add idl4k kernel firmware version 1.13.0.105

kernel/drivers/scsi/cxgb3i/Kbuild

@@ -0,0 +1,4 @@
+EXTRA_CFLAGS += -I$(srctree)/drivers/net/cxgb3
+
+cxgb3i-y := cxgb3i_init.o cxgb3i_iscsi.o cxgb3i_pdu.o cxgb3i_offload.o cxgb3i_ddp.o
+obj-$(CONFIG_SCSI_CXGB3_ISCSI) += cxgb3i.o

kernel/drivers/scsi/cxgb3i/Kconfig

@@ -0,0 +1,7 @@
+config SCSI_CXGB3_ISCSI
+	tristate "Chelsio S3xx iSCSI support"
+	depends on CHELSIO_T3_DEPENDS
+	select CHELSIO_T3
+	select SCSI_ISCSI_ATTRS
+	---help---
+	This driver supports iSCSI offload for the Chelsio S3 series devices.

kernel/drivers/scsi/cxgb3i/cxgb3i.h

@@ -0,0 +1,161 @@
+/*
+ * cxgb3i.h: Chelsio S3xx iSCSI driver.
+ *
+ * Copyright (c) 2008 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)
+ */
+
+#ifndef __CXGB3I_H__
+#define __CXGB3I_H__
+
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/list.h>
+#include <linux/netdevice.h>
+#include <linux/scatterlist.h>
+#include <linux/skbuff.h>
+#include <scsi/libiscsi_tcp.h>
+
+/* from cxgb3 LLD */
+#include "common.h"
+#include "t3_cpl.h"
+#include "t3cdev.h"
+#include "cxgb3_ctl_defs.h"
+#include "cxgb3_offload.h"
+#include "firmware_exports.h"
+
+#include "cxgb3i_offload.h"
+#include "cxgb3i_ddp.h"
+
+#define CXGB3I_SCSI_HOST_QDEPTH 1024
+#define CXGB3I_MAX_TARGET	CXGB3I_MAX_CONN
+#define CXGB3I_MAX_LUN		512
+#define ISCSI_PDU_NONPAYLOAD_MAX \
+	(sizeof(struct iscsi_hdr) + ISCSI_MAX_AHS_SIZE + 2*ISCSI_DIGEST_SIZE)
+
+struct cxgb3i_adapter;
+struct cxgb3i_hba;
+struct cxgb3i_endpoint;
+
+/**
+ * struct cxgb3i_hba - cxgb3i iscsi structure (per port)
+ *
+ * @snic:	cxgb3i adapter containing this port
+ * @ndev:	pointer to netdev structure
+ * @shost:	pointer to scsi host structure
+ */
+struct cxgb3i_hba {
+	struct cxgb3i_adapter *snic;
+	struct net_device *ndev;
+	struct Scsi_Host *shost;
+};
+
+/**
+ * struct cxgb3i_adapter - cxgb3i adapter structure (per pci)
+ *
+ * @listhead:	list head to link elements
+ * @lock:	lock for this structure
+ * @tdev:	pointer to t3cdev used by cxgb3 driver
+ * @pdev:	pointer to pci dev
+ * @hba_cnt:	# of hbas (the same as # of ports)
+ * @hba:	all the hbas on this adapter
+ * @flags:	bit flag for adapter event/status
+ * @tx_max_size: max. tx packet size supported
+ * @rx_max_size: max. rx packet size supported
+ * @tag_format: ddp tag format settings
+ */
+#define CXGB3I_ADAPTER_FLAG_RESET	0x1
+struct cxgb3i_adapter {
+	struct list_head list_head;
+	spinlock_t lock;
+	struct t3cdev *tdev;
+	struct pci_dev *pdev;
+	unsigned char hba_cnt;
+	struct cxgb3i_hba *hba[MAX_NPORTS];
+
+	unsigned int flags;
+	unsigned int tx_max_size;
+	unsigned int rx_max_size;
+
+	struct cxgb3i_tag_format tag_format;
+};
+
+/**
+ * struct cxgb3i_conn - cxgb3i iscsi connection
+ *
+ * @listhead:	list head to link elements
+ * @cep:	pointer to iscsi_endpoint structure
+ * @conn:	pointer to iscsi_conn structure
+ * @hba:	pointer to the hba this conn. is going through
+ * @task_idx_bits: # of bits needed for session->cmds_max
+ */
+struct cxgb3i_conn {
+	struct list_head list_head;
+	struct cxgb3i_endpoint *cep;
+	struct iscsi_conn *conn;
+	struct cxgb3i_hba *hba;
+	unsigned int task_idx_bits;
+};
+
+/**
+ * struct cxgb3i_endpoint - iscsi tcp endpoint
+ *
+ * @c3cn:	the h/w tcp connection representation
+ * @hba:	pointer to the hba this conn. is going through
+ * @cconn:	pointer to the associated cxgb3i iscsi connection
+ */
+struct cxgb3i_endpoint {
+	struct s3_conn *c3cn;
+	struct cxgb3i_hba *hba;
+	struct cxgb3i_conn *cconn;
+};
+
+/**
+ * struct cxgb3i_task_data - private iscsi task data
+ *
+ * @nr_frags:	# of coalesced page frags (from scsi sgl)
+ * @frags:	coalesced page frags (from scsi sgl)
+ * @skb:	tx pdu skb
+ * @offset:	data offset for the next pdu
+ * @count:	max. possible pdu payload
+ * @sgoffset:	offset to the first sg entry for a given offset
+ */
+#define MAX_PDU_FRAGS	((ULP2_MAX_PDU_PAYLOAD + 512 - 1) / 512)
+struct cxgb3i_task_data {
+	unsigned short nr_frags;
+	skb_frag_t frags[MAX_PDU_FRAGS];
+	struct sk_buff *skb;
+	unsigned int offset;
+	unsigned int count;
+	unsigned int sgoffset;
+};
+
+int cxgb3i_iscsi_init(void);
+void cxgb3i_iscsi_cleanup(void);
+
+struct cxgb3i_adapter *cxgb3i_adapter_find_by_tdev(struct t3cdev *);
+void cxgb3i_adapter_open(struct t3cdev *);
+void cxgb3i_adapter_close(struct t3cdev *);
+
+struct cxgb3i_hba *cxgb3i_hba_host_add(struct cxgb3i_adapter *,
+				       struct net_device *);
+void cxgb3i_hba_host_remove(struct cxgb3i_hba *);
+
+int cxgb3i_pdu_init(void);
+void cxgb3i_pdu_cleanup(void);
+void cxgb3i_conn_cleanup_task(struct iscsi_task *);
+int cxgb3i_conn_alloc_pdu(struct iscsi_task *, u8);
+int cxgb3i_conn_init_pdu(struct iscsi_task *, unsigned int, unsigned int);
+int cxgb3i_conn_xmit_pdu(struct iscsi_task *);
+
+void cxgb3i_release_itt(struct iscsi_task *task, itt_t hdr_itt);
+int cxgb3i_reserve_itt(struct iscsi_task *task, itt_t *hdr_itt);
+
+#endif

