iscsi_tcp.c

/*
 * iSCSI Initiator over TCP/IP Data-Path
 *
 * Copyright (C) 2004 Dmitry Yusupov
 * Copyright (C) 2004 Alex Aizman
 * Copyright (C) 2005 - 2006 Mike Christie
 * Copyright (C) 2006 Red Hat, Inc.  All rights reserved.
 * maintained by open-iscsi@googlegroups.com
 *
 * 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; either version 2 of the License, or
 * (at your option) any later version.
 *
 * 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 GNU
 * General Public License for more details.
 *
 * See the file COPYING included with this distribution for more details.
 *
 * Credits:
 *	Christoph Hellwig
 *	FUJITA Tomonori
 *	Arne Redlich
 *	Zhenyu Wang
 */

#include <linux/types.h>
#include <linux/list.h>
#include <linux/inet.h>
#include <linux/file.h>
#include <linux/blkdev.h>
#include <linux/crypto.h>
#include <linux/delay.h>
#include <linux/kfifo.h>
#include <linux/scatterlist.h>
#include <net/tcp.h>
#include <scsi/scsi_cmnd.h>
#include <scsi/scsi_device.h>
#include <scsi/scsi_host.h>
#include <scsi/scsi.h>
#include <scsi/scsi_transport_iscsi.h>

#include "iscsi_tcp.h"

MODULE_AUTHOR("Dmitry Yusupov <dmitry_yus@yahoo.com>, "
	      "Alex Aizman <itn780@yahoo.com>");
MODULE_DESCRIPTION("iSCSI/TCP data-path");
MODULE_LICENSE("GPL");
/* #define DEBUG_TCP */
#define DEBUG_ASSERT

#ifdef DEBUG_TCP
#define debug_tcp(fmt...) printk(KERN_INFO "tcp: " fmt)
#else
#define debug_tcp(fmt...)
#endif

#ifndef DEBUG_ASSERT
#ifdef BUG_ON
#undef BUG_ON
#endif
#define BUG_ON(expr)
#endif

static unsigned int iscsi_max_lun = 512;
module_param_named(max_lun, iscsi_max_lun, uint, S_IRUGO);

static inline void
iscsi_buf_init_iov(struct iscsi_buf *ibuf, char *vbuf, int size)
{
	sg_init_one(&ibuf->sg, vbuf, size);
	ibuf->sent = 0;
	ibuf->use_sendmsg = 1;
}

static inline void
iscsi_buf_init_sg(struct iscsi_buf *ibuf, struct scatterlist *sg)
{
	sg_init_table(&ibuf->sg, 1);
	sg_set_page(&ibuf->sg, sg_page(sg), sg->length, sg->offset);
	/*
	 * Fastpath: sg element fits into single page
	 */
	if (sg->length + sg->offset <= PAGE_SIZE && !PageSlab(sg_page(sg)))
		ibuf->use_sendmsg = 0;
	else
		ibuf->use_sendmsg = 1;
	ibuf->sent = 0;
}

static inline int
iscsi_buf_left(struct iscsi_buf *ibuf)
{
	int rc;

	rc = ibuf->sg.length - ibuf->sent;
	BUG_ON(rc < 0);
	return rc;
}

static inline void
iscsi_hdr_digest(struct iscsi_conn *conn, struct iscsi_buf *buf,
		 u8* crc)
{
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;

	crypto_hash_digest(&tcp_conn->tx_hash, &buf->sg, buf->sg.length, crc);
	buf->sg.length += sizeof(u32);
}

static inline int
iscsi_hdr_extract(struct iscsi_tcp_conn *tcp_conn)
{
	struct sk_buff *skb = tcp_conn->in.skb;

	tcp_conn->in.zero_copy_hdr = 0;

	if (tcp_conn->in.copy >= tcp_conn->hdr_size &&
	    tcp_conn->in_progress == IN_PROGRESS_WAIT_HEADER) {
		/*
		 * Zero-copy PDU Header: using connection context
		 * to store header pointer.
		 */
		if (skb_shinfo(skb)->frag_list == NULL &&
		    !skb_shinfo(skb)->nr_frags) {
			tcp_conn->in.hdr = (struct iscsi_hdr *)
				((char*)skb->data + tcp_conn->in.offset);
			tcp_conn->in.zero_copy_hdr = 1;
		} else {
			/* ignoring return code since we checked
			 * in.copy before */
			skb_copy_bits(skb, tcp_conn->in.offset,
				&tcp_conn->hdr, tcp_conn->hdr_size);
			tcp_conn->in.hdr = &tcp_conn->hdr;
		}
		tcp_conn->in.offset += tcp_conn->hdr_size;
		tcp_conn->in.copy -= tcp_conn->hdr_size;
	} else {
		int hdr_remains;
		int copylen;

