Hi Thomas,
I see rc3 out. Could this patch also go in 17.02 (rc4 ?).

This patch is ppc64le specific (w/o affecting other arch) and it enables pmd over vfio-pci be useful for this arch.

Thanks,
Gowrishankar

On Friday 10 February 2017 11:48 AM, Gowrishankar wrote:
From: Gowrishankar Muthukrishnan <gowrishanka...@linux.vnet.ibm.com>

Below changes adds pci probing support for vfio-pci devices in power8.

Signed-off-by: Gowrishankar Muthukrishnan <gowrishanka...@linux.vnet.ibm.com>
Acked-by: Chao Zhu <chao...@linux.vnet.ibm.com>
---
  lib/librte_eal/linuxapp/eal/eal_vfio.c | 88 ++++++++++++++++++++++++++++++++++
  lib/librte_eal/linuxapp/eal/eal_vfio.h |  1 +
  2 files changed, 89 insertions(+)

diff --git a/lib/librte_eal/linuxapp/eal/eal_vfio.c 
b/lib/librte_eal/linuxapp/eal/eal_vfio.c
index 702f7a2..1d4fea6 100644
--- a/lib/librte_eal/linuxapp/eal/eal_vfio.c
+++ b/lib/librte_eal/linuxapp/eal/eal_vfio.c
@@ -50,12 +50,15 @@
  static struct vfio_config vfio_cfg;

  static int vfio_type1_dma_map(int);
+static int vfio_spapr_dma_map(int);
  static int vfio_noiommu_dma_map(int);

  /* IOMMU types we support */
  static const struct vfio_iommu_type iommu_types[] = {
        /* x86 IOMMU, otherwise known as type 1 */
        { RTE_VFIO_TYPE1, "Type 1", &vfio_type1_dma_map},
+       /* ppc64 IOMMU, otherwise known as spapr */
+       { RTE_VFIO_SPAPR, "sPAPR", &vfio_spapr_dma_map},
        /* IOMMU-less mode */
        { RTE_VFIO_NOIOMMU, "No-IOMMU", &vfio_noiommu_dma_map},
  };
@@ -540,6 +543,91 @@ int vfio_setup_device(const char *sysfs_base, const char 
*dev_addr,
  }

  static int
+vfio_spapr_dma_map(int vfio_container_fd)
+{
+       const struct rte_memseg *ms = rte_eal_get_physmem_layout();
+       int i, ret;
+
+       struct vfio_iommu_spapr_register_memory reg = {
+               .argsz = sizeof(reg),
+               .flags = 0
+       };
+       struct vfio_iommu_spapr_tce_info info = {
+               .argsz = sizeof(info),
+       };
+       struct vfio_iommu_spapr_tce_create create = {
+               .argsz = sizeof(create),
+       };
+       struct vfio_iommu_spapr_tce_remove remove = {
+               .argsz = sizeof(remove),
+       };
+
+       /* query spapr iommu info */
+       ret = ioctl(vfio_container_fd, VFIO_IOMMU_SPAPR_TCE_GET_INFO, &info);
+       if (ret) {
+               RTE_LOG(ERR, EAL, "  cannot get iommu info, "
+                               "error %i (%s)\n", errno, strerror(errno));
+               return -1;
+       }
+
+       /* remove default DMA of 32 bit window */
+       remove.start_addr = info.dma32_window_start;
+       ret = ioctl(vfio_container_fd, VFIO_IOMMU_SPAPR_TCE_REMOVE, &remove);
+       if (ret) {
+               RTE_LOG(ERR, EAL, "  cannot remove default DMA window, "
+                               "error %i (%s)\n", errno, strerror(errno));
+               return -1;
+       }
+
+       /* calculate window size based on number of hugepages configured */
+       create.window_size = rte_eal_get_physmem_size();
+       create.page_shift = __builtin_ctzll(ms->hugepage_sz);
+       create.levels = 2;
+
+       ret = ioctl(vfio_container_fd, VFIO_IOMMU_SPAPR_TCE_CREATE, &create);
+       if (ret) {
+               RTE_LOG(ERR, EAL, "  cannot create new DMA window, "
+                               "error %i (%s)\n", errno, strerror(errno));
+               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;
+
+               if (ms[i].addr == NULL)
+                       break;
+
+               reg.vaddr = (uintptr_t) ms[i].addr;
+               reg.size = ms[i].len;
+               ret = ioctl(vfio_container_fd, VFIO_IOMMU_SPAPR_REGISTER_MEMORY, 
&reg);
+               if (ret) {
+                       RTE_LOG(ERR, EAL, "  cannot register vaddr for IOMMU, "
+                                       "error %i (%s)\n", errno, 
strerror(errno));
+                       return -1;
+               }
+
+               memset(&dma_map, 0, sizeof(dma_map));
+               dma_map.argsz = sizeof(struct vfio_iommu_type1_dma_map);
+               dma_map.vaddr = ms[i].addr_64;
+               dma_map.size = ms[i].len;
+               dma_map.iova = ms[i].phys_addr;
+               dma_map.flags = VFIO_DMA_MAP_FLAG_READ | 
VFIO_DMA_MAP_FLAG_WRITE;
+
+               ret = ioctl(vfio_container_fd, VFIO_IOMMU_MAP_DMA, &dma_map);
+
+               if (ret) {
+                       RTE_LOG(ERR, EAL, "  cannot set up DMA remapping, "
+                                       "error %i (%s)\n", errno, 
strerror(errno));
+                       return -1;
+               }
+
+       }
+
+       return 0;
+}
+
+static int
  vfio_noiommu_dma_map(int __rte_unused vfio_container_fd)
  {
        /* No-IOMMU mode does not need DMA mapping */
diff --git a/lib/librte_eal/linuxapp/eal/eal_vfio.h 
b/lib/librte_eal/linuxapp/eal/eal_vfio.h
index 29f7f3e..533b854 100644
--- a/lib/librte_eal/linuxapp/eal/eal_vfio.h
+++ b/lib/librte_eal/linuxapp/eal/eal_vfio.h
@@ -53,6 +53,7 @@
  #endif

  #define RTE_VFIO_TYPE1 VFIO_TYPE1_IOMMU
+#define RTE_VFIO_SPAPR VFIO_SPAPR_TCE_v2_IOMMU

  #if LINUX_VERSION_CODE < KERNEL_VERSION(4, 5, 0)
  #define RTE_VFIO_NOIOMMU 8

Reply via email to