kernel/drivers/scsi/cxgb3i/cxgb3i_ddp.c

@@ -0,0 +1,770 @@
+/*
+ * cxgb3i_ddp.c: Chelsio S3xx iSCSI DDP Manager.
+ *
+ * Copyright (c) 2008 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)
+ */
+
+#include <linux/skbuff.h>
+#include <linux/scatterlist.h>
+
+/* from cxgb3 LLD */
+#include "common.h"
+#include "t3_cpl.h"
+#include "t3cdev.h"
+#include "cxgb3_ctl_defs.h"
+#include "cxgb3_offload.h"
+#include "firmware_exports.h"
+
+#include "cxgb3i_ddp.h"
+
+#define ddp_log_error(fmt...) printk(KERN_ERR "cxgb3i_ddp: ERR! " fmt)
+#define ddp_log_warn(fmt...)  printk(KERN_WARNING "cxgb3i_ddp: WARN! " fmt)
+#define ddp_log_info(fmt...)  printk(KERN_INFO "cxgb3i_ddp: " fmt)
+
+#ifdef __DEBUG_CXGB3I_DDP__
+#define ddp_log_debug(fmt, args...) \
+	printk(KERN_INFO "cxgb3i_ddp: %s - " fmt, __func__ , ## args)
+#else
+#define ddp_log_debug(fmt...)
+#endif
+
+/*
+ * iSCSI Direct Data Placement
+ *
+ * T3 h/w can 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 or
+ * is the base for ITT/TTT.
+ */
+
+#define DDP_PGIDX_MAX		4
+#define DDP_THRESHOLD	2048
+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;
+
+/*
+ * functions to program the pagepod in h/w
+ */
+static inline void ulp_mem_io_set_hdr(struct sk_buff *skb, unsigned int addr)
+{
+	struct ulp_mem_io *req = (struct ulp_mem_io *)skb->head;
+
+	req->wr.wr_lo = 0;
+	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));
+}
+
+static int set_ddp_map(struct cxgb3i_ddp_info *ddp, struct pagepod_hdr *hdr,
+		       unsigned int idx, unsigned int npods,
+		       struct cxgb3i_gather_list *gl)
+{
+	unsigned int pm_addr = (idx << PPOD_SIZE_SHIFT) + ddp->llimit;
+	int i;
+
+	for (i = 0; i < npods; i++, idx++, pm_addr += PPOD_SIZE) {
+		struct sk_buff *skb = ddp->gl_skb[idx];
+		struct pagepod *ppod;
+		int j, pidx;
+
+		/* hold on to the skb until we clear the ddp mapping */
+		skb_get(skb);
+
+		ulp_mem_io_set_hdr(skb, pm_addr);
+		ppod = (struct pagepod *)
+		       (skb->head + sizeof(struct ulp_mem_io));
+		memcpy(&(ppod->hdr), hdr, sizeof(struct pagepod));
+		for (pidx = 4 * i, j = 0; j < 5; ++j, ++pidx)
+			ppod->addr[j] = pidx < gl->nelem ?
+				     cpu_to_be64(gl->phys_addr[pidx]) : 0UL;
+
+		skb->priority = CPL_PRIORITY_CONTROL;
+		cxgb3_ofld_send(ddp->tdev, skb);
+	}
+	return 0;
+}
+
+static void clear_ddp_map(struct cxgb3i_ddp_info *ddp, unsigned int tag,
+			 unsigned int idx, unsigned int npods)
+{
+	unsigned int pm_addr = (idx << PPOD_SIZE_SHIFT) + ddp->llimit;
+	int i;
+
+	for (i = 0; i < npods; i++, idx++, pm_addr += PPOD_SIZE) {
+		struct sk_buff *skb = ddp->gl_skb[idx];
+
+		if (!skb) {
+			ddp_log_error("ddp tag 0x%x, 0x%x, %d/%u, skb NULL.\n",
+					tag, idx, i, npods);
+			continue;
+		}
+		ddp->gl_skb[idx] = NULL;
+		memset((skb->head + sizeof(struct ulp_mem_io)), 0, PPOD_SIZE);
+		ulp_mem_io_set_hdr(skb, pm_addr);
+		skb->priority = CPL_PRIORITY_CONTROL;
+		cxgb3_ofld_send(ddp->tdev, skb);
+	}
+}
+
+static inline int ddp_find_unused_entries(struct cxgb3i_ddp_info *ddp,
+					  unsigned int start, unsigned int max,
+					  unsigned int count,
+					  struct cxgb3i_gather_list *gl)
+{
+	unsigned int i, j, k;
+
+	/* not enough entries */
+	if ((max - start) < count)
+		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);
+	return -EBUSY;
+}
+
+static inline void ddp_unmark_entries(struct cxgb3i_ddp_info *ddp,
+				      int start, int count)
+{
+	spin_lock(&ddp->map_lock);
+	memset(&ddp->gl_map[start], 0,
+	       count * sizeof(struct cxgb3i_gather_list *));
+	spin_unlock(&ddp->map_lock);
+}
+
+static inline void ddp_free_gl_skb(struct cxgb3i_ddp_info *ddp,
+				   int idx, int count)
+{
+	int i;
+
+	for (i = 0; i < count; i++, idx++)
+		if (ddp->gl_skb[idx]) {
+			kfree_skb(ddp->gl_skb[idx]);
+			ddp->gl_skb[idx] = NULL;
+		}
+}
+
+static inline int ddp_alloc_gl_skb(struct cxgb3i_ddp_info *ddp, int idx,
+				   int count, gfp_t gfp)
+{
+	int i;
+
+	for (i = 0; i < count; i++) {
+		struct sk_buff *skb = alloc_skb(sizeof(struct ulp_mem_io) +
+						PPOD_SIZE, gfp);
+		if (skb) {
+			ddp->gl_skb[idx + i] = skb;
+			skb_put(skb, sizeof(struct ulp_mem_io) + PPOD_SIZE);
+		} else {
+			ddp_free_gl_skb(ddp, idx, i);
+			return -ENOMEM;
+		}
+	}
+	return 0;
+}
+
+/**
+ * cxgb3i_ddp_find_page_index - return ddp page index for a given page size
+ * @pgsz: page size
+ * return the ddp page index, if no match is found return DDP_PGIDX_MAX.
+ */
+int cxgb3i_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;
+	}
+	ddp_log_debug("ddp page size 0x%lx not supported.\n", pgsz);
+	return DDP_PGIDX_MAX;
+}
+
+/**
+ * cxgb3i_ddp_adjust_page_table - adjust page table with PAGE_SIZE
+ * return the ddp page index, if no match is found return DDP_PGIDX_MAX.
+ */
+int cxgb3i_ddp_adjust_page_table(void)
+{
+	int i;
+	unsigned int base_order, order;
+
+	if (PAGE_SIZE < (1UL << ddp_page_shift[0])) {
+		ddp_log_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(1 << PAGE_SHIFT);
+	for (i = 0; i < DDP_PGIDX_MAX; i++) {
+		/* first is the kernel page size, then just doubling the size */
+		ddp_page_order[i] = order - base_order + i;
+		ddp_page_shift[i] = PAGE_SHIFT + i;
+	}
+	return 0;
+}
+
+static inline void ddp_gl_unmap(struct pci_dev *pdev,
+				struct cxgb3i_gather_list *gl)
+{
+	int i;
+
+	for (i = 0; i < gl->nelem; i++)
+		pci_unmap_page(pdev, gl->phys_addr[i], PAGE_SIZE,
+			       PCI_DMA_FROMDEVICE);
+}
+
+static inline int ddp_gl_map(struct pci_dev *pdev,
+			     struct cxgb3i_gather_list *gl)
+{
+	int i;
+
+	for (i = 0; i < gl->nelem; i++) {
+		gl->phys_addr[i] = pci_map_page(pdev, gl->pages[i], 0,
+						PAGE_SIZE,
+						PCI_DMA_FROMDEVICE);
+		if (unlikely(pci_dma_mapping_error(pdev, gl->phys_addr[i])))
+			goto unmap;
+	}
+
+	return i;
+
+unmap:
+	if (i) {
+		unsigned int nelem = gl->nelem;
+
+		gl->nelem = i;
+		ddp_gl_unmap(pdev, gl);
+		gl->nelem = nelem;
+	}
+	return -ENOMEM;
+}
+
+/**
+ * cxgb3i_ddp_make_gl - build ddp page buffer list
+ * @xferlen: total buffer length
+ * @sgl: page buffer scatter-gather list
+ * @sgcnt: # of page buffers
+ * @pdev: pci_dev, used for pci map
+ * @gfp: allocation mode
+ *
+ * construct a ddp page buffer list from the scsi scattergather list.
+ * coalesce buffers as much as possible, and obtain dma addresses for
+ * each page.
+ *
+ * Return the cxgb3i_gather_list constructed from the page buffers if the
+ * memory can be used for ddp. Return NULL otherwise.
+ */
+struct cxgb3i_gather_list *cxgb3i_ddp_make_gl(unsigned int xferlen,
+					      struct scatterlist *sgl,
+					      unsigned int sgcnt,
+					      struct pci_dev *pdev,
+					      gfp_t gfp)
+{
+	struct cxgb3i_gather_list *gl;
+	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) {
+		ddp_log_debug("xfer %u < threshold %u, no ddp.\n",
+			      xferlen, DDP_THRESHOLD);
+		return NULL;
+	}
+
+	gl = kzalloc(sizeof(struct cxgb3i_gather_list) +
+		     npages * (sizeof(dma_addr_t) + sizeof(struct page *)),
+		     gfp);
+	if (!gl)
+		return NULL;
+
+	gl->pages = (struct page **)&gl->phys_addr[npages];
+	gl->length = xferlen;
+	gl->offset = sgoffset;
+	gl->pages[0] = sgpage;
+
+	sg = sg_next(sg);
+	while (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)))
+				goto error_out;
+
+			j++;
+			if (j == gl->nelem || sg->offset)
+				goto error_out;
+			gl->pages[j] = page;
+			sglen = sg->length;
+			sgoffset = sg->offset;
+			sgpage = page;
+		}
+		i++;
+		sg = sg_next(sg);
+	}
+	gl->nelem = ++j;
+
+	if (ddp_gl_map(pdev, gl) < 0)
+		goto error_out;
+
+	return gl;
+
+error_out:
+	kfree(gl);
+	return NULL;
+}
+
+/**
+ * cxgb3i_ddp_release_gl - release a page buffer list
+ * @gl: a ddp page buffer list
+ * @pdev: pci_dev used for pci_unmap
+ * free a ddp page buffer list resulted from cxgb3i_ddp_make_gl().
+ */
+void cxgb3i_ddp_release_gl(struct cxgb3i_gather_list *gl,
+			   struct pci_dev *pdev)
+{
+	ddp_gl_unmap(pdev, gl);
+	kfree(gl);
+}
+
+/**
+ * cxgb3i_ddp_tag_reserve - set up ddp for a data transfer
+ * @tdev: t3cdev adapter
+ * @tid: connection id
+ * @tformat: tag format
+ * @tagp: contains s/w tag initially, will be updated with ddp/hw tag
+ * @gl: the page momory list
+ * @gfp: allocation mode
+ *
+ * ddp setup for a given page buffer list and construct the ddp tag.
+ * return 0 if success, < 0 otherwise.
+ */
+int cxgb3i_ddp_tag_reserve(struct t3cdev *tdev, unsigned int tid,
+			   struct cxgb3i_tag_format *tformat, u32 *tagp,
+			   struct cxgb3i_gather_list *gl, gfp_t gfp)
+{
+	struct cxgb3i_ddp_info *ddp = tdev->ulp_iscsi;
+	struct pagepod_hdr hdr;
+	unsigned int npods;
+	int idx = -1;
+	int err = -ENOMEM;
+	u32 sw_tag = *tagp;
+	u32 tag;
+
+	if (page_idx >= DDP_PGIDX_MAX || !ddp || !gl || !gl->nelem ||
+		gl->length < DDP_THRESHOLD) {
+		ddp_log_debug("pgidx %u, xfer %u/%u, NO ddp.\n",
+			      page_idx, gl->length, DDP_THRESHOLD);
+		return -EINVAL;
+	}
+
+	npods = (gl->nelem + PPOD_PAGES_MAX - 1) >> PPOD_PAGES_SHIFT;
+
+	if (ddp->idx_last == ddp->nppods)
+		idx = ddp_find_unused_entries(ddp, 0, ddp->nppods, npods, gl);
+	else {
+		idx = ddp_find_unused_entries(ddp, ddp->idx_last + 1,
+					      ddp->nppods, npods, gl);
+		if (idx < 0 && ddp->idx_last >= npods) {
+			idx = ddp_find_unused_entries(ddp, 0,
+				min(ddp->idx_last + npods, ddp->nppods),
+						      npods, gl);
+		}
+	}
+	if (idx < 0) {
+		ddp_log_debug("xferlen %u, gl %u, npods %u NO DDP.\n",
+			      gl->length, gl->nelem, npods);
+		return idx;
+	}
+
+	err = ddp_alloc_gl_skb(ddp, idx, npods, gfp);
+	if (err < 0)
+		goto unmark_entries;
+
+	tag = cxgb3i_ddp_tag_base(tformat, sw_tag);
+	tag |= idx << PPOD_IDX_SHIFT;
+
+	hdr.rsvd = 0;
+	hdr.vld_tid = htonl(F_PPOD_VALID | V_PPOD_TID(tid));
+	hdr.pgsz_tag_clr = htonl(tag & ddp->rsvd_tag_mask);
+	hdr.maxoffset = htonl(gl->length);
+	hdr.pgoffset = htonl(gl->offset);
