11 files changed, 574 insertions, 65 deletions

diff --git a/drivers/bus/pci/Makefile b/drivers/bus/pci/Makefile
index cf373068..f33e0120 100644
--- a/drivers/bus/pci/Makefile
+++ b/drivers/bus/pci/Makefile
@@ -4,7 +4,7 @@
 include $(RTE_SDK)/mk/rte.vars.mk
 
 LIB = librte_bus_pci.a
-LIBABIVER := 1
+LIBABIVER := 2
 EXPORT_MAP := rte_bus_pci_version.map
 
 CFLAGS := -I$(SRCDIR) $(CFLAGS)
@@ -26,10 +26,11 @@ CFLAGS += -I$(RTE_SDK)/lib/librte_eal/$(SYSTEM)app/eal
 CFLAGS += -DALLOW_EXPERIMENTAL_API
 
 LDLIBS += -lrte_eal -lrte_mbuf -lrte_mempool -lrte_ring
-LDLIBS += -lrte_ethdev -lrte_pci
+LDLIBS += -lrte_ethdev -lrte_pci -lrte_kvargs
 
 include $(RTE_SDK)/drivers/bus/pci/$(SYSTEM)/Makefile
 SRCS-$(CONFIG_RTE_LIBRTE_PCI_BUS) := $(addprefix $(SYSTEM)/,$(SRCS))
+SRCS-$(CONFIG_RTE_LIBRTE_PCI_BUS) += pci_params.c
 SRCS-$(CONFIG_RTE_LIBRTE_PCI_BUS) += pci_common.c
 SRCS-$(CONFIG_RTE_LIBRTE_PCI_BUS) += pci_common_uio.c
 
diff --git a/drivers/bus/pci/bsd/pci.c b/drivers/bus/pci/bsd/pci.c
index 655b34b7..d09f8ee5 100644
--- a/drivers/bus/pci/bsd/pci.c
+++ b/drivers/bus/pci/bsd/pci.c
@@ -223,6 +223,8 @@ pci_scan_one(int dev_pci_fd, struct pci_conf *conf)
 	}
 
 	memset(dev, 0, sizeof(*dev));
+	dev->device.bus = &rte_pci_bus.bus;
+
 	dev->addr.domain = conf->pc_sel.pc_domain;
 	dev->addr.bus = conf->pc_sel.pc_bus;
 	dev->addr.devid = conf->pc_sel.pc_dev;
@@ -439,6 +441,8 @@ int rte_pci_read_config(const struct rte_pci_device *dev,
 {
 	int fd = -1;
 	int size;
+	/* Copy Linux implementation's behaviour */
+	const int return_len = len;
 	struct pci_io pi = {
 		.pi_sel = {
 			.pc_domain = dev->addr.domain,
@@ -469,7 +473,7 @@ int rte_pci_read_config(const struct rte_pci_device *dev,
 	}
 	close(fd);
 
-	return 0;
+	return return_len;
 
  error:
 	if (fd >= 0)
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);
diff --git a/drivers/bus/pci/meson.build b/drivers/bus/pci/meson.build
index 72939e59..a3140ff9 100644
--- a/drivers/bus/pci/meson.build
+++ b/drivers/bus/pci/meson.build
@@ -1,15 +1,18 @@
 # SPDX-License-Identifier: BSD-3-Clause
 # Copyright(c) 2017 Intel Corporation
 
+version = 2
+
 deps += ['pci']
 install_headers('rte_bus_pci.h')
-sources = files('pci_common.c', 'pci_common_uio.c')
+sources = files('pci_common.c',
+	'pci_common_uio.c',
+	'pci_params.c')
 if host_machine.system() == 'linux'
 	sources += files('linux/pci.c',
 			'linux/pci_uio.c',
 			'linux/pci_vfio.c')
 	includes += include_directories('linux')
-	cflags += ['-D_GNU_SOURCE']
 else
 	sources += files('bsd/pci.c')
 	includes += include_directories('bsd')
@@ -17,3 +20,5 @@ endif
 
 # memseg walk is not part of stable API yet
 allow_experimental_apis = true
+
+deps += ['kvargs']
diff --git a/drivers/bus/pci/pci_common.c b/drivers/bus/pci/pci_common.c
index 7736b3f9..6276e5d6 100644
--- a/drivers/bus/pci/pci_common.c
+++ b/drivers/bus/pci/pci_common.c
@@ -6,6 +6,7 @@
 #include <string.h>
 #include <inttypes.h>
 #include <stdint.h>
+#include <stdbool.h>
 #include <stdlib.h>
 #include <stdio.h>
 #include <sys/queue.h>
@@ -23,12 +24,11 @@
 #include <rte_string_fns.h>
 #include <rte_common.h>
 #include <rte_devargs.h>
+#include <rte_vfio.h>
 
