Imported Upstream version 16.07-rc2

Change-Id: Ie9e8ec528a2a0dace085c5e44aa7fa3b489d4ba0
Signed-off-by: Ricardo Salveti <ricardo.salveti@linaro.org>

11 files changed, 724 insertions, 579 deletions

diff --git a/lib/librte_eal/linuxapp/eal/Makefile b/lib/librte_eal/linuxapp/eal/Makefile
index 30b30f33..1a976931 100644
--- a/lib/librte_eal/linuxapp/eal/Makefile
+++ b/lib/librte_eal/linuxapp/eal/Makefile
@@ -66,10 +66,11 @@ SRCS-$(CONFIG_RTE_EXEC_ENV_LINUXAPP) += eal_xen_memory.c
 endif
 SRCS-$(CONFIG_RTE_EXEC_ENV_LINUXAPP) += eal_thread.c
 SRCS-$(CONFIG_RTE_EXEC_ENV_LINUXAPP) += eal_log.c
+SRCS-$(CONFIG_RTE_EXEC_ENV_LINUXAPP) += eal_vfio.c
+SRCS-$(CONFIG_RTE_EXEC_ENV_LINUXAPP) += eal_vfio_mp_sync.c
 SRCS-$(CONFIG_RTE_EXEC_ENV_LINUXAPP) += eal_pci.c
 SRCS-$(CONFIG_RTE_EXEC_ENV_LINUXAPP) += eal_pci_uio.c
 SRCS-$(CONFIG_RTE_EXEC_ENV_LINUXAPP) += eal_pci_vfio.c
-SRCS-$(CONFIG_RTE_EXEC_ENV_LINUXAPP) += eal_pci_vfio_mp_sync.c
 SRCS-$(CONFIG_RTE_EXEC_ENV_LINUXAPP) += eal_debug.c
 SRCS-$(CONFIG_RTE_EXEC_ENV_LINUXAPP) += eal_lcore.c
 SRCS-$(CONFIG_RTE_EXEC_ENV_LINUXAPP) += eal_timer.c
@@ -110,7 +111,7 @@ CFLAGS_eal_common_cpuflags.o := $(CPUFLAGS_LIST)
 
 CFLAGS_eal.o := -D_GNU_SOURCE
 CFLAGS_eal_interrupts.o := -D_GNU_SOURCE
-CFLAGS_eal_pci_vfio_mp_sync.o := -D_GNU_SOURCE
+CFLAGS_eal_vfio_mp_sync.o := -D_GNU_SOURCE
 CFLAGS_eal_timer.o := -D_GNU_SOURCE
 CFLAGS_eal_lcore.o := -D_GNU_SOURCE
 CFLAGS_eal_thread.o := -D_GNU_SOURCE
diff --git a/lib/librte_eal/linuxapp/eal/eal.c b/lib/librte_eal/linuxapp/eal/eal.c
index 543ef869..3fb2188f 100644
--- a/lib/librte_eal/linuxapp/eal/eal.c
+++ b/lib/librte_eal/linuxapp/eal/eal.c
@@ -82,6 +82,7 @@
 #include "eal_filesystem.h"
 #include "eal_hugepages.h"
 #include "eal_options.h"
+#include "eal_vfio.h"
 
 #define MEMSIZE_IF_NO_HUGE_PAGE (64ULL * 1024ULL * 1024ULL)
 
@@ -701,6 +702,33 @@ rte_eal_iopl_init(void)
 	return 0;
 }
 
+#ifdef VFIO_PRESENT
+static int rte_eal_vfio_setup(void)
+{
+	int vfio_enabled = 0;
+
+	if (!internal_config.no_pci) {
+		pci_vfio_enable();
+		vfio_enabled |= pci_vfio_is_enabled();
+	}
+
+	if (vfio_enabled) {
+
+		/* if we are primary process, create a thread to communicate with
+		 * secondary processes. the thread will use a socket to wait for
+		 * requests from secondary process to send open file descriptors,
+		 * because VFIO does not allow multiple open descriptors on a group or
+		 * VFIO container.
+		 */
+		if (internal_config.process_type == RTE_PROC_PRIMARY &&
+				vfio_mp_sync_setup() < 0)
+			return -1;
+	}
+
+	return 0;
+}
+#endif
+
 /* Launch threads, called at application init(). */
 int
 rte_eal_init(int argc, char **argv)
@@ -764,6 +792,11 @@ rte_eal_init(int argc, char **argv)
 	if (rte_eal_pci_init() < 0)
 		rte_panic("Cannot init PCI\n");
 
+#ifdef VFIO_PRESENT
+	if (rte_eal_vfio_setup() < 0)
+		rte_panic("Cannot init VFIO\n");
+#endif
+
 #ifdef RTE_LIBRTE_IVSHMEM
 	if (rte_eal_ivshmem_init() < 0)
 		rte_panic("Cannot init IVSHMEM\n");
diff --git a/lib/librte_eal/linuxapp/eal/eal_memory.c b/lib/librte_eal/linuxapp/eal/eal_memory.c
index 5578c254..42a29faf 100644
--- a/lib/librte_eal/linuxapp/eal/eal_memory.c
+++ b/lib/librte_eal/linuxapp/eal/eal_memory.c
@@ -164,6 +164,29 @@ rte_mem_virt2phy(const void *virtaddr)
 	int page_size;
 	off_t offset;
 
+	/* when using dom0, /proc/self/pagemap always returns 0, check in
+	 * dpdk memory by browsing the memsegs */
+	if (rte_xen_dom0_supported()) {
+		struct rte_mem_config *mcfg;
+		struct rte_memseg *memseg;
+		unsigned i;
+
+		mcfg = rte_eal_get_configuration()->mem_config;
+		for (i = 0; i < RTE_MAX_MEMSEG; i++) {
+			memseg = &mcfg->memseg[i];
+			if (memseg->addr == NULL)
+				break;
+			if (virtaddr > memseg->addr &&
+					virtaddr < RTE_PTR_ADD(memseg->addr,
+						memseg->len)) {
+				return memseg->phys_addr +
+					RTE_PTR_DIFF(virtaddr, memseg->addr);
+			}
+		}
+
+		return RTE_BAD_PHYS_ADDR;
+	}
+
 	/* Cannot parse /proc/self/pagemap, no need to log errors everywhere */
 	if (!proc_pagemap_readable)
 		return RTE_BAD_PHYS_ADDR;
@@ -1136,7 +1159,7 @@ int
 rte_eal_hugepage_init(void)
 {
 	struct rte_mem_config *mcfg;
-	struct hugepage_file *hugepage, *tmp_hp = NULL;
+	struct hugepage_file *hugepage = NULL, *tmp_hp = NULL;
 	struct hugepage_info used_hp[MAX_HUGEPAGE_SIZES];
 
 	uint64_t memory[RTE_MAX_NUMA_NODES];
@@ -1479,14 +1502,19 @@ rte_eal_hugepage_init(void)
 			"of memory.\n",
 			i, nr_hugefiles, RTE_STR(CONFIG_RTE_MAX_MEMSEG),
 			RTE_MAX_MEMSEG);
-		return -ENOMEM;
+		goto fail;
 	}
 