		/*
		 * PDU header scattered across SKB's,
		 * copying it... This'll happen quite rarely.
		 */

		if (tcp_conn->in_progress == IN_PROGRESS_WAIT_HEADER)
			tcp_conn->in.hdr_offset = 0;

		hdr_remains = tcp_conn->hdr_size - tcp_conn->in.hdr_offset;
		BUG_ON(hdr_remains <= 0);

		copylen = min(tcp_conn->in.copy, hdr_remains);
		skb_copy_bits(skb, tcp_conn->in.offset,
			(char*)&tcp_conn->hdr + tcp_conn->in.hdr_offset,
			copylen);

		debug_tcp("PDU gather offset %d bytes %d in.offset %d "
		       "in.copy %d\n", tcp_conn->in.hdr_offset, copylen,
		       tcp_conn->in.offset, tcp_conn->in.copy);

		tcp_conn->in.offset += copylen;
		tcp_conn->in.copy -= copylen;
		if (copylen < hdr_remains)  {
			tcp_conn->in_progress = IN_PROGRESS_HEADER_GATHER;
			tcp_conn->in.hdr_offset += copylen;
		        return -EAGAIN;
		}
		tcp_conn->in.hdr = &tcp_conn->hdr;
		tcp_conn->discontiguous_hdr_cnt++;
	        tcp_conn->in_progress = IN_PROGRESS_WAIT_HEADER;
	}

	return 0;
}

/*
 * must be called with session lock
 */
static void
iscsi_tcp_cleanup_ctask(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask)
{
	struct iscsi_tcp_cmd_task *tcp_ctask = ctask->dd_data;
	struct iscsi_r2t_info *r2t;
	struct scsi_cmnd *sc;

	/* flush ctask's r2t queues */
	while (__kfifo_get(tcp_ctask->r2tqueue, (void*)&r2t, sizeof(void*))) {
		__kfifo_put(tcp_ctask->r2tpool.queue, (void*)&r2t,
			    sizeof(void*));
		debug_scsi("iscsi_tcp_cleanup_ctask pending r2t dropped\n");
	}

	sc = ctask->sc;
	if (unlikely(!sc))
		return;

	tcp_ctask->xmstate = XMSTATE_VALUE_IDLE;
	tcp_ctask->r2t = NULL;
}

/**
 * iscsi_data_rsp - SCSI Data-In Response processing
 * @conn: iscsi connection
 * @ctask: scsi command task
 **/
static int
iscsi_data_rsp(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask)
{
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
	struct iscsi_tcp_cmd_task *tcp_ctask = ctask->dd_data;
	struct iscsi_data_rsp *rhdr = (struct iscsi_data_rsp *)tcp_conn->in.hdr;
	struct iscsi_session *session = conn->session;
	struct scsi_cmnd *sc = ctask->sc;
	int datasn = be32_to_cpu(rhdr->datasn);

	iscsi_update_cmdsn(session, (struct iscsi_nopin*)rhdr);
	/*
	 * setup Data-In byte counter (gets decremented..)
	 */
	ctask->data_count = tcp_conn->in.datalen;

	if (tcp_conn->in.datalen == 0)
		return 0;

	if (tcp_ctask->exp_datasn != datasn) {
		debug_tcp("%s: ctask->exp_datasn(%d) != rhdr->datasn(%d)\n",
		          __FUNCTION__, tcp_ctask->exp_datasn, datasn);
		return ISCSI_ERR_DATASN;
	}

	tcp_ctask->exp_datasn++;

	tcp_ctask->data_offset = be32_to_cpu(rhdr->offset);
	if (tcp_ctask->data_offset + tcp_conn->in.datalen > scsi_bufflen(sc)) {
		debug_tcp("%s: data_offset(%d) + data_len(%d) > total_length_in(%d)\n",
		          __FUNCTION__, tcp_ctask->data_offset,
		          tcp_conn->in.datalen, scsi_bufflen(sc));
		return ISCSI_ERR_DATA_OFFSET;
	}

	if (rhdr->flags & ISCSI_FLAG_DATA_STATUS) {
		conn->exp_statsn = be32_to_cpu(rhdr->statsn) + 1;
		if (rhdr->flags & ISCSI_FLAG_DATA_UNDERFLOW) {
			int res_count = be32_to_cpu(rhdr->residual_count);