 #include "private.h"
 
 
-extern struct rte_pci_bus rte_pci_bus;
-
 #define SYSFS_PCI_DEVICES "/sys/bus/pci/devices"
 
 const char *rte_pci_get_sysfs_path(void)
@@ -123,6 +123,7 @@ rte_pci_probe_one_driver(struct rte_pci_driver *dr,
 			 struct rte_pci_device *dev)
 {
 	int ret;
+	bool already_probed;
 	struct rte_pci_addr *loc;
 
 	if ((dr == NULL) || (dev == NULL))
@@ -153,6 +154,13 @@ rte_pci_probe_one_driver(struct rte_pci_driver *dr,
 		dev->device.numa_node = 0;
 	}
 
+	already_probed = rte_dev_is_probed(&dev->device);
+	if (already_probed && !(dr->drv_flags & RTE_PCI_DRV_PROBE_AGAIN)) {
+		RTE_LOG(DEBUG, EAL, "Device %s is already probed\n",
+				dev->device.name);
+		return -EEXIST;
+	}
+
 	RTE_LOG(INFO, EAL, "  probe driver: %x:%x %s\n", dev->id.vendor_id,
 		dev->id.device_id, dr->driver.name);
 
@@ -161,24 +169,24 @@ rte_pci_probe_one_driver(struct rte_pci_driver *dr,
 	 * This needs to be before rte_pci_map_device(), as it enables to use
 	 * driver flags for adjusting configuration.
 	 */
-	dev->driver = dr;
-	dev->device.driver = &dr->driver;
+	if (!already_probed)
+		dev->driver = dr;
 
-	if (dr->drv_flags & RTE_PCI_DRV_NEED_MAPPING) {
+	if (!already_probed && (dr->drv_flags & RTE_PCI_DRV_NEED_MAPPING)) {
 		/* map resources for devices that use igb_uio */
 		ret = rte_pci_map_device(dev);
 		if (ret != 0) {
 			dev->driver = NULL;
-			dev->device.driver = NULL;
 			return ret;
 		}
 	}
 
 	/* call the driver probe() function */
 	ret = dr->probe(dr, dev);
+	if (already_probed)
+		return ret; /* no rollback if already succeeded earlier */
 	if (ret) {
 		dev->driver = NULL;
-		dev->device.driver = NULL;
 		if ((dr->drv_flags & RTE_PCI_DRV_NEED_MAPPING) &&
 			/* Don't unmap if device is unsupported and
 			 * driver needs mapped resources.
@@ -186,6 +194,8 @@ rte_pci_probe_one_driver(struct rte_pci_driver *dr,
 			!(ret > 0 &&
 				(dr->drv_flags & RTE_PCI_DRV_KEEP_MAPPED_RES)))
 			rte_pci_unmap_device(dev);
+	} else {
+		dev->device.driver = &dr->driver;
 	}
 
 	return ret;
@@ -233,7 +243,7 @@ rte_pci_detach_dev(struct rte_pci_device *dev)
 
 /*
  * If vendor/device ID match, call the probe() function of all
- * registered driver for the given device. Return -1 if initialization
+ * registered driver for the given device. Return < 0 if initialization
  * failed, return 1 if no driver is found for this device.
  */
 static int
@@ -243,17 +253,13 @@ pci_probe_all_drivers(struct rte_pci_device *dev)
 	int rc = 0;
 
 	if (dev == NULL)
-		return -1;
-
-	/* Check if a driver is already loaded */
-	if (dev->driver != NULL)
-		return 0;
+		return -EINVAL;
 
 	FOREACH_DRIVER_ON_PCIBUS(dr) {
 		rc = rte_pci_probe_one_driver(dr, dev);
 		if (rc < 0)
 			/* negative value is an error */
-			return -1;
+			return rc;
 		if (rc > 0)
 			/* positive value means driver doesn't support it */
 			continue;
@@ -290,11 +296,14 @@ rte_pci_probe(void)
 			devargs->policy == RTE_DEV_WHITELISTED)
 			ret = pci_probe_all_drivers(dev);
 		if (ret < 0) {
-			RTE_LOG(ERR, EAL, "Requested device " PCI_PRI_FMT
-				 " cannot be used\n", dev->addr.domain, dev->addr.bus,
-				 dev->addr.devid, dev->addr.function);
-			rte_errno = errno;
-			failed++;
+			if (ret != -EEXIST) {
+				RTE_LOG(ERR, EAL, "Requested device "
+					PCI_PRI_FMT " cannot be used\n",
+					dev->addr.domain, dev->addr.bus,
+					dev->addr.devid, dev->addr.function);
+				rte_errno = errno;
+				failed++;
+			}
 			ret = 0;
 		}
 	}
@@ -405,6 +414,98 @@ pci_find_device(const struct rte_device *start, rte_dev_cmp_t cmp,
 	return NULL;
 }
 
