxgbi_ppm *ppm = cdev2ppm(cdev);
+
+			cxgbi_ppm_ppod_release(ppm, ttinfo->idx);
+
+			dma_unmap_sg(&ppm->pdev->dev, ttinfo->sgl,
+				     ttinfo->nents, DMA_FROM_DEVICE);
+		} else {
+			put_page(sg_page(&ccmd->sg));
+		}
+
+		ccmd->release = false;
+	}
+}
+
+int cxgbit_ddp_init(struct cxgbit_device *cdev)
+{
+	struct cxgb4_lld_info *lldi = &cdev->lldi;
+	struct net_device *ndev = cdev->lldi.ports[0];
+	struct cxgbi_tag_format tformat;
+	unsigned int ppmax;
+	int ret, i;
+
+	if (!lldi->vr->iscsi.size) {
+		pr_warn("%s, iscsi NOT enabled, check config!\n", ndev->name);
+		return -EACCES;
+	}
+
+	ppmax = lldi->vr->iscsi.size >> PPOD_SIZE_SHIFT;
+
+	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);
+
+	ret = cxgbi_ppm_init(lldi->iscsi_ppm, cdev->lldi.ports[0],
+			     cdev->lldi.pdev, &cdev->lldi, &tformat,
+			     ppmax, lldi->iscsi_llimit,
+			     lldi->vr->iscsi.start, 2);
+	if (ret >= 0) {
+		struct cxgbi_ppm *ppm = (struct cxgbi_ppm *)(*lldi->iscsi_ppm);
+
+		if ((ppm->tformat.pgsz_idx_dflt < DDP_PGIDX_MAX) &&
+		    (ppm->ppmax >= 1024))
+			set_bit(CDEV_DDP_ENABLE, &cdev->flags);
+		ret = 0;
+	}
+
+	return ret;
+}

drivers/target/iscsi/cxgbit/cxgbit_lro.h

+/*
+ * Copyright (c) 2016 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.
+ *
+ */
+
+#ifndef	__CXGBIT_LRO_H__
+#define	__CXGBIT_LRO_H__
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/skbuff.h>
+
+#define LRO_FLUSH_LEN_MAX	65535
+
+struct cxgbit_lro_cb {
+	struct cxgbit_sock *csk;
+	u32 pdu_totallen;
+	u32 offset;
+	u8 pdu_idx;
+	bool complete;
+};
+
+enum cxgbit_pducb_flags {
+	PDUCBF_RX_HDR		= (1 << 0), /* received pdu header */
+	PDUCBF_RX_DATA		= (1 << 1), /* received pdu payload */
+	PDUCBF_RX_STATUS	= (1 << 2), /* received ddp status */
+	PDUCBF_RX_DATA_DDPD	= (1 << 3), /* pdu payload ddp'd */
+	PDUCBF_RX_HCRC_ERR	= (1 << 4), /* header digest error */
+	PDUCBF_RX_DCRC_ERR	= (1 << 5), /* data digest error */
+};
+
+struct cxgbit_lro_pdu_cb {
+	u8 flags;
+	u8 frags;
+	u8 hfrag_idx;
+	u8 nr_dfrags;
+	u8 dfrag_idx;
+	bool complete;
+	u32 seq;
+	u32 pdulen;
+	u32 hlen;
+	u32 dlen;
+	u32 doffset;
+	u32 ddigest;
+	void *hdr;
+};
+
+#define LRO_SKB_MAX_HEADROOM  \
+		(sizeof(struct cxgbit_lro_cb) + \
+		 (MAX_SKB_FRAGS * sizeof(struct cxgbit_lro_pdu_cb)))
+
+#define LRO_SKB_MIN_HEADROOM  \
+		(sizeof(struct cxgbit_lro_cb) + \
+		 sizeof(struct cxgbit_lro_pdu_cb))
+
+#define cxgbit_skb_lro_cb(skb)	((struct cxgbit_lro_cb *)skb->data)
+#define cxgbit_skb_lro_pdu_cb(skb, i)	\
+	((struct cxgbit_lro_pdu_cb *)(skb->data + sizeof(struct cxgbit_lro_cb) \