			if (res_count > 0 &&
			    res_count <= scsi_bufflen(sc)) {
				scsi_set_resid(sc, res_count);
				sc->result = (DID_OK << 16) | rhdr->cmd_status;
			} else
				sc->result = (DID_BAD_TARGET << 16) |
					rhdr->cmd_status;
		} else if (rhdr->flags & ISCSI_FLAG_DATA_OVERFLOW) {
			scsi_set_resid(sc, be32_to_cpu(rhdr->residual_count));
			sc->result = (DID_OK << 16) | rhdr->cmd_status;
		} else
			sc->result = (DID_OK << 16) | rhdr->cmd_status;
	}

	conn->datain_pdus_cnt++;
	return 0;
}

/**
 * iscsi_solicit_data_init - initialize first Data-Out
 * @conn: iscsi connection
 * @ctask: scsi command task
 * @r2t: R2T info
 *
 * Notes:
 *	Initialize first Data-Out within this R2T sequence and finds
 *	proper data_offset within this SCSI command.
 *
 *	This function is called with connection lock taken.
 **/
static void
iscsi_solicit_data_init(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask,
			struct iscsi_r2t_info *r2t)
{
	struct iscsi_data *hdr;
	struct scsi_cmnd *sc = ctask->sc;
	int i, sg_count = 0;
	struct scatterlist *sg;

	hdr = &r2t->dtask.hdr;
	memset(hdr, 0, sizeof(struct iscsi_data));
	hdr->ttt = r2t->ttt;
	hdr->datasn = cpu_to_be32(r2t->solicit_datasn);
	r2t->solicit_datasn++;
	hdr->opcode = ISCSI_OP_SCSI_DATA_OUT;
	memcpy(hdr->lun, ctask->hdr->lun, sizeof(hdr->lun));
	hdr->itt = ctask->hdr->itt;
	hdr->exp_statsn = r2t->exp_statsn;
	hdr->offset = cpu_to_be32(r2t->data_offset);
	if (r2t->data_length > conn->max_xmit_dlength) {
		hton24(hdr->dlength, conn->max_xmit_dlength);
		r2t->data_count = conn->max_xmit_dlength;
		hdr->flags = 0;
	} else {
		hton24(hdr->dlength, r2t->data_length);
		r2t->data_count = r2t->data_length;
		hdr->flags = ISCSI_FLAG_CMD_FINAL;
	}
	conn->dataout_pdus_cnt++;

	r2t->sent = 0;

	iscsi_buf_init_iov(&r2t->headbuf, (char*)hdr,
			   sizeof(struct iscsi_hdr));

	sg = scsi_sglist(sc);
	r2t->sg = NULL;
	for (i = 0; i < scsi_sg_count(sc); i++, sg += 1) {
		/* FIXME: prefetch ? */
		if (sg_count + sg->length > r2t->data_offset) {
			int page_offset;

			/* sg page found! */

			/* offset within this page */
			page_offset = r2t->data_offset - sg_count;

			/* fill in this buffer */
			iscsi_buf_init_sg(&r2t->sendbuf, sg);
			r2t->sendbuf.sg.offset += page_offset;
			r2t->sendbuf.sg.length -= page_offset;

			/* xmit logic will continue with next one */
			r2t->sg = sg + 1;
			break;
		}
		sg_count += sg->length;
	}
	BUG_ON(r2t->sg == NULL);
}

/**
 * iscsi_r2t_rsp - iSCSI R2T Response processing
 * @conn: iscsi connection
 * @ctask: scsi command task
 **/
static int
iscsi_r2t_rsp(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask)
{
	struct iscsi_r2t_info *r2t;
	struct iscsi_session *session = conn->session;
	struct iscsi_tcp_cmd_task *tcp_ctask = ctask->dd_data;
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
	struct iscsi_r2t_rsp *rhdr = (struct iscsi_r2t_rsp *)tcp_conn->in.hdr;
	int r2tsn = be32_to_cpu(rhdr->r2tsn);
	int rc;

	if (tcp_conn->in.datalen) {
		printk(KERN_ERR "iscsi_tcp: invalid R2t with datalen %d\n",
		       tcp_conn->in.datalen);
		return ISCSI_ERR_DATALEN;
	}

	if (tcp_ctask->exp_datasn != r2tsn){
		debug_tcp("%s: ctask->exp_datasn(%d) != rhdr->r2tsn(%d)\n",
		          __FUNCTION__, tcp_ctask->exp_datasn, r2tsn);
		return ISCSI_ERR_R2TSN;
	}

