Imported upstream release 16.04

* gbp import-orig ../dpdk-16.04.tar.xz

Change-Id: Iac2196db782ba322f6974d8a752acc34ce5024c3
Signed-off-by: C.J. Collier <cjcollier@linuxfoundation.org>

3 files changed, 749 insertions, 0 deletions

diff --git a/lib/librte_eal/linuxapp/igb_uio/Makefile b/lib/librte_eal/linuxapp/igb_uio/Makefile
new file mode 100644
index 00000000..ec6e702f
--- /dev/null
+++ b/lib/librte_eal/linuxapp/igb_uio/Makefile
@@ -0,0 +1,53 @@
+#   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 $(RTE_SDK)/mk/rte.vars.mk
+
+#
+# module name and path
+#
+MODULE = igb_uio
+MODULE_PATH = drivers/net/igb_uio
+
+#
+# CFLAGS
+#
+MODULE_CFLAGS += -I$(SRCDIR) --param max-inline-insns-single=100
+MODULE_CFLAGS += -I$(RTE_OUTPUT)/include
+MODULE_CFLAGS += -Winline -Wall -Werror
+MODULE_CFLAGS += -include $(RTE_OUTPUT)/include/rte_config.h
+
+#
+# all source are stored in SRCS-y
+#
+SRCS-y := igb_uio.c
+
+include $(RTE_SDK)/mk/rte.module.mk
diff --git a/lib/librte_eal/linuxapp/igb_uio/compat.h b/lib/librte_eal/linuxapp/igb_uio/compat.h
new file mode 100644
index 00000000..c1d45a66
--- /dev/null
+++ b/lib/librte_eal/linuxapp/igb_uio/compat.h
@@ -0,0 +1,116 @@
+/*
+ * Minimal wrappers to allow compiling igb_uio on older kernels.
+ */
+
+#ifndef RHEL_RELEASE_VERSION
+#define RHEL_RELEASE_VERSION(a, b) (((a) << 8) + (b))
+#endif
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 3, 0)
+#define pci_cfg_access_lock   pci_block_user_cfg_access
+#define pci_cfg_access_unlock pci_unblock_user_cfg_access
+#endif
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 18, 0)
+#define HAVE_PTE_MASK_PAGE_IOMAP
+#endif
+
+#ifndef PCI_MSIX_ENTRY_SIZE
+#define PCI_MSIX_ENTRY_SIZE             16
+#define  PCI_MSIX_ENTRY_LOWER_ADDR      0
+#define  PCI_MSIX_ENTRY_UPPER_ADDR      4
+#define  PCI_MSIX_ENTRY_DATA            8
+#define  PCI_MSIX_ENTRY_VECTOR_CTRL     12
+#define   PCI_MSIX_ENTRY_CTRL_MASKBIT   1
+#endif
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 34) && \
+	(!(defined(RHEL_RELEASE_CODE) && \
+	 RHEL_RELEASE_CODE >= RHEL_RELEASE_VERSION(5, 9)))
+
+static int pci_num_vf(struct pci_dev *dev)
+{
+	struct iov {
+		int pos;
+		int nres;
+		u32 cap;
+		u16 ctrl;
+		u16 total;
+		u16 initial;
+		u16 nr_virtfn;
+	} *iov = (struct iov *)dev->sriov;
+
+	if (!dev->is_physfn)
+		return 0;
+
+	return iov->nr_virtfn;
+}
+
+#endif /* < 2.6.34 */
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 39) && \
+	(!(defined(RHEL_RELEASE_CODE) && \
+	   RHEL_RELEASE_CODE >= RHEL_RELEASE_VERSION(6, 4)))
+
+#define kstrtoul strict_strtoul
+
+#endif /* < 2.6.39 */
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 3, 0) && \
+	(!(defined(RHEL_RELEASE_CODE) && \
+	   RHEL_RELEASE_CODE >= RHEL_RELEASE_VERSION(6, 3)))
+
+/* Check if INTX works to control irq's.