+
+	err = set_ddp_map(ddp, &hdr, idx, npods, gl);
+	if (err < 0)
+		goto free_gl_skb;
+
+	ddp->idx_last = idx;
+	ddp_log_debug("xfer %u, gl %u,%u, tid 0x%x, 0x%x -> 0x%x(%u,%u).\n",
+		      gl->length, gl->nelem, gl->offset, tid, sw_tag, tag,
+		      idx, npods);
+	*tagp = tag;
+	return 0;
+
+free_gl_skb:
+	ddp_free_gl_skb(ddp, idx, npods);
+unmark_entries:
+	ddp_unmark_entries(ddp, idx, npods);
+	return err;
+}
+
+/**
+ * cxgb3i_ddp_tag_release - release a ddp tag
+ * @tdev: t3cdev adapter
+ * @tag: ddp tag
+ * ddp cleanup for a given ddp tag and release all the resources held
+ */
+void cxgb3i_ddp_tag_release(struct t3cdev *tdev, u32 tag)
+{
+	struct cxgb3i_ddp_info *ddp = tdev->ulp_iscsi;
+	u32 idx;
+
+	if (!ddp) {
+		ddp_log_error("release ddp tag 0x%x, ddp NULL.\n", tag);
+		return;
+	}
+
+	idx = (tag >> PPOD_IDX_SHIFT) & ddp->idx_mask;
+	if (idx < ddp->nppods) {
+		struct cxgb3i_gather_list *gl = ddp->gl_map[idx];
+		unsigned int npods;
+
+		if (!gl || !gl->nelem) {
+			ddp_log_error("release 0x%x, idx 0x%x, gl 0x%p, %u.\n",
+				      tag, idx, gl, gl ? gl->nelem : 0);
+			return;
+		}
+		npods = (gl->nelem + PPOD_PAGES_MAX - 1) >> PPOD_PAGES_SHIFT;
+		ddp_log_debug("ddp tag 0x%x, release idx 0x%x, npods %u.\n",
+			      tag, idx, npods);
+		clear_ddp_map(ddp, tag, idx, npods);
+		ddp_unmark_entries(ddp, idx, npods);
+		cxgb3i_ddp_release_gl(gl, ddp->pdev);
+	} else
+		ddp_log_error("ddp tag 0x%x, idx 0x%x > max 0x%x.\n",
+			      tag, idx, ddp->nppods);
+}
+
+static int setup_conn_pgidx(struct t3cdev *tdev, unsigned int tid, int pg_idx,
+			    int reply)
+{
+	struct sk_buff *skb = alloc_skb(sizeof(struct cpl_set_tcb_field),
+					GFP_KERNEL);
+	struct cpl_set_tcb_field *req;
+	u64 val = pg_idx < DDP_PGIDX_MAX ? pg_idx : 0;
+
+	if (!skb)
+		return -ENOMEM;
+
+	/* set up ulp submode and page size */
+	req = (struct cpl_set_tcb_field *)skb_put(skb, sizeof(*req));
+	req->wr.wr_hi = htonl(V_WR_OP(FW_WROPCODE_FORWARD));
+	OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_SET_TCB_FIELD, tid));
+	req->reply = V_NO_REPLY(reply ? 0 : 1);
+	req->cpu_idx = 0;
+	req->word = htons(31);
+	req->mask = cpu_to_be64(0xF0000000);
+	req->val = cpu_to_be64(val << 28);
+	skb->priority = CPL_PRIORITY_CONTROL;
+
+	cxgb3_ofld_send(tdev, skb);
+	return 0;
+}
+
+/**
+ * cxgb3i_setup_conn_host_pagesize - setup the conn.'s ddp page size
+ * @tdev: t3cdev adapter
+ * @tid: connection id
+ * @reply: request reply from h/w
+ * set up the ddp page size based on the host PAGE_SIZE for a connection
+ * identified by tid
+ */
+int cxgb3i_setup_conn_host_pagesize(struct t3cdev *tdev, unsigned int tid,
+				    int reply)
+{
+	return setup_conn_pgidx(tdev, tid, page_idx, reply);
+}
+
+/**
+ * cxgb3i_setup_conn_pagesize - setup the conn.'s ddp page size
+ * @tdev: t3cdev adapter
+ * @tid: connection id
+ * @reply: request reply from h/w
+ * @pgsz: ddp page size
+ * set up the ddp page size for a connection identified by tid
+ */
+int cxgb3i_setup_conn_pagesize(struct t3cdev *tdev, unsigned int tid,
+				int reply, unsigned long pgsz)
+{
+	int pgidx = cxgb3i_ddp_find_page_index(pgsz);
+
+	return setup_conn_pgidx(tdev, tid, pgidx, reply);
+}
+
+/**
+ * cxgb3i_setup_conn_digest - setup conn. digest setting
+ * @tdev: t3cdev adapter
+ * @tid: connection id
+ * @hcrc: header digest enabled
+ * @dcrc: data digest enabled
+ * @reply: request reply from h/w
+ * set up the iscsi digest settings for a connection identified by tid
+ */
+int cxgb3i_setup_conn_digest(struct t3cdev *tdev, unsigned int tid,
+			     int hcrc, int dcrc, int reply)
+{
+	struct sk_buff *skb = alloc_skb(sizeof(struct cpl_set_tcb_field),
+					GFP_KERNEL);
+	struct cpl_set_tcb_field *req;
+	u64 val = (hcrc ? 1 : 0) | (dcrc ? 2 : 0);
+
+	if (!skb)
+		return -ENOMEM;
+
+	/* set up ulp submode and page size */
+	req = (struct cpl_set_tcb_field *)skb_put(skb, sizeof(*req));
+	req->wr.wr_hi = htonl(V_WR_OP(FW_WROPCODE_FORWARD));
+	OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_SET_TCB_FIELD, tid));
+	req->reply = V_NO_REPLY(reply ? 0 : 1);
+	req->cpu_idx = 0;
+	req->word = htons(31);
+	req->mask = cpu_to_be64(0x0F000000);
+	req->val = cpu_to_be64(val << 24);
+	skb->priority = CPL_PRIORITY_CONTROL;
+
+	cxgb3_ofld_send(tdev, skb);
+	return 0;
+}
+
+
+/**
+ * cxgb3i_adapter_ddp_info - read the adapter's ddp information
+ * @tdev: t3cdev adapter
+ * @tformat: tag format
+ * @txsz: max tx pdu payload size, filled in by this func.
+ * @rxsz: max rx pdu payload size, filled in by this func.
+ * setup the tag format for a given iscsi entity
+ */
+int cxgb3i_adapter_ddp_info(struct t3cdev *tdev,
+			    struct cxgb3i_tag_format *tformat,
+			    unsigned int *txsz, unsigned int *rxsz)
+{
+	struct cxgb3i_ddp_info *ddp;
+	unsigned char idx_bits;
+
+	if (!tformat)
+		return -EINVAL;
+
+	if (!tdev->ulp_iscsi)
+		return -EINVAL;
+
+	ddp = (struct cxgb3i_ddp_info *)tdev->ulp_iscsi;
+
+	idx_bits = 32 - tformat->sw_bits;
+	tformat->rsvd_bits = ddp->idx_bits;
+	tformat->rsvd_shift = PPOD_IDX_SHIFT;
+	tformat->rsvd_mask = (1 << tformat->rsvd_bits) - 1;
+
+	ddp_log_info("tag format: sw %u, rsvd %u,%u, mask 0x%x.\n",
+		      tformat->sw_bits, tformat->rsvd_bits,
+		      tformat->rsvd_shift, tformat->rsvd_mask);
+
+	*txsz = min_t(unsigned int, ULP2_MAX_PDU_PAYLOAD,
+			ddp->max_txsz - ISCSI_PDU_NONPAYLOAD_LEN);
+	*rxsz = min_t(unsigned int, ULP2_MAX_PDU_PAYLOAD,
+			ddp->max_rxsz - ISCSI_PDU_NONPAYLOAD_LEN);
+	ddp_log_info("max payload size: %u/%u, %u/%u.\n",
+		     *txsz, ddp->max_txsz, *rxsz, ddp->max_rxsz);
+	return 0;
+}
+
+/**
+ * cxgb3i_ddp_cleanup - release the cxgb3 adapter's ddp resource
+ * @tdev: t3cdev adapter
+ * release all the resource held by the ddp pagepod manager for a given
+ * adapter if needed
+ */
+
+static void ddp_cleanup(struct kref *kref)
+{
+	struct cxgb3i_ddp_info *ddp = container_of(kref,
+						struct cxgb3i_ddp_info,
+						refcnt);
+	int i = 0;
+
+	ddp_log_info("kref release ddp 0x%p, t3dev 0x%p.\n", ddp, ddp->tdev);
+
+	ddp->tdev->ulp_iscsi = NULL;
+	while (i < ddp->nppods) {
+		struct cxgb3i_gather_list *gl = ddp->gl_map[i];
+		if (gl) {
+			int npods = (gl->nelem + PPOD_PAGES_MAX - 1)
+					>> PPOD_PAGES_SHIFT;
+			ddp_log_info("t3dev 0x%p, ddp %d + %d.\n",
+					ddp->tdev, i, npods);
+			kfree(gl);
+			ddp_free_gl_skb(ddp, i, npods);
+			i += npods;
+		} else
+			i++;
+	}
+	cxgb3i_free_big_mem(ddp);
+}
+
+void cxgb3i_ddp_cleanup(struct t3cdev *tdev)
+{
+	struct cxgb3i_ddp_info *ddp = (struct cxgb3i_ddp_info *)tdev->ulp_iscsi;
+
+	ddp_log_info("t3dev 0x%p, release ddp 0x%p.\n", tdev, ddp);
+	if (ddp)
+		kref_put(&ddp->refcnt, ddp_cleanup);
+}
+
+/**
+ * ddp_init - initialize the cxgb3 adapter's ddp resource
+ * @tdev: t3cdev adapter
+ * initialize the ddp pagepod manager for a given adapter
+ */
+static void ddp_init(struct t3cdev *tdev)
+{
+	struct cxgb3i_ddp_info *ddp = tdev->ulp_iscsi;
+	struct ulp_iscsi_info uinfo;
+	unsigned int ppmax, bits;
+	int i, err;
+
+	if (ddp) {
+		kref_get(&ddp->refcnt);
+		ddp_log_warn("t3dev 0x%p, ddp 0x%p already set up.\n",
+				tdev, tdev->ulp_iscsi);
+		return;
+	}
+
+	err = tdev->ctl(tdev, ULP_ISCSI_GET_PARAMS, &uinfo);
+	if (err < 0) {
+		ddp_log_error("%s, failed to get iscsi param err=%d.\n",
+				 tdev->name, err);
+		return;
+	}
+
+	ppmax = (uinfo.ulimit - uinfo.llimit + 1) >> PPOD_SIZE_SHIFT;
+	bits = __ilog2_u32(ppmax) + 1;
+	if (bits > PPOD_IDX_MAX_SIZE)
+		bits = PPOD_IDX_MAX_SIZE;
+	ppmax = (1 << (bits - 1)) - 1;
+
+	ddp = cxgb3i_alloc_big_mem(sizeof(struct cxgb3i_ddp_info) +
+				   ppmax *
+					(sizeof(struct cxgb3i_gather_list *) +
+					sizeof(struct sk_buff *)),
+				   GFP_KERNEL);
+	if (!ddp) {
+		ddp_log_warn("%s unable to alloc ddp 0x%d, ddp disabled.\n",
+			     tdev->name, ppmax);
+		return;
+	}
+	ddp->gl_map = (struct cxgb3i_gather_list **)(ddp + 1);
+	ddp->gl_skb = (struct sk_buff **)(((char *)ddp->gl_map) +
+					  ppmax *
+					  sizeof(struct cxgb3i_gather_list *));
+	spin_lock_init(&ddp->map_lock);
+	kref_init(&ddp->refcnt);
+
+	ddp->tdev = tdev;
+	ddp->pdev = uinfo.pdev;
+	ddp->max_txsz = min_t(unsigned int, uinfo.max_txsz, ULP2_MAX_PKT_SIZE);
+	ddp->max_rxsz = min_t(unsigned int, uinfo.max_rxsz, ULP2_MAX_PKT_SIZE);
+	ddp->llimit = uinfo.llimit;
+	ddp->ulimit = uinfo.ulimit;
+	ddp->nppods = ppmax;
+	ddp->idx_last = ppmax;
+	ddp->idx_bits = bits;
+	ddp->idx_mask = (1 << bits) - 1;
+	ddp->rsvd_tag_mask = (1 << (bits + PPOD_IDX_SHIFT)) - 1;
+
+	uinfo.tagmask = ddp->idx_mask << PPOD_IDX_SHIFT;
+	for (i = 0; i < DDP_PGIDX_MAX; i++)
+		uinfo.pgsz_factor[i] = ddp_page_order[i];
+	uinfo.ulimit = uinfo.llimit + (ppmax << PPOD_SIZE_SHIFT);
+
+	err = tdev->ctl(tdev, ULP_ISCSI_SET_PARAMS, &uinfo);
+	if (err < 0) {
+		ddp_log_warn("%s unable to set iscsi param err=%d, "
+			      "ddp disabled.\n", tdev->name, err);
+		goto free_ddp_map;
+	}
+
+	tdev->ulp_iscsi = ddp;
+
+	ddp_log_info("tdev 0x%p, nppods %u, bits %u, mask 0x%x,0x%x pkt %u/%u,"
+			" %u/%u.\n",
+			tdev, ppmax, ddp->idx_bits, ddp->idx_mask,
+			ddp->rsvd_tag_mask, ddp->max_txsz, uinfo.max_txsz,
+			ddp->max_rxsz, uinfo.max_rxsz);
+	return;
+
+free_ddp_map:
+	cxgb3i_free_big_mem(ddp);
+}
+
+/**
+ * cxgb3i_ddp_init - initialize ddp functions
+ */
+void cxgb3i_ddp_init(struct t3cdev *tdev)
+{
+	if (page_idx == DDP_PGIDX_MAX) {
+		page_idx = cxgb3i_ddp_find_page_index(PAGE_SIZE);
+
+		if (page_idx == DDP_PGIDX_MAX) {
+			ddp_log_info("system PAGE_SIZE %lu, update hw.\n",
+					PAGE_SIZE);
+			if (cxgb3i_ddp_adjust_page_table() < 0) {
+				ddp_log_info("PAGE_SIZE %lu, ddp disabled.\n",
+						PAGE_SIZE);
+				return;
+			}
+			page_idx = cxgb3i_ddp_find_page_index(PAGE_SIZE);
+		}
+		ddp_log_info("system PAGE_SIZE %lu, ddp idx %u.\n",
+				PAGE_SIZE, page_idx);
+	}
+	ddp_init(tdev);
+}