	/* fill-in new R2T associated with the task */
	spin_lock(&session->lock);
	iscsi_update_cmdsn(session, (struct iscsi_nopin*)rhdr);

	if (!ctask->sc || ctask->mtask ||
	     session->state != ISCSI_STATE_LOGGED_IN) {
		printk(KERN_INFO "iscsi_tcp: dropping R2T itt %d in "
		       "recovery...\n", ctask->itt);
		spin_unlock(&session->lock);
		return 0;
	}

	rc = __kfifo_get(tcp_ctask->r2tpool.queue, (void*)&r2t, sizeof(void*));
	BUG_ON(!rc);

	r2t->exp_statsn = rhdr->statsn;
	r2t->data_length = be32_to_cpu(rhdr->data_length);
	if (r2t->data_length == 0) {
		printk(KERN_ERR "iscsi_tcp: invalid R2T with zero data len\n");
		spin_unlock(&session->lock);
		return ISCSI_ERR_DATALEN;
	}

	if (r2t->data_length > session->max_burst)
		debug_scsi("invalid R2T with data len %u and max burst %u."
			   "Attempting to execute request.\n",
			    r2t->data_length, session->max_burst);

	r2t->data_offset = be32_to_cpu(rhdr->data_offset);
	if (r2t->data_offset + r2t->data_length > scsi_bufflen(ctask->sc)) {
		spin_unlock(&session->lock);
		printk(KERN_ERR "iscsi_tcp: invalid R2T with data len %u at "
		       "offset %u and total length %d\n", r2t->data_length,
		       r2t->data_offset, scsi_bufflen(ctask->sc));
		return ISCSI_ERR_DATALEN;
	}

	r2t->ttt = rhdr->ttt; /* no flip */
	r2t->solicit_datasn = 0;

	iscsi_solicit_data_init(conn, ctask, r2t);

	tcp_ctask->exp_datasn = r2tsn + 1;
	__kfifo_put(tcp_ctask->r2tqueue, (void*)&r2t, sizeof(void*));
	set_bit(XMSTATE_BIT_SOL_HDR_INIT, &tcp_ctask->xmstate);
	list_move_tail(&ctask->running, &conn->xmitqueue);

	scsi_queue_work(session->host, &conn->xmitwork);
	conn->r2t_pdus_cnt++;
	spin_unlock(&session->lock);

	return 0;
}

static int
iscsi_tcp_hdr_recv(struct iscsi_conn *conn)
{
	int rc = 0, opcode, ahslen;
	struct iscsi_hdr *hdr;
	struct iscsi_session *session = conn->session;
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
	uint32_t cdgst, rdgst = 0, itt;

	hdr = tcp_conn->in.hdr;

	/* verify PDU length */
	tcp_conn->in.datalen = ntoh24(hdr->dlength);
	if (tcp_conn->in.datalen > conn->max_recv_dlength) {
		printk(KERN_ERR "iscsi_tcp: datalen %d > %d\n",
		       tcp_conn->in.datalen, conn->max_recv_dlength);
		return ISCSI_ERR_DATALEN;
	}
	tcp_conn->data_copied = 0;

	/* read AHS */
	ahslen = hdr->hlength << 2;
	tcp_conn->in.offset += ahslen;
	tcp_conn->in.copy -= ahslen;
	if (tcp_conn->in.copy < 0) {
		printk(KERN_ERR "iscsi_tcp: can't handle AHS with length "
		       "%d bytes\n", ahslen);
		return ISCSI_ERR_AHSLEN;
	}

	/* calculate read padding */
	tcp_conn->in.padding = tcp_conn->in.datalen & (ISCSI_PAD_LEN-1);
	if (tcp_conn->in.padding) {
		tcp_conn->in.padding = ISCSI_PAD_LEN - tcp_conn->in.padding;
		debug_scsi("read padding %d bytes\n", tcp_conn->in.padding);
	}

	if (conn->hdrdgst_en) {
		struct scatterlist sg;

		sg_init_one(&sg, (u8 *)hdr,
			    sizeof(struct iscsi_hdr) + ahslen);
		crypto_hash_digest(&tcp_conn->rx_hash, &sg, sg.length,
				   (u8 *)&cdgst);
		rdgst = *(uint32_t*)((char*)hdr + sizeof(struct iscsi_hdr) +
				     ahslen);
		if (cdgst != rdgst) {
			printk(KERN_ERR "iscsi_tcp: hdrdgst error "
			       "recv 0x%x calc 0x%x\n", rdgst, cdgst);
			return ISCSI_ERR_HDR_DGST;
		}
	}

	opcode = hdr->opcode & ISCSI_OPCODE_MASK;
	/* verify itt (itt encoding: age+cid+itt) */
	rc = iscsi_verify_itt(conn, hdr, &itt);
	if (rc == ISCSI_ERR_NO_SCSI_CMD) {
		tcp_conn->in.datalen = 0; /* force drop */
		return 0;
	} else if (rc)
		return rc;

	debug_tcp("opcode 0x%x offset %d copy %d ahslen %d datalen %d\n",
		  opcode, tcp_conn->in.offset, tcp_conn->in.copy,
		  ahslen, tcp_conn->in.datalen);