+		+ (i * sizeof(struct cxgbit_lro_pdu_cb))))
+
+#define CPL_RX_ISCSI_DDP_STATUS_DDP_SHIFT	16 /* ddp'able */
+#define CPL_RX_ISCSI_DDP_STATUS_PAD_SHIFT	19 /* pad error */
+#define CPL_RX_ISCSI_DDP_STATUS_HCRC_SHIFT	20 /* hcrc error */
+#define CPL_RX_ISCSI_DDP_STATUS_DCRC_SHIFT	21 /* dcrc error */
+
+#endif	/*__CXGBIT_LRO_H_*/

drivers/target/iscsi/cxgbit/cxgbit_main.c

+/*
+ * Copyright (c) 2016 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 version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define DRV_NAME "cxgbit"
+#define DRV_VERSION "1.0.0-ko"
+#define pr_fmt(fmt) DRV_NAME ": " fmt
+
+#include "cxgbit.h"
+
+#ifdef CONFIG_CHELSIO_T4_DCB
+#include <net/dcbevent.h>
+#include "cxgb4_dcb.h"
+#endif
+
+LIST_HEAD(cdev_list_head);
+/* cdev list lock */
+DEFINE_MUTEX(cdev_list_lock);
+
+void _cxgbit_free_cdev(struct kref *kref)
+{
+	struct cxgbit_device *cdev;
+
+	cdev = container_of(kref, struct cxgbit_device, kref);
+	kfree(cdev);
+}
+
+static void cxgbit_set_mdsl(struct cxgbit_device *cdev)
+{
+	struct cxgb4_lld_info *lldi = &cdev->lldi;
+	u32 mdsl;
+
+#define ULP2_MAX_PKT_LEN 16224
+#define ISCSI_PDU_NONPAYLOAD_LEN 312
+	mdsl = min_t(u32, lldi->iscsi_iolen - ISCSI_PDU_NONPAYLOAD_LEN,
+		     ULP2_MAX_PKT_LEN - ISCSI_PDU_NONPAYLOAD_LEN);
+	mdsl = min_t(u32, mdsl, 8192);
+	mdsl = min_t(u32, mdsl, (MAX_SKB_FRAGS - 1) * PAGE_SIZE);
+
+	cdev->mdsl = mdsl;
+}
+
+static void *cxgbit_uld_add(const struct cxgb4_lld_info *lldi)
+{
+	struct cxgbit_device *cdev;
+
+	if (is_t4(lldi->adapter_type))
+		return ERR_PTR(-ENODEV);
+
+	cdev = kzalloc(sizeof(*cdev), GFP_KERNEL);
+	if (!cdev)
+		return ERR_PTR(-ENOMEM);
+
+	kref_init(&cdev->kref);
+
+	cdev->lldi = *lldi;
+
+	cxgbit_set_mdsl(cdev);
+
+	if (cxgbit_ddp_init(cdev) < 0) {
+		kfree(cdev);
+		return ERR_PTR(-EINVAL);
+	}
+
+	if (!test_bit(CDEV_DDP_ENABLE, &cdev->flags))
+		pr_info("cdev %s ddp init failed\n",
+			pci_name(lldi->pdev));
+
+	if (lldi->fw_vers >= 0x10d2b00)
+		set_bit(CDEV_ISO_ENABLE, &cdev->flags);
+
+	spin_lock_init(&cdev->cskq.lock);
+	INIT_LIST_HEAD(&cdev->cskq.list);
+
+	mutex_lock(&cdev_list_lock);
+	list_add_tail(&cdev->list, &cdev_list_head);
+	mutex_unlock(&cdev_list_lock);
+
+	pr_info("cdev %s added for iSCSI target transport\n",
+		pci_name(lldi->pdev));
+
+	return cdev;
+}
+
+static void cxgbit_close_conn(struct cxgbit_device *cdev)
+{
+	struct cxgbit_sock *csk;
+	struct sk_buff *skb;
+	bool wakeup_thread = false;
+
+	spin_lock_bh(&cdev->cskq.lock);
+	list_for_each_entry(csk, &cdev->cskq.list, list) {
