1 files changed, 892 insertions, 1183 deletions

diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c
index 57ce2251abc..e5be5fd4ef5 100644
--- a/drivers/scsi/iscsi_tcp.c
+++ b/drivers/scsi/iscsi_tcp.c
@@ -48,7 +48,7 @@ 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 */
+#undef DEBUG_TCP
 #define DEBUG_ASSERT
 
 #ifdef DEBUG_TCP
@@ -67,115 +67,429 @@ MODULE_LICENSE("GPL");
 static unsigned int iscsi_max_lun = 512;
 module_param_named(max_lun, iscsi_max_lun, uint, S_IRUGO);
 
+static int iscsi_tcp_hdr_recv_done(struct iscsi_tcp_conn *tcp_conn,
+				   struct iscsi_segment *segment);
+
+/*
+ * Scatterlist handling: inside the iscsi_segment, we
+ * remember an index into the scatterlist, and set data/size
+ * to the current scatterlist entry. For highmem pages, we
+ * kmap as needed.
+ *
+ * Note that the page is unmapped when we return from
+ * TCP's data_ready handler, so we may end up mapping and
+ * unmapping the same page repeatedly. The whole reason
+ * for this is that we shouldn't keep the page mapped
+ * outside the softirq.
+ */
+
+/**
+ * iscsi_tcp_segment_init_sg - init indicated scatterlist entry
+ * @segment: the buffer object
+ * @sg: scatterlist
+ * @offset: byte offset into that sg entry
+ *
+ * This function sets up the segment so that subsequent
+ * data is copied to the indicated sg entry, at the given
+ * offset.
+ */
 static inline void
-iscsi_buf_init_iov(struct iscsi_buf *ibuf, char *vbuf, int size)
+iscsi_tcp_segment_init_sg(struct iscsi_segment *segment,
+			  struct scatterlist *sg, unsigned int offset)
 {
-	sg_init_one(&ibuf->sg, vbuf, size);
-	ibuf->sent = 0;
-	ibuf->use_sendmsg = 1;
+	segment->sg = sg;
+	segment->sg_offset = offset;
+	segment->size = min(sg->length - offset,
+			    segment->total_size - segment->total_copied);
+	segment->data = NULL;
 }
 
+/**
+ * iscsi_tcp_segment_map - map the current S/G page
+ * @segment: iscsi_segment
+ * @recv: 1 if called from recv path
+ *
+ * We only need to possibly kmap data if scatter lists are being used,
+ * because the iscsi passthrough and internal IO paths will never use high
+ * mem pages.
+ */
 static inline void
-iscsi_buf_init_sg(struct iscsi_buf *ibuf, struct scatterlist *sg)
+iscsi_tcp_segment_map(struct iscsi_segment *segment, int recv)
 {
-	sg_init_table(&ibuf->sg, 1);
-	sg_set_page(&ibuf->sg, sg_page(sg), sg->length, sg->offset);
+	struct scatterlist *sg;
+
+	if (segment->data != NULL || !segment->sg)
+		return;
+
+	sg = segment->sg;
+	BUG_ON(segment->sg_mapped);
+	BUG_ON(sg->length == 0);
+
 	/*
-	 * Fastpath: sg element fits into single page
+	 * If the page count is greater than one it is ok to send
+	 * to the network layer's zero copy send path. If not we
+	 * have to go the slow sendmsg path. We always map for the
+	 * recv path.
 	 */
-	if (sg->length + sg->offset <= PAGE_SIZE && !PageSlab(sg_page(sg)))
-		ibuf->use_sendmsg = 0;
-	else
-		ibuf->use_sendmsg = 1;
-	ibuf->sent = 0;
+	if (page_count(sg_page(sg)) >= 1 && !recv)
+		return;
+
+	debug_tcp("iscsi_tcp_segment_map %s %p\n", recv ? "recv" : "xmit",
+		  segment);
+	segment->sg_mapped = kmap_atomic(sg_page(sg), KM_SOFTIRQ0);
+	segment->data = segment->sg_mapped + sg->offset + segment->sg_offset;
 }
 