+ * Set's INTX_DISABLE flag and reads it back
+ */
+static bool pci_intx_mask_supported(struct pci_dev *pdev)
+{
+	bool mask_supported = false;
+	uint16_t orig, new;
+
+	pci_block_user_cfg_access(pdev);
+	pci_read_config_word(pdev, PCI_COMMAND, &orig);
+	pci_write_config_word(pdev, PCI_COMMAND,
+			      orig ^ PCI_COMMAND_INTX_DISABLE);
+	pci_read_config_word(pdev, PCI_COMMAND, &new);
+
+	if ((new ^ orig) & ~PCI_COMMAND_INTX_DISABLE) {
+		dev_err(&pdev->dev, "Command register changed from "
+			"0x%x to 0x%x: driver or hardware bug?\n", orig, new);
+	} else if ((new ^ orig) & PCI_COMMAND_INTX_DISABLE) {
+		mask_supported = true;
+		pci_write_config_word(pdev, PCI_COMMAND, orig);
+	}
+	pci_unblock_user_cfg_access(pdev);
+
+	return mask_supported;
+}
+
+static bool pci_check_and_mask_intx(struct pci_dev *pdev)
+{
+	bool pending;
+	uint32_t status;
+
+	pci_block_user_cfg_access(pdev);
+	pci_read_config_dword(pdev, PCI_COMMAND, &status);
+
+	/* interrupt is not ours, goes to out */
+	pending = (((status >> 16) & PCI_STATUS_INTERRUPT) != 0);
+	if (pending) {
+		uint16_t old, new;
+
+		old = status;
+		if (status != 0)
+			new = old & (~PCI_COMMAND_INTX_DISABLE);
+		else
+			new = old | PCI_COMMAND_INTX_DISABLE;
+
+		if (old != new)
+			pci_write_config_word(pdev, PCI_COMMAND, new);
+	}
+	pci_unblock_user_cfg_access(pdev);
+
+	return pending;
+}
+
+#endif /* < 3.3.0 */
diff --git a/lib/librte_eal/linuxapp/igb_uio/igb_uio.c b/lib/librte_eal/linuxapp/igb_uio/igb_uio.c
new file mode 100644
index 00000000..72b26923
--- /dev/null
+++ b/lib/librte_eal/linuxapp/igb_uio/igb_uio.c
@@ -0,0 +1,580 @@
+/*-
+ * GPL LICENSE SUMMARY
+ *
+ *   Copyright(c) 2010-2014 Intel Corporation. All rights reserved.
+ *
+ *   This program is free software; you can redistribute it and/or modify
+ *   it under the terms of version 2 of the GNU General Public License as
+ *   published by the Free Software Foundation.
+ *
+ *   This program is distributed in the hope that it will be useful, but
+ *   WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *   General Public License for more details.
+ *
+ *   You should have received a copy of the GNU General Public License
+ *   along with this program; if not, write to the Free Software
+ *   Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ *   The full GNU General Public License is included in this distribution
+ *   in the file called LICENSE.GPL.
+ *
+ *   Contact Information:
+ *   Intel Corporation
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/uio_driver.h>
+#include <linux/io.h>
+#include <linux/msi.h>
+#include <linux/version.h>
+#include <linux/slab.h>
+
+#ifdef CONFIG_XEN_DOM0
+#include <xen/xen.h>
+#endif
+#include <rte_pci_dev_features.h>
+
+#include "compat.h"
+
+/**
+ * A structure describing the private information for a uio device.