+		skb = alloc_skb(0, GFP_ATOMIC);
+		if (!skb)
+			continue;
+
+		spin_lock_bh(&csk->rxq.lock);
+		__skb_queue_tail(&csk->rxq, skb);
+		if (skb_queue_len(&csk->rxq) == 1)
+			wakeup_thread = true;
+		spin_unlock_bh(&csk->rxq.lock);
+
+		if (wakeup_thread) {
+			wake_up(&csk->waitq);
+			wakeup_thread = false;
+		}
+	}
+	spin_unlock_bh(&cdev->cskq.lock);
+}
+
+static void cxgbit_detach_cdev(struct cxgbit_device *cdev)
+{
+	bool free_cdev = false;
+
+	spin_lock_bh(&cdev->cskq.lock);
+	if (list_empty(&cdev->cskq.list))
+		free_cdev = true;
+	spin_unlock_bh(&cdev->cskq.lock);
+
+	if (free_cdev) {
+		mutex_lock(&cdev_list_lock);
+		list_del(&cdev->list);
+		mutex_unlock(&cdev_list_lock);
+
+		cxgbit_put_cdev(cdev);
+	} else {
+		cxgbit_close_conn(cdev);
+	}
+}
+
+static int cxgbit_uld_state_change(void *handle, enum cxgb4_state state)
+{
+	struct cxgbit_device *cdev = handle;
+
+	switch (state) {
+	case CXGB4_STATE_UP:
+		set_bit(CDEV_STATE_UP, &cdev->flags);
+		pr_info("cdev %s state UP.\n", pci_name(cdev->lldi.pdev));
+		break;
+	case CXGB4_STATE_START_RECOVERY:
+		clear_bit(CDEV_STATE_UP, &cdev->flags);
+		cxgbit_close_conn(cdev);
+		pr_info("cdev %s state RECOVERY.\n", pci_name(cdev->lldi.pdev));
+		break;
+	case CXGB4_STATE_DOWN:
+		pr_info("cdev %s state DOWN.\n", pci_name(cdev->lldi.pdev));
+		break;
+	case CXGB4_STATE_DETACH:
+		clear_bit(CDEV_STATE_UP, &cdev->flags);
+		pr_info("cdev %s state DETACH.\n", pci_name(cdev->lldi.pdev));
+		cxgbit_detach_cdev(cdev);
+		break;
+	default:
+		pr_info("cdev %s unknown state %d.\n",
+			pci_name(cdev->lldi.pdev), state);
+		break;
+	}
+	return 0;
+}
+
+static void
+cxgbit_proc_ddp_status(unsigned int tid, struct cpl_rx_data_ddp *cpl,
+		       struct cxgbit_lro_pdu_cb *pdu_cb)
+{
+	unsigned int status = ntohl(cpl->ddpvld);
+
+	pdu_cb->flags |= PDUCBF_RX_STATUS;
+	pdu_cb->ddigest = ntohl(cpl->ulp_crc);
+	pdu_cb->pdulen = ntohs(cpl->len);
+
+	if (status & (1 << CPL_RX_ISCSI_DDP_STATUS_HCRC_SHIFT)) {
+		pr_info("tid 0x%x, status 0x%x, hcrc bad.\n", tid, status);
+		pdu_cb->flags |= PDUCBF_RX_HCRC_ERR;
+	}
+
+	if (status & (1 << CPL_RX_ISCSI_DDP_STATUS_DCRC_SHIFT)) {
+		pr_info("tid 0x%x, status 0x%x, dcrc bad.\n", tid, status);
+		pdu_cb->flags |= PDUCBF_RX_DCRC_ERR;
+	}
+
+	if (status & (1 << CPL_RX_ISCSI_DDP_STATUS_PAD_SHIFT))
+		pr_info("tid 0x%x, status 0x%x, pad bad.\n", tid, status);
+
+	if ((status & (1 << CPL_RX_ISCSI_DDP_STATUS_DDP_SHIFT)) &&
+	    (!(pdu_cb->flags & PDUCBF_RX_DATA))) {
+		pdu_cb->flags |= PDUCBF_RX_DATA_DDPD;
+	}
+}
