--- v8
+++ v4
@@ -6,42 +6,16 @@
As we are here, this removes unnecessary checks for a value returned
by pfn_to_page() as it cannot possibly return NULL.
-This moves tce_iommu_disable() later to let tce_iommu_clear() know if
-the container has been enabled because if it has not been, then
-put_page() must not be called on TCEs from the TCE table. This situation
-is not yet possible but it will after KVM acceleration patchset is
-applied.
-
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
---
-Changes:
-v6:
-* tce_get_hva() returns hva via a pointer
----
- drivers/vfio/vfio_iommu_spapr_tce.c | 68 +++++++++++++++++++++++++++----------
- 1 file changed, 50 insertions(+), 18 deletions(-)
+ drivers/vfio/vfio_iommu_spapr_tce.c | 59 +++++++++++++++++++++++++++----------
+ 1 file changed, 44 insertions(+), 15 deletions(-)
diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
-index c137bb3..ec5ee83 100644
+index 67ea392..7fd60f9 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
-@@ -196,7 +196,6 @@ static void tce_iommu_release(void *iommu_data)
- struct iommu_table *tbl = container->tbl;
-
- WARN_ON(tbl && !tbl->it_group);
-- tce_iommu_disable(container);
-
- if (tbl) {
- tce_iommu_clear(container, tbl, tbl->it_offset, tbl->it_size);
-@@ -204,63 +203,96 @@ static void tce_iommu_release(void *iommu_data)
- if (tbl->it_group)
- tce_iommu_detach_group(iommu_data, tbl->it_group);
- }
-+
-+ tce_iommu_disable(container);
-+
- mutex_destroy(&container->lock);
-
+@@ -217,25 +217,34 @@ static void tce_iommu_release(void *iommu_data)
kfree(container);
}
@@ -51,15 +25,6 @@
+ struct page *page;
+
+ if (!(oldtce & (TCE_PCI_READ | TCE_PCI_WRITE)))
-+ return;
-+
-+ /*
-+ * VFIO cannot map/unmap when a container is not enabled so
-+ * we would not need this check but KVM could map/unmap and if
-+ * this happened, we must not put pages as KVM does not get them as
-+ * it expects memory pre-registation to do this part.
-+ */
-+ if (!container->enabled)
+ return;
+
+ page = pfn_to_page(__pa(oldtce) >> PAGE_SHIFT);
@@ -93,20 +58,26 @@
}
return 0;
+@@ -253,34 +262,54 @@ static enum dma_data_direction tce_iommu_direction(unsigned long tce)
+ return DMA_NONE;
}
-+static int tce_get_hva(unsigned long tce, unsigned long *hva)
++static unsigned long tce_get_hva(struct tce_container *container,
++ unsigned page_shift, unsigned long tce)
+{
++ long ret;
+ struct page *page = NULL;
-+ enum dma_data_direction direction = iommu_tce_direction(tce);
++ unsigned long hva;
++ enum dma_data_direction direction = tce_iommu_direction(tce);
+
-+ if (get_user_pages_fast(tce & PAGE_MASK, 1,
-+ direction != DMA_TO_DEVICE, &page) != 1)
-+ return -EFAULT;
++ ret = get_user_pages_fast(tce & PAGE_MASK, 1,
++ direction != DMA_TO_DEVICE, &page);
++ if (unlikely(ret != 1))
++ return -1;
+
-+ *hva = (unsigned long) page_address(page);
++ hva = (unsigned long) page_address(page);
+
-+ return 0;
++ return hva;
+}
+
static long tce_iommu_build(struct tce_container *container,
@@ -117,17 +88,17 @@
- struct page *page = NULL;
+ struct page *page;
unsigned long hva;
- enum dma_data_direction direction = iommu_tce_direction(tce);
+ enum dma_data_direction direction = tce_iommu_direction(tce);
for (i = 0; i < pages; ++i) {
- ret = get_user_pages_fast(tce & PAGE_MASK, 1,
- direction != DMA_TO_DEVICE, &page);
- if (unlikely(ret != 1)) {
-- ret = -EFAULT;
-+ ret = tce_get_hva(tce, &hva);
-+ if (ret)
++ hva = tce_get_hva(container, tbl->it_page_shift, tce);
++ if (hva == -1) {
+ ret = -EFAULT;
break;
-- }
+ }
+ page = pfn_to_page(__pa(hva) >> PAGE_SHIFT);
if (!tce_page_is_contained(page, tbl->it_page_shift)) {
@@ -139,6 +110,8 @@
- (tce & IOMMU_PAGE_MASK(tbl) & ~PAGE_MASK);
+ /* Preserve offset within IOMMU page */
+ hva |= tce & IOMMU_PAGE_MASK(tbl) & ~PAGE_MASK;
++ /* Preserve permission bits */
++ hva |= tce & (TCE_PCI_READ | TCE_PCI_WRITE);
ret = iommu_tce_build(tbl, entry + i, hva, direction);
if (ret) {