-static inline int
-iscsi_buf_left(struct iscsi_buf *ibuf)
+static inline void
+iscsi_tcp_segment_unmap(struct iscsi_segment *segment)
 {
-	int rc;
+	debug_tcp("iscsi_tcp_segment_unmap %p\n", segment);
 
-	rc = ibuf->sg.length - ibuf->sent;
-	BUG_ON(rc < 0);
-	return rc;
+	if (segment->sg_mapped) {
+		debug_tcp("iscsi_tcp_segment_unmap valid\n");
+		kunmap_atomic(segment->sg_mapped, KM_SOFTIRQ0);
+		segment->sg_mapped = NULL;
+		segment->data = NULL;
+	}
 }
 
+/*
+ * Splice the digest buffer into the buffer
+ */
 static inline void
-iscsi_hdr_digest(struct iscsi_conn *conn, struct iscsi_buf *buf,
-		 u8* crc)
+iscsi_tcp_segment_splice_digest(struct iscsi_segment *segment, void *digest)
 {
-	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);
+	segment->data = digest;
+	segment->digest_len = ISCSI_DIGEST_SIZE;
+	segment->total_size += ISCSI_DIGEST_SIZE;
+	segment->size = ISCSI_DIGEST_SIZE;
+	segment->copied = 0;
+	segment->sg = NULL;
+	segment->hash = NULL;
 }
 
+/**
+ * iscsi_tcp_segment_done - check whether the segment is complete
+ * @segment: iscsi segment to check
+ * @recv: set to one of this is called from the recv path
+ * @copied: number of bytes copied
+ *
+ * Check if we're done receiving this segment. If the receive
+ * buffer is full but we expect more data, move on to the
+ * next entry in the scatterlist.
+ *
+ * If the amount of data we received isn't a multiple of 4,
+ * we will transparently receive the pad bytes, too.
+ *
+ * This function must be re-entrant.
+ */
 static inline int
-iscsi_hdr_extract(struct iscsi_tcp_conn *tcp_conn)
+iscsi_tcp_segment_done(struct iscsi_segment *segment, int recv, unsigned copied)
 {
-	struct sk_buff *skb = tcp_conn->in.skb;
-
-	tcp_conn->in.zero_copy_hdr = 0;
+	static unsigned char padbuf[ISCSI_PAD_LEN];
+	struct scatterlist sg;
+	unsigned int pad;
 