kernel/drivers/scsi/cxgb3i/cxgb3i_ddp.h

@@ -0,0 +1,311 @@
+/*
+ * cxgb3i_ddp.h: Chelsio S3xx iSCSI DDP Manager.
+ *
+ * Copyright (c) 2008 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)
+ */
+
+#ifndef __CXGB3I_ULP2_DDP_H__
+#define __CXGB3I_ULP2_DDP_H__
+
+#include <linux/vmalloc.h>
+
+/**
+ * struct cxgb3i_tag_format - cxgb3i ulp tag format for an iscsi entity
+ *
+ * @sw_bits:	# of bits used by iscsi software layer
+ * @rsvd_bits:	# of bits used by h/w
+ * @rsvd_shift:	h/w bits shift left
+ * @rsvd_mask:	reserved bit mask
+ */
+struct cxgb3i_tag_format {
+	unsigned char sw_bits;
+	unsigned char rsvd_bits;
+	unsigned char rsvd_shift;
+	unsigned char filler[1];
+	u32 rsvd_mask;
+};
+
+/**
+ * struct cxgb3i_gather_list - cxgb3i direct data placement memory
+ *
+ * @tag:	ddp tag
+ * @length:	total data buffer length
+ * @offset:	initial offset to the 1st page
+ * @nelem:	# of pages
+ * @pages:	page pointers
+ * @phys_addr:	physical address
+ */
+struct cxgb3i_gather_list {
+	u32 tag;
+	unsigned int length;
+	unsigned int offset;
+	unsigned int nelem;
+	struct page **pages;
+	dma_addr_t phys_addr[0];
+};
+
+/**
+ * struct cxgb3i_ddp_info - cxgb3i direct data placement for pdu payload
+ *
+ * @list:	list head to link elements
+ * @refcnt:	ref. count
+ * @tdev:	pointer to t3cdev used by cxgb3 driver
+ * @max_txsz:	max tx packet size for ddp
+ * @max_rxsz:	max rx packet size for ddp
+ * @llimit:	lower bound of the page pod memory
+ * @ulimit:	upper bound of the page pod memory
+ * @nppods:	# of page pod entries
+ * @idx_last:	page pod entry last used
+ * @idx_bits:	# of bits the pagepod index would take
+ * @idx_mask:	pagepod index mask
+ * @rsvd_tag_mask: tag mask
+ * @map_lock:	lock to synchonize access to the page pod map
+ * @gl_map:	ddp memory gather list
+ * @gl_skb:	skb used to program the pagepod
+ */
+struct cxgb3i_ddp_info {
+	struct list_head list;
+	struct kref refcnt;
+	struct t3cdev *tdev;
+	struct pci_dev *pdev;
+	unsigned int max_txsz;
+	unsigned int max_rxsz;
+	unsigned int llimit;
+	unsigned int ulimit;
+	unsigned int nppods;
+	unsigned int idx_last;
+	unsigned char idx_bits;
+	unsigned char filler[3];
+	u32 idx_mask;
+	u32 rsvd_tag_mask;
+	spinlock_t map_lock;
+	struct cxgb3i_gather_list **gl_map;
+	struct sk_buff **gl_skb;
+};
+
+#define ISCSI_PDU_NONPAYLOAD_LEN	312 /* bhs(48) + ahs(256) + digest(8) */
+#define ULP2_MAX_PKT_SIZE	16224
+#define ULP2_MAX_PDU_PAYLOAD	(ULP2_MAX_PKT_SIZE - ISCSI_PDU_NONPAYLOAD_LEN)
+#define PPOD_PAGES_MAX		4
+#define PPOD_PAGES_SHIFT	2	/* 4 pages per pod */
+
+/*
+ * struct pagepod_hdr, pagepod - pagepod format
+ */
+struct pagepod_hdr {
+	u32 vld_tid;
+	u32 pgsz_tag_clr;
+	u32 maxoffset;
+	u32 pgoffset;
+	u64 rsvd;
+};
+
+struct pagepod {
+	struct pagepod_hdr hdr;
+	u64 addr[PPOD_PAGES_MAX + 1];
+};
+
+#define PPOD_SIZE		sizeof(struct pagepod)	/* 64 */
+#define PPOD_SIZE_SHIFT		6
+
+#define PPOD_COLOR_SHIFT	0
+#define PPOD_COLOR_SIZE		6
+#define PPOD_COLOR_MASK		((1 << PPOD_COLOR_SIZE) - 1)
+
+#define PPOD_IDX_SHIFT		PPOD_COLOR_SIZE
+#define PPOD_IDX_MAX_SIZE	24
+
+#define S_PPOD_TID    0
+#define M_PPOD_TID    0xFFFFFF
+#define V_PPOD_TID(x) ((x) << S_PPOD_TID)
+
+#define S_PPOD_VALID    24
+#define V_PPOD_VALID(x) ((x) << S_PPOD_VALID)
+#define F_PPOD_VALID    V_PPOD_VALID(1U)
+
+#define S_PPOD_COLOR    0
+#define M_PPOD_COLOR    0x3F
+#define V_PPOD_COLOR(x) ((x) << S_PPOD_COLOR)
+
+#define S_PPOD_TAG    6
+#define M_PPOD_TAG    0xFFFFFF
+#define V_PPOD_TAG(x) ((x) << S_PPOD_TAG)
+
+#define S_PPOD_PGSZ    30
+#define M_PPOD_PGSZ    0x3
+#define V_PPOD_PGSZ(x) ((x) << S_PPOD_PGSZ)
+
+/*
+ * large memory chunk allocation/release
+ * use vmalloc() if kmalloc() fails
+ */
+static inline void *cxgb3i_alloc_big_mem(unsigned int size,
+					 gfp_t gfp)
+{
+	void *p = kmalloc(size, gfp);
+	if (!p)
+		p = vmalloc(size);
+	if (p)
+		memset(p, 0, size);
+	return p;
+}
+
+static inline void cxgb3i_free_big_mem(void *addr)
+{
+	if (is_vmalloc_addr(addr))
+		vfree(addr);
+	else
+		kfree(addr);
+}
+
+/*
+ * cxgb3i ddp tag are 32 bits, it consists of reserved bits used by h/w and
+ * non-reserved bits that can be used by the iscsi s/w.
+ * The reserved bits are identified by the rsvd_bits and rsvd_shift fields
+ * in struct cxgb3i_tag_format.
+ *
+ * The upper most reserved bit can be used to check if a tag is ddp tag or not:
+ * 	if the bit is 0, the tag is a valid ddp tag
+ */
+
+/**
+ * cxgb3i_is_ddp_tag - check if a given tag is a hw/ddp tag
+ * @tformat: tag format information
+ * @tag: tag to be checked
+ *
+ * return true if the tag is a ddp tag, false otherwise.
+ */
+static inline int cxgb3i_is_ddp_tag(struct cxgb3i_tag_format *tformat, u32 tag)
+{
+	return !(tag & (1 << (tformat->rsvd_bits + tformat->rsvd_shift - 1)));
+}
+
+/**
+ * cxgb3i_sw_tag_usable - check if s/w tag has enough bits left for hw bits
+ * @tformat: tag format information
+ * @sw_tag: s/w tag to be checked
+ *
+ * return true if the tag can be used for hw ddp tag, false otherwise.
+ */
+static inline int cxgb3i_sw_tag_usable(struct cxgb3i_tag_format *tformat,
+					u32 sw_tag)
+{
+	sw_tag >>= (32 - tformat->rsvd_bits);
+	return !sw_tag;
+}
+
+/**
+ * cxgb3i_set_non_ddp_tag - mark a given s/w tag as an invalid ddp tag
+ * @tformat: tag format information
+ * @sw_tag: s/w tag to be checked
+ *
+ * insert 1 at the upper most reserved bit to mark it as an invalid ddp tag.
+ */
+static inline u32 cxgb3i_set_non_ddp_tag(struct cxgb3i_tag_format *tformat,
+					 u32 sw_tag)
+{
+	unsigned char shift = tformat->rsvd_bits + tformat->rsvd_shift - 1;
+	u32 mask = (1 << shift) - 1;
+
+	if (sw_tag && (sw_tag & ~mask)) {
+		u32 v1 = sw_tag & ((1 << shift) - 1);
+		u32 v2 = (sw_tag >> (shift - 1)) << shift;
+
+		return v2 | v1 | 1 << shift;
+	}
+	return sw_tag | 1 << shift;
+}
+
+/**
+ * cxgb3i_ddp_tag_base - shift s/w tag bits so that reserved bits are not used
+ * @tformat: tag format information
+ * @sw_tag: s/w tag to be checked
+ */
+static inline u32 cxgb3i_ddp_tag_base(struct cxgb3i_tag_format *tformat,
+				      u32 sw_tag)
+{
+	u32 mask = (1 << tformat->rsvd_shift) - 1;
+
+	if (sw_tag && (sw_tag & ~mask)) {
+		u32 v1 = sw_tag & mask;
+		u32 v2 = sw_tag >> tformat->rsvd_shift;
+
+		v2 <<= tformat->rsvd_shift + tformat->rsvd_bits;
+		return v2 | v1;
+	}
+	return sw_tag;
+}
+
+/**
+ * cxgb3i_tag_rsvd_bits - get the reserved bits used by the h/w
+ * @tformat: tag format information
+ * @tag: tag to be checked
+ *
+ * return the reserved bits in the tag
+ */
+static inline u32 cxgb3i_tag_rsvd_bits(struct cxgb3i_tag_format *tformat,
+				       u32 tag)
+{
+	if (cxgb3i_is_ddp_tag(tformat, tag))
+		return (tag >> tformat->rsvd_shift) & tformat->rsvd_mask;
+	return 0;
+}
+
+/**
+ * cxgb3i_tag_nonrsvd_bits - get the non-reserved bits used by the s/w
+ * @tformat: tag format information
+ * @tag: tag to be checked
+ *
+ * return the non-reserved bits in the tag.
+ */
+static inline u32 cxgb3i_tag_nonrsvd_bits(struct cxgb3i_tag_format *tformat,
+					  u32 tag)
+{
+	unsigned char shift = tformat->rsvd_bits + tformat->rsvd_shift - 1;
+	u32 v1, v2;
+
+	if (cxgb3i_is_ddp_tag(tformat, tag)) {
+		v1 = tag & ((1 << tformat->rsvd_shift) - 1);
+		v2 = (tag >> (shift + 1)) << tformat->rsvd_shift;
+	} else {
+		u32 mask = (1 << shift) - 1;
+
+		tag &= ~(1 << shift);
+		v1 = tag & mask;
+		v2 = (tag >> 1) & ~mask;
+	}
+	return v1 | v2;
+}
+
+int cxgb3i_ddp_tag_reserve(struct t3cdev *, unsigned int tid,
+			   struct cxgb3i_tag_format *, u32 *tag,
+			   struct cxgb3i_gather_list *, gfp_t gfp);
+void cxgb3i_ddp_tag_release(struct t3cdev *, u32 tag);
+
+struct cxgb3i_gather_list *cxgb3i_ddp_make_gl(unsigned int xferlen,
+				struct scatterlist *sgl,
+				unsigned int sgcnt,
+				struct pci_dev *pdev,
+				gfp_t gfp);
+void cxgb3i_ddp_release_gl(struct cxgb3i_gather_list *gl,
+				struct pci_dev *pdev);
+
+int cxgb3i_setup_conn_host_pagesize(struct t3cdev *, unsigned int tid,
+				    int reply);
+int cxgb3i_setup_conn_pagesize(struct t3cdev *, unsigned int tid, int reply,
+			       unsigned long pgsz);
+int cxgb3i_setup_conn_digest(struct t3cdev *, unsigned int tid,
+				int hcrc, int dcrc, int reply);
+int cxgb3i_ddp_find_page_index(unsigned long pgsz);
+int cxgb3i_adapter_ddp_info(struct t3cdev *, struct cxgb3i_tag_format *,
+			    unsigned int *txsz, unsigned int *rxsz);
+
+void cxgb3i_ddp_init(struct t3cdev *);
+void cxgb3i_ddp_cleanup(struct t3cdev *);
+#endif

