3 files changed, 277 insertions, 39 deletions

diff --git a/drivers/bus/pci/linux/Makefile b/drivers/bus/pci/linux/Makefile
index 96ea1d54..90404468 100644
--- a/drivers/bus/pci/linux/Makefile
+++ b/drivers/bus/pci/linux/Makefile
@@ -4,5 +4,3 @@
 SRCS += pci.c
 SRCS += pci_uio.c
 SRCS += pci_vfio.c
-
-CFLAGS += -D_GNU_SOURCE
diff --git a/drivers/bus/pci/linux/pci.c b/drivers/bus/pci/linux/pci.c
index 04648ac9..45c24ef7 100644
--- a/drivers/bus/pci/linux/pci.c
+++ b/drivers/bus/pci/linux/pci.c
@@ -119,7 +119,7 @@ rte_pci_unmap_device(struct rte_pci_device *dev)
 static int
 find_max_end_va(const struct rte_memseg_list *msl, void *arg)
 {
-	size_t sz = msl->memseg_arr.len * msl->page_sz;
+	size_t sz = msl->len;
 	void *end_va = RTE_PTR_ADD(msl->base_va, sz);
 	void **max_va = arg;
 
@@ -228,6 +228,7 @@ pci_scan_one(const char *dirname, const struct rte_pci_addr *addr)
 		return -1;
 
 	memset(dev, 0, sizeof(*dev));
+	dev->device.bus = &rte_pci_bus.bus;
 	dev->addr = *addr;
 
 	/* get vendor id */
@@ -588,10 +589,8 @@ pci_one_device_iommu_support_va(struct rte_pci_device *dev)
 	fclose(fp);
 
 	mgaw = ((vtd_cap_reg & VTD_CAP_MGAW_MASK) >> VTD_CAP_MGAW_SHIFT) + 1;
-	if (mgaw < X86_VA_WIDTH)
-		return false;
 
-	return true;
+	return rte_eal_check_dma_mask(mgaw) == 0 ? true : false;
 }
 #elif defined(RTE_ARCH_PPC_64)
 static bool
@@ -620,8 +619,11 @@ pci_devices_iommu_support_va(void)
 		FOREACH_DEVICE_ON_PCIBUS(dev) {
 			if (!rte_pci_match(drv, dev))
 				continue;
-			if (!pci_one_device_iommu_support_va(dev))
-				return false;
+			/*
+			 * just one PCI device needs to be checked out because
+			 * the IOMMU hardware is the same for all of them.
+			 */
+			return pci_one_device_iommu_support_va(dev);
 		}
 	}
 	return true;
@@ -672,23 +674,21 @@ rte_pci_get_iommu_class(void)
 int rte_pci_read_config(const struct rte_pci_device *device,
 		void *buf, size_t len, off_t offset)
 {
+	char devname[RTE_DEV_NAME_MAX_LEN] = "";
 	const struct rte_intr_handle *intr_handle = &device->intr_handle;
 
-	switch (intr_handle->type) {
-	case RTE_INTR_HANDLE_UIO:
-	case RTE_INTR_HANDLE_UIO_INTX:
+	switch (device->kdrv) {
+	case RTE_KDRV_IGB_UIO:
 		return pci_uio_read_config(intr_handle, buf, len, offset);
-
 #ifdef VFIO_PRESENT
-	case RTE_INTR_HANDLE_VFIO_MSIX:
-	case RTE_INTR_HANDLE_VFIO_MSI:
-	case RTE_INTR_HANDLE_VFIO_LEGACY:
+	case RTE_KDRV_VFIO:
 		return pci_vfio_read_config(intr_handle, buf, len, offset);
 #endif
 	default:
+		rte_pci_device_name(&device->addr, devname,
+				    RTE_DEV_NAME_MAX_LEN);
 		RTE_LOG(ERR, EAL,
-			"Unknown handle type of fd %d\n",
-					intr_handle->fd);
+			"Unknown driver type for %s\n", devname);
 		return -1;
 	}
 }
@@ -697,23 +697,21 @@ int rte_pci_read_config(const struct rte_pci_device *device,
 int rte_pci_write_config(const struct rte_pci_device *device,
 		const void *buf, size_t len, off_t offset)
 {
+	char devname[RTE_DEV_NAME_MAX_LEN] = "";
 	const struct rte_intr_handle *intr_handle = &device->intr_handle;
 