-	if (tcp_conn->in.copy >= tcp_conn->hdr_size &&
-	    tcp_conn->in_progress == IN_PROGRESS_WAIT_HEADER) {
+	debug_tcp("copied %u %u size %u %s\n", segment->copied, copied,
+		  segment->size, recv ? "recv" : "xmit");
+	if (segment->hash && copied) {
 		/*
-		 * Zero-copy PDU Header: using connection context
-		 * to store header pointer.
+		 * If a segment is kmapd we must unmap it before sending
+		 * to the crypto layer since that will try to kmap it again.
 		 */
-		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;
+		iscsi_tcp_segment_unmap(segment);
+
+		if (!segment->data) {
+			sg_init_table(&sg, 1);
+			sg_set_page(&sg, sg_page(segment->sg), copied,
+				    segment->copied + segment->sg_offset +
+							segment->sg->offset);
+		} else
+			sg_init_one(&sg, segment->data + segment->copied,
+				    copied);
+		crypto_hash_update(segment->hash, &sg, copied);
+	}
+
+	segment->copied += copied;
+	if (segment->copied < segment->size) {
+		iscsi_tcp_segment_map(segment, recv);
+		return 0;
+	}
+
+	segment->total_copied += segment->copied;
+	segment->copied = 0;
+	segment->size = 0;
+
+	/* Unmap the current scatterlist page, if there is one. */
+	iscsi_tcp_segment_unmap(segment);
+
+	/* Do we have more scatterlist entries? */
+	debug_tcp("total copied %u total size %u\n", segment->total_copied,
+		   segment->total_size);
+	if (segment->total_copied < segment->total_size) {
+		/* Proceed to the next entry in the scatterlist. */
+		iscsi_tcp_segment_init_sg(segment, sg_next(segment->sg),
+					  0);
+		iscsi_tcp_segment_map(segment, recv);
+		BUG_ON(segment->size == 0);
+		return 0;
+	}
+
+	/* Do we need to handle padding? */
+	pad = iscsi_padding(segment->total_copied);
+	if (pad != 0) {
+		debug_tcp("consume %d pad bytes\n", pad);
+		segment->total_size += pad;
+		segment->size = pad;
+		segment->data = padbuf;
+		return 0;
+	}
+
+	/*
+	 * Set us up for transferring the data digest. hdr digest
+	 * is completely handled in hdr done function.
+	 */
+	if (segment->hash) {
+		crypto_hash_final(segment->hash, segment->digest);
+		iscsi_tcp_segment_splice_digest(segment,
+				 recv ? segment->recv_digest : segment->digest);
+		return 0;
+	}
+
+	return 1;
+}
+
+/**
+ * iscsi_tcp_xmit_segment - transmit segment
+ * @tcp_conn: the iSCSI TCP connection
+ * @segment: the buffer to transmnit
+ *
+ * This function transmits as much of the buffer as
+ * the network layer will accept, and returns the number of
+ * bytes transmitted.
+ *
+ * If CRC hashing is enabled, the function will compute the
+ * hash as it goes. When the entire segment has been transmitted,
+ * it will retrieve the hash value and send it as well.
+ */
+static int
+iscsi_tcp_xmit_segment(struct iscsi_tcp_conn *tcp_conn,
+		       struct iscsi_segment *segment)
+{
+	struct socket *sk = tcp_conn->sock;
+	unsigned int copied = 0;
+	int r = 0;
+
+	while (!iscsi_tcp_segment_done(segment, 0, r)) {
+		struct scatterlist *sg;
+		unsigned int offset, copy;
+		int flags = 0;
+
+		r = 0;
+		offset = segment->copied;
+		copy = segment->size - offset;
+
+		if (segment->total_copied + segment->size < segment->total_size)
+			flags |= MSG_MORE;
+
+		/* Use sendpage if we can; else fall back to sendmsg */
+		if (!segment->data) {
+			sg = segment->sg;
+			offset += segment->sg_offset + sg->offset;
+			r = tcp_conn->sendpage(sk, sg_page(sg), offset, copy,
+					       flags);
 		} 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;
+			struct msghdr msg = { .msg_flags = flags };
+			struct kvec iov = {
+				.iov_base = segment->data + offset,
+				.iov_len = copy
+			};
+
+			r = kernel_sendmsg(sk, &msg, &iov, 1, copy);
 		}
-		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 (r < 0) {
+			iscsi_tcp_segment_unmap(segment);
+			if (copied || r == -EAGAIN)
+				break;
+			return r;
+		}
+		copied += r;
+	}
+	return copied;
+}
+
+/**
+ * iscsi_tcp_segment_recv - copy data to segment
+ * @tcp_conn: the iSCSI TCP connection
+ * @segment: the buffer to copy to
+ * @ptr: data pointer
+ * @len: amount of data available
+ *
+ * This function copies up to @len bytes to the
+ * given buffer, and returns the number of bytes
+ * consumed, which can actually be less than @len.
+ *
+ * If hash digest is enabled, the function will update the
+ * hash while copying.
+ * Combining these two operations doesn't buy us a lot (yet),
+ * but in the future we could implement combined copy+crc,
+ * just way we do for network layer checksums.
+ */
+static int
+iscsi_tcp_segment_recv(struct iscsi_tcp_conn *tcp_conn,
+		       struct iscsi_segment *segment, const void *ptr,
+		       unsigned int len)
+{
+	unsigned int copy = 0, copied = 0;
+
+	while (!iscsi_tcp_segment_done(segment, 1, copy)) {
+		if (copied == len) {
+			debug_tcp("iscsi_tcp_segment_recv copied %d bytes\n",
+				  len);
+			break;
+		}
+
+		copy = min(len - copied, segment->size - segment->copied);
+		debug_tcp("iscsi_tcp_segment_recv copying %d\n", copy);
+		memcpy(segment->data + segment->copied, ptr + copied, copy);
+		copied += copy;
+	}
+	return copied;
+}
 