kernel/drivers/scsi/cxgb3i/cxgb3i_init.c

@@ -0,0 +1,130 @@
+/* cxgb3i_init.c: Chelsio S3xx iSCSI driver.
+ *
+ * Copyright (c) 2008 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)
+ */
+
+#include "cxgb3i.h"
+
+#define DRV_MODULE_NAME         "cxgb3i"
+#define DRV_MODULE_VERSION	"1.0.2"
+#define DRV_MODULE_RELDATE	"Mar. 2009"
+
+static char version[] =
+	"Chelsio S3xx iSCSI Driver " DRV_MODULE_NAME
+	" v" DRV_MODULE_VERSION " (" DRV_MODULE_RELDATE ")\n";
+
+MODULE_AUTHOR("Karen Xie <kxie@chelsio.com>");
+MODULE_DESCRIPTION("Chelsio S3xx iSCSI Driver");
+MODULE_LICENSE("GPL");
+MODULE_VERSION(DRV_MODULE_VERSION);
+
+static void open_s3_dev(struct t3cdev *);
+static void close_s3_dev(struct t3cdev *);
+static void s3_event_handler(struct t3cdev *tdev, u32 event, u32 port);
+
+static cxgb3_cpl_handler_func cxgb3i_cpl_handlers[NUM_CPL_CMDS];
+static struct cxgb3_client t3c_client = {
+	.name = "iscsi_cxgb3",
+	.handlers = cxgb3i_cpl_handlers,
+	.add = open_s3_dev,
+	.remove = close_s3_dev,
+	.event_handler = s3_event_handler,
+};
+
+/**
+ * open_s3_dev - register with cxgb3 LLD
+ * @t3dev:	cxgb3 adapter instance
+ */
+static void open_s3_dev(struct t3cdev *t3dev)
+{
+	static int vers_printed;
+
+	if (!vers_printed) {
+		printk(KERN_INFO "%s", version);
+		vers_printed = 1;
+	}
+
+	cxgb3i_ddp_init(t3dev);
+	cxgb3i_sdev_add(t3dev, &t3c_client);
+	cxgb3i_adapter_open(t3dev);
+}
+
+/**
+ * close_s3_dev - de-register with cxgb3 LLD
+ * @t3dev:	cxgb3 adapter instance
+ */
+static void close_s3_dev(struct t3cdev *t3dev)
+{
+	cxgb3i_adapter_close(t3dev);
+	cxgb3i_sdev_remove(t3dev);
+	cxgb3i_ddp_cleanup(t3dev);
+}
+
+static void s3_event_handler(struct t3cdev *tdev, u32 event, u32 port)
+{
+	struct cxgb3i_adapter *snic = cxgb3i_adapter_find_by_tdev(tdev);
+
+	cxgb3i_log_info("snic 0x%p, tdev 0x%p, event 0x%x, port 0x%x.\n",
+			snic, tdev, event, port);
+	if (!snic)
+		return;
+
+	switch (event) {
+	case OFFLOAD_STATUS_DOWN:
+		snic->flags |= CXGB3I_ADAPTER_FLAG_RESET;
+		break;
+	case OFFLOAD_STATUS_UP:
+		snic->flags &= ~CXGB3I_ADAPTER_FLAG_RESET;
+		break;
+	}
+}
+
+/**
+ * cxgb3i_init_module - module init entry point
+ *
+ * initialize any driver wide global data structures and register itself
+ *	with the cxgb3 module
+ */
+static int __init cxgb3i_init_module(void)
+{
+	int err;
+
+	err = cxgb3i_sdev_init(cxgb3i_cpl_handlers);
+	if (err < 0)
+		return err;
+
+	err = cxgb3i_iscsi_init();
+	if (err < 0)
+		return err;
+
+	err = cxgb3i_pdu_init();
+	if (err < 0)
+		return err;
+
+	cxgb3_register_client(&t3c_client);
+
+	return 0;
+}
+
+/**
+ * cxgb3i_exit_module - module cleanup/exit entry point
+ *
+ * go through the driver hba list and for each hba, release any resource held.
+ *	and unregisters iscsi transport and the cxgb3 module
+ */
+static void __exit cxgb3i_exit_module(void)
+{
+	cxgb3_unregister_client(&t3c_client);
+	cxgb3i_pdu_cleanup();
+	cxgb3i_iscsi_cleanup();
+	cxgb3i_sdev_cleanup();
+}
+
+module_init(cxgb3i_init_module);
+module_exit(cxgb3i_exit_module);

