From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-pg1-x544.google.com (mail-pg1-x544.google.com. [2607:f8b0:4864:20::544]) by gmr-mx.google.com with ESMTPS id i27si28389uat.1.2020.02.05.09.17.47 for (version=TLS1_3 cipher=TLS_AES_128_GCM_SHA256 bits=128/128); Wed, 05 Feb 2020 09:17:47 -0800 (PST) Received: by mail-pg1-x544.google.com with SMTP id j4so1284307pgi.1 for ; Wed, 05 Feb 2020 09:17:47 -0800 (PST) Return-Path: Sender: Arindam Nath From: Arindam Nath Subject: [PATCH 3/4] ntb_perf: pass correct struct device to dma_alloc_coherent Date: Wed, 5 Feb 2020 22:46:57 +0530 Message-Id: In-Reply-To: References: In-Reply-To: References: To: Jon Mason , Dave Jiang , Allen Hubbe , Sanjay R Mehta Cc: linux-ntb@googlegroups.com, linux-kernel@vger.kernel.org, Arindam Nath List-ID: From: Sanjay R Mehta Currently, ntb->dev is passed to dma_alloc_coherent and dma_free_coherent calls. The returned dma_addr_t is the CPU physical address. This works fine as long as IOMMU is disabled. But when IOMMU is enabled, we need to make sure that IOVA is returned for dma_addr_t. So the correct way to achieve this is by changing the first parameter of dma_alloc_coherent() as ntb->pdev->dev instead. Fixes: 5648e56 ("NTB: ntb_perf: Add full multi-port NTB API support") Signed-off-by: Sanjay R Mehta Signed-off-by: Arindam Nath --- drivers/ntb/test/ntb_perf.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/ntb/test/ntb_perf.c b/drivers/ntb/test/ntb_perf.c index 5116655f0211..65501f24b742 100644 --- a/drivers/ntb/test/ntb_perf.c +++ b/drivers/ntb/test/ntb_perf.c @@ -558,7 +558,7 @@ static void perf_free_inbuf(struct perf_peer *peer) return; (void)ntb_mw_clear_trans(peer->perf->ntb, peer->pidx, peer->gidx); - dma_free_coherent(&peer->perf->ntb->dev, peer->inbuf_size, + dma_free_coherent(&peer->perf->ntb->pdev->dev, peer->inbuf_size, peer->inbuf, peer->inbuf_xlat); peer->inbuf = NULL; } @@ -587,8 +587,9 @@ static int perf_setup_inbuf(struct perf_peer *peer) perf_free_inbuf(peer); - peer->inbuf = dma_alloc_coherent(&perf->ntb->dev, peer->inbuf_size, - &peer->inbuf_xlat, GFP_KERNEL); + peer->inbuf = dma_alloc_coherent(&perf->ntb->pdev->dev, + peer->inbuf_size, &peer->inbuf_xlat, + GFP_KERNEL); if (!peer->inbuf) { dev_err(&perf->ntb->dev, "Failed to alloc inbuf of %pa\n", &peer->inbuf_size); -- 2.17.1