+ */
+struct rte_uio_pci_dev {
+	struct uio_info info;
+	struct pci_dev *pdev;
+	enum rte_intr_mode mode;
+};
+
+static char *intr_mode;
+static enum rte_intr_mode igbuio_intr_mode_preferred = RTE_INTR_MODE_MSIX;
+
+/* sriov sysfs */
+static ssize_t
+show_max_vfs(struct device *dev, struct device_attribute *attr,
+	     char *buf)
+{
+	return snprintf(buf, 10, "%u\n", dev_num_vf(dev));
+}
+
+static ssize_t
+store_max_vfs(struct device *dev, struct device_attribute *attr,
+	      const char *buf, size_t count)
+{
+	int err = 0;
+	unsigned long max_vfs;
+	struct pci_dev *pdev = to_pci_dev(dev);
+
+	if (0 != kstrtoul(buf, 0, &max_vfs))
+		return -EINVAL;
+
+	if (0 == max_vfs)
+		pci_disable_sriov(pdev);
+	else if (0 == pci_num_vf(pdev))
+		err = pci_enable_sriov(pdev, max_vfs);
+	else /* do nothing if change max_vfs number */
+		err = -EINVAL;
+
+	return err ? err : count;
+}
+
+#ifdef RTE_PCI_CONFIG
+static ssize_t
+show_extended_tag(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	dev_info(dev, "Deprecated\n");
+
+	return 0;
+}
+
+static ssize_t
+store_extended_tag(struct device *dev,
+		   struct device_attribute *attr,
+		   const char *buf,
+		   size_t count)
+{
+	dev_info(dev, "Deprecated\n");
+
+	return 0;
+}
+
+static ssize_t
+show_max_read_request_size(struct device *dev,
+			   struct device_attribute *attr,
+			   char *buf)
+{
+	dev_info(dev, "Deprecated\n");
+
+	return 0;
+}
+
+static ssize_t
+store_max_read_request_size(struct device *dev,
+			    struct device_attribute *attr,
+			    const char *buf,
+			    size_t count)
+{
+	dev_info(dev, "Deprecated\n");
+
+	return 0;
+}
+#endif
+
+static DEVICE_ATTR(max_vfs, S_IRUGO | S_IWUSR, show_max_vfs, store_max_vfs);
+#ifdef RTE_PCI_CONFIG
+static DEVICE_ATTR(extended_tag, S_IRUGO | S_IWUSR, show_extended_tag,
+	store_extended_tag);
+static DEVICE_ATTR(max_read_request_size, S_IRUGO | S_IWUSR,
+	show_max_read_request_size, store_max_read_request_size);
+#endif
+
+static struct attribute *dev_attrs[] = {
+	&dev_attr_max_vfs.attr,
+#ifdef RTE_PCI_CONFIG
+	&dev_attr_extended_tag.attr,
+	&dev_attr_max_read_request_size.attr,
+#endif
+	NULL,
+};
+
+static const struct attribute_group dev_attr_grp = {
+	.attrs = dev_attrs,
+};
+/*
+ * It masks the msix on/off of generating MSI-X messages.
+ */
+static void
+igbuio_msix_mask_irq(struct msi_desc *desc, int32_t state)
+{
+	u32 mask_bits = desc->masked;
+	unsigned offset = desc->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE +
+						PCI_MSIX_ENTRY_VECTOR_CTRL;
+
+	if (state != 0)
+		mask_bits &= ~PCI_MSIX_ENTRY_CTRL_MASKBIT;
+	else
+		mask_bits |= PCI_MSIX_ENTRY_CTRL_MASKBIT;
+
+	if (mask_bits != desc->masked) {
+		writel(mask_bits, desc->mask_base + offset);
+		readl(desc->mask_base);
+		desc->masked = mask_bits;
+	}
+}
+
+/**
+ * This is the irqcontrol callback to be registered to uio_info.
+ * It can be used to disable/enable interrupt from user space processes.
+ *
+ * @param info
+ *  pointer to uio_info.
+ * @param irq_state
+ *  state value. 1 to enable interrupt, 0 to disable interrupt.
+ *
+ * @return
+ *  - On success, 0.
+ *  - On failure, a negative value.
+ */
+static int
+igbuio_pci_irqcontrol(struct uio_info *info, s32 irq_state)
+{
+	struct rte_uio_pci_dev *udev = info->priv;
+	struct pci_dev *pdev = udev->pdev;
+
+	pci_cfg_access_lock(pdev);
+	if (udev->mode == RTE_INTR_MODE_LEGACY)
+		pci_intx(pdev, !!irq_state);
+
+	else if (udev->mode == RTE_INTR_MODE_MSIX) {
+		struct msi_desc *desc;
+
+#if (LINUX_VERSION_CODE < KERNEL_VERSION(4, 3, 0))
+		list_for_each_entry(desc, &pdev->msi_list, list)
+			igbuio_msix_mask_irq(desc, irq_state);
+#else
+		list_for_each_entry(desc, &pdev->dev.msi_list, list)
+			igbuio_msix_mask_irq(desc, irq_state);
+#endif
+	}
+	pci_cfg_access_unlock(pdev);
+
+	return 0;
+}
+
+/**
+ * This is interrupt handler which will check if the interrupt is for the right device.
