vfio: fix sPAPR IOMMU DMA window size

DMA window size needs to be big enough to span all memory segment's
physical addresses. We do not need multiple levels of IOMMU tables
as we already span ~70TB of physical memory with 16MB hugepages.

Signed-off-by: Jonas Pfefferle <jpf@zurich.ibm.com>
Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
Reviewed-by: Alexey Kardashevskiy <aik@ozlabs.ru>

diff --git a/lib/librte_eal/linuxapp/eal/eal_vfio.c b/lib/librte_eal/linuxapp/eal/eal_vfio.c
index b32cd09..9d66247 100644 (file)
--- a/lib/librte_eal/linuxapp/eal/eal_vfio.c
+++ b/lib/librte_eal/linuxapp/eal/eal_vfio.c
@@ -762,10 +762,19 @@ vfio_spapr_dma_map(int vfio_container_fd)
                return -1;
        }
 
-       /* calculate window size based on number of hugepages configured */
-       create.window_size = rte_eal_get_physmem_size();
+       /* create DMA window from 0 to max(phys_addr + len) */
+       for (i = 0; i < RTE_MAX_MEMSEG; i++) {
+               if (ms[i].addr == NULL)
+                       break;
+
+               create.window_size = RTE_MAX(create.window_size,
+                               ms[i].phys_addr + ms[i].len);
+       }
+
+       /* sPAPR requires window size to be a power of 2 */
+       create.window_size = rte_align64pow2(create.window_size);
        create.page_shift = __builtin_ctzll(ms->hugepage_sz);
-       create.levels = 2;
+       create.levels = 1;
 
        ret = ioctl(vfio_container_fd, VFIO_IOMMU_SPAPR_TCE_CREATE, &create);
        if (ret) {
@@ -774,6 +783,11 @@ vfio_spapr_dma_map(int vfio_container_fd)
                return -1;
        }
 
+       if (create.start_addr != 0) {
+               RTE_LOG(ERR, EAL, "  DMA window start address != 0\n");
+               return -1;
+       }
+
        /* map all DPDK segments for DMA. use 1:1 PA to IOVA mapping */
        for (i = 0; i < RTE_MAX_MEMSEG; i++) {
                struct vfio_iommu_type1_dma_map dma_map;