+	munmap(hugepage, nr_hugefiles * sizeof(struct hugepage_file));
+
 	return 0;
 
 fail:
 	huge_recover_sigbus();
 	free(tmp_hp);
+	if (hugepage != NULL)
+		munmap(hugepage, nr_hugefiles * sizeof(struct hugepage_file));
+
 	return -1;
 }
 
diff --git a/lib/librte_eal/linuxapp/eal/eal_pci.c b/lib/librte_eal/linuxapp/eal/eal_pci.c
index f9c3efd2..cd9de7cc 100644
--- a/lib/librte_eal/linuxapp/eal/eal_pci.c
+++ b/lib/librte_eal/linuxapp/eal/eal_pci.c
@@ -754,21 +754,6 @@ rte_eal_pci_init(void)
 		RTE_LOG(ERR, EAL, "%s(): Cannot scan PCI bus\n", __func__);
 		return -1;
 	}
-#ifdef VFIO_PRESENT
-	pci_vfio_enable();
-
-	if (pci_vfio_is_enabled()) {
-
-		/* if we are primary process, create a thread to communicate with
-		 * secondary processes. the thread will use a socket to wait for
-		 * requests from secondary process to send open file descriptors,
-		 * because VFIO does not allow multiple open descriptors on a group or
-		 * VFIO container.
-		 */
-		if (internal_config.process_type == RTE_PROC_PRIMARY &&
-				pci_vfio_mp_sync_setup() < 0)
-			return -1;
-	}
-#endif
+
 	return 0;
 }
diff --git a/lib/librte_eal/linuxapp/eal/eal_pci_init.h b/lib/librte_eal/linuxapp/eal/eal_pci_init.h
index f72a2548..6a960d1b 100644
--- a/lib/librte_eal/linuxapp/eal/eal_pci_init.h
+++ b/lib/librte_eal/linuxapp/eal/eal_pci_init.h
@@ -74,12 +74,6 @@ int pci_uio_ioport_unmap(struct rte_pci_ioport *p);
 
 #ifdef VFIO_PRESENT
 
-#define VFIO_MAX_GROUPS 64
-
-int pci_vfio_enable(void);
-int pci_vfio_is_enabled(void);
-int pci_vfio_mp_sync_setup(void);
-
 /* access config space */
 int pci_vfio_read_config(const struct rte_intr_handle *intr_handle,
 			 void *buf, size_t len, off_t offs);
@@ -96,41 +90,6 @@ int pci_vfio_ioport_unmap(struct rte_pci_ioport *p);
 
 /* map VFIO resource prototype */
 int pci_vfio_map_resource(struct rte_pci_device *dev);
-int pci_vfio_get_group_fd(int iommu_group_fd);
-int pci_vfio_get_container_fd(void);
-
-/*
- * Function prototypes for VFIO multiprocess sync functions
- */
-int vfio_mp_sync_send_request(int socket, int req);
-int vfio_mp_sync_receive_request(int socket);
-int vfio_mp_sync_send_fd(int socket, int fd);
-int vfio_mp_sync_receive_fd(int socket);
-int vfio_mp_sync_connect_to_primary(void);
-
-/* socket comm protocol definitions */
-#define SOCKET_REQ_CONTAINER 0x100
-#define SOCKET_REQ_GROUP 0x200
-#define SOCKET_OK 0x0
-#define SOCKET_NO_FD 0x1
-#define SOCKET_ERR 0xFF
-
-/*
- * we don't need to store device fd's anywhere since they can be obtained from
- * the group fd via an ioctl() call.
- */
-struct vfio_group {
-	int group_no;
-	int fd;
-};
-
-struct vfio_config {
-	int vfio_enabled;
-	int vfio_container_fd;
-	int vfio_container_has_dma;
-	int vfio_group_idx;
-	struct vfio_group vfio_groups[VFIO_MAX_GROUPS];
-};
 
 #endif
 
diff --git a/lib/librte_eal/linuxapp/eal/eal_pci_vfio.c b/lib/librte_eal/linuxapp/eal/eal_pci_vfio.c
index f91b9242..46cd6831 100644
--- a/lib/librte_eal/linuxapp/eal/eal_pci_vfio.c
+++ b/lib/librte_eal/linuxapp/eal/eal_pci_vfio.c
@@ -43,11 +43,11 @@
 #include <rte_pci.h>
 #include <rte_eal_memconfig.h>
 #include <rte_malloc.h>
-#include <eal_private.h>
 
 #include "eal_filesystem.h"
 #include "eal_pci_init.h"
 #include "eal_vfio.h"
+#include "eal_private.h"
 
 /**
  * @file
@@ -69,78 +69,6 @@ static struct rte_tailq_elem rte_vfio_tailq = {
 };
 EAL_REGISTER_TAILQ(rte_vfio_tailq)
 
-#define VFIO_DIR "/dev/vfio"
-#define VFIO_CONTAINER_PATH "/dev/vfio/vfio"
-#define VFIO_GROUP_FMT "/dev/vfio/%u"
-#define VFIO_NOIOMMU_GROUP_FMT "/dev/vfio/noiommu-%u"
-#define VFIO_GET_REGION_ADDR(x) ((uint64_t) x << 40ULL)
-#define VFIO_GET_REGION_IDX(x) (x >> 40)
-
-/* per-process VFIO config */
-static struct vfio_config vfio_cfg;
-
-/* DMA mapping function prototype.
- * Takes VFIO container fd as a parameter.
- * Returns 0 on success, -1 on error.
- * */
-typedef int (*vfio_dma_func_t)(int);
-
-struct vfio_iommu_type {
-	int type_id;
-	const char *name;
-	vfio_dma_func_t dma_map_func;
-};
-
-static int vfio_type1_dma_map(int);
-static int vfio_noiommu_dma_map(int);
-
-/* IOMMU types we support */
-static const struct vfio_iommu_type iommu_types[] = {
-	/* x86 IOMMU, otherwise known as type 1 */
-	{ RTE_VFIO_TYPE1, "Type 1", &vfio_type1_dma_map},
-	/* IOMMU-less mode */
-	{ RTE_VFIO_NOIOMMU, "No-IOMMU", &vfio_noiommu_dma_map},
-};
-
-int
-vfio_type1_dma_map(int vfio_container_fd)
-{
-	const struct rte_memseg *ms = rte_eal_get_physmem_layout();
-	int i, ret;
-
-	/* 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;
-
-		if (ms[i].addr == NULL)
-			break;
-
-		memset(&dma_map, 0, sizeof(dma_map));
-		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;
-		dma_map.flags = VFIO_DMA_MAP_FLAG_READ | VFIO_DMA_MAP_FLAG_WRITE;
-
-		ret = ioctl(vfio_container_fd, VFIO_IOMMU_MAP_DMA, &dma_map);
-
-		if (ret) {
-			RTE_LOG(ERR, EAL, "  cannot set up DMA remapping, "
-					"error %i (%s)\n", errno, strerror(errno));
-			return -1;
-		}
-	}
-
-	return 0;
-}
-
-int
-vfio_noiommu_dma_map(int __rte_unused vfio_container_fd)
-{
-	/* No-IOMMU mode does not need DMA mapping */
-	return 0;
-}
-
 int
 pci_vfio_read_config(const struct rte_intr_handle *intr_handle,
 		    void *buf, size_t len, off_t offs)
@@ -272,63 +200,6 @@ pci_vfio_set_bus_master(int dev_fd)
 	return 0;
 }
 