+
+static void
+cxgbit_lro_add_packet_rsp(struct sk_buff *skb, u8 op, const __be64 *rsp)
+{
+	struct cxgbit_lro_cb *lro_cb = cxgbit_skb_lro_cb(skb);
+	struct cxgbit_lro_pdu_cb *pdu_cb = cxgbit_skb_lro_pdu_cb(skb,
+						lro_cb->pdu_idx);
+	struct cpl_rx_iscsi_ddp *cpl = (struct cpl_rx_iscsi_ddp *)(rsp + 1);
+
+	cxgbit_proc_ddp_status(lro_cb->csk->tid, cpl, pdu_cb);
+
+	if (pdu_cb->flags & PDUCBF_RX_HDR)
+		pdu_cb->complete = true;
+
+	lro_cb->complete = true;
+	lro_cb->pdu_totallen += pdu_cb->pdulen;
+	lro_cb->pdu_idx++;
+}
+
+static void
+cxgbit_copy_frags(struct sk_buff *skb, const struct pkt_gl *gl,
+		  unsigned int offset)
+{
+	u8 skb_frag_idx = skb_shinfo(skb)->nr_frags;
+	u8 i;
+
+	/* usually there's just one frag */
+	__skb_fill_page_desc(skb, skb_frag_idx, gl->frags[0].page,
+			     gl->frags[0].offset + offset,
+			     gl->frags[0].size - offset);
+	for (i = 1; i < gl->nfrags; i++)
+		__skb_fill_page_desc(skb, skb_frag_idx + i,
+				     gl->frags[i].page,
+				     gl->frags[i].offset,
+				     gl->frags[i].size);
+
+	skb_shinfo(skb)->nr_frags += gl->nfrags;
+
+	/* get a reference to the last page, we don't own it */
+	get_page(gl->frags[gl->nfrags - 1].page);
+}
+
+static void
+cxgbit_lro_add_packet_gl(struct sk_buff *skb, u8 op, const struct pkt_gl *gl)
+{
+	struct cxgbit_lro_cb *lro_cb = cxgbit_skb_lro_cb(skb);
+	struct cxgbit_lro_pdu_cb *pdu_cb = cxgbit_skb_lro_pdu_cb(skb,
+						lro_cb->pdu_idx);
+	u32 len, offset;
+
+	if (op == CPL_ISCSI_HDR) {
+		struct cpl_iscsi_hdr *cpl = (struct cpl_iscsi_hdr *)gl->va;
+
+		offset = sizeof(struct cpl_iscsi_hdr);
+		pdu_cb->flags |= PDUCBF_RX_HDR;
+		pdu_cb->seq = ntohl(cpl->seq);
+		len = ntohs(cpl->len);
+		pdu_cb->hdr = gl->va + offset;
+		pdu_cb->hlen = len;
+		pdu_cb->hfrag_idx = skb_shinfo(skb)->nr_frags;
+
+		if (unlikely(gl->nfrags > 1))
+			cxgbit_skcb_flags(skb) = 0;
+
+		lro_cb->complete = false;
+	} else {
+		struct cpl_iscsi_data *cpl = (struct cpl_iscsi_data *)gl->va;
+
+		offset = sizeof(struct cpl_iscsi_data);
+		pdu_cb->flags |= PDUCBF_RX_DATA;
+		len = ntohs(cpl->len);
+		pdu_cb->dlen = len;
+		pdu_cb->doffset = lro_cb->offset;
+		pdu_cb->nr_dfrags = gl->nfrags;
+		pdu_cb->dfrag_idx = skb_shinfo(skb)->nr_frags;
+	}
+
+	cxgbit_copy_frags(skb, gl, offset);
+
+	pdu_cb->frags += gl->nfrags;
+	lro_cb->offset += len;
+	skb->len += len;
+	skb->data_len += len;
+	skb->truesize += len;
+}
+
+static struct sk_buff *
+cxgbit_lro_init_skb(struct cxgbit_sock *csk, u8 op, const struct pkt_gl *gl,
+		    const __be64 *rsp, struct napi_struct *napi)