kernel/drivers/scsi/cxgb3i/cxgb3i_offload.h

@@ -0,0 +1,243 @@
+/*
+ * cxgb3i_offload.h: Chelsio S3xx iscsi offloaded tcp connection management
+ *
+ * Copyright (C) 2003-2008 Chelsio Communications.  All rights reserved.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the LICENSE file included in this
+ * release for licensing terms and conditions.
+ *
+ * Written by:	Dimitris Michailidis (dm@chelsio.com)
+ *		Karen Xie (kxie@chelsio.com)
+ */
+
+#ifndef _CXGB3I_OFFLOAD_H
+#define _CXGB3I_OFFLOAD_H
+
+#include <linux/skbuff.h>
+#include <linux/in.h>
+
+#include "common.h"
+#include "adapter.h"
+#include "t3cdev.h"
+#include "cxgb3_offload.h"
+
+#define cxgb3i_log_error(fmt...) printk(KERN_ERR "cxgb3i: ERR! " fmt)
+#define cxgb3i_log_warn(fmt...)	 printk(KERN_WARNING "cxgb3i: WARN! " fmt)
+#define cxgb3i_log_info(fmt...)  printk(KERN_INFO "cxgb3i: " fmt)
+#define cxgb3i_log_debug(fmt, args...) \
+	printk(KERN_INFO "cxgb3i: %s - " fmt, __func__ , ## args)
+
+/**
+ * struct s3_conn - an iscsi tcp connection structure
+ *
+ * @dev:	net device of with connection
+ * @cdev:	adapter t3cdev for net device
+ * @flags:	see c3cn_flags below
+ * @tid:	connection id assigned by the h/w
+ * @qset:	queue set used by connection
+ * @mss_idx:	Maximum Segment Size table index
+ * @l2t:	ARP resolution entry for offload packets
+ * @wr_max:	maximum in-flight writes
+ * @wr_avail:	number of writes available
+ * @wr_unacked:	writes since last request for completion notification
+ * @wr_pending_head: head of pending write queue
+ * @wr_pending_tail: tail of pending write queue
+ * @cpl_close:	skb for cpl_close_req
+ * @cpl_abort_req: skb for cpl_abort_req
+ * @cpl_abort_rpl: skb for cpl_abort_rpl
+ * @lock:	connection status lock
+ * @refcnt:	reference count on connection
+ * @state:	connection state
+ * @saddr:	source ip/port address
+ * @daddr:	destination ip/port address
+ * @dst_cache:	reference to destination route
+ * @receive_queue: received PDUs
+ * @write_queue: un-pushed pending writes
+ * @retry_timer: retry timer for various operations
+ * @err:	connection error status
+ * @callback_lock: lock for opaque user context
+ * @user_data:	opaque user context
+ * @rcv_nxt:	next receive seq. #
+ * @copied_seq:	head of yet unread data
+ * @rcv_wup:	rcv_nxt on last window update sent
+ * @snd_nxt:	next sequence we send
+ * @snd_una:	first byte we want an ack for
+ * @write_seq:	tail+1 of data held in send buffer
+ */
+struct s3_conn {
+	struct net_device *dev;
+	struct t3cdev *cdev;
+	unsigned long flags;
+	int tid;
+	int qset;
+	int mss_idx;
+	struct l2t_entry *l2t;
+	int wr_max;
+	int wr_avail;
+	int wr_unacked;
+	struct sk_buff *wr_pending_head;
+	struct sk_buff *wr_pending_tail;
+	struct sk_buff *cpl_close;
+	struct sk_buff *cpl_abort_req;
+	struct sk_buff *cpl_abort_rpl;
+	spinlock_t lock;
+	atomic_t refcnt;
+	volatile unsigned int state;
+	struct sockaddr_in saddr;
+	struct sockaddr_in daddr;
+	struct dst_entry *dst_cache;
+	struct sk_buff_head receive_queue;
+	struct sk_buff_head write_queue;
+	struct timer_list retry_timer;
+	int err;
+	rwlock_t callback_lock;
+	void *user_data;
+
+	u32 rcv_nxt;
+	u32 copied_seq;
+	u32 rcv_wup;
+	u32 snd_nxt;
+	u32 snd_una;
+	u32 write_seq;
+};
+
+/*
+ * connection state
+ */
+enum conn_states {
+	C3CN_STATE_CONNECTING = 1,
+	C3CN_STATE_ESTABLISHED,
+	C3CN_STATE_ACTIVE_CLOSE,
+	C3CN_STATE_PASSIVE_CLOSE,
+	C3CN_STATE_CLOSE_WAIT_1,
+	C3CN_STATE_CLOSE_WAIT_2,
+	C3CN_STATE_ABORTING,
+	C3CN_STATE_CLOSED,
+};
+
+static inline unsigned int c3cn_is_closing(const struct s3_conn *c3cn)
+{
+	return c3cn->state >= C3CN_STATE_ACTIVE_CLOSE;
+}
+static inline unsigned int c3cn_is_established(const struct s3_conn *c3cn)
+{
+	return c3cn->state == C3CN_STATE_ESTABLISHED;
+}
+
+/*
+ * Connection flags -- many to track some close related events.
+ */
+enum c3cn_flags {
+	C3CN_ABORT_RPL_RCVD,	/* received one ABORT_RPL_RSS message */
+	C3CN_ABORT_REQ_RCVD,	/* received one ABORT_REQ_RSS message */
+	C3CN_ABORT_RPL_PENDING,	/* expecting an abort reply */
+	C3CN_TX_DATA_SENT,	/* already sent a TX_DATA WR */
+	C3CN_ACTIVE_CLOSE_NEEDED,	/* need to be closed */
+	C3CN_OFFLOAD_DOWN	/* offload function off */
+};
+
+/**
+ * cxgb3i_sdev_data - Per adapter data.
+ * Linked off of each Ethernet device port on the adapter.
+ * Also available via the t3cdev structure since we have pointers to our port
+ * net_device's there ...
+ *
+ * @list:	list head to link elements
+ * @cdev:	t3cdev adapter
+ * @client:	CPL client pointer
+ * @ports:	array of adapter ports
+ * @sport_next: next port
+ * @sport_conn:	source port connection
+ */
+struct cxgb3i_sdev_data {
+	struct list_head list;
+	struct t3cdev *cdev;
+	struct cxgb3_client *client;
+	struct adap_ports ports;
+	spinlock_t lock;
+	unsigned int sport_next;
+	struct s3_conn *sport_conn[0];
+};
+#define NDEV2CDATA(ndev) (*(struct cxgb3i_sdev_data **)&(ndev)->ec_ptr)
+#define CXGB3_SDEV_DATA(cdev) NDEV2CDATA((cdev)->lldev)
+
+void cxgb3i_sdev_cleanup(void);
+int cxgb3i_sdev_init(cxgb3_cpl_handler_func *);
+void cxgb3i_sdev_add(struct t3cdev *, struct cxgb3_client *);
+void cxgb3i_sdev_remove(struct t3cdev *);
+
+struct s3_conn *cxgb3i_c3cn_create(void);
+int cxgb3i_c3cn_connect(struct net_device *, struct s3_conn *,
+			struct sockaddr_in *);
+void cxgb3i_c3cn_rx_credits(struct s3_conn *, int);
+int cxgb3i_c3cn_send_pdus(struct s3_conn *, struct sk_buff *);
+void cxgb3i_c3cn_release(struct s3_conn *);
+
+/**
+ * cxgb3_skb_cb - control block for received pdu state and ULP mode management.
+ *
+ * @flag:	see C3CB_FLAG_* below
+ * @ulp_mode:	ULP mode/submode of sk_buff
+ * @seq:	tcp sequence number
+ */
+struct cxgb3_skb_rx_cb {
+	__u32 ddigest;			/* data digest */
+	__u32 pdulen;			/* recovered pdu length */
+};
+
+struct cxgb3_skb_tx_cb {
+	struct sk_buff *wr_next;	/* next wr */
+};
+
+struct cxgb3_skb_cb {
+	__u8 flags;
+	__u8 ulp_mode;
+	__u32 seq;
+	union {
+		struct cxgb3_skb_rx_cb rx;
+		struct cxgb3_skb_tx_cb tx;
+	};
+};
+
+#define CXGB3_SKB_CB(skb)	((struct cxgb3_skb_cb *)&((skb)->cb[0]))
+#define skb_flags(skb)		(CXGB3_SKB_CB(skb)->flags)
+#define skb_ulp_mode(skb)	(CXGB3_SKB_CB(skb)->ulp_mode)
+#define skb_tcp_seq(skb)	(CXGB3_SKB_CB(skb)->seq)
+#define skb_rx_ddigest(skb)	(CXGB3_SKB_CB(skb)->rx.ddigest)
+#define skb_rx_pdulen(skb)	(CXGB3_SKB_CB(skb)->rx.pdulen)
+#define skb_tx_wr_next(skb)	(CXGB3_SKB_CB(skb)->tx.wr_next)
+
+enum c3cb_flags {
+	C3CB_FLAG_NEED_HDR = 1 << 0,	/* packet needs a TX_DATA_WR header */
+	C3CB_FLAG_NO_APPEND = 1 << 1,	/* don't grow this skb */
+	C3CB_FLAG_COMPL = 1 << 2,	/* request WR completion */
+};
+
+/**
+ * sge_opaque_hdr -
+ * Opaque version of structure the SGE stores at skb->head of TX_DATA packets
+ * and for which we must reserve space.
+ */
+struct sge_opaque_hdr {
+	void *dev;
+	dma_addr_t addr[MAX_SKB_FRAGS + 1];
+};
+
+/* for TX: a skb must have a headroom of at least TX_HEADER_LEN bytes */
+#define TX_HEADER_LEN \
+		(sizeof(struct tx_data_wr) + sizeof(struct sge_opaque_hdr))
+#define SKB_TX_HEADROOM		SKB_MAX_HEAD(TX_HEADER_LEN)
+
+/*
+ * get and set private ip for iscsi traffic
+ */
+#define cxgb3i_get_private_ipv4addr(ndev) \
+	(((struct port_info *)(netdev_priv(ndev)))->iscsi_ipv4addr)
+#define cxgb3i_set_private_ipv4addr(ndev, addr) \
+	(((struct port_info *)(netdev_priv(ndev)))->iscsi_ipv4addr) = addr
+
+/* max. connections per adapter */
+#define CXGB3I_MAX_CONN		16384
+#endif /* _CXGB3_OFFLOAD_H */