-		if (tcp_conn->in_progress == IN_PROGRESS_WAIT_HEADER)
-			tcp_conn->in.hdr_offset = 0;
+static inline void
+iscsi_tcp_dgst_header(struct hash_desc *hash, const void *hdr, size_t hdrlen,
+		      unsigned char digest[ISCSI_DIGEST_SIZE])
+{
+	struct scatterlist sg;
 
-		hdr_remains = tcp_conn->hdr_size - tcp_conn->in.hdr_offset;
-		BUG_ON(hdr_remains <= 0);
+	sg_init_one(&sg, hdr, hdrlen);
+	crypto_hash_digest(hash, &sg, hdrlen, digest);
+}
 
-		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);
+static inline int
+iscsi_tcp_dgst_verify(struct iscsi_tcp_conn *tcp_conn,
+		      struct iscsi_segment *segment)
+{
+	if (!segment->digest_len)
+		return 1;
 
-		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);
+	if (memcmp(segment->recv_digest, segment->digest,
+		   segment->digest_len)) {
+		debug_scsi("digest mismatch\n");
+		return 0;
+	}
 
-		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;
+	return 1;
+}
+
+/*
+ * Helper function to set up segment buffer
+ */
+static inline void
+__iscsi_segment_init(struct iscsi_segment *segment, size_t size,
+		     iscsi_segment_done_fn_t *done, struct hash_desc *hash)
+{
+	memset(segment, 0, sizeof(*segment));
+	segment->total_size = size;
+	segment->done = done;
+
+	if (hash) {
+		segment->hash = hash;
+		crypto_hash_init(hash);
+	}
+}
+
+static inline void
+iscsi_segment_init_linear(struct iscsi_segment *segment, void *data,
+			  size_t size, iscsi_segment_done_fn_t *done,
+			  struct hash_desc *hash)
+{
+	__iscsi_segment_init(segment, size, done, hash);
+	segment->data = data;
+	segment->size = size;
+}
+
+static inline int
+iscsi_segment_seek_sg(struct iscsi_segment *segment,
+		      struct scatterlist *sg_list, unsigned int sg_count,
+		      unsigned int offset, size_t size,
+		      iscsi_segment_done_fn_t *done, struct hash_desc *hash)
+{
+	struct scatterlist *sg;
+	unsigned int i;
+
+	debug_scsi("iscsi_segment_seek_sg offset %u size %llu\n",
+		  offset, size);
+	__iscsi_segment_init(segment, size, done, hash);
+	for_each_sg(sg_list, sg, sg_count, i) {
+		debug_scsi("sg %d, len %u offset %u\n", i, sg->length,
+			   sg->offset);
+		if (offset < sg->length) {
+			iscsi_tcp_segment_init_sg(segment, sg, offset);
+			return 0;
 		}
-		tcp_conn->in.hdr = &tcp_conn->hdr;
-		tcp_conn->discontiguous_hdr_cnt++;
-	        tcp_conn->in_progress = IN_PROGRESS_WAIT_HEADER;
+		offset -= sg->length;
 	}
 