+{
+	struct sk_buff *skb;
+	struct cxgbit_lro_cb *lro_cb;
+
+	skb = napi_alloc_skb(napi, LRO_SKB_MAX_HEADROOM);
+
+	if (unlikely(!skb))
+		return NULL;
+
+	memset(skb->data, 0, LRO_SKB_MAX_HEADROOM);
+
+	cxgbit_skcb_flags(skb) |= SKCBF_RX_LRO;
+
+	lro_cb = cxgbit_skb_lro_cb(skb);
+
+	cxgbit_get_csk(csk);
+
+	lro_cb->csk = csk;
+
+	return skb;
+}
+
+static void cxgbit_queue_lro_skb(struct cxgbit_sock *csk, struct sk_buff *skb)
+{
+	bool wakeup_thread = false;
+
+	spin_lock(&csk->rxq.lock);
+	__skb_queue_tail(&csk->rxq, skb);
+	if (skb_queue_len(&csk->rxq) == 1)
+		wakeup_thread = true;
+	spin_unlock(&csk->rxq.lock);
+
+	if (wakeup_thread)
+		wake_up(&csk->waitq);
+}
+
+static void cxgbit_lro_flush(struct t4_lro_mgr *lro_mgr, struct sk_buff *skb)
+{
+	struct cxgbit_lro_cb *lro_cb = cxgbit_skb_lro_cb(skb);
+	struct cxgbit_sock *csk = lro_cb->csk;
+
+	csk->lro_skb = NULL;
+
+	__skb_unlink(skb, &lro_mgr->lroq);
+	cxgbit_queue_lro_skb(csk, skb);
+
+	cxgbit_put_csk(csk);
+
+	lro_mgr->lro_pkts++;
+	lro_mgr->lro_session_cnt--;
+}
+
+static void cxgbit_uld_lro_flush(struct t4_lro_mgr *lro_mgr)
+{
+	struct sk_buff *skb;
+
+	while ((skb = skb_peek(&lro_mgr->lroq)))
+		cxgbit_lro_flush(lro_mgr, skb);
+}
+
+static int
+cxgbit_lro_receive(struct cxgbit_sock *csk, u8 op, const __be64 *rsp,
+		   const struct pkt_gl *gl, struct t4_lro_mgr *lro_mgr,
+		   struct napi_struct *napi)
+{
+	struct sk_buff *skb;
+	struct cxgbit_lro_cb *lro_cb;
+
+	if (!csk) {
+		pr_err("%s: csk NULL, op 0x%x.\n", __func__, op);
+		goto out;
+	}
+
+	if (csk->lro_skb)
+		goto add_packet;
+
+start_lro:
+	if (lro_mgr->lro_session_cnt >= MAX_LRO_SESSIONS) {
+		cxgbit_uld_lro_flush(lro_mgr);
+		goto start_lro;
+	}
+
+	skb = cxgbit_lro_init_skb(csk, op, gl, rsp, napi);
+	if (unlikely(!skb))
+		goto out;
+
+	csk->lro_skb = skb;
+
+	__skb_queue_tail(&lro_mgr->lroq, skb);
+	lro_mgr->lro_session_cnt++;
+
+add_packet:
+	skb = csk->lro_skb;
+	lro_cb = cxgbit_skb_lro_cb(skb);
+
+	if ((gl && (((skb_shinfo(skb)->nr_frags + gl->nfrags) >
+	    MAX_SKB_FRAGS) || (lro_cb->pdu_totallen >= LRO_FLUSH_LEN_MAX))) ||
+	    (lro_cb->pdu_idx >= MAX_SKB_FRAGS)) {
+		cxgbit_lro_flush(lro_mgr, skb);
+		goto start_lro;
+	}
+
+	if (gl)
+		cxgbit_lro_add_packet_gl(skb, op, gl);
+	else
+		cxgbit_lro_add_packet_rsp(skb, op, rsp);
+
+	lro_mgr->lro_merged++;
+
+	return 0;
+
+out:
+	return -1;
+}
+
+static int
+cxgbit_uld_lro_rx_handler(void *hndl, const __be64 *rsp,
+			  const struct pkt_gl *gl, struct t4_lro_mgr *lro_mgr,
+			  struct napi_struct *napi)
+{
