From: Joerg Roedel Date: Thu, 21 Jun 2012 12:52:40 +0000 (+0200) Subject: iommu/amd: Initialize dma_ops for hotplug and sriov devices X-Git-Tag: firefly_0821_release~3680^2~2502^2~3 X-Git-Url: http://demsky.eecs.uci.edu/git/?a=commitdiff_plain;h=ac1534a55d1e87d59a21c09c570605933b551480;p=firefly-linux-kernel-4.4.55.git iommu/amd: Initialize dma_ops for hotplug and sriov devices When a device is added to the system at runtime the AMD IOMMU driver initializes the necessary data structures to handle translation for it. But it forgets to change the per-device dma_ops to point to the AMD IOMMU driver. So mapping actually never happens and all DMA accesses end in an IO_PAGE_FAULT. Fix this. Reported-by: Stefan Assmann Cc: stable@vger.kernel.org Signed-off-by: Joerg Roedel --- diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index a2e418cba0ff..dfe7d37c82c5 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -83,6 +83,8 @@ static struct iommu_ops amd_iommu_ops; static ATOMIC_NOTIFIER_HEAD(ppr_notifier); int amd_iommu_max_glx_val = -1; +static struct dma_map_ops amd_iommu_dma_ops; + /* * general struct to manage commands send to an IOMMU */ @@ -2267,6 +2269,13 @@ static int device_change_notifier(struct notifier_block *nb, list_add_tail(&dma_domain->list, &iommu_pd_list); spin_unlock_irqrestore(&iommu_pd_list_lock, flags); + dev_data = get_dev_data(dev); + + if (!dev_data->passthrough) + dev->archdata.dma_ops = &amd_iommu_dma_ops; + else + dev->archdata.dma_ops = &nommu_dma_ops; + break; case BUS_NOTIFY_DEL_DEVICE: