1
0
Fork 0

MLK-15007-1 iommu: arm: pgtable: alloc pagetable in DMA area

Normally the iommu pagetable could be in 64bit address space,
but we have one patch to address PCIE driver, 'commit 9e03e5076269
("MLK-15064-2 ARM64: DMA: limit the dma mask to be 32bit")'

The patch restrict swiotlb and iommu dma to be in 32bit address.

So if we allocate pages in highmem, then dma_map_single will return
a 32bit address. Then, we will get "Cannot accommodate DMA
translation for IOMMU page tables", because `dma != virt_to_phys(pages)`.

So we strict the lpae iommu pgtable in DMA area to fix this issue.

Signed-off-by: Peng Fan <peng.fan@nxp.com>
pull/10/head
Peng Fan 2017-06-28 10:46:03 +08:00 committed by Jason Liu
parent e0a722a622
commit 910ca91606
1 changed files with 2 additions and 1 deletions

View File

@ -14,6 +14,7 @@
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*
* Copyright (C) 2014 ARM Limited
* Copyright 2017 NXP
*
* Author: Will Deacon <will.deacon@arm.com>
*/
@ -215,7 +216,7 @@ static void *__arm_lpae_alloc_pages(size_t size, gfp_t gfp,
{
struct device *dev = cfg->iommu_dev;
dma_addr_t dma;
void *pages = alloc_pages_exact(size, gfp | __GFP_ZERO);
void *pages = alloc_pages_exact(size, gfp | __GFP_ZERO | __GFP_DMA);
if (!pages)
return NULL;