-	switch (intr_handle->type) {
-	case RTE_INTR_HANDLE_UIO:
-	case RTE_INTR_HANDLE_UIO_INTX:
+	switch (device->kdrv) {
+	case RTE_KDRV_IGB_UIO:
 		return pci_uio_write_config(intr_handle, buf, len, offset);
-
 #ifdef VFIO_PRESENT
-	case RTE_INTR_HANDLE_VFIO_MSIX:
-	case RTE_INTR_HANDLE_VFIO_MSI:
-	case RTE_INTR_HANDLE_VFIO_LEGACY:
+	case RTE_KDRV_VFIO:
 		return pci_vfio_write_config(intr_handle, buf, len, offset);
 #endif
 	default:
+		rte_pci_device_name(&device->addr, devname,
+				    RTE_DEV_NAME_MAX_LEN);
 		RTE_LOG(ERR, EAL,
-			"Unknown handle type of fd %d\n",
-					intr_handle->fd);
+			"Unknown driver type for %s\n", devname);
 		return -1;
 	}
 }
diff --git a/drivers/bus/pci/linux/pci_vfio.c b/drivers/bus/pci/linux/pci_vfio.c
index 686386d6..305cc060 100644
--- a/drivers/bus/pci/linux/pci_vfio.c
+++ b/drivers/bus/pci/linux/pci_vfio.c
@@ -17,6 +17,8 @@
 #include <rte_eal_memconfig.h>
 #include <rte_malloc.h>
 #include <rte_vfio.h>
+#include <rte_eal.h>
+#include <rte_bus.h>
 
 #include "eal_filesystem.h"
 
@@ -35,7 +37,9 @@
 
 #ifdef VFIO_PRESENT
 
+#ifndef PAGE_SIZE
 #define PAGE_SIZE   (sysconf(_SC_PAGESIZE))
+#endif
 #define PAGE_MASK   (~(PAGE_SIZE - 1))
 
 static struct rte_tailq_elem rte_vfio_tailq = {
@@ -277,6 +281,114 @@ pci_vfio_setup_interrupts(struct rte_pci_device *dev, int vfio_dev_fd)
 	return -1;
 }
 
