From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751514AbdAaFxG (ORCPT ); Tue, 31 Jan 2017 00:53:06 -0500 Received: from mail.linuxfoundation.org ([140.211.169.12]:60966 "EHLO mail.linuxfoundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751381AbdAaFvF (ORCPT ); Tue, 31 Jan 2017 00:51:05 -0500 From: Greg Kroah-Hartman To: linux-kernel@vger.kernel.org Cc: Greg Kroah-Hartman , stable@vger.kernel.org, Andy Lutomirski , "Michael S. Tsirkin" , Jean-Philippe Brucker , Robin Murphy Subject: [PATCH 4.9 61/66] virtio_mmio: Set DMA masks appropriately Date: Tue, 31 Jan 2017 06:37:05 +0100 Message-Id: <20170131053605.750031206@linuxfoundation.org> X-Mailer: git-send-email 2.11.0 In-Reply-To: <20170131053603.098140622@linuxfoundation.org> References: <20170131053603.098140622@linuxfoundation.org> User-Agent: quilt/0.65 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org 4.9-stable review patch. If anyone has any objections, please let me know. ------------------ From: Robin Murphy commit f7f6634d23830ff74335734fbdb28ea109c1f349 upstream. Once DMA API usage is enabled, it becomes apparent that virtio-mmio is inadvertently relying on the default 32-bit DMA mask, which leads to problems like rapidly exhausting SWIOTLB bounce buffers. Ensure that we set the appropriate 64-bit DMA mask whenever possible, with the coherent mask suitably limited for the legacy vring as per a0be1db4304f ("virtio_pci: Limit DMA mask to 44 bits for legacy virtio devices"). Cc: Andy Lutomirski Cc: Michael S. Tsirkin Reported-by: Jean-Philippe Brucker Fixes: b42111382f0e ("virtio_mmio: Use the DMA API if enabled") Signed-off-by: Robin Murphy Signed-off-by: Michael S. Tsirkin Signed-off-by: Greg Kroah-Hartman --- drivers/virtio/virtio_mmio.c | 20 +++++++++++++++++++- 1 file changed, 19 insertions(+), 1 deletion(-) --- a/drivers/virtio/virtio_mmio.c +++ b/drivers/virtio/virtio_mmio.c @@ -59,6 +59,7 @@ #define pr_fmt(fmt) "virtio-mmio: " fmt #include +#include #include #include #include @@ -497,6 +498,7 @@ static int virtio_mmio_probe(struct plat struct virtio_mmio_device *vm_dev; struct resource *mem; unsigned long magic; + int rc; mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); if (!mem) @@ -545,9 +547,25 @@ static int virtio_mmio_probe(struct plat } vm_dev->vdev.id.vendor = readl(vm_dev->base + VIRTIO_MMIO_VENDOR_ID); - if (vm_dev->version == 1) + if (vm_dev->version == 1) { writel(PAGE_SIZE, vm_dev->base + VIRTIO_MMIO_GUEST_PAGE_SIZE); + rc = dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)); + /* + * In the legacy case, ensure our coherently-allocated virtio + * ring will be at an address expressable as a 32-bit PFN. + */ + if (!rc) + dma_set_coherent_mask(&pdev->dev, + DMA_BIT_MASK(32 + PAGE_SHIFT)); + } else { + rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); + } + if (rc) + rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (rc) + dev_warn(&pdev->dev, "Failed to enable 64-bit or 32-bit DMA. Trying to continue, but this might not work.\n"); + platform_set_drvdata(pdev, vm_dev); return register_virtio_device(&vm_dev->vdev);