diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c
index 758e25893b38..508e833f05b4 100644
--- a/drivers/misc/fastrpc.c
+++ b/drivers/misc/fastrpc.c
@@ -279,6 +279,7 @@ struct fastrpc_session_ctx {
 	int sid;
 	bool used;
 	bool valid;
+	bool coherent;
 };
 
 struct fastrpc_channel_ctx {
@@ -1056,6 +1057,64 @@ static int fastrpc_create_maps(struct fastrpc_invoke_ctx *ctx)
 	return 0;
 }
 
+static void fastrpc_flush_args(struct fastrpc_invoke_ctx *ctx)
+{
+	union fastrpc_remote_arg *rpra = ctx->rpra;
+	int i, inbufs, outbufs;
+
+	inbufs = REMOTE_SCALARS_INBUFS(ctx->sc);
+	outbufs = REMOTE_SCALARS_OUTBUFS(ctx->sc);
+
+	for (i = 0; i < inbufs + outbufs; ++i) {
+		int raix = ctx->olaps[i].raix;
+		struct fastrpc_map *map = ctx->maps[raix];
+
+		if (raix + 1 > inbufs)
+			continue;
+		if (!map || !map->buf)
+			continue;
+
+		if (rpra[raix].buf.len && ctx->olaps[i].mstart) {
+			dma_buf_begin_cpu_access(map->buf, DMA_TO_DEVICE);
+			dma_buf_end_cpu_access(map->buf, DMA_TO_DEVICE);
+		}
+	}
+}
+
+static void fastrpc_inv_args(struct fastrpc_invoke_ctx *ctx)
+{
+	union fastrpc_remote_arg *rpra = ctx->rpra;
+	int i, inbufs, outbufs;
+
+	inbufs = REMOTE_SCALARS_INBUFS(ctx->sc);
+	outbufs = REMOTE_SCALARS_OUTBUFS(ctx->sc);
+
+	for (i = 0; i < inbufs + outbufs; ++i) {
+		int raix = ctx->olaps[i].raix;
+		struct fastrpc_map *map = ctx->maps[raix];
+
+		if (raix + 1 <= inbufs)
+			continue;
+		if (!rpra[raix].buf.len)
+			continue;
+		if (!map || !map->buf)
+			continue;
+
+		/*
+		 * Skip invalidation if the argument overlaps with the
+		 * RPC control header page.
+		 */
+		if (((uintptr_t)rpra & PAGE_MASK) ==
+			((uintptr_t)rpra[raix].buf.pv & PAGE_MASK))
+			continue;
+
+		if (ctx->olaps[i].mstart) {
+			dma_buf_begin_cpu_access(map->buf, DMA_FROM_DEVICE);
+			dma_buf_end_cpu_access(map->buf, DMA_TO_DEVICE);
+		}
+	}
+}
+
 static struct fastrpc_invoke_buf *fastrpc_invoke_buf_start(union fastrpc_remote_arg *pra, int len)
 {
 	return (struct fastrpc_invoke_buf *)(&pra[len]);
@@ -1179,6 +1238,9 @@ static int fastrpc_get_args(u32 kernel, struct fastrpc_invoke_ctx *ctx)
 		}
 	}
 
+	if (!ctx->fl->sctx->coherent)
+		fastrpc_flush_args(ctx);
+
 	for (i = ctx->nbufs; i < ctx->nscalars; ++i) {
 		list[i].num = ctx->args[i].length ? 1 : 0;
 		list[i].pgidx = i;
@@ -1404,6 +1466,9 @@ static int fastrpc_internal_invoke(struct fastrpc_user *fl,  u32 kernel,
 	}
 	/* make sure that all memory writes by DSP are seen by CPU */
 	dma_rmb();
+	if (!fl->sctx->coherent)
+		fastrpc_inv_args(ctx);
+
 	/* populate all the output buffers with results */
 	err = fastrpc_put_args(ctx, kernel);
 	if (err)
@@ -2334,6 +2399,7 @@ static int fastrpc_cb_probe(struct platform_device *pdev)
 	sess->used = false;
 	sess->valid = true;
 	sess->dev = dev;
+	sess->coherent = of_property_read_bool(dev->of_node, "dma-coherent");
 	dev_set_drvdata(dev, sess);
 
 	if (of_property_read_u32(dev->of_node, "reg", &sess->sid))