iscsi_tcp.c

linux 内核源代码

				   (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;
		}