-/* pick IOMMU type. returns a pointer to vfio_iommu_type or NULL for error */
-static const struct vfio_iommu_type *
-pci_vfio_set_iommu_type(int vfio_container_fd) {
-	unsigned idx;
-	for (idx = 0; idx < RTE_DIM(iommu_types); idx++) {
-		const struct vfio_iommu_type *t = &iommu_types[idx];
-
-		int ret = ioctl(vfio_container_fd, VFIO_SET_IOMMU,
-				t->type_id);
-		if (!ret) {
-			RTE_LOG(NOTICE, EAL, "  using IOMMU type %d (%s)\n",
-					t->type_id, t->name);
-			return t;
-		}
-		/* not an error, there may be more supported IOMMU types */
-		RTE_LOG(DEBUG, EAL, "  set IOMMU type %d (%s) failed, "
-				"error %i (%s)\n", t->type_id, t->name, errno,
-				strerror(errno));
-	}
-	/* if we didn't find a suitable IOMMU type, fail */
-	return NULL;
-}
-
-/* check if we have any supported extensions */
-static int
-pci_vfio_has_supported_extensions(int vfio_container_fd) {
-	int ret;
-	unsigned idx, n_extensions = 0;
-	for (idx = 0; idx < RTE_DIM(iommu_types); idx++) {
-		const struct vfio_iommu_type *t = &iommu_types[idx];
-
-		ret = ioctl(vfio_container_fd, VFIO_CHECK_EXTENSION,
-				t->type_id);
-		if (ret < 0) {
-			RTE_LOG(ERR, EAL, "  could not get IOMMU type, "
-				"error %i (%s)\n", errno,
-				strerror(errno));
-			close(vfio_container_fd);
-			return -1;
-		} else if (ret == 1) {
-			/* we found a supported extension */
-			n_extensions++;
-		}
-		RTE_LOG(DEBUG, EAL, "  IOMMU type %d (%s) is %s\n",
-				t->type_id, t->name,
-				ret ? "supported" : "not supported");
-	}
-
-	/* if we didn't find any supported IOMMU types, fail */
-	if (!n_extensions) {
-		close(vfio_container_fd);
-		return -1;
-	}
-
-	return 0;
-}
-
 /* set up interrupt support (but not enable interrupts) */
 static int
 pci_vfio_setup_interrupts(struct rte_pci_device *dev, int vfio_dev_fd)
@@ -425,220 +296,6 @@ pci_vfio_setup_interrupts(struct rte_pci_device *dev, int vfio_dev_fd)
 	return -1;
 }
 
-/* open container fd or get an existing one */
-int
-pci_vfio_get_container_fd(void)
-{
-	int ret, vfio_container_fd;
-
-	/* if we're in a primary process, try to open the container */
-	if (internal_config.process_type == RTE_PROC_PRIMARY) {
-		vfio_container_fd = open(VFIO_CONTAINER_PATH, O_RDWR);
-		if (vfio_container_fd < 0) {
-			RTE_LOG(ERR, EAL, "  cannot open VFIO container, "
-					"error %i (%s)\n", errno, strerror(errno));
-			return -1;
-		}
-
-		/* check VFIO API version */
-		ret = ioctl(vfio_container_fd, VFIO_GET_API_VERSION);
-		if (ret != VFIO_API_VERSION) {
-			if (ret < 0)
-				RTE_LOG(ERR, EAL, "  could not get VFIO API version, "
-						"error %i (%s)\n", errno, strerror(errno));
-			else
-				RTE_LOG(ERR, EAL, "  unsupported VFIO API version!\n");
-			close(vfio_container_fd);
-			return -1;
-		}
-
-		ret = pci_vfio_has_supported_extensions(vfio_container_fd);
-		if (ret) {
-			RTE_LOG(ERR, EAL, "  no supported IOMMU "
-					"extensions found!\n");
-			return -1;
-		}
-
-		return vfio_container_fd;
-	} else {
-		/*
-		 * if we're in a secondary process, request container fd from the
-		 * primary process via our socket
-		 */
-		int socket_fd;
-
-		socket_fd = vfio_mp_sync_connect_to_primary();
-		if (socket_fd < 0) {
-			RTE_LOG(ERR, EAL, "  cannot connect to primary process!\n");
-			return -1;
-		}
-		if (vfio_mp_sync_send_request(socket_fd, SOCKET_REQ_CONTAINER) < 0) {
-			RTE_LOG(ERR, EAL, "  cannot request container fd!\n");
-			close(socket_fd);
-			return -1;
-		}
-		vfio_container_fd = vfio_mp_sync_receive_fd(socket_fd);
-		if (vfio_container_fd < 0) {
-			RTE_LOG(ERR, EAL, "  cannot get container fd!\n");
-			close(socket_fd);
-			return -1;
-		}
-		close(socket_fd);
-		return vfio_container_fd;
-	}
-
-	return -1;
-}
-
-/* open group fd or get an existing one */
-int
-pci_vfio_get_group_fd(int iommu_group_no)
-{
-	int i;
-	int vfio_group_fd;
-	char filename[PATH_MAX];
-
-	/* check if we already have the group descriptor open */
-	for (i = 0; i < vfio_cfg.vfio_group_idx; i++)
-		if (vfio_cfg.vfio_groups[i].group_no == iommu_group_no)
-			return vfio_cfg.vfio_groups[i].fd;
-
-	/* if primary, try to open the group */
-	if (internal_config.process_type == RTE_PROC_PRIMARY) {
-		/* try regular group format */
-		snprintf(filename, sizeof(filename),
-				 VFIO_GROUP_FMT, iommu_group_no);
-		vfio_group_fd = open(filename, O_RDWR);
-		if (vfio_group_fd < 0) {
-			/* if file not found, it's not an error */
-			if (errno != ENOENT) {
-				RTE_LOG(ERR, EAL, "Cannot open %s: %s\n", filename,
-						strerror(errno));
-				return -1;
-			}
-
-			/* special case: try no-IOMMU path as well */
-			snprintf(filename, sizeof(filename),
-					VFIO_NOIOMMU_GROUP_FMT, iommu_group_no);
-			vfio_group_fd = open(filename, O_RDWR);
-			if (vfio_group_fd < 0) {
-				if (errno != ENOENT) {
-					RTE_LOG(ERR, EAL, "Cannot open %s: %s\n", filename,
-							strerror(errno));
-					return -1;
-				}
-				return 0;
-			}
-			/* noiommu group found */
-		}
-
-		/* if the fd is valid, create a new group for it */
-		if (vfio_cfg.vfio_group_idx == VFIO_MAX_GROUPS) {
-			RTE_LOG(ERR, EAL, "Maximum number of VFIO groups reached!\n");
-			close(vfio_group_fd);
-			return -1;
-		}
-		vfio_cfg.vfio_groups[vfio_cfg.vfio_group_idx].group_no = iommu_group_no;
-		vfio_cfg.vfio_groups[vfio_cfg.vfio_group_idx].fd = vfio_group_fd;
-		return vfio_group_fd;
-	}
-	/* if we're in a secondary process, request group fd from the primary
-	 * process via our socket
-	 */
-	else {
-		int socket_fd, ret;
-
-		socket_fd = vfio_mp_sync_connect_to_primary();
-
-		if (socket_fd < 0) {
-			RTE_LOG(ERR, EAL, "  cannot connect to primary process!\n");
-			return -1;
-		}
-		if (vfio_mp_sync_send_request(socket_fd, SOCKET_REQ_GROUP) < 0) {
-			RTE_LOG(ERR, EAL, "  cannot request container fd!\n");
-			close(socket_fd);
-			return -1;
-		}
-		if (vfio_mp_sync_send_request(socket_fd, iommu_group_no) < 0) {
-			RTE_LOG(ERR, EAL, "  cannot send group number!\n");
-			close(socket_fd);
-			return -1;
-		}
-		ret = vfio_mp_sync_receive_request(socket_fd);
-		switch (ret) {
-		case SOCKET_NO_FD:
-			close(socket_fd);
-			return 0;
-		case SOCKET_OK:
-			vfio_group_fd = vfio_mp_sync_receive_fd(socket_fd);
-			/* if we got the fd, return it */
-			if (vfio_group_fd > 0) {
-				close(socket_fd);
-				return vfio_group_fd;
-			}
-			/* fall-through on error */
-		default:
-			RTE_LOG(ERR, EAL, "  cannot get container fd!\n");
-			close(socket_fd);
-			return -1;
-		}
-	}
-	return -1;
-}
-
-/* parse IOMMU group number for a PCI device
- * returns 1 on success, -1 for errors, 0 for non-existent group
- */
-static int
-pci_vfio_get_group_no(const char *pci_addr, int *iommu_group_no)
-{
-	char linkname[PATH_MAX];
-	char filename[PATH_MAX];
-	char *tok[16], *group_tok, *end;
-	int ret;
-
-	memset(linkname, 0, sizeof(linkname));
-	memset(filename, 0, sizeof(filename));
-
-	/* try to find out IOMMU group for this device */
-	snprintf(linkname, sizeof(linkname),
-			 "%s/%s/iommu_group", pci_get_sysfs_path(), pci_addr);
-
-	ret = readlink(linkname, filename, sizeof(filename));
-
-	/* if the link doesn't exist, no VFIO for us */
-	if (ret < 0)
-		return 0;
-
-	ret = rte_strsplit(filename, sizeof(filename),
-			tok, RTE_DIM(tok), '/');
-
-	if (ret <= 0) {
-		RTE_LOG(ERR, EAL, "  %s cannot get IOMMU group\n", pci_addr);
-		return -1;
-	}
-
-	/* IOMMU group is always the last token */
-	errno = 0;
-	group_tok = tok[ret - 1];
-	end = group_tok;
-	*iommu_group_no = strtol(group_tok, &end, 10);
-	if ((end != group_tok && *end != '\0') || errno != 0) {
-		RTE_LOG(ERR, EAL, "  %s error parsing IOMMU number!\n", pci_addr);
-		return -1;
-	}
-
-	return 1;
-}
-
-static void
-clear_current_group(void)
-{
-	vfio_cfg.vfio_groups[vfio_cfg.vfio_group_idx].group_no = 0;
-	vfio_cfg.vfio_groups[vfio_cfg.vfio_group_idx].fd = -1;
-}
-
-
 /*
  * map the PCI resources of a PCI device in virtual memory (VFIO version).
  * primary and secondary processes follow almost exactly the same path
@@ -646,13 +303,9 @@ clear_current_group(void)
 int
 pci_vfio_map_resource(struct rte_pci_device *dev)
 {
-	struct vfio_group_status group_status = {
-			.argsz = sizeof(group_status)
-	};
 	struct vfio_device_info device_info = { .argsz = sizeof(device_info) };
-	int vfio_group_fd, vfio_dev_fd;
-	int iommu_group_no;
 	char pci_addr[PATH_MAX] = {0};
+	int vfio_dev_fd;
 	struct rte_pci_addr *loc = &dev->addr;
 	int i, ret, msix_bar;
 	struct mapped_pci_resource *vfio_res = NULL;
@@ -670,127 +323,9 @@ pci_vfio_map_resource(struct rte_pci_device *dev)
 	snprintf(pci_addr, sizeof(pci_addr), PCI_PRI_FMT,
 			loc->domain, loc->bus, loc->devid, loc->function);
 