+/*
+ * find the device which encounter the failure, by iterate over all device on
+ * PCI bus to check if the memory failure address is located in the range
+ * of the BARs of the device.
+ */
+static struct rte_pci_device *
+pci_find_device_by_addr(const void *failure_addr)
+{
+	struct rte_pci_device *pdev = NULL;
+	uint64_t check_point, start, end, len;
+	int i;
+
+	check_point = (uint64_t)(uintptr_t)failure_addr;
+
+	FOREACH_DEVICE_ON_PCIBUS(pdev) {
+		for (i = 0; i != RTE_DIM(pdev->mem_resource); i++) {
+			start = (uint64_t)(uintptr_t)pdev->mem_resource[i].addr;
+			len = pdev->mem_resource[i].len;
+			end = start + len;
+			if (check_point >= start && check_point < end) {
+				RTE_LOG(DEBUG, EAL, "Failure address %16.16"
+					PRIx64" belongs to device %s!\n",
+					check_point, pdev->device.name);
+				return pdev;
+			}
+		}
+	}
+	return NULL;
+}
+
+static int
+pci_hot_unplug_handler(struct rte_device *dev)
+{
+	struct rte_pci_device *pdev = NULL;
+	int ret = 0;
+
+	pdev = RTE_DEV_TO_PCI(dev);
+	if (!pdev)
+		return -1;
+
+	switch (pdev->kdrv) {
+#ifdef HAVE_VFIO_DEV_REQ_INTERFACE
+	case RTE_KDRV_VFIO:
+		/*
+		 * vfio kernel module guaranty the pci device would not be
+		 * deleted until the user space release the resource, so no
+		 * need to remap BARs resource here, just directly notify
+		 * the req event to the user space to handle it.
+		 */
+		rte_dev_event_callback_process(dev->name,
+					       RTE_DEV_EVENT_REMOVE);
+		break;
+#endif
+	case RTE_KDRV_IGB_UIO:
+	case RTE_KDRV_UIO_GENERIC:
+	case RTE_KDRV_NIC_UIO:
+		/* BARs resource is invalid, remap it to be safe. */
+		ret = pci_uio_remap_resource(pdev);
+		break;
+	default:
+		RTE_LOG(DEBUG, EAL,
+			"Not managed by a supported kernel driver, skipped\n");
+		ret = -1;
+		break;
+	}
+
+	return ret;
+}
+
+static int
+pci_sigbus_handler(const void *failure_addr)
+{
+	struct rte_pci_device *pdev = NULL;
+	int ret = 0;
+
+	pdev = pci_find_device_by_addr(failure_addr);
+	if (!pdev) {
+		/* It is a generic sigbus error, no bus would handle it. */
+		ret = 1;
+	} else {
+		/* The sigbus error is caused of hot-unplug. */
+		ret = pci_hot_unplug_handler(&pdev->device);
+		if (ret) {
+			RTE_LOG(ERR, EAL,
+				"Failed to handle hot-unplug for device %s",
+				pdev->name);
+			ret = -1;
+		}
+	}
+	return ret;
+}
+
 static int
 pci_plug(struct rte_device *dev)
 {
@@ -421,6 +522,7 @@ pci_unplug(struct rte_device *dev)
 	ret = rte_pci_detach_dev(pdev);
 	if (ret == 0) {
 		rte_pci_remove_device(pdev);
+		rte_devargs_remove(dev->devargs);
 		free(pdev);
 	}
 	return ret;
@@ -435,6 +537,9 @@ struct rte_pci_bus rte_pci_bus = {
 		.unplug = pci_unplug,
 		.parse = pci_parse,
 		.get_iommu_class = rte_pci_get_iommu_class,
+		.dev_iterate = rte_pci_dev_iterate,
+		.hot_unplug_handler = pci_hot_unplug_handler,
+		.sigbus_handler = pci_sigbus_handler,
 	},
 	.device_list = TAILQ_HEAD_INITIALIZER(rte_pci_bus.device_list),
 	.driver_list = TAILQ_HEAD_INITIALIZER(rte_pci_bus.driver_list),
diff --git a/drivers/bus/pci/pci_common_uio.c b/drivers/bus/pci/pci_common_uio.c
index 54bc20b5..7ea73dbc 100644
--- a/drivers/bus/pci/pci_common_uio.c
+++ b/drivers/bus/pci/pci_common_uio.c
@@ -146,6 +146,39 @@ pci_uio_unmap(struct mapped_pci_resource *uio_res)
 	}
 }
 
