Messages in this thread Patch in this message | | | From | Greg Kroah-Hartman <> | Subject | [ 054/187] iommu/amd: Initialize dma_ops for hotplug and sriov devices | Date | Thu, 12 Jul 2012 15:33:30 -0700 |
| |
From: Greg KH <gregkh@linuxfoundation.org>
3.4-stable review patch. If anyone has any objections, please let me know.
------------------
From: Joerg Roedel <joerg.roedel@amd.com>
commit ac1534a55d1e87d59a21c09c570605933b551480 upstream.
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 <sassmann@redhat.com> Signed-off-by: Joerg Roedel <joerg.roedel@amd.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
--- drivers/iommu/amd_iommu.c | 9 +++++++++ 1 file changed, 9 insertions(+)
--- 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 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:
| |