Add ops->flush_iotlb_all operation to enable virtio-iommu for the dma-iommu deferred flush scheme. This results in a significant increase in performance in exchange for a window in which devices can still access previously IOMMU mapped memory when running with CONFIG_IOMMU_DEFAULT_DMA_LAZY. The previous strict behavior can be achieved with iommu.strict=1 on the kernel command line or CONFIG_IOMMU_DEFAULT_DMA_STRICT.
Link: https://lore.kernel.org/lkml/20230802123612.GA6142@myrica/ Signed-off-by: Niklas Schnelle <schne...@linux.ibm.com> --- drivers/iommu/virtio-iommu.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c index 3f18f69d70d8..ef6a87445105 100644 --- a/drivers/iommu/virtio-iommu.c +++ b/drivers/iommu/virtio-iommu.c @@ -926,6 +926,19 @@ static int viommu_iotlb_sync_map(struct iommu_domain *domain, return viommu_sync_req(vdomain->viommu); } +static void viommu_flush_iotlb_all(struct iommu_domain *domain) +{ + struct viommu_domain *vdomain = to_viommu_domain(domain); + + /* + * May be called before the viommu is initialized including + * while creating direct mapping + */ + if (!vdomain->nr_endpoints) + return; + viommu_sync_req(vdomain->viommu); +} + static void viommu_get_resv_regions(struct device *dev, struct list_head *head) { struct iommu_resv_region *entry, *new_entry, *msi = NULL; @@ -1051,6 +1064,8 @@ static bool viommu_capable(struct device *dev, enum iommu_cap cap) switch (cap) { case IOMMU_CAP_CACHE_COHERENCY: return true; + case IOMMU_CAP_DEFERRED_FLUSH: + return true; default: return false; } @@ -1071,6 +1086,7 @@ static struct iommu_ops viommu_ops = { .map_pages = viommu_map_pages, .unmap_pages = viommu_unmap_pages, .iova_to_phys = viommu_iova_to_phys, + .flush_iotlb_all = viommu_flush_iotlb_all, .iotlb_sync = viommu_iotlb_sync, .iotlb_sync_map = viommu_iotlb_sync_map, .free = viommu_domain_free, -- 2.39.2