+#ifdef HAVE_VFIO_DEV_REQ_INTERFACE
+static void
+pci_vfio_req_handler(void *param)
+{
+	struct rte_bus *bus;
+	int ret;
+	struct rte_device *device = (struct rte_device *)param;
+
+	bus = rte_bus_find_by_device(device);
+	if (bus == NULL) {
+		RTE_LOG(ERR, EAL, "Cannot find bus for device (%s)\n",
+			device->name);
+		return;
+	}
+
+	/*
+	 * vfio kernel module request user space to release allocated
+	 * resources before device be deleted in kernel, so it can directly
+	 * call the vfio bus hot-unplug handler to process it.
+	 */
+	ret = bus->hot_unplug_handler(device);
+	if (ret)
+		RTE_LOG(ERR, EAL,
+			"Can not handle hot-unplug for device (%s)\n",
+			device->name);
+}
+
+/* enable notifier (only enable req now) */
+static int
+pci_vfio_enable_notifier(struct rte_pci_device *dev, int vfio_dev_fd)
+{
+	int ret;
+	int fd = -1;
+
+	/* set up an eventfd for req notifier */
+	fd = eventfd(0, EFD_NONBLOCK | EFD_CLOEXEC);
+	if (fd < 0) {
+		RTE_LOG(ERR, EAL, "Cannot set up eventfd, error %i (%s)\n",
+			errno, strerror(errno));
+		return -1;
+	}
+
+	dev->vfio_req_intr_handle.fd = fd;
+	dev->vfio_req_intr_handle.type = RTE_INTR_HANDLE_VFIO_REQ;
+	dev->vfio_req_intr_handle.vfio_dev_fd = vfio_dev_fd;
+
+	ret = rte_intr_callback_register(&dev->vfio_req_intr_handle,
+					 pci_vfio_req_handler,
+					 (void *)&dev->device);
+	if (ret) {
+		RTE_LOG(ERR, EAL, "Fail to register req notifier handler.\n");
+		goto error;
+	}
+
+	ret = rte_intr_enable(&dev->vfio_req_intr_handle);
+	if (ret) {
+		RTE_LOG(ERR, EAL, "Fail to enable req notifier.\n");
+		ret = rte_intr_callback_unregister(&dev->vfio_req_intr_handle,
+						 pci_vfio_req_handler,
+						 (void *)&dev->device);
+		if (ret < 0)
+			RTE_LOG(ERR, EAL,
+				"Fail to unregister req notifier handler.\n");
+		goto error;
+	}
+
+	return 0;
+error:
+	close(fd);
+
+	dev->vfio_req_intr_handle.fd = -1;
+	dev->vfio_req_intr_handle.type = RTE_INTR_HANDLE_UNKNOWN;
+	dev->vfio_req_intr_handle.vfio_dev_fd = -1;
+
+	return -1;
+}
+
+/* disable notifier (only disable req now) */
+static int
+pci_vfio_disable_notifier(struct rte_pci_device *dev)
+{
+	int ret;
+
+	ret = rte_intr_disable(&dev->vfio_req_intr_handle);
+	if (ret) {
+		RTE_LOG(ERR, EAL, "fail to disable req notifier.\n");
+		return -1;
+	}
+
+	ret = rte_intr_callback_unregister(&dev->vfio_req_intr_handle,
+					   pci_vfio_req_handler,
+					   (void *)&dev->device);
+	if (ret < 0) {
+		RTE_LOG(ERR, EAL,
+			 "fail to unregister req notifier handler.\n");
+		return -1;
+	}
+
+	close(dev->vfio_req_intr_handle.fd);
+
+	dev->vfio_req_intr_handle.fd = -1;
+	dev->vfio_req_intr_handle.type = RTE_INTR_HANDLE_UNKNOWN;
+	dev->vfio_req_intr_handle.vfio_dev_fd = -1;
+
+	return 0;
+}
+#endif
+
 static int
 pci_vfio_is_ioport_bar(int vfio_dev_fd, int bar_index)
 {
@@ -415,6 +527,93 @@ pci_vfio_mmap_bar(int vfio_dev_fd, struct mapped_pci_resource *vfio_res,
 	return 0;
 }
 
