[dpdk-dev] [PATCH 3/4] bus/pci: enable vfio unmap resource for secondary

[Qi Zhang]

Subroutine to unmap VFIO resource is shared by secondary and
primary, and it does not work on the secondary process. Since
for secondary process, it is not necessary to close interrupt
handler, set pci bus mastering and remove vfio_res from
vfio_res_list. So, the patch adds a dedicate function to handle
the situation when a device is unmapped on a secondary process.

Signed-off-by: Qi Zhang <qi.z.zhang at intel.com>
Reviewed-by: Anatoly Burakov <anatoly.burakov at intel.com>
---
 drivers/bus/pci/linux/pci_vfio.c | 118 +++++++++++++++++++++++++++++----------
 1 file changed, 90 insertions(+), 28 deletions(-)

diff --git a/drivers/bus/pci/linux/pci_vfio.c b/drivers/bus/pci/linux/pci_vfio.c
index 933b95540..686386d6a 100644
--- a/drivers/bus/pci/linux/pci_vfio.c
+++ b/drivers/bus/pci/linux/pci_vfio.c
@@ -584,6 +584,9 @@ pci_vfio_map_resource_secondary(struct rte_pci_device *dev)
 		dev->mem_resource[i].addr = maps[i].addr;
 	}
 
+	/* we need save vfio_dev_fd, so it can be used during release */
+	dev->intr_handle.vfio_dev_fd = vfio_dev_fd;
+
 	return 0;
 err_vfio_dev_fd:
 	close(vfio_dev_fd);
@@ -603,22 +606,58 @@ pci_vfio_map_resource(struct rte_pci_device *dev)
 		return pci_vfio_map_resource_secondary(dev);
 }
 
-int
-pci_vfio_unmap_resource(struct rte_pci_device *dev)
+static struct mapped_pci_resource *
+find_and_unmap_vfio_resource(struct mapped_pci_res_list *vfio_res_list,
+			struct rte_pci_device *dev,
+			const char *pci_addr)
+{
+	struct mapped_pci_resource *vfio_res = NULL;
+	struct pci_map *maps;
+	int i;
+
+	/* Get vfio_res */
+	TAILQ_FOREACH(vfio_res, vfio_res_list, next) {
+		if (rte_pci_addr_cmp(&vfio_res->pci_addr, &dev->addr))
+			continue;
+		break;
+	}
+
+	if  (vfio_res == NULL)
+		return vfio_res;
+
+	RTE_LOG(INFO, EAL, "Releasing pci mapped resource for %s\n",
+		pci_addr);
+
+	maps = vfio_res->maps;
+	for (i = 0; i < (int) vfio_res->nb_maps; i++) {
+
+		/*
+		 * We do not need to be aware of MSI-X table BAR mappings as
+		 * when mapping. Just using current maps array is enough
+		 */
+		if (maps[i].addr) {
+			RTE_LOG(INFO, EAL, "Calling pci_unmap_resource for %s at %p\n",
+				pci_addr, maps[i].addr);
+			pci_unmap_resource(maps[i].addr, maps[i].size);
+		}
+	}
+
+	return vfio_res;
+}
+
+static int
+pci_vfio_unmap_resource_primary(struct rte_pci_device *dev)
 {
 	char pci_addr[PATH_MAX] = {0};
 	struct rte_pci_addr *loc = &dev->addr;
-	int i, ret;
 	struct mapped_pci_resource *vfio_res = NULL;
 	struct mapped_pci_res_list *vfio_res_list;
-
-	struct pci_map *maps;
+	int ret;
 
 	/* store PCI address string */
 	snprintf(pci_addr, sizeof(pci_addr), PCI_PRI_FMT,
 			loc->domain, loc->bus, loc->devid, loc->function);
 
