diff options
Diffstat (limited to 'drivers')
| -rw-r--r-- | drivers/iommu/amd/iommu.c | 23 |
1 files changed, 22 insertions, 1 deletions
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 5e4b0ee98f64..0957be3b6274 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -2054,6 +2054,27 @@ static int amd_iommu_map(struct iommu_domain *dom, unsigned long iova, return ret; } +static void amd_iommu_iotlb_gather_add_page(struct iommu_domain *domain, + struct iommu_iotlb_gather *gather, + unsigned long iova, size_t size) +{ + /* + * AMD's IOMMU can flush as many pages as necessary in a single flush. + * Unless we run in a virtual machine, which can be inferred according + * to whether "non-present cache" is on, it is probably best to prefer + * (potentially) too extensive TLB flushing (i.e., more misses) over + * mutliple TLB flushes (i.e., more flushes). For virtual machines the + * hypervisor needs to synchronize the host IOMMU PTEs with those of + * the guest, and the trade-off is different: unnecessary TLB flushes + * should be avoided. + */ + if (amd_iommu_np_cache && + iommu_iotlb_gather_is_disjoint(gather, iova, size)) + iommu_iotlb_sync(domain, gather); + + iommu_iotlb_gather_add_range(gather, iova, size); +} + static size_t amd_iommu_unmap(struct iommu_domain *dom, unsigned long iova, size_t page_size, struct iommu_iotlb_gather *gather) @@ -2068,7 +2089,7 @@ static size_t amd_iommu_unmap(struct iommu_domain *dom, unsigned long iova, r = (ops->unmap) ? ops->unmap(ops, iova, page_size, gather) : 0; - iommu_iotlb_gather_add_page(dom, gather, iova, page_size); + amd_iommu_iotlb_gather_add_page(dom, gather, iova, page_size); return r; } |