	switch(opcode) {
	case ISCSI_OP_SCSI_DATA_IN:
		tcp_conn->in.ctask = session->cmds[itt];
		rc = iscsi_data_rsp(conn, tcp_conn->in.ctask);
		if (rc)
			return rc;
		/* fall through */
	case ISCSI_OP_SCSI_CMD_RSP:
		tcp_conn->in.ctask = session->cmds[itt];
		if (tcp_conn->in.datalen)
			goto copy_hdr;

		spin_lock(&session->lock);
		rc = __iscsi_complete_pdu(conn, hdr, NULL, 0);
		spin_unlock(&session->lock);
		break;
	case ISCSI_OP_R2T:
		tcp_conn->in.ctask = session->cmds[itt];
		if (ahslen)
			rc = ISCSI_ERR_AHSLEN;
		else if (tcp_conn->in.ctask->sc->sc_data_direction ==
								DMA_TO_DEVICE)
			rc = iscsi_r2t_rsp(conn, tcp_conn->in.ctask);
		else
			rc = ISCSI_ERR_PROTO;
		break;
	case ISCSI_OP_LOGIN_RSP:
	case ISCSI_OP_TEXT_RSP:
	case ISCSI_OP_REJECT:
	case ISCSI_OP_ASYNC_EVENT:
		/*
		 * It is possible that we could get a PDU with a buffer larger
		 * than 8K, but there are no targets that currently do this.
		 * For now we fail until we find a vendor that needs it
		 */
		if (ISCSI_DEF_MAX_RECV_SEG_LEN <
		    tcp_conn->in.datalen) {
			printk(KERN_ERR "iscsi_tcp: received buffer of len %u "
			      "but conn buffer is only %u (opcode %0x)\n",
			      tcp_conn->in.datalen,
			      ISCSI_DEF_MAX_RECV_SEG_LEN, opcode);
			rc = ISCSI_ERR_PROTO;
			break;
		}

		if (tcp_conn->in.datalen)
			goto copy_hdr;
	/* fall through */
	case ISCSI_OP_LOGOUT_RSP:
	case ISCSI_OP_NOOP_IN:
	case ISCSI_OP_SCSI_TMFUNC_RSP:
		rc = iscsi_complete_pdu(conn, hdr, NULL, 0);
		break;
	default:
		rc = ISCSI_ERR_BAD_OPCODE;
		break;
	}

	return rc;

copy_hdr:
	/*
	 * if we did zero copy for the header but we will need multiple
	 * skbs to complete the command then we have to copy the header
	 * for later use
	 */
	if (tcp_conn->in.zero_copy_hdr && tcp_conn->in.copy <=
	   (tcp_conn->in.datalen + tcp_conn->in.padding +
	    (conn->datadgst_en ? 4 : 0))) {
		debug_tcp("Copying header for later use. in.copy %d in.datalen"
			  " %d\n", tcp_conn->in.copy, tcp_conn->in.datalen);
		memcpy(&tcp_conn->hdr, tcp_conn->in.hdr,
		       sizeof(struct iscsi_hdr));
		tcp_conn->in.hdr = &tcp_conn->hdr;
		tcp_conn->in.zero_copy_hdr = 0;
	}
	return 0;
}

/**
 * iscsi_ctask_copy - copy skb bits to the destanation cmd task
 * @conn: iscsi tcp connection
 * @ctask: scsi command task
 * @buf: buffer to copy to
 * @buf_size: size of buffer
 * @offset: offset within the buffer
 *
 * Notes:
 *	The function calls skb_copy_bits() and updates per-connection and
 *	per-cmd byte counters.
 *
 *	Read counters (in bytes):
 *
 *	conn->in.offset		offset within in progress SKB
 *	conn->in.copy		left to copy from in progress SKB
 *				including padding
 *	conn->in.copied		copied already from in progress SKB
 *	conn->data_copied	copied already from in progress buffer
 *	ctask->sent		total bytes sent up to the MidLayer
 *	ctask->data_count	left to copy from in progress Data-In
 *	buf_left		left to copy from in progress buffer
 **/
static inline int
iscsi_ctask_copy(struct iscsi_tcp_conn *tcp_conn, struct iscsi_cmd_task *ctask,
		void *buf, int buf_size, int offset)
{
	struct iscsi_tcp_cmd_task *tcp_ctask = ctask->dd_data;
	int buf_left = buf_size - (tcp_conn->data_copied + offset);
	unsigned size = min(tcp_conn->in.copy, buf_left);
	int rc;

	size = min(size, ctask->data_count);

	debug_tcp("ctask_copy %d bytes at offset %d copied %d\n",
	       size, tcp_conn->in.offset, tcp_conn->in.copied);