-
 	if (close(dev->intr_handle.fd) < 0) {
 		RTE_LOG(INFO, EAL, "Error when closing eventfd file descriptor for %s\n",
 			pci_addr);
@@ -639,13 +678,10 @@ pci_vfio_unmap_resource(struct rte_pci_device *dev)
 		return ret;
 	}
 
-	vfio_res_list = RTE_TAILQ_CAST(rte_vfio_tailq.head, mapped_pci_res_list);
-	/* Get vfio_res */
-	TAILQ_FOREACH(vfio_res, vfio_res_list, next) {
-		if (rte_pci_addr_cmp(&vfio_res->pci_addr, &dev->addr))
-			continue;
-		break;
-	}
+	vfio_res_list =
+		RTE_TAILQ_CAST(rte_vfio_tailq.head, mapped_pci_res_list);
+	vfio_res = find_and_unmap_vfio_resource(vfio_res_list, dev, pci_addr);
+
 	/* if we haven't found our tailq entry, something's wrong */
 	if (vfio_res == NULL) {
 		RTE_LOG(ERR, EAL, "  %s cannot find TAILQ entry for PCI device!\n",
@@ -653,30 +689,56 @@ pci_vfio_unmap_resource(struct rte_pci_device *dev)
 		return -1;
 	}
 
-	/* unmap BARs */
-	maps = vfio_res->maps;
+	TAILQ_REMOVE(vfio_res_list, vfio_res, next);
 
-	RTE_LOG(INFO, EAL, "Releasing pci mapped resource for %s\n",
-		pci_addr);
-	for (i = 0; i < (int) vfio_res->nb_maps; i++) {
+	return 0;
+}
 
-		/*
-		 * We do not need to be aware of MSI-X table BAR mappings as
-		 * when mapping. Just using current maps array is enough
-		 */
-		if (maps[i].addr) {
-			RTE_LOG(INFO, EAL, "Calling pci_unmap_resource for %s at %p\n",
-				pci_addr, maps[i].addr);
-			pci_unmap_resource(maps[i].addr, maps[i].size);
-		}
+static int
+pci_vfio_unmap_resource_secondary(struct rte_pci_device *dev)
+{
+	char pci_addr[PATH_MAX] = {0};
+	struct rte_pci_addr *loc = &dev->addr;
+	struct mapped_pci_resource *vfio_res = NULL;
+	struct mapped_pci_res_list *vfio_res_list;
+	int ret;
+
+	/* store PCI address string */
+	snprintf(pci_addr, sizeof(pci_addr), PCI_PRI_FMT,
+			loc->domain, loc->bus, loc->devid, loc->function);
+
+	ret = rte_vfio_release_device(rte_pci_get_sysfs_path(), pci_addr,
+				  dev->intr_handle.vfio_dev_fd);
+	if (ret < 0) {
+		RTE_LOG(ERR, EAL,
+			"%s(): cannot release device\n", __func__);
+		return ret;
 	}
 
-	TAILQ_REMOVE(vfio_res_list, vfio_res, next);
+	vfio_res_list =
+		RTE_TAILQ_CAST(rte_vfio_tailq.head, mapped_pci_res_list);
+	vfio_res = find_and_unmap_vfio_resource(vfio_res_list, dev, pci_addr);
+
+	/* if we haven't found our tailq entry, something's wrong */
+	if (vfio_res == NULL) {
+		RTE_LOG(ERR, EAL, "  %s cannot find TAILQ entry for PCI device!\n",
+				pci_addr);
+		return -1;
+	}
 
 	return 0;
 }
 
 int
+pci_vfio_unmap_resource(struct rte_pci_device *dev)
+{
+	if (rte_eal_process_type() == RTE_PROC_PRIMARY)
+		return pci_vfio_unmap_resource_primary(dev);
+	else
+		return pci_vfio_unmap_resource_secondary(dev);
+}
+
+int
 pci_vfio_ioport_map(struct rte_pci_device *dev, int bar,
 		    struct rte_pci_ioport *p)
 {
-- 
2.13.6