-	/* get group number */
-	ret = pci_vfio_get_group_no(pci_addr, &iommu_group_no);
-	if (ret == 0) {
-		RTE_LOG(WARNING, EAL, "  %s not managed by VFIO driver, skipping\n",
-			pci_addr);
-		return 1;
-	}
-
-	/* if negative, something failed */
-	if (ret < 0)
-		return -1;
-
-	/* get the actual group fd */
-	vfio_group_fd = pci_vfio_get_group_fd(iommu_group_no);
-	if (vfio_group_fd < 0)
-		return -1;
-
-	/* store group fd */
-	vfio_cfg.vfio_groups[vfio_cfg.vfio_group_idx].group_no = iommu_group_no;
-	vfio_cfg.vfio_groups[vfio_cfg.vfio_group_idx].fd = vfio_group_fd;
-
-	/* if group_fd == 0, that means the device isn't managed by VFIO */
-	if (vfio_group_fd == 0) {
-		RTE_LOG(WARNING, EAL, "  %s not managed by VFIO driver, skipping\n",
-				pci_addr);
-		/* we store 0 as group fd to distinguish between existing but
-		 * unbound VFIO groups, and groups that don't exist at all.
-		 */
-		vfio_cfg.vfio_group_idx++;
-		return 1;
-	}
-
-	/*
-	 * at this point, we know at least one port on this device is bound to VFIO,
-	 * so we can proceed to try and set this particular port up
-	 */
-
-	/* check if the group is viable */
-	ret = ioctl(vfio_group_fd, VFIO_GROUP_GET_STATUS, &group_status);
-	if (ret) {
-		RTE_LOG(ERR, EAL, "  %s cannot get group status, "
-				"error %i (%s)\n", pci_addr, errno, strerror(errno));
-		close(vfio_group_fd);
-		clear_current_group();
-		return -1;
-	} else if (!(group_status.flags & VFIO_GROUP_FLAGS_VIABLE)) {
-		RTE_LOG(ERR, EAL, "  %s VFIO group is not viable!\n", pci_addr);
-		close(vfio_group_fd);
-		clear_current_group();
-		return -1;
-	}
-
-	/*
-	 * at this point, we know that this group is viable (meaning, all devices
-	 * are either bound to VFIO or not bound to anything)
-	 */
-
-	/* check if group does not have a container yet */
-	if (!(group_status.flags & VFIO_GROUP_FLAGS_CONTAINER_SET)) {
-
-		/* add group to a container */
-		ret = ioctl(vfio_group_fd, VFIO_GROUP_SET_CONTAINER,
-				&vfio_cfg.vfio_container_fd);
-		if (ret) {
-			RTE_LOG(ERR, EAL, "  %s cannot add VFIO group to container, "
-					"error %i (%s)\n", pci_addr, errno, strerror(errno));
-			close(vfio_group_fd);
-			clear_current_group();
-			return -1;
-		}
-		/*
-		 * at this point we know that this group has been successfully
-		 * initialized, so we increment vfio_group_idx to indicate that we can
-		 * add new groups.
-		 */
-		vfio_cfg.vfio_group_idx++;
-	}
-
-	/*
-	 * pick an IOMMU type and set up DMA mappings for container
-	 *
-	 * needs to be done only once, only when at least one group is assigned to
-	 * a container and only in primary process
-	 */
-	if (internal_config.process_type == RTE_PROC_PRIMARY &&
-			vfio_cfg.vfio_container_has_dma == 0) {
-		/* select an IOMMU type which we will be using */
-		const struct vfio_iommu_type *t =
-				pci_vfio_set_iommu_type(vfio_cfg.vfio_container_fd);
-		if (!t) {
-			RTE_LOG(ERR, EAL, "  %s failed to select IOMMU type\n", pci_addr);
-			return -1;
-		}
-		ret = t->dma_map_func(vfio_cfg.vfio_container_fd);
-		if (ret) {
-			RTE_LOG(ERR, EAL, "  %s DMA remapping failed, "
-					"error %i (%s)\n", pci_addr, errno, strerror(errno));
-			return -1;
-		}
-		vfio_cfg.vfio_container_has_dma = 1;
-	}
-
-	/* get a file descriptor for the device */
-	vfio_dev_fd = ioctl(vfio_group_fd, VFIO_GROUP_GET_DEVICE_FD, pci_addr);
-	if (vfio_dev_fd < 0) {
-		/* if we cannot get a device fd, this simply means that this
-		 * particular port is not bound to VFIO
-		 */
-		RTE_LOG(WARNING, EAL, "  %s not managed by VFIO driver, skipping\n",
-				pci_addr);
-		return 1;
-	}
-
-	/* test and setup the device */
-	ret = ioctl(vfio_dev_fd, VFIO_DEVICE_GET_INFO, &device_info);
-	if (ret) {
-		RTE_LOG(ERR, EAL, "  %s cannot get device info, "
-				"error %i (%s)\n", pci_addr, errno, strerror(errno));
-		close(vfio_dev_fd);
-		return -1;
-	}
+	if ((ret = vfio_setup_device(pci_get_sysfs_path(), pci_addr,
+					&vfio_dev_fd, &device_info)))
+		return ret;
 