	BUG_ON(size <= 0);
	BUG_ON(tcp_ctask->sent + size > scsi_bufflen(ctask->sc));

	rc = skb_copy_bits(tcp_conn->in.skb, tcp_conn->in.offset,
			   (char*)buf + (offset + tcp_conn->data_copied), size);
	/* must fit into skb->len */
	BUG_ON(rc);

	tcp_conn->in.offset += size;
	tcp_conn->in.copy -= size;
	tcp_conn->in.copied += size;
	tcp_conn->data_copied += size;
	tcp_ctask->sent += size;
	ctask->data_count -= size;

	BUG_ON(tcp_conn->in.copy < 0);
	BUG_ON(ctask->data_count < 0);

	if (buf_size != (tcp_conn->data_copied + offset)) {
		if (!ctask->data_count) {
			BUG_ON(buf_size - tcp_conn->data_copied < 0);
			/* done with this PDU */
			return buf_size - tcp_conn->data_copied;
		}
		return -EAGAIN;
	}

	/* done with this buffer or with both - PDU and buffer */
	tcp_conn->data_copied = 0;
	return 0;
}

/**
 * iscsi_tcp_copy - copy skb bits to the destanation buffer
 * @conn: iscsi tcp connection
 *
 * Notes:
 *	The function calls skb_copy_bits() and updates per-connection
 *	byte counters.
 **/
static inline int
iscsi_tcp_copy(struct iscsi_conn *conn, int buf_size)
{
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
	int buf_left = buf_size - tcp_conn->data_copied;
	int size = min(tcp_conn->in.copy, buf_left);
	int rc;

	debug_tcp("tcp_copy %d bytes at offset %d copied %d\n",
	       size, tcp_conn->in.offset, tcp_conn->data_copied);
	BUG_ON(size <= 0);

	rc = skb_copy_bits(tcp_conn->in.skb, tcp_conn->in.offset,
			   (char*)conn->data + tcp_conn->data_copied, size);
	BUG_ON(rc);

	tcp_conn->in.offset += size;
	tcp_conn->in.copy -= size;
	tcp_conn->in.copied += size;
	tcp_conn->data_copied += size;

	if (buf_size != tcp_conn->data_copied)
		return -EAGAIN;

	return 0;
}

static inline void
partial_sg_digest_update(struct hash_desc *desc, struct scatterlist *sg,
			 int offset, int length)
{
	struct scatterlist temp;

	sg_init_table(&temp, 1);
	sg_set_page(&temp, sg_page(sg), length, offset);
	crypto_hash_update(desc, &temp, length);
}

static void
iscsi_recv_digest_update(struct iscsi_tcp_conn *tcp_conn, char* buf, int len)
{
	struct scatterlist tmp;

	sg_init_one(&tmp, buf, len);
	crypto_hash_update(&tcp_conn->rx_hash, &tmp, len);
}

static int iscsi_scsi_data_in(struct iscsi_conn *conn)
{
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
	struct iscsi_cmd_task *ctask = tcp_conn->in.ctask;
	struct iscsi_tcp_cmd_task *tcp_ctask = ctask->dd_data;
	struct scsi_cmnd *sc = ctask->sc;
	struct scatterlist *sg;
	int i, offset, rc = 0;

	BUG_ON((void*)ctask != sc->SCp.ptr);

	offset = tcp_ctask->data_offset;
	sg = scsi_sglist(sc);

	if (tcp_ctask->data_offset)
		for (i = 0; i < tcp_ctask->sg_count; i++)
			offset -= sg[i].length;
	/* we've passed through partial sg*/
	if (offset < 0)
		offset = 0;

	for (i = tcp_ctask->sg_count; i < scsi_sg_count(sc); i++) {
		char *dest;

		dest = kmap_atomic(sg_page(&sg[i]), KM_SOFTIRQ0);
		rc = iscsi_ctask_copy(tcp_conn, ctask, dest + sg[i].offset,
				      sg[i].length, offset);
		kunmap_atomic(dest, KM_SOFTIRQ0);
		if (rc == -EAGAIN)
			/* continue with the next SKB/PDU */
			return rc;
		if (!rc) {
			if (conn->datadgst_en) {
				if (!offset)
					crypto_hash_update(
							&tcp_conn->rx_hash,
							&sg[i], sg[i].length);
				else
					partial_sg_digest_update(
							&tcp_conn->rx_hash,
							&sg[i],
							sg[i].offset + offset,
							sg[i].length - offset);
			}
			offset = 0;
			tcp_ctask->sg_count++;
		}

		if (!ctask->data_count) {
			if (rc && conn->datadgst_en)
				/*
				 * data-in is complete, but buffer not...
				 */
				partial_sg_digest_update(&tcp_conn->rx_hash,
							 &sg[i],
							 sg[i].offset,
							 sg[i].length-rc);
			rc = 0;
			break;
		}

		if (!tcp_conn->in.copy)
			return -EAGAIN;
	}
	BUG_ON(ctask->data_count);

