vfio: allow secondary process to query IOMMU type

It is only possible to know IOMMU type of a given VFIO container
by attempting to initialize it. Since secondary process never
attempts to set up VFIO container itself (because they're shared
between primary and secondary), it never knows which IOMMU type
the container is using, and never sets up the appropriate config
structures. This results in inability to perform DMA mappings in
secondary process.

Fix this by allowing secondary process to query IOMMU type of
primary's default container at device initialization.

Note that this fix is assuming we're only interested in default
container.

Bugzilla ID: 174
Fixes: 6bcb7c95fe ("vfio: share default container in multi-process")
Cc: stable@dpdk.org

Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>

lib/librte_eal/linuxapp/eal/eal_vfio.c

@@ -549,6 +549,65 @@ vfio_mem_event_callback(enum rte_mem_event type, const void *addr, size_t len,
 	}
 }
 
+static int
+vfio_sync_default_container(void)
+{
+	struct rte_mp_msg mp_req, *mp_rep;
+	struct rte_mp_reply mp_reply;
+	struct timespec ts = {.tv_sec = 5, .tv_nsec = 0};
+	struct vfio_mp_param *p = (struct vfio_mp_param *)mp_req.param;
+	int iommu_type_id;
+	unsigned int i;
+
+	/* cannot be called from primary */
+	if (rte_eal_process_type() != RTE_PROC_SECONDARY)
+		return -1;
+
+	/* default container fd should have been opened in rte_vfio_enable() */
+	if (!default_vfio_cfg->vfio_enabled ||
+			default_vfio_cfg->vfio_container_fd < 0) {
+		RTE_LOG(ERR, EAL, "VFIO support is not initialized\n");
+		return -1;
+	}
+
+	/* find default container's IOMMU type */
+	p->req = SOCKET_REQ_IOMMU_TYPE;
+	strcpy(mp_req.name, EAL_VFIO_MP);
+	mp_req.len_param = sizeof(*p);
+	mp_req.num_fds = 0;
+
+	iommu_type_id = -1;
+	if (rte_mp_request_sync(&mp_req, &mp_reply, &ts) == 0 &&
+			mp_reply.nb_received == 1) {
+		mp_rep = &mp_reply.msgs[0];
+		p = (struct vfio_mp_param *)mp_rep->param;
+		if (p->result == SOCKET_OK)
+			iommu_type_id = p->iommu_type_id;
+		free(mp_reply.msgs);
+	}
+	if (iommu_type_id < 0) {
+		RTE_LOG(ERR, EAL, "Could not get IOMMU type for default container\n");
+		return -1;
+	}
+
+	/* we now have an fd for default container, as well as its IOMMU type.
+	 * now, set up default VFIO container config to match.
+	 */
+	for (i = 0; i < RTE_DIM(iommu_types); i++) {
+		const struct vfio_iommu_type *t = &iommu_types[i];
+		if (t->type_id != iommu_type_id)
+			continue;
+
+		/* we found our IOMMU type */
+		default_vfio_cfg->vfio_iommu_type = t;
+
+		return 0;
+	}
+	RTE_LOG(ERR, EAL, "Could not find IOMMU type id (%i)\n",
+			iommu_type_id);
+	return -1;
+}
+
 int
 rte_vfio_clear_group(int vfio_group_fd)
 {
@@ -745,6 +804,26 @@ rte_vfio_setup_device(const char *sysfs_base, const char *dev_addr,
 			else
 				RTE_LOG(DEBUG, EAL, "Installed memory event callback for VFIO\n");
 		}
+	} else if (rte_eal_process_type() != RTE_PROC_PRIMARY &&
+			vfio_cfg == default_vfio_cfg &&
+			vfio_cfg->vfio_iommu_type == NULL) {
+		/* if we're not a primary process, we do not set up the VFIO
+		 * container because it's already been set up by the primary
+		 * process. instead, we simply ask the primary about VFIO type
+		 * we are using, and set the VFIO config up appropriately.
+		 */
+		ret = vfio_sync_default_container();
+		if (ret < 0) {
+			RTE_LOG(ERR, EAL, "Could not sync default VFIO container\n");
+			close(vfio_group_fd);
+			rte_vfio_clear_group(vfio_group_fd);
+			return -1;
+		}
+		/* we have successfully initialized VFIO, notify user */
+		const struct vfio_iommu_type *t =
+				default_vfio_cfg->vfio_iommu_type;
+		RTE_LOG(NOTICE, EAL, "  using IOMMU type %d (%s)\n",
+				t->type_id, t->name);
 	}
 
 	/* get a file descriptor for the device */
@@ -978,6 +1057,15 @@ vfio_get_default_container_fd(void)
 	return -1;
 }
 
+int
+vfio_get_iommu_type(void)
+{
+	if (default_vfio_cfg->vfio_iommu_type == NULL)
+		return -1;
+
+	return default_vfio_cfg->vfio_iommu_type->type_id;
+}
+
 const struct vfio_iommu_type *
 vfio_set_iommu_type(int vfio_container_fd)
 {

lib/librte_eal/linuxapp/eal/eal_vfio.h

@@ -5,6 +5,8 @@
 #ifndef EAL_VFIO_H_
 #define EAL_VFIO_H_
 
+#include <rte_common.h>
+
 /*
  * determine if VFIO is present on the system
  */
@@ -122,6 +124,9 @@ int vfio_get_default_container_fd(void);
 const struct vfio_iommu_type *
 vfio_set_iommu_type(int vfio_container_fd);
 
+int
+vfio_get_iommu_type(void);
+
 /* check if we have any supported extensions */
 int
 vfio_has_supported_extensions(int vfio_container_fd);
@@ -133,6 +138,7 @@ int vfio_mp_sync_setup(void);
 #define SOCKET_REQ_CONTAINER 0x100
 #define SOCKET_REQ_GROUP 0x200
 #define SOCKET_REQ_DEFAULT_CONTAINER 0x400
+#define SOCKET_REQ_IOMMU_TYPE 0x800
 #define SOCKET_OK 0x0
 #define SOCKET_NO_FD 0x1
 #define SOCKET_ERR 0xFF
@@ -140,7 +146,11 @@ int vfio_mp_sync_setup(void);
 struct vfio_mp_param {
 	int req;
 	int result;
-	int group_num;
+	RTE_STD_C11
+	union {
+		int group_num;
+		int iommu_type_id;
+	};
 };
 
 #endif /* VFIO_PRESENT */

lib/librte_eal/linuxapp/eal/eal_vfio_mp_sync.c

@@ -77,6 +77,22 @@ vfio_mp_primary(const struct rte_mp_msg *msg, const void *peer)
 			reply.fds[0] = fd;
 		}
 		break;
+	case SOCKET_REQ_IOMMU_TYPE:
+	{
+		int iommu_type_id;
+
+		r->req = SOCKET_REQ_IOMMU_TYPE;
+
+		iommu_type_id = vfio_get_iommu_type();
+
+		if (iommu_type_id < 0)
+			r->result = SOCKET_ERR;
+		else {
+			r->iommu_type_id = iommu_type_id;
+			r->result = SOCKET_OK;
+		}
+		break;
+	}
 	default:
 		RTE_LOG(ERR, EAL, "vfio received invalid message!\n");
 		return -1;