 	/* get MSI-X BAR, if any (we have to know where it is because we can't
 	 * easily mmap it when using VFIO) */
@@ -1048,50 +583,12 @@ pci_vfio_ioport_unmap(struct rte_pci_ioport *p)
 int
 pci_vfio_enable(void)
 {
-	/* initialize group list */
-	int i;
-	int vfio_available;
-
-	for (i = 0; i < VFIO_MAX_GROUPS; i++) {
-		vfio_cfg.vfio_groups[i].fd = -1;
-		vfio_cfg.vfio_groups[i].group_no = -1;
-	}
-
-	/* inform the user that we are probing for VFIO */
-	RTE_LOG(INFO, EAL, "Probing VFIO support...\n");
-
-	/* check if vfio-pci module is loaded */
-	vfio_available = rte_eal_check_module("vfio_pci");
-
-	/* return error directly */
-	if (vfio_available == -1) {
-		RTE_LOG(INFO, EAL, "Could not get loaded module details!\n");
-		return -1;
-	}
-
-	/* return 0 if VFIO modules not loaded */
-	if (vfio_available == 0) {
-		RTE_LOG(DEBUG, EAL, "VFIO modules not loaded, "
-			"skipping VFIO support...\n");
-		return 0;
-	}
-
-	vfio_cfg.vfio_container_fd = pci_vfio_get_container_fd();
-
-	/* check if we have VFIO driver enabled */
-	if (vfio_cfg.vfio_container_fd != -1) {
-		RTE_LOG(NOTICE, EAL, "VFIO support initialized\n");
-		vfio_cfg.vfio_enabled = 1;
-	} else {
-		RTE_LOG(NOTICE, EAL, "VFIO support could not be initialized\n");
-	}
-
-	return 0;
+	return vfio_enable("vfio_pci");
 }
 