+ * If yes, disable it here and will be enable later.
+ */
+static irqreturn_t
+igbuio_pci_irqhandler(int irq, struct uio_info *info)
+{
+	struct rte_uio_pci_dev *udev = info->priv;
+
+	/* Legacy mode need to mask in hardware */
+	if (udev->mode == RTE_INTR_MODE_LEGACY &&
+	    !pci_check_and_mask_intx(udev->pdev))
+		return IRQ_NONE;
+
+	/* Message signal mode, no share IRQ and automasked */
+	return IRQ_HANDLED;
+}
+
+#ifdef CONFIG_XEN_DOM0
+static int
+igbuio_dom0_mmap_phys(struct uio_info *info, struct vm_area_struct *vma)
+{
+	int idx;
+
+	idx = (int)vma->vm_pgoff;
+	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+#ifdef HAVE_PTE_MASK_PAGE_IOMAP
+	vma->vm_page_prot.pgprot |= _PAGE_IOMAP;
+#endif
+
+	return remap_pfn_range(vma,
+			vma->vm_start,
+			info->mem[idx].addr >> PAGE_SHIFT,
+			vma->vm_end - vma->vm_start,
+			vma->vm_page_prot);
+}
+
+/**
+ * This is uio device mmap method which will use igbuio mmap for Xen
+ * Dom0 environment.
+ */
+static int
+igbuio_dom0_pci_mmap(struct uio_info *info, struct vm_area_struct *vma)
+{
+	int idx;
+
+	if (vma->vm_pgoff >= MAX_UIO_MAPS)
+		return -EINVAL;
+
+	if (info->mem[vma->vm_pgoff].size == 0)
+		return -EINVAL;
+
+	idx = (int)vma->vm_pgoff;
+	switch (info->mem[idx].memtype) {
+	case UIO_MEM_PHYS:
+		return igbuio_dom0_mmap_phys(info, vma);
+	case UIO_MEM_LOGICAL:
+	case UIO_MEM_VIRTUAL:
+	default:
+		return -EINVAL;
+	}
+}
+#endif
+
+/* Remap pci resources described by bar #pci_bar in uio resource n. */
+static int
+igbuio_pci_setup_iomem(struct pci_dev *dev, struct uio_info *info,
+		       int n, int pci_bar, const char *name)
+{
+	unsigned long addr, len;
+	void *internal_addr;
+
+	if (n >= ARRAY_SIZE(info->mem))
+		return -EINVAL;
+
+	addr = pci_resource_start(dev, pci_bar);
+	len = pci_resource_len(dev, pci_bar);
+	if (addr == 0 || len == 0)
+		return -1;
+	internal_addr = ioremap(addr, len);
+	if (internal_addr == NULL)
+		return -1;
+	info->mem[n].name = name;
+	info->mem[n].addr = addr;
+	info->mem[n].internal_addr = internal_addr;
+	info->mem[n].size = len;
+	info->mem[n].memtype = UIO_MEM_PHYS;
+	return 0;
+}
+
+/* Get pci port io resources described by bar #pci_bar in uio resource n. */
+static int
+igbuio_pci_setup_ioport(struct pci_dev *dev, struct uio_info *info,
+		int n, int pci_bar, const char *name)
+{
+	unsigned long addr, len;
+
+	if (n >= ARRAY_SIZE(info->port))
+		return -EINVAL;
+
+	addr = pci_resource_start(dev, pci_bar);
+	len = pci_resource_len(dev, pci_bar);
+	if (addr == 0 || len == 0)
+		return -EINVAL;
+
+	info->port[n].name = name;
+	info->port[n].start = addr;
+	info->port[n].size = len;
+	info->port[n].porttype = UIO_PORT_X86;
+
+	return 0;
+}
+
+/* Unmap previously ioremap'd resources */
+static void
+igbuio_pci_release_iomem(struct uio_info *info)
+{
+	int i;
+
+	for (i = 0; i < MAX_UIO_MAPS; i++) {
+		if (info->mem[i].internal_addr)
+			iounmap(info->mem[i].internal_addr);
+	}
+}
+
+static int
+igbuio_setup_bars(struct pci_dev *dev, struct uio_info *info)