+/* remap the PCI resource of a PCI device in anonymous virtual memory */
+int
+pci_uio_remap_resource(struct rte_pci_device *dev)
+{
+	int i;
+	void *map_address;
+
+	if (dev == NULL)
+		return -1;
+
+	/* Remap all BARs */
+	for (i = 0; i != PCI_MAX_RESOURCE; i++) {
+		/* skip empty BAR */
+		if (dev->mem_resource[i].phys_addr == 0)
+			continue;
+		map_address = mmap(dev->mem_resource[i].addr,
+				(size_t)dev->mem_resource[i].len,
+				PROT_READ | PROT_WRITE,
+				MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED, -1, 0);
+		if (map_address == MAP_FAILED) {
+			RTE_LOG(ERR, EAL,
+				"Cannot remap resource for device %s\n",
+				dev->name);
+			return -1;
+		}
+		RTE_LOG(INFO, EAL,
+			"Successful remap resource for device %s\n",
+			dev->name);
+	}
+
+	return 0;
+}
+
 static struct mapped_pci_resource *
 pci_uio_find_resource(struct rte_pci_device *dev)
 {
diff --git a/drivers/bus/pci/pci_params.c b/drivers/bus/pci/pci_params.c
new file mode 100644
index 00000000..3192e9c9
--- /dev/null
+++ b/drivers/bus/pci/pci_params.c
@@ -0,0 +1,78 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright 2018 Gaëtan Rivet
+ */
+
+#include <rte_bus.h>
+#include <rte_bus_pci.h>
+#include <rte_dev.h>
+#include <rte_errno.h>
+#include <rte_kvargs.h>
+#include <rte_pci.h>
+
+#include "private.h"
+
+enum pci_params {
+	RTE_PCI_PARAM_ADDR,
+	RTE_PCI_PARAM_MAX,
+};
+
+static const char * const pci_params_keys[] = {
+	[RTE_PCI_PARAM_ADDR] = "addr",
+	[RTE_PCI_PARAM_MAX] = NULL,
+};
+
+static int
+pci_addr_kv_cmp(const char *key __rte_unused,
+		const char *value,
+		void *_addr2)
+{
+	struct rte_pci_addr _addr1;
+	struct rte_pci_addr *addr1 = &_addr1;
+	struct rte_pci_addr *addr2 = _addr2;
+
+	if (rte_pci_addr_parse(value, addr1))
+		return -1;
+	return -abs(rte_pci_addr_cmp(addr1, addr2));
+}
+
+static int
+pci_dev_match(const struct rte_device *dev,
+	      const void *_kvlist)
+{
+	const struct rte_kvargs *kvlist = _kvlist;
+	const struct rte_pci_device *pdev;
+
+	if (kvlist == NULL)
+		/* Empty string matches everything. */
+		return 0;
+	pdev = RTE_DEV_TO_PCI_CONST(dev);
+	/* if any field does not match. */
+	if (rte_kvargs_process(kvlist, pci_params_keys[RTE_PCI_PARAM_ADDR],
+			       &pci_addr_kv_cmp,
+			       (void *)(intptr_t)&pdev->addr))
+		return 1;
+	return 0;
+}
+
+void *
+rte_pci_dev_iterate(const void *start,
+		    const char *str,
+		    const struct rte_dev_iterator *it __rte_unused)
+{
+	rte_bus_find_device_t find_device;
+	struct rte_kvargs *kvargs = NULL;
+	struct rte_device *dev;
+
+	if (str != NULL) {
+		kvargs = rte_kvargs_parse(str, pci_params_keys);
+		if (kvargs == NULL) {
+			RTE_LOG(ERR, EAL, "cannot parse argument list\n");
+			rte_errno = EINVAL;
+			return NULL;
+		}
+	}
+	find_device = rte_pci_bus.bus.find_device;
+	dev = find_device(start, pci_dev_match, kvargs);
+	rte_kvargs_free(kvargs);
+	return dev;
+}
diff --git a/drivers/bus/pci/private.h b/drivers/bus/pci/private.h
index 8ddd03e1..13c3324b 100644
--- a/drivers/bus/pci/private.h
+++ b/drivers/bus/pci/private.h
@@ -10,9 +10,13 @@
 #include <rte_pci.h>
 #include <rte_bus_pci.h>
 