+	return ISCSI_ERR_DATA_OFFSET;
+}
+
+/**
+ * iscsi_tcp_hdr_recv_prep - prep segment for hdr reception
+ * @tcp_conn: iscsi connection to prep for
+ *
+ * This function always passes NULL for the hash argument, because when this
+ * function is called we do not yet know the final size of the header and want
+ * to delay the digest processing until we know that.
+ */
+static void
+iscsi_tcp_hdr_recv_prep(struct iscsi_tcp_conn *tcp_conn)
+{
+	debug_tcp("iscsi_tcp_hdr_recv_prep(%p%s)\n", tcp_conn,
+		  tcp_conn->iscsi_conn->hdrdgst_en ? ", digest enabled" : "");
+	iscsi_segment_init_linear(&tcp_conn->in.segment,
+				tcp_conn->in.hdr_buf, sizeof(struct iscsi_hdr),
+				iscsi_tcp_hdr_recv_done, NULL);
+}
+
+/*
+ * Handle incoming reply to any other type of command
+ */
+static int
+iscsi_tcp_data_recv_done(struct iscsi_tcp_conn *tcp_conn,
+			 struct iscsi_segment *segment)
+{
+	struct iscsi_conn *conn = tcp_conn->iscsi_conn;
+	int rc = 0;
+
+	if (!iscsi_tcp_dgst_verify(tcp_conn, segment))
+		return ISCSI_ERR_DATA_DGST;
+
+	rc = iscsi_complete_pdu(conn, tcp_conn->in.hdr,
+			conn->data, tcp_conn->in.datalen);
+	if (rc)
+		return rc;
+
+	iscsi_tcp_hdr_recv_prep(tcp_conn);
 	return 0;
 }
 
+static void
+iscsi_tcp_data_recv_prep(struct iscsi_tcp_conn *tcp_conn)
+{
+	struct iscsi_conn *conn = tcp_conn->iscsi_conn;
+	struct hash_desc *rx_hash = NULL;
+
+	if (conn->datadgst_en)
+		rx_hash = &tcp_conn->rx_hash;
+
+	iscsi_segment_init_linear(&tcp_conn->in.segment,
+				conn->data, tcp_conn->in.datalen,
+				iscsi_tcp_data_recv_done, rx_hash);
+}
+
 /*
  * must be called with session lock
  */
@@ -184,7 +498,6 @@ 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*))) {
@@ -193,12 +506,12 @@ iscsi_tcp_cleanup_ctask(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask)
 		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;
+	r2t = tcp_ctask->r2t;
+	if (r2t != NULL) {
+		__kfifo_put(tcp_ctask->r2tpool.queue, (void*)&r2t,
+			    sizeof(void*));
+		tcp_ctask->r2t = NULL;
+	}
 }
 
 /**
@@ -217,11 +530,6 @@ iscsi_data_rsp(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask)
 	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;
 
@@ -242,22 +550,20 @@ iscsi_data_rsp(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask)
 	}
 
 	if (rhdr->flags & ISCSI_FLAG_DATA_STATUS) {
+		sc->result = (DID_OK << 16) | rhdr->cmd_status;
 		conn->exp_statsn = be32_to_cpu(rhdr->statsn) + 1;
-		if (rhdr->flags & ISCSI_FLAG_DATA_UNDERFLOW) {
+		if (rhdr->flags & (ISCSI_FLAG_DATA_UNDERFLOW |
+		                   ISCSI_FLAG_DATA_OVERFLOW)) {
 			int res_count = be32_to_cpu(rhdr->residual_count);
 
 			if (res_count > 0 &&
-			    res_count <= scsi_bufflen(sc)) {
+			    (rhdr->flags & ISCSI_FLAG_CMD_OVERFLOW ||
+			     res_count <= scsi_bufflen(sc)))
 				scsi_set_resid(sc, res_count);
-				sc->result = (DID_OK << 16) | rhdr->cmd_status;
-			} else
+			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++;
@@ -281,9 +587,6 @@ 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));
@@ -307,34 +610,6 @@ iscsi_solicit_data_init(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask,
 	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);
 }
 