+{
+	int i, iom, iop, ret;
+	unsigned long flags;
+	static const char *bar_names[PCI_STD_RESOURCE_END + 1]  = {
+		"BAR0",
+		"BAR1",
+		"BAR2",
+		"BAR3",
+		"BAR4",
+		"BAR5",
+	};
+
+	iom = 0;
+	iop = 0;
+
+	for (i = 0; i < ARRAY_SIZE(bar_names); i++) {
+		if (pci_resource_len(dev, i) != 0 &&
+				pci_resource_start(dev, i) != 0) {
+			flags = pci_resource_flags(dev, i);
+			if (flags & IORESOURCE_MEM) {
+				ret = igbuio_pci_setup_iomem(dev, info, iom,
+							     i, bar_names[i]);
+				if (ret != 0)
+					return ret;
+				iom++;
+			} else if (flags & IORESOURCE_IO) {
+				ret = igbuio_pci_setup_ioport(dev, info, iop,
+							      i, bar_names[i]);
+				if (ret != 0)
+					return ret;
+				iop++;
+			}
+		}
+	}
+
+	return (iom != 0) ? ret : -ENOENT;
+}
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 8, 0)
+static int __devinit
+#else
+static int
+#endif
+igbuio_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
+{
+	struct rte_uio_pci_dev *udev;
+	struct msix_entry msix_entry;
+	int err;
+
+	udev = kzalloc(sizeof(struct rte_uio_pci_dev), GFP_KERNEL);
+	if (!udev)
+		return -ENOMEM;
+
+	/*
+	 * enable device: ask low-level code to enable I/O and
+	 * memory
+	 */
+	err = pci_enable_device(dev);
+	if (err != 0) {
+		dev_err(&dev->dev, "Cannot enable PCI device\n");
+		goto fail_free;
+	}
+
+	/*
+	 * reserve device's PCI memory regions for use by this
+	 * module
+	 */
+	err = pci_request_regions(dev, "igb_uio");
+	if (err != 0) {
+		dev_err(&dev->dev, "Cannot request regions\n");
+		goto fail_disable;
+	}
+
+	/* enable bus mastering on the device */
+	pci_set_master(dev);
+
+	/* remap IO memory */
+	err = igbuio_setup_bars(dev, &udev->info);
+	if (err != 0)
+		goto fail_release_iomem;
+
+	/* set 64-bit DMA mask */
+	err = pci_set_dma_mask(dev,  DMA_BIT_MASK(64));
+	if (err != 0) {
+		dev_err(&dev->dev, "Cannot set DMA mask\n");
+		goto fail_release_iomem;
+	}
+
+	err = pci_set_consistent_dma_mask(dev, DMA_BIT_MASK(64));
+	if (err != 0) {
+		dev_err(&dev->dev, "Cannot set consistent DMA mask\n");
+		goto fail_release_iomem;
+	}
+
+	/* fill uio infos */
+	udev->info.name = "igb_uio";
+	udev->info.version = "0.1";
+	udev->info.handler = igbuio_pci_irqhandler;
+	udev->info.irqcontrol = igbuio_pci_irqcontrol;
+#ifdef CONFIG_XEN_DOM0
+	/* check if the driver run on Xen Dom0 */
+	if (xen_initial_domain())
+		udev->info.mmap = igbuio_dom0_pci_mmap;
+#endif
+	udev->info.priv = udev;
+	udev->pdev = dev;
+
+	switch (igbuio_intr_mode_preferred) {
+	case RTE_INTR_MODE_MSIX:
+		/* Only 1 msi-x vector needed */
+		msix_entry.entry = 0;
+		if (pci_enable_msix(dev, &msix_entry, 1) == 0) {
+			dev_dbg(&dev->dev, "using MSI-X");
+			udev->info.irq = msix_entry.vector;
+			udev->mode = RTE_INTR_MODE_MSIX;
+			break;
+		}
+		/* fall back to INTX */
+	case RTE_INTR_MODE_LEGACY:
+		if (pci_intx_mask_supported(dev)) {
+			dev_dbg(&dev->dev, "using INTX");
+			udev->info.irq_flags = IRQF_SHARED;