 int
 pci_vfio_is_enabled(void)
 {
-	return vfio_cfg.vfio_enabled;
+	return vfio_is_enabled("vfio_pci");
 }
 #endif
diff --git a/lib/librte_eal/linuxapp/eal/eal_vfio.c b/lib/librte_eal/linuxapp/eal/eal_vfio.c
new file mode 100644
index 00000000..fcb0ab38
--- /dev/null
+++ b/lib/librte_eal/linuxapp/eal/eal_vfio.c
@@ -0,0 +1,547 @@
+/*-
+ *   BSD LICENSE
+ *
+ *   Copyright(c) 2010-2014 Intel Corporation. All rights reserved.
+ *   All rights reserved.
+ *
+ *   Redistribution and use in source and binary forms, with or without
+ *   modification, are permitted provided that the following conditions
+ *   are met:
+ *
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in
+ *       the documentation and/or other materials provided with the
+ *       distribution.
+ *     * Neither the name of Intel Corporation nor the names of its
+ *       contributors may be used to endorse or promote products derived
+ *       from this software without specific prior written permission.
+ *
+ *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <string.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include <sys/ioctl.h>
+
+#include <rte_log.h>
+#include <rte_memory.h>
+#include <rte_eal_memconfig.h>
+
+#include "eal_filesystem.h"
+#include "eal_vfio.h"
+#include "eal_private.h"
+
+#ifdef VFIO_PRESENT
+
+/* per-process VFIO config */
+static struct vfio_config vfio_cfg;
+
+static int vfio_type1_dma_map(int);
+static int vfio_noiommu_dma_map(int);
+
+/* IOMMU types we support */
+static const struct vfio_iommu_type iommu_types[] = {
+	/* x86 IOMMU, otherwise known as type 1 */
+	{ RTE_VFIO_TYPE1, "Type 1", &vfio_type1_dma_map},
+	/* IOMMU-less mode */
+	{ RTE_VFIO_NOIOMMU, "No-IOMMU", &vfio_noiommu_dma_map},
+};
+
+int
+vfio_get_group_fd(int iommu_group_no)
+{
+	int i;
+	int vfio_group_fd;
+	char filename[PATH_MAX];
+
+	/* check if we already have the group descriptor open */
+	for (i = 0; i < vfio_cfg.vfio_group_idx; i++)
+		if (vfio_cfg.vfio_groups[i].group_no == iommu_group_no)
+			return vfio_cfg.vfio_groups[i].fd;
+
+	/* if primary, try to open the group */
+	if (internal_config.process_type == RTE_PROC_PRIMARY) {
+		/* try regular group format */
+		snprintf(filename, sizeof(filename),
+				 VFIO_GROUP_FMT, iommu_group_no);
+		vfio_group_fd = open(filename, O_RDWR);
+		if (vfio_group_fd < 0) {
+			/* if file not found, it's not an error */
+			if (errno != ENOENT) {
+				RTE_LOG(ERR, EAL, "Cannot open %s: %s\n", filename,
+						strerror(errno));
+				return -1;
+			}
+
+			/* special case: try no-IOMMU path as well */
+			snprintf(filename, sizeof(filename),
+					VFIO_NOIOMMU_GROUP_FMT, iommu_group_no);
+			vfio_group_fd = open(filename, O_RDWR);
+			if (vfio_group_fd < 0) {
+				if (errno != ENOENT) {
+					RTE_LOG(ERR, EAL, "Cannot open %s: %s\n", filename,
+							strerror(errno));
+					return -1;
+				}
+				return 0;
+			}
+			/* noiommu group found */
+		}
+
+		/* if the fd is valid, create a new group for it */
+		if (vfio_cfg.vfio_group_idx == VFIO_MAX_GROUPS) {
+			RTE_LOG(ERR, EAL, "Maximum number of VFIO groups reached!\n");
+			close(vfio_group_fd);
+			return -1;
+		}
+		vfio_cfg.vfio_groups[vfio_cfg.vfio_group_idx].group_no = iommu_group_no;
+		vfio_cfg.vfio_groups[vfio_cfg.vfio_group_idx].fd = vfio_group_fd;
+		return vfio_group_fd;
+	}
+	/* if we're in a secondary process, request group fd from the primary
+	 * process via our socket
+	 */
+	else {
+		int socket_fd, ret;
+
+		socket_fd = vfio_mp_sync_connect_to_primary();
+
+		if (socket_fd < 0) {
+			RTE_LOG(ERR, EAL, "  cannot connect to primary process!\n");
+			return -1;
+		}
+		if (vfio_mp_sync_send_request(socket_fd, SOCKET_REQ_GROUP) < 0) {
+			RTE_LOG(ERR, EAL, "  cannot request container fd!\n");
+			close(socket_fd);
+			return -1;
+		}
+		if (vfio_mp_sync_send_request(socket_fd, iommu_group_no) < 0) {
+			RTE_LOG(ERR, EAL, "  cannot send group number!\n");
+			close(socket_fd);
+			return -1;
+		}
+		ret = vfio_mp_sync_receive_request(socket_fd);
+		switch (ret) {
+		case SOCKET_NO_FD:
+			close(socket_fd);
+			return 0;
+		case SOCKET_OK:
+			vfio_group_fd = vfio_mp_sync_receive_fd(socket_fd);
+			/* if we got the fd, return it */
+			if (vfio_group_fd > 0) {
+				close(socket_fd);
+				return vfio_group_fd;
+			}
+			/* fall-through on error */
+		default:
+			RTE_LOG(ERR, EAL, "  cannot get container fd!\n");
+			close(socket_fd);
+			return -1;
+		}
+	}
+	return -1;
+}
+
+static void
+clear_current_group(void)
+{
+	vfio_cfg.vfio_groups[vfio_cfg.vfio_group_idx].group_no = 0;
+	vfio_cfg.vfio_groups[vfio_cfg.vfio_group_idx].fd = -1;
+}
+
+int vfio_setup_device(const char *sysfs_base, const char *dev_addr,
+		int *vfio_dev_fd, struct vfio_device_info *device_info)
+{
+	struct vfio_group_status group_status = {
+			.argsz = sizeof(group_status)
+	};
+	int vfio_group_fd;
+	int iommu_group_no;
+	int ret;
+
+	/* get group number */
+	ret = vfio_get_group_no(sysfs_base, dev_addr, &iommu_group_no);
+	if (ret == 0) {
+		RTE_LOG(WARNING, EAL, "  %s not managed by VFIO driver, skipping\n",
+			dev_addr);
+		return 1;
+	}
+
+	/* if negative, something failed */
+	if (ret < 0)
+		return -1;
+
+	/* get the actual group fd */
+	vfio_group_fd = vfio_get_group_fd(iommu_group_no);
+	if (vfio_group_fd < 0)
+		return -1;
+
+	/* store group fd */
+	vfio_cfg.vfio_groups[vfio_cfg.vfio_group_idx].group_no = iommu_group_no;
+	vfio_cfg.vfio_groups[vfio_cfg.vfio_group_idx].fd = vfio_group_fd;
+
+	/* if group_fd == 0, that means the device isn't managed by VFIO */
+	if (vfio_group_fd == 0) {
+		RTE_LOG(WARNING, EAL, "  %s not managed by VFIO driver, skipping\n",
+				dev_addr);
+		/* we store 0 as group fd to distinguish between existing but
+		 * unbound VFIO groups, and groups that don't exist at all.
+		 */
+		vfio_cfg.vfio_group_idx++;
+		return 1;
+	}
+
+	/*
+	 * at this point, we know that this group is viable (meaning, all devices
+	 * are either bound to VFIO or not bound to anything)
+	 */
+
+	/* check if the group is viable */
+	ret = ioctl(vfio_group_fd, VFIO_GROUP_GET_STATUS, &group_status);
+	if (ret) {
+		RTE_LOG(ERR, EAL, "  %s cannot get group status, "
+				"error %i (%s)\n", dev_addr, errno, strerror(errno));
+		close(vfio_group_fd);
+		clear_current_group();
+		return -1;
+	} else if (!(group_status.flags & VFIO_GROUP_FLAGS_VIABLE)) {
+		RTE_LOG(ERR, EAL, "  %s VFIO group is not viable!\n", dev_addr);
+		close(vfio_group_fd);
+		clear_current_group();
+		return -1;
+	}
+
+	/* check if group does not have a container yet */
+	if (!(group_status.flags & VFIO_GROUP_FLAGS_CONTAINER_SET)) {
+
+		/* add group to a container */
+		ret = ioctl(vfio_group_fd, VFIO_GROUP_SET_CONTAINER,
+				&vfio_cfg.vfio_container_fd);
+		if (ret) {
+			RTE_LOG(ERR, EAL, "  %s cannot add VFIO group to container, "
+					"error %i (%s)\n", dev_addr, errno, strerror(errno));
+			close(vfio_group_fd);
+			clear_current_group();
+			return -1;
+		}
+		/*
+		 * at this point we know that this group has been successfully
+		 * initialized, so we increment vfio_group_idx to indicate that we can
+		 * add new groups.
+		 */
+		vfio_cfg.vfio_group_idx++;
+	}
+
+	/*
+	 * pick an IOMMU type and set up DMA mappings for container
+	 *
+	 * needs to be done only once, only when at least one group is assigned to
+	 * a container and only in primary process
+	 */
+	if (internal_config.process_type == RTE_PROC_PRIMARY &&
+			vfio_cfg.vfio_container_has_dma == 0) {
+		/* select an IOMMU type which we will be using */
+		const struct vfio_iommu_type *t =
+				vfio_set_iommu_type(vfio_cfg.vfio_container_fd);
+		if (!t) {
+			RTE_LOG(ERR, EAL, "  %s failed to select IOMMU type\n", dev_addr);
+			return -1;
+		}
+		ret = t->dma_map_func(vfio_cfg.vfio_container_fd);
+		if (ret) {
+			RTE_LOG(ERR, EAL, "  %s DMA remapping failed, "
+					"error %i (%s)\n", dev_addr, errno, strerror(errno));
+			return -1;
+		}
+		vfio_cfg.vfio_container_has_dma = 1;
+	}
+
+	/* get a file descriptor for the device */
+	*vfio_dev_fd = ioctl(vfio_group_fd, VFIO_GROUP_GET_DEVICE_FD, dev_addr);
+	if (*vfio_dev_fd < 0) {
+		/* if we cannot get a device fd, this simply means that this
+		* particular port is not bound to VFIO
+		*/
+		RTE_LOG(WARNING, EAL, "  %s not managed by VFIO driver, skipping\n",
+				dev_addr);
+		return 1;
+	}
+
+	/* test and setup the device */
+	ret = ioctl(*vfio_dev_fd, VFIO_DEVICE_GET_INFO, device_info);
+	if (ret) {
+		RTE_LOG(ERR, EAL, "  %s cannot get device info, "
+				"error %i (%s)\n", dev_addr, errno, strerror(errno));
+		close(*vfio_dev_fd);
+		return -1;
+	}
+
+	return 0;
+}
+
+int
+vfio_enable(const char *modname)
+{
+	/* initialize group list */
+	int i;
+	int vfio_available;
+
+	for (i = 0; i < VFIO_MAX_GROUPS; i++) {
+		vfio_cfg.vfio_groups[i].fd = -1;
+		vfio_cfg.vfio_groups[i].group_no = -1;
+	}
+
+	/* inform the user that we are probing for VFIO */
+	RTE_LOG(INFO, EAL, "Probing VFIO support...\n");
+
+	/* check if vfio-pci module is loaded */
+	vfio_available = rte_eal_check_module(modname);
+
+	/* return error directly */
+	if (vfio_available == -1) {
+		RTE_LOG(INFO, EAL, "Could not get loaded module details!\n");
+		return -1;
+	}
+
+	/* return 0 if VFIO modules not loaded */
+	if (vfio_available == 0) {
+		RTE_LOG(DEBUG, EAL, "VFIO modules not loaded, "
+			"skipping VFIO support...\n");
+		return 0;
+	}
+
+	vfio_cfg.vfio_container_fd = vfio_get_container_fd();
+
+	/* check if we have VFIO driver enabled */
+	if (vfio_cfg.vfio_container_fd != -1) {
+		RTE_LOG(NOTICE, EAL, "VFIO support initialized\n");
+		vfio_cfg.vfio_enabled = 1;
+	} else {
+		RTE_LOG(NOTICE, EAL, "VFIO support could not be initialized\n");
+	}
+
+	return 0;
+}
+
+int
+vfio_is_enabled(const char *modname)
+{
+	const int mod_available = rte_eal_check_module(modname);
+	return vfio_cfg.vfio_enabled && mod_available;
+}
+
+const struct vfio_iommu_type *
+vfio_set_iommu_type(int vfio_container_fd) {
+	unsigned idx;
+	for (idx = 0; idx < RTE_DIM(iommu_types); idx++) {
+		const struct vfio_iommu_type *t = &iommu_types[idx];
+
+		int ret = ioctl(vfio_container_fd, VFIO_SET_IOMMU,
+				t->type_id);
+		if (!ret) {
+			RTE_LOG(NOTICE, EAL, "  using IOMMU type %d (%s)\n",
+					t->type_id, t->name);
+			return t;
+		}
+		/* not an error, there may be more supported IOMMU types */
+		RTE_LOG(DEBUG, EAL, "  set IOMMU type %d (%s) failed, "
+				"error %i (%s)\n", t->type_id, t->name, errno,
+				strerror(errno));
+	}
+	/* if we didn't find a suitable IOMMU type, fail */
+	return NULL;
+}
+
+int
+vfio_has_supported_extensions(int vfio_container_fd) {
+	int ret;
+	unsigned idx, n_extensions = 0;
+	for (idx = 0; idx < RTE_DIM(iommu_types); idx++) {
+		const struct vfio_iommu_type *t = &iommu_types[idx];
+
+		ret = ioctl(vfio_container_fd, VFIO_CHECK_EXTENSION,
+				t->type_id);
+		if (ret < 0) {
+			RTE_LOG(ERR, EAL, "  could not get IOMMU type, "
+				"error %i (%s)\n", errno,
+				strerror(errno));
+			close(vfio_container_fd);
+			return -1;
+		} else if (ret == 1) {
+			/* we found a supported extension */
+			n_extensions++;
+		}
+		RTE_LOG(DEBUG, EAL, "  IOMMU type %d (%s) is %s\n",
+				t->type_id, t->name,
+				ret ? "supported" : "not supported");
+	}
+
+	/* if we didn't find any supported IOMMU types, fail */
+	if (!n_extensions) {
+		close(vfio_container_fd);
+		return -1;
+	}
+
+	return 0;
+}
+
+int
+vfio_get_container_fd(void)
+{
+	int ret, vfio_container_fd;
+
+	/* if we're in a primary process, try to open the container */
+	if (internal_config.process_type == RTE_PROC_PRIMARY) {
+		vfio_container_fd = open(VFIO_CONTAINER_PATH, O_RDWR);
+		if (vfio_container_fd < 0) {
+			RTE_LOG(ERR, EAL, "  cannot open VFIO container, "
+					"error %i (%s)\n", errno, strerror(errno));
+			return -1;
+		}
+
+		/* check VFIO API version */
+		ret = ioctl(vfio_container_fd, VFIO_GET_API_VERSION);
+		if (ret != VFIO_API_VERSION) {
+			if (ret < 0)
+				RTE_LOG(ERR, EAL, "  could not get VFIO API version, "
+						"error %i (%s)\n", errno, strerror(errno));
+			else
+				RTE_LOG(ERR, EAL, "  unsupported VFIO API version!\n");
+			close(vfio_container_fd);
+			return -1;
+		}
+
+		ret = vfio_has_supported_extensions(vfio_container_fd);
+		if (ret) {
+			RTE_LOG(ERR, EAL, "  no supported IOMMU "
+					"extensions found!\n");
+			return -1;
+		}
+
+		return vfio_container_fd;
+	} else {
+		/*
+		 * if we're in a secondary process, request container fd from the
+		 * primary process via our socket
+		 */
+		int socket_fd;
+
+		socket_fd = vfio_mp_sync_connect_to_primary();
+		if (socket_fd < 0) {
+			RTE_LOG(ERR, EAL, "  cannot connect to primary process!\n");
+			return -1;
+		}
+		if (vfio_mp_sync_send_request(socket_fd, SOCKET_REQ_CONTAINER) < 0) {
+			RTE_LOG(ERR, EAL, "  cannot request container fd!\n");
+			close(socket_fd);
+			return -1;
+		}
+		vfio_container_fd = vfio_mp_sync_receive_fd(socket_fd);
+		if (vfio_container_fd < 0) {
+			RTE_LOG(ERR, EAL, "  cannot get container fd!\n");
+			close(socket_fd);
+			return -1;
+		}
+		close(socket_fd);
+		return vfio_container_fd;
+	}
+
+	return -1;
+}
+
+int
+vfio_get_group_no(const char *sysfs_base,
+		const char *dev_addr, int *iommu_group_no)
+{
+	char linkname[PATH_MAX];
+	char filename[PATH_MAX];
+	char *tok[16], *group_tok, *end;
+	int ret;
+
+	memset(linkname, 0, sizeof(linkname));
+	memset(filename, 0, sizeof(filename));
+
+	/* try to find out IOMMU group for this device */
+	snprintf(linkname, sizeof(linkname),
+			 "%s/%s/iommu_group", sysfs_base, dev_addr);
+
+	ret = readlink(linkname, filename, sizeof(filename));
+
+	/* if the link doesn't exist, no VFIO for us */
+	if (ret < 0)
+		return 0;
+
+	ret = rte_strsplit(filename, sizeof(filename),
+			tok, RTE_DIM(tok), '/');
+
+	if (ret <= 0) {
+		RTE_LOG(ERR, EAL, "  %s cannot get IOMMU group\n", dev_addr);
+		return -1;
+	}
+
+	/* IOMMU group is always the last token */
+	errno = 0;
+	group_tok = tok[ret - 1];
+	end = group_tok;
+	*iommu_group_no = strtol(group_tok, &end, 10);
+	if ((end != group_tok && *end != '\0') || errno != 0) {
+		RTE_LOG(ERR, EAL, "  %s error parsing IOMMU number!\n", dev_addr);
+		return -1;
+	}
+
+	return 1;
+}
+
+static int
+vfio_type1_dma_map(int vfio_container_fd)
+{
+	const struct rte_memseg *ms = rte_eal_get_physmem_layout();
+	int i, ret;
+
+	/* 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;
+
+		if (ms[i].addr == NULL)
+			break;
+
+		memset(&dma_map, 0, sizeof(dma_map));
+		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;
+		dma_map.flags = VFIO_DMA_MAP_FLAG_READ | VFIO_DMA_MAP_FLAG_WRITE;
+
+		ret = ioctl(vfio_container_fd, VFIO_IOMMU_MAP_DMA, &dma_map);
+
+		if (ret) {
+			RTE_LOG(ERR, EAL, "  cannot set up DMA remapping, "
+					"error %i (%s)\n", errno, strerror(errno));
+			return -1;
+		}
+	}
+
+	return 0;
+}
+
+static int
+vfio_noiommu_dma_map(int __rte_unused vfio_container_fd)
+{
+	/* No-IOMMU mode does not need DMA mapping */
+	return 0;
+}
+
+#endif
diff --git a/lib/librte_eal/linuxapp/eal/eal_vfio.h b/lib/librte_eal/linuxapp/eal/eal_vfio.h
index f483bf40..29f7f3ec 100644
--- a/lib/librte_eal/linuxapp/eal/eal_vfio.h
+++ b/lib/librte_eal/linuxapp/eal/eal_vfio.h
@@ -60,6 +60,100 @@
 #define RTE_VFIO_NOIOMMU VFIO_NOIOMMU_IOMMU
 #endif
 