kernel/drivers/scsi/cxgb3i/cxgb3i_pdu.c

@@ -0,0 +1,496 @@
+/*
+ * cxgb3i_pdu.c: Chelsio S3xx iSCSI driver.
+ *
+ * Copyright (c) 2008 Chelsio Communications, Inc.
+ * Copyright (c) 2008 Mike Christie
+ * Copyright (c) 2008 Red Hat, Inc.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.
+ *
+ * Written by: Karen Xie (kxie@chelsio.com)
+ */
+
+#include <linux/skbuff.h>
+#include <linux/crypto.h>
+#include <scsi/scsi_cmnd.h>
+#include <scsi/scsi_host.h>
+
+#include "cxgb3i.h"
+#include "cxgb3i_pdu.h"
+
+#ifdef __DEBUG_CXGB3I_RX__
+#define cxgb3i_rx_debug		cxgb3i_log_debug
+#else
+#define cxgb3i_rx_debug(fmt...)
+#endif
+
+#ifdef __DEBUG_CXGB3I_TX__
+#define cxgb3i_tx_debug		cxgb3i_log_debug
+#else
+#define cxgb3i_tx_debug(fmt...)
+#endif
+
+/* always allocate rooms for AHS */
+#define SKB_TX_PDU_HEADER_LEN	\
+	(sizeof(struct iscsi_hdr) + ISCSI_MAX_AHS_SIZE)
+static unsigned int skb_extra_headroom;
+static struct page *pad_page;
+
+/*
+ * pdu receive, interact with libiscsi_tcp
+ */
+static inline int read_pdu_skb(struct iscsi_conn *conn, struct sk_buff *skb,
+			       unsigned int offset, int offloaded)
+{
+	int status = 0;
+	int bytes_read;
+
+	bytes_read = iscsi_tcp_recv_skb(conn, skb, offset, offloaded, &status);
+	switch (status) {
+	case ISCSI_TCP_CONN_ERR:
+		return -EIO;
+	case ISCSI_TCP_SUSPENDED:
+		/* no transfer - just have caller flush queue */
+		return bytes_read;
+	case ISCSI_TCP_SKB_DONE:
+		/*
+		 * pdus should always fit in the skb and we should get
+		 * segment done notifcation.
+		 */
+		iscsi_conn_printk(KERN_ERR, conn, "Invalid pdu or skb.");
+		return -EFAULT;
+	case ISCSI_TCP_SEGMENT_DONE:
+		return bytes_read;
+	default:
+		iscsi_conn_printk(KERN_ERR, conn, "Invalid iscsi_tcp_recv_skb "
+				  "status %d\n", status);
+		return -EINVAL;
+	}
+}
+
+static int cxgb3i_conn_read_pdu_skb(struct iscsi_conn *conn,
+				    struct sk_buff *skb)
+{
+	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
+	bool offloaded = 0;
+	unsigned int offset;
+	int rc;
+
+	cxgb3i_rx_debug("conn 0x%p, skb 0x%p, len %u, flag 0x%x.\n",
+			conn, skb, skb->len, skb_ulp_mode(skb));
+
+	if (!iscsi_tcp_recv_segment_is_hdr(tcp_conn)) {
+		iscsi_conn_failure(conn, ISCSI_ERR_PROTO);
+		return -EIO;
+	}
+
+	if (conn->hdrdgst_en && (skb_ulp_mode(skb) & ULP2_FLAG_HCRC_ERROR)) {
+		iscsi_conn_failure(conn, ISCSI_ERR_HDR_DGST);
+		return -EIO;
+	}
+
+	if (conn->datadgst_en && (skb_ulp_mode(skb) & ULP2_FLAG_DCRC_ERROR)) {
+		iscsi_conn_failure(conn, ISCSI_ERR_DATA_DGST);
+		return -EIO;
+	}
+
+	/* iscsi hdr */
+	rc = read_pdu_skb(conn, skb, 0, 0);
+	if (rc <= 0)
+		return rc;
+
+	if (iscsi_tcp_recv_segment_is_hdr(tcp_conn))
+		return 0;
+
+	offset = rc;
+	if (conn->hdrdgst_en)
+		offset += ISCSI_DIGEST_SIZE;
+
+	/* iscsi data */
+	if (skb_ulp_mode(skb) & ULP2_FLAG_DATA_DDPED) {
+		cxgb3i_rx_debug("skb 0x%p, opcode 0x%x, data %u, ddp'ed, "
+				"itt 0x%x.\n",
+				skb,
+				tcp_conn->in.hdr->opcode & ISCSI_OPCODE_MASK,
+				tcp_conn->in.datalen,
+				ntohl(tcp_conn->in.hdr->itt));
+		offloaded = 1;
+	} else {
+		cxgb3i_rx_debug("skb 0x%p, opcode 0x%x, data %u, NOT ddp'ed, "
+				"itt 0x%x.\n",
+				skb,
+				tcp_conn->in.hdr->opcode & ISCSI_OPCODE_MASK,
+				tcp_conn->in.datalen,
+				ntohl(tcp_conn->in.hdr->itt));
+		offset += sizeof(struct cpl_iscsi_hdr_norss);
+	}
+
+	rc = read_pdu_skb(conn, skb, offset, offloaded);
+	if (rc < 0)
+		return rc;
+	else
+		return 0;
+}
+
+/*
+ * pdu transmit, interact with libiscsi_tcp
+ */
+static inline void tx_skb_setmode(struct sk_buff *skb, int hcrc, int dcrc)
+{
+	u8 submode = 0;
+
+	if (hcrc)
+		submode |= 1;
+	if (dcrc)
+		submode |= 2;
+	skb_ulp_mode(skb) = (ULP_MODE_ISCSI << 4) | submode;
+}
+
+void cxgb3i_conn_cleanup_task(struct iscsi_task *task)
+{
+	struct cxgb3i_task_data *tdata = task->dd_data +
+					sizeof(struct iscsi_tcp_task);
+
+	/* never reached the xmit task callout */
+	if (tdata->skb)
+		__kfree_skb(tdata->skb);
+	memset(tdata, 0, sizeof(struct cxgb3i_task_data));
+
+	/* MNC - Do we need a check in case this is called but
+	 * cxgb3i_conn_alloc_pdu has never been called on the task */
+	cxgb3i_release_itt(task, task->hdr_itt);
+	iscsi_tcp_cleanup_task(task);
+}
+
+static int sgl_seek_offset(struct scatterlist *sgl, unsigned int sgcnt,
+				unsigned int offset, unsigned int *off,
+				struct scatterlist **sgp)
+{
+	int i;
+	struct scatterlist *sg;
+
+	for_each_sg(sgl, sg, sgcnt, i) {
+		if (offset < sg->length) {
+			*off = offset;
+			*sgp = sg;
+			return 0;
+		}
+		offset -= sg->length;
+	}
+	return -EFAULT;
+}
+
+static int sgl_read_to_frags(struct scatterlist *sg, unsigned int sgoffset,
+				unsigned int dlen, skb_frag_t *frags,
+				int frag_max)
+{
+	unsigned int datalen = dlen;
+	unsigned int sglen = sg->length - sgoffset;
+	struct page *page = sg_page(sg);
+	int i;
+
+	i = 0;
+	do {
+		unsigned int copy;
+
+		if (!sglen) {
+			sg = sg_next(sg);
+			if (!sg) {
+				cxgb3i_log_error("%s, sg NULL, len %u/%u.\n",
+						 __func__, datalen, dlen);
+				return -EINVAL;
+			}
+			sgoffset = 0;
+			sglen = sg->length;
+			page = sg_page(sg);
+
+		}
+		copy = min(datalen, sglen);
+		if (i && page == frags[i - 1].page &&
+		    sgoffset + sg->offset ==
+			frags[i - 1].page_offset + frags[i - 1].size) {
+			frags[i - 1].size += copy;
+		} else {
+			if (i >= frag_max) {
+				cxgb3i_log_error("%s, too many pages %u, "
+						 "dlen %u.\n", __func__,
+						 frag_max, dlen);
+				return -EINVAL;
+			}
+
+			frags[i].page = page;
+			frags[i].page_offset = sg->offset + sgoffset;
+			frags[i].size = copy;
+			i++;
+		}
+		datalen -= copy;
+		sgoffset += copy;
+		sglen -= copy;
+	} while (datalen);
+
+	return i;
+}
+
+int cxgb3i_conn_alloc_pdu(struct iscsi_task *task, u8 opcode)
+{
+	struct iscsi_conn *conn = task->conn;
+	struct iscsi_tcp_task *tcp_task = task->dd_data;
+	struct cxgb3i_task_data *tdata = task->dd_data + sizeof(*tcp_task);
+	struct scsi_cmnd *sc = task->sc;
+	int headroom = SKB_TX_PDU_HEADER_LEN;
+
+	tcp_task->dd_data = tdata;
+	task->hdr = NULL;
+
+	/* write command, need to send data pdus */
+	if (skb_extra_headroom && (opcode == ISCSI_OP_SCSI_DATA_OUT ||
+	    (opcode == ISCSI_OP_SCSI_CMD &&
+	    (scsi_bidi_cmnd(sc) || sc->sc_data_direction == DMA_TO_DEVICE))))
+		headroom += min(skb_extra_headroom, conn->max_xmit_dlength);
+
+	tdata->skb = alloc_skb(TX_HEADER_LEN + headroom, GFP_ATOMIC);
+	if (!tdata->skb)
+		return -ENOMEM;
+	skb_reserve(tdata->skb, TX_HEADER_LEN);
+
+	cxgb3i_tx_debug("task 0x%p, opcode 0x%x, skb 0x%p.\n",
+			task, opcode, tdata->skb);
+
+	task->hdr = (struct iscsi_hdr *)tdata->skb->data;
+	task->hdr_max = SKB_TX_PDU_HEADER_LEN;
+
+	/* data_out uses scsi_cmd's itt */
+	if (opcode != ISCSI_OP_SCSI_DATA_OUT)
+		cxgb3i_reserve_itt(task, &task->hdr->itt);
+
+	return 0;
+}
+
+int cxgb3i_conn_init_pdu(struct iscsi_task *task, unsigned int offset,
+			      unsigned int count)
+{
+	struct iscsi_conn *conn = task->conn;
+	struct iscsi_tcp_task *tcp_task = task->dd_data;
+	struct cxgb3i_task_data *tdata = tcp_task->dd_data;
+	struct sk_buff *skb = tdata->skb;
+	unsigned int datalen = count;
+	int i, padlen = iscsi_padding(count);
+	struct page *pg;
+
+	cxgb3i_tx_debug("task 0x%p,0x%p, offset %u, count %u, skb 0x%p.\n",
+			task, task->sc, offset, count, skb);
+
+	skb_put(skb, task->hdr_len);
+	tx_skb_setmode(skb, conn->hdrdgst_en, datalen ? conn->datadgst_en : 0);
+	if (!count)
+		return 0;
+
+	if (task->sc) {
+		struct scsi_data_buffer *sdb = scsi_out(task->sc);
+		struct scatterlist *sg = NULL;
+		int err;
+
+		tdata->offset = offset;
+		tdata->count = count;
+		err = sgl_seek_offset(sdb->table.sgl, sdb->table.nents,
+					tdata->offset, &tdata->sgoffset, &sg);
+		if (err < 0) {
+			cxgb3i_log_warn("tpdu, sgl %u, bad offset %u/%u.\n",
+					sdb->table.nents, tdata->offset,
+					sdb->length);
+			return err;
+		}
+		err = sgl_read_to_frags(sg, tdata->sgoffset, tdata->count,
+					tdata->frags, MAX_PDU_FRAGS);
+		if (err < 0) {
+			cxgb3i_log_warn("tpdu, sgl %u, bad offset %u + %u.\n",
+					sdb->table.nents, tdata->offset,
+					tdata->count);
+			return err;
+		}
+		tdata->nr_frags = err;
+
+		if (tdata->nr_frags > MAX_SKB_FRAGS ||
+		    (padlen && tdata->nr_frags == MAX_SKB_FRAGS)) {
+			char *dst = skb->data + task->hdr_len;
+			skb_frag_t *frag = tdata->frags;
+
+			/* data fits in the skb's headroom */
+			for (i = 0; i < tdata->nr_frags; i++, frag++) {
+				char *src = kmap_atomic(frag->page,
+							KM_SOFTIRQ0);
+
+				memcpy(dst, src+frag->page_offset, frag->size);
+				dst += frag->size;
+				kunmap_atomic(src, KM_SOFTIRQ0);
+			}
+			if (padlen) {
+				memset(dst, 0, padlen);
+				padlen = 0;
+			}
+			skb_put(skb, count + padlen);
+		} else {
+			/* data fit into frag_list */
+			for (i = 0; i < tdata->nr_frags; i++)
+				get_page(tdata->frags[i].page);
+
+			memcpy(skb_shinfo(skb)->frags, tdata->frags,
+				sizeof(skb_frag_t) * tdata->nr_frags);
+			skb_shinfo(skb)->nr_frags = tdata->nr_frags;
+			skb->len += count;
+			skb->data_len += count;
+			skb->truesize += count;
+		}
+
+	} else {
+		pg = virt_to_page(task->data);
+
+		get_page(pg);
+		skb_fill_page_desc(skb, 0, pg, offset_in_page(task->data),
+					count);
+		skb->len += count;
+		skb->data_len += count;
+		skb->truesize += count;
+	}
+
+	if (padlen) {
+		i = skb_shinfo(skb)->nr_frags;
+		get_page(pad_page);
+		skb_fill_page_desc(skb, skb_shinfo(skb)->nr_frags, pad_page, 0,
+				 padlen);
+
+		skb->data_len += padlen;
+		skb->truesize += padlen;
+		skb->len += padlen;
+	}
+
+	return 0;
+}
+
+int cxgb3i_conn_xmit_pdu(struct iscsi_task *task)
+{
+	struct iscsi_tcp_conn *tcp_conn = task->conn->dd_data;
+	struct cxgb3i_conn *cconn = tcp_conn->dd_data;
+	struct iscsi_tcp_task *tcp_task = task->dd_data;
+	struct cxgb3i_task_data *tdata = tcp_task->dd_data;
+	struct sk_buff *skb = tdata->skb;
+	unsigned int datalen;
+	int err;
+
+	if (!skb)
+		return 0;
+
+	datalen = skb->data_len;
+	tdata->skb = NULL;
+	err = cxgb3i_c3cn_send_pdus(cconn->cep->c3cn, skb);
+	if (err > 0) {
+		int pdulen = err;
+
+	cxgb3i_tx_debug("task 0x%p, skb 0x%p, len %u/%u, rv %d.\n",
+			task, skb, skb->len, skb->data_len, err);
+
+		if (task->conn->hdrdgst_en)
+			pdulen += ISCSI_DIGEST_SIZE;
+		if (datalen && task->conn->datadgst_en)
+			pdulen += ISCSI_DIGEST_SIZE;
+
+		task->conn->txdata_octets += pdulen;
+		return 0;
+	}
+
+	if (err == -EAGAIN || err == -ENOBUFS) {
+		/* reset skb to send when we are called again */
+		tdata->skb = skb;
+		return err;
+	}
+
+	kfree_skb(skb);
+	cxgb3i_tx_debug("itt 0x%x, skb 0x%p, len %u/%u, xmit err %d.\n",
+			task->itt, skb, skb->len, skb->data_len, err);
+	iscsi_conn_printk(KERN_ERR, task->conn, "xmit err %d.\n", err);
+	iscsi_conn_failure(task->conn, ISCSI_ERR_XMIT_FAILED);
+	return err;
+}
+
+int cxgb3i_pdu_init(void)
+{
+	if (SKB_TX_HEADROOM > (512 * MAX_SKB_FRAGS))
+		skb_extra_headroom = SKB_TX_HEADROOM;
+	pad_page = alloc_page(GFP_KERNEL);
+	if (!pad_page)
+		return -ENOMEM;
+	memset(page_address(pad_page), 0, PAGE_SIZE);
+	return 0;
+}
+
+void cxgb3i_pdu_cleanup(void)
+{
+	if (pad_page) {
+		__free_page(pad_page);
+		pad_page = NULL;
+	}
+}
+
+void cxgb3i_conn_pdu_ready(struct s3_conn *c3cn)
+{
+	struct sk_buff *skb;
+	unsigned int read = 0;
+	struct iscsi_conn *conn = c3cn->user_data;
+	int err = 0;
+
+	cxgb3i_rx_debug("cn 0x%p.\n", c3cn);
+
+	read_lock(&c3cn->callback_lock);
+	if (unlikely(!conn || conn->suspend_rx)) {
+		cxgb3i_rx_debug("conn 0x%p, id %d, suspend_rx %lu!\n",
+				conn, conn ? conn->id : 0xFF,
+				conn ? conn->suspend_rx : 0xFF);
+		read_unlock(&c3cn->callback_lock);
+		return;
+	}
+	skb = skb_peek(&c3cn->receive_queue);
+	while (!err && skb) {
+		__skb_unlink(skb, &c3cn->receive_queue);
+		read += skb_rx_pdulen(skb);
+		cxgb3i_rx_debug("conn 0x%p, cn 0x%p, rx skb 0x%p, pdulen %u.\n",
+				conn, c3cn, skb, skb_rx_pdulen(skb));
+		err = cxgb3i_conn_read_pdu_skb(conn, skb);
+		__kfree_skb(skb);
+		skb = skb_peek(&c3cn->receive_queue);
+	}
+	read_unlock(&c3cn->callback_lock);
+	if (c3cn) {
+		c3cn->copied_seq += read;
+		cxgb3i_c3cn_rx_credits(c3cn, read);
+	}
+	conn->rxdata_octets += read;
+
+	if (err) {
+		cxgb3i_log_info("conn 0x%p rx failed err %d.\n", conn, err);
+		iscsi_conn_failure(conn, ISCSI_ERR_CONN_FAILED);
+	}
+}
+
+void cxgb3i_conn_tx_open(struct s3_conn *c3cn)
+{
+	struct iscsi_conn *conn = c3cn->user_data;
+
+	cxgb3i_tx_debug("cn 0x%p.\n", c3cn);
+	if (conn) {
+		cxgb3i_tx_debug("cn 0x%p, cid %d.\n", c3cn, conn->id);
+		iscsi_conn_queue_work(conn);
+	}
+}
+
+void cxgb3i_conn_closing(struct s3_conn *c3cn)
+{
+	struct iscsi_conn *conn;
+
+	read_lock(&c3cn->callback_lock);
+	conn = c3cn->user_data;
+	if (conn && c3cn->state != C3CN_STATE_ESTABLISHED)
+		iscsi_conn_failure(conn, ISCSI_ERR_CONN_FAILED);
+	read_unlock(&c3cn->callback_lock);
+}