+	struct cxgbit_device *cdev = hndl;
+	struct cxgb4_lld_info *lldi = &cdev->lldi;
+	struct cpl_tx_data *rpl = NULL;
+	struct cxgbit_sock *csk = NULL;
+	unsigned int tid = 0;
+	struct sk_buff *skb;
+	unsigned int op = *(u8 *)rsp;
+	bool lro_flush = true;
+
+	switch (op) {
+	case CPL_ISCSI_HDR:
+	case CPL_ISCSI_DATA:
+	case CPL_RX_ISCSI_DDP:
+	case CPL_FW4_ACK:
+		lro_flush = false;
+	case CPL_ABORT_RPL_RSS:
+	case CPL_PASS_ESTABLISH:
+	case CPL_PEER_CLOSE:
+	case CPL_CLOSE_CON_RPL:
+	case CPL_ABORT_REQ_RSS:
+	case CPL_SET_TCB_RPL:
+	case CPL_RX_DATA:
+		rpl = gl ? (struct cpl_tx_data *)gl->va :
+			   (struct cpl_tx_data *)(rsp + 1);
+		tid = GET_TID(rpl);
+		csk = lookup_tid(lldi->tids, tid);
+		break;
+	default:
+		break;
+	}
+
+	if (csk && csk->lro_skb && lro_flush)
+		cxgbit_lro_flush(lro_mgr, csk->lro_skb);
+
+	if (!gl) {
+		unsigned int len;
+
+		if (op == CPL_RX_ISCSI_DDP) {
+			if (!cxgbit_lro_receive(csk, op, rsp, NULL, lro_mgr,
+						napi))
+				return 0;
+		}
+
+		len = 64 - sizeof(struct rsp_ctrl) - 8;
+		skb = napi_alloc_skb(napi, len);
+		if (!skb)
+			goto nomem;
+		__skb_put(skb, len);
+		skb_copy_to_linear_data(skb, &rsp[1], len);
+	} else {
+		if (unlikely(op != *(u8 *)gl->va)) {
+			pr_info("? FL 0x%p,RSS%#llx,FL %#llx,len %u.\n",
+				gl->va, be64_to_cpu(*rsp),
+				be64_to_cpu(*(u64 *)gl->va),
+				gl->tot_len);
+			return 0;
+		}
+
+		if (op == CPL_ISCSI_HDR || op == CPL_ISCSI_DATA) {
+			if (!cxgbit_lro_receive(csk, op, rsp, gl, lro_mgr,
+						napi))
+				return 0;
+		}
+
+#define RX_PULL_LEN 128
+		skb = cxgb4_pktgl_to_skb(gl, RX_PULL_LEN, RX_PULL_LEN);
+		if (unlikely(!skb))
+			goto nomem;
+	}
+
+	rpl = (struct cpl_tx_data *)skb->data;
+	op = rpl->ot.opcode;
+	cxgbit_skcb_rx_opcode(skb) = op;
+
+	pr_debug("cdev %p, opcode 0x%x(0x%x,0x%x), skb %p.\n",
+		 cdev, op, rpl->ot.opcode_tid,
+		 ntohl(rpl->ot.opcode_tid), skb);
+
+	if (op < NUM_CPL_CMDS && cxgbit_cplhandlers[op]) {
+		cxgbit_cplhandlers[op](cdev, skb);
+	} else {
+		pr_err("No handler for opcode 0x%x.\n", op);
+		__kfree_skb(skb);
+	}
+	return 0;
+nomem:
+	pr_err("%s OOM bailing out.\n", __func__);
+	return 1;
+}
+
+#ifdef CONFIG_CHELSIO_T4_DCB
+struct cxgbit_dcb_work {
+	struct dcb_app_type dcb_app;
+	struct work_struct work;
+};
+
+static void
+cxgbit_update_dcb_priority(struct cxgbit_device *cdev, u8 port_id,
+			   u8 dcb_priority, u16 port_num)
+{
+	struct cxgbit_sock *csk;
+	struct sk_buff *skb;
+	u16 local_port;
+	bool wakeup_thread = false;
+
+	spin_lock_bh(&cdev->cskq.lock);
+	list_for_each_entry(csk, &cdev->cskq.list, list) {