 /**
@@ -366,14 +641,11 @@ iscsi_r2t_rsp(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask)
 	}
 
 	/* 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) {
+	if (!ctask->sc || 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;
 	}
 
@@ -384,7 +656,8 @@ iscsi_r2t_rsp(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask)
 	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);
+		__kfifo_put(tcp_ctask->r2tpool.queue, (void*)&r2t,
+			    sizeof(void*));
 		return ISCSI_ERR_DATALEN;
 	}
 
@@ -395,10 +668,11 @@ iscsi_r2t_rsp(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask)
 
 	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));
+		__kfifo_put(tcp_ctask->r2tpool.queue, (void*)&r2t,
+			    sizeof(void*));
 		return ISCSI_ERR_DATALEN;
 	}
 
@@ -409,26 +683,55 @@ iscsi_r2t_rsp(struct iscsi_conn *conn, struct iscsi_cmd_task *ctask)
 
 	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);
 
+	iscsi_requeue_ctask(ctask);
 	return 0;
 }
 
+/*
+ * Handle incoming reply to DataIn command
+ */
 static int
-iscsi_tcp_hdr_recv(struct iscsi_conn *conn)
+iscsi_tcp_process_data_in(struct iscsi_tcp_conn *tcp_conn,
+			  struct iscsi_segment *segment)
+{
+	struct iscsi_conn *conn = tcp_conn->iscsi_conn;
+	struct iscsi_hdr *hdr = tcp_conn->in.hdr;
+	int rc;
+
+	if (!iscsi_tcp_dgst_verify(tcp_conn, segment))
+		return ISCSI_ERR_DATA_DGST;
+
+	/* check for non-exceptional status */
+	if (hdr->flags & ISCSI_FLAG_DATA_STATUS) {
+		rc = iscsi_complete_pdu(conn, tcp_conn->in.hdr, NULL, 0);
+		if (rc)
+			return rc;
+	}
+
+	iscsi_tcp_hdr_recv_prep(tcp_conn);
+	return 0;
+}
+
+/**
+ * iscsi_tcp_hdr_dissect - process PDU header
+ * @conn: iSCSI connection
+ * @hdr: PDU header
+ *
+ * This function analyzes the header of the PDU received,
+ * and performs several sanity checks. If the PDU is accompanied
+ * by data, the receive buffer is set up to copy the incoming data
+ * to the correct location.
+ */
+static int
+iscsi_tcp_hdr_dissect(struct iscsi_conn *conn, struct iscsi_hdr *hdr)
 {
 	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;
+	struct iscsi_cmd_task *ctask;
+	uint32_t itt;
 
 	/* verify PDU length */
 	tcp_conn->in.datalen = ntoh24(hdr->dlength);
@@ -437,78 +740,73 @@ iscsi_tcp_hdr_recv(struct iscsi_conn *conn)
 		       tcp_conn->in.datalen, conn->max_recv_dlength);
 		return ISCSI_ERR_DATALEN;
 	}
-	tcp_conn->data_copied = 0;
 