	/* check for non-exceptional status */
	if (tcp_conn->in.hdr->flags & ISCSI_FLAG_DATA_STATUS) {
		debug_scsi("done [sc %lx res %d itt 0x%x flags 0x%x]\n",
			   (long)sc, sc->result, ctask->itt,
			   tcp_conn->in.hdr->flags);
		spin_lock(&conn->session->lock);
		__iscsi_complete_pdu(conn, tcp_conn->in.hdr, NULL, 0);
		spin_unlock(&conn->session->lock);
	}

	return rc;
}

static int
iscsi_data_recv(struct iscsi_conn *conn)
{
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
	int rc = 0, opcode;

	opcode = tcp_conn->in.hdr->opcode & ISCSI_OPCODE_MASK;
	switch (opcode) {
	case ISCSI_OP_SCSI_DATA_IN:
		rc = iscsi_scsi_data_in(conn);
		break;
	case ISCSI_OP_SCSI_CMD_RSP:
	case ISCSI_OP_TEXT_RSP:
	case ISCSI_OP_LOGIN_RSP:
	case ISCSI_OP_ASYNC_EVENT:
	case ISCSI_OP_REJECT:
		/*
		 * Collect data segment to the connection's data
		 * placeholder
		 */
		if (iscsi_tcp_copy(conn, tcp_conn->in.datalen)) {
			rc = -EAGAIN;
			goto exit;
		}

		rc = iscsi_complete_pdu(conn, tcp_conn->in.hdr, conn->data,
					tcp_conn->in.datalen);
		if (!rc && conn->datadgst_en && opcode != ISCSI_OP_LOGIN_RSP)
			iscsi_recv_digest_update(tcp_conn, conn->data,
			  			tcp_conn->in.datalen);
		break;
	default:
		BUG_ON(1);
	}
exit:
	return rc;
}

/**
 * iscsi_tcp_data_recv - TCP receive in sendfile fashion
 * @rd_desc: read descriptor
 * @skb: socket buffer
 * @offset: offset in skb
 * @len: skb->len - offset
 **/
static int
iscsi_tcp_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb,
		unsigned int offset, size_t len)
{
	int rc;
	struct iscsi_conn *conn = rd_desc->arg.data;
	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
	int processed;
	char pad[ISCSI_PAD_LEN];
	struct scatterlist sg;

	/*
	 * Save current SKB and its offset in the corresponding
	 * connection context.
	 */
	tcp_conn->in.copy = skb->len - offset;
	tcp_conn->in.offset = offset;
	tcp_conn->in.skb = skb;
	tcp_conn->in.len = tcp_conn->in.copy;
	BUG_ON(tcp_conn->in.copy <= 0);
	debug_tcp("in %d bytes\n", tcp_conn->in.copy);

more:
	tcp_conn->in.copied = 0;
	rc = 0;

	if (unlikely(conn->suspend_rx)) {
		debug_tcp("conn %d Rx suspended!\n", conn->id);
		return 0;
	}

	if (tcp_conn->in_progress == IN_PROGRESS_WAIT_HEADER ||
	    tcp_conn->in_progress == IN_PROGRESS_HEADER_GATHER) {
		rc = iscsi_hdr_extract(tcp_conn);
		if (rc) {
		       if (rc == -EAGAIN)
				goto nomore;
		       else {
				iscsi_conn_failure(conn, ISCSI_ERR_CONN_FAILED);
				return 0;
		       }
		}

		/*
		 * Verify and process incoming PDU header.
		 */
		rc = iscsi_tcp_hdr_recv(conn);
		if (!rc && tcp_conn->in.datalen) {
			if (conn->datadgst_en)
				crypto_hash_init(&tcp_conn->rx_hash);
			tcp_conn->in_progress = IN_PROGRESS_DATA_RECV;
		} else if (rc) {
			iscsi_conn_failure(conn, rc);
			return 0;
		}
	}

	if (tcp_conn->in_progress == IN_PROGRESS_DDIGEST_RECV &&
	    tcp_conn->in.copy) {
		uint32_t recv_digest;

		debug_tcp("extra data_recv offset %d copy %d\n",
			  tcp_conn->in.offset, tcp_conn->in.copy);