kernel/drivers/scsi/cxgb3i/cxgb3i_pdu.h

@@ -0,0 +1,59 @@
+/*
+ * cxgb3i_ulp2.h: Chelsio S3xx iSCSI driver.
+ *
+ * Copyright (c) 2008 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)
+ */
+
+#ifndef __CXGB3I_ULP2_PDU_H__
+#define __CXGB3I_ULP2_PDU_H__
+
+struct cpl_iscsi_hdr_norss {
+	union opcode_tid ot;
+	u16 pdu_len_ddp;
+	u16 len;
+	u32 seq;
+	u16 urg;
+	u8 rsvd;
+	u8 status;
+};
+
+struct cpl_rx_data_ddp_norss {
+	union opcode_tid ot;
+	u16 urg;
+	u16 len;
+	u32 seq;
+	u32 nxt_seq;
+	u32 ulp_crc;
+	u32 ddp_status;
+};
+
+#define RX_DDP_STATUS_IPP_SHIFT		27	/* invalid pagepod */
+#define RX_DDP_STATUS_TID_SHIFT		26	/* tid mismatch */
+#define RX_DDP_STATUS_COLOR_SHIFT	25	/* color mismatch */
+#define RX_DDP_STATUS_OFFSET_SHIFT	24	/* offset mismatch */
+#define RX_DDP_STATUS_ULIMIT_SHIFT	23	/* ulimit error */
+#define RX_DDP_STATUS_TAG_SHIFT		22	/* tag mismatch */
+#define RX_DDP_STATUS_DCRC_SHIFT	21	/* dcrc error */
+#define RX_DDP_STATUS_HCRC_SHIFT	20	/* hcrc error */
+#define RX_DDP_STATUS_PAD_SHIFT		19	/* pad error */
+#define RX_DDP_STATUS_PPP_SHIFT		18	/* pagepod parity error */
+#define RX_DDP_STATUS_LLIMIT_SHIFT	17	/* llimit error */
+#define RX_DDP_STATUS_DDP_SHIFT		16	/* ddp'able */
+#define RX_DDP_STATUS_PMM_SHIFT		15	/* pagepod mismatch */
+
+#define ULP2_FLAG_DATA_READY		0x1
+#define ULP2_FLAG_DATA_DDPED		0x2
+#define ULP2_FLAG_HCRC_ERROR		0x10
+#define ULP2_FLAG_DCRC_ERROR		0x20
+#define ULP2_FLAG_PAD_ERROR		0x40
+
+void cxgb3i_conn_closing(struct s3_conn *c3cn);
+void cxgb3i_conn_pdu_ready(struct s3_conn *c3cn);
+void cxgb3i_conn_tx_open(struct s3_conn *c3cn);
+#endif