+#define VFIO_MAX_GROUPS 64
+
+/*
+ * Function prototypes for VFIO multiprocess sync functions
+ */
+int vfio_mp_sync_send_request(int socket, int req);
+int vfio_mp_sync_receive_request(int socket);
+int vfio_mp_sync_send_fd(int socket, int fd);
+int vfio_mp_sync_receive_fd(int socket);
+int vfio_mp_sync_connect_to_primary(void);
+
+/*
+ * we don't need to store device fd's anywhere since they can be obtained from
+ * the group fd via an ioctl() call.
+ */
+struct vfio_group {
+	int group_no;
+	int fd;
+};
+
+struct vfio_config {
+	int vfio_enabled;
+	int vfio_container_fd;
+	int vfio_container_has_dma;
+	int vfio_group_idx;
+	struct vfio_group vfio_groups[VFIO_MAX_GROUPS];
+};
+
+#define VFIO_DIR "/dev/vfio"
+#define VFIO_CONTAINER_PATH "/dev/vfio/vfio"
+#define VFIO_GROUP_FMT "/dev/vfio/%u"
+#define VFIO_NOIOMMU_GROUP_FMT "/dev/vfio/noiommu-%u"
+#define VFIO_GET_REGION_ADDR(x) ((uint64_t) x << 40ULL)
+#define VFIO_GET_REGION_IDX(x) (x >> 40)
+
+/* DMA mapping function prototype.
+ * Takes VFIO container fd as a parameter.
+ * Returns 0 on success, -1 on error.
+ * */
+typedef int (*vfio_dma_func_t)(int);
+
+struct vfio_iommu_type {
+	int type_id;
+	const char *name;
+	vfio_dma_func_t dma_map_func;
+};
+
+/* pick IOMMU type. returns a pointer to vfio_iommu_type or NULL for error */
+const struct vfio_iommu_type *
+vfio_set_iommu_type(int vfio_container_fd);
+
+/* check if we have any supported extensions */
+int
+vfio_has_supported_extensions(int vfio_container_fd);
+
+/* open container fd or get an existing one */
+int
+vfio_get_container_fd(void);
+
+/* parse IOMMU group number for a device
+ * returns 1 on success, -1 for errors, 0 for non-existent group
+ */
+int
+vfio_get_group_no(const char *sysfs_base,
+		const char *dev_addr, int *iommu_group_no);
+
+/* open group fd or get an existing one */
+int
+vfio_get_group_fd(int iommu_group_no);
+
+/**
+ * Setup vfio_cfg for the device identified by its address. It discovers
+ * the configured I/O MMU groups or sets a new one for the device. If a new
+ * groups is assigned, the DMA mapping is performed.
+ * Returns 0 on success, a negative value on failure and a positive value in
+ * case the given device cannot be managed this way.
+ */
+int vfio_setup_device(const char *sysfs_base, const char *dev_addr,
+		int *vfio_dev_fd, struct vfio_device_info *device_info);
+
+int vfio_enable(const char *modname);
+int vfio_is_enabled(const char *modname);
+
+int pci_vfio_enable(void);
+int pci_vfio_is_enabled(void);
+
+int vfio_mp_sync_setup(void);
+
+#define SOCKET_REQ_CONTAINER 0x100
+#define SOCKET_REQ_GROUP 0x200
+#define SOCKET_OK 0x0
+#define SOCKET_NO_FD 0x1
+#define SOCKET_ERR 0xFF
+
 #define VFIO_PRESENT
 #endif /* kernel version */
 #endif /* RTE_EAL_VFIO */
diff --git a/lib/librte_eal/linuxapp/eal/eal_pci_vfio_mp_sync.c b/lib/librte_eal/linuxapp/eal/eal_vfio_mp_sync.c
index d54ded88..00cf919b 100644
--- a/lib/librte_eal/linuxapp/eal/eal_pci_vfio_mp_sync.c
+++ b/lib/librte_eal/linuxapp/eal/eal_vfio_mp_sync.c
@@ -265,7 +265,7 @@ vfio_mp_sync_connect_to_primary(void)
  * socket listening thread for primary process
  */
 static __attribute__((noreturn)) void *
-pci_vfio_mp_sync_thread(void __rte_unused * arg)
+vfio_mp_sync_thread(void __rte_unused * arg)
 {
 	int ret, fd, vfio_group_no;
 
