diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c
index bd3825d..1df6c84 100644
--- a/net/rds/ib_send.c
+++ b/net/rds/ib_send.c
@@ -605,6 +605,8 @@
 		}
 
 		rds_message_addref(rm);
+		rm->data.op_dmasg = 0;
+		rm->data.op_dmaoff = 0;
 		ic->i_data_op = &rm->data;
 
 		/* Finalize the header */
@@ -658,7 +660,7 @@
 	send = &ic->i_sends[pos];
 	first = send;
 	prev = NULL;
-	scat = &ic->i_data_op->op_sg[sg];
+	scat = &ic->i_data_op->op_sg[rm->data.op_dmasg];
 	i = 0;
 	do {
 		unsigned int len = 0;
@@ -680,17 +682,20 @@
 		/* Set up the data, if present */
 		if (i < work_alloc
 		    && scat != &rm->data.op_sg[rm->data.op_count]) {
-			len = min(RDS_FRAG_SIZE, ib_sg_dma_len(dev, scat) - off);
+			len = min(RDS_FRAG_SIZE,
+				ib_sg_dma_len(dev, scat) - rm->data.op_dmaoff);
 			send->s_wr.num_sge = 2;
 
-			send->s_sge[1].addr = ib_sg_dma_address(dev, scat) + off;
+			send->s_sge[1].addr = ib_sg_dma_address(dev, scat);
+			send->s_sge[1].addr += rm->data.op_dmaoff;
 			send->s_sge[1].length = len;
 
 			bytes_sent += len;
-			off += len;
-			if (off == ib_sg_dma_len(dev, scat)) {
+			rm->data.op_dmaoff += len;
+			if (rm->data.op_dmaoff == ib_sg_dma_len(dev, scat)) {
 				scat++;
-				off = 0;
+				rm->data.op_dmasg++;
+				rm->data.op_dmaoff = 0;
 			}
 		}
 
diff --git a/net/rds/iw_send.c b/net/rds/iw_send.c
index 1383478..334fe98 100644
--- a/net/rds/iw_send.c
+++ b/net/rds/iw_send.c
@@ -581,6 +581,8 @@
 		ic->i_unsignaled_wrs = rds_iw_sysctl_max_unsig_wrs;
 		ic->i_unsignaled_bytes = rds_iw_sysctl_max_unsig_bytes;
 		rds_message_addref(rm);
+		rm->data.op_dmasg = 0;
+		rm->data.op_dmaoff = 0;
 		ic->i_rm = rm;
 
 		/* Finalize the header */
@@ -622,7 +624,7 @@
 	send = &ic->i_sends[pos];
 	first = send;
 	prev = NULL;
-	scat = &rm->data.op_sg[sg];
+	scat = &rm->data.op_sg[rm->data.op_dmasg];
 	sent = 0;
 	i = 0;
 
@@ -656,10 +658,11 @@
 
 		send = &ic->i_sends[pos];
 
-		len = min(RDS_FRAG_SIZE, ib_sg_dma_len(dev, scat) - off);
+		len = min(RDS_FRAG_SIZE,
+			  ib_sg_dma_len(dev, scat) - rm->data.op_dmaoff);
 		rds_iw_xmit_populate_wr(ic, send, pos,
-				ib_sg_dma_address(dev, scat) + off, len,
-				send_flags);
+			ib_sg_dma_address(dev, scat) + rm->data.op_dmaoff, len,
+			send_flags);
 
 		/*
 		 * We want to delay signaling completions just enough to get
@@ -687,10 +690,11 @@
 			 &send->s_wr, send->s_wr.num_sge, send->s_wr.next);
 
 		sent += len;
-		off += len;
-		if (off == ib_sg_dma_len(dev, scat)) {
+		rm->data.op_dmaoff += len;
+		if (rm->data.op_dmaoff == ib_sg_dma_len(dev, scat)) {
 			scat++;
-			off = 0;
+			rm->data.op_dmaoff = 0;
+			rm->data.op_dmasg++;
 		}
 
 add_header:
diff --git a/net/rds/rds.h b/net/rds/rds.h
index 0d41155..d2c6009 100644
--- a/net/rds/rds.h
+++ b/net/rds/rds.h
@@ -363,6 +363,8 @@
 			unsigned int		op_active:1;
 			unsigned int		op_nents;
 			unsigned int		op_count;
+			unsigned int		op_dmasg;
+			unsigned int		op_dmaoff;
 			struct scatterlist	*op_sg;
 		} data;
 	};