+extern struct rte_pci_bus rte_pci_bus;
+
 struct rte_pci_driver;
 struct rte_pci_device;
 
+extern struct rte_pci_bus rte_pci_bus;
+
 /**
  * Probe the PCI bus
  *
@@ -123,6 +127,18 @@ void pci_uio_free_resource(struct rte_pci_device *dev,
 		struct mapped_pci_resource *uio_res);
 
 /**
+ * Remap the PCI resource of a PCI device in anonymous virtual memory.
+ *
+ * @param dev
+ *   Point to the struct rte pci device.
+ * @return
+ *   - On success, zero.
+ *   - On failure, a negative value.
+ */
+int
+pci_uio_remap_resource(struct rte_pci_device *dev);
+
+/**
  * Map device memory to uio resource
  *
  * This function is private to EAL.
@@ -166,4 +182,27 @@ rte_pci_match(const struct rte_pci_driver *pci_drv,
 enum rte_iova_mode
 rte_pci_get_iommu_class(void);
 
+/*
+ * Iterate over internal devices,
+ * matching any device against the provided
+ * string.
+ *
+ * @param start
+ *   Iteration starting point.
+ *
+ * @param str
+ *   Device string to match against.
+ *
+ * @param it
+ *   (unused) iterator structure.
+ *
+ * @return
+ *   A pointer to the next matching device if any.
+ *   NULL otherwise.
+ */
+void *
+rte_pci_dev_iterate(const void *start,
+		    const char *str,
+		    const struct rte_dev_iterator *it);
+
 #endif /* _PCI_PRIVATE_H_ */
diff --git a/drivers/bus/pci/rte_bus_pci.h b/drivers/bus/pci/rte_bus_pci.h
index 0d1955ff..f0d6d81c 100644
--- a/drivers/bus/pci/rte_bus_pci.h
+++ b/drivers/bus/pci/rte_bus_pci.h
@@ -62,10 +62,12 @@ struct rte_pci_device {
 	struct rte_mem_resource mem_resource[PCI_MAX_RESOURCE];
 					    /**< PCI Memory Resource */
 	struct rte_intr_handle intr_handle; /**< Interrupt handle */
-	struct rte_pci_driver *driver;      /**< Associated driver */
+	struct rte_pci_driver *driver;      /**< PCI driver used in probing */
 	uint16_t max_vfs;                   /**< sriov enable if not zero */
 	enum rte_kernel_driver kdrv;        /**< Kernel driver passthrough */
 	char name[PCI_PRI_STR_SIZE+1];      /**< PCI location (ASCII) */
+	struct rte_intr_handle vfio_req_intr_handle;
+				/**< Handler of VFIO request interrupt */
 };
 
 /**
@@ -121,7 +123,7 @@ struct rte_pci_driver {
 	pci_probe_t *probe;                /**< Device Probe function. */
 	pci_remove_t *remove;              /**< Device Remove function. */
 	const struct rte_pci_id *id_table; /**< ID table, NULL terminated. */
-	uint32_t drv_flags;                /**< Flags contolling handling of device. */
+	uint32_t drv_flags;                /**< Flags RTE_PCI_DRV_*. */
 };
 
 /**
@@ -137,6 +139,8 @@ struct rte_pci_bus {
 #define RTE_PCI_DRV_NEED_MAPPING 0x0001
 /** Device needs PCI BAR mapping with enabled write combining (wc) */
 #define RTE_PCI_DRV_WC_ACTIVATE 0x0002
+/** Device already probed can be probed again to check for new ports. */
+#define RTE_PCI_DRV_PROBE_AGAIN 0x0004
 /** Device driver supports link state interrupt */
 #define RTE_PCI_DRV_INTR_LSC	0x0008
 /** Device driver supports device removal interrupt */
@@ -219,6 +223,8 @@ void rte_pci_unregister(struct rte_pci_driver *driver);
  *   The length of the data buffer.
  * @param offset
  *   The offset into PCI config space
+ * @return
+ *  Number of bytes read on success, negative on error.
  */
 int rte_pci_read_config(const struct rte_pci_device *device,
 		void *buf, size_t len, off_t offset);