@@ -296,7 +296,7 @@ pci_vfio_mp_sync_thread(void __rte_unused * arg)
 
 		switch (ret) {
 		case SOCKET_REQ_CONTAINER:
-			fd = pci_vfio_get_container_fd();
+			fd = vfio_get_container_fd();
 			if (fd < 0)
 				vfio_mp_sync_send_request(conn_sock, SOCKET_ERR);
 			else
@@ -310,7 +310,7 @@ pci_vfio_mp_sync_thread(void __rte_unused * arg)
 				continue;
 			}
 
-			fd = pci_vfio_get_group_fd(vfio_group_no);
+			fd = vfio_get_group_fd(vfio_group_no);
 
 			if (fd < 0)
 				vfio_mp_sync_send_request(conn_sock, SOCKET_ERR);
@@ -376,7 +376,7 @@ vfio_mp_sync_socket_setup(void)
  * set up a local socket and tell it to listen for incoming connections
  */
 int
-pci_vfio_mp_sync_setup(void)
+vfio_mp_sync_setup(void)
 {
 	int ret;
 	char thread_name[RTE_MAX_THREAD_NAME_LEN];
@@ -387,7 +387,7 @@ pci_vfio_mp_sync_setup(void)
 	}
 
 	ret = pthread_create(&socket_thread, NULL,
-			pci_vfio_mp_sync_thread, NULL);
+			vfio_mp_sync_thread, NULL);
 	if (ret) {
 		RTE_LOG(ERR, EAL,
 			"Failed to create thread for communication with secondary processes!\n");
@@ -396,7 +396,7 @@ pci_vfio_mp_sync_setup(void)
 	}
 
 	/* Set thread_name for aid in debugging. */
-	snprintf(thread_name, RTE_MAX_THREAD_NAME_LEN, "pci-vfio-sync");
+	snprintf(thread_name, RTE_MAX_THREAD_NAME_LEN, "vfio-sync");
 	ret = rte_thread_setname(socket_thread, thread_name);
 	if (ret)
 		RTE_LOG(DEBUG, EAL,
diff --git a/lib/librte_eal/linuxapp/eal/eal_xen_memory.c b/lib/librte_eal/linuxapp/eal/eal_xen_memory.c
index 0b612bb1..bddbdb07 100644
--- a/lib/librte_eal/linuxapp/eal/eal_xen_memory.c
+++ b/lib/librte_eal/linuxapp/eal/eal_xen_memory.c
@@ -167,8 +167,8 @@ rte_xen_mem_phy2mch(int32_t memseg_id, const phys_addr_t phy_addr)
 	if (memseg_id == -1) {
 		for (i = 0; i < RTE_MAX_MEMSEG; i++) {
 			if ((phy_addr >= memseg[i].phys_addr) &&
-					(phys_addr < memseg[i].phys_addr +
-						memseg[i].size)) {
+					(phy_addr < memseg[i].phys_addr +
+						memseg[i].len)) {
 				memseg_id = i;
 				break;
 			}
diff --git a/lib/librte_eal/linuxapp/eal/rte_eal_version.map b/lib/librte_eal/linuxapp/eal/rte_eal_version.map
index 05134673..a617b9e4 100644
--- a/lib/librte_eal/linuxapp/eal/rte_eal_version.map
+++ b/lib/librte_eal/linuxapp/eal/rte_eal_version.map
@@ -138,6 +138,7 @@ DPDK_2.2 {
 	rte_keepalive_mark_alive;
 	rte_keepalive_register_core;
 	rte_xen_dom0_supported;
+	rte_xen_mem_phy2mch;
 
 } DPDK_2.1;