+		if (csk->port_id != port_id)
+			continue;
+
+		if (csk->com.local_addr.ss_family == AF_INET6) {
+			struct sockaddr_in6 *sock_in6;
+
+			sock_in6 = (struct sockaddr_in6 *)&csk->com.local_addr;
+			local_port = ntohs(sock_in6->sin6_port);
+		} else {
+			struct sockaddr_in *sock_in;
+
+			sock_in = (struct sockaddr_in *)&csk->com.local_addr;
+			local_port = ntohs(sock_in->sin_port);
+		}
+
+		if (local_port != port_num)
+			continue;
+
+		if (csk->dcb_priority == dcb_priority)
+			continue;
+
+		skb = alloc_skb(0, GFP_ATOMIC);
+		if (!skb)
+			continue;
+
+		spin_lock(&csk->rxq.lock);
+		__skb_queue_tail(&csk->rxq, skb);
+		if (skb_queue_len(&csk->rxq) == 1)
+			wakeup_thread = true;
+		spin_unlock(&csk->rxq.lock);
+
+		if (wakeup_thread) {
+			wake_up(&csk->waitq);
+			wakeup_thread = false;
+		}
+	}
+	spin_unlock_bh(&cdev->cskq.lock);
+}
+
+static void cxgbit_dcb_workfn(struct work_struct *work)
+{
+	struct cxgbit_dcb_work *dcb_work;
+	struct net_device *ndev;
+	struct cxgbit_device *cdev = NULL;
+	struct dcb_app_type *iscsi_app;
+	u8 priority, port_id = 0xff;
+
+	dcb_work = container_of(work, struct cxgbit_dcb_work, work);
+	iscsi_app = &dcb_work->dcb_app;
+
+	if (iscsi_app->dcbx & DCB_CAP_DCBX_VER_IEEE) {
+		if (iscsi_app->app.selector != IEEE_8021QAZ_APP_SEL_ANY)
+			goto out;
+
+		priority = iscsi_app->app.priority;
+
+	} else if (iscsi_app->dcbx & DCB_CAP_DCBX_VER_CEE) {
+		if (iscsi_app->app.selector != DCB_APP_IDTYPE_PORTNUM)
+			goto out;
+
+		if (!iscsi_app->app.priority)
+			goto out;
+
+		priority = ffs(iscsi_app->app.priority) - 1;
+	} else {
+		goto out;
+	}
+
+	pr_debug("priority for ifid %d is %u\n",
+		 iscsi_app->ifindex, priority);
+
+	ndev = dev_get_by_index(&init_net, iscsi_app->ifindex);
+
+	if (!ndev)
+		goto out;
+
+	mutex_lock(&cdev_list_lock);
+	cdev = cxgbit_find_device(ndev, &port_id);
+
+	dev_put(ndev);
+
+	if (!cdev) {
+		mutex_unlock(&cdev_list_lock);
+		goto out;
+	}
+
+	cxgbit_update_dcb_priority(cdev, port_id, priority,
+				   iscsi_app->app.protocol);
+	mutex_unlock(&cdev_list_lock);
+out:
+	kfree(dcb_work);
+}
+
+static int
+cxgbit_dcbevent_notify(struct notifier_block *nb, unsigned long action,
+		       void *data)
+{
+	struct cxgbit_dcb_work *dcb_work;
+	struct dcb_app_type *dcb_app = data;
+
+	dcb_work = kzalloc(sizeof(*dcb_work), GFP_ATOMIC);
+	if (!dcb_work)
+		return NOTIFY_DONE;
+
+	dcb_work->dcb_app = *dcb_app;
+	INIT_WORK(&dcb_work->work, cxgbit_dcb_workfn);
+	schedule_work(&dcb_work->work);
+	return NOTIFY_OK;
+}
+#endif