		if (!tcp_conn->data_copied) {
			if (tcp_conn->in.padding) {
				debug_tcp("padding -> %d\n",
					  tcp_conn->in.padding);
				memset(pad, 0, tcp_conn->in.padding);
				sg_init_one(&sg, pad, tcp_conn->in.padding);
				crypto_hash_update(&tcp_conn->rx_hash,
						   &sg, sg.length);
			}
			crypto_hash_final(&tcp_conn->rx_hash,
					  (u8 *) &tcp_conn->in.datadgst);
			debug_tcp("rx digest 0x%x\n", tcp_conn->in.datadgst);
		}

		rc = iscsi_tcp_copy(conn, sizeof(uint32_t));
		if (rc) {
			if (rc == -EAGAIN)
				goto again;
			iscsi_conn_failure(conn, ISCSI_ERR_CONN_FAILED);
			return 0;
		}

		memcpy(&recv_digest, conn->data, sizeof(uint32_t));
		if (recv_digest != tcp_conn->in.datadgst) {
			debug_tcp("iscsi_tcp: data digest error!"
				  "0x%x != 0x%x\n", recv_digest,
				  tcp_conn->in.datadgst);
			iscsi_conn_failure(conn, ISCSI_ERR_DATA_DGST);
			return 0;
		} else {
			debug_tcp("iscsi_tcp: data digest match!"
				  "0x%x == 0x%x\n", recv_digest,
				  tcp_conn->in.datadgst);
			tcp_conn->in_progress = IN_PROGRESS_WAIT_HEADER;
		}
	}

	if (tcp_conn->in_progress == IN_PROGRESS_DATA_RECV &&
	    tcp_conn->in.copy) {
		debug_tcp("data_recv offset %d copy %d\n",
		       tcp_conn->in.offset, tcp_conn->in.copy);

		rc = iscsi_data_recv(conn);
		if (rc) {
			if (rc == -EAGAIN)
				goto again;
			iscsi_conn_failure(conn, ISCSI_ERR_CONN_FAILED);
			return 0;
		}

		if (tcp_conn->in.padding)
			tcp_conn->in_progress = IN_PROGRESS_PAD_RECV;
		else if (conn->datadgst_en)
			tcp_conn->in_progress = IN_PROGRESS_DDIGEST_RECV;
		else
			tcp_conn->in_progress = IN_PROGRESS_WAIT_HEADER;
		tcp_conn->data_copied = 0;
	}

	if (tcp_conn->in_progress == IN_PROGRESS_PAD_RECV &&
	    tcp_conn->in.copy) {
		int copylen = min(tcp_conn->in.padding - tcp_conn->data_copied,
				  tcp_conn->in.copy);

		tcp_conn->in.copy -= copylen;
		tcp_conn->in.offset += copylen;
		tcp_conn->data_copied += copylen;

		if (tcp_conn->data_copied != tcp_conn->in.padding)
			tcp_conn->in_progress = IN_PROGRESS_PAD_RECV;
		else if (conn->datadgst_en)
			tcp_conn->in_progress = IN_PROGRESS_DDIGEST_RECV;
		else
			tcp_conn->in_progress = IN_PROGRESS_WAIT_HEADER;
		tcp_conn->data_copied = 0;
	}

	debug_tcp("f, processed %d from out of %d padding %d\n",
	       tcp_conn->in.offset - offset, (int)len, tcp_conn->in.padding);
	BUG_ON(tcp_conn->in.offset - offset > len);

	if (tcp_conn->in.offset - offset != len) {
		debug_tcp("continue to process %d bytes\n",
		       (int)len - (tcp_conn->in.offset - offset));
		goto more;
	}

nomore:
	processed = tcp_conn->in.offset - offset;
	BUG_ON(processed == 0);
	return processed;

again:
	processed = tcp_conn->in.offset - offset;
	debug_tcp("c, processed %d from out of %d rd_desc_cnt %d\n",
	          processed, (int)len, (int)rd_desc->count);
	BUG_ON(processed == 0);
	BUG_ON(processed > len);

	conn->rxdata_octets += processed;
	return processed;
}

static void
iscsi_tcp_data_ready(struct sock *sk, int flag)
{
	struct iscsi_conn *conn = sk->sk_user_data;
	read_descriptor_t rd_desc;

	read_lock(&sk->sk_callback_lock);

	/*
	 * Use rd_desc to pass 'conn' to iscsi_tcp_data_recv.
	 * We set count to 1 because we want the network layer to
	 * hand us all the skbs that are available. iscsi_tcp_data_recv
	 * handled pdus that cross buffers or pdus that still need data.
	 */
	rd_desc.arg.data = conn;
	rd_desc.count = 1;
	tcp_read_sock(sk, &rd_desc, iscsi_tcp_data_recv);

	read_unlock(&sk->sk_callback_lock);