+/*
+ * region info may contain capability headers, so we need to keep reallocating
+ * the memory until we match allocated memory size with argsz.
+ */
+static int
+pci_vfio_get_region_info(int vfio_dev_fd, struct vfio_region_info **info,
+		int region)
+{
+	struct vfio_region_info *ri;
+	size_t argsz = sizeof(*ri);
+	int ret;
+
+	ri = malloc(sizeof(*ri));
+	if (ri == NULL) {
+		RTE_LOG(ERR, EAL, "Cannot allocate memory for region info\n");
+		return -1;
+	}
+again:
+	memset(ri, 0, argsz);
+	ri->argsz = argsz;
+	ri->index = region;
+
+	ret = ioctl(vfio_dev_fd, VFIO_DEVICE_GET_REGION_INFO, ri);
+	if (ret < 0) {
+		free(ri);
+		return ret;
+	}
+	if (ri->argsz != argsz) {
+		struct vfio_region_info *tmp;
+
+		argsz = ri->argsz;
+		tmp = realloc(ri, argsz);
+
+		if (tmp == NULL) {
+			/* realloc failed but the ri is still there */
+			free(ri);
+			RTE_LOG(ERR, EAL, "Cannot reallocate memory for region info\n");
+			return -1;
+		}
+		ri = tmp;
+		goto again;
+	}
+	*info = ri;
+
+	return 0;
+}
+
+static struct vfio_info_cap_header *
+pci_vfio_info_cap(struct vfio_region_info *info, int cap)
+{
+	struct vfio_info_cap_header *h;
+	size_t offset;
+
+	if ((info->flags & RTE_VFIO_INFO_FLAG_CAPS) == 0) {
+		/* VFIO info does not advertise capabilities */
+		return NULL;
+	}
+
+	offset = VFIO_CAP_OFFSET(info);
+	while (offset != 0) {
+		h = RTE_PTR_ADD(info, offset);
+		if (h->id == cap)
+			return h;
+		offset = h->next;
+	}
+	return NULL;
+}
+
+static int
+pci_vfio_msix_is_mappable(int vfio_dev_fd, int msix_region)
+{
+	struct vfio_region_info *info;
+	int ret;
+
+	ret = pci_vfio_get_region_info(vfio_dev_fd, &info, msix_region);
+	if (ret < 0)
+		return -1;
+
+	ret = pci_vfio_info_cap(info, RTE_VFIO_CAP_MSIX_MAPPABLE) != NULL;
+
+	/* cleanup */
+	free(info);
+
+	return ret;
+}
+
+
 static int
 pci_vfio_map_resource_primary(struct rte_pci_device *dev)
 {
@@ -430,6 +629,9 @@ pci_vfio_map_resource_primary(struct rte_pci_device *dev)
 	struct pci_map *maps;
 
 	dev->intr_handle.fd = -1;
+#ifdef HAVE_VFIO_DEV_REQ_INTERFACE
+	dev->vfio_req_intr_handle.fd = -1;
+#endif
 
 	/* store PCI address string */
 	snprintf(pci_addr, sizeof(pci_addr), PCI_PRI_FMT,
@@ -464,56 +666,75 @@ pci_vfio_map_resource_primary(struct rte_pci_device *dev)
 	if (ret < 0) {
 		RTE_LOG(ERR, EAL, "  %s cannot get MSI-X BAR number!\n",
 				pci_addr);
-		goto err_vfio_dev_fd;
+		goto err_vfio_res;
+	}
+	/* if we found our MSI-X BAR region, check if we can mmap it */
+	if (vfio_res->msix_table.bar_index != -1) {
+		int ret = pci_vfio_msix_is_mappable(vfio_dev_fd,
+				vfio_res->msix_table.bar_index);
+		if (ret < 0) {
+			RTE_LOG(ERR, EAL, "Couldn't check if MSI-X BAR is mappable\n");
+			goto err_vfio_res;
+		} else if (ret != 0) {
+			/* we can map it, so we don't care where it is */
+			RTE_LOG(DEBUG, EAL, "VFIO reports MSI-X BAR as mappable\n");
+			vfio_res->msix_table.bar_index = -1;
+		}
 	}
 
 	for (i = 0; i < (int) vfio_res->nb_maps; i++) {
-		struct vfio_region_info reg = { .argsz = sizeof(reg) };
+		struct vfio_region_info *reg = NULL;
 		void *bar_addr;
 
-		reg.index = i;
-
-		ret = ioctl(vfio_dev_fd, VFIO_DEVICE_GET_REGION_INFO, &reg);
-		if (ret) {
+		ret = pci_vfio_get_region_info(vfio_dev_fd, &reg, i);
+		if (ret < 0) {
 			RTE_LOG(ERR, EAL, "  %s cannot get device region info "
-					"error %i (%s)\n", pci_addr, errno, strerror(errno));
+				"error %i (%s)\n", pci_addr, errno,
+				strerror(errno));
 			goto err_vfio_res;
 		}
 
 		/* chk for io port region */
 		ret = pci_vfio_is_ioport_bar(vfio_dev_fd, i);
-		if (ret < 0)
+		if (ret < 0) {
+			free(reg);
 			goto err_vfio_res;
-		else if (ret) {
+		} else if (ret) {
 			RTE_LOG(INFO, EAL, "Ignore mapping IO port bar(%d)\n",
 					i);
+			free(reg);
 			continue;
 		}
 