+
+static enum target_prot_op cxgbit_get_sup_prot_ops(struct iscsi_conn *conn)
+{
+	return TARGET_PROT_NORMAL;
+}
+
+static struct iscsit_transport cxgbit_transport = {
+	.name			= DRV_NAME,
+	.transport_type		= ISCSI_HW_OFFLOAD,
+	.priv_size		= sizeof(struct cxgbit_cmd),
+	.owner			= THIS_MODULE,
+	.iscsit_setup_np	= cxgbit_setup_np,
+	.iscsit_accept_np	= cxgbit_accept_np,
+	.iscsit_free_np		= cxgbit_free_np,
+	.iscsit_free_conn	= cxgbit_free_conn,
+	.iscsit_get_login_rx	= cxgbit_get_login_rx,
+	.iscsit_put_login_tx	= cxgbit_put_login_tx,
+	.iscsit_immediate_queue	= iscsit_immediate_queue,
+	.iscsit_response_queue	= iscsit_response_queue,
+	.iscsit_get_dataout	= iscsit_build_r2ts_for_cmd,
+	.iscsit_queue_data_in	= iscsit_queue_rsp,
+	.iscsit_queue_status	= iscsit_queue_rsp,
+	.iscsit_xmit_pdu	= cxgbit_xmit_pdu,
+	.iscsit_get_r2t_ttt	= cxgbit_get_r2t_ttt,
+	.iscsit_get_rx_pdu	= cxgbit_get_rx_pdu,
+	.iscsit_validate_params	= cxgbit_validate_params,
+	.iscsit_release_cmd	= cxgbit_release_cmd,
+	.iscsit_aborted_task	= iscsit_aborted_task,
+	.iscsit_get_sup_prot_ops = cxgbit_get_sup_prot_ops,
+};
+
+static struct cxgb4_uld_info cxgbit_uld_info = {
+	.name		= DRV_NAME,
+	.add		= cxgbit_uld_add,
+	.state_change	= cxgbit_uld_state_change,
+	.lro_rx_handler = cxgbit_uld_lro_rx_handler,
+	.lro_flush	= cxgbit_uld_lro_flush,
+};
+
+#ifdef CONFIG_CHELSIO_T4_DCB
+static struct notifier_block cxgbit_dcbevent_nb = {
+	.notifier_call = cxgbit_dcbevent_notify,
+};
+#endif
+
+static int __init cxgbit_init(void)
+{
+	cxgb4_register_uld(CXGB4_ULD_ISCSIT, &cxgbit_uld_info);
+	iscsit_register_transport(&cxgbit_transport);
+
+#ifdef CONFIG_CHELSIO_T4_DCB
+	pr_info("%s dcb enabled.\n", DRV_NAME);
+	register_dcbevent_notifier(&cxgbit_dcbevent_nb);
+#endif
+	BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, cb) <
+		     sizeof(union cxgbit_skb_cb));
+	return 0;
+}
+
+static void __exit cxgbit_exit(void)
+{
+	struct cxgbit_device *cdev, *tmp;
+
+#ifdef CONFIG_CHELSIO_T4_DCB
+	unregister_dcbevent_notifier(&cxgbit_dcbevent_nb);
+#endif
+	mutex_lock(&cdev_list_lock);
+	list_for_each_entry_safe(cdev, tmp, &cdev_list_head, list) {
+		list_del(&cdev->list);
+		cxgbit_put_cdev(cdev);
+	}
+	mutex_unlock(&cdev_list_lock);
+	iscsit_unregister_transport(&cxgbit_transport);
+	cxgb4_unregister_uld(CXGB4_ULD_ISCSIT);
+}
+
+module_init(cxgbit_init);
+module_exit(cxgbit_exit);
+
+MODULE_DESCRIPTION("Chelsio iSCSI target offload driver");
+MODULE_AUTHOR("Chelsio Communications");
+MODULE_VERSION(DRV_VERSION);
+MODULE_LICENSE("GPL");