+			udev->info.irq = dev->irq;
+			udev->mode = RTE_INTR_MODE_LEGACY;
+			break;
+		}
+		dev_notice(&dev->dev, "PCI INTX mask not supported\n");
+		/* fall back to no IRQ */
+	case RTE_INTR_MODE_NONE:
+		udev->mode = RTE_INTR_MODE_NONE;
+		udev->info.irq = 0;
+		break;
+
+	default:
+		dev_err(&dev->dev, "invalid IRQ mode %u",
+			igbuio_intr_mode_preferred);
+		err = -EINVAL;
+		goto fail_release_iomem;
+	}
+
+	err = sysfs_create_group(&dev->dev.kobj, &dev_attr_grp);
+	if (err != 0)
+		goto fail_release_iomem;
+
+	/* register uio driver */
+	err = uio_register_device(&dev->dev, &udev->info);
+	if (err != 0)
+		goto fail_remove_group;
+
+	pci_set_drvdata(dev, udev);
+
+	dev_info(&dev->dev, "uio device registered with irq %lx\n",
+		 udev->info.irq);
+
+	return 0;
+
+fail_remove_group:
+	sysfs_remove_group(&dev->dev.kobj, &dev_attr_grp);
+fail_release_iomem:
+	igbuio_pci_release_iomem(&udev->info);
+	if (udev->mode == RTE_INTR_MODE_MSIX)
+		pci_disable_msix(udev->pdev);
+	pci_release_regions(dev);
+fail_disable:
+	pci_disable_device(dev);
+fail_free:
+	kfree(udev);
+
+	return err;
+}
+
+static void
+igbuio_pci_remove(struct pci_dev *dev)
+{
+	struct rte_uio_pci_dev *udev = pci_get_drvdata(dev);
+
+	sysfs_remove_group(&dev->dev.kobj, &dev_attr_grp);
+	uio_unregister_device(&udev->info);
+	igbuio_pci_release_iomem(&udev->info);
+	if (udev->mode == RTE_INTR_MODE_MSIX)
+		pci_disable_msix(dev);
+	pci_release_regions(dev);
+	pci_disable_device(dev);
+	pci_set_drvdata(dev, NULL);
+	kfree(udev);
+}
+
+static int
+igbuio_config_intr_mode(char *intr_str)
+{
+	if (!intr_str) {
+		pr_info("Use MSIX interrupt by default\n");
+		return 0;
+	}
+
+	if (!strcmp(intr_str, RTE_INTR_MODE_MSIX_NAME)) {
+		igbuio_intr_mode_preferred = RTE_INTR_MODE_MSIX;
+		pr_info("Use MSIX interrupt\n");
+	} else if (!strcmp(intr_str, RTE_INTR_MODE_LEGACY_NAME)) {
+		igbuio_intr_mode_preferred = RTE_INTR_MODE_LEGACY;
+		pr_info("Use legacy interrupt\n");
+	} else {
+		pr_info("Error: bad parameter - %s\n", intr_str);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static struct pci_driver igbuio_pci_driver = {
+	.name = "igb_uio",
+	.id_table = NULL,
+	.probe = igbuio_pci_probe,
+	.remove = igbuio_pci_remove,
+};
+
+static int __init
+igbuio_pci_init_module(void)
+{
+	int ret;
+
+	ret = igbuio_config_intr_mode(intr_mode);
+	if (ret < 0)
+		return ret;
+
+	return pci_register_driver(&igbuio_pci_driver);
+}
+
+static void __exit
+igbuio_pci_exit_module(void)
+{
+	pci_unregister_driver(&igbuio_pci_driver);
+}
+
+module_init(igbuio_pci_init_module);
+module_exit(igbuio_pci_exit_module);
+
+module_param(intr_mode, charp, S_IRUGO);
+MODULE_PARM_DESC(intr_mode,
+"igb_uio interrupt mode (default=msix):\n"
+"    " RTE_INTR_MODE_MSIX_NAME "       Use MSIX interrupt\n"
+"    " RTE_INTR_MODE_LEGACY_NAME "     Use Legacy interrupt\n"
+"\n");
+
+MODULE_DESCRIPTION("UIO driver for Intel IGB PCI cards");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Intel Corporation");