vfio: enable independently of PCI bus

[dpdk.git] / lib / librte_eal / linuxapp / eal / eal_vfio.c

diff --git a/lib/librte_eal/linuxapp/eal/eal_vfio.c b/lib/librte_eal/linuxapp/eal/eal_vfio.c
index d3eae20..e0d37dc 100644 (file)
--- a/lib/librte_eal/linuxapp/eal/eal_vfio.c
+++ b/lib/librte_eal/linuxapp/eal/eal_vfio.c
@@ -172,6 +172,55 @@ vfio_get_group_fd(int iommu_group_no)
        return -1;
 }
 
+
+static int
+get_vfio_group_idx(int vfio_group_fd)
+{
+       int i;
+       for (i = 0; i < VFIO_MAX_GROUPS; i++)
+               if (vfio_cfg.vfio_groups[i].fd == vfio_group_fd)
+                       return i;
+       return -1;
+}
+
+static void
+vfio_group_device_get(int vfio_group_fd)
+{
+       int i;
+
+       i = get_vfio_group_idx(vfio_group_fd);
+       if (i < 0 || i > (VFIO_MAX_GROUPS - 1))
+               RTE_LOG(ERR, EAL, "  wrong vfio_group index (%d)\n", i);
+       else
+               vfio_cfg.vfio_groups[i].devices++;
+}
+
+static void
+vfio_group_device_put(int vfio_group_fd)
+{
+       int i;
+
+       i = get_vfio_group_idx(vfio_group_fd);
+       if (i < 0 || i > (VFIO_MAX_GROUPS - 1))
+               RTE_LOG(ERR, EAL, "  wrong vfio_group index (%d)\n", i);
+       else
+               vfio_cfg.vfio_groups[i].devices--;
+}
+
+static int
+vfio_group_device_count(int vfio_group_fd)
+{
+       int i;
+
+       i = get_vfio_group_idx(vfio_group_fd);
+       if (i < 0 || i > (VFIO_MAX_GROUPS - 1)) {
+               RTE_LOG(ERR, EAL, "  wrong vfio_group index (%d)\n", i);
+               return -1;
+       }
+
+       return vfio_cfg.vfio_groups[i].devices;
+}
+
 int
 clear_group(int vfio_group_fd)
 {
@@ -180,15 +229,14 @@ clear_group(int vfio_group_fd)
 
        if (internal_config.process_type == RTE_PROC_PRIMARY) {
 
-               for (i = 0; i < VFIO_MAX_GROUPS; i++)
-                       if (vfio_cfg.vfio_groups[i].fd == vfio_group_fd) {
-                               vfio_cfg.vfio_groups[i].group_no = -1;
-                               vfio_cfg.vfio_groups[i].fd = -1;
-                               vfio_cfg.vfio_groups[i].devices = 0;
-                               vfio_cfg.vfio_active_groups--;
-                               return 0;
-                       }
-               return -1;
+               i = get_vfio_group_idx(vfio_group_fd);
+               if (i < 0)
+                       return -1;
+               vfio_cfg.vfio_groups[i].group_no = -1;
+               vfio_cfg.vfio_groups[i].fd = -1;
+               vfio_cfg.vfio_groups[i].devices = 0;
+               vfio_cfg.vfio_active_groups--;
+               return 0;
        }
 
        /* This is just for SECONDARY processes */
@@ -358,7 +406,7 @@ vfio_setup_device(const char *sysfs_base, const char *dev_addr,
                clear_group(vfio_group_fd);
                return -1;
        }
-       vfio_cfg.vfio_groups[vfio_group_fd].devices++;
+       vfio_group_device_get(vfio_group_fd);
 
        return 0;
 }
@@ -406,7 +454,8 @@ vfio_release_device(const char *sysfs_base, const char *dev_addr,
        /* An VFIO group can have several devices attached. Just when there is
         * no devices remaining should the group be closed.
         */
-       if (--vfio_cfg.vfio_groups[vfio_group_fd].devices == 0) {
+       vfio_group_device_put(vfio_group_fd);
+       if (!vfio_group_device_count(vfio_group_fd)) {
 
                if (close(vfio_group_fd) < 0) {
                        RTE_LOG(INFO, EAL, "Error when closing vfio_group_fd for %s\n",
@@ -440,7 +489,7 @@ vfio_enable(const char *modname)
        /* inform the user that we are probing for VFIO */
        RTE_LOG(INFO, EAL, "Probing VFIO support...\n");
 
-       /* check if vfio-pci module is loaded */
+       /* check if vfio module is loaded */
        vfio_available = rte_eal_check_module(modname);
 
        /* return error directly */
@@ -657,7 +706,10 @@ vfio_type1_dma_map(int vfio_container_fd)
                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;
+               if (rte_eal_iova_mode() == RTE_IOVA_VA)
+                       dma_map.iova = dma_map.vaddr;
+               else
+                       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);
@@ -710,10 +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) {
@@ -722,6 +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;
@@ -743,7 +809,10 @@ vfio_spapr_dma_map(int vfio_container_fd)
                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;
+               if (rte_eal_iova_mode() == RTE_IOVA_VA)
+                       dma_map.iova = dma_map.vaddr;
+               else
+                       dma_map.iova = ms[i].phys_addr;
                dma_map.flags = VFIO_DMA_MAP_FLAG_READ |
                                 VFIO_DMA_MAP_FLAG_WRITE;
 
@@ -767,4 +836,23 @@ vfio_noiommu_dma_map(int __rte_unused vfio_container_fd)
        return 0;
 }
 
+int
+vfio_noiommu_is_enabled(void)
+{
+       int fd, ret, cnt __rte_unused;
+       char c;
+
+       ret = -1;
+       fd = open(VFIO_NOIOMMU_MODE, O_RDONLY);
+       if (fd < 0)
+               return -1;
+
+       cnt = read(fd, &c, 1);
+       if (c == 'Y')
+               ret = 1;
+
+       close(fd);
+       return ret;
+}
+
 #endif