 		/* skip non-mmapable BARs */
-		if ((reg.flags & VFIO_REGION_INFO_FLAG_MMAP) == 0)
+		if ((reg->flags & VFIO_REGION_INFO_FLAG_MMAP) == 0) {
+			free(reg);
 			continue;
+		}
 
 		/* try mapping somewhere close to the end of hugepages */
 		if (pci_map_addr == NULL)
 			pci_map_addr = pci_find_max_end_va();
 
 		bar_addr = pci_map_addr;
-		pci_map_addr = RTE_PTR_ADD(bar_addr, (size_t) reg.size);
+		pci_map_addr = RTE_PTR_ADD(bar_addr, (size_t) reg->size);
 
 		maps[i].addr = bar_addr;
-		maps[i].offset = reg.offset;
-		maps[i].size = reg.size;
+		maps[i].offset = reg->offset;
+		maps[i].size = reg->size;
 		maps[i].path = NULL; /* vfio doesn't have per-resource paths */
 
 		ret = pci_vfio_mmap_bar(vfio_dev_fd, vfio_res, i, 0);
 		if (ret < 0) {
 			RTE_LOG(ERR, EAL, "  %s mapping BAR%i failed: %s\n",
 					pci_addr, i, strerror(errno));
+			free(reg);
 			goto err_vfio_res;
 		}
 
 		dev->mem_resource[i].addr = maps[i].addr;
+
+		free(reg);
 	}
 
 	if (pci_rte_vfio_setup_device(dev, vfio_dev_fd) < 0) {
@@ -521,6 +742,13 @@ pci_vfio_map_resource_primary(struct rte_pci_device *dev)
 		goto err_vfio_res;
 	}
 
+#ifdef HAVE_VFIO_DEV_REQ_INTERFACE
+	if (pci_vfio_enable_notifier(dev, vfio_dev_fd) != 0) {
+		RTE_LOG(ERR, EAL, "Error setting up notifier!\n");
+		goto err_vfio_res;
+	}
+
+#endif
 	TAILQ_INSERT_TAIL(vfio_res_list, vfio_res, next);
 
 	return 0;
@@ -546,6 +774,9 @@ pci_vfio_map_resource_secondary(struct rte_pci_device *dev)
 	struct pci_map *maps;
 
 	dev->intr_handle.fd = -1;
+#ifdef HAVE_VFIO_DEV_REQ_INTERFACE
+	dev->vfio_req_intr_handle.fd = -1;
+#endif
 
 	/* store PCI address string */
 	snprintf(pci_addr, sizeof(pci_addr), PCI_PRI_FMT,
@@ -586,6 +817,9 @@ pci_vfio_map_resource_secondary(struct rte_pci_device *dev)
 
 	/* we need save vfio_dev_fd, so it can be used during release */
 	dev->intr_handle.vfio_dev_fd = vfio_dev_fd;
+#ifdef HAVE_VFIO_DEV_REQ_INTERFACE
+	dev->vfio_req_intr_handle.vfio_dev_fd = vfio_dev_fd;
+#endif
 
 	return 0;
 err_vfio_dev_fd:
@@ -658,6 +892,14 @@ pci_vfio_unmap_resource_primary(struct rte_pci_device *dev)
 	snprintf(pci_addr, sizeof(pci_addr), PCI_PRI_FMT,
 			loc->domain, loc->bus, loc->devid, loc->function);
 
+#ifdef HAVE_VFIO_DEV_REQ_INTERFACE
+	ret = pci_vfio_disable_notifier(dev);
+	if (ret) {
+		RTE_LOG(ERR, EAL, "fail to disable req notifier.\n");
+		return -1;
+	}
+
+#endif
 	if (close(dev->intr_handle.fd) < 0) {
 		RTE_LOG(INFO, EAL, "Error when closing eventfd file descriptor for %s\n",
 			pci_addr);