-	/* read AHS */
+	/* Additional header segments. So far, we don't
+	 * process additional headers.
+	 */
 	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)
+	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);
+	debug_tcp("opcode 0x%x ahslen %d datalen %d\n",
+		  opcode, 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);
+		ctask = session->cmds[itt];
+		spin_lock(&conn->session->lock);
+		rc = iscsi_data_rsp(conn, ctask);
+		spin_unlock(&conn->session->lock);
 		if (rc)
 			return rc;
+		if (tcp_conn->in.datalen) {
+			struct iscsi_tcp_cmd_task *tcp_ctask = ctask->dd_data;
+			struct hash_desc *rx_hash = NULL;
+
+			/*
+			 * Setup copy of Data-In into the Scsi_Cmnd
+			 * Scatterlist case:
+			 * We set up the iscsi_segment to point to the next
+			 * scatterlist entry to copy to. As we go along,
+			 * we move on to the next scatterlist entry and
+			 * update the digest per-entry.
+			 */
+			if (conn->datadgst_en)
+				rx_hash = &tcp_conn->rx_hash;
+
+			debug_tcp("iscsi_tcp_begin_data_in(%p, offset=%d, "
+				  "datalen=%d)\n", tcp_conn,
+				  tcp_ctask->data_offset,
+				  tcp_conn->in.datalen);
+			return iscsi_segment_seek_sg(&tcp_conn->in.segment,
+						     scsi_sglist(ctask->sc),
+						     scsi_sg_count(ctask->sc),
+						     tcp_ctask->data_offset,
+						     tcp_conn->in.datalen,
+						     iscsi_tcp_process_data_in,
+						     rx_hash);
+		}
 		/* 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);
+		if (tcp_conn->in.datalen) {
+			iscsi_tcp_data_recv_prep(tcp_conn);
+			return 0;
+		}
+		rc = iscsi_complete_pdu(conn, hdr, NULL, 0);
 		break;
 	case ISCSI_OP_R2T:
-		tcp_conn->in.ctask = session->cmds[itt];
+		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
+		else if (ctask->sc->sc_data_direction == DMA_TO_DEVICE) {
+			spin_lock(&session->lock);
+			rc = iscsi_r2t_rsp(conn, ctask);
+			spin_unlock(&session->lock);
+		} else
 			rc = ISCSI_ERR_PROTO;
 		break;
 	case ISCSI_OP_LOGIN_RSP:
@@ -520,8 +818,7 @@ iscsi_tcp_hdr_recv(struct iscsi_conn *conn)
 		 * 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) {
+		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,
@@ -530,8 +827,13 @@ iscsi_tcp_hdr_recv(struct iscsi_conn *conn)
 			break;
 		}
 
-		if (tcp_conn->in.datalen)
-			goto copy_hdr;
+		/* If there's data coming in with the response,
+		 * receive it to the connection's buffer.
+		 */
+		if (tcp_conn->in.datalen) {
+			iscsi_tcp_data_recv_prep(tcp_conn);
+			return 0;
+		}
 	/* fall through */
 	case ISCSI_OP_LOGOUT_RSP:
 	case ISCSI_OP_NOOP_IN:
@@ -543,461 +845,161 @@ iscsi_tcp_hdr_recv(struct iscsi_conn *conn)
 		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;
+	if (rc == 0) {
+		/* Anything that comes with data should have
+		 * been handled above. */
+		if (tcp_conn->in.datalen)
+			return ISCSI_ERR_PROTO;
+		iscsi_tcp_hdr_recv_prep(tcp_conn);
 	}
 
-	/* done with this buffer or with both - PDU and buffer */
-	tcp_conn->data_copied = 0;
-	return 0;
+	return rc;
 }
 
 /**
- * iscsi_tcp_copy - copy skb bits to the destanation buffer
- * @conn: iscsi tcp connection
+ * iscsi_tcp_hdr_recv_done - process PDU header
  *
- * 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)
+ * This is the callback invoked when the PDU header has
+ * been received. If the header is followed by additional
+ * header segments, we go back for more data.
+ */
+static int
+iscsi_tcp_hdr_recv_done(struct iscsi_tcp_conn *tcp_conn,
+			struct iscsi_segment *segment)
 {
-	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);
+	struct iscsi_conn *conn = tcp_conn->iscsi_conn;
+	struct iscsi_hdr *hdr;
 
-	/* check for non-exceptional status */
-	if (tcp_conn->in.hdr->flags & ISCSI_FLAG_DA